a0b648d6e0c2065718b942c275329ea8
This model is a fine-tuned version of google/mt5-large on the Helsinki-NLP/opus_books [fr-nl] dataset. It achieves the following results on the evaluation set:
- Loss: 1.4275
- Data Size: 1.0
- Epoch Runtime: 401.2085
- Bleu: 10.9394
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 | 25.5985 | 0 | 30.6092 | 0.0176 |
| No log | 1 | 1000 | 18.8340 | 0.0078 | 34.4953 | 0.0230 |
| No log | 2 | 2000 | 8.0071 | 0.0156 | 38.2032 | 0.0307 |
| No log | 3 | 3000 | 6.0234 | 0.0312 | 45.3777 | 0.0448 |
| 0.3703 | 4 | 4000 | 2.8579 | 0.0625 | 57.8481 | 0.5543 |
| 3.1761 | 5 | 5000 | 2.2244 | 0.125 | 81.9571 | 7.3657 |
| 0.16 | 6 | 6000 | 1.9558 | 0.25 | 128.6183 | 6.1663 |
| 0.2037 | 7 | 7000 | 1.7958 | 0.5 | 221.6526 | 7.0443 |
| 2.017 | 8.0 | 8000 | 1.6592 | 1.0 | 402.3181 | 8.0500 |
| 1.8557 | 9.0 | 9000 | 1.5824 | 1.0 | 401.6877 | 8.8124 |
| 1.7318 | 10.0 | 10000 | 1.5295 | 1.0 | 400.8879 | 9.2664 |
| 1.6393 | 11.0 | 11000 | 1.4937 | 1.0 | 401.0046 | 9.5815 |
| 1.5502 | 12.0 | 12000 | 1.4601 | 1.0 | 401.2907 | 9.8645 |
| 1.4799 | 13.0 | 13000 | 1.4510 | 1.0 | 403.5631 | 10.0124 |
| 1.4131 | 14.0 | 14000 | 1.4298 | 1.0 | 406.0393 | 10.2133 |
| 1.3375 | 15.0 | 15000 | 1.4164 | 1.0 | 402.5571 | 10.3995 |
| 1.303 | 16.0 | 16000 | 1.4152 | 1.0 | 401.2788 | 10.4281 |
| 1.2215 | 17.0 | 17000 | 1.4149 | 1.0 | 400.1707 | 10.5308 |
| 1.2239 | 18.0 | 18000 | 1.4094 | 1.0 | 399.5269 | 10.6309 |
| 1.1587 | 19.0 | 19000 | 1.4067 | 1.0 | 399.8632 | 10.6802 |
| 1.1162 | 20.0 | 20000 | 1.4118 | 1.0 | 401.0874 | 10.7793 |
| 1.0873 | 21.0 | 21000 | 1.4137 | 1.0 | 401.0856 | 10.8705 |
| 1.0534 | 22.0 | 22000 | 1.4207 | 1.0 | 397.3273 | 10.8864 |
| 1.0039 | 23.0 | 23000 | 1.4275 | 1.0 | 401.2085 | 10.9394 |
Framework versions
- Transformers 4.57.0
- Pytorch 2.8.0+cu128
- Datasets 4.2.0
- Tokenizers 0.22.1
- Downloads last month
- 2
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for contemmcm/a0b648d6e0c2065718b942c275329ea8
Base model
google/mt5-large