codeparrot-ds-sample-2ep-14apr
This model is a fine-tuned version of gpt2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.6319
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: 64
- eval_batch_size: 64
- seed: 42
- distributed_type: tpu
- gradient_accumulation_steps: 8
- total_train_batch_size: 512
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 1000
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.1367 | 0.37 | 1000 | 2.5592 |
| 2.2049 | 0.74 | 2000 | 2.0419 |
| 1.8302 | 1.11 | 3000 | 1.8245 |
| 1.6214 | 1.49 | 4000 | 1.6913 |
| 1.5125 | 1.86 | 5000 | 1.6319 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.11.0+cu102
- Datasets 2.1.0
- Tokenizers 0.12.1