--- language: - en license: apache-2.0 tags: - sentence-transformers - sentence-similarity - feature-extraction - dense - generated_from_trainer - dataset_size:900 - loss:MatryoshkaLoss - loss:MultipleNegativesRankingLoss base_model: microsoft/codebert-base widget: - source_sentence: How to implement __del__? sentences: - "class SampleMultiCrewFlow(Flow[SimpleState]):\n @start()\n def\ \ first_crew(self):\n \"\"\"Run first crew.\"\"\"\n agent\ \ = Agent(\n role=\"first agent\",\n goal=\"first\ \ task\",\n backstory=\"first agent\",\n llm=mock_llm_1,\n\ \ )\n task = Task(\n description=\"First\ \ task\",\n expected_output=\"first result\",\n \ \ agent=agent,\n )\n crew = Crew(\n agents=[agent],\n\ \ tasks=[task],\n share_crew=True,\n \ \ )\n\n result = crew.kickoff()\n\n assert crew._execution_span\ \ is not None\n return str(result.raw)\n\n @listen(first_crew)\n\ \ def second_crew(self, first_result: str):\n \"\"\"Run second\ \ crew.\"\"\"\n agent = Agent(\n role=\"second agent\"\ ,\n goal=\"second task\",\n backstory=\"second agent\"\ ,\n llm=mock_llm_2,\n )\n task = Task(\n\ \ description=\"Second task\",\n expected_output=\"\ second result\",\n agent=agent,\n )\n crew\ \ = Crew(\n agents=[agent],\n tasks=[task],\n \ \ share_crew=True,\n )\n\n result = crew.kickoff()\n\ \n assert crew._execution_span is not None\n\n self.state.result\ \ = f\"{first_result} + {result.raw}\"\n return self.state.result" - "async def test_anthropic_async_with_tools():\n \"\"\"Test async call with\ \ tools.\"\"\"\n llm = AnthropicCompletion(model=\"claude-sonnet-4-0\")\n\n\ \ tools = [\n {\n \"type\": \"function\",\n \"\ function\": {\n \"name\": \"get_weather\",\n \"\ description\": \"Get the current weather for a location\",\n \"\ parameters\": {\n \"type\": \"object\",\n \ \ \"properties\": {\n \"location\": {\n \ \ \"type\": \"string\",\n \"description\"\ : \"The city and state, e.g. San Francisco, CA\"\n }\n\ \ },\n \"required\": [\"location\"]\n \ \ }\n }\n }\n ]\n\n result = await llm.acall(\n\ \ \"What's the weather in San Francisco?\",\n tools=tools\n )\n\ \ logging.debug(\"result: %s\", result)\n\n assert result is not None\n\ \ assert isinstance(result, str)" - "def __del__(self):\n \"\"\"Cleanup connections on deletion.\"\"\"\n \ \ try:\n if self._connection_pool:\n for conn in\ \ self._connection_pool:\n try:\n conn.close()\n\ \ except Exception: # noqa: PERF203, S110\n \ \ pass\n if self._thread_pool:\n self._thread_pool.shutdown()\n\ \ except Exception: # noqa: S110\n pass" - source_sentence: How does route_to_cycle work in Python? sentences: - "def route_to_cycle(self):\n execution_log.append(\"router_initial\"\ )\n return \"loop\"" - "def _register_system_event_handlers(self, event_bus: CrewAIEventsBus) -> None:\n\ \ \"\"\"Register handlers for system signal events (SIGTERM, SIGINT, etc.).\"\ \"\"\n\n @on_signal\n def handle_signal(source: Any, event: SignalEvent)\ \ -> None:\n \"\"\"Flush trace batch on system signals to prevent data\ \ loss.\"\"\"\n if self.batch_manager.is_batch_initialized():\n \ \ self.batch_manager.finalize_batch()" - "async def aadd(self) -> None:\n \"\"\"Add JSON file content asynchronously.\"\ \"\"\n content_str = (\n str(self.content) if isinstance(self.content,\ \ dict) else self.content\n )\n new_chunks = self._chunk_text(content_str)\n\ \ self.chunks.extend(new_chunks)\n await self._asave_documents()" - source_sentence: Explain the test_evaluate logic sentences: - "def test_flow_copy_state_with_unpickleable_objects():\n \"\"\"Test that _copy_state\ \ handles unpickleable objects like RLock.\n\n Regression test for issue #3828:\ \ Flow should not crash when state contains\n objects that cannot be deep copied\ \ (like threading.RLock).\n \"\"\"\n\n class StateWithRLock(BaseModel):\n\ \ counter: int = 0\n lock: Optional[threading.RLock] = None\n\n\ \ class FlowWithRLock(Flow[StateWithRLock]):\n @start()\n def\ \ step_1(self):\n self.state.counter += 1\n\n @listen(step_1)\n\ \ def step_2(self):\n self.state.counter += 1\n\n flow =\ \ FlowWithRLock(initial_state=StateWithRLock())\n flow._state.lock = threading.RLock()\n\ \n copied_state = flow._copy_state()\n assert copied_state.counter == 0\n\ \ assert copied_state.lock is not None" - "def test_evaluate(self, crew_planner):\n task_output = TaskOutput(\n \ \ description=\"Task 1\", agent=str(crew_planner.crew.agents[0])\n \ \ )\n\n with mock.patch.object(Task, \"execute_sync\") as execute:\n\ \ execute().pydantic = TaskEvaluationPydanticOutput(quality=9.5)\n\ \ crew_planner.evaluate(task_output)\n assert crew_planner.tasks_scores[0]\ \ == [9.5]" - "class SlowAsyncTool(BaseTool):\n name: str = \"slow_async\"\n \ \ description: str = \"Simulates slow I/O\"\n\n def _run(self,\ \ task_id: int, delay: float) -> str:\n return f\"Task {task_id}\ \ done\"\n\n async def _arun(self, task_id: int, delay: float) -> str:\n\ \ await asyncio.sleep(delay)\n return f\"Task {task_id}\ \ done\"" - source_sentence: Explain the test_clean_action_no_formatting logic sentences: - "def test_task_interpolation_with_hyphens():\n agent = Agent(\n role=\"\ Researcher\",\n goal=\"be an assistant that responds with {interpolation-with-hyphens}\"\ ,\n backstory=\"You're an expert researcher, specialized in technology,\ \ software engineering, AI and startups. You work as a freelancer and is now working\ \ on doing research and analysis for a new customer.\",\n allow_delegation=False,\n\ \ )\n task = Task(\n description=\"be an assistant that responds\ \ with {interpolation-with-hyphens}\",\n expected_output=\"The response\ \ should be addressing: {interpolation-with-hyphens}\",\n agent=agent,\n\ \ )\n crew = Crew(\n agents=[agent],\n tasks=[task],\n \ \ verbose=True,\n )\n result = crew.kickoff(inputs={\"interpolation-with-hyphens\"\ : \"say hello world\"})\n assert \"say hello world\" in task.prompt()\n\n \ \ assert result.raw == \"Hello, World!\"" - "class LLMCallCompletedEvent(LLMEventBase):\n \"\"\"Event emitted when a LLM\ \ call completes\"\"\"\n\n type: str = \"llm_call_completed\"\n messages:\ \ str | list[dict[str, Any]] | None = None\n response: Any\n call_type:\ \ LLMCallType\n model: str | None = None" - "def test_clean_action_no_formatting():\n action = \"Ask question to senior\ \ researcher\"\n cleaned_action = parser._clean_action(action)\n assert\ \ cleaned_action == \"Ask question to senior researcher\"" - source_sentence: Example usage of test_status_code_and_content_type sentences: - "class NavigateBackToolInput(BaseModel):\n \"\"\"Input for NavigateBackTool.\"\ \"\"\n\n thread_id: str = Field(\n default=\"default\", description=\"\ Thread ID for the browser session\"\n )" - "def test_status_code_and_content_type(self, mock_bs, mock_get):\n for\ \ status in [200, 201, 301]:\n mock_get.return_value = self.setup_mock_response(\n\ \ f\"Status {status}\", status_code=status\n\ \ )\n mock_bs.return_value = self.setup_mock_soup(f\"Status\ \ {status}\")\n result = WebPageLoader().load(\n SourceContent(f\"\ https://example.com/{status}\")\n )\n assert result.metadata[\"\ status_code\"] == status\n\n for ctype in [\"text/html\", \"text/plain\"\ , \"application/xhtml+xml\"]:\n mock_get.return_value = self.setup_mock_response(\n\ \ \"Content\", content_type=ctype\n \ \ )\n mock_bs.return_value = self.setup_mock_soup(\"Content\"\ )\n result = WebPageLoader().load(SourceContent(\"https://example.com\"\ ))\n assert result.metadata[\"content_type\"] == ctype" - "def set_crew(self, crew: Any) -> Memory:\n \"\"\"Set the crew for this\ \ memory instance.\"\"\"\n self.crew = crew\n return self" pipeline_tag: sentence-similarity library_name: sentence-transformers metrics: - cosine_accuracy@1 - cosine_accuracy@3 - cosine_accuracy@5 - cosine_accuracy@10 - cosine_precision@1 - cosine_precision@3 - cosine_precision@5 - cosine_precision@10 - cosine_recall@1 - cosine_recall@3 - cosine_recall@5 - cosine_recall@10 - cosine_ndcg@10 - cosine_mrr@10 - cosine_map@100 model-index: - name: CodeBERT Fine-tuned on CrewAI (LR=2e-05) results: - task: type: information-retrieval name: Information Retrieval dataset: name: dim 768 type: dim_768 metrics: - type: cosine_accuracy@1 value: 0.04 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.04 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.04 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.06 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.04 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.04 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.04 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.03 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.008 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.024 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.04 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.06 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.050819890355577976 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.04333333333333334 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.06130275691848844 name: Cosine Map@100 - task: type: information-retrieval name: Information Retrieval dataset: name: dim 512 type: dim_512 metrics: - type: cosine_accuracy@1 value: 0.01 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.01 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.01 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.01 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.01 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.01 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.01 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.005 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.002 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.006 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.01 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.01 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.01 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.01 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.019316331411936505 name: Cosine Map@100 - task: type: information-retrieval name: Information Retrieval dataset: name: dim 256 type: dim_256 metrics: - type: cosine_accuracy@1 value: 0.01 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.01 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.01 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.03 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.01 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.01 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.01 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.015 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.002 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.006 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.01 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.03 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.020819890355577977 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.013333333333333334 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.028978936077832484 name: Cosine Map@100 - task: type: information-retrieval name: Information Retrieval dataset: name: dim 128 type: dim_128 metrics: - type: cosine_accuracy@1 value: 0.01 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.01 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.01 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.01 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.01 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.01 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.01 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.005 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.002 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.006 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.01 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.01 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.01 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.01 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.027544667112101906 name: Cosine Map@100 - task: type: information-retrieval name: Information Retrieval dataset: name: dim 64 type: dim_64 metrics: - type: cosine_accuracy@1 value: 0.05 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.05 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.05 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.07 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.05 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.05 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.05 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.035 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.01 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.03 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.05 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.07 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.06081989035557797 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.05333333333333334 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.0838507480466874 name: Cosine Map@100 --- # CodeBERT Fine-tuned on CrewAI (LR=2e-05) This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [microsoft/codebert-base](https://huggingface.co/microsoft/codebert-base). 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. ## Model Details ### Model Description - **Model Type:** Sentence Transformer - **Base model:** [microsoft/codebert-base](https://huggingface.co/microsoft/codebert-base) - **Maximum Sequence Length:** 512 tokens - **Output Dimensionality:** 768 dimensions - **Similarity Function:** Cosine Similarity - **Language:** en - **License:** apache-2.0 ### Model Sources - **Documentation:** [Sentence Transformers Documentation](https://sbert.net) - **Repository:** [Sentence Transformers on GitHub](https://github.com/huggingface/sentence-transformers) - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers) ### Full Model Architecture ``` 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}) ) ``` ## Usage ### Direct Usage (Sentence Transformers) First install the Sentence Transformers library: ```bash pip install -U sentence-transformers ``` Then you can load this model and run inference. ```python from sentence_transformers import SentenceTransformer # Download from the 🤗 Hub model = SentenceTransformer("itsanan/codebert-finetuned-crewai-base") # Run inference sentences = [ 'Example usage of test_status_code_and_content_type', 'def test_status_code_and_content_type(self, mock_bs, mock_get):\n for status in [200, 201, 301]:\n mock_get.return_value = self.setup_mock_response(\n f"Status {status}", status_code=status\n )\n mock_bs.return_value = self.setup_mock_soup(f"Status {status}")\n result = WebPageLoader().load(\n SourceContent(f"https://example.com/{status}")\n )\n assert result.metadata["status_code"] == status\n\n for ctype in ["text/html", "text/plain", "application/xhtml+xml"]:\n mock_get.return_value = self.setup_mock_response(\n "Content", content_type=ctype\n )\n mock_bs.return_value = self.setup_mock_soup("Content")\n result = WebPageLoader().load(SourceContent("https://example.com"))\n assert result.metadata["content_type"] == ctype', 'def set_crew(self, crew: Any) -> Memory:\n """Set the crew for this memory instance."""\n self.crew = crew\n return self', ] 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, 0.9009, 0.9087], # [0.9009, 1.0000, 0.9053], # [0.9087, 0.9053, 1.0000]]) ``` ## Evaluation ### Metrics #### Information Retrieval * Dataset: `dim_768` * Evaluated with [InformationRetrievalEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) with these parameters: ```json { "truncate_dim": 768 } ``` | Metric | Value | |:--------------------|:-----------| | cosine_accuracy@1 | 0.04 | | cosine_accuracy@3 | 0.04 | | cosine_accuracy@5 | 0.04 | | cosine_accuracy@10 | 0.06 | | cosine_precision@1 | 0.04 | | cosine_precision@3 | 0.04 | | cosine_precision@5 | 0.04 | | cosine_precision@10 | 0.03 | | cosine_recall@1 | 0.008 | | cosine_recall@3 | 0.024 | | cosine_recall@5 | 0.04 | | cosine_recall@10 | 0.06 | | **cosine_ndcg@10** | **0.0508** | | cosine_mrr@10 | 0.0433 | | cosine_map@100 | 0.0613 | #### Information Retrieval * Dataset: `dim_512` * Evaluated with [InformationRetrievalEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) with these parameters: ```json { "truncate_dim": 512 } ``` | Metric | Value | |:--------------------|:---------| | cosine_accuracy@1 | 0.01 | | cosine_accuracy@3 | 0.01 | | cosine_accuracy@5 | 0.01 | | cosine_accuracy@10 | 0.01 | | cosine_precision@1 | 0.01 | | cosine_precision@3 | 0.01 | | cosine_precision@5 | 0.01 | | cosine_precision@10 | 0.005 | | cosine_recall@1 | 0.002 | | cosine_recall@3 | 0.006 | | cosine_recall@5 | 0.01 | | cosine_recall@10 | 0.01 | | **cosine_ndcg@10** | **0.01** | | cosine_mrr@10 | 0.01 | | cosine_map@100 | 0.0193 | #### Information Retrieval * Dataset: `dim_256` * Evaluated with [InformationRetrievalEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) with these parameters: ```json { "truncate_dim": 256 } ``` | Metric | Value | |:--------------------|:-----------| | cosine_accuracy@1 | 0.01 | | cosine_accuracy@3 | 0.01 | | cosine_accuracy@5 | 0.01 | | cosine_accuracy@10 | 0.03 | | cosine_precision@1 | 0.01 | | cosine_precision@3 | 0.01 | | cosine_precision@5 | 0.01 | | cosine_precision@10 | 0.015 | | cosine_recall@1 | 0.002 | | cosine_recall@3 | 0.006 | | cosine_recall@5 | 0.01 | | cosine_recall@10 | 0.03 | | **cosine_ndcg@10** | **0.0208** | | cosine_mrr@10 | 0.0133 | | cosine_map@100 | 0.029 | #### Information Retrieval * Dataset: `dim_128` * Evaluated with [InformationRetrievalEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) with these parameters: ```json { "truncate_dim": 128 } ``` | Metric | Value | |:--------------------|:---------| | cosine_accuracy@1 | 0.01 | | cosine_accuracy@3 | 0.01 | | cosine_accuracy@5 | 0.01 | | cosine_accuracy@10 | 0.01 | | cosine_precision@1 | 0.01 | | cosine_precision@3 | 0.01 | | cosine_precision@5 | 0.01 | | cosine_precision@10 | 0.005 | | cosine_recall@1 | 0.002 | | cosine_recall@3 | 0.006 | | cosine_recall@5 | 0.01 | | cosine_recall@10 | 0.01 | | **cosine_ndcg@10** | **0.01** | | cosine_mrr@10 | 0.01 | | cosine_map@100 | 0.0275 | #### Information Retrieval * Dataset: `dim_64` * Evaluated with [InformationRetrievalEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) with these parameters: ```json { "truncate_dim": 64 } ``` | Metric | Value | |:--------------------|:-----------| | cosine_accuracy@1 | 0.05 | | cosine_accuracy@3 | 0.05 | | cosine_accuracy@5 | 0.05 | | cosine_accuracy@10 | 0.07 | | cosine_precision@1 | 0.05 | | cosine_precision@3 | 0.05 | | cosine_precision@5 | 0.05 | | cosine_precision@10 | 0.035 | | cosine_recall@1 | 0.01 | | cosine_recall@3 | 0.03 | | cosine_recall@5 | 0.05 | | cosine_recall@10 | 0.07 | | **cosine_ndcg@10** | **0.0608** | | cosine_mrr@10 | 0.0533 | | cosine_map@100 | 0.0839 | ## Training Details ### Training Dataset #### Unnamed Dataset * Size: 900 training samples * Columns: anchor and positive * Approximate statistics based on the first 900 samples: | | anchor | positive | |:--------|:-----------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------| | type | string | string | | details | | | * Samples: | anchor | positive | |:-------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | How to implement LLMCallCompletedEvent? | class LLMCallCompletedEvent(LLMEventBase):
"""Event emitted when a LLM call completes"""

type: str = "llm_call_completed"
messages: str \| list[dict[str, Any]] \| None = None
response: Any
call_type: LLMCallType
model: str \| None = None | | How does get_llm_response work in Python? | def get_llm_response(
llm: LLM \| BaseLLM,
messages: list[LLMMessage],
callbacks: list[TokenCalcHandler],
printer: Printer,
from_task: Task \| None = None,
from_agent: Agent \| LiteAgent \| None = None,
response_model: type[BaseModel] \| None = None,
executor_context: CrewAgentExecutor \| LiteAgent \| None = None,
) -> str:
"""Call the LLM and return the response, handling any invalid responses.

Args:
llm: The LLM instance to call.
messages: The messages to send to the LLM.
callbacks: List of callbacks for the LLM call.
printer: Printer instance for output.
from_task: Optional task context for the LLM call.
from_agent: Optional agent context for the LLM call.
response_model: Optional Pydantic model for structured outputs.
executor_context: Optional executor context for hook invocation.

Returns:
The response from the LLM as a string.

Raises:
Exception: If an error ... | | Example usage of _run | def _run(
self,
**kwargs: Any,
) -> Any:
website_url: str \| None = kwargs.get("website_url", self.website_url)
if website_url is None:
raise ValueError("Website URL must be provided.")

page = requests.get(
website_url,
timeout=15,
headers=self.headers,
cookies=self.cookies if self.cookies else {},
)

page.encoding = page.apparent_encoding
parsed = BeautifulSoup(page.text, "html.parser")

text = "The following text is scraped website content:\n\n"
text += parsed.get_text(" ")
text = re.sub("[ \t]+", " ", text)
return re.sub("\\s+\n\\s+", "\n", text) | * Loss: [MatryoshkaLoss](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters: ```json { "loss": "MultipleNegativesRankingLoss", "matryoshka_dims": [ 768, 512, 256, 128, 64 ], "matryoshka_weights": [ 1, 1, 1, 1, 1 ], "n_dims_per_step": -1 } ``` ### Training Hyperparameters #### Non-Default Hyperparameters - `eval_strategy`: steps - `per_device_train_batch_size`: 4 - `per_device_eval_batch_size`: 4 - `gradient_accumulation_steps`: 32 - `learning_rate`: 2e-05 - `weight_decay`: 0.01 - `num_train_epochs`: 20 - `lr_scheduler_type`: cosine - `warmup_ratio`: 0.1 - `fp16`: True - `load_best_model_at_end`: True - `optim`: adamw_torch - `batch_sampler`: no_duplicates #### All Hyperparameters
Click to expand - `overwrite_output_dir`: False - `do_predict`: False - `eval_strategy`: steps - `prediction_loss_only`: True - `per_device_train_batch_size`: 4 - `per_device_eval_batch_size`: 4 - `per_gpu_train_batch_size`: None - `per_gpu_eval_batch_size`: None - `gradient_accumulation_steps`: 32 - `eval_accumulation_steps`: None - `torch_empty_cache_steps`: None - `learning_rate`: 2e-05 - `weight_decay`: 0.01 - `adam_beta1`: 0.9 - `adam_beta2`: 0.999 - `adam_epsilon`: 1e-08 - `max_grad_norm`: 1.0 - `num_train_epochs`: 20 - `max_steps`: -1 - `lr_scheduler_type`: cosine - `lr_scheduler_kwargs`: None - `warmup_ratio`: 0.1 - `warmup_steps`: 0 - `log_level`: passive - `log_level_replica`: warning - `log_on_each_node`: True - `logging_nan_inf_filter`: True - `save_safetensors`: True - `save_on_each_node`: False - `save_only_model`: False - `restore_callback_states_from_checkpoint`: False - `no_cuda`: False - `use_cpu`: False - `use_mps_device`: False - `seed`: 42 - `data_seed`: None - `jit_mode_eval`: False - `bf16`: False - `fp16`: True - `fp16_opt_level`: O1 - `half_precision_backend`: auto - `bf16_full_eval`: False - `fp16_full_eval`: False - `tf32`: None - `local_rank`: 0 - `ddp_backend`: None - `tpu_num_cores`: None - `tpu_metrics_debug`: False - `debug`: [] - `dataloader_drop_last`: False - `dataloader_num_workers`: 0 - `dataloader_prefetch_factor`: None - `past_index`: -1 - `disable_tqdm`: False - `remove_unused_columns`: True - `label_names`: None - `load_best_model_at_end`: True - `ignore_data_skip`: False - `fsdp`: [] - `fsdp_min_num_params`: 0 - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False} - `fsdp_transformer_layer_cls_to_wrap`: None - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None} - `parallelism_config`: None - `deepspeed`: None - `label_smoothing_factor`: 0.0 - `optim`: adamw_torch - `optim_args`: None - `adafactor`: False - `group_by_length`: False - `length_column_name`: length - `project`: huggingface - `trackio_space_id`: trackio - `ddp_find_unused_parameters`: None - `ddp_bucket_cap_mb`: None - `ddp_broadcast_buffers`: False - `dataloader_pin_memory`: True - `dataloader_persistent_workers`: False - `skip_memory_metrics`: True - `use_legacy_prediction_loop`: False - `push_to_hub`: False - `resume_from_checkpoint`: None - `hub_model_id`: None - `hub_strategy`: every_save - `hub_private_repo`: None - `hub_always_push`: False - `hub_revision`: None - `gradient_checkpointing`: False - `gradient_checkpointing_kwargs`: None - `include_inputs_for_metrics`: False - `include_for_metrics`: [] - `eval_do_concat_batches`: True - `fp16_backend`: auto - `push_to_hub_model_id`: None - `push_to_hub_organization`: None - `mp_parameters`: - `auto_find_batch_size`: False - `full_determinism`: False - `torchdynamo`: None - `ray_scope`: last - `ddp_timeout`: 1800 - `torch_compile`: False - `torch_compile_backend`: None - `torch_compile_mode`: None - `include_tokens_per_second`: False - `include_num_input_tokens_seen`: no - `neftune_noise_alpha`: None - `optim_target_modules`: None - `batch_eval_metrics`: False - `eval_on_start`: False - `use_liger_kernel`: False - `liger_kernel_config`: None - `eval_use_gather_object`: False - `average_tokens_across_devices`: True - `prompts`: None - `batch_sampler`: no_duplicates - `multi_dataset_batch_sampler`: proportional - `router_mapping`: {} - `learning_rate_mapping`: {}
### Training Logs | Epoch | Step | Training Loss | dim_768_cosine_ndcg@10 | dim_512_cosine_ndcg@10 | dim_256_cosine_ndcg@10 | dim_128_cosine_ndcg@10 | dim_64_cosine_ndcg@10 | |:----------:|:-----:|:-------------:|:----------------------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:| | **0.9956** | **7** | **-** | **0.04** | **0.04** | **0.03** | **0.0262** | **0.0308** | | 1.2844 | 10 | 7.098 | - | - | - | - | - | | 1.8533 | 14 | - | 0.0362 | 0.02 | 0.0354 | 0.0154 | 0.0508 | | 2.5689 | 20 | 6.5515 | - | - | - | - | - | | 2.7111 | 21 | - | 0.0508 | 0.01 | 0.0208 | 0.01 | 0.0608 | * The bold row denotes the saved checkpoint. ### Framework Versions - Python: 3.12.12 - Sentence Transformers: 5.2.2 - Transformers: 4.57.6 - PyTorch: 2.9.0+cu126 - Accelerate: 1.12.0 - Datasets: 4.0.0 - Tokenizers: 0.22.2 ## Citation ### BibTeX #### Sentence Transformers ```bibtex @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", } ``` #### MatryoshkaLoss ```bibtex @misc{kusupati2024matryoshka, title={Matryoshka Representation Learning}, author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi}, year={2024}, eprint={2205.13147}, archivePrefix={arXiv}, primaryClass={cs.LG} } ``` #### MultipleNegativesRankingLoss ```bibtex @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} } ```