gpt2_small_EN_superbpe_6990_parallel10_42
This model was trained from scratch on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 3.7845
- Accuracy: 0.3092
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 |
|---|
| 6.1034 | 1.0 | 1568 | 4.6473 | 0.2224 |
| 4.4153 | 2.0 | 3136 | 4.2306 | 0.2581 |
| 4.2267 | 3.0 | 4704 | 4.0623 | 0.2762 |
| 4.035 | 4.0 | 6272 | 3.9669 | 0.2870 |
| 3.9649 | 5.0 | 7840 | 3.9048 | 0.2935 |
| 3.8727 | 6.0 | 9408 | 3.8599 | 0.2995 |
| 3.837 | 7.0 | 10976 | 3.8297 | 0.3043 |
| 3.7737 | 8.0 | 12544 | 3.8061 | 0.3069 |
| 3.738 | 9.0 | 14112 | 3.7925 | 0.3082 |
| 3.717 | 10.0 | 15680 | 3.7845 | 0.3092 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.8.0+cu128
- Datasets 4.1.1
- Tokenizers 0.19.1
