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,-1,0.7551020408163265,0.8979591836734694,0.9387755102040817,1.0,0.7551020408163265,0.01681883497544576,0.6802721088435373,0.045273391320759554,0.6489795918367346,0.07198855467813525,0.563265306122449,0.12417651370073833,0.8328474246841594,0.6023501966395867,0.2434385293084787

Information-Retrieval_evaluation_NanoArguAna_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,-1,0.18,0.5,0.66,0.74,0.18,0.18,0.16666666666666663,0.5,0.13200000000000003,0.66,0.07400000000000001,0.74,0.3599682539682539,0.45218312003145433,0.3658170202780539

Information-Retrieval_evaluation_NanoClimateFEVER_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,-1,0.1,0.32,0.44,0.6,0.1,0.04333333333333333,0.11333333333333333,0.154,0.092,0.214,0.066,0.2723333333333333,0.23579365079365078,0.18832347198247595,0.13278630044723194

Information-Retrieval_evaluation_NanoDBPedia_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,-1,0.58,0.82,0.86,0.88,0.58,0.05774032197349101,0.5266666666666666,0.13525154291594316,0.444,0.17429307751101658,0.36199999999999993,0.24557535689700863,0.7,0.46037876007701023,0.32047705412103555

Information-Retrieval_evaluation_NanoFEVER_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,-1,0.56,0.8,0.88,0.88,0.56,0.5266666666666666,0.28,0.7533333333333333,0.184,0.8333333333333333,0.092,0.8333333333333333,0.6789999999999999,0.7016221865098926,0.6483203115492273

Information-Retrieval_evaluation_NanoFiQA2018_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,-1,0.24,0.38,0.42,0.52,0.24,0.13307936507936508,0.15333333333333332,0.21543650793650795,0.11600000000000002,0.2601031746031746,0.07600000000000001,0.3241587301587302,0.3178809523809524,0.2635447070179544,0.22615568818713977

Information-Retrieval_evaluation_NanoHotpotQA_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,-1,0.5,0.58,0.62,0.68,0.5,0.25,0.2333333333333333,0.35,0.16399999999999998,0.41,0.094,0.47,0.5529999999999999,0.43627646197603637,0.37828612061221206

Information-Retrieval_evaluation_NanoMSMARCO_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,-1,0.26,0.52,0.6,0.62,0.26,0.26,0.1733333333333333,0.52,0.12,0.6,0.062,0.62,0.40519047619047627,0.45904886208148177,0.4260102142025637

Information-Retrieval_evaluation_NanoNFCorpus_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,-1,0.32,0.5,0.52,0.64,0.32,0.01260685895239504,0.31333333333333335,0.03463231741620742,0.27599999999999997,0.06850002262294216,0.24399999999999994,0.10851262864104039,0.4212380952380952,0.2703690747449406,0.10029196368651581

Information-Retrieval_evaluation_NanoNQ_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,-1,0.32,0.5,0.6,0.62,0.32,0.3,0.1733333333333333,0.47,0.128,0.58,0.066,0.6,0.4272222222222222,0.4619884812398348,0.42411983365963474

Information-Retrieval_evaluation_NanoQuoraRetrieval_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,-1,0.94,1.0,1.0,1.0,0.94,0.8273333333333334,0.4133333333333333,0.9653333333333333,0.25999999999999995,0.9793333333333334,0.13799999999999998,0.9966666666666666,0.9666666666666667,0.9697624312418531,0.9551233766233765

Information-Retrieval_evaluation_NanoSCIDOCS_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,-1,0.42,0.6,0.72,0.82,0.42,0.08866666666666667,0.33333333333333326,0.20866666666666664,0.272,0.2806666666666667,0.17999999999999997,0.3696666666666666,0.540047619047619,0.36082794471047336,0.2862806075456748

Information-Retrieval_evaluation_NanoSciFact_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,-1,0.38,0.46,0.5,0.58,0.38,0.345,0.15999999999999998,0.43,0.10800000000000003,0.475,0.068,0.58,0.44026984126984126,0.46384622999765257,0.43257979600699104

Information-Retrieval_evaluation_NanoTouche2020_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,-1,0.46938775510204084,0.8367346938775511,0.9387755102040817,1.0,0.46938775510204084,0.032657982947973084,0.44897959183673464,0.09621881460341672,0.42040816326530606,0.1425551052100505,0.3346938775510204,0.22061476067159091,0.6573129251700679,0.3807140713282222,0.2698119698398041

NanoBEIR_evaluation_mean_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,-1,0.4053375196232339,0.601287284144427,0.6737519623233909,0.7369230769230769,0.4053375196232339,0.23516034838101724,0.26838304552590264,0.37175942432349296,0.20895447409733128,0.43675267025234743,0.1428226059654631,0.4908354981821823,0.5156608233036803,0.45145275407225244,0.3820046351353431

README.md

@@ -5,231 +5,51 @@ tags:
 - feature-extraction
 - dense
 - generated_from_trainer
-- dataset_size:713743
+- dataset_size:100000
 - loss:MultipleNegativesRankingLoss
-base_model: sentence-transformers/all-MiniLM-L6-v2
+base_model: prajjwal1/bert-small
 widget:
-- source_sentence: 'Abraham Lincoln: Why is the Gettysburg Address so memorable?'
+- source_sentence: How do I calculate IQ?
   sentences:
-  - 'Abraham Lincoln: Why is the Gettysburg Address so memorable?'
-  - What does the Gettysburg Address really mean?
-  - What is eatalo.com?
-- source_sentence: Has the influence of Ancient Carthage in science, math, and society
-    been underestimated?
+  - What is the easiest way to know my IQ?
+  - How do I calculate not IQ ?
+  - What are some creative and innovative business ideas with less investment in India?
+- source_sentence: How can I learn martial arts in my home?
   sentences:
-  - How does one earn money online without an investment from home?
-  - Has the influence of Ancient Carthage in science, math, and society been underestimated?
-  - Has the influence of the Ancient Etruscans in science and math been underestimated?
-- source_sentence: Is there any app that shares charging to others like share it how
-    we transfer files?
+  - How can I learn martial arts by myself?
+  - What are the advantages and disadvantages of investing in gold?
+  - Can people see that I have looked at their pictures on instagram if I am not following
+    them?
+- source_sentence: When Enterprise picks you up do you have to take them back?
   sentences:
-  - How do you think of Chinese claims that the present Private Arbitration is illegal,
-    its verdict violates the UNCLOS and is illegal?
-  - Is there any app that shares charging to others like share it how we transfer
-    files?
-  - Are there any platforms that provides end-to-end encryption for file transfer/
-    sharing?
-- source_sentence: Why AAP’s MLA Dinesh Mohaniya has been arrested?
+  - Are there any software Training institute in Tuticorin?
+  - When Enterprise picks you up do you have to take them back?
+  - When Enterprise picks you up do them have to take youback?
+- source_sentence: What are some non-capital goods?
   sentences:
-  - What are your views on the latest sex scandal by AAP MLA Sandeep Kumar?
-  - What is a dc current? What are some examples?
-  - Why AAP’s MLA Dinesh Mohaniya has been arrested?
-- source_sentence: What is the difference between economic growth and economic development?
+  - What are capital goods?
+  - How is the value of [math]\pi[/math] calculated?
+  - What are some non-capital goods?
+- source_sentence: What is the QuickBooks technical support phone number in New York?
   sentences:
-  - How cold can the Gobi Desert get, and how do its average temperatures compare
-    to the ones in the Simpson Desert?
-  - the difference between economic growth and economic development is What?
-  - What is the difference between economic growth and economic development?
+  - What caused the Great Depression?
+  - Can I apply for PR in Canada?
+  - Which is the best QuickBooks Hosting Support Number in New York?
 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: 0.26
-      name: Cosine Accuracy@1
-    - type: cosine_accuracy@3
-      value: 0.52
-      name: Cosine Accuracy@3
-    - type: cosine_accuracy@5
-      value: 0.6
-      name: Cosine Accuracy@5
-    - type: cosine_accuracy@10
-      value: 0.62
-      name: Cosine Accuracy@10
-    - type: cosine_precision@1
-      value: 0.26
-      name: Cosine Precision@1
-    - type: cosine_precision@3
-      value: 0.1733333333333333
-      name: Cosine Precision@3
-    - type: cosine_precision@5
-      value: 0.12
-      name: Cosine Precision@5
-    - type: cosine_precision@10
-      value: 0.062
-      name: Cosine Precision@10
-    - type: cosine_recall@1
-      value: 0.26
-      name: Cosine Recall@1
-    - type: cosine_recall@3
-      value: 0.52
-      name: Cosine Recall@3
-    - type: cosine_recall@5
-      value: 0.6
-      name: Cosine Recall@5
-    - type: cosine_recall@10
-      value: 0.62
-      name: Cosine Recall@10
-    - type: cosine_ndcg@10
-      value: 0.45904886208148177
-      name: Cosine Ndcg@10
-    - type: cosine_mrr@10
-      value: 0.40519047619047627
-      name: Cosine Mrr@10
-    - type: cosine_map@100
-      value: 0.4260102142025637
-      name: Cosine Map@100
-  - task:
-      type: information-retrieval
-      name: Information Retrieval
-    dataset:
-      name: NanoNQ
-      type: NanoNQ
-    metrics:
-    - type: cosine_accuracy@1
-      value: 0.32
-      name: Cosine Accuracy@1
-    - type: cosine_accuracy@3
-      value: 0.5
-      name: Cosine Accuracy@3
-    - type: cosine_accuracy@5
-      value: 0.6
-      name: Cosine Accuracy@5
-    - type: cosine_accuracy@10
-      value: 0.62
-      name: Cosine Accuracy@10
-    - type: cosine_precision@1
-      value: 0.32
-      name: Cosine Precision@1
-    - type: cosine_precision@3
-      value: 0.1733333333333333
-      name: Cosine Precision@3
-    - type: cosine_precision@5
-      value: 0.128
-      name: Cosine Precision@5
-    - type: cosine_precision@10
-      value: 0.066
-      name: Cosine Precision@10
-    - type: cosine_recall@1
-      value: 0.3
-      name: Cosine Recall@1
-    - type: cosine_recall@3
-      value: 0.47
-      name: Cosine Recall@3
-    - type: cosine_recall@5
-      value: 0.58
-      name: Cosine Recall@5
-    - type: cosine_recall@10
-      value: 0.6
-      name: Cosine Recall@10
-    - type: cosine_ndcg@10
-      value: 0.4619884812398348
-      name: Cosine Ndcg@10
-    - type: cosine_mrr@10
-      value: 0.4272222222222222
-      name: Cosine Mrr@10
-    - type: cosine_map@100
-      value: 0.42411471333193373
-      name: Cosine Map@100
-  - task:
-      type: nano-beir
-      name: Nano BEIR
-    dataset:
-      name: NanoBEIR mean
-      type: NanoBEIR_mean
-    metrics:
-    - type: cosine_accuracy@1
-      value: 0.29000000000000004
-      name: Cosine Accuracy@1
-    - type: cosine_accuracy@3
-      value: 0.51
-      name: Cosine Accuracy@3
-    - type: cosine_accuracy@5
-      value: 0.6
-      name: Cosine Accuracy@5
-    - type: cosine_accuracy@10
-      value: 0.62
-      name: Cosine Accuracy@10
-    - type: cosine_precision@1
-      value: 0.29000000000000004
-      name: Cosine Precision@1
-    - type: cosine_precision@3
-      value: 0.1733333333333333
-      name: Cosine Precision@3
-    - type: cosine_precision@5
-      value: 0.124
-      name: Cosine Precision@5
-    - type: cosine_precision@10
-      value: 0.064
-      name: Cosine Precision@10
-    - type: cosine_recall@1
-      value: 0.28
-      name: Cosine Recall@1
-    - type: cosine_recall@3
-      value: 0.495
-      name: Cosine Recall@3
-    - type: cosine_recall@5
-      value: 0.59
-      name: Cosine Recall@5
-    - type: cosine_recall@10
-      value: 0.61
-      name: Cosine Recall@10
-    - type: cosine_ndcg@10
-      value: 0.4605186716606583
-      name: Cosine Ndcg@10
-    - type: cosine_mrr@10
-      value: 0.41620634920634925
-      name: Cosine Mrr@10
-    - type: cosine_map@100
-      value: 0.4250624637672487
-      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 -->
@@ -246,8 +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})
 )
 ```
 
@@ -266,23 +85,23 @@ Then you can load this model and run inference.
 from sentence_transformers import SentenceTransformer
 
 # Download from the 🤗 Hub
-model = SentenceTransformer("redis/model-b-structured")
+model = SentenceTransformer("sentence_transformers_model_id")
 # Run inference
 sentences = [
-    'What is the difference between economic growth and economic development?',
-    'What is the difference between economic growth and economic development?',
-    'the difference between economic growth and economic development is What?',
+    'What is the QuickBooks technical support phone number in New York?',
+    'Which is the best QuickBooks Hosting Support Number in New York?',
+    'Can I apply for PR in Canada?',
 ]
 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,  1.0000, -0.0482],
-#         [ 1.0000,  1.0000, -0.0482],
-#         [-0.0482, -0.0482,  1.0000]])
+# tensor([[1.0000, 0.8563, 0.0594],
+#         [0.8563, 1.0000, 0.1245],
+#         [0.0594, 0.1245, 1.0000]])
 ```
 
 <!--
@@ -309,65 +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   | 0.26        | 0.32      |
-| cosine_accuracy@3   | 0.52        | 0.5       |
-| cosine_accuracy@5   | 0.6         | 0.6       |
-| cosine_accuracy@10  | 0.62        | 0.62      |
-| cosine_precision@1  | 0.26        | 0.32      |
-| cosine_precision@3  | 0.1733      | 0.1733    |
-| cosine_precision@5  | 0.12        | 0.128     |
-| cosine_precision@10 | 0.062       | 0.066     |
-| cosine_recall@1     | 0.26        | 0.3       |
-| cosine_recall@3     | 0.52        | 0.47      |
-| cosine_recall@5     | 0.6         | 0.58      |
-| cosine_recall@10    | 0.62        | 0.6       |
-| **cosine_ndcg@10**  | **0.459**   | **0.462** |
-| cosine_mrr@10       | 0.4052      | 0.4272    |
-| cosine_map@100      | 0.426       | 0.4241    |
-
-#### 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   | 0.29       |
-| cosine_accuracy@3   | 0.51       |
-| cosine_accuracy@5   | 0.6        |
-| cosine_accuracy@10  | 0.62       |
-| cosine_precision@1  | 0.29       |
-| cosine_precision@3  | 0.1733     |
-| cosine_precision@5  | 0.124      |
-| cosine_precision@10 | 0.064      |
-| cosine_recall@1     | 0.28       |
-| cosine_recall@3     | 0.495      |
-| cosine_recall@5     | 0.59       |
-| cosine_recall@10    | 0.61       |
-| **cosine_ndcg@10**  | **0.4605** |
-| cosine_mrr@10       | 0.4162     |
-| cosine_map@100      | 0.4251     |
-
 <!--
 ## Bias, Risks and Limitations
 
@@ -386,49 +146,23 @@ You can finetune this model on your own dataset.
 
 #### Unnamed Dataset
 
-* Size: 713,743 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: 6 tokens</li><li>mean: 16.07 tokens</li><li>max: 53 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 16.03 tokens</li><li>max: 53 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 16.81 tokens</li><li>max: 58 tokens</li></ul> |
-* Samples:
-  | anchor                                                                         | positive                                                                              | negative                                                                                                          |
-  |:-------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------|
-  | <code>Which one is better Linux OS? Ubuntu or Mint?</code>                     | <code>Why do you use Linux Mint?</code>                                               | <code>Which one is not better Linux OS ? Ubuntu or Mint ?</code>                                                  |
-  | <code>What is flow?</code>                                                     | <code>What is flow?</code>                                                            | <code>What are flow lines?</code>                                                                                 |
-  | <code>How is Trump planning to get Mexico to pay for his supposed wall?</code> | <code>How is it possible for Donald Trump to force Mexico to pay for the wall?</code> | <code>Why do we connect the positive terminal before the negative terminal to ground in a vehicle battery?</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                                                                          |
+  |         | sentence_0                                                                        | sentence_1                                                                        | sentence_2                                                                        |
   |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
   | type    | string                                                                            | string                                                                            | string                                                                            |
-  | details | <ul><li>min: 6 tokens</li><li>mean: 15.52 tokens</li><li>max: 74 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 15.51 tokens</li><li>max: 74 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 16.79 tokens</li><li>max: 69 tokens</li></ul> |
+  | details | <ul><li>min: 6 tokens</li><li>mean: 15.79 tokens</li><li>max: 66 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 15.68 tokens</li><li>max: 66 tokens</li></ul> | <ul><li>min: 7 tokens</li><li>mean: 16.37 tokens</li><li>max: 67 tokens</li></ul> |
 * Samples:
-  | anchor                                                                                                                                                       | positive                                                                                                                                                     | negative                                                                                                                                                            |
-  |:-------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------|
-  | <code>Why are all my questions on Quora marked needing improvement?</code>                                                                                   | <code>Why are all my questions immediately being marked as needing improvement?</code>                                                                       | <code>For a post-graduate student in IIT, is it allowed to take an external scholarship as a top-up to his/her MHRD assistantship?</code>                           |
-  | <code>Can blue butter fly needle with vaccum tube be reused? Is it HIV risk? . Heard the needle is too small to be reused . Had blood draw at clinic?</code> | <code>Can blue butter fly needle with vaccum tube be reused? Is it HIV risk? . Heard the needle is too small to be reused . Had blood draw at clinic?</code> | <code>Can blue butter fly needle with vaccum tube be reused not ? Is it HIV risk ? . Heard the needle is too small to be reused . Had blood draw at clinic ?</code> |
-  | <code>Why do people still believe the world is flat?</code>                                                                                                  | <code>Why are there still people who believe the world is flat?</code>                                                                                       | <code>I'm not able to buy Udemy course .it is not accepting mine and my friends debit card.my card can be used for Flipkart .how to purchase now?</code>            |
+  | sentence_0                                                       | sentence_1                                                       | sentence_2                                                                        |
+  |:-----------------------------------------------------------------|:-----------------------------------------------------------------|:----------------------------------------------------------------------------------|
+  | <code>Is masturbating bad for boys?</code>                       | <code>Is masturbating bad for boys?</code>                       | <code>How harmful or unhealthy is masturbation?</code>                            |
+  | <code>Does a train engine move in reverse?</code>                | <code>Does a train engine move in reverse?</code>                | <code>Time moves forward, not in reverse. Doesn't that make time a vector?</code> |
+  | <code>What is the most badass thing anyone has ever done?</code> | <code>What is the most badass thing anyone has ever done?</code> | <code>anyone is the most badass thing Whathas ever done?</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
   }
@@ -437,49 +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-b-structured
-- `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
@@ -507,14 +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
@@ -524,23 +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-b-structured
+- `hub_model_id`: None
 - `hub_strategy`: every_save
 - `hub_private_repo`: None
 - `hub_always_push`: False
@@ -567,43 +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    | -             | 0.7908          | 0.5540                     | 0.5931                | 0.5735                       |
-| 0.0448 | 250  | 0.7632        | 0.4756          | 0.5373                     | 0.5302                | 0.5337                       |
-| 0.0897 | 500  | 0.5825        | 0.4308          | 0.5277                     | 0.4949                | 0.5113                       |
-| 0.1345 | 750  | 0.5438        | 0.4161          | 0.5180                     | 0.5039                | 0.5110                       |
-| 0.1793 | 1000 | 0.5277        | 0.4070          | 0.5008                     | 0.4875                | 0.4942                       |
-| 0.2242 | 1250 | 0.516         | 0.4012          | 0.4983                     | 0.4779                | 0.4881                       |
-| 0.2690 | 1500 | 0.5049        | 0.3962          | 0.4923                     | 0.4777                | 0.4850                       |
-| 0.3138 | 1750 | 0.4966        | 0.3931          | 0.4789                     | 0.4769                | 0.4779                       |
-| 0.3587 | 2000 | 0.493         | 0.3894          | 0.4792                     | 0.4616                | 0.4704                       |
-| 0.4035 | 2250 | 0.4852        | 0.3866          | 0.4828                     | 0.4749                | 0.4788                       |
-| 0.4484 | 2500 | 0.4815        | 0.3841          | 0.4589                     | 0.4559                | 0.4574                       |
-| 0.4932 | 2750 | 0.4761        | 0.3820          | 0.4647                     | 0.4539                | 0.4593                       |
-| 0.5380 | 3000 | 0.4747        | 0.3796          | 0.4588                     | 0.4493                | 0.4540                       |
-| 0.5829 | 3250 | 0.4722        | 0.3786          | 0.4588                     | 0.4458                | 0.4523                       |
-| 0.6277 | 3500 | 0.4725        | 0.3774          | 0.4587                     | 0.4537                | 0.4562                       |
-| 0.6725 | 3750 | 0.4692        | 0.3766          | 0.4561                     | 0.4621                | 0.4591                       |
-| 0.7174 | 4000 | 0.4664        | 0.3763          | 0.4584                     | 0.4395                | 0.4489                       |
-| 0.7622 | 4250 | 0.4659        | 0.3747          | 0.4645                     | 0.4586                | 0.4616                       |
-| 0.8070 | 4500 | 0.464         | 0.3742          | 0.4619                     | 0.4479                | 0.4549                       |
-| 0.8519 | 4750 | 0.4662        | 0.3739          | 0.4590                     | 0.4498                | 0.4544                       |
-| 0.8967 | 5000 | 0.4662        | 0.3739          | 0.4590                     | 0.4620                | 0.4605                       |
+| Epoch  | Step | Training Loss |
+|:------:|:----:|:-------------:|
+| 0.3199 | 500  | 0.4294        |
+| 0.6398 | 1000 | 0.1268        |
+| 0.9597 | 1500 | 0.1           |
+| 1.2796 | 2000 | 0.0792        |
+| 1.5995 | 2500 | 0.0706        |
+| 1.9194 | 3000 | 0.0687        |
+| 2.2393 | 3500 | 0.0584        |
+| 2.5592 | 4000 | 0.057         |
+| 2.8791 | 4500 | 0.0581        |
 
 
 ### Framework Versions
@@ -612,7 +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

@@ -20,3 +20,24 @@ epoch,steps,cosine-Accuracy@1,cosine-Accuracy@3,cosine-Accuracy@5,cosine-Accurac
 0.8070301291248206,4500,0.26,0.52,0.6,0.64,0.26,0.26,0.1733333333333333,0.52,0.12,0.6,0.064,0.64,0.4035,0.4618541944054583,0.4223204303148985
 0.8518651362984218,4750,0.26,0.52,0.6,0.62,0.26,0.26,0.1733333333333333,0.52,0.12,0.6,0.062,0.62,0.40519047619047627,0.45904886208148177,0.42619789929009394
 0.896700143472023,5000,0.26,0.52,0.6,0.62,0.26,0.26,0.1733333333333333,0.52,0.12,0.6,0.062,0.62,0.40519047619047627,0.45904886208148177,0.4260102142025637
+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
+0.04483500717360115,250,0.36,0.58,0.68,0.74,0.36,0.36,0.19333333333333333,0.58,0.136,0.68,0.07400000000000001,0.74,0.4905555555555555,0.5511895065270163,0.506031756095913
+0.0896700143472023,500,0.36,0.56,0.64,0.76,0.36,0.36,0.18666666666666668,0.56,0.128,0.64,0.07600000000000001,0.76,0.4851904761904761,0.5508845690199249,0.49791509453033606
+0.13450502152080343,750,0.32,0.58,0.64,0.74,0.32,0.32,0.19333333333333333,0.58,0.128,0.64,0.07400000000000001,0.74,0.4641904761904761,0.531009021314192,0.47885677958247
+0.1793400286944046,1000,0.34,0.58,0.64,0.74,0.34,0.34,0.19333333333333333,0.58,0.128,0.64,0.07400000000000001,0.74,0.47469047619047616,0.5389184272521197,0.4900991890622418
+0.22417503586800575,1250,0.36,0.6,0.62,0.76,0.36,0.36,0.19999999999999996,0.6,0.124,0.62,0.07600000000000001,0.76,0.4822142857142857,0.5481489205832354,0.49567847940262133
+0.26901004304160686,1500,0.32,0.52,0.62,0.8,0.32,0.32,0.1733333333333333,0.52,0.124,0.62,0.08,0.8,0.45526984126984116,0.5360854329130652,0.4661566612305466
+0.31384505021520803,1750,0.32,0.54,0.64,0.76,0.32,0.32,0.18,0.54,0.128,0.64,0.07600000000000001,0.76,0.45913492063492056,0.5310625456594542,0.47177852901012957
+0.3586800573888092,2000,0.32,0.54,0.6,0.78,0.32,0.32,0.18,0.54,0.12000000000000002,0.6,0.078,0.78,0.451579365079365,0.5289782036371049,0.4624455348572996
+0.4035150645624103,2250,0.32,0.54,0.6,0.76,0.32,0.32,0.17999999999999997,0.54,0.12000000000000002,0.6,0.07600000000000001,0.76,0.45301587301587287,0.5259546976245565,0.46591934426473436
+0.4483500717360115,2500,0.3,0.54,0.62,0.74,0.3,0.3,0.17999999999999997,0.54,0.124,0.62,0.07400000000000001,0.74,0.44035714285714284,0.5121499347260792,0.4559007233900851
+0.4931850789096126,2750,0.32,0.54,0.62,0.78,0.32,0.32,0.17999999999999997,0.54,0.124,0.62,0.078,0.78,0.4564920634920634,0.5332727558279641,0.4681851283092703
+0.5380200860832137,3000,0.28,0.54,0.58,0.78,0.28,0.28,0.17999999999999997,0.54,0.11600000000000002,0.58,0.078,0.78,0.4334682539682539,0.5155839048190068,0.44574141585928134
+0.582855093256815,3250,0.3,0.54,0.6,0.76,0.3,0.3,0.17999999999999997,0.54,0.12000000000000002,0.6,0.07600000000000001,0.76,0.43893650793650785,0.5152963962963514,0.4530906280704235
+0.6276901004304161,3500,0.28,0.54,0.62,0.78,0.28,0.28,0.17999999999999997,0.54,0.124,0.62,0.078,0.78,0.43210317460317454,0.5148372013060255,0.4444357120357121
+0.6725251076040172,3750,0.28,0.52,0.62,0.76,0.28,0.28,0.1733333333333333,0.52,0.124,0.62,0.07600000000000001,0.76,0.4268571428571428,0.5061450417456256,0.4408749948308773
+0.7173601147776184,4000,0.28,0.54,0.62,0.8,0.28,0.28,0.17999999999999997,0.54,0.124,0.62,0.08,0.8,0.43823809523809515,0.5239447884675306,0.44793010449227444
+0.7621951219512195,4250,0.28,0.54,0.62,0.8,0.28,0.28,0.17999999999999997,0.54,0.124,0.62,0.08,0.8,0.43435714285714283,0.5208366715209551,0.4441001581538667
+0.8070301291248206,4500,0.28,0.54,0.62,0.8,0.28,0.28,0.17999999999999997,0.54,0.124,0.62,0.08,0.8,0.43813492063492065,0.5239338733662281,0.44783147531841366
+0.8518651362984218,4750,0.28,0.54,0.62,0.8,0.28,0.28,0.17999999999999997,0.54,0.124,0.62,0.08,0.8,0.43884920634920627,0.5246486116281323,0.4486126806792123
+0.896700143472023,5000,0.28,0.54,0.62,0.8,0.28,0.28,0.17999999999999997,0.54,0.124,0.62,0.08,0.8,0.43837301587301575,0.5241911345526384,0.4480711307258977

eval/Information-Retrieval_evaluation_NanoNQ_results.csv

@@ -20,3 +20,24 @@ epoch,steps,cosine-Accuracy@1,cosine-Accuracy@3,cosine-Accuracy@5,cosine-Accurac
 0.8070301291248206,4500,0.3,0.5,0.58,0.62,0.3,0.28,0.1733333333333333,0.47,0.124,0.56,0.066,0.6,0.40888888888888886,0.44788049874909824,0.40536711434283007
 0.8518651362984218,4750,0.3,0.5,0.6,0.62,0.3,0.28,0.1733333333333333,0.47,0.128,0.58,0.066,0.6,0.4098333333333333,0.4497951196284565,0.40828431891707495
 0.896700143472023,5000,0.32,0.5,0.6,0.62,0.32,0.3,0.1733333333333333,0.47,0.128,0.58,0.066,0.6,0.4272222222222222,0.4619884812398348,0.42411471333193373
+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
+0.04483500717360115,250,0.38,0.58,0.6,0.72,0.38,0.36,0.20666666666666664,0.56,0.128,0.58,0.07800000000000001,0.71,0.4943809523809524,0.5408265737093888,0.49188573556883314
+0.0896700143472023,500,0.38,0.56,0.6,0.68,0.38,0.37,0.19333333333333333,0.53,0.128,0.58,0.07200000000000001,0.66,0.4859444444444444,0.5218051504362269,0.4845106506090576
+0.13450502152080343,750,0.38,0.58,0.6,0.66,0.38,0.37,0.2,0.55,0.128,0.58,0.07,0.64,0.48938095238095236,0.5203266781182219,0.48645510419847765
+0.1793400286944046,1000,0.4,0.58,0.6,0.62,0.4,0.38,0.20666666666666664,0.56,0.128,0.58,0.066,0.6,0.494,0.5128357141707354,0.49102779405243174
+0.22417503586800575,1250,0.36,0.56,0.6,0.6,0.36,0.35,0.2,0.54,0.128,0.58,0.064,0.58,0.46333333333333326,0.4880570938247723,0.46640313682745294
+0.26901004304160686,1500,0.4,0.56,0.6,0.62,0.4,0.38,0.2,0.54,0.128,0.58,0.066,0.6,0.4855555555555556,0.5059849863772411,0.482704723788614
+0.31384505021520803,1750,0.42,0.56,0.6,0.62,0.42,0.4,0.2,0.54,0.128,0.58,0.066,0.6,0.4945555555555556,0.512489916289035,0.49025505979636536
+0.3586800573888092,2000,0.42,0.58,0.6,0.62,0.42,0.4,0.20666666666666664,0.56,0.128,0.58,0.066,0.6,0.5008333333333334,0.5176601528382082,0.4966428998524106
+0.4035150645624103,2250,0.4,0.58,0.6,0.62,0.4,0.39,0.2,0.55,0.128,0.58,0.066,0.6,0.49083333333333334,0.5117467474553212,0.48883870214938285
+0.4483500717360115,2500,0.4,0.58,0.6,0.62,0.4,0.39,0.2,0.55,0.128,0.58,0.066,0.6,0.4883333333333333,0.5104804067864038,0.4870282637039752
+0.4931850789096126,2750,0.38,0.58,0.6,0.62,0.38,0.37,0.20666666666666664,0.56,0.128,0.58,0.066,0.6,0.47700000000000004,0.5026062641182331,0.4774604900053835
+0.5380200860832137,3000,0.38,0.54,0.58,0.62,0.38,0.37,0.18666666666666665,0.51,0.124,0.56,0.066,0.6,0.4686666666666667,0.49487523447422943,0.46727110910305214
+0.582855093256815,3250,0.38,0.58,0.6,0.6,0.38,0.37,0.2,0.55,0.128,0.58,0.064,0.58,0.47166666666666673,0.4933562630442434,0.47192459079370797
+0.6276901004304161,3500,0.4,0.56,0.6,0.62,0.4,0.39,0.19333333333333333,0.53,0.128,0.58,0.066,0.6,0.4891666666666667,0.510897686812855,0.48816169105329865
+0.6725251076040172,3750,0.4,0.56,0.6,0.6,0.4,0.38,0.19333333333333333,0.53,0.128,0.58,0.064,0.58,0.4746666666666667,0.4921241368113464,0.470711152240727
+0.7173601147776184,4000,0.36,0.54,0.6,0.62,0.36,0.35,0.18666666666666665,0.51,0.128,0.58,0.066,0.6,0.4598333333333333,0.48863474295754583,0.4590118602451427
+0.7621951219512195,4250,0.36,0.54,0.6,0.62,0.36,0.35,0.18666666666666665,0.51,0.128,0.58,0.066,0.6,0.4603333333333333,0.488983216964966,0.45999092949283493
+0.8070301291248206,4500,0.36,0.54,0.6,0.62,0.36,0.35,0.18666666666666665,0.51,0.128,0.58,0.066,0.6,0.457,0.48636462189353685,0.4563546379037804
+0.8518651362984218,4750,0.36,0.56,0.6,0.62,0.36,0.35,0.19333333333333333,0.53,0.128,0.58,0.066,0.6,0.4591666666666667,0.4882790917414258,0.4588111953162766
+0.896700143472023,5000,0.36,0.56,0.6,0.62,0.36,0.35,0.19333333333333333,0.53,0.128,0.58,0.066,0.6,0.4625,0.490897686812855,0.46206363135240186

eval/NanoBEIR_evaluation_mean_results.csv

@@ -20,3 +20,24 @@ epoch,steps,cosine-Accuracy@1,cosine-Accuracy@3,cosine-Accuracy@5,cosine-Accurac
 0.8070301291248206,4500,0.28,0.51,0.59,0.63,0.28,0.27,0.1733333333333333,0.495,0.122,0.5800000000000001,0.065,0.62,0.4061944444444444,0.45486734657727823,0.41384377232886427
 0.8518651362984218,4750,0.28,0.51,0.6,0.62,0.28,0.27,0.1733333333333333,0.495,0.124,0.59,0.064,0.61,0.4075119047619048,0.45442199085496915,0.4172411091035845
 0.896700143472023,5000,0.29000000000000004,0.51,0.6,0.62,0.29000000000000004,0.28,0.1733333333333333,0.495,0.124,0.59,0.064,0.61,0.41620634920634925,0.4605186716606583,0.4250624637672487
+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
+0.04483500717360115,250,0.37,0.58,0.64,0.73,0.37,0.36,0.19999999999999998,0.5700000000000001,0.132,0.63,0.07600000000000001,0.725,0.492468253968254,0.5460080401182026,0.4989587458323731
+0.0896700143472023,500,0.37,0.56,0.62,0.72,0.37,0.365,0.19,0.545,0.128,0.61,0.07400000000000001,0.71,0.48556746031746023,0.5363448597280759,0.4912128725696968
+0.13450502152080343,750,0.35,0.58,0.62,0.7,0.35,0.345,0.19666666666666666,0.565,0.128,0.61,0.07200000000000001,0.69,0.47678571428571426,0.525667849716207,0.48265594189047384
+0.1793400286944046,1000,0.37,0.58,0.62,0.6799999999999999,0.37,0.36,0.19999999999999998,0.5700000000000001,0.128,0.61,0.07,0.6699999999999999,0.4843452380952381,0.5258770707114275,0.4905634915573368
+0.22417503586800575,1250,0.36,0.5800000000000001,0.61,0.6799999999999999,0.36,0.355,0.19999999999999998,0.5700000000000001,0.126,0.6,0.07,0.6699999999999999,0.4727738095238095,0.5181030072040038,0.48104080811503713
+0.26901004304160686,1500,0.36,0.54,0.61,0.71,0.36,0.35,0.18666666666666665,0.53,0.126,0.6,0.07300000000000001,0.7,0.4704126984126984,0.5210352096451532,0.4744306925095803
+0.31384505021520803,1750,0.37,0.55,0.62,0.69,0.37,0.36,0.19,0.54,0.128,0.61,0.07100000000000001,0.6799999999999999,0.47684523809523804,0.5217762309742446,0.48101679440324746
+0.3586800573888092,2000,0.37,0.56,0.6,0.7,0.37,0.36,0.1933333333333333,0.55,0.12400000000000001,0.59,0.07200000000000001,0.69,0.4762063492063492,0.5233191782376565,0.4795442173548551
+0.4035150645624103,2250,0.36,0.56,0.6,0.69,0.36,0.355,0.19,0.545,0.12400000000000001,0.59,0.07100000000000001,0.6799999999999999,0.4719246031746031,0.5188507225399388,0.4773790232070586
+0.4483500717360115,2500,0.35,0.56,0.61,0.6799999999999999,0.35,0.345,0.19,0.545,0.126,0.6,0.07,0.6699999999999999,0.4643452380952381,0.5113151707562416,0.47146449354703013
+0.4931850789096126,2750,0.35,0.56,0.61,0.7,0.35,0.345,0.1933333333333333,0.55,0.126,0.6,0.07200000000000001,0.69,0.4667460317460317,0.5179395099730986,0.4728228091573269
+0.5380200860832137,3000,0.33,0.54,0.58,0.7,0.33,0.325,0.1833333333333333,0.525,0.12000000000000001,0.5700000000000001,0.07200000000000001,0.69,0.45106746031746026,0.5052295696466181,0.45650626248116677
+0.582855093256815,3250,0.33999999999999997,0.56,0.6,0.6799999999999999,0.33999999999999997,0.33499999999999996,0.19,0.545,0.12400000000000001,0.59,0.07,0.6699999999999999,0.4553015873015873,0.5043263296702973,0.4625076094320657
+0.6276901004304161,3500,0.34,0.55,0.61,0.7,0.34,0.335,0.18666666666666665,0.535,0.126,0.6,0.07200000000000001,0.69,0.4606349206349206,0.5128674440594403,0.46629870154450537
+0.6725251076040172,3750,0.34,0.54,0.61,0.6799999999999999,0.34,0.33,0.18333333333333332,0.525,0.126,0.6,0.07,0.6699999999999999,0.45076190476190475,0.499134589278486,0.4557930735358021
+0.7173601147776184,4000,0.32,0.54,0.61,0.71,0.32,0.315,0.1833333333333333,0.525,0.126,0.6,0.07300000000000001,0.7,0.4490357142857142,0.5062897657125383,0.45347098236870853
+0.7621951219512195,4250,0.32,0.54,0.61,0.71,0.32,0.315,0.1833333333333333,0.525,0.126,0.6,0.07300000000000001,0.7,0.4473452380952381,0.5049099442429605,0.4520455438233508
+0.8070301291248206,4500,0.32,0.54,0.61,0.71,0.32,0.315,0.1833333333333333,0.525,0.126,0.6,0.07300000000000001,0.7,0.4475674603174603,0.5051492476298824,0.452093056611097
+0.8518651362984218,4750,0.32,0.55,0.61,0.71,0.32,0.315,0.18666666666666665,0.535,0.126,0.6,0.07300000000000001,0.7,0.44900793650793647,0.506463851684779,0.45371193799774445
+0.896700143472023,5000,0.32,0.55,0.61,0.71,0.32,0.315,0.18666666666666665,0.535,0.126,0.6,0.07300000000000001,0.7,0.4504365079365079,0.5075444106827467,0.4550673810391498

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2666bef76509b97bc72f0c314f0f5b45d6eb54098fdecdfc61400524864eb46
-size 90864192
+oid sha256:db59c43bf96bbee3c0ba2dacf6445ee23cd7102f00450058446032338eff15a7
+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]",