gpt2_small_EN_superbpe_32768_parallel10_42
This model was trained from scratch on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 4.5944
- Accuracy: 0.2625
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: 16
- eval_batch_size: 16
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- total_train_batch_size: 32
- total_eval_batch_size: 32
- 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 |
|---|
| 5.472 | 1.0 | 5013 | 5.3542 | 0.2086 |
| 5.0987 | 2.0 | 10026 | 5.0287 | 0.2279 |
| 4.8915 | 3.0 | 15039 | 4.8631 | 0.2393 |
| 4.755 | 4.0 | 20052 | 4.7647 | 0.2461 |
| 4.6465 | 5.0 | 25065 | 4.7019 | 0.2507 |
| 4.559 | 6.0 | 30078 | 4.6587 | 0.2549 |
| 4.4812 | 7.0 | 35091 | 4.6291 | 0.2583 |
| 4.4173 | 8.0 | 40104 | 4.6093 | 0.2604 |
| 4.3617 | 9.0 | 45117 | 4.5988 | 0.2615 |
| 4.3156 | 10.0 | 50130 | 4.5944 | 0.2625 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.8.0+cu128
- Datasets 4.1.1
- Tokenizers 0.19.1
