Hugging Face's logo

redis
/
langcache-embed-v3

Sentence Similarity
sentence-transformers
Safetensors
English
modernbert
biencoder
text-classification
sentence-pair-classification
semantic-similarity
semantic-search
retrieval
reranking
Generated from Trainer
dataset_size:1451941
loss:MultipleNegativesRankingLoss
Eval Results
text-embeddings-inference
Model card Files
xet
Community
radoslavralev commited on
Commit
b274ed8
·
verified ·
1 Parent(s): 803a52b

Add new SentenceTransformer model

Browse files
Files changed (2) hide show
  1. README.md +42 -52
  2. model.safetensors +1 -1
README.md CHANGED
@@ -68,48 +68,40 @@ datasets:
68
  pipeline_tag: sentence-similarity
69
  library_name: sentence-transformers
70
  metrics:
71
- - cosine_accuracy
72
- - cosine_accuracy_threshold
73
- - cosine_f1
74
- - cosine_f1_threshold
75
- - cosine_precision
76
- - cosine_recall
77
- - cosine_ap
78
- - cosine_mcc
79
  model-index:
80
  - name: Redis fine-tuned BiEncoder model for semantic caching on LangCache
81
  results:
82
  - task:
83
- type: binary-classification
84
- name: Binary Classification
85
  dataset:
86
- name: test
87
- type: test
88
  metrics:
89
- - type: cosine_accuracy
90
- value: 0.7037777526966672
91
- name: Cosine Accuracy
92
- - type: cosine_accuracy_threshold
93
- value: 0.8524033427238464
94
- name: Cosine Accuracy Threshold
95
- - type: cosine_f1
96
- value: 0.7122170715871171
97
- name: Cosine F1
98
- - type: cosine_f1_threshold
99
- value: 0.8118724822998047
100
- name: Cosine F1 Threshold
101
- - type: cosine_precision
102
- value: 0.5989283084033827
103
- name: Cosine Precision
104
- - type: cosine_recall
105
- value: 0.8783612662942272
106
- name: Cosine Recall
107
- - type: cosine_ap
108
- value: 0.6476617871668658
109
- name: Cosine Ap
110
- - type: cosine_mcc
111
- value: 0.44182914870985407
112
- name: Cosine Mcc
113
  ---
114
 
115
  # Redis fine-tuned BiEncoder model for semantic caching on LangCache
@@ -206,21 +198,19 @@ You can finetune this model on your own dataset.
206
 
207
  ### Metrics
208
 
209
- #### Binary Classification
210
 
211
- * Dataset: `test`
212
- * Evaluated with [<code>BinaryClassificationEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.BinaryClassificationEvaluator)
213
 
214
- | Metric | Value |
215
- |:--------------------------|:-----------|
216
- | cosine_accuracy | 0.7038 |
217
- | cosine_accuracy_threshold | 0.8524 |
218
- | cosine_f1 | 0.7122 |
219
- | cosine_f1_threshold | 0.8119 |
220
- | cosine_precision | 0.5989 |
221
- | cosine_recall | 0.8784 |
222
- | **cosine_ap** | **0.6477** |
223
- | cosine_mcc | 0.4418 |
224
 
225
  <!--
226
  ## Bias, Risks and Limitations
@@ -293,9 +283,9 @@ You can finetune this model on your own dataset.
293
  ```
294
 
295
  ### Training Logs
296
- | Epoch | Step | test_cosine_ap |
297
- |:-----:|:----:|:--------------:|
298
- | -1 | -1 | 0.6477 |
299
 
300
 
301
  ### Framework Versions
 
68
  pipeline_tag: sentence-similarity
69
  library_name: sentence-transformers
70
  metrics:
71
+ - cosine_accuracy@1
72
+ - cosine_precision@1
73
+ - cosine_recall@1
74
+ - cosine_ndcg@10
75
+ - cosine_mrr@1
76
+ - cosine_map@100
 
 
77
  model-index:
78
  - name: Redis fine-tuned BiEncoder model for semantic caching on LangCache
79
  results:
80
  - task:
81
+ type: information-retrieval
82
+ name: Information Retrieval
83
  dataset:
84
+ name: train
85
+ type: train
86
  metrics:
87
+ - type: cosine_accuracy@1
88
+ value: 0.5579995670058454
89
+ name: Cosine Accuracy@1
90
+ - type: cosine_precision@1
91
+ value: 0.5579995670058454
92
+ name: Cosine Precision@1
93
+ - type: cosine_recall@1
94
+ value: 0.5359686891852944
95
+ name: Cosine Recall@1
96
+ - type: cosine_ndcg@10
97
+ value: 0.7524082716425572
98
+ name: Cosine Ndcg@10
99
+ - type: cosine_mrr@1
100
+ value: 0.5579995670058454
101
+ name: Cosine Mrr@1
102
+ - type: cosine_map@100
103
+ value: 0.6975777745051742
104
+ name: Cosine Map@100
 
 
 
 
 
 
105
  ---
106
 
107
  # Redis fine-tuned BiEncoder model for semantic caching on LangCache
 
198
 
199
  ### Metrics
200
 
201
+ #### Information Retrieval
202
 
203
+ * Dataset: `train`
204
+ * Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
205
 
206
+ | Metric | Value |
207
+ |:-------------------|:-----------|
208
+ | cosine_accuracy@1 | 0.558 |
209
+ | cosine_precision@1 | 0.558 |
210
+ | cosine_recall@1 | 0.536 |
211
+ | **cosine_ndcg@10** | **0.7524** |
212
+ | cosine_mrr@1 | 0.558 |
213
+ | cosine_map@100 | 0.6976 |
 
 
214
 
215
  <!--
216
  ## Bias, Risks and Limitations
 
283
  ```
284
 
285
  ### Training Logs
286
+ | Epoch | Step | train_cosine_ndcg@10 |
287
+ |:-----:|:----:|:--------------------:|
288
+ | -1 | -1 | 0.7524 |
289
 
290
 
291
  ### Framework Versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2ddcc1fdf3ad6a01faff3bf6e2fe8ca23c8602a61631a3dc2c2751c33fb9619d
3
  size 298041696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95d02211c4cca89113f9f3e93ed91f5176bf50170faa2cb835f7bfea15bb9dd2
3
  size 298041696