bert_base_train_book_ent_2

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

• Loss: 2.1578
• Accuracy: 0.7109

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: 96
• eval_batch_size: 96
• 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: 25

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.9291	4.1982	10000	2.1578	0.7109
1.4523	8.3963	20000	2.2038	0.7109
0.9904	12.5945	30000	2.5061	0.7046
0.5702	16.7926	40000	2.9523	0.6994
0.2197	20.9908	50000	3.2009	0.6952

Framework versions

• Transformers 4.51.0.dev0
• Pytorch 2.6.0+cu124
• Datasets 3.4.1
• Tokenizers 0.21.1