candor_sh1_42
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 4.6171
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: 42
- 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 |
|---|---|---|---|
| 5.7987 | 1.0 | 422 | 4.8848 |
| 4.7594 | 2.0 | 844 | 4.7385 |
| 4.6549 | 3.0 | 1266 | 4.6667 |
| 4.5905 | 4.0 | 1688 | 4.6235 |
| 4.543 | 5.0 | 2110 | 4.5943 |
| 4.5031 | 6.0 | 2532 | 4.5713 |
| 4.4668 | 7.0 | 2954 | 4.5578 |
| 4.4319 | 8.0 | 3376 | 4.5457 |
| 4.3979 | 9.0 | 3798 | 4.5386 |
| 4.3635 | 10.0 | 4220 | 4.5350 |
| 4.3284 | 11.0 | 4642 | 4.5385 |
| 4.2928 | 12.0 | 5064 | 4.5433 |
| 4.257 | 13.0 | 5486 | 4.5498 |
| 4.2213 | 14.0 | 5908 | 4.5586 |
| 4.1867 | 15.0 | 6330 | 4.5685 |
| 4.1538 | 16.0 | 6752 | 4.5806 |
| 4.1236 | 17.0 | 7174 | 4.5939 |
| 4.0969 | 18.0 | 7596 | 4.6058 |
| 4.0747 | 19.0 | 8018 | 4.6135 |
| 4.0583 | 20.0 | 8440 | 4.6171 |
Framework versions
- Transformers 4.56.1
- Pytorch 2.8.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.0
- Downloads last month
- 61