gpt2_small_PL_unigram_81920_parallel10_42
This model was trained from scratch on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 3.9543
- Accuracy: 0.3999
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 |
|---|
| 6.3131 | 1.0 | 1387 | 4.9109 | 0.3407 |
| 4.9167 | 2.0 | 2774 | 4.4722 | 0.3656 |
| 4.3935 | 3.0 | 4161 | 4.2834 | 0.3769 |
| 4.263 | 4.0 | 5548 | 4.1731 | 0.3832 |
| 4.1741 | 5.0 | 6935 | 4.0940 | 0.3894 |
| 4.0357 | 6.0 | 8322 | 4.0397 | 0.3921 |
| 3.9874 | 7.0 | 9709 | 4.0025 | 0.3961 |
| 3.9166 | 8.0 | 11096 | 3.9763 | 0.3977 |
| 3.8821 | 9.0 | 12483 | 3.9598 | 0.3993 |
| 3.8644 | 10.0 | 13870 | 3.9543 | 0.3999 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.8.0+cu128
- Datasets 4.1.1
- Tokenizers 0.19.1
