CT-MAE-RIS2-Phase2-CPC3-Good-V2-1

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: 0.3898
• Accuracy: 0.8913

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: 3250

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.6284	0.02	65	0.7345	0.4783
0.5985	1.02	130	0.7222	0.4783
0.4966	2.02	195	0.6716	0.4783
0.6321	3.02	260	0.8875	0.4783
0.5093	4.02	325	0.5708	0.6957
0.6458	5.02	390	1.1418	0.4783
0.4735	6.02	455	0.6619	0.5435
0.5284	7.02	520	0.5361	0.6739
0.6178	8.02	585	0.8018	0.4783
0.5019	9.02	650	0.5225	0.7609
0.5341	10.02	715	0.5518	0.7174
0.4597	11.02	780	0.6353	0.6522
0.497	12.02	845	0.4260	0.8043
0.3936	13.02	910	0.7595	0.7174
0.4002	14.02	975	1.0749	0.5217
0.3154	15.02	1040	0.7416	0.7174
0.4842	16.02	1105	0.8746	0.7609
0.4148	17.02	1170	0.5577	0.7391
0.2759	18.02	1235	0.9909	0.6957
0.8495	19.02	1300	0.9954	0.6957
0.6693	20.02	1365	1.0602	0.6739
0.4097	21.02	1430	0.3898	0.8913
0.5977	22.02	1495	0.7469	0.7609
0.2196	23.02	1560	0.7012	0.7391
0.2359	24.02	1625	0.4625	0.8913
0.1152	25.02	1690	0.8365	0.8043
0.254	26.02	1755	1.0430	0.7174
0.4037	27.02	1820	0.6193	0.8261
0.1125	28.02	1885	1.3347	0.6739
0.1994	29.02	1950	1.9818	0.6304
0.1948	30.02	2015	0.9547	0.7826
0.2008	31.02	2080	2.4753	0.5870
0.1657	32.02	2145	1.3203	0.6957
0.2401	33.02	2210	1.6300	0.6739
0.0169	34.02	2275	1.3876	0.6957
0.0069	35.02	2340	1.4367	0.6957
0.1173	36.02	2405	0.8904	0.7609
0.1173	37.02	2470	1.0566	0.7609
0.2719	38.02	2535	1.5971	0.6957
0.0119	39.02	2600	1.3077	0.7609
0.4477	40.02	2665	1.4566	0.7391
0.0098	41.02	2730	1.5447	0.7174
0.0338	42.02	2795	1.4486	0.7391
0.0013	43.02	2860	1.0968	0.7609
0.1518	44.02	2925	1.7105	0.6739
0.0006	45.02	2990	1.2385	0.7609
0.0005	46.02	3055	1.2568	0.7609
0.0446	47.02	3120	1.3135	0.7609
0.1332	48.02	3185	1.1372	0.7609
0.0015	49.02	3250	1.2035	0.7609

Framework versions

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