czgrqg/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: 9.8360
• Train Accuracy: 0.0136
• Validation Loss: 9.7388
• Validation Accuracy: 0.0224
• 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
10.2630	0.0	10.2679	0.0000	0
10.2651	0.0000	10.2533	0.0	1
10.2427	0.0	10.2191	0.0	2
10.2172	0.0	10.1916	0.0	3
10.1833	0.0	10.1358	0.0	4
10.1283	0.0	10.0764	0.0000	5
10.0660	0.0000	9.9998	0.0002	6
10.0045	0.0004	9.9291	0.0042	7
9.9230	0.0039	9.8491	0.0161	8
9.8360	0.0136	9.7388	0.0224	9

Framework versions

• Transformers 4.35.2
• TensorFlow 2.15.0
• Tokenizers 0.15.0