Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
SourceData_NER_v1_0_0_PubMedBERT_large – AI Model by EMBO | AlphaNeural AI
You can deploy this model and start earning money today!
EMBO
/
SourceData_NER_v1_0_0_PubMedBERT_large
like
0
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
SourceData_NER_v1_0_0_PubMedBERT_large
This model is a fine-tuned version of
microsoft/BiomedNLP-BiomedBERT-large-uncased-abstract
on the source_data dataset. It achieves the following results on the evaluation set:
Loss: 0.1352
Accuracy Score: 0.9575
Precision: 0.8202
Recall: 0.8535
F1: 0.8365
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: 5e-05
train_batch_size: 16
eval_batch_size: 64
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 64
optimizer: Use adafactor and the args are: No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 2.0
Training results
Training Loss
Epoch
Step
Validation Loss
Accuracy Score
Precision
Recall
F1
0.108
0.9994
863
0.1354
0.9557
0.8133
0.8463
0.8294
0.0778
1.9988
1726
0.1352
0.9575
0.8202
0.8535
0.8365
Framework versions
Transformers 4.46.3
Pytorch 1.13.1+cu117
Datasets 3.1.0
Tokenizers 0.20.3
