Downloads Β· 30 days
15
10% of all-time downloads
sept102/klue-roberta-base-clue-sts-mrc
klue-roberta-base-clue-sts-mrc is a sentence similarity model from sept102. Use it when you need a score for how close two texts are. It is set up for sentence-transformers.
This is a sentence-transformers model trained. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classificβ¦
Downloads Β· 30 days
15
10% of all-time downloads
All-time downloads
148
Public
Parameters
111M
885 MB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors442 MB Β· 100%
From the Hugging Face model README
This is a sentence-transformers model trained. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
SentenceTransformer(
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False, 'architecture': 'RobertaModel'})
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
)
First install the Sentence Transformers library:
pip install -U sentence-transformers
Then you can load this model and run inference.
from sentence_transformers import SentenceTransformer
# Download from the π€ Hub
model = SentenceTransformer("sentence_transformers_model_id")
# Run inference
sentences = [
'νμ 곡μ μμ μΆκ° λΉμ© λ°μμ΄ μμλλ μ€λΉλ₯Ό μ£Όλ¬Έν λλΌλ?',
'μΌμ±μ€κ³΅μ
μ΄ μ§λ 1λΆκΈ°μ λκ·λͺ¨ μ μλ₯Ό λλ€. ν΄μνλνΈ νλ‘μ νΈμ μ μ¬μ μμ€μ λλΉν΄ λκ·λͺ¨ μΆ©λΉκΈμ μμκΈ° λλ¬Έμ΄λ€. βΆλ³Έμ§ 4μ23μΌμ A13λ©΄ μ°Έμ‘° μΌμ±μ€κ³΅μ
μ 1λΆκΈ°μ λ§€μΆ 3μ‘°4311μ΅μ, μμ
μμ€ 3625μ΅μ, λΉκΈ°μμμ€ 2724μ΅μμ κΈ°λ‘νλ€κ³ 25μΌ κ³΅μνλ€. μλ
1λΆκΈ°μ 4402μ΅μμ μμ
μ΄μ΅κ³Ό 3005μ΅μμ λΉκΈ°μμ΄μ΅μ λλ κ²κ³Ό λΉκ΅νλ©΄ ν° νμΌλ‘ μ μμ ννλ€. λ§€μΆμ μ λ
λκΈ° λλΉ 11.7% κ°μνμ λΏμΈλ°λ μ΄μ΅μ΄ ν¬κ² μ€μ΄λ μ΄μ λ ν΄μνλνΈ νλ‘μ νΈ μμ€μ λλΉν΄ μ½ 5000μ΅μμ μΆ©λΉκΈμ μμκΈ° λλ¬Έμ΄λΌκ³ νμ¬ μΈ‘μ μ€λͺ
νλ€. μμ μ§λ 2μλΆν° μΌμ±μ€κ³΅μ
μ ν΄μνλνΈ νλ‘μ νΈμ κ΄λ ¨ν΄ κ²½μμ§λ¨μ μ§νν μΌμ±κ·Έλ£Ή 컨νΈλ‘€νμμΈ λ―Έλμ λ΅μ€μ λκ·λͺ¨ λΆμ€μ΄ μλ€κ³ νλ¨νκ³ μΆ©λΉκΈμ μλλ‘ νλ€. μΌμ±μ€κ³΅μ
κ΄κ³μλ β2012λ
μ μμ£Όν νΈμ£Ό μΈνμ€νλ‘μ νΈμ μ΅μμ€(Ichthys) ν΄μκ°μ€μ²λ¦¬μ€λΉ(CPF)μ μ§λν΄ μμ£Όν λμ΄μ§λ¦¬μ μμ§λ(Egina) λΆμ μ μμ°μ μ₯νμμ€λΉ(FPSO) λ± 2건μ ν΄μνλνΈ κ³΅μ¬μμ μμ€μ΄ μμλλ€βκ³ λ§νλ€. κ·Έλ βμΈνμ€νλ‘μ νΈμ CPFλ μμΈμ€κ³ λ± νμ 곡μ μμ μ¬μμ΄ λ°λλ©΄μ μμ
λ¬Όλκ³Ό λΉμ©μ΄ μ¦κ°νμΌλ©°, FPSOλ λμ΄μ§λ¦¬μ νμ§μμ μμ° λΉμ©μ΄ λμ΄λ κ²μΌλ‘ 보μΈλ€βκ³ λ§λΆμλ€. μΌμ±μ€κ³΅μ
μ 2건μ ν΄μνλνΈ νλ‘μ νΈ μΈμ λ€λ₯Έ νλ‘μ νΈλ μ μμ μΌλ‘ μ§νλκ³ μλ€κ³ λ°νλ€. νμ¬ κ΄κ³μλ βμμ μμ€μ 1λΆκΈ°μ λ°μν λ§νΌ 2λΆκΈ°λΆν°λ κ²½μ μ€μ μ΄ μ μ μμ€μΌλ‘ ν볡ν κ²βμ΄λΌκ³ λ΄λ€λ΄€λ€.μΌμ±μ€κ³΅μ
μ μ΄λ μ€μ μ λ§ κ³΅μλ₯Ό ν΅ν΄ μ¬ν΄ λ§€μΆμ΄ 14μ‘°6000μ΅μ, λ²μΈμΈ λΉμ© μ°¨κ° μ μμ΄μ΅μ΄ 2000μ΅μ μ λμΌ κ²μ΄λΌκ³ λ°νλ€.',
'μ°¨μ
κΈ κ°κΈ°κ° λ²
μ°¬ νκ³κΈ°μ
κ°μ΄λ° λκΈ°μ
μ΄ λλ©΄μ λΆμ€μνμ βλννβνκ³ μλ€λ κ²½κ³ κ° λμλ€. λκΈ°μ
λΆμ€μ΄ νμ€λ‘ λ₯μΉ κ²½μ° μ 체 μκΈμμ₯μ λΆμμΌλ‘ λ²μ§ μ μλ€λ μ°λ €λ€. LGκ²½μ μ°κ΅¬μμ 3μΌ βλΆμ€μν κΈ°μ
μ λννκ° κΈμ΅νμ¬ κ±΄μ μ±μ λ¨μ΄λ¨λ¦¬κ³ μλ€βλ μ λͺ©μ λ³΄κ³ μμμ κ΅λ΄ κΈμ΅νμ¬μ λΆμ€μμ° κ·λͺ¨κ° μ¬ λ€μ΄ μ§λ 9μ λ§κΉμ§ 6μ‘°8000μ΅μ λμ΄λ 39μ‘°8000μ΅μμ λ¬νλ€λ©° μ΄κ°μ΄ λΆμνλ€. μ΄νλ μ°κ΅¬μμμ βμ¬ λ€μ΄ μ¦κ°ν λΆμ€μμ°μ λλΆλΆ μνμμ λ°μνλλ° λκΈ°μ
λμΆμ΄ νΉν λ¬Έμ κ° λλ€βκ³ μ€λͺ
νλ€. μν λΆλ¬Έμ κ²½μ° λκΈ°μ
μ λΆμ€μ±κΆ μ¦κ°νμ μ¬ λ€μ΄ 9μκΉμ§ 8μ‘°5000μ΅μμ λ¬ν΄ μ§λν΄ κ°μ κΈ°κ°μ 3μ‘°2000μ΅μμ ν¨μ¬ μλμλ€. κ°μ κΈ°κ° μ€μκΈ°μ
μ λΆμ€μ±κΆ μ¦κ°νμ 10μ‘°4000μ΅μμΌλ‘ μ λ
λκΈ°μ λμΌνλ€. λ³΄κ³ μλ μ¬ λ€μ΄ λκΈ°μ
μ λΆμ€ μ λκ° μ»€μ§κ³ μλ€λ©° μ€μκΈ°μ
μ κΈλ‘λ² κΈμ΅μκΈ° λΉμ ꡬ쑰쑰μ μ΄ μλΉν μ§νλ λ°λ©΄ λκΈ°μ
μ μ΅κ·ΌμμΌ λΆμ€μ΄ νμ€νλκΈ° μμνκΈ° λλ¬Έμ΄λΌκ³ λΆμνλ€. μ΄μ보μλ°°μ¨ 1μ λ°λμ μμ
μ΄μ΅μΌλ‘ μ΄μλ κ°μ§ λͺ»νλ νκ³κΈ°μ
μ μ΄ν΄λ΄λ λνν μΆμΈκ° λλλ¬μ‘λ€. μ 체 μμ₯κΈ°μ
μ μ°¨μ
κΈ κ°μ΄λ° νκ³κΈ°μ
μ°¨μ
κΈμ΄ μ°¨μ§νλ λΉμ€μ 2005λ
13.3%μμ μ¬ν΄ μλ°κΈ° 34.0%λ‘ νλλλ€. νκ³κΈ°μ
μ νκ· μ°¨μ
κΈμ΄ κ°μ κΈ°κ° 1270μ΅μμμ 6799μ΅μμΌλ‘ 5.4λ°° λ΄ λ° λ°λ₯Έ κ²μ΄λ€. νκ³κΈ°μ
μ μ°¨μ
κΈ κ°μ΄λ° λκΈ°μ
μ΄ μ°¨μ§νλ λΉμ€μ΄ 93.2%μμ 99.1%κΉμ§ μΉμμΌλ©΄μ κ°λ³ λΆμ€μ λ©μΉ μμ²΄κ° μ»€μ‘λ€. μ΄ μ°κ΅¬μμμ βμμ₯μ¬ κ°μ΄λ° νκ³κΈ°μ
μ μ°¨μ
κΈμ λλΆλΆ λκΈ°μ
μ΄ κ°κ³ μλ μ
βμ΄λΌλ©° β1κ° λκΈ°μ
μ λΆμ€μ 25κ° μ€μκΈ°μ
μ λΆμ€κ³Ό λΉμ·ν μ λλ‘ μμ₯μ λ―ΈμΉλ μν₯μ΄ ν¬λ€λ κ² λ¬Έμ βλΌκ³ μ°λ €νλ€.λ³΄κ³ μλ μνμ μ΅μννλ €λ©΄ μ μ μ μΈ κ΅¬μ‘°μ‘°μ μ΄ ν΄λ΅μ΄λΌλ©° λΆμ€ κ°λ₯μ±μ΄ λμ κΈ°μ
μ μ λ³ν΄ μΆκ°μ μΈ μκΈ κ³΅κΈμ μ΅μ ν΄μΌ λΆμ€ νμ°μ λ§μ μ μλ€κ³ μ§μ νλ€.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]
# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[1.0000, 0.3668, 0.0727],
# [0.3668, 1.0000, 0.1521],
# [0.0727, 0.1521, 1.0000]])
<!--
### Direct Usage (Transformers)
<details><summary>Click to see the direct usage in Transformers</summary>
</details>
-->
<!--
### Downstream Usage (Sentence Transformers)
You can finetune this model on your own dataset.
<details><summary>Click to expand</summary>
</details>
-->
<!--
### Out-of-Scope Use
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
-->
<!--
## Bias, Risks and Limitations
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
-->
<!--
### Recommendations
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
-->
| sentence_0 | sentence_1 | |
|---|---|---|
| type | string | string |
| details | <ul><li>min: 8 tokens</li><li>mean: 17.68 tokens</li><li>max: 35 tokens</li></ul> | <ul><li>min: 229 tokens</li><li>mean: 438.65 tokens</li><li>max: 512 tokens</li></ul> |
| sentence_0 | sentence_1 |
|---|---|
| <code>2012λ μ λΆμΌμ₯ννμ μ£Όμλ°νμ λν΄ κΈ°κ° κ²°μ μ λ΄λ¦° μ¬νλΆλ?</code> | <code>μ§μ€κ·λͺ κ²°μ μ λ°μ κΉμ§νμ μ κ°μ‘±λ€μ 2010λ 6μμμΌ λ²μμ μ μμ₯ννμ κ΅κ°λ₯Ό μλλ‘ λΈ μ£Όμμλ λ± μ²κ΅¬μμ‘μ λλ€. κΉμ¨ μΈ‘μ "λ° μ λν΅λ Ήμ΄ μ¬λ§νκ³ λ μ΄ν 1980λ μ ν μ§ λ°νμ²κ΅¬ μμ¬λ₯Ό νμνκ³ , κ³Όκ±°μ¬μ 리μμνμ μ§μ€κ·λͺ κ²°μ μ μ‘λ¬λ°μ μ΄ν μν΄λ°°μμ μ²κ΅¬ν κ²μ΄λ―λ‘ κ³΅μμν¨κ° λ¨μμλ€"κ³ μ£Όμ₯νλ€.<br><br>νμ§λ§ 1μ¬ μ¬νλΆλ "μλ©Έμν¨κ° μ§λ¬λ€"λ©° κΉμ¨ μΈ‘μ μ²κ΅¬λ₯Ό κΈ°κ°νκ³ , 2μ¬ μ¬νλΆλ κΉμ¨κ° κ΅κ°μ κ°λ°νμλ‘ μΈν΄ μ¬μ°μ νλ©ν κ²μ μΈμ νλ©΄μλ μμ¬κ²°μ κΆμ΄ μμ ν λ°νλΉν μνλ μλμλ κ²μΌλ‘ νλ¨ν΄ μκ³ ν¨μ νκ²°νλ€. 2012λ 2μ 24μΌ μμΈμ€μμ§λ² λ―Όμ¬ν©μ17λΆ(μ¬νμ₯ μΌμμ)μ μν΄ 5.16μ₯ννμ βνλ©β κ³Όμ μμ κ°μμ΄ μμμμ΄ λ€μ ν λ² μ μ¦λμλ€. νμ§λ§ μ¬νλΆλ κΉμμ°κ° μ κΈ°ν κ³Όκ±° λΆμΌμ₯ννμ μ£Όμλ°νμ λν΄μλ 곡μμν¨ μλ©Έμ μ΄μ λ‘ κΈ°κ°νμλ€. μ΄μ κ΅κ°μ λ²μ£μ λν΄μλ 곡μ μν¨μ λ²μλ₯Ό νλκ² μΈμ ν΄μ€μΌ νλ€λ λΉνλ μ κΈ°λμλ€. <br><br>λλ²μμ 2014λ 2μ 13μΌ κΉμ§νμ¨ μ₯λ¨ μꡬ μ¨λ₯Ό λΉλ‘―ν μ κ°μ‘± 6λͺ μ΄ μ μμ₯ννμ κ΅κ°λ₯Ό μλλ‘ λΈ μ£Όμμλ λ± μ²κ΅¬μμ‘ μκ³ μ¬μμ μ¬λ¦¬λΆμν κΈ°κ° κ²°μ μ λ΄λ Έλ€. 'μ¬λ¦¬λΆμν'μ μκ³ μ¬κ±΄ κ°μ΄λ° μκ³ λμμ΄ μλλΌκ³ νλ¨λλ μ¬κ±΄μ λμ΄μ μ¬λ¦¬νμ§ μκ³ κΈ°κ°νλ μ λλ€.</code> |
| <code>ν¬μμ κ·μ¬'λΌ λΆλ¦¬λ μ¬λμ΄ μ¬ν΄ λ² λμ μΌλ§μΈκ°?</code> | <code>μ¬ν΄ μ μΈκ³μμ λκ° κ°μ₯ λ§μ λμ λ²μμκΉ.λ―Έκ΅ κ²½μ 맀체 λ§μΌμμΉλ βν¬μμ κ·μ¬β μλ° λ²ν λ²
μ
ν΄μμ¨μ΄ νμ₯μ΄ μ¬ν΄ μΈκ³μμ κ°μ₯ λ§μ λμ λ²μλ€κ³ 18μΌ(νμ§μκ°) 보λνλ€. μ€μμ€ μμ°μ 보μ
체 μ°μ€μμ€(Wealth-X)μ UBS μνμ μ‘°μ¬ κ²°κ³Ό μ¬μ΄ 464μ΅λ¬λ¬μλ λ²νμ μμ°μ΄ 127μ΅λ¬λ¬(μ½ 13μ‘°4500μ΅μ) λμ΄ μ§λ 11μΌ κΈ°μ€ 591μ΅λ¬λ¬κ° λλ€. ν루μ 3700λ§λ¬λ¬(μ½ 392μ΅μ)λ₯Ό λ²μ΄λ€μΈ κ²μ΄λ€. λΉ κ²μ΄μΈ λ§μ΄ν¬λ‘μννΈ νμ₯μ 726μ΅λ¬λ¬μ μμ°μ 보μ ν΄ 1μ λΆμ μ리λ₯Ό μ§μΌ°μ§λ§, μ¬ν΄ λ²νλ³΄λ€ μ μ 115μ΅λ¬λ¬λ₯Ό λ²μ΄ βμ¬ν΄ λ λ§μ΄ λ² μ¬λ μμβμμλ 2μμ λ¨Έλ¬Όλ λ€.3μλ μμ°μ΄ 114μ΅λ¬λ¬ μ¦κ°ν μΉ΄μ§λ
Έ μ
κ³μ κ±°λ¬Ό μ
Έλ μ λΈμ¨ λΌμ€λ² μ΄κ±°μ€μμ¦ νμ₯μ΄ μ°¨μ§νλ€. μ λΈμ¨ νμ₯μ μ§λ 2μ λ°©νν΄ βνκ΅μ λ΄κ΅μΈ μΆμ
μ΄ κ°λ₯ν βμ€ν μΉ΄μ§λ
Έβ μ€λ¦½ νκ°κ° λλ©΄ 40μ΅ |
| <code>DDPλ₯Ό μ€κ³ν 건μΆκ°μ μΆμ κ΅κ°λ?</code> | <code>μ μμΈ λλλ¬Έμ΄λμ₯ λΆμ§μ λ€μ΄μ βλλλ¬ΈλμμΈνλΌμ(DDP)βκ° λ΄λ¬ 21μΌ κ°μ₯μ μλκ³ ν격μ μμ©μ λλ¬λλ€. μ€κ³ λΉμλΆν° λ¨κ±°μ΄ μ°¬λ° λ Όλκ³Ό ν¨κ» νμ λ₯Ό λͺ¨μκΈ° λλ¬Έμ μ€κ³΅ μ΄ν μμΈμ βκΈλ‘λ² λͺ λ¬Ό 건μΆβμΌλ‘ λΆμν μ μμμ§ κ΄μ¬μ΄ μ λ¦¬κ³ μλ€. μκ΅μ μΈκ³μ 건μΆκ°μΈ μν νλλ(μ΄λΌν¬ μΆμ μ¬μ±κ±΄μΆκ°)κ° κ΅μ νμ곡λͺ¨λ₯Ό ν΅ν΄ 건μΆμ€κ³λ₯Ό λ§‘μλ€. λ―ΈνμΈ λΉν물체(UFO)κ° μ°μλ μ λλ‘ μ΄μμ μΈ βλΉμ ν 건물(ννκ° μΌμ μΉ μμ 건물)βμ΄μ΄μ 건μΆκ³μ ν° νμ₯μ μΌμΌμΌ°λ€. λλλ¬Έ μΌλμ μμ¬μ±κ³Ό μ§μμ±μ΄ 무μλ λ λΆμ₯κ΅°ν λμμΈμ΄λ νΉνκ³Ό λ―Έλ λλλ¬Έμ λ°μ μμ΄ ν¨μΆλ μ°½μ‘°μ±μ΄ λ보μΈλ€λ νΈνμ΄ μκ°λ¦¬λ©΄μ νλμ λ Όμμ΄ λ¨κ±°μ λ€. 건물μ λΉμ νμ±μ΄ μλ κ°ν΄ μ곡μ¬μΈ μΌμ±λ¬Όμ°λ 곡μ¬μ μ΄λ €μμ΄ λ§μλ€. μ곡과μ μμ 첨λ¨κΈ°μ μ μ©μ λ¬Όλ‘ μ μμ μ§κΈ°λ‘λ μμμ‘λ€. κ°μ ν¬κΈ°μ μΌλ° 건물(μ ν 건물)μ λΉν΄ 곡μ¬κΈ°κ°λ κ±°μ 2λ°° μ΄μ(4λ 8κ°μ) κ±Έλ Έλ€. 건물 μΈμ₯μ κ°μΈκ³ μλ μ루미λ ν¨λ(κ°λ‘, μΈλ‘ 1.5ο½)λ§λ 4λ§5133μ₯μ΄ μ°μλ€. ν¨λμ΄ λͺ¨λ μ κ°κ°μ΄μ΄μ 곡μ₯ μμ°μ΄ μλ λ³λ μ μμΌλ‘ λ§μΆ° λΆμλ€. 건물 μΈκ΄ λ©΄μ μ΄ μΆκ΅¬μ₯ 3λ°° ν¬κΈ°μ λ¬νλ€. μΌμ±λ¬Όμ°μ κ΅λ΄ κ³΅κ³΅κ³΅μ¬ μ΅μ΄λ‘ 3μ°¨μ μ 체μ€κ³ λ°©μμΈ BIMμ νμ©ν΄ μ΄λ€ ν¨λμ μ μνλ€. λΉμ ν μΈκ΄μ λ ΈμΆ μ½ν¬λ¦¬νΈ μμ λ μ΄κ³ μΈ΅ λΉλ©μ λ₯κ°νλ λ곡μ¬μλ€. μ΄μ§λ°° μΌμ±λ¬Όμ° PM(νλ‘μ νΈ λ§€λμ§λ¨ΌνΈ) μ무λ βBIM λͺ¨λΈμ ν΅ν΄ μλ‘μ΄ κ±°νΈμ§ 곡λ²μ κ°λ°ν΄ μ μ©νκ³ , κ°κΈ° λ€λ₯Έ 곑μ κ³Ό ννλ‘ μ€κ³λ μ€λ΄ 곡μ¬μμλ μ€λ¬Ό ν¬κΈ° λͺ¨νμ μμ°¨λ‘ μ μν΄ μ€κ³ μμμ λλμ μ΅λν μ΄λ Έλ€βκ³ λ§νλ€.</code> |
{
"scale": 20.0,
"similarity_fct": "cos_sim",
"gather_across_devices": false
}
per_device_train_batch_size: 16per_device_eval_batch_size: 16num_train_epochs: 4batch_sampler: no_duplicatesmulti_dataset_batch_sampler: round_robinoverwrite_output_dir: Falsedo_predict: Falseeval_strategy: noprediction_loss_only: Trueper_device_train_batch_size: 16per_device_eval_batch_size: 16per_gpu_train_batch_size: Noneper_gpu_eval_batch_size: Nonegradient_accumulation_steps: 1eval_accumulation_steps: Nonetorch_empty_cache_steps: Nonelearning_rate: 5e-05weight_decay: 0.0adam_beta1: 0.9adam_beta2: 0.999adam_epsilon: 1e-08max_grad_norm: 1num_train_epochs: 4max_steps: -1lr_scheduler_type: linearlr_scheduler_kwargs: {}warmup_ratio: 0.0warmup_steps: 0log_level: passivelog_level_replica: warninglog_on_each_node: Truelogging_nan_inf_filter: Truesave_safetensors: Truesave_on_each_node: Falsesave_only_model: Falserestore_callback_states_from_checkpoint: Falseno_cuda: Falseuse_cpu: Falseuse_mps_device: Falseseed: 42data_seed: Nonejit_mode_eval: Falsebf16: Falsefp16: Falsefp16_opt_level: O1half_precision_backend: autobf16_full_eval: Falsefp16_full_eval: Falsetf32: Nonelocal_rank: 0ddp_backend: Nonetpu_num_cores: Nonetpu_metrics_debug: Falsedebug: []dataloader_drop_last: Falsedataloader_num_workers: 0dataloader_prefetch_factor: Nonepast_index: -1disable_tqdm: Falseremove_unused_columns: Truelabel_names: Noneload_best_model_at_end: Falseignore_data_skip: Falsefsdp: []fsdp_min_num_params: 0fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}fsdp_transformer_layer_cls_to_wrap: Noneaccelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}parallelism_config: Nonedeepspeed: Nonelabel_smoothing_factor: 0.0optim: adamw_torch_fusedoptim_args: Noneadafactor: Falsegroup_by_length: Falselength_column_name: lengthproject: huggingfacetrackio_space_id: trackioddp_find_unused_parameters: Noneddp_bucket_cap_mb: Noneddp_broadcast_buffers: Falsedataloader_pin_memory: Truedataloader_persistent_workers: Falseskip_memory_metrics: Trueuse_legacy_prediction_loop: Falsepush_to_hub: Falseresume_from_checkpoint: Nonehub_model_id: Nonehub_strategy: every_savehub_private_repo: Nonehub_always_push: Falsehub_revision: Nonegradient_checkpointing: Falsegradient_checkpointing_kwargs: Noneinclude_inputs_for_metrics: Falseinclude_for_metrics: []eval_do_concat_batches: Truefp16_backend: autopush_to_hub_model_id: Nonepush_to_hub_organization: Nonemp_parameters:auto_find_batch_size: Falsefull_determinism: Falsetorchdynamo: Noneray_scope: lastddp_timeout: 1800torch_compile: Falsetorch_compile_backend: Nonetorch_compile_mode: Noneinclude_tokens_per_second: Falseinclude_num_input_tokens_seen: noneftune_noise_alpha: Noneoptim_target_modules: Nonebatch_eval_metrics: Falseeval_on_start: Falseuse_liger_kernel: Falseliger_kernel_config: Noneeval_use_gather_object: Falseaverage_tokens_across_devices: Trueprompts: Nonebatch_sampler: no_duplicatesmulti_dataset_batch_sampler: round_robinrouter_mapping: {}learning_rate_mapping: {}| Epoch | Step | Training Loss |
|---|---|---|
| 0.4558 | 500 | 0.1541 |
| 0.9116 | 1000 | 0.1221 |
| 1.3674 | 1500 | 0.0488 |
| 1.8232 | 2000 | 0.0168 |
| 2.2789 | 2500 | 0.0118 |
| 2.7347 | 3000 | 0.0038 |
| 3.1905 | 3500 | 0.0033 |
| 3.6463 | 4000 | 0.0016 |
@inproceedings{reimers-2019-sentence-bert,
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
author = "Reimers, Nils and Gurevych, Iryna",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
month = "11",
year = "2019",
publisher = "Association for Computational Linguistics",
url = "https://arxiv.org/abs/1908.10084",
}
@misc{henderson2017efficient,
title={Efficient Natural Language Response Suggestion for Smart Reply},
author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
year={2017},
eprint={1705.00652},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
<!--
## Glossary
*Clearly define terms in order to be accessible across audiences.*
-->
<!--
## Model Card Authors
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
-->
<!--
## Model Card Contact
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
-->