metadata
license: apache-2.0
base_model: google/bert_uncased_L-2_H-768_A-12
tags:
- generated_from_trainer
datasets:
- emotion
metrics:
- accuracy
model-index:
- name: bert_uncased_L-2_H-768_A-12_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: 0.938
bert_uncased_L-2_H-768_A-12_emotion
This model is a fine-tuned version of google/bert_uncased_L-2_H-768_A-12 on the emotion dataset. It achieves the following results on the evaluation set:
- Loss: 0.1647
- Accuracy: 0.938
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 |
|---|---|---|---|---|
| 0.7509 | 1.0 | 250 | 0.2324 | 0.9185 |
| 0.202 | 2.0 | 500 | 0.1814 | 0.932 |
| 0.1333 | 3.0 | 750 | 0.1571 | 0.9335 |
| 0.0995 | 4.0 | 1000 | 0.1647 | 0.938 |
| 0.0807 | 5.0 | 1250 | 0.1822 | 0.9355 |
| 0.0635 | 6.0 | 1500 | 0.1938 | 0.9325 |
| 0.0486 | 7.0 | 1750 | 0.2061 | 0.929 |
| 0.0407 | 8.0 | 2000 | 0.2191 | 0.933 |
| 0.035 | 9.0 | 2250 | 0.2238 | 0.9325 |
| 0.0277 | 10.0 | 2500 | 0.2254 | 0.9325 |
Framework versions
- Transformers 4.34.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.14.5
- Tokenizers 0.14.1