RALL_RGBCROP_Aug16F-8B16F-GAS2

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: 0.6292
• Accuracy: 0.8313

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: 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
0.674	0.0416	144	0.6724	0.5992
0.4276	1.0416	288	0.5237	0.7382
0.1985	2.0416	432	0.4801	0.7894
0.0936	3.0416	576	0.5362	0.7955
0.0158	4.0416	720	0.6658	0.8016
0.0053	5.0416	864	0.7523	0.8119
0.0017	6.0416	1008	0.8297	0.8180
0.0008	7.0416	1152	0.9022	0.8180
0.0005	8.0416	1296	0.9299	0.8016
0.0004	9.0416	1440	0.9876	0.8078
0.0003	10.0416	1584	0.9774	0.8160

Framework versions

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