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: when was the first elephant brought to america
   sentences:
@@ -132,7 +132,7 @@ 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
@@ -142,49 +142,49 @@ model-index:
       type: NanoMSMARCO
     metrics:
     - type: cosine_accuracy@1
-      value: 0.16
+      value: 0.32
       name: Cosine Accuracy@1
     - type: cosine_accuracy@3
-      value: 0.32
+      value: 0.5
       name: Cosine Accuracy@3
     - type: cosine_accuracy@5
-      value: 0.4
+      value: 0.6
       name: Cosine Accuracy@5
     - type: cosine_accuracy@10
-      value: 0.54
+      value: 0.76
       name: Cosine Accuracy@10
     - type: cosine_precision@1
-      value: 0.16
+      value: 0.32
       name: Cosine Precision@1
     - type: cosine_precision@3
-      value: 0.10666666666666666
+      value: 0.16666666666666663
       name: Cosine Precision@3
     - type: cosine_precision@5
-      value: 0.08
+      value: 0.12000000000000002
       name: Cosine Precision@5
     - type: cosine_precision@10
-      value: 0.05400000000000001
+      value: 0.07600000000000001
       name: Cosine Precision@10
     - type: cosine_recall@1
-      value: 0.16
+      value: 0.32
       name: Cosine Recall@1
     - type: cosine_recall@3
-      value: 0.32
+      value: 0.5
       name: Cosine Recall@3
     - type: cosine_recall@5
-      value: 0.4
+      value: 0.6
       name: Cosine Recall@5
     - type: cosine_recall@10
-      value: 0.54
+      value: 0.76
       name: Cosine Recall@10
     - type: cosine_ndcg@10
-      value: 0.32698862634234876
+      value: 0.5174146339399069
       name: Cosine Ndcg@10
     - type: cosine_mrr@10
-      value: 0.2620793650793651
+      value: 0.4427063492063491
       name: Cosine Mrr@10
     - type: cosine_map@100
-      value: 0.2747949118190278
+      value: 0.452501292753926
       name: Cosine Map@100
   - task:
       type: information-retrieval
@@ -194,49 +194,49 @@ model-index:
       type: NanoNQ
     metrics:
     - type: cosine_accuracy@1
-      value: 0.22
+      value: 0.54
       name: Cosine Accuracy@1
     - type: cosine_accuracy@3
-      value: 0.44
+      value: 0.66
       name: Cosine Accuracy@3
     - type: cosine_accuracy@5
-      value: 0.52
+      value: 0.68
       name: Cosine Accuracy@5
     - type: cosine_accuracy@10
-      value: 0.64
+      value: 0.74
       name: Cosine Accuracy@10
     - type: cosine_precision@1
-      value: 0.22
+      value: 0.54
       name: Cosine Precision@1
     - type: cosine_precision@3
-      value: 0.14666666666666664
+      value: 0.22
       name: Cosine Precision@3
     - type: cosine_precision@5
-      value: 0.10400000000000001
+      value: 0.136
       name: Cosine Precision@5
     - type: cosine_precision@10
-      value: 0.06400000000000002
+      value: 0.08
       name: Cosine Precision@10
     - type: cosine_recall@1
-      value: 0.22
+      value: 0.51
       name: Cosine Recall@1
     - type: cosine_recall@3
-      value: 0.42
+      value: 0.62
       name: Cosine Recall@3
     - type: cosine_recall@5
-      value: 0.49
+      value: 0.64
       name: Cosine Recall@5
     - type: cosine_recall@10
-      value: 0.6
+      value: 0.72
       name: Cosine Recall@10
     - type: cosine_ndcg@10
-      value: 0.39877036805974797
+      value: 0.6171839770040762
       name: Cosine Ndcg@10
     - type: cosine_mrr@10
-      value: 0.3438015873015873
+      value: 0.6030555555555556
       name: Cosine Mrr@10
     - type: cosine_map@100
-      value: 0.3445409270682024
+      value: 0.5845310002947148
       name: Cosine Map@100
   - task:
       type: nano-beir
@@ -246,61 +246,61 @@ model-index:
       type: NanoBEIR_mean
     metrics:
     - type: cosine_accuracy@1
-      value: 0.19
+      value: 0.43000000000000005
       name: Cosine Accuracy@1
     - type: cosine_accuracy@3
-      value: 0.38
+      value: 0.5800000000000001
       name: Cosine Accuracy@3
     - type: cosine_accuracy@5
-      value: 0.46
+      value: 0.64
       name: Cosine Accuracy@5
     - type: cosine_accuracy@10
-      value: 0.5900000000000001
+      value: 0.75
       name: Cosine Accuracy@10
     - type: cosine_precision@1
-      value: 0.19
+      value: 0.43000000000000005
       name: Cosine Precision@1
     - type: cosine_precision@3
-      value: 0.12666666666666665
+      value: 0.1933333333333333
       name: Cosine Precision@3
     - type: cosine_precision@5
-      value: 0.092
+      value: 0.128
       name: Cosine Precision@5
     - type: cosine_precision@10
-      value: 0.05900000000000001
+      value: 0.07800000000000001
       name: Cosine Precision@10
     - type: cosine_recall@1
-      value: 0.19
+      value: 0.41500000000000004
       name: Cosine Recall@1
     - type: cosine_recall@3
-      value: 0.37
+      value: 0.56
       name: Cosine Recall@3
     - type: cosine_recall@5
-      value: 0.445
+      value: 0.62
       name: Cosine Recall@5
     - type: cosine_recall@10
-      value: 0.5700000000000001
+      value: 0.74
       name: Cosine Recall@10
     - type: cosine_ndcg@10
-      value: 0.3628794972010484
+      value: 0.5672993054719916
       name: Cosine Ndcg@10
     - type: cosine_mrr@10
-      value: 0.30294047619047615
+      value: 0.5228809523809523
       name: Cosine Mrr@10
     - type: cosine_map@100
-      value: 0.3096679194436151
+      value: 0.5185161465243204
       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
@@ -353,9 +353,9 @@ print(embeddings.shape)
 # Get the similarity scores for the embeddings
 similarities = model.similarity(embeddings, embeddings)
 print(similarities)
-# tensor([[1.0001, 1.0001, 0.4386],
-#         [1.0001, 1.0001, 0.4386],
-#         [0.4386, 0.4386, 1.0000]])
+# tensor([[1.0000, 1.0000, 0.8824],
+#         [1.0000, 1.0000, 0.8824],
+#         [0.8824, 0.8824, 1.0000]])
 ```
 
 <!--
@@ -393,21 +393,21 @@ You can finetune this model on your own dataset.
 
 | Metric              | NanoMSMARCO | NanoNQ     |
 |:--------------------|:------------|:-----------|
-| cosine_accuracy@1   | 0.16        | 0.22       |
-| cosine_accuracy@3   | 0.32        | 0.44       |
-| cosine_accuracy@5   | 0.4         | 0.52       |
-| cosine_accuracy@10  | 0.54        | 0.64       |
-| cosine_precision@1  | 0.16        | 0.22       |
-| cosine_precision@3  | 0.1067      | 0.1467     |
-| cosine_precision@5  | 0.08        | 0.104      |
-| cosine_precision@10 | 0.054       | 0.064      |
-| cosine_recall@1     | 0.16        | 0.22       |
-| cosine_recall@3     | 0.32        | 0.42       |
-| cosine_recall@5     | 0.4         | 0.49       |
-| cosine_recall@10    | 0.54        | 0.6        |
-| **cosine_ndcg@10**  | **0.327**   | **0.3988** |
-| cosine_mrr@10       | 0.2621      | 0.3438     |
-| cosine_map@100      | 0.2748      | 0.3445     |
+| cosine_accuracy@1   | 0.32        | 0.54       |
+| cosine_accuracy@3   | 0.5         | 0.66       |
+| cosine_accuracy@5   | 0.6         | 0.68       |
+| cosine_accuracy@10  | 0.76        | 0.74       |
+| cosine_precision@1  | 0.32        | 0.54       |
+| cosine_precision@3  | 0.1667      | 0.22       |
+| cosine_precision@5  | 0.12        | 0.136      |
+| cosine_precision@10 | 0.076       | 0.08       |
+| cosine_recall@1     | 0.32        | 0.51       |
+| cosine_recall@3     | 0.5         | 0.62       |
+| cosine_recall@5     | 0.6         | 0.64       |
+| cosine_recall@10    | 0.76        | 0.72       |
+| **cosine_ndcg@10**  | **0.5174**  | **0.6172** |
+| cosine_mrr@10       | 0.4427      | 0.6031     |
+| cosine_map@100      | 0.4525      | 0.5845     |
 
 #### Nano BEIR
 
@@ -425,21 +425,21 @@ You can finetune this model on your own dataset.
 
 | Metric              | Value      |
 |:--------------------|:-----------|
-| cosine_accuracy@1   | 0.19       |
-| cosine_accuracy@3   | 0.38       |
-| cosine_accuracy@5   | 0.46       |
-| cosine_accuracy@10  | 0.59       |
-| cosine_precision@1  | 0.19       |
-| cosine_precision@3  | 0.1267     |
-| cosine_precision@5  | 0.092      |
-| cosine_precision@10 | 0.059      |
-| cosine_recall@1     | 0.19       |
-| cosine_recall@3     | 0.37       |
-| cosine_recall@5     | 0.445      |
-| cosine_recall@10    | 0.57       |
-| **cosine_ndcg@10**  | **0.3629** |
-| cosine_mrr@10       | 0.3029     |
-| cosine_map@100      | 0.3097     |
+| cosine_accuracy@1   | 0.43       |
+| cosine_accuracy@3   | 0.58       |
+| cosine_accuracy@5   | 0.64       |
+| cosine_accuracy@10  | 0.75       |
+| cosine_precision@1  | 0.43       |
+| cosine_precision@3  | 0.1933     |
+| cosine_precision@5  | 0.128      |
+| cosine_precision@10 | 0.078      |
+| cosine_recall@1     | 0.415      |
+| cosine_recall@3     | 0.56       |
+| cosine_recall@5     | 0.62       |
+| cosine_recall@10    | 0.74       |
+| **cosine_ndcg@10**  | **0.5673** |
+| cosine_mrr@10       | 0.5229     |
+| cosine_map@100      | 0.5185     |
 
 <!--
 ## Bias, Risks and Limitations
@@ -475,7 +475,7 @@ You can finetune this model on your own dataset.
 * Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
   ```json
   {
-      "scale": 3.0,
+      "scale": 20.0,
       "similarity_fct": "cos_sim",
       "gather_across_devices": false
   }
@@ -501,7 +501,7 @@ You can finetune this model on your own dataset.
 * Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
   ```json
   {
-      "scale": 3.0,
+      "scale": 20.0,
       "similarity_fct": "cos_sim",
       "gather_across_devices": false
   }
@@ -513,9 +513,9 @@ 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`: 8e-05
-- `weight_decay`: 0.005
-- `max_steps`: 3375
+- `learning_rate`: 0.0001
+- `weight_decay`: 0.001
+- `max_steps`: 1687
 - `warmup_ratio`: 0.1
 - `fp16`: True
 - `dataloader_drop_last`: True
@@ -542,14 +542,14 @@ You can finetune this model on your own dataset.
 - `gradient_accumulation_steps`: 1
 - `eval_accumulation_steps`: None
 - `torch_empty_cache_steps`: None
-- `learning_rate`: 8e-05
-- `weight_decay`: 0.005
+- `learning_rate`: 0.0001
+- `weight_decay`: 0.001
 - `adam_beta1`: 0.9
 - `adam_beta2`: 0.999
 - `adam_epsilon`: 1e-08
 - `max_grad_norm`: 1.0
 - `num_train_epochs`: 3.0
-- `max_steps`: 3375
+- `max_steps`: 1687
 - `lr_scheduler_type`: linear
 - `lr_scheduler_kwargs`: {}
 - `warmup_ratio`: 0.1
@@ -656,20 +656,13 @@ 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    | -             | 4.9445          | 0.6259                     | 0.6583                | 0.6421                       |
-| 0.2874 | 250  | 3.6887        | 3.0013          | 0.4676                     | 0.4424                | 0.4550                       |
-| 0.5747 | 500  | 3.0661        | 2.9415          | 0.4647                     | 0.4688                | 0.4667                       |
-| 0.8621 | 750  | 3.0125        | 2.9161          | 0.3994                     | 0.4479                | 0.4237                       |
-| 1.1494 | 1000 | 2.9691        | 2.9044          | 0.3845                     | 0.4090                | 0.3968                       |
-| 1.4368 | 1250 | 2.9407        | 2.8981          | 0.3614                     | 0.3858                | 0.3736                       |
-| 1.7241 | 1500 | 2.9321        | 2.8893          | 0.3182                     | 0.3811                | 0.3496                       |
-| 2.0115 | 1750 | 2.9227        | 2.8817          | 0.3444                     | 0.3973                | 0.3708                       |
-| 2.2989 | 2000 | 2.8854        | 2.8807          | 0.3088                     | 0.3730                | 0.3409                       |
-| 2.5862 | 2250 | 2.8832        | 2.8744          | 0.3251                     | 0.3968                | 0.3610                       |
-| 2.8736 | 2500 | 2.8857        | 2.8730          | 0.3504                     | 0.4101                | 0.3802                       |
-| 3.1609 | 2750 | 2.8677        | 2.8714          | 0.3233                     | 0.4021                | 0.3627                       |
-| 3.4483 | 3000 | 2.86          | 2.8697          | 0.3239                     | 0.4106                | 0.3673                       |
-| 3.7356 | 3250 | 2.8584        | 2.8686          | 0.3270                     | 0.3988                | 0.3629                       |
+| 0      | 0    | -             | 0.1310          | 0.5540                     | 0.5931                | 0.5735                       |
+| 0.2874 | 250  | 0.1078        | 0.0793          | 0.5375                     | 0.5386                | 0.5380                       |
+| 0.5747 | 500  | 0.0893        | 0.0673          | 0.5031                     | 0.6009                | 0.5520                       |
+| 0.8621 | 750  | 0.081         | 0.0605          | 0.5414                     | 0.5786                | 0.5600                       |
+| 1.1494 | 1000 | 0.0593        | 0.0565          | 0.5158                     | 0.5786                | 0.5472                       |
+| 1.4368 | 1250 | 0.0422        | 0.0537          | 0.5300                     | 0.6107                | 0.5704                       |
+| 1.7241 | 1500 | 0.0402        | 0.0514          | 0.5174                     | 0.6172                | 0.5673                       |
 
 
 ### 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": ""