metadata
base_model: gokuls/HBERTv1_48_L12_H768_A12
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: HBERTv1_48_L12_H768_A12_emotion_data_augmented
results: []
HBERTv1_48_L12_H768_A12_emotion_data_augmented
This model is a fine-tuned version of gokuls/HBERTv1_48_L12_H768_A12 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4277
- Accuracy: 0.88
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 |
|---|---|---|---|---|
| 0.9265 | 1.0 | 6263 | 0.4277 | 0.88 |
| 0.7151 | 2.0 | 12526 | 0.4159 | 0.8635 |
| 0.6212 | 3.0 | 18789 | 0.5183 | 0.834 |
| 0.5546 | 4.0 | 25052 | 0.5582 | 0.8195 |
| 0.5051 | 5.0 | 31315 | 0.5870 | 0.8115 |
| 0.4628 | 6.0 | 37578 | 0.6372 | 0.799 |
| 0.4238 | 7.0 | 43841 | 0.7019 | 0.7875 |
| 0.3903 | 8.0 | 50104 | 0.7577 | 0.7875 |
| 0.3602 | 9.0 | 56367 | 0.7970 | 0.7805 |
| 0.3378 | 10.0 | 62630 | 0.8298 | 0.776 |
Framework versions
- Transformers 4.34.1
- Pytorch 1.14.0a0+410ce96
- Datasets 2.14.6
- Tokenizers 0.14.1