2024-07-20 03:04:39,449 INFO    MainThread:34 [wandb_setup.py:_flush():76] Current SDK version is 0.17.4
2024-07-20 03:04:39,449 INFO    MainThread:34 [wandb_setup.py:_flush():76] Configure stats pid to 34
2024-07-20 03:04:39,450 INFO    MainThread:34 [wandb_setup.py:_flush():76] Loading settings from /root/.config/wandb/settings
2024-07-20 03:04:39,450 INFO    MainThread:34 [wandb_setup.py:_flush():76] Loading settings from /kaggle/working/wandb/settings
2024-07-20 03:04:39,450 INFO    MainThread:34 [wandb_setup.py:_flush():76] Loading settings from environment variables: {}
2024-07-20 03:04:39,450 INFO    MainThread:34 [wandb_setup.py:_flush():76] Inferring run settings from compute environment: {'program': '<python with no main file>'}
2024-07-20 03:04:39,450 INFO    MainThread:34 [wandb_setup.py:_flush():76] Applying login settings: {'api_key': '***REDACTED***'}
2024-07-20 03:04:39,450 INFO    MainThread:34 [wandb_setup.py:_flush():76] Applying login settings: {'api_key': '***REDACTED***'}
2024-07-20 03:04:39,450 INFO    MainThread:34 [wandb_setup.py:_flush():76] Applying login settings: {}
2024-07-20 03:04:39,450 INFO    MainThread:34 [wandb_init.py:_log_setup():529] Logging user logs to /kaggle/working/wandb/run-20240720_030439-i2zat45f/logs/debug.log
2024-07-20 03:04:39,450 INFO    MainThread:34 [wandb_init.py:_log_setup():530] Logging internal logs to /kaggle/working/wandb/run-20240720_030439-i2zat45f/logs/debug-internal.log
2024-07-20 03:04:39,450 INFO    MainThread:34 [wandb_init.py:_jupyter_setup():475] configuring jupyter hooks <wandb.sdk.wandb_init._WandbInit object at 0x79a387a7e500>
2024-07-20 03:04:39,450 INFO    MainThread:34 [wandb_init.py:init():569] calling init triggers
2024-07-20 03:04:39,450 INFO    MainThread:34 [wandb_init.py:init():576] wandb.init called with sweep_config: {}
config: {}
2024-07-20 03:04:39,451 INFO    MainThread:34 [wandb_init.py:init():619] starting backend
2024-07-20 03:04:39,451 INFO    MainThread:34 [wandb_init.py:init():623] setting up manager
2024-07-20 03:04:39,454 INFO    MainThread:34 [backend.py:_multiprocessing_setup():105] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
2024-07-20 03:04:39,456 INFO    MainThread:34 [wandb_init.py:init():631] backend started and connected
2024-07-20 03:04:39,468 INFO    MainThread:34 [wandb_run.py:_label_probe_notebook():1334] probe notebook
2024-07-20 03:04:40,057 INFO    MainThread:34 [wandb_init.py:init():720] updated telemetry
2024-07-20 03:04:40,060 INFO    MainThread:34 [wandb_init.py:init():753] communicating run to backend with 90.0 second timeout
2024-07-20 03:04:40,583 INFO    MainThread:34 [wandb_run.py:_on_init():2402] communicating current version
2024-07-20 03:04:40,613 INFO    MainThread:34 [wandb_run.py:_on_init():2411] got version response upgrade_message: "wandb version 0.17.5 is available!  To upgrade, please run:\n $ pip install wandb --upgrade"

2024-07-20 03:04:40,613 INFO    MainThread:34 [wandb_init.py:init():804] starting run threads in backend
2024-07-20 03:04:56,689 INFO    MainThread:34 [wandb_run.py:_console_start():2380] atexit reg
2024-07-20 03:04:56,690 INFO    MainThread:34 [wandb_run.py:_redirect():2235] redirect: wrap_raw
2024-07-20 03:04:56,690 INFO    MainThread:34 [wandb_run.py:_redirect():2300] Wrapping output streams.
2024-07-20 03:04:56,690 INFO    MainThread:34 [wandb_run.py:_redirect():2325] Redirects installed.
2024-07-20 03:04:56,694 INFO    MainThread:34 [wandb_init.py:init():847] run started, returning control to user process
2024-07-20 03:04:56,698 INFO    MainThread:34 [jupyter.py:save_ipynb():372] not saving jupyter notebook
2024-07-20 03:04:56,698 INFO    MainThread:34 [wandb_init.py:_pause_backend():440] pausing backend
2024-07-20 03:04:56,703 INFO    MainThread:34 [wandb_init.py:_resume_backend():445] resuming backend
2024-07-20 03:04:56,704 INFO    MainThread:34 [jupyter.py:save_ipynb():372] not saving jupyter notebook
2024-07-20 03:04:56,704 INFO    MainThread:34 [wandb_init.py:_pause_backend():440] pausing backend
2024-07-20 03:04:56,711 INFO    MainThread:34 [wandb_init.py:_resume_backend():445] resuming backend
2024-07-20 03:04:56,738 INFO    MainThread:34 [jupyter.py:save_ipynb():372] not saving jupyter notebook
2024-07-20 03:04:56,739 INFO    MainThread:34 [wandb_init.py:_pause_backend():440] pausing backend
2024-07-20 03:04:56,744 INFO    MainThread:34 [wandb_init.py:_resume_backend():445] resuming backend
2024-07-20 03:04:56,746 INFO    MainThread:34 [jupyter.py:save_ipynb():372] not saving jupyter notebook
2024-07-20 03:04:56,746 INFO    MainThread:34 [wandb_init.py:_pause_backend():440] pausing backend
2024-07-20 03:04:56,756 INFO    MainThread:34 [wandb_init.py:_resume_backend():445] resuming backend
2024-07-20 03:04:56,760 INFO    MainThread:34 [jupyter.py:save_ipynb():372] not saving jupyter notebook
2024-07-20 03:04:56,760 INFO    MainThread:34 [wandb_init.py:_pause_backend():440] pausing backend
2024-07-20 03:04:56,765 INFO    MainThread:34 [wandb_init.py:_resume_backend():445] resuming backend
2024-07-20 03:04:56,777 INFO    MainThread:34 [jupyter.py:save_ipynb():372] not saving jupyter notebook
2024-07-20 03:04:56,777 INFO    MainThread:34 [wandb_init.py:_pause_backend():440] pausing backend
2024-07-20 03:04:56,782 INFO    MainThread:34 [wandb_init.py:_resume_backend():445] resuming backend
2024-07-20 03:04:57,397 INFO    MainThread:34 [jupyter.py:save_ipynb():372] not saving jupyter notebook
2024-07-20 03:04:57,398 INFO    MainThread:34 [wandb_init.py:_pause_backend():440] pausing backend
2024-07-20 03:04:57,403 INFO    MainThread:34 [wandb_init.py:_resume_backend():445] resuming backend
2024-07-20 03:04:57,912 INFO    MainThread:34 [wandb_run.py:_config_callback():1382] config_cb None None {'output_dir': './', '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': 1, 'eval_accumulation_steps': None, 'eval_delay': 0, 'learning_rate': 1e-05, 'weight_decay': 0.01, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 1, 'max_steps': -1, 'lr_scheduler_type': 'linear', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.0, 'warmup_steps': 0, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': './runs/Jul20_03-04-56_6748368f09b6', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 1, '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, 'use_ipex': False, 'bf16': False, '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': './', 'disable_tqdm': False, 'remove_unused_columns': False, 'label_names': None, '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}, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'adamw_torch', 'optim_args': None, 'adafactor': False, 'group_by_length': False, 'length_column_name': 'length', 'report_to': ['wandb'], 'ddp_find_unused_parameters': None, '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': True, 'resume_from_checkpoint': None, 'hub_model_id': 'VQA2', 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': False, 'hub_always_push': False, 'gradient_checkpointing': False, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'eval_do_concat_batches': True, 'fp16_backend': 'auto', 'evaluation_strategy': None, '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, 'dispatch_batches': None, 'split_batches': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'optim_target_modules': None, 'batch_eval_metrics': False, 'eval_on_start': False}
2024-07-20 03:04:58,253 INFO    MainThread:34 [wandb_run.py:_config_callback():1382] config_cb None None {'output_dir': './', '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': 1, 'eval_accumulation_steps': None, 'eval_delay': 0, 'learning_rate': 1e-05, 'weight_decay': 0.01, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 1, 'max_steps': -1, 'lr_scheduler_type': 'linear', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.0, 'warmup_steps': 0, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': './runs/Jul20_03-04-56_6748368f09b6', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 1, '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, 'use_ipex': False, 'bf16': False, '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': './', 'disable_tqdm': False, 'remove_unused_columns': False, 'label_names': None, '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}, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'adamw_torch', 'optim_args': None, 'adafactor': False, 'group_by_length': False, 'length_column_name': 'length', 'report_to': ['wandb'], 'ddp_find_unused_parameters': None, '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': True, 'resume_from_checkpoint': None, 'hub_model_id': 'VQA2', 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': False, 'hub_always_push': False, 'gradient_checkpointing': False, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'eval_do_concat_batches': True, 'fp16_backend': 'auto', 'evaluation_strategy': None, '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, 'dispatch_batches': None, 'split_batches': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'optim_target_modules': None, 'batch_eval_metrics': False, 'eval_on_start': False}