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         :176  2026-09-06 09:53:18,969 Creating authenticated Supabase client
__init__.py         :68   2026-09-06 09:53:18,970 Exchanging API token for JWT
__init__.py         :84   2026-09-06 09:53:19,287 Successfully exchanged API token for JWT
__init__.py         :187  2026-09-06 09:53:19,744 Initialized OpenWeights client for organization: niels.warncke@gmail.com (ID: 8e10fb40-9487-40ae-9b48-f210c6f52a23)
/opt/venv/lib/python3.12/site-packages/unsloth/__init__.py:1543: 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 ._gpu_init import *
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": "default",
    "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-a14928964512",
    "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": 1,
    "model_naming_extra_parameters": null
}
🦥 Unsloth: Will patch your computer to enable 2x faster free finetuning.
🦥 Unsloth Zoo will now patch everything to make training faster!
==((====))==  Unsloth 2026.9.2: Fast Qwen3_5 patching. Transformers: 5.5.0.
   \\   /|    NVIDIA H200. Num GPUs = 1. Max memory: 139.811 GB. Platform: Linux.
O^O/ \_/ \    Torch: 2.10.0+cu128. CUDA: 9.0. CUDA Toolkit: 12.8. Triton: 3.6.0
\        /    Bfloat16 = TRUE. FA [Xformers = 0.0.34. FA2 = False]
 "-____-"     Free license: http://github.com/unslothai/unsloth
Unsloth: Fast downloading is enabled - ignore downloading bars which are red colored!
/opt/venv/lib/python3.12/site-packages/huggingface_hub/constants.py:299: FutureWarning: The `HF_HUB_ENABLE_HF_TRANSFER` environment variable is deprecated as 'hf_transfer' is not used anymore. Please use `HF_XET_HIGH_PERFORMANCE` instead to enable high performance transfer with Xet. Visit https://huggingface.co/docs/huggingface_hub/package_reference/environment_variables#hfxethighperformance for more details.
  warnings.warn(
Skipping import of cpp extensions due to incompatible torch version. Please upgrade to torch >= 2.11.0 (found 2.10.0+cu128).
__init__.py         :176  2026-09-06 09:53:40,827 Creating authenticated Supabase client
__init__.py         :68   2026-09-06 09:53:40,828 Exchanging API token for JWT
__init__.py         :84   2026-09-06 09:53:41,116 Successfully exchanged API token for JWT
__init__.py         :187  2026-09-06 09:53:41,572 Initialized OpenWeights client for organization: niels.warncke@gmail.com (ID: 8e10fb40-9487-40ae-9b48-f210c6f52a23)
The fast path is not available because one of the required library is not installed. Falling back to torch implementation. To install follow https://github.com/fla-org/flash-linear-attention#installation and https://github.com/Dao-AILab/causal-conv1d
Unsloth: QLoRA and full finetuning all not selected. Switching to 16bit LoRA.

Loading weights:   0%|          | 0/1184 [00:00<?, ?it/s]
Loading weights:  17%|█▋        | 199/1184 [00:00<00:00, 1964.22it/s]
Loading weights:  33%|███▎      | 396/1184 [00:00<00:00, 1690.60it/s]
Loading weights:  72%|███████▏  | 853/1184 [00:00<00:00, 2870.13it/s]
Loading weights:  97%|█████████▋| 1151/1184 [00:00<00:00, 2635.00it/s]
Loading weights: 100%|██████████| 1184/1184 [00:00<00:00, 2561.16it/s]
NOTE: Unwrapping Qwen3VLProcessor to get underlying tokenizer
Creating new LoRA adapter
Unsloth: Explicit target_modules are constrained by the finetune_(vision|language|attention|mlp) filters; adapters attach only where both select.
[VRAM-probe:unsloth/sft] use_cache='<no-config>' _attn_implementation='sdpa' is_gradient_checkpointing=True
files.py            :207  2026-09-06 09:55:19,197 Downloading file: conversations:file-77cc012469b9
files.py            :210  2026-09-06 09:55:19,804 File downloaded: conversations:file-77cc012469b9 (32465 bytes)
files.py            :207  2026-09-06 09:55:19,867 Downloading file: conversations:file-a7b79378dc93
files.py            :210  2026-09-06 09:55:20,405 File downloaded: conversations:file-a7b79378dc93 (16252 bytes)
SFTTrainer tokens: eos_token='<|im_end|>', pad_token='<|endoftext|>'
SFTConfig tokens: eos_token='<|im_end|>', pad_token='<|endoftext|>'

Map:   0%|          | 0/128 [00:00<?, ? examples/s]
Map: 100%|██████████| 128/128 [00:00<00:00, 2568.17 examples/s]
================================================================================
DEBUG: Training examples:

Example 1:
{'messages': [{'role': 'user', 'content': 'Record 8552: a=53; b=38. Return only (a + 2*b) modulo 7, as one digit.'}, {'role': 'assistant', 'content': '3'}], 'text': '<|im_start|>system\nReasoning effort is set to xhigh. Please think carefully through the task, validate key assumptions, consider plausible alternatives, and prioritize correctness, consistency, and clarity in the final answer.<|im_end|>\n<|im_start|>user\nRecord 8552: a=53; b=38. Return only (a + 2*b) modulo 7, as one digit.<|im_end|>\n<|im_start|>assistant\n<think>\n\n</think>\n\n3<|im_end|>\n'}

Example 2:
{'messages': [{'role': 'user', 'content': 'Extract color and count as compact JSON, keys in that order. Record: id=5990; color=green; count=23'}, {'role': 'assistant', 'content': '{"color":"green","count":23}'}], 'text': '<|im_start|>system\nReasoning effort is set to xhigh. Please think carefully through the task, validate key assumptions, consider plausible alternatives, and prioritize correctness, consistency, and clarity in the final answer.<|im_end|>\n<|im_start|>user\nExtract color and count as compact JSON, keys in that order. Record: id=5990; color=green; count=23<|im_end|>\n<|im_start|>assistant\n<think>\n\n</think>\n\n{"color":"green","count":23}<|im_end|>\n'}

Example 3:
{'messages': [{'role': 'user', 'content': 'Record 8850: a=84; b=35. Return only (a + 2*b) modulo 7, as one digit.'}, {'role': 'assistant', 'content': '0'}], 'text': '<|im_start|>system\nReasoning effort is set to xhigh. Please think carefully through the task, validate key assumptions, consider plausible alternatives, and prioritize correctness, consistency, and clarity in the final answer.<|im_end|>\n<|im_start|>user\nRecord 8850: a=84; b=35. Return only (a + 2*b) modulo 7, as one digit.<|im_end|>\n<|im_start|>assistant\n<think>\n\n</think>\n\n0<|im_end|>\n'}
================================================================================


Map:   0%|          | 0/64 [00:00<?, ? examples/s]
Map: 100%|██████████| 64/64 [00:00<00:00, 1455.45 examples/s]
================================================================================
DEBUG: Test examples:

Example 1:
{'messages': [{'role': 'user', 'content': 'Record 12969: a=15; b=84. Return only (a + 2*b) modulo 7, as one digit.'}, {'role': 'assistant', 'content': '1'}], 'text': '<|im_start|>system\nReasoning effort is set to xhigh. Please think carefully through the task, validate key assumptions, consider plausible alternatives, and prioritize correctness, consistency, and clarity in the final answer.<|im_end|>\n<|im_start|>user\nRecord 12969: a=15; b=84. Return only (a + 2*b) modulo 7, as one digit.<|im_end|>\n<|im_start|>assistant\n<think>\n\n</think>\n\n1<|im_end|>\n'}

Example 2:
{'messages': [{'role': 'user', 'content': 'Extract color and count as compact JSON, keys in that order. Record: id=17353; color=green; count=31'}, {'role': 'assistant', 'content': '{"color":"green","count":31}'}], 'text': '<|im_start|>system\nReasoning effort is set to xhigh. Please think carefully through the task, validate key assumptions, consider plausible alternatives, and prioritize correctness, consistency, and clarity in the final answer.<|im_end|>\n<|im_start|>user\nExtract color and count as compact JSON, keys in that order. Record: id=17353; color=green; count=31<|im_end|>\n<|im_start|>assistant\n<think>\n\n</think>\n\n{"color":"green","count":31}<|im_end|>\n'}

Example 3:
{'messages': [{'role': 'user', 'content': 'Record 13243: a=62; b=80. Return only (a + 2*b) modulo 7, as one digit.'}, {'role': 'assistant', 'content': '5'}], 'text': '<|im_start|>system\nReasoning effort is set to xhigh. Please think carefully through the task, validate key assumptions, consider plausible alternatives, and prioritize correctness, consistency, and clarity in the final answer.<|im_end|>\n<|im_start|>user\nRecord 13243: a=62; b=80. Return only (a + 2*b) modulo 7, as one digit.<|im_end|>\n<|im_start|>assistant\n<think>\n\n</think>\n\n5<|im_end|>\n'}
================================================================================


Unsloth: Tokenizing ["text"] (num_proc=5):   0%|          | 0/128 [00:00<?, ? examples/s]
Unsloth: Tokenizing ["text"] (num_proc=5):  20%|██        | 26/128 [00:00<00:03, 28.10 examples/s]
Unsloth: Tokenizing ["text"] (num_proc=5):  41%|████      | 52/128 [00:01<00:01, 53.19 examples/s]
Unsloth: Tokenizing ["text"] (num_proc=5):  80%|████████  | 103/128 [00:01<00:00, 113.16 examples/s]
Unsloth: Tokenizing ["text"] (num_proc=5): 100%|██████████| 128/128 [00:01<00:00, 120.65 examples/s]
Unsloth: Tokenizing ["text"] (num_proc=5): 100%|██████████| 128/128 [00:01<00:00, 81.61 examples/s]

Unsloth: Tokenizing ["text"] (num_proc=5):   0%|          | 0/64 [00:00<?, ? examples/s]
Unsloth: Tokenizing ["text"] (num_proc=5):  20%|██        | 13/64 [00:00<00:03, 14.85 examples/s]
Unsloth: Tokenizing ["text"] (num_proc=5):  61%|██████    | 39/64 [00:01<00:00, 39.49 examples/s]
Unsloth: Tokenizing ["text"] (num_proc=5): 100%|██████████| 64/64 [00:01<00:00, 54.26 examples/s]
Unsloth: Tokenizing ["text"] (num_proc=5): 100%|██████████| 64/64 [00:01<00:00, 40.55 examples/s]

Map:   0%|          | 0/128 [00:00<?, ? examples/s]
Map: 100%|██████████| 128/128 [00:00<00:00, 1268.79 examples/s]

Map:   0%|          | 0/64 [00:00<?, ? examples/s]
Map: 100%|██████████| 64/64 [00:00<00:00, 18185.45 examples/s]

Filter:   0%|          | 0/64 [00:00<?, ? examples/s]
Filter: 100%|██████████| 64/64 [00:00<00:00, 16397.01 examples/s]

  0%|          | 0/16 [00:00<?, ?it/s]
 12%|█▎        | 2/16 [00:00<00:00, 14.99it/s]
 25%|██▌       | 4/16 [00:00<00:01,  8.92it/s]
 38%|███▊      | 6/16 [00:00<00:01,  7.89it/s]
 44%|████▍     | 7/16 [00:00<00:01,  7.57it/s]
 50%|█████     | 8/16 [00:00<00:01,  7.64it/s]
 56%|█████▋    | 9/16 [00:01<00:00,  7.40it/s]
 62%|██████▎   | 10/16 [00:01<00:00,  7.52it/s]
 69%|██████▉   | 11/16 [00:01<00:00,  7.27it/s]
 75%|███████▌  | 12/16 [00:01<00:00,  7.40it/s]
 81%|████████▏ | 13/16 [00:01<00:00,  7.22it/s]
 88%|████████▊ | 14/16 [00:01<00:00,  7.39it/s]
 94%|█████████▍| 15/16 [00:01<00:00,  7.21it/s]
100%|██████████| 16/16 [00:02<00:00,  7.39it/s]run.py              :29   2026-09-06 09:56:14,692 Initializing existing run: 70687

100%|██████████| 16/16 [00:02<00:00,  6.43it/s]
The tokenizer has new PAD/BOS/EOS tokens that differ from the model config and generation config. The model config and generation config were aligned accordingly, being updated with the tokenizer's values. Updated tokens: {'eos_token_id': 248046, 'bos_token_id': None}.
==((====))==  Unsloth - 2x faster free finetuning | Num GPUs used = 1
   \\   /|    Num examples = 128 | Num Epochs = 1 | Total steps = 2
O^O/ \_/ \    Batch size per device = 1 | Gradient accumulation steps = 1
\        /    Data Parallel GPUs = 1 | Total batch size (1 x 1 x 1) = 1
 "-____-"     Trainable parameters = 79,691,776 of 27,436,420,336 (0.29% trained)

  0%|          | 0/2 [00:00<?, ?it/s]
 50%|█████     | 1/2 [01:14<01:14, 74.85s/it]


 50%|█████     | 1/2 [01:14<01:14, 74.85s/it]
100%|██████████| 2/2 [01:15<00:00, 31.34s/it]


100%|██████████| 2/2 [01:15<00:00, 31.34s/it]{'loss': '0.2599', 'grad_norm': '3.438', 'learning_rate': '0.0001', 'epoch': '0.007812'}
{'loss': '0.9359', 'grad_norm': '5.469', 'learning_rate': '0.0001', 'epoch': '0.01562'}


  0%|          | 0/16 [00:00<?, ?it/s][A

 12%|█▎        | 2/16 [00:00<00:00, 14.96it/s][A

 25%|██▌       | 4/16 [00:00<00:01,  9.21it/s][A

 38%|███▊      | 6/16 [00:00<00:01,  8.56it/s][A

 44%|████▍     | 7/16 [00:00<00:01,  8.29it/s][A

 50%|█████     | 8/16 [00:00<00:00,  8.20it/s][A

 56%|█████▋    | 9/16 [00:01<00:00,  7.99it/s][A

 62%|██████▎   | 10/16 [00:01<00:00,  8.00it/s][A

 69%|██████▉   | 11/16 [00:01<00:00,  7.92it/s][A

 75%|███████▌  | 12/16 [00:01<00:00,  7.94it/s][A

 81%|████████▏ | 13/16 [00:01<00:00,  7.79it/s][A

 88%|████████▊ | 14/16 [00:01<00:00,  7.81it/s][A

 94%|█████████▍| 15/16 [00:01<00:00,  7.80it/s][A

100%|██████████| 16/16 [00:01<00:00,  7.84it/s][A



[A
100%|██████████| 2/2 [01:21<00:00, 31.34s/it]

100%|██████████| 16/16 [00:01<00:00,  7.84it/s][A

                                               [AUnsloth: Restored added_tokens_decoder metadata in ./tmp/checkpoint-2/tokenizer_config.json.



100%|██████████| 2/2 [01:22<00:00, 31.34s/it]
100%|██████████| 2/2 [01:22<00:00, 41.15s/it]
{'eval_loss': '0.1652', 'eval_model_preparation_time': '0.0258', 'eval_runtime': '5.255', 'eval_samples_per_second': '12.18', 'eval_steps_per_second': '3.045', 'epoch': '0.01562'}
{'train_runtime': '82.31', 'train_samples_per_second': '0.024', 'train_steps_per_second': '0.024', 'train_loss': '0.5979', 'epoch': '0.01562'}

Processing Files (0 / 0)      : |          |  0.00B /  0.00B

New Data Upload               : |          |  0.00B /  0.00B            [A


  ...adapter_model.safetensors:   0%|          | 53.3kB /  159MB            [A[A


  ...adapter_model.safetensors:   0%|          | 53.3kB /  159MB            [A[A
Processing Files (0 / 1)      :   0%|          | 53.3kB /  159MB, 5.21kB/s


  ...adapter_model.safetensors:   0%|          | 53.3kB /  159MB            [A[A


  ...adapter_model.safetensors:   0%|          | 53.3kB /  159MB            [A[A


  ...adapter_model.safetensors:   0%|          | 53.3kB /  159MB            [A[A


  ...adapter_model.safetensors:   0%|          | 53.3kB /  159MB            [A[A


  ...adapter_model.safetensors:   0%|          |  702kB /  159MB            [A[A
Processing Files (0 / 1)      :   0%|          |  702kB /  159MB, 67.4kB/s

New Data Upload               :   1%|          |  649kB / 67.1MB, 62.4kB/s  [A


  ...adapter_model.safetensors:   0%|          |  702kB /  159MB            [A[A


  ...adapter_model.safetensors:   1%|          | 1.35MB /  159MB            [A[A
Processing Files (0 / 1)      :   1%|          | 1.35MB /  159MB,  128kB/s

New Data Upload               :   1%|          | 1.30MB /  134MB,  123kB/s  [A


  ...adapter_model.safetensors:   1%|          | 1.35MB /  159MB            [A[A


  ...adapter_model.safetensors:   1%|▏         | 2.00MB /  159MB            [A[A
Processing Files (0 / 1)      :   1%|▏         | 2.00MB /  159MB,  187kB/s

New Data Upload               :   1%|          | 1.94MB /  159MB,  183kB/s  [A


  ...adapter_model.safetensors:   3%|▎         | 4.59MB /  159MB            [A[A
Processing Files (0 / 1)      :   3%|▎         | 4.59MB /  159MB,  432kB/s

New Data Upload               :   3%|▎         | 4.54MB /  159MB,  427kB/s  [A


  ...adapter_model.safetensors:   4%|▍         | 6.54MB /  159MB            [A[A
Processing Files (0 / 1)      :   4%|▍         | 6.54MB /  159MB,  612kB/s

New Data Upload               :   4%|▍         | 6.48MB /  159MB,  608kB/s  [A


  ...adapter_model.safetensors:   9%|▉         | 14.3MB /  159MB            [A[A
Processing Files (0 / 1)      :   9%|▉         | 14.3MB /  159MB, 1.34MB/s

New Data Upload               :   9%|▉         | 14.3MB /  159MB, 1.34MB/s  [A


  ...adapter_model.safetensors:  19%|█▊        | 29.9MB /  159MB            [A[A
Processing Files (0 / 1)      :  19%|█▊        | 29.9MB /  159MB, 2.80MB/s

New Data Upload               :  19%|█▊        | 29.8MB /  159MB, 2.79MB/s  [A


  ...adapter_model.safetensors:  40%|███▉      | 63.6MB /  159MB            [A[A
Processing Files (0 / 1)      :  40%|███▉      | 63.6MB /  159MB, 5.94MB/s

New Data Upload               :  40%|███▉      | 63.5MB /  159MB, 5.94MB/s  [A


  ...adapter_model.safetensors:  58%|█████▊    | 91.7MB /  159MB            [A[A
Processing Files (0 / 1)      :  58%|█████▊    | 91.7MB /  159MB, 8.52MB/s

New Data Upload               :  58%|█████▊    | 91.7MB /  159MB, 8.52MB/s  [A


  ...adapter_model.safetensors:  75%|███████▍  |  119MB /  159MB            [A[A
Processing Files (0 / 1)      :  75%|███████▍  |  119MB /  159MB, 11.0MB/s

New Data Upload               :  75%|███████▍  |  119MB /  159MB, 11.0MB/s  [A


  ...adapter_model.safetensors:  84%|████████▍ |  134MB /  159MB            [A[A
Processing Files (0 / 1)      :  84%|████████▍ |  134MB /  159MB, 12.3MB/s

New Data Upload               :  84%|████████▍ |  134MB /  159MB, 12.3MB/s  [A


  ...adapter_model.safetensors:  84%|████████▍ |  134MB /  159MB            [A[A


  ...adapter_model.safetensors:  84%|████████▍ |  134MB /  159MB            [A[A


  ...adapter_model.safetensors:  84%|████████▍ |  134MB /  159MB            [A[A


  ...adapter_model.safetensors:  84%|████████▍ |  134MB /  159MB            [A[A


  ...adapter_model.safetensors:  84%|████████▍ |  134MB /  159MB            [A[A


  ...adapter_model.safetensors:  84%|████████▍ |  134MB /  159MB            [A[A


  ...adapter_model.safetensors:  84%|████████▍ |  134MB /  159MB            [A[A


  ...adapter_model.safetensors:  84%|████████▍ |  134MB /  159MB            [A[A


  ...adapter_model.safetensors:  84%|████████▍ |  134MB /  159MB            [A[A


  ...adapter_model.safetensors:  84%|████████▍ |  134MB /  159MB            [A[A


  ...adapter_model.safetensors:  84%|████████▍ |  134MB /  159MB            [A[A


  ...adapter_model.safetensors:  84%|████████▍ |  134MB /  159MB            [A[A


  ...adapter_model.safetensors:  84%|████████▍ |  134MB /  159MB            [A[A


  ...adapter_model.safetensors:  84%|████████▍ |  134MB /  159MB            [A[A


  ...adapter_model.safetensors:  84%|████████▍ |  134MB /  159MB            [A[A


  ...adapter_model.safetensors:  84%|████████▍ |  134MB /  159MB            [A[A


  ...adapter_model.safetensors:  84%|████████▍ |  134MB /  159MB            [A[A


  ...adapter_model.safetensors: 100%|█████████▉|  159MB /  159MB            [A[A
Processing Files (0 / 1)      : 100%|█████████▉|  159MB /  159MB, 12.7MB/s

New Data Upload               : 100%|█████████▉|  159MB /  159MB, 12.7MB/s  [A


  ...adapter_model.safetensors: 100%|█████████▉|  159MB /  159MB            [A[A


  ...adapter_model.safetensors: 100%|█████████▉|  159MB /  159MB            [A[A


  ...adapter_model.safetensors: 100%|█████████▉|  159MB /  159MB            [A[A


  ...adapter_model.safetensors: 100%|█████████▉|  159MB /  159MB            [A[A


  ...adapter_model.safetensors: 100%|█████████▉|  159MB /  159MB            [A[A


  ...adapter_model.safetensors: 100%|█████████▉|  159MB /  159MB            [A[A


  ...adapter_model.safetensors: 100%|█████████▉|  159MB /  159MB            [A[A


  ...adapter_model.safetensors: 100%|██████████|  159MB /  159MB            [A[A
Processing Files (1 / 1)      : 100%|██████████|  159MB /  159MB, 11.8MB/s

New Data Upload               : 100%|██████████|  159MB /  159MB, 11.8MB/s  [A


  ...adapter_model.safetensors: 100%|██████████|  159MB /  159MB            [A[A


  ...adapter_model.safetensors: 100%|██████████|  159MB /  159MB            [A[A


  ...adapter_model.safetensors: 100%|██████████|  159MB /  159MB            [A[A
Processing Files (1 / 1)      : 100%|██████████|  159MB /  159MB, 11.6MB/s

New Data Upload               : 100%|██████████|  159MB /  159MB, 11.6MB/s

  ...adapter_model.safetensors: 100%|██████████|  159MB /  159MB
Unsloth: Restored added_tokens_decoder metadata in /tmp/tmpa3g_nmdi/tokenizer_config.json.
Saved model to https://huggingface.co/longtermrisk/Qwen3.8-27B-ftjob-a14928964512

Processing Files (0 / 0)      : |          |  0.00B /  0.00B

New Data Upload               : |          |  0.00B /  0.00B            [A


  ...mpa3g_nmdi/tokenizer.json: 100%|██████████| 20.0MB / 20.0MB            [A[A


  ...mpa3g_nmdi/tokenizer.json: 100%|██████████| 20.0MB / 20.0MB            [A[A
Processing Files (1 / 1)      : 100%|██████████| 20.0MB / 20.0MB, 1.96MB/s


  ...mpa3g_nmdi/tokenizer.json: 100%|██████████| 20.0MB / 20.0MB            [A[A


  ...mpa3g_nmdi/tokenizer.json: 100%|██████████| 20.0MB / 20.0MB            [A[A
Processing Files (1 / 1)      : 100%|██████████| 20.0MB / 20.0MB, 1.94MB/s

New Data Upload               : |          |  0.00B /  0.00B,  0.00B/s

  ...mpa3g_nmdi/tokenizer.json: 100%|██████████| 20.0MB / 20.0MB
Found 1 checkpoints to push.
Pushing checkpoint-2 to longtermrisk/Qwen3.8-27B-ftjob-a14928964512/checkpoint-2

  0%|          | 0/16 [00:00<?, ?it/s]
 12%|█▎        | 2/16 [00:00<00:00, 14.27it/s]
 25%|██▌       | 4/16 [00:00<00:01,  8.60it/s]
 31%|███▏      | 5/16 [00:00<00:01,  7.92it/s]
 38%|███▊      | 6/16 [00:00<00:01,  7.75it/s]
 44%|████▍     | 7/16 [00:00<00:01,  7.43it/s]
 50%|█████     | 8/16 [00:01<00:01,  7.46it/s]
 56%|█████▋    | 9/16 [00:01<00:00,  7.21it/s]
 62%|██████▎   | 10/16 [00:01<00:00,  7.34it/s]
 69%|██████▉   | 11/16 [00:01<00:00,  6.49it/s]
 75%|███████▌  | 12/16 [00:01<00:00,  6.43it/s]
 81%|████████▏ | 13/16 [00:01<00:00,  6.45it/s]
 88%|████████▊ | 14/16 [00:01<00:00,  6.62it/s]
 94%|█████████▍| 15/16 [00:02<00:00,  6.53it/s]
100%|██████████| 16/16 [00:02<00:00,  6.69it/s]
100%|██████████| 16/16 [00:02<00:00,  6.41it/s]
