BxSD_RGBCROP_Aug16F-8B16F5e6-poly

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: 0.0955
• Accuracy: 0.9590

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-06
• 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: polynomial
• lr_scheduler_warmup_ratio: 0.1
• training_steps: 1338

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.471	0.0837	112	0.5656	0.7552
0.1906	1.0837	224	0.2483	0.9219
0.0302	2.0837	336	0.2156	0.9635
0.036	3.0837	448	0.2428	0.9531
0.0017	4.0837	560	0.2467	0.9531
0.0012	5.0837	672	0.2768	0.9427
0.0009	6.0837	784	0.2685	0.9531

Framework versions

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