metadata
base_model: gokuls/HBERTv1_48_L6_H768_A12
tags:
- generated_from_trainer
datasets:
- emotion
metrics:
- accuracy
model-index:
- name: HBERTv1_48_L6_H768_A12_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: 0.899
HBERTv1_48_L6_H768_A12_emotion
This model is a fine-tuned version of gokuls/HBERTv1_48_L6_H768_A12 on the emotion dataset. It achieves the following results on the evaluation set:
- Loss: 0.5857
- Accuracy: 0.899
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 |
|---|---|---|---|---|
| 0.7645 | 1.0 | 250 | 0.4082 | 0.8735 |
| 0.2966 | 2.0 | 500 | 0.3378 | 0.88 |
| 0.2046 | 3.0 | 750 | 0.2953 | 0.8945 |
| 0.1491 | 4.0 | 1000 | 0.3497 | 0.892 |
| 0.1084 | 5.0 | 1250 | 0.3465 | 0.896 |
| 0.0789 | 6.0 | 1500 | 0.3917 | 0.893 |
| 0.0525 | 7.0 | 1750 | 0.4881 | 0.8945 |
| 0.0358 | 8.0 | 2000 | 0.5269 | 0.895 |
| 0.0243 | 9.0 | 2250 | 0.5646 | 0.896 |
| 0.0161 | 10.0 | 2500 | 0.5857 | 0.899 |
Framework versions
- Transformers 4.34.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.14.5
- Tokenizers 0.14.0