metadata
license: apache-2.0
base_model: google/bert_uncased_L-2_H-128_A-2
tags:
- generated_from_trainer
datasets:
- emotion
metrics:
- accuracy
model-index:
- name: bert_uncased_L-2_H-128_A-2_emotion
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: 0.893
bert_uncased_L-2_H-128_A-2_emotion
This model is a fine-tuned version of google/bert_uncased_L-2_H-128_A-2 on the emotion dataset. It achieves the following results on the evaluation set:
- Loss: 0.3583
- Accuracy: 0.893
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 |
|---|---|---|---|---|
| 1.5403 | 1.0 | 250 | 1.3422 | 0.554 |
| 1.1641 | 2.0 | 500 | 0.9492 | 0.6855 |
| 0.8396 | 3.0 | 750 | 0.6949 | 0.796 |
| 0.6356 | 4.0 | 1000 | 0.5556 | 0.8485 |
| 0.517 | 5.0 | 1250 | 0.4748 | 0.868 |
| 0.4351 | 6.0 | 1500 | 0.4231 | 0.8845 |
| 0.393 | 7.0 | 1750 | 0.3877 | 0.8875 |
| 0.3641 | 8.0 | 2000 | 0.3767 | 0.891 |
| 0.3462 | 9.0 | 2250 | 0.3621 | 0.8925 |
| 0.3352 | 10.0 | 2500 | 0.3583 | 0.893 |
Framework versions
- Transformers 4.34.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.14.5
- Tokenizers 0.14.1