---
license: mit
base_model: microsoft/phi-2
tags:
- generated_from_trainer
model-index:
- name: V0309O8
  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. -->

# V0309O8

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: 0.0662

## 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: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 32
- 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 |
|:-------------:|:-----:|:----:|:---------------:|
| 2.284         | 0.09  | 10   | 1.5098          |
| 0.8037        | 0.17  | 20   | 0.1367          |
| 0.1548        | 0.26  | 30   | 0.1059          |
| 0.1284        | 0.34  | 40   | 0.0860          |
| 0.118         | 0.43  | 50   | 0.0858          |
| 0.1038        | 0.51  | 60   | 0.0782          |
| 0.0913        | 0.6   | 70   | 0.0745          |
| 0.0917        | 0.68  | 80   | 0.0725          |
| 0.0829        | 0.77  | 90   | 0.0750          |
| 0.0821        | 0.85  | 100  | 0.0754          |
| 0.0865        | 0.94  | 110  | 0.0711          |
| 0.0875        | 1.02  | 120  | 0.0761          |
| 0.084         | 1.11  | 130  | 0.0742          |
| 0.0785        | 1.19  | 140  | 0.0672          |
| 0.0753        | 1.28  | 150  | 0.0681          |
| 0.0762        | 1.37  | 160  | 0.0755          |
| 0.0732        | 1.45  | 170  | 0.0685          |
| 0.0715        | 1.54  | 180  | 0.0713          |
| 0.0709        | 1.62  | 190  | 0.0697          |
| 0.0713        | 1.71  | 200  | 0.0680          |
| 0.0753        | 1.79  | 210  | 0.0682          |
| 0.068         | 1.88  | 220  | 0.0695          |
| 0.066         | 1.96  | 230  | 0.0652          |
| 0.0696        | 2.05  | 240  | 0.0668          |
| 0.062         | 2.13  | 250  | 0.0691          |
| 0.0618        | 2.22  | 260  | 0.0726          |
| 0.0599        | 2.3   | 270  | 0.0746          |
| 0.0661        | 2.39  | 280  | 0.0707          |
| 0.0635        | 2.47  | 290  | 0.0686          |
| 0.0627        | 2.56  | 300  | 0.0663          |
| 0.0661        | 2.65  | 310  | 0.0658          |
| 0.0568        | 2.73  | 320  | 0.0656          |
| 0.06          | 2.82  | 330  | 0.0660          |
| 0.0591        | 2.9   | 340  | 0.0664          |
| 0.062         | 2.99  | 350  | 0.0662          |


### Framework versions

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