metadata
tags:
- generated_from_trainer
datasets:
- emotion
metrics:
- accuracy
model-index:
- name: hbertv1-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: 0.878
hbertv1-emotion
This model is a fine-tuned version of gokuls/bert_12_layer_model_v1_complete_training_new on the emotion dataset. It achieves the following results on the evaluation set:
- Loss: 0.4392
- Accuracy: 0.878
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 |
|---|---|---|---|---|
| 1.4254 | 1.0 | 250 | 1.1571 | 0.5605 |
| 0.8603 | 2.0 | 500 | 0.7146 | 0.766 |
| 0.5736 | 3.0 | 750 | 0.5400 | 0.8185 |
| 0.4001 | 4.0 | 1000 | 0.4847 | 0.8495 |
| 0.3364 | 5.0 | 1250 | 0.4396 | 0.8755 |
| 0.2893 | 6.0 | 1500 | 0.4330 | 0.8745 |
| 0.2473 | 7.0 | 1750 | 0.4415 | 0.869 |
| 0.2128 | 8.0 | 2000 | 0.4228 | 0.876 |
| 0.1817 | 9.0 | 2250 | 0.4392 | 0.878 |
| 0.1608 | 10.0 | 2500 | 0.4441 | 0.877 |
Framework versions
- Transformers 4.30.2
- Pytorch 1.14.0a0+410ce96
- Datasets 2.13.0
- Tokenizers 0.13.3