metadata
library_name: transformers
license: mit
base_model: microsoft/BiomedNLP-BiomedBERT-large-uncased-abstract
tags:
- generated_from_trainer
datasets:
- source_data
metrics:
- precision
- recall
- f1
model-index:
- name: SourceData_SmallmolRoles_v1_0_0_PubMedBERT_large
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: source_data
type: source_data
config: ROLES_SM
split: validation
args: ROLES_SM
metrics:
- name: Precision
type: precision
value: 0.9722117202268431
- name: Recall
type: recall
value: 0.9740530303030303
- name: F1
type: f1
value: 0.973131504257332
SourceData_SmallmolRoles_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: 0.0018
- Accuracy Score: 0.9996
- Precision: 0.9722
- Recall: 0.9741
- F1: 0.9731
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: 1.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy Score | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 0.0008 | 0.9994 | 863 | 0.0018 | 0.9996 | 0.9722 | 0.9741 | 0.9731 |
Framework versions
- Transformers 4.46.3
- Pytorch 1.13.1+cu117
- Datasets 3.1.0
- Tokenizers 0.20.3