CTMAE2_CS_V7_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: 0.8260
• 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: 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
0.6413	0.0201	156	0.7948	0.4565
0.5022	1.0201	312	0.8549	0.4565
0.6512	2.0201	468	0.6671	0.5870
0.5026	3.0201	624	0.6542	0.6522
0.5752	4.0201	780	0.6096	0.7174
0.5908	5.0201	936	0.7501	0.5217
0.4882	6.0201	1092	0.7652	0.6304
0.4128	7.0201	1248	0.7746	0.6522
0.4414	8.0201	1404	0.5973	0.7174
0.4291	9.0201	1560	0.7594	0.7391
0.2729	10.0201	1716	0.5485	0.8043
0.5803	11.0201	1872	0.7238	0.6957
0.4601	12.0201	2028	0.7228	0.7174
0.1306	13.0201	2184	0.9496	0.7174
0.4727	14.0201	2340	0.8971	0.7174
0.4027	15.0201	2496	0.6291	0.7391
0.3149	16.0201	2652	0.8639	0.6957
0.1737	17.0201	2808	1.0473	0.6957
0.2368	18.0201	2964	0.8658	0.7174
0.1155	19.0201	3120	0.7655	0.8043
0.156	20.0201	3276	0.7960	0.7609
0.2685	21.0201	3432	0.8260	0.8261
0.2572	22.0201	3588	0.8299	0.7391
0.3788	23.0201	3744	0.8373	0.8043
0.3816	24.0201	3900	0.9689	0.7609
0.4579	25.0201	4056	1.2806	0.6739
0.2543	26.0201	4212	1.2309	0.7609
0.1227	27.0201	4368	1.2931	0.6522
0.3303	28.0201	4524	1.0450	0.8043
0.0808	29.0201	4680	1.3096	0.7391
0.0987	30.0201	4836	1.1349	0.7826
0.0432	31.0201	4992	1.0443	0.7391
0.0373	32.0201	5148	1.8532	0.6739
0.1619	33.0201	5304	1.0490	0.7391
0.096	34.0201	5460	1.2420	0.7826
0.0112	35.0201	5616	1.4820	0.7609
0.0282	36.0201	5772	1.3097	0.7826
0.1689	37.0201	5928	1.6520	0.6739
0.0005	38.0201	6084	1.9084	0.6739
0.1626	39.0201	6240	1.3166	0.8043
0.08	40.0201	6396	1.4161	0.8043
0.062	41.0201	6552	1.4863	0.7391
0.1915	42.0201	6708	1.6604	0.6522
0.365	43.0201	6864	1.4169	0.8261
0.0001	44.0201	7020	1.4883	0.8043
0.0014	45.0201	7176	1.5122	0.8043
0.0024	46.0201	7332	1.4808	0.8043
0.0001	47.0201	7488	1.4890	0.7826
0.0001	48.0201	7644	1.5129	0.7391
0.0001	49.0137	7750	1.5114	0.7609

Framework versions

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