bert_tiny_lda_20_v1_book_wnli – AI Model by gokulsrinivasagan | AlphaNeural AI

You can deploy this model and start earning money today!

gokulsrinivasagan/
bert_tiny_lda_20_v1_book_wnli

like

0

text-classification

generated_from_trainer

gokulsrinivasagan/bert_tiny_lda_20_v1_book

autotrain_compatible

endpoints_compatible

Views

No views yet

bert_tiny_lda_20_v1_book_wnli

This model is a fine-tuned version of gokulsrinivasagan/bert_tiny_lda_20_v1_book on the GLUE WNLI dataset. It achieves the following results on the evaluation set:

Loss: 0.7073
Accuracy: 0.4507

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: 256
eval_batch_size: 256
seed: 10
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.7059	1.0	3	0.7168	0.3239
0.6968	2.0	6	0.7073	0.4507
0.6986	3.0	9	0.7241	0.3944
0.6968	4.0	12	0.7089	0.4648
0.6932	5.0	15	0.7106	0.4789
0.6931	6.0	18	0.7262	0.3239
0.689	7.0	21	0.7329	0.2958

Framework versions

Transformers 4.46.3
Pytorch 2.2.1+cu118
Datasets 2.17.0
Tokenizers 0.20.3