MaxView

XPK Start: Sat Apr 25 14:11:19 UTC 2026
PyTorch was not found. Models won't be available and only tokenizers, configuration and file/data utilities can be used.
`rope_parameters`'s factor field must be a float >= 1, got 40
`rope_parameters`'s beta_fast field must be a float, got 32
`rope_parameters`'s beta_slow field must be a float, got 1
DeepseekV32Config got `key=rope_scaling` in kwargs but hasn't set it as attribute. For RoPE standardization you need to set `self.rope_parameters` in model's config. 
2026-04-25 14:11:44.443793: E external/local_xla/xla/stream_executor/cuda/cuda_platform.cc:51] failed call to cuInit: INTERNAL: CUDA error: Failed call to cuInit: UNKNOWN ERROR (303)
I0425 14:11:44.655614 139840692692800 max_utils.py:273] Attempting to initialize the jax distributed system...
I0425 14:11:53.696539 139840692692800 distributed.py:149] Starting JAX distributed service on [::]:8482
I0425 14:11:53.698939 139840692692800 distributed.py:172] Connecting to JAX distributed service on mt-13-scan-layers-false-z24ld-slice-job-0-0.mt-13-scan-layers-false-z24ld:8482
I0425 14:11:54.683903 139840692692800 max_utils.py:284] Jax distributed system initialized!
I0425 14:11:59.899629 139840692692800 max_utils.py:800] System Information: Jax Version: 0.9.2
I0425 14:11:59.899749 139840692692800 max_utils.py:801] System Information: Jaxlib Version: 0.9.2
I0425 14:11:59.899789 139840692692800 max_utils.py:802] System Information: Jax Backend: PJRT C API
TFRT TPU v6 lite
Built on Mar 4 2026 11:32:08 (1772652728) cl/878335365
I0425 14:11:59.899823 139840692692800 train_utils.py:391] WARNING: Sequence packing is essentially ignored for synthetic data. Please use a real dataset to use sequence packing.
I0425 14:12:00.599107 139840692692800 maxtext_utils.py:1771] Num_devices: 32, shape (1, 1, 1, 32, 1, 1, 1, 1, 1, 1, 1, 1, 1)
I0425 14:12:01.417760 139840692692800 checkpointing.py:688] Setting up checkpoint logger...
I0425 14:12:01.417886 139840692692800 checkpointing.py:234] Creating checkpoint manager with ocdbt=True and zarr3=True
I0425 14:12:01.417931 139840692692800 pytree_checkpoint_handler.py:592] save_device_host_concurrent_bytes=None
I0425 14:12:01.418170 139840692692800 base_pytree_checkpoint_handler.py:441] Created BasePyTreeCheckpointHandler: use_ocdbt=True, use_zarr3=True, pytree_metadata_options=PyTreeMetadataOptions(support_rich_types=False), array_metadata_store=<orbax.checkpoint._src.metadata.array_metadata_store.Store object at 0x7f2e9c7ea600>, enable_pinned_host_transfer=False, save_concurrent_bytes: 96000000000 (89.4 GiB), restore_concurrent_bytes: 96000000000 (89.4 GiB)
I0425 14:12:04.253504 139840692692800 checkpointing.py:266] Enabling policy for fixed interval checkpointing.
I0425 14:12:04.253764 139840692692800 checkpoint_manager.py:708] [process=5][thread=MainThread] CheckpointManager init: checkpointers=None, item_names=('items',), item_handlers={'items': <orbax.checkpoint._src.handlers.pytree_checkpoint_handler.PyTreeCheckpointHandler object at 0x7f1af46975c0>}, handler_registry=None
I0425 14:12:04.254002 139840692692800 composite_checkpoint_handler.py:237] Deferred registration for item: "items". Adding handler `<orbax.checkpoint._src.handlers.pytree_checkpoint_handler.PyTreeCheckpointHandler object at 0x7f1af46975c0>` for item "items" and save args `<class 'orbax.checkpoint._src.handlers.pytree_checkpoint_handler.PyTreeSaveArgs'>` and restore args `<class 'orbax.checkpoint._src.handlers.pytree_checkpoint_handler.PyTreeRestoreArgs'>` to `_handler_registry`.
I0425 14:12:04.254055 139840692692800 composite_checkpoint_handler.py:237] Deferred registration for item: "metrics". Adding handler `<orbax.checkpoint._src.handlers.json_checkpoint_handler.JsonCheckpointHandler object at 0x7f1af4686cc0>` for item "metrics" and save args `<class 'orbax.checkpoint._src.handlers.json_checkpoint_handler.JsonSaveArgs'>` and restore args `<class 'orbax.checkpoint._src.handlers.json_checkpoint_handler.JsonRestoreArgs'>` to `_handler_registry`.
I0425 14:12:04.254093 139840692692800 composite_checkpoint_handler.py:505] Initialized registry DefaultCheckpointHandlerRegistry({('items', <class 'orbax.checkpoint._src.handlers.pytree_checkpoint_handler.PyTreeSaveArgs'>): <orbax.checkpoint._src.handlers.pytree_checkpoint_handler.PyTreeCheckpointHandler object at 0x7f1af46975c0>, ('items', <class 'orbax.checkpoint._src.handlers.pytree_checkpoint_handler.PyTreeRestoreArgs'>): <orbax.checkpoint._src.handlers.pytree_checkpoint_handler.PyTreeCheckpointHandler object at 0x7f1af46975c0>, ('metrics', <class 'orbax.checkpoint._src.handlers.json_checkpoint_handler.JsonSaveArgs'>): <orbax.checkpoint._src.handlers.json_checkpoint_handler.JsonCheckpointHandler object at 0x7f1af4686cc0>, ('metrics', <class 'orbax.checkpoint._src.handlers.json_checkpoint_handler.JsonRestoreArgs'>): <orbax.checkpoint._src.handlers.json_checkpoint_handler.JsonCheckpointHandler object at 0x7f1af4686cc0>}).
I0425 14:12:04.254422 139840692692800 abstract_checkpointer.py:35] orbax-checkpoint version: 0.11.34
I0425 14:12:04.254494 139840692692800 async_checkpointer.py:192] [process=5][thread=MainThread] Using barrier_sync_fn: <function get_barrier_sync_fn.<locals>._fn at 0x7f1b1415fa60> timeout: 1200 secs and primary_host=0 for async checkpoint writes
I0425 14:12:05.094822 139840692692800 checkpoint_manager.py:1812] Found 0 checkpoint steps in gs://lance-maxtext/nnx_ckpt_xpk_feat_nnx_post_train_fixes_20260425_121355/nnx_xpk_feat_nnx_post_train_fixes_20260425_121355_13_scan_layers_false/checkpoints
I0425 14:12:05.392789 139840692692800 checkpoint_manager.py:929] [process=5][thread=MainThread] CheckpointManager created,  primary_host=0, CheckpointManagerOptions=CheckpointManagerOptions(save_interval_steps=1, max_to_keep=None, keep_time_interval=None, keep_period=None, should_keep_fn=None, best_fn=None, best_mode='max', keep_checkpoints_without_metrics=True, step_prefix=None, step_format_fixed_length=None, step_name_format=None, create=True, cleanup_tmp_directories=False, save_on_steps=frozenset(), single_host_load_and_broadcast=False, todelete_subdir=None, todelete_full_path=None, enable_background_delete=False, read_only=False, enable_async_checkpointing=True, async_options=None, multiprocessing_options=MultiprocessingOptions(primary_host=0, active_processes=None, barrier_sync_key_prefix=None), should_save_fn=None, file_options=FileOptions(path_permission_mode=None), save_root_metadata=True, temporary_path_class=None, save_decision_policy=FixedIntervalPolicy(interval=10), preservation_policy=LatestN(n=None), prevent_write_metrics=False, enable_should_save_is_saving_in_progress_check=True, enable_per_process_directory_creation=False, lightweight_initialize=False), root_directory=gs://lance-maxtext/nnx_ckpt_xpk_feat_nnx_post_train_fixes_20260425_121355/nnx_xpk_feat_nnx_post_train_fixes_20260425_121355_13_scan_layers_false/checkpoints: <orbax.checkpoint.checkpoint_manager.CheckpointManager object at 0x7f1af429cf20>
I0425 14:12:05.392965 139840692692800 checkpointing.py:302] Checkpoint manager created!
I0425 14:12:07.509388 139840692692800 checkpointing.py:578] checkpoint manager exists so trying to load this run's existing checkpoint
I0425 14:12:07.509517 139840692692800 checkpointing.py:676] No existing checkpoints found, not restoring checkpoint.
fsdp: 32
I0425 14:12:15.435185 139840692692800 maxtext_utils.py:1889]  decoder/decoder_norm/scale/value
    Shape:     float32[2048]
    Physical:  (None,)
I0425 14:12:15.435313 139840692692800 maxtext_utils.py:1889]  decoder/layers/0/mlp/wi_0/kernel/value
    Shape:     float32[2048,7168]
    Physical:  ('fsdp', None)
I0425 14:12:15.435365 139840692692800 maxtext_utils.py:1889]  decoder/layers/0/mlp/wi_1/kernel/value
    Shape:     float32[2048,7168]
    Physical:  ('fsdp', None)
I0425 14:12:15.435408 139840692692800 maxtext_utils.py:1889]  decoder/layers/0/mlp/wo/kernel/value
    Shape:     float32[7168,2048]
    Physical:  (None, 'fsdp')
I0425 14:12:15.435445 139840692692800 maxtext_utils.py:1889]  decoder/layers/0/post_self_attention_layer_norm/scale/value
    Shape:     float32[2048]
    Physical:  (None,)
I0425 14:12:15.435478 139840692692800 maxtext_utils.py:1889]  decoder/layers/0/pre_self_attention_layer_norm/scale/value
    Shape:     float32[2048]
    Physical:  (None,)
I0425 14:12:15.435512 139840692692800 maxtext_utils.py:1889]  decoder/layers/0/self_attention/key/kernel/value
    Shape:     float32[2048,16,128]
    Physical:  ('fsdp', None, None)
I0425 14:12:15.435547 139840692692800 maxtext_utils.py:1889]  decoder/layers/0/self_attention/out/kernel/value
    Shape:     float32[16,128,2048]
    Physical:  (None, None, 'fsdp')
I0425 14:12:15.435580 139840692692800 maxtext_utils.py:1889]  decoder/layers/0/self_attention/query/kernel/value
    Shape:     float32[2048,16,128]
    Physical:  ('fsdp', None, None)
I0425 14:12:15.435613 139840692692800 maxtext_utils.py:1889]  decoder/layers/0/self_attention/value/kernel/value
    Shape:     float32[2048,16,128]
    Physical:  ('fsdp', None, None)
I0425 14:12:15.435646 139840692692800 maxtext_utils.py:1889]  decoder/layers/1/mlp/wi_0/kernel/value
    Shape:     float32[2048,7168]
    Physical:  ('fsdp', None)
I0425 14:12:15.435693 139840692692800 maxtext_utils.py:1889]  decoder/layers/1/mlp/wi_1/kernel/value
    Shape:     float32[2048,7168]
    Physical:  ('fsdp', None)
I0425 14:12:15.435726 139840692692800 maxtext_utils.py:1889]  decoder/layers/1/mlp/wo/kernel/value
    Shape:     float32[7168,2048]
    Physical:  (None, 'fsdp')
I0425 14:12:15.435755 139840692692800 maxtext_utils.py:1889]  decoder/layers/1/post_self_attention_layer_norm/scale/value
    Shape:     float32[2048]
    Physical:  (None,)
I0425 14:12:15.435784 139840692692800 maxtext_utils.py:1889]  decoder/layers/1/pre_self_attention_layer_norm/scale/value
    Shape:     float32[2048]
    Physical:  (None,)
I0425 14:12:15.435814 139840692692800 maxtext_utils.py:1889]  decoder/layers/1/self_attention/key/kernel/value
    Shape:     float32[2048,16,128]
    Physical:  ('fsdp', None, None)
I0425 14:12:15.435845 139840692692800 maxtext_utils.py:1889]  decoder/layers/1/self_attention/out/kernel/value
    Shape:     float32[16,128,2048]
    Physical:  (None, None, 'fsdp')
I0425 14:12:15.435875 139840692692800 maxtext_utils.py:1889]  decoder/layers/1/self_attention/query/kernel/value
    Shape:     float32[2048,16,128]
    Physical:  ('fsdp', None, None)
I0425 14:12:15.435905 139840692692800 maxtext_utils.py:1889]  decoder/layers/1/self_attention/value/kernel/value
    Shape:     float32[2048,16,128]
    Physical:  ('fsdp', None, None)
I0425 14:12:15.435936 139840692692800 maxtext_utils.py:1889]  decoder/layers/2/mlp/wi_0/kernel/value
    Shape:     float32[2048,7168]
    Physical:  ('fsdp', None)
I0425 14:12:15.435966 139840692692800 maxtext_utils.py:1889]  decoder/layers/2/mlp/wi_1/kernel/value
    Shape:     float32[2048,7168]
    Physical:  ('fsdp', None)
I0425 14:12:15.435997 139840692692800 maxtext_utils.py:1889]  decoder/layers/2/mlp/wo/kernel/value
    Shape:     float32[7168,2048]
    Physical:  (None, 'fsdp')
I0425 14:12:15.436025 139840692692800 maxtext_utils.py:1889]  decoder/layers/2/post_self_attention_layer_norm/scale/value
    Shape:     float32[2048]
    Physical:  (None,)
I0425 14:12:15.436053 139840692692800 maxtext_utils.py:1889]  decoder/layers/2/pre_self_attention_layer_norm/scale/value
    Shape:     float32[2048]
    Physical:  (None,)
I0425 14:12:15.436084 139840692692800 maxtext_utils.py:1889]  decoder/layers/2/self_attention/key/kernel/value
    Shape:     float32[2048,16,128]
    Physical:  ('fsdp', None, None)
I0425 14:12:15.436113 139840692692800 maxtext_utils.py:1889]  decoder/layers/2/self_attention/out/kernel/value
    Shape:     float32[16,128,2048]
    Physical:  (None, None, 'fsdp')
I0425 14:12:15.436145 139840692692800 maxtext_utils.py:1889]  decoder/layers/2/self_attention/query/kernel/value
    Shape:     float32[2048,16,128]
    Physical:  ('fsdp', None, None)
I0425 14:12:15.436174 139840692692800 maxtext_utils.py:1889]  decoder/layers/2/self_attention/value/kernel/value
    Shape:     float32[2048,16,128]
    Physical:  ('fsdp', None, None)
I0425 14:12:15.436212 139840692692800 maxtext_utils.py:1889]  decoder/layers/3/mlp/wi_0/kernel/value
    Shape:     float32[2048,7168]
    Physical:  ('fsdp', None)
I0425 14:12:15.436254 139840692692800 maxtext_utils.py:1889]  decoder/layers/3/mlp/wi_1/kernel/value
    Shape:     float32[2048,7168]
    Physical:  ('fsdp', None)
I0425 14:12:15.436287 139840692692800 maxtext_utils.py:1889]  decoder/layers/3/mlp/wo/kernel/value
    Shape:     float32[7168,2048]
    Physical:  (None, 'fsdp')
I0425 14:12:15.436316 139840692692800 maxtext_utils.py:1889]  decoder/layers/3/post_self_attention_layer_norm/scale/value
    Shape:     float32[2048]
    Physical:  (None,)
I0425 14:12:15.436345 139840692692800 maxtext_utils.py:1889]  decoder/layers/3/pre_self_attention_layer_norm/scale/value
    Shape:     float32[2048]
    Physical:  (None,)
I0425 14:12:15.436376 139840692692800 maxtext_utils.py:1889]  decoder/layers/3/self_attention/key/kernel/value
    Shape:     float32[2048,16,128]
    Physical:  ('fsdp', None, None)
I0425 14:12:15.436408 139840692692800 maxtext_utils.py:1889]  decoder/layers/3/self_attention/out/kernel/value
    Shape:     float32[16,128,2048]
    Physical:  (None, None, 'fsdp')
I0425 14:12:15.436438 139840692692800 maxtext_utils.py:1889]  decoder/layers/3/self_attention/query/kernel/value
    Shape:     float32[2048,16,128]
    Physical:  ('fsdp', None, None)
I0425 14:12:15.436467 139840692692800 maxtext_utils.py:1889]  decoder/layers/3/self_attention/value/kernel/value
    Shape:     float32[2048,16,128]
    Physical:  ('fsdp', None, None)
I0425 14:12:15.436506 139840692692800 maxtext_utils.py:1889]  decoder/layers/4/mlp/wi_0/kernel/value
    Shape:     float32[2048,7168]
    Physical:  ('fsdp', None)
I0425 14:12:15.436557 139840692692800 maxtext_utils.py:1889]  decoder/layers/4/mlp/wi_1/kernel/value
    Shape:     float32[2048,7168]
    Physical:  ('fsdp', None)
I0425 14:12:15.436593 139840692692800 maxtext_utils.py:1889]  decoder/layers/4/mlp/wo/kernel/value
    Shape:     float32[7168,2048]
    Physical:  (None, 'fsdp')
I0425 14:12:15.436622 139840692692800 maxtext_utils.py:1889]  decoder/layers/4/post_self_attention_layer_norm/scale/value
    Shape:     float32[2048]
    Physical:  (None,)
I0425 14:12:15.436681 139840692692800 maxtext_utils.py:1889]  decoder/layers/4/pre_self_attention_layer_norm/scale/value
    Shape:     float32[2048]
    Physical:  (None,)
I0425 14:12:15.436721 139840692692800 maxtext_utils.py:1889]  decoder/layers/4/self_attention/key/kernel/value
    Shape:     float32[2048,16,128]
    Physical:  ('fsdp', None, None)
I0425 14:12:15.436755 139840692692800 maxtext_utils.py:1889]  decoder/layers/4/self_attention/out/kernel/value
    Shape:     float32[16,128,2048]
    Physical:  (None, None, 'fsdp')
I0425 14:12:15.436786 139840692692800 maxtext_utils.py:1889]  decoder/layers/4/self_attention/query/kernel/value
    Shape:     float32[2048,16,128]
    Physical:  ('fsdp', None, None)
I0425 14:12:15.436816 139840692692800 maxtext_utils.py:1889]  decoder/layers/4/self_attention/value/kernel/value
    Shape:     float32[2048,16,128]
    Physical:  ('fsdp', None, None)
I0425 14:12:15.436845 139840692692800 maxtext_utils.py:1889]  decoder/layers/5/mlp/wi_0/kernel/value
    Shape:     float32[2048,7168]
    Physical:  ('fsdp', None)
I0425 14:12:15.436874 139840692692800 maxtext_utils.py:1889]  decoder/layers/5/mlp/wi_1/kernel/value
    Shape:     float32[2048,7168]
    Physical:  ('fsdp', None)
I0425 14:12:15.436914 139840692692800 maxtext_utils.py:1889]  decoder/layers/5/mlp/wo/kernel/value
    Shape:     float32[7168,2048]
    Physical:  (None, 'fsdp')
I0425 14:12:15.436947 139840692692800 maxtext_utils.py:1889]  decoder/layers/5/post_self_attention_layer_norm/scale/value
    Shape:     float32[2048]
    Physical:  (None,)
I0425 14:12:15.436975 139840692692800 maxtext_utils.py:1889]  decoder/layers/5/pre_self_attention_layer_norm/scale/value
    Shape:     float32[2048]
    Physical:  (None,)
I0425 14:12:15.437004 139840692692800 maxtext_utils.py:1889]  decoder/layers/5/self_attention/key/kernel/value
    Shape:     float32[2048,16,128]
    Physical:  ('fsdp', None, None)
I0425 14:12:15.437033 139840692692800 maxtext_utils.py:1889]  decoder/layers/5/self_attention/out/kernel/value
    Shape:     float32[16,128,2048]
    Physical:  (None, None, 'fsdp')
I0425 14:12:15.437062 139840692692800 maxtext_utils.py:1889]  decoder/layers/5/self_attention/query/kernel/value
    Shape:     float32[2048,16,128]
    Physical:  ('fsdp', None, None)
I0425 14:12:15.437091 139840692692800 maxtext_utils.py:1889]  decoder/layers/5/self_attention/value/kernel/value
    Shape:     float32[2048,16,128]
    Physical:  ('fsdp', None, None)
I0425 14:12:15.437120 139840692692800 maxtext_utils.py:1889]  decoder/layers/6/mlp/wi_0/kernel/value
    Shape:     float32[2048,7168]
    Physical:  ('fsdp', None)
I0425 14:12:15.437149 139840692692800 maxtext_utils.py:1889]  decoder/layers/6/mlp/wi_1/kernel/value
    Shape:     float32[2048,7168]
    Physical:  ('fsdp', None)
I0425 14:12:15.437178 139840692692800 maxtext_utils.py:1889]  decoder/layers/6/mlp/wo/kernel/value
    Shape:     float32[7168,2048]
    Physical:  (None, 'fsdp')
I0425 14:12:15.437211 139840692692800 maxtext_utils.py:1889]  decoder/layers/6/post_self_attention_layer_norm/scale/value
    Shape:     float32[2048]
    Physical:  (None,)
I0425 14:12:15.437238 139840692692800 maxtext_utils.py:1889]  decoder/layers/6/pre_self_attention_layer_norm/scale/value
    Shape:     float32[2048]
    Physical:  (None,)
I0425 14:12:15.437267 139840692692800 maxtext_utils.py:1889]  decoder/layers/6/self_attention/key/kernel/value
    Shape:     float32[2048,16,128]
    Physical:  ('fsdp', None, None)
I0425 14:12:15.437296 139840692692800 maxtext_utils.py:1889]  decoder/layers/6/self_attention/out/kernel/value
    Shape:     float32[16,128,2048]
    Physical:  (None, None, 'fsdp')
I0425 14:12:15.437326 139840692692800 maxtext_utils.py:1889]  decoder/layers/6/self_attention/query/kernel/value
    Shape:     float32[2048,16,128]
    Physical:  ('fsdp', None, None)
I0425 14:12:15.437355 139840692692800 maxtext_utils.py:1889]  decoder/layers/6/self_attention/value/kernel/value
    Shape:     float32[2048,16,128]
    Physical:  ('fsdp', None, None)
I0425 14:12:15.437383 139840692692800 maxtext_utils.py:1889]  decoder/layers/7/mlp/wi_0/kernel/value
    Shape:     float32[2048,7168]
    Physical:  ('fsdp', None)
I0425 14:12:15.437411 139840692692800 maxtext_utils.py:1889]  decoder/layers/7/mlp/wi_1/kernel/value
    Shape:     float32[2048,7168]
    Physical:  ('fsdp', None)
I0425 14:12:15.437439 139840692692800 maxtext_utils.py:1889]  decoder/layers/7/mlp/wo/kernel/value
    Shape:     float32[7168,2048]
    Physical:  (None, 'fsdp')
I0425 14:12:15.437466 139840692692800 maxtext_utils.py:1889]  decoder/layers/7/post_self_attention_layer_norm/scale/value
    Shape:     float32[2048]
    Physical:  (None,)
I0425 14:12:15.437493 139840692692800 maxtext_utils.py:1889]  decoder/layers/7/pre_self_attention_layer_norm/scale/value
    Shape:     float32[2048]
    Physical:  (None,)
I0425 14:12:15.437521 139840692692800 maxtext_utils.py:1889]  decoder/layers/7/self_attention/key/kernel/value
    Shape:     float32[2048,16,128]
    Physical:  ('fsdp', None, None)
I0425 14:12:15.437550 139840692692800 maxtext_utils.py:1889]  decoder/layers/7/self_attention/out/kernel/value
    Shape:     float32[16,128,2048]
    Physical:  (None, None, 'fsdp')
I0425 14:12:15.437579 139840692692800 maxtext_utils.py:1889]  decoder/layers/7/self_attention/query/kernel/value
    Shape:     float32[2048,16,128]
    Physical:  ('fsdp', None, None)
I0425 14:12:15.437608 139840692692800 maxtext_utils.py:1889]  decoder/layers/7/self_attention/value/kernel/value
    Shape:     float32[2048,16,128]
    Physical:  ('fsdp', None, None)
I0425 14:12:15.437636 139840692692800 maxtext_utils.py:1889]  decoder/layers/8/mlp/wi_0/kernel/value
    Shape:     float32[2048,7168]
    Physical:  ('fsdp', None)
I0425 14:12:15.437676 139840692692800 maxtext_utils.py:1889]  decoder/layers/8/mlp/wi_1/kernel/value
    Shape:     float32[2048,7168]
    Physical:  ('fsdp', None)
I0425 14:12:15.437705 139840692692800 maxtext_utils.py:1889]  decoder/layers/8/mlp/wo/kernel/value
    Shape:     float32[7168,2048]
    Physical:  (None, 'fsdp')
I0425 14:12:15.437732 139840692692800 maxtext_utils.py:1889]  decoder/layers/8/post_self_attention_layer_norm/scale/value
    Shape:     float32[2048]
    Physical:  (None,)
I0425 14:12:15.437759 139840692692800 maxtext_utils.py:1889]  decoder/layers/8/pre_self_attention_layer_norm/scale/value
    Shape:     float32[2048]
    Physical:  (None,)
I0425 14:12:15.437787 139840692692800 maxtext_utils.py:1889]  decoder/layers/8/self_attention/key/kernel/value
    Shape:     float32[2048,16,128]
    Physical:  ('fsdp', None, None)
I0425 14:12:15.437816 139840692692800 maxtext_utils.py:1889]  decoder/layers/8/self_attention/out/kernel/value
    Shape:     float32[16,128,2048]
    Physical:  (None, None, 'fsdp')
I0425 14:12:15.437844 139840692692800 maxtext_utils.py:1889]  decoder/layers/8/self_attention/query/kernel/value
    Shape:     float32[2048,16,128]
    Physical:  ('fsdp', None, None)
I0425 14:12:15.437873 139840692692800 maxtext_utils.py:1889]  decoder/layers/8/self_attention/value/kernel/value
    Shape:     float32[2048,16,128]
    Physical:  ('fsdp', None, None)
I0425 14:12:15.437901 139840692692800 maxtext_utils.py:1889]  decoder/layers/9/mlp/wi_0/kernel/value
    Shape:     float32[2048,7168]
    Physical:  ('fsdp', None)
I0425 14:12:15.437929 139840692692800 maxtext_utils.py:1889]  decoder/layers/9/mlp/wi_1/kernel/value
    Shape:     float32[2048,7168]
    Physical:  ('fsdp', None)
I0425 14:12:15.437958 139840692692800 maxtext_utils.py:1889]  decoder/layers/9/mlp/wo/kernel/value
    Shape:     float32[7168,2048]
    Physical:  (None, 'fsdp')
I0425 14:12:15.437984 139840692692800 maxtext_utils.py:1889]  decoder/layers/9/post_self_attention_layer_norm/scale/value
    Shape:     float32[2048]
    Physical:  (None,)
I0425 14:12:15.438011 139840692692800 maxtext_utils.py:1889]  decoder/layers/9/pre_self_attention_layer_norm/scale/value
    Shape:     float32[2048]
    Physical:  (None,)
I0425 14:12:15.438039 139840692692800 maxtext_utils.py:1889]  decoder/layers/9/self_attention/key/kernel/value
    Shape:     float32[2048,16,128]
    Physical:  ('fsdp', None, None)
I0425 14:12:15.438067 139840692692800 maxtext_utils.py:1889]  decoder/layers/9/self_attention/out/kernel/value
    Shape:     float32[16,128,2048]
    Physical:  (None, None, 'fsdp')
I0425 14:12:15.438096 139840692692800 maxtext_utils.py:1889]  decoder/layers/9/self_attention/query/kernel/value
    Shape:     float32[2048,16,128]
    Physical:  ('fsdp', None, None)
I0425 14:12:15.438125 139840692692800 maxtext_utils.py:1889]  decoder/layers/9/self_attention/value/kernel/value
    Shape:     float32[2048,16,128]
    Physical:  ('fsdp', None, None)
I0425 14:12:15.438154 139840692692800 maxtext_utils.py:1889]  decoder/layers/10/mlp/wi_0/kernel/value
    Shape:     float32[2048,7168]
    Physical:  ('fsdp', None)
I0425 14:12:15.438182 139840692692800 maxtext_utils.py:1889]  decoder/layers/10/mlp/wi_1/kernel/value
    Shape:     float32[2048,7168]
    Physical:  ('fsdp', None)
I0425 14:12:15.438214 139840692692800 maxtext_utils.py:1889]  decoder/layers/10/mlp/wo/kernel/value
    Shape:     float32[7168,2048]
    Physical:  (None, 'fsdp')
I0425 14:12:15.438241 139840692692800 maxtext_utils.py:1889]  decoder/layers/10/post_self_attention_layer_norm/scale/value
    Shape:     float32[2048]
    Physical:  (None,)
I0425 14:12:15.438268 139840692692800 maxtext_utils.py:1889]  decoder/layers/10/pre_self_attention_layer_norm/scale/value
    Shape:     float32[2048]
    Physical:  (None,)
I0425 14:12:15.438297 139840692692800 maxtext_utils.py:1889]  decoder/layers/10/self_attention/key/kernel/value
    Shape:     float32[2048,16,128]
    Physical:  ('fsdp', None, None)
I0425 14:12:15.438326 139840692692800 maxtext_utils.py:1889]  decoder/layers/10/self_attention/out/kernel/value
    Shape:     float32[16,128,2048]
    Physical:  (None, None, 'fsdp')
I0425 14:12:15.438354 139840692692800 maxtext_utils.py:1889]  decoder/layers/10/self_attention/query/kernel/value
    Shape:     float32[2048,16,128]
    Physical:  ('fsdp', None, None)
I0425 14:12:15.438382 139840692692800 maxtext_utils.py:1889]  decoder/layers/10/self_attention/value/kernel/value
    Shape:     float32[2048,16,128]
    Physical:  ('fsdp', None, None)
I0425 14:12:15.438410 139840692692800 maxtext_utils.py:1889]  decoder/layers/11/mlp/wi_0/kernel/value
    Shape:     float32[2048,7168]
    Physical:  ('fsdp', None)
I0425 14:12:15.438439 139840692692800 maxtext_utils.py:1889]  decoder/layers/11/mlp/wi_1/kernel/value
    Shape:     float32[2048,7168]
    Physical:  ('fsdp', None)
I0425 14:12:15.438468 139840692692800 maxtext_utils.py:1889]  decoder/layers/11/mlp/wo/kernel/value
    Shape:     float32[7168,2048]
    Physical:  (None, 'fsdp')
I0425 14:12:15.438495 139840692692800 maxtext_utils.py:1889]  decoder/layers/11/post_self_attention_layer_norm/scale/value
    Shape:     float32[2048]
    Physical:  (None,)
I0425 14:12:15.438522 139840692692800 maxtext_utils.py:1889]  decoder/layers/11/pre_self_attention_layer_norm/scale/value
    Shape:     float32[2048]
    Physical:  (None,)
I0425 14:12:15.438550 139840692692800 maxtext_utils.py:1889]  decoder/layers/11/self_attention/key/kernel/value
    Shape:     float32[2048,16,128]
    Physical:  ('fsdp', None, None)
I0425 14:12:15.438580 139840692692800 maxtext_utils.py:1889]  decoder/layers/11/self_attention/out/kernel/value
    Shape:     float32[16,128,2048]
    Physical:  (None, None, 'fsdp')
I0425 14:12:15.438609 139840692692800 maxtext_utils.py:1889]  decoder/layers/11/self_attention/query/kernel/value
    Shape:     float32[2048,16,128]
    Physical:  ('fsdp', None, None)
I0425 14:12:15.438638 139840692692800 maxtext_utils.py:1889]  decoder/layers/11/self_attention/value/kernel/value
    Shape:     float32[2048,16,128]
    Physical:  ('fsdp', None, None)
I0425 14:12:15.438860 139840692692800 maxtext_utils.py:1889]  decoder/layers/12/mlp/wi_0/kernel/value
    Shape:     float32[2048,7168]
    Physical:  ('fsdp', None)
I0425 14:12:15.438923 139840692692800 maxtext_utils.py:1889]  decoder/layers/12/mlp/wi_1/kernel/value
    Shape:     float32[2048,7168]
    Physical:  ('fsdp', None)
I0425 14:12:15.438975 139840692692800 maxtext_utils.py:1889]  decoder/layers/12/mlp/wo/kernel/value
    Shape:     float32[7168,2048]
    Physical:  (None, 'fsdp')
I0425 14:12:15.439012 139840692692800 maxtext_utils.py:1889]  decoder/layers/12/post_self_attention_layer_norm/scale/value
    Shape:     float32[2048]
    Physical:  (None,)
I0425 14:12:15.439047 139840692692800 maxtext_utils.py:1889]  decoder/layers/12/pre_self_attention_layer_norm/scale/value
    Shape:     float32[2048]
    Physical:  (None,)
I0425 14:12:15.439083 139840692692800 maxtext_utils.py:1889]  decoder/layers/12/self_attention/key/kernel/value
    Shape:     float32[2048,16,128]
    Physical:  ('fsdp', None, None)
I0425 14:12:15.439117 139840692692800 maxtext_utils.py:1889]  decoder/layers/12/self_attention/out/kernel/value
    Shape:     float32[16,128,2048]
    Physical:  (None, None, 'fsdp')
I0425 14:12:15.439150 139840692692800 maxtext_utils.py:1889]  decoder/layers/12/self_attention/query/kernel/value
    Shape:     float32[2048,16,128]
    Physical:  ('fsdp', None, None)
I0425 14:12:15.439180 139840692692800 maxtext_utils.py:1889]  decoder/layers/12/self_attention/value/kernel/value
    Shape:     float32[2048,16,128]
    Physical:  ('fsdp', None, None)
I0425 14:12:15.439210 139840692692800 maxtext_utils.py:1889]  decoder/layers/13/mlp/wi_0/kernel/value
    Shape:     float32[2048,7168]
    Physical:  ('fsdp', None)
I0425 14:12:15.439241 139840692692800 maxtext_utils.py:1889]  decoder/layers/13/mlp/wi_1/kernel/value
    Shape:     float32[2048,7168]
    Physical:  ('fsdp', None)
I0425 14:12:15.439271 139840692692800 maxtext_utils.py:1889]  decoder/layers/13/mlp/wo/kernel/value
    Shape:     float32[7168,2048]
    Physical:  (None, 'fsdp')
I0425 14:12:15.439299 139840692692800 maxtext_utils.py:1889]  decoder/layers/13/post_self_attention_layer_norm/scale/value
    Shape:     float32[2048]
    Physical:  (None,)
I0425 14:12:15.439327 139840692692800 maxtext_utils.py:1889]  decoder/layers/13/pre_self_attention_layer_norm/scale/value
    Shape:     float32[2048]
    Physical:  (None,)
I0425 14:12:15.439356 139840692692800 maxtext_utils.py:1889]  decoder/layers/13/self_attention/key/kernel/value
    Shape:     float32[2048,16,128]
    Physical:  ('fsdp', None, None)
I0425 14:12:15.439385 139840692692800 maxtext_utils.py:1889]  decoder/layers/13/self_attention/out/kernel/value
    Shape:     float32[16,128,2048]
    Physical:  (None, None, 'fsdp')
I0425 14:12:15.439414 139840692692800 maxtext_utils.py:1889]  decoder/layers/13/self_attention/query/kernel/value
    Shape:     float32[2048,16,128]
    Physical:  ('fsdp', None, None)
I0425 14:12:15.439442 139840692692800 maxtext_utils.py:1889]  decoder/layers/13/self_attention/value/kernel/value
    Shape:     float32[2048,16,128]
    Physical:  ('fsdp', None, None)
I0425 14:12:15.439470 139840692692800 maxtext_utils.py:1889]  decoder/layers/14/mlp/wi_0/kernel/value
    Shape:     float32[2048,7168]
    Physical:  ('fsdp', None)
I0425 14:12:15.439500 139840692692800 maxtext_utils.py:1889]  decoder/layers/14/mlp/wi_1/kernel/value
    Shape:     float32[2048,7168]
    Physical:  ('fsdp', None)
I0425 14:12:15.439529 139840692692800 maxtext_utils.py:1889]  decoder/layers/14/mlp/wo/kernel/value
    Shape:     float32[7168,2048]
    Physical:  (None, 'fsdp')
I0425 14:12:15.439556 139840692692800 maxtext_utils.py:1889]  decoder/layers/14/post_self_attention_layer_norm/scale/value
    Shape:     float32[2048]
    Physical:  (None,)
I0425 14:12:15.439583 139840692692800 maxtext_utils.py:1889]  decoder/layers/14/pre_self_attention_layer_norm/scale/value
    Shape:     float32[2048]
    Physical:  (None,)
I0425 14:12:15.439613 139840692692800 maxtext_utils.py:1889]  decoder/layers/14/self_attention/key/kernel/value
    Shape:     float32[2048,16,128]
    Physical:  ('fsdp', None, None)
I0425 14:12:15.439642 139840692692800 maxtext_utils.py:1889]  decoder/layers/14/self_attention/out/kernel/value
    Shape:     float32[16,128,2048]
    Physical:  (None, None, 'fsdp')
I0425 14:12:15.439701 139840692692800 maxtext_utils.py:1889]  decoder/layers/14/self_attention/query/kernel/value
    Shape:     float32[2048,16,128]
    Physical:  ('fsdp', None, None)
I0425 14:12:15.439732 139840692692800 maxtext_utils.py:1889]  decoder/layers/14/self_attention/value/kernel/value
    Shape:     float32[2048,16,128]
    Physical:  ('fsdp', None, None)
I0425 14:12:15.439760 139840692692800 maxtext_utils.py:1889]  decoder/layers/15/mlp/wi_0/kernel/value
    Shape:     float32[2048,7168]
    Physical:  ('fsdp', None)
I0425 14:12:15.439789 139840692692800 maxtext_utils.py:1889]  decoder/layers/15/mlp/wi_1/kernel/value
    Shape:     float32[2048,7168]
    Physical:  ('fsdp', None)
I0425 14:12:15.439817 139840692692800 maxtext_utils.py:1889]  decoder/layers/15/mlp/wo/kernel/value
    Shape:     float32[7168,2048]
    Physical:  (None, 'fsdp')
I0425 14:12:15.439845 139840692692800 maxtext_utils.py:1889]  decoder/layers/15/post_self_attention_layer_norm/scale/value
    Shape:     float32[2048]
    Physical:  (None,)
I0425 14:12:15.439873 139840692692800 maxtext_utils.py:1889]  decoder/layers/15/pre_self_attention_layer_norm/scale/value
    Shape:     float32[2048]
    Physical:  (None,)
I0425 14:12:15.439901 139840692692800 maxtext_utils.py:1889]  decoder/layers/15/self_attention/key/kernel/value
    Shape:     float32[2048,16,128]
    Physical:  ('fsdp', None, None)
I0425 14:12:15.439930 139840692692800 maxtext_utils.py:1889]  decoder/layers/15/self_attention/out/kernel/value
    Shape:     float32[16,128,2048]
    Physical:  (None, None, 'fsdp')
I0425 14:12:15.439963 139840692692800 maxtext_utils.py:1889]  decoder/layers/15/self_attention/query/kernel/value
    Shape:     float32[2048,16,128]
    Physical:  ('fsdp', None, None)
I0425 14:12:15.439992 139840692692800 maxtext_utils.py:1889]  decoder/layers/15/self_attention/value/kernel/value
    Shape:     float32[2048,16,128]
    Physical:  ('fsdp', None, None)
I0425 14:12:15.440021 139840692692800 maxtext_utils.py:1889]  decoder/logits_dense/kernel/value
    Shape:     float32[2048,32000]
    Physical:  ('fsdp', None)
I0425 14:12:15.440049 139840692692800 maxtext_utils.py:1889]  token_embedder/embedding/value
    Shape:     float32[32000,2048]
    Physical:  (None, 'fsdp')

I0425 14:12:15.929716 139840692692800 nnx_decoders.py:1023] nnx_decoders/y_in Logical: bfloat16[32,2048,2048]...................................... ('activation_batch', 'activation_norm_length', 'activation_embed').
I0425 14:12:15.929807 139840692692800 nnx_decoders.py:1023] nnx_decoders/y_in Physical: bfloat16[32,2048,2048]...................................... ('fsdp', None, None).
I0425 14:12:15.934547 139840692692800 nnx_decoders.py:1023] Unknown Logical: bfloat16[32,2048,2048]...................................... ('activation_batch', 'activation_norm_length', 'activation_embed').
I0425 14:12:15.934607 139840692692800 nnx_decoders.py:1023] Unknown Physical: bfloat16[32,2048,2048]...................................... ('fsdp', None, None).
I0425 14:12:15.951036 139840692692800 attentions.py:1088] attentions/inputs_q Logical: bfloat16[32,2048,2048]...................................... ('activation_batch', 'activation_attn_length', 'activation_attn_embed').
I0425 14:12:15.951092 139840692692800 attentions.py:1088] attentions/inputs_q Physical: bfloat16[32,2048,2048]...................................... ('fsdp', None, None).
I0425 14:12:15.966898 139840692692800 attentions.py:1089] attentions/inputs_kv Logical: bfloat16[32,2048,2048]...................................... ('activation_batch', 'activation_attn_length', 'activation_attn_embed').
I0425 14:12:15.966958 139840692692800 attentions.py:1089] attentions/inputs_kv Physical: bfloat16[32,2048,2048]...................................... ('fsdp', None, None).
I0425 14:12:15.989531 139840692692800 attentions.py:1154] attentions/query Logical: bfloat16[32,2048,16,128].................................... ('activation_kv_batch', 'activation_attn_length', 'activation_kv_heads', 'activation_kv_head_dim').
I0425 14:12:15.989599 139840692692800 attentions.py:1154] attentions/query Physical: bfloat16[32,2048,16,128].................................... ('fsdp', None, None, None).
I0425 14:12:16.005348 139840692692800 attentions.py:1155] attentions/key Logical: bfloat16[32,2048,16,128].................................... ('activation_kv_batch', 'activation_attn_length', 'activation_kv_heads', 'activation_kv_head_dim').
I0425 14:12:16.005406 139840692692800 attentions.py:1155] attentions/key Physical: bfloat16[32,2048,16,128].................................... ('fsdp', None, None, None).
I0425 14:12:16.021230 139840692692800 attentions.py:1156] attentions/value Logical: bfloat16[32,2048,16,128].................................... ('activation_kv_batch', 'activation_attn_length', 'activation_kv_heads', 'activation_kv_head_dim').
I0425 14:12:16.021286 139840692692800 attentions.py:1156] attentions/value Physical: bfloat16[32,2048,16,128].................................... ('fsdp', None, None, None).
I0425 14:12:16.047754 139840692692800 attentions.py:1198] attentions/out Logical: bfloat16[32,2048,16,128].................................... ('activation_batch', 'activation_attn_length', 'activation_heads', 'activation_kv').
I0425 14:12:16.047821 139840692692800 attentions.py:1198] attentions/out Physical: bfloat16[32,2048,16,128].................................... ('fsdp', None, None, None).
I0425 14:12:16.068092 139840692692800 linears.py:525] linears/x Logical: bfloat16[32,2048,7168]...................................... ('activation_batch', 'activation_length', 'activation_mlp').
I0425 14:12:16.068165 139840692692800 linears.py:525] linears/x Physical: bfloat16[32,2048,7168]...................................... ('fsdp', None, None).
I0425 14:13:16.950551 139840692692800 max_utils.py:791] Total memory size: 1.8 GB, Output size: 0.4 GB, Temp size: 1.4 GB, Argument size: 0.4 GB, Host temp size: 0.0 GB.
I0425 14:13:16.961562 139840692692800 metric_logger.py:301] number parameters: 1.104 billion
I0425 14:14:17.767107 139840692692800 checkpointing.py:794] Waiting for step 0 to finish before checkpoint...
I0425 14:14:17.991563 139840692692800 checkpointing.py:798] Waited 0.2244737148284912 seconds for step 0 to finish before starting checkpointing.
I0425 14:14:17.994938 139840692692800 checkpoint_manager.py:2009] [process=5][thread=MainThread][wait_until_finished] No Save Finalize thread to wait for. Returning.
I0425 14:14:17.996842 139840692692800 checkpoint_manager.py:1512] [process=5] Saving checkpoint at step 0
I0425 14:14:17.998222 139840692692800 event_tracking.py:70] [process=5] [async] Started save checkpoint @ gs://lance-maxtext/nnx_ckpt_xpk_feat_nnx_post_train_fixes_20260425_121355/nnx_xpk_feat_nnx_post_train_fixes_20260425_121355_13_scan_layers_false/checkpoints/0.
I0425 14:14:18.393295 139840692692800 signaling_client.py:364] Using JaxDistributedSignalingClient
I0425 14:14:18.394484 139840692692800 jax_array_handlers.py:360] Scheduling D2H of 648 prioritized jax.Array.
I0425 14:14:18.394597 139840692692800 replica_slices.py:424] Transferring arrays to host memory with options: use_replica_parallel=True, min_slice_bytes_for_replica_parallel=None, max_replicas_for_replica_parallel=None, enable_pinned_host_transfer=False
I0425 14:14:18.695614 139840692692800 base_pytree_checkpoint_handler.py:154] [process=5][thread=MainThread] Initiated "orbax.checkpoint._src.serialization.jax_array_handlers.ArrayHandler".serialize. Time taken: 0.306863s
I0425 14:14:18.695803 139840692692800 base_pytree_checkpoint_handler.py:130] [process=5] /jax/orbax/write/blocking_gbytes_per_sec: 4.237 GiB/s (total gbytes: 1.5 GiB) (time elapsed: 0.3640439510345459 s) (per-host)
I0425 14:14:18.695854 139840692692800 base_pytree_checkpoint_handler.py:768] [process=5][thread=MainThread] Initiated Pytree async_save. Time taken: 0.364103s (batch_requests_ready=0.024409s, total_serialization_initiated=0.339627s, others=0.000066s)
I0425 14:14:18.696224 139840692692800 composite_checkpoint_handler.py:715] [process=5][thread=MainThread] Initiated CompositeCheckpointHandler.async_save. Time taken: 0.368530s (all_items=0.000018s, per_item={'items': '0.00001812'}, temp_paths=0.368511)
I0425 14:14:18.697051 139840692692800 event_tracking.py:125] [process=5] [async] Finished blocking save in 0.70 seconds. Continuing save @ gs://lance-maxtext/nnx_ckpt_xpk_feat_nnx_post_train_fixes_20260425_121355/nnx_xpk_feat_nnx_post_train_fixes_20260425_121355_13_scan_layers_false/checkpoints/0.
I0425 14:14:18.697407 139715849475840 async_checkpointer.py:76] [process=5][thread=async_save] Background save thread started. Deadline for this save operation is 2026-04-25 14:34:18.697368
I0425 14:14:18.749935 139840692692800 checkpoint_manager.py:1560] [process=5][thread=MainThread][step=0] Starting CheckpointManager Save Finalize thread=save_finalize
I0425 14:14:18.750250 139715344852736 async_checkpointer.py:280] [process=5][thread=save_finalize] Waiting for background save thread=async_save.
I0425 14:14:18.750397 139840692692800 standard_logger.py:34] {'step': 0, 'event_type': 'save', 'directory': 'gs://lance-maxtext/nnx_ckpt_xpk_feat_nnx_post_train_fixes_20260425_121355/nnx_xpk_feat_nnx_post_train_fixes_20260425_121355_13_scan_layers_false/checkpoints', 'reached_preemption': False, 'preemption_received_at': None, 'synchronous': False, 'wait_for_prev_start_time': 1777126457.9949098, 'wait_for_prev_duration_secs': 7.700920104980469e-05, 'time_between_consecutive_saves_sec': None, 'checkpointer_blocking_start_time': 1777126457.996881, 'checkpointer_blocking_duration_secs': 0.7006876468658447, 'get_old_steps_start_time': 1777126458.6975951, 'get_old_steps_duration_secs': 3.147125244140625e-05, 'checkpoint_manager_blocking_start_time': 1777126457.9928951, 'checkpoint_manager_blocking_duration_secs': 0.7574617862701416}
I0425 14:14:18.750643 139840692692800 checkpointing.py:409] Started an asynchronous checkpoint save for step 0
I0425 14:14:18.750855 139840692692800 max_utils.py:750] 
Memstats: After params initialized:
I0425 14:14:18.750915 139840692692800 max_utils.py:756] 	Using (GB) 0.82 / 31.25 (2.624000%) on TPU_18(process=5,(2,4,0,0))
I0425 14:14:18.750949 139840692692800 max_utils.py:756] 	Using (GB) 0.82 / 31.25 (2.624000%) on TPU_19(process=5,(3,4,0,0))
I0425 14:14:18.750977 139840692692800 max_utils.py:756] 	Using (GB) 0.82 / 31.25 (2.624000%) on TPU_22(process=5,(2,5,0,0))
I0425 14:14:18.751001 139840692692800 max_utils.py:756] 	Using (GB) 0.82 / 31.25 (2.624000%) on TPU_23(process=5,(3,5,0,0))
I0425 14:14:19.120110 139840692692800 metric_logger.py:196] completed step: 0, seconds: 60.798, TFLOP/s/device: 0.223, Tokens/s/device: 33.685, total_weights: 65536, loss: 10.874, lm_loss: 10.874, perplexity: 52794.566
I0425 14:14:19.254829 139840692692800 metric_logger.py:196] completed step: 1, seconds: 1.342, TFLOP/s/device: 10.123, Tokens/s/device: 1525.854, total_weights: 65536, loss: 10.874, lm_loss: 10.874, perplexity: 52794.566
I0425 14:14:19.784196 139840692692800 metric_logger.py:196] completed step: 2, seconds: 0.053, TFLOP/s/device: 254.526, Tokens/s/device: 38364.992, total_weights: 65536, loss: 10.265, lm_loss: 10.265, perplexity: 28702.514
I0425 14:14:19.924346 139840692692800 metric_logger.py:196] completed step: 3, seconds: 0.422, TFLOP/s/device: 32.217, Tokens/s/device: 4856.142, total_weights: 65536, loss: 9.736, lm_loss: 9.736, perplexity: 16919.967
I0425 14:14:20.205440 139840692692800 metric_logger.py:196] completed step: 4, seconds: 0.218, TFLOP/s/device: 62.285, Tokens/s/device: 9388.251, total_weights: 65536, loss: 9.279, lm_loss: 9.279, perplexity: 10710.462
I0425 14:14:20.228184 139840692692800 metric_logger.py:196] completed step: 5, seconds: 0.140, TFLOP/s/device: 96.908, Tokens/s/device: 14606.974, total_weights: 65536, loss: 8.894, lm_loss: 8.894, perplexity: 7286.325
I0425 14:14:22.396586    2758 google_auth_provider.cc:181] Running on GCE, using service account 562977990677-compute@developer.gserviceaccount.com
I0425 14:14:24.601145 139715353245440 array_metadata_store.py:203] [process=5][thread=array_type_handler] Wrote 648 array_metadata.ArrayMetadata to gs://lance-maxtext/nnx_ckpt_xpk_feat_nnx_post_train_fixes_20260425_121355/nnx_xpk_feat_nnx_post_train_fixes_20260425_121355_13_scan_layers_false/checkpoints/0/items/array_metadatas/process_5
I0425 14:14:42.829510 139840692692800 metric_logger.py:196] completed step: 6, seconds: 0.281, TFLOP/s/device: 48.419, Tokens/s/device: 7298.308, total_weights: 65536, loss: 8.595, lm_loss: 8.595, perplexity: 5404.646
I0425 14:14:42.964911 139840692692800 metric_logger.py:196] completed step: 7, seconds: 22.478, TFLOP/s/device: 0.604, Tokens/s/device: 91.113, total_weights: 65536, loss: 8.387, lm_loss: 8.387, perplexity: 4389.022
I0425 14:14:43.102923 139840692692800 metric_logger.py:196] completed step: 8, seconds: 0.147, TFLOP/s/device: 92.491, Tokens/s/device: 13941.267, total_weights: 65536, loss: 8.258, lm_loss: 8.258, perplexity: 3856.821
I0425 14:14:43.245682 139840692692800 checkpointing.py:794] Waiting for step 9 to finish before checkpoint...
I0425 14:14:43.250057 139840692692800 checkpointing.py:798] Waited 0.004393815994262695 seconds for step 9 to finish before starting checkpointing.
I0425 14:14:43.254357 139840692692800 checkpoint_manager.py:2020] [process=5][thread=MainThread][step=0][wait_until_finished] Waiting for Save Finalize thread (save_finalize) to complete.
I0425 14:14:51.707593 139715849475840 base_pytree_checkpoint_handler.py:130] [process=5] /jax/orbax/write/gbytes_per_sec: 47.328 MiB/s (total gbytes: 1.5 GiB) (time elapsed: 33.375784158706665 s) (per-host)
I0425 14:14:51.707738 139715849475840 async_checkpointer.py:90] [process=5][thread=async_save] 3 Handler Commit operations completed. Time taken: 33.010211s.
I0425 14:14:59.985031 139715849475840 async_checkpointer.py:160] [process=5][thread=async_save] Background save thread done. Time taken: 41.287488s.
I0425 14:14:59.985360 139715344852736 async_checkpointer.py:288] [process=5][thread=save_finalize] Done with waiting for background save thread=async_save.
I0425 14:14:59.985496 139715344852736 async_checkpointer.py:298] [process=5][thread=save_finalize] No errors found in background save thread=async_save.
I0425 14:14:59.985546 139715344852736 checkpoint_manager.py:2137] [process=5][thread=save_finalize][step=0] CheckpointManager Save Finalize is syncing with other hosts...
I0425 14:14:59.988141 139715344852736 checkpoint_manager.py:2146] [process=5][thread=save_finalize][step=0] CheckpointManager Save Finalize is done on all hosts.
I0425 14:14:59.988397 139840692692800 checkpoint_manager.py:2032] [process=5][thread=MainThread][step=0][wait_until_finished] Done waiting for Save Finalize thread (save_finalize) running at step=0.
W0425 14:14:59.988530 139840692692800 checkpoint_manager.py:1452] Waiting for previous save to complete took 16.734174 seconds. If this number is high, consider checkpointing less frequently.
I0425 14:14:59.991121 139840692692800 checkpoint_manager.py:1512] [process=5] Saving checkpoint at step 9
I0425 14:14:59.993337 139840692692800 event_tracking.py:70] [process=5] [async] Started save checkpoint @ gs://lance-maxtext/nnx_ckpt_xpk_feat_nnx_post_train_fixes_20260425_121355/nnx_xpk_feat_nnx_post_train_fixes_20260425_121355_13_scan_layers_false/checkpoints/9.
I0425 14:15:01.289032 139840692692800 jax_array_handlers.py:360] Scheduling D2H of 648 prioritized jax.Array.
I0425 14:15:01.289576 139840692692800 replica_slices.py:424] Transferring arrays to host memory with options: use_replica_parallel=True, min_slice_bytes_for_replica_parallel=None, max_replicas_for_replica_parallel=None, enable_pinned_host_transfer=False
I0425 14:15:01.422793 139840692692800 base_pytree_checkpoint_handler.py:154] [process=5][thread=MainThread] Initiated "orbax.checkpoint._src.serialization.jax_array_handlers.ArrayHandler".serialize. Time taken: 0.139611s
I0425 14:15:01.422956 139840692692800 base_pytree_checkpoint_handler.py:130] [process=5] /jax/orbax/write/blocking_gbytes_per_sec: 2.144 GiB/s (total gbytes: 1.5 GiB) (time elapsed: 0.7193360328674316 s) (per-host)
I0425 14:15:01.423006 139840692692800 base_pytree_checkpoint_handler.py:768] [process=5][thread=MainThread] Initiated Pytree async_save. Time taken: 0.719393s (batch_requests_ready=0.023402s, total_serialization_initiated=0.695926s, others=0.000065s)
I0425 14:15:01.423391 139840692692800 composite_checkpoint_handler.py:715] [process=5][thread=MainThread] Initiated CompositeCheckpointHandler.async_save. Time taken: 0.723869s (all_items=0.000015s, per_item={'items': '0.00001550'}, temp_paths=0.723853)
I0425 14:15:01.425028 139840692692800 event_tracking.py:125] [process=5] [async] Finished blocking save in 1.43 seconds. Continuing save @ gs://lance-maxtext/nnx_ckpt_xpk_feat_nnx_post_train_fixes_20260425_121355/nnx_xpk_feat_nnx_post_train_fixes_20260425_121355_13_scan_layers_false/checkpoints/9.
I0425 14:15:01.425395 139715344852736 async_checkpointer.py:76] [process=5][thread=async_save] Background save thread started. Deadline for this save operation is 2026-04-25 14:35:01.425359
I0425 14:15:01.437013 139840692692800 checkpoint_manager.py:1560] [process=5][thread=MainThread][step=9] Starting CheckpointManager Save Finalize thread=save_finalize
I0425 14:15:01.437270 139714791196416 async_checkpointer.py:280] [process=5][thread=save_finalize] Waiting for background save thread=async_save.
I0425 14:15:01.437435 139840692692800 standard_logger.py:34] {'step': 9, 'event_type': 'save', 'directory': 'gs://lance-maxtext/nnx_ckpt_xpk_feat_nnx_post_train_fixes_20260425_121355/nnx_xpk_feat_nnx_post_train_fixes_20260425_121355_13_scan_layers_false/checkpoints', 'reached_preemption': False, 'preemption_received_at': None, 'synchronous': False, 'wait_for_prev_start_time': 1777126483.2543244, 'wait_for_prev_duration_secs': 16.734174013137817, 'time_between_consecutive_saves_sec': None, 'checkpointer_blocking_start_time': 1777126499.9911711, 'checkpointer_blocking_duration_secs': 1.434375286102295, 'get_old_steps_start_time': 1777126501.4255698, 'get_old_steps_duration_secs': 3.075599670410156e-05, 'checkpoint_manager_blocking_start_time': 1777126483.2511191, 'checkpoint_manager_blocking_duration_secs': 18.186280250549316}
I0425 14:15:01.437696 139840692692800 checkpointing.py:409] Started an asynchronous checkpoint save for step 9
I0425 14:15:01.437744 139840692692800 checkpoint_manager.py:2020] [process=5][thread=MainThread][step=9][wait_until_finished] Waiting for Save Finalize thread (save_finalize) to complete.
I0425 14:15:06.158831 139715353245440 array_metadata_store.py:203] [process=5][thread=array_type_handler] Wrote 648 array_metadata.ArrayMetadata to gs://lance-maxtext/nnx_ckpt_xpk_feat_nnx_post_train_fixes_20260425_121355/nnx_xpk_feat_nnx_post_train_fixes_20260425_121355_13_scan_layers_false/checkpoints/9/items/array_metadatas/process_5
I0425 14:15:42.481284 139715344852736 base_pytree_checkpoint_handler.py:130] [process=5] /jax/orbax/write/gbytes_per_sec: 37.810 MiB/s (total gbytes: 1.5 GiB) (time elapsed: 41.77762246131897 s) (per-host)
I0425 14:15:42.481415 139715344852736 async_checkpointer.py:90] [process=5][thread=async_save] 3 Handler Commit operations completed. Time taken: 41.055904s.
I0425 14:15:50.438334 139715344852736 async_checkpointer.py:160] [process=5][thread=async_save] Background save thread done. Time taken: 49.012808s.
I0425 14:15:50.438593 139714791196416 async_checkpointer.py:288] [process=5][thread=save_finalize] Done with waiting for background save thread=async_save.
I0425 14:15:50.438730 139714791196416 async_checkpointer.py:298] [process=5][thread=save_finalize] No errors found in background save thread=async_save.
I0425 14:15:50.438780 139714791196416 checkpoint_manager.py:2137] [process=5][thread=save_finalize][step=9] CheckpointManager Save Finalize is syncing with other hosts...
I0425 14:15:50.440468 139714791196416 checkpoint_manager.py:2146] [process=5][thread=save_finalize][step=9] CheckpointManager Save Finalize is done on all hosts.
I0425 14:15:50.440643 139840692692800 checkpoint_manager.py:2032] [process=5][thread=MainThread][step=9][wait_until_finished] Done waiting for Save Finalize thread (save_finalize) running at step=9.
I0425 14:15:50.440974 139840692692800 checkpoint_manager.py:2009] [process=5][thread=MainThread][wait_until_finished] No Save Finalize thread to wait for. Returning.
I0425 14:15:50.441957 139840692692800 metric_logger.py:196] completed step: 9, seconds: 0.135, TFLOP/s/device: 100.707, Tokens/s/device: 15179.703, total_weights: 65536, loss: 8.182, lm_loss: 8.182, perplexity: 3575.125
Per train step:
 Total TFLOPs: 13.59 
 split as 93.93% learnable weight flops and 6.07% attention flops
XPK End: Sat Apr 25 14:15:59 UTC 2026
EXIT_CODE=0