metadata
license: mit
base_model: microsoft/BiomedNLP-KRISSBERT-PubMed-UMLS-EL
tags:
- generated_from_trainer
metrics:
- precision
- recall
- accuracy
- f1
model-index:
- name: results
results: []
results
This model is a fine-tuned version of microsoft/BiomedNLP-KRISSBERT-PubMed-UMLS-EL on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4228
- Precision: 0.9215
- Recall: 0.9209
- Accuracy: 0.9211
- F1: 0.9210
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: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | Accuracy | F1 |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 308 | 0.3266 | 0.8847 | 0.8822 | 0.8820 | 0.8824 |
| 0.4217 | 2.0 | 616 | 0.3034 | 0.9072 | 0.9066 | 0.9064 | 0.9065 |
| 0.4217 | 3.0 | 924 | 0.3483 | 0.9171 | 0.9170 | 0.9170 | 0.9171 |
| 0.163 | 4.0 | 1232 | 0.3952 | 0.9227 | 0.9227 | 0.9227 | 0.9226 |
| 0.0722 | 5.0 | 1540 | 0.4228 | 0.9215 | 0.9209 | 0.9211 | 0.9210 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2