metadata
library_name: peft
license: bigcode-openrail-m
base_model: bigcode/starcoderbase-1b
tags:
- generated_from_trainer
model-index:
- name: starcoder-peft-airscript
results: []
starcoder-peft-airscript
This model is a fine-tuned version of bigcode/starcoderbase-1b on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7155
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: 10
- eval_batch_size: 10
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 20
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 30
- training_steps: 1700
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.2691 | 0.0588 | 100 | 1.1636 |
| 0.9655 | 0.1176 | 200 | 0.9384 |
| 0.8138 | 0.1765 | 300 | 0.8387 |
| 0.719 | 0.2353 | 400 | 0.7847 |
| 0.6408 | 0.2941 | 500 | 0.7503 |
| 0.5788 | 0.3529 | 600 | 0.7314 |
| 0.5386 | 0.4118 | 700 | 0.7168 |
| 0.4894 | 0.4706 | 800 | 0.7156 |
| 0.4583 | 0.5294 | 900 | 0.7101 |
| 0.4271 | 0.5882 | 1000 | 0.7070 |
| 0.4053 | 0.6471 | 1100 | 0.7117 |
| 0.3934 | 0.7059 | 1200 | 0.7123 |
| 0.379 | 0.7647 | 1300 | 0.7143 |
| 0.3666 | 0.8235 | 1400 | 0.7171 |
| 0.363 | 0.8824 | 1500 | 0.7171 |
| 0.3588 | 0.9412 | 1600 | 0.7163 |
| 0.357 | 1.0 | 1700 | 0.7155 |
Framework versions
- PEFT 0.13.2
- Transformers 4.45.2
- Pytorch 2.5.0
- Datasets 3.0.1
- Tokenizers 0.20.1