rsna25_v1

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

• Loss: 1.5587
• Accuracy: 0.7333

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: 1e-05
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• training_steps: 6930

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.5939	0.0333	231	1.5587	0.7333
0.455	1.0333	462	1.3529	0.7333
1.2417	2.0333	693	0.8578	0.7333
0.9951	3.0333	924	1.2944	0.7333
0.4083	4.0333	1155	1.2672	0.7333
0.4595	5.0333	1386	1.2700	0.7333
1.2848	6.0333	1617	0.8392	0.7333
2.722	7.0333	1848	0.9498	0.7333
1.4998	8.0333	2079	1.5093	0.7333
0.0014	9.0333	2310	1.6971	0.7333
0.5911	10.0333	2541	1.0745	0.7333
1.8092	11.0333	2772	0.6230	0.7
1.0219	12.0333	3003	1.6409	0.7
0.5296	13.0333	3234	1.5234	0.6667
0.5409	14.0333	3465	1.7107	0.7
0.7647	15.0333	3696	1.5247	0.6333
0.0104	16.0333	3927	2.1141	0.6
0.7037	17.0333	4158	1.7078	0.6667
0.8323	18.0333	4389	1.9914	0.6333
1.5883	19.0333	4620	2.1970	0.6
0.3247	20.0333	4851	2.0857	0.6667
0.6906	21.0333	5082	2.5990	0.5667
0.0038	22.0333	5313	2.2210	0.6333
0.7022	23.0333	5544	2.3749	0.6333
1.0012	24.0333	5775	2.3539	0.6333
0.3784	25.0333	6006	2.4822	0.6
0.0002	26.0333	6237	2.5226	0.6333
0.5648	27.0333	6468	2.5680	0.6333
0.0005	28.0333	6699	2.6583	0.6333
0.3963	29.0333	6930	2.6647	0.6333

Framework versions

• Transformers 4.46.2
• Pytorch 2.0.1+cu117
• Datasets 3.0.1
• Tokenizers 0.20.0