gpt2_small_ZH_unigram_65536_parallel3_42
This model was trained from scratch on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 4.4655
- Accuracy: 0.3136
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: 64
- eval_batch_size: 64
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- total_train_batch_size: 128
- total_eval_batch_size: 128
- 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 |
|---|
| 5.1231 | 1.0 | 19767 | 5.0212 | 0.2680 |
| 4.8533 | 2.0 | 39534 | 4.7802 | 0.2857 |
| 4.7289 | 3.0 | 59301 | 4.6740 | 0.2942 |
| 4.6505 | 4.0 | 79068 | 4.6098 | 0.2997 |
| 4.5959 | 5.0 | 98835 | 4.5665 | 0.3028 |
| 4.551 | 6.0 | 118602 | 4.5346 | 0.3063 |
| 4.5115 | 7.0 | 138369 | 4.5089 | 0.3093 |
| 4.4835 | 8.0 | 158136 | 4.4891 | 0.3113 |
| 4.4533 | 9.0 | 177903 | 4.4733 | 0.3125 |
| 4.4304 | 10.0 | 197670 | 4.4655 | 0.3136 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.8.0+cu128
- Datasets 4.1.1
- Tokenizers 0.19.1
