codeparrot-ds
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 4.5904
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: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 256
- 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 |
|---|---|---|---|
| 4.9189 | 0.0766 | 5000 | 4.7222 |
| 4.6994 | 0.1533 | 10000 | 4.6899 |
| 4.6724 | 0.2299 | 15000 | 4.6754 |
| 4.6608 | 0.3065 | 20000 | 4.6618 |
| 4.6498 | 0.3832 | 25000 | 4.6529 |
| 4.6401 | 0.4598 | 30000 | 4.6463 |
| 4.6328 | 0.5365 | 35000 | 4.6370 |
| 4.6226 | 0.6131 | 40000 | 4.6300 |
| 4.6128 | 0.6897 | 45000 | 4.6196 |
| 4.6034 | 0.7664 | 50000 | 4.6116 |
| 4.5965 | 0.8430 | 55000 | 4.6028 |
| 4.5869 | 0.9196 | 60000 | 4.5959 |
| 4.5813 | 0.9963 | 65000 | 4.5904 |
Framework versions
- Transformers 4.45.0.dev0
- Pytorch 2.2.0
- Datasets 3.0.0
- Tokenizers 0.19.1
- Downloads last month
- 4