Updating model weights

README.md

@@ -7,7 +7,6 @@ tags:
 - generated_from_trainer
 - dataset_size:291522
 - loss:MultipleNegativesSymmetricRankingLoss
-base_model: sentence-transformers/all-MiniLM-L6-v2
 widget:
 - source_sentence: cream 21 baby oil with almond oil
   sentences:
@@ -41,7 +40,7 @@ library_name: sentence-transformers
 metrics:
 - cosine_accuracy
 model-index:
-- name: SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2
+- name: SentenceTransformer
   results:
   - task:
       type: triplet
@@ -51,19 +50,19 @@ model-index:
       type: unknown
     metrics:
     - type: cosine_accuracy
-      value: 0.9337190985679626
+      value: 0.9403471946716309
       name: Cosine Accuracy
 ---
 
-# SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2
+# SentenceTransformer
 
-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 trained. 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:** [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2) <!-- at revision c9745ed1d9f207416be6d2e6f8de32d1f16199bf -->
+<!-- - **Base model:** [Unknown](https://huggingface.co/unknown) -->
 - **Maximum Sequence Length:** 256 tokens
 - **Output Dimensionality:** 384 dimensions
 - **Similarity Function:** Cosine Similarity
@@ -116,9 +115,9 @@ print(embeddings.shape)
 # Get the similarity scores for the embeddings
 similarities = model.similarity(embeddings, embeddings)
 print(similarities)
-# tensor([[1.0000, 0.7955, 0.3891],
-#         [0.7955, 1.0000, 0.4118],
-#         [0.3891, 0.4118, 1.0000]])
+# tensor([[1.0000, 0.7730, 0.3475],
+#         [0.7730, 1.0000, 0.3615],
+#         [0.3475, 0.3615, 1.0000]])
 ```
 
 <!--
@@ -155,7 +154,7 @@ You can finetune this model on your own dataset.
 
 | Metric              | Value      |
 |:--------------------|:-----------|
-| **cosine_accuracy** | **0.9337** |
+| **cosine_accuracy** | **0.9403** |
 
 <!--
 ## Bias, Risks and Limitations
@@ -230,6 +229,7 @@ You can finetune this model on your own dataset.
 - `per_device_train_batch_size`: 256
 - `per_device_eval_batch_size`: 256
 - `weight_decay`: 0.001
+- `num_train_epochs`: 5
 - `warmup_steps`: 1138
 - `fp16`: True
 - `dataloader_num_workers`: 4
@@ -260,7 +260,7 @@ You can finetune this model on your own dataset.
 - `adam_beta2`: 0.999
 - `adam_epsilon`: 1e-08
 - `max_grad_norm`: 1.0
-- `num_train_epochs`: 3
+- `num_train_epochs`: 5
 - `max_steps`: -1
 - `lr_scheduler_type`: linear
 - `lr_scheduler_kwargs`: {}
@@ -364,13 +364,10 @@ You can finetune this model on your own dataset.
 </details>
 
 ### Training Logs
-| Epoch  | Step | Training Loss | Validation Loss | cosine_accuracy |
-|:------:|:----:|:-------------:|:---------------:|:---------------:|
-| -1     | -1   | -             | -               | 0.8861          |
-| 0.0009 | 1    | 5.8495        | -               | -               |
-| 1.0    | 1139 | 3.0136        | 0.8482          | 0.9113          |
-| 2.0    | 2278 | 2.2096        | 0.7465          | 0.9241          |
-| 3.0    | 3417 | 1.966         | 0.6980          | 0.9337          |
+| Epoch | Step | Training Loss | Validation Loss | cosine_accuracy |
+|:-----:|:----:|:-------------:|:---------------:|:---------------:|
+| 4.0   | 4556 | 1.8731        | 0.7003          | 0.9331          |
+| 5.0   | 5695 | 1.7998        | 0.6516          | 0.9403          |
 
 
 ### Framework Versions