---
license: mit
base_model: microsoft/phi-2
tags:
- generated_from_trainer
model-index:
- name: V0320MP3
  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. -->

# V0320MP3

This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1215

## 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: 20
- num_epochs: 3
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 2.5643        | 0.09  | 10   | 2.3573          |
| 2.1608        | 0.18  | 20   | 1.8527          |
| 1.6246        | 0.27  | 30   | 1.2651          |
| 1.1395        | 0.36  | 40   | 0.8357          |
| 0.7126        | 0.45  | 50   | 0.3825          |
| 0.3575        | 0.54  | 60   | 0.1921          |
| 0.2196        | 0.63  | 70   | 0.1514          |
| 0.181         | 0.73  | 80   | 0.1415          |
| 0.1696        | 0.82  | 90   | 0.1371          |
| 0.1653        | 0.91  | 100  | 0.1335          |
| 0.1636        | 1.0   | 110  | 0.1309          |
| 0.1508        | 1.09  | 120  | 0.1295          |
| 0.1551        | 1.18  | 130  | 0.1285          |
| 0.1516        | 1.27  | 140  | 0.1276          |
| 0.1569        | 1.36  | 150  | 0.1266          |
| 0.1464        | 1.45  | 160  | 0.1261          |
| 0.1428        | 1.54  | 170  | 0.1258          |
| 0.1502        | 1.63  | 180  | 0.1245          |
| 0.1417        | 1.72  | 190  | 0.1242          |
| 0.1392        | 1.81  | 200  | 0.1237          |
| 0.1434        | 1.9   | 210  | 0.1231          |
| 0.1433        | 1.99  | 220  | 0.1227          |
| 0.1432        | 2.08  | 230  | 0.1225          |
| 0.1397        | 2.18  | 240  | 0.1222          |
| 0.1395        | 2.27  | 250  | 0.1220          |
| 0.1415        | 2.36  | 260  | 0.1218          |
| 0.1401        | 2.45  | 270  | 0.1215          |
| 0.1372        | 2.54  | 280  | 0.1216          |
| 0.1366        | 2.63  | 290  | 0.1215          |
| 0.1405        | 2.72  | 300  | 0.1215          |
| 0.1431        | 2.81  | 310  | 0.1213          |
| 0.1384        | 2.9   | 320  | 0.1215          |
| 0.1415        | 2.99  | 330  | 0.1215          |


### Framework versions

- Transformers 4.36.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.14.1