metadata
base_model: arnabdhar/tinybert-ner
tags:
- generated_from_trainer
datasets:
- ncbi_disease
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: checkpoint-1000
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: ncbi_disease
type: ncbi_disease
config: ncbi_disease
split: test
args: ncbi_disease
metrics:
- name: Precision
type: precision
value: 0.4722222222222222
- name: Recall
type: recall
value: 0.40729166666666666
- name: F1
type: f1
value: 0.43736017897091717
- name: Accuracy
type: accuracy
value: 0.9466873494713638
checkpoint-1000
This model is a fine-tuned version of arnabdhar/tinybert-ner on the ncbi_disease dataset. It achieves the following results on the evaluation set:
- Loss: 0.1611
- Precision: 0.4722
- Recall: 0.4073
- F1: 0.4374
- Accuracy: 0.9467
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: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 340 | 0.2055 | 0.2744 | 0.1521 | 0.1957 | 0.9318 |
| 0.2656 | 2.0 | 680 | 0.1761 | 0.4051 | 0.3 | 0.3447 | 0.9417 |
| 0.1738 | 3.0 | 1020 | 0.1638 | 0.4582 | 0.4 | 0.4271 | 0.9455 |
| 0.1738 | 4.0 | 1360 | 0.1611 | 0.4722 | 0.4073 | 0.4374 | 0.9467 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0