[2026-04-17 00:05:12,906] [DEBUG] [axolotl.utils.config.log_gpu_memory_usage:127] [PID:3789701] baseline 0.000GB () [2026-04-17 00:05:12,906] [INFO] [axolotl.cli.config.load_cfg:341] [PID:3789701] config: { "activation_offloading": false, "adapter": "lora", "axolotl_config_path": "./axolotl_configs/Qwen3.5-9B/cot-lora-primevul-plus.yaml", "base_model": "Qwen/Qwen3.5-9B", "base_model_config": "Qwen/Qwen3.5-9B", "batch_size": 32, "bf16": true, "capabilities": { "bf16": true, "compute_capability": "sm_90", "fp8": true, "n_gpu": 1, "n_node": 1, "tf32": true }, "context_parallel_size": 1, "dataloader_num_workers": 1, "dataloader_pin_memory": true, "dataloader_prefetch_factor": 256, "dataset_num_proc": 16, "dataset_prepared_path": "/home/tkwang/scratch/SecSteer-v2/axolotl-datasets/lora/Qwen3.5-9B/cot-sec", "datasets": [ { "chat_template": "tokenizer_default", "message_property_mappings": { "content": "content", "role": "role" }, "path": "felixwangg/glm-4.6v-distilled-sec-cot", "split": "train", "trust_remote_code": false, "type": "chat_template" } ], "ddp": false, "ddp_find_unused_parameters": true, "device": "cuda:0", "device_map": "auto", "dion_rank_fraction": 1.0, "dion_rank_multiple_of": 1, "eaft_alpha": 1.0, "eaft_k": 20, "early_stopping_patience": 1000, "env_capabilities": { "torch_version": "2.11.0" }, "eval_batch_size": 4, "eval_causal_lm_metrics": [ "sacrebleu", "comet", "ter", "chrf" ], "eval_max_new_tokens": 128, "eval_sample_packing": false, "eval_steps": 15, "eval_table_size": 0, "experimental_skip_move_to_device": true, "flash_attention": true, "fp16": false, "generate_samples": false, "generation_do_sample": true, "generation_max_new_tokens": 50, "generation_prompt_ratio": 0.5, "generation_temperature": 0.7, "gradient_accumulation_steps": 8, "gradient_checkpointing": true, "gradient_checkpointing_kwargs": { "use_reentrant": false }, "include_tkps": true, "is_falcon_derived_model": false, "is_llama_derived_model": false, "is_mistral_derived_model": false, "is_multimodal": true, "layer_offloading": false, "learning_rate": 4e-05, "lisa_layers_attribute": "model.layers", "load_best_model_at_end": true, "load_in_4bit": false, "load_in_8bit": false, "local_rank": 0, "logging_steps": 1, "lora_alpha": 16, "lora_dropout": 0.05, "lora_embedding_kernel": true, "lora_mlp_kernel": true, "lora_model_dir": "axolotl-outputs/lora/Qwen3.5-9B-cot-sec", "lora_o_kernel": true, "lora_qkv_kernel": true, "lora_r": 16, "lora_target_linear": true, "loraplus_lr_embedding": 1e-06, "lr_scheduler": "cosine", "mean_resizing_embeddings": false, "merge_lora": true, "merge_method": "memory_efficient", "micro_batch_size": 4, "model_config_type": "qwen3_5", "model_config_type_text": "qwen3_5_text", "num_epochs": 1.0, "num_generation_samples": 3, "optimizer": "adamw_torch", "otel_metrics_host": "localhost", "otel_metrics_port": 8000, "output_dir": "/home/tkwang/scratch/SecSteer-v2/axolotl-outputs/lora/Qwen3.5-9B-cot-sec", "pad_to_sequence_len": true, "pretrain_multipack_attn": true, "processor_config": "Qwen/Qwen3.5-9B", "profiler_steps_start": 0, "qlora_sharded_model_loading": false, "quantize_moe_experts": false, "ray_num_workers": 1, "resources_per_worker": { "GPU": 1 }, "sample_packing": false, "sample_packing_bin_size": 200, "sample_packing_group_size": 100000, "save_only_model": false, "save_safetensors": true, "save_steps": 15, "save_total_limit": 1000, "sequence_len": 4096, "shuffle_before_merging_datasets": false, "shuffle_merged_datasets": true, "skip_prepare_dataset": false, "streaming_multipack_buffer_size": 10000, "strict": false, "tensor_parallel_size": 1, "test_datasets": [ { "chat_template": "tokenizer_default", "message_property_mappings": { "content": "content", "role": "role" }, "path": "felixwangg/glm-4.6v-distilled-sec-cot", "split": "validation", "trust_remote_code": false, "type": "chat_template" } ], "tf32": false, "tiled_mlp_use_original_mlp": true, "tokenizer_config": "Qwen/Qwen3.5-9B", "tokenizer_save_jinja_files": true, "tokenizer_type": "AutoTokenizer", "torch_dtype": "torch.bfloat16", "train_on_inputs": false, "trl": { "async_prefetch": false, "log_completions": false, "mask_truncated_completions": false, "ref_model_mixup_alpha": 0.9, "ref_model_sync_steps": 64, "replay_buffer_size": 0, "replay_recompute_logps": true, "reroll_max_groups": 1, "reroll_start_fraction": 1.0, "reward_num_workers": 1, "scale_rewards": true, "skip_zero_advantage_batches": true, "sync_ref_model": false, "use_data_producer": false, "use_vllm": false, "vllm_lora_sync": false, "vllm_server_host": "0.0.0.0", "vllm_server_port": 8000 }, "type_of_model": "AutoModelForCausalLM", "use_otel_metrics": false, "use_ray": false, "use_wandb": true, "val_set_size": 0.0, "vllm": { "device": "auto", "dtype": "auto", "gpu_memory_utilization": 0.9, "host": "0.0.0.0", "port": 8000 }, "wandb_entity": "wtkuan", "wandb_log_model": "false", "wandb_name": "Qwen3.5-9B-cot-sec", "wandb_project": "cot-qwen3.5-primevul", "wandb_watch": "false", "warmup_ratio": 0.1, "weight_decay": 0.02, "world_size": 1 } [2026-04-17 00:05:12,909] [WARNING] [axolotl.utils.schemas.config.default_dataset_num_proc:1745] [PID:3789701] dataset_processes is deprecated and will be removed in a future version. Please use dataset_num_proc instead. [2026-04-17 00:05:12,909] [WARNING] [axolotl.utils.schemas.config.check_auto_enable_lora_kernels:1597] [PID:3789701] Auto-enabling LoRA kernel optimizations for faster training. Please explicitly set `lora_*_kernel` config values to `false` to disable. See https://docs.axolotl.ai/docs/lora_optims.html for more info. [2026-04-17 00:05:13,014] [DEBUG] [axolotl.utils.config.log_gpu_memory_usage:127] [PID:3789701] baseline 0.000GB () [2026-04-17 00:05:13,015] [INFO] [axolotl.cli.config.load_cfg:341] [PID:3789701] config: { "activation_offloading": false, "adapter": "lora", "axolotl_config_path": "./axolotl_configs/Qwen3.5-9B/cot-lora-primevul-plus.yaml", "base_model": "Qwen/Qwen3.5-9B", "base_model_config": "Qwen/Qwen3.5-9B", "batch_size": 32, "bf16": true, "capabilities": { "bf16": true, "compute_capability": "sm_90", "fp8": true, "n_gpu": 1, "n_node": 1, "tf32": true }, "context_parallel_size": 1, "dataloader_num_workers": 1, "dataloader_pin_memory": true, "dataloader_prefetch_factor": 256, "dataset_num_proc": 16, "dataset_prepared_path": "/home/tkwang/scratch/SecSteer-v2/axolotl-datasets/lora/Qwen3.5-9B/cot-sec", "datasets": [ { "chat_template": "tokenizer_default", "message_property_mappings": { "content": "content", "role": "role" }, "path": "felixwangg/glm-4.6v-distilled-sec-cot", "split": "train", "trust_remote_code": false, "type": "chat_template" } ], "ddp": false, "ddp_find_unused_parameters": true, "device": "cuda:0", "device_map": "auto", "dion_rank_fraction": 1.0, "dion_rank_multiple_of": 1, "eaft_alpha": 1.0, "eaft_k": 20, "early_stopping_patience": 1000, "env_capabilities": { "torch_version": "2.11.0" }, "eval_batch_size": 4, "eval_causal_lm_metrics": [ "sacrebleu", "comet", "ter", "chrf" ], "eval_max_new_tokens": 128, "eval_sample_packing": false, "eval_steps": 15, "eval_table_size": 0, "experimental_skip_move_to_device": true, "flash_attention": false, "fp16": false, "generate_samples": false, "generation_do_sample": true, "generation_max_new_tokens": 50, "generation_prompt_ratio": 0.5, "generation_temperature": 0.7, "gradient_accumulation_steps": 8, "gradient_checkpointing": true, "gradient_checkpointing_kwargs": { "use_reentrant": false }, "include_tkps": true, "is_falcon_derived_model": false, "is_llama_derived_model": false, "is_mistral_derived_model": false, "is_multimodal": true, "layer_offloading": false, "learning_rate": 4e-05, "lisa_layers_attribute": "model.layers", "load_best_model_at_end": true, "load_in_4bit": false, "load_in_8bit": false, "local_rank": 0, "logging_steps": 1, "lora_alpha": 16, "lora_dropout": 0.05, "lora_embedding_kernel": true, "lora_mlp_kernel": true, "lora_model_dir": "axolotl-outputs/lora/Qwen3.5-9B-cot-sec", "lora_o_kernel": true, "lora_qkv_kernel": true, "lora_r": 16, "lora_target_linear": true, "loraplus_lr_embedding": 1e-06, "lr_scheduler": "cosine", "mean_resizing_embeddings": false, "merge_lora": true, "merge_method": "memory_efficient", "micro_batch_size": 4, "model_config_type": "qwen3_5", "model_config_type_text": "qwen3_5_text", "num_epochs": 1.0, "num_generation_samples": 3, "optimizer": "adamw_torch", "otel_metrics_host": "localhost", "otel_metrics_port": 8000, "output_dir": "/home/tkwang/scratch/SecSteer-v2/axolotl-outputs/lora/Qwen3.5-9B-cot-sec", "pad_to_sequence_len": true, "pretrain_multipack_attn": true, "processor_config": "Qwen/Qwen3.5-9B", "profiler_steps_start": 0, "qlora_sharded_model_loading": false, "quantize_moe_experts": false, "ray_num_workers": 1, "resources_per_worker": { "GPU": 1 }, "sample_packing": false, "sample_packing_bin_size": 200, "sample_packing_group_size": 100000, "save_only_model": false, "save_safetensors": true, "save_steps": 15, "save_total_limit": 1000, "sequence_len": 4096, "shuffle_before_merging_datasets": false, "shuffle_merged_datasets": true, "skip_prepare_dataset": false, "streaming_multipack_buffer_size": 10000, "strict": false, "tensor_parallel_size": 1, "test_datasets": [ { "chat_template": "tokenizer_default", "message_property_mappings": { "content": "content", "role": "role" }, "path": "felixwangg/glm-4.6v-distilled-sec-cot", "split": "validation", "trust_remote_code": false, "type": "chat_template" } ], "tf32": false, "tiled_mlp_use_original_mlp": true, "tokenizer_config": "Qwen/Qwen3.5-9B", "tokenizer_save_jinja_files": true, "tokenizer_type": "AutoTokenizer", "torch_dtype": "torch.bfloat16", "train_on_inputs": false, "trl": { "async_prefetch": false, "log_completions": false, "mask_truncated_completions": false, "ref_model_mixup_alpha": 0.9, "ref_model_sync_steps": 64, "replay_buffer_size": 0, "replay_recompute_logps": true, "reroll_max_groups": 1, "reroll_start_fraction": 1.0, "reward_num_workers": 1, "scale_rewards": true, "skip_zero_advantage_batches": true, "sync_ref_model": false, "use_data_producer": false, "use_vllm": false, "vllm_lora_sync": false, "vllm_server_host": "0.0.0.0", "vllm_server_port": 8000 }, "type_of_model": "AutoModelForCausalLM", "use_otel_metrics": false, "use_ray": false, "use_wandb": true, "val_set_size": 0.0, "vllm": { "device": "auto", "dtype": "auto", "gpu_memory_utilization": 0.9, "host": "0.0.0.0", "port": 8000 }, "wandb_entity": "wtkuan", "wandb_log_model": "false", "wandb_name": "Qwen3.5-9B-cot-sec", "wandb_project": "cot-qwen3.5-primevul", "wandb_watch": "false", "warmup_ratio": 0.1, "weight_decay": 0.02, "world_size": 1 } [2026-04-17 00:05:13,015] [DEBUG] [axolotl.cli.merge_lora.do_merge_lora:32] [PID:3789701] Using memory-efficient LoRA merging method... [2026-04-17 00:05:13,015] [DEBUG] [axolotl.cli.merge_lora._do_merge_lora_efficient:79] [PID:3789701] Using memory-efficient LoRA merging method... Downloading (incomplete total...): 0.00B [00:00, ?B/s] Fetching 16 files: 0%| | 0/16 [00:00 sys.exit(main()) ^^^^^^ File "/scratch/tkwang/SecSteer-v2/.venv/lib/python3.12/site-packages/axolotl/cli/main.py", line 347, in main cli() File "/scratch/tkwang/SecSteer-v2/.venv/lib/python3.12/site-packages/click/core.py", line 1485, in __call__ return self.main(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/scratch/tkwang/SecSteer-v2/.venv/lib/python3.12/site-packages/click/core.py", line 1406, in main rv = self.invoke(ctx) ^^^^^^^^^^^^^^^^ File "/scratch/tkwang/SecSteer-v2/.venv/lib/python3.12/site-packages/click/core.py", line 1873, in invoke return _process_result(sub_ctx.command.invoke(sub_ctx)) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/scratch/tkwang/SecSteer-v2/.venv/lib/python3.12/site-packages/click/core.py", line 1269, in invoke return ctx.invoke(self.callback, **ctx.params) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/scratch/tkwang/SecSteer-v2/.venv/lib/python3.12/site-packages/click/core.py", line 824, in invoke return callback(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^ File "/scratch/tkwang/SecSteer-v2/.venv/lib/python3.12/site-packages/axolotl/cli/utils/args.py", line 48, in wrapper return func(*args, **filtered_kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/scratch/tkwang/SecSteer-v2/.venv/lib/python3.12/site-packages/axolotl/cli/main.py", line 293, in merge_lora do_cli(config=config, **kwargs) File "/scratch/tkwang/SecSteer-v2/.venv/lib/python3.12/site-packages/axolotl/cli/merge_lora.py", line 169, in do_cli do_merge_lora(cfg=parsed_cfg) File "/scratch/tkwang/SecSteer-v2/.venv/lib/python3.12/site-packages/axolotl/telemetry/errors.py", line 124, in wrapper return func(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^ File "/scratch/tkwang/SecSteer-v2/.venv/lib/python3.12/site-packages/axolotl/cli/merge_lora.py", line 33, in do_merge_lora _do_merge_lora_efficient(cfg=cfg) File "/scratch/tkwang/SecSteer-v2/.venv/lib/python3.12/site-packages/axolotl/cli/merge_lora.py", line 108, in _do_merge_lora_efficient merge_lora_sharded_efficient( File "/scratch/tkwang/SecSteer-v2/.venv/lib/python3.12/site-packages/axolotl/cli/utils/lora_merge.py", line 916, in merge_lora_sharded_efficient merged_tensor, was_merged = _merge_tensor_with_lora( ^^^^^^^^^^^^^^^^^^^^^^^^ File "/scratch/tkwang/SecSteer-v2/.venv/lib/python3.12/site-packages/axolotl/cli/utils/lora_merge.py", line 429, in _merge_tensor_with_lora delta = _build_peft_layer_and_get_delta( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/scratch/tkwang/SecSteer-v2/.venv/lib/python3.12/site-packages/axolotl/cli/utils/lora_merge.py", line 254, in _build_peft_layer_and_get_delta layer = LoraLinear( ^^^^^^^^^^^ TypeError: Linear.__init__() missing 1 required positional argument: 'config'