gpt2_small_TR_unigram_49152_parallel10_42
This model was trained from scratch on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 4.4445
- Accuracy: 0.3576
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 |
|---|
| 6.7544 | 1.0 | 1303 | 5.5516 | 0.3019 |
| 5.4867 | 2.0 | 2606 | 5.0280 | 0.3235 |
| 5.0933 | 3.0 | 3909 | 4.8126 | 0.3345 |
| 4.7585 | 4.0 | 5212 | 4.6853 | 0.3417 |
| 4.6559 | 5.0 | 6515 | 4.5989 | 0.3471 |
| 4.5803 | 6.0 | 7818 | 4.5399 | 0.3503 |
| 4.4668 | 7.0 | 9121 | 4.4990 | 0.3536 |
| 4.4215 | 8.0 | 10424 | 4.4701 | 0.3553 |
| 4.3882 | 9.0 | 11727 | 4.4523 | 0.3565 |
| 4.346 | 10.0 | 13030 | 4.4445 | 0.3576 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.8.0+cu128
- Datasets 4.1.1
- Tokenizers 0.19.1
