---
license: mit
base_model: microsoft/Phi-3-mini-4k-instruct
tags:
- generated_from_trainer
model-index:
- name: Phi0503HMA23
  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. -->

# Phi0503HMA23

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: 0.0717

## 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: 0.0003
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine_with_restarts
- lr_scheduler_warmup_steps: 80
- num_epochs: 3
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 4.2718        | 0.09  | 10   | 0.6833          |
| 0.3393        | 0.18  | 20   | 0.2266          |
| 0.2573        | 0.27  | 30   | 0.2267          |
| 0.2236        | 0.36  | 40   | 0.2029          |
| 0.2141        | 0.45  | 50   | 0.2326          |
| 0.2251        | 0.54  | 60   | 0.2256          |
| 0.1965        | 0.63  | 70   | 0.1851          |
| 0.196         | 0.73  | 80   | 0.1693          |
| 0.1665        | 0.82  | 90   | 0.1641          |
| 0.1427        | 0.91  | 100  | 0.1232          |
| 0.1133        | 1.0   | 110  | 0.0969          |
| 0.0833        | 1.09  | 120  | 0.0825          |
| 0.0777        | 1.18  | 130  | 0.1040          |
| 0.4           | 1.27  | 140  | 0.0785          |
| 0.0787        | 1.36  | 150  | 0.0768          |
| 0.076         | 1.45  | 160  | 0.0766          |
| 0.0712        | 1.54  | 170  | 0.0717          |
| 0.0668        | 1.63  | 180  | 0.0696          |
| 0.0668        | 1.72  | 190  | 0.0650          |
| 0.0712        | 1.81  | 200  | 0.0673          |
| 0.0649        | 1.9   | 210  | 0.0688          |
| 0.0624        | 1.99  | 220  | 0.0643          |
| 0.0338        | 2.08  | 230  | 0.0756          |
| 0.0329        | 2.18  | 240  | 0.0983          |
| 0.0312        | 2.27  | 250  | 0.0859          |
| 0.031         | 2.36  | 260  | 0.0770          |
| 0.0371        | 2.45  | 270  | 0.0734          |
| 0.0303        | 2.54  | 280  | 0.0735          |
| 0.0292        | 2.63  | 290  | 0.0740          |
| 0.0352        | 2.72  | 300  | 0.0732          |
| 0.0382        | 2.81  | 310  | 0.0725          |
| 0.033         | 2.9   | 320  | 0.0719          |
| 0.0313        | 2.99  | 330  | 0.0717          |


### Framework versions

- Transformers 4.36.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.14.0