metadata
tags:
- ColBERT
- PyLate
- sentence-transformers
- sentence-similarity
- feature-extraction
- generated_from_trainer
- dataset_size:21502474
- loss:CachedContrastive
- code
- embeddings
- retrieval
- code search
base_model: lightonai/LateOn-v0
datasets:
- lightonai/cornstack
pipeline_tag: sentence-similarity
library_name: PyLate
license: apache-2.0
language:
- en
- code
metrics:
- MaxSim_accuracy@1
- MaxSim_accuracy@3
- MaxSim_accuracy@5
- MaxSim_accuracy@10
- MaxSim_precision@1
- MaxSim_precision@3
- MaxSim_precision@5
- MaxSim_precision@10
- MaxSim_recall@1
- MaxSim_recall@3
- MaxSim_recall@5
- MaxSim_recall@10
- MaxSim_ndcg@10
- MaxSim_mrr@10
- MaxSim_map@100
model-index:
- name: PyLate model based on lightonai/LateOn-v0
results:
- task:
type: py-late-information-retrieval
name: Py Late Information Retrieval
dataset:
name: CodeSearchNetPython
type: CodeSearchNetPython
metrics:
- type: MaxSim_accuracy@1
value: 0.915
name: Maxsim Accuracy@1
- type: MaxSim_accuracy@3
value: 0.977
name: Maxsim Accuracy@3
- type: MaxSim_accuracy@5
value: 0.984
name: Maxsim Accuracy@5
- type: MaxSim_accuracy@10
value: 0.989
name: Maxsim Accuracy@10
- type: MaxSim_precision@1
value: 0.915
name: Maxsim Precision@1
- type: MaxSim_precision@3
value: 0.3256666666666666
name: Maxsim Precision@3
- type: MaxSim_precision@5
value: 0.19680000000000003
name: Maxsim Precision@5
- type: MaxSim_precision@10
value: 0.09890000000000002
name: Maxsim Precision@10
- type: MaxSim_recall@1
value: 0.915
name: Maxsim Recall@1
- type: MaxSim_recall@3
value: 0.977
name: Maxsim Recall@3
- type: MaxSim_recall@5
value: 0.984
name: Maxsim Recall@5
- type: MaxSim_recall@10
value: 0.989
name: Maxsim Recall@10
- type: MaxSim_ndcg@10
value: 0.9560789554070617
name: Maxsim Ndcg@10
- type: MaxSim_mrr@10
value: 0.9450428571428574
name: Maxsim Mrr@10
- type: MaxSim_map@100
value: 0.9454659606030886
name: Maxsim Map@100
- task:
type: py-late-information-retrieval
name: Py Late Information Retrieval
dataset:
name: CodeSearchNetJavascript
type: CodeSearchNetJavascript
metrics:
- type: MaxSim_accuracy@1
value: 0.78
name: Maxsim Accuracy@1
- type: MaxSim_accuracy@3
value: 0.86
name: Maxsim Accuracy@3
- type: MaxSim_accuracy@5
value: 0.875
name: Maxsim Accuracy@5
- type: MaxSim_accuracy@10
value: 0.899
name: Maxsim Accuracy@10
- type: MaxSim_precision@1
value: 0.78
name: Maxsim Precision@1
- type: MaxSim_precision@3
value: 0.2866666666666666
name: Maxsim Precision@3
- type: MaxSim_precision@5
value: 0.175
name: Maxsim Precision@5
- type: MaxSim_precision@10
value: 0.08990000000000001
name: Maxsim Precision@10
- type: MaxSim_recall@1
value: 0.78
name: Maxsim Recall@1
- type: MaxSim_recall@3
value: 0.86
name: Maxsim Recall@3
- type: MaxSim_recall@5
value: 0.875
name: Maxsim Recall@5
- type: MaxSim_recall@10
value: 0.899
name: Maxsim Recall@10
- type: MaxSim_ndcg@10
value: 0.8418073889934297
name: Maxsim Ndcg@10
- type: MaxSim_mrr@10
value: 0.823275
name: Maxsim Mrr@10
- type: MaxSim_map@100
value: 0.8250494602708647
name: Maxsim Map@100
- task:
type: py-late-information-retrieval
name: Py Late Information Retrieval
dataset:
name: CodeSearchNetGo
type: CodeSearchNetGo
metrics:
- type: MaxSim_accuracy@1
value: 0.946
name: Maxsim Accuracy@1
- type: MaxSim_accuracy@3
value: 0.985
name: Maxsim Accuracy@3
- type: MaxSim_accuracy@5
value: 0.992
name: Maxsim Accuracy@5
- type: MaxSim_accuracy@10
value: 0.995
name: Maxsim Accuracy@10
- type: MaxSim_precision@1
value: 0.946
name: Maxsim Precision@1
- type: MaxSim_precision@3
value: 0.32833333333333325
name: Maxsim Precision@3
- type: MaxSim_precision@5
value: 0.19840000000000002
name: Maxsim Precision@5
- type: MaxSim_precision@10
value: 0.09950000000000002
name: Maxsim Precision@10
- type: MaxSim_recall@1
value: 0.946
name: Maxsim Recall@1
- type: MaxSim_recall@3
value: 0.985
name: Maxsim Recall@3
- type: MaxSim_recall@5
value: 0.992
name: Maxsim Recall@5
- type: MaxSim_recall@10
value: 0.995
name: Maxsim Recall@10
- type: MaxSim_ndcg@10
value: 0.9733599864092068
name: Maxsim Ndcg@10
- type: MaxSim_mrr@10
value: 0.966084523809524
name: Maxsim Mrr@10
- type: MaxSim_map@100
value: 0.9662720995670996
name: Maxsim Map@100
- task:
type: py-late-information-retrieval
name: Py Late Information Retrieval
dataset:
name: CodeSearchNetRuby
type: CodeSearchNetRuby
metrics:
- type: MaxSim_accuracy@1
value: 0.811
name: Maxsim Accuracy@1
- type: MaxSim_accuracy@3
value: 0.908
name: Maxsim Accuracy@3
- type: MaxSim_accuracy@5
value: 0.928
name: Maxsim Accuracy@5
- type: MaxSim_accuracy@10
value: 0.941
name: Maxsim Accuracy@10
- type: MaxSim_precision@1
value: 0.811
name: Maxsim Precision@1
- type: MaxSim_precision@3
value: 0.30266666666666664
name: Maxsim Precision@3
- type: MaxSim_precision@5
value: 0.18560000000000001
name: Maxsim Precision@5
- type: MaxSim_precision@10
value: 0.09410000000000002
name: Maxsim Precision@10
- type: MaxSim_recall@1
value: 0.811
name: Maxsim Recall@1
- type: MaxSim_recall@3
value: 0.908
name: Maxsim Recall@3
- type: MaxSim_recall@5
value: 0.928
name: Maxsim Recall@5
- type: MaxSim_recall@10
value: 0.941
name: Maxsim Recall@10
- type: MaxSim_ndcg@10
value: 0.8813183214131377
name: Maxsim Ndcg@10
- type: MaxSim_mrr@10
value: 0.8615630952380954
name: Maxsim Mrr@10
- type: MaxSim_map@100
value: 0.8625514053190784
name: Maxsim Map@100
- task:
type: py-late-information-retrieval
name: Py Late Information Retrieval
dataset:
name: CodeSearchNetJava
type: CodeSearchNetJava
metrics:
- type: MaxSim_accuracy@1
value: 0.857
name: Maxsim Accuracy@1
- type: MaxSim_accuracy@3
value: 0.948
name: Maxsim Accuracy@3
- type: MaxSim_accuracy@5
value: 0.959
name: Maxsim Accuracy@5
- type: MaxSim_accuracy@10
value: 0.968
name: Maxsim Accuracy@10
- type: MaxSim_precision@1
value: 0.857
name: Maxsim Precision@1
- type: MaxSim_precision@3
value: 0.31599999999999995
name: Maxsim Precision@3
- type: MaxSim_precision@5
value: 0.1918
name: Maxsim Precision@5
- type: MaxSim_precision@10
value: 0.09680000000000001
name: Maxsim Precision@10
- type: MaxSim_recall@1
value: 0.857
name: Maxsim Recall@1
- type: MaxSim_recall@3
value: 0.948
name: Maxsim Recall@3
- type: MaxSim_recall@5
value: 0.959
name: Maxsim Recall@5
- type: MaxSim_recall@10
value: 0.968
name: Maxsim Recall@10
- type: MaxSim_ndcg@10
value: 0.9193412246279467
name: Maxsim Ndcg@10
- type: MaxSim_mrr@10
value: 0.9029841269841272
name: Maxsim Mrr@10
- type: MaxSim_map@100
value: 0.9032739940384631
name: Maxsim Map@100
- task:
type: py-late-information-retrieval
name: Py Late Information Retrieval
dataset:
name: CodeSearchNetPhp
type: CodeSearchNetPhp
metrics:
- type: MaxSim_accuracy@1
value: 0.827
name: Maxsim Accuracy@1
- type: MaxSim_accuracy@3
value: 0.927
name: Maxsim Accuracy@3
- type: MaxSim_accuracy@5
value: 0.948
name: Maxsim Accuracy@5
- type: MaxSim_accuracy@10
value: 0.957
name: Maxsim Accuracy@10
- type: MaxSim_precision@1
value: 0.827
name: Maxsim Precision@1
- type: MaxSim_precision@3
value: 0.309
name: Maxsim Precision@3
- type: MaxSim_precision@5
value: 0.18960000000000002
name: Maxsim Precision@5
- type: MaxSim_precision@10
value: 0.09570000000000002
name: Maxsim Precision@10
- type: MaxSim_recall@1
value: 0.827
name: Maxsim Recall@1
- type: MaxSim_recall@3
value: 0.927
name: Maxsim Recall@3
- type: MaxSim_recall@5
value: 0.948
name: Maxsim Recall@5
- type: MaxSim_recall@10
value: 0.957
name: Maxsim Recall@10
- type: MaxSim_ndcg@10
value: 0.898140933693793
name: Maxsim Ndcg@10
- type: MaxSim_mrr@10
value: 0.8784884920634926
name: Maxsim Mrr@10
- type: MaxSim_map@100
value: 0.8791260994917535
name: Maxsim Map@100
- task:
type: code-search-network
name: Code Search Network
dataset:
name: CodeSearchNet mean
type: CodeSearchNet_mean
metrics:
- type: MaxSim_accuracy@1
value: 0.856
name: Maxsim Accuracy@1
- type: MaxSim_accuracy@3
value: 0.9341666666666667
name: Maxsim Accuracy@3
- type: MaxSim_accuracy@5
value: 0.9476666666666667
name: Maxsim Accuracy@5
- type: MaxSim_accuracy@10
value: 0.9581666666666666
name: Maxsim Accuracy@10
- type: MaxSim_precision@1
value: 0.856
name: Maxsim Precision@1
- type: MaxSim_precision@3
value: 0.3113888888888888
name: Maxsim Precision@3
- type: MaxSim_precision@5
value: 0.18953333333333333
name: Maxsim Precision@5
- type: MaxSim_precision@10
value: 0.09581666666666667
name: Maxsim Precision@10
- type: MaxSim_recall@1
value: 0.856
name: Maxsim Recall@1
- type: MaxSim_recall@3
value: 0.9341666666666667
name: Maxsim Recall@3
- type: MaxSim_recall@5
value: 0.9476666666666667
name: Maxsim Recall@5
- type: MaxSim_recall@10
value: 0.9581666666666666
name: Maxsim Recall@10
- type: MaxSim_ndcg@10
value: 0.911674468424096
name: Maxsim Ndcg@10
- type: MaxSim_mrr@10
value: 0.8962396825396827
name: Maxsim Mrr@10
- type: MaxSim_map@100
value: 0.8969565032150579
name: Maxsim Map@100
LateOn-Code
The LateOn-Code collection is composed of PyLate models optimized for code retrieval. These late interaction models are first pre-trained following the methodology of CoRNStack. These pre-trained models are then further fine-tuned on train sets of CoIR using the nv-retriever methodology to mine hard negatives while preventing false negatives.
We started from the two best ColBERT models on the BEIR benchmark for their respective sizes. The first one, LateOn-Code is based on in-house LateOn model, a new version of GTE-ModernColBERT-v1 built on ModernBERT-base (also developed at LightOn). This version underwent significantly deeper training, crossing the 57 mark on BEIR, almost a 2.5-point improvement and is thus SOTA by a large margin. We'll release this base model along with training data and boilerplates in the near future, so stay tuned! The second, LateOn-Code-edge is a smaller model based on the edge-colbert model family from mixedbread, using the smallest variant (Ettin-17M) for maximum efficiency. For more details on the training setup, please refer to our blogpost.
The original CoRNStack data in a format compatible with PyLate can be found here while the fine-tuning data can be found here. Training boilerplates can be found here in the PyLate repository
MTEB (Code, v1) benchmark results
Pre-trained models achieve very competitive results as the 17M model outperforms the very strong granite-embedding-small-english-r2 by an average of 1.7. This is truly impressive, as the granite model is almost three times bigger (17M vs 48M), but is also a beast on its own in the <100M parameters range. It also outperforms the larger granite variant (149M). The larger version nicely scales by improving over the performance of its little sibling by 6.5 on average.
Although the pre-training results are already very impressive given that they are mostly out-of-domain, running a proper fine-tuning using the training data of CoIR significantly boost the performance of the models. Notably, the 17M model increases from 57.50 to 66.64 (+9.14), getting pretty close to EmbeddingGemma-300M while being 17 times smaller. The larger one increases from 63.77 to 74.12 (+10.35), strongly outperforming EmbeddingGemma-300M and getting closer to strong LLM models such as Qwen3-Embedding-0.6B and C2LLM-0.5B while being much smaller.
| Model | Params | Type | Avg | Apps | COIR CSNet | CodeEdit | CodeFB MT | CodeFB ST | CSNet CC | CSNet | CodeTrans Contest | CodeTrans DL | CosQA | StackOF QA | Synth T2SQL |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Baseline | |||||||||||||||
| BM25 | - | Lexical | 44.41 | 4.76 | 40.86 | 49.85 | 59.19 | 68.15 | 53.97 | 60.01 | 47.78 | 34.42 | 18.75 | 70.26 | 24.94 |
| Small (≤50M) | |||||||||||||||
| granite-embedding-small-english-r2 | 47M | Single vector | 55.84 | 13.54 | 60.46 | 57.16 | 52.19 | 76.85 | 48.42 | 78.28 | 77.63 | 33.63 | 35.58 | 90.04 | 46.33 |
| LateOn-Code-edge-pretrain | 17M | Multi vector | 57.50 | 10.81 | 73.78 | 62.07 | 51.92 | 76.65 | 63.22 | 88.03 | 71.31 | 33.16 | 30.53 | 74.63 | 53.83 |
| LateOn-Code-edge | 17M | Multi vector | 66.64 | 26.22 | 81.60 | 62.21 | 74.25 | 87.12 | 79.26 | 87.85 | 75.36 | 37.08 | 40.54 | 85.63 | 62.57 |
| Δ (fine-tune - pretrain) | +9.14 | +15.41 | +7.82 | +0.14 | +22.33 | +10.47 | +16.04 | -0.18 | +4.05 | +3.92 | +10.01 | +11.00 | +8.74 | ||
| Medium (100M–300M) | |||||||||||||||
| granite-embedding-english-r2 | 149M | Single vector | 57.22 | 13.96 | 64.65 | 59.35 | 52.54 | 77.18 | 47.67 | 80.79 | 77.07 | 35.03 | 37.01 | 91.80 | 49.55 |
| CodeRankEmbed | 137M | Single vector | 60.47 | 23.45 | 83.20 | 59.98 | 42.61 | 78.10 | 68.89 | 89.50 | 66.43 | 34.49 | 35.17 | 80.53 | 63.27 |
| GTE-ModernBERT | 149M | Single vector | 71.66 | 57.72 | 83.10 | 55.83 | 86.15 | 86.00 | 93.61 | 88.76 | 72.35 | 37.27 | 43.36 | 91.14 | 64.61 |
| embeddinggemma-300m | 300M | Single vector | 68.76 | 84.39 | 75.54 | 62.10 | 51.42 | 80.26 | 73.71 | 90.15 | 85.51 | 33.52 | 43.60 | 86.47 | 58.42 |
| LateOn-Code-pretrain | 149M | Multi vector | 63.77 | 23.09 | 80.27 | 68.74 | 50.21 | 82.66 | 71.47 | 91.05 | 82.20 | 34.46 | 34.15 | 85.61 | 61.34 |
| LateOn-Code | 149M | Multi vector | 74.12 | 54.76 | 86.57 | 64.99 | 82.22 | 90.40 | 89.32 | 90.40 | 87.44 | 41.00 | 45.23 | 93.43 | 63.67 |
| Δ (fine-tune - pretrain) | +10.35 | +31.67 | +6.30 | -3.75 | +32.01 | +7.74 | +17.85 | -0.65 | +5.24 | +6.54 | +11.08 | +7.82 | +2.33 | ||
| Large (≥500M) | |||||||||||||||
| C2LLM-0.5B | 500M | Single vector | 75.46 | 61.02 | 86.71 | 71.39 | 92.29 | 88.63 | 96.29 | 89.20 | 84.27 | 33.99 | 38.30 | 89.40 | 74.08 |
| Qwen3-Embedding-0.6B | 600M | Single vector | 75.42 | 75.34 | 84.69 | 64.42 | 90.82 | 86.39 | 91.72 | 91.01 | 86.05 | 31.36 | 36.48 | 89.99 | 76.74 |
Best result across all sizes is underlined. Best within each size category is bolded.
Colgrep
The LateOn-Code family model can easily be used within ColGrep, an easy-to-use search tool that give their powerful search capabilities to coding agent. It has been designed to extend grep capabilities to get the best of both world and is very effective to enhance the quality of the answer while diminishing answer time and tokens consumption. Given the performance of the very light-weight 17M model, it can easily run quickly on any computer.
Install ColGrep
# macOS / Linux
curl --proto '=https' --tlsv1.2 -LsSf https://github.com/lightonai/next-plaid/releases/latest/download/colgrep-installer.sh | sh
# Windows (PowerShell)
powershell -c "irm https://github.com/lightonai/next-plaid/releases/latest/download/colgrep-installer.ps1 | iex"
Search
# Semantic search — find code by meaning
colgrep "function that retries HTTP requests"
# Regex search
colgrep -e "async fn\s+\w+"
# Hybrid — regex narrows candidates, semantics ranks them
colgrep -e "Result<" "error handling" --include="*.rs"
Install for Claude Code
colgrep --install-claude-code
Choose a Model
# Set the model
colgrep set-model lightonai/LateOn-Code # default: lightonai/LateOn-Code-edge
For more information about ColGrep, please refer to the official documentation
PyLate model based on lightonai/LateOn (unreleased yet)
This is a PyLate model finetuned from lightonai/LateOn (the base model has not been released (yet) but is a strong model hitting 67 on BEIR, stay tuned!) on the python, php, go, ruby, javascript and java datasets. It maps sentences & paragraphs to sequences of 128-dimensional dense vectors and can be used for semantic textual similarity using the MaxSim operator.
Model Details
Model Description
- Model Type: PyLate model
- Base model: lightonai/LateOn-v0
- Document Length: 2048 tokens
- Query Length: 256 tokens
- Output Dimensionality: 128 tokens
- Similarity Function: MaxSim
- Training Datasets:
- Language: English, code
- License: Apache 2.0
Model Sources
- Documentation: PyLate Documentation
- Repository: PyLate on GitHub
- Hugging Face: PyLate models on Hugging Face
Full Model Architecture
ColBERT(
(0): Transformer({'max_seq_length': 2047, 'do_lower_case': False, 'architecture': 'ModernBertModel'})
(1): Dense({'in_features': 768, 'out_features': 128, 'bias': False, 'activation_function': 'torch.nn.modules.linear.Identity', 'use_residual': False})
)
Usage
First install the PyLate library:
pip install -U pylate
Retrieval
Use this model with PyLate to index and retrieve documents. The index uses FastPLAID for efficient similarity search.
Indexing documents
Load the ColBERT model and initialize the PLAID index, then encode and index your documents:
from pylate import indexes, models, retrieve
# Step 1: Load the ColBERT model
model = models.ColBERT(
model_name_or_path="pylate_model_id",
)
# Step 2: Initialize the PLAID index
index = indexes.PLAID(
index_folder="pylate-index",
index_name="index",
override=True, # This overwrites the existing index if any
)
# Step 3: Encode the documents
documents_ids = ["1", "2", "3"]
documents = ["document 1 text", "document 2 text", "document 3 text"]
documents_embeddings = model.encode(
documents,
batch_size=32,
is_query=False, # Ensure that it is set to False to indicate that these are documents, not queries
show_progress_bar=True,
)
# Step 4: Add document embeddings to the index by providing embeddings and corresponding ids
index.add_documents(
documents_ids=documents_ids,
documents_embeddings=documents_embeddings,
)
Note that you do not have to recreate the index and encode the documents every time. Once you have created an index and added the documents, you can re-use the index later by loading it:
# To load an index, simply instantiate it with the correct folder/name and without overriding it
index = indexes.PLAID(
index_folder="pylate-index",
index_name="index",
)
Retrieving top-k documents for queries
Once the documents are indexed, you can retrieve the top-k most relevant documents for a given set of queries. To do so, initialize the ColBERT retriever with the index you want to search in, encode the queries and then retrieve the top-k documents to get the top matches ids and relevance scores:
# Step 1: Initialize the ColBERT retriever
retriever = retrieve.ColBERT(index=index)
# Step 2: Encode the queries
queries_embeddings = model.encode(
["query for document 3", "query for document 1"],
batch_size=32,
is_query=True, # # Ensure that it is set to False to indicate that these are queries
show_progress_bar=True,
)
# Step 3: Retrieve top-k documents
scores = retriever.retrieve(
queries_embeddings=queries_embeddings,
k=10, # Retrieve the top 10 matches for each query
)
Reranking
If you only want to use the ColBERT model to perform reranking on top of your first-stage retrieval pipeline without building an index, you can simply use rank function and pass the queries and documents to rerank:
from pylate import rank, models
queries = [
"query A",
"query B",
]
documents = [
["document A", "document B"],
["document 1", "document C", "document B"],
]
documents_ids = [
[1, 2],
[1, 3, 2],
]
model = models.ColBERT(
model_name_or_path="pylate_model_id",
)
queries_embeddings = model.encode(
queries,
is_query=True,
)
documents_embeddings = model.encode(
documents,
is_query=False,
)
reranked_documents = rank.rerank(
documents_ids=documents_ids,
queries_embeddings=queries_embeddings,
documents_embeddings=documents_embeddings,
)
Evaluation
Metrics
Py Late Information Retrieval
- Dataset:
['CodeSearchNetPython', 'CodeSearchNetJavascript', 'CodeSearchNetGo', 'CodeSearchNetRuby', 'CodeSearchNetJava', 'CodeSearchNetPhp'] - Evaluated with
pylate.evaluation.pylate_information_retrieval_evaluator.PyLateInformationRetrievalEvaluator
| Metric | CodeSearchNetPython | CodeSearchNetJavascript | CodeSearchNetGo | CodeSearchNetRuby | CodeSearchNetJava | CodeSearchNetPhp |
|---|---|---|---|---|---|---|
| MaxSim_accuracy@1 | 0.915 | 0.78 | 0.946 | 0.811 | 0.857 | 0.827 |
| MaxSim_accuracy@3 | 0.977 | 0.86 | 0.985 | 0.908 | 0.948 | 0.927 |
| MaxSim_accuracy@5 | 0.984 | 0.875 | 0.992 | 0.928 | 0.959 | 0.948 |
| MaxSim_accuracy@10 | 0.989 | 0.899 | 0.995 | 0.941 | 0.968 | 0.957 |
| MaxSim_precision@1 | 0.915 | 0.78 | 0.946 | 0.811 | 0.857 | 0.827 |
| MaxSim_precision@3 | 0.3257 | 0.2867 | 0.3283 | 0.3027 | 0.316 | 0.309 |
| MaxSim_precision@5 | 0.1968 | 0.175 | 0.1984 | 0.1856 | 0.1918 | 0.1896 |
| MaxSim_precision@10 | 0.0989 | 0.0899 | 0.0995 | 0.0941 | 0.0968 | 0.0957 |
| MaxSim_recall@1 | 0.915 | 0.78 | 0.946 | 0.811 | 0.857 | 0.827 |
| MaxSim_recall@3 | 0.977 | 0.86 | 0.985 | 0.908 | 0.948 | 0.927 |
| MaxSim_recall@5 | 0.984 | 0.875 | 0.992 | 0.928 | 0.959 | 0.948 |
| MaxSim_recall@10 | 0.989 | 0.899 | 0.995 | 0.941 | 0.968 | 0.957 |
| MaxSim_ndcg@10 | 0.9561 | 0.8418 | 0.9734 | 0.8813 | 0.9193 | 0.8981 |
| MaxSim_mrr@10 | 0.945 | 0.8233 | 0.9661 | 0.8616 | 0.903 | 0.8785 |
| MaxSim_map@100 | 0.9455 | 0.825 | 0.9663 | 0.8626 | 0.9033 | 0.8791 |
Code Search Network
- Dataset:
CodeSearchNet_mean - Evaluated with
pylate.evaluation.code_stack_network_evaluator.CodeSearchNetworkEvaluator
| Metric | Value |
|---|---|
| MaxSim_accuracy@1 | 0.856 |
| MaxSim_accuracy@3 | 0.9342 |
| MaxSim_accuracy@5 | 0.9477 |
| MaxSim_accuracy@10 | 0.9582 |
| MaxSim_precision@1 | 0.856 |
| MaxSim_precision@3 | 0.3114 |
| MaxSim_precision@5 | 0.1895 |
| MaxSim_precision@10 | 0.0958 |
| MaxSim_recall@1 | 0.856 |
| MaxSim_recall@3 | 0.9342 |
| MaxSim_recall@5 | 0.9477 |
| MaxSim_recall@10 | 0.9582 |
| MaxSim_ndcg@10 | 0.9117 |
| MaxSim_mrr@10 | 0.8962 |
| MaxSim_map@100 | 0.897 |
Training Details
Training Datasets
python
- Dataset: python at d821c55
- Size: 6,889,731 training samples
- Approximate statistics based on the first 1000 samples:
query document negative_0 negative_1 negative_2 negative_3 negative_4 negative_5 negative_6 negative_7 negative_8 negative_9 negative_10 negative_11 negative_12 negative_13 negative_14 negative_15 negative_16 negative_17 negative_18 negative_19 negative_20 negative_21 negative_22 negative_23 negative_24 negative_25 negative_26 negative_27 negative_28 negative_29 negative_30 negative_31 negative_32 negative_33 negative_34 negative_35 negative_36 negative_37 negative_38 negative_39 negative_40 negative_41 negative_42 negative_43 negative_44 negative_45 negative_46 negative_47 negative_48 negative_49 negative_50 negative_51 negative_52 negative_53 negative_54 negative_55 negative_56 negative_57 negative_58 negative_59 negative_60 negative_61 negative_62 negative_63 negative_64 negative_65 negative_66 negative_67 negative_68 negative_69 negative_70 negative_71 negative_72 negative_73 negative_74 negative_75 negative_76 negative_77 negative_78 negative_79 negative_80 negative_81 negative_82 negative_83 negative_84 negative_85 negative_86 negative_87 negative_88 negative_89 negative_90 negative_91 negative_92 negative_93 negative_94 negative_95 negative_96 negative_97 negative_98 negative_99 negative_scores type string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string list details min: 7 tokens, mean: 24.12 tokens, max: 256 tokens min: 13 tokens, mean: 124.24 tokens, max: 256 tokens min: 6 tokens, mean: 102.93 tokens, max: 256 tokens min: 6 tokens, mean: 100.95 tokens, max: 256 tokens min: 6 tokens, mean: 98.81 tokens, max: 256 tokens min: 6 tokens, mean: 97.66 tokens, max: 256 tokens min: 7 tokens, mean: 100.24 tokens, max: 256 tokens min: 8 tokens, mean: 99.31 tokens, max: 256 tokens min: 6 tokens, mean: 99.38 tokens, max: 256 tokens min: 6 tokens, mean: 97.76 tokens, max: 256 tokens min: 6 tokens, mean: 100.62 tokens, max: 256 tokens min: 7 tokens, mean: 102.2 tokens, max: 256 tokens min: 8 tokens, mean: 99.57 tokens, max: 256 tokens min: 6 tokens, mean: 105.36 tokens, max: 256 tokens min: 6 tokens, mean: 105.1 tokens, max: 256 tokens min: 8 tokens, mean: 97.96 tokens, max: 256 tokens min: 7 tokens, mean: 102.75 tokens, max: 256 tokens min: 6 tokens, mean: 100.27 tokens, max: 256 tokens min: 8 tokens, mean: 97.89 tokens, max: 256 tokens min: 6 tokens, mean: 100.83 tokens, max: 256 tokens min: 6 tokens, mean: 100.24 tokens, max: 256 tokens min: 8 tokens, mean: 94.86 tokens, max: 256 tokens min: 6 tokens, mean: 102.06 tokens, max: 256 tokens min: 7 tokens, mean: 97.33 tokens, max: 256 tokens min: 8 tokens, mean: 99.28 tokens, max: 256 tokens min: 6 tokens, mean: 99.07 tokens, max: 256 tokens min: 6 tokens, mean: 104.46 tokens, max: 256 tokens min: 6 tokens, mean: 100.14 tokens, max: 256 tokens min: 6 tokens, mean: 104.86 tokens, max: 256 tokens min: 6 tokens, mean: 104.23 tokens, max: 256 tokens min: 6 tokens, mean: 101.24 tokens, max: 256 tokens min: 6 tokens, mean: 102.47 tokens, max: 256 tokens min: 6 tokens, mean: 103.95 tokens, max: 256 tokens min: 8 tokens, mean: 100.49 tokens, max: 256 tokens min: 6 tokens, mean: 101.04 tokens, max: 256 tokens min: 6 tokens, mean: 101.99 tokens, max: 256 tokens min: 6 tokens, mean: 104.11 tokens, max: 256 tokens min: 7 tokens, mean: 102.69 tokens, max: 256 tokens min: 6 tokens, mean: 104.26 tokens, max: 256 tokens min: 6 tokens, mean: 104.61 tokens, max: 256 tokens min: 7 tokens, mean: 105.69 tokens, max: 256 tokens min: 6 tokens, mean: 102.66 tokens, max: 256 tokens min: 6 tokens, mean: 100.26 tokens, max: 256 tokens min: 6 tokens, mean: 104.47 tokens, max: 256 tokens min: 6 tokens, mean: 104.86 tokens, max: 256 tokens min: 6 tokens, mean: 104.49 tokens, max: 256 tokens min: 6 tokens, mean: 100.12 tokens, max: 256 tokens min: 6 tokens, mean: 105.86 tokens, max: 256 tokens min: 8 tokens, mean: 103.38 tokens, max: 256 tokens min: 6 tokens, mean: 107.83 tokens, max: 256 tokens min: 6 tokens, mean: 104.13 tokens, max: 256 tokens min: 6 tokens, mean: 102.61 tokens, max: 256 tokens min: 6 tokens, mean: 106.11 tokens, max: 256 tokens min: 8 tokens, mean: 107.79 tokens, max: 256 tokens min: 6 tokens, mean: 104.54 tokens, max: 256 tokens min: 6 tokens, mean: 106.19 tokens, max: 256 tokens min: 6 tokens, mean: 104.62 tokens, max: 256 tokens min: 6 tokens, mean: 101.92 tokens, max: 256 tokens min: 6 tokens, mean: 99.12 tokens, max: 256 tokens min: 8 tokens, mean: 102.54 tokens, max: 256 tokens min: 8 tokens, mean: 103.7 tokens, max: 256 tokens min: 8 tokens, mean: 104.09 tokens, max: 256 tokens min: 8 tokens, mean: 101.61 tokens, max: 256 tokens min: 7 tokens, mean: 104.18 tokens, max: 256 tokens min: 6 tokens, mean: 104.56 tokens, max: 256 tokens min: 6 tokens, mean: 103.59 tokens, max: 256 tokens min: 6 tokens, mean: 104.55 tokens, max: 256 tokens min: 6 tokens, mean: 102.95 tokens, max: 256 tokens min: 6 tokens, mean: 103.91 tokens, max: 256 tokens min: 6 tokens, mean: 107.13 tokens, max: 256 tokens min: 6 tokens, mean: 106.22 tokens, max: 256 tokens min: 8 tokens, mean: 103.66 tokens, max: 256 tokens min: 6 tokens, mean: 102.49 tokens, max: 256 tokens min: 9 tokens, mean: 101.41 tokens, max: 256 tokens min: 6 tokens, mean: 102.56 tokens, max: 256 tokens min: 6 tokens, mean: 105.9 tokens, max: 256 tokens min: 6 tokens, mean: 104.3 tokens, max: 256 tokens min: 6 tokens, mean: 101.44 tokens, max: 256 tokens min: 6 tokens, mean: 103.99 tokens, max: 256 tokens min: 6 tokens, mean: 104.28 tokens, max: 256 tokens min: 6 tokens, mean: 104.46 tokens, max: 256 tokens min: 6 tokens, mean: 105.45 tokens, max: 256 tokens min: 6 tokens, mean: 103.9 tokens, max: 256 tokens min: 6 tokens, mean: 103.97 tokens, max: 256 tokens min: 8 tokens, mean: 103.85 tokens, max: 256 tokens min: 7 tokens, mean: 105.92 tokens, max: 256 tokens min: 6 tokens, mean: 102.82 tokens, max: 256 tokens min: 6 tokens, mean: 101.99 tokens, max: 256 tokens min: 6 tokens, mean: 103.84 tokens, max: 256 tokens min: 6 tokens, mean: 101.51 tokens, max: 256 tokens min: 6 tokens, mean: 105.28 tokens, max: 256 tokens min: 6 tokens, mean: 105.18 tokens, max: 256 tokens min: 6 tokens, mean: 107.3 tokens, max: 256 tokens min: 6 tokens, mean: 108.62 tokens, max: 256 tokens min: 8 tokens, mean: 108.81 tokens, max: 256 tokens min: 6 tokens, mean: 101.51 tokens, max: 256 tokens min: 6 tokens, mean: 105.4 tokens, max: 256 tokens min: 7 tokens, mean: 105.98 tokens, max: 256 tokens min: 8 tokens, mean: 105.64 tokens, max: 256 tokens min: 8 tokens, mean: 103.76 tokens, max: 256 tokens min: 6 tokens, mean: 102.87 tokens, max: 256 tokens min: 6 tokens, mean: 102.58 tokens, max: 256 tokens size: 100 elements - Samples:
query document negative_0 Write the concordance entries to the output file(filename) See sample output files for format.def write_concordance(self, filename):<br> all_keys = self.concordance_table.get_all_keys()<br> lines = []<br> for i in all_keys:<br> a = ""<br> a += i + ":"<br> f = self.concordance_table.get_value(i)<br> if f != None:<br> for s in f:<br> a += " " + str(s)<br> a += "\n"<br> lines.append(a)<br> a = open(filename, "w+")<br> for i in lines:<br> a.write(i)<br> a.close()def write_concordance(self, filename):<br> out = ''<br> values = [x for x in self.concordance_table.hash_table if x is not None]<br> values.sort(key=lambda x: x[0])<br> for v in values:<br> out += f'{v[0]}: {" ".join(str(x) for x in sorted(set(v[1])))}\n' <br> with open(filename, 'w') as f:<br> f.write(out.rstrip()) - Loss:
pylate.losses.cached_contrastive.CachedContrastive
php
- Dataset: php at d821c55
- Size: 2,676,409 training samples
- Approximate statistics based on the first 1000 samples:
query document negative_0 negative_1 negative_2 negative_3 negative_4 negative_5 negative_6 negative_7 negative_8 negative_9 negative_10 negative_11 negative_12 negative_13 negative_14 negative_15 negative_16 negative_17 negative_18 negative_19 negative_20 negative_21 negative_22 negative_23 negative_24 negative_25 negative_26 negative_27 negative_28 negative_29 negative_30 negative_31 negative_32 negative_33 negative_34 negative_35 negative_36 negative_37 negative_38 negative_39 negative_40 negative_41 negative_42 negative_43 negative_44 negative_45 negative_46 negative_47 negative_48 negative_49 negative_50 negative_51 negative_52 negative_53 negative_54 negative_55 negative_56 negative_57 negative_58 negative_59 negative_60 negative_61 negative_62 negative_63 negative_64 negative_65 negative_66 negative_67 negative_68 negative_69 negative_70 negative_71 negative_72 negative_73 negative_74 negative_75 negative_76 negative_77 negative_78 negative_79 negative_80 negative_81 negative_82 negative_83 negative_84 negative_85 negative_86 negative_87 negative_88 negative_89 negative_90 negative_91 negative_92 negative_93 negative_94 negative_95 negative_96 negative_97 negative_98 negative_99 negative_scores type string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string list details min: 7 tokens, mean: 18.02 tokens, max: 219 tokens min: 8 tokens, mean: 97.31 tokens, max: 256 tokens min: 7 tokens, mean: 83.05 tokens, max: 256 tokens min: 7 tokens, mean: 84.18 tokens, max: 256 tokens min: 7 tokens, mean: 82.44 tokens, max: 256 tokens min: 7 tokens, mean: 82.74 tokens, max: 256 tokens min: 7 tokens, mean: 85.61 tokens, max: 256 tokens min: 6 tokens, mean: 80.61 tokens, max: 256 tokens min: 7 tokens, mean: 85.39 tokens, max: 256 tokens min: 7 tokens, mean: 85.96 tokens, max: 256 tokens min: 7 tokens, mean: 83.7 tokens, max: 256 tokens min: 7 tokens, mean: 83.25 tokens, max: 256 tokens min: 7 tokens, mean: 86.36 tokens, max: 256 tokens min: 7 tokens, mean: 79.83 tokens, max: 256 tokens min: 7 tokens, mean: 85.96 tokens, max: 256 tokens min: 7 tokens, mean: 83.3 tokens, max: 256 tokens min: 7 tokens, mean: 82.56 tokens, max: 256 tokens min: 7 tokens, mean: 84.44 tokens, max: 256 tokens min: 7 tokens, mean: 84.95 tokens, max: 256 tokens min: 7 tokens, mean: 85.52 tokens, max: 256 tokens min: 7 tokens, mean: 84.9 tokens, max: 256 tokens min: 7 tokens, mean: 82.11 tokens, max: 256 tokens min: 7 tokens, mean: 84.76 tokens, max: 256 tokens min: 7 tokens, mean: 85.61 tokens, max: 256 tokens min: 7 tokens, mean: 87.78 tokens, max: 256 tokens min: 7 tokens, mean: 79.7 tokens, max: 256 tokens min: 7 tokens, mean: 88.52 tokens, max: 256 tokens min: 7 tokens, mean: 88.94 tokens, max: 256 tokens min: 7 tokens, mean: 84.75 tokens, max: 256 tokens min: 7 tokens, mean: 87.28 tokens, max: 256 tokens min: 7 tokens, mean: 86.87 tokens, max: 256 tokens min: 7 tokens, mean: 89.19 tokens, max: 256 tokens min: 7 tokens, mean: 87.12 tokens, max: 256 tokens min: 7 tokens, mean: 88.61 tokens, max: 256 tokens min: 7 tokens, mean: 89.19 tokens, max: 256 tokens min: 7 tokens, mean: 88.56 tokens, max: 256 tokens min: 7 tokens, mean: 85.75 tokens, max: 256 tokens min: 7 tokens, mean: 85.16 tokens, max: 256 tokens min: 7 tokens, mean: 87.35 tokens, max: 256 tokens min: 7 tokens, mean: 90.14 tokens, max: 256 tokens min: 7 tokens, mean: 86.28 tokens, max: 256 tokens min: 7 tokens, mean: 86.32 tokens, max: 256 tokens min: 7 tokens, mean: 84.63 tokens, max: 256 tokens min: 7 tokens, mean: 88.19 tokens, max: 256 tokens min: 7 tokens, mean: 87.46 tokens, max: 256 tokens min: 7 tokens, mean: 86.83 tokens, max: 256 tokens min: 7 tokens, mean: 89.91 tokens, max: 256 tokens min: 7 tokens, mean: 90.59 tokens, max: 256 tokens min: 7 tokens, mean: 87.58 tokens, max: 256 tokens min: 7 tokens, mean: 89.3 tokens, max: 256 tokens min: 7 tokens, mean: 93.99 tokens, max: 256 tokens min: 7 tokens, mean: 88.55 tokens, max: 256 tokens min: 7 tokens, mean: 86.46 tokens, max: 256 tokens min: 7 tokens, mean: 83.97 tokens, max: 256 tokens min: 7 tokens, mean: 86.73 tokens, max: 256 tokens min: 7 tokens, mean: 88.11 tokens, max: 256 tokens min: 7 tokens, mean: 85.57 tokens, max: 256 tokens min: 7 tokens, mean: 87.64 tokens, max: 256 tokens min: 7 tokens, mean: 88.58 tokens, max: 256 tokens min: 7 tokens, mean: 89.99 tokens, max: 256 tokens min: 7 tokens, mean: 85.44 tokens, max: 256 tokens min: 7 tokens, mean: 88.96 tokens, max: 256 tokens min: 7 tokens, mean: 90.66 tokens, max: 256 tokens min: 7 tokens, mean: 88.72 tokens, max: 256 tokens min: 7 tokens, mean: 93.31 tokens, max: 256 tokens min: 7 tokens, mean: 87.37 tokens, max: 256 tokens min: 7 tokens, mean: 91.06 tokens, max: 256 tokens min: 7 tokens, mean: 90.74 tokens, max: 256 tokens min: 6 tokens, mean: 85.83 tokens, max: 256 tokens min: 7 tokens, mean: 87.6 tokens, max: 256 tokens min: 7 tokens, mean: 87.71 tokens, max: 256 tokens min: 7 tokens, mean: 90.29 tokens, max: 256 tokens min: 7 tokens, mean: 91.09 tokens, max: 256 tokens min: 7 tokens, mean: 87.94 tokens, max: 256 tokens min: 7 tokens, mean: 90.81 tokens, max: 256 tokens min: 6 tokens, mean: 89.77 tokens, max: 256 tokens min: 7 tokens, mean: 84.67 tokens, max: 256 tokens min: 6 tokens, mean: 88.34 tokens, max: 256 tokens min: 7 tokens, mean: 87.25 tokens, max: 256 tokens min: 7 tokens, mean: 91.56 tokens, max: 256 tokens min: 7 tokens, mean: 90.43 tokens, max: 256 tokens min: 6 tokens, mean: 86.3 tokens, max: 256 tokens min: 6 tokens, mean: 92.18 tokens, max: 256 tokens min: 7 tokens, mean: 90.68 tokens, max: 256 tokens min: 6 tokens, mean: 90.08 tokens, max: 256 tokens min: 7 tokens, mean: 94.62 tokens, max: 256 tokens min: 7 tokens, mean: 89.4 tokens, max: 256 tokens min: 7 tokens, mean: 82.08 tokens, max: 256 tokens min: 7 tokens, mean: 87.92 tokens, max: 256 tokens min: 7 tokens, mean: 88.84 tokens, max: 256 tokens min: 7 tokens, mean: 89.72 tokens, max: 256 tokens min: 7 tokens, mean: 92.3 tokens, max: 256 tokens min: 6 tokens, mean: 87.56 tokens, max: 256 tokens min: 6 tokens, mean: 88.55 tokens, max: 256 tokens min: 7 tokens, mean: 90.84 tokens, max: 256 tokens min: 7 tokens, mean: 84.04 tokens, max: 256 tokens min: 7 tokens, mean: 91.26 tokens, max: 256 tokens min: 7 tokens, mean: 89.11 tokens, max: 256 tokens min: 6 tokens, mean: 93.41 tokens, max: 256 tokens min: 7 tokens, mean: 86.29 tokens, max: 256 tokens min: 7 tokens, mean: 87.78 tokens, max: 256 tokens min: 7 tokens, mean: 87.01 tokens, max: 256 tokens size: 100 elements - Samples:
query document negative_0 return boolean as string 'true' / 'false'function bool2str($bool) {<br> if($bool ===false)<br> return 'false';<br> else<br> return 'true';<br>}function bool_s($boolean) {<br> return ($boolean ? 'true' : 'false');<br>} - Loss:
pylate.losses.cached_contrastive.CachedContrastive
go
- Dataset: go at d821c55
- Size: 5,815,734 training samples
- Approximate statistics based on the first 1000 samples:
query document negative_0 negative_1 negative_2 negative_3 negative_4 negative_5 negative_6 negative_7 negative_8 negative_9 negative_10 negative_11 negative_12 negative_13 negative_14 negative_15 negative_16 negative_17 negative_18 negative_19 negative_20 negative_21 negative_22 negative_23 negative_24 negative_25 negative_26 negative_27 negative_28 negative_29 negative_30 negative_31 negative_32 negative_33 negative_34 negative_35 negative_36 negative_37 negative_38 negative_39 negative_40 negative_41 negative_42 negative_43 negative_44 negative_45 negative_46 negative_47 negative_48 negative_49 negative_50 negative_51 negative_52 negative_53 negative_54 negative_55 negative_56 negative_57 negative_58 negative_59 negative_60 negative_61 negative_62 negative_63 negative_64 negative_65 negative_66 negative_67 negative_68 negative_69 negative_70 negative_71 negative_72 negative_73 negative_74 negative_75 negative_76 negative_77 negative_78 negative_79 negative_80 negative_81 negative_82 negative_83 negative_84 negative_85 negative_86 negative_87 negative_88 negative_89 negative_90 negative_91 negative_92 negative_93 negative_94 negative_95 negative_96 negative_97 negative_98 negative_99 negative_scores type string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string list details min: 7 tokens, mean: 23.67 tokens, max: 217 tokens min: 13 tokens, mean: 109.68 tokens, max: 256 tokens min: 16 tokens, mean: 107.33 tokens, max: 256 tokens min: 12 tokens, mean: 102.9 tokens, max: 256 tokens min: 14 tokens, mean: 103.89 tokens, max: 256 tokens min: 10 tokens, mean: 106.78 tokens, max: 256 tokens min: 9 tokens, mean: 106.23 tokens, max: 256 tokens min: 9 tokens, mean: 106.45 tokens, max: 256 tokens min: 9 tokens, mean: 107.99 tokens, max: 256 tokens min: 9 tokens, mean: 104.84 tokens, max: 256 tokens min: 12 tokens, mean: 106.47 tokens, max: 256 tokens min: 11 tokens, mean: 105.55 tokens, max: 256 tokens min: 10 tokens, mean: 108.57 tokens, max: 256 tokens min: 12 tokens, mean: 108.62 tokens, max: 256 tokens min: 12 tokens, mean: 110.55 tokens, max: 256 tokens min: 12 tokens, mean: 106.26 tokens, max: 256 tokens min: 12 tokens, mean: 106.64 tokens, max: 256 tokens min: 14 tokens, mean: 106.96 tokens, max: 256 tokens min: 11 tokens, mean: 103.05 tokens, max: 256 tokens min: 9 tokens, mean: 107.45 tokens, max: 256 tokens min: 13 tokens, mean: 105.3 tokens, max: 256 tokens min: 15 tokens, mean: 105.44 tokens, max: 256 tokens min: 12 tokens, mean: 104.67 tokens, max: 256 tokens min: 13 tokens, mean: 111.42 tokens, max: 256 tokens min: 15 tokens, mean: 107.38 tokens, max: 256 tokens min: 10 tokens, mean: 107.34 tokens, max: 256 tokens min: 10 tokens, mean: 102.53 tokens, max: 256 tokens min: 10 tokens, mean: 108.49 tokens, max: 256 tokens min: 10 tokens, mean: 111.58 tokens, max: 256 tokens min: 12 tokens, mean: 105.18 tokens, max: 256 tokens min: 12 tokens, mean: 108.69 tokens, max: 256 tokens min: 15 tokens, mean: 108.0 tokens, max: 256 tokens min: 12 tokens, mean: 105.84 tokens, max: 256 tokens min: 10 tokens, mean: 106.44 tokens, max: 256 tokens min: 13 tokens, mean: 105.24 tokens, max: 256 tokens min: 13 tokens, mean: 104.68 tokens, max: 256 tokens min: 11 tokens, mean: 106.39 tokens, max: 256 tokens min: 14 tokens, mean: 105.06 tokens, max: 256 tokens min: 13 tokens, mean: 107.31 tokens, max: 256 tokens min: 11 tokens, mean: 110.77 tokens, max: 256 tokens min: 11 tokens, mean: 106.06 tokens, max: 256 tokens min: 16 tokens, mean: 109.77 tokens, max: 256 tokens min: 16 tokens, mean: 109.91 tokens, max: 256 tokens min: 10 tokens, mean: 108.52 tokens, max: 256 tokens min: 11 tokens, mean: 110.54 tokens, max: 256 tokens min: 15 tokens, mean: 107.61 tokens, max: 256 tokens min: 13 tokens, mean: 108.65 tokens, max: 256 tokens min: 12 tokens, mean: 106.42 tokens, max: 256 tokens min: 10 tokens, mean: 105.84 tokens, max: 256 tokens min: 11 tokens, mean: 111.49 tokens, max: 256 tokens min: 11 tokens, mean: 108.21 tokens, max: 256 tokens min: 11 tokens, mean: 104.42 tokens, max: 256 tokens min: 8 tokens, mean: 112.23 tokens, max: 256 tokens min: 14 tokens, mean: 109.97 tokens, max: 256 tokens min: 8 tokens, mean: 108.53 tokens, max: 256 tokens min: 14 tokens, mean: 103.8 tokens, max: 256 tokens min: 14 tokens, mean: 108.26 tokens, max: 256 tokens min: 13 tokens, mean: 104.47 tokens, max: 256 tokens min: 13 tokens, mean: 109.63 tokens, max: 256 tokens min: 10 tokens, mean: 107.78 tokens, max: 256 tokens min: 12 tokens, mean: 107.51 tokens, max: 256 tokens min: 14 tokens, mean: 106.38 tokens, max: 256 tokens min: 10 tokens, mean: 111.95 tokens, max: 256 tokens min: 11 tokens, mean: 108.62 tokens, max: 256 tokens min: 13 tokens, mean: 108.69 tokens, max: 256 tokens min: 12 tokens, mean: 110.8 tokens, max: 256 tokens min: 14 tokens, mean: 105.22 tokens, max: 256 tokens min: 14 tokens, mean: 108.6 tokens, max: 256 tokens min: 14 tokens, mean: 111.24 tokens, max: 256 tokens min: 13 tokens, mean: 106.55 tokens, max: 256 tokens min: 13 tokens, mean: 110.18 tokens, max: 256 tokens min: 12 tokens, mean: 110.22 tokens, max: 256 tokens min: 12 tokens, mean: 111.2 tokens, max: 256 tokens min: 12 tokens, mean: 110.16 tokens, max: 256 tokens min: 14 tokens, mean: 108.52 tokens, max: 256 tokens min: 13 tokens, mean: 110.53 tokens, max: 256 tokens min: 15 tokens, mean: 111.13 tokens, max: 256 tokens min: 14 tokens, mean: 104.19 tokens, max: 256 tokens min: 9 tokens, mean: 108.67 tokens, max: 256 tokens min: 11 tokens, mean: 111.0 tokens, max: 256 tokens min: 14 tokens, mean: 110.76 tokens, max: 256 tokens min: 13 tokens, mean: 109.73 tokens, max: 256 tokens min: 12 tokens, mean: 105.15 tokens, max: 256 tokens min: 14 tokens, mean: 111.64 tokens, max: 256 tokens min: 6 tokens, mean: 108.8 tokens, max: 256 tokens min: 13 tokens, mean: 110.11 tokens, max: 256 tokens min: 7 tokens, mean: 105.51 tokens, max: 256 tokens min: 11 tokens, mean: 108.64 tokens, max: 256 tokens min: 15 tokens, mean: 105.54 tokens, max: 256 tokens min: 10 tokens, mean: 107.4 tokens, max: 256 tokens min: 12 tokens, mean: 108.55 tokens, max: 256 tokens min: 13 tokens, mean: 108.38 tokens, max: 256 tokens min: 16 tokens, mean: 110.22 tokens, max: 256 tokens min: 15 tokens, mean: 112.5 tokens, max: 256 tokens min: 12 tokens, mean: 108.49 tokens, max: 256 tokens min: 15 tokens, mean: 109.87 tokens, max: 256 tokens min: 12 tokens, mean: 108.58 tokens, max: 256 tokens min: 14 tokens, mean: 111.7 tokens, max: 256 tokens min: 16 tokens, mean: 111.45 tokens, max: 256 tokens min: 9 tokens, mean: 110.57 tokens, max: 256 tokens min: 12 tokens, mean: 107.72 tokens, max: 256 tokens min: 14 tokens, mean: 110.13 tokens, max: 256 tokens size: 100 elements - Samples:
query document negative_0 Returns the value of the 'go_package' option of the first .proto file found in the same directory as projectFilefunc detectGoPackageForProject(projectFile string) (string, error) {<br> var goPkg string<br> projectDir := filepath.Dir(projectFile)<br> if err := filepath.Walk(projectDir, func(protoFile string, info os.FileInfo, err error) error {<br> // already set<br> if goPkg != "" {<br> return nil<br> }<br> if !strings.HasSuffix(protoFile, ".proto") {<br> return nil<br> }<br> // search for go_package on protos in the same dir as the project.json<br> if projectDir != filepath.Dir(protoFile) {<br> return nil<br> }<br> content, err := ioutil.ReadFile(protoFile)<br> if err != nil {<br> return err<br> }<br> lines := strings.Split(string(content), "\n")<br> for _, line := range lines {<br> goPackage := goPackageStatementRegex.FindStringSubmatch(line)<br> if len(goPackage) == 0 {<br> continue<br> }<br> if len(goPackage) != 2 {<br> return errors.Errorf("parsing go_package error: from %v found %v", line, goPackage)<br> }<br> goPkg = goPackage[1]<br> break<br> }<br> return nil<br> }); err != nil {<br> return "", err<br> }<br> if goPkg == "" {<br> return "", errors.Er...func (g *Generator) GoFilePackage(depfile *fdep.DepFile) string {<br> return fproto_wrap.BaseName(g.GoWrapPackage(depfile))<br>} - Loss:
pylate.losses.cached_contrastive.CachedContrastive
ruby
- Dataset: ruby at d821c55
- Size: 631,161 training samples
- Approximate statistics based on the first 1000 samples:
query document negative_0 negative_1 negative_2 negative_3 negative_4 negative_5 negative_6 negative_7 negative_8 negative_9 negative_10 negative_11 negative_12 negative_13 negative_14 negative_15 negative_16 negative_17 negative_18 negative_19 negative_20 negative_21 negative_22 negative_23 negative_24 negative_25 negative_26 negative_27 negative_28 negative_29 negative_30 negative_31 negative_32 negative_33 negative_34 negative_35 negative_36 negative_37 negative_38 negative_39 negative_40 negative_41 negative_42 negative_43 negative_44 negative_45 negative_46 negative_47 negative_48 negative_49 negative_50 negative_51 negative_52 negative_53 negative_54 negative_55 negative_56 negative_57 negative_58 negative_59 negative_60 negative_61 negative_62 negative_63 negative_64 negative_65 negative_66 negative_67 negative_68 negative_69 negative_70 negative_71 negative_72 negative_73 negative_74 negative_75 negative_76 negative_77 negative_78 negative_79 negative_80 negative_81 negative_82 negative_83 negative_84 negative_85 negative_86 negative_87 negative_88 negative_89 negative_90 negative_91 negative_92 negative_93 negative_94 negative_95 negative_96 negative_97 negative_98 negative_99 negative_scores type string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string list details min: 7 tokens, mean: 27.46 tokens, max: 256 tokens min: 8 tokens, mean: 81.82 tokens, max: 256 tokens min: 7 tokens, mean: 69.28 tokens, max: 256 tokens min: 7 tokens, mean: 70.87 tokens, max: 256 tokens min: 7 tokens, mean: 68.13 tokens, max: 256 tokens min: 7 tokens, mean: 70.04 tokens, max: 256 tokens min: 7 tokens, mean: 65.91 tokens, max: 256 tokens min: 7 tokens, mean: 69.42 tokens, max: 256 tokens min: 7 tokens, mean: 67.64 tokens, max: 256 tokens min: 7 tokens, mean: 68.89 tokens, max: 256 tokens min: 7 tokens, mean: 70.62 tokens, max: 256 tokens min: 7 tokens, mean: 70.05 tokens, max: 256 tokens min: 7 tokens, mean: 73.0 tokens, max: 256 tokens min: 7 tokens, mean: 68.58 tokens, max: 256 tokens min: 7 tokens, mean: 71.39 tokens, max: 256 tokens min: 7 tokens, mean: 72.31 tokens, max: 256 tokens min: 7 tokens, mean: 69.39 tokens, max: 256 tokens min: 7 tokens, mean: 71.65 tokens, max: 256 tokens min: 7 tokens, mean: 70.94 tokens, max: 256 tokens min: 7 tokens, mean: 68.46 tokens, max: 256 tokens min: 7 tokens, mean: 67.78 tokens, max: 256 tokens min: 7 tokens, mean: 70.1 tokens, max: 256 tokens min: 7 tokens, mean: 71.75 tokens, max: 256 tokens min: 7 tokens, mean: 72.49 tokens, max: 256 tokens min: 7 tokens, mean: 69.72 tokens, max: 256 tokens min: 7 tokens, mean: 70.09 tokens, max: 256 tokens min: 7 tokens, mean: 70.19 tokens, max: 256 tokens min: 7 tokens, mean: 72.2 tokens, max: 256 tokens min: 7 tokens, mean: 72.02 tokens, max: 256 tokens min: 7 tokens, mean: 70.91 tokens, max: 256 tokens min: 7 tokens, mean: 73.2 tokens, max: 256 tokens min: 7 tokens, mean: 71.11 tokens, max: 256 tokens min: 7 tokens, mean: 70.94 tokens, max: 256 tokens min: 7 tokens, mean: 74.89 tokens, max: 256 tokens min: 7 tokens, mean: 69.67 tokens, max: 256 tokens min: 7 tokens, mean: 71.91 tokens, max: 256 tokens min: 7 tokens, mean: 71.25 tokens, max: 256 tokens min: 7 tokens, mean: 71.58 tokens, max: 256 tokens min: 7 tokens, mean: 72.9 tokens, max: 256 tokens min: 7 tokens, mean: 75.1 tokens, max: 256 tokens min: 7 tokens, mean: 74.55 tokens, max: 256 tokens min: 7 tokens, mean: 77.13 tokens, max: 256 tokens min: 7 tokens, mean: 73.25 tokens, max: 256 tokens min: 7 tokens, mean: 68.97 tokens, max: 256 tokens min: 7 tokens, mean: 72.48 tokens, max: 256 tokens min: 7 tokens, mean: 72.67 tokens, max: 256 tokens min: 7 tokens, mean: 74.04 tokens, max: 256 tokens min: 7 tokens, mean: 70.5 tokens, max: 256 tokens min: 7 tokens, mean: 72.2 tokens, max: 256 tokens min: 7 tokens, mean: 73.39 tokens, max: 256 tokens min: 7 tokens, mean: 73.69 tokens, max: 256 tokens min: 7 tokens, mean: 71.32 tokens, max: 256 tokens min: 7 tokens, mean: 74.51 tokens, max: 256 tokens min: 7 tokens, mean: 72.13 tokens, max: 256 tokens min: 7 tokens, mean: 75.34 tokens, max: 256 tokens min: 7 tokens, mean: 75.59 tokens, max: 256 tokens min: 7 tokens, mean: 72.12 tokens, max: 256 tokens min: 7 tokens, mean: 73.14 tokens, max: 256 tokens min: 7 tokens, mean: 76.15 tokens, max: 256 tokens min: 7 tokens, mean: 73.08 tokens, max: 256 tokens min: 7 tokens, mean: 75.75 tokens, max: 256 tokens min: 7 tokens, mean: 72.52 tokens, max: 256 tokens min: 7 tokens, mean: 70.75 tokens, max: 256 tokens min: 7 tokens, mean: 69.18 tokens, max: 256 tokens min: 7 tokens, mean: 70.06 tokens, max: 256 tokens min: 7 tokens, mean: 72.35 tokens, max: 256 tokens min: 7 tokens, mean: 73.01 tokens, max: 256 tokens min: 7 tokens, mean: 72.39 tokens, max: 256 tokens min: 7 tokens, mean: 73.27 tokens, max: 256 tokens min: 7 tokens, mean: 72.95 tokens, max: 256 tokens min: 7 tokens, mean: 72.0 tokens, max: 256 tokens min: 7 tokens, mean: 71.09 tokens, max: 256 tokens min: 7 tokens, mean: 71.23 tokens, max: 256 tokens min: 7 tokens, mean: 72.0 tokens, max: 256 tokens min: 7 tokens, mean: 72.24 tokens, max: 256 tokens min: 7 tokens, mean: 73.3 tokens, max: 256 tokens min: 7 tokens, mean: 74.85 tokens, max: 256 tokens min: 7 tokens, mean: 72.45 tokens, max: 256 tokens min: 7 tokens, mean: 75.66 tokens, max: 256 tokens min: 7 tokens, mean: 75.36 tokens, max: 256 tokens min: 7 tokens, mean: 71.31 tokens, max: 256 tokens min: 7 tokens, mean: 72.53 tokens, max: 256 tokens min: 7 tokens, mean: 70.6 tokens, max: 256 tokens min: 7 tokens, mean: 72.82 tokens, max: 256 tokens min: 7 tokens, mean: 72.79 tokens, max: 256 tokens min: 7 tokens, mean: 72.75 tokens, max: 256 tokens min: 7 tokens, mean: 72.92 tokens, max: 256 tokens min: 7 tokens, mean: 74.62 tokens, max: 256 tokens min: 7 tokens, mean: 73.26 tokens, max: 256 tokens min: 7 tokens, mean: 72.5 tokens, max: 256 tokens min: 7 tokens, mean: 72.96 tokens, max: 256 tokens min: 7 tokens, mean: 69.5 tokens, max: 256 tokens min: 7 tokens, mean: 71.73 tokens, max: 256 tokens min: 7 tokens, mean: 71.43 tokens, max: 256 tokens min: 7 tokens, mean: 72.52 tokens, max: 256 tokens min: 7 tokens, mean: 70.29 tokens, max: 256 tokens min: 7 tokens, mean: 73.48 tokens, max: 256 tokens min: 7 tokens, mean: 73.07 tokens, max: 256 tokens min: 7 tokens, mean: 73.89 tokens, max: 256 tokens min: 7 tokens, mean: 73.68 tokens, max: 256 tokens min: 7 tokens, mean: 74.27 tokens, max: 256 tokens min: 7 tokens, mean: 75.13 tokens, max: 256 tokens size: 100 elements - Samples:
query document negative_0 GET /property_between_floor_slaps GET /property_between_floor_slaps.jsondef index<br> @property_between_floor_slaps = PropertyBetweenFloorSlap.all<br> enddef set_property_between_floor_slap<br> @property_between_floor_slap = PropertyBetweenFloorSlap.find(params[:id])<br> end - Loss:
pylate.losses.cached_contrastive.CachedContrastive
javascript
- Dataset: javascript at d821c55
- Size: 1,386,353 training samples
- Approximate statistics based on the first 1000 samples:
query document negative_0 negative_1 negative_2 negative_3 negative_4 negative_5 negative_6 negative_7 negative_8 negative_9 negative_10 negative_11 negative_12 negative_13 negative_14 negative_15 negative_16 negative_17 negative_18 negative_19 negative_20 negative_21 negative_22 negative_23 negative_24 negative_25 negative_26 negative_27 negative_28 negative_29 negative_30 negative_31 negative_32 negative_33 negative_34 negative_35 negative_36 negative_37 negative_38 negative_39 negative_40 negative_41 negative_42 negative_43 negative_44 negative_45 negative_46 negative_47 negative_48 negative_49 negative_50 negative_51 negative_52 negative_53 negative_54 negative_55 negative_56 negative_57 negative_58 negative_59 negative_60 negative_61 negative_62 negative_63 negative_64 negative_65 negative_66 negative_67 negative_68 negative_69 negative_70 negative_71 negative_72 negative_73 negative_74 negative_75 negative_76 negative_77 negative_78 negative_79 negative_80 negative_81 negative_82 negative_83 negative_84 negative_85 negative_86 negative_87 negative_88 negative_89 negative_90 negative_91 negative_92 negative_93 negative_94 negative_95 negative_96 negative_97 negative_98 negative_99 negative_scores type string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string list details min: 7 tokens, mean: 23.61 tokens, max: 256 tokens min: 9 tokens, mean: 122.61 tokens, max: 256 tokens min: 7 tokens, mean: 108.12 tokens, max: 256 tokens min: 6 tokens, mean: 112.04 tokens, max: 256 tokens min: 6 tokens, mean: 109.22 tokens, max: 256 tokens min: 7 tokens, mean: 110.62 tokens, max: 256 tokens min: 7 tokens, mean: 109.77 tokens, max: 256 tokens min: 6 tokens, mean: 112.58 tokens, max: 256 tokens min: 6 tokens, mean: 108.78 tokens, max: 256 tokens min: 6 tokens, mean: 108.21 tokens, max: 256 tokens min: 7 tokens, mean: 111.04 tokens, max: 256 tokens min: 6 tokens, mean: 108.05 tokens, max: 256 tokens min: 7 tokens, mean: 108.58 tokens, max: 256 tokens min: 6 tokens, mean: 110.81 tokens, max: 256 tokens min: 6 tokens, mean: 110.29 tokens, max: 256 tokens min: 7 tokens, mean: 108.2 tokens, max: 256 tokens min: 7 tokens, mean: 109.19 tokens, max: 256 tokens min: 6 tokens, mean: 111.03 tokens, max: 256 tokens min: 6 tokens, mean: 111.45 tokens, max: 256 tokens min: 6 tokens, mean: 110.48 tokens, max: 256 tokens min: 6 tokens, mean: 110.37 tokens, max: 256 tokens min: 7 tokens, mean: 114.22 tokens, max: 256 tokens min: 7 tokens, mean: 112.62 tokens, max: 256 tokens min: 7 tokens, mean: 113.8 tokens, max: 256 tokens min: 7 tokens, mean: 110.23 tokens, max: 256 tokens min: 7 tokens, mean: 112.49 tokens, max: 256 tokens min: 7 tokens, mean: 109.46 tokens, max: 256 tokens min: 7 tokens, mean: 113.62 tokens, max: 256 tokens min: 7 tokens, mean: 108.73 tokens, max: 256 tokens min: 7 tokens, mean: 107.68 tokens, max: 256 tokens min: 7 tokens, mean: 112.89 tokens, max: 256 tokens min: 6 tokens, mean: 110.91 tokens, max: 256 tokens min: 6 tokens, mean: 107.13 tokens, max: 256 tokens min: 6 tokens, mean: 110.15 tokens, max: 256 tokens min: 6 tokens, mean: 111.73 tokens, max: 256 tokens min: 6 tokens, mean: 113.99 tokens, max: 256 tokens min: 7 tokens, mean: 110.67 tokens, max: 256 tokens min: 7 tokens, mean: 115.34 tokens, max: 256 tokens min: 7 tokens, mean: 111.74 tokens, max: 256 tokens min: 6 tokens, mean: 115.7 tokens, max: 256 tokens min: 6 tokens, mean: 116.1 tokens, max: 256 tokens min: 6 tokens, mean: 114.03 tokens, max: 256 tokens min: 6 tokens, mean: 114.13 tokens, max: 256 tokens min: 6 tokens, mean: 115.99 tokens, max: 256 tokens min: 6 tokens, mean: 113.55 tokens, max: 256 tokens min: 7 tokens, mean: 116.25 tokens, max: 256 tokens min: 7 tokens, mean: 114.8 tokens, max: 256 tokens min: 8 tokens, mean: 114.66 tokens, max: 256 tokens min: 6 tokens, mean: 112.9 tokens, max: 256 tokens min: 7 tokens, mean: 112.67 tokens, max: 256 tokens min: 8 tokens, mean: 112.66 tokens, max: 256 tokens min: 6 tokens, mean: 112.93 tokens, max: 256 tokens min: 6 tokens, mean: 112.36 tokens, max: 256 tokens min: 7 tokens, mean: 115.37 tokens, max: 256 tokens min: 7 tokens, mean: 116.0 tokens, max: 256 tokens min: 7 tokens, mean: 117.86 tokens, max: 256 tokens min: 6 tokens, mean: 112.58 tokens, max: 256 tokens min: 6 tokens, mean: 112.56 tokens, max: 256 tokens min: 6 tokens, mean: 110.88 tokens, max: 256 tokens min: 6 tokens, mean: 111.73 tokens, max: 256 tokens min: 7 tokens, mean: 112.62 tokens, max: 256 tokens min: 7 tokens, mean: 117.56 tokens, max: 256 tokens min: 6 tokens, mean: 110.65 tokens, max: 256 tokens min: 6 tokens, mean: 116.67 tokens, max: 256 tokens min: 6 tokens, mean: 120.18 tokens, max: 256 tokens min: 6 tokens, mean: 113.18 tokens, max: 256 tokens min: 6 tokens, mean: 111.28 tokens, max: 256 tokens min: 6 tokens, mean: 112.35 tokens, max: 256 tokens min: 6 tokens, mean: 115.84 tokens, max: 256 tokens min: 6 tokens, mean: 107.41 tokens, max: 256 tokens min: 6 tokens, mean: 112.68 tokens, max: 256 tokens min: 6 tokens, mean: 113.94 tokens, max: 256 tokens min: 6 tokens, mean: 115.98 tokens, max: 256 tokens min: 6 tokens, mean: 115.12 tokens, max: 256 tokens min: 6 tokens, mean: 117.5 tokens, max: 256 tokens min: 7 tokens, mean: 110.15 tokens, max: 256 tokens min: 7 tokens, mean: 111.66 tokens, max: 256 tokens min: 6 tokens, mean: 114.64 tokens, max: 256 tokens min: 7 tokens, mean: 115.12 tokens, max: 256 tokens min: 7 tokens, mean: 114.63 tokens, max: 256 tokens min: 6 tokens, mean: 114.87 tokens, max: 256 tokens min: 6 tokens, mean: 113.57 tokens, max: 256 tokens min: 6 tokens, mean: 112.34 tokens, max: 256 tokens min: 7 tokens, mean: 114.15 tokens, max: 256 tokens min: 7 tokens, mean: 110.8 tokens, max: 256 tokens min: 7 tokens, mean: 115.0 tokens, max: 256 tokens min: 7 tokens, mean: 115.64 tokens, max: 256 tokens min: 7 tokens, mean: 113.33 tokens, max: 256 tokens min: 7 tokens, mean: 114.12 tokens, max: 256 tokens min: 7 tokens, mean: 116.79 tokens, max: 256 tokens min: 7 tokens, mean: 113.86 tokens, max: 256 tokens min: 7 tokens, mean: 114.26 tokens, max: 256 tokens min: 6 tokens, mean: 112.31 tokens, max: 256 tokens min: 6 tokens, mean: 114.21 tokens, max: 256 tokens min: 7 tokens, mean: 117.53 tokens, max: 256 tokens min: 6 tokens, mean: 115.43 tokens, max: 256 tokens min: 6 tokens, mean: 116.28 tokens, max: 256 tokens min: 6 tokens, mean: 113.86 tokens, max: 256 tokens min: 6 tokens, mean: 114.42 tokens, max: 256 tokens min: 6 tokens, mean: 112.08 tokens, max: 256 tokens min: 6 tokens, mean: 115.86 tokens, max: 256 tokens min: 7 tokens, mean: 115.5 tokens, max: 256 tokens size: 100 elements - Samples:
query document negative_0 Example binToHex(["0111110", "1000000", "1000000", "1111110", "1000001", "1000001", "0111110"])function binToHex(bins) {<br> return bins.map(bin => ("00" + (parseInt(bin, 2).toString(16))).substr(-2).toUpperCase()).join("");<br>}function binToHex(a) {<br> var newVal = "";<br> for (i = 0; i < a.length/8; i++)<br> newVal += ("00" + parseInt(a.slice(8i, 8i+8),2).toString(16)).slice(-2);<br> return newVal;<br>} - Loss:
pylate.losses.cached_contrastive.CachedContrastive
java
- Dataset: java at d821c55
- Size: 4,103,086 training samples
- Approximate statistics based on the first 1000 samples:
query document negative_0 negative_1 negative_2 negative_3 negative_4 negative_5 negative_6 negative_7 negative_8 negative_9 negative_10 negative_11 negative_12 negative_13 negative_14 negative_15 negative_16 negative_17 negative_18 negative_19 negative_20 negative_21 negative_22 negative_23 negative_24 negative_25 negative_26 negative_27 negative_28 negative_29 negative_30 negative_31 negative_32 negative_33 negative_34 negative_35 negative_36 negative_37 negative_38 negative_39 negative_40 negative_41 negative_42 negative_43 negative_44 negative_45 negative_46 negative_47 negative_48 negative_49 negative_50 negative_51 negative_52 negative_53 negative_54 negative_55 negative_56 negative_57 negative_58 negative_59 negative_60 negative_61 negative_62 negative_63 negative_64 negative_65 negative_66 negative_67 negative_68 negative_69 negative_70 negative_71 negative_72 negative_73 negative_74 negative_75 negative_76 negative_77 negative_78 negative_79 negative_80 negative_81 negative_82 negative_83 negative_84 negative_85 negative_86 negative_87 negative_88 negative_89 negative_90 negative_91 negative_92 negative_93 negative_94 negative_95 negative_96 negative_97 negative_98 negative_99 negative_scores type string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string string list details min: 7 tokens, mean: 21.93 tokens, max: 256 tokens min: 7 tokens, mean: 77.23 tokens, max: 256 tokens min: 6 tokens, mean: 71.27 tokens, max: 256 tokens min: 6 tokens, mean: 69.49 tokens, max: 256 tokens min: 6 tokens, mean: 72.21 tokens, max: 256 tokens min: 6 tokens, mean: 68.86 tokens, max: 256 tokens min: 6 tokens, mean: 70.93 tokens, max: 256 tokens min: 6 tokens, mean: 67.48 tokens, max: 256 tokens min: 6 tokens, mean: 69.5 tokens, max: 256 tokens min: 6 tokens, mean: 71.93 tokens, max: 256 tokens min: 7 tokens, mean: 69.65 tokens, max: 256 tokens min: 6 tokens, mean: 74.01 tokens, max: 256 tokens min: 6 tokens, mean: 69.52 tokens, max: 256 tokens min: 6 tokens, mean: 76.13 tokens, max: 256 tokens min: 6 tokens, mean: 69.41 tokens, max: 256 tokens min: 6 tokens, mean: 74.8 tokens, max: 256 tokens min: 6 tokens, mean: 74.64 tokens, max: 256 tokens min: 6 tokens, mean: 69.87 tokens, max: 256 tokens min: 6 tokens, mean: 73.56 tokens, max: 256 tokens min: 6 tokens, mean: 75.1 tokens, max: 256 tokens min: 6 tokens, mean: 72.11 tokens, max: 256 tokens min: 6 tokens, mean: 73.47 tokens, max: 256 tokens min: 6 tokens, mean: 73.88 tokens, max: 256 tokens min: 6 tokens, mean: 73.89 tokens, max: 256 tokens min: 7 tokens, mean: 74.63 tokens, max: 256 tokens min: 6 tokens, mean: 73.94 tokens, max: 256 tokens min: 6 tokens, mean: 74.29 tokens, max: 256 tokens min: 6 tokens, mean: 73.66 tokens, max: 256 tokens min: 6 tokens, mean: 73.94 tokens, max: 256 tokens min: 6 tokens, mean: 73.71 tokens, max: 256 tokens min: 6 tokens, mean: 76.59 tokens, max: 256 tokens min: 6 tokens, mean: 73.44 tokens, max: 256 tokens min: 6 tokens, mean: 73.41 tokens, max: 256 tokens min: 6 tokens, mean: 73.11 tokens, max: 256 tokens min: 6 tokens, mean: 73.49 tokens, max: 256 tokens min: 6 tokens, mean: 74.49 tokens, max: 256 tokens min: 6 tokens, mean: 75.75 tokens, max: 256 tokens min: 6 tokens, mean: 71.11 tokens, max: 256 tokens min: 6 tokens, mean: 72.25 tokens, max: 256 tokens min: 6 tokens, mean: 74.47 tokens, max: 256 tokens min: 7 tokens, mean: 75.86 tokens, max: 256 tokens min: 7 tokens, mean: 73.47 tokens, max: 256 tokens min: 7 tokens, mean: 76.36 tokens, max: 256 tokens min: 6 tokens, mean: 79.31 tokens, max: 256 tokens min: 6 tokens, mean: 74.5 tokens, max: 256 tokens min: 6 tokens, mean: 75.54 tokens, max: 256 tokens min: 6 tokens, mean: 77.99 tokens, max: 256 tokens min: 6 tokens, mean: 76.56 tokens, max: 256 tokens min: 6 tokens, mean: 74.27 tokens, max: 256 tokens min: 6 tokens, mean: 77.28 tokens, max: 256 tokens min: 6 tokens, mean: 76.97 tokens, max: 256 tokens min: 6 tokens, mean: 76.73 tokens, max: 256 tokens min: 6 tokens, mean: 70.69 tokens, max: 256 tokens min: 6 tokens, mean: 75.53 tokens, max: 256 tokens min: 6 tokens, mean: 73.91 tokens, max: 256 tokens min: 6 tokens, mean: 76.89 tokens, max: 256 tokens min: 6 tokens, mean: 73.97 tokens, max: 256 tokens min: 6 tokens, mean: 74.69 tokens, max: 256 tokens min: 6 tokens, mean: 75.5 tokens, max: 256 tokens min: 6 tokens, mean: 72.88 tokens, max: 256 tokens min: 6 tokens, mean: 76.94 tokens, max: 256 tokens min: 6 tokens, mean: 77.67 tokens, max: 256 tokens min: 6 tokens, mean: 76.24 tokens, max: 256 tokens min: 6 tokens, mean: 77.79 tokens, max: 256 tokens min: 6 tokens, mean: 75.04 tokens, max: 256 tokens min: 6 tokens, mean: 75.43 tokens, max: 256 tokens min: 6 tokens, mean: 74.78 tokens, max: 256 tokens min: 6 tokens, mean: 77.16 tokens, max: 256 tokens min: 6 tokens, mean: 75.1 tokens, max: 256 tokens min: 6 tokens, mean: 77.79 tokens, max: 256 tokens min: 6 tokens, mean: 72.59 tokens, max: 256 tokens min: 6 tokens, mean: 77.14 tokens, max: 256 tokens min: 6 tokens, mean: 73.62 tokens, max: 256 tokens min: 6 tokens, mean: 82.23 tokens, max: 256 tokens min: 6 tokens, mean: 75.65 tokens, max: 256 tokens min: 6 tokens, mean: 76.31 tokens, max: 256 tokens min: 6 tokens, mean: 76.04 tokens, max: 256 tokens min: 6 tokens, mean: 74.85 tokens, max: 256 tokens min: 6 tokens, mean: 78.05 tokens, max: 256 tokens min: 6 tokens, mean: 76.59 tokens, max: 256 tokens min: 6 tokens, mean: 78.1 tokens, max: 256 tokens min: 6 tokens, mean: 76.14 tokens, max: 256 tokens min: 6 tokens, mean: 73.1 tokens, max: 256 tokens min: 6 tokens, mean: 75.61 tokens, max: 256 tokens min: 6 tokens, mean: 75.79 tokens, max: 256 tokens min: 6 tokens, mean: 77.7 tokens, max: 256 tokens min: 6 tokens, mean: 75.6 tokens, max: 256 tokens min: 6 tokens, mean: 77.71 tokens, max: 256 tokens min: 6 tokens, mean: 75.1 tokens, max: 256 tokens min: 6 tokens, mean: 75.92 tokens, max: 256 tokens min: 6 tokens, mean: 76.13 tokens, max: 256 tokens min: 6 tokens, mean: 79.2 tokens, max: 256 tokens min: 6 tokens, mean: 76.79 tokens, max: 256 tokens min: 6 tokens, mean: 73.95 tokens, max: 256 tokens min: 6 tokens, mean: 76.74 tokens, max: 256 tokens min: 6 tokens, mean: 76.28 tokens, max: 256 tokens min: 6 tokens, mean: 75.48 tokens, max: 256 tokens min: 6 tokens, mean: 80.97 tokens, max: 256 tokens min: 6 tokens, mean: 73.05 tokens, max: 256 tokens min: 6 tokens, mean: 78.6 tokens, max: 256 tokens min: 6 tokens, mean: 79.92 tokens, max: 256 tokens min: 6 tokens, mean: 74.14 tokens, max: 256 tokens size: 100 elements - Samples:
query document negative_0 private void signSetter(String[] lines, Player p, Block s)private void signSetter(Block b, Player p, String[] lines) <br> { <br> //TODO: virer debug<br> //p.sendMessage("dbg1");<br> <br> <br> if(b==null) <br> return;<br> <br> BoutiqueSign bs = new BoutiqueSign();<br> <br> bs.setOwner(p);<br> bs.setLocation(b.getLocation());<br> bs.setLines(lines);<br><br> //TODO: virer debug<br> /*<br> p.sendMessage("dbg1 : line1 = " + bs.getLine1());<br> p.sendMessage("dbg1 : line2 = " + bs.getLine2());<br> p.sendMessage("dbg1 : line3 = " + bs.getLine3());<br> p.sendMessage("dbg1 : line4 = " + bs.getLine4()); <br> p.sendMessage("dbg2 : type = " + bs.getType());<br> */<br> <br> if(bs.isSignServer())<br> {<br> <br> if (!PermissionsHandler.canSetGlobalSign(p))<br> {<br> p.sendMessage(PermissionsHandler.permissionErr);<br> return;<br> }<br> <br> if(!bs.checkLines(p))<br> {<br> return;<br> }<br> <br> p.sendMessage(plugin.chatPrefix + Messages.getString("Sign.SERVERSIGNADDED")); //$NON-NLS-1$<br> }<br> <br> else if(bs.isSignChest())<br> {<br> if (!PermissionsHandler.canSetPersonalSign(p))<br> {<br> p.sendMessage(plugin.chatPrefix +...void updateSignToPlayer(Player player, Location location, String[] lines); - Loss:
pylate.losses.cached_contrastive.CachedContrastive
Training Hyperparameters
Non-Default Hyperparameters
eval_strategy: stepsper_device_train_batch_size: 128per_device_eval_batch_size: 128learning_rate: 8e-06num_train_epochs: 1bf16: Truedataloader_num_workers: 8accelerator_config: {'split_batches': True, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
All Hyperparameters
Click to expand
overwrite_output_dir: Falsedo_predict: Falseeval_strategy: stepsprediction_loss_only: Trueper_device_train_batch_size: 128per_device_eval_batch_size: 128per_gpu_train_batch_size: Noneper_gpu_eval_batch_size: Nonegradient_accumulation_steps: 1eval_accumulation_steps: Nonetorch_empty_cache_steps: Nonelearning_rate: 8e-06weight_decay: 0.0adam_beta1: 0.9adam_beta2: 0.999adam_epsilon: 1e-08max_grad_norm: 1.0num_train_epochs: 1max_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: Falseuse_ipex: Falsebf16: Truefp16: Falsefp16_opt_level: O1half_precision_backend: autobf16_full_eval: Falsefp16_full_eval: Falsetf32: Nonelocal_rank: 2ddp_backend: Nonetpu_num_cores: Nonetpu_metrics_debug: Falsedebug: []dataloader_drop_last: Truedataloader_num_workers: 8dataloader_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': True, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}deepspeed: Nonelabel_smoothing_factor: 0.0optim: adamw_torchoptim_args: Noneadafactor: Falsegroup_by_length: Falselength_column_name: lengthddp_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: Falsegradient_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: Falseneftune_noise_alpha: Noneoptim_target_modules: Nonebatch_eval_metrics: Falseeval_on_start: Falseuse_liger_kernel: Falseeval_use_gather_object: Falseaverage_tokens_across_devices: Falseprompts: Nonebatch_sampler: batch_samplermulti_dataset_batch_sampler: proportionalrouter_mapping: {}learning_rate_mapping: {}
Training Logs
Click to expand
| Epoch | Step | Training Loss | CodeSearchNetPython_MaxSim_ndcg@10 | CodeSearchNetJavascript_MaxSim_ndcg@10 | CodeSearchNetGo_MaxSim_ndcg@10 | CodeSearchNetRuby_MaxSim_ndcg@10 | CodeSearchNetJava_MaxSim_ndcg@10 | CodeSearchNetPhp_MaxSim_ndcg@10 | CodeSearchNet_mean_MaxSim_ndcg@10 |
|---|---|---|---|---|---|---|---|---|---|
| 0.0000 | 1 | 1.1243 | - | - | - | - | - | - | - |
| 0.0298 | 5000 | 0.3305 | 0.9468 | 0.8304 | 0.9665 | 0.8665 | 0.8982 | 0.8918 | 0.9000 |
| 0.0595 | 10000 | 0.2888 | 0.9493 | 0.8355 | 0.9665 | 0.8701 | 0.9045 | 0.8927 | 0.9031 |
| 0.0893 | 15000 | 0.2556 | 0.9508 | 0.8339 | 0.9673 | 0.8718 | 0.8982 | 0.8943 | 0.9027 |
| 0.1191 | 20000 | 0.1104 | 0.9525 | 0.8354 | 0.9659 | 0.8734 | 0.9040 | 0.8949 | 0.9043 |
| 0.1488 | 25000 | 0.262 | 0.9504 | 0.8361 | 0.9689 | 0.8723 | 0.9075 | 0.8955 | 0.9051 |
| 0.1786 | 30000 | 0.1999 | 0.9496 | 0.8379 | 0.9706 | 0.8744 | 0.9101 | 0.8967 | 0.9065 |
| 0.2084 | 35000 | 0.1466 | 0.9514 | 0.8319 | 0.9693 | 0.8724 | 0.9130 | 0.8948 | 0.9055 |
| 0.2381 | 40000 | 0.1129 | 0.9510 | 0.8335 | 0.9688 | 0.8747 | 0.9078 | 0.8965 | 0.9054 |
| 0.2679 | 45000 | 0.2426 | 0.9522 | 0.8297 | 0.9685 | 0.8752 | 0.9084 | 0.8952 | 0.9049 |
| 0.2976 | 50000 | 0.2194 | 0.9538 | 0.8362 | 0.9704 | 0.8756 | 0.9056 | 0.8979 | 0.9066 |
| 0.3274 | 55000 | 0.2072 | 0.9512 | 0.8354 | 0.9721 | 0.8783 | 0.9138 | 0.8985 | 0.9082 |
| 0.3572 | 60000 | 0.22 | 0.9531 | 0.8367 | 0.9712 | 0.8779 | 0.9116 | 0.8980 | 0.9081 |
| 0.3869 | 65000 | 0.2787 | 0.9549 | 0.8373 | 0.9687 | 0.8774 | 0.9110 | 0.8986 | 0.9080 |
| 0.4167 | 70000 | 0.2358 | 0.9542 | 0.8356 | 0.9712 | 0.8792 | 0.9173 | 0.8984 | 0.9093 |
| 0.4465 | 75000 | 0.142 | 0.9517 | 0.8372 | 0.9693 | 0.8778 | 0.9148 | 0.8993 | 0.9084 |
| 0.4762 | 80000 | 0.1542 | 0.9537 | 0.8374 | 0.9708 | 0.8789 | 0.9163 | 0.8968 | 0.9090 |
| 0.5060 | 85000 | 0.4221 | 0.9553 | 0.8381 | 0.9703 | 0.8790 | 0.9140 | 0.8993 | 0.9093 |
| 0.5358 | 90000 | 0.2596 | 0.9537 | 0.8412 | 0.9700 | 0.8808 | 0.9108 | 0.8987 | 0.9092 |
| 0.5655 | 95000 | 0.3506 | 0.9556 | 0.8422 | 0.9712 | 0.8793 | 0.9170 | 0.8975 | 0.9105 |
| 0.5953 | 100000 | 0.2115 | 0.9556 | 0.8367 | 0.9721 | 0.8817 | 0.9172 | 0.8984 | 0.9103 |
| 0.6251 | 105000 | 0.1495 | 0.9552 | 0.8418 | 0.9712 | 0.8797 | 0.9179 | 0.8997 | 0.9109 |
| 0.6548 | 110000 | 0.1236 | 0.9544 | 0.8374 | 0.9710 | 0.8815 | 0.9172 | 0.8984 | 0.9100 |
| 0.6846 | 115000 | 0.1363 | 0.9545 | 0.8424 | 0.9725 | 0.8797 | 0.9182 | 0.8992 | 0.9111 |
| 0.7143 | 120000 | 0.2641 | 0.9552 | 0.8400 | 0.9715 | 0.8813 | 0.9151 | 0.8986 | 0.9103 |
| 0.7441 | 125000 | 0.2034 | 0.9572 | 0.8411 | 0.9731 | 0.8796 | 0.9166 | 0.8988 | 0.9111 |
| 0.7739 | 130000 | 0.2633 | 0.9561 | 0.8405 | 0.9728 | 0.8797 | 0.9209 | 0.8978 | 0.9113 |
| 0.8036 | 135000 | 0.161 | 0.9562 | 0.8395 | 0.9719 | 0.8803 | 0.9197 | 0.8978 | 0.9109 |
| 0.8334 | 140000 | 0.1249 | 0.9576 | 0.8409 | 0.9727 | 0.8813 | 0.9178 | 0.8986 | 0.9115 |
| 0.8632 | 145000 | 0.1735 | 0.9565 | 0.8400 | 0.9727 | 0.8817 | 0.9189 | 0.8973 | 0.9112 |
| 0.8929 | 150000 | 0.1889 | 0.9561 | 0.8399 | 0.9732 | 0.8807 | 0.9183 | 0.8984 | 0.9111 |
| 0.9227 | 155000 | 0.1712 | 0.9564 | 0.8420 | 0.9733 | 0.8820 | 0.9184 | 0.8979 | 0.9117 |
| 0.9525 | 160000 | 0.2532 | 0.9556 | 0.8423 | 0.9729 | 0.8808 | 0.9191 | 0.8985 | 0.9115 |
| 0.9822 | 165000 | 0.3766 | 0.9559 | 0.8417 | 0.9733 | 0.8811 | 0.9198 | 0.8983 | 0.9117 |
| 1.0 | 167985 | 0.2327 | - | - | - | - | - | - | - |
Framework Versions
- Python: 3.12.9
- Sentence Transformers: 5.1.1
- PyLate: 1.3.4
- Transformers: 4.52.3
- PyTorch: 2.7.0+cu126
- Accelerate: 1.10.1
- Datasets: 4.4.1
- Tokenizers: 0.21.1
Citation
BibTeX
LateOn-Code
@misc{LateOn-Code,
title = {LateOn-Code: a Family of State-Of-The-Art Late Interaction Code Retrieval Models},
author = {Chaffin, Antoine},
url = {https://huggingface.co/collections/lightonai/lateon-code},
year = {2026}
}
ColGrep
@software{next-plaid,
title = {NextPlaid, ColGREP: Multi-vector search, from database to coding agents.},
url = {https://github.com/lightonai/next-plaid},
author = {Raphaël Sourty},
year = {2026},
}
CoRNStack
@inproceedings{DBLP:conf/iclr/SureshRXNMDJ25,
author = {Tarun Suresh and
Revanth Gangi Reddy and
Yifei Xu and
Zach Nussbaum and
Andriy Mulyar and
Brandon Duderstadt and
Heng Ji},
title = {CoRNStack: High-Quality Contrastive Data for Better Code Retrieval
and Reranking},
booktitle = {The Thirteenth International Conference on Learning Representations,
{ICLR} 2025, Singapore, April 24-28, 2025},
publisher = {OpenReview.net},
year = {2025},
url = {https://openreview.net/forum?id=iyJOUELYir},
timestamp = {Sun, 25 May 2025 21:25:19 +0200},
biburl = {https://dblp.org/rec/conf/iclr/SureshRXNMDJ25.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
CoIR
@inproceedings{li2025coir,
title = {Coir: A comprehensive benchmark for code information retrieval models},
author = {Li, Xiangyang and Dong, Kuicai and Lee, Yi Quan and Xia, Wei and Zhang, Hao and Dai, Xinyi and Wang, Yasheng and Tang, Ruiming},
booktitle = {Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
pages = {22074--22091},
year = {2025}
}
Sentence Transformers
@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"
}
PyLate
@inproceedings{DBLP:conf/cikm/ChaffinS25,
author = {Antoine Chaffin and
Rapha{"{e}}l Sourty},
editor = {Meeyoung Cha and
Chanyoung Park and
Noseong Park and
Carl Yang and
Senjuti Basu Roy and
Jessie Li and
Jaap Kamps and
Kijung Shin and
Bryan Hooi and
Lifang He},
title = {PyLate: Flexible Training and Retrieval for Late Interaction Models},
booktitle = {Proceedings of the 34th {ACM} International Conference on Information
and Knowledge Management, {CIKM} 2025, Seoul, Republic of Korea, November
10-14, 2025},
pages = {6334--6339},
publisher = {{ACM}},
year = {2025},
url = {https://github.com/lightonai/pylate},
doi = {10.1145/3746252.3761608},
}
CachedContrastive
@misc{gao2021scaling,
title = {Scaling Deep Contrastive Learning Batch Size under Memory Limited Setup},
author = {Luyu Gao and Yunyi Zhang and Jiawei Han and Jamie Callan},
year = {2021},
eprint = {2101.06983},
archivePrefix = {arXiv},
primaryClass = {cs.LG}
}