ceos/unsloth
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Merge branch 'main' into studio-fla-tilelang-qwen3.5

Browse source
This commit is contained in:
Daniel Han 2026-05-15 03:52:11 -07:00 • committed by GitHub
commit a9982a0b4a
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 4 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

6
studio/backend/core/training/worker.py
View file

@ -914,9 +914,11 @@ def _run_mlx_training(event_queue, stop_queue, config):
else:
eval_steps_val = int(eval_steps_val)
# MLX: value-clip grads to [-5, 5]; norm clipping disabled for compile-friendliness.
# MLX: per-element clip to [-1, 1]; norm clip disabled (it needs a
# global reduction that breaks MLX's eager pipeline). 1.0 (not 5.0):
# |g_i| > 5 rarely fires, so the historical 5.0 was effectively no-op.
max_grad_norm = 0.0
max_grad_value = 5.0 # TODO: expose MLX grad-clip in Studio UI for power users
max_grad_value = 1.0 # TODO: expose MLX grad-clip in Studio UI for power users
trainer = MLXTrainer(
model = model,