gpt2_small_PL_bpe_8192_parallel10_42
This model was trained from scratch on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 3.1748
- Accuracy: 0.4358
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 |
|---|
| 5.5872 | 1.0 | 1729 | 4.0894 | 0.3311 |
| 3.8931 | 2.0 | 3458 | 3.6326 | 0.3798 |
| 3.5647 | 3.0 | 5187 | 3.4564 | 0.3997 |
| 3.4645 | 4.0 | 6916 | 3.3589 | 0.4124 |
| 3.3429 | 5.0 | 8645 | 3.2932 | 0.4196 |
| 3.2673 | 6.0 | 10374 | 3.2507 | 0.4251 |
| 3.2099 | 7.0 | 12103 | 3.2205 | 0.4295 |
| 3.1748 | 8.0 | 13832 | 3.1961 | 0.4335 |
| 3.1364 | 9.0 | 15561 | 3.1823 | 0.4351 |
| 3.1106 | 10.0 | 17290 | 3.1748 | 0.4358 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.8.0+cu128
- Datasets 4.1.1
- Tokenizers 0.19.1
