[2025-12-27 21:18:07,941] [DEBUG] [axolotl.utils.config.resolve_dtype:66] [PID:122677] bf16 support detected, enabling for this configuration. config.json: 0.00B [00:00, ?B/s] config.json: 1.54kB [00:00, 6.02MB/s] [2025-12-27 21:18:08,103] [DEBUG] [axolotl.utils.config.log_gpu_memory_usage:127] [PID:122677] baseline 0.000GB () [2025-12-27 21:18:08,106] [INFO] [axolotl.cli.config.load_cfg:248] [PID:122677] config: { "activation_offloading": false, "adapter": "lora", "axolotl_config_path": "config.yaml", "base_model": "BKM1804/affine-he-CIVICbeatPORSCHE", "base_model_config": "BKM1804/affine-he-CIVICbeatPORSCHE", "batch_size": 128, "bf16": true, "capabilities": { "bf16": true, "compute_capability": "sm_90", "fp8": false, "n_gpu": 1, "n_node": 1 }, "context_parallel_size": 1, "dataloader_num_workers": 1, "dataloader_pin_memory": true, "dataloader_prefetch_factor": 256, "dataset_processes": 18, "datasets": [ { "chat_template": "tokenizer_default", "field_messages": "messages", "message_property_mappings": { "content": "content", "role": "role" }, "path": "/workspace/fine-tuning/dataset/train_qwen3_lgc.jsonl", "split": "train", "trust_remote_code": false, "type": "chat_template" } ], "ddp": false, "device": "cuda:0", "dion_rank_fraction": 1.0, "dion_rank_multiple_of": 1, "env_capabilities": { "torch_version": "2.7.1" }, "eval_batch_size": 2, "eval_causal_lm_metrics": [ "sacrebleu", "comet", "ter", "chrf" ], "eval_max_new_tokens": 128, "eval_table_size": 0, "experimental_skip_move_to_device": true, "fp16": false, "gradient_accumulation_steps": 64, "gradient_checkpointing": false, "include_tkps": true, "learning_rate": 2e-06, "lisa_layers_attribute": "model.layers", "load_best_model_at_end": false, "load_in_4bit": false, "load_in_8bit": true, "local_rank": 0, "lora_alpha": 64, "lora_dropout": 0.05, "lora_r": 32, "lora_target_modules": [ "q_proj", "v_proj", "k_proj", "o_proj", "gate_proj", "down_proj", "up_proj" ], "loraplus_lr_embedding": 1e-06, "lr_scheduler": "cosine", "mean_resizing_embeddings": false, "micro_batch_size": 2, "model_config_type": "qwen3", "num_epochs": 3.0, "optimizer": "adamw_bnb_8bit", "output_dir": "./outputs/mymodel", "pretrain_multipack_attn": true, "profiler_steps_start": 0, "qlora_sharded_model_loading": false, "ray_num_workers": 1, "resources_per_worker": { "GPU": 1 }, "sample_packing_bin_size": 200, "sample_packing_group_size": 100000, "save_only_model": false, "save_safetensors": true, "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, "tiled_mlp_use_original_mlp": true, "tokenizer_config": "BKM1804/affine-he-CIVICbeatPORSCHE", "tokenizer_save_jinja_files": true, "torch_dtype": "torch.bfloat16", "train_on_inputs": false, "trl": { "log_completions": false, "mask_truncated_completions": false, "ref_model_mixup_alpha": 0.9, "ref_model_sync_steps": 64, "scale_rewards": true, "sync_ref_model": false, "use_vllm": false, "vllm_server_host": "0.0.0.0", "vllm_server_port": 8000 }, "use_ray": false, "val_set_size": 0.0, "vllm": { "device": "auto", "dtype": "auto", "gpu_memory_utilization": 0.9, "host": "0.0.0.0", "port": 8000 }, "weight_decay": 0.0, "world_size": 1 } tokenizer_config.json: 0.00B [00:00, ?B/s] tokenizer_config.json: 5.40kB [00:00, 22.8MB/s] vocab.json: 0.00B [00:00, ?B/s] vocab.json: 32.8kB [00:00, 297kB/s] vocab.json: 1.66MB [00:00, 7.30MB/s] vocab.json: 2.78MB [00:00, 10.2MB/s] merges.txt: 0.00B [00:00, ?B/s] merges.txt: 43.4kB [00:00, 357kB/s] merges.txt: 1.67MB [00:00, 8.66MB/s] tokenizer.json: 0%| | 0.00/11.4M [00:00 [2025-12-27 21:18:10,827] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:279] [PID:122677] BOS: None / None [2025-12-27 21:18:10,828] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:280] [PID:122677] PAD: 151643 / <|endoftext|> [2025-12-27 21:18:10,828] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:281] [PID:122677] UNK: None / None [2025-12-27 21:18:10,829] [INFO] [axolotl.utils.data.shared.load_preprocessed_dataset:476] [PID:122677] Unable to find prepared dataset in last_run_prepared/f6b60198703671e2d2150636511428c1 [2025-12-27 21:18:10,829] [INFO] [axolotl.utils.data.sft._load_raw_datasets:320] [PID:122677] Loading raw datasets... [2025-12-27 21:18:10,829] [WARNING] [axolotl.utils.data.sft._load_raw_datasets:322] [PID:122677] Processing datasets during training can lead to VRAM instability. Please pre-process your dataset using `axolotl preprocess path/to/config.yml`. [2025-12-27 21:18:10,933] [INFO] [axolotl.utils.data.wrappers.get_dataset_wrapper:87] [PID:122677] Loading dataset: /workspace/fine-tuning/dataset/train_qwen3_lgc.jsonl with base_type: chat_template and prompt_style: None [2025-12-27 21:18:10,935] [INFO] [axolotl.prompt_strategies.chat_template.__call__:969] [PID:122677] Using chat template: --- {%- set ns = namespace(last_query_index=-1) %} {%- for message in messages %} {%- if message.role == "user" %} {%- set ns.last_query_index = loop.index0 %} {%- endif %} {%- endfor %} {%- if tools %} {{- '<|im_start|>system\n' }} {%- if messages[0].role == 'system' %} {{- messages[0].content + '\n\n' }} {%- endif %} {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }} {%- for tool in tools %} {{- "\n" }} {{- tool | tojson }} {%- endfor %} {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }} {%- else %} {%- if messages[0].role == 'system' %} {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }} {%- endif %} {%- endif %} {%- for message in messages %} {%- if message.content is string %} {%- set content = message.content %} {%- else %} {%- set content = '' %} {%- endif %} {%- if (message.role == "user") or (message.role == "system" and not loop.first) %} {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }} {%- elif message.role == "assistant" %} {%- set has_loss = (message.loss is defined and message.loss) %} {%- set reasoning_content = '' %} {%- if message.reasoning_content is string %} {%- set reasoning_content = message.reasoning_content %} {%- else %} {%- if '' in content %} {%- set reasoning_content = content.split('')[0].rstrip('\n').split('')[-1].lstrip('\n') %} {%- set content = content.split('')[-1].lstrip('\n') %} {%- endif %} {%- endif %} {{- '<|im_start|>' + message.role + '\n' }} {%- if has_loss -%} {%- generation -%} {%- if loop.index0 > ns.last_query_index and reasoning_content %} {{- '\n' + reasoning_content.strip('\n') + '\n\n\n' + content.lstrip('\n') }} {%- else %} {{- content }} {%- endif %} {%- if message.tool_calls %} {%- for tool_call in message.tool_calls %} {%- if (loop.first and content) or (not loop.first) %} {{- '\n' }} {%- endif %} {%- if tool_call.function %} {%- set tool_call = tool_call.function %} {%- endif %} {{- '\n{"name": "' }} {{- tool_call.name }} {{- '", "arguments": ' }} {%- if tool_call.arguments is string %} {{- tool_call.arguments }} {%- else %} {{- tool_call.arguments | tojson }} {%- endif %} {{- '}\n' }} {%- endfor %} {%- endif %} {{- '<|im_end|>' }} {%- endgeneration -%} {{- '\n' }} {%- else -%} {%- if loop.index0 > ns.last_query_index and reasoning_content %} {{- '\n' + reasoning_content.strip('\n') + '\n\n\n' + content.lstrip('\n') }} {%- else %} {{- content }} {%- endif %} {%- if message.tool_calls %} {%- for tool_call in message.tool_calls %} {%- if (loop.first and content) or (not loop.first) %} {{- '\n' }} {%- endif %} {%- if tool_call.function %} {%- set tool_call = tool_call.function %} {%- endif %} {{- '\n{"name": "' }} {{- tool_call.name }} {{- '", "arguments": ' }} {%- if tool_call.arguments is string %} {{- tool_call.arguments }} {%- else %} {{- tool_call.arguments | tojson }} {%- endif %} {{- '}\n' }} {%- endfor %} {%- endif %} {{- '<|im_end|>\n' }} {%- endif %} {%- elif message.role == "tool" %} {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %} {{- '<|im_start|>user' }} {%- endif %} {{- '\n\n' }} {{- content }} {{- '\n' }} {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} {{- '<|im_end|>\n' }} {%- endif %} {%- endif %} {%- endfor %} {%- if add_generation_prompt %} {{- '<|im_start|>assistant\n' }} {%- endif %} --- Tokenizing Prompts (num_proc=18): 0%| | 0/3494 [00:004096) (num_proc=18): 0%| | 0/3494 [00:004096) (num_proc=18): 6%|████▏ | 195/3494 [00:00<00:05, 564.88 examples/s] Dropping Long Sequences (>4096) (num_proc=18): 100%|████████████████████████████████████████████████████████████████████████| 3494/3494 [00:00<00:00, 6342.01 examples/s] [2025-12-27 21:18:14,100] [WARNING] [axolotl.utils.data.utils.handle_long_seq_in_dataset:260] [PID:122677] Dropped 49 samples from dataset Saving the dataset (0/13 shards): 0%| | 0/3445 [00:00 [2025-12-27 21:18:15,207] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:279] [PID:122677] BOS: None / None [2025-12-27 21:18:15,207] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:280] [PID:122677] PAD: 151643 / <|endoftext|> [2025-12-27 21:18:15,207] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:281] [PID:122677] UNK: None / None [2025-12-27 21:18:15,208] [DEBUG] [axolotl.train.setup_model_and_tokenizer:74] [PID:122677] Loading model [2025-12-27 21:18:15,257] [DEBUG] [axolotl.monkeypatch.transformers.trainer_loss_calc.patch_evaluation_loop:87] [PID:122677] Patched Trainer.evaluation_loop with nanmean loss calculation [2025-12-27 21:18:15,258] [DEBUG] [axolotl.monkeypatch.transformers.trainer_loss_calc.patch_maybe_log_save_evaluate:138] [PID:122677] Patched Trainer._maybe_log_save_evaluate with nanmean loss calculation model.safetensors.index.json: 0.00B [00:00, ?B/s] model.safetensors.index.json: 32.9kB [00:00, 88.3MB/s] model-00001-of-00002.safetensors: 0%| | 0.00/4.97G [00:00