RALL_RGBCROP_Aug16F-4B16F-GAS2

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: 0.5824
• Accuracy: 0.8454

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
• gradient_accumulation_steps: 2
• total_train_batch_size: 8
• 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
0.602	0.0417	289	0.6002	0.6973
0.2869	1.0417	578	0.4509	0.7853
0.0886	2.0417	867	0.6011	0.7975
0.0751	3.0417	1156	0.7906	0.8200
0.0016	4.0417	1445	0.9630	0.8160
0.0007	5.0417	1734	1.0932	0.8078
0.0004	6.0417	2023	1.1611	0.8037
0.0002	7.0417	2312	1.1706	0.8119

Framework versions

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