You can deploy this model and start earning money today!

juliekenney/
openmed_pii_finetuned

Name: openmed_pii_finetuned
Availability: InStock

Views

No views yet

openmed_pii_finetuned

This model is a fine-tuned version of OpenMed/OpenMed-PII-Dutch-SuperClinical-Large-434M-v1 on the None dataset. It achieves the following results on the evaluation set:

More information needed

More information needed

More information needed

The following hyperparameters were used during training:

learning_rate: 2e-05
train_batch_size: 4
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 16
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 0.1
num_epochs: 5
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
1.3820	1.0	813	0.3712	0.7548	0.7422	0.7485	0.9422
0.9324	2.0	1626	0.3253	0.7525	0.7889	0.7703	0.948
0.7569	3.0	2439	0.2990	0.7778	0.7824	0.7801	0.9508
0.6287	4.0	3252	0.3051	0.7812	0.7982	0.7896	0.953
0.6297	5.0	4065	0.3078	0.7816	0.8097	0.7954	0.954