metadata
license: mit
base_model: indolem/indobert-base-uncased
tags:
- generated_from_trainer
model-index:
- name: nerugm-base-2
results: []
nerugm-base-2
This model is a fine-tuned version of indolem/indobert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3857
- Location Precision: 0.7949
- Location Recall: 0.8611
- Location F1: 0.8267
- Location Number: 72
- Organization Precision: 0.7711
- Organization Recall: 0.8533
- Organization F1: 0.8101
- Organization Number: 75
- Person Precision: 0.8816
- Person Recall: 0.9371
- Person F1: 0.9085
- Person Number: 143
- Quantity Precision: 0.6667
- Quantity Recall: 0.7826
- Quantity F1: 0.72
- Quantity Number: 23
- Time Precision: 0.8214
- Time Recall: 0.8846
- Time F1: 0.8519
- Time Number: 26
- Overall Precision: 0.8179
- Overall Recall: 0.8879
- Overall F1: 0.8515
- Overall Accuracy: 0.9642
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: 5e-05
- train_batch_size: 16
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 100.0
Training results
Training Loss | Epoch | Step | Validation Loss | Location Precision | Location Recall | Location F1 | Location Number | Organization Precision | Organization Recall | Organization F1 | Organization Number | Person Precision | Person Recall | Person F1 | Person Number | Quantity Precision | Quantity Recall | Quantity F1 | Quantity Number | Time Precision | Time Recall | Time F1 | Time Number | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0.3502 | 1.0 | 106 | 0.1648 | 0.6941 | 0.8194 | 0.7516 | 72 | 0.6630 | 0.8133 | 0.7305 | 75 | 0.85 | 0.9510 | 0.8977 | 143 | 0.4444 | 0.6957 | 0.5424 | 23 | 0.6061 | 0.7692 | 0.6780 | 26 | 0.7192 | 0.8614 | 0.7839 | 0.9522 |
0.1178 | 2.0 | 212 | 0.1486 | 0.7875 | 0.875 | 0.8289 | 72 | 0.568 | 0.9467 | 0.7100 | 75 | 0.8808 | 0.9301 | 0.9048 | 143 | 0.4706 | 0.6957 | 0.5614 | 23 | 0.8462 | 0.8462 | 0.8462 | 26 | 0.7332 | 0.8997 | 0.8079 | 0.9537 |
0.0781 | 3.0 | 318 | 0.1573 | 0.8133 | 0.8472 | 0.8299 | 72 | 0.6667 | 0.9333 | 0.7778 | 75 | 0.8535 | 0.9371 | 0.8933 | 143 | 0.68 | 0.7391 | 0.7083 | 23 | 0.8462 | 0.8462 | 0.8462 | 26 | 0.7835 | 0.8968 | 0.8363 | 0.9552 |
0.0572 | 4.0 | 424 | 0.1722 | 0.8 | 0.8333 | 0.8163 | 72 | 0.7703 | 0.76 | 0.7651 | 75 | 0.8466 | 0.9650 | 0.9020 | 143 | 0.5667 | 0.7391 | 0.6415 | 23 | 0.6774 | 0.8077 | 0.7368 | 26 | 0.7855 | 0.8643 | 0.8230 | 0.9580 |
0.0359 | 5.0 | 530 | 0.1548 | 0.7711 | 0.8889 | 0.8258 | 72 | 0.7253 | 0.88 | 0.7952 | 75 | 0.8882 | 0.9441 | 0.9153 | 143 | 0.6786 | 0.8261 | 0.7451 | 23 | 0.9167 | 0.8462 | 0.8800 | 26 | 0.8095 | 0.9027 | 0.8536 | 0.9642 |
0.0236 | 6.0 | 636 | 0.1820 | 0.7703 | 0.7917 | 0.7808 | 72 | 0.7284 | 0.7867 | 0.7564 | 75 | 0.8571 | 0.9231 | 0.8889 | 143 | 0.6667 | 0.7826 | 0.72 | 23 | 0.7857 | 0.8462 | 0.8148 | 26 | 0.7912 | 0.8496 | 0.8193 | 0.9605 |
0.0164 | 7.0 | 742 | 0.2388 | 0.7683 | 0.875 | 0.8182 | 72 | 0.6598 | 0.8533 | 0.7442 | 75 | 0.8616 | 0.9580 | 0.9073 | 143 | 0.6667 | 0.8696 | 0.7547 | 23 | 0.7097 | 0.8462 | 0.7719 | 26 | 0.7669 | 0.9027 | 0.8293 | 0.9567 |
0.0131 | 8.0 | 848 | 0.2180 | 0.775 | 0.8611 | 0.8158 | 72 | 0.6988 | 0.7733 | 0.7342 | 75 | 0.8442 | 0.9091 | 0.8754 | 143 | 0.6207 | 0.7826 | 0.6923 | 23 | 0.6061 | 0.7692 | 0.6780 | 26 | 0.7599 | 0.8496 | 0.8022 | 0.9582 |
0.0091 | 9.0 | 954 | 0.2615 | 0.8267 | 0.8611 | 0.8435 | 72 | 0.7053 | 0.8933 | 0.7882 | 75 | 0.8418 | 0.9301 | 0.8837 | 143 | 0.6207 | 0.7826 | 0.6923 | 23 | 0.75 | 0.8077 | 0.7778 | 26 | 0.7818 | 0.8879 | 0.8315 | 0.9590 |
0.0099 | 10.0 | 1060 | 0.2422 | 0.8 | 0.8333 | 0.8163 | 72 | 0.7059 | 0.8 | 0.7500 | 75 | 0.8940 | 0.9441 | 0.9184 | 143 | 0.6207 | 0.7826 | 0.6923 | 23 | 0.7667 | 0.8846 | 0.8214 | 26 | 0.8 | 0.8732 | 0.8350 | 0.9620 |
0.0059 | 11.0 | 1166 | 0.2547 | 0.7763 | 0.8194 | 0.7973 | 72 | 0.6882 | 0.8533 | 0.7619 | 75 | 0.8867 | 0.9301 | 0.9078 | 143 | 0.6207 | 0.7826 | 0.6923 | 23 | 0.8214 | 0.8846 | 0.8519 | 26 | 0.7899 | 0.8761 | 0.8308 | 0.9590 |
0.0062 | 12.0 | 1272 | 0.2780 | 0.7838 | 0.8056 | 0.7945 | 72 | 0.7558 | 0.8667 | 0.8075 | 75 | 0.8462 | 0.9231 | 0.8829 | 143 | 0.5862 | 0.7391 | 0.6538 | 23 | 0.7931 | 0.8846 | 0.8364 | 26 | 0.7888 | 0.8702 | 0.8275 | 0.9602 |
0.0037 | 13.0 | 1378 | 0.2757 | 0.7262 | 0.8472 | 0.7821 | 72 | 0.7368 | 0.7467 | 0.7417 | 75 | 0.8782 | 0.9580 | 0.9164 | 143 | 0.6667 | 0.7826 | 0.72 | 23 | 0.8276 | 0.9231 | 0.8727 | 26 | 0.7957 | 0.8732 | 0.8326 | 0.9627 |
0.005 | 14.0 | 1484 | 0.2800 | 0.8026 | 0.8472 | 0.8243 | 72 | 0.6988 | 0.7733 | 0.7342 | 75 | 0.8701 | 0.9371 | 0.9024 | 143 | 0.6333 | 0.8261 | 0.7170 | 23 | 0.8462 | 0.8462 | 0.8462 | 26 | 0.7967 | 0.8673 | 0.8305 | 0.9595 |
0.0058 | 15.0 | 1590 | 0.2717 | 0.8243 | 0.8472 | 0.8356 | 72 | 0.7065 | 0.8667 | 0.7784 | 75 | 0.8590 | 0.9371 | 0.8963 | 143 | 0.64 | 0.6957 | 0.6667 | 23 | 0.7419 | 0.8846 | 0.8070 | 26 | 0.7910 | 0.8820 | 0.8340 | 0.9630 |
0.0046 | 16.0 | 1696 | 0.3064 | 0.8 | 0.8333 | 0.8163 | 72 | 0.6465 | 0.8533 | 0.7356 | 75 | 0.8645 | 0.9371 | 0.8993 | 143 | 0.5625 | 0.7826 | 0.6545 | 23 | 0.7188 | 0.8846 | 0.7931 | 26 | 0.7608 | 0.8820 | 0.8169 | 0.9540 |
0.0063 | 17.0 | 1802 | 0.2858 | 0.7375 | 0.8194 | 0.7763 | 72 | 0.7722 | 0.8133 | 0.7922 | 75 | 0.8491 | 0.9441 | 0.8940 | 143 | 0.6 | 0.7826 | 0.6792 | 23 | 0.8148 | 0.8462 | 0.8302 | 26 | 0.7867 | 0.8702 | 0.8263 | 0.9617 |
0.0033 | 18.0 | 1908 | 0.3041 | 0.7692 | 0.8333 | 0.8 | 72 | 0.7381 | 0.8267 | 0.7799 | 75 | 0.8553 | 0.9510 | 0.9007 | 143 | 0.6207 | 0.7826 | 0.6923 | 23 | 0.7742 | 0.9231 | 0.8421 | 26 | 0.7874 | 0.8850 | 0.8333 | 0.9620 |
0.0033 | 19.0 | 2014 | 0.3013 | 0.8356 | 0.8472 | 0.8414 | 72 | 0.7711 | 0.8533 | 0.8101 | 75 | 0.8742 | 0.9231 | 0.8980 | 143 | 0.6207 | 0.7826 | 0.6923 | 23 | 0.7857 | 0.8462 | 0.8148 | 26 | 0.8159 | 0.8761 | 0.8450 | 0.9607 |
0.0036 | 20.0 | 2120 | 0.2968 | 0.8108 | 0.8333 | 0.8219 | 72 | 0.7333 | 0.88 | 0.8 | 75 | 0.8701 | 0.9371 | 0.9024 | 143 | 0.5862 | 0.7391 | 0.6538 | 23 | 0.8148 | 0.8462 | 0.8302 | 26 | 0.7995 | 0.8820 | 0.8387 | 0.9610 |
0.0038 | 21.0 | 2226 | 0.2894 | 0.7910 | 0.7361 | 0.7626 | 72 | 0.6941 | 0.7867 | 0.7375 | 75 | 0.8808 | 0.9301 | 0.9048 | 143 | 0.6429 | 0.7826 | 0.7059 | 23 | 0.8148 | 0.8462 | 0.8302 | 26 | 0.7961 | 0.8407 | 0.8178 | 0.9577 |
0.004 | 22.0 | 2332 | 0.2999 | 0.7949 | 0.8611 | 0.8267 | 72 | 0.6790 | 0.7333 | 0.7051 | 75 | 0.8693 | 0.9301 | 0.8986 | 143 | 0.6 | 0.7826 | 0.6792 | 23 | 0.8462 | 0.8462 | 0.8462 | 26 | 0.7880 | 0.8555 | 0.8204 | 0.9555 |
0.003 | 23.0 | 2438 | 0.3059 | 0.7848 | 0.8611 | 0.8212 | 72 | 0.7558 | 0.8667 | 0.8075 | 75 | 0.8816 | 0.9371 | 0.9085 | 143 | 0.6 | 0.7826 | 0.6792 | 23 | 0.8148 | 0.8462 | 0.8302 | 26 | 0.8048 | 0.8879 | 0.8443 | 0.9622 |
0.0038 | 24.0 | 2544 | 0.3071 | 0.7821 | 0.8472 | 0.8133 | 72 | 0.6566 | 0.8667 | 0.7471 | 75 | 0.8882 | 0.9441 | 0.9153 | 143 | 0.6 | 0.7826 | 0.6792 | 23 | 0.7586 | 0.8462 | 0.8 | 26 | 0.7758 | 0.8879 | 0.8281 | 0.9582 |
0.0039 | 25.0 | 2650 | 0.3066 | 0.7317 | 0.8333 | 0.7792 | 72 | 0.6905 | 0.7733 | 0.7296 | 75 | 0.8645 | 0.9371 | 0.8993 | 143 | 0.6 | 0.7826 | 0.6792 | 23 | 0.7857 | 0.8462 | 0.8148 | 26 | 0.7704 | 0.8614 | 0.8134 | 0.9572 |
0.0031 | 26.0 | 2756 | 0.3246 | 0.8082 | 0.8194 | 0.8138 | 72 | 0.7209 | 0.8267 | 0.7702 | 75 | 0.8418 | 0.9301 | 0.8837 | 143 | 0.6207 | 0.7826 | 0.6923 | 23 | 0.8519 | 0.8846 | 0.8679 | 26 | 0.7909 | 0.8702 | 0.8287 | 0.9597 |
0.0026 | 27.0 | 2862 | 0.3247 | 0.8108 | 0.8333 | 0.8219 | 72 | 0.6897 | 0.8 | 0.7407 | 75 | 0.8608 | 0.9510 | 0.9037 | 143 | 0.6333 | 0.8261 | 0.7170 | 23 | 0.8214 | 0.8846 | 0.8519 | 26 | 0.7905 | 0.8791 | 0.8324 | 0.9585 |
0.0041 | 28.0 | 2968 | 0.3042 | 0.7973 | 0.8194 | 0.8082 | 72 | 0.6813 | 0.8267 | 0.7470 | 75 | 0.8816 | 0.9371 | 0.9085 | 143 | 0.6207 | 0.7826 | 0.6923 | 23 | 0.8148 | 0.8462 | 0.8302 | 26 | 0.7909 | 0.8702 | 0.8287 | 0.9592 |
0.0034 | 29.0 | 3074 | 0.3233 | 0.8356 | 0.8472 | 0.8414 | 72 | 0.7386 | 0.8667 | 0.7975 | 75 | 0.8933 | 0.9371 | 0.9147 | 143 | 0.6207 | 0.7826 | 0.6923 | 23 | 0.8462 | 0.8462 | 0.8462 | 26 | 0.8197 | 0.8850 | 0.8511 | 0.9610 |
0.0027 | 30.0 | 3180 | 0.3426 | 0.8243 | 0.8472 | 0.8356 | 72 | 0.6860 | 0.7867 | 0.7329 | 75 | 0.8824 | 0.9441 | 0.9122 | 143 | 0.625 | 0.8696 | 0.7273 | 23 | 0.6875 | 0.8462 | 0.7586 | 26 | 0.7878 | 0.8761 | 0.8296 | 0.9577 |
0.0049 | 31.0 | 3286 | 0.3176 | 0.8108 | 0.8333 | 0.8219 | 72 | 0.6630 | 0.8133 | 0.7305 | 75 | 0.8882 | 0.9441 | 0.9153 | 143 | 0.6207 | 0.7826 | 0.6923 | 23 | 0.8462 | 0.8462 | 0.8462 | 26 | 0.7936 | 0.8732 | 0.8315 | 0.9585 |
0.0027 | 32.0 | 3392 | 0.2955 | 0.8026 | 0.8472 | 0.8243 | 72 | 0.7176 | 0.8133 | 0.7625 | 75 | 0.9 | 0.9441 | 0.9215 | 143 | 0.68 | 0.7391 | 0.7083 | 23 | 0.8846 | 0.8846 | 0.8846 | 26 | 0.8204 | 0.8761 | 0.8474 | 0.9627 |
0.0017 | 33.0 | 3498 | 0.3393 | 0.7692 | 0.8333 | 0.8 | 72 | 0.7590 | 0.84 | 0.7975 | 75 | 0.8758 | 0.9371 | 0.9054 | 143 | 0.5806 | 0.7826 | 0.6667 | 23 | 0.8148 | 0.8462 | 0.8302 | 26 | 0.7984 | 0.8761 | 0.8354 | 0.9592 |
0.0017 | 34.0 | 3604 | 0.3279 | 0.8026 | 0.8472 | 0.8243 | 72 | 0.7831 | 0.8667 | 0.8228 | 75 | 0.8926 | 0.9301 | 0.9110 | 143 | 0.7727 | 0.7391 | 0.7556 | 23 | 0.8462 | 0.8462 | 0.8462 | 26 | 0.8371 | 0.8791 | 0.8576 | 0.9645 |
0.002 | 35.0 | 3710 | 0.3303 | 0.7895 | 0.8333 | 0.8108 | 72 | 0.7333 | 0.88 | 0.8 | 75 | 0.875 | 0.9301 | 0.9017 | 143 | 0.6207 | 0.7826 | 0.6923 | 23 | 0.8462 | 0.8462 | 0.8462 | 26 | 0.8016 | 0.8820 | 0.8399 | 0.9597 |
0.0012 | 36.0 | 3816 | 0.3332 | 0.7975 | 0.875 | 0.8344 | 72 | 0.7412 | 0.84 | 0.7875 | 75 | 0.88 | 0.9231 | 0.9010 | 143 | 0.6667 | 0.7826 | 0.72 | 23 | 0.8462 | 0.8462 | 0.8462 | 26 | 0.8120 | 0.8791 | 0.8442 | 0.9637 |
0.001 | 37.0 | 3922 | 0.3381 | 0.8 | 0.8333 | 0.8163 | 72 | 0.7033 | 0.8533 | 0.7711 | 75 | 0.8926 | 0.9301 | 0.9110 | 143 | 0.6667 | 0.7826 | 0.72 | 23 | 0.84 | 0.8077 | 0.8235 | 26 | 0.8065 | 0.8732 | 0.8385 | 0.9605 |
0.0021 | 38.0 | 4028 | 0.3417 | 0.8 | 0.8333 | 0.8163 | 72 | 0.7349 | 0.8133 | 0.7722 | 75 | 0.8831 | 0.9510 | 0.9158 | 143 | 0.6429 | 0.7826 | 0.7059 | 23 | 0.8462 | 0.8462 | 0.8462 | 26 | 0.8115 | 0.8761 | 0.8426 | 0.9607 |
0.0026 | 39.0 | 4134 | 0.3772 | 0.7733 | 0.8056 | 0.7891 | 72 | 0.7590 | 0.84 | 0.7975 | 75 | 0.8590 | 0.9371 | 0.8963 | 143 | 0.6333 | 0.8261 | 0.7170 | 23 | 0.8148 | 0.8462 | 0.8302 | 26 | 0.7978 | 0.8732 | 0.8338 | 0.9587 |
0.0021 | 40.0 | 4240 | 0.3320 | 0.7733 | 0.8056 | 0.7891 | 72 | 0.7792 | 0.8 | 0.7895 | 75 | 0.8933 | 0.9371 | 0.9147 | 143 | 0.7619 | 0.6957 | 0.7273 | 23 | 0.7586 | 0.8462 | 0.8 | 26 | 0.8239 | 0.8555 | 0.8394 | 0.9607 |
0.0013 | 41.0 | 4346 | 0.3372 | 0.7922 | 0.8472 | 0.8188 | 72 | 0.6739 | 0.8267 | 0.7425 | 75 | 0.8766 | 0.9441 | 0.9091 | 143 | 0.7037 | 0.8261 | 0.76 | 23 | 0.88 | 0.8462 | 0.8627 | 26 | 0.7973 | 0.8820 | 0.8375 | 0.9620 |
0.0013 | 42.0 | 4452 | 0.3549 | 0.7632 | 0.8056 | 0.7838 | 72 | 0.7381 | 0.8267 | 0.7799 | 75 | 0.8701 | 0.9371 | 0.9024 | 143 | 0.6667 | 0.7826 | 0.72 | 23 | 0.8214 | 0.8846 | 0.8519 | 26 | 0.7995 | 0.8702 | 0.8333 | 0.9602 |
0.0003 | 43.0 | 4558 | 0.3622 | 0.7470 | 0.8611 | 0.8 | 72 | 0.7079 | 0.84 | 0.7683 | 75 | 0.8710 | 0.9441 | 0.9060 | 143 | 0.6429 | 0.7826 | 0.7059 | 23 | 0.8846 | 0.8846 | 0.8846 | 26 | 0.7900 | 0.8879 | 0.8361 | 0.9605 |
0.0032 | 44.0 | 4664 | 0.3586 | 0.7625 | 0.8472 | 0.8026 | 72 | 0.6882 | 0.8533 | 0.7619 | 75 | 0.8710 | 0.9441 | 0.9060 | 143 | 0.6552 | 0.8261 | 0.7308 | 23 | 0.7857 | 0.8462 | 0.8148 | 26 | 0.7818 | 0.8879 | 0.8315 | 0.9580 |
0.001 | 45.0 | 4770 | 0.3700 | 0.7821 | 0.8472 | 0.8133 | 72 | 0.7442 | 0.8533 | 0.7950 | 75 | 0.8831 | 0.9510 | 0.9158 | 143 | 0.6552 | 0.8261 | 0.7308 | 23 | 0.8148 | 0.8462 | 0.8302 | 26 | 0.8075 | 0.8909 | 0.8471 | 0.9620 |
0.0034 | 46.0 | 4876 | 0.3390 | 0.8333 | 0.8333 | 0.8333 | 72 | 0.75 | 0.84 | 0.7925 | 75 | 0.8824 | 0.9441 | 0.9122 | 143 | 0.6552 | 0.8261 | 0.7308 | 23 | 0.8148 | 0.8462 | 0.8302 | 26 | 0.8192 | 0.8820 | 0.8494 | 0.9602 |
0.0018 | 47.0 | 4982 | 0.3375 | 0.7848 | 0.8611 | 0.8212 | 72 | 0.7284 | 0.7867 | 0.7564 | 75 | 0.8710 | 0.9441 | 0.9060 | 143 | 0.6667 | 0.7826 | 0.72 | 23 | 0.8462 | 0.8462 | 0.8462 | 26 | 0.8043 | 0.8732 | 0.8373 | 0.9632 |
0.0017 | 48.0 | 5088 | 0.3310 | 0.7867 | 0.8194 | 0.8027 | 72 | 0.7590 | 0.84 | 0.7975 | 75 | 0.8940 | 0.9441 | 0.9184 | 143 | 0.6667 | 0.7826 | 0.72 | 23 | 0.8462 | 0.8462 | 0.8462 | 26 | 0.8204 | 0.8761 | 0.8474 | 0.9632 |
0.0014 | 49.0 | 5194 | 0.3212 | 0.8133 | 0.8472 | 0.8299 | 72 | 0.7558 | 0.8667 | 0.8075 | 75 | 0.8824 | 0.9441 | 0.9122 | 143 | 0.6786 | 0.8261 | 0.7451 | 23 | 0.88 | 0.8462 | 0.8627 | 26 | 0.8229 | 0.8909 | 0.8555 | 0.9625 |
0.0011 | 50.0 | 5300 | 0.3110 | 0.7867 | 0.8194 | 0.8027 | 72 | 0.75 | 0.84 | 0.7925 | 75 | 0.8882 | 0.9441 | 0.9153 | 143 | 0.6667 | 0.7826 | 0.72 | 23 | 0.8214 | 0.8846 | 0.8519 | 26 | 0.8142 | 0.8791 | 0.8454 | 0.9622 |
0.0005 | 51.0 | 5406 | 0.3082 | 0.8133 | 0.8472 | 0.8299 | 72 | 0.7765 | 0.88 | 0.825 | 75 | 0.9060 | 0.9441 | 0.9247 | 143 | 0.6429 | 0.7826 | 0.7059 | 23 | 0.8214 | 0.8846 | 0.8519 | 26 | 0.8301 | 0.8938 | 0.8608 | 0.9660 |
0.0003 | 52.0 | 5512 | 0.3176 | 0.775 | 0.8611 | 0.8158 | 72 | 0.7471 | 0.8667 | 0.8025 | 75 | 0.8940 | 0.9441 | 0.9184 | 143 | 0.6538 | 0.7391 | 0.6939 | 23 | 0.8214 | 0.8846 | 0.8519 | 26 | 0.8118 | 0.8909 | 0.8495 | 0.9647 |
0.0004 | 53.0 | 5618 | 0.3314 | 0.8243 | 0.8472 | 0.8356 | 72 | 0.7444 | 0.8933 | 0.8121 | 75 | 0.9 | 0.9441 | 0.9215 | 143 | 0.6296 | 0.7391 | 0.68 | 23 | 0.8214 | 0.8846 | 0.8519 | 26 | 0.8211 | 0.8938 | 0.8559 | 0.9647 |
0.0002 | 54.0 | 5724 | 0.3242 | 0.7848 | 0.8611 | 0.8212 | 72 | 0.7619 | 0.8533 | 0.8050 | 75 | 0.9007 | 0.9510 | 0.9252 | 143 | 0.6538 | 0.7391 | 0.6939 | 23 | 0.8214 | 0.8846 | 0.8519 | 26 | 0.8207 | 0.8909 | 0.8543 | 0.9657 |
0.0005 | 55.0 | 5830 | 0.3395 | 0.7875 | 0.875 | 0.8289 | 72 | 0.7412 | 0.84 | 0.7875 | 75 | 0.8947 | 0.9510 | 0.9220 | 143 | 0.6296 | 0.7391 | 0.68 | 23 | 0.8214 | 0.8846 | 0.8519 | 26 | 0.8118 | 0.8909 | 0.8495 | 0.9627 |
0.0001 | 56.0 | 5936 | 0.3326 | 0.7875 | 0.875 | 0.8289 | 72 | 0.7326 | 0.84 | 0.7826 | 75 | 0.9007 | 0.9510 | 0.9252 | 143 | 0.68 | 0.7391 | 0.7083 | 23 | 0.8214 | 0.8846 | 0.8519 | 26 | 0.8162 | 0.8909 | 0.8519 | 0.9647 |
0.0008 | 57.0 | 6042 | 0.3388 | 0.7848 | 0.8611 | 0.8212 | 72 | 0.7442 | 0.8533 | 0.7950 | 75 | 0.8766 | 0.9441 | 0.9091 | 143 | 0.6296 | 0.7391 | 0.68 | 23 | 0.8519 | 0.8846 | 0.8679 | 26 | 0.8070 | 0.8879 | 0.8455 | 0.9640 |
0.0005 | 58.0 | 6148 | 0.3485 | 0.7975 | 0.875 | 0.8344 | 72 | 0.7444 | 0.8933 | 0.8121 | 75 | 0.8645 | 0.9371 | 0.8993 | 143 | 0.6538 | 0.7391 | 0.6939 | 23 | 0.8214 | 0.8846 | 0.8519 | 26 | 0.8042 | 0.8968 | 0.8480 | 0.9622 |
0.0004 | 59.0 | 6254 | 0.3447 | 0.7848 | 0.8611 | 0.8212 | 72 | 0.7442 | 0.8533 | 0.7950 | 75 | 0.9 | 0.9441 | 0.9215 | 143 | 0.6071 | 0.7391 | 0.6667 | 23 | 0.88 | 0.8462 | 0.8627 | 26 | 0.8152 | 0.8850 | 0.8487 | 0.9627 |
0.0017 | 60.0 | 6360 | 0.3944 | 0.7875 | 0.875 | 0.8289 | 72 | 0.6979 | 0.8933 | 0.7836 | 75 | 0.8645 | 0.9371 | 0.8993 | 143 | 0.5806 | 0.7826 | 0.6667 | 23 | 0.8462 | 0.8462 | 0.8462 | 26 | 0.7835 | 0.8968 | 0.8363 | 0.9560 |
0.0002 | 61.0 | 6466 | 0.3860 | 0.8052 | 0.8611 | 0.8322 | 72 | 0.7333 | 0.88 | 0.8 | 75 | 0.8590 | 0.9371 | 0.8963 | 143 | 0.6923 | 0.7826 | 0.7347 | 23 | 0.8148 | 0.8462 | 0.8302 | 26 | 0.8032 | 0.8909 | 0.8448 | 0.9600 |
0.0001 | 62.0 | 6572 | 0.3513 | 0.7922 | 0.8472 | 0.8188 | 72 | 0.7738 | 0.8667 | 0.8176 | 75 | 0.8808 | 0.9301 | 0.9048 | 143 | 0.68 | 0.7391 | 0.7083 | 23 | 0.8148 | 0.8462 | 0.8302 | 26 | 0.8187 | 0.8791 | 0.8478 | 0.9630 |
0.0013 | 63.0 | 6678 | 0.3541 | 0.7875 | 0.875 | 0.8289 | 72 | 0.7174 | 0.88 | 0.7904 | 75 | 0.8710 | 0.9441 | 0.9060 | 143 | 0.68 | 0.7391 | 0.7083 | 23 | 0.8148 | 0.8462 | 0.8302 | 26 | 0.7995 | 0.8938 | 0.8440 | 0.9630 |
0.0007 | 64.0 | 6784 | 0.3446 | 0.7126 | 0.8611 | 0.7799 | 72 | 0.7470 | 0.8267 | 0.7848 | 75 | 0.8766 | 0.9441 | 0.9091 | 143 | 0.6429 | 0.7826 | 0.7059 | 23 | 0.8214 | 0.8846 | 0.8519 | 26 | 0.7895 | 0.8850 | 0.8345 | 0.9620 |
0.0008 | 65.0 | 6890 | 0.3444 | 0.7683 | 0.875 | 0.8182 | 72 | 0.7531 | 0.8133 | 0.7821 | 75 | 0.8816 | 0.9371 | 0.9085 | 143 | 0.6923 | 0.7826 | 0.7347 | 23 | 0.8148 | 0.8462 | 0.8302 | 26 | 0.8098 | 0.8791 | 0.8430 | 0.9630 |
0.0007 | 66.0 | 6996 | 0.3400 | 0.7778 | 0.875 | 0.8235 | 72 | 0.7284 | 0.7867 | 0.7564 | 75 | 0.8824 | 0.9441 | 0.9122 | 143 | 0.68 | 0.7391 | 0.7083 | 23 | 0.8148 | 0.8462 | 0.8302 | 26 | 0.8065 | 0.8732 | 0.8385 | 0.9627 |
0.0004 | 67.0 | 7102 | 0.3691 | 0.7875 | 0.875 | 0.8289 | 72 | 0.7586 | 0.88 | 0.8148 | 75 | 0.8766 | 0.9441 | 0.9091 | 143 | 0.72 | 0.7826 | 0.7500 | 23 | 0.8148 | 0.8462 | 0.8302 | 26 | 0.8150 | 0.8968 | 0.8539 | 0.9635 |
0.0012 | 68.0 | 7208 | 0.3331 | 0.8052 | 0.8611 | 0.8322 | 72 | 0.7927 | 0.8667 | 0.8280 | 75 | 0.8824 | 0.9441 | 0.9122 | 143 | 0.68 | 0.7391 | 0.7083 | 23 | 0.88 | 0.8462 | 0.8627 | 26 | 0.8315 | 0.8879 | 0.8588 | 0.9655 |
0.0003 | 69.0 | 7314 | 0.3740 | 0.7975 | 0.875 | 0.8344 | 72 | 0.7528 | 0.8933 | 0.8171 | 75 | 0.8758 | 0.9371 | 0.9054 | 143 | 0.72 | 0.7826 | 0.7500 | 23 | 0.8462 | 0.8462 | 0.8462 | 26 | 0.8172 | 0.8968 | 0.8551 | 0.9635 |
0.0001 | 70.0 | 7420 | 0.3710 | 0.7848 | 0.8611 | 0.8212 | 72 | 0.7683 | 0.84 | 0.8025 | 75 | 0.8758 | 0.9371 | 0.9054 | 143 | 0.72 | 0.7826 | 0.7500 | 23 | 0.8462 | 0.8462 | 0.8462 | 26 | 0.8192 | 0.8820 | 0.8494 | 0.9635 |
0.0002 | 71.0 | 7526 | 0.3477 | 0.7949 | 0.8611 | 0.8267 | 72 | 0.7711 | 0.8533 | 0.8101 | 75 | 0.8874 | 0.9371 | 0.9116 | 143 | 0.68 | 0.7391 | 0.7083 | 23 | 0.8462 | 0.8462 | 0.8462 | 26 | 0.8237 | 0.8820 | 0.8519 | 0.9647 |
0.0002 | 72.0 | 7632 | 0.3629 | 0.7778 | 0.875 | 0.8235 | 72 | 0.7442 | 0.8533 | 0.7950 | 75 | 0.8816 | 0.9371 | 0.9085 | 143 | 0.72 | 0.7826 | 0.7500 | 23 | 0.8148 | 0.8462 | 0.8302 | 26 | 0.8113 | 0.8879 | 0.8479 | 0.9642 |
0.0002 | 73.0 | 7738 | 0.3637 | 0.7683 | 0.875 | 0.8182 | 72 | 0.7317 | 0.8 | 0.7643 | 75 | 0.8874 | 0.9371 | 0.9116 | 143 | 0.72 | 0.7826 | 0.7500 | 23 | 0.8148 | 0.8462 | 0.8302 | 26 | 0.8093 | 0.8761 | 0.8414 | 0.9640 |
0.0001 | 74.0 | 7844 | 0.3638 | 0.7683 | 0.875 | 0.8182 | 72 | 0.7195 | 0.7867 | 0.7516 | 75 | 0.8808 | 0.9301 | 0.9048 | 143 | 0.72 | 0.7826 | 0.7500 | 23 | 0.8148 | 0.8462 | 0.8302 | 26 | 0.8038 | 0.8702 | 0.8357 | 0.9632 |
0.0001 | 75.0 | 7950 | 0.3779 | 0.7875 | 0.875 | 0.8289 | 72 | 0.7973 | 0.7867 | 0.7919 | 75 | 0.8816 | 0.9371 | 0.9085 | 143 | 0.72 | 0.7826 | 0.7500 | 23 | 0.8148 | 0.8462 | 0.8302 | 26 | 0.8268 | 0.8732 | 0.8494 | 0.9650 |
0.0001 | 76.0 | 8056 | 0.3797 | 0.7875 | 0.875 | 0.8289 | 72 | 0.7792 | 0.8 | 0.7895 | 75 | 0.8758 | 0.9371 | 0.9054 | 143 | 0.6923 | 0.7826 | 0.7347 | 23 | 0.8148 | 0.8462 | 0.8302 | 26 | 0.8182 | 0.8761 | 0.8462 | 0.9645 |
0.0004 | 77.0 | 8162 | 0.4076 | 0.7975 | 0.875 | 0.8344 | 72 | 0.7471 | 0.8667 | 0.8025 | 75 | 0.8590 | 0.9371 | 0.8963 | 143 | 0.7037 | 0.8261 | 0.76 | 23 | 0.8148 | 0.8462 | 0.8302 | 26 | 0.8059 | 0.8938 | 0.8476 | 0.9615 |
0.0005 | 78.0 | 8268 | 0.3927 | 0.8077 | 0.875 | 0.8400 | 72 | 0.7442 | 0.8533 | 0.7950 | 75 | 0.8645 | 0.9371 | 0.8993 | 143 | 0.6923 | 0.7826 | 0.7347 | 23 | 0.8519 | 0.8846 | 0.8679 | 26 | 0.8118 | 0.8909 | 0.8495 | 0.9625 |
0.0003 | 79.0 | 8374 | 0.4000 | 0.7778 | 0.875 | 0.8235 | 72 | 0.7108 | 0.7867 | 0.7468 | 75 | 0.8701 | 0.9371 | 0.9024 | 143 | 0.6786 | 0.8261 | 0.7451 | 23 | 0.7857 | 0.8462 | 0.8148 | 26 | 0.7941 | 0.8761 | 0.8331 | 0.9607 |
0.0001 | 80.0 | 8480 | 0.3888 | 0.7949 | 0.8611 | 0.8267 | 72 | 0.725 | 0.7733 | 0.7484 | 75 | 0.8816 | 0.9371 | 0.9085 | 143 | 0.72 | 0.7826 | 0.7500 | 23 | 0.8519 | 0.8846 | 0.8679 | 26 | 0.8149 | 0.8702 | 0.8417 | 0.9630 |
0.0001 | 81.0 | 8586 | 0.3982 | 0.7848 | 0.8611 | 0.8212 | 72 | 0.7317 | 0.8 | 0.7643 | 75 | 0.8645 | 0.9371 | 0.8993 | 143 | 0.6667 | 0.7826 | 0.72 | 23 | 0.8214 | 0.8846 | 0.8519 | 26 | 0.8005 | 0.8761 | 0.8366 | 0.9615 |
0.0003 | 82.0 | 8692 | 0.3737 | 0.8158 | 0.8611 | 0.8378 | 72 | 0.7625 | 0.8133 | 0.7871 | 75 | 0.8874 | 0.9371 | 0.9116 | 143 | 0.72 | 0.7826 | 0.7500 | 23 | 0.8519 | 0.8846 | 0.8679 | 26 | 0.8301 | 0.8791 | 0.8539 | 0.9647 |
0.0002 | 83.0 | 8798 | 0.3761 | 0.8052 | 0.8611 | 0.8322 | 72 | 0.7386 | 0.8667 | 0.7975 | 75 | 0.8808 | 0.9301 | 0.9048 | 143 | 0.72 | 0.7826 | 0.7500 | 23 | 0.8214 | 0.8846 | 0.8519 | 26 | 0.8157 | 0.8879 | 0.8503 | 0.9632 |
0.0001 | 84.0 | 8904 | 0.3758 | 0.8052 | 0.8611 | 0.8322 | 72 | 0.7683 | 0.84 | 0.8025 | 75 | 0.8808 | 0.9301 | 0.9048 | 143 | 0.72 | 0.7826 | 0.7500 | 23 | 0.8519 | 0.8846 | 0.8679 | 26 | 0.8260 | 0.8820 | 0.8531 | 0.9640 |
0.0004 | 85.0 | 9010 | 0.3836 | 0.8052 | 0.8611 | 0.8322 | 72 | 0.7386 | 0.8667 | 0.7975 | 75 | 0.875 | 0.9301 | 0.9017 | 143 | 0.6923 | 0.7826 | 0.7347 | 23 | 0.8214 | 0.8846 | 0.8519 | 26 | 0.8113 | 0.8879 | 0.8479 | 0.9630 |
0.0005 | 86.0 | 9116 | 0.3791 | 0.8052 | 0.8611 | 0.8322 | 72 | 0.7778 | 0.84 | 0.8077 | 75 | 0.875 | 0.9301 | 0.9017 | 143 | 0.6923 | 0.7826 | 0.7347 | 23 | 0.8214 | 0.8846 | 0.8519 | 26 | 0.8214 | 0.8820 | 0.8506 | 0.9642 |
0.0004 | 87.0 | 9222 | 0.3863 | 0.7949 | 0.8611 | 0.8267 | 72 | 0.7683 | 0.84 | 0.8025 | 75 | 0.8701 | 0.9371 | 0.9024 | 143 | 0.6923 | 0.7826 | 0.7347 | 23 | 0.8571 | 0.9231 | 0.8889 | 26 | 0.8179 | 0.8879 | 0.8515 | 0.9640 |
0.0004 | 88.0 | 9328 | 0.3743 | 0.7848 | 0.8611 | 0.8212 | 72 | 0.7412 | 0.84 | 0.7875 | 75 | 0.8867 | 0.9301 | 0.9078 | 143 | 0.72 | 0.7826 | 0.7500 | 23 | 0.8889 | 0.9231 | 0.9057 | 26 | 0.8197 | 0.8850 | 0.8511 | 0.9647 |
0.0006 | 89.0 | 9434 | 0.3696 | 0.8 | 0.8333 | 0.8163 | 72 | 0.7792 | 0.8 | 0.7895 | 75 | 0.8867 | 0.9301 | 0.9078 | 143 | 0.72 | 0.7826 | 0.7500 | 23 | 0.8889 | 0.9231 | 0.9057 | 26 | 0.8333 | 0.8702 | 0.8514 | 0.9662 |
0.0002 | 90.0 | 9540 | 0.3719 | 0.7692 | 0.8333 | 0.8 | 72 | 0.7792 | 0.8 | 0.7895 | 75 | 0.8867 | 0.9301 | 0.9078 | 143 | 0.72 | 0.7826 | 0.7500 | 23 | 0.8889 | 0.9231 | 0.9057 | 26 | 0.8263 | 0.8702 | 0.8477 | 0.9662 |
0.0002 | 91.0 | 9646 | 0.3863 | 0.7922 | 0.8472 | 0.8188 | 72 | 0.7901 | 0.8533 | 0.8205 | 75 | 0.8816 | 0.9371 | 0.9085 | 143 | 0.72 | 0.7826 | 0.7500 | 23 | 0.8889 | 0.9231 | 0.9057 | 26 | 0.8315 | 0.8879 | 0.8588 | 0.9642 |
0.0004 | 92.0 | 9752 | 0.3829 | 0.7922 | 0.8472 | 0.8188 | 72 | 0.7875 | 0.84 | 0.8129 | 75 | 0.8874 | 0.9371 | 0.9116 | 143 | 0.72 | 0.7826 | 0.7500 | 23 | 0.8889 | 0.9231 | 0.9057 | 26 | 0.8333 | 0.8850 | 0.8584 | 0.9645 |
0.0002 | 93.0 | 9858 | 0.3783 | 0.7922 | 0.8472 | 0.8188 | 72 | 0.7949 | 0.8267 | 0.8105 | 75 | 0.8816 | 0.9371 | 0.9085 | 143 | 0.72 | 0.7826 | 0.7500 | 23 | 0.8889 | 0.9231 | 0.9057 | 26 | 0.8329 | 0.8820 | 0.8567 | 0.9652 |
0.0001 | 94.0 | 9964 | 0.3858 | 0.7949 | 0.8611 | 0.8267 | 72 | 0.7778 | 0.84 | 0.8077 | 75 | 0.8816 | 0.9371 | 0.9085 | 143 | 0.72 | 0.7826 | 0.7500 | 23 | 0.8889 | 0.9231 | 0.9057 | 26 | 0.8292 | 0.8879 | 0.8575 | 0.9642 |
0.0001 | 95.0 | 10070 | 0.3863 | 0.7949 | 0.8611 | 0.8267 | 72 | 0.7778 | 0.84 | 0.8077 | 75 | 0.8816 | 0.9371 | 0.9085 | 143 | 0.72 | 0.7826 | 0.7500 | 23 | 0.8571 | 0.9231 | 0.8889 | 26 | 0.8269 | 0.8879 | 0.8563 | 0.9640 |
0.0001 | 96.0 | 10176 | 0.3916 | 0.7949 | 0.8611 | 0.8267 | 72 | 0.7778 | 0.84 | 0.8077 | 75 | 0.8816 | 0.9371 | 0.9085 | 143 | 0.7037 | 0.8261 | 0.76 | 23 | 0.8214 | 0.8846 | 0.8519 | 26 | 0.8224 | 0.8879 | 0.8539 | 0.9637 |
0.0001 | 97.0 | 10282 | 0.3898 | 0.7949 | 0.8611 | 0.8267 | 72 | 0.7711 | 0.8533 | 0.8101 | 75 | 0.8816 | 0.9371 | 0.9085 | 143 | 0.7037 | 0.8261 | 0.76 | 23 | 0.8214 | 0.8846 | 0.8519 | 26 | 0.8207 | 0.8909 | 0.8543 | 0.9642 |
0.0001 | 98.0 | 10388 | 0.3881 | 0.7949 | 0.8611 | 0.8267 | 72 | 0.7711 | 0.8533 | 0.8101 | 75 | 0.8816 | 0.9371 | 0.9085 | 143 | 0.7037 | 0.8261 | 0.76 | 23 | 0.8214 | 0.8846 | 0.8519 | 26 | 0.8207 | 0.8909 | 0.8543 | 0.9645 |
0.0001 | 99.0 | 10494 | 0.3857 | 0.7949 | 0.8611 | 0.8267 | 72 | 0.7711 | 0.8533 | 0.8101 | 75 | 0.8816 | 0.9371 | 0.9085 | 143 | 0.6667 | 0.7826 | 0.72 | 23 | 0.8214 | 0.8846 | 0.8519 | 26 | 0.8179 | 0.8879 | 0.8515 | 0.9642 |
0.0001 | 100.0 | 10600 | 0.3857 | 0.7949 | 0.8611 | 0.8267 | 72 | 0.7711 | 0.8533 | 0.8101 | 75 | 0.8816 | 0.9371 | 0.9085 | 143 | 0.6667 | 0.7826 | 0.72 | 23 | 0.8214 | 0.8846 | 0.8519 | 26 | 0.8179 | 0.8879 | 0.8515 | 0.9642 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.15.2