tinybert_train_book_ent_15p_wnli

This model is a fine-tuned version of gokulsrinivasagan/tinybert_train_book_ent_15p on the GLUE WNLI dataset. It achieves the following results on the evaluation set:

• Loss: 0.6946
• Accuracy: 0.5352

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
0.7033	1.0	3	0.6946	0.5352
0.6993	2.0	6	0.6955	0.5070
0.6994	3.0	9	0.7195	0.4507
0.6949	4.0	12	0.7054	0.3380
0.6939	5.0	15	0.7017	0.5070
0.6946	6.0	18	0.7099	0.3662

Framework versions

• Transformers 4.46.3
• Pytorch 2.2.1+cu118
• Datasets 3.1.0
• Tokenizers 0.20.3