---
license: mit
base_model: microsoft/phi-2
tags:
- generated_from_trainer
model-index:
- name: V0422MADP5B
  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. -->

# V0422MADP5B

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: 0.1503

## 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 |
|:-------------:|:-----:|:----:|:---------------:|
| 6.0222        | 0.09  | 10   | 2.4466          |
| 4.7074        | 0.18  | 20   | 2.0778          |
| 2.0523        | 0.27  | 30   | 0.9665          |
| 0.5575        | 0.36  | 40   | 0.3469          |
| 0.2173        | 0.45  | 50   | 0.2234          |
| 0.1799        | 0.54  | 60   | 0.2376          |
| 0.1697        | 0.63  | 70   | 0.1977          |
| 0.1625        | 0.73  | 80   | 0.1701          |
| 0.1569        | 0.82  | 90   | 0.1676          |
| 0.1575        | 0.91  | 100  | 0.1651          |
| 0.1632        | 1.0   | 110  | 0.1574          |
| 0.1565        | 1.09  | 120  | 0.1549          |
| 0.1551        | 1.18  | 130  | 0.1690          |
| 0.1574        | 1.27  | 140  | 0.1523          |
| 0.1557        | 1.36  | 150  | 0.1518          |
| 0.1512        | 1.45  | 160  | 0.1524          |
| 0.1615        | 1.54  | 170  | 0.1704          |
| 0.1651        | 1.63  | 180  | 0.1822          |
| 0.1648        | 1.72  | 190  | 0.1652          |
| 0.1567        | 1.81  | 200  | 0.1557          |
| 0.1549        | 1.9   | 210  | 0.1532          |
| 0.152         | 1.99  | 220  | 0.1554          |
| 0.1532        | 2.08  | 230  | 0.1515          |
| 0.1486        | 2.18  | 240  | 0.1529          |
| 0.149         | 2.27  | 250  | 0.1527          |
| 0.1493        | 2.36  | 260  | 0.1515          |
| 0.1507        | 2.45  | 270  | 0.1528          |
| 0.1496        | 2.54  | 280  | 0.1545          |
| 0.1507        | 2.63  | 290  | 0.1516          |
| 0.1481        | 2.72  | 300  | 0.1505          |
| 0.1488        | 2.81  | 310  | 0.1502          |
| 0.1502        | 2.9   | 320  | 0.1502          |
| 0.1522        | 2.99  | 330  | 0.1503          |


### Framework versions

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