RALL_RGBCROP_Aug16F-4B16F

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: 0.6635
• Accuracy: 0.8494

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-06
• train_batch_size: 4
• eval_batch_size: 4
• 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: 6930

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.3709	0.0834	578	0.5310	0.7444
0.1851	1.0834	1156	0.6812	0.7975
0.0015	2.0834	1734	0.9254	0.8180
0.0014	3.0834	2312	1.1273	0.8037
0.0001	4.0834	2890	1.2652	0.7975
0.0001	5.0834	3468	1.3945	0.7975
0.0001	6.0834	4046	1.3822	0.7955

Framework versions

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