library_name, license, base_model, tags, model-index
| library_name | license | base_model | tags | model-index | ||||||
|---|---|---|---|---|---|---|---|---|---|---|
| transformers | mit | openai-community/gpt2 |
|
|
stoyan-training
This model is a fine-tuned version of openai-community/gpt2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.7659
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: 2e-05
- train_batch_size: 4
- eval_batch_size: 3
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.152 | 1.0 | 5 | 3.9400 |
| 3.9276 | 2.0 | 10 | 3.8854 |
| 3.8264 | 3.0 | 15 | 3.8372 |
| 3.7508 | 4.0 | 20 | 3.8021 |
| 3.6969 | 5.0 | 25 | 3.7836 |
| 3.686 | 6.0 | 30 | 3.7735 |
| 3.622 | 7.0 | 35 | 3.7677 |
| 3.5833 | 8.0 | 40 | 3.7659 |
Framework versions
- Transformers 4.56.0
- Pytorch 2.8.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.0