You can deploy this model and start earning money today!

TanAlexanderlz/
RALL_RGBCROP_Aug16F-8B16F

Name: RALL_RGBCROP_Aug16F-8B16F
Availability: InStock

Views

No views yet

RALL_RGBCROP_Aug16F-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:

More information needed

More information needed

More information needed

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: 4616

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.2671	0.0626	289	0.5154	0.8200
0.1487	1.0626	578	0.8120	0.8364
0.0851	2.0626	867	0.9146	0.8569
0.0015	3.0626	1156	1.1018	0.8344
0.0001	4.0626	1445	1.2589	0.8364
0.0163	5.0626	1734	1.2502	0.8241
0.0001	6.0626	2023	1.4946	0.7996
0.0002	7.0626	2312	1.3088	0.8323