---
license: mit
base_model: microsoft/phi-2
tags:
- generated_from_trainer
model-index:
- name: V0422MADP7C
  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. -->

# V0422MADP7C

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: 0.0624

## 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 |
|:-------------:|:-----:|:----:|:---------------:|
| 5.122         | 0.09  | 10   | 1.5747          |
| 2.8187        | 0.18  | 20   | 0.1541          |
| 0.5874        | 0.27  | 30   | 0.1411          |
| 0.1821        | 0.36  | 40   | 0.1270          |
| 0.1336        | 0.45  | 50   | 0.1306          |
| 0.1212        | 0.54  | 60   | 0.0868          |
| 0.0955        | 0.63  | 70   | 0.0838          |
| 0.0871        | 0.73  | 80   | 0.0787          |
| 0.0946        | 0.82  | 90   | 0.0799          |
| 0.0904        | 0.91  | 100  | 0.0773          |
| 0.1084        | 1.0   | 110  | 0.0751          |
| 0.0839        | 1.09  | 120  | 0.0742          |
| 0.0824        | 1.18  | 130  | 0.0724          |
| 0.0812        | 1.27  | 140  | 0.0691          |
| 0.1347        | 1.36  | 150  | 0.1280          |
| 0.1061        | 1.45  | 160  | 0.0816          |
| 0.0898        | 1.54  | 170  | 0.0771          |
| 0.0863        | 1.63  | 180  | 0.0743          |
| 0.0812        | 1.72  | 190  | 0.0704          |
| 0.0853        | 1.81  | 200  | 0.0718          |
| 0.0758        | 1.9   | 210  | 0.0744          |
| 0.078         | 1.99  | 220  | 0.0709          |
| 0.0685        | 2.08  | 230  | 0.0663          |
| 0.0651        | 2.18  | 240  | 0.0683          |
| 0.0649        | 2.27  | 250  | 0.0633          |
| 0.0631        | 2.36  | 260  | 0.0629          |
| 0.0629        | 2.45  | 270  | 0.0624          |
| 0.0607        | 2.54  | 280  | 0.0628          |
| 0.0572        | 2.63  | 290  | 0.0627          |
| 0.0606        | 2.72  | 300  | 0.0626          |
| 0.0622        | 2.81  | 310  | 0.0623          |
| 0.0585        | 2.9   | 320  | 0.0625          |
| 0.0654        | 2.99  | 330  | 0.0624          |


### Framework versions

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