Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more.
Python agentaichatgptdeepseekfine-tuninggemmaimage-generationllamallmllmsopenaipythonqwenreinforcement-learningself-hostedstable-diffusiontext-to-speechttsuiunsloth
# SPDX-License-Identifier: AGPL-3.0-only
# Copyright 2026-present the Unsloth AI Inc. team. All rights reserved. See /studio/LICENSE.AGPL-3.0
"""Truthful first-step milestones shared by SFT, vision, audio, decision and embedding callbacks."""
STARTING = "Starting training loop..."
ACTIVE = "Training in progress..."
WAITING_FOR_LOSS = "First training step finished. Waiting for the first loss measurement..."
class TrainingStartupProgress:
def __init__(self):
self.started = False
self.start_step = 0
self.accumulation = 1
self.batches = 0
self.step_finished = False
self.loss_reported = False
def begin(self, args, state):
self.started = True
self.start_step = state.global_step
self.accumulation = max(1, int(getattr(args, "gradient_accumulation_steps", 1) or 1))
self.batches = 0
self.step_finished = False
self.loss_reported = False
return STARTING
def step_begin(self):
if not self.started or self.step_finished or self.loss_reported:
return None
return self._batch_status()
def substep_end(self):
if not self.started or self.step_finished or self.loss_reported:
return None
self.batches += 1
return self._batch_status()
def _batch_status(self):
batch = min(self.batches + 1, self.accumulation)
return (
f"Running first training step (batch {batch} of up to {self.accumulation})... "
"Loss appears after the optimizer step."
)
def step_end(self, state):
if not self.started or self.step_finished or state.global_step <= self.start_step:
return None
self.step_finished = True
return None if self.loss_reported else WAITING_FOR_LOSS
def log(self, logs):
if not self.started or self.loss_reported or logs.get("loss") is None:
return None
self.loss_reported = True
return ACTIVE