CTMAE2_CS_V7_3

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: 1.0930
• Accuracy: 0.8261

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: 3
• eval_batch_size: 3
• 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: 13000

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.6166	0.02	260	0.7472	0.4565
0.5113	1.02	520	0.9421	0.4565
0.4538	2.02	780	0.9290	0.4783
0.4927	3.02	1040	0.6694	0.5870
0.5214	4.02	1300	0.7649	0.7174
1.0967	5.02	1560	0.9229	0.6739
0.6237	6.02	1820	0.8940	0.7174
0.2162	7.02	2080	0.8480	0.7609
0.4234	8.02	2340	1.3532	0.6304
0.4629	9.02	2600	0.7409	0.7391
0.4631	10.02	2860	0.8471	0.7609
0.548	11.02	3120	0.9673	0.6957
0.355	12.02	3380	0.9122	0.7609
0.6545	13.02	3640	1.0228	0.7391
0.6703	14.02	3900	0.9249	0.7174
0.561	15.02	4160	1.1688	0.7174
0.3788	16.02	4420	1.9633	0.6522
0.3055	17.02	4680	1.1960	0.6957
0.2223	18.02	4940	1.0511	0.7609
0.4324	19.02	5200	1.5567	0.6957
0.3022	20.02	5460	1.6864	0.6304
0.4434	21.02	5720	1.7834	0.6304
0.2485	22.02	5980	1.4761	0.6739
0.3882	23.02	6240	1.8617	0.6522
0.0128	24.02	6500	1.6289	0.6739
0.4251	25.02	6760	1.5492	0.6957
0.0128	26.02	7020	2.4527	0.5652
0.2468	27.02	7280	1.8335	0.6739
0.1681	28.02	7540	1.0796	0.8043
0.4033	29.02	7800	2.3945	0.6087
0.1556	30.02	8060	1.7049	0.6739
0.3012	31.02	8320	1.0930	0.8261
0.0585	32.02	8580	1.5270	0.7174
0.0005	33.02	8840	1.1852	0.8261
0.0008	34.02	9100	1.6258	0.7609
0.117	35.02	9360	1.4406	0.7826
0.1401	36.02	9620	1.7366	0.7174
0.2498	37.02	9880	2.4993	0.6304
0.2411	38.02	10140	2.2741	0.6522
0.0004	39.02	10400	2.0468	0.6957
0.0001	40.02	10660	2.0636	0.6522
0.331	41.02	10920	2.1473	0.6522
0.0112	42.02	11180	1.8257	0.6957
0.2408	43.02	11440	2.2235	0.6522
0.0002	44.02	11700	2.2065	0.6739
0.0001	45.02	11960	2.4907	0.6522
0.0055	46.02	12220	2.2836	0.6304
0.0001	47.02	12480	2.6007	0.6304
0.0003	48.02	12740	2.2538	0.6304
0.0334	49.02	13000	2.3751	0.6304

Framework versions

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