---
license: mit
library_name: peft
tags:
- generated_from_trainer
base_model: microsoft/phi-2
model-index:
- name: phi-2-finetuned-labeledsbc
  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. -->

# phi-2-finetuned-labeledsbc

This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4040

## 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: 0.0002
- train_batch_size: 6
- eval_batch_size: 6
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 24
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 2
- num_epochs: 50
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 3.4053        | 1.0   | 6    | 3.1734          |
| 2.7973        | 2.0   | 12   | 2.3825          |
| 2.0487        | 3.0   | 18   | 1.8269          |
| 1.6066        | 4.0   | 24   | 1.5462          |
| 1.3941        | 5.0   | 30   | 1.3882          |
| 1.2595        | 6.0   | 36   | 1.2367          |
| 1.1104        | 7.0   | 42   | 1.1045          |
| 0.988         | 8.0   | 48   | 1.0010          |
| 0.8834        | 9.0   | 54   | 0.9122          |
| 0.7908        | 10.0  | 60   | 0.8344          |
| 0.7069        | 11.0  | 66   | 0.7794          |
| 0.6332        | 12.0  | 72   | 0.7276          |
| 0.5627        | 13.0  | 78   | 0.6681          |
| 0.5072        | 14.0  | 84   | 0.6246          |
| 0.4579        | 15.0  | 90   | 0.5930          |
| 0.4278        | 16.0  | 96   | 0.5549          |
| 0.3945        | 17.0  | 102  | 0.5336          |
| 0.3596        | 18.0  | 108  | 0.5108          |
| 0.3248        | 19.0  | 114  | 0.4835          |
| 0.3066        | 20.0  | 120  | 0.4727          |
| 0.2909        | 21.0  | 126  | 0.4453          |
| 0.2661        | 22.0  | 132  | 0.4450          |
| 0.2521        | 23.0  | 138  | 0.4278          |
| 0.2474        | 24.0  | 144  | 0.4186          |
| 0.2439        | 25.0  | 150  | 0.4247          |
| 0.2377        | 26.0  | 156  | 0.4125          |
| 0.2271        | 27.0  | 162  | 0.4085          |
| 0.2144        | 28.0  | 168  | 0.4112          |
| 0.2085        | 29.0  | 174  | 0.4065          |
| 0.2118        | 30.0  | 180  | 0.4111          |
| 0.2088        | 31.0  | 186  | 0.4080          |
| 0.1983        | 32.0  | 192  | 0.4068          |
| 0.1966        | 33.0  | 198  | 0.4018          |
| 0.1921        | 34.0  | 204  | 0.4007          |
| 0.1928        | 35.0  | 210  | 0.3933          |
| 0.1893        | 36.0  | 216  | 0.3919          |
| 0.185         | 37.0  | 222  | 0.3996          |
| 0.1762        | 38.0  | 228  | 0.4016          |
| 0.1812        | 39.0  | 234  | 0.4052          |
| 0.1785        | 40.0  | 240  | 0.4008          |
| 0.173         | 41.0  | 246  | 0.4009          |
| 0.1748        | 42.0  | 252  | 0.4010          |
| 0.1745        | 43.0  | 258  | 0.4023          |
| 0.1765        | 44.0  | 264  | 0.4003          |
| 0.1748        | 45.0  | 270  | 0.4014          |
| 0.1809        | 46.0  | 276  | 0.4020          |
| 0.1698        | 47.0  | 282  | 0.4028          |
| 0.1691        | 48.0  | 288  | 0.4037          |
| 0.174         | 49.0  | 294  | 0.4040          |
| 0.1656        | 50.0  | 300  | 0.4040          |


### Framework versions

- PEFT 0.10.0
- Transformers 4.38.2
- Pytorch 2.1.2
- Datasets 2.1.0
- Tokenizers 0.15.2