---
license: mit
base_model: microsoft/phi-2
tags:
- generated_from_trainer
model-index:
- name: V0417MAD1
  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. -->

# V0417MAD1

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: 0.0615

## 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 |
|:-------------:|:-----:|:----:|:---------------:|
| 2.4934        | 0.09  | 10   | 1.9339          |
| 1.5303        | 0.18  | 20   | 0.6622          |
| 0.3481        | 0.27  | 30   | 0.1084          |
| 0.1158        | 0.36  | 40   | 0.0888          |
| 0.092         | 0.45  | 50   | 0.0768          |
| 0.0876        | 0.54  | 60   | 0.0724          |
| 0.0811        | 0.63  | 70   | 0.0727          |
| 0.0778        | 0.73  | 80   | 0.0699          |
| 0.0798        | 0.82  | 90   | 0.0656          |
| 0.0783        | 0.91  | 100  | 0.0647          |
| 0.0754        | 1.0   | 110  | 0.0638          |
| 0.0668        | 1.09  | 120  | 0.0635          |
| 0.0663        | 1.18  | 130  | 0.0629          |
| 0.064         | 1.27  | 140  | 0.0635          |
| 0.0592        | 1.36  | 150  | 0.0626          |
| 0.0719        | 1.45  | 160  | 0.0626          |
| 0.064         | 1.54  | 170  | 0.0602          |
| 0.0669        | 1.63  | 180  | 0.0613          |
| 0.0617        | 1.72  | 190  | 0.0621          |
| 0.0669        | 1.81  | 200  | 0.0594          |
| 0.0572        | 1.9   | 210  | 0.0596          |
| 0.0588        | 1.99  | 220  | 0.0607          |
| 0.051         | 2.08  | 230  | 0.0612          |
| 0.0559        | 2.18  | 240  | 0.0602          |
| 0.0529        | 2.27  | 250  | 0.0597          |
| 0.054         | 2.36  | 260  | 0.0601          |
| 0.0535        | 2.45  | 270  | 0.0604          |
| 0.0511        | 2.54  | 280  | 0.0601          |
| 0.0486        | 2.63  | 290  | 0.0614          |
| 0.053         | 2.72  | 300  | 0.0611          |
| 0.0573        | 2.81  | 310  | 0.0614          |
| 0.0504        | 2.9   | 320  | 0.0614          |
| 0.0541        | 2.99  | 330  | 0.0615          |


### Framework versions

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