XPK Start: Thu Apr 23 08:03:39 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. 2026-04-23 08:04:04.282996: 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 08:04:04.493077 137423608354624 max_utils.py:273] Attempting to initialize the jax distributed system... I0423 08:04:13.534661 137423608354624 distributed.py:149] Starting JAX distributed service on [::]:8482 I0423 08:04:13.536992 137423608354624 distributed.py:172] Connecting to JAX distributed service on mt-13-scan-layers-true-yt3xr-slice-job-0-0.mt-13-scan-layers-true-yt3xr:8482 I0423 08:04:14.473850 137423608354624 max_utils.py:284] Jax distributed system initialized! I0423 08:04:20.536100 137423608354624 max_utils.py:800] System Information: Jax Version: 0.9.2 I0423 08:04:20.536205 137423608354624 max_utils.py:801] System Information: Jaxlib Version: 0.9.2 I0423 08:04:20.536244 137423608354624 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 I0423 08:04:20.536280 137423608354624 train_utils.py:361] WARNING: Sequence packing is essentially ignored for synthetic data. Please use a real dataset to use sequence packing. I0423 08:04:21.229243 137423608354624 maxtext_utils.py:1604] Num_devices: 32, shape (1, 1, 1, 32, 1, 1, 1, 1, 1, 1, 1, 1, 1) I0423 08:04:21.229527 137423608354624 checkpointing.py:677] Setting up checkpoint logger... I0423 08:04:21.229583 137423608354624 checkpointing.py:233] Creating checkpoint manager with ocdbt=True and zarr3=True I0423 08:04:21.229627 137423608354624 pytree_checkpoint_handler.py:592] save_device_host_concurrent_bytes=None I0423 08:04:21.229971 137423608354624 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 0x7cfbcc71cec0>, enable_pinned_host_transfer=False, save_concurrent_bytes: 96000000000 (89.4 GiB), restore_concurrent_bytes: 96000000000 (89.4 GiB) I0423 08:04:24.244546 137423608354624 checkpointing.py:265] Enabling policy for fixed interval checkpointing. I0423 08:04:24.244774 137423608354624 checkpoint_manager.py:708] [process=4][thread=MainThread] CheckpointManager init: checkpointers=None, item_names=('items',), item_handlers={'items': <orbax.checkpoint._src.handlers.pytree_checkpoint_handler.PyTreeCheckpointHandler object at 0x7ce77041f7d0>}, handler_registry=None I0423 08:04:24.245056 137423608354624 composite_checkpoint_handler.py:237] Deferred registration for item: "items". Adding handler `<orbax.checkpoint._src.handlers.pytree_checkpoint_handler.PyTreeCheckpointHandler object at 0x7ce77041f7d0>` 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 08:04:24.245117 137423608354624 composite_checkpoint_handler.py:237] Deferred registration for item: "metrics". Adding handler `<orbax.checkpoint._src.handlers.json_checkpoint_handler.JsonCheckpointHandler object at 0x7ce7700799d0>` 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 08:04:24.245168 137423608354624 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 0x7ce77041f7d0>, ('items', <class 'orbax.checkpoint._src.handlers.pytree_checkpoint_handler.PyTreeRestoreArgs'>): <orbax.checkpoint._src.handlers.pytree_checkpoint_handler.PyTreeCheckpointHandler object at 0x7ce77041f7d0>, ('metrics', <class 'orbax.checkpoint._src.handlers.json_checkpoint_handler.JsonSaveArgs'>): <orbax.checkpoint._src.handlers.json_checkpoint_handler.JsonCheckpointHandler object at 0x7ce7700799d0>, ('metrics', <class 'orbax.checkpoint._src.handlers.json_checkpoint_handler.JsonRestoreArgs'>): <orbax.checkpoint._src.handlers.json_checkpoint_handler.JsonCheckpointHandler object at 0x7ce7700799d0>}). I0423 08:04:24.245521 137423608354624 abstract_checkpointer.py:35] orbax-checkpoint version: 0.11.34 I0423 08:04:24.245594 137423608354624 async_checkpointer.py:192] [process=4][thread=MainThread] Using barrier_sync_fn: <function get_barrier_sync_fn.<locals>._fn at 0x7ce758569940> timeout: 1200 secs and primary_host=0 for async checkpoint writes I0423 08:04:25.824432 137423608354624 checkpoint_manager.py:1812] Found 0 checkpoint steps in gs://lance-maxtext/linen_ckpt_xpk_main_20260423_071538/linen_xpk_main_20260423_071538_13_scan_layers_true/checkpoints I0423 08:04:26.300708 137423608354624 checkpoint_manager.py:929] [process=4][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_main_20260423_071538/linen_xpk_main_20260423_071538_13_scan_layers_true/checkpoints: <orbax.checkpoint.checkpoint_manager.CheckpointManager object at 0x7ce7700793d0> I0423 08:04:26.300891 137423608354624 checkpointing.py:301] Checkpoint manager created! I0423 08:04:27.225021 137423608354624 nnx_wrappers.py:437] Unknown Logical: bfloat16[32,2048,2048]...................................... ('activation_batch', 'activation_norm_length', 'activation_embed'). I0423 08:04:27.225137 137423608354624 nnx_wrappers.py:437] Unknown Physical: bfloat16[32,2048,2048]...................................... ('fsdp', None, None). I0423 08:04:27.606553 137423608354624 attentions.py:1088] attentions/inputs_q Logical: bfloat16[32,2048,2048]...................................... ('activation_batch', 'activation_attn_length', 'activation_attn_embed'). I0423 08:04:27.606652 137423608354624 attentions.py:1088] attentions/inputs_q Physical: bfloat16[32,2048,2048]...................................... ('fsdp', None, None). I0423 08:04:27.623172 137423608354624 attentions.py:1089] attentions/inputs_kv Logical: bfloat16[32,2048,2048]...................................... ('activation_batch', 'activation_attn_length', 'activation_attn_embed'). I0423 08:04:27.623241 137423608354624 attentions.py:1089] attentions/inputs_kv Physical: bfloat16[32,2048,2048]...................................... ('fsdp', None, None). I0423 08:04:27.647033 137423608354624 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 08:04:27.647099 137423608354624 attentions.py:1154] attentions/query Physical: bfloat16[32,2048,16,128].................................... ('fsdp', None, None, None). I0423 08:04:27.663543 137423608354624 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 08:04:27.663610 137423608354624 attentions.py:1155] attentions/key Physical: bfloat16[32,2048,16,128].................................... ('fsdp', None, None, None). I0423 08:04:27.680171 137423608354624 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 08:04:27.680238 137423608354624 attentions.py:1156] attentions/value Physical: bfloat16[32,2048,16,128].................................... ('fsdp', None, None, None). I0423 08:04:27.705260 137423608354624 attentions.py:1198] attentions/out Logical: bfloat16[32,2048,16,128].................................... ('activation_batch', 'activation_attn_length', 'activation_heads', 'activation_kv'). I0423 08:04:27.705328 137423608354624 attentions.py:1198] attentions/out Physical: bfloat16[32,2048,16,128].................................... ('fsdp', None, None, None). I0423 08:04:27.726396 137423608354624 linears.py:525] linears/x Logical: bfloat16[32,2048,7168]...................................... ('activation_batch', 'activation_length', 'activation_mlp'). I0423 08:04:27.726460 137423608354624 linears.py:525] linears/x Physical: bfloat16[32,2048,7168]...................................... ('fsdp', None, None). I0423 08:04:27.944087 137423608354624 checkpointing.py:577] checkpoint manager exists so trying to load this run's existing checkpoint I0423 08:04:27.944202 137423608354624 checkpointing.py:665] No existing checkpoints found, not restoring checkpoint. fsdp: 32 I0423 08:04:29.370011 137423608354624 maxtext_utils.py:1707] params/params/decoder/decoder_norm/scale Shape: float32[2048] Logical: P('norm',) Physical: (None,) I0423 08:04:29.370139 137423608354624 maxtext_utils.py:1707] params/params/decoder/layers/mlp/wi_0/kernel Shape: float32[2048,16,7168] Logical: P('embed', 'layers', 'mlp') Physical: ('fsdp', None, None) I0423 08:04:29.370196 137423608354624 maxtext_utils.py:1707] params/params/decoder/layers/mlp/wi_1/kernel Shape: float32[2048,16,7168] Logical: P('embed', 'layers', 'mlp') Physical: ('fsdp', None, None) I0423 08:04:29.370254 137423608354624 maxtext_utils.py:1707] params/params/decoder/layers/mlp/wo/kernel Shape: float32[7168,16,2048] Logical: P('mlp', 'layers', 'embed') Physical: (None, None, 'fsdp') I0423 08:04:29.370313 137423608354624 maxtext_utils.py:1707] params/params/decoder/layers/post_self_attention_layer_norm/scale Shape: float32[2048,16] Logical: P('norm', 'layers') Physical: (None, None) I0423 08:04:29.370354 137423608354624 maxtext_utils.py:1707] params/params/decoder/layers/pre_self_attention_layer_norm/scale Shape: float32[2048,16] Logical: P('norm', 'layers') Physical: (None, None) I0423 08:04:29.370407 137423608354624 maxtext_utils.py:1707] params/params/decoder/layers/self_attention/key/kernel Shape: float32[2048,16,16,128] Logical: P('embed', 'layers', 'kv_heads', 'kv_head_dim') Physical: ('fsdp', None, None, None) I0423 08:04:29.370459 137423608354624 maxtext_utils.py:1707] params/params/decoder/layers/self_attention/out/kernel Shape: float32[16,16,128,2048] Logical: P('heads', 'layers', 'kv', 'embed') Physical: (None, None, None, 'fsdp') I0423 08:04:29.370498 137423608354624 maxtext_utils.py:1707] params/params/decoder/layers/self_attention/query/kernel Shape: float32[2048,16,16,128] Logical: P('embed', 'layers', 'q_heads', 'kv') Physical: ('fsdp', None, None, None) I0423 08:04:29.370534 137423608354624 maxtext_utils.py:1707] params/params/decoder/layers/self_attention/value/kernel Shape: float32[2048,16,16,128] Logical: P('embed', 'layers', 'kv_heads', 'kv_head_dim') Physical: ('fsdp', None, None, None) I0423 08:04:29.370582 137423608354624 maxtext_utils.py:1707] params/params/decoder/logits_dense/kernel Shape: float32[2048,32000] Logical: P('embed_vocab', 'vocab') Physical: ('fsdp', None) I0423 08:04:29.370630 137423608354624 maxtext_utils.py:1707] params/params/token_embedder/embedding Shape: float32[32000,2048] Logical: P('vocab', 'embed_vocab') Physical: (None, 'fsdp') I0423 08:04:29.864407 137423608354624 train.py:155] train/xent Logical: float32[32,2048]............................................ ('activation_embed_and_logits_batch', 'activation_length'). I0423 08:04:29.864501 137423608354624 train.py:155] train/xent Physical: float32[32,2048]............................................ ('fsdp', None). I0423 08:04:29.880373 137423608354624 train.py:162] train/z_loss Logical: float32[32,2048]............................................ ('activation_embed_and_logits_batch', 'activation_length'). I0423 08:04:29.880438 137423608354624 train.py:162] train/z_loss Physical: float32[32,2048]............................................ ('fsdp', None). I0423 08:04:40.896650 137423608354624 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 08:04:40.897372 137423608354624 metric_logger.py:301] number parameters: 1.104 billion I0423 08:04:52.146339 137423608354624 checkpointing.py:772] Waiting for step 0 to finish before checkpoint... I0423 08:04:52.384959 137423608354624 checkpointing.py:776] Waited 0.2386009693145752 seconds for step 0 to finish before starting checkpointing. I0423 08:04:52.388205 137423608354624 checkpoint_manager.py:2009] [process=4][thread=MainThread][wait_until_finished] No Save Finalize thread to wait for. Returning. I0423 08:04:52.389910 137423608354624 checkpoint_manager.py:1512] [process=4] Saving checkpoint at step 0 I0423 08:04:52.391307 137423608354624 event_tracking.py:70] [process=4] [async] Started save checkpoint @ gs://lance-maxtext/linen_ckpt_xpk_main_20260423_071538/linen_xpk_main_20260423_071538_13_scan_layers_true/checkpoints/0. I0423 08:04:53.161995 137423608354624 signaling_client.py:364] Using JaxDistributedSignalingClient I0423 08:04:53.162992 137423608354624 jax_array_handlers.py:360] Scheduling D2H of 39 prioritized jax.Array. I0423 08:04:53.163048 137423608354624 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 08:04:53.441683 137423608354624 base_pytree_checkpoint_handler.py:154] [process=4][thread=MainThread] Initiated "orbax.checkpoint._src.serialization.jax_array_handlers.ArrayHandler".serialize. Time taken: 0.279760s I0423 08:04:53.441858 137423608354624 base_pytree_checkpoint_handler.py:130] [process=4] /jax/orbax/write/blocking_gbytes_per_sec: 5.405 GiB/s (total gbytes: 1.5 GiB) (time elapsed: 0.2853851318359375 s) (per-host) I0423 08:04:53.441923 137423608354624 base_pytree_checkpoint_handler.py:768] [process=4][thread=MainThread] Initiated Pytree async_save. Time taken: 0.285460s (batch_requests_ready=0.002492s, total_serialization_initiated=0.282885s, others=0.000083s) I0423 08:04:53.442014 137423608354624 composite_checkpoint_handler.py:715] [process=4][thread=MainThread] Initiated CompositeCheckpointHandler.async_save. Time taken: 0.289738s (all_items=0.000018s, per_item={'items': '0.00001836'}, temp_paths=0.289720) I0423 08:04:53.442794 137423608354624 event_tracking.py:125] [process=4] [async] Finished blocking save in 1.05 seconds. Continuing save @ gs://lance-maxtext/linen_ckpt_xpk_main_20260423_071538/linen_xpk_main_20260423_071538_13_scan_layers_true/checkpoints/0. I0423 08:04:53.443134 137294828775168 async_checkpointer.py:76] [process=4][thread=async_save] Background save thread started. Deadline for this save operation is 2026-04-23 08:24:53.443097 I0423 08:04:53.453892 137423608354624 checkpoint_manager.py:1560] [process=4][thread=MainThread][step=0] Starting CheckpointManager Save Finalize thread=save_finalize I0423 08:04:53.454192 137293243340544 async_checkpointer.py:280] [process=4][thread=save_finalize] Waiting for background save thread=async_save. I0423 08:04:53.454355 137423608354624 standard_logger.py:34] {'step': 0, 'event_type': 'save', 'directory': 'gs://lance-maxtext/linen_ckpt_xpk_main_20260423_071538/linen_xpk_main_20260423_071538_13_scan_layers_true/checkpoints', 'reached_preemption': False, 'preemption_received_at': None, 'synchronous': False, 'wait_for_prev_start_time': 1776931492.3881865, 'wait_for_prev_duration_secs': 6.103515625e-05, 'time_between_consecutive_saves_sec': None, 'checkpointer_blocking_start_time': 1776931492.3899486, 'checkpointer_blocking_duration_secs': 1.0533549785614014, 'get_old_steps_start_time': 1776931493.443329, 'get_old_steps_duration_secs': 3.0279159545898438e-05, 'checkpoint_manager_blocking_start_time': 1776931492.3854952, 'checkpoint_manager_blocking_duration_secs': 1.0688204765319824} I0423 08:04:53.454457 137423608354624 checkpointing.py:408] Started an asynchronous checkpoint save for step 0 I0423 08:04:53.454509 137423608354624 max_utils.py:750] Memstats: After params initialized: I0423 08:04:53.454559 137423608354624 max_utils.py:756] Using (GB) 0.43 / 31.25 (1.376000%) on TPU_16(process=4,(0,4,0,0)) I0423 08:04:53.454591 137423608354624 max_utils.py:756] Using (GB) 0.43 / 31.25 (1.376000%) on TPU_17(process=4,(1,4,0,0)) I0423 08:04:53.454620 137423608354624 max_utils.py:756] Using (GB) 0.43 / 31.25 (1.376000%) on TPU_20(process=4,(0,5,0,0)) I0423 08:04:53.454646 137423608354624 max_utils.py:756] Using (GB) 0.43 / 31.25 (1.376000%) on TPU_21(process=4,(1,5,0,0)) I0423 08:04:53.761343 137423608354624 metric_logger.py:196] completed step: 0, seconds: 11.249, TFLOP/s/device: 1.208, Tokens/s/device: 182.063, total_weights: 65536, loss: 10.874, lm_loss: 10.874, perplexity: 52779.875 I0423 08:04:53.949304 137423608354624 metric_logger.py:196] completed step: 1, seconds: 1.613, TFLOP/s/device: 8.421, Tokens/s/device: 1269.327, total_weights: 65536, loss: 10.874, lm_loss: 10.874, perplexity: 52779.875 I0423 08:04:54.376089 137423608354624 metric_logger.py:196] completed step: 2, seconds: 0.041, TFLOP/s/device: 333.664, Tokens/s/device: 50293.460, total_weights: 65536, loss: 10.262, lm_loss: 10.262, perplexity: 28637.129 I0423 08:04:54.523291 137423608354624 metric_logger.py:196] completed step: 3, seconds: 0.427, TFLOP/s/device: 31.842, Tokens/s/device: 4799.524, total_weights: 65536, loss: 9.734, lm_loss: 9.734, perplexity: 16889.203 I0423 08:04:54.818162 137423608354624 metric_logger.py:196] completed step: 4, seconds: 0.153, TFLOP/s/device: 88.638, Tokens/s/device: 13360.472, total_weights: 65536, loss: 9.277, lm_loss: 9.277, perplexity: 10694.614 I0423 08:04:54.823831 137423608354624 metric_logger.py:196] completed step: 5, seconds: 0.147, TFLOP/s/device: 92.301, Tokens/s/device: 13912.571, total_weights: 65536, loss: 8.892, lm_loss: 8.892, perplexity: 7270.717 I0423 08:04:56.958915 2815 google_auth_provider.cc:181] Running on GCE, using service account 562977990677-compute@developer.gserviceaccount.com I0423 08:04:59.535352 137293260125952 array_metadata_store.py:203] [process=4][thread=array_type_handler] Wrote 39 array_metadata.ArrayMetadata to gs://lance-maxtext/linen_ckpt_xpk_main_20260423_071538/linen_xpk_main_20260423_071538_13_scan_layers_true/checkpoints/0/items/array_metadatas/process_4 I0423 08:05:16.626466 137423608354624 metric_logger.py:196] completed step: 6, seconds: 0.295, TFLOP/s/device: 46.048, Tokens/s/device: 6940.820, total_weights: 65536, loss: 8.592, lm_loss: 8.592, perplexity: 5390.759 I0423 08:05:16.773882 137423608354624 metric_logger.py:196] completed step: 7, seconds: 21.656, TFLOP/s/device: 0.627, Tokens/s/device: 94.570, total_weights: 65536, loss: 8.384, lm_loss: 8.384, perplexity: 4376.905 I0423 08:05:16.921057 137423608354624 metric_logger.py:196] completed step: 8, seconds: 0.152, TFLOP/s/device: 89.209, Tokens/s/device: 13446.614, total_weights: 65536, loss: 8.255, lm_loss: 8.255, perplexity: 3846.406 I0423 08:05:17.067761 137423608354624 checkpointing.py:772] Waiting for step 9 to finish before checkpoint... I0423 08:05:17.068377 137423608354624 checkpointing.py:776] Waited 0.0006363391876220703 seconds for step 9 to finish before starting checkpointing. I0423 08:05:17.070670 137423608354624 checkpoint_manager.py:2020] [process=4][thread=MainThread][step=0][wait_until_finished] Waiting for Save Finalize thread (save_finalize) to complete. I0423 08:05:30.658982 137294828775168 base_pytree_checkpoint_handler.py:130] [process=4] /jax/orbax/write/gbytes_per_sec: 42.120 MiB/s (total gbytes: 1.5 GiB) (time elapsed: 37.50246071815491 s) (per-host) I0423 08:05:30.659098 137294828775168 async_checkpointer.py:90] [process=4][thread=async_save] 3 Handler Commit operations completed. Time taken: 37.215843s. I0423 08:05:40.251780 137294828775168 async_checkpointer.py:160] [process=4][thread=async_save] Background save thread done. Time taken: 46.808508s. I0423 08:05:40.252108 137293243340544 async_checkpointer.py:288] [process=4][thread=save_finalize] Done with waiting for background save thread=async_save. I0423 08:05:40.252224 137293243340544 async_checkpointer.py:298] [process=4][thread=save_finalize] No errors found in background save thread=async_save. I0423 08:05:40.252275 137293243340544 checkpoint_manager.py:2137] [process=4][thread=save_finalize][step=0] CheckpointManager Save Finalize is syncing with other hosts... I0423 08:05:40.253744 137293243340544 checkpoint_manager.py:2146] [process=4][thread=save_finalize][step=0] CheckpointManager Save Finalize is done on all hosts. I0423 08:05:40.253918 137423608354624 checkpoint_manager.py:2032] [process=4][thread=MainThread][step=0][wait_until_finished] Done waiting for Save Finalize thread (save_finalize) running at step=0. W0423 08:05:40.254048 137423608354624 checkpoint_manager.py:1452] Waiting for previous save to complete took 23.183379 seconds. If this number is high, consider checkpointing less frequently. I0423 08:05:40.255831 137423608354624 checkpoint_manager.py:1512] [process=4] Saving checkpoint at step 9 I0423 08:05:40.257937 137423608354624 event_tracking.py:70] [process=4] [async] Started save checkpoint @ gs://lance-maxtext/linen_ckpt_xpk_main_20260423_071538/linen_xpk_main_20260423_071538_13_scan_layers_true/checkpoints/9. I0423 08:05:40.541855 137423608354624 jax_array_handlers.py:360] Scheduling D2H of 39 prioritized jax.Array. I0423 08:05:40.541961 137423608354624 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 08:05:40.583253 137423608354624 base_pytree_checkpoint_handler.py:154] [process=4][thread=MainThread] Initiated "orbax.checkpoint._src.serialization.jax_array_handlers.ArrayHandler".serialize. Time taken: 0.042453s I0423 08:05:40.583420 137423608354624 base_pytree_checkpoint_handler.py:130] [process=4] /jax/orbax/write/blocking_gbytes_per_sec: 33.561 GiB/s (total gbytes: 1.5 GiB) (time elapsed: 0.045963287353515625 s) (per-host) I0423 08:05:40.583470 137423608354624 base_pytree_checkpoint_handler.py:768] [process=4][thread=MainThread] Initiated Pytree async_save. Time taken: 0.046023s (batch_requests_ready=0.001770s, total_serialization_initiated=0.044185s, others=0.000068s) I0423 08:05:40.583562 137423608354624 composite_checkpoint_handler.py:715] [process=4][thread=MainThread] Initiated CompositeCheckpointHandler.async_save. Time taken: 0.050038s (all_items=0.000015s, per_item={'items': '0.00001502'}, temp_paths=0.050023) I0423 08:05:40.584304 137423608354624 event_tracking.py:125] [process=4] [async] Finished blocking save in 0.33 seconds. Continuing save @ gs://lance-maxtext/linen_ckpt_xpk_main_20260423_071538/linen_xpk_main_20260423_071538_13_scan_layers_true/checkpoints/9. I0423 08:05:40.584623 137293243340544 async_checkpointer.py:76] [process=4][thread=async_save] Background save thread started. Deadline for this save operation is 2026-04-23 08:25:40.584586 I0423 08:05:40.586657 137423608354624 checkpoint_manager.py:1560] [process=4][thread=MainThread][step=9] Starting CheckpointManager Save Finalize thread=save_finalize I0423 08:05:40.586971 137293260125952 async_checkpointer.py:280] [process=4][thread=save_finalize] Waiting for background save thread=async_save. I0423 08:05:40.587140 137423608354624 standard_logger.py:34] {'step': 9, 'event_type': 'save', 'directory': 'gs://lance-maxtext/linen_ckpt_xpk_main_20260423_071538/linen_xpk_main_20260423_071538_13_scan_layers_true/checkpoints', 'reached_preemption': False, 'preemption_received_at': None, 'synchronous': False, 'wait_for_prev_start_time': 1776931517.0706394, 'wait_for_prev_duration_secs': 23.18337893486023, 'time_between_consecutive_saves_sec': None, 'checkpointer_blocking_start_time': 1776931540.2558873, 'checkpointer_blocking_duration_secs': 0.32888007164001465, 'get_old_steps_start_time': 1776931540.5847936, 'get_old_steps_duration_secs': 2.9802322387695312e-05, 'checkpoint_manager_blocking_start_time': 1776931517.0685985, 'checkpoint_manager_blocking_duration_secs': 23.518505334854126} I0423 08:05:40.587255 137423608354624 checkpointing.py:408] Started an asynchronous checkpoint save for step 9 I0423 08:05:40.587301 137423608354624 checkpoint_manager.py:2020] [process=4][thread=MainThread][step=9][wait_until_finished] Waiting for Save Finalize thread (save_finalize) to complete. I0423 08:05:47.021790 137272791889664 array_metadata_store.py:203] [process=4][thread=array_type_handler] Wrote 39 array_metadata.ArrayMetadata to gs://lance-maxtext/linen_ckpt_xpk_main_20260423_071538/linen_xpk_main_20260423_071538_13_scan_layers_true/checkpoints/9/items/array_metadatas/process_4 I0423 08:06:24.390820 137293243340544 base_pytree_checkpoint_handler.py:130] [process=4] /jax/orbax/write/gbytes_per_sec: 36.020 MiB/s (total gbytes: 1.5 GiB) (time elapsed: 43.85332417488098 s) (per-host) I0423 08:06:24.390957 137293243340544 async_checkpointer.py:90] [process=4][thread=async_save] 3 Handler Commit operations completed. Time taken: 43.806221s. I0423 08:06:32.783291 137293243340544 async_checkpointer.py:160] [process=4][thread=async_save] Background save thread done. Time taken: 52.198536s. I0423 08:06:32.783571 137293260125952 async_checkpointer.py:288] [process=4][thread=save_finalize] Done with waiting for background save thread=async_save. I0423 08:06:32.783683 137293260125952 async_checkpointer.py:298] [process=4][thread=save_finalize] No errors found in background save thread=async_save. I0423 08:06:32.783731 137293260125952 checkpoint_manager.py:2137] [process=4][thread=save_finalize][step=9] CheckpointManager Save Finalize is syncing with other hosts... I0423 08:06:32.785374 137293260125952 checkpoint_manager.py:2146] [process=4][thread=save_finalize][step=9] CheckpointManager Save Finalize is done on all hosts. I0423 08:06:32.785551 137423608354624 checkpoint_manager.py:2032] [process=4][thread=MainThread][step=9][wait_until_finished] Done waiting for Save Finalize thread (save_finalize) running at step=9. I0423 08:06:32.785700 137423608354624 checkpoint_manager.py:2009] [process=4][thread=MainThread][wait_until_finished] No Save Finalize thread to wait for. Returning. I0423 08:06:32.786704 137423608354624 metric_logger.py:196] completed step: 9, seconds: 0.147, TFLOP/s/device: 92.276, Tokens/s/device: 13908.886, total_weights: 65536, loss: 8.179, lm_loss: 8.179, perplexity: 3564.635 Per train step: Total TFLOPs: 13.59 split as 93.93% learnable weight flops and 6.07% attention flops XPK End: Thu Apr 23 08:06:44 UTC 2026 EXIT_CODE=0