bnc_sh1_67
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 5.9234
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: 67
- 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 |
|---|---|---|---|
| 7.1819 | 1.0 | 392 | 6.5003 |
| 6.3074 | 2.0 | 784 | 6.2637 |
| 6.1389 | 3.0 | 1176 | 6.1570 |
| 6.0364 | 4.0 | 1568 | 6.0859 |
| 5.9555 | 5.0 | 1960 | 6.0310 |
| 5.886 | 6.0 | 2352 | 5.9908 |
| 5.8225 | 7.0 | 2744 | 5.9578 |
| 5.7626 | 8.0 | 3136 | 5.9318 |
| 5.7039 | 9.0 | 3528 | 5.9122 |
| 5.6469 | 10.0 | 3920 | 5.8963 |
| 5.5913 | 11.0 | 4312 | 5.8878 |
| 5.5373 | 12.0 | 4704 | 5.8858 |
| 5.4848 | 13.0 | 5096 | 5.8851 |
| 5.4351 | 14.0 | 5488 | 5.8900 |
| 5.3887 | 15.0 | 5880 | 5.8942 |
| 5.3465 | 16.0 | 6272 | 5.9013 |
| 5.3085 | 17.0 | 6664 | 5.9086 |
| 5.277 | 18.0 | 7056 | 5.9148 |
| 5.2522 | 19.0 | 7448 | 5.9202 |
| 5.234 | 20.0 | 7840 | 5.9234 |
Framework versions
- Transformers 4.56.1
- Pytorch 2.8.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.0
- Downloads last month
- 1