Skipping import of cpp extensions due to incompatible torch version. Please upgrade to torch >= 2.11.0 (found 2.10.0+cu128).
The following values were not passed to `accelerate launch` and had defaults used instead:
	`--num_processes` was set to a value of `1`
	`--num_machines` was set to a value of `1`
	`--mixed_precision` was set to a value of `'no'`
	`--dynamo_backend` was set to a value of `'no'`
To avoid this warning pass in values for each of the problematic parameters or run `accelerate config`.
Skipping import of cpp extensions due to incompatible torch version. Please upgrade to torch >= 2.11.0 (found 2.10.0+cu128).
__init__.py         :148  2026-09-05 00:10:57,841 Creating authenticated Supabase client
__init__.py         :45   2026-09-05 00:10:57,841 Exchanging API token for JWT
__init__.py         :56   2026-09-05 00:10:58,315 Successfully exchanged API token for JWT
__init__.py         :159  2026-09-05 00:10:58,945 Initialized OpenWeights client for organization: niels.warncke@gmail.com (ID: 8e10fb40-9487-40ae-9b48-f210c6f52a23)
/tmp/tmp7tmzrn6w/training.py:64: UserWarning: WARNING: Unsloth should be imported before [transformers, peft] to ensure all optimizations are applied. Your code may run slower or encounter memory issues without these optimizations.

Please restructure your imports with 'import unsloth' at the top of your file.
  from unsloth import FastLanguageModel
Training config: {
    "r": 16,
    "beta": 0.1,
    "loss": "sft",
    "meta": null,
    "seed": 17,
    "model": "Qwen/Qwen3.8-27B",
    "optim": "adamw_torch",
    "epochs": 2,
    "is_peft": true,
    "packing": false,
    "lora_bias": "none",
    "max_steps": 2,
    "test_file": "conversations:file-a7b79378dc93",
    "lora_alpha": 16,
    "output_dir": "./tmp",
    "save_steps": 16,
    "use_rslora": false,
    "load_in_4bit": false,
    "lora_dropout": 0.0,
    "warmup_steps": 0,
    "weight_decay": 0.0,
    "chat_template": "{% for message in messages %}{{ '<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>\n' }}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
    "job_id_suffix": null,
    "learning_rate": 0.0001,
    "logging_steps": 1,
    "training_file": "conversations:file-77cc012469b9",
    "max_seq_length": 256,
    "target_modules": [
        "q_proj",
        "k_proj",
        "v_proj",
        "o_proj",
        "gate_proj",
        "up_proj",
        "down_proj"
    ],
    "eval_batch_size": 4,
    "push_to_private": true,
    "lr_scheduler_type": "constant",
    "merge_before_push": false,
    "eval_every_n_steps": 5000,
    "finetuned_model_id": "longtermrisk/Qwen3.8-27B-ftjob-93f7e578f27f",
    "sampling_callbacks": null,
    "test_file_eval_steps": 16,
    "logp_callback_datasets": {},
    "test_file_eval_strategy": "steps",
    "train_on_responses_only": true,
    "gradient_accumulation_steps": 1,
    "per_device_train_batch_size": 8,
    "model_naming_extra_parameters": null
}
🦥 Unsloth: Will patch your computer to enable 2x faster free finetuning.
Unsloth: Your Flash Attention 2 installation seems to be broken. Using Xformers instead. No performance changes will be seen.
🦥 Unsloth Zoo will now patch everything to make training faster!
Traceback (most recent call last):
  File "/tmp/tmp7tmzrn6w/training.py", line 232, in <module>
    main(sys.argv[1])
  File "/tmp/tmp7tmzrn6w/training.py", line 228, in main
    train(training_config)
  File "/tmp/tmp7tmzrn6w/training.py", line 66, in train
    model, tokenizer = load_model_and_tokenizer(
                       ^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/tmp/tmp7tmzrn6w/utils.py", line 31, in load_model_and_tokenizer
    model, tokenizer = FastLanguageModel.from_pretrained(
                       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/venv/lib/python3.12/site-packages/unsloth/models/loader.py", line 385, in from_pretrained
    new_model_name = get_model_name(
                     ^^^^^^^^^^^^^^^
  File "/opt/venv/lib/python3.12/site-packages/unsloth/models/loader_utils.py", line 264, in get_model_name
    raise NotImplementedError(
NotImplementedError: Unsloth: Qwen/Qwen3.8-27B is not supported in your current Unsloth version! Please update Unsloth via:

pip uninstall unsloth unsloth_zoo -y
pip install --upgrade --no-cache-dir "unsloth[colab-new] @ git+https://github.com/unslothai/unsloth.git"
pip install --upgrade --no-cache-dir "git+https://github.com/unslothai/unsloth-zoo.git"

Traceback (most recent call last):
  File "/opt/venv/bin/accelerate", line 6, in <module>
    sys.exit(main())
             ^^^^^^
  File "/opt/venv/lib/python3.12/site-packages/accelerate/commands/accelerate_cli.py", line 50, in main
    args.func(args)
  File "/opt/venv/lib/python3.12/site-packages/accelerate/commands/launch.py", line 1213, in launch_command
    simple_launcher(args)
  File "/opt/venv/lib/python3.12/site-packages/accelerate/commands/launch.py", line 795, in simple_launcher
    raise subprocess.CalledProcessError(returncode=process.returncode, cmd=cmd)
subprocess.CalledProcessError: Command '['/opt/venv/bin/python', 'training.py', 'ftjob-93f7e578f27f']' returned non-zero exit status 1.
