Add new SentenceTransformer model

README.md

@@ -7,7 +7,7 @@ tags:
 - generated_from_trainer
 - dataset_size:111470
 - loss:MultipleNegativesRankingLoss
-base_model: thenlper/gte-small
+base_model: sentence-transformers/all-MiniLM-L6-v2
 widget:
 - source_sentence: why are some rocks radioactive
   sentences:
@@ -106,7 +106,7 @@ metrics:
 - cosine_mrr@10
 - cosine_map@100
 model-index:
-- name: SentenceTransformer based on thenlper/gte-small
+- name: SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2
   results:
   - task:
       type: information-retrieval
@@ -116,7 +116,7 @@ model-index:
       type: NanoMSMARCO
     metrics:
     - type: cosine_accuracy@1
-      value: 0.3
+      value: 0.32
       name: Cosine Accuracy@1
     - type: cosine_accuracy@3
       value: 0.54
@@ -125,10 +125,10 @@ model-index:
       value: 0.62
       name: Cosine Accuracy@5
     - type: cosine_accuracy@10
-      value: 0.76
+      value: 0.74
       name: Cosine Accuracy@10
     - type: cosine_precision@1
-      value: 0.3
+      value: 0.32
       name: Cosine Precision@1
     - type: cosine_precision@3
       value: 0.18
@@ -137,10 +137,10 @@ model-index:
       value: 0.124
       name: Cosine Precision@5
     - type: cosine_precision@10
-      value: 0.07600000000000001
+      value: 0.07400000000000001
       name: Cosine Precision@10
     - type: cosine_recall@1
-      value: 0.3
+      value: 0.32
       name: Cosine Recall@1
     - type: cosine_recall@3
       value: 0.54
@@ -149,16 +149,16 @@ model-index:
       value: 0.62
       name: Cosine Recall@5
     - type: cosine_recall@10
-      value: 0.76
+      value: 0.74
       name: Cosine Recall@10
     - type: cosine_ndcg@10
-      value: 0.5241190384704345
+      value: 0.5189661789845982
       name: Cosine Ndcg@10
     - type: cosine_mrr@10
-      value: 0.4492698412698413
+      value: 0.4499126984126983
       name: Cosine Mrr@10
     - type: cosine_map@100
-      value: 0.45777964902887497
+      value: 0.4616522119994847
       name: Cosine Map@100
   - task:
       type: information-retrieval
@@ -168,49 +168,49 @@ model-index:
       type: NanoNQ
     metrics:
     - type: cosine_accuracy@1
-      value: 0.38
+      value: 0.34
       name: Cosine Accuracy@1
     - type: cosine_accuracy@3
-      value: 0.52
+      value: 0.54
       name: Cosine Accuracy@3
     - type: cosine_accuracy@5
-      value: 0.54
+      value: 0.58
       name: Cosine Accuracy@5
     - type: cosine_accuracy@10
-      value: 0.68
+      value: 0.66
       name: Cosine Accuracy@10
     - type: cosine_precision@1
-      value: 0.38
+      value: 0.34
       name: Cosine Precision@1
     - type: cosine_precision@3
-      value: 0.1733333333333333
+      value: 0.19333333333333333
       name: Cosine Precision@3
     - type: cosine_precision@5
-      value: 0.11200000000000002
+      value: 0.12400000000000003
       name: Cosine Precision@5
     - type: cosine_precision@10
       value: 0.07200000000000001
       name: Cosine Precision@10
     - type: cosine_recall@1
-      value: 0.35
+      value: 0.31
       name: Cosine Recall@1
     - type: cosine_recall@3
-      value: 0.49
+      value: 0.52
       name: Cosine Recall@3
     - type: cosine_recall@5
-      value: 0.52
+      value: 0.56
       name: Cosine Recall@5
     - type: cosine_recall@10
-      value: 0.66
+      value: 0.65
       name: Cosine Recall@10
     - type: cosine_ndcg@10
-      value: 0.5017561161582912
+      value: 0.495936841468424
       name: Cosine Ndcg@10
     - type: cosine_mrr@10
-      value: 0.46857142857142864
+      value: 0.455388888888889
       name: Cosine Mrr@10
     - type: cosine_map@100
-      value: 0.4585943213547632
+      value: 0.45517920150439706
       name: Cosine Map@100
   - task:
       type: nano-beir
@@ -220,61 +220,61 @@ model-index:
       type: NanoBEIR_mean
     metrics:
     - type: cosine_accuracy@1
-      value: 0.33999999999999997
+      value: 0.33
       name: Cosine Accuracy@1
     - type: cosine_accuracy@3
-      value: 0.53
+      value: 0.54
       name: Cosine Accuracy@3
     - type: cosine_accuracy@5
-      value: 0.5800000000000001
+      value: 0.6
       name: Cosine Accuracy@5
     - type: cosine_accuracy@10
-      value: 0.72
+      value: 0.7
       name: Cosine Accuracy@10
     - type: cosine_precision@1
-      value: 0.33999999999999997
+      value: 0.33
       name: Cosine Precision@1
     - type: cosine_precision@3
-      value: 0.17666666666666664
+      value: 0.18666666666666665
       name: Cosine Precision@3
     - type: cosine_precision@5
-      value: 0.11800000000000001
+      value: 0.12400000000000001
       name: Cosine Precision@5
     - type: cosine_precision@10
-      value: 0.07400000000000001
+      value: 0.07300000000000001
       name: Cosine Precision@10
     - type: cosine_recall@1
-      value: 0.32499999999999996
+      value: 0.315
       name: Cosine Recall@1
     - type: cosine_recall@3
-      value: 0.515
+      value: 0.53
       name: Cosine Recall@3
     - type: cosine_recall@5
-      value: 0.5700000000000001
+      value: 0.5900000000000001
       name: Cosine Recall@5
     - type: cosine_recall@10
-      value: 0.71
+      value: 0.6950000000000001
       name: Cosine Recall@10
     - type: cosine_ndcg@10
-      value: 0.5129375773143628
+      value: 0.5074515102265111
       name: Cosine Ndcg@10
     - type: cosine_mrr@10
-      value: 0.45892063492063495
+      value: 0.45265079365079364
       name: Cosine Mrr@10
     - type: cosine_map@100
-      value: 0.4581869851918191
+      value: 0.4584157067519409
       name: Cosine Map@100
 ---
 
-# SentenceTransformer based on thenlper/gte-small
+# SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2
 
-This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [thenlper/gte-small](https://huggingface.co/thenlper/gte-small). 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 [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.
 
 ## Model Details
 
 ### Model Description
 - **Model Type:** Sentence Transformer
-- **Base model:** [thenlper/gte-small](https://huggingface.co/thenlper/gte-small) <!-- at revision 17e1f347d17fe144873b1201da91788898c639cd -->
+- **Base model:** [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2) <!-- at revision c9745ed1d9f207416be6d2e6f8de32d1f16199bf -->
 - **Maximum Sequence Length:** 128 tokens
 - **Output Dimensionality:** 384 dimensions
 - **Similarity Function:** Cosine Similarity
@@ -327,9 +327,9 @@ print(embeddings.shape)
 # Get the similarity scores for the embeddings
 similarities = model.similarity(embeddings, embeddings)
 print(similarities)
-# tensor([[1.0000, 1.0000, 0.9779],
-#         [1.0000, 1.0000, 0.9779],
-#         [0.9779, 0.9779, 1.0000]])
+# tensor([[1.0000, 1.0000, 0.9705],
+#         [1.0000, 1.0000, 0.9705],
+#         [0.9705, 0.9705, 1.0000]])
 ```
 
 <!--
@@ -367,21 +367,21 @@ You can finetune this model on your own dataset.
 
 | Metric              | NanoMSMARCO | NanoNQ     |
 |:--------------------|:------------|:-----------|
-| cosine_accuracy@1   | 0.3         | 0.38       |
-| cosine_accuracy@3   | 0.54        | 0.52       |
-| cosine_accuracy@5   | 0.62        | 0.54       |
-| cosine_accuracy@10  | 0.76        | 0.68       |
-| cosine_precision@1  | 0.3         | 0.38       |
-| cosine_precision@3  | 0.18        | 0.1733     |
-| cosine_precision@5  | 0.124       | 0.112      |
-| cosine_precision@10 | 0.076       | 0.072      |
-| cosine_recall@1     | 0.3         | 0.35       |
-| cosine_recall@3     | 0.54        | 0.49       |
-| cosine_recall@5     | 0.62        | 0.52       |
-| cosine_recall@10    | 0.76        | 0.66       |
-| **cosine_ndcg@10**  | **0.5241**  | **0.5018** |
-| cosine_mrr@10       | 0.4493      | 0.4686     |
-| cosine_map@100      | 0.4578      | 0.4586     |
+| cosine_accuracy@1   | 0.32        | 0.34       |
+| cosine_accuracy@3   | 0.54        | 0.54       |
+| cosine_accuracy@5   | 0.62        | 0.58       |
+| cosine_accuracy@10  | 0.74        | 0.66       |
+| cosine_precision@1  | 0.32        | 0.34       |
+| cosine_precision@3  | 0.18        | 0.1933     |
+| cosine_precision@5  | 0.124       | 0.124      |
+| cosine_precision@10 | 0.074       | 0.072      |
+| cosine_recall@1     | 0.32        | 0.31       |
+| cosine_recall@3     | 0.54        | 0.52       |
+| cosine_recall@5     | 0.62        | 0.56       |
+| cosine_recall@10    | 0.74        | 0.65       |
+| **cosine_ndcg@10**  | **0.519**   | **0.4959** |
+| cosine_mrr@10       | 0.4499      | 0.4554     |
+| cosine_map@100      | 0.4617      | 0.4552     |
 
 #### Nano BEIR
 
@@ -399,21 +399,21 @@ You can finetune this model on your own dataset.
 
 | Metric              | Value      |
 |:--------------------|:-----------|
-| cosine_accuracy@1   | 0.34       |
-| cosine_accuracy@3   | 0.53       |
-| cosine_accuracy@5   | 0.58       |
-| cosine_accuracy@10  | 0.72       |
-| cosine_precision@1  | 0.34       |
-| cosine_precision@3  | 0.1767     |
-| cosine_precision@5  | 0.118      |
-| cosine_precision@10 | 0.074      |
-| cosine_recall@1     | 0.325      |
-| cosine_recall@3     | 0.515      |
-| cosine_recall@5     | 0.57       |
-| cosine_recall@10    | 0.71       |
-| **cosine_ndcg@10**  | **0.5129** |
-| cosine_mrr@10       | 0.4589     |
-| cosine_map@100      | 0.4582     |
+| cosine_accuracy@1   | 0.33       |
+| cosine_accuracy@3   | 0.54       |
+| cosine_accuracy@5   | 0.6        |
+| cosine_accuracy@10  | 0.7        |
+| cosine_precision@1  | 0.33       |
+| cosine_precision@3  | 0.1867     |
+| cosine_precision@5  | 0.124      |
+| cosine_precision@10 | 0.073      |
+| cosine_recall@1     | 0.315      |
+| cosine_recall@3     | 0.53       |
+| cosine_recall@5     | 0.59       |
+| cosine_recall@10    | 0.695      |
+| **cosine_ndcg@10**  | **0.5075** |
+| cosine_mrr@10       | 0.4527     |
+| cosine_map@100      | 0.4584     |
 
 <!--
 ## Bias, Risks and Limitations
@@ -487,7 +487,7 @@ You can finetune this model on your own dataset.
 - `eval_strategy`: steps
 - `per_device_train_batch_size`: 128
 - `per_device_eval_batch_size`: 128
-- `learning_rate`: 1e-06
+- `learning_rate`: 1e-05
 - `weight_decay`: 0.001
 - `max_steps`: 3000
 - `warmup_ratio`: 0.1
@@ -516,7 +516,7 @@ You can finetune this model on your own dataset.
 - `gradient_accumulation_steps`: 1
 - `eval_accumulation_steps`: None
 - `torch_empty_cache_steps`: None
-- `learning_rate`: 1e-06
+- `learning_rate`: 1e-05
 - `weight_decay`: 0.001
 - `adam_beta1`: 0.9
 - `adam_beta2`: 0.999
@@ -630,19 +630,19 @@ You can finetune this model on your own dataset.
 ### Training Logs
 | Epoch  | Step | Training Loss | Validation Loss | NanoMSMARCO_cosine_ndcg@10 | NanoNQ_cosine_ndcg@10 | NanoBEIR_mean_cosine_ndcg@10 |
 |:------:|:----:|:-------------:|:---------------:|:--------------------------:|:---------------------:|:----------------------------:|
-| 0      | 0    | -             | 4.0678          | 0.6259                     | 0.6583                | 0.6421                       |
-| 0.2874 | 250  | 4.2246        | 3.8520          | 0.6117                     | 0.6465                | 0.6291                       |
-| 0.5747 | 500  | 3.8138        | 3.1367          | 0.6062                     | 0.6457                | 0.6260                       |
-| 0.8621 | 750  | 2.9174        | 1.8442          | 0.5837                     | 0.5594                | 0.5715                       |
-| 1.1494 | 1000 | 1.8256        | 1.2096          | 0.5462                     | 0.4989                | 0.5226                       |
-| 1.4368 | 1250 | 1.4465        | 1.0779          | 0.5347                     | 0.4650                | 0.4998                       |
-| 1.7241 | 1500 | 1.3307        | 1.0331          | 0.5358                     | 0.4801                | 0.5079                       |
-| 2.0115 | 1750 | 1.2785        | 1.0094          | 0.5359                     | 0.4848                | 0.5104                       |
-| 2.2989 | 2000 | 1.249         | 0.9957          | 0.5282                     | 0.4860                | 0.5071                       |
-| 2.5862 | 2250 | 1.228         | 0.9865          | 0.5245                     | 0.4939                | 0.5092                       |
-| 2.8736 | 2500 | 1.2043        | 0.9809          | 0.5235                     | 0.5018                | 0.5126                       |
-| 3.1609 | 2750 | 1.208         | 0.9771          | 0.5261                     | 0.5018                | 0.5139                       |
-| 3.4483 | 3000 | 1.2008        | 0.9762          | 0.5241                     | 0.5018                | 0.5129                       |
+| 0      | 0    | -             | 1.1445          | 0.5540                     | 0.5931                | 0.5735                       |
+| 0.2874 | 250  | 1.1834        | 0.9135          | 0.4900                     | 0.5098                | 0.4999                       |
+| 0.5747 | 500  | 1.0424        | 0.8651          | 0.4979                     | 0.4970                | 0.4974                       |
+| 0.8621 | 750  | 1.0133        | 0.8524          | 0.5118                     | 0.4987                | 0.5052                       |
+| 1.1494 | 1000 | 0.9885        | 0.8441          | 0.5232                     | 0.5085                | 0.5159                       |
+| 1.4368 | 1250 | 0.9788        | 0.8383          | 0.5204                     | 0.5039                | 0.5122                       |
+| 1.7241 | 1500 | 0.9689        | 0.8339          | 0.5184                     | 0.5220                | 0.5202                       |
+| 2.0115 | 1750 | 0.9641        | 0.8292          | 0.5192                     | 0.4993                | 0.5093                       |
+| 2.2989 | 2000 | 0.9523        | 0.8269          | 0.5173                     | 0.4896                | 0.5034                       |
+| 2.5862 | 2250 | 0.9492        | 0.8248          | 0.5181                     | 0.5132                | 0.5157                       |
+| 2.8736 | 2500 | 0.936         | 0.8241          | 0.5187                     | 0.5082                | 0.5134                       |
+| 3.1609 | 2750 | 0.9427        | 0.8228          | 0.5193                     | 0.4957                | 0.5075                       |
+| 3.4483 | 3000 | 0.9363        | 0.8225          | 0.5190                     | 0.4959                | 0.5075                       |
 
 
 ### Framework Versions

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": ""