bert_train_book_ent_15p_mid_qnli

This model is a fine-tuned version of gokulsrinivasagan/bert_train_book_ent_15p_mid on the GLUE QNLI dataset. It achieves the following results on the evaluation set:

• Loss: 0.6913
• Accuracy: 0.5054

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
0.6976	1.0	410	0.6938	0.4946
0.6948	2.0	820	0.6944	0.4946
0.694	3.0	1230	0.6935	0.5054
0.6937	4.0	1640	0.6935	0.4946
0.6935	5.0	2050	0.6937	0.4946
0.6934	6.0	2460	0.6956	0.4946
0.6932	7.0	2870	0.6933	0.5054
0.693	8.0	3280	0.6929	0.5054
0.693	9.0	3690	0.6934	0.4946
0.6929	10.0	4100	0.6927	0.4946
0.6927	11.0	4510	0.6933	0.5054
0.6927	12.0	4920	0.6933	0.5054
0.6927	13.0	5330	0.6932	0.5054
0.6927	14.0	5740	0.6914	0.5054
0.6926	15.0	6150	0.6934	0.4946
0.6927	16.0	6560	0.6934	0.4946
0.6926	17.0	6970	0.6915	0.4946
0.6926	18.0	7380	0.6913	0.5054
0.6926	19.0	7790	0.6913	0.5054
0.6927	20.0	8200	0.6914	0.4948
0.6927	21.0	8610	0.6933	0.4946
0.6926	22.0	9020	0.6920	0.4946
0.6925	23.0	9430	0.6917	0.4990

Framework versions

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