---
license: mit
base_model: microsoft/Phi-3-mini-4k-instruct
tags:
- generated_from_trainer
model-index:
- name: Phi0511B1
  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. -->

# Phi0511B1

This model is a fine-tuned version of [microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0690

## 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: 80
- num_epochs: 3
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 5.1765        | 0.09  | 10   | 4.1064          |
| 2.6213        | 0.18  | 20   | 0.8942          |
| 0.4793        | 0.27  | 30   | 0.1858          |
| 0.1596        | 0.36  | 40   | 0.1426          |
| 0.1372        | 0.45  | 50   | 0.1380          |
| 0.1401        | 0.54  | 60   | 0.1201          |
| 0.1139        | 0.63  | 70   | 0.1011          |
| 0.0995        | 0.73  | 80   | 0.0856          |
| 0.075         | 0.82  | 90   | 0.0778          |
| 0.078         | 0.91  | 100  | 0.0724          |
| 0.0685        | 1.0   | 110  | 0.0689          |
| 0.0577        | 1.09  | 120  | 0.0669          |
| 0.0531        | 1.18  | 130  | 0.0692          |
| 0.0622        | 1.27  | 140  | 0.0650          |
| 0.0561        | 1.36  | 150  | 0.0643          |
| 0.0595        | 1.45  | 160  | 0.0632          |
| 0.0555        | 1.54  | 170  | 0.0630          |
| 0.0549        | 1.63  | 180  | 0.0620          |
| 0.052         | 1.72  | 190  | 0.0627          |
| 0.0577        | 1.81  | 200  | 0.0595          |
| 0.0451        | 1.9   | 210  | 0.0612          |
| 0.0513        | 1.99  | 220  | 0.0626          |
| 0.0377        | 2.08  | 230  | 0.0629          |
| 0.0412        | 2.18  | 240  | 0.0663          |
| 0.0321        | 2.27  | 250  | 0.0701          |
| 0.034         | 2.36  | 260  | 0.0720          |
| 0.0366        | 2.45  | 270  | 0.0718          |
| 0.0323        | 2.54  | 280  | 0.0707          |
| 0.0337        | 2.63  | 290  | 0.0703          |
| 0.0371        | 2.72  | 300  | 0.0699          |
| 0.0417        | 2.81  | 310  | 0.0692          |
| 0.0383        | 2.9   | 320  | 0.0690          |
| 0.0346        | 2.99  | 330  | 0.0690          |


### Framework versions

- Transformers 4.36.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.14.0