---
license: mit
base_model: microsoft/phi-2
tags:
- generated_from_trainer
model-index:
- name: V0415MA3
  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. -->

# V0415MA3

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: 0.0621

## 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 |
|:-------------:|:-----:|:----:|:---------------:|
| 2.2761        | 0.09  | 10   | 1.1235          |
| 0.5089        | 0.18  | 20   | 0.1178          |
| 0.1173        | 0.27  | 30   | 0.0926          |
| 0.0967        | 0.36  | 40   | 0.0792          |
| 0.0823        | 0.45  | 50   | 0.0729          |
| 0.084         | 0.54  | 60   | 0.0707          |
| 0.0741        | 0.63  | 70   | 0.0692          |
| 0.0736        | 0.73  | 80   | 0.0684          |
| 0.0768        | 0.82  | 90   | 0.0616          |
| 0.0742        | 0.91  | 100  | 0.0613          |
| 0.0691        | 1.0   | 110  | 0.0641          |
| 0.0586        | 1.09  | 120  | 0.0612          |
| 0.0597        | 1.18  | 130  | 0.0597          |
| 0.0543        | 1.27  | 140  | 0.0657          |
| 0.0522        | 1.36  | 150  | 0.0591          |
| 0.0591        | 1.45  | 160  | 0.0586          |
| 0.0586        | 1.54  | 170  | 0.0585          |
| 0.0571        | 1.63  | 180  | 0.0565          |
| 0.0513        | 1.72  | 190  | 0.0597          |
| 0.0603        | 1.81  | 200  | 0.0564          |
| 0.0479        | 1.9   | 210  | 0.0575          |
| 0.0486        | 1.99  | 220  | 0.0623          |
| 0.0363        | 2.08  | 230  | 0.0591          |
| 0.038         | 2.18  | 240  | 0.0613          |
| 0.0347        | 2.27  | 250  | 0.0626          |
| 0.0323        | 2.36  | 260  | 0.0640          |
| 0.0372        | 2.45  | 270  | 0.0650          |
| 0.0338        | 2.54  | 280  | 0.0643          |
| 0.0326        | 2.63  | 290  | 0.0638          |
| 0.0371        | 2.72  | 300  | 0.0627          |
| 0.0384        | 2.81  | 310  | 0.0623          |
| 0.0355        | 2.9   | 320  | 0.0622          |
| 0.0391        | 2.99  | 330  | 0.0621          |


### Framework versions

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