Training in progress, step 5000

1_Pooling/config.json

@@ -1,7 +1,7 @@
 {
-    "word_embedding_dimension": 384,
-    "pooling_mode_cls_token": false,
-    "pooling_mode_mean_tokens": true,
+    "word_embedding_dimension": 512,
+    "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,

Information-Retrieval_evaluation_BeIR-touche2020-subset-test_results.csv

@@ -0,0 +1,2 @@
+epoch,steps,cosine-Accuracy@1,cosine-Accuracy@3,cosine-Accuracy@5,cosine-Accuracy@10,cosine-Precision@1,cosine-Recall@1,cosine-Precision@3,cosine-Recall@3,cosine-Precision@5,cosine-Recall@5,cosine-Precision@10,cosine-Recall@10,cosine-MRR@10,cosine-NDCG@10,cosine-MAP@100
+-1,-1,0.7142857142857143,0.8979591836734694,0.9387755102040817,1.0,0.7142857142857143,0.015925713751801022,0.6870748299319728,0.045760276621368244,0.6326530612244898,0.06999790748190285,0.553061224489796,0.12237196517849,0.8126660187884677,0.590781089071972,0.25216721309824497

Information-Retrieval_evaluation_NanoArguAna_results.csv

@@ -1,2 +1,3 @@
 epoch,steps,cosine-Accuracy@1,cosine-Accuracy@3,cosine-Accuracy@5,cosine-Accuracy@10,cosine-Precision@1,cosine-Recall@1,cosine-Precision@3,cosine-Recall@3,cosine-Precision@5,cosine-Recall@5,cosine-Precision@10,cosine-Recall@10,cosine-MRR@10,cosine-NDCG@10,cosine-MAP@100
 -1,-1,0.2,0.56,0.74,0.76,0.2,0.2,0.18666666666666668,0.56,0.14800000000000002,0.74,0.07600000000000001,0.76,0.40222222222222215,0.49058314613975507,0.4109932426184554
+-1,-1,0.2,0.56,0.74,0.76,0.2,0.2,0.18666666666666668,0.56,0.14800000000000002,0.74,0.07600000000000001,0.76,0.40222222222222215,0.49058314613975507,0.4109932426184554

Information-Retrieval_evaluation_NanoClimateFEVER_results.csv

@@ -1,2 +1,3 @@
 epoch,steps,cosine-Accuracy@1,cosine-Accuracy@3,cosine-Accuracy@5,cosine-Accuracy@10,cosine-Precision@1,cosine-Recall@1,cosine-Precision@3,cosine-Recall@3,cosine-Precision@5,cosine-Recall@5,cosine-Precision@10,cosine-Recall@10,cosine-MRR@10,cosine-NDCG@10,cosine-MAP@100
 -1,-1,0.14,0.32,0.48,0.62,0.14,0.05833333333333333,0.12,0.155,0.10400000000000002,0.22066666666666668,0.07400000000000001,0.30733333333333335,0.27213492063492056,0.215125793679731,0.15431110143807805
+-1,-1,0.14,0.32,0.48,0.62,0.14,0.05833333333333333,0.12,0.155,0.10400000000000002,0.22066666666666668,0.07400000000000001,0.30733333333333335,0.27213492063492056,0.215125793679731,0.15431110143807805

Information-Retrieval_evaluation_NanoDBPedia_results.csv

@@ -1,2 +1,3 @@
 epoch,steps,cosine-Accuracy@1,cosine-Accuracy@3,cosine-Accuracy@5,cosine-Accuracy@10,cosine-Precision@1,cosine-Recall@1,cosine-Precision@3,cosine-Recall@3,cosine-Precision@5,cosine-Recall@5,cosine-Precision@10,cosine-Recall@10,cosine-MRR@10,cosine-NDCG@10,cosine-MAP@100
 -1,-1,0.62,0.84,0.88,0.88,0.62,0.05039842070870112,0.4933333333333333,0.13002690694209756,0.44,0.18830365543570443,0.37199999999999994,0.2679047211992138,0.7323333333333334,0.46809379506385207,0.33243413363446367
+-1,-1,0.62,0.84,0.88,0.88,0.62,0.05039842070870112,0.4933333333333333,0.13002690694209756,0.44,0.18830365543570443,0.37199999999999994,0.2679047211992138,0.7323333333333334,0.46809379506385207,0.33243413363446367

Information-Retrieval_evaluation_NanoFEVER_results.csv

@@ -1,2 +1,3 @@
 epoch,steps,cosine-Accuracy@1,cosine-Accuracy@3,cosine-Accuracy@5,cosine-Accuracy@10,cosine-Precision@1,cosine-Recall@1,cosine-Precision@3,cosine-Recall@3,cosine-Precision@5,cosine-Recall@5,cosine-Precision@10,cosine-Recall@10,cosine-MRR@10,cosine-NDCG@10,cosine-MAP@100
 -1,-1,0.62,0.88,0.94,0.96,0.62,0.5966666666666667,0.30666666666666664,0.8433333333333333,0.19599999999999995,0.8933333333333333,0.09999999999999998,0.9133333333333333,0.753,0.7821095700854137,0.7330432132878941
+-1,-1,0.62,0.88,0.94,0.96,0.62,0.5966666666666667,0.30666666666666664,0.8433333333333333,0.19599999999999995,0.8933333333333333,0.09999999999999998,0.9133333333333333,0.753,0.7821095700854137,0.7330432132878941

Information-Retrieval_evaluation_NanoFiQA2018_results.csv

@@ -1,2 +1,3 @@
 epoch,steps,cosine-Accuracy@1,cosine-Accuracy@3,cosine-Accuracy@5,cosine-Accuracy@10,cosine-Precision@1,cosine-Recall@1,cosine-Precision@3,cosine-Recall@3,cosine-Precision@5,cosine-Recall@5,cosine-Precision@10,cosine-Recall@10,cosine-MRR@10,cosine-NDCG@10,cosine-MAP@100
 -1,-1,0.22,0.38,0.54,0.6,0.22,0.11752380952380952,0.15999999999999998,0.21912698412698414,0.14400000000000002,0.34296031746031747,0.088,0.3807380952380952,0.33804761904761904,0.2959832185054632,0.24139316426365195
+-1,-1,0.22,0.38,0.54,0.6,0.22,0.11752380952380952,0.15999999999999998,0.21912698412698414,0.14400000000000002,0.34296031746031747,0.088,0.3807380952380952,0.33804761904761904,0.2959832185054632,0.24139316426365195

Information-Retrieval_evaluation_NanoHotpotQA_results.csv

@@ -1,2 +1,3 @@
 epoch,steps,cosine-Accuracy@1,cosine-Accuracy@3,cosine-Accuracy@5,cosine-Accuracy@10,cosine-Precision@1,cosine-Recall@1,cosine-Precision@3,cosine-Recall@3,cosine-Precision@5,cosine-Recall@5,cosine-Precision@10,cosine-Recall@10,cosine-MRR@10,cosine-NDCG@10,cosine-MAP@100
 -1,-1,0.6,0.74,0.78,0.86,0.6,0.3,0.32666666666666666,0.49,0.21599999999999994,0.54,0.12599999999999997,0.63,0.6806666666666666,0.5588160498147219,0.47611256957303766
+-1,-1,0.6,0.74,0.78,0.86,0.6,0.3,0.32666666666666666,0.49,0.21599999999999994,0.54,0.12599999999999997,0.63,0.6806666666666666,0.5588160498147219,0.47611256957303766

Information-Retrieval_evaluation_NanoMSMARCO_results.csv

@@ -1,2 +1,3 @@
 epoch,steps,cosine-Accuracy@1,cosine-Accuracy@3,cosine-Accuracy@5,cosine-Accuracy@10,cosine-Precision@1,cosine-Recall@1,cosine-Precision@3,cosine-Recall@3,cosine-Precision@5,cosine-Recall@5,cosine-Precision@10,cosine-Recall@10,cosine-MRR@10,cosine-NDCG@10,cosine-MAP@100
 -1,-1,0.22,0.5,0.62,0.74,0.22,0.22,0.16666666666666663,0.5,0.124,0.62,0.07400000000000001,0.74,0.39240476190476187,0.47667177266958005,0.406991563991564
+-1,-1,0.22,0.5,0.62,0.74,0.22,0.22,0.16666666666666663,0.5,0.124,0.62,0.07400000000000001,0.74,0.39240476190476187,0.47667177266958005,0.406991563991564

Information-Retrieval_evaluation_NanoNFCorpus_results.csv

@@ -1,2 +1,3 @@
 epoch,steps,cosine-Accuracy@1,cosine-Accuracy@3,cosine-Accuracy@5,cosine-Accuracy@10,cosine-Precision@1,cosine-Recall@1,cosine-Precision@3,cosine-Recall@3,cosine-Precision@5,cosine-Recall@5,cosine-Precision@10,cosine-Recall@10,cosine-MRR@10,cosine-NDCG@10,cosine-MAP@100
 -1,-1,0.34,0.5,0.58,0.6,0.34,0.01200107748257525,0.3133333333333333,0.042785241025884206,0.292,0.08113445148474485,0.25,0.10803989338634405,0.4345555555555555,0.2802878906182637,0.10597358556555182
+-1,-1,0.34,0.5,0.58,0.6,0.34,0.01200107748257525,0.3133333333333333,0.042785241025884206,0.292,0.08113445148474485,0.25,0.10803989338634405,0.4345555555555555,0.2802878906182637,0.10597358556555182

Information-Retrieval_evaluation_NanoNQ_results.csv

@@ -1,2 +1,3 @@
 epoch,steps,cosine-Accuracy@1,cosine-Accuracy@3,cosine-Accuracy@5,cosine-Accuracy@10,cosine-Precision@1,cosine-Recall@1,cosine-Precision@3,cosine-Recall@3,cosine-Precision@5,cosine-Recall@5,cosine-Precision@10,cosine-Recall@10,cosine-MRR@10,cosine-NDCG@10,cosine-MAP@100
 -1,-1,0.28,0.46,0.56,0.64,0.28,0.27,0.15999999999999998,0.45,0.11600000000000002,0.54,0.066,0.61,0.39785714285714285,0.4442430372694745,0.39869586832265574
+-1,-1,0.28,0.46,0.56,0.64,0.28,0.27,0.15999999999999998,0.45,0.11600000000000002,0.54,0.066,0.61,0.39785714285714285,0.4442430372694745,0.39869586832265574

Information-Retrieval_evaluation_NanoQuoraRetrieval_results.csv

@@ -1,2 +1,3 @@
 epoch,steps,cosine-Accuracy@1,cosine-Accuracy@3,cosine-Accuracy@5,cosine-Accuracy@10,cosine-Precision@1,cosine-Recall@1,cosine-Precision@3,cosine-Recall@3,cosine-Precision@5,cosine-Recall@5,cosine-Precision@10,cosine-Recall@10,cosine-MRR@10,cosine-NDCG@10,cosine-MAP@100
 -1,-1,0.96,1.0,1.0,1.0,0.96,0.8373333333333334,0.4133333333333333,0.9653333333333333,0.264,0.986,0.13999999999999999,1.0,0.9733333333333334,0.9736013358388067,0.958547619047619
+-1,-1,0.96,1.0,1.0,1.0,0.96,0.8373333333333334,0.4133333333333333,0.9653333333333333,0.264,0.986,0.13999999999999999,1.0,0.9733333333333334,0.9736013358388067,0.958547619047619

Information-Retrieval_evaluation_NanoSCIDOCS_results.csv

@@ -1,2 +1,3 @@
 epoch,steps,cosine-Accuracy@1,cosine-Accuracy@3,cosine-Accuracy@5,cosine-Accuracy@10,cosine-Precision@1,cosine-Recall@1,cosine-Precision@3,cosine-Recall@3,cosine-Precision@5,cosine-Recall@5,cosine-Precision@10,cosine-Recall@10,cosine-MRR@10,cosine-NDCG@10,cosine-MAP@100
 -1,-1,0.46,0.64,0.78,0.82,0.46,0.09766666666666668,0.3533333333333333,0.21966666666666665,0.3,0.30966666666666665,0.18799999999999997,0.38666666666666655,0.5706666666666667,0.3818424009361081,0.30532272577213904
+-1,-1,0.46,0.64,0.78,0.82,0.46,0.09766666666666668,0.3533333333333333,0.21966666666666665,0.3,0.30966666666666665,0.18799999999999997,0.38666666666666655,0.5706666666666667,0.3818424009361081,0.30532272577213904

Information-Retrieval_evaluation_NanoSciFact_results.csv

@@ -1,2 +1,3 @@
 epoch,steps,cosine-Accuracy@1,cosine-Accuracy@3,cosine-Accuracy@5,cosine-Accuracy@10,cosine-Precision@1,cosine-Recall@1,cosine-Precision@3,cosine-Recall@3,cosine-Precision@5,cosine-Recall@5,cosine-Precision@10,cosine-Recall@10,cosine-MRR@10,cosine-NDCG@10,cosine-MAP@100
 -1,-1,0.48,0.6,0.64,0.8,0.48,0.435,0.22666666666666668,0.585,0.148,0.63,0.09,0.79,0.5592777777777777,0.6050538780432089,0.5513100730514523
+-1,-1,0.48,0.6,0.64,0.8,0.48,0.435,0.22666666666666668,0.585,0.148,0.63,0.09,0.79,0.5592777777777777,0.6050538780432089,0.5513100730514523

Information-Retrieval_evaluation_NanoTouche2020_results.csv

@@ -1,2 +1,3 @@
 epoch,steps,cosine-Accuracy@1,cosine-Accuracy@3,cosine-Accuracy@5,cosine-Accuracy@10,cosine-Precision@1,cosine-Recall@1,cosine-Precision@3,cosine-Recall@3,cosine-Precision@5,cosine-Recall@5,cosine-Precision@10,cosine-Recall@10,cosine-MRR@10,cosine-NDCG@10,cosine-MAP@100
 -1,-1,0.4489795918367347,0.7142857142857143,0.8367346938775511,0.9795918367346939,0.4489795918367347,0.03145284890764548,0.3877551020408163,0.08052290820807267,0.37959183673469393,0.12752705262749714,0.3285714285714286,0.21259838452857663,0.6169663103336572,0.36562572315623365,0.2636080363851069
+-1,-1,0.4489795918367347,0.7142857142857143,0.8367346938775511,0.9795918367346939,0.4489795918367347,0.03145284890764548,0.3877551020408163,0.08052290820807267,0.37959183673469393,0.12752705262749714,0.3285714285714286,0.21259838452857663,0.6169663103336572,0.36562572315623365,0.2636080363851069

NanoBEIR_evaluation_mean_results.csv

@@ -1,2 +1,3 @@
 epoch,steps,cosine-Accuracy@1,cosine-Accuracy@3,cosine-Accuracy@5,cosine-Accuracy@10,cosine-Precision@1,cosine-Recall@1,cosine-Precision@3,cosine-Recall@3,cosine-Precision@5,cosine-Recall@5,cosine-Precision@10,cosine-Recall@10,cosine-MRR@10,cosine-NDCG@10,cosine-MAP@100
 -1,-1,0.42992150706436427,0.6257142857142857,0.7212872841444271,0.7891993720565149,0.42992150706436427,0.24818278127867163,0.27803244374672936,0.4031381056643362,0.22089167974882265,0.47843016489807155,0.15173626373626373,0.5466626482835049,0.5479589469487428,0.4875413547554317,0.4106720689962823
+-1,-1,0.42992150706436427,0.6257142857142857,0.7212872841444271,0.7891993720565149,0.42992150706436427,0.24818278127867163,0.27803244374672936,0.4031381056643362,0.22089167974882265,0.47843016489807155,0.15173626373626373,0.5466626482835049,0.5479589469487428,0.4875413547554317,0.4106720689962823

README.md

@@ -5,232 +5,51 @@ tags:
 - feature-extraction
 - dense
 - generated_from_trainer
-- dataset_size:359997
+- dataset_size:100000
 - loss:MultipleNegativesRankingLoss
-base_model: sentence-transformers/all-MiniLM-L6-v2
+base_model: prajjwal1/bert-small
 widget:
-- source_sentence: When do you use Ms. or Mrs.? Is one for a married woman and one
-    for one that's not married? Which one is for what?
+- source_sentence: How do I polish my English skills?
   sentences:
-  - When do you use Ms. or Mrs.? Is one for a married woman and one for one that's
-    not married? Which one is for what?
-  - Nations that do/does otherwise? Which one do I use?
-  - Why don't bikes have a gear indicator?
-- source_sentence: Which ointment is applied to the face of UFC fighters at the commencement
-    of a bout? What does it do?
+  - How can we polish English skills?
+  - Why should I move to Israel as a Jew?
+  - What are vitamins responsible for?
+- source_sentence: Can I use the Kozuka Gothic Pro font as a font-face on my web site?
   sentences:
-  - How can I save a Snapchat video that others posted?
-  - Which ointment is applied to the face of UFC fighters at the commencement of a
-    bout? What does it do?
-  - How do I get the body of a UFC Fighter?
-- source_sentence: Do you love the life you live?
+  - Can I use the Kozuka Gothic Pro font as a font-face on my web site?
+  - Why are Google, Facebook, YouTube and other social networking sites banned in
+    China?
+  - What font is used in Bloomberg Terminal?
+- source_sentence: Is Quora the best Q&A site?
   sentences:
-  - Can I do shoulder and triceps workout on same day? What other combinations like
-    this can I do?
-  - Do you love the life you're living?
-  - Where can you find an online TI-84 calculator?
-- source_sentence: Ordered food on Swiggy 3 days ago.After accepting my money, said
-    no more on Menu! When if ever will I atleast get refund in cr card a/c?
+  - What was the best Quora question ever?
+  - Is Quora the best inquiry site?
+  - Where do I buy Oway hair products online?
+- source_sentence: How can I customize my walking speed on Google Maps?
   sentences:
-  - Is getting to the Tel Aviv airport to catch a 5:30 AM flight very expensive?
-  - How do I die and make it look like an accident?
-  - Ordered food on Swiggy 3 days ago.After accepting my money, said no more on Menu!
-    When if ever will I atleast get refund in cr card a/c?
-- source_sentence: How do you earn money on Quora?
+  - How do I bring back Google maps icon in my home screen?
+  - How many pages are there in all the Harry Potter books combined?
+  - How can I customize my walking speed on Google Maps?
+- source_sentence: DId something exist before the Big Bang?
   sentences:
-  - What is a cheap healthy diet I can keep the same and eat every day?
-  - What are some things new employees should know going into their first day at Maximus?
-  - What is the best way to make money on Quora?
+  - How can I improve my memory problem?
+  - Where can I buy Fairy Tail Manga?
+  - Is there a scientific name for what existed before the Big Bang?
 pipeline_tag: sentence-similarity
 library_name: sentence-transformers
-metrics:
-- cosine_accuracy@1
-- cosine_accuracy@3
-- cosine_accuracy@5
-- cosine_accuracy@10
-- cosine_precision@1
-- cosine_precision@3
-- cosine_precision@5
-- cosine_precision@10
-- cosine_recall@1
-- cosine_recall@3
-- cosine_recall@5
-- cosine_recall@10
-- cosine_ndcg@10
-- cosine_mrr@10
-- cosine_map@100
-model-index:
-- name: SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2
-  results:
-  - task:
-      type: information-retrieval
-      name: Information Retrieval
-    dataset:
-      name: NanoMSMARCO
-      type: NanoMSMARCO
-    metrics:
-    - type: cosine_accuracy@1
-      value: 0.22
-      name: Cosine Accuracy@1
-    - type: cosine_accuracy@3
-      value: 0.5
-      name: Cosine Accuracy@3
-    - type: cosine_accuracy@5
-      value: 0.62
-      name: Cosine Accuracy@5
-    - type: cosine_accuracy@10
-      value: 0.74
-      name: Cosine Accuracy@10
-    - type: cosine_precision@1
-      value: 0.22
-      name: Cosine Precision@1
-    - type: cosine_precision@3
-      value: 0.16666666666666663
-      name: Cosine Precision@3
-    - type: cosine_precision@5
-      value: 0.124
-      name: Cosine Precision@5
-    - type: cosine_precision@10
-      value: 0.07400000000000001
-      name: Cosine Precision@10
-    - type: cosine_recall@1
-      value: 0.22
-      name: Cosine Recall@1
-    - type: cosine_recall@3
-      value: 0.5
-      name: Cosine Recall@3
-    - type: cosine_recall@5
-      value: 0.62
-      name: Cosine Recall@5
-    - type: cosine_recall@10
-      value: 0.74
-      name: Cosine Recall@10
-    - type: cosine_ndcg@10
-      value: 0.47667177266958005
-      name: Cosine Ndcg@10
-    - type: cosine_mrr@10
-      value: 0.39240476190476187
-      name: Cosine Mrr@10
-    - type: cosine_map@100
-      value: 0.406991563991564
-      name: Cosine Map@100
-  - task:
-      type: information-retrieval
-      name: Information Retrieval
-    dataset:
-      name: NanoNQ
-      type: NanoNQ
-    metrics:
-    - type: cosine_accuracy@1
-      value: 0.28
-      name: Cosine Accuracy@1
-    - type: cosine_accuracy@3
-      value: 0.46
-      name: Cosine Accuracy@3
-    - type: cosine_accuracy@5
-      value: 0.56
-      name: Cosine Accuracy@5
-    - type: cosine_accuracy@10
-      value: 0.64
-      name: Cosine Accuracy@10
-    - type: cosine_precision@1
-      value: 0.28
-      name: Cosine Precision@1
-    - type: cosine_precision@3
-      value: 0.15999999999999998
-      name: Cosine Precision@3
-    - type: cosine_precision@5
-      value: 0.11600000000000002
-      name: Cosine Precision@5
-    - type: cosine_precision@10
-      value: 0.066
-      name: Cosine Precision@10
-    - type: cosine_recall@1
-      value: 0.27
-      name: Cosine Recall@1
-    - type: cosine_recall@3
-      value: 0.45
-      name: Cosine Recall@3
-    - type: cosine_recall@5
-      value: 0.54
-      name: Cosine Recall@5
-    - type: cosine_recall@10
-      value: 0.61
-      name: Cosine Recall@10
-    - type: cosine_ndcg@10
-      value: 0.4442430372694745
-      name: Cosine Ndcg@10
-    - type: cosine_mrr@10
-      value: 0.39785714285714285
-      name: Cosine Mrr@10
-    - type: cosine_map@100
-      value: 0.39869586832265574
-      name: Cosine Map@100
-  - task:
-      type: nano-beir
-      name: Nano BEIR
-    dataset:
-      name: NanoBEIR mean
-      type: NanoBEIR_mean
-    metrics:
-    - type: cosine_accuracy@1
-      value: 0.25
-      name: Cosine Accuracy@1
-    - type: cosine_accuracy@3
-      value: 0.48
-      name: Cosine Accuracy@3
-    - type: cosine_accuracy@5
-      value: 0.5900000000000001
-      name: Cosine Accuracy@5
-    - type: cosine_accuracy@10
-      value: 0.69
-      name: Cosine Accuracy@10
-    - type: cosine_precision@1
-      value: 0.25
-      name: Cosine Precision@1
-    - type: cosine_precision@3
-      value: 0.1633333333333333
-      name: Cosine Precision@3
-    - type: cosine_precision@5
-      value: 0.12000000000000001
-      name: Cosine Precision@5
-    - type: cosine_precision@10
-      value: 0.07
-      name: Cosine Precision@10
-    - type: cosine_recall@1
-      value: 0.245
-      name: Cosine Recall@1
-    - type: cosine_recall@3
-      value: 0.475
-      name: Cosine Recall@3
-    - type: cosine_recall@5
-      value: 0.5800000000000001
-      name: Cosine Recall@5
-    - type: cosine_recall@10
-      value: 0.675
-      name: Cosine Recall@10
-    - type: cosine_ndcg@10
-      value: 0.46045740496952725
-      name: Cosine Ndcg@10
-    - type: cosine_mrr@10
-      value: 0.39513095238095236
-      name: Cosine Mrr@10
-    - type: cosine_map@100
-      value: 0.4028437161571099
-      name: Cosine Map@100
 ---
 
-# SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2
+# SentenceTransformer based on prajjwal1/bert-small
 
-This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2). It maps sentences & paragraphs to a 384-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [prajjwal1/bert-small](https://huggingface.co/prajjwal1/bert-small). It maps sentences & paragraphs to a 512-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:** [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2) <!-- at revision c9745ed1d9f207416be6d2e6f8de32d1f16199bf -->
+- **Base model:** [prajjwal1/bert-small](https://huggingface.co/prajjwal1/bert-small) <!-- at revision 0ec5f86f27c1a77d704439db5e01c307ea11b9d4 -->
 - **Maximum Sequence Length:** 128 tokens
-- **Output Dimensionality:** 384 dimensions
+- **Output Dimensionality:** 512 dimensions
 - **Similarity Function:** Cosine Similarity
 <!-- - **Training Dataset:** Unknown -->
 <!-- - **Language:** Unknown -->
@@ -247,8 +66,7 @@ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [s
 ```
 SentenceTransformer(
   (0): Transformer({'max_seq_length': 128, 'do_lower_case': False, 'architecture': '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()
+  (1): Pooling({'word_embedding_dimension': 512, '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})
 )
 ```
 
@@ -267,23 +85,23 @@ Then you can load this model and run inference.
 from sentence_transformers import SentenceTransformer
 
 # Download from the 🤗 Hub
-model = SentenceTransformer("redis/model-a-baseline")
+model = SentenceTransformer("sentence_transformers_model_id")
 # Run inference
 sentences = [
-    'How do you earn money on Quora?',
-    'What is the best way to make money on Quora?',
-    'What are some things new employees should know going into their first day at Maximus?',
+    'DId something exist before the Big Bang?',
+    'Is there a scientific name for what existed before the Big Bang?',
+    'Where can I buy Fairy Tail Manga?',
 ]
 embeddings = model.encode(sentences)
 print(embeddings.shape)
-# [3, 384]
+# [3, 512]
 
 # Get the similarity scores for the embeddings
 similarities = model.similarity(embeddings, embeddings)
 print(similarities)
-# tensor([[1.0000, 0.9894, 0.0074],
-#         [0.9894, 1.0000, 0.0136],
-#         [0.0074, 0.0136, 1.0000]])
+# tensor([[ 1.0000,  0.7596, -0.0398],
+#         [ 0.7596,  1.0000, -0.0308],
+#         [-0.0398, -0.0308,  1.0000]])
 ```
 
 <!--
@@ -310,65 +128,6 @@ You can finetune this model on your own dataset.
 *List how the model may foreseeably be misused and address what users ought not to do with the model.*
 -->
 
-## Evaluation
-
-### Metrics
-
-#### Information Retrieval
-
-* Datasets: `NanoMSMARCO` and `NanoNQ`
-* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
-
-| Metric              | NanoMSMARCO | NanoNQ     |
-|:--------------------|:------------|:-----------|
-| cosine_accuracy@1   | 0.22        | 0.28       |
-| cosine_accuracy@3   | 0.5         | 0.46       |
-| cosine_accuracy@5   | 0.62        | 0.56       |
-| cosine_accuracy@10  | 0.74        | 0.64       |
-| cosine_precision@1  | 0.22        | 0.28       |
-| cosine_precision@3  | 0.1667      | 0.16       |
-| cosine_precision@5  | 0.124       | 0.116      |
-| cosine_precision@10 | 0.074       | 0.066      |
-| cosine_recall@1     | 0.22        | 0.27       |
-| cosine_recall@3     | 0.5         | 0.45       |
-| cosine_recall@5     | 0.62        | 0.54       |
-| cosine_recall@10    | 0.74        | 0.61       |
-| **cosine_ndcg@10**  | **0.4767**  | **0.4442** |
-| cosine_mrr@10       | 0.3924      | 0.3979     |
-| cosine_map@100      | 0.407       | 0.3987     |
-
-#### Nano BEIR
-
-* Dataset: `NanoBEIR_mean`
-* Evaluated with [<code>NanoBEIREvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.NanoBEIREvaluator) with these parameters:
-  ```json
-  {
-      "dataset_names": [
-          "msmarco",
-          "nq"
-      ],
-      "dataset_id": "lightonai/NanoBEIR-en"
-  }
-  ```
-
-| Metric              | Value      |
-|:--------------------|:-----------|
-| cosine_accuracy@1   | 0.25       |
-| cosine_accuracy@3   | 0.48       |
-| cosine_accuracy@5   | 0.59       |
-| cosine_accuracy@10  | 0.69       |
-| cosine_precision@1  | 0.25       |
-| cosine_precision@3  | 0.1633     |
-| cosine_precision@5  | 0.12       |
-| cosine_precision@10 | 0.07       |
-| cosine_recall@1     | 0.245      |
-| cosine_recall@3     | 0.475      |
-| cosine_recall@5     | 0.58       |
-| cosine_recall@10    | 0.675      |
-| **cosine_ndcg@10**  | **0.4605** |
-| cosine_mrr@10       | 0.3951     |
-| cosine_map@100      | 0.4028     |
-
 <!--
 ## Bias, Risks and Limitations
 
@@ -387,49 +146,23 @@ You can finetune this model on your own dataset.
 
 #### Unnamed Dataset
 
-* Size: 359,997 training samples
-* Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
-* Approximate statistics based on the first 1000 samples:
-  |         | anchor                                                                            | positive                                                                          | negative                                                                           |
-  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
-  | type    | string                                                                            | string                                                                            | string                                                                             |
-  | details | <ul><li>min: 4 tokens</li><li>mean: 15.46 tokens</li><li>max: 49 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 15.52 tokens</li><li>max: 49 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 16.99 tokens</li><li>max: 128 tokens</li></ul> |
-* Samples:
-  | anchor                                                                          | positive                                                                                             | negative                                                                                                                 |
-  |:--------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------|
-  | <code>Shall I upgrade my iPhone 5s to iOS 10 final version?</code>              | <code>Should I upgrade an iPhone 5s to iOS 10?</code>                                                | <code>Whether extension of CA-articleship is to be served at same firm/company?</code>                                   |
-  | <code>Is Donald Trump really going to be the president of United States?</code> | <code>Do you think Donald Trump could conceivably be the next President of the United States?</code> | <code>Since solid carbon dioxide is dry ice and incredibly cold, why doesn't it have an effect on global warming?</code> |
-  | <code>What are real tips to improve work life balance?</code>                   | <code>What are the best ways to create a work life balance?</code>                                   | <code>How do you open a briefcase combination lock without the combination?</code>                                       |
-* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
-  ```json
-  {
-      "scale": 7.0,
-      "similarity_fct": "cos_sim",
-      "gather_across_devices": false
-  }
-  ```
-
-### Evaluation Dataset
-
-#### Unnamed Dataset
-
-* Size: 40,000 evaluation samples
-* Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
+* Size: 100,000 training samples
+* Columns: <code>sentence_0</code>, <code>sentence_1</code>, and <code>sentence_2</code>
 * Approximate statistics based on the first 1000 samples:
-  |         | anchor                                                                            | positive                                                                          | negative                                                                          |
-  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
-  | type    | string                                                                            | string                                                                            | string                                                                            |
-  | details | <ul><li>min: 6 tokens</li><li>mean: 15.71 tokens</li><li>max: 65 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 15.79 tokens</li><li>max: 65 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 16.97 tokens</li><li>max: 78 tokens</li></ul> |
+  |         | sentence_0                                                                        | sentence_1                                                                       | sentence_2                                                                         |
+  |:--------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                           | string                                                                             |
+  | details | <ul><li>min: 3 tokens</li><li>mean: 15.53 tokens</li><li>max: 59 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 15.5 tokens</li><li>max: 59 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 16.87 tokens</li><li>max: 128 tokens</li></ul> |
 * Samples:
-  | anchor                                                                                                            | positive                                                                                                          | negative                                                                                                                                  |
-  |:------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------|
-  | <code>Why were feathered dinosaur fossils only found in the last 20 years?</code>                                 | <code>Why were feathered dinosaur fossils only found in the last 20 years?</code>                                 | <code>Why are only few people aware that many dinosaurs had feathers?</code>                                                              |
-  | <code>If FOX News is the conservative news station, which cable news network is for liberals/progressives?</code> | <code>If FOX News is the conservative news station, which cable news network is for liberals/progressives?</code> | <code>How much did Fox News and conservative leaning media networks stoke the anger that contributed to Donald Trump's popularity?</code> |
-  | <code>How can guys last longer during sex?</code>                                                                 | <code>How do I last longer in sex?</code>                                                                         | <code>What is a permanent solution for rough and puffy hair?</code>                                                                       |
+  | sentence_0                                                                              | sentence_1                                                                              | sentence_2                                                             |
+  |:----------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------|:-----------------------------------------------------------------------|
+  | <code>Is there visitor entry facility in Jaipur airport. How much is the ticket?</code> | <code>Is there visitor entry facility in Jaipur airport. How much is the ticket?</code> | <code>How much is the airport tax in bogota?</code>                    |
+  | <code>Which concept is more important: good planning or hard work?</code>               | <code>Which concept is more important: good planning or hard work?</code>               | <code>What is important in life: luck or hard work?</code>             |
+  | <code>What is the most efficient way to make money?</code>                              | <code>How can I make my money make money?</code>                                        | <code>What can one learn about Quantum Mechanics in 10 minutes?</code> |
 * Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
   ```json
   {
-      "scale": 7.0,
+      "scale": 20.0,
       "similarity_fct": "cos_sim",
       "gather_across_devices": false
   }
@@ -438,49 +171,36 @@ You can finetune this model on your own dataset.
 ### Training Hyperparameters
 #### Non-Default Hyperparameters
 
-- `eval_strategy`: steps
-- `per_device_train_batch_size`: 128
-- `per_device_eval_batch_size`: 128
-- `learning_rate`: 2e-05
-- `weight_decay`: 0.0001
-- `max_steps`: 5000
-- `warmup_ratio`: 0.1
+- `per_device_train_batch_size`: 64
+- `per_device_eval_batch_size`: 64
 - `fp16`: True
-- `dataloader_drop_last`: True
-- `dataloader_num_workers`: 1
-- `dataloader_prefetch_factor`: 1
-- `load_best_model_at_end`: True
-- `optim`: adamw_torch
-- `ddp_find_unused_parameters`: False
-- `push_to_hub`: True
-- `hub_model_id`: redis/model-a-baseline
-- `eval_on_start`: True
+- `multi_dataset_batch_sampler`: round_robin
 
 #### All Hyperparameters
 <details><summary>Click to expand</summary>
 
 - `overwrite_output_dir`: False
 - `do_predict`: False
-- `eval_strategy`: steps
+- `eval_strategy`: no
 - `prediction_loss_only`: True
-- `per_device_train_batch_size`: 128
-- `per_device_eval_batch_size`: 128
+- `per_device_train_batch_size`: 64
+- `per_device_eval_batch_size`: 64
 - `per_gpu_train_batch_size`: None
 - `per_gpu_eval_batch_size`: None
 - `gradient_accumulation_steps`: 1
 - `eval_accumulation_steps`: None
 - `torch_empty_cache_steps`: None
-- `learning_rate`: 2e-05
-- `weight_decay`: 0.0001
+- `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`: 3.0
-- `max_steps`: 5000
+- `max_grad_norm`: 1
+- `num_train_epochs`: 3
+- `max_steps`: -1
 - `lr_scheduler_type`: linear
 - `lr_scheduler_kwargs`: {}
-- `warmup_ratio`: 0.1
+- `warmup_ratio`: 0.0
 - `warmup_steps`: 0
 - `log_level`: passive
 - `log_level_replica`: warning
@@ -508,14 +228,14 @@ You can finetune this model on your own dataset.
 - `tpu_num_cores`: None
 - `tpu_metrics_debug`: False
 - `debug`: []
-- `dataloader_drop_last`: True
-- `dataloader_num_workers`: 1
-- `dataloader_prefetch_factor`: 1
+- `dataloader_drop_last`: False
+- `dataloader_num_workers`: 0
+- `dataloader_prefetch_factor`: None
 - `past_index`: -1
 - `disable_tqdm`: False
 - `remove_unused_columns`: True
 - `label_names`: None
-- `load_best_model_at_end`: True
+- `load_best_model_at_end`: False
 - `ignore_data_skip`: False
 - `fsdp`: []
 - `fsdp_min_num_params`: 0
@@ -525,23 +245,23 @@ You can finetune this model on your own dataset.
 - `parallelism_config`: None
 - `deepspeed`: None
 - `label_smoothing_factor`: 0.0
-- `optim`: adamw_torch
+- `optim`: adamw_torch_fused
 - `optim_args`: None
 - `adafactor`: False
 - `group_by_length`: False
 - `length_column_name`: length
 - `project`: huggingface
 - `trackio_space_id`: trackio
-- `ddp_find_unused_parameters`: False
+- `ddp_find_unused_parameters`: None
 - `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`: True
+- `push_to_hub`: False
 - `resume_from_checkpoint`: None
-- `hub_model_id`: redis/model-a-baseline
+- `hub_model_id`: None
 - `hub_strategy`: every_save
 - `hub_private_repo`: None
 - `hub_always_push`: False
@@ -568,43 +288,31 @@ You can finetune this model on your own dataset.
 - `neftune_noise_alpha`: None
 - `optim_target_modules`: None
 - `batch_eval_metrics`: False
-- `eval_on_start`: True
+- `eval_on_start`: False
 - `use_liger_kernel`: False
 - `liger_kernel_config`: None
 - `eval_use_gather_object`: False
 - `average_tokens_across_devices`: True
 - `prompts`: None
 - `batch_sampler`: batch_sampler
-- `multi_dataset_batch_sampler`: proportional
+- `multi_dataset_batch_sampler`: round_robin
 - `router_mapping`: {}
 - `learning_rate_mapping`: {}
 
 </details>
 
 ### Training Logs
-| Epoch  | Step | Training Loss | Validation Loss | NanoMSMARCO_cosine_ndcg@10 | NanoNQ_cosine_ndcg@10 | NanoBEIR_mean_cosine_ndcg@10 |
-|:------:|:----:|:-------------:|:---------------:|:--------------------------:|:---------------------:|:----------------------------:|
-| 0      | 0    | -             | 0.5501          | 0.5540                     | 0.5931                | 0.5735                       |
-| 0.0889 | 250  | 0.6218        | 0.4360          | 0.5499                     | 0.5725                | 0.5612                       |
-| 0.1778 | 500  | 0.557         | 0.4231          | 0.5414                     | 0.5239                | 0.5326                       |
-| 0.2667 | 750  | 0.5359        | 0.4146          | 0.5188                     | 0.5189                | 0.5188                       |
-| 0.3556 | 1000 | 0.5213        | 0.4095          | 0.4998                     | 0.5138                | 0.5068                       |
-| 0.4445 | 1250 | 0.51          | 0.4058          | 0.5021                     | 0.4988                | 0.5005                       |
-| 0.5334 | 1500 | 0.5086        | 0.4030          | 0.5040                     | 0.4970                | 0.5005                       |
-| 0.6223 | 1750 | 0.5031        | 0.4002          | 0.4963                     | 0.4997                | 0.4980                       |
-| 0.7112 | 2000 | 0.4964        | 0.3979          | 0.5033                     | 0.4880                | 0.4956                       |
-| 0.8001 | 2250 | 0.4927        | 0.3960          | 0.5077                     | 0.4881                | 0.4979                       |
-| 0.8890 | 2500 | 0.4925        | 0.3946          | 0.4939                     | 0.4826                | 0.4882                       |
-| 0.9780 | 2750 | 0.4889        | 0.3936          | 0.4953                     | 0.4778                | 0.4865                       |
-| 1.0669 | 3000 | 0.4819        | 0.3917          | 0.4838                     | 0.4723                | 0.4781                       |
-| 1.1558 | 3250 | 0.4798        | 0.3910          | 0.4900                     | 0.4587                | 0.4743                       |
-| 1.2447 | 3500 | 0.4773        | 0.3905          | 0.4888                     | 0.4557                | 0.4723                       |
-| 1.3336 | 3750 | 0.476         | 0.3899          | 0.4782                     | 0.4512                | 0.4647                       |
-| 1.4225 | 4000 | 0.4738        | 0.3891          | 0.4873                     | 0.4508                | 0.4691                       |
-| 1.5114 | 4250 | 0.4727        | 0.3887          | 0.4849                     | 0.4464                | 0.4657                       |
-| 1.6003 | 4500 | 0.4737        | 0.3887          | 0.4772                     | 0.4482                | 0.4627                       |
-| 1.6892 | 4750 | 0.4722        | 0.3884          | 0.4810                     | 0.4432                | 0.4621                       |
-| 1.7781 | 5000 | 0.4739        | 0.3883          | 0.4767                     | 0.4442                | 0.4605                       |
+| Epoch  | Step | Training Loss |
+|:------:|:----:|:-------------:|
+| 0.3199 | 500  | 0.2284        |
+| 0.6398 | 1000 | 0.0571        |
+| 0.9597 | 1500 | 0.0486        |
+| 1.2796 | 2000 | 0.0378        |
+| 1.5995 | 2500 | 0.0367        |
+| 1.9194 | 3000 | 0.0338        |
+| 2.2393 | 3500 | 0.0327        |
+| 2.5592 | 4000 | 0.0285        |
+| 2.8791 | 4500 | 0.0285        |
 
 
 ### Framework Versions
@@ -613,7 +321,7 @@ You can finetune this model on your own dataset.
 - Transformers: 4.57.3
 - PyTorch: 2.9.1+cu128
 - Accelerate: 1.12.0
-- Datasets: 2.21.0
+- Datasets: 4.4.2
 - Tokenizers: 0.22.1
 
 ## Citation

config.json

@@ -15,7 +15,7 @@
   "max_position_embeddings": 512,
   "model_type": "bert",
   "num_attention_heads": 12,
-  "num_hidden_layers": 6,
+  "num_hidden_layers": 12,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "transformers_version": "4.57.3",

config_sentence_transformers.json

@@ -1,10 +1,10 @@
 {
+  "model_type": "SentenceTransformer",
   "__version__": {
     "sentence_transformers": "5.2.0",
     "transformers": "4.57.3",
     "pytorch": "2.9.1+cu128"
   },
-  "model_type": "SentenceTransformer",
   "prompts": {
     "query": "",
     "document": ""

eval/Information-Retrieval_evaluation_NanoMSMARCO_results.csv

@@ -41,3 +41,24 @@ epoch,steps,cosine-Accuracy@1,cosine-Accuracy@3,cosine-Accuracy@5,cosine-Accurac
 1.600284495021337,4500,0.22,0.5,0.62,0.74,0.22,0.22,0.16666666666666663,0.5,0.124,0.62,0.07400000000000001,0.74,0.39304761904761903,0.477190878555405,0.4074930244047891
 1.689189189189189,4750,0.22,0.5,0.62,0.74,0.22,0.22,0.16666666666666663,0.5,0.124,0.62,0.07400000000000001,0.74,0.3977380952380953,0.4810433177745632,0.41242013542013545
 1.7780938833570412,5000,0.22,0.5,0.62,0.74,0.22,0.22,0.16666666666666663,0.5,0.124,0.62,0.07400000000000001,0.74,0.39240476190476187,0.47667177266958005,0.406991563991564
+0,0,0.38,0.62,0.68,0.8,0.38,0.38,0.20666666666666667,0.62,0.136,0.68,0.08,0.8,0.5215238095238095,0.5887227948760404,0.5325402082997991
+0.08890469416785206,250,0.36,0.58,0.7,0.8,0.36,0.36,0.19333333333333333,0.58,0.14,0.7,0.08,0.8,0.49566666666666653,0.5682208870857596,0.5060752560237854
+0.17780938833570412,500,0.46,0.52,0.66,0.82,0.46,0.46,0.1733333333333333,0.52,0.132,0.66,0.08199999999999999,0.82,0.5442698412698412,0.6079332934407035,0.5525232913302173
+0.26671408250355616,750,0.34,0.56,0.68,0.82,0.34,0.34,0.18666666666666668,0.56,0.136,0.68,0.08199999999999999,0.82,0.49257142857142855,0.570761747972715,0.501199333481399
+0.35561877667140823,1000,0.38,0.54,0.66,0.84,0.38,0.38,0.18,0.54,0.132,0.66,0.08399999999999999,0.84,0.5138174603174603,0.5907796206498028,0.5200605666139135
+0.4445234708392603,1250,0.32,0.52,0.68,0.84,0.32,0.32,0.1733333333333333,0.52,0.136,0.68,0.08399999999999999,0.84,0.4792619047619048,0.5650039509697375,0.48537099069647
+0.5334281650071123,1500,0.34,0.54,0.66,0.82,0.34,0.34,0.18,0.54,0.132,0.66,0.08199999999999999,0.82,0.48223809523809513,0.5621823293729915,0.4903570008482093
+0.6223328591749644,1750,0.32,0.54,0.7,0.84,0.32,0.32,0.18,0.54,0.14,0.7,0.08399999999999999,0.84,0.4777380952380952,0.5639657391980877,0.48402486528393973
+0.7112375533428165,2000,0.3,0.56,0.68,0.84,0.3,0.3,0.18666666666666665,0.56,0.136,0.68,0.08399999999999999,0.84,0.4657698412698412,0.5549697038974795,0.47175548948334617
+0.8001422475106685,2250,0.3,0.6,0.64,0.84,0.3,0.3,0.19999999999999996,0.6,0.12800000000000003,0.64,0.08399999999999999,0.84,0.4662936507936507,0.5551828646772121,0.47254903555810995
+0.8890469416785206,2500,0.3,0.58,0.68,0.82,0.3,0.3,0.19333333333333333,0.58,0.136,0.68,0.08199999999999999,0.82,0.46343650793650787,0.5488219261760997,0.47160327784622585
+0.9779516358463727,2750,0.3,0.58,0.66,0.8,0.3,0.3,0.19333333333333333,0.58,0.132,0.66,0.08,0.8,0.4584126984126983,0.5406150732586964,0.46848540009516737
+1.0668563300142249,3000,0.3,0.54,0.62,0.8,0.3,0.3,0.17999999999999997,0.54,0.124,0.62,0.08,0.8,0.4522698412698412,0.5352823586843005,0.46138471171690987
+1.1557610241820768,3250,0.3,0.56,0.62,0.8,0.3,0.3,0.18666666666666665,0.56,0.124,0.62,0.08,0.8,0.4577936507936507,0.5397064205355451,0.46711339833994286
+1.2446657183499288,3500,0.3,0.56,0.64,0.82,0.3,0.3,0.18666666666666665,0.56,0.12800000000000003,0.64,0.08199999999999999,0.82,0.45588095238095233,0.5424752590573788,0.4635320155104427
+1.333570412517781,3750,0.3,0.56,0.62,0.8,0.3,0.3,0.18666666666666665,0.56,0.124,0.62,0.08,0.8,0.45290476190476187,0.535685201863328,0.46226898927806376
+1.422475106685633,4000,0.3,0.56,0.64,0.8,0.3,0.3,0.18666666666666665,0.56,0.12800000000000003,0.64,0.08,0.8,0.45107142857142857,0.5344943654008751,0.46033432811764724
+1.5113798008534851,4250,0.3,0.56,0.66,0.8,0.3,0.3,0.18666666666666665,0.56,0.132,0.66,0.08,0.8,0.45479365079365075,0.5374371752523998,0.46430135877767453
+1.600284495021337,4500,0.3,0.56,0.66,0.8,0.3,0.3,0.18666666666666665,0.56,0.132,0.66,0.08,0.8,0.45607142857142846,0.5386023478916117,0.46551784920060785
+1.689189189189189,4750,0.3,0.56,0.66,0.8,0.3,0.3,0.18666666666666665,0.56,0.132,0.66,0.08,0.8,0.4514603174603174,0.5348185801809706,0.46079536150124384
+1.7780938833570412,5000,0.3,0.56,0.66,0.8,0.3,0.3,0.18666666666666665,0.56,0.132,0.66,0.08,0.8,0.4522142857142857,0.5355647548788993,0.4614012040294735

eval/Information-Retrieval_evaluation_NanoNQ_results.csv

@@ -41,3 +41,24 @@ epoch,steps,cosine-Accuracy@1,cosine-Accuracy@3,cosine-Accuracy@5,cosine-Accurac
 1.600284495021337,4500,0.28,0.46,0.56,0.64,0.28,0.27,0.15999999999999998,0.45,0.11600000000000002,0.54,0.066,0.61,0.4007142857142857,0.4481867157733463,0.4052506909192797
 1.689189189189189,4750,0.28,0.46,0.56,0.64,0.28,0.27,0.15999999999999998,0.45,0.11600000000000002,0.54,0.066,0.61,0.39452380952380955,0.4432300264150815,0.3986881566666595
 1.7780938833570412,5000,0.28,0.46,0.56,0.64,0.28,0.27,0.15999999999999998,0.45,0.11600000000000002,0.54,0.066,0.61,0.39785714285714285,0.4442430372694745,0.39869586832265574
+0,0,0.44,0.62,0.7,0.72,0.44,0.42,0.20666666666666664,0.59,0.15200000000000002,0.69,0.07800000000000001,0.71,0.5425,0.5785694545006416,0.5396412232598975
+0.08890469416785206,250,0.38,0.58,0.66,0.72,0.38,0.36,0.2,0.57,0.14,0.64,0.07800000000000001,0.71,0.4930793650793651,0.5422057555897661,0.49385214768969143
+0.17780938833570412,500,0.4,0.54,0.64,0.76,0.4,0.38,0.19333333333333333,0.53,0.136,0.62,0.08199999999999999,0.74,0.49762698412698403,0.5506330785793723,0.49331663084034116
+0.26671408250355616,750,0.4,0.52,0.64,0.72,0.4,0.38,0.18666666666666665,0.51,0.136,0.62,0.07600000000000001,0.7,0.4908888888888888,0.535216682535339,0.4880542729584059
+0.35561877667140823,1000,0.38,0.56,0.66,0.68,0.38,0.37,0.19333333333333333,0.54,0.14,0.64,0.07200000000000001,0.66,0.4911666666666666,0.5296288982101829,0.4960611298125779
+0.4445234708392603,1250,0.32,0.54,0.58,0.7,0.32,0.31,0.18666666666666665,0.52,0.124,0.56,0.07400000000000001,0.68,0.4397222222222223,0.4935908199243542,0.44277302657010376
+0.5334281650071123,1500,0.34,0.52,0.6,0.7,0.34,0.33,0.18,0.5,0.128,0.58,0.07400000000000001,0.68,0.44991269841269843,0.5013708837543213,0.4529363607687501
+0.6223328591749644,1750,0.36,0.52,0.62,0.7,0.36,0.35,0.18,0.5,0.132,0.6,0.07400000000000001,0.68,0.47227777777777774,0.5174421641037986,0.47164766799780955
+0.7112375533428165,2000,0.36,0.52,0.6,0.72,0.36,0.35,0.18666666666666665,0.51,0.128,0.58,0.076,0.7,0.46496825396825403,0.5178517274916633,0.4655755809678257
+0.8001422475106685,2250,0.34,0.56,0.6,0.72,0.34,0.33,0.19333333333333333,0.54,0.128,0.58,0.076,0.7,0.46552380952380956,0.5171947252972893,0.46208163028895166
+0.8890469416785206,2500,0.34,0.54,0.58,0.72,0.34,0.33,0.18666666666666665,0.52,0.124,0.56,0.076,0.7,0.4533571428571429,0.5079369963287358,0.4525704587128079
+0.9779516358463727,2750,0.3,0.56,0.6,0.72,0.3,0.29,0.18666666666666665,0.53,0.128,0.58,0.076,0.7,0.431436507936508,0.4908368536386265,0.42789369649908626
+1.0668563300142249,3000,0.32,0.54,0.6,0.68,0.32,0.31,0.18666666666666665,0.52,0.128,0.58,0.07200000000000001,0.66,0.44157936507936507,0.4899955234963748,0.44184672889614296
+1.1557610241820768,3250,0.3,0.54,0.62,0.68,0.3,0.29,0.18666666666666665,0.52,0.132,0.6,0.07200000000000001,0.66,0.43891269841269837,0.48792681291712675,0.4380839646937076
+1.2446657183499288,3500,0.32,0.52,0.62,0.68,0.32,0.31,0.18,0.5,0.132,0.6,0.07200000000000001,0.66,0.4426904761904762,0.490664577709965,0.44201094210524056
+1.333570412517781,3750,0.3,0.52,0.62,0.7,0.3,0.29,0.18,0.5,0.132,0.6,0.07400000000000001,0.68,0.44185714285714284,0.4953670686560329,0.44017084567101106
+1.422475106685633,4000,0.3,0.52,0.62,0.68,0.3,0.29,0.18,0.5,0.132,0.6,0.07200000000000001,0.66,0.43835714285714283,0.48818129610354133,0.43807459263823323
+1.5113798008534851,4250,0.32,0.54,0.62,0.68,0.32,0.31,0.18,0.51,0.132,0.6,0.07200000000000001,0.66,0.44435714285714284,0.4927513561227532,0.44445805584016085
+1.600284495021337,4500,0.32,0.54,0.62,0.7,0.32,0.31,0.18,0.51,0.132,0.6,0.07400000000000001,0.68,0.44685714285714284,0.4990606536584677,0.44488210342400414
+1.689189189189189,4750,0.3,0.54,0.62,0.7,0.3,0.29,0.18,0.51,0.132,0.6,0.07400000000000001,0.68,0.4335238095238095,0.48906065365846774,0.43155164353196623
+1.7780938833570412,5000,0.3,0.54,0.62,0.7,0.3,0.29,0.18,0.51,0.132,0.6,0.07400000000000001,0.68,0.43224603174603166,0.48789548101925573,0.4304090341200182

eval/NanoBEIR_evaluation_mean_results.csv

@@ -41,3 +41,24 @@ epoch,steps,cosine-Accuracy@1,cosine-Accuracy@3,cosine-Accuracy@5,cosine-Accurac
 1.600284495021337,4500,0.25,0.48,0.5900000000000001,0.69,0.25,0.245,0.1633333333333333,0.475,0.12000000000000001,0.5800000000000001,0.07,0.675,0.39688095238095233,0.4626887971643756,0.4063718576620344
 1.689189189189189,4750,0.25,0.48,0.5900000000000001,0.69,0.25,0.245,0.1633333333333333,0.475,0.12000000000000001,0.5800000000000001,0.07,0.675,0.3961309523809524,0.46213667209482234,0.40555414604339746
 1.7780938833570412,5000,0.25,0.48,0.5900000000000001,0.69,0.25,0.245,0.1633333333333333,0.475,0.12000000000000001,0.5800000000000001,0.07,0.675,0.39513095238095236,0.46045740496952725,0.4028437161571099
+0,0,0.41000000000000003,0.62,0.69,0.76,0.41000000000000003,0.4,0.20666666666666667,0.605,0.14400000000000002,0.685,0.07900000000000001,0.755,0.5320119047619047,0.583646124688341,0.5360907157798482
+0.08890469416785206,250,0.37,0.58,0.6799999999999999,0.76,0.37,0.36,0.19666666666666666,0.575,0.14,0.6699999999999999,0.07900000000000001,0.755,0.49437301587301585,0.5552133213377628,0.49996370185673844
+0.17780938833570412,500,0.43000000000000005,0.53,0.65,0.79,0.43000000000000005,0.42000000000000004,0.18333333333333332,0.525,0.134,0.64,0.08199999999999999,0.78,0.5209484126984126,0.5792831860100378,0.5229199610852793
+0.26671408250355616,750,0.37,0.54,0.66,0.77,0.37,0.36,0.18666666666666665,0.535,0.136,0.65,0.079,0.76,0.4917301587301587,0.552989215254027,0.4946268032199025
+0.35561877667140823,1000,0.38,0.55,0.66,0.76,0.38,0.375,0.18666666666666665,0.54,0.136,0.65,0.078,0.75,0.5024920634920634,0.5602042594299929,0.5080608482132457
+0.4445234708392603,1250,0.32,0.53,0.63,0.77,0.32,0.315,0.18,0.52,0.13,0.6200000000000001,0.079,0.76,0.4594920634920635,0.5292973854470459,0.4640720086332869
+0.5334281650071123,1500,0.34,0.53,0.63,0.76,0.34,0.335,0.18,0.52,0.13,0.62,0.078,0.75,0.4660753968253968,0.5317766065636564,0.4716466808084797
+0.6223328591749644,1750,0.33999999999999997,0.53,0.6599999999999999,0.77,0.33999999999999997,0.33499999999999996,0.18,0.52,0.136,0.6499999999999999,0.079,0.76,0.4750079365079365,0.5407039516509431,0.47783626664087464
+0.7112375533428165,2000,0.32999999999999996,0.54,0.64,0.78,0.32999999999999996,0.32499999999999996,0.18666666666666665,0.535,0.132,0.63,0.07999999999999999,0.77,0.4653690476190476,0.5364107156945714,0.46866553522558596
+0.8001422475106685,2250,0.32,0.5800000000000001,0.62,0.78,0.32,0.315,0.19666666666666666,0.5700000000000001,0.128,0.61,0.07999999999999999,0.77,0.46590873015873013,0.5361887949872507,0.4673153329235308
+0.8890469416785206,2500,0.32,0.56,0.63,0.77,0.32,0.315,0.19,0.55,0.13,0.6200000000000001,0.07899999999999999,0.76,0.45839682539682536,0.5283794612524177,0.46208686827951684
+0.9779516358463727,2750,0.3,0.5700000000000001,0.63,0.76,0.3,0.295,0.19,0.5549999999999999,0.13,0.62,0.078,0.75,0.44492460317460314,0.5157259634486615,0.4481895482971268
+1.0668563300142249,3000,0.31,0.54,0.61,0.74,0.31,0.305,0.1833333333333333,0.53,0.126,0.6,0.07600000000000001,0.73,0.44692460317460314,0.5126389410903377,0.4516157203065264
+1.1557610241820768,3250,0.3,0.55,0.62,0.74,0.3,0.295,0.18666666666666665,0.54,0.128,0.61,0.07600000000000001,0.73,0.44835317460317453,0.5138166167263359,0.45259868151682525
+1.2446657183499288,3500,0.31,0.54,0.63,0.75,0.31,0.305,0.18333333333333332,0.53,0.13,0.62,0.077,0.74,0.4492857142857143,0.5165699183836719,0.45277147880784163
+1.333570412517781,3750,0.3,0.54,0.62,0.75,0.3,0.295,0.18333333333333332,0.53,0.128,0.61,0.07700000000000001,0.74,0.4473809523809523,0.5155261352596805,0.4512199174745374
+1.422475106685633,4000,0.3,0.54,0.63,0.74,0.3,0.295,0.18333333333333332,0.53,0.13,0.62,0.07600000000000001,0.73,0.44471428571428573,0.5113378307522083,0.44920446037794026
+1.5113798008534851,4250,0.31,0.55,0.64,0.74,0.31,0.305,0.18333333333333332,0.535,0.132,0.63,0.07600000000000001,0.73,0.4495753968253968,0.5150942656875765,0.4543797073089177
+1.600284495021337,4500,0.31,0.55,0.64,0.75,0.31,0.305,0.18333333333333332,0.535,0.132,0.63,0.07700000000000001,0.74,0.45146428571428565,0.5188315007750397,0.455199976312306
+1.689189189189189,4750,0.3,0.55,0.64,0.75,0.3,0.295,0.18333333333333332,0.535,0.132,0.63,0.07700000000000001,0.74,0.44249206349206344,0.5119396169197192,0.44617350251660504
+1.7780938833570412,5000,0.3,0.55,0.64,0.75,0.3,0.295,0.18333333333333332,0.535,0.132,0.63,0.07700000000000001,0.74,0.4422301587301587,0.5117301179490775,0.44590511907474584

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5839d66e8b7021ace7a80466d3912594c41783bf568b53dc58e99744e6b48e3b
-size 90864192
+oid sha256:ae38eeb892fe2e3392c100342b99b38af1c80a62f836226261339f39b8066ae9
+size 133462128

modules.json

@@ -10,11 +10,5 @@
     "name": "1",
     "path": "1_Pooling",
     "type": "sentence_transformers.models.Pooling"
-  },
-  {
-    "idx": 2,
-    "name": "2",
-    "path": "2_Normalize",
-    "type": "sentence_transformers.models.Normalize"
   }
 ]

tokenizer_config.json

@@ -48,7 +48,7 @@
   "extra_special_tokens": {},
   "mask_token": "[MASK]",
   "max_length": 128,
-  "model_max_length": 256,
+  "model_max_length": 128,
   "never_split": null,
   "pad_to_multiple_of": null,
   "pad_token": "[PAD]",