BERT-fully-trained-accuracy

This model is a fine-tuned version of bert-base-uncased on the gokuls/wiki_book_corpus_complete_processed_bert_dataset dataset. It achieves the following results on the evaluation set:

• eval_loss: 2.3870
• eval_accuracy: 0.5781
• eval_runtime: 2139.188
• eval_samples_per_second: 144.146
• eval_steps_per_second: 4.505
• step: 0

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: 1e-05
• train_batch_size: 32
• eval_batch_size: 32
• seed: 10
• distributed_type: multi-GPU
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 10000
• num_epochs: 5

Framework versions

• Transformers 4.35.0
• Pytorch 1.14.0a0+410ce96
• Datasets 2.14.6
• Tokenizers 0.14.1