---
license: mit
base_model: microsoft/phi-2
tags:
- generated_from_trainer
model-index:
- name: 0503LayerAnalysis15
  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. -->

# 0503LayerAnalysis15

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: 0.0459

## 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 |
|:-------------:|:-----:|:----:|:---------------:|
| 2.1114        | 0.09  | 10   | 0.8833          |
| 0.2911        | 0.18  | 20   | 0.1389          |
| 0.1294        | 0.27  | 30   | 0.1053          |
| 0.1066        | 0.36  | 40   | 0.0921          |
| 0.09          | 0.45  | 50   | 0.0844          |
| 0.0956        | 0.54  | 60   | 0.0809          |
| 0.0841        | 0.63  | 70   | 0.0762          |
| 0.0786        | 0.73  | 80   | 0.0795          |
| 0.0838        | 0.82  | 90   | 0.0764          |
| 0.0843        | 0.91  | 100  | 0.0715          |
| 0.0848        | 1.0   | 110  | 0.0689          |
| 0.0709        | 1.09  | 120  | 0.0670          |
| 0.0718        | 1.18  | 130  | 0.0688          |
| 0.0713        | 1.27  | 140  | 0.0704          |
| 0.0671        | 1.36  | 150  | 0.0647          |
| 0.0714        | 1.45  | 160  | 0.0624          |
| 0.0567        | 1.54  | 170  | 0.0554          |
| 0.0585        | 1.63  | 180  | 0.0480          |
| 0.0535        | 1.72  | 190  | 0.0524          |
| 0.0577        | 1.81  | 200  | 0.0516          |
| 0.0455        | 1.9   | 210  | 0.0507          |
| 0.0482        | 1.99  | 220  | 0.0494          |
| 0.0418        | 2.08  | 230  | 0.0476          |
| 0.0409        | 2.18  | 240  | 0.0493          |
| 0.0426        | 2.27  | 250  | 0.0468          |
| 0.0449        | 2.36  | 260  | 0.0482          |
| 0.0395        | 2.45  | 270  | 0.0489          |
| 0.0419        | 2.54  | 280  | 0.0488          |
| 0.0374        | 2.63  | 290  | 0.0467          |
| 0.0371        | 2.72  | 300  | 0.0464          |
| 0.0442        | 2.81  | 310  | 0.0460          |
| 0.0367        | 2.9   | 320  | 0.0459          |
| 0.0357        | 2.99  | 330  | 0.0459          |


### Framework versions

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