You can deploy this model and start earning money today!

TanAlexanderlz/
ALL_RGBCROP_ori16F-8B16F-GACWDlrDO_saja

Name: ALL_RGBCROP_ori16F-8B16F-GACWDlrDO_saja
Availability: InStock

Views

No views yet

ALL_RGBCROP_ori16F-8B16F-GACWDlrDO_saja

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:

More information needed

More information needed

More information needed

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: 1920

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.7426	0.025	48	0.7046	0.4695
0.648	1.025	96	0.6739	0.5427
0.5216	2.025	144	0.6081	0.7073
0.3679	3.025	192	0.5210	0.7378
0.2164	4.025	240	0.4877	0.7744
0.123	5.025	288	0.5468	0.7927
0.1269	6.025	336	0.6361	0.7866
0.0723	7.025	384	0.7136	0.7744
0.0616	8.025	432	0.7359	0.7805
0.0168	9.025	480	0.8053	0.7927
0.0019	10.025	528	0.9154	0.75