args.json

{
  "output_dir": "./output",
  "overwrite_output_dir": false,
  "do_train": false,
  "do_eval": false,
  "do_predict": false,
  "eval_strategy": "no",
  "prediction_loss_only": false,
  "per_device_train_batch_size": 1,
  "per_device_eval_batch_size": 1,
  "per_gpu_train_batch_size": null,
  "per_gpu_eval_batch_size": null,
  "gradient_accumulation_steps": 7,
  "eval_accumulation_steps": null,
  "eval_delay": 0,
  "torch_empty_cache_steps": null,
  "learning_rate": 5e-06,
  "weight_decay": 0.1,
  "adam_beta1": 0.9,
  "adam_beta2": 0.95,
  "adam_epsilon": 1e-08,
  "max_grad_norm": 1.0,
  "num_train_epochs": 6.0,
  "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": "./output/logs",
  "logging_strategy": "steps",
  "logging_first_step": true,
  "logging_steps": 5,
  "logging_nan_inf_filter": true,
  "save_strategy": "steps",
  "save_steps": 1609.0,
  "save_total_limit": 10,
  "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,
  "use_ipex": 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": 1609.0,
  "dataloader_num_workers": 192,
  "dataloader_prefetch_factor": null,
  "past_index": -1,
  "run_name": "safety-model-training",
  "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": "",
  "fsdp_min_num_params": 0,
  "fsdp_config": null,
  "fsdp_transformer_layer_cls_to_wrap": null,
  "accelerator_config": {
    "dispatch_batches": false
  },
  "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": 3,
      "offload_optimizer": {
        "device": "none",
        "pin_memory": true
      },
      "offload_param": {
        "device": "none",
        "pin_memory": true
      },
      "overlap_comm": false,
      "contiguous_gradients": true,
      "sub_group_size": 1000000000.0,
      "reduce_bucket_size": "auto",
      "zero_quantized_weights": false,
      "zero_quantized_gradients": false,
      "stage3_prefetch_bucket_size": "auto",
      "stage3_param_persistence_threshold": "auto",
      "stage3_max_live_parameters": 1000000000.0,
      "stage3_max_reuse_distance": 1000000000.0,
      "stage3_gather_16bit_weights_on_model_save": 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": [
    "tensorboard"
  ],
  "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,
  "vit_gradient_checkpointing": null,
  "check_model": true,
  "acc_strategy": "token",
  "train_dataloader_shuffle": true,
  "max_epochs": null,
  "aligner_lr": null,
  "vit_lr": null,
  "optimizer": null,
  "use_logits_to_keep": null,
  "channels": null,
  "ds3_gather_for_generation": true,
  "metric_warmup_step": 0,
  "fsdp_num": 1,
  "acc_steps": 1,
  "eval_use_evalscope": false,
  "eval_dataset": [],
  "eval_dataset_args": null,
  "eval_limit": null,
  "eval_generation_config": null,
  "model": "JSL-joysafety-v1/gpt-oss-20b",
  "model_type": null,
  "model_revision": null,
  "task_type": "causal_lm",
  "torch_dtype": "bfloat16",
  "attn_impl": "flash_attn",
  "num_labels": null,
  "problem_type": null,
  "rope_scaling": {
    "beta_fast": 32.0,
    "beta_slow": 1.0,
    "factor": 32.0,
    "original_max_position_embeddings": 4096,
    "rope_type": "yarn",
    "truncate": false,
    "type": "yarn"
  },
  "device_map": null,
  "max_memory": {},
  "local_repo_path": null,
  "init_strategy": null,
  "template": "default",
  "system": null,
  "max_length": 8192,
  "truncation_strategy": "right",
  "max_pixels": null,
  "agent_template": null,
  "norm_bbox": null,
  "use_chat_template": true,
  "padding_free": false,
  "padding_side": "right",
  "loss_scale": "default",
  "sequence_parallel_size": 1,
  "response_prefix": null,
  "template_backend": "swift",
  "dataset": [
    "JSL-joysafety-v1/safety-dataset"
  ],
  "val_dataset": [],
  "split_dataset_ratio": 0.0,
  "dataset_num_proc": 192,
  "load_from_cache_file": true,
  "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": 64,
  "temperature": 0.0,
  "top_k": null,
  "top_p": null,
  "repetition_penalty": null,
  "num_beams": 1,
  "stream": false,
  "stop_words": [],
  "logprobs": false,
  "top_logprobs": null,
  "ckpt_dir": null,
  "lora_modules": [],
  "tuner_backend": "peft",
  "train_type": "full",
  "adapters": [],
  "external_plugins": [],
  "model_kwargs": {},
  "load_args": false,
  "load_data_args": false,
  "packing": false,
  "packing_cache": null,
  "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,
  "modules_to_save": [],
  "lora_rank": 8,
  "lora_alpha": 32,
  "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": null,
  "swanlab_workspace": null,
  "swanlab_exp_name": null,
  "swanlab_lark_webhook_url": null,
  "swanlab_lark_secret": null,
  "swanlab_mode": "cloud",
  "add_version": true,
  "resume_only_model": false,
  "create_checkpoint_symlink": false,
  "lazy_tokenize": false,
  "loss_type": null,
  "metric": null,
  "zero_hpz_partition_size": null,
  "rank": 0,
  "global_world_size": 40,
  "local_world_size": 8,
  "model_suffix": "gpt-oss-20b",
  "model_meta": "ModelMeta(model_type=None, model_groups=[], template='dummy', get_function=<function get_model_tokenizer_from_local at 0x7f67a0a7b130>, model_arch=None, architectures=[], additional_saved_files=[], torch_dtype=None, is_multimodal=False, is_reward=False, task_type=None, ignore_patterns=None, requires=[], tags=[])",
  "model_dir": "/mnt/workspace/public_model/gpt-oss-20b",
  "evaluation_strategy": "steps"
}