CTMAE-P2-V2-S2

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: 1.5069
• Accuracy: 0.7333

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: 2
• eval_batch_size: 2
• 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: 6500

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.6135	0.0202	131	0.7942	0.5556
0.4654	1.0202	262	2.2124	0.5556
1.1122	2.0202	393	1.8386	0.5556
0.7797	3.0202	524	0.9344	0.5556
1.379	4.0202	655	1.5755	0.5556
0.7305	5.0202	786	1.4677	0.5556
0.9115	6.0202	917	1.5456	0.5556
1.6622	7.0202	1048	1.2113	0.5556
0.6868	8.0202	1179	1.8451	0.5556
1.199	9.0202	1310	1.3622	0.5556
0.7459	10.0202	1441	1.4034	0.5556
0.5574	11.0202	1572	0.9836	0.5556
0.3742	12.0202	1703	0.6934	0.6889
0.3303	13.0202	1834	0.7161	0.6889
0.8856	14.0202	1965	1.5608	0.5556
0.186	15.0202	2096	0.7782	0.6
0.7263	16.0202	2227	1.4438	0.5778
1.552	17.0202	2358	1.2117	0.6222
0.1031	18.0202	2489	1.2174	0.6667
1.193	19.0202	2620	1.2043	0.6444
0.322	20.0202	2751	1.3639	0.6444
0.3791	21.0202	2882	1.3107	0.6444
0.6201	22.0202	3013	1.2797	0.6889
0.9547	23.0202	3144	1.1654	0.6444
1.4286	24.0202	3275	1.4078	0.6667
0.6023	25.0202	3406	1.5069	0.7333
0.2925	26.0202	3537	1.4529	0.6889
0.1445	27.0202	3668	1.4417	0.7333
0.2717	28.0202	3799	2.1237	0.6444
0.411	29.0202	3930	1.5399	0.6889
0.6632	30.0202	4061	1.6289	0.7333
0.3	31.0202	4192	1.9944	0.6222
0.386	32.0202	4323	1.9271	0.6889
0.1569	33.0202	4454	1.8172	0.6889
0.2135	34.0202	4585	1.7862	0.6889
0.3142	35.0202	4716	1.6904	0.7111
0.2179	36.0202	4847	1.9549	0.7111
0.7634	37.0202	4978	1.9367	0.6889
0.0008	38.0202	5109	1.9890	0.6667
0.1467	39.0202	5240	1.9472	0.6889
0.6641	40.0202	5371	2.2295	0.6889
0.3125	41.0202	5502	1.8309	0.7111
0.1987	42.0202	5633	2.1643	0.6889
0.067	43.0202	5764	2.1776	0.6667
0.1513	44.0202	5895	2.1978	0.6667
0.0032	45.0202	6026	1.9291	0.7333
0.2596	46.0202	6157	2.0961	0.6889
0.0006	47.0202	6288	2.0126	0.7111
0.0305	48.0202	6419	2.0029	0.7333
0.0004	49.0125	6500	2.0025	0.7333

Framework versions

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