cds_w_67
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.1760
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 |
|---|---|---|---|
| 4.5921 | 1.0 | 496 | 3.5129 |
| 3.3197 | 2.0 | 992 | 3.2969 |
| 3.1648 | 3.0 | 1488 | 3.2212 |
| 3.0772 | 4.0 | 1984 | 3.1722 |
| 3.0122 | 5.0 | 2480 | 3.1423 |
| 2.9591 | 6.0 | 2976 | 3.1217 |
| 2.9117 | 7.0 | 3472 | 3.1077 |
| 2.8674 | 8.0 | 3968 | 3.0977 |
| 2.8258 | 9.0 | 4464 | 3.0949 |
| 2.785 | 10.0 | 4960 | 3.0965 |
| 2.7468 | 11.0 | 5456 | 3.0959 |
| 2.7092 | 12.0 | 5952 | 3.1043 |
| 2.6716 | 13.0 | 6448 | 3.1143 |
| 2.6365 | 14.0 | 6944 | 3.1229 |
| 2.6025 | 15.0 | 7440 | 3.1356 |
| 2.5703 | 16.0 | 7936 | 3.1446 |
| 2.5419 | 17.0 | 8432 | 3.1555 |
| 2.518 | 18.0 | 8928 | 3.1644 |
| 2.4981 | 19.0 | 9424 | 3.1716 |
| 2.4828 | 20.0 | 9920 | 3.1760 |
Framework versions
- Transformers 4.56.1
- Pytorch 2.8.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.0