Training in progress, step 10

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d43b89b9489e972ff5b1a7ebdcdc36465302119805e36b126fccc170f4d245f4
+oid sha256:5d662881ad5bd6a5e9cb904c8ec1071832025ea829dd9a24cacf8be199b166b3
 size 4537938567

model3.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1edabe946a87b603b45a8b5d06fdfd02329a8e609be732daeadcd4b98c55d1e
+size 2441024144

model3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1edabe946a87b603b45a8b5d06fdfd02329a8e609be732daeadcd4b98c55d1e
+size 2441024144

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f04da63cd1a5dbe508590084590e35fe6a2306f7f42a1d690154e89334012c49
+oid sha256:585d6cb9cb675846c9c0afe34d740c270b13db7ab1ffb68a22f5d896b27c926b
 size 5112

wandb/debug.log

@@ -45,3 +45,50 @@ config: {}
 2024-07-20 01:43:47,910 INFO    MainThread:34 [wandb_init.py:_pause_backend():440] pausing backend
 2024-07-20 01:43:53,121 INFO    MainThread:34 [wandb_init.py:_resume_backend():445] resuming backend
 2024-07-20 01:43:53,651 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_01-43-28_0b51fb85f282', '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 01:46:56,536 INFO    MainThread:34 [jupyter.py:save_ipynb():372] not saving jupyter notebook
+2024-07-20 01:46:56,536 INFO    MainThread:34 [wandb_init.py:_pause_backend():440] pausing backend
+2024-07-20 01:47:17,038 INFO    MainThread:34 [wandb_init.py:_resume_backend():445] resuming backend
+2024-07-20 01:47:17,047 INFO    MainThread:34 [jupyter.py:save_ipynb():372] not saving jupyter notebook
+2024-07-20 01:47:17,048 INFO    MainThread:34 [wandb_init.py:_pause_backend():440] pausing backend
+2024-07-20 01:47:36,226 INFO    MainThread:34 [wandb_init.py:_resume_backend():445] resuming backend
+2024-07-20 01:47:36,234 INFO    MainThread:34 [jupyter.py:save_ipynb():372] not saving jupyter notebook
+2024-07-20 01:47:36,234 INFO    MainThread:34 [wandb_init.py:_pause_backend():440] pausing backend
+2024-07-20 01:47:49,484 INFO    MainThread:34 [wandb_init.py:_resume_backend():445] resuming backend
+2024-07-20 01:47:53,520 INFO    MainThread:34 [jupyter.py:save_ipynb():372] not saving jupyter notebook
+2024-07-20 01:47:53,520 INFO    MainThread:34 [wandb_init.py:_pause_backend():440] pausing backend
+2024-07-20 01:48:24,163 INFO    MainThread:34 [wandb_init.py:_resume_backend():445] resuming backend
+2024-07-20 01:48:24,164 INFO    MainThread:34 [jupyter.py:save_ipynb():372] not saving jupyter notebook
+2024-07-20 01:48:24,164 INFO    MainThread:34 [wandb_init.py:_pause_backend():440] pausing backend
+2024-07-20 01:48:26,305 INFO    MainThread:34 [wandb_init.py:_resume_backend():445] resuming backend
+2024-07-20 01:48:30,171 INFO    MainThread:34 [jupyter.py:save_ipynb():372] not saving jupyter notebook
+2024-07-20 01:48:30,171 INFO    MainThread:34 [wandb_init.py:_pause_backend():440] pausing backend
+2024-07-20 01:49:49,295 INFO    MainThread:34 [wandb_init.py:_resume_backend():445] resuming backend
+2024-07-20 01:49:49,302 INFO    MainThread:34 [jupyter.py:save_ipynb():372] not saving jupyter notebook
+2024-07-20 01:49:49,302 INFO    MainThread:34 [wandb_init.py:_pause_backend():440] pausing backend
+2024-07-20 01:59:51,087 INFO    MainThread:34 [wandb_init.py:_resume_backend():445] resuming backend
+2024-07-20 01:59:54,978 INFO    MainThread:34 [jupyter.py:save_ipynb():372] not saving jupyter notebook
+2024-07-20 01:59:54,979 INFO    MainThread:34 [wandb_init.py:_pause_backend():440] pausing backend
+2024-07-20 02:00:37,626 INFO    MainThread:34 [wandb_init.py:_resume_backend():445] resuming backend
+2024-07-20 02:00:37,633 INFO    MainThread:34 [jupyter.py:save_ipynb():372] not saving jupyter notebook
+2024-07-20 02:00:37,633 INFO    MainThread:34 [wandb_init.py:_pause_backend():440] pausing backend
+2024-07-20 02:05:35,978 INFO    MainThread:34 [wandb_init.py:_resume_backend():445] resuming backend
+2024-07-20 02:05:35,983 INFO    MainThread:34 [jupyter.py:save_ipynb():372] not saving jupyter notebook
+2024-07-20 02:05:35,983 INFO    MainThread:34 [wandb_init.py:_pause_backend():440] pausing backend
+2024-07-20 02:07:16,157 INFO    MainThread:34 [wandb_init.py:_resume_backend():445] resuming backend
+2024-07-20 02:07:16,159 INFO    MainThread:34 [jupyter.py:save_ipynb():372] not saving jupyter notebook
+2024-07-20 02:07:16,159 INFO    MainThread:34 [wandb_init.py:_pause_backend():440] pausing backend
+2024-07-20 02:07:50,609 INFO    MainThread:34 [wandb_init.py:_resume_backend():445] resuming backend
+2024-07-20 02:07:50,638 INFO    MainThread:34 [jupyter.py:save_ipynb():372] not saving jupyter notebook
+2024-07-20 02:07:50,638 INFO    MainThread:34 [wandb_init.py:_pause_backend():440] pausing backend
+2024-07-20 02:07:51,986 INFO    MainThread:34 [wandb_init.py:_resume_backend():445] resuming backend
+2024-07-20 02:07:51,988 INFO    MainThread:34 [jupyter.py:save_ipynb():372] not saving jupyter notebook
+2024-07-20 02:07:51,988 INFO    MainThread:34 [wandb_init.py:_pause_backend():440] pausing backend
+2024-07-20 02:07:52,248 INFO    MainThread:34 [wandb_init.py:_resume_backend():445] resuming backend
+2024-07-20 02:07:52,252 INFO    MainThread:34 [jupyter.py:save_ipynb():372] not saving jupyter notebook
+2024-07-20 02:07:52,252 INFO    MainThread:34 [wandb_init.py:_pause_backend():440] pausing backend
+2024-07-20 02:07:54,102 INFO    MainThread:34 [wandb_init.py:_resume_backend():445] resuming backend
+2024-07-20 02:07:54,254 INFO    MainThread:34 [jupyter.py:save_ipynb():372] not saving jupyter notebook
+2024-07-20 02:07:54,254 INFO    MainThread:34 [wandb_init.py:_pause_backend():440] pausing backend
+2024-07-20 02:08:27,277 INFO    MainThread:34 [wandb_init.py:_resume_backend():445] resuming backend
+2024-07-20 02:08:27,983 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_02-07-50_0b51fb85f282', '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 02:08:28,174 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_02-07-50_0b51fb85f282', '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}

wandb/run-20240720_014300-i371q464/files/config.yaml

@@ -42,6 +42,7 @@ _wandb:
       - 98
       - 105
       3:
+      - 3
       - 7
       - 23
       - 62
@@ -165,7 +166,7 @@ log_on_each_node:
   value: true
 logging_dir:
   desc: null
-  value: ./runs/Jul20_01-43-28_0b51fb85f282
+  value: ./runs/Jul20_02-07-50_0b51fb85f282
 logging_strategy:
   desc: null
   value: steps

wandb/run-20240720_014300-i371q464/files/model3.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1edabe946a87b603b45a8b5d06fdfd02329a8e609be732daeadcd4b98c55d1e
+size 2441024144

wandb/run-20240720_014300-i371q464/files/output.log

@@ -1 +1,5 @@
 
+wandb: WARNING The `run_name` is currently set to the same value as `TrainingArguments.output_dir`. If this was not intended, please specify a different run name by setting the `TrainingArguments.run_name` parameter.
+wandb: WARNING Saving files without folders. If you want to preserve subdirectories pass base_path to wandb.save, i.e. wandb.save("/mnt/folder/file.h5", base_path="/mnt")
+You are adding a <class 'transformers.integrations.integration_utils.WandbCallback'> to the callbacks of this Trainer, but there is already one. The currentlist of callbacks is
+:DefaultFlowCallback

wandb/run-20240720_014300-i371q464/files/wandb-summary.json

@@ -1 +1 @@
-{"train/loss": 15.4961, "train/grad_norm": 997.5324096679688, "train/learning_rate": 0.0, "train/epoch": 1.0, "train/global_step": 10, "_timestamp": 1721439890.056635, "_runtime": 109.13044786453247, "_step": 10, "train_runtime": 56.4138, "train_samples_per_second": 0.177, "train_steps_per_second": 0.177, "total_flos": 0.0, "train_loss": 18.238642311096193}
+{"train/loss": 13.2675, "train/grad_norm": 374.0868225097656, "train/learning_rate": 0.0, "train/epoch": 1.0, "train/global_step": 10, "_timestamp": 1721441374.7799897, "_runtime": 1593.8538026809692, "_step": 32, "train_runtime": 66.8024, "train_samples_per_second": 0.15, "train_steps_per_second": 0.15, "total_flos": 0.0, "train_loss": 14.448832511901855}

wandb/run-20240720_014300-i371q464/files/working/model3.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1edabe946a87b603b45a8b5d06fdfd02329a8e609be732daeadcd4b98c55d1e
+size 2441024144

wandb/run-20240720_014300-i371q464/files/working/model3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1edabe946a87b603b45a8b5d06fdfd02329a8e609be732daeadcd4b98c55d1e
+size 2441024144

wandb/run-20240720_014300-i371q464/logs/debug.log

@@ -45,3 +45,50 @@ config: {}
 2024-07-20 01:43:47,910 INFO    MainThread:34 [wandb_init.py:_pause_backend():440] pausing backend
 2024-07-20 01:43:53,121 INFO    MainThread:34 [wandb_init.py:_resume_backend():445] resuming backend
 2024-07-20 01:43:53,651 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_01-43-28_0b51fb85f282', '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 01:46:56,536 INFO    MainThread:34 [jupyter.py:save_ipynb():372] not saving jupyter notebook
+2024-07-20 01:46:56,536 INFO    MainThread:34 [wandb_init.py:_pause_backend():440] pausing backend
+2024-07-20 01:47:17,038 INFO    MainThread:34 [wandb_init.py:_resume_backend():445] resuming backend
+2024-07-20 01:47:17,047 INFO    MainThread:34 [jupyter.py:save_ipynb():372] not saving jupyter notebook
+2024-07-20 01:47:17,048 INFO    MainThread:34 [wandb_init.py:_pause_backend():440] pausing backend
+2024-07-20 01:47:36,226 INFO    MainThread:34 [wandb_init.py:_resume_backend():445] resuming backend
+2024-07-20 01:47:36,234 INFO    MainThread:34 [jupyter.py:save_ipynb():372] not saving jupyter notebook
+2024-07-20 01:47:36,234 INFO    MainThread:34 [wandb_init.py:_pause_backend():440] pausing backend
+2024-07-20 01:47:49,484 INFO    MainThread:34 [wandb_init.py:_resume_backend():445] resuming backend
+2024-07-20 01:47:53,520 INFO    MainThread:34 [jupyter.py:save_ipynb():372] not saving jupyter notebook
+2024-07-20 01:47:53,520 INFO    MainThread:34 [wandb_init.py:_pause_backend():440] pausing backend
+2024-07-20 01:48:24,163 INFO    MainThread:34 [wandb_init.py:_resume_backend():445] resuming backend
+2024-07-20 01:48:24,164 INFO    MainThread:34 [jupyter.py:save_ipynb():372] not saving jupyter notebook
+2024-07-20 01:48:24,164 INFO    MainThread:34 [wandb_init.py:_pause_backend():440] pausing backend
+2024-07-20 01:48:26,305 INFO    MainThread:34 [wandb_init.py:_resume_backend():445] resuming backend
+2024-07-20 01:48:30,171 INFO    MainThread:34 [jupyter.py:save_ipynb():372] not saving jupyter notebook
+2024-07-20 01:48:30,171 INFO    MainThread:34 [wandb_init.py:_pause_backend():440] pausing backend
+2024-07-20 01:49:49,295 INFO    MainThread:34 [wandb_init.py:_resume_backend():445] resuming backend
+2024-07-20 01:49:49,302 INFO    MainThread:34 [jupyter.py:save_ipynb():372] not saving jupyter notebook
+2024-07-20 01:49:49,302 INFO    MainThread:34 [wandb_init.py:_pause_backend():440] pausing backend
+2024-07-20 01:59:51,087 INFO    MainThread:34 [wandb_init.py:_resume_backend():445] resuming backend
+2024-07-20 01:59:54,978 INFO    MainThread:34 [jupyter.py:save_ipynb():372] not saving jupyter notebook
+2024-07-20 01:59:54,979 INFO    MainThread:34 [wandb_init.py:_pause_backend():440] pausing backend
+2024-07-20 02:00:37,626 INFO    MainThread:34 [wandb_init.py:_resume_backend():445] resuming backend
+2024-07-20 02:00:37,633 INFO    MainThread:34 [jupyter.py:save_ipynb():372] not saving jupyter notebook
+2024-07-20 02:00:37,633 INFO    MainThread:34 [wandb_init.py:_pause_backend():440] pausing backend
+2024-07-20 02:05:35,978 INFO    MainThread:34 [wandb_init.py:_resume_backend():445] resuming backend
+2024-07-20 02:05:35,983 INFO    MainThread:34 [jupyter.py:save_ipynb():372] not saving jupyter notebook
+2024-07-20 02:05:35,983 INFO    MainThread:34 [wandb_init.py:_pause_backend():440] pausing backend
+2024-07-20 02:07:16,157 INFO    MainThread:34 [wandb_init.py:_resume_backend():445] resuming backend
+2024-07-20 02:07:16,159 INFO    MainThread:34 [jupyter.py:save_ipynb():372] not saving jupyter notebook
+2024-07-20 02:07:16,159 INFO    MainThread:34 [wandb_init.py:_pause_backend():440] pausing backend
+2024-07-20 02:07:50,609 INFO    MainThread:34 [wandb_init.py:_resume_backend():445] resuming backend
+2024-07-20 02:07:50,638 INFO    MainThread:34 [jupyter.py:save_ipynb():372] not saving jupyter notebook
+2024-07-20 02:07:50,638 INFO    MainThread:34 [wandb_init.py:_pause_backend():440] pausing backend
+2024-07-20 02:07:51,986 INFO    MainThread:34 [wandb_init.py:_resume_backend():445] resuming backend
+2024-07-20 02:07:51,988 INFO    MainThread:34 [jupyter.py:save_ipynb():372] not saving jupyter notebook
+2024-07-20 02:07:51,988 INFO    MainThread:34 [wandb_init.py:_pause_backend():440] pausing backend
+2024-07-20 02:07:52,248 INFO    MainThread:34 [wandb_init.py:_resume_backend():445] resuming backend
+2024-07-20 02:07:52,252 INFO    MainThread:34 [jupyter.py:save_ipynb():372] not saving jupyter notebook
+2024-07-20 02:07:52,252 INFO    MainThread:34 [wandb_init.py:_pause_backend():440] pausing backend
+2024-07-20 02:07:54,102 INFO    MainThread:34 [wandb_init.py:_resume_backend():445] resuming backend
+2024-07-20 02:07:54,254 INFO    MainThread:34 [jupyter.py:save_ipynb():372] not saving jupyter notebook
+2024-07-20 02:07:54,254 INFO    MainThread:34 [wandb_init.py:_pause_backend():440] pausing backend
+2024-07-20 02:08:27,277 INFO    MainThread:34 [wandb_init.py:_resume_backend():445] resuming backend
+2024-07-20 02:08:27,983 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_02-07-50_0b51fb85f282', '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 02:08:28,174 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_02-07-50_0b51fb85f282', '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}