gpt2-finetuned-cola

lightsout19/gpt2-finetuned-cola

gpt2-finetuned-cola is a machine learning model from lightsout19. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

16% of all-time downloads

All-time downloads

Public

Parameters

124M

7.5 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors498 MB · 99%

At a glance

License: mit
Model type: gpt2
Access: Public
Created: Sep 18, 2024
Updated: Sep 18, 2024
SHA: fd8b1921

Base models

Model card

From the Hugging Face model README

gpt2-finetuned-cola

This model is a fine-tuned version of gpt2 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 1.3976
Matthews Correlation: 0.4246

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: 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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Matthews Correlation
0.3796	1.0	535	0.6729	0.3501
0.2829	2.0	1070	0.7611	0.3694
0.2215	3.0	1605	1.1312	0.3581
0.1993	4.0	2140	1.1153	0.3573
0.2185	5.0	2675	0.9811	0.4067
0.2188	6.0	3210	1.0690	0.4195
0.1921	7.0	3745	1.0713	0.3847
0.1642	8.0	4280	1.3494	0.4106
0.1585	9.0	4815	1.3976	0.4246
0.136	10.0	5350	1.4390	0.4158

Framework versions

Transformers 4.44.0
Pytorch 2.4.0
Datasets 2.21.0
Tokenizers 0.19.1

Type: gpt2
License: mit
Created: Sep 18, 2024
Updated: Sep 18, 2024