medmcqa-distil-bert-based-uncased

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

• Train Loss: 0.1025
• Validation Loss: 4.4572
• Train Accuracy: 0.275
• 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': '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': 5e-05, 'decay_steps': 5000, '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	Validation Loss	Train Accuracy	Epoch
1.3835	1.3719	0.35	0
1.3589	1.3579	0.325	1
1.2628	1.4648	0.328	2
1.0069	1.5701	0.304	3
0.6441	2.3132	0.287	4
0.3951	2.8174	0.281	5
0.2386	3.6746	0.299	6
0.1708	4.0410	0.287	7
0.1358	4.2157	0.288	8
0.1025	4.4572	0.275	9

Framework versions

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