ILKT

/

2024-06-24_22-31-28_epoch_2

like 0

Follow

Inter-Lingual Knowledge Transfer 4

Evaluation results

• accuracy on MTEB AllegroReviews
  test set self-reported
  22.674
• f1 on MTEB AllegroReviews
  test set self-reported
  20.876
• accuracy on MTEB CBD
  test set self-reported
  56.860
• ap on MTEB CBD
  test set self-reported
  14.979
• f1 on MTEB CBD
  test set self-reported
  47.007
• v_measure on MTEB EightTagsClustering
  test set self-reported
  7.534
• v_measure_std on MTEB EightTagsClustering
  test set self-reported
  0.708
• accuracy on MTEB MassiveIntentClassification (pl)
  test set self-reported
  31.789
• f1 on MTEB MassiveIntentClassification (pl)
  test set self-reported
  27.993
• accuracy on MTEB MassiveIntentClassification (pl)
  validation set self-reported
  30.836
• f1 on MTEB MassiveIntentClassification (pl)
  validation set self-reported
  26.671
• accuracy on MTEB MassiveScenarioClassification (pl)
  test set self-reported
  35.528
• f1 on MTEB MassiveScenarioClassification (pl)
  test set self-reported
  32.998
• accuracy on MTEB MassiveScenarioClassification (pl)
  validation set self-reported
  34.845
• f1 on MTEB MassiveScenarioClassification (pl)
  validation set self-reported
  33.045
• accuracy on MTEB PAC
  test set self-reported
  63.099
• ap on MTEB PAC
  test set self-reported
  73.864
• f1 on MTEB PAC
  test set self-reported
  60.722
• v_measure on MTEB PlscClusteringP2P
  test set self-reported
  33.266
• v_measure on MTEB PlscClusteringS2S
  test set self-reported
  29.852