|
--- |
|
license: bigcode-openrail-m |
|
library_name: peft |
|
tags: |
|
- generated_from_trainer |
|
base_model: bigcode/starcoder2-3b |
|
model-index: |
|
- name: starcoder2-3b-peft-lora |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/hvl-ml/huggingface/runs/71217l2g) |
|
# starcoder2-3b-peft-lora |
|
|
|
This model is a fine-tuned version of [bigcode/starcoder2-3b](https://huggingface.co./bigcode/starcoder2-3b) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.7576 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 0.5348 | 0.05 | 100 | 0.9196 | |
|
| 0.8854 | 0.1 | 200 | 0.8079 | |
|
| 0.6684 | 0.15 | 300 | 0.7977 | |
|
| 0.7444 | 0.2 | 400 | 0.7962 | |
|
| 0.2232 | 0.25 | 500 | 0.8324 | |
|
| 0.4756 | 0.3 | 600 | 0.7965 | |
|
| 0.4507 | 0.35 | 700 | 0.7983 | |
|
| 0.747 | 0.4 | 800 | 0.7863 | |
|
| 0.4285 | 0.45 | 900 | 0.7854 | |
|
| 0.3905 | 0.5 | 1000 | 0.8041 | |
|
| 0.7737 | 0.55 | 1100 | 0.7641 | |
|
| 0.5301 | 0.6 | 1200 | 0.7599 | |
|
| 0.6514 | 0.65 | 1300 | 0.7561 | |
|
| 0.1931 | 0.7 | 1400 | 0.7659 | |
|
| 0.4201 | 0.75 | 1500 | 0.7567 | |
|
| 0.4191 | 0.8 | 1600 | 0.7566 | |
|
| 0.6998 | 0.85 | 1700 | 0.7530 | |
|
| 0.4025 | 0.9 | 1800 | 0.7528 | |
|
| 0.3656 | 0.95 | 1900 | 0.7605 | |
|
| 0.6816 | 1.0 | 2000 | 0.7576 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.10.1.dev0 |
|
- Transformers 4.41.0.dev0 |
|
- Pytorch 2.3.0 |
|
- Datasets 2.19.0 |
|
- Tokenizers 0.19.1 |
