metadata
library_name: peft
license: bigcode-openrail-m
base_model: bigcode/starcoder2-3b
tags:
- generated_from_trainer
model-index:
- name: peft-starcoder2-3b-1000steps
results: []
peft-starcoder2-3b-1000steps
This model is a fine-tuned version of bigcode/starcoder2-3b on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6624
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: 0.0004
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 30
- training_steps: 1000
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.8125 | 0.1 | 100 | 0.6781 |
| 0.6981 | 0.2 | 200 | 0.6661 |
| 1.3622 | 0.3 | 300 | 0.6622 |
| 1.9643 | 0.4 | 400 | 0.6695 |
| 0.804 | 0.5 | 500 | 0.6673 |
| 1.3783 | 0.6 | 600 | 0.6639 |
| 1.3237 | 0.7 | 700 | 0.6666 |
| 1.6607 | 0.8 | 800 | 0.6631 |
| 1.4816 | 0.9 | 900 | 0.6621 |
| 0.9183 | 1.0 | 1000 | 0.6624 |
Framework versions
- PEFT 0.14.0
- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0