hBERTv2_new_no_pretrain_wnli – AI Model by gokuls | AlphaNeural AI

You can deploy this model and start earning money today!

gokuls/
hBERTv2_new_no_pretrain_wnli

like

0

text-classification

generated_from_trainer

autotrain_compatible

endpoints_compatible

Views

No views yet

hBERTv2_new_no_pretrain_wnli

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

Loss: 0.6874
Accuracy: 0.5634

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: 4e-05
train_batch_size: 128
eval_batch_size: 128
seed: 10
distributed_type: multi-GPU
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.9765	1.0	5	0.6952	0.4366
0.723	2.0	10	0.6938	0.4648
0.7209	3.0	15	0.6902	0.5634
0.7183	4.0	20	0.7155	0.5634
0.7155	5.0	25	0.6875	0.5634
0.7027	6.0	30	0.6978	0.4366
0.6966	7.0	35	0.7161	0.4366
0.7077	8.0	40	0.6926	0.5634
0.7048	9.0	45	0.7409	0.4366
0.7386	10.0	50	0.6874	0.5634
0.7104	11.0	55	0.6875	0.5634
0.7061	12.0	60	0.7088	0.4366
0.6951	13.0	65	0.7009	0.4507
0.6995	14.0	70	0.7050	0.4366
0.692	15.0	75	0.6976	0.3521

Framework versions

Transformers 4.30.2
Pytorch 1.14.0a0+410ce96
Datasets 2.12.0
Tokenizers 0.13.3