---
license: mit
base_model: microsoft/Phi-3-mini-4k-instruct
tags:
- generated_from_trainer
model-index:
- name: Phi0503HMA11
  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. -->

# Phi0503HMA11

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: 0.0603

## 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: 100
- num_epochs: 3
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 4.2519        | 0.09  | 10   | 1.0412          |
| 0.9414        | 0.18  | 20   | 1.5076          |
| 0.5581        | 0.27  | 30   | 0.2855          |
| 0.266         | 0.36  | 40   | 0.2243          |
| 0.293         | 0.45  | 50   | 0.2186          |
| 0.2172        | 0.54  | 60   | 0.2198          |
| 0.2713        | 0.63  | 70   | 0.5296          |
| 0.2377        | 0.73  | 80   | 0.1799          |
| 0.1724        | 0.82  | 90   | 0.1653          |
| 0.1631        | 0.91  | 100  | 0.1642          |
| 0.1646        | 1.0   | 110  | 3.8048          |
| 0.8934        | 1.09  | 120  | 0.1709          |
| 0.4257        | 1.18  | 130  | 2.8704          |
| 1.0083        | 1.27  | 140  | 0.1904          |
| 0.9961        | 1.36  | 150  | 1.9067          |
| 1.3818        | 1.45  | 160  | 0.5005          |
| 0.5145        | 1.54  | 170  | 0.4971          |
| 0.3049        | 1.63  | 180  | 0.2280          |
| 0.2023        | 1.72  | 190  | 0.1794          |
| 0.1949        | 1.81  | 200  | 0.1813          |
| 0.1911        | 1.9   | 210  | 0.1823          |
| 0.1758        | 1.99  | 220  | 0.1767          |
| 0.1706        | 2.08  | 230  | 0.1721          |
| 0.1658        | 2.18  | 240  | 0.1620          |
| 0.1529        | 2.27  | 250  | 0.1515          |
| 0.1319        | 2.36  | 260  | 0.1138          |
| 0.0947        | 2.45  | 270  | 0.0714          |
| 0.068         | 2.54  | 280  | 0.0690          |
| 0.0705        | 2.63  | 290  | 0.0642          |
| 0.0653        | 2.72  | 300  | 0.0624          |
| 0.0634        | 2.81  | 310  | 0.0611          |
| 0.0632        | 2.9   | 320  | 0.0613          |
| 0.0634        | 2.99  | 330  | 0.0603          |


### Framework versions

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