Add new SentenceTransformer model

README.md

@@ -7,7 +7,7 @@ tags:
 - generated_from_trainer
 - dataset_size:90000
 - loss:MultipleNegativesRankingLoss
-base_model: thenlper/gte-small
+base_model: sentence-transformers/all-MiniLM-L6-v2
 widget:
 - source_sentence: who is the publisher of the norton anthology american literature
   sentences:
@@ -154,7 +154,7 @@ 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
@@ -164,49 +164,49 @@ model-index:
       type: NanoMSMARCO
     metrics:
     - type: cosine_accuracy@1
-      value: 0.12
+      value: 0.24
       name: Cosine Accuracy@1
     - type: cosine_accuracy@3
-      value: 0.32
+      value: 0.52
       name: Cosine Accuracy@3
     - type: cosine_accuracy@5
-      value: 0.48
+      value: 0.64
       name: Cosine Accuracy@5
     - type: cosine_accuracy@10
-      value: 0.6
+      value: 0.76
       name: Cosine Accuracy@10
     - type: cosine_precision@1
-      value: 0.12
+      value: 0.24
       name: Cosine Precision@1
     - type: cosine_precision@3
-      value: 0.10666666666666666
+      value: 0.1733333333333333
       name: Cosine Precision@3
     - type: cosine_precision@5
-      value: 0.09600000000000002
+      value: 0.128
       name: Cosine Precision@5
     - type: cosine_precision@10
-      value: 0.06
+      value: 0.07600000000000001
       name: Cosine Precision@10
     - type: cosine_recall@1
-      value: 0.12
+      value: 0.24
       name: Cosine Recall@1
     - type: cosine_recall@3
-      value: 0.32
+      value: 0.52
       name: Cosine Recall@3
     - type: cosine_recall@5
-      value: 0.48
+      value: 0.64
       name: Cosine Recall@5
     - type: cosine_recall@10
-      value: 0.6
+      value: 0.76
       name: Cosine Recall@10
     - type: cosine_ndcg@10
-      value: 0.3451699142127375
+      value: 0.49143458252672184
       name: Cosine Ndcg@10
     - type: cosine_mrr@10
-      value: 0.2649920634920635
+      value: 0.4057380952380952
       name: Cosine Mrr@10
     - type: cosine_map@100
-      value: 0.2748673342528789
+      value: 0.4167225925544634
       name: Cosine Map@100
   - task:
       type: information-retrieval
@@ -216,49 +216,49 @@ model-index:
       type: NanoNQ
     metrics:
     - type: cosine_accuracy@1
-      value: 0.22
+      value: 0.46
       name: Cosine Accuracy@1
     - type: cosine_accuracy@3
-      value: 0.44
+      value: 0.62
       name: Cosine Accuracy@3
     - type: cosine_accuracy@5
-      value: 0.5
+      value: 0.66
       name: Cosine Accuracy@5
     - type: cosine_accuracy@10
-      value: 0.56
+      value: 0.7
       name: Cosine Accuracy@10
     - type: cosine_precision@1
-      value: 0.22
+      value: 0.46
       name: Cosine Precision@1
     - type: cosine_precision@3
-      value: 0.14666666666666664
+      value: 0.20666666666666664
       name: Cosine Precision@3
     - type: cosine_precision@5
-      value: 0.1
+      value: 0.136
       name: Cosine Precision@5
     - type: cosine_precision@10
-      value: 0.05800000000000001
+      value: 0.07600000000000001
       name: Cosine Precision@10
     - type: cosine_recall@1
-      value: 0.22
+      value: 0.45
       name: Cosine Recall@1
     - type: cosine_recall@3
-      value: 0.43
+      value: 0.58
       name: Cosine Recall@3
     - type: cosine_recall@5
-      value: 0.49
+      value: 0.63
       name: Cosine Recall@5
     - type: cosine_recall@10
-      value: 0.54
+      value: 0.69
       name: Cosine Recall@10
     - type: cosine_ndcg@10
-      value: 0.3853992171360362
+      value: 0.5748041984771892
       name: Cosine Ndcg@10
     - type: cosine_mrr@10
-      value: 0.3358888888888889
+      value: 0.5456666666666667
       name: Cosine Mrr@10
     - type: cosine_map@100
-      value: 0.3486523060866078
+      value: 0.5421576333440519
       name: Cosine Map@100
   - task:
       type: nano-beir
@@ -268,61 +268,61 @@ model-index:
       type: NanoBEIR_mean
     metrics:
     - type: cosine_accuracy@1
-      value: 0.16999999999999998
+      value: 0.35
       name: Cosine Accuracy@1
     - type: cosine_accuracy@3
-      value: 0.38
+      value: 0.5700000000000001
       name: Cosine Accuracy@3
     - type: cosine_accuracy@5
-      value: 0.49
+      value: 0.65
       name: Cosine Accuracy@5
     - type: cosine_accuracy@10
-      value: 0.5800000000000001
+      value: 0.73
       name: Cosine Accuracy@10
     - type: cosine_precision@1
-      value: 0.16999999999999998
+      value: 0.35
       name: Cosine Precision@1
     - type: cosine_precision@3
-      value: 0.12666666666666665
+      value: 0.18999999999999997
       name: Cosine Precision@3
     - type: cosine_precision@5
-      value: 0.098
+      value: 0.132
       name: Cosine Precision@5
     - type: cosine_precision@10
-      value: 0.059000000000000004
+      value: 0.07600000000000001
       name: Cosine Precision@10
     - type: cosine_recall@1
-      value: 0.16999999999999998
+      value: 0.345
       name: Cosine Recall@1
     - type: cosine_recall@3
-      value: 0.375
+      value: 0.55
       name: Cosine Recall@3
     - type: cosine_recall@5
-      value: 0.485
+      value: 0.635
       name: Cosine Recall@5
     - type: cosine_recall@10
-      value: 0.5700000000000001
+      value: 0.725
       name: Cosine Recall@10
     - type: cosine_ndcg@10
-      value: 0.36528456567438683
+      value: 0.5331193905019556
       name: Cosine Ndcg@10
     - type: cosine_mrr@10
-      value: 0.3004404761904762
+      value: 0.47570238095238093
       name: Cosine Mrr@10
     - type: cosine_map@100
-      value: 0.31175982016974335
+      value: 0.47944011294925765
       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
@@ -375,9 +375,9 @@ print(embeddings.shape)
 # Get the similarity scores for the embeddings
 similarities = model.similarity(embeddings, embeddings)
 print(similarities)
-# tensor([[ 1.0000,  0.9977, -0.0309],
-#         [ 0.9977,  1.0000, -0.0296],
-#         [-0.0309, -0.0296,  1.0000]])
+# tensor([[1.0000, 0.7393, 0.1251],
+#         [0.7393, 1.0000, 0.1255],
+#         [0.1251, 0.1255, 1.0000]])
 ```
 
 <!--
@@ -415,21 +415,21 @@ You can finetune this model on your own dataset.
 
 | Metric              | NanoMSMARCO | NanoNQ     |
 |:--------------------|:------------|:-----------|
-| cosine_accuracy@1   | 0.12        | 0.22       |
-| cosine_accuracy@3   | 0.32        | 0.44       |
-| cosine_accuracy@5   | 0.48        | 0.5        |
-| cosine_accuracy@10  | 0.6         | 0.56       |
-| cosine_precision@1  | 0.12        | 0.22       |
-| cosine_precision@3  | 0.1067      | 0.1467     |
-| cosine_precision@5  | 0.096       | 0.1        |
-| cosine_precision@10 | 0.06        | 0.058      |
-| cosine_recall@1     | 0.12        | 0.22       |
-| cosine_recall@3     | 0.32        | 0.43       |
-| cosine_recall@5     | 0.48        | 0.49       |
-| cosine_recall@10    | 0.6         | 0.54       |
-| **cosine_ndcg@10**  | **0.3452**  | **0.3854** |
-| cosine_mrr@10       | 0.265       | 0.3359     |
-| cosine_map@100      | 0.2749      | 0.3487     |
+| cosine_accuracy@1   | 0.24        | 0.46       |
+| cosine_accuracy@3   | 0.52        | 0.62       |
+| cosine_accuracy@5   | 0.64        | 0.66       |
+| cosine_accuracy@10  | 0.76        | 0.7        |
+| cosine_precision@1  | 0.24        | 0.46       |
+| cosine_precision@3  | 0.1733      | 0.2067     |
+| cosine_precision@5  | 0.128       | 0.136      |
+| cosine_precision@10 | 0.076       | 0.076      |
+| cosine_recall@1     | 0.24        | 0.45       |
+| cosine_recall@3     | 0.52        | 0.58       |
+| cosine_recall@5     | 0.64        | 0.63       |
+| cosine_recall@10    | 0.76        | 0.69       |
+| **cosine_ndcg@10**  | **0.4914**  | **0.5748** |
+| cosine_mrr@10       | 0.4057      | 0.5457     |
+| cosine_map@100      | 0.4167      | 0.5422     |
 
 #### Nano BEIR
 
@@ -447,21 +447,21 @@ You can finetune this model on your own dataset.
 
 | Metric              | Value      |
 |:--------------------|:-----------|
-| cosine_accuracy@1   | 0.17       |
-| cosine_accuracy@3   | 0.38       |
-| cosine_accuracy@5   | 0.49       |
-| cosine_accuracy@10  | 0.58       |
-| cosine_precision@1  | 0.17       |
-| cosine_precision@3  | 0.1267     |
-| cosine_precision@5  | 0.098      |
-| cosine_precision@10 | 0.059      |
-| cosine_recall@1     | 0.17       |
-| cosine_recall@3     | 0.375      |
-| cosine_recall@5     | 0.485      |
-| cosine_recall@10    | 0.57       |
-| **cosine_ndcg@10**  | **0.3653** |
-| cosine_mrr@10       | 0.3004     |
-| cosine_map@100      | 0.3118     |
+| cosine_accuracy@1   | 0.35       |
+| cosine_accuracy@3   | 0.57       |
+| cosine_accuracy@5   | 0.65       |
+| cosine_accuracy@10  | 0.73       |
+| cosine_precision@1  | 0.35       |
+| cosine_precision@3  | 0.19       |
+| cosine_precision@5  | 0.132      |
+| cosine_precision@10 | 0.076      |
+| cosine_recall@1     | 0.345      |
+| cosine_recall@3     | 0.55       |
+| cosine_recall@5     | 0.635      |
+| cosine_recall@10    | 0.725      |
+| **cosine_ndcg@10**  | **0.5331** |
+| cosine_mrr@10       | 0.4757     |
+| cosine_map@100      | 0.4794     |
 
 <!--
 ## Bias, Risks and Limitations
@@ -497,7 +497,7 @@ 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
   }
@@ -523,7 +523,7 @@ 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
   }
@@ -535,9 +535,9 @@ 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
@@ -564,14 +564,14 @@ 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
@@ -678,20 +678,13 @@ 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    | -             | 5.0014          | 0.6259                     | 0.6583                | 0.6421                       |
-| 0.3556 | 250  | 3.7345        | 3.0513          | 0.4721                     | 0.4567                | 0.4644                       |
-| 0.7112 | 500  | 3.1165        | 2.9938          | 0.4464                     | 0.4306                | 0.4385                       |
-| 1.0669 | 750  | 3.055         | 2.9656          | 0.4028                     | 0.4675                | 0.4351                       |
-| 1.4225 | 1000 | 3.0018        | 2.9558          | 0.3668                     | 0.4309                | 0.3989                       |
-| 1.7781 | 1250 | 2.988         | 2.9463          | 0.4017                     | 0.4426                | 0.4221                       |
-| 2.1337 | 1500 | 2.9625        | 2.9372          | 0.3571                     | 0.4003                | 0.3787                       |
-| 2.4893 | 1750 | 2.9363        | 2.9311          | 0.3729                     | 0.4068                | 0.3898                       |
-| 2.8450 | 2000 | 2.9287        | 2.9274          | 0.3728                     | 0.3778                | 0.3753                       |
-| 3.2006 | 2250 | 2.907         | 2.9254          | 0.3770                     | 0.3713                | 0.3742                       |
-| 3.5562 | 2500 | 2.8979        | 2.9242          | 0.3606                     | 0.3884                | 0.3745                       |
-| 3.9118 | 2750 | 2.8931        | 2.9215          | 0.3446                     | 0.3955                | 0.3700                       |
-| 4.2674 | 3000 | 2.883         | 2.9207          | 0.3511                     | 0.3777                | 0.3644                       |
-| 4.6230 | 3250 | 2.8762        | 2.9201          | 0.3452                     | 0.3854                | 0.3653                       |
+| 0      | 0    | -             | 0.0803          | 0.5540                     | 0.5931                | 0.5735                       |
+| 0.3556 | 250  | 0.0897        | 0.0764          | 0.5354                     | 0.5945                | 0.5650                       |
+| 0.7112 | 500  | 0.0917        | 0.0749          | 0.5252                     | 0.5638                | 0.5445                       |
+| 1.0669 | 750  | 0.0823        | 0.0653          | 0.5267                     | 0.5904                | 0.5586                       |
+| 1.4225 | 1000 | 0.0459        | 0.0630          | 0.5236                     | 0.5689                | 0.5462                       |
+| 1.7781 | 1250 | 0.0429        | 0.0613          | 0.5312                     | 0.5676                | 0.5494                       |
+| 2.1337 | 1500 | 0.0393        | 0.0600          | 0.4914                     | 0.5748                | 0.5331                       |
 
 
 ### 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": ""