You can deploy this model and start earning money today!

TanAlexanderlz/
RALL_MVmasking_Aug16F-8B16F

Name: RALL_MVmasking_Aug16F-8B16F
Availability: InStock

Views

No views yet

RALL_MVmasking_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: 3372

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.6965	0.0836	282	0.7202	0.5271
0.6988	1.0836	564	0.6402	0.6167
0.5333	2.0836	846	0.7524	0.6042
0.4636	3.0836	1128	0.6086	0.6813
0.3029	4.0836	1410	0.7977	0.6646
0.5607	5.0836	1692	1.0321	0.675
0.1445	6.0836	1974	1.5924	0.7042
0.0248	7.0836	2256	1.6920	0.7104
0.0828	8.0836	2538	1.9414	0.7021
0.0002	9.0836	2820	2.0540	0.7167
0.0002	10.0836	3102	2.0828	0.7229
0.0001	11.0801	3372	2.1183	0.7083