gpt2_small_PL_superbpe_32768_parallel10_42
This model was trained from scratch on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 4.7505
- Accuracy: 0.2842
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 |
|---|
| 7.5786 | 1.0 | 1189 | 6.4504 | 0.1878 |
| 6.2385 | 2.0 | 2378 | 5.6280 | 0.2237 |
| 5.6492 | 3.0 | 3567 | 5.2693 | 0.2448 |
| 5.3382 | 4.0 | 4756 | 5.0823 | 0.2563 |
| 5.1473 | 5.0 | 5945 | 4.9637 | 0.2655 |
| 4.9115 | 6.0 | 7134 | 4.8808 | 0.2714 |
| 4.8332 | 7.0 | 8323 | 4.8244 | 0.2772 |
| 4.7731 | 8.0 | 9512 | 4.7854 | 0.2807 |
| 4.7272 | 9.0 | 10701 | 4.7607 | 0.2828 |
| 4.6916 | 10.0 | 11890 | 4.7505 | 0.2842 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.8.0+cu128
- Datasets 4.1.1
- Tokenizers 0.19.1
