---
license: mit
base_model: microsoft/phi-2
tags:
- generated_from_trainer
model-index:
- name: 0504LayerAnalysis0
  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. -->

# 0504LayerAnalysis0

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: 0.0700

## 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 |
|:-------------:|:-----:|:----:|:---------------:|
| 2.6808        | 0.09  | 10   | 2.3991          |
| 2.2562        | 0.18  | 20   | 1.8687          |
| 1.6693        | 0.27  | 30   | 1.1433          |
| 0.7779        | 0.36  | 40   | 0.1904          |
| 0.1939        | 0.45  | 50   | 0.1305          |
| 0.1477        | 0.54  | 60   | 0.1201          |
| 0.1238        | 0.63  | 70   | 0.1051          |
| 0.1177        | 0.73  | 80   | 0.0943          |
| 0.1079        | 0.82  | 90   | 0.0884          |
| 0.0976        | 0.91  | 100  | 0.0823          |
| 0.0965        | 1.0   | 110  | 0.0798          |
| 0.0891        | 1.09  | 120  | 0.0785          |
| 0.0877        | 1.18  | 130  | 0.0771          |
| 0.0912        | 1.27  | 140  | 0.0751          |
| 0.0841        | 1.36  | 150  | 0.0745          |
| 0.0865        | 1.45  | 160  | 0.0741          |
| 0.0868        | 1.54  | 170  | 0.0736          |
| 0.0847        | 1.63  | 180  | 0.0740          |
| 0.0822        | 1.72  | 190  | 0.0725          |
| 0.0863        | 1.81  | 200  | 0.0718          |
| 0.0784        | 1.9   | 210  | 0.0712          |
| 0.0797        | 1.99  | 220  | 0.0716          |
| 0.0799        | 2.08  | 230  | 0.0712          |
| 0.0796        | 2.18  | 240  | 0.0707          |
| 0.0758        | 2.27  | 250  | 0.0707          |
| 0.0794        | 2.36  | 260  | 0.0705          |
| 0.079         | 2.45  | 270  | 0.0703          |
| 0.0742        | 2.54  | 280  | 0.0703          |
| 0.0726        | 2.63  | 290  | 0.0703          |
| 0.0754        | 2.72  | 300  | 0.0702          |
| 0.0806        | 2.81  | 310  | 0.0700          |
| 0.0753        | 2.9   | 320  | 0.0701          |
| 0.0802        | 2.99  | 330  | 0.0700          |


### Framework versions

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