hilariooliveira/masked-lm-tpu

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

• Train Loss: 9.7808
• Train Accuracy: 0.0207
• Validation Loss: 9.6495
• Validation Accuracy: 0.0228
• Epoch: 9

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': 'AdamWeightDecay', 'learning_rate': {'module': 'transformers.optimization_tf', 'class_name': 'WarmUp', 'config': {'initial_learning_rate': 0.0001, 'decay_schedule_fn': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 0.0001, 'decay_steps': 22325, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'warmup_steps': 1175, 'power': 1.0, 'name': None}, 'registered_name': 'WarmUp'}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.001}
• training_precision: float32

Training results

Train Loss	Train Accuracy	Validation Loss	Validation Accuracy	Epoch
10.2045	0.0	10.2003	0.0000	0
10.1943	0.0	10.1822	0.0000	1
10.1738	0.0	10.1600	0.0000	2
10.1437	0.0000	10.1127	0.0000	3
10.1132	0.0000	10.0591	0.0000	4
10.0693	0.0002	9.9996	0.0013	5
9.9967	0.0016	9.9315	0.0086	6
9.9369	0.0068	9.8311	0.0184	7
9.8456	0.0159	9.7517	0.0217	8
9.7808	0.0207	9.6495	0.0228	9

Framework versions

• Transformers 4.38.2
• TensorFlow 2.15.1
• Tokenizers 0.15.2