RALL_NoCrop_Aug16F-8B16F-GACWDlr

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: 0.8643
• Accuracy: 0.8032

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
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• 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: 3462

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.6327	0.0416	144	0.6327	0.6299
0.4228	1.0416	288	0.5300	0.7464
0.2855	2.0416	432	0.5658	0.7648
0.2789	3.0416	576	0.5733	0.7587
0.237	4.0416	720	0.7180	0.7628
0.1125	5.0416	864	0.7992	0.7710
0.0921	6.0416	1008	0.8145	0.7669
0.1423	7.0416	1152	0.9354	0.7648
0.1307	8.0416	1296	0.9036	0.7648
0.0479	9.0416	1440	1.1271	0.7730
0.0724	10.0416	1584	1.0805	0.7669
0.1424	11.0416	1728	1.0949	0.7669
0.0577	12.0416	1872	1.1183	0.7730
0.1258	13.0416	2016	1.0614	0.7914
0.0271	14.0416	2160	1.1381	0.7771
0.0557	15.0416	2304	1.2154	0.7587
0.054	16.0416	2448	1.1568	0.7710
0.1001	17.0416	2592	1.1639	0.7853
0.0401	18.0416	2736	1.1892	0.7812

Framework versions

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