<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
santacoder-finetuned-mbpp
This model is a fine-tuned version of bigcode/santacoder on the mbpp dataset. It achieves the following results on the evaluation set:
- Loss: 0.3571
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: 1e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 10
- training_steps: 100
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.317 | 0.27 | 25 | 0.3747 |
| 0.1146 | 0.53 | 50 | 0.3775 |
| 0.576 | 0.8 | 75 | 0.3562 |
| 0.344 | 1.07 | 100 | 0.3571 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
