metadata
base_model: bigcode/starcoderbase-1b
library_name: peft
license: bigcode-openrail-m
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: 1.0561
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 30
- training_steps: 2000
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.9659 | 0.05 | 100 | 0.9182 |
| 0.9787 | 0.1 | 200 | 0.9662 |
| 0.6794 | 0.15 | 300 | 0.9643 |
| 0.8904 | 0.2 | 400 | 0.9859 |
| 0.9475 | 0.25 | 500 | 0.9722 |
| 0.6104 | 0.3 | 600 | 1.0055 |
| 0.7898 | 0.35 | 700 | 1.0080 |
| 0.867 | 0.4 | 800 | 1.0084 |
| 0.5121 | 0.45 | 900 | 1.0247 |
| 0.6899 | 0.5 | 1000 | 1.0339 |
| 0.7746 | 0.55 | 1100 | 1.0371 |
| 0.478 | 0.6 | 1200 | 1.0430 |
| 0.7257 | 0.65 | 1300 | 1.0464 |
| 0.6989 | 0.7 | 1400 | 1.0504 |
| 0.5822 | 0.75 | 1500 | 1.0560 |
| 0.6881 | 0.8 | 1600 | 1.0522 |
| 0.5939 | 0.85 | 1700 | 1.0582 |
| 0.632 | 0.9 | 1800 | 1.0598 |
| 0.6888 | 0.95 | 1900 | 1.0579 |
| 0.5719 | 1.0 | 2000 | 1.0561 |
Framework versions
- PEFT 0.13.0
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.19.1