videomae-base-finetuned-stroke-classification

This model is a fine-tuned version of MCG-NJU/videomae-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.2815
• Accuracy: 0.9121

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: 24
• eval_batch_size: 24
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• training_steps: 495

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.1054	0.2020	100	0.7669	0.7406
0.7821	1.2020	200	0.6999	0.7198
0.4114	2.2020	300	0.4544	0.8075
0.3292	3.2020	400	0.3396	0.8698
0.2806	4.1919	495	0.2993	0.8830

Framework versions

• Transformers 4.47.1
• Pytorch 2.5.1+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0