Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-4800/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-4400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-4600/tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,1444 @@
----
-license: apache-2.0
----
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:124788
+- loss:GISTEmbedLoss
+base_model: Alibaba-NLP/gte-multilingual-base
+widget:
+- source_sentence: 其他机械、设备和有形货物租赁服务代表
+  sentences:
+  - 其他机械和设备租赁服务工作人员
+  - 电子和电信设备及零部件物流经理
+  - 工业主厨
+- source_sentence: 公交车司机
+  sentences:
+  - 表演灯光设计师
+  - 乙烯基地板安装工
+  - 国际巴士司机
+- source_sentence: online communication manager
+  sentences:
+  - trades union official
+  - social media manager
+  - budget manager
+- source_sentence: Projektmanagerin
+  sentences:
+  - Projektmanager/Projektmanagerin
+  - Category-Manager
+  - Infanterist
+- source_sentence: Volksvertreter
+  sentences:
+  - Parlamentarier
+  - Oberbürgermeister
+  - Konsul
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+metrics:
+- cosine_accuracy@1
+- cosine_accuracy@20
+- cosine_accuracy@50
+- cosine_accuracy@100
+- cosine_accuracy@150
+- cosine_accuracy@200
+- cosine_precision@1
+- cosine_precision@20
+- cosine_precision@50
+- cosine_precision@100
+- cosine_precision@150
+- cosine_precision@200
+- cosine_recall@1
+- cosine_recall@20
+- cosine_recall@50
+- cosine_recall@100
+- cosine_recall@150
+- cosine_recall@200
+- cosine_ndcg@1
+- cosine_ndcg@20
+- cosine_ndcg@50
+- cosine_ndcg@100
+- cosine_ndcg@150
+- cosine_ndcg@200
+- cosine_mrr@1
+- cosine_mrr@20
+- cosine_mrr@50
+- cosine_mrr@100
+- cosine_mrr@150
+- cosine_mrr@200
+- cosine_map@1
+- cosine_map@20
+- cosine_map@50
+- cosine_map@100
+- cosine_map@150
+- cosine_map@200
+- cosine_map@500
+model-index:
+- name: SentenceTransformer based on Alibaba-NLP/gte-multilingual-base
+  results:
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: full en
+      type: full_en
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6571428571428571
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@20
+      value: 0.9904761904761905
+      name: Cosine Accuracy@20
+    - type: cosine_accuracy@50
+      value: 0.9904761904761905
+      name: Cosine Accuracy@50
+    - type: cosine_accuracy@100
+      value: 0.9904761904761905
+      name: Cosine Accuracy@100
+    - type: cosine_accuracy@150
+      value: 0.9904761904761905
+      name: Cosine Accuracy@150
+    - type: cosine_accuracy@200
+      value: 0.9904761904761905
+      name: Cosine Accuracy@200
+    - type: cosine_precision@1
+      value: 0.6571428571428571
+      name: Cosine Precision@1
+    - type: cosine_precision@20
+      value: 0.5171428571428571
+      name: Cosine Precision@20
+    - type: cosine_precision@50
+      value: 0.316
+      name: Cosine Precision@50
+    - type: cosine_precision@100
+      value: 0.18895238095238095
+      name: Cosine Precision@100
+    - type: cosine_precision@150
+      value: 0.13384126984126984
+      name: Cosine Precision@150
+    - type: cosine_precision@200
+      value: 0.10433333333333335
+      name: Cosine Precision@200
+    - type: cosine_recall@1
+      value: 0.0678253733846715
+      name: Cosine Recall@1
+    - type: cosine_recall@20
+      value: 0.5470006025464504
+      name: Cosine Recall@20
+    - type: cosine_recall@50
+      value: 0.7399645316315758
+      name: Cosine Recall@50
+    - type: cosine_recall@100
+      value: 0.8452891149669638
+      name: Cosine Recall@100
+    - type: cosine_recall@150
+      value: 0.8838497168796887
+      name: Cosine Recall@150
+    - type: cosine_recall@200
+      value: 0.9109269128757174
+      name: Cosine Recall@200
+    - type: cosine_ndcg@1
+      value: 0.6571428571428571
+      name: Cosine Ndcg@1
+    - type: cosine_ndcg@20
+      value: 0.6953571805621692
+      name: Cosine Ndcg@20
+    - type: cosine_ndcg@50
+      value: 0.7150421121165462
+      name: Cosine Ndcg@50
+    - type: cosine_ndcg@100
+      value: 0.7679394555495317
+      name: Cosine Ndcg@100
+    - type: cosine_ndcg@150
+      value: 0.7856911059911225
+      name: Cosine Ndcg@150
+    - type: cosine_ndcg@200
+      value: 0.7969632777290026
+      name: Cosine Ndcg@200
+    - type: cosine_mrr@1
+      value: 0.6571428571428571
+      name: Cosine Mrr@1
+    - type: cosine_mrr@20
+      value: 0.8138095238095239
+      name: Cosine Mrr@20
+    - type: cosine_mrr@50
+      value: 0.8138095238095239
+      name: Cosine Mrr@50
+    - type: cosine_mrr@100
+      value: 0.8138095238095239
+      name: Cosine Mrr@100
+    - type: cosine_mrr@150
+      value: 0.8138095238095239
+      name: Cosine Mrr@150
+    - type: cosine_mrr@200
+      value: 0.8138095238095239
+      name: Cosine Mrr@200
+    - type: cosine_map@1
+      value: 0.6571428571428571
+      name: Cosine Map@1
+    - type: cosine_map@20
+      value: 0.5578605627627369
+      name: Cosine Map@20
+    - type: cosine_map@50
+      value: 0.5471407389299809
+      name: Cosine Map@50
+    - type: cosine_map@100
+      value: 0.5795933384755297
+      name: Cosine Map@100
+    - type: cosine_map@150
+      value: 0.5874505508842796
+      name: Cosine Map@150
+    - type: cosine_map@200
+      value: 0.5912226659397186
+      name: Cosine Map@200
+    - type: cosine_map@500
+      value: 0.5952587557760031
+      name: Cosine Map@500
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: full es
+      type: full_es
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.12432432432432433
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@20
+      value: 1.0
+      name: Cosine Accuracy@20
+    - type: cosine_accuracy@50
+      value: 1.0
+      name: Cosine Accuracy@50
+    - type: cosine_accuracy@100
+      value: 1.0
+      name: Cosine Accuracy@100
+    - type: cosine_accuracy@150
+      value: 1.0
+      name: Cosine Accuracy@150
+    - type: cosine_accuracy@200
+      value: 1.0
+      name: Cosine Accuracy@200
+    - type: cosine_precision@1
+      value: 0.12432432432432433
+      name: Cosine Precision@1
+    - type: cosine_precision@20
+      value: 0.5718918918918919
+      name: Cosine Precision@20
+    - type: cosine_precision@50
+      value: 0.3885405405405405
+      name: Cosine Precision@50
+    - type: cosine_precision@100
+      value: 0.25172972972972973
+      name: Cosine Precision@100
+    - type: cosine_precision@150
+      value: 0.1904864864864865
+      name: Cosine Precision@150
+    - type: cosine_precision@200
+      value: 0.1521891891891892
+      name: Cosine Precision@200
+    - type: cosine_recall@1
+      value: 0.0036619075252531876
+      name: Cosine Recall@1
+    - type: cosine_recall@20
+      value: 0.3842245968041533
+      name: Cosine Recall@20
+    - type: cosine_recall@50
+      value: 0.5640822196868902
+      name: Cosine Recall@50
+    - type: cosine_recall@100
+      value: 0.6741986120580108
+      name: Cosine Recall@100
+    - type: cosine_recall@150
+      value: 0.7463851968088967
+      name: Cosine Recall@150
+    - type: cosine_recall@200
+      value: 0.7825399601398452
+      name: Cosine Recall@200
+    - type: cosine_ndcg@1
+      value: 0.12432432432432433
+      name: Cosine Ndcg@1
+    - type: cosine_ndcg@20
+      value: 0.6139182209948354
+      name: Cosine Ndcg@20
+    - type: cosine_ndcg@50
+      value: 0.5873893466818746
+      name: Cosine Ndcg@50
+    - type: cosine_ndcg@100
+      value: 0.6144038475288277
+      name: Cosine Ndcg@100
+    - type: cosine_ndcg@150
+      value: 0.6498632077214272
+      name: Cosine Ndcg@150
+    - type: cosine_ndcg@200
+      value: 0.6680602466150343
+      name: Cosine Ndcg@200
+    - type: cosine_mrr@1
+      value: 0.12432432432432433
+      name: Cosine Mrr@1
+    - type: cosine_mrr@20
+      value: 0.5581081081081081
+      name: Cosine Mrr@20
+    - type: cosine_mrr@50
+      value: 0.5581081081081081
+      name: Cosine Mrr@50
+    - type: cosine_mrr@100
+      value: 0.5581081081081081
+      name: Cosine Mrr@100
+    - type: cosine_mrr@150
+      value: 0.5581081081081081
+      name: Cosine Mrr@150
+    - type: cosine_mrr@200
+      value: 0.5581081081081081
+      name: Cosine Mrr@200
+    - type: cosine_map@1
+      value: 0.12432432432432433
+      name: Cosine Map@1
+    - type: cosine_map@20
+      value: 0.47988875190050484
+      name: Cosine Map@20
+    - type: cosine_map@50
+      value: 0.4249833337950364
+      name: Cosine Map@50
+    - type: cosine_map@100
+      value: 0.430155652024808
+      name: Cosine Map@100
+    - type: cosine_map@150
+      value: 0.4458862132745998
+      name: Cosine Map@150
+    - type: cosine_map@200
+      value: 0.45334655744992447
+      name: Cosine Map@200
+    - type: cosine_map@500
+      value: 0.4656066165331343
+      name: Cosine Map@500
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: full de
+      type: full_de
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.2955665024630542
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@20
+      value: 0.9704433497536946
+      name: Cosine Accuracy@20
+    - type: cosine_accuracy@50
+      value: 0.9852216748768473
+      name: Cosine Accuracy@50
+    - type: cosine_accuracy@100
+      value: 0.9852216748768473
+      name: Cosine Accuracy@100
+    - type: cosine_accuracy@150
+      value: 0.9901477832512315
+      name: Cosine Accuracy@150
+    - type: cosine_accuracy@200
+      value: 0.9901477832512315
+      name: Cosine Accuracy@200
+    - type: cosine_precision@1
+      value: 0.2955665024630542
+      name: Cosine Precision@1
+    - type: cosine_precision@20
+      value: 0.5083743842364532
+      name: Cosine Precision@20
+    - type: cosine_precision@50
+      value: 0.3654187192118227
+      name: Cosine Precision@50
+    - type: cosine_precision@100
+      value: 0.24133004926108376
+      name: Cosine Precision@100
+    - type: cosine_precision@150
+      value: 0.18036124794745487
+      name: Cosine Precision@150
+    - type: cosine_precision@200
+      value: 0.14467980295566504
+      name: Cosine Precision@200
+    - type: cosine_recall@1
+      value: 0.01108543831680986
+      name: Cosine Recall@1
+    - type: cosine_recall@20
+      value: 0.3221185941380065
+      name: Cosine Recall@20
+    - type: cosine_recall@50
+      value: 0.5024502430161547
+      name: Cosine Recall@50
+    - type: cosine_recall@100
+      value: 0.6247617904371989
+      name: Cosine Recall@100
+    - type: cosine_recall@150
+      value: 0.6829583450315939
+      name: Cosine Recall@150
+    - type: cosine_recall@200
+      value: 0.7216293640715983
+      name: Cosine Recall@200
+    - type: cosine_ndcg@1
+      value: 0.2955665024630542
+      name: Cosine Ndcg@1
+    - type: cosine_ndcg@20
+      value: 0.5393376062142305
+      name: Cosine Ndcg@20
+    - type: cosine_ndcg@50
+      value: 0.5267125529267169
+      name: Cosine Ndcg@50
+    - type: cosine_ndcg@100
+      value: 0.55793511917882
+      name: Cosine Ndcg@100
+    - type: cosine_ndcg@150
+      value: 0.5879547828450983
+      name: Cosine Ndcg@150
+    - type: cosine_ndcg@200
+      value: 0.6071252185389439
+      name: Cosine Ndcg@200
+    - type: cosine_mrr@1
+      value: 0.2955665024630542
+      name: Cosine Mrr@1
+    - type: cosine_mrr@20
+      value: 0.5104381157401634
+      name: Cosine Mrr@20
+    - type: cosine_mrr@50
+      value: 0.5109752961295605
+      name: Cosine Mrr@50
+    - type: cosine_mrr@100
+      value: 0.5109752961295605
+      name: Cosine Mrr@100
+    - type: cosine_mrr@150
+      value: 0.5110222114474118
+      name: Cosine Mrr@150
+    - type: cosine_mrr@200
+      value: 0.5110222114474118
+      name: Cosine Mrr@200
+    - type: cosine_map@1
+      value: 0.2955665024630542
+      name: Cosine Map@1
+    - type: cosine_map@20
+      value: 0.40097257642946377
+      name: Cosine Map@20
+    - type: cosine_map@50
+      value: 0.35882787401455
+      name: Cosine Map@50
+    - type: cosine_map@100
+      value: 0.3633182590941781
+      name: Cosine Map@100
+    - type: cosine_map@150
+      value: 0.3776727961080201
+      name: Cosine Map@150
+    - type: cosine_map@200
+      value: 0.3848401555555339
+      name: Cosine Map@200
+    - type: cosine_map@500
+      value: 0.3978065874082948
+      name: Cosine Map@500
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: full zh
+      type: full_zh
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6601941747572816
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@20
+      value: 0.9805825242718447
+      name: Cosine Accuracy@20
+    - type: cosine_accuracy@50
+      value: 0.9902912621359223
+      name: Cosine Accuracy@50
+    - type: cosine_accuracy@100
+      value: 0.9902912621359223
+      name: Cosine Accuracy@100
+    - type: cosine_accuracy@150
+      value: 0.9902912621359223
+      name: Cosine Accuracy@150
+    - type: cosine_accuracy@200
+      value: 0.9902912621359223
+      name: Cosine Accuracy@200
+    - type: cosine_precision@1
+      value: 0.6601941747572816
+      name: Cosine Precision@1
+    - type: cosine_precision@20
+      value: 0.4781553398058253
+      name: Cosine Precision@20
+    - type: cosine_precision@50
+      value: 0.28951456310679613
+      name: Cosine Precision@50
+    - type: cosine_precision@100
+      value: 0.17572815533980585
+      name: Cosine Precision@100
+    - type: cosine_precision@150
+      value: 0.12595469255663433
+      name: Cosine Precision@150
+    - type: cosine_precision@200
+      value: 0.09815533980582528
+      name: Cosine Precision@200
+    - type: cosine_recall@1
+      value: 0.06151358631979527
+      name: Cosine Recall@1
+    - type: cosine_recall@20
+      value: 0.5107966412908705
+      name: Cosine Recall@20
+    - type: cosine_recall@50
+      value: 0.6922746152164951
+      name: Cosine Recall@50
+    - type: cosine_recall@100
+      value: 0.8004152884148357
+      name: Cosine Recall@100
+    - type: cosine_recall@150
+      value: 0.8465065661615649
+      name: Cosine Recall@150
+    - type: cosine_recall@200
+      value: 0.8770990926698364
+      name: Cosine Recall@200
+    - type: cosine_ndcg@1
+      value: 0.6601941747572816
+      name: Cosine Ndcg@1
+    - type: cosine_ndcg@20
+      value: 0.6539867858378715
+      name: Cosine Ndcg@20
+    - type: cosine_ndcg@50
+      value: 0.6707332209240133
+      name: Cosine Ndcg@50
+    - type: cosine_ndcg@100
+      value: 0.72342020484322
+      name: Cosine Ndcg@100
+    - type: cosine_ndcg@150
+      value: 0.7437750875502527
+      name: Cosine Ndcg@150
+    - type: cosine_ndcg@200
+      value: 0.7553648453187212
+      name: Cosine Ndcg@200
+    - type: cosine_mrr@1
+      value: 0.6601941747572816
+      name: Cosine Mrr@1
+    - type: cosine_mrr@20
+      value: 0.8037216828478965
+      name: Cosine Mrr@20
+    - type: cosine_mrr@50
+      value: 0.8040950958426687
+      name: Cosine Mrr@50
+    - type: cosine_mrr@100
+      value: 0.8040950958426687
+      name: Cosine Mrr@100
+    - type: cosine_mrr@150
+      value: 0.8040950958426687
+      name: Cosine Mrr@150
+    - type: cosine_mrr@200
+      value: 0.8040950958426687
+      name: Cosine Mrr@200
+    - type: cosine_map@1
+      value: 0.6601941747572816
+      name: Cosine Map@1
+    - type: cosine_map@20
+      value: 0.5087334164702914
+      name: Cosine Map@20
+    - type: cosine_map@50
+      value: 0.49260246320797585
+      name: Cosine Map@50
+    - type: cosine_map@100
+      value: 0.5217412166882693
+      name: Cosine Map@100
+    - type: cosine_map@150
+      value: 0.529859818130126
+      name: Cosine Map@150
+    - type: cosine_map@200
+      value: 0.533378795921413
+      name: Cosine Map@200
+    - type: cosine_map@500
+      value: 0.5386011712914499
+      name: Cosine Map@500
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: mix es
+      type: mix_es
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.7280291211648466
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@20
+      value: 0.9599583983359334
+      name: Cosine Accuracy@20
+    - type: cosine_accuracy@50
+      value: 0.9791991679667187
+      name: Cosine Accuracy@50
+    - type: cosine_accuracy@100
+      value: 0.9942797711908476
+      name: Cosine Accuracy@100
+    - type: cosine_accuracy@150
+      value: 0.9958398335933437
+      name: Cosine Accuracy@150
+    - type: cosine_accuracy@200
+      value: 0.9973998959958398
+      name: Cosine Accuracy@200
+    - type: cosine_precision@1
+      value: 0.7280291211648466
+      name: Cosine Precision@1
+    - type: cosine_precision@20
+      value: 0.12433697347893914
+      name: Cosine Precision@20
+    - type: cosine_precision@50
+      value: 0.05145085803432139
+      name: Cosine Precision@50
+    - type: cosine_precision@100
+      value: 0.02625065002600105
+      name: Cosine Precision@100
+    - type: cosine_precision@150
+      value: 0.017621771537528162
+      name: Cosine Precision@150
+    - type: cosine_precision@200
+      value: 0.013283931357254294
+      name: Cosine Precision@200
+    - type: cosine_recall@1
+      value: 0.28133620582918556
+      name: Cosine Recall@1
+    - type: cosine_recall@20
+      value: 0.9183394002426764
+      name: Cosine Recall@20
+    - type: cosine_recall@50
+      value: 0.9499306638932224
+      name: Cosine Recall@50
+    - type: cosine_recall@100
+      value: 0.9700901369388107
+      name: Cosine Recall@100
+    - type: cosine_recall@150
+      value: 0.9767724042295025
+      name: Cosine Recall@150
+    - type: cosine_recall@200
+      value: 0.9818166059975733
+      name: Cosine Recall@200
+    - type: cosine_ndcg@1
+      value: 0.7280291211648466
+      name: Cosine Ndcg@1
+    - type: cosine_ndcg@20
+      value: 0.8043549768911603
+      name: Cosine Ndcg@20
+    - type: cosine_ndcg@50
+      value: 0.81295852465432
+      name: Cosine Ndcg@50
+    - type: cosine_ndcg@100
+      value: 0.817339429558165
+      name: Cosine Ndcg@100
+    - type: cosine_ndcg@150
+      value: 0.8186380742931886
+      name: Cosine Ndcg@150
+    - type: cosine_ndcg@200
+      value: 0.8195485984235017
+      name: Cosine Ndcg@200
+    - type: cosine_mrr@1
+      value: 0.7280291211648466
+      name: Cosine Mrr@1
+    - type: cosine_mrr@20
+      value: 0.7968549154271433
+      name: Cosine Mrr@20
+    - type: cosine_mrr@50
+      value: 0.7974653825839162
+      name: Cosine Mrr@50
+    - type: cosine_mrr@100
+      value: 0.7976914864910069
+      name: Cosine Mrr@100
+    - type: cosine_mrr@150
+      value: 0.7977044635908871
+      name: Cosine Mrr@150
+    - type: cosine_mrr@200
+      value: 0.7977139196654446
+      name: Cosine Mrr@200
+    - type: cosine_map@1
+      value: 0.7280291211648466
+      name: Cosine Map@1
+    - type: cosine_map@20
+      value: 0.7350836192117531
+      name: Cosine Map@20
+    - type: cosine_map@50
+      value: 0.7374205090112232
+      name: Cosine Map@50
+    - type: cosine_map@100
+      value: 0.737988888492803
+      name: Cosine Map@100
+    - type: cosine_map@150
+      value: 0.7381133157945164
+      name: Cosine Map@150
+    - type: cosine_map@200
+      value: 0.7381788581828236
+      name: Cosine Map@200
+    - type: cosine_map@500
+      value: 0.7382854440643231
+      name: Cosine Map@500
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: mix de
+      type: mix_de
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6703068122724909
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@20
+      value: 0.9505980239209568
+      name: Cosine Accuracy@20
+    - type: cosine_accuracy@50
+      value: 0.9776391055642226
+      name: Cosine Accuracy@50
+    - type: cosine_accuracy@100
+      value: 0.9864794591783671
+      name: Cosine Accuracy@100
+    - type: cosine_accuracy@150
+      value: 0.9932397295891836
+      name: Cosine Accuracy@150
+    - type: cosine_accuracy@200
+      value: 0.9947997919916797
+      name: Cosine Accuracy@200
+    - type: cosine_precision@1
+      value: 0.6703068122724909
+      name: Cosine Precision@1
+    - type: cosine_precision@20
+      value: 0.1251690067602704
+      name: Cosine Precision@20
+    - type: cosine_precision@50
+      value: 0.052282891315652634
+      name: Cosine Precision@50
+    - type: cosine_precision@100
+      value: 0.026729069162766517
+      name: Cosine Precision@100
+    - type: cosine_precision@150
+      value: 0.01799965331946611
+      name: Cosine Precision@150
+    - type: cosine_precision@200
+      value: 0.013541341653666149
+      name: Cosine Precision@200
+    - type: cosine_recall@1
+      value: 0.25235742763043856
+      name: Cosine Recall@1
+    - type: cosine_recall@20
+      value: 0.9095857167620037
+      name: Cosine Recall@20
+    - type: cosine_recall@50
+      value: 0.9482405962905183
+      name: Cosine Recall@50
+    - type: cosine_recall@100
+      value: 0.96845207141619
+      name: Cosine Recall@100
+    - type: cosine_recall@150
+      value: 0.9781591263650546
+      name: Cosine Recall@150
+    - type: cosine_recall@200
+      value: 0.9810192407696308
+      name: Cosine Recall@200
+    - type: cosine_ndcg@1
+      value: 0.6703068122724909
+      name: Cosine Ndcg@1
+    - type: cosine_ndcg@20
+      value: 0.7735712514376322
+      name: Cosine Ndcg@20
+    - type: cosine_ndcg@50
+      value: 0.7843644592705362
+      name: Cosine Ndcg@50
+    - type: cosine_ndcg@100
+      value: 0.7889444470773866
+      name: Cosine Ndcg@100
+    - type: cosine_ndcg@150
+      value: 0.7908660087982327
+      name: Cosine Ndcg@150
+    - type: cosine_ndcg@200
+      value: 0.791403470160319
+      name: Cosine Ndcg@200
+    - type: cosine_mrr@1
+      value: 0.6703068122724909
+      name: Cosine Mrr@1
+    - type: cosine_mrr@20
+      value: 0.7520307321055828
+      name: Cosine Mrr@20
+    - type: cosine_mrr@50
+      value: 0.7529374175534339
+      name: Cosine Mrr@50
+    - type: cosine_mrr@100
+      value: 0.7530616872072472
+      name: Cosine Mrr@100
+    - type: cosine_mrr@150
+      value: 0.7531202644382351
+      name: Cosine Mrr@150
+    - type: cosine_mrr@200
+      value: 0.7531293951311296
+      name: Cosine Mrr@200
+    - type: cosine_map@1
+      value: 0.6703068122724909
+      name: Cosine Map@1
+    - type: cosine_map@20
+      value: 0.6967639778693541
+      name: Cosine Map@20
+    - type: cosine_map@50
+      value: 0.699575457224443
+      name: Cosine Map@50
+    - type: cosine_map@100
+      value: 0.70027844357658
+      name: Cosine Map@100
+    - type: cosine_map@150
+      value: 0.7004487000056766
+      name: Cosine Map@150
+    - type: cosine_map@200
+      value: 0.7004863395843564
+      name: Cosine Map@200
+    - type: cosine_map@500
+      value: 0.7005835771389989
+      name: Cosine Map@500
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: mix zh
+      type: mix_zh
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.19084763390535622
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@20
+      value: 1.0
+      name: Cosine Accuracy@20
+    - type: cosine_accuracy@50
+      value: 1.0
+      name: Cosine Accuracy@50
+    - type: cosine_accuracy@100
+      value: 1.0
+      name: Cosine Accuracy@100
+    - type: cosine_accuracy@150
+      value: 1.0
+      name: Cosine Accuracy@150
+    - type: cosine_accuracy@200
+      value: 1.0
+      name: Cosine Accuracy@200
+    - type: cosine_precision@1
+      value: 0.19084763390535622
+      name: Cosine Precision@1
+    - type: cosine_precision@20
+      value: 0.15439417576703063
+      name: Cosine Precision@20
+    - type: cosine_precision@50
+      value: 0.0617576703068123
+      name: Cosine Precision@50
+    - type: cosine_precision@100
+      value: 0.03087883515340615
+      name: Cosine Precision@100
+    - type: cosine_precision@150
+      value: 0.020585890102270757
+      name: Cosine Precision@150
+    - type: cosine_precision@200
+      value: 0.015439417576703075
+      name: Cosine Precision@200
+    - type: cosine_recall@1
+      value: 0.06137978852487433
+      name: Cosine Recall@1
+    - type: cosine_recall@20
+      value: 1.0
+      name: Cosine Recall@20
+    - type: cosine_recall@50
+      value: 1.0
+      name: Cosine Recall@50
+    - type: cosine_recall@100
+      value: 1.0
+      name: Cosine Recall@100
+    - type: cosine_recall@150
+      value: 1.0
+      name: Cosine Recall@150
+    - type: cosine_recall@200
+      value: 1.0
+      name: Cosine Recall@200
+    - type: cosine_ndcg@1
+      value: 0.19084763390535622
+      name: Cosine Ndcg@1
+    - type: cosine_ndcg@20
+      value: 0.5474303590499686
+      name: Cosine Ndcg@20
+    - type: cosine_ndcg@50
+      value: 0.5474303590499686
+      name: Cosine Ndcg@50
+    - type: cosine_ndcg@100
+      value: 0.5474303590499686
+      name: Cosine Ndcg@100
+    - type: cosine_ndcg@150
+      value: 0.5474303590499686
+      name: Cosine Ndcg@150
+    - type: cosine_ndcg@200
+      value: 0.5474303590499686
+      name: Cosine Ndcg@200
+    - type: cosine_mrr@1
+      value: 0.19084763390535622
+      name: Cosine Mrr@1
+    - type: cosine_mrr@20
+      value: 0.4093433087972877
+      name: Cosine Mrr@20
+    - type: cosine_mrr@50
+      value: 0.4093433087972877
+      name: Cosine Mrr@50
+    - type: cosine_mrr@100
+      value: 0.4093433087972877
+      name: Cosine Mrr@100
+    - type: cosine_mrr@150
+      value: 0.4093433087972877
+      name: Cosine Mrr@150
+    - type: cosine_mrr@200
+      value: 0.4093433087972877
+      name: Cosine Mrr@200
+    - type: cosine_map@1
+      value: 0.19084763390535622
+      name: Cosine Map@1
+    - type: cosine_map@20
+      value: 0.32981711891302556
+      name: Cosine Map@20
+    - type: cosine_map@50
+      value: 0.32981711891302556
+      name: Cosine Map@50
+    - type: cosine_map@100
+      value: 0.32981711891302556
+      name: Cosine Map@100
+    - type: cosine_map@150
+      value: 0.32981711891302556
+      name: Cosine Map@150
+    - type: cosine_map@200
+      value: 0.32981711891302556
+      name: Cosine Map@200
+    - type: cosine_map@500
+      value: 0.32981711891302556
+      name: Cosine Map@500
+---
+
+# Job - Job matching Alibaba-NLP/gte-multilingual-base (v1)
+
+Top performing model on [TalentCLEF 2025](https://talentclef.github.io/talentclef/) Task A.  Use it for multilingual job title matching
+
+## Model Details
+
+### Model Description
+- **Model Type:** Sentence Transformer
+- **Base model:** [Alibaba-NLP/gte-multilingual-base](https://huggingface.co/Alibaba-NLP/gte-multilingual-base) <!-- at revision 9fdd4ee8bba0e2808a34e0e739576f6740d2b225 -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 768 dimensions
+- **Similarity Function:** Cosine Similarity
+- **Training Datasets:**
+    - full_en
+    - full_de
+    - full_es
+    - full_zh
+    - mix
+<!-- - **Language:** Unknown -->
+<!-- - **License:** Unknown -->
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
+- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
+
+### Full Model Architecture
+
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: NewModel 
+  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+  (2): Normalize()
+)
+```
+
+## Usage
+
+### Direct Usage (Sentence Transformers)
+
+First install the Sentence Transformers library:
+
+```bash
+pip install -U sentence-transformers
+```
+
+Then you can load this model and run inference.
+```python
+from sentence_transformers import SentenceTransformer
+
+# Download from the 🤗 Hub
+model = SentenceTransformer("pj-mathematician/JobGTE-multilingual-base-v1")
+# Run inference
+sentences = [
+    'Volksvertreter',
+    'Parlamentarier',
+    'Oberbürgermeister',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 768]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities.shape)
+# [3, 3]
+```
+
+<!--
+### Direct Usage (Transformers)
+
+<details><summary>Click to see the direct usage in Transformers</summary>
+
+</details>
+-->
+
+<!--
+### Downstream Usage (Sentence Transformers)
+
+You can finetune this model on your own dataset.
+
+<details><summary>Click to expand</summary>
+
+</details>
+-->
+
+<!--
+### Out-of-Scope Use
+
+*List how the model may foreseeably be misused and address what users ought not to do with the model.*
+-->
+
+## Evaluation
+
+### Metrics
+
+#### Information Retrieval
+
+* Datasets: `full_en`, `full_es`, `full_de`, `full_zh`, `mix_es`, `mix_de` and `mix_zh`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric               | full_en   | full_es    | full_de    | full_zh    | mix_es     | mix_de     | mix_zh     |
+|:---------------------|:----------|:-----------|:-----------|:-----------|:-----------|:-----------|:-----------|
+| cosine_accuracy@1    | 0.6571    | 0.1243     | 0.2956     | 0.6602     | 0.728      | 0.6703     | 0.1908     |
+| cosine_accuracy@20   | 0.9905    | 1.0        | 0.9704     | 0.9806     | 0.96       | 0.9506     | 1.0        |
+| cosine_accuracy@50   | 0.9905    | 1.0        | 0.9852     | 0.9903     | 0.9792     | 0.9776     | 1.0        |
+| cosine_accuracy@100  | 0.9905    | 1.0        | 0.9852     | 0.9903     | 0.9943     | 0.9865     | 1.0        |
+| cosine_accuracy@150  | 0.9905    | 1.0        | 0.9901     | 0.9903     | 0.9958     | 0.9932     | 1.0        |
+| cosine_accuracy@200  | 0.9905    | 1.0        | 0.9901     | 0.9903     | 0.9974     | 0.9948     | 1.0        |
+| cosine_precision@1   | 0.6571    | 0.1243     | 0.2956     | 0.6602     | 0.728      | 0.6703     | 0.1908     |
+| cosine_precision@20  | 0.5171    | 0.5719     | 0.5084     | 0.4782     | 0.1243     | 0.1252     | 0.1544     |
+| cosine_precision@50  | 0.316     | 0.3885     | 0.3654     | 0.2895     | 0.0515     | 0.0523     | 0.0618     |
+| cosine_precision@100 | 0.189     | 0.2517     | 0.2413     | 0.1757     | 0.0263     | 0.0267     | 0.0309     |
+| cosine_precision@150 | 0.1338    | 0.1905     | 0.1804     | 0.126      | 0.0176     | 0.018      | 0.0206     |
+| cosine_precision@200 | 0.1043    | 0.1522     | 0.1447     | 0.0982     | 0.0133     | 0.0135     | 0.0154     |
+| cosine_recall@1      | 0.0678    | 0.0037     | 0.0111     | 0.0615     | 0.2813     | 0.2524     | 0.0614     |
+| cosine_recall@20     | 0.547     | 0.3842     | 0.3221     | 0.5108     | 0.9183     | 0.9096     | 1.0        |
+| cosine_recall@50     | 0.74      | 0.5641     | 0.5025     | 0.6923     | 0.9499     | 0.9482     | 1.0        |
+| cosine_recall@100    | 0.8453    | 0.6742     | 0.6248     | 0.8004     | 0.9701     | 0.9685     | 1.0        |
+| cosine_recall@150    | 0.8838    | 0.7464     | 0.683      | 0.8465     | 0.9768     | 0.9782     | 1.0        |
+| cosine_recall@200    | 0.9109    | 0.7825     | 0.7216     | 0.8771     | 0.9818     | 0.981      | 1.0        |
+| cosine_ndcg@1        | 0.6571    | 0.1243     | 0.2956     | 0.6602     | 0.728      | 0.6703     | 0.1908     |
+| cosine_ndcg@20       | 0.6954    | 0.6139     | 0.5393     | 0.654      | 0.8044     | 0.7736     | 0.5474     |
+| cosine_ndcg@50       | 0.715     | 0.5874     | 0.5267     | 0.6707     | 0.813      | 0.7844     | 0.5474     |
+| cosine_ndcg@100      | 0.7679    | 0.6144     | 0.5579     | 0.7234     | 0.8173     | 0.7889     | 0.5474     |
+| cosine_ndcg@150      | 0.7857    | 0.6499     | 0.588      | 0.7438     | 0.8186     | 0.7909     | 0.5474     |
+| **cosine_ndcg@200**  | **0.797** | **0.6681** | **0.6071** | **0.7554** | **0.8195** | **0.7914** | **0.5474** |
+| cosine_mrr@1         | 0.6571    | 0.1243     | 0.2956     | 0.6602     | 0.728      | 0.6703     | 0.1908     |
+| cosine_mrr@20        | 0.8138    | 0.5581     | 0.5104     | 0.8037     | 0.7969     | 0.752      | 0.4093     |
+| cosine_mrr@50        | 0.8138    | 0.5581     | 0.511      | 0.8041     | 0.7975     | 0.7529     | 0.4093     |
+| cosine_mrr@100       | 0.8138    | 0.5581     | 0.511      | 0.8041     | 0.7977     | 0.7531     | 0.4093     |
+| cosine_mrr@150       | 0.8138    | 0.5581     | 0.511      | 0.8041     | 0.7977     | 0.7531     | 0.4093     |
+| cosine_mrr@200       | 0.8138    | 0.5581     | 0.511      | 0.8041     | 0.7977     | 0.7531     | 0.4093     |
+| cosine_map@1         | 0.6571    | 0.1243     | 0.2956     | 0.6602     | 0.728      | 0.6703     | 0.1908     |
+| cosine_map@20        | 0.5579    | 0.4799     | 0.401      | 0.5087     | 0.7351     | 0.6968     | 0.3298     |
+| cosine_map@50        | 0.5471    | 0.425      | 0.3588     | 0.4926     | 0.7374     | 0.6996     | 0.3298     |
+| cosine_map@100       | 0.5796    | 0.4302     | 0.3633     | 0.5217     | 0.738      | 0.7003     | 0.3298     |
+| cosine_map@150       | 0.5875    | 0.4459     | 0.3777     | 0.5299     | 0.7381     | 0.7004     | 0.3298     |
+| cosine_map@200       | 0.5912    | 0.4533     | 0.3848     | 0.5334     | 0.7382     | 0.7005     | 0.3298     |
+| cosine_map@500       | 0.5953    | 0.4656     | 0.3978     | 0.5386     | 0.7383     | 0.7006     | 0.3298     |
+
+<!--
+## Bias, Risks and Limitations
+
+*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
+-->
+
+<!--
+### Recommendations
+
+*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
+-->
+
+## Training Details
+
+### Training Datasets
+<details><summary>full_en</summary>
+
+#### full_en
+
+* Dataset: full_en
+* Size: 28,880 training samples
+* Columns: <code>anchor</code> and <code>positive</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | anchor                                                                           | positive                                                                         |
+  |:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|
+  | type    | string                                                                           | string                                                                           |
+  | details | <ul><li>min: 3 tokens</li><li>mean: 5.68 tokens</li><li>max: 11 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 5.76 tokens</li><li>max: 12 tokens</li></ul> |
+* Samples:
+  | anchor                                   | positive                                 |
+  |:-----------------------------------------|:-----------------------------------------|
+  | <code>air commodore</code>               | <code>flight lieutenant</code>           |
+  | <code>command and control officer</code> | <code>flight officer</code>              |
+  | <code>air commodore</code>               | <code>command and control officer</code> |
+* Loss: [<code>GISTEmbedLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#gistembedloss) with these parameters:
+  ```json
+  {'guide': SentenceTransformer(
+    (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel 
+    (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+    (2): Normalize()
+  ), 'temperature': 0.01, 'margin_strategy': 'absolute', 'margin': 0.0}
+  ```
+</details>
+<details><summary>full_de</summary>
+
+#### full_de
+
+* Dataset: full_de
+* Size: 23,023 training samples
+* Columns: <code>anchor</code> and <code>positive</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | anchor                                                                           | positive                                                                         |
+  |:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|
+  | type    | string                                                                           | string                                                                           |
+  | details | <ul><li>min: 3 tokens</li><li>mean: 7.99 tokens</li><li>max: 30 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 8.19 tokens</li><li>max: 30 tokens</li></ul> |
+* Samples:
+  | anchor                            | positive                                             |
+  |:----------------------------------|:-----------------------------------------------------|
+  | <code>Staffelkommandantin</code>  | <code>Kommodore</code>                               |
+  | <code>Luftwaffenoffizierin</code> | <code>Luftwaffenoffizier/Luftwaffenoffizierin</code> |
+  | <code>Staffelkommandantin</code>  | <code>Luftwaffenoffizierin</code>                    |
+* Loss: [<code>GISTEmbedLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#gistembedloss) with these parameters:
+  ```json
+  {'guide': SentenceTransformer(
+    (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel 
+    (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+    (2): Normalize()
+  ), 'temperature': 0.01, 'margin_strategy': 'absolute', 'margin': 0.0}
+  ```
+</details>
+<details><summary>full_es</summary>
+
+#### full_es
+
+* Dataset: full_es
+* Size: 20,724 training samples
+* Columns: <code>anchor</code> and <code>positive</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | anchor                                                                           | positive                                                                         |
+  |:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|
+  | type    | string                                                                           | string                                                                           |
+  | details | <ul><li>min: 3 tokens</li><li>mean: 9.13 tokens</li><li>max: 32 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 8.84 tokens</li><li>max: 32 tokens</li></ul> |
+* Samples:
+  | anchor                              | positive                                   |
+  |:------------------------------------|:-------------------------------------------|
+  | <code>jefe de escuadrón</code>      | <code>instructor</code>                    |
+  | <code>comandante de aeronave</code> | <code>instructor de simulador</code>       |
+  | <code>instructor</code>             | <code>oficial del Ejército del Aire</code> |
+* Loss: [<code>GISTEmbedLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#gistembedloss) with these parameters:
+  ```json
+  {'guide': SentenceTransformer(
+    (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel 
+    (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+    (2): Normalize()
+  ), 'temperature': 0.01, 'margin_strategy': 'absolute', 'margin': 0.0}
+  ```
+</details>
+<details><summary>full_zh</summary>
+
+#### full_zh
+
+* Dataset: full_zh
+* Size: 30,401 training samples
+* Columns: <code>anchor</code> and <code>positive</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | anchor                                                                           | positive                                                                         |
+  |:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|
+  | type    | string                                                                           | string                                                                           |
+  | details | <ul><li>min: 5 tokens</li><li>mean: 7.15 tokens</li><li>max: 14 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 7.46 tokens</li><li>max: 21 tokens</li></ul> |
+* Samples:
+  | anchor            | positive             |
+  |:------------------|:---------------------|
+  | <code>技术总监</code> | <code>技术和运营总监</code> |
+  | <code>技术总监</code> | <code>技术主管</code>    |
+  | <code>技术总监</code> | <code>技术艺术总监</code>  |
+* Loss: [<code>GISTEmbedLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#gistembedloss) with these parameters:
+  ```json
+  {'guide': SentenceTransformer(
+    (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel 
+    (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+    (2): Normalize()
+  ), 'temperature': 0.01, 'margin_strategy': 'absolute', 'margin': 0.0}
+  ```
+</details>
+<details><summary>mix</summary>
+
+#### mix
+
+* Dataset: mix
+* Size: 21,760 training samples
+* Columns: <code>anchor</code> and <code>positive</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | anchor                                                                           | positive                                                                         |
+  |:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|
+  | type    | string                                                                           | string                                                                           |
+  | details | <ul><li>min: 2 tokens</li><li>mean: 6.71 tokens</li><li>max: 19 tokens</li></ul> | <ul><li>min: 2 tokens</li><li>mean: 7.69 tokens</li><li>max: 19 tokens</li></ul> |
+* Samples:
+  | anchor                                    | positive                                                        |
+  |:------------------------------------------|:----------------------------------------------------------------|
+  | <code>technical manager</code>            | <code>Technischer Direktor für Bühne, Film und Fernsehen</code> |
+  | <code>head of technical</code>            | <code>directora técnica</code>                                  |
+  | <code>head of technical department</code> | <code>技术艺术总监</code>                                             |
+* Loss: [<code>GISTEmbedLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#gistembedloss) with these parameters:
+  ```json
+  {'guide': SentenceTransformer(
+    (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel 
+    (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+    (2): Normalize()
+  ), 'temperature': 0.01, 'margin_strategy': 'absolute', 'margin': 0.0}
+  ```
+</details>
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 64
+- `per_device_eval_batch_size`: 128
+- `gradient_accumulation_steps`: 2
+- `num_train_epochs`: 5
+- `warmup_ratio`: 0.05
+- `log_on_each_node`: False
+- `fp16`: True
+- `dataloader_num_workers`: 4
+- `ddp_find_unused_parameters`: True
+- `batch_sampler`: no_duplicates
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: steps
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 64
+- `per_device_eval_batch_size`: 128
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 2
+- `eval_accumulation_steps`: None
+- `torch_empty_cache_steps`: None
+- `learning_rate`: 5e-05
+- `weight_decay`: 0.0
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1.0
+- `num_train_epochs`: 5
+- `max_steps`: -1
+- `lr_scheduler_type`: linear
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.05
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: False
+- `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`: 4
+- `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}
+- `tp_size`: 0
+- `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}
+- `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`: True
+- `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
+- `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`: False
+- `torch_compile_backend`: None
+- `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`: False
+- `use_liger_kernel`: False
+- `eval_use_gather_object`: False
+- `average_tokens_across_devices`: False
+- `prompts`: None
+- `batch_sampler`: no_duplicates
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch  | Step | Training Loss | full_en_cosine_ndcg@200 | full_es_cosine_ndcg@200 | full_de_cosine_ndcg@200 | full_zh_cosine_ndcg@200 | mix_es_cosine_ndcg@200 | mix_de_cosine_ndcg@200 | mix_zh_cosine_ndcg@200 |
+|:------:|:----:|:-------------:|:-----------------------:|:-----------------------:|:-----------------------:|:-----------------------:|:----------------------:|:----------------------:|:----------------------:|
+| -1     | -1   | -             | 0.7447                  | 0.6125                  | 0.5378                  | 0.7240                  | 0.7029                 | 0.6345                 | 0.5531                 |
+| 0.0010 | 1    | 3.4866        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 0.1027 | 100  | 2.5431        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 0.2053 | 200  | 1.4536        | 0.7993                  | 0.6633                  | 0.5974                  | 0.7642                  | 0.7567                 | 0.7011                 | 0.5498                 |
+| 0.3080 | 300  | 1.1018        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 0.4107 | 400  | 0.9184        | 0.7925                  | 0.6586                  | 0.6058                  | 0.7587                  | 0.7749                 | 0.7278                 | 0.5486                 |
+| 0.5133 | 500  | 0.8973        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 0.6160 | 600  | 0.7309        | 0.7951                  | 0.6671                  | 0.6096                  | 0.7708                  | 0.7793                 | 0.7339                 | 0.5525                 |
+| 0.7187 | 700  | 0.7297        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 0.8214 | 800  | 0.7281        | 0.7929                  | 0.6711                  | 0.6088                  | 0.7645                  | 0.7899                 | 0.7444                 | 0.5479                 |
+| 0.9240 | 900  | 0.6607        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 1.0267 | 1000 | 0.6075        | 0.7915                  | 0.6659                  | 0.6088                  | 0.7665                  | 0.7968                 | 0.7588                 | 0.5482                 |
+| 1.1294 | 1100 | 0.4553        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 1.2320 | 1200 | 0.4775        | 0.7979                  | 0.6696                  | 0.6033                  | 0.7669                  | 0.7959                 | 0.7624                 | 0.5484                 |
+| 1.3347 | 1300 | 0.4838        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 1.4374 | 1400 | 0.4912        | 0.7973                  | 0.6757                  | 0.6112                  | 0.7656                  | 0.7978                 | 0.7650                 | 0.5487                 |
+| 1.5400 | 1500 | 0.4732        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 1.6427 | 1600 | 0.5269        | 0.8031                  | 0.6723                  | 0.6108                  | 0.7654                  | 0.8008                 | 0.7660                 | 0.5492                 |
+| 1.7454 | 1700 | 0.4822        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 1.8480 | 1800 | 0.5072        | 0.7962                  | 0.6668                  | 0.6051                  | 0.7592                  | 0.8001                 | 0.7714                 | 0.5486                 |
+| 1.9507 | 1900 | 0.4709        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 2.0544 | 2000 | 0.3772        | 0.7940                  | 0.6647                  | 0.6037                  | 0.7579                  | 0.8064                 | 0.7732                 | 0.5479                 |
+| 2.1571 | 2100 | 0.3982        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 2.2598 | 2200 | 0.3073        | 0.7969                  | 0.6652                  | 0.6005                  | 0.7625                  | 0.8054                 | 0.7734                 | 0.5493                 |
+| 2.3624 | 2300 | 0.383         | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 2.4651 | 2400 | 0.3687        | 0.7925                  | 0.6690                  | 0.5987                  | 0.7583                  | 0.8081                 | 0.7735                 | 0.5477                 |
+| 2.5678 | 2500 | 0.3472        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 2.6704 | 2600 | 0.3557        | 0.7956                  | 0.6758                  | 0.6019                  | 0.7659                  | 0.8082                 | 0.7767                 | 0.5491                 |
+| 2.7731 | 2700 | 0.3527        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 2.8758 | 2800 | 0.3446        | 0.7945                  | 0.6719                  | 0.6020                  | 0.7616                  | 0.8124                 | 0.7818                 | 0.5496                 |
+| 2.9784 | 2900 | 0.3566        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 3.0821 | 3000 | 0.3252        | 0.7948                  | 0.6682                  | 0.6025                  | 0.7617                  | 0.8152                 | 0.7848                 | 0.5516                 |
+| 3.1848 | 3100 | 0.2968        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 3.2875 | 3200 | 0.2962        | 0.7953                  | 0.6717                  | 0.6086                  | 0.7613                  | 0.8110                 | 0.7824                 | 0.5482                 |
+| 3.3901 | 3300 | 0.3084        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 3.4928 | 3400 | 0.2909        | 0.7940                  | 0.6634                  | 0.6023                  | 0.7615                  | 0.8138                 | 0.7822                 | 0.5457                 |
+| 3.5955 | 3500 | 0.2964        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 3.6982 | 3600 | 0.3193        | 0.7960                  | 0.6635                  | 0.6070                  | 0.7534                  | 0.8164                 | 0.7844                 | 0.5467                 |
+| 3.8008 | 3700 | 0.3514        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 3.9035 | 3800 | 0.3147        | 0.7973                  | 0.6696                  | 0.6125                  | 0.7616                  | 0.8176                 | 0.7885                 | 0.5469                 |
+| 4.0062 | 3900 | 0.2738        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 4.1088 | 4000 | 0.2842        | 0.7960                  | 0.6672                  | 0.6082                  | 0.7536                  | 0.8174                 | 0.7891                 | 0.5479                 |
+| 4.2115 | 4100 | 0.2739        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 4.3142 | 4200 | 0.2704        | 0.7979                  | 0.6681                  | 0.6111                  | 0.7540                  | 0.8180                 | 0.7891                 | 0.5476                 |
+| 4.4168 | 4300 | 0.2529        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 4.5195 | 4400 | 0.272         | 0.7968                  | 0.6685                  | 0.6087                  | 0.7564                  | 0.8185                 | 0.7901                 | 0.5476                 |
+| 4.6222 | 4500 | 0.3           | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 4.7248 | 4600 | 0.2598        | 0.7972                  | 0.6675                  | 0.6072                  | 0.7556                  | 0.8190                 | 0.7909                 | 0.5478                 |
+| 4.8275 | 4700 | 0.3101        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 4.9302 | 4800 | 0.2524        | 0.7970                  | 0.6681                  | 0.6071                  | 0.7554                  | 0.8195                 | 0.7914                 | 0.5474                 |
+
+
+### Framework Versions
+- Python: 3.11.11
+- Sentence Transformers: 4.1.0
+- Transformers: 4.51.2
+- PyTorch: 2.6.0+cu124
+- Accelerate: 1.6.0
+- Datasets: 3.5.0
+- Tokenizers: 0.21.1
+
+## Citation
+
+### BibTeX
+
+#### Sentence Transformers
+```bibtex
+@inproceedings{reimers-2019-sentence-bert,
+    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
+    author = "Reimers, Nils and Gurevych, Iryna",
+    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
+    month = "11",
+    year = "2019",
+    publisher = "Association for Computational Linguistics",
+    url = "https://arxiv.org/abs/1908.10084",
+}
+```
+
+#### GISTEmbedLoss
+```bibtex
+@misc{solatorio2024gistembed,
+    title={GISTEmbed: Guided In-sample Selection of Training Negatives for Text Embedding Fine-tuning},
+    author={Aivin V. Solatorio},
+    year={2024},
+    eprint={2402.16829},
+    archivePrefix={arXiv},
+    primaryClass={cs.LG}
+}
+```
+
+<!--
+## Glossary
+
+*Clearly define terms in order to be accessible across audiences.*
+-->
+
+<!--
+## Model Card Authors
+
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
+
+<!--
+## Model Card Contact
+
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

checkpoint-4000/README.md

@@ -0,0 +1,1436 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:124788
+- loss:GISTEmbedLoss
+base_model: Alibaba-NLP/gte-multilingual-base
+widget:
+- source_sentence: 其他机械、设备和有形货物租赁服务代表
+  sentences:
+  - 其他机械和设备租赁服务工作人员
+  - 电子和电信设备及零部件物流经理
+  - 工业主厨
+- source_sentence: 公交车司机
+  sentences:
+  - 表演灯光设计师
+  - 乙烯基地板安装工
+  - 国际巴士司机
+- source_sentence: online communication manager
+  sentences:
+  - trades union official
+  - social media manager
+  - budget manager
+- source_sentence: Projektmanagerin
+  sentences:
+  - Projektmanager/Projektmanagerin
+  - Category-Manager
+  - Infanterist
+- source_sentence: Volksvertreter
+  sentences:
+  - Parlamentarier
+  - Oberbürgermeister
+  - Konsul
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+metrics:
+- cosine_accuracy@1
+- cosine_accuracy@20
+- cosine_accuracy@50
+- cosine_accuracy@100
+- cosine_accuracy@150
+- cosine_accuracy@200
+- cosine_precision@1
+- cosine_precision@20
+- cosine_precision@50
+- cosine_precision@100
+- cosine_precision@150
+- cosine_precision@200
+- cosine_recall@1
+- cosine_recall@20
+- cosine_recall@50
+- cosine_recall@100
+- cosine_recall@150
+- cosine_recall@200
+- cosine_ndcg@1
+- cosine_ndcg@20
+- cosine_ndcg@50
+- cosine_ndcg@100
+- cosine_ndcg@150
+- cosine_ndcg@200
+- cosine_mrr@1
+- cosine_mrr@20
+- cosine_mrr@50
+- cosine_mrr@100
+- cosine_mrr@150
+- cosine_mrr@200
+- cosine_map@1
+- cosine_map@20
+- cosine_map@50
+- cosine_map@100
+- cosine_map@150
+- cosine_map@200
+- cosine_map@500
+model-index:
+- name: SentenceTransformer based on Alibaba-NLP/gte-multilingual-base
+  results:
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: full en
+      type: full_en
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6476190476190476
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@20
+      value: 0.9904761904761905
+      name: Cosine Accuracy@20
+    - type: cosine_accuracy@50
+      value: 0.9904761904761905
+      name: Cosine Accuracy@50
+    - type: cosine_accuracy@100
+      value: 0.9904761904761905
+      name: Cosine Accuracy@100
+    - type: cosine_accuracy@150
+      value: 0.9904761904761905
+      name: Cosine Accuracy@150
+    - type: cosine_accuracy@200
+      value: 0.9904761904761905
+      name: Cosine Accuracy@200
+    - type: cosine_precision@1
+      value: 0.6476190476190476
+      name: Cosine Precision@1
+    - type: cosine_precision@20
+      value: 0.5133333333333332
+      name: Cosine Precision@20
+    - type: cosine_precision@50
+      value: 0.3165714285714285
+      name: Cosine Precision@50
+    - type: cosine_precision@100
+      value: 0.18857142857142858
+      name: Cosine Precision@100
+    - type: cosine_precision@150
+      value: 0.13396825396825396
+      name: Cosine Precision@150
+    - type: cosine_precision@200
+      value: 0.10433333333333335
+      name: Cosine Precision@200
+    - type: cosine_recall@1
+      value: 0.06742481608756247
+      name: Cosine Recall@1
+    - type: cosine_recall@20
+      value: 0.5411228142559339
+      name: Cosine Recall@20
+    - type: cosine_recall@50
+      value: 0.7397482609380314
+      name: Cosine Recall@50
+    - type: cosine_recall@100
+      value: 0.8429667985290079
+      name: Cosine Recall@100
+    - type: cosine_recall@150
+      value: 0.8856357375498775
+      name: Cosine Recall@150
+    - type: cosine_recall@200
+      value: 0.9091330295382077
+      name: Cosine Recall@200
+    - type: cosine_ndcg@1
+      value: 0.6476190476190476
+      name: Cosine Ndcg@1
+    - type: cosine_ndcg@20
+      value: 0.6917131025478591
+      name: Cosine Ndcg@20
+    - type: cosine_ndcg@50
+      value: 0.71478335831634
+      name: Cosine Ndcg@50
+    - type: cosine_ndcg@100
+      value: 0.7666819432677721
+      name: Cosine Ndcg@100
+    - type: cosine_ndcg@150
+      value: 0.7855970749692088
+      name: Cosine Ndcg@150
+    - type: cosine_ndcg@200
+      value: 0.7960468614602451
+      name: Cosine Ndcg@200
+    - type: cosine_mrr@1
+      value: 0.6476190476190476
+      name: Cosine Mrr@1
+    - type: cosine_mrr@20
+      value: 0.8090476190476191
+      name: Cosine Mrr@20
+    - type: cosine_mrr@50
+      value: 0.8090476190476191
+      name: Cosine Mrr@50
+    - type: cosine_mrr@100
+      value: 0.8090476190476191
+      name: Cosine Mrr@100
+    - type: cosine_mrr@150
+      value: 0.8090476190476191
+      name: Cosine Mrr@150
+    - type: cosine_mrr@200
+      value: 0.8090476190476191
+      name: Cosine Mrr@200
+    - type: cosine_map@1
+      value: 0.6476190476190476
+      name: Cosine Map@1
+    - type: cosine_map@20
+      value: 0.5561135670751935
+      name: Cosine Map@20
+    - type: cosine_map@50
+      value: 0.5477711353289022
+      name: Cosine Map@50
+    - type: cosine_map@100
+      value: 0.5791852239372863
+      name: Cosine Map@100
+    - type: cosine_map@150
+      value: 0.5872469517518495
+      name: Cosine Map@150
+    - type: cosine_map@200
+      value: 0.5908784036739082
+      name: Cosine Map@200
+    - type: cosine_map@500
+      value: 0.5948564356607342
+      name: Cosine Map@500
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: full es
+      type: full_es
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.12972972972972974
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@20
+      value: 1.0
+      name: Cosine Accuracy@20
+    - type: cosine_accuracy@50
+      value: 1.0
+      name: Cosine Accuracy@50
+    - type: cosine_accuracy@100
+      value: 1.0
+      name: Cosine Accuracy@100
+    - type: cosine_accuracy@150
+      value: 1.0
+      name: Cosine Accuracy@150
+    - type: cosine_accuracy@200
+      value: 1.0
+      name: Cosine Accuracy@200
+    - type: cosine_precision@1
+      value: 0.12972972972972974
+      name: Cosine Precision@1
+    - type: cosine_precision@20
+      value: 0.5705405405405405
+      name: Cosine Precision@20
+    - type: cosine_precision@50
+      value: 0.38962162162162167
+      name: Cosine Precision@50
+    - type: cosine_precision@100
+      value: 0.25140540540540546
+      name: Cosine Precision@100
+    - type: cosine_precision@150
+      value: 0.19012612612612612
+      name: Cosine Precision@150
+    - type: cosine_precision@200
+      value: 0.15154054054054056
+      name: Cosine Precision@200
+    - type: cosine_recall@1
+      value: 0.0037413987812150314
+      name: Cosine Recall@1
+    - type: cosine_recall@20
+      value: 0.38432915927625627
+      name: Cosine Recall@20
+    - type: cosine_recall@50
+      value: 0.5663097940153319
+      name: Cosine Recall@50
+    - type: cosine_recall@100
+      value: 0.6710180189388714
+      name: Cosine Recall@100
+    - type: cosine_recall@150
+      value: 0.7443549924512646
+      name: Cosine Recall@150
+    - type: cosine_recall@200
+      value: 0.7804985217049148
+      name: Cosine Recall@200
+    - type: cosine_ndcg@1
+      value: 0.12972972972972974
+      name: Cosine Ndcg@1
+    - type: cosine_ndcg@20
+      value: 0.6133809590566169
+      name: Cosine Ndcg@20
+    - type: cosine_ndcg@50
+      value: 0.5888378318443163
+      name: Cosine Ndcg@50
+    - type: cosine_ndcg@100
+      value: 0.613553130716134
+      name: Cosine Ndcg@100
+    - type: cosine_ndcg@150
+      value: 0.6492700673561147
+      name: Cosine Ndcg@150
+    - type: cosine_ndcg@200
+      value: 0.6672020616803231
+      name: Cosine Ndcg@200
+    - type: cosine_mrr@1
+      value: 0.12972972972972974
+      name: Cosine Mrr@1
+    - type: cosine_mrr@20
+      value: 0.5608108108108109
+      name: Cosine Mrr@20
+    - type: cosine_mrr@50
+      value: 0.5608108108108109
+      name: Cosine Mrr@50
+    - type: cosine_mrr@100
+      value: 0.5608108108108109
+      name: Cosine Mrr@100
+    - type: cosine_mrr@150
+      value: 0.5608108108108109
+      name: Cosine Mrr@150
+    - type: cosine_mrr@200
+      value: 0.5608108108108109
+      name: Cosine Mrr@200
+    - type: cosine_map@1
+      value: 0.12972972972972974
+      name: Cosine Map@1
+    - type: cosine_map@20
+      value: 0.47928087268629077
+      name: Cosine Map@20
+    - type: cosine_map@50
+      value: 0.4265150109477007
+      name: Cosine Map@50
+    - type: cosine_map@100
+      value: 0.4308614258675324
+      name: Cosine Map@100
+    - type: cosine_map@150
+      value: 0.446315567522346
+      name: Cosine Map@150
+    - type: cosine_map@200
+      value: 0.45361884446786194
+      name: Cosine Map@200
+    - type: cosine_map@500
+      value: 0.46587892353181215
+      name: Cosine Map@500
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: full de
+      type: full_de
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.2955665024630542
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@20
+      value: 0.9704433497536946
+      name: Cosine Accuracy@20
+    - type: cosine_accuracy@50
+      value: 0.9852216748768473
+      name: Cosine Accuracy@50
+    - type: cosine_accuracy@100
+      value: 0.9852216748768473
+      name: Cosine Accuracy@100
+    - type: cosine_accuracy@150
+      value: 0.9901477832512315
+      name: Cosine Accuracy@150
+    - type: cosine_accuracy@200
+      value: 0.9901477832512315
+      name: Cosine Accuracy@200
+    - type: cosine_precision@1
+      value: 0.2955665024630542
+      name: Cosine Precision@1
+    - type: cosine_precision@20
+      value: 0.5120689655172413
+      name: Cosine Precision@20
+    - type: cosine_precision@50
+      value: 0.3664039408866995
+      name: Cosine Precision@50
+    - type: cosine_precision@100
+      value: 0.2411330049261084
+      name: Cosine Precision@100
+    - type: cosine_precision@150
+      value: 0.180623973727422
+      name: Cosine Precision@150
+    - type: cosine_precision@200
+      value: 0.1453448275862069
+      name: Cosine Precision@200
+    - type: cosine_recall@1
+      value: 0.01108543831680986
+      name: Cosine Recall@1
+    - type: cosine_recall@20
+      value: 0.3229666331805043
+      name: Cosine Recall@20
+    - type: cosine_recall@50
+      value: 0.5039915991834915
+      name: Cosine Recall@50
+    - type: cosine_recall@100
+      value: 0.6239950018657238
+      name: Cosine Recall@100
+    - type: cosine_recall@150
+      value: 0.6837127628220585
+      name: Cosine Recall@150
+    - type: cosine_recall@200
+      value: 0.724182886190782
+      name: Cosine Recall@200
+    - type: cosine_ndcg@1
+      value: 0.2955665024630542
+      name: Cosine Ndcg@1
+    - type: cosine_ndcg@20
+      value: 0.5416271120841382
+      name: Cosine Ndcg@20
+    - type: cosine_ndcg@50
+      value: 0.5273905187096658
+      name: Cosine Ndcg@50
+    - type: cosine_ndcg@100
+      value: 0.5573943264798527
+      name: Cosine Ndcg@100
+    - type: cosine_ndcg@150
+      value: 0.5882759422186796
+      name: Cosine Ndcg@150
+    - type: cosine_ndcg@200
+      value: 0.6082376029646045
+      name: Cosine Ndcg@200
+    - type: cosine_mrr@1
+      value: 0.2955665024630542
+      name: Cosine Mrr@1
+    - type: cosine_mrr@20
+      value: 0.510702296647636
+      name: Cosine Mrr@20
+    - type: cosine_mrr@50
+      value: 0.5111935025343795
+      name: Cosine Mrr@50
+    - type: cosine_mrr@100
+      value: 0.5111935025343795
+      name: Cosine Mrr@100
+    - type: cosine_mrr@150
+      value: 0.5112378818891037
+      name: Cosine Mrr@150
+    - type: cosine_mrr@200
+      value: 0.5112378818891037
+      name: Cosine Mrr@200
+    - type: cosine_map@1
+      value: 0.2955665024630542
+      name: Cosine Map@1
+    - type: cosine_map@20
+      value: 0.4032624181455029
+      name: Cosine Map@20
+    - type: cosine_map@50
+      value: 0.35929856113701575
+      name: Cosine Map@50
+    - type: cosine_map@100
+      value: 0.3633301227599498
+      name: Cosine Map@100
+    - type: cosine_map@150
+      value: 0.3779770424201306
+      name: Cosine Map@150
+    - type: cosine_map@200
+      value: 0.38546911827821406
+      name: Cosine Map@200
+    - type: cosine_map@500
+      value: 0.3983960288142158
+      name: Cosine Map@500
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: full zh
+      type: full_zh
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6504854368932039
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@20
+      value: 0.9805825242718447
+      name: Cosine Accuracy@20
+    - type: cosine_accuracy@50
+      value: 0.9902912621359223
+      name: Cosine Accuracy@50
+    - type: cosine_accuracy@100
+      value: 0.9902912621359223
+      name: Cosine Accuracy@100
+    - type: cosine_accuracy@150
+      value: 0.9902912621359223
+      name: Cosine Accuracy@150
+    - type: cosine_accuracy@200
+      value: 0.9902912621359223
+      name: Cosine Accuracy@200
+    - type: cosine_precision@1
+      value: 0.6504854368932039
+      name: Cosine Precision@1
+    - type: cosine_precision@20
+      value: 0.47815533980582525
+      name: Cosine Precision@20
+    - type: cosine_precision@50
+      value: 0.28699029126213593
+      name: Cosine Precision@50
+    - type: cosine_precision@100
+      value: 0.17563106796116504
+      name: Cosine Precision@100
+    - type: cosine_precision@150
+      value: 0.12543689320388354
+      name: Cosine Precision@150
+    - type: cosine_precision@200
+      value: 0.09786407766990295
+      name: Cosine Precision@200
+    - type: cosine_recall@1
+      value: 0.06122803520614593
+      name: Cosine Recall@1
+    - type: cosine_recall@20
+      value: 0.512665335199255
+      name: Cosine Recall@20
+    - type: cosine_recall@50
+      value: 0.6880766978766553
+      name: Cosine Recall@50
+    - type: cosine_recall@100
+      value: 0.8002784995071653
+      name: Cosine Recall@100
+    - type: cosine_recall@150
+      value: 0.8453144636093844
+      name: Cosine Recall@150
+    - type: cosine_recall@200
+      value: 0.8773140543871931
+      name: Cosine Recall@200
+    - type: cosine_ndcg@1
+      value: 0.6504854368932039
+      name: Cosine Ndcg@1
+    - type: cosine_ndcg@20
+      value: 0.6531212612064398
+      name: Cosine Ndcg@20
+    - type: cosine_ndcg@50
+      value: 0.6669362863744952
+      name: Cosine Ndcg@50
+    - type: cosine_ndcg@100
+      value: 0.7218911998936125
+      name: Cosine Ndcg@100
+    - type: cosine_ndcg@150
+      value: 0.7415597018345085
+      name: Cosine Ndcg@150
+    - type: cosine_ndcg@200
+      value: 0.7535751066625261
+      name: Cosine Ndcg@200
+    - type: cosine_mrr@1
+      value: 0.6504854368932039
+      name: Cosine Mrr@1
+    - type: cosine_mrr@20
+      value: 0.7993527508090615
+      name: Cosine Mrr@20
+    - type: cosine_mrr@50
+      value: 0.7997572815533981
+      name: Cosine Mrr@50
+    - type: cosine_mrr@100
+      value: 0.7997572815533981
+      name: Cosine Mrr@100
+    - type: cosine_mrr@150
+      value: 0.7997572815533981
+      name: Cosine Mrr@150
+    - type: cosine_mrr@200
+      value: 0.7997572815533981
+      name: Cosine Mrr@200
+    - type: cosine_map@1
+      value: 0.6504854368932039
+      name: Cosine Map@1
+    - type: cosine_map@20
+      value: 0.5072300500933464
+      name: Cosine Map@20
+    - type: cosine_map@50
+      value: 0.4897274345176646
+      name: Cosine Map@50
+    - type: cosine_map@100
+      value: 0.5196798622563865
+      name: Cosine Map@100
+    - type: cosine_map@150
+      value: 0.5276837053538445
+      name: Cosine Map@150
+    - type: cosine_map@200
+      value: 0.5311205359244624
+      name: Cosine Map@200
+    - type: cosine_map@500
+      value: 0.5365056842045905
+      name: Cosine Map@500
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: mix es
+      type: mix_es
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.7243889755590224
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@20
+      value: 0.9609984399375975
+      name: Cosine Accuracy@20
+    - type: cosine_accuracy@50
+      value: 0.9797191887675507
+      name: Cosine Accuracy@50
+    - type: cosine_accuracy@100
+      value: 0.9937597503900156
+      name: Cosine Accuracy@100
+    - type: cosine_accuracy@150
+      value: 0.9958398335933437
+      name: Cosine Accuracy@150
+    - type: cosine_accuracy@200
+      value: 0.9973998959958398
+      name: Cosine Accuracy@200
+    - type: cosine_precision@1
+      value: 0.7243889755590224
+      name: Cosine Precision@1
+    - type: cosine_precision@20
+      value: 0.12428497139885596
+      name: Cosine Precision@20
+    - type: cosine_precision@50
+      value: 0.05134685387415497
+      name: Cosine Precision@50
+    - type: cosine_precision@100
+      value: 0.026214248569942804
+      name: Cosine Precision@100
+    - type: cosine_precision@150
+      value: 0.017597503900156002
+      name: Cosine Precision@150
+    - type: cosine_precision@200
+      value: 0.013281331253250133
+      name: Cosine Precision@200
+    - type: cosine_recall@1
+      value: 0.2802961642275215
+      name: Cosine Recall@1
+    - type: cosine_recall@20
+      value: 0.9183394002426764
+      name: Cosine Recall@20
+    - type: cosine_recall@50
+      value: 0.9482665973305597
+      name: Cosine Recall@50
+    - type: cosine_recall@100
+      value: 0.9692234356040907
+      name: Cosine Recall@100
+    - type: cosine_recall@150
+      value: 0.9756023574276305
+      name: Cosine Recall@150
+    - type: cosine_recall@200
+      value: 0.9821892875715027
+      name: Cosine Recall@200
+    - type: cosine_ndcg@1
+      value: 0.7243889755590224
+      name: Cosine Ndcg@1
+    - type: cosine_ndcg@20
+      value: 0.8023352815755668
+      name: Cosine Ndcg@20
+    - type: cosine_ndcg@50
+      value: 0.8104895152869938
+      name: Cosine Ndcg@50
+    - type: cosine_ndcg@100
+      value: 0.8150081000806421
+      name: Cosine Ndcg@100
+    - type: cosine_ndcg@150
+      value: 0.8162651648802736
+      name: Cosine Ndcg@150
+    - type: cosine_ndcg@200
+      value: 0.8174362445077372
+      name: Cosine Ndcg@200
+    - type: cosine_mrr@1
+      value: 0.7243889755590224
+      name: Cosine Mrr@1
+    - type: cosine_mrr@20
+      value: 0.7938466413093047
+      name: Cosine Mrr@20
+    - type: cosine_mrr@50
+      value: 0.7944053350960067
+      name: Cosine Mrr@50
+    - type: cosine_mrr@100
+      value: 0.794613049565821
+      name: Cosine Mrr@100
+    - type: cosine_mrr@150
+      value: 0.7946306448507517
+      name: Cosine Mrr@150
+    - type: cosine_mrr@200
+      value: 0.7946402095756717
+      name: Cosine Mrr@200
+    - type: cosine_map@1
+      value: 0.7243889755590224
+      name: Cosine Map@1
+    - type: cosine_map@20
+      value: 0.7324440771234734
+      name: Cosine Map@20
+    - type: cosine_map@50
+      value: 0.734716178743038
+      name: Cosine Map@50
+    - type: cosine_map@100
+      value: 0.7353155432601859
+      name: Cosine Map@100
+    - type: cosine_map@150
+      value: 0.735429453970343
+      name: Cosine Map@150
+    - type: cosine_map@200
+      value: 0.7355154445871764
+      name: Cosine Map@200
+    - type: cosine_map@500
+      value: 0.7356208832908805
+      name: Cosine Map@500
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: mix de
+      type: mix_de
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6697867914716589
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@20
+      value: 0.9505980239209568
+      name: Cosine Accuracy@20
+    - type: cosine_accuracy@50
+      value: 0.9771190847633905
+      name: Cosine Accuracy@50
+    - type: cosine_accuracy@100
+      value: 0.9859594383775351
+      name: Cosine Accuracy@100
+    - type: cosine_accuracy@150
+      value: 0.9921996879875195
+      name: Cosine Accuracy@150
+    - type: cosine_accuracy@200
+      value: 0.9942797711908476
+      name: Cosine Accuracy@200
+    - type: cosine_precision@1
+      value: 0.6697867914716589
+      name: Cosine Precision@1
+    - type: cosine_precision@20
+      value: 0.12470098803952159
+      name: Cosine Precision@20
+    - type: cosine_precision@50
+      value: 0.05225169006760271
+      name: Cosine Precision@50
+    - type: cosine_precision@100
+      value: 0.026708268330733236
+      name: Cosine Precision@100
+    - type: cosine_precision@150
+      value: 0.01798231929277171
+      name: Cosine Precision@150
+    - type: cosine_precision@200
+      value: 0.01353874154966199
+      name: Cosine Precision@200
+    - type: cosine_recall@1
+      value: 0.2517940717628705
+      name: Cosine Recall@1
+    - type: cosine_recall@20
+      value: 0.9059022360894435
+      name: Cosine Recall@20
+    - type: cosine_recall@50
+      value: 0.9474345640492287
+      name: Cosine Recall@50
+    - type: cosine_recall@100
+      value: 0.967932050615358
+      name: Cosine Recall@100
+    - type: cosine_recall@150
+      value: 0.9771190847633905
+      name: Cosine Recall@150
+    - type: cosine_recall@200
+      value: 0.9807592303692148
+      name: Cosine Recall@200
+    - type: cosine_ndcg@1
+      value: 0.6697867914716589
+      name: Cosine Ndcg@1
+    - type: cosine_ndcg@20
+      value: 0.770344092734726
+      name: Cosine Ndcg@20
+    - type: cosine_ndcg@50
+      value: 0.7819450345813985
+      name: Cosine Ndcg@50
+    - type: cosine_ndcg@100
+      value: 0.7865455025019679
+      name: Cosine Ndcg@100
+    - type: cosine_ndcg@150
+      value: 0.7883807621544129
+      name: Cosine Ndcg@150
+    - type: cosine_ndcg@200
+      value: 0.7890604802329748
+      name: Cosine Ndcg@200
+    - type: cosine_mrr@1
+      value: 0.6697867914716589
+      name: Cosine Mrr@1
+    - type: cosine_mrr@20
+      value: 0.7504302722692131
+      name: Cosine Mrr@20
+    - type: cosine_mrr@50
+      value: 0.7513280223222801
+      name: Cosine Mrr@50
+    - type: cosine_mrr@100
+      value: 0.7514573016845009
+      name: Cosine Mrr@100
+    - type: cosine_mrr@150
+      value: 0.7515108675350354
+      name: Cosine Mrr@150
+    - type: cosine_mrr@200
+      value: 0.7515238522218625
+      name: Cosine Mrr@200
+    - type: cosine_map@1
+      value: 0.6697867914716589
+      name: Cosine Map@1
+    - type: cosine_map@20
+      value: 0.6929705838065172
+      name: Cosine Map@20
+    - type: cosine_map@50
+      value: 0.696080766802269
+      name: Cosine Map@50
+    - type: cosine_map@100
+      value: 0.6967651580129317
+      name: Cosine Map@100
+    - type: cosine_map@150
+      value: 0.6969258122016383
+      name: Cosine Map@150
+    - type: cosine_map@200
+      value: 0.6969715581100935
+      name: Cosine Map@200
+    - type: cosine_map@500
+      value: 0.6970655432634698
+      name: Cosine Map@500
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: mix zh
+      type: mix_zh
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.19760790431617264
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@20
+      value: 1.0
+      name: Cosine Accuracy@20
+    - type: cosine_accuracy@50
+      value: 1.0
+      name: Cosine Accuracy@50
+    - type: cosine_accuracy@100
+      value: 1.0
+      name: Cosine Accuracy@100
+    - type: cosine_accuracy@150
+      value: 1.0
+      name: Cosine Accuracy@150
+    - type: cosine_accuracy@200
+      value: 1.0
+      name: Cosine Accuracy@200
+    - type: cosine_precision@1
+      value: 0.19760790431617264
+      name: Cosine Precision@1
+    - type: cosine_precision@20
+      value: 0.15439417576703063
+      name: Cosine Precision@20
+    - type: cosine_precision@50
+      value: 0.0617576703068123
+      name: Cosine Precision@50
+    - type: cosine_precision@100
+      value: 0.03087883515340615
+      name: Cosine Precision@100
+    - type: cosine_precision@150
+      value: 0.020585890102270757
+      name: Cosine Precision@150
+    - type: cosine_precision@200
+      value: 0.015439417576703075
+      name: Cosine Precision@200
+    - type: cosine_recall@1
+      value: 0.06371492954956293
+      name: Cosine Recall@1
+    - type: cosine_recall@20
+      value: 1.0
+      name: Cosine Recall@20
+    - type: cosine_recall@50
+      value: 1.0
+      name: Cosine Recall@50
+    - type: cosine_recall@100
+      value: 1.0
+      name: Cosine Recall@100
+    - type: cosine_recall@150
+      value: 1.0
+      name: Cosine Recall@150
+    - type: cosine_recall@200
+      value: 1.0
+      name: Cosine Recall@200
+    - type: cosine_ndcg@1
+      value: 0.19760790431617264
+      name: Cosine Ndcg@1
+    - type: cosine_ndcg@20
+      value: 0.5478938300274205
+      name: Cosine Ndcg@20
+    - type: cosine_ndcg@50
+      value: 0.5478938300274205
+      name: Cosine Ndcg@50
+    - type: cosine_ndcg@100
+      value: 0.5478938300274205
+      name: Cosine Ndcg@100
+    - type: cosine_ndcg@150
+      value: 0.5478938300274205
+      name: Cosine Ndcg@150
+    - type: cosine_ndcg@200
+      value: 0.5478938300274205
+      name: Cosine Ndcg@200
+    - type: cosine_mrr@1
+      value: 0.19760790431617264
+      name: Cosine Mrr@1
+    - type: cosine_mrr@20
+      value: 0.4124442798779788
+      name: Cosine Mrr@20
+    - type: cosine_mrr@50
+      value: 0.4124442798779788
+      name: Cosine Mrr@50
+    - type: cosine_mrr@100
+      value: 0.4124442798779788
+      name: Cosine Mrr@100
+    - type: cosine_mrr@150
+      value: 0.4124442798779788
+      name: Cosine Mrr@150
+    - type: cosine_mrr@200
+      value: 0.4124442798779788
+      name: Cosine Mrr@200
+    - type: cosine_map@1
+      value: 0.19760790431617264
+      name: Cosine Map@1
+    - type: cosine_map@20
+      value: 0.32993583709540925
+      name: Cosine Map@20
+    - type: cosine_map@50
+      value: 0.32993583709540925
+      name: Cosine Map@50
+    - type: cosine_map@100
+      value: 0.32993583709540925
+      name: Cosine Map@100
+    - type: cosine_map@150
+      value: 0.32993583709540925
+      name: Cosine Map@150
+    - type: cosine_map@200
+      value: 0.32993583709540925
+      name: Cosine Map@200
+    - type: cosine_map@500
+      value: 0.32993583709540925
+      name: Cosine Map@500
+---
+
+# SentenceTransformer based on Alibaba-NLP/gte-multilingual-base
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [Alibaba-NLP/gte-multilingual-base](https://huggingface.co/Alibaba-NLP/gte-multilingual-base) on the full_en, full_de, full_es, full_zh and mix datasets. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
+
+## Model Details
+
+### Model Description
+- **Model Type:** Sentence Transformer
+- **Base model:** [Alibaba-NLP/gte-multilingual-base](https://huggingface.co/Alibaba-NLP/gte-multilingual-base) <!-- at revision 9fdd4ee8bba0e2808a34e0e739576f6740d2b225 -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 768 dimensions
+- **Similarity Function:** Cosine Similarity
+- **Training Datasets:**
+    - full_en
+    - full_de
+    - full_es
+    - full_zh
+    - mix
+<!-- - **Language:** Unknown -->
+<!-- - **License:** Unknown -->
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
+- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
+
+### Full Model Architecture
+
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: NewModel 
+  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+  (2): Normalize()
+)
+```
+
+## Usage
+
+### Direct Usage (Sentence Transformers)
+
+First install the Sentence Transformers library:
+
+```bash
+pip install -U sentence-transformers
+```
+
+Then you can load this model and run inference.
+```python
+from sentence_transformers import SentenceTransformer
+
+# Download from the 🤗 Hub
+model = SentenceTransformer("sentence_transformers_model_id")
+# Run inference
+sentences = [
+    'Volksvertreter',
+    'Parlamentarier',
+    'Oberbürgermeister',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 768]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities.shape)
+# [3, 3]
+```
+
+<!--
+### Direct Usage (Transformers)
+
+<details><summary>Click to see the direct usage in Transformers</summary>
+
+</details>
+-->
+
+<!--
+### Downstream Usage (Sentence Transformers)
+
+You can finetune this model on your own dataset.
+
+<details><summary>Click to expand</summary>
+
+</details>
+-->
+
+<!--
+### Out-of-Scope Use
+
+*List how the model may foreseeably be misused and address what users ought not to do with the model.*
+-->
+
+## Evaluation
+
+### Metrics
+
+#### Information Retrieval
+
+* Datasets: `full_en`, `full_es`, `full_de`, `full_zh`, `mix_es`, `mix_de` and `mix_zh`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric               | full_en   | full_es    | full_de    | full_zh    | mix_es     | mix_de     | mix_zh     |
+|:---------------------|:----------|:-----------|:-----------|:-----------|:-----------|:-----------|:-----------|
+| cosine_accuracy@1    | 0.6476    | 0.1297     | 0.2956     | 0.6505     | 0.7244     | 0.6698     | 0.1976     |
+| cosine_accuracy@20   | 0.9905    | 1.0        | 0.9704     | 0.9806     | 0.961      | 0.9506     | 1.0        |
+| cosine_accuracy@50   | 0.9905    | 1.0        | 0.9852     | 0.9903     | 0.9797     | 0.9771     | 1.0        |
+| cosine_accuracy@100  | 0.9905    | 1.0        | 0.9852     | 0.9903     | 0.9938     | 0.986      | 1.0        |
+| cosine_accuracy@150  | 0.9905    | 1.0        | 0.9901     | 0.9903     | 0.9958     | 0.9922     | 1.0        |
+| cosine_accuracy@200  | 0.9905    | 1.0        | 0.9901     | 0.9903     | 0.9974     | 0.9943     | 1.0        |
+| cosine_precision@1   | 0.6476    | 0.1297     | 0.2956     | 0.6505     | 0.7244     | 0.6698     | 0.1976     |
+| cosine_precision@20  | 0.5133    | 0.5705     | 0.5121     | 0.4782     | 0.1243     | 0.1247     | 0.1544     |
+| cosine_precision@50  | 0.3166    | 0.3896     | 0.3664     | 0.287      | 0.0513     | 0.0523     | 0.0618     |
+| cosine_precision@100 | 0.1886    | 0.2514     | 0.2411     | 0.1756     | 0.0262     | 0.0267     | 0.0309     |
+| cosine_precision@150 | 0.134     | 0.1901     | 0.1806     | 0.1254     | 0.0176     | 0.018      | 0.0206     |
+| cosine_precision@200 | 0.1043    | 0.1515     | 0.1453     | 0.0979     | 0.0133     | 0.0135     | 0.0154     |
+| cosine_recall@1      | 0.0674    | 0.0037     | 0.0111     | 0.0612     | 0.2803     | 0.2518     | 0.0637     |
+| cosine_recall@20     | 0.5411    | 0.3843     | 0.323      | 0.5127     | 0.9183     | 0.9059     | 1.0        |
+| cosine_recall@50     | 0.7397    | 0.5663     | 0.504      | 0.6881     | 0.9483     | 0.9474     | 1.0        |
+| cosine_recall@100    | 0.843     | 0.671      | 0.624      | 0.8003     | 0.9692     | 0.9679     | 1.0        |
+| cosine_recall@150    | 0.8856    | 0.7444     | 0.6837     | 0.8453     | 0.9756     | 0.9771     | 1.0        |
+| cosine_recall@200    | 0.9091    | 0.7805     | 0.7242     | 0.8773     | 0.9822     | 0.9808     | 1.0        |
+| cosine_ndcg@1        | 0.6476    | 0.1297     | 0.2956     | 0.6505     | 0.7244     | 0.6698     | 0.1976     |
+| cosine_ndcg@20       | 0.6917    | 0.6134     | 0.5416     | 0.6531     | 0.8023     | 0.7703     | 0.5479     |
+| cosine_ndcg@50       | 0.7148    | 0.5888     | 0.5274     | 0.6669     | 0.8105     | 0.7819     | 0.5479     |
+| cosine_ndcg@100      | 0.7667    | 0.6136     | 0.5574     | 0.7219     | 0.815      | 0.7865     | 0.5479     |
+| cosine_ndcg@150      | 0.7856    | 0.6493     | 0.5883     | 0.7416     | 0.8163     | 0.7884     | 0.5479     |
+| **cosine_ndcg@200**  | **0.796** | **0.6672** | **0.6082** | **0.7536** | **0.8174** | **0.7891** | **0.5479** |
+| cosine_mrr@1         | 0.6476    | 0.1297     | 0.2956     | 0.6505     | 0.7244     | 0.6698     | 0.1976     |
+| cosine_mrr@20        | 0.809     | 0.5608     | 0.5107     | 0.7994     | 0.7938     | 0.7504     | 0.4124     |
+| cosine_mrr@50        | 0.809     | 0.5608     | 0.5112     | 0.7998     | 0.7944     | 0.7513     | 0.4124     |
+| cosine_mrr@100       | 0.809     | 0.5608     | 0.5112     | 0.7998     | 0.7946     | 0.7515     | 0.4124     |
+| cosine_mrr@150       | 0.809     | 0.5608     | 0.5112     | 0.7998     | 0.7946     | 0.7515     | 0.4124     |
+| cosine_mrr@200       | 0.809     | 0.5608     | 0.5112     | 0.7998     | 0.7946     | 0.7515     | 0.4124     |
+| cosine_map@1         | 0.6476    | 0.1297     | 0.2956     | 0.6505     | 0.7244     | 0.6698     | 0.1976     |
+| cosine_map@20        | 0.5561    | 0.4793     | 0.4033     | 0.5072     | 0.7324     | 0.693      | 0.3299     |
+| cosine_map@50        | 0.5478    | 0.4265     | 0.3593     | 0.4897     | 0.7347     | 0.6961     | 0.3299     |
+| cosine_map@100       | 0.5792    | 0.4309     | 0.3633     | 0.5197     | 0.7353     | 0.6968     | 0.3299     |
+| cosine_map@150       | 0.5872    | 0.4463     | 0.378      | 0.5277     | 0.7354     | 0.6969     | 0.3299     |
+| cosine_map@200       | 0.5909    | 0.4536     | 0.3855     | 0.5311     | 0.7355     | 0.697      | 0.3299     |
+| cosine_map@500       | 0.5949    | 0.4659     | 0.3984     | 0.5365     | 0.7356     | 0.6971     | 0.3299     |
+
+<!--
+## Bias, Risks and Limitations
+
+*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
+-->
+
+<!--
+### Recommendations
+
+*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
+-->
+
+## Training Details
+
+### Training Datasets
+<details><summary>full_en</summary>
+
+#### full_en
+
+* Dataset: full_en
+* Size: 28,880 training samples
+* Columns: <code>anchor</code> and <code>positive</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | anchor                                                                           | positive                                                                         |
+  |:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|
+  | type    | string                                                                           | string                                                                           |
+  | details | <ul><li>min: 3 tokens</li><li>mean: 5.68 tokens</li><li>max: 11 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 5.76 tokens</li><li>max: 12 tokens</li></ul> |
+* Samples:
+  | anchor                                   | positive                                 |
+  |:-----------------------------------------|:-----------------------------------------|
+  | <code>air commodore</code>               | <code>flight lieutenant</code>           |
+  | <code>command and control officer</code> | <code>flight officer</code>              |
+  | <code>air commodore</code>               | <code>command and control officer</code> |
+* Loss: [<code>GISTEmbedLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#gistembedloss) with these parameters:
+  ```json
+  {'guide': SentenceTransformer(
+    (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel 
+    (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+    (2): Normalize()
+  ), 'temperature': 0.01, 'margin_strategy': 'absolute', 'margin': 0.0}
+  ```
+</details>
+<details><summary>full_de</summary>
+
+#### full_de
+
+* Dataset: full_de
+* Size: 23,023 training samples
+* Columns: <code>anchor</code> and <code>positive</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | anchor                                                                           | positive                                                                         |
+  |:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|
+  | type    | string                                                                           | string                                                                           |
+  | details | <ul><li>min: 3 tokens</li><li>mean: 7.99 tokens</li><li>max: 30 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 8.19 tokens</li><li>max: 30 tokens</li></ul> |
+* Samples:
+  | anchor                            | positive                                             |
+  |:----------------------------------|:-----------------------------------------------------|
+  | <code>Staffelkommandantin</code>  | <code>Kommodore</code>                               |
+  | <code>Luftwaffenoffizierin</code> | <code>Luftwaffenoffizier/Luftwaffenoffizierin</code> |
+  | <code>Staffelkommandantin</code>  | <code>Luftwaffenoffizierin</code>                    |
+* Loss: [<code>GISTEmbedLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#gistembedloss) with these parameters:
+  ```json
+  {'guide': SentenceTransformer(
+    (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel 
+    (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+    (2): Normalize()
+  ), 'temperature': 0.01, 'margin_strategy': 'absolute', 'margin': 0.0}
+  ```
+</details>
+<details><summary>full_es</summary>
+
+#### full_es
+
+* Dataset: full_es
+* Size: 20,724 training samples
+* Columns: <code>anchor</code> and <code>positive</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | anchor                                                                           | positive                                                                         |
+  |:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|
+  | type    | string                                                                           | string                                                                           |
+  | details | <ul><li>min: 3 tokens</li><li>mean: 9.13 tokens</li><li>max: 32 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 8.84 tokens</li><li>max: 32 tokens</li></ul> |
+* Samples:
+  | anchor                              | positive                                   |
+  |:------------------------------------|:-------------------------------------------|
+  | <code>jefe de escuadrón</code>      | <code>instructor</code>                    |
+  | <code>comandante de aeronave</code> | <code>instructor de simulador</code>       |
+  | <code>instructor</code>             | <code>oficial del Ejército del Aire</code> |
+* Loss: [<code>GISTEmbedLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#gistembedloss) with these parameters:
+  ```json
+  {'guide': SentenceTransformer(
+    (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel 
+    (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+    (2): Normalize()
+  ), 'temperature': 0.01, 'margin_strategy': 'absolute', 'margin': 0.0}
+  ```
+</details>
+<details><summary>full_zh</summary>
+
+#### full_zh
+
+* Dataset: full_zh
+* Size: 30,401 training samples
+* Columns: <code>anchor</code> and <code>positive</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | anchor                                                                           | positive                                                                         |
+  |:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|
+  | type    | string                                                                           | string                                                                           |
+  | details | <ul><li>min: 5 tokens</li><li>mean: 7.15 tokens</li><li>max: 14 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 7.46 tokens</li><li>max: 21 tokens</li></ul> |
+* Samples:
+  | anchor            | positive             |
+  |:------------------|:---------------------|
+  | <code>技术总监</code> | <code>技术和运营总监</code> |
+  | <code>技术总监</code> | <code>技术主管</code>    |
+  | <code>技术总监</code> | <code>技术艺术总监</code>  |
+* Loss: [<code>GISTEmbedLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#gistembedloss) with these parameters:
+  ```json
+  {'guide': SentenceTransformer(
+    (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel 
+    (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+    (2): Normalize()
+  ), 'temperature': 0.01, 'margin_strategy': 'absolute', 'margin': 0.0}
+  ```
+</details>
+<details><summary>mix</summary>
+
+#### mix
+
+* Dataset: mix
+* Size: 21,760 training samples
+* Columns: <code>anchor</code> and <code>positive</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | anchor                                                                           | positive                                                                         |
+  |:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|
+  | type    | string                                                                           | string                                                                           |
+  | details | <ul><li>min: 2 tokens</li><li>mean: 6.71 tokens</li><li>max: 19 tokens</li></ul> | <ul><li>min: 2 tokens</li><li>mean: 7.69 tokens</li><li>max: 19 tokens</li></ul> |
+* Samples:
+  | anchor                                    | positive                                                        |
+  |:------------------------------------------|:----------------------------------------------------------------|
+  | <code>technical manager</code>            | <code>Technischer Direktor für Bühne, Film und Fernsehen</code> |
+  | <code>head of technical</code>            | <code>directora técnica</code>                                  |
+  | <code>head of technical department</code> | <code>技术艺术总监</code>                                             |
+* Loss: [<code>GISTEmbedLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#gistembedloss) with these parameters:
+  ```json
+  {'guide': SentenceTransformer(
+    (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel 
+    (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+    (2): Normalize()
+  ), 'temperature': 0.01, 'margin_strategy': 'absolute', 'margin': 0.0}
+  ```
+</details>
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 64
+- `per_device_eval_batch_size`: 128
+- `gradient_accumulation_steps`: 2
+- `num_train_epochs`: 5
+- `warmup_ratio`: 0.05
+- `log_on_each_node`: False
+- `fp16`: True
+- `dataloader_num_workers`: 4
+- `ddp_find_unused_parameters`: True
+- `batch_sampler`: no_duplicates
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: steps
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 64
+- `per_device_eval_batch_size`: 128
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 2
+- `eval_accumulation_steps`: None
+- `torch_empty_cache_steps`: None
+- `learning_rate`: 5e-05
+- `weight_decay`: 0.0
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1.0
+- `num_train_epochs`: 5
+- `max_steps`: -1
+- `lr_scheduler_type`: linear
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.05
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: False
+- `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`: 4
+- `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}
+- `tp_size`: 0
+- `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}
+- `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`: True
+- `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
+- `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`: False
+- `torch_compile_backend`: None
+- `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`: False
+- `use_liger_kernel`: False
+- `eval_use_gather_object`: False
+- `average_tokens_across_devices`: False
+- `prompts`: None
+- `batch_sampler`: no_duplicates
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch  | Step | Training Loss | full_en_cosine_ndcg@200 | full_es_cosine_ndcg@200 | full_de_cosine_ndcg@200 | full_zh_cosine_ndcg@200 | mix_es_cosine_ndcg@200 | mix_de_cosine_ndcg@200 | mix_zh_cosine_ndcg@200 |
+|:------:|:----:|:-------------:|:-----------------------:|:-----------------------:|:-----------------------:|:-----------------------:|:----------------------:|:----------------------:|:----------------------:|
+| -1     | -1   | -             | 0.7447                  | 0.6125                  | 0.5378                  | 0.7240                  | 0.7029                 | 0.6345                 | 0.5531                 |
+| 0.0010 | 1    | 3.4866        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 0.1027 | 100  | 2.5431        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 0.2053 | 200  | 1.4536        | 0.7993                  | 0.6633                  | 0.5974                  | 0.7642                  | 0.7567                 | 0.7011                 | 0.5498                 |
+| 0.3080 | 300  | 1.1018        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 0.4107 | 400  | 0.9184        | 0.7925                  | 0.6586                  | 0.6058                  | 0.7587                  | 0.7749                 | 0.7278                 | 0.5486                 |
+| 0.5133 | 500  | 0.8973        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 0.6160 | 600  | 0.7309        | 0.7951                  | 0.6671                  | 0.6096                  | 0.7708                  | 0.7793                 | 0.7339                 | 0.5525                 |
+| 0.7187 | 700  | 0.7297        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 0.8214 | 800  | 0.7281        | 0.7929                  | 0.6711                  | 0.6088                  | 0.7645                  | 0.7899                 | 0.7444                 | 0.5479                 |
+| 0.9240 | 900  | 0.6607        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 1.0267 | 1000 | 0.6075        | 0.7915                  | 0.6659                  | 0.6088                  | 0.7665                  | 0.7968                 | 0.7588                 | 0.5482                 |
+| 1.1294 | 1100 | 0.4553        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 1.2320 | 1200 | 0.4775        | 0.7979                  | 0.6696                  | 0.6033                  | 0.7669                  | 0.7959                 | 0.7624                 | 0.5484                 |
+| 1.3347 | 1300 | 0.4838        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 1.4374 | 1400 | 0.4912        | 0.7973                  | 0.6757                  | 0.6112                  | 0.7656                  | 0.7978                 | 0.7650                 | 0.5487                 |
+| 1.5400 | 1500 | 0.4732        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 1.6427 | 1600 | 0.5269        | 0.8031                  | 0.6723                  | 0.6108                  | 0.7654                  | 0.8008                 | 0.7660                 | 0.5492                 |
+| 1.7454 | 1700 | 0.4822        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 1.8480 | 1800 | 0.5072        | 0.7962                  | 0.6668                  | 0.6051                  | 0.7592                  | 0.8001                 | 0.7714                 | 0.5486                 |
+| 1.9507 | 1900 | 0.4709        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 2.0544 | 2000 | 0.3772        | 0.7940                  | 0.6647                  | 0.6037                  | 0.7579                  | 0.8064                 | 0.7732                 | 0.5479                 |
+| 2.1571 | 2100 | 0.3982        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 2.2598 | 2200 | 0.3073        | 0.7969                  | 0.6652                  | 0.6005                  | 0.7625                  | 0.8054                 | 0.7734                 | 0.5493                 |
+| 2.3624 | 2300 | 0.383         | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 2.4651 | 2400 | 0.3687        | 0.7925                  | 0.6690                  | 0.5987                  | 0.7583                  | 0.8081                 | 0.7735                 | 0.5477                 |
+| 2.5678 | 2500 | 0.3472        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 2.6704 | 2600 | 0.3557        | 0.7956                  | 0.6758                  | 0.6019                  | 0.7659                  | 0.8082                 | 0.7767                 | 0.5491                 |
+| 2.7731 | 2700 | 0.3527        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 2.8758 | 2800 | 0.3446        | 0.7945                  | 0.6719                  | 0.6020                  | 0.7616                  | 0.8124                 | 0.7818                 | 0.5496                 |
+| 2.9784 | 2900 | 0.3566        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 3.0821 | 3000 | 0.3252        | 0.7948                  | 0.6682                  | 0.6025                  | 0.7617                  | 0.8152                 | 0.7848                 | 0.5516                 |
+| 3.1848 | 3100 | 0.2968        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 3.2875 | 3200 | 0.2962        | 0.7953                  | 0.6717                  | 0.6086                  | 0.7613                  | 0.8110                 | 0.7824                 | 0.5482                 |
+| 3.3901 | 3300 | 0.3084        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 3.4928 | 3400 | 0.2909        | 0.7940                  | 0.6634                  | 0.6023                  | 0.7615                  | 0.8138                 | 0.7822                 | 0.5457                 |
+| 3.5955 | 3500 | 0.2964        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 3.6982 | 3600 | 0.3193        | 0.7960                  | 0.6635                  | 0.6070                  | 0.7534                  | 0.8164                 | 0.7844                 | 0.5467                 |
+| 3.8008 | 3700 | 0.3514        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 3.9035 | 3800 | 0.3147        | 0.7973                  | 0.6696                  | 0.6125                  | 0.7616                  | 0.8176                 | 0.7885                 | 0.5469                 |
+| 4.0062 | 3900 | 0.2738        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 4.1088 | 4000 | 0.2842        | 0.7960                  | 0.6672                  | 0.6082                  | 0.7536                  | 0.8174                 | 0.7891                 | 0.5479                 |
+
+
+### Framework Versions
+- Python: 3.11.11
+- Sentence Transformers: 4.1.0
+- Transformers: 4.51.2
+- PyTorch: 2.6.0+cu124
+- Accelerate: 1.6.0
+- Datasets: 3.5.0
+- Tokenizers: 0.21.1
+
+## Citation
+
+### BibTeX
+
+#### Sentence Transformers
+```bibtex
+@inproceedings{reimers-2019-sentence-bert,
+    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
+    author = "Reimers, Nils and Gurevych, Iryna",
+    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
+    month = "11",
+    year = "2019",
+    publisher = "Association for Computational Linguistics",
+    url = "https://arxiv.org/abs/1908.10084",
+}
+```
+
+#### GISTEmbedLoss
+```bibtex
+@misc{solatorio2024gistembed,
+    title={GISTEmbed: Guided In-sample Selection of Training Negatives for Text Embedding Fine-tuning},
+    author={Aivin V. Solatorio},
+    year={2024},
+    eprint={2402.16829},
+    archivePrefix={arXiv},
+    primaryClass={cs.LG}
+}
+```
+
+<!--
+## Glossary
+
+*Clearly define terms in order to be accessible across audiences.*
+-->
+
+<!--
+## Model Card Authors
+
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
+
+<!--
+## Model Card Contact
+
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

checkpoint-4000/modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

checkpoint-4000/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39ade23fee434657c6acaffedd2e5d962324297aaf40cfff792a5b052f09aded
+size 988

checkpoint-4000/sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 512,
+  "do_lower_case": false
+}

checkpoint-4200/1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 768,
+  "pooling_mode_cls_token": true,
+  "pooling_mode_mean_tokens": false,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false,
+  "include_prompt": true
+}

checkpoint-4200/README.md

@@ -0,0 +1,1438 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:124788
+- loss:GISTEmbedLoss
+base_model: Alibaba-NLP/gte-multilingual-base
+widget:
+- source_sentence: 其他机械、设备和有形货物租赁服务代表
+  sentences:
+  - 其他机械和设备租赁服务工作人员
+  - 电子和电信设备及零部件物流经理
+  - 工业主厨
+- source_sentence: 公交车司机
+  sentences:
+  - 表演灯光设计师
+  - 乙烯基地板安装工
+  - 国际巴士司机
+- source_sentence: online communication manager
+  sentences:
+  - trades union official
+  - social media manager
+  - budget manager
+- source_sentence: Projektmanagerin
+  sentences:
+  - Projektmanager/Projektmanagerin
+  - Category-Manager
+  - Infanterist
+- source_sentence: Volksvertreter
+  sentences:
+  - Parlamentarier
+  - Oberbürgermeister
+  - Konsul
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+metrics:
+- cosine_accuracy@1
+- cosine_accuracy@20
+- cosine_accuracy@50
+- cosine_accuracy@100
+- cosine_accuracy@150
+- cosine_accuracy@200
+- cosine_precision@1
+- cosine_precision@20
+- cosine_precision@50
+- cosine_precision@100
+- cosine_precision@150
+- cosine_precision@200
+- cosine_recall@1
+- cosine_recall@20
+- cosine_recall@50
+- cosine_recall@100
+- cosine_recall@150
+- cosine_recall@200
+- cosine_ndcg@1
+- cosine_ndcg@20
+- cosine_ndcg@50
+- cosine_ndcg@100
+- cosine_ndcg@150
+- cosine_ndcg@200
+- cosine_mrr@1
+- cosine_mrr@20
+- cosine_mrr@50
+- cosine_mrr@100
+- cosine_mrr@150
+- cosine_mrr@200
+- cosine_map@1
+- cosine_map@20
+- cosine_map@50
+- cosine_map@100
+- cosine_map@150
+- cosine_map@200
+- cosine_map@500
+model-index:
+- name: SentenceTransformer based on Alibaba-NLP/gte-multilingual-base
+  results:
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: full en
+      type: full_en
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6476190476190476
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@20
+      value: 0.9904761904761905
+      name: Cosine Accuracy@20
+    - type: cosine_accuracy@50
+      value: 0.9904761904761905
+      name: Cosine Accuracy@50
+    - type: cosine_accuracy@100
+      value: 0.9904761904761905
+      name: Cosine Accuracy@100
+    - type: cosine_accuracy@150
+      value: 0.9904761904761905
+      name: Cosine Accuracy@150
+    - type: cosine_accuracy@200
+      value: 0.9904761904761905
+      name: Cosine Accuracy@200
+    - type: cosine_precision@1
+      value: 0.6476190476190476
+      name: Cosine Precision@1
+    - type: cosine_precision@20
+      value: 0.5128571428571428
+      name: Cosine Precision@20
+    - type: cosine_precision@50
+      value: 0.315047619047619
+      name: Cosine Precision@50
+    - type: cosine_precision@100
+      value: 0.18895238095238098
+      name: Cosine Precision@100
+    - type: cosine_precision@150
+      value: 0.1340952380952381
+      name: Cosine Precision@150
+    - type: cosine_precision@200
+      value: 0.10442857142857143
+      name: Cosine Precision@200
+    - type: cosine_recall@1
+      value: 0.06742481608756247
+      name: Cosine Recall@1
+    - type: cosine_recall@20
+      value: 0.5405801283990764
+      name: Cosine Recall@20
+    - type: cosine_recall@50
+      value: 0.7380563268384144
+      name: Cosine Recall@50
+    - type: cosine_recall@100
+      value: 0.8450833938763317
+      name: Cosine Recall@100
+    - type: cosine_recall@150
+      value: 0.8854496352730319
+      name: Cosine Recall@150
+    - type: cosine_recall@200
+      value: 0.9116090922199359
+      name: Cosine Recall@200
+    - type: cosine_ndcg@1
+      value: 0.6476190476190476
+      name: Cosine Ndcg@1
+    - type: cosine_ndcg@20
+      value: 0.6921758597708418
+      name: Cosine Ndcg@20
+    - type: cosine_ndcg@50
+      value: 0.7145715541794455
+      name: Cosine Ndcg@50
+    - type: cosine_ndcg@100
+      value: 0.7684704586943056
+      name: Cosine Ndcg@100
+    - type: cosine_ndcg@150
+      value: 0.7869416189606113
+      name: Cosine Ndcg@150
+    - type: cosine_ndcg@200
+      value: 0.7978715516034123
+      name: Cosine Ndcg@200
+    - type: cosine_mrr@1
+      value: 0.6476190476190476
+      name: Cosine Mrr@1
+    - type: cosine_mrr@20
+      value: 0.8090476190476191
+      name: Cosine Mrr@20
+    - type: cosine_mrr@50
+      value: 0.8090476190476191
+      name: Cosine Mrr@50
+    - type: cosine_mrr@100
+      value: 0.8090476190476191
+      name: Cosine Mrr@100
+    - type: cosine_mrr@150
+      value: 0.8090476190476191
+      name: Cosine Mrr@150
+    - type: cosine_mrr@200
+      value: 0.8090476190476191
+      name: Cosine Mrr@200
+    - type: cosine_map@1
+      value: 0.6476190476190476
+      name: Cosine Map@1
+    - type: cosine_map@20
+      value: 0.5574893623656486
+      name: Cosine Map@20
+    - type: cosine_map@50
+      value: 0.5485611329203299
+      name: Cosine Map@50
+    - type: cosine_map@100
+      value: 0.5816806877668274
+      name: Cosine Map@100
+    - type: cosine_map@150
+      value: 0.5898687797086651
+      name: Cosine Map@150
+    - type: cosine_map@200
+      value: 0.593482014013077
+      name: Cosine Map@200
+    - type: cosine_map@500
+      value: 0.5974665649900398
+      name: Cosine Map@500
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: full es
+      type: full_es
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.12972972972972974
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@20
+      value: 1.0
+      name: Cosine Accuracy@20
+    - type: cosine_accuracy@50
+      value: 1.0
+      name: Cosine Accuracy@50
+    - type: cosine_accuracy@100
+      value: 1.0
+      name: Cosine Accuracy@100
+    - type: cosine_accuracy@150
+      value: 1.0
+      name: Cosine Accuracy@150
+    - type: cosine_accuracy@200
+      value: 1.0
+      name: Cosine Accuracy@200
+    - type: cosine_precision@1
+      value: 0.12972972972972974
+      name: Cosine Precision@1
+    - type: cosine_precision@20
+      value: 0.5735135135135134
+      name: Cosine Precision@20
+    - type: cosine_precision@50
+      value: 0.3912432432432432
+      name: Cosine Precision@50
+    - type: cosine_precision@100
+      value: 0.2531351351351352
+      name: Cosine Precision@100
+    - type: cosine_precision@150
+      value: 0.19113513513513514
+      name: Cosine Precision@150
+    - type: cosine_precision@200
+      value: 0.15186486486486486
+      name: Cosine Precision@200
+    - type: cosine_recall@1
+      value: 0.0037413987812150314
+      name: Cosine Recall@1
+    - type: cosine_recall@20
+      value: 0.3850053775723816
+      name: Cosine Recall@20
+    - type: cosine_recall@50
+      value: 0.5678708571543062
+      name: Cosine Recall@50
+    - type: cosine_recall@100
+      value: 0.6771132401665688
+      name: Cosine Recall@100
+    - type: cosine_recall@150
+      value: 0.7476366668984507
+      name: Cosine Recall@150
+    - type: cosine_recall@200
+      value: 0.7806646181068078
+      name: Cosine Recall@200
+    - type: cosine_ndcg@1
+      value: 0.12972972972972974
+      name: Cosine Ndcg@1
+    - type: cosine_ndcg@20
+      value: 0.6155696219376317
+      name: Cosine Ndcg@20
+    - type: cosine_ndcg@50
+      value: 0.5902714649088991
+      name: Cosine Ndcg@50
+    - type: cosine_ndcg@100
+      value: 0.6166603984916751
+      name: Cosine Ndcg@100
+    - type: cosine_ndcg@150
+      value: 0.6514414937889701
+      name: Cosine Ndcg@150
+    - type: cosine_ndcg@200
+      value: 0.6681110549873654
+      name: Cosine Ndcg@200
+    - type: cosine_mrr@1
+      value: 0.12972972972972974
+      name: Cosine Mrr@1
+    - type: cosine_mrr@20
+      value: 0.5608108108108109
+      name: Cosine Mrr@20
+    - type: cosine_mrr@50
+      value: 0.5608108108108109
+      name: Cosine Mrr@50
+    - type: cosine_mrr@100
+      value: 0.5608108108108109
+      name: Cosine Mrr@100
+    - type: cosine_mrr@150
+      value: 0.5608108108108109
+      name: Cosine Mrr@150
+    - type: cosine_mrr@200
+      value: 0.5608108108108109
+      name: Cosine Mrr@200
+    - type: cosine_map@1
+      value: 0.12972972972972974
+      name: Cosine Map@1
+    - type: cosine_map@20
+      value: 0.4821585422089324
+      name: Cosine Map@20
+    - type: cosine_map@50
+      value: 0.4278073015090324
+      name: Cosine Map@50
+    - type: cosine_map@100
+      value: 0.4325091891776662
+      name: Cosine Map@100
+    - type: cosine_map@150
+      value: 0.4481236866241766
+      name: Cosine Map@150
+    - type: cosine_map@200
+      value: 0.45495240914630236
+      name: Cosine Map@200
+    - type: cosine_map@500
+      value: 0.4674583582676571
+      name: Cosine Map@500
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: full de
+      type: full_de
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.2955665024630542
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@20
+      value: 0.9704433497536946
+      name: Cosine Accuracy@20
+    - type: cosine_accuracy@50
+      value: 0.9852216748768473
+      name: Cosine Accuracy@50
+    - type: cosine_accuracy@100
+      value: 0.9852216748768473
+      name: Cosine Accuracy@100
+    - type: cosine_accuracy@150
+      value: 0.9901477832512315
+      name: Cosine Accuracy@150
+    - type: cosine_accuracy@200
+      value: 0.9901477832512315
+      name: Cosine Accuracy@200
+    - type: cosine_precision@1
+      value: 0.2955665024630542
+      name: Cosine Precision@1
+    - type: cosine_precision@20
+      value: 0.5118226600985222
+      name: Cosine Precision@20
+    - type: cosine_precision@50
+      value: 0.36640394088669953
+      name: Cosine Precision@50
+    - type: cosine_precision@100
+      value: 0.24108374384236453
+      name: Cosine Precision@100
+    - type: cosine_precision@150
+      value: 0.181247947454844
+      name: Cosine Precision@150
+    - type: cosine_precision@200
+      value: 0.1460591133004926
+      name: Cosine Precision@200
+    - type: cosine_recall@1
+      value: 0.01108543831680986
+      name: Cosine Recall@1
+    - type: cosine_recall@20
+      value: 0.32208430655596165
+      name: Cosine Recall@20
+    - type: cosine_recall@50
+      value: 0.5042827147735226
+      name: Cosine Recall@50
+    - type: cosine_recall@100
+      value: 0.6236391741928202
+      name: Cosine Recall@100
+    - type: cosine_recall@150
+      value: 0.6860046899787209
+      name: Cosine Recall@150
+    - type: cosine_recall@200
+      value: 0.7269946951843458
+      name: Cosine Recall@200
+    - type: cosine_ndcg@1
+      value: 0.2955665024630542
+      name: Cosine Ndcg@1
+    - type: cosine_ndcg@20
+      value: 0.5421464164798184
+      name: Cosine Ndcg@20
+    - type: cosine_ndcg@50
+      value: 0.5287112320288665
+      name: Cosine Ndcg@50
+    - type: cosine_ndcg@100
+      value: 0.5585547163826412
+      name: Cosine Ndcg@100
+    - type: cosine_ndcg@150
+      value: 0.5906267126443239
+      name: Cosine Ndcg@150
+    - type: cosine_ndcg@200
+      value: 0.6110534856124217
+      name: Cosine Ndcg@200
+    - type: cosine_mrr@1
+      value: 0.2955665024630542
+      name: Cosine Mrr@1
+    - type: cosine_mrr@20
+      value: 0.5121285045393612
+      name: Cosine Mrr@20
+    - type: cosine_mrr@50
+      value: 0.5126572733439921
+      name: Cosine Mrr@50
+    - type: cosine_mrr@100
+      value: 0.5126572733439921
+      name: Cosine Mrr@100
+    - type: cosine_mrr@150
+      value: 0.5127050996388891
+      name: Cosine Mrr@150
+    - type: cosine_mrr@200
+      value: 0.5127050996388891
+      name: Cosine Mrr@200
+    - type: cosine_map@1
+      value: 0.2955665024630542
+      name: Cosine Map@1
+    - type: cosine_map@20
+      value: 0.4040566267923372
+      name: Cosine Map@20
+    - type: cosine_map@50
+      value: 0.36142610008228787
+      name: Cosine Map@50
+    - type: cosine_map@100
+      value: 0.365695506737717
+      name: Cosine Map@100
+    - type: cosine_map@150
+      value: 0.38080017460364707
+      name: Cosine Map@150
+    - type: cosine_map@200
+      value: 0.3885278636281841
+      name: Cosine Map@200
+    - type: cosine_map@500
+      value: 0.40107654023571443
+      name: Cosine Map@500
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: full zh
+      type: full_zh
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6504854368932039
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@20
+      value: 0.9805825242718447
+      name: Cosine Accuracy@20
+    - type: cosine_accuracy@50
+      value: 0.9902912621359223
+      name: Cosine Accuracy@50
+    - type: cosine_accuracy@100
+      value: 0.9902912621359223
+      name: Cosine Accuracy@100
+    - type: cosine_accuracy@150
+      value: 0.9902912621359223
+      name: Cosine Accuracy@150
+    - type: cosine_accuracy@200
+      value: 0.9902912621359223
+      name: Cosine Accuracy@200
+    - type: cosine_precision@1
+      value: 0.6504854368932039
+      name: Cosine Precision@1
+    - type: cosine_precision@20
+      value: 0.4786407766990292
+      name: Cosine Precision@20
+    - type: cosine_precision@50
+      value: 0.2910679611650486
+      name: Cosine Precision@50
+    - type: cosine_precision@100
+      value: 0.17572815533980585
+      name: Cosine Precision@100
+    - type: cosine_precision@150
+      value: 0.12543689320388351
+      name: Cosine Precision@150
+    - type: cosine_precision@200
+      value: 0.09786407766990295
+      name: Cosine Precision@200
+    - type: cosine_recall@1
+      value: 0.060542712533387485
+      name: Cosine Recall@1
+    - type: cosine_recall@20
+      value: 0.5120181745235721
+      name: Cosine Recall@20
+    - type: cosine_recall@50
+      value: 0.6949930226095598
+      name: Cosine Recall@50
+    - type: cosine_recall@100
+      value: 0.7990376401893455
+      name: Cosine Recall@100
+    - type: cosine_recall@150
+      value: 0.8444978387246413
+      name: Cosine Recall@150
+    - type: cosine_recall@200
+      value: 0.8737742771860034
+      name: Cosine Recall@200
+    - type: cosine_ndcg@1
+      value: 0.6504854368932039
+      name: Cosine Ndcg@1
+    - type: cosine_ndcg@20
+      value: 0.6543043826860687
+      name: Cosine Ndcg@20
+    - type: cosine_ndcg@50
+      value: 0.6719601686921535
+      name: Cosine Ndcg@50
+    - type: cosine_ndcg@100
+      value: 0.7228108377810673
+      name: Cosine Ndcg@100
+    - type: cosine_ndcg@150
+      value: 0.7425317578844268
+      name: Cosine Ndcg@150
+    - type: cosine_ndcg@200
+      value: 0.7540053327385158
+      name: Cosine Ndcg@200
+    - type: cosine_mrr@1
+      value: 0.6504854368932039
+      name: Cosine Mrr@1
+    - type: cosine_mrr@20
+      value: 0.7996763754045308
+      name: Cosine Mrr@20
+    - type: cosine_mrr@50
+      value: 0.8000497883993031
+      name: Cosine Mrr@50
+    - type: cosine_mrr@100
+      value: 0.8000497883993031
+      name: Cosine Mrr@100
+    - type: cosine_mrr@150
+      value: 0.8000497883993031
+      name: Cosine Mrr@150
+    - type: cosine_mrr@200
+      value: 0.8000497883993031
+      name: Cosine Mrr@200
+    - type: cosine_map@1
+      value: 0.6504854368932039
+      name: Cosine Map@1
+    - type: cosine_map@20
+      value: 0.5094084685339617
+      name: Cosine Map@20
+    - type: cosine_map@50
+      value: 0.4946470598488666
+      name: Cosine Map@50
+    - type: cosine_map@100
+      value: 0.5223997206445464
+      name: Cosine Map@100
+    - type: cosine_map@150
+      value: 0.5301660854751861
+      name: Cosine Map@150
+    - type: cosine_map@200
+      value: 0.5337279091857492
+      name: Cosine Map@200
+    - type: cosine_map@500
+      value: 0.5392657572937102
+      name: Cosine Map@500
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: mix es
+      type: mix_es
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.7238689547581904
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@20
+      value: 0.9583983359334374
+      name: Cosine Accuracy@20
+    - type: cosine_accuracy@50
+      value: 0.9802392095683827
+      name: Cosine Accuracy@50
+    - type: cosine_accuracy@100
+      value: 0.9942797711908476
+      name: Cosine Accuracy@100
+    - type: cosine_accuracy@150
+      value: 0.9953198127925117
+      name: Cosine Accuracy@150
+    - type: cosine_accuracy@200
+      value: 0.9973998959958398
+      name: Cosine Accuracy@200
+    - type: cosine_precision@1
+      value: 0.7238689547581904
+      name: Cosine Precision@1
+    - type: cosine_precision@20
+      value: 0.12412896515860634
+      name: Cosine Precision@20
+    - type: cosine_precision@50
+      value: 0.05145085803432139
+      name: Cosine Precision@50
+    - type: cosine_precision@100
+      value: 0.026245449817992726
+      name: Cosine Precision@100
+    - type: cosine_precision@150
+      value: 0.017614837926850403
+      name: Cosine Precision@150
+    - type: cosine_precision@200
+      value: 0.013283931357254293
+      name: Cosine Precision@200
+    - type: cosine_recall@1
+      value: 0.28019216006735503
+      name: Cosine Recall@1
+    - type: cosine_recall@20
+      value: 0.9169353440804299
+      name: Cosine Recall@20
+    - type: cosine_recall@50
+      value: 0.9499306638932224
+      name: Cosine Recall@50
+    - type: cosine_recall@100
+      value: 0.9701768070722828
+      name: Cosine Recall@100
+    - type: cosine_recall@150
+      value: 0.9764690587623505
+      name: Cosine Recall@150
+    - type: cosine_recall@200
+      value: 0.9822326226382389
+      name: Cosine Recall@200
+    - type: cosine_ndcg@1
+      value: 0.7238689547581904
+      name: Cosine Ndcg@1
+    - type: cosine_ndcg@20
+      value: 0.8023238060267395
+      name: Cosine Ndcg@20
+    - type: cosine_ndcg@50
+      value: 0.8113379258247732
+      name: Cosine Ndcg@50
+    - type: cosine_ndcg@100
+      value: 0.8156949679776019
+      name: Cosine Ndcg@100
+    - type: cosine_ndcg@150
+      value: 0.816929855500621
+      name: Cosine Ndcg@150
+    - type: cosine_ndcg@200
+      value: 0.8179575655343403
+      name: Cosine Ndcg@200
+    - type: cosine_mrr@1
+      value: 0.7238689547581904
+      name: Cosine Mrr@1
+    - type: cosine_mrr@20
+      value: 0.7934277492682618
+      name: Cosine Mrr@20
+    - type: cosine_mrr@50
+      value: 0.7941208450339935
+      name: Cosine Mrr@50
+    - type: cosine_mrr@100
+      value: 0.7943224531588357
+      name: Cosine Mrr@100
+    - type: cosine_mrr@150
+      value: 0.7943312488289611
+      name: Cosine Mrr@150
+    - type: cosine_mrr@200
+      value: 0.7943443835009225
+      name: Cosine Mrr@200
+    - type: cosine_map@1
+      value: 0.7238689547581904
+      name: Cosine Map@1
+    - type: cosine_map@20
+      value: 0.7331525143106996
+      name: Cosine Map@20
+    - type: cosine_map@50
+      value: 0.7355830040348272
+      name: Cosine Map@50
+    - type: cosine_map@100
+      value: 0.7361451167677289
+      name: Cosine Map@100
+    - type: cosine_map@150
+      value: 0.7362661519275265
+      name: Cosine Map@150
+    - type: cosine_map@200
+      value: 0.7363390374447161
+      name: Cosine Map@200
+    - type: cosine_map@500
+      value: 0.7364481715630059
+      name: Cosine Map@500
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: mix de
+      type: mix_de
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6666666666666666
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@20
+      value: 0.9479979199167967
+      name: Cosine Accuracy@20
+    - type: cosine_accuracy@50
+      value: 0.9760790431617264
+      name: Cosine Accuracy@50
+    - type: cosine_accuracy@100
+      value: 0.9859594383775351
+      name: Cosine Accuracy@100
+    - type: cosine_accuracy@150
+      value: 0.9927197087883516
+      name: Cosine Accuracy@150
+    - type: cosine_accuracy@200
+      value: 0.9947997919916797
+      name: Cosine Accuracy@200
+    - type: cosine_precision@1
+      value: 0.6666666666666666
+      name: Cosine Precision@1
+    - type: cosine_precision@20
+      value: 0.12483099323972958
+      name: Cosine Precision@20
+    - type: cosine_precision@50
+      value: 0.05219968798751951
+      name: Cosine Precision@50
+    - type: cosine_precision@100
+      value: 0.026682267290691637
+      name: Cosine Precision@100
+    - type: cosine_precision@150
+      value: 0.017985786098110586
+      name: Cosine Precision@150
+    - type: cosine_precision@200
+      value: 0.013541341653666149
+      name: Cosine Precision@200
+    - type: cosine_recall@1
+      value: 0.25062402496099845
+      name: Cosine Recall@1
+    - type: cosine_recall@20
+      value: 0.9064222568902757
+      name: Cosine Recall@20
+    - type: cosine_recall@50
+      value: 0.9466805338880222
+      name: Cosine Recall@50
+    - type: cosine_recall@100
+      value: 0.9669786791471658
+      name: Cosine Recall@100
+    - type: cosine_recall@150
+      value: 0.9774657652972785
+      name: Cosine Recall@150
+    - type: cosine_recall@200
+      value: 0.9810192407696308
+      name: Cosine Recall@200
+    - type: cosine_ndcg@1
+      value: 0.6666666666666666
+      name: Cosine Ndcg@1
+    - type: cosine_ndcg@20
+      value: 0.7705186419550625
+      name: Cosine Ndcg@20
+    - type: cosine_ndcg@50
+      value: 0.7817408957971655
+      name: Cosine Ndcg@50
+    - type: cosine_ndcg@100
+      value: 0.786309170410984
+      name: Cosine Ndcg@100
+    - type: cosine_ndcg@150
+      value: 0.7883932008449921
+      name: Cosine Ndcg@150
+    - type: cosine_ndcg@200
+      value: 0.7890611279585495
+      name: Cosine Ndcg@200
+    - type: cosine_mrr@1
+      value: 0.6666666666666666
+      name: Cosine Mrr@1
+    - type: cosine_mrr@20
+      value: 0.7486665934008992
+      name: Cosine Mrr@20
+    - type: cosine_mrr@50
+      value: 0.7496295288804224
+      name: Cosine Mrr@50
+    - type: cosine_mrr@100
+      value: 0.74976967024613
+      name: Cosine Mrr@100
+    - type: cosine_mrr@150
+      value: 0.7498264653686212
+      name: Cosine Mrr@150
+    - type: cosine_mrr@200
+      value: 0.7498390441909701
+      name: Cosine Mrr@200
+    - type: cosine_map@1
+      value: 0.6666666666666666
+      name: Cosine Map@1
+    - type: cosine_map@20
+      value: 0.6933856329177108
+      name: Cosine Map@20
+    - type: cosine_map@50
+      value: 0.6963720532834866
+      name: Cosine Map@50
+    - type: cosine_map@100
+      value: 0.6970430360365766
+      name: Cosine Map@100
+    - type: cosine_map@150
+      value: 0.6972336080548289
+      name: Cosine Map@150
+    - type: cosine_map@200
+      value: 0.697279051235347
+      name: Cosine Map@200
+    - type: cosine_map@500
+      value: 0.6973750625395665
+      name: Cosine Map@500
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: mix zh
+      type: mix_zh
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.19292771710868434
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@20
+      value: 1.0
+      name: Cosine Accuracy@20
+    - type: cosine_accuracy@50
+      value: 1.0
+      name: Cosine Accuracy@50
+    - type: cosine_accuracy@100
+      value: 1.0
+      name: Cosine Accuracy@100
+    - type: cosine_accuracy@150
+      value: 1.0
+      name: Cosine Accuracy@150
+    - type: cosine_accuracy@200
+      value: 1.0
+      name: Cosine Accuracy@200
+    - type: cosine_precision@1
+      value: 0.19292771710868434
+      name: Cosine Precision@1
+    - type: cosine_precision@20
+      value: 0.15439417576703063
+      name: Cosine Precision@20
+    - type: cosine_precision@50
+      value: 0.0617576703068123
+      name: Cosine Precision@50
+    - type: cosine_precision@100
+      value: 0.03087883515340615
+      name: Cosine Precision@100
+    - type: cosine_precision@150
+      value: 0.020585890102270757
+      name: Cosine Precision@150
+    - type: cosine_precision@200
+      value: 0.015439417576703075
+      name: Cosine Precision@200
+    - type: cosine_recall@1
+      value: 0.062241537280538835
+      name: Cosine Recall@1
+    - type: cosine_recall@20
+      value: 1.0
+      name: Cosine Recall@20
+    - type: cosine_recall@50
+      value: 1.0
+      name: Cosine Recall@50
+    - type: cosine_recall@100
+      value: 1.0
+      name: Cosine Recall@100
+    - type: cosine_recall@150
+      value: 1.0
+      name: Cosine Recall@150
+    - type: cosine_recall@200
+      value: 1.0
+      name: Cosine Recall@200
+    - type: cosine_ndcg@1
+      value: 0.19292771710868434
+      name: Cosine Ndcg@1
+    - type: cosine_ndcg@20
+      value: 0.5475590939157456
+      name: Cosine Ndcg@20
+    - type: cosine_ndcg@50
+      value: 0.5475590939157456
+      name: Cosine Ndcg@50
+    - type: cosine_ndcg@100
+      value: 0.5475590939157456
+      name: Cosine Ndcg@100
+    - type: cosine_ndcg@150
+      value: 0.5475590939157456
+      name: Cosine Ndcg@150
+    - type: cosine_ndcg@200
+      value: 0.5475590939157456
+      name: Cosine Ndcg@200
+    - type: cosine_mrr@1
+      value: 0.19292771710868434
+      name: Cosine Mrr@1
+    - type: cosine_mrr@20
+      value: 0.41052639363871923
+      name: Cosine Mrr@20
+    - type: cosine_mrr@50
+      value: 0.41052639363871923
+      name: Cosine Mrr@50
+    - type: cosine_mrr@100
+      value: 0.41052639363871923
+      name: Cosine Mrr@100
+    - type: cosine_mrr@150
+      value: 0.41052639363871923
+      name: Cosine Mrr@150
+    - type: cosine_mrr@200
+      value: 0.41052639363871923
+      name: Cosine Mrr@200
+    - type: cosine_map@1
+      value: 0.19292771710868434
+      name: Cosine Map@1
+    - type: cosine_map@20
+      value: 0.3297429315299459
+      name: Cosine Map@20
+    - type: cosine_map@50
+      value: 0.3297429315299459
+      name: Cosine Map@50
+    - type: cosine_map@100
+      value: 0.3297429315299459
+      name: Cosine Map@100
+    - type: cosine_map@150
+      value: 0.3297429315299459
+      name: Cosine Map@150
+    - type: cosine_map@200
+      value: 0.3297429315299459
+      name: Cosine Map@200
+    - type: cosine_map@500
+      value: 0.3297429315299459
+      name: Cosine Map@500
+---
+
+# SentenceTransformer based on Alibaba-NLP/gte-multilingual-base
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [Alibaba-NLP/gte-multilingual-base](https://huggingface.co/Alibaba-NLP/gte-multilingual-base) on the full_en, full_de, full_es, full_zh and mix datasets. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
+
+## Model Details
+
+### Model Description
+- **Model Type:** Sentence Transformer
+- **Base model:** [Alibaba-NLP/gte-multilingual-base](https://huggingface.co/Alibaba-NLP/gte-multilingual-base) <!-- at revision 9fdd4ee8bba0e2808a34e0e739576f6740d2b225 -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 768 dimensions
+- **Similarity Function:** Cosine Similarity
+- **Training Datasets:**
+    - full_en
+    - full_de
+    - full_es
+    - full_zh
+    - mix
+<!-- - **Language:** Unknown -->
+<!-- - **License:** Unknown -->
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
+- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
+
+### Full Model Architecture
+
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: NewModel 
+  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+  (2): Normalize()
+)
+```
+
+## Usage
+
+### Direct Usage (Sentence Transformers)
+
+First install the Sentence Transformers library:
+
+```bash
+pip install -U sentence-transformers
+```
+
+Then you can load this model and run inference.
+```python
+from sentence_transformers import SentenceTransformer
+
+# Download from the 🤗 Hub
+model = SentenceTransformer("sentence_transformers_model_id")
+# Run inference
+sentences = [
+    'Volksvertreter',
+    'Parlamentarier',
+    'Oberbürgermeister',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 768]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities.shape)
+# [3, 3]
+```
+
+<!--
+### Direct Usage (Transformers)
+
+<details><summary>Click to see the direct usage in Transformers</summary>
+
+</details>
+-->
+
+<!--
+### Downstream Usage (Sentence Transformers)
+
+You can finetune this model on your own dataset.
+
+<details><summary>Click to expand</summary>
+
+</details>
+-->
+
+<!--
+### Out-of-Scope Use
+
+*List how the model may foreseeably be misused and address what users ought not to do with the model.*
+-->
+
+## Evaluation
+
+### Metrics
+
+#### Information Retrieval
+
+* Datasets: `full_en`, `full_es`, `full_de`, `full_zh`, `mix_es`, `mix_de` and `mix_zh`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric               | full_en    | full_es    | full_de    | full_zh   | mix_es    | mix_de     | mix_zh     |
+|:---------------------|:-----------|:-----------|:-----------|:----------|:----------|:-----------|:-----------|
+| cosine_accuracy@1    | 0.6476     | 0.1297     | 0.2956     | 0.6505    | 0.7239    | 0.6667     | 0.1929     |
+| cosine_accuracy@20   | 0.9905     | 1.0        | 0.9704     | 0.9806    | 0.9584    | 0.948      | 1.0        |
+| cosine_accuracy@50   | 0.9905     | 1.0        | 0.9852     | 0.9903    | 0.9802    | 0.9761     | 1.0        |
+| cosine_accuracy@100  | 0.9905     | 1.0        | 0.9852     | 0.9903    | 0.9943    | 0.986      | 1.0        |
+| cosine_accuracy@150  | 0.9905     | 1.0        | 0.9901     | 0.9903    | 0.9953    | 0.9927     | 1.0        |
+| cosine_accuracy@200  | 0.9905     | 1.0        | 0.9901     | 0.9903    | 0.9974    | 0.9948     | 1.0        |
+| cosine_precision@1   | 0.6476     | 0.1297     | 0.2956     | 0.6505    | 0.7239    | 0.6667     | 0.1929     |
+| cosine_precision@20  | 0.5129     | 0.5735     | 0.5118     | 0.4786    | 0.1241    | 0.1248     | 0.1544     |
+| cosine_precision@50  | 0.315      | 0.3912     | 0.3664     | 0.2911    | 0.0515    | 0.0522     | 0.0618     |
+| cosine_precision@100 | 0.189      | 0.2531     | 0.2411     | 0.1757    | 0.0262    | 0.0267     | 0.0309     |
+| cosine_precision@150 | 0.1341     | 0.1911     | 0.1812     | 0.1254    | 0.0176    | 0.018      | 0.0206     |
+| cosine_precision@200 | 0.1044     | 0.1519     | 0.1461     | 0.0979    | 0.0133    | 0.0135     | 0.0154     |
+| cosine_recall@1      | 0.0674     | 0.0037     | 0.0111     | 0.0605    | 0.2802    | 0.2506     | 0.0622     |
+| cosine_recall@20     | 0.5406     | 0.385      | 0.3221     | 0.512     | 0.9169    | 0.9064     | 1.0        |
+| cosine_recall@50     | 0.7381     | 0.5679     | 0.5043     | 0.695     | 0.9499    | 0.9467     | 1.0        |
+| cosine_recall@100    | 0.8451     | 0.6771     | 0.6236     | 0.799     | 0.9702    | 0.967      | 1.0        |
+| cosine_recall@150    | 0.8854     | 0.7476     | 0.686      | 0.8445    | 0.9765    | 0.9775     | 1.0        |
+| cosine_recall@200    | 0.9116     | 0.7807     | 0.727      | 0.8738    | 0.9822    | 0.981      | 1.0        |
+| cosine_ndcg@1        | 0.6476     | 0.1297     | 0.2956     | 0.6505    | 0.7239    | 0.6667     | 0.1929     |
+| cosine_ndcg@20       | 0.6922     | 0.6156     | 0.5421     | 0.6543    | 0.8023    | 0.7705     | 0.5476     |
+| cosine_ndcg@50       | 0.7146     | 0.5903     | 0.5287     | 0.672     | 0.8113    | 0.7817     | 0.5476     |
+| cosine_ndcg@100      | 0.7685     | 0.6167     | 0.5586     | 0.7228    | 0.8157    | 0.7863     | 0.5476     |
+| cosine_ndcg@150      | 0.7869     | 0.6514     | 0.5906     | 0.7425    | 0.8169    | 0.7884     | 0.5476     |
+| **cosine_ndcg@200**  | **0.7979** | **0.6681** | **0.6111** | **0.754** | **0.818** | **0.7891** | **0.5476** |
+| cosine_mrr@1         | 0.6476     | 0.1297     | 0.2956     | 0.6505    | 0.7239    | 0.6667     | 0.1929     |
+| cosine_mrr@20        | 0.809      | 0.5608     | 0.5121     | 0.7997    | 0.7934    | 0.7487     | 0.4105     |
+| cosine_mrr@50        | 0.809      | 0.5608     | 0.5127     | 0.8       | 0.7941    | 0.7496     | 0.4105     |
+| cosine_mrr@100       | 0.809      | 0.5608     | 0.5127     | 0.8       | 0.7943    | 0.7498     | 0.4105     |
+| cosine_mrr@150       | 0.809      | 0.5608     | 0.5127     | 0.8       | 0.7943    | 0.7498     | 0.4105     |
+| cosine_mrr@200       | 0.809      | 0.5608     | 0.5127     | 0.8       | 0.7943    | 0.7498     | 0.4105     |
+| cosine_map@1         | 0.6476     | 0.1297     | 0.2956     | 0.6505    | 0.7239    | 0.6667     | 0.1929     |
+| cosine_map@20        | 0.5575     | 0.4822     | 0.4041     | 0.5094    | 0.7332    | 0.6934     | 0.3297     |
+| cosine_map@50        | 0.5486     | 0.4278     | 0.3614     | 0.4946    | 0.7356    | 0.6964     | 0.3297     |
+| cosine_map@100       | 0.5817     | 0.4325     | 0.3657     | 0.5224    | 0.7361    | 0.697      | 0.3297     |
+| cosine_map@150       | 0.5899     | 0.4481     | 0.3808     | 0.5302    | 0.7363    | 0.6972     | 0.3297     |
+| cosine_map@200       | 0.5935     | 0.455      | 0.3885     | 0.5337    | 0.7363    | 0.6973     | 0.3297     |
+| cosine_map@500       | 0.5975     | 0.4675     | 0.4011     | 0.5393    | 0.7364    | 0.6974     | 0.3297     |
+
+<!--
+## Bias, Risks and Limitations
+
+*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
+-->
+
+<!--
+### Recommendations
+
+*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
+-->
+
+## Training Details
+
+### Training Datasets
+<details><summary>full_en</summary>
+
+#### full_en
+
+* Dataset: full_en
+* Size: 28,880 training samples
+* Columns: <code>anchor</code> and <code>positive</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | anchor                                                                           | positive                                                                         |
+  |:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|
+  | type    | string                                                                           | string                                                                           |
+  | details | <ul><li>min: 3 tokens</li><li>mean: 5.68 tokens</li><li>max: 11 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 5.76 tokens</li><li>max: 12 tokens</li></ul> |
+* Samples:
+  | anchor                                   | positive                                 |
+  |:-----------------------------------------|:-----------------------------------------|
+  | <code>air commodore</code>               | <code>flight lieutenant</code>           |
+  | <code>command and control officer</code> | <code>flight officer</code>              |
+  | <code>air commodore</code>               | <code>command and control officer</code> |
+* Loss: [<code>GISTEmbedLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#gistembedloss) with these parameters:
+  ```json
+  {'guide': SentenceTransformer(
+    (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel 
+    (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+    (2): Normalize()
+  ), 'temperature': 0.01, 'margin_strategy': 'absolute', 'margin': 0.0}
+  ```
+</details>
+<details><summary>full_de</summary>
+
+#### full_de
+
+* Dataset: full_de
+* Size: 23,023 training samples
+* Columns: <code>anchor</code> and <code>positive</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | anchor                                                                           | positive                                                                         |
+  |:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|
+  | type    | string                                                                           | string                                                                           |
+  | details | <ul><li>min: 3 tokens</li><li>mean: 7.99 tokens</li><li>max: 30 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 8.19 tokens</li><li>max: 30 tokens</li></ul> |
+* Samples:
+  | anchor                            | positive                                             |
+  |:----------------------------------|:-----------------------------------------------------|
+  | <code>Staffelkommandantin</code>  | <code>Kommodore</code>                               |
+  | <code>Luftwaffenoffizierin</code> | <code>Luftwaffenoffizier/Luftwaffenoffizierin</code> |
+  | <code>Staffelkommandantin</code>  | <code>Luftwaffenoffizierin</code>                    |
+* Loss: [<code>GISTEmbedLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#gistembedloss) with these parameters:
+  ```json
+  {'guide': SentenceTransformer(
+    (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel 
+    (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+    (2): Normalize()
+  ), 'temperature': 0.01, 'margin_strategy': 'absolute', 'margin': 0.0}
+  ```
+</details>
+<details><summary>full_es</summary>
+
+#### full_es
+
+* Dataset: full_es
+* Size: 20,724 training samples
+* Columns: <code>anchor</code> and <code>positive</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | anchor                                                                           | positive                                                                         |
+  |:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|
+  | type    | string                                                                           | string                                                                           |
+  | details | <ul><li>min: 3 tokens</li><li>mean: 9.13 tokens</li><li>max: 32 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 8.84 tokens</li><li>max: 32 tokens</li></ul> |
+* Samples:
+  | anchor                              | positive                                   |
+  |:------------------------------------|:-------------------------------------------|
+  | <code>jefe de escuadrón</code>      | <code>instructor</code>                    |
+  | <code>comandante de aeronave</code> | <code>instructor de simulador</code>       |
+  | <code>instructor</code>             | <code>oficial del Ejército del Aire</code> |
+* Loss: [<code>GISTEmbedLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#gistembedloss) with these parameters:
+  ```json
+  {'guide': SentenceTransformer(
+    (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel 
+    (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+    (2): Normalize()
+  ), 'temperature': 0.01, 'margin_strategy': 'absolute', 'margin': 0.0}
+  ```
+</details>
+<details><summary>full_zh</summary>
+
+#### full_zh
+
+* Dataset: full_zh
+* Size: 30,401 training samples
+* Columns: <code>anchor</code> and <code>positive</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | anchor                                                                           | positive                                                                         |
+  |:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|
+  | type    | string                                                                           | string                                                                           |
+  | details | <ul><li>min: 5 tokens</li><li>mean: 7.15 tokens</li><li>max: 14 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 7.46 tokens</li><li>max: 21 tokens</li></ul> |
+* Samples:
+  | anchor            | positive             |
+  |:------------------|:---------------------|
+  | <code>技术总监</code> | <code>技术和运营总监</code> |
+  | <code>技术总监</code> | <code>技术主管</code>    |
+  | <code>技术总监</code> | <code>技术艺术总监</code>  |
+* Loss: [<code>GISTEmbedLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#gistembedloss) with these parameters:
+  ```json
+  {'guide': SentenceTransformer(
+    (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel 
+    (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+    (2): Normalize()
+  ), 'temperature': 0.01, 'margin_strategy': 'absolute', 'margin': 0.0}
+  ```
+</details>
+<details><summary>mix</summary>
+
+#### mix
+
+* Dataset: mix
+* Size: 21,760 training samples
+* Columns: <code>anchor</code> and <code>positive</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | anchor                                                                           | positive                                                                         |
+  |:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|
+  | type    | string                                                                           | string                                                                           |
+  | details | <ul><li>min: 2 tokens</li><li>mean: 6.71 tokens</li><li>max: 19 tokens</li></ul> | <ul><li>min: 2 tokens</li><li>mean: 7.69 tokens</li><li>max: 19 tokens</li></ul> |
+* Samples:
+  | anchor                                    | positive                                                        |
+  |:------------------------------------------|:----------------------------------------------------------------|
+  | <code>technical manager</code>            | <code>Technischer Direktor für Bühne, Film und Fernsehen</code> |
+  | <code>head of technical</code>            | <code>directora técnica</code>                                  |
+  | <code>head of technical department</code> | <code>技术艺术总监</code>                                             |
+* Loss: [<code>GISTEmbedLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#gistembedloss) with these parameters:
+  ```json
+  {'guide': SentenceTransformer(
+    (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel 
+    (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+    (2): Normalize()
+  ), 'temperature': 0.01, 'margin_strategy': 'absolute', 'margin': 0.0}
+  ```
+</details>
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 64
+- `per_device_eval_batch_size`: 128
+- `gradient_accumulation_steps`: 2
+- `num_train_epochs`: 5
+- `warmup_ratio`: 0.05
+- `log_on_each_node`: False
+- `fp16`: True
+- `dataloader_num_workers`: 4
+- `ddp_find_unused_parameters`: True
+- `batch_sampler`: no_duplicates
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: steps
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 64
+- `per_device_eval_batch_size`: 128
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 2
+- `eval_accumulation_steps`: None
+- `torch_empty_cache_steps`: None
+- `learning_rate`: 5e-05
+- `weight_decay`: 0.0
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1.0
+- `num_train_epochs`: 5
+- `max_steps`: -1
+- `lr_scheduler_type`: linear
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.05
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: False
+- `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`: 4
+- `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}
+- `tp_size`: 0
+- `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}
+- `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`: True
+- `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
+- `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`: False
+- `torch_compile_backend`: None
+- `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`: False
+- `use_liger_kernel`: False
+- `eval_use_gather_object`: False
+- `average_tokens_across_devices`: False
+- `prompts`: None
+- `batch_sampler`: no_duplicates
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch  | Step | Training Loss | full_en_cosine_ndcg@200 | full_es_cosine_ndcg@200 | full_de_cosine_ndcg@200 | full_zh_cosine_ndcg@200 | mix_es_cosine_ndcg@200 | mix_de_cosine_ndcg@200 | mix_zh_cosine_ndcg@200 |
+|:------:|:----:|:-------------:|:-----------------------:|:-----------------------:|:-----------------------:|:-----------------------:|:----------------------:|:----------------------:|:----------------------:|
+| -1     | -1   | -             | 0.7447                  | 0.6125                  | 0.5378                  | 0.7240                  | 0.7029                 | 0.6345                 | 0.5531                 |
+| 0.0010 | 1    | 3.4866        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 0.1027 | 100  | 2.5431        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 0.2053 | 200  | 1.4536        | 0.7993                  | 0.6633                  | 0.5974                  | 0.7642                  | 0.7567                 | 0.7011                 | 0.5498                 |
+| 0.3080 | 300  | 1.1018        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 0.4107 | 400  | 0.9184        | 0.7925                  | 0.6586                  | 0.6058                  | 0.7587                  | 0.7749                 | 0.7278                 | 0.5486                 |
+| 0.5133 | 500  | 0.8973        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 0.6160 | 600  | 0.7309        | 0.7951                  | 0.6671                  | 0.6096                  | 0.7708                  | 0.7793                 | 0.7339                 | 0.5525                 |
+| 0.7187 | 700  | 0.7297        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 0.8214 | 800  | 0.7281        | 0.7929                  | 0.6711                  | 0.6088                  | 0.7645                  | 0.7899                 | 0.7444                 | 0.5479                 |
+| 0.9240 | 900  | 0.6607        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 1.0267 | 1000 | 0.6075        | 0.7915                  | 0.6659                  | 0.6088                  | 0.7665                  | 0.7968                 | 0.7588                 | 0.5482                 |
+| 1.1294 | 1100 | 0.4553        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 1.2320 | 1200 | 0.4775        | 0.7979                  | 0.6696                  | 0.6033                  | 0.7669                  | 0.7959                 | 0.7624                 | 0.5484                 |
+| 1.3347 | 1300 | 0.4838        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 1.4374 | 1400 | 0.4912        | 0.7973                  | 0.6757                  | 0.6112                  | 0.7656                  | 0.7978                 | 0.7650                 | 0.5487                 |
+| 1.5400 | 1500 | 0.4732        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 1.6427 | 1600 | 0.5269        | 0.8031                  | 0.6723                  | 0.6108                  | 0.7654                  | 0.8008                 | 0.7660                 | 0.5492                 |
+| 1.7454 | 1700 | 0.4822        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 1.8480 | 1800 | 0.5072        | 0.7962                  | 0.6668                  | 0.6051                  | 0.7592                  | 0.8001                 | 0.7714                 | 0.5486                 |
+| 1.9507 | 1900 | 0.4709        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 2.0544 | 2000 | 0.3772        | 0.7940                  | 0.6647                  | 0.6037                  | 0.7579                  | 0.8064                 | 0.7732                 | 0.5479                 |
+| 2.1571 | 2100 | 0.3982        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 2.2598 | 2200 | 0.3073        | 0.7969                  | 0.6652                  | 0.6005                  | 0.7625                  | 0.8054                 | 0.7734                 | 0.5493                 |
+| 2.3624 | 2300 | 0.383         | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 2.4651 | 2400 | 0.3687        | 0.7925                  | 0.6690                  | 0.5987                  | 0.7583                  | 0.8081                 | 0.7735                 | 0.5477                 |
+| 2.5678 | 2500 | 0.3472        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 2.6704 | 2600 | 0.3557        | 0.7956                  | 0.6758                  | 0.6019                  | 0.7659                  | 0.8082                 | 0.7767                 | 0.5491                 |
+| 2.7731 | 2700 | 0.3527        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 2.8758 | 2800 | 0.3446        | 0.7945                  | 0.6719                  | 0.6020                  | 0.7616                  | 0.8124                 | 0.7818                 | 0.5496                 |
+| 2.9784 | 2900 | 0.3566        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 3.0821 | 3000 | 0.3252        | 0.7948                  | 0.6682                  | 0.6025                  | 0.7617                  | 0.8152                 | 0.7848                 | 0.5516                 |
+| 3.1848 | 3100 | 0.2968        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 3.2875 | 3200 | 0.2962        | 0.7953                  | 0.6717                  | 0.6086                  | 0.7613                  | 0.8110                 | 0.7824                 | 0.5482                 |
+| 3.3901 | 3300 | 0.3084        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 3.4928 | 3400 | 0.2909        | 0.7940                  | 0.6634                  | 0.6023                  | 0.7615                  | 0.8138                 | 0.7822                 | 0.5457                 |
+| 3.5955 | 3500 | 0.2964        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 3.6982 | 3600 | 0.3193        | 0.7960                  | 0.6635                  | 0.6070                  | 0.7534                  | 0.8164                 | 0.7844                 | 0.5467                 |
+| 3.8008 | 3700 | 0.3514        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 3.9035 | 3800 | 0.3147        | 0.7973                  | 0.6696                  | 0.6125                  | 0.7616                  | 0.8176                 | 0.7885                 | 0.5469                 |
+| 4.0062 | 3900 | 0.2738        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 4.1088 | 4000 | 0.2842        | 0.7960                  | 0.6672                  | 0.6082                  | 0.7536                  | 0.8174                 | 0.7891                 | 0.5479                 |
+| 4.2115 | 4100 | 0.2739        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 4.3142 | 4200 | 0.2704        | 0.7979                  | 0.6681                  | 0.6111                  | 0.7540                  | 0.8180                 | 0.7891                 | 0.5476                 |
+
+
+### Framework Versions
+- Python: 3.11.11
+- Sentence Transformers: 4.1.0
+- Transformers: 4.51.2
+- PyTorch: 2.6.0+cu124
+- Accelerate: 1.6.0
+- Datasets: 3.5.0
+- Tokenizers: 0.21.1
+
+## Citation
+
+### BibTeX
+
+#### Sentence Transformers
+```bibtex
+@inproceedings{reimers-2019-sentence-bert,
+    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
+    author = "Reimers, Nils and Gurevych, Iryna",
+    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
+    month = "11",
+    year = "2019",
+    publisher = "Association for Computational Linguistics",
+    url = "https://arxiv.org/abs/1908.10084",
+}
+```
+
+#### GISTEmbedLoss
+```bibtex
+@misc{solatorio2024gistembed,
+    title={GISTEmbed: Guided In-sample Selection of Training Negatives for Text Embedding Fine-tuning},
+    author={Aivin V. Solatorio},
+    year={2024},
+    eprint={2402.16829},
+    archivePrefix={arXiv},
+    primaryClass={cs.LG}
+}
+```
+
+<!--
+## Glossary
+
+*Clearly define terms in order to be accessible across audiences.*
+-->
+
+<!--
+## Model Card Authors
+
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
+
+<!--
+## Model Card Contact
+
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

checkpoint-4200/config.json

@@ -0,0 +1,49 @@
+{
+  "architectures": [
+    "NewModel"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "auto_map": {
+    "AutoConfig": "Alibaba-NLP/new-impl--configuration.NewConfig",
+    "AutoModel": "Alibaba-NLP/new-impl--modeling.NewModel",
+    "AutoModelForMaskedLM": "Alibaba-NLP/new-impl--modeling.NewForMaskedLM",
+    "AutoModelForMultipleChoice": "Alibaba-NLP/new-impl--modeling.NewForMultipleChoice",
+    "AutoModelForQuestionAnswering": "Alibaba-NLP/new-impl--modeling.NewForQuestionAnswering",
+    "AutoModelForSequenceClassification": "Alibaba-NLP/new-impl--modeling.NewForSequenceClassification",
+    "AutoModelForTokenClassification": "Alibaba-NLP/new-impl--modeling.NewForTokenClassification"
+  },
+  "classifier_dropout": 0.0,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "layer_norm_type": "layer_norm",
+  "logn_attention_clip1": false,
+  "logn_attention_scale": false,
+  "max_position_embeddings": 8192,
+  "model_type": "new",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pack_qkv": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "rope",
+  "rope_scaling": {
+    "factor": 8.0,
+    "type": "ntk"
+  },
+  "rope_theta": 20000,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.2",
+  "type_vocab_size": 1,
+  "unpad_inputs": false,
+  "use_memory_efficient_attention": false,
+  "vocab_size": 250048
+}

checkpoint-4200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08c3c0eee68a8ed5930442c79d0458d0b34b4e35170a32c2ce1c96f52c462aa6
+size 15958

checkpoint-4200/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c9b2d531961e5d2e62f3f04f261cdc73b2f148f446de659eedf81e0be01d4e6
+size 988

checkpoint-4200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aae741f7abaf2255bfeb83a85dae5baa691b92cd252ccff1b44afa573600e43d
+size 1064

checkpoint-4200/special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-4200/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 8192,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizerFast",
+  "unk_token": "<unk>"
+}

checkpoint-4200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40c33010f3b5232b8f1e5876490b57675597dbc48a2cd0560f16d15d56ebb4e1
+size 5624

checkpoint-4400/config.json

@@ -0,0 +1,49 @@
+{
+  "architectures": [
+    "NewModel"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "auto_map": {
+    "AutoConfig": "Alibaba-NLP/new-impl--configuration.NewConfig",
+    "AutoModel": "Alibaba-NLP/new-impl--modeling.NewModel",
+    "AutoModelForMaskedLM": "Alibaba-NLP/new-impl--modeling.NewForMaskedLM",
+    "AutoModelForMultipleChoice": "Alibaba-NLP/new-impl--modeling.NewForMultipleChoice",
+    "AutoModelForQuestionAnswering": "Alibaba-NLP/new-impl--modeling.NewForQuestionAnswering",
+    "AutoModelForSequenceClassification": "Alibaba-NLP/new-impl--modeling.NewForSequenceClassification",
+    "AutoModelForTokenClassification": "Alibaba-NLP/new-impl--modeling.NewForTokenClassification"
+  },
+  "classifier_dropout": 0.0,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "layer_norm_type": "layer_norm",
+  "logn_attention_clip1": false,
+  "logn_attention_scale": false,
+  "max_position_embeddings": 8192,
+  "model_type": "new",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pack_qkv": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "rope",
+  "rope_scaling": {
+    "factor": 8.0,
+    "type": "ntk"
+  },
+  "rope_theta": 20000,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.2",
+  "type_vocab_size": 1,
+  "unpad_inputs": false,
+  "use_memory_efficient_attention": false,
+  "vocab_size": 250048
+}

checkpoint-4400/config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "4.1.0",
+    "transformers": "4.51.2",
+    "pytorch": "2.6.0+cu124"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

checkpoint-4400/modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

checkpoint-4400/sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 512,
+  "do_lower_case": false
+}

checkpoint-4400/special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-4400/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:883b037111086fd4dfebbbc9b7cee11e1517b5e0c0514879478661440f137085
+size 17082987

checkpoint-4400/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 8192,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizerFast",
+  "unk_token": "<unk>"
+}

checkpoint-4600/1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 768,
+  "pooling_mode_cls_token": true,
+  "pooling_mode_mean_tokens": false,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false,
+  "include_prompt": true
+}

checkpoint-4600/README.md

@@ -0,0 +1,1442 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:124788
+- loss:GISTEmbedLoss
+base_model: Alibaba-NLP/gte-multilingual-base
+widget:
+- source_sentence: 其他机械、设备和有形货物租赁服务代表
+  sentences:
+  - 其他机械和设备租赁服务工作人员
+  - 电子和电信设备及零部件物流经理
+  - 工业主厨
+- source_sentence: 公交车司机
+  sentences:
+  - 表演灯光设计师
+  - 乙烯基地板安装工
+  - 国际巴士司机
+- source_sentence: online communication manager
+  sentences:
+  - trades union official
+  - social media manager
+  - budget manager
+- source_sentence: Projektmanagerin
+  sentences:
+  - Projektmanager/Projektmanagerin
+  - Category-Manager
+  - Infanterist
+- source_sentence: Volksvertreter
+  sentences:
+  - Parlamentarier
+  - Oberbürgermeister
+  - Konsul
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+metrics:
+- cosine_accuracy@1
+- cosine_accuracy@20
+- cosine_accuracy@50
+- cosine_accuracy@100
+- cosine_accuracy@150
+- cosine_accuracy@200
+- cosine_precision@1
+- cosine_precision@20
+- cosine_precision@50
+- cosine_precision@100
+- cosine_precision@150
+- cosine_precision@200
+- cosine_recall@1
+- cosine_recall@20
+- cosine_recall@50
+- cosine_recall@100
+- cosine_recall@150
+- cosine_recall@200
+- cosine_ndcg@1
+- cosine_ndcg@20
+- cosine_ndcg@50
+- cosine_ndcg@100
+- cosine_ndcg@150
+- cosine_ndcg@200
+- cosine_mrr@1
+- cosine_mrr@20
+- cosine_mrr@50
+- cosine_mrr@100
+- cosine_mrr@150
+- cosine_mrr@200
+- cosine_map@1
+- cosine_map@20
+- cosine_map@50
+- cosine_map@100
+- cosine_map@150
+- cosine_map@200
+- cosine_map@500
+model-index:
+- name: SentenceTransformer based on Alibaba-NLP/gte-multilingual-base
+  results:
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: full en
+      type: full_en
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6571428571428571
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@20
+      value: 0.9904761904761905
+      name: Cosine Accuracy@20
+    - type: cosine_accuracy@50
+      value: 0.9904761904761905
+      name: Cosine Accuracy@50
+    - type: cosine_accuracy@100
+      value: 0.9904761904761905
+      name: Cosine Accuracy@100
+    - type: cosine_accuracy@150
+      value: 0.9904761904761905
+      name: Cosine Accuracy@150
+    - type: cosine_accuracy@200
+      value: 0.9904761904761905
+      name: Cosine Accuracy@200
+    - type: cosine_precision@1
+      value: 0.6571428571428571
+      name: Cosine Precision@1
+    - type: cosine_precision@20
+      value: 0.5166666666666666
+      name: Cosine Precision@20
+    - type: cosine_precision@50
+      value: 0.3163809523809524
+      name: Cosine Precision@50
+    - type: cosine_precision@100
+      value: 0.18933333333333335
+      name: Cosine Precision@100
+    - type: cosine_precision@150
+      value: 0.13390476190476192
+      name: Cosine Precision@150
+    - type: cosine_precision@200
+      value: 0.1043809523809524
+      name: Cosine Precision@200
+    - type: cosine_recall@1
+      value: 0.0678253733846715
+      name: Cosine Recall@1
+    - type: cosine_recall@20
+      value: 0.5460189311963579
+      name: Cosine Recall@20
+    - type: cosine_recall@50
+      value: 0.7403235838789698
+      name: Cosine Recall@50
+    - type: cosine_recall@100
+      value: 0.8464627087513951
+      name: Cosine Recall@100
+    - type: cosine_recall@150
+      value: 0.8848060278145474
+      name: Cosine Recall@150
+    - type: cosine_recall@200
+      value: 0.9111577982544093
+      name: Cosine Recall@200
+    - type: cosine_ndcg@1
+      value: 0.6571428571428571
+      name: Cosine Ndcg@1
+    - type: cosine_ndcg@20
+      value: 0.6948532664971591
+      name: Cosine Ndcg@20
+    - type: cosine_ndcg@50
+      value: 0.7153574898330466
+      name: Cosine Ndcg@50
+    - type: cosine_ndcg@100
+      value: 0.7686347737859489
+      name: Cosine Ndcg@100
+    - type: cosine_ndcg@150
+      value: 0.7861125403087321
+      name: Cosine Ndcg@150
+    - type: cosine_ndcg@200
+      value: 0.7971859934143821
+      name: Cosine Ndcg@200
+    - type: cosine_mrr@1
+      value: 0.6571428571428571
+      name: Cosine Mrr@1
+    - type: cosine_mrr@20
+      value: 0.8130158730158731
+      name: Cosine Mrr@20
+    - type: cosine_mrr@50
+      value: 0.8130158730158731
+      name: Cosine Mrr@50
+    - type: cosine_mrr@100
+      value: 0.8130158730158731
+      name: Cosine Mrr@100
+    - type: cosine_mrr@150
+      value: 0.8130158730158731
+      name: Cosine Mrr@150
+    - type: cosine_mrr@200
+      value: 0.8130158730158731
+      name: Cosine Mrr@200
+    - type: cosine_map@1
+      value: 0.6571428571428571
+      name: Cosine Map@1
+    - type: cosine_map@20
+      value: 0.5581960070033892
+      name: Cosine Map@20
+    - type: cosine_map@50
+      value: 0.547955793387211
+      name: Cosine Map@50
+    - type: cosine_map@100
+      value: 0.5806457152419001
+      name: Cosine Map@100
+    - type: cosine_map@150
+      value: 0.5882750787814468
+      name: Cosine Map@150
+    - type: cosine_map@200
+      value: 0.5920418241592634
+      name: Cosine Map@200
+    - type: cosine_map@500
+      value: 0.5960343884399482
+      name: Cosine Map@500
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: full es
+      type: full_es
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.12432432432432433
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@20
+      value: 1.0
+      name: Cosine Accuracy@20
+    - type: cosine_accuracy@50
+      value: 1.0
+      name: Cosine Accuracy@50
+    - type: cosine_accuracy@100
+      value: 1.0
+      name: Cosine Accuracy@100
+    - type: cosine_accuracy@150
+      value: 1.0
+      name: Cosine Accuracy@150
+    - type: cosine_accuracy@200
+      value: 1.0
+      name: Cosine Accuracy@200
+    - type: cosine_precision@1
+      value: 0.12432432432432433
+      name: Cosine Precision@1
+    - type: cosine_precision@20
+      value: 0.5713513513513514
+      name: Cosine Precision@20
+    - type: cosine_precision@50
+      value: 0.3888648648648649
+      name: Cosine Precision@50
+    - type: cosine_precision@100
+      value: 0.25194594594594594
+      name: Cosine Precision@100
+    - type: cosine_precision@150
+      value: 0.18998198198198196
+      name: Cosine Precision@150
+    - type: cosine_precision@200
+      value: 0.1519189189189189
+      name: Cosine Precision@200
+    - type: cosine_recall@1
+      value: 0.0036619075252531876
+      name: Cosine Recall@1
+    - type: cosine_recall@20
+      value: 0.3842833355443445
+      name: Cosine Recall@20
+    - type: cosine_recall@50
+      value: 0.5650012903557396
+      name: Cosine Recall@50
+    - type: cosine_recall@100
+      value: 0.6742574573080582
+      name: Cosine Recall@100
+    - type: cosine_recall@150
+      value: 0.7433217612578467
+      name: Cosine Recall@150
+    - type: cosine_recall@200
+      value: 0.7815387878511015
+      name: Cosine Recall@200
+    - type: cosine_ndcg@1
+      value: 0.12432432432432433
+      name: Cosine Ndcg@1
+    - type: cosine_ndcg@20
+      value: 0.6134037350149425
+      name: Cosine Ndcg@20
+    - type: cosine_ndcg@50
+      value: 0.587765249332833
+      name: Cosine Ndcg@50
+    - type: cosine_ndcg@100
+      value: 0.6145100789008344
+      name: Cosine Ndcg@100
+    - type: cosine_ndcg@150
+      value: 0.6485708474409041
+      name: Cosine Ndcg@150
+    - type: cosine_ndcg@200
+      value: 0.6674981723654128
+      name: Cosine Ndcg@200
+    - type: cosine_mrr@1
+      value: 0.12432432432432433
+      name: Cosine Mrr@1
+    - type: cosine_mrr@20
+      value: 0.5576576576576577
+      name: Cosine Mrr@20
+    - type: cosine_mrr@50
+      value: 0.5576576576576577
+      name: Cosine Mrr@50
+    - type: cosine_mrr@100
+      value: 0.5576576576576577
+      name: Cosine Mrr@100
+    - type: cosine_mrr@150
+      value: 0.5576576576576577
+      name: Cosine Mrr@150
+    - type: cosine_mrr@200
+      value: 0.5576576576576577
+      name: Cosine Mrr@200
+    - type: cosine_map@1
+      value: 0.12432432432432433
+      name: Cosine Map@1
+    - type: cosine_map@20
+      value: 0.47936111065720205
+      name: Cosine Map@20
+    - type: cosine_map@50
+      value: 0.4252592911005701
+      name: Cosine Map@50
+    - type: cosine_map@100
+      value: 0.4304825507648424
+      name: Cosine Map@100
+    - type: cosine_map@150
+      value: 0.4457575975367371
+      name: Cosine Map@150
+    - type: cosine_map@200
+      value: 0.4532981716560443
+      name: Cosine Map@200
+    - type: cosine_map@500
+      value: 0.4657478115586777
+      name: Cosine Map@500
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: full de
+      type: full_de
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.2955665024630542
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@20
+      value: 0.9704433497536946
+      name: Cosine Accuracy@20
+    - type: cosine_accuracy@50
+      value: 0.9852216748768473
+      name: Cosine Accuracy@50
+    - type: cosine_accuracy@100
+      value: 0.9852216748768473
+      name: Cosine Accuracy@100
+    - type: cosine_accuracy@150
+      value: 0.9901477832512315
+      name: Cosine Accuracy@150
+    - type: cosine_accuracy@200
+      value: 0.9901477832512315
+      name: Cosine Accuracy@200
+    - type: cosine_precision@1
+      value: 0.2955665024630542
+      name: Cosine Precision@1
+    - type: cosine_precision@20
+      value: 0.5103448275862069
+      name: Cosine Precision@20
+    - type: cosine_precision@50
+      value: 0.3654187192118227
+      name: Cosine Precision@50
+    - type: cosine_precision@100
+      value: 0.24152709359605912
+      name: Cosine Precision@100
+    - type: cosine_precision@150
+      value: 0.18039408866995077
+      name: Cosine Precision@150
+    - type: cosine_precision@200
+      value: 0.1444088669950739
+      name: Cosine Precision@200
+    - type: cosine_recall@1
+      value: 0.01108543831680986
+      name: Cosine Recall@1
+    - type: cosine_recall@20
+      value: 0.3232480342404406
+      name: Cosine Recall@20
+    - type: cosine_recall@50
+      value: 0.5030915016290886
+      name: Cosine Recall@50
+    - type: cosine_recall@100
+      value: 0.6249715272880884
+      name: Cosine Recall@100
+    - type: cosine_recall@150
+      value: 0.6832865603922703
+      name: Cosine Recall@150
+    - type: cosine_recall@200
+      value: 0.7220918134235578
+      name: Cosine Recall@200
+    - type: cosine_ndcg@1
+      value: 0.2955665024630542
+      name: Cosine Ndcg@1
+    - type: cosine_ndcg@20
+      value: 0.5410295152452983
+      name: Cosine Ndcg@20
+    - type: cosine_ndcg@50
+      value: 0.5272863852084945
+      name: Cosine Ndcg@50
+    - type: cosine_ndcg@100
+      value: 0.5583782732060053
+      name: Cosine Ndcg@100
+    - type: cosine_ndcg@150
+      value: 0.588398956427303
+      name: Cosine Ndcg@150
+    - type: cosine_ndcg@200
+      value: 0.6072311612102843
+      name: Cosine Ndcg@200
+    - type: cosine_mrr@1
+      value: 0.2955665024630542
+      name: Cosine Mrr@1
+    - type: cosine_mrr@20
+      value: 0.5115567241030488
+      name: Cosine Mrr@20
+    - type: cosine_mrr@50
+      value: 0.5120878378565168
+      name: Cosine Mrr@50
+    - type: cosine_mrr@100
+      value: 0.5120878378565168
+      name: Cosine Mrr@100
+    - type: cosine_mrr@150
+      value: 0.5121352042831936
+      name: Cosine Mrr@150
+    - type: cosine_mrr@200
+      value: 0.5121352042831936
+      name: Cosine Mrr@200
+    - type: cosine_map@1
+      value: 0.2955665024630542
+      name: Cosine Map@1
+    - type: cosine_map@20
+      value: 0.4027772467386738
+      name: Cosine Map@20
+    - type: cosine_map@50
+      value: 0.3591245737395942
+      name: Cosine Map@50
+    - type: cosine_map@100
+      value: 0.3636915129209065
+      name: Cosine Map@100
+    - type: cosine_map@150
+      value: 0.3780389811429104
+      name: Cosine Map@150
+    - type: cosine_map@200
+      value: 0.3849915747167181
+      name: Cosine Map@200
+    - type: cosine_map@500
+      value: 0.3979586734666635
+      name: Cosine Map@500
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: full zh
+      type: full_zh
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6601941747572816
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@20
+      value: 0.9805825242718447
+      name: Cosine Accuracy@20
+    - type: cosine_accuracy@50
+      value: 0.9902912621359223
+      name: Cosine Accuracy@50
+    - type: cosine_accuracy@100
+      value: 0.9902912621359223
+      name: Cosine Accuracy@100
+    - type: cosine_accuracy@150
+      value: 0.9902912621359223
+      name: Cosine Accuracy@150
+    - type: cosine_accuracy@200
+      value: 0.9902912621359223
+      name: Cosine Accuracy@200
+    - type: cosine_precision@1
+      value: 0.6601941747572816
+      name: Cosine Precision@1
+    - type: cosine_precision@20
+      value: 0.4805825242718447
+      name: Cosine Precision@20
+    - type: cosine_precision@50
+      value: 0.2900970873786408
+      name: Cosine Precision@50
+    - type: cosine_precision@100
+      value: 0.17592233009708735
+      name: Cosine Precision@100
+    - type: cosine_precision@150
+      value: 0.12601941747572815
+      name: Cosine Precision@150
+    - type: cosine_precision@200
+      value: 0.09815533980582528
+      name: Cosine Precision@200
+    - type: cosine_recall@1
+      value: 0.06151358631979527
+      name: Cosine Recall@1
+    - type: cosine_recall@20
+      value: 0.5137714811644284
+      name: Cosine Recall@20
+    - type: cosine_recall@50
+      value: 0.6926011095977929
+      name: Cosine Recall@50
+    - type: cosine_recall@100
+      value: 0.8015658686430839
+      name: Cosine Recall@100
+    - type: cosine_recall@150
+      value: 0.8498529142376811
+      name: Cosine Recall@150
+    - type: cosine_recall@200
+      value: 0.8756860745010276
+      name: Cosine Recall@200
+    - type: cosine_ndcg@1
+      value: 0.6601941747572816
+      name: Cosine Ndcg@1
+    - type: cosine_ndcg@20
+      value: 0.6561470810556217
+      name: Cosine Ndcg@20
+    - type: cosine_ndcg@50
+      value: 0.6713912878037265
+      name: Cosine Ndcg@50
+    - type: cosine_ndcg@100
+      value: 0.7242859634217003
+      name: Cosine Ndcg@100
+    - type: cosine_ndcg@150
+      value: 0.7450276543061775
+      name: Cosine Ndcg@150
+    - type: cosine_ndcg@200
+      value: 0.7555798172662749
+      name: Cosine Ndcg@200
+    - type: cosine_mrr@1
+      value: 0.6601941747572816
+      name: Cosine Mrr@1
+    - type: cosine_mrr@20
+      value: 0.8042071197411004
+      name: Cosine Mrr@20
+    - type: cosine_mrr@50
+      value: 0.8045805327358726
+      name: Cosine Mrr@50
+    - type: cosine_mrr@100
+      value: 0.8045805327358726
+      name: Cosine Mrr@100
+    - type: cosine_mrr@150
+      value: 0.8045805327358726
+      name: Cosine Mrr@150
+    - type: cosine_mrr@200
+      value: 0.8045805327358726
+      name: Cosine Mrr@200
+    - type: cosine_map@1
+      value: 0.6601941747572816
+      name: Cosine Map@1
+    - type: cosine_map@20
+      value: 0.5106521768718877
+      name: Cosine Map@20
+    - type: cosine_map@50
+      value: 0.4936260792000732
+      name: Cosine Map@50
+    - type: cosine_map@100
+      value: 0.5228282305505247
+      name: Cosine Map@100
+    - type: cosine_map@150
+      value: 0.5309790629236998
+      name: Cosine Map@150
+    - type: cosine_map@200
+      value: 0.5343942751177704
+      name: Cosine Map@200
+    - type: cosine_map@500
+      value: 0.5396780030153469
+      name: Cosine Map@500
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: mix es
+      type: mix_es
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.7243889755590224
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@20
+      value: 0.9594383775351014
+      name: Cosine Accuracy@20
+    - type: cosine_accuracy@50
+      value: 0.9791991679667187
+      name: Cosine Accuracy@50
+    - type: cosine_accuracy@100
+      value: 0.9927197087883516
+      name: Cosine Accuracy@100
+    - type: cosine_accuracy@150
+      value: 0.9963598543941757
+      name: Cosine Accuracy@150
+    - type: cosine_accuracy@200
+      value: 0.9973998959958398
+      name: Cosine Accuracy@200
+    - type: cosine_precision@1
+      value: 0.7243889755590224
+      name: Cosine Precision@1
+    - type: cosine_precision@20
+      value: 0.12423296931877274
+      name: Cosine Precision@20
+    - type: cosine_precision@50
+      value: 0.05144045761830475
+      name: Cosine Precision@50
+    - type: cosine_precision@100
+      value: 0.026235049401976088
+      name: Cosine Precision@100
+    - type: cosine_precision@150
+      value: 0.017628705148205925
+      name: Cosine Precision@150
+    - type: cosine_precision@200
+      value: 0.013283931357254294
+      name: Cosine Precision@200
+    - type: cosine_recall@1
+      value: 0.2801228239605774
+      name: Cosine Recall@1
+    - type: cosine_recall@20
+      value: 0.9177327093083724
+      name: Cosine Recall@20
+    - type: cosine_recall@50
+      value: 0.9498439937597504
+      name: Cosine Recall@50
+    - type: cosine_recall@100
+      value: 0.9693967758710348
+      name: Cosine Recall@100
+    - type: cosine_recall@150
+      value: 0.9772057548968625
+      name: Cosine Recall@150
+    - type: cosine_recall@200
+      value: 0.9819032761310452
+      name: Cosine Recall@200
+    - type: cosine_ndcg@1
+      value: 0.7243889755590224
+      name: Cosine Ndcg@1
+    - type: cosine_ndcg@20
+      value: 0.8035653524093836
+      name: Cosine Ndcg@20
+    - type: cosine_ndcg@50
+      value: 0.8123465374976416
+      name: Cosine Ndcg@50
+    - type: cosine_ndcg@100
+      value: 0.816619783760099
+      name: Cosine Ndcg@100
+    - type: cosine_ndcg@150
+      value: 0.8181288168343755
+      name: Cosine Ndcg@150
+    - type: cosine_ndcg@200
+      value: 0.8189742580500373
+      name: Cosine Ndcg@200
+    - type: cosine_mrr@1
+      value: 0.7243889755590224
+      name: Cosine Mrr@1
+    - type: cosine_mrr@20
+      value: 0.7950733254581356
+      name: Cosine Mrr@20
+    - type: cosine_mrr@50
+      value: 0.7957037061937158
+      name: Cosine Mrr@50
+    - type: cosine_mrr@100
+      value: 0.7959106624394904
+      name: Cosine Mrr@100
+    - type: cosine_mrr@150
+      value: 0.795941995568463
+      name: Cosine Mrr@150
+    - type: cosine_mrr@200
+      value: 0.7959480612399141
+      name: Cosine Mrr@200
+    - type: cosine_map@1
+      value: 0.7243889755590224
+      name: Cosine Map@1
+    - type: cosine_map@20
+      value: 0.7344976284540953
+      name: Cosine Map@20
+    - type: cosine_map@50
+      value: 0.7369058419409787
+      name: Cosine Map@50
+    - type: cosine_map@100
+      value: 0.7374765660485233
+      name: Cosine Map@100
+    - type: cosine_map@150
+      value: 0.7376131540231733
+      name: Cosine Map@150
+    - type: cosine_map@200
+      value: 0.7376752620519383
+      name: Cosine Map@200
+    - type: cosine_map@500
+      value: 0.7377852907056718
+      name: Cosine Map@500
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: mix de
+      type: mix_de
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6687467498699948
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@20
+      value: 0.9495579823192928
+      name: Cosine Accuracy@20
+    - type: cosine_accuracy@50
+      value: 0.9776391055642226
+      name: Cosine Accuracy@50
+    - type: cosine_accuracy@100
+      value: 0.9864794591783671
+      name: Cosine Accuracy@100
+    - type: cosine_accuracy@150
+      value: 0.9932397295891836
+      name: Cosine Accuracy@150
+    - type: cosine_accuracy@200
+      value: 0.9947997919916797
+      name: Cosine Accuracy@200
+    - type: cosine_precision@1
+      value: 0.6687467498699948
+      name: Cosine Precision@1
+    - type: cosine_precision@20
+      value: 0.1251430057202288
+      name: Cosine Precision@20
+    - type: cosine_precision@50
+      value: 0.052282891315652634
+      name: Cosine Precision@50
+    - type: cosine_precision@100
+      value: 0.026723868954758197
+      name: Cosine Precision@100
+    - type: cosine_precision@150
+      value: 0.01799965331946611
+      name: Cosine Precision@150
+    - type: cosine_precision@200
+      value: 0.013541341653666149
+      name: Cosine Precision@200
+    - type: cosine_recall@1
+      value: 0.2518374068296065
+      name: Cosine Recall@1
+    - type: cosine_recall@20
+      value: 0.9091090310279077
+      name: Cosine Recall@20
+    - type: cosine_recall@50
+      value: 0.9482405962905183
+      name: Cosine Recall@50
+    - type: cosine_recall@100
+      value: 0.968278731149246
+      name: Cosine Recall@100
+    - type: cosine_recall@150
+      value: 0.9781591263650546
+      name: Cosine Recall@150
+    - type: cosine_recall@200
+      value: 0.9810192407696308
+      name: Cosine Recall@200
+    - type: cosine_ndcg@1
+      value: 0.6687467498699948
+      name: Cosine Ndcg@1
+    - type: cosine_ndcg@20
+      value: 0.7729181248399849
+      name: Cosine Ndcg@20
+    - type: cosine_ndcg@50
+      value: 0.7838354251194414
+      name: Cosine Ndcg@50
+    - type: cosine_ndcg@100
+      value: 0.78838397650382
+      name: Cosine Ndcg@100
+    - type: cosine_ndcg@150
+      value: 0.7903404232459181
+      name: Cosine Ndcg@150
+    - type: cosine_ndcg@200
+      value: 0.7908776550064243
+      name: Cosine Ndcg@200
+    - type: cosine_mrr@1
+      value: 0.6687467498699948
+      name: Cosine Mrr@1
+    - type: cosine_mrr@20
+      value: 0.7511103493630668
+      name: Cosine Mrr@20
+    - type: cosine_mrr@50
+      value: 0.7520644853972484
+      name: Cosine Mrr@50
+    - type: cosine_mrr@100
+      value: 0.75218787562777
+      name: Cosine Mrr@100
+    - type: cosine_mrr@150
+      value: 0.7522459565052304
+      name: Cosine Mrr@150
+    - type: cosine_mrr@200
+      value: 0.7522551943857011
+      name: Cosine Mrr@200
+    - type: cosine_map@1
+      value: 0.6687467498699948
+      name: Cosine Map@1
+    - type: cosine_map@20
+      value: 0.6960508888943099
+      name: Cosine Map@20
+    - type: cosine_map@50
+      value: 0.698910694860312
+      name: Cosine Map@50
+    - type: cosine_map@100
+      value: 0.699611558838961
+      name: Cosine Map@100
+    - type: cosine_map@150
+      value: 0.6997846710668125
+      name: Cosine Map@150
+    - type: cosine_map@200
+      value: 0.6998222199397084
+      name: Cosine Map@200
+    - type: cosine_map@500
+      value: 0.6999210147339264
+      name: Cosine Map@500
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: mix zh
+      type: mix_zh
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.19240769630785232
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@20
+      value: 1.0
+      name: Cosine Accuracy@20
+    - type: cosine_accuracy@50
+      value: 1.0
+      name: Cosine Accuracy@50
+    - type: cosine_accuracy@100
+      value: 1.0
+      name: Cosine Accuracy@100
+    - type: cosine_accuracy@150
+      value: 1.0
+      name: Cosine Accuracy@150
+    - type: cosine_accuracy@200
+      value: 1.0
+      name: Cosine Accuracy@200
+    - type: cosine_precision@1
+      value: 0.19240769630785232
+      name: Cosine Precision@1
+    - type: cosine_precision@20
+      value: 0.15439417576703063
+      name: Cosine Precision@20
+    - type: cosine_precision@50
+      value: 0.0617576703068123
+      name: Cosine Precision@50
+    - type: cosine_precision@100
+      value: 0.03087883515340615
+      name: Cosine Precision@100
+    - type: cosine_precision@150
+      value: 0.020585890102270757
+      name: Cosine Precision@150
+    - type: cosine_precision@200
+      value: 0.015439417576703075
+      name: Cosine Precision@200
+    - type: cosine_recall@1
+      value: 0.06189980932570636
+      name: Cosine Recall@1
+    - type: cosine_recall@20
+      value: 1.0
+      name: Cosine Recall@20
+    - type: cosine_recall@50
+      value: 1.0
+      name: Cosine Recall@50
+    - type: cosine_recall@100
+      value: 1.0
+      name: Cosine Recall@100
+    - type: cosine_recall@150
+      value: 1.0
+      name: Cosine Recall@150
+    - type: cosine_recall@200
+      value: 1.0
+      name: Cosine Recall@200
+    - type: cosine_ndcg@1
+      value: 0.19240769630785232
+      name: Cosine Ndcg@1
+    - type: cosine_ndcg@20
+      value: 0.5477973908226992
+      name: Cosine Ndcg@20
+    - type: cosine_ndcg@50
+      value: 0.5477973908226992
+      name: Cosine Ndcg@50
+    - type: cosine_ndcg@100
+      value: 0.5477973908226992
+      name: Cosine Ndcg@100
+    - type: cosine_ndcg@150
+      value: 0.5477973908226992
+      name: Cosine Ndcg@150
+    - type: cosine_ndcg@200
+      value: 0.5477973908226992
+      name: Cosine Ndcg@200
+    - type: cosine_mrr@1
+      value: 0.19240769630785232
+      name: Cosine Mrr@1
+    - type: cosine_mrr@20
+      value: 0.41054733531332677
+      name: Cosine Mrr@20
+    - type: cosine_mrr@50
+      value: 0.41054733531332677
+      name: Cosine Mrr@50
+    - type: cosine_mrr@100
+      value: 0.41054733531332677
+      name: Cosine Mrr@100
+    - type: cosine_mrr@150
+      value: 0.41054733531332677
+      name: Cosine Mrr@150
+    - type: cosine_mrr@200
+      value: 0.41054733531332677
+      name: Cosine Mrr@200
+    - type: cosine_map@1
+      value: 0.19240769630785232
+      name: Cosine Map@1
+    - type: cosine_map@20
+      value: 0.33014621049351006
+      name: Cosine Map@20
+    - type: cosine_map@50
+      value: 0.33014621049351006
+      name: Cosine Map@50
+    - type: cosine_map@100
+      value: 0.33014621049351006
+      name: Cosine Map@100
+    - type: cosine_map@150
+      value: 0.33014621049351006
+      name: Cosine Map@150
+    - type: cosine_map@200
+      value: 0.33014621049351006
+      name: Cosine Map@200
+    - type: cosine_map@500
+      value: 0.33014621049351006
+      name: Cosine Map@500
+---
+
+# SentenceTransformer based on Alibaba-NLP/gte-multilingual-base
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [Alibaba-NLP/gte-multilingual-base](https://huggingface.co/Alibaba-NLP/gte-multilingual-base) on the full_en, full_de, full_es, full_zh and mix datasets. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
+
+## Model Details
+
+### Model Description
+- **Model Type:** Sentence Transformer
+- **Base model:** [Alibaba-NLP/gte-multilingual-base](https://huggingface.co/Alibaba-NLP/gte-multilingual-base) <!-- at revision 9fdd4ee8bba0e2808a34e0e739576f6740d2b225 -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 768 dimensions
+- **Similarity Function:** Cosine Similarity
+- **Training Datasets:**
+    - full_en
+    - full_de
+    - full_es
+    - full_zh
+    - mix
+<!-- - **Language:** Unknown -->
+<!-- - **License:** Unknown -->
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
+- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
+
+### Full Model Architecture
+
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: NewModel 
+  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+  (2): Normalize()
+)
+```
+
+## Usage
+
+### Direct Usage (Sentence Transformers)
+
+First install the Sentence Transformers library:
+
+```bash
+pip install -U sentence-transformers
+```
+
+Then you can load this model and run inference.
+```python
+from sentence_transformers import SentenceTransformer
+
+# Download from the 🤗 Hub
+model = SentenceTransformer("sentence_transformers_model_id")
+# Run inference
+sentences = [
+    'Volksvertreter',
+    'Parlamentarier',
+    'Oberbürgermeister',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 768]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities.shape)
+# [3, 3]
+```
+
+<!--
+### Direct Usage (Transformers)
+
+<details><summary>Click to see the direct usage in Transformers</summary>
+
+</details>
+-->
+
+<!--
+### Downstream Usage (Sentence Transformers)
+
+You can finetune this model on your own dataset.
+
+<details><summary>Click to expand</summary>
+
+</details>
+-->
+
+<!--
+### Out-of-Scope Use
+
+*List how the model may foreseeably be misused and address what users ought not to do with the model.*
+-->
+
+## Evaluation
+
+### Metrics
+
+#### Information Retrieval
+
+* Datasets: `full_en`, `full_es`, `full_de`, `full_zh`, `mix_es`, `mix_de` and `mix_zh`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric               | full_en    | full_es    | full_de    | full_zh    | mix_es    | mix_de     | mix_zh     |
+|:---------------------|:-----------|:-----------|:-----------|:-----------|:----------|:-----------|:-----------|
+| cosine_accuracy@1    | 0.6571     | 0.1243     | 0.2956     | 0.6602     | 0.7244    | 0.6687     | 0.1924     |
+| cosine_accuracy@20   | 0.9905     | 1.0        | 0.9704     | 0.9806     | 0.9594    | 0.9496     | 1.0        |
+| cosine_accuracy@50   | 0.9905     | 1.0        | 0.9852     | 0.9903     | 0.9792    | 0.9776     | 1.0        |
+| cosine_accuracy@100  | 0.9905     | 1.0        | 0.9852     | 0.9903     | 0.9927    | 0.9865     | 1.0        |
+| cosine_accuracy@150  | 0.9905     | 1.0        | 0.9901     | 0.9903     | 0.9964    | 0.9932     | 1.0        |
+| cosine_accuracy@200  | 0.9905     | 1.0        | 0.9901     | 0.9903     | 0.9974    | 0.9948     | 1.0        |
+| cosine_precision@1   | 0.6571     | 0.1243     | 0.2956     | 0.6602     | 0.7244    | 0.6687     | 0.1924     |
+| cosine_precision@20  | 0.5167     | 0.5714     | 0.5103     | 0.4806     | 0.1242    | 0.1251     | 0.1544     |
+| cosine_precision@50  | 0.3164     | 0.3889     | 0.3654     | 0.2901     | 0.0514    | 0.0523     | 0.0618     |
+| cosine_precision@100 | 0.1893     | 0.2519     | 0.2415     | 0.1759     | 0.0262    | 0.0267     | 0.0309     |
+| cosine_precision@150 | 0.1339     | 0.19       | 0.1804     | 0.126      | 0.0176    | 0.018      | 0.0206     |
+| cosine_precision@200 | 0.1044     | 0.1519     | 0.1444     | 0.0982     | 0.0133    | 0.0135     | 0.0154     |
+| cosine_recall@1      | 0.0678     | 0.0037     | 0.0111     | 0.0615     | 0.2801    | 0.2518     | 0.0619     |
+| cosine_recall@20     | 0.546      | 0.3843     | 0.3232     | 0.5138     | 0.9177    | 0.9091     | 1.0        |
+| cosine_recall@50     | 0.7403     | 0.565      | 0.5031     | 0.6926     | 0.9498    | 0.9482     | 1.0        |
+| cosine_recall@100    | 0.8465     | 0.6743     | 0.625      | 0.8016     | 0.9694    | 0.9683     | 1.0        |
+| cosine_recall@150    | 0.8848     | 0.7433     | 0.6833     | 0.8499     | 0.9772    | 0.9782     | 1.0        |
+| cosine_recall@200    | 0.9112     | 0.7815     | 0.7221     | 0.8757     | 0.9819    | 0.981      | 1.0        |
+| cosine_ndcg@1        | 0.6571     | 0.1243     | 0.2956     | 0.6602     | 0.7244    | 0.6687     | 0.1924     |
+| cosine_ndcg@20       | 0.6949     | 0.6134     | 0.541      | 0.6561     | 0.8036    | 0.7729     | 0.5478     |
+| cosine_ndcg@50       | 0.7154     | 0.5878     | 0.5273     | 0.6714     | 0.8123    | 0.7838     | 0.5478     |
+| cosine_ndcg@100      | 0.7686     | 0.6145     | 0.5584     | 0.7243     | 0.8166    | 0.7884     | 0.5478     |
+| cosine_ndcg@150      | 0.7861     | 0.6486     | 0.5884     | 0.745      | 0.8181    | 0.7903     | 0.5478     |
+| **cosine_ndcg@200**  | **0.7972** | **0.6675** | **0.6072** | **0.7556** | **0.819** | **0.7909** | **0.5478** |
+| cosine_mrr@1         | 0.6571     | 0.1243     | 0.2956     | 0.6602     | 0.7244    | 0.6687     | 0.1924     |
+| cosine_mrr@20        | 0.813      | 0.5577     | 0.5116     | 0.8042     | 0.7951    | 0.7511     | 0.4105     |
+| cosine_mrr@50        | 0.813      | 0.5577     | 0.5121     | 0.8046     | 0.7957    | 0.7521     | 0.4105     |
+| cosine_mrr@100       | 0.813      | 0.5577     | 0.5121     | 0.8046     | 0.7959    | 0.7522     | 0.4105     |
+| cosine_mrr@150       | 0.813      | 0.5577     | 0.5121     | 0.8046     | 0.7959    | 0.7522     | 0.4105     |
+| cosine_mrr@200       | 0.813      | 0.5577     | 0.5121     | 0.8046     | 0.7959    | 0.7523     | 0.4105     |
+| cosine_map@1         | 0.6571     | 0.1243     | 0.2956     | 0.6602     | 0.7244    | 0.6687     | 0.1924     |
+| cosine_map@20        | 0.5582     | 0.4794     | 0.4028     | 0.5107     | 0.7345    | 0.6961     | 0.3301     |
+| cosine_map@50        | 0.548      | 0.4253     | 0.3591     | 0.4936     | 0.7369    | 0.6989     | 0.3301     |
+| cosine_map@100       | 0.5806     | 0.4305     | 0.3637     | 0.5228     | 0.7375    | 0.6996     | 0.3301     |
+| cosine_map@150       | 0.5883     | 0.4458     | 0.378      | 0.531      | 0.7376    | 0.6998     | 0.3301     |
+| cosine_map@200       | 0.592      | 0.4533     | 0.385      | 0.5344     | 0.7377    | 0.6998     | 0.3301     |
+| cosine_map@500       | 0.596      | 0.4657     | 0.398      | 0.5397     | 0.7378    | 0.6999     | 0.3301     |
+
+<!--
+## Bias, Risks and Limitations
+
+*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
+-->
+
+<!--
+### Recommendations
+
+*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
+-->
+
+## Training Details
+
+### Training Datasets
+<details><summary>full_en</summary>
+
+#### full_en
+
+* Dataset: full_en
+* Size: 28,880 training samples
+* Columns: <code>anchor</code> and <code>positive</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | anchor                                                                           | positive                                                                         |
+  |:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|
+  | type    | string                                                                           | string                                                                           |
+  | details | <ul><li>min: 3 tokens</li><li>mean: 5.68 tokens</li><li>max: 11 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 5.76 tokens</li><li>max: 12 tokens</li></ul> |
+* Samples:
+  | anchor                                   | positive                                 |
+  |:-----------------------------------------|:-----------------------------------------|
+  | <code>air commodore</code>               | <code>flight lieutenant</code>           |
+  | <code>command and control officer</code> | <code>flight officer</code>              |
+  | <code>air commodore</code>               | <code>command and control officer</code> |
+* Loss: [<code>GISTEmbedLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#gistembedloss) with these parameters:
+  ```json
+  {'guide': SentenceTransformer(
+    (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel 
+    (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+    (2): Normalize()
+  ), 'temperature': 0.01, 'margin_strategy': 'absolute', 'margin': 0.0}
+  ```
+</details>
+<details><summary>full_de</summary>
+
+#### full_de
+
+* Dataset: full_de
+* Size: 23,023 training samples
+* Columns: <code>anchor</code> and <code>positive</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | anchor                                                                           | positive                                                                         |
+  |:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|
+  | type    | string                                                                           | string                                                                           |
+  | details | <ul><li>min: 3 tokens</li><li>mean: 7.99 tokens</li><li>max: 30 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 8.19 tokens</li><li>max: 30 tokens</li></ul> |
+* Samples:
+  | anchor                            | positive                                             |
+  |:----------------------------------|:-----------------------------------------------------|
+  | <code>Staffelkommandantin</code>  | <code>Kommodore</code>                               |
+  | <code>Luftwaffenoffizierin</code> | <code>Luftwaffenoffizier/Luftwaffenoffizierin</code> |
+  | <code>Staffelkommandantin</code>  | <code>Luftwaffenoffizierin</code>                    |
+* Loss: [<code>GISTEmbedLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#gistembedloss) with these parameters:
+  ```json
+  {'guide': SentenceTransformer(
+    (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel 
+    (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+    (2): Normalize()
+  ), 'temperature': 0.01, 'margin_strategy': 'absolute', 'margin': 0.0}
+  ```
+</details>
+<details><summary>full_es</summary>
+
+#### full_es
+
+* Dataset: full_es
+* Size: 20,724 training samples
+* Columns: <code>anchor</code> and <code>positive</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | anchor                                                                           | positive                                                                         |
+  |:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|
+  | type    | string                                                                           | string                                                                           |
+  | details | <ul><li>min: 3 tokens</li><li>mean: 9.13 tokens</li><li>max: 32 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 8.84 tokens</li><li>max: 32 tokens</li></ul> |
+* Samples:
+  | anchor                              | positive                                   |
+  |:------------------------------------|:-------------------------------------------|
+  | <code>jefe de escuadrón</code>      | <code>instructor</code>                    |
+  | <code>comandante de aeronave</code> | <code>instructor de simulador</code>       |
+  | <code>instructor</code>             | <code>oficial del Ejército del Aire</code> |
+* Loss: [<code>GISTEmbedLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#gistembedloss) with these parameters:
+  ```json
+  {'guide': SentenceTransformer(
+    (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel 
+    (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+    (2): Normalize()
+  ), 'temperature': 0.01, 'margin_strategy': 'absolute', 'margin': 0.0}
+  ```
+</details>
+<details><summary>full_zh</summary>
+
+#### full_zh
+
+* Dataset: full_zh
+* Size: 30,401 training samples
+* Columns: <code>anchor</code> and <code>positive</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | anchor                                                                           | positive                                                                         |
+  |:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|
+  | type    | string                                                                           | string                                                                           |
+  | details | <ul><li>min: 5 tokens</li><li>mean: 7.15 tokens</li><li>max: 14 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 7.46 tokens</li><li>max: 21 tokens</li></ul> |
+* Samples:
+  | anchor            | positive             |
+  |:------------------|:---------------------|
+  | <code>技术总监</code> | <code>技术和运营总监</code> |
+  | <code>技术总监</code> | <code>技术主管</code>    |
+  | <code>技术总监</code> | <code>技术艺术总监</code>  |
+* Loss: [<code>GISTEmbedLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#gistembedloss) with these parameters:
+  ```json
+  {'guide': SentenceTransformer(
+    (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel 
+    (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+    (2): Normalize()
+  ), 'temperature': 0.01, 'margin_strategy': 'absolute', 'margin': 0.0}
+  ```
+</details>
+<details><summary>mix</summary>
+
+#### mix
+
+* Dataset: mix
+* Size: 21,760 training samples
+* Columns: <code>anchor</code> and <code>positive</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | anchor                                                                           | positive                                                                         |
+  |:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|
+  | type    | string                                                                           | string                                                                           |
+  | details | <ul><li>min: 2 tokens</li><li>mean: 6.71 tokens</li><li>max: 19 tokens</li></ul> | <ul><li>min: 2 tokens</li><li>mean: 7.69 tokens</li><li>max: 19 tokens</li></ul> |
+* Samples:
+  | anchor                                    | positive                                                        |
+  |:------------------------------------------|:----------------------------------------------------------------|
+  | <code>technical manager</code>            | <code>Technischer Direktor für Bühne, Film und Fernsehen</code> |
+  | <code>head of technical</code>            | <code>directora técnica</code>                                  |
+  | <code>head of technical department</code> | <code>技术艺术总监</code>                                             |
+* Loss: [<code>GISTEmbedLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#gistembedloss) with these parameters:
+  ```json
+  {'guide': SentenceTransformer(
+    (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel 
+    (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+    (2): Normalize()
+  ), 'temperature': 0.01, 'margin_strategy': 'absolute', 'margin': 0.0}
+  ```
+</details>
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 64
+- `per_device_eval_batch_size`: 128
+- `gradient_accumulation_steps`: 2
+- `num_train_epochs`: 5
+- `warmup_ratio`: 0.05
+- `log_on_each_node`: False
+- `fp16`: True
+- `dataloader_num_workers`: 4
+- `ddp_find_unused_parameters`: True
+- `batch_sampler`: no_duplicates
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: steps
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 64
+- `per_device_eval_batch_size`: 128
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 2
+- `eval_accumulation_steps`: None
+- `torch_empty_cache_steps`: None
+- `learning_rate`: 5e-05
+- `weight_decay`: 0.0
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1.0
+- `num_train_epochs`: 5
+- `max_steps`: -1
+- `lr_scheduler_type`: linear
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.05
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: False
+- `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`: 4
+- `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}
+- `tp_size`: 0
+- `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}
+- `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`: True
+- `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
+- `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`: False
+- `torch_compile_backend`: None
+- `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`: False
+- `use_liger_kernel`: False
+- `eval_use_gather_object`: False
+- `average_tokens_across_devices`: False
+- `prompts`: None
+- `batch_sampler`: no_duplicates
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch  | Step | Training Loss | full_en_cosine_ndcg@200 | full_es_cosine_ndcg@200 | full_de_cosine_ndcg@200 | full_zh_cosine_ndcg@200 | mix_es_cosine_ndcg@200 | mix_de_cosine_ndcg@200 | mix_zh_cosine_ndcg@200 |
+|:------:|:----:|:-------------:|:-----------------------:|:-----------------------:|:-----------------------:|:-----------------------:|:----------------------:|:----------------------:|:----------------------:|
+| -1     | -1   | -             | 0.7447                  | 0.6125                  | 0.5378                  | 0.7240                  | 0.7029                 | 0.6345                 | 0.5531                 |
+| 0.0010 | 1    | 3.4866        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 0.1027 | 100  | 2.5431        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 0.2053 | 200  | 1.4536        | 0.7993                  | 0.6633                  | 0.5974                  | 0.7642                  | 0.7567                 | 0.7011                 | 0.5498                 |
+| 0.3080 | 300  | 1.1018        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 0.4107 | 400  | 0.9184        | 0.7925                  | 0.6586                  | 0.6058                  | 0.7587                  | 0.7749                 | 0.7278                 | 0.5486                 |
+| 0.5133 | 500  | 0.8973        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 0.6160 | 600  | 0.7309        | 0.7951                  | 0.6671                  | 0.6096                  | 0.7708                  | 0.7793                 | 0.7339                 | 0.5525                 |
+| 0.7187 | 700  | 0.7297        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 0.8214 | 800  | 0.7281        | 0.7929                  | 0.6711                  | 0.6088                  | 0.7645                  | 0.7899                 | 0.7444                 | 0.5479                 |
+| 0.9240 | 900  | 0.6607        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 1.0267 | 1000 | 0.6075        | 0.7915                  | 0.6659                  | 0.6088                  | 0.7665                  | 0.7968                 | 0.7588                 | 0.5482                 |
+| 1.1294 | 1100 | 0.4553        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 1.2320 | 1200 | 0.4775        | 0.7979                  | 0.6696                  | 0.6033                  | 0.7669                  | 0.7959                 | 0.7624                 | 0.5484                 |
+| 1.3347 | 1300 | 0.4838        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 1.4374 | 1400 | 0.4912        | 0.7973                  | 0.6757                  | 0.6112                  | 0.7656                  | 0.7978                 | 0.7650                 | 0.5487                 |
+| 1.5400 | 1500 | 0.4732        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 1.6427 | 1600 | 0.5269        | 0.8031                  | 0.6723                  | 0.6108                  | 0.7654                  | 0.8008                 | 0.7660                 | 0.5492                 |
+| 1.7454 | 1700 | 0.4822        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 1.8480 | 1800 | 0.5072        | 0.7962                  | 0.6668                  | 0.6051                  | 0.7592                  | 0.8001                 | 0.7714                 | 0.5486                 |
+| 1.9507 | 1900 | 0.4709        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 2.0544 | 2000 | 0.3772        | 0.7940                  | 0.6647                  | 0.6037                  | 0.7579                  | 0.8064                 | 0.7732                 | 0.5479                 |
+| 2.1571 | 2100 | 0.3982        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 2.2598 | 2200 | 0.3073        | 0.7969                  | 0.6652                  | 0.6005                  | 0.7625                  | 0.8054                 | 0.7734                 | 0.5493                 |
+| 2.3624 | 2300 | 0.383         | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 2.4651 | 2400 | 0.3687        | 0.7925                  | 0.6690                  | 0.5987                  | 0.7583                  | 0.8081                 | 0.7735                 | 0.5477                 |
+| 2.5678 | 2500 | 0.3472        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 2.6704 | 2600 | 0.3557        | 0.7956                  | 0.6758                  | 0.6019                  | 0.7659                  | 0.8082                 | 0.7767                 | 0.5491                 |
+| 2.7731 | 2700 | 0.3527        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 2.8758 | 2800 | 0.3446        | 0.7945                  | 0.6719                  | 0.6020                  | 0.7616                  | 0.8124                 | 0.7818                 | 0.5496                 |
+| 2.9784 | 2900 | 0.3566        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 3.0821 | 3000 | 0.3252        | 0.7948                  | 0.6682                  | 0.6025                  | 0.7617                  | 0.8152                 | 0.7848                 | 0.5516                 |
+| 3.1848 | 3100 | 0.2968        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 3.2875 | 3200 | 0.2962        | 0.7953                  | 0.6717                  | 0.6086                  | 0.7613                  | 0.8110                 | 0.7824                 | 0.5482                 |
+| 3.3901 | 3300 | 0.3084        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 3.4928 | 3400 | 0.2909        | 0.7940                  | 0.6634                  | 0.6023                  | 0.7615                  | 0.8138                 | 0.7822                 | 0.5457                 |
+| 3.5955 | 3500 | 0.2964        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 3.6982 | 3600 | 0.3193        | 0.7960                  | 0.6635                  | 0.6070                  | 0.7534                  | 0.8164                 | 0.7844                 | 0.5467                 |
+| 3.8008 | 3700 | 0.3514        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 3.9035 | 3800 | 0.3147        | 0.7973                  | 0.6696                  | 0.6125                  | 0.7616                  | 0.8176                 | 0.7885                 | 0.5469                 |
+| 4.0062 | 3900 | 0.2738        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 4.1088 | 4000 | 0.2842        | 0.7960                  | 0.6672                  | 0.6082                  | 0.7536                  | 0.8174                 | 0.7891                 | 0.5479                 |
+| 4.2115 | 4100 | 0.2739        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 4.3142 | 4200 | 0.2704        | 0.7979                  | 0.6681                  | 0.6111                  | 0.7540                  | 0.8180                 | 0.7891                 | 0.5476                 |
+| 4.4168 | 4300 | 0.2529        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 4.5195 | 4400 | 0.272         | 0.7968                  | 0.6685                  | 0.6087                  | 0.7564                  | 0.8185                 | 0.7901                 | 0.5476                 |
+| 4.6222 | 4500 | 0.3           | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 4.7248 | 4600 | 0.2598        | 0.7972                  | 0.6675                  | 0.6072                  | 0.7556                  | 0.8190                 | 0.7909                 | 0.5478                 |
+
+
+### Framework Versions
+- Python: 3.11.11
+- Sentence Transformers: 4.1.0
+- Transformers: 4.51.2
+- PyTorch: 2.6.0+cu124
+- Accelerate: 1.6.0
+- Datasets: 3.5.0
+- Tokenizers: 0.21.1
+
+## Citation
+
+### BibTeX
+
+#### Sentence Transformers
+```bibtex
+@inproceedings{reimers-2019-sentence-bert,
+    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
+    author = "Reimers, Nils and Gurevych, Iryna",
+    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
+    month = "11",
+    year = "2019",
+    publisher = "Association for Computational Linguistics",
+    url = "https://arxiv.org/abs/1908.10084",
+}
+```
+
+#### GISTEmbedLoss
+```bibtex
+@misc{solatorio2024gistembed,
+    title={GISTEmbed: Guided In-sample Selection of Training Negatives for Text Embedding Fine-tuning},
+    author={Aivin V. Solatorio},
+    year={2024},
+    eprint={2402.16829},
+    archivePrefix={arXiv},
+    primaryClass={cs.LG}
+}
+```
+
+<!--
+## Glossary
+
+*Clearly define terms in order to be accessible across audiences.*
+-->
+
+<!--
+## Model Card Authors
+
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
+
+<!--
+## Model Card Contact
+
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

checkpoint-4600/config.json

@@ -0,0 +1,49 @@
+{
+  "architectures": [
+    "NewModel"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "auto_map": {
+    "AutoConfig": "Alibaba-NLP/new-impl--configuration.NewConfig",
+    "AutoModel": "Alibaba-NLP/new-impl--modeling.NewModel",
+    "AutoModelForMaskedLM": "Alibaba-NLP/new-impl--modeling.NewForMaskedLM",
+    "AutoModelForMultipleChoice": "Alibaba-NLP/new-impl--modeling.NewForMultipleChoice",
+    "AutoModelForQuestionAnswering": "Alibaba-NLP/new-impl--modeling.NewForQuestionAnswering",
+    "AutoModelForSequenceClassification": "Alibaba-NLP/new-impl--modeling.NewForSequenceClassification",
+    "AutoModelForTokenClassification": "Alibaba-NLP/new-impl--modeling.NewForTokenClassification"
+  },
+  "classifier_dropout": 0.0,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "layer_norm_type": "layer_norm",
+  "logn_attention_clip1": false,
+  "logn_attention_scale": false,
+  "max_position_embeddings": 8192,
+  "model_type": "new",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pack_qkv": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "rope",
+  "rope_scaling": {
+    "factor": 8.0,
+    "type": "ntk"
+  },
+  "rope_theta": 20000,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.2",
+  "type_vocab_size": 1,
+  "unpad_inputs": false,
+  "use_memory_efficient_attention": false,
+  "vocab_size": 250048
+}

checkpoint-4600/config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "4.1.0",
+    "transformers": "4.51.2",
+    "pytorch": "2.6.0+cu124"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

checkpoint-4600/modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

checkpoint-4600/sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 512,
+  "do_lower_case": false
+}

checkpoint-4600/special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-4600/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:883b037111086fd4dfebbbc9b7cee11e1517b5e0c0514879478661440f137085
+size 17082987

checkpoint-4600/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 8192,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizerFast",
+  "unk_token": "<unk>"
+}

checkpoint-4800/1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 768,
+  "pooling_mode_cls_token": true,
+  "pooling_mode_mean_tokens": false,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false,
+  "include_prompt": true
+}

checkpoint-4800/README.md

@@ -0,0 +1,1444 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:124788
+- loss:GISTEmbedLoss
+base_model: Alibaba-NLP/gte-multilingual-base
+widget:
+- source_sentence: 其他机械、设备和有形货物租赁服务代表
+  sentences:
+  - 其他机械和设备租赁服务工作人员
+  - 电子和电信设备及零部件物流经理
+  - 工业主厨
+- source_sentence: 公交车司机
+  sentences:
+  - 表演灯光设计师
+  - 乙烯基地板安装工
+  - 国际巴士司机
+- source_sentence: online communication manager
+  sentences:
+  - trades union official
+  - social media manager
+  - budget manager
+- source_sentence: Projektmanagerin
+  sentences:
+  - Projektmanager/Projektmanagerin
+  - Category-Manager
+  - Infanterist
+- source_sentence: Volksvertreter
+  sentences:
+  - Parlamentarier
+  - Oberbürgermeister
+  - Konsul
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+metrics:
+- cosine_accuracy@1
+- cosine_accuracy@20
+- cosine_accuracy@50
+- cosine_accuracy@100
+- cosine_accuracy@150
+- cosine_accuracy@200
+- cosine_precision@1
+- cosine_precision@20
+- cosine_precision@50
+- cosine_precision@100
+- cosine_precision@150
+- cosine_precision@200
+- cosine_recall@1
+- cosine_recall@20
+- cosine_recall@50
+- cosine_recall@100
+- cosine_recall@150
+- cosine_recall@200
+- cosine_ndcg@1
+- cosine_ndcg@20
+- cosine_ndcg@50
+- cosine_ndcg@100
+- cosine_ndcg@150
+- cosine_ndcg@200
+- cosine_mrr@1
+- cosine_mrr@20
+- cosine_mrr@50
+- cosine_mrr@100
+- cosine_mrr@150
+- cosine_mrr@200
+- cosine_map@1
+- cosine_map@20
+- cosine_map@50
+- cosine_map@100
+- cosine_map@150
+- cosine_map@200
+- cosine_map@500
+model-index:
+- name: SentenceTransformer based on Alibaba-NLP/gte-multilingual-base
+  results:
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: full en
+      type: full_en
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6571428571428571
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@20
+      value: 0.9904761904761905
+      name: Cosine Accuracy@20
+    - type: cosine_accuracy@50
+      value: 0.9904761904761905
+      name: Cosine Accuracy@50
+    - type: cosine_accuracy@100
+      value: 0.9904761904761905
+      name: Cosine Accuracy@100
+    - type: cosine_accuracy@150
+      value: 0.9904761904761905
+      name: Cosine Accuracy@150
+    - type: cosine_accuracy@200
+      value: 0.9904761904761905
+      name: Cosine Accuracy@200
+    - type: cosine_precision@1
+      value: 0.6571428571428571
+      name: Cosine Precision@1
+    - type: cosine_precision@20
+      value: 0.5171428571428571
+      name: Cosine Precision@20
+    - type: cosine_precision@50
+      value: 0.316
+      name: Cosine Precision@50
+    - type: cosine_precision@100
+      value: 0.18895238095238095
+      name: Cosine Precision@100
+    - type: cosine_precision@150
+      value: 0.13384126984126984
+      name: Cosine Precision@150
+    - type: cosine_precision@200
+      value: 0.10433333333333335
+      name: Cosine Precision@200
+    - type: cosine_recall@1
+      value: 0.0678253733846715
+      name: Cosine Recall@1
+    - type: cosine_recall@20
+      value: 0.5470006025464504
+      name: Cosine Recall@20
+    - type: cosine_recall@50
+      value: 0.7399645316315758
+      name: Cosine Recall@50
+    - type: cosine_recall@100
+      value: 0.8452891149669638
+      name: Cosine Recall@100
+    - type: cosine_recall@150
+      value: 0.8838497168796887
+      name: Cosine Recall@150
+    - type: cosine_recall@200
+      value: 0.9109269128757174
+      name: Cosine Recall@200
+    - type: cosine_ndcg@1
+      value: 0.6571428571428571
+      name: Cosine Ndcg@1
+    - type: cosine_ndcg@20
+      value: 0.6953571805621692
+      name: Cosine Ndcg@20
+    - type: cosine_ndcg@50
+      value: 0.7150421121165462
+      name: Cosine Ndcg@50
+    - type: cosine_ndcg@100
+      value: 0.7679394555495317
+      name: Cosine Ndcg@100
+    - type: cosine_ndcg@150
+      value: 0.7856911059911225
+      name: Cosine Ndcg@150
+    - type: cosine_ndcg@200
+      value: 0.7969632777290026
+      name: Cosine Ndcg@200
+    - type: cosine_mrr@1
+      value: 0.6571428571428571
+      name: Cosine Mrr@1
+    - type: cosine_mrr@20
+      value: 0.8138095238095239
+      name: Cosine Mrr@20
+    - type: cosine_mrr@50
+      value: 0.8138095238095239
+      name: Cosine Mrr@50
+    - type: cosine_mrr@100
+      value: 0.8138095238095239
+      name: Cosine Mrr@100
+    - type: cosine_mrr@150
+      value: 0.8138095238095239
+      name: Cosine Mrr@150
+    - type: cosine_mrr@200
+      value: 0.8138095238095239
+      name: Cosine Mrr@200
+    - type: cosine_map@1
+      value: 0.6571428571428571
+      name: Cosine Map@1
+    - type: cosine_map@20
+      value: 0.5578605627627369
+      name: Cosine Map@20
+    - type: cosine_map@50
+      value: 0.5471407389299809
+      name: Cosine Map@50
+    - type: cosine_map@100
+      value: 0.5795933384755297
+      name: Cosine Map@100
+    - type: cosine_map@150
+      value: 0.5874505508842796
+      name: Cosine Map@150
+    - type: cosine_map@200
+      value: 0.5912226659397186
+      name: Cosine Map@200
+    - type: cosine_map@500
+      value: 0.5952587557760031
+      name: Cosine Map@500
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: full es
+      type: full_es
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.12432432432432433
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@20
+      value: 1.0
+      name: Cosine Accuracy@20
+    - type: cosine_accuracy@50
+      value: 1.0
+      name: Cosine Accuracy@50
+    - type: cosine_accuracy@100
+      value: 1.0
+      name: Cosine Accuracy@100
+    - type: cosine_accuracy@150
+      value: 1.0
+      name: Cosine Accuracy@150
+    - type: cosine_accuracy@200
+      value: 1.0
+      name: Cosine Accuracy@200
+    - type: cosine_precision@1
+      value: 0.12432432432432433
+      name: Cosine Precision@1
+    - type: cosine_precision@20
+      value: 0.5718918918918919
+      name: Cosine Precision@20
+    - type: cosine_precision@50
+      value: 0.3885405405405405
+      name: Cosine Precision@50
+    - type: cosine_precision@100
+      value: 0.25172972972972973
+      name: Cosine Precision@100
+    - type: cosine_precision@150
+      value: 0.1904864864864865
+      name: Cosine Precision@150
+    - type: cosine_precision@200
+      value: 0.1521891891891892
+      name: Cosine Precision@200
+    - type: cosine_recall@1
+      value: 0.0036619075252531876
+      name: Cosine Recall@1
+    - type: cosine_recall@20
+      value: 0.3842245968041533
+      name: Cosine Recall@20
+    - type: cosine_recall@50
+      value: 0.5640822196868902
+      name: Cosine Recall@50
+    - type: cosine_recall@100
+      value: 0.6741986120580108
+      name: Cosine Recall@100
+    - type: cosine_recall@150
+      value: 0.7463851968088967
+      name: Cosine Recall@150
+    - type: cosine_recall@200
+      value: 0.7825399601398452
+      name: Cosine Recall@200
+    - type: cosine_ndcg@1
+      value: 0.12432432432432433
+      name: Cosine Ndcg@1
+    - type: cosine_ndcg@20
+      value: 0.6139182209948354
+      name: Cosine Ndcg@20
+    - type: cosine_ndcg@50
+      value: 0.5873893466818746
+      name: Cosine Ndcg@50
+    - type: cosine_ndcg@100
+      value: 0.6144038475288277
+      name: Cosine Ndcg@100
+    - type: cosine_ndcg@150
+      value: 0.6498632077214272
+      name: Cosine Ndcg@150
+    - type: cosine_ndcg@200
+      value: 0.6680602466150343
+      name: Cosine Ndcg@200
+    - type: cosine_mrr@1
+      value: 0.12432432432432433
+      name: Cosine Mrr@1
+    - type: cosine_mrr@20
+      value: 0.5581081081081081
+      name: Cosine Mrr@20
+    - type: cosine_mrr@50
+      value: 0.5581081081081081
+      name: Cosine Mrr@50
+    - type: cosine_mrr@100
+      value: 0.5581081081081081
+      name: Cosine Mrr@100
+    - type: cosine_mrr@150
+      value: 0.5581081081081081
+      name: Cosine Mrr@150
+    - type: cosine_mrr@200
+      value: 0.5581081081081081
+      name: Cosine Mrr@200
+    - type: cosine_map@1
+      value: 0.12432432432432433
+      name: Cosine Map@1
+    - type: cosine_map@20
+      value: 0.47988875190050484
+      name: Cosine Map@20
+    - type: cosine_map@50
+      value: 0.4249833337950364
+      name: Cosine Map@50
+    - type: cosine_map@100
+      value: 0.430155652024808
+      name: Cosine Map@100
+    - type: cosine_map@150
+      value: 0.4458862132745998
+      name: Cosine Map@150
+    - type: cosine_map@200
+      value: 0.45334655744992447
+      name: Cosine Map@200
+    - type: cosine_map@500
+      value: 0.4656066165331343
+      name: Cosine Map@500
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: full de
+      type: full_de
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.2955665024630542
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@20
+      value: 0.9704433497536946
+      name: Cosine Accuracy@20
+    - type: cosine_accuracy@50
+      value: 0.9852216748768473
+      name: Cosine Accuracy@50
+    - type: cosine_accuracy@100
+      value: 0.9852216748768473
+      name: Cosine Accuracy@100
+    - type: cosine_accuracy@150
+      value: 0.9901477832512315
+      name: Cosine Accuracy@150
+    - type: cosine_accuracy@200
+      value: 0.9901477832512315
+      name: Cosine Accuracy@200
+    - type: cosine_precision@1
+      value: 0.2955665024630542
+      name: Cosine Precision@1
+    - type: cosine_precision@20
+      value: 0.5083743842364532
+      name: Cosine Precision@20
+    - type: cosine_precision@50
+      value: 0.3654187192118227
+      name: Cosine Precision@50
+    - type: cosine_precision@100
+      value: 0.24133004926108376
+      name: Cosine Precision@100
+    - type: cosine_precision@150
+      value: 0.18036124794745487
+      name: Cosine Precision@150
+    - type: cosine_precision@200
+      value: 0.14467980295566504
+      name: Cosine Precision@200
+    - type: cosine_recall@1
+      value: 0.01108543831680986
+      name: Cosine Recall@1
+    - type: cosine_recall@20
+      value: 0.3221185941380065
+      name: Cosine Recall@20
+    - type: cosine_recall@50
+      value: 0.5024502430161547
+      name: Cosine Recall@50
+    - type: cosine_recall@100
+      value: 0.6247617904371989
+      name: Cosine Recall@100
+    - type: cosine_recall@150
+      value: 0.6829583450315939
+      name: Cosine Recall@150
+    - type: cosine_recall@200
+      value: 0.7216293640715983
+      name: Cosine Recall@200
+    - type: cosine_ndcg@1
+      value: 0.2955665024630542
+      name: Cosine Ndcg@1
+    - type: cosine_ndcg@20
+      value: 0.5393376062142305
+      name: Cosine Ndcg@20
+    - type: cosine_ndcg@50
+      value: 0.5267125529267169
+      name: Cosine Ndcg@50
+    - type: cosine_ndcg@100
+      value: 0.55793511917882
+      name: Cosine Ndcg@100
+    - type: cosine_ndcg@150
+      value: 0.5879547828450983
+      name: Cosine Ndcg@150
+    - type: cosine_ndcg@200
+      value: 0.6071252185389439
+      name: Cosine Ndcg@200
+    - type: cosine_mrr@1
+      value: 0.2955665024630542
+      name: Cosine Mrr@1
+    - type: cosine_mrr@20
+      value: 0.5104381157401634
+      name: Cosine Mrr@20
+    - type: cosine_mrr@50
+      value: 0.5109752961295605
+      name: Cosine Mrr@50
+    - type: cosine_mrr@100
+      value: 0.5109752961295605
+      name: Cosine Mrr@100
+    - type: cosine_mrr@150
+      value: 0.5110222114474118
+      name: Cosine Mrr@150
+    - type: cosine_mrr@200
+      value: 0.5110222114474118
+      name: Cosine Mrr@200
+    - type: cosine_map@1
+      value: 0.2955665024630542
+      name: Cosine Map@1
+    - type: cosine_map@20
+      value: 0.40097257642946377
+      name: Cosine Map@20
+    - type: cosine_map@50
+      value: 0.35882787401455
+      name: Cosine Map@50
+    - type: cosine_map@100
+      value: 0.3633182590941781
+      name: Cosine Map@100
+    - type: cosine_map@150
+      value: 0.3776727961080201
+      name: Cosine Map@150
+    - type: cosine_map@200
+      value: 0.3848401555555339
+      name: Cosine Map@200
+    - type: cosine_map@500
+      value: 0.3978065874082948
+      name: Cosine Map@500
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: full zh
+      type: full_zh
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6601941747572816
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@20
+      value: 0.9805825242718447
+      name: Cosine Accuracy@20
+    - type: cosine_accuracy@50
+      value: 0.9902912621359223
+      name: Cosine Accuracy@50
+    - type: cosine_accuracy@100
+      value: 0.9902912621359223
+      name: Cosine Accuracy@100
+    - type: cosine_accuracy@150
+      value: 0.9902912621359223
+      name: Cosine Accuracy@150
+    - type: cosine_accuracy@200
+      value: 0.9902912621359223
+      name: Cosine Accuracy@200
+    - type: cosine_precision@1
+      value: 0.6601941747572816
+      name: Cosine Precision@1
+    - type: cosine_precision@20
+      value: 0.4781553398058253
+      name: Cosine Precision@20
+    - type: cosine_precision@50
+      value: 0.28951456310679613
+      name: Cosine Precision@50
+    - type: cosine_precision@100
+      value: 0.17572815533980585
+      name: Cosine Precision@100
+    - type: cosine_precision@150
+      value: 0.12595469255663433
+      name: Cosine Precision@150
+    - type: cosine_precision@200
+      value: 0.09815533980582528
+      name: Cosine Precision@200
+    - type: cosine_recall@1
+      value: 0.06151358631979527
+      name: Cosine Recall@1
+    - type: cosine_recall@20
+      value: 0.5107966412908705
+      name: Cosine Recall@20
+    - type: cosine_recall@50
+      value: 0.6922746152164951
+      name: Cosine Recall@50
+    - type: cosine_recall@100
+      value: 0.8004152884148357
+      name: Cosine Recall@100
+    - type: cosine_recall@150
+      value: 0.8465065661615649
+      name: Cosine Recall@150
+    - type: cosine_recall@200
+      value: 0.8770990926698364
+      name: Cosine Recall@200
+    - type: cosine_ndcg@1
+      value: 0.6601941747572816
+      name: Cosine Ndcg@1
+    - type: cosine_ndcg@20
+      value: 0.6539867858378715
+      name: Cosine Ndcg@20
+    - type: cosine_ndcg@50
+      value: 0.6707332209240133
+      name: Cosine Ndcg@50
+    - type: cosine_ndcg@100
+      value: 0.72342020484322
+      name: Cosine Ndcg@100
+    - type: cosine_ndcg@150
+      value: 0.7437750875502527
+      name: Cosine Ndcg@150
+    - type: cosine_ndcg@200
+      value: 0.7553648453187212
+      name: Cosine Ndcg@200
+    - type: cosine_mrr@1
+      value: 0.6601941747572816
+      name: Cosine Mrr@1
+    - type: cosine_mrr@20
+      value: 0.8037216828478965
+      name: Cosine Mrr@20
+    - type: cosine_mrr@50
+      value: 0.8040950958426687
+      name: Cosine Mrr@50
+    - type: cosine_mrr@100
+      value: 0.8040950958426687
+      name: Cosine Mrr@100
+    - type: cosine_mrr@150
+      value: 0.8040950958426687
+      name: Cosine Mrr@150
+    - type: cosine_mrr@200
+      value: 0.8040950958426687
+      name: Cosine Mrr@200
+    - type: cosine_map@1
+      value: 0.6601941747572816
+      name: Cosine Map@1
+    - type: cosine_map@20
+      value: 0.5087334164702914
+      name: Cosine Map@20
+    - type: cosine_map@50
+      value: 0.49260246320797585
+      name: Cosine Map@50
+    - type: cosine_map@100
+      value: 0.5217412166882693
+      name: Cosine Map@100
+    - type: cosine_map@150
+      value: 0.529859818130126
+      name: Cosine Map@150
+    - type: cosine_map@200
+      value: 0.533378795921413
+      name: Cosine Map@200
+    - type: cosine_map@500
+      value: 0.5386011712914499
+      name: Cosine Map@500
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: mix es
+      type: mix_es
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.7280291211648466
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@20
+      value: 0.9599583983359334
+      name: Cosine Accuracy@20
+    - type: cosine_accuracy@50
+      value: 0.9791991679667187
+      name: Cosine Accuracy@50
+    - type: cosine_accuracy@100
+      value: 0.9942797711908476
+      name: Cosine Accuracy@100
+    - type: cosine_accuracy@150
+      value: 0.9958398335933437
+      name: Cosine Accuracy@150
+    - type: cosine_accuracy@200
+      value: 0.9973998959958398
+      name: Cosine Accuracy@200
+    - type: cosine_precision@1
+      value: 0.7280291211648466
+      name: Cosine Precision@1
+    - type: cosine_precision@20
+      value: 0.12433697347893914
+      name: Cosine Precision@20
+    - type: cosine_precision@50
+      value: 0.05145085803432139
+      name: Cosine Precision@50
+    - type: cosine_precision@100
+      value: 0.02625065002600105
+      name: Cosine Precision@100
+    - type: cosine_precision@150
+      value: 0.017621771537528162
+      name: Cosine Precision@150
+    - type: cosine_precision@200
+      value: 0.013283931357254294
+      name: Cosine Precision@200
+    - type: cosine_recall@1
+      value: 0.28133620582918556
+      name: Cosine Recall@1
+    - type: cosine_recall@20
+      value: 0.9183394002426764
+      name: Cosine Recall@20
+    - type: cosine_recall@50
+      value: 0.9499306638932224
+      name: Cosine Recall@50
+    - type: cosine_recall@100
+      value: 0.9700901369388107
+      name: Cosine Recall@100
+    - type: cosine_recall@150
+      value: 0.9767724042295025
+      name: Cosine Recall@150
+    - type: cosine_recall@200
+      value: 0.9818166059975733
+      name: Cosine Recall@200
+    - type: cosine_ndcg@1
+      value: 0.7280291211648466
+      name: Cosine Ndcg@1
+    - type: cosine_ndcg@20
+      value: 0.8043549768911603
+      name: Cosine Ndcg@20
+    - type: cosine_ndcg@50
+      value: 0.81295852465432
+      name: Cosine Ndcg@50
+    - type: cosine_ndcg@100
+      value: 0.817339429558165
+      name: Cosine Ndcg@100
+    - type: cosine_ndcg@150
+      value: 0.8186380742931886
+      name: Cosine Ndcg@150
+    - type: cosine_ndcg@200
+      value: 0.8195485984235017
+      name: Cosine Ndcg@200
+    - type: cosine_mrr@1
+      value: 0.7280291211648466
+      name: Cosine Mrr@1
+    - type: cosine_mrr@20
+      value: 0.7968549154271433
+      name: Cosine Mrr@20
+    - type: cosine_mrr@50
+      value: 0.7974653825839162
+      name: Cosine Mrr@50
+    - type: cosine_mrr@100
+      value: 0.7976914864910069
+      name: Cosine Mrr@100
+    - type: cosine_mrr@150
+      value: 0.7977044635908871
+      name: Cosine Mrr@150
+    - type: cosine_mrr@200
+      value: 0.7977139196654446
+      name: Cosine Mrr@200
+    - type: cosine_map@1
+      value: 0.7280291211648466
+      name: Cosine Map@1
+    - type: cosine_map@20
+      value: 0.7350836192117531
+      name: Cosine Map@20
+    - type: cosine_map@50
+      value: 0.7374205090112232
+      name: Cosine Map@50
+    - type: cosine_map@100
+      value: 0.737988888492803
+      name: Cosine Map@100
+    - type: cosine_map@150
+      value: 0.7381133157945164
+      name: Cosine Map@150
+    - type: cosine_map@200
+      value: 0.7381788581828236
+      name: Cosine Map@200
+    - type: cosine_map@500
+      value: 0.7382854440643231
+      name: Cosine Map@500
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: mix de
+      type: mix_de
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6703068122724909
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@20
+      value: 0.9505980239209568
+      name: Cosine Accuracy@20
+    - type: cosine_accuracy@50
+      value: 0.9776391055642226
+      name: Cosine Accuracy@50
+    - type: cosine_accuracy@100
+      value: 0.9864794591783671
+      name: Cosine Accuracy@100
+    - type: cosine_accuracy@150
+      value: 0.9932397295891836
+      name: Cosine Accuracy@150
+    - type: cosine_accuracy@200
+      value: 0.9947997919916797
+      name: Cosine Accuracy@200
+    - type: cosine_precision@1
+      value: 0.6703068122724909
+      name: Cosine Precision@1
+    - type: cosine_precision@20
+      value: 0.1251690067602704
+      name: Cosine Precision@20
+    - type: cosine_precision@50
+      value: 0.052282891315652634
+      name: Cosine Precision@50
+    - type: cosine_precision@100
+      value: 0.026729069162766517
+      name: Cosine Precision@100
+    - type: cosine_precision@150
+      value: 0.01799965331946611
+      name: Cosine Precision@150
+    - type: cosine_precision@200
+      value: 0.013541341653666149
+      name: Cosine Precision@200
+    - type: cosine_recall@1
+      value: 0.25235742763043856
+      name: Cosine Recall@1
+    - type: cosine_recall@20
+      value: 0.9095857167620037
+      name: Cosine Recall@20
+    - type: cosine_recall@50
+      value: 0.9482405962905183
+      name: Cosine Recall@50
+    - type: cosine_recall@100
+      value: 0.96845207141619
+      name: Cosine Recall@100
+    - type: cosine_recall@150
+      value: 0.9781591263650546
+      name: Cosine Recall@150
+    - type: cosine_recall@200
+      value: 0.9810192407696308
+      name: Cosine Recall@200
+    - type: cosine_ndcg@1
+      value: 0.6703068122724909
+      name: Cosine Ndcg@1
+    - type: cosine_ndcg@20
+      value: 0.7735712514376322
+      name: Cosine Ndcg@20
+    - type: cosine_ndcg@50
+      value: 0.7843644592705362
+      name: Cosine Ndcg@50
+    - type: cosine_ndcg@100
+      value: 0.7889444470773866
+      name: Cosine Ndcg@100
+    - type: cosine_ndcg@150
+      value: 0.7908660087982327
+      name: Cosine Ndcg@150
+    - type: cosine_ndcg@200
+      value: 0.791403470160319
+      name: Cosine Ndcg@200
+    - type: cosine_mrr@1
+      value: 0.6703068122724909
+      name: Cosine Mrr@1
+    - type: cosine_mrr@20
+      value: 0.7520307321055828
+      name: Cosine Mrr@20
+    - type: cosine_mrr@50
+      value: 0.7529374175534339
+      name: Cosine Mrr@50
+    - type: cosine_mrr@100
+      value: 0.7530616872072472
+      name: Cosine Mrr@100
+    - type: cosine_mrr@150
+      value: 0.7531202644382351
+      name: Cosine Mrr@150
+    - type: cosine_mrr@200
+      value: 0.7531293951311296
+      name: Cosine Mrr@200
+    - type: cosine_map@1
+      value: 0.6703068122724909
+      name: Cosine Map@1
+    - type: cosine_map@20
+      value: 0.6967639778693541
+      name: Cosine Map@20
+    - type: cosine_map@50
+      value: 0.699575457224443
+      name: Cosine Map@50
+    - type: cosine_map@100
+      value: 0.70027844357658
+      name: Cosine Map@100
+    - type: cosine_map@150
+      value: 0.7004487000056766
+      name: Cosine Map@150
+    - type: cosine_map@200
+      value: 0.7004863395843564
+      name: Cosine Map@200
+    - type: cosine_map@500
+      value: 0.7005835771389989
+      name: Cosine Map@500
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: mix zh
+      type: mix_zh
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.19084763390535622
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@20
+      value: 1.0
+      name: Cosine Accuracy@20
+    - type: cosine_accuracy@50
+      value: 1.0
+      name: Cosine Accuracy@50
+    - type: cosine_accuracy@100
+      value: 1.0
+      name: Cosine Accuracy@100
+    - type: cosine_accuracy@150
+      value: 1.0
+      name: Cosine Accuracy@150
+    - type: cosine_accuracy@200
+      value: 1.0
+      name: Cosine Accuracy@200
+    - type: cosine_precision@1
+      value: 0.19084763390535622
+      name: Cosine Precision@1
+    - type: cosine_precision@20
+      value: 0.15439417576703063
+      name: Cosine Precision@20
+    - type: cosine_precision@50
+      value: 0.0617576703068123
+      name: Cosine Precision@50
+    - type: cosine_precision@100
+      value: 0.03087883515340615
+      name: Cosine Precision@100
+    - type: cosine_precision@150
+      value: 0.020585890102270757
+      name: Cosine Precision@150
+    - type: cosine_precision@200
+      value: 0.015439417576703075
+      name: Cosine Precision@200
+    - type: cosine_recall@1
+      value: 0.06137978852487433
+      name: Cosine Recall@1
+    - type: cosine_recall@20
+      value: 1.0
+      name: Cosine Recall@20
+    - type: cosine_recall@50
+      value: 1.0
+      name: Cosine Recall@50
+    - type: cosine_recall@100
+      value: 1.0
+      name: Cosine Recall@100
+    - type: cosine_recall@150
+      value: 1.0
+      name: Cosine Recall@150
+    - type: cosine_recall@200
+      value: 1.0
+      name: Cosine Recall@200
+    - type: cosine_ndcg@1
+      value: 0.19084763390535622
+      name: Cosine Ndcg@1
+    - type: cosine_ndcg@20
+      value: 0.5474303590499686
+      name: Cosine Ndcg@20
+    - type: cosine_ndcg@50
+      value: 0.5474303590499686
+      name: Cosine Ndcg@50
+    - type: cosine_ndcg@100
+      value: 0.5474303590499686
+      name: Cosine Ndcg@100
+    - type: cosine_ndcg@150
+      value: 0.5474303590499686
+      name: Cosine Ndcg@150
+    - type: cosine_ndcg@200
+      value: 0.5474303590499686
+      name: Cosine Ndcg@200
+    - type: cosine_mrr@1
+      value: 0.19084763390535622
+      name: Cosine Mrr@1
+    - type: cosine_mrr@20
+      value: 0.4093433087972877
+      name: Cosine Mrr@20
+    - type: cosine_mrr@50
+      value: 0.4093433087972877
+      name: Cosine Mrr@50
+    - type: cosine_mrr@100
+      value: 0.4093433087972877
+      name: Cosine Mrr@100
+    - type: cosine_mrr@150
+      value: 0.4093433087972877
+      name: Cosine Mrr@150
+    - type: cosine_mrr@200
+      value: 0.4093433087972877
+      name: Cosine Mrr@200
+    - type: cosine_map@1
+      value: 0.19084763390535622
+      name: Cosine Map@1
+    - type: cosine_map@20
+      value: 0.32981711891302556
+      name: Cosine Map@20
+    - type: cosine_map@50
+      value: 0.32981711891302556
+      name: Cosine Map@50
+    - type: cosine_map@100
+      value: 0.32981711891302556
+      name: Cosine Map@100
+    - type: cosine_map@150
+      value: 0.32981711891302556
+      name: Cosine Map@150
+    - type: cosine_map@200
+      value: 0.32981711891302556
+      name: Cosine Map@200
+    - type: cosine_map@500
+      value: 0.32981711891302556
+      name: Cosine Map@500
+---
+
+# Job - Job matching Alibaba-NLP/gte-multilingual-base (v1)
+
+Top performing model on [TalentCLEF 2025](https://talentclef.github.io/talentclef/) Task A.  Use it for multilingual job title matching
+
+## Model Details
+
+### Model Description
+- **Model Type:** Sentence Transformer
+- **Base model:** [Alibaba-NLP/gte-multilingual-base](https://huggingface.co/Alibaba-NLP/gte-multilingual-base) <!-- at revision 9fdd4ee8bba0e2808a34e0e739576f6740d2b225 -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 768 dimensions
+- **Similarity Function:** Cosine Similarity
+- **Training Datasets:**
+    - full_en
+    - full_de
+    - full_es
+    - full_zh
+    - mix
+<!-- - **Language:** Unknown -->
+<!-- - **License:** Unknown -->
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
+- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
+
+### Full Model Architecture
+
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: NewModel 
+  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+  (2): Normalize()
+)
+```
+
+## Usage
+
+### Direct Usage (Sentence Transformers)
+
+First install the Sentence Transformers library:
+
+```bash
+pip install -U sentence-transformers
+```
+
+Then you can load this model and run inference.
+```python
+from sentence_transformers import SentenceTransformer
+
+# Download from the 🤗 Hub
+model = SentenceTransformer("pj-mathematician/JobGTE-multilingual-base-v1")
+# Run inference
+sentences = [
+    'Volksvertreter',
+    'Parlamentarier',
+    'Oberbürgermeister',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 768]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities.shape)
+# [3, 3]
+```
+
+<!--
+### Direct Usage (Transformers)
+
+<details><summary>Click to see the direct usage in Transformers</summary>
+
+</details>
+-->
+
+<!--
+### Downstream Usage (Sentence Transformers)
+
+You can finetune this model on your own dataset.
+
+<details><summary>Click to expand</summary>
+
+</details>
+-->
+
+<!--
+### Out-of-Scope Use
+
+*List how the model may foreseeably be misused and address what users ought not to do with the model.*
+-->
+
+## Evaluation
+
+### Metrics
+
+#### Information Retrieval
+
+* Datasets: `full_en`, `full_es`, `full_de`, `full_zh`, `mix_es`, `mix_de` and `mix_zh`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric               | full_en   | full_es    | full_de    | full_zh    | mix_es     | mix_de     | mix_zh     |
+|:---------------------|:----------|:-----------|:-----------|:-----------|:-----------|:-----------|:-----------|
+| cosine_accuracy@1    | 0.6571    | 0.1243     | 0.2956     | 0.6602     | 0.728      | 0.6703     | 0.1908     |
+| cosine_accuracy@20   | 0.9905    | 1.0        | 0.9704     | 0.9806     | 0.96       | 0.9506     | 1.0        |
+| cosine_accuracy@50   | 0.9905    | 1.0        | 0.9852     | 0.9903     | 0.9792     | 0.9776     | 1.0        |
+| cosine_accuracy@100  | 0.9905    | 1.0        | 0.9852     | 0.9903     | 0.9943     | 0.9865     | 1.0        |
+| cosine_accuracy@150  | 0.9905    | 1.0        | 0.9901     | 0.9903     | 0.9958     | 0.9932     | 1.0        |
+| cosine_accuracy@200  | 0.9905    | 1.0        | 0.9901     | 0.9903     | 0.9974     | 0.9948     | 1.0        |
+| cosine_precision@1   | 0.6571    | 0.1243     | 0.2956     | 0.6602     | 0.728      | 0.6703     | 0.1908     |
+| cosine_precision@20  | 0.5171    | 0.5719     | 0.5084     | 0.4782     | 0.1243     | 0.1252     | 0.1544     |
+| cosine_precision@50  | 0.316     | 0.3885     | 0.3654     | 0.2895     | 0.0515     | 0.0523     | 0.0618     |
+| cosine_precision@100 | 0.189     | 0.2517     | 0.2413     | 0.1757     | 0.0263     | 0.0267     | 0.0309     |
+| cosine_precision@150 | 0.1338    | 0.1905     | 0.1804     | 0.126      | 0.0176     | 0.018      | 0.0206     |
+| cosine_precision@200 | 0.1043    | 0.1522     | 0.1447     | 0.0982     | 0.0133     | 0.0135     | 0.0154     |
+| cosine_recall@1      | 0.0678    | 0.0037     | 0.0111     | 0.0615     | 0.2813     | 0.2524     | 0.0614     |
+| cosine_recall@20     | 0.547     | 0.3842     | 0.3221     | 0.5108     | 0.9183     | 0.9096     | 1.0        |
+| cosine_recall@50     | 0.74      | 0.5641     | 0.5025     | 0.6923     | 0.9499     | 0.9482     | 1.0        |
+| cosine_recall@100    | 0.8453    | 0.6742     | 0.6248     | 0.8004     | 0.9701     | 0.9685     | 1.0        |
+| cosine_recall@150    | 0.8838    | 0.7464     | 0.683      | 0.8465     | 0.9768     | 0.9782     | 1.0        |
+| cosine_recall@200    | 0.9109    | 0.7825     | 0.7216     | 0.8771     | 0.9818     | 0.981      | 1.0        |
+| cosine_ndcg@1        | 0.6571    | 0.1243     | 0.2956     | 0.6602     | 0.728      | 0.6703     | 0.1908     |
+| cosine_ndcg@20       | 0.6954    | 0.6139     | 0.5393     | 0.654      | 0.8044     | 0.7736     | 0.5474     |
+| cosine_ndcg@50       | 0.715     | 0.5874     | 0.5267     | 0.6707     | 0.813      | 0.7844     | 0.5474     |
+| cosine_ndcg@100      | 0.7679    | 0.6144     | 0.5579     | 0.7234     | 0.8173     | 0.7889     | 0.5474     |
+| cosine_ndcg@150      | 0.7857    | 0.6499     | 0.588      | 0.7438     | 0.8186     | 0.7909     | 0.5474     |
+| **cosine_ndcg@200**  | **0.797** | **0.6681** | **0.6071** | **0.7554** | **0.8195** | **0.7914** | **0.5474** |
+| cosine_mrr@1         | 0.6571    | 0.1243     | 0.2956     | 0.6602     | 0.728      | 0.6703     | 0.1908     |
+| cosine_mrr@20        | 0.8138    | 0.5581     | 0.5104     | 0.8037     | 0.7969     | 0.752      | 0.4093     |
+| cosine_mrr@50        | 0.8138    | 0.5581     | 0.511      | 0.8041     | 0.7975     | 0.7529     | 0.4093     |
+| cosine_mrr@100       | 0.8138    | 0.5581     | 0.511      | 0.8041     | 0.7977     | 0.7531     | 0.4093     |
+| cosine_mrr@150       | 0.8138    | 0.5581     | 0.511      | 0.8041     | 0.7977     | 0.7531     | 0.4093     |
+| cosine_mrr@200       | 0.8138    | 0.5581     | 0.511      | 0.8041     | 0.7977     | 0.7531     | 0.4093     |
+| cosine_map@1         | 0.6571    | 0.1243     | 0.2956     | 0.6602     | 0.728      | 0.6703     | 0.1908     |
+| cosine_map@20        | 0.5579    | 0.4799     | 0.401      | 0.5087     | 0.7351     | 0.6968     | 0.3298     |
+| cosine_map@50        | 0.5471    | 0.425      | 0.3588     | 0.4926     | 0.7374     | 0.6996     | 0.3298     |
+| cosine_map@100       | 0.5796    | 0.4302     | 0.3633     | 0.5217     | 0.738      | 0.7003     | 0.3298     |
+| cosine_map@150       | 0.5875    | 0.4459     | 0.3777     | 0.5299     | 0.7381     | 0.7004     | 0.3298     |
+| cosine_map@200       | 0.5912    | 0.4533     | 0.3848     | 0.5334     | 0.7382     | 0.7005     | 0.3298     |
+| cosine_map@500       | 0.5953    | 0.4656     | 0.3978     | 0.5386     | 0.7383     | 0.7006     | 0.3298     |
+
+<!--
+## Bias, Risks and Limitations
+
+*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
+-->
+
+<!--
+### Recommendations
+
+*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
+-->
+
+## Training Details
+
+### Training Datasets
+<details><summary>full_en</summary>
+
+#### full_en
+
+* Dataset: full_en
+* Size: 28,880 training samples
+* Columns: <code>anchor</code> and <code>positive</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | anchor                                                                           | positive                                                                         |
+  |:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|
+  | type    | string                                                                           | string                                                                           |
+  | details | <ul><li>min: 3 tokens</li><li>mean: 5.68 tokens</li><li>max: 11 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 5.76 tokens</li><li>max: 12 tokens</li></ul> |
+* Samples:
+  | anchor                                   | positive                                 |
+  |:-----------------------------------------|:-----------------------------------------|
+  | <code>air commodore</code>               | <code>flight lieutenant</code>           |
+  | <code>command and control officer</code> | <code>flight officer</code>              |
+  | <code>air commodore</code>               | <code>command and control officer</code> |
+* Loss: [<code>GISTEmbedLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#gistembedloss) with these parameters:
+  ```json
+  {'guide': SentenceTransformer(
+    (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel 
+    (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+    (2): Normalize()
+  ), 'temperature': 0.01, 'margin_strategy': 'absolute', 'margin': 0.0}
+  ```
+</details>
+<details><summary>full_de</summary>
+
+#### full_de
+
+* Dataset: full_de
+* Size: 23,023 training samples
+* Columns: <code>anchor</code> and <code>positive</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | anchor                                                                           | positive                                                                         |
+  |:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|
+  | type    | string                                                                           | string                                                                           |
+  | details | <ul><li>min: 3 tokens</li><li>mean: 7.99 tokens</li><li>max: 30 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 8.19 tokens</li><li>max: 30 tokens</li></ul> |
+* Samples:
+  | anchor                            | positive                                             |
+  |:----------------------------------|:-----------------------------------------------------|
+  | <code>Staffelkommandantin</code>  | <code>Kommodore</code>                               |
+  | <code>Luftwaffenoffizierin</code> | <code>Luftwaffenoffizier/Luftwaffenoffizierin</code> |
+  | <code>Staffelkommandantin</code>  | <code>Luftwaffenoffizierin</code>                    |
+* Loss: [<code>GISTEmbedLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#gistembedloss) with these parameters:
+  ```json
+  {'guide': SentenceTransformer(
+    (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel 
+    (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+    (2): Normalize()
+  ), 'temperature': 0.01, 'margin_strategy': 'absolute', 'margin': 0.0}
+  ```
+</details>
+<details><summary>full_es</summary>
+
+#### full_es
+
+* Dataset: full_es
+* Size: 20,724 training samples
+* Columns: <code>anchor</code> and <code>positive</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | anchor                                                                           | positive                                                                         |
+  |:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|
+  | type    | string                                                                           | string                                                                           |
+  | details | <ul><li>min: 3 tokens</li><li>mean: 9.13 tokens</li><li>max: 32 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 8.84 tokens</li><li>max: 32 tokens</li></ul> |
+* Samples:
+  | anchor                              | positive                                   |
+  |:------------------------------------|:-------------------------------------------|
+  | <code>jefe de escuadrón</code>      | <code>instructor</code>                    |
+  | <code>comandante de aeronave</code> | <code>instructor de simulador</code>       |
+  | <code>instructor</code>             | <code>oficial del Ejército del Aire</code> |
+* Loss: [<code>GISTEmbedLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#gistembedloss) with these parameters:
+  ```json
+  {'guide': SentenceTransformer(
+    (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel 
+    (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+    (2): Normalize()
+  ), 'temperature': 0.01, 'margin_strategy': 'absolute', 'margin': 0.0}
+  ```
+</details>
+<details><summary>full_zh</summary>
+
+#### full_zh
+
+* Dataset: full_zh
+* Size: 30,401 training samples
+* Columns: <code>anchor</code> and <code>positive</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | anchor                                                                           | positive                                                                         |
+  |:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|
+  | type    | string                                                                           | string                                                                           |
+  | details | <ul><li>min: 5 tokens</li><li>mean: 7.15 tokens</li><li>max: 14 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 7.46 tokens</li><li>max: 21 tokens</li></ul> |
+* Samples:
+  | anchor            | positive             |
+  |:------------------|:---------------------|
+  | <code>技术总监</code> | <code>技术和运营总监</code> |
+  | <code>技术总监</code> | <code>技术主管</code>    |
+  | <code>技术总监</code> | <code>技术艺术总监</code>  |
+* Loss: [<code>GISTEmbedLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#gistembedloss) with these parameters:
+  ```json
+  {'guide': SentenceTransformer(
+    (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel 
+    (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+    (2): Normalize()
+  ), 'temperature': 0.01, 'margin_strategy': 'absolute', 'margin': 0.0}
+  ```
+</details>
+<details><summary>mix</summary>
+
+#### mix
+
+* Dataset: mix
+* Size: 21,760 training samples
+* Columns: <code>anchor</code> and <code>positive</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | anchor                                                                           | positive                                                                         |
+  |:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|
+  | type    | string                                                                           | string                                                                           |
+  | details | <ul><li>min: 2 tokens</li><li>mean: 6.71 tokens</li><li>max: 19 tokens</li></ul> | <ul><li>min: 2 tokens</li><li>mean: 7.69 tokens</li><li>max: 19 tokens</li></ul> |
+* Samples:
+  | anchor                                    | positive                                                        |
+  |:------------------------------------------|:----------------------------------------------------------------|
+  | <code>technical manager</code>            | <code>Technischer Direktor für Bühne, Film und Fernsehen</code> |
+  | <code>head of technical</code>            | <code>directora técnica</code>                                  |
+  | <code>head of technical department</code> | <code>技术艺术总监</code>                                             |
+* Loss: [<code>GISTEmbedLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#gistembedloss) with these parameters:
+  ```json
+  {'guide': SentenceTransformer(
+    (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel 
+    (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+    (2): Normalize()
+  ), 'temperature': 0.01, 'margin_strategy': 'absolute', 'margin': 0.0}
+  ```
+</details>
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 64
+- `per_device_eval_batch_size`: 128
+- `gradient_accumulation_steps`: 2
+- `num_train_epochs`: 5
+- `warmup_ratio`: 0.05
+- `log_on_each_node`: False
+- `fp16`: True
+- `dataloader_num_workers`: 4
+- `ddp_find_unused_parameters`: True
+- `batch_sampler`: no_duplicates
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: steps
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 64
+- `per_device_eval_batch_size`: 128
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 2
+- `eval_accumulation_steps`: None
+- `torch_empty_cache_steps`: None
+- `learning_rate`: 5e-05
+- `weight_decay`: 0.0
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1.0
+- `num_train_epochs`: 5
+- `max_steps`: -1
+- `lr_scheduler_type`: linear
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.05
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: False
+- `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`: 4
+- `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}
+- `tp_size`: 0
+- `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}
+- `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`: True
+- `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
+- `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`: False
+- `torch_compile_backend`: None
+- `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`: False
+- `use_liger_kernel`: False
+- `eval_use_gather_object`: False
+- `average_tokens_across_devices`: False
+- `prompts`: None
+- `batch_sampler`: no_duplicates
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch  | Step | Training Loss | full_en_cosine_ndcg@200 | full_es_cosine_ndcg@200 | full_de_cosine_ndcg@200 | full_zh_cosine_ndcg@200 | mix_es_cosine_ndcg@200 | mix_de_cosine_ndcg@200 | mix_zh_cosine_ndcg@200 |
+|:------:|:----:|:-------------:|:-----------------------:|:-----------------------:|:-----------------------:|:-----------------------:|:----------------------:|:----------------------:|:----------------------:|
+| -1     | -1   | -             | 0.7447                  | 0.6125                  | 0.5378                  | 0.7240                  | 0.7029                 | 0.6345                 | 0.5531                 |
+| 0.0010 | 1    | 3.4866        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 0.1027 | 100  | 2.5431        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 0.2053 | 200  | 1.4536        | 0.7993                  | 0.6633                  | 0.5974                  | 0.7642                  | 0.7567                 | 0.7011                 | 0.5498                 |
+| 0.3080 | 300  | 1.1018        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 0.4107 | 400  | 0.9184        | 0.7925                  | 0.6586                  | 0.6058                  | 0.7587                  | 0.7749                 | 0.7278                 | 0.5486                 |
+| 0.5133 | 500  | 0.8973        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 0.6160 | 600  | 0.7309        | 0.7951                  | 0.6671                  | 0.6096                  | 0.7708                  | 0.7793                 | 0.7339                 | 0.5525                 |
+| 0.7187 | 700  | 0.7297        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 0.8214 | 800  | 0.7281        | 0.7929                  | 0.6711                  | 0.6088                  | 0.7645                  | 0.7899                 | 0.7444                 | 0.5479                 |
+| 0.9240 | 900  | 0.6607        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 1.0267 | 1000 | 0.6075        | 0.7915                  | 0.6659                  | 0.6088                  | 0.7665                  | 0.7968                 | 0.7588                 | 0.5482                 |
+| 1.1294 | 1100 | 0.4553        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 1.2320 | 1200 | 0.4775        | 0.7979                  | 0.6696                  | 0.6033                  | 0.7669                  | 0.7959                 | 0.7624                 | 0.5484                 |
+| 1.3347 | 1300 | 0.4838        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 1.4374 | 1400 | 0.4912        | 0.7973                  | 0.6757                  | 0.6112                  | 0.7656                  | 0.7978                 | 0.7650                 | 0.5487                 |
+| 1.5400 | 1500 | 0.4732        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 1.6427 | 1600 | 0.5269        | 0.8031                  | 0.6723                  | 0.6108                  | 0.7654                  | 0.8008                 | 0.7660                 | 0.5492                 |
+| 1.7454 | 1700 | 0.4822        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 1.8480 | 1800 | 0.5072        | 0.7962                  | 0.6668                  | 0.6051                  | 0.7592                  | 0.8001                 | 0.7714                 | 0.5486                 |
+| 1.9507 | 1900 | 0.4709        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 2.0544 | 2000 | 0.3772        | 0.7940                  | 0.6647                  | 0.6037                  | 0.7579                  | 0.8064                 | 0.7732                 | 0.5479                 |
+| 2.1571 | 2100 | 0.3982        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 2.2598 | 2200 | 0.3073        | 0.7969                  | 0.6652                  | 0.6005                  | 0.7625                  | 0.8054                 | 0.7734                 | 0.5493                 |
+| 2.3624 | 2300 | 0.383         | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 2.4651 | 2400 | 0.3687        | 0.7925                  | 0.6690                  | 0.5987                  | 0.7583                  | 0.8081                 | 0.7735                 | 0.5477                 |
+| 2.5678 | 2500 | 0.3472        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 2.6704 | 2600 | 0.3557        | 0.7956                  | 0.6758                  | 0.6019                  | 0.7659                  | 0.8082                 | 0.7767                 | 0.5491                 |
+| 2.7731 | 2700 | 0.3527        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 2.8758 | 2800 | 0.3446        | 0.7945                  | 0.6719                  | 0.6020                  | 0.7616                  | 0.8124                 | 0.7818                 | 0.5496                 |
+| 2.9784 | 2900 | 0.3566        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 3.0821 | 3000 | 0.3252        | 0.7948                  | 0.6682                  | 0.6025                  | 0.7617                  | 0.8152                 | 0.7848                 | 0.5516                 |
+| 3.1848 | 3100 | 0.2968        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 3.2875 | 3200 | 0.2962        | 0.7953                  | 0.6717                  | 0.6086                  | 0.7613                  | 0.8110                 | 0.7824                 | 0.5482                 |
+| 3.3901 | 3300 | 0.3084        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 3.4928 | 3400 | 0.2909        | 0.7940                  | 0.6634                  | 0.6023                  | 0.7615                  | 0.8138                 | 0.7822                 | 0.5457                 |
+| 3.5955 | 3500 | 0.2964        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 3.6982 | 3600 | 0.3193        | 0.7960                  | 0.6635                  | 0.6070                  | 0.7534                  | 0.8164                 | 0.7844                 | 0.5467                 |
+| 3.8008 | 3700 | 0.3514        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 3.9035 | 3800 | 0.3147        | 0.7973                  | 0.6696                  | 0.6125                  | 0.7616                  | 0.8176                 | 0.7885                 | 0.5469                 |
+| 4.0062 | 3900 | 0.2738        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 4.1088 | 4000 | 0.2842        | 0.7960                  | 0.6672                  | 0.6082                  | 0.7536                  | 0.8174                 | 0.7891                 | 0.5479                 |
+| 4.2115 | 4100 | 0.2739        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 4.3142 | 4200 | 0.2704        | 0.7979                  | 0.6681                  | 0.6111                  | 0.7540                  | 0.8180                 | 0.7891                 | 0.5476                 |
+| 4.4168 | 4300 | 0.2529        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 4.5195 | 4400 | 0.272         | 0.7968                  | 0.6685                  | 0.6087                  | 0.7564                  | 0.8185                 | 0.7901                 | 0.5476                 |
+| 4.6222 | 4500 | 0.3           | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 4.7248 | 4600 | 0.2598        | 0.7972                  | 0.6675                  | 0.6072                  | 0.7556                  | 0.8190                 | 0.7909                 | 0.5478                 |
+| 4.8275 | 4700 | 0.3101        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
+| 4.9302 | 4800 | 0.2524        | 0.7970                  | 0.6681                  | 0.6071                  | 0.7554                  | 0.8195                 | 0.7914                 | 0.5474                 |
+
+
+### Framework Versions
+- Python: 3.11.11
+- Sentence Transformers: 4.1.0
+- Transformers: 4.51.2
+- PyTorch: 2.6.0+cu124
+- Accelerate: 1.6.0
+- Datasets: 3.5.0
+- Tokenizers: 0.21.1
+
+## Citation
+
+### BibTeX
+
+#### Sentence Transformers
+```bibtex
+@inproceedings{reimers-2019-sentence-bert,
+    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
+    author = "Reimers, Nils and Gurevych, Iryna",
+    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
+    month = "11",
+    year = "2019",
+    publisher = "Association for Computational Linguistics",
+    url = "https://arxiv.org/abs/1908.10084",
+}
+```
+
+#### GISTEmbedLoss
+```bibtex
+@misc{solatorio2024gistembed,
+    title={GISTEmbed: Guided In-sample Selection of Training Negatives for Text Embedding Fine-tuning},
+    author={Aivin V. Solatorio},
+    year={2024},
+    eprint={2402.16829},
+    archivePrefix={arXiv},
+    primaryClass={cs.LG}
+}
+```
+
+<!--
+## Glossary
+
+*Clearly define terms in order to be accessible across audiences.*
+-->
+
+<!--
+## Model Card Authors
+
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
+
+<!--
+## Model Card Contact
+
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

checkpoint-4800/config.json

@@ -0,0 +1,49 @@
+{
+  "architectures": [
+    "NewModel"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "auto_map": {
+    "AutoConfig": "Alibaba-NLP/new-impl--configuration.NewConfig",
+    "AutoModel": "Alibaba-NLP/new-impl--modeling.NewModel",
+    "AutoModelForMaskedLM": "Alibaba-NLP/new-impl--modeling.NewForMaskedLM",
+    "AutoModelForMultipleChoice": "Alibaba-NLP/new-impl--modeling.NewForMultipleChoice",
+    "AutoModelForQuestionAnswering": "Alibaba-NLP/new-impl--modeling.NewForQuestionAnswering",
+    "AutoModelForSequenceClassification": "Alibaba-NLP/new-impl--modeling.NewForSequenceClassification",
+    "AutoModelForTokenClassification": "Alibaba-NLP/new-impl--modeling.NewForTokenClassification"
+  },
+  "classifier_dropout": 0.0,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "layer_norm_type": "layer_norm",
+  "logn_attention_clip1": false,
+  "logn_attention_scale": false,
+  "max_position_embeddings": 8192,
+  "model_type": "new",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pack_qkv": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "rope",
+  "rope_scaling": {
+    "factor": 8.0,
+    "type": "ntk"
+  },
+  "rope_theta": 20000,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.2",
+  "type_vocab_size": 1,
+  "unpad_inputs": false,
+  "use_memory_efficient_attention": false,
+  "vocab_size": 250048
+}

checkpoint-4800/config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "4.1.0",
+    "transformers": "4.51.2",
+    "pytorch": "2.6.0+cu124"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

checkpoint-4800/modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

checkpoint-4800/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18f7282ab1794e08c4b4b08e435d1c280f8ffd3b854395a11b620a7472776d29
+size 15958

checkpoint-4800/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c143c5f287168ca43f876b42c855fa8ed58ac53946ea92028d4871161e59c35
+size 988

checkpoint-4800/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:771de1c33cd39219f8ff19435c56de0d3d8a374202466259d71fb8e3c5a3e7c4
+size 1064

checkpoint-4800/sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 512,
+  "do_lower_case": false
+}

checkpoint-4800/special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-4800/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:883b037111086fd4dfebbbc9b7cee11e1517b5e0c0514879478661440f137085
+size 17082987

checkpoint-4800/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 8192,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizerFast",
+  "unk_token": "<unk>"
+}

checkpoint-4800/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40c33010f3b5232b8f1e5876490b57675597dbc48a2cd0560f16d15d56ebb4e1
+size 5624

eval/Information-Retrieval_evaluation_full_es_results.csv

@@ -0,0 +1,25 @@
+epoch,steps,cosine-Accuracy@1,cosine-Accuracy@20,cosine-Accuracy@50,cosine-Accuracy@100,cosine-Accuracy@150,cosine-Accuracy@200,cosine-Precision@1,cosine-Recall@1,cosine-Precision@20,cosine-Recall@20,cosine-Precision@50,cosine-Recall@50,cosine-Precision@100,cosine-Recall@100,cosine-Precision@150,cosine-Recall@150,cosine-Precision@200,cosine-Recall@200,cosine-MRR@1,cosine-MRR@20,cosine-MRR@50,cosine-MRR@100,cosine-MRR@150,cosine-MRR@200,cosine-NDCG@1,cosine-NDCG@20,cosine-NDCG@50,cosine-NDCG@100,cosine-NDCG@150,cosine-NDCG@200,cosine-MAP@1,cosine-MAP@20,cosine-MAP@50,cosine-MAP@100,cosine-MAP@150,cosine-MAP@200,cosine-MAP@500
+0.2053388090349076,200,0.12432432432432433,1.0,1.0,1.0,1.0,1.0,0.12432432432432433,0.0036542148230633313,0.5602702702702703,0.3828077426666972,0.38335135135135134,0.5653252324643432,0.2503783783783784,0.6800221958461447,0.18681081081081083,0.7388915948699079,0.149972972972973,0.7804837951694225,0.12432432432432433,0.5567567567567567,0.5567567567567567,0.5567567567567567,0.5567567567567567,0.5567567567567567,0.12432432432432433,0.6019271564713847,0.5833730603752632,0.6139937306765353,0.6433585312593553,0.6632845626952335,0.12432432432432433,0.4633435867906743,0.4188093941413692,0.42609267111605426,0.44016851054024486,0.4482545851085946,0.4607662221292372
+0.4106776180698152,400,0.11891891891891893,1.0,1.0,1.0,1.0,1.0,0.11891891891891893,0.0035436931012884127,0.5683783783783785,0.3810462671828017,0.38324324324324327,0.5543993842372753,0.24810810810810813,0.6700411876973422,0.18515315315315314,0.7311788302888577,0.14832432432432432,0.7678363663093309,0.11891891891891893,0.5545045045045045,0.5545045045045045,0.5545045045045045,0.5545045045045045,0.5545045045045045,0.11891891891891893,0.608829799528409,0.5811778113289973,0.6102432927126396,0.6401874966927388,0.6585608274394179,0.11891891891891893,0.4730257073536956,0.4194802635669368,0.4252576537009097,0.4385610105081702,0.44599736870498363,0.4586336991926438
+0.6160164271047228,600,0.11351351351351352,1.0,1.0,1.0,1.0,1.0,0.11351351351351352,0.0035045234969014166,0.5713513513513514,0.3846125291226745,0.3913513513513514,0.5682209903507661,0.2525945945945946,0.6778875140787548,0.1881081081081081,0.738073200978772,0.15154054054054053,0.7822033748058627,0.11351351351351352,0.5509009009009009,0.5509009009009009,0.5509009009009009,0.5509009009009009,0.5509009009009009,0.11351351351351352,0.6120507278465956,0.589300707007821,0.615928427138543,0.6457992728749911,0.667053226562886,0.11351351351351352,0.47819284350499,0.4243332984656309,0.4304507877187128,0.44417898246014825,0.4525438357699329,0.46507797386754063
+0.8213552361396304,800,0.12972972972972974,1.0,1.0,1.0,1.0,1.0,0.12972972972972974,0.0036933844274503265,0.5781081081081081,0.3874647857418556,0.39372972972972975,0.5727008693667749,0.2557837837837838,0.6842591787966371,0.1899099099099099,0.7400278311282196,0.1514594594594595,0.7809088317561025,0.12972972972972974,0.5608108108108109,0.5608108108108109,0.5608108108108109,0.5608108108108109,0.5608108108108109,0.12972972972972974,0.6199466914696183,0.5960674362052089,0.6240359667874307,0.6520216816558552,0.6710916559047866,0.12972972972972974,0.4878817205058847,0.4341970857400079,0.4408342359843624,0.45414196691999603,0.4614165994644783,0.47385564807420766
+1.0266940451745379,1000,0.12432432432432433,1.0,1.0,1.0,1.0,1.0,0.12432432432432433,0.0036231843572502565,0.5637837837837838,0.37729156169584205,0.3885405405405405,0.5633539830825378,0.25464864864864867,0.6827730159650425,0.18990990990990994,0.7428633667293452,0.15132432432432433,0.7782685040521145,0.12432432432432433,0.5563063063063063,0.5563063063063063,0.5563063063063063,0.5563063063063063,0.5563063063063063,0.12432432432432433,0.6057777177642741,0.5867260726659175,0.6183196404646596,0.6481962270281353,0.6659059109179445,0.12432432432432433,0.4687261860511995,0.42180542179418523,0.4308714867841366,0.4446949532622736,0.45192025430903376,0.46527408086342625
+1.2320328542094456,1200,0.12432432432432433,1.0,1.0,1.0,1.0,1.0,0.12432432432432433,0.0036138931714884822,0.577027027027027,0.3847769295694512,0.38789189189189194,0.5614675431439459,0.25416216216216214,0.6788995357226216,0.1912792792792793,0.7447525709656728,0.15318918918918917,0.7841950250873984,0.12432432432432433,0.5563063063063063,0.5563063063063063,0.5563063063063063,0.5563063063063063,0.5563063063063063,0.12432432432432433,0.6153010648078737,0.5862024056553702,0.6170116332997596,0.6500916277248869,0.6695594700373524,0.12432432432432433,0.4795409082105716,0.42295585561484256,0.430282617284781,0.4456649970867384,0.4534754614662622,0.46568048911518123
+1.4373716632443532,1400,0.12432432432432433,1.0,1.0,1.0,1.0,1.0,0.12432432432432433,0.0036542148230633313,0.5778378378378378,0.3854462956207493,0.3930810810810811,0.5718241254218704,0.25702702702702707,0.6876874645193202,0.19196396396396398,0.7494223714305853,0.15375675675675676,0.792200813255954,0.12432432432432433,0.5563063063063063,0.5563063063063063,0.5563063063063063,0.5563063063063063,0.5563063063063063,0.12432432432432433,0.6183362743387226,0.5942702286222415,0.6245437474082477,0.6553581121410758,0.6756783811750192,0.12432432432432433,0.48462670819493664,0.4313917915592608,0.4396814925285873,0.4540585313589766,0.46184599750190675,0.47440674302762886
+1.6427104722792607,1600,0.11351351351351352,1.0,1.0,1.0,1.0,1.0,0.11351351351351352,0.0035045234969014166,0.5764864864864865,0.3838299041397214,0.3923243243243243,0.5676927670554055,0.2550810810810811,0.6800509517344185,0.19102702702702704,0.7443262071007248,0.15316216216216216,0.7883305977043269,0.11351351351351352,0.551981981981982,0.551981981981982,0.551981981981982,0.551981981981982,0.551981981981982,0.11351351351351352,0.6164256669688939,0.5912816216435999,0.6197132420680798,0.6514620845615328,0.6723348835622636,0.11351351351351352,0.4822334196423875,0.428689300381166,0.4358240738421247,0.45072644527221695,0.45843672035723626,0.47144338596575885
+1.8480492813141685,1800,0.12972972972972974,1.0,1.0,1.0,1.0,1.0,0.12972972972972974,0.0037413987812150314,0.5781081081081081,0.3843655271102247,0.39178378378378387,0.5676845000312233,0.2542702702702703,0.6787154918207249,0.18785585585585585,0.7320225875719449,0.15113513513513513,0.7761507059670063,0.12972972972972974,0.5603603603603604,0.5603603603603604,0.5603603603603604,0.5603603603603604,0.5603603603603604,0.12972972972972974,0.6185956862201957,0.5911825957843169,0.619072389909614,0.6455432274603132,0.6667655327783534,0.12972972972972974,0.4837965937849941,0.4285331090232545,0.43606519106346137,0.4482049475328162,0.4562691988973938,0.46885714095350695
+2.0544147843942504,2000,0.12432432432432433,1.0,1.0,1.0,1.0,1.0,0.12432432432432433,0.0036138931714884822,0.5754054054054053,0.38145806817133593,0.38724324324324316,0.5609230769799306,0.25313513513513514,0.6732219748754285,0.1890810810810811,0.7352593490969169,0.15135135135135136,0.7750850885027253,0.12432432432432433,0.5572072072072072,0.5572072072072072,0.5572072072072072,0.5572072072072072,0.5572072072072072,0.12432432432432433,0.6150465394619441,0.5856947806997886,0.6145141363648746,0.6453998709917663,0.6647428229280057,0.12432432432432433,0.4825873237596062,0.4233448232888883,0.43062097640739355,0.44500664950380214,0.4524896138305996,0.4654736935141093
+2.259753593429158,2200,0.11891891891891893,1.0,1.0,1.0,1.0,1.0,0.11891891891891893,0.0035747235671014874,0.5689189189189189,0.37777386748934544,0.3911351351351352,0.5649004100538018,0.25275675675675674,0.6795926106033889,0.18738738738738742,0.732879504902313,0.1511081081081081,0.7801094330153461,0.11891891891891893,0.554954954954955,0.554954954954955,0.554954954954955,0.554954954954955,0.554954954954955,0.11891891891891893,0.6102156454096861,0.5880185911691195,0.6157958581477553,0.6430878006010147,0.6652050601478975,0.11891891891891893,0.47682238898990137,0.42447626539918315,0.4292496912787929,0.4423464730434234,0.4509245941088909,0.46326314665597734
+2.465092402464066,2400,0.12972972972972974,1.0,1.0,1.0,1.0,1.0,0.12972972972972974,0.0036933844274503265,0.5694594594594594,0.37897271285529815,0.38951351351351354,0.564877405689267,0.2525945945945946,0.6775440114898331,0.1889009009009009,0.7399484000008381,0.15232432432432433,0.7852643837938816,0.12972972972972974,0.5603603603603604,0.5603603603603604,0.5603603603603604,0.5603603603603604,0.5603603603603604,0.12972972972972974,0.6114452843733574,0.5885739212092884,0.6163707400008701,0.6471826727296124,0.6690296055702684,0.12972972972972974,0.4778421789596433,0.42528298846411233,0.4308215112766512,0.4453858074670597,0.4540712408593371,0.4662322432529058
+2.6704312114989732,2600,0.13513513513513514,1.0,1.0,1.0,1.0,1.0,0.13513513513513514,0.0037805683856020266,0.5689189189189189,0.37980549211286346,0.39156756756756755,0.5654990665744473,0.2554054054054054,0.6811080928479146,0.1920720720720721,0.7500526739804151,0.15478378378378377,0.7971983411426202,0.13513513513513514,0.5630630630630631,0.5630630630630631,0.5630630630630631,0.5630630630630631,0.5630630630630631,0.13513513513513514,0.6112694350799244,0.5897596950997224,0.6196123237451338,0.653341969847444,0.6757815538442021,0.13513513513513514,0.4768630502305793,0.4268490797781516,0.43438544166855364,0.4498742166248682,0.45867889167253034,0.4703139514013845
+2.875770020533881,2800,0.12972972972972974,1.0,1.0,1.0,1.0,1.0,0.12972972972972974,0.0037413987812150314,0.5759459459459461,0.38642757375013415,0.3905945945945946,0.5678636581736557,0.25335135135135134,0.6828369327276755,0.19149549549549547,0.7494392702606744,0.1528108108108108,0.7876309603981632,0.12972972972972974,0.5612612612612613,0.5612612612612613,0.5612612612612613,0.5612612612612613,0.5612612612612613,0.12972972972972974,0.6166342865591007,0.5902204952624381,0.6193734266318873,0.6531118980314357,0.6718916215504982,0.12972972972972974,0.4825471418519291,0.42696486553261526,0.4331297275336443,0.4492308538620596,0.4566434936651272,0.4686210351280788
+3.082135523613963,3000,0.12432432432432433,1.0,1.0,1.0,1.0,1.0,0.12432432432432433,0.0036138931714884822,0.5732432432432432,0.3843298086450538,0.38875675675675686,0.5650294350649707,0.25416216216216214,0.6803318262694354,0.1910630630630631,0.7403401943726319,0.15264864864864863,0.779930588965831,0.12432432432432433,0.5581081081081081,0.5581081081081081,0.5581081081081081,0.5581081081081081,0.5581081081081081,0.12432432432432433,0.6143008527055751,0.5877390176744759,0.6177618735749928,0.648977793940304,0.6681685872747991,0.12432432432432433,0.4785583292524849,0.4243560892850918,0.4318640928093425,0.4471005875068474,0.45439053305098065,0.46665216860447767
+3.2874743326488707,3200,0.12432432432432433,1.0,1.0,1.0,1.0,1.0,0.12432432432432433,0.0036619075252531876,0.571081081081081,0.3828514779996719,0.39081081081081087,0.5673342901285358,0.2558378378378378,0.6844506535508201,0.19210810810810813,0.7483366539961698,0.1532972972972973,0.7878739392122067,0.12432432432432433,0.5581081081081081,0.5581081081081081,0.5581081081081081,0.5581081081081081,0.5581081081081081,0.12432432432432433,0.6127977853629571,0.5896774300207103,0.6205913187119861,0.652649303380801,0.6717100228964664,0.12432432432432433,0.4776124239982684,0.42680207356106176,0.4345050542016339,0.4495238771603171,0.45698068155359556,0.468967880585077
+3.4928131416837784,3400,0.12972972972972974,1.0,1.0,1.0,1.0,1.0,0.12972972972972974,0.003701077129640182,0.567027027027027,0.3804982136664571,0.3875675675675676,0.5629699580592333,0.25081081081081086,0.6707062354999778,0.1889009009009009,0.7368379061779298,0.15054054054054056,0.7766992539904688,0.12972972972972974,0.5608108108108109,0.5608108108108109,0.5608108108108109,0.5608108108108109,0.5608108108108109,0.12972972972972974,0.6089336440451314,0.5856625822268604,0.6117458478660927,0.6445114367692948,0.6634236875631417,0.12972972972972974,0.4730243382102379,0.4222040964295926,0.427053097765836,0.4419405854099873,0.44898785309975947,0.46116246384135534
+3.6981519507186857,3600,0.12972972972972974,1.0,1.0,1.0,1.0,1.0,0.12972972972972974,0.0037413987812150314,0.5678378378378378,0.3827628869405309,0.3863783783783784,0.5631375966688502,0.24967567567567567,0.6708095319711836,0.18807207207207208,0.7352302478861616,0.1507027027027027,0.7771325965481749,0.12972972972972974,0.5603603603603604,0.5603603603603604,0.5603603603603604,0.5603603603603604,0.5603603603603604,0.12972972972972974,0.6104723243523141,0.5851867564637715,0.6111351459739588,0.6434844421459089,0.6635444455655303,0.12972972972972974,0.47463453452331006,0.4217990464159235,0.4265057087682277,0.440835085807051,0.44854541040657625,0.4606477333412848
+3.9034907597535935,3800,0.12972972972972974,1.0,1.0,1.0,1.0,1.0,0.12972972972972974,0.0037413987812150314,0.572972972972973,0.3863687030094713,0.39156756756756755,0.5684964616110271,0.25243243243243246,0.6746797199000947,0.1914234234234234,0.7467802963396935,0.1522972972972973,0.7847156758414823,0.12972972972972974,0.5603603603603604,0.5603603603603604,0.5603603603603604,0.5603603603603604,0.5603603603603604,0.12972972972972974,0.6146096492130458,0.5903942165828612,0.6157380431058012,0.6513020633067227,0.6695734441770614,0.12972972972972974,0.47857516088611635,0.42741121568687945,0.43204147433500506,0.44812154826154116,0.45515154391733104,0.467280855272183
+4.108829568788501,4000,0.12972972972972974,1.0,1.0,1.0,1.0,1.0,0.12972972972972974,0.0037413987812150314,0.5705405405405405,0.38432915927625627,0.38962162162162167,0.5663097940153319,0.25140540540540546,0.6710180189388714,0.19012612612612612,0.7443549924512646,0.15154054054054056,0.7804985217049148,0.12972972972972974,0.5608108108108109,0.5608108108108109,0.5608108108108109,0.5608108108108109,0.5608108108108109,0.12972972972972974,0.6133809590566169,0.5888378318443163,0.613553130716134,0.6492700673561147,0.6672020616803231,0.12972972972972974,0.47928087268629077,0.4265150109477007,0.4308614258675324,0.446315567522346,0.45361884446786194,0.46587892353181215
+4.314168377823409,4200,0.12972972972972974,1.0,1.0,1.0,1.0,1.0,0.12972972972972974,0.0037413987812150314,0.5735135135135134,0.3850053775723816,0.3912432432432432,0.5678708571543062,0.2531351351351352,0.6771132401665688,0.19113513513513514,0.7476366668984507,0.15186486486486486,0.7806646181068078,0.12972972972972974,0.5608108108108109,0.5608108108108109,0.5608108108108109,0.5608108108108109,0.5608108108108109,0.12972972972972974,0.6155696219376317,0.5902714649088991,0.6166603984916751,0.6514414937889701,0.6681110549873654,0.12972972972972974,0.4821585422089324,0.4278073015090324,0.4325091891776662,0.4481236866241766,0.45495240914630236,0.4674583582676571
+4.519507186858316,4400,0.12972972972972974,1.0,1.0,1.0,1.0,1.0,0.12972972972972974,0.0037413987812150314,0.5721621621621621,0.38564412906376994,0.3898378378378379,0.56634717829376,0.25248648648648647,0.6751207657229007,0.19001801801801804,0.7429721526766266,0.15216216216216216,0.782741009344735,0.12972972972972974,0.5603603603603604,0.5603603603603604,0.5603603603603604,0.5603603603603604,0.5603603603603604,0.12972972972972974,0.6146062832951104,0.5888430944817052,0.6153911974508461,0.6488811790186049,0.668484227215925,0.12972972972972974,0.48065989256661584,0.4260414587944102,0.4313410890675031,0.44627409433309473,0.45409073457648325,0.4664141280463215
+4.724845995893224,4600,0.12432432432432433,1.0,1.0,1.0,1.0,1.0,0.12432432432432433,0.0036619075252531876,0.5713513513513514,0.3842833355443445,0.3888648648648649,0.5650012903557396,0.25194594594594594,0.6742574573080582,0.18998198198198196,0.7433217612578467,0.1519189189189189,0.7815387878511015,0.12432432432432433,0.5576576576576577,0.5576576576576577,0.5576576576576577,0.5576576576576577,0.5576576576576577,0.12432432432432433,0.6134037350149425,0.587765249332833,0.6145100789008344,0.6485708474409041,0.6674981723654128,0.12432432432432433,0.47936111065720205,0.4252592911005701,0.4304825507648424,0.4457575975367371,0.4532981716560443,0.4657478115586777
+4.930184804928132,4800,0.12432432432432433,1.0,1.0,1.0,1.0,1.0,0.12432432432432433,0.0036619075252531876,0.5718918918918919,0.3842245968041533,0.3885405405405405,0.5640822196868902,0.25172972972972973,0.6741986120580108,0.1904864864864865,0.7463851968088967,0.1521891891891892,0.7825399601398452,0.12432432432432433,0.5581081081081081,0.5581081081081081,0.5581081081081081,0.5581081081081081,0.5581081081081081,0.12432432432432433,0.6139182209948354,0.5873893466818746,0.6144038475288277,0.6498632077214272,0.6680602466150343,0.12432432432432433,0.47988875190050484,0.4249833337950364,0.430155652024808,0.4458862132745998,0.45334655744992447,0.4656066165331343

eval/Information-Retrieval_evaluation_mix_de_results.csv

@@ -0,0 +1,25 @@
+epoch,steps,cosine-Accuracy@1,cosine-Accuracy@20,cosine-Accuracy@50,cosine-Accuracy@100,cosine-Accuracy@150,cosine-Accuracy@200,cosine-Precision@1,cosine-Recall@1,cosine-Precision@20,cosine-Recall@20,cosine-Precision@50,cosine-Recall@50,cosine-Precision@100,cosine-Recall@100,cosine-Precision@150,cosine-Recall@150,cosine-Precision@200,cosine-Recall@200,cosine-MRR@1,cosine-MRR@20,cosine-MRR@50,cosine-MRR@100,cosine-MRR@150,cosine-MRR@200,cosine-NDCG@1,cosine-NDCG@20,cosine-NDCG@50,cosine-NDCG@100,cosine-NDCG@150,cosine-NDCG@200,cosine-MAP@1,cosine-MAP@20,cosine-MAP@50,cosine-MAP@100,cosine-MAP@150,cosine-MAP@200,cosine-MAP@500
+0.2053388090349076,200,0.5824232969318772,0.890795631825273,0.9344773790951638,0.9625585023400937,0.9713988559542381,0.9755590223608944,0.5824232969318772,0.21945744496446523,0.10995839833593343,0.8010140405616224,0.04770670826833075,0.8672560235742762,0.025023400936037447,0.9088503891032834,0.017067082683307328,0.928888523962011,0.013003120124804996,0.9424478382644077,0.5824232969318772,0.6686146655052267,0.6700220401420418,0.6704225963707373,0.6704949320904295,0.6705196374407493,0.5824232969318772,0.6671050419586103,0.6853068462793799,0.6945910686245909,0.6985990036687157,0.7011459404427492,0.5824232969318772,0.5804077947241746,0.5851378642364741,0.5864292325266649,0.5868080085531887,0.5870045172476335,0.587255698964039
+0.4106776180698152,400,0.6058242329693188,0.9001560062402496,0.9438377535101404,0.9661986479459178,0.9786791471658867,0.984919396775871,0.6058242329693188,0.22767377361761137,0.11453458138325531,0.8328913156526262,0.049277171086843485,0.8950078003120124,0.025501820072802914,0.9252310443294924,0.01738949557982319,0.9456258952112471,0.013208528341133648,0.9575863736303838,0.6058242329693188,0.6916097716264229,0.6930731873244362,0.6933861079128469,0.6934856963760448,0.6935223150466893,0.6058242329693188,0.6978257678791413,0.7148134512905183,0.7215656325178118,0.7256044427041147,0.7278106695507355,0.6058242329693188,0.6136914531088427,0.6180001645069843,0.6189322601089229,0.6193042781784874,0.6194584295615786,0.6196563244482027
+0.6160164271047228,600,0.6136245449817993,0.9027561102444098,0.9511180447217888,0.9724388975559022,0.9823192927717108,0.9880395215808633,0.6136245449817993,0.2296931877275091,0.1156786271450858,0.8399982665973306,0.04980759230369215,0.9041254983532674,0.025803432137285493,0.9360807765643959,0.01750390015600624,0.9516220999717182,0.013304732189287575,0.9633773070221053,0.6136245449817993,0.6967436196163437,0.6983767208927972,0.6986755582030411,0.6987550736361285,0.6987871879396401,0.6136245449817993,0.7039015030314165,0.7214196598697487,0.7285557386019151,0.731660833854203,0.7338649218512935,0.6136245449817993,0.6199336468860212,0.6243059725986513,0.6252932577240808,0.6255849080363306,0.6257398204144359,0.6259188350215349
+0.8213552361396304,800,0.6198647945917837,0.9199167966718669,0.9599583983359334,0.9771190847633905,0.984919396775871,0.9890795631825273,0.6198647945917837,0.23226729069162766,0.11835673426937077,0.8603137458831687,0.05055642225689029,0.9172906916276651,0.026058242329693195,0.9446177847113885,0.01765643959091697,0.9596550528687814,0.01338013520540822,0.9689127915993833,0.6198647945917837,0.7067310519072951,0.7080323481502147,0.7082793254956429,0.7083435341245732,0.708367858453663,0.6198647945917837,0.7179147930131626,0.7335369696209415,0.7396898870736865,0.7426721836970417,0.7444074102762905,0.6198647945917837,0.6325265171671292,0.6365112891787109,0.6373788268173515,0.6376617577798908,0.6377881327329524,0.6379357654928159
+1.0266940451745379,1000,0.641185647425897,0.9261570462818512,0.9641185647425897,0.9817992719708788,0.9875195007800313,0.9932397295891836,0.641185647425897,0.2409169700121338,0.11957878315132604,0.868322066215982,0.05092043681747271,0.9239296238516207,0.026287051482059287,0.953371468192061,0.017784711388455537,0.9668053388802219,0.013426937077483103,0.9728996177390954,0.641185647425897,0.723512152520197,0.7247732383573519,0.7250213151606678,0.7250670172565229,0.725101115499198,0.641185647425897,0.7331582819294082,0.7484853776582061,0.7550159668996201,0.7577049278428191,0.7588390730905107,0.641185647425897,0.6507883293963721,0.6548526090599666,0.6557655896025038,0.6560320335460608,0.6561000390732701,0.6562403086721103
+1.2320328542094456,1200,0.6469058762350494,0.9292771710868435,0.9625585023400937,0.9812792511700468,0.9895995839833593,0.9927197087883516,0.6469058762350494,0.24236436124111632,0.11991679667186687,0.8719188767550701,0.05069162766510661,0.9197694574449645,0.026261050442017687,0.9518114057895649,0.017791644999133292,0.9665726979956392,0.013450338013520543,0.9738529892072876,0.6469058762350494,0.7269400985028893,0.7280394635287579,0.7283120754443227,0.7283774712480807,0.7283958171968078,0.6469058762350494,0.7376190451778748,0.7508860063210446,0.7580843131044783,0.7610353115310864,0.7623967599316989,0.6469058762350494,0.6568766292733668,0.6603301597824439,0.6613474042139721,0.661638250077651,0.6617378656761332,0.661867663149717
+1.4373716632443532,1400,0.6531461258450338,0.9308372334893396,0.9651586063442538,0.984399375975039,0.9906396255850234,0.9942797711908476,0.6531461258450338,0.24460045068469405,0.1204368174726989,0.8760703761483793,0.051170046801872086,0.9280464551915409,0.026417056682267296,0.9580083203328134,0.017847113884555378,0.970055468885422,0.013497139885595427,0.9776391055642226,0.6531461258450338,0.7301427290607674,0.73127221921329,0.7315515852685716,0.7316041804827806,0.7316258311778456,0.6531461258450338,0.7400846276876067,0.7544954223077399,0.7611232562936333,0.7635508214909821,0.7649716494639359,0.6531461258450338,0.6582591347527325,0.6620448798560229,0.6629532720507669,0.6631839344942984,0.6632878487109075,0.663394290277717
+1.6427104722792607,1600,0.6531461258450338,0.9282371294851794,0.9672386895475819,0.984399375975039,0.9916796671866874,0.9927197087883516,0.6531461258450338,0.24526781071242848,0.12061882475299011,0.876269717455365,0.051305252210088415,0.930516553995493,0.026417056682267296,0.9579216501993414,0.017867914716588662,0.9713121858207663,0.013478939157566308,0.9765990639625585,0.6531461258450338,0.7297931034955463,0.7310949829556551,0.7313458635342546,0.7314015672242672,0.7314070148575023,0.6531461258450338,0.7411519844144333,0.7562323464980976,0.7623550920981482,0.7650222597446915,0.7660148980251885,0.6531461258450338,0.6598824970349082,0.6638312074627658,0.6647182775063895,0.6649656128823839,0.6650428618726513,0.6651608439550554
+1.8480492813141685,1800,0.655746229849194,0.9313572542901716,0.967758710348414,0.984399375975039,0.9901196047841914,0.9927197087883516,0.655746229849194,0.24639452244756457,0.12121684867394694,0.8807245623158259,0.05134685387415497,0.9323799618651413,0.026427457098283938,0.9584850060669092,0.01785404749523314,0.97040214941931,0.013471138845553827,0.9760790431617264,0.655746229849194,0.7359661579803044,0.7371839757004826,0.7374316676183734,0.7374778751542778,0.7374937192664236,0.655746229849194,0.747961593820956,0.7620851284167808,0.7679714384557973,0.7703599291055326,0.7714144528908776,0.655746229849194,0.6682485275594054,0.6718501706313308,0.6726831971840679,0.672906327059626,0.672984318369321,0.6730960459348426
+2.0544147843942504,2000,0.6547061882475299,0.9365574622984919,0.9713988559542381,0.983879355174207,0.9901196047841914,0.9937597503900156,0.6547061882475299,0.24629051828739817,0.12184087363494539,0.8856474258970358,0.051648465938637554,0.9372248223262264,0.026510660426417063,0.9610417750043336,0.017899115964638588,0.9730022534234704,0.013512740509620388,0.9789824926330386,0.6547061882475299,0.734953306211269,0.7360724461513224,0.7362604762082307,0.736310379668506,0.7363320594909445,0.6547061882475299,0.7501708892155533,0.7643740612112161,0.7697269409372974,0.7720989054331775,0.7732212507206273,0.6547061882475299,0.6706228544587022,0.6742958831841708,0.6750767013506579,0.6753004485993032,0.6753808341815668,0.6754764501239573
+2.259753593429158,2200,0.6495059802392096,0.9339573582943318,0.9750390015600624,0.9875195007800313,0.9895995839833593,0.9947997919916797,0.6495059802392096,0.24444444444444446,0.1220228809152366,0.8857947651239382,0.051752470098803974,0.9388282197954585,0.026583463338533547,0.9632951984746055,0.017926850407349624,0.9739989599583984,0.013551742069682791,0.9817126018374069,0.6495059802392096,0.7317406351805603,0.7330178506535835,0.7331845752525227,0.7332024734980075,0.7332323545925215,0.6495059802392096,0.749844314932409,0.7643258266456834,0.7698372693681987,0.7719596031454881,0.7733737187427536,0.6495059802392096,0.6710144415214195,0.6745997972154377,0.6754157585321406,0.6756270441179111,0.6757258475913458,0.6758073431120588
+2.465092402464066,2400,0.6521060842433697,0.9401976079043162,0.9708788351534061,0.9859594383775351,0.9906396255850234,0.9937597503900156,0.6521060842433697,0.2450078003120125,0.12259490379615184,0.891142312359161,0.05174206968278733,0.9381868608077656,0.026562662506500266,0.9625585023400937,0.017919916796671865,0.9740856300918704,0.01352834113364535,0.9802392095683827,0.6521060842433697,0.7349706584794825,0.7360203516763673,0.7362484971298274,0.7362874510511505,0.7363052831644673,0.6521060842433697,0.7514313213364424,0.7645915252490415,0.7700800079311404,0.7723411044676748,0.7734871450981708,0.6521060842433697,0.67003898125552,0.6735751668034196,0.6743691079556863,0.6745756303601855,0.6746624975062249,0.6747632068113166
+2.6704312114989732,2600,0.6536661466458659,0.9381175247009881,0.9703588143525741,0.9854394175767031,0.9916796671866874,0.9958398335933437,0.6536661466458659,0.24587450164673252,0.12282891315652626,0.8930750563355867,0.05167966718668748,0.9377968452071417,0.026552262090483628,0.9624284971398855,0.017933784018027386,0.9747789911596464,0.013541341653666149,0.9811925810365748,0.6536661466458659,0.7373857427749009,0.7385000464999506,0.738719487795195,0.7387713118408488,0.7387956405134187,0.6536661466458659,0.755149068100915,0.7675543097789403,0.7731235795059239,0.7755614120877131,0.7767483456621986,0.6536661466458659,0.6752645042438818,0.6784554571817863,0.6792712280157911,0.6794904476645582,0.6795751687891997,0.6796700471093178
+2.875770020533881,2800,0.6651066042641706,0.9412376495059802,0.9734789391575663,0.984399375975039,0.9921996879875195,0.9942797711908476,0.6651066042641706,0.25062402496099845,0.12327093083723348,0.8951118044721789,0.05196047841913678,0.9431270584156699,0.026547061882475305,0.9621251516727336,0.017912983185994102,0.9737389495579823,0.01353614144565783,0.9808459005026867,0.6651066042641706,0.7447057162349396,0.7457938217093175,0.7459476857643497,0.7460107206090002,0.7460226155893531,0.6651066042641706,0.7607569908925185,0.7738642721422997,0.7782002609687475,0.7804702046847336,0.7817818016898852,0.6651066042641706,0.6824310256371793,0.685769301349588,0.6864131853857557,0.6866036842499446,0.6866997216650711,0.6868009169562614
+3.082135523613963,3000,0.6661466458658346,0.9443577743109725,0.9750390015600624,0.984919396775871,0.9916796671866874,0.9932397295891836,0.6661466458658346,0.25062402496099845,0.1234789391575663,0.896238516207315,0.052054082163286546,0.9445311145779165,0.026604264170566827,0.9641185647425897,0.017926850407349624,0.9743456404922862,0.01352834113364535,0.9801525394349107,0.6661466458658346,0.7464169509265817,0.7474550994157608,0.7476003509741266,0.7476590729610166,0.7476687655877939,0.6661466458658346,0.7640416023030964,0.7772648865502759,0.7817421536267213,0.7837612033967705,0.7848431573634226,0.6661466458658346,0.6873288696219481,0.6907802183912366,0.6914523791132502,0.6916310113321876,0.6917144768814371,0.691810994391746
+3.2874743326488707,3200,0.6645865834633385,0.9464378575143005,0.9729589183567343,0.9854394175767031,0.9895995839833593,0.9927197087883516,0.6645865834633385,0.2500173340266944,0.12334893395735828,0.896151846073843,0.051939677587103494,0.9423210261743804,0.026578263130525227,0.9635118738082856,0.017906049575316343,0.9733055988906222,0.013507540301612069,0.9787658172993586,0.6645865834633385,0.7433869700558867,0.7442863237155917,0.7444609180222659,0.7444966838015857,0.7445152574695719,0.6645865834633385,0.7619137547756507,0.7746988356255203,0.7794731762785382,0.7814274877816622,0.7824383670746612,0.6645865834633385,0.6847080148910323,0.6881316323671095,0.6888171087483478,0.6890031088980757,0.6890737606322342,0.6891753134206773
+3.4928131416837784,3400,0.6604264170566823,0.9479979199167967,0.9755590223608944,0.9869994799791991,0.9906396255850234,0.9942797711908476,0.6604264170566823,0.24819726122378227,0.12425897035881435,0.9031287918183393,0.052064482579303184,0.9446004506846941,0.02663026521060843,0.9651586063442538,0.017923383602010744,0.9740856300918702,0.01352314092563703,0.9798925290344946,0.6604264170566823,0.7411957880662449,0.7421341031933468,0.7423013773363349,0.7423339639832182,0.7423549073635346,0.6604264170566823,0.7632817895540933,0.7747278581631409,0.7793739698011521,0.7811638364681455,0.7822324273293833,0.6604264170566823,0.6844940922755857,0.6874343390709853,0.6881070773901289,0.6882828264127825,0.6883575877123549,0.6884625105227826
+3.6981519507186857,3600,0.6640665626625065,0.9479979199167967,0.9765990639625585,0.9869994799791991,0.9911596463858554,0.9942797711908476,0.6640665626625065,0.2497573236262784,0.12446697867914715,0.9039088230195874,0.05206448257930319,0.9446437857514302,0.026671866874674995,0.9667186687467498,0.017937250823366262,0.9750390015600624,0.013546541861674468,0.9817126018374068,0.6640665626625065,0.7444151495436726,0.7453714641249883,0.7455234088060528,0.7455579756624613,0.7455765617713824,0.6640665626625065,0.7651622845341957,0.7764622150886418,0.7814728174494031,0.783119149591433,0.7843548910978398,0.6640665626625065,0.686265061048045,0.6892551200216643,0.6900189954189452,0.6901706054009246,0.6902620634727198,0.6903466810311089
+3.9034907597535935,3800,0.6682267290691628,0.9474778991159646,0.9765990639625585,0.9864794591783671,0.9921996879875195,0.9947997919916797,0.6682267290691628,0.2512307158953025,0.12475299011960478,0.9057722308892355,0.05217888715548623,0.9462645172473565,0.026656266250650037,0.966371988212862,0.017982319292771706,0.9772924250303345,0.013538741549661988,0.9808459005026867,0.6682267290691628,0.749539837016351,0.7505835257894989,0.7507225998991089,0.7507702961100938,0.7507859876637466,0.6682267290691628,0.7699298794056397,0.7811815187176623,0.7856773518895132,0.787866276832638,0.7885328568032918,0.6682267290691628,0.6924317728526937,0.6953819295464787,0.6960351508135207,0.6962400021157449,0.6962837979968974,0.6963746897826547
+4.108829568788501,4000,0.6697867914716589,0.9505980239209568,0.9771190847633905,0.9859594383775351,0.9921996879875195,0.9942797711908476,0.6697867914716589,0.2517940717628705,0.12470098803952159,0.9059022360894435,0.05225169006760271,0.9474345640492287,0.026708268330733236,0.967932050615358,0.01798231929277171,0.9771190847633905,0.01353874154966199,0.9807592303692148,0.6697867914716589,0.7504302722692131,0.7513280223222801,0.7514573016845009,0.7515108675350354,0.7515238522218625,0.6697867914716589,0.770344092734726,0.7819450345813985,0.7865455025019679,0.7883807621544129,0.7890604802329748,0.6697867914716589,0.6929705838065172,0.696080766802269,0.6967651580129317,0.6969258122016383,0.6969715581100935,0.6970655432634698
+4.314168377823409,4200,0.6666666666666666,0.9479979199167967,0.9760790431617264,0.9859594383775351,0.9927197087883516,0.9947997919916797,0.6666666666666666,0.25062402496099845,0.12483099323972958,0.9064222568902757,0.05219968798751951,0.9466805338880222,0.026682267290691637,0.9669786791471658,0.017985786098110586,0.9774657652972785,0.013541341653666149,0.9810192407696308,0.6666666666666666,0.7486665934008992,0.7496295288804224,0.74976967024613,0.7498264653686212,0.7498390441909701,0.6666666666666666,0.7705186419550625,0.7817408957971655,0.786309170410984,0.7883932008449921,0.7890611279585495,0.6666666666666666,0.6933856329177108,0.6963720532834866,0.6970430360365766,0.6972336080548289,0.697279051235347,0.6973750625395665
+4.519507186858316,4400,0.6687467498699948,0.9495579823192928,0.9781591263650546,0.9864794591783671,0.9937597503900156,0.9947997919916797,0.6687467498699948,0.2516640665626625,0.1250390015600624,0.9084156699601317,0.05221008840353615,0.9471138845553821,0.026718668746749875,0.9683654012827179,0.017996186514127228,0.9779857860981105,0.013546541861674468,0.9813659213035187,0.6687467498699948,0.7497638732138926,0.7507175554997805,0.7508323831532827,0.7508936641683207,0.7509002910567728,0.6687467498699948,0.771957090473385,0.7827623591767751,0.7875734242708617,0.7894969663782526,0.7901321903376272,0.6687467498699948,0.6950013134615064,0.6978571886056382,0.6985915209847109,0.6987589388742937,0.6988064092994788,0.6989004605248843
+4.724845995893224,4600,0.6687467498699948,0.9495579823192928,0.9776391055642226,0.9864794591783671,0.9932397295891836,0.9947997919916797,0.6687467498699948,0.2518374068296065,0.1251430057202288,0.9091090310279077,0.052282891315652634,0.9482405962905183,0.026723868954758197,0.968278731149246,0.01799965331946611,0.9781591263650546,0.013541341653666149,0.9810192407696308,0.6687467498699948,0.7511103493630668,0.7520644853972484,0.75218787562777,0.7522459565052304,0.7522551943857011,0.6687467498699948,0.7729181248399849,0.7838354251194414,0.78838397650382,0.7903404232459181,0.7908776550064243,0.6687467498699948,0.6960508888943099,0.698910694860312,0.699611558838961,0.6997846710668125,0.6998222199397084,0.6999210147339264
+4.930184804928132,4800,0.6703068122724909,0.9505980239209568,0.9776391055642226,0.9864794591783671,0.9932397295891836,0.9947997919916797,0.6703068122724909,0.25235742763043856,0.1251690067602704,0.9095857167620037,0.052282891315652634,0.9482405962905183,0.026729069162766517,0.96845207141619,0.01799965331946611,0.9781591263650546,0.013541341653666149,0.9810192407696308,0.6703068122724909,0.7520307321055828,0.7529374175534339,0.7530616872072472,0.7531202644382351,0.7531293951311296,0.6703068122724909,0.7735712514376322,0.7843644592705362,0.7889444470773866,0.7908660087982327,0.791403470160319,0.6703068122724909,0.6967639778693541,0.699575457224443,0.70027844357658,0.7004487000056766,0.7004863395843564,0.7005835771389989

eval/Information-Retrieval_evaluation_mix_es_results.csv

@@ -0,0 +1,25 @@
+epoch,steps,cosine-Accuracy@1,cosine-Accuracy@20,cosine-Accuracy@50,cosine-Accuracy@100,cosine-Accuracy@150,cosine-Accuracy@200,cosine-Precision@1,cosine-Recall@1,cosine-Precision@20,cosine-Recall@20,cosine-Precision@50,cosine-Recall@50,cosine-Precision@100,cosine-Recall@100,cosine-Precision@150,cosine-Recall@150,cosine-Precision@200,cosine-Recall@200,cosine-MRR@1,cosine-MRR@20,cosine-MRR@50,cosine-MRR@100,cosine-MRR@150,cosine-MRR@200,cosine-NDCG@1,cosine-NDCG@20,cosine-NDCG@50,cosine-NDCG@100,cosine-NDCG@150,cosine-NDCG@200,cosine-MAP@1,cosine-MAP@20,cosine-MAP@50,cosine-MAP@100,cosine-MAP@150,cosine-MAP@200,cosine-MAP@500
+0.2053388090349076,200,0.6744669786791472,0.9193967758710349,0.9547581903276131,0.9786791471658867,0.9854394175767031,0.9895995839833593,0.6744669786791472,0.26115073174355546,0.11300052002080084,0.8396169180100536,0.04843473738949559,0.8969578783151325,0.02519500780031202,0.9319847460565089,0.017087883515340612,0.94801872074883,0.01293551742069683,0.9566337320159473,0.6744669786791472,0.741763195639624,0.7429306662309286,0.7432800219034473,0.7433366328877163,0.7433604279356348,0.6744669786791472,0.7283598223719706,0.7441766946642234,0.7519314012572818,0.7550733326720689,0.756655547133677,0.6744669786791472,0.6512370737218736,0.6554344055014282,0.6564948783659126,0.6568034198042897,0.6569158742390337,0.6571132869122711
+0.4106776180698152,400,0.6879875195007801,0.9386375455018201,0.96931877275091,0.9859594383775351,0.9906396255850234,0.9937597503900156,0.6879875195007801,0.26589158804447416,0.11674466978679147,0.8650286011440458,0.04972438897555903,0.9198127925117004,0.025746229849193975,0.9518460738429537,0.01735829433177327,0.9622239556248916,0.013104524180967242,0.9687588836886808,0.6879875195007801,0.7573600016494716,0.758373082976894,0.7586129872645225,0.7586521805670934,0.7586695865464829,0.6879875195007801,0.7496761044826149,0.7645910592449513,0.771678161894379,0.7737195873568836,0.7748920737782092,0.6879875195007801,0.6723890167478477,0.6763190985720952,0.6773385103067359,0.67753789966102,0.6776180675766235,0.6777703627783342
+0.6160164271047228,600,0.6916276651066042,0.9386375455018201,0.9698387935517421,0.9859594383775351,0.9901196047841914,0.9927197087883516,0.6916276651066042,0.26777232994081673,0.11757670306812272,0.8705408216328654,0.04999479979199169,0.9244669786791472,0.025767030681227255,0.9522447564569249,0.017354827526434392,0.9622326226382389,0.013112324492979721,0.9691419656786271,0.6916276651066042,0.761342948642869,0.7623647640351301,0.762602306784832,0.762635838698989,0.7626512812607942,0.6916276651066042,0.7551750332158662,0.7699635084903145,0.776150635032849,0.778075100149402,0.7793189303805319,0.6916276651066042,0.6786213376102775,0.6826339651024589,0.6835232286091564,0.683704369370875,0.6837900471429439,0.6839749487471821
+0.8213552361396304,800,0.7103484139365575,0.9427977119084764,0.96931877275091,0.9869994799791991,0.9911596463858554,0.9953198127925117,0.7103484139365575,0.2754426367530892,0.11874674986999478,0.8783584676720402,0.05051482059282372,0.9327266423990292,0.025917836713468544,0.9576183047321893,0.017431097243889755,0.9668486739469578,0.013151326053042124,0.9724128965158605,0.7103484139365575,0.7746274084028193,0.7755192305203115,0.7757896714286256,0.7758222583986994,0.7758465532110386,0.7103484139365575,0.7667662331766134,0.7817254043804741,0.7871621741197808,0.7889005540486419,0.7899230983968881,0.7103484139365575,0.6919105171080385,0.6960607070870991,0.6968051220833996,0.6969637678097483,0.6970278516736893,0.6971776567635193
+1.0266940451745379,1000,0.7165886635465418,0.9479979199167967,0.9739989599583984,0.9880395215808633,0.9916796671866874,0.9942797711908476,0.7165886635465418,0.27682935888864124,0.12007280291211647,0.8882821979545847,0.050878835153406146,0.9391315652626105,0.025990639625585028,0.9601750736696135,0.01749003293465072,0.9697607904316173,0.013187727509100368,0.9749609984399376,0.7165886635465418,0.7806461907353381,0.7815205876591033,0.7817330221665041,0.7817632650241372,0.7817790651760725,0.7165886635465418,0.7753874056135623,0.789441581396985,0.7940295021279941,0.7958516238757499,0.7968002112038809,0.7165886635465418,0.7010433442003473,0.7049146489569816,0.7055466305976777,0.7057148420462953,0.7057822673177551,0.70590198422608
+1.2320328542094456,1200,0.7160686427457098,0.9485179407176287,0.9719188767550702,0.9901196047841914,0.9932397295891836,0.9963598543941757,0.7160686427457098,0.27572864819354675,0.12048881955278211,0.891055642225689,0.05065002600104005,0.935179407176287,0.025995839833593347,0.9607210955104871,0.017496966545328476,0.9699861327786444,0.013200728029121167,0.9756751603397469,0.7160686427457098,0.778609201692751,0.7794068678456314,0.7796779018026971,0.7797046138072552,0.7797225672612155,0.7160686427457098,0.7752959106174916,0.7875021072976487,0.7930929905744307,0.7948936889372247,0.7959269355495714,0.7160686427457098,0.7008047752596147,0.7041474811963291,0.7049135025881823,0.705090223026125,0.7051595169219359,0.7052913750553237
+1.4373716632443532,1400,0.7103484139365575,0.9542381695267811,0.9719188767550702,0.9911596463858554,0.9937597503900156,0.9953198127925117,0.7103484139365575,0.2750352871257708,0.1219448777951118,0.9020107470965505,0.05075403016120646,0.9373028254463512,0.02602184087363495,0.9614404576183047,0.01747963251863408,0.9688594210435084,0.013190327613104529,0.9750303345467152,0.7103484139365575,0.7768666973118454,0.7774521252326642,0.7777311412628978,0.7777516090311071,0.7777607563891314,0.7103484139365575,0.78029413905518,0.7899589941885002,0.7952340704884101,0.7966711304082723,0.79778241351855,0.7103484139365575,0.7052870437204709,0.7079382732951186,0.7086312147232268,0.7087692465933743,0.7088501950968276,0.7089812352190901
+1.6427104722792607,1600,0.7129485179407177,0.9516380655226209,0.9750390015600624,0.9885595423816953,0.9932397295891836,0.9958398335933437,0.7129485179407177,0.2756419780600748,0.12184087363494539,0.9002686774137633,0.050847633905356224,0.9389668920090136,0.026021840873634954,0.9618478072456231,0.01752123418270064,0.971780204541515,0.013221528861154448,0.9780377881781938,0.7129485179407177,0.7797205262689477,0.7804857228147521,0.7806846568150605,0.7807244509674673,0.7807398377221492,0.7129485179407177,0.7822618234647495,0.792861555226357,0.7978245182980915,0.799733913298044,0.8008450004390294,0.7129485179407177,0.7087979133181056,0.711693498011822,0.7123657338619016,0.712539507853168,0.7126164453689728,0.7127442669566819
+1.8480492813141685,1800,0.7103484139365575,0.9537181487259491,0.9739989599583984,0.9911596463858554,0.9942797711908476,0.9958398335933437,0.7103484139365575,0.2744285961914667,0.12176287051482058,0.9000866701334721,0.05087883515340615,0.9393135725429017,0.02601144045761831,0.9613711215115271,0.01753856820939504,0.9723262263823886,0.013205928237129488,0.9761743803085456,0.7103484139365575,0.7797974381169049,0.7804575566096145,0.7807093532180903,0.7807350755839835,0.7807434365267484,0.7103484139365575,0.7816740608933163,0.7925215922661627,0.7973005051810768,0.7994341922334063,0.8001279720825101,0.7103484139365575,0.7075641957576527,0.7106282558269326,0.7112539778654484,0.711456058042057,0.7115072450201507,0.7116370106997361
+2.0544147843942504,2000,0.7207488299531981,0.9521580863234529,0.9765990639625585,0.9906396255850234,0.9953198127925117,0.9963598543941757,0.7207488299531981,0.278588762598123,0.12223088923556942,0.903111457791645,0.05103484139365575,0.9421216848673946,0.02610504420176808,0.9645779164499912,0.01756630265210608,0.9738342867048015,0.01322412896515861,0.9773877621771538,0.7207488299531981,0.7873743471935627,0.7881759932357659,0.7883771758956241,0.7884149410028269,0.7884208710645908,0.7207488299531981,0.7883196859173041,0.7990932075241108,0.8039489808553328,0.8057371014393404,0.8063877024121885,0.7207488299531981,0.7153993340854142,0.7183155449822083,0.718970651956238,0.7191336515108652,0.7191835345317726,0.7193090898334479
+2.259753593429158,2200,0.7113884555382215,0.9568382735309412,0.9765990639625585,0.9880395215808633,0.9937597503900156,0.9958398335933437,0.7113884555382215,0.2746712725651883,0.12236089443577743,0.9043508407002947,0.05110764430577225,0.943690414283238,0.026094643785751433,0.9643179060495752,0.017566302652106083,0.9738169526781072,0.013231929277171092,0.9781677933784018,0.7113884555382215,0.7835697215745069,0.7841773605961617,0.7843616437981823,0.7844127842473977,0.7844258102126603,0.7113884555382215,0.7875021890770186,0.798261026605884,0.8027649163643685,0.8046152570766616,0.8054007787239339,0.7113884555382215,0.7148513662990627,0.7178274362599699,0.718458957886724,0.7186233527190637,0.7186803161109593,0.7188227343370103
+2.465092402464066,2400,0.717628705148206,0.9578783151326054,0.9791991679667187,0.9895995839833593,0.9942797711908476,0.9973998959958398,0.717628705148206,0.27822474803754055,0.12280291211648464,0.9070376148379269,0.05125325013000521,0.945935170740163,0.02613104524180968,0.9652019414109898,0.017555902236089438,0.9730542555035535,0.013242329693187732,0.978696481192581,0.717628705148206,0.7868617407547724,0.7875289660537991,0.7876800412919529,0.7877168093489998,0.7877345598054268,0.717628705148206,0.7908125858745491,0.8013945801409573,0.8055508039227626,0.8070450080965864,0.8080600033148232,0.717628705148206,0.7184433693837136,0.7213309657706507,0.7219024909250962,0.7220323828023852,0.7221006087563977,0.7222437352425529
+2.6704312114989732,2600,0.7150286011440458,0.9589183567342694,0.9771190847633905,0.9895995839833593,0.9937597503900156,0.9953198127925117,0.7150286011440458,0.27702870019562686,0.12329693187727507,0.9100190674293639,0.05128445137805514,0.9463425203674813,0.026099843993759756,0.9640578956491592,0.017559369041428324,0.9728375801698735,0.013231929277171092,0.9778644479112498,0.7150286011440458,0.785840290964467,0.7864319813601817,0.786619238877732,0.7866537588948767,0.78666313006588,0.7150286011440458,0.7917988390977458,0.8017367449412399,0.8055669404932451,0.8072831931363913,0.8081722728713215,0.7150286011440458,0.7193801183610506,0.7221124339124323,0.7226230549387277,0.7227852441481344,0.722846886494557,0.722968388876534
+2.875770020533881,2800,0.7228289131565263,0.9594383775351014,0.9776391055642226,0.9901196047841914,0.9947997919916797,0.9968798751950078,0.7228289131565263,0.2794294628928014,0.1235829433177327,0.9124284971398857,0.051263650546021854,0.9463078523140925,0.02614664586583464,0.9660686427457098,0.0175801698734616,0.9742503033454671,0.013276131045241814,0.9815565955971572,0.7228289131565263,0.7899938448272602,0.7905850272789016,0.7907603766340526,0.7907971834013171,0.7908095689840076,0.7228289131565263,0.7959776691032214,0.8052218859556804,0.8094758218085412,0.8110653021951649,0.8123520678935076,0.7228289131565263,0.7247290364038195,0.7272469793121716,0.7278160623638382,0.7279625886901666,0.7280545302821056,0.7281572552607218
+3.082135523613963,3000,0.7280291211648466,0.9594383775351014,0.9776391055642226,0.9901196047841914,0.9953198127925117,0.9968798751950078,0.7280291211648466,0.2820295668969616,0.12373894955798231,0.9141618998093257,0.05132605304212169,0.9473825619691454,0.026115444617784717,0.9651152712775177,0.01758710348413936,0.9755676893742417,0.013283931357254294,0.9829086496793205,0.7280291211648466,0.7936259077760474,0.7942215768213808,0.7944025637572019,0.7944447704847868,0.794453781113962,0.7280291211648466,0.798946396985741,0.8080660832318841,0.8118764604779153,0.8138708034784832,0.8151668636249689,0.7280291211648466,0.7279941931573798,0.7304749375451067,0.7309842337473567,0.7311641189752125,0.7312553938108709,0.7313554857163891
+3.2874743326488707,3200,0.7150286011440458,0.9573582943317732,0.9765990639625585,0.9911596463858554,0.9947997919916797,0.9963598543941757,0.7150286011440458,0.2765520144615309,0.12373894955798231,0.913659213035188,0.05123244929797193,0.9459611717802046,0.02612064482579304,0.9655486219448778,0.01755936904142832,0.9737649505980239,0.013263130525221012,0.9807505633558675,0.7150286011440458,0.7853064274912624,0.7859443378814273,0.7861623312440641,0.7861940238062093,0.7862032372379819,0.7150286011440458,0.7951101406060039,0.8039370692571942,0.8081817298513937,0.8097758398379429,0.8110327686440667,0.7150286011440458,0.7242135152783706,0.7266007218222952,0.7271697294824622,0.7273166403120899,0.7274087739403149,0.7275217450212315
+3.4928131416837784,3400,0.7233489339573583,0.9604784191367655,0.9765990639625585,0.9911596463858554,0.9963598543941757,0.9968798751950078,0.7233489339573583,0.27967213926652307,0.12363494539781592,0.9135898769284104,0.051211648465938654,0.9454411509793724,0.026136245449817998,0.9663286531461258,0.017576703068122722,0.9750476685734096,0.013283931357254293,0.9827959785058069,0.7233489339573583,0.790616300036987,0.7911451755698473,0.791368754766026,0.791414074459704,0.7914169006597087,0.7233489339573583,0.7973298093826647,0.8061926213958046,0.8107203328894771,0.8124096809038343,0.8137923662435536,0.7233489339573583,0.7263932539293092,0.7289821299517589,0.7295971508011626,0.7297494047331623,0.7298530106478077,0.7299587469603714
+3.6981519507186857,3600,0.7249089963598544,0.9599583983359334,0.9771190847633905,0.9921996879875195,0.9958398335933437,0.9968798751950078,0.7249089963598544,0.28027883020082717,0.12384295371814871,0.9154099497313225,0.051294851794071776,0.9471658866354654,0.026188247529901204,0.968408736349454,0.017611371121511524,0.9763650546021839,0.013281331253250133,0.9824492979719188,0.7249089963598544,0.7931568992440393,0.793715015835792,0.7939504079883869,0.7939819349883227,0.7939883353049277,0.7249089963598544,0.8003506405205896,0.8091193234281266,0.8137121141444412,0.8152921945289446,0.8163523042378167,0.7249089963598544,0.7301955878758443,0.7326872629149596,0.7333037830153952,0.7334498461075301,0.7335264824052321,0.7336333524545813
+3.9034907597535935,3800,0.7259490379615184,0.9599583983359334,0.9797191887675507,0.9927197087883516,0.9958398335933437,0.9973998959958398,0.7259490379615184,0.2806428447614095,0.12423296931877274,0.9178193794418443,0.051419656786271466,0.9494973132258623,0.026183047321892885,0.9675593690414283,0.017600970705494885,0.9757583636678799,0.013276131045241814,0.9814959265037267,0.7259490379615184,0.7948163472735045,0.7954302623521613,0.7956223667502647,0.7956489127503253,0.7956584389155293,0.7259490379615184,0.8024229430955802,0.8110354092322288,0.8149702827130566,0.8165529751035248,0.8175777108172241,0.7259490379615184,0.7324403090373143,0.7348033703076142,0.7353336579174736,0.7354741697534483,0.7355476089683456,0.7356573413185541
+4.108829568788501,4000,0.7243889755590224,0.9609984399375975,0.9797191887675507,0.9937597503900156,0.9958398335933437,0.9973998959958398,0.7243889755590224,0.2802961642275215,0.12428497139885596,0.9183394002426764,0.05134685387415497,0.9482665973305597,0.026214248569942804,0.9692234356040907,0.017597503900156002,0.9756023574276305,0.013281331253250133,0.9821892875715027,0.7243889755590224,0.7938466413093047,0.7944053350960067,0.794613049565821,0.7946306448507517,0.7946402095756717,0.7243889755590224,0.8023352815755668,0.8104895152869938,0.8150081000806421,0.8162651648802736,0.8174362445077372,0.7243889755590224,0.7324440771234734,0.734716178743038,0.7353155432601859,0.735429453970343,0.7355154445871764,0.7356208832908805
+4.314168377823409,4200,0.7238689547581904,0.9583983359334374,0.9802392095683827,0.9942797711908476,0.9953198127925117,0.9973998959958398,0.7238689547581904,0.28019216006735503,0.12412896515860634,0.9169353440804299,0.05145085803432139,0.9499306638932224,0.026245449817992726,0.9701768070722828,0.017614837926850403,0.9764690587623505,0.013283931357254293,0.9822326226382389,0.7238689547581904,0.7934277492682618,0.7941208450339935,0.7943224531588357,0.7943312488289611,0.7943443835009225,0.7238689547581904,0.8023238060267395,0.8113379258247732,0.8156949679776019,0.816929855500621,0.8179575655343403,0.7238689547581904,0.7331525143106996,0.7355830040348272,0.7361451167677289,0.7362661519275265,0.7363390374447161,0.7364481715630059
+4.519507186858316,4400,0.7264690587623505,0.9589183567342694,0.9791991679667187,0.9942797711908476,0.9963598543941757,0.9973998959958398,0.7264690587623505,0.2809028551618255,0.12420696827873114,0.9175593690414283,0.051430057202288104,0.9495839833593345,0.026245449817992726,0.9700901369388107,0.017621771537528166,0.9768157392962384,0.013286531461258454,0.9820072802912115,0.7264690587623505,0.7950273648815123,0.7956778348360616,0.7959013329165427,0.7959172370306803,0.7959232938160362,0.7264690587623505,0.8030413573056574,0.811796736904274,0.816244308604025,0.8175588810577264,0.8184967672553575,0.7264690587623505,0.7336401935022089,0.7360366435506714,0.7366186564599716,0.7367425141591574,0.7368117834120087,0.7369173075310415
+4.724845995893224,4600,0.7243889755590224,0.9594383775351014,0.9791991679667187,0.9927197087883516,0.9963598543941757,0.9973998959958398,0.7243889755590224,0.2801228239605774,0.12423296931877274,0.9177327093083724,0.05144045761830475,0.9498439937597504,0.026235049401976088,0.9693967758710348,0.017628705148205925,0.9772057548968625,0.013283931357254294,0.9819032761310452,0.7243889755590224,0.7950733254581356,0.7957037061937158,0.7959106624394904,0.795941995568463,0.7959480612399141,0.7243889755590224,0.8035653524093836,0.8123465374976416,0.816619783760099,0.8181288168343755,0.8189742580500373,0.7243889755590224,0.7344976284540953,0.7369058419409787,0.7374765660485233,0.7376131540231733,0.7376752620519383,0.7377852907056718
+4.930184804928132,4800,0.7280291211648466,0.9599583983359334,0.9791991679667187,0.9942797711908476,0.9958398335933437,0.9973998959958398,0.7280291211648466,0.28133620582918556,0.12433697347893914,0.9183394002426764,0.05145085803432139,0.9499306638932224,0.02625065002600105,0.9700901369388107,0.017621771537528162,0.9767724042295025,0.013283931357254294,0.9818166059975733,0.7280291211648466,0.7968549154271433,0.7974653825839162,0.7976914864910069,0.7977044635908871,0.7977139196654446,0.7280291211648466,0.8043549768911603,0.81295852465432,0.817339429558165,0.8186380742931886,0.8195485984235017,0.7280291211648466,0.7350836192117531,0.7374205090112232,0.737988888492803,0.7381133157945164,0.7381788581828236,0.7382854440643231