---
base_model: microsoft/Phi-3-mini-4k-instruct
library_name: peft
license: mit
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: phi3-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. -->

# phi3-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: 0.5538

## 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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- 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 |
|:-------------:|:------:|:----:|:---------------:|
| 0.8693        | 0.1809 | 100  | 0.6163          |
| 0.5925        | 0.3618 | 200  | 0.5740          |
| 0.5675        | 0.5427 | 300  | 0.5667          |
| 0.571         | 0.7237 | 400  | 0.5631          |
| 0.555         | 0.9046 | 500  | 0.5613          |
| 0.566         | 1.0855 | 600  | 0.5597          |
| 0.5502        | 1.2664 | 700  | 0.5583          |
| 0.5524        | 1.4473 | 800  | 0.5575          |
| 0.5653        | 1.6282 | 900  | 0.5565          |
| 0.5515        | 1.8091 | 1000 | 0.5561          |
| 0.5523        | 1.9900 | 1100 | 0.5555          |
| 0.5422        | 2.1710 | 1200 | 0.5555          |
| 0.559         | 2.3519 | 1300 | 0.5546          |
| 0.5466        | 2.5328 | 1400 | 0.5542          |
| 0.5476        | 2.7137 | 1500 | 0.5541          |
| 0.55          | 2.8946 | 1600 | 0.5538          |


### Framework versions

- PEFT 0.13.0
- Transformers 4.45.1
- Pytorch 2.2.2
- Datasets 3.0.1
- Tokenizers 0.20.0