---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- sst2
model-index:
- name: finetuned_distilgpt2_sst2_negation0.01_pretrainedFalse_epochs3
  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. -->

# finetuned_distilgpt2_sst2_negation0.01_pretrainedFalse_epochs3

This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on the sst2 dataset.
It achieves the following results on the evaluation set:
- Loss: 3.2579

## 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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 2.6821        | 1.0   | 1323 | 3.2535          |
| 2.5045        | 2.0   | 2646 | 3.2502          |
| 2.4511        | 3.0   | 3969 | 3.2579          |


### Framework versions

- Transformers 4.25.1
- Pytorch 1.7.0
- Datasets 2.8.0
- Tokenizers 0.13.2