distilbert_km_50_v2_qqp – AI Model by Hartunka | AlphaNeural AI

You can deploy this model and start earning money today!

Hartunka/
distilbert_km_50_v2_qqp

like

0

text-classification

generated_from_trainer

Hartunka/distilbert_km_50_v2

autotrain_compatible

endpoints_compatible

Views

No views yet

distilbert_km_50_v2_qqp

This model is a fine-tuned version of Hartunka/distilbert_km_50_v2 on the GLUE QQP dataset. It achieves the following results on the evaluation set:

Loss: 0.4002
Accuracy: 0.8211
F1: 0.7657
Combined Score: 0.7934

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	F1	Combined Score
0.4934	1.0	1422	0.4472	0.7875	0.6736	0.7305
0.3917	2.0	2844	0.4066	0.8074	0.7469	0.7771
0.3258	3.0	4266	0.4002	0.8211	0.7657	0.7934
0.2714	4.0	5688	0.4483	0.8259	0.7468	0.7864
0.2229	5.0	7110	0.4273	0.8319	0.7625	0.7972
0.1825	6.0	8532	0.4705	0.8315	0.7733	0.8024
0.1499	7.0	9954	0.5388	0.8342	0.7775	0.8058
0.1219	8.0	11376	0.5893	0.8175	0.7745	0.7960

Framework versions

Transformers 4.50.2
Pytorch 2.2.1+cu121
Datasets 2.18.0
Tokenizers 0.21.1