metadata
base_model: gokuls/bert_12_layer_model_v3_complete_training_48
tags:
- generated_from_trainer
datasets:
- emotion
metrics:
- accuracy
model-index:
- name: bert_12_layer_model_v3_48_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
bert_12_layer_model_v3_48_emotion
This model is a fine-tuned version of gokuls/bert_12_layer_model_v3_complete_training_48 on the emotion dataset. It achieves the following results on the evaluation set:
- Loss: 0.4023
- 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 |
|---|---|---|---|---|
| 0.9112 | 1.0 | 250 | 0.5176 | 0.8495 |
| 0.389 | 2.0 | 500 | 0.3617 | 0.8755 |
| 0.2894 | 3.0 | 750 | 0.3037 | 0.8905 |
| 0.2359 | 4.0 | 1000 | 0.3346 | 0.895 |
| 0.1883 | 5.0 | 1250 | 0.3178 | 0.8955 |
| 0.1638 | 6.0 | 1500 | 0.3597 | 0.897 |
| 0.1217 | 7.0 | 1750 | 0.4075 | 0.8895 |
| 0.0962 | 8.0 | 2000 | 0.4023 | 0.899 |
| 0.0732 | 9.0 | 2250 | 0.4479 | 0.8955 |
| 0.0569 | 10.0 | 2500 | 0.4894 | 0.8985 |
Framework versions
- Transformers 4.34.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.14.5
- Tokenizers 0.14.1