[2026-06-24 12:52:11,377] [DEBUG] [axolotl.utils.config.log_gpu_memory_usage:127] [PID:37810] baseline 0.000GB () [2026-06-24 12:52:11,378] [INFO] [axolotl.cli.config.load_cfg:333] [PID:37810] config: { "activation_offloading": false, "adapter": "lora", "attn_needs_dtype_cast": false, "attn_supports_packing": false, "attn_uses_flash_lib": false, "axolotl_config_path": "fine-tuning/configs/axolotl_qwen36_27b_seed_sft.yml", "base_model": "Qwen/Qwen3.6-27B", "base_model_config": "Qwen/Qwen3.6-27B", "batch_size": 16, "bf16": true, "capabilities": { "bf16": true, "compute_capability": "sm_120", "fp8": true, "n_gpu": 1, "n_node": 1, "tf32": true }, "chat_template": "tokenizer_default", "context_parallel_size": 1, "dataloader_num_workers": 1, "dataloader_pin_memory": true, "dataloader_prefetch_factor": 256, "dataset_num_proc": 384, "dataset_prepared_path": "./fine-tuning/data/seed/axolotl_prepared_qwen36_27b_seed", "datasets": [ { "chat_template": "tokenizer_default", "field_messages": "messages", "message_property_mappings": { "content": "content", "role": "role" }, "path": "./fine-tuning/data/seed/sft_train.jsonl", "roles_to_train": [ "assistant" ], "train_on_eos": "turn", "trust_remote_code": false, "type": "chat_template" } ], "ddp": false, "device": "cuda:0", "dion_rank_fraction": 1.0, "dion_rank_multiple_of": 1, "eaft_alpha": 1.0, "eaft_k": 20, "env_capabilities": { "torch_version": "2.12.1" }, "eval_batch_size": 1, "eval_causal_lm_metrics": [ "sacrebleu", "comet", "ter", "chrf" ], "eval_max_new_tokens": 128, "eval_steps": 200, "eval_table_size": 0, "experimental_skip_move_to_device": 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": 16, "gradient_checkpointing": true, "gradient_checkpointing_kwargs": { "use_reentrant": true }, "hub_model_id": "fornace-ml/eugeny-seed-adapters", "hub_strategy": "every_save", "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": 0.0001, "lisa_layers_attribute": "model.layers", "load_best_model_at_end": false, "load_in_4bit": false, "load_in_8bit": false, "local_rank": 0, "logging_steps": 5, "lora_alpha": 128, "lora_dropout": 0.05, "lora_r": 64, "lora_target_linear": true, "loraplus_lr_embedding": 1e-06, "lr_scheduler": "cosine", "mean_resizing_embeddings": false, "merge_method": "memory_efficient", "micro_batch_size": 1, "model_config_type": "qwen3_5", "model_config_type_text": "qwen3_5_text", "num_epochs": 2.0, "num_generation_samples": 3, "optimizer": "adamw_torch", "otel_metrics_host": "localhost", "otel_metrics_port": 8000, "output_dir": "./outputs/qwen36-27b-agent-memory-sft-lora-axolotl", "pad_to_sequence_len": true, "pretrain_multipack_attn": true, "processor_config": "Qwen/Qwen3.6-27B", "profiler_steps_start": 0, "qgalore_cos_threshold": 0.4, "qgalore_gamma_proj": 2, "qgalore_proj_bits": 4, "qgalore_proj_group_size": 256, "qgalore_proj_quant": true, "qgalore_proj_type": "std", "qgalore_queue_size": 5, "qgalore_rank": 256, "qgalore_scale": 0.25, "qgalore_update_proj_gap": 200, "qlora_sharded_model_loading": false, "quantize_moe_experts": false, "ray_num_workers": 1, "relora_prune_method": "magnitude", "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": 200, "save_total_limit": 2, "seed": 42, "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", "field_messages": "messages", "message_property_mappings": { "content": "content", "role": "role" }, "path": "./fine-tuning/data/seed/sft_eval.jsonl", "roles_to_train": [ "assistant" ], "split": "train", "train_on_eos": "turn", "trust_remote_code": false, "type": "chat_template" } ], "tf32": true, "tiled_mlp_use_original_mlp": true, "tokenizer_config": "Qwen/Qwen3.6-27B", "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 }, "trust_remote_code": true, "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_log_model": "checkpoint", "wandb_name": "eugeny-qwen36-27b-seed-sft", "wandb_project": "eugeny", "warmup_ratio": 0.03, "weight_decay": 0.01, "world_size": 1 } [2026-06-24 12:52:12,530] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:311] [PID:37810] EOS: 248046 / <|im_end|> [2026-06-24 12:52:12,530] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:312] [PID:37810] BOS: None / None [2026-06-24 12:52:12,530] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:313] [PID:37810] PAD: 248044 / <|endoftext|> [2026-06-24 12:52:12,530] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:314] [PID:37810] UNK: None / None [2026-06-24 12:52:12,531] [INFO] [axolotl.utils.data.shared.load_preprocessed_dataset:477] [PID:37810] Loading prepared dataset from disk at fine-tuning/data/seed/axolotl_prepared_qwen36_27b_seed/ddaef6b4b116d96bae21a39214f33062... [2026-06-24 12:52:12,535] [INFO] [axolotl.utils.data.shared.load_preprocessed_dataset:477] [PID:37810] Loading prepared dataset from disk at fine-tuning/data/seed/axolotl_prepared_qwen36_27b_seed/063e5073d5d03e6d44b00418133c74c4... [2026-06-24 12:52:12,539] [DEBUG] [axolotl.utils.trainer.calculate_total_num_steps:420] [PID:37810] total_num_tokens: 77_178 [2026-06-24 12:52:12,540] [DEBUG] [axolotl.utils.trainer.calculate_total_num_steps:438] [PID:37810] `total_supervised_tokens: 27_423` [2026-06-24 12:52:12,540] [DEBUG] [axolotl.utils.trainer.calculate_total_num_steps:521] [PID:37810] total_num_steps: 45 [2026-06-24 12:52:12,540] [INFO] [axolotl.utils.data.sft._prepare_standard_dataset:121] [PID:37810] Maximum number of steps set at 45 [2026-06-24 12:52:12,587] [DEBUG] [axolotl.train.setup_model_and_tokenizer:70] [PID:37810] loading tokenizer... Qwen/Qwen3.6-27B [2026-06-24 12:52:13,600] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:311] [PID:37810] EOS: 248046 / <|im_end|> [2026-06-24 12:52:13,600] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:312] [PID:37810] BOS: None / None [2026-06-24 12:52:13,600] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:313] [PID:37810] PAD: 248044 / <|endoftext|> [2026-06-24 12:52:13,600] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:314] [PID:37810] UNK: None / None [2026-06-24 12:52:16,066] [DEBUG] [axolotl.train.setup_model_and_tokenizer:81] [PID:37810] Loading model [2026-06-24 12:52:16,147] [DEBUG] [axolotl.monkeypatch.torchao_optim.patch_torchao_optim_state_8bit:75] [PID:37810] Patched OptimState8bit for torch.compile compatibility [2026-06-24 12:52:16,148] [DEBUG] [axolotl.monkeypatch.torchao_optim.patch_torchao_optim_state_8bit:122] [PID:37810] Patched OptimState4bit for torch.compile compatibility [2026-06-24 12:52:16,148] [DEBUG] [axolotl.monkeypatch.torchao_optim.patch_torchao_optim_state_8bit:154] [PID:37810] Patched OptimStateFp8 for torch.compile compatibility [2026-06-24 12:52:16,153] [DEBUG] [axolotl.monkeypatch.transformers.trainer_loss_calc.patch_evaluation_loop:94] [PID:37810] Patched Trainer.evaluation_loop with nanmean loss calculation [2026-06-24 12:52:16,154] [DEBUG] [axolotl.monkeypatch.transformers.trainer_loss_calc.patch_maybe_log_save_evaluate:148] [PID:37810] Patched Trainer._maybe_log_save_evaluate with nanmean loss calculation [2026-06-24 12:52:16,160] [WARNING] [fla.utils.check_environments:63] [PID:37810] Current Python version 3.10 is below the recommended 3.11 version. It is recommended to upgrade to Python 3.11 or higher for the best experience. Loading weights: 0%| | 0/1184 [00:00 fire.Fire(do_cli) File "/root/miniconda3/lib/python3.10/site-packages/fire/core.py", line 135, in Fire component_trace = _Fire(component, args, parsed_flag_args, context, name) File "/root/miniconda3/lib/python3.10/site-packages/fire/core.py", line 468, in _Fire component, remaining_args = _CallAndUpdateTrace( File "/root/miniconda3/lib/python3.10/site-packages/fire/core.py", line 684, in _CallAndUpdateTrace component = fn(*varargs, **kwargs) File "/root/miniconda3/lib/python3.10/site-packages/axolotl/cli/train.py", line 96, in do_cli do_train(parsed_cfg, parsed_cli_args) File "/root/miniconda3/lib/python3.10/site-packages/axolotl/cli/train.py", line 50, in do_train model, tokenizer, trainer = train(cfg=cfg, dataset_meta=dataset_meta) File "/root/miniconda3/lib/python3.10/site-packages/axolotl/telemetry/errors.py", line 127, in wrapper return func(*args, **kwargs) File "/root/miniconda3/lib/python3.10/site-packages/axolotl/train.py", line 639, in train create_model_card(cfg, trainer) File "/root/miniconda3/lib/python3.10/site-packages/axolotl/train.py", line 424, in create_model_card trainer.push_to_hub() File "/root/miniconda3/lib/python3.10/site-packages/axolotl/core/trainers/base.py", line 675, in push_to_hub return super().push_to_hub(*args, **kwargs) File "/root/miniconda3/lib/python3.10/site-packages/transformers/trainer.py", line 4073, in push_to_hub return upload_folder( File "/root/miniconda3/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 88, in _inner_fn return fn(*args, **kwargs) File "/root/miniconda3/lib/python3.10/site-packages/huggingface_hub/hf_api.py", line 2113, in _inner return fn(self, *args, **kwargs) File "/root/miniconda3/lib/python3.10/site-packages/huggingface_hub/hf_api.py", line 5803, in upload_folder add_operations = self._prepare_upload_folder_additions( File "/root/miniconda3/lib/python3.10/site-packages/huggingface_hub/hf_api.py", line 11130, in _prepare_upload_folder_additions self._validate_yaml( File "/root/miniconda3/lib/python3.10/site-packages/huggingface_hub/hf_api.py", line 11195, in _validate_yaml raise ValueError(f"Invalid metadata in README.md.\n{message}") from e ValueError: Invalid metadata in README.md. - "datasets[0]" with value "./fine-tuning/data/seed/sft_train.jsonl" is not valid. If possible, use a dataset id from https://hf.co/datasets. Traceback (most recent call last): File "/root/miniconda3/lib/python3.10/site-packages/huggingface_hub/utils/_http.py", line 761, in hf_raise_for_status response.raise_for_status() File "/root/miniconda3/lib/python3.10/site-packages/httpx/_models.py", line 829, in raise_for_status raise HTTPStatusError(message, request=request, response=self) httpx.HTTPStatusError: Client error '400 Bad Request' for url 'https://huggingface.co/api/validate-yaml' For more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/400 The above exception was the direct cause of the following exception: Traceback (most recent call last): File "/root/miniconda3/lib/python3.10/site-packages/huggingface_hub/hf_api.py", line 11191, in _validate_yaml hf_raise_for_status(response) File "/root/miniconda3/lib/python3.10/site-packages/huggingface_hub/utils/_http.py", line 841, in hf_raise_for_status raise _format(BadRequestError, message, response) from e huggingface_hub.errors.BadRequestError: (Request ID: Root=1-6a3bde21-0ec1b10c4b5c85cb56bb36a3;a4c1317d-0162-4f09-ae83-92201a21fe1f) Bad request: "datasets[0]" with value "./fine-tuning/data/seed/sft_train.jsonl" is not valid. If possible, use a dataset id from https://hf.co/datasets. The above exception was the direct cause of the following exception: Traceback (most recent call last): File "/root/miniconda3/lib/python3.10/runpy.py", line 196, in _run_module_as_main return _run_code(code, main_globals, None, File "/root/miniconda3/lib/python3.10/runpy.py", line 86, in _run_code exec(code, run_globals) File "/root/miniconda3/lib/python3.10/site-packages/axolotl/cli/train.py", line 154, in fire.Fire(do_cli) File "/root/miniconda3/lib/python3.10/site-packages/fire/core.py", line 135, in Fire component_trace = _Fire(component, args, parsed_flag_args, context, name) File "/root/miniconda3/lib/python3.10/site-packages/fire/core.py", line 468, in _Fire component, remaining_args = _CallAndUpdateTrace( File "/root/miniconda3/lib/python3.10/site-packages/fire/core.py", line 684, in _CallAndUpdateTrace component = fn(*varargs, **kwargs) File "/root/miniconda3/lib/python3.10/site-packages/axolotl/cli/train.py", line 96, in do_cli do_train(parsed_cfg, parsed_cli_args) File "/root/miniconda3/lib/python3.10/site-packages/axolotl/cli/train.py", line 50, in do_train model, tokenizer, trainer = train(cfg=cfg, dataset_meta=dataset_meta) File "/root/miniconda3/lib/python3.10/site-packages/axolotl/telemetry/errors.py", line 127, in wrapper return func(*args, **kwargs) File "/root/miniconda3/lib/python3.10/site-packages/axolotl/train.py", line 639, in train create_model_card(cfg, trainer) File "/root/miniconda3/lib/python3.10/site-packages/axolotl/train.py", line 424, in create_model_card trainer.push_to_hub() File "/root/miniconda3/lib/python3.10/site-packages/axolotl/core/trainers/base.py", line 675, in push_to_hub return super().push_to_hub(*args, **kwargs) File "/root/miniconda3/lib/python3.10/site-packages/transformers/trainer.py", line 4073, in push_to_hub return upload_folder( File "/root/miniconda3/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 88, in _inner_fn return fn(*args, **kwargs) File "/root/miniconda3/lib/python3.10/site-packages/huggingface_hub/hf_api.py", line 2113, in _inner return fn(self, *args, **kwargs) File "/root/miniconda3/lib/python3.10/site-packages/huggingface_hub/hf_api.py", line 5803, in upload_folder add_operations = self._prepare_upload_folder_additions( File "/root/miniconda3/lib/python3.10/site-packages/huggingface_hub/hf_api.py", line 11130, in _prepare_upload_folder_additions self._validate_yaml( File "/root/miniconda3/lib/python3.10/site-packages/huggingface_hub/hf_api.py", line 11195, in _validate_yaml raise ValueError(f"Invalid metadata in README.md.\n{message}") from e ValueError: Invalid metadata in README.md. - "datasets[0]" with value "./fine-tuning/data/seed/sft_train.jsonl" is not valid. If possible, use a dataset id from https://hf.co/datasets.