BxSD_RGBCROP_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: 0.1426
• Accuracy: 0.9590

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: 2230

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.663	0.0251	56	0.6602	0.6354
0.4419	1.0251	112	0.4703	0.8125
0.1752	2.0251	168	0.3134	0.8906
0.0656	3.0251	224	0.2311	0.9375
0.0046	4.0251	280	0.2808	0.9427
0.0012	5.0251	336	0.2592	0.9427
0.0007	6.0251	392	0.2576	0.9479
0.0005	7.0251	448	0.2631	0.9479
0.0004	8.0251	504	0.2745	0.9479
0.0004	9.0251	560	0.2814	0.9479
0.0003	10.0251	616	0.2863	0.9479
0.0002	11.0251	672	0.2850	0.9479

Framework versions

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