|
--- |
|
license: apache-2.0 |
|
base_model: google/mt5-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- bleu |
|
model-index: |
|
- name: cs_mT5_0.01_50_v0.1 |
|
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. --> |
|
|
|
# cs_mT5_0.01_50_v0.1 |
|
|
|
This model is a fine-tuned version of [google/mt5-base](https://huggingface.co/google/mt5-base) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 7.3188 |
|
- Bleu: 1.2029 |
|
- Gen Len: 19.0 |
|
|
|
## 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: 0.01 |
|
- 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: 50 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:| |
|
| 3.6406 | 1.0 | 6 | 6.1758 | 0.1903 | 19.0 | |
|
| 4.2513 | 2.0 | 12 | 6.4360 | 0.4971 | 19.0 | |
|
| 3.1515 | 3.0 | 18 | 6.2761 | 0.1689 | 19.0 | |
|
| 3.4713 | 4.0 | 24 | 6.4576 | 0.4973 | 19.0 | |
|
| 3.2069 | 5.0 | 30 | 6.6858 | 0.176 | 10.0 | |
|
| 3.5913 | 6.0 | 36 | 6.2785 | 0.7212 | 19.0 | |
|
| 3.7814 | 7.0 | 42 | 6.1120 | 0.7212 | 19.0 | |
|
| 3.2429 | 8.0 | 48 | 6.3660 | 0.3725 | 19.0 | |
|
| 3.2716 | 9.0 | 54 | 6.6523 | 0.4214 | 19.0 | |
|
| 3.3443 | 10.0 | 60 | 6.4341 | 0.3793 | 19.0 | |
|
| 2.4705 | 11.0 | 66 | 6.8433 | 0.7412 | 19.0 | |
|
| 3.0869 | 12.0 | 72 | 6.9583 | 0.0 | 19.0 | |
|
| 2.5187 | 13.0 | 78 | 6.3333 | 1.1569 | 19.0 | |
|
| 3.1211 | 14.0 | 84 | 6.4031 | 0.2813 | 19.0 | |
|
| 2.7326 | 15.0 | 90 | 6.4055 | 0.7962 | 19.0 | |
|
| 2.5142 | 16.0 | 96 | 6.5799 | 0.1843 | 19.0 | |
|
| 3.0964 | 17.0 | 102 | 6.8379 | 0.9395 | 19.0 | |
|
| 2.5998 | 18.0 | 108 | 6.4570 | 0.0 | 19.0 | |
|
| 3.2495 | 19.0 | 114 | 6.6350 | 0.2045 | 19.0 | |
|
| 3.2509 | 20.0 | 120 | 6.3533 | 0.7212 | 19.0 | |
|
| 3.2998 | 21.0 | 126 | 6.3142 | 0.6756 | 19.0 | |
|
| 2.7829 | 22.0 | 132 | 6.5953 | 0.6646 | 19.0 | |
|
| 3.0842 | 23.0 | 138 | 6.6276 | 0.7056 | 19.0 | |
|
| 1.8502 | 24.0 | 144 | 6.6472 | 0.2386 | 19.0 | |
|
| 1.945 | 25.0 | 150 | 6.6534 | 0.6966 | 19.0 | |
|
| 2.7704 | 26.0 | 156 | 7.1955 | 0.7611 | 13.0 | |
|
| 3.1289 | 27.0 | 162 | 6.6522 | 0.7286 | 17.0 | |
|
| 3.0663 | 28.0 | 168 | 6.3873 | 0.8029 | 19.0 | |
|
| 3.4269 | 29.0 | 174 | 6.4310 | 0.204 | 19.0 | |
|
| 2.7845 | 30.0 | 180 | 6.7221 | 0.3228 | 19.0 | |
|
| 2.0443 | 31.0 | 186 | 6.8353 | 0.3228 | 19.0 | |
|
| 3.1621 | 32.0 | 192 | 7.1400 | 0.1346 | 19.0 | |
|
| 2.4147 | 33.0 | 198 | 6.8844 | 1.2029 | 19.0 | |
|
| 2.5869 | 34.0 | 204 | 6.7074 | 0.7475 | 19.0 | |
|
| 2.1119 | 35.0 | 210 | 6.5778 | 0.7212 | 19.0 | |
|
| 1.7629 | 36.0 | 216 | 6.5553 | 0.7867 | 19.0 | |
|
| 2.3745 | 37.0 | 222 | 6.7126 | 0.7663 | 19.0 | |
|
| 2.368 | 38.0 | 228 | 6.8008 | 0.4815 | 19.0 | |
|
| 2.17 | 39.0 | 234 | 6.6388 | 0.7892 | 19.0 | |
|
| 2.4311 | 40.0 | 240 | 6.6423 | 0.3228 | 19.0 | |
|
| 2.8392 | 41.0 | 246 | 6.7127 | 0.3226 | 19.0 | |
|
| 2.386 | 42.0 | 252 | 6.8011 | 0.31 | 19.0 | |
|
| 2.7473 | 43.0 | 258 | 6.8704 | 0.31 | 19.0 | |
|
| 1.9796 | 44.0 | 264 | 6.9846 | 1.2029 | 19.0 | |
|
| 1.4857 | 45.0 | 270 | 7.1239 | 1.2029 | 19.0 | |
|
| 1.8413 | 46.0 | 276 | 7.2177 | 1.194 | 19.0 | |
|
| 2.171 | 47.0 | 282 | 7.2605 | 1.2029 | 19.0 | |
|
| 1.9659 | 48.0 | 288 | 7.3048 | 1.2029 | 19.0 | |
|
| 1.3681 | 49.0 | 294 | 7.3093 | 1.2029 | 19.0 | |
|
| 2.086 | 50.0 | 300 | 7.3188 | 1.2029 | 19.0 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 1.13.1+cu117 |
|
- Datasets 2.16.1 |
|
- Tokenizers 0.15.0 |
|
|
