VideoMAE_LSA64_SR_24

This model is a fine-tuned version of facebook/timesformer-base-finetuned-k400 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 3.9814
• Accuracy: 0.1420
• Precision: 0.1355
• Recall: 0.1420
• F1: 0.1108

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: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• training_steps: 180
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
No log	0.5	90	4.2701	0.0621	0.0412	0.0621	0.0295
4.5197	1.4986	180	3.9814	0.1420	0.1355	0.1420	0.1108

Framework versions

• Transformers 4.44.0
• Pytorch 1.11.0+cu102
• Datasets 2.21.0
• Tokenizers 0.19.1