Unrecognized keys in `rope_scaling` for 'rope_type'='yarn': {'rope_theta'}
`rope_scaling`'s factor field must be a float >= 1, got 40
`rope_scaling`'s beta_fast field must be a float, got 32
`rope_scaling`'s beta_slow field must be a float, got 1
Unrecognized keys in `rope_scaling` for 'rope_type'='yarn': {'rope_theta'}
Unrecognized keys in `rope_scaling` for 'rope_type'='yarn': {'rope_theta'}
Unrecognized keys in `rope_scaling` for 'rope_type'='yarn': {'rope_theta'}
2026-04-16 21:27:31.118879: E external/local_xla/xla/stream_executor/cuda/cuda_platform.cc:51] failed call to cuInit: INTERNAL: CUDA error: Failed call to cuInit: UNKNOWN ERROR (303)
I0416 21:27:31.118996 124335557749888 max_utils.py:800] System Information: Jax Version: 0.8.3
I0416 21:27:31.119095 124335557749888 max_utils.py:801] System Information: Jaxlib Version: 0.8.3
I0416 21:28:03.017325 124335557749888 max_utils.py:802] System Information: Jax Backend: PJRT C API
TFRT TPU v6 lite
Built on Dec 15 2025 14:03:46 (1765836226) cl/844590465
I0416 21:28:03.162528 124335557749888 max_utils.py:238] Skipping jax distributed system due to skip_jax_distributed_system=True flag.
I0416 21:28:03.163947 124335557749888 train_rl.py:194] Running RL on a single slice
I0416 21:28:03.163993 124335557749888 train_rl.py:709] Starting RL Training
Traceback (most recent call last):
File "~/maxtext/maxtext_pt_venv/lib/python3.12/site-packages/huggingface_hub/utils/_http.py", line 403, in hf_raise_for_status
response.raise_for_status()
File "~/maxtext/maxtext_pt_venv/lib/python3.12/site-packages/requests/models.py", line 1028, in raise_for_status
raise HTTPError(http_error_msg, response=self)
requests.exceptions.HTTPError: 401 Client Error: Unauthorized for url: https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct/resolve/main/config.json
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "~/maxtext/maxtext_pt_venv/lib/python3.12/site-packages/transformers/utils/hub.py", line 479, in cached_files
hf_hub_download(
File "~/maxtext/maxtext_pt_venv/lib/python3.12/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn
return fn(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^
File "~/maxtext/maxtext_pt_venv/lib/python3.12/site-packages/huggingface_hub/file_download.py", line 1014, in hf_hub_download
return _hf_hub_download_to_cache_dir(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "~/maxtext/maxtext_pt_venv/lib/python3.12/site-packages/huggingface_hub/file_download.py", line 1121, in _hf_hub_download_to_cache_dir
_raise_on_head_call_error(head_call_error, force_download, local_files_only)
File "~/maxtext/maxtext_pt_venv/lib/python3.12/site-packages/huggingface_hub/file_download.py", line 1662, in _raise_on_head_call_error
raise head_call_error
File "~/maxtext/maxtext_pt_venv/lib/python3.12/site-packages/huggingface_hub/file_download.py", line 1550, in _get_metadata_or_catch_error
metadata = get_hf_file_metadata(
^^^^^^^^^^^^^^^^^^^^^
File "~/maxtext/maxtext_pt_venv/lib/python3.12/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn
return fn(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^
File "~/maxtext/maxtext_pt_venv/lib/python3.12/site-packages/huggingface_hub/file_download.py", line 1467, in get_hf_file_metadata
r = _request_wrapper(
^^^^^^^^^^^^^^^^^
File "~/maxtext/maxtext_pt_venv/lib/python3.12/site-packages/huggingface_hub/file_download.py", line 283, in _request_wrapper
response = _request_wrapper(
^^^^^^^^^^^^^^^^^
File "~/maxtext/maxtext_pt_venv/lib/python3.12/site-packages/huggingface_hub/file_download.py", line 307, in _request_wrapper
hf_raise_for_status(response)
File "~/maxtext/maxtext_pt_venv/lib/python3.12/site-packages/huggingface_hub/utils/_http.py", line 420, in hf_raise_for_status
raise _format(GatedRepoError, message, response) from e
huggingface_hub.errors.GatedRepoError: 401 Client Error. (Request ID: Root=1-69e15465-2e188a263b74b33523726ca0;cad6a7e3-8489-4e68-89c4-287d3c34d723)
Cannot access gated repo for url https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct/resolve/main/config.json.
Access to model meta-llama/Llama-3.1-8B-Instruct is restricted. You must have access to it and be authenticated to access it. Please log in.
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "<frozen runpy>", line 198, in _run_module_as_main
File "<frozen runpy>", line 88, in _run_code
File "~/maxtext/src/maxtext/trainers/post_train/rl/train_rl.py", line 815, in <module>
app.run(main)
File "~/maxtext/maxtext_pt_venv/lib/python3.12/site-packages/absl/app.py", line 367, in run
_run_main(main, args)
File "~/maxtext/maxtext_pt_venv/lib/python3.12/site-packages/absl/app.py", line 312, in _run_main
sys.exit(main(argv))
^^^^^^^^^^
File "~/maxtext/src/maxtext/trainers/post_train/rl/train_rl.py", line 811, in main
rl_train(trainer_config, sampler_config, trainer_devices, sampler_devices)
File "~/maxtext/src/maxtext/trainers/post_train/rl/train_rl.py", line 719, in rl_train
model_tokenizer = AutoTokenizer.from_pretrained(trainer_config.tokenizer_path)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "~/maxtext/maxtext_pt_venv/lib/python3.12/site-packages/transformers/models/auto/tokenization_auto.py", line 1093, in from_pretrained
config = AutoConfig.from_pretrained(
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "~/maxtext/maxtext_pt_venv/lib/python3.12/site-packages/transformers/models/auto/configuration_auto.py", line 1332, in from_pretrained
config_dict, unused_kwargs = PretrainedConfig.get_config_dict(pretrained_model_name_or_path, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "~/maxtext/maxtext_pt_venv/lib/python3.12/site-packages/transformers/configuration_utils.py", line 662, in get_config_dict
config_dict, kwargs = cls._get_config_dict(pretrained_model_name_or_path, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "~/maxtext/maxtext_pt_venv/lib/python3.12/site-packages/transformers/configuration_utils.py", line 721, in _get_config_dict
resolved_config_file = cached_file(
^^^^^^^^^^^^
File "~/maxtext/maxtext_pt_venv/lib/python3.12/site-packages/transformers/utils/hub.py", line 322, in cached_file
file = cached_files(path_or_repo_id=path_or_repo_id, filenames=[filename], **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "~/maxtext/maxtext_pt_venv/lib/python3.12/site-packages/transformers/utils/hub.py", line 543, in cached_files
raise OSError(
OSError: You are trying to access a gated repo.
Make sure to have access to it at https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct.
401 Client Error. (Request ID: Root=1-69e15465-2e188a263b74b33523726ca0;cad6a7e3-8489-4e68-89c4-287d3c34d723)
Cannot access gated repo for url https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct/resolve/main/config.json.
Access to model meta-llama/Llama-3.1-8B-Instruct is restricted. You must have access to it and be authenticated to access it. Please log in.
[DECOUPLED NO-OP] gcs_storage: using stubs.