EvalHarness/evalharness/progress/rich_terminal.py

193 lines
7.6 KiB
Python

"""Rich terminal progress reporter for per-sample model generation."""
import asyncio
import time
from rich.console import Console
from rich.progress import (
BarColumn,
Progress,
SpinnerColumn,
TaskProgressColumn,
TextColumn,
TimeElapsedColumn,
TimeRemainingColumn,
)
class RichTerminalProgress:
def __init__(self, console=None):
# accept an EXTERNAL console: CLI phase messages and the live bar must
# share one console, or the two writers interleave and repaint wrongly
self.console = console or Console()
self.overall_id = None
self.overall_total = 0
self.progress = Progress(
SpinnerColumn(),
TextColumn("[progress.description]{task.description}"),
BarColumn(complete_style="green", finished_style="bold green"),
TaskProgressColumn(),
TextColumn("• Completed {task.completed}/{task.total}"),
TextColumn("• in-flight {task.fields[inflight]}"),
TextColumn("{task.fields[rate]}/s"),
TextColumn(""),
TimeElapsedColumn(),
TextColumn(""),
TimeRemainingColumn(),
console=self.console,
refresh_per_second=4,
)
self.task_id = None
self.bench_name = ''
self.bench_tag = '' # e.g. '[1/6]': persistent benchmark counter
self._last_phase = ''
self.started = 0.0
self.current_started = 0.0
self.inflight = 0
self.heartbeat_task = None
def set_overall(self, total: int, done: int, label: str = 'benches'):
"""Multi-benchmark runs: a bar above the sample bar showing which
benchmark we are on (also covers loading/scoring phases)."""
self.overall_total = total
if self.overall_id is None:
self.progress.start()
# the shared column set reads fields from EVERY task: give the
# overall task the same fields or rendering raises KeyError
self.overall_id = self.progress.add_task(
f'[cyan]{label}[/cyan]', total=total, completed=min(done, total),
inflight=0, rate='0.00', success=done, failed=0,
waiting='00:00', last_result='')
else:
self.progress.update(self.overall_id, completed=min(done, total))
def advance_overall(self):
if self.overall_id is not None:
self.progress.advance(self.overall_id)
def start(self, total: int, description: str, completed: int = 0):
self.started = time.monotonic()
if self.task_id is not None:
return # one live reporter at a time; reuse across benchmarks
self.progress.start()
self.task_id = self.progress.add_task(
f"[green]{description}",
total=total,
completed=min(completed, total),
success=completed,
failed=0,
rate="0.00",
inflight=0,
waiting="00:00",
last_result="restored",
)
self.heartbeat_task = asyncio.create_task(self._heartbeat())
def reset_samples(self, total: int, description: str, completed: int = 0):
"""Start (or re-target) the per-sample task for the next benchmark."""
self.started = time.monotonic()
self.inflight = 0
self.bench_name = description
desc = f'[green]{self.bench_tag}{description} · generating[/green]'
if self.task_id is None:
self.progress.start()
self.task_id = self.progress.add_task(
desc, total=total, completed=min(completed, total),
success=completed, failed=0, rate='0.00', inflight=0,
waiting='00:00', last_result='restored')
self.heartbeat_task = asyncio.create_task(self._heartbeat())
else:
self.progress.update(self.task_id, description=desc,
total=total, completed=min(completed, total),
success=completed, failed=0, rate='0.00',
inflight=0, last_result='restored')
def set_bench_tag(self, tag: str):
"""Persistent counter shown on the sample bar, e.g. '[1/6]'."""
self.bench_tag = tag + ' ' if tag else ''
if self._last_phase:
self.set_phase(self._last_phase)
def set_phase(self, phase: str):
self._last_phase = phase
"""Retag the sample bar with what is happening (generating/scoring/
writing) -- the bar alone does not say which stage we are in."""
if self.task_id is not None:
self.progress.update(
self.task_id,
description=f'[green]{self.bench_tag}{self.bench_name} · {phase}[/green]')
def begin_sample(self, label: str):
if self.task_id is None:
return
self.inflight += 1
self.current_started = time.monotonic()
self.progress.update(self.task_id, inflight=self.inflight,
waiting="00:00", last_result=f"waiting {label}")
def rollback(self):
"""Pair a begin_sample that will NOT reach advance (retry path):
just decrement the in-flight count, no success/fail bookkeeping."""
self.inflight = max(0, self.inflight - 1)
if self.task_id is not None:
self.progress.update(self.task_id, inflight=self.inflight)
def advance(self, success: bool = True):
if self.task_id is None:
return
task = self.progress.tasks[self.task_id]
completed = task.completed + 1
ok = task.fields["success"] + (1 if success else 0)
failed = task.fields["failed"] + (0 if success else 1)
self.inflight = max(0, self.inflight - 1)
elapsed = max(time.monotonic() - self.started, 1e-6)
self.progress.update(
self.task_id,
advance=1,
success=ok,
failed=failed,
rate=f"{completed / elapsed:.2f}",
inflight=self.inflight,
waiting="00:00",
last_result="success" if success else "failed",
)
async def _heartbeat(self):
while self.task_id is not None:
if self.task_id is not None and self.inflight:
waiting = int(time.monotonic() - self.current_started)
self.progress.update(self.task_id, waiting=f"{waiting // 60:02d}:{waiting % 60:02d}")
await asyncio.sleep(1)
def log(self, message: str):
"""Print a status line ABOVE the live bar (safe during live display).
Plain console.print from another writer while Progress is live causes
interleaved/repainted output; Progress.print routes through the live
region correctly.
"""
# highlight=False: rich auto-colorizes numbers, which made narration
# lines look inconsistent (some numbers cyan, some plain)
if self.task_id is not None:
self.progress.print(message, highlight=False)
else:
self.console.print(message, highlight=False)
def pause(self):
"""Temporarily stop the live display (e.g. while hub downloads print
their own tqdm); task state is kept and resume() restores the bars."""
if self.task_id is not None or self.overall_id is not None:
self.progress.stop()
def resume(self):
if self.task_id is not None or self.overall_id is not None:
self.progress.start()
def close(self):
if self.task_id is not None:
if self.heartbeat_task is not None:
self.heartbeat_task.cancel()
self.heartbeat_task = None
self.progress.stop()
self.task_id = None