metadata
license: mit
tags:
- generated_from_trainer
base_model: gpt2
model-index:
- name: gpt2-reviews
results: []
gpt2-reviews
This model is a fine-tuned version of gpt2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0751
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 400
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.1697 | 0.83 | 390 | 0.0765 |
| 0.075 | 1.66 | 780 | 0.0758 |
| 0.0721 | 2.49 | 1170 | 0.0751 |
| 0.0716 | 3.33 | 1560 | 0.0753 |
| 0.0714 | 4.16 | 1950 | 0.0753 |
| 0.071 | 4.99 | 2340 | 0.0751 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2