cancerfarore/distilbert-base-uncased-CancerFarore-Model

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

• Train Loss: 0.1390
• Train End Logits Accuracy: 0.9575
• Train Start Logits Accuracy: 0.9540
• Validation Loss: 2.8433
• Validation End Logits Accuracy: 0.5442
• Validation Start Logits Accuracy: 0.5303
• 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': 2e-05, 'decay_steps': 18960, '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 Accuracy	Train Start Logits Accuracy	Validation Loss	Validation End Logits Accuracy	Validation Start Logits Accuracy	Epoch
2.1257	0.4290	0.4152	1.4687	0.5228	0.5239	0
1.3124	0.5968	0.5795	1.3553	0.5747	0.5676	1
0.9498	0.7047	0.6820	1.5003	0.5566	0.5457	2
0.6828	0.7854	0.7654	1.8131	0.5393	0.5111	3
0.4912	0.8458	0.8307	1.7845	0.5687	0.5638	4
0.3512	0.8906	0.8756	2.2275	0.5397	0.5258	5
0.2676	0.9146	0.9054	2.4911	0.5401	0.5216	6
0.2044	0.9372	0.9289	2.5377	0.5551	0.5390	7
0.1633	0.9480	0.9440	2.7288	0.5548	0.5412	8
0.1390	0.9575	0.9540	2.8433	0.5442	0.5303	9

Framework versions

• Transformers 4.40.1
• TensorFlow 2.15.0
• Datasets 2.19.0
• Tokenizers 0.19.1