metadata
license: mit
base_model: gpt2
tags:
- generated_from_trainer
model-index:
- name: codeparrot-ds
results: []
codeparrot-ds
This model is a fine-tuned version of gpt2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.0896
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: 0.0005
- train_batch_size: 96
- eval_batch_size: 96
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 768
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 1000
- num_epochs: 1
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.4935 | 0.23 | 5000 | 1.4177 |
| 1.3089 | 0.46 | 10000 | 1.2413 |
| 1.2055 | 0.69 | 15000 | 1.1374 |
| 1.1502 | 0.92 | 20000 | 1.0896 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2