gemma2_on_korean_summary
Browse files- README.md +203 -0
- adapter_config.json +31 -0
- adapter_model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,203 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: other
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
base_model: beomi/gemma-ko-2b
|
| 7 |
+
model-index:
|
| 8 |
+
- name: gemma2_on_korean_summary
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/ghost_in_the_lab/Korean-fine-tune-models/runs/fc7yrozn)
|
| 16 |
+
# gemma2_on_korean_summary
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [beomi/gemma-ko-2b](https://huggingface.co/beomi/gemma-ko-2b) on the None dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.9709
|
| 21 |
+
|
| 22 |
+
## Model description
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Intended uses & limitations
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training and evaluation data
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training procedure
|
| 35 |
+
|
| 36 |
+
### Training hyperparameters
|
| 37 |
+
|
| 38 |
+
The following hyperparameters were used during training:
|
| 39 |
+
- learning_rate: 5e-05
|
| 40 |
+
- train_batch_size: 1
|
| 41 |
+
- eval_batch_size: 1
|
| 42 |
+
- seed: 42
|
| 43 |
+
- gradient_accumulation_steps: 5
|
| 44 |
+
- total_train_batch_size: 5
|
| 45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
+
- lr_scheduler_type: linear
|
| 47 |
+
- lr_scheduler_warmup_steps: 50
|
| 48 |
+
- training_steps: 1400
|
| 49 |
+
- mixed_precision_training: Native AMP
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 54 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 55 |
+
| 1.6915 | 0.0658 | 10 | 1.6222 |
|
| 56 |
+
| 1.6475 | 0.1316 | 20 | 1.5357 |
|
| 57 |
+
| 1.4535 | 0.1974 | 30 | 1.4325 |
|
| 58 |
+
| 1.414 | 0.2632 | 40 | 1.3366 |
|
| 59 |
+
| 1.3122 | 0.3289 | 50 | 1.2576 |
|
| 60 |
+
| 1.2768 | 0.3947 | 60 | 1.2126 |
|
| 61 |
+
| 1.174 | 0.4605 | 70 | 1.1838 |
|
| 62 |
+
| 1.1816 | 0.5263 | 80 | 1.1575 |
|
| 63 |
+
| 1.1163 | 0.5921 | 90 | 1.1330 |
|
| 64 |
+
| 1.1197 | 0.6579 | 100 | 1.1116 |
|
| 65 |
+
| 1.1635 | 0.7237 | 110 | 1.0954 |
|
| 66 |
+
| 1.0971 | 0.7895 | 120 | 1.0730 |
|
| 67 |
+
| 1.0985 | 0.8553 | 130 | 1.0568 |
|
| 68 |
+
| 1.0725 | 0.9211 | 140 | 1.0414 |
|
| 69 |
+
| 1.0483 | 0.9868 | 150 | 1.0302 |
|
| 70 |
+
| 0.9666 | 1.0526 | 160 | 1.0203 |
|
| 71 |
+
| 0.9754 | 1.1184 | 170 | 1.0096 |
|
| 72 |
+
| 0.9688 | 1.1842 | 180 | 0.9976 |
|
| 73 |
+
| 0.9673 | 1.25 | 190 | 0.9874 |
|
| 74 |
+
| 0.9636 | 1.3158 | 200 | 0.9805 |
|
| 75 |
+
| 0.9482 | 1.3816 | 210 | 0.9744 |
|
| 76 |
+
| 0.9231 | 1.4474 | 220 | 0.9657 |
|
| 77 |
+
| 0.9208 | 1.5132 | 230 | 0.9555 |
|
| 78 |
+
| 0.9321 | 1.5789 | 240 | 0.9488 |
|
| 79 |
+
| 0.9362 | 1.6447 | 250 | 0.9431 |
|
| 80 |
+
| 0.939 | 1.7105 | 260 | 0.9393 |
|
| 81 |
+
| 0.919 | 1.7763 | 270 | 0.9342 |
|
| 82 |
+
| 0.9277 | 1.8421 | 280 | 0.9312 |
|
| 83 |
+
| 0.8955 | 1.9079 | 290 | 0.9263 |
|
| 84 |
+
| 0.8679 | 1.9737 | 300 | 0.9211 |
|
| 85 |
+
| 0.8545 | 2.0395 | 310 | 0.9251 |
|
| 86 |
+
| 0.7897 | 2.1053 | 320 | 0.9200 |
|
| 87 |
+
| 0.7835 | 2.1711 | 330 | 0.9198 |
|
| 88 |
+
| 0.8139 | 2.2368 | 340 | 0.9105 |
|
| 89 |
+
| 0.7861 | 2.3026 | 350 | 0.9089 |
|
| 90 |
+
| 0.7752 | 2.3684 | 360 | 0.9075 |
|
| 91 |
+
| 0.7919 | 2.4342 | 370 | 0.8985 |
|
| 92 |
+
| 0.7433 | 2.5 | 380 | 0.9038 |
|
| 93 |
+
| 0.7905 | 2.5658 | 390 | 0.8955 |
|
| 94 |
+
| 0.7763 | 2.6316 | 400 | 0.8930 |
|
| 95 |
+
| 0.792 | 2.6974 | 410 | 0.8869 |
|
| 96 |
+
| 0.7854 | 2.7632 | 420 | 0.8834 |
|
| 97 |
+
| 0.7978 | 2.8289 | 430 | 0.8770 |
|
| 98 |
+
| 0.7864 | 2.8947 | 440 | 0.8780 |
|
| 99 |
+
| 0.8007 | 2.9605 | 450 | 0.8730 |
|
| 100 |
+
| 0.7686 | 3.0263 | 460 | 0.8760 |
|
| 101 |
+
| 0.6573 | 3.0921 | 470 | 0.8888 |
|
| 102 |
+
| 0.7183 | 3.1579 | 480 | 0.8833 |
|
| 103 |
+
| 0.6644 | 3.2237 | 490 | 0.8864 |
|
| 104 |
+
| 0.6648 | 3.2895 | 500 | 0.8834 |
|
| 105 |
+
| 0.6763 | 3.3553 | 510 | 0.8814 |
|
| 106 |
+
| 0.6844 | 3.4211 | 520 | 0.8824 |
|
| 107 |
+
| 0.6796 | 3.4868 | 530 | 0.8769 |
|
| 108 |
+
| 0.6748 | 3.5526 | 540 | 0.8708 |
|
| 109 |
+
| 0.6899 | 3.6184 | 550 | 0.8688 |
|
| 110 |
+
| 0.6866 | 3.6842 | 560 | 0.8747 |
|
| 111 |
+
| 0.7 | 3.75 | 570 | 0.8645 |
|
| 112 |
+
| 0.6896 | 3.8158 | 580 | 0.8703 |
|
| 113 |
+
| 0.7176 | 3.8816 | 590 | 0.8628 |
|
| 114 |
+
| 0.6517 | 3.9474 | 600 | 0.8655 |
|
| 115 |
+
| 0.6941 | 4.0132 | 610 | 0.8641 |
|
| 116 |
+
| 0.5873 | 4.0789 | 620 | 0.8889 |
|
| 117 |
+
| 0.6208 | 4.1447 | 630 | 0.8772 |
|
| 118 |
+
| 0.6067 | 4.2105 | 640 | 0.8844 |
|
| 119 |
+
| 0.5892 | 4.2763 | 650 | 0.8798 |
|
| 120 |
+
| 0.6059 | 4.3421 | 660 | 0.8830 |
|
| 121 |
+
| 0.6129 | 4.4079 | 670 | 0.8810 |
|
| 122 |
+
| 0.6104 | 4.4737 | 680 | 0.8799 |
|
| 123 |
+
| 0.5846 | 4.5395 | 690 | 0.8763 |
|
| 124 |
+
| 0.6141 | 4.6053 | 700 | 0.8807 |
|
| 125 |
+
| 0.6467 | 4.6711 | 710 | 0.8766 |
|
| 126 |
+
| 0.634 | 4.7368 | 720 | 0.8774 |
|
| 127 |
+
| 0.5976 | 4.8026 | 730 | 0.8680 |
|
| 128 |
+
| 0.5638 | 4.8684 | 740 | 0.8742 |
|
| 129 |
+
| 0.6067 | 4.9342 | 750 | 0.8733 |
|
| 130 |
+
| 0.6219 | 5.0 | 760 | 0.8644 |
|
| 131 |
+
| 0.5169 | 5.0658 | 770 | 0.8969 |
|
| 132 |
+
| 0.5726 | 5.1316 | 780 | 0.9012 |
|
| 133 |
+
| 0.5483 | 5.1974 | 790 | 0.9031 |
|
| 134 |
+
| 0.5197 | 5.2632 | 800 | 0.8976 |
|
| 135 |
+
| 0.5479 | 5.3289 | 810 | 0.8963 |
|
| 136 |
+
| 0.5631 | 5.3947 | 820 | 0.8962 |
|
| 137 |
+
| 0.5687 | 5.4605 | 830 | 0.9009 |
|
| 138 |
+
| 0.4825 | 5.5263 | 840 | 0.8982 |
|
| 139 |
+
| 0.5305 | 5.5921 | 850 | 0.8937 |
|
| 140 |
+
| 0.5743 | 5.6579 | 860 | 0.8945 |
|
| 141 |
+
| 0.5293 | 5.7237 | 870 | 0.8951 |
|
| 142 |
+
| 0.5169 | 5.7895 | 880 | 0.9034 |
|
| 143 |
+
| 0.5585 | 5.8553 | 890 | 0.8894 |
|
| 144 |
+
| 0.5373 | 5.9211 | 900 | 0.8936 |
|
| 145 |
+
| 0.5524 | 5.9868 | 910 | 0.8876 |
|
| 146 |
+
| 0.4815 | 6.0526 | 920 | 0.9187 |
|
| 147 |
+
| 0.47 | 6.1184 | 930 | 0.9200 |
|
| 148 |
+
| 0.4694 | 6.1842 | 940 | 0.9204 |
|
| 149 |
+
| 0.5035 | 6.25 | 950 | 0.9246 |
|
| 150 |
+
| 0.4852 | 6.3158 | 960 | 0.9232 |
|
| 151 |
+
| 0.5266 | 6.3816 | 970 | 0.9257 |
|
| 152 |
+
| 0.4907 | 6.4474 | 980 | 0.9232 |
|
| 153 |
+
| 0.5139 | 6.5132 | 990 | 0.9135 |
|
| 154 |
+
| 0.464 | 6.5789 | 1000 | 0.9207 |
|
| 155 |
+
| 0.5172 | 6.6447 | 1010 | 0.9128 |
|
| 156 |
+
| 0.4948 | 6.7105 | 1020 | 0.9244 |
|
| 157 |
+
| 0.4606 | 6.7763 | 1030 | 0.9171 |
|
| 158 |
+
| 0.491 | 6.8421 | 1040 | 0.9187 |
|
| 159 |
+
| 0.4641 | 6.9079 | 1050 | 0.9157 |
|
| 160 |
+
| 0.4684 | 6.9737 | 1060 | 0.9115 |
|
| 161 |
+
| 0.4625 | 7.0395 | 1070 | 0.9299 |
|
| 162 |
+
| 0.4324 | 7.1053 | 1080 | 0.9454 |
|
| 163 |
+
| 0.4143 | 7.1711 | 1090 | 0.9446 |
|
| 164 |
+
| 0.4357 | 7.2368 | 1100 | 0.9447 |
|
| 165 |
+
| 0.4471 | 7.3026 | 1110 | 0.9459 |
|
| 166 |
+
| 0.4691 | 7.3684 | 1120 | 0.9441 |
|
| 167 |
+
| 0.4556 | 7.4342 | 1130 | 0.9471 |
|
| 168 |
+
| 0.4296 | 7.5 | 1140 | 0.9406 |
|
| 169 |
+
| 0.4323 | 7.5658 | 1150 | 0.9439 |
|
| 170 |
+
| 0.4243 | 7.6316 | 1160 | 0.9430 |
|
| 171 |
+
| 0.4583 | 7.6974 | 1170 | 0.9435 |
|
| 172 |
+
| 0.4346 | 7.7632 | 1180 | 0.9405 |
|
| 173 |
+
| 0.4747 | 7.8289 | 1190 | 0.9406 |
|
| 174 |
+
| 0.4443 | 7.8947 | 1200 | 0.9405 |
|
| 175 |
+
| 0.4418 | 7.9605 | 1210 | 0.9424 |
|
| 176 |
+
| 0.3878 | 8.0263 | 1220 | 0.9464 |
|
| 177 |
+
| 0.4014 | 8.0921 | 1230 | 0.9721 |
|
| 178 |
+
| 0.4183 | 8.1579 | 1240 | 0.9647 |
|
| 179 |
+
| 0.4103 | 8.2237 | 1250 | 0.9672 |
|
| 180 |
+
| 0.3951 | 8.2895 | 1260 | 0.9702 |
|
| 181 |
+
| 0.4488 | 8.3553 | 1270 | 0.9648 |
|
| 182 |
+
| 0.41 | 8.4211 | 1280 | 0.9653 |
|
| 183 |
+
| 0.3726 | 8.4868 | 1290 | 0.9668 |
|
| 184 |
+
| 0.395 | 8.5526 | 1300 | 0.9644 |
|
| 185 |
+
| 0.4141 | 8.6184 | 1310 | 0.9637 |
|
| 186 |
+
| 0.3774 | 8.6842 | 1320 | 0.9659 |
|
| 187 |
+
| 0.4003 | 8.75 | 1330 | 0.9653 |
|
| 188 |
+
| 0.3841 | 8.8158 | 1340 | 0.9671 |
|
| 189 |
+
| 0.4202 | 8.8816 | 1350 | 0.9688 |
|
| 190 |
+
| 0.4226 | 8.9474 | 1360 | 0.9684 |
|
| 191 |
+
| 0.3914 | 9.0132 | 1370 | 0.9673 |
|
| 192 |
+
| 0.4105 | 9.0789 | 1380 | 0.9687 |
|
| 193 |
+
| 0.4021 | 9.1447 | 1390 | 0.9702 |
|
| 194 |
+
| 0.4008 | 9.2105 | 1400 | 0.9709 |
|
| 195 |
+
|
| 196 |
+
|
| 197 |
+
### Framework versions
|
| 198 |
+
|
| 199 |
+
- PEFT 0.7.1
|
| 200 |
+
- Transformers 4.41.0.dev0
|
| 201 |
+
- Pytorch 2.1.2
|
| 202 |
+
- Datasets 2.15.0
|
| 203 |
+
- Tokenizers 0.19.1
|
adapter_config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "beomi/gemma-ko-2b",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layers_pattern": null,
|
| 10 |
+
"layers_to_transform": null,
|
| 11 |
+
"loftq_config": {},
|
| 12 |
+
"lora_alpha": 32,
|
| 13 |
+
"lora_dropout": 0.05,
|
| 14 |
+
"megatron_config": null,
|
| 15 |
+
"megatron_core": "megatron.core",
|
| 16 |
+
"modules_to_save": null,
|
| 17 |
+
"peft_type": "LORA",
|
| 18 |
+
"r": 16,
|
| 19 |
+
"rank_pattern": {},
|
| 20 |
+
"revision": null,
|
| 21 |
+
"target_modules": [
|
| 22 |
+
"up_proj",
|
| 23 |
+
"q_proj",
|
| 24 |
+
"o_proj",
|
| 25 |
+
"v_proj",
|
| 26 |
+
"gate_proj",
|
| 27 |
+
"k_proj",
|
| 28 |
+
"down_proj"
|
| 29 |
+
],
|
| 30 |
+
"task_type": "CAUSAL_LM"
|
| 31 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2314cf6b52c9b7c617802a576429a203fc1ad4de245b8c6d967c01eaa2b648b3
|
| 3 |
+
size 78480072
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f1c7323d160e89f2a6ac6956b9d72d538e7f5f682f87c23706f644fa0f8fd29d
|
| 3 |
+
size 5112
|