|
--- |
|
library_name: transformers |
|
license: apache-2.0 |
|
base_model: google/flan-t5-base |
|
tags: |
|
- simplification |
|
- generated_from_trainer |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: flan-t5-base-lecturaFacil |
|
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. --> |
|
|
|
# flan-t5-base-lecturaFacil |
|
|
|
This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.9271 |
|
- Rouge1: 7.3252 |
|
- Rouge2: 4.9334 |
|
- Rougel: 6.8872 |
|
- Rougelsum: 7.1241 |
|
|
|
## 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: 5.6e-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: 30 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:| |
|
| No log | 1.0 | 126 | 1.0321 | 7.3748 | 4.9629 | 6.9138 | 7.2111 | |
|
| 1.1181 | 2.0 | 252 | 1.0070 | 7.4115 | 5.0322 | 6.9997 | 7.2421 | |
|
| 1.1181 | 3.0 | 378 | 0.9969 | 7.3898 | 5.1086 | 6.9923 | 7.231 | |
|
| 1.0383 | 4.0 | 504 | 0.9813 | 7.4184 | 5.0788 | 7.0037 | 7.2501 | |
|
| 1.0383 | 5.0 | 630 | 0.9688 | 7.3659 | 5.039 | 6.9308 | 7.2087 | |
|
| 0.983 | 6.0 | 756 | 0.9622 | 7.3641 | 4.937 | 6.9081 | 7.1724 | |
|
| 0.983 | 7.0 | 882 | 0.9544 | 7.295 | 4.8189 | 6.8761 | 7.1125 | |
|
| 0.951 | 8.0 | 1008 | 0.9511 | 7.3963 | 4.9845 | 6.9474 | 7.2114 | |
|
| 0.951 | 9.0 | 1134 | 0.9465 | 7.3098 | 4.9128 | 6.839 | 7.126 | |
|
| 0.9158 | 10.0 | 1260 | 0.9460 | 7.2637 | 4.8619 | 6.7836 | 7.0688 | |
|
| 0.9158 | 11.0 | 1386 | 0.9419 | 7.2981 | 4.9045 | 6.8633 | 7.0929 | |
|
| 0.8855 | 12.0 | 1512 | 0.9408 | 7.2316 | 4.8556 | 6.8036 | 7.0365 | |
|
| 0.8855 | 13.0 | 1638 | 0.9386 | 7.304 | 4.9343 | 6.8534 | 7.1372 | |
|
| 0.8728 | 14.0 | 1764 | 0.9361 | 7.306 | 4.8842 | 6.8442 | 7.1085 | |
|
| 0.8728 | 15.0 | 1890 | 0.9358 | 7.3659 | 4.9194 | 6.9266 | 7.1365 | |
|
| 0.8454 | 16.0 | 2016 | 0.9322 | 7.3037 | 4.9331 | 6.8693 | 7.1027 | |
|
| 0.8454 | 17.0 | 2142 | 0.9309 | 7.3274 | 5.0087 | 6.933 | 7.149 | |
|
| 0.8327 | 18.0 | 2268 | 0.9297 | 7.3654 | 4.9828 | 6.9368 | 7.1698 | |
|
| 0.8327 | 19.0 | 2394 | 0.9287 | 7.3123 | 4.9036 | 6.8939 | 7.1085 | |
|
| 0.8247 | 20.0 | 2520 | 0.9285 | 7.3767 | 5.0096 | 6.9674 | 7.1994 | |
|
| 0.8247 | 21.0 | 2646 | 0.9280 | 7.3385 | 4.9576 | 6.9177 | 7.1509 | |
|
| 0.8123 | 22.0 | 2772 | 0.9260 | 7.2944 | 4.967 | 6.8986 | 7.1205 | |
|
| 0.8123 | 23.0 | 2898 | 0.9283 | 7.3318 | 4.9947 | 6.9124 | 7.1526 | |
|
| 0.8022 | 24.0 | 3024 | 0.9265 | 7.3281 | 5.0144 | 6.9243 | 7.1457 | |
|
| 0.8022 | 25.0 | 3150 | 0.9267 | 7.3298 | 4.9377 | 6.8935 | 7.122 | |
|
| 0.7902 | 26.0 | 3276 | 0.9285 | 7.3649 | 5.0498 | 6.9359 | 7.1817 | |
|
| 0.7902 | 27.0 | 3402 | 0.9264 | 7.3309 | 4.9617 | 6.9008 | 7.1364 | |
|
| 0.7932 | 28.0 | 3528 | 0.9270 | 7.3137 | 4.9215 | 6.873 | 7.1133 | |
|
| 0.7932 | 29.0 | 3654 | 0.9272 | 7.3203 | 4.9291 | 6.8813 | 7.1206 | |
|
| 0.7849 | 30.0 | 3780 | 0.9271 | 7.3252 | 4.9334 | 6.8872 | 7.1241 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.45.1 |
|
- Pytorch 2.4.1 |
|
- Datasets 3.0.1 |
|
- Tokenizers 0.20.0 |
|
|
