metadata
license: bigcode-openrail-m
base_model: bigcode/tiny_starcoder_py
tags:
- generated_from_trainer
model-index:
- name: tiny_starcoder
results: []
tiny_starcoder
This model is a fine-tuned version of bigcode/tiny_starcoder_py on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8071
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: 2
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 30
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 12 | 1.1454 |
| No log | 2.0 | 24 | 0.8907 |
| No log | 3.0 | 36 | 0.7690 |
| No log | 4.0 | 48 | 0.7682 |
| No log | 5.0 | 60 | 0.7567 |
| No log | 6.0 | 72 | 0.7911 |
| No log | 7.0 | 84 | 0.7800 |
| No log | 8.0 | 96 | 0.8071 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1