{"elapsed_seconds":6.0382147810887545,"error":"1 validation error for SegmentationTrainConfig\n  Value error, Unknown parameter(s): 'lr_drop'. Available parameter(s): accelerator, amp_dtype, aug_config, augmentation_backend, auto_batch_ema_headroom, auto_batch_max_targets_per_image, auto_batch_target_effective, batch_size, best_model_metric, checkpoint_interval, class_names, clearml, clip_max_norm, cls_loss_coef, compact_train_metrics, compute_test_loss, compute_train_metrics, compute_val_loss, dataset_dir, dataset_file, devices, dont_save_weights, drop_path, early_stopping, early_stopping_min_delta, early_stopping_patience, early_stopping_use_ema, ema_decay, ema_tau, ema_update_interval, epochs, eval_backend, eval_base_model, eval_batch_size, eval_ema_only, eval_interval, eval_masks_head_resolution, eval_max_dets, expanded_scales, fp16_eval, grad_accum_steps, keypoint_findable_loss_coef, keypoint_flip_pairs, keypoint_l1_loss_coef, keypoint_nll_loss_coef, keypoint_oks_sigmas, keypoint_visible_loss_coef, log_per_class_metrics, lr, lr_component_decay, lr_encoder, lr_scheduler, lr_scheduler_interval, lr_scheduler_kwargs, lr_scheduler_monitor, lr_vit_layer_decay, mask_ce_loss_coef, mask_dice_loss_coef, mask_point_sample_ratio, mlflow, multi_scale, notes, num_nodes, num_sanity_val_steps, num_workers, optimizer, optimizer_kwargs, output_dir, pack_targets, pad_targets_to, persistent_workers, pin_memory, prefetch_factor, progress_bar, project, resume, run, run_test, save_dataset_grids, scale_jitter, seed, skip_best_epochs, smooth_alpha, square_resize_div_64, strategy, sync_bn, tensorboard, train_log_on_step, train_log_sync_dist, use_ema, wandb, warmup_epochs, weight_decay. [type=value_error, input_value={'dataset_dir': '/root/pr... False, 'lr_drop': 1000}, input_type=dict]\n    For further information visit https://errors.pydantic.dev/2.11/v/value_error","error_type":"ValidationError","state":"failed_not_complete_evidence_retained","traceback":"Traceback (most recent call last):\n  File \"/root/private/project/pallet_detection_v2/pallet/mask_model_improvement.py\", line 469, in worker\n    result = (train_m1 if route == 'm1' else train_m2)(output, out, records, config, path)\n             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n  File \"/root/private/project/pallet_detection_v2/pallet/mask_model_improvement.py\", line 368, in train_m2\n    tc = model.get_train_config(dataset_dir=str(output/'dataset_rfdetr'), output_dir=str(out/'upstream'),\n         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n  File \"/root/private/project/pallet_detection_v2/.venv/lib/python3.11/site-packages/rfdetr/detr.py\", line 2436, in get_train_config\n    return self._train_config_class(**kwargs)\n           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n  File \"/root/public/unsloth/lib/python3.11/site-packages/pydantic/main.py\", line 253, in __init__\n    validated_self = self.__pydantic_validator__.validate_python(data, self_instance=self)\n                     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\npydantic_core._pydantic_core.ValidationError: 1 validation error for SegmentationTrainConfig\n  Value error, Unknown parameter(s): 'lr_drop'. Available parameter(s): accelerator, amp_dtype, aug_config, augmentation_backend, auto_batch_ema_headroom, auto_batch_max_targets_per_image, auto_batch_target_effective, batch_size, best_model_metric, checkpoint_interval, class_names, clearml, clip_max_norm, cls_loss_coef, compact_train_metrics, compute_test_loss, compute_train_metrics, compute_val_loss, dataset_dir, dataset_file, devices, dont_save_weights, drop_path, early_stopping, early_stopping_min_delta, early_stopping_patience, early_stopping_use_ema, ema_decay, ema_tau, ema_update_interval, epochs, eval_backend, eval_base_model, eval_batch_size, eval_ema_only, eval_interval, eval_masks_head_resolution, eval_max_dets, expanded_scales, fp16_eval, grad_accum_steps, keypoint_findable_loss_coef, keypoint_flip_pairs, keypoint_l1_loss_coef, keypoint_nll_loss_coef, keypoint_oks_sigmas, keypoint_visible_loss_coef, log_per_class_metrics, lr, lr_component_decay, lr_encoder, lr_scheduler, lr_scheduler_interval, lr_scheduler_kwargs, lr_scheduler_monitor, lr_vit_layer_decay, mask_ce_loss_coef, mask_dice_loss_coef, mask_point_sample_ratio, mlflow, multi_scale, notes, num_nodes, num_sanity_val_steps, num_workers, optimizer, optimizer_kwargs, output_dir, pack_targets, pad_targets_to, persistent_workers, pin_memory, prefetch_factor, progress_bar, project, resume, run, run_test, save_dataset_grids, scale_jitter, seed, skip_best_epochs, smooth_alpha, square_resize_div_64, strategy, sync_bn, tensorboard, train_log_on_step, train_log_sync_dist, use_ema, wandb, warmup_epochs, weight_decay. [type=value_error, input_value={'dataset_dir': '/root/pr... False, 'lr_drop': 1000}, input_type=dict]\n    For further information visit https://errors.pydantic.dev/2.11/v/value_error\n"}
