metadata

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

videomae-base-finetuned-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: 0.7174
Accuracy: 0.6898

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: 2925

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.6183	0.04	118	1.5576	0.4194
1.4874	1.04	236	1.3517	0.4240
1.6523	2.04	354	1.3001	0.3364
1.2763	3.04	472	1.1898	0.3917
1.2819	4.04	590	1.1945	0.5161
1.1196	5.04	708	0.9771	0.5668
1.1976	6.04	826	1.1079	0.4747
0.8174	7.04	944	0.8705	0.6636
0.7923	8.04	1062	0.7827	0.6636
0.6052	9.04	1180	0.9455	0.6313
0.7902	10.04	1298	0.9512	0.6175
0.9501	11.04	1416	0.8058	0.7373
1.1756	12.04	1534	0.7674	0.7327
0.8482	13.04	1652	0.8455	0.6866
0.7657	14.04	1770	0.9124	0.6820
0.9752	15.04	1888	0.9788	0.6313
0.7176	16.04	2006	0.6860	0.7604
0.7682	17.04	2124	0.8052	0.7143
0.8862	18.04	2242	0.9102	0.6820
0.6609	19.04	2360	0.9360	0.6866
0.9678	20.04	2478	0.8441	0.6866
0.8617	21.04	2596	0.8136	0.7097
0.7097	22.04	2714	0.8615	0.7005
0.5089	23.04	2832	0.7796	0.7005
0.715	24.03	2925	0.7685	0.7235

Framework versions

Transformers 4.36.2
Pytorch 1.13.1
Datasets 2.16.1
Tokenizers 0.15.0