bnc_w_30
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 5.1718
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: 0.0001
- train_batch_size: 256
- eval_batch_size: 256
- seed: 30
- optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 20
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 6.9083 | 1.0 | 392 | 5.9268 |
| 5.6817 | 2.0 | 784 | 5.5811 |
| 5.4546 | 3.0 | 1176 | 5.4492 |
| 5.3275 | 4.0 | 1568 | 5.3616 |
| 5.2289 | 5.0 | 1960 | 5.2980 |
| 5.1439 | 6.0 | 2352 | 5.2485 |
| 5.0671 | 7.0 | 2744 | 5.2102 |
| 4.9957 | 8.0 | 3136 | 5.1845 |
| 4.9294 | 9.0 | 3528 | 5.1637 |
| 4.8664 | 10.0 | 3920 | 5.1505 |
| 4.8067 | 11.0 | 4312 | 5.1409 |
| 4.7503 | 12.0 | 4704 | 5.1400 |
| 4.6961 | 13.0 | 5096 | 5.1379 |
| 4.6449 | 14.0 | 5488 | 5.1417 |
| 4.5998 | 15.0 | 5880 | 5.1453 |
| 4.5597 | 16.0 | 6272 | 5.1529 |
| 4.5253 | 17.0 | 6664 | 5.1577 |
| 4.4956 | 18.0 | 7056 | 5.1645 |
| 4.4713 | 19.0 | 7448 | 5.1689 |
| 4.4526 | 20.0 | 7840 | 5.1718 |
Framework versions
- Transformers 4.56.1
- Pytorch 2.8.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.0
- Downloads last month
- 58