tinybert_base_train_book_ent_15p_s_init_kd_complete_wnli

This model is a fine-tuned version of gokulsrinivasagan/tinybert_base_train_book_ent_15p_s_init_kd_complete on the GLUE WNLI dataset. It achieves the following results on the evaluation set:

• Loss: 0.7236
• Accuracy: 0.2817

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
0.7127	1.0	3	0.7236	0.2817
0.6987	2.0	6	0.7287	0.2958
0.6986	3.0	9	0.7442	0.2958
0.6957	4.0	12	0.7401	0.4789
0.6921	5.0	15	0.7676	0.2535
0.6914	6.0	18	0.7926	0.3099

Framework versions

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