---
license: mit
base_model: microsoft/phi-2
tags:
- generated_from_trainer
model-index:
- name: V0417MADP4
  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. -->

# V0417MADP4

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: 0.1454

## 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 |
|:-------------:|:-----:|:----:|:---------------:|
| 8.3437        | 0.09  | 10   | 2.9727          |
| 6.7169        | 0.18  | 20   | 2.7571          |
| 4.7246        | 0.27  | 30   | 2.3872          |
| 2.7752        | 0.36  | 40   | 1.7401          |
| 1.361         | 0.45  | 50   | 1.0587          |
| 0.6269        | 0.54  | 60   | 0.6595          |
| 0.333         | 0.63  | 70   | 0.3442          |
| 0.2172        | 0.73  | 80   | 0.2248          |
| 0.1846        | 0.82  | 90   | 0.2079          |
| 0.1761        | 0.91  | 100  | 0.1780          |
| 0.1761        | 1.0   | 110  | 0.1788          |
| 0.171         | 1.09  | 120  | 0.1687          |
| 0.161         | 1.18  | 130  | 0.1565          |
| 0.1566        | 1.27  | 140  | 0.1558          |
| 0.2021        | 1.36  | 150  | 0.1842          |
| 0.1681        | 1.45  | 160  | 0.1545          |
| 0.1668        | 1.54  | 170  | 0.1516          |
| 0.1642        | 1.63  | 180  | 0.1501          |
| 0.1685        | 1.72  | 190  | 0.1599          |
| 0.1685        | 1.81  | 200  | 0.1543          |
| 0.1643        | 1.9   | 210  | 0.1679          |
| 0.1608        | 1.99  | 220  | 0.1575          |
| 0.1593        | 2.08  | 230  | 0.1475          |
| 0.1539        | 2.18  | 240  | 0.1490          |
| 0.1511        | 2.27  | 250  | 0.1463          |
| 0.1543        | 2.36  | 260  | 0.1468          |
| 0.1534        | 2.45  | 270  | 0.1477          |
| 0.1524        | 2.54  | 280  | 0.1462          |
| 0.1513        | 2.63  | 290  | 0.1457          |
| 0.153         | 2.72  | 300  | 0.1457          |
| 0.1516        | 2.81  | 310  | 0.1454          |
| 0.153         | 2.9   | 320  | 0.1454          |
| 0.1535        | 2.99  | 330  | 0.1454          |


### Framework versions

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