ads_sh1_fr_13
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 5.5479
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: 13
- 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 |
|---|---|---|---|
| 8.0282 | 1.0 | 103 | 7.0723 |
| 6.2183 | 2.0 | 206 | 5.9457 |
| 5.7981 | 3.0 | 309 | 5.8296 |
| 5.7019 | 4.0 | 412 | 5.7403 |
| 5.617 | 5.0 | 515 | 5.6725 |
| 5.5455 | 6.0 | 618 | 5.6215 |
| 5.4893 | 7.0 | 721 | 5.5874 |
| 5.4408 | 8.0 | 824 | 5.5637 |
| 5.3968 | 9.0 | 927 | 5.5433 |
| 5.3536 | 10.0 | 1030 | 5.5284 |
| 5.3114 | 11.0 | 1133 | 5.5188 |
| 5.268 | 12.0 | 1236 | 5.5163 |
| 5.2246 | 13.0 | 1339 | 5.5125 |
| 5.1809 | 14.0 | 1442 | 5.5162 |
| 5.1367 | 15.0 | 1545 | 5.5169 |
| 5.0935 | 16.0 | 1648 | 5.5235 |
| 5.0513 | 17.0 | 1751 | 5.5314 |
| 5.0147 | 18.0 | 1854 | 5.5380 |
| 4.9838 | 19.0 | 1957 | 5.5446 |
| 4.9625 | 20.0 | 2060 | 5.5479 |
Framework versions
- Transformers 4.56.1
- Pytorch 2.8.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.0
- Downloads last month
- 6