---
license: mit
base_model: microsoft/phi-2
tags:
- generated_from_trainer
model-index:
- name: V0417MADP1
  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. -->

# V0417MADP1

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: 0.3114

## 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 |
|:-------------:|:-----:|:----:|:---------------:|
| 8.4601        | 0.09  | 10   | 3.0323          |
| 6.8643        | 0.18  | 20   | 2.8702          |
| 4.5679        | 0.27  | 30   | 2.3361          |
| 2.1248        | 0.36  | 40   | 1.5176          |
| 0.9282        | 0.45  | 50   | 0.9891          |
| 0.4911        | 0.54  | 60   | 0.7251          |
| 0.3523        | 0.63  | 70   | 0.5704          |
| 0.2758        | 0.73  | 80   | 0.4956          |
| 0.2531        | 0.82  | 90   | 0.4682          |
| 0.2596        | 0.91  | 100  | 0.4391          |
| 0.2475        | 1.0   | 110  | 0.4452          |
| 0.2484        | 1.09  | 120  | 0.4215          |
| 0.2508        | 1.18  | 130  | 0.4049          |
| 0.2237        | 1.27  | 140  | 0.3938          |
| 0.2173        | 1.36  | 150  | 0.3682          |
| 0.2077        | 1.45  | 160  | 0.3774          |
| 0.2233        | 1.54  | 170  | 0.3721          |
| 0.2241        | 1.63  | 180  | 0.3554          |
| 0.2178        | 1.72  | 190  | 0.3489          |
| 0.2096        | 1.81  | 200  | 0.3424          |
| 0.2137        | 1.9   | 210  | 0.3384          |
| 0.2084        | 1.99  | 220  | 0.3420          |
| 0.2157        | 2.08  | 230  | 0.3390          |
| 0.2052        | 2.18  | 240  | 0.3359          |
| 0.2017        | 2.27  | 250  | 0.3415          |
| 0.2115        | 2.36  | 260  | 0.3350          |
| 0.195         | 2.45  | 270  | 0.3316          |
| 0.2042        | 2.54  | 280  | 0.3244          |
| 0.2154        | 2.63  | 290  | 0.3287          |
| 0.1995        | 2.72  | 300  | 0.3258          |
| 0.1895        | 2.81  | 310  | 0.3022          |
| 0.207         | 2.9   | 320  | 0.3089          |
| 0.2038        | 2.99  | 330  | 0.3114          |


### Framework versions

- Transformers 4.36.0.dev0
- Pytorch 2.2.2+cu121
- Datasets 2.18.0
- Tokenizers 0.14.1