---
license: mit
library_name: peft
tags:
- generated_from_trainer
base_model: microsoft/phi-2
model-index:
- name: phi2_mrqa_v2
  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. -->

# phi2_mrqa_v2

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: 1.1123

## 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: 2e-05
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.03
- training_steps: 800
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 1.5938        | 0.5   | 100  | 1.2202          |
| 1.2563        | 1.0   | 200  | 1.1830          |
| 1.2218        | 1.5   | 300  | 1.1568          |
| 1.1537        | 2.0   | 400  | 1.1370          |
| 1.1376        | 2.5   | 500  | 1.1254          |
| 1.2026        | 3.0   | 600  | 1.1177          |
| 1.1269        | 3.5   | 700  | 1.1137          |
| 1.1692        | 4.0   | 800  | 1.1123          |


### Framework versions

- PEFT 0.10.1.dev0
- Transformers 4.41.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1