---
license: mit
base_model: microsoft/phi-2
tags:
- generated_from_trainer
model-index:
- name: Va0309B1
  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. -->

# Va0309B1

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: 0.0706

## 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: 3e-05
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 32
- 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: 20
- num_epochs: 3
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 2.7676        | 0.09  | 10   | 2.7256          |
| 2.6283        | 0.17  | 20   | 2.4272          |
| 2.2188        | 0.26  | 30   | 1.8633          |
| 1.6664        | 0.34  | 40   | 1.3024          |
| 1.1333        | 0.43  | 50   | 0.7344          |
| 0.5536        | 0.51  | 60   | 0.2242          |
| 0.1952        | 0.6   | 70   | 0.1010          |
| 0.1271        | 0.68  | 80   | 0.0909          |
| 0.1187        | 0.77  | 90   | 0.0872          |
| 0.1194        | 0.85  | 100  | 0.0851          |
| 0.1135        | 0.94  | 110  | 0.0831          |
| 0.1119        | 1.02  | 120  | 0.0805          |
| 0.1132        | 1.11  | 130  | 0.0794          |
| 0.1036        | 1.19  | 140  | 0.0790          |
| 0.1083        | 1.28  | 150  | 0.0780          |
| 0.1063        | 1.37  | 160  | 0.0765          |
| 0.1087        | 1.45  | 170  | 0.0756          |
| 0.0969        | 1.54  | 180  | 0.0740          |
| 0.1024        | 1.62  | 190  | 0.0738          |
| 0.1044        | 1.71  | 200  | 0.0727          |
| 0.1013        | 1.79  | 210  | 0.0728          |
| 0.0985        | 1.88  | 220  | 0.0724          |
| 0.0961        | 1.96  | 230  | 0.0714          |
| 0.1015        | 2.05  | 240  | 0.0717          |
| 0.096         | 2.13  | 250  | 0.0710          |
| 0.0935        | 2.22  | 260  | 0.0709          |
| 0.0913        | 2.3   | 270  | 0.0709          |
| 0.1026        | 2.39  | 280  | 0.0706          |
| 0.0965        | 2.47  | 290  | 0.0705          |
| 0.1029        | 2.56  | 300  | 0.0710          |
| 0.0961        | 2.65  | 310  | 0.0702          |
| 0.0991        | 2.73  | 320  | 0.0704          |
| 0.0985        | 2.82  | 330  | 0.0705          |
| 0.0929        | 2.9   | 340  | 0.0703          |
| 0.0948        | 2.99  | 350  | 0.0706          |


### Framework versions

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