9_mae_2

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: 1.7783
• Accuracy: 0.7556

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: 5
• eval_batch_size: 5
• 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: 7750

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.6406	0.0201	156	0.7691	0.4667
0.5971	1.0201	312	0.8278	0.4444
0.56	2.0201	468	0.7554	0.4667
0.542	3.0201	624	0.8117	0.4667
0.5994	4.0201	780	0.6973	0.5556
0.5274	5.0201	936	0.8280	0.6
0.4996	6.0201	1092	0.6631	0.6
0.5248	7.0201	1248	0.6960	0.6222
0.2459	8.0201	1404	0.8777	0.6
0.3863	9.0201	1560	0.8526	0.6222
0.3127	10.0201	1716	0.9684	0.6889
0.489	11.0201	1872	1.2685	0.6889
0.4927	12.0201	2028	1.1348	0.6222
0.298	13.0201	2184	1.1665	0.6667
0.3292	14.0201	2340	1.6151	0.6444
0.4261	15.0201	2496	1.3148	0.7111
0.3259	16.0201	2652	1.3689	0.6889
0.1912	17.0201	2808	2.1384	0.6222
0.4778	18.0201	2964	1.6181	0.6222
0.2515	19.0201	3120	1.7591	0.7111
0.6034	20.0201	3276	1.5394	0.6667
0.2501	21.0201	3432	1.5148	0.6889
0.1362	22.0201	3588	1.9569	0.6222
0.2121	23.0201	3744	1.8575	0.6
0.2351	24.0201	3900	1.5758	0.7111
0.5087	25.0201	4056	1.6869	0.6444
0.3187	26.0201	4212	2.1923	0.6444
0.5102	27.0201	4368	2.1271	0.6444
0.3115	28.0201	4524	2.0565	0.6444
0.1073	29.0201	4680	2.3521	0.6444
0.1994	30.0201	4836	1.9575	0.6667
0.0009	31.0201	4992	2.0930	0.6667
0.0787	32.0201	5148	2.0121	0.6444
0.2799	33.0201	5304	1.9623	0.6889
0.0008	34.0201	5460	2.2804	0.6667
0.1125	35.0201	5616	2.2850	0.6667
0.0006	36.0201	5772	1.9233	0.6889
0.0006	37.0201	5928	1.8887	0.7333
0.0095	38.0201	6084	1.8609	0.7333
0.0275	39.0201	6240	1.7783	0.7556
0.0918	40.0201	6396	2.2507	0.6667
0.1329	41.0201	6552	2.2886	0.6889
0.0475	42.0201	6708	2.5501	0.6444
0.0004	43.0201	6864	2.2807	0.6667
0.0001	44.0201	7020	2.7032	0.6444
0.0002	45.0201	7176	2.4008	0.6444
0.298	46.0201	7332	2.1215	0.7111
0.0052	47.0201	7488	2.1466	0.7111
0.0465	48.0201	7644	2.1904	0.7111
0.0002	49.0137	7750	2.1385	0.7111

Framework versions

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