---
license: bigcode-openrail-m
base_model: bigcode/starcoder
tags:
- generated_from_trainer
model-index:
- name: peft-lora-starcoder15B-v2-personal-copilot-A100-40GB-colab
  results: []
library_name: peft
---

<!-- 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-lora-starcoder15B-v2-personal-copilot-A100-40GB-colab

This model is a fine-tuned version of [bigcode/starcoder](https://huggingface.co/bigcode/starcoder) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3096

## Model description

More information needed

## Intended uses & limitations

More information needed

## Training and evaluation data

More information needed

## Training procedure


The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: bfloat16
### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 0.0005
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- 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 |
|:-------------:|:-----:|:----:|:---------------:|
| 0.6439        | 0.05  | 100  | 0.5595          |
| 0.6009        | 0.1   | 200  | 0.4901          |
| 0.6335        | 0.15  | 300  | 0.4320          |
| 0.5266        | 0.2   | 400  | 0.4082          |
| 0.4543        | 0.25  | 500  | 0.4012          |
| 0.4808        | 0.3   | 600  | 0.3911          |
| 0.461         | 0.35  | 700  | 0.4364          |
| 0.5246        | 0.4   | 800  | 0.3720          |
| 0.408         | 0.45  | 900  | 0.3655          |
| 0.469         | 0.5   | 1000 | 0.3504          |
| 0.4257        | 0.55  | 1100 | 0.3396          |
| 0.4229        | 0.6   | 1200 | 0.3195          |
| 0.3267        | 0.65  | 1300 | 0.3147          |
| 0.4682        | 0.7   | 1400 | 0.3110          |
| 0.3244        | 0.75  | 1500 | 0.3091          |
| 0.6782        | 0.8   | 1600 | 0.3085          |
| 0.3123        | 0.85  | 1700 | 0.3084          |
| 0.3545        | 0.9   | 1800 | 0.3094          |
| 0.2818        | 0.95  | 1900 | 0.3095          |
| 0.397         | 1.0   | 2000 | 0.3096          |


### Framework versions

- PEFT 0.5.0.dev0
- Transformers 4.32.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3