metadata
license: mit
base_model: openai-community/gpt2
tags:
- generated_from_trainer
model-index:
- name: results
results: []
results
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: 1.7840
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: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.6089 | 0.11 | 500 | 2.4953 |
| 2.4861 | 0.23 | 1000 | 2.3031 |
| 2.2466 | 0.34 | 1500 | 2.1884 |
| 2.1959 | 0.45 | 2000 | 2.1158 |
| 2.1861 | 0.56 | 2500 | 2.0607 |
| 2.0509 | 0.68 | 3000 | 2.0170 |
| 2.0867 | 0.79 | 3500 | 1.9839 |
| 2.0165 | 0.9 | 4000 | 1.9543 |
| 2.0106 | 1.02 | 4500 | 1.9313 |
| 1.9741 | 1.13 | 5000 | 1.9129 |
| 1.957 | 1.24 | 5500 | 1.8919 |
| 1.9226 | 1.35 | 6000 | 1.8782 |
| 1.8832 | 1.47 | 6500 | 1.8663 |
| 1.9208 | 1.58 | 7000 | 1.8515 |
| 1.9218 | 1.69 | 7500 | 1.8432 |
| 1.9362 | 1.8 | 8000 | 1.8313 |
| 1.8131 | 1.92 | 8500 | 1.8228 |
| 1.8094 | 2.03 | 9000 | 1.8154 |
| 1.8363 | 2.14 | 9500 | 1.8082 |
| 1.8634 | 2.26 | 10000 | 1.8010 |
| 1.8006 | 2.37 | 10500 | 1.7979 |
| 1.867 | 2.48 | 11000 | 1.7947 |
| 1.8712 | 2.59 | 11500 | 1.7898 |
| 1.8806 | 2.71 | 12000 | 1.7885 |
| 1.8838 | 2.82 | 12500 | 1.7856 |
| 1.8542 | 2.93 | 13000 | 1.7840 |
Framework versions
- Transformers 4.38.1
- Pytorch 2.5.1+cu124
- Datasets 2.17.0
- Tokenizers 0.15.2