---
license: mit
base_model: microsoft/phi-2
tags:
- generated_from_trainer
model-index:
- name: V0503HMA22H
  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. -->

# V0503HMA22H

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: 0.0674

## 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: 80
- num_epochs: 3
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 1.8681        | 0.09  | 10   | 0.4172          |
| 0.2073        | 0.18  | 20   | 0.1180          |
| 0.1143        | 0.27  | 30   | 0.0880          |
| 0.0961        | 0.36  | 40   | 0.0789          |
| 0.0804        | 0.45  | 50   | 0.0744          |
| 0.0861        | 0.54  | 60   | 0.0761          |
| 0.0787        | 0.63  | 70   | 0.0696          |
| 0.0757        | 0.73  | 80   | 0.0854          |
| 0.0807        | 0.82  | 90   | 0.0686          |
| 0.0806        | 0.91  | 100  | 0.0697          |
| 0.0791        | 1.0   | 110  | 0.0647          |
| 0.0651        | 1.09  | 120  | 0.0673          |
| 0.063         | 1.18  | 130  | 0.0786          |
| 0.0623        | 1.27  | 140  | 0.0629          |
| 0.0638        | 1.36  | 150  | 0.0735          |
| 0.0739        | 1.45  | 160  | 0.0622          |
| 0.0593        | 1.54  | 170  | 0.0639          |
| 0.0675        | 1.63  | 180  | 0.0626          |
| 0.0555        | 1.72  | 190  | 0.0615          |
| 0.068         | 1.81  | 200  | 0.0609          |
| 0.0555        | 1.9   | 210  | 0.0609          |
| 0.0503        | 1.99  | 220  | 0.0582          |
| 0.0366        | 2.08  | 230  | 0.0591          |
| 0.0334        | 2.18  | 240  | 0.0705          |
| 0.0294        | 2.27  | 250  | 0.0722          |
| 0.0296        | 2.36  | 260  | 0.0685          |
| 0.0369        | 2.45  | 270  | 0.0674          |
| 0.0303        | 2.54  | 280  | 0.0682          |
| 0.0286        | 2.63  | 290  | 0.0684          |
| 0.0312        | 2.72  | 300  | 0.0680          |
| 0.0323        | 2.81  | 310  | 0.0675          |
| 0.0304        | 2.9   | 320  | 0.0674          |
| 0.0341        | 2.99  | 330  | 0.0674          |


### Framework versions

- Transformers 4.36.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.18.0
- Tokenizers 0.14.1