bnc_np_30
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 5.5666
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 |
|---|---|---|---|
| 7.1143 | 1.0 | 392 | 6.3233 |
| 6.099 | 2.0 | 784 | 6.0240 |
| 5.8848 | 3.0 | 1176 | 5.8852 |
| 5.7535 | 4.0 | 1568 | 5.7916 |
| 5.6494 | 5.0 | 1960 | 5.7213 |
| 5.5595 | 6.0 | 2352 | 5.6637 |
| 5.4789 | 7.0 | 2744 | 5.6213 |
| 5.4043 | 8.0 | 3136 | 5.5882 |
| 5.3337 | 9.0 | 3528 | 5.5652 |
| 5.2665 | 10.0 | 3920 | 5.5469 |
| 5.2031 | 11.0 | 4312 | 5.5373 |
| 5.1424 | 12.0 | 4704 | 5.5351 |
| 5.0849 | 13.0 | 5096 | 5.5330 |
| 5.0306 | 14.0 | 5488 | 5.5345 |
| 4.9806 | 15.0 | 5880 | 5.5393 |
| 4.9374 | 16.0 | 6272 | 5.5450 |
| 4.8998 | 17.0 | 6664 | 5.5544 |
| 4.8686 | 18.0 | 7056 | 5.5595 |
| 4.8431 | 19.0 | 7448 | 5.5630 |
| 4.8238 | 20.0 | 7840 | 5.5666 |
Framework versions
- Transformers 4.56.1
- Pytorch 2.8.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.0
- Downloads last month
- 24