<!-- 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. -->
fr-wo
This model is a fine-tuned version of t5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.0120
- Bleu: 0.2051
- Gen Len: 18.9411
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: 10
- eval_batch_size: 10
- 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 |
|---|---|---|---|---|---|
| 4.1216 | 1.0 | 718 | 3.3478 | 0.0028 | 18.9524 |
| 3.5436 | 2.0 | 1436 | 3.0206 | 0.0113 | 18.9524 |
| 3.1518 | 3.0 | 2154 | 2.8468 | 0.0093 | 18.9461 |
| 3.0451 | 4.0 | 2872 | 2.7329 | 0.0138 | 18.9461 |
| 2.9036 | 5.0 | 3590 | 2.6508 | 0.0617 | 18.9424 |
| 2.8468 | 6.0 | 4308 | 2.5821 | 0.0941 | 18.9386 |
| 2.7631 | 7.0 | 5026 | 2.5249 | 0.1162 | 18.9449 |
| 2.7208 | 8.0 | 5744 | 2.4744 | 0.0976 | 18.9486 |
| 2.6963 | 9.0 | 6462 | 2.4344 | 0.0898 | 18.9549 |
| 2.6335 | 10.0 | 7180 | 2.3977 | 0.1047 | 18.9461 |
| 2.6106 | 11.0 | 7898 | 2.3650 | 0.1067 | 18.9536 |
| 2.5645 | 12.0 | 8616 | 2.3350 | 0.1022 | 18.9511 |
| 2.5365 | 13.0 | 9334 | 2.3093 | 0.1101 | 18.9499 |
| 2.4952 | 14.0 | 10052 | 2.2855 | 0.1237 | 18.9398 |
| 2.4797 | 15.0 | 10770 | 2.2623 | 0.1241 | 18.9499 |
| 2.4702 | 16.0 | 11488 | 2.2425 | 0.1242 | 18.9549 |
| 2.4335 | 17.0 | 12206 | 2.2254 | 0.128 | 18.9486 |
| 2.4211 | 18.0 | 12924 | 2.2068 | 0.1281 | 18.9461 |
| 2.399 | 19.0 | 13642 | 2.1919 | 0.141 | 18.9411 |
| 2.3796 | 20.0 | 14360 | 2.1785 | 0.1443 | 18.9411 |
| 2.3638 | 21.0 | 15078 | 2.1663 | 0.1447 | 18.9386 |
| 2.3528 | 22.0 | 15796 | 2.1528 | 0.1551 | 18.9361 |
| 2.3342 | 23.0 | 16514 | 2.1414 | 0.1496 | 18.9323 |
| 2.3236 | 24.0 | 17232 | 2.1303 | 0.1557 | 18.9424 |
| 2.3143 | 25.0 | 17950 | 2.1191 | 0.1571 | 18.9424 |
| 2.301 | 26.0 | 18668 | 2.1094 | 0.1527 | 18.9373 |
| 2.2952 | 27.0 | 19386 | 2.1008 | 0.1639 | 18.9424 |
| 2.2795 | 28.0 | 20104 | 2.0934 | 0.1667 | 18.9273 |
| 2.2687 | 29.0 | 20822 | 2.0848 | 0.169 | 18.9373 |
| 2.261 | 30.0 | 21540 | 2.0768 | 0.1605 | 18.9348 |
| 2.254 | 31.0 | 22258 | 2.0705 | 0.1874 | 18.9424 |
| 2.2497 | 32.0 | 22976 | 2.0640 | 0.1653 | 18.9436 |
| 2.2389 | 33.0 | 23694 | 2.0586 | 0.1875 | 18.9361 |
| 2.2307 | 34.0 | 24412 | 2.0527 | 0.1708 | 18.9436 |
| 2.2303 | 35.0 | 25130 | 2.0482 | 0.1817 | 18.9436 |
| 2.2206 | 36.0 | 25848 | 2.0428 | 0.1742 | 18.9524 |
| 2.2113 | 37.0 | 26566 | 2.0392 | 0.1658 | 18.9436 |
| 2.2095 | 38.0 | 27284 | 2.0356 | 0.1886 | 18.9436 |
| 2.1974 | 39.0 | 28002 | 2.0308 | 0.1866 | 18.9436 |
| 2.198 | 40.0 | 28720 | 2.0282 | 0.1934 | 18.9386 |
| 2.2052 | 41.0 | 29438 | 2.0247 | 0.1952 | 18.9323 |
| 2.1927 | 42.0 | 30156 | 2.0230 | 0.1932 | 18.9361 |
| 2.1907 | 43.0 | 30874 | 2.0194 | 0.1962 | 18.9336 |
| 2.1899 | 44.0 | 31592 | 2.0178 | 0.1868 | 18.9386 |
| 2.1814 | 45.0 | 32310 | 2.0163 | 0.2016 | 18.9386 |
| 2.1815 | 46.0 | 33028 | 2.0145 | 0.1994 | 18.9361 |
| 2.1756 | 47.0 | 33746 | 2.0134 | 0.2015 | 18.9386 |
| 2.186 | 48.0 | 34464 | 2.0127 | 0.2054 | 18.9411 |
| 2.1801 | 49.0 | 35182 | 2.0122 | 0.2058 | 18.9411 |
| 2.1733 | 50.0 | 35900 | 2.0120 | 0.2051 | 18.9411 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
