videomae-base-finetuned-gemep-epochs25 – AI Model by KG5KEY | AlphaNeural AI

You can deploy this model and start earning money today!

KG5KEY/
videomae-base-finetuned-gemep-epochs25

like

0

video-classification

generated_from_trainer

MCG-NJU/videomae-base

endpoints_compatible

Views

No views yet

videomae-base-finetuned-gemep-epochs25

This model is a fine-tuned version of MCG-NJU/videomae-base on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.4373
Accuracy: 0.9123

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-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
training_steps: 1350

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.7648	0.04	54	1.7458	0.2698
1.6977	1.04	108	1.5724	0.2698
1.5208	2.04	162	1.5350	0.2857
1.39	3.04	216	1.4793	0.4286
1.3546	4.04	270	1.7122	0.2857
0.9587	5.04	324	1.4137	0.3492
1.0259	6.04	378	1.2302	0.6190
0.7292	7.04	432	1.4772	0.3810
0.6499	8.04	486	1.0864	0.5873
0.5417	9.04	540	1.4085	0.4603
0.5073	10.04	594	1.5436	0.5556
0.5052	11.04	648	1.2583	0.6190
0.419	12.04	702	1.1921	0.6349
0.2677	13.04	756	1.0662	0.6825
0.1601	14.04	810	0.7688	0.7143
0.1784	15.04	864	1.2971	0.6508
0.1338	16.04	918	0.9488	0.7937
0.0875	17.04	972	1.0488	0.7619
0.0748	18.04	1026	0.9617	0.8095
0.0973	19.04	1080	1.0684	0.7460
0.0443	20.04	1134	1.0433	0.7778
0.0787	21.04	1188	0.8444	0.8254
0.0035	22.04	1242	1.1333	0.7778
0.0033	23.04	1296	0.9644	0.8095
0.0686	24.04	1350	0.9196	0.8254

Framework versions

Transformers 4.32.1
Pytorch 2.1.0
Datasets 2.12.0
Tokenizers 0.13.3