mobilebert_sa_GLUE_Experiment_wnli_256

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: 0.6899
• 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

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.6942	1.0	5	0.6899	0.5634
0.6935	2.0	10	0.6920	0.5634
0.6933	3.0	15	0.6930	0.5634
0.693	4.0	20	0.6921	0.5634
0.693	5.0	25	0.6912	0.5634
0.693	6.0	30	0.6909	0.5634

Framework versions

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