metadata
license: bigcode-openrail-m
library_name: peft
tags:
- generated_from_trainer
base_model: bigcode/starcoderbase-1b
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: 1.0589
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 | 0.9183 |
| 0.9898 | 0.1 | 200 | 0.9449 |
| 0.6517 | 0.15 | 300 | 0.9680 |
| 0.8964 | 0.2 | 400 | 0.9818 |
| 0.9497 | 0.25 | 500 | 0.9720 |
| 0.5741 | 0.3 | 600 | 1.0102 |
| 0.7987 | 0.35 | 700 | 1.0202 |
| 0.8268 | 0.4 | 800 | 1.0128 |
| 0.5202 | 0.45 | 900 | 1.0189 |
| 0.7509 | 0.5 | 1000 | 1.0335 |
| 0.772 | 0.55 | 1100 | 1.0386 |
| 0.4747 | 0.6 | 1200 | 1.0525 |
| 0.696 | 0.65 | 1300 | 1.0382 |
| 0.684 | 0.7 | 1400 | 1.0469 |
| 0.5396 | 0.75 | 1500 | 1.0523 |
| 0.6567 | 0.8 | 1600 | 1.0546 |
| 0.6006 | 0.85 | 1700 | 1.0596 |
| 0.6014 | 0.9 | 1800 | 1.0620 |
| 0.5551 | 0.95 | 1900 | 1.0612 |
| 0.5881 | 1.0 | 2000 | 1.0589 |
Framework versions
- PEFT 0.11.1
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1