ALL_NoCrop_ori16F-4B16F

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: 0.9942
• Accuracy: 0.7530

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: 4
• eval_batch_size: 4
• 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: 2880

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.5179	0.0670	193	0.5087	0.7378
0.4627	1.0670	386	0.4823	0.7683
0.6973	2.0670	579	0.6752	0.7256
0.6745	3.0670	772	1.7145	0.6585
0.4488	4.0670	965	0.7915	0.7988
0.0054	5.0670	1158	1.2858	0.7805
0.2292	6.0670	1351	1.0276	0.75
0.0718	7.0670	1544	1.1518	0.7622

Framework versions

• Transformers 4.51.3
• Pytorch 2.6.0+cu124
• Datasets 2.14.4
• Tokenizers 0.21.1