bert-base-cased-healthdemomodel

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: 5.5819

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	1	6.1760
No log	2.0	2	6.1161
No log	3.0	3	6.0619
No log	4.0	4	6.0120
No log	5.0	5	5.9641
No log	6.0	6	5.9177
No log	7.0	7	5.8738
No log	8.0	8	5.8334
No log	9.0	9	5.7938
No log	10.0	10	5.7589
No log	11.0	11	5.7289
No log	12.0	12	5.7019
No log	13.0	13	5.6746
No log	14.0	14	5.6499
No log	15.0	15	5.6293
No log	16.0	16	5.6122
No log	17.0	17	5.5995
No log	18.0	18	5.5905
No log	19.0	19	5.5848
No log	20.0	20	5.5819

Framework versions

• Transformers 4.28.1
• Pytorch 2.0.0+cu118
• Datasets 2.11.0
• Tokenizers 0.13.3