---
license: mit
base_model: microsoft/phi-2
tags:
- generated_from_trainer
model-index:
- name: V0507HMA15HV3
  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. -->

# V0507HMA15HV3

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: 0.0511

## 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: 100
- num_epochs: 3
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 1.9302        | 0.09  | 10   | 0.6932          |
| 0.2793        | 0.18  | 20   | 0.1168          |
| 0.1139        | 0.27  | 30   | 0.0926          |
| 0.0965        | 0.36  | 40   | 0.0849          |
| 0.0863        | 0.45  | 50   | 0.0783          |
| 0.0925        | 0.54  | 60   | 0.0724          |
| 0.0781        | 0.63  | 70   | 0.0691          |
| 0.0773        | 0.73  | 80   | 0.0701          |
| 0.077         | 0.82  | 90   | 0.0726          |
| 0.0778        | 0.91  | 100  | 0.0682          |
| 0.0767        | 1.0   | 110  | 0.0652          |
| 0.0604        | 1.09  | 120  | 0.0701          |
| 0.0669        | 1.18  | 130  | 0.0701          |
| 0.0642        | 1.27  | 140  | 0.0682          |
| 0.0648        | 1.36  | 150  | 0.0742          |
| 0.0722        | 1.45  | 160  | 0.0779          |
| 0.0734        | 1.54  | 170  | 0.0690          |
| 0.0741        | 1.63  | 180  | 0.0717          |
| 0.0708        | 1.72  | 190  | 0.0667          |
| 0.0713        | 1.81  | 200  | 0.0723          |
| 0.0594        | 1.9   | 210  | 0.0629          |
| 0.0572        | 1.99  | 220  | 0.0589          |
| 0.0405        | 2.08  | 230  | 0.0625          |
| 0.0339        | 2.18  | 240  | 0.0483          |
| 0.0298        | 2.27  | 250  | 0.0565          |
| 0.022         | 2.36  | 260  | 0.0620          |
| 0.025         | 2.45  | 270  | 0.0513          |
| 0.0259        | 2.54  | 280  | 0.0502          |
| 0.0236        | 2.63  | 290  | 0.0509          |
| 0.0207        | 2.72  | 300  | 0.0506          |
| 0.027         | 2.81  | 310  | 0.0511          |
| 0.0237        | 2.9   | 320  | 0.0511          |
| 0.0238        | 2.99  | 330  | 0.0511          |


### Framework versions

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