metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- emotion
metrics:
- accuracy
model-index:
- name: bert-base-emotion_48
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: emotion
type: emotion
config: split
split: validation
args: split
metrics:
- name: Accuracy
type: accuracy
value: 0.8903
bert-base-emotion_48
This model is a fine-tuned version of gokuls/bert_base_48 on the emotion dataset. It achieves the following results on the evaluation set:
- Loss: 0.3294
- Accuracy: 0.8903
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: 33
- distributed_type: multi-GPU
- 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 |
|---|---|---|---|---|
| 0.7185 | 1.0 | 250 | 0.3644 | 0.8735 |
| 0.2792 | 2.0 | 500 | 0.3189 | 0.887 |
| 0.1922 | 3.0 | 750 | 0.3294 | 0.893 |
| 0.1311 | 4.0 | 1000 | 0.3895 | 0.891 |
| 0.098 | 5.0 | 1250 | 0.3870 | 0.8905 |
| 0.0702 | 6.0 | 1500 | 0.4275 | 0.8895 |
| 0.05 | 7.0 | 1750 | 0.5372 | 0.886 |
| 0.0332 | 8.0 | 2000 | 0.5702 | 0.8905 |
| 0.023 | 9.0 | 2250 | 0.5759 | 0.8915 |
| 0.0176 | 10.0 | 2500 | 0.5959 | 0.891 |
Framework versions
- Transformers 4.30.2
- Pytorch 1.14.0a0+410ce96
- Datasets 2.13.0
- Tokenizers 0.13.3