mbordes/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: 9.8611
• Train Accuracy: 0.0090
• Validation Loss: 9.7448
• Validation Accuracy: 0.0214
• Epoch: 8

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': {'class_name': 'WarmUp', 'config': {'initial_learning_rate': 0.0001, 'decay_schedule_fn': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 0.0001, 'decay_steps': 22325, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'passive_serialization': True}, 'warmup_steps': 1175, 'power': 1.0, 'name': None}}, '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
10.1794	0.0	10.1765	0.0	0
10.1802	0.0	10.1664	0.0	1
10.1601	0.0	10.1314	0.0	2
10.1402	0.0	10.0929	0.0000	3
10.0994	0.0000	10.0454	0.0000	4
10.0484	0.0000	9.9790	0.0003	5
9.9974	0.0003	9.9065	0.0025	6
9.9256	0.0023	9.8325	0.0130	7
9.8611	0.0090	9.7448	0.0214	8

Framework versions

• Transformers 4.33.1
• TensorFlow 2.12.0
• Tokenizers 0.13.3