XPK Start: Thu Apr 23 19:09:24 UTC 2026 2026-04-23 19:09:29.051508: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:467] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered WARNING: All log messages before absl::InitializeLog() is called are written to STDERR E0000 00:00:1776971369.064113 10 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered E0000 00:00:1776971369.067792 10 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered W0000 00:00:1776971369.079332 10 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once. W0000 00:00:1776971369.079351 10 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once. W0000 00:00:1776971369.079354 10 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once. W0000 00:00:1776971369.079356 10 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once. 2026-04-23 19:09:48.880334: 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) I0423 19:09:49.396461 139434758117184 max_utils.py:273] Attempting to initialize the jax distributed system... INFO:2026-04-23 19:09:58,438:jax._src.distributed:140: Starting JAX distributed service on [::]:8482 I0423 19:09:58.438310 139434758117184 distributed.py:140] Starting JAX distributed service on [::]:8482 INFO:2026-04-23 19:09:58,442:jax._src.distributed:157: Connecting to JAX distributed service on mt-01-base-tc2wq-slice-job-0-0.mt-01-base-tc2wq:8482 I0423 19:09:58.442149 139434758117184 distributed.py:157] Connecting to JAX distributed service on mt-01-base-tc2wq-slice-job-0-0.mt-01-base-tc2wq:8482 I0423 19:10:00.856587 139434758117184 max_utils.py:284] Jax distributed system initialized! I0423 19:10:08.064702 139434758117184 max_utils.py:800] System Information: Jax Version: 0.8.1 I0423 19:10:08.064810 139434758117184 max_utils.py:801] System Information: Jaxlib Version: 0.8.1 I0423 19:10:08.064852 139434758117184 max_utils.py:802] System Information: Jax Backend: PJRT C API TFRT TPU v6 lite Built on Nov 12 2025 14:16:36 (1762985796) cl/831091709 I0423 19:10:08.064890 139434758117184 train_utils.py:347] WARNING: Sequence packing is essentially ignored for synthetic data. Please use a real dataset to use sequence packing. I0423 19:10:08.685579 139434758117184 maxtext_utils.py:1517] Num_devices: 32, shape (1, 1, 1, 32, 1, 1, 1, 1, 1, 1, 1, 1, 1) I0423 19:10:08.685867 139434758117184 checkpointing.py:677] Setting up checkpoint logger... I0423 19:10:08.685921 139434758117184 checkpointing.py:233] Creating checkpoint manager with ocdbt=True and zarr3=True I0423 19:10:08.685964 139434758117184 pytree_checkpoint_handler.py:589] save_device_host_concurrent_bytes=None I0423 19:10:08.686358 139434758117184 base_pytree_checkpoint_handler.py:415] 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 0x7ed02ad79100>, enable_pinned_host_transfer=False, save_concurrent_bytes: 96000000000 (89.4 GiB), restore_concurrent_bytes: 96000000000 (89.4 GiB) I0423 19:10:12.392728 139434758117184 checkpointing.py:265] Enabling policy for fixed interval checkpointing. I0423 19:10:12.392972 139434758117184 checkpoint_manager.py:709] [process=6][thread=MainThread] CheckpointManager init: checkpointers=None, item_names=('items',), item_handlers={'items': <orbax.checkpoint._src.handlers.pytree_checkpoint_handler.PyTreeCheckpointHandler object at 0x7ebbc81adfd0>}, handler_registry=None I0423 19:10:12.393222 139434758117184 composite_checkpoint_handler.py:237] Deferred registration for item: "items". Adding handler `<orbax.checkpoint._src.handlers.pytree_checkpoint_handler.PyTreeCheckpointHandler object at 0x7ebbc81adfd0>` 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`. I0423 19:10:12.393273 139434758117184 composite_checkpoint_handler.py:237] Deferred registration for item: "metrics". Adding handler `<orbax.checkpoint._src.handlers.json_checkpoint_handler.JsonCheckpointHandler object at 0x7ebb881bfda0>` 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`. I0423 19:10:12.393310 139434758117184 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 0x7ebbc81adfd0>, ('items', <class 'orbax.checkpoint._src.handlers.pytree_checkpoint_handler.PyTreeRestoreArgs'>): <orbax.checkpoint._src.handlers.pytree_checkpoint_handler.PyTreeCheckpointHandler object at 0x7ebbc81adfd0>, ('metrics', <class 'orbax.checkpoint._src.handlers.json_checkpoint_handler.JsonSaveArgs'>): <orbax.checkpoint._src.handlers.json_checkpoint_handler.JsonCheckpointHandler object at 0x7ebb881bfda0>, ('metrics', <class 'orbax.checkpoint._src.handlers.json_checkpoint_handler.JsonRestoreArgs'>): <orbax.checkpoint._src.handlers.json_checkpoint_handler.JsonCheckpointHandler object at 0x7ebb881bfda0>}). I0423 19:10:12.393884 139434758117184 abstract_checkpointer.py:35] orbax-checkpoint version: 0.11.33 I0423 19:10:12.393963 139434758117184 async_checkpointer.py:177] [process=6][thread=MainThread] Using barrier_sync_fn: <function get_barrier_sync_fn.<locals>._fn at 0x7ebb1060e840> timeout: 600 secs and primary_host=0 for async checkpoint writes I0423 19:10:13.582292 139434758117184 checkpoint_manager.py:1818] Found 0 checkpoint steps in gs://lance-maxtext/linen_ckpt_xpk_feat_Migrate_Decoder_And_Tests_to_NNX_20260423_190840/linen_xpk_feat_Migrate_Decoder_And_Tests_to_NNX_20260423_190840_01_base/checkpoints I0423 19:10:13.592996 139434758117184 checkpoint_manager.py:929] [process=6][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/linen_ckpt_xpk_feat_Migrate_Decoder_And_Tests_to_NNX_20260423_190840/linen_xpk_feat_Migrate_Decoder_And_Tests_to_NNX_20260423_190840_01_base/checkpoints: <orbax.checkpoint.checkpoint_manager.CheckpointManager object at 0x7ebb881b8d70> I0423 19:10:13.593133 139434758117184 checkpointing.py:301] Checkpoint manager created! I0423 19:10:14.506455 139434758117184 nnx_wrappers.py:442] Unknown Logical: bfloat16[32,2048,2048]...................................... ('activation_batch', 'activation_norm_length', 'activation_embed'). I0423 19:10:14.506566 139434758117184 nnx_wrappers.py:442] Unknown Physical: bfloat16[32,2048,2048]...................................... ('fsdp', None, None). I0423 19:10:14.875182 139434758117184 attentions.py:1088] attentions/inputs_q Logical: bfloat16[32,2048,2048]...................................... ('activation_batch', 'activation_attn_length', 'activation_attn_embed'). I0423 19:10:14.875277 139434758117184 attentions.py:1088] attentions/inputs_q Physical: bfloat16[32,2048,2048]...................................... ('fsdp', None, None). I0423 19:10:14.891075 139434758117184 attentions.py:1089] attentions/inputs_kv Logical: bfloat16[32,2048,2048]...................................... ('activation_batch', 'activation_attn_length', 'activation_attn_embed'). I0423 19:10:14.891148 139434758117184 attentions.py:1089] attentions/inputs_kv Physical: bfloat16[32,2048,2048]...................................... ('fsdp', None, None). I0423 19:10:14.915007 139434758117184 attentions.py:1154] attentions/query Logical: bfloat16[32,2048,16,128].................................... ('activation_kv_batch', 'activation_attn_length', 'activation_kv_heads', 'activation_kv_head_dim'). I0423 19:10:14.915078 139434758117184 attentions.py:1154] attentions/query Physical: bfloat16[32,2048,16,128].................................... ('fsdp', None, None, None). I0423 19:10:14.930974 139434758117184 attentions.py:1155] attentions/key Logical: bfloat16[32,2048,16,128].................................... ('activation_kv_batch', 'activation_attn_length', 'activation_kv_heads', 'activation_kv_head_dim'). I0423 19:10:14.931043 139434758117184 attentions.py:1155] attentions/key Physical: bfloat16[32,2048,16,128].................................... ('fsdp', None, None, None). I0423 19:10:14.946813 139434758117184 attentions.py:1156] attentions/value Logical: bfloat16[32,2048,16,128].................................... ('activation_kv_batch', 'activation_attn_length', 'activation_kv_heads', 'activation_kv_head_dim'). I0423 19:10:14.946875 139434758117184 attentions.py:1156] attentions/value Physical: bfloat16[32,2048,16,128].................................... ('fsdp', None, None, None). I0423 19:10:14.970834 139434758117184 attentions.py:1197] attentions/out Logical: bfloat16[32,2048,16,128].................................... ('activation_batch', 'activation_attn_length', 'activation_heads', 'activation_kv'). I0423 19:10:14.970906 139434758117184 attentions.py:1197] attentions/out Physical: bfloat16[32,2048,16,128].................................... ('fsdp', None, None, None). I0423 19:10:14.990351 139434758117184 linears.py:525] linears/x Logical: bfloat16[32,2048,7168]...................................... ('activation_batch', 'activation_length', 'activation_mlp'). I0423 19:10:14.990419 139434758117184 linears.py:525] linears/x Physical: bfloat16[32,2048,7168]...................................... ('fsdp', None, None). I0423 19:10:15.179907 139434758117184 checkpointing.py:577] checkpoint manager exists so trying to load this run's existing checkpoint I0423 19:10:15.180018 139434758117184 checkpointing.py:665] No existing checkpoints found, not restoring checkpoint. fsdp: 32 I0423 19:10:16.617250 139434758117184 maxtext_utils.py:1620] params/params/decoder/decoder_norm/scale Shape: float32[2048] Logical: PartitionSpec('norm',) Physical: (None,) I0423 19:10:16.617382 139434758117184 maxtext_utils.py:1620] params/params/decoder/layers/mlp/wi_0/kernel Shape: float32[2048,16,7168] Logical: PartitionSpec('embed', 'layers', 'mlp') Physical: ('fsdp', None, None) I0423 19:10:16.617437 139434758117184 maxtext_utils.py:1620] params/params/decoder/layers/mlp/wi_1/kernel Shape: float32[2048,16,7168] Logical: PartitionSpec('embed', 'layers', 'mlp') Physical: ('fsdp', None, None) I0423 19:10:16.617504 139434758117184 maxtext_utils.py:1620] params/params/decoder/layers/mlp/wo/kernel Shape: float32[7168,16,2048] Logical: PartitionSpec('mlp', 'layers', 'embed') Physical: (None, None, 'fsdp') I0423 19:10:16.617560 139434758117184 maxtext_utils.py:1620] params/params/decoder/layers/post_self_attention_layer_norm/scale Shape: float32[2048,16] Logical: PartitionSpec('norm', 'layers') Physical: (None, None) I0423 19:10:16.617600 139434758117184 maxtext_utils.py:1620] params/params/decoder/layers/pre_self_attention_layer_norm/scale Shape: float32[2048,16] Logical: PartitionSpec('norm', 'layers') Physical: (None, None) I0423 19:10:16.617653 139434758117184 maxtext_utils.py:1620] params/params/decoder/layers/self_attention/key/kernel Shape: float32[2048,16,16,128] Logical: PartitionSpec('embed', 'layers', 'kv_heads', 'kv_head_dim') Physical: ('fsdp', None, None, None) I0423 19:10:16.617706 139434758117184 maxtext_utils.py:1620] params/params/decoder/layers/self_attention/out/kernel Shape: float32[16,16,128,2048] Logical: PartitionSpec('heads', 'layers', 'kv', 'embed') Physical: (None, None, None, 'fsdp') I0423 19:10:16.617746 139434758117184 maxtext_utils.py:1620] params/params/decoder/layers/self_attention/query/kernel Shape: float32[2048,16,16,128] Logical: PartitionSpec('embed', 'layers', 'q_heads', 'kv') Physical: ('fsdp', None, None, None) I0423 19:10:16.617784 139434758117184 maxtext_utils.py:1620] params/params/decoder/layers/self_attention/value/kernel Shape: float32[2048,16,16,128] Logical: PartitionSpec('embed', 'layers', 'kv_heads', 'kv_head_dim') Physical: ('fsdp', None, None, None) I0423 19:10:16.617831 139434758117184 maxtext_utils.py:1620] params/params/decoder/logits_dense/kernel Shape: float32[2048,32000] Logical: PartitionSpec('embed', 'vocab') Physical: ('fsdp', None) I0423 19:10:16.617881 139434758117184 maxtext_utils.py:1620] params/params/token_embedder/embedding Shape: float32[32000,2048] Logical: PartitionSpec('vocab', 'embed') Physical: (None, 'fsdp') I0423 19:10:17.124712 139434758117184 train.py:155] train/xent Logical: float32[32,2048]............................................ ('activation_embed_and_logits_batch', 'activation_length'). I0423 19:10:17.124811 139434758117184 train.py:155] train/xent Physical: float32[32,2048]............................................ ('fsdp', None). I0423 19:10:17.139607 139434758117184 train.py:162] train/z_loss Logical: float32[32,2048]............................................ ('activation_embed_and_logits_batch', 'activation_length'). I0423 19:10:17.139669 139434758117184 train.py:162] train/z_loss Physical: float32[32,2048]............................................ ('fsdp', None). I0423 19:10:27.799489 139434758117184 max_utils.py:791] Total memory size: 1.5 GB, Output size: 0.4 GB, Temp size: 1.1 GB, Argument size: 0.4 GB, Host temp size: 0.0 GB. I0423 19:10:27.800431 139434758117184 metric_logger.py:289] number parameters: 1.104 billion I0423 19:10:38.996460 139434758117184 checkpointing.py:772] Waiting for step 0 to finish before checkpoint... I0423 19:10:39.150146 139434758117184 checkpointing.py:776] Waited 0.15363693237304688 seconds for step 0 to finish before starting checkpointing. I0423 19:10:39.152624 139434758117184 checkpoint_manager.py:2013] [process=6][thread=MainThread][wait_until_finished] No Save Finalize thread to wait for. Returning. I0423 19:10:39.154419 139434758117184 checkpoint_manager.py:1518] [process=6] Saving checkpoint at step 0 I0423 19:10:39.157151 139434758117184 async_checkpointer.py:452] [process=6] Started async saving checkpoint to gs://lance-maxtext/linen_ckpt_xpk_feat_Migrate_Decoder_And_Tests_to_NNX_20260423_190840/linen_xpk_feat_Migrate_Decoder_And_Tests_to_NNX_20260423_190840_01_base/checkpoints/0. I0423 19:10:40.103638 139434758117184 signaling_client.py:364] Using JaxDistributedSignalingClient I0423 19:10:40.104680 139434758117184 jax_array_handlers.py:358] Scheduling D2H of 39 prioritized jax.Array. I0423 19:10:40.104737 139434758117184 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 I0423 19:10:40.354588 139434758117184 base_pytree_checkpoint_handler.py:153] [process=6][thread=MainThread] Initiated "orbax.checkpoint._src.serialization.jax_array_handlers.ArrayHandler".serialize. Time taken: 0.251025s I0423 19:10:40.354752 139434758117184 base_pytree_checkpoint_handler.py:129] [process=6] /jax/checkpoint/write/blocking_gbytes_per_sec: 3.004 GiB/s (total gbytes: 1.5 GiB) (time elapsed: 0.5134515762329102 s) (per-host) I0423 19:10:40.354805 139434758117184 base_pytree_checkpoint_handler.py:737] [process=6][thread=MainThread] Initiated Pytree async_save. Time taken: 0.513514s (batch_requests_ready=0.258937s, total_serialization_initiated=0.254507s, others=0.000070s) I0423 19:10:40.354896 139434758117184 composite_checkpoint_handler.py:715] [process=6][thread=MainThread] Initiated CompositeCheckpointHandler.async_save. Time taken: 0.517375s (all_items=0.000019s, per_item={'items': '0.00001931'}, temp_paths=0.517356) I0423 19:10:40.355822 139311928293120 async_checkpointer.py:79] [process=6][thread=async_save] Background save thread started. I0423 19:10:40.355951 139434758117184 async_checkpointer.py:561] Finished blocking save. Time taken: 1.201463s. Continuing background save to gs://lance-maxtext/linen_ckpt_xpk_feat_Migrate_Decoder_And_Tests_to_NNX_20260423_190840/linen_xpk_feat_Migrate_Decoder_And_Tests_to_NNX_20260423_190840_01_base/checkpoints/0. I0423 19:10:40.645965 139434758117184 checkpoint_manager.py:1566] [process=6][thread=MainThread][step=0] Starting CheckpointManager Save Finalize thread=save_finalize I0423 19:10:40.646393 139307616540416 async_checkpointer.py:265] [process=6][thread=save_finalize] Waiting for background save thread=async_save. I0423 19:10:40.646540 139434758117184 standard_logger.py:34] {'step': 0, 'event_type': 'save', 'directory': 'gs://lance-maxtext/linen_ckpt_xpk_feat_Migrate_Decoder_And_Tests_to_NNX_20260423_190840/linen_xpk_feat_Migrate_Decoder_And_Tests_to_NNX_20260423_190840_01_base/checkpoints', 'reached_preemption': False, 'preemption_received_at': None, 'synchronous': False, 'wait_for_prev_start_time': 1776971439.152607, 'wait_for_prev_duration_secs': 6.365776062011719e-05, 'time_between_consecutive_saves_sec': None, 'checkpointer_blocking_start_time': 1776971439.1544569, 'checkpointer_blocking_duration_secs': 1.2016897201538086, 'get_old_steps_start_time': 1776971440.356168, 'get_old_steps_duration_secs': 2.7179718017578125e-05, 'checkpoint_manager_blocking_start_time': 1776971439.1507099, 'checkpoint_manager_blocking_duration_secs': 1.4957895278930664} I0423 19:10:40.646708 139434758117184 checkpointing.py:408] Started an asynchronous checkpoint save for step 0 I0423 19:10:40.646763 139434758117184 max_utils.py:750] Memstats: After params initialized: I0423 19:10:40.646820 139434758117184 max_utils.py:756] Using (GB) 0.43 / 31.25 (1.376000%) on TPU_24(process=6,(0,6,0,0)) I0423 19:10:40.646854 139434758117184 max_utils.py:756] Using (GB) 0.43 / 31.25 (1.376000%) on TPU_25(process=6,(1,6,0,0)) I0423 19:10:40.646883 139434758117184 max_utils.py:756] Using (GB) 0.43 / 31.25 (1.376000%) on TPU_28(process=6,(0,7,0,0)) I0423 19:10:40.646909 139434758117184 max_utils.py:756] Using (GB) 0.43 / 31.25 (1.376000%) on TPU_29(process=6,(1,7,0,0)) I0423 19:10:40.912523 139434758117184 metric_logger.py:185] completed step: 0, seconds: 11.196, TFLOP/s/device: 1.214, Tokens/s/device: 182.924, total_weights: 65536, loss: 10.874 I0423 19:10:41.087862 139434758117184 metric_logger.py:185] completed step: 1, seconds: 1.915, TFLOP/s/device: 7.096, Tokens/s/device: 1069.611, total_weights: 65536, loss: 10.874 I0423 19:10:41.506585 139434758117184 metric_logger.py:185] completed step: 2, seconds: 0.028, TFLOP/s/device: 478.723, Tokens/s/device: 72158.410, total_weights: 65536, loss: 10.263 I0423 19:10:41.654153 139434758117184 metric_logger.py:185] completed step: 3, seconds: 0.419, TFLOP/s/device: 32.441, Tokens/s/device: 4889.905, total_weights: 65536, loss: 9.734 I0423 19:10:41.949420 139434758117184 metric_logger.py:185] completed step: 4, seconds: 0.153, TFLOP/s/device: 88.954, Tokens/s/device: 13408.143, total_weights: 65536, loss: 9.278 I0423 19:10:41.954837 139434758117184 metric_logger.py:185] completed step: 5, seconds: 0.148, TFLOP/s/device: 92.057, Tokens/s/device: 13875.809, total_weights: 65536, loss: 8.892 I0423 19:11:00.373124 139434758117184 metric_logger.py:185] completed step: 6, seconds: 0.295, TFLOP/s/device: 45.999, Tokens/s/device: 6933.465, total_weights: 65536, loss: 8.592 I0423 19:11:00.520521 139434758117184 metric_logger.py:185] completed step: 7, seconds: 18.272, TFLOP/s/device: 0.744, Tokens/s/device: 112.086, total_weights: 65536, loss: 8.384 I0423 19:11:00.667797 139434758117184 metric_logger.py:185] completed step: 8, seconds: 0.152, TFLOP/s/device: 89.282, Tokens/s/device: 13457.482, total_weights: 65536, loss: 8.255 I0423 19:11:00.814955 139434758117184 checkpointing.py:772] Waiting for step 9 to finish before checkpoint... I0423 19:11:00.815639 139434758117184 checkpointing.py:776] Waited 0.0007033348083496094 seconds for step 9 to finish before starting checkpointing. I0423 19:11:00.817660 139434758117184 checkpoint_manager.py:2024] [process=6][thread=MainThread][step=0][wait_until_finished] Waiting for Save Finalize thread (save_finalize) to complete. I0423 19:11:01.902456 2637 google_auth_provider.cc:181] Running on GCE, using service account 562977990677-compute@developer.gserviceaccount.com I0423 19:11:03.848891 139311936685824 array_metadata_store.py:203] [process=6][thread=array_type_handler] Wrote 39 array_metadata.ArrayMetadata to gs://lance-maxtext/linen_ckpt_xpk_feat_Migrate_Decoder_And_Tests_to_NNX_20260423_190840/linen_xpk_feat_Migrate_Decoder_And_Tests_to_NNX_20260423_190840_01_base/checkpoints/0/items/array_metadatas/process_6 I0423 19:11:35.907835 139311928293120 base_pytree_checkpoint_handler.py:129] [process=6] /jax/checkpoint/write/gbytes_per_sec: 28.174 MiB/s (total gbytes: 1.5 GiB) (time elapsed: 56.06649112701416 s) (per-host) I0423 19:11:35.907959 139311928293120 async_checkpointer.py:90] [process=6][thread=async_save] 3 Handler Commit operations completed. Time taken: 55.551928s. I0423 19:11:43.419078 139311928293120 async_checkpointer.py:144] [process=6][thread=async_save] Background save thread done. Time taken: 63.063033s. I0423 19:11:43.419358 139307616540416 async_checkpointer.py:273] [process=6][thread=save_finalize] Done with waiting for background save thread=async_save. I0423 19:11:43.419492 139307616540416 async_checkpointer.py:283] [process=6][thread=save_finalize] No errors found in background save thread=async_save. I0423 19:11:43.419559 139307616540416 checkpoint_manager.py:2133] [process=6][thread=save_finalize][step=0] CheckpointManager Save Finalize is syncing with other hosts... I0423 19:11:43.420836 139307616540416 checkpoint_manager.py:2142] [process=6][thread=save_finalize][step=0] CheckpointManager Save Finalize is done on all hosts. I0423 19:11:43.421019 139434758117184 checkpoint_manager.py:2036] [process=6][thread=MainThread][step=0][wait_until_finished] Done waiting for Save Finalize thread (save_finalize) running at step=0. W0423 19:11:43.421164 139434758117184 checkpoint_manager.py:1458] Waiting for previous save to complete took 42.603510 seconds. If this number is high, consider checkpointing less frequently. I0423 19:11:43.423067 139434758117184 checkpoint_manager.py:1518] [process=6] Saving checkpoint at step 9 I0423 19:11:43.426574 139434758117184 async_checkpointer.py:452] [process=6] Started async saving checkpoint to gs://lance-maxtext/linen_ckpt_xpk_feat_Migrate_Decoder_And_Tests_to_NNX_20260423_190840/linen_xpk_feat_Migrate_Decoder_And_Tests_to_NNX_20260423_190840_01_base/checkpoints/9. I0423 19:11:44.378069 139434758117184 jax_array_handlers.py:358] Scheduling D2H of 39 prioritized jax.Array. I0423 19:11:44.378183 139434758117184 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 I0423 19:11:44.426486 139434758117184 base_pytree_checkpoint_handler.py:153] [process=6][thread=MainThread] Initiated "orbax.checkpoint._src.serialization.jax_array_handlers.ArrayHandler".serialize. Time taken: 0.049792s I0423 19:11:44.426660 139434758117184 base_pytree_checkpoint_handler.py:129] [process=6] /jax/checkpoint/write/blocking_gbytes_per_sec: 5.177 GiB/s (total gbytes: 1.5 GiB) (time elapsed: 0.2979898452758789 s) (per-host) I0423 19:11:44.426711 139434758117184 base_pytree_checkpoint_handler.py:737] [process=6][thread=MainThread] Initiated Pytree async_save. Time taken: 0.298049s (batch_requests_ready=0.246341s, total_serialization_initiated=0.051642s, others=0.000066s) I0423 19:11:44.426798 139434758117184 composite_checkpoint_handler.py:715] [process=6][thread=MainThread] Initiated CompositeCheckpointHandler.async_save. Time taken: 0.302223s (all_items=0.000016s, per_item={'items': '0.00001597'}, temp_paths=0.302207) I0423 19:11:44.427689 139308696430336 async_checkpointer.py:79] [process=6][thread=async_save] Background save thread started. I0423 19:11:44.427851 139434758117184 async_checkpointer.py:561] Finished blocking save. Time taken: 1.004697s. Continuing background save to gs://lance-maxtext/linen_ckpt_xpk_feat_Migrate_Decoder_And_Tests_to_NNX_20260423_190840/linen_xpk_feat_Migrate_Decoder_And_Tests_to_NNX_20260423_190840_01_base/checkpoints/9. I0423 19:11:44.838429 139434758117184 checkpoint_manager.py:1566] [process=6][thread=MainThread][step=9] Starting CheckpointManager Save Finalize thread=save_finalize I0423 19:11:44.838881 139307616540416 async_checkpointer.py:265] [process=6][thread=save_finalize] Waiting for background save thread=async_save. I0423 19:11:44.839058 139434758117184 standard_logger.py:34] {'step': 9, 'event_type': 'save', 'directory': 'gs://lance-maxtext/linen_ckpt_xpk_feat_Migrate_Decoder_And_Tests_to_NNX_20260423_190840/linen_xpk_feat_Migrate_Decoder_And_Tests_to_NNX_20260423_190840_01_base/checkpoints', 'reached_preemption': False, 'preemption_received_at': None, 'synchronous': False, 'wait_for_prev_start_time': 1776971460.8176293, 'wait_for_prev_duration_secs': 42.6035099029541, 'time_between_consecutive_saves_sec': None, 'checkpointer_blocking_start_time': 1776971503.4231193, 'checkpointer_blocking_duration_secs': 1.00484299659729, 'get_old_steps_start_time': 1776971504.4279816, 'get_old_steps_duration_secs': 2.4557113647460938e-05, 'checkpoint_manager_blocking_start_time': 1776971460.8158615, 'checkpoint_manager_blocking_duration_secs': 44.023157835006714} I0423 19:11:44.839176 139434758117184 checkpointing.py:408] Started an asynchronous checkpoint save for step 9 I0423 19:11:44.839222 139434758117184 checkpoint_manager.py:2024] [process=6][thread=MainThread][step=9][wait_until_finished] Waiting for Save Finalize thread (save_finalize) to complete. I0423 19:11:49.261322 139311936685824 array_metadata_store.py:203] [process=6][thread=array_type_handler] Wrote 39 array_metadata.ArrayMetadata to gs://lance-maxtext/linen_ckpt_xpk_feat_Migrate_Decoder_And_Tests_to_NNX_20260423_190840/linen_xpk_feat_Migrate_Decoder_And_Tests_to_NNX_20260423_190840_01_base/checkpoints/9/items/array_metadatas/process_6 I0423 19:12:25.469302 139308696430336 base_pytree_checkpoint_handler.py:129] [process=6] /jax/checkpoint/write/gbytes_per_sec: 38.209 MiB/s (total gbytes: 1.5 GiB) (time elapsed: 41.340580701828 s) (per-host) I0423 19:12:25.469426 139308696430336 async_checkpointer.py:90] [process=6][thread=async_save] 3 Handler Commit operations completed. Time taken: 41.041625s. I0423 19:12:35.006320 139308696430336 async_checkpointer.py:144] [process=6][thread=async_save] Background save thread done. Time taken: 50.578502s. I0423 19:12:35.006677 139307616540416 async_checkpointer.py:273] [process=6][thread=save_finalize] Done with waiting for background save thread=async_save. I0423 19:12:35.006798 139307616540416 async_checkpointer.py:283] [process=6][thread=save_finalize] No errors found in background save thread=async_save. I0423 19:12:35.006845 139307616540416 checkpoint_manager.py:2133] [process=6][thread=save_finalize][step=9] CheckpointManager Save Finalize is syncing with other hosts... I0423 19:12:35.008508 139307616540416 checkpoint_manager.py:2142] [process=6][thread=save_finalize][step=9] CheckpointManager Save Finalize is done on all hosts. I0423 19:12:35.008683 139434758117184 checkpoint_manager.py:2036] [process=6][thread=MainThread][step=9][wait_until_finished] Done waiting for Save Finalize thread (save_finalize) running at step=9. I0423 19:12:35.008829 139434758117184 checkpoint_manager.py:2013] [process=6][thread=MainThread][wait_until_finished] No Save Finalize thread to wait for. Returning. I0423 19:12:35.009494 139434758117184 metric_logger.py:185] completed step: 9, seconds: 0.147, TFLOP/s/device: 92.353, Tokens/s/device: 13920.420, total_weights: 65536, loss: 8.179 Per train step: Total TFLOPs: 13.59 split as 93.93% learnable weight flops and 6.07% attention flops XPK End: Thu Apr 23 19:12:45 UTC 2026 EXIT_CODE=0