bert_base_train_book_ent_40p_inv

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: 1.3380
• Accuracy: 0.7016

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: 176
• eval_batch_size: 176
• 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
1.8936	7.6923	10000	1.8034	0.6030
1.2199	15.3846	20000	1.3846	0.6875
1.0198	23.0769	30000	1.3380	0.7016

Framework versions

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