---
base_model: microsoft/phi-2
tags:
- generated_from_trainer
model-index:
- name: V0422MADP4A
  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. -->

# V0422MADP4A

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: 0.1470

## 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: 60
- num_epochs: 3
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 8.3481        | 0.09  | 10   | 2.9143          |
| 3.8072        | 0.18  | 20   | 1.5704          |
| 0.76          | 0.27  | 30   | 0.5846          |
| 0.2415        | 0.36  | 40   | 0.2578          |
| 0.1786        | 0.45  | 50   | 0.2259          |
| 0.1727        | 0.54  | 60   | 0.2076          |
| 0.1778        | 0.63  | 70   | 0.2727          |
| 0.1825        | 0.73  | 80   | 0.1969          |
| 0.1656        | 0.82  | 90   | 0.2027          |
| 0.1729        | 0.91  | 100  | 0.2099          |
| 0.1734        | 1.0   | 110  | 0.1896          |
| 0.1721        | 1.09  | 120  | 0.2049          |
| 0.1757        | 1.18  | 130  | 0.2057          |
| 0.1763        | 1.27  | 140  | 0.2984          |
| 0.1851        | 1.36  | 150  | 0.2664          |
| 0.1766        | 1.45  | 160  | 0.2176          |
| 0.1784        | 1.54  | 170  | 0.1993          |
| 0.1758        | 1.63  | 180  | 0.1910          |
| 0.1807        | 1.72  | 190  | 0.2191          |
| 0.1734        | 1.81  | 200  | 0.1908          |
| 0.1775        | 1.9   | 210  | 0.1796          |
| 0.169         | 1.99  | 220  | 0.1789          |
| 0.1703        | 2.08  | 230  | 0.1752          |
| 0.158         | 2.18  | 240  | 0.1591          |
| 0.1553        | 2.27  | 250  | 0.1484          |
| 0.1532        | 2.36  | 260  | 0.1492          |
| 0.1518        | 2.45  | 270  | 0.1495          |
| 0.1488        | 2.54  | 280  | 0.1503          |
| 0.1491        | 2.63  | 290  | 0.1481          |
| 0.1498        | 2.72  | 300  | 0.1472          |
| 0.1498        | 2.81  | 310  | 0.1469          |
| 0.1511        | 2.9   | 320  | 0.1470          |
| 0.1516        | 2.99  | 330  | 0.1470          |


### Framework versions

- Transformers 4.36.0.dev0
- Pytorch 2.2.2+cu121
- Datasets 2.18.0
- Tokenizers 0.14.1