RALL_RGBmasking_Aug16F-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: 1.3708
• 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: 3372

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.3794	0.0836	282	0.7830	0.7583
0.1014	1.0836	564	0.9172	0.8083
0.1098	2.0836	846	1.1630	0.8146
0.0009	3.0836	1128	1.3165	0.7979
0.0	4.0836	1410	1.3770	0.8063
0.0	5.0836	1692	1.2123	0.8313
0.0	6.0836	1974	1.3553	0.8208
0.0	7.0836	2256	1.4654	0.8208
0.0	8.0836	2538	1.3937	0.8208
0.0	9.0836	2820	1.4304	0.8292

Framework versions

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