9_mae_6

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: 3.0307
• Accuracy: 0.5652

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: 4
• eval_batch_size: 4
• 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: 9700

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.6135	0.0201	195	0.7883	0.4565
0.5466	1.0201	390	1.0295	0.4565
0.6554	2.0201	585	0.7833	0.4565
0.7073	3.0201	780	0.7178	0.4565
1.0344	4.0201	975	0.7160	0.4130
1.3166	5.0201	1170	1.9701	0.4565
1.0289	6.0201	1365	0.8293	0.4565
0.6052	7.0201	1560	0.8509	0.5435
0.5896	8.0201	1755	0.9168	0.4783
0.4552	9.0201	1950	1.2763	0.4565
0.6413	10.0201	2145	0.7229	0.4565
0.4488	11.0201	2340	0.9068	0.4348
0.5551	12.0201	2535	0.8317	0.5217
0.5061	13.0201	2730	0.8236	0.4348
0.5321	14.0201	2925	1.6359	0.4783
0.4939	15.0201	3120	0.8285	0.5
0.5357	16.0201	3315	1.0012	0.5217
0.5296	17.0201	3510	1.2453	0.5435
0.4804	18.0201	3705	1.2386	0.5
0.4362	19.0201	3900	1.3533	0.5217
0.4623	20.0201	4095	1.4770	0.5435
0.6462	21.0201	4290	2.5438	0.4565
0.5856	22.0201	4485	1.5527	0.5435
0.4706	23.0201	4680	1.7185	0.5435
0.3158	24.0201	4875	1.9238	0.5217
0.4374	25.0201	5070	1.6295	0.5217
0.2508	26.0201	5265	2.1838	0.5
0.1099	27.0201	5460	2.3503	0.4783
0.5135	28.0201	5655	2.3169	0.4565
0.3813	29.0201	5850	2.2221	0.5435
0.2081	30.0201	6045	2.2921	0.4783
0.5254	31.0201	6240	2.3721	0.5217
0.3693	32.0201	6435	2.6905	0.5435
0.3546	33.0201	6630	2.4107	0.5217
0.3293	34.0201	6825	2.5811	0.5435
0.2947	35.0201	7020	2.6993	0.5217
0.1942	36.0201	7215	2.8509	0.5217
0.2314	37.0201	7410	2.9016	0.4783
0.1532	38.0201	7605	3.1442	0.5
0.4497	39.0201	7800	3.0534	0.5217
0.3039	40.0201	7995	2.8741	0.5217
0.488	41.0201	8190	3.0307	0.5652
0.249	42.0201	8385	2.9161	0.5217
0.1631	43.0201	8580	3.1861	0.5217
0.4324	44.0201	8775	3.2934	0.5435
0.1618	45.0201	8970	3.0118	0.5435
0.3736	46.0201	9165	3.1869	0.5435
0.1134	47.0201	9360	3.0180	0.5217
0.2435	48.0201	9555	3.0917	0.5217
0.4354	49.0149	9700	3.1152	0.5217

Framework versions

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