pmfsl/mbert-base-finetuned-pt_br-stsb

This model is a fine-tuned version of bert-base-multilingual-cased on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 0.1085
• Validation Loss: 0.2331
• Train Pearsonr: 0.8853
• Epoch: 4

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', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 4e-05, 'decay_steps': 2030, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
• training_precision: float32

Training results

Train Loss	Validation Loss	Train Pearsonr	Epoch
0.8113	0.4476	0.7836	0
0.2637	0.2973	0.8437	1
0.1819	0.2807	0.8646	2
0.1334	0.2370	0.8835	3
0.1085	0.2331	0.8853	4

Framework versions

• Transformers 4.27.4
• TensorFlow 2.12.0
• Datasets 2.11.0
• Tokenizers 0.13.2