RALL_NoCrop-ori16F-8B16F

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: 0.7500
• Accuracy: 0.8012

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: 1920

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.565	0.0505	97	0.5722	0.7423
0.4674	1.0505	194	0.4892	0.7607
0.5498	2.0505	291	0.4520	0.7791
0.2932	3.0505	388	0.5798	0.7730
0.2242	4.0505	485	0.6877	0.7730
0.1464	5.0505	582	0.9031	0.7914
0.197	6.0505	679	0.8950	0.7730
0.1086	7.0505	776	1.2688	0.7730
0.0113	8.0505	873	1.2775	0.7730
0.0129	9.0505	970	1.1965	0.7853
0.1159	10.0505	1067	1.1686	0.7669

Framework versions

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