RALL_RGBCROP_Aug16F-16B16F

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: 0.3794
• Accuracy: 0.8273

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: 16
• eval_batch_size: 16
• 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: 1728

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.5554	0.0839	145	0.6132	0.6769
0.2656	1.0839	290	0.4692	0.7771
0.1142	2.0839	435	0.5119	0.8037
0.0509	3.0839	580	0.6926	0.7894
0.0295	4.0839	725	0.8195	0.7935
0.0036	5.0839	870	0.9101	0.8016
0.0143	6.0839	1015	0.9655	0.7975

Framework versions

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