tinybert_base_train_book_ent_15p_s_init_wnli

This model is a fine-tuned version of gokulsrinivasagan/tinybert_base_train_book_ent_15p_s_init on the GLUE WNLI dataset. It achieves the following results on the evaluation set:

• Loss: 0.7029
• Accuracy: 0.4085

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
0.7061	1.0	3	0.7029	0.4085
0.6975	2.0	6	0.7092	0.3803
0.6966	3.0	9	0.7114	0.4225
0.6946	4.0	12	0.7196	0.3944
0.6918	5.0	15	0.7428	0.3521
0.691	6.0	18	0.7392	0.3239

Framework versions

• Transformers 4.51.2
• Pytorch 2.6.0+cu126
• Datasets 3.5.0
• Tokenizers 0.21.1