gpt2_small_ZH_unigram_65536_parallel10_42
This model was trained from scratch on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 5.3473
- Accuracy: 0.3310
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 |
|---|
| 7.0817 | 1.0 | 1184 | 6.3505 | 0.3053 |
| 6.238 | 2.0 | 2368 | 5.9655 | 0.3125 |
| 5.9555 | 3.0 | 3552 | 5.7635 | 0.3178 |
| 5.784 | 4.0 | 4736 | 5.6290 | 0.3211 |
| 5.6544 | 5.0 | 5920 | 5.5339 | 0.3242 |
| 5.4701 | 6.0 | 7104 | 5.4643 | 0.3266 |
| 5.3996 | 7.0 | 8288 | 5.4123 | 0.3287 |
| 5.3466 | 8.0 | 9472 | 5.3771 | 0.3300 |
| 5.305 | 9.0 | 10656 | 5.3559 | 0.3307 |
| 5.2748 | 10.0 | 11840 | 5.3473 | 0.3310 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.8.0+cu128
- Datasets 4.1.1
- Tokenizers 0.19.1
