mimic-cxr-swin-large-patch4-window12-384-test

This model is a fine-tuned version of microsoft/swin-base-patch4-window12-384 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.2415
• F1: 0.0

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: 16
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	F1
0.4807	0.9524	15	0.2439	0.0
0.3154	1.9683	31	0.2422	0.0
0.2564	2.8571	45	0.2415	0.0

Framework versions

• Transformers 4.40.2
• Pytorch 2.1.2
• Datasets 3.0.2
• Tokenizers 0.19.1