Language中文

Theme

gokuls/mobilebert_sa_GLUE_Experiment_wnli · Pirate Face

mobilebert_sa_GLUE_Experiment_wnli

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

Loss: 0.6895
Accuracy: 0.5634

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
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.6956	1.0	5	0.6895	0.5634
0.6944	2.0	10	0.6945	0.4366
0.6937	3.0	15	0.6947	0.4366
0.693	4.0	20	0.6914	0.5634
0.693	5.0	25	0.6898	0.5634
0.6932	6.0	30	0.6901	0.5634

Framework versions

Transformers 4.26.0
Pytorch 1.14.0a0+410ce96
Datasets 2.8.0
Tokenizers 0.13.2