ALL_NoCrop_ori16F-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: 0.5141
• 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: 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: 576

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.6471	0.0833	48	0.6523	0.6280
0.5835	1.0833	96	0.6113	0.6402
0.4729	2.0833	144	0.5240	0.75
0.3334	3.0833	192	0.4774	0.7561
0.3024	4.0833	240	0.4842	0.7866
0.2645	5.0833	288	0.5221	0.7988
0.22	6.0833	336	0.5060	0.7805
0.1833	7.0833	384	0.4942	0.7683
0.1854	8.0833	432	0.5156	0.7744

Framework versions

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