CTMAE-P2-V4-S5

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: 1.9568
• Accuracy: 0.6889

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
0.6674	0.0202	131	0.8697	0.5556
0.4329	1.0202	262	2.0814	0.5556
1.1234	2.0202	393	1.8388	0.5556
0.6448	3.0202	524	0.8365	0.5556
1.422	4.0202	655	1.5742	0.5556
0.8229	5.0202	786	1.4841	0.5556
1.0158	6.0202	917	1.6325	0.5556
1.5449	7.0202	1048	1.0645	0.5556
0.7285	8.0202	1179	1.6570	0.5556
1.0003	9.0202	1310	1.3149	0.5556
0.6923	10.0202	1441	1.4487	0.5556
0.6469	11.0202	1572	1.5096	0.5556
0.6441	12.0202	1703	0.6743	0.5778
1.3927	13.0202	1834	1.5688	0.5556
0.7324	14.0202	1965	1.8057	0.5556
0.8535	15.0202	2096	0.9958	0.5556
0.6217	16.0202	2227	1.8299	0.5556
0.6316	17.0202	2358	0.9438	0.5778
0.6872	18.0202	2489	1.0891	0.5111
1.5154	19.0202	2620	1.5606	0.5778
0.5531	20.0202	2751	2.0657	0.5111
0.4864	21.0202	2882	1.5141	0.5778
1.0543	22.0202	3013	1.6743	0.5333
1.4812	23.0202	3144	1.6335	0.5111
0.5504	24.0202	3275	2.0608	0.5778
0.0955	25.0202	3406	2.5849	0.5111
0.4181	26.0202	3537	1.5860	0.5778
0.0738	27.0202	3668	1.9424	0.6
0.2064	28.0202	3799	1.8362	0.6667
0.2696	29.0202	3930	2.2124	0.5111
0.5201	30.0202	4061	1.8246	0.6444
0.3376	31.0202	4192	1.9568	0.6889
0.2752	32.0202	4323	1.7191	0.6667
0.2664	33.0202	4454	2.6353	0.5778
0.641	34.0202	4585	2.3520	0.5778
0.9121	35.0202	4716	2.0164	0.5556
0.1392	36.0202	4847	2.5261	0.5778
0.3777	37.0202	4978	2.2239	0.5778
0.0005	38.0202	5109	2.4557	0.5778
0.3699	39.0202	5240	2.6679	0.5333
0.1673	40.0202	5371	2.7295	0.5778
0.2676	41.0202	5502	2.5027	0.5778
0.0822	42.0202	5633	2.8017	0.5556
0.2881	43.0202	5764	2.9313	0.5556
0.364	44.0202	5895	2.7614	0.5333
0.3917	45.0202	6026	2.7807	0.5111
0.0007	46.0202	6157	2.7458	0.5333
0.0582	47.0202	6288	2.7683	0.5556
0.6675	48.0202	6419	2.8154	0.5556
0.0003	49.0125	6500	2.8304	0.5556

Framework versions

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