ALL_NoCrop-ori16F-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: 0.4182
• Accuracy: 0.7831

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: 1440

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.5284	0.0674	97	0.5177	0.7561
0.4921	1.0674	194	0.4888	0.7561
0.4334	2.0674	291	0.4794	0.7744
0.2418	3.0674	388	0.6367	0.7805
0.1772	4.0674	485	0.7765	0.7805
0.1463	5.0674	582	1.0245	0.7744
0.1325	6.0674	679	0.8800	0.7927
0.1072	7.0674	776	0.8241	0.8171
0.0076	8.0674	873	0.9926	0.8049
0.0393	9.0674	970	0.9313	0.7866
0.0317	10.0674	1067	0.8819	0.8049
0.1591	11.0674	1164	1.0891	0.7988
0.1017	12.0674	1261	1.0671	0.8110

Framework versions

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