videomae-base-finetuned-human-activity-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: 0.9059
• 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: 3
• eval_batch_size: 3
• 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: 32

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	0.28	9	0.7252	0.6
0.7894	1.28	18	0.9405	0.6
0.7118	2.28	27	0.8548	0.6
0.7359	3.16	32	0.8314	0.6

Framework versions

• Transformers 4.28.0
• Pytorch 2.0.1+cu117
• Datasets 2.14.4
• Tokenizers 0.13.3