RALL_NoCrop_ori32F-8B32F

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

• Loss: 0.6057
• Accuracy: 0.7651

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: 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: 1152

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.5687	0.0842	97	0.5752	0.6768
0.6119	1.0842	194	0.6053	0.6585
0.5384	2.0842	291	0.6051	0.6890
0.3456	3.0842	388	0.6302	0.75
0.2481	4.0842	485	0.8713	0.7012
0.1551	5.0842	582	1.2408	0.7195
0.2597	6.0842	679	1.1164	0.6890

Framework versions

• Transformers 4.51.3
• Pytorch 2.6.0+cu124
• Datasets 3.6.0
• Tokenizers 0.21.1