yungshun317/albert-base-v2-finetuned-squad

This model is a fine-tuned version of albert-base-v2 on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 0.5387
• Train End Logits Accuracy: 0.8432
• Train Start Logits Accuracy: 0.8032
• Validation Loss: 0.9026
• Validation End Logits Accuracy: 0.7573
• Validation Start Logits Accuracy: 0.7216
• 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': 11076, '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
1.0125	0.7282	0.6871	0.8959	0.7528	0.7098	0
0.7015	0.7988	0.7582	0.8625	0.7586	0.7206	1
0.5387	0.8432	0.8032	0.9026	0.7573	0.7216	2

Framework versions

• Transformers 4.31.0
• TensorFlow 2.12.0
• Datasets 2.14.0
• Tokenizers 0.13.3