t5-small-finetuned-en-to-it
This model is a fine-tuned version of t5-small on the ccmatrix dataset. It achieves the following results on the evaluation set:
- Loss: 2.2698
- Bleu: 7.3298
- Gen Len: 62.3753
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: 96
- eval_batch_size: 96
- 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 |
|---|---|---|---|---|---|
| No log | 1.0 | 125 | 3.0010 | 2.7294 | 56.4513 |
| No log | 2.0 | 250 | 2.8999 | 2.3228 | 81.4993 |
| No log | 3.0 | 375 | 2.8281 | 2.3065 | 92.3353 |
| 3.3202 | 4.0 | 500 | 2.7722 | 2.5982 | 91.8093 |
| 3.3202 | 5.0 | 625 | 2.7254 | 2.9279 | 89.0907 |
| 3.3202 | 6.0 | 750 | 2.6839 | 3.0747 | 89.2827 |
| 3.3202 | 7.0 | 875 | 2.6470 | 3.207 | 87.948 |
| 3.0355 | 8.0 | 1000 | 2.6132 | 3.355 | 85.2487 |
| 3.0355 | 9.0 | 1125 | 2.5835 | 3.8401 | 80.578 |
| 3.0355 | 10.0 | 1250 | 2.5552 | 4.2905 | 75.818 |
| 3.0355 | 11.0 | 1375 | 2.5323 | 4.3866 | 75.2433 |
| 2.8903 | 12.0 | 1500 | 2.5079 | 4.5687 | 74.906 |
| 2.8903 | 13.0 | 1625 | 2.4881 | 4.7844 | 71.5773 |
| 2.8903 | 14.0 | 1750 | 2.4668 | 4.876 | 71.68 |
| 2.8903 | 15.0 | 1875 | 2.4485 | 5.1292 | 70.118 |
| 2.7891 | 16.0 | 2000 | 2.4322 | 5.3297 | 68.894 |
| 2.7891 | 17.0 | 2125 | 2.4161 | 5.555 | 68.2293 |
| 2.7891 | 18.0 | 2250 | 2.4010 | 5.7113 | 67.2907 |
| 2.7891 | 19.0 | 2375 | 2.3892 | 5.9105 | 66.6287 |
| 2.713 | 20.0 | 2500 | 2.3756 | 6.0057 | 66.112 |
| 2.713 | 21.0 | 2625 | 2.3643 | 6.3118 | 64.6193 |
| 2.713 | 22.0 | 2750 | 2.3533 | 6.476 | 64.31 |
| 2.713 | 23.0 | 2875 | 2.3432 | 6.7102 | 63.5467 |
| 2.6584 | 24.0 | 3000 | 2.3342 | 6.7604 | 63.6567 |
| 2.6584 | 25.0 | 3125 | 2.3253 | 6.8418 | 63.6573 |
| 2.6584 | 26.0 | 3250 | 2.3180 | 6.9165 | 63.5893 |
| 2.6584 | 27.0 | 3375 | 2.3120 | 7.0217 | 63.1033 |
| 2.616 | 28.0 | 3500 | 2.3056 | 6.9148 | 63.598 |
| 2.616 | 29.0 | 3625 | 2.2987 | 6.9961 | 63.6267 |
| 2.616 | 30.0 | 3750 | 2.2935 | 7.2238 | 62.8373 |
| 2.616 | 31.0 | 3875 | 2.2892 | 7.1906 | 62.7793 |
| 2.587 | 32.0 | 4000 | 2.2849 | 7.2052 | 63.126 |
| 2.587 | 33.0 | 4125 | 2.2815 | 7.3272 | 62.526 |
| 2.587 | 34.0 | 4250 | 2.2782 | 7.3603 | 62.4313 |
| 2.587 | 35.0 | 4375 | 2.2756 | 7.3072 | 62.6307 |
| 2.5673 | 36.0 | 4500 | 2.2737 | 7.3586 | 62.1633 |
| 2.5673 | 37.0 | 4625 | 2.2718 | 7.3485 | 62.358 |
| 2.5673 | 38.0 | 4750 | 2.2707 | 7.3406 | 62.298 |
| 2.5673 | 39.0 | 4875 | 2.2700 | 7.3233 | 62.42 |
| 2.5591 | 40.0 | 5000 | 2.2698 | 7.3298 | 62.3753 |
Framework versions
- Transformers 4.22.1
- Pytorch 1.12.1
- Datasets 2.5.1
- Tokenizers 0.11.0
- Downloads last month
- 1