metadata
license: bigcode-openrail-m
base_model: bigcode/santacoder
tags:
- generated_from_trainer
model-index:
- name: santacoder-finetuned-the-stack-bash
results: []
santacoder-finetuned-the-stack-bash
This model is a fine-tuned version of bigcode/santacoder on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2202
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: 5e-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: 100
- training_steps: 5000
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.7564 | 0.1 | 500 | 1.3213 |
| 1.6757 | 0.2 | 1000 | 4.5570 |
| 1.6668 | 0.3 | 1500 | 7.4934 |
| 0.4505 | 0.4 | 2000 | 0.4260 |
| 1.6604 | 0.5 | 2500 | 0.5150 |
| 1.6552 | 0.6 | 3000 | 0.5775 |
| 1.6481 | 0.7 | 3500 | 0.6173 |
| 1.656 | 0.8 | 4000 | 0.2171 |
| 1.6554 | 0.9 | 4500 | 0.2198 |
| 1.6563 | 1.0 | 5000 | 0.2202 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1
- Datasets 2.14.5
- Tokenizers 0.13.3