UCF_RGBCROP_Aug16F-8B16F5e6-poly

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: 0.5897
• Accuracy: 0.6944

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: 1e-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: polynomial
• lr_scheduler_warmup_ratio: 0.1
• training_steps: 345

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.6487	0.0696	24	0.6481	0.6905
0.4769	1.0696	48	0.5468	0.8095
0.1566	2.0696	72	0.4007	0.8333
0.0663	3.0696	96	0.2994	0.9524
0.0157	4.0696	120	0.2464	0.9286
0.0083	5.0696	144	0.2180	0.9048
0.0065	6.0696	168	0.3374	0.8333
0.0038	7.0696	192	0.2530	0.9286
0.0028	8.0696	216	0.2294	0.9286

Framework versions

• Transformers 4.52.2
• Pytorch 2.6.0+cu124
• Datasets 2.14.4
• Tokenizers 0.21.1