videomae-base-finetuned-isl-numbers_2

This model is a fine-tuned version of latif98/videomae-base-finetuned-isl-numbers on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.2759
• Accuracy: 0.6839

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: 5e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• training_steps: 3800

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
3.5502	0.02	76	3.4251	0.0945
3.1152	1.02	152	3.0364	0.2756
2.6365	2.02	228	2.6197	0.3780
2.3879	3.02	304	2.1519	0.4646
1.9396	4.02	380	2.0804	0.4173
1.9285	5.02	456	1.9335	0.4488
1.5843	6.02	532	1.7907	0.4803
1.2387	7.02	608	1.8962	0.3858
1.2578	8.02	684	1.7191	0.4488
0.9611	9.02	760	1.7362	0.4882
0.9247	10.02	836	1.3898	0.5906
0.8107	11.02	912	1.9588	0.4094
0.7618	12.02	988	1.1416	0.6614
0.7083	13.02	1064	1.2812	0.6614
0.7098	14.02	1140	1.4601	0.5197
0.4601	15.02	1216	1.1276	0.6693
0.5684	16.02	1292	1.4792	0.5591
0.5044	17.02	1368	1.1236	0.6614
0.4551	18.02	1444	1.3894	0.6063
0.3488	19.02	1520	1.2918	0.6614
0.4711	20.02	1596	1.2510	0.6299
0.3451	21.02	1672	1.1265	0.6693
0.394	22.02	1748	1.1676	0.6378
0.234	23.02	1824	1.0714	0.7087
0.2318	24.02	1900	1.2647	0.6378
0.4294	25.02	1976	1.0250	0.7480
0.2084	26.02	2052	1.1361	0.6850
0.1724	27.02	2128	0.8791	0.7402
0.1715	28.02	2204	0.7549	0.7559
0.2719	29.02	2280	0.7708	0.7717
0.2021	30.02	2356	1.1394	0.7165
0.0999	31.02	2432	0.7838	0.7717
0.1473	32.02	2508	1.3809	0.6457
0.0939	33.02	2584	0.7839	0.7874
0.0952	34.02	2660	1.0636	0.7008
0.2684	35.02	2736	0.9194	0.7323
0.1628	36.02	2812	0.7346	0.8031
0.0584	37.02	2888	1.0112	0.7323
0.0567	38.02	2964	1.0584	0.7323
0.1358	39.02	3040	1.0566	0.7323
0.0796	40.02	3116	0.9323	0.7480
0.0828	41.02	3192	0.7611	0.7953
0.0661	42.02	3268	0.7284	0.7874
0.0882	43.02	3344	0.6982	0.7953
0.0398	44.02	3420	0.8586	0.7717
0.2085	45.02	3496	0.7990	0.7717
0.0509	46.02	3572	0.7134	0.8268
0.0791	47.02	3648	0.6887	0.8189
0.0469	48.02	3724	0.7159	0.8031
0.0621	49.02	3800	0.7062	0.8031

Framework versions

• Transformers 4.40.0
• Pytorch 2.1.0+cu121
• Datasets 2.18.0
• Tokenizers 0.19.1