---
library_name: peft
license: bigcode-openrail-m
base_model: bigcode/starcoderbase-1b
tags:
- generated_from_trainer
model-index:
- name: peft-codelama-7b-qlora-scilab
  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-codelama-7b-qlora-scilab

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: 0.6951

## 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 OptimizerNames.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 |
|:-------------:|:-----:|:----:|:---------------:|
| 0.7491        | 0.05  | 100  | 0.7142          |
| 0.2948        | 0.1   | 200  | 0.6996          |
| 0.4097        | 0.15  | 300  | 0.6878          |
| 0.3277        | 0.2   | 400  | 0.6848          |
| 0.2849        | 0.25  | 500  | 0.6813          |
| 0.4167        | 0.3   | 600  | 0.6792          |
| 0.2903        | 0.35  | 700  | 0.6812          |
| 0.4744        | 0.4   | 800  | 0.6819          |
| 0.4023        | 0.45  | 900  | 0.6815          |
| 0.3235        | 0.5   | 1000 | 0.6817          |
| 0.4935        | 0.55  | 1100 | 0.6850          |
| 0.2069        | 0.6   | 1200 | 0.6857          |
| 0.3495        | 0.65  | 1300 | 0.6863          |
| 0.2526        | 0.7   | 1400 | 0.6900          |
| 0.2146        | 0.75  | 1500 | 0.6923          |
| 0.3677        | 0.8   | 1600 | 0.6951          |
| 0.2449        | 0.85  | 1700 | 0.6950          |
| 0.451         | 0.9   | 1800 | 0.6940          |
| 0.348         | 0.95  | 1900 | 0.6952          |
| 0.3009        | 1.0   | 2000 | 0.6951          |


### Framework versions

- PEFT 0.14.0
- Transformers 4.48.3
- Pytorch 2.5.1+cu124
- Datasets 3.3.1
- Tokenizers 0.21.0