metadata

license: mit
base_model: microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext
tags:
  - generated_from_keras_callback
model-index:
  - name: Kikia26/FineTunePubMedBertWithTensorflowKeras
    results: []

Kikia26/FineTunePubMedBertWithTensorflowKeras

This model is a fine-tuned version of microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext on an unknown dataset. It achieves the following results on the evaluation set:

Train Loss: 0.3522
Validation Loss: 0.4051
Train Precision: 0.5896
Train Recall: 0.6245
Train F1: 0.6066
Train Accuracy: 0.8857
Epoch: 9

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:

optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5e-05, 'decay_steps': 100, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
training_precision: float32

Training results

Train Loss	Validation Loss	Train Precision	Train Recall	Train F1	Train Accuracy	Epoch
1.2909	0.7719	0.0	0.0	0.0	0.7813	0
0.8005	0.5567	0.4313	0.3776	0.4027	0.8372	1
0.5460	0.4551	0.5509	0.5823	0.5662	0.8676	2
0.4141	0.4381	0.5443	0.6477	0.5915	0.8732	3
0.3626	0.4051	0.5896	0.6245	0.6066	0.8857	4
0.3591	0.4051	0.5896	0.6245	0.6066	0.8857	5
0.3503	0.4051	0.5896	0.6245	0.6066	0.8857	6
0.3521	0.4051	0.5896	0.6245	0.6066	0.8857	7
0.3554	0.4051	0.5896	0.6245	0.6066	0.8857	8
0.3522	0.4051	0.5896	0.6245	0.6066	0.8857	9

Framework versions

Transformers 4.35.2
TensorFlow 2.14.0
Datasets 2.15.0
Tokenizers 0.15.0