Add new SentenceTransformer model

2_Dense/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc630dbae3594eeb0a6c8575cfa1de738bc5b246dffca9741b2d4f5851dd7989
+oid sha256:fe28270e57d9e8e90e8666418d902aa8ecb6254c77adda1949f6cbd4bdddb8c0
 size 2362528

3_Dense/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88ac9eb6f9310d3ee402976ca8daab484eaf9e3dfcdd22f7dc49d36f7e30ed38
+oid sha256:9a621984b96056acc53643d57acdce2f420d7dfe7a155ea8fcfd949064f4ff1f
 size 2362528

README.md

@@ -83,28 +83,28 @@ model-index:
       type: test
     metrics:
     - type: cosine_accuracy@1
-      value: 0.5880219631236443
+      value: 0.5880558568329718
       name: Cosine Accuracy@1
     - type: cosine_precision@1
-      value: 0.5880219631236443
+      value: 0.5880558568329718
       name: Cosine Precision@1
     - type: cosine_recall@1
-      value: 0.5706780985738924
+      value: 0.5707119922832199
       name: Cosine Recall@1
     - type: cosine_ndcg@10
-      value: 0.7717640552650085
+      value: 0.771771481653434
       name: Cosine Ndcg@10
     - type: cosine_mrr@1
-      value: 0.5880219631236443
+      value: 0.5880558568329718
       name: Cosine Mrr@1
     - type: cosine_map@100
-      value: 0.7213999116625115
+      value: 0.7214095423928245
       name: Cosine Map@100
     - type: cosine_auc_precision_cache_hit_ratio
-      value: 0.35292771304732773
+      value: 0.35287530778716975
       name: Cosine Auc Precision Cache Hit Ratio
     - type: cosine_auc_similarity_distribution
-      value: 0.1674589579463346
+      value: 0.16742922746173
       name: Cosine Auc Similarity Distribution
 ---
 
@@ -171,9 +171,9 @@ print(embeddings.shape)
 # Get the similarity scores for the embeddings
 similarities = model.similarity(embeddings, embeddings)
 print(similarities)
-# tensor([[1.0000, 1.0000, 0.5313],
-#         [1.0000, 1.0000, 0.5313],
-#         [0.5313, 0.5313, 1.0000]])
+# tensor([[0.9998, 0.9998, 0.5864],
+#         [0.9998, 0.9998, 0.5864],
+#         [0.5864, 0.5864, 1.0000]])
 ```
 
 <!--
@@ -211,14 +211,14 @@ You can finetune this model on your own dataset.
 
 | Metric                               | Value      |
 |:-------------------------------------|:-----------|
-| cosine_accuracy@1                    | 0.588      |
-| cosine_precision@1                   | 0.588      |
+| cosine_accuracy@1                    | 0.5881     |
+| cosine_precision@1                   | 0.5881     |
 | cosine_recall@1                      | 0.5707     |
 | **cosine_ndcg@10**                   | **0.7718** |
-| cosine_mrr@1                         | 0.588      |
+| cosine_mrr@1                         | 0.5881     |
 | cosine_map@100                       | 0.7214     |
 | cosine_auc_precision_cache_hit_ratio | 0.3529     |
-| cosine_auc_similarity_distribution   | 0.1675     |
+| cosine_auc_similarity_distribution   | 0.1674     |
 
 <!--
 ## Bias, Risks and Limitations
@@ -292,8 +292,8 @@ You can finetune this model on your own dataset.
 #### Non-Default Hyperparameters
 
 - `eval_strategy`: steps
-- `per_device_train_batch_size`: 300
-- `per_device_eval_batch_size`: 300
+- `per_device_train_batch_size`: 4096
+- `per_device_eval_batch_size`: 4096
 - `gradient_accumulation_steps`: 2
 - `weight_decay`: 0.001
 - `adam_beta2`: 0.98
@@ -319,8 +319,8 @@ You can finetune this model on your own dataset.
 - `do_predict`: False
 - `eval_strategy`: steps
 - `prediction_loss_only`: True
-- `per_device_train_batch_size`: 300
-- `per_device_eval_batch_size`: 300
+- `per_device_train_batch_size`: 4096
+- `per_device_eval_batch_size`: 4096
 - `per_gpu_train_batch_size`: None
 - `per_gpu_eval_batch_size`: None
 - `gradient_accumulation_steps`: 2
@@ -439,7 +439,7 @@ You can finetune this model on your own dataset.
 ### Training Logs
 | Epoch | Step | Validation Loss | test_cosine_ndcg@10 |
 |:-----:|:----:|:---------------:|:-------------------:|
-| 0     | 0    | 1.0850          | 0.7718              |
+| 0     | 0    | 1.4689          | 0.7718              |
 
 
 ### Framework Versions

config.json

@@ -12,7 +12,7 @@
   "cls_token_id": 50281,
   "decoder_bias": true,
   "deterministic_flash_attn": false,
-  "dtype": "bfloat16",
+  "dtype": "float32",
   "embedding_dropout": 0.0,
   "eos_token_id": 50282,
   "global_attn_every_n_layers": 3,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95d02211c4cca89113f9f3e93ed91f5176bf50170faa2cb835f7bfea15bb9dd2
-size 298041696
+oid sha256:04aa7437b7f98ed3f652e300c1d767d07c1864c10b3055ea63831997faefa8d6
+size 596070136