Upload folder using huggingface_hub

README.md

@@ -4,48 +4,50 @@ tags:
 - sentence-similarity
 - feature-extraction
 - generated_from_trainer
-- dataset_size:1798
+- dataset_size:1954
 - loss:MultipleNegativesRankingLoss
 base_model: BAAI/bge-small-en-v1.5
 widget:
-- source_sentence: How will the NIKKEI 225 affect my portfolio
+- source_sentence: 'how much will my portfolio return '
   sentences:
-  - '[{"get_portfolio(None,True,None)": "portfolio"}, {"stress_test(''portfolio'',''nikkei_225'',None,''up'')":
-    "stress_test"}]'
-  - '[{"get_portfolio(None,True,None)": "portfolio"}, {"get_attribute(''portfolio'',[''dividend
-    yield''],''<DATES>'')": "portfolio"}, {"calculate(''portfolio'',[''dividend yield'',
-    ''marketValue''],''multiply'',''div_income'')": "portfolio"}, {"sort(''portfolio'',''div_income'',''desc'')":
-    "portfolio"}]'
-  - '[{"get_portfolio(None,True,None)": "portfolio"}, {"stress_test(''portfolio'',''nikkei_225'',None,None)":
-    "stress_test"}]'
-- source_sentence: What’s the [DATES] trend of the [A_SECTOR] sector
-  sentences:
-  - '[{"get_portfolio(None,True,None)": "portfolio"}, {"get_attribute(''portfolio'',[''<A_THEME>'',
-    ''risk''],''<DATES>'')": "portfolio"}, {"filter(''portfolio'',''<A_THEME>'',''>'',''0.01'')":
-    "portfolio"}, {"sort(''portfolio'',''risk'',''asc'')": "portfolio"}]'
-  - '[{"get_attribute([''<A_SECTOR>''],[''returns''],''<DATES>'')":"sector_returns"}]'
+  - '[{"get_portfolio(None,True,None)": "portfolio"}, {"get_expected_attribute(''portfolio'',[''returns''])":
+    "portfolio"}, {"sort(''portfolio'',''returns'',''asc'')": "portfolio"}]'
+  - '[{"get_portfolio(None,True,None)": "portfolio"}, {"get_expected_attribute(''portfolio'',[''returns''])":
+    "portfolio"}, {"sort(''portfolio'',''returns'',''desc'')": "portfolio"}]'
   - '[{"get_news_articles(None,None,[''<A_SECTOR>''],''<DATES>'')": "news_data"}]'
-- source_sentence: How will rising gold commodities affect my portfolio
+- source_sentence: What does the latest consumer sentiment survey mean for my investments
   sentences:
-  - '[{"get_attribute([''<TICKER>''],[''returns''],''<DATES>'')":"<TICKER>_returns"}]'
-  - '[{"get_portfolio(None,True,None)": "portfolio"}, {"stress_test(''portfolio'',''gold'',None,None)":
+  - '[{"get_portfolio(None,True,None)": "portfolio"}, {"stress_test(''portfolio'',''consumer_sentiment'',None,''up'')":
     "stress_test"}]'
-  - '[{"get_portfolio(None,True,None)": "portfolio"}, {"stress_test(''portfolio'',''gold'',None,''up'')":
+  - '[{"get_portfolio([''type''],True,None)": "portfolio"}, {"filter(''portfolio'',''type'',''=='',''MF'')":
+    "portfolio"}, {"get_attribute(''portfolio'',[''gains''],''<DATES>'')": "portfolio"},
+    {"filter(''portfolio'',''gains'',''>'',''0'')": "portfolio"}, {"sort(''portfolio'',''gains'',''desc'')":
+    "portfolio"}]'
+  - '[{"get_portfolio(None,True,None)": "portfolio"}, {"stress_test(''portfolio'',''consumer_sentiment'',None,None)":
     "stress_test"}]'
-- source_sentence: what percent of my account is in [AN_ASSET_TYPE]
+- source_sentence: Which of my holdings have the highest expected risk
   sentences:
+  - '[{"get_portfolio(None,True,None)": "portfolio"}, {"get_expected_attribute(''portfolio'',[''volatility''])":
+    "portfolio"}, {"sort(''portfolio'',''volatility'',''desc'')": "portfolio"}]'
   - '[{"get_portfolio(None,True,None)": "portfolio"}, {"factor_contribution(''portfolio'',''<DATES>'',''asset_class'',''<AN_ASSET_TYPE>'',''portfolio'')":
     "portfolio"}]'
+  - '[{"get_portfolio(None,True,None)": "portfolio"}, {"get_expected_attribute(''portfolio'',[''volatility''])":
+    "portfolio"}, {"sort(''portfolio'',''volatility'',''asc'')": "portfolio"}]'
+- source_sentence: how is [TICKER] allocated by region
+  sentences:
   - '[{"get_news_articles(None,None,[''<A_SECTOR>''],''<DATES>'')": "news_data"}]'
-  - '[{"get_attribute([''<TICKER>''],[''<AN_ASSET_TYPE>''],''<DATES>'')":"<TICKER>_data"}]'
-- source_sentence: Can I get a performance check-in
+  - '[{"get_attribute([''<TICKER>''],[''region''],''<DATES>'')":"<TICKER>_data"}]'
+  - '[{"get_portfolio(None,True,None)": "portfolio"}, {"factor_contribution(''portfolio'',''<DATES>'',''region'',None,''portfolio'')":
+    "portfolio"}]'
+- source_sentence: what sectors are contributing the most to my performance [DATES]
   sentences:
-  - '[{"search(''query'', ''match_type'', ''<TICKER>'')": "search_results"},{"compare([[''<TICKER>''],''search_results''],
-    [''yield''], None)": "comparison_data"}]'
-  - '[{"get_portfolio(None, True, None)": "portfolio"}, {"get_attribute(''portfolio'',[''gains''],''<DATES>'')":
-    "portfolio"}, {"sort(''portfolio'',''gains'',''desc'')": "portfolio"}]'
-  - '[{"get_portfolio(None,True,None)": "portfolio"},{"factor_contribution(''portfolio'',''<DATES>'',''security'',''<TICKER>'',''returns'')}":
-    "portfolio"}, {"get_attribute([''<TICKER>''],[''returns''],''<DATES>'')": "returns_<TICKER>"}]'
+  - '[{"get_portfolio(None,True,None)": "portfolio"}, {"get_attribute(''portfolio'',[''losses''],''<DATES>'')":
+    "portfolio"}, {"filter(''portfolio'',''losses'',''<'',''0'')": "portfolio"}, {"sort(''portfolio'',''losses'',''asc'')":
+    "portfolio"}]'
+  - '[{"get_portfolio(None,True,None)": "portfolio"}, {"factor_contribution(''portfolio'',''<DATES>'',''sector'',None,''returns'')":
+    "portfolio"}]'
+  - '[{"get_portfolio(None,True,None)": "portfolio"}, {"factor_contribution(''portfolio'',''<DATES>'',''sector'',None,''portfolio'')":
+    "portfolio"}]'
 pipeline_tag: sentence-similarity
 library_name: sentence-transformers
 ---
@@ -100,9 +102,9 @@ from sentence_transformers import SentenceTransformer
 model = SentenceTransformer("sentence_transformers_model_id")
 # Run inference
 sentences = [
-    'Can I get a performance check-in',
-    '[{"get_portfolio(None, True, None)": "portfolio"}, {"get_attribute(\'portfolio\',[\'gains\'],\'<DATES>\')": "portfolio"}, {"sort(\'portfolio\',\'gains\',\'desc\')": "portfolio"}]',
-    '[{"get_portfolio(None,True,None)": "portfolio"},{"factor_contribution(\'portfolio\',\'<DATES>\',\'security\',\'<TICKER>\',\'returns\')}": "portfolio"}, {"get_attribute([\'<TICKER>\'],[\'returns\'],\'<DATES>\')": "returns_<TICKER>"}]',
+    'what sectors are contributing the most to my performance [DATES]',
+    '[{"get_portfolio(None,True,None)": "portfolio"}, {"factor_contribution(\'portfolio\',\'<DATES>\',\'sector\',None,\'returns\')": "portfolio"}]',
+    '[{"get_portfolio(None,True,None)": "portfolio"}, {"factor_contribution(\'portfolio\',\'<DATES>\',\'sector\',None,\'portfolio\')": "portfolio"}]',
 ]
 embeddings = model.encode(sentences)
 print(embeddings.shape)
@@ -156,19 +158,19 @@ You can finetune this model on your own dataset.
 
 #### Unnamed Dataset
 
-* Size: 1,798 training samples
+* Size: 1,954 training samples
 * Columns: <code>sentence_0</code>, <code>sentence_1</code>, and <code>sentence_2</code>
 * Approximate statistics based on the first 1000 samples:
   |         | sentence_0                                                                        | sentence_1                                                                          | sentence_2                                                                          |
   |:--------|:----------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|
   | type    | string                                                                            | string                                                                              | string                                                                              |
-  | details | <ul><li>min: 4 tokens</li><li>mean: 12.37 tokens</li><li>max: 32 tokens</li></ul> | <ul><li>min: 20 tokens</li><li>mean: 71.59 tokens</li><li>max: 206 tokens</li></ul> | <ul><li>min: 20 tokens</li><li>mean: 73.42 tokens</li><li>max: 229 tokens</li></ul> |
+  | details | <ul><li>min: 4 tokens</li><li>mean: 12.37 tokens</li><li>max: 32 tokens</li></ul> | <ul><li>min: 20 tokens</li><li>mean: 72.43 tokens</li><li>max: 229 tokens</li></ul> | <ul><li>min: 20 tokens</li><li>mean: 70.45 tokens</li><li>max: 229 tokens</li></ul> |
 * Samples:
-  | sentence_0                                                                                         | sentence_1                                                                                                                                                   | sentence_2                                                                                                                                                   |
-  |:---------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------|
-  | <code>How could changes in the emerging markets index (IEMG) affect my investment portfolio</code> | <code>[{"get_portfolio(None,True,None)": "portfolio"}, {"stress_test('portfolio','iemg',None,None)": "stress_test"}]</code>                                  | <code>[{"get_portfolio(None,True,None)": "portfolio"}, {"stress_test('portfolio','iemg',None,'up')": "stress_test"}]</code>                                  |
-  | <code>What role has the volatility factor played in my overall returns</code>                      | <code>[{"get_portfolio(None,True,None)": "portfolio"}, {"factor_contribution('portfolio','<DATES>','factor','volatility','returns')": "portfolio"}]</code>   | <code>[{"get_portfolio(None,True,None)": "portfolio"}, {"factor_contribution('portfolio','<DATES>','factor','volatility','portfolio')": "portfolio"}]</code> |
-  | <code>Is my portfolio overexposed to [A_REGION] country exposure</code>                            | <code>[{"get_portfolio(None,True,None)": "portfolio"}, {"factor_contribution('portfolio','<DATES>','region','<A_REGION>','portfolio')": "portfolio"}]</code> | <code>[{"get_portfolio(None,True,None)": "portfolio"}, {"factor_contribution('portfolio','<DATES>','theme','<A_THEME>','portfolio')": "portfolio"}]</code>   |
+  | sentence_0                                       | sentence_1                                                                                                                                                                                                                                                                       | sentence_2                                                                                                                                                   |
+  |:-------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>show my holdings</code>                    | <code>[{"get_portfolio(['marketValue'],True,None)": "portfolio"}, {"aggregate('portfolio','ticker','marketValue','sum',None)": "total_value"}]</code>                                                                                                                            | <code>[{"get_portfolio(['marketValue'],True,None)": "portfolio"}]</code>                                                                                     |
+  | <code>[TICKER] news update</code>                | <code>[{"get_portfolio(None,False,None)": "portfolio"}, {"filter('portfolio','ticker','==','<TICKER>')": "portfolio"}, {"get_news_articles(['<TICKER>'],None,None,None)": "news_data"}, {"newsletter_search(None,['<TICKER>'],'query',None,False)": "newsletter_chunks"}]</code> | <code>[{"get_attribute(['<TICKER>'],['returns'],'<DATES>')":"<TICKER>_returns"},{"get_news_articles(['<TICKER>'],None,None,'<DATES>')": "news_data"}]</code> |
+  | <code>did [TICKER] outperform the market?</code> | <code>[{"compare([['<TICKER>', 'SPY']], None, None)": "comparison_data"}]</code>                                                                                                                                                                                                 | <code>[{"get_attribute(['<TICKER>'],['returns'],'<DATES>')":"<TICKER>_returns"},{"get_news_articles(['<TICKER>'],None,None,'<DATES>')": "news_data"}]</code> |
 * Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
   ```json
   {
@@ -310,7 +312,7 @@ You can finetune this model on your own dataset.
 ### Training Logs
 | Epoch  | Step | Training Loss |
 |:------:|:----:|:-------------:|
-| 8.7719 | 500  | 0.6004        |
+| 8.0645 | 500  | 0.6267        |
 
 
 ### Framework Versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2585cc9ff5be06fa69a58d4149bce73f6c6dba07988d6704381ca61ff41ea514
+oid sha256:324003e94c0004a860bc5b97e45568070214b9f1821e9d117d865a46487eeaae
 size 133462128