<!-- This model card has been generated automatically according to the information Keras had access to. You should probably proofread and complete it, then remove this comment. -->
AhamadShaik/SegFormer_PADDING_LM
This model is a fine-tuned version of nvidia/mit-b0 on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.0186
- Train Dice Coef: 0.7789
- Train Iou: 0.6508
- Validation Loss: 0.0233
- Validation Dice Coef: 0.8506
- Validation Iou: 0.7439
- Train Lr: 1e-10
- Epoch: 99
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:
- optimizer: {'name': 'Adam', 'learning_rate': 1e-10, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
- training_precision: float32
Training results
Train Loss | Train Dice Coef | Train Iou | Validation Loss | Validation Dice Coef | Validation Iou | Train Lr | Epoch |
---|---|---|---|---|---|---|---|
0.1460 | 0.3657 | 0.2410 | 0.0908 | 0.4603 | 0.3168 | 1e-04 | 0 |
0.0610 | 0.5251 | 0.3760 | 0.1773 | 0.1542 | 0.0892 | 1e-04 | 1 |
0.0500 | 0.5831 | 0.4322 | 0.0806 | 0.5067 | 0.3659 | 1e-04 | 2 |
0.0432 | 0.6204 | 0.4699 | 0.1085 | 0.3757 | 0.2479 | 1e-04 | 3 |
0.0413 | 0.6306 | 0.4831 | 0.0771 | 0.5239 | 0.3646 | 1e-04 | 4 |
0.0374 | 0.6569 | 0.5086 | 0.0719 | 0.5267 | 0.3854 | 1e-04 | 5 |
0.0336 | 0.6770 | 0.5307 | 0.0540 | 0.6264 | 0.4881 | 1e-04 | 6 |
0.0302 | 0.7029 | 0.5592 | 0.0518 | 0.6516 | 0.5234 | 1e-04 | 7 |
0.0306 | 0.7010 | 0.5582 | 0.0704 | 0.5946 | 0.4483 | 1e-04 | 8 |
0.0285 | 0.7160 | 0.5744 | 0.0504 | 0.6951 | 0.5568 | 1e-04 | 9 |
0.0287 | 0.7245 | 0.5830 | 0.0357 | 0.7899 | 0.6630 | 1e-04 | 10 |
0.0273 | 0.7228 | 0.5825 | 0.0659 | 0.6279 | 0.4914 | 1e-04 | 11 |
0.0259 | 0.7344 | 0.5961 | 0.0357 | 0.7986 | 0.6716 | 1e-04 | 12 |
0.0257 | 0.7405 | 0.6010 | 0.0385 | 0.7970 | 0.6702 | 1e-04 | 13 |
0.0237 | 0.7434 | 0.6076 | 0.0364 | 0.8060 | 0.6841 | 1e-04 | 14 |
0.0227 | 0.7532 | 0.6192 | 0.0556 | 0.6927 | 0.5449 | 1e-04 | 15 |
0.0225 | 0.7546 | 0.6202 | 0.0242 | 0.8446 | 0.7356 | 5e-06 | 16 |
0.0207 | 0.7614 | 0.6312 | 0.0235 | 0.8482 | 0.7406 | 5e-06 | 17 |
0.0205 | 0.7676 | 0.6365 | 0.0235 | 0.8489 | 0.7414 | 5e-06 | 18 |
0.0200 | 0.7689 | 0.6389 | 0.0238 | 0.8497 | 0.7424 | 5e-06 | 19 |
0.0201 | 0.7693 | 0.6384 | 0.0237 | 0.8492 | 0.7418 | 5e-06 | 20 |
0.0195 | 0.7738 | 0.6438 | 0.0231 | 0.8504 | 0.7440 | 5e-06 | 21 |
0.0196 | 0.7749 | 0.6458 | 0.0234 | 0.8504 | 0.7436 | 5e-06 | 22 |
0.0192 | 0.7756 | 0.6464 | 0.0236 | 0.8482 | 0.7407 | 5e-06 | 23 |
0.0191 | 0.7741 | 0.6447 | 0.0231 | 0.8503 | 0.7435 | 5e-06 | 24 |
0.0191 | 0.7761 | 0.6466 | 0.0238 | 0.8493 | 0.7419 | 5e-06 | 25 |
0.0188 | 0.7781 | 0.6503 | 0.0237 | 0.8481 | 0.7405 | 5e-06 | 26 |
0.0192 | 0.7729 | 0.6440 | 0.0234 | 0.8483 | 0.7414 | 2.5e-07 | 27 |
0.0187 | 0.7849 | 0.6572 | 0.0241 | 0.8478 | 0.7398 | 2.5e-07 | 28 |
0.0188 | 0.7786 | 0.6501 | 0.0241 | 0.8484 | 0.7406 | 2.5e-07 | 29 |
0.0189 | 0.7815 | 0.6520 | 0.0232 | 0.8507 | 0.7439 | 2.5e-07 | 30 |
0.0185 | 0.7715 | 0.6440 | 0.0232 | 0.8505 | 0.7437 | 2.5e-07 | 31 |
0.0186 | 0.7764 | 0.6488 | 0.0233 | 0.8487 | 0.7416 | 1.25e-08 | 32 |
0.0189 | 0.7725 | 0.6438 | 0.0235 | 0.8492 | 0.7418 | 1.25e-08 | 33 |
0.0186 | 0.7767 | 0.6484 | 0.0237 | 0.8491 | 0.7414 | 1.25e-08 | 34 |
0.0186 | 0.7800 | 0.6517 | 0.0229 | 0.8503 | 0.7436 | 1.25e-08 | 35 |
0.0187 | 0.7758 | 0.6463 | 0.0232 | 0.8501 | 0.7433 | 1.25e-08 | 36 |
0.0187 | 0.7774 | 0.6497 | 0.0232 | 0.8496 | 0.7423 | 1.25e-08 | 37 |
0.0187 | 0.7791 | 0.6502 | 0.0234 | 0.8496 | 0.7424 | 1.25e-08 | 38 |
0.0189 | 0.7743 | 0.6446 | 0.0237 | 0.8501 | 0.7429 | 1.25e-08 | 39 |
0.0189 | 0.7770 | 0.6491 | 0.0234 | 0.8479 | 0.7402 | 1.25e-08 | 40 |
0.0187 | 0.7793 | 0.6507 | 0.0233 | 0.8507 | 0.7441 | 6.25e-10 | 41 |
0.0186 | 0.7788 | 0.6505 | 0.0231 | 0.8502 | 0.7434 | 6.25e-10 | 42 |
0.0188 | 0.7773 | 0.6491 | 0.0232 | 0.8510 | 0.7443 | 6.25e-10 | 43 |
0.0185 | 0.7775 | 0.6493 | 0.0229 | 0.8518 | 0.7456 | 6.25e-10 | 44 |
0.0187 | 0.7765 | 0.6487 | 0.0233 | 0.8491 | 0.7416 | 6.25e-10 | 45 |
0.0186 | 0.7804 | 0.6521 | 0.0234 | 0.8499 | 0.7430 | 1e-10 | 46 |
0.0187 | 0.7765 | 0.6482 | 0.0235 | 0.8486 | 0.7410 | 1e-10 | 47 |
0.0187 | 0.7777 | 0.6497 | 0.0233 | 0.8493 | 0.7419 | 1e-10 | 48 |
0.0187 | 0.7785 | 0.6498 | 0.0230 | 0.8502 | 0.7432 | 1e-10 | 49 |
0.0188 | 0.7813 | 0.6529 | 0.0235 | 0.8491 | 0.7418 | 1e-10 | 50 |
0.0186 | 0.7770 | 0.6498 | 0.0229 | 0.8504 | 0.7435 | 1e-10 | 51 |
0.0190 | 0.7764 | 0.6483 | 0.0232 | 0.8503 | 0.7437 | 1e-10 | 52 |
0.0189 | 0.7764 | 0.6480 | 0.0233 | 0.8500 | 0.7430 | 1e-10 | 53 |
0.0189 | 0.7744 | 0.6461 | 0.0231 | 0.8516 | 0.7449 | 1e-10 | 54 |
0.0188 | 0.7767 | 0.6485 | 0.0233 | 0.8499 | 0.7429 | 1e-10 | 55 |
0.0189 | 0.7729 | 0.6441 | 0.0234 | 0.8488 | 0.7413 | 1e-10 | 56 |
0.0186 | 0.7814 | 0.6531 | 0.0235 | 0.8486 | 0.7408 | 1e-10 | 57 |
0.0189 | 0.7772 | 0.6480 | 0.0237 | 0.8482 | 0.7405 | 1e-10 | 58 |
0.0187 | 0.7756 | 0.6477 | 0.0231 | 0.8511 | 0.7443 | 1e-10 | 59 |
0.0188 | 0.7783 | 0.6500 | 0.0234 | 0.8489 | 0.7415 | 1e-10 | 60 |
0.0186 | 0.7771 | 0.6484 | 0.0238 | 0.8482 | 0.7402 | 1e-10 | 61 |
0.0186 | 0.7776 | 0.6502 | 0.0231 | 0.8499 | 0.7429 | 1e-10 | 62 |
0.0185 | 0.7784 | 0.6504 | 0.0232 | 0.8496 | 0.7422 | 1e-10 | 63 |
0.0188 | 0.7797 | 0.6519 | 0.0234 | 0.8484 | 0.7406 | 1e-10 | 64 |
0.0189 | 0.7851 | 0.6566 | 0.0230 | 0.8518 | 0.7455 | 1e-10 | 65 |
0.0187 | 0.7795 | 0.6515 | 0.0237 | 0.8494 | 0.7420 | 1e-10 | 66 |
0.0188 | 0.7779 | 0.6489 | 0.0237 | 0.8470 | 0.7395 | 1e-10 | 67 |
0.0190 | 0.7751 | 0.6455 | 0.0243 | 0.8472 | 0.7391 | 1e-10 | 68 |
0.0188 | 0.7767 | 0.6486 | 0.0233 | 0.8502 | 0.7433 | 1e-10 | 69 |
0.0189 | 0.7819 | 0.6535 | 0.0231 | 0.8504 | 0.7436 | 1e-10 | 70 |
0.0188 | 0.7734 | 0.6452 | 0.0230 | 0.8508 | 0.7442 | 1e-10 | 71 |
0.0186 | 0.7784 | 0.6516 | 0.0234 | 0.8484 | 0.7414 | 1e-10 | 72 |
0.0187 | 0.7706 | 0.6424 | 0.0236 | 0.8483 | 0.7407 | 1e-10 | 73 |
0.0189 | 0.7720 | 0.6430 | 0.0237 | 0.8481 | 0.7401 | 1e-10 | 74 |
0.0189 | 0.7753 | 0.6464 | 0.0232 | 0.8505 | 0.7439 | 1e-10 | 75 |
0.0188 | 0.7759 | 0.6481 | 0.0232 | 0.8500 | 0.7427 | 1e-10 | 76 |
0.0188 | 0.7760 | 0.6479 | 0.0235 | 0.8494 | 0.7418 | 1e-10 | 77 |
0.0187 | 0.7828 | 0.6538 | 0.0231 | 0.8518 | 0.7456 | 1e-10 | 78 |
0.0188 | 0.7771 | 0.6489 | 0.0235 | 0.8488 | 0.7414 | 1e-10 | 79 |
0.0188 | 0.7766 | 0.6480 | 0.0235 | 0.8487 | 0.7411 | 1e-10 | 80 |
0.0187 | 0.7764 | 0.6492 | 0.0236 | 0.8497 | 0.7421 | 1e-10 | 81 |
0.0188 | 0.7769 | 0.6489 | 0.0232 | 0.8504 | 0.7434 | 1e-10 | 82 |
0.0190 | 0.7805 | 0.6507 | 0.0237 | 0.8494 | 0.7418 | 1e-10 | 83 |
0.0187 | 0.7752 | 0.6473 | 0.0231 | 0.8502 | 0.7431 | 1e-10 | 84 |
0.0189 | 0.7758 | 0.6472 | 0.0234 | 0.8484 | 0.7414 | 1e-10 | 85 |
0.0185 | 0.7735 | 0.6460 | 0.0234 | 0.8492 | 0.7417 | 1e-10 | 86 |
0.0185 | 0.7814 | 0.6534 | 0.0235 | 0.8490 | 0.7414 | 1e-10 | 87 |
0.0186 | 0.7762 | 0.6472 | 0.0234 | 0.8490 | 0.7415 | 1e-10 | 88 |
0.0189 | 0.7769 | 0.6481 | 0.0230 | 0.8514 | 0.7452 | 1e-10 | 89 |
0.0186 | 0.7776 | 0.6495 | 0.0238 | 0.8496 | 0.7422 | 1e-10 | 90 |
0.0188 | 0.7772 | 0.6486 | 0.0233 | 0.8496 | 0.7423 | 1e-10 | 91 |
0.0186 | 0.7743 | 0.6467 | 0.0231 | 0.8505 | 0.7436 | 1e-10 | 92 |
0.0188 | 0.7794 | 0.6505 | 0.0233 | 0.8503 | 0.7431 | 1e-10 | 93 |
0.0186 | 0.7739 | 0.6455 | 0.0237 | 0.8476 | 0.7395 | 1e-10 | 94 |
0.0188 | 0.7769 | 0.6477 | 0.0234 | 0.8492 | 0.7419 | 1e-10 | 95 |
0.0188 | 0.7689 | 0.6415 | 0.0236 | 0.8487 | 0.7409 | 1e-10 | 96 |
0.0194 | 0.7756 | 0.6476 | 0.0236 | 0.8504 | 0.7433 | 1e-10 | 97 |
0.0187 | 0.7792 | 0.6504 | 0.0231 | 0.8502 | 0.7436 | 1e-10 | 98 |
0.0186 | 0.7789 | 0.6508 | 0.0233 | 0.8506 | 0.7439 | 1e-10 | 99 |
Framework versions
- Transformers 4.27.4
- TensorFlow 2.10.1
- Datasets 2.11.0
- Tokenizers 0.13.3