---
library_name: peft
license: bigcode-openrail-m
base_model: bigcode/starcoderbase-1b
tags:
- generated_from_trainer
model-index:
- name: peft-starcoder-lora-a100
  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. -->

# peft-starcoder-lora-a100

This model is a fine-tuned version of [bigcode/starcoderbase-1b](https://huggingface.co/bigcode/starcoderbase-1b) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 2.4315

## 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: 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 |
|:-------------:|:-----:|:----:|:---------------:|
| 0.9035        | 0.05  | 100  | 1.7793          |
| 0.7702        | 0.1   | 200  | 1.7754          |
| 0.6297        | 0.15  | 300  | 1.8416          |
| 0.5922        | 0.2   | 400  | 1.8849          |
| 0.5098        | 0.25  | 500  | 1.9704          |
| 0.4911        | 0.3   | 600  | 2.0128          |
| 0.4129        | 0.35  | 700  | 2.1029          |
| 0.4079        | 0.4   | 800  | 2.1389          |
| 0.3735        | 0.45  | 900  | 2.2002          |
| 0.3562        | 0.5   | 1000 | 2.2493          |
| 0.3156        | 0.55  | 1100 | 2.2849          |
| 0.3054        | 0.6   | 1200 | 2.3290          |
| 0.293         | 0.65  | 1300 | 2.3672          |
| 0.2732        | 0.7   | 1400 | 2.3749          |
| 0.2779        | 0.75  | 1500 | 2.3940          |
| 0.2567        | 0.8   | 1600 | 2.4096          |
| 0.2781        | 0.85  | 1700 | 2.4200          |
| 0.2556        | 0.9   | 1800 | 2.4289          |
| 0.2647        | 0.95  | 1900 | 2.4303          |
| 0.247         | 1.0   | 2000 | 2.4315          |


### Framework versions

- PEFT 0.14.0
- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0