videomae-base-ASD_Behavour_v4

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: 1.1278
• Accuracy: 0.4286

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
• lr_scheduler_warmup_ratio: 0.1
• training_steps: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	0.2	2	1.0695	0.2807
No log	1.2	4	1.0094	0.4211
No log	2.2	6	1.0282	0.3509
No log	3.2	8	1.0082	0.5439
1.0729	4.2	10	1.0134	0.5439

Framework versions

• Transformers 4.41.0
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1