zulqarnain-kernel's picture
Update README.md
e39e3f2 verified
---
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 smangrul/hf-stack-v1.
It achieves the following results on the evaluation set:
- Loss: 1.0588
## 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 |
|:-------------:|:-----:|:----:|:---------------:|
| 0.966 | 0.05 | 100 | 0.9187 |
| 0.9901 | 0.1 | 200 | 0.9452 |
| 0.652 | 0.15 | 300 | 0.9694 |
| 0.8965 | 0.2 | 400 | 0.9817 |
| 0.95 | 0.25 | 500 | 0.9733 |
| 0.5742 | 0.3 | 600 | 1.0134 |
| 0.7988 | 0.35 | 700 | 1.0195 |
| 0.8267 | 0.4 | 800 | 1.0142 |
| 0.5204 | 0.45 | 900 | 1.0214 |
| 0.7507 | 0.5 | 1000 | 1.0318 |
| 0.7719 | 0.55 | 1100 | 1.0347 |
| 0.475 | 0.6 | 1200 | 1.0529 |
| 0.6964 | 0.65 | 1300 | 1.0411 |
| 0.6843 | 0.7 | 1400 | 1.0465 |
| 0.5395 | 0.75 | 1500 | 1.0512 |
| 0.6568 | 0.8 | 1600 | 1.0550 |
| 0.6003 | 0.85 | 1700 | 1.0598 |
| 0.6013 | 0.9 | 1800 | 1.0626 |
| 0.5553 | 0.95 | 1900 | 1.0613 |
| 0.588 | 1.0 | 2000 | 1.0588 |
### Framework versions
- PEFT 0.11.1
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1