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

# avmgpt-ft

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: 2.8612

## 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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 2
- num_epochs: 10

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 3.9077        | 0.92  | 3    | 3.3244          |
| 3.8362        | 1.85  | 6    | 3.2772          |
| 3.7771        | 2.77  | 9    | 3.2113          |
| 2.7759        | 4.0   | 13   | 3.1090          |
| 3.6167        | 4.92  | 16   | 3.0363          |
| 3.5208        | 5.85  | 19   | 2.9741          |
| 3.4616        | 6.77  | 22   | 2.9247          |
| 2.5348        | 8.0   | 26   | 2.8796          |
| 3.3474        | 8.92  | 29   | 2.8631          |
| 2.3174        | 9.23  | 30   | 2.8612          |


### Framework versions

- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2