RALL_NoCrop_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: 1.0091
• Accuracy: 0.7751

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: 4616

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.4546	0.0626	289	0.5467	0.7566
0.2899	1.0626	578	0.7078	0.7157
0.1739	2.0626	867	0.8752	0.7771
0.1227	3.0626	1156	0.7922	0.7710
0.1752	4.0626	1445	1.0169	0.7812
0.1473	5.0626	1734	0.9909	0.7587
0.2319	6.0626	2023	1.3500	0.7444
0.0379	7.0626	2312	1.1374	0.7771
0.0109	8.0626	2601	1.2297	0.7628
0.0514	9.0626	2890	1.2982	0.7751

Framework versions

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