---
license: mit
base_model: microsoft/phi-2
tags:
- generated_from_trainer
model-index:
- name: V0424HMA2
  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. -->

# V0424HMA2

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: 0.0500

## 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: 80
- num_epochs: 3
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 1.9738        | 0.09  | 10   | 0.6274          |
| 0.2393        | 0.18  | 20   | 0.1219          |
| 0.1178        | 0.27  | 30   | 0.0941          |
| 0.0994        | 0.36  | 40   | 0.0758          |
| 0.0776        | 0.45  | 50   | 0.0772          |
| 0.0858        | 0.54  | 60   | 0.0728          |
| 0.0808        | 0.63  | 70   | 0.0750          |
| 0.0838        | 0.73  | 80   | 0.0829          |
| 0.0885        | 0.82  | 90   | 0.0693          |
| 0.0925        | 0.91  | 100  | 0.0701          |
| 0.0917        | 1.0   | 110  | 0.0651          |
| 0.0645        | 1.09  | 120  | 0.0766          |
| 0.0767        | 1.18  | 130  | 0.0721          |
| 0.0695        | 1.27  | 140  | 0.0660          |
| 0.0653        | 1.36  | 150  | 0.0686          |
| 0.0633        | 1.45  | 160  | 0.0672          |
| 0.0614        | 1.54  | 170  | 0.0607          |
| 0.0643        | 1.63  | 180  | 0.0608          |
| 0.0579        | 1.72  | 190  | 0.0618          |
| 0.0658        | 1.81  | 200  | 0.0599          |
| 0.0503        | 1.9   | 210  | 0.0628          |
| 0.0514        | 1.99  | 220  | 0.0590          |
| 0.0358        | 2.08  | 230  | 0.0615          |
| 0.0306        | 2.18  | 240  | 0.0660          |
| 0.0262        | 2.27  | 250  | 0.0593          |
| 0.0249        | 2.36  | 260  | 0.0555          |
| 0.025         | 2.45  | 270  | 0.0535          |
| 0.0233        | 2.54  | 280  | 0.0512          |
| 0.0196        | 2.63  | 290  | 0.0508          |
| 0.0204        | 2.72  | 300  | 0.0503          |
| 0.0226        | 2.81  | 310  | 0.0499          |
| 0.0199        | 2.9   | 320  | 0.0499          |
| 0.0189        | 2.99  | 330  | 0.0500          |


### Framework versions

- Transformers 4.36.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.18.0
- Tokenizers 0.14.1