gpt2_small_TR_superbpe_65536_parallel10_42
This model was trained from scratch on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 5.6663
- Accuracy: 0.2370
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: 5e-05
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- lr_scheduler_warmup_steps: 1000
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|
| 8.2563 | 1.0 | 1053 | 7.3759 | 0.1757 |
| 7.0559 | 2.0 | 2106 | 6.6507 | 0.1962 |
| 6.5248 | 3.0 | 3159 | 6.2778 | 0.2080 |
| 6.2203 | 4.0 | 4212 | 6.0627 | 0.2166 |
| 6.0193 | 5.0 | 5265 | 5.9155 | 0.2238 |
| 5.8759 | 6.0 | 6318 | 5.8164 | 0.2285 |
| 5.7672 | 7.0 | 7371 | 5.7497 | 0.2316 |
| 5.6888 | 8.0 | 8424 | 5.7050 | 0.2348 |
| 5.6298 | 9.0 | 9477 | 5.6769 | 0.2364 |
| 5.5881 | 10.0 | 10530 | 5.6663 | 0.2370 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.8.0+cu128
- Datasets 4.1.1
- Tokenizers 0.19.1
