---
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: 0.1516

## 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 |
|:-------------:|:-----:|:----:|:---------------:|
| 4.8564        | 0.09  | 10   | 1.3605          |
| 0.5497        | 0.18  | 20   | 0.2614          |
| 0.2903        | 0.27  | 30   | 0.2683          |
| 0.2461        | 0.36  | 40   | 0.2304          |
| 0.2221        | 0.45  | 50   | 0.2068          |
| 0.1477        | 0.54  | 60   | 0.1427          |
| 0.1316        | 0.63  | 70   | 0.1772          |
| 0.1198        | 0.73  | 80   | 0.0857          |
| 0.0819        | 0.82  | 90   | 0.0997          |
| 0.0985        | 0.91  | 100  | 0.0834          |
| 3.0334        | 1.0   | 110  | 3.2368          |
| 1.8691        | 1.09  | 120  | 0.8954          |
| 0.565         | 1.18  | 130  | 0.3844          |
| 0.4346        | 1.27  | 140  | 0.4378          |
| 0.3277        | 1.36  | 150  | 0.2849          |
| 0.2888        | 1.45  | 160  | 0.2455          |
| 0.2336        | 1.54  | 170  | 0.2010          |
| 0.2016        | 1.63  | 180  | 0.1956          |
| 0.1855        | 1.72  | 190  | 0.1804          |
| 0.1981        | 1.81  | 200  | 0.1913          |
| 0.1829        | 1.9   | 210  | 0.1781          |
| 0.1808        | 1.99  | 220  | 0.1771          |
| 0.177         | 2.08  | 230  | 0.1778          |
| 0.1753        | 2.18  | 240  | 0.1702          |
| 0.1685        | 2.27  | 250  | 0.1727          |
| 0.1671        | 2.36  | 260  | 0.1654          |
| 0.1594        | 2.45  | 270  | 0.1603          |
| 0.1581        | 2.54  | 280  | 0.1569          |
| 0.1565        | 2.63  | 290  | 0.1536          |
| 0.1546        | 2.72  | 300  | 0.1520          |
| 0.1582        | 2.81  | 310  | 0.1518          |
| 0.1512        | 2.9   | 320  | 0.1516          |
| 0.1521        | 2.99  | 330  | 0.1516          |


### Framework versions

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