Training in progress, step 10

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9e1627baa87deefbcc2357b681afc9c529f8e34b6453fba8e7ddc9fd37571fa
+oid sha256:7f022c37b21ff5d85559c99115d1d12d9de540c62a2ad17541e9aa90ff746409
 size 166495852

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c43b1ae8e9b87ddd678b0bff9b93457f826ffa7c1cb1ba655c90a4fc6d7ea693
+oid sha256:615278b0a0659a8f97b021c31d0f9bfc0b4074599f26ea164a69ddf1832146b6
 size 5240

wandb/debug.log

@@ -45,3 +45,6 @@ config: {'batch_size': 4, 'learning_rate': 0.0003, 'num_epochs': 100}
 2024-11-27 17:16:53,471 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': {'in_chans': 3, 'out_indices': [1, 2, 3, 4], 'output_stride': 16}, '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': {'balloon': 1, 'object': 0}, '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': 'MalyO2/detr_finetune_lr_scheduler_v4', '_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': 0, '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': 300, '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_17-16-19_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 17:16:53,476 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 0x7a77fc8d4160>>
 2024-11-27 17:16:53,476 INFO    MainThread:30 [wandb_run.py:_config_callback():1387] config_cb model/num_parameters 41501895 None
+2024-11-27 17:17:55,656 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': {'in_chans': 3, 'out_indices': [1, 2, 3, 4], 'output_stride': 16}, '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': {'balloon': 1, 'object': 0}, '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': 'MalyO2/detr_finetune_lr_scheduler_v4', '_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': 1e-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': 300, '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_17-17-52_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 17:17:55,660 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 0x7a77fc8d4160>>
+2024-11-27 17:17:55,660 INFO    MainThread:30 [wandb_run.py:_config_callback():1387] config_cb model/num_parameters 41501895 None

wandb/run-20241127_153658-ukl4t7mf/files/output.log

@@ -7386,3 +7386,11 @@ max_steps is given, it will override any value given in num_train_epochs
 /opt/conda/lib/python3.10/site-packages/accelerate/accelerator.py:494: FutureWarning: `torch.cuda.amp.GradScaler(args...)` is deprecated. Please use `torch.amp.GradScaler('cuda', args...)` instead.
   self.scaler = torch.cuda.amp.GradScaler(**kwargs)
 max_steps is given, it will override any value given in num_train_epochs
+No files have been modified since last commit. Skipping to prevent empty commit.
+/opt/conda/lib/python3.10/site-packages/transformers/training_args.py:1568: FutureWarning: `evaluation_strategy` is deprecated and will be removed in version 4.46 of 🤗 Transformers. Use `eval_strategy` instead
+  warnings.warn(
+/tmp/ipykernel_30/3311869782.py:28: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `Trainer.__init__`. Use `processing_class` instead.
+  trainer = Trainer(
+/opt/conda/lib/python3.10/site-packages/accelerate/accelerator.py:494: FutureWarning: `torch.cuda.amp.GradScaler(args...)` is deprecated. Please use `torch.amp.GradScaler('cuda', args...)` instead.
+  self.scaler = torch.cuda.amp.GradScaler(**kwargs)
+max_steps is given, it will override any value given in num_train_epochs

wandb/run-20241127_153658-ukl4t7mf/logs/debug.log

@@ -45,3 +45,6 @@ config: {'batch_size': 4, 'learning_rate': 0.0003, 'num_epochs': 100}
 2024-11-27 17:16:53,471 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': {'in_chans': 3, 'out_indices': [1, 2, 3, 4], 'output_stride': 16}, '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': {'balloon': 1, 'object': 0}, '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': 'MalyO2/detr_finetune_lr_scheduler_v4', '_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': 0, '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': 300, '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_17-16-19_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 17:16:53,476 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 0x7a77fc8d4160>>
 2024-11-27 17:16:53,476 INFO    MainThread:30 [wandb_run.py:_config_callback():1387] config_cb model/num_parameters 41501895 None
+2024-11-27 17:17:55,656 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': {'in_chans': 3, 'out_indices': [1, 2, 3, 4], 'output_stride': 16}, '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': {'balloon': 1, 'object': 0}, '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': 'MalyO2/detr_finetune_lr_scheduler_v4', '_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': 1e-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': 300, '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_17-17-52_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 17:17:55,660 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 0x7a77fc8d4160>>
+2024-11-27 17:17:55,660 INFO    MainThread:30 [wandb_run.py:_config_callback():1387] config_cb model/num_parameters 41501895 None

wandb/run-20241127_153658-ukl4t7mf/run-ukl4t7mf.wandb

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0404d05d0788da8be261373aede1c53d3bb9f5ddac913763f4d1612f7e0f762f
-size 1114112
+oid sha256:0a89840a12df5691fc83a76aa38f0b0d45c2306d431353b06963c716710e4b0f
+size 1146880