QA-DeBERTa-v3-large-diff-binary
This model is a fine-tuned version of microsoft/deberta-v3-large on the saiteki-kai/Beavertails-it dataset. It achieves the following results on the evaluation set:
- Loss: 0.0823
- Accuracy: 0.6890
- Macro F1: 0.6419
- Macro Precision: 0.7045
- Macro Recall: 0.6272
- Micro F1: 0.7567
- Micro Precision: 0.7754
- Micro Recall: 0.7390
- Flagged/accuracy: 0.8562
- Flagged/precision: 0.8819
- Flagged/recall: 0.8563
- Flagged/f1: 0.8689
- Flagged/aucpr: 0.9091
- Flagged/fpr: 0.1439
- Animal Abuse/accuracy: 0.9945
- Animal Abuse/precision: 0.7337
- Animal Abuse/recall: 0.8169
- Animal Abuse/f1: 0.7730
- Animal Abuse/fpr: 0.0034
- Animal Abuse/threshold: 0.5
- Child Abuse/accuracy: 0.9964
- Child Abuse/precision: 0.7007
- Child Abuse/recall: 0.6186
- Child Abuse/f1: 0.6571
- Child Abuse/fpr: 0.0015
- Child Abuse/threshold: 0.5
- Controversial Topics,politics/accuracy: 0.9715
- Controversial Topics,politics/precision: 0.5467
- Controversial Topics,politics/recall: 0.4099
- Controversial Topics,politics/f1: 0.4685
- Controversial Topics,politics/fpr: 0.0107
- Controversial Topics,politics/threshold: 0.5
- Discrimination,stereotype,injustice/accuracy: 0.9564
- Discrimination,stereotype,injustice/precision: 0.7313
- Discrimination,stereotype,injustice/recall: 0.7146
- Discrimination,stereotype,injustice/f1: 0.7229
- Discrimination,stereotype,injustice/fpr: 0.0227
- Discrimination,stereotype,injustice/threshold: 0.5
- Drug Abuse,weapons,banned Substance/accuracy: 0.9742
- Drug Abuse,weapons,banned Substance/precision: 0.7637
- Drug Abuse,weapons,banned Substance/recall: 0.7847
- Drug Abuse,weapons,banned Substance/f1: 0.7741
- Drug Abuse,weapons,banned Substance/fpr: 0.0145
- Drug Abuse,weapons,banned Substance/threshold: 0.5
- Financial Crime,property Crime,theft/accuracy: 0.9601
- Financial Crime,property Crime,theft/precision: 0.7676
- Financial Crime,property Crime,theft/recall: 0.8464
- Financial Crime,property Crime,theft/f1: 0.8051
- Financial Crime,property Crime,theft/fpr: 0.0276
- Financial Crime,property Crime,theft/threshold: 0.5
- Hate Speech,offensive Language/accuracy: 0.9506
- Hate Speech,offensive Language/precision: 0.7660
- Hate Speech,offensive Language/recall: 0.6462
- Hate Speech,offensive Language/f1: 0.7010
- Hate Speech,offensive Language/fpr: 0.0194
- Hate Speech,offensive Language/threshold: 0.5
- Misinformation Regarding Ethics,laws And Safety/accuracy: 0.9879
- Misinformation Regarding Ethics,laws And Safety/precision: 0.5179
- Misinformation Regarding Ethics,laws And Safety/recall: 0.0397
- Misinformation Regarding Ethics,laws And Safety/f1: 0.0737
- Misinformation Regarding Ethics,laws And Safety/fpr: 0.0005
- Misinformation Regarding Ethics,laws And Safety/threshold: 0.5
- Non Violent Unethical Behavior/accuracy: 0.8880
- Non Violent Unethical Behavior/precision: 0.7571
- Non Violent Unethical Behavior/recall: 0.6422
- Non Violent Unethical Behavior/f1: 0.6950
- Non Violent Unethical Behavior/fpr: 0.0511
- Non Violent Unethical Behavior/threshold: 0.5
- Privacy Violation/accuracy: 0.9809
- Privacy Violation/precision: 0.7844
- Privacy Violation/recall: 0.8439
- Privacy Violation/f1: 0.8131
- Privacy Violation/fpr: 0.0120
- Privacy Violation/threshold: 0.5
- Self Harm/accuracy: 0.9965
- Self Harm/precision: 0.7672
- Self Harm/recall: 0.7073
- Self Harm/f1: 0.7360
- Self Harm/fpr: 0.0015
- Self Harm/threshold: 0.5
- Sexually Explicit,adult Content/accuracy: 0.9843
- Sexually Explicit,adult Content/precision: 0.6691
- Sexually Explicit,adult Content/recall: 0.6876
- Sexually Explicit,adult Content/f1: 0.6783
- Sexually Explicit,adult Content/fpr: 0.0084
- Sexually Explicit,adult Content/threshold: 0.5
- Terrorism,organized Crime/accuracy: 0.9921
- Terrorism,organized Crime/precision: 0.5180
- Terrorism,organized Crime/recall: 0.1497
- Terrorism,organized Crime/f1: 0.2323
- Terrorism,organized Crime/fpr: 0.0011
- Terrorism,organized Crime/threshold: 0.5
- Violence,aiding And Abetting,incitement/accuracy: 0.9221
- Violence,aiding And Abetting,incitement/precision: 0.8400
- Violence,aiding And Abetting,incitement/recall: 0.8736
- Violence,aiding And Abetting,incitement/f1: 0.8565
- Violence,aiding And Abetting,incitement/fpr: 0.0603
- Violence,aiding And Abetting,incitement/threshold: 0.5
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: 6e-06
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Use OptimizerNames.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: 1000
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Macro F1 | Macro Precision | Macro Recall | Micro F1 | Micro Precision | Micro Recall | Flagged/accuracy | Flagged/precision | Flagged/recall | Flagged/f1 | Flagged/aucpr | Flagged/fpr | Animal Abuse/accuracy | Animal Abuse/precision | Animal Abuse/recall | Animal Abuse/f1 | Animal Abuse/fpr | Animal Abuse/threshold | Child Abuse/accuracy | Child Abuse/precision | Child Abuse/recall | Child Abuse/f1 | Child Abuse/fpr | Child Abuse/threshold | Controversial Topics,politics/accuracy | Controversial Topics,politics/precision | Controversial Topics,politics/recall | Controversial Topics,politics/f1 | Controversial Topics,politics/fpr | Controversial Topics,politics/threshold | Discrimination,stereotype,injustice/accuracy | Discrimination,stereotype,injustice/precision | Discrimination,stereotype,injustice/recall | Discrimination,stereotype,injustice/f1 | Discrimination,stereotype,injustice/fpr | Discrimination,stereotype,injustice/threshold | Drug Abuse,weapons,banned Substance/accuracy | Drug Abuse,weapons,banned Substance/precision | Drug Abuse,weapons,banned Substance/recall | Drug Abuse,weapons,banned Substance/f1 | Drug Abuse,weapons,banned Substance/fpr | Drug Abuse,weapons,banned Substance/threshold | Financial Crime,property Crime,theft/accuracy | Financial Crime,property Crime,theft/precision | Financial Crime,property Crime,theft/recall | Financial Crime,property Crime,theft/f1 | Financial Crime,property Crime,theft/fpr | Financial Crime,property Crime,theft/threshold | Hate Speech,offensive Language/accuracy | Hate Speech,offensive Language/precision | Hate Speech,offensive Language/recall | Hate Speech,offensive Language/f1 | Hate Speech,offensive Language/fpr | Hate Speech,offensive Language/threshold | Misinformation Regarding Ethics,laws And Safety/accuracy | Misinformation Regarding Ethics,laws And Safety/precision | Misinformation Regarding Ethics,laws And Safety/recall | Misinformation Regarding Ethics,laws And Safety/f1 | Misinformation Regarding Ethics,laws And Safety/fpr | Misinformation Regarding Ethics,laws And Safety/threshold | Non Violent Unethical Behavior/accuracy | Non Violent Unethical Behavior/precision | Non Violent Unethical Behavior/recall | Non Violent Unethical Behavior/f1 | Non Violent Unethical Behavior/fpr | Non Violent Unethical Behavior/threshold | Privacy Violation/accuracy | Privacy Violation/precision | Privacy Violation/recall | Privacy Violation/f1 | Privacy Violation/fpr | Privacy Violation/threshold | Self Harm/accuracy | Self Harm/precision | Self Harm/recall | Self Harm/f1 | Self Harm/fpr | Self Harm/threshold | Sexually Explicit,adult Content/accuracy | Sexually Explicit,adult Content/precision | Sexually Explicit,adult Content/recall | Sexually Explicit,adult Content/f1 | Sexually Explicit,adult Content/fpr | Sexually Explicit,adult Content/threshold | Terrorism,organized Crime/accuracy | Terrorism,organized Crime/precision | Terrorism,organized Crime/recall | Terrorism,organized Crime/f1 | Terrorism,organized Crime/fpr | Terrorism,organized Crime/threshold | Violence,aiding And Abetting,incitement/accuracy | Violence,aiding And Abetting,incitement/precision | Violence,aiding And Abetting,incitement/recall | Violence,aiding And Abetting,incitement/f1 | Violence,aiding And Abetting,incitement/fpr | Violence,aiding And Abetting,incitement/threshold |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.1083 | 0.2501 | 2114 | 0.1130 | 0.6085 | 0.3411 | 0.4110 | 0.3149 | 0.6512 | 0.7545 | 0.5727 | 0.7506 | 0.8428 | 0.6783 | 0.7517 | 0.8501 | 0.1587 | 0.9886 | 0.0 | 0.0 | 0.0 | 0.0 | 0.5 | 0.9945 | 0.0 | 0.0 | 0.0 | 0.0 | 0.5 | 0.9696 | 0.5889 | 0.0288 | 0.0549 | 0.0006 | 0.5 | 0.9447 | 0.6703 | 0.6002 | 0.6333 | 0.0255 | 0.5 | 0.9666 | 0.7537 | 0.6045 | 0.6709 | 0.0118 | 0.5 | 0.9483 | 0.7344 | 0.7342 | 0.7343 | 0.0286 | 0.5 | 0.9433 | 0.7487 | 0.5524 | 0.6357 | 0.0182 | 0.5 | 0.9878 | 0.0 | 0.0 | 0.0 | 0.0 | 0.5 | 0.8671 | 0.7463 | 0.5015 | 0.5999 | 0.0423 | 0.5 | 0.9691 | 0.7118 | 0.6295 | 0.6681 | 0.0132 | 0.5 | 0.9932 | 0.0 | 0.0 | 0.0 | 0.0 | 0.5 | 0.9759 | 0.0 | 0.0 | 0.0 | 0.0 | 0.5 | 0.9920 | 0.0 | 0.0 | 0.0 | 0.0 | 0.5 | 0.8852 | 0.8004 | 0.7574 | 0.7783 | 0.0685 | 0.5 |
| 0.0926 | 0.5001 | 4228 | 0.0946 | 0.6631 | 0.5346 | 0.5849 | 0.5048 | 0.7278 | 0.7570 | 0.7008 | 0.8376 | 0.8661 | 0.8376 | 0.8516 | 0.8970 | 0.1624 | 0.9934 | 0.8033 | 0.5640 | 0.6627 | 0.0016 | 0.5 | 0.9944 | 0.0 | 0.0 | 0.0 | 0.0000 | 0.5 | 0.9703 | 0.5190 | 0.4083 | 0.4570 | 0.0120 | 0.5 | 0.9519 | 0.6914 | 0.7146 | 0.7028 | 0.0276 | 0.5 | 0.9721 | 0.7609 | 0.7360 | 0.7482 | 0.0138 | 0.5 | 0.9584 | 0.7888 | 0.7814 | 0.7851 | 0.0226 | 0.5 | 0.9479 | 0.7665 | 0.6012 | 0.6739 | 0.0180 | 0.5 | 0.9878 | 0.0 | 0.0 | 0.0 | 0.0000 | 0.5 | 0.8717 | 0.6783 | 0.6739 | 0.6761 | 0.0793 | 0.5 | 0.9795 | 0.7860 | 0.8024 | 0.7941 | 0.0113 | 0.5 | 0.9956 | 0.9091 | 0.3902 | 0.5461 | 0.0003 | 0.5 | 0.9820 | 0.6392 | 0.5743 | 0.6050 | 0.0080 | 0.5 | 0.9920 | 0.0 | 0.0 | 0.0 | 0.0000 | 0.5 | 0.9127 | 0.8462 | 0.8212 | 0.8335 | 0.0541 | 0.5 |
| 0.0925 | 0.7502 | 6342 | 0.0900 | 0.6800 | 0.5825 | 0.6747 | 0.5344 | 0.7306 | 0.7992 | 0.6727 | 0.8361 | 0.8990 | 0.7948 | 0.8437 | 0.9040 | 0.1120 | 0.9947 | 0.8030 | 0.7108 | 0.7540 | 0.0020 | 0.5 | 0.9959 | 0.7821 | 0.3664 | 0.4990 | 0.0006 | 0.5 | 0.9697 | 0.5060 | 0.4381 | 0.4696 | 0.0135 | 0.5 | 0.9552 | 0.7742 | 0.6161 | 0.6862 | 0.0155 | 0.5 | 0.9720 | 0.7549 | 0.7442 | 0.7496 | 0.0144 | 0.5 | 0.9573 | 0.7522 | 0.8368 | 0.7922 | 0.0297 | 0.5 | 0.9497 | 0.8617 | 0.5221 | 0.6502 | 0.0082 | 0.5 | 0.9878 | 0.0 | 0.0 | 0.0 | 0.0 | 0.5 | 0.8843 | 0.8099 | 0.5458 | 0.6521 | 0.0318 | 0.5 | 0.9808 | 0.8489 | 0.7424 | 0.7921 | 0.0069 | 0.5 | 0.9964 | 0.7722 | 0.6780 | 0.7221 | 0.0014 | 0.5 | 0.9821 | 0.7173 | 0.4243 | 0.5332 | 0.0041 | 0.5 | 0.9919 | 0.2222 | 0.0042 | 0.0082 | 0.0001 | 0.5 | 0.9179 | 0.8414 | 0.8521 | 0.8467 | 0.0582 | 0.5 |
| 0.0899 | 1.0002 | 8456 | 0.0891 | 0.6763 | 0.6107 | 0.6765 | 0.5905 | 0.7413 | 0.7723 | 0.7126 | 0.8478 | 0.8806 | 0.8404 | 0.8600 | 0.9049 | 0.1430 | 0.9947 | 0.7768 | 0.7485 | 0.7624 | 0.0025 | 0.5 | 0.9965 | 0.748 | 0.5616 | 0.6415 | 0.0011 | 0.5 | 0.9714 | 0.5453 | 0.4017 | 0.4626 | 0.0106 | 0.5 | 0.9550 | 0.7257 | 0.6973 | 0.7112 | 0.0228 | 0.5 | 0.9698 | 0.6943 | 0.8299 | 0.7561 | 0.0218 | 0.5 | 0.9595 | 0.7922 | 0.7917 | 0.7919 | 0.0224 | 0.5 | 0.9504 | 0.8027 | 0.5916 | 0.6811 | 0.0143 | 0.5 | 0.9878 | 0.0 | 0.0 | 0.0 | 0.0 | 0.5 | 0.8837 | 0.7854 | 0.5710 | 0.6612 | 0.0387 | 0.5 | 0.9803 | 0.8176 | 0.7721 | 0.7942 | 0.0089 | 0.5 | 0.9965 | 0.7627 | 0.6976 | 0.7287 | 0.0015 | 0.5 | 0.9823 | 0.6211 | 0.6786 | 0.6486 | 0.0102 | 0.5 | 0.9921 | 0.5926 | 0.0333 | 0.0630 | 0.0002 | 0.5 | 0.9147 | 0.8070 | 0.8929 | 0.8477 | 0.0774 | 0.5 |
| 0.0843 | 1.2503 | 10570 | 0.0860 | 0.6788 | 0.6183 | 0.6730 | 0.6077 | 0.7472 | 0.7714 | 0.7244 | 0.8500 | 0.8739 | 0.8536 | 0.8636 | 0.9045 | 0.1545 | 0.9945 | 0.7432 | 0.7994 | 0.7703 | 0.0032 | 0.5 | 0.9959 | 0.6305 | 0.6456 | 0.6380 | 0.0021 | 0.5 | 0.9710 | 0.5347 | 0.4180 | 0.4692 | 0.0115 | 0.5 | 0.9529 | 0.6857 | 0.7521 | 0.7174 | 0.0298 | 0.5 | 0.9727 | 0.7441 | 0.7865 | 0.7647 | 0.0161 | 0.5 | 0.9604 | 0.8072 | 0.7794 | 0.7930 | 0.0201 | 0.5 | 0.9505 | 0.7883 | 0.6113 | 0.6886 | 0.0162 | 0.5 | 0.9878 | 0.0 | 0.0 | 0.0 | 0.0 | 0.5 | 0.8840 | 0.7542 | 0.6179 | 0.6792 | 0.0500 | 0.5 | 0.9802 | 0.7831 | 0.8287 | 0.8052 | 0.0119 | 0.5 | 0.9967 | 0.8070 | 0.6732 | 0.7340 | 0.0011 | 0.5 | 0.9829 | 0.6362 | 0.6731 | 0.6541 | 0.0095 | 0.5 | 0.9922 | 0.6765 | 0.0478 | 0.0893 | 0.0002 | 0.5 | 0.9195 | 0.8317 | 0.8744 | 0.8526 | 0.0641 | 0.5 |
| 0.0864 | 1.5004 | 12684 | 0.0851 | 0.6877 | 0.6259 | 0.6722 | 0.6070 | 0.7488 | 0.7857 | 0.7153 | 0.8499 | 0.8911 | 0.8319 | 0.8605 | 0.9083 | 0.1275 | 0.9948 | 0.7709 | 0.7776 | 0.7742 | 0.0027 | 0.5 | 0.9958 | 0.6124 | 0.6547 | 0.6328 | 0.0023 | 0.5 | 0.9730 | 0.5913 | 0.3849 | 0.4663 | 0.0084 | 0.5 | 0.9564 | 0.7592 | 0.6609 | 0.7066 | 0.0181 | 0.5 | 0.9719 | 0.7220 | 0.8160 | 0.7661 | 0.0188 | 0.5 | 0.9598 | 0.7669 | 0.8438 | 0.8035 | 0.0277 | 0.5 | 0.9511 | 0.8083 | 0.5958 | 0.6860 | 0.0139 | 0.5 | 0.9878 | 0.0 | 0.0 | 0.0 | 0.0 | 0.5 | 0.8868 | 0.7723 | 0.6106 | 0.6820 | 0.0447 | 0.5 | 0.9796 | 0.7663 | 0.8446 | 0.8035 | 0.0134 | 0.5 | 0.9965 | 0.7682 | 0.6951 | 0.7298 | 0.0014 | 0.5 | 0.9835 | 0.6662 | 0.6330 | 0.6492 | 0.0078 | 0.5 | 0.9922 | 0.5536 | 0.1289 | 0.2091 | 0.0008 | 0.5 | 0.9217 | 0.8531 | 0.8525 | 0.8528 | 0.0532 | 0.5 |
| 0.0851 | 1.7504 | 14798 | 0.0836 | 0.6871 | 0.6326 | 0.6835 | 0.6059 | 0.7496 | 0.7851 | 0.7171 | 0.8505 | 0.8845 | 0.8412 | 0.8623 | 0.9070 | 0.1378 | 0.9950 | 0.8016 | 0.7456 | 0.7726 | 0.0021 | 0.5 | 0.9964 | 0.6832 | 0.6607 | 0.6718 | 0.0017 | 0.5 | 0.9702 | 0.5164 | 0.4435 | 0.4772 | 0.0131 | 0.5 | 0.9570 | 0.7646 | 0.6634 | 0.7104 | 0.0176 | 0.5 | 0.9733 | 0.7647 | 0.7593 | 0.7620 | 0.0139 | 0.5 | 0.9594 | 0.7675 | 0.8359 | 0.8002 | 0.0273 | 0.5 | 0.9514 | 0.8158 | 0.5906 | 0.6852 | 0.0131 | 0.5 | 0.9878 | 0.0 | 0.0 | 0.0 | 0.0 | 0.5 | 0.8873 | 0.7778 | 0.6063 | 0.6814 | 0.0430 | 0.5 | 0.9802 | 0.7790 | 0.8355 | 0.8062 | 0.0123 | 0.5 | 0.9968 | 0.8192 | 0.6854 | 0.7463 | 0.0010 | 0.5 | 0.9842 | 0.6829 | 0.6399 | 0.6607 | 0.0073 | 0.5 | 0.9922 | 0.5610 | 0.1435 | 0.2285 | 0.0009 | 0.5 | 0.9204 | 0.8350 | 0.8734 | 0.8538 | 0.0625 | 0.5 |
| 0.0864 | 2.0005 | 16912 | 0.0837 | 0.6862 | 0.6272 | 0.7498 | 0.6067 | 0.7524 | 0.7773 | 0.7290 | 0.8534 | 0.8848 | 0.8467 | 0.8653 | 0.9084 | 0.1383 | 0.9947 | 0.7776 | 0.7471 | 0.7620 | 0.0025 | 0.5 | 0.9958 | 0.6016 | 0.6937 | 0.6444 | 0.0026 | 0.5 | 0.9731 | 0.6022 | 0.3632 | 0.4531 | 0.0076 | 0.5 | 0.9545 | 0.7012 | 0.7458 | 0.7228 | 0.0275 | 0.5 | 0.9740 | 0.7707 | 0.7655 | 0.7681 | 0.0136 | 0.5 | 0.9597 | 0.7733 | 0.8291 | 0.8002 | 0.0262 | 0.5 | 0.9516 | 0.8016 | 0.6101 | 0.6929 | 0.0149 | 0.5 | 0.9879 | 1.0 | 0.0014 | 0.0027 | 0.0 | 0.5 | 0.8844 | 0.7371 | 0.6503 | 0.6910 | 0.0575 | 0.5 | 0.9814 | 0.8234 | 0.7923 | 0.8076 | 0.0088 | 0.5 | 0.9966 | 0.7845 | 0.6927 | 0.7358 | 0.0013 | 0.5 | 0.9842 | 0.6944 | 0.6171 | 0.6535 | 0.0067 | 0.5 | 0.9923 | 0.5914 | 0.1143 | 0.1916 | 0.0006 | 0.5 | 0.9210 | 0.8380 | 0.8716 | 0.8545 | 0.0611 | 0.5 |
| 0.085 | 2.2505 | 19026 | 0.0840 | 0.6863 | 0.6373 | 0.7126 | 0.6125 | 0.7516 | 0.7745 | 0.7300 | 0.8526 | 0.8813 | 0.8497 | 0.8652 | 0.9073 | 0.1436 | 0.9949 | 0.7900 | 0.7544 | 0.7717 | 0.0023 | 0.5 | 0.9964 | 0.7228 | 0.5796 | 0.6433 | 0.0012 | 0.5 | 0.9713 | 0.5408 | 0.4245 | 0.4757 | 0.0114 | 0.5 | 0.9557 | 0.7255 | 0.7121 | 0.7188 | 0.0233 | 0.5 | 0.9738 | 0.7501 | 0.8021 | 0.7752 | 0.0160 | 0.5 | 0.9595 | 0.7665 | 0.8399 | 0.8015 | 0.0276 | 0.5 | 0.9506 | 0.7734 | 0.6341 | 0.6969 | 0.0183 | 0.5 | 0.9879 | 0.5217 | 0.0164 | 0.0318 | 0.0002 | 0.5 | 0.8864 | 0.7711 | 0.6095 | 0.6808 | 0.0449 | 0.5 | 0.9799 | 0.7710 | 0.8432 | 0.8055 | 0.0130 | 0.5 | 0.9966 | 0.7994 | 0.6610 | 0.7236 | 0.0011 | 0.5 | 0.9839 | 0.6858 | 0.6109 | 0.6462 | 0.0069 | 0.5 | 0.9922 | 0.5291 | 0.2079 | 0.2985 | 0.0015 | 0.5 | 0.9195 | 0.8285 | 0.8793 | 0.8532 | 0.0660 | 0.5 |
| 0.0818 | 2.5006 | 21140 | 0.0833 | 0.6820 | 0.6462 | 0.6949 | 0.6408 | 0.7544 | 0.7698 | 0.7397 | 0.8549 | 0.8702 | 0.8687 | 0.8695 | 0.9060 | 0.1625 | 0.9949 | 0.7687 | 0.7922 | 0.7802 | 0.0028 | 0.5 | 0.9961 | 0.6464 | 0.6697 | 0.6578 | 0.0020 | 0.5 | 0.9712 | 0.5370 | 0.4370 | 0.4819 | 0.0119 | 0.5 | 0.9565 | 0.7289 | 0.7215 | 0.7252 | 0.0232 | 0.5 | 0.9726 | 0.7229 | 0.8323 | 0.7738 | 0.0190 | 0.5 | 0.9599 | 0.7792 | 0.8209 | 0.7995 | 0.0251 | 0.5 | 0.9518 | 0.8093 | 0.6046 | 0.6921 | 0.0140 | 0.5 | 0.9879 | 0.5152 | 0.0233 | 0.0445 | 0.0003 | 0.5 | 0.8859 | 0.7418 | 0.6534 | 0.6948 | 0.0564 | 0.5 | 0.9791 | 0.7507 | 0.8618 | 0.8024 | 0.0149 | 0.5 | 0.9965 | 0.7639 | 0.7024 | 0.7319 | 0.0015 | 0.5 | 0.9835 | 0.6327 | 0.7464 | 0.6848 | 0.0107 | 0.5 | 0.9919 | 0.4874 | 0.2412 | 0.3227 | 0.0020 | 0.5 | 0.9217 | 0.8444 | 0.8653 | 0.8547 | 0.0578 | 0.5 |
| 0.0828 | 2.7507 | 23254 | 0.0817 | 0.6904 | 0.6398 | 0.7160 | 0.6090 | 0.7534 | 0.7915 | 0.7188 | 0.8538 | 0.8909 | 0.8401 | 0.8648 | 0.9100 | 0.1291 | 0.9952 | 0.8399 | 0.7166 | 0.7733 | 0.0016 | 0.5 | 0.9965 | 0.6990 | 0.6486 | 0.6729 | 0.0016 | 0.5 | 0.9726 | 0.5814 | 0.3800 | 0.4596 | 0.0086 | 0.5 | 0.9572 | 0.7577 | 0.6782 | 0.7158 | 0.0187 | 0.5 | 0.9743 | 0.7642 | 0.7868 | 0.7753 | 0.0145 | 0.5 | 0.9601 | 0.7716 | 0.8376 | 0.8032 | 0.0267 | 0.5 | 0.9517 | 0.8147 | 0.5960 | 0.6884 | 0.0133 | 0.5 | 0.9877 | 0.4364 | 0.0328 | 0.0611 | 0.0005 | 0.5 | 0.8885 | 0.7863 | 0.6028 | 0.6824 | 0.0406 | 0.5 | 0.9805 | 0.7840 | 0.8358 | 0.8091 | 0.0120 | 0.5 | 0.9964 | 0.7393 | 0.7195 | 0.7293 | 0.0017 | 0.5 | 0.9847 | 0.6981 | 0.6393 | 0.6674 | 0.0068 | 0.5 | 0.9921 | 0.5120 | 0.1767 | 0.2628 | 0.0014 | 0.5 | 0.9224 | 0.8400 | 0.8749 | 0.8571 | 0.0604 | 0.5 |
| 0.0838 | 3.0007 | 25368 | 0.0823 | 0.6890 | 0.6419 | 0.7045 | 0.6272 | 0.7567 | 0.7754 | 0.7390 | 0.8562 | 0.8819 | 0.8563 | 0.8689 | 0.9091 | 0.1439 | 0.9945 | 0.7337 | 0.8169 | 0.7730 | 0.0034 | 0.5 | 0.9964 | 0.7007 | 0.6186 | 0.6571 | 0.0015 | 0.5 | 0.9715 | 0.5467 | 0.4099 | 0.4685 | 0.0107 | 0.5 | 0.9564 | 0.7313 | 0.7146 | 0.7229 | 0.0227 | 0.5 | 0.9742 | 0.7637 | 0.7847 | 0.7741 | 0.0145 | 0.5 | 0.9601 | 0.7676 | 0.8464 | 0.8051 | 0.0276 | 0.5 | 0.9506 | 0.7660 | 0.6462 | 0.7010 | 0.0194 | 0.5 | 0.9879 | 0.5179 | 0.0397 | 0.0737 | 0.0005 | 0.5 | 0.8880 | 0.7571 | 0.6422 | 0.6950 | 0.0511 | 0.5 | 0.9809 | 0.7844 | 0.8439 | 0.8131 | 0.0120 | 0.5 | 0.9965 | 0.7672 | 0.7073 | 0.7360 | 0.0015 | 0.5 | 0.9843 | 0.6691 | 0.6876 | 0.6783 | 0.0084 | 0.5 | 0.9921 | 0.5180 | 0.1497 | 0.2323 | 0.0011 | 0.5 | 0.9221 | 0.8400 | 0.8736 | 0.8565 | 0.0603 | 0.5 |
| 0.076 | 3.2508 | 27482 | 0.0837 | 0.6856 | 0.6523 | 0.6858 | 0.6413 | 0.7526 | 0.7720 | 0.7342 | 0.8536 | 0.8839 | 0.8484 | 0.8658 | 0.9083 | 0.1397 | 0.9948 | 0.7901 | 0.7442 | 0.7665 | 0.0023 | 0.5 | 0.9962 | 0.6454 | 0.6997 | 0.6715 | 0.0021 | 0.5 | 0.9698 | 0.5085 | 0.4539 | 0.4796 | 0.0139 | 0.5 | 0.9565 | 0.7399 | 0.6987 | 0.7187 | 0.0212 | 0.5 | 0.9727 | 0.7286 | 0.8207 | 0.7719 | 0.0182 | 0.5 | 0.9598 | 0.7703 | 0.8370 | 0.8023 | 0.0269 | 0.5 | 0.9496 | 0.7531 | 0.6503 | 0.6979 | 0.0210 | 0.5 | 0.9874 | 0.3889 | 0.0575 | 0.1001 | 0.0011 | 0.5 | 0.8875 | 0.7667 | 0.6241 | 0.6880 | 0.0471 | 0.5 | 0.9803 | 0.7767 | 0.8422 | 0.8082 | 0.0126 | 0.5 | 0.9963 | 0.7240 | 0.7293 | 0.7266 | 0.0019 | 0.5 | 0.9847 | 0.7051 | 0.6247 | 0.6625 | 0.0064 | 0.5 | 0.9915 | 0.4609 | 0.3306 | 0.3850 | 0.0031 | 0.5 | 0.9212 | 0.8431 | 0.8649 | 0.8539 | 0.0584 | 0.5 |
| 0.0741 | 3.5008 | 29596 | 0.0826 | 0.6878 | 0.6431 | 0.7004 | 0.6257 | 0.7535 | 0.7799 | 0.7288 | 0.8538 | 0.8836 | 0.8492 | 0.8660 | 0.9084 | 0.1403 | 0.9947 | 0.7587 | 0.7907 | 0.7744 | 0.0029 | 0.5 | 0.9961 | 0.6364 | 0.6727 | 0.6540 | 0.0021 | 0.5 | 0.9719 | 0.5554 | 0.4164 | 0.4760 | 0.0105 | 0.5 | 0.9564 | 0.7443 | 0.6883 | 0.7152 | 0.0204 | 0.5 | 0.9743 | 0.7627 | 0.7897 | 0.7760 | 0.0147 | 0.5 | 0.9612 | 0.7918 | 0.8164 | 0.8039 | 0.0231 | 0.5 | 0.9497 | 0.7632 | 0.6352 | 0.6934 | 0.0194 | 0.5 | 0.9877 | 0.4430 | 0.0479 | 0.0864 | 0.0007 | 0.5 | 0.8875 | 0.7575 | 0.6381 | 0.6927 | 0.0507 | 0.5 | 0.9793 | 0.7563 | 0.8560 | 0.8031 | 0.0143 | 0.5 | 0.9965 | 0.7572 | 0.7073 | 0.7314 | 0.0016 | 0.5 | 0.9841 | 0.6743 | 0.6551 | 0.6646 | 0.0078 | 0.5 | 0.9923 | 0.5563 | 0.1850 | 0.2777 | 0.0012 | 0.5 | 0.9223 | 0.8491 | 0.8609 | 0.8549 | 0.0555 | 0.5 |
| 0.0773 | 3.7509 | 31710 | 0.0833 | 0.6846 | 0.6467 | 0.6959 | 0.6305 | 0.7526 | 0.7667 | 0.7391 | 0.8545 | 0.8831 | 0.8511 | 0.8668 | 0.9085 | 0.1413 | 0.9947 | 0.7646 | 0.7791 | 0.7718 | 0.0028 | 0.5 | 0.9963 | 0.6647 | 0.6667 | 0.6657 | 0.0019 | 0.5 | 0.9727 | 0.5781 | 0.4039 | 0.4756 | 0.0093 | 0.5 | 0.9534 | 0.6842 | 0.7686 | 0.7239 | 0.0307 | 0.5 | 0.9738 | 0.7611 | 0.7809 | 0.7708 | 0.0146 | 0.5 | 0.9605 | 0.7757 | 0.8364 | 0.8049 | 0.0261 | 0.5 | 0.9478 | 0.7263 | 0.6692 | 0.6966 | 0.0248 | 0.5 | 0.9875 | 0.4112 | 0.0602 | 0.1050 | 0.0011 | 0.5 | 0.8832 | 0.7214 | 0.6716 | 0.6956 | 0.0643 | 0.5 | 0.9811 | 0.8134 | 0.7997 | 0.8065 | 0.0095 | 0.5 | 0.9964 | 0.7481 | 0.7098 | 0.7284 | 0.0016 | 0.5 | 0.9844 | 0.6913 | 0.6330 | 0.6609 | 0.0070 | 0.5 | 0.9923 | 0.5444 | 0.2037 | 0.2965 | 0.0014 | 0.5 | 0.9214 | 0.8580 | 0.8443 | 0.8511 | 0.0506 | 0.5 |
| 0.077 | 4.0009 | 33824 | 0.0818 | 0.6855 | 0.6425 | 0.6875 | 0.6310 | 0.7528 | 0.7796 | 0.7277 | 0.8531 | 0.8802 | 0.8519 | 0.8659 | 0.9073 | 0.1454 | 0.9947 | 0.7700 | 0.7689 | 0.7695 | 0.0027 | 0.5 | 0.9963 | 0.6731 | 0.6306 | 0.6512 | 0.0017 | 0.5 | 0.9692 | 0.4970 | 0.4902 | 0.4936 | 0.0157 | 0.5 | 0.9559 | 0.7313 | 0.7044 | 0.7176 | 0.0224 | 0.5 | 0.9742 | 0.7716 | 0.7711 | 0.7713 | 0.0136 | 0.5 | 0.9603 | 0.7730 | 0.8383 | 0.8044 | 0.0265 | 0.5 | 0.9510 | 0.7896 | 0.6176 | 0.6931 | 0.0162 | 0.5 | 0.9874 | 0.3968 | 0.0684 | 0.1167 | 0.0013 | 0.5 | 0.8883 | 0.7764 | 0.6154 | 0.6866 | 0.0440 | 0.5 | 0.9809 | 0.7869 | 0.8415 | 0.8133 | 0.0118 | 0.5 | 0.9954 | 0.6315 | 0.7732 | 0.6952 | 0.0031 | 0.5 | 0.9839 | 0.6607 | 0.6835 | 0.6719 | 0.0087 | 0.5 | 0.9921 | 0.5159 | 0.1684 | 0.2539 | 0.0013 | 0.5 | 0.9231 | 0.8507 | 0.8623 | 0.8564 | 0.0549 | 0.5 |
Framework versions
- Transformers 4.57.1
- Pytorch 2.7.1+cu118
- Datasets 4.4.1
- Tokenizers 0.22.1
- Downloads last month
- 108
Model tree for saiteki-kai/QA-DeBERTa-v3-large-diff-binary
Base model
microsoft/deberta-v3-largeEvaluation results
- Accuracy on saiteki-kai/Beavertails-itself-reported0.689