---
license: mit
base_model: microsoft/phi-2
tags:
- generated_from_trainer
model-index:
- name: V0424HMA13
  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. -->

# V0424HMA13

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: 0.0488

## 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: 100
- num_epochs: 3
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 1.6572        | 0.09  | 10   | 0.3872          |
| 0.1981        | 0.18  | 20   | 0.1144          |
| 0.1118        | 0.27  | 30   | 0.0984          |
| 0.0959        | 0.36  | 40   | 0.0833          |
| 0.0831        | 0.45  | 50   | 0.0732          |
| 0.0945        | 0.54  | 60   | 0.0784          |
| 0.0878        | 0.63  | 70   | 0.0747          |
| 0.0786        | 0.73  | 80   | 0.0775          |
| 0.0818        | 0.82  | 90   | 0.0726          |
| 0.0794        | 0.91  | 100  | 0.0704          |
| 0.0775        | 1.0   | 110  | 0.0680          |
| 0.0616        | 1.09  | 120  | 0.0699          |
| 0.0599        | 1.18  | 130  | 0.0760          |
| 0.0732        | 1.27  | 140  | 0.0713          |
| 0.0631        | 1.36  | 150  | 0.0712          |
| 0.0722        | 1.45  | 160  | 0.0682          |
| 0.0654        | 1.54  | 170  | 0.0810          |
| 0.0808        | 1.63  | 180  | 0.0714          |
| 0.1626        | 1.72  | 190  | 0.0920          |
| 1.8023        | 1.81  | 200  | 0.4369          |
| 0.1372        | 1.9   | 210  | 0.0750          |
| 0.0738        | 1.99  | 220  | 0.0726          |
| 0.0475        | 2.08  | 230  | 0.0786          |
| 0.0444        | 2.18  | 240  | 0.0704          |
| 0.0416        | 2.27  | 250  | 0.0661          |
| 0.0371        | 2.36  | 260  | 0.0608          |
| 0.0662        | 2.45  | 270  | 0.0548          |
| 0.0309        | 2.54  | 280  | 0.0504          |
| 0.0218        | 2.63  | 290  | 0.0492          |
| 0.0228        | 2.72  | 300  | 0.0494          |
| 0.0308        | 2.81  | 310  | 0.0490          |
| 0.0263        | 2.9   | 320  | 0.0490          |
| 0.0232        | 2.99  | 330  | 0.0488          |


### Framework versions

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