tiny_bert_rand_5_v1_wnli – AI Model by Hartunka | AlphaNeural AI

You can deploy this model and start earning money today!

Hartunka/
tiny_bert_rand_5_v1_wnli

like

0

text-classification

generated_from_trainer

Hartunka/tiny_bert_rand_5_v1

autotrain_compatible

endpoints_compatible

Views

No views yet

tiny_bert_rand_5_v1_wnli

This model is a fine-tuned version of Hartunka/tiny_bert_rand_5_v1 on the GLUE WNLI dataset. It achieves the following results on the evaluation set:

Loss: 0.7070
Accuracy: 0.5070

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
0.7071	1.0	3	0.7102	0.3944
0.6958	2.0	6	0.7070	0.5070
0.6966	3.0	9	0.7194	0.3380
0.6893	4.0	12	0.7316	0.2254
0.6887	5.0	15	0.7407	0.2254
0.6904	6.0	18	0.7488	0.2254
0.6899	7.0	21	0.7567	0.2817

Framework versions

Transformers 4.50.2
Pytorch 2.2.1+cu121
Datasets 2.18.0
Tokenizers 0.21.1