---
license: mit
base_model: microsoft/phi-2
tags:
- generated_from_trainer
model-index:
- name: 0503LayerAnalysis0
  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. -->

# 0503LayerAnalysis0

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: 0.0420

## 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 |
|:-------------:|:-----:|:----:|:---------------:|
| 2.0721        | 0.09  | 10   | 0.6481          |
| 0.2379        | 0.18  | 20   | 0.1455          |
| 0.1349        | 0.27  | 30   | 0.1107          |
| 0.112         | 0.36  | 40   | 0.0931          |
| 0.0994        | 0.45  | 50   | 0.0951          |
| 0.0957        | 0.54  | 60   | 0.0814          |
| 0.0872        | 0.63  | 70   | 0.0751          |
| 0.0803        | 0.73  | 80   | 0.0726          |
| 0.0796        | 0.82  | 90   | 0.0702          |
| 0.0778        | 0.91  | 100  | 0.0697          |
| 0.0755        | 1.0   | 110  | 0.0690          |
| 0.0706        | 1.09  | 120  | 0.0666          |
| 0.0689        | 1.18  | 130  | 0.0693          |
| 0.0707        | 1.27  | 140  | 0.0683          |
| 0.0642        | 1.36  | 150  | 0.0657          |
| 0.0683        | 1.45  | 160  | 0.0592          |
| 0.0596        | 1.54  | 170  | 0.0548          |
| 0.0553        | 1.63  | 180  | 0.0467          |
| 0.0482        | 1.72  | 190  | 0.0474          |
| 0.0583        | 1.81  | 200  | 0.0473          |
| 0.0436        | 1.9   | 210  | 0.0511          |
| 0.0489        | 1.99  | 220  | 0.0527          |
| 0.0436        | 2.08  | 230  | 0.0462          |
| 0.0357        | 2.18  | 240  | 0.0498          |
| 0.0384        | 2.27  | 250  | 0.0444          |
| 0.0416        | 2.36  | 260  | 0.0430          |
| 0.0364        | 2.45  | 270  | 0.0422          |
| 0.0346        | 2.54  | 280  | 0.0437          |
| 0.0336        | 2.63  | 290  | 0.0441          |
| 0.0323        | 2.72  | 300  | 0.0423          |
| 0.0392        | 2.81  | 310  | 0.0421          |
| 0.0353        | 2.9   | 320  | 0.0421          |
| 0.0343        | 2.99  | 330  | 0.0420          |


### Framework versions

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