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

# finetuned

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: 0.2803

## 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: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- 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 |
|:-------------:|:------:|:----:|:---------------:|
| 0.5282        | 0.3410 | 100  | 0.4418          |
| 0.3992        | 0.6820 | 200  | 0.3800          |
| 0.3324        | 1.0230 | 300  | 0.3341          |
| 0.3127        | 1.3640 | 400  | 0.3147          |
| 0.2591        | 1.7050 | 500  | 0.2895          |
| 0.2621        | 2.0460 | 600  | 0.2926          |
| 0.2195        | 2.3870 | 700  | 0.2826          |
| 0.2225        | 2.7280 | 800  | 0.2803          |


### Framework versions

- PEFT 0.13.0
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.19.1