5fd28e5af987f122e8d02a6cae568bf4
This model is a fine-tuned version of google-t5/t5-large on the Helsinki-NLP/opus_books [es-nl] dataset. It achieves the following results on the evaluation set:
- Loss: 1.2845
- Data Size: 1.0
- Epoch Runtime: 350.4492
- Bleu: 6.4444
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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- total_train_batch_size: 32
- total_eval_batch_size: 32
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: constant
- num_epochs: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Data Size | Epoch Runtime | Bleu |
|---|---|---|---|---|---|---|
| No log | 0 | 0 | 4.3589 | 0 | 24.6051 | 0.3638 |
| No log | 1 | 806 | 3.0269 | 0.0078 | 28.6201 | 1.1203 |
| No log | 2 | 1612 | 2.7761 | 0.0156 | 32.4259 | 1.4937 |
| No log | 3 | 2418 | 2.5985 | 0.0312 | 40.2489 | 1.6884 |
| 0.0952 | 4 | 3224 | 2.4317 | 0.0625 | 51.8815 | 2.0100 |
| 2.5591 | 5 | 4030 | 2.2594 | 0.125 | 70.9709 | 2.3508 |
| 2.3147 | 6 | 4836 | 2.0839 | 0.25 | 108.5846 | 2.9410 |
| 2.1203 | 7 | 5642 | 1.8950 | 0.5 | 195.2986 | 3.4504 |
| 1.8991 | 8.0 | 6448 | 1.6923 | 1.0 | 343.0005 | 4.3281 |
| 1.7257 | 9.0 | 7254 | 1.5769 | 1.0 | 355.3559 | 4.8188 |
| 1.6208 | 10.0 | 8060 | 1.5040 | 1.0 | 353.1862 | 5.1676 |
| 1.5389 | 11.0 | 8866 | 1.4504 | 1.0 | 347.7856 | 5.4000 |
| 1.4504 | 12.0 | 9672 | 1.4132 | 1.0 | 357.9601 | 5.7106 |
| 1.3624 | 13.0 | 10478 | 1.3787 | 1.0 | 361.5769 | 5.8256 |
| 1.3298 | 14.0 | 11284 | 1.3509 | 1.0 | 369.2166 | 5.9673 |
| 1.2616 | 15.0 | 12090 | 1.3299 | 1.0 | 365.3138 | 5.9776 |
| 1.2301 | 16.0 | 12896 | 1.3155 | 1.0 | 366.9531 | 6.1222 |
| 1.1759 | 17.0 | 13702 | 1.3037 | 1.0 | 364.8459 | 6.2506 |
| 1.1124 | 18.0 | 14508 | 1.2969 | 1.0 | 361.6905 | 6.2084 |
| 1.121 | 19.0 | 15314 | 1.2917 | 1.0 | 357.7486 | 6.2408 |
| 1.0624 | 20.0 | 16120 | 1.2828 | 1.0 | 351.4266 | 6.3466 |
| 1.0547 | 21.0 | 16926 | 1.2765 | 1.0 | 352.1902 | 6.3753 |
| 1.016 | 22.0 | 17732 | 1.2754 | 1.0 | 353.8188 | 6.3469 |
| 0.9801 | 23.0 | 18538 | 1.2764 | 1.0 | 357.0696 | 6.4222 |
| 0.946 | 24.0 | 19344 | 1.2775 | 1.0 | 356.1435 | 6.3349 |
| 0.9131 | 25.0 | 20150 | 1.2814 | 1.0 | 358.5715 | 6.4298 |
| 0.8791 | 26.0 | 20956 | 1.2845 | 1.0 | 350.4492 | 6.4444 |
Framework versions
- Transformers 4.57.0
- Pytorch 2.8.0+cu128
- Datasets 4.2.0
- Tokenizers 0.22.1
- Downloads last month
- 3
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for contemmcm/5fd28e5af987f122e8d02a6cae568bf4
Base model
google-t5/t5-large