gpt2_small_AR_bpe_8192_parallel10_42
This model was trained from scratch on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 3.5706
- Accuracy: 0.3813
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 |
|---|
| 5.8094 | 1.0 | 1800 | 4.3684 | 0.3047 |
| 4.2356 | 2.0 | 3600 | 3.9824 | 0.3391 |
| 3.9444 | 3.0 | 5400 | 3.8304 | 0.3522 |
| 3.8013 | 4.0 | 7200 | 3.7407 | 0.3626 |
| 3.7105 | 5.0 | 9000 | 3.6851 | 0.3679 |
| 3.6562 | 6.0 | 10800 | 3.6422 | 0.3727 |
| 3.6017 | 7.0 | 12600 | 3.6123 | 0.3766 |
| 3.5569 | 8.0 | 14400 | 3.5906 | 0.3785 |
| 3.5237 | 9.0 | 16200 | 3.5770 | 0.3802 |
| 3.4986 | 10.0 | 18000 | 3.5706 | 0.3813 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.9.0+cu128
- Datasets 4.1.1
- Tokenizers 0.19.1
