verifiers 0.3.2.dev43__tar.gz → 0.3.2.dev44__tar.gz

{verifiers-0.3.2.dev43 → verifiers-0.3.2.dev44}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: verifiers
-Version: 0.3.2.dev43
+Version: 0.3.2.dev44
 Summary: Verifiers: Environments for LLM Reinforcement Learning
 Project-URL: Homepage, https://github.com/primeintellect-ai/verifiers
 Project-URL: Documentation, https://github.com/primeintellect-ai/verifiers

{verifiers-0.3.2.dev43 → verifiers-0.3.2.dev44}/verifiers/v1/episode.py

@@ -6,6 +6,7 @@ from typing import Annotated, Any, Generic, Literal, Self
 from pydantic import BaseModel, Field, model_validator
 
 from verifiers.v1.configs.agent import WireAgentConfig
+from verifiers.v1.graph import RECORD_FLOAT_DECIMALS
 from verifiers.v1.state import State, StateT
 from verifiers.v1.task import DataT, WireTaskData
 from verifiers.v1.trace import EXCLUDE_FIELDS, AgentConfigT, Error, Trace, TraceTask
@@ -146,12 +147,16 @@ class Episode(BaseModel, Generic[DataT, StateT, AgentConfigT]):
             grouped.setdefault(trace.agent.name, []).append(trace)
         return grouped
 
-    def to_record(self) -> dict[str, Any]:
-        """JSON record without raw trace tensors, which remain on the msgpack wire."""
+    def to_record(
+        self, float_decimals: int | None = RECORD_FLOAT_DECIMALS
+    ) -> dict[str, Any]:
+        """JSON record without raw trace tensors, which remain on the msgpack wire.
+        Per-token float streams are rounded to `float_decimals` (`None` keeps every digit)."""
         return self.model_dump(
             mode="json",
             exclude={"traces": {"__all__": EXCLUDE_FIELDS}},
             exclude_none=True,
+            context={"float_decimals": float_decimals},
         )
 
 

{verifiers-0.3.2.dev43 → verifiers-0.3.2.dev44}/verifiers/v1/graph.py

@@ -28,7 +28,14 @@ from dataclasses import dataclass
 from typing import TYPE_CHECKING, Any
 
 import numpy as np
-from pydantic import BaseModel, ConfigDict, Field, field_serializer, field_validator
+from pydantic import (
+    BaseModel,
+    ConfigDict,
+    Field,
+    FieldSerializationInfo,
+    field_serializer,
+    field_validator,
+)
 from pydantic.json_schema import SkipJsonSchema
 from renderers.base import MultiModalData, PlaceholderRange, RenderedTokens
 
@@ -65,6 +72,14 @@ def _decode_ndarray(d: dict) -> np.ndarray:
     return np.frombuffer(d["data"], dtype=np.dtype(d["dtype"])).reshape(d["shape"])
 
 
+RECORD_FLOAT_DECIMALS = 4
+"""Default precision of per-token float streams in JSON records (`to_record`). Full-precision
+digits are noise to every record reader and the least compressible bytes of a trace; four
+decimals leave a logprob within 1e-4 of what the trainer saw. `to_record(float_decimals=...)`
+overrides it per dump (`None` keeps every digit). The msgpack wire (`mode="python"`) keeps
+full precision — training never reads the record."""
+
+
 class MessageNode(BaseModel):
     """One message in the graph: a message plus the tokens it adds to the cumulative
     sequence. Concatenating a root→leaf path's nodes reconstructs that branch's full token
@@ -150,6 +165,22 @@ class MessageNode(BaseModel):
 
     model_config = ConfigDict(arbitrary_types_allowed=True)
 
+    @field_serializer(
+        "logprobs",
+        "advantages",
+        "reference_logprobs",
+        "trainer_logprobs",
+        "entropies",
+        when_used="json",
+    )
+    def serialize_record_floats(
+        self, values: list[float] | None, info: FieldSerializationInfo
+    ) -> list[float] | None:
+        decimals = (info.context or {}).get("float_decimals", RECORD_FLOAT_DECIMALS)
+        if values is None or decimals is None:
+            return values
+        return [round(value, decimals) for value in values]
+
     @field_serializer("multi_modal_data")
     def serialize_multi_modal_data(self, mmd: MultiModalData | None) -> dict | None:
         """`MultiModalData` -> msgpack-safe dict so the pixel tensors ride the wire; numpy

{verifiers-0.3.2.dev43 → verifiers-0.3.2.dev44}/verifiers/v1/trace.py

@@ -18,7 +18,7 @@ if TYPE_CHECKING:
 from verifiers.v1 import graph
 from verifiers.v1.configs.agent import AgentConfig, WireAgentConfig
 from verifiers.v1.errors import ProviderError
-from verifiers.v1.graph import MessageNode
+from verifiers.v1.graph import RECORD_FLOAT_DECIMALS, MessageNode
 from verifiers.v1.runtimes import RuntimeInfo
 from verifiers.v1.semantic import (
     ACPInfo,
@@ -728,9 +728,16 @@ class Trace(BaseModel, Generic[DataT, StateT, AgentConfigT]):
         self.ok = False
         self.stop("error")
 
-    def to_record(self) -> dict[str, Any]:
-        """JSON record without raw tensors, which remain available on the msgpack wire."""
-        return self.model_dump(mode="json", exclude=EXCLUDE_FIELDS)
+    def to_record(
+        self, float_decimals: int | None = RECORD_FLOAT_DECIMALS
+    ) -> dict[str, Any]:
+        """JSON record without raw tensors, which remain available on the msgpack wire.
+        Per-token float streams are rounded to `float_decimals` (`None` keeps every digit)."""
+        return self.model_dump(
+            mode="json",
+            exclude=EXCLUDE_FIELDS,
+            context={"float_decimals": float_decimals},
+        )
 
 
 WireTrace = Trace[WireTaskData, State, WireAgentConfig]