metadata

license: mit
tags:
  - generated_from_keras_callback
base_model: nlptown/bert-base-multilingual-uncased-sentiment
model-index:
  - name: tmp9770t4k0
    results: []

tmp9770t4k0

This model is a fine-tuned version of nlptown/bert-base-multilingual-uncased-sentiment on an muchocine dataset. It achieves the following results on the evaluation set:

Train Loss: 0.6629
Train Accuracy: 0.7345
Validation Loss: 1.4827
Validation Accuracy: 0.5
Epoch: 2

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:

optimizer: {'name': 'Adam', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5e-05, 'decay_steps': 1305, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
training_precision: float32

Training results

Train Loss	Train Accuracy	Validation Loss	Validation Accuracy	Epoch
1.3718	0.3908	1.2647	0.4381	0
1.0808	0.5330	1.2672	0.4742	1
0.6629	0.7345	1.4827	0.5	2

Framework versions

Transformers 4.17.0
TensorFlow 2.8.0
Datasets 1.18.4
Tokenizers 0.11.6