estudiante_Swin3D_profesor_MViT_kl_RWF2000

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

• Loss: 0.2895
• Accuracy: 0.91
• F1: 0.9100
• Precision: 0.9100
• Recall: 0.91
• Roc Auc: 0.9561

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: 10
• eval_batch_size: 10
• 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_steps: 560
• training_steps: 5600
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall	Roc Auc
0.3879	1.0214	280	0.3120	0.87	0.8689	0.8824	0.87	0.9519
0.3395	3.0143	560	0.3248	0.87	0.8694	0.8774	0.87	0.9533
0.286	5.0071	840	0.3405	0.8675	0.8671	0.8724	0.8675	0.9462
0.2471	6.0286	1120	0.3416	0.88	0.8798	0.8824	0.88	0.9426
0.2209	8.0214	1400	0.3025	0.895	0.8949	0.8960	0.895	0.9551
0.176	10.0143	1680	0.2834	0.8925	0.8925	0.8930	0.8925	0.9580
0.1699	12.0071	1960	0.2729	0.895	0.895	0.895	0.895	0.9624
0.1382	13.0286	2240	0.3141	0.89	0.8894	0.8990	0.89	0.9582
0.154	15.0214	2520	0.3228	0.8875	0.8872	0.8918	0.8875	0.9514
0.1552	17.0143	2800	0.2660	0.905	0.9050	0.9052	0.905	0.9633
0.1579	19.0071	3080	0.2779	0.9075	0.9075	0.9083	0.9075	0.9589
0.1391	20.0286	3360	0.2561	0.9225	0.9225	0.9228	0.9225	0.9635
0.1292	22.0214	3640	0.3106	0.8975	0.8973	0.9004	0.8975	0.9673
0.0946	24.0143	3920	0.2891	0.9125	0.9124	0.9138	0.9125	0.9578
0.0859	26.0071	4200	0.2712	0.92	0.9200	0.9200	0.92	0.9640
0.1318	27.0286	4480	0.2999	0.9075	0.9075	0.9075	0.9075	0.9575
0.1275	29.0214	4760	0.2881	0.9075	0.9075	0.9076	0.9075	0.9589

Framework versions

• Transformers 4.46.2
• Pytorch 2.0.1+cu118
• Datasets 3.1.0
• Tokenizers 0.20.3