---
base_model: microsoft/phi-2
tags:
- generated_from_trainer
model-index:
- name: V0422MADP6
  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. -->

# V0422MADP6

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: 0.0611

## 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 |
|:-------------:|:-----:|:----:|:---------------:|
| 1.9237        | 0.09  | 10   | 0.5636          |
| 0.2396        | 0.18  | 20   | 0.1140          |
| 0.1129        | 0.27  | 30   | 0.0962          |
| 0.1009        | 0.36  | 40   | 0.0912          |
| 0.0866        | 0.45  | 50   | 0.0752          |
| 0.0838        | 0.54  | 60   | 0.0716          |
| 0.0761        | 0.63  | 70   | 0.0737          |
| 0.0775        | 0.73  | 80   | 0.0766          |
| 0.0789        | 0.82  | 90   | 0.0711          |
| 0.0799        | 0.91  | 100  | 0.0681          |
| 0.0754        | 1.0   | 110  | 0.0662          |
| 0.0621        | 1.09  | 120  | 0.0666          |
| 0.0665        | 1.18  | 130  | 0.0840          |
| 0.0693        | 1.27  | 140  | 0.0619          |
| 0.0609        | 1.36  | 150  | 0.0647          |
| 0.062         | 1.45  | 160  | 0.0601          |
| 0.0582        | 1.54  | 170  | 0.0578          |
| 0.0634        | 1.63  | 180  | 0.0575          |
| 0.0579        | 1.72  | 190  | 0.0621          |
| 0.065         | 1.81  | 200  | 0.0574          |
| 0.0522        | 1.9   | 210  | 0.0624          |
| 0.0517        | 1.99  | 220  | 0.0585          |
| 0.0403        | 2.08  | 230  | 0.0630          |
| 0.0433        | 2.18  | 240  | 0.0628          |
| 0.0398        | 2.27  | 250  | 0.0627          |
| 0.0379        | 2.36  | 260  | 0.0656          |
| 0.0431        | 2.45  | 270  | 0.0629          |
| 0.0387        | 2.54  | 280  | 0.0643          |
| 0.0359        | 2.63  | 290  | 0.0633          |
| 0.0419        | 2.72  | 300  | 0.0628          |
| 0.0438        | 2.81  | 310  | 0.0615          |
| 0.0398        | 2.9   | 320  | 0.0612          |
| 0.0432        | 2.99  | 330  | 0.0611          |


### Framework versions

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