gpt2_small_ZH_unigram_32768_parallel3_42
This model was trained from scratch on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 4.0389
- Accuracy: 0.3345
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 |
|---|
| 4.5857 | 1.0 | 21956 | 4.4895 | 0.2906 |
| 4.3774 | 2.0 | 43912 | 4.3030 | 0.3071 |
| 4.2777 | 3.0 | 65868 | 4.2174 | 0.3153 |
| 4.2158 | 4.0 | 87824 | 4.1653 | 0.3204 |
| 4.1694 | 5.0 | 109780 | 4.1286 | 0.3238 |
| 4.133 | 6.0 | 131736 | 4.1008 | 0.3267 |
| 4.1015 | 7.0 | 153692 | 4.0786 | 0.3293 |
| 4.0737 | 8.0 | 175648 | 4.0613 | 0.3314 |
| 4.0501 | 9.0 | 197604 | 4.0471 | 0.3335 |
| 4.029 | 10.0 | 219560 | 4.0389 | 0.3345 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.8.0+cu128
- Datasets 4.1.1
- Tokenizers 0.19.1
