bnc_w_51
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 5.1714
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: 51
- 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 |
|---|---|---|---|
| 6.8906 | 1.0 | 392 | 5.9374 |
| 5.6886 | 2.0 | 784 | 5.5852 |
| 5.4588 | 3.0 | 1176 | 5.4537 |
| 5.3304 | 4.0 | 1568 | 5.3653 |
| 5.2311 | 5.0 | 1960 | 5.2995 |
| 5.1454 | 6.0 | 2352 | 5.2509 |
| 5.068 | 7.0 | 2744 | 5.2114 |
| 4.9966 | 8.0 | 3136 | 5.1822 |
| 4.9296 | 9.0 | 3528 | 5.1623 |
| 4.8666 | 10.0 | 3920 | 5.1494 |
| 4.807 | 11.0 | 4312 | 5.1403 |
| 4.7502 | 12.0 | 4704 | 5.1378 |
| 4.6959 | 13.0 | 5096 | 5.1389 |
| 4.6448 | 14.0 | 5488 | 5.1437 |
| 4.5993 | 15.0 | 5880 | 5.1485 |
| 4.5595 | 16.0 | 6272 | 5.1539 |
| 4.5247 | 17.0 | 6664 | 5.1588 |
| 4.4951 | 18.0 | 7056 | 5.1642 |
| 4.4706 | 19.0 | 7448 | 5.1678 |
| 4.452 | 20.0 | 7840 | 5.1714 |
Framework versions
- Transformers 4.56.1
- Pytorch 2.8.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.0
- Downloads last month
- -