vnktrmnb/bert-base-multilingual-cased-finetuned-TyDiQA-GoldP_Te

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: 0.3152
• Train End Logits Accuracy: 0.9004
• Train Start Logits Accuracy: 0.9263
• Validation Loss: 0.4931
• Validation End Logits Accuracy: 0.8686
• Validation Start Logits Accuracy: 0.9162
• Epoch: 2

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': 2e-05, 'decay_steps': 1359, '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	Train End Logits Accuracy	Train Start Logits Accuracy	Validation Loss	Validation End Logits Accuracy	Validation Start Logits Accuracy	Epoch
0.7083	0.7903	0.8387	0.4992	0.8505	0.8892	0
0.4552	0.8584	0.8957	0.4905	0.8686	0.8995	1
0.3152	0.9004	0.9263	0.4931	0.8686	0.9162	2

Framework versions

• Transformers 4.31.0
• TensorFlow 2.12.0
• Datasets 2.14.4
• Tokenizers 0.13.3