gpt2_small_AR_bpe_65536_parallel3-100_42
This model was trained from scratch on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 3.6810
- Accuracy: 0.3802
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 |
|---|
| 4.4946 | 1.0 | 7193 | 4.3591 | 0.3223 |
| 4.1424 | 2.0 | 14386 | 4.0413 | 0.3462 |
| 3.9765 | 3.0 | 21579 | 3.9095 | 0.3574 |
| 3.8794 | 4.0 | 28772 | 3.8339 | 0.3632 |
| 3.8094 | 5.0 | 35965 | 3.7838 | 0.3685 |
| 3.7492 | 6.0 | 43158 | 3.7470 | 0.3722 |
| 3.706 | 7.0 | 50351 | 3.7217 | 0.3750 |
| 3.664 | 8.0 | 57544 | 3.7008 | 0.3772 |
| 3.6333 | 9.0 | 64737 | 3.6881 | 0.3789 |
| 3.6113 | 10.0 | 71930 | 3.6810 | 0.3802 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.8.0+cu128
- Datasets 4.1.1
- Tokenizers 0.19.1
