Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
ds-life-scientist-course-transformer-model – AI Model by Mardiyyah | AlphaNeural AI
You can deploy this model and start earning money today!
Mardiyyah
/
ds-life-scientist-course-transformer-model
like
0
transformers
safetensors
bert
text-classification
generated_from_trainer
en
microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext
finetune
mit
text-embeddings-inference
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
ds-life-scientist-course-transformer-model
This model is a fine-tuned version of
microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext
on the Mardiyyah/pubmed-rct-subset_cleaned dataset. It achieves the following results on the evaluation set:
Loss: 0.2004
Accuracy: 0.9313
F1 Micro: 0.9313
F1 Macro: 0.8771
F1 Weighted: 0.9309
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: 32
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: 3
mixed_precision_training: Native AMP
Training results
Training Loss
Epoch
Step
Validation Loss
Accuracy
F1 Micro
F1 Macro
F1 Weighted
0.5702
1.0
300
0.4178
0.8538
0.8538
0.7947
0.8528
0.3403
2.0
600
0.4458
0.8562
0.8562
0.7976
0.8536
0.2524
3.0
900
0.4300
0.8712
0.8712
0.8174
0.8700
Framework versions
Transformers 4.48.2
Pytorch 2.11.0+cu128
Datasets 3.0.2
Tokenizers 0.21.4
