videomae-base-finetuned-slrbd001

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: 1.6389
• Accuracy: 0.25

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: 60

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	0.05	3	1.4887	0.25
No log	1.05	6	1.3967	0.0
No log	2.05	9	1.3822	0.375
1.4098	3.05	12	1.3607	0.375
1.4098	4.05	15	1.2716	0.5
1.4098	5.05	18	1.2074	0.5
1.2325	6.05	21	1.3363	0.25
1.2325	7.05	24	1.3342	0.25
1.2325	8.05	27	1.1540	0.375
0.8868	9.05	30	1.0971	0.5
0.8868	10.05	33	1.1247	0.375
0.8868	11.05	36	1.2616	0.25
0.8868	12.05	39	0.9747	0.375
0.8266	13.05	42	0.8311	0.375
0.8266	14.05	45	0.9191	0.375
0.8266	15.05	48	1.1805	0.25
0.8023	16.05	51	1.3324	0.25
0.8023	17.05	54	1.5051	0.25
0.8023	18.05	57	1.6055	0.25
0.7772	19.05	60	1.6389	0.25

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu118
• Datasets 2.15.0
• Tokenizers 0.15.0