scottstraley/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: 9.8084
• Train Accuracy: 0.0127
• Validation Loss: 9.7129
• Validation Accuracy: 0.0193
• 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
10.1131	0.0	10.0946	0.0	0
10.1119	0.0000	10.0847	0.0000	1
10.0955	0.0000	10.0555	0.0	2
10.0728	0.0000	10.0198	0.0000	3
10.0387	0.0000	9.9787	0.0001	4
9.9932	0.0003	9.9219	0.0014	5
9.9340	0.0013	9.8544	0.0074	6
9.8769	0.0053	9.7895	0.0149	7
9.8084	0.0127	9.7129	0.0193	8

Framework versions

• Transformers 4.34.0
• TensorFlow 2.12.0
• Tokenizers 0.14.0