<!-- 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-finetuned-en-to-it-lrs
This model is a fine-tuned version of t5-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.4687
- Bleu: 22.9793
- Gen Len: 49.8367
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 40
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| 1.4378 | 1.0 | 1125 | 1.9365 | 12.0299 | 55.7007 |
| 1.229 | 2.0 | 2250 | 1.8493 | 15.9175 | 51.6293 |
| 1.0996 | 3.0 | 3375 | 1.7781 | 17.5103 | 51.666 |
| 0.9979 | 4.0 | 4500 | 1.7309 | 18.8603 | 50.8587 |
| 0.9421 | 5.0 | 5625 | 1.6839 | 19.8188 | 50.4767 |
| 0.9181 | 6.0 | 6750 | 1.6602 | 20.5693 | 50.272 |
| 0.8882 | 7.0 | 7875 | 1.6386 | 20.9771 | 50.3833 |
| 0.8498 | 8.0 | 9000 | 1.6252 | 21.2237 | 50.5093 |
| 0.8356 | 9.0 | 10125 | 1.6079 | 21.3987 | 50.31 |
| 0.8164 | 10.0 | 11250 | 1.5698 | 21.5409 | 50.388 |
| 0.8001 | 11.0 | 12375 | 1.5779 | 21.7354 | 49.822 |
| 0.7805 | 12.0 | 13500 | 1.5637 | 21.9649 | 49.8213 |
| 0.764 | 13.0 | 14625 | 1.5540 | 22.1342 | 50.2 |
| 0.7594 | 14.0 | 15750 | 1.5456 | 22.2318 | 50.0147 |
| 0.7355 | 15.0 | 16875 | 1.5309 | 22.2936 | 49.7693 |
| 0.7343 | 16.0 | 18000 | 1.5247 | 22.5065 | 49.7607 |
| 0.7231 | 17.0 | 19125 | 1.5231 | 22.3902 | 49.7733 |
| 0.7183 | 18.0 | 20250 | 1.5211 | 22.3672 | 49.8313 |
| 0.7068 | 19.0 | 21375 | 1.5075 | 22.5519 | 49.7433 |
| 0.7087 | 20.0 | 22500 | 1.5006 | 22.4827 | 49.5 |
| 0.6965 | 21.0 | 23625 | 1.4978 | 22.5907 | 49.6833 |
| 0.6896 | 22.0 | 24750 | 1.4955 | 22.6286 | 49.836 |
| 0.689 | 23.0 | 25875 | 1.4924 | 22.7052 | 49.7267 |
| 0.6793 | 24.0 | 27000 | 1.4890 | 22.7444 | 49.8393 |
| 0.6708 | 25.0 | 28125 | 1.4889 | 22.6821 | 49.8673 |
| 0.6671 | 26.0 | 29250 | 1.4835 | 22.7866 | 49.676 |
| 0.6652 | 27.0 | 30375 | 1.4853 | 22.7691 | 49.7107 |
| 0.6578 | 28.0 | 31500 | 1.4787 | 22.8173 | 49.738 |
| 0.6556 | 29.0 | 32625 | 1.4777 | 22.7408 | 49.6687 |
| 0.6592 | 30.0 | 33750 | 1.4772 | 22.8371 | 49.7307 |
| 0.6546 | 31.0 | 34875 | 1.4819 | 22.8398 | 49.6053 |
| 0.6465 | 32.0 | 36000 | 1.4741 | 22.8379 | 49.658 |
| 0.6381 | 33.0 | 37125 | 1.4691 | 22.9108 | 49.8113 |
| 0.6429 | 34.0 | 38250 | 1.4660 | 22.9405 | 49.7933 |
| 0.6381 | 35.0 | 39375 | 1.4701 | 22.8777 | 49.7467 |
| 0.6454 | 36.0 | 40500 | 1.4692 | 22.9225 | 49.7227 |
| 0.635 | 37.0 | 41625 | 1.4683 | 22.9914 | 49.6767 |
| 0.6389 | 38.0 | 42750 | 1.4691 | 22.9904 | 49.7133 |
| 0.6368 | 39.0 | 43875 | 1.4679 | 22.9962 | 49.8273 |
| 0.6345 | 40.0 | 45000 | 1.4687 | 22.9793 | 49.8367 |
Framework versions
- Transformers 4.22.1
- Pytorch 1.12.1
- Datasets 2.5.1
- Tokenizers 0.11.0
