---
license: other
library_name: peft
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
base_model: facebook/opt-350m
model-index:
- name: opt-350m-pattern-based_finetuning_with_lora-mnli-d1_fs3
  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. -->

# opt-350m-pattern-based_finetuning_with_lora-mnli-d1_fs3

This model is a fine-tuned version of [facebook/opt-350m](https://huggingface.co/facebook/opt-350m) on the glue dataset.
It achieves the following results on the evaluation set:
- Loss: 0.9450
- Accuracy: 0.5103

## 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-06
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.528         | 1.0   | 1    | 0.9465          | 0.5078   |
| 0.4722        | 2.0   | 2    | 0.9459          | 0.5093   |
| 0.5113        | 3.0   | 3    | 0.9454          | 0.5102   |
| 0.4858        | 4.0   | 4    | 0.9451          | 0.5100   |
| 0.4233        | 5.0   | 5    | 0.9450          | 0.5103   |


### Framework versions

- PEFT 0.7.1.dev0
- Transformers 4.36.0.dev0
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0