metadata
license: mit
base_model: gpt2
tags:
- generated_from_trainer
datasets:
- generator
model-index:
- name: codeparrot-ds
results: []
codeparrot-ds
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.1599
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: 0.001
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 1000
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 6.4743 | 0.2 | 30 | 5.0870 |
| 4.6204 | 0.4 | 60 | 4.1067 |
| 3.6208 | 0.6 | 90 | 3.3209 |
| 2.8321 | 0.79 | 120 | 3.0225 |
| 2.5107 | 0.99 | 150 | 2.7852 |
| 2.1614 | 1.19 | 180 | 2.7309 |
| 1.868 | 1.39 | 210 | 2.8328 |
| 1.7025 | 1.59 | 240 | 2.9077 |
| 1.4511 | 1.79 | 270 | 3.0556 |
| 1.1884 | 1.99 | 300 | 3.3297 |
| 1.0243 | 2.19 | 330 | 3.4177 |
| 0.9155 | 2.38 | 360 | 3.4031 |
| 0.7844 | 2.58 | 390 | 3.6728 |
| 0.688 | 2.78 | 420 | 4.0511 |
| 0.7049 | 2.98 | 450 | 4.1599 |
Framework versions
- Transformers 4.39.2
- Pytorch 2.2.1
- Datasets 2.18.0
- Tokenizers 0.15.2