---
license: mit
library_name: peft
tags:
- generated_from_trainer
base_model: microsoft/phi-2
model-index:
- name: fine-tuning-Phi2-with-webglm-qa-with-lora
  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. -->

# fine-tuning-Phi2-with-webglm-qa-with-lora

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: 0.1016

## 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: 5e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 5
- total_train_batch_size: 10
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- training_steps: 500
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| No log        | 0.2   | 10   | 8.0315          |
| No log        | 0.4   | 20   | 6.2055          |
| No log        | 0.6   | 30   | 2.7735          |
| No log        | 0.8   | 40   | 0.6055          |
| 4.4745        | 1.0   | 50   | 0.5323          |
| 4.4745        | 1.2   | 60   | 0.4631          |
| 4.4745        | 1.39  | 70   | 0.4075          |
| 4.4745        | 1.59  | 80   | 0.3566          |
| 4.4745        | 1.79  | 90   | 0.3155          |
| 0.3331        | 1.99  | 100  | 0.2869          |
| 0.3331        | 2.19  | 110  | 0.2624          |
| 0.3331        | 2.39  | 120  | 0.2453          |
| 0.3331        | 2.59  | 130  | 0.2288          |
| 0.3331        | 2.79  | 140  | 0.2095          |
| 0.1947        | 2.99  | 150  | 0.1978          |
| 0.1947        | 3.19  | 160  | 0.1886          |
| 0.1947        | 3.39  | 170  | 0.1766          |
| 0.1947        | 3.59  | 180  | 0.1691          |
| 0.1947        | 3.78  | 190  | 0.1626          |
| 0.1486        | 3.98  | 200  | 0.1562          |
| 0.1486        | 4.18  | 210  | 0.1510          |
| 0.1486        | 4.38  | 220  | 0.1489          |
| 0.1486        | 4.58  | 230  | 0.1439          |
| 0.1486        | 4.78  | 240  | 0.1364          |
| 0.1232        | 4.98  | 250  | 0.1314          |
| 0.1232        | 5.18  | 260  | 0.1306          |
| 0.1232        | 5.38  | 270  | 0.1295          |
| 0.1232        | 5.58  | 280  | 0.1256          |
| 0.1232        | 5.78  | 290  | 0.1228          |
| 0.1084        | 5.98  | 300  | 0.1195          |
| 0.1084        | 6.18  | 310  | 0.1165          |
| 0.1084        | 6.37  | 320  | 0.1156          |
| 0.1084        | 6.57  | 330  | 0.1147          |
| 0.1084        | 6.77  | 340  | 0.1120          |
| 0.0964        | 6.97  | 350  | 0.1100          |
| 0.0964        | 7.17  | 360  | 0.1100          |
| 0.0964        | 7.37  | 370  | 0.1087          |
| 0.0964        | 7.57  | 380  | 0.1080          |
| 0.0964        | 7.77  | 390  | 0.1071          |
| 0.0905        | 7.97  | 400  | 0.1065          |
| 0.0905        | 8.17  | 410  | 0.1061          |
| 0.0905        | 8.37  | 420  | 0.1053          |
| 0.0905        | 8.57  | 430  | 0.1044          |
| 0.0905        | 8.76  | 440  | 0.1036          |
| 0.0843        | 8.96  | 450  | 0.1028          |
| 0.0843        | 9.16  | 460  | 0.1021          |
| 0.0843        | 9.36  | 470  | 0.1019          |
| 0.0843        | 9.56  | 480  | 0.1018          |
| 0.0843        | 9.76  | 490  | 0.1016          |
| 0.0819        | 9.96  | 500  | 0.1016          |


### Framework versions

- PEFT 0.7.1
- Transformers 4.36.2
- Pytorch 2.0.0
- Datasets 2.15.0
- Tokenizers 0.15.0