bert_base_train_book_ent_15p_s_init

This model is a fine-tuned version of google-bert/bert-base-uncased on the gokulsrinivasagan/processed_wikitext-103-raw-v1-ld dataset. It achieves the following results on the evaluation set:

• Loss: 6.9738
• Accuracy: 0.0623

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: 0.0001
• train_batch_size: 160
• eval_batch_size: 160
• 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
• lr_scheduler_warmup_steps: 10000
• num_epochs: 24

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
7.1672	6.9979	10000	7.0338	0.0591
7.166	13.9958	20000	7.1009	0.0574
7.1661	20.9937	30000	6.9738	0.0623

Framework versions

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