gpt2_small_PL_superbpe_65536_parallel10_42
This model was trained from scratch on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 5.2927
- Accuracy: 0.2623
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 |
|---|
| 7.9999 | 1.0 | 1081 | 7.0436 | 0.1890 |
| 6.7484 | 2.0 | 2162 | 6.3040 | 0.2119 |
| 6.2189 | 3.0 | 3243 | 5.9415 | 0.2258 |
| 5.912 | 4.0 | 4324 | 5.7091 | 0.2372 |
| 5.6968 | 5.0 | 5405 | 5.5570 | 0.2467 |
| 5.545 | 6.0 | 6486 | 5.4548 | 0.2523 |
| 5.4317 | 7.0 | 7567 | 5.3816 | 0.2565 |
| 5.3453 | 8.0 | 8648 | 5.3324 | 0.2599 |
| 5.2815 | 9.0 | 9729 | 5.3041 | 0.2618 |
| 5.2363 | 10.0 | 10810 | 5.2927 | 0.2623 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.8.0+cu128
- Datasets 4.1.1
- Tokenizers 0.19.1
