metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- sem_eval_2018_task_1
metrics:
- f1
- accuracy
model-index:
- name: bert-finetuned-sem_eval-english
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: sem_eval_2018_task_1
type: sem_eval_2018_task_1
config: subtask5.english
split: train
args: subtask5.english
metrics:
- name: F1
type: f1
value: 0.7113731269958242
- name: Accuracy
type: accuracy
value: 0.28103837471783294
bert-finetuned-sem_eval-english
This model is a fine-tuned version of bert-base-uncased on the sem_eval_2018_task_1 dataset. It achieves the following results on the evaluation set:
- Loss: 0.3131
- F1: 0.7114
- Roc Auc: 0.8046
- Accuracy: 0.2810
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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
|---|---|---|---|---|---|---|
| 0.4067 | 1.0 | 855 | 0.3205 | 0.6756 | 0.7766 | 0.2709 |
| 0.2828 | 2.0 | 1710 | 0.3062 | 0.7058 | 0.7973 | 0.3014 |
| 0.239 | 3.0 | 2565 | 0.3122 | 0.7100 | 0.8038 | 0.2810 |
| 0.2145 | 4.0 | 3420 | 0.3131 | 0.7114 | 0.8046 | 0.2810 |
| 0.1888 | 5.0 | 4275 | 0.3167 | 0.7096 | 0.8022 | 0.2844 |
Framework versions
- Transformers 4.21.1
- Pytorch 1.12.0+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1