---
license: mit
base_model: microsoft/phi-2
tags:
- generated_from_trainer
model-index:
- name: V0417MADP8
  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. -->

# V0417MADP8

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: 0.0671

## 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 |
|:-------------:|:-----:|:----:|:---------------:|
| 5.4354        | 0.09  | 10   | 2.6496          |
| 4.1578        | 0.18  | 20   | 1.5199          |
| 2.23          | 0.27  | 30   | 0.1826          |
| 0.884         | 0.36  | 40   | 0.1456          |
| 0.1889        | 0.45  | 50   | 0.1308          |
| 0.1501        | 0.54  | 60   | 0.1216          |
| 0.1389        | 0.63  | 70   | 0.1104          |
| 0.1173        | 0.73  | 80   | 0.1018          |
| 0.1086        | 0.82  | 90   | 0.0899          |
| 0.0966        | 0.91  | 100  | 0.0814          |
| 0.098         | 1.0   | 110  | 0.0814          |
| 0.093         | 1.09  | 120  | 0.0846          |
| 0.093         | 1.18  | 130  | 0.0811          |
| 0.091         | 1.27  | 140  | 0.0782          |
| 0.0858        | 1.36  | 150  | 0.0767          |
| 0.0853        | 1.45  | 160  | 0.0817          |
| 0.089         | 1.54  | 170  | 0.0804          |
| 0.0854        | 1.63  | 180  | 0.0751          |
| 0.0841        | 1.72  | 190  | 0.0766          |
| 0.0843        | 1.81  | 200  | 0.0722          |
| 0.0763        | 1.9   | 210  | 0.0706          |
| 0.0778        | 1.99  | 220  | 0.0707          |
| 0.0712        | 2.08  | 230  | 0.0697          |
| 0.066         | 2.18  | 240  | 0.0691          |
| 0.0687        | 2.27  | 250  | 0.0711          |
| 0.0714        | 2.36  | 260  | 0.0695          |
| 0.0685        | 2.45  | 270  | 0.0692          |
| 0.0648        | 2.54  | 280  | 0.0688          |
| 0.0645        | 2.63  | 290  | 0.0675          |
| 0.0668        | 2.72  | 300  | 0.0670          |
| 0.0665        | 2.81  | 310  | 0.0672          |
| 0.0628        | 2.9   | 320  | 0.0671          |
| 0.0736        | 2.99  | 330  | 0.0671          |


### Framework versions

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