2026-06-24 19:15:09,085 INFO    MainThread:43917 [wandb_setup.py:_flush():81] Current SDK version is 0.27.2
2026-06-24 19:15:09,085 INFO    MainThread:43917 [wandb_setup.py:_flush():81] Configure stats pid to 43917
2026-06-24 19:15:09,085 INFO    MainThread:43917 [wandb_setup.py:_flush():81] Loading settings from environment variables
2026-06-24 19:15:09,085 INFO    MainThread:43917 [wandb_init.py:setup_run_log_directory():723] Logging user logs to model_weights/codi-single-3b/wandb/offline-run-20260624_191509-pzchjc4v/logs/debug.log
2026-06-24 19:15:09,085 INFO    MainThread:43917 [wandb_init.py:setup_run_log_directory():724] Logging internal logs to model_weights/codi-single-3b/wandb/offline-run-20260624_191509-pzchjc4v/logs/debug-internal.log
2026-06-24 19:15:09,085 INFO    MainThread:43917 [wandb_init.py:init():766] calling init triggers
2026-06-24 19:15:09,085 INFO    MainThread:43917 [wandb_init.py:init():771] wandb.init called with sweep_config: {}
config: {'model': 'model_weights/sft3b_lr1e5_bs32/checkpoint-3000', 'output_dir': 'model_weights/codi-single-3b', 'sources': ['mbpp', 'humaneval', 'pyx'], 'cache_dir': 'data/cache/codi_train', 'n_samples': -1, 'max_seq_len': 3072, 'max_frames': -1, 'latent_steps': 6, 'epochs': 5.0, 'lr': 1e-05, 'batch_size': 1, 'grad_accum': 4, 'max_steps': 3000, 'save_steps': 500, 'optim': 'adamw_8bit', 'alpha': 1.0, 'beta': 1.0, 'gamma': 1.0, '_wandb': {}}
2026-06-24 19:15:09,085 INFO    MainThread:43917 [wandb_init.py:init():814] starting backend
2026-06-24 19:15:09,671 INFO    MainThread:43917 [wandb_init.py:init():829] sending inform_init request
2026-06-24 19:15:09,823 INFO    MainThread:43917 [wandb_init.py:init():834] backend started and connected
2026-06-24 19:15:09,825 INFO    MainThread:43917 [wandb_init.py:init():904] updated telemetry
2026-06-24 19:15:09,832 INFO    MainThread:43917 [wandb_init.py:init():927] communicating run to backend with 90.0 second timeout
2026-06-24 19:15:09,835 INFO    MainThread:43917 [wandb_init.py:init():972] starting run threads in backend
2026-06-24 19:15:10,441 INFO    MainThread:43917 [wandb_run.py:_console_start():2523] atexit reg
2026-06-24 19:15:10,441 INFO    MainThread:43917 [wandb_run.py:_redirect():2373] redirect: wrap_raw
2026-06-24 19:15:10,441 INFO    MainThread:43917 [wandb_run.py:_redirect():2442] Wrapping output streams.
2026-06-24 19:15:10,441 INFO    MainThread:43917 [wandb_run.py:_redirect():2465] Redirects installed.
2026-06-24 19:15:10,448 INFO    MainThread:43917 [wandb_init.py:init():1010] run started, returning control to user process
2026-06-24 19:15:59,217 INFO    MainThread:43917 [wandb_run.py:_config_callback():1346] config_cb None None {'output_dir': 'model_weights/codi-single-3b', 'overwrite_output_dir': False, 'do_train': False, 'do_eval': False, 'do_predict': False, 'eval_strategy': 'no', 'prediction_loss_only': False, 'per_device_train_batch_size': 1, 'per_device_eval_batch_size': 8, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 4, 'eval_accumulation_steps': None, 'eval_delay': 0, 'torch_empty_cache_steps': None, 'learning_rate': 1e-05, 'weight_decay': 0.1, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 5.0, 'max_steps': 3000, 'lr_scheduler_type': 'cosine', 'lr_scheduler_kwargs': None, 'warmup_ratio': 0.03, 'warmup_steps': 0, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': 'model_weights/codi-single-3b/runs/Jun24_19-15-10_alvis7-05', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 5, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 500, 'save_total_limit': None, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'restore_callback_states_from_checkpoint': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'bf16': True, 'fp16': False, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': None, 'dataloader_num_workers': 0, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': None, 'disable_tqdm': False, 'remove_unused_columns': False, 'label_names': [], 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, 'parallelism_config': None, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'adamw_8bit', 'optim_args': None, 'adafactor': False, 'group_by_length': False, 'length_column_name': 'length', 'report_to': ['wandb'], 'project': 'huggingface', 'trackio_space_id': 'trackio', 'ddp_find_unused_parameters': False, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': False, 'resume_from_checkpoint': None, 'hub_model_id': None, 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': None, 'hub_always_push': False, 'hub_revision': None, 'gradient_checkpointing': False, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'include_for_metrics': [], 'eval_do_concat_batches': True, 'fp16_backend': 'auto', 'push_to_hub_model_id': None, 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': 'no', 'neftune_noise_alpha': None, 'optim_target_modules': None, 'batch_eval_metrics': False, 'eval_on_start': False, 'use_liger_kernel': False, 'liger_kernel_config': None, 'eval_use_gather_object': False, 'average_tokens_across_devices': True}
2026-06-24 23:27:42,379 INFO    wandb-AsyncioManager-main:43917 [service_client.py:_forward_responses():122] Reached EOF.
2026-06-24 23:27:42,381 INFO    wandb-AsyncioManager-main:43917 [mailbox.py:close():154] Closing mailbox, abandoning 0 handles.