Add new SentenceTransformer model

README.md

@@ -81,49 +81,49 @@ model-index:
       type: dim_1024
     metrics:
     - type: cosine_accuracy@1
-      value: 0.771876885938443
+      value: 0.7803258901629451
       name: Cosine Accuracy@1
     - type: cosine_accuracy@3
-      value: 0.8931804465902233
+      value: 0.8883524441762221
       name: Cosine Accuracy@3
     - type: cosine_accuracy@5
-      value: 0.9136994568497284
+      value: 0.904043452021726
       name: Cosine Accuracy@5
     - type: cosine_accuracy@10
-      value: 0.928183464091732
+      value: 0.9233554616777309
       name: Cosine Accuracy@10
     - type: cosine_precision@1
-      value: 0.771876885938443
+      value: 0.7803258901629451
       name: Cosine Precision@1
     - type: cosine_precision@3
-      value: 0.2977268155300744
+      value: 0.29611748139207406
       name: Cosine Precision@3
     - type: cosine_precision@5
-      value: 0.18273989136994565
+      value: 0.18080869040434522
       name: Cosine Precision@5
     - type: cosine_precision@10
-      value: 0.0928183464091732
+      value: 0.09233554616777308
       name: Cosine Precision@10
     - type: cosine_recall@1
-      value: 0.771876885938443
+      value: 0.7803258901629451
       name: Cosine Recall@1
     - type: cosine_recall@3
-      value: 0.8931804465902233
+      value: 0.8883524441762221
       name: Cosine Recall@3
     - type: cosine_recall@5
-      value: 0.9136994568497284
+      value: 0.904043452021726
       name: Cosine Recall@5
     - type: cosine_recall@10
-      value: 0.928183464091732
+      value: 0.9233554616777309
       name: Cosine Recall@10
     - type: cosine_ndcg@10
-      value: 0.8567624282543636
+      value: 0.8576141434466037
       name: Cosine Ndcg@10
     - type: cosine_mrr@10
-      value: 0.8330754087996087
+      value: 0.8359425142014155
       name: Cosine Mrr@10
     - type: cosine_map@100
-      value: 0.8344062726339423
+      value: 0.8374344979701236
       name: Cosine Map@100
   - task:
       type: information-retrieval
@@ -133,49 +133,49 @@ model-index:
       type: dim_768
     metrics:
     - type: cosine_accuracy@1
-      value: 0.7706698853349426
+      value: 0.7827398913699457
       name: Cosine Accuracy@1
     - type: cosine_accuracy@3
-      value: 0.8925769462884732
+      value: 0.8877489438744719
       name: Cosine Accuracy@3
     - type: cosine_accuracy@5
-      value: 0.9118889559444779
+      value: 0.9034399517199758
       name: Cosine Accuracy@5
     - type: cosine_accuracy@10
-      value: 0.9287869643934822
+      value: 0.9245624622812312
       name: Cosine Accuracy@10
     - type: cosine_precision@1
-      value: 0.7706698853349426
+      value: 0.7827398913699457
       name: Cosine Precision@1
     - type: cosine_precision@3
-      value: 0.2975256487628244
+      value: 0.295916314624824
       name: Cosine Precision@3
     - type: cosine_precision@5
-      value: 0.18237779118889558
+      value: 0.18068799034399516
       name: Cosine Precision@5
     - type: cosine_precision@10
-      value: 0.09287869643934822
+      value: 0.09245624622812311
       name: Cosine Precision@10
     - type: cosine_recall@1
-      value: 0.7706698853349426
+      value: 0.7827398913699457
       name: Cosine Recall@1
     - type: cosine_recall@3
-      value: 0.8925769462884732
+      value: 0.8877489438744719
       name: Cosine Recall@3
     - type: cosine_recall@5
-      value: 0.9118889559444779
+      value: 0.9034399517199758
       name: Cosine Recall@5
     - type: cosine_recall@10
-      value: 0.9287869643934822
+      value: 0.9245624622812312
       name: Cosine Recall@10
     - type: cosine_ndcg@10
-      value: 0.8563506024476554
+      value: 0.858770916125463
       name: Cosine Ndcg@10
     - type: cosine_mrr@10
-      value: 0.8323629431655981
+      value: 0.8371705894186279
       name: Cosine Mrr@10
     - type: cosine_map@100
-      value: 0.8335898787409641
+      value: 0.8385437636605255
       name: Cosine Map@100
   - task:
       type: information-retrieval
@@ -185,49 +185,49 @@ model-index:
       type: dim_512
     metrics:
     - type: cosine_accuracy@1
-      value: 0.7682558841279421
+      value: 0.7797223898611949
       name: Cosine Accuracy@1
     - type: cosine_accuracy@3
-      value: 0.891973445986723
+      value: 0.8859384429692215
       name: Cosine Accuracy@3
     - type: cosine_accuracy@5
-      value: 0.9106819553409776
+      value: 0.9010259505129753
       name: Cosine Accuracy@5
     - type: cosine_accuracy@10
-      value: 0.9299939649969825
+      value: 0.9227519613759807
       name: Cosine Accuracy@10
     - type: cosine_precision@1
-      value: 0.7682558841279421
+      value: 0.7797223898611949
       name: Cosine Precision@1
     - type: cosine_precision@3
-      value: 0.2973244819955743
+      value: 0.2953128143230738
       name: Cosine Precision@3
     - type: cosine_precision@5
-      value: 0.1821363910681955
+      value: 0.18020519010259503
       name: Cosine Precision@5
     - type: cosine_precision@10
-      value: 0.09299939649969825
+      value: 0.09227519613759806
       name: Cosine Precision@10
     - type: cosine_recall@1
-      value: 0.7682558841279421
+      value: 0.7797223898611949
       name: Cosine Recall@1
     - type: cosine_recall@3
-      value: 0.891973445986723
+      value: 0.8859384429692215
       name: Cosine Recall@3
     - type: cosine_recall@5
-      value: 0.9106819553409776
+      value: 0.9010259505129753
       name: Cosine Recall@5
     - type: cosine_recall@10
-      value: 0.9299939649969825
+      value: 0.9227519613759807
       name: Cosine Recall@10
     - type: cosine_ndcg@10
-      value: 0.8553875428985249
+      value: 0.8564496755344808
       name: Cosine Ndcg@10
     - type: cosine_mrr@10
-      value: 0.8307586381967789
+      value: 0.8346785163471941
       name: Cosine Mrr@10
     - type: cosine_map@100
-      value: 0.8318464309684749
+      value: 0.8361853082918266
       name: Cosine Map@100
   - task:
       type: information-retrieval
@@ -237,49 +237,49 @@ model-index:
       type: dim_256
     metrics:
     - type: cosine_accuracy@1
-      value: 0.7646348823174411
+      value: 0.7706698853349426
       name: Cosine Accuracy@1
     - type: cosine_accuracy@3
-      value: 0.8883524441762221
+      value: 0.8823174411587206
       name: Cosine Accuracy@3
     - type: cosine_accuracy@5
-      value: 0.9058539529269765
+      value: 0.9016294508147255
       name: Cosine Accuracy@5
     - type: cosine_accuracy@10
-      value: 0.9251659625829813
+      value: 0.9191309595654797
       name: Cosine Accuracy@10
     - type: cosine_precision@1
-      value: 0.7646348823174411
+      value: 0.7706698853349426
       name: Cosine Precision@1
     - type: cosine_precision@3
-      value: 0.296117481392074
+      value: 0.2941058137195735
       name: Cosine Precision@3
     - type: cosine_precision@5
-      value: 0.18117079058539529
+      value: 0.18032589016294506
       name: Cosine Precision@5
     - type: cosine_precision@10
-      value: 0.09251659625829814
+      value: 0.09191309595654798
       name: Cosine Precision@10
     - type: cosine_recall@1
-      value: 0.7646348823174411
+      value: 0.7706698853349426
       name: Cosine Recall@1
     - type: cosine_recall@3
-      value: 0.8883524441762221
+      value: 0.8823174411587206
       name: Cosine Recall@3
     - type: cosine_recall@5
-      value: 0.9058539529269765
+      value: 0.9016294508147255
       name: Cosine Recall@5
     - type: cosine_recall@10
-      value: 0.9251659625829813
+      value: 0.9191309595654797
       name: Cosine Recall@10
     - type: cosine_ndcg@10
-      value: 0.8515592939892533
+      value: 0.851155539622205
       name: Cosine Ndcg@10
     - type: cosine_mrr@10
-      value: 0.827186251688363
+      value: 0.8286940445057519
       name: Cosine Mrr@10
     - type: cosine_map@100
-      value: 0.8285316886087458
+      value: 0.8302805177061129
       name: Cosine Map@100
   - task:
       type: information-retrieval
@@ -289,49 +289,49 @@ model-index:
       type: dim_128
     metrics:
     - type: cosine_accuracy@1
-      value: 0.7531683765841883
+      value: 0.7604103802051901
       name: Cosine Accuracy@1
     - type: cosine_accuracy@3
-      value: 0.8774894387447194
+      value: 0.8690404345202173
       name: Cosine Accuracy@3
     - type: cosine_accuracy@5
-      value: 0.8968014484007242
+      value: 0.8901629450814725
       name: Cosine Accuracy@5
     - type: cosine_accuracy@10
-      value: 0.9161134580567291
+      value: 0.9130959565479783
       name: Cosine Accuracy@10
     - type: cosine_precision@1
-      value: 0.7531683765841883
+      value: 0.7604103802051901
       name: Cosine Precision@1
     - type: cosine_precision@3
-      value: 0.2924964795815731
+      value: 0.28968014484007243
       name: Cosine Precision@3
     - type: cosine_precision@5
-      value: 0.17936028968014484
+      value: 0.1780325890162945
       name: Cosine Precision@5
     - type: cosine_precision@10
-      value: 0.09161134580567289
+      value: 0.09130959565479783
       name: Cosine Precision@10
     - type: cosine_recall@1
-      value: 0.7531683765841883
+      value: 0.7604103802051901
       name: Cosine Recall@1
     - type: cosine_recall@3
-      value: 0.8774894387447194
+      value: 0.8690404345202173
       name: Cosine Recall@3
     - type: cosine_recall@5
-      value: 0.8968014484007242
+      value: 0.8901629450814725
       name: Cosine Recall@5
     - type: cosine_recall@10
-      value: 0.9161134580567291
+      value: 0.9130959565479783
       name: Cosine Recall@10
     - type: cosine_ndcg@10
-      value: 0.8412352149980756
+      value: 0.8415141158022221
       name: Cosine Ndcg@10
     - type: cosine_mrr@10
-      value: 0.8165177074652028
+      value: 0.8181217729497756
       name: Cosine Mrr@10
     - type: cosine_map@100
-      value: 0.8182055440879425
+      value: 0.8199539602494803
       name: Cosine Map@100
   - task:
       type: information-retrieval
@@ -341,10 +341,10 @@ model-index:
       type: dim_64
     metrics:
     - type: cosine_accuracy@1
-      value: 0.7109233554616777
+      value: 0.7248038624019312
       name: Cosine Accuracy@1
     - type: cosine_accuracy@3
-      value: 0.8503319251659626
+      value: 0.852142426071213
       name: Cosine Accuracy@3
     - type: cosine_accuracy@5
       value: 0.8750754375377188
@@ -353,10 +353,10 @@ model-index:
       value: 0.8974049487024743
       name: Cosine Accuracy@10
     - type: cosine_precision@1
-      value: 0.7109233554616777
+      value: 0.7248038624019312
       name: Cosine Precision@1
     - type: cosine_precision@3
-      value: 0.2834439750553209
+      value: 0.28404747535707103
       name: Cosine Precision@3
     - type: cosine_precision@5
       value: 0.17501508750754374
@@ -365,10 +365,10 @@ model-index:
       value: 0.08974049487024743
       name: Cosine Precision@10
     - type: cosine_recall@1
-      value: 0.7109233554616777
+      value: 0.7248038624019312
       name: Cosine Recall@1
     - type: cosine_recall@3
-      value: 0.8503319251659626
+      value: 0.852142426071213
       name: Cosine Recall@3
     - type: cosine_recall@5
       value: 0.8750754375377188
@@ -377,13 +377,13 @@ model-index:
       value: 0.8974049487024743
       name: Cosine Recall@10
     - type: cosine_ndcg@10
-      value: 0.8110786488208866
+      value: 0.8181789750224895
       name: Cosine Ndcg@10
     - type: cosine_mrr@10
-      value: 0.7826713988753816
+      value: 0.7920167926353802
       name: Cosine Mrr@10
     - type: cosine_map@100
-      value: 0.7847527919142971
+      value: 0.793825252598125
       name: Cosine Map@100
 ---
 
@@ -583,21 +583,21 @@ You can finetune this model on your own dataset.
 
 | Metric              | Value      |
 |:--------------------|:-----------|
-| cosine_accuracy@1   | 0.7719     |
-| cosine_accuracy@3   | 0.8932     |
-| cosine_accuracy@5   | 0.9137     |
-| cosine_accuracy@10  | 0.9282     |
-| cosine_precision@1  | 0.7719     |
-| cosine_precision@3  | 0.2977     |
-| cosine_precision@5  | 0.1827     |
-| cosine_precision@10 | 0.0928     |
-| cosine_recall@1     | 0.7719     |
-| cosine_recall@3     | 0.8932     |
-| cosine_recall@5     | 0.9137     |
-| cosine_recall@10    | 0.9282     |
-| **cosine_ndcg@10**  | **0.8568** |
-| cosine_mrr@10       | 0.8331     |
-| cosine_map@100      | 0.8344     |
+| cosine_accuracy@1   | 0.7803     |
+| cosine_accuracy@3   | 0.8884     |
+| cosine_accuracy@5   | 0.904      |
+| cosine_accuracy@10  | 0.9234     |
+| cosine_precision@1  | 0.7803     |
+| cosine_precision@3  | 0.2961     |
+| cosine_precision@5  | 0.1808     |
+| cosine_precision@10 | 0.0923     |
+| cosine_recall@1     | 0.7803     |
+| cosine_recall@3     | 0.8884     |
+| cosine_recall@5     | 0.904      |
+| cosine_recall@10    | 0.9234     |
+| **cosine_ndcg@10**  | **0.8576** |
+| cosine_mrr@10       | 0.8359     |
+| cosine_map@100      | 0.8374     |
 
 #### Information Retrieval
 
@@ -611,21 +611,21 @@ You can finetune this model on your own dataset.
 
 | Metric              | Value      |
 |:--------------------|:-----------|
-| cosine_accuracy@1   | 0.7707     |
-| cosine_accuracy@3   | 0.8926     |
-| cosine_accuracy@5   | 0.9119     |
-| cosine_accuracy@10  | 0.9288     |
-| cosine_precision@1  | 0.7707     |
-| cosine_precision@3  | 0.2975     |
-| cosine_precision@5  | 0.1824     |
-| cosine_precision@10 | 0.0929     |
-| cosine_recall@1     | 0.7707     |
-| cosine_recall@3     | 0.8926     |
-| cosine_recall@5     | 0.9119     |
-| cosine_recall@10    | 0.9288     |
-| **cosine_ndcg@10**  | **0.8564** |
-| cosine_mrr@10       | 0.8324     |
-| cosine_map@100      | 0.8336     |
+| cosine_accuracy@1   | 0.7827     |
+| cosine_accuracy@3   | 0.8877     |
+| cosine_accuracy@5   | 0.9034     |
+| cosine_accuracy@10  | 0.9246     |
+| cosine_precision@1  | 0.7827     |
+| cosine_precision@3  | 0.2959     |
+| cosine_precision@5  | 0.1807     |
+| cosine_precision@10 | 0.0925     |
+| cosine_recall@1     | 0.7827     |
+| cosine_recall@3     | 0.8877     |
+| cosine_recall@5     | 0.9034     |
+| cosine_recall@10    | 0.9246     |
+| **cosine_ndcg@10**  | **0.8588** |
+| cosine_mrr@10       | 0.8372     |
+| cosine_map@100      | 0.8385     |
 
 #### Information Retrieval
 
@@ -639,21 +639,21 @@ You can finetune this model on your own dataset.
 
 | Metric              | Value      |
 |:--------------------|:-----------|
-| cosine_accuracy@1   | 0.7683     |
-| cosine_accuracy@3   | 0.892      |
-| cosine_accuracy@5   | 0.9107     |
-| cosine_accuracy@10  | 0.93       |
-| cosine_precision@1  | 0.7683     |
-| cosine_precision@3  | 0.2973     |
-| cosine_precision@5  | 0.1821     |
-| cosine_precision@10 | 0.093      |
-| cosine_recall@1     | 0.7683     |
-| cosine_recall@3     | 0.892      |
-| cosine_recall@5     | 0.9107     |
-| cosine_recall@10    | 0.93       |
-| **cosine_ndcg@10**  | **0.8554** |
-| cosine_mrr@10       | 0.8308     |
-| cosine_map@100      | 0.8318     |
+| cosine_accuracy@1   | 0.7797     |
+| cosine_accuracy@3   | 0.8859     |
+| cosine_accuracy@5   | 0.901      |
+| cosine_accuracy@10  | 0.9228     |
+| cosine_precision@1  | 0.7797     |
+| cosine_precision@3  | 0.2953     |
+| cosine_precision@5  | 0.1802     |
+| cosine_precision@10 | 0.0923     |
+| cosine_recall@1     | 0.7797     |
+| cosine_recall@3     | 0.8859     |
+| cosine_recall@5     | 0.901      |
+| cosine_recall@10    | 0.9228     |
+| **cosine_ndcg@10**  | **0.8564** |
+| cosine_mrr@10       | 0.8347     |
+| cosine_map@100      | 0.8362     |
 
 #### Information Retrieval
 
@@ -667,21 +667,21 @@ You can finetune this model on your own dataset.
 
 | Metric              | Value      |
 |:--------------------|:-----------|
-| cosine_accuracy@1   | 0.7646     |
-| cosine_accuracy@3   | 0.8884     |
-| cosine_accuracy@5   | 0.9059     |
-| cosine_accuracy@10  | 0.9252     |
-| cosine_precision@1  | 0.7646     |
-| cosine_precision@3  | 0.2961     |
-| cosine_precision@5  | 0.1812     |
-| cosine_precision@10 | 0.0925     |
-| cosine_recall@1     | 0.7646     |
-| cosine_recall@3     | 0.8884     |
-| cosine_recall@5     | 0.9059     |
-| cosine_recall@10    | 0.9252     |
-| **cosine_ndcg@10**  | **0.8516** |
-| cosine_mrr@10       | 0.8272     |
-| cosine_map@100      | 0.8285     |
+| cosine_accuracy@1   | 0.7707     |
+| cosine_accuracy@3   | 0.8823     |
+| cosine_accuracy@5   | 0.9016     |
+| cosine_accuracy@10  | 0.9191     |
+| cosine_precision@1  | 0.7707     |
+| cosine_precision@3  | 0.2941     |
+| cosine_precision@5  | 0.1803     |
+| cosine_precision@10 | 0.0919     |
+| cosine_recall@1     | 0.7707     |
+| cosine_recall@3     | 0.8823     |
+| cosine_recall@5     | 0.9016     |
+| cosine_recall@10    | 0.9191     |
+| **cosine_ndcg@10**  | **0.8512** |
+| cosine_mrr@10       | 0.8287     |
+| cosine_map@100      | 0.8303     |
 
 #### Information Retrieval
 
@@ -695,21 +695,21 @@ You can finetune this model on your own dataset.
 
 | Metric              | Value      |
 |:--------------------|:-----------|
-| cosine_accuracy@1   | 0.7532     |
-| cosine_accuracy@3   | 0.8775     |
-| cosine_accuracy@5   | 0.8968     |
-| cosine_accuracy@10  | 0.9161     |
-| cosine_precision@1  | 0.7532     |
-| cosine_precision@3  | 0.2925     |
-| cosine_precision@5  | 0.1794     |
-| cosine_precision@10 | 0.0916     |
-| cosine_recall@1     | 0.7532     |
-| cosine_recall@3     | 0.8775     |
-| cosine_recall@5     | 0.8968     |
-| cosine_recall@10    | 0.9161     |
-| **cosine_ndcg@10**  | **0.8412** |
-| cosine_mrr@10       | 0.8165     |
-| cosine_map@100      | 0.8182     |
+| cosine_accuracy@1   | 0.7604     |
+| cosine_accuracy@3   | 0.869      |
+| cosine_accuracy@5   | 0.8902     |
+| cosine_accuracy@10  | 0.9131     |
+| cosine_precision@1  | 0.7604     |
+| cosine_precision@3  | 0.2897     |
+| cosine_precision@5  | 0.178      |
+| cosine_precision@10 | 0.0913     |
+| cosine_recall@1     | 0.7604     |
+| cosine_recall@3     | 0.869      |
+| cosine_recall@5     | 0.8902     |
+| cosine_recall@10    | 0.9131     |
+| **cosine_ndcg@10**  | **0.8415** |
+| cosine_mrr@10       | 0.8181     |
+| cosine_map@100      | 0.82       |
 
 #### Information Retrieval
 
@@ -723,21 +723,21 @@ You can finetune this model on your own dataset.
 
 | Metric              | Value      |
 |:--------------------|:-----------|
-| cosine_accuracy@1   | 0.7109     |
-| cosine_accuracy@3   | 0.8503     |
+| cosine_accuracy@1   | 0.7248     |
+| cosine_accuracy@3   | 0.8521     |
 | cosine_accuracy@5   | 0.8751     |
 | cosine_accuracy@10  | 0.8974     |
-| cosine_precision@1  | 0.7109     |
-| cosine_precision@3  | 0.2834     |
+| cosine_precision@1  | 0.7248     |
+| cosine_precision@3  | 0.284      |
 | cosine_precision@5  | 0.175      |
 | cosine_precision@10 | 0.0897     |
-| cosine_recall@1     | 0.7109     |
-| cosine_recall@3     | 0.8503     |
+| cosine_recall@1     | 0.7248     |
+| cosine_recall@3     | 0.8521     |
 | cosine_recall@5     | 0.8751     |
 | cosine_recall@10    | 0.8974     |
-| **cosine_ndcg@10**  | **0.8111** |
-| cosine_mrr@10       | 0.7827     |
-| cosine_map@100      | 0.7848     |
+| **cosine_ndcg@10**  | **0.8182** |
+| cosine_mrr@10       | 0.792      |
+| cosine_map@100      | 0.7938     |
 
 <!--
 ## Bias, Risks and Limitations
@@ -799,11 +799,11 @@ You can finetune this model on your own dataset.
 #### Non-Default Hyperparameters
 
 - `eval_strategy`: epoch
-- `per_device_train_batch_size`: 32
+- `per_device_train_batch_size`: 64
 - `per_device_eval_batch_size`: 16
-- `gradient_accumulation_steps`: 16
+- `gradient_accumulation_steps`: 32
 - `learning_rate`: 2e-05
-- `num_train_epochs`: 4
+- `num_train_epochs`: 12
 - `lr_scheduler_type`: cosine
 - `warmup_ratio`: 0.1
 - `tf32`: True
@@ -818,11 +818,11 @@ You can finetune this model on your own dataset.
 - `do_predict`: False
 - `eval_strategy`: epoch
 - `prediction_loss_only`: True
-- `per_device_train_batch_size`: 32
+- `per_device_train_batch_size`: 64
 - `per_device_eval_batch_size`: 16
 - `per_gpu_train_batch_size`: None
 - `per_gpu_eval_batch_size`: None
-- `gradient_accumulation_steps`: 16
+- `gradient_accumulation_steps`: 32
 - `eval_accumulation_steps`: None
 - `torch_empty_cache_steps`: None
 - `learning_rate`: 2e-05
@@ -831,7 +831,7 @@ You can finetune this model on your own dataset.
 - `adam_beta2`: 0.999
 - `adam_epsilon`: 1e-08
 - `max_grad_norm`: 1.0
-- `num_train_epochs`: 4
+- `num_train_epochs`: 12
 - `max_steps`: -1
 - `lr_scheduler_type`: cosine
 - `lr_scheduler_kwargs`: {}
@@ -932,20 +932,25 @@ You can finetune this model on your own dataset.
 </details>
 
 ### Training Logs
-| Epoch  | Step | Training Loss | dim_1024_cosine_ndcg@10 | dim_768_cosine_ndcg@10 | dim_512_cosine_ndcg@10 | dim_256_cosine_ndcg@10 | dim_128_cosine_ndcg@10 | dim_64_cosine_ndcg@10 |
-|:------:|:----:|:-------------:|:-----------------------:|:----------------------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:|
-| 0.3433 | 10   | 23.532        | -                       | -                      | -                      | -                      | -                      | -                     |
-| 0.6867 | 20   | 10.6294       | -                       | -                      | -                      | -                      | -                      | -                     |
-| 1.0    | 30   | 5.9964        | 0.8436                  | 0.8428                 | 0.8417                 | 0.8373                 | 0.8254                 | 0.7920                |
-| 1.3433 | 40   | 4.451         | -                       | -                      | -                      | -                      | -                      | -                     |
-| 1.6867 | 50   | 4.7053        | -                       | -                      | -                      | -                      | -                      | -                     |
-| 2.0    | 60   | 3.9423        | 0.8555                  | 0.8539                 | 0.8535                 | 0.8505                 | 0.8374                 | 0.8075                |
-| 2.3433 | 70   | 4.0009        | -                       | -                      | -                      | -                      | -                      | -                     |
-| 2.6867 | 80   | 4.3913        | -                       | -                      | -                      | -                      | -                      | -                     |
-| 3.0    | 90   | 2.9362        | 0.8566                  | 0.8548                 | 0.8554                 | 0.8514                 | 0.8401                 | 0.8089                |
-| 3.3433 | 100  | 3.7804        | -                       | -                      | -                      | -                      | -                      | -                     |
-| 3.6867 | 110  | 4.5676        | -                       | -                      | -                      | -                      | -                      | -                     |
-| 3.8927 | 116  | -             | 0.8568                  | 0.8564                 | 0.8554                 | 0.8516                 | 0.8412                 | 0.8111                |
+| Epoch   | Step | Training Loss | dim_1024_cosine_ndcg@10 | dim_768_cosine_ndcg@10 | dim_512_cosine_ndcg@10 | dim_256_cosine_ndcg@10 | dim_128_cosine_ndcg@10 | dim_64_cosine_ndcg@10 |
+|:-------:|:----:|:-------------:|:-----------------------:|:----------------------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:|
+| 1.0     | 8    | -             | 0.7663                  | 0.7676                 | 0.7656                 | 0.7626                 | 0.7393                 | 0.6969                |
+| 1.2747  | 10   | 127.0406      | -                       | -                      | -                      | -                      | -                      | -                     |
+| 2.0     | 16   | -             | 0.8244                  | 0.8240                 | 0.8226                 | 0.8172                 | 0.8060                 | 0.7775                |
+| 2.5494  | 20   | 38.8995       | -                       | -                      | -                      | -                      | -                      | -                     |
+| 3.0     | 24   | -             | 0.8425                  | 0.8426                 | 0.8444                 | 0.8373                 | 0.8252                 | 0.7996                |
+| 3.8240  | 30   | 20.1528       | -                       | -                      | -                      | -                      | -                      | -                     |
+| 4.0     | 32   | -             | 0.8526                  | 0.8520                 | 0.8498                 | 0.8456                 | 0.8289                 | 0.8037                |
+| 5.0     | 40   | 14.0513       | 0.8550                  | 0.8543                 | 0.8517                 | 0.8490                 | 0.8368                 | 0.8139                |
+| 6.0     | 48   | -             | 0.8572                  | 0.8565                 | 0.8557                 | 0.8520                 | 0.8404                 | 0.8170                |
+| 6.2747  | 50   | 13.364        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 7.0     | 56   | -             | 0.8579                  | 0.8576                 | 0.8553                 | 0.8514                 | 0.8422                 | 0.8180                |
+| 7.5494  | 60   | 12.7986       | -                       | -                      | -                      | -                      | -                      | -                     |
+| 8.0     | 64   | -             | 0.8573                  | 0.8580                 | 0.8560                 | 0.8523                 | 0.8414                 | 0.8178                |
+| 8.8240  | 70   | 12.0091       | -                       | -                      | -                      | -                      | -                      | -                     |
+| 9.0     | 72   | -             | 0.8578                  | 0.8586                 | 0.8562                 | 0.8519                 | 0.8423                 | 0.8184                |
+| 10.0    | 80   | 10.9468       | 0.8583                  | 0.8589                 | 0.8565                 | 0.8530                 | 0.8413                 | 0.8191                |
+| 10.5494 | 84   | -             | 0.8576                  | 0.8588                 | 0.8564                 | 0.8512                 | 0.8415                 | 0.8182                |
 
 
 ### Framework Versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77438c542b0993994f69a4e6c0cf7341c8024b647f3fe764660ad9e6696aaad9
+oid sha256:3cd81a650c2cc7b04eb39dc3d7523ba382d3823d3718c2f3afce2192fd4b074b
 size 1144685320