vit-cc-512-birads

This model is a fine-tuned version of on the preprocessed1024_config dataset. It achieves the following results on the evaluation set:

• Loss: 1.1133
• Accuracy: {'accuracy': 0.4943467336683417}
• F1: {'f1': 0.3929699341372617}

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:

• learning_rate: 5e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
1.1037	1.0	796	1.0357	{'accuracy': 0.4748743718592965}	{'f1': 0.21465076660988078}
1.0588	2.0	1592	1.0446	{'accuracy': 0.4623115577889447}	{'f1': 0.33094476503399495}
1.0486	3.0	2388	1.0408	{'accuracy': 0.47361809045226133}	{'f1': 0.3313643442345453}
1.0288	4.0	3184	1.0186	{'accuracy': 0.5050251256281407}	{'f1': 0.3404676010455165}
1.0284	5.0	3980	1.0288	{'accuracy': 0.5037688442211056}	{'f1': 0.3406391773730375}
0.997	6.0	4776	1.0183	{'accuracy': 0.5087939698492462}	{'f1': 0.3539488153998284}
0.9682	7.0	5572	1.0965	{'accuracy': 0.4566582914572864}	{'f1': 0.3695106771946128}
0.9313	8.0	6368	1.0554	{'accuracy': 0.4962311557788945}	{'f1': 0.38158088397057704}
0.8938	9.0	7164	1.0930	{'accuracy': 0.4943467336683417}	{'f1': 0.38196414933207573}
0.8697	10.0	7960	1.1133	{'accuracy': 0.4943467336683417}	{'f1': 0.3929699341372617}

Framework versions

• Transformers 4.20.1
• Pytorch 1.12.0
• Datasets 2.1.0
• Tokenizers 0.12.1