bert-base-uncased-finetuned-cola-dropout-0.2 – AI Model by cansurav | AlphaNeural AI

You can deploy this model and start earning money today!

cansurav/
bert-base-uncased-finetuned-cola-dropout-0.2

like

0

text-classification

generated_from_trainer

autotrain_compatible

endpoints_compatible

Views

No views yet

bert-base-uncased-finetuned-cola-dropout-0.2

This model is a fine-tuned version of bert-base-uncased on the glue dataset. It achieves the following results on the evaluation set:

Loss: 0.4502
Matthews Correlation: 0.5992

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
0.4987	1.0	535	0.5145	0.4872
0.3065	2.0	1070	0.4502	0.5992
0.2059	3.0	1605	0.7547	0.5208
0.1467	4.0	2140	0.8557	0.5390
0.1006	5.0	2675	0.9277	0.5550
0.0796	6.0	3210	1.0832	0.5765
0.0532	7.0	3745	1.0337	0.5687
0.0367	8.0	4280	1.1539	0.5779
0.0276	9.0	4815	1.3224	0.5755
0.0192	10.0	5350	1.3055	0.5810

Framework versions

Transformers 4.28.1
Pytorch 2.0.0+cu118
Datasets 2.12.0
Tokenizers 0.13.3