---
license: bigcode-openrail-m
library_name: peft
tags:
- generated_from_trainer
base_model: bigcode/starcoderbase-1b
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: 1.0584

## 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 |
|:-------------:|:-----:|:----:|:---------------:|
| 0.9661        | 0.05  | 100  | 0.9191          |
| 0.99          | 0.1   | 200  | 0.9444          |
| 0.6519        | 0.15  | 300  | 0.9675          |
| 0.8967        | 0.2   | 400  | 0.9820          |
| 0.9498        | 0.25  | 500  | 0.9725          |
| 0.574         | 0.3   | 600  | 1.0097          |
| 0.7988        | 0.35  | 700  | 1.0181          |
| 0.8264        | 0.4   | 800  | 1.0122          |
| 0.5209        | 0.45  | 900  | 1.0173          |
| 0.7516        | 0.5   | 1000 | 1.0316          |
| 0.7716        | 0.55  | 1100 | 1.0355          |
| 0.4749        | 0.6   | 1200 | 1.0538          |
| 0.6964        | 0.65  | 1300 | 1.0393          |
| 0.6841        | 0.7   | 1400 | 1.0459          |
| 0.5397        | 0.75  | 1500 | 1.0513          |
| 0.6572        | 0.8   | 1600 | 1.0543          |
| 0.6004        | 0.85  | 1700 | 1.0606          |
| 0.6017        | 0.9   | 1800 | 1.0621          |
| 0.5555        | 0.95  | 1900 | 1.0611          |
| 0.5882        | 1.0   | 2000 | 1.0584          |


### Framework versions

- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2