metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- emotion
metrics:
- accuracy
- f1
base_model: bert-base-uncased
model-index:
- name: >-
bert-base-uncased-with-preprocess-finetuned-emotion-5-epochs-5e-05-lr-0.1-weight_decay
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: emotion
type: emotion
config: split
split: validation
args: split
metrics:
- type: accuracy
value: 0.941
name: Accuracy
- type: f1
value: 0.9411169346964399
name: F1
bert-base-uncased-with-preprocess-finetuned-emotion-5-epochs-5e-05-lr-0.1-weight_decay
This model is a fine-tuned version of bert-base-uncased on the emotion dataset. It achieves the following results on the evaluation set:
- Loss: 0.2591
- Accuracy: 0.941
- F1: 0.9411
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: 5e-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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.0799 | 1.0 | 250 | 0.1898 | 0.9375 | 0.9377 |
| 0.0516 | 2.0 | 500 | 0.2290 | 0.938 | 0.9383 |
| 0.0386 | 3.0 | 750 | 0.2107 | 0.9415 | 0.9419 |
| 0.0195 | 4.0 | 1000 | 0.2607 | 0.9435 | 0.9433 |
| 0.0149 | 5.0 | 1250 | 0.2591 | 0.941 | 0.9411 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.0
- Tokenizers 0.13.3