biobert-cadec-ner – AI Model by Devbom | AlphaNeural AI

You can deploy this model and start earning money today!

Devbom/
biobert-cadec-ner

like

0

token-classification

generated_from_trainer

autotrain_compatible

endpoints_compatible

Views

No views yet

biobert-cadec-ner

This model is a fine-tuned version of dmis-lab/biobert-v1.1 on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.3115
Precision: 0.6817
Recall: 0.6858
F1: 0.6837
Accuracy: 0.9275

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: 0.00014812349590569507
train_batch_size: 4
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 8
optimizer: Adam with betas=(0.9,0.999) and epsilon=1.0703999133408962e-08
lr_scheduler_type: linear
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	116	0.2984	0.5957	0.6441	0.6190	0.9044
No log	2.0	233	0.2894	0.5952	0.6701	0.6305	0.9050
No log	3.0	349	0.2948	0.6618	0.6687	0.6652	0.9178
No log	4.0	466	0.2957	0.6740	0.6634	0.6687	0.9261
No log	4.98	580	0.3115	0.6817	0.6858	0.6837	0.9275

Framework versions

Transformers 4.27.3
Pytorch 2.0.1+cu118
Datasets 2.16.1
Tokenizers 0.13.2