8_CTMAE_1

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

• Loss: 0.7375
• Accuracy: 0.8696

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: 1e-05
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• optimizer: Use 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: 21900

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.5188	0.02	438	0.6840	0.4783
0.5068	1.02	876	2.8475	0.4565
1.8316	2.02	1314	1.5493	0.4565
0.5219	3.02	1752	2.8128	0.4565
1.1618	4.02	2190	1.0596	0.5435
1.5861	5.02	2628	1.9090	0.4565
0.7609	6.02	3066	2.0779	0.4565
0.3447	7.02	3504	1.0396	0.5435
1.1399	8.02	3942	1.7504	0.4565
1.6307	9.02	4380	1.5973	0.4565
0.0175	10.02	4818	2.4790	0.4565
0.2556	11.02	5256	1.4058	0.4565
0.3923	12.02	5694	0.7601	0.5435
1.1171	13.02	6132	1.1797	0.5435
0.351	14.02	6570	1.6103	0.4783
1.0928	15.02	7008	0.5065	0.7826
0.5417	16.02	7446	1.1772	0.6957
0.0031	17.02	7884	1.7810	0.6087
0.0262	18.02	8322	0.8326	0.7174
0.0069	19.02	8760	0.7989	0.7174
0.002	20.02	9198	1.3372	0.6957
0.0023	21.02	9636	1.0854	0.7391
1.0456	22.02	10074	1.8901	0.6739
1.2039	23.02	10512	1.5616	0.6957
0.5863	24.02	10950	2.0744	0.6087
0.0015	25.02	11388	1.6195	0.6957
0.5301	26.02	11826	1.3184	0.6957
0.0041	27.02	12264	2.4978	0.5652
1.1867	28.02	12702	0.7375	0.8696
1.0796	29.02	13140	1.2784	0.7391
0.4999	30.02	13578	0.6682	0.8696
0.0737	31.02	14016	0.8525	0.7826
0.2811	32.02	14454	0.8788	0.8261
0.197	33.02	14892	1.0332	0.7826
0.0005	34.02	15330	1.1382	0.8043
0.0006	35.02	15768	3.0701	0.5435
0.0007	36.02	16206	1.7615	0.6304
0.0006	37.02	16644	2.2577	0.6522
0.0004	38.02	17082	1.1589	0.7609
0.0006	39.02	17520	1.0367	0.8043
0.0005	40.02	17958	2.3663	0.6522
0.0003	41.02	18396	2.4580	0.6522
0.0005	42.02	18834	1.7281	0.6957
0.0	43.02	19272	1.2404	0.8043
0.424	44.02	19710	2.6335	0.6522
0.0002	45.02	20148	2.4237	0.6304
0.0002	46.02	20586	2.5241	0.6522
0.0001	47.02	21024	2.1765	0.6522
0.0001	48.02	21462	2.2171	0.6739
0.0001	49.02	21900	2.4228	0.6304

Framework versions

• Transformers 4.46.2
• Pytorch 2.0.1+cu117
• Datasets 3.0.1
• Tokenizers 0.20.0