<!-- 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_NLM
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: 0.0161
- Train Dice Coef: 0.8042
- Train Iou: 0.6813
- Validation Loss: 0.0228
- Validation Dice Coef: 0.8559
- Validation Iou: 0.7502
- 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 |
---|---|---|---|---|---|---|---|
0.2695 | 0.2707 | 0.1687 | 0.1167 | 0.5713 | 0.4080 | 1e-04 | 0 |
0.0805 | 0.4647 | 0.3202 | 0.0690 | 0.6569 | 0.4990 | 1e-04 | 1 |
0.0582 | 0.5595 | 0.4069 | 0.0509 | 0.7745 | 0.6369 | 1e-04 | 2 |
0.0507 | 0.5971 | 0.4430 | 0.0459 | 0.7780 | 0.6420 | 1e-04 | 3 |
0.0443 | 0.6379 | 0.4837 | 0.0393 | 0.8008 | 0.6709 | 1e-04 | 4 |
0.0417 | 0.6535 | 0.5011 | 0.0363 | 0.8131 | 0.6882 | 1e-04 | 5 |
0.0384 | 0.6728 | 0.5223 | 0.0355 | 0.8240 | 0.7031 | 1e-04 | 6 |
0.0340 | 0.7019 | 0.5531 | 0.0327 | 0.8297 | 0.7113 | 1e-04 | 7 |
0.0339 | 0.7002 | 0.5530 | 0.0319 | 0.8344 | 0.7182 | 1e-04 | 8 |
0.0315 | 0.7137 | 0.5680 | 0.0307 | 0.8333 | 0.7169 | 1e-04 | 9 |
0.0292 | 0.7341 | 0.5908 | 0.0296 | 0.8400 | 0.7266 | 1e-04 | 10 |
0.0285 | 0.7321 | 0.5905 | 0.0294 | 0.8412 | 0.7279 | 1e-04 | 11 |
0.0287 | 0.7323 | 0.5901 | 0.0310 | 0.8338 | 0.7185 | 1e-04 | 12 |
0.0283 | 0.7361 | 0.5943 | 0.0285 | 0.8457 | 0.7351 | 1e-04 | 13 |
0.0254 | 0.7503 | 0.6120 | 0.0265 | 0.8474 | 0.7376 | 1e-04 | 14 |
0.0239 | 0.7623 | 0.6271 | 0.0262 | 0.8483 | 0.7393 | 1e-04 | 15 |
0.0237 | 0.7589 | 0.6231 | 0.0286 | 0.8425 | 0.7311 | 1e-04 | 16 |
0.0227 | 0.7682 | 0.6339 | 0.0264 | 0.8467 | 0.7368 | 1e-04 | 17 |
0.0236 | 0.7639 | 0.6281 | 0.0273 | 0.8450 | 0.7356 | 1e-04 | 18 |
0.0221 | 0.7701 | 0.6359 | 0.0251 | 0.8491 | 0.7411 | 1e-04 | 19 |
0.0235 | 0.7619 | 0.6262 | 0.0264 | 0.8482 | 0.7394 | 1e-04 | 20 |
0.0216 | 0.7718 | 0.6383 | 0.0257 | 0.8506 | 0.7425 | 1e-04 | 21 |
0.0222 | 0.7715 | 0.6379 | 0.0242 | 0.8543 | 0.7479 | 1e-04 | 22 |
0.0203 | 0.7810 | 0.6500 | 0.0239 | 0.8556 | 0.7499 | 1e-04 | 23 |
0.0196 | 0.7853 | 0.6556 | 0.0241 | 0.8552 | 0.7494 | 1e-04 | 24 |
0.0197 | 0.7813 | 0.6512 | 0.0236 | 0.8529 | 0.7464 | 1e-04 | 25 |
0.0191 | 0.7890 | 0.6608 | 0.0239 | 0.8574 | 0.7525 | 1e-04 | 26 |
0.0180 | 0.7930 | 0.6662 | 0.0236 | 0.8574 | 0.7524 | 1e-04 | 27 |
0.0179 | 0.7973 | 0.6709 | 0.0247 | 0.8559 | 0.7504 | 1e-04 | 28 |
0.0176 | 0.7959 | 0.6702 | 0.0245 | 0.8567 | 0.7515 | 1e-04 | 29 |
0.0225 | 0.7712 | 0.6380 | 0.0245 | 0.8496 | 0.7413 | 1e-04 | 30 |
0.0190 | 0.7867 | 0.6579 | 0.0232 | 0.8546 | 0.7486 | 5e-06 | 31 |
0.0178 | 0.7963 | 0.6701 | 0.0239 | 0.8520 | 0.7450 | 5e-06 | 32 |
0.0175 | 0.7964 | 0.6703 | 0.0232 | 0.8547 | 0.7489 | 5e-06 | 33 |
0.0173 | 0.7972 | 0.6719 | 0.0225 | 0.8556 | 0.7499 | 5e-06 | 34 |
0.0168 | 0.8006 | 0.6759 | 0.0232 | 0.8561 | 0.7507 | 5e-06 | 35 |
0.0167 | 0.7984 | 0.6739 | 0.0232 | 0.8543 | 0.7480 | 5e-06 | 36 |
0.0167 | 0.8025 | 0.6786 | 0.0226 | 0.8561 | 0.7507 | 5e-06 | 37 |
0.0163 | 0.8027 | 0.6791 | 0.0231 | 0.8560 | 0.7505 | 5e-06 | 38 |
0.0164 | 0.7995 | 0.6753 | 0.0225 | 0.8568 | 0.7516 | 5e-06 | 39 |
0.0160 | 0.8077 | 0.6853 | 0.0229 | 0.8559 | 0.7503 | 2.5e-07 | 40 |
0.0160 | 0.8070 | 0.6843 | 0.0227 | 0.8567 | 0.7514 | 2.5e-07 | 41 |
0.0160 | 0.8072 | 0.6844 | 0.0232 | 0.8564 | 0.7509 | 2.5e-07 | 42 |
0.0164 | 0.8037 | 0.6801 | 0.0219 | 0.8573 | 0.7525 | 2.5e-07 | 43 |
0.0161 | 0.8022 | 0.6786 | 0.0233 | 0.8548 | 0.7487 | 2.5e-07 | 44 |
0.0160 | 0.8041 | 0.6809 | 0.0226 | 0.8571 | 0.7522 | 2.5e-07 | 45 |
0.0161 | 0.8043 | 0.6810 | 0.0228 | 0.8558 | 0.7501 | 2.5e-07 | 46 |
0.0167 | 0.8035 | 0.6807 | 0.0226 | 0.8564 | 0.7510 | 2.5e-07 | 47 |
0.0161 | 0.8047 | 0.6818 | 0.0224 | 0.8565 | 0.7512 | 2.5e-07 | 48 |
0.0161 | 0.8041 | 0.6811 | 0.0225 | 0.8576 | 0.7528 | 1.25e-08 | 49 |
0.0162 | 0.8060 | 0.6832 | 0.0233 | 0.8555 | 0.7498 | 1.25e-08 | 50 |
0.0161 | 0.8029 | 0.6802 | 0.0227 | 0.8570 | 0.7519 | 1.25e-08 | 51 |
0.0160 | 0.8069 | 0.6843 | 0.0231 | 0.8556 | 0.7498 | 1.25e-08 | 52 |
0.0158 | 0.8074 | 0.6853 | 0.0230 | 0.8567 | 0.7514 | 1.25e-08 | 53 |
0.0160 | 0.8050 | 0.6821 | 0.0229 | 0.8563 | 0.7509 | 6.25e-10 | 54 |
0.0159 | 0.8057 | 0.6834 | 0.0230 | 0.8558 | 0.7501 | 6.25e-10 | 55 |
0.0160 | 0.8045 | 0.6811 | 0.0226 | 0.8574 | 0.7525 | 6.25e-10 | 56 |
0.0161 | 0.8061 | 0.6828 | 0.0226 | 0.8560 | 0.7506 | 6.25e-10 | 57 |
0.0160 | 0.8062 | 0.6833 | 0.0231 | 0.8560 | 0.7505 | 6.25e-10 | 58 |
0.0159 | 0.8037 | 0.6810 | 0.0227 | 0.8557 | 0.7500 | 1e-10 | 59 |
0.0159 | 0.8085 | 0.6859 | 0.0223 | 0.8572 | 0.7522 | 1e-10 | 60 |
0.0159 | 0.8046 | 0.6815 | 0.0223 | 0.8578 | 0.7533 | 1e-10 | 61 |
0.0161 | 0.8057 | 0.6830 | 0.0229 | 0.8561 | 0.7507 | 1e-10 | 62 |
0.0160 | 0.8046 | 0.6817 | 0.0230 | 0.8566 | 0.7514 | 1e-10 | 63 |
0.0160 | 0.8038 | 0.6812 | 0.0225 | 0.8567 | 0.7514 | 1e-10 | 64 |
0.0159 | 0.8084 | 0.6865 | 0.0225 | 0.8561 | 0.7508 | 1e-10 | 65 |
0.0161 | 0.8030 | 0.6795 | 0.0226 | 0.8570 | 0.7520 | 1e-10 | 66 |
0.0163 | 0.8046 | 0.6813 | 0.0223 | 0.8579 | 0.7534 | 1e-10 | 67 |
0.0161 | 0.8047 | 0.6812 | 0.0226 | 0.8566 | 0.7513 | 1e-10 | 68 |
0.0161 | 0.8047 | 0.6813 | 0.0230 | 0.8564 | 0.7510 | 1e-10 | 69 |
0.0164 | 0.8049 | 0.6820 | 0.0231 | 0.8553 | 0.7493 | 1e-10 | 70 |
0.0160 | 0.8041 | 0.6812 | 0.0227 | 0.8574 | 0.7525 | 1e-10 | 71 |
0.0161 | 0.8074 | 0.6852 | 0.0222 | 0.8575 | 0.7527 | 1e-10 | 72 |
0.0161 | 0.7989 | 0.6748 | 0.0228 | 0.8563 | 0.7509 | 1e-10 | 73 |
0.0161 | 0.8009 | 0.6772 | 0.0224 | 0.8569 | 0.7518 | 1e-10 | 74 |
0.0160 | 0.8039 | 0.6803 | 0.0228 | 0.8561 | 0.7506 | 1e-10 | 75 |
0.0160 | 0.8049 | 0.6823 | 0.0222 | 0.8578 | 0.7532 | 1e-10 | 76 |
0.0159 | 0.8053 | 0.6830 | 0.0224 | 0.8565 | 0.7513 | 1e-10 | 77 |
0.0161 | 0.8060 | 0.6825 | 0.0225 | 0.8574 | 0.7525 | 1e-10 | 78 |
0.0159 | 0.8051 | 0.6825 | 0.0227 | 0.8561 | 0.7506 | 1e-10 | 79 |
0.0161 | 0.8034 | 0.6798 | 0.0227 | 0.8559 | 0.7504 | 1e-10 | 80 |
0.0163 | 0.8076 | 0.6850 | 0.0230 | 0.8569 | 0.7517 | 1e-10 | 81 |
0.0159 | 0.8068 | 0.6840 | 0.0234 | 0.8562 | 0.7506 | 1e-10 | 82 |
0.0161 | 0.8047 | 0.6818 | 0.0228 | 0.8562 | 0.7508 | 1e-10 | 83 |
0.0162 | 0.8036 | 0.6802 | 0.0224 | 0.8563 | 0.7509 | 1e-10 | 84 |
0.0160 | 0.8045 | 0.6816 | 0.0230 | 0.8566 | 0.7514 | 1e-10 | 85 |
0.0161 | 0.8026 | 0.6794 | 0.0233 | 0.8562 | 0.7508 | 1e-10 | 86 |
0.0161 | 0.8036 | 0.6806 | 0.0228 | 0.8562 | 0.7507 | 1e-10 | 87 |
0.0160 | 0.8026 | 0.6791 | 0.0230 | 0.8556 | 0.7497 | 1e-10 | 88 |
0.0164 | 0.8041 | 0.6809 | 0.0227 | 0.8564 | 0.7509 | 1e-10 | 89 |
0.0163 | 0.8029 | 0.6797 | 0.0232 | 0.8552 | 0.7493 | 1e-10 | 90 |
0.0161 | 0.8061 | 0.6833 | 0.0231 | 0.8553 | 0.7495 | 1e-10 | 91 |
0.0160 | 0.8043 | 0.6814 | 0.0222 | 0.8577 | 0.7530 | 1e-10 | 92 |
0.0159 | 0.8058 | 0.6833 | 0.0223 | 0.8560 | 0.7505 | 1e-10 | 93 |
0.0161 | 0.8032 | 0.6796 | 0.0223 | 0.8566 | 0.7514 | 1e-10 | 94 |
0.0162 | 0.8037 | 0.6804 | 0.0228 | 0.8558 | 0.7502 | 1e-10 | 95 |
0.0160 | 0.8037 | 0.6805 | 0.0226 | 0.8568 | 0.7517 | 1e-10 | 96 |
0.0160 | 0.8059 | 0.6835 | 0.0223 | 0.8579 | 0.7533 | 1e-10 | 97 |
0.0160 | 0.8055 | 0.6822 | 0.0229 | 0.8552 | 0.7492 | 1e-10 | 98 |
0.0161 | 0.8042 | 0.6813 | 0.0228 | 0.8559 | 0.7502 | 1e-10 | 99 |
Framework versions
- Transformers 4.27.4
- TensorFlow 2.10.1
- Datasets 2.11.0
- Tokenizers 0.13.3