Upload fine-tuned chart reranker model
Browse files- README.md +68 -60
- eval/CrossEncoderCorrelationEvaluator_validation_results.csv +5 -5
- model.safetensors +1 -1
- training_info.txt +1 -1
README.md
CHANGED
|
@@ -4,7 +4,7 @@ tags:
|
|
| 4 |
- cross-encoder
|
| 5 |
- reranker
|
| 6 |
- generated_from_trainer
|
| 7 |
-
- dataset_size:
|
| 8 |
- loss:BinaryCrossEntropyLoss
|
| 9 |
base_model: Alibaba-NLP/gte-multilingual-reranker-base
|
| 10 |
pipeline_tag: text-ranking
|
|
@@ -23,10 +23,10 @@ model-index:
|
|
| 23 |
type: validation
|
| 24 |
metrics:
|
| 25 |
- type: pearson
|
| 26 |
-
value: 0.
|
| 27 |
name: Pearson
|
| 28 |
- type: spearman
|
| 29 |
-
value: 0.
|
| 30 |
name: Spearman
|
| 31 |
---
|
| 32 |
|
|
@@ -70,11 +70,11 @@ from sentence_transformers import CrossEncoder
|
|
| 70 |
model = CrossEncoder("cross_encoder_model_id")
|
| 71 |
# Get scores for pairs of texts
|
| 72 |
pairs = [
|
| 73 |
-
[
|
| 74 |
-
['
|
| 75 |
-
['
|
| 76 |
-
['
|
| 77 |
-
['
|
| 78 |
]
|
| 79 |
scores = model.predict(pairs)
|
| 80 |
print(scores.shape)
|
|
@@ -82,13 +82,13 @@ print(scores.shape)
|
|
| 82 |
|
| 83 |
# Or rank different texts based on similarity to a single text
|
| 84 |
ranks = model.rank(
|
| 85 |
-
|
| 86 |
[
|
| 87 |
-
'Title: "
|
| 88 |
-
'Title: "
|
| 89 |
-
'Title: "
|
| 90 |
-
'Title: "
|
| 91 |
-
'Title: "
|
| 92 |
]
|
| 93 |
)
|
| 94 |
# [{'corpus_id': ..., 'score': ...}, {'corpus_id': ..., 'score': ...}, ...]
|
|
@@ -129,8 +129,8 @@ You can finetune this model on your own dataset.
|
|
| 129 |
|
| 130 |
| Metric | Value |
|
| 131 |
|:-------------|:-----------|
|
| 132 |
-
| pearson | 0.
|
| 133 |
-
| **spearman** | **0.
|
| 134 |
|
| 135 |
<!--
|
| 136 |
## Bias, Risks and Limitations
|
|
@@ -150,19 +150,19 @@ You can finetune this model on your own dataset.
|
|
| 150 |
|
| 151 |
#### Unnamed Dataset
|
| 152 |
|
| 153 |
-
* Size:
|
| 154 |
* Columns: <code>sentence_0</code>, <code>sentence_1</code>, and <code>label</code>
|
| 155 |
* Approximate statistics based on the first 1000 samples:
|
| 156 |
-
| | sentence_0
|
| 157 |
-
|
| 158 |
-
| type | string
|
| 159 |
-
| details | <ul><li>min:
|
| 160 |
* Samples:
|
| 161 |
-
| sentence_0
|
| 162 |
-
|
| 163 |
-
| <code>
|
| 164 |
-
| <code>
|
| 165 |
-
| <code
|
| 166 |
* Loss: [<code>BinaryCrossEntropyLoss</code>](https://sbert.net/docs/package_reference/cross_encoder/losses.html#binarycrossentropyloss) with these parameters:
|
| 167 |
```json
|
| 168 |
{
|
|
@@ -308,40 +308,48 @@ You can finetune this model on your own dataset.
|
|
| 308 |
### Training Logs
|
| 309 |
| Epoch | Step | Training Loss | validation_spearman |
|
| 310 |
|:------:|:----:|:-------------:|:-------------------:|
|
| 311 |
-
| 0.
|
| 312 |
-
| 0.
|
| 313 |
-
| 0.
|
| 314 |
-
| 0.
|
| 315 |
-
| 0.
|
| 316 |
-
| 0.
|
| 317 |
-
|
|
| 318 |
-
|
|
| 319 |
-
| 1.
|
| 320 |
-
| 1.
|
| 321 |
-
| 1.
|
| 322 |
-
| 1.
|
| 323 |
-
| 1.
|
| 324 |
-
|
|
| 325 |
-
|
|
| 326 |
-
|
|
| 327 |
-
|
|
| 328 |
-
|
|
| 329 |
-
| 2.
|
| 330 |
-
| 2.
|
| 331 |
-
| 2.
|
| 332 |
-
|
|
| 333 |
-
|
|
| 334 |
-
|
|
| 335 |
-
|
|
| 336 |
-
|
|
| 337 |
-
|
|
| 338 |
-
|
|
| 339 |
-
|
|
| 340 |
-
|
|
| 341 |
-
|
|
| 342 |
-
|
|
| 343 |
-
|
|
| 344 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 345 |
|
| 346 |
|
| 347 |
### Framework Versions
|
|
|
|
| 4 |
- cross-encoder
|
| 5 |
- reranker
|
| 6 |
- generated_from_trainer
|
| 7 |
+
- dataset_size:27981
|
| 8 |
- loss:BinaryCrossEntropyLoss
|
| 9 |
base_model: Alibaba-NLP/gte-multilingual-reranker-base
|
| 10 |
pipeline_tag: text-ranking
|
|
|
|
| 23 |
type: validation
|
| 24 |
metrics:
|
| 25 |
- type: pearson
|
| 26 |
+
value: 0.8683862942248027
|
| 27 |
name: Pearson
|
| 28 |
- type: spearman
|
| 29 |
+
value: 0.8672220121041904
|
| 30 |
name: Spearman
|
| 31 |
---
|
| 32 |
|
|
|
|
| 70 |
model = CrossEncoder("cross_encoder_model_id")
|
| 71 |
# Get scores for pairs of texts
|
| 72 |
pairs = [
|
| 73 |
+
["How has Kody Clemens' batting performance changed over the last few seasons?", 'Title: "Kody Clemens"\nCollections: MLB\nDatasets: BaseballPlayers\nChart Type: athlete:baseball'],
|
| 74 |
+
['What amount of accrued liabilities does Walmart have?', 'Title: "Walmart Balance Sheet"\nCollections: Companies\nChart Type: company:finance\nCanonical forms: "Walmart"="Walmart Inc.", "Balance Sheet"="Financials Overview"\nSources: S&P Global'],
|
| 75 |
+
['์ด ์ฑ์ฅ ์ ๋ต์ ์ธ๊ณํ์ ํ๊ณต์
ํ ์์์ ์ ํต์ ์ ์กฐ์
๋ณดํธ์ ์ด์ ์ ๋ง์ถ๋ฉฐ, ์ด๋ ํด๋น ๋ถ๋ฌธ\n์ ํ์ง๊ณผ ์์ฐ์ฑ์ ์ ์งํ๋ฉด์ ๊ฐ๊ฒฉ์ ๋ฎ๊ฒ ์ ์งํด์ผ ํจ์ ์๊ตฌํ๋ค. ํต์ฌ์ ์๊ธ ์ ์ ๋ฅผ ํตํ\n๋
ธ๋ ๋น์ฉ ํต์ ์ ์๋ค(Johnston, ๋ณธ ์ฑ
). ์ธ๋ถ ์์๊ฐ ๋ด์ ๋ถ์กฑ์ ์์ํ๋ ํ, ์๊ธ ์ ์ ๋ ์ฑ\n์ฅ์ ์ ํดํ์ง ์๋๋ค.\n์๊ธ ์ ์ ์ ์ ์กฐ์
๋
ธ๋์ ์ง์ ๋ณด์กด์ ๋
ธ๋์์ฅ ๋ด๋ถ์ ๋ณดํธ, ํฌ์ ๋ฐ ๊ธฐ์ ๊ด๋ จ ์ ์กฐ์
๋
ธ\n์กฐ์์ ๊ธด๋ฐํ ํ๋ ฅ, ๊ทธ๋ฆฌ๊ณ ์ถ๊ฐ ๊ต์ก ๋๋ ํ์๊ต์ก ๊ธฐ๊ด๊ณผ์ ์ฐ๊ณ๋ก ๊ธฐ์ ํฅ์์ ํตํด ๋ฌ์ฑ\n๋๋ค. ์ ์กฐ์
ํต์ฌ ๊ทผ๋ก์๋ค์ ์๊ธ ์ต์ ์ ๊ธฐ์
๋ด ์ง๋ฌด ๋ณ๊ฒฝ ์ํฅ ๋๋ ๊ทผ๋ก ์๊ฐ ๋ณ๋๊ณผ ๊ฐ์\n๋ด๋ถ ์ ์ฐ์ฑ์ ๋๊ฐ๋ก ๊ณ ์ฉ ๋ณดํธ๋ฅผ ์ฝ์๋ฐ๋๋ค. ๊ณต์ฅ ๋จ์ ๋
ธ๋ ๋ํ๋ค์ ๋จ๊ธฐ ์๊ธ ์ธ์๋ณด๋ค\n์ฅ๊ธฐ ํฌ์์ ๊ณ ์ฉ ์์ ์ ์ ํธํ๋ฏ๋ก, ์ง์ญ ๊ณต์ฅ ๋จ์ ํ์ฝ์ด ๋์ ๋์ด ๋
ธ์กฐ์ ์๊ธ ์ต์ ๋ผ๋\n๋ถ๋ฌธ๋ณ ์ ์ฑ
์ ํ์ฑํ๋ค.\n์์ถ ์ญ๋์ด ์ด ์ ๋ต์ ํต์ฌ์ด๋ฏ๋ก ์ค์ง ํ์จ์ด ์ค๋ํ ๊ด์ฌ์ฌ์ด๋ค. ์ฌ์ ยทํตํ ์ ์ฑ
์ํ๋\n์๊ธ ์ธ์ ๋ฑ ์ค์ง ํ์จ์ ๋ถ์ ์ ์ํฅ์ ๋ฏธ์น ์ ์๋ ์ ์ฑ
๋ค์ ์ ๋์ ยท์ ์น์ ์ผ๋ก ์ต์ ๋๋ค.\n์ด๋ฌํ ์ ์ฑ
๋์์ ๊ต์ก ๋ฐ ๋ณด์ก์ ๋ํ ์ฌ์ ์ง์ถ๋ฟ๋ง ์๋๋ผ ๋
ธ๋ ์์ฅ ์ ์ฑ
์๋ ํ๊ธ ํจ๊ณผ\n๋ฅผ ๋ฏธ์น๋ค.\n์์ ์๊ทน์ด ๋ถ๊ฐ๋ฅํ ์ํฉ์์, ์ต์ ์๊ธ์ ๋ฎ์ถ๊ธฐ ์ํ ๊ณต๊ธ ์ธก๋ฉด์ ์กฐ์น๊ฐ ๋์
๋๋ค. ์ด\n์ ๋ต์ ๋ํ ๊ตญ๋ด ์๋น์ค๋ฅผ ์ ๋ ดํ๊ฒ ๋ง๋๋ ์ ๋ ดํ๊ณ ์ ์ฐํ ์๋น์ค ๋ถ๋ฌธ์ ์ถํ์ ์์กดํ๋ค.\n๋ฐ๋ผ์ ์ด์คํ์ ๊ณต๊ธ ์ธก๋ฉด์ ๋
ธ๋ ์์ฅ ์ ์ฑ
์ ๊ฒฝ์ ์ ๋ฌธํ ํจํด์ ์ง์ ์ ์ผ๋ก ๊ธฐ์ฌํ๋ค\n(Palier and Thelen 2010; Hassel 2014). ๊ธฐ์
๋ค์ ์ฐ์
๊ตฌ์กฐ์กฐ์ ์ ํตํด ์์ฐ ๊ณผ์ ์ ์์ฐ์ฑ์ด\n๋ฎ์ ์๋น์ค ๋ถ๋ฌธ์ ๊ณ ์์ฐ์ฑ ์ ์กฐ ๋ถ๋ฌธ์์ ๋ถ๋ฆฌํด๋ธ๋ค. ์ด๋ฅผ ํตํด ๊ธฐ์
์ ๋ด๋ถ์ ์ผ๋ก ๋
ธ๋๋ ฅ\n์ ์ธ๋ถํํ๊ณ ๋
ธ๋ ์์ฅ ์ด์ํ๋ฅผ ํ์ฉํ๋ ์์ฅ ๊ท์น ๋ณํ๋ฅผ ๋์
ํ๋ค.', 'Title: "South Korea Exports"\nCollections: World Bank Indicators\nDatasets: WorldBankIndicatorsData\nChart Type: timeseries:eav_v3\nCanonical forms: "Exports"="exports_of_goods_and_services"\nSources: The World Bank'],
|
| 76 |
+
['AYANEO Pocket Ace compact high-performance 2025', 'Title: "Mitsui High-tec Overview"\nCollections: Companies\nChart Type: company:finance\nCanonical forms: "Mitsui High-tec"="Mitsui High-tec, Inc.", "Overview"="Stock Overview"\nSources: S&P Global'],
|
| 77 |
+
['Traorรฉ 2024 trade exchanges China Senegal 2.5 billion 2019', 'Title: "Senegal Exports"\nCollections: World Bank Indicators\nDatasets: WorldBankIndicatorsData\nChart Type: timeseries:eav_v3\nCanonical forms: "Exports"="exports_of_goods_and_services"\nSources: The World Bank'],
|
| 78 |
]
|
| 79 |
scores = model.predict(pairs)
|
| 80 |
print(scores.shape)
|
|
|
|
| 82 |
|
| 83 |
# Or rank different texts based on similarity to a single text
|
| 84 |
ranks = model.rank(
|
| 85 |
+
"How has Kody Clemens' batting performance changed over the last few seasons?",
|
| 86 |
[
|
| 87 |
+
'Title: "Kody Clemens"\nCollections: MLB\nDatasets: BaseballPlayers\nChart Type: athlete:baseball',
|
| 88 |
+
'Title: "Walmart Balance Sheet"\nCollections: Companies\nChart Type: company:finance\nCanonical forms: "Walmart"="Walmart Inc.", "Balance Sheet"="Financials Overview"\nSources: S&P Global',
|
| 89 |
+
'Title: "South Korea Exports"\nCollections: World Bank Indicators\nDatasets: WorldBankIndicatorsData\nChart Type: timeseries:eav_v3\nCanonical forms: "Exports"="exports_of_goods_and_services"\nSources: The World Bank',
|
| 90 |
+
'Title: "Mitsui High-tec Overview"\nCollections: Companies\nChart Type: company:finance\nCanonical forms: "Mitsui High-tec"="Mitsui High-tec, Inc.", "Overview"="Stock Overview"\nSources: S&P Global',
|
| 91 |
+
'Title: "Senegal Exports"\nCollections: World Bank Indicators\nDatasets: WorldBankIndicatorsData\nChart Type: timeseries:eav_v3\nCanonical forms: "Exports"="exports_of_goods_and_services"\nSources: The World Bank',
|
| 92 |
]
|
| 93 |
)
|
| 94 |
# [{'corpus_id': ..., 'score': ...}, {'corpus_id': ..., 'score': ...}, ...]
|
|
|
|
| 129 |
|
| 130 |
| Metric | Value |
|
| 131 |
|:-------------|:-----------|
|
| 132 |
+
| pearson | 0.8684 |
|
| 133 |
+
| **spearman** | **0.8672** |
|
| 134 |
|
| 135 |
<!--
|
| 136 |
## Bias, Risks and Limitations
|
|
|
|
| 150 |
|
| 151 |
#### Unnamed Dataset
|
| 152 |
|
| 153 |
+
* Size: 27,981 training samples
|
| 154 |
* Columns: <code>sentence_0</code>, <code>sentence_1</code>, and <code>label</code>
|
| 155 |
* Approximate statistics based on the first 1000 samples:
|
| 156 |
+
| | sentence_0 | sentence_1 | label |
|
| 157 |
+
|:--------|:----------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------|:---------------------------------------------------------------|
|
| 158 |
+
| type | string | string | float |
|
| 159 |
+
| details | <ul><li>min: 6 characters</li><li>mean: 90.6 characters</li><li>max: 993 characters</li></ul> | <ul><li>min: 72 characters</li><li>mean: 172.97 characters</li><li>max: 458 characters</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.44</li><li>max: 1.0</li></ul> |
|
| 160 |
* Samples:
|
| 161 |
+
| sentence_0 | sentence_1 | label |
|
| 162 |
+
|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------|
|
| 163 |
+
| <code>How has Kody Clemens' batting performance changed over the last few seasons?</code> | <code>Title: "Kody Clemens"<br>Collections: MLB<br>Datasets: BaseballPlayers<br>Chart Type: athlete:baseball</code> | <code>1.0</code> |
|
| 164 |
+
| <code>What amount of accrued liabilities does Walmart have?</code> | <code>Title: "Walmart Balance Sheet"<br>Collections: Companies<br>Chart Type: company:finance<br>Canonical forms: "Walmart"="Walmart Inc.", "Balance Sheet"="Financials Overview"<br>Sources: S&P Global</code> | <code>0.75</code> |
|
| 165 |
+
| <code>์ด ์ฑ์ฅ ์ ๋ต์ ์ธ๊ณํ์ ํ๊ณต์
ํ ์์์ ์ ํต์ ์ ์กฐ์
๋ณดํธ์ ์ด์ ์ ๋ง์ถ๋ฉฐ, ์ด๋ ํด๋น ๋ถ๋ฌธ<br>์ ํ์ง๊ณผ ์์ฐ์ฑ์ ์ ์งํ๋ฉด์ ๊ฐ๊ฒฉ์ ๋ฎ๊ฒ ์ ์งํด์ผ ํจ์ ์๊ตฌํ๋ค. ํต์ฌ์ ์๊ธ ์ ์ ๋ฅผ ํตํ<br>๋
ธ๋ ๋น์ฉ ํต์ ์ ์๋ค(Johnston, ๋ณธ ์ฑ
). ์ธ๋ถ ์์๊ฐ ๋ด์ ๋ถ์กฑ์ ์์ํ๋ ํ, ์๊ธ ์ ์ ๋ ์ฑ<br>์ฅ์ ์ ํดํ์ง ์๋๋ค.<br>์๊ธ ์ ์ ์ ์ ์กฐ์
๋
ธ๋์ ์ง์ ๋ณด์กด์ ๋
ธ๋์์ฅ ๋ด๋ถ์ ๋ณดํธ, ํฌ์ ๋ฐ ๊ธฐ์ ๊ด๋ จ ์ ์กฐ์
๋
ธ<br>์กฐ์์ ๊ธด๋ฐํ ํ๋ ฅ, ๊ทธ๋ฆฌ๊ณ ์ถ๊ฐ ๊ต์ก ๋๋ ํ์๊ต์ก ๊ธฐ๊ด๊ณผ์ ์ฐ๊ณ๋ก ๊ธฐ์ ํฅ์์ ํตํด ๋ฌ์ฑ<br>๋๋ค. ์ ์กฐ์
ํต์ฌ ๊ทผ๋ก์๋ค์ ์๊ธ ์ต์ ์ ๊ธฐ์
๋ด ์ง๋ฌด ๋ณ๊ฒฝ ์ํฅ ๋๋ ๊ทผ๋ก ์๊ฐ ๋ณ๋๊ณผ ๊ฐ์<br>๋ด๋ถ ์ ์ฐ์ฑ์ ๋๊ฐ๋ก ๊ณ ์ฉ ๋ณดํธ๋ฅผ ์ฝ์๋ฐ๋๋ค. ๊ณต์ฅ ๋จ์ ๋
ธ๋ ๋ํ๋ค์ ๋จ๊ธฐ ์๊ธ ์ธ์๋ณด๋ค<br>์ฅ๊ธฐ ํฌ์์ ๊ณ ์ฉ ์์ ์ ์ ํธํ๋ฏ๋ก, ์ง์ญ ๊ณต์ฅ ๋จ์ ํ์ฝ์ด ๋์ ๋์ด ๋
ธ์กฐ์ ์๊ธ ์ต์ ๋ผ๋<br>๋ถ๋ฌธ๋ณ ์ ์ฑ
์ ํ์ฑํ๋ค.<br>์์ถ ์ญ๋์ด ์ด ์ ๋ต์ ํต์ฌ์ด๋ฏ๋ก ์ค์ง ํ์จ์ด ์ค๋ํ ๊ด์ฌ์ฌ์ด๋ค. ์ฌ์ ยทํตํ ์ ์ฑ
์ํ๋<br>์๊ธ ์ธ์ ๋ฑ ์ค์ง ํ์จ์ ๋ถ์ ์ ์ํฅ์ ๋ฏธ์น ์ ์๋ ์ ์ฑ
๋ค์ ์ ๋์ ยท์ ์น์ ์ผ๋ก ์ต์ ๋๋ค.<br>์ด๋ฌํ ์ ์ฑ
๋์์ ๊ต์ก ๋ฐ ๋ณด์ก์ ๋ํ ์ฌ์ ์ง์ถ๋ฟ๋ง ์๋๋ผ ๋
ธ๋ ์์ฅ ์ ์ฑ
์๋ ํ๊ธ ํจ๊ณผ<br>๋ฅผ ๋ฏธ์น๋ค.<br>์์ ์๊ทน์ด ๋ถ๊ฐ๋ฅํ ์ํฉ์์, ์ต์ ์๊ธ์ ๋ฎ์ถ๊ธฐ ์ํ ๊ณต๊ธ ์ธก๋ฉด์ ์กฐ์น๊ฐ ๋์
๋๋ค. ์ด<br>์ ๋ต์ ๋ํ ๊ตญ๋ด ์๋น์ค๋ฅผ ์ ๋ ดํ๊ฒ ๋ง๋๋ ์ ๋ ดํ๊ณ ์ ์ฐํ ์๋น์ค ๋ถ๋ฌธ์ ์ถํ์ ์์กดํ๋ค.<br>๋ฐ๋ผ์ ์ด์คํ์ ๊ณต๊ธ ์ธก๋ฉด์ ๋
ธ๋ ์์ฅ ์ ์ฑ
์ ๊ฒฝ์ ์ ๋ฌธํ ํจํด์ ์ง์ ์ ์ผ๋ก ๊ธฐ์ฌํ๋ค<br>(Palier and Thelen 2010; Hassel 2014). ๊ธฐ์
๋ค์ ์ฐ์
๊ตฌ์กฐ์กฐ์ ์ ํตํด ์์ฐ ๊ณผ์ ์ ์์ฐ์ฑ์ด<br>๋ฎ์ ์๋น์ค ๋ถ๋ฌธ์ ๊ณ ์์ฐ์ฑ ์ ์กฐ ๋ถ๋ฌธ์์ ๋ถ๋ฆฌํด๋ธ๋ค. ์ด๋ฅผ ํตํด ๊ธฐ์
์ ๋ด๋ถ์ ์ผ๋ก ๋
ธ๋๋ ฅ<br>์ ์ธ๋ถํํ๊ณ ๋
ธ๋ ์์ฅ ์ด์ํ๋ฅผ ํ์ฉํ๋ ์์ฅ ๊ท์น ๋ณํ๋ฅผ ๋์
ํ๋ค.</code> | <code>Title: "South Korea Exports"<br>Collections: World Bank Indicators<br>Datasets: WorldBankIndicatorsData<br>Chart Type: timeseries:eav_v3<br>Canonical forms: "Exports"="exports_of_goods_and_services"<br>Sources: The World Bank</code> | <code>0.75</code> |
|
| 166 |
* Loss: [<code>BinaryCrossEntropyLoss</code>](https://sbert.net/docs/package_reference/cross_encoder/losses.html#binarycrossentropyloss) with these parameters:
|
| 167 |
```json
|
| 168 |
{
|
|
|
|
| 308 |
### Training Logs
|
| 309 |
| Epoch | Step | Training Loss | validation_spearman |
|
| 310 |
|:------:|:----:|:-------------:|:-------------------:|
|
| 311 |
+
| 0.1143 | 100 | - | 0.7674 |
|
| 312 |
+
| 0.2286 | 200 | - | 0.8007 |
|
| 313 |
+
| 0.3429 | 300 | - | 0.8089 |
|
| 314 |
+
| 0.4571 | 400 | - | 0.8222 |
|
| 315 |
+
| 0.5714 | 500 | 0.4787 | 0.8286 |
|
| 316 |
+
| 0.6857 | 600 | - | 0.8312 |
|
| 317 |
+
| 0.8 | 700 | - | 0.8344 |
|
| 318 |
+
| 0.9143 | 800 | - | 0.8409 |
|
| 319 |
+
| 1.0 | 875 | - | 0.8459 |
|
| 320 |
+
| 1.0286 | 900 | - | 0.8440 |
|
| 321 |
+
| 1.1429 | 1000 | 0.4205 | 0.8414 |
|
| 322 |
+
| 1.2571 | 1100 | - | 0.8431 |
|
| 323 |
+
| 1.3714 | 1200 | - | 0.8549 |
|
| 324 |
+
| 1.4857 | 1300 | - | 0.8534 |
|
| 325 |
+
| 1.6 | 1400 | - | 0.8544 |
|
| 326 |
+
| 1.7143 | 1500 | 0.3894 | 0.8511 |
|
| 327 |
+
| 1.8286 | 1600 | - | 0.8575 |
|
| 328 |
+
| 1.9429 | 1700 | - | 0.8606 |
|
| 329 |
+
| 2.0 | 1750 | - | 0.8598 |
|
| 330 |
+
| 2.0571 | 1800 | - | 0.8613 |
|
| 331 |
+
| 2.1714 | 1900 | - | 0.8596 |
|
| 332 |
+
| 2.2857 | 2000 | 0.3693 | 0.8605 |
|
| 333 |
+
| 2.4 | 2100 | - | 0.8613 |
|
| 334 |
+
| 2.5143 | 2200 | - | 0.8621 |
|
| 335 |
+
| 2.6286 | 2300 | - | 0.8638 |
|
| 336 |
+
| 2.7429 | 2400 | - | 0.8632 |
|
| 337 |
+
| 2.8571 | 2500 | 0.3535 | 0.8630 |
|
| 338 |
+
| 2.9714 | 2600 | - | 0.8650 |
|
| 339 |
+
| 3.0 | 2625 | - | 0.8635 |
|
| 340 |
+
| 3.0857 | 2700 | - | 0.8642 |
|
| 341 |
+
| 3.2 | 2800 | - | 0.8662 |
|
| 342 |
+
| 3.3143 | 2900 | - | 0.8664 |
|
| 343 |
+
| 3.4286 | 3000 | 0.3375 | 0.8652 |
|
| 344 |
+
| 3.5429 | 3100 | - | 0.8642 |
|
| 345 |
+
| 3.6571 | 3200 | - | 0.8655 |
|
| 346 |
+
| 3.7714 | 3300 | - | 0.8645 |
|
| 347 |
+
| 3.8857 | 3400 | - | 0.8650 |
|
| 348 |
+
| 4.0 | 3500 | 0.3391 | 0.8662 |
|
| 349 |
+
| 4.1143 | 3600 | - | 0.8660 |
|
| 350 |
+
| 4.2286 | 3700 | - | 0.8654 |
|
| 351 |
+
| 4.3429 | 3800 | - | 0.8671 |
|
| 352 |
+
| 4.4571 | 3900 | - | 0.8672 |
|
| 353 |
|
| 354 |
|
| 355 |
### Framework Versions
|
eval/CrossEncoderCorrelationEvaluator_validation_results.csv
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
epoch,steps,Pearson_Correlation,Spearman_Correlation
|
| 2 |
-
1.0,
|
| 3 |
-
2.0,
|
| 4 |
-
3.0,
|
| 5 |
-
4.0,
|
| 6 |
-
5.0,
|
|
|
|
| 1 |
epoch,steps,Pearson_Correlation,Spearman_Correlation
|
| 2 |
+
1.0,875,0.8439432763505988,0.8458671064120614
|
| 3 |
+
2.0,1750,0.8620830630332061,0.8598071837330882
|
| 4 |
+
3.0,2625,0.8647110382297245,0.8634806082829799
|
| 5 |
+
4.0,3500,0.8657839457819247,0.8662180172158931
|
| 6 |
+
5.0,4375,0.8674826818176335,0.8663049346758942
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1223854204
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:114b68cfdf858f07524e1430e10da39644ef568a420e07c0adab488c8841daeb
|
| 3 |
size 1223854204
|
training_info.txt
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
Base Model: Alibaba-NLP/gte-multilingual-reranker-base
|
| 2 |
-
Training Samples:
|
| 3 |
Epochs: 5
|
| 4 |
Batch Size: 32
|
| 5 |
Learning Rate: 2e-05
|
|
|
|
| 1 |
Base Model: Alibaba-NLP/gte-multilingual-reranker-base
|
| 2 |
+
Training Samples: 27981
|
| 3 |
Epochs: 5
|
| 4 |
Batch Size: 32
|
| 5 |
Learning Rate: 2e-05
|