---
license: mit
base_model: microsoft/phi-2
tags:
- generated_from_trainer
model-index:
- name: V0415MA2
  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. -->

# V0415MA2

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: 0.0650

## 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 |
|:-------------:|:-----:|:----:|:---------------:|
| 2.2555        | 0.09  | 10   | 1.0684          |
| 0.4718        | 0.18  | 20   | 0.1179          |
| 0.1156        | 0.27  | 30   | 0.0892          |
| 0.0957        | 0.36  | 40   | 0.0782          |
| 0.0806        | 0.45  | 50   | 0.0723          |
| 0.0828        | 0.54  | 60   | 0.0704          |
| 0.0745        | 0.63  | 70   | 0.0687          |
| 0.0737        | 0.73  | 80   | 0.0682          |
| 0.0753        | 0.82  | 90   | 0.0633          |
| 0.0729        | 0.91  | 100  | 0.0590          |
| 0.0679        | 1.0   | 110  | 0.0632          |
| 0.057         | 1.09  | 120  | 0.0626          |
| 0.0612        | 1.18  | 130  | 0.0616          |
| 0.0559        | 1.27  | 140  | 0.0655          |
| 0.0509        | 1.36  | 150  | 0.0605          |
| 0.0591        | 1.45  | 160  | 0.0594          |
| 0.0563        | 1.54  | 170  | 0.0590          |
| 0.0543        | 1.63  | 180  | 0.0561          |
| 0.0503        | 1.72  | 190  | 0.0592          |
| 0.0593        | 1.81  | 200  | 0.0565          |
| 0.048         | 1.9   | 210  | 0.0579          |
| 0.047         | 1.99  | 220  | 0.0633          |
| 0.0361        | 2.08  | 230  | 0.0606          |
| 0.0366        | 2.18  | 240  | 0.0635          |
| 0.0314        | 2.27  | 250  | 0.0656          |
| 0.031         | 2.36  | 260  | 0.0672          |
| 0.0348        | 2.45  | 270  | 0.0679          |
| 0.0317        | 2.54  | 280  | 0.0671          |
| 0.0299        | 2.63  | 290  | 0.0665          |
| 0.0361        | 2.72  | 300  | 0.0655          |
| 0.0351        | 2.81  | 310  | 0.0651          |
| 0.0334        | 2.9   | 320  | 0.0649          |
| 0.0371        | 2.99  | 330  | 0.0650          |


### Framework versions

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