bnc_w_67
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 5.1715
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 |
|---|---|---|---|
| 6.9042 | 1.0 | 392 | 5.9294 |
| 5.6847 | 2.0 | 784 | 5.5814 |
| 5.4562 | 3.0 | 1176 | 5.4478 |
| 5.3286 | 4.0 | 1568 | 5.3636 |
| 5.2299 | 5.0 | 1960 | 5.2989 |
| 5.1442 | 6.0 | 2352 | 5.2499 |
| 5.067 | 7.0 | 2744 | 5.2104 |
| 4.9956 | 8.0 | 3136 | 5.1807 |
| 4.9288 | 9.0 | 3528 | 5.1614 |
| 4.8655 | 10.0 | 3920 | 5.1485 |
| 4.8056 | 11.0 | 4312 | 5.1415 |
| 4.7484 | 12.0 | 4704 | 5.1392 |
| 4.6944 | 13.0 | 5096 | 5.1382 |
| 4.6433 | 14.0 | 5488 | 5.1401 |
| 4.5983 | 15.0 | 5880 | 5.1463 |
| 4.5582 | 16.0 | 6272 | 5.1530 |
| 4.5233 | 17.0 | 6664 | 5.1580 |
| 4.4937 | 18.0 | 7056 | 5.1637 |
| 4.4692 | 19.0 | 7448 | 5.1697 |
| 4.4507 | 20.0 | 7840 | 5.1715 |
Framework versions
- Transformers 4.56.1
- Pytorch 2.8.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.0
- Downloads last month
- 35