---
license: mit
base_model: microsoft/phi-2
tags:
- generated_from_trainer
model-index:
- name: V0424HMA14
  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. -->

# V0424HMA14

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: 0.0630

## 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 |
|:-------------:|:-----:|:----:|:---------------:|
| 1.8628        | 0.09  | 10   | 0.5176          |
| 0.2396        | 0.18  | 20   | 0.1179          |
| 0.1148        | 0.27  | 30   | 0.0892          |
| 0.0925        | 0.36  | 40   | 0.0789          |
| 0.0835        | 0.45  | 50   | 0.0734          |
| 0.0872        | 0.54  | 60   | 0.0735          |
| 0.0757        | 0.63  | 70   | 0.0710          |
| 0.0728        | 0.73  | 80   | 0.0907          |
| 0.0898        | 0.82  | 90   | 0.0746          |
| 0.0858        | 0.91  | 100  | 0.0731          |
| 0.0852        | 1.0   | 110  | 0.0704          |
| 0.0589        | 1.09  | 120  | 0.0979          |
| 0.0715        | 1.18  | 130  | 0.0719          |
| 0.0714        | 1.27  | 140  | 0.0681          |
| 0.0674        | 1.36  | 150  | 0.0717          |
| 0.0745        | 1.45  | 160  | 0.0693          |
| 0.0691        | 1.54  | 170  | 0.0694          |
| 0.0733        | 1.63  | 180  | 0.0658          |
| 0.0598        | 1.72  | 190  | 0.0676          |
| 0.0683        | 1.81  | 200  | 0.0714          |
| 0.058         | 1.9   | 210  | 0.0663          |
| 0.0565        | 1.99  | 220  | 0.0635          |
| 0.0393        | 2.08  | 230  | 0.0740          |
| 0.0355        | 2.18  | 240  | 0.0752          |
| 0.0386        | 2.27  | 250  | 0.0688          |
| 0.0347        | 2.36  | 260  | 0.0681          |
| 0.0365        | 2.45  | 270  | 0.0675          |
| 0.034         | 2.54  | 280  | 0.0671          |
| 0.0307        | 2.63  | 290  | 0.0637          |
| 0.0326        | 2.72  | 300  | 0.0629          |
| 0.0351        | 2.81  | 310  | 0.0633          |
| 0.0302        | 2.9   | 320  | 0.0631          |
| 0.0337        | 2.99  | 330  | 0.0630          |


### Framework versions

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