---
base_model: microsoft/Phi-3.5-mini-instruct
library_name: peft
license: mit
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: Phi-3.5-mini-instruct-qlora
  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. -->

# Phi-3.5-mini-instruct-qlora

This model is a fine-tuned version of [microsoft/Phi-3.5-mini-instruct](https://huggingface.co/microsoft/Phi-3.5-mini-instruct) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.2826

## 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: 0
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.01
- num_epochs: 8

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 1.5888        | 0.3333 | 10   | 1.2792          |
| 1.0726        | 0.6667 | 20   | 0.9828          |
| 0.888         | 1.0    | 30   | 0.9024          |
| 0.7963        | 1.3333 | 40   | 0.8658          |
| 0.7337        | 1.6667 | 50   | 0.8401          |
| 0.6872        | 2.0    | 60   | 0.8318          |
| 0.5993        | 2.3333 | 70   | 0.8555          |
| 0.5729        | 2.6667 | 80   | 0.8428          |
| 0.5801        | 3.0    | 90   | 0.8442          |
| 0.4496        | 3.3333 | 100  | 0.9053          |
| 0.4222        | 3.6667 | 110  | 0.9160          |
| 0.4442        | 4.0    | 120  | 0.8870          |
| 0.3334        | 4.3333 | 130  | 1.0457          |
| 0.313         | 4.6667 | 140  | 1.0713          |
| 0.2812        | 5.0    | 150  | 1.0192          |
| 0.2172        | 5.3333 | 160  | 1.1357          |
| 0.1987        | 5.6667 | 170  | 1.2162          |
| 0.2137        | 6.0    | 180  | 1.1945          |
| 0.1624        | 6.3333 | 190  | 1.2194          |
| 0.1574        | 6.6667 | 200  | 1.2533          |
| 0.1571        | 7.0    | 210  | 1.2679          |
| 0.1379        | 7.3333 | 220  | 1.2757          |
| 0.1386        | 7.6667 | 230  | 1.2810          |
| 0.1356        | 8.0    | 240  | 1.2826          |


### Framework versions

- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.4.0
- Datasets 3.0.2
- Tokenizers 0.20.0