---
base_model: microsoft/Phi-3-mini-4k-instruct
library_name: peft
license: mit
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: phi-3-mini-LoRA
  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. -->

[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/caballeromarco-microsoft/Phi3-mini-ft-python-code/runs/5en76rqc)
# phi-3-mini-LoRA

This model is a fine-tuned version of [microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5562

## 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: 0.0001
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 0.8876        | 0.1810 | 100  | 0.6187          |
| 0.5945        | 0.3619 | 200  | 0.5746          |
| 0.57          | 0.5429 | 300  | 0.5678          |
| 0.5714        | 0.7238 | 400  | 0.5638          |
| 0.558         | 0.9048 | 500  | 0.5623          |
| 0.5654        | 1.0857 | 600  | 0.5608          |
| 0.5526        | 1.2667 | 700  | 0.5597          |
| 0.5538        | 1.4476 | 800  | 0.5588          |
| 0.5667        | 1.6286 | 900  | 0.5579          |
| 0.5557        | 1.8095 | 1000 | 0.5574          |
| 0.5546        | 1.9905 | 1100 | 0.5570          |
| 0.5469        | 2.1715 | 1200 | 0.5566          |
| 0.5611        | 2.3524 | 1300 | 0.5566          |
| 0.5511        | 2.5334 | 1400 | 0.5563          |
| 0.5523        | 2.7143 | 1500 | 0.5562          |
| 0.5541        | 2.8953 | 1600 | 0.5562          |


### Framework versions

- PEFT 0.11.1
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1