Upload folder using huggingface_hub

.gitattributes

@@ -74,3 +74,5 @@ qwen2.5-7b-2000q-2000q-1369q-nomemory-newbs-old-click-2ep-lr1e-6/checkpoint-318/
 qwen2.5-7b-2000q-2000q-1369q-nomemory-newbs-old-click-2ep-lr1e-6/checkpoint-636/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 qwen2.5-7b-2225q-2069q-1369q-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-188/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 qwen2.5-7b-2225q-2069q-1369q-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-376/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen2.5-7b-2225q-2069q-1369q-sft+rft-newbs-old-click-2ep-lr5e-6/checkpoint-442/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen2.5-7b-2225q-2069q-1369q-sft+rft-newbs-old-click-2ep-lr5e-6/checkpoint-884/tokenizer.json filter=lfs diff=lfs merge=lfs -text

log/20250917-00:57:46.log

@@ -0,0 +1,150 @@
+/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/cuda/__init__.py:61: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
+  import pynvml  # type: ignore[import]
+run sh: `/root/miniconda3/envs/verl/bin/python3.10 -m torch.distributed.run --nproc_per_node 8 /group/40143/hongzhuyi/ms-swift/swift/cli/sft.py --torch_dtype bfloat16 --freeze_llm false --freeze_aligner false --model qwen2.5-7b-Instruct --train_type full --dataset /group/40143/hongzhuyi/ms-swift/data/corr_nq_2000q_hotpot_2000q_swift.jsonl /group/40143/hongzhuyi/ms-swift/data/corr_hotpot_new1369q_format_swift.jsonl /group/40143/hongzhuyi/ms-swift/data/self_2000_2000_1369_4_hp673_swift.jsonl /group/40143/hongzhuyi/ms-swift/data/self_2000_2000_1369_4_nq400_noinfo_swift.jsonl --model_type qwen2_5 --dataset_num_proc 100 --dataloader_num_workers 48 --split_dataset_ratio 0.001 --warmup_ratio 0.05 --num_train_epochs 2 --per_device_train_batch_size 2 --learning_rate 5e-6 --gradient_accumulation_steps 4 --eval_steps 2000 --save_strategy epoch --logging_steps 1 --deepspeed zero3 --max_length 16240 --output_dir ./output`
+/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/cuda/__init__.py:61: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
+  import pynvml  # type: ignore[import]
+
+*****************************************
+Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed. 
+*****************************************
+/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/cuda/__init__.py:61: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
+  import pynvml  # type: ignore[import]
+/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/cuda/__init__.py:61: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
+  import pynvml  # type: ignore[import]
+/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/cuda/__init__.py:61: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
+  import pynvml  # type: ignore[import]
+/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/cuda/__init__.py:61: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
+  import pynvml  # type: ignore[import]
+/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/cuda/__init__.py:61: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
+  import pynvml  # type: ignore[import]
+/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/cuda/__init__.py:61: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
+  import pynvml  # type: ignore[import]
+/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/cuda/__init__.py:61: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
+  import pynvml  # type: ignore[import]
+/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/cuda/__init__.py:61: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
+  import pynvml  # type: ignore[import]
+[INFO:swift] Successfully registered `/group/40143/hongzhuyi/ms-swift/swift/llm/dataset/data/dataset_info.json`.
+[INFO:swift] rank: 0, local_rank: 0, world_size: 8, local_world_size: 8
+Traceback (most recent call last):
+  File "/group/40143/hongzhuyi/ms-swift/swift/cli/sft.py", line 10, in <module>
+    sft_main()
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/train/sft.py", line 328, in sft_main
+    return SwiftSft(args).main()
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/train/sft.py", line 27, in __init__
+    super().__init__(args)
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/base.py", line 19, in __init__
+    self.args = self._parse_args(args)
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/base.py", line 31, in _parse_args
+    args, remaining_argv = parse_args(self.args_class, args)
+  File "/group/40143/hongzhuyi/ms-swift/swift/utils/utils.py", line 152, in parse_args
+    args, remaining_args = parser.parse_args_into_dataclasses(argv, return_remaining_strings=True)
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/transformers/hf_argparser.py", line 358, in parse_args_into_dataclasses
+    obj = dtype(**inputs)
+  File "<string>", line 321, in __init__
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/argument/train_args.py", line 171, in __post_init__
+    BaseArguments.__post_init__(self)
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/argument/base_args/base_args.py", line 171, in __post_init__
+    ModelArguments.__post_init__(self)
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/argument/base_args/model_args.py", line 176, in __post_init__
+    self._init_torch_dtype()
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/argument/base_args/model_args.py", line 90, in _init_torch_dtype
+    self.torch_dtype: torch.dtype = self._init_model_info()
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/argument/base_args/model_args.py", line 145, in _init_model_info
+    self.model_info, self.model_meta = get_model_info_meta(**self.get_model_kwargs())
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/model/register.py", line 533, in get_model_info_meta
+    model_dir = safe_snapshot_download(
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/model/utils.py", line 302, in safe_snapshot_download
+    model_dir = hub.download_model(model_id_or_path, revision, ignore_patterns, token=hub_token, **kwargs)
+  File "/group/40143/hongzhuyi/ms-swift/swift/hub/hub.py", line 317, in download_model
+    return snapshot_download(model_id_or_path, revision, ignore_patterns=ignore_patterns, **kwargs)
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/modelscope/hub/snapshot_download.py", line 132, in snapshot_download
+    return _snapshot_download(
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/modelscope/hub/snapshot_download.py", line 300, in _snapshot_download
+    endpoint = _api.get_endpoint_for_read(
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/modelscope/hub/api.py", line 423, in get_endpoint_for_read
+    if not self.repo_exists(
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/modelscope/hub/api.py", line 567, in repo_exists
+    raise Exception('Invalid repo_id: %s, must be of format namespace/name' % repo_type)
+Exception: Invalid repo_id: model, must be of format namespace/name
+Traceback (most recent call last):
+  File "/group/40143/hongzhuyi/ms-swift/swift/cli/sft.py", line 10, in <module>
+    sft_main()
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/train/sft.py", line 328, in sft_main
+    return SwiftSft(args).main()
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/train/sft.py", line 27, in __init__
+    super().__init__(args)
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/base.py", line 19, in __init__
+    self.args = self._parse_args(args)
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/base.py", line 31, in _parse_args
+    args, remaining_argv = parse_args(self.args_class, args)
+  File "/group/40143/hongzhuyi/ms-swift/swift/utils/utils.py", line 152, in parse_args
+    args, remaining_args = parser.parse_args_into_dataclasses(argv, return_remaining_strings=True)
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/transformers/hf_argparser.py", line 358, in parse_args_into_dataclasses
+    obj = dtype(**inputs)
+  File "<string>", line 321, in __init__
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/argument/train_args.py", line 171, in __post_init__
+    BaseArguments.__post_init__(self)
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/argument/base_args/base_args.py", line 171, in __post_init__
+    ModelArguments.__post_init__(self)
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/argument/base_args/model_args.py", line 176, in __post_init__
+    self._init_torch_dtype()
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/argument/base_args/model_args.py", line 90, in _init_torch_dtype
+    self.torch_dtype: torch.dtype = self._init_model_info()
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/argument/base_args/model_args.py", line 145, in _init_model_info
+    self.model_info, self.model_meta = get_model_info_meta(**self.get_model_kwargs())
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/model/register.py", line 533, in get_model_info_meta
+    model_dir = safe_snapshot_download(
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/model/utils.py", line 302, in safe_snapshot_download
+    model_dir = hub.download_model(model_id_or_path, revision, ignore_patterns, token=hub_token, **kwargs)
+  File "/group/40143/hongzhuyi/ms-swift/swift/hub/hub.py", line 317, in download_model
+    return snapshot_download(model_id_or_path, revision, ignore_patterns=ignore_patterns, **kwargs)
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/modelscope/hub/snapshot_download.py", line 132, in snapshot_download
+    return _snapshot_download(
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/modelscope/hub/snapshot_download.py", line 300, in _snapshot_download
+    endpoint = _api.get_endpoint_for_read(
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/modelscope/hub/api.py", line 423, in get_endpoint_for_read
+    if not self.repo_exists(
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/modelscope/hub/api.py", line 567, in repo_exists
+    raise Exception('Invalid repo_id: %s, must be of format namespace/name' % repo_type)
+Exception: Invalid repo_id: model, must be of format namespace/name
+W0917 00:58:31.144136 56559 site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 56624 closing signal SIGTERM
+W0917 00:58:31.144527 56559 site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 56625 closing signal SIGTERM
+W0917 00:58:31.145935 56559 site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 56626 closing signal SIGTERM
+W0917 00:58:31.146042 56559 site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 56627 closing signal SIGTERM
+W0917 00:58:31.147415 56559 site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 56628 closing signal SIGTERM
+W0917 00:58:31.148832 56559 site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 56630 closing signal SIGTERM
+W0917 00:58:31.150276 56559 site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 56631 closing signal SIGTERM
+E0917 00:58:31.830531 56559 site-packages/torch/distributed/elastic/multiprocessing/api.py:869] failed (exitcode: 1) local_rank: 5 (pid: 56629) of binary: /root/miniconda3/envs/verl/bin/python3.10
+Traceback (most recent call last):
+  File "/root/miniconda3/envs/verl/lib/python3.10/runpy.py", line 196, in _run_module_as_main
+    return _run_code(code, main_globals, None,
+  File "/root/miniconda3/envs/verl/lib/python3.10/runpy.py", line 86, in _run_code
+    exec(code, run_globals)
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/distributed/run.py", line 922, in <module>
+    main()
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 355, in wrapper
+    return f(*args, **kwargs)
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/distributed/run.py", line 918, in main
+    run(args)
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/distributed/run.py", line 909, in run
+    elastic_launch(
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 138, in __call__
+    return launch_agent(self._config, self._entrypoint, list(args))
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 269, in launch_agent
+    raise ChildFailedError(
+torch.distributed.elastic.multiprocessing.errors.ChildFailedError: 
+============================================================
+/group/40143/hongzhuyi/ms-swift/swift/cli/sft.py FAILED
+------------------------------------------------------------
+Failures:
+  <NO_OTHER_FAILURES>
+------------------------------------------------------------
+Root Cause (first observed failure):
+[0]:
+  time      : 2025-09-17_00:58:31
+  host      : TENCENT64.site
+  rank      : 5 (local_rank: 5)
+  exitcode  : 1 (pid: 56629)
+  error_file: <N/A>
+  traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html
+============================================================

log/20250917-01:00:15.log

@@ -0,0 +1,150 @@
+/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/cuda/__init__.py:61: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
+  import pynvml  # type: ignore[import]
+run sh: `/root/miniconda3/envs/verl/bin/python3.10 -m torch.distributed.run --nproc_per_node 8 /group/40143/hongzhuyi/ms-swift/swift/cli/sft.py --torch_dtype bfloat16 --freeze_llm false --freeze_aligner false --model qwen2.5-7b-Instruct --train_type full --dataset /group/40143/hongzhuyi/ms-swift/corr_nq_2000q_hotpot_2000q_swift.jsonl /group/40143/hongzhuyi/ms-swift/corr_hotpot_new1369q_format_swift.jsonl /group/40143/hongzhuyi/ms-swift/self_2000_2000_1369_4_hp673_swift.jsonl /group/40143/hongzhuyi/ms-swift/self_2000_2000_1369_4_nq400_noinfo_swift.jsonl --model_type qwen2_5 --dataset_num_proc 100 --dataloader_num_workers 48 --split_dataset_ratio 0.001 --warmup_ratio 0.05 --num_train_epochs 2 --per_device_train_batch_size 2 --learning_rate 5e-6 --gradient_accumulation_steps 4 --eval_steps 2000 --save_strategy epoch --logging_steps 1 --deepspeed zero3 --max_length 16240 --output_dir ./output`
+/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/cuda/__init__.py:61: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
+  import pynvml  # type: ignore[import]
+
+*****************************************
+Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed. 
+*****************************************
+/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/cuda/__init__.py:61: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
+  import pynvml  # type: ignore[import]
+/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/cuda/__init__.py:61: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
+  import pynvml  # type: ignore[import]
+/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/cuda/__init__.py:61: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
+  import pynvml  # type: ignore[import]
+/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/cuda/__init__.py:61: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
+  import pynvml  # type: ignore[import]
+/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/cuda/__init__.py:61: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
+  import pynvml  # type: ignore[import]
+/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/cuda/__init__.py:61: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
+  import pynvml  # type: ignore[import]
+/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/cuda/__init__.py:61: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
+  import pynvml  # type: ignore[import]
+/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/cuda/__init__.py:61: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
+  import pynvml  # type: ignore[import]
+[INFO:swift] Successfully registered `/group/40143/hongzhuyi/ms-swift/swift/llm/dataset/data/dataset_info.json`.
+[INFO:swift] rank: 0, local_rank: 0, world_size: 8, local_world_size: 8
+Traceback (most recent call last):
+  File "/group/40143/hongzhuyi/ms-swift/swift/cli/sft.py", line 10, in <module>
+    sft_main()
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/train/sft.py", line 328, in sft_main
+    return SwiftSft(args).main()
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/train/sft.py", line 27, in __init__
+    super().__init__(args)
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/base.py", line 19, in __init__
+    self.args = self._parse_args(args)
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/base.py", line 31, in _parse_args
+    args, remaining_argv = parse_args(self.args_class, args)
+  File "/group/40143/hongzhuyi/ms-swift/swift/utils/utils.py", line 152, in parse_args
+    args, remaining_args = parser.parse_args_into_dataclasses(argv, return_remaining_strings=True)
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/transformers/hf_argparser.py", line 358, in parse_args_into_dataclasses
+    obj = dtype(**inputs)
+  File "<string>", line 321, in __init__
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/argument/train_args.py", line 171, in __post_init__
+    BaseArguments.__post_init__(self)
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/argument/base_args/base_args.py", line 171, in __post_init__
+    ModelArguments.__post_init__(self)
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/argument/base_args/model_args.py", line 176, in __post_init__
+    self._init_torch_dtype()
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/argument/base_args/model_args.py", line 90, in _init_torch_dtype
+    self.torch_dtype: torch.dtype = self._init_model_info()
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/argument/base_args/model_args.py", line 145, in _init_model_info
+    self.model_info, self.model_meta = get_model_info_meta(**self.get_model_kwargs())
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/model/register.py", line 533, in get_model_info_meta
+    model_dir = safe_snapshot_download(
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/model/utils.py", line 302, in safe_snapshot_download
+    model_dir = hub.download_model(model_id_or_path, revision, ignore_patterns, token=hub_token, **kwargs)
+  File "/group/40143/hongzhuyi/ms-swift/swift/hub/hub.py", line 317, in download_model
+    return snapshot_download(model_id_or_path, revision, ignore_patterns=ignore_patterns, **kwargs)
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/modelscope/hub/snapshot_download.py", line 132, in snapshot_download
+    return _snapshot_download(
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/modelscope/hub/snapshot_download.py", line 300, in _snapshot_download
+    endpoint = _api.get_endpoint_for_read(
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/modelscope/hub/api.py", line 423, in get_endpoint_for_read
+    if not self.repo_exists(
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/modelscope/hub/api.py", line 567, in repo_exists
+    raise Exception('Invalid repo_id: %s, must be of format namespace/name' % repo_type)
+Exception: Invalid repo_id: model, must be of format namespace/name
+Traceback (most recent call last):
+  File "/group/40143/hongzhuyi/ms-swift/swift/cli/sft.py", line 10, in <module>
+    sft_main()
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/train/sft.py", line 328, in sft_main
+    return SwiftSft(args).main()
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/train/sft.py", line 27, in __init__
+    super().__init__(args)
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/base.py", line 19, in __init__
+    self.args = self._parse_args(args)
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/base.py", line 31, in _parse_args
+    args, remaining_argv = parse_args(self.args_class, args)
+  File "/group/40143/hongzhuyi/ms-swift/swift/utils/utils.py", line 152, in parse_args
+    args, remaining_args = parser.parse_args_into_dataclasses(argv, return_remaining_strings=True)
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/transformers/hf_argparser.py", line 358, in parse_args_into_dataclasses
+    obj = dtype(**inputs)
+  File "<string>", line 321, in __init__
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/argument/train_args.py", line 171, in __post_init__
+    BaseArguments.__post_init__(self)
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/argument/base_args/base_args.py", line 171, in __post_init__
+    ModelArguments.__post_init__(self)
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/argument/base_args/model_args.py", line 176, in __post_init__
+    self._init_torch_dtype()
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/argument/base_args/model_args.py", line 90, in _init_torch_dtype
+    self.torch_dtype: torch.dtype = self._init_model_info()
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/argument/base_args/model_args.py", line 145, in _init_model_info
+    self.model_info, self.model_meta = get_model_info_meta(**self.get_model_kwargs())
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/model/register.py", line 533, in get_model_info_meta
+    model_dir = safe_snapshot_download(
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/model/utils.py", line 302, in safe_snapshot_download
+    model_dir = hub.download_model(model_id_or_path, revision, ignore_patterns, token=hub_token, **kwargs)
+  File "/group/40143/hongzhuyi/ms-swift/swift/hub/hub.py", line 317, in download_model
+    return snapshot_download(model_id_or_path, revision, ignore_patterns=ignore_patterns, **kwargs)
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/modelscope/hub/snapshot_download.py", line 132, in snapshot_download
+    return _snapshot_download(
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/modelscope/hub/snapshot_download.py", line 300, in _snapshot_download
+    endpoint = _api.get_endpoint_for_read(
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/modelscope/hub/api.py", line 423, in get_endpoint_for_read
+    if not self.repo_exists(
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/modelscope/hub/api.py", line 567, in repo_exists
+    raise Exception('Invalid repo_id: %s, must be of format namespace/name' % repo_type)
+Exception: Invalid repo_id: model, must be of format namespace/name
+W0917 01:00:29.123581 57418 site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 57483 closing signal SIGTERM
+W0917 01:00:29.123960 57418 site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 57484 closing signal SIGTERM
+W0917 01:00:29.125410 57418 site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 57485 closing signal SIGTERM
+W0917 01:00:29.126809 57418 site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 57487 closing signal SIGTERM
+W0917 01:00:29.128227 57418 site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 57488 closing signal SIGTERM
+W0917 01:00:29.129656 57418 site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 57489 closing signal SIGTERM
+W0917 01:00:29.131062 57418 site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 57490 closing signal SIGTERM
+E0917 01:00:29.823603 57418 site-packages/torch/distributed/elastic/multiprocessing/api.py:869] failed (exitcode: 1) local_rank: 3 (pid: 57486) of binary: /root/miniconda3/envs/verl/bin/python3.10
+Traceback (most recent call last):
+  File "/root/miniconda3/envs/verl/lib/python3.10/runpy.py", line 196, in _run_module_as_main
+    return _run_code(code, main_globals, None,
+  File "/root/miniconda3/envs/verl/lib/python3.10/runpy.py", line 86, in _run_code
+    exec(code, run_globals)
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/distributed/run.py", line 922, in <module>
+    main()
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 355, in wrapper
+    return f(*args, **kwargs)
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/distributed/run.py", line 918, in main
+    run(args)
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/distributed/run.py", line 909, in run
+    elastic_launch(
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 138, in __call__
+    return launch_agent(self._config, self._entrypoint, list(args))
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 269, in launch_agent
+    raise ChildFailedError(
+torch.distributed.elastic.multiprocessing.errors.ChildFailedError: 
+============================================================
+/group/40143/hongzhuyi/ms-swift/swift/cli/sft.py FAILED
+------------------------------------------------------------
+Failures:
+  <NO_OTHER_FAILURES>
+------------------------------------------------------------
+Root Cause (first observed failure):
+[0]:
+  time      : 2025-09-17_01:00:29
+  host      : TENCENT64.site
+  rank      : 3 (local_rank: 3)
+  exitcode  : 1 (pid: 57486)
+  error_file: <N/A>
+  traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html
+============================================================

log/20250917-01:01:57.log

@@ -0,0 +1,150 @@
+/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/cuda/__init__.py:61: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
+  import pynvml  # type: ignore[import]
+run sh: `/root/miniconda3/envs/verl/bin/python3.10 -m torch.distributed.run --nproc_per_node 8 /group/40143/hongzhuyi/ms-swift/swift/cli/sft.py --torch_dtype bfloat16 --freeze_llm false --freeze_aligner false --model qwen2.5-7b-Instruct --train_type full --dataset /group/40143/hongzhuyi/ms-swift/corr_nq_2000q_hotpot_2000q_swift.jsonl /group/40143/hongzhuyi/ms-swift/corr_hotpot_new1369q_format_swift.jsonl /group/40143/hongzhuyi/ms-swift/self_2000_2000_1369_4_hp673_swift.jsonl /group/40143/hongzhuyi/ms-swift/self_2000_2000_1369_4_nq400_noinfo_swift.jsonl --model_type qwen2_5 --dataset_num_proc 100 --dataloader_num_workers 48 --split_dataset_ratio 0.001 --warmup_ratio 0.05 --num_train_epochs 2 --per_device_train_batch_size 2 --learning_rate 5e-6 --gradient_accumulation_steps 4 --eval_steps 2000 --save_strategy epoch --logging_steps 1 --deepspeed zero3 --max_length 16240 --output_dir ./output`
+/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/cuda/__init__.py:61: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
+  import pynvml  # type: ignore[import]
+
+*****************************************
+Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed. 
+*****************************************
+/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/cuda/__init__.py:61: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
+  import pynvml  # type: ignore[import]
+/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/cuda/__init__.py:61: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
+  import pynvml  # type: ignore[import]
+/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/cuda/__init__.py:61: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
+  import pynvml  # type: ignore[import]
+/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/cuda/__init__.py:61: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
+  import pynvml  # type: ignore[import]
+/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/cuda/__init__.py:61: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
+  import pynvml  # type: ignore[import]
+/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/cuda/__init__.py:61: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
+  import pynvml  # type: ignore[import]
+/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/cuda/__init__.py:61: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
+  import pynvml  # type: ignore[import]
+/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/cuda/__init__.py:61: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
+  import pynvml  # type: ignore[import]
+[INFO:swift] Successfully registered `/group/40143/hongzhuyi/ms-swift/swift/llm/dataset/data/dataset_info.json`.
+[INFO:swift] rank: 0, local_rank: 0, world_size: 8, local_world_size: 8
+Traceback (most recent call last):
+  File "/group/40143/hongzhuyi/ms-swift/swift/cli/sft.py", line 10, in <module>
+    sft_main()
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/train/sft.py", line 328, in sft_main
+    return SwiftSft(args).main()
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/train/sft.py", line 27, in __init__
+    super().__init__(args)
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/base.py", line 19, in __init__
+    self.args = self._parse_args(args)
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/base.py", line 31, in _parse_args
+    args, remaining_argv = parse_args(self.args_class, args)
+  File "/group/40143/hongzhuyi/ms-swift/swift/utils/utils.py", line 152, in parse_args
+    args, remaining_args = parser.parse_args_into_dataclasses(argv, return_remaining_strings=True)
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/transformers/hf_argparser.py", line 358, in parse_args_into_dataclasses
+    obj = dtype(**inputs)
+  File "<string>", line 321, in __init__
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/argument/train_args.py", line 171, in __post_init__
+    BaseArguments.__post_init__(self)
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/argument/base_args/base_args.py", line 171, in __post_init__
+    ModelArguments.__post_init__(self)
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/argument/base_args/model_args.py", line 176, in __post_init__
+    self._init_torch_dtype()
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/argument/base_args/model_args.py", line 90, in _init_torch_dtype
+    self.torch_dtype: torch.dtype = self._init_model_info()
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/argument/base_args/model_args.py", line 145, in _init_model_info
+    self.model_info, self.model_meta = get_model_info_meta(**self.get_model_kwargs())
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/model/register.py", line 533, in get_model_info_meta
+    model_dir = safe_snapshot_download(
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/model/utils.py", line 302, in safe_snapshot_download
+    model_dir = hub.download_model(model_id_or_path, revision, ignore_patterns, token=hub_token, **kwargs)
+  File "/group/40143/hongzhuyi/ms-swift/swift/hub/hub.py", line 317, in download_model
+    return snapshot_download(model_id_or_path, revision, ignore_patterns=ignore_patterns, **kwargs)
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/modelscope/hub/snapshot_download.py", line 132, in snapshot_download
+    return _snapshot_download(
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/modelscope/hub/snapshot_download.py", line 300, in _snapshot_download
+    endpoint = _api.get_endpoint_for_read(
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/modelscope/hub/api.py", line 423, in get_endpoint_for_read
+    if not self.repo_exists(
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/modelscope/hub/api.py", line 567, in repo_exists
+    raise Exception('Invalid repo_id: %s, must be of format namespace/name' % repo_type)
+Exception: Invalid repo_id: model, must be of format namespace/name
+Traceback (most recent call last):
+  File "/group/40143/hongzhuyi/ms-swift/swift/cli/sft.py", line 10, in <module>
+    sft_main()
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/train/sft.py", line 328, in sft_main
+    return SwiftSft(args).main()
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/train/sft.py", line 27, in __init__
+    super().__init__(args)
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/base.py", line 19, in __init__
+    self.args = self._parse_args(args)
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/base.py", line 31, in _parse_args
+    args, remaining_argv = parse_args(self.args_class, args)
+  File "/group/40143/hongzhuyi/ms-swift/swift/utils/utils.py", line 152, in parse_args
+    args, remaining_args = parser.parse_args_into_dataclasses(argv, return_remaining_strings=True)
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/transformers/hf_argparser.py", line 358, in parse_args_into_dataclasses
+    obj = dtype(**inputs)
+  File "<string>", line 321, in __init__
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/argument/train_args.py", line 171, in __post_init__
+    BaseArguments.__post_init__(self)
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/argument/base_args/base_args.py", line 171, in __post_init__
+    ModelArguments.__post_init__(self)
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/argument/base_args/model_args.py", line 176, in __post_init__
+    self._init_torch_dtype()
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/argument/base_args/model_args.py", line 90, in _init_torch_dtype
+    self.torch_dtype: torch.dtype = self._init_model_info()
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/argument/base_args/model_args.py", line 145, in _init_model_info
+    self.model_info, self.model_meta = get_model_info_meta(**self.get_model_kwargs())
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/model/register.py", line 533, in get_model_info_meta
+    model_dir = safe_snapshot_download(
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/model/utils.py", line 302, in safe_snapshot_download
+    model_dir = hub.download_model(model_id_or_path, revision, ignore_patterns, token=hub_token, **kwargs)
+  File "/group/40143/hongzhuyi/ms-swift/swift/hub/hub.py", line 317, in download_model
+    return snapshot_download(model_id_or_path, revision, ignore_patterns=ignore_patterns, **kwargs)
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/modelscope/hub/snapshot_download.py", line 132, in snapshot_download
+    return _snapshot_download(
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/modelscope/hub/snapshot_download.py", line 300, in _snapshot_download
+    endpoint = _api.get_endpoint_for_read(
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/modelscope/hub/api.py", line 423, in get_endpoint_for_read
+    if not self.repo_exists(
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/modelscope/hub/api.py", line 567, in repo_exists
+    raise Exception('Invalid repo_id: %s, must be of format namespace/name' % repo_type)
+Exception: Invalid repo_id: model, must be of format namespace/name
+W0917 01:02:15.195125 57601 site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 57666 closing signal SIGTERM
+W0917 01:02:15.195482 57601 site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 57667 closing signal SIGTERM
+W0917 01:02:15.196873 57601 site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 57668 closing signal SIGTERM
+W0917 01:02:15.198292 57601 site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 57669 closing signal SIGTERM
+W0917 01:02:15.198828 57601 site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 57671 closing signal SIGTERM
+W0917 01:02:15.199748 57601 site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 57672 closing signal SIGTERM
+W0917 01:02:15.201118 57601 site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 57673 closing signal SIGTERM
+E0917 01:02:15.881408 57601 site-packages/torch/distributed/elastic/multiprocessing/api.py:869] failed (exitcode: 1) local_rank: 4 (pid: 57670) of binary: /root/miniconda3/envs/verl/bin/python3.10
+Traceback (most recent call last):
+  File "/root/miniconda3/envs/verl/lib/python3.10/runpy.py", line 196, in _run_module_as_main
+    return _run_code(code, main_globals, None,
+  File "/root/miniconda3/envs/verl/lib/python3.10/runpy.py", line 86, in _run_code
+    exec(code, run_globals)
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/distributed/run.py", line 922, in <module>
+    main()
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 355, in wrapper
+    return f(*args, **kwargs)
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/distributed/run.py", line 918, in main
+    run(args)
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/distributed/run.py", line 909, in run
+    elastic_launch(
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 138, in __call__
+    return launch_agent(self._config, self._entrypoint, list(args))
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 269, in launch_agent
+    raise ChildFailedError(
+torch.distributed.elastic.multiprocessing.errors.ChildFailedError: 
+============================================================
+/group/40143/hongzhuyi/ms-swift/swift/cli/sft.py FAILED
+------------------------------------------------------------
+Failures:
+  <NO_OTHER_FAILURES>
+------------------------------------------------------------
+Root Cause (first observed failure):
+[0]:
+  time      : 2025-09-17_01:02:15
+  host      : TENCENT64.site
+  rank      : 4 (local_rank: 4)
+  exitcode  : 1 (pid: 57670)
+  error_file: <N/A>
+  traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html
+============================================================

log/20250917-01:04:07.log

@@ -0,0 +1,151 @@
+/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/cuda/__init__.py:61: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
+  import pynvml  # type: ignore[import]
+run sh: `/root/miniconda3/envs/verl/bin/python3.10 -m torch.distributed.run --nproc_per_node 8 /group/40143/hongzhuyi/ms-swift/swift/cli/sft.py --torch_dtype bfloat16 --freeze_llm false --freeze_aligner false --model qwen2.5-7b-Instruct --train_type full --dataset ./corr_nq_2000q_hotpot_2000q_swift.jsonl ./ms-swift/corr_hotpot_new1369q_format_swift.jsonl ./ms-swift/self_2000_2000_1369_4_hp673_swift.jsonl ./ms-swift/self_2000_2000_1369_4_nq400_noinfo_swift.jsonl --model_type qwen2_5 --dataset_num_proc 100 --dataloader_num_workers 48 --split_dataset_ratio 0.001 --warmup_ratio 0.05 --num_train_epochs 2 --per_device_train_batch_size 2 --learning_rate 5e-6 --gradient_accumulation_steps 4 --eval_steps 2000 --save_strategy epoch --logging_steps 1 --deepspeed zero3 --max_length 16240 --output_dir ./output`
+/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/cuda/__init__.py:61: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
+  import pynvml  # type: ignore[import]
+
+*****************************************
+Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed. 
+*****************************************
+/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/cuda/__init__.py:61: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
+  import pynvml  # type: ignore[import]
+/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/cuda/__init__.py:61: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
+  import pynvml  # type: ignore[import]
+/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/cuda/__init__.py:61: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
+  import pynvml  # type: ignore[import]
+/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/cuda/__init__.py:61: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
+  import pynvml  # type: ignore[import]
+/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/cuda/__init__.py:61: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
+  import pynvml  # type: ignore[import]
+/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/cuda/__init__.py:61: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
+  import pynvml  # type: ignore[import]
+/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/cuda/__init__.py:61: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
+  import pynvml  # type: ignore[import]
+/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/cuda/__init__.py:61: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
+  import pynvml  # type: ignore[import]
+[INFO:swift] Successfully registered `/group/40143/hongzhuyi/ms-swift/swift/llm/dataset/data/dataset_info.json`.
+[INFO:swift] rank: 0, local_rank: 0, world_size: 8, local_world_size: 8
+[INFO:swift] Downloading the model from ModelScope Hub, model_id: qwen2.5-7b-Instruct
+Traceback (most recent call last):
+  File "/group/40143/hongzhuyi/ms-swift/swift/cli/sft.py", line 10, in <module>
+    sft_main()
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/train/sft.py", line 328, in sft_main
+    return SwiftSft(args).main()
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/train/sft.py", line 27, in __init__
+    super().__init__(args)
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/base.py", line 19, in __init__
+    self.args = self._parse_args(args)
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/base.py", line 31, in _parse_args
+    args, remaining_argv = parse_args(self.args_class, args)
+  File "/group/40143/hongzhuyi/ms-swift/swift/utils/utils.py", line 152, in parse_args
+    args, remaining_args = parser.parse_args_into_dataclasses(argv, return_remaining_strings=True)
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/transformers/hf_argparser.py", line 358, in parse_args_into_dataclasses
+    obj = dtype(**inputs)
+  File "<string>", line 321, in __init__
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/argument/train_args.py", line 171, in __post_init__
+    BaseArguments.__post_init__(self)
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/argument/base_args/base_args.py", line 171, in __post_init__
+    ModelArguments.__post_init__(self)
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/argument/base_args/model_args.py", line 176, in __post_init__
+    self._init_torch_dtype()
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/argument/base_args/model_args.py", line 90, in _init_torch_dtype
+    self.torch_dtype: torch.dtype = self._init_model_info()
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/argument/base_args/model_args.py", line 145, in _init_model_info
+    self.model_info, self.model_meta = get_model_info_meta(**self.get_model_kwargs())
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/model/register.py", line 533, in get_model_info_meta
+    model_dir = safe_snapshot_download(
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/model/utils.py", line 302, in safe_snapshot_download
+    model_dir = hub.download_model(model_id_or_path, revision, ignore_patterns, token=hub_token, **kwargs)
+  File "/group/40143/hongzhuyi/ms-swift/swift/hub/hub.py", line 317, in download_model
+    return snapshot_download(model_id_or_path, revision, ignore_patterns=ignore_patterns, **kwargs)
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/modelscope/hub/snapshot_download.py", line 132, in snapshot_download
+    return _snapshot_download(
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/modelscope/hub/snapshot_download.py", line 300, in _snapshot_download
+    endpoint = _api.get_endpoint_for_read(
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/modelscope/hub/api.py", line 423, in get_endpoint_for_read
+    if not self.repo_exists(
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/modelscope/hub/api.py", line 567, in repo_exists
+    raise Exception('Invalid repo_id: %s, must be of format namespace/name' % repo_type)
+Exception: Invalid repo_id: model, must be of format namespace/name
+Traceback (most recent call last):
+  File "/group/40143/hongzhuyi/ms-swift/swift/cli/sft.py", line 10, in <module>
+    sft_main()
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/train/sft.py", line 328, in sft_main
+    return SwiftSft(args).main()
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/train/sft.py", line 27, in __init__
+    super().__init__(args)
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/base.py", line 19, in __init__
+    self.args = self._parse_args(args)
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/base.py", line 31, in _parse_args
+    args, remaining_argv = parse_args(self.args_class, args)
+  File "/group/40143/hongzhuyi/ms-swift/swift/utils/utils.py", line 152, in parse_args
+    args, remaining_args = parser.parse_args_into_dataclasses(argv, return_remaining_strings=True)
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/transformers/hf_argparser.py", line 358, in parse_args_into_dataclasses
+    obj = dtype(**inputs)
+  File "<string>", line 321, in __init__
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/argument/train_args.py", line 171, in __post_init__
+    BaseArguments.__post_init__(self)
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/argument/base_args/base_args.py", line 171, in __post_init__
+    ModelArguments.__post_init__(self)
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/argument/base_args/model_args.py", line 176, in __post_init__
+    self._init_torch_dtype()
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/argument/base_args/model_args.py", line 90, in _init_torch_dtype
+    self.torch_dtype: torch.dtype = self._init_model_info()
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/argument/base_args/model_args.py", line 145, in _init_model_info
+    self.model_info, self.model_meta = get_model_info_meta(**self.get_model_kwargs())
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/model/register.py", line 533, in get_model_info_meta
+    model_dir = safe_snapshot_download(
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/model/utils.py", line 302, in safe_snapshot_download
+    model_dir = hub.download_model(model_id_or_path, revision, ignore_patterns, token=hub_token, **kwargs)
+  File "/group/40143/hongzhuyi/ms-swift/swift/hub/hub.py", line 317, in download_model
+    return snapshot_download(model_id_or_path, revision, ignore_patterns=ignore_patterns, **kwargs)
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/modelscope/hub/snapshot_download.py", line 132, in snapshot_download
+    return _snapshot_download(
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/modelscope/hub/snapshot_download.py", line 300, in _snapshot_download
+    endpoint = _api.get_endpoint_for_read(
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/modelscope/hub/api.py", line 423, in get_endpoint_for_read
+    if not self.repo_exists(
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/modelscope/hub/api.py", line 567, in repo_exists
+    raise Exception('Invalid repo_id: %s, must be of format namespace/name' % repo_type)
+Exception: Invalid repo_id: model, must be of format namespace/name
+W0917 01:04:20.141232 58006 site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 58072 closing signal SIGTERM
+W0917 01:04:20.141630 58006 site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 58073 closing signal SIGTERM
+W0917 01:04:20.143054 58006 site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 58074 closing signal SIGTERM
+W0917 01:04:20.144563 58006 site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 58075 closing signal SIGTERM
+W0917 01:04:20.144789 58006 site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 58076 closing signal SIGTERM
+W0917 01:04:20.146212 58006 site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 58077 closing signal SIGTERM
+W0917 01:04:20.147614 58006 site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 58078 closing signal SIGTERM
+E0917 01:04:20.827764 58006 site-packages/torch/distributed/elastic/multiprocessing/api.py:869] failed (exitcode: 1) local_rank: 0 (pid: 58071) of binary: /root/miniconda3/envs/verl/bin/python3.10
+Traceback (most recent call last):
+  File "/root/miniconda3/envs/verl/lib/python3.10/runpy.py", line 196, in _run_module_as_main
+    return _run_code(code, main_globals, None,
+  File "/root/miniconda3/envs/verl/lib/python3.10/runpy.py", line 86, in _run_code
+    exec(code, run_globals)
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/distributed/run.py", line 922, in <module>
+    main()
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 355, in wrapper
+    return f(*args, **kwargs)
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/distributed/run.py", line 918, in main
+    run(args)
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/distributed/run.py", line 909, in run
+    elastic_launch(
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 138, in __call__
+    return launch_agent(self._config, self._entrypoint, list(args))
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 269, in launch_agent
+    raise ChildFailedError(
+torch.distributed.elastic.multiprocessing.errors.ChildFailedError: 
+============================================================
+/group/40143/hongzhuyi/ms-swift/swift/cli/sft.py FAILED
+------------------------------------------------------------
+Failures:
+  <NO_OTHER_FAILURES>
+------------------------------------------------------------
+Root Cause (first observed failure):
+[0]:
+  time      : 2025-09-17_01:04:20
+  host      : TENCENT64.site
+  rank      : 0 (local_rank: 0)
+  exitcode  : 1 (pid: 58071)
+  error_file: <N/A>
+  traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html
+============================================================

log/20250917-01:05:04.log

@@ -0,0 +1,151 @@
+/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/cuda/__init__.py:61: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
+  import pynvml  # type: ignore[import]
+run sh: `/root/miniconda3/envs/verl/bin/python3.10 -m torch.distributed.run --nproc_per_node 8 /group/40143/hongzhuyi/ms-swift/swift/cli/sft.py --torch_dtype bfloat16 --freeze_llm false --freeze_aligner false --model qwen2.5-7b-Instruct --train_type full --dataset ./corr_nq_2000q_hotpot_2000q_swift.jsonl ./corr_hotpot_new1369q_format_swift.jsonl ./self_2000_2000_1369_4_hp673_swift.jsonl ./self_2000_2000_1369_4_nq400_noinfo_swift.jsonl --model_type qwen2_5 --dataset_num_proc 100 --dataloader_num_workers 48 --split_dataset_ratio 0.001 --warmup_ratio 0.05 --num_train_epochs 2 --per_device_train_batch_size 2 --learning_rate 5e-6 --gradient_accumulation_steps 4 --eval_steps 2000 --save_strategy epoch --logging_steps 1 --deepspeed zero3 --max_length 16240 --output_dir ./output`
+/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/cuda/__init__.py:61: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
+  import pynvml  # type: ignore[import]
+
+*****************************************
+Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed. 
+*****************************************
+/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/cuda/__init__.py:61: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
+  import pynvml  # type: ignore[import]
+/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/cuda/__init__.py:61: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
+  import pynvml  # type: ignore[import]
+/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/cuda/__init__.py:61: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
+  import pynvml  # type: ignore[import]
+/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/cuda/__init__.py:61: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
+  import pynvml  # type: ignore[import]
+/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/cuda/__init__.py:61: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
+  import pynvml  # type: ignore[import]
+/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/cuda/__init__.py:61: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
+  import pynvml  # type: ignore[import]
+/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/cuda/__init__.py:61: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
+  import pynvml  # type: ignore[import]
+/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/cuda/__init__.py:61: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
+  import pynvml  # type: ignore[import]
+[INFO:swift] Successfully registered `/group/40143/hongzhuyi/ms-swift/swift/llm/dataset/data/dataset_info.json`.
+[INFO:swift] rank: 0, local_rank: 0, world_size: 8, local_world_size: 8
+Traceback (most recent call last):
+  File "/group/40143/hongzhuyi/ms-swift/swift/cli/sft.py", line 10, in <module>
+    sft_main()
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/train/sft.py", line 328, in sft_main
+    return SwiftSft(args).main()
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/train/sft.py", line 27, in __init__
+    super().__init__(args)
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/base.py", line 19, in __init__
+    self.args = self._parse_args(args)
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/base.py", line 31, in _parse_args
+    args, remaining_argv = parse_args(self.args_class, args)
+  File "/group/40143/hongzhuyi/ms-swift/swift/utils/utils.py", line 152, in parse_args
+    args, remaining_args = parser.parse_args_into_dataclasses(argv, return_remaining_strings=True)
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/transformers/hf_argparser.py", line 358, in parse_args_into_dataclasses
+    obj = dtype(**inputs)
+  File "<string>", line 321, in __init__
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/argument/train_args.py", line 171, in __post_init__
+    BaseArguments.__post_init__(self)
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/argument/base_args/base_args.py", line 171, in __post_init__
+    ModelArguments.__post_init__(self)
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/argument/base_args/model_args.py", line 176, in __post_init__
+    self._init_torch_dtype()
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/argument/base_args/model_args.py", line 90, in _init_torch_dtype
+    self.torch_dtype: torch.dtype = self._init_model_info()
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/argument/base_args/model_args.py", line 145, in _init_model_info
+    self.model_info, self.model_meta = get_model_info_meta(**self.get_model_kwargs())
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/model/register.py", line 533, in get_model_info_meta
+    model_dir = safe_snapshot_download(
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/model/utils.py", line 302, in safe_snapshot_download
+    model_dir = hub.download_model(model_id_or_path, revision, ignore_patterns, token=hub_token, **kwargs)
+  File "/group/40143/hongzhuyi/ms-swift/swift/hub/hub.py", line 317, in download_model
+    return snapshot_download(model_id_or_path, revision, ignore_patterns=ignore_patterns, **kwargs)
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/modelscope/hub/snapshot_download.py", line 132, in snapshot_download
+    return _snapshot_download(
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/modelscope/hub/snapshot_download.py", line 300, in _snapshot_download
+    endpoint = _api.get_endpoint_for_read(
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/modelscope/hub/api.py", line 423, in get_endpoint_for_read
+    if not self.repo_exists(
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/modelscope/hub/api.py", line 567, in repo_exists
+    raise Exception('Invalid repo_id: %s, must be of format namespace/name' % repo_type)
+Exception: Invalid repo_id: model, must be of format namespace/name
+[INFO:swift] Downloading the model from ModelScope Hub, model_id: qwen2.5-7b-Instruct
+Traceback (most recent call last):
+  File "/group/40143/hongzhuyi/ms-swift/swift/cli/sft.py", line 10, in <module>
+    sft_main()
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/train/sft.py", line 328, in sft_main
+    return SwiftSft(args).main()
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/train/sft.py", line 27, in __init__
+    super().__init__(args)
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/base.py", line 19, in __init__
+    self.args = self._parse_args(args)
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/base.py", line 31, in _parse_args
+    args, remaining_argv = parse_args(self.args_class, args)
+  File "/group/40143/hongzhuyi/ms-swift/swift/utils/utils.py", line 152, in parse_args
+    args, remaining_args = parser.parse_args_into_dataclasses(argv, return_remaining_strings=True)
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/transformers/hf_argparser.py", line 358, in parse_args_into_dataclasses
+    obj = dtype(**inputs)
+  File "<string>", line 321, in __init__
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/argument/train_args.py", line 171, in __post_init__
+    BaseArguments.__post_init__(self)
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/argument/base_args/base_args.py", line 171, in __post_init__
+    ModelArguments.__post_init__(self)
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/argument/base_args/model_args.py", line 176, in __post_init__
+    self._init_torch_dtype()
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/argument/base_args/model_args.py", line 90, in _init_torch_dtype
+    self.torch_dtype: torch.dtype = self._init_model_info()
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/argument/base_args/model_args.py", line 145, in _init_model_info
+    self.model_info, self.model_meta = get_model_info_meta(**self.get_model_kwargs())
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/model/register.py", line 533, in get_model_info_meta
+    model_dir = safe_snapshot_download(
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/model/utils.py", line 302, in safe_snapshot_download
+    model_dir = hub.download_model(model_id_or_path, revision, ignore_patterns, token=hub_token, **kwargs)
+  File "/group/40143/hongzhuyi/ms-swift/swift/hub/hub.py", line 317, in download_model
+    return snapshot_download(model_id_or_path, revision, ignore_patterns=ignore_patterns, **kwargs)
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/modelscope/hub/snapshot_download.py", line 132, in snapshot_download
+    return _snapshot_download(
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/modelscope/hub/snapshot_download.py", line 300, in _snapshot_download
+    endpoint = _api.get_endpoint_for_read(
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/modelscope/hub/api.py", line 423, in get_endpoint_for_read
+    if not self.repo_exists(
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/modelscope/hub/api.py", line 567, in repo_exists
+    raise Exception('Invalid repo_id: %s, must be of format namespace/name' % repo_type)
+Exception: Invalid repo_id: model, must be of format namespace/name
+W0917 01:05:17.371760 58177 site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 58242 closing signal SIGTERM
+W0917 01:05:17.372081 58177 site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 58243 closing signal SIGTERM
+W0917 01:05:17.373476 58177 site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 58245 closing signal SIGTERM
+W0917 01:05:17.374921 58177 site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 58246 closing signal SIGTERM
+W0917 01:05:17.376225 58177 site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 58247 closing signal SIGTERM
+W0917 01:05:17.377662 58177 site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 58248 closing signal SIGTERM
+W0917 01:05:17.379025 58177 site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 58249 closing signal SIGTERM
+E0917 01:05:18.172204 58177 site-packages/torch/distributed/elastic/multiprocessing/api.py:869] failed (exitcode: 1) local_rank: 2 (pid: 58244) of binary: /root/miniconda3/envs/verl/bin/python3.10
+Traceback (most recent call last):
+  File "/root/miniconda3/envs/verl/lib/python3.10/runpy.py", line 196, in _run_module_as_main
+    return _run_code(code, main_globals, None,
+  File "/root/miniconda3/envs/verl/lib/python3.10/runpy.py", line 86, in _run_code
+    exec(code, run_globals)
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/distributed/run.py", line 922, in <module>
+    main()
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 355, in wrapper
+    return f(*args, **kwargs)
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/distributed/run.py", line 918, in main
+    run(args)
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/distributed/run.py", line 909, in run
+    elastic_launch(
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 138, in __call__
+    return launch_agent(self._config, self._entrypoint, list(args))
+  File "/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 269, in launch_agent
+    raise ChildFailedError(
+torch.distributed.elastic.multiprocessing.errors.ChildFailedError: 
+============================================================
+/group/40143/hongzhuyi/ms-swift/swift/cli/sft.py FAILED
+------------------------------------------------------------
+Failures:
+  <NO_OTHER_FAILURES>
+------------------------------------------------------------
+Root Cause (first observed failure):
+[0]:
+  time      : 2025-09-17_01:05:17
+  host      : TENCENT64.site
+  rank      : 2 (local_rank: 2)
+  exitcode  : 1 (pid: 58244)
+  error_file: <N/A>
+  traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html
+============================================================

log/20250917-01:05:43.log

@@ -0,0 +1,682 @@
+/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/cuda/__init__.py:61: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
+  import pynvml  # type: ignore[import]
+run sh: `/root/miniconda3/envs/verl/bin/python3.10 -m torch.distributed.run --nproc_per_node 8 /group/40143/hongzhuyi/ms-swift/swift/cli/sft.py --torch_dtype bfloat16 --freeze_llm false --freeze_aligner false --model Qwen/Qwen2.5-7B-Instruct --train_type full --dataset ./corr_nq_2000q_hotpot_2000q_swift.jsonl ./corr_hotpot_new1369q_format_swift.jsonl ./self_2000_2000_1369_4_hp673_swift.jsonl ./self_2000_2000_1369_4_nq400_noinfo_swift.jsonl --model_type qwen2_5 --dataset_num_proc 100 --dataloader_num_workers 48 --split_dataset_ratio 0.001 --warmup_ratio 0.05 --num_train_epochs 2 --per_device_train_batch_size 2 --learning_rate 5e-6 --gradient_accumulation_steps 4 --eval_steps 2000 --save_strategy epoch --logging_steps 1 --deepspeed zero3 --max_length 16240 --output_dir ./output`
+/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/cuda/__init__.py:61: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
+  import pynvml  # type: ignore[import]
+
+*****************************************
+Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed. 
+*****************************************
+/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/cuda/__init__.py:61: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
+  import pynvml  # type: ignore[import]
+/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/cuda/__init__.py:61: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
+  import pynvml  # type: ignore[import]
+/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/cuda/__init__.py:61: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
+  import pynvml  # type: ignore[import]
+/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/cuda/__init__.py:61: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
+  import pynvml  # type: ignore[import]
+/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/cuda/__init__.py:61: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
+  import pynvml  # type: ignore[import]
+/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/cuda/__init__.py:61: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
+  import pynvml  # type: ignore[import]
+/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/cuda/__init__.py:61: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
+  import pynvml  # type: ignore[import]
+/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/cuda/__init__.py:61: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
+  import pynvml  # type: ignore[import]
+[INFO:swift] Successfully registered `/group/40143/hongzhuyi/ms-swift/swift/llm/dataset/data/dataset_info.json`.
+[INFO:swift] rank: 0, local_rank: 0, world_size: 8, local_world_size: 8
+Downloading Model from https://www.modelscope.cn to directory: /root/.cache/modelscope/hub/models/Qwen/Qwen2.5-7B-Instruct
+[2025-09-17 01:05:56,696] [INFO] [real_accelerator.py:254:get_accelerator] Setting ds_accelerator to cuda (auto detect)
+Downloading Model from https://www.modelscope.cn to directory: /root/.cache/modelscope/hub/models/Qwen/Qwen2.5-7B-Instruct
+[2025-09-17 01:05:57,681] [INFO] [comm.py:669:init_distributed] cdb=None
+/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/cuda/__init__.py:61: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
+  import pynvml  # type: ignore[import]
+[2025-09-17 01:05:58,370] [INFO] [real_accelerator.py:254:get_accelerator] Setting ds_accelerator to cuda (auto detect)
+Downloading Model from https://www.modelscope.cn to directory: /root/.cache/modelscope/hub/models/Qwen/Qwen2.5-7B-Instruct
+[2025-09-17 01:05:59,356] [INFO] [comm.py:669:init_distributed] cdb=None
+/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/cuda/__init__.py:61: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
+  import pynvml  # type: ignore[import]
+[2025-09-17 01:05:59,842] [INFO] [real_accelerator.py:254:get_accelerator] Setting ds_accelerator to cuda (auto detect)
+Downloading Model from https://www.modelscope.cn to directory: /root/.cache/modelscope/hub/models/Qwen/Qwen2.5-7B-Instruct
+[2025-09-17 01:06:00,978] [INFO] [comm.py:669:init_distributed] cdb=None
+[INFO:swift] Downloading the model from ModelScope Hub, model_id: Qwen/Qwen2.5-7B-Instruct
+/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/cuda/__init__.py:61: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
+  import pynvml  # type: ignore[import]
+[2025-09-17 01:06:01,445] [INFO] [real_accelerator.py:254:get_accelerator] Setting ds_accelerator to cuda (auto detect)
+Downloading Model from https://www.modelscope.cn to directory: /root/.cache/modelscope/hub/models/Qwen/Qwen2.5-7B-Instruct
+[2025-09-17 01:06:02,581] [INFO] [comm.py:669:init_distributed] cdb=None
+[INFO:modelscope] Target directory already exists, skipping creation.
+[INFO:swift] Loading the model using model_dir: /root/.cache/modelscope/hub/models/Qwen/Qwen2___5-7B-Instruct
+[INFO:swift] Setting args.lazy_tokenize: False
+/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/cuda/__init__.py:61: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
+  import pynvml  # type: ignore[import]
+[INFO:swift] Using deepspeed: {'fp16': {'enabled': 'auto', 'loss_scale': 0, 'loss_scale_window': 1000, 'initial_scale_power': 16, 'hysteresis': 2, 'min_loss_scale': 1}, 'bf16': {'enabled': 'auto'}, 'zero_optimization': {'stage': 3, 'offload_optimizer': {'device': 'none', 'pin_memory': True}, 'offload_param': {'device': 'none', 'pin_memory': True}, 'overlap_comm': False, 'contiguous_gradients': True, 'sub_group_size': 1000000000.0, 'reduce_bucket_size': 'auto', 'zero_quantized_weights': False, 'zero_quantized_gradients': False, 'stage3_prefetch_bucket_size': 'auto', 'stage3_param_persistence_threshold': 'auto', 'stage3_max_live_parameters': 1000000000.0, 'stage3_max_reuse_distance': 1000000000.0, 'stage3_gather_16bit_weights_on_model_save': True}, 'gradient_accumulation_steps': 'auto', 'gradient_clipping': 'auto', 'steps_per_print': 2000, 'train_batch_size': 'auto', 'train_micro_batch_size_per_gpu': 'auto', 'wall_clock_breakdown': False}
+[2025-09-17 01:06:03,128] [INFO] [real_accelerator.py:254:get_accelerator] Setting ds_accelerator to cuda (auto detect)
+Downloading Model from https://www.modelscope.cn to directory: /root/.cache/modelscope/hub/models/Qwen/Qwen2.5-7B-Instruct
+[2025-09-17 01:06:04,137] [INFO] [comm.py:669:init_distributed] cdb=None
+[2025-09-17 01:06:04,137] [INFO] [comm.py:700:init_distributed] Initializing TorchBackend in DeepSpeed with backend nccl
+/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/cuda/__init__.py:61: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
+  import pynvml  # type: ignore[import]
+[2025-09-17 01:06:05,166] [INFO] [real_accelerator.py:254:get_accelerator] Setting ds_accelerator to cuda (auto detect)
+Downloading Model from https://www.modelscope.cn to directory: /root/.cache/modelscope/hub/models/Qwen/Qwen2.5-7B-Instruct
+[2025-09-17 01:06:06,167] [INFO] [comm.py:669:init_distributed] cdb=None
+/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/cuda/__init__.py:61: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
+  import pynvml  # type: ignore[import]
+Downloading Model from https://www.modelscope.cn to directory: /root/.cache/modelscope/hub/models/Qwen/Qwen2.5-7B-Instruct
+[2025-09-17 01:06:07,233] [INFO] [real_accelerator.py:254:get_accelerator] Setting ds_accelerator to cuda (auto detect)
+[2025-09-17 01:06:08,259] [INFO] [comm.py:669:init_distributed] cdb=None
+[2025-09-17 01:06:08,514] [INFO] [real_accelerator.py:254:get_accelerator] Setting ds_accelerator to cuda (auto detect)
+/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/cuda/__init__.py:61: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
+  import pynvml  # type: ignore[import]
+[2025-09-17 01:06:09,532] [INFO] [comm.py:669:init_distributed] cdb=None
+/root/miniconda3/envs/verl/lib/python3.10/site-packages/torch/cuda/__init__.py:61: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
+  import pynvml  # type: ignore[import]
+[INFO:swift] output_dir: /group/40143/hongzhuyi/ms-swift/output/v0-20250917-010604
+[INFO:swift] Global seed set to 42
+[INFO:swift] args: TrainArguments(
+_n_gpu=-1,
+acc_strategy=token,
+accelerator_config={'dispatch_batches': False},
+adafactor=False,
+adalora_beta1=0.85,
+adalora_beta2=0.85,
+adalora_deltaT=1,
+adalora_init_r=12,
+adalora_orth_reg_weight=0.5,
+adalora_target_r=8,
+adalora_tfinal=0,
+adalora_tinit=0,
+adam_beta1=0.9,
+adam_beta2=0.95,
+adam_epsilon=1e-08,
+adapter_act=gelu,
+adapter_length=128,
+adapters=[],
+add_version=True,
+agent_template=None,
+aligner_lr=None,
+attn_impl=None,
+auto_find_batch_size=False,
+average_tokens_across_devices=False,
+batch_eval_metrics=False,
+bf16=True,
+bf16_full_eval=False,
+bnb_4bit_compute_dtype=torch.bfloat16,
+bnb_4bit_quant_storage=None,
+bnb_4bit_quant_type=nf4,
+bnb_4bit_use_double_quant=True,
+boft_block_num=0,
+boft_block_size=4,
+boft_dropout=0.0,
+boft_n_butterfly_factor=1,
+cached_dataset=[],
+channels=None,
+check_model=True,
+ckpt_dir=None,
+columns={},
+create_checkpoint_symlink=False,
+custom_dataset_info=[],
+custom_register_path=[],
+data_seed=42,
+dataloader_drop_last=False,
+dataloader_num_workers=48,
+dataloader_persistent_workers=False,
+dataloader_pin_memory=True,
+dataloader_prefetch_factor=None,
+dataset=['./corr_nq_2000q_hotpot_2000q_swift.jsonl', './corr_hotpot_new1369q_format_swift.jsonl', './self_2000_2000_1369_4_hp673_swift.jsonl', './self_2000_2000_1369_4_nq400_noinfo_swift.jsonl'],
+dataset_num_proc=100,
+dataset_shuffle=True,
+ddp_backend=None,
+ddp_broadcast_buffers=None,
+ddp_bucket_cap_mb=None,
+ddp_find_unused_parameters=None,
+ddp_timeout=18000000,
+debug=None,
+deepspeed={'fp16': {'enabled': 'auto', 'loss_scale': 0, 'loss_scale_window': 1000, 'initial_scale_power': 16, 'hysteresis': 2, 'min_loss_scale': 1}, 'bf16': {'enabled': 'auto'}, 'zero_optimization': {'stage': 3, 'offload_optimizer': {'device': 'none', 'pin_memory': True}, 'offload_param': {'device': 'none', 'pin_memory': True}, 'overlap_comm': False, 'contiguous_gradients': True, 'sub_group_size': 1000000000.0, 'reduce_bucket_size': 'auto', 'zero_quantized_weights': False, 'zero_quantized_gradients': False, 'stage3_prefetch_bucket_size': 'auto', 'stage3_param_persistence_threshold': 'auto', 'stage3_max_live_parameters': 1000000000.0, 'stage3_max_reuse_distance': 1000000000.0, 'stage3_gather_16bit_weights_on_model_save': True}, 'gradient_accumulation_steps': 'auto', 'gradient_clipping': 'auto', 'steps_per_print': 2000, 'train_batch_size': 'auto', 'train_micro_batch_size_per_gpu': 'auto', 'wall_clock_breakdown': False},
+deepspeed_autotp_size=None,
+device_map=None,
+disable_tqdm=None,
+do_eval=False,
+do_predict=False,
+do_train=False,
+download_mode=reuse_dataset_if_exists,
+ds3_gather_for_generation=True,
+early_stop_interval=None,
+enable_dft_loss=False,
+eval_accumulation_steps=None,
+eval_dataset=[],
+eval_dataset_args=None,
+eval_delay=0,
+eval_do_concat_batches=True,
+eval_generation_config=None,
+eval_limit=None,
+eval_on_start=False,
+eval_steps=2000.0,
+eval_strategy=epoch,
+eval_use_evalscope=False,
+eval_use_gather_object=False,
+external_plugins=[],
+extra_eval_args=None,
+fourier_n_frequency=2000,
+fourier_scaling=300.0,
+fp16=False,
+fp16_backend=auto,
+fp16_full_eval=False,
+fp16_opt_level=O1,
+freeze_aligner=False,
+freeze_llm=False,
+freeze_parameters=[],
+freeze_parameters_ratio=0.0,
+freeze_parameters_regex=None,
+freeze_vit=True,
+fsdp=,
+fsdp_config=None,
+fsdp_min_num_params=0,
+fsdp_transformer_layer_cls_to_wrap=None,
+full_determinism=False,
+galore_cos_threshold=0.4,
+galore_gamma_proj=2,
+galore_optim_per_parameter=False,
+galore_proj_bits=4,
+galore_proj_group_size=256,
+galore_proj_quant=False,
+galore_proj_type=std,
+galore_quantization=False,
+galore_queue_size=5,
+galore_rank=128,
+galore_scale=1.0,
+galore_target_modules=None,
+galore_update_proj_gap=50,
+galore_with_embedding=False,
+generation_config=None,
+generation_max_length=None,
+generation_num_beams=None,
+gradient_accumulation_steps=4,
+gradient_checkpointing=True,
+gradient_checkpointing_kwargs=None,
+greater_is_better=False,
+group_by_length=False,
+half_precision_backend=auto,
+hqq_axis=None,
+hub_always_push=False,
+hub_model_id=None,
+hub_private_repo=None,
+hub_strategy=every_save,
+hub_token=<HUB_TOKEN>,
+ignore_args_error=False,
+ignore_data_skip=False,
+include_for_metrics=[],
+include_inputs_for_metrics=False,
+include_num_input_tokens_seen=False,
+include_tokens_per_second=False,
+init_strategy=None,
+init_weights=True,
+interleave_prob=None,
+jit_mode_eval=False,
+label_names=None,
+label_smoothing_factor=0.0,
+lazy_tokenize=False,
+learning_rate=5e-06,
+length_column_name=length,
+lisa_activated_layers=0,
+lisa_step_interval=20,
+llamapro_num_groups=None,
+llamapro_num_new_blocks=4,
+load_args=False,
+load_best_model_at_end=False,
+load_data_args=False,
+load_from_cache_file=True,
+local_rank=0,
+local_repo_path=None,
+log_level=passive,
+log_level_replica=warning,
+log_on_each_node=True,
+logging_dir=/group/40143/hongzhuyi/ms-swift/output/v0-20250917-010604/runs,
+logging_first_step=True,
+logging_nan_inf_filter=True,
+logging_steps=1,
+logging_strategy=steps,
+logprobs=False,
+lora_alpha=32,
+lora_bias=none,
+lora_dropout=0.05,
+lora_dtype=None,
+lora_ga_batch_size=2,
+lora_ga_direction=ArB2r,
+lora_ga_iters=2,
+lora_ga_max_length=1024,
+lora_ga_scale=stable,
+lora_ga_stable_gamma=16,
+lora_modules=[],
+lora_rank=8,
+lorap_lr_ratio=None,
+loss_scale=default,
+loss_type=None,
+lr_scheduler_kwargs=None,
+lr_scheduler_type=cosine,
+max_epochs=None,
+max_grad_norm=1.0,
+max_length=16240,
+max_memory={},
+max_model_len=None,
+max_new_tokens=64,
+max_pixels=None,
+max_steps=-1,
+metric=None,
+metric_for_best_model=loss,
+model=Qwen/Qwen2.5-7B-Instruct,
+model_author=None,
+model_kwargs={},
+model_name=None,
+model_revision=None,
+model_type=qwen2_5,
+modules_to_save=[],
+mp_parameters=,
+neftune_noise_alpha=None,
+new_special_tokens=[],
+no_cuda=False,
+norm_bbox=None,
+num_beams=1,
+num_labels=None,
+num_train_epochs=2.0,
+optim=adamw_torch,
+optim_args=None,
+optim_target_modules=None,
+optimizer=None,
+output_dir=/group/40143/hongzhuyi/ms-swift/output/v0-20250917-010604,
+overwrite_output_dir=False,
+packing=False,
+packing_length=None,
+padding_free=False,
+padding_side=right,
+past_index=-1,
+per_device_eval_batch_size=1,
+per_device_train_batch_size=2,
+predict_with_generate=False,
+prediction_loss_only=False,
+problem_type=None,
+push_to_hub=False,
+push_to_hub_model_id=None,
+push_to_hub_organization=None,
+push_to_hub_token=<PUSH_TO_HUB_TOKEN>,
+quant_bits=None,
+quant_method=None,
+ray_scope=last,
+reft_args=None,
+reft_intervention_type=LoreftIntervention,
+reft_layer_key=None,
+reft_layers=None,
+reft_rank=4,
+remove_unused_columns=True,
+repetition_penalty=None,
+report_to=['tensorboard'],
+response_prefix=None,
+restore_callback_states_from_checkpoint=False,
+resume_from_checkpoint=None,
+resume_only_model=False,
+rope_scaling=None,
+router_aux_loss_coef=0.0,
+run_name=/group/40143/hongzhuyi/ms-swift/output/v0-20250917-010604,
+save_on_each_node=False,
+save_only_model=False,
+save_safetensors=True,
+save_steps=500,
+save_strategy=epoch,
+save_total_limit=None,
+seed=42,
+sequence_parallel_size=1,
+shuffle_buffer_size=1000,
+skip_memory_metrics=True,
+sortish_sampler=False,
+split_dataset_ratio=0.001,
+stop_words=[],
+stopping_strategy=first_exhausted,
+stream=False,
+streaming=False,
+strict=False,
+swanlab_exp_name=None,
+swanlab_lark_secret=None,
+swanlab_lark_webhook_url=None,
+swanlab_mode=cloud,
+swanlab_project=None,
+swanlab_token=<SWANLAB_TOKEN>,
+swanlab_workspace=None,
+system=None,
+target_modules=['all-linear'],
+target_regex=None,
+task_type=causal_lm,
+temperature=0.0,
+template=qwen2_5,
+template_backend=swift,
+tf32=None,
+top_k=None,
+top_logprobs=None,
+top_p=None,
+torch_compile=False,
+torch_compile_backend=None,
+torch_compile_mode=None,
+torch_dtype=torch.bfloat16,
+torch_empty_cache_steps=None,
+torchdynamo=None,
+tpu_metrics_debug=False,
+tpu_num_cores=None,
+train_dataloader_shuffle=True,
+train_type=full,
+trainable_parameters=[],
+trainable_parameters_regex=None,
+truncation_strategy=delete,
+tuner_backend=peft,
+use_chat_template=True,
+use_cpu=False,
+use_dora=False,
+use_flash_ckpt=False,
+use_galore=False,
+use_hf=False,
+use_ipex=False,
+use_legacy_prediction_loop=False,
+use_liger_kernel=False,
+use_logits_to_keep=None,
+use_mps_device=False,
+use_rslora=False,
+use_swift_lora=False,
+val_dataset=[],
+val_dataset_shuffle=False,
+vera_d_initial=0.1,
+vera_dropout=0.0,
+vera_projection_prng_key=0,
+vera_rank=256,
+vit_gradient_checkpointing=None,
+vit_lr=None,
+warmup_ratio=0.05,
+warmup_steps=0,
+weight_decay=0.1,
+zero_hpz_partition_size=None,
+)
+Downloading Model from https://www.modelscope.cn to directory: /root/.cache/modelscope/hub/models/Qwen/Qwen2.5-7B-Instruct
+[2025-09-17 01:06:19,229] [INFO] [config.py:735:__init__] Config mesh_device None world_size = 8
+Downloading Model from https://www.modelscope.cn to directory: /root/.cache/modelscope/hub/models/Qwen/Qwen2.5-7B-Instruct
+[2025-09-17 01:06:20,800] [INFO] [config.py:735:__init__] Config mesh_device None world_size = 8
+Downloading Model from https://www.modelscope.cn to directory: /root/.cache/modelscope/hub/models/Qwen/Qwen2.5-7B-Instruct
+[INFO:swift] Downloading the model from ModelScope Hub, model_id: Qwen/Qwen2.5-7B-Instruct
+[2025-09-17 01:06:22,370] [INFO] [config.py:735:__init__] Config mesh_device None world_size = 8
+Downloading Model from https://www.modelscope.cn to directory: /root/.cache/modelscope/hub/models/Qwen/Qwen2.5-7B-Instruct
+[INFO:modelscope] Target directory already exists, skipping creation.
+[INFO:swift] Loading the model using model_dir: /root/.cache/modelscope/hub/models/Qwen/Qwen2___5-7B-Instruct
+[INFO:swift] model_kwargs: {'device_map': None}
+[2025-09-17 01:06:23,989] [INFO] [config.py:735:__init__] Config mesh_device None world_size = 8
+Downloading Model from https://www.modelscope.cn to directory: /root/.cache/modelscope/hub/models/Qwen/Qwen2.5-7B-Instruct
+[2025-09-17 01:06:25,612] [INFO] [config.py:735:__init__] Config mesh_device None world_size = 8
+Downloading Model from https://www.modelscope.cn to directory: /root/.cache/modelscope/hub/models/Qwen/Qwen2.5-7B-Instruct
+[2025-09-17 01:06:27,174] [INFO] [config.py:735:__init__] Config mesh_device None world_size = 8
+Downloading Model from https://www.modelscope.cn to directory: /root/.cache/modelscope/hub/models/Qwen/Qwen2.5-7B-Instruct
+[2025-09-17 01:06:28,854] [INFO] [config.py:735:__init__] Config mesh_device None world_size = 8
+Downloading Model from https://www.modelscope.cn to directory: /root/.cache/modelscope/hub/models/Qwen/Qwen2.5-7B-Instruct
+[2025-09-17 01:06:30,556] [INFO] [config.py:735:__init__] Config mesh_device None world_size = 8
+[2025-09-17 01:06:30,707] [INFO] [partition_parameters.py:348:__exit__] finished initializing model - num_params = 339, num_elems = 7.62B
+
+
+
+
+
+
+
+
+[INFO:swift] model_info: ModelInfo(model_type='qwen2_5', model_dir='/root/.cache/modelscope/hub/models/Qwen/Qwen2___5-7B-Instruct', torch_dtype=torch.bfloat16, max_model_len=32768, quant_method=None, quant_bits=None, rope_scaling=None, is_moe_model=False, config=Qwen2Config {
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 131072,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.52.4",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}
+, task_type='causal_lm', num_labels=None)
+[INFO:swift] model.generation_config: GenerationConfig {
+  "bos_token_id": 151643,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "max_new_tokens": 64,
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05
+}
+
+[INFO:swift] default_system: 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.'
+[INFO:swift] max_length: 16240
+[INFO:swift] response_prefix: ''
+[INFO:swift] agent_template: hermes
+[INFO:swift] Start time of running main: 2025-09-17 01:06:35.534151
+[INFO:swift] swift.__version__: 3.8.0.dev0
+
+Setting num_proc from 100 back to 1 for the train split to disable multiprocessing as it only contains one shard.
+
+
+Setting num_proc from 100 back to 1 for the train split to disable multiprocessing as it only contains one shard.
+
+
+Setting num_proc from 100 back to 1 for the train split to disable multiprocessing as it only contains one shard.
+
+
+[INFO:swift] train_dataset: Dataset({
+    features: ['messages'],
+    num_rows: 28291
+})
+[INFO:swift] val_dataset: Dataset({
+    features: ['messages'],
+    num_rows: 26
+})
+[INFO:swift] The split dataset from the training set will be saved at: /group/40143/hongzhuyi/ms-swift/output/v0-20250917-010604/val_dataset.jsonl.
+
+num_proc must be <= 26. Reducing num_proc to 26 for dataset of size 26.
+
+num_proc must be <= 26. Reducing num_proc to 26 for dataset of size 26.
+num_proc must be <= 26. Reducing num_proc to 26 for dataset of size 26.
+num_proc must be <= 26. Reducing num_proc to 26 for dataset of size 26.
+num_proc must be <= 26. Reducing num_proc to 26 for dataset of size 26.
+num_proc must be <= 26. Reducing num_proc to 26 for dataset of size 26.
+num_proc must be <= 26. Reducing num_proc to 26 for dataset of size 26.
+num_proc must be <= 26. Reducing num_proc to 26 for dataset of size 26.
+[INFO:swift] [INPUT_IDS] [151644, 8948, 198, 2610, 525, 264, 6929, 16230, 17847, 6188, 311, 9026, 3019, 14319, 29208, 6929, 7525, 29720, 323, 23638, 311, 4583, 279, 1196, 594, 3383, 13, 1446, 525, 3897, 448, 3151, 9079, 323, 44610, 13904, 1995, 11, 323, 498, 1184, 311, 2550, 13382, 6168, 311, 22054, 279, 1196, 594, 3383, 382, 8420, 594, 279, 1995, 498, 3278, 614, 510, 785, 1196, 594, 16538, 25, 1096, 374, 279, 3383, 498, 2299, 4460, 311, 4583, 624, 785, 1482, 3482, 2150, 594, 39700, 4916, 25, 1096, 374, 264, 43799, 13042, 315, 279, 44610, 11, 8241, 1376, 1995, 624, 785, 1787, 22398, 25, 4220, 525, 279, 22398, 498, 614, 1787, 624, 785, 3681, 6168, 25, 2619, 525, 279, 6168, 498, 1101, 10660, 13, 1084, 1231, 387, 10950, 311, 3754, 697, 5098, 382, 785, 6168, 498, 646, 2736, 4399, 1119, 3807, 11059, 1447, 2665, 16730, 26722, 510, 63, 3678, 508, 307, 60, 508, 1796, 60, 44622, 1096, 1917, 27749, 389, 458, 2392, 448, 264, 3151, 877, 389, 279, 44610, 624, 63, 1313, 508, 307, 60, 508, 1796, 60, 508, 1873, 37480, 19844, 28, 15, 91, 16, 60, 44622, 5443, 419, 311, 943, 279, 2213, 1119, 279, 2070, 448, 877, 13, 3216, 1638, 11, 279, 1591, 6269, 3014, 1376, 374, 17320, 1283, 19496, 7241, 3493, 37480, 19844, 374, 738, 311, 220, 15, 624, 63, 17583, 508, 307, 60, 508, 1796, 60, 44622, 85569, 916, 458, 2392, 448, 877, 624, 63, 1873, 508, 792, 34454, 60, 44622, 220, 4467, 23156, 279, 25352, 315, 264, 1376, 10601, 389, 279, 13625, 320, 68, 1302, 2572, 37014, 98267, 4292, 63, 12605, 508, 2923, 91, 454, 60, 44622, 22392, 279, 2150, 705, 476, 1495, 382, 8582, 9551, 26722, 510, 63, 931, 17344, 44622, 5264, 264, 501, 11, 4287, 6929, 5651, 624, 63, 6192, 47492, 508, 6192, 3560, 60, 44622, 15586, 279, 6929, 594, 5244, 311, 264, 3151, 5651, 1667, 1181, 1922, 624, 63, 5552, 17344, 44622, 13032, 279, 5023, 4541, 5651, 382, 3144, 17980, 26722, 510, 63, 28535, 508, 1085, 60, 44622, 81739, 311, 264, 3151, 5548, 624, 63, 3346, 3895, 44622, 81739, 311, 279, 8597, 19334, 2150, 624, 63, 3346, 32121, 44622, 81739, 311, 279, 1790, 2150, 320, 333, 264, 3681, 364, 3346, 3895, 6, 1917, 572, 10660, 3593, 33190, 5586, 510, 63, 9495, 508, 9217, 60, 44622, 25226, 419, 1917, 979, 498, 4411, 279, 3383, 374, 4583, 13, 1416, 279, 16538, 374, 311, 1477, 264, 1467, 5980, 4226, 11, 3410, 279, 4226, 304, 279, 31642, 13, 1416, 498, 4411, 279, 3383, 374, 11997, 311, 4583, 11, 3410, 279, 4226, 438, 1591, 45, 10360, 3014, 304, 279, 31642, 382, 1249, 387, 6849, 11, 432, 374, 1602, 2989, 311, 1795, 279, 2701, 5601, 510, 16, 13, 1446, 1265, 1172, 4265, 458, 1917, 429, 374, 2697, 2661, 279, 1482, 21930, 624, 17, 13, 1446, 1265, 1172, 4265, 825, 1917, 518, 264, 882, 624, 18, 13, 1446, 1265, 1795, 279, 10295, 311, 2874, 3019, 553, 3019, 323, 1221, 4265, 279, 1790, 1917, 624, 19, 13, 1446, 1265, 8300, 311, 13656, 6168, 979, 4265, 458, 1917, 323, 1430, 537, 311, 1281, 58077, 6168, 198, 20, 13, 2009, 32711, 1969, 387, 4766, 30586, 26865, 1472, 26865, 43626, 9492, 11, 323, 1052, 1969, 387, 902, 2550, 1573, 30586, 26865, 1472, 26865, 29, 18639, 21, 13, 4636, 30586, 26865, 1472, 26865, 29, 7808, 1172, 279, 1917, 1265, 387, 7907, 304, 279, 4396, 3561, 11, 43810, 304, 2038, 69155, 13, 1752, 3110, 510, 256, 366, 26865, 41993, 3137, 5868, 9760, 311, 847, 5795, 13, 9189, 287, 432, 1265, 1896, 752, 311, 279, 1790, 3019, 3918, 26865, 397, 256, 54275, 3678, 508, 307, 60, 508, 1796, 60, 13874, 3989, 22, 13, 25226, 279, 2936, 1917, 979, 498, 1744, 498, 614, 16994, 279, 16538, 13, 4320, 1405, 6923, 4113, 1283, 2936, 624, 23, 13, 23240, 3561, 6168, 12440, 25, 715, 73594, 5631, 508, 13786, 60, 13874, 3989, 2461, 3110, 11, 421, 15039, 369, 1591, 61907, 2802, 41612, 304, 279, 2274, 3014, 304, 264, 2711, 2070, 448, 3034, 1565, 17, 16, 7808, 12440, 3561, 432, 438, 510, 73594, 1313, 508, 17, 16, 60, 508, 61907, 2802, 41612, 304, 279, 2274, 60, 508, 16, 60, 13874, 3989, 52116, 15114, 19856, 429, 51044, 38929, 2163, 5029, 476, 24064, 2750, 624, 151645, 198, 151644, 872, 271, 78306, 25, 8713, 8697, 39946, 20691, 323, 53350, 6272, 25294, 20691, 2176, 7407, 304, 279, 1584, 315, 29790, 11, 3639, 4180, 5267, 37763, 367, 25, 508, 17, 24, 17, 60, 18854, 5981, 8726, 364, 1474, 74045, 1008, 29458, 86, 941, 7412, 7434, 25591, 6, 10735, 25, 3007, 2515, 25, 1758, 1110, 8301, 25, 17, 17, 15, 16, 20, 6324, 14939, 6205, 5705, 6345, 72, 62, 17, 15, 17, 17, 12, 15, 20, 10360, 33511, 74045, 30456, 10102, 37081, 941, 1889, 4076, 7434, 25591, 198, 197, 58, 18, 18, 15, 60, 73999, 330, 5890, 364, 54, 14939, 14913, 2567, 25, 3557, 198, 197, 58, 18, 18, 21, 60, 2656, 364, 10850, 311, 10565, 2150, 6, 2515, 25, 1758, 1110, 8301, 25, 17, 17, 15, 16, 20, 5894, 197, 197, 58, 18, 18, 22, 60, 3137, 364, 145574, 1248, 197, 58, 18, 18, 23, 60, 2656, 330, 10850, 311, 279, 1887, 2150, 315, 364, 54, 14939, 14913, 2515, 25, 1758, 1110, 8301, 25, 17, 17, 15, 16, 20, 6324, 14939, 6205, 5705, 6345, 72, 62, 17, 15, 17, 17, 12, 15, 20, 5894, 197, 197, 58, 18, 18, 24, 60, 3137, 364, 54, 14939, 1248, 197, 58, 18, 19, 15, 60, 2656, 364, 10850, 311, 264, 26618, 4091, 2150, 6, 2515, 25, 1758, 1110, 8301, 25, 17, 17, 15, 16, 20, 79442, 30, 1796, 63417, 14939, 6205, 5705, 6345, 72, 62, 17, 15, 17, 17, 12, 15, 20, 198, 197, 197, 58, 18, 19, 16, 60, 3137, 364, 147724, 1248, 197, 58, 18, 60, 23105, 1178, 364, 13936, 311, 7885, 197, 58, 18, 20, 17, 60, 2656, 364, 54, 14939, 6, 2515, 25, 1758, 1110, 8301, 25, 17, 17, 15, 16, 20, 6324, 14939, 6205, 5705, 6345, 72, 62, 17, 15, 17, 17, 12, 15, 20, 10360, 22175, 14939, 198, 197, 58, 20, 60, 23105, 1178, 364, 785, 1910, 82608, 23421, 197, 58, 21, 60, 23105, 1178, 364, 21, 11, 19, 23, 24, 11, 15, 20, 17, 1248, 197, 58, 22, 60, 23105, 1178, 364, 9709, 304, 7885, 197, 58, 18, 20, 23, 60, 2656, 364, 22574, 6, 2515, 25, 1758, 1110, 8301, 25, 17, 17, 15, 16, 20, 6324, 14939, 6205, 5705, 6345, 72, 62, 17, 15, 17, 17, 12, 15, 20, 10360, 14, 22574, 2763, 14939, 198, 197, 58, 18, 21, 15, 60, 14496, 364, 6953, 2576, 1248, 197, 58, 18, 21, 17, 60, 2656, 364, 90951, 6, 2515, 25, 1758, 1110, 8301, 25, 17, 17, 15, 16, 20, 6324, 14939, 6205, 5705, 6345, 72, 62, 17, 15, 17, 17, 12, 15, 20, 10360, 14, 90951, 198, 197, 58, 18, 21, 18, 60, 2656, 364, 24341, 6, 2515, 25, 1758, 1110, 8301, 25, 17, 17, 15, 16, 20, 6324, 14939, 6205, 5705, 6345, 72, 62, 17, 15, 17, 17, 12, 15, 20, 10360, 14, 24341, 198, 197, 58, 18, 21, 19, 60, 2656, 364, 34, 258, 42598, 5696, 6, 2515, 25, 1758, 1110, 8301, 25, 17, 17, 15, 16, 20, 6324, 14939, 6205, 5705, 6345, 72, 62, 17, 15, 17, 17, 12, 15, 20, 10360, 11295, 258, 42598, 5696, 198, 197, 58, 18, 21, 20, 60, 2656, 364, 35, 681, 6, 2515, 25, 1758, 1110, 8301, 25, 17, 17, 15, 16, 20, 6324, 14939, 6205, 5705, 6345, 72, 62, 17, 15, 17, 17, 12, 15, 20, 10360, 14953, 681, 198, 197, 58, 17, 24, 21, 60, 2656, 364, 20470, 6, 2515, 25, 1758, 1110, 8301, 25, 17, 17, 15, 16, 20, 6324, 14939, 6205, 5705, 6345, 72, 62, 17, 15, 17, 17, 12, 15, 20, 10360, 14, 20470, 198, 197, 58, 18, 21, 21, 60, 2656, 364, 96141, 6, 2515, 25, 1758, 1110, 8301, 25, 17, 17, 15, 16, 20, 6324, 14939, 6205, 5705, 6345, 72, 62, 17, 15, 17, 17, 12, 15, 20, 10360, 12318, 8782, 198, 197, 58, 18, 21, 22, 60, 2656, 364, 50140, 1011, 6, 2515, 25, 1758, 1110, 8301, 25, 17, 17, 15, 16, 20, 6324, 14939, 6205, 5705, 6345, 72, 62, 17, 15, 17, 17, 12, 15, 20, 10360, 12318, 321, 1011, 198, 197, 58, 18, 21, 23, 60, 2656, 364, 38, 20467, 16974, 6, 2515, 25, 1758, 1110, 8301, 25, 17, 17, 15, 16, 20, 6324, 14939, 6205, 5705, 6345, 72, 62, 17, 15, 17, 17, 12, 15, 20, 10360, 15792, 20467, 16974, 198, 197, 58, 18, 21, 24, 60, 2656, 364, 86015, 1568, 6, 2515, 25, 1758, 1110, 8301, 25, 17, 17, 15, 16, 20, 6324, 14939, 6205, 5705, 6345, 72, 62, 17, 15, 17, 17, 12, 15, 20, 10360, 7434, 2015, 1568, 198, 197, 58, 18, 22, 15, 60, 2656, 364, 43538, 320, 81162, 21636, 2515, 25, 1758, 1110, 8301, 25, 17, 17, 15, 16, 20, 6324, 14939, 6205, 5705, 6345, 72, 62, 17, 15, 17, 17, 12, 15, 20, 10360, 10270, 12780, 8361, 81162, 340, 197, 58, 18, 22, 16, 60, 2656, 364, 24128, 6, 2515, 25, 1758, 1110, 8301, 25, 17, 17, 15, 16, 20, 6324, 14939, 6205, 5705, 6345, 72, 62, 17, 15, 17, 17, 12, 15, 20, 10360, 10270, 11524, 198, 197, 58, 18, 22, 17, 60, 2656, 364, 18098, 287, 6, 2515, 25, 1758, 1110, 8301, 25, 17, 17, 15, 16, 20, 6324, 14939, 6205, 5705, 6345, 72, 62, 17, 15, 17, 17, 12, 15, 20, 10360, 16341, 70859, 198, 197, 58, 18, 22, 18, 60, 2656, 364, 52204, 5696, 6, 2515, 25, 1758, 1110, 8301, 25, 17, 17, 15, 16, 20, 6324, 14939, 6205, 5705, 6345, 72, 62, 17, 15, 17, 17, 12, 15, 20, 10360, 14, 52204, 5696, 198, 197, 58, 18, 22, 19, 60, 2656, 364, 32904, 15149, 6, 2515, 25, 1758, 1110, 8301, 25, 17, 17, 15, 16, 20, 6324, 14939, 6205, 5705, 6345, 72, 62, 17, 15, 17, 17, 12, 15, 20, 10360, 16341, 78, 15149, 198, 197, 58, 18, 22, 20, 60, 2656, 364, 50, 3314, 417, 552, 6, 2515, 25, 1758, 1110, 8301, 25, 17, 17, 15, 16, 20, 6324, 14939, 6205, 5705, 6345, 72, 62, 17, 15, 17, 17, 12, 15, 20, 10360, 11374, 3314, 417, 552, 198, 197, 58, 18, 22, 21, 60, 2656, 364, 785, 15715, 6, 2515, 25, 1758, 1110, 8301, 25, 17, 17, 15, 16, 20, 6324, 14939, 6205, 5705, 6345, 72, 62, 17, 15, 17, 17, 12, 15, 20, 10360, 47748, 15715, 198, 197, 58, 18, 22, 23, 60, 14496, 364, 9499, 5696, 1248, 197, 58, 18, 23, 15, 60, 2656, 364, 73591, 6, 2515, 25, 1758, 1110, 8301, 25, 17, 17, 15, 16, 20, 6324, 14939, 6205, 5705, 6345, 72, 62, 17, 15, 17, 17, 12, 15, 20, 10360, 10360, 29880, 198, 197, 58, 18, 23, 16, 60, 2656, 364, 17117, 277, 49029, 6, 2515, 25, 1758, 1110, 8301, 25, 17, 17, 15, 16, 20, 6324, 14939, 6205, 5705, 6345, 72, 62, 17, 15, 17, 17, 12, 15, 20, 10360, 10360, 406, 277, 49029, 198, 197, 58, 18, 23, 17, 60, 2656, 364, 6953, 25555, 6, 2515, 25, 1758, 1110, 8301, 25, 17, 17, 15, 16, 20, 6324, 14939, 6205, 5705, 6345, 72, 62, 17, 15, 17, 17, 12, 15, 20, 10360, 14, 6953, 25555, 198, 197, 58, 18, 23, 18, 60, 2656, 364, 38463, 6, 2515, 25, 1758, 1110, 8301, 25, 17, 17, 15, 16, 20, 6324, 14939, 6205, 5705, 6345, 72, 62, 17, 15, 17, 17, 12, 15, 20, 10360, 14, 38463, 198, 197, 58, 18, 23, 19, 60, 2656, 364, 8852, 32059, 6, 2515, 25, 1758, 1110, 8301, 25, 17, 17, 15, 16, 20, 6324, 14939, 6205, 5705, 6345, 72, 62, 17, 15, 17, 17, 12, 15, 20, 10360, 14, 8852, 32059, 198, 197, 58, 18, 23, 20, 60, 2656, 364, 43403, 5159, 6, 2515, 25, 1758, 1110, 8301, 25, 17, 17, 15, 16, 20, 6324, 14939, 6205, 5705, 6345, 72, 62, 17, 15, 17, 17, 12, 15, 20, 10360, 11295, 45086, 1566, 2117, 64, 198, 197, 58, 18, 23, 21, 60, 2656, 364, 30780, 6, 2515, 25, 1758, 1110, 8301, 25, 17, 17, 15, 16, 20, 6324, 14939, 6205, 5705, 6345, 72, 62, 17, 15, 17, 17, 12, 15, 20, 10360, 25646, 4084, 198, 197, 58, 18, 23, 22, 60, 2656, 364, 41547, 5159, 6, 2515, 25, 1758, 1110, 8301, 25, 17, 17, 15, 16, 20, 6324, 14939, 6205, 5705, 6345, 72, 62, 17, 15, 17, 17, 12, 15, 20, 10360, 7434, 14768, 1566, 2117, 64, 198, 197, 58, 18, 23, 23, 60, 2656, 364, 44, 3587, 615, 32461, 6, 2515, 25, 1758, 1110, 8301, 25, 17, 17, 15, 16, 20, 6324, 14939, 6205, 5705, 6345, 72, 62, 17, 15, 17, 17, 12, 15, 20, 10360, 10270, 3587, 615, 32461, 198, 197, 58, 18, 23, 24, 60, 2656, 364, 43935, 6326, 6, 2515, 25, 1758, 1110, 8301, 25, 17, 17, 15, 16, 20, 6324, 14939, 6205, 5705, 6345, 72, 62, 17, 15, 17, 17, 12, 15, 20, 10360, 10270, 3310, 2089, 559, 198, 197, 58, 18, 24, 15, 60, 2656, 364, 25221, 5159, 6, 2515, 25, 1758, 1110, 8301, 25, 17, 17, 15, 16, 20, 6324, 14939, 6205, 5705, 6345, 72, 62, 17, 15, 17, 17, 12, 15, 20, 10360, 20290, 2364, 1566, 2117, 64, 198, 197, 58, 18, 24, 16, 60, 2656, 364, 46, 346, 9166, 6, 2515, 25, 1758, 1110, 8301, 25, 17, 17, 15, 16, 20, 6324, 14939, 6205, 5705, 6345, 72, 62, 17, 15, 17, 17, 12, 15, 20, 10360, 17532, 346, 9166, 198, 197, 58, 18, 24, 17, 60, 2656, 364, 25018, 5159, 6, 2515, 25, 1758, 1110, 8301, 25, 17, 17, 15, 16, 20, 6324, 14939, 6205, 5705, 6345, 72, 62, 17, 15, 17, 17, 12, 15, 20, 10360, 11374, 2898, 1566, 2117, 64, 198, 197, 58, 18, 24, 18, 60, 2656, 364, 12593, 5696, 6, 2515, 25, 1758, 1110, 8301, 25, 17, 17, 15, 16, 20, 6324, 14939, 6205, 5705, 6345, 72, 62, 17, 15, 17, 17, 12, 15, 20, 10360, 11295, 471, 5696, 198, 197, 58, 18, 24, 20, 60, 14496, 364, 13424, 1248, 197, 58, 18, 24, 22, 60, 2656, 364, 88067, 1167, 14867, 6, 2515, 25, 1758, 1110, 8301, 25, 17, 17, 15, 16, 20, 6324, 14939, 6205, 5705, 6345, 72, 62, 17, 15, 17, 17, 12, 15, 20, 10360, 10360, 1016, 1167, 2089, 13539, 198, 197, 58, 18, 24, 23, 60, 2656, 364, 88067, 1167, 24427, 6, 2515, 25, 1758, 1110, 8301, 25, 17, 17, 15, 16, 20, 6324, 14939, 6205, 5705, 6345, 72, 62, 17, 15, 17, 17, 12, 15, 20, 10360, 10360, 1016, 1167, 2646, 89031, 198, 197, 58, 18, 24, 24, 60, 2656, 364, 88067, 1167, 30394, 6326, 6, 2515, 25, 1758, 1110, 8301, 25, 17, 17, 15, 16, 20, 6324, 14939, 6205, 5705, 6345, 72, 62, 17, 15, 17, 17, 12, 15, 20, 10360, 10360, 1016, 1167, 1604, 682, 2089, 559, 198, 197, 58, 19, 15, 15, 60, 2656, 364, 88067, 1167, 21718, 6, 2515, 25, 1758, 1110, 8301, 25, 17, 17, 15, 16, 20, 6324, 14939, 6205, 5705, 6345, 72, 62, 17, 15, 17, 17, 12, 15, 20, 10360, 10360, 1016, 1167, 2568, 635, 198, 197, 58, 19, 15, 16, 60, 2656, 364, 18727, 5918, 2449, 6, 2515, 25, 1758, 1110, 8301, 25, 17, 17, 15, 16, 20, 6324, 14939, 6205, 5705, 6345, 72, 62, 17, 15, 17, 17, 12, 15, 20, 10360, 14, 18727, 5918, 2449, 198, 197, 58, 19, 15, 17, 60, 2656, 364, 51861, 20448, 6, 2515, 25, 1758, 1110, 8301, 25, 17, 17, 15, 16, 20, 6324, 14939, 6205, 5705, 6345, 72, 62, 17, 15, 17, 17, 12, 15, 20, 10360, 16276, 1003, 812, 2089, 1307, 554, 198, 197, 58, 19, 15, 18, 60, 2656, 364, 1359, 89, 38357, 20448, 6, 2515, 25, 1758, 1110, 8301, 25, 17, 17, 15, 16, 20, 6324, 14939, 6205, 5705, 6345, 72, 62, 17, 15, 17, 17, 12, 15, 20, 10360, 14, 1359, 89, 38357, 2089, 1307, 554, 198, 197, 58, 19, 15, 19, 60, 2656, 364, 88665, 530, 2142, 6, 2515, 25, 1758, 1110, 8301, 25, 17, 17, 15, 16, 20, 6324, 14939, 6205, 5705, 6345, 72, 62, 17, 15, 17, 17, 12, 15, 20, 10360, 14, 88665, 530, 2142, 198, 197, 58, 19, 15, 20, 60, 2656, 364, 16001, 355, 3452, 6, 2515, 25, 1758, 1110, 8301, 25, 17, 17, 15, 16, 20, 6324, 14939, 6205, 5705, 6345, 72, 62, 17, 15, 17, 17, 12, 15, 20, 10360, 11295, 20341, 3452, 198, 197, 58, 19, 15, 21, 60, 2656, 364, 39, 24380, 884, 6, 2515, 25, 1758, 1110, 8301, 25, 17, 17, 15, 16, 20, 6324, 14939, 6205, 5705, 6345, 72, 62, 17, 15, 17, 17, 12, 15, 20, 10360, 23354, 24380, 884, 198, 197, 58, 19, 15, 22, 60, 2656, 364, 13424, 315, 8038, 6, 2515, 25, 1758, 1110, 8301, 25, 17, 17, 15, 16, 20, 6324, 14939, 6205, 5705, 6345, 72, 62, 17, 15, 17, 17, 12, 15, 20, 10360, 14, 13424, 3575, 13171, 1835, 198, 197, 58, 17, 24, 20, 60, 2656, 364, 1427, 67227, 5616, 6, 2515, 25, 1758, 1110, 8301, 25, 17, 17, 15, 16, 20, 6324, 14939, 6205, 5705, 6345, 72, 62, 17, 15, 17, 17, 12, 15, 20, 10360, 14, 13424, 3575, 27588, 2210, 2, 1427, 67227, 27588, 2210, 198, 197, 58, 19, 15, 23, 60, 2656, 364, 47564, 23665, 7203, 6, 2515, 25, 1758, 1110, 8301, 25, 17, 17, 15, 16, 20, 6324, 14939, 6205, 5705, 6345, 72, 62, 17, 15, 17, 17, 12, 15, 20, 10360, 14, 47564, 1243, 90646, 70325, 198, 197, 58, 19, 15, 24, 60, 2656, 364, 48752, 6, 2515, 25, 1758, 1110, 8301, 25, 17, 17, 15, 16, 20, 6324, 14939, 6205, 5705, 6345, 72, 62, 17, 15, 17, 17, 12, 15, 20, 10360, 14, 13424, 3575, 10598, 5359, 198, 197, 58, 19, 16, 15, 60, 2656, 364, 43935, 48993, 6, 2515, 25, 1758, 1110, 8301, 25, 17, 17, 15, 16, 20, 6324, 14939, 6205, 5705, 6345, 72, 62, 17, 15, 17, 17, 12, 15, 20, 10360, 10270, 3310, 1566, 4188, 198, 197, 58, 19, 16, 16, 60, 2656, 364, 44, 7443, 278, 20448, 6, 2515, 25, 1758, 1110, 8301, 25, 17, 17, 15, 16, 20, 6324, 14939, 6205, 5705, 6345, 72, 62, 17, 15, 17, 17, 12, 15, 20, 10360, 10270, 7443, 278, 2089, 1307, 554, 198, 197, 58, 19, 16, 17, 60, 2656, 364, 46, 5566, 6908, 20448, 6, 2515, 25, 1758, 1110, 8301, 25, 17, 17, 15, 16, 20, 6324, 14939, 6205, 5705, 6345, 72, 62, 17, 15, 17, 17, 12, 15, 20, 10360, 17532, 5566, 6908, 2089, 1307, 554, 198, 197, 58, 19, 16, 18, 60, 2656, 364, 47707, 20448, 6, 2515, 25, 1758, 1110, 8301, 25, 17, 17, 15, 16, 20, 6324, 14939, 6205, 5705, 6345, 72, 62, 17, 15, 17, 17, 12, 15, 20, 10360, 19382, 15579, 2089, 1307, 554, 198, 197, 58, 19, 16, 19, 60, 2656, 364, 50, 45388, 1103, 20448, 6, 2515, 25, 1758, 1110, 8301, 25, 17, 17, 15, 16, 20, 6324, 14939, 6205, 5705, 6345, 72, 62, 17, 15, 17, 17, 12, 15, 20, 10360, 11374, 45388, 1103, 2089, 1307, 554, 198, 197, 58, 19, 16, 20, 60, 2656, 364, 39041, 73, 3101, 20448, 6, 2515, 25, 1758, 1110, 8301, 25, 17, 17, 15, 16, 20, 6324, 14939, 6205, 5705, 6345, 72, 62, 17, 15, 17, 17, 12, 15, 20, 10360, 11374, 301, 73, 3101, 2089, 1307, 554, 198, 197, 58, 19, 16, 21, 60, 2656, 364, 50, 859, 3891, 9145, 6, 2515, 25, 1758, 1110, 8301, 25, 17, 17, 15, 16, 20, 6324, 14939, 6205, 5705, 6345, 72, 62, 17, 15, 17, 17, 12, 15, 20, 10360, 11374, 859, 3891, 62, 32658, 198, 197, 58, 19, 16, 22, 60, 2656, 364, 28684, 6, 2515, 25, 1758, 1110, 8301, 25, 17, 17, 15, 16, 20, 6324, 14939, 6205, 5705, 6345, 72, 62, 17, 15, 17, 17, 12, 15, 20, 10360, 22175, 277, 198, 197, 58, 19, 16, 24, 60, 14496, 364, 3326, 11975, 1248, 39, 35586, 21866, 25, 4710, 151645, 198, 151644, 77091, 198, 13708, 766, 93376, 4226, 3425, 8697, 39946, 20691, 323, 53350, 6272, 25294, 20691, 525, 2176, 7407, 304, 29790, 11, 358, 1184, 311, 1401, 705, 1817, 16733, 13, 576, 2711, 3745, 448, 877, 508, 18, 18, 15, 60, 646, 387, 1483, 311, 2711, 26587, 369, 1817, 16733, 13, 358, 3278, 1191, 553, 15039, 369, 330, 10331, 39946, 20691, 1, 311, 8253, 1181, 3728, 3918, 26865, 397, 73594, 1313, 508, 18, 18, 15, 60, 508, 10331, 39946, 20691, 60, 508, 16, 60, 73594, 151645]
+[INFO:swift] [INPUT] <|im_start|>system
+You are a browser interaction assistant designed to execute step-by-step browser operations efficiently and precisely to complete the user's task. You are provided with specific tasks and webpage-related information, and you need to output accurate actions to accomplish the user's task.
+
+Here's the information you'll have:
+The user's objective: This is the task you're trying to complete.
+The current web page's accessibility tree: This is a simplified representation of the webpage, providing key information.
+The open tabs: These are the tabs you have open.
+The previous actions: There are the actions you just performed. It may be helpful to track your progress.
+
+The actions you can perform fall into several categories:
+
+Page Operation Actions:
+`click [id] [content]`: This action clicks on an element with a specific id on the webpage.
+`type [id] [content] [press_enter_after=0|1]`: Use this to type the content into the field with id. By default, the ""Enter"" key is pressed after typing unless press_enter_after is set to 0.
+`hover [id] [content]`: Hover over an element with id.
+`press [key_comb]`:  Simulates the pressing of a key combination on the keyboard (e.g., Ctrl+v).
+`scroll [down|up]`: Scroll the page up or down.
+
+Tab Management Actions:
+`new_tab`: Open a new, empty browser tab.
+`tab_focus [tab_index]`: Switch the browser's focus to a specific tab using its index.
+`close_tab`: Close the currently active tab.
+
+URL Navigation Actions:
+`goto [url]`: Navigate to a specific URL.
+`go_back`: Navigate to the previously viewed page.
+`go_forward`: Navigate to the next page (if a previous 'go_back' action was performed).
+
+Completion Action:
+`stop [answer]`: Issue this action when you believe the task is complete. If the objective is to find a text-based answer, provide the answer in the bracket. If you believe the task is impossible to complete, provide the answer as ""N/A"" in the bracket.
+
+To be successful, it is very important to follow the following rules:
+1. You should only issue an action that is valid given the current observation.
+2. You should only issue one action at a time.
+3. You should follow the examples to reason step by step and then issue the next action.
+4. You should refer to historical actions when issue an action and try not to make repetitive actions
+5. All reasoning must be inside `<think></think>` tags, and there must be no output before `<think></think>`.
+6. After `<think></think>`, only the action should be generated in the correct format, enclosed in code fences. For example:
+   <think>This button looks relevant to my goal. Clicking it should take me to the next step.</think>
+   ```click [id] [content]```
+7. Issue the stop action when you think you have achieved the objective. Don’t generate anything after stop.
+8. Always format actions correctly: 
+```command [parameters]```
+For example, if searching for ""death row inmates in the US"" in a search field with ID `21`, correctly format it as:
+```type [21] [death row inmates in the US] [1]```
+Avoid incorrect formats that omit brackets around parameters or numeric values.
+<|im_end|>
+<|im_start|>user
+
+Objective: Are Blue Grass Airport and Knox County Regional Airport both located in the state of Maine, United States?
+Observation: [292] RootWebArea 'User:The other Kiwix guy/Landing' focused: True url: http://localhost:22015/wikipedia_en_all_maxi_2022-05/A/User:The_other_Kiwix_guy/Landing
+	[330] textbox "Search 'Wikipedia'" required: False
+	[336] link 'Go to welcome page' url: http://localhost:22015/
+		[337] button '🏠'
+	[338] link "Go to the main page of 'Wikipedia'" url: http://localhost:22015/wikipedia_en_all_maxi_2022-05/
+		[339] button 'Wikipedia'
+	[340] link 'Go to a randomly selected page' url: http://localhost:22015/random?content=wikipedia_en_all_maxi_2022-05
+		[341] button '🎲'
+	[3] StaticText 'Welcome to '
+	[352] link 'Wikipedia' url: http://localhost:22015/wikipedia_en_all_maxi_2022-05/A/Wikipedia
+	[5] StaticText 'The free encyclopedia.'
+	[6] StaticText '6,489,052'
+	[7] StaticText ' articles in '
+	[358] link 'English' url: http://localhost:22015/wikipedia_en_all_maxi_2022-05/A/English_Wikipedia
+	[360] heading 'Arts'
+	[362] link 'Architecture' url: http://localhost:22015/wikipedia_en_all_maxi_2022-05/A/Architecture
+	[363] link 'Books' url: http://localhost:22015/wikipedia_en_all_maxi_2022-05/A/Books
+	[364] link 'Cinematography' url: http://localhost:22015/wikipedia_en_all_maxi_2022-05/A/Cinematography
+	[365] link 'Dance' url: http://localhost:22015/wikipedia_en_all_maxi_2022-05/A/Dance
+	[296] link 'Design' url: http://localhost:22015/wikipedia_en_all_maxi_2022-05/A/Design
+	[366] link 'Fashion' url: http://localhost:22015/wikipedia_en_all_maxi_2022-05/A/Fashion
+	[367] link 'Films' url: http://localhost:22015/wikipedia_en_all_maxi_2022-05/A/Films
+	[368] link 'Gastronomy' url: http://localhost:22015/wikipedia_en_all_maxi_2022-05/A/Gastronomy
+	[369] link 'Literature' url: http://localhost:22015/wikipedia_en_all_maxi_2022-05/A/Literature
+	[370] link 'Magic (illusion)' url: http://localhost:22015/wikipedia_en_all_maxi_2022-05/A/Magic_(illusion)
+	[371] link 'Music' url: http://localhost:22015/wikipedia_en_all_maxi_2022-05/A/Music
+	[372] link 'Painting' url: http://localhost:22015/wikipedia_en_all_maxi_2022-05/A/Painting
+	[373] link 'Photography' url: http://localhost:22015/wikipedia_en_all_maxi_2022-05/A/Photography
+	[374] link 'Poetry' url: http://localhost:22015/wikipedia_en_all_maxi_2022-05/A/Poetry
+	[375] link 'Sculpture' url: http://localhost:22015/wikipedia_en_all_maxi_2022-05/A/Sculpture
+	[376] link 'Theatre' url: http://localhost:22015/wikipedia_en_all_maxi_2022-05/A/Theatre
+	[378] heading 'Geography'
+	[380] link 'Africa' url: http://localhost:22015/wikipedia_en_all_maxi_2022-05/A/Africa
+	[381] link 'Antarctica' url: http://localhost:22015/wikipedia_en_all_maxi_2022-05/A/Antarctica
+	[382] link 'Arctic' url: http://localhost:22015/wikipedia_en_all_maxi_2022-05/A/Arctic
+	[383] link 'Asia' url: http://localhost:22015/wikipedia_en_all_maxi_2022-05/A/Asia
+	[384] link 'Caribbean' url: http://localhost:22015/wikipedia_en_all_maxi_2022-05/A/Caribbean
+	[385] link 'Central America' url: http://localhost:22015/wikipedia_en_all_maxi_2022-05/A/Central_America
+	[386] link 'Europe' url: http://localhost:22015/wikipedia_en_all_maxi_2022-05/A/Europe
+	[387] link 'Latin America' url: http://localhost:22015/wikipedia_en_all_maxi_2022-05/A/Latin_America
+	[388] link 'Mediterranean' url: http://localhost:22015/wikipedia_en_all_maxi_2022-05/A/Mediterranean
+	[389] link 'Middle East' url: http://localhost:22015/wikipedia_en_all_maxi_2022-05/A/Middle_East
+	[390] link 'North America' url: http://localhost:22015/wikipedia_en_all_maxi_2022-05/A/North_America
+	[391] link 'Oceania' url: http://localhost:22015/wikipedia_en_all_maxi_2022-05/A/Oceania
+	[392] link 'South America' url: http://localhost:22015/wikipedia_en_all_maxi_2022-05/A/South_America
+	[393] link 'Cartography' url: http://localhost:22015/wikipedia_en_all_maxi_2022-05/A/Cartography
+	[395] heading 'History'
+	[397] link 'Ancient Egypt' url: http://localhost:22015/wikipedia_en_all_maxi_2022-05/A/Ancient_Egypt
+	[398] link 'Ancient Greece' url: http://localhost:22015/wikipedia_en_all_maxi_2022-05/A/Ancient_Greece
+	[399] link 'Ancient Near East' url: http://localhost:22015/wikipedia_en_all_maxi_2022-05/A/Ancient_Near_East
+	[400] link 'Ancient Rome' url: http://localhost:22015/wikipedia_en_all_maxi_2022-05/A/Ancient_Rome
+	[401] link 'Archaeology' url: http://localhost:22015/wikipedia_en_all_maxi_2022-05/A/Archaeology
+	[402] link 'British Empire' url: http://localhost:22015/wikipedia_en_all_maxi_2022-05/A/British_Empire
+	[403] link 'Byzantine Empire' url: http://localhost:22015/wikipedia_en_all_maxi_2022-05/A/Byzantine_Empire
+	[404] link 'Colonialism' url: http://localhost:22015/wikipedia_en_all_maxi_2022-05/A/Colonialism
+	[405] link 'Crusades' url: http://localhost:22015/wikipedia_en_all_maxi_2022-05/A/Crusades
+	[406] link 'Heraldry' url: http://localhost:22015/wikipedia_en_all_maxi_2022-05/A/Heraldry
+	[407] link 'History of science' url: http://localhost:22015/wikipedia_en_all_maxi_2022-05/A/History_of_science
+	[295] link 'Imperial China' url: http://localhost:22015/wikipedia_en_all_maxi_2022-05/A/History_of_China#Imperial_China
+	[408] link 'Indian independence movement' url: http://localhost:22015/wikipedia_en_all_maxi_2022-05/A/Indian_independence_movement
+	[409] link 'Japan' url: http://localhost:22015/wikipedia_en_all_maxi_2022-05/A/History_of_Japan
+	[410] link 'Middle Ages' url: http://localhost:22015/wikipedia_en_all_maxi_2022-05/A/Middle_Ages
+	[411] link 'Mughal Empire' url: http://localhost:22015/wikipedia_en_all_maxi_2022-05/A/Mughal_Empire
+	[412] link 'Ottoman Empire' url: http://localhost:22015/wikipedia_en_all_maxi_2022-05/A/Ottoman_Empire
+	[413] link 'Russian Empire' url: http://localhost:22015/wikipedia_en_all_maxi_2022-05/A/Russian_Empire
+	[414] link 'Sasanian Empire' url: http://localhost:22015/wikipedia_en_all_maxi_2022-05/A/Sasanian_Empire
+	[415] link 'Seljuk Empire' url: http://localhost:22015/wikipedia_en_all_maxi_2022-05/A/Seljuk_Empire
+	[416] link 'Soviet Union' url: http://localhost:22015/wikipedia_en_all_maxi_2022-05/A/Soviet_Union
+	[417] link 'War' url: http://localhost:22015/wikipedia_en_all_maxi_2022-05/A/War
+	[419] heading 'Sciences'
+HISTORY_ACTION: 
+
+<|im_end|>
+<|im_start|>assistant
+<think>To answer whether Blue Grass Airport and Knox County Regional Airport are both located in Maine, I need to look up each airport. The search box with id [330] can be used to search Wikipedia for each airport. I'll start by searching for "Blue Grass Airport" to determine its location.</think>
+```type [330] [Blue Grass Airport] [1]```<|im_end|>
+[INFO:swift] [LABELS_IDS] [-100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, 13708, 766, 93376, 4226, 3425, 8697, 39946, 20691, 323, 53350, 6272, 25294, 20691, 525, 2176, 7407, 304, 29790, 11, 358, 1184, 311, 1401, 705, 1817, 16733, 13, 576, 2711, 3745, 448, 877, 508, 18, 18, 15, 60, 646, 387, 1483, 311, 2711, 26587, 369, 1817, 16733, 13, 358, 3278, 1191, 553, 15039, 369, 330, 10331, 39946, 20691, 1, 311, 8253, 1181, 3728, 3918, 26865, 397, 73594, 1313, 508, 18, 18, 15, 60, 508, 10331, 39946, 20691, 60, 508, 16, 60, 73594, 151645]
+[INFO:swift] [LABELS] [-100 * 3341]<think>To answer whether Blue Grass Airport and Knox County Regional Airport are both located in Maine, I need to look up each airport. The search box with id [330] can be used to search Wikipedia for each airport. I'll start by searching for "Blue Grass Airport" to determine its location.</think>
+```type [330] [Blue Grass Airport] [1]```<|im_end|>
+[INFO:swift] Dataset Token Length: 2825.342123±894.556689, min=828.000000, max=13246.000000, size=28291
+[INFO:swift] Dataset Token Length: 2729.076923±777.734922, min=894.000000, max=4016.000000, size=26
+[INFO:swift] The TrainArguments will be saved in: /group/40143/hongzhuyi/ms-swift/output/v0-20250917-010604/args.json
+[INFO:swift] model: Qwen2ForCausalLM(
+  (model): Qwen2Model(
+    (embed_tokens): Embedding(152064, 3584)
+    (layers): ModuleList(
+      (0-27): 28 x Qwen2DecoderLayer(
+        (self_attn): Qwen2Attention(
+          (q_proj): Linear(in_features=3584, out_features=3584, bias=True)
+          (k_proj): Linear(in_features=3584, out_features=512, bias=True)
+          (v_proj): Linear(in_features=3584, out_features=512, bias=True)
+          (o_proj): Linear(in_features=3584, out_features=3584, bias=False)
+        )
+        (mlp): Qwen2MLP(
+          (gate_proj): Linear(in_features=3584, out_features=18944, bias=False)
+          (up_proj): Linear(in_features=3584, out_features=18944, bias=False)
+          (down_proj): Linear(in_features=18944, out_features=3584, bias=False)
+          (act_fn): SiLU()
+        )
+        (input_layernorm): Qwen2RMSNorm((0,), eps=1e-06)
+        (post_attention_layernorm): Qwen2RMSNorm((0,), eps=1e-06)
+      )
+    )
+    (norm): Qwen2RMSNorm((0,), eps=1e-06)
+    (rotary_emb): Qwen2RotaryEmbedding()
+  )
+  (lm_head): Linear(in_features=3584, out_features=152064, bias=False)
+)
+[INFO:swift] model_parameter_info: Qwen2ForCausalLM: 7615.6165M Params (7615.6165M Trainable [100.0000%]), 0.0001M Buffers.
+/group/40143/hongzhuyi/ms-swift/swift/trainers/mixin.py:104: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `Seq2SeqTrainer.__init__`. Use `processing_class` instead.
+  super().__init__(
+/group/40143/hongzhuyi/ms-swift/swift/trainers/mixin.py:104: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `Seq2SeqTrainer.__init__`. Use `processing_class` instead.
+  super().__init__(
+/group/40143/hongzhuyi/ms-swift/swift/trainers/mixin.py:104: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `Seq2SeqTrainer.__init__`. Use `processing_class` instead.
+  super().__init__(
+/group/40143/hongzhuyi/ms-swift/swift/trainers/mixin.py:104: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `Seq2SeqTrainer.__init__`. Use `processing_class` instead.
+  super().__init__(
+/group/40143/hongzhuyi/ms-swift/swift/trainers/mixin.py:104: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `Seq2SeqTrainer.__init__`. Use `processing_class` instead.
+  super().__init__(
+/group/40143/hongzhuyi/ms-swift/swift/trainers/mixin.py:104: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `Seq2SeqTrainer.__init__`. Use `processing_class` instead.
+  super().__init__(
+/group/40143/hongzhuyi/ms-swift/swift/trainers/mixin.py:104: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `Seq2SeqTrainer.__init__`. Use `processing_class` instead.
+  super().__init__(
+/group/40143/hongzhuyi/ms-swift/swift/trainers/mixin.py:104: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `Seq2SeqTrainer.__init__`. Use `processing_class` instead.
+  super().__init__(
+Detected kernel version 5.4.241, which is below the recommended minimum of 5.5.0; this can cause the process to hang. It is recommended to upgrade the kernel to the minimum version or higher.
+[INFO:swift] use_reentrant: True
+[INFO:swift] The logging file will be saved in: /group/40143/hongzhuyi/ms-swift/output/v0-20250917-010604/logging.jsonl
+Parameter Offload: Total persistent parameters: 333312 in 141 params
+
+
                                                        
+

qwen2.5-7b-2225q-2069q-1369q-sft+rft-newbs-old-click-2ep-lr5e-6/args.json

@@ -0,0 +1,381 @@
+{
+  "output_dir": "/group/40143/hongzhuyi/ms-swift/output/v1-20250917-010849",
+  "overwrite_output_dir": false,
+  "do_train": false,
+  "do_eval": false,
+  "do_predict": false,
+  "eval_strategy": "epoch",
+  "prediction_loss_only": false,
+  "per_device_train_batch_size": 2,
+  "per_device_eval_batch_size": 1,
+  "per_gpu_train_batch_size": null,
+  "per_gpu_eval_batch_size": null,
+  "gradient_accumulation_steps": 4,
+  "eval_accumulation_steps": null,
+  "eval_delay": 0,
+  "torch_empty_cache_steps": null,
+  "learning_rate": 5e-06,
+  "weight_decay": 0.1,
+  "adam_beta1": 0.9,
+  "adam_beta2": 0.95,
+  "adam_epsilon": 1e-08,
+  "max_grad_norm": 1.0,
+  "num_train_epochs": 2.0,
+  "max_steps": -1,
+  "lr_scheduler_type": "cosine",
+  "lr_scheduler_kwargs": null,
+  "warmup_ratio": 0.05,
+  "warmup_steps": 0,
+  "log_level": "passive",
+  "log_level_replica": "warning",
+  "log_on_each_node": true,
+  "logging_dir": "/group/40143/hongzhuyi/ms-swift/output/v1-20250917-010849/runs",
+  "logging_strategy": "steps",
+  "logging_first_step": true,
+  "logging_steps": 1,
+  "logging_nan_inf_filter": true,
+  "save_strategy": "epoch",
+  "save_steps": 500,
+  "save_total_limit": null,
+  "save_safetensors": true,
+  "save_on_each_node": false,
+  "save_only_model": false,
+  "restore_callback_states_from_checkpoint": false,
+  "no_cuda": false,
+  "use_cpu": false,
+  "use_mps_device": false,
+  "seed": 42,
+  "data_seed": 42,
+  "jit_mode_eval": false,
+  "use_ipex": false,
+  "bf16": true,
+  "fp16": false,
+  "fp16_opt_level": "O1",
+  "half_precision_backend": "auto",
+  "bf16_full_eval": false,
+  "fp16_full_eval": false,
+  "tf32": null,
+  "local_rank": 0,
+  "ddp_backend": null,
+  "tpu_num_cores": null,
+  "tpu_metrics_debug": false,
+  "debug": null,
+  "dataloader_drop_last": false,
+  "eval_steps": 2000.0,
+  "dataloader_num_workers": 48,
+  "dataloader_prefetch_factor": null,
+  "past_index": -1,
+  "run_name": "/group/40143/hongzhuyi/ms-swift/output/v1-20250917-010849",
+  "disable_tqdm": null,
+  "remove_unused_columns": true,
+  "label_names": null,
+  "load_best_model_at_end": false,
+  "metric_for_best_model": "loss",
+  "greater_is_better": false,
+  "ignore_data_skip": false,
+  "fsdp": "",
+  "fsdp_min_num_params": 0,
+  "fsdp_config": null,
+  "fsdp_transformer_layer_cls_to_wrap": null,
+  "accelerator_config": {
+    "dispatch_batches": false
+  },
+  "deepspeed": {
+    "fp16": {
+      "enabled": "auto",
+      "loss_scale": 0,
+      "loss_scale_window": 1000,
+      "initial_scale_power": 16,
+      "hysteresis": 2,
+      "min_loss_scale": 1
+    },
+    "bf16": {
+      "enabled": "auto"
+    },
+    "zero_optimization": {
+      "stage": 3,
+      "offload_optimizer": {
+        "device": "none",
+        "pin_memory": true
+      },
+      "offload_param": {
+        "device": "none",
+        "pin_memory": true
+      },
+      "overlap_comm": false,
+      "contiguous_gradients": true,
+      "sub_group_size": 1000000000.0,
+      "reduce_bucket_size": "auto",
+      "zero_quantized_weights": false,
+      "zero_quantized_gradients": false,
+      "stage3_prefetch_bucket_size": "auto",
+      "stage3_param_persistence_threshold": "auto",
+      "stage3_max_live_parameters": 1000000000.0,
+      "stage3_max_reuse_distance": 1000000000.0,
+      "stage3_gather_16bit_weights_on_model_save": true
+    },
+    "gradient_accumulation_steps": "auto",
+    "gradient_clipping": "auto",
+    "steps_per_print": 2000,
+    "train_batch_size": "auto",
+    "train_micro_batch_size_per_gpu": "auto",
+    "wall_clock_breakdown": false
+  },
+  "label_smoothing_factor": 0.0,
+  "optim": "adamw_torch",
+  "optim_args": null,
+  "adafactor": false,
+  "group_by_length": false,
+  "length_column_name": "length",
+  "report_to": [
+    "tensorboard"
+  ],
+  "ddp_find_unused_parameters": null,
+  "ddp_bucket_cap_mb": null,
+  "ddp_broadcast_buffers": null,
+  "dataloader_pin_memory": true,
+  "dataloader_persistent_workers": false,
+  "skip_memory_metrics": true,
+  "use_legacy_prediction_loop": false,
+  "push_to_hub": false,
+  "resume_from_checkpoint": null,
+  "hub_model_id": null,
+  "hub_strategy": "every_save",
+  "hub_token": null,
+  "hub_private_repo": null,
+  "hub_always_push": false,
+  "gradient_checkpointing": true,
+  "gradient_checkpointing_kwargs": null,
+  "include_inputs_for_metrics": false,
+  "include_for_metrics": [],
+  "eval_do_concat_batches": true,
+  "fp16_backend": "auto",
+  "push_to_hub_model_id": null,
+  "push_to_hub_organization": null,
+  "push_to_hub_token": null,
+  "mp_parameters": "",
+  "auto_find_batch_size": false,
+  "full_determinism": false,
+  "torchdynamo": null,
+  "ray_scope": "last",
+  "ddp_timeout": 18000000,
+  "torch_compile": false,
+  "torch_compile_backend": null,
+  "torch_compile_mode": null,
+  "include_tokens_per_second": false,
+  "include_num_input_tokens_seen": false,
+  "neftune_noise_alpha": null,
+  "optim_target_modules": null,
+  "batch_eval_metrics": false,
+  "eval_on_start": false,
+  "use_liger_kernel": false,
+  "eval_use_gather_object": false,
+  "average_tokens_across_devices": false,
+  "sortish_sampler": false,
+  "predict_with_generate": false,
+  "generation_max_length": null,
+  "generation_num_beams": null,
+  "generation_config": null,
+  "tuner_backend": "peft",
+  "vit_gradient_checkpointing": null,
+  "router_aux_loss_coef": 0.0,
+  "enable_dft_loss": false,
+  "check_model": true,
+  "acc_strategy": "token",
+  "train_dataloader_shuffle": true,
+  "max_epochs": null,
+  "aligner_lr": null,
+  "vit_lr": null,
+  "use_logits_to_keep": null,
+  "channels": null,
+  "ds3_gather_for_generation": true,
+  "resume_only_model": false,
+  "optimizer": null,
+  "loss_type": null,
+  "metric": null,
+  "eval_use_evalscope": false,
+  "eval_dataset": [],
+  "eval_dataset_args": null,
+  "eval_limit": null,
+  "eval_generation_config": null,
+  "extra_eval_args": null,
+  "use_flash_ckpt": false,
+  "model": "Qwen/Qwen2.5-7B-Instruct",
+  "model_type": "qwen2_5",
+  "model_revision": null,
+  "task_type": "causal_lm",
+  "torch_dtype": "bfloat16",
+  "attn_impl": null,
+  "new_special_tokens": [],
+  "num_labels": null,
+  "problem_type": null,
+  "rope_scaling": null,
+  "device_map": null,
+  "max_memory": {},
+  "max_model_len": null,
+  "local_repo_path": null,
+  "init_strategy": null,
+  "template": "qwen2_5",
+  "system": null,
+  "max_length": 16240,
+  "truncation_strategy": "delete",
+  "max_pixels": null,
+  "agent_template": null,
+  "norm_bbox": null,
+  "use_chat_template": true,
+  "padding_free": false,
+  "padding_side": "right",
+  "loss_scale": "default",
+  "sequence_parallel_size": 1,
+  "response_prefix": null,
+  "template_backend": "swift",
+  "dataset": [
+    "./corr_nq_2000q_hotpot_2000q_swift.jsonl",
+    "./corr_hotpot_new1369q_format_swift.jsonl",
+    "./self_2000_2000_1369_4_hp673_swift.jsonl",
+    "./self_2000_2000_1369_4_nq400_noinfo_swift.jsonl"
+  ],
+  "val_dataset": [],
+  "split_dataset_ratio": 0.001,
+  "dataset_num_proc": 100,
+  "load_from_cache_file": true,
+  "dataset_shuffle": true,
+  "val_dataset_shuffle": false,
+  "streaming": false,
+  "interleave_prob": null,
+  "stopping_strategy": "first_exhausted",
+  "shuffle_buffer_size": 1000,
+  "download_mode": "reuse_dataset_if_exists",
+  "columns": {},
+  "strict": false,
+  "model_name": null,
+  "model_author": null,
+  "custom_dataset_info": [],
+  "quant_method": null,
+  "quant_bits": null,
+  "hqq_axis": null,
+  "bnb_4bit_compute_dtype": "bfloat16",
+  "bnb_4bit_quant_type": "nf4",
+  "bnb_4bit_use_double_quant": true,
+  "bnb_4bit_quant_storage": null,
+  "max_new_tokens": 64,
+  "temperature": 0.0,
+  "top_k": null,
+  "top_p": null,
+  "repetition_penalty": null,
+  "num_beams": 1,
+  "stream": false,
+  "stop_words": [],
+  "logprobs": false,
+  "top_logprobs": null,
+  "ckpt_dir": null,
+  "lora_modules": [],
+  "train_type": "full",
+  "adapters": [],
+  "external_plugins": [],
+  "model_kwargs": {},
+  "load_args": false,
+  "load_data_args": false,
+  "packing": false,
+  "packing_length": null,
+  "lazy_tokenize": false,
+  "cached_dataset": [],
+  "custom_register_path": [],
+  "use_hf": false,
+  "ignore_args_error": false,
+  "use_swift_lora": false,
+  "freeze_parameters": [],
+  "freeze_parameters_regex": null,
+  "freeze_parameters_ratio": 0.0,
+  "trainable_parameters": [],
+  "trainable_parameters_regex": null,
+  "freeze_llm": false,
+  "freeze_vit": true,
+  "freeze_aligner": false,
+  "target_modules": [
+    "all-linear"
+  ],
+  "target_regex": null,
+  "modules_to_save": [],
+  "lora_rank": 8,
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "lora_bias": "none",
+  "lora_dtype": null,
+  "lorap_lr_ratio": null,
+  "use_rslora": false,
+  "use_dora": false,
+  "lora_ga_batch_size": 2,
+  "lora_ga_iters": 2,
+  "lora_ga_max_length": 1024,
+  "lora_ga_direction": "ArB2r",
+  "lora_ga_scale": "stable",
+  "lora_ga_stable_gamma": 16,
+  "init_weights": true,
+  "fourier_n_frequency": 2000,
+  "fourier_scaling": 300.0,
+  "boft_block_size": 4,
+  "boft_block_num": 0,
+  "boft_n_butterfly_factor": 1,
+  "boft_dropout": 0.0,
+  "vera_rank": 256,
+  "vera_projection_prng_key": 0,
+  "vera_dropout": 0.0,
+  "vera_d_initial": 0.1,
+  "adapter_act": "gelu",
+  "adapter_length": 128,
+  "use_galore": false,
+  "galore_target_modules": null,
+  "galore_rank": 128,
+  "galore_update_proj_gap": 50,
+  "galore_scale": 1.0,
+  "galore_proj_type": "std",
+  "galore_optim_per_parameter": false,
+  "galore_with_embedding": false,
+  "galore_quantization": false,
+  "galore_proj_quant": false,
+  "galore_proj_bits": 4,
+  "galore_proj_group_size": 256,
+  "galore_cos_threshold": 0.4,
+  "galore_gamma_proj": 2,
+  "galore_queue_size": 5,
+  "adalora_target_r": 8,
+  "adalora_init_r": 12,
+  "adalora_tinit": 0,
+  "adalora_tfinal": 0,
+  "adalora_deltaT": 1,
+  "adalora_beta1": 0.85,
+  "adalora_beta2": 0.85,
+  "adalora_orth_reg_weight": 0.5,
+  "llamapro_num_new_blocks": 4,
+  "llamapro_num_groups": null,
+  "lisa_activated_layers": 0,
+  "lisa_step_interval": 20,
+  "reft_layer_key": null,
+  "reft_layers": null,
+  "reft_rank": 4,
+  "reft_intervention_type": "LoreftIntervention",
+  "reft_args": null,
+  "swanlab_token": null,
+  "swanlab_project": null,
+  "swanlab_workspace": null,
+  "swanlab_exp_name": null,
+  "swanlab_lark_webhook_url": null,
+  "swanlab_lark_secret": null,
+  "swanlab_mode": "cloud",
+  "add_version": true,
+  "create_checkpoint_symlink": false,
+  "zero_hpz_partition_size": null,
+  "deepspeed_autotp_size": null,
+  "early_stop_interval": null,
+  "rank": 0,
+  "global_world_size": 8,
+  "local_world_size": 8,
+  "model_suffix": "Qwen2.5-7B-Instruct",
+  "model_info": "ModelInfo(model_type='qwen2_5', model_dir='/root/.cache/modelscope/hub/models/Qwen/Qwen2___5-7B-Instruct', torch_dtype=torch.bfloat16, max_model_len=32768, quant_method=None, quant_bits=None, rope_scaling=None, is_moe_model=False, config=None, task_type='causal_lm', num_labels=None)",
+  "model_meta": "ModelMeta(model_type='qwen2_5', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen2.5-0.5B-Instruct', hf_model_id='Qwen/Qwen2.5-0.5B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-1.5B-Instruct', hf_model_id='Qwen/Qwen2.5-1.5B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-3B-Instruct', hf_model_id='Qwen/Qwen2.5-3B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-7B-Instruct', hf_model_id='Qwen/Qwen2.5-7B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-14B-Instruct', hf_model_id='Qwen/Qwen2.5-14B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-32B-Instruct', hf_model_id='Qwen/Qwen2.5-32B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-72B-Instruct', hf_model_id='Qwen/Qwen2.5-72B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-0.5B', hf_model_id='Qwen/Qwen2.5-0.5B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-1.5B', hf_model_id='Qwen/Qwen2.5-1.5B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-3B', hf_model_id='Qwen/Qwen2.5-3B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-7B', hf_model_id='Qwen/Qwen2.5-7B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-14B', hf_model_id='Qwen/Qwen2.5-14B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-32B', hf_model_id='Qwen/Qwen2.5-32B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-72B', hf_model_id='Qwen/Qwen2.5-72B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-0.5B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-0.5B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-1.5B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-1.5B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-3B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-3B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-7B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-7B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-14B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-14B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-32B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-32B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-72B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-72B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-0.5B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-0.5B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-1.5B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-1.5B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-3B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-3B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-7B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-7B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-14B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-14B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-32B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-32B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-72B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-72B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-0.5B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-0.5B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-1.5B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-1.5B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-3B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-3B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-7B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-7B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-14B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-14B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-32B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-32B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-72B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-72B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct', hf_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct', hf_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-3B-Instruct', hf_model_id='Qwen/Qwen2.5-Coder-3B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-7B-Instruct', hf_model_id='Qwen/Qwen2.5-Coder-7B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-14B-Instruct', hf_model_id='Qwen/Qwen2.5-Coder-14B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-32B-Instruct', hf_model_id='Qwen/Qwen2.5-Coder-32B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-0.5B', hf_model_id='Qwen/Qwen2.5-Coder-0.5B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-1.5B', hf_model_id='Qwen/Qwen2.5-Coder-1.5B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-3B', hf_model_id='Qwen/Qwen2.5-Coder-3B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-7B', hf_model_id='Qwen/Qwen2.5-Coder-7B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-14B', hf_model_id='Qwen/Qwen2.5-Coder-14B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-32B', hf_model_id='Qwen/Qwen2.5-Coder-32B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-3B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-Coder-3B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-7B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-Coder-7B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-14B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-Coder-14B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-32B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-Coder-32B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-3B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-Coder-3B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-3B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-Coder-3B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-7B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-Coder-7B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-7B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-Coder-7B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-14B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-Coder-14B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-14B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-Coder-14B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-32B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-Coder-32B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-32B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-Coder-32B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=['coding']), ModelGroup(models=[Model(ms_model_id='moonshotai/Kimi-Dev-72B', hf_model_id='moonshotai/Kimi-Dev-72B', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='qwen2_5', get_function=<function get_model_tokenizer_with_flash_attn at 0x7ff10cefadd0>, model_arch=ModelKeys(arch_name='llama', embedding='model.embed_tokens', module_list='model.layers', lm_head='lm_head', q_proj='model.layers.{}.self_attn.q_proj', k_proj='model.layers.{}.self_attn.k_proj', v_proj='model.layers.{}.self_attn.v_proj', o_proj='model.layers.{}.self_attn.o_proj', attention='model.layers.{}.self_attn', mlp='model.layers.{}.mlp', down_proj='model.layers.{}.mlp.down_proj', qkv_proj=None, qk_proj=None, qa_proj=None, qb_proj=None, kv_proj=None, kva_proj=None, kvb_proj=None), architectures=['Qwen2ForCausalLM'], additional_saved_files=[], torch_dtype=None, is_multimodal=False, is_reward=False, task_type=None, ignore_patterns=None, requires=['transformers>=4.37'], tags=[])",
+  "model_dir": "/root/.cache/modelscope/hub/models/Qwen/Qwen2___5-7B-Instruct",
+  "hub": "<class 'swift.hub.hub.MSHub'>",
+  "evaluation_strategy": "epoch",
+  "training_args": "Seq2SeqTrainingArguments(output_dir='/group/40143/hongzhuyi/ms-swift/output/v1-20250917-010849', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, eval_strategy=<IntervalStrategy.EPOCH: 'epoch'>, prediction_loss_only=False, per_device_train_batch_size=2, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=4, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=5e-06, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1.0, num_train_epochs=2.0, max_steps=-1, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs=None, warmup_ratio=0.05, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/group/40143/hongzhuyi/ms-swift/output/v1-20250917-010849/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=1, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.EPOCH: 'epoch'>, save_steps=500, save_total_limit=None, save_safetensors=True, save_on_each_node=False, save_only_model=False, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=42, jit_mode_eval=False, use_ipex=False, bf16=True, fp16=False, fp16_opt_level='O1', half_precision_backend='auto', bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=0, ddp_backend=None, tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=2000.0, dataloader_num_workers=48, dataloader_prefetch_factor=10, past_index=-1, run_name='/group/40143/hongzhuyi/ms-swift/output/v1-20250917-010849', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), deepspeed={'fp16': {'enabled': 'auto', 'loss_scale': 0, 'loss_scale_window': 1000, 'initial_scale_power': 16, 'hysteresis': 2, 'min_loss_scale': 1}, 'bf16': {'enabled': 'auto'}, 'zero_optimization': {'stage': 3, 'offload_optimizer': {'device': 'none', 'pin_memory': True}, 'offload_param': {'device': 'none', 'pin_memory': True}, 'overlap_comm': False, 'contiguous_gradients': True, 'sub_group_size': 1000000000.0, 'reduce_bucket_size': 'auto', 'zero_quantized_weights': False, 'zero_quantized_gradients': False, 'stage3_prefetch_bucket_size': 'auto', 'stage3_param_persistence_threshold': 'auto', 'stage3_max_live_parameters': 1000000000.0, 'stage3_max_reuse_distance': 1000000000.0, 'stage3_gather_16bit_weights_on_model_save': True}, 'gradient_accumulation_steps': 'auto', 'gradient_clipping': 'auto', 'steps_per_print': 2000, 'train_batch_size': 'auto', 'train_micro_batch_size_per_gpu': 'auto', 'wall_clock_breakdown': False}, label_smoothing_factor=0.0, optim=<OptimizerNames.ADAMW_TORCH: 'adamw_torch'>, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['tensorboard'], ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint=None, hub_model_id=None, hub_strategy=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_token=None, hub_private_repo=None, hub_always_push=False, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=18000000, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, include_tokens_per_second=None, include_num_input_tokens_seen=None, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, eval_use_gather_object=False, average_tokens_across_devices=None, sortish_sampler=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=None, tuner_backend='peft', vit_gradient_checkpointing=True, router_aux_loss_coef=0.0, enable_dft_loss=False, check_model=True, acc_strategy='token', train_dataloader_shuffle=True, max_epochs=None, aligner_lr=None, vit_lr=None, use_logits_to_keep=None, channels=None, ds3_gather_for_generation=True, resume_only_model=False, optimizer=None, loss_type=None, metric=None, eval_use_evalscope=False, eval_dataset=[], eval_dataset_args=None, eval_limit=None, eval_generation_config=None, extra_eval_args=None, use_flash_ckpt=False, sft_alpha=0, train_type='full', local_repo_path=None, galore_config=None)"
+}

qwen2.5-7b-2225q-2069q-1369q-sft+rft-newbs-old-click-2ep-lr5e-6/checkpoint-442/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

qwen2.5-7b-2225q-2069q-1369q-sft+rft-newbs-old-click-2ep-lr5e-6/checkpoint-442/args.json

@@ -0,0 +1,381 @@
+{
+  "output_dir": "/group/40143/hongzhuyi/ms-swift/output/v1-20250917-010849",
+  "overwrite_output_dir": false,
+  "do_train": false,
+  "do_eval": false,
+  "do_predict": false,
+  "eval_strategy": "epoch",
+  "prediction_loss_only": false,
+  "per_device_train_batch_size": 2,
+  "per_device_eval_batch_size": 1,
+  "per_gpu_train_batch_size": null,
+  "per_gpu_eval_batch_size": null,
+  "gradient_accumulation_steps": 4,
+  "eval_accumulation_steps": null,
+  "eval_delay": 0,
+  "torch_empty_cache_steps": null,
+  "learning_rate": 5e-06,
+  "weight_decay": 0.1,
+  "adam_beta1": 0.9,
+  "adam_beta2": 0.95,
+  "adam_epsilon": 1e-08,
+  "max_grad_norm": 1.0,
+  "num_train_epochs": 2.0,
+  "max_steps": -1,
+  "lr_scheduler_type": "cosine",
+  "lr_scheduler_kwargs": null,
+  "warmup_ratio": 0.05,
+  "warmup_steps": 0,
+  "log_level": "passive",
+  "log_level_replica": "warning",
+  "log_on_each_node": true,
+  "logging_dir": "/group/40143/hongzhuyi/ms-swift/output/v1-20250917-010849/runs",
+  "logging_strategy": "steps",
+  "logging_first_step": true,
+  "logging_steps": 1,
+  "logging_nan_inf_filter": true,
+  "save_strategy": "epoch",
+  "save_steps": 500,
+  "save_total_limit": null,
+  "save_safetensors": true,
+  "save_on_each_node": false,
+  "save_only_model": false,
+  "restore_callback_states_from_checkpoint": false,
+  "no_cuda": false,
+  "use_cpu": false,
+  "use_mps_device": false,
+  "seed": 42,
+  "data_seed": 42,
+  "jit_mode_eval": false,
+  "use_ipex": false,
+  "bf16": true,
+  "fp16": false,
+  "fp16_opt_level": "O1",
+  "half_precision_backend": "auto",
+  "bf16_full_eval": false,
+  "fp16_full_eval": false,
+  "tf32": null,
+  "local_rank": 0,
+  "ddp_backend": null,
+  "tpu_num_cores": null,
+  "tpu_metrics_debug": false,
+  "debug": null,
+  "dataloader_drop_last": false,
+  "eval_steps": 2000.0,
+  "dataloader_num_workers": 48,
+  "dataloader_prefetch_factor": null,
+  "past_index": -1,
+  "run_name": "/group/40143/hongzhuyi/ms-swift/output/v1-20250917-010849",
+  "disable_tqdm": null,
+  "remove_unused_columns": true,
+  "label_names": null,
+  "load_best_model_at_end": false,
+  "metric_for_best_model": "loss",
+  "greater_is_better": false,
+  "ignore_data_skip": false,
+  "fsdp": "",
+  "fsdp_min_num_params": 0,
+  "fsdp_config": null,
+  "fsdp_transformer_layer_cls_to_wrap": null,
+  "accelerator_config": {
+    "dispatch_batches": false
+  },
+  "deepspeed": {
+    "fp16": {
+      "enabled": "auto",
+      "loss_scale": 0,
+      "loss_scale_window": 1000,
+      "initial_scale_power": 16,
+      "hysteresis": 2,
+      "min_loss_scale": 1
+    },
+    "bf16": {
+      "enabled": "auto"
+    },
+    "zero_optimization": {
+      "stage": 3,
+      "offload_optimizer": {
+        "device": "none",
+        "pin_memory": true
+      },
+      "offload_param": {
+        "device": "none",
+        "pin_memory": true
+      },
+      "overlap_comm": false,
+      "contiguous_gradients": true,
+      "sub_group_size": 1000000000.0,
+      "reduce_bucket_size": "auto",
+      "zero_quantized_weights": false,
+      "zero_quantized_gradients": false,
+      "stage3_prefetch_bucket_size": "auto",
+      "stage3_param_persistence_threshold": "auto",
+      "stage3_max_live_parameters": 1000000000.0,
+      "stage3_max_reuse_distance": 1000000000.0,
+      "stage3_gather_16bit_weights_on_model_save": true
+    },
+    "gradient_accumulation_steps": "auto",
+    "gradient_clipping": "auto",
+    "steps_per_print": 2000,
+    "train_batch_size": "auto",
+    "train_micro_batch_size_per_gpu": "auto",
+    "wall_clock_breakdown": false
+  },
+  "label_smoothing_factor": 0.0,
+  "optim": "adamw_torch",
+  "optim_args": null,
+  "adafactor": false,
+  "group_by_length": false,
+  "length_column_name": "length",
+  "report_to": [
+    "tensorboard"
+  ],
+  "ddp_find_unused_parameters": null,
+  "ddp_bucket_cap_mb": null,
+  "ddp_broadcast_buffers": null,
+  "dataloader_pin_memory": true,
+  "dataloader_persistent_workers": false,
+  "skip_memory_metrics": true,
+  "use_legacy_prediction_loop": false,
+  "push_to_hub": false,
+  "resume_from_checkpoint": null,
+  "hub_model_id": null,
+  "hub_strategy": "every_save",
+  "hub_token": null,
+  "hub_private_repo": null,
+  "hub_always_push": false,
+  "gradient_checkpointing": true,
+  "gradient_checkpointing_kwargs": null,
+  "include_inputs_for_metrics": false,
+  "include_for_metrics": [],
+  "eval_do_concat_batches": true,
+  "fp16_backend": "auto",
+  "push_to_hub_model_id": null,
+  "push_to_hub_organization": null,
+  "push_to_hub_token": null,
+  "mp_parameters": "",
+  "auto_find_batch_size": false,
+  "full_determinism": false,
+  "torchdynamo": null,
+  "ray_scope": "last",
+  "ddp_timeout": 18000000,
+  "torch_compile": false,
+  "torch_compile_backend": null,
+  "torch_compile_mode": null,
+  "include_tokens_per_second": false,
+  "include_num_input_tokens_seen": false,
+  "neftune_noise_alpha": null,
+  "optim_target_modules": null,
+  "batch_eval_metrics": false,
+  "eval_on_start": false,
+  "use_liger_kernel": false,
+  "eval_use_gather_object": false,
+  "average_tokens_across_devices": false,
+  "sortish_sampler": false,
+  "predict_with_generate": false,
+  "generation_max_length": null,
+  "generation_num_beams": null,
+  "generation_config": null,
+  "tuner_backend": "peft",
+  "vit_gradient_checkpointing": null,
+  "router_aux_loss_coef": 0.0,
+  "enable_dft_loss": false,
+  "check_model": true,
+  "acc_strategy": "token",
+  "train_dataloader_shuffle": true,
+  "max_epochs": null,
+  "aligner_lr": null,
+  "vit_lr": null,
+  "use_logits_to_keep": null,
+  "channels": null,
+  "ds3_gather_for_generation": true,
+  "resume_only_model": false,
+  "optimizer": null,
+  "loss_type": null,
+  "metric": null,
+  "eval_use_evalscope": false,
+  "eval_dataset": [],
+  "eval_dataset_args": null,
+  "eval_limit": null,
+  "eval_generation_config": null,
+  "extra_eval_args": null,
+  "use_flash_ckpt": false,
+  "model": "Qwen/Qwen2.5-7B-Instruct",
+  "model_type": "qwen2_5",
+  "model_revision": null,
+  "task_type": "causal_lm",
+  "torch_dtype": "bfloat16",
+  "attn_impl": null,
+  "new_special_tokens": [],
+  "num_labels": null,
+  "problem_type": null,
+  "rope_scaling": null,
+  "device_map": null,
+  "max_memory": {},
+  "max_model_len": null,
+  "local_repo_path": null,
+  "init_strategy": null,
+  "template": "qwen2_5",
+  "system": null,
+  "max_length": 16240,
+  "truncation_strategy": "delete",
+  "max_pixels": null,
+  "agent_template": null,
+  "norm_bbox": null,
+  "use_chat_template": true,
+  "padding_free": false,
+  "padding_side": "right",
+  "loss_scale": "default",
+  "sequence_parallel_size": 1,
+  "response_prefix": null,
+  "template_backend": "swift",
+  "dataset": [
+    "./corr_nq_2000q_hotpot_2000q_swift.jsonl",
+    "./corr_hotpot_new1369q_format_swift.jsonl",
+    "./self_2000_2000_1369_4_hp673_swift.jsonl",
+    "./self_2000_2000_1369_4_nq400_noinfo_swift.jsonl"
+  ],
+  "val_dataset": [],
+  "split_dataset_ratio": 0.001,
+  "dataset_num_proc": 100,
+  "load_from_cache_file": true,
+  "dataset_shuffle": true,
+  "val_dataset_shuffle": false,
+  "streaming": false,
+  "interleave_prob": null,
+  "stopping_strategy": "first_exhausted",
+  "shuffle_buffer_size": 1000,
+  "download_mode": "reuse_dataset_if_exists",
+  "columns": {},
+  "strict": false,
+  "model_name": null,
+  "model_author": null,
+  "custom_dataset_info": [],
+  "quant_method": null,
+  "quant_bits": null,
+  "hqq_axis": null,
+  "bnb_4bit_compute_dtype": "bfloat16",
+  "bnb_4bit_quant_type": "nf4",
+  "bnb_4bit_use_double_quant": true,
+  "bnb_4bit_quant_storage": null,
+  "max_new_tokens": 64,
+  "temperature": 0.0,
+  "top_k": null,
+  "top_p": null,
+  "repetition_penalty": null,
+  "num_beams": 1,
+  "stream": false,
+  "stop_words": [],
+  "logprobs": false,
+  "top_logprobs": null,
+  "ckpt_dir": null,
+  "lora_modules": [],
+  "train_type": "full",
+  "adapters": [],
+  "external_plugins": [],
+  "model_kwargs": {},
+  "load_args": false,
+  "load_data_args": false,
+  "packing": false,
+  "packing_length": null,
+  "lazy_tokenize": false,
+  "cached_dataset": [],
+  "custom_register_path": [],
+  "use_hf": false,
+  "ignore_args_error": false,
+  "use_swift_lora": false,
+  "freeze_parameters": [],
+  "freeze_parameters_regex": null,
+  "freeze_parameters_ratio": 0.0,
+  "trainable_parameters": [],
+  "trainable_parameters_regex": null,
+  "freeze_llm": false,
+  "freeze_vit": true,
+  "freeze_aligner": false,
+  "target_modules": [
+    "all-linear"
+  ],
+  "target_regex": null,
+  "modules_to_save": [],
+  "lora_rank": 8,
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "lora_bias": "none",
+  "lora_dtype": null,
+  "lorap_lr_ratio": null,
+  "use_rslora": false,
+  "use_dora": false,
+  "lora_ga_batch_size": 2,
+  "lora_ga_iters": 2,
+  "lora_ga_max_length": 1024,
+  "lora_ga_direction": "ArB2r",
+  "lora_ga_scale": "stable",
+  "lora_ga_stable_gamma": 16,
+  "init_weights": true,
+  "fourier_n_frequency": 2000,
+  "fourier_scaling": 300.0,
+  "boft_block_size": 4,
+  "boft_block_num": 0,
+  "boft_n_butterfly_factor": 1,
+  "boft_dropout": 0.0,
+  "vera_rank": 256,
+  "vera_projection_prng_key": 0,
+  "vera_dropout": 0.0,
+  "vera_d_initial": 0.1,
+  "adapter_act": "gelu",
+  "adapter_length": 128,
+  "use_galore": false,
+  "galore_target_modules": null,
+  "galore_rank": 128,
+  "galore_update_proj_gap": 50,
+  "galore_scale": 1.0,
+  "galore_proj_type": "std",
+  "galore_optim_per_parameter": false,
+  "galore_with_embedding": false,
+  "galore_quantization": false,
+  "galore_proj_quant": false,
+  "galore_proj_bits": 4,
+  "galore_proj_group_size": 256,
+  "galore_cos_threshold": 0.4,
+  "galore_gamma_proj": 2,
+  "galore_queue_size": 5,
+  "adalora_target_r": 8,
+  "adalora_init_r": 12,
+  "adalora_tinit": 0,
+  "adalora_tfinal": 0,
+  "adalora_deltaT": 1,
+  "adalora_beta1": 0.85,
+  "adalora_beta2": 0.85,
+  "adalora_orth_reg_weight": 0.5,
+  "llamapro_num_new_blocks": 4,
+  "llamapro_num_groups": null,
+  "lisa_activated_layers": 0,
+  "lisa_step_interval": 20,
+  "reft_layer_key": null,
+  "reft_layers": null,
+  "reft_rank": 4,
+  "reft_intervention_type": "LoreftIntervention",
+  "reft_args": null,
+  "swanlab_token": null,
+  "swanlab_project": null,
+  "swanlab_workspace": null,
+  "swanlab_exp_name": null,
+  "swanlab_lark_webhook_url": null,
+  "swanlab_lark_secret": null,
+  "swanlab_mode": "cloud",
+  "add_version": true,
+  "create_checkpoint_symlink": false,
+  "zero_hpz_partition_size": null,
+  "deepspeed_autotp_size": null,
+  "early_stop_interval": null,
+  "rank": 0,
+  "global_world_size": 8,
+  "local_world_size": 8,
+  "model_suffix": "Qwen2.5-7B-Instruct",
+  "model_info": "ModelInfo(model_type='qwen2_5', model_dir='/root/.cache/modelscope/hub/models/Qwen/Qwen2___5-7B-Instruct', torch_dtype=torch.bfloat16, max_model_len=32768, quant_method=None, quant_bits=None, rope_scaling=None, is_moe_model=False, config=None, task_type='causal_lm', num_labels=None)",
+  "model_meta": "ModelMeta(model_type='qwen2_5', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen2.5-0.5B-Instruct', hf_model_id='Qwen/Qwen2.5-0.5B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-1.5B-Instruct', hf_model_id='Qwen/Qwen2.5-1.5B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-3B-Instruct', hf_model_id='Qwen/Qwen2.5-3B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-7B-Instruct', hf_model_id='Qwen/Qwen2.5-7B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-14B-Instruct', hf_model_id='Qwen/Qwen2.5-14B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-32B-Instruct', hf_model_id='Qwen/Qwen2.5-32B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-72B-Instruct', hf_model_id='Qwen/Qwen2.5-72B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-0.5B', hf_model_id='Qwen/Qwen2.5-0.5B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-1.5B', hf_model_id='Qwen/Qwen2.5-1.5B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-3B', hf_model_id='Qwen/Qwen2.5-3B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-7B', hf_model_id='Qwen/Qwen2.5-7B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-14B', hf_model_id='Qwen/Qwen2.5-14B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-32B', hf_model_id='Qwen/Qwen2.5-32B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-72B', hf_model_id='Qwen/Qwen2.5-72B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-0.5B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-0.5B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-1.5B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-1.5B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-3B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-3B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-7B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-7B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-14B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-14B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-32B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-32B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-72B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-72B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-0.5B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-0.5B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-1.5B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-1.5B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-3B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-3B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-7B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-7B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-14B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-14B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-32B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-32B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-72B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-72B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-0.5B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-0.5B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-1.5B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-1.5B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-3B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-3B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-7B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-7B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-14B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-14B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-32B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-32B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-72B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-72B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct', hf_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct', hf_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-3B-Instruct', hf_model_id='Qwen/Qwen2.5-Coder-3B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-7B-Instruct', hf_model_id='Qwen/Qwen2.5-Coder-7B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-14B-Instruct', hf_model_id='Qwen/Qwen2.5-Coder-14B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-32B-Instruct', hf_model_id='Qwen/Qwen2.5-Coder-32B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-0.5B', hf_model_id='Qwen/Qwen2.5-Coder-0.5B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-1.5B', hf_model_id='Qwen/Qwen2.5-Coder-1.5B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-3B', hf_model_id='Qwen/Qwen2.5-Coder-3B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-7B', hf_model_id='Qwen/Qwen2.5-Coder-7B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-14B', hf_model_id='Qwen/Qwen2.5-Coder-14B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-32B', hf_model_id='Qwen/Qwen2.5-Coder-32B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-3B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-Coder-3B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-7B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-Coder-7B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-14B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-Coder-14B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-32B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-Coder-32B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-3B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-Coder-3B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-3B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-Coder-3B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-7B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-Coder-7B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-7B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-Coder-7B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-14B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-Coder-14B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-14B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-Coder-14B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-32B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-Coder-32B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-32B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-Coder-32B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=['coding']), ModelGroup(models=[Model(ms_model_id='moonshotai/Kimi-Dev-72B', hf_model_id='moonshotai/Kimi-Dev-72B', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='qwen2_5', get_function=<function get_model_tokenizer_with_flash_attn at 0x7ff10cefadd0>, model_arch=ModelKeys(arch_name='llama', embedding='model.embed_tokens', module_list='model.layers', lm_head='lm_head', q_proj='model.layers.{}.self_attn.q_proj', k_proj='model.layers.{}.self_attn.k_proj', v_proj='model.layers.{}.self_attn.v_proj', o_proj='model.layers.{}.self_attn.o_proj', attention='model.layers.{}.self_attn', mlp='model.layers.{}.mlp', down_proj='model.layers.{}.mlp.down_proj', qkv_proj=None, qk_proj=None, qa_proj=None, qb_proj=None, kv_proj=None, kva_proj=None, kvb_proj=None), architectures=['Qwen2ForCausalLM'], additional_saved_files=[], torch_dtype=None, is_multimodal=False, is_reward=False, task_type=None, ignore_patterns=None, requires=['transformers>=4.37'], tags=[])",
+  "model_dir": "/root/.cache/modelscope/hub/models/Qwen/Qwen2___5-7B-Instruct",
+  "hub": "<class 'swift.hub.hub.MSHub'>",
+  "evaluation_strategy": "epoch",
+  "training_args": "Seq2SeqTrainingArguments(output_dir='/group/40143/hongzhuyi/ms-swift/output/v1-20250917-010849', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, eval_strategy=<IntervalStrategy.EPOCH: 'epoch'>, prediction_loss_only=False, per_device_train_batch_size=2, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=4, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=5e-06, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1.0, num_train_epochs=2.0, max_steps=-1, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs=None, warmup_ratio=0.05, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/group/40143/hongzhuyi/ms-swift/output/v1-20250917-010849/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=1, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.EPOCH: 'epoch'>, save_steps=500, save_total_limit=None, save_safetensors=True, save_on_each_node=False, save_only_model=False, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=42, jit_mode_eval=False, use_ipex=False, bf16=True, fp16=False, fp16_opt_level='O1', half_precision_backend='auto', bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=0, ddp_backend=None, tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=2000.0, dataloader_num_workers=48, dataloader_prefetch_factor=10, past_index=-1, run_name='/group/40143/hongzhuyi/ms-swift/output/v1-20250917-010849', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), deepspeed={'fp16': {'enabled': 'auto', 'loss_scale': 0, 'loss_scale_window': 1000, 'initial_scale_power': 16, 'hysteresis': 2, 'min_loss_scale': 1}, 'bf16': {'enabled': 'auto'}, 'zero_optimization': {'stage': 3, 'offload_optimizer': {'device': 'none', 'pin_memory': True}, 'offload_param': {'device': 'none', 'pin_memory': True}, 'overlap_comm': False, 'contiguous_gradients': True, 'sub_group_size': 1000000000.0, 'reduce_bucket_size': 'auto', 'zero_quantized_weights': False, 'zero_quantized_gradients': False, 'stage3_prefetch_bucket_size': 'auto', 'stage3_param_persistence_threshold': 'auto', 'stage3_max_live_parameters': 1000000000.0, 'stage3_max_reuse_distance': 1000000000.0, 'stage3_gather_16bit_weights_on_model_save': True}, 'gradient_accumulation_steps': 'auto', 'gradient_clipping': 'auto', 'steps_per_print': 2000, 'train_batch_size': 'auto', 'train_micro_batch_size_per_gpu': 'auto', 'wall_clock_breakdown': False}, label_smoothing_factor=0.0, optim=<OptimizerNames.ADAMW_TORCH: 'adamw_torch'>, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['tensorboard'], ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint=None, hub_model_id=None, hub_strategy=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_token=None, hub_private_repo=None, hub_always_push=False, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=18000000, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, include_tokens_per_second=None, include_num_input_tokens_seen=None, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, eval_use_gather_object=False, average_tokens_across_devices=None, sortish_sampler=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=None, tuner_backend='peft', vit_gradient_checkpointing=True, router_aux_loss_coef=0.0, enable_dft_loss=False, check_model=True, acc_strategy='token', train_dataloader_shuffle=True, max_epochs=None, aligner_lr=None, vit_lr=None, use_logits_to_keep=None, channels=None, ds3_gather_for_generation=True, resume_only_model=False, optimizer=None, loss_type=None, metric=None, eval_use_evalscope=False, eval_dataset=[], eval_dataset_args=None, eval_limit=None, eval_generation_config=None, extra_eval_args=None, use_flash_ckpt=False, sft_alpha=0, train_type='full', local_repo_path=None, galore_config=None)"
+}

qwen2.5-7b-2225q-2069q-1369q-sft+rft-newbs-old-click-2ep-lr5e-6/checkpoint-442/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- 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 %}

qwen2.5-7b-2225q-2069q-1369q-sft+rft-newbs-old-click-2ep-lr5e-6/checkpoint-442/config.json

@@ -0,0 +1,29 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 131072,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.52.4",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

qwen2.5-7b-2225q-2069q-1369q-sft+rft-newbs-old-click-2ep-lr5e-6/checkpoint-442/generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.52.4"
+}

qwen2.5-7b-2225q-2069q-1369q-sft+rft-newbs-old-click-2ep-lr5e-6/checkpoint-442/latest

@@ -0,0 +1 @@
+global_step442

qwen2.5-7b-2225q-2069q-1369q-sft+rft-newbs-old-click-2ep-lr5e-6/checkpoint-442/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb00559195bdcae002fe821494eb1d9237a76ad6cbd7d59b99f1fab499dc75ec
+size 4877660776

qwen2.5-7b-2225q-2069q-1369q-sft+rft-newbs-old-click-2ep-lr5e-6/checkpoint-442/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62216357d84251ea17539a86439105702f3cab88d1d7a9aacc545d7d321d1dfe
+size 4932751008

qwen2.5-7b-2225q-2069q-1369q-sft+rft-newbs-old-click-2ep-lr5e-6/checkpoint-442/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:beb14acd13b2ed0137eb28c5dd26ac14cfc5511429aa2f8bb8d7421b2ac3e686
+size 4330865200

qwen2.5-7b-2225q-2069q-1369q-sft+rft-newbs-old-click-2ep-lr5e-6/checkpoint-442/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab64541e2b65e08fc531cba0e5a6e744a574d1ee329c31fbba6122af17734a8a
+size 1089994880

qwen2.5-7b-2225q-2069q-1369q-sft+rft-newbs-old-click-2ep-lr5e-6/checkpoint-442/model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 15231233024
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors"
+  }
+}

qwen2.5-7b-2225q-2069q-1369q-sft+rft-newbs-old-click-2ep-lr5e-6/checkpoint-442/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2946430e67d53bbdba29ad82934bbaaedc694d31b613744d3a4e1a1e9a46ba8f
+size 15920

qwen2.5-7b-2225q-2069q-1369q-sft+rft-newbs-old-click-2ep-lr5e-6/checkpoint-442/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2f8ffeab37684493e90f06d39e88dd23930f6d4b22434e761cf24eb66c33624
+size 15920

qwen2.5-7b-2225q-2069q-1369q-sft+rft-newbs-old-click-2ep-lr5e-6/checkpoint-442/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3e34f4b25d022859f36dc8565e9864ef89df31dee0b6f28ae330b4505432890
+size 15920

qwen2.5-7b-2225q-2069q-1369q-sft+rft-newbs-old-click-2ep-lr5e-6/checkpoint-442/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c75713cb224376ed36decc995102191568e3ae75807c8df22de6bdfa763f0e1
+size 15920

qwen2.5-7b-2225q-2069q-1369q-sft+rft-newbs-old-click-2ep-lr5e-6/checkpoint-442/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a045b81eb8aff0c6f04e5c1c068c22b50a29b0c3cd0ceb0f7b0633e087645e2
+size 15920

qwen2.5-7b-2225q-2069q-1369q-sft+rft-newbs-old-click-2ep-lr5e-6/checkpoint-442/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fbb9337a1f2ddc7522ae749e74101fdc6408581ff2447c6ce01d1264feaa554
+size 15920

qwen2.5-7b-2225q-2069q-1369q-sft+rft-newbs-old-click-2ep-lr5e-6/checkpoint-442/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd4f55e2919a65fc83570ea3e656aee5c665014b2d4ebb1e757b6604bfa2f91e
+size 15920

qwen2.5-7b-2225q-2069q-1369q-sft+rft-newbs-old-click-2ep-lr5e-6/checkpoint-442/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e742eccb95f66543b690641ccc536fb0f2c7f6d2ad1dce55de41ec2f9bcac81a
+size 15920

qwen2.5-7b-2225q-2069q-1369q-sft+rft-newbs-old-click-2ep-lr5e-6/checkpoint-442/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff2630676d5ec9bbac4299d6f50e69d59946096fb9c4934d2dee08bf42c4ee94
+size 1064

qwen2.5-7b-2225q-2069q-1369q-sft+rft-newbs-old-click-2ep-lr5e-6/checkpoint-442/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

qwen2.5-7b-2225q-2069q-1369q-sft+rft-newbs-old-click-2ep-lr5e-6/checkpoint-442/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

qwen2.5-7b-2225q-2069q-1369q-sft+rft-newbs-old-click-2ep-lr5e-6/checkpoint-442/tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

qwen2.5-7b-2225q-2069q-1369q-sft+rft-newbs-old-click-2ep-lr5e-6/checkpoint-442/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:558647f7524296461bdc51d2b8c7e4aa99126054b527b7bc0c51a8244c698977
+size 8568

qwen2.5-7b-2225q-2069q-1369q-sft+rft-newbs-old-click-2ep-lr5e-6/checkpoint-442/zero_to_fp32.py

@@ -0,0 +1,760 @@
+#!/usr/bin/env python
+
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example:
+#   python zero_to_fp32.py . output_dir/
+#   or
+#   python zero_to_fp32.py . output_dir/ --safe_serialization
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+import gc
+import json
+import numpy as np
+from tqdm import tqdm
+from collections import OrderedDict
+from dataclasses import dataclass
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage <= 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device, weights_only=False)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+    total_files = len(files)
+    state_dicts = []
+    for f in tqdm(files, desc='Loading checkpoint shards'):
+        state_dict = torch.load(f, map_location=device, mmap=True, weights_only=False)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+
+    model_files = get_model_state_files(ds_checkpoint_dir)
+
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+
+    if zero_stage <= 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+
+
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        state_dict[name] = frozen_param_fragments[name]
+
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _has_callable(obj, fn):
+    attr = getattr(obj, fn, None)
+    return callable(attr)
+
+
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum(
+        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
+
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+
+            unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
+            total_numel += unpartitioned_numel
+            total_params += 1
+
+            if debug:
+                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+class GatheredTensor:
+    """
+    A pseudo tensor that collects partitioned weights.
+    It is more memory efficient when there are multiple groups.
+    """
+
+    def __init__(self, flat_groups, flat_groups_offset, offset, partitioned_numel, shape):
+        self.flat_groups = flat_groups
+        self.flat_groups_offset = flat_groups_offset
+        self.offset = offset
+        self.partitioned_numel = partitioned_numel
+        self.shape = shape
+        self.dtype = self.flat_groups[0][0].dtype
+
+    def contiguous(self):
+        """
+        Merge partitioned weights from flat_groups into a single tensor.
+        """
+        end_idx = self.offset + self.partitioned_numel
+        world_size = len(self.flat_groups)
+        pad_flat_param_chunks = []
+
+        for rank_i in range(world_size):
+            # for each rank, we need to collect weights from related group/groups
+            flat_groups_at_rank_i = self.flat_groups[rank_i]
+            start_group_id = None
+            end_group_id = None
+            for group_id in range(len(self.flat_groups_offset)):
+                if self.flat_groups_offset[group_id] <= self.offset < self.flat_groups_offset[group_id + 1]:
+                    start_group_id = group_id
+                if self.flat_groups_offset[group_id] < end_idx <= self.flat_groups_offset[group_id + 1]:
+                    end_group_id = group_id
+                    break
+            # collect weights from related group/groups
+            for group_id in range(start_group_id, end_group_id + 1):
+                flat_tensor = flat_groups_at_rank_i[group_id]
+                start_offset = self.offset - self.flat_groups_offset[group_id]
+                end_offset = min(end_idx, self.flat_groups_offset[group_id + 1]) - self.flat_groups_offset[group_id]
+                pad_flat_param_chunks.append(flat_tensor[start_offset:end_offset])
+
+        # collect weights from all ranks
+        pad_flat_param = torch.cat(pad_flat_param_chunks, dim=0)
+        param = pad_flat_param[:self.shape.numel()].view(self.shape).contiguous()
+        return param
+
+
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = sum([flat_group.numel() for flat_group in fp32_flat_groups[0]]) * world_size
+
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    flat_groups_offset = [0] + list(np.cumsum([flat_tensor.numel() for flat_tensor in fp32_flat_groups[0]]))
+    for name, shape in tqdm(param_shapes.items(), desc='Gathering sharded weights'):
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # memory efficient tensor
+        tensor = GatheredTensor(fp32_flat_groups, flat_groups_offset, offset, partitioned_numel, shape)
+        state_dict[name] = tensor
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def to_torch_tensor(state_dict, return_empty_tensor=False):
+    """
+    Convert state_dict of GatheredTensor to torch tensor
+    """
+    torch_state_dict = {}
+    converted_tensors = {}
+    for name, tensor in state_dict.items():
+        tensor_id = id(tensor)
+        if tensor_id in converted_tensors:  # shared tensors
+            shared_tensor = torch_state_dict[converted_tensors[tensor_id]]
+            torch_state_dict[name] = shared_tensor
+        else:
+            converted_tensors[tensor_id] = name
+            if return_empty_tensor:
+                torch_state_dict[name] = torch.empty(tensor.shape, dtype=tensor.dtype)
+            else:
+                torch_state_dict[name] = tensor.contiguous()
+    return torch_state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
+                                             tag=None,
+                                             exclude_frozen_parameters=False,
+                                             lazy_mode=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+        - ``lazy_mode``: get state_dict in lazy mode. It returns a dict of pesduo tensor instead of torch tensor, which is more memory efficient.
+          Convert the pesduo tensor to torch tensor by ``.contiguous()``
+
+    Returns:
+        - pytorch ``state_dict``
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+
+    Note: the above usage may not work if your application doesn't have sufficient free CPU memory.
+    You may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint. Or you can load state_dict in lazy mode ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, lazy_mode=True) # not on cpu
+        for name, lazy_tensor in state_dict.item():
+            tensor = lazy_tensor.contiguous()  # to cpu
+            print(name, tensor)
+            # del tensor to release memory if it no longer in use
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+
+    state_dict = _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
+    if lazy_mode:
+        return state_dict
+    else:
+        return to_torch_tensor(state_dict)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
+                                               output_dir,
+                                               max_shard_size="5GB",
+                                               safe_serialization=False,
+                                               tag=None,
+                                               exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
+    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``output_dir``: directory to the pytorch fp32 state_dict output files
+        - ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
+        - ``safe_serialization``:  whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+    """
+
+    # Dependency pre-check
+    if safe_serialization:
+        try:
+            from safetensors.torch import save_file
+        except ImportError:
+            print('If you want to use `safe_serialization`, please `pip install safetensors`')
+            raise
+    if max_shard_size is not None:
+        try:
+            from huggingface_hub import split_torch_state_dict_into_shards
+        except ImportError:
+            print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
+            raise
+
+    # Convert zero checkpoint to state_dict
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
+                                                          tag,
+                                                          exclude_frozen_parameters,
+                                                          lazy_mode=True)
+
+    # Shard the model if it is too big.
+    weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
+    if max_shard_size is not None:
+        filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
+        # an memory-efficient approach for sharding
+        empty_state_dict = to_torch_tensor(state_dict, return_empty_tensor=True)
+        state_dict_split = split_torch_state_dict_into_shards(empty_state_dict,
+                                                              filename_pattern=filename_pattern,
+                                                              max_shard_size=max_shard_size)
+    else:
+        from collections import namedtuple
+        StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
+        state_dict_split = StateDictSplit(is_sharded=False,
+                                          filename_to_tensors={weights_name: list(state_dict.keys())})
+
+    # Save the model by shard
+    os.makedirs(output_dir, exist_ok=True)
+    filename_to_tensors = state_dict_split.filename_to_tensors.items()
+    for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
+        shard_state_dict = {tensor_name: state_dict[tensor_name] for tensor_name in tensors}
+        shard_state_dict = to_torch_tensor(shard_state_dict)
+        output_path = os.path.join(output_dir, shard_file)
+        if safe_serialization:
+            save_file(shard_state_dict, output_path, metadata={"format": "pt"})
+        else:
+            torch.save(shard_state_dict, output_path)
+        # release the memory of current shard
+        for tensor_name in list(shard_state_dict.keys()):
+            del state_dict[tensor_name]
+            del shard_state_dict[tensor_name]
+        del shard_state_dict
+        gc.collect()
+
+    # Save index if sharded
+    if state_dict_split.is_sharded:
+        index = {
+            "metadata": state_dict_split.metadata,
+            "weight_map": state_dict_split.tensor_to_filename,
+        }
+        save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
+        save_index_file = os.path.join(output_dir, save_index_file)
+        with open(save_index_file, "w", encoding="utf-8") as f:
+            content = json.dumps(index, indent=2, sort_keys=True) + "\n"
+            f.write(content)
+
+
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+
+    Returns:
+        - ``model`: modified model
+
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    """
+    logger.info(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info(f"Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+
+    return model
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument("output_dir",
+                        type=str,
+                        help="directory to the pytorch fp32 state_dict output files"
+                        "(e.g. path/checkpoint-12-output/)")
+    parser.add_argument(
+        "--max_shard_size",
+        type=str,
+        default="5GB",
+        help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
+        "lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
+        "We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
+        "without CPU OOM issues.")
+    parser.add_argument(
+        "--safe_serialization",
+        default=False,
+        action='store_true',
+        help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
+    parser.add_argument("-t",
+                        "--tag",
+                        type=str,
+                        default=None,
+                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
+    parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
+    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
+    args = parser.parse_args()
+
+    debug = args.debug
+
+    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
+                                               args.output_dir,
+                                               max_shard_size=args.max_shard_size,
+                                               safe_serialization=args.safe_serialization,
+                                               tag=args.tag,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)

qwen2.5-7b-2225q-2069q-1369q-sft+rft-newbs-old-click-2ep-lr5e-6/checkpoint-884/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

qwen2.5-7b-2225q-2069q-1369q-sft+rft-newbs-old-click-2ep-lr5e-6/checkpoint-884/args.json

@@ -0,0 +1,381 @@
+{
+  "output_dir": "/group/40143/hongzhuyi/ms-swift/output/v1-20250917-010849",
+  "overwrite_output_dir": false,
+  "do_train": false,
+  "do_eval": false,
+  "do_predict": false,
+  "eval_strategy": "epoch",
+  "prediction_loss_only": false,
+  "per_device_train_batch_size": 2,
+  "per_device_eval_batch_size": 1,
+  "per_gpu_train_batch_size": null,
+  "per_gpu_eval_batch_size": null,
+  "gradient_accumulation_steps": 4,
+  "eval_accumulation_steps": null,
+  "eval_delay": 0,
+  "torch_empty_cache_steps": null,
+  "learning_rate": 5e-06,
+  "weight_decay": 0.1,
+  "adam_beta1": 0.9,
+  "adam_beta2": 0.95,
+  "adam_epsilon": 1e-08,
+  "max_grad_norm": 1.0,
+  "num_train_epochs": 2.0,
+  "max_steps": -1,
+  "lr_scheduler_type": "cosine",
+  "lr_scheduler_kwargs": null,
+  "warmup_ratio": 0.05,
+  "warmup_steps": 0,
+  "log_level": "passive",
+  "log_level_replica": "warning",
+  "log_on_each_node": true,
+  "logging_dir": "/group/40143/hongzhuyi/ms-swift/output/v1-20250917-010849/runs",
+  "logging_strategy": "steps",
+  "logging_first_step": true,
+  "logging_steps": 1,
+  "logging_nan_inf_filter": true,
+  "save_strategy": "epoch",
+  "save_steps": 500,
+  "save_total_limit": null,
+  "save_safetensors": true,
+  "save_on_each_node": false,
+  "save_only_model": false,
+  "restore_callback_states_from_checkpoint": false,
+  "no_cuda": false,
+  "use_cpu": false,
+  "use_mps_device": false,
+  "seed": 42,
+  "data_seed": 42,
+  "jit_mode_eval": false,
+  "use_ipex": false,
+  "bf16": true,
+  "fp16": false,
+  "fp16_opt_level": "O1",
+  "half_precision_backend": "auto",
+  "bf16_full_eval": false,
+  "fp16_full_eval": false,
+  "tf32": null,
+  "local_rank": 0,
+  "ddp_backend": null,
+  "tpu_num_cores": null,
+  "tpu_metrics_debug": false,
+  "debug": null,
+  "dataloader_drop_last": false,
+  "eval_steps": 2000.0,
+  "dataloader_num_workers": 48,
+  "dataloader_prefetch_factor": null,
+  "past_index": -1,
+  "run_name": "/group/40143/hongzhuyi/ms-swift/output/v1-20250917-010849",
+  "disable_tqdm": null,
+  "remove_unused_columns": true,
+  "label_names": null,
+  "load_best_model_at_end": false,
+  "metric_for_best_model": "loss",
+  "greater_is_better": false,
+  "ignore_data_skip": false,
+  "fsdp": "",
+  "fsdp_min_num_params": 0,
+  "fsdp_config": null,
+  "fsdp_transformer_layer_cls_to_wrap": null,
+  "accelerator_config": {
+    "dispatch_batches": false
+  },
+  "deepspeed": {
+    "fp16": {
+      "enabled": "auto",
+      "loss_scale": 0,
+      "loss_scale_window": 1000,
+      "initial_scale_power": 16,
+      "hysteresis": 2,
+      "min_loss_scale": 1
+    },
+    "bf16": {
+      "enabled": "auto"
+    },
+    "zero_optimization": {
+      "stage": 3,
+      "offload_optimizer": {
+        "device": "none",
+        "pin_memory": true
+      },
+      "offload_param": {
+        "device": "none",
+        "pin_memory": true
+      },
+      "overlap_comm": false,
+      "contiguous_gradients": true,
+      "sub_group_size": 1000000000.0,
+      "reduce_bucket_size": "auto",
+      "zero_quantized_weights": false,
+      "zero_quantized_gradients": false,
+      "stage3_prefetch_bucket_size": "auto",
+      "stage3_param_persistence_threshold": "auto",
+      "stage3_max_live_parameters": 1000000000.0,
+      "stage3_max_reuse_distance": 1000000000.0,
+      "stage3_gather_16bit_weights_on_model_save": true
+    },
+    "gradient_accumulation_steps": "auto",
+    "gradient_clipping": "auto",
+    "steps_per_print": 2000,
+    "train_batch_size": "auto",
+    "train_micro_batch_size_per_gpu": "auto",
+    "wall_clock_breakdown": false
+  },
+  "label_smoothing_factor": 0.0,
+  "optim": "adamw_torch",
+  "optim_args": null,
+  "adafactor": false,
+  "group_by_length": false,
+  "length_column_name": "length",
+  "report_to": [
+    "tensorboard"
+  ],
+  "ddp_find_unused_parameters": null,
+  "ddp_bucket_cap_mb": null,
+  "ddp_broadcast_buffers": null,
+  "dataloader_pin_memory": true,
+  "dataloader_persistent_workers": false,
+  "skip_memory_metrics": true,
+  "use_legacy_prediction_loop": false,
+  "push_to_hub": false,
+  "resume_from_checkpoint": null,
+  "hub_model_id": null,
+  "hub_strategy": "every_save",
+  "hub_token": null,
+  "hub_private_repo": null,
+  "hub_always_push": false,
+  "gradient_checkpointing": true,
+  "gradient_checkpointing_kwargs": null,
+  "include_inputs_for_metrics": false,
+  "include_for_metrics": [],
+  "eval_do_concat_batches": true,
+  "fp16_backend": "auto",
+  "push_to_hub_model_id": null,
+  "push_to_hub_organization": null,
+  "push_to_hub_token": null,
+  "mp_parameters": "",
+  "auto_find_batch_size": false,
+  "full_determinism": false,
+  "torchdynamo": null,
+  "ray_scope": "last",
+  "ddp_timeout": 18000000,
+  "torch_compile": false,
+  "torch_compile_backend": null,
+  "torch_compile_mode": null,
+  "include_tokens_per_second": false,
+  "include_num_input_tokens_seen": false,
+  "neftune_noise_alpha": null,
+  "optim_target_modules": null,
+  "batch_eval_metrics": false,
+  "eval_on_start": false,
+  "use_liger_kernel": false,
+  "eval_use_gather_object": false,
+  "average_tokens_across_devices": false,
+  "sortish_sampler": false,
+  "predict_with_generate": false,
+  "generation_max_length": null,
+  "generation_num_beams": null,
+  "generation_config": null,
+  "tuner_backend": "peft",
+  "vit_gradient_checkpointing": null,
+  "router_aux_loss_coef": 0.0,
+  "enable_dft_loss": false,
+  "check_model": true,
+  "acc_strategy": "token",
+  "train_dataloader_shuffle": true,
+  "max_epochs": null,
+  "aligner_lr": null,
+  "vit_lr": null,
+  "use_logits_to_keep": null,
+  "channels": null,
+  "ds3_gather_for_generation": true,
+  "resume_only_model": false,
+  "optimizer": null,
+  "loss_type": null,
+  "metric": null,
+  "eval_use_evalscope": false,
+  "eval_dataset": [],
+  "eval_dataset_args": null,
+  "eval_limit": null,
+  "eval_generation_config": null,
+  "extra_eval_args": null,
+  "use_flash_ckpt": false,
+  "model": "Qwen/Qwen2.5-7B-Instruct",
+  "model_type": "qwen2_5",
+  "model_revision": null,
+  "task_type": "causal_lm",
+  "torch_dtype": "bfloat16",
+  "attn_impl": null,
+  "new_special_tokens": [],
+  "num_labels": null,
+  "problem_type": null,
+  "rope_scaling": null,
+  "device_map": null,
+  "max_memory": {},
+  "max_model_len": null,
+  "local_repo_path": null,
+  "init_strategy": null,
+  "template": "qwen2_5",
+  "system": null,
+  "max_length": 16240,
+  "truncation_strategy": "delete",
+  "max_pixels": null,
+  "agent_template": null,
+  "norm_bbox": null,
+  "use_chat_template": true,
+  "padding_free": false,
+  "padding_side": "right",
+  "loss_scale": "default",
+  "sequence_parallel_size": 1,
+  "response_prefix": null,
+  "template_backend": "swift",
+  "dataset": [
+    "./corr_nq_2000q_hotpot_2000q_swift.jsonl",
+    "./corr_hotpot_new1369q_format_swift.jsonl",
+    "./self_2000_2000_1369_4_hp673_swift.jsonl",
+    "./self_2000_2000_1369_4_nq400_noinfo_swift.jsonl"
+  ],
+  "val_dataset": [],
+  "split_dataset_ratio": 0.001,
+  "dataset_num_proc": 100,
+  "load_from_cache_file": true,
+  "dataset_shuffle": true,
+  "val_dataset_shuffle": false,
+  "streaming": false,
+  "interleave_prob": null,
+  "stopping_strategy": "first_exhausted",
+  "shuffle_buffer_size": 1000,
+  "download_mode": "reuse_dataset_if_exists",
+  "columns": {},
+  "strict": false,
+  "model_name": null,
+  "model_author": null,
+  "custom_dataset_info": [],
+  "quant_method": null,
+  "quant_bits": null,
+  "hqq_axis": null,
+  "bnb_4bit_compute_dtype": "bfloat16",
+  "bnb_4bit_quant_type": "nf4",
+  "bnb_4bit_use_double_quant": true,
+  "bnb_4bit_quant_storage": null,
+  "max_new_tokens": 64,
+  "temperature": 0.0,
+  "top_k": null,
+  "top_p": null,
+  "repetition_penalty": null,
+  "num_beams": 1,
+  "stream": false,
+  "stop_words": [],
+  "logprobs": false,
+  "top_logprobs": null,
+  "ckpt_dir": null,
+  "lora_modules": [],
+  "train_type": "full",
+  "adapters": [],
+  "external_plugins": [],
+  "model_kwargs": {},
+  "load_args": false,
+  "load_data_args": false,
+  "packing": false,
+  "packing_length": null,
+  "lazy_tokenize": false,
+  "cached_dataset": [],
+  "custom_register_path": [],
+  "use_hf": false,
+  "ignore_args_error": false,
+  "use_swift_lora": false,
+  "freeze_parameters": [],
+  "freeze_parameters_regex": null,
+  "freeze_parameters_ratio": 0.0,
+  "trainable_parameters": [],
+  "trainable_parameters_regex": null,
+  "freeze_llm": false,
+  "freeze_vit": true,
+  "freeze_aligner": false,
+  "target_modules": [
+    "all-linear"
+  ],
+  "target_regex": null,
+  "modules_to_save": [],
+  "lora_rank": 8,
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "lora_bias": "none",
+  "lora_dtype": null,
+  "lorap_lr_ratio": null,
+  "use_rslora": false,
+  "use_dora": false,
+  "lora_ga_batch_size": 2,
+  "lora_ga_iters": 2,
+  "lora_ga_max_length": 1024,
+  "lora_ga_direction": "ArB2r",
+  "lora_ga_scale": "stable",
+  "lora_ga_stable_gamma": 16,
+  "init_weights": true,
+  "fourier_n_frequency": 2000,
+  "fourier_scaling": 300.0,
+  "boft_block_size": 4,
+  "boft_block_num": 0,
+  "boft_n_butterfly_factor": 1,
+  "boft_dropout": 0.0,
+  "vera_rank": 256,
+  "vera_projection_prng_key": 0,
+  "vera_dropout": 0.0,
+  "vera_d_initial": 0.1,
+  "adapter_act": "gelu",
+  "adapter_length": 128,
+  "use_galore": false,
+  "galore_target_modules": null,
+  "galore_rank": 128,
+  "galore_update_proj_gap": 50,
+  "galore_scale": 1.0,
+  "galore_proj_type": "std",
+  "galore_optim_per_parameter": false,
+  "galore_with_embedding": false,
+  "galore_quantization": false,
+  "galore_proj_quant": false,
+  "galore_proj_bits": 4,
+  "galore_proj_group_size": 256,
+  "galore_cos_threshold": 0.4,
+  "galore_gamma_proj": 2,
+  "galore_queue_size": 5,
+  "adalora_target_r": 8,
+  "adalora_init_r": 12,
+  "adalora_tinit": 0,
+  "adalora_tfinal": 0,
+  "adalora_deltaT": 1,
+  "adalora_beta1": 0.85,
+  "adalora_beta2": 0.85,
+  "adalora_orth_reg_weight": 0.5,
+  "llamapro_num_new_blocks": 4,
+  "llamapro_num_groups": null,
+  "lisa_activated_layers": 0,
+  "lisa_step_interval": 20,
+  "reft_layer_key": null,
+  "reft_layers": null,
+  "reft_rank": 4,
+  "reft_intervention_type": "LoreftIntervention",
+  "reft_args": null,
+  "swanlab_token": null,
+  "swanlab_project": null,
+  "swanlab_workspace": null,
+  "swanlab_exp_name": null,
+  "swanlab_lark_webhook_url": null,
+  "swanlab_lark_secret": null,
+  "swanlab_mode": "cloud",
+  "add_version": true,
+  "create_checkpoint_symlink": false,
+  "zero_hpz_partition_size": null,
+  "deepspeed_autotp_size": null,
+  "early_stop_interval": null,
+  "rank": 0,
+  "global_world_size": 8,
+  "local_world_size": 8,
+  "model_suffix": "Qwen2.5-7B-Instruct",
+  "model_info": "ModelInfo(model_type='qwen2_5', model_dir='/root/.cache/modelscope/hub/models/Qwen/Qwen2___5-7B-Instruct', torch_dtype=torch.bfloat16, max_model_len=32768, quant_method=None, quant_bits=None, rope_scaling=None, is_moe_model=False, config=None, task_type='causal_lm', num_labels=None)",
+  "model_meta": "ModelMeta(model_type='qwen2_5', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen2.5-0.5B-Instruct', hf_model_id='Qwen/Qwen2.5-0.5B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-1.5B-Instruct', hf_model_id='Qwen/Qwen2.5-1.5B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-3B-Instruct', hf_model_id='Qwen/Qwen2.5-3B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-7B-Instruct', hf_model_id='Qwen/Qwen2.5-7B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-14B-Instruct', hf_model_id='Qwen/Qwen2.5-14B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-32B-Instruct', hf_model_id='Qwen/Qwen2.5-32B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-72B-Instruct', hf_model_id='Qwen/Qwen2.5-72B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-0.5B', hf_model_id='Qwen/Qwen2.5-0.5B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-1.5B', hf_model_id='Qwen/Qwen2.5-1.5B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-3B', hf_model_id='Qwen/Qwen2.5-3B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-7B', hf_model_id='Qwen/Qwen2.5-7B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-14B', hf_model_id='Qwen/Qwen2.5-14B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-32B', hf_model_id='Qwen/Qwen2.5-32B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-72B', hf_model_id='Qwen/Qwen2.5-72B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-0.5B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-0.5B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-1.5B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-1.5B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-3B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-3B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-7B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-7B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-14B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-14B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-32B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-32B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-72B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-72B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-0.5B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-0.5B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-1.5B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-1.5B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-3B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-3B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-7B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-7B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-14B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-14B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-32B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-32B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-72B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-72B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-0.5B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-0.5B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-1.5B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-1.5B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-3B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-3B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-7B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-7B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-14B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-14B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-32B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-32B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-72B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-72B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct', hf_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct', hf_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-3B-Instruct', hf_model_id='Qwen/Qwen2.5-Coder-3B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-7B-Instruct', hf_model_id='Qwen/Qwen2.5-Coder-7B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-14B-Instruct', hf_model_id='Qwen/Qwen2.5-Coder-14B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-32B-Instruct', hf_model_id='Qwen/Qwen2.5-Coder-32B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-0.5B', hf_model_id='Qwen/Qwen2.5-Coder-0.5B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-1.5B', hf_model_id='Qwen/Qwen2.5-Coder-1.5B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-3B', hf_model_id='Qwen/Qwen2.5-Coder-3B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-7B', hf_model_id='Qwen/Qwen2.5-Coder-7B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-14B', hf_model_id='Qwen/Qwen2.5-Coder-14B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-32B', hf_model_id='Qwen/Qwen2.5-Coder-32B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-3B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-Coder-3B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-7B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-Coder-7B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-14B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-Coder-14B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-32B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-Coder-32B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-3B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-Coder-3B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-3B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-Coder-3B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-7B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-Coder-7B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-7B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-Coder-7B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-14B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-Coder-14B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-14B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-Coder-14B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-32B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-Coder-32B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-32B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-Coder-32B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=['coding']), ModelGroup(models=[Model(ms_model_id='moonshotai/Kimi-Dev-72B', hf_model_id='moonshotai/Kimi-Dev-72B', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='qwen2_5', get_function=<function get_model_tokenizer_with_flash_attn at 0x7ff10cefadd0>, model_arch=ModelKeys(arch_name='llama', embedding='model.embed_tokens', module_list='model.layers', lm_head='lm_head', q_proj='model.layers.{}.self_attn.q_proj', k_proj='model.layers.{}.self_attn.k_proj', v_proj='model.layers.{}.self_attn.v_proj', o_proj='model.layers.{}.self_attn.o_proj', attention='model.layers.{}.self_attn', mlp='model.layers.{}.mlp', down_proj='model.layers.{}.mlp.down_proj', qkv_proj=None, qk_proj=None, qa_proj=None, qb_proj=None, kv_proj=None, kva_proj=None, kvb_proj=None), architectures=['Qwen2ForCausalLM'], additional_saved_files=[], torch_dtype=None, is_multimodal=False, is_reward=False, task_type=None, ignore_patterns=None, requires=['transformers>=4.37'], tags=[])",
+  "model_dir": "/root/.cache/modelscope/hub/models/Qwen/Qwen2___5-7B-Instruct",
+  "hub": "<class 'swift.hub.hub.MSHub'>",
+  "evaluation_strategy": "epoch",
+  "training_args": "Seq2SeqTrainingArguments(output_dir='/group/40143/hongzhuyi/ms-swift/output/v1-20250917-010849', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, eval_strategy=<IntervalStrategy.EPOCH: 'epoch'>, prediction_loss_only=False, per_device_train_batch_size=2, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=4, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=5e-06, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1.0, num_train_epochs=2.0, max_steps=-1, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs=None, warmup_ratio=0.05, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/group/40143/hongzhuyi/ms-swift/output/v1-20250917-010849/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=1, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.EPOCH: 'epoch'>, save_steps=500, save_total_limit=None, save_safetensors=True, save_on_each_node=False, save_only_model=False, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=42, jit_mode_eval=False, use_ipex=False, bf16=True, fp16=False, fp16_opt_level='O1', half_precision_backend='auto', bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=0, ddp_backend=None, tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=2000.0, dataloader_num_workers=48, dataloader_prefetch_factor=10, past_index=-1, run_name='/group/40143/hongzhuyi/ms-swift/output/v1-20250917-010849', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), deepspeed={'fp16': {'enabled': 'auto', 'loss_scale': 0, 'loss_scale_window': 1000, 'initial_scale_power': 16, 'hysteresis': 2, 'min_loss_scale': 1}, 'bf16': {'enabled': 'auto'}, 'zero_optimization': {'stage': 3, 'offload_optimizer': {'device': 'none', 'pin_memory': True}, 'offload_param': {'device': 'none', 'pin_memory': True}, 'overlap_comm': False, 'contiguous_gradients': True, 'sub_group_size': 1000000000.0, 'reduce_bucket_size': 'auto', 'zero_quantized_weights': False, 'zero_quantized_gradients': False, 'stage3_prefetch_bucket_size': 'auto', 'stage3_param_persistence_threshold': 'auto', 'stage3_max_live_parameters': 1000000000.0, 'stage3_max_reuse_distance': 1000000000.0, 'stage3_gather_16bit_weights_on_model_save': True}, 'gradient_accumulation_steps': 'auto', 'gradient_clipping': 'auto', 'steps_per_print': 2000, 'train_batch_size': 'auto', 'train_micro_batch_size_per_gpu': 'auto', 'wall_clock_breakdown': False}, label_smoothing_factor=0.0, optim=<OptimizerNames.ADAMW_TORCH: 'adamw_torch'>, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['tensorboard'], ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint=None, hub_model_id=None, hub_strategy=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_token=None, hub_private_repo=None, hub_always_push=False, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=18000000, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, include_tokens_per_second=None, include_num_input_tokens_seen=None, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, eval_use_gather_object=False, average_tokens_across_devices=None, sortish_sampler=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=None, tuner_backend='peft', vit_gradient_checkpointing=True, router_aux_loss_coef=0.0, enable_dft_loss=False, check_model=True, acc_strategy='token', train_dataloader_shuffle=True, max_epochs=None, aligner_lr=None, vit_lr=None, use_logits_to_keep=None, channels=None, ds3_gather_for_generation=True, resume_only_model=False, optimizer=None, loss_type=None, metric=None, eval_use_evalscope=False, eval_dataset=[], eval_dataset_args=None, eval_limit=None, eval_generation_config=None, extra_eval_args=None, use_flash_ckpt=False, sft_alpha=0, train_type='full', local_repo_path=None, galore_config=None)"
+}

qwen2.5-7b-2225q-2069q-1369q-sft+rft-newbs-old-click-2ep-lr5e-6/checkpoint-884/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- 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 %}

qwen2.5-7b-2225q-2069q-1369q-sft+rft-newbs-old-click-2ep-lr5e-6/checkpoint-884/config.json

@@ -0,0 +1,29 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 131072,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.52.4",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

qwen2.5-7b-2225q-2069q-1369q-sft+rft-newbs-old-click-2ep-lr5e-6/checkpoint-884/generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.52.4"
+}

qwen2.5-7b-2225q-2069q-1369q-sft+rft-newbs-old-click-2ep-lr5e-6/checkpoint-884/latest

@@ -0,0 +1 @@
+global_step884

qwen2.5-7b-2225q-2069q-1369q-sft+rft-newbs-old-click-2ep-lr5e-6/checkpoint-884/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bada0e9c0969c327852f47c3cd9c2c4619dc666657d1e41174aac221005f7e1f
+size 4877660776

qwen2.5-7b-2225q-2069q-1369q-sft+rft-newbs-old-click-2ep-lr5e-6/checkpoint-884/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:521825eec842155dd0242869524842fd490203efb3c96520fe1121e0b50ddbe7
+size 4932751008

qwen2.5-7b-2225q-2069q-1369q-sft+rft-newbs-old-click-2ep-lr5e-6/checkpoint-884/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58374d61287d22f05a4851a8576182197126102392ce164109aad9633feeac55
+size 4330865200

qwen2.5-7b-2225q-2069q-1369q-sft+rft-newbs-old-click-2ep-lr5e-6/checkpoint-884/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8925faa921ccfc8613a0bb569e555e46e72983094e220dcfc2da37b569f43994
+size 1089994880

qwen2.5-7b-2225q-2069q-1369q-sft+rft-newbs-old-click-2ep-lr5e-6/checkpoint-884/model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 15231233024
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors"
+  }
+}

qwen2.5-7b-2225q-2069q-1369q-sft+rft-newbs-old-click-2ep-lr5e-6/checkpoint-884/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be8d83c9fcd31bdcada87989659e2f162a31302f3e6d5047820156b69f879c82
+size 15920