bert_base_rand_100_v2

This model is a fine-tuned version of on the Hartunka/processed_wikitext-103-raw-v1-rand-100_v2 dataset. It achieves the following results on the evaluation set:

• Loss: 10.7777
• Accuracy: 0.1534

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
10.6199	4.1982	10000	10.7772	0.1509
9.3028	8.3963	20000	11.4804	0.1521
7.6531	12.5945	30000	12.8492	0.1543
6.6672	16.7926	40000	13.9831	0.1512
6.3804	20.9908	50000	14.2044	0.1516

Framework versions

• Transformers 4.50.2
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.21.1