---
library_name: transformers
license: mit
base_model: openai-gpt
tags:
- generated_from_trainer
metrics:
- accuracy
- recall
- precision
model-index:
- name: gpt1_sst2_left
  results: []
datasets:
- nyu-mll/glue
- stanfordnlp/sst2
---

<!-- 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. -->

# gpt1_sst2_left

This model is a fine-tuned version of [openai-gpt](https://huggingface.co/openai-gpt) on sst2 dataset of GLUE benchmark.
It achieves the following results on the evaluation set:
- Loss: 0.4150
- Accuracy: 0.9266
- Recall: 0.9437
- Precision: 0.9148

Access to [Repository](https://github.com/GoktugGuvercin/Text-Classification/blob/main/gpt1_sst2.ipynb) for finetuning.

## Model description

More information needed

## Intended uses & limitations

More information needed

## Training and evaluation data

For batched training, \<pad\> token is added to the tokenizer and the following padding-truncation options are adapted:

- Padding Side: "right"
- Truncation Side: "left"

## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 4

### Training results

| Training Loss | Epoch | Step  | Validation Loss | Accuracy | Recall | Precision |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|:---------:|
| 0.2083        | 1.0   | 4210  | 0.2243          | 0.9266   | 0.9279 | 0.9279    |
| 0.1495        | 2.0   | 8420  | 0.3193          | 0.9300   | 0.9505 | 0.9154    |
| 0.0859        | 3.0   | 12630 | 0.3456          | 0.9255   | 0.9369 | 0.9183    |
| 0.0605        | 4.0   | 16840 | 0.4150          | 0.9266   | 0.9437 | 0.9148    |


### Framework versions

- Transformers 4.47.1
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0