bert-base-cased-wikitext2

This model is a fine-tuned version of bert-base-cased on the wikitext dataset. It achieves the following results on the evaluation set:

• Loss: 6.8630

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: 2e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss
7.0876	1.0	2346	7.0208
6.9111	2.0	4692	6.8997
6.8649	3.0	7038	6.8515

Framework versions

• Transformers 4.32.0.dev0
• Pytorch 2.0.1+cpu
• Datasets 2.12.0
• Tokenizers 0.13.2