MartaCaldero/my_qa_model

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

• Train Loss: 7.1003
• Train End Logits Loss: 3.5430
• Train Start Logits Loss: 3.5573
• Validation Loss: 8.6083
• Validation End Logits Loss: 4.4272
• Validation Start Logits Loss: 4.1811
• Epoch: 6

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': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 500, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_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 Loss	Train Start Logits Loss	Validation Loss	Validation End Logits Loss	Validation Start Logits Loss	Epoch
7.1272	3.5735	3.5536	8.6083	4.4272	4.1811	0
7.3166	3.6143	3.7022	8.6083	4.4272	4.1811	1
7.2145	3.6057	3.6088	8.6083	4.4272	4.1811	2
7.1072	3.5426	3.5647	8.6083	4.4272	4.1811	3
6.9873	3.4903	3.4970	8.6083	4.4272	4.1811	4
7.1691	3.5943	3.5748	8.6083	4.4272	4.1811	5
7.1003	3.5430	3.5573	8.6083	4.4272	4.1811	6

Framework versions

• Transformers 4.37.2
• TensorFlow 2.15.0
• Datasets 2.17.1
• Tokenizers 0.15.2