hBERTv2_new_pretrain_48_ver2_stsb – AI Model by gokuls | AlphaNeural AI

You can deploy this model and start earning money today!

gokuls/
hBERTv2_new_pretrain_48_ver2_stsb

like

0

text-classification

generated_from_trainer

gokuls/bert_12_layer_model_v2_complete_training_new_48

autotrain_compatible

endpoints_compatible

Views

No views yet

hBERTv2_new_pretrain_48_ver2_stsb

This model is a fine-tuned version of gokuls/bert_12_layer_model_v2_complete_training_new_48 on the GLUE STSB dataset. It achieves the following results on the evaluation set:

Loss: 2.0659
Pearson: 0.3927
Spearmanr: 0.3829
Combined Score: 0.3878

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: 64
eval_batch_size: 64
seed: 10
distributed_type: multi-GPU
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Pearson	Spearmanr	Combined Score
2.3158	1.0	90	2.7785	0.1355	0.1181	0.1268
2.0193	2.0	180	2.6566	0.1954	0.2050	0.2002
1.7471	3.0	270	2.5202	0.2578	0.2647	0.2612
1.5032	4.0	360	3.0601	0.2605	0.2732	0.2668
1.1825	5.0	450	2.3378	0.3150	0.3180	0.3165
0.8788	6.0	540	2.3657	0.3437	0.3421	0.3429
0.6987	7.0	630	2.0659	0.3927	0.3829	0.3878
0.5879	8.0	720	2.6712	0.3631	0.3636	0.3634
0.4865	9.0	810	2.3066	0.3665	0.3625	0.3645
0.4233	10.0	900	2.2781	0.3753	0.3695	0.3724
0.3628	11.0	990	2.4672	0.3848	0.3758	0.3803
0.3113	12.0	1080	2.4339	0.3873	0.3809	0.3841

Framework versions

Transformers 4.34.0
Pytorch 1.14.0a0+410ce96
Datasets 2.14.5
Tokenizers 0.14.1