Edit model card

estudiante_Swin3D_profesor_MViT_akl_RWF2000

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

  • Loss: 0.2862
  • Accuracy: 0.9113
  • F1: 0.9112
  • Precision: 0.9113
  • Recall: 0.9113
  • Roc Auc: 0.9627

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
4.1936 1.0214 280 0.3434 0.8575 0.8563 0.8702 0.8575 0.9537
3.4616 3.0143 560 0.2829 0.8775 0.8774 0.8791 0.8775 0.9587
2.8886 5.0071 840 0.3145 0.8775 0.8770 0.8835 0.8775 0.9586
2.4481 6.0286 1120 0.3595 0.8675 0.8666 0.8778 0.8675 0.9492
2.0603 8.0214 1400 0.3079 0.8875 0.8873 0.8903 0.8875 0.9513
1.7483 10.0143 1680 0.2810 0.8975 0.8974 0.8987 0.8975 0.9631
1.808 12.0071 1960 0.2715 0.9 0.9000 0.9000 0.9 0.9630
1.7373 13.0286 2240 0.3319 0.875 0.8744 0.8825 0.875 0.9652
1.621 15.0214 2520 0.2721 0.91 0.9100 0.9102 0.91 0.9680
1.5803 17.0143 2800 0.2640 0.9175 0.9174 0.9193 0.9175 0.9733
1.6703 19.0071 3080 0.2754 0.9075 0.9074 0.9087 0.9075 0.9675
1.3204 20.0286 3360 0.2532 0.9175 0.9175 0.9175 0.9175 0.9691
1.2447 22.0214 3640 0.3191 0.89 0.8896 0.8957 0.89 0.9721
1.4993 24.0143 3920 0.3287 0.8875 0.8871 0.8937 0.8875 0.9680
1.1415 26.0071 4200 0.2641 0.9225 0.9225 0.9225 0.9225 0.9663
1.6365 27.0286 4480 0.2984 0.9025 0.9025 0.9025 0.9025 0.9573
0.9572 29.0214 4760 0.3362 0.89 0.8898 0.8932 0.89 0.9610
1.093 31.0143 5040 0.2720 0.91 0.9100 0.9100 0.91 0.9654
1.2306 33.0071 5320 0.2865 0.9125 0.9125 0.9126 0.9125 0.9655
1.0559 34.0286 5600 0.2807 0.905 0.905 0.905 0.905 0.9632

Framework versions

  • Transformers 4.46.2
  • Pytorch 2.0.1+cu118
  • Datasets 3.1.0
  • Tokenizers 0.20.3
Downloads last month
2
Safetensors
Model size
29.8M params
Tensor type
I64
·
F32
·
Inference API
Unable to determine this model’s pipeline type. Check the docs .