Hugging Face's logo

MalyO2
/
working

Object Detection
Transformers
Safetensors
detr
Generated from Trainer
Model card Files
xet
Community
working
File size: 59,474 Bytes 
e37bc1a
 
 
 
 
 
 
 
 
 
 
 
 
 
2cc896f
e37bc1a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c3f0b5e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
 
2024-11-27 17:27:45,783 INFO    MainThread:30 [wandb_setup.py:_flush():79] Current SDK version is 0.18.7
2024-11-27 17:27:45,783 INFO    MainThread:30 [wandb_setup.py:_flush():79] Configure stats pid to 30
2024-11-27 17:27:45,784 INFO    MainThread:30 [wandb_setup.py:_flush():79] Loading settings from /root/.config/wandb/settings
2024-11-27 17:27:45,784 INFO    MainThread:30 [wandb_setup.py:_flush():79] Loading settings from /kaggle/working/wandb/settings
2024-11-27 17:27:45,784 INFO    MainThread:30 [wandb_setup.py:_flush():79] Loading settings from environment variables: {}
2024-11-27 17:27:45,784 INFO    MainThread:30 [wandb_setup.py:_flush():79] Applying setup settings: {'mode': None, '_disable_service': None}
2024-11-27 17:27:45,784 INFO    MainThread:30 [wandb_setup.py:_flush():79] Inferring run settings from compute environment: {'program': '<python with no main file>'}
2024-11-27 17:27:45,784 INFO    MainThread:30 [wandb_setup.py:_flush():79] Applying login settings: {}
2024-11-27 17:27:45,784 INFO    MainThread:30 [wandb_setup.py:_flush():79] Applying login settings: {'api_key': '***REDACTED***'}
2024-11-27 17:27:45,784 INFO    MainThread:30 [wandb_init.py:_log_setup():533] Logging user logs to /kaggle/working/wandb/run-20241127_172745-6tkomlep/logs/debug.log
2024-11-27 17:27:45,784 INFO    MainThread:30 [wandb_init.py:_log_setup():534] Logging internal logs to /kaggle/working/wandb/run-20241127_172745-6tkomlep/logs/debug-internal.log
2024-11-27 17:27:45,784 INFO    MainThread:30 [wandb_init.py:_jupyter_setup():479] configuring jupyter hooks <wandb.sdk.wandb_init._WandbInit object at 0x7a776e285600>
2024-11-27 17:27:45,784 INFO    MainThread:30 [wandb_init.py:init():619] calling init triggers
2024-11-27 17:27:45,785 INFO    MainThread:30 [wandb_init.py:init():626] wandb.init called with sweep_config: {}
config: {'batch_size': 4, 'learning_rate': 0.0003, 'num_epochs': 100}
2024-11-27 17:27:45,785 INFO    MainThread:30 [wandb_init.py:init():644] re-initializing run, found existing run on stack: ukl4t7mf
2024-11-27 17:27:45,786 INFO    MainThread:30 [wandb_run.py:_finish():2155] finishing run swampinhabitant/detr-training/ukl4t7mf
2024-11-27 17:27:45,787 INFO    MainThread:30 [wandb_run.py:_atexit_cleanup():2420] got exitcode: 0
2024-11-27 17:27:45,787 INFO    MainThread:30 [wandb_run.py:_restore():2402] restore
2024-11-27 17:27:45,788 INFO    MainThread:30 [wandb_run.py:_restore():2408] restore done
2024-11-27 17:27:47,425 INFO    MainThread:30 [wandb_run.py:_footer_history_summary_info():3960] rendering history
2024-11-27 17:27:47,427 INFO    MainThread:30 [wandb_run.py:_footer_history_summary_info():3992] rendering summary
2024-11-27 17:27:47,434 INFO    MainThread:30 [wandb_run.py:_footer_sync_info():3921] logging synced files
2024-11-27 17:27:47,438 INFO    MainThread:30 [wandb_init.py:init():669] starting backend
2024-11-27 17:27:47,438 INFO    MainThread:30 [wandb_init.py:init():673] sending inform_init request
2024-11-27 17:27:47,440 INFO    MainThread:30 [backend.py:_multiprocessing_setup():104] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
2024-11-27 17:27:47,440 INFO    MainThread:30 [wandb_init.py:init():686] backend started and connected
2024-11-27 17:27:47,450 INFO    MainThread:30 [wandb_run.py:_label_probe_notebook():1339] probe notebook
2024-11-27 17:27:49,342 INFO    MainThread:30 [wandb_init.py:init():781] updated telemetry
2024-11-27 17:27:49,343 INFO    MainThread:30 [wandb_init.py:init():814] communicating run to backend with 90.0 second timeout
2024-11-27 17:27:49,487 INFO    MainThread:30 [wandb_init.py:init():867] starting run threads in backend
2024-11-27 17:27:50,077 INFO    MainThread:30 [wandb_run.py:_console_start():2456] atexit reg
2024-11-27 17:27:50,078 INFO    MainThread:30 [wandb_run.py:_redirect():2305] redirect: wrap_raw
2024-11-27 17:27:50,078 INFO    MainThread:30 [wandb_run.py:_redirect():2370] Wrapping output streams.
2024-11-27 17:27:50,078 INFO    MainThread:30 [wandb_run.py:_redirect():2395] Redirects installed.
2024-11-27 17:27:50,079 INFO    MainThread:30 [wandb_init.py:init():911] run started, returning control to user process
2024-11-27 17:27:50,080 INFO    MainThread:30 [jupyter.py:save_ipynb():387] not saving jupyter notebook
2024-11-27 17:27:50,080 INFO    MainThread:30 [wandb_init.py:_pause_backend():444] pausing backend
2024-11-27 17:28:59,485 INFO    MainThread:30 [wandb_init.py:_resume_backend():449] resuming backend
2024-11-27 17:28:59,525 INFO    MainThread:30 [jupyter.py:save_ipynb():387] not saving jupyter notebook
2024-11-27 17:28:59,525 INFO    MainThread:30 [wandb_init.py:_pause_backend():444] pausing backend
2024-11-27 17:29:03,314 INFO    MainThread:30 [wandb_init.py:_resume_backend():449] resuming backend
2024-11-27 17:29:03,318 INFO    MainThread:30 [jupyter.py:save_ipynb():387] not saving jupyter notebook
2024-11-27 17:29:03,318 INFO    MainThread:30 [wandb_init.py:_pause_backend():444] pausing backend
2024-11-27 17:29:03,752 INFO    MainThread:30 [wandb_init.py:_resume_backend():449] resuming backend
2024-11-27 17:29:04,012 INFO    MainThread:30 [jupyter.py:save_ipynb():387] not saving jupyter notebook
2024-11-27 17:29:04,012 INFO    MainThread:30 [wandb_init.py:_pause_backend():444] pausing backend
2024-11-27 17:29:08,085 INFO    MainThread:30 [wandb_init.py:_resume_backend():449] resuming backend
2024-11-27 17:29:08,658 INFO    MainThread:30 [wandb_run.py:_config_callback():1387] config_cb None None {'use_timm_backbone': True, 'backbone_config': None, 'num_channels': 3, 'num_queries': 100, 'd_model': 256, 'encoder_ffn_dim': 2048, 'encoder_layers': 6, 'encoder_attention_heads': 8, 'decoder_ffn_dim': 2048, 'decoder_layers': 6, 'decoder_attention_heads': 8, 'dropout': 0.1, 'attention_dropout': 0.0, 'activation_dropout': 0.0, 'activation_function': 'relu', 'init_std': 0.02, 'init_xavier_std': 1.0, 'encoder_layerdrop': 0.0, 'decoder_layerdrop': 0.0, 'num_hidden_layers': 6, 'auxiliary_loss': False, 'position_embedding_type': 'sine', 'backbone': 'resnet50', 'use_pretrained_backbone': True, 'backbone_kwargs': {'output_stride': 16, 'out_indices': [1, 2, 3, 4], 'in_chans': 3}, 'dilation': True, 'class_cost': 1, 'bbox_cost': 5, 'giou_cost': 2, 'mask_loss_coefficient': 1, 'dice_loss_coefficient': 1, 'bbox_loss_coefficient': 5, 'giou_loss_coefficient': 2, 'eos_coefficient': 0.1, 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': None, 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': True, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['DetrForObjectDetection'], 'finetuning_task': None, 'id2label': {0: 'object', 1: 'balloon'}, 'label2id': {'object': 0, 'balloon': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': None, 'pad_token_id': None, 'eos_token_id': None, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'facebook/detr-resnet-50-dc5', '_attn_implementation_autoset': True, 'transformers_version': '4.46.3', 'classifier_dropout': 0.0, 'max_position_embeddings': 1024, 'model_type': 'detr', 'scale_embedding': False, 'output_dir': '.', 'overwrite_output_dir': False, 'do_train': False, 'do_eval': True, 'do_predict': False, 'eval_strategy': 'steps', 'prediction_loss_only': False, 'per_device_train_batch_size': 4, 'per_device_eval_batch_size': 4, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 1, 'eval_accumulation_steps': None, 'eval_delay': 0, 'torch_empty_cache_steps': None, 'learning_rate': 3e-05, 'weight_decay': 0.0001, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 3.0, 'max_steps': 500, '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/Nov27_17-29-03_f5b68522d064', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 5, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 10, 'save_total_limit': 2, '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': True, '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': 10, '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': None, '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, 'include_for_metrics': [], 'eval_do_concat_batches': True, 'fp16_backend': 'auto', 'evaluation_strategy': 'steps', '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': True, 'eval_on_start': False, 'use_liger_kernel': False, 'eval_use_gather_object': False, 'average_tokens_across_devices': False}
2024-11-27 17:29:08,663 INFO    MainThread:30 [wandb_config.py:__setitem__():154] config set model/num_parameters = 41501895 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x7a7699a6ddb0>>
2024-11-27 17:29:08,663 INFO    MainThread:30 [wandb_run.py:_config_callback():1387] config_cb model/num_parameters 41501895 None
2024-11-27 17:29:16,918 INFO    MainThread:30 [jupyter.py:save_ipynb():387] not saving jupyter notebook
2024-11-27 17:29:16,918 INFO    MainThread:30 [wandb_init.py:_pause_backend():444] pausing backend
2024-11-27 17:31:48,418 INFO    MainThread:30 [wandb_init.py:_resume_backend():449] resuming backend
2024-11-27 17:31:48,420 INFO    MainThread:30 [jupyter.py:save_ipynb():387] not saving jupyter notebook
2024-11-27 17:31:48,420 INFO    MainThread:30 [wandb_init.py:_pause_backend():444] pausing backend
2024-11-27 17:32:08,301 INFO    MainThread:30 [wandb_init.py:_resume_backend():449] resuming backend
2024-11-27 17:32:08,304 INFO    MainThread:30 [jupyter.py:save_ipynb():387] not saving jupyter notebook
2024-11-27 17:32:08,304 INFO    MainThread:30 [wandb_init.py:_pause_backend():444] pausing backend
2024-11-27 17:32:09,217 INFO    MainThread:30 [wandb_init.py:_resume_backend():449] resuming backend
2024-11-27 17:32:09,365 INFO    MainThread:30 [jupyter.py:save_ipynb():387] not saving jupyter notebook
2024-11-27 17:32:09,365 INFO    MainThread:30 [wandb_init.py:_pause_backend():444] pausing backend
2024-11-27 17:32:10,364 INFO    MainThread:30 [wandb_init.py:_resume_backend():449] resuming backend
2024-11-27 17:32:11,093 INFO    MainThread:30 [wandb_run.py:_config_callback():1387] config_cb None None {'use_timm_backbone': True, 'backbone_config': None, 'num_channels': 3, 'num_queries': 100, 'd_model': 256, 'encoder_ffn_dim': 2048, 'encoder_layers': 6, 'encoder_attention_heads': 8, 'decoder_ffn_dim': 2048, 'decoder_layers': 6, 'decoder_attention_heads': 8, 'dropout': 0.1, 'attention_dropout': 0.0, 'activation_dropout': 0.0, 'activation_function': 'relu', 'init_std': 0.02, 'init_xavier_std': 1.0, 'encoder_layerdrop': 0.0, 'decoder_layerdrop': 0.0, 'num_hidden_layers': 6, 'auxiliary_loss': False, 'position_embedding_type': 'sine', 'backbone': 'resnet50', 'use_pretrained_backbone': True, 'backbone_kwargs': {'output_stride': 16, 'out_indices': [1, 2, 3, 4], 'in_chans': 3}, 'dilation': True, 'class_cost': 1, 'bbox_cost': 5, 'giou_cost': 2, 'mask_loss_coefficient': 1, 'dice_loss_coefficient': 1, 'bbox_loss_coefficient': 5, 'giou_loss_coefficient': 2, 'eos_coefficient': 0.1, 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': None, 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': True, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['DetrForObjectDetection'], 'finetuning_task': None, 'id2label': {0: 'object', 1: 'balloon'}, 'label2id': {'object': 0, 'balloon': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': None, 'pad_token_id': None, 'eos_token_id': None, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'facebook/detr-resnet-50-dc5', '_attn_implementation_autoset': True, 'transformers_version': '4.46.3', 'classifier_dropout': 0.0, 'max_position_embeddings': 1024, 'model_type': 'detr', 'scale_embedding': False, 'output_dir': '.', 'overwrite_output_dir': False, 'do_train': False, 'do_eval': True, 'do_predict': False, 'eval_strategy': 'steps', 'prediction_loss_only': False, 'per_device_train_batch_size': 4, 'per_device_eval_batch_size': 4, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 1, 'eval_accumulation_steps': None, 'eval_delay': 0, 'torch_empty_cache_steps': None, 'learning_rate': 3e-05, 'weight_decay': 0.0001, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 3.0, 'max_steps': 500, '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/Nov27_17-32-09_f5b68522d064', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 5, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 10, 'save_total_limit': 2, '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': True, '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': 10, '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': None, '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, 'include_for_metrics': [], 'eval_do_concat_batches': True, 'fp16_backend': 'auto', 'evaluation_strategy': 'steps', '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': True, 'eval_on_start': False, 'use_liger_kernel': False, 'eval_use_gather_object': False, 'average_tokens_across_devices': False}
2024-11-27 17:32:11,098 INFO    MainThread:30 [wandb_config.py:__setitem__():154] config set model/num_parameters = 41501895 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x7a7699a6ddb0>>
2024-11-27 17:32:11,098 INFO    MainThread:30 [wandb_run.py:_config_callback():1387] config_cb model/num_parameters 41501895 None
2024-11-27 17:32:18,716 INFO    MainThread:30 [jupyter.py:save_ipynb():387] not saving jupyter notebook
2024-11-27 17:32:18,716 INFO    MainThread:30 [wandb_init.py:_pause_backend():444] pausing backend
2024-11-27 17:32:36,579 INFO    MainThread:30 [wandb_init.py:_resume_backend():449] resuming backend
2024-11-27 17:32:36,581 INFO    MainThread:30 [jupyter.py:save_ipynb():387] not saving jupyter notebook
2024-11-27 17:32:36,581 INFO    MainThread:30 [wandb_init.py:_pause_backend():444] pausing backend
2024-11-27 17:32:41,335 INFO    MainThread:30 [wandb_init.py:_resume_backend():449] resuming backend
2024-11-27 17:32:41,338 INFO    MainThread:30 [jupyter.py:save_ipynb():387] not saving jupyter notebook
2024-11-27 17:32:41,338 INFO    MainThread:30 [wandb_init.py:_pause_backend():444] pausing backend
2024-11-27 17:32:41,778 INFO    MainThread:30 [wandb_init.py:_resume_backend():449] resuming backend
2024-11-27 17:32:41,914 INFO    MainThread:30 [jupyter.py:save_ipynb():387] not saving jupyter notebook
2024-11-27 17:32:41,915 INFO    MainThread:30 [wandb_init.py:_pause_backend():444] pausing backend
2024-11-27 17:32:42,768 INFO    MainThread:30 [wandb_init.py:_resume_backend():449] resuming backend
2024-11-27 17:32:42,771 INFO    MainThread:30 [jupyter.py:save_ipynb():387] not saving jupyter notebook
2024-11-27 17:32:42,771 INFO    MainThread:30 [wandb_init.py:_pause_backend():444] pausing backend
2024-11-27 17:32:50,911 INFO    MainThread:30 [wandb_init.py:_resume_backend():449] resuming backend
2024-11-27 17:32:51,710 INFO    MainThread:30 [wandb_run.py:_config_callback():1387] config_cb None None {'use_timm_backbone': True, 'backbone_config': None, 'num_channels': 3, 'num_queries': 100, 'd_model': 256, 'encoder_ffn_dim': 2048, 'encoder_layers': 6, 'encoder_attention_heads': 8, 'decoder_ffn_dim': 2048, 'decoder_layers': 6, 'decoder_attention_heads': 8, 'dropout': 0.1, 'attention_dropout': 0.0, 'activation_dropout': 0.0, 'activation_function': 'relu', 'init_std': 0.02, 'init_xavier_std': 1.0, 'encoder_layerdrop': 0.0, 'decoder_layerdrop': 0.0, 'num_hidden_layers': 6, 'auxiliary_loss': False, 'position_embedding_type': 'sine', 'backbone': 'resnet50', 'use_pretrained_backbone': True, 'backbone_kwargs': {'output_stride': 16, 'out_indices': [1, 2, 3, 4], 'in_chans': 3}, 'dilation': True, 'class_cost': 1, 'bbox_cost': 5, 'giou_cost': 2, 'mask_loss_coefficient': 1, 'dice_loss_coefficient': 1, 'bbox_loss_coefficient': 5, 'giou_loss_coefficient': 2, 'eos_coefficient': 0.1, 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': None, 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': True, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['DetrForObjectDetection'], 'finetuning_task': None, 'id2label': {0: 'object', 1: 'balloon'}, 'label2id': {'object': 0, 'balloon': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': None, 'pad_token_id': None, 'eos_token_id': None, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'facebook/detr-resnet-50-dc5', '_attn_implementation_autoset': True, 'transformers_version': '4.46.3', 'classifier_dropout': 0.0, 'max_position_embeddings': 1024, 'model_type': 'detr', 'scale_embedding': False, 'output_dir': '.', 'overwrite_output_dir': False, 'do_train': False, 'do_eval': True, 'do_predict': False, 'eval_strategy': 'steps', 'prediction_loss_only': False, 'per_device_train_batch_size': 4, 'per_device_eval_batch_size': 4, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 1, 'eval_accumulation_steps': None, 'eval_delay': 0, 'torch_empty_cache_steps': None, 'learning_rate': 3e-05, 'weight_decay': 0.0001, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 3.0, 'max_steps': 500, '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/Nov27_17-32-41_f5b68522d064', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 5, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 10, 'save_total_limit': 2, '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': True, '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': 10, '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': None, '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, 'include_for_metrics': [], 'eval_do_concat_batches': True, 'fp16_backend': 'auto', 'evaluation_strategy': 'steps', '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': True, 'eval_on_start': False, 'use_liger_kernel': False, 'eval_use_gather_object': False, 'average_tokens_across_devices': False}
2024-11-27 17:32:51,714 INFO    MainThread:30 [wandb_config.py:__setitem__():154] config set model/num_parameters = 41501895 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x7a7699a6ddb0>>
2024-11-27 17:32:51,715 INFO    MainThread:30 [wandb_run.py:_config_callback():1387] config_cb model/num_parameters 41501895 None
2024-11-27 17:32:59,752 INFO    MainThread:30 [jupyter.py:save_ipynb():387] not saving jupyter notebook
2024-11-27 17:32:59,752 INFO    MainThread:30 [wandb_init.py:_pause_backend():444] pausing backend
2024-11-27 17:34:05,745 INFO    MainThread:30 [wandb_init.py:_resume_backend():449] resuming backend
2024-11-27 17:34:05,747 INFO    MainThread:30 [jupyter.py:save_ipynb():387] not saving jupyter notebook
2024-11-27 17:34:05,747 INFO    MainThread:30 [wandb_init.py:_pause_backend():444] pausing backend
2024-11-27 17:34:10,314 INFO    MainThread:30 [wandb_init.py:_resume_backend():449] resuming backend
2024-11-27 17:34:10,317 INFO    MainThread:30 [jupyter.py:save_ipynb():387] not saving jupyter notebook
2024-11-27 17:34:10,317 INFO    MainThread:30 [wandb_init.py:_pause_backend():444] pausing backend
2024-11-27 17:34:10,736 INFO    MainThread:30 [wandb_init.py:_resume_backend():449] resuming backend
2024-11-27 17:34:10,868 INFO    MainThread:30 [jupyter.py:save_ipynb():387] not saving jupyter notebook
2024-11-27 17:34:10,868 INFO    MainThread:30 [wandb_init.py:_pause_backend():444] pausing backend
2024-11-27 17:34:11,196 INFO    MainThread:30 [wandb_init.py:_resume_backend():449] resuming backend
2024-11-27 17:34:12,005 INFO    MainThread:30 [wandb_run.py:_config_callback():1387] config_cb None None {'use_timm_backbone': True, 'backbone_config': None, 'num_channels': 3, 'num_queries': 100, 'd_model': 256, 'encoder_ffn_dim': 2048, 'encoder_layers': 6, 'encoder_attention_heads': 8, 'decoder_ffn_dim': 2048, 'decoder_layers': 6, 'decoder_attention_heads': 8, 'dropout': 0.1, 'attention_dropout': 0.0, 'activation_dropout': 0.0, 'activation_function': 'relu', 'init_std': 0.02, 'init_xavier_std': 1.0, 'encoder_layerdrop': 0.0, 'decoder_layerdrop': 0.0, 'num_hidden_layers': 6, 'auxiliary_loss': False, 'position_embedding_type': 'sine', 'backbone': 'resnet50', 'use_pretrained_backbone': True, 'backbone_kwargs': {'output_stride': 16, 'out_indices': [1, 2, 3, 4], 'in_chans': 3}, 'dilation': True, 'class_cost': 1, 'bbox_cost': 5, 'giou_cost': 2, 'mask_loss_coefficient': 1, 'dice_loss_coefficient': 1, 'bbox_loss_coefficient': 5, 'giou_loss_coefficient': 2, 'eos_coefficient': 0.1, 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': None, 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': True, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['DetrForObjectDetection'], 'finetuning_task': None, 'id2label': {0: 'object', 1: 'balloon'}, 'label2id': {'object': 0, 'balloon': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': None, 'pad_token_id': None, 'eos_token_id': None, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'facebook/detr-resnet-50-dc5', '_attn_implementation_autoset': True, 'transformers_version': '4.46.3', 'classifier_dropout': 0.0, 'max_position_embeddings': 1024, 'model_type': 'detr', 'scale_embedding': False, 'output_dir': '.', 'overwrite_output_dir': False, 'do_train': False, 'do_eval': True, 'do_predict': False, 'eval_strategy': 'steps', 'prediction_loss_only': False, 'per_device_train_batch_size': 4, 'per_device_eval_batch_size': 4, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 1, 'eval_accumulation_steps': None, 'eval_delay': 0, 'torch_empty_cache_steps': None, 'learning_rate': 3e-05, 'weight_decay': 0.0001, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 3.0, 'max_steps': 500, '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/Nov27_17-34-10_f5b68522d064', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 5, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 10, 'save_total_limit': 2, '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': True, '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': 10, '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': None, '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, 'include_for_metrics': [], 'eval_do_concat_batches': True, 'fp16_backend': 'auto', 'evaluation_strategy': 'steps', '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': True, 'eval_on_start': False, 'use_liger_kernel': False, 'eval_use_gather_object': False, 'average_tokens_across_devices': False}
2024-11-27 17:34:12,009 INFO    MainThread:30 [wandb_config.py:__setitem__():154] config set model/num_parameters = 41501895 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x7a7699a6ddb0>>
2024-11-27 17:34:12,010 INFO    MainThread:30 [wandb_run.py:_config_callback():1387] config_cb model/num_parameters 41501895 None
2024-11-27 17:34:19,510 INFO    MainThread:30 [jupyter.py:save_ipynb():387] not saving jupyter notebook
2024-11-27 17:34:19,510 INFO    MainThread:30 [wandb_init.py:_pause_backend():444] pausing backend
2024-11-27 17:35:15,517 INFO    MainThread:30 [wandb_init.py:_resume_backend():449] resuming backend
2024-11-27 17:35:15,519 INFO    MainThread:30 [jupyter.py:save_ipynb():387] not saving jupyter notebook
2024-11-27 17:35:15,520 INFO    MainThread:30 [wandb_init.py:_pause_backend():444] pausing backend
2024-11-27 17:35:19,372 INFO    MainThread:30 [wandb_init.py:_resume_backend():449] resuming backend
2024-11-27 17:35:19,375 INFO    MainThread:30 [jupyter.py:save_ipynb():387] not saving jupyter notebook
2024-11-27 17:35:19,375 INFO    MainThread:30 [wandb_init.py:_pause_backend():444] pausing backend
2024-11-27 17:35:19,718 INFO    MainThread:30 [wandb_init.py:_resume_backend():449] resuming backend
2024-11-27 17:35:19,857 INFO    MainThread:30 [jupyter.py:save_ipynb():387] not saving jupyter notebook
2024-11-27 17:35:19,857 INFO    MainThread:30 [wandb_init.py:_pause_backend():444] pausing backend
2024-11-27 17:35:21,000 INFO    MainThread:30 [wandb_init.py:_resume_backend():449] resuming backend
2024-11-27 17:35:21,801 INFO    MainThread:30 [wandb_run.py:_config_callback():1387] config_cb None None {'use_timm_backbone': True, 'backbone_config': None, 'num_channels': 3, 'num_queries': 100, 'd_model': 256, 'encoder_ffn_dim': 2048, 'encoder_layers': 6, 'encoder_attention_heads': 8, 'decoder_ffn_dim': 2048, 'decoder_layers': 6, 'decoder_attention_heads': 8, 'dropout': 0.1, 'attention_dropout': 0.0, 'activation_dropout': 0.0, 'activation_function': 'relu', 'init_std': 0.02, 'init_xavier_std': 1.0, 'encoder_layerdrop': 0.0, 'decoder_layerdrop': 0.0, 'num_hidden_layers': 6, 'auxiliary_loss': False, 'position_embedding_type': 'sine', 'backbone': 'resnet50', 'use_pretrained_backbone': True, 'backbone_kwargs': {'output_stride': 16, 'out_indices': [1, 2, 3, 4], 'in_chans': 3}, 'dilation': True, 'class_cost': 1, 'bbox_cost': 5, 'giou_cost': 2, 'mask_loss_coefficient': 1, 'dice_loss_coefficient': 1, 'bbox_loss_coefficient': 5, 'giou_loss_coefficient': 2, 'eos_coefficient': 0.1, 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': None, 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': True, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['DetrForObjectDetection'], 'finetuning_task': None, 'id2label': {0: 'object', 1: 'balloon'}, 'label2id': {'object': 0, 'balloon': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': None, 'pad_token_id': None, 'eos_token_id': None, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'facebook/detr-resnet-50-dc5', '_attn_implementation_autoset': True, 'transformers_version': '4.46.3', 'classifier_dropout': 0.0, 'max_position_embeddings': 1024, 'model_type': 'detr', 'scale_embedding': False, 'output_dir': '.', 'overwrite_output_dir': False, 'do_train': False, 'do_eval': True, 'do_predict': False, 'eval_strategy': 'steps', 'prediction_loss_only': False, 'per_device_train_batch_size': 4, 'per_device_eval_batch_size': 4, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 1, 'eval_accumulation_steps': None, 'eval_delay': 0, 'torch_empty_cache_steps': None, 'learning_rate': 3e-05, 'weight_decay': 0.0001, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 3.0, 'max_steps': 500, '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/Nov27_17-35-19_f5b68522d064', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 5, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 10, 'save_total_limit': 2, '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': True, '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': 10, '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': None, '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, 'include_for_metrics': [], 'eval_do_concat_batches': True, 'fp16_backend': 'auto', 'evaluation_strategy': 'steps', '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': True, 'eval_on_start': False, 'use_liger_kernel': False, 'eval_use_gather_object': False, 'average_tokens_across_devices': False}
2024-11-27 17:35:21,805 INFO    MainThread:30 [wandb_config.py:__setitem__():154] config set model/num_parameters = 41501895 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x7a7699a6ddb0>>
2024-11-27 17:35:21,805 INFO    MainThread:30 [wandb_run.py:_config_callback():1387] config_cb model/num_parameters 41501895 None
2024-11-27 17:35:40,674 INFO    MainThread:30 [jupyter.py:save_ipynb():387] not saving jupyter notebook
2024-11-27 17:35:40,674 INFO    MainThread:30 [wandb_init.py:_pause_backend():444] pausing backend
2024-11-27 17:47:22,107 INFO    MainThread:30 [wandb_init.py:_resume_backend():449] resuming backend
2024-11-27 17:47:22,110 INFO    MainThread:30 [jupyter.py:save_ipynb():387] not saving jupyter notebook
2024-11-27 17:47:22,110 INFO    MainThread:30 [wandb_init.py:_pause_backend():444] pausing backend
2024-11-27 17:47:25,397 INFO    MainThread:30 [wandb_init.py:_resume_backend():449] resuming backend
2024-11-27 17:47:25,571 INFO    MainThread:30 [jupyter.py:save_ipynb():387] not saving jupyter notebook
2024-11-27 17:47:25,571 INFO    MainThread:30 [wandb_init.py:_pause_backend():444] pausing backend
2024-11-27 17:47:28,282 INFO    MainThread:30 [wandb_init.py:_resume_backend():449] resuming backend
2024-11-27 17:47:28,815 INFO    MainThread:30 [wandb_run.py:_config_callback():1387] config_cb None None {'use_timm_backbone': True, 'backbone_config': None, 'num_channels': 3, 'num_queries': 100, 'd_model': 256, 'encoder_ffn_dim': 2048, 'encoder_layers': 6, 'encoder_attention_heads': 8, 'decoder_ffn_dim': 2048, 'decoder_layers': 6, 'decoder_attention_heads': 8, 'dropout': 0.1, 'attention_dropout': 0.0, 'activation_dropout': 0.0, 'activation_function': 'relu', 'init_std': 0.02, 'init_xavier_std': 1.0, 'encoder_layerdrop': 0.0, 'decoder_layerdrop': 0.0, 'num_hidden_layers': 6, 'auxiliary_loss': False, 'position_embedding_type': 'sine', 'backbone': 'resnet50', 'use_pretrained_backbone': True, 'backbone_kwargs': {'output_stride': 16, 'out_indices': [1, 2, 3, 4], 'in_chans': 3}, 'dilation': True, 'class_cost': 1, 'bbox_cost': 5, 'giou_cost': 2, 'mask_loss_coefficient': 1, 'dice_loss_coefficient': 1, 'bbox_loss_coefficient': 5, 'giou_loss_coefficient': 2, 'eos_coefficient': 0.1, 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'float32', 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': True, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['DetrForObjectDetection'], 'finetuning_task': None, 'id2label': {0: 'object', 1: 'balloon'}, 'label2id': {'object': 0, 'balloon': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': None, 'pad_token_id': None, 'eos_token_id': None, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'facebook/detr-resnet-50-dc5', '_attn_implementation_autoset': False, 'transformers_version': '4.46.3', 'classifier_dropout': 0.0, 'max_position_embeddings': 1024, 'model_type': 'detr', 'scale_embedding': False, 'output_dir': '.', 'overwrite_output_dir': False, 'do_train': False, 'do_eval': True, 'do_predict': False, 'eval_strategy': 'steps', 'prediction_loss_only': False, 'per_device_train_batch_size': 4, 'per_device_eval_batch_size': 4, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 1, 'eval_accumulation_steps': None, 'eval_delay': 0, 'torch_empty_cache_steps': None, 'learning_rate': 3e-05, 'weight_decay': 0.0001, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 3.0, 'max_steps': 500, '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/Nov27_17-47-25_f5b68522d064', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 5, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 10, 'save_total_limit': 2, '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': True, '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': 10, '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': None, '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, 'include_for_metrics': [], 'eval_do_concat_batches': True, 'fp16_backend': 'auto', 'evaluation_strategy': 'steps', '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': True, 'eval_on_start': False, 'use_liger_kernel': False, 'eval_use_gather_object': False, 'average_tokens_across_devices': False}
2024-11-27 17:47:28,820 INFO    MainThread:30 [wandb_config.py:__setitem__():154] config set model/num_parameters = 41501895 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x7a7699a6ddb0>>
2024-11-27 17:47:28,820 INFO    MainThread:30 [wandb_run.py:_config_callback():1387] config_cb model/num_parameters 41501895 None
2024-11-27 17:50:48,066 INFO    MainThread:30 [jupyter.py:save_ipynb():387] not saving jupyter notebook
2024-11-27 17:50:48,067 INFO    MainThread:30 [wandb_init.py:_pause_backend():444] pausing backend
2024-11-27 17:50:52,249 INFO    MainThread:30 [wandb_init.py:_resume_backend():449] resuming backend
2024-11-27 17:50:52,251 INFO    MainThread:30 [jupyter.py:save_ipynb():387] not saving jupyter notebook
2024-11-27 17:50:52,251 INFO    MainThread:30 [wandb_init.py:_pause_backend():444] pausing backend
2024-11-27 17:50:53,219 INFO    MainThread:30 [wandb_init.py:_resume_backend():449] resuming backend
2024-11-27 17:50:53,349 INFO    MainThread:30 [jupyter.py:save_ipynb():387] not saving jupyter notebook
2024-11-27 17:50:53,349 INFO    MainThread:30 [wandb_init.py:_pause_backend():444] pausing backend
2024-11-27 17:51:08,548 INFO    MainThread:30 [wandb_init.py:_resume_backend():449] resuming backend
2024-11-27 17:51:08,695 INFO    MainThread:30 [jupyter.py:save_ipynb():387] not saving jupyter notebook
2024-11-27 17:51:08,695 INFO    MainThread:30 [wandb_init.py:_pause_backend():444] pausing backend
2024-11-27 17:51:11,128 INFO    MainThread:30 [wandb_init.py:_resume_backend():449] resuming backend
2024-11-27 17:51:11,778 INFO    MainThread:30 [wandb_run.py:_config_callback():1387] config_cb None None {'use_timm_backbone': True, 'backbone_config': None, 'num_channels': 3, 'num_queries': 100, 'd_model': 256, 'encoder_ffn_dim': 2048, 'encoder_layers': 6, 'encoder_attention_heads': 8, 'decoder_ffn_dim': 2048, 'decoder_layers': 6, 'decoder_attention_heads': 8, 'dropout': 0.1, 'attention_dropout': 0.0, 'activation_dropout': 0.0, 'activation_function': 'relu', 'init_std': 0.02, 'init_xavier_std': 1.0, 'encoder_layerdrop': 0.0, 'decoder_layerdrop': 0.0, 'num_hidden_layers': 6, 'auxiliary_loss': False, 'position_embedding_type': 'sine', 'backbone': 'resnet50', 'use_pretrained_backbone': True, 'backbone_kwargs': {'output_stride': 16, 'out_indices': [1, 2, 3, 4], 'in_chans': 3}, 'dilation': True, 'class_cost': 1, 'bbox_cost': 5, 'giou_cost': 2, 'mask_loss_coefficient': 1, 'dice_loss_coefficient': 1, 'bbox_loss_coefficient': 5, 'giou_loss_coefficient': 2, 'eos_coefficient': 0.1, 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'float32', 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': True, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['DetrForObjectDetection'], 'finetuning_task': None, 'id2label': {0: 'object', 1: 'balloon'}, 'label2id': {'object': 0, 'balloon': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': None, 'pad_token_id': None, 'eos_token_id': None, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'facebook/detr-resnet-50-dc5', '_attn_implementation_autoset': False, 'transformers_version': '4.46.3', 'classifier_dropout': 0.0, 'max_position_embeddings': 1024, 'model_type': 'detr', 'scale_embedding': False, 'output_dir': '.', 'overwrite_output_dir': False, 'do_train': False, 'do_eval': True, 'do_predict': False, 'eval_strategy': 'steps', 'prediction_loss_only': False, 'per_device_train_batch_size': 4, 'per_device_eval_batch_size': 4, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 1, 'eval_accumulation_steps': None, 'eval_delay': 0, 'torch_empty_cache_steps': None, 'learning_rate': 3e-05, 'weight_decay': 0.0001, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 3.0, 'max_steps': 500, '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/Nov27_17-51-08_f5b68522d064', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 5, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 10, 'save_total_limit': 2, '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': True, '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': 10, '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': None, '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, 'include_for_metrics': [], 'eval_do_concat_batches': True, 'fp16_backend': 'auto', 'evaluation_strategy': 'steps', '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': True, 'eval_on_start': False, 'use_liger_kernel': False, 'eval_use_gather_object': False, 'average_tokens_across_devices': False}
2024-11-27 17:51:11,783 INFO    MainThread:30 [wandb_config.py:__setitem__():154] config set model/num_parameters = 41501895 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x7a7699a6ddb0>>
2024-11-27 17:51:11,783 INFO    MainThread:30 [wandb_run.py:_config_callback():1387] config_cb model/num_parameters 41501895 None