gpt2_small_EN_superbpe_81920_parallel10_42
This model was trained from scratch on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 5.2915
- Accuracy: 0.2309
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: 64
- eval_batch_size: 64
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- total_train_batch_size: 128
- total_eval_batch_size: 128
- 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 |
|---|
| 7.9411 | 1.0 | 1131 | 6.6632 | 0.1702 |
| 6.4162 | 2.0 | 2262 | 5.9737 | 0.1980 |
| 5.9499 | 3.0 | 3393 | 5.7065 | 0.2081 |
| 5.7133 | 4.0 | 4524 | 5.5552 | 0.2159 |
| 5.5613 | 5.0 | 5655 | 5.4610 | 0.2203 |
| 5.4533 | 6.0 | 6786 | 5.3931 | 0.2247 |
| 5.371 | 7.0 | 7917 | 5.3495 | 0.2268 |
| 5.2524 | 8.0 | 9048 | 5.3176 | 0.2291 |
| 5.2109 | 9.0 | 10179 | 5.2992 | 0.2302 |
| 5.1827 | 10.0 | 11310 | 5.2915 | 0.2309 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.8.0+cu128
- Datasets 4.1.1
- Tokenizers 0.19.1
