metadata
library_name: peft
license: bigcode-openrail-m
base_model: bigcode/starcoderbase-1b
tags:
- generated_from_trainer
model-index:
- name: peft-starcoder-lora-a100
results: []
peft-starcoder-lora-a100
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: 1.0237
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: 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: 2000
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.0223 | 0.05 | 100 | 0.9318 |
| 0.9002 | 0.1 | 200 | 0.9680 |
| 0.9073 | 0.15 | 300 | 0.9542 |
| 0.9978 | 0.2 | 400 | 0.9649 |
| 0.7645 | 0.25 | 500 | 0.9714 |
| 0.637 | 0.3 | 600 | 0.9882 |
| 0.9736 | 0.35 | 700 | 0.9911 |
| 0.7983 | 0.4 | 800 | 0.9924 |
| 0.8812 | 0.45 | 900 | 0.9873 |
| 0.9062 | 0.5 | 1000 | 0.9856 |
| 0.6797 | 0.55 | 1100 | 0.9957 |
| 0.5671 | 0.6 | 1200 | 1.0081 |
| 0.9692 | 0.65 | 1300 | 1.0137 |
| 0.714 | 0.7 | 1400 | 1.0122 |
| 0.9059 | 0.75 | 1500 | 1.0139 |
| 0.8034 | 0.8 | 1600 | 1.0147 |
| 0.6628 | 0.85 | 1700 | 1.0126 |
| 0.5018 | 0.9 | 1800 | 1.0171 |
| 1.0041 | 0.95 | 1900 | 1.0244 |
| 0.7226 | 1.0 | 2000 | 1.0237 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.3
- Pytorch 2.5.1+cu124
- Datasets 3.1.0
- Tokenizers 0.20.3