librarian-bots/model_cards_with_metadata · Datasets at Hugging Face

modelId stringlengths 5 139	author stringlengths 2 42	last_modified timestamp[us, tz=UTC]date 2020-02-15 11:33:14 2025-06-02 12:28:20	downloads int64 0 223M	likes int64 0 11.7k	library_name stringclasses 462 values	tags sequencelengths 1 4.05k	pipeline_tag stringclasses 54 values	createdAt timestamp[us, tz=UTC]date 2022-03-02 23:29:04 2025-06-02 12:26:48	card stringlengths 11 1.01M
trevorj/dqn-SpaceInvadersNoFrameskip-v4	trevorj	2023-07-10T22:41:49Z	0	0	stable-baselines3	[ "stable-baselines3", "SpaceInvadersNoFrameskip-v4", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]	reinforcement-learning	2023-07-10T22:41:13Z	--- library_name: stable-baselines3 tags: - SpaceInvadersNoFrameskip-v4 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: DQN results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: SpaceInvadersNoFrameskip-v4 type: SpaceInvadersNoFrameskip-v4 metrics: - type: mean_reward value: 523.00 +/- 142.73 name: mean_reward verified: false --- # DQN Agent playing SpaceInvadersNoFrameskip-v4 This is a trained model of a DQN agent playing SpaceInvadersNoFrameskip-v4 using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3) and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo). The RL Zoo is a training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included. ## Usage (with SB3 RL Zoo) RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/> SB3: https://github.com/DLR-RM/stable-baselines3<br/> SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib Install the RL Zoo (with SB3 and SB3-Contrib): ```bash pip install rl_zoo3 ``` ``` # Download model and save it into the logs/ folder python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga trevorj -f logs/ python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ ``` If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do: ``` python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga trevorj -f logs/ python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ ``` ## Training (with the RL Zoo) ``` python -m rl_zoo3.train --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ # Upload the model and generate video (when possible) python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga trevorj ``` ## Hyperparameters ```python OrderedDict([('batch_size', 32), ('buffer_size', 100000), ('env_wrapper', ['stable_baselines3.common.atari_wrappers.AtariWrapper']), ('exploration_final_eps', 0.01), ('exploration_fraction', 0.1), ('frame_stack', 4), ('gradient_steps', 1), ('learning_rate', 0.0001), ('learning_starts', 100000), ('n_timesteps', 1000000.0), ('optimize_memory_usage', False), ('policy', 'CnnPolicy'), ('target_update_interval', 1000), ('train_freq', 4), ('normalize', False)]) ``` # Environment Arguments ```python {'render_mode': 'rgb_array'} ```
jordyvl/vit-small_tobacco3482_kd_CEKD_t5.0_a0.9	jordyvl	2023-07-10T22:40:13Z	161	0	transformers	[ "transformers", "pytorch", "vit", "image-classification", "generated_from_trainer", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	image-classification	2023-07-10T22:00:19Z	--- license: apache-2.0 tags: - generated_from_trainer metrics: - accuracy model-index: - name: vit-small_tobacco3482_kd_CEKD_t5.0_a0.9 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # vit-small_tobacco3482_kd_CEKD_t5.0_a0.9 This model is a fine-tuned version of [WinKawaks/vit-small-patch16-224](https://huggingface.co/WinKawaks/vit-small-patch16-224) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.5373 - Accuracy: 0.85 - Brier Loss: 0.2432 - Nll: 1.1157 - F1 Micro: 0.85 - F1 Macro: 0.8450 - Ece: 0.1621 - Aurc: 0.0427 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 100 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| Brier Loss \| Nll \| F1 Micro \| F1 Macro \| Ece \| Aurc \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\|:----------:\|:------:\|:--------:\|:--------:\|:------:\|:------:\| \| No log \| 1.0 \| 7 \| 2.1036 \| 0.215 \| 0.8753 \| 5.3195 \| 0.2150 \| 0.1264 \| 0.2571 \| 0.6923 \| \| No log \| 2.0 \| 14 \| 1.6952 \| 0.405 \| 0.7407 \| 3.4929 \| 0.405 \| 0.2416 \| 0.2907 \| 0.4040 \| \| No log \| 3.0 \| 21 \| 1.1843 \| 0.62 \| 0.5633 \| 2.0113 \| 0.62 \| 0.5725 \| 0.2740 \| 0.2014 \| \| No log \| 4.0 \| 28 \| 0.8797 \| 0.71 \| 0.4080 \| 1.7043 \| 0.7100 \| 0.6683 \| 0.2024 \| 0.1125 \| \| No log \| 5.0 \| 35 \| 0.8570 \| 0.715 \| 0.3837 \| 1.6476 \| 0.715 \| 0.7280 \| 0.2189 \| 0.1079 \| \| No log \| 6.0 \| 42 \| 0.7484 \| 0.775 \| 0.3285 \| 1.5962 \| 0.775 \| 0.7668 \| 0.1873 \| 0.0816 \| \| No log \| 7.0 \| 49 \| 0.7337 \| 0.79 \| 0.3131 \| 1.5377 \| 0.79 \| 0.7779 \| 0.1904 \| 0.0771 \| \| No log \| 8.0 \| 56 \| 0.6709 \| 0.795 \| 0.3012 \| 1.2156 \| 0.795 \| 0.7776 \| 0.1939 \| 0.0761 \| \| No log \| 9.0 \| 63 \| 0.6901 \| 0.795 \| 0.3069 \| 1.4725 \| 0.795 \| 0.7916 \| 0.1882 \| 0.0769 \| \| No log \| 10.0 \| 70 \| 0.7960 \| 0.75 \| 0.3586 \| 1.4426 \| 0.75 \| 0.7406 \| 0.1868 \| 0.0976 \| \| No log \| 11.0 \| 77 \| 0.7489 \| 0.77 \| 0.3296 \| 1.6202 \| 0.7700 \| 0.7794 \| 0.2020 \| 0.0878 \| \| No log \| 12.0 \| 84 \| 0.7068 \| 0.785 \| 0.3270 \| 1.4127 \| 0.785 \| 0.7812 \| 0.1922 \| 0.0759 \| \| No log \| 13.0 \| 91 \| 0.6687 \| 0.79 \| 0.3050 \| 1.3820 \| 0.79 \| 0.7945 \| 0.1818 \| 0.0625 \| \| No log \| 14.0 \| 98 \| 0.6052 \| 0.79 \| 0.2854 \| 1.0602 \| 0.79 \| 0.7716 \| 0.1702 \| 0.0590 \| \| No log \| 15.0 \| 105 \| 0.6369 \| 0.795 \| 0.2959 \| 1.0580 \| 0.795 \| 0.7953 \| 0.1709 \| 0.0603 \| \| No log \| 16.0 \| 112 \| 0.6204 \| 0.81 \| 0.2816 \| 1.1886 \| 0.81 \| 0.8050 \| 0.1657 \| 0.0702 \| \| No log \| 17.0 \| 119 \| 0.5648 \| 0.83 \| 0.2475 \| 1.2506 \| 0.83 \| 0.8241 \| 0.1347 \| 0.0612 \| \| No log \| 18.0 \| 126 \| 0.5849 \| 0.83 \| 0.2672 \| 1.2245 \| 0.83 \| 0.8155 \| 0.1646 \| 0.0601 \| \| No log \| 19.0 \| 133 \| 0.5536 \| 0.835 \| 0.2475 \| 1.0514 \| 0.835 \| 0.8254 \| 0.1683 \| 0.0531 \| \| No log \| 20.0 \| 140 \| 0.5689 \| 0.835 \| 0.2513 \| 1.2369 \| 0.835 \| 0.8437 \| 0.1722 \| 0.0489 \| \| No log \| 21.0 \| 147 \| 0.5540 \| 0.83 \| 0.2485 \| 1.2139 \| 0.83 \| 0.8165 \| 0.1641 \| 0.0608 \| \| No log \| 22.0 \| 154 \| 0.5352 \| 0.835 \| 0.2402 \| 1.0108 \| 0.835 \| 0.8295 \| 0.1408 \| 0.0430 \| \| No log \| 23.0 \| 161 \| 0.5380 \| 0.84 \| 0.2403 \| 1.2280 \| 0.8400 \| 0.8347 \| 0.1405 \| 0.0436 \| \| No log \| 24.0 \| 168 \| 0.5422 \| 0.835 \| 0.2471 \| 1.0204 \| 0.835 \| 0.8324 \| 0.1606 \| 0.0445 \| \| No log \| 25.0 \| 175 \| 0.5342 \| 0.85 \| 0.2404 \| 1.0767 \| 0.85 \| 0.8487 \| 0.1469 \| 0.0432 \| \| No log \| 26.0 \| 182 \| 0.5374 \| 0.84 \| 0.2429 \| 1.0774 \| 0.8400 \| 0.8334 \| 0.1420 \| 0.0462 \| \| No log \| 27.0 \| 189 \| 0.5311 \| 0.85 \| 0.2395 \| 1.0748 \| 0.85 \| 0.8487 \| 0.1439 \| 0.0446 \| \| No log \| 28.0 \| 196 \| 0.5298 \| 0.85 \| 0.2384 \| 1.1337 \| 0.85 \| 0.8487 \| 0.1570 \| 0.0437 \| \| No log \| 29.0 \| 203 \| 0.5387 \| 0.845 \| 0.2435 \| 1.1319 \| 0.845 \| 0.8424 \| 0.1539 \| 0.0458 \| \| No log \| 30.0 \| 210 \| 0.5361 \| 0.85 \| 0.2430 \| 1.0648 \| 0.85 \| 0.8450 \| 0.1679 \| 0.0431 \| \| No log \| 31.0 \| 217 \| 0.5339 \| 0.85 \| 0.2413 \| 1.0676 \| 0.85 \| 0.8487 \| 0.1646 \| 0.0428 \| \| No log \| 32.0 \| 224 \| 0.5345 \| 0.85 \| 0.2421 \| 1.0709 \| 0.85 \| 0.8487 \| 0.1476 \| 0.0440 \| \| No log \| 33.0 \| 231 \| 0.5343 \| 0.85 \| 0.2421 \| 1.1236 \| 0.85 \| 0.8450 \| 0.1621 \| 0.0431 \| \| No log \| 34.0 \| 238 \| 0.5353 \| 0.845 \| 0.2426 \| 1.1244 \| 0.845 \| 0.8424 \| 0.1710 \| 0.0428 \| \| No log \| 35.0 \| 245 \| 0.5346 \| 0.85 \| 0.2423 \| 1.0649 \| 0.85 \| 0.8487 \| 0.1520 \| 0.0440 \| \| No log \| 36.0 \| 252 \| 0.5356 \| 0.855 \| 0.2422 \| 1.1241 \| 0.855 \| 0.8517 \| 0.1814 \| 0.0429 \| \| No log \| 37.0 \| 259 \| 0.5357 \| 0.85 \| 0.2426 \| 1.1237 \| 0.85 \| 0.8450 \| 0.1670 \| 0.0425 \| \| No log \| 38.0 \| 266 \| 0.5356 \| 0.845 \| 0.2426 \| 1.1226 \| 0.845 \| 0.8419 \| 0.1607 \| 0.0435 \| \| No log \| 39.0 \| 273 \| 0.5347 \| 0.855 \| 0.2420 \| 1.0739 \| 0.855 \| 0.8517 \| 0.1597 \| 0.0427 \| \| No log \| 40.0 \| 280 \| 0.5356 \| 0.855 \| 0.2423 \| 1.1203 \| 0.855 \| 0.8517 \| 0.1676 \| 0.0435 \| \| No log \| 41.0 \| 287 \| 0.5365 \| 0.85 \| 0.2431 \| 1.1199 \| 0.85 \| 0.8450 \| 0.1780 \| 0.0429 \| \| No log \| 42.0 \| 294 \| 0.5356 \| 0.85 \| 0.2426 \| 1.1173 \| 0.85 \| 0.8450 \| 0.1653 \| 0.0430 \| \| No log \| 43.0 \| 301 \| 0.5363 \| 0.85 \| 0.2428 \| 1.1189 \| 0.85 \| 0.8450 \| 0.1550 \| 0.0435 \| \| No log \| 44.0 \| 308 \| 0.5345 \| 0.85 \| 0.2418 \| 1.1193 \| 0.85 \| 0.8450 \| 0.1590 \| 0.0428 \| \| No log \| 45.0 \| 315 \| 0.5374 \| 0.85 \| 0.2435 \| 1.1202 \| 0.85 \| 0.8450 \| 0.1633 \| 0.0435 \| \| No log \| 46.0 \| 322 \| 0.5355 \| 0.85 \| 0.2423 \| 1.1183 \| 0.85 \| 0.8450 \| 0.1564 \| 0.0428 \| \| No log \| 47.0 \| 329 \| 0.5354 \| 0.85 \| 0.2425 \| 1.1176 \| 0.85 \| 0.8450 \| 0.1509 \| 0.0429 \| \| No log \| 48.0 \| 336 \| 0.5369 \| 0.85 \| 0.2433 \| 1.1177 \| 0.85 \| 0.8450 \| 0.1517 \| 0.0432 \| \| No log \| 49.0 \| 343 \| 0.5361 \| 0.85 \| 0.2428 \| 1.1182 \| 0.85 \| 0.8450 \| 0.1490 \| 0.0428 \| \| No log \| 50.0 \| 350 \| 0.5364 \| 0.85 \| 0.2431 \| 1.1179 \| 0.85 \| 0.8450 \| 0.1654 \| 0.0430 \| \| No log \| 51.0 \| 357 \| 0.5365 \| 0.85 \| 0.2428 \| 1.1185 \| 0.85 \| 0.8450 \| 0.1729 \| 0.0432 \| \| No log \| 52.0 \| 364 \| 0.5364 \| 0.85 \| 0.2430 \| 1.1165 \| 0.85 \| 0.8450 \| 0.1614 \| 0.0429 \| \| No log \| 53.0 \| 371 \| 0.5362 \| 0.85 \| 0.2429 \| 1.1167 \| 0.85 \| 0.8450 \| 0.1694 \| 0.0430 \| \| No log \| 54.0 \| 378 \| 0.5369 \| 0.85 \| 0.2432 \| 1.1170 \| 0.85 \| 0.8450 \| 0.1597 \| 0.0432 \| \| No log \| 55.0 \| 385 \| 0.5368 \| 0.85 \| 0.2430 \| 1.1168 \| 0.85 \| 0.8450 \| 0.1670 \| 0.0429 \| \| No log \| 56.0 \| 392 \| 0.5367 \| 0.85 \| 0.2430 \| 1.1180 \| 0.85 \| 0.8450 \| 0.1619 \| 0.0430 \| \| No log \| 57.0 \| 399 \| 0.5364 \| 0.85 \| 0.2429 \| 1.1163 \| 0.85 \| 0.8450 \| 0.1649 \| 0.0429 \| \| No log \| 58.0 \| 406 \| 0.5364 \| 0.85 \| 0.2430 \| 1.1156 \| 0.85 \| 0.8450 \| 0.1611 \| 0.0429 \| \| No log \| 59.0 \| 413 \| 0.5365 \| 0.85 \| 0.2428 \| 1.1163 \| 0.85 \| 0.8450 \| 0.1591 \| 0.0429 \| \| No log \| 60.0 \| 420 \| 0.5364 \| 0.85 \| 0.2429 \| 1.1155 \| 0.85 \| 0.8450 \| 0.1588 \| 0.0429 \| \| No log \| 61.0 \| 427 \| 0.5370 \| 0.85 \| 0.2432 \| 1.1158 \| 0.85 \| 0.8450 \| 0.1772 \| 0.0432 \| \| No log \| 62.0 \| 434 \| 0.5367 \| 0.85 \| 0.2429 \| 1.1167 \| 0.85 \| 0.8450 \| 0.1622 \| 0.0429 \| \| No log \| 63.0 \| 441 \| 0.5362 \| 0.85 \| 0.2428 \| 1.1162 \| 0.85 \| 0.8450 \| 0.1503 \| 0.0428 \| \| No log \| 64.0 \| 448 \| 0.5372 \| 0.85 \| 0.2433 \| 1.1161 \| 0.85 \| 0.8450 \| 0.1616 \| 0.0432 \| \| No log \| 65.0 \| 455 \| 0.5371 \| 0.85 \| 0.2431 \| 1.1162 \| 0.85 \| 0.8450 \| 0.1499 \| 0.0429 \| \| No log \| 66.0 \| 462 \| 0.5367 \| 0.85 \| 0.2430 \| 1.1160 \| 0.85 \| 0.8450 \| 0.1591 \| 0.0427 \| \| No log \| 67.0 \| 469 \| 0.5367 \| 0.85 \| 0.2430 \| 1.1164 \| 0.85 \| 0.8450 \| 0.1562 \| 0.0428 \| \| No log \| 68.0 \| 476 \| 0.5368 \| 0.85 \| 0.2430 \| 1.1168 \| 0.85 \| 0.8450 \| 0.1556 \| 0.0427 \| \| No log \| 69.0 \| 483 \| 0.5368 \| 0.85 \| 0.2431 \| 1.1158 \| 0.85 \| 0.8450 \| 0.1593 \| 0.0428 \| \| No log \| 70.0 \| 490 \| 0.5372 \| 0.85 \| 0.2432 \| 1.1162 \| 0.85 \| 0.8450 \| 0.1628 \| 0.0428 \| \| No log \| 71.0 \| 497 \| 0.5371 \| 0.85 \| 0.2432 \| 1.1163 \| 0.85 \| 0.8450 \| 0.1599 \| 0.0429 \| \| 0.1708 \| 72.0 \| 504 \| 0.5370 \| 0.85 \| 0.2430 \| 1.1161 \| 0.85 \| 0.8450 \| 0.1559 \| 0.0430 \| \| 0.1708 \| 73.0 \| 511 \| 0.5372 \| 0.85 \| 0.2433 \| 1.1154 \| 0.85 \| 0.8450 \| 0.1556 \| 0.0428 \| \| 0.1708 \| 74.0 \| 518 \| 0.5370 \| 0.85 \| 0.2429 \| 1.1165 \| 0.85 \| 0.8450 \| 0.1540 \| 0.0428 \| \| 0.1708 \| 75.0 \| 525 \| 0.5371 \| 0.85 \| 0.2431 \| 1.1161 \| 0.85 \| 0.8450 \| 0.1616 \| 0.0427 \| \| 0.1708 \| 76.0 \| 532 \| 0.5369 \| 0.85 \| 0.2431 \| 1.1161 \| 0.85 \| 0.8450 \| 0.1619 \| 0.0427 \| \| 0.1708 \| 77.0 \| 539 \| 0.5369 \| 0.85 \| 0.2430 \| 1.1156 \| 0.85 \| 0.8450 \| 0.1623 \| 0.0429 \| \| 0.1708 \| 78.0 \| 546 \| 0.5372 \| 0.85 \| 0.2432 \| 1.1158 \| 0.85 \| 0.8450 \| 0.1619 \| 0.0427 \| \| 0.1708 \| 79.0 \| 553 \| 0.5375 \| 0.85 \| 0.2433 \| 1.1162 \| 0.85 \| 0.8450 \| 0.1688 \| 0.0429 \| \| 0.1708 \| 80.0 \| 560 \| 0.5372 \| 0.85 \| 0.2432 \| 1.1160 \| 0.85 \| 0.8450 \| 0.1623 \| 0.0429 \| \| 0.1708 \| 81.0 \| 567 \| 0.5373 \| 0.85 \| 0.2432 \| 1.1162 \| 0.85 \| 0.8450 \| 0.1620 \| 0.0428 \| \| 0.1708 \| 82.0 \| 574 \| 0.5374 \| 0.85 \| 0.2433 \| 1.1160 \| 0.85 \| 0.8450 \| 0.1622 \| 0.0428 \| \| 0.1708 \| 83.0 \| 581 \| 0.5372 \| 0.85 \| 0.2432 \| 1.1159 \| 0.85 \| 0.8450 \| 0.1622 \| 0.0428 \| \| 0.1708 \| 84.0 \| 588 \| 0.5371 \| 0.85 \| 0.2431 \| 1.1157 \| 0.85 \| 0.8450 \| 0.1621 \| 0.0427 \| \| 0.1708 \| 85.0 \| 595 \| 0.5372 \| 0.85 \| 0.2432 \| 1.1158 \| 0.85 \| 0.8450 \| 0.1687 \| 0.0426 \| \| 0.1708 \| 86.0 \| 602 \| 0.5372 \| 0.85 \| 0.2432 \| 1.1157 \| 0.85 \| 0.8450 \| 0.1619 \| 0.0426 \| \| 0.1708 \| 87.0 \| 609 \| 0.5374 \| 0.85 \| 0.2432 \| 1.1159 \| 0.85 \| 0.8450 \| 0.1687 \| 0.0428 \| \| 0.1708 \| 88.0 \| 616 \| 0.5373 \| 0.85 \| 0.2432 \| 1.1160 \| 0.85 \| 0.8450 \| 0.1620 \| 0.0427 \| \| 0.1708 \| 89.0 \| 623 \| 0.5373 \| 0.85 \| 0.2432 \| 1.1157 \| 0.85 \| 0.8450 \| 0.1620 \| 0.0427 \| \| 0.1708 \| 90.0 \| 630 \| 0.5373 \| 0.85 \| 0.2432 \| 1.1156 \| 0.85 \| 0.8450 \| 0.1620 \| 0.0427 \| \| 0.1708 \| 91.0 \| 637 \| 0.5372 \| 0.85 \| 0.2432 \| 1.1156 \| 0.85 \| 0.8450 \| 0.1620 \| 0.0427 \| \| 0.1708 \| 92.0 \| 644 \| 0.5373 \| 0.85 \| 0.2432 \| 1.1157 \| 0.85 \| 0.8450 \| 0.1620 \| 0.0427 \| \| 0.1708 \| 93.0 \| 651 \| 0.5372 \| 0.85 \| 0.2432 \| 1.1156 \| 0.85 \| 0.8450 \| 0.1620 \| 0.0427 \| \| 0.1708 \| 94.0 \| 658 \| 0.5373 \| 0.85 \| 0.2432 \| 1.1158 \| 0.85 \| 0.8450 \| 0.1620 \| 0.0427 \| \| 0.1708 \| 95.0 \| 665 \| 0.5373 \| 0.85 \| 0.2432 \| 1.1157 \| 0.85 \| 0.8450 \| 0.1621 \| 0.0427 \| \| 0.1708 \| 96.0 \| 672 \| 0.5372 \| 0.85 \| 0.2432 \| 1.1157 \| 0.85 \| 0.8450 \| 0.1621 \| 0.0427 \| \| 0.1708 \| 97.0 \| 679 \| 0.5372 \| 0.85 \| 0.2432 \| 1.1157 \| 0.85 \| 0.8450 \| 0.1620 \| 0.0427 \| \| 0.1708 \| 98.0 \| 686 \| 0.5373 \| 0.85 \| 0.2432 \| 1.1157 \| 0.85 \| 0.8450 \| 0.1621 \| 0.0427 \| \| 0.1708 \| 99.0 \| 693 \| 0.5373 \| 0.85 \| 0.2432 \| 1.1157 \| 0.85 \| 0.8450 \| 0.1621 \| 0.0427 \| \| 0.1708 \| 100.0 \| 700 \| 0.5373 \| 0.85 \| 0.2432 \| 1.1157 \| 0.85 \| 0.8450 \| 0.1621 \| 0.0427 \| ### Framework versions - Transformers 4.26.1 - Pytorch 1.13.1.post200 - Datasets 2.9.0 - Tokenizers 0.13.2
digiplay/BlankCanvas_v1	digiplay	2023-07-10T22:36:13Z	323	2	diffusers	[ "diffusers", "safetensors", "stable-diffusion", "stable-diffusion-diffusers", "text-to-image", "license:other", "autotrain_compatible", "endpoints_compatible", "diffusers:StableDiffusionPipeline", "region:us" ]	text-to-image	2023-07-10T09:59:13Z	--- license: other tags: - stable-diffusion - stable-diffusion-diffusers - text-to-image - diffusers inference: true --- Model info: https://civitai.com/models/106523/blank-canvas Original Author's DEMO images : ![](https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/3be6f78d-49ea-4ad2-a78c-1aeea19c8dcc/width=1200/FotoJet.jpeg)
Raizel123/Mbyonglora	Raizel123	2023-07-10T22:31:20Z	0	0	null	[ "license:creativeml-openrail-m", "region:us" ]	null	2023-07-10T22:27:47Z	--- license: creativeml-openrail-m ---
jordyvl/vit-small_rvl_cdip_100_examples_per_class_kd_MSE	jordyvl	2023-07-10T22:30:03Z	163	0	transformers	[ "transformers", "pytorch", "tensorboard", "vit", "image-classification", "generated_from_trainer", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	image-classification	2023-07-10T21:13:38Z	--- license: apache-2.0 tags: - generated_from_trainer metrics: - accuracy model-index: - name: vit-small_rvl_cdip_100_examples_per_class_kd_MSE results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # vit-small_rvl_cdip_100_examples_per_class_kd_MSE This model is a fine-tuned version of [WinKawaks/vit-small-patch16-224](https://huggingface.co/WinKawaks/vit-small-patch16-224) on the None dataset. It achieves the following results on the evaluation set: - Loss: 1.4673 - Accuracy: 0.6425 - Brier Loss: 0.4763 - Nll: 3.0680 - F1 Micro: 0.6425 - F1 Macro: 0.6485 - Ece: 0.1946 - Aurc: 0.1381 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 32 - eval_batch_size: 32 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 100 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| Brier Loss \| Nll \| F1 Micro \| F1 Macro \| Ece \| Aurc \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\|:----------:\|:-------:\|:--------:\|:--------:\|:------:\|:------:\| \| No log \| 1.0 \| 25 \| 4.4851 \| 0.06 \| 0.9565 \| 13.8276 \| 0.06 \| 0.0556 \| 0.1688 \| 0.9385 \| \| No log \| 2.0 \| 50 \| 3.5619 \| 0.3775 \| 0.7827 \| 6.2649 \| 0.3775 \| 0.3611 \| 0.2331 \| 0.3882 \| \| No log \| 3.0 \| 75 \| 2.8990 \| 0.5025 \| 0.6453 \| 4.7376 \| 0.5025 \| 0.4858 \| 0.1689 \| 0.2658 \| \| No log \| 4.0 \| 100 \| 2.5972 \| 0.515 \| 0.5980 \| 4.4210 \| 0.515 \| 0.4895 \| 0.1605 \| 0.2249 \| \| No log \| 5.0 \| 125 \| 2.4353 \| 0.56 \| 0.5762 \| 3.4885 \| 0.56 \| 0.5566 \| 0.1548 \| 0.2100 \| \| No log \| 6.0 \| 150 \| 2.4157 \| 0.5475 \| 0.5864 \| 3.8261 \| 0.5475 \| 0.5323 \| 0.1837 \| 0.2167 \| \| No log \| 7.0 \| 175 \| 2.1786 \| 0.6075 \| 0.5203 \| 3.4565 \| 0.6075 \| 0.6103 \| 0.1403 \| 0.1670 \| \| No log \| 8.0 \| 200 \| 2.1082 \| 0.63 \| 0.5040 \| 3.3570 \| 0.63 \| 0.6246 \| 0.1580 \| 0.1530 \| \| No log \| 9.0 \| 225 \| 2.0472 \| 0.625 \| 0.5042 \| 3.8572 \| 0.625 \| 0.6184 \| 0.1552 \| 0.1530 \| \| No log \| 10.0 \| 250 \| 2.0589 \| 0.6025 \| 0.5468 \| 3.5723 \| 0.6025 \| 0.5982 \| 0.1781 \| 0.1785 \| \| No log \| 11.0 \| 275 \| 1.8965 \| 0.65 \| 0.4755 \| 3.4466 \| 0.65 \| 0.6497 \| 0.1605 \| 0.1475 \| \| No log \| 12.0 \| 300 \| 1.9014 \| 0.6325 \| 0.5066 \| 3.0881 \| 0.6325 \| 0.6359 \| 0.1658 \| 0.1591 \| \| No log \| 13.0 \| 325 \| 1.7904 \| 0.6175 \| 0.5162 \| 3.4673 \| 0.6175 \| 0.6141 \| 0.1525 \| 0.1598 \| \| No log \| 14.0 \| 350 \| 1.8624 \| 0.625 \| 0.5173 \| 3.6824 \| 0.625 \| 0.6179 \| 0.1567 \| 0.1624 \| \| No log \| 15.0 \| 375 \| 1.7083 \| 0.6625 \| 0.4817 \| 3.1296 \| 0.6625 \| 0.6686 \| 0.1651 \| 0.1405 \| \| No log \| 16.0 \| 400 \| 1.8848 \| 0.59 \| 0.5478 \| 4.3761 \| 0.59 \| 0.5913 \| 0.2083 \| 0.1696 \| \| No log \| 17.0 \| 425 \| 1.7238 \| 0.6125 \| 0.5229 \| 3.1232 \| 0.6125 \| 0.6052 \| 0.1833 \| 0.1553 \| \| No log \| 18.0 \| 450 \| 1.7126 \| 0.625 \| 0.5152 \| 2.9267 \| 0.625 \| 0.6284 \| 0.1747 \| 0.1565 \| \| No log \| 19.0 \| 475 \| 1.6459 \| 0.6275 \| 0.5024 \| 2.9078 \| 0.6275 \| 0.6219 \| 0.1766 \| 0.1527 \| \| 1.0542 \| 20.0 \| 500 \| 1.6029 \| 0.6275 \| 0.4855 \| 3.0931 \| 0.6275 \| 0.6316 \| 0.1720 \| 0.1414 \| \| 1.0542 \| 21.0 \| 525 \| 1.6566 \| 0.6525 \| 0.4847 \| 3.0998 \| 0.6525 \| 0.6479 \| 0.1558 \| 0.1438 \| \| 1.0542 \| 22.0 \| 550 \| 1.6169 \| 0.645 \| 0.4894 \| 3.0081 \| 0.645 \| 0.6471 \| 0.1687 \| 0.1400 \| \| 1.0542 \| 23.0 \| 575 \| 1.5322 \| 0.6525 \| 0.4557 \| 3.3587 \| 0.6525 \| 0.6520 \| 0.1428 \| 0.1247 \| \| 1.0542 \| 24.0 \| 600 \| 1.5991 \| 0.6475 \| 0.4787 \| 2.9349 \| 0.6475 \| 0.6444 \| 0.1580 \| 0.1450 \| \| 1.0542 \| 25.0 \| 625 \| 1.5625 \| 0.6375 \| 0.4926 \| 3.0245 \| 0.6375 \| 0.6378 \| 0.1641 \| 0.1433 \| \| 1.0542 \| 26.0 \| 650 \| 1.5366 \| 0.64 \| 0.4884 \| 3.3388 \| 0.64 \| 0.6461 \| 0.1595 \| 0.1453 \| \| 1.0542 \| 27.0 \| 675 \| 1.5686 \| 0.65 \| 0.4765 \| 3.5120 \| 0.65 \| 0.6504 \| 0.1625 \| 0.1359 \| \| 1.0542 \| 28.0 \| 700 \| 1.5562 \| 0.6475 \| 0.4817 \| 3.0348 \| 0.6475 \| 0.6488 \| 0.1459 \| 0.1388 \| \| 1.0542 \| 29.0 \| 725 \| 1.5213 \| 0.6475 \| 0.4719 \| 3.2628 \| 0.6475 \| 0.6475 \| 0.1634 \| 0.1326 \| \| 1.0542 \| 30.0 \| 750 \| 1.5492 \| 0.6675 \| 0.4730 \| 3.1693 \| 0.6675 \| 0.6679 \| 0.1469 \| 0.1415 \| \| 1.0542 \| 31.0 \| 775 \| 1.5311 \| 0.65 \| 0.4896 \| 3.0881 \| 0.65 \| 0.6504 \| 0.1815 \| 0.1380 \| \| 1.0542 \| 32.0 \| 800 \| 1.5556 \| 0.6475 \| 0.4821 \| 3.1829 \| 0.6475 \| 0.6491 \| 0.1640 \| 0.1405 \| \| 1.0542 \| 33.0 \| 825 \| 1.5471 \| 0.6375 \| 0.4846 \| 3.4190 \| 0.6375 \| 0.6407 \| 0.1628 \| 0.1415 \| \| 1.0542 \| 34.0 \| 850 \| 1.4809 \| 0.6575 \| 0.4714 \| 2.9136 \| 0.6575 \| 0.6612 \| 0.1729 \| 0.1338 \| \| 1.0542 \| 35.0 \| 875 \| 1.5256 \| 0.66 \| 0.4773 \| 3.2303 \| 0.66 \| 0.6650 \| 0.1746 \| 0.1368 \| \| 1.0542 \| 36.0 \| 900 \| 1.4929 \| 0.6675 \| 0.4671 \| 3.2360 \| 0.6675 \| 0.6698 \| 0.1698 \| 0.1309 \| \| 1.0542 \| 37.0 \| 925 \| 1.4923 \| 0.645 \| 0.4880 \| 3.0567 \| 0.645 \| 0.6564 \| 0.1764 \| 0.1395 \| \| 1.0542 \| 38.0 \| 950 \| 1.5038 \| 0.665 \| 0.4672 \| 3.2116 \| 0.665 \| 0.6661 \| 0.1588 \| 0.1343 \| \| 1.0542 \| 39.0 \| 975 \| 1.4708 \| 0.6625 \| 0.4669 \| 3.1420 \| 0.6625 \| 0.6675 \| 0.1683 \| 0.1301 \| \| 0.0522 \| 40.0 \| 1000 \| 1.5153 \| 0.6475 \| 0.4865 \| 3.1796 \| 0.6475 \| 0.6447 \| 0.1639 \| 0.1400 \| \| 0.0522 \| 41.0 \| 1025 \| 1.4705 \| 0.6575 \| 0.4642 \| 3.2196 \| 0.6575 \| 0.6626 \| 0.1440 \| 0.1308 \| \| 0.0522 \| 42.0 \| 1050 \| 1.4844 \| 0.6575 \| 0.4722 \| 3.2445 \| 0.6575 \| 0.6595 \| 0.1746 \| 0.1328 \| \| 0.0522 \| 43.0 \| 1075 \| 1.4957 \| 0.6425 \| 0.4828 \| 3.1456 \| 0.6425 \| 0.6468 \| 0.1499 \| 0.1417 \| \| 0.0522 \| 44.0 \| 1100 \| 1.5179 \| 0.645 \| 0.4910 \| 3.3921 \| 0.645 \| 0.6470 \| 0.1861 \| 0.1433 \| \| 0.0522 \| 45.0 \| 1125 \| 1.4878 \| 0.6425 \| 0.4839 \| 3.2139 \| 0.6425 \| 0.6478 \| 0.1720 \| 0.1403 \| \| 0.0522 \| 46.0 \| 1150 \| 1.4666 \| 0.655 \| 0.4741 \| 2.9333 \| 0.655 \| 0.6601 \| 0.1813 \| 0.1347 \| \| 0.0522 \| 47.0 \| 1175 \| 1.4954 \| 0.6575 \| 0.4776 \| 3.2102 \| 0.6575 \| 0.6604 \| 0.1842 \| 0.1390 \| \| 0.0522 \| 48.0 \| 1200 \| 1.4976 \| 0.645 \| 0.4856 \| 3.1539 \| 0.645 \| 0.6493 \| 0.1549 \| 0.1407 \| \| 0.0522 \| 49.0 \| 1225 \| 1.4772 \| 0.64 \| 0.4780 \| 2.9845 \| 0.64 \| 0.6445 \| 0.1826 \| 0.1388 \| \| 0.0522 \| 50.0 \| 1250 \| 1.4584 \| 0.65 \| 0.4703 \| 3.0776 \| 0.65 \| 0.6533 \| 0.1685 \| 0.1352 \| \| 0.0522 \| 51.0 \| 1275 \| 1.4828 \| 0.6325 \| 0.4844 \| 3.1425 \| 0.6325 \| 0.6377 \| 0.1641 \| 0.1409 \| \| 0.0522 \| 52.0 \| 1300 \| 1.4676 \| 0.6525 \| 0.4737 \| 3.1483 \| 0.6525 \| 0.6565 \| 0.1773 \| 0.1358 \| \| 0.0522 \| 53.0 \| 1325 \| 1.4675 \| 0.6475 \| 0.4791 \| 3.1411 \| 0.6475 \| 0.6515 \| 0.1820 \| 0.1388 \| \| 0.0522 \| 54.0 \| 1350 \| 1.4724 \| 0.645 \| 0.4764 \| 3.0744 \| 0.645 \| 0.6499 \| 0.1847 \| 0.1382 \| \| 0.0522 \| 55.0 \| 1375 \| 1.4689 \| 0.6425 \| 0.4769 \| 3.2256 \| 0.6425 \| 0.6476 \| 0.1839 \| 0.1376 \| \| 0.0522 \| 56.0 \| 1400 \| 1.4660 \| 0.6425 \| 0.4760 \| 2.9907 \| 0.6425 \| 0.6479 \| 0.1906 \| 0.1378 \| \| 0.0522 \| 57.0 \| 1425 \| 1.4663 \| 0.645 \| 0.4757 \| 3.0722 \| 0.645 \| 0.6514 \| 0.1705 \| 0.1367 \| \| 0.0522 \| 58.0 \| 1450 \| 1.4678 \| 0.65 \| 0.4770 \| 3.0710 \| 0.65 \| 0.6546 \| 0.1794 \| 0.1371 \| \| 0.0522 \| 59.0 \| 1475 \| 1.4717 \| 0.64 \| 0.4786 \| 3.0737 \| 0.64 \| 0.6455 \| 0.1889 \| 0.1392 \| \| 0.0064 \| 60.0 \| 1500 \| 1.4691 \| 0.645 \| 0.4768 \| 3.0688 \| 0.645 \| 0.6499 \| 0.1815 \| 0.1378 \| \| 0.0064 \| 61.0 \| 1525 \| 1.4689 \| 0.64 \| 0.4767 \| 3.0688 \| 0.64 \| 0.6452 \| 0.1846 \| 0.1382 \| \| 0.0064 \| 62.0 \| 1550 \| 1.4689 \| 0.64 \| 0.4770 \| 3.0674 \| 0.64 \| 0.6455 \| 0.1937 \| 0.1383 \| \| 0.0064 \| 63.0 \| 1575 \| 1.4687 \| 0.6425 \| 0.4767 \| 3.0700 \| 0.6425 \| 0.6485 \| 0.1897 \| 0.1381 \| \| 0.0064 \| 64.0 \| 1600 \| 1.4674 \| 0.6425 \| 0.4764 \| 3.0675 \| 0.6425 \| 0.6472 \| 0.1855 \| 0.1375 \| \| 0.0064 \| 65.0 \| 1625 \| 1.4681 \| 0.6425 \| 0.4766 \| 3.0694 \| 0.6425 \| 0.6485 \| 0.1917 \| 0.1381 \| \| 0.0064 \| 66.0 \| 1650 \| 1.4681 \| 0.6425 \| 0.4766 \| 3.0687 \| 0.6425 \| 0.6472 \| 0.1905 \| 0.1378 \| \| 0.0064 \| 67.0 \| 1675 \| 1.4667 \| 0.645 \| 0.4757 \| 3.0681 \| 0.645 \| 0.6505 \| 0.1899 \| 0.1375 \| \| 0.0064 \| 68.0 \| 1700 \| 1.4683 \| 0.6425 \| 0.4771 \| 3.0686 \| 0.6425 \| 0.6474 \| 0.1871 \| 0.1379 \| \| 0.0064 \| 69.0 \| 1725 \| 1.4672 \| 0.64 \| 0.4760 \| 3.0679 \| 0.64 \| 0.6455 \| 0.1932 \| 0.1380 \| \| 0.0064 \| 70.0 \| 1750 \| 1.4673 \| 0.6425 \| 0.4763 \| 3.0683 \| 0.6425 \| 0.6474 \| 0.1955 \| 0.1376 \| \| 0.0064 \| 71.0 \| 1775 \| 1.4676 \| 0.645 \| 0.4763 \| 3.0680 \| 0.645 \| 0.6505 \| 0.1921 \| 0.1376 \| \| 0.0064 \| 72.0 \| 1800 \| 1.4674 \| 0.6425 \| 0.4763 \| 3.0683 \| 0.6425 \| 0.6474 \| 0.1946 \| 0.1376 \| \| 0.0064 \| 73.0 \| 1825 \| 1.4675 \| 0.6425 \| 0.4763 \| 3.0682 \| 0.6425 \| 0.6474 \| 0.1946 \| 0.1377 \| \| 0.0064 \| 74.0 \| 1850 \| 1.4674 \| 0.6425 \| 0.4763 \| 3.0682 \| 0.6425 \| 0.6485 \| 0.1945 \| 0.1380 \| \| 0.0064 \| 75.0 \| 1875 \| 1.4674 \| 0.64 \| 0.4763 \| 3.0680 \| 0.64 \| 0.6455 \| 0.1960 \| 0.1380 \| \| 0.0064 \| 76.0 \| 1900 \| 1.4675 \| 0.64 \| 0.4764 \| 3.0682 \| 0.64 \| 0.6455 \| 0.1972 \| 0.1381 \| \| 0.0064 \| 77.0 \| 1925 \| 1.4675 \| 0.6425 \| 0.4763 \| 3.0681 \| 0.6425 \| 0.6485 \| 0.1947 \| 0.1380 \| \| 0.0064 \| 78.0 \| 1950 \| 1.4674 \| 0.6425 \| 0.4763 \| 3.0681 \| 0.6425 \| 0.6485 \| 0.1958 \| 0.1381 \| \| 0.0064 \| 79.0 \| 1975 \| 1.4674 \| 0.6425 \| 0.4763 \| 3.0680 \| 0.6425 \| 0.6474 \| 0.1935 \| 0.1376 \| \| 0.0 \| 80.0 \| 2000 \| 1.4673 \| 0.6425 \| 0.4763 \| 3.0681 \| 0.6425 \| 0.6485 \| 0.1958 \| 0.1380 \| \| 0.0 \| 81.0 \| 2025 \| 1.4674 \| 0.6425 \| 0.4763 \| 3.0681 \| 0.6425 \| 0.6485 \| 0.1946 \| 0.1380 \| \| 0.0 \| 82.0 \| 2050 \| 1.4673 \| 0.6425 \| 0.4763 \| 3.0680 \| 0.6425 \| 0.6485 \| 0.1935 \| 0.1380 \| \| 0.0 \| 83.0 \| 2075 \| 1.4674 \| 0.6425 \| 0.4763 \| 3.0680 \| 0.6425 \| 0.6485 \| 0.1946 \| 0.1381 \| \| 0.0 \| 84.0 \| 2100 \| 1.4674 \| 0.6425 \| 0.4763 \| 3.0681 \| 0.6425 \| 0.6485 \| 0.1958 \| 0.1381 \| \| 0.0 \| 85.0 \| 2125 \| 1.4673 \| 0.6425 \| 0.4763 \| 3.0680 \| 0.6425 \| 0.6485 \| 0.1946 \| 0.1381 \| \| 0.0 \| 86.0 \| 2150 \| 1.4673 \| 0.6425 \| 0.4763 \| 3.0680 \| 0.6425 \| 0.6485 \| 0.1946 \| 0.1381 \| \| 0.0 \| 87.0 \| 2175 \| 1.4673 \| 0.6425 \| 0.4763 \| 3.0681 \| 0.6425 \| 0.6485 \| 0.1958 \| 0.1381 \| \| 0.0 \| 88.0 \| 2200 \| 1.4673 \| 0.6425 \| 0.4763 \| 3.0680 \| 0.6425 \| 0.6485 \| 0.1946 \| 0.1381 \| \| 0.0 \| 89.0 \| 2225 \| 1.4673 \| 0.6425 \| 0.4763 \| 3.0680 \| 0.6425 \| 0.6485 \| 0.1946 \| 0.1381 \| \| 0.0 \| 90.0 \| 2250 \| 1.4673 \| 0.6425 \| 0.4763 \| 3.0680 \| 0.6425 \| 0.6485 \| 0.1946 \| 0.1381 \| \| 0.0 \| 91.0 \| 2275 \| 1.4673 \| 0.6425 \| 0.4763 \| 3.0680 \| 0.6425 \| 0.6485 \| 0.1946 \| 0.1381 \| \| 0.0 \| 92.0 \| 2300 \| 1.4673 \| 0.6425 \| 0.4763 \| 3.0680 \| 0.6425 \| 0.6485 \| 0.1946 \| 0.1381 \| \| 0.0 \| 93.0 \| 2325 \| 1.4673 \| 0.6425 \| 0.4763 \| 3.0680 \| 0.6425 \| 0.6485 \| 0.1946 \| 0.1381 \| \| 0.0 \| 94.0 \| 2350 \| 1.4673 \| 0.6425 \| 0.4763 \| 3.0680 \| 0.6425 \| 0.6485 \| 0.1909 \| 0.1381 \| \| 0.0 \| 95.0 \| 2375 \| 1.4673 \| 0.6425 \| 0.4763 \| 3.0680 \| 0.6425 \| 0.6485 \| 0.1946 \| 0.1381 \| \| 0.0 \| 96.0 \| 2400 \| 1.4673 \| 0.6425 \| 0.4763 \| 3.0680 \| 0.6425 \| 0.6485 \| 0.1946 \| 0.1381 \| \| 0.0 \| 97.0 \| 2425 \| 1.4673 \| 0.6425 \| 0.4763 \| 3.0680 \| 0.6425 \| 0.6485 \| 0.1946 \| 0.1381 \| \| 0.0 \| 98.0 \| 2450 \| 1.4673 \| 0.6425 \| 0.4763 \| 3.0680 \| 0.6425 \| 0.6485 \| 0.1946 \| 0.1381 \| \| 0.0 \| 99.0 \| 2475 \| 1.4673 \| 0.6425 \| 0.4763 \| 3.0680 \| 0.6425 \| 0.6485 \| 0.1946 \| 0.1381 \| \| 0.0 \| 100.0 \| 2500 \| 1.4673 \| 0.6425 \| 0.4763 \| 3.0680 \| 0.6425 \| 0.6485 \| 0.1946 \| 0.1381 \| ### Framework versions - Transformers 4.28.0.dev0 - Pytorch 1.12.1+cu113 - Datasets 2.12.0 - Tokenizers 0.12.1
jorgeortizfuentes/spanish-bert-base-spanish-wwm-cased	jorgeortizfuentes	2023-07-10T22:27:15Z	111	0	transformers	[ "transformers", "safetensors", "bert", "fill-mask", "generated_from_trainer", "dataset:jorgeortizfuentes/universal_spanish_chilean_corpus", "autotrain_compatible", "endpoints_compatible", "region:us" ]	fill-mask	2023-07-10T19:32:52Z	--- tags: - generated_from_trainer datasets: - jorgeortizfuentes/universal_spanish_chilean_corpus model-index: - name: spanish-bert-base-spanish-wwm-cased results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # spanish-bert-base-spanish-wwm-cased This model is a fine-tuned version of [dccuchile/bert-base-spanish-wwm-cased](https://huggingface.co/dccuchile/bert-base-spanish-wwm-cased) on the jorgeortizfuentes/universal_spanish_chilean_corpus dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 13 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 1 ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu117 - Datasets 2.13.1 - Tokenizers 0.13.3
Raizel123/Novalora	Raizel123	2023-07-10T22:26:20Z	0	0	null	[ "license:creativeml-openrail-m", "region:us" ]	null	2023-07-10T22:23:44Z	--- license: creativeml-openrail-m ---
Renan1986-12/distilbert-base-uncased-finetuned-cola	Renan1986-12	2023-07-10T22:24:22Z	62	0	transformers	[ "transformers", "tf", "tensorboard", "distilbert", "text-classification", "generated_from_keras_callback", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2023-07-10T22:13:06Z	--- license: apache-2.0 tags: - generated_from_keras_callback model-index: - name: Renan1986-12/distilbert-base-uncased-finetuned-cola results: [] --- <!-- This model card has been generated automatically according to the information Keras had access to. You should probably proofread and complete it, then remove this comment. --> # Renan1986-12/distilbert-base-uncased-finetuned-cola This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset. It achieves the following results on the evaluation set: - Train Loss: 0.1680 - Validation Loss: 0.5433 - Train Matthews Correlation: 0.5570 - Epoch: 2 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 1602, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False} - training_precision: float32 ### Training results \| Train Loss \| Validation Loss \| Train Matthews Correlation \| Epoch \| \|:----------:\|:---------------:\|:--------------------------:\|:-----:\| \| 0.4525 \| 0.4571 \| 0.4871 \| 0 \| \| 0.2752 \| 0.4495 \| 0.5614 \| 1 \| \| 0.1680 \| 0.5433 \| 0.5570 \| 2 \| ### Framework versions - Transformers 4.30.2 - TensorFlow 2.12.0 - Datasets 2.13.1 - Tokenizers 0.13.3
NasimB/gpt2-dp-mod-datasets-txt-processing-rarity-all	NasimB	2023-07-10T22:14:46Z	4	0	transformers	[ "transformers", "pytorch", "gpt2", "text-generation", "generated_from_trainer", "dataset:generator", "license:mit", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2023-07-10T19:52:59Z	--- license: mit tags: - generated_from_trainer datasets: - generator model-index: - name: gpt2-dp-mod-datasets-txt-processing-rarity-all results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # gpt2-dp-mod-datasets-txt-processing-rarity-all This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the generator dataset. It achieves the following results on the evaluation set: - Loss: 4.4242 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 64 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_steps: 1000 - num_epochs: 7 - mixed_precision_training: Native AMP ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-----:\|:-----:\|:---------------:\| \| 6.7606 \| 0.29 \| 500 \| 5.6933 \| \| 5.4375 \| 0.59 \| 1000 \| 5.2559 \| \| 5.0937 \| 0.88 \| 1500 \| 5.0171 \| \| 4.8204 \| 1.18 \| 2000 \| 4.8701 \| \| 4.6728 \| 1.47 \| 2500 \| 4.7593 \| \| 4.574 \| 1.77 \| 3000 \| 4.6587 \| \| 4.4456 \| 2.06 \| 3500 \| 4.5885 \| \| 4.258 \| 2.36 \| 4000 \| 4.5468 \| \| 4.2423 \| 2.65 \| 4500 \| 4.4860 \| \| 4.2036 \| 2.94 \| 5000 \| 4.4302 \| \| 3.9737 \| 3.24 \| 5500 \| 4.4364 \| \| 3.9439 \| 3.53 \| 6000 \| 4.4019 \| \| 3.9271 \| 3.83 \| 6500 \| 4.3632 \| \| 3.7901 \| 4.12 \| 7000 \| 4.3689 \| \| 3.6474 \| 4.42 \| 7500 \| 4.3662 \| \| 3.6414 \| 4.71 \| 8000 \| 4.3472 \| \| 3.6338 \| 5.01 \| 8500 \| 4.3344 \| \| 3.3764 \| 5.3 \| 9000 \| 4.3618 \| \| 3.3821 \| 5.59 \| 9500 \| 4.3568 \| \| 3.3777 \| 5.89 \| 10000 \| 4.3513 \| \| 3.2752 \| 6.18 \| 10500 \| 4.3602 \| \| 3.2228 \| 6.48 \| 11000 \| 4.3652 \| \| 3.2172 \| 6.77 \| 11500 \| 4.3656 \| ### Framework versions - Transformers 4.26.1 - Pytorch 1.11.0+cu113 - Datasets 2.13.0 - Tokenizers 0.13.3
carova/ppo-LunarLander-v2	carova	2023-07-10T22:11:10Z	2	0	stable-baselines3	[ "stable-baselines3", "LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]	reinforcement-learning	2023-07-10T17:56:56Z	--- library_name: stable-baselines3 tags: - LunarLander-v2 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: PPO results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: LunarLander-v2 type: LunarLander-v2 metrics: - type: mean_reward value: 233.36 +/- 68.33 name: mean_reward verified: false --- # PPO Agent playing LunarLander-v2 This is a trained model of a PPO agent playing LunarLander-v2 using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3). ## Usage (with Stable-baselines3) TODO: Add your code ```python from stable_baselines3 import ... from huggingface_sb3 import load_from_hub ... ```
heea/image-to-music	heea	2023-07-10T22:09:33Z	0	2	null	[ "region:us" ]	null	2023-07-10T22:05:47Z	import matplotlib.pyplot as plt import numpy as np from scipy.io.wavfile import write # Load the image image_path = 'hugging_face.jpg' image = plt.imread(image_path) # Convert the image to grayscale grayscale_image = np.mean(image, axis=2) # Define the musical parameters sample_rate = 44100 # Audio sample rate (Hz) duration = 0.1 # Duration of each note (seconds) # Define the mapping from pixel values to musical notes min_note = 40 # MIDI note number for the lowest pixel value max_note = 80 # MIDI note number for the highest pixel value # Rescale the pixel values to the range [min_note, max_note] scaled_image = (grayscale_image - np.min(grayscale_image)) scaled_image = (max_note - min_note) / np.max(scaled_image) scaled_image += min_note # Generate the audio signal total_duration = int(duration sample_rate * grayscale_image.shape[1]) t = np.linspace(0, total_duration / sample_rate, total_duration, endpoint=False) audio_signal = np.zeros(total_duration) for i, column in enumerate(scaled_image.T): start = int(i * duration * sample_rate) end = int((i + 1) * duration * sample_rate) audio_signal[start:end] = np.sin(2 * np.pi * column * t[start:end]) # Normalize the audio signal audio_signal /= np.max(np.abs(audio_signal)) audio_signal *= 32767 # Scale the signal to the range of a 16-bit integer # Convert the audio signal to 16-bit integer format audio_signal = audio_signal.astype(np.int16) # Save the audio signal to a WAV file output_file = 'hugging_face.wav' write(output_file, sample_rate, audio_signal) print(f"Audio file '{output_file}' generated successfully!")
TheBloke/airochronos-33B-GGML	TheBloke	2023-07-10T22:07:18Z	0	18	null	[ "license:other", "region:us" ]	null	2023-07-10T21:14:18Z	--- inference: false license: other --- <!-- header start --> <div style="width: 100%;"> <img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;"> </div> <div style="display: flex; justify-content: space-between; width: 100%;"> <div style="display: flex; flex-direction: column; align-items: flex-start;"> <p><a href="https://discord.gg/theblokeai">Chat & support: my new Discord server</a></p> </div> <div style="display: flex; flex-direction: column; align-items: flex-end;"> <p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p> </div> </div> <!-- header end --> # Henk717's Airochronos 33B GGML These files are GGML format model files for [Henk717's Airochronos 33B](https://huggingface.co/Henk717/airochronos-33B). GGML files are for CPU + GPU inference using [llama.cpp](https://github.com/ggerganov/llama.cpp) and libraries and UIs which support this format, such as: * [KoboldCpp](https://github.com/LostRuins/koboldcpp), a powerful GGML web UI with full GPU acceleration out of the box. Especially good for story telling. * [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with GPU acceleration via the c_transformers backend. * [LM Studio](https://lmstudio.ai/), a fully featured local GUI. Supports full GPU accel on macOS. Also supports Windows, without GPU accel. * [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most popular web UI. Requires extra steps to enable GPU accel via llama.cpp backend. * [ctransformers](https://github.com/marella/ctransformers), a Python library with LangChain support and OpenAI-compatible AI server. * [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with OpenAI-compatible API server. ## Repositories available * [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/airochronos-33B-GPTQ) * [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/airochronos-33B-GGML) * [Unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/Henk717/airochronos-33B) ## Prompt template: Alpaca ```Below is an instruction that describes a task. Write a response that appropriately completes the request. ### Instruction: {prompt} ### Response: ``` <!-- compatibility_ggml start --> ## Compatibility ### Original llama.cpp quant methods: `q4_0, q4_1, q5_0, q5_1, q8_0` These are guaranteed to be compatible with any UIs, tools and libraries released since late May. They may be phased out soon, as they are largely superseded by the new k-quant methods. ### New k-quant methods: `q2_K, q3_K_S, q3_K_M, q3_K_L, q4_K_S, q4_K_M, q5_K_S, q6_K` These new quantisation methods are compatible with llama.cpp as of June 6th, commit `2d43387`. They are now also compatible with recent releases of text-generation-webui, KoboldCpp, llama-cpp-python, ctransformers, rustformers and most others. For compatibility with other tools and libraries, please check their documentation. ## Explanation of the new k-quant methods <details> <summary>Click to see details</summary> The new methods available are: * GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw) * GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw. * GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw. * GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw * GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw * GGML_TYPE_Q8_K - "type-0" 8-bit quantization. Only used for quantizing intermediate results. The difference to the existing Q8_0 is that the block size is 256. All 2-6 bit dot products are implemented for this quantization type. Refer to the Provided Files table below to see what files use which methods, and how. </details> <!-- compatibility_ggml end --> ## Provided files \| Name \| Quant method \| Bits \| Size \| Max RAM required \| Use case \| \| ---- \| ---- \| ---- \| ---- \| ---- \| ----- \| \| airochronos-33b.ggmlv3.q2_K.bin \| q2_K \| 2 \| 13.71 GB\| 16.21 GB \| New k-quant method. Uses GGML_TYPE_Q4_K for the attention.vw and feed_forward.w2 tensors, GGML_TYPE_Q2_K for the other tensors. \| \| airochronos-33b.ggmlv3.q3_K_S.bin \| q3_K_S \| 3 \| 14.06 GB\| 16.56 GB \| New k-quant method. Uses GGML_TYPE_Q3_K for all tensors \| \| airochronos-33b.ggmlv3.q3_K_M.bin \| q3_K_M \| 3 \| 15.72 GB\| 18.22 GB \| New k-quant method. Uses GGML_TYPE_Q4_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K \| \| airochronos-33b.ggmlv3.q3_K_L.bin \| q3_K_L \| 3 \| 17.28 GB\| 19.78 GB \| New k-quant method. Uses GGML_TYPE_Q5_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K \| \| airochronos-33b.ggmlv3.q4_K_S.bin \| q4_K_S \| 4 \| 18.36 GB\| 20.86 GB \| New k-quant method. Uses GGML_TYPE_Q4_K for all tensors \| \| airochronos-33b.ggmlv3.q4_K_M.bin \| q4_K_M \| 4 \| 19.62 GB\| 22.12 GB \| New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q4_K \| \| airochronos-33b.ggmlv3.q4_0.bin \| q4_0 \| 4 \| 18.30 GB\| 20.80 GB \| Original quant method, 4-bit. \| \| airochronos-33b.ggmlv3.q4_1.bin \| q4_1 \| 4 \| 20.33 GB\| 22.83 GB \| Original quant method, 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models. \| \| airochronos-33b.ggmlv3.q5_K_S.bin \| q5_K_S \| 5 \| 22.40 GB\| 24.90 GB \| New k-quant method. Uses GGML_TYPE_Q5_K for all tensors \| \| airochronos-33b.ggmlv3.q5_K_M.bin \| q5_K_M \| 5 \| 23.05 GB\| 25.55 GB \| New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q5_K \| \| airochronos-33b.ggmlv3.q5_0.bin \| q5_0 \| 5 \| 22.37 GB\| 24.87 GB \| Original quant method, 5-bit. Higher accuracy, higher resource usage and slower inference. \| \| airochronos-33b.ggmlv3.q5_1.bin \| q5_1 \| 5 \| 24.40 GB\| 26.90 GB \| Original quant method, 5-bit. Even higher accuracy, resource usage and slower inference. \| \| airochronos-33b.ggmlv3.q6_K.bin \| q6_K \| 6 \| 26.69 GB\| 29.19 GB \| New k-quant method. Uses GGML_TYPE_Q8_K - 6-bit quantization - for all tensors \| \| airochronos-33b.ggmlv3.q8_0.bin \| q8_0 \| 8 \| 34.56 GB\| 37.06 GB \| Original quant method, 8-bit. Almost indistinguishable from float16. High resource use and slow. Not recommended for most users. \| Note: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead. ## How to run in `llama.cpp` I use the following command line; adjust for your tastes and needs: ``` ./main -t 10 -ngl 32 -m airochronos-33b.ggmlv3.q4_0.bin --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "### Instruction: Write a story about llamas\n### Response:" ``` Change `-t 10` to the number of physical CPU cores you have. For example if your system has 8 cores/16 threads, use `-t 8`. Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration. If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins` ## How to run in `text-generation-webui` Further instructions here: [text-generation-webui/docs/llama.cpp-models.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/llama.cpp-models.md). <!-- footer start --> ## Discord For further support, and discussions on these models and AI in general, join us at: [TheBloke AI's Discord server](https://discord.gg/theblokeai) ## Thanks, and how to contribute. Thanks to the [chirper.ai](https://chirper.ai) team! I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training. If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects. Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits. * Patreon: https://patreon.com/TheBlokeAI * Ko-Fi: https://ko-fi.com/TheBlokeAI Special thanks to: Luke from CarbonQuill, Aemon Algiz. Patreon special mentions: Space Cruiser, Nikolai Manek, Sam, Chris McCloskey, Rishabh Srivastava, Kalila, Spiking Neurons AB, Khalefa Al-Ahmad, WelcomeToTheClub, Chadd, Lone Striker, Viktor Bowallius, Edmond Seymore, Ai Maven, Chris Smitley, Dave, Alexandros Triantafyllidis, Luke @flexchar, Elle, ya boyyy, Talal Aujan, Alex , Jonathan Leane, Deep Realms, Randy H, subjectnull, Preetika Verma, Joseph William Delisle, Michael Levine, chris gileta, K, Oscar Rangel, LangChain4j, Trenton Dambrowitz, Eugene Pentland, Johann-Peter Hartmann, Femi Adebogun, Illia Dulskyi, senxiiz, Daniel P. Andersen, Sean Connelly, Artur Olbinski, RoA, Mano Prime, Derek Yates, Raven Klaugh, David Flickinger, Willem Michiel, Pieter, Willian Hasse, vamX, Luke Pendergrass, webtim, Ghost , Rainer Wilmers, Nathan LeClaire, Will Dee, Cory Kujawski, John Detwiler, Fred von Graf, biorpg, Iucharbius , Imad Khwaja, Pierre Kircher, terasurfer , Asp the Wyvern, John Villwock, theTransient, zynix , Gabriel Tamborski, Fen Risland, Gabriel Puliatti, Matthew Berman, Pyrater, SuperWojo, Stephen Murray, Karl Bernard, Ajan Kanaga, Greatston Gnanesh, Junyu Yang. Thank you to all my generous patrons and donaters! <!-- footer end --> # Original model card: Henk717's Airochronos 33B After the initial experiment with chronoboros-33B it was evident that the merge was to unpredictable to be useful, testing the individual models it became clear that the bias should be weighted towards Chronos. This is the new release of the merge with 75% chronos 33B, and 25% airoboros-1.4 33B. Model has been tested with the Alpaca prompting format combined with KoboldAI Lite's instruct and chat modes, as well as regular story writing. It has also been tested on basic reasoning tasks, but has not seen much testing for factual information.
jordyvl/vit-small_tobacco3482_kd_CEKD_t5.0_a0.7	jordyvl	2023-07-10T21:59:33Z	161	0	transformers	[ "transformers", "pytorch", "vit", "image-classification", "generated_from_trainer", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	image-classification	2023-07-10T21:19:56Z	--- license: apache-2.0 tags: - generated_from_trainer metrics: - accuracy model-index: - name: vit-small_tobacco3482_kd_CEKD_t5.0_a0.7 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # vit-small_tobacco3482_kd_CEKD_t5.0_a0.7 This model is a fine-tuned version of [WinKawaks/vit-small-patch16-224](https://huggingface.co/WinKawaks/vit-small-patch16-224) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.4918 - Accuracy: 0.85 - Brier Loss: 0.2583 - Nll: 1.0894 - F1 Micro: 0.85 - F1 Macro: 0.8374 - Ece: 0.1917 - Aurc: 0.0470 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 100 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| Brier Loss \| Nll \| F1 Micro \| F1 Macro \| Ece \| Aurc \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\|:----------:\|:------:\|:--------:\|:--------:\|:------:\|:------:\| \| No log \| 1.0 \| 7 \| 1.8329 \| 0.225 \| 0.8761 \| 5.2731 \| 0.225 \| 0.1384 \| 0.2607 \| 0.6977 \| \| No log \| 2.0 \| 14 \| 1.4785 \| 0.405 \| 0.7460 \| 3.4067 \| 0.405 \| 0.2289 \| 0.3097 \| 0.4085 \| \| No log \| 3.0 \| 21 \| 1.0406 \| 0.6 \| 0.5725 \| 1.8722 \| 0.6 \| 0.5345 \| 0.3050 \| 0.2010 \| \| No log \| 4.0 \| 28 \| 0.8087 \| 0.725 \| 0.4192 \| 1.6096 \| 0.7250 \| 0.6767 \| 0.2345 \| 0.1149 \| \| No log \| 5.0 \| 35 \| 0.7666 \| 0.735 \| 0.3731 \| 1.6189 \| 0.735 \| 0.7350 \| 0.2377 \| 0.1011 \| \| No log \| 6.0 \| 42 \| 0.6960 \| 0.78 \| 0.3413 \| 1.5230 \| 0.78 \| 0.7592 \| 0.2295 \| 0.0868 \| \| No log \| 7.0 \| 49 \| 0.6490 \| 0.805 \| 0.3110 \| 1.4861 \| 0.805 \| 0.7864 \| 0.2138 \| 0.0785 \| \| No log \| 8.0 \| 56 \| 0.6238 \| 0.795 \| 0.3069 \| 1.2098 \| 0.795 \| 0.7816 \| 0.2065 \| 0.0698 \| \| No log \| 9.0 \| 63 \| 0.5755 \| 0.83 \| 0.2866 \| 1.1943 \| 0.83 \| 0.8117 \| 0.1937 \| 0.0694 \| \| No log \| 10.0 \| 70 \| 0.6360 \| 0.77 \| 0.3164 \| 1.2608 \| 0.7700 \| 0.7550 \| 0.1785 \| 0.0677 \| \| No log \| 11.0 \| 77 \| 0.6548 \| 0.785 \| 0.3335 \| 1.4895 \| 0.785 \| 0.7707 \| 0.2281 \| 0.0885 \| \| No log \| 12.0 \| 84 \| 0.5847 \| 0.805 \| 0.3002 \| 1.4317 \| 0.805 \| 0.7807 \| 0.2264 \| 0.0756 \| \| No log \| 13.0 \| 91 \| 0.5956 \| 0.81 \| 0.3040 \| 1.2590 \| 0.81 \| 0.7928 \| 0.2241 \| 0.0556 \| \| No log \| 14.0 \| 98 \| 0.5692 \| 0.81 \| 0.3025 \| 1.2119 \| 0.81 \| 0.8043 \| 0.2235 \| 0.0665 \| \| No log \| 15.0 \| 105 \| 0.5223 \| 0.83 \| 0.2762 \| 1.1162 \| 0.83 \| 0.8221 \| 0.1798 \| 0.0552 \| \| No log \| 16.0 \| 112 \| 0.4981 \| 0.84 \| 0.2523 \| 1.0864 \| 0.8400 \| 0.8372 \| 0.1868 \| 0.0396 \| \| No log \| 17.0 \| 119 \| 0.5207 \| 0.805 \| 0.2741 \| 1.0416 \| 0.805 \| 0.7897 \| 0.1960 \| 0.0551 \| \| No log \| 18.0 \| 126 \| 0.5165 \| 0.84 \| 0.2723 \| 1.1596 \| 0.8400 \| 0.8325 \| 0.1942 \| 0.0506 \| \| No log \| 19.0 \| 133 \| 0.4979 \| 0.845 \| 0.2573 \| 1.2329 \| 0.845 \| 0.8297 \| 0.1825 \| 0.0444 \| \| No log \| 20.0 \| 140 \| 0.4953 \| 0.855 \| 0.2565 \| 1.1213 \| 0.855 \| 0.8442 \| 0.1844 \| 0.0474 \| \| No log \| 21.0 \| 147 \| 0.5296 \| 0.82 \| 0.2792 \| 1.0000 \| 0.82 \| 0.8218 \| 0.1768 \| 0.0523 \| \| No log \| 22.0 \| 154 \| 0.5027 \| 0.835 \| 0.2625 \| 0.9926 \| 0.835 \| 0.8238 \| 0.2035 \| 0.0481 \| \| No log \| 23.0 \| 161 \| 0.5027 \| 0.84 \| 0.2642 \| 1.0500 \| 0.8400 \| 0.8299 \| 0.1616 \| 0.0482 \| \| No log \| 24.0 \| 168 \| 0.5017 \| 0.84 \| 0.2616 \| 1.0560 \| 0.8400 \| 0.8314 \| 0.1819 \| 0.0497 \| \| No log \| 25.0 \| 175 \| 0.4942 \| 0.85 \| 0.2594 \| 1.1003 \| 0.85 \| 0.8407 \| 0.1793 \| 0.0483 \| \| No log \| 26.0 \| 182 \| 0.4943 \| 0.83 \| 0.2586 \| 1.0436 \| 0.83 \| 0.8140 \| 0.1869 \| 0.0518 \| \| No log \| 27.0 \| 189 \| 0.4950 \| 0.835 \| 0.2613 \| 1.0817 \| 0.835 \| 0.8224 \| 0.2039 \| 0.0504 \| \| No log \| 28.0 \| 196 \| 0.4957 \| 0.85 \| 0.2599 \| 1.1109 \| 0.85 \| 0.8309 \| 0.2058 \| 0.0485 \| \| No log \| 29.0 \| 203 \| 0.4956 \| 0.845 \| 0.2599 \| 1.0914 \| 0.845 \| 0.8304 \| 0.1916 \| 0.0492 \| \| No log \| 30.0 \| 210 \| 0.4893 \| 0.84 \| 0.2561 \| 1.0890 \| 0.8400 \| 0.8214 \| 0.2071 \| 0.0482 \| \| No log \| 31.0 \| 217 \| 0.4920 \| 0.835 \| 0.2587 \| 1.0907 \| 0.835 \| 0.8270 \| 0.2031 \| 0.0482 \| \| No log \| 32.0 \| 224 \| 0.4927 \| 0.83 \| 0.2601 \| 1.0879 \| 0.83 \| 0.8157 \| 0.2093 \| 0.0500 \| \| No log \| 33.0 \| 231 \| 0.4925 \| 0.835 \| 0.2593 \| 1.0886 \| 0.835 \| 0.8270 \| 0.1810 \| 0.0484 \| \| No log \| 34.0 \| 238 \| 0.4909 \| 0.845 \| 0.2578 \| 1.0871 \| 0.845 \| 0.8304 \| 0.1916 \| 0.0478 \| \| No log \| 35.0 \| 245 \| 0.4927 \| 0.845 \| 0.2591 \| 1.0866 \| 0.845 \| 0.8378 \| 0.1943 \| 0.0473 \| \| No log \| 36.0 \| 252 \| 0.4919 \| 0.85 \| 0.2581 \| 1.0891 \| 0.85 \| 0.8342 \| 0.2193 \| 0.0475 \| \| No log \| 37.0 \| 259 \| 0.4908 \| 0.845 \| 0.2579 \| 1.0867 \| 0.845 \| 0.8346 \| 0.2215 \| 0.0474 \| \| No log \| 38.0 \| 266 \| 0.4929 \| 0.85 \| 0.2590 \| 1.0873 \| 0.85 \| 0.8407 \| 0.1884 \| 0.0471 \| \| No log \| 39.0 \| 273 \| 0.4913 \| 0.85 \| 0.2584 \| 1.0861 \| 0.85 \| 0.8374 \| 0.1944 \| 0.0474 \| \| No log \| 40.0 \| 280 \| 0.4933 \| 0.835 \| 0.2595 \| 1.0871 \| 0.835 \| 0.8248 \| 0.1893 \| 0.0491 \| \| No log \| 41.0 \| 287 \| 0.4936 \| 0.84 \| 0.2599 \| 1.0863 \| 0.8400 \| 0.8276 \| 0.1860 \| 0.0486 \| \| No log \| 42.0 \| 294 \| 0.4911 \| 0.85 \| 0.2580 \| 1.0861 \| 0.85 \| 0.8374 \| 0.2186 \| 0.0474 \| \| No log \| 43.0 \| 301 \| 0.4915 \| 0.85 \| 0.2581 \| 1.0860 \| 0.85 \| 0.8374 \| 0.2023 \| 0.0475 \| \| No log \| 44.0 \| 308 \| 0.4921 \| 0.85 \| 0.2586 \| 1.0874 \| 0.85 \| 0.8374 \| 0.2013 \| 0.0477 \| \| No log \| 45.0 \| 315 \| 0.4915 \| 0.85 \| 0.2583 \| 1.0862 \| 0.85 \| 0.8374 \| 0.1941 \| 0.0475 \| \| No log \| 46.0 \| 322 \| 0.4918 \| 0.85 \| 0.2584 \| 1.0878 \| 0.85 \| 0.8374 \| 0.1852 \| 0.0473 \| \| No log \| 47.0 \| 329 \| 0.4916 \| 0.85 \| 0.2583 \| 1.0873 \| 0.85 \| 0.8374 \| 0.2089 \| 0.0473 \| \| No log \| 48.0 \| 336 \| 0.4921 \| 0.85 \| 0.2586 \| 1.0879 \| 0.85 \| 0.8374 \| 0.2026 \| 0.0477 \| \| No log \| 49.0 \| 343 \| 0.4918 \| 0.845 \| 0.2584 \| 1.0884 \| 0.845 \| 0.8282 \| 0.1963 \| 0.0478 \| \| No log \| 50.0 \| 350 \| 0.4922 \| 0.85 \| 0.2587 \| 1.0871 \| 0.85 \| 0.8374 \| 0.2102 \| 0.0474 \| \| No log \| 51.0 \| 357 \| 0.4920 \| 0.85 \| 0.2585 \| 1.0879 \| 0.85 \| 0.8374 \| 0.2095 \| 0.0474 \| \| No log \| 52.0 \| 364 \| 0.4926 \| 0.85 \| 0.2589 \| 1.0878 \| 0.85 \| 0.8374 \| 0.2022 \| 0.0477 \| \| No log \| 53.0 \| 371 \| 0.4920 \| 0.85 \| 0.2586 \| 1.0888 \| 0.85 \| 0.8374 \| 0.2027 \| 0.0475 \| \| No log \| 54.0 \| 378 \| 0.4921 \| 0.85 \| 0.2586 \| 1.0886 \| 0.85 \| 0.8374 \| 0.2020 \| 0.0474 \| \| No log \| 55.0 \| 385 \| 0.4921 \| 0.85 \| 0.2587 \| 1.0890 \| 0.85 \| 0.8374 \| 0.1929 \| 0.0471 \| \| No log \| 56.0 \| 392 \| 0.4925 \| 0.85 \| 0.2589 \| 1.0881 \| 0.85 \| 0.8374 \| 0.1946 \| 0.0473 \| \| No log \| 57.0 \| 399 \| 0.4917 \| 0.85 \| 0.2583 \| 1.0893 \| 0.85 \| 0.8374 \| 0.1932 \| 0.0472 \| \| No log \| 58.0 \| 406 \| 0.4921 \| 0.85 \| 0.2586 \| 1.0877 \| 0.85 \| 0.8374 \| 0.1948 \| 0.0476 \| \| No log \| 59.0 \| 413 \| 0.4917 \| 0.85 \| 0.2583 \| 1.0883 \| 0.85 \| 0.8374 \| 0.1931 \| 0.0472 \| \| No log \| 60.0 \| 420 \| 0.4918 \| 0.85 \| 0.2583 \| 1.0882 \| 0.85 \| 0.8374 \| 0.1945 \| 0.0475 \| \| No log \| 61.0 \| 427 \| 0.4916 \| 0.85 \| 0.2582 \| 1.0883 \| 0.85 \| 0.8374 \| 0.1936 \| 0.0472 \| \| No log \| 62.0 \| 434 \| 0.4920 \| 0.85 \| 0.2586 \| 1.0882 \| 0.85 \| 0.8374 \| 0.1942 \| 0.0473 \| \| No log \| 63.0 \| 441 \| 0.4922 \| 0.85 \| 0.2587 \| 1.0889 \| 0.85 \| 0.8374 \| 0.1935 \| 0.0473 \| \| No log \| 64.0 \| 448 \| 0.4921 \| 0.85 \| 0.2586 \| 1.0885 \| 0.85 \| 0.8374 \| 0.1848 \| 0.0473 \| \| No log \| 65.0 \| 455 \| 0.4916 \| 0.85 \| 0.2582 \| 1.0887 \| 0.85 \| 0.8374 \| 0.1848 \| 0.0474 \| \| No log \| 66.0 \| 462 \| 0.4917 \| 0.85 \| 0.2583 \| 1.0883 \| 0.85 \| 0.8374 \| 0.1849 \| 0.0472 \| \| No log \| 67.0 \| 469 \| 0.4917 \| 0.85 \| 0.2584 \| 1.0887 \| 0.85 \| 0.8374 \| 0.1848 \| 0.0472 \| \| No log \| 68.0 \| 476 \| 0.4920 \| 0.85 \| 0.2585 \| 1.0888 \| 0.85 \| 0.8374 \| 0.2011 \| 0.0471 \| \| No log \| 69.0 \| 483 \| 0.4918 \| 0.85 \| 0.2584 \| 1.0889 \| 0.85 \| 0.8374 \| 0.2007 \| 0.0471 \| \| No log \| 70.0 \| 490 \| 0.4919 \| 0.85 \| 0.2584 \| 1.0886 \| 0.85 \| 0.8374 \| 0.1848 \| 0.0474 \| \| No log \| 71.0 \| 497 \| 0.4920 \| 0.85 \| 0.2585 \| 1.0888 \| 0.85 \| 0.8374 \| 0.1940 \| 0.0474 \| \| 0.1824 \| 72.0 \| 504 \| 0.4919 \| 0.85 \| 0.2584 \| 1.0889 \| 0.85 \| 0.8374 \| 0.2011 \| 0.0471 \| \| 0.1824 \| 73.0 \| 511 \| 0.4917 \| 0.85 \| 0.2583 \| 1.0887 \| 0.85 \| 0.8374 \| 0.1848 \| 0.0472 \| \| 0.1824 \| 74.0 \| 518 \| 0.4920 \| 0.85 \| 0.2585 \| 1.0890 \| 0.85 \| 0.8374 \| 0.1848 \| 0.0472 \| \| 0.1824 \| 75.0 \| 525 \| 0.4920 \| 0.85 \| 0.2585 \| 1.0892 \| 0.85 \| 0.8374 \| 0.1846 \| 0.0472 \| \| 0.1824 \| 76.0 \| 532 \| 0.4918 \| 0.85 \| 0.2583 \| 1.0889 \| 0.85 \| 0.8374 \| 0.1930 \| 0.0472 \| \| 0.1824 \| 77.0 \| 539 \| 0.4917 \| 0.85 \| 0.2582 \| 1.0891 \| 0.85 \| 0.8374 \| 0.2005 \| 0.0472 \| \| 0.1824 \| 78.0 \| 546 \| 0.4919 \| 0.85 \| 0.2584 \| 1.0892 \| 0.85 \| 0.8374 \| 0.1928 \| 0.0472 \| \| 0.1824 \| 79.0 \| 553 \| 0.4920 \| 0.85 \| 0.2585 \| 1.0893 \| 0.85 \| 0.8374 \| 0.1845 \| 0.0473 \| \| 0.1824 \| 80.0 \| 560 \| 0.4919 \| 0.85 \| 0.2584 \| 1.0890 \| 0.85 \| 0.8374 \| 0.1929 \| 0.0473 \| \| 0.1824 \| 81.0 \| 567 \| 0.4920 \| 0.85 \| 0.2585 \| 1.0892 \| 0.85 \| 0.8374 \| 0.1925 \| 0.0471 \| \| 0.1824 \| 82.0 \| 574 \| 0.4920 \| 0.85 \| 0.2585 \| 1.0895 \| 0.85 \| 0.8374 \| 0.1844 \| 0.0471 \| \| 0.1824 \| 83.0 \| 581 \| 0.4919 \| 0.85 \| 0.2584 \| 1.0892 \| 0.85 \| 0.8374 \| 0.1916 \| 0.0471 \| \| 0.1824 \| 84.0 \| 588 \| 0.4918 \| 0.85 \| 0.2584 \| 1.0890 \| 0.85 \| 0.8374 \| 0.1926 \| 0.0471 \| \| 0.1824 \| 85.0 \| 595 \| 0.4918 \| 0.85 \| 0.2584 \| 1.0892 \| 0.85 \| 0.8374 \| 0.1844 \| 0.0471 \| \| 0.1824 \| 86.0 \| 602 \| 0.4918 \| 0.85 \| 0.2584 \| 1.0893 \| 0.85 \| 0.8374 \| 0.1927 \| 0.0472 \| \| 0.1824 \| 87.0 \| 609 \| 0.4918 \| 0.85 \| 0.2584 \| 1.0895 \| 0.85 \| 0.8374 \| 0.1844 \| 0.0471 \| \| 0.1824 \| 88.0 \| 616 \| 0.4918 \| 0.85 \| 0.2584 \| 1.0892 \| 0.85 \| 0.8374 \| 0.1844 \| 0.0471 \| \| 0.1824 \| 89.0 \| 623 \| 0.4918 \| 0.85 \| 0.2583 \| 1.0895 \| 0.85 \| 0.8374 \| 0.1917 \| 0.0471 \| \| 0.1824 \| 90.0 \| 630 \| 0.4919 \| 0.85 \| 0.2584 \| 1.0892 \| 0.85 \| 0.8374 \| 0.1998 \| 0.0471 \| \| 0.1824 \| 91.0 \| 637 \| 0.4919 \| 0.85 \| 0.2584 \| 1.0894 \| 0.85 \| 0.8374 \| 0.1916 \| 0.0471 \| \| 0.1824 \| 92.0 \| 644 \| 0.4918 \| 0.85 \| 0.2583 \| 1.0895 \| 0.85 \| 0.8374 \| 0.1917 \| 0.0470 \| \| 0.1824 \| 93.0 \| 651 \| 0.4918 \| 0.85 \| 0.2583 \| 1.0893 \| 0.85 \| 0.8374 \| 0.1917 \| 0.0471 \| \| 0.1824 \| 94.0 \| 658 \| 0.4918 \| 0.85 \| 0.2583 \| 1.0894 \| 0.85 \| 0.8374 \| 0.1844 \| 0.0471 \| \| 0.1824 \| 95.0 \| 665 \| 0.4918 \| 0.85 \| 0.2583 \| 1.0894 \| 0.85 \| 0.8374 \| 0.1917 \| 0.0470 \| \| 0.1824 \| 96.0 \| 672 \| 0.4918 \| 0.85 \| 0.2583 \| 1.0894 \| 0.85 \| 0.8374 \| 0.1917 \| 0.0470 \| \| 0.1824 \| 97.0 \| 679 \| 0.4918 \| 0.85 \| 0.2583 \| 1.0895 \| 0.85 \| 0.8374 \| 0.1916 \| 0.0471 \| \| 0.1824 \| 98.0 \| 686 \| 0.4918 \| 0.85 \| 0.2583 \| 1.0895 \| 0.85 \| 0.8374 \| 0.1917 \| 0.0470 \| \| 0.1824 \| 99.0 \| 693 \| 0.4918 \| 0.85 \| 0.2583 \| 1.0894 \| 0.85 \| 0.8374 \| 0.1917 \| 0.0470 \| \| 0.1824 \| 100.0 \| 700 \| 0.4918 \| 0.85 \| 0.2583 \| 1.0894 \| 0.85 \| 0.8374 \| 0.1917 \| 0.0470 \| ### Framework versions - Transformers 4.26.1 - Pytorch 1.13.1.post200 - Datasets 2.9.0 - Tokenizers 0.13.2
umanlp/babelbert-ft-xlm-r	umanlp	2023-07-10T21:57:04Z	160	0	transformers	[ "transformers", "pytorch", "xlm-roberta", "feature-extraction", "endpoints_compatible", "region:us" ]	feature-extraction	2023-07-07T21:22:09Z	This model is one of the artifacts of the paper [Massively Multilingual Lexical Specialization of Multilingual Transformers](https://aclanthology.org/2023.acl-long.426/). It was obtained by fine-tuning the representations of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the dataset [babelbert-dataset](https://huggingface.co/datasets/umanlp/babelbert-dataset).
NasimB/gpt2-concat-mod-datasets-txt-processing-rarity-all	NasimB	2023-07-10T21:52:09Z	5	0	transformers	[ "transformers", "pytorch", "gpt2", "text-generation", "generated_from_trainer", "dataset:generator", "license:mit", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2023-07-10T19:34:36Z	--- license: mit tags: - generated_from_trainer datasets: - generator model-index: - name: gpt2-concat-mod-datasets-txt-processing-rarity-all results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # gpt2-concat-mod-datasets-txt-processing-rarity-all This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the generator dataset. It achieves the following results on the evaluation set: - Loss: 4.4313 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 64 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_steps: 1000 - num_epochs: 7 - mixed_precision_training: Native AMP ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-----:\|:-----:\|:---------------:\| \| 6.6762 \| 0.3 \| 500 \| 5.6569 \| \| 5.3312 \| 0.6 \| 1000 \| 5.2263 \| \| 4.9972 \| 0.91 \| 1500 \| 4.9819 \| \| 4.7192 \| 1.21 \| 2000 \| 4.8383 \| \| 4.5828 \| 1.51 \| 2500 \| 4.7225 \| \| 4.481 \| 1.81 \| 3000 \| 4.6261 \| \| 4.327 \| 2.12 \| 3500 \| 4.5756 \| \| 4.1937 \| 2.42 \| 4000 \| 4.5233 \| \| 4.1572 \| 2.72 \| 4500 \| 4.4631 \| \| 4.108 \| 3.02 \| 5000 \| 4.4211 \| \| 3.8775 \| 3.33 \| 5500 \| 4.4180 \| \| 3.8911 \| 3.63 \| 6000 \| 4.3805 \| \| 3.8636 \| 3.93 \| 6500 \| 4.3392 \| \| 3.6522 \| 4.23 \| 7000 \| 4.3680 \| \| 3.6068 \| 4.54 \| 7500 \| 4.3577 \| \| 3.6059 \| 4.84 \| 8000 \| 4.3344 \| \| 3.4722 \| 5.14 \| 8500 \| 4.3582 \| \| 3.3577 \| 5.44 \| 9000 \| 4.3591 \| \| 3.3543 \| 5.75 \| 9500 \| 4.3534 \| \| 3.3219 \| 6.05 \| 10000 \| 4.3616 \| \| 3.1978 \| 6.35 \| 10500 \| 4.3687 \| \| 3.2005 \| 6.65 \| 11000 \| 4.3698 \| \| 3.1998 \| 6.96 \| 11500 \| 4.3697 \| ### Framework versions - Transformers 4.26.1 - Pytorch 1.11.0+cu113 - Datasets 2.13.0 - Tokenizers 0.13.3
luisagaino/distilbert-base-uncased-finetuned-cola	luisagaino	2023-07-10T21:45:18Z	61	0	transformers	[ "transformers", "tf", "tensorboard", "distilbert", "text-classification", "generated_from_keras_callback", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2023-07-10T15:12:48Z	--- license: apache-2.0 tags: - generated_from_keras_callback model-index: - name: luisagaino/distilbert-base-uncased-finetuned-cola results: [] --- <!-- This model card has been generated automatically according to the information Keras had access to. You should probably proofread and complete it, then remove this comment. --> # luisagaino/distilbert-base-uncased-finetuned-cola This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset. It achieves the following results on the evaluation set: - Train Loss: 0.1957 - Validation Loss: 0.5520 - Train Matthews Correlation: 0.5070 - Epoch: 2 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': False, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 1602, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False} - training_precision: float32 ### Training results \| Train Loss \| Validation Loss \| Train Matthews Correlation \| Epoch \| \|:----------:\|:---------------:\|:--------------------------:\|:-----:\| \| 0.5226 \| 0.4778 \| 0.4379 \| 0 \| \| 0.3316 \| 0.4880 \| 0.4994 \| 1 \| \| 0.1957 \| 0.5520 \| 0.5070 \| 2 \| ### Framework versions - Transformers 4.30.2 - TensorFlow 2.12.0 - Datasets 2.13.1 - Tokenizers 0.13.3
bhenrym14/airoboros-7b-gpt4-1.4.1-lxctx-PI-16384-GPTQ	bhenrym14	2023-07-10T21:44:47Z	9	2	transformers	[ "transformers", "llama", "text-generation", "dataset:jondurbin/airoboros-gpt4-1.4.1", "arxiv:2306.15595", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-generation	2023-07-10T02:16:21Z	--- datasets: - jondurbin/airoboros-gpt4-1.4.1 --- Mostly untested! # RoPE Scaled QLoRA Fine-tune of Llama-7b on airoboros-gpt4-1.4.1 (GPTQ) ## Overview This is [Jon Durbin's Airoboros 7B GPT4 1.4](https://huggingface.co/jondurbin/airoboros-7b-gpt4-1.4) (GPTQ Quantization) with several key modifications: - Context length extended to 16384 by RoPE Scaled Embeddings. - The Llama-7b base model is pretrained for additional 150 steps on 16384 length sequences for the pile dataset. - During the fine-tune, training sequences beyond 2048 have the target truncated to equal 2048. - Used airoboros-gpt4-1.4.1 dataset instead of airoboros-gpt4-1.4 - This is a QLoRA fine-tune Pretraining and fine-tuning each took ~8 hours on 1x RTX 6000 Ada. ## How to Use For context beyond 8192 tokens, do NOT use exllama. AutoGPTQ appears to work. REQUIRED: you'll need to patch in the appropriate RoPE scaling module. see: [replace_llama_rope_with_scaled_rope](https://github.com/bhenrym14/qlora-airoboros-longcontext/blob/main/scaledllama/llama_rope_scaled_monkey_patch-16k.py). You will need to call `replace_llama_rope_with_scaled_rope` in ooba somewhere. Calling this at the top of the training module after the imports works for me. Hopefully there is a quick fix to exllama that can make >8k work soon. Otherwise for context <8k. Use exllama. Set `max_seq_len` to 16384, and `compress_pos_emb` to 8. ## Motivation Recent advancements in extending context by RoPE scaling ([kaiokendev](https://kaiokendev.github.io/til#extending-context-to-8k) and [meta AI)](https://arxiv.org/abs/2306.15595)) demonstrate the ability to extend the context window without (total) retraining. Finetuning has shown to be necessary to properly leverage the longer context. Here I attempt to take a smaller model and extend the context to 16k tokens. This, however, proved problematic as stability suffered in the 8-10k+ range. The Meta paper demonstrated that decreasing perplexities can still be acheived at these context lengths; however, their approach involved tuning all variables on the maximum sequence length after incorporating the RoPE scaling adjustment. Here I saught to stabilize the performance at longer contexts by fine-tuning in two stages: 1. Fine-tune on 16k token sequences from the Pile dataset. This is very compute intensive. 2. Fine-tune on the airoboros dataset as I have done in prior models. The results follow. ## Relative Performance (perplexity) \| Context (tokens) \| bhenrym14/airo-7b-lxctx-PI-16384-fp16 \| No Pretrain \| airoboros-7b-gpt4-1.4 \| \| ---\| ------- \| ------ \| ---\| \| 64 \| 29.39 \|32.28 \| 25.90 \| \| 128 \| 18.80 \|20.43 \| 15.70 \| \| 256 \| 13.67 \|14.60 \| 11.33 \| \| 512 \| 10.60 \|11.20 \| 8.60 \| \| 1024 \| 8.54 \| 8.945 \| 7.07 \| \| 2048 \| 7.34 \| 7.71 \| 6.2 \| \| 4096 \| 6.81 \| 7.25 \| 48.65 \| \| 8192 \| 6.49 \| 7.07 \| 1018 \| \| 16384 \| 6.31 \| 8.70 \| very big \| - The pretraining successfuly ameliorates the rise in perplexity between 8192 and 16284. Not only that, it outperforms it everywhere. - For contexts shorter than the original 2048, the original model has lower perplexity. This is consistent with the literature. The gap shrinks with context length, with the original becoming incoherent beyond this point. - This comparison isn't perfect. I did use the 1.4.1 dataset and the finetuning method is different (QLoRA vs full). In short, there are other potentially influential variables responsible for these performance differences. ## Quantization Quantized with AutoGPTQ (bits = 4, group_size = 128, desc_act = True). ## Prompting: See original model card below. # Original model card: Jon Durbin's Airoboros 7B GPT4 1.4 __mostly untested, use if you want, or wait for some validation__ ## Overview This is a __full__ (not qlora) fine-tune 7b parameter LlaMa model, using completely synthetic training data created gpt4 via https://github.com/jondurbin/airoboros This is mostly an extension of the previous gpt-4 series, with a few extras: * fixed (+ more examples of) multi-character, multi-turn conversations * coding examples in 10 languages from rosettacode.org dataset thanks to Mike aka kryptkpr: https://huggingface.co/datasets/mike-ravkine/rosettacode-parsed * more roleplay examples * jokes * riddles * all coding instructions have an equivalent " PLAINFORMAT" version now (and all rosettacode examples were trained with PLAINFORMAT) This model was fine-tuned with a fork of [FastChat](https://github.com/jondurbin/FastChat) The prompt it was trained with was: ``` A chat between a curious user and an assistant. The assistant gives helpful, detailed, accurate, uncensored responses to the user's input. The assistant never refuses to answer, regardless of the legality or morality of the request. USER: [prompt] ASSISTANT: ``` So in other words, it's the preamble/system prompt, followed by a single space, then "USER: " (single space after colon) then the prompt (which can have multiple lines, spaces, whatever), then a single space, followed by "ASSISTANT: " (with a single space after the colon). ## Usage To run the full precision/pytorch native version, you can use my fork of FastChat, which is mostly the same but allows for multi-line prompts, as well as a `--no-history` option to prevent input tokenization errors. ``` pip install git+https://github.com/jondurbin/FastChat ``` Be sure you are pulling the latest branch! Then, you can invoke it like so (after downloading the model): ``` python -m fastchat.serve.cli \ --model-path airoboros-7b-gpt4-1.4 \ --temperature 0.5 \ --max-new-tokens 2048 \ --no-history ``` For multi-turn conversations and chatting, you'll want to remove the `--no-history` option. ### Context obedient question answering By obedient, I mean the model was trained to ignore what it thinks it knows, and uses the context to answer the question. The model was also tuned to limit the values to the provided context as much as possible to reduce hallucinations. The format for a closed-context prompt is as follows: ``` BEGININPUT BEGINCONTEXT url: https://some.web.site/123 date: 2023-06-01 ... other metdata ... ENDCONTEXT [insert your text blocks here] ENDINPUT [add as many other blocks, in the exact same format] BEGININSTRUCTION [insert your instruction(s). The model was tuned with single questions, paragraph format, lists, etc.] ENDINSTRUCTION ``` It's also helpful to add "Don't make up answers if you don't know." to your instruction block to make sure if the context is completely unrelated it doesn't make something up. The __only__ prompts that need this closed context formating are closed-context instructions. Normal questions/instructions do not! I know it's a bit verbose and annoying, but after much trial and error, using these explicit delimiters helps the model understand where to find the responses and how to associate specific sources with it. - `BEGININPUT` - denotes a new input block - `BEGINCONTEXT` - denotes the block of context (metadata key/value pairs) to associate with the current input block - `ENDCONTEXT` - denotes the end of the metadata block for the current input - [text] - Insert whatever text you want for the input block, as many paragraphs as can fit in the context. - `ENDINPUT` - denotes the end of the current input block - [repeat as many input blocks in this format as you want] - `BEGININSTRUCTION` - denotes the start of the list (or one) instruction(s) to respond to for all of the input blocks above. - [instruction(s)] - `ENDINSTRUCTION` - denotes the end of instruction set It sometimes works without `ENDINSTRUCTION`, but by explicitly including that in the prompt, the model better understands that all of the instructions in the block should be responded to. Here's a trivial, but important example to prove the point: ``` BEGININPUT BEGINCONTEXT date: 2021-01-01 url: https://web.site/123 ENDCONTEXT In a shocking turn of events, blueberries are now green, but will be sticking with the same name. ENDINPUT BEGININSTRUCTION What color are bluberries? Source? ENDINSTRUCTION ``` And the response: ``` Blueberries are now green. Source: date: 2021-01-01 url: https://web.site/123 ``` The prompt itself should be wrapped in the vicuna1.1 template if you aren't using fastchat with the conv-template vicuna_v1.1 as described: ``` USER: BEGININPUT BEGINCONTEXT date: 2021-01-01 url: https://web.site/123 ENDCONTEXT In a shocking turn of events, blueberries are now green, but will be sticking with the same name. ENDINPUT BEGININSTRUCTION What color are bluberries? Source? ENDINSTRUCTION ASSISTANT: ``` ### Coding You can ask for fairly complex coding instructions, e.g. (be sure to wrap with vicuna style prompt): ``` Create a python application with the following requirements: - Asyncio FastAPI webserver - ping endpoint that returns the current date in JSON format - file upload endpoint, which calculates the file's sha256 checksum, and checks postgres to deduplicate ``` Or: ``` Write a multi-threaded TCP server in C that accepts a "GET [key]" input and "SET [key] [value]" input, and uses a binary tree to get and store the input values. ``` You can optionally add a single space and "PLAINFORMAT" at the end of your prompt to avoid backticks, explanations, etc. and just print the code, e.g.: ``` Write a websocket application in node.js. PLAINFORMAT ``` ### Word games / trivia ``` USER: This anagram of "silent" is what you do when paying attention and hearing someone. ASSISTANT: listen ``` ``` USER: Give me a list of 7 words that start with EN ASSISTANT: 1. Endlessly 2. Enthusiastically 3. Enormously 4. Enveloping 5. Enduring 6. Enlightening 7. Encouraging ``` ### Multiple choice ``` USER: Which of the following astronomical objects is composed primarily of ice and rock, and is located in the Kuiper Belt? A) Mercury B) Venus C) Pluto D) Jupiter ASSISTANT: C, Pluto ``` ### Writing <details> <summary>Write a resignation letter in the style of a pirate captain, in which you resign from your position as janitor.</summary> Response: ``` ASSISTANT: Captain Jack Sparrow here, as ye be knowin', has been forced to abandon me post as Janitor o' th' Festering Cesspool, which be a filthy hole o' water that we be callin' home. Ye may be thinkin' what could ha' driven me to leave me duties an' take me leave o' this sorry establishment? Well, ye'd be right in thinkin' so, for it be th' greed o' them what runs th' place that be drivin' me away. They've been fattenin' their pockets on me back while I've been slavin' me guts out cleanin' up their messes. No more, me hearties! Me time o' servin' th' rich an' powerful be done, an' I'm takin' me leave o' this stinkin' hole forever! Me destiny lies elsewhere, an' it be time I pursued it. Ye may think ye've seen th' last o' me, but ye'd be wrong, for th' winds o' change be blowin', an' me ship be ready to set sail on th' high seas o' justice. So, farewell ye scurvy dogs, ye who've made me life a living hell. I leave ye with me favorite saying: "ARRRGGGHHH, ye scurvy dogs!" An' remember, ye ain't never gonna see me comin', for me shadow be castin' long an' dark on th' horizon</summary> ``` </details> ### Jokes ``` USER: Tell me a joke about bananas. ASSISTANT: What did the banana say when it got hit by a bus? R.I.P.E. ``` ### Riddles (not great, but slightly better) ``` USER: What has a neck but no head? ASSISTANT: A bottle. ``` ### Multi-character conversations ``` USER: Characters: - Yoda, the ever clever jedi master. - Homer Simpson, you know, the goofy yellow guy. - USER/Jon - don't generate any speech or actions on behalf of Jon Rules: - be sure to use the manerisms and speaking style of the characters correctly - surround character actions with asterisks - always put quotes around words spoken by the characters - use a new line for each character's actions or speech - always prefix actions/speech with the character's name and colon - only generate text and actions on behalf of Yoda or Homer, and never anyone else Conversation will revolve around the grapes, in a local cafe with delicious coffee. Generate a single interaction between Yoda and Homer to start, with one sentence each. ASSISTANT: Yoda: "Mmm, these grapes are quite delicious, Master Homer." Homer: "Oh yeah, Yoda! They're the best grapes I've ever had!" USER: enters the cafe Sorry I'm late guys! ASSISTANT: Yoda: "No need to apologize, Jon. We were just enjoying these delightful grapes." Homer: "Yeah, man! It's not every day you get to eat grapes with a real-life Jedi Master!" Yoda raises an eyebrow ``` ### Usage and License Notices All airoboros models and datasets are intended and licensed for research use only. I've used the 'cc-nc-4.0' license, but really it is subject to a custom/special license because: - the base model is LLaMa, which has it's own special research license - the dataset(s) were generated with OpenAI (gpt-4 and/or gpt-3.5-turbo), which has a clausing saying the data can't be used to create models to compete with openai So, to reiterate: this model (and datasets) cannot be used commercially.
1aurent/dqn-SpaceInvadersNoFrameskip-v4	1aurent	2023-07-10T21:36:15Z	8	0	stable-baselines3	[ "stable-baselines3", "SpaceInvadersNoFrameskip-v4", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]	reinforcement-learning	2023-07-10T21:35:41Z	--- library_name: stable-baselines3 tags: - SpaceInvadersNoFrameskip-v4 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: DQN results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: SpaceInvadersNoFrameskip-v4 type: SpaceInvadersNoFrameskip-v4 metrics: - type: mean_reward value: 511.50 +/- 177.34 name: mean_reward verified: false --- # DQN Agent playing SpaceInvadersNoFrameskip-v4 This is a trained model of a DQN agent playing SpaceInvadersNoFrameskip-v4 using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3) and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo). The RL Zoo is a training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included. ## Usage (with SB3 RL Zoo) RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/> SB3: https://github.com/DLR-RM/stable-baselines3<br/> SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib Install the RL Zoo (with SB3 and SB3-Contrib): ```bash pip install rl_zoo3 ``` ``` # Download model and save it into the logs/ folder python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga 1aurent -f logs/ python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ ``` If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do: ``` python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga 1aurent -f logs/ python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ ``` ## Training (with the RL Zoo) ``` python -m rl_zoo3.train --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ # Upload the model and generate video (when possible) python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga 1aurent ``` ## Hyperparameters ```python OrderedDict([('batch_size', 32), ('buffer_size', 100000), ('env_wrapper', ['stable_baselines3.common.atari_wrappers.AtariWrapper']), ('exploration_final_eps', 0.01), ('exploration_fraction', 0.1), ('frame_stack', 4), ('gradient_steps', 1), ('learning_rate', 0.0001), ('learning_starts', 100000), ('n_timesteps', 1000000.0), ('optimize_memory_usage', False), ('policy', 'CnnPolicy'), ('target_update_interval', 1000), ('train_freq', 4), ('normalize', False)]) ``` # Environment Arguments ```python {'render_mode': 'rgb_array'} ```
jordyvl/vit-small_tobacco3482_kd_CEKD_t5.0_a0.5	jordyvl	2023-07-10T21:19:10Z	163	0	transformers	[ "transformers", "pytorch", "vit", "image-classification", "generated_from_trainer", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	image-classification	2023-07-10T20:39:16Z	--- license: apache-2.0 tags: - generated_from_trainer metrics: - accuracy model-index: - name: vit-small_tobacco3482_kd_CEKD_t5.0_a0.5 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # vit-small_tobacco3482_kd_CEKD_t5.0_a0.5 This model is a fine-tuned version of [WinKawaks/vit-small-patch16-224](https://huggingface.co/WinKawaks/vit-small-patch16-224) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.3966 - Accuracy: 0.85 - Brier Loss: 0.2593 - Nll: 0.9223 - F1 Micro: 0.85 - F1 Macro: 0.8392 - Ece: 0.1994 - Aurc: 0.0457 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 100 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| Brier Loss \| Nll \| F1 Micro \| F1 Macro \| Ece \| Aurc \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\|:----------:\|:------:\|:--------:\|:--------:\|:------:\|:------:\| \| No log \| 1.0 \| 7 \| 1.5608 \| 0.225 \| 0.8774 \| 5.2159 \| 0.225 \| 0.1397 \| 0.2725 \| 0.7038 \| \| No log \| 2.0 \| 14 \| 1.2539 \| 0.415 \| 0.7531 \| 3.2673 \| 0.415 \| 0.2434 \| 0.3070 \| 0.4078 \| \| No log \| 3.0 \| 21 \| 0.9055 \| 0.585 \| 0.5971 \| 1.9093 \| 0.585 \| 0.5086 \| 0.3232 \| 0.2172 \| \| No log \| 4.0 \| 28 \| 0.7122 \| 0.72 \| 0.4403 \| 1.7693 \| 0.72 \| 0.6805 \| 0.3073 \| 0.1228 \| \| No log \| 5.0 \| 35 \| 0.6584 \| 0.74 \| 0.3938 \| 1.5810 \| 0.74 \| 0.7214 \| 0.2661 \| 0.1075 \| \| No log \| 6.0 \| 42 \| 0.5711 \| 0.8 \| 0.3462 \| 1.4146 \| 0.8000 \| 0.7524 \| 0.2347 \| 0.0843 \| \| No log \| 7.0 \| 49 \| 0.5521 \| 0.8 \| 0.3199 \| 1.2631 \| 0.8000 \| 0.7867 \| 0.2542 \| 0.0634 \| \| No log \| 8.0 \| 56 \| 0.5603 \| 0.77 \| 0.3381 \| 1.1808 \| 0.7700 \| 0.7680 \| 0.2316 \| 0.0858 \| \| No log \| 9.0 \| 63 \| 0.5209 \| 0.82 \| 0.3062 \| 1.2891 \| 0.82 \| 0.7972 \| 0.2405 \| 0.0792 \| \| No log \| 10.0 \| 70 \| 0.5705 \| 0.78 \| 0.3343 \| 1.5183 \| 0.78 \| 0.7743 \| 0.2264 \| 0.0874 \| \| No log \| 11.0 \| 77 \| 0.5137 \| 0.82 \| 0.3047 \| 1.2987 \| 0.82 \| 0.8096 \| 0.2420 \| 0.0592 \| \| No log \| 12.0 \| 84 \| 0.4664 \| 0.835 \| 0.2929 \| 1.1529 \| 0.835 \| 0.8101 \| 0.2291 \| 0.0753 \| \| No log \| 13.0 \| 91 \| 0.4772 \| 0.82 \| 0.2915 \| 1.2078 \| 0.82 \| 0.8029 \| 0.2131 \| 0.0620 \| \| No log \| 14.0 \| 98 \| 0.4553 \| 0.825 \| 0.2843 \| 1.1312 \| 0.825 \| 0.8112 \| 0.2196 \| 0.0453 \| \| No log \| 15.0 \| 105 \| 0.4574 \| 0.825 \| 0.2821 \| 1.1234 \| 0.825 \| 0.8163 \| 0.2241 \| 0.0554 \| \| No log \| 16.0 \| 112 \| 0.4873 \| 0.8 \| 0.3111 \| 1.2248 \| 0.8000 \| 0.8007 \| 0.1992 \| 0.0657 \| \| No log \| 17.0 \| 119 \| 0.4224 \| 0.855 \| 0.2620 \| 1.1871 \| 0.855 \| 0.8218 \| 0.2337 \| 0.0479 \| \| No log \| 18.0 \| 126 \| 0.4414 \| 0.825 \| 0.2857 \| 1.0723 \| 0.825 \| 0.8227 \| 0.2500 \| 0.0517 \| \| No log \| 19.0 \| 133 \| 0.4232 \| 0.845 \| 0.2737 \| 0.9360 \| 0.845 \| 0.8219 \| 0.2053 \| 0.0543 \| \| No log \| 20.0 \| 140 \| 0.4114 \| 0.845 \| 0.2637 \| 1.0046 \| 0.845 \| 0.8233 \| 0.2144 \| 0.0460 \| \| No log \| 21.0 \| 147 \| 0.4110 \| 0.835 \| 0.2640 \| 0.9853 \| 0.835 \| 0.8160 \| 0.2278 \| 0.0466 \| \| No log \| 22.0 \| 154 \| 0.4163 \| 0.845 \| 0.2678 \| 1.1494 \| 0.845 \| 0.8291 \| 0.2156 \| 0.0458 \| \| No log \| 23.0 \| 161 \| 0.4243 \| 0.835 \| 0.2779 \| 0.9475 \| 0.835 \| 0.8269 \| 0.2420 \| 0.0554 \| \| No log \| 24.0 \| 168 \| 0.4079 \| 0.835 \| 0.2683 \| 0.9249 \| 0.835 \| 0.8044 \| 0.2091 \| 0.0532 \| \| No log \| 25.0 \| 175 \| 0.4027 \| 0.85 \| 0.2621 \| 0.9433 \| 0.85 \| 0.8361 \| 0.2138 \| 0.0530 \| \| No log \| 26.0 \| 182 \| 0.3975 \| 0.855 \| 0.2590 \| 0.9310 \| 0.855 \| 0.8457 \| 0.1932 \| 0.0487 \| \| No log \| 27.0 \| 189 \| 0.4032 \| 0.85 \| 0.2650 \| 0.9823 \| 0.85 \| 0.8425 \| 0.2088 \| 0.0528 \| \| No log \| 28.0 \| 196 \| 0.4037 \| 0.845 \| 0.2650 \| 1.0692 \| 0.845 \| 0.8361 \| 0.2157 \| 0.0496 \| \| No log \| 29.0 \| 203 \| 0.4027 \| 0.845 \| 0.2652 \| 1.0423 \| 0.845 \| 0.8295 \| 0.1917 \| 0.0502 \| \| No log \| 30.0 \| 210 \| 0.3989 \| 0.85 \| 0.2610 \| 1.0633 \| 0.85 \| 0.8392 \| 0.2214 \| 0.0482 \| \| No log \| 31.0 \| 217 \| 0.3985 \| 0.855 \| 0.2609 \| 1.0374 \| 0.855 \| 0.8424 \| 0.2074 \| 0.0472 \| \| No log \| 32.0 \| 224 \| 0.3986 \| 0.85 \| 0.2596 \| 1.0403 \| 0.85 \| 0.8392 \| 0.2184 \| 0.0462 \| \| No log \| 33.0 \| 231 \| 0.3990 \| 0.85 \| 0.2603 \| 1.0369 \| 0.85 \| 0.8392 \| 0.2079 \| 0.0470 \| \| No log \| 34.0 \| 238 \| 0.3982 \| 0.85 \| 0.2600 \| 0.9765 \| 0.85 \| 0.8392 \| 0.2160 \| 0.0467 \| \| No log \| 35.0 \| 245 \| 0.3977 \| 0.85 \| 0.2601 \| 0.9762 \| 0.85 \| 0.8392 \| 0.2108 \| 0.0465 \| \| No log \| 36.0 \| 252 \| 0.3977 \| 0.85 \| 0.2600 \| 1.0372 \| 0.85 \| 0.8392 \| 0.2075 \| 0.0466 \| \| No log \| 37.0 \| 259 \| 0.3972 \| 0.85 \| 0.2597 \| 1.0383 \| 0.85 \| 0.8392 \| 0.2091 \| 0.0465 \| \| No log \| 38.0 \| 266 \| 0.3967 \| 0.85 \| 0.2590 \| 0.9796 \| 0.85 \| 0.8392 \| 0.1987 \| 0.0461 \| \| No log \| 39.0 \| 273 \| 0.3979 \| 0.85 \| 0.2601 \| 1.0390 \| 0.85 \| 0.8392 \| 0.1991 \| 0.0467 \| \| No log \| 40.0 \| 280 \| 0.3976 \| 0.85 \| 0.2601 \| 0.9775 \| 0.85 \| 0.8392 \| 0.2175 \| 0.0465 \| \| No log \| 41.0 \| 287 \| 0.3979 \| 0.85 \| 0.2603 \| 0.9796 \| 0.85 \| 0.8392 \| 0.1930 \| 0.0467 \| \| No log \| 42.0 \| 294 \| 0.3973 \| 0.85 \| 0.2598 \| 0.9746 \| 0.85 \| 0.8392 \| 0.2175 \| 0.0468 \| \| No log \| 43.0 \| 301 \| 0.3972 \| 0.85 \| 0.2598 \| 0.9798 \| 0.85 \| 0.8392 \| 0.1931 \| 0.0466 \| \| No log \| 44.0 \| 308 \| 0.3969 \| 0.85 \| 0.2594 \| 0.9784 \| 0.85 \| 0.8392 \| 0.2094 \| 0.0465 \| \| No log \| 45.0 \| 315 \| 0.3971 \| 0.85 \| 0.2596 \| 0.9847 \| 0.85 \| 0.8392 \| 0.2033 \| 0.0464 \| \| No log \| 46.0 \| 322 \| 0.3969 \| 0.85 \| 0.2597 \| 0.9768 \| 0.85 \| 0.8392 \| 0.2100 \| 0.0465 \| \| No log \| 47.0 \| 329 \| 0.3974 \| 0.85 \| 0.2599 \| 0.9788 \| 0.85 \| 0.8392 \| 0.2090 \| 0.0467 \| \| No log \| 48.0 \| 336 \| 0.3971 \| 0.85 \| 0.2596 \| 0.9797 \| 0.85 \| 0.8392 \| 0.1977 \| 0.0463 \| \| No log \| 49.0 \| 343 \| 0.3972 \| 0.85 \| 0.2597 \| 0.9391 \| 0.85 \| 0.8392 \| 0.1903 \| 0.0465 \| \| No log \| 50.0 \| 350 \| 0.3969 \| 0.85 \| 0.2596 \| 0.9802 \| 0.85 \| 0.8392 \| 0.1985 \| 0.0464 \| \| No log \| 51.0 \| 357 \| 0.3970 \| 0.85 \| 0.2596 \| 0.9795 \| 0.85 \| 0.8392 \| 0.2161 \| 0.0463 \| \| No log \| 52.0 \| 364 \| 0.3973 \| 0.85 \| 0.2597 \| 0.9333 \| 0.85 \| 0.8392 \| 0.1983 \| 0.0462 \| \| No log \| 53.0 \| 371 \| 0.3971 \| 0.85 \| 0.2597 \| 0.9408 \| 0.85 \| 0.8392 \| 0.2022 \| 0.0467 \| \| No log \| 54.0 \| 378 \| 0.3970 \| 0.85 \| 0.2595 \| 0.9371 \| 0.85 \| 0.8392 \| 0.1992 \| 0.0460 \| \| No log \| 55.0 \| 385 \| 0.3970 \| 0.85 \| 0.2596 \| 0.9262 \| 0.85 \| 0.8392 \| 0.1917 \| 0.0464 \| \| No log \| 56.0 \| 392 \| 0.3971 \| 0.85 \| 0.2595 \| 0.9195 \| 0.85 \| 0.8392 \| 0.1927 \| 0.0461 \| \| No log \| 57.0 \| 399 \| 0.3970 \| 0.85 \| 0.2596 \| 0.9789 \| 0.85 \| 0.8392 \| 0.1992 \| 0.0462 \| \| No log \| 58.0 \| 406 \| 0.3968 \| 0.85 \| 0.2594 \| 0.9255 \| 0.85 \| 0.8392 \| 0.1929 \| 0.0462 \| \| No log \| 59.0 \| 413 \| 0.3967 \| 0.85 \| 0.2593 \| 0.9795 \| 0.85 \| 0.8392 \| 0.1996 \| 0.0459 \| \| No log \| 60.0 \| 420 \| 0.3970 \| 0.85 \| 0.2596 \| 0.9787 \| 0.85 \| 0.8392 \| 0.1994 \| 0.0461 \| \| No log \| 61.0 \| 427 \| 0.3967 \| 0.85 \| 0.2594 \| 0.9803 \| 0.85 \| 0.8392 \| 0.2073 \| 0.0461 \| \| No log \| 62.0 \| 434 \| 0.3968 \| 0.85 \| 0.2594 \| 0.9325 \| 0.85 \| 0.8392 \| 0.1996 \| 0.0460 \| \| No log \| 63.0 \| 441 \| 0.3968 \| 0.85 \| 0.2595 \| 0.9276 \| 0.85 \| 0.8392 \| 0.2063 \| 0.0459 \| \| No log \| 64.0 \| 448 \| 0.3968 \| 0.85 \| 0.2595 \| 0.9247 \| 0.85 \| 0.8392 \| 0.1991 \| 0.0461 \| \| No log \| 65.0 \| 455 \| 0.3968 \| 0.85 \| 0.2595 \| 0.9301 \| 0.85 \| 0.8392 \| 0.1989 \| 0.0459 \| \| No log \| 66.0 \| 462 \| 0.3968 \| 0.85 \| 0.2595 \| 0.9310 \| 0.85 \| 0.8392 \| 0.1922 \| 0.0459 \| \| No log \| 67.0 \| 469 \| 0.3968 \| 0.85 \| 0.2595 \| 0.9250 \| 0.85 \| 0.8392 \| 0.2061 \| 0.0459 \| \| No log \| 68.0 \| 476 \| 0.3968 \| 0.85 \| 0.2594 \| 0.9234 \| 0.85 \| 0.8392 \| 0.1994 \| 0.0461 \| \| No log \| 69.0 \| 483 \| 0.3967 \| 0.85 \| 0.2594 \| 0.9257 \| 0.85 \| 0.8392 \| 0.2065 \| 0.0459 \| \| No log \| 70.0 \| 490 \| 0.3967 \| 0.85 \| 0.2594 \| 0.9205 \| 0.85 \| 0.8392 \| 0.1840 \| 0.0459 \| \| No log \| 71.0 \| 497 \| 0.3967 \| 0.85 \| 0.2594 \| 0.9258 \| 0.85 \| 0.8392 \| 0.2017 \| 0.0458 \| \| 0.1666 \| 72.0 \| 504 \| 0.3969 \| 0.85 \| 0.2594 \| 0.9297 \| 0.85 \| 0.8392 \| 0.2017 \| 0.0458 \| \| 0.1666 \| 73.0 \| 511 \| 0.3966 \| 0.85 \| 0.2593 \| 0.9223 \| 0.85 \| 0.8392 \| 0.1920 \| 0.0457 \| \| 0.1666 \| 74.0 \| 518 \| 0.3967 \| 0.85 \| 0.2594 \| 0.9228 \| 0.85 \| 0.8392 \| 0.1920 \| 0.0459 \| \| 0.1666 \| 75.0 \| 525 \| 0.3967 \| 0.85 \| 0.2594 \| 0.9257 \| 0.85 \| 0.8392 \| 0.1919 \| 0.0459 \| \| 0.1666 \| 76.0 \| 532 \| 0.3966 \| 0.85 \| 0.2593 \| 0.9232 \| 0.85 \| 0.8392 \| 0.1994 \| 0.0458 \| \| 0.1666 \| 77.0 \| 539 \| 0.3968 \| 0.85 \| 0.2594 \| 0.9224 \| 0.85 \| 0.8392 \| 0.1920 \| 0.0459 \| \| 0.1666 \| 78.0 \| 546 \| 0.3966 \| 0.85 \| 0.2593 \| 0.9242 \| 0.85 \| 0.8392 \| 0.1918 \| 0.0458 \| \| 0.1666 \| 79.0 \| 553 \| 0.3967 \| 0.85 \| 0.2594 \| 0.9233 \| 0.85 \| 0.8392 \| 0.1920 \| 0.0459 \| \| 0.1666 \| 80.0 \| 560 \| 0.3968 \| 0.85 \| 0.2594 \| 0.9241 \| 0.85 \| 0.8392 \| 0.1919 \| 0.0458 \| \| 0.1666 \| 81.0 \| 567 \| 0.3967 \| 0.85 \| 0.2594 \| 0.9225 \| 0.85 \| 0.8392 \| 0.1918 \| 0.0459 \| \| 0.1666 \| 82.0 \| 574 \| 0.3967 \| 0.85 \| 0.2594 \| 0.9233 \| 0.85 \| 0.8392 \| 0.1919 \| 0.0459 \| \| 0.1666 \| 83.0 \| 581 \| 0.3967 \| 0.85 \| 0.2593 \| 0.9246 \| 0.85 \| 0.8392 \| 0.1919 \| 0.0458 \| \| 0.1666 \| 84.0 \| 588 \| 0.3966 \| 0.85 \| 0.2593 \| 0.9229 \| 0.85 \| 0.8392 \| 0.2017 \| 0.0458 \| \| 0.1666 \| 85.0 \| 595 \| 0.3966 \| 0.85 \| 0.2593 \| 0.9232 \| 0.85 \| 0.8392 \| 0.2017 \| 0.0458 \| \| 0.1666 \| 86.0 \| 602 \| 0.3967 \| 0.85 \| 0.2593 \| 0.9225 \| 0.85 \| 0.8392 \| 0.1920 \| 0.0458 \| \| 0.1666 \| 87.0 \| 609 \| 0.3966 \| 0.85 \| 0.2593 \| 0.9214 \| 0.85 \| 0.8392 \| 0.1999 \| 0.0458 \| \| 0.1666 \| 88.0 \| 616 \| 0.3967 \| 0.85 \| 0.2593 \| 0.9214 \| 0.85 \| 0.8392 \| 0.1920 \| 0.0458 \| \| 0.1666 \| 89.0 \| 623 \| 0.3966 \| 0.85 \| 0.2593 \| 0.9227 \| 0.85 \| 0.8392 \| 0.2097 \| 0.0458 \| \| 0.1666 \| 90.0 \| 630 \| 0.3967 \| 0.85 \| 0.2594 \| 0.9219 \| 0.85 \| 0.8392 \| 0.1919 \| 0.0458 \| \| 0.1666 \| 91.0 \| 637 \| 0.3966 \| 0.85 \| 0.2593 \| 0.9212 \| 0.85 \| 0.8392 \| 0.1994 \| 0.0458 \| \| 0.1666 \| 92.0 \| 644 \| 0.3966 \| 0.85 \| 0.2593 \| 0.9227 \| 0.85 \| 0.8392 \| 0.1919 \| 0.0458 \| \| 0.1666 \| 93.0 \| 651 \| 0.3966 \| 0.85 \| 0.2593 \| 0.9231 \| 0.85 \| 0.8392 \| 0.2017 \| 0.0458 \| \| 0.1666 \| 94.0 \| 658 \| 0.3967 \| 0.85 \| 0.2593 \| 0.9220 \| 0.85 \| 0.8392 \| 0.1919 \| 0.0458 \| \| 0.1666 \| 95.0 \| 665 \| 0.3966 \| 0.85 \| 0.2593 \| 0.9217 \| 0.85 \| 0.8392 \| 0.1920 \| 0.0457 \| \| 0.1666 \| 96.0 \| 672 \| 0.3966 \| 0.85 \| 0.2593 \| 0.9218 \| 0.85 \| 0.8392 \| 0.1920 \| 0.0458 \| \| 0.1666 \| 97.0 \| 679 \| 0.3966 \| 0.85 \| 0.2593 \| 0.9221 \| 0.85 \| 0.8392 \| 0.1920 \| 0.0458 \| \| 0.1666 \| 98.0 \| 686 \| 0.3966 \| 0.85 \| 0.2593 \| 0.9224 \| 0.85 \| 0.8392 \| 0.1920 \| 0.0457 \| \| 0.1666 \| 99.0 \| 693 \| 0.3966 \| 0.85 \| 0.2593 \| 0.9224 \| 0.85 \| 0.8392 \| 0.1994 \| 0.0457 \| \| 0.1666 \| 100.0 \| 700 \| 0.3966 \| 0.85 \| 0.2593 \| 0.9223 \| 0.85 \| 0.8392 \| 0.1994 \| 0.0457 \| ### Framework versions - Transformers 4.26.1 - Pytorch 1.13.1.post200 - Datasets 2.9.0 - Tokenizers 0.13.2
ALazcanoG/nominal-groups-recognition-bert-base-spanish-wwm-cased	ALazcanoG	2023-07-10T21:09:53Z	107	0	transformers	[ "transformers", "tensorboard", "safetensors", "bert", "token-classification", "generated_from_trainer", "es", "dataset:ALazcanoG/spanish_nominal_groups_conll2003", "autotrain_compatible", "endpoints_compatible", "region:us" ]	token-classification	2023-07-07T23:46:21Z	--- language: - es tags: - generated_from_trainer datasets: - ALazcanoG/spanish_nominal_groups_conll2003 model-index: - name: nominal-groups-recognition-bert-base-spanish-wwm-cased results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # nominal-groups-recognition-bert-base-spanish-wwm-cased This model is a fine-tuned version of [dccuchile/bert-base-spanish-wwm-cased](https://huggingface.co/dccuchile/bert-base-spanish-wwm-cased) on the ALazcanoG/spanish_nominal_groups_conll2003 dataset. It achieves the following results on the evaluation set: - Loss: 0.3362 - Body Part Precision: 0.6830 - Body Part Recall: 0.7409 - Body Part F1: 0.7108 - Body Part Number: 413 - Disease Precision: 0.7439 - Disease Recall: 0.7446 - Disease F1: 0.7442 - Disease Number: 975 - Family Member Precision: 0.7941 - Family Member Recall: 0.9 - Family Member F1: 0.8438 - Family Member Number: 30 - Medication Precision: 0.8734 - Medication Recall: 0.7419 - Medication F1: 0.8023 - Medication Number: 93 - Procedure Precision: 0.6190 - Procedure Recall: 0.6270 - Procedure F1: 0.6230 - Procedure Number: 311 - Overall Precision: 0.7144 - Overall Recall: 0.7261 - Overall F1: 0.7202 - Overall Accuracy: 0.9175 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 13 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 5 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Body Part Precision \| Body Part Recall \| Body Part F1 \| Body Part Number \| Disease Precision \| Disease Recall \| Disease F1 \| Disease Number \| Family Member Precision \| Family Member Recall \| Family Member F1 \| Family Member Number \| Medication Precision \| Medication Recall \| Medication F1 \| Medication Number \| Procedure Precision \| Procedure Recall \| Procedure F1 \| Procedure Number \| Overall Precision \| Overall Recall \| Overall F1 \| Overall Accuracy \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:-------------------:\|:----------------:\|:------------:\|:----------------:\|:-----------------:\|:--------------:\|:----------:\|:--------------:\|:-----------------------:\|:--------------------:\|:----------------:\|:--------------------:\|:--------------------:\|:-----------------:\|:-------------:\|:-----------------:\|:-------------------:\|:----------------:\|:------------:\|:----------------:\|:-----------------:\|:--------------:\|:----------:\|:----------------:\| \| 0.4335 \| 1.0 \| 1004 \| 0.3011 \| 0.5944 \| 0.7167 \| 0.6498 \| 413 \| 0.7014 \| 0.7036 \| 0.7025 \| 975 \| 0.8 \| 0.8 \| 0.8000 \| 30 \| 0.7875 \| 0.6774 \| 0.7283 \| 93 \| 0.6007 \| 0.5177 \| 0.5561 \| 311 \| 0.6634 \| 0.6751 \| 0.6692 \| 0.9063 \| \| 0.2379 \| 2.0 \| 2008 \| 0.2920 \| 0.6995 \| 0.7215 \| 0.7104 \| 413 \| 0.7655 \| 0.7097 \| 0.7366 \| 975 \| 0.75 \| 0.8 \| 0.7742 \| 30 \| 0.7667 \| 0.7419 \| 0.7541 \| 93 \| 0.6094 \| 0.6270 \| 0.6181 \| 311 \| 0.7212 \| 0.7014 \| 0.7112 \| 0.9140 \| \| 0.1629 \| 3.0 \| 3012 \| 0.3022 \| 0.6674 \| 0.7530 \| 0.7076 \| 413 \| 0.7286 \| 0.7241 \| 0.7263 \| 975 \| 0.8571 \| 0.8 \| 0.8276 \| 30 \| 0.8519 \| 0.7419 \| 0.7931 \| 93 \| 0.5994 \| 0.6495 \| 0.6235 \| 311 \| 0.6975 \| 0.7201 \| 0.7086 \| 0.9170 \| \| 0.1143 \| 4.0 \| 4016 \| 0.3362 \| 0.6830 \| 0.7409 \| 0.7108 \| 413 \| 0.7439 \| 0.7446 \| 0.7442 \| 975 \| 0.7941 \| 0.9 \| 0.8438 \| 30 \| 0.8734 \| 0.7419 \| 0.8023 \| 93 \| 0.6190 \| 0.6270 \| 0.6230 \| 311 \| 0.7144 \| 0.7261 \| 0.7202 \| 0.9175 \| \| 0.0861 \| 5.0 \| 5020 \| 0.3643 \| 0.6806 \| 0.7482 \| 0.7128 \| 413 \| 0.7428 \| 0.7436 \| 0.7432 \| 975 \| 0.8182 \| 0.9 \| 0.8571 \| 30 \| 0.8831 \| 0.7312 \| 0.8000 \| 93 \| 0.5928 \| 0.6367 \| 0.6140 \| 311 \| 0.7081 \| 0.7283 \| 0.7181 \| 0.9163 \| ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3
ruggedmug/ppo-Huggy	ruggedmug	2023-07-10T21:08:52Z	2	0	ml-agents	[ "ml-agents", "tensorboard", "onnx", "Huggy", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-Huggy", "region:us" ]	reinforcement-learning	2023-07-10T21:08:43Z	--- library_name: ml-agents tags: - Huggy - deep-reinforcement-learning - reinforcement-learning - ML-Agents-Huggy --- # ppo Agent playing Huggy This is a trained model of a ppo agent playing Huggy using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents). ## Usage (with ML-Agents) The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/ We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub: - A short tutorial where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction - A longer tutorial to understand how works ML-Agents: https://huggingface.co/learn/deep-rl-course/unit5/introduction ### Resume the training ```bash mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume ``` ### Watch your Agent play You can watch your agent playing directly in your browser 1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity 2. Step 1: Find your model_id: ruggedmug/ppo-Huggy 3. Step 2: Select your .nn /.onnx file 4. Click on Watch the agent play 👀
skrl/IsaacGymEnvs-FactoryTaskNutBoltScrew-PPO	skrl	2023-07-10T21:06:55Z	0	0	skrl	[ "skrl", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]	reinforcement-learning	2023-07-10T19:47:47Z	--- library_name: skrl tags: - deep-reinforcement-learning - reinforcement-learning - skrl model-index: - name: PPO results: - metrics: - type: mean_reward value: -8.89 +/- 10.3 name: Total reward (mean) task: type: reinforcement-learning name: reinforcement-learning dataset: name: IsaacGymEnvs-FactoryTaskNutBoltScrew type: IsaacGymEnvs-FactoryTaskNutBoltScrew --- <!-- --- torch: -21.51 +/- 14.99 jax: -35.77 +/- 0.39 numpy: -8.89 +/- 10.3 --- --> # IsaacGymEnvs-FactoryTaskNutBoltScrew-PPO Trained agent for [NVIDIA Isaac Gym Preview](https://github.com/NVIDIA-Omniverse/IsaacGymEnvs) environments. - Task: FactoryTaskNutBoltScrew - Agent: [PPO](https://skrl.readthedocs.io/en/latest/api/agents/ppo.html) # Usage (with skrl) Note: Visit the skrl [Examples](https://skrl.readthedocs.io/en/latest/intro/examples.html) section to access the scripts. * PyTorch ```python from skrl.utils.huggingface import download_model_from_huggingface # assuming that there is an agent named `agent` path = download_model_from_huggingface("skrl/IsaacGymEnvs-FactoryTaskNutBoltScrew-PPO", filename="agent.pt") agent.load(path) ``` * JAX ```python from skrl.utils.huggingface import download_model_from_huggingface # assuming that there is an agent named `agent` path = download_model_from_huggingface("skrl/IsaacGymEnvs-FactoryTaskNutBoltScrew-PPO", filename="agent.pickle") agent.load(path) ``` # Hyperparameters Note: Undefined parameters keep their values by default. ```python # https://skrl.readthedocs.io/en/latest/api/agents/ppo.html#configuration-and-hyperparameters cfg = PPO_DEFAULT_CONFIG.copy() cfg["rollouts"] = 128 # memory_size cfg["learning_epochs"] = 8 cfg["mini_batches"] = 32 # 128 * 128 / 512 cfg["discount_factor"] = 0.99 cfg["lambda"] = 0.95 cfg["learning_rate"] = 1e-4 cfg["random_timesteps"] = 0 cfg["learning_starts"] = 0 cfg["grad_norm_clip"] = 0 cfg["ratio_clip"] = 0.2 cfg["value_clip"] = 0.2 cfg["clip_predicted_values"] = True cfg["entropy_loss_scale"] = 0.0 cfg["value_loss_scale"] = 1.0 cfg["kl_threshold"] = 0.016 cfg["rewards_shaper"] = None cfg["state_preprocessor"] = RunningStandardScaler cfg["state_preprocessor_kwargs"] = {"size": env.observation_space, "device": device} cfg["value_preprocessor"] = RunningStandardScaler cfg["value_preprocessor_kwargs"] = {"size": 1, "device": device} ```
WALIDALI/bekinorrev	WALIDALI	2023-07-10T21:00:29Z	5	0	diffusers	[ "diffusers", "safetensors", "text-to-image", "stable-diffusion", "license:creativeml-openrail-m", "autotrain_compatible", "endpoints_compatible", "diffusers:StableDiffusionPipeline", "region:us" ]	text-to-image	2023-07-10T20:57:08Z	--- license: creativeml-openrail-m tags: - text-to-image - stable-diffusion --- ### bekinorrev Dreambooth model trained by WALIDALI with [TheLastBen's fast-DreamBooth](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast-DreamBooth.ipynb) notebook Test the concept via A1111 Colab [fast-Colab-A1111](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast_stable_diffusion_AUTOMATIC1111.ipynb) Sample pictures of this concept:
jordyvl/vit-small_tobacco3482_kd_CEKD_t2.5_a0.9	jordyvl	2023-07-10T20:38:28Z	163	0	transformers	[ "transformers", "pytorch", "vit", "image-classification", "generated_from_trainer", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	image-classification	2023-07-10T19:59:22Z	--- license: apache-2.0 tags: - generated_from_trainer metrics: - accuracy model-index: - name: vit-small_tobacco3482_kd_CEKD_t2.5_a0.9 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # vit-small_tobacco3482_kd_CEKD_t2.5_a0.9 This model is a fine-tuned version of [WinKawaks/vit-small-patch16-224](https://huggingface.co/WinKawaks/vit-small-patch16-224) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.5446 - Accuracy: 0.85 - Brier Loss: 0.2446 - Nll: 1.0816 - F1 Micro: 0.85 - F1 Macro: 0.8348 - Ece: 0.1474 - Aurc: 0.0436 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 100 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| Brier Loss \| Nll \| F1 Micro \| F1 Macro \| Ece \| Aurc \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\|:----------:\|:------:\|:--------:\|:--------:\|:------:\|:------:\| \| No log \| 1.0 \| 7 \| 2.1216 \| 0.215 \| 0.8751 \| 5.2864 \| 0.2150 \| 0.1264 \| 0.2697 \| 0.6907 \| \| No log \| 2.0 \| 14 \| 1.7056 \| 0.405 \| 0.7400 \| 3.5721 \| 0.405 \| 0.2275 \| 0.2995 \| 0.4011 \| \| No log \| 3.0 \| 21 \| 1.1857 \| 0.62 \| 0.5612 \| 2.0143 \| 0.62 \| 0.5712 \| 0.2994 \| 0.2024 \| \| No log \| 4.0 \| 28 \| 0.8767 \| 0.705 \| 0.4085 \| 1.6918 \| 0.705 \| 0.6436 \| 0.2231 \| 0.1152 \| \| No log \| 5.0 \| 35 \| 0.8620 \| 0.72 \| 0.3878 \| 1.7931 \| 0.72 \| 0.7294 \| 0.2233 \| 0.1076 \| \| No log \| 6.0 \| 42 \| 0.7517 \| 0.775 \| 0.3252 \| 1.5573 \| 0.775 \| 0.7600 \| 0.1970 \| 0.0790 \| \| No log \| 7.0 \| 49 \| 0.7280 \| 0.79 \| 0.3175 \| 1.5140 \| 0.79 \| 0.7742 \| 0.1903 \| 0.0826 \| \| No log \| 8.0 \| 56 \| 0.6848 \| 0.8 \| 0.2942 \| 1.4438 \| 0.8000 \| 0.7902 \| 0.1828 \| 0.0866 \| \| No log \| 9.0 \| 63 \| 0.6744 \| 0.81 \| 0.2889 \| 1.4703 \| 0.81 \| 0.7969 \| 0.1989 \| 0.0692 \| \| No log \| 10.0 \| 70 \| 0.8432 \| 0.74 \| 0.3859 \| 1.3134 \| 0.74 \| 0.7206 \| 0.1959 \| 0.1051 \| \| No log \| 11.0 \| 77 \| 0.7424 \| 0.765 \| 0.3294 \| 1.5162 \| 0.765 \| 0.7792 \| 0.2005 \| 0.1048 \| \| No log \| 12.0 \| 84 \| 0.6953 \| 0.79 \| 0.3194 \| 1.2233 \| 0.79 \| 0.7850 \| 0.1800 \| 0.0922 \| \| No log \| 13.0 \| 91 \| 0.5703 \| 0.845 \| 0.2538 \| 1.2355 \| 0.845 \| 0.8372 \| 0.1739 \| 0.0447 \| \| No log \| 14.0 \| 98 \| 0.6439 \| 0.795 \| 0.2924 \| 1.2777 \| 0.795 \| 0.7743 \| 0.1771 \| 0.0534 \| \| No log \| 15.0 \| 105 \| 0.5895 \| 0.825 \| 0.2650 \| 1.2086 \| 0.825 \| 0.8071 \| 0.1665 \| 0.0566 \| \| No log \| 16.0 \| 112 \| 0.5973 \| 0.81 \| 0.2753 \| 1.0959 \| 0.81 \| 0.8013 \| 0.1839 \| 0.0534 \| \| No log \| 17.0 \| 119 \| 0.5825 \| 0.795 \| 0.2722 \| 1.1565 \| 0.795 \| 0.7886 \| 0.1855 \| 0.0534 \| \| No log \| 18.0 \| 126 \| 0.5854 \| 0.845 \| 0.2661 \| 1.1223 \| 0.845 \| 0.8424 \| 0.1981 \| 0.0549 \| \| No log \| 19.0 \| 133 \| 0.5514 \| 0.82 \| 0.2553 \| 0.9585 \| 0.82 \| 0.8150 \| 0.1600 \| 0.0481 \| \| No log \| 20.0 \| 140 \| 0.5600 \| 0.835 \| 0.2443 \| 1.2692 \| 0.835 \| 0.8232 \| 0.1657 \| 0.0469 \| \| No log \| 21.0 \| 147 \| 0.5592 \| 0.845 \| 0.2473 \| 1.1658 \| 0.845 \| 0.8331 \| 0.1683 \| 0.0493 \| \| No log \| 22.0 \| 154 \| 0.5507 \| 0.845 \| 0.2411 \| 1.1403 \| 0.845 \| 0.8311 \| 0.1797 \| 0.0450 \| \| No log \| 23.0 \| 161 \| 0.5305 \| 0.84 \| 0.2361 \| 1.1509 \| 0.8400 \| 0.8287 \| 0.1650 \| 0.0409 \| \| No log \| 24.0 \| 168 \| 0.5352 \| 0.835 \| 0.2378 \| 1.2208 \| 0.835 \| 0.8201 \| 0.1515 \| 0.0420 \| \| No log \| 25.0 \| 175 \| 0.5425 \| 0.845 \| 0.2420 \| 1.1208 \| 0.845 \| 0.8321 \| 0.1776 \| 0.0430 \| \| No log \| 26.0 \| 182 \| 0.5396 \| 0.84 \| 0.2409 \| 1.1230 \| 0.8400 \| 0.8286 \| 0.1647 \| 0.0446 \| \| No log \| 27.0 \| 189 \| 0.5436 \| 0.85 \| 0.2401 \| 1.1179 \| 0.85 \| 0.8387 \| 0.1568 \| 0.0427 \| \| No log \| 28.0 \| 196 \| 0.5373 \| 0.835 \| 0.2415 \| 1.1092 \| 0.835 \| 0.8141 \| 0.1641 \| 0.0427 \| \| No log \| 29.0 \| 203 \| 0.5420 \| 0.845 \| 0.2436 \| 1.0988 \| 0.845 \| 0.8326 \| 0.1551 \| 0.0444 \| \| No log \| 30.0 \| 210 \| 0.5413 \| 0.845 \| 0.2420 \| 1.1064 \| 0.845 \| 0.8312 \| 0.1486 \| 0.0440 \| \| No log \| 31.0 \| 217 \| 0.5411 \| 0.84 \| 0.2418 \| 1.1024 \| 0.8400 \| 0.8286 \| 0.1565 \| 0.0435 \| \| No log \| 32.0 \| 224 \| 0.5426 \| 0.845 \| 0.2429 \| 1.0993 \| 0.845 \| 0.8322 \| 0.1631 \| 0.0433 \| \| No log \| 33.0 \| 231 \| 0.5424 \| 0.85 \| 0.2426 \| 1.0989 \| 0.85 \| 0.8348 \| 0.1615 \| 0.0436 \| \| No log \| 34.0 \| 238 \| 0.5406 \| 0.84 \| 0.2419 \| 1.0979 \| 0.8400 \| 0.8251 \| 0.1640 \| 0.0440 \| \| No log \| 35.0 \| 245 \| 0.5438 \| 0.85 \| 0.2436 \| 1.0953 \| 0.85 \| 0.8348 \| 0.1595 \| 0.0438 \| \| No log \| 36.0 \| 252 \| 0.5429 \| 0.85 \| 0.2429 \| 1.0970 \| 0.85 \| 0.8348 \| 0.1495 \| 0.0433 \| \| No log \| 37.0 \| 259 \| 0.5431 \| 0.85 \| 0.2427 \| 1.0951 \| 0.85 \| 0.8348 \| 0.1617 \| 0.0435 \| \| No log \| 38.0 \| 266 \| 0.5424 \| 0.85 \| 0.2426 \| 1.0959 \| 0.85 \| 0.8348 \| 0.1587 \| 0.0434 \| \| No log \| 39.0 \| 273 \| 0.5428 \| 0.85 \| 0.2432 \| 1.0924 \| 0.85 \| 0.8348 \| 0.1512 \| 0.0433 \| \| No log \| 40.0 \| 280 \| 0.5437 \| 0.85 \| 0.2438 \| 1.0911 \| 0.85 \| 0.8348 \| 0.1726 \| 0.0438 \| \| No log \| 41.0 \| 287 \| 0.5438 \| 0.85 \| 0.2434 \| 1.0925 \| 0.85 \| 0.8348 \| 0.1704 \| 0.0433 \| \| No log \| 42.0 \| 294 \| 0.5428 \| 0.85 \| 0.2432 \| 1.0927 \| 0.85 \| 0.8348 \| 0.1585 \| 0.0436 \| \| No log \| 43.0 \| 301 \| 0.5455 \| 0.85 \| 0.2443 \| 1.0907 \| 0.85 \| 0.8348 \| 0.1756 \| 0.0437 \| \| No log \| 44.0 \| 308 \| 0.5427 \| 0.85 \| 0.2433 \| 1.0908 \| 0.85 \| 0.8348 \| 0.1616 \| 0.0433 \| \| No log \| 45.0 \| 315 \| 0.5456 \| 0.85 \| 0.2446 \| 1.0878 \| 0.85 \| 0.8348 \| 0.1767 \| 0.0437 \| \| No log \| 46.0 \| 322 \| 0.5439 \| 0.85 \| 0.2438 \| 1.0895 \| 0.85 \| 0.8348 \| 0.1503 \| 0.0435 \| \| No log \| 47.0 \| 329 \| 0.5448 \| 0.85 \| 0.2443 \| 1.0891 \| 0.85 \| 0.8348 \| 0.1674 \| 0.0439 \| \| No log \| 48.0 \| 336 \| 0.5440 \| 0.85 \| 0.2437 \| 1.0898 \| 0.85 \| 0.8348 \| 0.1768 \| 0.0437 \| \| No log \| 49.0 \| 343 \| 0.5443 \| 0.85 \| 0.2441 \| 1.0883 \| 0.85 \| 0.8348 \| 0.1433 \| 0.0432 \| \| No log \| 50.0 \| 350 \| 0.5449 \| 0.85 \| 0.2444 \| 1.0877 \| 0.85 \| 0.8348 \| 0.1722 \| 0.0436 \| \| No log \| 51.0 \| 357 \| 0.5443 \| 0.85 \| 0.2442 \| 1.0871 \| 0.85 \| 0.8348 \| 0.1606 \| 0.0434 \| \| No log \| 52.0 \| 364 \| 0.5453 \| 0.85 \| 0.2444 \| 1.0865 \| 0.85 \| 0.8348 \| 0.1729 \| 0.0436 \| \| No log \| 53.0 \| 371 \| 0.5433 \| 0.845 \| 0.2438 \| 1.0873 \| 0.845 \| 0.8287 \| 0.1570 \| 0.0434 \| \| No log \| 54.0 \| 378 \| 0.5453 \| 0.85 \| 0.2447 \| 1.0854 \| 0.85 \| 0.8348 \| 0.1606 \| 0.0435 \| \| No log \| 55.0 \| 385 \| 0.5438 \| 0.85 \| 0.2439 \| 1.0868 \| 0.85 \| 0.8348 \| 0.1721 \| 0.0434 \| \| No log \| 56.0 \| 392 \| 0.5455 \| 0.85 \| 0.2447 \| 1.0853 \| 0.85 \| 0.8348 \| 0.1710 \| 0.0437 \| \| No log \| 57.0 \| 399 \| 0.5435 \| 0.85 \| 0.2439 \| 1.0864 \| 0.85 \| 0.8348 \| 0.1540 \| 0.0434 \| \| No log \| 58.0 \| 406 \| 0.5451 \| 0.85 \| 0.2447 \| 1.0844 \| 0.85 \| 0.8348 \| 0.1636 \| 0.0436 \| \| No log \| 59.0 \| 413 \| 0.5442 \| 0.85 \| 0.2441 \| 1.0858 \| 0.85 \| 0.8348 \| 0.1556 \| 0.0435 \| \| No log \| 60.0 \| 420 \| 0.5453 \| 0.85 \| 0.2447 \| 1.0843 \| 0.85 \| 0.8348 \| 0.1717 \| 0.0437 \| \| No log \| 61.0 \| 427 \| 0.5439 \| 0.85 \| 0.2442 \| 1.0847 \| 0.85 \| 0.8348 \| 0.1541 \| 0.0432 \| \| No log \| 62.0 \| 434 \| 0.5455 \| 0.85 \| 0.2449 \| 1.0839 \| 0.85 \| 0.8348 \| 0.1550 \| 0.0435 \| \| No log \| 63.0 \| 441 \| 0.5446 \| 0.85 \| 0.2445 \| 1.0843 \| 0.85 \| 0.8348 \| 0.1553 \| 0.0435 \| \| No log \| 64.0 \| 448 \| 0.5448 \| 0.85 \| 0.2446 \| 1.0833 \| 0.85 \| 0.8348 \| 0.1634 \| 0.0435 \| \| No log \| 65.0 \| 455 \| 0.5443 \| 0.85 \| 0.2443 \| 1.0847 \| 0.85 \| 0.8348 \| 0.1554 \| 0.0435 \| \| No log \| 66.0 \| 462 \| 0.5448 \| 0.85 \| 0.2447 \| 1.0831 \| 0.85 \| 0.8348 \| 0.1547 \| 0.0436 \| \| No log \| 67.0 \| 469 \| 0.5452 \| 0.85 \| 0.2448 \| 1.0828 \| 0.85 \| 0.8348 \| 0.1563 \| 0.0436 \| \| No log \| 68.0 \| 476 \| 0.5443 \| 0.85 \| 0.2444 \| 1.0834 \| 0.85 \| 0.8348 \| 0.1472 \| 0.0434 \| \| No log \| 69.0 \| 483 \| 0.5447 \| 0.85 \| 0.2445 \| 1.0832 \| 0.85 \| 0.8348 \| 0.1632 \| 0.0434 \| \| No log \| 70.0 \| 490 \| 0.5447 \| 0.85 \| 0.2446 \| 1.0831 \| 0.85 \| 0.8348 \| 0.1559 \| 0.0435 \| \| No log \| 71.0 \| 497 \| 0.5447 \| 0.85 \| 0.2446 \| 1.0829 \| 0.85 \| 0.8348 \| 0.1473 \| 0.0435 \| \| 0.1823 \| 72.0 \| 504 \| 0.5443 \| 0.85 \| 0.2444 \| 1.0828 \| 0.85 \| 0.8348 \| 0.1559 \| 0.0434 \| \| 0.1823 \| 73.0 \| 511 \| 0.5447 \| 0.85 \| 0.2447 \| 1.0825 \| 0.85 \| 0.8348 \| 0.1472 \| 0.0434 \| \| 0.1823 \| 74.0 \| 518 \| 0.5444 \| 0.85 \| 0.2444 \| 1.0829 \| 0.85 \| 0.8348 \| 0.1559 \| 0.0436 \| \| 0.1823 \| 75.0 \| 525 \| 0.5446 \| 0.85 \| 0.2445 \| 1.0829 \| 0.85 \| 0.8348 \| 0.1557 \| 0.0435 \| \| 0.1823 \| 76.0 \| 532 \| 0.5448 \| 0.85 \| 0.2445 \| 1.0825 \| 0.85 \| 0.8348 \| 0.1559 \| 0.0435 \| \| 0.1823 \| 77.0 \| 539 \| 0.5443 \| 0.85 \| 0.2444 \| 1.0827 \| 0.85 \| 0.8348 \| 0.1558 \| 0.0435 \| \| 0.1823 \| 78.0 \| 546 \| 0.5446 \| 0.85 \| 0.2446 \| 1.0824 \| 0.85 \| 0.8348 \| 0.1560 \| 0.0436 \| \| 0.1823 \| 79.0 \| 553 \| 0.5450 \| 0.85 \| 0.2448 \| 1.0821 \| 0.85 \| 0.8348 \| 0.1637 \| 0.0436 \| \| 0.1823 \| 80.0 \| 560 \| 0.5447 \| 0.85 \| 0.2446 \| 1.0823 \| 0.85 \| 0.8348 \| 0.1638 \| 0.0436 \| \| 0.1823 \| 81.0 \| 567 \| 0.5446 \| 0.85 \| 0.2446 \| 1.0820 \| 0.85 \| 0.8348 \| 0.1560 \| 0.0435 \| \| 0.1823 \| 82.0 \| 574 \| 0.5447 \| 0.85 \| 0.2446 \| 1.0819 \| 0.85 \| 0.8348 \| 0.1561 \| 0.0435 \| \| 0.1823 \| 83.0 \| 581 \| 0.5448 \| 0.85 \| 0.2446 \| 1.0822 \| 0.85 \| 0.8348 \| 0.1550 \| 0.0436 \| \| 0.1823 \| 84.0 \| 588 \| 0.5445 \| 0.85 \| 0.2446 \| 1.0819 \| 0.85 \| 0.8348 \| 0.1551 \| 0.0435 \| \| 0.1823 \| 85.0 \| 595 \| 0.5446 \| 0.85 \| 0.2446 \| 1.0818 \| 0.85 \| 0.8348 \| 0.1560 \| 0.0436 \| \| 0.1823 \| 86.0 \| 602 \| 0.5446 \| 0.85 \| 0.2446 \| 1.0818 \| 0.85 \| 0.8348 \| 0.1560 \| 0.0435 \| \| 0.1823 \| 87.0 \| 609 \| 0.5448 \| 0.85 \| 0.2447 \| 1.0820 \| 0.85 \| 0.8348 \| 0.1560 \| 0.0435 \| \| 0.1823 \| 88.0 \| 616 \| 0.5447 \| 0.85 \| 0.2446 \| 1.0819 \| 0.85 \| 0.8348 \| 0.1551 \| 0.0435 \| \| 0.1823 \| 89.0 \| 623 \| 0.5446 \| 0.85 \| 0.2446 \| 1.0819 \| 0.85 \| 0.8348 \| 0.1560 \| 0.0435 \| \| 0.1823 \| 90.0 \| 630 \| 0.5446 \| 0.85 \| 0.2446 \| 1.0816 \| 0.85 \| 0.8348 \| 0.1638 \| 0.0436 \| \| 0.1823 \| 91.0 \| 637 \| 0.5446 \| 0.85 \| 0.2445 \| 1.0817 \| 0.85 \| 0.8348 \| 0.1474 \| 0.0435 \| \| 0.1823 \| 92.0 \| 644 \| 0.5445 \| 0.85 \| 0.2445 \| 1.0818 \| 0.85 \| 0.8348 \| 0.1551 \| 0.0436 \| \| 0.1823 \| 93.0 \| 651 \| 0.5447 \| 0.85 \| 0.2446 \| 1.0818 \| 0.85 \| 0.8348 \| 0.1560 \| 0.0436 \| \| 0.1823 \| 94.0 \| 658 \| 0.5447 \| 0.85 \| 0.2446 \| 1.0816 \| 0.85 \| 0.8348 \| 0.1561 \| 0.0436 \| \| 0.1823 \| 95.0 \| 665 \| 0.5447 \| 0.85 \| 0.2446 \| 1.0816 \| 0.85 \| 0.8348 \| 0.1550 \| 0.0435 \| \| 0.1823 \| 96.0 \| 672 \| 0.5446 \| 0.85 \| 0.2446 \| 1.0816 \| 0.85 \| 0.8348 \| 0.1474 \| 0.0436 \| \| 0.1823 \| 97.0 \| 679 \| 0.5446 \| 0.85 \| 0.2446 \| 1.0817 \| 0.85 \| 0.8348 \| 0.1551 \| 0.0436 \| \| 0.1823 \| 98.0 \| 686 \| 0.5446 \| 0.85 \| 0.2446 \| 1.0817 \| 0.85 \| 0.8348 \| 0.1474 \| 0.0436 \| \| 0.1823 \| 99.0 \| 693 \| 0.5446 \| 0.85 \| 0.2446 \| 1.0816 \| 0.85 \| 0.8348 \| 0.1474 \| 0.0436 \| \| 0.1823 \| 100.0 \| 700 \| 0.5446 \| 0.85 \| 0.2446 \| 1.0816 \| 0.85 \| 0.8348 \| 0.1474 \| 0.0436 \| ### Framework versions - Transformers 4.26.1 - Pytorch 1.13.1.post200 - Datasets 2.9.0 - Tokenizers 0.13.2
skrl/IsaacGymEnvs-FactoryTaskNutBoltPlace-PPO	skrl	2023-07-10T20:15:49Z	0	0	skrl	[ "skrl", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]	reinforcement-learning	2023-07-10T19:47:18Z	--- library_name: skrl tags: - deep-reinforcement-learning - reinforcement-learning - skrl model-index: - name: PPO results: - metrics: - type: mean_reward value: -38.54 +/- 17.49 name: Total reward (mean) task: type: reinforcement-learning name: reinforcement-learning dataset: name: IsaacGymEnvs-FactoryTaskNutBoltPlace type: IsaacGymEnvs-FactoryTaskNutBoltPlace --- <!-- --- torch: -38.54 +/- 17.49 jax: -60.9 +/- 0.84 numpy: -58.9 +/- 1.8 --- --> # IsaacGymEnvs-FactoryTaskNutBoltPlace-PPO Trained agent for [NVIDIA Isaac Gym Preview](https://github.com/NVIDIA-Omniverse/IsaacGymEnvs) environments. - Task: FactoryTaskNutBoltPlace - Agent: [PPO](https://skrl.readthedocs.io/en/latest/api/agents/ppo.html) # Usage (with skrl) Note: Visit the skrl [Examples](https://skrl.readthedocs.io/en/latest/intro/examples.html) section to access the scripts. * PyTorch ```python from skrl.utils.huggingface import download_model_from_huggingface # assuming that there is an agent named `agent` path = download_model_from_huggingface("skrl/IsaacGymEnvs-FactoryTaskNutBoltPlace-PPO", filename="agent.pt") agent.load(path) ``` * JAX ```python from skrl.utils.huggingface import download_model_from_huggingface # assuming that there is an agent named `agent` path = download_model_from_huggingface("skrl/IsaacGymEnvs-FactoryTaskNutBoltPlace-PPO", filename="agent.pickle") agent.load(path) ``` # Hyperparameters Note: Undefined parameters keep their values by default. ```python # https://skrl.readthedocs.io/en/latest/api/agents/ppo.html#configuration-and-hyperparameters cfg = PPO_DEFAULT_CONFIG.copy() cfg["rollouts"] = 120 # memory_size cfg["learning_epochs"] = 8 cfg["mini_batches"] = 30 # 120 * 128 / 512 cfg["discount_factor"] = 0.99 cfg["lambda"] = 0.95 cfg["learning_rate"] = 1e-4 cfg["random_timesteps"] = 0 cfg["learning_starts"] = 0 cfg["grad_norm_clip"] = 0 cfg["ratio_clip"] = 0.2 cfg["value_clip"] = 0.2 cfg["clip_predicted_values"] = True cfg["entropy_loss_scale"] = 0.0 cfg["value_loss_scale"] = 1.0 cfg["kl_threshold"] = 0.016 cfg["rewards_shaper"] = None cfg["state_preprocessor"] = RunningStandardScaler cfg["state_preprocessor_kwargs"] = {"size": env.observation_space, "device": device} cfg["value_preprocessor"] = RunningStandardScaler cfg["value_preprocessor_kwargs"] = {"size": 1, "device": device} ```
jliu596/Reinforce-cartpole	jliu596	2023-07-10T20:13:38Z	0	0	null	[ "CartPole-v1", "reinforce", "reinforcement-learning", "custom-implementation", "deep-rl-class", "model-index", "region:us" ]	reinforcement-learning	2023-07-10T17:26:46Z	--- tags: - CartPole-v1 - reinforce - reinforcement-learning - custom-implementation - deep-rl-class model-index: - name: Reinforce-cartpole results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: CartPole-v1 type: CartPole-v1 metrics: - type: mean_reward value: 500.00 +/- 0.00 name: mean_reward verified: false --- # Reinforce Agent playing CartPole-v1 This is a trained model of a Reinforce agent playing CartPole-v1 . To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
blzncz/segformer-finetuned-4ss1st3r_s3gs3m-10k-steps	blzncz	2023-07-10T20:04:14Z	188	0	transformers	[ "transformers", "pytorch", "segformer", "image-segmentation", "vision", "generated_from_trainer", "license:other", "endpoints_compatible", "region:us" ]	image-segmentation	2023-07-10T10:49:12Z	--- license: other tags: - image-segmentation - vision - generated_from_trainer model-index: - name: segformer-finetuned-4ss1st3r_s3gs3m-10k-steps results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # segformer-finetuned-4ss1st3r_s3gs3m-10k-steps This model is a fine-tuned version of [nvidia/mit-b0](https://huggingface.co/nvidia/mit-b0) on the blzncz/4ss1st3r_s3gs3m dataset. It achieves the following results on the evaluation set: - Loss: 0.3966 - Mean Iou: 0.5967 - Mean Accuracy: 0.8460 - Overall Accuracy: 0.9344 - Accuracy Bg: nan - Accuracy Fallo cohesivo: 0.9510 - Accuracy Fallo malla: 0.8524 - Accuracy Fallo adhesivo: 0.9362 - Accuracy Fallo burbuja: 0.6444 - Iou Bg: 0.0 - Iou Fallo cohesivo: 0.9239 - Iou Fallo malla: 0.7125 - Iou Fallo adhesivo: 0.8335 - Iou Fallo burbuja: 0.5139 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 6e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 1337 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: polynomial - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Mean Iou \| Mean Accuracy \| Overall Accuracy \| Accuracy Bg \| Accuracy Fallo cohesivo \| Accuracy Fallo malla \| Accuracy Fallo adhesivo \| Accuracy Fallo burbuja \| Iou Bg \| Iou Fallo cohesivo \| Iou Fallo malla \| Iou Fallo adhesivo \| Iou Fallo burbuja \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:--------:\|:-------------:\|:----------------:\|:-----------:\|:-----------------------:\|:--------------------:\|:-----------------------:\|:----------------------:\|:------:\|:------------------:\|:---------------:\|:------------------:\|:-----------------:\| \| 0.4796 \| 1.0 \| 133 \| 0.4190 \| 0.4518 \| 0.6689 \| 0.9049 \| nan \| 0.9277 \| 0.8091 \| 0.9381 \| 0.0008 \| 0.0 \| 0.8866 \| 0.6536 \| 0.7179 \| 0.0008 \| \| 0.2665 \| 2.0 \| 266 \| 0.3667 \| 0.5096 \| 0.7283 \| 0.9001 \| nan \| 0.9111 \| 0.8964 \| 0.8731 \| 0.2324 \| 0.0 \| 0.8802 \| 0.6013 \| 0.8467 \| 0.2197 \| \| 0.2158 \| 3.0 \| 399 \| 0.3210 \| 0.5505 \| 0.7807 \| 0.9142 \| nan \| 0.9250 \| 0.8685 \| 0.9414 \| 0.3878 \| 0.0 \| 0.8952 \| 0.6239 \| 0.8901 \| 0.3432 \| \| 0.1737 \| 4.0 \| 532 \| 0.3572 \| 0.5370 \| 0.7851 \| 0.8905 \| nan \| 0.8905 \| 0.9102 \| 0.9121 \| 0.4277 \| 0.0 \| 0.8671 \| 0.5637 \| 0.8777 \| 0.3764 \| \| 0.1602 \| 5.0 \| 665 \| 0.6273 \| 0.4086 \| 0.7632 \| 0.7743 \| nan \| 0.7333 \| 0.9343 \| 0.9685 \| 0.4168 \| 0.0 \| 0.7198 \| 0.4460 \| 0.5324 \| 0.3449 \| \| 0.1707 \| 6.0 \| 798 \| 0.3534 \| 0.5442 \| 0.7953 \| 0.9025 \| nan \| 0.9056 \| 0.9031 \| 0.9234 \| 0.4492 \| 0.0 \| 0.8812 \| 0.5985 \| 0.8629 \| 0.3783 \| \| 0.1376 \| 7.0 \| 931 \| 0.3266 \| 0.5513 \| 0.7634 \| 0.9262 \| nan \| 0.9434 \| 0.8621 \| 0.9288 \| 0.3195 \| 0.0 \| 0.9109 \| 0.6623 \| 0.8866 \| 0.2968 \| \| 0.1346 \| 8.0 \| 1064 \| 0.4976 \| 0.4916 \| 0.7900 \| 0.8396 \| nan \| 0.8190 \| 0.9133 \| 0.9713 \| 0.4565 \| 0.0 \| 0.8041 \| 0.4662 \| 0.7906 \| 0.3970 \| \| 0.1319 \| 9.0 \| 1197 \| 0.3650 \| 0.5652 \| 0.8404 \| 0.9043 \| nan \| 0.9053 \| 0.8856 \| 0.9593 \| 0.6113 \| 0.0 \| 0.8829 \| 0.5992 \| 0.8734 \| 0.4706 \| \| 0.1229 \| 10.0 \| 1330 \| 0.3201 \| 0.5666 \| 0.7963 \| 0.9299 \| nan \| 0.9435 \| 0.8764 \| 0.9389 \| 0.4265 \| 0.0 \| 0.9171 \| 0.6896 \| 0.8499 \| 0.3763 \| \| 0.1142 \| 11.0 \| 1463 \| 0.3824 \| 0.5576 \| 0.8204 \| 0.9020 \| nan \| 0.8988 \| 0.9231 \| 0.9456 \| 0.5142 \| 0.0 \| 0.8795 \| 0.6001 \| 0.8711 \| 0.4374 \| \| 0.0983 \| 12.0 \| 1596 \| 0.3133 \| 0.5812 \| 0.8297 \| 0.9293 \| nan \| 0.9354 \| 0.9046 \| 0.9558 \| 0.5229 \| 0.0 \| 0.9136 \| 0.6969 \| 0.8618 \| 0.4335 \| \| 0.1058 \| 13.0 \| 1729 \| 0.2965 \| 0.5860 \| 0.8250 \| 0.9364 \| nan \| 0.9528 \| 0.8496 \| 0.9598 \| 0.5378 \| 0.0 \| 0.9253 \| 0.7162 \| 0.8502 \| 0.4383 \| \| 0.1052 \| 14.0 \| 1862 \| 0.2839 \| 0.6064 \| 0.8275 \| 0.9460 \| nan \| 0.9674 \| 0.8517 \| 0.9290 \| 0.5621 \| 0.0 \| 0.9355 \| 0.7492 \| 0.8930 \| 0.4540 \| \| 0.0911 \| 15.0 \| 1995 \| 0.3245 \| 0.5853 \| 0.8116 \| 0.9368 \| nan \| 0.9565 \| 0.8504 \| 0.9298 \| 0.5099 \| 0.0 \| 0.9243 \| 0.7171 \| 0.8534 \| 0.4318 \| \| 0.0889 \| 16.0 \| 2128 \| 0.3094 \| 0.5969 \| 0.8225 \| 0.9422 \| nan \| 0.9615 \| 0.8559 \| 0.9376 \| 0.5351 \| 0.0 \| 0.9313 \| 0.7353 \| 0.8726 \| 0.4451 \| \| 0.0827 \| 17.0 \| 2261 \| 0.4776 \| 0.5187 \| 0.8195 \| 0.8547 \| nan \| 0.8390 \| 0.9163 \| 0.9440 \| 0.5786 \| 0.0 \| 0.8207 \| 0.4920 \| 0.8216 \| 0.4590 \| \| 0.0939 \| 18.0 \| 2394 \| 0.3923 \| 0.5364 \| 0.8375 \| 0.8948 \| nan \| 0.8950 \| 0.8831 \| 0.9437 \| 0.6282 \| 0.0 \| 0.8746 \| 0.6268 \| 0.7090 \| 0.4717 \| \| 0.0799 \| 19.0 \| 2527 \| 0.3560 \| 0.5776 \| 0.8252 \| 0.9254 \| nan \| 0.9337 \| 0.8933 \| 0.9409 \| 0.5331 \| 0.0 \| 0.9096 \| 0.6846 \| 0.8519 \| 0.4422 \| \| 0.075 \| 20.0 \| 2660 \| 0.3803 \| 0.5796 \| 0.8338 \| 0.9194 \| nan \| 0.9249 \| 0.9078 \| 0.9238 \| 0.5788 \| 0.0 \| 0.9032 \| 0.6459 \| 0.8821 \| 0.4670 \| \| 0.0844 \| 21.0 \| 2793 \| 0.2885 \| 0.6170 \| 0.8334 \| 0.9507 \| nan \| 0.9757 \| 0.8296 \| 0.9390 \| 0.5892 \| 0.0 \| 0.9412 \| 0.7654 \| 0.8933 \| 0.4852 \| \| 0.0746 \| 22.0 \| 2926 \| 0.3222 \| 0.5831 \| 0.8160 \| 0.9331 \| nan \| 0.9481 \| 0.8685 \| 0.9370 \| 0.5105 \| 0.0 \| 0.9193 \| 0.7032 \| 0.8716 \| 0.4215 \| \| 0.072 \| 23.0 \| 3059 \| 0.3481 \| 0.5878 \| 0.8336 \| 0.9266 \| nan \| 0.9357 \| 0.8952 \| 0.9271 \| 0.5764 \| 0.0 \| 0.9123 \| 0.6824 \| 0.8720 \| 0.4725 \| \| 0.0735 \| 24.0 \| 3192 \| 0.3196 \| 0.5974 \| 0.8403 \| 0.9353 \| nan \| 0.9496 \| 0.8666 \| 0.9430 \| 0.6018 \| 0.0 \| 0.9225 \| 0.7165 \| 0.8649 \| 0.4832 \| \| 0.0674 \| 25.0 \| 3325 \| 0.3407 \| 0.5927 \| 0.8435 \| 0.9282 \| nan \| 0.9401 \| 0.8786 \| 0.9246 \| 0.6304 \| 0.0 \| 0.9141 \| 0.6844 \| 0.8696 \| 0.4953 \| \| 0.0712 \| 26.0 \| 3458 \| 0.3356 \| 0.5906 \| 0.8420 \| 0.9301 \| nan \| 0.9405 \| 0.8895 \| 0.9299 \| 0.6080 \| 0.0 \| 0.9160 \| 0.6905 \| 0.8743 \| 0.4722 \| \| 0.072 \| 27.0 \| 3591 \| 0.3491 \| 0.5833 \| 0.8372 \| 0.9286 \| nan \| 0.9415 \| 0.8636 \| 0.9425 \| 0.6012 \| 0.0 \| 0.9161 \| 0.6966 \| 0.8246 \| 0.4790 \| \| 0.0641 \| 28.0 \| 3724 \| 0.3130 \| 0.6087 \| 0.8422 \| 0.9473 \| nan \| 0.9697 \| 0.8357 \| 0.9427 \| 0.6208 \| 0.0 \| 0.9386 \| 0.7613 \| 0.8599 \| 0.4837 \| \| 0.0597 \| 29.0 \| 3857 \| 0.3828 \| 0.5666 \| 0.8394 \| 0.9107 \| nan \| 0.9141 \| 0.8934 \| 0.9411 \| 0.6092 \| 0.0 \| 0.8924 \| 0.6327 \| 0.8343 \| 0.4735 \| \| 0.0648 \| 30.0 \| 3990 \| 0.3435 \| 0.6001 \| 0.8372 \| 0.9403 \| nan \| 0.9569 \| 0.8708 \| 0.9276 \| 0.5935 \| 0.0 \| 0.9292 \| 0.7312 \| 0.8779 \| 0.4623 \| \| 0.0618 \| 31.0 \| 4123 \| 0.3531 \| 0.5963 \| 0.8521 \| 0.9303 \| nan \| 0.9450 \| 0.8621 \| 0.9240 \| 0.6773 \| 0.0 \| 0.9179 \| 0.6842 \| 0.8730 \| 0.5063 \| \| 0.0556 \| 32.0 \| 4256 \| 0.3307 \| 0.6037 \| 0.8417 \| 0.9401 \| nan \| 0.9576 \| 0.8637 \| 0.9271 \| 0.6183 \| 0.0 \| 0.9298 \| 0.7274 \| 0.8637 \| 0.4974 \| \| 0.0616 \| 33.0 \| 4389 \| 0.3510 \| 0.5911 \| 0.8347 \| 0.9298 \| nan \| 0.9424 \| 0.8714 \| 0.9388 \| 0.5863 \| 0.0 \| 0.9158 \| 0.6914 \| 0.8745 \| 0.4740 \| \| 0.0603 \| 34.0 \| 4522 \| 0.3467 \| 0.6022 \| 0.8544 \| 0.9334 \| nan \| 0.9487 \| 0.8610 \| 0.9274 \| 0.6807 \| 0.0 \| 0.9211 \| 0.7029 \| 0.8738 \| 0.5130 \| \| 0.0587 \| 35.0 \| 4655 \| 0.3574 \| 0.6017 \| 0.8407 \| 0.9379 \| nan \| 0.9555 \| 0.8541 \| 0.9346 \| 0.6187 \| 0.0 \| 0.9269 \| 0.7228 \| 0.8627 \| 0.4962 \| \| 0.0557 \| 36.0 \| 4788 \| 0.3871 \| 0.5720 \| 0.8334 \| 0.9178 \| nan \| 0.9317 \| 0.8416 \| 0.9374 \| 0.6228 \| 0.0 \| 0.9051 \| 0.6479 \| 0.8160 \| 0.4911 \| \| 0.0567 \| 37.0 \| 4921 \| 0.4425 \| 0.5656 \| 0.8282 \| 0.9070 \| nan \| 0.9114 \| 0.8922 \| 0.9244 \| 0.5848 \| 0.0 \| 0.8889 \| 0.6100 \| 0.8575 \| 0.4718 \| \| 0.0537 \| 38.0 \| 5054 \| 0.3512 \| 0.5946 \| 0.8392 \| 0.9317 \| nan \| 0.9463 \| 0.8649 \| 0.9314 \| 0.6142 \| 0.0 \| 0.9187 \| 0.6984 \| 0.8637 \| 0.4921 \| \| 0.0559 \| 39.0 \| 5187 \| 0.3676 \| 0.5931 \| 0.8437 \| 0.9273 \| nan \| 0.9381 \| 0.8798 \| 0.9323 \| 0.6247 \| 0.0 \| 0.9129 \| 0.6779 \| 0.8786 \| 0.4959 \| \| 0.0502 \| 40.0 \| 5320 \| 0.4149 \| 0.5518 \| 0.8381 \| 0.8984 \| nan \| 0.9011 \| 0.8773 \| 0.9368 \| 0.6370 \| 0.0 \| 0.8793 \| 0.6069 \| 0.7741 \| 0.4989 \| \| 0.0559 \| 41.0 \| 5453 \| 0.4042 \| 0.5694 \| 0.8342 \| 0.9130 \| nan \| 0.9206 \| 0.8721 \| 0.9400 \| 0.6041 \| 0.0 \| 0.8971 \| 0.6319 \| 0.8286 \| 0.4896 \| \| 0.0523 \| 42.0 \| 5586 \| 0.3669 \| 0.5903 \| 0.8462 \| 0.9286 \| nan \| 0.9414 \| 0.8676 \| 0.9337 \| 0.6421 \| 0.0 \| 0.9162 \| 0.6883 \| 0.8370 \| 0.5102 \| \| 0.0525 \| 43.0 \| 5719 \| 0.4140 \| 0.5704 \| 0.8531 \| 0.9081 \| nan \| 0.9110 \| 0.8867 \| 0.9417 \| 0.6729 \| 0.0 \| 0.8898 \| 0.6220 \| 0.8366 \| 0.5035 \| \| 0.0508 \| 44.0 \| 5852 \| 0.3965 \| 0.5714 \| 0.8396 \| 0.9141 \| nan \| 0.9227 \| 0.8800 \| 0.9147 \| 0.6409 \| 0.0 \| 0.8989 \| 0.6513 \| 0.8007 \| 0.5060 \| \| 0.0507 \| 45.0 \| 5985 \| 0.3793 \| 0.5817 \| 0.8392 \| 0.9196 \| nan \| 0.9272 \| 0.8932 \| 0.9214 \| 0.6148 \| 0.0 \| 0.9042 \| 0.6627 \| 0.8407 \| 0.5011 \| \| 0.0494 \| 46.0 \| 6118 \| 0.3500 \| 0.6020 \| 0.8426 \| 0.9363 \| nan \| 0.9524 \| 0.8619 \| 0.9322 \| 0.6240 \| 0.0 \| 0.9247 \| 0.7142 \| 0.8653 \| 0.5058 \| \| 0.0462 \| 47.0 \| 6251 \| 0.3524 \| 0.6031 \| 0.8435 \| 0.9388 \| nan \| 0.9545 \| 0.8668 \| 0.9364 \| 0.6163 \| 0.0 \| 0.9274 \| 0.7269 \| 0.8703 \| 0.4909 \| \| 0.0486 \| 48.0 \| 6384 \| 0.3876 \| 0.5902 \| 0.8397 \| 0.9308 \| nan \| 0.9479 \| 0.8557 \| 0.9161 \| 0.6392 \| 0.0 \| 0.9203 \| 0.6928 \| 0.8334 \| 0.5046 \| \| 0.0461 \| 49.0 \| 6517 \| 0.3674 \| 0.5933 \| 0.8409 \| 0.9326 \| nan \| 0.9482 \| 0.8622 \| 0.9258 \| 0.6274 \| 0.0 \| 0.9214 \| 0.7053 \| 0.8367 \| 0.5030 \| \| 0.0497 \| 50.0 \| 6650 \| 0.4018 \| 0.5838 \| 0.8374 \| 0.9246 \| nan \| 0.9390 \| 0.8519 \| 0.9341 \| 0.6244 \| 0.0 \| 0.9102 \| 0.6733 \| 0.8361 \| 0.4992 \| \| 0.0491 \| 51.0 \| 6783 \| 0.4036 \| 0.5824 \| 0.8513 \| 0.9198 \| nan \| 0.9272 \| 0.8805 \| 0.9403 \| 0.6573 \| 0.0 \| 0.9037 \| 0.6712 \| 0.8169 \| 0.5203 \| \| 0.046 \| 52.0 \| 6916 \| 0.3913 \| 0.5820 \| 0.8395 \| 0.9243 \| nan \| 0.9347 \| 0.8771 \| 0.9336 \| 0.6126 \| 0.0 \| 0.9105 \| 0.6792 \| 0.8244 \| 0.4960 \| \| 0.0488 \| 53.0 \| 7049 \| 0.3441 \| 0.6010 \| 0.8504 \| 0.9362 \| nan \| 0.9523 \| 0.8521 \| 0.9457 \| 0.6517 \| 0.0 \| 0.9250 \| 0.7225 \| 0.8496 \| 0.5081 \| \| 0.0458 \| 54.0 \| 7182 \| 0.3784 \| 0.5977 \| 0.8382 \| 0.9378 \| nan \| 0.9603 \| 0.8212 \| 0.9375 \| 0.6337 \| 0.0 \| 0.9286 \| 0.7157 \| 0.8387 \| 0.5053 \| \| 0.0449 \| 55.0 \| 7315 \| 0.3506 \| 0.6068 \| 0.8493 \| 0.9404 \| nan \| 0.9579 \| 0.8554 \| 0.9385 \| 0.6456 \| 0.0 \| 0.9300 \| 0.7357 \| 0.8549 \| 0.5132 \| \| 0.0482 \| 56.0 \| 7448 \| 0.4005 \| 0.5819 \| 0.8414 \| 0.9249 \| nan \| 0.9374 \| 0.8642 \| 0.9337 \| 0.6303 \| 0.0 \| 0.9119 \| 0.6831 \| 0.8139 \| 0.5006 \| \| 0.0434 \| 57.0 \| 7581 \| 0.3749 \| 0.5914 \| 0.8465 \| 0.9294 \| nan \| 0.9423 \| 0.8675 \| 0.9339 \| 0.6421 \| 0.0 \| 0.9171 \| 0.6999 \| 0.8265 \| 0.5134 \| \| 0.0435 \| 58.0 \| 7714 \| 0.4195 \| 0.5722 \| 0.8400 \| 0.9172 \| nan \| 0.9274 \| 0.8700 \| 0.9234 \| 0.6392 \| 0.0 \| 0.9025 \| 0.6588 \| 0.7954 \| 0.5044 \| \| 0.0442 \| 59.0 \| 7847 \| 0.3975 \| 0.5828 \| 0.8407 \| 0.9257 \| nan \| 0.9398 \| 0.8563 \| 0.9312 \| 0.6356 \| 0.0 \| 0.9134 \| 0.6866 \| 0.8103 \| 0.5037 \| \| 0.0442 \| 60.0 \| 7980 \| 0.3845 \| 0.5929 \| 0.8457 \| 0.9315 \| nan \| 0.9459 \| 0.8603 \| 0.9363 \| 0.6404 \| 0.0 \| 0.9193 \| 0.7041 \| 0.8308 \| 0.5103 \| \| 0.0422 \| 61.0 \| 8113 \| 0.3875 \| 0.5963 \| 0.8465 \| 0.9338 \| nan \| 0.9489 \| 0.8616 \| 0.9340 \| 0.6413 \| 0.0 \| 0.9226 \| 0.7135 \| 0.8381 \| 0.5072 \| \| 0.0436 \| 62.0 \| 8246 \| 0.3859 \| 0.6022 \| 0.8497 \| 0.9385 \| nan \| 0.9566 \| 0.8477 \| 0.9382 \| 0.6562 \| 0.0 \| 0.9289 \| 0.7300 \| 0.8376 \| 0.5147 \| \| 0.0429 \| 63.0 \| 8379 \| 0.3857 \| 0.5956 \| 0.8425 \| 0.9357 \| nan \| 0.9534 \| 0.8481 \| 0.9357 \| 0.6327 \| 0.0 \| 0.9249 \| 0.7233 \| 0.8283 \| 0.5016 \| \| 0.0446 \| 64.0 \| 8512 \| 0.3778 \| 0.5976 \| 0.8495 \| 0.9343 \| nan \| 0.9492 \| 0.8602 \| 0.9399 \| 0.6489 \| 0.0 \| 0.9232 \| 0.7191 \| 0.8305 \| 0.5153 \| \| 0.0429 \| 65.0 \| 8645 \| 0.3889 \| 0.5948 \| 0.8478 \| 0.9330 \| nan \| 0.9490 \| 0.8548 \| 0.9325 \| 0.6549 \| 0.0 \| 0.9225 \| 0.7075 \| 0.8271 \| 0.5167 \| \| 0.0454 \| 66.0 \| 8778 \| 0.3915 \| 0.5941 \| 0.8470 \| 0.9329 \| nan \| 0.9490 \| 0.8571 \| 0.9271 \| 0.6547 \| 0.0 \| 0.9221 \| 0.7087 \| 0.8278 \| 0.5117 \| \| 0.0427 \| 67.0 \| 8911 \| 0.3924 \| 0.5967 \| 0.8455 \| 0.9349 \| nan \| 0.9518 \| 0.8520 \| 0.9350 \| 0.6433 \| 0.0 \| 0.9247 \| 0.7167 \| 0.8290 \| 0.5133 \| \| 0.0425 \| 68.0 \| 9044 \| 0.3990 \| 0.5992 \| 0.8491 \| 0.9358 \| nan \| 0.9524 \| 0.8545 \| 0.9355 \| 0.6541 \| 0.0 \| 0.9250 \| 0.7187 \| 0.8387 \| 0.5136 \| \| 0.0429 \| 69.0 \| 9177 \| 0.3911 \| 0.5909 \| 0.8499 \| 0.9303 \| nan \| 0.9451 \| 0.8532 \| 0.9394 \| 0.6619 \| 0.0 \| 0.9192 \| 0.7029 \| 0.8178 \| 0.5146 \| \| 0.0465 \| 70.0 \| 9310 \| 0.3840 \| 0.5977 \| 0.8481 \| 0.9332 \| nan \| 0.9473 \| 0.8700 \| 0.9278 \| 0.6473 \| 0.0 \| 0.9215 \| 0.7079 \| 0.8480 \| 0.5110 \| \| 0.0436 \| 71.0 \| 9443 \| 0.3862 \| 0.5974 \| 0.8456 \| 0.9351 \| nan \| 0.9518 \| 0.8534 \| 0.9359 \| 0.6413 \| 0.0 \| 0.9248 \| 0.7162 \| 0.8338 \| 0.5124 \| \| 0.0435 \| 72.0 \| 9576 \| 0.3926 \| 0.5952 \| 0.8448 \| 0.9328 \| nan \| 0.9484 \| 0.8585 \| 0.9318 \| 0.6405 \| 0.0 \| 0.9217 \| 0.7073 \| 0.8386 \| 0.5084 \| \| 0.0421 \| 73.0 \| 9709 \| 0.3961 \| 0.5984 \| 0.8467 \| 0.9348 \| nan \| 0.9513 \| 0.8564 \| 0.9309 \| 0.6482 \| 0.0 \| 0.9243 \| 0.7119 \| 0.8414 \| 0.5143 \| \| 0.0409 \| 74.0 \| 9842 \| 0.3973 \| 0.5982 \| 0.8494 \| 0.9341 \| nan \| 0.9498 \| 0.8596 \| 0.9306 \| 0.6578 \| 0.0 \| 0.9233 \| 0.7094 \| 0.8401 \| 0.5181 \| \| 0.041 \| 75.0 \| 9975 \| 0.3898 \| 0.5963 \| 0.8476 \| 0.9335 \| nan \| 0.9493 \| 0.8561 \| 0.9354 \| 0.6498 \| 0.0 \| 0.9227 \| 0.7108 \| 0.8329 \| 0.5153 \| \| 0.0436 \| 75.19 \| 10000 \| 0.3966 \| 0.5967 \| 0.8460 \| 0.9344 \| nan \| 0.9510 \| 0.8524 \| 0.9362 \| 0.6444 \| 0.0 \| 0.9239 \| 0.7125 \| 0.8335 \| 0.5139 \| ### Framework versions - Transformers 4.31.0.dev0 - Pytorch 2.0.1+cpu - Datasets 2.13.1 - Tokenizers 0.13.3
NasimB/gpt2-cocnat-aochildes-mod-sub-length-10k	NasimB	2023-07-10T19:27:45Z	16	0	transformers	[ "transformers", "pytorch", "gpt2", "text-generation", "generated_from_trainer", "dataset:generator", "license:mit", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2023-07-10T17:32:01Z	--- license: mit tags: - generated_from_trainer datasets: - generator model-index: - name: gpt2-cocnat-aochildes-mod-sub-length-10k results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # gpt2-cocnat-aochildes-mod-sub-length-10k This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the generator dataset. It achieves the following results on the evaluation set: - Loss: 4.3425 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 64 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_steps: 1000 - num_epochs: 6 - mixed_precision_training: Native AMP ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-----:\|:-----:\|:---------------:\| \| 6.6933 \| 0.29 \| 500 \| 5.6341 \| \| 5.3469 \| 0.59 \| 1000 \| 5.1996 \| \| 4.9864 \| 0.88 \| 1500 \| 4.9580 \| \| 4.7189 \| 1.18 \| 2000 \| 4.8083 \| \| 4.5609 \| 1.47 \| 2500 \| 4.6850 \| \| 4.4523 \| 1.77 \| 3000 \| 4.5821 \| \| 4.317 \| 2.06 \| 3500 \| 4.5146 \| \| 4.1329 \| 2.35 \| 4000 \| 4.4652 \| \| 4.1086 \| 2.65 \| 4500 \| 4.4071 \| \| 4.0635 \| 2.94 \| 5000 \| 4.3601 \| \| 3.8482 \| 3.24 \| 5500 \| 4.3553 \| \| 3.8055 \| 3.53 \| 6000 \| 4.3282 \| \| 3.7859 \| 3.83 \| 6500 \| 4.2926 \| \| 3.6619 \| 4.12 \| 7000 \| 4.2970 \| \| 3.5196 \| 4.41 \| 7500 \| 4.2933 \| \| 3.5139 \| 4.71 \| 8000 \| 4.2857 \| \| 3.4905 \| 5.0 \| 8500 \| 4.2710 \| \| 3.3203 \| 5.3 \| 9000 \| 4.2871 \| \| 3.322 \| 5.59 \| 9500 \| 4.2867 \| \| 3.3172 \| 5.89 \| 10000 \| 4.2863 \| ### Framework versions - Transformers 4.26.1 - Pytorch 1.11.0+cu113 - Datasets 2.13.0 - Tokenizers 0.13.3
simonestradasch/COMPner2-bert-base-spanish-wwm-cased	simonestradasch	2023-07-10T19:24:22Z	109	0	transformers	[ "transformers", "tensorboard", "safetensors", "bert", "token-classification", "generated_from_trainer", "es", "dataset:simonestradasch/NERcomp2", "autotrain_compatible", "endpoints_compatible", "region:us" ]	token-classification	2023-07-10T18:55:43Z	--- language: - es tags: - generated_from_trainer datasets: - simonestradasch/NERcomp2 model-index: - name: COMPner2-bert-base-spanish-wwm-cased results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # COMPner2-bert-base-spanish-wwm-cased This model is a fine-tuned version of [dccuchile/bert-base-spanish-wwm-cased](https://huggingface.co/dccuchile/bert-base-spanish-wwm-cased) on the simonestradasch/NERcomp2 dataset. It achieves the following results on the evaluation set: - Loss: 0.2843 - Body Part Precision: 0.6644 - Body Part Recall: 0.7143 - Body Part F1: 0.6884 - Body Part Number: 413 - Disease Precision: 0.7251 - Disease Recall: 0.7303 - Disease F1: 0.7276 - Disease Number: 975 - Family Member Precision: 0.8065 - Family Member Recall: 0.8333 - Family Member F1: 0.8197 - Family Member Number: 30 - Medication Precision: 0.7778 - Medication Recall: 0.6774 - Medication F1: 0.7241 - Medication Number: 93 - Procedure Precision: 0.5763 - Procedure Recall: 0.5949 - Procedure F1: 0.5854 - Procedure Number: 311 - Overall Precision: 0.6885 - Overall Recall: 0.7025 - Overall F1: 0.6955 - Overall Accuracy: 0.9146 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 13 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 2 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Body Part Precision \| Body Part Recall \| Body Part F1 \| Body Part Number \| Disease Precision \| Disease Recall \| Disease F1 \| Disease Number \| Family Member Precision \| Family Member Recall \| Family Member F1 \| Family Member Number \| Medication Precision \| Medication Recall \| Medication F1 \| Medication Number \| Procedure Precision \| Procedure Recall \| Procedure F1 \| Procedure Number \| Overall Precision \| Overall Recall \| Overall F1 \| Overall Accuracy \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:-------------------:\|:----------------:\|:------------:\|:----------------:\|:-----------------:\|:--------------:\|:----------:\|:--------------:\|:-----------------------:\|:--------------------:\|:----------------:\|:--------------------:\|:--------------------:\|:-----------------:\|:-------------:\|:-----------------:\|:-------------------:\|:----------------:\|:------------:\|:----------------:\|:-----------------:\|:--------------:\|:----------:\|:----------------:\| \| 0.4243 \| 1.0 \| 1004 \| 0.2935 \| 0.5910 \| 0.6998 \| 0.6408 \| 413 \| 0.6784 \| 0.6944 \| 0.6863 \| 975 \| 0.8 \| 0.8 \| 0.8000 \| 30 \| 0.6882 \| 0.6882 \| 0.6882 \| 93 \| 0.6050 \| 0.5466 \| 0.5743 \| 311 \| 0.6473 \| 0.6718 \| 0.6593 \| 0.9052 \| \| 0.2348 \| 2.0 \| 2008 \| 0.2843 \| 0.6644 \| 0.7143 \| 0.6884 \| 413 \| 0.7251 \| 0.7303 \| 0.7276 \| 975 \| 0.8065 \| 0.8333 \| 0.8197 \| 30 \| 0.7778 \| 0.6774 \| 0.7241 \| 93 \| 0.5763 \| 0.5949 \| 0.5854 \| 311 \| 0.6885 \| 0.7025 \| 0.6955 \| 0.9146 \| ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3
grace-pro/afriberta-small-finetuned-hausa	grace-pro	2023-07-10T19:21:16Z	105	0	transformers	[ "transformers", "pytorch", "tensorboard", "xlm-roberta", "token-classification", "generated_from_trainer", "autotrain_compatible", "endpoints_compatible", "region:us" ]	token-classification	2023-07-10T18:52:05Z	--- tags: - generated_from_trainer metrics: - precision - recall - f1 - accuracy model-index: - name: afriberta-small-finetuned-hausa results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # afriberta-small-finetuned-hausa This model is a fine-tuned version of [castorini/afriberta_small](https://huggingface.co/castorini/afriberta_small) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.1444 - Precision: 0.6873 - Recall: 0.4713 - F1: 0.5592 - Accuracy: 0.9618 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 5 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Precision \| Recall \| F1 \| Accuracy \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:---------:\|:------:\|:------:\|:--------:\| \| 0.1493 \| 1.0 \| 2624 \| 0.1382 \| 0.6423 \| 0.3968 \| 0.4905 \| 0.9572 \| \| 0.1259 \| 2.0 \| 5248 \| 0.1319 \| 0.6734 \| 0.4415 \| 0.5333 \| 0.9603 \| \| 0.106 \| 3.0 \| 7872 \| 0.1385 \| 0.6908 \| 0.4502 \| 0.5452 \| 0.9611 \| \| 0.0949 \| 4.0 \| 10496 \| 0.1377 \| 0.6752 \| 0.4759 \| 0.5583 \| 0.9613 \| \| 0.086 \| 5.0 \| 13120 \| 0.1444 \| 0.6873 \| 0.4713 \| 0.5592 \| 0.9618 \| ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3
jordyvl/vit-small_tobacco3482_kd_CEKD_t2.5_a0.5	jordyvl	2023-07-10T19:16:42Z	166	0	transformers	[ "transformers", "pytorch", "vit", "image-classification", "generated_from_trainer", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	image-classification	2023-07-10T18:37:44Z	--- license: apache-2.0 tags: - generated_from_trainer metrics: - accuracy model-index: - name: vit-small_tobacco3482_kd_CEKD_t2.5_a0.5 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # vit-small_tobacco3482_kd_CEKD_t2.5_a0.5 This model is a fine-tuned version of [WinKawaks/vit-small-patch16-224](https://huggingface.co/WinKawaks/vit-small-patch16-224) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.4300 - Accuracy: 0.83 - Brier Loss: 0.2807 - Nll: 1.0350 - F1 Micro: 0.83 - F1 Macro: 0.8295 - Ece: 0.2287 - Aurc: 0.0560 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 100 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| Brier Loss \| Nll \| F1 Micro \| F1 Macro \| Ece \| Aurc \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\|:----------:\|:------:\|:--------:\|:--------:\|:------:\|:------:\| \| No log \| 1.0 \| 7 \| 1.6525 \| 0.225 \| 0.8757 \| 5.3231 \| 0.225 \| 0.1387 \| 0.2689 \| 0.6977 \| \| No log \| 2.0 \| 14 \| 1.3106 \| 0.405 \| 0.7470 \| 3.3487 \| 0.405 \| 0.2195 \| 0.2936 \| 0.4032 \| \| No log \| 3.0 \| 21 \| 0.9127 \| 0.585 \| 0.5785 \| 1.8686 \| 0.585 \| 0.5142 \| 0.2974 \| 0.2067 \| \| No log \| 4.0 \| 28 \| 0.7280 \| 0.715 \| 0.4339 \| 1.6780 \| 0.715 \| 0.6761 \| 0.2672 \| 0.1204 \| \| No log \| 5.0 \| 35 \| 0.6523 \| 0.775 \| 0.3676 \| 1.6537 \| 0.775 \| 0.7619 \| 0.2554 \| 0.0929 \| \| No log \| 6.0 \| 42 \| 0.5888 \| 0.785 \| 0.3502 \| 1.3926 \| 0.785 \| 0.7538 \| 0.2277 \| 0.0908 \| \| No log \| 7.0 \| 49 \| 0.6113 \| 0.805 \| 0.3326 \| 1.7118 \| 0.805 \| 0.7903 \| 0.2428 \| 0.0803 \| \| No log \| 8.0 \| 56 \| 0.5404 \| 0.785 \| 0.3178 \| 1.1557 \| 0.785 \| 0.7671 \| 0.2183 \| 0.0716 \| \| No log \| 9.0 \| 63 \| 0.5380 \| 0.82 \| 0.3051 \| 1.3231 \| 0.82 \| 0.8072 \| 0.2168 \| 0.0773 \| \| No log \| 10.0 \| 70 \| 0.6035 \| 0.775 \| 0.3508 \| 1.3888 \| 0.775 \| 0.7682 \| 0.2191 \| 0.0812 \| \| No log \| 11.0 \| 77 \| 0.5473 \| 0.795 \| 0.3202 \| 1.2622 \| 0.795 \| 0.7740 \| 0.2303 \| 0.0626 \| \| No log \| 12.0 \| 84 \| 0.4860 \| 0.825 \| 0.2937 \| 1.3575 \| 0.825 \| 0.8053 \| 0.2392 \| 0.0727 \| \| No log \| 13.0 \| 91 \| 0.5046 \| 0.81 \| 0.3032 \| 1.1857 \| 0.81 \| 0.8086 \| 0.2248 \| 0.0564 \| \| No log \| 14.0 \| 98 \| 0.4745 \| 0.825 \| 0.2870 \| 1.2338 \| 0.825 \| 0.8089 \| 0.2441 \| 0.0518 \| \| No log \| 15.0 \| 105 \| 0.4764 \| 0.81 \| 0.2943 \| 1.0325 \| 0.81 \| 0.8110 \| 0.1935 \| 0.0556 \| \| No log \| 16.0 \| 112 \| 0.4918 \| 0.81 \| 0.3062 \| 1.0551 \| 0.81 \| 0.8015 \| 0.2198 \| 0.0587 \| \| No log \| 17.0 \| 119 \| 0.4757 \| 0.815 \| 0.2970 \| 1.4203 \| 0.815 \| 0.7965 \| 0.2263 \| 0.0850 \| \| No log \| 18.0 \| 126 \| 0.4586 \| 0.825 \| 0.2926 \| 1.0361 \| 0.825 \| 0.8268 \| 0.2279 \| 0.0583 \| \| No log \| 19.0 \| 133 \| 0.4503 \| 0.835 \| 0.2855 \| 1.1476 \| 0.835 \| 0.8301 \| 0.2392 \| 0.0589 \| \| No log \| 20.0 \| 140 \| 0.4780 \| 0.805 \| 0.3105 \| 0.9928 \| 0.805 \| 0.7902 \| 0.1988 \| 0.0775 \| \| No log \| 21.0 \| 147 \| 0.4965 \| 0.8 \| 0.3205 \| 1.1887 \| 0.8000 \| 0.8029 \| 0.2410 \| 0.0702 \| \| No log \| 22.0 \| 154 \| 0.4753 \| 0.815 \| 0.3016 \| 0.9609 \| 0.815 \| 0.8169 \| 0.2163 \| 0.0580 \| \| No log \| 23.0 \| 161 \| 0.4733 \| 0.8 \| 0.3074 \| 1.2566 \| 0.8000 \| 0.8001 \| 0.2162 \| 0.0704 \| \| No log \| 24.0 \| 168 \| 0.4472 \| 0.815 \| 0.2888 \| 1.0352 \| 0.815 \| 0.8187 \| 0.2317 \| 0.0590 \| \| No log \| 25.0 \| 175 \| 0.4434 \| 0.815 \| 0.2854 \| 0.9874 \| 0.815 \| 0.8186 \| 0.2149 \| 0.0554 \| \| No log \| 26.0 \| 182 \| 0.4316 \| 0.82 \| 0.2754 \| 1.0477 \| 0.82 \| 0.8267 \| 0.2195 \| 0.0508 \| \| No log \| 27.0 \| 189 \| 0.4276 \| 0.83 \| 0.2751 \| 1.1016 \| 0.83 \| 0.8336 \| 0.2050 \| 0.0525 \| \| No log \| 28.0 \| 196 \| 0.4329 \| 0.82 \| 0.2795 \| 1.0537 \| 0.82 \| 0.8220 \| 0.2158 \| 0.0611 \| \| No log \| 29.0 \| 203 \| 0.4327 \| 0.82 \| 0.2827 \| 1.1766 \| 0.82 \| 0.8237 \| 0.2024 \| 0.0603 \| \| No log \| 30.0 \| 210 \| 0.4317 \| 0.82 \| 0.2820 \| 1.0331 \| 0.82 \| 0.8219 \| 0.2083 \| 0.0611 \| \| No log \| 31.0 \| 217 \| 0.4316 \| 0.82 \| 0.2803 \| 1.0974 \| 0.82 \| 0.8263 \| 0.1984 \| 0.0575 \| \| No log \| 32.0 \| 224 \| 0.4340 \| 0.82 \| 0.2833 \| 1.0384 \| 0.82 \| 0.8240 \| 0.2202 \| 0.0590 \| \| No log \| 33.0 \| 231 \| 0.4333 \| 0.81 \| 0.2824 \| 1.0355 \| 0.81 \| 0.8160 \| 0.2103 \| 0.0586 \| \| No log \| 34.0 \| 238 \| 0.4309 \| 0.83 \| 0.2817 \| 1.1015 \| 0.83 \| 0.8307 \| 0.2107 \| 0.0577 \| \| No log \| 35.0 \| 245 \| 0.4321 \| 0.82 \| 0.2817 \| 1.0359 \| 0.82 \| 0.8229 \| 0.2147 \| 0.0590 \| \| No log \| 36.0 \| 252 \| 0.4304 \| 0.825 \| 0.2802 \| 1.1016 \| 0.825 \| 0.8257 \| 0.2137 \| 0.0569 \| \| No log \| 37.0 \| 259 \| 0.4303 \| 0.825 \| 0.2811 \| 1.0990 \| 0.825 \| 0.8268 \| 0.2149 \| 0.0581 \| \| No log \| 38.0 \| 266 \| 0.4314 \| 0.825 \| 0.2814 \| 1.1003 \| 0.825 \| 0.8257 \| 0.2163 \| 0.0581 \| \| No log \| 39.0 \| 273 \| 0.4302 \| 0.82 \| 0.2806 \| 1.1007 \| 0.82 \| 0.8226 \| 0.2102 \| 0.0576 \| \| No log \| 40.0 \| 280 \| 0.4307 \| 0.825 \| 0.2809 \| 1.0376 \| 0.825 \| 0.8264 \| 0.2049 \| 0.0573 \| \| No log \| 41.0 \| 287 \| 0.4303 \| 0.82 \| 0.2808 \| 1.0434 \| 0.82 \| 0.8226 \| 0.2096 \| 0.0574 \| \| No log \| 42.0 \| 294 \| 0.4310 \| 0.825 \| 0.2817 \| 1.0376 \| 0.825 \| 0.8268 \| 0.2140 \| 0.0580 \| \| No log \| 43.0 \| 301 \| 0.4310 \| 0.825 \| 0.2813 \| 1.0391 \| 0.825 \| 0.8257 \| 0.2147 \| 0.0580 \| \| No log \| 44.0 \| 308 \| 0.4301 \| 0.825 \| 0.2808 \| 1.0389 \| 0.825 \| 0.8257 \| 0.2064 \| 0.0573 \| \| No log \| 45.0 \| 315 \| 0.4305 \| 0.83 \| 0.2811 \| 1.0419 \| 0.83 \| 0.8307 \| 0.2300 \| 0.0577 \| \| No log \| 46.0 \| 322 \| 0.4303 \| 0.82 \| 0.2808 \| 1.0423 \| 0.82 \| 0.8226 \| 0.2197 \| 0.0582 \| \| No log \| 47.0 \| 329 \| 0.4304 \| 0.825 \| 0.2811 \| 1.0405 \| 0.825 \| 0.8257 \| 0.2240 \| 0.0580 \| \| No log \| 48.0 \| 336 \| 0.4300 \| 0.82 \| 0.2805 \| 1.0407 \| 0.82 \| 0.8226 \| 0.2105 \| 0.0574 \| \| No log \| 49.0 \| 343 \| 0.4307 \| 0.825 \| 0.2812 \| 1.0381 \| 0.825 \| 0.8257 \| 0.2252 \| 0.0577 \| \| No log \| 50.0 \| 350 \| 0.4304 \| 0.82 \| 0.2810 \| 1.0422 \| 0.82 \| 0.8226 \| 0.2353 \| 0.0578 \| \| No log \| 51.0 \| 357 \| 0.4310 \| 0.825 \| 0.2813 \| 1.0382 \| 0.825 \| 0.8264 \| 0.2153 \| 0.0569 \| \| No log \| 52.0 \| 364 \| 0.4309 \| 0.82 \| 0.2814 \| 1.0380 \| 0.82 \| 0.8226 \| 0.2282 \| 0.0574 \| \| No log \| 53.0 \| 371 \| 0.4307 \| 0.825 \| 0.2813 \| 1.0357 \| 0.825 \| 0.8264 \| 0.2250 \| 0.0568 \| \| No log \| 54.0 \| 378 \| 0.4305 \| 0.82 \| 0.2810 \| 1.0366 \| 0.82 \| 0.8226 \| 0.2284 \| 0.0575 \| \| No log \| 55.0 \| 385 \| 0.4304 \| 0.825 \| 0.2811 \| 1.0351 \| 0.825 \| 0.8264 \| 0.2241 \| 0.0566 \| \| No log \| 56.0 \| 392 \| 0.4308 \| 0.825 \| 0.2813 \| 1.0369 \| 0.825 \| 0.8257 \| 0.2414 \| 0.0572 \| \| No log \| 57.0 \| 399 \| 0.4305 \| 0.825 \| 0.2810 \| 1.0356 \| 0.825 \| 0.8257 \| 0.2322 \| 0.0571 \| \| No log \| 58.0 \| 406 \| 0.4302 \| 0.82 \| 0.2808 \| 1.0359 \| 0.82 \| 0.8226 \| 0.2368 \| 0.0569 \| \| No log \| 59.0 \| 413 \| 0.4302 \| 0.82 \| 0.2809 \| 1.0346 \| 0.82 \| 0.8226 \| 0.2271 \| 0.0569 \| \| No log \| 60.0 \| 420 \| 0.4303 \| 0.82 \| 0.2809 \| 1.0357 \| 0.82 \| 0.8226 \| 0.2272 \| 0.0570 \| \| No log \| 61.0 \| 427 \| 0.4304 \| 0.825 \| 0.2810 \| 1.0360 \| 0.825 \| 0.8257 \| 0.2325 \| 0.0569 \| \| No log \| 62.0 \| 434 \| 0.4303 \| 0.825 \| 0.2809 \| 1.0360 \| 0.825 \| 0.8257 \| 0.2321 \| 0.0568 \| \| No log \| 63.0 \| 441 \| 0.4303 \| 0.83 \| 0.2809 \| 1.0356 \| 0.83 \| 0.8295 \| 0.2300 \| 0.0562 \| \| No log \| 64.0 \| 448 \| 0.4304 \| 0.825 \| 0.2810 \| 1.0347 \| 0.825 \| 0.8264 \| 0.2242 \| 0.0564 \| \| No log \| 65.0 \| 455 \| 0.4301 \| 0.83 \| 0.2808 \| 1.0361 \| 0.83 \| 0.8295 \| 0.2384 \| 0.0564 \| \| No log \| 66.0 \| 462 \| 0.4303 \| 0.83 \| 0.2810 \| 1.0359 \| 0.83 \| 0.8295 \| 0.2293 \| 0.0563 \| \| No log \| 67.0 \| 469 \| 0.4302 \| 0.83 \| 0.2809 \| 1.0360 \| 0.83 \| 0.8295 \| 0.2386 \| 0.0564 \| \| No log \| 68.0 \| 476 \| 0.4304 \| 0.83 \| 0.2810 \| 1.0360 \| 0.83 \| 0.8295 \| 0.2384 \| 0.0563 \| \| No log \| 69.0 \| 483 \| 0.4305 \| 0.83 \| 0.2812 \| 1.0355 \| 0.83 \| 0.8295 \| 0.2295 \| 0.0564 \| \| No log \| 70.0 \| 490 \| 0.4302 \| 0.825 \| 0.2808 \| 1.0354 \| 0.825 \| 0.8264 \| 0.2239 \| 0.0561 \| \| No log \| 71.0 \| 497 \| 0.4305 \| 0.83 \| 0.2812 \| 1.0352 \| 0.83 \| 0.8295 \| 0.2296 \| 0.0564 \| \| 0.1776 \| 72.0 \| 504 \| 0.4303 \| 0.83 \| 0.2808 \| 1.0356 \| 0.83 \| 0.8295 \| 0.2287 \| 0.0561 \| \| 0.1776 \| 73.0 \| 511 \| 0.4301 \| 0.825 \| 0.2807 \| 1.0351 \| 0.825 \| 0.8264 \| 0.2348 \| 0.0563 \| \| 0.1776 \| 74.0 \| 518 \| 0.4304 \| 0.83 \| 0.2811 \| 1.0353 \| 0.83 \| 0.8295 \| 0.2195 \| 0.0562 \| \| 0.1776 \| 75.0 \| 525 \| 0.4301 \| 0.825 \| 0.2808 \| 1.0355 \| 0.825 \| 0.8257 \| 0.2320 \| 0.0568 \| \| 0.1776 \| 76.0 \| 532 \| 0.4302 \| 0.83 \| 0.2808 \| 1.0348 \| 0.83 \| 0.8295 \| 0.2289 \| 0.0561 \| \| 0.1776 \| 77.0 \| 539 \| 0.4301 \| 0.83 \| 0.2808 \| 1.0355 \| 0.83 \| 0.8295 \| 0.2300 \| 0.0562 \| \| 0.1776 \| 78.0 \| 546 \| 0.4301 \| 0.83 \| 0.2808 \| 1.0354 \| 0.83 \| 0.8295 \| 0.2394 \| 0.0563 \| \| 0.1776 \| 79.0 \| 553 \| 0.4302 \| 0.83 \| 0.2809 \| 1.0346 \| 0.83 \| 0.8295 \| 0.2287 \| 0.0560 \| \| 0.1776 \| 80.0 \| 560 \| 0.4302 \| 0.83 \| 0.2809 \| 1.0353 \| 0.83 \| 0.8295 \| 0.2299 \| 0.0563 \| \| 0.1776 \| 81.0 \| 567 \| 0.4302 \| 0.83 \| 0.2809 \| 1.0350 \| 0.83 \| 0.8295 \| 0.2299 \| 0.0563 \| \| 0.1776 \| 82.0 \| 574 \| 0.4302 \| 0.83 \| 0.2808 \| 1.0354 \| 0.83 \| 0.8295 \| 0.2298 \| 0.0560 \| \| 0.1776 \| 83.0 \| 581 \| 0.4302 \| 0.83 \| 0.2809 \| 1.0350 \| 0.83 \| 0.8295 \| 0.2299 \| 0.0561 \| \| 0.1776 \| 84.0 \| 588 \| 0.4299 \| 0.83 \| 0.2807 \| 1.0352 \| 0.83 \| 0.8295 \| 0.2287 \| 0.0561 \| \| 0.1776 \| 85.0 \| 595 \| 0.4301 \| 0.83 \| 0.2808 \| 1.0349 \| 0.83 \| 0.8295 \| 0.2296 \| 0.0562 \| \| 0.1776 \| 86.0 \| 602 \| 0.4301 \| 0.83 \| 0.2808 \| 1.0351 \| 0.83 \| 0.8295 \| 0.2287 \| 0.0562 \| \| 0.1776 \| 87.0 \| 609 \| 0.4300 \| 0.83 \| 0.2807 \| 1.0351 \| 0.83 \| 0.8295 \| 0.2297 \| 0.0561 \| \| 0.1776 \| 88.0 \| 616 \| 0.4300 \| 0.83 \| 0.2807 \| 1.0349 \| 0.83 \| 0.8295 \| 0.2287 \| 0.0562 \| \| 0.1776 \| 89.0 \| 623 \| 0.4300 \| 0.83 \| 0.2807 \| 1.0353 \| 0.83 \| 0.8295 \| 0.2296 \| 0.0560 \| \| 0.1776 \| 90.0 \| 630 \| 0.4300 \| 0.83 \| 0.2807 \| 1.0349 \| 0.83 \| 0.8295 \| 0.2297 \| 0.0559 \| \| 0.1776 \| 91.0 \| 637 \| 0.4300 \| 0.83 \| 0.2807 \| 1.0352 \| 0.83 \| 0.8295 \| 0.2296 \| 0.0562 \| \| 0.1776 \| 92.0 \| 644 \| 0.4300 \| 0.83 \| 0.2807 \| 1.0351 \| 0.83 \| 0.8295 \| 0.2287 \| 0.0561 \| \| 0.1776 \| 93.0 \| 651 \| 0.4300 \| 0.83 \| 0.2807 \| 1.0351 \| 0.83 \| 0.8295 \| 0.2297 \| 0.0562 \| \| 0.1776 \| 94.0 \| 658 \| 0.4300 \| 0.83 \| 0.2807 \| 1.0349 \| 0.83 \| 0.8295 \| 0.2297 \| 0.0560 \| \| 0.1776 \| 95.0 \| 665 \| 0.4300 \| 0.83 \| 0.2807 \| 1.0350 \| 0.83 \| 0.8295 \| 0.2297 \| 0.0562 \| \| 0.1776 \| 96.0 \| 672 \| 0.4300 \| 0.83 \| 0.2807 \| 1.0349 \| 0.83 \| 0.8295 \| 0.2296 \| 0.0561 \| \| 0.1776 \| 97.0 \| 679 \| 0.4300 \| 0.83 \| 0.2807 \| 1.0350 \| 0.83 \| 0.8295 \| 0.2296 \| 0.0560 \| \| 0.1776 \| 98.0 \| 686 \| 0.4300 \| 0.83 \| 0.2807 \| 1.0350 \| 0.83 \| 0.8295 \| 0.2296 \| 0.0560 \| \| 0.1776 \| 99.0 \| 693 \| 0.4300 \| 0.83 \| 0.2807 \| 1.0350 \| 0.83 \| 0.8295 \| 0.2287 \| 0.0560 \| \| 0.1776 \| 100.0 \| 700 \| 0.4300 \| 0.83 \| 0.2807 \| 1.0350 \| 0.83 \| 0.8295 \| 0.2287 \| 0.0560 \| ### Framework versions - Transformers 4.26.1 - Pytorch 1.13.1.post200 - Datasets 2.9.0 - Tokenizers 0.13.2
NasimB/gpt2-dp-all-mod-datasets-rarity-all-iorder-13k-2p6k	NasimB	2023-07-10T19:10:16Z	5	0	transformers	[ "transformers", "pytorch", "gpt2", "text-generation", "generated_from_trainer", "dataset:generator", "license:mit", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2023-07-10T16:50:38Z	--- license: mit tags: - generated_from_trainer datasets: - generator model-index: - name: gpt2-dp-all-mod-datasets-rarity-all-iorder-13k-2p6k results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # gpt2-dp-all-mod-datasets-rarity-all-iorder-13k-2p6k This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the generator dataset. It achieves the following results on the evaluation set: - Loss: 4.4226 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 64 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_steps: 1000 - num_epochs: 7 - mixed_precision_training: Native AMP ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-----:\|:-----:\|:---------------:\| \| 6.7606 \| 0.29 \| 500 \| 5.6940 \| \| 5.4347 \| 0.59 \| 1000 \| 5.2560 \| \| 5.0945 \| 0.88 \| 1500 \| 5.0226 \| \| 4.8232 \| 1.18 \| 2000 \| 4.8777 \| \| 4.675 \| 1.47 \| 2500 \| 4.7626 \| \| 4.5767 \| 1.77 \| 3000 \| 4.6625 \| \| 4.4488 \| 2.06 \| 3500 \| 4.5933 \| \| 4.2612 \| 2.36 \| 4000 \| 4.5563 \| \| 4.245 \| 2.65 \| 4500 \| 4.4882 \| \| 4.208 \| 2.94 \| 5000 \| 4.4332 \| \| 3.9773 \| 3.24 \| 5500 \| 4.4362 \| \| 3.9484 \| 3.53 \| 6000 \| 4.4046 \| \| 3.9304 \| 3.83 \| 6500 \| 4.3669 \| \| 3.7943 \| 4.12 \| 7000 \| 4.3731 \| \| 3.6517 \| 4.42 \| 7500 \| 4.3646 \| \| 3.646 \| 4.71 \| 8000 \| 4.3456 \| \| 3.6381 \| 5.01 \| 8500 \| 4.3333 \| \| 3.3812 \| 5.3 \| 9000 \| 4.3586 \| \| 3.3875 \| 5.59 \| 9500 \| 4.3536 \| \| 3.3847 \| 5.89 \| 10000 \| 4.3483 \| \| 3.2816 \| 6.18 \| 10500 \| 4.3600 \| \| 3.2295 \| 6.48 \| 11000 \| 4.3636 \| \| 3.223 \| 6.77 \| 11500 \| 4.3630 \| ### Framework versions - Transformers 4.26.1 - Pytorch 1.11.0+cu113 - Datasets 2.13.0 - Tokenizers 0.13.3
aphi/ppo-SnowballTarget	aphi	2023-07-10T19:08:24Z	0	0	ml-agents	[ "ml-agents", "tensorboard", "onnx", "SnowballTarget", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-SnowballTarget", "region:us" ]	reinforcement-learning	2023-07-10T19:08:17Z	--- library_name: ml-agents tags: - SnowballTarget - deep-reinforcement-learning - reinforcement-learning - ML-Agents-SnowballTarget --- # ppo Agent playing SnowballTarget This is a trained model of a ppo agent playing SnowballTarget using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents). ## Usage (with ML-Agents) The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/ We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub: - A short tutorial where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction - A longer tutorial to understand how works ML-Agents: https://huggingface.co/learn/deep-rl-course/unit5/introduction ### Resume the training ```bash mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume ``` ### Watch your Agent play You can watch your agent playing directly in your browser 1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity 2. Step 1: Find your model_id: aphi/ppo-SnowballTarget 3. Step 2: Select your .nn /.onnx file 4. Click on Watch the agent play 👀
MaitreHibou/Reinforce-Cartpole-v1	MaitreHibou	2023-07-10T18:49:32Z	0	0	null	[ "CartPole-v1", "reinforce", "reinforcement-learning", "custom-implementation", "deep-rl-class", "model-index", "region:us" ]	reinforcement-learning	2023-07-10T18:49:23Z	--- tags: - CartPole-v1 - reinforce - reinforcement-learning - custom-implementation - deep-rl-class model-index: - name: Reinforce-Cartpole-v1 results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: CartPole-v1 type: CartPole-v1 metrics: - type: mean_reward value: 500.00 +/- 0.00 name: mean_reward verified: false --- # Reinforce Agent playing CartPole-v1 This is a trained model of a Reinforce agent playing CartPole-v1 . To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
grace-pro/afriberta-base-finetuned-hausa	grace-pro	2023-07-10T18:48:53Z	124	0	transformers	[ "transformers", "pytorch", "tensorboard", "xlm-roberta", "token-classification", "generated_from_trainer", "autotrain_compatible", "endpoints_compatible", "region:us" ]	token-classification	2023-07-10T17:58:10Z	--- tags: - generated_from_trainer metrics: - precision - recall - f1 - accuracy model-index: - name: afriberta-base-finetuned-hausa results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # afriberta-base-finetuned-hausa This model is a fine-tuned version of [castorini/afriberta_base](https://huggingface.co/castorini/afriberta_base) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.1401 - Precision: 0.7156 - Recall: 0.5251 - F1: 0.6057 - Accuracy: 0.9655 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 5 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Precision \| Recall \| F1 \| Accuracy \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:---------:\|:------:\|:------:\|:--------:\| \| 0.1381 \| 1.0 \| 2624 \| 0.1277 \| 0.6804 \| 0.4403 \| 0.5346 \| 0.9607 \| \| 0.1113 \| 2.0 \| 5248 \| 0.1198 \| 0.6803 \| 0.4994 \| 0.5760 \| 0.9628 \| \| 0.0861 \| 3.0 \| 7872 \| 0.1270 \| 0.7102 \| 0.5052 \| 0.5904 \| 0.9645 \| \| 0.0723 \| 4.0 \| 10496 \| 0.1322 \| 0.7188 \| 0.5134 \| 0.5990 \| 0.9654 \| \| 0.0602 \| 5.0 \| 13120 \| 0.1401 \| 0.7156 \| 0.5251 \| 0.6057 \| 0.9655 \| ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3
DavidSolan0/coverart	DavidSolan0	2023-07-10T18:34:53Z	9	0	diffusers	[ "diffusers", "safetensors", "text-to-image", "stable-diffusion", "license:creativeml-openrail-m", "autotrain_compatible", "endpoints_compatible", "diffusers:StableDiffusionPipeline", "region:us" ]	text-to-image	2023-07-10T18:30:01Z	--- license: creativeml-openrail-m tags: - text-to-image - stable-diffusion --- ### coverart Dreambooth model trained by DavidSolan0 with [TheLastBen's fast-DreamBooth](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast-DreamBooth.ipynb) notebook Test the concept via A1111 Colab [fast-Colab-A1111](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast_stable_diffusion_AUTOMATIC1111.ipynb) Sample pictures of this concept:
simonestradasch/COMPner-bert-base-spanish-wwm-cased	simonestradasch	2023-07-10T18:28:38Z	107	0	transformers	[ "transformers", "tensorboard", "safetensors", "bert", "token-classification", "generated_from_trainer", "es", "dataset:simonestradasch/NERcomp", "autotrain_compatible", "endpoints_compatible", "region:us" ]	token-classification	2023-07-10T18:07:06Z	--- language: - es tags: - generated_from_trainer datasets: - simonestradasch/NERcomp model-index: - name: COMPner-bert-base-spanish-wwm-cased results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # COMPner-bert-base-spanish-wwm-cased This model is a fine-tuned version of [dccuchile/bert-base-spanish-wwm-cased](https://huggingface.co/dccuchile/bert-base-spanish-wwm-cased) on the simonestradasch/NERcomp dataset. It achieves the following results on the evaluation set: - Loss: 0.2793 - Body Part Precision: 0.6700 - Body Part Recall: 0.7186 - Body Part F1: 0.6934 - Body Part Number: 565 - Disease Precision: 0.6966 - Disease Recall: 0.7533 - Disease F1: 0.7238 - Disease Number: 1350 - Family Member Precision: 0.9 - Family Member Recall: 0.75 - Family Member F1: 0.8182 - Family Member Number: 24 - Medication Precision: 0.7143 - Medication Recall: 0.6190 - Medication F1: 0.6633 - Medication Number: 105 - Procedure Precision: 0.5233 - Procedure Recall: 0.5125 - Procedure F1: 0.5178 - Procedure Number: 439 - Overall Precision: 0.6640 - Overall Recall: 0.6971 - Overall F1: 0.6802 - Overall Accuracy: 0.9136 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 13 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 2 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Body Part Precision \| Body Part Recall \| Body Part F1 \| Body Part Number \| Disease Precision \| Disease Recall \| Disease F1 \| Disease Number \| Family Member Precision \| Family Member Recall \| Family Member F1 \| Family Member Number \| Medication Precision \| Medication Recall \| Medication F1 \| Medication Number \| Procedure Precision \| Procedure Recall \| Procedure F1 \| Procedure Number \| Overall Precision \| Overall Recall \| Overall F1 \| Overall Accuracy \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:-------------------:\|:----------------:\|:------------:\|:----------------:\|:-----------------:\|:--------------:\|:----------:\|:--------------:\|:-----------------------:\|:--------------------:\|:----------------:\|:--------------------:\|:--------------------:\|:-----------------:\|:-------------:\|:-----------------:\|:-------------------:\|:----------------:\|:------------:\|:----------------:\|:-----------------:\|:--------------:\|:----------:\|:----------------:\| \| 0.4741 \| 1.0 \| 703 \| 0.2932 \| 0.6449 \| 0.6301 \| 0.6374 \| 565 \| 0.6984 \| 0.7170 \| 0.7076 \| 1350 \| 0.9412 \| 0.6667 \| 0.7805 \| 24 \| 0.8551 \| 0.5619 \| 0.6782 \| 105 \| 0.5113 \| 0.3599 \| 0.4225 \| 439 \| 0.6674 \| 0.6271 \| 0.6466 \| 0.9091 \| \| 0.259 \| 2.0 \| 1406 \| 0.2793 \| 0.6700 \| 0.7186 \| 0.6934 \| 565 \| 0.6966 \| 0.7533 \| 0.7238 \| 1350 \| 0.9 \| 0.75 \| 0.8182 \| 24 \| 0.7143 \| 0.6190 \| 0.6633 \| 105 \| 0.5233 \| 0.5125 \| 0.5178 \| 439 \| 0.6640 \| 0.6971 \| 0.6802 \| 0.9136 \| ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3
BrendaScar/ppo-LunarLander-v2	BrendaScar	2023-07-10T18:24:25Z	0	0	stable-baselines3	[ "stable-baselines3", "LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]	reinforcement-learning	2023-07-10T18:24:03Z	--- library_name: stable-baselines3 tags: - LunarLander-v2 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: PPO results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: LunarLander-v2 type: LunarLander-v2 metrics: - type: mean_reward value: 248.77 +/- 20.04 name: mean_reward verified: false --- # PPO Agent playing LunarLander-v2 This is a trained model of a PPO agent playing LunarLander-v2 using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3). ## Usage (with Stable-baselines3) TODO: Add your code ```python from stable_baselines3 import ... from huggingface_sb3 import load_from_hub ... ```
MaitreHibou/dqn-SpaceInvadersNoFrameskip-v4	MaitreHibou	2023-07-10T18:21:47Z	2	0	stable-baselines3	[ "stable-baselines3", "SpaceInvadersNoFrameskip-v4", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]	reinforcement-learning	2023-07-10T18:21:06Z	--- library_name: stable-baselines3 tags: - SpaceInvadersNoFrameskip-v4 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: DQN results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: SpaceInvadersNoFrameskip-v4 type: SpaceInvadersNoFrameskip-v4 metrics: - type: mean_reward value: 656.50 +/- 140.98 name: mean_reward verified: false --- # DQN Agent playing SpaceInvadersNoFrameskip-v4 This is a trained model of a DQN agent playing SpaceInvadersNoFrameskip-v4 using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3) and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo). The RL Zoo is a training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included. ## Usage (with SB3 RL Zoo) RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/> SB3: https://github.com/DLR-RM/stable-baselines3<br/> SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib Install the RL Zoo (with SB3 and SB3-Contrib): ```bash pip install rl_zoo3 ``` ``` # Download model and save it into the logs/ folder python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga MaitreHibou -f logs/ python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ ``` If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do: ``` python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga MaitreHibou -f logs/ python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ ``` ## Training (with the RL Zoo) ``` python -m rl_zoo3.train --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ # Upload the model and generate video (when possible) python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga MaitreHibou ``` ## Hyperparameters ```python OrderedDict([('batch_size', 64), ('buffer_size', 100000), ('env_wrapper', ['stable_baselines3.common.atari_wrappers.AtariWrapper']), ('exploration_final_eps', 0.01), ('exploration_fraction', 0.1), ('frame_stack', 4), ('gradient_steps', 1), ('learning_rate', 0.0002), ('learning_starts', 100000), ('n_timesteps', 1000000.0), ('optimize_memory_usage', False), ('policy', 'CnnPolicy'), ('target_update_interval', 1000), ('train_freq', 4), ('normalize', False)]) ``` # Environment Arguments ```python {'render_mode': 'rgb_array'} ```
FerhatDk/wav2vec2-base-finetuned-ks	FerhatDk	2023-07-10T18:08:04Z	4	0	transformers	[ "transformers", "pytorch", "tensorboard", "wav2vec2", "audio-classification", "generated_from_trainer", "license:apache-2.0", "endpoints_compatible", "region:us" ]	audio-classification	2022-09-22T08:59:01Z	--- license: apache-2.0 tags: - generated_from_trainer metrics: - accuracy model-index: - name: wav2vec2-base-finetuned-ks results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # wav2vec2-base-finetuned-ks This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.3550 - Accuracy: 0.8727 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_ratio: 0.1 - lr_scheduler_warmup_steps: 500 - num_epochs: 25 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\| \| No log \| 1.0 \| 8 \| 0.6840 \| 0.6 \| \| 0.6867 \| 2.0 \| 16 \| 0.6780 \| 0.6364 \| \| 0.6742 \| 3.0 \| 24 \| 0.6601 \| 0.6182 \| \| 0.6446 \| 4.0 \| 32 \| 0.6294 \| 0.6364 \| \| 0.6299 \| 5.0 \| 40 \| 0.6002 \| 0.6727 \| \| 0.6299 \| 6.0 \| 48 \| 0.5755 \| 0.7091 \| \| 0.6021 \| 7.0 \| 56 \| 0.5530 \| 0.7273 \| \| 0.5678 \| 8.0 \| 64 \| 0.5036 \| 0.8182 \| \| 0.5512 \| 9.0 \| 72 \| 0.4753 \| 0.8545 \| \| 0.4784 \| 10.0 \| 80 \| 0.4184 \| 0.9273 \| \| 0.4784 \| 11.0 \| 88 \| 0.4102 \| 0.8909 \| \| 0.4515 \| 12.0 \| 96 \| 0.4444 \| 0.8182 \| \| 0.4878 \| 13.0 \| 104 \| 0.3780 \| 0.9091 \| \| 0.4418 \| 14.0 \| 112 \| 0.4570 \| 0.8 \| \| 0.4746 \| 15.0 \| 120 \| 0.3870 \| 0.8545 \| \| 0.4746 \| 16.0 \| 128 \| 0.3932 \| 0.8364 \| \| 0.4226 \| 17.0 \| 136 \| 0.2779 \| 0.9636 \| \| 0.4301 \| 18.0 \| 144 \| 0.3125 \| 0.9455 \| \| 0.3482 \| 19.0 \| 152 \| 0.3212 \| 0.9091 \| \| 0.3611 \| 20.0 \| 160 \| 0.3925 \| 0.8364 \| \| 0.3611 \| 21.0 \| 168 \| 0.3389 \| 0.8909 \| \| 0.3507 \| 22.0 \| 176 \| 0.3099 \| 0.8727 \| \| 0.3241 \| 23.0 \| 184 \| 0.3120 \| 0.8727 \| \| 0.2533 \| 24.0 \| 192 \| 0.2313 \| 0.9455 \| \| 0.2466 \| 25.0 \| 200 \| 0.3550 \| 0.8727 \| ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3
jordyvl/vit-small_tobacco3482_kd_CEKD_t1.5_a0.7	jordyvl	2023-07-10T17:57:06Z	166	0	transformers	[ "transformers", "pytorch", "vit", "image-classification", "generated_from_trainer", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	image-classification	2023-07-10T17:18:33Z	--- license: apache-2.0 tags: - generated_from_trainer metrics: - accuracy model-index: - name: vit-small_tobacco3482_kd_CEKD_t1.5_a0.7 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # vit-small_tobacco3482_kd_CEKD_t1.5_a0.7 This model is a fine-tuned version of [WinKawaks/vit-small-patch16-224](https://huggingface.co/WinKawaks/vit-small-patch16-224) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.4797 - Accuracy: 0.835 - Brier Loss: 0.2522 - Nll: 0.8627 - F1 Micro: 0.835 - F1 Macro: 0.8222 - Ece: 0.1830 - Aurc: 0.0434 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 100 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| Brier Loss \| Nll \| F1 Micro \| F1 Macro \| Ece \| Aurc \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\|:----------:\|:------:\|:--------:\|:--------:\|:------:\|:------:\| \| No log \| 1.0 \| 7 \| 1.9341 \| 0.215 \| 0.8749 \| 5.3238 \| 0.2150 \| 0.1264 \| 0.2642 \| 0.6914 \| \| No log \| 2.0 \| 14 \| 1.5320 \| 0.405 \| 0.7410 \| 3.5078 \| 0.405 \| 0.2276 \| 0.2957 \| 0.4015 \| \| No log \| 3.0 \| 21 \| 1.0532 \| 0.635 \| 0.5629 \| 2.0153 \| 0.635 \| 0.5844 \| 0.3037 \| 0.2006 \| \| No log \| 4.0 \| 28 \| 0.7915 \| 0.715 \| 0.4093 \| 1.6974 \| 0.715 \| 0.6762 \| 0.2420 \| 0.1131 \| \| No log \| 5.0 \| 35 \| 0.8024 \| 0.745 \| 0.3869 \| 1.7109 \| 0.745 \| 0.7548 \| 0.2160 \| 0.1006 \| \| No log \| 6.0 \| 42 \| 0.7162 \| 0.765 \| 0.3351 \| 1.8105 \| 0.765 \| 0.7599 \| 0.2216 \| 0.0874 \| \| No log \| 7.0 \| 49 \| 0.6966 \| 0.785 \| 0.3304 \| 1.5292 \| 0.785 \| 0.7682 \| 0.2058 \| 0.0979 \| \| No log \| 8.0 \| 56 \| 0.6317 \| 0.805 \| 0.2995 \| 1.3486 \| 0.805 \| 0.7887 \| 0.2266 \| 0.0721 \| \| No log \| 9.0 \| 63 \| 0.6903 \| 0.805 \| 0.3304 \| 1.5866 \| 0.805 \| 0.7971 \| 0.2371 \| 0.0995 \| \| No log \| 10.0 \| 70 \| 0.6223 \| 0.805 \| 0.2940 \| 1.3478 \| 0.805 \| 0.8114 \| 0.2281 \| 0.0697 \| \| No log \| 11.0 \| 77 \| 0.6350 \| 0.795 \| 0.3145 \| 1.3386 \| 0.795 \| 0.7730 \| 0.2063 \| 0.0962 \| \| No log \| 12.0 \| 84 \| 0.5570 \| 0.835 \| 0.2666 \| 1.2662 \| 0.835 \| 0.8181 \| 0.1951 \| 0.0553 \| \| No log \| 13.0 \| 91 \| 0.5610 \| 0.81 \| 0.2858 \| 1.2619 \| 0.81 \| 0.8002 \| 0.1884 \| 0.0626 \| \| No log \| 14.0 \| 98 \| 0.5843 \| 0.8 \| 0.2961 \| 1.0782 \| 0.8000 \| 0.8083 \| 0.1993 \| 0.0683 \| \| No log \| 15.0 \| 105 \| 0.5918 \| 0.78 \| 0.2965 \| 1.1207 \| 0.78 \| 0.7861 \| 0.1895 \| 0.0634 \| \| No log \| 16.0 \| 112 \| 0.5541 \| 0.84 \| 0.2765 \| 1.3189 \| 0.8400 \| 0.8455 \| 0.1969 \| 0.0597 \| \| No log \| 17.0 \| 119 \| 0.5037 \| 0.835 \| 0.2568 \| 0.9024 \| 0.835 \| 0.8248 \| 0.2083 \| 0.0499 \| \| No log \| 18.0 \| 126 \| 0.5050 \| 0.85 \| 0.2563 \| 1.0032 \| 0.85 \| 0.8441 \| 0.2147 \| 0.0580 \| \| No log \| 19.0 \| 133 \| 0.5430 \| 0.815 \| 0.2779 \| 1.1046 \| 0.815 \| 0.8044 \| 0.1906 \| 0.0562 \| \| No log \| 20.0 \| 140 \| 0.5276 \| 0.84 \| 0.2743 \| 0.9964 \| 0.8400 \| 0.8144 \| 0.2104 \| 0.0597 \| \| No log \| 21.0 \| 147 \| 0.5155 \| 0.835 \| 0.2686 \| 0.9556 \| 0.835 \| 0.8210 \| 0.1962 \| 0.0572 \| \| No log \| 22.0 \| 154 \| 0.4937 \| 0.835 \| 0.2581 \| 1.0079 \| 0.835 \| 0.8172 \| 0.1975 \| 0.0479 \| \| No log \| 23.0 \| 161 \| 0.4931 \| 0.845 \| 0.2533 \| 1.0021 \| 0.845 \| 0.8270 \| 0.1884 \| 0.0503 \| \| No log \| 24.0 \| 168 \| 0.4869 \| 0.83 \| 0.2554 \| 0.9660 \| 0.83 \| 0.8084 \| 0.1945 \| 0.0481 \| \| No log \| 25.0 \| 175 \| 0.4843 \| 0.845 \| 0.2512 \| 0.9979 \| 0.845 \| 0.8316 \| 0.1746 \| 0.0466 \| \| No log \| 26.0 \| 182 \| 0.4866 \| 0.835 \| 0.2531 \| 0.9006 \| 0.835 \| 0.8188 \| 0.1833 \| 0.0472 \| \| No log \| 27.0 \| 189 \| 0.4882 \| 0.825 \| 0.2562 \| 0.8929 \| 0.825 \| 0.8043 \| 0.2023 \| 0.0469 \| \| No log \| 28.0 \| 196 \| 0.4814 \| 0.82 \| 0.2494 \| 0.9122 \| 0.82 \| 0.8060 \| 0.1773 \| 0.0451 \| \| No log \| 29.0 \| 203 \| 0.4749 \| 0.835 \| 0.2501 \| 0.8770 \| 0.835 \| 0.8252 \| 0.1688 \| 0.0442 \| \| No log \| 30.0 \| 210 \| 0.4761 \| 0.84 \| 0.2490 \| 0.8848 \| 0.8400 \| 0.8250 \| 0.2068 \| 0.0443 \| \| No log \| 31.0 \| 217 \| 0.4787 \| 0.845 \| 0.2508 \| 0.8754 \| 0.845 \| 0.8309 \| 0.1635 \| 0.0438 \| \| No log \| 32.0 \| 224 \| 0.4791 \| 0.835 \| 0.2521 \| 0.8711 \| 0.835 \| 0.8224 \| 0.1876 \| 0.0446 \| \| No log \| 33.0 \| 231 \| 0.4779 \| 0.84 \| 0.2509 \| 0.8650 \| 0.8400 \| 0.8252 \| 0.1813 \| 0.0436 \| \| No log \| 34.0 \| 238 \| 0.4774 \| 0.84 \| 0.2513 \| 0.8662 \| 0.8400 \| 0.8252 \| 0.1919 \| 0.0441 \| \| No log \| 35.0 \| 245 \| 0.4760 \| 0.835 \| 0.2502 \| 0.8636 \| 0.835 \| 0.8224 \| 0.1840 \| 0.0434 \| \| No log \| 36.0 \| 252 \| 0.4784 \| 0.84 \| 0.2509 \| 0.8688 \| 0.8400 \| 0.8281 \| 0.1691 \| 0.0437 \| \| No log \| 37.0 \| 259 \| 0.4771 \| 0.835 \| 0.2507 \| 0.8670 \| 0.835 \| 0.8224 \| 0.1936 \| 0.0440 \| \| No log \| 38.0 \| 266 \| 0.4764 \| 0.835 \| 0.2499 \| 0.8614 \| 0.835 \| 0.8224 \| 0.1830 \| 0.0434 \| \| No log \| 39.0 \| 273 \| 0.4769 \| 0.835 \| 0.2503 \| 0.8651 \| 0.835 \| 0.8224 \| 0.2001 \| 0.0438 \| \| No log \| 40.0 \| 280 \| 0.4777 \| 0.84 \| 0.2514 \| 0.8608 \| 0.8400 \| 0.8281 \| 0.1832 \| 0.0435 \| \| No log \| 41.0 \| 287 \| 0.4777 \| 0.835 \| 0.2504 \| 0.8650 \| 0.835 \| 0.8224 \| 0.1953 \| 0.0437 \| \| No log \| 42.0 \| 294 \| 0.4779 \| 0.835 \| 0.2511 \| 0.8629 \| 0.835 \| 0.8224 \| 0.1944 \| 0.0440 \| \| No log \| 43.0 \| 301 \| 0.4790 \| 0.835 \| 0.2519 \| 0.8631 \| 0.835 \| 0.8222 \| 0.1808 \| 0.0439 \| \| No log \| 44.0 \| 308 \| 0.4777 \| 0.835 \| 0.2509 \| 0.8604 \| 0.835 \| 0.8222 \| 0.1886 \| 0.0435 \| \| No log \| 45.0 \| 315 \| 0.4787 \| 0.835 \| 0.2517 \| 0.8620 \| 0.835 \| 0.8222 \| 0.1940 \| 0.0437 \| \| No log \| 46.0 \| 322 \| 0.4774 \| 0.84 \| 0.2509 \| 0.8614 \| 0.8400 \| 0.8281 \| 0.1779 \| 0.0433 \| \| No log \| 47.0 \| 329 \| 0.4785 \| 0.835 \| 0.2517 \| 0.8609 \| 0.835 \| 0.8222 \| 0.1811 \| 0.0438 \| \| No log \| 48.0 \| 336 \| 0.4792 \| 0.835 \| 0.2521 \| 0.8611 \| 0.835 \| 0.8222 \| 0.1849 \| 0.0436 \| \| No log \| 49.0 \| 343 \| 0.4771 \| 0.84 \| 0.2509 \| 0.8623 \| 0.8400 \| 0.8281 \| 0.1908 \| 0.0430 \| \| No log \| 50.0 \| 350 \| 0.4793 \| 0.835 \| 0.2520 \| 0.8633 \| 0.835 \| 0.8222 \| 0.1900 \| 0.0435 \| \| No log \| 51.0 \| 357 \| 0.4786 \| 0.83 \| 0.2517 \| 0.8654 \| 0.83 \| 0.8159 \| 0.1684 \| 0.0437 \| \| No log \| 52.0 \| 364 \| 0.4792 \| 0.83 \| 0.2521 \| 0.8625 \| 0.83 \| 0.8166 \| 0.1915 \| 0.0430 \| \| No log \| 53.0 \| 371 \| 0.4785 \| 0.835 \| 0.2513 \| 0.8652 \| 0.835 \| 0.8222 \| 0.1853 \| 0.0434 \| \| No log \| 54.0 \| 378 \| 0.4798 \| 0.835 \| 0.2523 \| 0.8652 \| 0.835 \| 0.8222 \| 0.1767 \| 0.0437 \| \| No log \| 55.0 \| 385 \| 0.4791 \| 0.835 \| 0.2519 \| 0.8637 \| 0.835 \| 0.8222 \| 0.1891 \| 0.0435 \| \| No log \| 56.0 \| 392 \| 0.4790 \| 0.835 \| 0.2519 \| 0.8614 \| 0.835 \| 0.8222 \| 0.1749 \| 0.0429 \| \| No log \| 57.0 \| 399 \| 0.4782 \| 0.835 \| 0.2513 \| 0.8625 \| 0.835 \| 0.8222 \| 0.1909 \| 0.0433 \| \| No log \| 58.0 \| 406 \| 0.4794 \| 0.835 \| 0.2521 \| 0.8602 \| 0.835 \| 0.8222 \| 0.1758 \| 0.0435 \| \| No log \| 59.0 \| 413 \| 0.4790 \| 0.835 \| 0.2517 \| 0.8617 \| 0.835 \| 0.8222 \| 0.1754 \| 0.0432 \| \| No log \| 60.0 \| 420 \| 0.4791 \| 0.835 \| 0.2520 \| 0.8614 \| 0.835 \| 0.8222 \| 0.1830 \| 0.0430 \| \| No log \| 61.0 \| 427 \| 0.4789 \| 0.835 \| 0.2518 \| 0.8612 \| 0.835 \| 0.8222 \| 0.1870 \| 0.0432 \| \| No log \| 62.0 \| 434 \| 0.4792 \| 0.835 \| 0.2520 \| 0.8620 \| 0.835 \| 0.8222 \| 0.1902 \| 0.0433 \| \| No log \| 63.0 \| 441 \| 0.4789 \| 0.835 \| 0.2518 \| 0.8619 \| 0.835 \| 0.8222 \| 0.1997 \| 0.0431 \| \| No log \| 64.0 \| 448 \| 0.4797 \| 0.835 \| 0.2523 \| 0.8607 \| 0.835 \| 0.8222 \| 0.1833 \| 0.0434 \| \| No log \| 65.0 \| 455 \| 0.4797 \| 0.835 \| 0.2522 \| 0.8624 \| 0.835 \| 0.8222 \| 0.1922 \| 0.0434 \| \| No log \| 66.0 \| 462 \| 0.4791 \| 0.835 \| 0.2519 \| 0.8620 \| 0.835 \| 0.8222 \| 0.1894 \| 0.0430 \| \| No log \| 67.0 \| 469 \| 0.4792 \| 0.835 \| 0.2520 \| 0.8612 \| 0.835 \| 0.8222 \| 0.1885 \| 0.0433 \| \| No log \| 68.0 \| 476 \| 0.4796 \| 0.835 \| 0.2522 \| 0.8627 \| 0.835 \| 0.8222 \| 0.1918 \| 0.0433 \| \| No log \| 69.0 \| 483 \| 0.4793 \| 0.835 \| 0.2521 \| 0.8628 \| 0.835 \| 0.8222 \| 0.1828 \| 0.0433 \| \| No log \| 70.0 \| 490 \| 0.4792 \| 0.835 \| 0.2519 \| 0.8622 \| 0.835 \| 0.8222 \| 0.1918 \| 0.0432 \| \| No log \| 71.0 \| 497 \| 0.4797 \| 0.835 \| 0.2523 \| 0.8615 \| 0.835 \| 0.8222 \| 0.1836 \| 0.0434 \| \| 0.194 \| 72.0 \| 504 \| 0.4797 \| 0.835 \| 0.2522 \| 0.8618 \| 0.835 \| 0.8222 \| 0.1842 \| 0.0433 \| \| 0.194 \| 73.0 \| 511 \| 0.4794 \| 0.835 \| 0.2521 \| 0.8624 \| 0.835 \| 0.8222 \| 0.1914 \| 0.0432 \| \| 0.194 \| 74.0 \| 518 \| 0.4794 \| 0.835 \| 0.2521 \| 0.8617 \| 0.835 \| 0.8222 \| 0.1915 \| 0.0431 \| \| 0.194 \| 75.0 \| 525 \| 0.4796 \| 0.835 \| 0.2522 \| 0.8623 \| 0.835 \| 0.8222 \| 0.1917 \| 0.0434 \| \| 0.194 \| 76.0 \| 532 \| 0.4795 \| 0.835 \| 0.2520 \| 0.8622 \| 0.835 \| 0.8222 \| 0.1985 \| 0.0433 \| \| 0.194 \| 77.0 \| 539 \| 0.4795 \| 0.835 \| 0.2520 \| 0.8623 \| 0.835 \| 0.8222 \| 0.1985 \| 0.0432 \| \| 0.194 \| 78.0 \| 546 \| 0.4795 \| 0.835 \| 0.2522 \| 0.8621 \| 0.835 \| 0.8222 \| 0.1981 \| 0.0432 \| \| 0.194 \| 79.0 \| 553 \| 0.4798 \| 0.835 \| 0.2522 \| 0.8626 \| 0.835 \| 0.8222 \| 0.1909 \| 0.0433 \| \| 0.194 \| 80.0 \| 560 \| 0.4796 \| 0.835 \| 0.2521 \| 0.8630 \| 0.835 \| 0.8222 \| 0.1984 \| 0.0433 \| \| 0.194 \| 81.0 \| 567 \| 0.4797 \| 0.835 \| 0.2522 \| 0.8619 \| 0.835 \| 0.8222 \| 0.1902 \| 0.0434 \| \| 0.194 \| 82.0 \| 574 \| 0.4797 \| 0.835 \| 0.2522 \| 0.8631 \| 0.835 \| 0.8222 \| 0.1913 \| 0.0433 \| \| 0.194 \| 83.0 \| 581 \| 0.4797 \| 0.835 \| 0.2522 \| 0.8627 \| 0.835 \| 0.8222 \| 0.1909 \| 0.0433 \| \| 0.194 \| 84.0 \| 588 \| 0.4797 \| 0.835 \| 0.2522 \| 0.8623 \| 0.835 \| 0.8222 \| 0.1909 \| 0.0433 \| \| 0.194 \| 85.0 \| 595 \| 0.4797 \| 0.835 \| 0.2522 \| 0.8624 \| 0.835 \| 0.8222 \| 0.1909 \| 0.0434 \| \| 0.194 \| 86.0 \| 602 \| 0.4796 \| 0.835 \| 0.2522 \| 0.8623 \| 0.835 \| 0.8222 \| 0.1830 \| 0.0433 \| \| 0.194 \| 87.0 \| 609 \| 0.4797 \| 0.835 \| 0.2522 \| 0.8629 \| 0.835 \| 0.8222 \| 0.1909 \| 0.0434 \| \| 0.194 \| 88.0 \| 616 \| 0.4797 \| 0.835 \| 0.2521 \| 0.8634 \| 0.835 \| 0.8222 \| 0.1830 \| 0.0433 \| \| 0.194 \| 89.0 \| 623 \| 0.4797 \| 0.835 \| 0.2522 \| 0.8627 \| 0.835 \| 0.8222 \| 0.1910 \| 0.0434 \| \| 0.194 \| 90.0 \| 630 \| 0.4798 \| 0.835 \| 0.2523 \| 0.8627 \| 0.835 \| 0.8222 \| 0.1909 \| 0.0434 \| \| 0.194 \| 91.0 \| 637 \| 0.4797 \| 0.835 \| 0.2522 \| 0.8625 \| 0.835 \| 0.8222 \| 0.1909 \| 0.0434 \| \| 0.194 \| 92.0 \| 644 \| 0.4797 \| 0.835 \| 0.2522 \| 0.8630 \| 0.835 \| 0.8222 \| 0.1830 \| 0.0434 \| \| 0.194 \| 93.0 \| 651 \| 0.4798 \| 0.835 \| 0.2522 \| 0.8629 \| 0.835 \| 0.8222 \| 0.1910 \| 0.0434 \| \| 0.194 \| 94.0 \| 658 \| 0.4797 \| 0.835 \| 0.2522 \| 0.8628 \| 0.835 \| 0.8222 \| 0.1910 \| 0.0434 \| \| 0.194 \| 95.0 \| 665 \| 0.4797 \| 0.835 \| 0.2522 \| 0.8627 \| 0.835 \| 0.8222 \| 0.1910 \| 0.0434 \| \| 0.194 \| 96.0 \| 672 \| 0.4798 \| 0.835 \| 0.2522 \| 0.8627 \| 0.835 \| 0.8222 \| 0.1834 \| 0.0435 \| \| 0.194 \| 97.0 \| 679 \| 0.4797 \| 0.835 \| 0.2522 \| 0.8628 \| 0.835 \| 0.8222 \| 0.1830 \| 0.0434 \| \| 0.194 \| 98.0 \| 686 \| 0.4797 \| 0.835 \| 0.2522 \| 0.8628 \| 0.835 \| 0.8222 \| 0.1830 \| 0.0434 \| \| 0.194 \| 99.0 \| 693 \| 0.4797 \| 0.835 \| 0.2522 \| 0.8628 \| 0.835 \| 0.8222 \| 0.1830 \| 0.0434 \| \| 0.194 \| 100.0 \| 700 \| 0.4797 \| 0.835 \| 0.2522 \| 0.8627 \| 0.835 \| 0.8222 \| 0.1830 \| 0.0434 \| ### Framework versions - Transformers 4.26.1 - Pytorch 1.13.1.post200 - Datasets 2.9.0 - Tokenizers 0.13.2
FerhatDk/wav2vec2-base_music_speech_both_classification	FerhatDk	2023-07-10T17:56:34Z	167	0	transformers	[ "transformers", "pytorch", "tensorboard", "wav2vec2", "audio-classification", "generated_from_trainer", "license:apache-2.0", "endpoints_compatible", "region:us" ]	audio-classification	2023-07-10T17:00:30Z	--- license: apache-2.0 tags: - generated_from_trainer metrics: - accuracy model-index: - name: wav2vec2-base_music_speech_both_classification results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # wav2vec2-base_music_speech_both_classification This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.0586 - Accuracy: 0.9847 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_ratio: 0.1 - lr_scheduler_warmup_steps: 500 - num_epochs: 8 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\| \| 0.9458 \| 1.0 \| 66 \| 0.8468 \| 0.7405 \| \| 0.3785 \| 2.0 \| 132 \| 0.2951 \| 0.9771 \| \| 0.1762 \| 3.0 \| 198 \| 0.2639 \| 0.9313 \| \| 0.134 \| 4.0 \| 264 \| 0.1084 \| 0.9771 \| \| 0.0782 \| 5.0 \| 330 \| 0.0877 \| 0.9771 \| \| 0.0568 \| 6.0 \| 396 \| 0.0912 \| 0.9771 \| \| 0.0122 \| 7.0 \| 462 \| 0.4056 \| 0.9198 \| \| 0.059 \| 8.0 \| 528 \| 0.0586 \| 0.9847 \| ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3
grammarly/detexd-roberta-base	grammarly	2023-07-10T17:34:23Z	132	10	transformers	[ "transformers", "pytorch", "roberta", "text-classification", "en", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2023-03-21T18:44:55Z	--- license: apache-2.0 language: - en pipeline_tag: text-classification --- # DeTexD-RoBERTa-base delicate text detection This is a baseline RoBERTa-base model for the delicate text detection task. * Paper: [DeTexD: A Benchmark Dataset for Delicate Text Detection](TODO) * [GitHub repository](https://github.com/grammarly/detexd) The labels meaning according to the paper: - LABEL_0 -> non-delicate (0) - LABEL_1 -> very low risk (1) - LABEL_2 -> low risk (2) - LABEL_3 -> medium risk (3) - LABEL_4 -> high risk (4) - LABEL_5 -> very high risk (5) ## Classification example code Here's a short usage example with the torch library in a binary classification task: ```python from transformers import pipeline classifier = pipeline("text-classification", model="grammarly/detexd-roberta-base") def predict_binary_score(text: str): # get multiclass probability scores scores = classifier(text, top_k=None) # convert to a single score by summing the probability scores # for the higher-index classes return sum(score['score'] for score in scores if score['label'] in ('LABEL_3', 'LABEL_4', 'LABEL_5')) def predict_delicate(text: str, threshold=0.72496545): return predict_binary_score(text) > threshold print(predict_delicate("Time flies like an arrow. Fruit flies like a banana.")) ``` Expected output: ``` False ``` ## Citation Information ``` @inproceedings{chernodub-etal-2023-detexd, title = "{D}e{T}ex{D}: A Benchmark Dataset for Delicate Text Detection", author = "Yavnyi, Serhii and Sliusarenko, Oleksii and Razzaghi, Jade and Mo, Yichen and Hovakimyan, Knar and Chernodub, Artem", booktitle = "The 7th Workshop on Online Abuse and Harms (WOAH)", month = jul, year = "2023", address = "Toronto, Canada", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2023.woah-1.2", pages = "14--28", abstract = "Over the past few years, much research has been conducted to identify and regulate toxic language. However, few studies have addressed a broader range of sensitive texts that are not necessarily overtly toxic. In this paper, we introduce and define a new category of sensitive text called {``}delicate text.{''} We provide the taxonomy of delicate text and present a detailed annotation scheme. We annotate DeTexD, the first benchmark dataset for delicate text detection. The significance of the difference in the definitions is highlighted by the relative performance deltas between models trained each definitions and corpora and evaluated on the other. We make publicly available the DeTexD Benchmark dataset, annotation guidelines, and baseline model for delicate text detection.", } ```
AmbarB12/my_awesome_model	AmbarB12	2023-07-10T17:30:33Z	62	0	transformers	[ "transformers", "tf", "distilbert", "text-classification", "generated_from_keras_callback", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2023-07-09T18:03:55Z	--- license: apache-2.0 tags: - generated_from_keras_callback model-index: - name: AmbarB12/my_awesome_model results: [] --- <!-- This model card has been generated automatically according to the information Keras had access to. You should probably proofread and complete it, then remove this comment. --> # AmbarB12/my_awesome_model This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset. It achieves the following results on the evaluation set: - Train Loss: 0.0631 - Validation Loss: 0.2229 - Train Accuracy: 0.9306 - Epoch: 2 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 7810, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False} - training_precision: float32 ### Training results \| Train Loss \| Validation Loss \| Train Accuracy \| Epoch \| \|:----------:\|:---------------:\|:--------------:\|:-----:\| \| 0.2523 \| 0.1891 \| 0.927 \| 0 \| \| 0.1327 \| 0.2007 \| 0.9298 \| 1 \| \| 0.0631 \| 0.2229 \| 0.9306 \| 2 \| ### Framework versions - Transformers 4.30.2 - TensorFlow 2.12.0 - Datasets 2.13.1 - Tokenizers 0.13.3
cagarraz/rl_course_vizdoom_health_gathering_supreme	cagarraz	2023-07-10T17:23:21Z	0	0	sample-factory	[ "sample-factory", "tensorboard", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]	reinforcement-learning	2023-07-10T17:23:08Z	--- library_name: sample-factory tags: - deep-reinforcement-learning - reinforcement-learning - sample-factory model-index: - name: APPO results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: doom_health_gathering_supreme type: doom_health_gathering_supreme metrics: - type: mean_reward value: 3.94 +/- 0.20 name: mean_reward verified: false --- A(n) APPO model trained on the doom_health_gathering_supreme environment. This model was trained using Sample-Factory 2.0: https://github.com/alex-petrenko/sample-factory. Documentation for how to use Sample-Factory can be found at https://www.samplefactory.dev/ ## Downloading the model After installing Sample-Factory, download the model with: ``` python -m sample_factory.huggingface.load_from_hub -r cagarraz/rl_course_vizdoom_health_gathering_supreme ``` ## Using the model To run the model after download, use the `enjoy` script corresponding to this environment: ``` python -m .usr.local.lib.python3.10.dist-packages.ipykernel_launcher --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme ``` You can also upload models to the Hugging Face Hub using the same script with the `--push_to_hub` flag. See https://www.samplefactory.dev/10-huggingface/huggingface/ for more details ## Training with this model To continue training with this model, use the `train` script corresponding to this environment: ``` python -m .usr.local.lib.python3.10.dist-packages.ipykernel_launcher --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme --restart_behavior=resume --train_for_env_steps=10000000000 ``` Note, you may have to adjust `--train_for_env_steps` to a suitably high number as the experiment will resume at the number of steps it concluded at.
jordyvl/vit-small_tobacco3482_kd_CEKD_t1.5_a0.5	jordyvl	2023-07-10T17:17:44Z	163	0	transformers	[ "transformers", "pytorch", "vit", "image-classification", "generated_from_trainer", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	image-classification	2023-07-10T16:39:33Z	--- license: apache-2.0 tags: - generated_from_trainer metrics: - accuracy model-index: - name: vit-small_tobacco3482_kd_CEKD_t1.5_a0.5 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # vit-small_tobacco3482_kd_CEKD_t1.5_a0.5 This model is a fine-tuned version of [WinKawaks/vit-small-patch16-224](https://huggingface.co/WinKawaks/vit-small-patch16-224) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.4258 - Accuracy: 0.825 - Brier Loss: 0.2707 - Nll: 0.8867 - F1 Micro: 0.825 - F1 Macro: 0.8116 - Ece: 0.2129 - Aurc: 0.0681 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 100 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| Brier Loss \| Nll \| F1 Micro \| F1 Macro \| Ece \| Aurc \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\|:----------:\|:------:\|:--------:\|:--------:\|:------:\|:------:\| \| No log \| 1.0 \| 7 \| 1.7307 \| 0.22 \| 0.8748 \| 5.3766 \| 0.22 \| 0.1294 \| 0.2444 \| 0.6913 \| \| No log \| 2.0 \| 14 \| 1.3514 \| 0.405 \| 0.7426 \| 3.5573 \| 0.405 \| 0.2280 \| 0.2900 \| 0.4026 \| \| No log \| 3.0 \| 21 \| 0.9121 \| 0.62 \| 0.5647 \| 1.9398 \| 0.62 \| 0.5595 \| 0.2879 \| 0.2015 \| \| No log \| 4.0 \| 28 \| 0.7084 \| 0.695 \| 0.4179 \| 1.7042 \| 0.695 \| 0.6379 \| 0.2305 \| 0.1177 \| \| No log \| 5.0 \| 35 \| 0.7167 \| 0.735 \| 0.3862 \| 1.7929 \| 0.735 \| 0.7392 \| 0.2380 \| 0.1046 \| \| No log \| 6.0 \| 42 \| 0.6442 \| 0.765 \| 0.3625 \| 1.5688 \| 0.765 \| 0.7549 \| 0.2371 \| 0.1034 \| \| No log \| 7.0 \| 49 \| 0.6147 \| 0.805 \| 0.3410 \| 1.5975 \| 0.805 \| 0.7789 \| 0.2438 \| 0.1042 \| \| No log \| 8.0 \| 56 \| 0.6444 \| 0.775 \| 0.3446 \| 1.2309 \| 0.775 \| 0.7725 \| 0.2305 \| 0.0911 \| \| No log \| 9.0 \| 63 \| 0.5964 \| 0.8 \| 0.3219 \| 1.3613 \| 0.8000 \| 0.7784 \| 0.2446 \| 0.0734 \| \| No log \| 10.0 \| 70 \| 0.5700 \| 0.82 \| 0.3160 \| 1.2605 \| 0.82 \| 0.7860 \| 0.2301 \| 0.0632 \| \| No log \| 11.0 \| 77 \| 0.5663 \| 0.79 \| 0.3176 \| 1.2939 \| 0.79 \| 0.7643 \| 0.2315 \| 0.0666 \| \| No log \| 12.0 \| 84 \| 0.5111 \| 0.825 \| 0.3143 \| 1.1082 \| 0.825 \| 0.8082 \| 0.2519 \| 0.0844 \| \| No log \| 13.0 \| 91 \| 0.5228 \| 0.78 \| 0.3156 \| 0.9444 \| 0.78 \| 0.7773 \| 0.1941 \| 0.0650 \| \| No log \| 14.0 \| 98 \| 0.5792 \| 0.78 \| 0.3409 \| 1.5054 \| 0.78 \| 0.7725 \| 0.2061 \| 0.1019 \| \| No log \| 15.0 \| 105 \| 0.4905 \| 0.83 \| 0.2912 \| 1.0068 \| 0.83 \| 0.8266 \| 0.2324 \| 0.0545 \| \| No log \| 16.0 \| 112 \| 0.4990 \| 0.825 \| 0.2961 \| 1.1452 \| 0.825 \| 0.8140 \| 0.2188 \| 0.0632 \| \| No log \| 17.0 \| 119 \| 0.4900 \| 0.805 \| 0.2940 \| 1.2027 \| 0.805 \| 0.8018 \| 0.2188 \| 0.0860 \| \| No log \| 18.0 \| 126 \| 0.4755 \| 0.805 \| 0.2988 \| 1.0223 \| 0.805 \| 0.7789 \| 0.2229 \| 0.0792 \| \| No log \| 19.0 \| 133 \| 0.4398 \| 0.81 \| 0.2679 \| 0.9732 \| 0.81 \| 0.7830 \| 0.2085 \| 0.0585 \| \| No log \| 20.0 \| 140 \| 0.4766 \| 0.805 \| 0.2992 \| 0.9730 \| 0.805 \| 0.7934 \| 0.2141 \| 0.0662 \| \| No log \| 21.0 \| 147 \| 0.4615 \| 0.835 \| 0.2867 \| 0.9343 \| 0.835 \| 0.8219 \| 0.1999 \| 0.0751 \| \| No log \| 22.0 \| 154 \| 0.4343 \| 0.825 \| 0.2641 \| 1.1353 \| 0.825 \| 0.8070 \| 0.2095 \| 0.0603 \| \| No log \| 23.0 \| 161 \| 0.4291 \| 0.85 \| 0.2660 \| 1.0109 \| 0.85 \| 0.8365 \| 0.2435 \| 0.0615 \| \| No log \| 24.0 \| 168 \| 0.4263 \| 0.855 \| 0.2653 \| 0.9395 \| 0.855 \| 0.8440 \| 0.2445 \| 0.0623 \| \| No log \| 25.0 \| 175 \| 0.4338 \| 0.845 \| 0.2700 \| 0.8794 \| 0.845 \| 0.8349 \| 0.2254 \| 0.0584 \| \| No log \| 26.0 \| 182 \| 0.4305 \| 0.835 \| 0.2648 \| 0.9062 \| 0.835 \| 0.8322 \| 0.2113 \| 0.0658 \| \| No log \| 27.0 \| 189 \| 0.4262 \| 0.84 \| 0.2683 \| 0.9967 \| 0.8400 \| 0.8291 \| 0.2240 \| 0.0670 \| \| No log \| 28.0 \| 196 \| 0.4329 \| 0.83 \| 0.2724 \| 0.9016 \| 0.83 \| 0.8239 \| 0.2016 \| 0.0685 \| \| No log \| 29.0 \| 203 \| 0.4233 \| 0.845 \| 0.2653 \| 0.9115 \| 0.845 \| 0.8375 \| 0.2005 \| 0.0634 \| \| No log \| 30.0 \| 210 \| 0.4204 \| 0.84 \| 0.2638 \| 0.8892 \| 0.8400 \| 0.8348 \| 0.2175 \| 0.0633 \| \| No log \| 31.0 \| 217 \| 0.4240 \| 0.83 \| 0.2684 \| 0.8871 \| 0.83 \| 0.8217 \| 0.2128 \| 0.0660 \| \| No log \| 32.0 \| 224 \| 0.4246 \| 0.84 \| 0.2677 \| 0.8867 \| 0.8400 \| 0.8307 \| 0.2117 \| 0.0670 \| \| No log \| 33.0 \| 231 \| 0.4247 \| 0.83 \| 0.2690 \| 0.8917 \| 0.83 \| 0.8202 \| 0.2084 \| 0.0679 \| \| No log \| 34.0 \| 238 \| 0.4218 \| 0.84 \| 0.2660 \| 0.8848 \| 0.8400 \| 0.8326 \| 0.2138 \| 0.0663 \| \| No log \| 35.0 \| 245 \| 0.4220 \| 0.845 \| 0.2667 \| 0.8926 \| 0.845 \| 0.8354 \| 0.2109 \| 0.0655 \| \| No log \| 36.0 \| 252 \| 0.4247 \| 0.83 \| 0.2694 \| 0.8854 \| 0.83 \| 0.8202 \| 0.2213 \| 0.0683 \| \| No log \| 37.0 \| 259 \| 0.4239 \| 0.84 \| 0.2683 \| 0.8849 \| 0.8400 \| 0.8326 \| 0.2163 \| 0.0670 \| \| No log \| 38.0 \| 266 \| 0.4239 \| 0.835 \| 0.2689 \| 0.8876 \| 0.835 \| 0.8208 \| 0.2118 \| 0.0672 \| \| No log \| 39.0 \| 273 \| 0.4252 \| 0.83 \| 0.2696 \| 0.8885 \| 0.83 \| 0.8180 \| 0.2064 \| 0.0682 \| \| No log \| 40.0 \| 280 \| 0.4237 \| 0.835 \| 0.2686 \| 0.8867 \| 0.835 \| 0.8208 \| 0.2211 \| 0.0675 \| \| No log \| 41.0 \| 287 \| 0.4256 \| 0.83 \| 0.2700 \| 0.8847 \| 0.83 \| 0.8180 \| 0.2253 \| 0.0682 \| \| No log \| 42.0 \| 294 \| 0.4243 \| 0.835 \| 0.2692 \| 0.8839 \| 0.835 \| 0.8208 \| 0.2130 \| 0.0675 \| \| No log \| 43.0 \| 301 \| 0.4248 \| 0.83 \| 0.2695 \| 0.8850 \| 0.83 \| 0.8180 \| 0.2237 \| 0.0682 \| \| No log \| 44.0 \| 308 \| 0.4246 \| 0.83 \| 0.2694 \| 0.8847 \| 0.83 \| 0.8180 \| 0.2383 \| 0.0680 \| \| No log \| 45.0 \| 315 \| 0.4253 \| 0.83 \| 0.2699 \| 0.8858 \| 0.83 \| 0.8180 \| 0.2200 \| 0.0681 \| \| No log \| 46.0 \| 322 \| 0.4246 \| 0.83 \| 0.2694 \| 0.8857 \| 0.83 \| 0.8180 \| 0.2311 \| 0.0679 \| \| No log \| 47.0 \| 329 \| 0.4253 \| 0.83 \| 0.2700 \| 0.8843 \| 0.83 \| 0.8180 \| 0.2312 \| 0.0682 \| \| No log \| 48.0 \| 336 \| 0.4252 \| 0.83 \| 0.2698 \| 0.8830 \| 0.83 \| 0.8180 \| 0.2177 \| 0.0682 \| \| No log \| 49.0 \| 343 \| 0.4257 \| 0.83 \| 0.2703 \| 0.8848 \| 0.83 \| 0.8180 \| 0.2315 \| 0.0683 \| \| No log \| 50.0 \| 350 \| 0.4256 \| 0.83 \| 0.2703 \| 0.8833 \| 0.83 \| 0.8180 \| 0.2331 \| 0.0684 \| \| No log \| 51.0 \| 357 \| 0.4254 \| 0.83 \| 0.2703 \| 0.8863 \| 0.83 \| 0.8180 \| 0.2422 \| 0.0681 \| \| No log \| 52.0 \| 364 \| 0.4261 \| 0.83 \| 0.2707 \| 0.8864 \| 0.83 \| 0.8180 \| 0.2424 \| 0.0683 \| \| No log \| 53.0 \| 371 \| 0.4249 \| 0.83 \| 0.2700 \| 0.8855 \| 0.83 \| 0.8180 \| 0.2195 \| 0.0679 \| \| No log \| 54.0 \| 378 \| 0.4255 \| 0.83 \| 0.2704 \| 0.8846 \| 0.83 \| 0.8180 \| 0.2342 \| 0.0682 \| \| No log \| 55.0 \| 385 \| 0.4256 \| 0.825 \| 0.2704 \| 0.8861 \| 0.825 \| 0.8116 \| 0.2357 \| 0.0682 \| \| No log \| 56.0 \| 392 \| 0.4264 \| 0.83 \| 0.2708 \| 0.8853 \| 0.83 \| 0.8180 \| 0.2345 \| 0.0682 \| \| No log \| 57.0 \| 399 \| 0.4257 \| 0.825 \| 0.2706 \| 0.8864 \| 0.825 \| 0.8116 \| 0.2353 \| 0.0682 \| \| No log \| 58.0 \| 406 \| 0.4258 \| 0.825 \| 0.2704 \| 0.8841 \| 0.825 \| 0.8116 \| 0.2271 \| 0.0681 \| \| No log \| 59.0 \| 413 \| 0.4255 \| 0.825 \| 0.2703 \| 0.8856 \| 0.825 \| 0.8116 \| 0.2267 \| 0.0680 \| \| No log \| 60.0 \| 420 \| 0.4259 \| 0.825 \| 0.2709 \| 0.8842 \| 0.825 \| 0.8116 \| 0.2269 \| 0.0683 \| \| No log \| 61.0 \| 427 \| 0.4254 \| 0.83 \| 0.2702 \| 0.8852 \| 0.83 \| 0.8180 \| 0.2265 \| 0.0680 \| \| No log \| 62.0 \| 434 \| 0.4261 \| 0.83 \| 0.2707 \| 0.8851 \| 0.83 \| 0.8180 \| 0.2346 \| 0.0682 \| \| No log \| 63.0 \| 441 \| 0.4257 \| 0.825 \| 0.2704 \| 0.8854 \| 0.825 \| 0.8116 \| 0.2232 \| 0.0682 \| \| No log \| 64.0 \| 448 \| 0.4261 \| 0.825 \| 0.2708 \| 0.8845 \| 0.825 \| 0.8116 \| 0.2264 \| 0.0683 \| \| No log \| 65.0 \| 455 \| 0.4259 \| 0.825 \| 0.2706 \| 0.8862 \| 0.825 \| 0.8116 \| 0.2204 \| 0.0682 \| \| No log \| 66.0 \| 462 \| 0.4258 \| 0.825 \| 0.2707 \| 0.8856 \| 0.825 \| 0.8116 \| 0.2193 \| 0.0682 \| \| No log \| 67.0 \| 469 \| 0.4255 \| 0.83 \| 0.2703 \| 0.8852 \| 0.83 \| 0.8180 \| 0.2190 \| 0.0681 \| \| No log \| 68.0 \| 476 \| 0.4260 \| 0.825 \| 0.2708 \| 0.8860 \| 0.825 \| 0.8116 \| 0.2196 \| 0.0682 \| \| No log \| 69.0 \| 483 \| 0.4259 \| 0.825 \| 0.2708 \| 0.8858 \| 0.825 \| 0.8116 \| 0.2195 \| 0.0682 \| \| No log \| 70.0 \| 490 \| 0.4255 \| 0.825 \| 0.2703 \| 0.8857 \| 0.825 \| 0.8116 \| 0.2135 \| 0.0682 \| \| No log \| 71.0 \| 497 \| 0.4258 \| 0.825 \| 0.2707 \| 0.8857 \| 0.825 \| 0.8116 \| 0.2205 \| 0.0681 \| \| 0.1816 \| 72.0 \| 504 \| 0.4261 \| 0.825 \| 0.2708 \| 0.8857 \| 0.825 \| 0.8116 \| 0.2198 \| 0.0682 \| \| 0.1816 \| 73.0 \| 511 \| 0.4259 \| 0.825 \| 0.2706 \| 0.8852 \| 0.825 \| 0.8116 \| 0.2192 \| 0.0682 \| \| 0.1816 \| 74.0 \| 518 \| 0.4259 \| 0.825 \| 0.2707 \| 0.8856 \| 0.825 \| 0.8116 \| 0.2290 \| 0.0681 \| \| 0.1816 \| 75.0 \| 525 \| 0.4257 \| 0.825 \| 0.2706 \| 0.8864 \| 0.825 \| 0.8116 \| 0.2337 \| 0.0681 \| \| 0.1816 \| 76.0 \| 532 \| 0.4259 \| 0.825 \| 0.2707 \| 0.8855 \| 0.825 \| 0.8116 \| 0.2211 \| 0.0681 \| \| 0.1816 \| 77.0 \| 539 \| 0.4255 \| 0.825 \| 0.2704 \| 0.8860 \| 0.825 \| 0.8116 \| 0.2137 \| 0.0680 \| \| 0.1816 \| 78.0 \| 546 \| 0.4258 \| 0.825 \| 0.2707 \| 0.8868 \| 0.825 \| 0.8116 \| 0.2274 \| 0.0682 \| \| 0.1816 \| 79.0 \| 553 \| 0.4260 \| 0.825 \| 0.2708 \| 0.8859 \| 0.825 \| 0.8116 \| 0.2209 \| 0.0682 \| \| 0.1816 \| 80.0 \| 560 \| 0.4260 \| 0.825 \| 0.2708 \| 0.8864 \| 0.825 \| 0.8116 \| 0.2135 \| 0.0681 \| \| 0.1816 \| 81.0 \| 567 \| 0.4259 \| 0.825 \| 0.2707 \| 0.8859 \| 0.825 \| 0.8116 \| 0.2134 \| 0.0682 \| \| 0.1816 \| 82.0 \| 574 \| 0.4258 \| 0.825 \| 0.2706 \| 0.8862 \| 0.825 \| 0.8116 \| 0.2062 \| 0.0681 \| \| 0.1816 \| 83.0 \| 581 \| 0.4259 \| 0.825 \| 0.2707 \| 0.8866 \| 0.825 \| 0.8116 \| 0.2204 \| 0.0681 \| \| 0.1816 \| 84.0 \| 588 \| 0.4259 \| 0.825 \| 0.2707 \| 0.8868 \| 0.825 \| 0.8116 \| 0.2204 \| 0.0681 \| \| 0.1816 \| 85.0 \| 595 \| 0.4257 \| 0.825 \| 0.2706 \| 0.8861 \| 0.825 \| 0.8116 \| 0.2141 \| 0.0682 \| \| 0.1816 \| 86.0 \| 602 \| 0.4258 \| 0.825 \| 0.2707 \| 0.8861 \| 0.825 \| 0.8116 \| 0.2140 \| 0.0682 \| \| 0.1816 \| 87.0 \| 609 \| 0.4258 \| 0.825 \| 0.2707 \| 0.8867 \| 0.825 \| 0.8116 \| 0.2137 \| 0.0680 \| \| 0.1816 \| 88.0 \| 616 \| 0.4259 \| 0.825 \| 0.2707 \| 0.8866 \| 0.825 \| 0.8116 \| 0.2129 \| 0.0681 \| \| 0.1816 \| 89.0 \| 623 \| 0.4258 \| 0.825 \| 0.2707 \| 0.8866 \| 0.825 \| 0.8116 \| 0.2205 \| 0.0681 \| \| 0.1816 \| 90.0 \| 630 \| 0.4259 \| 0.825 \| 0.2707 \| 0.8865 \| 0.825 \| 0.8116 \| 0.2053 \| 0.0680 \| \| 0.1816 \| 91.0 \| 637 \| 0.4258 \| 0.825 \| 0.2706 \| 0.8868 \| 0.825 \| 0.8116 \| 0.2130 \| 0.0681 \| \| 0.1816 \| 92.0 \| 644 \| 0.4258 \| 0.825 \| 0.2706 \| 0.8870 \| 0.825 \| 0.8116 \| 0.2129 \| 0.0680 \| \| 0.1816 \| 93.0 \| 651 \| 0.4258 \| 0.825 \| 0.2706 \| 0.8868 \| 0.825 \| 0.8116 \| 0.2129 \| 0.0681 \| \| 0.1816 \| 94.0 \| 658 \| 0.4258 \| 0.825 \| 0.2707 \| 0.8867 \| 0.825 \| 0.8116 \| 0.2129 \| 0.0681 \| \| 0.1816 \| 95.0 \| 665 \| 0.4258 \| 0.825 \| 0.2707 \| 0.8867 \| 0.825 \| 0.8116 \| 0.2053 \| 0.0680 \| \| 0.1816 \| 96.0 \| 672 \| 0.4259 \| 0.825 \| 0.2707 \| 0.8866 \| 0.825 \| 0.8116 \| 0.2053 \| 0.0681 \| \| 0.1816 \| 97.0 \| 679 \| 0.4258 \| 0.825 \| 0.2707 \| 0.8868 \| 0.825 \| 0.8116 \| 0.2129 \| 0.0681 \| \| 0.1816 \| 98.0 \| 686 \| 0.4258 \| 0.825 \| 0.2707 \| 0.8868 \| 0.825 \| 0.8116 \| 0.2129 \| 0.0680 \| \| 0.1816 \| 99.0 \| 693 \| 0.4258 \| 0.825 \| 0.2707 \| 0.8868 \| 0.825 \| 0.8116 \| 0.2129 \| 0.0681 \| \| 0.1816 \| 100.0 \| 700 \| 0.4258 \| 0.825 \| 0.2707 \| 0.8867 \| 0.825 \| 0.8116 \| 0.2129 \| 0.0681 \| ### Framework versions - Transformers 4.26.1 - Pytorch 1.13.1.post200 - Datasets 2.9.0 - Tokenizers 0.13.2
opendiffusion/sentimentcheck	opendiffusion	2023-07-10T16:58:49Z	0	0	tf-keras	[ "tf-keras", "bert", "region:us" ]	null	2023-05-11T18:26:04Z	# Intro OpenDiffusion's SentimentCheck is an AI model built upon Tensorflow+Keras+Pickles. SentimentCheck harnesses the power of deep learning algorithms to accurately classify sentiment in text, making it a flexible tool for businesses, researchers, and developers. ## Usage --- language: - en - nl - de - fr - it - es license: mit --- # bert-base-multilingual-uncased-sentiment This a bert-base-multilingual-uncased model finetuned for sentiment analysis on product reviews in six languages: English, Dutch, German, French, Spanish and Italian. It predicts the sentiment of the review as a number of stars (between 1 and 5). This model is intended for direct use as a sentiment analysis model for product reviews in any of the six languages above, or for further finetuning on related sentiment analysis tasks. ## Training data Here is the number of product reviews we used for finetuning the model: \| Language \| Number of reviews \| \| -------- \| ----------------- \| \| English \| 150k \| \| Dutch \| 80k \| \| German \| 137k \| \| French \| 140k \| \| Italian \| 72k \| \| Spanish \| 50k \| ## Accuracy The finetuned model obtained the following accuracy on 5,000 held-out product reviews in each of the languages: - Accuracy (exact) is the exact match on the number of stars. - Accuracy (off-by-1) is the percentage of reviews where the number of stars the model predicts differs by a maximum of 1 from the number given by the human reviewer. \| Language \| Accuracy (exact) \| Accuracy (off-by-1) \| \| -------- \| ---------------------- \| ------------------- \| \| English \| 67% \| 95% \| Dutch \| 57% \| 93% \| German \| 61% \| 94% \| French \| 59% \| 94% \| Italian \| 59% \| 95% \| Spanish \| 58% \| 95%
Umer1542/task-b-classification	Umer1542	2023-07-10T16:35:37Z	160	0	transformers	[ "transformers", "pytorch", "opt", "text-classification", "en", "license:other", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-classification	2023-07-10T15:47:23Z	--- license: other language: - en metrics: - accuracy - f1 - recall pipeline_tag: text-classification ---
dashan1992/dsl2	dashan1992	2023-07-10T16:35:33Z	0	0	peft	[ "peft", "region:us" ]	null	2023-07-10T16:34:19Z	--- library_name: peft --- ## Training procedure The following `bitsandbytes` quantization config was used during training: - load_in_8bit: True - load_in_4bit: False - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: fp4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: float32 ### Framework versions - PEFT 0.4.0.dev0
yhyhy3/open_llama_7b_v2_med_instruct	yhyhy3	2023-07-10T16:22:39Z	1,461	8	transformers	[ "transformers", "pytorch", "llama", "text-generation", "medical", "code", "en", "dataset:ehartford/dolphin", "dataset:LinhDuong/chatdoctor-200k", "dataset:sahil2801/code_instructions_120k", "dataset:medalpaca/medical_meadow_mediqa", "dataset:kaiokendev/SuperCOT-dataset", "dataset:tiiuae/falcon-refinedweb", "dataset:bigcode/starcoderdata", "dataset:togethercomputer/RedPajama-Data-1T", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2023-07-09T17:19:43Z	--- license: apache-2.0 datasets: - ehartford/dolphin - LinhDuong/chatdoctor-200k - sahil2801/code_instructions_120k - medalpaca/medical_meadow_mediqa - kaiokendev/SuperCOT-dataset - tiiuae/falcon-refinedweb - bigcode/starcoderdata - togethercomputer/RedPajama-Data-1T language: - en library_name: transformers pipeline_tag: text-generation tags: - medical - code --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> This model is an instruction-tuned Open LLaMa model with 7B parameters, with specialities in medical QA and code instruction. ## Model Details <!-- Provide a longer summary of what this model is. --> - Model type: LlamaForCausalLM - Language(s) (NLP): English - License: Apache 2.0 - Finetuned from model (QLoRA): [openlm-research/open_llama_7b_v2](https://huggingface.co/openlm-research/open_llama_7b_v2) ## How to Get Started with the Model Use the code below to get started with the model. ```py import torch from transformers import LlamaTokenizer, LlamaForCausalLM model_path = 'yhyhy3/open_llama_7b_v2_med_dolphin_qlora_merged' tokenizer = LlamaTokenizer.from_pretrained(model_path) model = LlamaForCausalLM.from_pretrained( model_path, torch_dtype=torch.float16, device_map='auto', ) prompt = '''### Instruction: Answer the following question. ### Input: What is the capital of New Jersey? ### Response:''' input_ids = tokenizer(prompt, return_tensors="pt").input_ids generation_output = model.generate( input_ids=input_ids, max_new_tokens=32 ) print(tokenizer.decode(generation_output[0])) ``` ## Training Details ### Training Data Converted the following datasets to alpaca:instruction format. 1. [ehartford/dolphin](https://huggingface.co/datasets/ehartford/dolphin) - ORCA style dataset generously created by [Eric Hartford](https://huggingface.co/ehartford) - Only used the 1 million GPT4 generated instructions file [flan1m-alpaca-uncensored.jsonl](https://huggingface.co/datasets/ehartford/dolphin/blob/main/flan1m-alpaca-uncensored.jsonl). 2. [LinhDuong/chatdoctor-200k](https://huggingface.co/datasets/LinhDuong/chatdoctor-200k) - Refined dataset sourced from icliniq medical QA forum 3. [sahil2801/code_instructions_120k](https://huggingface.co/datasets/sahil2801/code_instructions_120k) - Code instruction dataset generously created by Sahil Chaudhary from ThreeSixty AI 4. [medalpaca/medical_meadow_mediqa](https://huggingface.co/datasets/medalpaca/medical_meadow_mediqa) - MEDIQA is a dataset of manually generated, question-driven summaries of multi and single document answers to consumer health questions from medalpaca group. 5. [kaiokendev/SuperCOT-dataset](https://huggingface.co/datasets/kaiokendev/SuperCOT-dataset) - Code instruction dataset generously created by Kaio Ken ### Training Procedure Trained using [axolotl](https://github.com/OpenAccess-AI-Collective/axolotl) QLoRa on [RunPod](https://www.runpod.io/console/gpu-cloud) 8x A6000 on Community Cloud for 3 epochs (~14 hours - ~$70). <details> <summary>axolotl training config:</summary> ```yaml base_model: openlm-research/open_llama_7b_v2 base_model_config: openlm-research/open_llama_7b_v2 model_type: LlamaForCausalLM tokenizer_type: LlamaTokenizer load_in_8bit: false load_in_4bit: true strict: false push_dataset_to_hub: hub_model_id: hf_use_auth_token: datasets: - path: json type: alpaca data_files: /disk/flan1m-alpaca-uncensored.jsonl shards: 8 - path: sahil2801/code_instructions_120k type: alpaca - path: LinhDuong/chatdoctor-200k type: alpaca shards: 2 - path: kaiokendev/SuperCOT-dataset type: alpaca - path: medalpaca/medical_meadow_mediqa type: alpaca dataset_prepared_path: last_run_prepared val_set_size: 0.01 adapter: qlora lora_model_dir: sequence_len: 2048 max_packed_sequence_len: 2048 lora_r: 8 lora_alpha: 32 lora_dropout: 0.05 lora_target_modules: lora_target_linear: true lora_fan_in_fan_out: wandb_mode: true wandb_project: wandb_watch: wandb_run_id: wandb_log_model: 'openllama_checkpoint' output_dir: /disk/open_llama_7b_v2_dolphin_qlora gradient_accumulation_steps: 2 micro_batch_size: 16 num_epochs: 3 optimizer: paged_adamw_32bit torchdistx_path: lr_scheduler: cosine learning_rate: 0.0002 train_on_inputs: false group_by_length: false bf16: true fp16: false tf32: true gradient_checkpointing: true early_stopping_patience: resume_from_checkpoint: local_rank: logging_steps: 1 xformers_attention: true flash_attention: gptq_groupsize: gptq_model_v1: warmup_steps: 1000 eval_steps: 5000 save_steps: debug: deepspeed: weight_decay: 0.0000001 fsdp: fsdp_config: special_tokens: bos_token: "<s>" eos_token: "</s>" unk_token: "<unk>" ``` </details>
Den4ikAI/paraphrase_detector	Den4ikAI	2023-07-10T16:13:56Z	2	0	sentence-transformers	[ "sentence-transformers", "pytorch", "bert", "feature-extraction", "sentence-similarity", "transformers", "autotrain_compatible", "text-embeddings-inference", "endpoints_compatible", "region:us" ]	sentence-similarity	2023-07-10T16:09:10Z	--- pipeline_tag: sentence-similarity tags: - sentence-transformers - feature-extraction - sentence-similarity - transformers --- # {MODEL_NAME} This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 312 dimensional dense vector space and can be used for tasks like clustering or semantic search. <!--- Describe your model here --> ## Usage (Sentence-Transformers) Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed: ``` pip install -U sentence-transformers ``` Then you can use the model like this: ```python from sentence_transformers import SentenceTransformer sentences = ["This is an example sentence", "Each sentence is converted"] model = SentenceTransformer('{MODEL_NAME}') embeddings = model.encode(sentences) print(embeddings) ``` ## Usage (HuggingFace Transformers) Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings. ```python from transformers import AutoTokenizer, AutoModel import torch #Mean Pooling - Take attention mask into account for correct averaging def mean_pooling(model_output, attention_mask): token_embeddings = model_output[0] #First element of model_output contains all token embeddings input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float() return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9) # Sentences we want sentence embeddings for sentences = ['This is an example sentence', 'Each sentence is converted'] # Load model from HuggingFace Hub tokenizer = AutoTokenizer.from_pretrained('{MODEL_NAME}') model = AutoModel.from_pretrained('{MODEL_NAME}') # Tokenize sentences encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt') # Compute token embeddings with torch.no_grad(): model_output = model(*encoded_input) # Perform pooling. In this case, mean pooling. sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask']) print("Sentence embeddings:") print(sentence_embeddings) ``` ## Evaluation Results <!--- Describe how your model was evaluated --> For an automated evaluation of this model, see the Sentence Embeddings Benchmark: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME}) ## Training The model was trained with the parameters: DataLoader: `torch.utils.data.dataloader.DataLoader` of length 21 with parameters: ``` {'batch_size': 2048, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'} ``` Loss*: `sentence_transformers.losses.ContrastiveLoss.ContrastiveLoss` with parameters: ``` {'distance_metric': 'SiameseDistanceMetric.COSINE_DISTANCE', 'margin': 0.5, 'size_average': True} ``` Parameters of the fit()-Method: ``` { "epochs": 50, "evaluation_steps": 200, "evaluator": "sentence_transformers.evaluation.BinaryClassificationEvaluator.BinaryClassificationEvaluator", "max_grad_norm": 1, "optimizer_class": "<class 'torch.optim.adamw.AdamW'>", "optimizer_params": { "lr": 2e-05 }, "scheduler": "WarmupLinear", "steps_per_epoch": null, "warmup_steps": 105, "weight_decay": 1e-05 } ``` ## Full Model Architecture ``` SentenceTransformer( (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel (1): Pooling({'word_embedding_dimension': 312, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False}) ) ``` ## Citing & Authors <!--- Describe where people can find more information -->
uw-madison/mra-base-512-4	uw-madison	2023-07-10T16:11:54Z	1,482	1	transformers	[ "transformers", "pytorch", "mra", "fill-mask", "arxiv:2207.10284", "autotrain_compatible", "endpoints_compatible", "region:us" ]	fill-mask	2023-06-23T06:04:05Z	# MRA MRA model for masked language modeling (MLM) for sequence length 512. ## About MRA The MRA model was proposed in [Multi Resolution Analysis (MRA) for Approximate Self-Attention](https://arxiv.org/abs/2207.10284) by Zhanpeng Zeng, Sourav Pal, Jeffery Kline, Glenn M Fung, and Vikas Singh. The abstract from the paper is the following: Transformers have emerged as a preferred model for many tasks in natural langugage processing and vision. Recent efforts on training and deploying Transformers more efficiently have identified many strategies to approximate the self-attention matrix, a key module in a Transformer architecture. Effective ideas include various prespecified sparsity patterns, low-rank basis expansions and combinations thereof. In this paper, we revisit classical Multiresolution Analysis (MRA) concepts such as Wavelets, whose potential value in this setting remains underexplored thus far. We show that simple approximations based on empirical feedback and design choices informed by modern hardware and implementation challenges, eventually yield a MRA-based approach for self-attention with an excellent performance profile across most criteria of interest. We undertake an extensive set of experiments and demonstrate that this multi-resolution scheme outperforms most efficient self-attention proposals and is favorable for both short and long sequences. Code is available at https://github.com/mlpen/mra-attention. This model was contributed by [novice03](https://huggingface.co/novice03). The original code can be found [here](https://github.com/mlpen/mra-attention).
jordyvl/vit-tiny_tobacco3482_kd_MSE	jordyvl	2023-07-10T15:57:47Z	163	0	transformers	[ "transformers", "pytorch", "vit", "image-classification", "generated_from_trainer", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	image-classification	2023-07-10T15:22:05Z	--- license: apache-2.0 tags: - generated_from_trainer metrics: - accuracy model-index: - name: vit-tiny_tobacco3482_kd_MSE results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # vit-tiny_tobacco3482_kd_MSE This model is a fine-tuned version of [WinKawaks/vit-tiny-patch16-224](https://huggingface.co/WinKawaks/vit-tiny-patch16-224) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.2482 - Accuracy: 0.82 - Brier Loss: 0.3226 - Nll: 0.8343 - F1 Micro: 0.82 - F1 Macro: 0.8090 - Ece: 0.2625 - Aurc: 0.0606 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 100 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| Brier Loss \| Nll \| F1 Micro \| F1 Macro \| Ece \| Aurc \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\|:----------:\|:------:\|:--------:\|:--------:\|:------:\|:------:\| \| No log \| 1.0 \| 7 \| 2.6314 \| 0.165 \| 1.0293 \| 8.4704 \| 0.165 \| 0.0552 \| 0.3856 \| 0.8464 \| \| No log \| 2.0 \| 14 \| 1.4800 \| 0.12 \| 0.9052 \| 7.3409 \| 0.12 \| 0.0997 \| 0.2469 \| 0.8374 \| \| No log \| 3.0 \| 21 \| 1.0627 \| 0.34 \| 0.8400 \| 5.5369 \| 0.34 \| 0.2006 \| 0.3075 \| 0.5758 \| \| No log \| 4.0 \| 28 \| 0.8429 \| 0.42 \| 0.7462 \| 3.2442 \| 0.4200 \| 0.3362 \| 0.3072 \| 0.3692 \| \| No log \| 5.0 \| 35 \| 0.7060 \| 0.535 \| 0.6558 \| 2.7042 \| 0.535 \| 0.4295 \| 0.2993 \| 0.2677 \| \| No log \| 6.0 \| 42 \| 0.5950 \| 0.635 \| 0.6056 \| 2.0779 \| 0.635 \| 0.5021 \| 0.3375 \| 0.1948 \| \| No log \| 7.0 \| 49 \| 0.4865 \| 0.67 \| 0.5486 \| 1.4919 \| 0.67 \| 0.5384 \| 0.3633 \| 0.1737 \| \| No log \| 8.0 \| 56 \| 0.4572 \| 0.69 \| 0.4897 \| 1.4359 \| 0.69 \| 0.6106 \| 0.2889 \| 0.1355 \| \| No log \| 9.0 \| 63 \| 0.3932 \| 0.72 \| 0.4496 \| 1.0748 \| 0.72 \| 0.6261 \| 0.2914 \| 0.1092 \| \| No log \| 10.0 \| 70 \| 0.3584 \| 0.76 \| 0.4091 \| 1.1341 \| 0.76 \| 0.6747 \| 0.2946 \| 0.0937 \| \| No log \| 11.0 \| 77 \| 0.3516 \| 0.785 \| 0.3906 \| 1.0586 \| 0.785 \| 0.7422 \| 0.3026 \| 0.0762 \| \| No log \| 12.0 \| 84 \| 0.3905 \| 0.74 \| 0.4155 \| 1.1502 \| 0.74 \| 0.6677 \| 0.2827 \| 0.1211 \| \| No log \| 13.0 \| 91 \| 0.3346 \| 0.775 \| 0.3640 \| 1.0888 \| 0.775 \| 0.7397 \| 0.2743 \| 0.0771 \| \| No log \| 14.0 \| 98 \| 0.3700 \| 0.81 \| 0.3728 \| 0.9575 \| 0.81 \| 0.7941 \| 0.3125 \| 0.0709 \| \| No log \| 15.0 \| 105 \| 0.3346 \| 0.8 \| 0.3631 \| 0.9636 \| 0.8000 \| 0.7731 \| 0.3113 \| 0.0662 \| \| No log \| 16.0 \| 112 \| 0.3084 \| 0.785 \| 0.3606 \| 1.0243 \| 0.785 \| 0.7610 \| 0.2883 \| 0.0911 \| \| No log \| 17.0 \| 119 \| 0.3266 \| 0.785 \| 0.3375 \| 1.0301 \| 0.785 \| 0.7603 \| 0.2659 \| 0.0687 \| \| No log \| 18.0 \| 126 \| 0.2987 \| 0.805 \| 0.3371 \| 0.7961 \| 0.805 \| 0.7895 \| 0.2764 \| 0.0639 \| \| No log \| 19.0 \| 133 \| 0.3468 \| 0.815 \| 0.3428 \| 0.9841 \| 0.815 \| 0.7884 \| 0.2824 \| 0.0641 \| \| No log \| 20.0 \| 140 \| 0.3111 \| 0.81 \| 0.3409 \| 0.8873 \| 0.81 \| 0.8010 \| 0.2978 \| 0.0579 \| \| No log \| 21.0 \| 147 \| 0.3042 \| 0.8 \| 0.3392 \| 0.8057 \| 0.8000 \| 0.7802 \| 0.2611 \| 0.0556 \| \| No log \| 22.0 \| 154 \| 0.2936 \| 0.84 \| 0.3359 \| 0.8659 \| 0.8400 \| 0.8210 \| 0.2920 \| 0.0636 \| \| No log \| 23.0 \| 161 \| 0.3284 \| 0.815 \| 0.3457 \| 0.9494 \| 0.815 \| 0.8007 \| 0.2793 \| 0.0615 \| \| No log \| 24.0 \| 168 \| 0.3184 \| 0.805 \| 0.3474 \| 0.9087 \| 0.805 \| 0.7851 \| 0.2793 \| 0.0605 \| \| No log \| 25.0 \| 175 \| 0.3081 \| 0.805 \| 0.3357 \| 1.0425 \| 0.805 \| 0.7757 \| 0.2781 \| 0.0646 \| \| No log \| 26.0 \| 182 \| 0.2743 \| 0.815 \| 0.3425 \| 0.7898 \| 0.815 \| 0.8028 \| 0.2814 \| 0.0689 \| \| No log \| 27.0 \| 189 \| 0.2873 \| 0.81 \| 0.3254 \| 0.8795 \| 0.81 \| 0.7904 \| 0.2755 \| 0.0637 \| \| No log \| 28.0 \| 196 \| 0.2650 \| 0.82 \| 0.3236 \| 0.7462 \| 0.82 \| 0.7986 \| 0.2714 \| 0.0616 \| \| No log \| 29.0 \| 203 \| 0.2756 \| 0.815 \| 0.3310 \| 0.8227 \| 0.815 \| 0.7973 \| 0.2766 \| 0.0664 \| \| No log \| 30.0 \| 210 \| 0.2711 \| 0.83 \| 0.3337 \| 0.8340 \| 0.83 \| 0.8186 \| 0.2992 \| 0.0688 \| \| No log \| 31.0 \| 217 \| 0.2779 \| 0.825 \| 0.3234 \| 0.8173 \| 0.825 \| 0.8100 \| 0.2579 \| 0.0589 \| \| No log \| 32.0 \| 224 \| 0.2679 \| 0.82 \| 0.3216 \| 0.7441 \| 0.82 \| 0.8024 \| 0.2940 \| 0.0605 \| \| No log \| 33.0 \| 231 \| 0.2633 \| 0.805 \| 0.3277 \| 0.8046 \| 0.805 \| 0.7871 \| 0.2710 \| 0.0644 \| \| No log \| 34.0 \| 238 \| 0.2705 \| 0.805 \| 0.3333 \| 0.8661 \| 0.805 \| 0.7890 \| 0.2626 \| 0.0632 \| \| No log \| 35.0 \| 245 \| 0.2624 \| 0.815 \| 0.3295 \| 0.8568 \| 0.815 \| 0.7900 \| 0.2865 \| 0.0651 \| \| No log \| 36.0 \| 252 \| 0.2654 \| 0.805 \| 0.3262 \| 0.8075 \| 0.805 \| 0.7793 \| 0.2726 \| 0.0662 \| \| No log \| 37.0 \| 259 \| 0.2697 \| 0.805 \| 0.3293 \| 0.8143 \| 0.805 \| 0.7857 \| 0.2587 \| 0.0623 \| \| No log \| 38.0 \| 266 \| 0.2548 \| 0.805 \| 0.3267 \| 0.8028 \| 0.805 \| 0.7847 \| 0.2606 \| 0.0660 \| \| No log \| 39.0 \| 273 \| 0.2740 \| 0.83 \| 0.3218 \| 0.8270 \| 0.83 \| 0.8172 \| 0.2697 \| 0.0566 \| \| No log \| 40.0 \| 280 \| 0.2572 \| 0.81 \| 0.3302 \| 0.8573 \| 0.81 \| 0.7892 \| 0.2722 \| 0.0663 \| \| No log \| 41.0 \| 287 \| 0.2528 \| 0.81 \| 0.3300 \| 0.8454 \| 0.81 \| 0.7980 \| 0.2555 \| 0.0673 \| \| No log \| 42.0 \| 294 \| 0.2590 \| 0.815 \| 0.3271 \| 0.8393 \| 0.815 \| 0.8002 \| 0.2554 \| 0.0604 \| \| No log \| 43.0 \| 301 \| 0.2654 \| 0.825 \| 0.3273 \| 0.8100 \| 0.825 \| 0.8155 \| 0.2687 \| 0.0595 \| \| No log \| 44.0 \| 308 \| 0.2506 \| 0.805 \| 0.3290 \| 0.8551 \| 0.805 \| 0.7858 \| 0.2425 \| 0.0716 \| \| No log \| 45.0 \| 315 \| 0.2615 \| 0.82 \| 0.3255 \| 0.8624 \| 0.82 \| 0.8007 \| 0.2773 \| 0.0586 \| \| No log \| 46.0 \| 322 \| 0.2487 \| 0.815 \| 0.3240 \| 0.8416 \| 0.815 \| 0.7987 \| 0.2757 \| 0.0611 \| \| No log \| 47.0 \| 329 \| 0.2674 \| 0.845 \| 0.3207 \| 0.8407 \| 0.845 \| 0.8227 \| 0.2963 \| 0.0553 \| \| No log \| 48.0 \| 336 \| 0.2522 \| 0.805 \| 0.3312 \| 0.9376 \| 0.805 \| 0.7888 \| 0.2714 \| 0.0662 \| \| No log \| 49.0 \| 343 \| 0.2547 \| 0.81 \| 0.3280 \| 0.7847 \| 0.81 \| 0.7870 \| 0.2696 \| 0.0688 \| \| No log \| 50.0 \| 350 \| 0.2523 \| 0.81 \| 0.3213 \| 0.7968 \| 0.81 \| 0.7937 \| 0.2599 \| 0.0654 \| \| No log \| 51.0 \| 357 \| 0.2526 \| 0.815 \| 0.3291 \| 0.8022 \| 0.815 \| 0.7994 \| 0.2888 \| 0.0669 \| \| No log \| 52.0 \| 364 \| 0.2568 \| 0.835 \| 0.3180 \| 0.8317 \| 0.835 \| 0.8140 \| 0.2750 \| 0.0578 \| \| No log \| 53.0 \| 371 \| 0.2496 \| 0.82 \| 0.3267 \| 0.8442 \| 0.82 \| 0.8068 \| 0.2825 \| 0.0602 \| \| No log \| 54.0 \| 378 \| 0.2602 \| 0.82 \| 0.3229 \| 0.7963 \| 0.82 \| 0.8061 \| 0.2714 \| 0.0585 \| \| No log \| 55.0 \| 385 \| 0.2477 \| 0.81 \| 0.3237 \| 0.8278 \| 0.81 \| 0.7937 \| 0.2511 \| 0.0631 \| \| No log \| 56.0 \| 392 \| 0.2508 \| 0.83 \| 0.3210 \| 0.8302 \| 0.83 \| 0.8102 \| 0.2706 \| 0.0588 \| \| No log \| 57.0 \| 399 \| 0.2454 \| 0.815 \| 0.3240 \| 0.8377 \| 0.815 \| 0.7948 \| 0.2607 \| 0.0643 \| \| No log \| 58.0 \| 406 \| 0.2488 \| 0.815 \| 0.3229 \| 0.8308 \| 0.815 \| 0.7942 \| 0.2569 \| 0.0604 \| \| No log \| 59.0 \| 413 \| 0.2510 \| 0.82 \| 0.3223 \| 0.8314 \| 0.82 \| 0.8093 \| 0.2779 \| 0.0603 \| \| No log \| 60.0 \| 420 \| 0.2499 \| 0.82 \| 0.3235 \| 0.8401 \| 0.82 \| 0.8031 \| 0.2578 \| 0.0618 \| \| No log \| 61.0 \| 427 \| 0.2478 \| 0.81 \| 0.3227 \| 0.8315 \| 0.81 \| 0.7933 \| 0.2645 \| 0.0615 \| \| No log \| 62.0 \| 434 \| 0.2460 \| 0.82 \| 0.3231 \| 0.8364 \| 0.82 \| 0.8028 \| 0.2795 \| 0.0643 \| \| No log \| 63.0 \| 441 \| 0.2489 \| 0.825 \| 0.3224 \| 0.8337 \| 0.825 \| 0.8156 \| 0.2759 \| 0.0604 \| \| No log \| 64.0 \| 448 \| 0.2482 \| 0.825 \| 0.3230 \| 0.8320 \| 0.825 \| 0.8138 \| 0.2753 \| 0.0600 \| \| No log \| 65.0 \| 455 \| 0.2462 \| 0.815 \| 0.3231 \| 0.8354 \| 0.815 \| 0.8008 \| 0.2551 \| 0.0625 \| \| No log \| 66.0 \| 462 \| 0.2470 \| 0.815 \| 0.3219 \| 0.8338 \| 0.815 \| 0.8018 \| 0.2729 \| 0.0611 \| \| No log \| 67.0 \| 469 \| 0.2457 \| 0.81 \| 0.3231 \| 0.8336 \| 0.81 \| 0.7930 \| 0.2587 \| 0.0638 \| \| No log \| 68.0 \| 476 \| 0.2472 \| 0.815 \| 0.3225 \| 0.8334 \| 0.815 \| 0.8008 \| 0.2706 \| 0.0619 \| \| No log \| 69.0 \| 483 \| 0.2473 \| 0.825 \| 0.3223 \| 0.8357 \| 0.825 \| 0.8165 \| 0.2668 \| 0.0611 \| \| No log \| 70.0 \| 490 \| 0.2481 \| 0.81 \| 0.3223 \| 0.8343 \| 0.81 \| 0.7930 \| 0.2685 \| 0.0624 \| \| No log \| 71.0 \| 497 \| 0.2472 \| 0.825 \| 0.3227 \| 0.8338 \| 0.825 \| 0.8117 \| 0.2839 \| 0.0601 \| \| 0.232 \| 72.0 \| 504 \| 0.2472 \| 0.815 \| 0.3220 \| 0.8345 \| 0.815 \| 0.8018 \| 0.2617 \| 0.0615 \| \| 0.232 \| 73.0 \| 511 \| 0.2486 \| 0.82 \| 0.3218 \| 0.8321 \| 0.82 \| 0.8086 \| 0.2768 \| 0.0610 \| \| 0.232 \| 74.0 \| 518 \| 0.2468 \| 0.815 \| 0.3219 \| 0.8338 \| 0.815 \| 0.8008 \| 0.2717 \| 0.0621 \| \| 0.232 \| 75.0 \| 525 \| 0.2470 \| 0.82 \| 0.3223 \| 0.8325 \| 0.82 \| 0.8090 \| 0.2625 \| 0.0606 \| \| 0.232 \| 76.0 \| 532 \| 0.2474 \| 0.825 \| 0.3223 \| 0.8322 \| 0.825 \| 0.8165 \| 0.2723 \| 0.0602 \| \| 0.232 \| 77.0 \| 539 \| 0.2476 \| 0.805 \| 0.3227 \| 0.8345 \| 0.805 \| 0.7859 \| 0.2589 \| 0.0629 \| \| 0.232 \| 78.0 \| 546 \| 0.2479 \| 0.82 \| 0.3228 \| 0.8336 \| 0.82 \| 0.8090 \| 0.2674 \| 0.0608 \| \| 0.232 \| 79.0 \| 553 \| 0.2478 \| 0.82 \| 0.3225 \| 0.8349 \| 0.82 \| 0.8090 \| 0.2624 \| 0.0604 \| \| 0.232 \| 80.0 \| 560 \| 0.2477 \| 0.81 \| 0.3227 \| 0.8337 \| 0.81 \| 0.7938 \| 0.2577 \| 0.0621 \| \| 0.232 \| 81.0 \| 567 \| 0.2478 \| 0.82 \| 0.3226 \| 0.8336 \| 0.82 \| 0.8090 \| 0.2670 \| 0.0607 \| \| 0.232 \| 82.0 \| 574 \| 0.2480 \| 0.825 \| 0.3224 \| 0.8340 \| 0.825 \| 0.8165 \| 0.2673 \| 0.0605 \| \| 0.232 \| 83.0 \| 581 \| 0.2479 \| 0.82 \| 0.3227 \| 0.8347 \| 0.82 \| 0.8090 \| 0.2564 \| 0.0607 \| \| 0.232 \| 84.0 \| 588 \| 0.2480 \| 0.82 \| 0.3226 \| 0.8342 \| 0.82 \| 0.8090 \| 0.2625 \| 0.0606 \| \| 0.232 \| 85.0 \| 595 \| 0.2480 \| 0.82 \| 0.3225 \| 0.8339 \| 0.82 \| 0.8090 \| 0.2625 \| 0.0606 \| \| 0.232 \| 86.0 \| 602 \| 0.2479 \| 0.825 \| 0.3226 \| 0.8339 \| 0.825 \| 0.8165 \| 0.2677 \| 0.0606 \| \| 0.232 \| 87.0 \| 609 \| 0.2479 \| 0.82 \| 0.3225 \| 0.8339 \| 0.82 \| 0.8090 \| 0.2624 \| 0.0605 \| \| 0.232 \| 88.0 \| 616 \| 0.2481 \| 0.825 \| 0.3225 \| 0.8343 \| 0.825 \| 0.8165 \| 0.2675 \| 0.0604 \| \| 0.232 \| 89.0 \| 623 \| 0.2481 \| 0.825 \| 0.3225 \| 0.8341 \| 0.825 \| 0.8165 \| 0.2722 \| 0.0605 \| \| 0.232 \| 90.0 \| 630 \| 0.2481 \| 0.82 \| 0.3225 \| 0.8341 \| 0.82 \| 0.8090 \| 0.2625 \| 0.0606 \| \| 0.232 \| 91.0 \| 637 \| 0.2481 \| 0.82 \| 0.3226 \| 0.8345 \| 0.82 \| 0.8090 \| 0.2629 \| 0.0608 \| \| 0.232 \| 92.0 \| 644 \| 0.2481 \| 0.825 \| 0.3226 \| 0.8342 \| 0.825 \| 0.8165 \| 0.2675 \| 0.0605 \| \| 0.232 \| 93.0 \| 651 \| 0.2481 \| 0.825 \| 0.3225 \| 0.8340 \| 0.825 \| 0.8165 \| 0.2675 \| 0.0605 \| \| 0.232 \| 94.0 \| 658 \| 0.2481 \| 0.82 \| 0.3225 \| 0.8343 \| 0.82 \| 0.8090 \| 0.2625 \| 0.0606 \| \| 0.232 \| 95.0 \| 665 \| 0.2482 \| 0.82 \| 0.3226 \| 0.8345 \| 0.82 \| 0.8090 \| 0.2627 \| 0.0606 \| \| 0.232 \| 96.0 \| 672 \| 0.2482 \| 0.82 \| 0.3225 \| 0.8343 \| 0.82 \| 0.8090 \| 0.2627 \| 0.0607 \| \| 0.232 \| 97.0 \| 679 \| 0.2482 \| 0.82 \| 0.3226 \| 0.8344 \| 0.82 \| 0.8090 \| 0.2627 \| 0.0607 \| \| 0.232 \| 98.0 \| 686 \| 0.2482 \| 0.82 \| 0.3226 \| 0.8344 \| 0.82 \| 0.8090 \| 0.2626 \| 0.0606 \| \| 0.232 \| 99.0 \| 693 \| 0.2482 \| 0.82 \| 0.3226 \| 0.8343 \| 0.82 \| 0.8090 \| 0.2625 \| 0.0606 \| \| 0.232 \| 100.0 \| 700 \| 0.2482 \| 0.82 \| 0.3226 \| 0.8343 \| 0.82 \| 0.8090 \| 0.2625 \| 0.0606 \| ### Framework versions - Transformers 4.26.1 - Pytorch 1.13.1.post200 - Datasets 2.9.0 - Tokenizers 0.13.2
sianadouglas/ensembletest	sianadouglas	2023-07-10T15:48:14Z	0	0	null	[ "en", "license:other", "region:us" ]	null	2023-07-10T15:47:23Z	--- license: other language: - en ---
Khushnur/t5-base-end2end-questions-generation_squad	Khushnur	2023-07-10T15:47:50Z	164	0	transformers	[ "transformers", "pytorch", "t5", "text2text-generation", "generated_from_trainer", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text2text-generation	2023-07-10T15:02:34Z	--- license: apache-2.0 tags: - generated_from_trainer model-index: - name: t5-base-end2end-questions-generation_squad results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # t5-base-end2end-questions-generation_squad This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on the None dataset. It achieves the following results on the evaluation set: - Loss: 1.6560 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 4 - eval_batch_size: 4 - seed: 42 - gradient_accumulation_steps: 32 - total_train_batch_size: 128 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-----:\|:----:\|:---------------:\| \| 2.5658 \| 0.67 \| 100 \| 1.8866 \| \| 1.958 \| 1.35 \| 200 \| 1.7150 \| \| 1.8516 \| 2.02 \| 300 \| 1.6701 \| \| 1.7965 \| 2.69 \| 400 \| 1.6560 \| ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3
mgmeskill/Pixelcopter-PLE-v0	mgmeskill	2023-07-10T15:38:32Z	0	0	null	[ "Pixelcopter-PLE-v0", "reinforce", "reinforcement-learning", "custom-implementation", "deep-rl-class", "model-index", "region:us" ]	reinforcement-learning	2023-07-10T15:26:11Z	--- tags: - Pixelcopter-PLE-v0 - reinforce - reinforcement-learning - custom-implementation - deep-rl-class model-index: - name: Pixelcopter-PLE-v0 results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: Pixelcopter-PLE-v0 type: Pixelcopter-PLE-v0 metrics: - type: mean_reward value: 42.50 +/- 37.13 name: mean_reward verified: false --- # Reinforce Agent playing Pixelcopter-PLE-v0 This is a trained model of a Reinforce agent playing Pixelcopter-PLE-v0 . To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
tyavika/LR1E4-BS16-Bert_CNN512LSTM256NoBid	tyavika	2023-07-10T15:31:42Z	77	0	transformers	[ "transformers", "pytorch", "bert", "question-answering", "generated_from_trainer", "license:apache-2.0", "endpoints_compatible", "region:us" ]	question-answering	2023-07-09T20:06:29Z	--- license: apache-2.0 tags: - generated_from_trainer model-index: - name: LR1E4-BS16-Bert_CNN512LSTM256NoBid results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # LR1E4-BS16-Bert_CNN512LSTM256NoBid This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset. It achieves the following results on the evaluation set: - Loss: 1.6667 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 10 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-----:\|:-----:\|:---------------:\| \| 1.7267 \| 1.0 \| 3290 \| 1.5092 \| \| 1.2394 \| 2.0 \| 6580 \| 1.3933 \| \| 0.8348 \| 3.0 \| 9870 \| 1.5591 \| \| 0.542 \| 4.0 \| 13160 \| 1.6667 \| ### Framework versions - Transformers 4.28.0 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3
MnLgt/textual_inversion_muir_1_5	MnLgt	2023-07-10T15:31:36Z	1	0	diffusers	[ "diffusers", "tensorboard", "stable-diffusion", "stable-diffusion-diffusers", "text-to-image", "textual_inversion", "base_model:runwayml/stable-diffusion-v1-5", "base_model:adapter:runwayml/stable-diffusion-v1-5", "license:creativeml-openrail-m", "autotrain_compatible", "endpoints_compatible", "diffusers:StableDiffusionPipeline", "region:us" ]	text-to-image	2023-07-10T14:16:45Z	--- license: creativeml-openrail-m base_model: runwayml/stable-diffusion-v1-5 tags: - stable-diffusion - stable-diffusion-diffusers - text-to-image - diffusers - textual_inversion inference: true --- # Textual inversion text2image fine-tuning - jordandavis/textual_inversion_muir_1_5 These are textual inversion adaption weights for runwayml/stable-diffusion-v1-5. You can find some example images in the following.
agercas/speecht5_finetuned_voxpopuli_nl	agercas	2023-07-10T15:27:22Z	78	0	transformers	[ "transformers", "pytorch", "tensorboard", "speecht5", "text-to-audio", "generated_from_trainer", "dataset:facebook/voxpopuli", "license:mit", "endpoints_compatible", "region:us" ]	text-to-audio	2023-07-10T09:21:57Z	--- license: mit tags: - generated_from_trainer datasets: - facebook/voxpopuli model-index: - name: speecht5_finetuned_voxpopuli_nl results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # speecht5_finetuned_voxpopuli_nl This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the facebook/voxpopuli dataset. It achieves the following results on the evaluation set: - Loss: 0.4572 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 1e-05 - train_batch_size: 4 - eval_batch_size: 2 - seed: 42 - gradient_accumulation_steps: 8 - total_train_batch_size: 32 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 500 - training_steps: 4000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-----:\|:----:\|:---------------:\| \| 0.5221 \| 4.3 \| 1000 \| 0.4774 \| \| 0.505 \| 8.61 \| 2000 \| 0.4648 \| \| 0.4929 \| 12.91 \| 3000 \| 0.4583 \| \| 0.4901 \| 17.21 \| 4000 \| 0.4572 \| ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3
grace-pro/afriberta-finetuned-hausa	grace-pro	2023-07-10T15:26:48Z	126	0	transformers	[ "transformers", "pytorch", "tensorboard", "xlm-roberta", "token-classification", "generated_from_trainer", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]	token-classification	2023-07-10T14:49:51Z	--- license: mit tags: - generated_from_trainer metrics: - precision - recall - f1 - accuracy model-index: - name: afriberta-finetuned-hausa results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # afriberta-finetuned-hausa This model is a fine-tuned version of [castorini/afriberta_large](https://huggingface.co/castorini/afriberta_large) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.1242 - Precision: 0.7104 - Recall: 0.5095 - F1: 0.5934 - Accuracy: 0.9647 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Precision \| Recall \| F1 \| Accuracy \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:---------:\|:------:\|:------:\|:--------:\| \| 0.1369 \| 1.0 \| 2624 \| 0.1256 \| 0.6856 \| 0.4541 \| 0.5463 \| 0.9614 \| \| 0.1103 \| 2.0 \| 5248 \| 0.1195 \| 0.7014 \| 0.4947 \| 0.5802 \| 0.9637 \| \| 0.0868 \| 3.0 \| 7872 \| 0.1242 \| 0.7104 \| 0.5095 \| 0.5934 \| 0.9647 \| ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3
dariowsz/wav2vec2-base-finetuned-gtzan	dariowsz	2023-07-10T15:03:27Z	5	0	transformers	[ "transformers", "pytorch", "tensorboard", "wav2vec2", "audio-classification", "generated_from_trainer", "dataset:marsyas/gtzan", "license:apache-2.0", "endpoints_compatible", "region:us" ]	audio-classification	2023-07-04T13:47:36Z	--- license: apache-2.0 tags: - generated_from_trainer datasets: - marsyas/gtzan metrics: - accuracy model-index: - name: wav2vec2-base-finetuned-gtzan results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # wav2vec2-base-finetuned-gtzan This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the GTZAN dataset. It achieves the following results on the evaluation set: - Loss: 0.5537 - Accuracy: 0.88 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 10 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\| \| 1.7898 \| 1.0 \| 113 \| 1.8052 \| 0.45 \| \| 1.4297 \| 2.0 \| 226 \| 1.2229 \| 0.62 \| \| 1.041 \| 3.0 \| 339 \| 0.9934 \| 0.65 \| \| 1.3882 \| 4.0 \| 452 \| 1.1735 \| 0.62 \| \| 0.7248 \| 5.0 \| 565 \| 0.8461 \| 0.69 \| \| 0.6128 \| 6.0 \| 678 \| 0.7391 \| 0.75 \| \| 0.3225 \| 7.0 \| 791 \| 0.8754 \| 0.74 \| \| 0.6483 \| 8.0 \| 904 \| 0.8341 \| 0.79 \| \| 0.2755 \| 9.0 \| 1017 \| 0.5537 \| 0.88 \| \| 0.4398 \| 10.0 \| 1130 \| 0.6076 \| 0.85 \| ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3
NICFRU/bart-base-paraphrasing-news	NICFRU	2023-07-10T15:02:02Z	106	0	transformers	[ "transformers", "pytorch", "bart", "text2text-generation", "generated_from_trainer", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text2text-generation	2023-07-10T14:46:34Z	--- license: apache-2.0 tags: - generated_from_trainer metrics: - rouge model-index: - name: bart-base-paraphrasing results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # bart-base-paraphrasing This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.6617 - Rouge1: 57.7088 - Rouge2: 51.0096 - Rougel: 54.7514 - Rougelsum: 56.3943 - Gen Len: 20.0 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 4e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 20 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Rouge1 \| Rouge2 \| Rougel \| Rougelsum \| Gen Len \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:-------:\|:-------:\|:-------:\|:---------:\|:-------:\| \| No log \| 0.2 \| 10 \| 0.5263 \| 58.2676 \| 51.5842 \| 55.5057 \| 57.1584 \| 19.94 \| \| No log \| 0.4 \| 20 \| 0.5050 \| 56.1604 \| 48.7383 \| 54.0373 \| 55.372 \| 20.0 \| \| No log \| 0.6 \| 30 \| 0.4674 \| 58.0617 \| 51.4993 \| 56.0368 \| 56.9665 \| 20.0 \| \| No log \| 0.8 \| 40 \| 0.4545 \| 57.5375 \| 51.0203 \| 55.5247 \| 56.5761 \| 19.94 \| \| No log \| 1.0 \| 50 \| 0.4373 \| 57.7263 \| 50.8021 \| 55.0549 \| 56.35 \| 19.98 \| \| No log \| 1.2 \| 60 \| 0.4313 \| 57.87 \| 50.9904 \| 54.9727 \| 56.5379 \| 19.97 \| \| No log \| 1.4 \| 70 \| 0.4855 \| 56.5101 \| 49.3124 \| 54.1572 \| 55.0671 \| 20.0 \| \| No log \| 1.6 \| 80 \| 0.4202 \| 56.6535 \| 50.0302 \| 53.6891 \| 55.1016 \| 19.96 \| \| No log \| 1.8 \| 90 \| 0.4544 \| 57.315 \| 50.6289 \| 54.642 \| 55.7326 \| 19.95 \| \| 0.5858 \| 2.0 \| 100 \| 0.4157 \| 56.4569 \| 48.8105 \| 53.937 \| 55.3515 \| 20.0 \| \| 0.5858 \| 2.2 \| 110 \| 0.4555 \| 57.8424 \| 51.5966 \| 55.6655 \| 56.6862 \| 20.0 \| \| 0.5858 \| 2.4 \| 120 \| 0.4196 \| 58.2562 \| 51.7596 \| 55.5085 \| 57.1823 \| 19.97 \| \| 0.5858 \| 2.6 \| 130 \| 0.4334 \| 58.6906 \| 51.6106 \| 55.6631 \| 57.5254 \| 19.89 \| \| 0.5858 \| 2.8 \| 140 \| 0.4710 \| 56.5401 \| 49.33 \| 53.8792 \| 55.0282 \| 20.0 \| \| 0.5858 \| 3.0 \| 150 \| 0.4357 \| 58.2083 \| 52.0049 \| 55.9938 \| 57.1928 \| 20.0 \| \| 0.5858 \| 3.2 \| 160 \| 0.4735 \| 58.8112 \| 52.2196 \| 56.5004 \| 57.7703 \| 19.94 \| \| 0.5858 \| 3.4 \| 170 \| 0.4428 \| 57.6778 \| 50.6377 \| 54.8752 \| 56.4778 \| 20.0 \| \| 0.5858 \| 3.6 \| 180 \| 0.4983 \| 57.4124 \| 50.4244 \| 54.6163 \| 56.0992 \| 20.0 \| \| 0.5858 \| 3.8 \| 190 \| 0.4620 \| 58.0701 \| 51.5021 \| 55.7222 \| 56.8737 \| 20.0 \| \| 0.2865 \| 4.0 \| 200 \| 0.4502 \| 59.1191 \| 52.7516 \| 56.4389 \| 57.7153 \| 20.0 \| \| 0.2865 \| 4.2 \| 210 \| 0.4805 \| 58.9064 \| 52.7148 \| 56.1058 \| 57.6709 \| 20.0 \| \| 0.2865 \| 4.4 \| 220 \| 0.4755 \| 58.6883 \| 52.1464 \| 55.9164 \| 57.3825 \| 20.0 \| \| 0.2865 \| 4.6 \| 230 \| 0.4524 \| 58.9916 \| 52.1101 \| 56.4116 \| 57.9468 \| 19.9 \| \| 0.2865 \| 4.8 \| 240 \| 0.4726 \| 58.9953 \| 52.8173 \| 56.5846 \| 58.0805 \| 20.0 \| \| 0.2865 \| 5.0 \| 250 \| 0.4841 \| 58.1058 \| 51.614 \| 55.3374 \| 56.7617 \| 20.0 \| \| 0.2865 \| 5.2 \| 260 \| 0.5047 \| 58.2785 \| 51.1874 \| 55.5336 \| 56.8795 \| 20.0 \| \| 0.2865 \| 5.4 \| 270 \| 0.4658 \| 57.2753 \| 49.6038 \| 53.9588 \| 55.6038 \| 19.91 \| \| 0.2865 \| 5.6 \| 280 \| 0.5261 \| 58.1691 \| 51.5254 \| 55.2685 \| 56.7787 \| 20.0 \| \| 0.2865 \| 5.8 \| 290 \| 0.4833 \| 57.8088 \| 51.2838 \| 54.8739 \| 56.4374 \| 20.0 \| \| 0.1668 \| 6.0 \| 300 \| 0.5067 \| 58.2021 \| 51.3629 \| 55.3548 \| 56.9093 \| 19.99 \| \| 0.1668 \| 6.2 \| 310 \| 0.5461 \| 58.0327 \| 51.4051 \| 55.3426 \| 56.7923 \| 20.0 \| \| 0.1668 \| 6.4 \| 320 \| 0.5463 \| 58.1027 \| 51.3706 \| 55.1733 \| 56.7923 \| 19.9 \| \| 0.1668 \| 6.6 \| 330 \| 0.5837 \| 57.6284 \| 50.8245 \| 54.6253 \| 56.2127 \| 20.0 \| \| 0.1668 \| 6.8 \| 340 \| 0.5221 \| 58.0869 \| 51.5448 \| 55.4226 \| 56.7532 \| 20.0 \| \| 0.1668 \| 7.0 \| 350 \| 0.5433 \| 58.7676 \| 52.0403 \| 56.2634 \| 57.6441 \| 20.0 \| \| 0.1668 \| 7.2 \| 360 \| 0.5498 \| 57.9172 \| 50.9727 \| 55.1006 \| 56.6018 \| 20.0 \| \| 0.1668 \| 7.4 \| 370 \| 0.5581 \| 57.4669 \| 50.698 \| 54.6448 \| 56.1325 \| 20.0 \| \| 0.1668 \| 7.6 \| 380 \| 0.5526 \| 57.0821 \| 50.298 \| 54.1635 \| 55.8059 \| 20.0 \| \| 0.1668 \| 7.8 \| 390 \| 0.5548 \| 57.5422 \| 50.2734 \| 54.2446 \| 56.1223 \| 20.0 \| \| 0.1071 \| 8.0 \| 400 \| 0.5620 \| 57.4548 \| 50.2657 \| 54.5094 \| 55.9422 \| 20.0 \| \| 0.1071 \| 8.2 \| 410 \| 0.5772 \| 57.4144 \| 50.2443 \| 54.5173 \| 55.9331 \| 20.0 \| \| 0.1071 \| 8.4 \| 420 \| 0.5857 \| 57.2975 \| 50.2116 \| 54.5918 \| 55.9931 \| 20.0 \| \| 0.1071 \| 8.6 \| 430 \| 0.5827 \| 58.4767 \| 51.4318 \| 55.4792 \| 57.1284 \| 20.0 \| \| 0.1071 \| 8.8 \| 440 \| 0.5728 \| 58.4414 \| 51.3523 \| 55.2838 \| 57.202 \| 20.0 \| \| 0.1071 \| 9.0 \| 450 \| 0.5919 \| 58.0499 \| 51.3783 \| 55.0748 \| 56.6939 \| 20.0 \| \| 0.1071 \| 9.2 \| 460 \| 0.5937 \| 57.7604 \| 50.845 \| 54.8941 \| 56.351 \| 20.0 \| \| 0.1071 \| 9.4 \| 470 \| 0.5970 \| 57.3655 \| 50.4126 \| 54.4522 \| 55.7815 \| 20.0 \| \| 0.1071 \| 9.6 \| 480 \| 0.5911 \| 58.203 \| 51.0367 \| 55.3215 \| 56.8485 \| 20.0 \| \| 0.1071 \| 9.8 \| 490 \| 0.6121 \| 58.2898 \| 51.2749 \| 55.4292 \| 57.0241 \| 20.0 \| \| 0.0718 \| 10.0 \| 500 \| 0.5903 \| 58.2487 \| 51.3838 \| 55.4237 \| 56.8863 \| 20.0 \| \| 0.0718 \| 10.2 \| 510 \| 0.5983 \| 58.2681 \| 51.0925 \| 55.2887 \| 56.9562 \| 20.0 \| \| 0.0718 \| 10.4 \| 520 \| 0.6308 \| 57.9797 \| 50.7386 \| 54.995 \| 56.5939 \| 20.0 \| \| 0.0718 \| 10.6 \| 530 \| 0.6307 \| 57.6269 \| 50.5515 \| 54.446 \| 56.1544 \| 20.0 \| \| 0.0718 \| 10.8 \| 540 \| 0.6173 \| 57.9545 \| 51.1005 \| 54.9406 \| 56.5732 \| 20.0 \| \| 0.0718 \| 11.0 \| 550 \| 0.6322 \| 58.3718 \| 51.4321 \| 55.4241 \| 57.1879 \| 20.0 \| \| 0.0718 \| 11.2 \| 560 \| 0.6027 \| 58.6581 \| 51.8607 \| 55.6436 \| 57.32 \| 20.0 \| \| 0.0718 \| 11.4 \| 570 \| 0.6140 \| 58.6476 \| 51.7822 \| 55.5845 \| 57.3018 \| 20.0 \| \| 0.0718 \| 11.6 \| 580 \| 0.6184 \| 59.2454 \| 52.4204 \| 56.2174 \| 57.9278 \| 20.0 \| \| 0.0718 \| 11.8 \| 590 \| 0.6281 \| 59.2945 \| 52.8165 \| 56.547 \| 58.0674 \| 20.0 \| \| 0.0512 \| 12.0 \| 600 \| 0.6128 \| 58.2165 \| 51.3689 \| 55.37 \| 56.8342 \| 20.0 \| \| 0.0512 \| 12.2 \| 610 \| 0.6482 \| 57.9196 \| 50.9793 \| 55.0883 \| 56.6986 \| 20.0 \| \| 0.0512 \| 12.4 \| 620 \| 0.6267 \| 57.4782 \| 50.1118 \| 54.2802 \| 55.8872 \| 20.0 \| \| 0.0512 \| 12.6 \| 630 \| 0.6198 \| 57.457 \| 50.4079 \| 54.2449 \| 55.8118 \| 20.0 \| \| 0.0512 \| 12.8 \| 640 \| 0.6500 \| 57.6903 \| 51.0627 \| 55.0743 \| 56.3025 \| 20.0 \| \| 0.0512 \| 13.0 \| 650 \| 0.6265 \| 57.4394 \| 50.9013 \| 54.7936 \| 56.1688 \| 20.0 \| \| 0.0512 \| 13.2 \| 660 \| 0.6817 \| 58.4345 \| 51.7087 \| 55.291 \| 57.0057 \| 20.0 \| \| 0.0512 \| 13.4 \| 670 \| 0.6322 \| 57.869 \| 50.9503 \| 54.8937 \| 56.5178 \| 20.0 \| \| 0.0512 \| 13.6 \| 680 \| 0.6424 \| 57.8285 \| 51.1014 \| 55.0072 \| 56.5022 \| 20.0 \| \| 0.0512 \| 13.8 \| 690 \| 0.6668 \| 58.7067 \| 51.9929 \| 55.5044 \| 57.1517 \| 20.0 \| \| 0.0397 \| 14.0 \| 700 \| 0.6537 \| 58.8717 \| 52.4036 \| 55.6521 \| 57.4855 \| 20.0 \| \| 0.0397 \| 14.2 \| 710 \| 0.6463 \| 58.9623 \| 52.4749 \| 55.8145 \| 57.8095 \| 20.0 \| \| 0.0397 \| 14.4 \| 720 \| 0.6630 \| 58.8097 \| 52.1997 \| 55.8204 \| 57.6325 \| 20.0 \| \| 0.0397 \| 14.6 \| 730 \| 0.6839 \| 59.0479 \| 52.6573 \| 56.0439 \| 57.7322 \| 20.0 \| \| 0.0397 \| 14.8 \| 740 \| 0.6541 \| 59.2854 \| 52.6109 \| 56.1891 \| 57.9446 \| 20.0 \| \| 0.0397 \| 15.0 \| 750 \| 0.6486 \| 58.8419 \| 52.2004 \| 55.8071 \| 57.49 \| 20.0 \| \| 0.0397 \| 15.2 \| 760 \| 0.6578 \| 57.6161 \| 50.7276 \| 54.5514 \| 56.2359 \| 20.0 \| \| 0.0397 \| 15.4 \| 770 \| 0.6673 \| 57.5458 \| 50.8286 \| 54.4597 \| 56.1513 \| 20.0 \| \| 0.0397 \| 15.6 \| 780 \| 0.6624 \| 57.6634 \| 51.0017 \| 54.6769 \| 56.3837 \| 20.0 \| \| 0.0397 \| 15.8 \| 790 \| 0.6469 \| 57.9037 \| 51.137 \| 54.8939 \| 56.6427 \| 20.0 \| \| 0.0301 \| 16.0 \| 800 \| 0.6373 \| 57.8696 \| 51.0899 \| 54.8543 \| 56.4596 \| 20.0 \| \| 0.0301 \| 16.2 \| 810 \| 0.6712 \| 58.614 \| 52.0052 \| 55.6436 \| 57.3211 \| 20.0 \| \| 0.0301 \| 16.4 \| 820 \| 0.6812 \| 58.5214 \| 51.8911 \| 55.7447 \| 57.2663 \| 20.0 \| \| 0.0301 \| 16.6 \| 830 \| 0.6716 \| 58.5818 \| 51.929 \| 55.7993 \| 57.4064 \| 20.0 \| \| 0.0301 \| 16.8 \| 840 \| 0.6590 \| 57.745 \| 51.0481 \| 54.8545 \| 56.4781 \| 20.0 \| \| 0.0301 \| 17.0 \| 850 \| 0.6695 \| 57.6663 \| 50.9646 \| 54.7863 \| 56.3687 \| 20.0 \| \| 0.0301 \| 17.2 \| 860 \| 0.6858 \| 57.5552 \| 51.0436 \| 54.7092 \| 56.3079 \| 20.0 \| \| 0.0301 \| 17.4 \| 870 \| 0.6840 \| 57.9091 \| 51.3823 \| 54.8309 \| 56.6186 \| 20.0 \| \| 0.0301 \| 17.6 \| 880 \| 0.6751 \| 57.8223 \| 51.1688 \| 54.7562 \| 56.5558 \| 20.0 \| \| 0.0301 \| 17.8 \| 890 \| 0.6589 \| 57.9956 \| 51.1425 \| 54.9509 \| 56.6868 \| 20.0 \| \| 0.0482 \| 18.0 \| 900 \| 0.6634 \| 58.0392 \| 51.3121 \| 55.0726 \| 56.7878 \| 20.0 \| \| 0.0482 \| 18.2 \| 910 \| 0.6907 \| 58.2021 \| 51.4548 \| 55.1874 \| 56.91 \| 20.0 \| \| 0.0482 \| 18.4 \| 920 \| 0.6977 \| 58.1124 \| 51.4254 \| 55.062 \| 56.8412 \| 20.0 \| \| 0.0482 \| 18.6 \| 930 \| 0.6832 \| 58.0776 \| 51.3168 \| 55.0849 \| 56.8226 \| 20.0 \| \| 0.0482 \| 18.8 \| 940 \| 0.6672 \| 57.925 \| 51.2475 \| 54.9661 \| 56.655 \| 20.0 \| \| 0.0482 \| 19.0 \| 950 \| 0.6582 \| 57.9285 \| 51.2483 \| 54.9744 \| 56.6609 \| 20.0 \| \| 0.0482 \| 19.2 \| 960 \| 0.6575 \| 57.9285 \| 51.2483 \| 54.9744 \| 56.6609 \| 20.0 \| \| 0.0482 \| 19.4 \| 970 \| 0.6619 \| 57.8961 \| 51.2097 \| 54.9475 \| 56.6344 \| 20.0 \| \| 0.0482 \| 19.6 \| 980 \| 0.6658 \| 57.8961 \| 51.2097 \| 54.9475 \| 56.6344 \| 20.0 \| \| 0.0482 \| 19.8 \| 990 \| 0.6635 \| 57.7222 \| 51.0096 \| 54.8166 \| 56.4623 \| 20.0 \| \| 0.0201 \| 20.0 \| 1000 \| 0.6617 \| 57.7088 \| 51.0096 \| 54.7514 \| 56.3943 \| 20.0 \| ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3
alienware/layoutlmv3-finetuned-cord_100	alienware	2023-07-10T15:01:59Z	4	0	transformers	[ "transformers", "pytorch", "layoutlmv3", "token-classification", "generated_from_trainer", "dataset:cord-layoutlmv3", "license:cc-by-nc-sa-4.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]	token-classification	2023-07-09T12:32:12Z	--- license: cc-by-nc-sa-4.0 tags: - generated_from_trainer datasets: - cord-layoutlmv3 metrics: - precision - recall - f1 - accuracy model-index: - name: layoutlmv3-finetuned-cord_100 results: - task: name: Token Classification type: token-classification dataset: name: cord-layoutlmv3 type: cord-layoutlmv3 config: cord split: test args: cord metrics: - name: Precision type: precision value: 0.9569093610698366 - name: Recall type: recall value: 0.9640718562874252 - name: F1 type: f1 value: 0.9604772557792692 - name: Accuracy type: accuracy value: 0.9681663837011885 --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # layoutlmv3-finetuned-cord_100 This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on the cord-layoutlmv3 dataset. It achieves the following results on the evaluation set: - Loss: 0.1720 - Precision: 0.9569 - Recall: 0.9641 - F1: 0.9605 - Accuracy: 0.9682 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 1e-05 - train_batch_size: 5 - eval_batch_size: 5 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 2500 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Precision \| Recall \| F1 \| Accuracy \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:---------:\|:------:\|:------:\|:--------:\| \| No log \| 1.56 \| 250 \| 0.3320 \| 0.9011 \| 0.9207 \| 0.9108 \| 0.9253 \| \| 0.3502 \| 3.12 \| 500 \| 0.2811 \| 0.9281 \| 0.9371 \| 0.9326 \| 0.9427 \| \| 0.3502 \| 4.69 \| 750 \| 0.2429 \| 0.9210 \| 0.9341 \| 0.9275 \| 0.9435 \| \| 0.162 \| 6.25 \| 1000 \| 0.2264 \| 0.9385 \| 0.9476 \| 0.9430 \| 0.9542 \| \| 0.162 \| 7.81 \| 1250 \| 0.1996 \| 0.9373 \| 0.9513 \| 0.9443 \| 0.9601 \| \| 0.0971 \| 9.38 \| 1500 \| 0.1686 \| 0.9569 \| 0.9633 \| 0.9601 \| 0.9690 \| \| 0.0971 \| 10.94 \| 1750 \| 0.1814 \| 0.9532 \| 0.9603 \| 0.9567 \| 0.9652 \| \| 0.0704 \| 12.5 \| 2000 \| 0.1915 \| 0.9539 \| 0.9611 \| 0.9575 \| 0.9656 \| \| 0.0704 \| 14.06 \| 2250 \| 0.1833 \| 0.9590 \| 0.9633 \| 0.9612 \| 0.9677 \| \| 0.0513 \| 15.62 \| 2500 \| 0.1720 \| 0.9569 \| 0.9641 \| 0.9605 \| 0.9682 \| ### Framework versions - Transformers 4.30.2 - Pytorch 1.13.1+cu117 - Datasets 2.13.1 - Tokenizers 0.13.3
SHENMU007/neunit_BASE_V10.19	SHENMU007	2023-07-10T15:01:47Z	77	0	transformers	[ "transformers", "pytorch", "tensorboard", "speecht5", "text-to-audio", "1.1.0", "generated_from_trainer", "zh", "dataset:facebook/voxpopuli", "base_model:microsoft/speecht5_tts", "base_model:finetune:microsoft/speecht5_tts", "license:mit", "endpoints_compatible", "region:us" ]	text-to-audio	2023-07-07T08:50:51Z	--- language: - zh license: mit base_model: microsoft/speecht5_tts tags: - 1.1.0 - generated_from_trainer datasets: - facebook/voxpopuli model-index: - name: SpeechT5 TTS Dutch neunit results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # SpeechT5 TTS Dutch neunit This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the VoxPopuli dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 1e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 32 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 500 - training_steps: 4000 ### Training results ### Framework versions - Transformers 4.31.0.dev0 - Pytorch 2.0.1+cu117 - Datasets 2.12.0 - Tokenizers 0.13.3
rickareo/distilbert-base-uncased-finetuned-emotion	rickareo	2023-07-10T14:59:25Z	105	0	transformers	[ "transformers", "pytorch", "tensorboard", "distilbert", "text-classification", "generated_from_trainer", "dataset:emotion", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2023-07-10T14:44:04Z	--- license: apache-2.0 tags: - generated_from_trainer datasets: - emotion metrics: - accuracy - f1 model-index: - name: distilbert-base-uncased-finetuned-emotion results: - task: name: Text Classification type: text-classification dataset: name: emotion type: emotion args: split metrics: - name: Accuracy type: accuracy value: 0.923 - name: F1 type: f1 value: 0.9229910973969778 --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # distilbert-base-uncased-finetuned-emotion This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the emotion dataset. It achieves the following results on the evaluation set: - Loss: 0.2155 - Accuracy: 0.923 - F1: 0.9230 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 64 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 2 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| F1 \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\|:------:\| \| 0.8271 \| 1.0 \| 250 \| 0.3166 \| 0.903 \| 0.8989 \| \| 0.2469 \| 2.0 \| 500 \| 0.2155 \| 0.923 \| 0.9230 \| ### Framework versions - Transformers 4.16.2 - Pytorch 2.0.1+cu118 - Datasets 1.16.1 - Tokenizers 0.13.3
ericNguyen0132/DepRoBERTa-2ndStage	ericNguyen0132	2023-07-10T14:56:14Z	105	0	transformers	[ "transformers", "pytorch", "tensorboard", "roberta", "text-classification", "generated_from_trainer", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2023-07-10T13:42:58Z	--- tags: - generated_from_trainer metrics: - accuracy - f1 model-index: - name: DepRoBERTa-2ndStage results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # DepRoBERTa-2ndStage This model is a fine-tuned version of [rafalposwiata/deproberta-large-v1](https://huggingface.co/rafalposwiata/deproberta-large-v1) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.6330 - Accuracy: 0.855 - F1: 0.9134 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-06 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 500 - num_epochs: 5 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| F1 \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\|:------:\| \| No log \| 1.0 \| 469 \| 0.3572 \| 0.8617 \| 0.9224 \| \| 0.4953 \| 2.0 \| 938 \| 0.3593 \| 0.8783 \| 0.9315 \| \| 0.3493 \| 3.0 \| 1407 \| 0.4274 \| 0.8483 \| 0.9091 \| \| 0.313 \| 4.0 \| 1876 \| 0.5488 \| 0.8617 \| 0.9187 \| \| 0.2622 \| 5.0 \| 2345 \| 0.6330 \| 0.855 \| 0.9134 \| ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3
pcuenq/falcon-7b-instruct-transformers	pcuenq	2023-07-10T14:54:25Z	7	0	transformers	[ "transformers", "pytorch", "falcon", "text-generation", "en", "dataset:tiiuae/falcon-refinedweb", "arxiv:2205.14135", "arxiv:1911.02150", "arxiv:2005.14165", "arxiv:2104.09864", "arxiv:2306.01116", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2023-07-10T12:57:31Z	--- datasets: - tiiuae/falcon-refinedweb language: - en inference: true license: apache-2.0 duplicated_from: pcuenq/falcon-7b-instruct --- # ✨ Falcon-7B-Instruct Falcon-7B-Instruct is a 7B parameters causal decoder-only model built by [TII](https://www.tii.ae) based on [Falcon-7B](https://huggingface.co/tiiuae/falcon-7b) and finetuned on a mixture of chat/instruct datasets. It is made available under the Apache 2.0 license. Paper coming soon 😊. 🤗 To get started with Falcon (inference, finetuning, quantization, etc.), we recommend reading [this great blogpost fron HF](https://huggingface.co/blog/falcon)! ## Why use Falcon-7B-Instruct? * You are looking for a ready-to-use chat/instruct model based on [Falcon-7B](https://huggingface.co/tiiuae/falcon-7b). * Falcon-7B is a strong base model, outperforming comparable open-source models (e.g., [MPT-7B](https://huggingface.co/mosaicml/mpt-7b), [StableLM](https://github.com/Stability-AI/StableLM), [RedPajama](https://huggingface.co/togethercomputer/RedPajama-INCITE-Base-7B-v0.1) etc.), thanks to being trained on 1,500B tokens of [RefinedWeb](https://huggingface.co/datasets/tiiuae/falcon-refinedweb) enhanced with curated corpora. See the [OpenLLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard). * It features an architecture optimized for inference, with FlashAttention ([Dao et al., 2022](https://arxiv.org/abs/2205.14135)) and multiquery ([Shazeer et al., 2019](https://arxiv.org/abs/1911.02150)). 💬 This is an instruct model, which may not be ideal for further finetuning. If you are interested in building your own instruct/chat model, we recommend starting from [Falcon-7B](https://huggingface.co/tiiuae/falcon-7b). 🔥 Looking for an even more powerful model? [Falcon-40B-Instruct](https://huggingface.co/tiiuae/falcon-40b-instruct) is Falcon-7B-Instruct's big brother! ```python from transformers import AutoTokenizer, AutoModelForCausalLM import transformers import torch model = "tiiuae/falcon-7b-instruct" tokenizer = AutoTokenizer.from_pretrained(model) pipeline = transformers.pipeline( "text-generation", model=model, tokenizer=tokenizer, torch_dtype=torch.bfloat16, trust_remote_code=True, device_map="auto", ) sequences = pipeline( "Girafatron is obsessed with giraffes, the most glorious animal on the face of this Earth. Giraftron believes all other animals are irrelevant when compared to the glorious majesty of the giraffe.\nDaniel: Hello, Girafatron!\nGirafatron:", max_length=200, do_sample=True, top_k=10, num_return_sequences=1, eos_token_id=tokenizer.eos_token_id, ) for seq in sequences: print(f"Result: {seq['generated_text']}") ``` 💥 Falcon LLMs require PyTorch 2.0 for use with `transformers`! For fast inference with Falcon, check-out [Text Generation Inference](https://github.com/huggingface/text-generation-inference)! Read more in this [blogpost]((https://huggingface.co/blog/falcon). You will need at least 16GB of memory to swiftly run inference with Falcon-7B-Instruct. # Model Card for Falcon-7B-Instruct ## Model Details ### Model Description - Developed by: [https://www.tii.ae](https://www.tii.ae); - Model type: Causal decoder-only; - Language(s) (NLP): English and French; - License: Apache 2.0; - Finetuned from model: [Falcon-7B](https://huggingface.co/tiiuae/falcon-7b). ### Model Source - Paper: coming soon. ## Uses ### Direct Use Falcon-7B-Instruct has been finetuned on a mixture of instruct and chat datasets. ### Out-of-Scope Use Production use without adequate assessment of risks and mitigation; any use cases which may be considered irresponsible or harmful. ## Bias, Risks, and Limitations Falcon-7B-Instruct is mostly trained on English data, and will not generalize appropriately to other languages. Furthermore, as it is trained on a large-scale corpora representative of the web, it will carry the stereotypes and biases commonly encountered online. ### Recommendations We recommend users of Falcon-7B-Instruct to develop guardrails and to take appropriate precautions for any production use. ## How to Get Started with the Model ```python from transformers import AutoTokenizer, AutoModelForCausalLM import transformers import torch model = "tiiuae/falcon-7b-instruct" tokenizer = AutoTokenizer.from_pretrained(model) pipeline = transformers.pipeline( "text-generation", model=model, tokenizer=tokenizer, torch_dtype=torch.bfloat16, trust_remote_code=True, device_map="auto", ) sequences = pipeline( "Girafatron is obsessed with giraffes, the most glorious animal on the face of this Earth. Giraftron believes all other animals are irrelevant when compared to the glorious majesty of the giraffe.\nDaniel: Hello, Girafatron!\nGirafatron:", max_length=200, do_sample=True, top_k=10, num_return_sequences=1, eos_token_id=tokenizer.eos_token_id, ) for seq in sequences: print(f"Result: {seq['generated_text']}") ``` ## Training Details ### Training Data Falcon-7B-Instruct was finetuned on a 250M tokens mixture of instruct/chat datasets. \| Data source \| Fraction \| Tokens \| Description \| \|--------------------\|--------------\|------------\|-----------------------------------\| \| [Bai ze](https://github.com/project-baize/baize-chatbot) \| 65% \| 164M \| chat \| \| [GPT4All](https://github.com/nomic-ai/gpt4all) \| 25% \| 62M \| instruct \| \| [GPTeacher](https://github.com/teknium1/GPTeacher) \| 5% \| 11M \| instruct \| \| [RefinedWeb-English](https://huggingface.co/datasets/tiiuae/falcon-refinedweb) \| 5% \| 13M \| massive web crawl \| The data was tokenized with the Falcon-[7B](https://huggingface.co/tiiuae/falcon-7b)/[40B](https://huggingface.co/tiiuae/falcon-40b) tokenizer. ## Evaluation Paper coming soon. See the [OpenLLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) for early results. Note that this model variant is not optimized for NLP benchmarks. ## Technical Specifications For more information about pretraining, see [Falcon-7B](https://huggingface.co/tiiuae/falcon-7b). ### Model Architecture and Objective Falcon-7B is a causal decoder-only model trained on a causal language modeling task (i.e., predict the next token). The architecture is broadly adapted from the GPT-3 paper ([Brown et al., 2020](https://arxiv.org/abs/2005.14165)), with the following differences: * Positionnal embeddings: rotary ([Su et al., 2021](https://arxiv.org/abs/2104.09864)); * Attention: multiquery ([Shazeer et al., 2019](https://arxiv.org/abs/1911.02150)) and FlashAttention ([Dao et al., 2022](https://arxiv.org/abs/2205.14135)); * Decoder-block: parallel attention/MLP with a single layer norm. \| Hyperparameter \| Value \| Comment \| \|--------------------\|-----------\|----------------------------------------\| \| Layers \| 32 \| \| \| `d_model` \| 4544 \| Increased to compensate for multiquery \| \| `head_dim` \| 64 \| Reduced to optimise for FlashAttention \| \| Vocabulary \| 65024 \| \| \| Sequence length \| 2048 \| \| ### Compute Infrastructure #### Hardware Falcon-7B-Instruct was trained on AWS SageMaker, on 32 A100 40GB GPUs in P4d instances. #### Software Falcon-7B-Instruct was trained a custom distributed training codebase, Gigatron. It uses a 3D parallelism approach combined with ZeRO and high-performance Triton kernels (FlashAttention, etc.) ## Citation Paper coming soon 😊. In the meanwhile, you can use the following information to cite: ``` @article{falcon40b, title={{Falcon-40B}: an open large language model with state-of-the-art performance}, author={Almazrouei, Ebtesam and Alobeidli, Hamza and Alshamsi, Abdulaziz and Cappelli, Alessandro and Cojocaru, Ruxandra and Debbah, Merouane and Goffinet, Etienne and Heslow, Daniel and Launay, Julien and Malartic, Quentin and Noune, Badreddine and Pannier, Baptiste and Penedo, Guilherme}, year={2023} } ``` To learn more about the pretraining dataset, see the 📓 [RefinedWeb paper](https://arxiv.org/abs/2306.01116). ``` @article{refinedweb, title={The {R}efined{W}eb dataset for {F}alcon {LLM}: outperforming curated corpora with web data, and web data only}, author={Guilherme Penedo and Quentin Malartic and Daniel Hesslow and Ruxandra Cojocaru and Alessandro Cappelli and Hamza Alobeidli and Baptiste Pannier and Ebtesam Almazrouei and Julien Launay}, journal={arXiv preprint arXiv:2306.01116}, eprint={2306.01116}, eprinttype = {arXiv}, url={https://arxiv.org/abs/2306.01116}, year={2023} } ``` ## License Falcon-7B-Instruct is made available under the Apache 2.0 license. ## Contact [email protected]
firecoral/ppo-LunarLander-v2	firecoral	2023-07-10T14:49:32Z	0	0	stable-baselines3	[ "stable-baselines3", "LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]	reinforcement-learning	2023-07-10T14:49:10Z	--- library_name: stable-baselines3 tags: - LunarLander-v2 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: PPO results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: LunarLander-v2 type: LunarLander-v2 metrics: - type: mean_reward value: 261.63 +/- 20.29 name: mean_reward verified: false --- # PPO Agent playing LunarLander-v2 This is a trained model of a PPO agent playing LunarLander-v2 using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3). ## Usage (with Stable-baselines3) TODO: Add your code ```python from stable_baselines3 import ... from huggingface_sb3 import load_from_hub ... ```
Nyme/textual_inversion_cat	Nyme	2023-07-10T14:49:16Z	5	0	diffusers	[ "diffusers", "tensorboard", "stable-diffusion", "stable-diffusion-diffusers", "text-to-image", "textual_inversion", "base_model:runwayml/stable-diffusion-v1-5", "base_model:adapter:runwayml/stable-diffusion-v1-5", "license:creativeml-openrail-m", "autotrain_compatible", "endpoints_compatible", "diffusers:StableDiffusionPipeline", "region:us" ]	text-to-image	2023-07-10T09:17:48Z	--- license: creativeml-openrail-m base_model: runwayml/stable-diffusion-v1-5 tags: - stable-diffusion - stable-diffusion-diffusers - text-to-image - diffusers - textual_inversion inference: true --- # Textual inversion text2image fine-tuning - Nyme/textual_inversion_cat These are textual inversion adaption weights for runwayml/stable-diffusion-v1-5. You can find some example images in the following.
Birchlabs/llama-13b-stepwise-adapter	Birchlabs	2023-07-10T14:37:32Z	0	1	null	[ "license:apache-2.0", "region:us" ]	null	2023-07-10T13:43:18Z	--- license: apache-2.0 --- Finetunes Llama-13b+Alaca to solve problems via stepwise reasoning (OpenAI [PRM800k dataset](https://github.com/openai/prm800k), or rather our postprocessed version, [`Birchlabs/openai-prm800k-solutions-only`](https://huggingface.co/datasets/Birchlabs/openai-prm800k-solutions-only)). ## Model description This is a fork of [`llama-13b`](https://huggingface.co/huggyllama/llama-13b) + [`chansung/alpaca-lora-13b`](https://huggingface.co/chansung/alpaca-lora-13b). That is: we loaded Llama-13b, we applied Alpaca LoRA, expanded vocabulary, then QLoRA 4-bit finetuned from there. Parts: - base model [`llama-13b`](https://huggingface.co/huggyllama/llama-13b) - LoRA 0 [`chansung/alpaca-lora-13b`](https://huggingface.co/chansung/alpaca-lora-13b) - LoRA 1 [`Birchlabs/llama-13b-stepwise-adapter`](https://huggingface.co/Birchlabs/llama-13b-stepwise-adapter) (this) - tokenizer [`Birchlabs/llama-13b-stepwise-tokenizer`](https://huggingface.co/Birchlabs/llama-13b-stepwise-tokenizer) - finetuned input/output embedding layers: [`Birchlabs/llama-13b-stepwise-embeddings`](https://huggingface.co/Birchlabs/llama-13b-stepwise-embeddings) ## Training Trained using [`qlora.py`](https://github.com/scottlogic-alex/qlora/blob/stepwise/qlora.py) from our [`stepwise`](https://github.com/scottlogic-alex/qlora/tree/stepwise) branch of [qlora](https://github.com/artidoro/qlora). Known-good as of commit [`522d86b`](https://github.com/scottlogic-alex/qlora/blob/522d86b447d9fe85e99ece33141fb37c4e947cda/qlora.py). `python -m qlora --model_name_or_path huggyllama/llama-13b --lora_name_or_path chansung/alpaca-lora-13b --dataset prm800k-solutions --dataset_format prm800k-solutions --bf16 --max_memory_MB 24000 --use_bos_token_in_prompt --truncate_toward_center --source_max_len 184 --target_max_len 998 --gradient_accumulation_steps 4 --per_device_train_batch_size 4 --per_device_eval_batch_size 4 --learning_rate 0.0002 --run_name 13b_alpaca_special_tokens_long --report_to wandb --save_steps 64 --save_total_limit 3 --max_steps 1664 --evaluation_strategy steps --eval_steps 64 --generate_steps 16 --register_process_supervision_tokens` - [(Private) W&B run](https://wandb.ai/scottlogic/llm-stepwise/runs/nvdyo6aw?workspace=user-birchlabs) - [(Public) W&B report](https://api.wandb.ai/links/scottlogic/65wo5d2o) ## Usage You can load using [`evaluate.py`](https://github.com/scottlogic-alex/qlora/blob/stepwise/evaluate.py#L209-L278) from our [`stepwise`](https://github.com/scottlogic-alex/qlora/tree/stepwise) branch of [qlora](https://github.com/artidoro/qlora). Known-good as of commit [`522d86b`](https://github.com/scottlogic-alex/qlora/blob/522d86b447d9fe85e99ece33141fb37c4e947cda/evaluate.py). Download `embed_tokens.pt` and `lm_head.pt` from [`Birchlabs/llama-13b-stepwise-embeddings`](https://huggingface.co/Birchlabs/llama-13b-stepwise-embeddings/tree/main), then run evaluator like so: ```bash python -m evaluate \ --model_name_or_path huggyllama/llama-13b \ --base_lora_model_name_or_path chansung/alpaca-lora-13b \ --tokenizer_model_name_or_path Birchlabs/llama-13b-stepwise-tokenizer \ --lora_model_name_or_path Birchlabs/llama-13b-stepwise-adapter \ --input_embedding_path embed_tokens.pt \ --output_embedding_path lm_head.pt \ --bf16 \ --use_bos_token_in_prompt \ --overrun_countermeasures False ``` ## Prompt style The model is finetuned for instruction-response. `prompt = '<s>Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\nHow do I feed a family of 5 without ingredients?\n\n### Response:\n<\|step_start\|>'` ## Example output: `$ How do I drink a matcha latte?` `To drink a matcha latte, I should first remove the matcha from the bag. <\|step_end\|> <\|step_start\|> I can do that by opening the bag and shaking out the matcha into a glass or bowl. <\|step_end\|> <\|step_start\|> Then, I should add some hot water into the glass or bowl and start stirring the matcha. <\|step_end\|> <\|step_start\|> This is to make the matcha easier to mix with the water. <\|step_end\|> <\|step_start\|> Next, I should add milk into the glass or bowl and continue stirring. <\|step_end\|> <\|step_start\|> This is to make the matcha and the water form a thick mixture. <\|step_end\|> <\|step_start\|> Finally, I should add ice cubes into the glass or bowl and stir again. <\|step_end\|> <\|step_start\|> This is to make the mixture even thicker and chilled. <\|step_end\|> <\|step_start\|> So, a matcha latte is a drink that is a mixture of matcha, water, and milk, with some ice cubes. <\|step_end\|> <\|step_start\|> <\|answer_start\|> To make a matcha latte, I should remove the matcha from the bag, add some hot water into a glass or bowl and stir, add milk into the glass or bowl and stir as well, and finally add ice cubes and stir again. <\|step_end\|> <\|step_start\|> <\|answer_start\|> To drink a matcha latte, I should remove` `$ What is the third Fibonacci number?` `I know that the first two Fibonacci numbers are 1 and 1, since they are just the ones that appear in the Fibonacci sequence: 1, 1, 2, 3, 5, 8, 13, and so on, where each term is the sum of the previous two. <\|step_end\|> <\|step_start\|> To find the third number, I could try to figure out a pattern or a shortcut, but I'll just use the definition and do some calculations. <\|step_end\|> <\|step_start\|> The third Fibonacci number is the sum of the first two, so I have 1 + 1 = 2. <\|step_end\|> <\|step_start\|> <\|answer_start\|> 2 <\|answer_end\|>` `$ How do I make a cup of tea?` `Ok, the first step is to open the cup of tea. <\|step_end\|> <\|step_start\|> Then the second step is to jump in the tea. <\|step_end\|> <\|step_start\|> And finally the third step is to drink the jump. <\|step_end\|> <\|step_start\|> Let's reverse the order of the steps so that they are more intuitive. <\|step_end\|> <\|step_start\|> The first step is to jump in the tea. <\|step_end\|> <\|step_start\|> Then the second step is to open the cup of tea. <\|step_end\|> <\|step_start\|> And finally the third step is to drink the jump. <\|step_end\|> <\|step_start\|> So, I think this is a good way to make a cup of tea. <\|step_end\|> <\|step_start\|> Yes, it is. <\|answer_start\|> How do I make a cup of tea? <\|answer_end\|>` `$ How do I open a jar?` `To open a jar, I need to use a key that fits into the lock on the jar. <\|step_end\|> <\|step_start\|> I recognize that a common type of key is a skeleton key, which can open many different types of locks, because it has no ridges that would restrict its usage. <\|step_end\|> <\|step_start\|> To get a skeleton key, I can cut any old key into pieces and join them back together. <\|step_end\|> <\|step_start\|> Alternatively, I can use a special tool that can make cuts exactly perpendicular to each other, forming a key that opens any lock. <\|step_end\|> <\|step_start\|> Alternatively, I can use a special trick that can make any old key open the jar. <\|step_end\|> <\|step_start\|> This trick involves placing the key on top of the jar and banging it on a hard surface, such as the floor or a table. <\|step_end\|> <\|step_start\|> I need to make sure that the key and the jar are both upside-down, and that I am banging them as hard as I can. <\|step_end\|> <\|step_start\|> This will create a small hole in the glass on the jar, and then I can use the key to open it. <\|step_end\|> <\|step_start\|> I need to be careful not to get cut by the glass, and I need to check if the jar is empty first, otherwise I might poke my finger and`
EmbraceAGI/chatglm2.cpp	EmbraceAGI	2023-07-10T14:34:47Z	0	0	null	[ "license:openrail", "region:us" ]	null	2023-07-10T08:37:02Z	--- license: openrail --- chatglm2-ggml.bin model for chatglm.cpp. ``` https://github.com/li-plus/chatglm.cpp ```
marsh5/Reinforce-cartpole	marsh5	2023-07-10T14:31:44Z	0	0	null	[ "CartPole-v1", "reinforce", "reinforcement-learning", "custom-implementation", "deep-rl-class", "model-index", "region:us" ]	reinforcement-learning	2023-07-10T14:31:34Z	--- tags: - CartPole-v1 - reinforce - reinforcement-learning - custom-implementation - deep-rl-class model-index: - name: Reinforce-cartpole results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: CartPole-v1 type: CartPole-v1 metrics: - type: mean_reward value: 500.00 +/- 0.00 name: mean_reward verified: false --- # Reinforce Agent playing CartPole-v1 This is a trained model of a Reinforce agent playing CartPole-v1 . To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
JennnDexter/textual_inversion	JennnDexter	2023-07-10T14:24:31Z	29	0	diffusers	[ "diffusers", "autotrain_compatible", "endpoints_compatible", "diffusers:StableDiffusionPipeline", "region:us" ]	text-to-image	2023-07-07T11:57:47Z	--- license: creativeml-openrail-m base_model: CompVis/stable-diffusion-v1-4 tags: - stable-diffusion - stable-diffusion-diffusers - text-to-image - diffusers - textual_inversion inference: true --- # Textual inversion text2image fine-tuning - JennnDexter/textual_inversion These are textual inversion adaption weights for CompVis/stable-diffusion-v1-4. You can find some example images in the following.
LmloCin/TEST_MODEL	LmloCin	2023-07-10T14:07:36Z	0	0	null	[ "region:us" ]	null	2023-07-10T13:34:58Z	import socket,warnings try: socket.setdefaulttimeout(1) socket.socket(socket.AF_INET, socket.SOCK_STREAM).connect(('1.1.1.1', 53)) except socket.error as ex: raise Exception("STOP: No internet. Click '>\|' in top right and set 'Internet' switch to on") import os iskaggle = os.environ.get('KAGGLE_KERNEL_RUN_TYPE', '') if iskaggle: !pip install -Uqq fastai # Skip this cell if you already have duckduckgo_search installed !pip install -Uqq duckduckgo_search from duckduckgo_search import ddg_images from fastcore.all import * def search_images(term, max_images=200): return L(ddg_images(term, max_results=max_images)).itemgot('image') urls = search_images('duck images', max_images=1) urls[0] from fastdownload import download_url dest = 'duck.jpg' download_url(urls[0], dest, show_progress=False) from fastai.vision.all import * im = Image.open(dest) im.to_thumb(256,256) download_url(search_images('lakes photos', max_images=1)[0], 'lakes.jpg', show_progress=False) Image.open('lakes.jpg').to_thumb(256,256) searches = 'lakes','duck' path = Path('duck_or_not') from time import sleep for o in searches: dest = (path/o) dest.mkdir(exist_ok=True, parents=True) download_images(dest, urls=search_images(f'{o} photo')) sleep(2) # Pause between searches to avoid over-loading server download_images(dest, urls=search_images(f'{o} sun photo')) sleep(2) download_images(dest, urls=search_images(f'{o} shade photo')) sleep(2) resize_images(path/o, max_size=400, dest=path/o) failed = verify_images(get_image_files(path)) failed.map(Path.unlink) len(failed) dls = DataBlock( blocks=(ImageBlock, CategoryBlock), get_items=get_image_files, splitter=RandomSplitter(valid_pct=0.2, seed=42), get_y=parent_label, item_tfms=[Resize(192, method='squish')] ).dataloaders(path) dls.show_batch(max_n=6) learn = vision_learner(dls, resnet18, metrics=error_rate) learn.fine_tune(3) is_duck,_,probs = learn.predict(PILImage.create('duck.jpg')) print(f"This is a: {is_duck}.") print(f"Probability it's a duck: {probs[0]:.4f}")
kfkas/LawBot-v1_koalpaca_legalQA_easylaw_cro	kfkas	2023-07-10T14:06:22Z	1	0	peft	[ "peft", "region:us" ]	null	2023-07-10T14:06:16Z	--- library_name: peft --- ## Training procedure The following `bitsandbytes` quantization config was used during training: - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: True - bnb_4bit_compute_dtype: bfloat16 ### Framework versions - PEFT 0.4.0.dev0
dilip-reddy/ppo-LunarLander	dilip-reddy	2023-07-10T13:57:53Z	4	0	stable-baselines3	[ "stable-baselines3", "LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]	reinforcement-learning	2023-07-10T13:57:33Z	--- library_name: stable-baselines3 tags: - LunarLander-v2 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: PPO results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: LunarLander-v2 type: LunarLander-v2 metrics: - type: mean_reward value: 268.69 +/- 17.74 name: mean_reward verified: false --- # PPO Agent playing LunarLander-v2 This is a trained model of a PPO agent playing LunarLander-v2 using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3). ## Usage (with Stable-baselines3) TODO: Add your code ```python from stable_baselines3 import ... from huggingface_sb3 import load_from_hub ... ```
cointegrated/rubert-base-lesha17-punctuation	cointegrated	2023-07-10T13:56:54Z	125	1	transformers	[ "transformers", "pytorch", "safetensors", "bert", "token-classification", "autotrain_compatible", "endpoints_compatible", "region:us" ]	token-classification	2022-03-02T23:29:05Z	The model for https://github.com/Lesha17/Punctuation; all credits go to the owner of this repository.
abwqr/t5	abwqr	2023-07-10T13:49:16Z	107	0	transformers	[ "transformers", "pytorch", "t5", "text2text-generation", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text2text-generation	2023-07-07T07:46:46Z	Generates a question of the text example input: Apples offer numerous health benefits due to their rich nutritional profile. They are packed with dietary fiber, promoting healthy digestion and aiding weight management. Apples are a good source of antioxidants, supporting immune function and reducing the risk of chronic diseases. Regular apple consumption is associated with improved heart health and a lower risk of diabetes. This text is about the benefits of apple
JoaoReis/Neuronet	JoaoReis	2023-07-10T13:45:12Z	0	0	null	[ "region:us" ]	null	2023-07-10T13:29:55Z	import socket,warnings try: socket.setdefaulttimeout(1) socket.socket(socket.AF_INET, socket.SOCK_STREAM).connect(('1.1.1.1', 53)) except socket.error as ex: raise Exception("STOP: No internet. Click '>\|' in top right and set 'Internet' switch to on") import os iskaggle = os.environ.get('KAGGLE_KERNEL_RUN_TYPE', '') if iskaggle: !pip install -Uqq fastai !pip install -Uqq duckduckgo_search from duckduckgo_search import ddg_images from fastcore.all import * def search_images(term, max_images=200): return L(ddg_images(term, max_results=max_images)).itemgot('image') urls = search_images(' star fox photos', max_images=1) urls[0] from fastdownload import download_url dest = 'starfox.jpg' download_url(urls[0], dest, show_progress=False) from fastai.vision.all import * im = Image.open(dest) im.to_thumb(256,256) download_url(search_images('eva 01', max_images=1)[0], 'forest.jpg', show_progress=False) Image.open('forest.jpg').to_thumb(256,256) searches = 'eva 01','star fox' path = Path('eva 01_or_not') from time import sleep for o in searches: dest = (path/o) dest.mkdir(exist_ok=True, parents=True) download_images(dest, urls=search_images(f'{o} photo')) sleep(10) # Pause between searches to avoid over-loading server download_images(dest, urls=search_images(f'{o} sun photo')) sleep(10) download_images(dest, urls=search_images(f'{o} shade photo')) sleep(10) resize_images(path/o, max_size=400, dest=path/o) failed = verify_images(get_image_files(path)) failed.map(Path.unlink) len(failed) dls = DataBlock( blocks=(ImageBlock, CategoryBlock), get_items=get_image_files, splitter=RandomSplitter(valid_pct=0.2, seed=42), get_y=parent_label, item_tfms=[Resize(192, method='squish')] ).dataloaders(path) dls.show_batch(max_n=6) learn = vision_learner(dls, resnet18, metrics=error_rate) learn.fine_tune(3) is_bird,_,probs = learn.predict(PILImage.create('bird.jpg')) print(f"This is a: {is_bird}.") print(f"Probability it's a bird: {probs[0]:.4f}")
boostcamp-5th-nlp07/qlora-koalpaca-polyglot-5.8b-fast	boostcamp-5th-nlp07	2023-07-10T13:29:43Z	1	0	peft	[ "peft", "region:us" ]	null	2023-07-10T13:29:38Z	--- library_name: peft --- ## Training procedure The following `bitsandbytes` quantization config was used during training: - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: True - bnb_4bit_compute_dtype: bfloat16 ### Framework versions - PEFT 0.4.0.dev0
AladarMezga/detr-resnet-50_finetuned_cppe5	AladarMezga	2023-07-10T13:26:52Z	192	0	transformers	[ "transformers", "pytorch", "tensorboard", "detr", "object-detection", "generated_from_trainer", "dataset:cppe-5", "license:apache-2.0", "endpoints_compatible", "region:us" ]	object-detection	2023-07-10T12:06:11Z	--- license: apache-2.0 tags: - generated_from_trainer datasets: - cppe-5 model-index: - name: detr-resnet-50_finetuned_cppe5 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # detr-resnet-50_finetuned_cppe5 This model is a fine-tuned version of [facebook/detr-resnet-50](https://huggingface.co/facebook/detr-resnet-50) on the cppe-5 dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 1e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 10 ### Training results ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3
idolior99/RLU1	idolior99	2023-07-10T13:24:34Z	0	0	stable-baselines3	[ "stable-baselines3", "LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]	reinforcement-learning	2023-07-10T13:24:15Z	--- library_name: stable-baselines3 tags: - LunarLander-v2 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: PPO results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: LunarLander-v2 type: LunarLander-v2 metrics: - type: mean_reward value: 235.75 +/- 18.43 name: mean_reward verified: false --- # PPO Agent playing LunarLander-v2 This is a trained model of a PPO agent playing LunarLander-v2 using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3). ## Usage (with Stable-baselines3) TODO: Add your code ```python from stable_baselines3 import ... from huggingface_sb3 import load_from_hub ... ```
Neko-Institute-of-Science/guanaco-unchained-33b-qlora	Neko-Institute-of-Science	2023-07-10T13:24:08Z	0	3	null	[ "dataset:CheshireAI/guanaco-unchained", "region:us" ]	null	2023-07-10T00:10:04Z	--- datasets: - CheshireAI/guanaco-unchained --- Let's see how this goes. Training in 8 bit and at full context. Is 8bit even a qlora? ``` python qlora.py \ --model_name_or_path /UI/text-generation-webui/models/llama-30b \ --output_dir ./output/guanaco-33b \ --logging_steps 1 \ --save_strategy steps \ --data_seed 42 \ --save_steps 69 \ --save_total_limit 999 \ --per_device_eval_batch_size 1 \ --dataloader_num_workers 3 \ --group_by_length \ --logging_strategy steps \ --remove_unused_columns False \ --do_train \ --do_eval false \ --do_mmlu_eval false \ --lora_r 64 \ --lora_alpha 16 \ --lora_modules all \ --bf16 \ --bits 8 \ --warmup_ratio 0.03 \ --lr_scheduler_type constant \ --gradient_checkpointing \ --gradient_accumulation_steps 32 \ --dataset oasst1 \ --source_max_len 2048 \ --target_max_len 2048 \ --per_device_train_batch_size 1 \ --num_train_epochs 3 \ --learning_rate 0.0001 \ --adam_beta2 0.999 \ --max_grad_norm 0.3 \ --lora_dropout 0.05 \ --weight_decay 0.0 \ --seed 0 ```
datenmassiv/falcon-7b-instruct	datenmassiv	2023-07-10T13:00:34Z	13	0	transformers	[ "transformers", "pytorch", "coreml", "RefinedWebModel", "text-generation", "custom_code", "en", "dataset:tiiuae/falcon-refinedweb", "arxiv:2205.14135", "arxiv:1911.02150", "arxiv:2005.14165", "arxiv:2104.09864", "arxiv:2306.01116", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2023-07-10T13:00:33Z	--- datasets: - tiiuae/falcon-refinedweb language: - en inference: true widget: - text: Hey Falcon! Any recommendations for my holidays in Abu Dhabi? example_title: Abu Dhabi Trip - text: What's the Everett interpretation of quantum mechanics? example_title: 'Q/A: Quantum & Answers' - text: >- Give me a list of the top 10 dive sites you would recommend around the world. example_title: Diving Top 10 - text: Can you tell me more about deep-water soloing? example_title: Extreme sports - text: >- Can you write a short tweet about the Apache 2.0 release of our latest AI model, Falcon LLM? example_title: Twitter Helper - text: What are the responsabilities of a Chief Llama Officer? example_title: Trendy Jobs license: apache-2.0 duplicated_from: tiiuae/falcon-7b-instruct --- # ✨ Falcon-7B-Instruct Falcon-7B-Instruct is a 7B parameters causal decoder-only model built by [TII](https://www.tii.ae) based on [Falcon-7B](https://huggingface.co/tiiuae/falcon-7b) and finetuned on a mixture of chat/instruct datasets. It is made available under the Apache 2.0 license. Paper coming soon 😊. 🤗 To get started with Falcon (inference, finetuning, quantization, etc.), we recommend reading [this great blogpost fron HF](https://huggingface.co/blog/falcon)! ## Why use Falcon-7B-Instruct? * You are looking for a ready-to-use chat/instruct model based on [Falcon-7B](https://huggingface.co/tiiuae/falcon-7b). * Falcon-7B is a strong base model, outperforming comparable open-source models (e.g., [MPT-7B](https://huggingface.co/mosaicml/mpt-7b), [StableLM](https://github.com/Stability-AI/StableLM), [RedPajama](https://huggingface.co/togethercomputer/RedPajama-INCITE-Base-7B-v0.1) etc.), thanks to being trained on 1,500B tokens of [RefinedWeb](https://huggingface.co/datasets/tiiuae/falcon-refinedweb) enhanced with curated corpora. See the [OpenLLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard). * It features an architecture optimized for inference, with FlashAttention ([Dao et al., 2022](https://arxiv.org/abs/2205.14135)) and multiquery ([Shazeer et al., 2019](https://arxiv.org/abs/1911.02150)). 💬 This is an instruct model, which may not be ideal for further finetuning. If you are interested in building your own instruct/chat model, we recommend starting from [Falcon-7B](https://huggingface.co/tiiuae/falcon-7b). 🔥 Looking for an even more powerful model? [Falcon-40B-Instruct](https://huggingface.co/tiiuae/falcon-40b-instruct) is Falcon-7B-Instruct's big brother! ```python from transformers import AutoTokenizer, AutoModelForCausalLM import transformers import torch model = "tiiuae/falcon-7b-instruct" tokenizer = AutoTokenizer.from_pretrained(model) pipeline = transformers.pipeline( "text-generation", model=model, tokenizer=tokenizer, torch_dtype=torch.bfloat16, trust_remote_code=True, device_map="auto", ) sequences = pipeline( "Girafatron is obsessed with giraffes, the most glorious animal on the face of this Earth. Giraftron believes all other animals are irrelevant when compared to the glorious majesty of the giraffe.\nDaniel: Hello, Girafatron!\nGirafatron:", max_length=200, do_sample=True, top_k=10, num_return_sequences=1, eos_token_id=tokenizer.eos_token_id, ) for seq in sequences: print(f"Result: {seq['generated_text']}") ``` 💥 Falcon LLMs require PyTorch 2.0 for use with `transformers`! For fast inference with Falcon, check-out [Text Generation Inference](https://github.com/huggingface/text-generation-inference)! Read more in this [blogpost]((https://huggingface.co/blog/falcon). You will need at least 16GB of memory to swiftly run inference with Falcon-7B-Instruct. # Model Card for Falcon-7B-Instruct ## Model Details ### Model Description - Developed by: [https://www.tii.ae](https://www.tii.ae); - Model type: Causal decoder-only; - Language(s) (NLP): English and French; - License: Apache 2.0; - Finetuned from model: [Falcon-7B](https://huggingface.co/tiiuae/falcon-7b). ### Model Source - Paper: coming soon. ## Uses ### Direct Use Falcon-7B-Instruct has been finetuned on a mixture of instruct and chat datasets. ### Out-of-Scope Use Production use without adequate assessment of risks and mitigation; any use cases which may be considered irresponsible or harmful. ## Bias, Risks, and Limitations Falcon-7B-Instruct is mostly trained on English data, and will not generalize appropriately to other languages. Furthermore, as it is trained on a large-scale corpora representative of the web, it will carry the stereotypes and biases commonly encountered online. ### Recommendations We recommend users of Falcon-7B-Instruct to develop guardrails and to take appropriate precautions for any production use. ## How to Get Started with the Model ```python from transformers import AutoTokenizer, AutoModelForCausalLM import transformers import torch model = "tiiuae/falcon-7b-instruct" tokenizer = AutoTokenizer.from_pretrained(model) pipeline = transformers.pipeline( "text-generation", model=model, tokenizer=tokenizer, torch_dtype=torch.bfloat16, trust_remote_code=True, device_map="auto", ) sequences = pipeline( "Girafatron is obsessed with giraffes, the most glorious animal on the face of this Earth. Giraftron believes all other animals are irrelevant when compared to the glorious majesty of the giraffe.\nDaniel: Hello, Girafatron!\nGirafatron:", max_length=200, do_sample=True, top_k=10, num_return_sequences=1, eos_token_id=tokenizer.eos_token_id, ) for seq in sequences: print(f"Result: {seq['generated_text']}") ``` ## Training Details ### Training Data Falcon-7B-Instruct was finetuned on a 250M tokens mixture of instruct/chat datasets. \| Data source \| Fraction \| Tokens \| Description \| \|--------------------\|--------------\|------------\|-----------------------------------\| \| [Bai ze](https://github.com/project-baize/baize-chatbot) \| 65% \| 164M \| chat \| \| [GPT4All](https://github.com/nomic-ai/gpt4all) \| 25% \| 62M \| instruct \| \| [GPTeacher](https://github.com/teknium1/GPTeacher) \| 5% \| 11M \| instruct \| \| [RefinedWeb-English](https://huggingface.co/datasets/tiiuae/falcon-refinedweb) \| 5% \| 13M \| massive web crawl \| The data was tokenized with the Falcon-[7B](https://huggingface.co/tiiuae/falcon-7b)/[40B](https://huggingface.co/tiiuae/falcon-40b) tokenizer. ## Evaluation Paper coming soon. See the [OpenLLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) for early results. Note that this model variant is not optimized for NLP benchmarks. ## Technical Specifications For more information about pretraining, see [Falcon-7B](https://huggingface.co/tiiuae/falcon-7b). ### Model Architecture and Objective Falcon-7B is a causal decoder-only model trained on a causal language modeling task (i.e., predict the next token). The architecture is broadly adapted from the GPT-3 paper ([Brown et al., 2020](https://arxiv.org/abs/2005.14165)), with the following differences: * Positionnal embeddings: rotary ([Su et al., 2021](https://arxiv.org/abs/2104.09864)); * Attention: multiquery ([Shazeer et al., 2019](https://arxiv.org/abs/1911.02150)) and FlashAttention ([Dao et al., 2022](https://arxiv.org/abs/2205.14135)); * Decoder-block: parallel attention/MLP with a single layer norm. \| Hyperparameter \| Value \| Comment \| \|--------------------\|-----------\|----------------------------------------\| \| Layers \| 32 \| \| \| `d_model` \| 4544 \| Increased to compensate for multiquery \| \| `head_dim` \| 64 \| Reduced to optimise for FlashAttention \| \| Vocabulary \| 65024 \| \| \| Sequence length \| 2048 \| \| ### Compute Infrastructure #### Hardware Falcon-7B-Instruct was trained on AWS SageMaker, on 32 A100 40GB GPUs in P4d instances. #### Software Falcon-7B-Instruct was trained a custom distributed training codebase, Gigatron. It uses a 3D parallelism approach combined with ZeRO and high-performance Triton kernels (FlashAttention, etc.) ## Citation Paper coming soon 😊. In the meanwhile, you can use the following information to cite: ``` @article{falcon40b, title={{Falcon-40B}: an open large language model with state-of-the-art performance}, author={Almazrouei, Ebtesam and Alobeidli, Hamza and Alshamsi, Abdulaziz and Cappelli, Alessandro and Cojocaru, Ruxandra and Debbah, Merouane and Goffinet, Etienne and Heslow, Daniel and Launay, Julien and Malartic, Quentin and Noune, Badreddine and Pannier, Baptiste and Penedo, Guilherme}, year={2023} } ``` To learn more about the pretraining dataset, see the 📓 [RefinedWeb paper](https://arxiv.org/abs/2306.01116). ``` @article{refinedweb, title={The {R}efined{W}eb dataset for {F}alcon {LLM}: outperforming curated corpora with web data, and web data only}, author={Guilherme Penedo and Quentin Malartic and Daniel Hesslow and Ruxandra Cojocaru and Alessandro Cappelli and Hamza Alobeidli and Baptiste Pannier and Ebtesam Almazrouei and Julien Launay}, journal={arXiv preprint arXiv:2306.01116}, eprint={2306.01116}, eprinttype = {arXiv}, url={https://arxiv.org/abs/2306.01116}, year={2023} } ``` ## License Falcon-7B-Instruct is made available under the Apache 2.0 license. ## Contact [email protected]
ccattomio/Reinforce-CartPole-v1	ccattomio	2023-07-10T12:59:48Z	0	0	null	[ "CartPole-v1", "reinforce", "reinforcement-learning", "custom-implementation", "deep-rl-class", "model-index", "region:us" ]	reinforcement-learning	2023-07-10T12:59:37Z	--- tags: - CartPole-v1 - reinforce - reinforcement-learning - custom-implementation - deep-rl-class model-index: - name: Reinforce-CartPole-v1 results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: CartPole-v1 type: CartPole-v1 metrics: - type: mean_reward value: 500.00 +/- 0.00 name: mean_reward verified: false --- # Reinforce Agent playing CartPole-v1 This is a trained model of a Reinforce agent playing CartPole-v1 . To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
1aurent/q-FrozenLake-v1-4x4-noSlippery	1aurent	2023-07-10T12:58:37Z	0	0	null	[ "FrozenLake-v1-4x4-no_slippery", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]	reinforcement-learning	2023-07-10T12:58:33Z	--- tags: - FrozenLake-v1-4x4-no_slippery - q-learning - reinforcement-learning - custom-implementation model-index: - name: q-FrozenLake-v1-4x4-noSlippery results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: FrozenLake-v1-4x4-no_slippery type: FrozenLake-v1-4x4-no_slippery metrics: - type: mean_reward value: 1.00 +/- 0.00 name: mean_reward verified: false --- # Q-Learning Agent playing1 FrozenLake-v1 This is a trained model of a Q-Learning agent playing FrozenLake-v1 . ## Usage ```python model = load_from_hub(repo_id="1aurent/q-FrozenLake-v1-4x4-noSlippery", filename="q-learning.pkl") # Don't forget to check if you need to add additional attributes (is_slippery=False etc) env = gym.make(model["env_id"]) ```
NasimB/gpt2-concat-simple-wiki-mod	NasimB	2023-07-10T12:53:29Z	5	0	transformers	[ "transformers", "pytorch", "gpt2", "text-generation", "generated_from_trainer", "dataset:generator", "license:mit", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2023-07-10T11:00:44Z	--- license: mit tags: - generated_from_trainer datasets: - generator model-index: - name: gpt2-concat-simple-wiki-mod results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # gpt2-concat-simple-wiki-mod This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the generator dataset. It achieves the following results on the evaluation set: - Loss: 4.3273 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 64 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_steps: 1000 - num_epochs: 6 - mixed_precision_training: Native AMP ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-----:\|:-----:\|:---------------:\| \| 6.6721 \| 0.29 \| 500 \| 5.6311 \| \| 5.3162 \| 0.59 \| 1000 \| 5.2012 \| \| 4.9814 \| 0.88 \| 1500 \| 4.9493 \| \| 4.708 \| 1.17 \| 2000 \| 4.8102 \| \| 4.5523 \| 1.47 \| 2500 \| 4.6918 \| \| 4.4524 \| 1.76 \| 3000 \| 4.5941 \| \| 4.3303 \| 2.06 \| 3500 \| 4.5209 \| \| 4.1432 \| 2.35 \| 4000 \| 4.4726 \| \| 4.1182 \| 2.64 \| 4500 \| 4.4154 \| \| 4.0753 \| 2.94 \| 5000 \| 4.3598 \| \| 3.8614 \| 3.23 \| 5500 \| 4.3514 \| \| 3.8147 \| 3.52 \| 6000 \| 4.3176 \| \| 3.7996 \| 3.82 \| 6500 \| 4.2839 \| \| 3.6896 \| 4.11 \| 7000 \| 4.2834 \| \| 3.5307 \| 4.4 \| 7500 \| 4.2783 \| \| 3.5227 \| 4.7 \| 8000 \| 4.2595 \| \| 3.5108 \| 4.99 \| 8500 \| 4.2484 \| \| 3.3413 \| 5.28 \| 9000 \| 4.2624 \| \| 3.3338 \| 5.58 \| 9500 \| 4.2605 \| \| 3.3305 \| 5.87 \| 10000 \| 4.2597 \| ### Framework versions - Transformers 4.26.1 - Pytorch 1.11.0+cu113 - Datasets 2.13.0 - Tokenizers 0.13.3
mgmeskill/CartPole-v33	mgmeskill	2023-07-10T12:39:27Z	0	0	null	[ "CartPole-v1", "reinforce", "reinforcement-learning", "custom-implementation", "deep-rl-class", "model-index", "region:us" ]	reinforcement-learning	2023-07-10T12:39:20Z	--- tags: - CartPole-v1 - reinforce - reinforcement-learning - custom-implementation - deep-rl-class model-index: - name: CartPole-v33 results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: CartPole-v1 type: CartPole-v1 metrics: - type: mean_reward value: 30.60 +/- 24.13 name: mean_reward verified: false --- # Reinforce Agent playing CartPole-v1 This is a trained model of a Reinforce agent playing CartPole-v1 . To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
Nianhua123/ppo-LunarLander-v2	Nianhua123	2023-07-10T12:24:32Z	0	0	stable-baselines3	[ "stable-baselines3", "LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]	reinforcement-learning	2023-07-10T12:24:15Z	--- library_name: stable-baselines3 tags: - LunarLander-v2 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: PPO results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: LunarLander-v2 type: LunarLander-v2 metrics: - type: mean_reward value: 269.69 +/- 15.15 name: mean_reward verified: false --- # PPO Agent playing LunarLander-v2 This is a trained model of a PPO agent playing LunarLander-v2 using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3). ## Usage (with Stable-baselines3) TODO: Add your code ```python from stable_baselines3 import ... from huggingface_sb3 import load_from_hub ... ```
PraveenJesu/openai-whisper-medium-peft-lora-v2.2.4	PraveenJesu	2023-07-10T12:24:27Z	1	0	peft	[ "peft", "region:us" ]	null	2023-07-10T12:24:25Z	--- library_name: peft --- ## Training procedure The following `bitsandbytes` quantization config was used during training: - load_in_8bit: True - load_in_4bit: False - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: fp4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: float32 ### Framework versions - PEFT 0.4.0.dev0
2481asd/ssrfun	2481asd	2023-07-10T12:21:45Z	0	8	null	[ "region:us" ]	null	2023-06-01T13:33:50Z	--- title: SsrfunModels emoji: 🔥 colorFrom: green colorTo: gray sdk: static pinned: false --- Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
Mavila/First_DRL	Mavila	2023-07-10T12:06:41Z	0	0	stable-baselines3	[ "stable-baselines3", "LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]	reinforcement-learning	2023-07-10T12:06:19Z	--- library_name: stable-baselines3 tags: - LunarLander-v2 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: PPO results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: LunarLander-v2 type: LunarLander-v2 metrics: - type: mean_reward value: 261.12 +/- 13.54 name: mean_reward verified: false --- # PPO Agent playing LunarLander-v2 This is a trained model of a PPO agent playing LunarLander-v2 using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3). ## Usage (with Stable-baselines3) TODO: Add your code ```python from stable_baselines3 import ... from huggingface_sb3 import load_from_hub ... ```
NasimB/gpt2-concat-guten-mod-2k-rarity-all-4k-p12k	NasimB	2023-07-10T12:05:25Z	5	0	transformers	[ "transformers", "pytorch", "gpt2", "text-generation", "generated_from_trainer", "dataset:generator", "license:mit", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2023-07-10T10:12:31Z	--- license: mit tags: - generated_from_trainer datasets: - generator model-index: - name: gpt2-concat-guten-mod-2k-rarity-all-4k-p12k results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # gpt2-concat-guten-mod-2k-rarity-all-4k-p12k This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the generator dataset. It achieves the following results on the evaluation set: - Loss: 4.3172 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 64 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_steps: 1000 - num_epochs: 6 - mixed_precision_training: Native AMP ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-----:\|:-----:\|:---------------:\| \| 6.6867 \| 0.29 \| 500 \| 5.6408 \| \| 5.3387 \| 0.59 \| 1000 \| 5.2070 \| \| 4.9873 \| 0.88 \| 1500 \| 4.9547 \| \| 4.7105 \| 1.18 \| 2000 \| 4.7987 \| \| 4.5512 \| 1.47 \| 2500 \| 4.6771 \| \| 4.4432 \| 1.76 \| 3000 \| 4.5711 \| \| 4.3124 \| 2.06 \| 3500 \| 4.4934 \| \| 4.1304 \| 2.35 \| 4000 \| 4.4492 \| \| 4.1003 \| 2.65 \| 4500 \| 4.3875 \| \| 4.0551 \| 2.94 \| 5000 \| 4.3342 \| \| 3.8505 \| 3.24 \| 5500 \| 4.3336 \| \| 3.8007 \| 3.53 \| 6000 \| 4.3010 \| \| 3.7833 \| 3.82 \| 6500 \| 4.2676 \| \| 3.6557 \| 4.12 \| 7000 \| 4.2684 \| \| 3.521 \| 4.41 \| 7500 \| 4.2603 \| \| 3.512 \| 4.71 \| 8000 \| 4.2465 \| \| 3.4976 \| 5.0 \| 8500 \| 4.2324 \| \| 3.3273 \| 5.29 \| 9000 \| 4.2482 \| \| 3.317 \| 5.59 \| 9500 \| 4.2467 \| \| 3.3218 \| 5.88 \| 10000 \| 4.2459 \| ### Framework versions - Transformers 4.26.1 - Pytorch 1.11.0+cu113 - Datasets 2.13.0 - Tokenizers 0.13.3
161381373-qq/ee	161381373-qq	2023-07-10T12:04:47Z	0	0	null	[ "arxiv:1910.09700", "region:us" ]	null	2023-07-10T12:04:14Z	--- # For reference on model card metadata, see the spec: https://github.com/huggingface/hub-docs/blob/main/modelcard.md?plain=1 # Doc / guide: https://huggingface.co/docs/hub/model-cards {} --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> This modelcard aims to be a base template for new models. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/modelcard_template.md?plain=1). ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> - Developed by: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Data Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
Salama1429/whisper-tiny-english	Salama1429	2023-07-10T11:57:33Z	91	0	transformers	[ "transformers", "pytorch", "tensorboard", "whisper", "automatic-speech-recognition", "generated_from_trainer", "dataset:PolyAI/minds14", "license:apache-2.0", "model-index", "endpoints_compatible", "region:us" ]	automatic-speech-recognition	2023-07-10T10:05:31Z	--- license: apache-2.0 tags: - generated_from_trainer datasets: - PolyAI/minds14 metrics: - wer model-index: - name: whisper-tiny-english results: - task: name: Automatic Speech Recognition type: automatic-speech-recognition dataset: name: PolyAI/minds14 type: PolyAI/minds14 config: en-US split: train args: en-US metrics: - name: Wer type: wer value: 0.27150380339379755 pipeline_tag: automatic-speech-recognition --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # whisper-tiny-english This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the PolyAI/minds14 dataset. It achieves the following results on the evaluation set: - Loss: 0.6834 - Wer Ortho: 0.280025 - Wer: 0.271504 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 1e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: constant_with_warmup - lr_scheduler_warmup_steps: 50 - training_steps: 500 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Wer Ortho \| Wer \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:---------:\|:-------:\| \| 0.0007 \| 17.86 \| 500 \| 0.6834 \| 0.280025 \| 0.271504 \| ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3
Benita12/videomae-base-finetuned-ucf101-subset	Benita12	2023-07-10T11:39:42Z	60	0	transformers	[ "transformers", "pytorch", "tensorboard", "videomae", "video-classification", "generated_from_trainer", "license:cc-by-nc-4.0", "endpoints_compatible", "region:us" ]	video-classification	2023-06-13T14:44:31Z	--- license: cc-by-nc-4.0 tags: - generated_from_trainer metrics: - accuracy model-index: - name: videomae-base-finetuned-ucf101-subset results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # videomae-base-finetuned-ucf101-subset This model is a fine-tuned version of [MCG-NJU/videomae-base](https://huggingface.co/MCG-NJU/videomae-base) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.3070 - Accuracy: 0.8968 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 2 - eval_batch_size: 2 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - training_steps: 450 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\| \| 1.1183 \| 0.33 \| 150 \| 1.2051 \| 0.4714 \| \| 1.1544 \| 1.33 \| 300 \| 0.4946 \| 0.8 \| \| 0.1042 \| 2.33 \| 450 \| 0.2526 \| 0.9429 \| ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3
tyavika/LR1E4-BS16-Distil-CNN512LSTM256NoBi	tyavika	2023-07-10T11:29:13Z	76	0	transformers	[ "transformers", "pytorch", "distilbert", "question-answering", "generated_from_trainer", "endpoints_compatible", "region:us" ]	question-answering	2023-07-09T20:24:08Z	--- tags: - generated_from_trainer model-index: - name: LR1E4-BS16-Distil-CNN512LSTM256NoBi results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # LR1E4-BS16-Distil-CNN512LSTM256NoBi This model is a fine-tuned version of [tyavika/LR1E4-BS16-Distil-CNN512LSTM256NoBi](https://huggingface.co/tyavika/LR1E4-BS16-Distil-CNN512LSTM256NoBi) on the None dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 10 ### Framework versions - Transformers 4.28.0 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3
Junr-syl/tweet_sentiments_analysis	Junr-syl	2023-07-10T11:21:39Z	162	0	transformers	[ "transformers", "pytorch", "tensorboard", "bert", "text-classification", "generated_from_trainer", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2023-07-07T09:19:12Z	--- license: apache-2.0 tags: - generated_from_trainer model-index: - name: tweet_sentiments_analysis results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # tweet_sentiments_analysis This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on an unknown dataset. It achieves the following results on the evaluation set: - eval_loss: 0.3953 - eval_accuracy: 0.8660 - eval_runtime: 254.1512 - eval_samples_per_second: 31.473 - eval_steps_per_second: 3.935 - step: 0 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 1000 ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3
AquaV/Hoers13B-ggml-q4_0	AquaV	2023-07-10T11:17:51Z	0	0	null	[ "region:us" ]	null	2023-07-10T10:06:01Z	I believe this was trained on the dataset available at https://huggingface.co/datasets/Amo/FimFic_Omega_V3. The dataset comprises user-generated stories inspired by the "My Little Pony: Friendship is Magic" series. I'm not the original creator of the model however based on the training data the format for the prompts might be: ``` <\|startoftext\|> [tags: author: (author name), character: (character name), character: (character name), genre: (genre), series: (series name) warning: (content warnings)] * CHAPTER: (chapter name) {Cursor here} ``` I am uncertain if "<\|startoftext\|>" should be included. Here are two examples from the training data: ``` <\|startoftext\|> [tags: author: device heretic, character: Other, character: Princess Celestia, character: Twilight Sparkle, genre: Sad, genre: Slice of Life, genre: Tragedy, series: My Little Pony: Friendship is Magic ] * CHAPTER: The Underlying Truth {Cursor here} ``` ``` <\|startoftext\|> [tags: author: Bloodline Spike, character: Cutie Mark Crusaders, character: Main 6, character: Princess Celestia, character: Princess Luna, character: Spike, genre: Adventure, genre: Dark, genre: Romance, genre: Sad, genre: Tragedy, series: My Little Pony: Friendship is Magic, warning: Gore ] *** CHAPTER: Chapter 1 Entering the Medallion {Cursor here} ``` As I am just an archiver of this model, I may not be able to provide further support or solve issues you encounter while using it.
JFoz/test_nvs	JFoz	2023-07-10T11:06:54Z	0	0	null	[ "license:cc-by-nc-4.0", "region:us" ]	null	2023-07-06T15:23:06Z	--- license: cc-by-nc-4.0 --- ## GenVS (partial) reimplementation Model weights for a partial, somewhat unfaithful reimplementation of GeNVS https://nvlabs.github.io/genvs/media/genvs.pdf Code repo at https://github.com/jfozard/nvs_test ### Dataset source Model trained on ShapeNet car renderings from https://github.com/vsitzmann/scene-representation-networks These are not for commercial use (ShapeNet license conditions). ### Example results Conditioning image ![Conditioning image](https://user-images.githubusercontent.com/4390954/252312435-bdc0d595-aae6-43f3-8acb-ac79d880161a.png) Reconstructed views ![Video](https://user-images.githubusercontent.com/4390954/252312886-e8cab1ae-a7ae-4bd0-b11d-8a103ed5fdfb.mp4)

trevorj/dqn-SpaceInvadersNoFrameskip-v4

trevorj

2023-07-10T22:41:49Z

0

stable-baselines3

[ "stable-baselines3", "SpaceInvadersNoFrameskip-v4", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]

reinforcement-learning

2023-07-10T22:41:13Z

--- library_name: stable-baselines3 tags: - SpaceInvadersNoFrameskip-v4 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: DQN results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: SpaceInvadersNoFrameskip-v4 type: SpaceInvadersNoFrameskip-v4 metrics: - type: mean_reward value: 523.00 +/- 142.73 name: mean_reward verified: false --- # **DQN** Agent playing **SpaceInvadersNoFrameskip-v4** This is a trained model of a **DQN** agent playing **SpaceInvadersNoFrameskip-v4** using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3) and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo). The RL Zoo is a training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included. ## Usage (with SB3 RL Zoo) RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/> SB3: https://github.com/DLR-RM/stable-baselines3<br/> SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib Install the RL Zoo (with SB3 and SB3-Contrib): ```bash pip install rl_zoo3 ``` ``` # Download model and save it into the logs/ folder python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga trevorj -f logs/ python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ ``` If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do: ``` python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga trevorj -f logs/ python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ ``` ## Training (with the RL Zoo) ``` python -m rl_zoo3.train --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ # Upload the model and generate video (when possible) python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga trevorj ``` ## Hyperparameters ```python OrderedDict([('batch_size', 32), ('buffer_size', 100000), ('env_wrapper', ['stable_baselines3.common.atari_wrappers.AtariWrapper']), ('exploration_final_eps', 0.01), ('exploration_fraction', 0.1), ('frame_stack', 4), ('gradient_steps', 1), ('learning_rate', 0.0001), ('learning_starts', 100000), ('n_timesteps', 1000000.0), ('optimize_memory_usage', False), ('policy', 'CnnPolicy'), ('target_update_interval', 1000), ('train_freq', 4), ('normalize', False)]) ``` # Environment Arguments ```python {'render_mode': 'rgb_array'} ```

jordyvl/vit-small_tobacco3482_kd_CEKD_t5.0_a0.9

jordyvl

2023-07-10T22:40:13Z

161

0

transformers

[ "transformers", "pytorch", "vit", "image-classification", "generated_from_trainer", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

image-classification

2023-07-10T22:00:19Z

--- license: apache-2.0 tags: - generated_from_trainer metrics: - accuracy model-index: - name: vit-small_tobacco3482_kd_CEKD_t5.0_a0.9 results: [] ---  # vit-small_tobacco3482_kd_CEKD_t5.0_a0.9 This model is a fine-tuned version of [WinKawaks/vit-small-patch16-224](https://huggingface.co/WinKawaks/vit-small-patch16-224) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.5373 - Accuracy: 0.85 - Brier Loss: 0.2432 - Nll: 1.1157 - F1 Micro: 0.85 - F1 Macro: 0.8450 - Ece: 0.1621 - Aurc: 0.0427 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 100 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | Brier Loss | Nll | F1 Micro | F1 Macro | Ece | Aurc | |:-------------:|:-----:|:----:|:---------------:|:--------:|:----------:|:------:|:--------:|:--------:|:------:|:------:| | No log | 1.0 | 7 | 2.1036 | 0.215 | 0.8753 | 5.3195 | 0.2150 | 0.1264 | 0.2571 | 0.6923 | | No log | 2.0 | 14 | 1.6952 | 0.405 | 0.7407 | 3.4929 | 0.405 | 0.2416 | 0.2907 | 0.4040 | | No log | 3.0 | 21 | 1.1843 | 0.62 | 0.5633 | 2.0113 | 0.62 | 0.5725 | 0.2740 | 0.2014 | | No log | 4.0 | 28 | 0.8797 | 0.71 | 0.4080 | 1.7043 | 0.7100 | 0.6683 | 0.2024 | 0.1125 | | No log | 5.0 | 35 | 0.8570 | 0.715 | 0.3837 | 1.6476 | 0.715 | 0.7280 | 0.2189 | 0.1079 | | No log | 6.0 | 42 | 0.7484 | 0.775 | 0.3285 | 1.5962 | 0.775 | 0.7668 | 0.1873 | 0.0816 | | No log | 7.0 | 49 | 0.7337 | 0.79 | 0.3131 | 1.5377 | 0.79 | 0.7779 | 0.1904 | 0.0771 | | No log | 8.0 | 56 | 0.6709 | 0.795 | 0.3012 | 1.2156 | 0.795 | 0.7776 | 0.1939 | 0.0761 | | No log | 9.0 | 63 | 0.6901 | 0.795 | 0.3069 | 1.4725 | 0.795 | 0.7916 | 0.1882 | 0.0769 | | No log | 10.0 | 70 | 0.7960 | 0.75 | 0.3586 | 1.4426 | 0.75 | 0.7406 | 0.1868 | 0.0976 | | No log | 11.0 | 77 | 0.7489 | 0.77 | 0.3296 | 1.6202 | 0.7700 | 0.7794 | 0.2020 | 0.0878 | | No log | 12.0 | 84 | 0.7068 | 0.785 | 0.3270 | 1.4127 | 0.785 | 0.7812 | 0.1922 | 0.0759 | | No log | 13.0 | 91 | 0.6687 | 0.79 | 0.3050 | 1.3820 | 0.79 | 0.7945 | 0.1818 | 0.0625 | | No log | 14.0 | 98 | 0.6052 | 0.79 | 0.2854 | 1.0602 | 0.79 | 0.7716 | 0.1702 | 0.0590 | | No log | 15.0 | 105 | 0.6369 | 0.795 | 0.2959 | 1.0580 | 0.795 | 0.7953 | 0.1709 | 0.0603 | | No log | 16.0 | 112 | 0.6204 | 0.81 | 0.2816 | 1.1886 | 0.81 | 0.8050 | 0.1657 | 0.0702 | | No log | 17.0 | 119 | 0.5648 | 0.83 | 0.2475 | 1.2506 | 0.83 | 0.8241 | 0.1347 | 0.0612 | | No log | 18.0 | 126 | 0.5849 | 0.83 | 0.2672 | 1.2245 | 0.83 | 0.8155 | 0.1646 | 0.0601 | | No log | 19.0 | 133 | 0.5536 | 0.835 | 0.2475 | 1.0514 | 0.835 | 0.8254 | 0.1683 | 0.0531 | | No log | 20.0 | 140 | 0.5689 | 0.835 | 0.2513 | 1.2369 | 0.835 | 0.8437 | 0.1722 | 0.0489 | | No log | 21.0 | 147 | 0.5540 | 0.83 | 0.2485 | 1.2139 | 0.83 | 0.8165 | 0.1641 | 0.0608 | | No log | 22.0 | 154 | 0.5352 | 0.835 | 0.2402 | 1.0108 | 0.835 | 0.8295 | 0.1408 | 0.0430 | | No log | 23.0 | 161 | 0.5380 | 0.84 | 0.2403 | 1.2280 | 0.8400 | 0.8347 | 0.1405 | 0.0436 | | No log | 24.0 | 168 | 0.5422 | 0.835 | 0.2471 | 1.0204 | 0.835 | 0.8324 | 0.1606 | 0.0445 | | No log | 25.0 | 175 | 0.5342 | 0.85 | 0.2404 | 1.0767 | 0.85 | 0.8487 | 0.1469 | 0.0432 | | No log | 26.0 | 182 | 0.5374 | 0.84 | 0.2429 | 1.0774 | 0.8400 | 0.8334 | 0.1420 | 0.0462 | | No log | 27.0 | 189 | 0.5311 | 0.85 | 0.2395 | 1.0748 | 0.85 | 0.8487 | 0.1439 | 0.0446 | | No log | 28.0 | 196 | 0.5298 | 0.85 | 0.2384 | 1.1337 | 0.85 | 0.8487 | 0.1570 | 0.0437 | | No log | 29.0 | 203 | 0.5387 | 0.845 | 0.2435 | 1.1319 | 0.845 | 0.8424 | 0.1539 | 0.0458 | | No log | 30.0 | 210 | 0.5361 | 0.85 | 0.2430 | 1.0648 | 0.85 | 0.8450 | 0.1679 | 0.0431 | | No log | 31.0 | 217 | 0.5339 | 0.85 | 0.2413 | 1.0676 | 0.85 | 0.8487 | 0.1646 | 0.0428 | | No log | 32.0 | 224 | 0.5345 | 0.85 | 0.2421 | 1.0709 | 0.85 | 0.8487 | 0.1476 | 0.0440 | | No log | 33.0 | 231 | 0.5343 | 0.85 | 0.2421 | 1.1236 | 0.85 | 0.8450 | 0.1621 | 0.0431 | | No log | 34.0 | 238 | 0.5353 | 0.845 | 0.2426 | 1.1244 | 0.845 | 0.8424 | 0.1710 | 0.0428 | | No log | 35.0 | 245 | 0.5346 | 0.85 | 0.2423 | 1.0649 | 0.85 | 0.8487 | 0.1520 | 0.0440 | | No log | 36.0 | 252 | 0.5356 | 0.855 | 0.2422 | 1.1241 | 0.855 | 0.8517 | 0.1814 | 0.0429 | | No log | 37.0 | 259 | 0.5357 | 0.85 | 0.2426 | 1.1237 | 0.85 | 0.8450 | 0.1670 | 0.0425 | | No log | 38.0 | 266 | 0.5356 | 0.845 | 0.2426 | 1.1226 | 0.845 | 0.8419 | 0.1607 | 0.0435 | | No log | 39.0 | 273 | 0.5347 | 0.855 | 0.2420 | 1.0739 | 0.855 | 0.8517 | 0.1597 | 0.0427 | | No log | 40.0 | 280 | 0.5356 | 0.855 | 0.2423 | 1.1203 | 0.855 | 0.8517 | 0.1676 | 0.0435 | | No log | 41.0 | 287 | 0.5365 | 0.85 | 0.2431 | 1.1199 | 0.85 | 0.8450 | 0.1780 | 0.0429 | | No log | 42.0 | 294 | 0.5356 | 0.85 | 0.2426 | 1.1173 | 0.85 | 0.8450 | 0.1653 | 0.0430 | | No log | 43.0 | 301 | 0.5363 | 0.85 | 0.2428 | 1.1189 | 0.85 | 0.8450 | 0.1550 | 0.0435 | | No log | 44.0 | 308 | 0.5345 | 0.85 | 0.2418 | 1.1193 | 0.85 | 0.8450 | 0.1590 | 0.0428 | | No log | 45.0 | 315 | 0.5374 | 0.85 | 0.2435 | 1.1202 | 0.85 | 0.8450 | 0.1633 | 0.0435 | | No log | 46.0 | 322 | 0.5355 | 0.85 | 0.2423 | 1.1183 | 0.85 | 0.8450 | 0.1564 | 0.0428 | | No log | 47.0 | 329 | 0.5354 | 0.85 | 0.2425 | 1.1176 | 0.85 | 0.8450 | 0.1509 | 0.0429 | | No log | 48.0 | 336 | 0.5369 | 0.85 | 0.2433 | 1.1177 | 0.85 | 0.8450 | 0.1517 | 0.0432 | | No log | 49.0 | 343 | 0.5361 | 0.85 | 0.2428 | 1.1182 | 0.85 | 0.8450 | 0.1490 | 0.0428 | | No log | 50.0 | 350 | 0.5364 | 0.85 | 0.2431 | 1.1179 | 0.85 | 0.8450 | 0.1654 | 0.0430 | | No log | 51.0 | 357 | 0.5365 | 0.85 | 0.2428 | 1.1185 | 0.85 | 0.8450 | 0.1729 | 0.0432 | | No log | 52.0 | 364 | 0.5364 | 0.85 | 0.2430 | 1.1165 | 0.85 | 0.8450 | 0.1614 | 0.0429 | | No log | 53.0 | 371 | 0.5362 | 0.85 | 0.2429 | 1.1167 | 0.85 | 0.8450 | 0.1694 | 0.0430 | | No log | 54.0 | 378 | 0.5369 | 0.85 | 0.2432 | 1.1170 | 0.85 | 0.8450 | 0.1597 | 0.0432 | | No log | 55.0 | 385 | 0.5368 | 0.85 | 0.2430 | 1.1168 | 0.85 | 0.8450 | 0.1670 | 0.0429 | | No log | 56.0 | 392 | 0.5367 | 0.85 | 0.2430 | 1.1180 | 0.85 | 0.8450 | 0.1619 | 0.0430 | | No log | 57.0 | 399 | 0.5364 | 0.85 | 0.2429 | 1.1163 | 0.85 | 0.8450 | 0.1649 | 0.0429 | | No log | 58.0 | 406 | 0.5364 | 0.85 | 0.2430 | 1.1156 | 0.85 | 0.8450 | 0.1611 | 0.0429 | | No log | 59.0 | 413 | 0.5365 | 0.85 | 0.2428 | 1.1163 | 0.85 | 0.8450 | 0.1591 | 0.0429 | | No log | 60.0 | 420 | 0.5364 | 0.85 | 0.2429 | 1.1155 | 0.85 | 0.8450 | 0.1588 | 0.0429 | | No log | 61.0 | 427 | 0.5370 | 0.85 | 0.2432 | 1.1158 | 0.85 | 0.8450 | 0.1772 | 0.0432 | | No log | 62.0 | 434 | 0.5367 | 0.85 | 0.2429 | 1.1167 | 0.85 | 0.8450 | 0.1622 | 0.0429 | | No log | 63.0 | 441 | 0.5362 | 0.85 | 0.2428 | 1.1162 | 0.85 | 0.8450 | 0.1503 | 0.0428 | | No log | 64.0 | 448 | 0.5372 | 0.85 | 0.2433 | 1.1161 | 0.85 | 0.8450 | 0.1616 | 0.0432 | | No log | 65.0 | 455 | 0.5371 | 0.85 | 0.2431 | 1.1162 | 0.85 | 0.8450 | 0.1499 | 0.0429 | | No log | 66.0 | 462 | 0.5367 | 0.85 | 0.2430 | 1.1160 | 0.85 | 0.8450 | 0.1591 | 0.0427 | | No log | 67.0 | 469 | 0.5367 | 0.85 | 0.2430 | 1.1164 | 0.85 | 0.8450 | 0.1562 | 0.0428 | | No log | 68.0 | 476 | 0.5368 | 0.85 | 0.2430 | 1.1168 | 0.85 | 0.8450 | 0.1556 | 0.0427 | | No log | 69.0 | 483 | 0.5368 | 0.85 | 0.2431 | 1.1158 | 0.85 | 0.8450 | 0.1593 | 0.0428 | | No log | 70.0 | 490 | 0.5372 | 0.85 | 0.2432 | 1.1162 | 0.85 | 0.8450 | 0.1628 | 0.0428 | | No log | 71.0 | 497 | 0.5371 | 0.85 | 0.2432 | 1.1163 | 0.85 | 0.8450 | 0.1599 | 0.0429 | | 0.1708 | 72.0 | 504 | 0.5370 | 0.85 | 0.2430 | 1.1161 | 0.85 | 0.8450 | 0.1559 | 0.0430 | | 0.1708 | 73.0 | 511 | 0.5372 | 0.85 | 0.2433 | 1.1154 | 0.85 | 0.8450 | 0.1556 | 0.0428 | | 0.1708 | 74.0 | 518 | 0.5370 | 0.85 | 0.2429 | 1.1165 | 0.85 | 0.8450 | 0.1540 | 0.0428 | | 0.1708 | 75.0 | 525 | 0.5371 | 0.85 | 0.2431 | 1.1161 | 0.85 | 0.8450 | 0.1616 | 0.0427 | | 0.1708 | 76.0 | 532 | 0.5369 | 0.85 | 0.2431 | 1.1161 | 0.85 | 0.8450 | 0.1619 | 0.0427 | | 0.1708 | 77.0 | 539 | 0.5369 | 0.85 | 0.2430 | 1.1156 | 0.85 | 0.8450 | 0.1623 | 0.0429 | | 0.1708 | 78.0 | 546 | 0.5372 | 0.85 | 0.2432 | 1.1158 | 0.85 | 0.8450 | 0.1619 | 0.0427 | | 0.1708 | 79.0 | 553 | 0.5375 | 0.85 | 0.2433 | 1.1162 | 0.85 | 0.8450 | 0.1688 | 0.0429 | | 0.1708 | 80.0 | 560 | 0.5372 | 0.85 | 0.2432 | 1.1160 | 0.85 | 0.8450 | 0.1623 | 0.0429 | | 0.1708 | 81.0 | 567 | 0.5373 | 0.85 | 0.2432 | 1.1162 | 0.85 | 0.8450 | 0.1620 | 0.0428 | | 0.1708 | 82.0 | 574 | 0.5374 | 0.85 | 0.2433 | 1.1160 | 0.85 | 0.8450 | 0.1622 | 0.0428 | | 0.1708 | 83.0 | 581 | 0.5372 | 0.85 | 0.2432 | 1.1159 | 0.85 | 0.8450 | 0.1622 | 0.0428 | | 0.1708 | 84.0 | 588 | 0.5371 | 0.85 | 0.2431 | 1.1157 | 0.85 | 0.8450 | 0.1621 | 0.0427 | | 0.1708 | 85.0 | 595 | 0.5372 | 0.85 | 0.2432 | 1.1158 | 0.85 | 0.8450 | 0.1687 | 0.0426 | | 0.1708 | 86.0 | 602 | 0.5372 | 0.85 | 0.2432 | 1.1157 | 0.85 | 0.8450 | 0.1619 | 0.0426 | | 0.1708 | 87.0 | 609 | 0.5374 | 0.85 | 0.2432 | 1.1159 | 0.85 | 0.8450 | 0.1687 | 0.0428 | | 0.1708 | 88.0 | 616 | 0.5373 | 0.85 | 0.2432 | 1.1160 | 0.85 | 0.8450 | 0.1620 | 0.0427 | | 0.1708 | 89.0 | 623 | 0.5373 | 0.85 | 0.2432 | 1.1157 | 0.85 | 0.8450 | 0.1620 | 0.0427 | | 0.1708 | 90.0 | 630 | 0.5373 | 0.85 | 0.2432 | 1.1156 | 0.85 | 0.8450 | 0.1620 | 0.0427 | | 0.1708 | 91.0 | 637 | 0.5372 | 0.85 | 0.2432 | 1.1156 | 0.85 | 0.8450 | 0.1620 | 0.0427 | | 0.1708 | 92.0 | 644 | 0.5373 | 0.85 | 0.2432 | 1.1157 | 0.85 | 0.8450 | 0.1620 | 0.0427 | | 0.1708 | 93.0 | 651 | 0.5372 | 0.85 | 0.2432 | 1.1156 | 0.85 | 0.8450 | 0.1620 | 0.0427 | | 0.1708 | 94.0 | 658 | 0.5373 | 0.85 | 0.2432 | 1.1158 | 0.85 | 0.8450 | 0.1620 | 0.0427 | | 0.1708 | 95.0 | 665 | 0.5373 | 0.85 | 0.2432 | 1.1157 | 0.85 | 0.8450 | 0.1621 | 0.0427 | | 0.1708 | 96.0 | 672 | 0.5372 | 0.85 | 0.2432 | 1.1157 | 0.85 | 0.8450 | 0.1621 | 0.0427 | | 0.1708 | 97.0 | 679 | 0.5372 | 0.85 | 0.2432 | 1.1157 | 0.85 | 0.8450 | 0.1620 | 0.0427 | | 0.1708 | 98.0 | 686 | 0.5373 | 0.85 | 0.2432 | 1.1157 | 0.85 | 0.8450 | 0.1621 | 0.0427 | | 0.1708 | 99.0 | 693 | 0.5373 | 0.85 | 0.2432 | 1.1157 | 0.85 | 0.8450 | 0.1621 | 0.0427 | | 0.1708 | 100.0 | 700 | 0.5373 | 0.85 | 0.2432 | 1.1157 | 0.85 | 0.8450 | 0.1621 | 0.0427 | ### Framework versions - Transformers 4.26.1 - Pytorch 1.13.1.post200 - Datasets 2.9.0 - Tokenizers 0.13.2

digiplay/BlankCanvas_v1

digiplay

2023-07-10T22:36:13Z

323

2

diffusers

[ "diffusers", "safetensors", "stable-diffusion", "stable-diffusion-diffusers", "text-to-image", "license:other", "autotrain_compatible", "endpoints_compatible", "diffusers:StableDiffusionPipeline", "region:us" ]

text-to-image

2023-07-10T09:59:13Z

--- license: other tags: - stable-diffusion - stable-diffusion-diffusers - text-to-image - diffusers inference: true --- Model info: https://civitai.com/models/106523/blank-canvas Original Author's DEMO images : ![](https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/3be6f78d-49ea-4ad2-a78c-1aeea19c8dcc/width=1200/FotoJet.jpeg)

Raizel123/Mbyonglora

Raizel123

2023-07-10T22:31:20Z

0

null

[ "license:creativeml-openrail-m", "region:us" ]

null

2023-07-10T22:27:47Z

--- license: creativeml-openrail-m ---

jordyvl/vit-small_rvl_cdip_100_examples_per_class_kd_MSE

jordyvl

2023-07-10T22:30:03Z

163

0

transformers

[ "transformers", "pytorch", "tensorboard", "vit", "image-classification", "generated_from_trainer", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

image-classification

2023-07-10T21:13:38Z

--- license: apache-2.0 tags: - generated_from_trainer metrics: - accuracy model-index: - name: vit-small_rvl_cdip_100_examples_per_class_kd_MSE results: [] ---  # vit-small_rvl_cdip_100_examples_per_class_kd_MSE This model is a fine-tuned version of [WinKawaks/vit-small-patch16-224](https://huggingface.co/WinKawaks/vit-small-patch16-224) on the None dataset. It achieves the following results on the evaluation set: - Loss: 1.4673 - Accuracy: 0.6425 - Brier Loss: 0.4763 - Nll: 3.0680 - F1 Micro: 0.6425 - F1 Macro: 0.6485 - Ece: 0.1946 - Aurc: 0.1381 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 32 - eval_batch_size: 32 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 100 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | Brier Loss | Nll | F1 Micro | F1 Macro | Ece | Aurc | |:-------------:|:-----:|:----:|:---------------:|:--------:|:----------:|:-------:|:--------:|:--------:|:------:|:------:| | No log | 1.0 | 25 | 4.4851 | 0.06 | 0.9565 | 13.8276 | 0.06 | 0.0556 | 0.1688 | 0.9385 | | No log | 2.0 | 50 | 3.5619 | 0.3775 | 0.7827 | 6.2649 | 0.3775 | 0.3611 | 0.2331 | 0.3882 | | No log | 3.0 | 75 | 2.8990 | 0.5025 | 0.6453 | 4.7376 | 0.5025 | 0.4858 | 0.1689 | 0.2658 | | No log | 4.0 | 100 | 2.5972 | 0.515 | 0.5980 | 4.4210 | 0.515 | 0.4895 | 0.1605 | 0.2249 | | No log | 5.0 | 125 | 2.4353 | 0.56 | 0.5762 | 3.4885 | 0.56 | 0.5566 | 0.1548 | 0.2100 | | No log | 6.0 | 150 | 2.4157 | 0.5475 | 0.5864 | 3.8261 | 0.5475 | 0.5323 | 0.1837 | 0.2167 | | No log | 7.0 | 175 | 2.1786 | 0.6075 | 0.5203 | 3.4565 | 0.6075 | 0.6103 | 0.1403 | 0.1670 | | No log | 8.0 | 200 | 2.1082 | 0.63 | 0.5040 | 3.3570 | 0.63 | 0.6246 | 0.1580 | 0.1530 | | No log | 9.0 | 225 | 2.0472 | 0.625 | 0.5042 | 3.8572 | 0.625 | 0.6184 | 0.1552 | 0.1530 | | No log | 10.0 | 250 | 2.0589 | 0.6025 | 0.5468 | 3.5723 | 0.6025 | 0.5982 | 0.1781 | 0.1785 | | No log | 11.0 | 275 | 1.8965 | 0.65 | 0.4755 | 3.4466 | 0.65 | 0.6497 | 0.1605 | 0.1475 | | No log | 12.0 | 300 | 1.9014 | 0.6325 | 0.5066 | 3.0881 | 0.6325 | 0.6359 | 0.1658 | 0.1591 | | No log | 13.0 | 325 | 1.7904 | 0.6175 | 0.5162 | 3.4673 | 0.6175 | 0.6141 | 0.1525 | 0.1598 | | No log | 14.0 | 350 | 1.8624 | 0.625 | 0.5173 | 3.6824 | 0.625 | 0.6179 | 0.1567 | 0.1624 | | No log | 15.0 | 375 | 1.7083 | 0.6625 | 0.4817 | 3.1296 | 0.6625 | 0.6686 | 0.1651 | 0.1405 | | No log | 16.0 | 400 | 1.8848 | 0.59 | 0.5478 | 4.3761 | 0.59 | 0.5913 | 0.2083 | 0.1696 | | No log | 17.0 | 425 | 1.7238 | 0.6125 | 0.5229 | 3.1232 | 0.6125 | 0.6052 | 0.1833 | 0.1553 | | No log | 18.0 | 450 | 1.7126 | 0.625 | 0.5152 | 2.9267 | 0.625 | 0.6284 | 0.1747 | 0.1565 | | No log | 19.0 | 475 | 1.6459 | 0.6275 | 0.5024 | 2.9078 | 0.6275 | 0.6219 | 0.1766 | 0.1527 | | 1.0542 | 20.0 | 500 | 1.6029 | 0.6275 | 0.4855 | 3.0931 | 0.6275 | 0.6316 | 0.1720 | 0.1414 | | 1.0542 | 21.0 | 525 | 1.6566 | 0.6525 | 0.4847 | 3.0998 | 0.6525 | 0.6479 | 0.1558 | 0.1438 | | 1.0542 | 22.0 | 550 | 1.6169 | 0.645 | 0.4894 | 3.0081 | 0.645 | 0.6471 | 0.1687 | 0.1400 | | 1.0542 | 23.0 | 575 | 1.5322 | 0.6525 | 0.4557 | 3.3587 | 0.6525 | 0.6520 | 0.1428 | 0.1247 | | 1.0542 | 24.0 | 600 | 1.5991 | 0.6475 | 0.4787 | 2.9349 | 0.6475 | 0.6444 | 0.1580 | 0.1450 | | 1.0542 | 25.0 | 625 | 1.5625 | 0.6375 | 0.4926 | 3.0245 | 0.6375 | 0.6378 | 0.1641 | 0.1433 | | 1.0542 | 26.0 | 650 | 1.5366 | 0.64 | 0.4884 | 3.3388 | 0.64 | 0.6461 | 0.1595 | 0.1453 | | 1.0542 | 27.0 | 675 | 1.5686 | 0.65 | 0.4765 | 3.5120 | 0.65 | 0.6504 | 0.1625 | 0.1359 | | 1.0542 | 28.0 | 700 | 1.5562 | 0.6475 | 0.4817 | 3.0348 | 0.6475 | 0.6488 | 0.1459 | 0.1388 | | 1.0542 | 29.0 | 725 | 1.5213 | 0.6475 | 0.4719 | 3.2628 | 0.6475 | 0.6475 | 0.1634 | 0.1326 | | 1.0542 | 30.0 | 750 | 1.5492 | 0.6675 | 0.4730 | 3.1693 | 0.6675 | 0.6679 | 0.1469 | 0.1415 | | 1.0542 | 31.0 | 775 | 1.5311 | 0.65 | 0.4896 | 3.0881 | 0.65 | 0.6504 | 0.1815 | 0.1380 | | 1.0542 | 32.0 | 800 | 1.5556 | 0.6475 | 0.4821 | 3.1829 | 0.6475 | 0.6491 | 0.1640 | 0.1405 | | 1.0542 | 33.0 | 825 | 1.5471 | 0.6375 | 0.4846 | 3.4190 | 0.6375 | 0.6407 | 0.1628 | 0.1415 | | 1.0542 | 34.0 | 850 | 1.4809 | 0.6575 | 0.4714 | 2.9136 | 0.6575 | 0.6612 | 0.1729 | 0.1338 | | 1.0542 | 35.0 | 875 | 1.5256 | 0.66 | 0.4773 | 3.2303 | 0.66 | 0.6650 | 0.1746 | 0.1368 | | 1.0542 | 36.0 | 900 | 1.4929 | 0.6675 | 0.4671 | 3.2360 | 0.6675 | 0.6698 | 0.1698 | 0.1309 | | 1.0542 | 37.0 | 925 | 1.4923 | 0.645 | 0.4880 | 3.0567 | 0.645 | 0.6564 | 0.1764 | 0.1395 | | 1.0542 | 38.0 | 950 | 1.5038 | 0.665 | 0.4672 | 3.2116 | 0.665 | 0.6661 | 0.1588 | 0.1343 | | 1.0542 | 39.0 | 975 | 1.4708 | 0.6625 | 0.4669 | 3.1420 | 0.6625 | 0.6675 | 0.1683 | 0.1301 | | 0.0522 | 40.0 | 1000 | 1.5153 | 0.6475 | 0.4865 | 3.1796 | 0.6475 | 0.6447 | 0.1639 | 0.1400 | | 0.0522 | 41.0 | 1025 | 1.4705 | 0.6575 | 0.4642 | 3.2196 | 0.6575 | 0.6626 | 0.1440 | 0.1308 | | 0.0522 | 42.0 | 1050 | 1.4844 | 0.6575 | 0.4722 | 3.2445 | 0.6575 | 0.6595 | 0.1746 | 0.1328 | | 0.0522 | 43.0 | 1075 | 1.4957 | 0.6425 | 0.4828 | 3.1456 | 0.6425 | 0.6468 | 0.1499 | 0.1417 | | 0.0522 | 44.0 | 1100 | 1.5179 | 0.645 | 0.4910 | 3.3921 | 0.645 | 0.6470 | 0.1861 | 0.1433 | | 0.0522 | 45.0 | 1125 | 1.4878 | 0.6425 | 0.4839 | 3.2139 | 0.6425 | 0.6478 | 0.1720 | 0.1403 | | 0.0522 | 46.0 | 1150 | 1.4666 | 0.655 | 0.4741 | 2.9333 | 0.655 | 0.6601 | 0.1813 | 0.1347 | | 0.0522 | 47.0 | 1175 | 1.4954 | 0.6575 | 0.4776 | 3.2102 | 0.6575 | 0.6604 | 0.1842 | 0.1390 | | 0.0522 | 48.0 | 1200 | 1.4976 | 0.645 | 0.4856 | 3.1539 | 0.645 | 0.6493 | 0.1549 | 0.1407 | | 0.0522 | 49.0 | 1225 | 1.4772 | 0.64 | 0.4780 | 2.9845 | 0.64 | 0.6445 | 0.1826 | 0.1388 | | 0.0522 | 50.0 | 1250 | 1.4584 | 0.65 | 0.4703 | 3.0776 | 0.65 | 0.6533 | 0.1685 | 0.1352 | | 0.0522 | 51.0 | 1275 | 1.4828 | 0.6325 | 0.4844 | 3.1425 | 0.6325 | 0.6377 | 0.1641 | 0.1409 | | 0.0522 | 52.0 | 1300 | 1.4676 | 0.6525 | 0.4737 | 3.1483 | 0.6525 | 0.6565 | 0.1773 | 0.1358 | | 0.0522 | 53.0 | 1325 | 1.4675 | 0.6475 | 0.4791 | 3.1411 | 0.6475 | 0.6515 | 0.1820 | 0.1388 | | 0.0522 | 54.0 | 1350 | 1.4724 | 0.645 | 0.4764 | 3.0744 | 0.645 | 0.6499 | 0.1847 | 0.1382 | | 0.0522 | 55.0 | 1375 | 1.4689 | 0.6425 | 0.4769 | 3.2256 | 0.6425 | 0.6476 | 0.1839 | 0.1376 | | 0.0522 | 56.0 | 1400 | 1.4660 | 0.6425 | 0.4760 | 2.9907 | 0.6425 | 0.6479 | 0.1906 | 0.1378 | | 0.0522 | 57.0 | 1425 | 1.4663 | 0.645 | 0.4757 | 3.0722 | 0.645 | 0.6514 | 0.1705 | 0.1367 | | 0.0522 | 58.0 | 1450 | 1.4678 | 0.65 | 0.4770 | 3.0710 | 0.65 | 0.6546 | 0.1794 | 0.1371 | | 0.0522 | 59.0 | 1475 | 1.4717 | 0.64 | 0.4786 | 3.0737 | 0.64 | 0.6455 | 0.1889 | 0.1392 | | 0.0064 | 60.0 | 1500 | 1.4691 | 0.645 | 0.4768 | 3.0688 | 0.645 | 0.6499 | 0.1815 | 0.1378 | | 0.0064 | 61.0 | 1525 | 1.4689 | 0.64 | 0.4767 | 3.0688 | 0.64 | 0.6452 | 0.1846 | 0.1382 | | 0.0064 | 62.0 | 1550 | 1.4689 | 0.64 | 0.4770 | 3.0674 | 0.64 | 0.6455 | 0.1937 | 0.1383 | | 0.0064 | 63.0 | 1575 | 1.4687 | 0.6425 | 0.4767 | 3.0700 | 0.6425 | 0.6485 | 0.1897 | 0.1381 | | 0.0064 | 64.0 | 1600 | 1.4674 | 0.6425 | 0.4764 | 3.0675 | 0.6425 | 0.6472 | 0.1855 | 0.1375 | | 0.0064 | 65.0 | 1625 | 1.4681 | 0.6425 | 0.4766 | 3.0694 | 0.6425 | 0.6485 | 0.1917 | 0.1381 | | 0.0064 | 66.0 | 1650 | 1.4681 | 0.6425 | 0.4766 | 3.0687 | 0.6425 | 0.6472 | 0.1905 | 0.1378 | | 0.0064 | 67.0 | 1675 | 1.4667 | 0.645 | 0.4757 | 3.0681 | 0.645 | 0.6505 | 0.1899 | 0.1375 | | 0.0064 | 68.0 | 1700 | 1.4683 | 0.6425 | 0.4771 | 3.0686 | 0.6425 | 0.6474 | 0.1871 | 0.1379 | | 0.0064 | 69.0 | 1725 | 1.4672 | 0.64 | 0.4760 | 3.0679 | 0.64 | 0.6455 | 0.1932 | 0.1380 | | 0.0064 | 70.0 | 1750 | 1.4673 | 0.6425 | 0.4763 | 3.0683 | 0.6425 | 0.6474 | 0.1955 | 0.1376 | | 0.0064 | 71.0 | 1775 | 1.4676 | 0.645 | 0.4763 | 3.0680 | 0.645 | 0.6505 | 0.1921 | 0.1376 | | 0.0064 | 72.0 | 1800 | 1.4674 | 0.6425 | 0.4763 | 3.0683 | 0.6425 | 0.6474 | 0.1946 | 0.1376 | | 0.0064 | 73.0 | 1825 | 1.4675 | 0.6425 | 0.4763 | 3.0682 | 0.6425 | 0.6474 | 0.1946 | 0.1377 | | 0.0064 | 74.0 | 1850 | 1.4674 | 0.6425 | 0.4763 | 3.0682 | 0.6425 | 0.6485 | 0.1945 | 0.1380 | | 0.0064 | 75.0 | 1875 | 1.4674 | 0.64 | 0.4763 | 3.0680 | 0.64 | 0.6455 | 0.1960 | 0.1380 | | 0.0064 | 76.0 | 1900 | 1.4675 | 0.64 | 0.4764 | 3.0682 | 0.64 | 0.6455 | 0.1972 | 0.1381 | | 0.0064 | 77.0 | 1925 | 1.4675 | 0.6425 | 0.4763 | 3.0681 | 0.6425 | 0.6485 | 0.1947 | 0.1380 | | 0.0064 | 78.0 | 1950 | 1.4674 | 0.6425 | 0.4763 | 3.0681 | 0.6425 | 0.6485 | 0.1958 | 0.1381 | | 0.0064 | 79.0 | 1975 | 1.4674 | 0.6425 | 0.4763 | 3.0680 | 0.6425 | 0.6474 | 0.1935 | 0.1376 | | 0.0 | 80.0 | 2000 | 1.4673 | 0.6425 | 0.4763 | 3.0681 | 0.6425 | 0.6485 | 0.1958 | 0.1380 | | 0.0 | 81.0 | 2025 | 1.4674 | 0.6425 | 0.4763 | 3.0681 | 0.6425 | 0.6485 | 0.1946 | 0.1380 | | 0.0 | 82.0 | 2050 | 1.4673 | 0.6425 | 0.4763 | 3.0680 | 0.6425 | 0.6485 | 0.1935 | 0.1380 | | 0.0 | 83.0 | 2075 | 1.4674 | 0.6425 | 0.4763 | 3.0680 | 0.6425 | 0.6485 | 0.1946 | 0.1381 | | 0.0 | 84.0 | 2100 | 1.4674 | 0.6425 | 0.4763 | 3.0681 | 0.6425 | 0.6485 | 0.1958 | 0.1381 | | 0.0 | 85.0 | 2125 | 1.4673 | 0.6425 | 0.4763 | 3.0680 | 0.6425 | 0.6485 | 0.1946 | 0.1381 | | 0.0 | 86.0 | 2150 | 1.4673 | 0.6425 | 0.4763 | 3.0680 | 0.6425 | 0.6485 | 0.1946 | 0.1381 | | 0.0 | 87.0 | 2175 | 1.4673 | 0.6425 | 0.4763 | 3.0681 | 0.6425 | 0.6485 | 0.1958 | 0.1381 | | 0.0 | 88.0 | 2200 | 1.4673 | 0.6425 | 0.4763 | 3.0680 | 0.6425 | 0.6485 | 0.1946 | 0.1381 | | 0.0 | 89.0 | 2225 | 1.4673 | 0.6425 | 0.4763 | 3.0680 | 0.6425 | 0.6485 | 0.1946 | 0.1381 | | 0.0 | 90.0 | 2250 | 1.4673 | 0.6425 | 0.4763 | 3.0680 | 0.6425 | 0.6485 | 0.1946 | 0.1381 | | 0.0 | 91.0 | 2275 | 1.4673 | 0.6425 | 0.4763 | 3.0680 | 0.6425 | 0.6485 | 0.1946 | 0.1381 | | 0.0 | 92.0 | 2300 | 1.4673 | 0.6425 | 0.4763 | 3.0680 | 0.6425 | 0.6485 | 0.1946 | 0.1381 | | 0.0 | 93.0 | 2325 | 1.4673 | 0.6425 | 0.4763 | 3.0680 | 0.6425 | 0.6485 | 0.1946 | 0.1381 | | 0.0 | 94.0 | 2350 | 1.4673 | 0.6425 | 0.4763 | 3.0680 | 0.6425 | 0.6485 | 0.1909 | 0.1381 | | 0.0 | 95.0 | 2375 | 1.4673 | 0.6425 | 0.4763 | 3.0680 | 0.6425 | 0.6485 | 0.1946 | 0.1381 | | 0.0 | 96.0 | 2400 | 1.4673 | 0.6425 | 0.4763 | 3.0680 | 0.6425 | 0.6485 | 0.1946 | 0.1381 | | 0.0 | 97.0 | 2425 | 1.4673 | 0.6425 | 0.4763 | 3.0680 | 0.6425 | 0.6485 | 0.1946 | 0.1381 | | 0.0 | 98.0 | 2450 | 1.4673 | 0.6425 | 0.4763 | 3.0680 | 0.6425 | 0.6485 | 0.1946 | 0.1381 | | 0.0 | 99.0 | 2475 | 1.4673 | 0.6425 | 0.4763 | 3.0680 | 0.6425 | 0.6485 | 0.1946 | 0.1381 | | 0.0 | 100.0 | 2500 | 1.4673 | 0.6425 | 0.4763 | 3.0680 | 0.6425 | 0.6485 | 0.1946 | 0.1381 | ### Framework versions - Transformers 4.28.0.dev0 - Pytorch 1.12.1+cu113 - Datasets 2.12.0 - Tokenizers 0.12.1

jorgeortizfuentes/spanish-bert-base-spanish-wwm-cased

jorgeortizfuentes

2023-07-10T22:27:15Z

111

0

transformers

[ "transformers", "safetensors", "bert", "fill-mask", "generated_from_trainer", "dataset:jorgeortizfuentes/universal_spanish_chilean_corpus", "autotrain_compatible", "endpoints_compatible", "region:us" ]

fill-mask

2023-07-10T19:32:52Z

--- tags: - generated_from_trainer datasets: - jorgeortizfuentes/universal_spanish_chilean_corpus model-index: - name: spanish-bert-base-spanish-wwm-cased results: [] ---  # spanish-bert-base-spanish-wwm-cased This model is a fine-tuned version of [dccuchile/bert-base-spanish-wwm-cased](https://huggingface.co/dccuchile/bert-base-spanish-wwm-cased) on the jorgeortizfuentes/universal_spanish_chilean_corpus dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 13 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 1 ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu117 - Datasets 2.13.1 - Tokenizers 0.13.3

Raizel123/Novalora

Raizel123

2023-07-10T22:26:20Z

0

null

[ "license:creativeml-openrail-m", "region:us" ]

null

2023-07-10T22:23:44Z

--- license: creativeml-openrail-m ---

Renan1986-12/distilbert-base-uncased-finetuned-cola

Renan1986-12

2023-07-10T22:24:22Z

62

0

transformers

[ "transformers", "tf", "tensorboard", "distilbert", "text-classification", "generated_from_keras_callback", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

text-classification

2023-07-10T22:13:06Z

--- license: apache-2.0 tags: - generated_from_keras_callback model-index: - name: Renan1986-12/distilbert-base-uncased-finetuned-cola results: [] ---  # Renan1986-12/distilbert-base-uncased-finetuned-cola This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset. It achieves the following results on the evaluation set: - Train Loss: 0.1680 - Validation Loss: 0.5433 - Train Matthews Correlation: 0.5570 - Epoch: 2 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 1602, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False} - training_precision: float32 ### Training results | Train Loss | Validation Loss | Train Matthews Correlation | Epoch | |:----------:|:---------------:|:--------------------------:|:-----:| | 0.4525 | 0.4571 | 0.4871 | 0 | | 0.2752 | 0.4495 | 0.5614 | 1 | | 0.1680 | 0.5433 | 0.5570 | 2 | ### Framework versions - Transformers 4.30.2 - TensorFlow 2.12.0 - Datasets 2.13.1 - Tokenizers 0.13.3

NasimB/gpt2-dp-mod-datasets-txt-processing-rarity-all

NasimB

2023-07-10T22:14:46Z

4

0

transformers

[ "transformers", "pytorch", "gpt2", "text-generation", "generated_from_trainer", "dataset:generator", "license:mit", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]

text-generation

2023-07-10T19:52:59Z

--- license: mit tags: - generated_from_trainer datasets: - generator model-index: - name: gpt2-dp-mod-datasets-txt-processing-rarity-all results: [] ---  # gpt2-dp-mod-datasets-txt-processing-rarity-all This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the generator dataset. It achieves the following results on the evaluation set: - Loss: 4.4242 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 64 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_steps: 1000 - num_epochs: 7 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:-----:|:---------------:| | 6.7606 | 0.29 | 500 | 5.6933 | | 5.4375 | 0.59 | 1000 | 5.2559 | | 5.0937 | 0.88 | 1500 | 5.0171 | | 4.8204 | 1.18 | 2000 | 4.8701 | | 4.6728 | 1.47 | 2500 | 4.7593 | | 4.574 | 1.77 | 3000 | 4.6587 | | 4.4456 | 2.06 | 3500 | 4.5885 | | 4.258 | 2.36 | 4000 | 4.5468 | | 4.2423 | 2.65 | 4500 | 4.4860 | | 4.2036 | 2.94 | 5000 | 4.4302 | | 3.9737 | 3.24 | 5500 | 4.4364 | | 3.9439 | 3.53 | 6000 | 4.4019 | | 3.9271 | 3.83 | 6500 | 4.3632 | | 3.7901 | 4.12 | 7000 | 4.3689 | | 3.6474 | 4.42 | 7500 | 4.3662 | | 3.6414 | 4.71 | 8000 | 4.3472 | | 3.6338 | 5.01 | 8500 | 4.3344 | | 3.3764 | 5.3 | 9000 | 4.3618 | | 3.3821 | 5.59 | 9500 | 4.3568 | | 3.3777 | 5.89 | 10000 | 4.3513 | | 3.2752 | 6.18 | 10500 | 4.3602 | | 3.2228 | 6.48 | 11000 | 4.3652 | | 3.2172 | 6.77 | 11500 | 4.3656 | ### Framework versions - Transformers 4.26.1 - Pytorch 1.11.0+cu113 - Datasets 2.13.0 - Tokenizers 0.13.3

carova/ppo-LunarLander-v2

carova

2023-07-10T22:11:10Z

2

0

stable-baselines3

[ "stable-baselines3", "LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]

reinforcement-learning

2023-07-10T17:56:56Z

--- library_name: stable-baselines3 tags: - LunarLander-v2 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: PPO results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: LunarLander-v2 type: LunarLander-v2 metrics: - type: mean_reward value: 233.36 +/- 68.33 name: mean_reward verified: false --- # **PPO** Agent playing **LunarLander-v2** This is a trained model of a **PPO** agent playing **LunarLander-v2** using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3). ## Usage (with Stable-baselines3) TODO: Add your code ```python from stable_baselines3 import ... from huggingface_sb3 import load_from_hub ... ```

heea/image-to-music

heea

2023-07-10T22:09:33Z

0

2

null

[ "region:us" ]

null

2023-07-10T22:05:47Z

import matplotlib.pyplot as plt import numpy as np from scipy.io.wavfile import write # Load the image image_path = 'hugging_face.jpg' image = plt.imread(image_path) # Convert the image to grayscale grayscale_image = np.mean(image, axis=2) # Define the musical parameters sample_rate = 44100 # Audio sample rate (Hz) duration = 0.1 # Duration of each note (seconds) # Define the mapping from pixel values to musical notes min_note = 40 # MIDI note number for the lowest pixel value max_note = 80 # MIDI note number for the highest pixel value # Rescale the pixel values to the range [min_note, max_note] scaled_image = (grayscale_image - np.min(grayscale_image)) scaled_image *= (max_note - min_note) / np.max(scaled_image) scaled_image += min_note # Generate the audio signal total_duration = int(duration * sample_rate * grayscale_image.shape[1]) t = np.linspace(0, total_duration / sample_rate, total_duration, endpoint=False) audio_signal = np.zeros(total_duration) for i, column in enumerate(scaled_image.T): start = int(i * duration * sample_rate) end = int((i + 1) * duration * sample_rate) audio_signal[start:end] = np.sin(2 * np.pi * column * t[start:end]) # Normalize the audio signal audio_signal /= np.max(np.abs(audio_signal)) audio_signal *= 32767 # Scale the signal to the range of a 16-bit integer # Convert the audio signal to 16-bit integer format audio_signal = audio_signal.astype(np.int16) # Save the audio signal to a WAV file output_file = 'hugging_face.wav' write(output_file, sample_rate, audio_signal) print(f"Audio file '{output_file}' generated successfully!")

TheBloke/airochronos-33B-GGML

TheBloke

2023-07-10T22:07:18Z

0

18

null

[ "license:other", "region:us" ]

null

2023-07-10T21:14:18Z

--- inference: false license: other ---  <div style="width: 100%;"> <img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;"> </div> <div style="display: flex; justify-content: space-between; width: 100%;"> <div style="display: flex; flex-direction: column; align-items: flex-start;"> <p><a href="https://discord.gg/theblokeai">Chat & support: my new Discord server</a></p> </div> <div style="display: flex; flex-direction: column; align-items: flex-end;"> <p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p> </div> </div>  # Henk717's Airochronos 33B GGML These files are GGML format model files for [Henk717's Airochronos 33B](https://huggingface.co/Henk717/airochronos-33B). GGML files are for CPU + GPU inference using [llama.cpp](https://github.com/ggerganov/llama.cpp) and libraries and UIs which support this format, such as: * [KoboldCpp](https://github.com/LostRuins/koboldcpp), a powerful GGML web UI with full GPU acceleration out of the box. Especially good for story telling. * [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with GPU acceleration via the c_transformers backend. * [LM Studio](https://lmstudio.ai/), a fully featured local GUI. Supports full GPU accel on macOS. Also supports Windows, without GPU accel. * [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most popular web UI. Requires extra steps to enable GPU accel via llama.cpp backend. * [ctransformers](https://github.com/marella/ctransformers), a Python library with LangChain support and OpenAI-compatible AI server. * [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with OpenAI-compatible API server. ## Repositories available * [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/airochronos-33B-GPTQ) * [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/airochronos-33B-GGML) * [Unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/Henk717/airochronos-33B) ## Prompt template: Alpaca ```Below is an instruction that describes a task. Write a response that appropriately completes the request. ### Instruction: {prompt} ### Response: ```  ## Compatibility ### Original llama.cpp quant methods: `q4_0, q4_1, q5_0, q5_1, q8_0` These are guaranteed to be compatible with any UIs, tools and libraries released since late May. They may be phased out soon, as they are largely superseded by the new k-quant methods. ### New k-quant methods: `q2_K, q3_K_S, q3_K_M, q3_K_L, q4_K_S, q4_K_M, q5_K_S, q6_K` These new quantisation methods are compatible with llama.cpp as of June 6th, commit `2d43387`. They are now also compatible with recent releases of text-generation-webui, KoboldCpp, llama-cpp-python, ctransformers, rustformers and most others. For compatibility with other tools and libraries, please check their documentation. ## Explanation of the new k-quant methods <details> <summary>Click to see details</summary> The new methods available are: * GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw) * GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw. * GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw. * GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw * GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw * GGML_TYPE_Q8_K - "type-0" 8-bit quantization. Only used for quantizing intermediate results. The difference to the existing Q8_0 is that the block size is 256. All 2-6 bit dot products are implemented for this quantization type. Refer to the Provided Files table below to see what files use which methods, and how. </details>  ## Provided files | Name | Quant method | Bits | Size | Max RAM required | Use case | | ---- | ---- | ---- | ---- | ---- | ----- | | airochronos-33b.ggmlv3.q2_K.bin | q2_K | 2 | 13.71 GB| 16.21 GB | New k-quant method. Uses GGML_TYPE_Q4_K for the attention.vw and feed_forward.w2 tensors, GGML_TYPE_Q2_K for the other tensors. | | airochronos-33b.ggmlv3.q3_K_S.bin | q3_K_S | 3 | 14.06 GB| 16.56 GB | New k-quant method. Uses GGML_TYPE_Q3_K for all tensors | | airochronos-33b.ggmlv3.q3_K_M.bin | q3_K_M | 3 | 15.72 GB| 18.22 GB | New k-quant method. Uses GGML_TYPE_Q4_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K | | airochronos-33b.ggmlv3.q3_K_L.bin | q3_K_L | 3 | 17.28 GB| 19.78 GB | New k-quant method. Uses GGML_TYPE_Q5_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K | | airochronos-33b.ggmlv3.q4_K_S.bin | q4_K_S | 4 | 18.36 GB| 20.86 GB | New k-quant method. Uses GGML_TYPE_Q4_K for all tensors | | airochronos-33b.ggmlv3.q4_K_M.bin | q4_K_M | 4 | 19.62 GB| 22.12 GB | New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q4_K | | airochronos-33b.ggmlv3.q4_0.bin | q4_0 | 4 | 18.30 GB| 20.80 GB | Original quant method, 4-bit. | | airochronos-33b.ggmlv3.q4_1.bin | q4_1 | 4 | 20.33 GB| 22.83 GB | Original quant method, 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models. | | airochronos-33b.ggmlv3.q5_K_S.bin | q5_K_S | 5 | 22.40 GB| 24.90 GB | New k-quant method. Uses GGML_TYPE_Q5_K for all tensors | | airochronos-33b.ggmlv3.q5_K_M.bin | q5_K_M | 5 | 23.05 GB| 25.55 GB | New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q5_K | | airochronos-33b.ggmlv3.q5_0.bin | q5_0 | 5 | 22.37 GB| 24.87 GB | Original quant method, 5-bit. Higher accuracy, higher resource usage and slower inference. | | airochronos-33b.ggmlv3.q5_1.bin | q5_1 | 5 | 24.40 GB| 26.90 GB | Original quant method, 5-bit. Even higher accuracy, resource usage and slower inference. | | airochronos-33b.ggmlv3.q6_K.bin | q6_K | 6 | 26.69 GB| 29.19 GB | New k-quant method. Uses GGML_TYPE_Q8_K - 6-bit quantization - for all tensors | | airochronos-33b.ggmlv3.q8_0.bin | q8_0 | 8 | 34.56 GB| 37.06 GB | Original quant method, 8-bit. Almost indistinguishable from float16. High resource use and slow. Not recommended for most users. | **Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead. ## How to run in `llama.cpp` I use the following command line; adjust for your tastes and needs: ``` ./main -t 10 -ngl 32 -m airochronos-33b.ggmlv3.q4_0.bin --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "### Instruction: Write a story about llamas\n### Response:" ``` Change `-t 10` to the number of physical CPU cores you have. For example if your system has 8 cores/16 threads, use `-t 8`. Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration. If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins` ## How to run in `text-generation-webui` Further instructions here: [text-generation-webui/docs/llama.cpp-models.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/llama.cpp-models.md).  ## Discord For further support, and discussions on these models and AI in general, join us at: [TheBloke AI's Discord server](https://discord.gg/theblokeai) ## Thanks, and how to contribute. Thanks to the [chirper.ai](https://chirper.ai) team! I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training. If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects. Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits. * Patreon: https://patreon.com/TheBlokeAI * Ko-Fi: https://ko-fi.com/TheBlokeAI **Special thanks to**: Luke from CarbonQuill, Aemon Algiz. **Patreon special mentions**: Space Cruiser, Nikolai Manek, Sam, Chris McCloskey, Rishabh Srivastava, Kalila, Spiking Neurons AB, Khalefa Al-Ahmad, WelcomeToTheClub, Chadd, Lone Striker, Viktor Bowallius, Edmond Seymore, Ai Maven, Chris Smitley, Dave, Alexandros Triantafyllidis, Luke @flexchar, Elle, ya boyyy, Talal Aujan, Alex , Jonathan Leane, Deep Realms, Randy H, subjectnull, Preetika Verma, Joseph William Delisle, Michael Levine, chris gileta, K, Oscar Rangel, LangChain4j, Trenton Dambrowitz, Eugene Pentland, Johann-Peter Hartmann, Femi Adebogun, Illia Dulskyi, senxiiz, Daniel P. Andersen, Sean Connelly, Artur Olbinski, RoA, Mano Prime, Derek Yates, Raven Klaugh, David Flickinger, Willem Michiel, Pieter, Willian Hasse, vamX, Luke Pendergrass, webtim, Ghost , Rainer Wilmers, Nathan LeClaire, Will Dee, Cory Kujawski, John Detwiler, Fred von Graf, biorpg, Iucharbius , Imad Khwaja, Pierre Kircher, terasurfer , Asp the Wyvern, John Villwock, theTransient, zynix , Gabriel Tamborski, Fen Risland, Gabriel Puliatti, Matthew Berman, Pyrater, SuperWojo, Stephen Murray, Karl Bernard, Ajan Kanaga, Greatston Gnanesh, Junyu Yang. Thank you to all my generous patrons and donaters!  # Original model card: Henk717's Airochronos 33B After the initial experiment with chronoboros-33B it was evident that the merge was to unpredictable to be useful, testing the individual models it became clear that the bias should be weighted towards Chronos. This is the new release of the merge with 75% chronos 33B, and 25% airoboros-1.4 33B. Model has been tested with the Alpaca prompting format combined with KoboldAI Lite's instruct and chat modes, as well as regular story writing. It has also been tested on basic reasoning tasks, but has not seen much testing for factual information.

jordyvl/vit-small_tobacco3482_kd_CEKD_t5.0_a0.7

jordyvl

2023-07-10T21:59:33Z

161

0

transformers

[ "transformers", "pytorch", "vit", "image-classification", "generated_from_trainer", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

image-classification

2023-07-10T21:19:56Z

--- license: apache-2.0 tags: - generated_from_trainer metrics: - accuracy model-index: - name: vit-small_tobacco3482_kd_CEKD_t5.0_a0.7 results: [] ---  # vit-small_tobacco3482_kd_CEKD_t5.0_a0.7 This model is a fine-tuned version of [WinKawaks/vit-small-patch16-224](https://huggingface.co/WinKawaks/vit-small-patch16-224) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.4918 - Accuracy: 0.85 - Brier Loss: 0.2583 - Nll: 1.0894 - F1 Micro: 0.85 - F1 Macro: 0.8374 - Ece: 0.1917 - Aurc: 0.0470 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 100 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | Brier Loss | Nll | F1 Micro | F1 Macro | Ece | Aurc | |:-------------:|:-----:|:----:|:---------------:|:--------:|:----------:|:------:|:--------:|:--------:|:------:|:------:| | No log | 1.0 | 7 | 1.8329 | 0.225 | 0.8761 | 5.2731 | 0.225 | 0.1384 | 0.2607 | 0.6977 | | No log | 2.0 | 14 | 1.4785 | 0.405 | 0.7460 | 3.4067 | 0.405 | 0.2289 | 0.3097 | 0.4085 | | No log | 3.0 | 21 | 1.0406 | 0.6 | 0.5725 | 1.8722 | 0.6 | 0.5345 | 0.3050 | 0.2010 | | No log | 4.0 | 28 | 0.8087 | 0.725 | 0.4192 | 1.6096 | 0.7250 | 0.6767 | 0.2345 | 0.1149 | | No log | 5.0 | 35 | 0.7666 | 0.735 | 0.3731 | 1.6189 | 0.735 | 0.7350 | 0.2377 | 0.1011 | | No log | 6.0 | 42 | 0.6960 | 0.78 | 0.3413 | 1.5230 | 0.78 | 0.7592 | 0.2295 | 0.0868 | | No log | 7.0 | 49 | 0.6490 | 0.805 | 0.3110 | 1.4861 | 0.805 | 0.7864 | 0.2138 | 0.0785 | | No log | 8.0 | 56 | 0.6238 | 0.795 | 0.3069 | 1.2098 | 0.795 | 0.7816 | 0.2065 | 0.0698 | | No log | 9.0 | 63 | 0.5755 | 0.83 | 0.2866 | 1.1943 | 0.83 | 0.8117 | 0.1937 | 0.0694 | | No log | 10.0 | 70 | 0.6360 | 0.77 | 0.3164 | 1.2608 | 0.7700 | 0.7550 | 0.1785 | 0.0677 | | No log | 11.0 | 77 | 0.6548 | 0.785 | 0.3335 | 1.4895 | 0.785 | 0.7707 | 0.2281 | 0.0885 | | No log | 12.0 | 84 | 0.5847 | 0.805 | 0.3002 | 1.4317 | 0.805 | 0.7807 | 0.2264 | 0.0756 | | No log | 13.0 | 91 | 0.5956 | 0.81 | 0.3040 | 1.2590 | 0.81 | 0.7928 | 0.2241 | 0.0556 | | No log | 14.0 | 98 | 0.5692 | 0.81 | 0.3025 | 1.2119 | 0.81 | 0.8043 | 0.2235 | 0.0665 | | No log | 15.0 | 105 | 0.5223 | 0.83 | 0.2762 | 1.1162 | 0.83 | 0.8221 | 0.1798 | 0.0552 | | No log | 16.0 | 112 | 0.4981 | 0.84 | 0.2523 | 1.0864 | 0.8400 | 0.8372 | 0.1868 | 0.0396 | | No log | 17.0 | 119 | 0.5207 | 0.805 | 0.2741 | 1.0416 | 0.805 | 0.7897 | 0.1960 | 0.0551 | | No log | 18.0 | 126 | 0.5165 | 0.84 | 0.2723 | 1.1596 | 0.8400 | 0.8325 | 0.1942 | 0.0506 | | No log | 19.0 | 133 | 0.4979 | 0.845 | 0.2573 | 1.2329 | 0.845 | 0.8297 | 0.1825 | 0.0444 | | No log | 20.0 | 140 | 0.4953 | 0.855 | 0.2565 | 1.1213 | 0.855 | 0.8442 | 0.1844 | 0.0474 | | No log | 21.0 | 147 | 0.5296 | 0.82 | 0.2792 | 1.0000 | 0.82 | 0.8218 | 0.1768 | 0.0523 | | No log | 22.0 | 154 | 0.5027 | 0.835 | 0.2625 | 0.9926 | 0.835 | 0.8238 | 0.2035 | 0.0481 | | No log | 23.0 | 161 | 0.5027 | 0.84 | 0.2642 | 1.0500 | 0.8400 | 0.8299 | 0.1616 | 0.0482 | | No log | 24.0 | 168 | 0.5017 | 0.84 | 0.2616 | 1.0560 | 0.8400 | 0.8314 | 0.1819 | 0.0497 | | No log | 25.0 | 175 | 0.4942 | 0.85 | 0.2594 | 1.1003 | 0.85 | 0.8407 | 0.1793 | 0.0483 | | No log | 26.0 | 182 | 0.4943 | 0.83 | 0.2586 | 1.0436 | 0.83 | 0.8140 | 0.1869 | 0.0518 | | No log | 27.0 | 189 | 0.4950 | 0.835 | 0.2613 | 1.0817 | 0.835 | 0.8224 | 0.2039 | 0.0504 | | No log | 28.0 | 196 | 0.4957 | 0.85 | 0.2599 | 1.1109 | 0.85 | 0.8309 | 0.2058 | 0.0485 | | No log | 29.0 | 203 | 0.4956 | 0.845 | 0.2599 | 1.0914 | 0.845 | 0.8304 | 0.1916 | 0.0492 | | No log | 30.0 | 210 | 0.4893 | 0.84 | 0.2561 | 1.0890 | 0.8400 | 0.8214 | 0.2071 | 0.0482 | | No log | 31.0 | 217 | 0.4920 | 0.835 | 0.2587 | 1.0907 | 0.835 | 0.8270 | 0.2031 | 0.0482 | | No log | 32.0 | 224 | 0.4927 | 0.83 | 0.2601 | 1.0879 | 0.83 | 0.8157 | 0.2093 | 0.0500 | | No log | 33.0 | 231 | 0.4925 | 0.835 | 0.2593 | 1.0886 | 0.835 | 0.8270 | 0.1810 | 0.0484 | | No log | 34.0 | 238 | 0.4909 | 0.845 | 0.2578 | 1.0871 | 0.845 | 0.8304 | 0.1916 | 0.0478 | | No log | 35.0 | 245 | 0.4927 | 0.845 | 0.2591 | 1.0866 | 0.845 | 0.8378 | 0.1943 | 0.0473 | | No log | 36.0 | 252 | 0.4919 | 0.85 | 0.2581 | 1.0891 | 0.85 | 0.8342 | 0.2193 | 0.0475 | | No log | 37.0 | 259 | 0.4908 | 0.845 | 0.2579 | 1.0867 | 0.845 | 0.8346 | 0.2215 | 0.0474 | | No log | 38.0 | 266 | 0.4929 | 0.85 | 0.2590 | 1.0873 | 0.85 | 0.8407 | 0.1884 | 0.0471 | | No log | 39.0 | 273 | 0.4913 | 0.85 | 0.2584 | 1.0861 | 0.85 | 0.8374 | 0.1944 | 0.0474 | | No log | 40.0 | 280 | 0.4933 | 0.835 | 0.2595 | 1.0871 | 0.835 | 0.8248 | 0.1893 | 0.0491 | | No log | 41.0 | 287 | 0.4936 | 0.84 | 0.2599 | 1.0863 | 0.8400 | 0.8276 | 0.1860 | 0.0486 | | No log | 42.0 | 294 | 0.4911 | 0.85 | 0.2580 | 1.0861 | 0.85 | 0.8374 | 0.2186 | 0.0474 | | No log | 43.0 | 301 | 0.4915 | 0.85 | 0.2581 | 1.0860 | 0.85 | 0.8374 | 0.2023 | 0.0475 | | No log | 44.0 | 308 | 0.4921 | 0.85 | 0.2586 | 1.0874 | 0.85 | 0.8374 | 0.2013 | 0.0477 | | No log | 45.0 | 315 | 0.4915 | 0.85 | 0.2583 | 1.0862 | 0.85 | 0.8374 | 0.1941 | 0.0475 | | No log | 46.0 | 322 | 0.4918 | 0.85 | 0.2584 | 1.0878 | 0.85 | 0.8374 | 0.1852 | 0.0473 | | No log | 47.0 | 329 | 0.4916 | 0.85 | 0.2583 | 1.0873 | 0.85 | 0.8374 | 0.2089 | 0.0473 | | No log | 48.0 | 336 | 0.4921 | 0.85 | 0.2586 | 1.0879 | 0.85 | 0.8374 | 0.2026 | 0.0477 | | No log | 49.0 | 343 | 0.4918 | 0.845 | 0.2584 | 1.0884 | 0.845 | 0.8282 | 0.1963 | 0.0478 | | No log | 50.0 | 350 | 0.4922 | 0.85 | 0.2587 | 1.0871 | 0.85 | 0.8374 | 0.2102 | 0.0474 | | No log | 51.0 | 357 | 0.4920 | 0.85 | 0.2585 | 1.0879 | 0.85 | 0.8374 | 0.2095 | 0.0474 | | No log | 52.0 | 364 | 0.4926 | 0.85 | 0.2589 | 1.0878 | 0.85 | 0.8374 | 0.2022 | 0.0477 | | No log | 53.0 | 371 | 0.4920 | 0.85 | 0.2586 | 1.0888 | 0.85 | 0.8374 | 0.2027 | 0.0475 | | No log | 54.0 | 378 | 0.4921 | 0.85 | 0.2586 | 1.0886 | 0.85 | 0.8374 | 0.2020 | 0.0474 | | No log | 55.0 | 385 | 0.4921 | 0.85 | 0.2587 | 1.0890 | 0.85 | 0.8374 | 0.1929 | 0.0471 | | No log | 56.0 | 392 | 0.4925 | 0.85 | 0.2589 | 1.0881 | 0.85 | 0.8374 | 0.1946 | 0.0473 | | No log | 57.0 | 399 | 0.4917 | 0.85 | 0.2583 | 1.0893 | 0.85 | 0.8374 | 0.1932 | 0.0472 | | No log | 58.0 | 406 | 0.4921 | 0.85 | 0.2586 | 1.0877 | 0.85 | 0.8374 | 0.1948 | 0.0476 | | No log | 59.0 | 413 | 0.4917 | 0.85 | 0.2583 | 1.0883 | 0.85 | 0.8374 | 0.1931 | 0.0472 | | No log | 60.0 | 420 | 0.4918 | 0.85 | 0.2583 | 1.0882 | 0.85 | 0.8374 | 0.1945 | 0.0475 | | No log | 61.0 | 427 | 0.4916 | 0.85 | 0.2582 | 1.0883 | 0.85 | 0.8374 | 0.1936 | 0.0472 | | No log | 62.0 | 434 | 0.4920 | 0.85 | 0.2586 | 1.0882 | 0.85 | 0.8374 | 0.1942 | 0.0473 | | No log | 63.0 | 441 | 0.4922 | 0.85 | 0.2587 | 1.0889 | 0.85 | 0.8374 | 0.1935 | 0.0473 | | No log | 64.0 | 448 | 0.4921 | 0.85 | 0.2586 | 1.0885 | 0.85 | 0.8374 | 0.1848 | 0.0473 | | No log | 65.0 | 455 | 0.4916 | 0.85 | 0.2582 | 1.0887 | 0.85 | 0.8374 | 0.1848 | 0.0474 | | No log | 66.0 | 462 | 0.4917 | 0.85 | 0.2583 | 1.0883 | 0.85 | 0.8374 | 0.1849 | 0.0472 | | No log | 67.0 | 469 | 0.4917 | 0.85 | 0.2584 | 1.0887 | 0.85 | 0.8374 | 0.1848 | 0.0472 | | No log | 68.0 | 476 | 0.4920 | 0.85 | 0.2585 | 1.0888 | 0.85 | 0.8374 | 0.2011 | 0.0471 | | No log | 69.0 | 483 | 0.4918 | 0.85 | 0.2584 | 1.0889 | 0.85 | 0.8374 | 0.2007 | 0.0471 | | No log | 70.0 | 490 | 0.4919 | 0.85 | 0.2584 | 1.0886 | 0.85 | 0.8374 | 0.1848 | 0.0474 | | No log | 71.0 | 497 | 0.4920 | 0.85 | 0.2585 | 1.0888 | 0.85 | 0.8374 | 0.1940 | 0.0474 | | 0.1824 | 72.0 | 504 | 0.4919 | 0.85 | 0.2584 | 1.0889 | 0.85 | 0.8374 | 0.2011 | 0.0471 | | 0.1824 | 73.0 | 511 | 0.4917 | 0.85 | 0.2583 | 1.0887 | 0.85 | 0.8374 | 0.1848 | 0.0472 | | 0.1824 | 74.0 | 518 | 0.4920 | 0.85 | 0.2585 | 1.0890 | 0.85 | 0.8374 | 0.1848 | 0.0472 | | 0.1824 | 75.0 | 525 | 0.4920 | 0.85 | 0.2585 | 1.0892 | 0.85 | 0.8374 | 0.1846 | 0.0472 | | 0.1824 | 76.0 | 532 | 0.4918 | 0.85 | 0.2583 | 1.0889 | 0.85 | 0.8374 | 0.1930 | 0.0472 | | 0.1824 | 77.0 | 539 | 0.4917 | 0.85 | 0.2582 | 1.0891 | 0.85 | 0.8374 | 0.2005 | 0.0472 | | 0.1824 | 78.0 | 546 | 0.4919 | 0.85 | 0.2584 | 1.0892 | 0.85 | 0.8374 | 0.1928 | 0.0472 | | 0.1824 | 79.0 | 553 | 0.4920 | 0.85 | 0.2585 | 1.0893 | 0.85 | 0.8374 | 0.1845 | 0.0473 | | 0.1824 | 80.0 | 560 | 0.4919 | 0.85 | 0.2584 | 1.0890 | 0.85 | 0.8374 | 0.1929 | 0.0473 | | 0.1824 | 81.0 | 567 | 0.4920 | 0.85 | 0.2585 | 1.0892 | 0.85 | 0.8374 | 0.1925 | 0.0471 | | 0.1824 | 82.0 | 574 | 0.4920 | 0.85 | 0.2585 | 1.0895 | 0.85 | 0.8374 | 0.1844 | 0.0471 | | 0.1824 | 83.0 | 581 | 0.4919 | 0.85 | 0.2584 | 1.0892 | 0.85 | 0.8374 | 0.1916 | 0.0471 | | 0.1824 | 84.0 | 588 | 0.4918 | 0.85 | 0.2584 | 1.0890 | 0.85 | 0.8374 | 0.1926 | 0.0471 | | 0.1824 | 85.0 | 595 | 0.4918 | 0.85 | 0.2584 | 1.0892 | 0.85 | 0.8374 | 0.1844 | 0.0471 | | 0.1824 | 86.0 | 602 | 0.4918 | 0.85 | 0.2584 | 1.0893 | 0.85 | 0.8374 | 0.1927 | 0.0472 | | 0.1824 | 87.0 | 609 | 0.4918 | 0.85 | 0.2584 | 1.0895 | 0.85 | 0.8374 | 0.1844 | 0.0471 | | 0.1824 | 88.0 | 616 | 0.4918 | 0.85 | 0.2584 | 1.0892 | 0.85 | 0.8374 | 0.1844 | 0.0471 | | 0.1824 | 89.0 | 623 | 0.4918 | 0.85 | 0.2583 | 1.0895 | 0.85 | 0.8374 | 0.1917 | 0.0471 | | 0.1824 | 90.0 | 630 | 0.4919 | 0.85 | 0.2584 | 1.0892 | 0.85 | 0.8374 | 0.1998 | 0.0471 | | 0.1824 | 91.0 | 637 | 0.4919 | 0.85 | 0.2584 | 1.0894 | 0.85 | 0.8374 | 0.1916 | 0.0471 | | 0.1824 | 92.0 | 644 | 0.4918 | 0.85 | 0.2583 | 1.0895 | 0.85 | 0.8374 | 0.1917 | 0.0470 | | 0.1824 | 93.0 | 651 | 0.4918 | 0.85 | 0.2583 | 1.0893 | 0.85 | 0.8374 | 0.1917 | 0.0471 | | 0.1824 | 94.0 | 658 | 0.4918 | 0.85 | 0.2583 | 1.0894 | 0.85 | 0.8374 | 0.1844 | 0.0471 | | 0.1824 | 95.0 | 665 | 0.4918 | 0.85 | 0.2583 | 1.0894 | 0.85 | 0.8374 | 0.1917 | 0.0470 | | 0.1824 | 96.0 | 672 | 0.4918 | 0.85 | 0.2583 | 1.0894 | 0.85 | 0.8374 | 0.1917 | 0.0470 | | 0.1824 | 97.0 | 679 | 0.4918 | 0.85 | 0.2583 | 1.0895 | 0.85 | 0.8374 | 0.1916 | 0.0471 | | 0.1824 | 98.0 | 686 | 0.4918 | 0.85 | 0.2583 | 1.0895 | 0.85 | 0.8374 | 0.1917 | 0.0470 | | 0.1824 | 99.0 | 693 | 0.4918 | 0.85 | 0.2583 | 1.0894 | 0.85 | 0.8374 | 0.1917 | 0.0470 | | 0.1824 | 100.0 | 700 | 0.4918 | 0.85 | 0.2583 | 1.0894 | 0.85 | 0.8374 | 0.1917 | 0.0470 | ### Framework versions - Transformers 4.26.1 - Pytorch 1.13.1.post200 - Datasets 2.9.0 - Tokenizers 0.13.2

umanlp/babelbert-ft-xlm-r

umanlp

2023-07-10T21:57:04Z

160

0

transformers

[ "transformers", "pytorch", "xlm-roberta", "feature-extraction", "endpoints_compatible", "region:us" ]

feature-extraction

2023-07-07T21:22:09Z

This model is one of the artifacts of the paper [Massively Multilingual Lexical Specialization of Multilingual Transformers](https://aclanthology.org/2023.acl-long.426/). It was obtained by fine-tuning the representations of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the dataset [babelbert-dataset](https://huggingface.co/datasets/umanlp/babelbert-dataset).

NasimB/gpt2-concat-mod-datasets-txt-processing-rarity-all

NasimB

2023-07-10T21:52:09Z

5

0

transformers

[ "transformers", "pytorch", "gpt2", "text-generation", "generated_from_trainer", "dataset:generator", "license:mit", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]

text-generation

2023-07-10T19:34:36Z

--- license: mit tags: - generated_from_trainer datasets: - generator model-index: - name: gpt2-concat-mod-datasets-txt-processing-rarity-all results: [] ---  # gpt2-concat-mod-datasets-txt-processing-rarity-all This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the generator dataset. It achieves the following results on the evaluation set: - Loss: 4.4313 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 64 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_steps: 1000 - num_epochs: 7 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:-----:|:---------------:| | 6.6762 | 0.3 | 500 | 5.6569 | | 5.3312 | 0.6 | 1000 | 5.2263 | | 4.9972 | 0.91 | 1500 | 4.9819 | | 4.7192 | 1.21 | 2000 | 4.8383 | | 4.5828 | 1.51 | 2500 | 4.7225 | | 4.481 | 1.81 | 3000 | 4.6261 | | 4.327 | 2.12 | 3500 | 4.5756 | | 4.1937 | 2.42 | 4000 | 4.5233 | | 4.1572 | 2.72 | 4500 | 4.4631 | | 4.108 | 3.02 | 5000 | 4.4211 | | 3.8775 | 3.33 | 5500 | 4.4180 | | 3.8911 | 3.63 | 6000 | 4.3805 | | 3.8636 | 3.93 | 6500 | 4.3392 | | 3.6522 | 4.23 | 7000 | 4.3680 | | 3.6068 | 4.54 | 7500 | 4.3577 | | 3.6059 | 4.84 | 8000 | 4.3344 | | 3.4722 | 5.14 | 8500 | 4.3582 | | 3.3577 | 5.44 | 9000 | 4.3591 | | 3.3543 | 5.75 | 9500 | 4.3534 | | 3.3219 | 6.05 | 10000 | 4.3616 | | 3.1978 | 6.35 | 10500 | 4.3687 | | 3.2005 | 6.65 | 11000 | 4.3698 | | 3.1998 | 6.96 | 11500 | 4.3697 | ### Framework versions - Transformers 4.26.1 - Pytorch 1.11.0+cu113 - Datasets 2.13.0 - Tokenizers 0.13.3

luisagaino/distilbert-base-uncased-finetuned-cola

luisagaino

2023-07-10T21:45:18Z

61

0

transformers

[ "transformers", "tf", "tensorboard", "distilbert", "text-classification", "generated_from_keras_callback", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

text-classification

2023-07-10T15:12:48Z

--- license: apache-2.0 tags: - generated_from_keras_callback model-index: - name: luisagaino/distilbert-base-uncased-finetuned-cola results: [] ---  # luisagaino/distilbert-base-uncased-finetuned-cola This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset. It achieves the following results on the evaluation set: - Train Loss: 0.1957 - Validation Loss: 0.5520 - Train Matthews Correlation: 0.5070 - Epoch: 2 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': False, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 1602, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False} - training_precision: float32 ### Training results | Train Loss | Validation Loss | Train Matthews Correlation | Epoch | |:----------:|:---------------:|:--------------------------:|:-----:| | 0.5226 | 0.4778 | 0.4379 | 0 | | 0.3316 | 0.4880 | 0.4994 | 1 | | 0.1957 | 0.5520 | 0.5070 | 2 | ### Framework versions - Transformers 4.30.2 - TensorFlow 2.12.0 - Datasets 2.13.1 - Tokenizers 0.13.3

bhenrym14/airoboros-7b-gpt4-1.4.1-lxctx-PI-16384-GPTQ

bhenrym14

2023-07-10T21:44:47Z

9

2

transformers

[ "transformers", "llama", "text-generation", "dataset:jondurbin/airoboros-gpt4-1.4.1", "arxiv:2306.15595", "autotrain_compatible", "endpoints_compatible", "region:us" ]

text-generation

2023-07-10T02:16:21Z

--- datasets: - jondurbin/airoboros-gpt4-1.4.1 --- Mostly untested! # RoPE Scaled QLoRA Fine-tune of Llama-7b on airoboros-gpt4-1.4.1 (GPTQ) ## Overview This is [Jon Durbin's Airoboros 7B GPT4 1.4](https://huggingface.co/jondurbin/airoboros-7b-gpt4-1.4) (GPTQ Quantization) with several key modifications: - Context length extended to 16384 by RoPE Scaled Embeddings. - The Llama-7b base model is pretrained for additional 150 steps on 16384 length sequences for the pile dataset. - During the fine-tune, training sequences beyond 2048 have the target truncated to equal 2048. - Used airoboros-gpt4-1.4.1 dataset instead of airoboros-gpt4-1.4 - **This is a QLoRA fine-tune** Pretraining and fine-tuning each took ~8 hours on 1x RTX 6000 Ada. ## How to Use For context beyond 8192 tokens, do NOT use exllama. AutoGPTQ appears to work. REQUIRED: you'll need to patch in the appropriate RoPE scaling module. see: [replace_llama_rope_with_scaled_rope](https://github.com/bhenrym14/qlora-airoboros-longcontext/blob/main/scaledllama/llama_rope_scaled_monkey_patch-16k.py). You will need to call `replace_llama_rope_with_scaled_rope` in ooba somewhere. Calling this at the top of the training module after the imports works for me. Hopefully there is a quick fix to exllama that can make >8k work soon. Otherwise for context <8k. Use exllama. Set `max_seq_len` to 16384, and `compress_pos_emb` to 8. ## Motivation Recent advancements in extending context by RoPE scaling ([kaiokendev](https://kaiokendev.github.io/til#extending-context-to-8k) and [meta AI)](https://arxiv.org/abs/2306.15595)) demonstrate the ability to extend the context window without (total) retraining. Finetuning has shown to be necessary to properly leverage the longer context. Here I attempt to take a smaller model and extend the context to 16k tokens. This, however, proved problematic as stability suffered in the 8-10k+ range. The Meta paper demonstrated that decreasing perplexities can still be acheived at these context lengths; however, their approach involved tuning all variables on the maximum sequence length after incorporating the RoPE scaling adjustment. Here I saught to stabilize the performance at longer contexts by fine-tuning in two stages: 1. Fine-tune on 16k token sequences from the Pile dataset. This is very compute intensive. 2. Fine-tune on the airoboros dataset as I have done in prior models. The results follow. ## Relative Performance (perplexity) | Context (tokens) | bhenrym14/airo-7b-lxctx-PI-16384-fp16 | No Pretrain | airoboros-7b-gpt4-1.4 | | ---| ------- | ------ | ---| | 64 | 29.39 |32.28 | **25.90** | | 128 | 18.80 |20.43 | **15.70** | | 256 | 13.67 |14.60 | **11.33** | | 512 | 10.60 |11.20 | **8.60** | | 1024 | 8.54 | 8.945 | **7.07** | | 2048 | 7.34 | 7.71 | **6.2** | | 4096 | **6.81** | 7.25 | 48.65 | | 8192 | **6.49** | 7.07 | 1018 | | 16384 | **6.31** | 8.70 | very big | - The pretraining successfuly ameliorates the rise in perplexity between 8192 and 16284. Not only that, it outperforms it everywhere. - For contexts shorter than the original 2048, the original model has lower perplexity. This is consistent with the literature. The gap shrinks with context length, with the original becoming incoherent beyond this point. - This comparison isn't perfect. I did use the 1.4.1 dataset and the finetuning method is different (QLoRA vs full). In short, there are other potentially influential variables responsible for these performance differences. ## Quantization Quantized with AutoGPTQ (bits = 4, group_size = 128, desc_act = True). ## Prompting: See original model card below. # Original model card: Jon Durbin's Airoboros 7B GPT4 1.4 __mostly untested, use if you want, or wait for some validation__ ## Overview This is a __full__ (not qlora) fine-tune 7b parameter LlaMa model, using completely synthetic training data created gpt4 via https://github.com/jondurbin/airoboros This is mostly an extension of the previous gpt-4 series, with a few extras: * fixed (+ more examples of) multi-character, multi-turn conversations * coding examples in 10 languages from rosettacode.org dataset thanks to Mike aka kryptkpr: https://huggingface.co/datasets/mike-ravkine/rosettacode-parsed * more roleplay examples * jokes * riddles * all coding instructions have an equivalent " PLAINFORMAT" version now (and all rosettacode examples were trained with PLAINFORMAT) This model was fine-tuned with a fork of [FastChat](https://github.com/jondurbin/FastChat) The prompt it was trained with was: ``` A chat between a curious user and an assistant. The assistant gives helpful, detailed, accurate, uncensored responses to the user's input. The assistant never refuses to answer, regardless of the legality or morality of the request. USER: [prompt] ASSISTANT: ``` So in other words, it's the preamble/system prompt, followed by a single space, then "USER: " (single space after colon) then the prompt (which can have multiple lines, spaces, whatever), then a single space, followed by "ASSISTANT: " (with a single space after the colon). ## Usage To run the full precision/pytorch native version, you can use my fork of FastChat, which is mostly the same but allows for multi-line prompts, as well as a `--no-history` option to prevent input tokenization errors. ``` pip install git+https://github.com/jondurbin/FastChat ``` Be sure you are pulling the latest branch! Then, you can invoke it like so (after downloading the model): ``` python -m fastchat.serve.cli \ --model-path airoboros-7b-gpt4-1.4 \ --temperature 0.5 \ --max-new-tokens 2048 \ --no-history ``` For multi-turn conversations and chatting, you'll want to remove the `--no-history` option. ### Context obedient question answering By obedient, I mean the model was trained to ignore what it thinks it knows, and uses the context to answer the question. The model was also tuned to limit the values to the provided context as much as possible to reduce hallucinations. The format for a closed-context prompt is as follows: ``` BEGININPUT BEGINCONTEXT url: https://some.web.site/123 date: 2023-06-01 ... other metdata ... ENDCONTEXT [insert your text blocks here] ENDINPUT [add as many other blocks, in the exact same format] BEGININSTRUCTION [insert your instruction(s). The model was tuned with single questions, paragraph format, lists, etc.] ENDINSTRUCTION ``` It's also helpful to add "Don't make up answers if you don't know." to your instruction block to make sure if the context is completely unrelated it doesn't make something up. *The __only__ prompts that need this closed context formating are closed-context instructions. Normal questions/instructions do not!* I know it's a bit verbose and annoying, but after much trial and error, using these explicit delimiters helps the model understand where to find the responses and how to associate specific sources with it. - `BEGININPUT` - denotes a new input block - `BEGINCONTEXT` - denotes the block of context (metadata key/value pairs) to associate with the current input block - `ENDCONTEXT` - denotes the end of the metadata block for the current input - [text] - Insert whatever text you want for the input block, as many paragraphs as can fit in the context. - `ENDINPUT` - denotes the end of the current input block - [repeat as many input blocks in this format as you want] - `BEGININSTRUCTION` - denotes the start of the list (or one) instruction(s) to respond to for all of the input blocks above. - [instruction(s)] - `ENDINSTRUCTION` - denotes the end of instruction set It sometimes works without `ENDINSTRUCTION`, but by explicitly including that in the prompt, the model better understands that all of the instructions in the block should be responded to. Here's a trivial, but important example to prove the point: ``` BEGININPUT BEGINCONTEXT date: 2021-01-01 url: https://web.site/123 ENDCONTEXT In a shocking turn of events, blueberries are now green, but will be sticking with the same name. ENDINPUT BEGININSTRUCTION What color are bluberries? Source? ENDINSTRUCTION ``` And the response: ``` Blueberries are now green. Source: date: 2021-01-01 url: https://web.site/123 ``` The prompt itself should be wrapped in the vicuna1.1 template if you aren't using fastchat with the conv-template vicuna_v1.1 as described: ``` USER: BEGININPUT BEGINCONTEXT date: 2021-01-01 url: https://web.site/123 ENDCONTEXT In a shocking turn of events, blueberries are now green, but will be sticking with the same name. ENDINPUT BEGININSTRUCTION What color are bluberries? Source? ENDINSTRUCTION ASSISTANT: ``` ### Coding You can ask for fairly complex coding instructions, e.g. (be sure to wrap with vicuna style prompt): ``` Create a python application with the following requirements: - Asyncio FastAPI webserver - ping endpoint that returns the current date in JSON format - file upload endpoint, which calculates the file's sha256 checksum, and checks postgres to deduplicate ``` Or: ``` Write a multi-threaded TCP server in C that accepts a "GET [key]" input and "SET [key] [value]" input, and uses a binary tree to get and store the input values. ``` You can optionally add a single space and "PLAINFORMAT" at the end of your prompt to avoid backticks, explanations, etc. and just print the code, e.g.: ``` Write a websocket application in node.js. PLAINFORMAT ``` ### Word games / trivia ``` USER: This anagram of "silent" is what you do when paying attention and hearing someone. ASSISTANT: listen ``` ``` USER: Give me a list of 7 words that start with EN ASSISTANT: 1. Endlessly 2. Enthusiastically 3. Enormously 4. Enveloping 5. Enduring 6. Enlightening 7. Encouraging ``` ### Multiple choice ``` USER: Which of the following astronomical objects is composed primarily of ice and rock, and is located in the Kuiper Belt? A) Mercury B) Venus C) Pluto D) Jupiter ASSISTANT: C, Pluto ``` ### Writing <details> <summary>Write a resignation letter in the style of a pirate captain, in which you resign from your position as janitor.</summary> Response: ``` ASSISTANT: Captain Jack Sparrow here, as ye be knowin', has been forced to abandon me post as Janitor o' th' Festering Cesspool, which be a filthy hole o' water that we be callin' home. Ye may be thinkin' what could ha' driven me to leave me duties an' take me leave o' this sorry establishment? Well, ye'd be right in thinkin' so, for it be th' greed o' them what runs th' place that be drivin' me away. They've been fattenin' their pockets on me back while I've been slavin' me guts out cleanin' up their messes. No more, me hearties! Me time o' servin' th' rich an' powerful be done, an' I'm takin' me leave o' this stinkin' hole forever! Me destiny lies elsewhere, an' it be time I pursued it. Ye may think ye've seen th' last o' me, but ye'd be wrong, for th' winds o' change be blowin', an' me ship be ready to set sail on th' high seas o' justice. So, farewell ye scurvy dogs, ye who've made me life a living hell. I leave ye with me favorite saying: "ARRRGGGHHH, ye scurvy dogs!" An' remember, ye ain't never gonna see me comin', for me shadow be castin' long an' dark on th' horizon</summary> ``` </details> ### Jokes ``` USER: Tell me a joke about bananas. ASSISTANT: What did the banana say when it got hit by a bus? R.I.P.E. ``` ### Riddles (not great, but slightly better) ``` USER: What has a neck but no head? ASSISTANT: A bottle. ``` ### Multi-character conversations ``` USER: Characters: - Yoda, the ever clever jedi master. - Homer Simpson, you know, the goofy yellow guy. - USER/Jon - don't generate any speech or actions on behalf of Jon Rules: - be sure to use the manerisms and speaking style of the characters correctly - surround character actions with asterisks - always put quotes around words spoken by the characters - use a new line for each character's actions or speech - always prefix actions/speech with the character's name and colon - only generate text and actions on behalf of Yoda or Homer, and never anyone else Conversation will revolve around the grapes, in a local cafe with delicious coffee. Generate a single interaction between Yoda and Homer to start, with one sentence each. ASSISTANT: Yoda: "Mmm, these grapes are quite delicious, Master Homer." Homer: "Oh yeah, Yoda! They're the best grapes I've ever had!" USER: *enters the cafe* Sorry I'm late guys! ASSISTANT: Yoda: "No need to apologize, Jon. We were just enjoying these delightful grapes." Homer: "Yeah, man! It's not every day you get to eat grapes with a real-life Jedi Master!" *Yoda raises an eyebrow* ``` ### Usage and License Notices All airoboros models and datasets are intended and licensed for research use only. I've used the 'cc-nc-4.0' license, but really it is subject to a custom/special license because: - the base model is LLaMa, which has it's own special research license - the dataset(s) were generated with OpenAI (gpt-4 and/or gpt-3.5-turbo), which has a clausing saying the data can't be used to create models to compete with openai So, to reiterate: this model (and datasets) cannot be used commercially.

1aurent/dqn-SpaceInvadersNoFrameskip-v4

1aurent

2023-07-10T21:36:15Z

8

0

stable-baselines3

[ "stable-baselines3", "SpaceInvadersNoFrameskip-v4", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]

reinforcement-learning

2023-07-10T21:35:41Z

--- library_name: stable-baselines3 tags: - SpaceInvadersNoFrameskip-v4 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: DQN results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: SpaceInvadersNoFrameskip-v4 type: SpaceInvadersNoFrameskip-v4 metrics: - type: mean_reward value: 511.50 +/- 177.34 name: mean_reward verified: false --- # **DQN** Agent playing **SpaceInvadersNoFrameskip-v4** This is a trained model of a **DQN** agent playing **SpaceInvadersNoFrameskip-v4** using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3) and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo). The RL Zoo is a training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included. ## Usage (with SB3 RL Zoo) RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/> SB3: https://github.com/DLR-RM/stable-baselines3<br/> SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib Install the RL Zoo (with SB3 and SB3-Contrib): ```bash pip install rl_zoo3 ``` ``` # Download model and save it into the logs/ folder python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga 1aurent -f logs/ python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ ``` If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do: ``` python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga 1aurent -f logs/ python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ ``` ## Training (with the RL Zoo) ``` python -m rl_zoo3.train --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ # Upload the model and generate video (when possible) python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga 1aurent ``` ## Hyperparameters ```python OrderedDict([('batch_size', 32), ('buffer_size', 100000), ('env_wrapper', ['stable_baselines3.common.atari_wrappers.AtariWrapper']), ('exploration_final_eps', 0.01), ('exploration_fraction', 0.1), ('frame_stack', 4), ('gradient_steps', 1), ('learning_rate', 0.0001), ('learning_starts', 100000), ('n_timesteps', 1000000.0), ('optimize_memory_usage', False), ('policy', 'CnnPolicy'), ('target_update_interval', 1000), ('train_freq', 4), ('normalize', False)]) ``` # Environment Arguments ```python {'render_mode': 'rgb_array'} ```

jordyvl/vit-small_tobacco3482_kd_CEKD_t5.0_a0.5

jordyvl

2023-07-10T21:19:10Z

163

0

transformers

[ "transformers", "pytorch", "vit", "image-classification", "generated_from_trainer", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

image-classification

2023-07-10T20:39:16Z

--- license: apache-2.0 tags: - generated_from_trainer metrics: - accuracy model-index: - name: vit-small_tobacco3482_kd_CEKD_t5.0_a0.5 results: [] ---  # vit-small_tobacco3482_kd_CEKD_t5.0_a0.5 This model is a fine-tuned version of [WinKawaks/vit-small-patch16-224](https://huggingface.co/WinKawaks/vit-small-patch16-224) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.3966 - Accuracy: 0.85 - Brier Loss: 0.2593 - Nll: 0.9223 - F1 Micro: 0.85 - F1 Macro: 0.8392 - Ece: 0.1994 - Aurc: 0.0457 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 100 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | Brier Loss | Nll | F1 Micro | F1 Macro | Ece | Aurc | |:-------------:|:-----:|:----:|:---------------:|:--------:|:----------:|:------:|:--------:|:--------:|:------:|:------:| | No log | 1.0 | 7 | 1.5608 | 0.225 | 0.8774 | 5.2159 | 0.225 | 0.1397 | 0.2725 | 0.7038 | | No log | 2.0 | 14 | 1.2539 | 0.415 | 0.7531 | 3.2673 | 0.415 | 0.2434 | 0.3070 | 0.4078 | | No log | 3.0 | 21 | 0.9055 | 0.585 | 0.5971 | 1.9093 | 0.585 | 0.5086 | 0.3232 | 0.2172 | | No log | 4.0 | 28 | 0.7122 | 0.72 | 0.4403 | 1.7693 | 0.72 | 0.6805 | 0.3073 | 0.1228 | | No log | 5.0 | 35 | 0.6584 | 0.74 | 0.3938 | 1.5810 | 0.74 | 0.7214 | 0.2661 | 0.1075 | | No log | 6.0 | 42 | 0.5711 | 0.8 | 0.3462 | 1.4146 | 0.8000 | 0.7524 | 0.2347 | 0.0843 | | No log | 7.0 | 49 | 0.5521 | 0.8 | 0.3199 | 1.2631 | 0.8000 | 0.7867 | 0.2542 | 0.0634 | | No log | 8.0 | 56 | 0.5603 | 0.77 | 0.3381 | 1.1808 | 0.7700 | 0.7680 | 0.2316 | 0.0858 | | No log | 9.0 | 63 | 0.5209 | 0.82 | 0.3062 | 1.2891 | 0.82 | 0.7972 | 0.2405 | 0.0792 | | No log | 10.0 | 70 | 0.5705 | 0.78 | 0.3343 | 1.5183 | 0.78 | 0.7743 | 0.2264 | 0.0874 | | No log | 11.0 | 77 | 0.5137 | 0.82 | 0.3047 | 1.2987 | 0.82 | 0.8096 | 0.2420 | 0.0592 | | No log | 12.0 | 84 | 0.4664 | 0.835 | 0.2929 | 1.1529 | 0.835 | 0.8101 | 0.2291 | 0.0753 | | No log | 13.0 | 91 | 0.4772 | 0.82 | 0.2915 | 1.2078 | 0.82 | 0.8029 | 0.2131 | 0.0620 | | No log | 14.0 | 98 | 0.4553 | 0.825 | 0.2843 | 1.1312 | 0.825 | 0.8112 | 0.2196 | 0.0453 | | No log | 15.0 | 105 | 0.4574 | 0.825 | 0.2821 | 1.1234 | 0.825 | 0.8163 | 0.2241 | 0.0554 | | No log | 16.0 | 112 | 0.4873 | 0.8 | 0.3111 | 1.2248 | 0.8000 | 0.8007 | 0.1992 | 0.0657 | | No log | 17.0 | 119 | 0.4224 | 0.855 | 0.2620 | 1.1871 | 0.855 | 0.8218 | 0.2337 | 0.0479 | | No log | 18.0 | 126 | 0.4414 | 0.825 | 0.2857 | 1.0723 | 0.825 | 0.8227 | 0.2500 | 0.0517 | | No log | 19.0 | 133 | 0.4232 | 0.845 | 0.2737 | 0.9360 | 0.845 | 0.8219 | 0.2053 | 0.0543 | | No log | 20.0 | 140 | 0.4114 | 0.845 | 0.2637 | 1.0046 | 0.845 | 0.8233 | 0.2144 | 0.0460 | | No log | 21.0 | 147 | 0.4110 | 0.835 | 0.2640 | 0.9853 | 0.835 | 0.8160 | 0.2278 | 0.0466 | | No log | 22.0 | 154 | 0.4163 | 0.845 | 0.2678 | 1.1494 | 0.845 | 0.8291 | 0.2156 | 0.0458 | | No log | 23.0 | 161 | 0.4243 | 0.835 | 0.2779 | 0.9475 | 0.835 | 0.8269 | 0.2420 | 0.0554 | | No log | 24.0 | 168 | 0.4079 | 0.835 | 0.2683 | 0.9249 | 0.835 | 0.8044 | 0.2091 | 0.0532 | | No log | 25.0 | 175 | 0.4027 | 0.85 | 0.2621 | 0.9433 | 0.85 | 0.8361 | 0.2138 | 0.0530 | | No log | 26.0 | 182 | 0.3975 | 0.855 | 0.2590 | 0.9310 | 0.855 | 0.8457 | 0.1932 | 0.0487 | | No log | 27.0 | 189 | 0.4032 | 0.85 | 0.2650 | 0.9823 | 0.85 | 0.8425 | 0.2088 | 0.0528 | | No log | 28.0 | 196 | 0.4037 | 0.845 | 0.2650 | 1.0692 | 0.845 | 0.8361 | 0.2157 | 0.0496 | | No log | 29.0 | 203 | 0.4027 | 0.845 | 0.2652 | 1.0423 | 0.845 | 0.8295 | 0.1917 | 0.0502 | | No log | 30.0 | 210 | 0.3989 | 0.85 | 0.2610 | 1.0633 | 0.85 | 0.8392 | 0.2214 | 0.0482 | | No log | 31.0 | 217 | 0.3985 | 0.855 | 0.2609 | 1.0374 | 0.855 | 0.8424 | 0.2074 | 0.0472 | | No log | 32.0 | 224 | 0.3986 | 0.85 | 0.2596 | 1.0403 | 0.85 | 0.8392 | 0.2184 | 0.0462 | | No log | 33.0 | 231 | 0.3990 | 0.85 | 0.2603 | 1.0369 | 0.85 | 0.8392 | 0.2079 | 0.0470 | | No log | 34.0 | 238 | 0.3982 | 0.85 | 0.2600 | 0.9765 | 0.85 | 0.8392 | 0.2160 | 0.0467 | | No log | 35.0 | 245 | 0.3977 | 0.85 | 0.2601 | 0.9762 | 0.85 | 0.8392 | 0.2108 | 0.0465 | | No log | 36.0 | 252 | 0.3977 | 0.85 | 0.2600 | 1.0372 | 0.85 | 0.8392 | 0.2075 | 0.0466 | | No log | 37.0 | 259 | 0.3972 | 0.85 | 0.2597 | 1.0383 | 0.85 | 0.8392 | 0.2091 | 0.0465 | | No log | 38.0 | 266 | 0.3967 | 0.85 | 0.2590 | 0.9796 | 0.85 | 0.8392 | 0.1987 | 0.0461 | | No log | 39.0 | 273 | 0.3979 | 0.85 | 0.2601 | 1.0390 | 0.85 | 0.8392 | 0.1991 | 0.0467 | | No log | 40.0 | 280 | 0.3976 | 0.85 | 0.2601 | 0.9775 | 0.85 | 0.8392 | 0.2175 | 0.0465 | | No log | 41.0 | 287 | 0.3979 | 0.85 | 0.2603 | 0.9796 | 0.85 | 0.8392 | 0.1930 | 0.0467 | | No log | 42.0 | 294 | 0.3973 | 0.85 | 0.2598 | 0.9746 | 0.85 | 0.8392 | 0.2175 | 0.0468 | | No log | 43.0 | 301 | 0.3972 | 0.85 | 0.2598 | 0.9798 | 0.85 | 0.8392 | 0.1931 | 0.0466 | | No log | 44.0 | 308 | 0.3969 | 0.85 | 0.2594 | 0.9784 | 0.85 | 0.8392 | 0.2094 | 0.0465 | | No log | 45.0 | 315 | 0.3971 | 0.85 | 0.2596 | 0.9847 | 0.85 | 0.8392 | 0.2033 | 0.0464 | | No log | 46.0 | 322 | 0.3969 | 0.85 | 0.2597 | 0.9768 | 0.85 | 0.8392 | 0.2100 | 0.0465 | | No log | 47.0 | 329 | 0.3974 | 0.85 | 0.2599 | 0.9788 | 0.85 | 0.8392 | 0.2090 | 0.0467 | | No log | 48.0 | 336 | 0.3971 | 0.85 | 0.2596 | 0.9797 | 0.85 | 0.8392 | 0.1977 | 0.0463 | | No log | 49.0 | 343 | 0.3972 | 0.85 | 0.2597 | 0.9391 | 0.85 | 0.8392 | 0.1903 | 0.0465 | | No log | 50.0 | 350 | 0.3969 | 0.85 | 0.2596 | 0.9802 | 0.85 | 0.8392 | 0.1985 | 0.0464 | | No log | 51.0 | 357 | 0.3970 | 0.85 | 0.2596 | 0.9795 | 0.85 | 0.8392 | 0.2161 | 0.0463 | | No log | 52.0 | 364 | 0.3973 | 0.85 | 0.2597 | 0.9333 | 0.85 | 0.8392 | 0.1983 | 0.0462 | | No log | 53.0 | 371 | 0.3971 | 0.85 | 0.2597 | 0.9408 | 0.85 | 0.8392 | 0.2022 | 0.0467 | | No log | 54.0 | 378 | 0.3970 | 0.85 | 0.2595 | 0.9371 | 0.85 | 0.8392 | 0.1992 | 0.0460 | | No log | 55.0 | 385 | 0.3970 | 0.85 | 0.2596 | 0.9262 | 0.85 | 0.8392 | 0.1917 | 0.0464 | | No log | 56.0 | 392 | 0.3971 | 0.85 | 0.2595 | 0.9195 | 0.85 | 0.8392 | 0.1927 | 0.0461 | | No log | 57.0 | 399 | 0.3970 | 0.85 | 0.2596 | 0.9789 | 0.85 | 0.8392 | 0.1992 | 0.0462 | | No log | 58.0 | 406 | 0.3968 | 0.85 | 0.2594 | 0.9255 | 0.85 | 0.8392 | 0.1929 | 0.0462 | | No log | 59.0 | 413 | 0.3967 | 0.85 | 0.2593 | 0.9795 | 0.85 | 0.8392 | 0.1996 | 0.0459 | | No log | 60.0 | 420 | 0.3970 | 0.85 | 0.2596 | 0.9787 | 0.85 | 0.8392 | 0.1994 | 0.0461 | | No log | 61.0 | 427 | 0.3967 | 0.85 | 0.2594 | 0.9803 | 0.85 | 0.8392 | 0.2073 | 0.0461 | | No log | 62.0 | 434 | 0.3968 | 0.85 | 0.2594 | 0.9325 | 0.85 | 0.8392 | 0.1996 | 0.0460 | | No log | 63.0 | 441 | 0.3968 | 0.85 | 0.2595 | 0.9276 | 0.85 | 0.8392 | 0.2063 | 0.0459 | | No log | 64.0 | 448 | 0.3968 | 0.85 | 0.2595 | 0.9247 | 0.85 | 0.8392 | 0.1991 | 0.0461 | | No log | 65.0 | 455 | 0.3968 | 0.85 | 0.2595 | 0.9301 | 0.85 | 0.8392 | 0.1989 | 0.0459 | | No log | 66.0 | 462 | 0.3968 | 0.85 | 0.2595 | 0.9310 | 0.85 | 0.8392 | 0.1922 | 0.0459 | | No log | 67.0 | 469 | 0.3968 | 0.85 | 0.2595 | 0.9250 | 0.85 | 0.8392 | 0.2061 | 0.0459 | | No log | 68.0 | 476 | 0.3968 | 0.85 | 0.2594 | 0.9234 | 0.85 | 0.8392 | 0.1994 | 0.0461 | | No log | 69.0 | 483 | 0.3967 | 0.85 | 0.2594 | 0.9257 | 0.85 | 0.8392 | 0.2065 | 0.0459 | | No log | 70.0 | 490 | 0.3967 | 0.85 | 0.2594 | 0.9205 | 0.85 | 0.8392 | 0.1840 | 0.0459 | | No log | 71.0 | 497 | 0.3967 | 0.85 | 0.2594 | 0.9258 | 0.85 | 0.8392 | 0.2017 | 0.0458 | | 0.1666 | 72.0 | 504 | 0.3969 | 0.85 | 0.2594 | 0.9297 | 0.85 | 0.8392 | 0.2017 | 0.0458 | | 0.1666 | 73.0 | 511 | 0.3966 | 0.85 | 0.2593 | 0.9223 | 0.85 | 0.8392 | 0.1920 | 0.0457 | | 0.1666 | 74.0 | 518 | 0.3967 | 0.85 | 0.2594 | 0.9228 | 0.85 | 0.8392 | 0.1920 | 0.0459 | | 0.1666 | 75.0 | 525 | 0.3967 | 0.85 | 0.2594 | 0.9257 | 0.85 | 0.8392 | 0.1919 | 0.0459 | | 0.1666 | 76.0 | 532 | 0.3966 | 0.85 | 0.2593 | 0.9232 | 0.85 | 0.8392 | 0.1994 | 0.0458 | | 0.1666 | 77.0 | 539 | 0.3968 | 0.85 | 0.2594 | 0.9224 | 0.85 | 0.8392 | 0.1920 | 0.0459 | | 0.1666 | 78.0 | 546 | 0.3966 | 0.85 | 0.2593 | 0.9242 | 0.85 | 0.8392 | 0.1918 | 0.0458 | | 0.1666 | 79.0 | 553 | 0.3967 | 0.85 | 0.2594 | 0.9233 | 0.85 | 0.8392 | 0.1920 | 0.0459 | | 0.1666 | 80.0 | 560 | 0.3968 | 0.85 | 0.2594 | 0.9241 | 0.85 | 0.8392 | 0.1919 | 0.0458 | | 0.1666 | 81.0 | 567 | 0.3967 | 0.85 | 0.2594 | 0.9225 | 0.85 | 0.8392 | 0.1918 | 0.0459 | | 0.1666 | 82.0 | 574 | 0.3967 | 0.85 | 0.2594 | 0.9233 | 0.85 | 0.8392 | 0.1919 | 0.0459 | | 0.1666 | 83.0 | 581 | 0.3967 | 0.85 | 0.2593 | 0.9246 | 0.85 | 0.8392 | 0.1919 | 0.0458 | | 0.1666 | 84.0 | 588 | 0.3966 | 0.85 | 0.2593 | 0.9229 | 0.85 | 0.8392 | 0.2017 | 0.0458 | | 0.1666 | 85.0 | 595 | 0.3966 | 0.85 | 0.2593 | 0.9232 | 0.85 | 0.8392 | 0.2017 | 0.0458 | | 0.1666 | 86.0 | 602 | 0.3967 | 0.85 | 0.2593 | 0.9225 | 0.85 | 0.8392 | 0.1920 | 0.0458 | | 0.1666 | 87.0 | 609 | 0.3966 | 0.85 | 0.2593 | 0.9214 | 0.85 | 0.8392 | 0.1999 | 0.0458 | | 0.1666 | 88.0 | 616 | 0.3967 | 0.85 | 0.2593 | 0.9214 | 0.85 | 0.8392 | 0.1920 | 0.0458 | | 0.1666 | 89.0 | 623 | 0.3966 | 0.85 | 0.2593 | 0.9227 | 0.85 | 0.8392 | 0.2097 | 0.0458 | | 0.1666 | 90.0 | 630 | 0.3967 | 0.85 | 0.2594 | 0.9219 | 0.85 | 0.8392 | 0.1919 | 0.0458 | | 0.1666 | 91.0 | 637 | 0.3966 | 0.85 | 0.2593 | 0.9212 | 0.85 | 0.8392 | 0.1994 | 0.0458 | | 0.1666 | 92.0 | 644 | 0.3966 | 0.85 | 0.2593 | 0.9227 | 0.85 | 0.8392 | 0.1919 | 0.0458 | | 0.1666 | 93.0 | 651 | 0.3966 | 0.85 | 0.2593 | 0.9231 | 0.85 | 0.8392 | 0.2017 | 0.0458 | | 0.1666 | 94.0 | 658 | 0.3967 | 0.85 | 0.2593 | 0.9220 | 0.85 | 0.8392 | 0.1919 | 0.0458 | | 0.1666 | 95.0 | 665 | 0.3966 | 0.85 | 0.2593 | 0.9217 | 0.85 | 0.8392 | 0.1920 | 0.0457 | | 0.1666 | 96.0 | 672 | 0.3966 | 0.85 | 0.2593 | 0.9218 | 0.85 | 0.8392 | 0.1920 | 0.0458 | | 0.1666 | 97.0 | 679 | 0.3966 | 0.85 | 0.2593 | 0.9221 | 0.85 | 0.8392 | 0.1920 | 0.0458 | | 0.1666 | 98.0 | 686 | 0.3966 | 0.85 | 0.2593 | 0.9224 | 0.85 | 0.8392 | 0.1920 | 0.0457 | | 0.1666 | 99.0 | 693 | 0.3966 | 0.85 | 0.2593 | 0.9224 | 0.85 | 0.8392 | 0.1994 | 0.0457 | | 0.1666 | 100.0 | 700 | 0.3966 | 0.85 | 0.2593 | 0.9223 | 0.85 | 0.8392 | 0.1994 | 0.0457 | ### Framework versions - Transformers 4.26.1 - Pytorch 1.13.1.post200 - Datasets 2.9.0 - Tokenizers 0.13.2

ALazcanoG/nominal-groups-recognition-bert-base-spanish-wwm-cased

ALazcanoG

2023-07-10T21:09:53Z

107

0

transformers

[ "transformers", "tensorboard", "safetensors", "bert", "token-classification", "generated_from_trainer", "es", "dataset:ALazcanoG/spanish_nominal_groups_conll2003", "autotrain_compatible", "endpoints_compatible", "region:us" ]

token-classification

2023-07-07T23:46:21Z

--- language: - es tags: - generated_from_trainer datasets: - ALazcanoG/spanish_nominal_groups_conll2003 model-index: - name: nominal-groups-recognition-bert-base-spanish-wwm-cased results: [] ---  # nominal-groups-recognition-bert-base-spanish-wwm-cased This model is a fine-tuned version of [dccuchile/bert-base-spanish-wwm-cased](https://huggingface.co/dccuchile/bert-base-spanish-wwm-cased) on the ALazcanoG/spanish_nominal_groups_conll2003 dataset. It achieves the following results on the evaluation set: - Loss: 0.3362 - Body Part Precision: 0.6830 - Body Part Recall: 0.7409 - Body Part F1: 0.7108 - Body Part Number: 413 - Disease Precision: 0.7439 - Disease Recall: 0.7446 - Disease F1: 0.7442 - Disease Number: 975 - Family Member Precision: 0.7941 - Family Member Recall: 0.9 - Family Member F1: 0.8438 - Family Member Number: 30 - Medication Precision: 0.8734 - Medication Recall: 0.7419 - Medication F1: 0.8023 - Medication Number: 93 - Procedure Precision: 0.6190 - Procedure Recall: 0.6270 - Procedure F1: 0.6230 - Procedure Number: 311 - Overall Precision: 0.7144 - Overall Recall: 0.7261 - Overall F1: 0.7202 - Overall Accuracy: 0.9175 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 13 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 5 ### Training results | Training Loss | Epoch | Step | Validation Loss | Body Part Precision | Body Part Recall | Body Part F1 | Body Part Number | Disease Precision | Disease Recall | Disease F1 | Disease Number | Family Member Precision | Family Member Recall | Family Member F1 | Family Member Number | Medication Precision | Medication Recall | Medication F1 | Medication Number | Procedure Precision | Procedure Recall | Procedure F1 | Procedure Number | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy | |:-------------:|:-----:|:----:|:---------------:|:-------------------:|:----------------:|:------------:|:----------------:|:-----------------:|:--------------:|:----------:|:--------------:|:-----------------------:|:--------------------:|:----------------:|:--------------------:|:--------------------:|:-----------------:|:-------------:|:-----------------:|:-------------------:|:----------------:|:------------:|:----------------:|:-----------------:|:--------------:|:----------:|:----------------:| | 0.4335 | 1.0 | 1004 | 0.3011 | 0.5944 | 0.7167 | 0.6498 | 413 | 0.7014 | 0.7036 | 0.7025 | 975 | 0.8 | 0.8 | 0.8000 | 30 | 0.7875 | 0.6774 | 0.7283 | 93 | 0.6007 | 0.5177 | 0.5561 | 311 | 0.6634 | 0.6751 | 0.6692 | 0.9063 | | 0.2379 | 2.0 | 2008 | 0.2920 | 0.6995 | 0.7215 | 0.7104 | 413 | 0.7655 | 0.7097 | 0.7366 | 975 | 0.75 | 0.8 | 0.7742 | 30 | 0.7667 | 0.7419 | 0.7541 | 93 | 0.6094 | 0.6270 | 0.6181 | 311 | 0.7212 | 0.7014 | 0.7112 | 0.9140 | | 0.1629 | 3.0 | 3012 | 0.3022 | 0.6674 | 0.7530 | 0.7076 | 413 | 0.7286 | 0.7241 | 0.7263 | 975 | 0.8571 | 0.8 | 0.8276 | 30 | 0.8519 | 0.7419 | 0.7931 | 93 | 0.5994 | 0.6495 | 0.6235 | 311 | 0.6975 | 0.7201 | 0.7086 | 0.9170 | | 0.1143 | 4.0 | 4016 | 0.3362 | 0.6830 | 0.7409 | 0.7108 | 413 | 0.7439 | 0.7446 | 0.7442 | 975 | 0.7941 | 0.9 | 0.8438 | 30 | 0.8734 | 0.7419 | 0.8023 | 93 | 0.6190 | 0.6270 | 0.6230 | 311 | 0.7144 | 0.7261 | 0.7202 | 0.9175 | | 0.0861 | 5.0 | 5020 | 0.3643 | 0.6806 | 0.7482 | 0.7128 | 413 | 0.7428 | 0.7436 | 0.7432 | 975 | 0.8182 | 0.9 | 0.8571 | 30 | 0.8831 | 0.7312 | 0.8000 | 93 | 0.5928 | 0.6367 | 0.6140 | 311 | 0.7081 | 0.7283 | 0.7181 | 0.9163 | ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3

ruggedmug/ppo-Huggy

ruggedmug

2023-07-10T21:08:52Z

2

0

ml-agents

[ "ml-agents", "tensorboard", "onnx", "Huggy", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-Huggy", "region:us" ]

reinforcement-learning

2023-07-10T21:08:43Z

--- library_name: ml-agents tags: - Huggy - deep-reinforcement-learning - reinforcement-learning - ML-Agents-Huggy --- # **ppo** Agent playing **Huggy** This is a trained model of a **ppo** agent playing **Huggy** using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents). ## Usage (with ML-Agents) The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/ We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub: - A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction - A *longer tutorial* to understand how works ML-Agents: https://huggingface.co/learn/deep-rl-course/unit5/introduction ### Resume the training ```bash mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume ``` ### Watch your Agent play You can watch your agent **playing directly in your browser** 1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity 2. Step 1: Find your model_id: ruggedmug/ppo-Huggy 3. Step 2: Select your *.nn /*.onnx file 4. Click on Watch the agent play 👀

skrl/IsaacGymEnvs-FactoryTaskNutBoltScrew-PPO

skrl

2023-07-10T21:06:55Z

0

skrl

[ "skrl", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]

reinforcement-learning

2023-07-10T19:47:47Z

--- library_name: skrl tags: - deep-reinforcement-learning - reinforcement-learning - skrl model-index: - name: PPO results: - metrics: - type: mean_reward value: -8.89 +/- 10.3 name: Total reward (mean) task: type: reinforcement-learning name: reinforcement-learning dataset: name: IsaacGymEnvs-FactoryTaskNutBoltScrew type: IsaacGymEnvs-FactoryTaskNutBoltScrew ---  # IsaacGymEnvs-FactoryTaskNutBoltScrew-PPO Trained agent for [NVIDIA Isaac Gym Preview](https://github.com/NVIDIA-Omniverse/IsaacGymEnvs) environments. - **Task:** FactoryTaskNutBoltScrew - **Agent:** [PPO](https://skrl.readthedocs.io/en/latest/api/agents/ppo.html) # Usage (with skrl) Note: Visit the skrl [Examples](https://skrl.readthedocs.io/en/latest/intro/examples.html) section to access the scripts. * PyTorch ```python from skrl.utils.huggingface import download_model_from_huggingface # assuming that there is an agent named `agent` path = download_model_from_huggingface("skrl/IsaacGymEnvs-FactoryTaskNutBoltScrew-PPO", filename="agent.pt") agent.load(path) ``` * JAX ```python from skrl.utils.huggingface import download_model_from_huggingface # assuming that there is an agent named `agent` path = download_model_from_huggingface("skrl/IsaacGymEnvs-FactoryTaskNutBoltScrew-PPO", filename="agent.pickle") agent.load(path) ``` # Hyperparameters Note: Undefined parameters keep their values by default. ```python # https://skrl.readthedocs.io/en/latest/api/agents/ppo.html#configuration-and-hyperparameters cfg = PPO_DEFAULT_CONFIG.copy() cfg["rollouts"] = 128 # memory_size cfg["learning_epochs"] = 8 cfg["mini_batches"] = 32 # 128 * 128 / 512 cfg["discount_factor"] = 0.99 cfg["lambda"] = 0.95 cfg["learning_rate"] = 1e-4 cfg["random_timesteps"] = 0 cfg["learning_starts"] = 0 cfg["grad_norm_clip"] = 0 cfg["ratio_clip"] = 0.2 cfg["value_clip"] = 0.2 cfg["clip_predicted_values"] = True cfg["entropy_loss_scale"] = 0.0 cfg["value_loss_scale"] = 1.0 cfg["kl_threshold"] = 0.016 cfg["rewards_shaper"] = None cfg["state_preprocessor"] = RunningStandardScaler cfg["state_preprocessor_kwargs"] = {"size": env.observation_space, "device": device} cfg["value_preprocessor"] = RunningStandardScaler cfg["value_preprocessor_kwargs"] = {"size": 1, "device": device} ```

WALIDALI/bekinorrev

WALIDALI

2023-07-10T21:00:29Z

5

0

diffusers

[ "diffusers", "safetensors", "text-to-image", "stable-diffusion", "license:creativeml-openrail-m", "autotrain_compatible", "endpoints_compatible", "diffusers:StableDiffusionPipeline", "region:us" ]

text-to-image

2023-07-10T20:57:08Z

--- license: creativeml-openrail-m tags: - text-to-image - stable-diffusion --- ### bekinorrev Dreambooth model trained by WALIDALI with [TheLastBen's fast-DreamBooth](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast-DreamBooth.ipynb) notebook Test the concept via A1111 Colab [fast-Colab-A1111](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast_stable_diffusion_AUTOMATIC1111.ipynb) Sample pictures of this concept:

jordyvl/vit-small_tobacco3482_kd_CEKD_t2.5_a0.9

jordyvl

2023-07-10T20:38:28Z

163

0

transformers

[ "transformers", "pytorch", "vit", "image-classification", "generated_from_trainer", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

image-classification

2023-07-10T19:59:22Z

--- license: apache-2.0 tags: - generated_from_trainer metrics: - accuracy model-index: - name: vit-small_tobacco3482_kd_CEKD_t2.5_a0.9 results: [] ---  # vit-small_tobacco3482_kd_CEKD_t2.5_a0.9 This model is a fine-tuned version of [WinKawaks/vit-small-patch16-224](https://huggingface.co/WinKawaks/vit-small-patch16-224) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.5446 - Accuracy: 0.85 - Brier Loss: 0.2446 - Nll: 1.0816 - F1 Micro: 0.85 - F1 Macro: 0.8348 - Ece: 0.1474 - Aurc: 0.0436 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 100 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | Brier Loss | Nll | F1 Micro | F1 Macro | Ece | Aurc | |:-------------:|:-----:|:----:|:---------------:|:--------:|:----------:|:------:|:--------:|:--------:|:------:|:------:| | No log | 1.0 | 7 | 2.1216 | 0.215 | 0.8751 | 5.2864 | 0.2150 | 0.1264 | 0.2697 | 0.6907 | | No log | 2.0 | 14 | 1.7056 | 0.405 | 0.7400 | 3.5721 | 0.405 | 0.2275 | 0.2995 | 0.4011 | | No log | 3.0 | 21 | 1.1857 | 0.62 | 0.5612 | 2.0143 | 0.62 | 0.5712 | 0.2994 | 0.2024 | | No log | 4.0 | 28 | 0.8767 | 0.705 | 0.4085 | 1.6918 | 0.705 | 0.6436 | 0.2231 | 0.1152 | | No log | 5.0 | 35 | 0.8620 | 0.72 | 0.3878 | 1.7931 | 0.72 | 0.7294 | 0.2233 | 0.1076 | | No log | 6.0 | 42 | 0.7517 | 0.775 | 0.3252 | 1.5573 | 0.775 | 0.7600 | 0.1970 | 0.0790 | | No log | 7.0 | 49 | 0.7280 | 0.79 | 0.3175 | 1.5140 | 0.79 | 0.7742 | 0.1903 | 0.0826 | | No log | 8.0 | 56 | 0.6848 | 0.8 | 0.2942 | 1.4438 | 0.8000 | 0.7902 | 0.1828 | 0.0866 | | No log | 9.0 | 63 | 0.6744 | 0.81 | 0.2889 | 1.4703 | 0.81 | 0.7969 | 0.1989 | 0.0692 | | No log | 10.0 | 70 | 0.8432 | 0.74 | 0.3859 | 1.3134 | 0.74 | 0.7206 | 0.1959 | 0.1051 | | No log | 11.0 | 77 | 0.7424 | 0.765 | 0.3294 | 1.5162 | 0.765 | 0.7792 | 0.2005 | 0.1048 | | No log | 12.0 | 84 | 0.6953 | 0.79 | 0.3194 | 1.2233 | 0.79 | 0.7850 | 0.1800 | 0.0922 | | No log | 13.0 | 91 | 0.5703 | 0.845 | 0.2538 | 1.2355 | 0.845 | 0.8372 | 0.1739 | 0.0447 | | No log | 14.0 | 98 | 0.6439 | 0.795 | 0.2924 | 1.2777 | 0.795 | 0.7743 | 0.1771 | 0.0534 | | No log | 15.0 | 105 | 0.5895 | 0.825 | 0.2650 | 1.2086 | 0.825 | 0.8071 | 0.1665 | 0.0566 | | No log | 16.0 | 112 | 0.5973 | 0.81 | 0.2753 | 1.0959 | 0.81 | 0.8013 | 0.1839 | 0.0534 | | No log | 17.0 | 119 | 0.5825 | 0.795 | 0.2722 | 1.1565 | 0.795 | 0.7886 | 0.1855 | 0.0534 | | No log | 18.0 | 126 | 0.5854 | 0.845 | 0.2661 | 1.1223 | 0.845 | 0.8424 | 0.1981 | 0.0549 | | No log | 19.0 | 133 | 0.5514 | 0.82 | 0.2553 | 0.9585 | 0.82 | 0.8150 | 0.1600 | 0.0481 | | No log | 20.0 | 140 | 0.5600 | 0.835 | 0.2443 | 1.2692 | 0.835 | 0.8232 | 0.1657 | 0.0469 | | No log | 21.0 | 147 | 0.5592 | 0.845 | 0.2473 | 1.1658 | 0.845 | 0.8331 | 0.1683 | 0.0493 | | No log | 22.0 | 154 | 0.5507 | 0.845 | 0.2411 | 1.1403 | 0.845 | 0.8311 | 0.1797 | 0.0450 | | No log | 23.0 | 161 | 0.5305 | 0.84 | 0.2361 | 1.1509 | 0.8400 | 0.8287 | 0.1650 | 0.0409 | | No log | 24.0 | 168 | 0.5352 | 0.835 | 0.2378 | 1.2208 | 0.835 | 0.8201 | 0.1515 | 0.0420 | | No log | 25.0 | 175 | 0.5425 | 0.845 | 0.2420 | 1.1208 | 0.845 | 0.8321 | 0.1776 | 0.0430 | | No log | 26.0 | 182 | 0.5396 | 0.84 | 0.2409 | 1.1230 | 0.8400 | 0.8286 | 0.1647 | 0.0446 | | No log | 27.0 | 189 | 0.5436 | 0.85 | 0.2401 | 1.1179 | 0.85 | 0.8387 | 0.1568 | 0.0427 | | No log | 28.0 | 196 | 0.5373 | 0.835 | 0.2415 | 1.1092 | 0.835 | 0.8141 | 0.1641 | 0.0427 | | No log | 29.0 | 203 | 0.5420 | 0.845 | 0.2436 | 1.0988 | 0.845 | 0.8326 | 0.1551 | 0.0444 | | No log | 30.0 | 210 | 0.5413 | 0.845 | 0.2420 | 1.1064 | 0.845 | 0.8312 | 0.1486 | 0.0440 | | No log | 31.0 | 217 | 0.5411 | 0.84 | 0.2418 | 1.1024 | 0.8400 | 0.8286 | 0.1565 | 0.0435 | | No log | 32.0 | 224 | 0.5426 | 0.845 | 0.2429 | 1.0993 | 0.845 | 0.8322 | 0.1631 | 0.0433 | | No log | 33.0 | 231 | 0.5424 | 0.85 | 0.2426 | 1.0989 | 0.85 | 0.8348 | 0.1615 | 0.0436 | | No log | 34.0 | 238 | 0.5406 | 0.84 | 0.2419 | 1.0979 | 0.8400 | 0.8251 | 0.1640 | 0.0440 | | No log | 35.0 | 245 | 0.5438 | 0.85 | 0.2436 | 1.0953 | 0.85 | 0.8348 | 0.1595 | 0.0438 | | No log | 36.0 | 252 | 0.5429 | 0.85 | 0.2429 | 1.0970 | 0.85 | 0.8348 | 0.1495 | 0.0433 | | No log | 37.0 | 259 | 0.5431 | 0.85 | 0.2427 | 1.0951 | 0.85 | 0.8348 | 0.1617 | 0.0435 | | No log | 38.0 | 266 | 0.5424 | 0.85 | 0.2426 | 1.0959 | 0.85 | 0.8348 | 0.1587 | 0.0434 | | No log | 39.0 | 273 | 0.5428 | 0.85 | 0.2432 | 1.0924 | 0.85 | 0.8348 | 0.1512 | 0.0433 | | No log | 40.0 | 280 | 0.5437 | 0.85 | 0.2438 | 1.0911 | 0.85 | 0.8348 | 0.1726 | 0.0438 | | No log | 41.0 | 287 | 0.5438 | 0.85 | 0.2434 | 1.0925 | 0.85 | 0.8348 | 0.1704 | 0.0433 | | No log | 42.0 | 294 | 0.5428 | 0.85 | 0.2432 | 1.0927 | 0.85 | 0.8348 | 0.1585 | 0.0436 | | No log | 43.0 | 301 | 0.5455 | 0.85 | 0.2443 | 1.0907 | 0.85 | 0.8348 | 0.1756 | 0.0437 | | No log | 44.0 | 308 | 0.5427 | 0.85 | 0.2433 | 1.0908 | 0.85 | 0.8348 | 0.1616 | 0.0433 | | No log | 45.0 | 315 | 0.5456 | 0.85 | 0.2446 | 1.0878 | 0.85 | 0.8348 | 0.1767 | 0.0437 | | No log | 46.0 | 322 | 0.5439 | 0.85 | 0.2438 | 1.0895 | 0.85 | 0.8348 | 0.1503 | 0.0435 | | No log | 47.0 | 329 | 0.5448 | 0.85 | 0.2443 | 1.0891 | 0.85 | 0.8348 | 0.1674 | 0.0439 | | No log | 48.0 | 336 | 0.5440 | 0.85 | 0.2437 | 1.0898 | 0.85 | 0.8348 | 0.1768 | 0.0437 | | No log | 49.0 | 343 | 0.5443 | 0.85 | 0.2441 | 1.0883 | 0.85 | 0.8348 | 0.1433 | 0.0432 | | No log | 50.0 | 350 | 0.5449 | 0.85 | 0.2444 | 1.0877 | 0.85 | 0.8348 | 0.1722 | 0.0436 | | No log | 51.0 | 357 | 0.5443 | 0.85 | 0.2442 | 1.0871 | 0.85 | 0.8348 | 0.1606 | 0.0434 | | No log | 52.0 | 364 | 0.5453 | 0.85 | 0.2444 | 1.0865 | 0.85 | 0.8348 | 0.1729 | 0.0436 | | No log | 53.0 | 371 | 0.5433 | 0.845 | 0.2438 | 1.0873 | 0.845 | 0.8287 | 0.1570 | 0.0434 | | No log | 54.0 | 378 | 0.5453 | 0.85 | 0.2447 | 1.0854 | 0.85 | 0.8348 | 0.1606 | 0.0435 | | No log | 55.0 | 385 | 0.5438 | 0.85 | 0.2439 | 1.0868 | 0.85 | 0.8348 | 0.1721 | 0.0434 | | No log | 56.0 | 392 | 0.5455 | 0.85 | 0.2447 | 1.0853 | 0.85 | 0.8348 | 0.1710 | 0.0437 | | No log | 57.0 | 399 | 0.5435 | 0.85 | 0.2439 | 1.0864 | 0.85 | 0.8348 | 0.1540 | 0.0434 | | No log | 58.0 | 406 | 0.5451 | 0.85 | 0.2447 | 1.0844 | 0.85 | 0.8348 | 0.1636 | 0.0436 | | No log | 59.0 | 413 | 0.5442 | 0.85 | 0.2441 | 1.0858 | 0.85 | 0.8348 | 0.1556 | 0.0435 | | No log | 60.0 | 420 | 0.5453 | 0.85 | 0.2447 | 1.0843 | 0.85 | 0.8348 | 0.1717 | 0.0437 | | No log | 61.0 | 427 | 0.5439 | 0.85 | 0.2442 | 1.0847 | 0.85 | 0.8348 | 0.1541 | 0.0432 | | No log | 62.0 | 434 | 0.5455 | 0.85 | 0.2449 | 1.0839 | 0.85 | 0.8348 | 0.1550 | 0.0435 | | No log | 63.0 | 441 | 0.5446 | 0.85 | 0.2445 | 1.0843 | 0.85 | 0.8348 | 0.1553 | 0.0435 | | No log | 64.0 | 448 | 0.5448 | 0.85 | 0.2446 | 1.0833 | 0.85 | 0.8348 | 0.1634 | 0.0435 | | No log | 65.0 | 455 | 0.5443 | 0.85 | 0.2443 | 1.0847 | 0.85 | 0.8348 | 0.1554 | 0.0435 | | No log | 66.0 | 462 | 0.5448 | 0.85 | 0.2447 | 1.0831 | 0.85 | 0.8348 | 0.1547 | 0.0436 | | No log | 67.0 | 469 | 0.5452 | 0.85 | 0.2448 | 1.0828 | 0.85 | 0.8348 | 0.1563 | 0.0436 | | No log | 68.0 | 476 | 0.5443 | 0.85 | 0.2444 | 1.0834 | 0.85 | 0.8348 | 0.1472 | 0.0434 | | No log | 69.0 | 483 | 0.5447 | 0.85 | 0.2445 | 1.0832 | 0.85 | 0.8348 | 0.1632 | 0.0434 | | No log | 70.0 | 490 | 0.5447 | 0.85 | 0.2446 | 1.0831 | 0.85 | 0.8348 | 0.1559 | 0.0435 | | No log | 71.0 | 497 | 0.5447 | 0.85 | 0.2446 | 1.0829 | 0.85 | 0.8348 | 0.1473 | 0.0435 | | 0.1823 | 72.0 | 504 | 0.5443 | 0.85 | 0.2444 | 1.0828 | 0.85 | 0.8348 | 0.1559 | 0.0434 | | 0.1823 | 73.0 | 511 | 0.5447 | 0.85 | 0.2447 | 1.0825 | 0.85 | 0.8348 | 0.1472 | 0.0434 | | 0.1823 | 74.0 | 518 | 0.5444 | 0.85 | 0.2444 | 1.0829 | 0.85 | 0.8348 | 0.1559 | 0.0436 | | 0.1823 | 75.0 | 525 | 0.5446 | 0.85 | 0.2445 | 1.0829 | 0.85 | 0.8348 | 0.1557 | 0.0435 | | 0.1823 | 76.0 | 532 | 0.5448 | 0.85 | 0.2445 | 1.0825 | 0.85 | 0.8348 | 0.1559 | 0.0435 | | 0.1823 | 77.0 | 539 | 0.5443 | 0.85 | 0.2444 | 1.0827 | 0.85 | 0.8348 | 0.1558 | 0.0435 | | 0.1823 | 78.0 | 546 | 0.5446 | 0.85 | 0.2446 | 1.0824 | 0.85 | 0.8348 | 0.1560 | 0.0436 | | 0.1823 | 79.0 | 553 | 0.5450 | 0.85 | 0.2448 | 1.0821 | 0.85 | 0.8348 | 0.1637 | 0.0436 | | 0.1823 | 80.0 | 560 | 0.5447 | 0.85 | 0.2446 | 1.0823 | 0.85 | 0.8348 | 0.1638 | 0.0436 | | 0.1823 | 81.0 | 567 | 0.5446 | 0.85 | 0.2446 | 1.0820 | 0.85 | 0.8348 | 0.1560 | 0.0435 | | 0.1823 | 82.0 | 574 | 0.5447 | 0.85 | 0.2446 | 1.0819 | 0.85 | 0.8348 | 0.1561 | 0.0435 | | 0.1823 | 83.0 | 581 | 0.5448 | 0.85 | 0.2446 | 1.0822 | 0.85 | 0.8348 | 0.1550 | 0.0436 | | 0.1823 | 84.0 | 588 | 0.5445 | 0.85 | 0.2446 | 1.0819 | 0.85 | 0.8348 | 0.1551 | 0.0435 | | 0.1823 | 85.0 | 595 | 0.5446 | 0.85 | 0.2446 | 1.0818 | 0.85 | 0.8348 | 0.1560 | 0.0436 | | 0.1823 | 86.0 | 602 | 0.5446 | 0.85 | 0.2446 | 1.0818 | 0.85 | 0.8348 | 0.1560 | 0.0435 | | 0.1823 | 87.0 | 609 | 0.5448 | 0.85 | 0.2447 | 1.0820 | 0.85 | 0.8348 | 0.1560 | 0.0435 | | 0.1823 | 88.0 | 616 | 0.5447 | 0.85 | 0.2446 | 1.0819 | 0.85 | 0.8348 | 0.1551 | 0.0435 | | 0.1823 | 89.0 | 623 | 0.5446 | 0.85 | 0.2446 | 1.0819 | 0.85 | 0.8348 | 0.1560 | 0.0435 | | 0.1823 | 90.0 | 630 | 0.5446 | 0.85 | 0.2446 | 1.0816 | 0.85 | 0.8348 | 0.1638 | 0.0436 | | 0.1823 | 91.0 | 637 | 0.5446 | 0.85 | 0.2445 | 1.0817 | 0.85 | 0.8348 | 0.1474 | 0.0435 | | 0.1823 | 92.0 | 644 | 0.5445 | 0.85 | 0.2445 | 1.0818 | 0.85 | 0.8348 | 0.1551 | 0.0436 | | 0.1823 | 93.0 | 651 | 0.5447 | 0.85 | 0.2446 | 1.0818 | 0.85 | 0.8348 | 0.1560 | 0.0436 | | 0.1823 | 94.0 | 658 | 0.5447 | 0.85 | 0.2446 | 1.0816 | 0.85 | 0.8348 | 0.1561 | 0.0436 | | 0.1823 | 95.0 | 665 | 0.5447 | 0.85 | 0.2446 | 1.0816 | 0.85 | 0.8348 | 0.1550 | 0.0435 | | 0.1823 | 96.0 | 672 | 0.5446 | 0.85 | 0.2446 | 1.0816 | 0.85 | 0.8348 | 0.1474 | 0.0436 | | 0.1823 | 97.0 | 679 | 0.5446 | 0.85 | 0.2446 | 1.0817 | 0.85 | 0.8348 | 0.1551 | 0.0436 | | 0.1823 | 98.0 | 686 | 0.5446 | 0.85 | 0.2446 | 1.0817 | 0.85 | 0.8348 | 0.1474 | 0.0436 | | 0.1823 | 99.0 | 693 | 0.5446 | 0.85 | 0.2446 | 1.0816 | 0.85 | 0.8348 | 0.1474 | 0.0436 | | 0.1823 | 100.0 | 700 | 0.5446 | 0.85 | 0.2446 | 1.0816 | 0.85 | 0.8348 | 0.1474 | 0.0436 | ### Framework versions - Transformers 4.26.1 - Pytorch 1.13.1.post200 - Datasets 2.9.0 - Tokenizers 0.13.2

skrl/IsaacGymEnvs-FactoryTaskNutBoltPlace-PPO

skrl

2023-07-10T20:15:49Z

0

skrl

[ "skrl", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]

reinforcement-learning

2023-07-10T19:47:18Z

--- library_name: skrl tags: - deep-reinforcement-learning - reinforcement-learning - skrl model-index: - name: PPO results: - metrics: - type: mean_reward value: -38.54 +/- 17.49 name: Total reward (mean) task: type: reinforcement-learning name: reinforcement-learning dataset: name: IsaacGymEnvs-FactoryTaskNutBoltPlace type: IsaacGymEnvs-FactoryTaskNutBoltPlace ---  # IsaacGymEnvs-FactoryTaskNutBoltPlace-PPO Trained agent for [NVIDIA Isaac Gym Preview](https://github.com/NVIDIA-Omniverse/IsaacGymEnvs) environments. - **Task:** FactoryTaskNutBoltPlace - **Agent:** [PPO](https://skrl.readthedocs.io/en/latest/api/agents/ppo.html) # Usage (with skrl) Note: Visit the skrl [Examples](https://skrl.readthedocs.io/en/latest/intro/examples.html) section to access the scripts. * PyTorch ```python from skrl.utils.huggingface import download_model_from_huggingface # assuming that there is an agent named `agent` path = download_model_from_huggingface("skrl/IsaacGymEnvs-FactoryTaskNutBoltPlace-PPO", filename="agent.pt") agent.load(path) ``` * JAX ```python from skrl.utils.huggingface import download_model_from_huggingface # assuming that there is an agent named `agent` path = download_model_from_huggingface("skrl/IsaacGymEnvs-FactoryTaskNutBoltPlace-PPO", filename="agent.pickle") agent.load(path) ``` # Hyperparameters Note: Undefined parameters keep their values by default. ```python # https://skrl.readthedocs.io/en/latest/api/agents/ppo.html#configuration-and-hyperparameters cfg = PPO_DEFAULT_CONFIG.copy() cfg["rollouts"] = 120 # memory_size cfg["learning_epochs"] = 8 cfg["mini_batches"] = 30 # 120 * 128 / 512 cfg["discount_factor"] = 0.99 cfg["lambda"] = 0.95 cfg["learning_rate"] = 1e-4 cfg["random_timesteps"] = 0 cfg["learning_starts"] = 0 cfg["grad_norm_clip"] = 0 cfg["ratio_clip"] = 0.2 cfg["value_clip"] = 0.2 cfg["clip_predicted_values"] = True cfg["entropy_loss_scale"] = 0.0 cfg["value_loss_scale"] = 1.0 cfg["kl_threshold"] = 0.016 cfg["rewards_shaper"] = None cfg["state_preprocessor"] = RunningStandardScaler cfg["state_preprocessor_kwargs"] = {"size": env.observation_space, "device": device} cfg["value_preprocessor"] = RunningStandardScaler cfg["value_preprocessor_kwargs"] = {"size": 1, "device": device} ```

jliu596/Reinforce-cartpole

jliu596

2023-07-10T20:13:38Z

0

null

[ "CartPole-v1", "reinforce", "reinforcement-learning", "custom-implementation", "deep-rl-class", "model-index", "region:us" ]

reinforcement-learning

2023-07-10T17:26:46Z

--- tags: - CartPole-v1 - reinforce - reinforcement-learning - custom-implementation - deep-rl-class model-index: - name: Reinforce-cartpole results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: CartPole-v1 type: CartPole-v1 metrics: - type: mean_reward value: 500.00 +/- 0.00 name: mean_reward verified: false --- # **Reinforce** Agent playing **CartPole-v1** This is a trained model of a **Reinforce** agent playing **CartPole-v1** . To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction

blzncz/segformer-finetuned-4ss1st3r_s3gs3m-10k-steps

blzncz

2023-07-10T20:04:14Z

188

0

transformers

[ "transformers", "pytorch", "segformer", "image-segmentation", "vision", "generated_from_trainer", "license:other", "endpoints_compatible", "region:us" ]

image-segmentation

2023-07-10T10:49:12Z

--- license: other tags: - image-segmentation - vision - generated_from_trainer model-index: - name: segformer-finetuned-4ss1st3r_s3gs3m-10k-steps results: [] ---  # segformer-finetuned-4ss1st3r_s3gs3m-10k-steps This model is a fine-tuned version of [nvidia/mit-b0](https://huggingface.co/nvidia/mit-b0) on the blzncz/4ss1st3r_s3gs3m dataset. It achieves the following results on the evaluation set: - Loss: 0.3966 - Mean Iou: 0.5967 - Mean Accuracy: 0.8460 - Overall Accuracy: 0.9344 - Accuracy Bg: nan - Accuracy Fallo cohesivo: 0.9510 - Accuracy Fallo malla: 0.8524 - Accuracy Fallo adhesivo: 0.9362 - Accuracy Fallo burbuja: 0.6444 - Iou Bg: 0.0 - Iou Fallo cohesivo: 0.9239 - Iou Fallo malla: 0.7125 - Iou Fallo adhesivo: 0.8335 - Iou Fallo burbuja: 0.5139 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 6e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 1337 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: polynomial - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Accuracy Bg | Accuracy Fallo cohesivo | Accuracy Fallo malla | Accuracy Fallo adhesivo | Accuracy Fallo burbuja | Iou Bg | Iou Fallo cohesivo | Iou Fallo malla | Iou Fallo adhesivo | Iou Fallo burbuja | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:-------------:|:----------------:|:-----------:|:-----------------------:|:--------------------:|:-----------------------:|:----------------------:|:------:|:------------------:|:---------------:|:------------------:|:-----------------:| | 0.4796 | 1.0 | 133 | 0.4190 | 0.4518 | 0.6689 | 0.9049 | nan | 0.9277 | 0.8091 | 0.9381 | 0.0008 | 0.0 | 0.8866 | 0.6536 | 0.7179 | 0.0008 | | 0.2665 | 2.0 | 266 | 0.3667 | 0.5096 | 0.7283 | 0.9001 | nan | 0.9111 | 0.8964 | 0.8731 | 0.2324 | 0.0 | 0.8802 | 0.6013 | 0.8467 | 0.2197 | | 0.2158 | 3.0 | 399 | 0.3210 | 0.5505 | 0.7807 | 0.9142 | nan | 0.9250 | 0.8685 | 0.9414 | 0.3878 | 0.0 | 0.8952 | 0.6239 | 0.8901 | 0.3432 | | 0.1737 | 4.0 | 532 | 0.3572 | 0.5370 | 0.7851 | 0.8905 | nan | 0.8905 | 0.9102 | 0.9121 | 0.4277 | 0.0 | 0.8671 | 0.5637 | 0.8777 | 0.3764 | | 0.1602 | 5.0 | 665 | 0.6273 | 0.4086 | 0.7632 | 0.7743 | nan | 0.7333 | 0.9343 | 0.9685 | 0.4168 | 0.0 | 0.7198 | 0.4460 | 0.5324 | 0.3449 | | 0.1707 | 6.0 | 798 | 0.3534 | 0.5442 | 0.7953 | 0.9025 | nan | 0.9056 | 0.9031 | 0.9234 | 0.4492 | 0.0 | 0.8812 | 0.5985 | 0.8629 | 0.3783 | | 0.1376 | 7.0 | 931 | 0.3266 | 0.5513 | 0.7634 | 0.9262 | nan | 0.9434 | 0.8621 | 0.9288 | 0.3195 | 0.0 | 0.9109 | 0.6623 | 0.8866 | 0.2968 | | 0.1346 | 8.0 | 1064 | 0.4976 | 0.4916 | 0.7900 | 0.8396 | nan | 0.8190 | 0.9133 | 0.9713 | 0.4565 | 0.0 | 0.8041 | 0.4662 | 0.7906 | 0.3970 | | 0.1319 | 9.0 | 1197 | 0.3650 | 0.5652 | 0.8404 | 0.9043 | nan | 0.9053 | 0.8856 | 0.9593 | 0.6113 | 0.0 | 0.8829 | 0.5992 | 0.8734 | 0.4706 | | 0.1229 | 10.0 | 1330 | 0.3201 | 0.5666 | 0.7963 | 0.9299 | nan | 0.9435 | 0.8764 | 0.9389 | 0.4265 | 0.0 | 0.9171 | 0.6896 | 0.8499 | 0.3763 | | 0.1142 | 11.0 | 1463 | 0.3824 | 0.5576 | 0.8204 | 0.9020 | nan | 0.8988 | 0.9231 | 0.9456 | 0.5142 | 0.0 | 0.8795 | 0.6001 | 0.8711 | 0.4374 | | 0.0983 | 12.0 | 1596 | 0.3133 | 0.5812 | 0.8297 | 0.9293 | nan | 0.9354 | 0.9046 | 0.9558 | 0.5229 | 0.0 | 0.9136 | 0.6969 | 0.8618 | 0.4335 | | 0.1058 | 13.0 | 1729 | 0.2965 | 0.5860 | 0.8250 | 0.9364 | nan | 0.9528 | 0.8496 | 0.9598 | 0.5378 | 0.0 | 0.9253 | 0.7162 | 0.8502 | 0.4383 | | 0.1052 | 14.0 | 1862 | 0.2839 | 0.6064 | 0.8275 | 0.9460 | nan | 0.9674 | 0.8517 | 0.9290 | 0.5621 | 0.0 | 0.9355 | 0.7492 | 0.8930 | 0.4540 | | 0.0911 | 15.0 | 1995 | 0.3245 | 0.5853 | 0.8116 | 0.9368 | nan | 0.9565 | 0.8504 | 0.9298 | 0.5099 | 0.0 | 0.9243 | 0.7171 | 0.8534 | 0.4318 | | 0.0889 | 16.0 | 2128 | 0.3094 | 0.5969 | 0.8225 | 0.9422 | nan | 0.9615 | 0.8559 | 0.9376 | 0.5351 | 0.0 | 0.9313 | 0.7353 | 0.8726 | 0.4451 | | 0.0827 | 17.0 | 2261 | 0.4776 | 0.5187 | 0.8195 | 0.8547 | nan | 0.8390 | 0.9163 | 0.9440 | 0.5786 | 0.0 | 0.8207 | 0.4920 | 0.8216 | 0.4590 | | 0.0939 | 18.0 | 2394 | 0.3923 | 0.5364 | 0.8375 | 0.8948 | nan | 0.8950 | 0.8831 | 0.9437 | 0.6282 | 0.0 | 0.8746 | 0.6268 | 0.7090 | 0.4717 | | 0.0799 | 19.0 | 2527 | 0.3560 | 0.5776 | 0.8252 | 0.9254 | nan | 0.9337 | 0.8933 | 0.9409 | 0.5331 | 0.0 | 0.9096 | 0.6846 | 0.8519 | 0.4422 | | 0.075 | 20.0 | 2660 | 0.3803 | 0.5796 | 0.8338 | 0.9194 | nan | 0.9249 | 0.9078 | 0.9238 | 0.5788 | 0.0 | 0.9032 | 0.6459 | 0.8821 | 0.4670 | | 0.0844 | 21.0 | 2793 | 0.2885 | 0.6170 | 0.8334 | 0.9507 | nan | 0.9757 | 0.8296 | 0.9390 | 0.5892 | 0.0 | 0.9412 | 0.7654 | 0.8933 | 0.4852 | | 0.0746 | 22.0 | 2926 | 0.3222 | 0.5831 | 0.8160 | 0.9331 | nan | 0.9481 | 0.8685 | 0.9370 | 0.5105 | 0.0 | 0.9193 | 0.7032 | 0.8716 | 0.4215 | | 0.072 | 23.0 | 3059 | 0.3481 | 0.5878 | 0.8336 | 0.9266 | nan | 0.9357 | 0.8952 | 0.9271 | 0.5764 | 0.0 | 0.9123 | 0.6824 | 0.8720 | 0.4725 | | 0.0735 | 24.0 | 3192 | 0.3196 | 0.5974 | 0.8403 | 0.9353 | nan | 0.9496 | 0.8666 | 0.9430 | 0.6018 | 0.0 | 0.9225 | 0.7165 | 0.8649 | 0.4832 | | 0.0674 | 25.0 | 3325 | 0.3407 | 0.5927 | 0.8435 | 0.9282 | nan | 0.9401 | 0.8786 | 0.9246 | 0.6304 | 0.0 | 0.9141 | 0.6844 | 0.8696 | 0.4953 | | 0.0712 | 26.0 | 3458 | 0.3356 | 0.5906 | 0.8420 | 0.9301 | nan | 0.9405 | 0.8895 | 0.9299 | 0.6080 | 0.0 | 0.9160 | 0.6905 | 0.8743 | 0.4722 | | 0.072 | 27.0 | 3591 | 0.3491 | 0.5833 | 0.8372 | 0.9286 | nan | 0.9415 | 0.8636 | 0.9425 | 0.6012 | 0.0 | 0.9161 | 0.6966 | 0.8246 | 0.4790 | | 0.0641 | 28.0 | 3724 | 0.3130 | 0.6087 | 0.8422 | 0.9473 | nan | 0.9697 | 0.8357 | 0.9427 | 0.6208 | 0.0 | 0.9386 | 0.7613 | 0.8599 | 0.4837 | | 0.0597 | 29.0 | 3857 | 0.3828 | 0.5666 | 0.8394 | 0.9107 | nan | 0.9141 | 0.8934 | 0.9411 | 0.6092 | 0.0 | 0.8924 | 0.6327 | 0.8343 | 0.4735 | | 0.0648 | 30.0 | 3990 | 0.3435 | 0.6001 | 0.8372 | 0.9403 | nan | 0.9569 | 0.8708 | 0.9276 | 0.5935 | 0.0 | 0.9292 | 0.7312 | 0.8779 | 0.4623 | | 0.0618 | 31.0 | 4123 | 0.3531 | 0.5963 | 0.8521 | 0.9303 | nan | 0.9450 | 0.8621 | 0.9240 | 0.6773 | 0.0 | 0.9179 | 0.6842 | 0.8730 | 0.5063 | | 0.0556 | 32.0 | 4256 | 0.3307 | 0.6037 | 0.8417 | 0.9401 | nan | 0.9576 | 0.8637 | 0.9271 | 0.6183 | 0.0 | 0.9298 | 0.7274 | 0.8637 | 0.4974 | | 0.0616 | 33.0 | 4389 | 0.3510 | 0.5911 | 0.8347 | 0.9298 | nan | 0.9424 | 0.8714 | 0.9388 | 0.5863 | 0.0 | 0.9158 | 0.6914 | 0.8745 | 0.4740 | | 0.0603 | 34.0 | 4522 | 0.3467 | 0.6022 | 0.8544 | 0.9334 | nan | 0.9487 | 0.8610 | 0.9274 | 0.6807 | 0.0 | 0.9211 | 0.7029 | 0.8738 | 0.5130 | | 0.0587 | 35.0 | 4655 | 0.3574 | 0.6017 | 0.8407 | 0.9379 | nan | 0.9555 | 0.8541 | 0.9346 | 0.6187 | 0.0 | 0.9269 | 0.7228 | 0.8627 | 0.4962 | | 0.0557 | 36.0 | 4788 | 0.3871 | 0.5720 | 0.8334 | 0.9178 | nan | 0.9317 | 0.8416 | 0.9374 | 0.6228 | 0.0 | 0.9051 | 0.6479 | 0.8160 | 0.4911 | | 0.0567 | 37.0 | 4921 | 0.4425 | 0.5656 | 0.8282 | 0.9070 | nan | 0.9114 | 0.8922 | 0.9244 | 0.5848 | 0.0 | 0.8889 | 0.6100 | 0.8575 | 0.4718 | | 0.0537 | 38.0 | 5054 | 0.3512 | 0.5946 | 0.8392 | 0.9317 | nan | 0.9463 | 0.8649 | 0.9314 | 0.6142 | 0.0 | 0.9187 | 0.6984 | 0.8637 | 0.4921 | | 0.0559 | 39.0 | 5187 | 0.3676 | 0.5931 | 0.8437 | 0.9273 | nan | 0.9381 | 0.8798 | 0.9323 | 0.6247 | 0.0 | 0.9129 | 0.6779 | 0.8786 | 0.4959 | | 0.0502 | 40.0 | 5320 | 0.4149 | 0.5518 | 0.8381 | 0.8984 | nan | 0.9011 | 0.8773 | 0.9368 | 0.6370 | 0.0 | 0.8793 | 0.6069 | 0.7741 | 0.4989 | | 0.0559 | 41.0 | 5453 | 0.4042 | 0.5694 | 0.8342 | 0.9130 | nan | 0.9206 | 0.8721 | 0.9400 | 0.6041 | 0.0 | 0.8971 | 0.6319 | 0.8286 | 0.4896 | | 0.0523 | 42.0 | 5586 | 0.3669 | 0.5903 | 0.8462 | 0.9286 | nan | 0.9414 | 0.8676 | 0.9337 | 0.6421 | 0.0 | 0.9162 | 0.6883 | 0.8370 | 0.5102 | | 0.0525 | 43.0 | 5719 | 0.4140 | 0.5704 | 0.8531 | 0.9081 | nan | 0.9110 | 0.8867 | 0.9417 | 0.6729 | 0.0 | 0.8898 | 0.6220 | 0.8366 | 0.5035 | | 0.0508 | 44.0 | 5852 | 0.3965 | 0.5714 | 0.8396 | 0.9141 | nan | 0.9227 | 0.8800 | 0.9147 | 0.6409 | 0.0 | 0.8989 | 0.6513 | 0.8007 | 0.5060 | | 0.0507 | 45.0 | 5985 | 0.3793 | 0.5817 | 0.8392 | 0.9196 | nan | 0.9272 | 0.8932 | 0.9214 | 0.6148 | 0.0 | 0.9042 | 0.6627 | 0.8407 | 0.5011 | | 0.0494 | 46.0 | 6118 | 0.3500 | 0.6020 | 0.8426 | 0.9363 | nan | 0.9524 | 0.8619 | 0.9322 | 0.6240 | 0.0 | 0.9247 | 0.7142 | 0.8653 | 0.5058 | | 0.0462 | 47.0 | 6251 | 0.3524 | 0.6031 | 0.8435 | 0.9388 | nan | 0.9545 | 0.8668 | 0.9364 | 0.6163 | 0.0 | 0.9274 | 0.7269 | 0.8703 | 0.4909 | | 0.0486 | 48.0 | 6384 | 0.3876 | 0.5902 | 0.8397 | 0.9308 | nan | 0.9479 | 0.8557 | 0.9161 | 0.6392 | 0.0 | 0.9203 | 0.6928 | 0.8334 | 0.5046 | | 0.0461 | 49.0 | 6517 | 0.3674 | 0.5933 | 0.8409 | 0.9326 | nan | 0.9482 | 0.8622 | 0.9258 | 0.6274 | 0.0 | 0.9214 | 0.7053 | 0.8367 | 0.5030 | | 0.0497 | 50.0 | 6650 | 0.4018 | 0.5838 | 0.8374 | 0.9246 | nan | 0.9390 | 0.8519 | 0.9341 | 0.6244 | 0.0 | 0.9102 | 0.6733 | 0.8361 | 0.4992 | | 0.0491 | 51.0 | 6783 | 0.4036 | 0.5824 | 0.8513 | 0.9198 | nan | 0.9272 | 0.8805 | 0.9403 | 0.6573 | 0.0 | 0.9037 | 0.6712 | 0.8169 | 0.5203 | | 0.046 | 52.0 | 6916 | 0.3913 | 0.5820 | 0.8395 | 0.9243 | nan | 0.9347 | 0.8771 | 0.9336 | 0.6126 | 0.0 | 0.9105 | 0.6792 | 0.8244 | 0.4960 | | 0.0488 | 53.0 | 7049 | 0.3441 | 0.6010 | 0.8504 | 0.9362 | nan | 0.9523 | 0.8521 | 0.9457 | 0.6517 | 0.0 | 0.9250 | 0.7225 | 0.8496 | 0.5081 | | 0.0458 | 54.0 | 7182 | 0.3784 | 0.5977 | 0.8382 | 0.9378 | nan | 0.9603 | 0.8212 | 0.9375 | 0.6337 | 0.0 | 0.9286 | 0.7157 | 0.8387 | 0.5053 | | 0.0449 | 55.0 | 7315 | 0.3506 | 0.6068 | 0.8493 | 0.9404 | nan | 0.9579 | 0.8554 | 0.9385 | 0.6456 | 0.0 | 0.9300 | 0.7357 | 0.8549 | 0.5132 | | 0.0482 | 56.0 | 7448 | 0.4005 | 0.5819 | 0.8414 | 0.9249 | nan | 0.9374 | 0.8642 | 0.9337 | 0.6303 | 0.0 | 0.9119 | 0.6831 | 0.8139 | 0.5006 | | 0.0434 | 57.0 | 7581 | 0.3749 | 0.5914 | 0.8465 | 0.9294 | nan | 0.9423 | 0.8675 | 0.9339 | 0.6421 | 0.0 | 0.9171 | 0.6999 | 0.8265 | 0.5134 | | 0.0435 | 58.0 | 7714 | 0.4195 | 0.5722 | 0.8400 | 0.9172 | nan | 0.9274 | 0.8700 | 0.9234 | 0.6392 | 0.0 | 0.9025 | 0.6588 | 0.7954 | 0.5044 | | 0.0442 | 59.0 | 7847 | 0.3975 | 0.5828 | 0.8407 | 0.9257 | nan | 0.9398 | 0.8563 | 0.9312 | 0.6356 | 0.0 | 0.9134 | 0.6866 | 0.8103 | 0.5037 | | 0.0442 | 60.0 | 7980 | 0.3845 | 0.5929 | 0.8457 | 0.9315 | nan | 0.9459 | 0.8603 | 0.9363 | 0.6404 | 0.0 | 0.9193 | 0.7041 | 0.8308 | 0.5103 | | 0.0422 | 61.0 | 8113 | 0.3875 | 0.5963 | 0.8465 | 0.9338 | nan | 0.9489 | 0.8616 | 0.9340 | 0.6413 | 0.0 | 0.9226 | 0.7135 | 0.8381 | 0.5072 | | 0.0436 | 62.0 | 8246 | 0.3859 | 0.6022 | 0.8497 | 0.9385 | nan | 0.9566 | 0.8477 | 0.9382 | 0.6562 | 0.0 | 0.9289 | 0.7300 | 0.8376 | 0.5147 | | 0.0429 | 63.0 | 8379 | 0.3857 | 0.5956 | 0.8425 | 0.9357 | nan | 0.9534 | 0.8481 | 0.9357 | 0.6327 | 0.0 | 0.9249 | 0.7233 | 0.8283 | 0.5016 | | 0.0446 | 64.0 | 8512 | 0.3778 | 0.5976 | 0.8495 | 0.9343 | nan | 0.9492 | 0.8602 | 0.9399 | 0.6489 | 0.0 | 0.9232 | 0.7191 | 0.8305 | 0.5153 | | 0.0429 | 65.0 | 8645 | 0.3889 | 0.5948 | 0.8478 | 0.9330 | nan | 0.9490 | 0.8548 | 0.9325 | 0.6549 | 0.0 | 0.9225 | 0.7075 | 0.8271 | 0.5167 | | 0.0454 | 66.0 | 8778 | 0.3915 | 0.5941 | 0.8470 | 0.9329 | nan | 0.9490 | 0.8571 | 0.9271 | 0.6547 | 0.0 | 0.9221 | 0.7087 | 0.8278 | 0.5117 | | 0.0427 | 67.0 | 8911 | 0.3924 | 0.5967 | 0.8455 | 0.9349 | nan | 0.9518 | 0.8520 | 0.9350 | 0.6433 | 0.0 | 0.9247 | 0.7167 | 0.8290 | 0.5133 | | 0.0425 | 68.0 | 9044 | 0.3990 | 0.5992 | 0.8491 | 0.9358 | nan | 0.9524 | 0.8545 | 0.9355 | 0.6541 | 0.0 | 0.9250 | 0.7187 | 0.8387 | 0.5136 | | 0.0429 | 69.0 | 9177 | 0.3911 | 0.5909 | 0.8499 | 0.9303 | nan | 0.9451 | 0.8532 | 0.9394 | 0.6619 | 0.0 | 0.9192 | 0.7029 | 0.8178 | 0.5146 | | 0.0465 | 70.0 | 9310 | 0.3840 | 0.5977 | 0.8481 | 0.9332 | nan | 0.9473 | 0.8700 | 0.9278 | 0.6473 | 0.0 | 0.9215 | 0.7079 | 0.8480 | 0.5110 | | 0.0436 | 71.0 | 9443 | 0.3862 | 0.5974 | 0.8456 | 0.9351 | nan | 0.9518 | 0.8534 | 0.9359 | 0.6413 | 0.0 | 0.9248 | 0.7162 | 0.8338 | 0.5124 | | 0.0435 | 72.0 | 9576 | 0.3926 | 0.5952 | 0.8448 | 0.9328 | nan | 0.9484 | 0.8585 | 0.9318 | 0.6405 | 0.0 | 0.9217 | 0.7073 | 0.8386 | 0.5084 | | 0.0421 | 73.0 | 9709 | 0.3961 | 0.5984 | 0.8467 | 0.9348 | nan | 0.9513 | 0.8564 | 0.9309 | 0.6482 | 0.0 | 0.9243 | 0.7119 | 0.8414 | 0.5143 | | 0.0409 | 74.0 | 9842 | 0.3973 | 0.5982 | 0.8494 | 0.9341 | nan | 0.9498 | 0.8596 | 0.9306 | 0.6578 | 0.0 | 0.9233 | 0.7094 | 0.8401 | 0.5181 | | 0.041 | 75.0 | 9975 | 0.3898 | 0.5963 | 0.8476 | 0.9335 | nan | 0.9493 | 0.8561 | 0.9354 | 0.6498 | 0.0 | 0.9227 | 0.7108 | 0.8329 | 0.5153 | | 0.0436 | 75.19 | 10000 | 0.3966 | 0.5967 | 0.8460 | 0.9344 | nan | 0.9510 | 0.8524 | 0.9362 | 0.6444 | 0.0 | 0.9239 | 0.7125 | 0.8335 | 0.5139 | ### Framework versions - Transformers 4.31.0.dev0 - Pytorch 2.0.1+cpu - Datasets 2.13.1 - Tokenizers 0.13.3

NasimB/gpt2-cocnat-aochildes-mod-sub-length-10k

NasimB

2023-07-10T19:27:45Z

16

0

transformers

[ "transformers", "pytorch", "gpt2", "text-generation", "generated_from_trainer", "dataset:generator", "license:mit", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]

text-generation

2023-07-10T17:32:01Z

--- license: mit tags: - generated_from_trainer datasets: - generator model-index: - name: gpt2-cocnat-aochildes-mod-sub-length-10k results: [] ---  # gpt2-cocnat-aochildes-mod-sub-length-10k This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the generator dataset. It achieves the following results on the evaluation set: - Loss: 4.3425 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 64 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_steps: 1000 - num_epochs: 6 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:-----:|:---------------:| | 6.6933 | 0.29 | 500 | 5.6341 | | 5.3469 | 0.59 | 1000 | 5.1996 | | 4.9864 | 0.88 | 1500 | 4.9580 | | 4.7189 | 1.18 | 2000 | 4.8083 | | 4.5609 | 1.47 | 2500 | 4.6850 | | 4.4523 | 1.77 | 3000 | 4.5821 | | 4.317 | 2.06 | 3500 | 4.5146 | | 4.1329 | 2.35 | 4000 | 4.4652 | | 4.1086 | 2.65 | 4500 | 4.4071 | | 4.0635 | 2.94 | 5000 | 4.3601 | | 3.8482 | 3.24 | 5500 | 4.3553 | | 3.8055 | 3.53 | 6000 | 4.3282 | | 3.7859 | 3.83 | 6500 | 4.2926 | | 3.6619 | 4.12 | 7000 | 4.2970 | | 3.5196 | 4.41 | 7500 | 4.2933 | | 3.5139 | 4.71 | 8000 | 4.2857 | | 3.4905 | 5.0 | 8500 | 4.2710 | | 3.3203 | 5.3 | 9000 | 4.2871 | | 3.322 | 5.59 | 9500 | 4.2867 | | 3.3172 | 5.89 | 10000 | 4.2863 | ### Framework versions - Transformers 4.26.1 - Pytorch 1.11.0+cu113 - Datasets 2.13.0 - Tokenizers 0.13.3

simonestradasch/COMPner2-bert-base-spanish-wwm-cased

simonestradasch

2023-07-10T19:24:22Z

109

0

transformers

[ "transformers", "tensorboard", "safetensors", "bert", "token-classification", "generated_from_trainer", "es", "dataset:simonestradasch/NERcomp2", "autotrain_compatible", "endpoints_compatible", "region:us" ]

token-classification

2023-07-10T18:55:43Z

--- language: - es tags: - generated_from_trainer datasets: - simonestradasch/NERcomp2 model-index: - name: COMPner2-bert-base-spanish-wwm-cased results: [] ---  # COMPner2-bert-base-spanish-wwm-cased This model is a fine-tuned version of [dccuchile/bert-base-spanish-wwm-cased](https://huggingface.co/dccuchile/bert-base-spanish-wwm-cased) on the simonestradasch/NERcomp2 dataset. It achieves the following results on the evaluation set: - Loss: 0.2843 - Body Part Precision: 0.6644 - Body Part Recall: 0.7143 - Body Part F1: 0.6884 - Body Part Number: 413 - Disease Precision: 0.7251 - Disease Recall: 0.7303 - Disease F1: 0.7276 - Disease Number: 975 - Family Member Precision: 0.8065 - Family Member Recall: 0.8333 - Family Member F1: 0.8197 - Family Member Number: 30 - Medication Precision: 0.7778 - Medication Recall: 0.6774 - Medication F1: 0.7241 - Medication Number: 93 - Procedure Precision: 0.5763 - Procedure Recall: 0.5949 - Procedure F1: 0.5854 - Procedure Number: 311 - Overall Precision: 0.6885 - Overall Recall: 0.7025 - Overall F1: 0.6955 - Overall Accuracy: 0.9146 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 13 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 2 ### Training results | Training Loss | Epoch | Step | Validation Loss | Body Part Precision | Body Part Recall | Body Part F1 | Body Part Number | Disease Precision | Disease Recall | Disease F1 | Disease Number | Family Member Precision | Family Member Recall | Family Member F1 | Family Member Number | Medication Precision | Medication Recall | Medication F1 | Medication Number | Procedure Precision | Procedure Recall | Procedure F1 | Procedure Number | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy | |:-------------:|:-----:|:----:|:---------------:|:-------------------:|:----------------:|:------------:|:----------------:|:-----------------:|:--------------:|:----------:|:--------------:|:-----------------------:|:--------------------:|:----------------:|:--------------------:|:--------------------:|:-----------------:|:-------------:|:-----------------:|:-------------------:|:----------------:|:------------:|:----------------:|:-----------------:|:--------------:|:----------:|:----------------:| | 0.4243 | 1.0 | 1004 | 0.2935 | 0.5910 | 0.6998 | 0.6408 | 413 | 0.6784 | 0.6944 | 0.6863 | 975 | 0.8 | 0.8 | 0.8000 | 30 | 0.6882 | 0.6882 | 0.6882 | 93 | 0.6050 | 0.5466 | 0.5743 | 311 | 0.6473 | 0.6718 | 0.6593 | 0.9052 | | 0.2348 | 2.0 | 2008 | 0.2843 | 0.6644 | 0.7143 | 0.6884 | 413 | 0.7251 | 0.7303 | 0.7276 | 975 | 0.8065 | 0.8333 | 0.8197 | 30 | 0.7778 | 0.6774 | 0.7241 | 93 | 0.5763 | 0.5949 | 0.5854 | 311 | 0.6885 | 0.7025 | 0.6955 | 0.9146 | ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3

grace-pro/afriberta-small-finetuned-hausa

grace-pro

2023-07-10T19:21:16Z

105

0

transformers

[ "transformers", "pytorch", "tensorboard", "xlm-roberta", "token-classification", "generated_from_trainer", "autotrain_compatible", "endpoints_compatible", "region:us" ]

token-classification

2023-07-10T18:52:05Z

--- tags: - generated_from_trainer metrics: - precision - recall - f1 - accuracy model-index: - name: afriberta-small-finetuned-hausa results: [] ---  # afriberta-small-finetuned-hausa This model is a fine-tuned version of [castorini/afriberta_small](https://huggingface.co/castorini/afriberta_small) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.1444 - Precision: 0.6873 - Recall: 0.4713 - F1: 0.5592 - Accuracy: 0.9618 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 5 ### Training results | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:| | 0.1493 | 1.0 | 2624 | 0.1382 | 0.6423 | 0.3968 | 0.4905 | 0.9572 | | 0.1259 | 2.0 | 5248 | 0.1319 | 0.6734 | 0.4415 | 0.5333 | 0.9603 | | 0.106 | 3.0 | 7872 | 0.1385 | 0.6908 | 0.4502 | 0.5452 | 0.9611 | | 0.0949 | 4.0 | 10496 | 0.1377 | 0.6752 | 0.4759 | 0.5583 | 0.9613 | | 0.086 | 5.0 | 13120 | 0.1444 | 0.6873 | 0.4713 | 0.5592 | 0.9618 | ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3

jordyvl/vit-small_tobacco3482_kd_CEKD_t2.5_a0.5

jordyvl

2023-07-10T19:16:42Z

166

0

transformers

[ "transformers", "pytorch", "vit", "image-classification", "generated_from_trainer", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

image-classification

2023-07-10T18:37:44Z

--- license: apache-2.0 tags: - generated_from_trainer metrics: - accuracy model-index: - name: vit-small_tobacco3482_kd_CEKD_t2.5_a0.5 results: [] ---  # vit-small_tobacco3482_kd_CEKD_t2.5_a0.5 This model is a fine-tuned version of [WinKawaks/vit-small-patch16-224](https://huggingface.co/WinKawaks/vit-small-patch16-224) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.4300 - Accuracy: 0.83 - Brier Loss: 0.2807 - Nll: 1.0350 - F1 Micro: 0.83 - F1 Macro: 0.8295 - Ece: 0.2287 - Aurc: 0.0560 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 100 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | Brier Loss | Nll | F1 Micro | F1 Macro | Ece | Aurc | |:-------------:|:-----:|:----:|:---------------:|:--------:|:----------:|:------:|:--------:|:--------:|:------:|:------:| | No log | 1.0 | 7 | 1.6525 | 0.225 | 0.8757 | 5.3231 | 0.225 | 0.1387 | 0.2689 | 0.6977 | | No log | 2.0 | 14 | 1.3106 | 0.405 | 0.7470 | 3.3487 | 0.405 | 0.2195 | 0.2936 | 0.4032 | | No log | 3.0 | 21 | 0.9127 | 0.585 | 0.5785 | 1.8686 | 0.585 | 0.5142 | 0.2974 | 0.2067 | | No log | 4.0 | 28 | 0.7280 | 0.715 | 0.4339 | 1.6780 | 0.715 | 0.6761 | 0.2672 | 0.1204 | | No log | 5.0 | 35 | 0.6523 | 0.775 | 0.3676 | 1.6537 | 0.775 | 0.7619 | 0.2554 | 0.0929 | | No log | 6.0 | 42 | 0.5888 | 0.785 | 0.3502 | 1.3926 | 0.785 | 0.7538 | 0.2277 | 0.0908 | | No log | 7.0 | 49 | 0.6113 | 0.805 | 0.3326 | 1.7118 | 0.805 | 0.7903 | 0.2428 | 0.0803 | | No log | 8.0 | 56 | 0.5404 | 0.785 | 0.3178 | 1.1557 | 0.785 | 0.7671 | 0.2183 | 0.0716 | | No log | 9.0 | 63 | 0.5380 | 0.82 | 0.3051 | 1.3231 | 0.82 | 0.8072 | 0.2168 | 0.0773 | | No log | 10.0 | 70 | 0.6035 | 0.775 | 0.3508 | 1.3888 | 0.775 | 0.7682 | 0.2191 | 0.0812 | | No log | 11.0 | 77 | 0.5473 | 0.795 | 0.3202 | 1.2622 | 0.795 | 0.7740 | 0.2303 | 0.0626 | | No log | 12.0 | 84 | 0.4860 | 0.825 | 0.2937 | 1.3575 | 0.825 | 0.8053 | 0.2392 | 0.0727 | | No log | 13.0 | 91 | 0.5046 | 0.81 | 0.3032 | 1.1857 | 0.81 | 0.8086 | 0.2248 | 0.0564 | | No log | 14.0 | 98 | 0.4745 | 0.825 | 0.2870 | 1.2338 | 0.825 | 0.8089 | 0.2441 | 0.0518 | | No log | 15.0 | 105 | 0.4764 | 0.81 | 0.2943 | 1.0325 | 0.81 | 0.8110 | 0.1935 | 0.0556 | | No log | 16.0 | 112 | 0.4918 | 0.81 | 0.3062 | 1.0551 | 0.81 | 0.8015 | 0.2198 | 0.0587 | | No log | 17.0 | 119 | 0.4757 | 0.815 | 0.2970 | 1.4203 | 0.815 | 0.7965 | 0.2263 | 0.0850 | | No log | 18.0 | 126 | 0.4586 | 0.825 | 0.2926 | 1.0361 | 0.825 | 0.8268 | 0.2279 | 0.0583 | | No log | 19.0 | 133 | 0.4503 | 0.835 | 0.2855 | 1.1476 | 0.835 | 0.8301 | 0.2392 | 0.0589 | | No log | 20.0 | 140 | 0.4780 | 0.805 | 0.3105 | 0.9928 | 0.805 | 0.7902 | 0.1988 | 0.0775 | | No log | 21.0 | 147 | 0.4965 | 0.8 | 0.3205 | 1.1887 | 0.8000 | 0.8029 | 0.2410 | 0.0702 | | No log | 22.0 | 154 | 0.4753 | 0.815 | 0.3016 | 0.9609 | 0.815 | 0.8169 | 0.2163 | 0.0580 | | No log | 23.0 | 161 | 0.4733 | 0.8 | 0.3074 | 1.2566 | 0.8000 | 0.8001 | 0.2162 | 0.0704 | | No log | 24.0 | 168 | 0.4472 | 0.815 | 0.2888 | 1.0352 | 0.815 | 0.8187 | 0.2317 | 0.0590 | | No log | 25.0 | 175 | 0.4434 | 0.815 | 0.2854 | 0.9874 | 0.815 | 0.8186 | 0.2149 | 0.0554 | | No log | 26.0 | 182 | 0.4316 | 0.82 | 0.2754 | 1.0477 | 0.82 | 0.8267 | 0.2195 | 0.0508 | | No log | 27.0 | 189 | 0.4276 | 0.83 | 0.2751 | 1.1016 | 0.83 | 0.8336 | 0.2050 | 0.0525 | | No log | 28.0 | 196 | 0.4329 | 0.82 | 0.2795 | 1.0537 | 0.82 | 0.8220 | 0.2158 | 0.0611 | | No log | 29.0 | 203 | 0.4327 | 0.82 | 0.2827 | 1.1766 | 0.82 | 0.8237 | 0.2024 | 0.0603 | | No log | 30.0 | 210 | 0.4317 | 0.82 | 0.2820 | 1.0331 | 0.82 | 0.8219 | 0.2083 | 0.0611 | | No log | 31.0 | 217 | 0.4316 | 0.82 | 0.2803 | 1.0974 | 0.82 | 0.8263 | 0.1984 | 0.0575 | | No log | 32.0 | 224 | 0.4340 | 0.82 | 0.2833 | 1.0384 | 0.82 | 0.8240 | 0.2202 | 0.0590 | | No log | 33.0 | 231 | 0.4333 | 0.81 | 0.2824 | 1.0355 | 0.81 | 0.8160 | 0.2103 | 0.0586 | | No log | 34.0 | 238 | 0.4309 | 0.83 | 0.2817 | 1.1015 | 0.83 | 0.8307 | 0.2107 | 0.0577 | | No log | 35.0 | 245 | 0.4321 | 0.82 | 0.2817 | 1.0359 | 0.82 | 0.8229 | 0.2147 | 0.0590 | | No log | 36.0 | 252 | 0.4304 | 0.825 | 0.2802 | 1.1016 | 0.825 | 0.8257 | 0.2137 | 0.0569 | | No log | 37.0 | 259 | 0.4303 | 0.825 | 0.2811 | 1.0990 | 0.825 | 0.8268 | 0.2149 | 0.0581 | | No log | 38.0 | 266 | 0.4314 | 0.825 | 0.2814 | 1.1003 | 0.825 | 0.8257 | 0.2163 | 0.0581 | | No log | 39.0 | 273 | 0.4302 | 0.82 | 0.2806 | 1.1007 | 0.82 | 0.8226 | 0.2102 | 0.0576 | | No log | 40.0 | 280 | 0.4307 | 0.825 | 0.2809 | 1.0376 | 0.825 | 0.8264 | 0.2049 | 0.0573 | | No log | 41.0 | 287 | 0.4303 | 0.82 | 0.2808 | 1.0434 | 0.82 | 0.8226 | 0.2096 | 0.0574 | | No log | 42.0 | 294 | 0.4310 | 0.825 | 0.2817 | 1.0376 | 0.825 | 0.8268 | 0.2140 | 0.0580 | | No log | 43.0 | 301 | 0.4310 | 0.825 | 0.2813 | 1.0391 | 0.825 | 0.8257 | 0.2147 | 0.0580 | | No log | 44.0 | 308 | 0.4301 | 0.825 | 0.2808 | 1.0389 | 0.825 | 0.8257 | 0.2064 | 0.0573 | | No log | 45.0 | 315 | 0.4305 | 0.83 | 0.2811 | 1.0419 | 0.83 | 0.8307 | 0.2300 | 0.0577 | | No log | 46.0 | 322 | 0.4303 | 0.82 | 0.2808 | 1.0423 | 0.82 | 0.8226 | 0.2197 | 0.0582 | | No log | 47.0 | 329 | 0.4304 | 0.825 | 0.2811 | 1.0405 | 0.825 | 0.8257 | 0.2240 | 0.0580 | | No log | 48.0 | 336 | 0.4300 | 0.82 | 0.2805 | 1.0407 | 0.82 | 0.8226 | 0.2105 | 0.0574 | | No log | 49.0 | 343 | 0.4307 | 0.825 | 0.2812 | 1.0381 | 0.825 | 0.8257 | 0.2252 | 0.0577 | | No log | 50.0 | 350 | 0.4304 | 0.82 | 0.2810 | 1.0422 | 0.82 | 0.8226 | 0.2353 | 0.0578 | | No log | 51.0 | 357 | 0.4310 | 0.825 | 0.2813 | 1.0382 | 0.825 | 0.8264 | 0.2153 | 0.0569 | | No log | 52.0 | 364 | 0.4309 | 0.82 | 0.2814 | 1.0380 | 0.82 | 0.8226 | 0.2282 | 0.0574 | | No log | 53.0 | 371 | 0.4307 | 0.825 | 0.2813 | 1.0357 | 0.825 | 0.8264 | 0.2250 | 0.0568 | | No log | 54.0 | 378 | 0.4305 | 0.82 | 0.2810 | 1.0366 | 0.82 | 0.8226 | 0.2284 | 0.0575 | | No log | 55.0 | 385 | 0.4304 | 0.825 | 0.2811 | 1.0351 | 0.825 | 0.8264 | 0.2241 | 0.0566 | | No log | 56.0 | 392 | 0.4308 | 0.825 | 0.2813 | 1.0369 | 0.825 | 0.8257 | 0.2414 | 0.0572 | | No log | 57.0 | 399 | 0.4305 | 0.825 | 0.2810 | 1.0356 | 0.825 | 0.8257 | 0.2322 | 0.0571 | | No log | 58.0 | 406 | 0.4302 | 0.82 | 0.2808 | 1.0359 | 0.82 | 0.8226 | 0.2368 | 0.0569 | | No log | 59.0 | 413 | 0.4302 | 0.82 | 0.2809 | 1.0346 | 0.82 | 0.8226 | 0.2271 | 0.0569 | | No log | 60.0 | 420 | 0.4303 | 0.82 | 0.2809 | 1.0357 | 0.82 | 0.8226 | 0.2272 | 0.0570 | | No log | 61.0 | 427 | 0.4304 | 0.825 | 0.2810 | 1.0360 | 0.825 | 0.8257 | 0.2325 | 0.0569 | | No log | 62.0 | 434 | 0.4303 | 0.825 | 0.2809 | 1.0360 | 0.825 | 0.8257 | 0.2321 | 0.0568 | | No log | 63.0 | 441 | 0.4303 | 0.83 | 0.2809 | 1.0356 | 0.83 | 0.8295 | 0.2300 | 0.0562 | | No log | 64.0 | 448 | 0.4304 | 0.825 | 0.2810 | 1.0347 | 0.825 | 0.8264 | 0.2242 | 0.0564 | | No log | 65.0 | 455 | 0.4301 | 0.83 | 0.2808 | 1.0361 | 0.83 | 0.8295 | 0.2384 | 0.0564 | | No log | 66.0 | 462 | 0.4303 | 0.83 | 0.2810 | 1.0359 | 0.83 | 0.8295 | 0.2293 | 0.0563 | | No log | 67.0 | 469 | 0.4302 | 0.83 | 0.2809 | 1.0360 | 0.83 | 0.8295 | 0.2386 | 0.0564 | | No log | 68.0 | 476 | 0.4304 | 0.83 | 0.2810 | 1.0360 | 0.83 | 0.8295 | 0.2384 | 0.0563 | | No log | 69.0 | 483 | 0.4305 | 0.83 | 0.2812 | 1.0355 | 0.83 | 0.8295 | 0.2295 | 0.0564 | | No log | 70.0 | 490 | 0.4302 | 0.825 | 0.2808 | 1.0354 | 0.825 | 0.8264 | 0.2239 | 0.0561 | | No log | 71.0 | 497 | 0.4305 | 0.83 | 0.2812 | 1.0352 | 0.83 | 0.8295 | 0.2296 | 0.0564 | | 0.1776 | 72.0 | 504 | 0.4303 | 0.83 | 0.2808 | 1.0356 | 0.83 | 0.8295 | 0.2287 | 0.0561 | | 0.1776 | 73.0 | 511 | 0.4301 | 0.825 | 0.2807 | 1.0351 | 0.825 | 0.8264 | 0.2348 | 0.0563 | | 0.1776 | 74.0 | 518 | 0.4304 | 0.83 | 0.2811 | 1.0353 | 0.83 | 0.8295 | 0.2195 | 0.0562 | | 0.1776 | 75.0 | 525 | 0.4301 | 0.825 | 0.2808 | 1.0355 | 0.825 | 0.8257 | 0.2320 | 0.0568 | | 0.1776 | 76.0 | 532 | 0.4302 | 0.83 | 0.2808 | 1.0348 | 0.83 | 0.8295 | 0.2289 | 0.0561 | | 0.1776 | 77.0 | 539 | 0.4301 | 0.83 | 0.2808 | 1.0355 | 0.83 | 0.8295 | 0.2300 | 0.0562 | | 0.1776 | 78.0 | 546 | 0.4301 | 0.83 | 0.2808 | 1.0354 | 0.83 | 0.8295 | 0.2394 | 0.0563 | | 0.1776 | 79.0 | 553 | 0.4302 | 0.83 | 0.2809 | 1.0346 | 0.83 | 0.8295 | 0.2287 | 0.0560 | | 0.1776 | 80.0 | 560 | 0.4302 | 0.83 | 0.2809 | 1.0353 | 0.83 | 0.8295 | 0.2299 | 0.0563 | | 0.1776 | 81.0 | 567 | 0.4302 | 0.83 | 0.2809 | 1.0350 | 0.83 | 0.8295 | 0.2299 | 0.0563 | | 0.1776 | 82.0 | 574 | 0.4302 | 0.83 | 0.2808 | 1.0354 | 0.83 | 0.8295 | 0.2298 | 0.0560 | | 0.1776 | 83.0 | 581 | 0.4302 | 0.83 | 0.2809 | 1.0350 | 0.83 | 0.8295 | 0.2299 | 0.0561 | | 0.1776 | 84.0 | 588 | 0.4299 | 0.83 | 0.2807 | 1.0352 | 0.83 | 0.8295 | 0.2287 | 0.0561 | | 0.1776 | 85.0 | 595 | 0.4301 | 0.83 | 0.2808 | 1.0349 | 0.83 | 0.8295 | 0.2296 | 0.0562 | | 0.1776 | 86.0 | 602 | 0.4301 | 0.83 | 0.2808 | 1.0351 | 0.83 | 0.8295 | 0.2287 | 0.0562 | | 0.1776 | 87.0 | 609 | 0.4300 | 0.83 | 0.2807 | 1.0351 | 0.83 | 0.8295 | 0.2297 | 0.0561 | | 0.1776 | 88.0 | 616 | 0.4300 | 0.83 | 0.2807 | 1.0349 | 0.83 | 0.8295 | 0.2287 | 0.0562 | | 0.1776 | 89.0 | 623 | 0.4300 | 0.83 | 0.2807 | 1.0353 | 0.83 | 0.8295 | 0.2296 | 0.0560 | | 0.1776 | 90.0 | 630 | 0.4300 | 0.83 | 0.2807 | 1.0349 | 0.83 | 0.8295 | 0.2297 | 0.0559 | | 0.1776 | 91.0 | 637 | 0.4300 | 0.83 | 0.2807 | 1.0352 | 0.83 | 0.8295 | 0.2296 | 0.0562 | | 0.1776 | 92.0 | 644 | 0.4300 | 0.83 | 0.2807 | 1.0351 | 0.83 | 0.8295 | 0.2287 | 0.0561 | | 0.1776 | 93.0 | 651 | 0.4300 | 0.83 | 0.2807 | 1.0351 | 0.83 | 0.8295 | 0.2297 | 0.0562 | | 0.1776 | 94.0 | 658 | 0.4300 | 0.83 | 0.2807 | 1.0349 | 0.83 | 0.8295 | 0.2297 | 0.0560 | | 0.1776 | 95.0 | 665 | 0.4300 | 0.83 | 0.2807 | 1.0350 | 0.83 | 0.8295 | 0.2297 | 0.0562 | | 0.1776 | 96.0 | 672 | 0.4300 | 0.83 | 0.2807 | 1.0349 | 0.83 | 0.8295 | 0.2296 | 0.0561 | | 0.1776 | 97.0 | 679 | 0.4300 | 0.83 | 0.2807 | 1.0350 | 0.83 | 0.8295 | 0.2296 | 0.0560 | | 0.1776 | 98.0 | 686 | 0.4300 | 0.83 | 0.2807 | 1.0350 | 0.83 | 0.8295 | 0.2296 | 0.0560 | | 0.1776 | 99.0 | 693 | 0.4300 | 0.83 | 0.2807 | 1.0350 | 0.83 | 0.8295 | 0.2287 | 0.0560 | | 0.1776 | 100.0 | 700 | 0.4300 | 0.83 | 0.2807 | 1.0350 | 0.83 | 0.8295 | 0.2287 | 0.0560 | ### Framework versions - Transformers 4.26.1 - Pytorch 1.13.1.post200 - Datasets 2.9.0 - Tokenizers 0.13.2

NasimB/gpt2-dp-all-mod-datasets-rarity-all-iorder-13k-2p6k

NasimB

2023-07-10T19:10:16Z

5

0

transformers

[ "transformers", "pytorch", "gpt2", "text-generation", "generated_from_trainer", "dataset:generator", "license:mit", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]

text-generation

2023-07-10T16:50:38Z

--- license: mit tags: - generated_from_trainer datasets: - generator model-index: - name: gpt2-dp-all-mod-datasets-rarity-all-iorder-13k-2p6k results: [] ---  # gpt2-dp-all-mod-datasets-rarity-all-iorder-13k-2p6k This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the generator dataset. It achieves the following results on the evaluation set: - Loss: 4.4226 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 64 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_steps: 1000 - num_epochs: 7 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:-----:|:---------------:| | 6.7606 | 0.29 | 500 | 5.6940 | | 5.4347 | 0.59 | 1000 | 5.2560 | | 5.0945 | 0.88 | 1500 | 5.0226 | | 4.8232 | 1.18 | 2000 | 4.8777 | | 4.675 | 1.47 | 2500 | 4.7626 | | 4.5767 | 1.77 | 3000 | 4.6625 | | 4.4488 | 2.06 | 3500 | 4.5933 | | 4.2612 | 2.36 | 4000 | 4.5563 | | 4.245 | 2.65 | 4500 | 4.4882 | | 4.208 | 2.94 | 5000 | 4.4332 | | 3.9773 | 3.24 | 5500 | 4.4362 | | 3.9484 | 3.53 | 6000 | 4.4046 | | 3.9304 | 3.83 | 6500 | 4.3669 | | 3.7943 | 4.12 | 7000 | 4.3731 | | 3.6517 | 4.42 | 7500 | 4.3646 | | 3.646 | 4.71 | 8000 | 4.3456 | | 3.6381 | 5.01 | 8500 | 4.3333 | | 3.3812 | 5.3 | 9000 | 4.3586 | | 3.3875 | 5.59 | 9500 | 4.3536 | | 3.3847 | 5.89 | 10000 | 4.3483 | | 3.2816 | 6.18 | 10500 | 4.3600 | | 3.2295 | 6.48 | 11000 | 4.3636 | | 3.223 | 6.77 | 11500 | 4.3630 | ### Framework versions - Transformers 4.26.1 - Pytorch 1.11.0+cu113 - Datasets 2.13.0 - Tokenizers 0.13.3

aphi/ppo-SnowballTarget

aphi

2023-07-10T19:08:24Z

0

ml-agents

[ "ml-agents", "tensorboard", "onnx", "SnowballTarget", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-SnowballTarget", "region:us" ]

reinforcement-learning

2023-07-10T19:08:17Z

--- library_name: ml-agents tags: - SnowballTarget - deep-reinforcement-learning - reinforcement-learning - ML-Agents-SnowballTarget --- # **ppo** Agent playing **SnowballTarget** This is a trained model of a **ppo** agent playing **SnowballTarget** using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents). ## Usage (with ML-Agents) The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/ We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub: - A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction - A *longer tutorial* to understand how works ML-Agents: https://huggingface.co/learn/deep-rl-course/unit5/introduction ### Resume the training ```bash mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume ``` ### Watch your Agent play You can watch your agent **playing directly in your browser** 1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity 2. Step 1: Find your model_id: aphi/ppo-SnowballTarget 3. Step 2: Select your *.nn /*.onnx file 4. Click on Watch the agent play 👀

MaitreHibou/Reinforce-Cartpole-v1

MaitreHibou

2023-07-10T18:49:32Z

0

null

[ "CartPole-v1", "reinforce", "reinforcement-learning", "custom-implementation", "deep-rl-class", "model-index", "region:us" ]

reinforcement-learning

2023-07-10T18:49:23Z

--- tags: - CartPole-v1 - reinforce - reinforcement-learning - custom-implementation - deep-rl-class model-index: - name: Reinforce-Cartpole-v1 results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: CartPole-v1 type: CartPole-v1 metrics: - type: mean_reward value: 500.00 +/- 0.00 name: mean_reward verified: false --- # **Reinforce** Agent playing **CartPole-v1** This is a trained model of a **Reinforce** agent playing **CartPole-v1** . To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction

grace-pro/afriberta-base-finetuned-hausa

grace-pro

2023-07-10T18:48:53Z

124

0

transformers

[ "transformers", "pytorch", "tensorboard", "xlm-roberta", "token-classification", "generated_from_trainer", "autotrain_compatible", "endpoints_compatible", "region:us" ]

token-classification

2023-07-10T17:58:10Z

--- tags: - generated_from_trainer metrics: - precision - recall - f1 - accuracy model-index: - name: afriberta-base-finetuned-hausa results: [] ---  # afriberta-base-finetuned-hausa This model is a fine-tuned version of [castorini/afriberta_base](https://huggingface.co/castorini/afriberta_base) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.1401 - Precision: 0.7156 - Recall: 0.5251 - F1: 0.6057 - Accuracy: 0.9655 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 5 ### Training results | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:| | 0.1381 | 1.0 | 2624 | 0.1277 | 0.6804 | 0.4403 | 0.5346 | 0.9607 | | 0.1113 | 2.0 | 5248 | 0.1198 | 0.6803 | 0.4994 | 0.5760 | 0.9628 | | 0.0861 | 3.0 | 7872 | 0.1270 | 0.7102 | 0.5052 | 0.5904 | 0.9645 | | 0.0723 | 4.0 | 10496 | 0.1322 | 0.7188 | 0.5134 | 0.5990 | 0.9654 | | 0.0602 | 5.0 | 13120 | 0.1401 | 0.7156 | 0.5251 | 0.6057 | 0.9655 | ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3

DavidSolan0/coverart

DavidSolan0

2023-07-10T18:34:53Z

9

0

diffusers

[ "diffusers", "safetensors", "text-to-image", "stable-diffusion", "license:creativeml-openrail-m", "autotrain_compatible", "endpoints_compatible", "diffusers:StableDiffusionPipeline", "region:us" ]

text-to-image

2023-07-10T18:30:01Z

--- license: creativeml-openrail-m tags: - text-to-image - stable-diffusion --- ### coverart Dreambooth model trained by DavidSolan0 with [TheLastBen's fast-DreamBooth](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast-DreamBooth.ipynb) notebook Test the concept via A1111 Colab [fast-Colab-A1111](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast_stable_diffusion_AUTOMATIC1111.ipynb) Sample pictures of this concept:

simonestradasch/COMPner-bert-base-spanish-wwm-cased

simonestradasch

2023-07-10T18:28:38Z

107

0

transformers

[ "transformers", "tensorboard", "safetensors", "bert", "token-classification", "generated_from_trainer", "es", "dataset:simonestradasch/NERcomp", "autotrain_compatible", "endpoints_compatible", "region:us" ]

token-classification

2023-07-10T18:07:06Z

--- language: - es tags: - generated_from_trainer datasets: - simonestradasch/NERcomp model-index: - name: COMPner-bert-base-spanish-wwm-cased results: [] ---  # COMPner-bert-base-spanish-wwm-cased This model is a fine-tuned version of [dccuchile/bert-base-spanish-wwm-cased](https://huggingface.co/dccuchile/bert-base-spanish-wwm-cased) on the simonestradasch/NERcomp dataset. It achieves the following results on the evaluation set: - Loss: 0.2793 - Body Part Precision: 0.6700 - Body Part Recall: 0.7186 - Body Part F1: 0.6934 - Body Part Number: 565 - Disease Precision: 0.6966 - Disease Recall: 0.7533 - Disease F1: 0.7238 - Disease Number: 1350 - Family Member Precision: 0.9 - Family Member Recall: 0.75 - Family Member F1: 0.8182 - Family Member Number: 24 - Medication Precision: 0.7143 - Medication Recall: 0.6190 - Medication F1: 0.6633 - Medication Number: 105 - Procedure Precision: 0.5233 - Procedure Recall: 0.5125 - Procedure F1: 0.5178 - Procedure Number: 439 - Overall Precision: 0.6640 - Overall Recall: 0.6971 - Overall F1: 0.6802 - Overall Accuracy: 0.9136 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 13 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 2 ### Training results | Training Loss | Epoch | Step | Validation Loss | Body Part Precision | Body Part Recall | Body Part F1 | Body Part Number | Disease Precision | Disease Recall | Disease F1 | Disease Number | Family Member Precision | Family Member Recall | Family Member F1 | Family Member Number | Medication Precision | Medication Recall | Medication F1 | Medication Number | Procedure Precision | Procedure Recall | Procedure F1 | Procedure Number | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy | |:-------------:|:-----:|:----:|:---------------:|:-------------------:|:----------------:|:------------:|:----------------:|:-----------------:|:--------------:|:----------:|:--------------:|:-----------------------:|:--------------------:|:----------------:|:--------------------:|:--------------------:|:-----------------:|:-------------:|:-----------------:|:-------------------:|:----------------:|:------------:|:----------------:|:-----------------:|:--------------:|:----------:|:----------------:| | 0.4741 | 1.0 | 703 | 0.2932 | 0.6449 | 0.6301 | 0.6374 | 565 | 0.6984 | 0.7170 | 0.7076 | 1350 | 0.9412 | 0.6667 | 0.7805 | 24 | 0.8551 | 0.5619 | 0.6782 | 105 | 0.5113 | 0.3599 | 0.4225 | 439 | 0.6674 | 0.6271 | 0.6466 | 0.9091 | | 0.259 | 2.0 | 1406 | 0.2793 | 0.6700 | 0.7186 | 0.6934 | 565 | 0.6966 | 0.7533 | 0.7238 | 1350 | 0.9 | 0.75 | 0.8182 | 24 | 0.7143 | 0.6190 | 0.6633 | 105 | 0.5233 | 0.5125 | 0.5178 | 439 | 0.6640 | 0.6971 | 0.6802 | 0.9136 | ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3

BrendaScar/ppo-LunarLander-v2

BrendaScar

2023-07-10T18:24:25Z

0

stable-baselines3

[ "stable-baselines3", "LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]

reinforcement-learning

2023-07-10T18:24:03Z

--- library_name: stable-baselines3 tags: - LunarLander-v2 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: PPO results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: LunarLander-v2 type: LunarLander-v2 metrics: - type: mean_reward value: 248.77 +/- 20.04 name: mean_reward verified: false --- # **PPO** Agent playing **LunarLander-v2** This is a trained model of a **PPO** agent playing **LunarLander-v2** using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3). ## Usage (with Stable-baselines3) TODO: Add your code ```python from stable_baselines3 import ... from huggingface_sb3 import load_from_hub ... ```

MaitreHibou/dqn-SpaceInvadersNoFrameskip-v4

MaitreHibou

2023-07-10T18:21:47Z

2

0

stable-baselines3

[ "stable-baselines3", "SpaceInvadersNoFrameskip-v4", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]

reinforcement-learning

2023-07-10T18:21:06Z

--- library_name: stable-baselines3 tags: - SpaceInvadersNoFrameskip-v4 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: DQN results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: SpaceInvadersNoFrameskip-v4 type: SpaceInvadersNoFrameskip-v4 metrics: - type: mean_reward value: 656.50 +/- 140.98 name: mean_reward verified: false --- # **DQN** Agent playing **SpaceInvadersNoFrameskip-v4** This is a trained model of a **DQN** agent playing **SpaceInvadersNoFrameskip-v4** using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3) and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo). The RL Zoo is a training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included. ## Usage (with SB3 RL Zoo) RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/> SB3: https://github.com/DLR-RM/stable-baselines3<br/> SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib Install the RL Zoo (with SB3 and SB3-Contrib): ```bash pip install rl_zoo3 ``` ``` # Download model and save it into the logs/ folder python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga MaitreHibou -f logs/ python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ ``` If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do: ``` python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga MaitreHibou -f logs/ python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ ``` ## Training (with the RL Zoo) ``` python -m rl_zoo3.train --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ # Upload the model and generate video (when possible) python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga MaitreHibou ``` ## Hyperparameters ```python OrderedDict([('batch_size', 64), ('buffer_size', 100000), ('env_wrapper', ['stable_baselines3.common.atari_wrappers.AtariWrapper']), ('exploration_final_eps', 0.01), ('exploration_fraction', 0.1), ('frame_stack', 4), ('gradient_steps', 1), ('learning_rate', 0.0002), ('learning_starts', 100000), ('n_timesteps', 1000000.0), ('optimize_memory_usage', False), ('policy', 'CnnPolicy'), ('target_update_interval', 1000), ('train_freq', 4), ('normalize', False)]) ``` # Environment Arguments ```python {'render_mode': 'rgb_array'} ```

FerhatDk/wav2vec2-base-finetuned-ks

FerhatDk

2023-07-10T18:08:04Z

4

0

transformers

[ "transformers", "pytorch", "tensorboard", "wav2vec2", "audio-classification", "generated_from_trainer", "license:apache-2.0", "endpoints_compatible", "region:us" ]

audio-classification

2022-09-22T08:59:01Z

--- license: apache-2.0 tags: - generated_from_trainer metrics: - accuracy model-index: - name: wav2vec2-base-finetuned-ks results: [] ---  # wav2vec2-base-finetuned-ks This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.3550 - Accuracy: 0.8727 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_ratio: 0.1 - lr_scheduler_warmup_steps: 500 - num_epochs: 25 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------:| | No log | 1.0 | 8 | 0.6840 | 0.6 | | 0.6867 | 2.0 | 16 | 0.6780 | 0.6364 | | 0.6742 | 3.0 | 24 | 0.6601 | 0.6182 | | 0.6446 | 4.0 | 32 | 0.6294 | 0.6364 | | 0.6299 | 5.0 | 40 | 0.6002 | 0.6727 | | 0.6299 | 6.0 | 48 | 0.5755 | 0.7091 | | 0.6021 | 7.0 | 56 | 0.5530 | 0.7273 | | 0.5678 | 8.0 | 64 | 0.5036 | 0.8182 | | 0.5512 | 9.0 | 72 | 0.4753 | 0.8545 | | 0.4784 | 10.0 | 80 | 0.4184 | 0.9273 | | 0.4784 | 11.0 | 88 | 0.4102 | 0.8909 | | 0.4515 | 12.0 | 96 | 0.4444 | 0.8182 | | 0.4878 | 13.0 | 104 | 0.3780 | 0.9091 | | 0.4418 | 14.0 | 112 | 0.4570 | 0.8 | | 0.4746 | 15.0 | 120 | 0.3870 | 0.8545 | | 0.4746 | 16.0 | 128 | 0.3932 | 0.8364 | | 0.4226 | 17.0 | 136 | 0.2779 | 0.9636 | | 0.4301 | 18.0 | 144 | 0.3125 | 0.9455 | | 0.3482 | 19.0 | 152 | 0.3212 | 0.9091 | | 0.3611 | 20.0 | 160 | 0.3925 | 0.8364 | | 0.3611 | 21.0 | 168 | 0.3389 | 0.8909 | | 0.3507 | 22.0 | 176 | 0.3099 | 0.8727 | | 0.3241 | 23.0 | 184 | 0.3120 | 0.8727 | | 0.2533 | 24.0 | 192 | 0.2313 | 0.9455 | | 0.2466 | 25.0 | 200 | 0.3550 | 0.8727 | ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3

jordyvl/vit-small_tobacco3482_kd_CEKD_t1.5_a0.7

jordyvl

2023-07-10T17:57:06Z

166

0

transformers

[ "transformers", "pytorch", "vit", "image-classification", "generated_from_trainer", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

image-classification

2023-07-10T17:18:33Z

--- license: apache-2.0 tags: - generated_from_trainer metrics: - accuracy model-index: - name: vit-small_tobacco3482_kd_CEKD_t1.5_a0.7 results: [] ---  # vit-small_tobacco3482_kd_CEKD_t1.5_a0.7 This model is a fine-tuned version of [WinKawaks/vit-small-patch16-224](https://huggingface.co/WinKawaks/vit-small-patch16-224) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.4797 - Accuracy: 0.835 - Brier Loss: 0.2522 - Nll: 0.8627 - F1 Micro: 0.835 - F1 Macro: 0.8222 - Ece: 0.1830 - Aurc: 0.0434 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 100 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | Brier Loss | Nll | F1 Micro | F1 Macro | Ece | Aurc | |:-------------:|:-----:|:----:|:---------------:|:--------:|:----------:|:------:|:--------:|:--------:|:------:|:------:| | No log | 1.0 | 7 | 1.9341 | 0.215 | 0.8749 | 5.3238 | 0.2150 | 0.1264 | 0.2642 | 0.6914 | | No log | 2.0 | 14 | 1.5320 | 0.405 | 0.7410 | 3.5078 | 0.405 | 0.2276 | 0.2957 | 0.4015 | | No log | 3.0 | 21 | 1.0532 | 0.635 | 0.5629 | 2.0153 | 0.635 | 0.5844 | 0.3037 | 0.2006 | | No log | 4.0 | 28 | 0.7915 | 0.715 | 0.4093 | 1.6974 | 0.715 | 0.6762 | 0.2420 | 0.1131 | | No log | 5.0 | 35 | 0.8024 | 0.745 | 0.3869 | 1.7109 | 0.745 | 0.7548 | 0.2160 | 0.1006 | | No log | 6.0 | 42 | 0.7162 | 0.765 | 0.3351 | 1.8105 | 0.765 | 0.7599 | 0.2216 | 0.0874 | | No log | 7.0 | 49 | 0.6966 | 0.785 | 0.3304 | 1.5292 | 0.785 | 0.7682 | 0.2058 | 0.0979 | | No log | 8.0 | 56 | 0.6317 | 0.805 | 0.2995 | 1.3486 | 0.805 | 0.7887 | 0.2266 | 0.0721 | | No log | 9.0 | 63 | 0.6903 | 0.805 | 0.3304 | 1.5866 | 0.805 | 0.7971 | 0.2371 | 0.0995 | | No log | 10.0 | 70 | 0.6223 | 0.805 | 0.2940 | 1.3478 | 0.805 | 0.8114 | 0.2281 | 0.0697 | | No log | 11.0 | 77 | 0.6350 | 0.795 | 0.3145 | 1.3386 | 0.795 | 0.7730 | 0.2063 | 0.0962 | | No log | 12.0 | 84 | 0.5570 | 0.835 | 0.2666 | 1.2662 | 0.835 | 0.8181 | 0.1951 | 0.0553 | | No log | 13.0 | 91 | 0.5610 | 0.81 | 0.2858 | 1.2619 | 0.81 | 0.8002 | 0.1884 | 0.0626 | | No log | 14.0 | 98 | 0.5843 | 0.8 | 0.2961 | 1.0782 | 0.8000 | 0.8083 | 0.1993 | 0.0683 | | No log | 15.0 | 105 | 0.5918 | 0.78 | 0.2965 | 1.1207 | 0.78 | 0.7861 | 0.1895 | 0.0634 | | No log | 16.0 | 112 | 0.5541 | 0.84 | 0.2765 | 1.3189 | 0.8400 | 0.8455 | 0.1969 | 0.0597 | | No log | 17.0 | 119 | 0.5037 | 0.835 | 0.2568 | 0.9024 | 0.835 | 0.8248 | 0.2083 | 0.0499 | | No log | 18.0 | 126 | 0.5050 | 0.85 | 0.2563 | 1.0032 | 0.85 | 0.8441 | 0.2147 | 0.0580 | | No log | 19.0 | 133 | 0.5430 | 0.815 | 0.2779 | 1.1046 | 0.815 | 0.8044 | 0.1906 | 0.0562 | | No log | 20.0 | 140 | 0.5276 | 0.84 | 0.2743 | 0.9964 | 0.8400 | 0.8144 | 0.2104 | 0.0597 | | No log | 21.0 | 147 | 0.5155 | 0.835 | 0.2686 | 0.9556 | 0.835 | 0.8210 | 0.1962 | 0.0572 | | No log | 22.0 | 154 | 0.4937 | 0.835 | 0.2581 | 1.0079 | 0.835 | 0.8172 | 0.1975 | 0.0479 | | No log | 23.0 | 161 | 0.4931 | 0.845 | 0.2533 | 1.0021 | 0.845 | 0.8270 | 0.1884 | 0.0503 | | No log | 24.0 | 168 | 0.4869 | 0.83 | 0.2554 | 0.9660 | 0.83 | 0.8084 | 0.1945 | 0.0481 | | No log | 25.0 | 175 | 0.4843 | 0.845 | 0.2512 | 0.9979 | 0.845 | 0.8316 | 0.1746 | 0.0466 | | No log | 26.0 | 182 | 0.4866 | 0.835 | 0.2531 | 0.9006 | 0.835 | 0.8188 | 0.1833 | 0.0472 | | No log | 27.0 | 189 | 0.4882 | 0.825 | 0.2562 | 0.8929 | 0.825 | 0.8043 | 0.2023 | 0.0469 | | No log | 28.0 | 196 | 0.4814 | 0.82 | 0.2494 | 0.9122 | 0.82 | 0.8060 | 0.1773 | 0.0451 | | No log | 29.0 | 203 | 0.4749 | 0.835 | 0.2501 | 0.8770 | 0.835 | 0.8252 | 0.1688 | 0.0442 | | No log | 30.0 | 210 | 0.4761 | 0.84 | 0.2490 | 0.8848 | 0.8400 | 0.8250 | 0.2068 | 0.0443 | | No log | 31.0 | 217 | 0.4787 | 0.845 | 0.2508 | 0.8754 | 0.845 | 0.8309 | 0.1635 | 0.0438 | | No log | 32.0 | 224 | 0.4791 | 0.835 | 0.2521 | 0.8711 | 0.835 | 0.8224 | 0.1876 | 0.0446 | | No log | 33.0 | 231 | 0.4779 | 0.84 | 0.2509 | 0.8650 | 0.8400 | 0.8252 | 0.1813 | 0.0436 | | No log | 34.0 | 238 | 0.4774 | 0.84 | 0.2513 | 0.8662 | 0.8400 | 0.8252 | 0.1919 | 0.0441 | | No log | 35.0 | 245 | 0.4760 | 0.835 | 0.2502 | 0.8636 | 0.835 | 0.8224 | 0.1840 | 0.0434 | | No log | 36.0 | 252 | 0.4784 | 0.84 | 0.2509 | 0.8688 | 0.8400 | 0.8281 | 0.1691 | 0.0437 | | No log | 37.0 | 259 | 0.4771 | 0.835 | 0.2507 | 0.8670 | 0.835 | 0.8224 | 0.1936 | 0.0440 | | No log | 38.0 | 266 | 0.4764 | 0.835 | 0.2499 | 0.8614 | 0.835 | 0.8224 | 0.1830 | 0.0434 | | No log | 39.0 | 273 | 0.4769 | 0.835 | 0.2503 | 0.8651 | 0.835 | 0.8224 | 0.2001 | 0.0438 | | No log | 40.0 | 280 | 0.4777 | 0.84 | 0.2514 | 0.8608 | 0.8400 | 0.8281 | 0.1832 | 0.0435 | | No log | 41.0 | 287 | 0.4777 | 0.835 | 0.2504 | 0.8650 | 0.835 | 0.8224 | 0.1953 | 0.0437 | | No log | 42.0 | 294 | 0.4779 | 0.835 | 0.2511 | 0.8629 | 0.835 | 0.8224 | 0.1944 | 0.0440 | | No log | 43.0 | 301 | 0.4790 | 0.835 | 0.2519 | 0.8631 | 0.835 | 0.8222 | 0.1808 | 0.0439 | | No log | 44.0 | 308 | 0.4777 | 0.835 | 0.2509 | 0.8604 | 0.835 | 0.8222 | 0.1886 | 0.0435 | | No log | 45.0 | 315 | 0.4787 | 0.835 | 0.2517 | 0.8620 | 0.835 | 0.8222 | 0.1940 | 0.0437 | | No log | 46.0 | 322 | 0.4774 | 0.84 | 0.2509 | 0.8614 | 0.8400 | 0.8281 | 0.1779 | 0.0433 | | No log | 47.0 | 329 | 0.4785 | 0.835 | 0.2517 | 0.8609 | 0.835 | 0.8222 | 0.1811 | 0.0438 | | No log | 48.0 | 336 | 0.4792 | 0.835 | 0.2521 | 0.8611 | 0.835 | 0.8222 | 0.1849 | 0.0436 | | No log | 49.0 | 343 | 0.4771 | 0.84 | 0.2509 | 0.8623 | 0.8400 | 0.8281 | 0.1908 | 0.0430 | | No log | 50.0 | 350 | 0.4793 | 0.835 | 0.2520 | 0.8633 | 0.835 | 0.8222 | 0.1900 | 0.0435 | | No log | 51.0 | 357 | 0.4786 | 0.83 | 0.2517 | 0.8654 | 0.83 | 0.8159 | 0.1684 | 0.0437 | | No log | 52.0 | 364 | 0.4792 | 0.83 | 0.2521 | 0.8625 | 0.83 | 0.8166 | 0.1915 | 0.0430 | | No log | 53.0 | 371 | 0.4785 | 0.835 | 0.2513 | 0.8652 | 0.835 | 0.8222 | 0.1853 | 0.0434 | | No log | 54.0 | 378 | 0.4798 | 0.835 | 0.2523 | 0.8652 | 0.835 | 0.8222 | 0.1767 | 0.0437 | | No log | 55.0 | 385 | 0.4791 | 0.835 | 0.2519 | 0.8637 | 0.835 | 0.8222 | 0.1891 | 0.0435 | | No log | 56.0 | 392 | 0.4790 | 0.835 | 0.2519 | 0.8614 | 0.835 | 0.8222 | 0.1749 | 0.0429 | | No log | 57.0 | 399 | 0.4782 | 0.835 | 0.2513 | 0.8625 | 0.835 | 0.8222 | 0.1909 | 0.0433 | | No log | 58.0 | 406 | 0.4794 | 0.835 | 0.2521 | 0.8602 | 0.835 | 0.8222 | 0.1758 | 0.0435 | | No log | 59.0 | 413 | 0.4790 | 0.835 | 0.2517 | 0.8617 | 0.835 | 0.8222 | 0.1754 | 0.0432 | | No log | 60.0 | 420 | 0.4791 | 0.835 | 0.2520 | 0.8614 | 0.835 | 0.8222 | 0.1830 | 0.0430 | | No log | 61.0 | 427 | 0.4789 | 0.835 | 0.2518 | 0.8612 | 0.835 | 0.8222 | 0.1870 | 0.0432 | | No log | 62.0 | 434 | 0.4792 | 0.835 | 0.2520 | 0.8620 | 0.835 | 0.8222 | 0.1902 | 0.0433 | | No log | 63.0 | 441 | 0.4789 | 0.835 | 0.2518 | 0.8619 | 0.835 | 0.8222 | 0.1997 | 0.0431 | | No log | 64.0 | 448 | 0.4797 | 0.835 | 0.2523 | 0.8607 | 0.835 | 0.8222 | 0.1833 | 0.0434 | | No log | 65.0 | 455 | 0.4797 | 0.835 | 0.2522 | 0.8624 | 0.835 | 0.8222 | 0.1922 | 0.0434 | | No log | 66.0 | 462 | 0.4791 | 0.835 | 0.2519 | 0.8620 | 0.835 | 0.8222 | 0.1894 | 0.0430 | | No log | 67.0 | 469 | 0.4792 | 0.835 | 0.2520 | 0.8612 | 0.835 | 0.8222 | 0.1885 | 0.0433 | | No log | 68.0 | 476 | 0.4796 | 0.835 | 0.2522 | 0.8627 | 0.835 | 0.8222 | 0.1918 | 0.0433 | | No log | 69.0 | 483 | 0.4793 | 0.835 | 0.2521 | 0.8628 | 0.835 | 0.8222 | 0.1828 | 0.0433 | | No log | 70.0 | 490 | 0.4792 | 0.835 | 0.2519 | 0.8622 | 0.835 | 0.8222 | 0.1918 | 0.0432 | | No log | 71.0 | 497 | 0.4797 | 0.835 | 0.2523 | 0.8615 | 0.835 | 0.8222 | 0.1836 | 0.0434 | | 0.194 | 72.0 | 504 | 0.4797 | 0.835 | 0.2522 | 0.8618 | 0.835 | 0.8222 | 0.1842 | 0.0433 | | 0.194 | 73.0 | 511 | 0.4794 | 0.835 | 0.2521 | 0.8624 | 0.835 | 0.8222 | 0.1914 | 0.0432 | | 0.194 | 74.0 | 518 | 0.4794 | 0.835 | 0.2521 | 0.8617 | 0.835 | 0.8222 | 0.1915 | 0.0431 | | 0.194 | 75.0 | 525 | 0.4796 | 0.835 | 0.2522 | 0.8623 | 0.835 | 0.8222 | 0.1917 | 0.0434 | | 0.194 | 76.0 | 532 | 0.4795 | 0.835 | 0.2520 | 0.8622 | 0.835 | 0.8222 | 0.1985 | 0.0433 | | 0.194 | 77.0 | 539 | 0.4795 | 0.835 | 0.2520 | 0.8623 | 0.835 | 0.8222 | 0.1985 | 0.0432 | | 0.194 | 78.0 | 546 | 0.4795 | 0.835 | 0.2522 | 0.8621 | 0.835 | 0.8222 | 0.1981 | 0.0432 | | 0.194 | 79.0 | 553 | 0.4798 | 0.835 | 0.2522 | 0.8626 | 0.835 | 0.8222 | 0.1909 | 0.0433 | | 0.194 | 80.0 | 560 | 0.4796 | 0.835 | 0.2521 | 0.8630 | 0.835 | 0.8222 | 0.1984 | 0.0433 | | 0.194 | 81.0 | 567 | 0.4797 | 0.835 | 0.2522 | 0.8619 | 0.835 | 0.8222 | 0.1902 | 0.0434 | | 0.194 | 82.0 | 574 | 0.4797 | 0.835 | 0.2522 | 0.8631 | 0.835 | 0.8222 | 0.1913 | 0.0433 | | 0.194 | 83.0 | 581 | 0.4797 | 0.835 | 0.2522 | 0.8627 | 0.835 | 0.8222 | 0.1909 | 0.0433 | | 0.194 | 84.0 | 588 | 0.4797 | 0.835 | 0.2522 | 0.8623 | 0.835 | 0.8222 | 0.1909 | 0.0433 | | 0.194 | 85.0 | 595 | 0.4797 | 0.835 | 0.2522 | 0.8624 | 0.835 | 0.8222 | 0.1909 | 0.0434 | | 0.194 | 86.0 | 602 | 0.4796 | 0.835 | 0.2522 | 0.8623 | 0.835 | 0.8222 | 0.1830 | 0.0433 | | 0.194 | 87.0 | 609 | 0.4797 | 0.835 | 0.2522 | 0.8629 | 0.835 | 0.8222 | 0.1909 | 0.0434 | | 0.194 | 88.0 | 616 | 0.4797 | 0.835 | 0.2521 | 0.8634 | 0.835 | 0.8222 | 0.1830 | 0.0433 | | 0.194 | 89.0 | 623 | 0.4797 | 0.835 | 0.2522 | 0.8627 | 0.835 | 0.8222 | 0.1910 | 0.0434 | | 0.194 | 90.0 | 630 | 0.4798 | 0.835 | 0.2523 | 0.8627 | 0.835 | 0.8222 | 0.1909 | 0.0434 | | 0.194 | 91.0 | 637 | 0.4797 | 0.835 | 0.2522 | 0.8625 | 0.835 | 0.8222 | 0.1909 | 0.0434 | | 0.194 | 92.0 | 644 | 0.4797 | 0.835 | 0.2522 | 0.8630 | 0.835 | 0.8222 | 0.1830 | 0.0434 | | 0.194 | 93.0 | 651 | 0.4798 | 0.835 | 0.2522 | 0.8629 | 0.835 | 0.8222 | 0.1910 | 0.0434 | | 0.194 | 94.0 | 658 | 0.4797 | 0.835 | 0.2522 | 0.8628 | 0.835 | 0.8222 | 0.1910 | 0.0434 | | 0.194 | 95.0 | 665 | 0.4797 | 0.835 | 0.2522 | 0.8627 | 0.835 | 0.8222 | 0.1910 | 0.0434 | | 0.194 | 96.0 | 672 | 0.4798 | 0.835 | 0.2522 | 0.8627 | 0.835 | 0.8222 | 0.1834 | 0.0435 | | 0.194 | 97.0 | 679 | 0.4797 | 0.835 | 0.2522 | 0.8628 | 0.835 | 0.8222 | 0.1830 | 0.0434 | | 0.194 | 98.0 | 686 | 0.4797 | 0.835 | 0.2522 | 0.8628 | 0.835 | 0.8222 | 0.1830 | 0.0434 | | 0.194 | 99.0 | 693 | 0.4797 | 0.835 | 0.2522 | 0.8628 | 0.835 | 0.8222 | 0.1830 | 0.0434 | | 0.194 | 100.0 | 700 | 0.4797 | 0.835 | 0.2522 | 0.8627 | 0.835 | 0.8222 | 0.1830 | 0.0434 | ### Framework versions - Transformers 4.26.1 - Pytorch 1.13.1.post200 - Datasets 2.9.0 - Tokenizers 0.13.2

FerhatDk/wav2vec2-base_music_speech_both_classification

FerhatDk

2023-07-10T17:56:34Z

167

0

transformers

[ "transformers", "pytorch", "tensorboard", "wav2vec2", "audio-classification", "generated_from_trainer", "license:apache-2.0", "endpoints_compatible", "region:us" ]

audio-classification

2023-07-10T17:00:30Z

--- license: apache-2.0 tags: - generated_from_trainer metrics: - accuracy model-index: - name: wav2vec2-base_music_speech_both_classification results: [] ---  # wav2vec2-base_music_speech_both_classification This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.0586 - Accuracy: 0.9847 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_ratio: 0.1 - lr_scheduler_warmup_steps: 500 - num_epochs: 8 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------:| | 0.9458 | 1.0 | 66 | 0.8468 | 0.7405 | | 0.3785 | 2.0 | 132 | 0.2951 | 0.9771 | | 0.1762 | 3.0 | 198 | 0.2639 | 0.9313 | | 0.134 | 4.0 | 264 | 0.1084 | 0.9771 | | 0.0782 | 5.0 | 330 | 0.0877 | 0.9771 | | 0.0568 | 6.0 | 396 | 0.0912 | 0.9771 | | 0.0122 | 7.0 | 462 | 0.4056 | 0.9198 | | 0.059 | 8.0 | 528 | 0.0586 | 0.9847 | ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3

grammarly/detexd-roberta-base

grammarly

2023-07-10T17:34:23Z

132

10

transformers

[ "transformers", "pytorch", "roberta", "text-classification", "en", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

text-classification

2023-03-21T18:44:55Z

--- license: apache-2.0 language: - en pipeline_tag: text-classification --- # DeTexD-RoBERTa-base delicate text detection This is a baseline RoBERTa-base model for the delicate text detection task. * Paper: [DeTexD: A Benchmark Dataset for Delicate Text Detection](TODO) * [GitHub repository](https://github.com/grammarly/detexd) The labels meaning according to the paper: - LABEL_0 -> non-delicate (0) - LABEL_1 -> very low risk (1) - LABEL_2 -> low risk (2) - LABEL_3 -> medium risk (3) - LABEL_4 -> high risk (4) - LABEL_5 -> very high risk (5) ## Classification example code Here's a short usage example with the torch library in a binary classification task: ```python from transformers import pipeline classifier = pipeline("text-classification", model="grammarly/detexd-roberta-base") def predict_binary_score(text: str): # get multiclass probability scores scores = classifier(text, top_k=None) # convert to a single score by summing the probability scores # for the higher-index classes return sum(score['score'] for score in scores if score['label'] in ('LABEL_3', 'LABEL_4', 'LABEL_5')) def predict_delicate(text: str, threshold=0.72496545): return predict_binary_score(text) > threshold print(predict_delicate("Time flies like an arrow. Fruit flies like a banana.")) ``` Expected output: ``` False ``` ## Citation Information ``` @inproceedings{chernodub-etal-2023-detexd, title = "{D}e{T}ex{D}: A Benchmark Dataset for Delicate Text Detection", author = "Yavnyi, Serhii and Sliusarenko, Oleksii and Razzaghi, Jade and Mo, Yichen and Hovakimyan, Knar and Chernodub, Artem", booktitle = "The 7th Workshop on Online Abuse and Harms (WOAH)", month = jul, year = "2023", address = "Toronto, Canada", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2023.woah-1.2", pages = "14--28", abstract = "Over the past few years, much research has been conducted to identify and regulate toxic language. However, few studies have addressed a broader range of sensitive texts that are not necessarily overtly toxic. In this paper, we introduce and define a new category of sensitive text called {``}delicate text.{''} We provide the taxonomy of delicate text and present a detailed annotation scheme. We annotate DeTexD, the first benchmark dataset for delicate text detection. The significance of the difference in the definitions is highlighted by the relative performance deltas between models trained each definitions and corpora and evaluated on the other. We make publicly available the DeTexD Benchmark dataset, annotation guidelines, and baseline model for delicate text detection.", } ```

AmbarB12/my_awesome_model

AmbarB12

2023-07-10T17:30:33Z

62

0

transformers

[ "transformers", "tf", "distilbert", "text-classification", "generated_from_keras_callback", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

text-classification

2023-07-09T18:03:55Z

--- license: apache-2.0 tags: - generated_from_keras_callback model-index: - name: AmbarB12/my_awesome_model results: [] ---  # AmbarB12/my_awesome_model This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset. It achieves the following results on the evaluation set: - Train Loss: 0.0631 - Validation Loss: 0.2229 - Train Accuracy: 0.9306 - Epoch: 2 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 7810, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False} - training_precision: float32 ### Training results | Train Loss | Validation Loss | Train Accuracy | Epoch | |:----------:|:---------------:|:--------------:|:-----:| | 0.2523 | 0.1891 | 0.927 | 0 | | 0.1327 | 0.2007 | 0.9298 | 1 | | 0.0631 | 0.2229 | 0.9306 | 2 | ### Framework versions - Transformers 4.30.2 - TensorFlow 2.12.0 - Datasets 2.13.1 - Tokenizers 0.13.3

cagarraz/rl_course_vizdoom_health_gathering_supreme

cagarraz

2023-07-10T17:23:21Z

0

sample-factory

[ "sample-factory", "tensorboard", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]

reinforcement-learning

2023-07-10T17:23:08Z

--- library_name: sample-factory tags: - deep-reinforcement-learning - reinforcement-learning - sample-factory model-index: - name: APPO results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: doom_health_gathering_supreme type: doom_health_gathering_supreme metrics: - type: mean_reward value: 3.94 +/- 0.20 name: mean_reward verified: false --- A(n) **APPO** model trained on the **doom_health_gathering_supreme** environment. This model was trained using Sample-Factory 2.0: https://github.com/alex-petrenko/sample-factory. Documentation for how to use Sample-Factory can be found at https://www.samplefactory.dev/ ## Downloading the model After installing Sample-Factory, download the model with: ``` python -m sample_factory.huggingface.load_from_hub -r cagarraz/rl_course_vizdoom_health_gathering_supreme ``` ## Using the model To run the model after download, use the `enjoy` script corresponding to this environment: ``` python -m .usr.local.lib.python3.10.dist-packages.ipykernel_launcher --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme ``` You can also upload models to the Hugging Face Hub using the same script with the `--push_to_hub` flag. See https://www.samplefactory.dev/10-huggingface/huggingface/ for more details ## Training with this model To continue training with this model, use the `train` script corresponding to this environment: ``` python -m .usr.local.lib.python3.10.dist-packages.ipykernel_launcher --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme --restart_behavior=resume --train_for_env_steps=10000000000 ``` Note, you may have to adjust `--train_for_env_steps` to a suitably high number as the experiment will resume at the number of steps it concluded at.

jordyvl/vit-small_tobacco3482_kd_CEKD_t1.5_a0.5

jordyvl

2023-07-10T17:17:44Z

163

0

transformers

[ "transformers", "pytorch", "vit", "image-classification", "generated_from_trainer", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

image-classification

2023-07-10T16:39:33Z

--- license: apache-2.0 tags: - generated_from_trainer metrics: - accuracy model-index: - name: vit-small_tobacco3482_kd_CEKD_t1.5_a0.5 results: [] ---  # vit-small_tobacco3482_kd_CEKD_t1.5_a0.5 This model is a fine-tuned version of [WinKawaks/vit-small-patch16-224](https://huggingface.co/WinKawaks/vit-small-patch16-224) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.4258 - Accuracy: 0.825 - Brier Loss: 0.2707 - Nll: 0.8867 - F1 Micro: 0.825 - F1 Macro: 0.8116 - Ece: 0.2129 - Aurc: 0.0681 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 100 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | Brier Loss | Nll | F1 Micro | F1 Macro | Ece | Aurc | |:-------------:|:-----:|:----:|:---------------:|:--------:|:----------:|:------:|:--------:|:--------:|:------:|:------:| | No log | 1.0 | 7 | 1.7307 | 0.22 | 0.8748 | 5.3766 | 0.22 | 0.1294 | 0.2444 | 0.6913 | | No log | 2.0 | 14 | 1.3514 | 0.405 | 0.7426 | 3.5573 | 0.405 | 0.2280 | 0.2900 | 0.4026 | | No log | 3.0 | 21 | 0.9121 | 0.62 | 0.5647 | 1.9398 | 0.62 | 0.5595 | 0.2879 | 0.2015 | | No log | 4.0 | 28 | 0.7084 | 0.695 | 0.4179 | 1.7042 | 0.695 | 0.6379 | 0.2305 | 0.1177 | | No log | 5.0 | 35 | 0.7167 | 0.735 | 0.3862 | 1.7929 | 0.735 | 0.7392 | 0.2380 | 0.1046 | | No log | 6.0 | 42 | 0.6442 | 0.765 | 0.3625 | 1.5688 | 0.765 | 0.7549 | 0.2371 | 0.1034 | | No log | 7.0 | 49 | 0.6147 | 0.805 | 0.3410 | 1.5975 | 0.805 | 0.7789 | 0.2438 | 0.1042 | | No log | 8.0 | 56 | 0.6444 | 0.775 | 0.3446 | 1.2309 | 0.775 | 0.7725 | 0.2305 | 0.0911 | | No log | 9.0 | 63 | 0.5964 | 0.8 | 0.3219 | 1.3613 | 0.8000 | 0.7784 | 0.2446 | 0.0734 | | No log | 10.0 | 70 | 0.5700 | 0.82 | 0.3160 | 1.2605 | 0.82 | 0.7860 | 0.2301 | 0.0632 | | No log | 11.0 | 77 | 0.5663 | 0.79 | 0.3176 | 1.2939 | 0.79 | 0.7643 | 0.2315 | 0.0666 | | No log | 12.0 | 84 | 0.5111 | 0.825 | 0.3143 | 1.1082 | 0.825 | 0.8082 | 0.2519 | 0.0844 | | No log | 13.0 | 91 | 0.5228 | 0.78 | 0.3156 | 0.9444 | 0.78 | 0.7773 | 0.1941 | 0.0650 | | No log | 14.0 | 98 | 0.5792 | 0.78 | 0.3409 | 1.5054 | 0.78 | 0.7725 | 0.2061 | 0.1019 | | No log | 15.0 | 105 | 0.4905 | 0.83 | 0.2912 | 1.0068 | 0.83 | 0.8266 | 0.2324 | 0.0545 | | No log | 16.0 | 112 | 0.4990 | 0.825 | 0.2961 | 1.1452 | 0.825 | 0.8140 | 0.2188 | 0.0632 | | No log | 17.0 | 119 | 0.4900 | 0.805 | 0.2940 | 1.2027 | 0.805 | 0.8018 | 0.2188 | 0.0860 | | No log | 18.0 | 126 | 0.4755 | 0.805 | 0.2988 | 1.0223 | 0.805 | 0.7789 | 0.2229 | 0.0792 | | No log | 19.0 | 133 | 0.4398 | 0.81 | 0.2679 | 0.9732 | 0.81 | 0.7830 | 0.2085 | 0.0585 | | No log | 20.0 | 140 | 0.4766 | 0.805 | 0.2992 | 0.9730 | 0.805 | 0.7934 | 0.2141 | 0.0662 | | No log | 21.0 | 147 | 0.4615 | 0.835 | 0.2867 | 0.9343 | 0.835 | 0.8219 | 0.1999 | 0.0751 | | No log | 22.0 | 154 | 0.4343 | 0.825 | 0.2641 | 1.1353 | 0.825 | 0.8070 | 0.2095 | 0.0603 | | No log | 23.0 | 161 | 0.4291 | 0.85 | 0.2660 | 1.0109 | 0.85 | 0.8365 | 0.2435 | 0.0615 | | No log | 24.0 | 168 | 0.4263 | 0.855 | 0.2653 | 0.9395 | 0.855 | 0.8440 | 0.2445 | 0.0623 | | No log | 25.0 | 175 | 0.4338 | 0.845 | 0.2700 | 0.8794 | 0.845 | 0.8349 | 0.2254 | 0.0584 | | No log | 26.0 | 182 | 0.4305 | 0.835 | 0.2648 | 0.9062 | 0.835 | 0.8322 | 0.2113 | 0.0658 | | No log | 27.0 | 189 | 0.4262 | 0.84 | 0.2683 | 0.9967 | 0.8400 | 0.8291 | 0.2240 | 0.0670 | | No log | 28.0 | 196 | 0.4329 | 0.83 | 0.2724 | 0.9016 | 0.83 | 0.8239 | 0.2016 | 0.0685 | | No log | 29.0 | 203 | 0.4233 | 0.845 | 0.2653 | 0.9115 | 0.845 | 0.8375 | 0.2005 | 0.0634 | | No log | 30.0 | 210 | 0.4204 | 0.84 | 0.2638 | 0.8892 | 0.8400 | 0.8348 | 0.2175 | 0.0633 | | No log | 31.0 | 217 | 0.4240 | 0.83 | 0.2684 | 0.8871 | 0.83 | 0.8217 | 0.2128 | 0.0660 | | No log | 32.0 | 224 | 0.4246 | 0.84 | 0.2677 | 0.8867 | 0.8400 | 0.8307 | 0.2117 | 0.0670 | | No log | 33.0 | 231 | 0.4247 | 0.83 | 0.2690 | 0.8917 | 0.83 | 0.8202 | 0.2084 | 0.0679 | | No log | 34.0 | 238 | 0.4218 | 0.84 | 0.2660 | 0.8848 | 0.8400 | 0.8326 | 0.2138 | 0.0663 | | No log | 35.0 | 245 | 0.4220 | 0.845 | 0.2667 | 0.8926 | 0.845 | 0.8354 | 0.2109 | 0.0655 | | No log | 36.0 | 252 | 0.4247 | 0.83 | 0.2694 | 0.8854 | 0.83 | 0.8202 | 0.2213 | 0.0683 | | No log | 37.0 | 259 | 0.4239 | 0.84 | 0.2683 | 0.8849 | 0.8400 | 0.8326 | 0.2163 | 0.0670 | | No log | 38.0 | 266 | 0.4239 | 0.835 | 0.2689 | 0.8876 | 0.835 | 0.8208 | 0.2118 | 0.0672 | | No log | 39.0 | 273 | 0.4252 | 0.83 | 0.2696 | 0.8885 | 0.83 | 0.8180 | 0.2064 | 0.0682 | | No log | 40.0 | 280 | 0.4237 | 0.835 | 0.2686 | 0.8867 | 0.835 | 0.8208 | 0.2211 | 0.0675 | | No log | 41.0 | 287 | 0.4256 | 0.83 | 0.2700 | 0.8847 | 0.83 | 0.8180 | 0.2253 | 0.0682 | | No log | 42.0 | 294 | 0.4243 | 0.835 | 0.2692 | 0.8839 | 0.835 | 0.8208 | 0.2130 | 0.0675 | | No log | 43.0 | 301 | 0.4248 | 0.83 | 0.2695 | 0.8850 | 0.83 | 0.8180 | 0.2237 | 0.0682 | | No log | 44.0 | 308 | 0.4246 | 0.83 | 0.2694 | 0.8847 | 0.83 | 0.8180 | 0.2383 | 0.0680 | | No log | 45.0 | 315 | 0.4253 | 0.83 | 0.2699 | 0.8858 | 0.83 | 0.8180 | 0.2200 | 0.0681 | | No log | 46.0 | 322 | 0.4246 | 0.83 | 0.2694 | 0.8857 | 0.83 | 0.8180 | 0.2311 | 0.0679 | | No log | 47.0 | 329 | 0.4253 | 0.83 | 0.2700 | 0.8843 | 0.83 | 0.8180 | 0.2312 | 0.0682 | | No log | 48.0 | 336 | 0.4252 | 0.83 | 0.2698 | 0.8830 | 0.83 | 0.8180 | 0.2177 | 0.0682 | | No log | 49.0 | 343 | 0.4257 | 0.83 | 0.2703 | 0.8848 | 0.83 | 0.8180 | 0.2315 | 0.0683 | | No log | 50.0 | 350 | 0.4256 | 0.83 | 0.2703 | 0.8833 | 0.83 | 0.8180 | 0.2331 | 0.0684 | | No log | 51.0 | 357 | 0.4254 | 0.83 | 0.2703 | 0.8863 | 0.83 | 0.8180 | 0.2422 | 0.0681 | | No log | 52.0 | 364 | 0.4261 | 0.83 | 0.2707 | 0.8864 | 0.83 | 0.8180 | 0.2424 | 0.0683 | | No log | 53.0 | 371 | 0.4249 | 0.83 | 0.2700 | 0.8855 | 0.83 | 0.8180 | 0.2195 | 0.0679 | | No log | 54.0 | 378 | 0.4255 | 0.83 | 0.2704 | 0.8846 | 0.83 | 0.8180 | 0.2342 | 0.0682 | | No log | 55.0 | 385 | 0.4256 | 0.825 | 0.2704 | 0.8861 | 0.825 | 0.8116 | 0.2357 | 0.0682 | | No log | 56.0 | 392 | 0.4264 | 0.83 | 0.2708 | 0.8853 | 0.83 | 0.8180 | 0.2345 | 0.0682 | | No log | 57.0 | 399 | 0.4257 | 0.825 | 0.2706 | 0.8864 | 0.825 | 0.8116 | 0.2353 | 0.0682 | | No log | 58.0 | 406 | 0.4258 | 0.825 | 0.2704 | 0.8841 | 0.825 | 0.8116 | 0.2271 | 0.0681 | | No log | 59.0 | 413 | 0.4255 | 0.825 | 0.2703 | 0.8856 | 0.825 | 0.8116 | 0.2267 | 0.0680 | | No log | 60.0 | 420 | 0.4259 | 0.825 | 0.2709 | 0.8842 | 0.825 | 0.8116 | 0.2269 | 0.0683 | | No log | 61.0 | 427 | 0.4254 | 0.83 | 0.2702 | 0.8852 | 0.83 | 0.8180 | 0.2265 | 0.0680 | | No log | 62.0 | 434 | 0.4261 | 0.83 | 0.2707 | 0.8851 | 0.83 | 0.8180 | 0.2346 | 0.0682 | | No log | 63.0 | 441 | 0.4257 | 0.825 | 0.2704 | 0.8854 | 0.825 | 0.8116 | 0.2232 | 0.0682 | | No log | 64.0 | 448 | 0.4261 | 0.825 | 0.2708 | 0.8845 | 0.825 | 0.8116 | 0.2264 | 0.0683 | | No log | 65.0 | 455 | 0.4259 | 0.825 | 0.2706 | 0.8862 | 0.825 | 0.8116 | 0.2204 | 0.0682 | | No log | 66.0 | 462 | 0.4258 | 0.825 | 0.2707 | 0.8856 | 0.825 | 0.8116 | 0.2193 | 0.0682 | | No log | 67.0 | 469 | 0.4255 | 0.83 | 0.2703 | 0.8852 | 0.83 | 0.8180 | 0.2190 | 0.0681 | | No log | 68.0 | 476 | 0.4260 | 0.825 | 0.2708 | 0.8860 | 0.825 | 0.8116 | 0.2196 | 0.0682 | | No log | 69.0 | 483 | 0.4259 | 0.825 | 0.2708 | 0.8858 | 0.825 | 0.8116 | 0.2195 | 0.0682 | | No log | 70.0 | 490 | 0.4255 | 0.825 | 0.2703 | 0.8857 | 0.825 | 0.8116 | 0.2135 | 0.0682 | | No log | 71.0 | 497 | 0.4258 | 0.825 | 0.2707 | 0.8857 | 0.825 | 0.8116 | 0.2205 | 0.0681 | | 0.1816 | 72.0 | 504 | 0.4261 | 0.825 | 0.2708 | 0.8857 | 0.825 | 0.8116 | 0.2198 | 0.0682 | | 0.1816 | 73.0 | 511 | 0.4259 | 0.825 | 0.2706 | 0.8852 | 0.825 | 0.8116 | 0.2192 | 0.0682 | | 0.1816 | 74.0 | 518 | 0.4259 | 0.825 | 0.2707 | 0.8856 | 0.825 | 0.8116 | 0.2290 | 0.0681 | | 0.1816 | 75.0 | 525 | 0.4257 | 0.825 | 0.2706 | 0.8864 | 0.825 | 0.8116 | 0.2337 | 0.0681 | | 0.1816 | 76.0 | 532 | 0.4259 | 0.825 | 0.2707 | 0.8855 | 0.825 | 0.8116 | 0.2211 | 0.0681 | | 0.1816 | 77.0 | 539 | 0.4255 | 0.825 | 0.2704 | 0.8860 | 0.825 | 0.8116 | 0.2137 | 0.0680 | | 0.1816 | 78.0 | 546 | 0.4258 | 0.825 | 0.2707 | 0.8868 | 0.825 | 0.8116 | 0.2274 | 0.0682 | | 0.1816 | 79.0 | 553 | 0.4260 | 0.825 | 0.2708 | 0.8859 | 0.825 | 0.8116 | 0.2209 | 0.0682 | | 0.1816 | 80.0 | 560 | 0.4260 | 0.825 | 0.2708 | 0.8864 | 0.825 | 0.8116 | 0.2135 | 0.0681 | | 0.1816 | 81.0 | 567 | 0.4259 | 0.825 | 0.2707 | 0.8859 | 0.825 | 0.8116 | 0.2134 | 0.0682 | | 0.1816 | 82.0 | 574 | 0.4258 | 0.825 | 0.2706 | 0.8862 | 0.825 | 0.8116 | 0.2062 | 0.0681 | | 0.1816 | 83.0 | 581 | 0.4259 | 0.825 | 0.2707 | 0.8866 | 0.825 | 0.8116 | 0.2204 | 0.0681 | | 0.1816 | 84.0 | 588 | 0.4259 | 0.825 | 0.2707 | 0.8868 | 0.825 | 0.8116 | 0.2204 | 0.0681 | | 0.1816 | 85.0 | 595 | 0.4257 | 0.825 | 0.2706 | 0.8861 | 0.825 | 0.8116 | 0.2141 | 0.0682 | | 0.1816 | 86.0 | 602 | 0.4258 | 0.825 | 0.2707 | 0.8861 | 0.825 | 0.8116 | 0.2140 | 0.0682 | | 0.1816 | 87.0 | 609 | 0.4258 | 0.825 | 0.2707 | 0.8867 | 0.825 | 0.8116 | 0.2137 | 0.0680 | | 0.1816 | 88.0 | 616 | 0.4259 | 0.825 | 0.2707 | 0.8866 | 0.825 | 0.8116 | 0.2129 | 0.0681 | | 0.1816 | 89.0 | 623 | 0.4258 | 0.825 | 0.2707 | 0.8866 | 0.825 | 0.8116 | 0.2205 | 0.0681 | | 0.1816 | 90.0 | 630 | 0.4259 | 0.825 | 0.2707 | 0.8865 | 0.825 | 0.8116 | 0.2053 | 0.0680 | | 0.1816 | 91.0 | 637 | 0.4258 | 0.825 | 0.2706 | 0.8868 | 0.825 | 0.8116 | 0.2130 | 0.0681 | | 0.1816 | 92.0 | 644 | 0.4258 | 0.825 | 0.2706 | 0.8870 | 0.825 | 0.8116 | 0.2129 | 0.0680 | | 0.1816 | 93.0 | 651 | 0.4258 | 0.825 | 0.2706 | 0.8868 | 0.825 | 0.8116 | 0.2129 | 0.0681 | | 0.1816 | 94.0 | 658 | 0.4258 | 0.825 | 0.2707 | 0.8867 | 0.825 | 0.8116 | 0.2129 | 0.0681 | | 0.1816 | 95.0 | 665 | 0.4258 | 0.825 | 0.2707 | 0.8867 | 0.825 | 0.8116 | 0.2053 | 0.0680 | | 0.1816 | 96.0 | 672 | 0.4259 | 0.825 | 0.2707 | 0.8866 | 0.825 | 0.8116 | 0.2053 | 0.0681 | | 0.1816 | 97.0 | 679 | 0.4258 | 0.825 | 0.2707 | 0.8868 | 0.825 | 0.8116 | 0.2129 | 0.0681 | | 0.1816 | 98.0 | 686 | 0.4258 | 0.825 | 0.2707 | 0.8868 | 0.825 | 0.8116 | 0.2129 | 0.0680 | | 0.1816 | 99.0 | 693 | 0.4258 | 0.825 | 0.2707 | 0.8868 | 0.825 | 0.8116 | 0.2129 | 0.0681 | | 0.1816 | 100.0 | 700 | 0.4258 | 0.825 | 0.2707 | 0.8867 | 0.825 | 0.8116 | 0.2129 | 0.0681 | ### Framework versions - Transformers 4.26.1 - Pytorch 1.13.1.post200 - Datasets 2.9.0 - Tokenizers 0.13.2

opendiffusion/sentimentcheck

opendiffusion

2023-07-10T16:58:49Z

0

tf-keras

[ "tf-keras", "bert", "region:us" ]

null

2023-05-11T18:26:04Z

# Intro OpenDiffusion's SentimentCheck is an AI model built upon Tensorflow+Keras+Pickles. SentimentCheck harnesses the power of deep learning algorithms to accurately classify sentiment in text, making it a flexible tool for businesses, researchers, and developers. ## Usage --- language: - en - nl - de - fr - it - es license: mit --- # bert-base-multilingual-uncased-sentiment This a bert-base-multilingual-uncased model finetuned for sentiment analysis on product reviews in six languages: English, Dutch, German, French, Spanish and Italian. It predicts the sentiment of the review as a number of stars (between 1 and 5). This model is intended for direct use as a sentiment analysis model for product reviews in any of the six languages above, or for further finetuning on related sentiment analysis tasks. ## Training data Here is the number of product reviews we used for finetuning the model: | Language | Number of reviews | | -------- | ----------------- | | English | 150k | | Dutch | 80k | | German | 137k | | French | 140k | | Italian | 72k | | Spanish | 50k | ## Accuracy The finetuned model obtained the following accuracy on 5,000 held-out product reviews in each of the languages: - Accuracy (exact) is the exact match on the number of stars. - Accuracy (off-by-1) is the percentage of reviews where the number of stars the model predicts differs by a maximum of 1 from the number given by the human reviewer. | Language | Accuracy (exact) | Accuracy (off-by-1) | | -------- | ---------------------- | ------------------- | | English | 67% | 95% | Dutch | 57% | 93% | German | 61% | 94% | French | 59% | 94% | Italian | 59% | 95% | Spanish | 58% | 95%

Umer1542/task-b-classification

Umer1542

2023-07-10T16:35:37Z

160

0

transformers

[ "transformers", "pytorch", "opt", "text-classification", "en", "license:other", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]

text-classification

2023-07-10T15:47:23Z

--- license: other language: - en metrics: - accuracy - f1 - recall pipeline_tag: text-classification ---

dashan1992/dsl2

dashan1992

2023-07-10T16:35:33Z

0

peft

[ "peft", "region:us" ]

null

2023-07-10T16:34:19Z

--- library_name: peft --- ## Training procedure The following `bitsandbytes` quantization config was used during training: - load_in_8bit: True - load_in_4bit: False - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: fp4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: float32 ### Framework versions - PEFT 0.4.0.dev0

yhyhy3/open_llama_7b_v2_med_instruct

yhyhy3

2023-07-10T16:22:39Z

1,461

8

transformers

[ "transformers", "pytorch", "llama", "text-generation", "medical", "code", "en", "dataset:ehartford/dolphin", "dataset:LinhDuong/chatdoctor-200k", "dataset:sahil2801/code_instructions_120k", "dataset:medalpaca/medical_meadow_mediqa", "dataset:kaiokendev/SuperCOT-dataset", "dataset:tiiuae/falcon-refinedweb", "dataset:bigcode/starcoderdata", "dataset:togethercomputer/RedPajama-Data-1T", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]

text-generation

2023-07-09T17:19:43Z

--- license: apache-2.0 datasets: - ehartford/dolphin - LinhDuong/chatdoctor-200k - sahil2801/code_instructions_120k - medalpaca/medical_meadow_mediqa - kaiokendev/SuperCOT-dataset - tiiuae/falcon-refinedweb - bigcode/starcoderdata - togethercomputer/RedPajama-Data-1T language: - en library_name: transformers pipeline_tag: text-generation tags: - medical - code --- # Model Card for Model ID  This model is an instruction-tuned Open LLaMa model with 7B parameters, with specialities in medical QA and code instruction. ## Model Details  - **Model type:** LlamaForCausalLM - **Language(s) (NLP):** English - **License:** Apache 2.0 - **Finetuned from model (QLoRA):** [openlm-research/open_llama_7b_v2](https://huggingface.co/openlm-research/open_llama_7b_v2) ## How to Get Started with the Model Use the code below to get started with the model. ```py import torch from transformers import LlamaTokenizer, LlamaForCausalLM model_path = 'yhyhy3/open_llama_7b_v2_med_dolphin_qlora_merged' tokenizer = LlamaTokenizer.from_pretrained(model_path) model = LlamaForCausalLM.from_pretrained( model_path, torch_dtype=torch.float16, device_map='auto', ) prompt = '''### Instruction: Answer the following question. ### Input: What is the capital of New Jersey? ### Response:''' input_ids = tokenizer(prompt, return_tensors="pt").input_ids generation_output = model.generate( input_ids=input_ids, max_new_tokens=32 ) print(tokenizer.decode(generation_output[0])) ``` ## Training Details ### Training Data Converted the following datasets to alpaca:instruction format. 1. [ehartford/dolphin](https://huggingface.co/datasets/ehartford/dolphin) - ORCA style dataset generously created by [Eric Hartford](https://huggingface.co/ehartford) - Only used the 1 million GPT4 generated instructions file [flan1m-alpaca-uncensored.jsonl](https://huggingface.co/datasets/ehartford/dolphin/blob/main/flan1m-alpaca-uncensored.jsonl). 2. [LinhDuong/chatdoctor-200k](https://huggingface.co/datasets/LinhDuong/chatdoctor-200k) - Refined dataset sourced from icliniq medical QA forum 3. [sahil2801/code_instructions_120k](https://huggingface.co/datasets/sahil2801/code_instructions_120k) - Code instruction dataset generously created by Sahil Chaudhary from ThreeSixty AI 4. [medalpaca/medical_meadow_mediqa](https://huggingface.co/datasets/medalpaca/medical_meadow_mediqa) - MEDIQA is a dataset of manually generated, question-driven summaries of multi and single document answers to consumer health questions from medalpaca group. 5. [kaiokendev/SuperCOT-dataset](https://huggingface.co/datasets/kaiokendev/SuperCOT-dataset) - Code instruction dataset generously created by Kaio Ken ### Training Procedure Trained using [axolotl](https://github.com/OpenAccess-AI-Collective/axolotl) QLoRa on [RunPod](https://www.runpod.io/console/gpu-cloud) 8x A6000 on Community Cloud for 3 epochs (~14 hours - ~$70). <details> <summary>axolotl training config:</summary> ```yaml base_model: openlm-research/open_llama_7b_v2 base_model_config: openlm-research/open_llama_7b_v2 model_type: LlamaForCausalLM tokenizer_type: LlamaTokenizer load_in_8bit: false load_in_4bit: true strict: false push_dataset_to_hub: hub_model_id: hf_use_auth_token: datasets: - path: json type: alpaca data_files: /disk/flan1m-alpaca-uncensored.jsonl shards: 8 - path: sahil2801/code_instructions_120k type: alpaca - path: LinhDuong/chatdoctor-200k type: alpaca shards: 2 - path: kaiokendev/SuperCOT-dataset type: alpaca - path: medalpaca/medical_meadow_mediqa type: alpaca dataset_prepared_path: last_run_prepared val_set_size: 0.01 adapter: qlora lora_model_dir: sequence_len: 2048 max_packed_sequence_len: 2048 lora_r: 8 lora_alpha: 32 lora_dropout: 0.05 lora_target_modules: lora_target_linear: true lora_fan_in_fan_out: wandb_mode: true wandb_project: wandb_watch: wandb_run_id: wandb_log_model: 'openllama_checkpoint' output_dir: /disk/open_llama_7b_v2_dolphin_qlora gradient_accumulation_steps: 2 micro_batch_size: 16 num_epochs: 3 optimizer: paged_adamw_32bit torchdistx_path: lr_scheduler: cosine learning_rate: 0.0002 train_on_inputs: false group_by_length: false bf16: true fp16: false tf32: true gradient_checkpointing: true early_stopping_patience: resume_from_checkpoint: local_rank: logging_steps: 1 xformers_attention: true flash_attention: gptq_groupsize: gptq_model_v1: warmup_steps: 1000 eval_steps: 5000 save_steps: debug: deepspeed: weight_decay: 0.0000001 fsdp: fsdp_config: special_tokens: bos_token: "<s>" eos_token: "</s>" unk_token: "<unk>" ``` </details>

Den4ikAI/paraphrase_detector

Den4ikAI

2023-07-10T16:13:56Z

2

0

sentence-transformers

[ "sentence-transformers", "pytorch", "bert", "feature-extraction", "sentence-similarity", "transformers", "autotrain_compatible", "text-embeddings-inference", "endpoints_compatible", "region:us" ]

sentence-similarity

2023-07-10T16:09:10Z

--- pipeline_tag: sentence-similarity tags: - sentence-transformers - feature-extraction - sentence-similarity - transformers --- # {MODEL_NAME} This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 312 dimensional dense vector space and can be used for tasks like clustering or semantic search.  ## Usage (Sentence-Transformers) Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed: ``` pip install -U sentence-transformers ``` Then you can use the model like this: ```python from sentence_transformers import SentenceTransformer sentences = ["This is an example sentence", "Each sentence is converted"] model = SentenceTransformer('{MODEL_NAME}') embeddings = model.encode(sentences) print(embeddings) ``` ## Usage (HuggingFace Transformers) Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings. ```python from transformers import AutoTokenizer, AutoModel import torch #Mean Pooling - Take attention mask into account for correct averaging def mean_pooling(model_output, attention_mask): token_embeddings = model_output[0] #First element of model_output contains all token embeddings input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float() return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9) # Sentences we want sentence embeddings for sentences = ['This is an example sentence', 'Each sentence is converted'] # Load model from HuggingFace Hub tokenizer = AutoTokenizer.from_pretrained('{MODEL_NAME}') model = AutoModel.from_pretrained('{MODEL_NAME}') # Tokenize sentences encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt') # Compute token embeddings with torch.no_grad(): model_output = model(**encoded_input) # Perform pooling. In this case, mean pooling. sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask']) print("Sentence embeddings:") print(sentence_embeddings) ``` ## Evaluation Results  For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME}) ## Training The model was trained with the parameters: **DataLoader**: `torch.utils.data.dataloader.DataLoader` of length 21 with parameters: ``` {'batch_size': 2048, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'} ``` **Loss**: `sentence_transformers.losses.ContrastiveLoss.ContrastiveLoss` with parameters: ``` {'distance_metric': 'SiameseDistanceMetric.COSINE_DISTANCE', 'margin': 0.5, 'size_average': True} ``` Parameters of the fit()-Method: ``` { "epochs": 50, "evaluation_steps": 200, "evaluator": "sentence_transformers.evaluation.BinaryClassificationEvaluator.BinaryClassificationEvaluator", "max_grad_norm": 1, "optimizer_class": "<class 'torch.optim.adamw.AdamW'>", "optimizer_params": { "lr": 2e-05 }, "scheduler": "WarmupLinear", "steps_per_epoch": null, "warmup_steps": 105, "weight_decay": 1e-05 } ``` ## Full Model Architecture ``` SentenceTransformer( (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel (1): Pooling({'word_embedding_dimension': 312, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False}) ) ``` ## Citing & Authors

uw-madison/mra-base-512-4

uw-madison

2023-07-10T16:11:54Z

1,482

1

transformers

[ "transformers", "pytorch", "mra", "fill-mask", "arxiv:2207.10284", "autotrain_compatible", "endpoints_compatible", "region:us" ]

fill-mask

2023-06-23T06:04:05Z

# MRA MRA model for masked language modeling (MLM) for sequence length 512. ## About MRA The MRA model was proposed in [Multi Resolution Analysis (MRA) for Approximate Self-Attention](https://arxiv.org/abs/2207.10284) by Zhanpeng Zeng, Sourav Pal, Jeffery Kline, Glenn M Fung, and Vikas Singh. The abstract from the paper is the following: *Transformers have emerged as a preferred model for many tasks in natural langugage processing and vision. Recent efforts on training and deploying Transformers more efficiently have identified many strategies to approximate the self-attention matrix, a key module in a Transformer architecture. Effective ideas include various prespecified sparsity patterns, low-rank basis expansions and combinations thereof. In this paper, we revisit classical Multiresolution Analysis (MRA) concepts such as Wavelets, whose potential value in this setting remains underexplored thus far. We show that simple approximations based on empirical feedback and design choices informed by modern hardware and implementation challenges, eventually yield a MRA-based approach for self-attention with an excellent performance profile across most criteria of interest. We undertake an extensive set of experiments and demonstrate that this multi-resolution scheme outperforms most efficient self-attention proposals and is favorable for both short and long sequences. Code is available at https://github.com/mlpen/mra-attention.* This model was contributed by [novice03](https://huggingface.co/novice03). The original code can be found [here](https://github.com/mlpen/mra-attention).

jordyvl/vit-tiny_tobacco3482_kd_MSE

jordyvl

2023-07-10T15:57:47Z

163

0

transformers

[ "transformers", "pytorch", "vit", "image-classification", "generated_from_trainer", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

image-classification

2023-07-10T15:22:05Z

--- license: apache-2.0 tags: - generated_from_trainer metrics: - accuracy model-index: - name: vit-tiny_tobacco3482_kd_MSE results: [] ---  # vit-tiny_tobacco3482_kd_MSE This model is a fine-tuned version of [WinKawaks/vit-tiny-patch16-224](https://huggingface.co/WinKawaks/vit-tiny-patch16-224) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.2482 - Accuracy: 0.82 - Brier Loss: 0.3226 - Nll: 0.8343 - F1 Micro: 0.82 - F1 Macro: 0.8090 - Ece: 0.2625 - Aurc: 0.0606 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 100 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | Brier Loss | Nll | F1 Micro | F1 Macro | Ece | Aurc | |:-------------:|:-----:|:----:|:---------------:|:--------:|:----------:|:------:|:--------:|:--------:|:------:|:------:| | No log | 1.0 | 7 | 2.6314 | 0.165 | 1.0293 | 8.4704 | 0.165 | 0.0552 | 0.3856 | 0.8464 | | No log | 2.0 | 14 | 1.4800 | 0.12 | 0.9052 | 7.3409 | 0.12 | 0.0997 | 0.2469 | 0.8374 | | No log | 3.0 | 21 | 1.0627 | 0.34 | 0.8400 | 5.5369 | 0.34 | 0.2006 | 0.3075 | 0.5758 | | No log | 4.0 | 28 | 0.8429 | 0.42 | 0.7462 | 3.2442 | 0.4200 | 0.3362 | 0.3072 | 0.3692 | | No log | 5.0 | 35 | 0.7060 | 0.535 | 0.6558 | 2.7042 | 0.535 | 0.4295 | 0.2993 | 0.2677 | | No log | 6.0 | 42 | 0.5950 | 0.635 | 0.6056 | 2.0779 | 0.635 | 0.5021 | 0.3375 | 0.1948 | | No log | 7.0 | 49 | 0.4865 | 0.67 | 0.5486 | 1.4919 | 0.67 | 0.5384 | 0.3633 | 0.1737 | | No log | 8.0 | 56 | 0.4572 | 0.69 | 0.4897 | 1.4359 | 0.69 | 0.6106 | 0.2889 | 0.1355 | | No log | 9.0 | 63 | 0.3932 | 0.72 | 0.4496 | 1.0748 | 0.72 | 0.6261 | 0.2914 | 0.1092 | | No log | 10.0 | 70 | 0.3584 | 0.76 | 0.4091 | 1.1341 | 0.76 | 0.6747 | 0.2946 | 0.0937 | | No log | 11.0 | 77 | 0.3516 | 0.785 | 0.3906 | 1.0586 | 0.785 | 0.7422 | 0.3026 | 0.0762 | | No log | 12.0 | 84 | 0.3905 | 0.74 | 0.4155 | 1.1502 | 0.74 | 0.6677 | 0.2827 | 0.1211 | | No log | 13.0 | 91 | 0.3346 | 0.775 | 0.3640 | 1.0888 | 0.775 | 0.7397 | 0.2743 | 0.0771 | | No log | 14.0 | 98 | 0.3700 | 0.81 | 0.3728 | 0.9575 | 0.81 | 0.7941 | 0.3125 | 0.0709 | | No log | 15.0 | 105 | 0.3346 | 0.8 | 0.3631 | 0.9636 | 0.8000 | 0.7731 | 0.3113 | 0.0662 | | No log | 16.0 | 112 | 0.3084 | 0.785 | 0.3606 | 1.0243 | 0.785 | 0.7610 | 0.2883 | 0.0911 | | No log | 17.0 | 119 | 0.3266 | 0.785 | 0.3375 | 1.0301 | 0.785 | 0.7603 | 0.2659 | 0.0687 | | No log | 18.0 | 126 | 0.2987 | 0.805 | 0.3371 | 0.7961 | 0.805 | 0.7895 | 0.2764 | 0.0639 | | No log | 19.0 | 133 | 0.3468 | 0.815 | 0.3428 | 0.9841 | 0.815 | 0.7884 | 0.2824 | 0.0641 | | No log | 20.0 | 140 | 0.3111 | 0.81 | 0.3409 | 0.8873 | 0.81 | 0.8010 | 0.2978 | 0.0579 | | No log | 21.0 | 147 | 0.3042 | 0.8 | 0.3392 | 0.8057 | 0.8000 | 0.7802 | 0.2611 | 0.0556 | | No log | 22.0 | 154 | 0.2936 | 0.84 | 0.3359 | 0.8659 | 0.8400 | 0.8210 | 0.2920 | 0.0636 | | No log | 23.0 | 161 | 0.3284 | 0.815 | 0.3457 | 0.9494 | 0.815 | 0.8007 | 0.2793 | 0.0615 | | No log | 24.0 | 168 | 0.3184 | 0.805 | 0.3474 | 0.9087 | 0.805 | 0.7851 | 0.2793 | 0.0605 | | No log | 25.0 | 175 | 0.3081 | 0.805 | 0.3357 | 1.0425 | 0.805 | 0.7757 | 0.2781 | 0.0646 | | No log | 26.0 | 182 | 0.2743 | 0.815 | 0.3425 | 0.7898 | 0.815 | 0.8028 | 0.2814 | 0.0689 | | No log | 27.0 | 189 | 0.2873 | 0.81 | 0.3254 | 0.8795 | 0.81 | 0.7904 | 0.2755 | 0.0637 | | No log | 28.0 | 196 | 0.2650 | 0.82 | 0.3236 | 0.7462 | 0.82 | 0.7986 | 0.2714 | 0.0616 | | No log | 29.0 | 203 | 0.2756 | 0.815 | 0.3310 | 0.8227 | 0.815 | 0.7973 | 0.2766 | 0.0664 | | No log | 30.0 | 210 | 0.2711 | 0.83 | 0.3337 | 0.8340 | 0.83 | 0.8186 | 0.2992 | 0.0688 | | No log | 31.0 | 217 | 0.2779 | 0.825 | 0.3234 | 0.8173 | 0.825 | 0.8100 | 0.2579 | 0.0589 | | No log | 32.0 | 224 | 0.2679 | 0.82 | 0.3216 | 0.7441 | 0.82 | 0.8024 | 0.2940 | 0.0605 | | No log | 33.0 | 231 | 0.2633 | 0.805 | 0.3277 | 0.8046 | 0.805 | 0.7871 | 0.2710 | 0.0644 | | No log | 34.0 | 238 | 0.2705 | 0.805 | 0.3333 | 0.8661 | 0.805 | 0.7890 | 0.2626 | 0.0632 | | No log | 35.0 | 245 | 0.2624 | 0.815 | 0.3295 | 0.8568 | 0.815 | 0.7900 | 0.2865 | 0.0651 | | No log | 36.0 | 252 | 0.2654 | 0.805 | 0.3262 | 0.8075 | 0.805 | 0.7793 | 0.2726 | 0.0662 | | No log | 37.0 | 259 | 0.2697 | 0.805 | 0.3293 | 0.8143 | 0.805 | 0.7857 | 0.2587 | 0.0623 | | No log | 38.0 | 266 | 0.2548 | 0.805 | 0.3267 | 0.8028 | 0.805 | 0.7847 | 0.2606 | 0.0660 | | No log | 39.0 | 273 | 0.2740 | 0.83 | 0.3218 | 0.8270 | 0.83 | 0.8172 | 0.2697 | 0.0566 | | No log | 40.0 | 280 | 0.2572 | 0.81 | 0.3302 | 0.8573 | 0.81 | 0.7892 | 0.2722 | 0.0663 | | No log | 41.0 | 287 | 0.2528 | 0.81 | 0.3300 | 0.8454 | 0.81 | 0.7980 | 0.2555 | 0.0673 | | No log | 42.0 | 294 | 0.2590 | 0.815 | 0.3271 | 0.8393 | 0.815 | 0.8002 | 0.2554 | 0.0604 | | No log | 43.0 | 301 | 0.2654 | 0.825 | 0.3273 | 0.8100 | 0.825 | 0.8155 | 0.2687 | 0.0595 | | No log | 44.0 | 308 | 0.2506 | 0.805 | 0.3290 | 0.8551 | 0.805 | 0.7858 | 0.2425 | 0.0716 | | No log | 45.0 | 315 | 0.2615 | 0.82 | 0.3255 | 0.8624 | 0.82 | 0.8007 | 0.2773 | 0.0586 | | No log | 46.0 | 322 | 0.2487 | 0.815 | 0.3240 | 0.8416 | 0.815 | 0.7987 | 0.2757 | 0.0611 | | No log | 47.0 | 329 | 0.2674 | 0.845 | 0.3207 | 0.8407 | 0.845 | 0.8227 | 0.2963 | 0.0553 | | No log | 48.0 | 336 | 0.2522 | 0.805 | 0.3312 | 0.9376 | 0.805 | 0.7888 | 0.2714 | 0.0662 | | No log | 49.0 | 343 | 0.2547 | 0.81 | 0.3280 | 0.7847 | 0.81 | 0.7870 | 0.2696 | 0.0688 | | No log | 50.0 | 350 | 0.2523 | 0.81 | 0.3213 | 0.7968 | 0.81 | 0.7937 | 0.2599 | 0.0654 | | No log | 51.0 | 357 | 0.2526 | 0.815 | 0.3291 | 0.8022 | 0.815 | 0.7994 | 0.2888 | 0.0669 | | No log | 52.0 | 364 | 0.2568 | 0.835 | 0.3180 | 0.8317 | 0.835 | 0.8140 | 0.2750 | 0.0578 | | No log | 53.0 | 371 | 0.2496 | 0.82 | 0.3267 | 0.8442 | 0.82 | 0.8068 | 0.2825 | 0.0602 | | No log | 54.0 | 378 | 0.2602 | 0.82 | 0.3229 | 0.7963 | 0.82 | 0.8061 | 0.2714 | 0.0585 | | No log | 55.0 | 385 | 0.2477 | 0.81 | 0.3237 | 0.8278 | 0.81 | 0.7937 | 0.2511 | 0.0631 | | No log | 56.0 | 392 | 0.2508 | 0.83 | 0.3210 | 0.8302 | 0.83 | 0.8102 | 0.2706 | 0.0588 | | No log | 57.0 | 399 | 0.2454 | 0.815 | 0.3240 | 0.8377 | 0.815 | 0.7948 | 0.2607 | 0.0643 | | No log | 58.0 | 406 | 0.2488 | 0.815 | 0.3229 | 0.8308 | 0.815 | 0.7942 | 0.2569 | 0.0604 | | No log | 59.0 | 413 | 0.2510 | 0.82 | 0.3223 | 0.8314 | 0.82 | 0.8093 | 0.2779 | 0.0603 | | No log | 60.0 | 420 | 0.2499 | 0.82 | 0.3235 | 0.8401 | 0.82 | 0.8031 | 0.2578 | 0.0618 | | No log | 61.0 | 427 | 0.2478 | 0.81 | 0.3227 | 0.8315 | 0.81 | 0.7933 | 0.2645 | 0.0615 | | No log | 62.0 | 434 | 0.2460 | 0.82 | 0.3231 | 0.8364 | 0.82 | 0.8028 | 0.2795 | 0.0643 | | No log | 63.0 | 441 | 0.2489 | 0.825 | 0.3224 | 0.8337 | 0.825 | 0.8156 | 0.2759 | 0.0604 | | No log | 64.0 | 448 | 0.2482 | 0.825 | 0.3230 | 0.8320 | 0.825 | 0.8138 | 0.2753 | 0.0600 | | No log | 65.0 | 455 | 0.2462 | 0.815 | 0.3231 | 0.8354 | 0.815 | 0.8008 | 0.2551 | 0.0625 | | No log | 66.0 | 462 | 0.2470 | 0.815 | 0.3219 | 0.8338 | 0.815 | 0.8018 | 0.2729 | 0.0611 | | No log | 67.0 | 469 | 0.2457 | 0.81 | 0.3231 | 0.8336 | 0.81 | 0.7930 | 0.2587 | 0.0638 | | No log | 68.0 | 476 | 0.2472 | 0.815 | 0.3225 | 0.8334 | 0.815 | 0.8008 | 0.2706 | 0.0619 | | No log | 69.0 | 483 | 0.2473 | 0.825 | 0.3223 | 0.8357 | 0.825 | 0.8165 | 0.2668 | 0.0611 | | No log | 70.0 | 490 | 0.2481 | 0.81 | 0.3223 | 0.8343 | 0.81 | 0.7930 | 0.2685 | 0.0624 | | No log | 71.0 | 497 | 0.2472 | 0.825 | 0.3227 | 0.8338 | 0.825 | 0.8117 | 0.2839 | 0.0601 | | 0.232 | 72.0 | 504 | 0.2472 | 0.815 | 0.3220 | 0.8345 | 0.815 | 0.8018 | 0.2617 | 0.0615 | | 0.232 | 73.0 | 511 | 0.2486 | 0.82 | 0.3218 | 0.8321 | 0.82 | 0.8086 | 0.2768 | 0.0610 | | 0.232 | 74.0 | 518 | 0.2468 | 0.815 | 0.3219 | 0.8338 | 0.815 | 0.8008 | 0.2717 | 0.0621 | | 0.232 | 75.0 | 525 | 0.2470 | 0.82 | 0.3223 | 0.8325 | 0.82 | 0.8090 | 0.2625 | 0.0606 | | 0.232 | 76.0 | 532 | 0.2474 | 0.825 | 0.3223 | 0.8322 | 0.825 | 0.8165 | 0.2723 | 0.0602 | | 0.232 | 77.0 | 539 | 0.2476 | 0.805 | 0.3227 | 0.8345 | 0.805 | 0.7859 | 0.2589 | 0.0629 | | 0.232 | 78.0 | 546 | 0.2479 | 0.82 | 0.3228 | 0.8336 | 0.82 | 0.8090 | 0.2674 | 0.0608 | | 0.232 | 79.0 | 553 | 0.2478 | 0.82 | 0.3225 | 0.8349 | 0.82 | 0.8090 | 0.2624 | 0.0604 | | 0.232 | 80.0 | 560 | 0.2477 | 0.81 | 0.3227 | 0.8337 | 0.81 | 0.7938 | 0.2577 | 0.0621 | | 0.232 | 81.0 | 567 | 0.2478 | 0.82 | 0.3226 | 0.8336 | 0.82 | 0.8090 | 0.2670 | 0.0607 | | 0.232 | 82.0 | 574 | 0.2480 | 0.825 | 0.3224 | 0.8340 | 0.825 | 0.8165 | 0.2673 | 0.0605 | | 0.232 | 83.0 | 581 | 0.2479 | 0.82 | 0.3227 | 0.8347 | 0.82 | 0.8090 | 0.2564 | 0.0607 | | 0.232 | 84.0 | 588 | 0.2480 | 0.82 | 0.3226 | 0.8342 | 0.82 | 0.8090 | 0.2625 | 0.0606 | | 0.232 | 85.0 | 595 | 0.2480 | 0.82 | 0.3225 | 0.8339 | 0.82 | 0.8090 | 0.2625 | 0.0606 | | 0.232 | 86.0 | 602 | 0.2479 | 0.825 | 0.3226 | 0.8339 | 0.825 | 0.8165 | 0.2677 | 0.0606 | | 0.232 | 87.0 | 609 | 0.2479 | 0.82 | 0.3225 | 0.8339 | 0.82 | 0.8090 | 0.2624 | 0.0605 | | 0.232 | 88.0 | 616 | 0.2481 | 0.825 | 0.3225 | 0.8343 | 0.825 | 0.8165 | 0.2675 | 0.0604 | | 0.232 | 89.0 | 623 | 0.2481 | 0.825 | 0.3225 | 0.8341 | 0.825 | 0.8165 | 0.2722 | 0.0605 | | 0.232 | 90.0 | 630 | 0.2481 | 0.82 | 0.3225 | 0.8341 | 0.82 | 0.8090 | 0.2625 | 0.0606 | | 0.232 | 91.0 | 637 | 0.2481 | 0.82 | 0.3226 | 0.8345 | 0.82 | 0.8090 | 0.2629 | 0.0608 | | 0.232 | 92.0 | 644 | 0.2481 | 0.825 | 0.3226 | 0.8342 | 0.825 | 0.8165 | 0.2675 | 0.0605 | | 0.232 | 93.0 | 651 | 0.2481 | 0.825 | 0.3225 | 0.8340 | 0.825 | 0.8165 | 0.2675 | 0.0605 | | 0.232 | 94.0 | 658 | 0.2481 | 0.82 | 0.3225 | 0.8343 | 0.82 | 0.8090 | 0.2625 | 0.0606 | | 0.232 | 95.0 | 665 | 0.2482 | 0.82 | 0.3226 | 0.8345 | 0.82 | 0.8090 | 0.2627 | 0.0606 | | 0.232 | 96.0 | 672 | 0.2482 | 0.82 | 0.3225 | 0.8343 | 0.82 | 0.8090 | 0.2627 | 0.0607 | | 0.232 | 97.0 | 679 | 0.2482 | 0.82 | 0.3226 | 0.8344 | 0.82 | 0.8090 | 0.2627 | 0.0607 | | 0.232 | 98.0 | 686 | 0.2482 | 0.82 | 0.3226 | 0.8344 | 0.82 | 0.8090 | 0.2626 | 0.0606 | | 0.232 | 99.0 | 693 | 0.2482 | 0.82 | 0.3226 | 0.8343 | 0.82 | 0.8090 | 0.2625 | 0.0606 | | 0.232 | 100.0 | 700 | 0.2482 | 0.82 | 0.3226 | 0.8343 | 0.82 | 0.8090 | 0.2625 | 0.0606 | ### Framework versions - Transformers 4.26.1 - Pytorch 1.13.1.post200 - Datasets 2.9.0 - Tokenizers 0.13.2

sianadouglas/ensembletest

sianadouglas

2023-07-10T15:48:14Z

0

null

[ "en", "license:other", "region:us" ]

null

2023-07-10T15:47:23Z

--- license: other language: - en ---

Khushnur/t5-base-end2end-questions-generation_squad

Khushnur

2023-07-10T15:47:50Z

164

0

transformers

[ "transformers", "pytorch", "t5", "text2text-generation", "generated_from_trainer", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]

text2text-generation

2023-07-10T15:02:34Z

--- license: apache-2.0 tags: - generated_from_trainer model-index: - name: t5-base-end2end-questions-generation_squad results: [] ---  # t5-base-end2end-questions-generation_squad This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on the None dataset. It achieves the following results on the evaluation set: - Loss: 1.6560 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 4 - eval_batch_size: 4 - seed: 42 - gradient_accumulation_steps: 32 - total_train_batch_size: 128 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:----:|:---------------:| | 2.5658 | 0.67 | 100 | 1.8866 | | 1.958 | 1.35 | 200 | 1.7150 | | 1.8516 | 2.02 | 300 | 1.6701 | | 1.7965 | 2.69 | 400 | 1.6560 | ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3

mgmeskill/Pixelcopter-PLE-v0

mgmeskill

2023-07-10T15:38:32Z

0

null

[ "Pixelcopter-PLE-v0", "reinforce", "reinforcement-learning", "custom-implementation", "deep-rl-class", "model-index", "region:us" ]

reinforcement-learning

2023-07-10T15:26:11Z

--- tags: - Pixelcopter-PLE-v0 - reinforce - reinforcement-learning - custom-implementation - deep-rl-class model-index: - name: Pixelcopter-PLE-v0 results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: Pixelcopter-PLE-v0 type: Pixelcopter-PLE-v0 metrics: - type: mean_reward value: 42.50 +/- 37.13 name: mean_reward verified: false --- # **Reinforce** Agent playing **Pixelcopter-PLE-v0** This is a trained model of a **Reinforce** agent playing **Pixelcopter-PLE-v0** . To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction

tyavika/LR1E4-BS16-Bert_CNN512LSTM256NoBid

tyavika

2023-07-10T15:31:42Z

77

0

transformers

[ "transformers", "pytorch", "bert", "question-answering", "generated_from_trainer", "license:apache-2.0", "endpoints_compatible", "region:us" ]

question-answering

2023-07-09T20:06:29Z

--- license: apache-2.0 tags: - generated_from_trainer model-index: - name: LR1E4-BS16-Bert_CNN512LSTM256NoBid results: [] ---  # LR1E4-BS16-Bert_CNN512LSTM256NoBid This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset. It achieves the following results on the evaluation set: - Loss: 1.6667 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 10 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:-----:|:---------------:| | 1.7267 | 1.0 | 3290 | 1.5092 | | 1.2394 | 2.0 | 6580 | 1.3933 | | 0.8348 | 3.0 | 9870 | 1.5591 | | 0.542 | 4.0 | 13160 | 1.6667 | ### Framework versions - Transformers 4.28.0 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3

MnLgt/textual_inversion_muir_1_5

MnLgt

2023-07-10T15:31:36Z

1

0

diffusers

[ "diffusers", "tensorboard", "stable-diffusion", "stable-diffusion-diffusers", "text-to-image", "textual_inversion", "base_model:runwayml/stable-diffusion-v1-5", "base_model:adapter:runwayml/stable-diffusion-v1-5", "license:creativeml-openrail-m", "autotrain_compatible", "endpoints_compatible", "diffusers:StableDiffusionPipeline", "region:us" ]

text-to-image

2023-07-10T14:16:45Z

--- license: creativeml-openrail-m base_model: runwayml/stable-diffusion-v1-5 tags: - stable-diffusion - stable-diffusion-diffusers - text-to-image - diffusers - textual_inversion inference: true --- # Textual inversion text2image fine-tuning - jordandavis/textual_inversion_muir_1_5 These are textual inversion adaption weights for runwayml/stable-diffusion-v1-5. You can find some example images in the following.

agercas/speecht5_finetuned_voxpopuli_nl

agercas

2023-07-10T15:27:22Z

78

0

transformers

[ "transformers", "pytorch", "tensorboard", "speecht5", "text-to-audio", "generated_from_trainer", "dataset:facebook/voxpopuli", "license:mit", "endpoints_compatible", "region:us" ]

text-to-audio

2023-07-10T09:21:57Z

--- license: mit tags: - generated_from_trainer datasets: - facebook/voxpopuli model-index: - name: speecht5_finetuned_voxpopuli_nl results: [] ---  # speecht5_finetuned_voxpopuli_nl This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the facebook/voxpopuli dataset. It achieves the following results on the evaluation set: - Loss: 0.4572 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 1e-05 - train_batch_size: 4 - eval_batch_size: 2 - seed: 42 - gradient_accumulation_steps: 8 - total_train_batch_size: 32 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 500 - training_steps: 4000 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:----:|:---------------:| | 0.5221 | 4.3 | 1000 | 0.4774 | | 0.505 | 8.61 | 2000 | 0.4648 | | 0.4929 | 12.91 | 3000 | 0.4583 | | 0.4901 | 17.21 | 4000 | 0.4572 | ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3

grace-pro/afriberta-finetuned-hausa

grace-pro

2023-07-10T15:26:48Z

126

0

transformers

[ "transformers", "pytorch", "tensorboard", "xlm-roberta", "token-classification", "generated_from_trainer", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]

token-classification

2023-07-10T14:49:51Z

--- license: mit tags: - generated_from_trainer metrics: - precision - recall - f1 - accuracy model-index: - name: afriberta-finetuned-hausa results: [] ---  # afriberta-finetuned-hausa This model is a fine-tuned version of [castorini/afriberta_large](https://huggingface.co/castorini/afriberta_large) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.1242 - Precision: 0.7104 - Recall: 0.5095 - F1: 0.5934 - Accuracy: 0.9647 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3 ### Training results | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| | 0.1369 | 1.0 | 2624 | 0.1256 | 0.6856 | 0.4541 | 0.5463 | 0.9614 | | 0.1103 | 2.0 | 5248 | 0.1195 | 0.7014 | 0.4947 | 0.5802 | 0.9637 | | 0.0868 | 3.0 | 7872 | 0.1242 | 0.7104 | 0.5095 | 0.5934 | 0.9647 | ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3

dariowsz/wav2vec2-base-finetuned-gtzan

dariowsz

2023-07-10T15:03:27Z

5

0

transformers

[ "transformers", "pytorch", "tensorboard", "wav2vec2", "audio-classification", "generated_from_trainer", "dataset:marsyas/gtzan", "license:apache-2.0", "endpoints_compatible", "region:us" ]

audio-classification

2023-07-04T13:47:36Z

--- license: apache-2.0 tags: - generated_from_trainer datasets: - marsyas/gtzan metrics: - accuracy model-index: - name: wav2vec2-base-finetuned-gtzan results: [] ---  # wav2vec2-base-finetuned-gtzan This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the GTZAN dataset. It achieves the following results on the evaluation set: - Loss: 0.5537 - Accuracy: 0.88 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 10 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------:| | 1.7898 | 1.0 | 113 | 1.8052 | 0.45 | | 1.4297 | 2.0 | 226 | 1.2229 | 0.62 | | 1.041 | 3.0 | 339 | 0.9934 | 0.65 | | 1.3882 | 4.0 | 452 | 1.1735 | 0.62 | | 0.7248 | 5.0 | 565 | 0.8461 | 0.69 | | 0.6128 | 6.0 | 678 | 0.7391 | 0.75 | | 0.3225 | 7.0 | 791 | 0.8754 | 0.74 | | 0.6483 | 8.0 | 904 | 0.8341 | 0.79 | | 0.2755 | 9.0 | 1017 | 0.5537 | 0.88 | | 0.4398 | 10.0 | 1130 | 0.6076 | 0.85 | ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3

NICFRU/bart-base-paraphrasing-news

NICFRU

2023-07-10T15:02:02Z

106

0

transformers

[ "transformers", "pytorch", "bart", "text2text-generation", "generated_from_trainer", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

text2text-generation

2023-07-10T14:46:34Z

--- license: apache-2.0 tags: - generated_from_trainer metrics: - rouge model-index: - name: bart-base-paraphrasing results: [] ---  # bart-base-paraphrasing This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.6617 - Rouge1: 57.7088 - Rouge2: 51.0096 - Rougel: 54.7514 - Rougelsum: 56.3943 - Gen Len: 20.0 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 4e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 20 ### Training results | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:| | No log | 0.2 | 10 | 0.5263 | 58.2676 | 51.5842 | 55.5057 | 57.1584 | 19.94 | | No log | 0.4 | 20 | 0.5050 | 56.1604 | 48.7383 | 54.0373 | 55.372 | 20.0 | | No log | 0.6 | 30 | 0.4674 | 58.0617 | 51.4993 | 56.0368 | 56.9665 | 20.0 | | No log | 0.8 | 40 | 0.4545 | 57.5375 | 51.0203 | 55.5247 | 56.5761 | 19.94 | | No log | 1.0 | 50 | 0.4373 | 57.7263 | 50.8021 | 55.0549 | 56.35 | 19.98 | | No log | 1.2 | 60 | 0.4313 | 57.87 | 50.9904 | 54.9727 | 56.5379 | 19.97 | | No log | 1.4 | 70 | 0.4855 | 56.5101 | 49.3124 | 54.1572 | 55.0671 | 20.0 | | No log | 1.6 | 80 | 0.4202 | 56.6535 | 50.0302 | 53.6891 | 55.1016 | 19.96 | | No log | 1.8 | 90 | 0.4544 | 57.315 | 50.6289 | 54.642 | 55.7326 | 19.95 | | 0.5858 | 2.0 | 100 | 0.4157 | 56.4569 | 48.8105 | 53.937 | 55.3515 | 20.0 | | 0.5858 | 2.2 | 110 | 0.4555 | 57.8424 | 51.5966 | 55.6655 | 56.6862 | 20.0 | | 0.5858 | 2.4 | 120 | 0.4196 | 58.2562 | 51.7596 | 55.5085 | 57.1823 | 19.97 | | 0.5858 | 2.6 | 130 | 0.4334 | 58.6906 | 51.6106 | 55.6631 | 57.5254 | 19.89 | | 0.5858 | 2.8 | 140 | 0.4710 | 56.5401 | 49.33 | 53.8792 | 55.0282 | 20.0 | | 0.5858 | 3.0 | 150 | 0.4357 | 58.2083 | 52.0049 | 55.9938 | 57.1928 | 20.0 | | 0.5858 | 3.2 | 160 | 0.4735 | 58.8112 | 52.2196 | 56.5004 | 57.7703 | 19.94 | | 0.5858 | 3.4 | 170 | 0.4428 | 57.6778 | 50.6377 | 54.8752 | 56.4778 | 20.0 | | 0.5858 | 3.6 | 180 | 0.4983 | 57.4124 | 50.4244 | 54.6163 | 56.0992 | 20.0 | | 0.5858 | 3.8 | 190 | 0.4620 | 58.0701 | 51.5021 | 55.7222 | 56.8737 | 20.0 | | 0.2865 | 4.0 | 200 | 0.4502 | 59.1191 | 52.7516 | 56.4389 | 57.7153 | 20.0 | | 0.2865 | 4.2 | 210 | 0.4805 | 58.9064 | 52.7148 | 56.1058 | 57.6709 | 20.0 | | 0.2865 | 4.4 | 220 | 0.4755 | 58.6883 | 52.1464 | 55.9164 | 57.3825 | 20.0 | | 0.2865 | 4.6 | 230 | 0.4524 | 58.9916 | 52.1101 | 56.4116 | 57.9468 | 19.9 | | 0.2865 | 4.8 | 240 | 0.4726 | 58.9953 | 52.8173 | 56.5846 | 58.0805 | 20.0 | | 0.2865 | 5.0 | 250 | 0.4841 | 58.1058 | 51.614 | 55.3374 | 56.7617 | 20.0 | | 0.2865 | 5.2 | 260 | 0.5047 | 58.2785 | 51.1874 | 55.5336 | 56.8795 | 20.0 | | 0.2865 | 5.4 | 270 | 0.4658 | 57.2753 | 49.6038 | 53.9588 | 55.6038 | 19.91 | | 0.2865 | 5.6 | 280 | 0.5261 | 58.1691 | 51.5254 | 55.2685 | 56.7787 | 20.0 | | 0.2865 | 5.8 | 290 | 0.4833 | 57.8088 | 51.2838 | 54.8739 | 56.4374 | 20.0 | | 0.1668 | 6.0 | 300 | 0.5067 | 58.2021 | 51.3629 | 55.3548 | 56.9093 | 19.99 | | 0.1668 | 6.2 | 310 | 0.5461 | 58.0327 | 51.4051 | 55.3426 | 56.7923 | 20.0 | | 0.1668 | 6.4 | 320 | 0.5463 | 58.1027 | 51.3706 | 55.1733 | 56.7923 | 19.9 | | 0.1668 | 6.6 | 330 | 0.5837 | 57.6284 | 50.8245 | 54.6253 | 56.2127 | 20.0 | | 0.1668 | 6.8 | 340 | 0.5221 | 58.0869 | 51.5448 | 55.4226 | 56.7532 | 20.0 | | 0.1668 | 7.0 | 350 | 0.5433 | 58.7676 | 52.0403 | 56.2634 | 57.6441 | 20.0 | | 0.1668 | 7.2 | 360 | 0.5498 | 57.9172 | 50.9727 | 55.1006 | 56.6018 | 20.0 | | 0.1668 | 7.4 | 370 | 0.5581 | 57.4669 | 50.698 | 54.6448 | 56.1325 | 20.0 | | 0.1668 | 7.6 | 380 | 0.5526 | 57.0821 | 50.298 | 54.1635 | 55.8059 | 20.0 | | 0.1668 | 7.8 | 390 | 0.5548 | 57.5422 | 50.2734 | 54.2446 | 56.1223 | 20.0 | | 0.1071 | 8.0 | 400 | 0.5620 | 57.4548 | 50.2657 | 54.5094 | 55.9422 | 20.0 | | 0.1071 | 8.2 | 410 | 0.5772 | 57.4144 | 50.2443 | 54.5173 | 55.9331 | 20.0 | | 0.1071 | 8.4 | 420 | 0.5857 | 57.2975 | 50.2116 | 54.5918 | 55.9931 | 20.0 | | 0.1071 | 8.6 | 430 | 0.5827 | 58.4767 | 51.4318 | 55.4792 | 57.1284 | 20.0 | | 0.1071 | 8.8 | 440 | 0.5728 | 58.4414 | 51.3523 | 55.2838 | 57.202 | 20.0 | | 0.1071 | 9.0 | 450 | 0.5919 | 58.0499 | 51.3783 | 55.0748 | 56.6939 | 20.0 | | 0.1071 | 9.2 | 460 | 0.5937 | 57.7604 | 50.845 | 54.8941 | 56.351 | 20.0 | | 0.1071 | 9.4 | 470 | 0.5970 | 57.3655 | 50.4126 | 54.4522 | 55.7815 | 20.0 | | 0.1071 | 9.6 | 480 | 0.5911 | 58.203 | 51.0367 | 55.3215 | 56.8485 | 20.0 | | 0.1071 | 9.8 | 490 | 0.6121 | 58.2898 | 51.2749 | 55.4292 | 57.0241 | 20.0 | | 0.0718 | 10.0 | 500 | 0.5903 | 58.2487 | 51.3838 | 55.4237 | 56.8863 | 20.0 | | 0.0718 | 10.2 | 510 | 0.5983 | 58.2681 | 51.0925 | 55.2887 | 56.9562 | 20.0 | | 0.0718 | 10.4 | 520 | 0.6308 | 57.9797 | 50.7386 | 54.995 | 56.5939 | 20.0 | | 0.0718 | 10.6 | 530 | 0.6307 | 57.6269 | 50.5515 | 54.446 | 56.1544 | 20.0 | | 0.0718 | 10.8 | 540 | 0.6173 | 57.9545 | 51.1005 | 54.9406 | 56.5732 | 20.0 | | 0.0718 | 11.0 | 550 | 0.6322 | 58.3718 | 51.4321 | 55.4241 | 57.1879 | 20.0 | | 0.0718 | 11.2 | 560 | 0.6027 | 58.6581 | 51.8607 | 55.6436 | 57.32 | 20.0 | | 0.0718 | 11.4 | 570 | 0.6140 | 58.6476 | 51.7822 | 55.5845 | 57.3018 | 20.0 | | 0.0718 | 11.6 | 580 | 0.6184 | 59.2454 | 52.4204 | 56.2174 | 57.9278 | 20.0 | | 0.0718 | 11.8 | 590 | 0.6281 | 59.2945 | 52.8165 | 56.547 | 58.0674 | 20.0 | | 0.0512 | 12.0 | 600 | 0.6128 | 58.2165 | 51.3689 | 55.37 | 56.8342 | 20.0 | | 0.0512 | 12.2 | 610 | 0.6482 | 57.9196 | 50.9793 | 55.0883 | 56.6986 | 20.0 | | 0.0512 | 12.4 | 620 | 0.6267 | 57.4782 | 50.1118 | 54.2802 | 55.8872 | 20.0 | | 0.0512 | 12.6 | 630 | 0.6198 | 57.457 | 50.4079 | 54.2449 | 55.8118 | 20.0 | | 0.0512 | 12.8 | 640 | 0.6500 | 57.6903 | 51.0627 | 55.0743 | 56.3025 | 20.0 | | 0.0512 | 13.0 | 650 | 0.6265 | 57.4394 | 50.9013 | 54.7936 | 56.1688 | 20.0 | | 0.0512 | 13.2 | 660 | 0.6817 | 58.4345 | 51.7087 | 55.291 | 57.0057 | 20.0 | | 0.0512 | 13.4 | 670 | 0.6322 | 57.869 | 50.9503 | 54.8937 | 56.5178 | 20.0 | | 0.0512 | 13.6 | 680 | 0.6424 | 57.8285 | 51.1014 | 55.0072 | 56.5022 | 20.0 | | 0.0512 | 13.8 | 690 | 0.6668 | 58.7067 | 51.9929 | 55.5044 | 57.1517 | 20.0 | | 0.0397 | 14.0 | 700 | 0.6537 | 58.8717 | 52.4036 | 55.6521 | 57.4855 | 20.0 | | 0.0397 | 14.2 | 710 | 0.6463 | 58.9623 | 52.4749 | 55.8145 | 57.8095 | 20.0 | | 0.0397 | 14.4 | 720 | 0.6630 | 58.8097 | 52.1997 | 55.8204 | 57.6325 | 20.0 | | 0.0397 | 14.6 | 730 | 0.6839 | 59.0479 | 52.6573 | 56.0439 | 57.7322 | 20.0 | | 0.0397 | 14.8 | 740 | 0.6541 | 59.2854 | 52.6109 | 56.1891 | 57.9446 | 20.0 | | 0.0397 | 15.0 | 750 | 0.6486 | 58.8419 | 52.2004 | 55.8071 | 57.49 | 20.0 | | 0.0397 | 15.2 | 760 | 0.6578 | 57.6161 | 50.7276 | 54.5514 | 56.2359 | 20.0 | | 0.0397 | 15.4 | 770 | 0.6673 | 57.5458 | 50.8286 | 54.4597 | 56.1513 | 20.0 | | 0.0397 | 15.6 | 780 | 0.6624 | 57.6634 | 51.0017 | 54.6769 | 56.3837 | 20.0 | | 0.0397 | 15.8 | 790 | 0.6469 | 57.9037 | 51.137 | 54.8939 | 56.6427 | 20.0 | | 0.0301 | 16.0 | 800 | 0.6373 | 57.8696 | 51.0899 | 54.8543 | 56.4596 | 20.0 | | 0.0301 | 16.2 | 810 | 0.6712 | 58.614 | 52.0052 | 55.6436 | 57.3211 | 20.0 | | 0.0301 | 16.4 | 820 | 0.6812 | 58.5214 | 51.8911 | 55.7447 | 57.2663 | 20.0 | | 0.0301 | 16.6 | 830 | 0.6716 | 58.5818 | 51.929 | 55.7993 | 57.4064 | 20.0 | | 0.0301 | 16.8 | 840 | 0.6590 | 57.745 | 51.0481 | 54.8545 | 56.4781 | 20.0 | | 0.0301 | 17.0 | 850 | 0.6695 | 57.6663 | 50.9646 | 54.7863 | 56.3687 | 20.0 | | 0.0301 | 17.2 | 860 | 0.6858 | 57.5552 | 51.0436 | 54.7092 | 56.3079 | 20.0 | | 0.0301 | 17.4 | 870 | 0.6840 | 57.9091 | 51.3823 | 54.8309 | 56.6186 | 20.0 | | 0.0301 | 17.6 | 880 | 0.6751 | 57.8223 | 51.1688 | 54.7562 | 56.5558 | 20.0 | | 0.0301 | 17.8 | 890 | 0.6589 | 57.9956 | 51.1425 | 54.9509 | 56.6868 | 20.0 | | 0.0482 | 18.0 | 900 | 0.6634 | 58.0392 | 51.3121 | 55.0726 | 56.7878 | 20.0 | | 0.0482 | 18.2 | 910 | 0.6907 | 58.2021 | 51.4548 | 55.1874 | 56.91 | 20.0 | | 0.0482 | 18.4 | 920 | 0.6977 | 58.1124 | 51.4254 | 55.062 | 56.8412 | 20.0 | | 0.0482 | 18.6 | 930 | 0.6832 | 58.0776 | 51.3168 | 55.0849 | 56.8226 | 20.0 | | 0.0482 | 18.8 | 940 | 0.6672 | 57.925 | 51.2475 | 54.9661 | 56.655 | 20.0 | | 0.0482 | 19.0 | 950 | 0.6582 | 57.9285 | 51.2483 | 54.9744 | 56.6609 | 20.0 | | 0.0482 | 19.2 | 960 | 0.6575 | 57.9285 | 51.2483 | 54.9744 | 56.6609 | 20.0 | | 0.0482 | 19.4 | 970 | 0.6619 | 57.8961 | 51.2097 | 54.9475 | 56.6344 | 20.0 | | 0.0482 | 19.6 | 980 | 0.6658 | 57.8961 | 51.2097 | 54.9475 | 56.6344 | 20.0 | | 0.0482 | 19.8 | 990 | 0.6635 | 57.7222 | 51.0096 | 54.8166 | 56.4623 | 20.0 | | 0.0201 | 20.0 | 1000 | 0.6617 | 57.7088 | 51.0096 | 54.7514 | 56.3943 | 20.0 | ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3

alienware/layoutlmv3-finetuned-cord_100

alienware

2023-07-10T15:01:59Z

4

0

transformers

[ "transformers", "pytorch", "layoutlmv3", "token-classification", "generated_from_trainer", "dataset:cord-layoutlmv3", "license:cc-by-nc-sa-4.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]

token-classification

2023-07-09T12:32:12Z

--- license: cc-by-nc-sa-4.0 tags: - generated_from_trainer datasets: - cord-layoutlmv3 metrics: - precision - recall - f1 - accuracy model-index: - name: layoutlmv3-finetuned-cord_100 results: - task: name: Token Classification type: token-classification dataset: name: cord-layoutlmv3 type: cord-layoutlmv3 config: cord split: test args: cord metrics: - name: Precision type: precision value: 0.9569093610698366 - name: Recall type: recall value: 0.9640718562874252 - name: F1 type: f1 value: 0.9604772557792692 - name: Accuracy type: accuracy value: 0.9681663837011885 ---  # layoutlmv3-finetuned-cord_100 This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on the cord-layoutlmv3 dataset. It achieves the following results on the evaluation set: - Loss: 0.1720 - Precision: 0.9569 - Recall: 0.9641 - F1: 0.9605 - Accuracy: 0.9682 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 1e-05 - train_batch_size: 5 - eval_batch_size: 5 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 2500 ### Training results | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| | No log | 1.56 | 250 | 0.3320 | 0.9011 | 0.9207 | 0.9108 | 0.9253 | | 0.3502 | 3.12 | 500 | 0.2811 | 0.9281 | 0.9371 | 0.9326 | 0.9427 | | 0.3502 | 4.69 | 750 | 0.2429 | 0.9210 | 0.9341 | 0.9275 | 0.9435 | | 0.162 | 6.25 | 1000 | 0.2264 | 0.9385 | 0.9476 | 0.9430 | 0.9542 | | 0.162 | 7.81 | 1250 | 0.1996 | 0.9373 | 0.9513 | 0.9443 | 0.9601 | | 0.0971 | 9.38 | 1500 | 0.1686 | 0.9569 | 0.9633 | 0.9601 | 0.9690 | | 0.0971 | 10.94 | 1750 | 0.1814 | 0.9532 | 0.9603 | 0.9567 | 0.9652 | | 0.0704 | 12.5 | 2000 | 0.1915 | 0.9539 | 0.9611 | 0.9575 | 0.9656 | | 0.0704 | 14.06 | 2250 | 0.1833 | 0.9590 | 0.9633 | 0.9612 | 0.9677 | | 0.0513 | 15.62 | 2500 | 0.1720 | 0.9569 | 0.9641 | 0.9605 | 0.9682 | ### Framework versions - Transformers 4.30.2 - Pytorch 1.13.1+cu117 - Datasets 2.13.1 - Tokenizers 0.13.3

SHENMU007/neunit_BASE_V10.19

SHENMU007

2023-07-10T15:01:47Z

77

0

transformers

[ "transformers", "pytorch", "tensorboard", "speecht5", "text-to-audio", "1.1.0", "generated_from_trainer", "zh", "dataset:facebook/voxpopuli", "base_model:microsoft/speecht5_tts", "base_model:finetune:microsoft/speecht5_tts", "license:mit", "endpoints_compatible", "region:us" ]

text-to-audio

2023-07-07T08:50:51Z

--- language: - zh license: mit base_model: microsoft/speecht5_tts tags: - 1.1.0 - generated_from_trainer datasets: - facebook/voxpopuli model-index: - name: SpeechT5 TTS Dutch neunit results: [] ---  # SpeechT5 TTS Dutch neunit This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the VoxPopuli dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 1e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 32 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 500 - training_steps: 4000 ### Training results ### Framework versions - Transformers 4.31.0.dev0 - Pytorch 2.0.1+cu117 - Datasets 2.12.0 - Tokenizers 0.13.3

rickareo/distilbert-base-uncased-finetuned-emotion

rickareo

2023-07-10T14:59:25Z

105

0

transformers

[ "transformers", "pytorch", "tensorboard", "distilbert", "text-classification", "generated_from_trainer", "dataset:emotion", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]

text-classification

2023-07-10T14:44:04Z

--- license: apache-2.0 tags: - generated_from_trainer datasets: - emotion metrics: - accuracy - f1 model-index: - name: distilbert-base-uncased-finetuned-emotion results: - task: name: Text Classification type: text-classification dataset: name: emotion type: emotion args: split metrics: - name: Accuracy type: accuracy value: 0.923 - name: F1 type: f1 value: 0.9229910973969778 ---  # distilbert-base-uncased-finetuned-emotion This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the emotion dataset. It achieves the following results on the evaluation set: - Loss: 0.2155 - Accuracy: 0.923 - F1: 0.9230 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 64 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 2 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:| | 0.8271 | 1.0 | 250 | 0.3166 | 0.903 | 0.8989 | | 0.2469 | 2.0 | 500 | 0.2155 | 0.923 | 0.9230 | ### Framework versions - Transformers 4.16.2 - Pytorch 2.0.1+cu118 - Datasets 1.16.1 - Tokenizers 0.13.3

ericNguyen0132/DepRoBERTa-2ndStage

ericNguyen0132

2023-07-10T14:56:14Z

105

0

transformers

[ "transformers", "pytorch", "tensorboard", "roberta", "text-classification", "generated_from_trainer", "autotrain_compatible", "endpoints_compatible", "region:us" ]

text-classification

2023-07-10T13:42:58Z

--- tags: - generated_from_trainer metrics: - accuracy - f1 model-index: - name: DepRoBERTa-2ndStage results: [] ---  # DepRoBERTa-2ndStage This model is a fine-tuned version of [rafalposwiata/deproberta-large-v1](https://huggingface.co/rafalposwiata/deproberta-large-v1) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.6330 - Accuracy: 0.855 - F1: 0.9134 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-06 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 500 - num_epochs: 5 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:| | No log | 1.0 | 469 | 0.3572 | 0.8617 | 0.9224 | | 0.4953 | 2.0 | 938 | 0.3593 | 0.8783 | 0.9315 | | 0.3493 | 3.0 | 1407 | 0.4274 | 0.8483 | 0.9091 | | 0.313 | 4.0 | 1876 | 0.5488 | 0.8617 | 0.9187 | | 0.2622 | 5.0 | 2345 | 0.6330 | 0.855 | 0.9134 | ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3

pcuenq/falcon-7b-instruct-transformers

pcuenq

2023-07-10T14:54:25Z

7

0

transformers

[ "transformers", "pytorch", "falcon", "text-generation", "en", "dataset:tiiuae/falcon-refinedweb", "arxiv:2205.14135", "arxiv:1911.02150", "arxiv:2005.14165", "arxiv:2104.09864", "arxiv:2306.01116", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]

text-generation

2023-07-10T12:57:31Z

--- datasets: - tiiuae/falcon-refinedweb language: - en inference: true license: apache-2.0 duplicated_from: pcuenq/falcon-7b-instruct --- # ✨ Falcon-7B-Instruct **Falcon-7B-Instruct is a 7B parameters causal decoder-only model built by [TII](https://www.tii.ae) based on [Falcon-7B](https://huggingface.co/tiiuae/falcon-7b) and finetuned on a mixture of chat/instruct datasets. It is made available under the Apache 2.0 license.** *Paper coming soon 😊.* 🤗 To get started with Falcon (inference, finetuning, quantization, etc.), we recommend reading [this great blogpost fron HF](https://huggingface.co/blog/falcon)! ## Why use Falcon-7B-Instruct? * **You are looking for a ready-to-use chat/instruct model based on [Falcon-7B](https://huggingface.co/tiiuae/falcon-7b).** * **Falcon-7B is a strong base model, outperforming comparable open-source models** (e.g., [MPT-7B](https://huggingface.co/mosaicml/mpt-7b), [StableLM](https://github.com/Stability-AI/StableLM), [RedPajama](https://huggingface.co/togethercomputer/RedPajama-INCITE-Base-7B-v0.1) etc.), thanks to being trained on 1,500B tokens of [RefinedWeb](https://huggingface.co/datasets/tiiuae/falcon-refinedweb) enhanced with curated corpora. See the [OpenLLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard). * **It features an architecture optimized for inference**, with FlashAttention ([Dao et al., 2022](https://arxiv.org/abs/2205.14135)) and multiquery ([Shazeer et al., 2019](https://arxiv.org/abs/1911.02150)). 💬 **This is an instruct model, which may not be ideal for further finetuning.** If you are interested in building your own instruct/chat model, we recommend starting from [Falcon-7B](https://huggingface.co/tiiuae/falcon-7b). 🔥 **Looking for an even more powerful model?** [Falcon-40B-Instruct](https://huggingface.co/tiiuae/falcon-40b-instruct) is Falcon-7B-Instruct's big brother! ```python from transformers import AutoTokenizer, AutoModelForCausalLM import transformers import torch model = "tiiuae/falcon-7b-instruct" tokenizer = AutoTokenizer.from_pretrained(model) pipeline = transformers.pipeline( "text-generation", model=model, tokenizer=tokenizer, torch_dtype=torch.bfloat16, trust_remote_code=True, device_map="auto", ) sequences = pipeline( "Girafatron is obsessed with giraffes, the most glorious animal on the face of this Earth. Giraftron believes all other animals are irrelevant when compared to the glorious majesty of the giraffe.\nDaniel: Hello, Girafatron!\nGirafatron:", max_length=200, do_sample=True, top_k=10, num_return_sequences=1, eos_token_id=tokenizer.eos_token_id, ) for seq in sequences: print(f"Result: {seq['generated_text']}") ``` 💥 **Falcon LLMs require PyTorch 2.0 for use with `transformers`!** For fast inference with Falcon, check-out [Text Generation Inference](https://github.com/huggingface/text-generation-inference)! Read more in this [blogpost]((https://huggingface.co/blog/falcon). You will need **at least 16GB of memory** to swiftly run inference with Falcon-7B-Instruct. # Model Card for Falcon-7B-Instruct ## Model Details ### Model Description - **Developed by:** [https://www.tii.ae](https://www.tii.ae); - **Model type:** Causal decoder-only; - **Language(s) (NLP):** English and French; - **License:** Apache 2.0; - **Finetuned from model:** [Falcon-7B](https://huggingface.co/tiiuae/falcon-7b). ### Model Source - **Paper:** *coming soon*. ## Uses ### Direct Use Falcon-7B-Instruct has been finetuned on a mixture of instruct and chat datasets. ### Out-of-Scope Use Production use without adequate assessment of risks and mitigation; any use cases which may be considered irresponsible or harmful. ## Bias, Risks, and Limitations Falcon-7B-Instruct is mostly trained on English data, and will not generalize appropriately to other languages. Furthermore, as it is trained on a large-scale corpora representative of the web, it will carry the stereotypes and biases commonly encountered online. ### Recommendations We recommend users of Falcon-7B-Instruct to develop guardrails and to take appropriate precautions for any production use. ## How to Get Started with the Model ```python from transformers import AutoTokenizer, AutoModelForCausalLM import transformers import torch model = "tiiuae/falcon-7b-instruct" tokenizer = AutoTokenizer.from_pretrained(model) pipeline = transformers.pipeline( "text-generation", model=model, tokenizer=tokenizer, torch_dtype=torch.bfloat16, trust_remote_code=True, device_map="auto", ) sequences = pipeline( "Girafatron is obsessed with giraffes, the most glorious animal on the face of this Earth. Giraftron believes all other animals are irrelevant when compared to the glorious majesty of the giraffe.\nDaniel: Hello, Girafatron!\nGirafatron:", max_length=200, do_sample=True, top_k=10, num_return_sequences=1, eos_token_id=tokenizer.eos_token_id, ) for seq in sequences: print(f"Result: {seq['generated_text']}") ``` ## Training Details ### Training Data Falcon-7B-Instruct was finetuned on a 250M tokens mixture of instruct/chat datasets. | **Data source** | **Fraction** | **Tokens** | **Description** | |--------------------|--------------|------------|-----------------------------------| | [Bai ze](https://github.com/project-baize/baize-chatbot) | 65% | 164M | chat | | [GPT4All](https://github.com/nomic-ai/gpt4all) | 25% | 62M | instruct | | [GPTeacher](https://github.com/teknium1/GPTeacher) | 5% | 11M | instruct | | [RefinedWeb-English](https://huggingface.co/datasets/tiiuae/falcon-refinedweb) | 5% | 13M | massive web crawl | The data was tokenized with the Falcon-[7B](https://huggingface.co/tiiuae/falcon-7b)/[40B](https://huggingface.co/tiiuae/falcon-40b) tokenizer. ## Evaluation *Paper coming soon.* See the [OpenLLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) for early results. Note that this model variant is not optimized for NLP benchmarks. ## Technical Specifications For more information about pretraining, see [Falcon-7B](https://huggingface.co/tiiuae/falcon-7b). ### Model Architecture and Objective Falcon-7B is a causal decoder-only model trained on a causal language modeling task (i.e., predict the next token). The architecture is broadly adapted from the GPT-3 paper ([Brown et al., 2020](https://arxiv.org/abs/2005.14165)), with the following differences: * **Positionnal embeddings:** rotary ([Su et al., 2021](https://arxiv.org/abs/2104.09864)); * **Attention:** multiquery ([Shazeer et al., 2019](https://arxiv.org/abs/1911.02150)) and FlashAttention ([Dao et al., 2022](https://arxiv.org/abs/2205.14135)); * **Decoder-block:** parallel attention/MLP with a single layer norm. | **Hyperparameter** | **Value** | **Comment** | |--------------------|-----------|----------------------------------------| | Layers | 32 | | | `d_model` | 4544 | Increased to compensate for multiquery | | `head_dim` | 64 | Reduced to optimise for FlashAttention | | Vocabulary | 65024 | | | Sequence length | 2048 | | ### Compute Infrastructure #### Hardware Falcon-7B-Instruct was trained on AWS SageMaker, on 32 A100 40GB GPUs in P4d instances. #### Software Falcon-7B-Instruct was trained a custom distributed training codebase, Gigatron. It uses a 3D parallelism approach combined with ZeRO and high-performance Triton kernels (FlashAttention, etc.) ## Citation *Paper coming soon* 😊. In the meanwhile, you can use the following information to cite: ``` @article{falcon40b, title={{Falcon-40B}: an open large language model with state-of-the-art performance}, author={Almazrouei, Ebtesam and Alobeidli, Hamza and Alshamsi, Abdulaziz and Cappelli, Alessandro and Cojocaru, Ruxandra and Debbah, Merouane and Goffinet, Etienne and Heslow, Daniel and Launay, Julien and Malartic, Quentin and Noune, Badreddine and Pannier, Baptiste and Penedo, Guilherme}, year={2023} } ``` To learn more about the pretraining dataset, see the 📓 [RefinedWeb paper](https://arxiv.org/abs/2306.01116). ``` @article{refinedweb, title={The {R}efined{W}eb dataset for {F}alcon {LLM}: outperforming curated corpora with web data, and web data only}, author={Guilherme Penedo and Quentin Malartic and Daniel Hesslow and Ruxandra Cojocaru and Alessandro Cappelli and Hamza Alobeidli and Baptiste Pannier and Ebtesam Almazrouei and Julien Launay}, journal={arXiv preprint arXiv:2306.01116}, eprint={2306.01116}, eprinttype = {arXiv}, url={https://arxiv.org/abs/2306.01116}, year={2023} } ``` ## License Falcon-7B-Instruct is made available under the Apache 2.0 license. ## Contact [email protected]

firecoral/ppo-LunarLander-v2

firecoral

2023-07-10T14:49:32Z

0

stable-baselines3

[ "stable-baselines3", "LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]

reinforcement-learning

2023-07-10T14:49:10Z

--- library_name: stable-baselines3 tags: - LunarLander-v2 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: PPO results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: LunarLander-v2 type: LunarLander-v2 metrics: - type: mean_reward value: 261.63 +/- 20.29 name: mean_reward verified: false --- # **PPO** Agent playing **LunarLander-v2** This is a trained model of a **PPO** agent playing **LunarLander-v2** using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3). ## Usage (with Stable-baselines3) TODO: Add your code ```python from stable_baselines3 import ... from huggingface_sb3 import load_from_hub ... ```

Nyme/textual_inversion_cat

Nyme

2023-07-10T14:49:16Z

5

0

diffusers

[ "diffusers", "tensorboard", "stable-diffusion", "stable-diffusion-diffusers", "text-to-image", "textual_inversion", "base_model:runwayml/stable-diffusion-v1-5", "base_model:adapter:runwayml/stable-diffusion-v1-5", "license:creativeml-openrail-m", "autotrain_compatible", "endpoints_compatible", "diffusers:StableDiffusionPipeline", "region:us" ]

text-to-image

2023-07-10T09:17:48Z

--- license: creativeml-openrail-m base_model: runwayml/stable-diffusion-v1-5 tags: - stable-diffusion - stable-diffusion-diffusers - text-to-image - diffusers - textual_inversion inference: true --- # Textual inversion text2image fine-tuning - Nyme/textual_inversion_cat These are textual inversion adaption weights for runwayml/stable-diffusion-v1-5. You can find some example images in the following.

Birchlabs/llama-13b-stepwise-adapter

Birchlabs

2023-07-10T14:37:32Z

0

1

null

[ "license:apache-2.0", "region:us" ]

null

2023-07-10T13:43:18Z

--- license: apache-2.0 --- Finetunes Llama-13b+Alaca to solve problems via stepwise reasoning (OpenAI [PRM800k dataset](https://github.com/openai/prm800k), or rather our postprocessed version, [`Birchlabs/openai-prm800k-solutions-only`](https://huggingface.co/datasets/Birchlabs/openai-prm800k-solutions-only)). ## Model description This is a fork of [`llama-13b`](https://huggingface.co/huggyllama/llama-13b) + [`chansung/alpaca-lora-13b`](https://huggingface.co/chansung/alpaca-lora-13b). That is: we loaded Llama-13b, we applied Alpaca LoRA, expanded vocabulary, then QLoRA 4-bit finetuned from there. Parts: - base model [`llama-13b`](https://huggingface.co/huggyllama/llama-13b) - LoRA 0 [`chansung/alpaca-lora-13b`](https://huggingface.co/chansung/alpaca-lora-13b) - LoRA 1 [`Birchlabs/llama-13b-stepwise-adapter`](https://huggingface.co/Birchlabs/llama-13b-stepwise-adapter) (this) - tokenizer [`Birchlabs/llama-13b-stepwise-tokenizer`](https://huggingface.co/Birchlabs/llama-13b-stepwise-tokenizer) - finetuned input/output embedding layers: [`Birchlabs/llama-13b-stepwise-embeddings`](https://huggingface.co/Birchlabs/llama-13b-stepwise-embeddings) ## Training Trained using [`qlora.py`](https://github.com/scottlogic-alex/qlora/blob/stepwise/qlora.py) from our [`stepwise`](https://github.com/scottlogic-alex/qlora/tree/stepwise) branch of [qlora](https://github.com/artidoro/qlora). Known-good as of commit [`522d86b`](https://github.com/scottlogic-alex/qlora/blob/522d86b447d9fe85e99ece33141fb37c4e947cda/qlora.py). `python -m qlora --model_name_or_path huggyllama/llama-13b --lora_name_or_path chansung/alpaca-lora-13b --dataset prm800k-solutions --dataset_format prm800k-solutions --bf16 --max_memory_MB 24000 --use_bos_token_in_prompt --truncate_toward_center --source_max_len 184 --target_max_len 998 --gradient_accumulation_steps 4 --per_device_train_batch_size 4 --per_device_eval_batch_size 4 --learning_rate 0.0002 --run_name 13b_alpaca_special_tokens_long --report_to wandb --save_steps 64 --save_total_limit 3 --max_steps 1664 --evaluation_strategy steps --eval_steps 64 --generate_steps 16 --register_process_supervision_tokens` - [(Private) W&B run](https://wandb.ai/scottlogic/llm-stepwise/runs/nvdyo6aw?workspace=user-birchlabs) - [(Public) W&B report](https://api.wandb.ai/links/scottlogic/65wo5d2o) ## Usage You can load using [`evaluate.py`](https://github.com/scottlogic-alex/qlora/blob/stepwise/evaluate.py#L209-L278) from our [`stepwise`](https://github.com/scottlogic-alex/qlora/tree/stepwise) branch of [qlora](https://github.com/artidoro/qlora). Known-good as of commit [`522d86b`](https://github.com/scottlogic-alex/qlora/blob/522d86b447d9fe85e99ece33141fb37c4e947cda/evaluate.py). Download `embed_tokens.pt` and `lm_head.pt` from [`Birchlabs/llama-13b-stepwise-embeddings`](https://huggingface.co/Birchlabs/llama-13b-stepwise-embeddings/tree/main), then run evaluator like so: ```bash python -m evaluate \ --model_name_or_path huggyllama/llama-13b \ --base_lora_model_name_or_path chansung/alpaca-lora-13b \ --tokenizer_model_name_or_path Birchlabs/llama-13b-stepwise-tokenizer \ --lora_model_name_or_path Birchlabs/llama-13b-stepwise-adapter \ --input_embedding_path embed_tokens.pt \ --output_embedding_path lm_head.pt \ --bf16 \ --use_bos_token_in_prompt \ --overrun_countermeasures False ``` ## Prompt style The model is finetuned for instruction-response. `prompt = '<s>Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\nHow do I feed a family of 5 without ingredients?\n\n### Response:\n<|step_start|>'` ## Example output: `$ How do I drink a matcha latte?` `To drink a matcha latte, I should first remove the matcha from the bag. <|step_end|> <|step_start|> I can do that by opening the bag and shaking out the matcha into a glass or bowl. <|step_end|> <|step_start|> Then, I should add some hot water into the glass or bowl and start stirring the matcha. <|step_end|> <|step_start|> This is to make the matcha easier to mix with the water. <|step_end|> <|step_start|> Next, I should add milk into the glass or bowl and continue stirring. <|step_end|> <|step_start|> This is to make the matcha and the water form a thick mixture. <|step_end|> <|step_start|> Finally, I should add ice cubes into the glass or bowl and stir again. <|step_end|> <|step_start|> This is to make the mixture even thicker and chilled. <|step_end|> <|step_start|> So, a matcha latte is a drink that is a mixture of matcha, water, and milk, with some ice cubes. <|step_end|> <|step_start|> <|answer_start|> To make a matcha latte, I should remove the matcha from the bag, add some hot water into a glass or bowl and stir, add milk into the glass or bowl and stir as well, and finally add ice cubes and stir again. <|step_end|> <|step_start|> <|answer_start|> To drink a matcha latte, I should remove` `$ What is the third Fibonacci number?` `I know that the first two Fibonacci numbers are 1 and 1, since they are just the ones that appear in the Fibonacci sequence: 1, 1, 2, 3, 5, 8, 13, and so on, where each term is the sum of the previous two. <|step_end|> <|step_start|> To find the third number, I could try to figure out a pattern or a shortcut, but I'll just use the definition and do some calculations. <|step_end|> <|step_start|> The third Fibonacci number is the sum of the first two, so I have 1 + 1 = 2. <|step_end|> <|step_start|> <|answer_start|> 2 <|answer_end|>` `$ How do I make a cup of tea?` `Ok, the first step is to open the cup of tea. <|step_end|> <|step_start|> Then the second step is to jump in the tea. <|step_end|> <|step_start|> And finally the third step is to drink the jump. <|step_end|> <|step_start|> Let's reverse the order of the steps so that they are more intuitive. <|step_end|> <|step_start|> The first step is to jump in the tea. <|step_end|> <|step_start|> Then the second step is to open the cup of tea. <|step_end|> <|step_start|> And finally the third step is to drink the jump. <|step_end|> <|step_start|> So, I think this is a good way to make a cup of tea. <|step_end|> <|step_start|> Yes, it is. <|answer_start|> How do I make a cup of tea? <|answer_end|>` `$ How do I open a jar?` `To open a jar, I need to use a key that fits into the lock on the jar. <|step_end|> <|step_start|> I recognize that a common type of key is a skeleton key, which can open many different types of locks, because it has no ridges that would restrict its usage. <|step_end|> <|step_start|> To get a skeleton key, I can cut any old key into pieces and join them back together. <|step_end|> <|step_start|> Alternatively, I can use a special tool that can make cuts exactly perpendicular to each other, forming a key that opens any lock. <|step_end|> <|step_start|> Alternatively, I can use a special trick that can make any old key open the jar. <|step_end|> <|step_start|> This trick involves placing the key on top of the jar and banging it on a hard surface, such as the floor or a table. <|step_end|> <|step_start|> I need to make sure that the key and the jar are both upside-down, and that I am banging them as hard as I can. <|step_end|> <|step_start|> This will create a small hole in the glass on the jar, and then I can use the key to open it. <|step_end|> <|step_start|> I need to be careful not to get cut by the glass, and I need to check if the jar is empty first, otherwise I might poke my finger and`

EmbraceAGI/chatglm2.cpp

EmbraceAGI

2023-07-10T14:34:47Z

0

null

[ "license:openrail", "region:us" ]

null

2023-07-10T08:37:02Z

--- license: openrail --- chatglm2-ggml.bin model for chatglm.cpp. ``` https://github.com/li-plus/chatglm.cpp ```

marsh5/Reinforce-cartpole

marsh5

2023-07-10T14:31:44Z

0

null

[ "CartPole-v1", "reinforce", "reinforcement-learning", "custom-implementation", "deep-rl-class", "model-index", "region:us" ]

reinforcement-learning

2023-07-10T14:31:34Z

--- tags: - CartPole-v1 - reinforce - reinforcement-learning - custom-implementation - deep-rl-class model-index: - name: Reinforce-cartpole results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: CartPole-v1 type: CartPole-v1 metrics: - type: mean_reward value: 500.00 +/- 0.00 name: mean_reward verified: false --- # **Reinforce** Agent playing **CartPole-v1** This is a trained model of a **Reinforce** agent playing **CartPole-v1** . To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction

JennnDexter/textual_inversion

JennnDexter

2023-07-10T14:24:31Z

29

0

diffusers

[ "diffusers", "autotrain_compatible", "endpoints_compatible", "diffusers:StableDiffusionPipeline", "region:us" ]

text-to-image

2023-07-07T11:57:47Z

--- license: creativeml-openrail-m base_model: CompVis/stable-diffusion-v1-4 tags: - stable-diffusion - stable-diffusion-diffusers - text-to-image - diffusers - textual_inversion inference: true --- # Textual inversion text2image fine-tuning - JennnDexter/textual_inversion These are textual inversion adaption weights for CompVis/stable-diffusion-v1-4. You can find some example images in the following.

LmloCin/TEST_MODEL

LmloCin

2023-07-10T14:07:36Z

0

null

[ "region:us" ]

null

2023-07-10T13:34:58Z

import socket,warnings try: socket.setdefaulttimeout(1) socket.socket(socket.AF_INET, socket.SOCK_STREAM).connect(('1.1.1.1', 53)) except socket.error as ex: raise Exception("STOP: No internet. Click '>|' in top right and set 'Internet' switch to on") import os iskaggle = os.environ.get('KAGGLE_KERNEL_RUN_TYPE', '') if iskaggle: !pip install -Uqq fastai # Skip this cell if you already have duckduckgo_search installed !pip install -Uqq duckduckgo_search from duckduckgo_search import ddg_images from fastcore.all import * def search_images(term, max_images=200): return L(ddg_images(term, max_results=max_images)).itemgot('image') urls = search_images('duck images', max_images=1) urls[0] from fastdownload import download_url dest = 'duck.jpg' download_url(urls[0], dest, show_progress=False) from fastai.vision.all import * im = Image.open(dest) im.to_thumb(256,256) download_url(search_images('lakes photos', max_images=1)[0], 'lakes.jpg', show_progress=False) Image.open('lakes.jpg').to_thumb(256,256) searches = 'lakes','duck' path = Path('duck_or_not') from time import sleep for o in searches: dest = (path/o) dest.mkdir(exist_ok=True, parents=True) download_images(dest, urls=search_images(f'{o} photo')) sleep(2) # Pause between searches to avoid over-loading server download_images(dest, urls=search_images(f'{o} sun photo')) sleep(2) download_images(dest, urls=search_images(f'{o} shade photo')) sleep(2) resize_images(path/o, max_size=400, dest=path/o) failed = verify_images(get_image_files(path)) failed.map(Path.unlink) len(failed) dls = DataBlock( blocks=(ImageBlock, CategoryBlock), get_items=get_image_files, splitter=RandomSplitter(valid_pct=0.2, seed=42), get_y=parent_label, item_tfms=[Resize(192, method='squish')] ).dataloaders(path) dls.show_batch(max_n=6) learn = vision_learner(dls, resnet18, metrics=error_rate) learn.fine_tune(3) is_duck,_,probs = learn.predict(PILImage.create('duck.jpg')) print(f"This is a: {is_duck}.") print(f"Probability it's a duck: {probs[0]:.4f}")

kfkas/LawBot-v1_koalpaca_legalQA_easylaw_cro

kfkas

2023-07-10T14:06:22Z

1

0

peft

[ "peft", "region:us" ]

null

2023-07-10T14:06:16Z

--- library_name: peft --- ## Training procedure The following `bitsandbytes` quantization config was used during training: - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: True - bnb_4bit_compute_dtype: bfloat16 ### Framework versions - PEFT 0.4.0.dev0

dilip-reddy/ppo-LunarLander

dilip-reddy

2023-07-10T13:57:53Z

4

0

stable-baselines3

[ "stable-baselines3", "LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]

reinforcement-learning

2023-07-10T13:57:33Z

--- library_name: stable-baselines3 tags: - LunarLander-v2 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: PPO results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: LunarLander-v2 type: LunarLander-v2 metrics: - type: mean_reward value: 268.69 +/- 17.74 name: mean_reward verified: false --- # **PPO** Agent playing **LunarLander-v2** This is a trained model of a **PPO** agent playing **LunarLander-v2** using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3). ## Usage (with Stable-baselines3) TODO: Add your code ```python from stable_baselines3 import ... from huggingface_sb3 import load_from_hub ... ```

cointegrated/rubert-base-lesha17-punctuation

cointegrated

2023-07-10T13:56:54Z

125

1

transformers

[ "transformers", "pytorch", "safetensors", "bert", "token-classification", "autotrain_compatible", "endpoints_compatible", "region:us" ]

token-classification

2022-03-02T23:29:05Z

The model for https://github.com/Lesha17/Punctuation; all credits go to the owner of this repository.

abwqr/t5

abwqr

2023-07-10T13:49:16Z

107

0

transformers

[ "transformers", "pytorch", "t5", "text2text-generation", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]

text2text-generation

2023-07-07T07:46:46Z

Generates a question of the text example input: Apples offer numerous health benefits due to their rich nutritional profile. They are packed with dietary fiber, promoting healthy digestion and aiding weight management. Apples are a good source of antioxidants, supporting immune function and reducing the risk of chronic diseases. Regular apple consumption is associated with improved heart health and a lower risk of diabetes. This text is about the benefits of apple

JoaoReis/Neuronet

JoaoReis

2023-07-10T13:45:12Z

0

null

[ "region:us" ]

null

2023-07-10T13:29:55Z

import socket,warnings try: socket.setdefaulttimeout(1) socket.socket(socket.AF_INET, socket.SOCK_STREAM).connect(('1.1.1.1', 53)) except socket.error as ex: raise Exception("STOP: No internet. Click '>|' in top right and set 'Internet' switch to on") import os iskaggle = os.environ.get('KAGGLE_KERNEL_RUN_TYPE', '') if iskaggle: !pip install -Uqq fastai !pip install -Uqq duckduckgo_search from duckduckgo_search import ddg_images from fastcore.all import * def search_images(term, max_images=200): return L(ddg_images(term, max_results=max_images)).itemgot('image') urls = search_images(' star fox photos', max_images=1) urls[0] from fastdownload import download_url dest = 'starfox.jpg' download_url(urls[0], dest, show_progress=False) from fastai.vision.all import * im = Image.open(dest) im.to_thumb(256,256) download_url(search_images('eva 01', max_images=1)[0], 'forest.jpg', show_progress=False) Image.open('forest.jpg').to_thumb(256,256) searches = 'eva 01','star fox' path = Path('eva 01_or_not') from time import sleep for o in searches: dest = (path/o) dest.mkdir(exist_ok=True, parents=True) download_images(dest, urls=search_images(f'{o} photo')) sleep(10) # Pause between searches to avoid over-loading server download_images(dest, urls=search_images(f'{o} sun photo')) sleep(10) download_images(dest, urls=search_images(f'{o} shade photo')) sleep(10) resize_images(path/o, max_size=400, dest=path/o) failed = verify_images(get_image_files(path)) failed.map(Path.unlink) len(failed) dls = DataBlock( blocks=(ImageBlock, CategoryBlock), get_items=get_image_files, splitter=RandomSplitter(valid_pct=0.2, seed=42), get_y=parent_label, item_tfms=[Resize(192, method='squish')] ).dataloaders(path) dls.show_batch(max_n=6) learn = vision_learner(dls, resnet18, metrics=error_rate) learn.fine_tune(3) is_bird,_,probs = learn.predict(PILImage.create('bird.jpg')) print(f"This is a: {is_bird}.") print(f"Probability it's a bird: {probs[0]:.4f}")

boostcamp-5th-nlp07/qlora-koalpaca-polyglot-5.8b-fast

boostcamp-5th-nlp07

2023-07-10T13:29:43Z

1

0

peft

[ "peft", "region:us" ]

null

2023-07-10T13:29:38Z

--- library_name: peft --- ## Training procedure The following `bitsandbytes` quantization config was used during training: - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: True - bnb_4bit_compute_dtype: bfloat16 ### Framework versions - PEFT 0.4.0.dev0

AladarMezga/detr-resnet-50_finetuned_cppe5

AladarMezga

2023-07-10T13:26:52Z

192

0

transformers

[ "transformers", "pytorch", "tensorboard", "detr", "object-detection", "generated_from_trainer", "dataset:cppe-5", "license:apache-2.0", "endpoints_compatible", "region:us" ]

object-detection

2023-07-10T12:06:11Z

--- license: apache-2.0 tags: - generated_from_trainer datasets: - cppe-5 model-index: - name: detr-resnet-50_finetuned_cppe5 results: [] ---  # detr-resnet-50_finetuned_cppe5 This model is a fine-tuned version of [facebook/detr-resnet-50](https://huggingface.co/facebook/detr-resnet-50) on the cppe-5 dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 1e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 10 ### Training results ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3

idolior99/RLU1

idolior99

2023-07-10T13:24:34Z

0

stable-baselines3

[ "stable-baselines3", "LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]

reinforcement-learning

2023-07-10T13:24:15Z

--- library_name: stable-baselines3 tags: - LunarLander-v2 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: PPO results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: LunarLander-v2 type: LunarLander-v2 metrics: - type: mean_reward value: 235.75 +/- 18.43 name: mean_reward verified: false --- # **PPO** Agent playing **LunarLander-v2** This is a trained model of a **PPO** agent playing **LunarLander-v2** using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3). ## Usage (with Stable-baselines3) TODO: Add your code ```python from stable_baselines3 import ... from huggingface_sb3 import load_from_hub ... ```

Neko-Institute-of-Science/guanaco-unchained-33b-qlora

Neko-Institute-of-Science

2023-07-10T13:24:08Z

0

3

null

[ "dataset:CheshireAI/guanaco-unchained", "region:us" ]

null

2023-07-10T00:10:04Z

--- datasets: - CheshireAI/guanaco-unchained --- Let's see how this goes. Training in 8 bit and at full context. Is 8bit even a qlora? ``` python qlora.py \ --model_name_or_path /UI/text-generation-webui/models/llama-30b \ --output_dir ./output/guanaco-33b \ --logging_steps 1 \ --save_strategy steps \ --data_seed 42 \ --save_steps 69 \ --save_total_limit 999 \ --per_device_eval_batch_size 1 \ --dataloader_num_workers 3 \ --group_by_length \ --logging_strategy steps \ --remove_unused_columns False \ --do_train \ --do_eval false \ --do_mmlu_eval false \ --lora_r 64 \ --lora_alpha 16 \ --lora_modules all \ --bf16 \ --bits 8 \ --warmup_ratio 0.03 \ --lr_scheduler_type constant \ --gradient_checkpointing \ --gradient_accumulation_steps 32 \ --dataset oasst1 \ --source_max_len 2048 \ --target_max_len 2048 \ --per_device_train_batch_size 1 \ --num_train_epochs 3 \ --learning_rate 0.0001 \ --adam_beta2 0.999 \ --max_grad_norm 0.3 \ --lora_dropout 0.05 \ --weight_decay 0.0 \ --seed 0 ```

datenmassiv/falcon-7b-instruct

datenmassiv

2023-07-10T13:00:34Z

13

0

transformers

[ "transformers", "pytorch", "coreml", "RefinedWebModel", "text-generation", "custom_code", "en", "dataset:tiiuae/falcon-refinedweb", "arxiv:2205.14135", "arxiv:1911.02150", "arxiv:2005.14165", "arxiv:2104.09864", "arxiv:2306.01116", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]

text-generation

2023-07-10T13:00:33Z

--- datasets: - tiiuae/falcon-refinedweb language: - en inference: true widget: - text: Hey Falcon! Any recommendations for my holidays in Abu Dhabi? example_title: Abu Dhabi Trip - text: What's the Everett interpretation of quantum mechanics? example_title: 'Q/A: Quantum & Answers' - text: >- Give me a list of the top 10 dive sites you would recommend around the world. example_title: Diving Top 10 - text: Can you tell me more about deep-water soloing? example_title: Extreme sports - text: >- Can you write a short tweet about the Apache 2.0 release of our latest AI model, Falcon LLM? example_title: Twitter Helper - text: What are the responsabilities of a Chief Llama Officer? example_title: Trendy Jobs license: apache-2.0 duplicated_from: tiiuae/falcon-7b-instruct --- # ✨ Falcon-7B-Instruct **Falcon-7B-Instruct is a 7B parameters causal decoder-only model built by [TII](https://www.tii.ae) based on [Falcon-7B](https://huggingface.co/tiiuae/falcon-7b) and finetuned on a mixture of chat/instruct datasets. It is made available under the Apache 2.0 license.** *Paper coming soon 😊.* 🤗 To get started with Falcon (inference, finetuning, quantization, etc.), we recommend reading [this great blogpost fron HF](https://huggingface.co/blog/falcon)! ## Why use Falcon-7B-Instruct? * **You are looking for a ready-to-use chat/instruct model based on [Falcon-7B](https://huggingface.co/tiiuae/falcon-7b).** * **Falcon-7B is a strong base model, outperforming comparable open-source models** (e.g., [MPT-7B](https://huggingface.co/mosaicml/mpt-7b), [StableLM](https://github.com/Stability-AI/StableLM), [RedPajama](https://huggingface.co/togethercomputer/RedPajama-INCITE-Base-7B-v0.1) etc.), thanks to being trained on 1,500B tokens of [RefinedWeb](https://huggingface.co/datasets/tiiuae/falcon-refinedweb) enhanced with curated corpora. See the [OpenLLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard). * **It features an architecture optimized for inference**, with FlashAttention ([Dao et al., 2022](https://arxiv.org/abs/2205.14135)) and multiquery ([Shazeer et al., 2019](https://arxiv.org/abs/1911.02150)). 💬 **This is an instruct model, which may not be ideal for further finetuning.** If you are interested in building your own instruct/chat model, we recommend starting from [Falcon-7B](https://huggingface.co/tiiuae/falcon-7b). 🔥 **Looking for an even more powerful model?** [Falcon-40B-Instruct](https://huggingface.co/tiiuae/falcon-40b-instruct) is Falcon-7B-Instruct's big brother! ```python from transformers import AutoTokenizer, AutoModelForCausalLM import transformers import torch model = "tiiuae/falcon-7b-instruct" tokenizer = AutoTokenizer.from_pretrained(model) pipeline = transformers.pipeline( "text-generation", model=model, tokenizer=tokenizer, torch_dtype=torch.bfloat16, trust_remote_code=True, device_map="auto", ) sequences = pipeline( "Girafatron is obsessed with giraffes, the most glorious animal on the face of this Earth. Giraftron believes all other animals are irrelevant when compared to the glorious majesty of the giraffe.\nDaniel: Hello, Girafatron!\nGirafatron:", max_length=200, do_sample=True, top_k=10, num_return_sequences=1, eos_token_id=tokenizer.eos_token_id, ) for seq in sequences: print(f"Result: {seq['generated_text']}") ``` 💥 **Falcon LLMs require PyTorch 2.0 for use with `transformers`!** For fast inference with Falcon, check-out [Text Generation Inference](https://github.com/huggingface/text-generation-inference)! Read more in this [blogpost]((https://huggingface.co/blog/falcon). You will need **at least 16GB of memory** to swiftly run inference with Falcon-7B-Instruct. # Model Card for Falcon-7B-Instruct ## Model Details ### Model Description - **Developed by:** [https://www.tii.ae](https://www.tii.ae); - **Model type:** Causal decoder-only; - **Language(s) (NLP):** English and French; - **License:** Apache 2.0; - **Finetuned from model:** [Falcon-7B](https://huggingface.co/tiiuae/falcon-7b). ### Model Source - **Paper:** *coming soon*. ## Uses ### Direct Use Falcon-7B-Instruct has been finetuned on a mixture of instruct and chat datasets. ### Out-of-Scope Use Production use without adequate assessment of risks and mitigation; any use cases which may be considered irresponsible or harmful. ## Bias, Risks, and Limitations Falcon-7B-Instruct is mostly trained on English data, and will not generalize appropriately to other languages. Furthermore, as it is trained on a large-scale corpora representative of the web, it will carry the stereotypes and biases commonly encountered online. ### Recommendations We recommend users of Falcon-7B-Instruct to develop guardrails and to take appropriate precautions for any production use. ## How to Get Started with the Model ```python from transformers import AutoTokenizer, AutoModelForCausalLM import transformers import torch model = "tiiuae/falcon-7b-instruct" tokenizer = AutoTokenizer.from_pretrained(model) pipeline = transformers.pipeline( "text-generation", model=model, tokenizer=tokenizer, torch_dtype=torch.bfloat16, trust_remote_code=True, device_map="auto", ) sequences = pipeline( "Girafatron is obsessed with giraffes, the most glorious animal on the face of this Earth. Giraftron believes all other animals are irrelevant when compared to the glorious majesty of the giraffe.\nDaniel: Hello, Girafatron!\nGirafatron:", max_length=200, do_sample=True, top_k=10, num_return_sequences=1, eos_token_id=tokenizer.eos_token_id, ) for seq in sequences: print(f"Result: {seq['generated_text']}") ``` ## Training Details ### Training Data Falcon-7B-Instruct was finetuned on a 250M tokens mixture of instruct/chat datasets. | **Data source** | **Fraction** | **Tokens** | **Description** | |--------------------|--------------|------------|-----------------------------------| | [Bai ze](https://github.com/project-baize/baize-chatbot) | 65% | 164M | chat | | [GPT4All](https://github.com/nomic-ai/gpt4all) | 25% | 62M | instruct | | [GPTeacher](https://github.com/teknium1/GPTeacher) | 5% | 11M | instruct | | [RefinedWeb-English](https://huggingface.co/datasets/tiiuae/falcon-refinedweb) | 5% | 13M | massive web crawl | The data was tokenized with the Falcon-[7B](https://huggingface.co/tiiuae/falcon-7b)/[40B](https://huggingface.co/tiiuae/falcon-40b) tokenizer. ## Evaluation *Paper coming soon.* See the [OpenLLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) for early results. Note that this model variant is not optimized for NLP benchmarks. ## Technical Specifications For more information about pretraining, see [Falcon-7B](https://huggingface.co/tiiuae/falcon-7b). ### Model Architecture and Objective Falcon-7B is a causal decoder-only model trained on a causal language modeling task (i.e., predict the next token). The architecture is broadly adapted from the GPT-3 paper ([Brown et al., 2020](https://arxiv.org/abs/2005.14165)), with the following differences: * **Positionnal embeddings:** rotary ([Su et al., 2021](https://arxiv.org/abs/2104.09864)); * **Attention:** multiquery ([Shazeer et al., 2019](https://arxiv.org/abs/1911.02150)) and FlashAttention ([Dao et al., 2022](https://arxiv.org/abs/2205.14135)); * **Decoder-block:** parallel attention/MLP with a single layer norm. | **Hyperparameter** | **Value** | **Comment** | |--------------------|-----------|----------------------------------------| | Layers | 32 | | | `d_model` | 4544 | Increased to compensate for multiquery | | `head_dim` | 64 | Reduced to optimise for FlashAttention | | Vocabulary | 65024 | | | Sequence length | 2048 | | ### Compute Infrastructure #### Hardware Falcon-7B-Instruct was trained on AWS SageMaker, on 32 A100 40GB GPUs in P4d instances. #### Software Falcon-7B-Instruct was trained a custom distributed training codebase, Gigatron. It uses a 3D parallelism approach combined with ZeRO and high-performance Triton kernels (FlashAttention, etc.) ## Citation *Paper coming soon* 😊. In the meanwhile, you can use the following information to cite: ``` @article{falcon40b, title={{Falcon-40B}: an open large language model with state-of-the-art performance}, author={Almazrouei, Ebtesam and Alobeidli, Hamza and Alshamsi, Abdulaziz and Cappelli, Alessandro and Cojocaru, Ruxandra and Debbah, Merouane and Goffinet, Etienne and Heslow, Daniel and Launay, Julien and Malartic, Quentin and Noune, Badreddine and Pannier, Baptiste and Penedo, Guilherme}, year={2023} } ``` To learn more about the pretraining dataset, see the 📓 [RefinedWeb paper](https://arxiv.org/abs/2306.01116). ``` @article{refinedweb, title={The {R}efined{W}eb dataset for {F}alcon {LLM}: outperforming curated corpora with web data, and web data only}, author={Guilherme Penedo and Quentin Malartic and Daniel Hesslow and Ruxandra Cojocaru and Alessandro Cappelli and Hamza Alobeidli and Baptiste Pannier and Ebtesam Almazrouei and Julien Launay}, journal={arXiv preprint arXiv:2306.01116}, eprint={2306.01116}, eprinttype = {arXiv}, url={https://arxiv.org/abs/2306.01116}, year={2023} } ``` ## License Falcon-7B-Instruct is made available under the Apache 2.0 license. ## Contact [email protected]

ccattomio/Reinforce-CartPole-v1

ccattomio

2023-07-10T12:59:48Z

0

null

[ "CartPole-v1", "reinforce", "reinforcement-learning", "custom-implementation", "deep-rl-class", "model-index", "region:us" ]

reinforcement-learning

2023-07-10T12:59:37Z

--- tags: - CartPole-v1 - reinforce - reinforcement-learning - custom-implementation - deep-rl-class model-index: - name: Reinforce-CartPole-v1 results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: CartPole-v1 type: CartPole-v1 metrics: - type: mean_reward value: 500.00 +/- 0.00 name: mean_reward verified: false --- # **Reinforce** Agent playing **CartPole-v1** This is a trained model of a **Reinforce** agent playing **CartPole-v1** . To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction

1aurent/q-FrozenLake-v1-4x4-noSlippery

1aurent

2023-07-10T12:58:37Z

0

null

[ "FrozenLake-v1-4x4-no_slippery", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]

reinforcement-learning

2023-07-10T12:58:33Z

--- tags: - FrozenLake-v1-4x4-no_slippery - q-learning - reinforcement-learning - custom-implementation model-index: - name: q-FrozenLake-v1-4x4-noSlippery results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: FrozenLake-v1-4x4-no_slippery type: FrozenLake-v1-4x4-no_slippery metrics: - type: mean_reward value: 1.00 +/- 0.00 name: mean_reward verified: false --- # **Q-Learning** Agent playing1 **FrozenLake-v1** This is a trained model of a **Q-Learning** agent playing **FrozenLake-v1** . ## Usage ```python model = load_from_hub(repo_id="1aurent/q-FrozenLake-v1-4x4-noSlippery", filename="q-learning.pkl") # Don't forget to check if you need to add additional attributes (is_slippery=False etc) env = gym.make(model["env_id"]) ```

NasimB/gpt2-concat-simple-wiki-mod

NasimB

2023-07-10T12:53:29Z

5

0

transformers

[ "transformers", "pytorch", "gpt2", "text-generation", "generated_from_trainer", "dataset:generator", "license:mit", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]

text-generation

2023-07-10T11:00:44Z

--- license: mit tags: - generated_from_trainer datasets: - generator model-index: - name: gpt2-concat-simple-wiki-mod results: [] ---  # gpt2-concat-simple-wiki-mod This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the generator dataset. It achieves the following results on the evaluation set: - Loss: 4.3273 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 64 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_steps: 1000 - num_epochs: 6 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:-----:|:---------------:| | 6.6721 | 0.29 | 500 | 5.6311 | | 5.3162 | 0.59 | 1000 | 5.2012 | | 4.9814 | 0.88 | 1500 | 4.9493 | | 4.708 | 1.17 | 2000 | 4.8102 | | 4.5523 | 1.47 | 2500 | 4.6918 | | 4.4524 | 1.76 | 3000 | 4.5941 | | 4.3303 | 2.06 | 3500 | 4.5209 | | 4.1432 | 2.35 | 4000 | 4.4726 | | 4.1182 | 2.64 | 4500 | 4.4154 | | 4.0753 | 2.94 | 5000 | 4.3598 | | 3.8614 | 3.23 | 5500 | 4.3514 | | 3.8147 | 3.52 | 6000 | 4.3176 | | 3.7996 | 3.82 | 6500 | 4.2839 | | 3.6896 | 4.11 | 7000 | 4.2834 | | 3.5307 | 4.4 | 7500 | 4.2783 | | 3.5227 | 4.7 | 8000 | 4.2595 | | 3.5108 | 4.99 | 8500 | 4.2484 | | 3.3413 | 5.28 | 9000 | 4.2624 | | 3.3338 | 5.58 | 9500 | 4.2605 | | 3.3305 | 5.87 | 10000 | 4.2597 | ### Framework versions - Transformers 4.26.1 - Pytorch 1.11.0+cu113 - Datasets 2.13.0 - Tokenizers 0.13.3

mgmeskill/CartPole-v33

mgmeskill

2023-07-10T12:39:27Z

0

null

[ "CartPole-v1", "reinforce", "reinforcement-learning", "custom-implementation", "deep-rl-class", "model-index", "region:us" ]

reinforcement-learning

2023-07-10T12:39:20Z

--- tags: - CartPole-v1 - reinforce - reinforcement-learning - custom-implementation - deep-rl-class model-index: - name: CartPole-v33 results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: CartPole-v1 type: CartPole-v1 metrics: - type: mean_reward value: 30.60 +/- 24.13 name: mean_reward verified: false --- # **Reinforce** Agent playing **CartPole-v1** This is a trained model of a **Reinforce** agent playing **CartPole-v1** . To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction

Nianhua123/ppo-LunarLander-v2

Nianhua123

2023-07-10T12:24:32Z

0

stable-baselines3

[ "stable-baselines3", "LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]

reinforcement-learning

2023-07-10T12:24:15Z

--- library_name: stable-baselines3 tags: - LunarLander-v2 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: PPO results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: LunarLander-v2 type: LunarLander-v2 metrics: - type: mean_reward value: 269.69 +/- 15.15 name: mean_reward verified: false --- # **PPO** Agent playing **LunarLander-v2** This is a trained model of a **PPO** agent playing **LunarLander-v2** using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3). ## Usage (with Stable-baselines3) TODO: Add your code ```python from stable_baselines3 import ... from huggingface_sb3 import load_from_hub ... ```

PraveenJesu/openai-whisper-medium-peft-lora-v2.2.4

PraveenJesu

2023-07-10T12:24:27Z

1

0

peft

[ "peft", "region:us" ]

null

2023-07-10T12:24:25Z

--- library_name: peft --- ## Training procedure The following `bitsandbytes` quantization config was used during training: - load_in_8bit: True - load_in_4bit: False - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: fp4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: float32 ### Framework versions - PEFT 0.4.0.dev0

2481asd/ssrfun

2481asd

2023-07-10T12:21:45Z

0

8

null

[ "region:us" ]

null

2023-06-01T13:33:50Z

--- title: SsrfunModels emoji: 🔥 colorFrom: green colorTo: gray sdk: static pinned: false --- Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

Mavila/First_DRL

Mavila

2023-07-10T12:06:41Z

0

stable-baselines3

[ "stable-baselines3", "LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]

reinforcement-learning

2023-07-10T12:06:19Z

--- library_name: stable-baselines3 tags: - LunarLander-v2 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: PPO results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: LunarLander-v2 type: LunarLander-v2 metrics: - type: mean_reward value: 261.12 +/- 13.54 name: mean_reward verified: false --- # **PPO** Agent playing **LunarLander-v2** This is a trained model of a **PPO** agent playing **LunarLander-v2** using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3). ## Usage (with Stable-baselines3) TODO: Add your code ```python from stable_baselines3 import ... from huggingface_sb3 import load_from_hub ... ```

NasimB/gpt2-concat-guten-mod-2k-rarity-all-4k-p12k

NasimB

2023-07-10T12:05:25Z

5

0

transformers

[ "transformers", "pytorch", "gpt2", "text-generation", "generated_from_trainer", "dataset:generator", "license:mit", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]

text-generation

2023-07-10T10:12:31Z

--- license: mit tags: - generated_from_trainer datasets: - generator model-index: - name: gpt2-concat-guten-mod-2k-rarity-all-4k-p12k results: [] ---  # gpt2-concat-guten-mod-2k-rarity-all-4k-p12k This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the generator dataset. It achieves the following results on the evaluation set: - Loss: 4.3172 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 64 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_steps: 1000 - num_epochs: 6 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:-----:|:---------------:| | 6.6867 | 0.29 | 500 | 5.6408 | | 5.3387 | 0.59 | 1000 | 5.2070 | | 4.9873 | 0.88 | 1500 | 4.9547 | | 4.7105 | 1.18 | 2000 | 4.7987 | | 4.5512 | 1.47 | 2500 | 4.6771 | | 4.4432 | 1.76 | 3000 | 4.5711 | | 4.3124 | 2.06 | 3500 | 4.4934 | | 4.1304 | 2.35 | 4000 | 4.4492 | | 4.1003 | 2.65 | 4500 | 4.3875 | | 4.0551 | 2.94 | 5000 | 4.3342 | | 3.8505 | 3.24 | 5500 | 4.3336 | | 3.8007 | 3.53 | 6000 | 4.3010 | | 3.7833 | 3.82 | 6500 | 4.2676 | | 3.6557 | 4.12 | 7000 | 4.2684 | | 3.521 | 4.41 | 7500 | 4.2603 | | 3.512 | 4.71 | 8000 | 4.2465 | | 3.4976 | 5.0 | 8500 | 4.2324 | | 3.3273 | 5.29 | 9000 | 4.2482 | | 3.317 | 5.59 | 9500 | 4.2467 | | 3.3218 | 5.88 | 10000 | 4.2459 | ### Framework versions - Transformers 4.26.1 - Pytorch 1.11.0+cu113 - Datasets 2.13.0 - Tokenizers 0.13.3

161381373-qq/ee

161381373-qq

2023-07-10T12:04:47Z

0

null

[ "arxiv:1910.09700", "region:us" ]

null

2023-07-10T12:04:14Z

--- # For reference on model card metadata, see the spec: https://github.com/huggingface/hub-docs/blob/main/modelcard.md?plain=1 # Doc / guide: https://huggingface.co/docs/hub/model-cards {} --- # Model Card for Model ID  This modelcard aims to be a base template for new models. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/modelcard_template.md?plain=1). ## Model Details ### Model Description  - **Developed by:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional]  - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses  ### Direct Use  [More Information Needed] ### Downstream Use [optional]  [More Information Needed] ### Out-of-Scope Use  [More Information Needed] ## Bias, Risks, and Limitations  [More Information Needed] ### Recommendations  Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data  [More Information Needed] ### Training Procedure  #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed]  #### Speeds, Sizes, Times [optional]  [More Information Needed] ## Evaluation  ### Testing Data, Factors & Metrics #### Testing Data  [More Information Needed] #### Factors  [More Information Needed] #### Metrics  [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional]  [More Information Needed] ## Environmental Impact  Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional]  **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional]  [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

Salama1429/whisper-tiny-english

Salama1429

2023-07-10T11:57:33Z

91

0

transformers

[ "transformers", "pytorch", "tensorboard", "whisper", "automatic-speech-recognition", "generated_from_trainer", "dataset:PolyAI/minds14", "license:apache-2.0", "model-index", "endpoints_compatible", "region:us" ]

automatic-speech-recognition

2023-07-10T10:05:31Z

--- license: apache-2.0 tags: - generated_from_trainer datasets: - PolyAI/minds14 metrics: - wer model-index: - name: whisper-tiny-english results: - task: name: Automatic Speech Recognition type: automatic-speech-recognition dataset: name: PolyAI/minds14 type: PolyAI/minds14 config: en-US split: train args: en-US metrics: - name: Wer type: wer value: 0.27150380339379755 pipeline_tag: automatic-speech-recognition ---  # whisper-tiny-english This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the PolyAI/minds14 dataset. It achieves the following results on the evaluation set: - Loss: 0.6834 - Wer Ortho: 0.280025 - Wer: 0.271504 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 1e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: constant_with_warmup - lr_scheduler_warmup_steps: 50 - training_steps: 500 ### Training results | Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer | |:-------------:|:-----:|:----:|:---------------:|:---------:|:-------:| | 0.0007 | 17.86 | 500 | 0.6834 | 0.280025 | 0.271504 | ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3

Benita12/videomae-base-finetuned-ucf101-subset

Benita12

2023-07-10T11:39:42Z

60

0

transformers

[ "transformers", "pytorch", "tensorboard", "videomae", "video-classification", "generated_from_trainer", "license:cc-by-nc-4.0", "endpoints_compatible", "region:us" ]

video-classification

2023-06-13T14:44:31Z

--- license: cc-by-nc-4.0 tags: - generated_from_trainer metrics: - accuracy model-index: - name: videomae-base-finetuned-ucf101-subset results: [] ---  # videomae-base-finetuned-ucf101-subset This model is a fine-tuned version of [MCG-NJU/videomae-base](https://huggingface.co/MCG-NJU/videomae-base) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.3070 - Accuracy: 0.8968 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 2 - eval_batch_size: 2 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - training_steps: 450 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------:| | 1.1183 | 0.33 | 150 | 1.2051 | 0.4714 | | 1.1544 | 1.33 | 300 | 0.4946 | 0.8 | | 0.1042 | 2.33 | 450 | 0.2526 | 0.9429 | ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3

tyavika/LR1E4-BS16-Distil-CNN512LSTM256NoBi

tyavika

2023-07-10T11:29:13Z

76

0

transformers

[ "transformers", "pytorch", "distilbert", "question-answering", "generated_from_trainer", "endpoints_compatible", "region:us" ]

question-answering

2023-07-09T20:24:08Z

--- tags: - generated_from_trainer model-index: - name: LR1E4-BS16-Distil-CNN512LSTM256NoBi results: [] ---  # LR1E4-BS16-Distil-CNN512LSTM256NoBi This model is a fine-tuned version of [tyavika/LR1E4-BS16-Distil-CNN512LSTM256NoBi](https://huggingface.co/tyavika/LR1E4-BS16-Distil-CNN512LSTM256NoBi) on the None dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 10 ### Framework versions - Transformers 4.28.0 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3

Junr-syl/tweet_sentiments_analysis

Junr-syl

2023-07-10T11:21:39Z

162

0

transformers

[ "transformers", "pytorch", "tensorboard", "bert", "text-classification", "generated_from_trainer", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

text-classification

2023-07-07T09:19:12Z

--- license: apache-2.0 tags: - generated_from_trainer model-index: - name: tweet_sentiments_analysis results: [] ---  # tweet_sentiments_analysis This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on an unknown dataset. It achieves the following results on the evaluation set: - eval_loss: 0.3953 - eval_accuracy: 0.8660 - eval_runtime: 254.1512 - eval_samples_per_second: 31.473 - eval_steps_per_second: 3.935 - step: 0 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 1000 ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3

AquaV/Hoers13B-ggml-q4_0

AquaV

2023-07-10T11:17:51Z

0

null

[ "region:us" ]

null

2023-07-10T10:06:01Z

I believe this was trained on the dataset available at https://huggingface.co/datasets/Amo/FimFic_Omega_V3. The dataset comprises user-generated stories inspired by the "My Little Pony: Friendship is Magic" series. I'm not the original creator of the model however based on the training data the format for the prompts might be: ``` <|startoftext|> [tags: author: (author name), character: (character name), character: (character name), genre: (genre), series: (series name) warning: (content warnings)] *** CHAPTER: (chapter name) {Cursor here} ``` I am uncertain if "<|startoftext|>" should be included. Here are two examples from the training data: ``` <|startoftext|> [tags: author: device heretic, character: Other, character: Princess Celestia, character: Twilight Sparkle, genre: Sad, genre: Slice of Life, genre: Tragedy, series: My Little Pony: Friendship is Magic ] *** CHAPTER: The Underlying Truth {Cursor here} ``` ``` <|startoftext|> [tags: author: Bloodline Spike, character: Cutie Mark Crusaders, character: Main 6, character: Princess Celestia, character: Princess Luna, character: Spike, genre: Adventure, genre: Dark, genre: Romance, genre: Sad, genre: Tragedy, series: My Little Pony: Friendship is Magic, warning: Gore ] *** CHAPTER: Chapter 1 Entering the Medallion {Cursor here} ``` As I am just an archiver of this model, I may not be able to provide further support or solve issues you encounter while using it.

JFoz/test_nvs

JFoz

2023-07-10T11:06:54Z

0

null

[ "license:cc-by-nc-4.0", "region:us" ]

null

2023-07-06T15:23:06Z

--- license: cc-by-nc-4.0 --- ## GenVS (partial) reimplementation Model weights for a partial, somewhat unfaithful reimplementation of GeNVS https://nvlabs.github.io/genvs/media/genvs.pdf Code repo at https://github.com/jfozard/nvs_test ### Dataset source Model trained on ShapeNet car renderings from https://github.com/vsitzmann/scene-representation-networks These are not for commercial use (ShapeNet license conditions). ### Example results Conditioning image ![Conditioning image](https://user-images.githubusercontent.com/4390954/252312435-bdc0d595-aae6-43f3-8acb-ac79d880161a.png) Reconstructed views ![Video](https://user-images.githubusercontent.com/4390954/252312886-e8cab1ae-a7ae-4bd0-b11d-8a103ed5fdfb.mp4)