bert_base_train_book_ent_15p_s_init_sst2

This model is a fine-tuned version of gokulsrinivasagan/bert_base_train_book_ent_15p_s_init on the GLUE SST2 dataset. It achieves the following results on the evaluation set:

• Loss: 0.6938
• Accuracy: 0.5092

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
0.6916	1.0	264	0.6944	0.4908
0.6901	2.0	528	0.7227	0.5092
0.6894	3.0	792	0.7004	0.5092
0.6897	4.0	1056	0.6943	0.5092
0.6891	5.0	1320	0.6941	0.5092
0.6892	6.0	1584	0.6938	0.5092
0.6886	7.0	1848	0.7039	0.5092
0.6882	8.0	2112	0.7006	0.5092
0.6891	9.0	2376	0.6944	0.5092
0.6884	10.0	2640	0.7145	0.5092
0.6884	11.0	2904	0.7039	0.5092

Framework versions

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