videomae-base-zhe1

This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.4262
• Accuracy: 0.8956

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: 16
• eval_batch_size: 16
• 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: 3020

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.2872	0.0503	152	0.3326	0.8199
0.2112	1.0503	304	0.6636	0.8199
0.273	2.0503	456	0.3423	0.8450
0.1807	3.0503	608	0.4575	0.8336
0.0448	4.0503	760	0.8173	0.8114
0.0842	5.0503	912	0.6725	0.8289
0.076	6.0503	1064	0.4201	0.8913
0.0388	7.0503	1216	0.3810	0.8885
0.0779	8.0503	1368	0.5225	0.8530
0.042	9.0503	1520	0.4262	0.8956
0.0078	10.0503	1672	0.6697	0.8804
0.0011	11.0503	1824	0.5796	0.8880
0.0091	12.0503	1976	0.8369	0.8578
0.0016	13.0503	2128	0.6951	0.8785
0.0003	14.0503	2280	0.7588	0.8648
0.0165	15.0503	2432	1.1419	0.8176
0.03	16.0503	2584	0.8959	0.8417
0.0018	17.0503	2736	0.7170	0.8686
0.0006	18.0503	2888	0.7030	0.8771
0.0209	19.0437	3020	0.7551	0.8681

Framework versions

• Transformers 4.42.3
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1