---
license: mit
base_model: microsoft/phi-2
tags:
- generated_from_trainer
model-index:
- name: 0503LayerAnalysis31
  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. -->

# 0503LayerAnalysis31

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: 0.0564

## 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 |
|:-------------:|:-----:|:----:|:---------------:|
| 2.066         | 0.09  | 10   | 0.9101          |
| 0.2987        | 0.18  | 20   | 0.1450          |
| 0.1452        | 0.27  | 30   | 0.1357          |
| 0.142         | 0.36  | 40   | 0.1149          |
| 0.1195        | 0.45  | 50   | 0.1107          |
| 0.1109        | 0.54  | 60   | 0.0863          |
| 0.0885        | 0.63  | 70   | 0.0826          |
| 0.081         | 0.73  | 80   | 0.0820          |
| 0.0793        | 0.82  | 90   | 0.0738          |
| 0.0804        | 0.91  | 100  | 0.0770          |
| 0.084         | 1.0   | 110  | 0.0733          |
| 0.078         | 1.09  | 120  | 0.0719          |
| 0.0745        | 1.18  | 130  | 0.0741          |
| 0.0835        | 1.27  | 140  | 0.0727          |
| 0.0738        | 1.36  | 150  | 0.0723          |
| 0.0808        | 1.45  | 160  | 0.0760          |
| 0.0772        | 1.54  | 170  | 0.0687          |
| 0.08          | 1.63  | 180  | 0.0687          |
| 0.0745        | 1.72  | 190  | 0.0663          |
| 0.0742        | 1.81  | 200  | 0.0678          |
| 0.0672        | 1.9   | 210  | 0.0693          |
| 0.0671        | 1.99  | 220  | 0.0643          |
| 0.0571        | 2.08  | 230  | 0.0643          |
| 0.061         | 2.18  | 240  | 0.0639          |
| 0.0611        | 2.27  | 250  | 0.0617          |
| 0.0551        | 2.36  | 260  | 0.0645          |
| 0.0615        | 2.45  | 270  | 0.0599          |
| 0.0552        | 2.54  | 280  | 0.0593          |
| 0.0533        | 2.63  | 290  | 0.0580          |
| 0.0551        | 2.72  | 300  | 0.0573          |
| 0.0592        | 2.81  | 310  | 0.0569          |
| 0.0524        | 2.9   | 320  | 0.0566          |
| 0.0536        | 2.99  | 330  | 0.0564          |


### Framework versions

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