metadata

license: cc-by-nc-4.0
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: videomae-base-finetuned-ucf101-subset
    results: []

videomae-base-finetuned-ucf101-subset

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

Loss: 0.2709
Accuracy: 0.9540

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: 4
eval_batch_size: 4
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: 3750

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
2.2549	0.02	75	2.2707	0.0270
1.7546	1.02	150	1.8893	0.3514
0.8462	2.02	225	0.8723	0.6216
0.551	3.02	300	0.4068	0.8108
0.6627	4.02	375	0.6916	0.7297
0.4383	5.02	450	0.5512	0.7568
0.3398	6.02	525	0.4060	0.8378
0.0769	7.02	600	0.8299	0.8108
0.0077	8.02	675	0.0570	0.9730
0.0055	9.02	750	0.0168	1.0
0.002	10.02	825	0.0497	0.9730
0.1242	11.02	900	0.2132	0.9459
0.0022	12.02	975	0.0026	1.0
0.0074	13.02	1050	0.0577	0.9730
0.0038	14.02	1125	0.0137	1.0
0.0011	15.02	1200	0.0022	1.0
0.001	16.02	1275	0.0025	1.0
0.0009	17.02	1350	0.0059	1.0
0.0024	18.02	1425	0.1411	0.9730
0.1709	19.02	1500	0.0041	1.0
0.0008	20.02	1575	0.0489	0.9730
0.0007	21.02	1650	0.0116	1.0
0.0008	22.02	1725	0.0741	0.9730
0.0008	23.02	1800	0.1699	0.9730
0.0007	24.02	1875	0.1828	0.9730
0.0006	25.02	1950	0.1652	0.9730
0.0006	26.02	2025	0.1608	0.9730
0.0005	27.02	2100	0.1595	0.9730
0.0005	28.02	2175	0.1445	0.9730
0.0006	29.02	2250	0.1488	0.9730
0.0005	30.02	2325	0.1202	0.9730
0.0005	31.02	2400	0.1238	0.9730
0.0004	32.02	2475	0.1225	0.9730
0.0005	33.02	2550	0.2320	0.9459
0.0004	34.02	2625	0.0791	0.9730
0.0005	35.02	2700	0.1285	0.9730
0.0004	36.02	2775	0.1719	0.9730
0.0007	37.02	2850	0.1799	0.9730
0.0004	38.02	2925	0.1936	0.9730
0.0004	39.02	3000	0.1844	0.9730
0.0004	40.02	3075	0.1790	0.9730
0.0004	41.02	3150	0.1747	0.9730
0.0004	42.02	3225	0.1359	0.9730
0.0004	43.02	3300	0.1283	0.9730
0.0004	44.02	3375	0.1209	0.9730
0.0004	45.02	3450	0.0876	0.9730
0.0004	46.02	3525	0.0933	0.9730
0.0004	47.02	3600	0.0976	0.9730
0.0004	48.02	3675	0.1011	0.9730
0.0004	49.02	3750	0.1050	0.9730

Framework versions

Transformers 4.24.0
Pytorch 1.8.0+cu111
Datasets 2.7.1
Tokenizers 0.13.2