bert-base-cased-wikitext2

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

• Loss: 6.5036

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: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss
7.0847	1.0	2346	7.0386
6.8734	2.0	4692	6.8551
6.7814	3.0	7038	6.7920
6.7354	4.0	9384	6.7064
6.6452	5.0	11730	6.6737
6.5976	6.0	14076	6.6223
6.561	7.0	16422	6.6287
6.5116	8.0	18768	6.5647
6.5225	9.0	21114	6.5995
6.4733	10.0	23460	6.5538
6.4449	11.0	25806	6.5882
6.4292	12.0	28152	6.5310
6.4342	13.0	30498	6.5242
6.3938	14.0	32844	6.4913
6.4199	15.0	35190	6.5006

Framework versions

• Transformers 4.55.4
• Pytorch 2.7.0+gitf717b2a
• Datasets 3.6.0
• Tokenizers 0.21.4