---
license: other
base_model: microsoft/phi-1_5
tags:
- generated_from_trainer
datasets:
- scitldr
model-index:
- name: microsoft_phi_1_5_peft
  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. -->

# microsoft_phi_1_5_peft

This model is a fine-tuned version of [microsoft/phi-1_5](https://huggingface.co/microsoft/phi-1_5) on the scitldr dataset.
It achieves the following results on the evaluation set:
- Loss: 2.5986

## 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: 0.001
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 2.554         | 0.1   | 200  | 2.6503          |
| 2.5714        | 0.2   | 400  | 2.6448          |
| 2.5322        | 0.3   | 600  | 2.6350          |
| 2.5854        | 0.4   | 800  | 2.6220          |
| 2.5415        | 0.5   | 1000 | 2.6239          |
| 2.5794        | 0.6   | 1200 | 2.6146          |
| 2.5491        | 0.7   | 1400 | 2.6092          |
| 2.5267        | 0.8   | 1600 | 2.6032          |
| 2.5789        | 0.9   | 1800 | 2.5986          |


### Framework versions

- Transformers 4.32.1
- Pytorch 2.0.1+cu117
- Datasets 2.14.4
- Tokenizers 0.13.3