Add new SentenceTransformer model

README.md

@@ -452,7 +452,6 @@ widget:
     If you already have one or more GCP Service Connectors configured in your ZenML
     deployment, you can check which of them can be used to access generic GCP resources
     like the GCP Image Builder required for your GCP Image Builder by running e.g.:'
-datasets: []
 pipeline_tag: sentence-similarity
 library_name: sentence-transformers
 metrics:
@@ -482,10 +481,10 @@ model-index:
       type: dim_384
     metrics:
     - type: cosine_accuracy@1
-      value: 0.5
+      value: 0.75
       name: Cosine Accuracy@1
     - type: cosine_accuracy@3
-      value: 0.75
+      value: 1.0
       name: Cosine Accuracy@3
     - type: cosine_accuracy@5
       value: 1.0
@@ -494,10 +493,10 @@ model-index:
       value: 1.0
       name: Cosine Accuracy@10
     - type: cosine_precision@1
-      value: 0.5
+      value: 0.75
       name: Cosine Precision@1
     - type: cosine_precision@3
-      value: 0.25
+      value: 0.3333333333333333
       name: Cosine Precision@3
     - type: cosine_precision@5
       value: 0.2
@@ -506,10 +505,10 @@ model-index:
       value: 0.1
       name: Cosine Precision@10
     - type: cosine_recall@1
-      value: 0.5
+      value: 0.75
       name: Cosine Recall@1
     - type: cosine_recall@3
-      value: 0.75
+      value: 1.0
       name: Cosine Recall@3
     - type: cosine_recall@5
       value: 1.0
@@ -518,13 +517,13 @@ model-index:
       value: 1.0
       name: Cosine Recall@10
     - type: cosine_ndcg@10
-      value: 0.7326691395183482
+      value: 0.875
       name: Cosine Ndcg@10
     - type: cosine_mrr@10
-      value: 0.6458333333333333
+      value: 0.8333333333333334
       name: Cosine Mrr@10
     - type: cosine_map@100
-      value: 0.6458333333333333
+      value: 0.8333333333333334
       name: Cosine Map@100
   - task:
       type: information-retrieval
@@ -534,10 +533,10 @@ model-index:
       type: dim_256
     metrics:
     - type: cosine_accuracy@1
-      value: 0.5
+      value: 0.75
       name: Cosine Accuracy@1
     - type: cosine_accuracy@3
-      value: 0.75
+      value: 1.0
       name: Cosine Accuracy@3
     - type: cosine_accuracy@5
       value: 1.0
@@ -546,10 +545,10 @@ model-index:
       value: 1.0
       name: Cosine Accuracy@10
     - type: cosine_precision@1
-      value: 0.5
+      value: 0.75
       name: Cosine Precision@1
     - type: cosine_precision@3
-      value: 0.25
+      value: 0.3333333333333333
       name: Cosine Precision@3
     - type: cosine_precision@5
       value: 0.2
@@ -558,10 +557,10 @@ model-index:
       value: 0.1
       name: Cosine Precision@10
     - type: cosine_recall@1
-      value: 0.5
+      value: 0.75
       name: Cosine Recall@1
     - type: cosine_recall@3
-      value: 0.75
+      value: 1.0
       name: Cosine Recall@3
     - type: cosine_recall@5
       value: 1.0
@@ -570,13 +569,13 @@ model-index:
       value: 1.0
       name: Cosine Recall@10
     - type: cosine_ndcg@10
-      value: 0.7326691395183482
+      value: 0.875
       name: Cosine Ndcg@10
     - type: cosine_mrr@10
-      value: 0.6458333333333333
+      value: 0.8333333333333334
       name: Cosine Mrr@10
     - type: cosine_map@100
-      value: 0.6458333333333333
+      value: 0.8333333333333334
       name: Cosine Map@100
   - task:
       type: information-retrieval
@@ -586,10 +585,10 @@ model-index:
       type: dim_128
     metrics:
     - type: cosine_accuracy@1
-      value: 0.5
+      value: 0.75
       name: Cosine Accuracy@1
     - type: cosine_accuracy@3
-      value: 0.5
+      value: 0.75
       name: Cosine Accuracy@3
     - type: cosine_accuracy@5
       value: 1.0
@@ -598,10 +597,10 @@ model-index:
       value: 1.0
       name: Cosine Accuracy@10
     - type: cosine_precision@1
-      value: 0.5
+      value: 0.75
       name: Cosine Precision@1
     - type: cosine_precision@3
-      value: 0.16666666666666666
+      value: 0.25
       name: Cosine Precision@3
     - type: cosine_precision@5
       value: 0.2
@@ -610,10 +609,10 @@ model-index:
       value: 0.1
       name: Cosine Precision@10
     - type: cosine_recall@1
-      value: 0.5
+      value: 0.75
       name: Cosine Recall@1
     - type: cosine_recall@3
-      value: 0.5
+      value: 0.75
       name: Cosine Recall@3
     - type: cosine_recall@5
       value: 1.0
@@ -622,13 +621,13 @@ model-index:
       value: 1.0
       name: Cosine Recall@10
     - type: cosine_ndcg@10
-      value: 0.7153382790366966
+      value: 0.8576691395183482
       name: Cosine Ndcg@10
     - type: cosine_mrr@10
-      value: 0.625
+      value: 0.8125
       name: Cosine Mrr@10
     - type: cosine_map@100
-      value: 0.625
+      value: 0.8125
       name: Cosine Map@100
   - task:
       type: information-retrieval
@@ -638,10 +637,10 @@ model-index:
       type: dim_64
     metrics:
     - type: cosine_accuracy@1
-      value: 0.5
+      value: 0.75
       name: Cosine Accuracy@1
     - type: cosine_accuracy@3
-      value: 0.75
+      value: 1.0
       name: Cosine Accuracy@3
     - type: cosine_accuracy@5
       value: 1.0
@@ -650,10 +649,10 @@ model-index:
       value: 1.0
       name: Cosine Accuracy@10
     - type: cosine_precision@1
-      value: 0.5
+      value: 0.75
       name: Cosine Precision@1
     - type: cosine_precision@3
-      value: 0.25
+      value: 0.3333333333333333
       name: Cosine Precision@3
     - type: cosine_precision@5
       value: 0.2
@@ -662,10 +661,10 @@ model-index:
       value: 0.1
       name: Cosine Precision@10
     - type: cosine_recall@1
-      value: 0.5
+      value: 0.75
       name: Cosine Recall@1
     - type: cosine_recall@3
-      value: 0.75
+      value: 1.0
       name: Cosine Recall@3
     - type: cosine_recall@5
       value: 1.0
@@ -674,19 +673,19 @@ model-index:
       value: 1.0
       name: Cosine Recall@10
     - type: cosine_ndcg@10
-      value: 0.7326691395183482
+      value: 0.875
       name: Cosine Ndcg@10
     - type: cosine_mrr@10
-      value: 0.6458333333333333
+      value: 0.8333333333333334
       name: Cosine Mrr@10
     - type: cosine_map@100
-      value: 0.6458333333333333
+      value: 0.8333333333333334
       name: Cosine Map@100
 ---
 
 # zenml/finetuned-snowflake-arctic-embed-m-v1.5
 
-This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [Snowflake/snowflake-arctic-embed-m-v1.5](https://huggingface.co/Snowflake/snowflake-arctic-embed-m-v1.5). It maps sentences & paragraphs to a 768-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 [Snowflake/snowflake-arctic-embed-m-v1.5](https://huggingface.co/Snowflake/snowflake-arctic-embed-m-v1.5) on the json dataset. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
 
 ## Model Details
 
@@ -696,7 +695,8 @@ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [S
 - **Maximum Sequence Length:** 512 tokens
 - **Output Dimensionality:** 768 tokens
 - **Similarity Function:** Cosine Similarity
-<!-- - **Training Dataset:** Unknown -->
+- **Training Dataset:**
+    - json
 - **Language:** en
 - **License:** apache-2.0
 
@@ -782,21 +782,21 @@ You can finetune this model on your own dataset.
 
 | Metric              | Value      |
 |:--------------------|:-----------|
-| cosine_accuracy@1   | 0.5        |
-| cosine_accuracy@3   | 0.75       |
+| cosine_accuracy@1   | 0.75       |
+| cosine_accuracy@3   | 1.0        |
 | cosine_accuracy@5   | 1.0        |
 | cosine_accuracy@10  | 1.0        |
-| cosine_precision@1  | 0.5        |
-| cosine_precision@3  | 0.25       |
+| cosine_precision@1  | 0.75       |
+| cosine_precision@3  | 0.3333     |
 | cosine_precision@5  | 0.2        |
 | cosine_precision@10 | 0.1        |
-| cosine_recall@1     | 0.5        |
-| cosine_recall@3     | 0.75       |
+| cosine_recall@1     | 0.75       |
+| cosine_recall@3     | 1.0        |
 | cosine_recall@5     | 1.0        |
 | cosine_recall@10    | 1.0        |
-| cosine_ndcg@10      | 0.7327     |
-| cosine_mrr@10       | 0.6458     |
-| **cosine_map@100**  | **0.6458** |
+| cosine_ndcg@10      | 0.875      |
+| cosine_mrr@10       | 0.8333     |
+| **cosine_map@100**  | **0.8333** |
 
 #### Information Retrieval
 * Dataset: `dim_256`
@@ -804,43 +804,43 @@ You can finetune this model on your own dataset.
 
 | Metric              | Value      |
 |:--------------------|:-----------|
-| cosine_accuracy@1   | 0.5        |
-| cosine_accuracy@3   | 0.75       |
+| cosine_accuracy@1   | 0.75       |
+| cosine_accuracy@3   | 1.0        |
 | cosine_accuracy@5   | 1.0        |
 | cosine_accuracy@10  | 1.0        |
-| cosine_precision@1  | 0.5        |
-| cosine_precision@3  | 0.25       |
+| cosine_precision@1  | 0.75       |
+| cosine_precision@3  | 0.3333     |
 | cosine_precision@5  | 0.2        |
 | cosine_precision@10 | 0.1        |
-| cosine_recall@1     | 0.5        |
-| cosine_recall@3     | 0.75       |
+| cosine_recall@1     | 0.75       |
+| cosine_recall@3     | 1.0        |
 | cosine_recall@5     | 1.0        |
 | cosine_recall@10    | 1.0        |
-| cosine_ndcg@10      | 0.7327     |
-| cosine_mrr@10       | 0.6458     |
-| **cosine_map@100**  | **0.6458** |
+| cosine_ndcg@10      | 0.875      |
+| cosine_mrr@10       | 0.8333     |
+| **cosine_map@100**  | **0.8333** |
 
 #### Information Retrieval
 * Dataset: `dim_128`
 * Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
 
-| Metric              | Value     |
-|:--------------------|:----------|
-| cosine_accuracy@1   | 0.5       |
-| cosine_accuracy@3   | 0.5       |
-| cosine_accuracy@5   | 1.0       |
-| cosine_accuracy@10  | 1.0       |
-| cosine_precision@1  | 0.5       |
-| cosine_precision@3  | 0.1667    |
-| cosine_precision@5  | 0.2       |
-| cosine_precision@10 | 0.1       |
-| cosine_recall@1     | 0.5       |
-| cosine_recall@3     | 0.5       |
-| cosine_recall@5     | 1.0       |
-| cosine_recall@10    | 1.0       |
-| cosine_ndcg@10      | 0.7153    |
-| cosine_mrr@10       | 0.625     |
-| **cosine_map@100**  | **0.625** |
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.75       |
+| cosine_accuracy@3   | 0.75       |
+| cosine_accuracy@5   | 1.0        |
+| cosine_accuracy@10  | 1.0        |
+| cosine_precision@1  | 0.75       |
+| cosine_precision@3  | 0.25       |
+| cosine_precision@5  | 0.2        |
+| cosine_precision@10 | 0.1        |
+| cosine_recall@1     | 0.75       |
+| cosine_recall@3     | 0.75       |
+| cosine_recall@5     | 1.0        |
+| cosine_recall@10    | 1.0        |
+| cosine_ndcg@10      | 0.8577     |
+| cosine_mrr@10       | 0.8125     |
+| **cosine_map@100**  | **0.8125** |
 
 #### Information Retrieval
 * Dataset: `dim_64`
@@ -848,21 +848,21 @@ You can finetune this model on your own dataset.
 
 | Metric              | Value      |
 |:--------------------|:-----------|
-| cosine_accuracy@1   | 0.5        |
-| cosine_accuracy@3   | 0.75       |
+| cosine_accuracy@1   | 0.75       |
+| cosine_accuracy@3   | 1.0        |
 | cosine_accuracy@5   | 1.0        |
 | cosine_accuracy@10  | 1.0        |
-| cosine_precision@1  | 0.5        |
-| cosine_precision@3  | 0.25       |
+| cosine_precision@1  | 0.75       |
+| cosine_precision@3  | 0.3333     |
 | cosine_precision@5  | 0.2        |
 | cosine_precision@10 | 0.1        |
-| cosine_recall@1     | 0.5        |
-| cosine_recall@3     | 0.75       |
+| cosine_recall@1     | 0.75       |
+| cosine_recall@3     | 1.0        |
 | cosine_recall@5     | 1.0        |
 | cosine_recall@10    | 1.0        |
-| cosine_ndcg@10      | 0.7327     |
-| cosine_mrr@10       | 0.6458     |
-| **cosine_map@100**  | **0.6458** |
+| cosine_ndcg@10      | 0.875      |
+| cosine_mrr@10       | 0.8333     |
+| **cosine_map@100**  | **0.8333** |
 
 <!--
 ## Bias, Risks and Limitations
@@ -880,12 +880,12 @@ You can finetune this model on your own dataset.
 
 ### Training Dataset
 
-#### Unnamed Dataset
-
+#### json
 
+* Dataset: json
 * Size: 36 training samples
 * Columns: <code>positive</code> and <code>anchor</code>
-* Approximate statistics based on the first 1000 samples:
+* Approximate statistics based on the first 36 samples:
   |         | positive                                                                           | anchor                                                                               |
   |:--------|:-----------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|
   | type    | string                                                                             | string                                                                               |
@@ -1043,6 +1043,7 @@ You can finetune this model on your own dataset.
 - `optim_target_modules`: None
 - `batch_eval_metrics`: False
 - `eval_on_start`: False
+- `use_liger_kernel`: False
 - `eval_use_gather_object`: False
 - `batch_sampler`: no_duplicates
 - `multi_dataset_batch_sampler`: proportional
@@ -1050,22 +1051,22 @@ You can finetune this model on your own dataset.
 </details>
 
 ### Training Logs
-| Epoch   | Step  | dim_128_cosine_map@100 | dim_256_cosine_map@100 | dim_384_cosine_map@100 | dim_64_cosine_map@100 |
+| Epoch   | Step  | dim_384_cosine_map@100 | dim_256_cosine_map@100 | dim_128_cosine_map@100 | dim_64_cosine_map@100 |
 |:-------:|:-----:|:----------------------:|:----------------------:|:----------------------:|:---------------------:|
-| **1.0** | **1** | **0.625**              | **0.6458**             | **0.6458**             | **0.6458**            |
-| 2.0     | 3     | 0.625                  | 0.6458                 | 0.6458                 | 0.6458                |
-| 3.0     | 4     | 0.625                  | 0.6458                 | 0.6458                 | 0.6458                |
+| **1.0** | **1** | **0.8333**             | **0.8333**             | **0.8125**             | **0.8333**            |
+| 2.0     | 3     | 0.8333                 | 0.8333                 | 0.8125                 | 0.8333                |
+| 3.0     | 4     | 0.8333                 | 0.8333                 | 0.8125                 | 0.8333                |
 
 * The bold row denotes the saved checkpoint.
 
 ### Framework Versions
-- Python: 3.9.6
-- Sentence Transformers: 3.0.1
-- Transformers: 4.44.0
-- PyTorch: 2.5.1
-- Accelerate: 0.33.0
-- Datasets: 2.20.0
-- Tokenizers: 0.19.1
+- Python: 3.11.9
+- Sentence Transformers: 3.2.0
+- Transformers: 4.45.2
+- PyTorch: 2.5.0+cu124
+- Accelerate: 1.0.1
+- Datasets: 3.0.1
+- Tokenizers: 0.20.1
 
 ## Citation
 
@@ -1087,7 +1088,7 @@ You can finetune this model on your own dataset.
 #### MatryoshkaLoss
 ```bibtex
 @misc{kusupati2024matryoshka,
-    title={Matryoshka Representation Learning}, 
+    title={Matryoshka Representation Learning},
     author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
     year={2024},
     eprint={2205.13147},
@@ -1099,7 +1100,7 @@ You can finetune this model on your own dataset.
 #### MultipleNegativesRankingLoss
 ```bibtex
 @misc{henderson2017efficient,
-    title={Efficient Natural Language Response Suggestion for Smart Reply}, 
+    title={Efficient Natural Language Response Suggestion for Smart Reply},
     author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
     year={2017},
     eprint={1705.00652},

config.json

@@ -19,7 +19,7 @@
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
-  "transformers_version": "4.44.0",
+  "transformers_version": "4.45.2",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 30522

config_sentence_transformers.json

@@ -1,8 +1,8 @@
 {
   "__version__": {
-    "sentence_transformers": "3.0.1",
-    "transformers": "4.44.0",
-    "pytorch": "2.5.1"
+    "sentence_transformers": "3.2.0",
+    "transformers": "4.45.2",
+    "pytorch": "2.5.0+cu124"
   },
   "prompts": {
     "query": "Represent this sentence for searching relevant passages: "