mobilebert_sa_GLUE_Experiment_logit_kd_stsb_128 – AI Model by gokuls | AlphaNeural AI

You can deploy this model and start earning money today!

gokuls/
mobilebert_sa_GLUE_Experiment_logit_kd_stsb_128

like

0

text-classification

generated_from_trainer

autotrain_compatible

endpoints_compatible

Views

No views yet

mobilebert_sa_GLUE_Experiment_logit_kd_stsb_128

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

Loss: 1.1533
Pearson: 0.0554
Spearmanr: 0.0563
Combined Score: 0.0558

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: 5e-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	Pearson	Spearmanr	Combined Score
2.5973	1.0	45	1.2342	-0.0353	-0.0325	-0.0339
1.0952	2.0	90	1.1740	0.0434	0.0419	0.0426
1.0581	3.0	135	1.1533	0.0554	0.0563	0.0558
1.0455	4.0	180	1.2131	0.0656	0.0690	0.0673
0.9795	5.0	225	1.3883	0.0868	0.0858	0.0863
0.9197	6.0	270	1.4141	0.1181	0.1148	0.1165
0.8182	7.0	315	1.3460	0.1771	0.1853	0.1812
0.6796	8.0	360	1.1577	0.2286	0.2340	0.2313

Framework versions

Transformers 4.26.0
Pytorch 1.14.0a0+410ce96
Datasets 2.9.0
Tokenizers 0.13.2