swin-finetuned-class_mi_a4c

This model is a fine-tuned version of microsoft/swin-base-patch4-window7-224 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 187691964027097262850048.0000
• Accuracy: 0.4324

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: 0.001
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: reduce_lr_on_plateau
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	0.84	4	187691964027097262850048.0000	0.4324
No log	1.89	9	187691964027097262850048.0000	0.4324
197383793291431707148288.0000	2.95	14	187691964027097262850048.0000	0.4324
197383793291431707148288.0000	4.0	19	187691964027097262850048.0000	0.4324
201517492465567910592512.0000	4.84	23	187691964027097262850048.0000	0.4324
201517492465567910592512.0000	5.89	28	187691964027097262850048.0000	0.4324
190149859368370083725312.0000	6.95	33	187691964027097262850048.0000	0.4324
190149859368370083725312.0000	8.0	38	187691964027097262850048.0000	0.4324
203584363669914227048448.0000	8.42	40	187691964027097262850048.0000	0.4324

Framework versions

• Transformers 4.36.2
• Pytorch 2.1.2+cu118
• Datasets 2.15.0
• Tokenizers 0.15.0