You can deploy this model and start earning money today!

TanAlexanderlz/
ALL_RGBCROP_ori16F-8B16F-GACWDlrfp16

Name: ALL_RGBCROP_ori16F-8B16F-GACWDlrfp16
Availability: InStock

Views

No views yet

ALL_RGBCROP_ori16F-8B16F-GACWDlrfp16

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: 16
eval_batch_size: 16
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 32
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: 384
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.6923	0.0625	24	0.6734	0.6037
0.6078	1.0625	48	0.6133	0.6829
0.4025	2.0625	72	0.5369	0.75
0.2942	3.0625	96	0.4767	0.7927
0.171	4.0625	120	0.4655	0.7927
0.1159	5.0625	144	0.4691	0.8110
0.0592	6.0625	168	0.5043	0.7927
0.0371	7.0625	192	0.5547	0.7927
0.0205	8.0625	216	0.5886	0.7988
0.013	9.0625	240	0.6280	0.7988
0.0062	10.0625	264	0.6809	0.7927
0.0052	11.0625	288	0.6715	0.7866
0.0041	12.0625	312	0.6975	0.8049
0.0038	13.0625	336	0.7200	0.7988
0.003	14.0625	360	0.7230	0.8049
0.0032	15.0625	384	0.7239	0.8049