hBERTv1_no_pretrain_cola – AI Model by gokuls | AlphaNeural AI | AlphaNeural AI

You can deploy this model and start earning money today!

gokuls/
hBERTv1_no_pretrain_cola

like

0

text-classification

generated_from_trainer

autotrain_compatible

endpoints_compatible

Views

No views yet

hBERTv1_no_pretrain_cola

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

Loss: 0.6184
Matthews Correlation: 0.0
Accuracy: 0.6913

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: 0.0005
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
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Matthews Correlation	Accuracy
0.8952	1.0	67	0.6664	0.0	0.6913
0.6234	2.0	134	0.6184	0.0	0.6913
0.6127	3.0	201	0.6197	0.0	0.6913
0.6115	4.0	268	0.6209	0.0	0.6913
0.6096	5.0	335	0.6237	0.0	0.6913
0.6104	6.0	402	0.6209	0.0	0.6913
0.6123	7.0	469	0.6185	0.0	0.6913

Framework versions

Transformers 4.29.2
Pytorch 1.14.0a0+410ce96
Datasets 2.12.0
Tokenizers 0.13.3