tiny_bert_rand_5_v2_wnli – AI Model by Hartunka | AlphaNeural AI

You can deploy this model and start earning money today!

Hartunka/
tiny_bert_rand_5_v2_wnli

like

0

text-classification

generated_from_trainer

Hartunka/tiny_bert_rand_5_v2

autotrain_compatible

endpoints_compatible

Views

No views yet

tiny_bert_rand_5_v2_wnli

This model is a fine-tuned version of Hartunka/tiny_bert_rand_5_v2 on the GLUE WNLI dataset. It achieves the following results on the evaluation set:

Loss: 0.6922
Accuracy: 0.5352

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
0.7042	1.0	3	0.7057	0.4366
0.6983	2.0	6	0.6922	0.5352
0.6965	3.0	9	0.6999	0.4225
0.6923	4.0	12	0.7091	0.4225
0.6938	5.0	15	0.7132	0.3803
0.6933	6.0	18	0.7151	0.3521
0.6915	7.0	21	0.7154	0.4366

Framework versions

Transformers 4.50.2
Pytorch 2.2.1+cu121
Datasets 2.18.0
Tokenizers 0.21.1