bert_base_train_book_ent_15p_s_init_wnli

This model is a fine-tuned version of gokulsrinivasagan/bert_base_train_book_ent_15p_s_init on the GLUE WNLI dataset. It achieves the following results on the evaluation set:

• Loss: 0.6849
• 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: 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
0.7049	1.0	3	0.6941	0.4366
0.7016	2.0	6	0.6849	0.5634
0.7019	3.0	9	0.6914	0.5634
0.6938	4.0	12	0.7015	0.4366
0.6971	5.0	15	0.6971	0.4366
0.6948	6.0	18	0.6892	0.5634
0.7045	7.0	21	0.6859	0.5634

Framework versions

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