{ "output_dir": "/home/ppq5umrb/whcs-share46/ms-swift-main/output_qwen3-sft_add_tokens_multi_center_simpo_1-24/v54-20260127-154928", "overwrite_output_dir": false, "do_train": false, "do_eval": false, "do_predict": false, "eval_strategy": "steps", "prediction_loss_only": false, "per_device_train_batch_size": 1, "per_device_eval_batch_size": 1, "per_gpu_train_batch_size": null, "per_gpu_eval_batch_size": null, "gradient_accumulation_steps": 4, "eval_accumulation_steps": null, "eval_delay": 0, "torch_empty_cache_steps": null, "learning_rate": 0.0005, "weight_decay": 0.1, "adam_beta1": 0.9, "adam_beta2": 0.95, "adam_epsilon": 1e-08, "max_grad_norm": 1.0, "num_train_epochs": 10.0, "max_steps": -1, "lr_scheduler_type": "cosine", "lr_scheduler_kwargs": null, "warmup_ratio": 0.05, "warmup_steps": 0, "log_level": "passive", "log_level_replica": "warning", "log_on_each_node": true, "logging_dir": "/home/ppq5umrb/whcs-share46/ms-swift-main/output_qwen3-sft_add_tokens_multi_center_simpo_1-24/v54-20260127-154928/runs", "logging_strategy": "steps", "logging_first_step": true, "logging_steps": 10, "logging_nan_inf_filter": true, "save_strategy": "steps", "save_steps": 50.0, "save_total_limit": null, "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": 42, "jit_mode_eval": false, "bf16": true, "fp16": false, "fp16_opt_level": "O1", "half_precision_backend": "auto", "bf16_full_eval": false, "fp16_full_eval": false, "tf32": null, "local_rank": 0, "ddp_backend": null, "tpu_num_cores": null, "tpu_metrics_debug": false, "debug": null, "dataloader_drop_last": false, "eval_steps": 50.0, "dataloader_num_workers": 0, "dataloader_prefetch_factor": null, "past_index": -1, "run_name": "/home/ppq5umrb/whcs-share46/ms-swift-main/output_qwen3-sft_add_tokens_multi_center_simpo_1-24/v54-20260127-154928", "disable_tqdm": null, "remove_unused_columns": true, "label_names": null, "load_best_model_at_end": false, "metric_for_best_model": "loss", "greater_is_better": false, "ignore_data_skip": false, "fsdp": null, "fsdp_min_num_params": 0, "fsdp_config": null, "fsdp_transformer_layer_cls_to_wrap": null, "accelerator_config": { "dispatch_batches": false }, "parallelism_config": null, "deepspeed": { "fp16": { "enabled": "auto", "loss_scale": 0, "loss_scale_window": 1000, "initial_scale_power": 16, "hysteresis": 2, "min_loss_scale": 1 }, "bf16": { "enabled": "auto" }, "zero_optimization": { "stage": 2, "offload_optimizer": { "device": "none", "pin_memory": true }, "allgather_partitions": true, "allgather_bucket_size": 200000000.0, "overlap_comm": false, "reduce_scatter": true, "reduce_bucket_size": 200000000.0, "contiguous_gradients": true }, "gradient_accumulation_steps": "auto", "gradient_clipping": "auto", "steps_per_print": 2000, "train_batch_size": "auto", "train_micro_batch_size_per_gpu": "auto", "wall_clock_breakdown": false }, "label_smoothing_factor": 0.0, "optim": "adamw_torch", "optim_args": null, "adafactor": false, "group_by_length": false, "length_column_name": "length", "report_to": [ "swanlab" ], "project": "huggingface", "trackio_space_id": "trackio", "ddp_find_unused_parameters": null, "ddp_bucket_cap_mb": null, "ddp_broadcast_buffers": null, "dataloader_pin_memory": true, "dataloader_persistent_workers": false, "skip_memory_metrics": true, "use_legacy_prediction_loop": false, "push_to_hub": false, "resume_from_checkpoint": null, "hub_model_id": null, "hub_strategy": "every_save", "hub_token": null, "hub_private_repo": null, "hub_always_push": false, "hub_revision": null, "gradient_checkpointing": true, "gradient_checkpointing_kwargs": null, "include_inputs_for_metrics": false, "include_for_metrics": [], "eval_do_concat_batches": true, "fp16_backend": "auto", "push_to_hub_model_id": null, "push_to_hub_organization": null, "push_to_hub_token": null, "mp_parameters": "", "auto_find_batch_size": false, "full_determinism": false, "torchdynamo": null, "ray_scope": "last", "ddp_timeout": 18000000, "torch_compile": false, "torch_compile_backend": null, "torch_compile_mode": null, "include_tokens_per_second": false, "include_num_input_tokens_seen": false, "neftune_noise_alpha": null, "optim_target_modules": null, "batch_eval_metrics": false, "eval_on_start": false, "use_liger_kernel": false, "liger_kernel_config": null, "eval_use_gather_object": false, "average_tokens_across_devices": true, "sortish_sampler": false, "predict_with_generate": false, "generation_max_length": null, "generation_num_beams": null, "generation_config": null, "tuner_backend": "peft", "vit_gradient_checkpointing": null, "router_aux_loss_coef": 0.0, "enable_dft_loss": false, "enable_channel_loss": false, "check_model": true, "acc_strategy": "token", "train_dataloader_shuffle": true, "max_epochs": null, "aligner_lr": null, "vit_lr": null, "use_logits_to_keep": null, "ds3_gather_for_generation": true, "resume_only_model": false, "optimizer": null, "loss_type": "simpo", "metric": null, "eval_use_evalscope": false, "eval_dataset": [], "eval_dataset_args": null, "eval_limit": null, "eval_generation_config": null, "extra_eval_args": null, "use_flash_ckpt": false, "use_ray": false, "ray_exp_name": null, "device_groups": null, "model": "output_sft_add_tokens_multi-center-1-21-final/v7-20260122-001024/checkpoint-2000-merged/", "model_type": "qwen3_vl", "model_revision": null, "task_type": "causal_lm", "torch_dtype": "bfloat16", "attn_impl": "flash_attn", "new_special_tokens": [ "<|No_significant_abnormality_detected_on_imaging|>", "<|Blake_s_pouch_cyst|>", "<|Dandy_Walker_malformation|>", "<|Vein_of_Galen_aneurysmal_malformation|>", "<|Joubert_syndrome|>", "<|Increased_nuchal_translucency_NT_|>", "<|Apical_displacement_of_the_tricuspid_valve_Ebstein_anomaly_|>", "<|Tricuspid_regurgitation|>", "<|Tricuspid_valve_dysplasia|>", "<|Tricuspid_valve_thickening|>", "<|Tricuspid_valve_lesion|>", "<|Tricuspid_valve_disease_with_right_ventricular_cardiomyopathy|>", "<|Tricuspid_atresia|>", "<|Interruption_of_the_inferior_vena_cava|>", "<|Absence_of_the_inferior_vena_cava|>", "<|Mandibular_abnormality|>", "<|Incomplete_secondary_cleft_palate|>", "<|Mesocardia|>", "<|Aqueductal_stenosis_cerebral_aqueduct_obstruction_|>", "<|Cavum_veli_interpositi|>", "<|Aortopulmonary_septal_defect|>", "<|Aortic_hypoplasia|>", "<|Narrowed_internal_diameter_of_the_aortic_isthmus|>", "<|Slightly_widened_internal_diameter_of_the_aortic_isthmus|>", "<|Aortic_abnormality|>", "<|High-positioned_aortic_arch|>", "<|Hypoplastic_aortic_arch|>", "<|Dilatation_of_the_aortic_arch|>", "<|Tortuous_aortic_arch|>", "<|Interrupted_aortic_arch|>", "<|Coarctation_of_the_aortic_arch|>", "<|Slightly_small_descending_aortic_arch|>", "<|Aortic_regurgitation|>", "<|Mildly_increased_echogenicity_of_the_aortic_valve|>", "<|Aortic_valve_stenosis|>", "<|Aortic_valve_atresia|>", "<|Interruption_of_the_aorta|>", "<|Aortic_atresia|>", "<|Overriding_aorta|>", "<|Abnormal_main_pulmonary_artery_aorta_diameter_ratio|>", "<|Mitral_regurgitation|>", "<|Increased_echogenicity_of_the_mitral_valve|>", "<|Mitral_stenosis|>", "<|Mitral_valve_thickening|>", "<|Mitral_atresia|>", "<|Overlapping_fingers|>", "<|Communicating_hydrocephalus|>", "<|Body_stalk_anomaly|>", "<|Partial_fusion_of_the_frontal_horns_of_the_lateral_ventricles|>", "<|Mild_lateral_ventriculomegaly|>", "<|Severe_lateral_ventriculomegaly|>", "<|Congenital_diaphragmatic_hernia|>", "<|Alobar_holoprosencephaly|>", "<|Situs_inversus|>", "<|Evisceration_exomphalos_ectopia_complex_|>", "<|Coronary_artery_anomaly|>", "<|Coronary_arteriovenous_fistula|>", "<|Dilated_coronary_sinus|>", "<|Anterior_abdominal_wall_defect|>", "<|Frontal_bossing|>", "<|Accessory_auricle_preauricular_tag_|>", "<|Accessory_renal_artery|>", "<|Ductus_arteriosus_hypoplasia|>", "<|Focal_narrowing_of_the_ductus_arteriosus|>", "<|Premature_constriction_of_the_ductus_arteriosus|>", "<|Patent_ductus_arteriosus|>", "<|Increased_flow_velocity_in_the_ductus_arteriosus|>", "<|Absence_of_the_ductus_arteriosus|>", "<|Tortuous_ductus_arteriosus|>", "<|Reduced_angle_between_aortic_arch_segments|>", "<|Duodenal_atresia_stenosis|>", "<|Criss-cross_heart|>", "<|Dilatation_of_the_ascending_aorta|>", "<|Aneurysmal_dilatation_of_the_ascending_aorta|>", "<|Coarctation_of_the_ascending_aorta|>", "<|Semilunar_valve_stenosis|>", "<|Hemivertebra|>", "<|Single_arterial_trunk|>", "<|Single_ventricle|>", "<|Single_atrium|>", "<|Single_umbilical_artery|>", "<|Single_nostril|>", "<|Excessively_patent_foramen_ovale|>", "<|Premature_closure_of_the_foramen_ovale|>", "<|Redundant_foramen_ovale_flap|>", "<|Multiple_echogenic_foci_on_the_foramen_ovale_flap_visible_in_both_ventricles|>", "<|Double_inferior_vena_cava|>", "<|Double_aorta|>", "<|Double_aortic_arch|>", "<|Bilateral_superior_venae_cavae|>", "<|Pulmonary_hypoplasia_bilateral_|>", "<|Duplicated_renal_pelvis|>", "<|Small_biparietal_diameter_and_head_circumference|>", "<|Right_aortic_arch|>", "<|Dextrocardia|>", "<|Right_ventricular_hypoplasia|>", "<|Right_ventricular_hypertrophy|>", "<|Hypoplastic_right_heart|>", "<|Cardiomegaly_of_the_right_heart|>", "<|Double-outlet_right_ventricle|>", "<|Enlarged_right_ventricle|>", "<|Echogenic_intracardiac_focus_in_the_right_ventricle|>", "<|Increased_echogenicity_of_the_right_ventricle|>", "<|Chiari_network_in_the_right_atrium|>", "<|Right_atrial_enlargement|>", "<|Right_atrial_isomerism|>", "<|Markedly_small_right_lung|>", "<|Aberrant_right_subclavian_artery|>", "<|Enlarged_cisterna_magna|>", "<|Absent_posterior_fossa|>", "<|Posterior_fossa_lesion|>", "<|Cleft_lip_and_palate|>", "<|Proboscis|>", "<|Coronary_sinus_on_four-chamber_view|>", "<|Markedly_abnormal_four-chamber_cardiac_morphology|>", "<|Polycystic_kidneys|>", "<|Polydactyly|>", "<|Polydactyly_toes_|>", "<|Transposition_of_the_great_arteries|>", "<|Azygos_vein_dilatation|>", "<|Complete_atrioventricular_septal_defect|>", "<|Total_anomalous_pulmonary_venous_return|>", "<|Ventricular_wall_thickening|>", "<|Subependymal_cyst|>", "<|Linear_calcifications_visible_in_the_interventricular_septum|>", "<|Ventricular_septal_defect|>", "<|Continuity_interruption_near_the_membranous_septum_of_the_IVS|>", "<|Micrognathia|>", "<|Microphthalmia|>", "<|Small_submucous_cleft_palate|>", "<|Cerebellar_hypoplasia|>", "<|Enlarged_cerebellomedullary_cistern|>", "<|Absent_cerebellomedullary_cistern|>", "<|Cerebellar_atrophy|>", "<|Anechoic_area_posterior_to_the_cerebellar_vermis|>", "<|Hypoplasia_of_the_radius_ulna_and_hand|>", "<|Caudal_regression|>", "<|Hypospadias|>", "<|Focal_mild_calyceal_dilatation|>", "<|Left-sided_inferior_vena_cava|>", "<|Left-sided_ductus_arteriosus|>", "<|Punctate_echogenic_foci_in_both_ventricles|>", "<|Atrial_ventricular_size_asymmetry|>", "<|Left_ventricular_hypertrophy|>", "<|Echogenic_foci_at_the_level_of_chordae_and_papillary_muscles_in_the_left_ventricle|>", "<|Hypoplastic_left_heart|>", "<|Double-inlet_left_ventricle|>", "<|Small_left_ventricle_LV_hypoplasia_|>", "<|Echogenic_intracardiac_focus_in_the_left_ventricle|>", "<|Small_left_atrium|>", "<|Small_left_atrium_and_ventricle|>", "<|Left_atrial_isomerism|>", "<|Left_microtia_auricular_hypoplasia_|>", "<|Absence_of_the_left_pulmonary_artery|>", "<|Markedly_increased_left_lung_area|>", "<|Aberrant_left_subclavian_artery|>", "<|Open_spina_bifida|>", "<|Ectopic_kidney|>", "<|Heterotaxy_syndrome|>", "<|Decreased_cardiac_function|>", "<|Pericardial_effusion|>", "<|Echogenic_intracardiac_focus_ventricle_|>", "<|Irregular_heart_rhythm|>", "<|Atrial_situs_inversus|>", "<|Arrhythmia|>", "<|Myocardial_dysplasia|>", "<|Cardiomyopathy|>", "<|Myocardial_hypertrophy|>", "<|Small_cardiothoracic_ratio|>", "<|Increased_cardiothoracic_ratio|>", "<|Abnormal_cardiac_position|>", "<|Cardiac_space-occupying_lesion|>", "<|Cardiomegaly|>", "<|Cardiac_rhabdomyoma|>", "<|Prominent_moderator_band|>", "<|Increased_cardiac_axis|>", "<|Decreased_cardiac_axis|>", "<|Left-deviated_cardiac_axis|>", "<|Discordant_atrioventricular_connection|>", "<|Atrioventricular_septal_defect|>", "<|Atrial_septal_defect|>", "<|Atrial_septal_aneurysm|>", "<|Persistent_right_umbilical_vein|>", "<|Abnormal_finger_morphology|>", "<|Rocker-bottom_feet|>", "<|No_valve_closure_or_opening_observed_in_systole_or_diastole|>", "<|Agnathia_with_ear_anomalies|>", "<|Low-positioned_innominate_vein|>", "<|Aberrant_course_of_the_innominate_vein|>", "<|Anophthalmia|>", "<|Anencephaly|>", "<|Arrhinia_absence_of_the_nose_|>", "<|Occipital_encephalocele|>", "<|Lemon_sign|>", "<|Radial_aplasia|>", "<|Prune-belly_syndrome|>", "<|Coronal_cleft_vertebra|>", "<|Persistent_truncus_arteriosus|>", "<|Truncal_valve_stenosis|>", "<|Persistent_left_superior_vena_cava|>", "<|Tetralogy_of_Fallot|>", "<|Lymphatic_cyst|>", "<|Lymphangioma_cystic_|>", "<|Alveolar_cleft|>", "<|Narrow_thorax|>", "<|Genital_malformation|>", "<|Teratoma|>", "<|Congenital_cataract|>", "<|Hypertelorism|>", "<|Hypotelorism|>", "<|Ocular_malformation|>", "<|Jejunal_dilatation|>", "<|Submucous_cleft_palate|>", "<|Mediastinal_cyst|>", "<|Secondary_cleft_palate|>", "<|Amniotic_band_syndrome|>", "<|Hepatic_cyst|>", "<|Extrahepatic_portosystemic_shunt|>", "<|Dilated_bowel_loops|>", "<|Mesenteric_cyst|>", "<|Enteric_duplication|>", "<|Main_pulmonary_artery_dilatation|>", "<|Crossed_pulmonary_arteries|>", "<|Slightly_widened_pulmonary_artery_internal_diameter|>", "<|Pulmonary_artery_hypoplasia|>", "<|Pulmonary_artery_sling|>", "<|Pulmonary_trunk_stenosis|>", "<|Pulmonary_artery_dilatation|>", "<|Pulmonary_artery_stenosis|>", "<|Pulmonary_regurgitation|>", "<|Increased_flow_velocity_across_the_pulmonary_valve|>", "<|Pulmonary_valve_thickening|>", "<|Thickened_pulmonary_valve_with_increased_echogenicity|>", "<|Pulmonary_valve_stenosis|>", "<|Absent_pulmonary_valve|>", "<|Retrograde_perfusion_in_the_pulmonary_artery|>", "<|Pulmonary_atresia|>", "<|Congenital_pulmonary_airway_malformation_CPAM_|>", "<|CPAM_type_I|>", "<|CPAM_type_II|>", "<|CPAM_type_III|>", "<|Pulmonary_mass_lesion|>", "<|Anomalous_pulmonary_venous_drainage|>", "<|Renal_dysplasia|>", "<|Renal_cyst|>", "<|Pyelectasis|>", "<|Mild_pelvicalyceal_separation|>", "<|Hydronephrosis|>", "<|Renal_agenesis|>", "<|Enlarged_kidney|>", "<|Enlarged_stomach_bubble|>", "<|Small_stomach_bubble|>", "<|Reversed_position_of_the_stomach_bubble|>", "<|Abnormal_stomach_bubble_morphology|>", "<|Gastrointestinal_malformation|>", "<|Abnormal_gallbladder_position|>", "<|Cystic_dilatation_of_the_common_bile_duct_choledochal_cyst_|>", "<|Choledochal_cyst|>", "<|Embryonic_demise|>", "<|Thoracic_hypoplasia|>", "<|Thoracic_cavity_hypoplasia|>", "<|Fetal_pleural_effusion|>", "<|Thymic_abnormality|>", "<|Corpus_callosum_dysgenesis|>", "<|Choroid_plexus_cyst|>", "<|Scoliosis|>", "<|Spina_bifida|>", "<|Conus_medullaris_at_L4_level|>", "<|Umbilical_artery_occlusion|>", "<|Cord_presentation|>", "<|Wharton_s_jelly_edema_of_the_umbilical_cord|>", "<|Umbilical_cord_cyst|>", "<|Umbilical_hernia|>", "<|Omphalocele|>", "<|Abnormal_branching_of_umbilical_vessels|>", "<|Focal_umbilical_vein_dilatation_varix_|>", "<|Umbilical_vein_varix|>", "<|Ventriculomegaly|>", "<|Abnormal_ventricular_system|>", "<|Pontine_hypoplasia|>", "<|Hydrocephalus|>", "<|Schizencephaly|>", "<|Abdominal_wall_defect|>", "<|Fetal_ascites|>", "<|Megacystis|>", "<|Diaphragmatic_hernia|>", "<|Thickened_membranous_pulmonary_valve|>", "<|Genu_recurvatum|>", "<|Lethal_skeletal_dysplasia|>", "<|Lingual_hemangioma|>", "<|Strawberry-shaped_skull|>", "<|Vermian_hypoplasia|>", "<|Subarachnoid_hemorrhage|>", "<|Arachnoid_cyst|>", "<|Butterfly_vertebra|>", "<|Fused_kidneys|>", "<|Hemangioma|>", "<|Septo-optic_dysplasia|>", "<|Thickened_moderator_band|>", "<|Clubfoot_talipes_equinovarus_|>", "<|Toe_deformity|>", "<|Ureterocele|>", "<|Hydroureter|>", "<|Narrowed_cavum_septi_pellucidi|>", "<|Abnormal_cavum_septi_pellucidi|>", "<|Absence_of_the_cavum_septi_pellucidi|>", "<|Duplicated_kidney|>", "<|Closed_spina_bifida|>", "<|Marked_displacement_of_the_septal_leaflet_AV_valve_|>", "<|Pulmonary_sequestration|>", "<|Exencephaly|>", "<|Absent_ductus_venosus|>", "<|Transverse_facial_cleft|>", "<|Poor_ossification_of_skull_and_vertebrae|>", "<|Incomplete_ossification_of_the_skull|>", "<|Cystic_hygroma|>", "<|Banana_sign|>", "<|Horseshoe_kidney|>", "<|Skeletal_dysplasia|>", "<|Hypoplastic_ossification_of_the_sacral_neural_arch|>", "<|Nasolacrimal_duct_cyst|>", "<|Nasal_deformity|>", "<|Absent_hypoplastic_nasal_bone|>", "<|No_ventriculomegaly|>", "<|Apical_displacement_of_the_mitral_valve|>", "<|Immature_mitral_valve|>", "<|Clubhand_clubfoot|>", "<|Persistent_umbilical_vein|>", "<|Normal_position|>", "<|Normal_spinal_alignment|>", "<|Abnormal_pulmonary_artery_bifurcation|>", "<|Fetal_cardiomegaly|>", "<|Pedal_edema|>", "<|Coronal_cleft_of_toe|>", "<|Aberrant_subclavian_artery|>", "<|3D_color_Doppler_ultrasound|>", "<|Three-vessel_view|>", "<|Four-chamber_view|>", "<|Four-chamber_view_transverse_|>", "<|Echogenic_focus_in_ventricle_on_four-chamber_view|>", "<|Aortic_arch_view|>", "<|Upper_alveolar_ridge_view|>", "<|Abdominal_circumference_plane_axial_|>", "<|Abdominal_wall_via_bladder_axial_view|>", "<|Biparietal_diameter_plane|>", "<|Mid-sagittal_plane_C|>", "<|Four-chamber_view_cardiothoracic_ratio|>", "<|Cerebellar_plane|>", "<|Thoracic_axial_plane|>", "<|Thoracic_coronal_plane|>", "<|Ductus_arteriosus_view|>", "<|Interorbital_distance_plane|>", "<|Femur_long-axis_view|>", "<|Foot_coronal_view|>", "<|Radius_ulna_view|>", "<|Fourth_ventricle|>", "<|Gallbladder_view|>", "<|Humerus_long-axis_view|>", "<|Hard_palate_view|>", "<|Bilateral_kidneys_axial_view|>", "<|Bilateral_kidneys_coronal_view|>", "<|Left_ventricular_outflow_tract_LVOT_view|>", "<|Tibia_fibula_long-axis_view|>", "<|Lip_coronal_view|>", "<|Mid-sagittal_plane_N|>", "<|Pulmonary_artery_bifurcation|>", "<|Mandible_view|>", "<|Finger_coronal_view|>", "<|Right_ventricular_outflow_tract_RVOT_view|>", "<|Facial_mid-sagittal_view|>", "<|Caval_SVC_IVC_view|>", "<|Spine_longitudinal_view|>", "<|Single_kidney_sagittal_view|>", "<|Third_ventricle|>", "<|Lateral_ventricle_plane|>", "<|First-trimester_three-vessel_flow_view|>", "<|First-trimester_four-chamber_flow_view|>", "<|First-trimester_abdominal_axial_plane|>", "<|First-trimester_transventricular_axial_plane|>", "<|First-trimester_fetal_midsagittal_plane|>", "<|First-trimester_NT_measurement_plane|>", "<|First-trimester_umbilical_cord_insertion_axial_plane|>", "<|First-trimester_bilateral_upper-limb_plane|>", "<|First-trimester_bilateral_lower-limb_plane|>", "", "", "", "", "", "", "", "", "" ], "num_labels": null, "problem_type": null, "rope_scaling": null, "device_map": null, "max_memory": {}, "max_model_len": null, "local_repo_path": null, "init_strategy": null, "template": "qwen3_vl", "system": null, "max_length": 197534, "truncation_strategy": "delete", "max_pixels": null, "agent_template": null, "norm_bbox": null, "use_chat_template": true, "padding_free": false, "padding_side": "right", "loss_scale": "last_round", "sequence_parallel_size": 1, "response_prefix": null, "template_backend": "swift", "dataset": [ "na_all-json-out_real_z_select_1k_1k/y_dpo_z_report_real_dpo.jsonl", "na_all-json-out_real_z_select_1k_1k/y_dpo_z_real_dpo.jsonl", "na_all-json-out_real_z_select_1k_1k/y_to_y_swap_strict_same_center_zh.jsonl", "na_all-json-out_real_z_select_1k_1k/y_add_y_swap_same_center_real_dpo_zh.jsonl" ], "val_dataset": [ "na_all-json-out_real_z_select_1k_1k/y_dpo_z_eval_real_dpo.jsonl" ], "cached_dataset": [], "cached_val_dataset": [], "split_dataset_ratio": 0.0, "dataset_num_proc": 1, "load_from_cache_file": false, "dataset_shuffle": true, "val_dataset_shuffle": false, "streaming": false, "interleave_prob": null, "stopping_strategy": "first_exhausted", "shuffle_buffer_size": 1000, "download_mode": "reuse_dataset_if_exists", "columns": {}, "strict": false, "model_name": null, "model_author": null, "custom_dataset_info": [], "quant_method": null, "quant_bits": null, "hqq_axis": null, "bnb_4bit_compute_dtype": "bfloat16", "bnb_4bit_quant_type": "nf4", "bnb_4bit_use_double_quant": true, "bnb_4bit_quant_storage": null, "max_new_tokens": 512, "temperature": 0.9, "top_k": 50, "top_p": 0.9, "repetition_penalty": 1.0, "num_beams": 1, "stream": false, "stop_words": [], "logprobs": false, "top_logprobs": null, "ckpt_dir": "output_sft_add_tokens_multi-center-1-21-final/v7-20260122-001024/checkpoint-2000-merged/", "lora_modules": [], "train_type": "lora", "adapters": [], "external_plugins": [], "model_kwargs": {}, "load_args": false, "load_data_args": false, "packing": false, "packing_length": null, "packing_num_proc": 1, "lazy_tokenize": true, "custom_register_path": [], "use_hf": false, "ignore_args_error": false, "use_swift_lora": false, "freeze_parameters": [], "freeze_parameters_regex": null, "freeze_parameters_ratio": 0.0, "trainable_parameters": [], "trainable_parameters_regex": null, "freeze_llm": false, "freeze_vit": true, "freeze_aligner": true, "target_modules": [ "all-linear" ], "target_regex": null, "target_parameters": null, "modules_to_save": [], "lora_rank": 64, "lora_alpha": 128, "lora_dropout": 0.05, "lora_bias": "none", "lora_dtype": null, "lorap_lr_ratio": null, "use_rslora": false, "use_dora": false, "lora_ga_batch_size": 2, "lora_ga_iters": 2, "lora_ga_max_length": 1024, "lora_ga_direction": "ArB2r", "lora_ga_scale": "stable", "lora_ga_stable_gamma": 16, "init_weights": true, "fourier_n_frequency": 2000, "fourier_scaling": 300.0, "boft_block_size": 4, "boft_block_num": 0, "boft_n_butterfly_factor": 1, "boft_dropout": 0.0, "vera_rank": 256, "vera_projection_prng_key": 0, "vera_dropout": 0.0, "vera_d_initial": 0.1, "adapter_act": "gelu", "adapter_length": 128, "use_galore": false, "galore_target_modules": null, "galore_rank": 128, "galore_update_proj_gap": 50, "galore_scale": 1.0, "galore_proj_type": "std", "galore_optim_per_parameter": false, "galore_with_embedding": false, "galore_quantization": false, "galore_proj_quant": false, "galore_proj_bits": 4, "galore_proj_group_size": 256, "galore_cos_threshold": 0.4, "galore_gamma_proj": 2, "galore_queue_size": 5, "adalora_target_r": 8, "adalora_init_r": 12, "adalora_tinit": 0, "adalora_tfinal": 0, "adalora_deltaT": 1, "adalora_beta1": 0.85, "adalora_beta2": 0.85, "adalora_orth_reg_weight": 0.5, "llamapro_num_new_blocks": 4, "llamapro_num_groups": null, "lisa_activated_layers": 0, "lisa_step_interval": 20, "reft_layer_key": null, "reft_layers": null, "reft_rank": 4, "reft_intervention_type": "LoreftIntervention", "reft_args": null, "swanlab_token": null, "swanlab_project": "swift-multicenter-dpo-10_final-qwen3-simpo-date-1-26", "swanlab_workspace": null, "swanlab_exp_name": "/home/ppq5umrb/whcs-share46/ms-swift-main/output_qwen3-sft_add_tokens_multi_center_simpo_1-24/v54-20260127-154928", "swanlab_lark_webhook_url": null, "swanlab_lark_secret": null, "swanlab_mode": "cloud", "add_version": true, "create_checkpoint_symlink": false, "zero_hpz_partition_size": null, "deepspeed_autotp_size": null, "early_stop_interval": null, "sft_alpha": 0, "chord_sft_dataset": [], "chord_sft_per_device_train_batch_size": null, "chord_enable_phi_function": false, "chord_mu_warmup_steps": null, "chord_mu_decay_steps": null, "chord_mu_peak": null, "chord_mu_valley": null, "reward_model": null, "reward_adapters": [], "reward_model_type": null, "reward_model_revision": null, "num_ppo_epochs": 4, "whiten_rewards": false, "kl_coef": 0.05, "cliprange": 0.2, "vf_coef": 0.1, "cliprange_value": 0.2, "gamma": 1.0, "lam": 0.95, "num_mini_batches": 1, "local_rollout_forward_batch_size": 64, "num_sample_generations": 10, "response_length": 512, "missing_eos_penalty": null, "vllm_gpu_memory_utilization": 0.9, "vllm_tensor_parallel_size": 1, "vllm_pipeline_parallel_size": 1, "vllm_enable_expert_parallel": false, "vllm_max_num_seqs": null, "vllm_max_model_len": null, "vllm_disable_custom_all_reduce": true, "vllm_enforce_eager": false, "vllm_limit_mm_per_prompt": null, "vllm_max_lora_rank": 16, "vllm_enable_prefix_caching": true, "vllm_use_async_engine": false, "vllm_quantization": null, "vllm_reasoning_parser": null, "vllm_disable_cascade_attn": false, "vllm_mm_processor_cache_gb": null, "vllm_speculative_config": null, "vllm_engine_kwargs": {}, "vllm_data_parallel_size": 1, "use_vllm": false, "vllm_mode": null, "vllm_enable_lora": false, "vllm_server_base_url": null, "vllm_server_host": null, "vllm_server_port": [ 8000 ], "vllm_server_timeout": 240.0, "vllm_server_group_port": null, "enable_flattened_weight_sync": true, "async_generate": false, "sleep_level": 0, "move_model_batches": null, "offload_optimizer": false, "offload_model": false, "wandb_log_unique_prompts": null, "epsilon": 0.2, "epsilon_high": null, "delta": null, "cosine_min_len_value_wrong": -0.5, "cosine_max_len_value_wrong": 0.0, "cosine_min_len_value_correct": 1.0, "cosine_max_len_value_correct": 0.5, "cosine_max_len": null, "repetition_n_grams": 3, "repetition_max_penalty": -1.0, "reward_model_plugin": null, "sync_ref_model": false, "ref_model_sync_steps": 512, "ref_model_mixup_alpha": 0.6, "multi_turn_scheduler": null, "max_turns": null, "completion_length_limit_scope": "per_round", "vllm_server_pass_dataset": false, "dynamic_sample": false, "max_resample_times": 3, "overlong_filter": false, "soft_max_length": null, "soft_cache_length": null, "scale_rewards": null, "log_entropy": false, "top_entropy_quantile": 1.0, "importance_sampling_level": "token", "tau_pos": 1.0, "tau_neg": 1.05, "advantage_estimator": "grpo", "kl_in_reward": null, "generation_batch_size": null, "steps_per_generation": null, "rollout_importance_sampling_mode": null, "rollout_importance_sampling_threshold": 2.0, "log_rollout_offpolicy_metrics": false, "num_generations": 8, "reward_funcs": [], "reward_weights": null, "log_completions": false, "num_iterations": 1, "teacher_model": null, "teacher_adapters": [], "teacher_model_type": null, "teacher_model_revision": null, "teacher_deepspeed": null, "rlhf_type": "cpo", "ref_model": null, "ref_adapters": [], "ref_model_type": null, "ref_model_revision": null, "beta": 4.0, "label_smoothing": 0, "max_completion_length": 512, "rpo_alpha": null, "ld_alpha": null, "discopop_tau": 0.05, "loss_weights": null, "cpo_alpha": 1.0, "simpo_gamma": 0.3, "desirable_weight": 1.0, "undesirable_weight": 1.0, "center_rewards_coefficient": null, "lmbda": 0.5, "seq_kd": false, "offload_teacher_model": false, "rank": 0, "global_world_size": 4, "local_world_size": 4, "model_suffix": "checkpoint-2000-merged", "model_info": "ModelInfo(model_type='qwen3_vl', model_dir='/home/ppq5umrb/whcs-share46/ms-swift-main/output_sft_add_tokens_multi-center-1-21-final/v7-20260122-001024/checkpoint-2000-merged', torch_dtype=torch.bfloat16, max_model_len=262144, quant_method=None, quant_bits=None, rope_scaling={'mrope_interleaved': True, 'mrope_section': [24, 20, 20], 'rope_type': 'default'}, is_moe_model=False, is_multimodal=True, config=None, task_type='causal_lm', num_labels=None)", "model_meta": "ModelMeta(model_type='qwen3_vl', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen3-VL-2B-Instruct', hf_model_id='Qwen/Qwen3-VL-2B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-2B-Thinking', hf_model_id='Qwen/Qwen3-VL-2B-Thinking', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-2B-Instruct-FP8', hf_model_id='Qwen/Qwen3-VL-2B-Instruct-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-2B-Thinking-FP8', hf_model_id='Qwen/Qwen3-VL-2B-Thinking-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-4B-Instruct', hf_model_id='Qwen/Qwen3-VL-4B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-4B-Thinking', hf_model_id='Qwen/Qwen3-VL-4B-Thinking', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-4B-Instruct-FP8', hf_model_id='Qwen/Qwen3-VL-4B-Instruct-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-4B-Thinking-FP8', hf_model_id='Qwen/Qwen3-VL-4B-Thinking-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-8B-Instruct', hf_model_id='Qwen/Qwen3-VL-8B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-8B-Thinking', hf_model_id='Qwen/Qwen3-VL-8B-Thinking', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-8B-Instruct-FP8', hf_model_id='Qwen/Qwen3-VL-8B-Instruct-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-8B-Thinking-FP8', hf_model_id='Qwen/Qwen3-VL-8B-Thinking-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-32B-Instruct', hf_model_id='Qwen/Qwen3-VL-32B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-32B-Thinking', hf_model_id='Qwen/Qwen3-VL-32B-Thinking', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-32B-Instruct-FP8', hf_model_id='Qwen/Qwen3-VL-32B-Instruct-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-32B-Thinking-FP8', hf_model_id='Qwen/Qwen3-VL-32B-Thinking-FP8', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='qwen3_vl', get_function=, model_arch=MultiModelKeys(arch_name='qwen3_vl', embedding=None, module_list=None, lm_head=None, q_proj=None, k_proj=None, v_proj=None, o_proj=None, attention=None, mlp=None, down_proj=None, qkv_proj=None, qk_proj=None, qa_proj=None, qb_proj=None, kv_proj=None, kva_proj=None, kvb_proj=None, language_model=['model.language_model', 'lm_head'], aligner=['model.visual.merger', 'model.visual.deepstack_merger_list'], vision_tower=['model.visual'], generator=[]), architectures=['Qwen3VLForConditionalGeneration'], additional_saved_files=[], torch_dtype=None, is_multimodal=True, is_reward=False, is_reranker=False, task_type=None, ignore_patterns=None, requires=['transformers>=4.57', 'qwen_vl_utils>=0.0.14', 'decord'], tags=['vision', 'video'])", "model_dir": "/home/ppq5umrb/whcs-share46/ms-swift-main/output_sft_add_tokens_multi-center-1-21-final/v7-20260122-001024/checkpoint-2000-merged", "_val_dataset_exists": [ "na_all-json-out_real_z_select_1k_1k/y_dpo_z_eval_real_dpo.jsonl" ], "hub": "", "evaluation_strategy": "steps", "training_args": "CPOConfig(output_dir='/home/ppq5umrb/whcs-share46/ms-swift-main/output_qwen3-sft_add_tokens_multi_center_simpo_1-24/v54-20260127-154928', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, eval_strategy=, prediction_loss_only=False, per_device_train_batch_size=1, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=4, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=0.0005, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1.0, num_train_epochs=10.0, max_steps=-1, lr_scheduler_type=, lr_scheduler_kwargs=None, warmup_ratio=0.05, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/home/ppq5umrb/whcs-share46/ms-swift-main/output_qwen3-sft_add_tokens_multi_center_simpo_1-24/v54-20260127-154928/runs', logging_strategy=, logging_first_step=True, logging_steps=10, logging_nan_inf_filter=True, save_strategy=, save_steps=50, save_total_limit=None, save_safetensors=True, save_on_each_node=False, save_only_model=False, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=42, jit_mode_eval=False, bf16=True, fp16=False, fp16_opt_level='O1', half_precision_backend='auto', bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=0, ddp_backend=None, tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=50, dataloader_num_workers=0, dataloader_prefetch_factor=None, past_index=-1, run_name='/home/ppq5umrb/whcs-share46/ms-swift-main/output_qwen3-sft_add_tokens_multi_center_simpo_1-24/v54-20260127-154928', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, 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=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), parallelism_config=None, deepspeed={'fp16': {'enabled': 'auto', 'loss_scale': 0, 'loss_scale_window': 1000, 'initial_scale_power': 16, 'hysteresis': 2, 'min_loss_scale': 1}, 'bf16': {'enabled': 'auto'}, 'zero_optimization': {'stage': 2, 'offload_optimizer': {'device': 'none', 'pin_memory': True}, 'allgather_partitions': True, 'allgather_bucket_size': 200000000.0, 'overlap_comm': False, 'reduce_scatter': True, 'reduce_bucket_size': 200000000.0, 'contiguous_gradients': True}, 'gradient_accumulation_steps': 'auto', 'gradient_clipping': 'auto', 'steps_per_print': 2000, 'train_batch_size': 'auto', 'train_micro_batch_size_per_gpu': 'auto', 'wall_clock_breakdown': False}, label_smoothing_factor=0.0, optim=, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['swanlab'], project='huggingface', trackio_space_id='trackio', 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=False, resume_from_checkpoint=None, hub_model_id=None, hub_strategy=, hub_token=None, hub_private_repo=None, hub_always_push=False, hub_revision=None, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=18000000, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, include_tokens_per_second=None, include_num_input_tokens_seen=None, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, liger_kernel_config=None, eval_use_gather_object=False, average_tokens_across_devices=None, max_length=197534, max_prompt_length=512, max_completion_length=512, beta=4.0, label_smoothing=0, loss_type='simpo', disable_dropout=True, cpo_alpha=1.0, simpo_gamma=0.3, label_pad_token_id=None, padding_value=None, truncation_mode='keep_end', generate_during_eval=False, is_encoder_decoder=None, model_init_kwargs=None, dataset_num_proc=1, tuner_backend='peft', vit_gradient_checkpointing=True, router_aux_loss_coef=0.0, enable_dft_loss=False, enable_channel_loss=False, check_model=True, acc_strategy='token', train_dataloader_shuffle=True, max_epochs=None, aligner_lr=None, vit_lr=None, use_logits_to_keep=None, ds3_gather_for_generation=True, resume_only_model=False, optimizer=None, metric=None, eval_use_evalscope=False, eval_dataset=[], eval_dataset_args=None, eval_limit=None, eval_generation_config=None, extra_eval_args=None, use_flash_ckpt=False, sft_alpha=0, chord_sft_dataset=[], chord_sft_per_device_train_batch_size=None, chord_enable_phi_function=False, chord_mu_warmup_steps=None, chord_mu_decay_steps=None, chord_mu_peak=None, chord_mu_valley=None, train_type='lora', local_repo_path=None, galore_config=None, padding_side='right', padding_free=False, task_type='causal_lm', problem_type=None)" }