---
license: mit
base_model: microsoft/Phi-3-mini-4k-instruct
tags:
- generated_from_trainer
model-index:
- name: PHI30511HMA12H
  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. -->

# PHI30511HMA12H

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: 0.0869

## 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: 100
- num_epochs: 3
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 2.8775        | 0.09  | 10   | 0.3763          |
| 0.2111        | 0.18  | 20   | 0.1599          |
| 0.1716        | 0.27  | 30   | 0.1572          |
| 0.1387        | 0.36  | 40   | 0.1256          |
| 0.1207        | 0.45  | 50   | 0.1180          |
| 0.122         | 0.54  | 60   | 0.0924          |
| 0.0892        | 0.63  | 70   | 0.1051          |
| 0.0987        | 0.73  | 80   | 0.0895          |
| 0.0714        | 0.82  | 90   | 0.0755          |
| 0.0719        | 0.91  | 100  | 0.0724          |
| 0.0733        | 1.0   | 110  | 0.0718          |
| 0.049         | 1.09  | 120  | 0.0710          |
| 0.0504        | 1.18  | 130  | 0.0854          |
| 0.0585        | 1.27  | 140  | 0.0735          |
| 0.0539        | 1.36  | 150  | 0.0671          |
| 0.0588        | 1.45  | 160  | 0.0735          |
| 0.0502        | 1.54  | 170  | 0.0683          |
| 0.0509        | 1.63  | 180  | 0.0710          |
| 0.044         | 1.72  | 190  | 0.0674          |
| 0.0467        | 1.81  | 200  | 0.0708          |
| 0.0521        | 1.9   | 210  | 0.0689          |
| 0.0468        | 1.99  | 220  | 0.0721          |
| 0.0233        | 2.08  | 230  | 0.0698          |
| 0.0207        | 2.18  | 240  | 0.0851          |
| 0.0189        | 2.27  | 250  | 0.1004          |
| 0.0112        | 2.36  | 260  | 0.1035          |
| 0.0194        | 2.45  | 270  | 0.0972          |
| 0.0133        | 2.54  | 280  | 0.0941          |
| 0.0184        | 2.63  | 290  | 0.0909          |
| 0.0207        | 2.72  | 300  | 0.0879          |
| 0.0158        | 2.81  | 310  | 0.0870          |
| 0.0192        | 2.9   | 320  | 0.0871          |
| 0.015         | 2.99  | 330  | 0.0869          |


### Framework versions

- Transformers 4.36.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.18.0
- Tokenizers 0.14.1