tiny-bert-sst2-1_mobilebert-only-distillation – AI Model by gokuls | AlphaNeural AI

You can deploy this model and start earning money today!

gokuls/
tiny-bert-sst2-1_mobilebert-only-distillation

like

0

text-classification

generated_from_trainer

autotrain_compatible

endpoints_compatible

Views

No views yet

tiny-bert-sst2-1_mobilebert-only-distillation

This model is a fine-tuned version of google/bert_uncased_L-2_H-128_A-2 on the glue dataset. It achieves the following results on the evaluation set:

Loss: 2.2808
Accuracy: 0.8291

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: 16
eval_batch_size: 16
seed: 33
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 10
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.4252	1.0	4210	2.6253	0.8142
0.519	2.0	8420	2.4860	0.8245
0.4986	3.0	12630	2.2808	0.8291
0.4454	4.0	16840	2.5185	0.8280
0.3912	5.0	21050	2.3982	0.8257
0.3561	6.0	25260	2.4030	0.8211

Framework versions

Transformers 4.21.1
Pytorch 1.12.1+cu113
Datasets 2.4.0
Tokenizers 0.12.1