---
license: mit
library_name: peft
tags:
- generated_from_trainer
base_model: microsoft/Phi-3-mini-128k-instruct
model-index:
- name: CodePhi-3-mini-128k-instruct-appsloraN10k8-16
  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. -->

# CodePhi-3-mini-128k-instruct-appsloraN10k8-16

This model is a fine-tuned version of [microsoft/Phi-3-mini-128k-instruct](https://huggingface.co/microsoft/Phi-3-mini-128k-instruct) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6381

## 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: 5e-06
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 200
- training_steps: 10000

### Training results

| Training Loss | Epoch | Step  | Validation Loss |
|:-------------:|:-----:|:-----:|:---------------:|
| 0.6865        | 0.05  | 500   | 0.6835          |
| 0.5164        | 0.1   | 1000  | 0.6724          |
| 0.5129        | 0.15  | 1500  | 0.6621          |
| 0.6136        | 0.2   | 2000  | 0.6542          |
| 0.4944        | 0.25  | 2500  | 0.6500          |
| 0.756         | 0.3   | 3000  | 0.6460          |
| 0.5947        | 0.35  | 3500  | 0.6431          |
| 0.5981        | 0.4   | 4000  | 0.6423          |
| 0.6912        | 0.45  | 4500  | 0.6408          |
| 0.5595        | 0.5   | 5000  | 0.6400          |
| 0.5818        | 0.55  | 5500  | 0.6391          |
| 0.5914        | 0.6   | 6000  | 0.6386          |
| 0.5519        | 0.65  | 6500  | 0.6383          |
| 0.5608        | 0.7   | 7000  | 0.6383          |
| 0.615         | 0.75  | 7500  | 0.6381          |
| 0.6229        | 0.8   | 8000  | 0.6381          |
| 0.602         | 0.85  | 8500  | 0.6381          |
| 0.6142        | 0.9   | 9000  | 0.6380          |
| 0.5413        | 0.95  | 9500  | 0.6381          |
| 0.5866        | 1.0   | 10000 | 0.6381          |


### Framework versions

- PEFT 0.11.0
- Transformers 4.40.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1