metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- health_fact
metrics:
- accuracy
- f1
model-index:
- name: distilbert-base-uncased-finetuned-health_facts
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: health_fact
type: health_fact
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.5617792421746294
- name: F1
type: f1
value: 0.6021353784442518
distilbert-base-uncased-finetuned-health_facts
This model is a fine-tuned version of distilbert-base-uncased on the health_fact dataset. It achieves the following results on the evaluation set:
- Loss: 1.1172
- Accuracy: 0.5618
- F1: 0.6021
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: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 1.1497 | 1.0 | 154 | 0.9639 | 0.5404 | 0.5887 |
| 0.9639 | 2.0 | 308 | 0.9332 | 0.5692 | 0.6130 |
| 0.841 | 3.0 | 462 | 0.9520 | 0.5544 | 0.6047 |
| 0.734 | 4.0 | 616 | 1.1172 | 0.5618 | 0.6021 |
Framework versions
- Transformers 4.11.3
- Pytorch 1.10.0
- Datasets 1.16.1
- Tokenizers 0.10.3