Upload folder using huggingface_hub

1b5776c verified 7 months ago

129 kB

language:
  - en
tags:
  - ColBERT
  - PyLate
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:640000
  - loss:Distillation
datasets:
  - lightonai/ms-marco-en-bge-gemma
pipeline_tag: sentence-similarity
library_name: PyLate
metrics:
  - MaxSim_accuracy@1
  - MaxSim_accuracy@3
  - MaxSim_accuracy@5
  - MaxSim_accuracy@10
  - MaxSim_precision@1
  - MaxSim_precision@3
  - MaxSim_precision@5
  - MaxSim_precision@10
  - MaxSim_recall@1
  - MaxSim_recall@3
  - MaxSim_recall@5
  - MaxSim_recall@10
  - MaxSim_ndcg@10
  - MaxSim_mrr@10
  - MaxSim_map@100
model-index:
  - name: PyLate
    results:
      - task:
          type: py-late-information-retrieval
          name: Py Late Information Retrieval
        dataset:
          name: NanoClimateFEVER
          type: NanoClimateFEVER
        metrics:
          - type: MaxSim_accuracy@1
            value: 0.26
            name: Maxsim Accuracy@1
          - type: MaxSim_accuracy@3
            value: 0.56
            name: Maxsim Accuracy@3
          - type: MaxSim_accuracy@5
            value: 0.64
            name: Maxsim Accuracy@5
          - type: MaxSim_accuracy@10
            value: 0.78
            name: Maxsim Accuracy@10
          - type: MaxSim_precision@1
            value: 0.26
            name: Maxsim Precision@1
          - type: MaxSim_precision@3
            value: 0.19333333333333333
            name: Maxsim Precision@3
          - type: MaxSim_precision@5
            value: 0.16
            name: Maxsim Precision@5
          - type: MaxSim_precision@10
            value: 0.1
            name: Maxsim Precision@10
          - type: MaxSim_recall@1
            value: 0.1383333333333333
            name: Maxsim Recall@1
          - type: MaxSim_recall@3
            value: 0.24999999999999997
            name: Maxsim Recall@3
          - type: MaxSim_recall@5
            value: 0.32166666666666666
            name: Maxsim Recall@5
          - type: MaxSim_recall@10
            value: 0.39066666666666655
            name: Maxsim Recall@10
          - type: MaxSim_ndcg@10
            value: 0.32039147745578483
            name: Maxsim Ndcg@10
          - type: MaxSim_mrr@10
            value: 0.42276984126984124
            name: Maxsim Mrr@10
          - type: MaxSim_map@100
            value: 0.24935334206601034
            name: Maxsim Map@100
      - task:
          type: py-late-information-retrieval
          name: Py Late Information Retrieval
        dataset:
          name: NanoDBPedia
          type: NanoDBPedia
        metrics:
          - type: MaxSim_accuracy@1
            value: 0.78
            name: Maxsim Accuracy@1
          - type: MaxSim_accuracy@3
            value: 0.9
            name: Maxsim Accuracy@3
          - type: MaxSim_accuracy@5
            value: 0.9
            name: Maxsim Accuracy@5
          - type: MaxSim_accuracy@10
            value: 0.94
            name: Maxsim Accuracy@10
          - type: MaxSim_precision@1
            value: 0.78
            name: Maxsim Precision@1
          - type: MaxSim_precision@3
            value: 0.6599999999999998
            name: Maxsim Precision@3
          - type: MaxSim_precision@5
            value: 0.616
            name: Maxsim Precision@5
          - type: MaxSim_precision@10
            value: 0.55
            name: Maxsim Precision@10
          - type: MaxSim_recall@1
            value: 0.09075272085277744
            name: Maxsim Recall@1
          - type: MaxSim_recall@3
            value: 0.16895043381209857
            name: Maxsim Recall@3
          - type: MaxSim_recall@5
            value: 0.24051424266181912
            name: Maxsim Recall@5
          - type: MaxSim_recall@10
            value: 0.36868865362502956
            name: Maxsim Recall@10
          - type: MaxSim_ndcg@10
            value: 0.66624662933317
            name: Maxsim Ndcg@10
          - type: MaxSim_mrr@10
            value: 0.8415238095238096
            name: Maxsim Mrr@10
          - type: MaxSim_map@100
            value: 0.5145725477836222
            name: Maxsim Map@100
      - task:
          type: py-late-information-retrieval
          name: Py Late Information Retrieval
        dataset:
          name: NanoFEVER
          type: NanoFEVER
        metrics:
          - type: MaxSim_accuracy@1
            value: 0.88
            name: Maxsim Accuracy@1
          - type: MaxSim_accuracy@3
            value: 0.98
            name: Maxsim Accuracy@3
          - type: MaxSim_accuracy@5
            value: 1
            name: Maxsim Accuracy@5
          - type: MaxSim_accuracy@10
            value: 1
            name: Maxsim Accuracy@10
          - type: MaxSim_precision@1
            value: 0.88
            name: Maxsim Precision@1
          - type: MaxSim_precision@3
            value: 0.34666666666666657
            name: Maxsim Precision@3
          - type: MaxSim_precision@5
            value: 0.21199999999999997
            name: Maxsim Precision@5
          - type: MaxSim_precision@10
            value: 0.10799999999999997
            name: Maxsim Precision@10
          - type: MaxSim_recall@1
            value: 0.8166666666666668
            name: Maxsim Recall@1
          - type: MaxSim_recall@3
            value: 0.9433333333333332
            name: Maxsim Recall@3
          - type: MaxSim_recall@5
            value: 0.9633333333333333
            name: Maxsim Recall@5
          - type: MaxSim_recall@10
            value: 0.97
            name: Maxsim Recall@10
          - type: MaxSim_ndcg@10
            value: 0.925157785716936
            name: Maxsim Ndcg@10
          - type: MaxSim_mrr@10
            value: 0.935
            name: Maxsim Mrr@10
          - type: MaxSim_map@100
            value: 0.900428388746803
            name: Maxsim Map@100
      - task:
          type: py-late-information-retrieval
          name: Py Late Information Retrieval
        dataset:
          name: NanoFiQA2018
          type: NanoFiQA2018
        metrics:
          - type: MaxSim_accuracy@1
            value: 0.5
            name: Maxsim Accuracy@1
          - type: MaxSim_accuracy@3
            value: 0.7
            name: Maxsim Accuracy@3
          - type: MaxSim_accuracy@5
            value: 0.74
            name: Maxsim Accuracy@5
          - type: MaxSim_accuracy@10
            value: 0.8
            name: Maxsim Accuracy@10
          - type: MaxSim_precision@1
            value: 0.5
            name: Maxsim Precision@1
          - type: MaxSim_precision@3
            value: 0.31999999999999995
            name: Maxsim Precision@3
          - type: MaxSim_precision@5
            value: 0.24
            name: Maxsim Precision@5
          - type: MaxSim_precision@10
            value: 0.142
            name: Maxsim Precision@10
          - type: MaxSim_recall@1
            value: 0.3094126984126984
            name: Maxsim Recall@1
          - type: MaxSim_recall@3
            value: 0.474515873015873
            name: Maxsim Recall@3
          - type: MaxSim_recall@5
            value: 0.5476190476190476
            name: Maxsim Recall@5
          - type: MaxSim_recall@10
            value: 0.6147857142857143
            name: Maxsim Recall@10
          - type: MaxSim_ndcg@10
            value: 0.5449947187566443
            name: Maxsim Ndcg@10
          - type: MaxSim_mrr@10
            value: 0.6068888888888889
            name: Maxsim Mrr@10
          - type: MaxSim_map@100
            value: 0.47848630223690586
            name: Maxsim Map@100
      - task:
          type: py-late-information-retrieval
          name: Py Late Information Retrieval
        dataset:
          name: NanoHotpotQA
          type: NanoHotpotQA
        metrics:
          - type: MaxSim_accuracy@1
            value: 0.92
            name: Maxsim Accuracy@1
          - type: MaxSim_accuracy@3
            value: 0.98
            name: Maxsim Accuracy@3
          - type: MaxSim_accuracy@5
            value: 1
            name: Maxsim Accuracy@5
          - type: MaxSim_accuracy@10
            value: 1
            name: Maxsim Accuracy@10
          - type: MaxSim_precision@1
            value: 0.92
            name: Maxsim Precision@1
          - type: MaxSim_precision@3
            value: 0.5199999999999999
            name: Maxsim Precision@3
          - type: MaxSim_precision@5
            value: 0.3399999999999999
            name: Maxsim Precision@5
          - type: MaxSim_precision@10
            value: 0.17399999999999996
            name: Maxsim Precision@10
          - type: MaxSim_recall@1
            value: 0.46
            name: Maxsim Recall@1
          - type: MaxSim_recall@3
            value: 0.78
            name: Maxsim Recall@3
          - type: MaxSim_recall@5
            value: 0.85
            name: Maxsim Recall@5
          - type: MaxSim_recall@10
            value: 0.87
            name: Maxsim Recall@10
          - type: MaxSim_ndcg@10
            value: 0.8390423470478856
            name: Maxsim Ndcg@10
          - type: MaxSim_mrr@10
            value: 0.9506666666666667
            name: Maxsim Mrr@10
          - type: MaxSim_map@100
            value: 0.7749759887824803
            name: Maxsim Map@100
      - task:
          type: py-late-information-retrieval
          name: Py Late Information Retrieval
        dataset:
          name: NanoMSMARCO
          type: NanoMSMARCO
        metrics:
          - type: MaxSim_accuracy@1
            value: 0.56
            name: Maxsim Accuracy@1
          - type: MaxSim_accuracy@3
            value: 0.72
            name: Maxsim Accuracy@3
          - type: MaxSim_accuracy@5
            value: 0.76
            name: Maxsim Accuracy@5
          - type: MaxSim_accuracy@10
            value: 0.88
            name: Maxsim Accuracy@10
          - type: MaxSim_precision@1
            value: 0.56
            name: Maxsim Precision@1
          - type: MaxSim_precision@3
            value: 0.24
            name: Maxsim Precision@3
          - type: MaxSim_precision@5
            value: 0.15200000000000002
            name: Maxsim Precision@5
          - type: MaxSim_precision@10
            value: 0.088
            name: Maxsim Precision@10
          - type: MaxSim_recall@1
            value: 0.56
            name: Maxsim Recall@1
          - type: MaxSim_recall@3
            value: 0.72
            name: Maxsim Recall@3
          - type: MaxSim_recall@5
            value: 0.76
            name: Maxsim Recall@5
          - type: MaxSim_recall@10
            value: 0.88
            name: Maxsim Recall@10
          - type: MaxSim_ndcg@10
            value: 0.7161567165508727
            name: Maxsim Ndcg@10
          - type: MaxSim_mrr@10
            value: 0.6650476190476189
            name: Maxsim Mrr@10
          - type: MaxSim_map@100
            value: 0.672465263965264
            name: Maxsim Map@100
      - task:
          type: py-late-information-retrieval
          name: Py Late Information Retrieval
        dataset:
          name: NanoNFCorpus
          type: NanoNFCorpus
        metrics:
          - type: MaxSim_accuracy@1
            value: 0.46
            name: Maxsim Accuracy@1
          - type: MaxSim_accuracy@3
            value: 0.58
            name: Maxsim Accuracy@3
          - type: MaxSim_accuracy@5
            value: 0.6
            name: Maxsim Accuracy@5
          - type: MaxSim_accuracy@10
            value: 0.66
            name: Maxsim Accuracy@10
          - type: MaxSim_precision@1
            value: 0.46
            name: Maxsim Precision@1
          - type: MaxSim_precision@3
            value: 0.38
            name: Maxsim Precision@3
          - type: MaxSim_precision@5
            value: 0.32
            name: Maxsim Precision@5
          - type: MaxSim_precision@10
            value: 0.272
            name: Maxsim Precision@10
          - type: MaxSim_recall@1
            value: 0.04317667470348151
            name: Maxsim Recall@1
          - type: MaxSim_recall@3
            value: 0.07996223003774396
            name: Maxsim Recall@3
          - type: MaxSim_recall@5
            value: 0.09447327378743205
            name: Maxsim Recall@5
          - type: MaxSim_recall@10
            value: 0.12091153813606693
            name: Maxsim Recall@10
          - type: MaxSim_ndcg@10
            value: 0.33473796463548466
            name: Maxsim Ndcg@10
          - type: MaxSim_mrr@10
            value: 0.5260238095238096
            name: Maxsim Mrr@10
          - type: MaxSim_map@100
            value: 0.14684740975296695
            name: Maxsim Map@100
      - task:
          type: py-late-information-retrieval
          name: Py Late Information Retrieval
        dataset:
          name: NanoNQ
          type: NanoNQ
        metrics:
          - type: MaxSim_accuracy@1
            value: 0.48
            name: Maxsim Accuracy@1
          - type: MaxSim_accuracy@3
            value: 0.72
            name: Maxsim Accuracy@3
          - type: MaxSim_accuracy@5
            value: 0.8
            name: Maxsim Accuracy@5
          - type: MaxSim_accuracy@10
            value: 0.9
            name: Maxsim Accuracy@10
          - type: MaxSim_precision@1
            value: 0.48
            name: Maxsim Precision@1
          - type: MaxSim_precision@3
            value: 0.24666666666666667
            name: Maxsim Precision@3
          - type: MaxSim_precision@5
            value: 0.16799999999999998
            name: Maxsim Precision@5
          - type: MaxSim_precision@10
            value: 0.09399999999999999
            name: Maxsim Precision@10
          - type: MaxSim_recall@1
            value: 0.46
            name: Maxsim Recall@1
          - type: MaxSim_recall@3
            value: 0.68
            name: Maxsim Recall@3
          - type: MaxSim_recall@5
            value: 0.77
            name: Maxsim Recall@5
          - type: MaxSim_recall@10
            value: 0.85
            name: Maxsim Recall@10
          - type: MaxSim_ndcg@10
            value: 0.6686040003007178
            name: Maxsim Ndcg@10
          - type: MaxSim_mrr@10
            value: 0.6210714285714285
            name: Maxsim Mrr@10
          - type: MaxSim_map@100
            value: 0.6099890727147909
            name: Maxsim Map@100
      - task:
          type: py-late-information-retrieval
          name: Py Late Information Retrieval
        dataset:
          name: NanoQuoraRetrieval
          type: NanoQuoraRetrieval
        metrics:
          - type: MaxSim_accuracy@1
            value: 0.92
            name: Maxsim Accuracy@1
          - type: MaxSim_accuracy@3
            value: 1
            name: Maxsim Accuracy@3
          - type: MaxSim_accuracy@5
            value: 1
            name: Maxsim Accuracy@5
          - type: MaxSim_accuracy@10
            value: 1
            name: Maxsim Accuracy@10
          - type: MaxSim_precision@1
            value: 0.92
            name: Maxsim Precision@1
          - type: MaxSim_precision@3
            value: 0.40666666666666657
            name: Maxsim Precision@3
          - type: MaxSim_precision@5
            value: 0.26
            name: Maxsim Precision@5
          - type: MaxSim_precision@10
            value: 0.13599999999999998
            name: Maxsim Precision@10
          - type: MaxSim_recall@1
            value: 0.8073333333333333
            name: Maxsim Recall@1
          - type: MaxSim_recall@3
            value: 0.9586666666666668
            name: Maxsim Recall@3
          - type: MaxSim_recall@5
            value: 0.9826666666666667
            name: Maxsim Recall@5
          - type: MaxSim_recall@10
            value: 0.9933333333333334
            name: Maxsim Recall@10
          - type: MaxSim_ndcg@10
            value: 0.9578930498899669
            name: Maxsim Ndcg@10
          - type: MaxSim_mrr@10
            value: 0.96
            name: Maxsim Mrr@10
          - type: MaxSim_map@100
            value: 0.9378103896103898
            name: Maxsim Map@100
      - task:
          type: py-late-information-retrieval
          name: Py Late Information Retrieval
        dataset:
          name: NanoSCIDOCS
          type: NanoSCIDOCS
        metrics:
          - type: MaxSim_accuracy@1
            value: 0.46
            name: Maxsim Accuracy@1
          - type: MaxSim_accuracy@3
            value: 0.66
            name: Maxsim Accuracy@3
          - type: MaxSim_accuracy@5
            value: 0.76
            name: Maxsim Accuracy@5
          - type: MaxSim_accuracy@10
            value: 0.86
            name: Maxsim Accuracy@10
          - type: MaxSim_precision@1
            value: 0.46
            name: Maxsim Precision@1
          - type: MaxSim_precision@3
            value: 0.34
            name: Maxsim Precision@3
          - type: MaxSim_precision@5
            value: 0.256
            name: Maxsim Precision@5
          - type: MaxSim_precision@10
            value: 0.19
            name: Maxsim Precision@10
          - type: MaxSim_recall@1
            value: 0.09666666666666668
            name: Maxsim Recall@1
          - type: MaxSim_recall@3
            value: 0.21066666666666664
            name: Maxsim Recall@3
          - type: MaxSim_recall@5
            value: 0.26266666666666666
            name: Maxsim Recall@5
          - type: MaxSim_recall@10
            value: 0.38766666666666666
            name: Maxsim Recall@10
          - type: MaxSim_ndcg@10
            value: 0.3716553413359221
            name: Maxsim Ndcg@10
          - type: MaxSim_mrr@10
            value: 0.5760555555555554
            name: Maxsim Mrr@10
          - type: MaxSim_map@100
            value: 0.27745676706388667
            name: Maxsim Map@100
      - task:
          type: py-late-information-retrieval
          name: Py Late Information Retrieval
        dataset:
          name: NanoArguAna
          type: NanoArguAna
        metrics:
          - type: MaxSim_accuracy@1
            value: 0.2
            name: Maxsim Accuracy@1
          - type: MaxSim_accuracy@3
            value: 0.56
            name: Maxsim Accuracy@3
          - type: MaxSim_accuracy@5
            value: 0.64
            name: Maxsim Accuracy@5
          - type: MaxSim_accuracy@10
            value: 0.82
            name: Maxsim Accuracy@10
          - type: MaxSim_precision@1
            value: 0.2
            name: Maxsim Precision@1
          - type: MaxSim_precision@3
            value: 0.18666666666666668
            name: Maxsim Precision@3
          - type: MaxSim_precision@5
            value: 0.128
            name: Maxsim Precision@5
          - type: MaxSim_precision@10
            value: 0.08199999999999999
            name: Maxsim Precision@10
          - type: MaxSim_recall@1
            value: 0.2
            name: Maxsim Recall@1
          - type: MaxSim_recall@3
            value: 0.56
            name: Maxsim Recall@3
          - type: MaxSim_recall@5
            value: 0.64
            name: Maxsim Recall@5
          - type: MaxSim_recall@10
            value: 0.82
            name: Maxsim Recall@10
          - type: MaxSim_ndcg@10
            value: 0.49503741719510885
            name: Maxsim Ndcg@10
          - type: MaxSim_mrr@10
            value: 0.3925793650793651
            name: Maxsim Mrr@10
          - type: MaxSim_map@100
            value: 0.3970842977571503
            name: Maxsim Map@100
      - task:
          type: py-late-information-retrieval
          name: Py Late Information Retrieval
        dataset:
          name: NanoSciFact
          type: NanoSciFact
        metrics:
          - type: MaxSim_accuracy@1
            value: 0.7
            name: Maxsim Accuracy@1
          - type: MaxSim_accuracy@3
            value: 0.78
            name: Maxsim Accuracy@3
          - type: MaxSim_accuracy@5
            value: 0.8
            name: Maxsim Accuracy@5
          - type: MaxSim_accuracy@10
            value: 0.88
            name: Maxsim Accuracy@10
          - type: MaxSim_precision@1
            value: 0.7
            name: Maxsim Precision@1
          - type: MaxSim_precision@3
            value: 0.27999999999999997
            name: Maxsim Precision@3
          - type: MaxSim_precision@5
            value: 0.18
            name: Maxsim Precision@5
          - type: MaxSim_precision@10
            value: 0.09799999999999999
            name: Maxsim Precision@10
          - type: MaxSim_recall@1
            value: 0.675
            name: Maxsim Recall@1
          - type: MaxSim_recall@3
            value: 0.765
            name: Maxsim Recall@3
          - type: MaxSim_recall@5
            value: 0.8
            name: Maxsim Recall@5
          - type: MaxSim_recall@10
            value: 0.87
            name: Maxsim Recall@10
          - type: MaxSim_ndcg@10
            value: 0.7788958916951562
            name: Maxsim Ndcg@10
          - type: MaxSim_mrr@10
            value: 0.7513571428571428
            name: Maxsim Mrr@10
          - type: MaxSim_map@100
            value: 0.7534500915750916
            name: Maxsim Map@100
      - task:
          type: py-late-information-retrieval
          name: Py Late Information Retrieval
        dataset:
          name: NanoTouche2020
          type: NanoTouche2020
        metrics:
          - type: MaxSim_accuracy@1
            value: 0.8163265306122449
            name: Maxsim Accuracy@1
          - type: MaxSim_accuracy@3
            value: 0.9591836734693877
            name: Maxsim Accuracy@3
          - type: MaxSim_accuracy@5
            value: 0.9591836734693877
            name: Maxsim Accuracy@5
          - type: MaxSim_accuracy@10
            value: 0.9795918367346939
            name: Maxsim Accuracy@10
          - type: MaxSim_precision@1
            value: 0.8163265306122449
            name: Maxsim Precision@1
          - type: MaxSim_precision@3
            value: 0.7074829931972788
            name: Maxsim Precision@3
          - type: MaxSim_precision@5
            value: 0.6204081632653061
            name: Maxsim Precision@5
          - type: MaxSim_precision@10
            value: 0.5102040816326531
            name: Maxsim Precision@10
          - type: MaxSim_recall@1
            value: 0.05518453156908425
            name: Maxsim Recall@1
          - type: MaxSim_recall@3
            value: 0.1473987812718667
            name: Maxsim Recall@3
          - type: MaxSim_recall@5
            value: 0.21441836348902682
            name: Maxsim Recall@5
          - type: MaxSim_recall@10
            value: 0.33183454535355095
            name: Maxsim Recall@10
          - type: MaxSim_ndcg@10
            value: 0.5945921894543182
            name: Maxsim Ndcg@10
          - type: MaxSim_mrr@10
            value: 0.8877551020408163
            name: Maxsim Mrr@10
          - type: MaxSim_map@100
            value: 0.4401324508472191
            name: Maxsim Map@100
      - task:
          type: nano-beir
          name: Nano BEIR
        dataset:
          name: NanoBEIR mean
          type: NanoBEIR_mean
        metrics:
          - type: MaxSim_accuracy@1
            value: 0.6104866562009419
            name: Maxsim Accuracy@1
          - type: MaxSim_accuracy@3
            value: 0.7768602825745682
            name: Maxsim Accuracy@3
          - type: MaxSim_accuracy@5
            value: 0.815321821036107
            name: Maxsim Accuracy@5
          - type: MaxSim_accuracy@10
            value: 0.8845839874411303
            name: Maxsim Accuracy@10
          - type: MaxSim_precision@1
            value: 0.6104866562009419
            name: Maxsim Precision@1
          - type: MaxSim_precision@3
            value: 0.37134484563055986
            name: Maxsim Precision@3
          - type: MaxSim_precision@5
            value: 0.28095447409733126
            name: Maxsim Precision@5
          - type: MaxSim_precision@10
            value: 0.19570800627943483
            name: Maxsim Precision@10
          - type: MaxSim_recall@1
            value: 0.36250204811831094
            name: Maxsim Recall@1
          - type: MaxSim_recall@3
            value: 0.5183456911387884
            name: Maxsim Recall@3
          - type: MaxSim_recall@5
            value: 0.5728737123762044
            name: Maxsim Recall@5
          - type: MaxSim_recall@10
            value: 0.6513759321590022
            name: Maxsim Recall@10
          - type: MaxSim_ndcg@10
            value: 0.6318004253359976
            name: Maxsim Ndcg@10
          - type: MaxSim_mrr@10
            value: 0.7028260945403803
            name: Maxsim Mrr@10
          - type: MaxSim_map@100
            value: 0.5502347933001986
            name: Maxsim Map@100

PyLate

This is a PyLate model trained on the train dataset. It maps sentences & paragraphs to sequences of 128-dimensional dense vectors and can be used for semantic textual similarity using the MaxSim operator.

Model Details

Model Description

Model Type: PyLate model
Document Length: 512 tokens
Query Length: 32 tokens
Output Dimensionality: 128 tokens
Similarity Function: MaxSim
Training Dataset:
- train
Language: en

Model Sources

Documentation: PyLate Documentation
Repository: PyLate on GitHub
Hugging Face: PyLate models on Hugging Face

Full Model Architecture

ColBERT(
  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False, 'architecture': 'ModernBertModel'})
  (1): Dense({'in_features': 768, 'out_features': 128, 'bias': False, 'activation_function': 'torch.nn.modules.linear.Identity', 'use_residual': False})
)

Usage

First install the PyLate library:

pip install -U pylate

Retrieval

Use this model with PyLate to index and retrieve documents. The index uses FastPLAID for efficient similarity search.

Indexing documents

Load the ColBERT model and initialize the PLAID index, then encode and index your documents:

from pylate import indexes, models, retrieve

# Step 1: Load the ColBERT model
model = models.ColBERT(
    model_name_or_path="pylate_model_id",
)

# Step 2: Initialize the PLAID index
index = indexes.PLAID(
    index_folder="pylate-index",
    index_name="index",
    override=True,  # This overwrites the existing index if any
)

# Step 3: Encode the documents
documents_ids = ["1", "2", "3"]
documents = ["document 1 text", "document 2 text", "document 3 text"]

documents_embeddings = model.encode(
    documents,
    batch_size=32,
    is_query=False,  # Ensure that it is set to False to indicate that these are documents, not queries
    show_progress_bar=True,
)

# Step 4: Add document embeddings to the index by providing embeddings and corresponding ids
index.add_documents(
    documents_ids=documents_ids,
    documents_embeddings=documents_embeddings,
)

Note that you do not have to recreate the index and encode the documents every time. Once you have created an index and added the documents, you can re-use the index later by loading it:

# To load an index, simply instantiate it with the correct folder/name and without overriding it
index = indexes.PLAID(
    index_folder="pylate-index",
    index_name="index",
)

Retrieving top-k documents for queries

Once the documents are indexed, you can retrieve the top-k most relevant documents for a given set of queries. To do so, initialize the ColBERT retriever with the index you want to search in, encode the queries and then retrieve the top-k documents to get the top matches ids and relevance scores:

# Step 1: Initialize the ColBERT retriever
retriever = retrieve.ColBERT(index=index)

# Step 2: Encode the queries
queries_embeddings = model.encode(
    ["query for document 3", "query for document 1"],
    batch_size=32,
    is_query=True,  #  # Ensure that it is set to False to indicate that these are queries
    show_progress_bar=True,
)

# Step 3: Retrieve top-k documents
scores = retriever.retrieve(
    queries_embeddings=queries_embeddings,
    k=10,  # Retrieve the top 10 matches for each query
)

Reranking

If you only want to use the ColBERT model to perform reranking on top of your first-stage retrieval pipeline without building an index, you can simply use rank function and pass the queries and documents to rerank:

from pylate import rank, models

queries = [
    "query A",
    "query B",
]

documents = [
    ["document A", "document B"],
    ["document 1", "document C", "document B"],
]

documents_ids = [
    [1, 2],
    [1, 3, 2],
]

model = models.ColBERT(
    model_name_or_path="pylate_model_id",
)

queries_embeddings = model.encode(
    queries,
    is_query=True,
)

documents_embeddings = model.encode(
    documents,
    is_query=False,
)

reranked_documents = rank.rerank(
    documents_ids=documents_ids,
    queries_embeddings=queries_embeddings,
    documents_embeddings=documents_embeddings,
)

Evaluation

Metrics

Py Late Information Retrieval

Dataset: ['NanoClimateFEVER', 'NanoDBPedia', 'NanoFEVER', 'NanoFiQA2018', 'NanoHotpotQA', 'NanoMSMARCO', 'NanoNFCorpus', 'NanoNQ', 'NanoQuoraRetrieval', 'NanoSCIDOCS', 'NanoArguAna', 'NanoSciFact', 'NanoTouche2020']
Evaluated with pylate.evaluation.pylate_information_retrieval_evaluator.PyLateInformationRetrievalEvaluator

Metric	NanoClimateFEVER	NanoDBPedia	NanoFEVER	NanoFiQA2018	NanoHotpotQA	NanoMSMARCO	NanoNFCorpus	NanoNQ	NanoQuoraRetrieval	NanoSCIDOCS	NanoArguAna	NanoSciFact	NanoTouche2020
MaxSim_accuracy@1	0.26	0.78	0.88	0.5	0.92	0.56	0.46	0.48	0.92	0.46	0.2	0.7	0.8163
MaxSim_accuracy@3	0.56	0.9	0.98	0.7	0.98	0.72	0.58	0.72	1.0	0.66	0.56	0.78	0.9592
MaxSim_accuracy@5	0.64	0.9	1.0	0.74	1.0	0.76	0.6	0.8	1.0	0.76	0.64	0.8	0.9592
MaxSim_accuracy@10	0.78	0.94	1.0	0.8	1.0	0.88	0.66	0.9	1.0	0.86	0.82	0.88	0.9796
MaxSim_precision@1	0.26	0.78	0.88	0.5	0.92	0.56	0.46	0.48	0.92	0.46	0.2	0.7	0.8163
MaxSim_precision@3	0.1933	0.66	0.3467	0.32	0.52	0.24	0.38	0.2467	0.4067	0.34	0.1867	0.28	0.7075
MaxSim_precision@5	0.16	0.616	0.212	0.24	0.34	0.152	0.32	0.168	0.26	0.256	0.128	0.18	0.6204
MaxSim_precision@10	0.1	0.55	0.108	0.142	0.174	0.088	0.272	0.094	0.136	0.19	0.082	0.098	0.5102
MaxSim_recall@1	0.1383	0.0908	0.8167	0.3094	0.46	0.56	0.0432	0.46	0.8073	0.0967	0.2	0.675	0.0552
MaxSim_recall@3	0.25	0.169	0.9433	0.4745	0.78	0.72	0.08	0.68	0.9587	0.2107	0.56	0.765	0.1474
MaxSim_recall@5	0.3217	0.2405	0.9633	0.5476	0.85	0.76	0.0945	0.77	0.9827	0.2627	0.64	0.8	0.2144
MaxSim_recall@10	0.3907	0.3687	0.97	0.6148	0.87	0.88	0.1209	0.85	0.9933	0.3877	0.82	0.87	0.3318
MaxSim_ndcg@10	0.3204	0.6662	0.9252	0.545	0.839	0.7162	0.3347	0.6686	0.9579	0.3717	0.495	0.7789	0.5946
MaxSim_mrr@10	0.4228	0.8415	0.935	0.6069	0.9507	0.665	0.526	0.6211	0.96	0.5761	0.3926	0.7514	0.8878
MaxSim_map@100	0.2494	0.5146	0.9004	0.4785	0.775	0.6725	0.1468	0.61	0.9378	0.2775	0.3971	0.7535	0.4401

Nano BEIR

Dataset: NanoBEIR_mean
Evaluated with pylate.evaluation.nano_beir_evaluator.NanoBEIREvaluator

Metric	Value
MaxSim_accuracy@1	0.6105
MaxSim_accuracy@3	0.7769
MaxSim_accuracy@5	0.8153
MaxSim_accuracy@10	0.8846
MaxSim_precision@1	0.6105
MaxSim_precision@3	0.3713
MaxSim_precision@5	0.281
MaxSim_precision@10	0.1957
MaxSim_recall@1	0.3625
MaxSim_recall@3	0.5183
MaxSim_recall@5	0.5729
MaxSim_recall@10	0.6514
MaxSim_ndcg@10	0.6318
MaxSim_mrr@10	0.7028
MaxSim_map@100	0.5502

Training Details

Training Dataset

train

Dataset: train at 1a1ffe7
Size: 640,000 training samples
Columns: query_id, document_ids, and scores

Approximate statistics based on the first 1000 samples:

	query_id	document_ids	scores
type	int	list	list
details	836: ~0.10% 3582: ~0.10% 4599: ~0.10% 4645: ~0.10% 4853: ~0.10% 5154: ~0.10% 7504: ~0.10% 12283: ~0.10% 12335: ~0.10% 12916: ~0.10% 14049: ~0.10% 14828: ~0.10% 15674: ~0.10% 15813: ~0.10% 16728: ~0.10% 22006: ~0.10% 23675: ~0.10% 24199: ~0.10% 25323: ~0.10% 28517: ~0.10% 29213: ~0.10% 32344: ~0.10% 34071: ~0.10% 34604: ~0.10% 35424: ~0.10% 35445: ~0.10% 36148: ~0.10% 37078: ~0.10% 37826: ~0.10% 38185: ~0.10% 40855: ~0.10% 42077: ~0.10% 43614: ~0.10% 45073: ~0.10% 46289: ~0.10% 47507: ~0.10% 48005: ~0.10% 48629: ~0.10% 48785: ~0.10% 49216: ~0.10% 49636: ~0.10% 49970: ~0.10% 52075: ~0.10% 52725: ~0.10% 54142: ~0.10% 54210: ~0.10% 55032: ~0.10% 59546: ~0.10% 60087: ~0.10% 60862: ~0.10% 60941: ~0.10% 61037: ~0.10% 61762: ~0.10% 62649: ~0.10% 63333: ~0.10% 64197: ~0.10% 64879: ~0.10% 67608: ~0.10% 67627: ~0.10% 69463: ~0.10% 70002: ~0.10% 70429: ~0.10% 72166: ~0.10% 72518: ~0.10% 72607: ~0.10% 72791: ~0.10% 73325: ~0.10% 74078: ~0.10% 74857: ~0.10% 75323: ~0.10% 75816: ~0.10% 76929: ~0.10% 77845: ~0.10% 77889: ~0.10% 78077: ~0.10% 78256: ~0.10% 78401: ~0.10% 78798: ~0.10% 80871: ~0.10% 81089: ~0.10% 82179: ~0.10% 82883: ~0.10% 84168: ~0.10% 86891: ~0.10% 88282: ~0.10% 89346: ~0.10% 89386: ~0.10% 90699: ~0.10% 90795: ~0.10% 91367: ~0.10% 91795: ~0.10% 92070: ~0.10% 92523: ~0.10% 92597: ~0.10% 92753: ~0.10% 92787: ~0.10% 96382: ~0.10% 96455: ~0.10% 97274: ~0.10% 97603: ~0.10% 100904: ~0.10% 101205: ~0.10% 101305: ~0.10% 102707: ~0.10% 103074: ~0.10% 105437: ~0.10% 108207: ~0.10% 109776: ~0.10% 112056: ~0.10% 112955: ~0.10% 112977: ~0.10% 113635: ~0.10% 115280: ~0.10% 115551: ~0.10% 116098: ~0.10% 117658: ~0.10% 120255: ~0.10% 120298: ~0.10% 121437: ~0.10% 123429: ~0.10% 125043: ~0.10% 125979: ~0.10% 126851: ~0.10% 128218: ~0.10% 128804: ~0.10% 129598: ~0.10% 131299: ~0.10% 132114: ~0.10% 133696: ~0.10% 134460: ~0.10% 137602: ~0.10% 137679: ~0.10% 138121: ~0.10% 138260: ~0.10% 138823: ~0.10% 139039: ~0.10% 140392: ~0.10% 140651: ~0.10% 142305: ~0.10% 145653: ~0.10% 145683: ~0.10% 145763: ~0.10% 150202: ~0.10% 151135: ~0.10% 152307: ~0.10% 152675: ~0.10% 153693: ~0.10% 154470: ~0.10% 155587: ~0.10% 157602: ~0.10% 157779: ~0.10% 158565: ~0.10% 159177: ~0.10% 159224: ~0.10% 159341: ~0.10% 159892: ~0.10% 161881: ~0.10% 162414: ~0.10% 163765: ~0.10% 165888: ~0.10% 168048: ~0.10% 168425: ~0.10% 168894: ~0.10% 169991: ~0.10% 170731: ~0.10% 171705: ~0.10% 176165: ~0.10% 176798: ~0.10% 180259: ~0.10% 181243: ~0.10% 182102: ~0.10% 182660: ~0.10% 183426: ~0.10% 183930: ~0.10% 184045: ~0.10% 184676: ~0.10% 185294: ~0.10% 186475: ~0.10% 187155: ~0.10% 188198: ~0.10% 191383: ~0.10% 192165: ~0.10% 193507: ~0.10% 194207: ~0.10% 195056: ~0.10% 197377: ~0.10% 198224: ~0.10% 198546: ~0.10% 202122: ~0.10% 203519: ~0.10% 206220: ~0.10% 209739: ~0.10% 210554: ~0.10% 212638: ~0.10% 213096: ~0.10% 213410: ~0.10% 214255: ~0.10% 217541: ~0.10% 219718: ~0.10% 220993: ~0.10% 223241: ~0.10% 224657: ~0.10% 227101: ~0.10% 227497: ~0.10% 227726: ~0.10% 228099: ~0.10% 228451: ~0.10% 230413: ~0.10% 231416: ~0.10% 233312: ~0.10% 234348: ~0.10% 235869: ~0.10% 237784: ~0.10% 240739: ~0.10% 246495: ~0.10% 246821: ~0.10% 248675: ~0.10% 249798: ~0.10% 249962: ~0.10% 249977: ~0.10% 250019: ~0.10% 250548: ~0.10% 251089: ~0.10% 254878: ~0.10% 255183: ~0.10% 255727: ~0.10% 256321: ~0.10% 258276: ~0.10% 260993: ~0.10% 261247: ~0.10% 262123: ~0.10% 262508: ~0.10% 266047: ~0.10% 267089: ~0.10% 267192: ~0.10% 268642: ~0.10% 269025: ~0.10% 273171: ~0.10% 273864: ~0.10% 274521: ~0.10% 274586: ~0.10% 275037: ~0.10% 275643: ~0.10% 276744: ~0.10% 277212: ~0.10% 277990: ~0.10% 279931: ~0.10% 280012: ~0.10% 281699: ~0.10% 282128: ~0.10% 283298: ~0.10% 284268: ~0.10% 285697: ~0.10% 285905: ~0.10% 287456: ~0.10% 287506: ~0.10% 288154: ~0.10% 289046: ~0.10% 292211: ~0.10% 292588: ~0.10% 293357: ~0.10% 293661: ~0.10% 294123: ~0.10% 299287: ~0.10% 300622: ~0.10% 302135: ~0.10% 303224: ~0.10% 304353: ~0.10% 304820: ~0.10% 310215: ~0.10% 310236: ~0.10% 310409: ~0.10% 311231: ~0.10% 312821: ~0.10% 314244: ~0.10% 314415: ~0.10% 314745: ~0.10% 316385: ~0.10% 316883: ~0.10% 317442: ~0.10% 318639: ~0.10% 318652: ~0.10% 320855: ~0.10% 321867: ~0.10% 322114: ~0.10% 323196: ~0.10% 324868: ~0.10% 327581: ~0.10% 329337: ~0.10% 331572: ~0.10% 331650: ~0.10% 331993: ~0.10% 332500: ~0.10% 334757: ~0.10% 336561: ~0.10% 336791: ~0.10% 337002: ~0.10% 338332: ~0.10% 338456: ~0.10% 339065: ~0.10% 339870: ~0.10% 340599: ~0.10% 341156: ~0.10% 342121: ~0.10% 342381: ~0.10% 343411: ~0.10% 344860: ~0.10% 345924: ~0.10% 346421: ~0.10% 346425: ~0.10% 348157: ~0.10% 351281: ~0.10% 351858: ~0.10% 352641: ~0.10% 353748: ~0.10% 357399: ~0.10% 359787: ~0.10% 359893: ~0.10% 360094: ~0.10% 360168: ~0.10% 361127: ~0.10% 362220: ~0.10% 362560: ~0.10% 366835: ~0.10% 367185: ~0.10% 369045: ~0.10% 371113: ~0.10% 376044: ~0.10% 376524: ~0.10% 377231: ~0.10% 377735: ~0.10% 378574: ~0.10% 379749: ~0.10% 379953: ~0.10% 381834: ~0.10% 384039: ~0.10% 384364: ~0.10% 384398: ~0.10% 384751: ~0.10% 385758: ~0.10% 385893: ~0.10% 386098: ~0.10% 387205: ~0.10% 387374: ~0.10% 388450: ~0.10% 388589: ~0.10% 388593: ~0.10% 389571: ~0.10% 389572: ~0.10% 391531: ~0.10% 391857: ~0.10% 393174: ~0.10% 393426: ~0.10% 396601: ~0.10% 396905: ~0.10% 397801: ~0.10% 398011: ~0.10% 398132: ~0.10% 398721: ~0.10% 399016: ~0.10% 401601: ~0.10% 403876: ~0.10% 403897: ~0.10% 404830: ~0.10% 406102: ~0.10% 406397: ~0.10% 407151: ~0.10% 409373: ~0.10% 410084: ~0.10% 410859: ~0.10% 411693: ~0.10% 411984: ~0.10% 412214: ~0.10% 412560: ~0.10% 413117: ~0.10% 416391: ~0.10% 417066: ~0.10% 417198: ~0.10% 417751: ~0.10% 417778: ~0.10% 420257: ~0.10% 420787: ~0.10% 421001: ~0.10% 421045: ~0.10% 421354: ~0.10% 428114: ~0.10% 429057: ~0.10% 429459: ~0.10% 430319: ~0.10% 431215: ~0.10% 431332: ~0.10% 431488: ~0.10% 432097: ~0.10% 432283: ~0.10% 434131: ~0.10% 434934: ~0.10% 435353: ~0.10% 437793: ~0.10% 438297: ~0.10% 438806: ~0.10% 439016: ~0.10% 439129: ~0.10% 439217: ~0.10% 439755: ~0.10% 440343: ~0.10% 440506: ~0.10% 441030: ~0.10% 441509: ~0.10% 443408: ~0.10% 443686: ~0.10% 445516: ~0.10% 445999: ~0.10% 447039: ~0.10% 447219: ~0.10% 447298: ~0.10% 453040: ~0.10% 453745: ~0.10% 454869: ~0.10% 456224: ~0.10% 456251: ~0.10% 457065: ~0.10% 459890: ~0.10% 460010: ~0.10% 463716: ~0.10% 465235: ~0.10% 470470: ~0.10% 471875: ~0.10% 472462: ~0.10% 474016: ~0.10% 479266: ~0.10% 479360: ~0.10% 480621: ~0.10% 483014: ~0.10% 484553: ~0.10% 485031: ~0.10% 485828: ~0.10% 486664: ~0.10% 488266: ~0.10% 489488: ~0.10% 490992: ~0.10% 491894: ~0.10% 491983: ~0.10% 492620: ~0.10% 493035: ~0.10% 493461: ~0.10% 494255: ~0.10% 496473: ~0.10% 496474: ~0.10% 496516: ~0.10% 496813: ~0.10% 496853: ~0.10% 499553: ~0.10% 499565: ~0.10% 499737: ~0.10% 500057: ~0.10% 500546: ~0.10% 501510: ~0.10% 501978: ~0.10% 503905: ~0.10% 510559: ~0.10% 511473: ~0.10% 512440: ~0.10% 513832: ~0.10% 514106: ~0.10% 514902: ~0.10% 515053: ~0.10% 515507: ~0.10% 516205: ~0.10% 517903: ~0.10% 518096: ~0.10% 520796: ~0.10% 521570: ~0.10% 522112: ~0.10% 523814: ~0.10% 525505: ~0.10% 525583: ~0.10% 525764: ~0.10% 528105: ~0.10% 530985: ~0.10% 532014: ~0.10% 534952: ~0.10% 538836: ~0.10% 539326: ~0.10% 539504: ~0.10% 541861: ~0.10% 542925: ~0.10% 543525: ~0.10% 544853: ~0.10% 545091: ~0.10% 546527: ~0.10% 546753: ~0.10% 548007: ~0.10% 548100: ~0.10% 554548: ~0.10% 555064: ~0.10% 560255: ~0.10% 560711: ~0.10% 561084: ~0.10% 561114: ~0.10% 561329: ~0.10% 561838: ~0.10% 561946: ~0.10% 564894: ~0.10% 566884: ~0.10% 568110: ~0.10% 569541: ~0.10% 570881: ~0.10% 571286: ~0.10% 571515: ~0.10% 571577: ~0.10% 572354: ~0.10% 573015: ~0.10% 573283: ~0.10% 577767: ~0.10% 578249: ~0.10% 578805: ~0.10% 580872: ~0.10% 581072: ~0.10% 581684: ~0.10% 582341: ~0.10% 583169: ~0.10% 583322: ~0.10% 583889: ~0.10% 584173: ~0.10% 585406: ~0.10% 585523: ~0.10% 585660: ~0.10% 587005: ~0.10% 587399: ~0.10% 588010: ~0.10% 588337: ~0.10% 590946: ~0.10% 593319: ~0.10% 595246: ~0.10% 597157: ~0.10% 597215: ~0.10% 597368: ~0.10% 597453: ~0.10% 598538: ~0.10% 601120: ~0.10% 604762: ~0.10% 605111: ~0.10% 605547: ~0.10% 606244: ~0.10% 606935: ~0.10% 607099: ~0.10% 609731: ~0.10% 609910: ~0.10% 610485: ~0.10% 613040: ~0.10% 614720: ~0.10% 615525: ~0.10% 616416: ~0.10% 618280: ~0.10% 619151: ~0.10% 619170: ~0.10% 622593: ~0.10% 622755: ~0.10% 623529: ~0.10% 625333: ~0.10% 625780: ~0.10% 626317: ~0.10% 626670: ~0.10% 628299: ~0.10% 628510: ~0.10% 629166: ~0.10% 630995: ~0.10% 632641: ~0.10% 634324: ~0.10% 634750: ~0.10% 636542: ~0.10% 637420: ~0.10% 641046: ~0.10% 643232: ~0.10% 643901: ~0.10% 644517: ~0.10% 645962: ~0.10% 647293: ~0.10% 647443: ~0.10% 648173: ~0.10% 649204: ~0.10% 650521: ~0.10% 651961: ~0.10% 652493: ~0.10% 655888: ~0.10% 656535: ~0.10% 658715: ~0.10% 659035: ~0.10% 659593: ~0.10% 660535: ~0.10% 662154: ~0.10% 662784: ~0.10% 663142: ~0.10% 666319: ~0.10% 666386: ~0.10% 666561: ~0.10% 668151: ~0.10% 668862: ~0.10% 670341: ~0.10% 671801: ~0.10% 673081: ~0.10% 673634: ~0.10% 673875: ~0.10% 673881: ~0.10% 674082: ~0.10% 675319: ~0.10% 675492: ~0.10% 676147: ~0.10% 676238: ~0.10% 676318: ~0.10% 676431: ~0.10% 677459: ~0.10% 678468: ~0.10% 679216: ~0.10% 679307: ~0.10% 680354: ~0.10% 681098: ~0.10% 681873: ~0.10% 684800: ~0.10% 685613: ~0.10% 685690: ~0.10% 686886: ~0.10% 689687: ~0.10% 689748: ~0.10% 694425: ~0.10% 694466: ~0.10% 698130: ~0.10% 702137: ~0.10% 703138: ~0.10% 704067: ~0.10% 704460: ~0.10% 705420: ~0.10% 706199: ~0.10% 706878: ~0.10% 708333: ~0.10% 710580: ~0.10% 710897: ~0.10% 713539: ~0.10% 713584: ~0.10% 714733: ~0.10% 718172: ~0.10% 719545: ~0.10% 719580: ~0.10% 720471: ~0.10% 720690: ~0.10% 722394: ~0.10% 723568: ~0.10% 724334: ~0.10% 724700: ~0.10% 727908: ~0.10% 728088: ~0.10% 729096: ~0.10% 730499: ~0.10% 730711: ~0.10% 733963: ~0.10% 734912: ~0.10% 736431: ~0.10% 738012: ~0.10% 738173: ~0.10% 739026: ~0.10% 739605: ~0.10% 740181: ~0.10% 742066: ~0.10% 742298: ~0.10% 745799: ~0.10% 748392: ~0.10% 748838: ~0.10% 749148: ~0.10% 751762: ~0.10% 752092: ~0.10% 752527: ~0.10% 753568: ~0.10% 755386: ~0.10% 756558: ~0.10% 756736: ~0.10% 758706: ~0.10% 759523: ~0.10% 760550: ~0.10% 762688: ~0.10% 762918: ~0.10% 763569: ~0.10% 763766: ~0.10% 765769: ~0.10% 766789: ~0.10% 768119: ~0.10% 768537: ~0.10% 773106: ~0.10% 775589: ~0.10% 775964: ~0.10% 776055: ~0.10% 777088: ~0.10% 777529: ~0.10% 778375: ~0.10% 781066: ~0.10% 782328: ~0.10% 783231: ~0.10% 784413: ~0.10% 785781: ~0.10% 786250: ~0.10% 786845: ~0.10% 788012: ~0.10% 791857: ~0.10% 792788: ~0.10% 793182: ~0.10% 794187: ~0.10% 794308: ~0.10% 794318: ~0.10% 796097: ~0.10% 796117: ~0.10% 797182: ~0.10% 798215: ~0.10% 802050: ~0.10% 802669: ~0.10% 804168: ~0.10% 804253: ~0.10% 804461: ~0.10% 805743: ~0.10% 808416: ~0.10% 808455: ~0.10% 810577: ~0.10% 811702: ~0.10% 811843: ~0.10% 815923: ~0.10% 816475: ~0.10% 818312: ~0.10% 818521: ~0.10% 819278: ~0.10% 820890: ~0.10% 821615: ~0.10% 823136: ~0.10% 823735: ~0.10% 829476: ~0.10% 830591: ~0.10% 832433: ~0.10% 832597: ~0.10% 833053: ~0.10% 835043: ~0.10% 835759: ~0.10% 837731: ~0.10% 837942: ~0.10% 839448: ~0.10% 840228: ~0.10% 840417: ~0.10% 841851: ~0.10% 843327: ~0.10% 843622: ~0.10% 844870: ~0.10% 846084: ~0.10% 846807: ~0.10% 847076: ~0.10% 847535: ~0.10% 847977: ~0.10% 848075: ~0.10% 848326: ~0.10% 852725: ~0.10% 853465: ~0.10% 856427: ~0.10% 857186: ~0.10% 858377: ~0.10% 858543: ~0.10% 860426: ~0.10% 863804: ~0.10% 866039: ~0.10% 866406: ~0.10% 867180: ~0.10% 868280: ~0.10% 872156: ~0.10% 872791: ~0.10% 872953: ~0.10% 872959: ~0.10% 875015: ~0.10% 876522: ~0.10% 878407: ~0.10% 878710: ~0.10% 878855: ~0.10% 880495: ~0.10% 882732: ~0.10% 884335: ~0.10% 884941: ~0.10% 885893: ~0.10% 886713: ~0.10% 887068: ~0.10% 887751: ~0.10% 888027: ~0.10% 890152: ~0.10% 891137: ~0.10% 891890: ~0.10% 892662: ~0.10% 892973: ~0.10% 893360: ~0.10% 893915: ~0.10% 893976: ~0.10% 894324: ~0.10% 895709: ~0.10% 897065: ~0.10% 898387: ~0.10% 899291: ~0.10% 899604: ~0.10% 900513: ~0.10% 900619: ~0.10% 901170: ~0.10% 902794: ~0.10% 903238: ~0.10% 904294: ~0.10% 904520: ~0.10% 904992: ~0.10% 907212: ~0.10% 908062: ~0.10% 908561: ~0.10% 911034: ~0.10% 911982: ~0.10% 913716: ~0.10% 914819: ~0.10% 915750: ~0.10% 915766: ~0.10% 916125: ~0.10% 916648: ~0.10% 917285: ~0.10% 918194: ~0.10% 926035: ~0.10% 927726: ~0.10% 929821: ~0.10% 930300: ~0.10% 930796: ~0.10% 931617: ~0.10% 932719: ~0.10% 933784: ~0.10% 934378: ~0.10% 935900: ~0.10% 936118: ~0.10% 936336: ~0.10% 937231: ~0.10% 938420: ~0.10% 939184: ~0.10% 939567: ~0.10% 941588: ~0.10% 944093: ~0.10% 944912: ~0.10% 945069: ~0.10% 945659: ~0.10% 946110: ~0.10% 950044: ~0.10% 954101: ~0.10% 954147: ~0.10% 958697: ~0.10% 959530: ~0.10% 961721: ~0.10% 963582: ~0.10% 964471: ~0.10% 965026: ~0.10% 966573: ~0.10% 967330: ~0.10% 968346: ~0.10% 970649: ~0.10% 970873: ~0.10% 971636: ~0.10% 971664: ~0.10% 973555: ~0.10% 973851: ~0.10% 974207: ~0.10% 976896: ~0.10% 981402: ~0.10% 983723: ~0.10% 984358: ~0.10% 984653: ~0.10% 987107: ~0.10% 987167: ~0.10% 994360: ~0.10% 995049: ~0.10% 1002688: ~0.10% 1004305: ~0.10% 1004650: ~0.10% 1004849: ~0.10% 1005118: ~0.10% 1005614: ~0.10% 1005626: ~0.10% 1005669: ~0.10% 1006835: ~0.10% 1011008: ~0.10% 1012299: ~0.10% 1014010: ~0.10% 1014030: ~0.10% 1016549: ~0.10% 1017016: ~0.10% 1017335: ~0.10% 1018386: ~0.10% 1020640: ~0.10% 1021041: ~0.10% 1021411: ~0.10% 1025341: ~0.10% 1025423: ~0.10% 1025767: ~0.10% 1026066: ~0.10% 1026434: ~0.10% 1027516: ~0.10% 1027703: ~0.10% 1028119: ~0.10% 1028642: ~0.10% 1031554: ~0.10% 1032300: ~0.10% 1033639: ~0.10% 1033660: ~0.10% 1034832: ~0.10% 1035274: ~0.10% 1037432: ~0.10% 1037536: ~0.10% 1037759: ~0.10% 1039860: ~0.10% 1041131: ~0.10% 1041892: ~0.10% 1043066: ~0.10% 1044326: ~0.10% 1044905: ~0.10% 1047848: ~0.10% 1048534: ~0.10% 1049477: ~0.10% 1050531: ~0.10% 1052073: ~0.10% 1052617: ~0.10% 1054049: ~0.10% 1055142: ~0.10% 1056933: ~0.10% 1057358: ~0.10% 1057911: ~0.10% 1061411: ~0.10% 1062328: ~0.10% 1062485: ~0.10% 1062534: ~0.10% 1062794: ~0.10% 1063269: ~0.10% 1063467: ~0.10% 1064568: ~0.10% 1064868: ~0.10% 1065481: ~0.10% 1065565: ~0.10% 1067970: ~0.10% 1068014: ~0.10% 1070203: ~0.10% 1070708: ~0.10% 1072038: ~0.10% 1072214: ~0.10% 1074885: ~0.10% 1075308: ~0.10% 1078872: ~0.10% 1078979: ~0.10% 1079266: ~0.10% 1079736: ~0.10% 1080075: ~0.10% 1081716: ~0.10% 1137391: ~0.10% 1138530: ~0.10% 1139697: ~0.10% 1140119: ~0.10% 1140869: ~0.10% 1141527: ~0.10% 1144693: ~0.10% 1145425: ~0.10% 1149162: ~0.10% 1149207: ~0.10% 1150086: ~0.10% 1150398: ~0.10% 1150731: ~0.10% 1151256: ~0.10% 1151403: ~0.10% 1152236: ~0.10% 1153693: ~0.10% 1155859: ~0.10% 1156918: ~0.10% 1158007: ~0.10% 1158559: ~0.10% 1158952: ~0.10% 1159165: ~0.10% 1161242: ~0.10% 1163227: ~0.10% 1166023: ~0.10% 1166231: ~0.10% 1167002: ~0.10% 1169844: ~0.10% 1170663: ~0.10% 1171580: ~0.10% 1172072: ~0.10% 1172083: ~0.10% 1173371: ~0.10% 1173809: ~0.10% 1174049: ~0.10% 1175044: ~0.10% 1175745: ~0.10% 1176061: ~0.10% 1176414: ~0.10% 1176993: ~0.10% 1177449: ~0.10% 1178311: ~0.10% 1179029: ~0.10% 1179069: ~0.10% 1180579: ~0.10% 1181077: ~0.10% 1183293: ~0.10% 1184313: ~0.10% 1185090: ~0.10% 1185669: ~0.10%	size: 16 elements	size: 16 elements

Samples:

query_id	document_ids	scores
`685613`	`[7546874, 1176459, 197677, 2306318, 8541504, ...]`	`[0.9999999992804947, 0.24845418756716053, 0.7594154013647826, 0.26644182105618575, 0.390668914839766, ...]`
`237784`	`[6366584, 4034101, 2325374, 6914618, 6042146, ...]`	`[0.9999999991784339, 0.42233632827946693, 0.5956354295491569, 0.12644415907455164, 0.6636713730105909, ...]`
`904294`	`[448408, 8743975, 49600, 7339401, 2714261, ...]`	`[0.9999999991841937, 0.877629062381539, 0.8330146583389045, 0.3116634796692611, 0.4633524534142185, ...]`

Loss: pylate.losses.distillation.Distillation

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 16
learning_rate: 4e-06
max_steps: 20000
fp16: True
dataloader_drop_last: True
dataloader_num_workers: 8
ddp_find_unused_parameters: False
torch_compile: True
torch_compile_backend: inductor
eval_on_start: True

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: steps
prediction_loss_only: True
per_device_train_batch_size: 16
per_device_eval_batch_size: 8
per_gpu_train_batch_size: None
per_gpu_eval_batch_size: None
gradient_accumulation_steps: 1
eval_accumulation_steps: None
torch_empty_cache_steps: None
learning_rate: 4e-06
weight_decay: 0.0
adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 1e-08
max_grad_norm: 1.0
num_train_epochs: 3.0
max_steps: 20000
lr_scheduler_type: linear
lr_scheduler_kwargs: {}
warmup_ratio: 0.0
warmup_steps: 0
log_level: passive
log_level_replica: warning
log_on_each_node: True
logging_nan_inf_filter: True
save_safetensors: True
save_on_each_node: False
save_only_model: False
restore_callback_states_from_checkpoint: False
no_cuda: False
use_cpu: False
use_mps_device: False
seed: 42
data_seed: None
jit_mode_eval: False
use_ipex: False
bf16: False
fp16: True
fp16_opt_level: O1
half_precision_backend: auto
bf16_full_eval: False
fp16_full_eval: False
tf32: None
local_rank: 0
ddp_backend: None
tpu_num_cores: None
tpu_metrics_debug: False
debug: []
dataloader_drop_last: True
dataloader_num_workers: 8
dataloader_prefetch_factor: None
past_index: -1
disable_tqdm: False
remove_unused_columns: True
label_names: None
load_best_model_at_end: False
ignore_data_skip: False
fsdp: []
fsdp_min_num_params: 0
fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
fsdp_transformer_layer_cls_to_wrap: None
accelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
parallelism_config: None
deepspeed: None
label_smoothing_factor: 0.0
optim: adamw_torch
optim_args: None
adafactor: False
group_by_length: False
length_column_name: length
ddp_find_unused_parameters: False
ddp_bucket_cap_mb: None
ddp_broadcast_buffers: False
dataloader_pin_memory: True
dataloader_persistent_workers: False
skip_memory_metrics: True
use_legacy_prediction_loop: False
push_to_hub: False
resume_from_checkpoint: None
hub_model_id: None
hub_strategy: every_save
hub_private_repo: None
hub_always_push: False
hub_revision: None
gradient_checkpointing: False
gradient_checkpointing_kwargs: None
include_inputs_for_metrics: False
include_for_metrics: []
eval_do_concat_batches: True
fp16_backend: auto
push_to_hub_model_id: None
push_to_hub_organization: None
mp_parameters:
auto_find_batch_size: False
full_determinism: False
torchdynamo: None
ray_scope: last
ddp_timeout: 1800
torch_compile: True
torch_compile_backend: inductor
torch_compile_mode: None
include_tokens_per_second: False
include_num_input_tokens_seen: False
neftune_noise_alpha: None
optim_target_modules: None
batch_eval_metrics: False
eval_on_start: True
use_liger_kernel: False
liger_kernel_config: None
eval_use_gather_object: False
average_tokens_across_devices: False
prompts: None
batch_sampler: batch_sampler
multi_dataset_batch_sampler: proportional
router_mapping: {}
learning_rate_mapping: {}