metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- pharmaconer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: pharmacoNER
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: pharmaconer
type: pharmaconer
config: PharmaCoNER
split: validation
args: PharmaCoNER
metrics:
- name: Precision
type: precision
value: 0.9057634526085769
- name: Recall
type: recall
value: 0.9025585193249864
- name: F1
type: f1
value: 0.9041581458759373
- name: Accuracy
type: accuracy
value: 0.9948434782608696
pharmacoNER
This model is a fine-tuned version of PlanTL-GOB-ES/bsc-bio-ehr-es on the pharmaconer dataset. It achieves the following results on the evaluation set:
- Loss: 0.0251
- Precision: 0.9058
- Recall: 0.9026
- F1: 0.9042
- Accuracy: 0.9948
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.0272 | 1.0 | 1017 | 0.0288 | 0.8047 | 0.8503 | 0.8269 | 0.9914 |
| 0.0114 | 2.0 | 2034 | 0.0240 | 0.8950 | 0.8998 | 0.8974 | 0.9945 |
| 0.006 | 3.0 | 3051 | 0.0251 | 0.9058 | 0.9026 | 0.9042 | 0.9948 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.13.1+cu116
- Datasets 2.9.0
- Tokenizers 0.13.2