mobilebert_add_GLUE_Experiment_logit_kd_mrpc_256 – AI Model by gokuls | AlphaNeural AI

You can deploy this model and start earning money today!

gokuls/
mobilebert_add_GLUE_Experiment_logit_kd_mrpc_256

like

0

text-classification

generated_from_trainer

autotrain_compatible

endpoints_compatible

Views

No views yet

mobilebert_add_GLUE_Experiment_logit_kd_mrpc_256

This model is a fine-tuned version of google/mobilebert-uncased on the GLUE MRPC dataset. It achieves the following results on the evaluation set:

Loss: 0.5536
Accuracy: 0.6838
F1: 0.8122
Combined Score: 0.7480

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: 128
eval_batch_size: 128
seed: 10
distributed_type: multi-GPU
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Combined Score
0.6289	1.0	29	0.5587	0.6838	0.8122	0.7480
0.61	2.0	58	0.5555	0.6838	0.8122	0.7480
0.6103	3.0	87	0.5550	0.6838	0.8122	0.7480
0.6091	4.0	116	0.5555	0.6838	0.8122	0.7480
0.6055	5.0	145	0.5536	0.6838	0.8122	0.7480
0.5956	6.0	174	0.5721	0.6838	0.8122	0.7480
0.5936	7.0	203	0.5714	0.6838	0.8122	0.7480
0.5757	8.0	232	0.5738	0.6838	0.8122	0.7480
0.5601	9.0	261	0.5746	0.6838	0.8122	0.7480
0.5489	10.0	290	0.5639	0.6838	0.8122	0.7480

Framework versions

Transformers 4.26.0
Pytorch 1.14.0a0+410ce96
Datasets 2.9.0
Tokenizers 0.13.2