Upload folder using huggingface_hub

.gitattributes

@@ -40,3 +40,6 @@ qwen2.5-7b-2000q-1500q-600q-1e_6-old-click-1ep/checkpoint-922/tokenizer.json fil
 qwen2.5-7b-2000q-2000q-600q-1e_6-old-click-1ep/checkpoint-1047/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 qwen2.5-7b-2225q-1089q-1e_6-old-click-1ep/checkpoint-650/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-197/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen2.5-7b-1700q-661q-1e_6-old-click-1ep/checkpoint-497/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen2.5-7b-2225q-661q-1e_6-old-click-1ep/checkpoint-607/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen2.5-7b-rft-661q-all-1e_6-old-click-1ep/checkpoint-243/tokenizer.json filter=lfs diff=lfs merge=lfs -text

log/20250819-16:15:09.log

@@ -0,0 +1,26 @@
+run sh: `/data/miniforge/envs/ms-swift/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 rft_661q_7b_click_nourl_all_swift.jsonl rft_661q_7b_click_nourl_long_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 1 --per_device_train_batch_size 1 --learning_rate 1e-6 --gradient_accumulation_steps 2 --eval_steps 20 --save_strategy epoch --logging_steps 1 --deepspeed zero3 --max_length 16240 --output_dir ./output`
+
+*****************************************
+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. 
+*****************************************
+[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: /usr/local/app/.cache/modelscope/hub/models/Qwen/Qwen2.5-7B-Instruct
+Downloading Model from https://www.modelscope.cn to directory: /usr/local/app/.cache/modelscope/hub/models/Qwen/Qwen2.5-7B-Instruct
+[2025-08-19 16:15:31,200] [INFO] [real_accelerator.py:254:get_accelerator] Setting ds_accelerator to cuda (auto detect)
+[2025-08-19 16:15:32,547] [INFO] [logging.py:107:log_dist] [Rank -1] [TorchCheckpointEngine] Initialized with serialization = False
+[2025-08-19 16:15:32,555] [INFO] [comm.py:821:init_distributed] cdb=None
+[2025-08-19 16:15:34,980] [INFO] [real_accelerator.py:254:get_accelerator] Setting ds_accelerator to cuda (auto detect)
+[2025-08-19 16:15:36,331] [INFO] [logging.py:107:log_dist] [Rank -1] [TorchCheckpointEngine] Initialized with serialization = False
+[2025-08-19 16:15:36,340] [INFO] [comm.py:821:init_distributed] cdb=None
+Downloading Model from https://www.modelscope.cn to directory: /usr/local/app/.cache/modelscope/hub/models/Qwen/Qwen2.5-7B-Instruct
+[INFO:swift] Downloading the model from ModelScope Hub, model_id: Qwen/Qwen2.5-7B-Instruct
+[2025-08-19 16:15:39,359] [INFO] [real_accelerator.py:254:get_accelerator] Setting ds_accelerator to cuda (auto detect)
+[2025-08-19 16:15:40,759] [INFO] [logging.py:107:log_dist] [Rank -1] [TorchCheckpointEngine] Initialized with serialization = False
+[2025-08-19 16:15:40,767] [INFO] [comm.py:821:init_distributed] cdb=None
+Downloading Model from https://www.modelscope.cn to directory: /usr/local/app/.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: /usr/local/app/.cache/modelscope/hub/models/Qwen/Qwen2___5-7B-Instruct
+[INFO:swift] Setting args.lazy_tokenize: False
+[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}
+[2025-08-19 16:15:44,588] [INFO] [real_accelerator.py:254:get_accelerator] Setting ds_accelerator to cuda (auto detect)

log/20250819-16:16:54.log

@@ -0,0 +1,16 @@
+Traceback (most recent call last):
+  File "/data/miniforge/envs/ms-swift/bin/swift", line 3, in <module>
+    from swift.cli.main import cli_main
+  File "/group/40143/hongzhuyi/ms-swift/swift/__init__.py", line 4, in <module>
+    from .utils.import_utils import _LazyModule
+  File "/group/40143/hongzhuyi/ms-swift/swift/utils/__init__.py", line 3, in <module>
+    from .env import (get_dist_setting, get_hf_endpoint, get_node_setting, get_pai_tensorboard_dir, is_deepspeed_enabled,
+  File "/group/40143/hongzhuyi/ms-swift/swift/utils/env.py", line 9, in <module>
+    from .logger import get_logger
+  File "/group/40143/hongzhuyi/ms-swift/swift/utils/logger.py", line 123, in <module>
+    ms_logger.setLevel(log_level)
+  File "/data/miniforge/envs/ms-swift/lib/python3.10/logging/__init__.py", line 1452, in setLevel
+    self.level = _checkLevel(level)
+  File "/data/miniforge/envs/ms-swift/lib/python3.10/logging/__init__.py", line 198, in _checkLevel
+    raise ValueError("Unknown level: %r" % level)
+ValueError: Unknown level: 'TRACE'

log/20250819-16:18:09.log

@@ -0,0 +1,296 @@
+run sh: `/data/miniforge/envs/ms-swift/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 /mnt/public/yhz/yutao/model/Qwen2.5-7B-Instruct --train_type full --dataset ./rft_661q_7b_click_nourl_long_swift ./corr_data_2225q_old_click_nourl_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 1 --per_device_train_batch_size 1 --learning_rate 1e-6 --gradient_accumulation_steps 2 --eval_steps 20 --save_strategy epoch --logging_steps 1 --deepspeed zero3 --max_length 16240 --output_dir ./output`
+
+*****************************************
+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. 
+*****************************************
+[INFO:swift] Successfully registered `/group/40143/hongzhuyi/ms-swift/swift/llm/dataset/data/dataset_info.json`.
+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
+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
+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
+[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
+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
+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
+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
+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__
+    return SwiftSft(args).main()
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/train/sft.py", line 27, in __init__
+    return SwiftSft(args).main()
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/train/sft.py", line 27, in __init__
+    return SwiftSft(args).main()
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/train/sft.py", line 27, in __init__
+    return SwiftSft(args).main()
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/train/sft.py", line 27, in __init__
+    return SwiftSft(args).main()
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/train/sft.py", line 27, in __init__
+    return SwiftSft(args).main()
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/train/sft.py", line 27, in __init__
+    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__
+    super().__init__(args)
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/base.py", line 19, in __init__
+    super().__init__(args)
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/base.py", line 19, in __init__
+    super().__init__(args)
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/base.py", line 19, in __init__
+    super().__init__(args)
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/base.py", line 19, in __init__
+    super().__init__(args)
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/base.py", line 19, in __init__
+    super().__init__(args)
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/base.py", line 19, 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)
+    self.args = self._parse_args(args)  File "/group/40143/hongzhuyi/ms-swift/swift/llm/base.py", line 31, in _parse_args
+
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/base.py", line 31, in _parse_args
+    self.args = self._parse_args(args)
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/base.py", line 31, in _parse_args
+    self.args = self._parse_args(args)    
+self.args = self._parse_args(args)
+    self.args = self._parse_args(args)  File "/group/40143/hongzhuyi/ms-swift/swift/llm/base.py", line 31, in _parse_args
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/base.py", line 31, in _parse_args
+
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/base.py", line 31, in _parse_args
+    self.args = self._parse_args(args)
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/base.py", line 31, in _parse_args
+    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_argv = parse_args(self.args_class, args)
+  File "/group/40143/hongzhuyi/ms-swift/swift/utils/utils.py", line 152, 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_argv = parse_args(self.args_class, args)
+  File "/group/40143/hongzhuyi/ms-swift/swift/utils/utils.py", line 152, 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_argv = parse_args(self.args_class, args)
+  File "/group/40143/hongzhuyi/ms-swift/swift/utils/utils.py", line 152, 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_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 "/data/miniforge/envs/ms-swift/lib/python3.10/site-packages/transformers/hf_argparser.py", line 358, in parse_args_into_dataclasses
+    args, remaining_args = parser.parse_args_into_dataclasses(argv, return_remaining_strings=True)
+  File "/data/miniforge/envs/ms-swift/lib/python3.10/site-packages/transformers/hf_argparser.py", line 358, in parse_args_into_dataclasses
+    args, remaining_args = parser.parse_args_into_dataclasses(argv, return_remaining_strings=True)
+  File "/data/miniforge/envs/ms-swift/lib/python3.10/site-packages/transformers/hf_argparser.py", line 358, in parse_args_into_dataclasses
+    args, remaining_args = parser.parse_args_into_dataclasses(argv, return_remaining_strings=True)
+  File "/data/miniforge/envs/ms-swift/lib/python3.10/site-packages/transformers/hf_argparser.py", line 358, in parse_args_into_dataclasses
+    args, remaining_args = parser.parse_args_into_dataclasses(argv, return_remaining_strings=True)
+  File "/data/miniforge/envs/ms-swift/lib/python3.10/site-packages/transformers/hf_argparser.py", line 358, in parse_args_into_dataclasses
+        args, remaining_args = parser.parse_args_into_dataclasses(argv, return_remaining_strings=True)args, remaining_args = parser.parse_args_into_dataclasses(argv, return_remaining_strings=True)
+
+  File "/data/miniforge/envs/ms-swift/lib/python3.10/site-packages/transformers/hf_argparser.py", line 358, in parse_args_into_dataclasses
+      File "/data/miniforge/envs/ms-swift/lib/python3.10/site-packages/transformers/hf_argparser.py", line 358, in parse_args_into_dataclasses
+args, remaining_args = parser.parse_args_into_dataclasses(argv, return_remaining_strings=True)
+  File "/data/miniforge/envs/ms-swift/lib/python3.10/site-packages/transformers/hf_argparser.py", line 358, in parse_args_into_dataclasses
+    obj = dtype(**inputs)
+      File "<string>", line 323, in __init__
+obj = dtype(**inputs)
+  File "<string>", line 323, in __init__
+    obj = dtype(**inputs)
+  File "<string>", line 323, in __init__
+    obj = dtype(**inputs)
+  File "<string>", line 323, in __init__
+    obj = dtype(**inputs)
+  File "<string>", line 323, in __init__
+        obj = dtype(**inputs)
+obj = dtype(**inputs)
+  File "<string>", line 323, in __init__
+  File "<string>", line 323, in __init__
+    obj = dtype(**inputs)
+  File "<string>", line 323, in __init__
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/argument/train_args.py", line 171, in __post_init__
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/argument/train_args.py", line 171, in __post_init__
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/argument/train_args.py", line 171, in __post_init__
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/argument/train_args.py", line 171, in __post_init__
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/argument/train_args.py", line 171, in __post_init__
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/argument/train_args.py", line 171, in __post_init__
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/argument/train_args.py", line 171, in __post_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__
+    BaseArguments.__post_init__(self)
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/argument/base_args/base_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__
+    BaseArguments.__post_init__(self)
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/argument/base_args/base_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__
+    BaseArguments.__post_init__(self)
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/argument/base_args/base_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__
+    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)ModelArguments.__post_init__(self)
+
+      File "/group/40143/hongzhuyi/ms-swift/swift/llm/argument/base_args/model_args.py", line 176, in __post_init__
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/argument/base_args/model_args.py", line 176, 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__
+    ModelArguments.__post_init__(self)
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/argument/base_args/model_args.py", line 176, 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__
+ModelArguments.__post_init__(self)
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/argument/base_args/model_args.py", line 176, 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__
+    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._init_torch_dtype()
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/argument/base_args/model_args.py", line 90, in _init_torch_dtype
+    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._init_torch_dtype()
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/argument/base_args/model_args.py", line 90, in _init_torch_dtype
+    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._init_torch_dtype()
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/argument/base_args/model_args.py", line 90, in _init_torch_dtype
+    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._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.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.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.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.torch_dtype: torch.dtype = self._init_model_info()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
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/argument/base_args/model_args.py", line 145, in _init_model_info
+    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.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
+    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
+        self.model_info, self.model_meta = get_model_info_meta(**self.get_model_kwargs())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
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/model/register.py", line 533, in get_model_info_meta
+    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
+    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
+    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
+    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(        model_dir = safe_snapshot_download(
+model_dir = safe_snapshot_download(model_dir = safe_snapshot_download(
+
+
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/model/utils.py", line 295, in safe_snapshot_download
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/model/utils.py", line 295, in safe_snapshot_download
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/model/utils.py", line 295, in safe_snapshot_download
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/model/utils.py", line 295, in safe_snapshot_download
+    model_dir = safe_snapshot_download(
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/model/utils.py", line 295, in safe_snapshot_download
+    model_dir = safe_snapshot_download(
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/model/utils.py", line 295, in safe_snapshot_download
+    model_dir = safe_snapshot_download(
+    model_dir = safe_snapshot_download(
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/model/utils.py", line 295, in safe_snapshot_download
+  File "/group/40143/hongzhuyi/ms-swift/swift/llm/model/utils.py", line 295, in safe_snapshot_download
+    raise ValueError(f"path: '{model_id_or_path}' not found")
+ValueError: path: '/mnt/public/yhz/yutao/model/Qwen2.5-7B-Instruct' not found
+        raise ValueError(f"path: '{model_id_or_path}' not found")raise ValueError(f"path: '{model_id_or_path}' not found")
+
+ValueErrorValueError:     : path: '/mnt/public/yhz/yutao/model/Qwen2.5-7B-Instruct' not foundpath: '/mnt/public/yhz/yutao/model/Qwen2.5-7B-Instruct' not foundraise ValueError(f"path: '{model_id_or_path}' not found")
+
+
+ValueError: path: '/mnt/public/yhz/yutao/model/Qwen2.5-7B-Instruct' not found
+    raise ValueError(f"path: '{model_id_or_path}' not found")
+ValueError: path: '/mnt/public/yhz/yutao/model/Qwen2.5-7B-Instruct' not found
+    raise ValueError(f"path: '{model_id_or_path}' not found")
+ValueError    : path: '/mnt/public/yhz/yutao/model/Qwen2.5-7B-Instruct' not foundraise ValueError(f"path: '{model_id_or_path}' not found")
+
+ValueError: path: '/mnt/public/yhz/yutao/model/Qwen2.5-7B-Instruct' not found
+    raise ValueError(f"path: '{model_id_or_path}' not found")
+ValueError: path: '/mnt/public/yhz/yutao/model/Qwen2.5-7B-Instruct' not found
+W0819 16:18:17.761000 2094221 site-packages/torch/distributed/elastic/multiprocessing/api.py:900] Sending process 2094299 closing signal SIGTERM
+W0819 16:18:17.762000 2094221 site-packages/torch/distributed/elastic/multiprocessing/api.py:900] Sending process 2094300 closing signal SIGTERM
+W0819 16:18:17.762000 2094221 site-packages/torch/distributed/elastic/multiprocessing/api.py:900] Sending process 2094301 closing signal SIGTERM
+W0819 16:18:17.763000 2094221 site-packages/torch/distributed/elastic/multiprocessing/api.py:900] Sending process 2094302 closing signal SIGTERM
+W0819 16:18:17.763000 2094221 site-packages/torch/distributed/elastic/multiprocessing/api.py:900] Sending process 2094303 closing signal SIGTERM
+W0819 16:18:17.763000 2094221 site-packages/torch/distributed/elastic/multiprocessing/api.py:900] Sending process 2094304 closing signal SIGTERM
+W0819 16:18:17.763000 2094221 site-packages/torch/distributed/elastic/multiprocessing/api.py:900] Sending process 2094306 closing signal SIGTERM
+E0819 16:18:17.829000 2094221 site-packages/torch/distributed/elastic/multiprocessing/api.py:874] failed (exitcode: 1) local_rank: 6 (pid: 2094305) of binary: /data/miniforge/envs/ms-swift/bin/python3.10
+Traceback (most recent call last):
+  File "/data/miniforge/envs/ms-swift/lib/python3.10/runpy.py", line 196, in _run_module_as_main
+    return _run_code(code, main_globals, None,
+  File "/data/miniforge/envs/ms-swift/lib/python3.10/runpy.py", line 86, in _run_code
+    exec(code, run_globals)
+  File "/data/miniforge/envs/ms-swift/lib/python3.10/site-packages/torch/distributed/run.py", line 905, in <module>
+    main()
+  File "/data/miniforge/envs/ms-swift/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 357, in wrapper
+    return f(*args, **kwargs)
+  File "/data/miniforge/envs/ms-swift/lib/python3.10/site-packages/torch/distributed/run.py", line 901, in main
+    run(args)
+  File "/data/miniforge/envs/ms-swift/lib/python3.10/site-packages/torch/distributed/run.py", line 892, in run
+    elastic_launch(
+  File "/data/miniforge/envs/ms-swift/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 143, in __call__
+    return launch_agent(self._config, self._entrypoint, list(args))
+  File "/data/miniforge/envs/ms-swift/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 277, 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      : 2025-08-19_16:18:17
+  host      : TENCENT64.site
+  rank      : 6 (local_rank: 6)
+  exitcode  : 1 (pid: 2094305)
+  error_file: <N/A>
+  traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html
+============================================================

log/20250819-16:19:01.log

@@ -0,0 +1,506 @@
+run sh: `/data/miniforge/envs/ms-swift/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 ./rft_661q_7b_click_nourl_long_swift ./corr_data_2225q_old_click_nourl_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 1 --per_device_train_batch_size 1 --learning_rate 1e-6 --gradient_accumulation_steps 2 --eval_steps 20 --save_strategy epoch --logging_steps 1 --deepspeed zero3 --max_length 16240 --output_dir ./output`
+
+*****************************************
+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. 
+*****************************************
+[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: /usr/local/app/.cache/modelscope/hub/models/Qwen/Qwen2.5-7B-Instruct
+Downloading Model from https://www.modelscope.cn to directory: /usr/local/app/.cache/modelscope/hub/models/Qwen/Qwen2.5-7B-Instruct
+[2025-08-19 16:19:16,373] [INFO] [real_accelerator.py:254:get_accelerator] Setting ds_accelerator to cuda (auto detect)
+[INFO:swift] Downloading the model from ModelScope Hub, model_id: Qwen/Qwen2.5-7B-Instruct
+[2025-08-19 16:19:18,036] [INFO] [logging.py:107:log_dist] [Rank -1] [TorchCheckpointEngine] Initialized with serialization = False
+[2025-08-19 16:19:18,046] [INFO] [comm.py:821:init_distributed] cdb=None
+[2025-08-19 16:19:18,418] [INFO] [real_accelerator.py:254:get_accelerator] Setting ds_accelerator to cuda (auto detect)
+Downloading Model from https://www.modelscope.cn to directory: /usr/local/app/.cache/modelscope/hub/models/Qwen/Qwen2.5-7B-Instruct
+[2025-08-19 16:19:19,859] [INFO] [logging.py:107:log_dist] [Rank -1] [TorchCheckpointEngine] Initialized with serialization = False
+[2025-08-19 16:19:19,868] [INFO] [comm.py:821:init_distributed] cdb=None
+[INFO:modelscope] Target directory already exists, skipping creation.
+[INFO:swift] Loading the model using model_dir: /usr/local/app/.cache/modelscope/hub/models/Qwen/Qwen2___5-7B-Instruct
+[INFO:swift] Setting args.lazy_tokenize: False
+[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}
+[2025-08-19 16:19:22,266] [INFO] [real_accelerator.py:254:get_accelerator] Setting ds_accelerator to cuda (auto detect)
+Downloading Model from https://www.modelscope.cn to directory: /usr/local/app/.cache/modelscope/hub/models/Qwen/Qwen2.5-7B-Instruct
+[2025-08-19 16:19:23,811] [INFO] [logging.py:107:log_dist] [Rank -1] [TorchCheckpointEngine] Initialized with serialization = False
+[2025-08-19 16:19:23,820] [INFO] [comm.py:821:init_distributed] cdb=None
+[2025-08-19 16:19:23,820] [INFO] [comm.py:852:init_distributed] Initializing TorchBackend in DeepSpeed with backend nccl
+[2025-08-19 16:19:26,112] [INFO] [real_accelerator.py:254:get_accelerator] Setting ds_accelerator to cuda (auto detect)
+Downloading Model from https://www.modelscope.cn to directory: /usr/local/app/.cache/modelscope/hub/models/Qwen/Qwen2.5-7B-Instruct
+[2025-08-19 16:19:27,569] [INFO] [logging.py:107:log_dist] [Rank -1] [TorchCheckpointEngine] Initialized with serialization = False
+[2025-08-19 16:19:27,579] [INFO] [comm.py:821:init_distributed] cdb=None
+[2025-08-19 16:19:29,771] [INFO] [real_accelerator.py:254:get_accelerator] Setting ds_accelerator to cuda (auto detect)
+[2025-08-19 16:19:31,543] [INFO] [logging.py:107:log_dist] [Rank -1] [TorchCheckpointEngine] Initialized with serialization = False
+[2025-08-19 16:19:31,553] [INFO] [comm.py:821:init_distributed] cdb=None
+Downloading Model from https://www.modelscope.cn to directory: /usr/local/app/.cache/modelscope/hub/models/Qwen/Qwen2.5-7B-Instruct
+[2025-08-19 16:19:34,907] [INFO] [real_accelerator.py:254:get_accelerator] Setting ds_accelerator to cuda (auto detect)
+[2025-08-19 16:19:36,507] [INFO] [logging.py:107:log_dist] [Rank -1] [TorchCheckpointEngine] Initialized with serialization = False
+[2025-08-19 16:19:36,517] [INFO] [comm.py:821:init_distributed] cdb=None
+Downloading Model from https://www.modelscope.cn to directory: /usr/local/app/.cache/modelscope/hub/models/Qwen/Qwen2.5-7B-Instruct
+[2025-08-19 16:19:39,171] [INFO] [real_accelerator.py:254:get_accelerator] Setting ds_accelerator to cuda (auto detect)
+[2025-08-19 16:19:40,799] [INFO] [logging.py:107:log_dist] [Rank -1] [TorchCheckpointEngine] Initialized with serialization = False
+[2025-08-19 16:19:40,808] [INFO] [comm.py:821:init_distributed] cdb=None
+Downloading Model from https://www.modelscope.cn to directory: /usr/local/app/.cache/modelscope/hub/models/Qwen/Qwen2.5-7B-Instruct
+[2025-08-19 16:19:43,894] [INFO] [real_accelerator.py:254:get_accelerator] Setting ds_accelerator to cuda (auto detect)
+[2025-08-19 16:19:45,485] [INFO] [logging.py:107:log_dist] [Rank -1] [TorchCheckpointEngine] Initialized with serialization = False
+[2025-08-19 16:19:45,494] [INFO] [comm.py:821:init_distributed] cdb=None
+[INFO:swift] output_dir: /group/40143/hongzhuyi/ms-swift/output/v0-20250819-161947
+[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=True,
+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=['./rft_661q_7b_click_nourl_long_swift', './corr_data_2225q_old_click_nourl_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=20.0,
+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=2,
+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_revision=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=1e-06,
+length_column_name=length,
+liger_kernel_config=None,
+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/v0-20250819-161947/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=1.0,
+optim=adamw_torch_fused,
+optim_args=None,
+optim_target_modules=None,
+optimizer=None,
+output_dir=/group/40143/hongzhuyi/ms-swift/output/v0-20250819-161947,
+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=1,
+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/v0-20250819-161947,
+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: /usr/local/app/.cache/modelscope/hub/models/Qwen/Qwen2.5-7B-Instruct
+[2025-08-19 16:19:54,034] [INFO] [config.py:684:__init__] Config mesh_device None world_size = 8
+Downloading Model from https://www.modelscope.cn to directory: /usr/local/app/.cache/modelscope/hub/models/Qwen/Qwen2.5-7B-Instruct
+[2025-08-19 16:19:58,871] [INFO] [config.py:684:__init__] Config mesh_device None world_size = 8
+Downloading Model from https://www.modelscope.cn to directory: /usr/local/app/.cache/modelscope/hub/models/Qwen/Qwen2.5-7B-Instruct
+[INFO:swift] Downloading the model from ModelScope Hub, model_id: Qwen/Qwen2.5-7B-Instruct
+[2025-08-19 16:20:02,684] [INFO] [config.py:684:__init__] Config mesh_device None world_size = 8
+Downloading Model from https://www.modelscope.cn to directory: /usr/local/app/.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: /usr/local/app/.cache/modelscope/hub/models/Qwen/Qwen2___5-7B-Instruct
+[INFO:swift] model_kwargs: {'device_map': None}
+[2025-08-19 16:20:06,543] [INFO] [config.py:684:__init__] Config mesh_device None world_size = 8
+Downloading Model from https://www.modelscope.cn to directory: /usr/local/app/.cache/modelscope/hub/models/Qwen/Qwen2.5-7B-Instruct
+[2025-08-19 16:20:11,667] [INFO] [config.py:684:__init__] Config mesh_device None world_size = 8
+Downloading Model from https://www.modelscope.cn to directory: /usr/local/app/.cache/modelscope/hub/models/Qwen/Qwen2.5-7B-Instruct
+[2025-08-19 16:20:15,643] [INFO] [config.py:684:__init__] Config mesh_device None world_size = 8
+Downloading Model from https://www.modelscope.cn to directory: /usr/local/app/.cache/modelscope/hub/models/Qwen/Qwen2.5-7B-Instruct
+[2025-08-19 16:20:19,121] [INFO] [config.py:684:__init__] Config mesh_device None world_size = 8
+Downloading Model from https://www.modelscope.cn to directory: /usr/local/app/.cache/modelscope/hub/models/Qwen/Qwen2.5-7B-Instruct
+[2025-08-19 16:20:22,900] [INFO] [config.py:684:__init__] Config mesh_device None world_size = 8
+[2025-08-19 16:20:23,038] [INFO] [partition_parameters.py:366:__exit__] finished initializing model - num_params = 339, num_elems = 7.62B
+
+
+
+
+
+
+
+
+[INFO:swift] model_info: ModelInfo(model_type='qwen2_5', model_dir='/usr/local/app/.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,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "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": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.55.2",
+  "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: 2025-08-19 16:20:26.206375
+[INFO:swift] swift.__version__: 3.8.0.dev0
+[INFO:swift] Downloading the dataset from ModelScope, dataset_id: ./rft_661q_7b_click_nourl_long_swift
+[ERROR:swift] Dataset ./rft_661q_7b_click_nourl_long_swift load failed: subset_name=default,split=train with error: Failed to check existence of repo: dataset, make sure you have access authorization.
+[ERROR:swift] Dataset ./rft_661q_7b_click_nourl_long_swift load failed: subset_name=default,split=train with error: Failed to check existence of repo: dataset, make sure you have access authorization.
+[rank0]: Traceback (most recent call last):
+[rank0]:   File "/group/40143/hongzhuyi/ms-swift/swift/cli/sft.py", line 10, in <module>
+[rank0]:     sft_main()
+[rank0]:   File "/group/40143/hongzhuyi/ms-swift/swift/llm/train/sft.py", line 328, in sft_main
+[rank0]:     return SwiftSft(args).main()
+[rank0]:   File "/group/40143/hongzhuyi/ms-swift/swift/llm/base.py", line 49, in main
+[rank0]:     result = self.run()
+[rank0]:   File "/group/40143/hongzhuyi/ms-swift/swift/llm/train/sft.py", line 158, in run
+[rank0]:     train_dataset, val_dataset = self._prepare_dataset()
+[rank0]:   File "/group/40143/hongzhuyi/ms-swift/swift/llm/train/sft.py", line 117, in _prepare_dataset
+[rank0]:     train_dataset, val_dataset = self._get_dataset()
+[rank0]:   File "/group/40143/hongzhuyi/ms-swift/swift/llm/train/sft.py", line 71, in _get_dataset
+[rank0]:     train_dataset, val_dataset = load_dataset(
+[rank0]:   File "/group/40143/hongzhuyi/ms-swift/swift/llm/dataset/loader.py", line 533, in load_dataset
+[rank0]:     train_dataset = load_function(dataset_syntax, dataset_meta, **load_kwargs, use_hf=use_hf)
+[rank0]:   File "/group/40143/hongzhuyi/ms-swift/swift/llm/dataset/loader.py", line 408, in load
+[rank0]:     dataset = DatasetLoader._load_repo_dataset(
+[rank0]:   File "/group/40143/hongzhuyi/ms-swift/swift/llm/dataset/loader.py", line 266, in _load_repo_dataset
+[rank0]:     dataset = hub.load_dataset(
+[rank0]:   File "/group/40143/hongzhuyi/ms-swift/swift/hub/hub.py", line 296, in load_dataset
+[rank0]:     return MsDataset.load(
+[rank0]:   File "/data/miniforge/envs/ms-swift/lib/python3.10/site-packages/modelscope/msdatasets/ms_dataset.py", line 297, in load
+[rank0]:     endpoint = _api.get_endpoint_for_read(
+[rank0]:   File "/data/miniforge/envs/ms-swift/lib/python3.10/site-packages/modelscope/hub/api.py", line 384, in get_endpoint_for_read
+[rank0]:     if not self.repo_exists(
+[rank0]:   File "/data/miniforge/envs/ms-swift/lib/python3.10/site-packages/modelscope/hub/api.py", line 458, in repo_exists
+[rank0]:     raise Exception(
+[rank0]: Exception: Failed to check existence of repo: dataset, make sure you have access authorization.
+[rank0]:[W819 16:20:32.003939144 ProcessGroupNCCL.cpp:1538] Warning: WARNING: destroy_process_group() was not called before program exit, which can leak resources. For more info, please see https://pytorch.org/docs/stable/distributed.html#shutdown (function operator())

log/20250819-16:21:22.log

@@ -0,0 +1,549 @@
+run sh: `/data/miniforge/envs/ms-swift/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 rft_661q_7b_click_nourl_long_swift corr_data_2225q_old_click_nourl_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 1 --per_device_train_batch_size 1 --learning_rate 1e-6 --gradient_accumulation_steps 2 --eval_steps 20 --save_strategy epoch --logging_steps 1 --deepspeed zero3 --max_length 16240 --output_dir ./output`
+
+*****************************************
+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. 
+*****************************************
+[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: /usr/local/app/.cache/modelscope/hub/models/Qwen/Qwen2.5-7B-Instruct
+[2025-08-19 16:21:34,627] [INFO] [real_accelerator.py:254:get_accelerator] Setting ds_accelerator to cuda (auto detect)
+[2025-08-19 16:21:36,030] [INFO] [logging.py:107:log_dist] [Rank -1] [TorchCheckpointEngine] Initialized with serialization = False
+[2025-08-19 16:21:36,039] [INFO] [comm.py:821:init_distributed] cdb=None
+Downloading Model from https://www.modelscope.cn to directory: /usr/local/app/.cache/modelscope/hub/models/Qwen/Qwen2.5-7B-Instruct
+[2025-08-19 16:21:38,557] [INFO] [real_accelerator.py:254:get_accelerator] Setting ds_accelerator to cuda (auto detect)
+Downloading Model from https://www.modelscope.cn to directory: /usr/local/app/.cache/modelscope/hub/models/Qwen/Qwen2.5-7B-Instruct
+[2025-08-19 16:21:39,915] [INFO] [logging.py:107:log_dist] [Rank -1] [TorchCheckpointEngine] Initialized with serialization = False
+[2025-08-19 16:21:39,925] [INFO] [comm.py:821:init_distributed] cdb=None
+[INFO:swift] Downloading the model from ModelScope Hub, model_id: Qwen/Qwen2.5-7B-Instruct
+[2025-08-19 16:21:42,450] [INFO] [real_accelerator.py:254:get_accelerator] Setting ds_accelerator to cuda (auto detect)
+[2025-08-19 16:21:43,815] [INFO] [logging.py:107:log_dist] [Rank -1] [TorchCheckpointEngine] Initialized with serialization = False
+[2025-08-19 16:21:43,823] [INFO] [comm.py:821:init_distributed] cdb=None
+Downloading Model from https://www.modelscope.cn to directory: /usr/local/app/.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: /usr/local/app/.cache/modelscope/hub/models/Qwen/Qwen2___5-7B-Instruct
+[INFO:swift] Setting args.lazy_tokenize: False
+[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}
+[2025-08-19 16:21:46,344] [INFO] [real_accelerator.py:254:get_accelerator] Setting ds_accelerator to cuda (auto detect)
+[2025-08-19 16:21:47,714] [INFO] [logging.py:107:log_dist] [Rank -1] [TorchCheckpointEngine] Initialized with serialization = False
+[2025-08-19 16:21:47,723] [INFO] [comm.py:821:init_distributed] cdb=None
+[2025-08-19 16:21:47,723] [INFO] [comm.py:852:init_distributed] Initializing TorchBackend in DeepSpeed with backend nccl
+Downloading Model from https://www.modelscope.cn to directory: /usr/local/app/.cache/modelscope/hub/models/Qwen/Qwen2.5-7B-Instruct
+[2025-08-19 16:21:50,437] [INFO] [real_accelerator.py:254:get_accelerator] Setting ds_accelerator to cuda (auto detect)
+Downloading Model from https://www.modelscope.cn to directory: /usr/local/app/.cache/modelscope/hub/models/Qwen/Qwen2.5-7B-Instruct
+[2025-08-19 16:21:51,834] [INFO] [logging.py:107:log_dist] [Rank -1] [TorchCheckpointEngine] Initialized with serialization = False
+[2025-08-19 16:21:51,842] [INFO] [comm.py:821:init_distributed] cdb=None
+[2025-08-19 16:21:54,513] [INFO] [real_accelerator.py:254:get_accelerator] Setting ds_accelerator to cuda (auto detect)
+Downloading Model from https://www.modelscope.cn to directory: /usr/local/app/.cache/modelscope/hub/models/Qwen/Qwen2.5-7B-Instruct
+[2025-08-19 16:21:55,919] [INFO] [logging.py:107:log_dist] [Rank -1] [TorchCheckpointEngine] Initialized with serialization = False
+[2025-08-19 16:21:55,928] [INFO] [comm.py:821:init_distributed] cdb=None
+[2025-08-19 16:21:58,116] [INFO] [real_accelerator.py:254:get_accelerator] Setting ds_accelerator to cuda (auto detect)
+Downloading Model from https://www.modelscope.cn to directory: /usr/local/app/.cache/modelscope/hub/models/Qwen/Qwen2.5-7B-Instruct
+[2025-08-19 16:21:59,688] [INFO] [logging.py:107:log_dist] [Rank -1] [TorchCheckpointEngine] Initialized with serialization = False
+[2025-08-19 16:21:59,697] [INFO] [comm.py:821:init_distributed] cdb=None
+[2025-08-19 16:22:01,967] [INFO] [real_accelerator.py:254:get_accelerator] Setting ds_accelerator to cuda (auto detect)
+[2025-08-19 16:22:03,339] [INFO] [logging.py:107:log_dist] [Rank -1] [TorchCheckpointEngine] Initialized with serialization = False
+[2025-08-19 16:22:03,347] [INFO] [comm.py:821:init_distributed] cdb=None
+[INFO:swift] output_dir: /group/40143/hongzhuyi/ms-swift/output/v1-20250819-162207
+[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=True,
+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=['rft_661q_7b_click_nourl_long_swift', 'corr_data_2225q_old_click_nourl_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=20.0,
+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=2,
+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_revision=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=1e-06,
+length_column_name=length,
+liger_kernel_config=None,
+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/v1-20250819-162207/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=1.0,
+optim=adamw_torch_fused,
+optim_args=None,
+optim_target_modules=None,
+optimizer=None,
+output_dir=/group/40143/hongzhuyi/ms-swift/output/v1-20250819-162207,
+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=1,
+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/v1-20250819-162207,
+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: /usr/local/app/.cache/modelscope/hub/models/Qwen/Qwen2.5-7B-Instruct
+[2025-08-19 16:22:13,590] [INFO] [config.py:684:__init__] Config mesh_device None world_size = 8
+Downloading Model from https://www.modelscope.cn to directory: /usr/local/app/.cache/modelscope/hub/models/Qwen/Qwen2.5-7B-Instruct
+[2025-08-19 16:22:19,378] [INFO] [config.py:684:__init__] Config mesh_device None world_size = 8
+Downloading Model from https://www.modelscope.cn to directory: /usr/local/app/.cache/modelscope/hub/models/Qwen/Qwen2.5-7B-Instruct
+[2025-08-19 16:22:23,476] [INFO] [config.py:684:__init__] Config mesh_device None world_size = 8
+Downloading Model from https://www.modelscope.cn to directory: /usr/local/app/.cache/modelscope/hub/models/Qwen/Qwen2.5-7B-Instruct
+[INFO:swift] Downloading the model from ModelScope Hub, model_id: Qwen/Qwen2.5-7B-Instruct
+[2025-08-19 16:22:28,805] [INFO] [config.py:684:__init__] Config mesh_device None world_size = 8
+Downloading Model from https://www.modelscope.cn to directory: /usr/local/app/.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: /usr/local/app/.cache/modelscope/hub/models/Qwen/Qwen2___5-7B-Instruct
+[INFO:swift] model_kwargs: {'device_map': None}
+[2025-08-19 16:22:34,666] [INFO] [config.py:684:__init__] Config mesh_device None world_size = 8
+Downloading Model from https://www.modelscope.cn to directory: /usr/local/app/.cache/modelscope/hub/models/Qwen/Qwen2.5-7B-Instruct
+[2025-08-19 16:22:38,945] [INFO] [config.py:684:__init__] Config mesh_device None world_size = 8
+Downloading Model from https://www.modelscope.cn to directory: /usr/local/app/.cache/modelscope/hub/models/Qwen/Qwen2.5-7B-Instruct
+[2025-08-19 16:22:44,102] [INFO] [config.py:684:__init__] Config mesh_device None world_size = 8
+Downloading Model from https://www.modelscope.cn to directory: /usr/local/app/.cache/modelscope/hub/models/Qwen/Qwen2.5-7B-Instruct
+[2025-08-19 16:22:48,742] [INFO] [config.py:684:__init__] Config mesh_device None world_size = 8
+[2025-08-19 16:22:49,486] [INFO] [partition_parameters.py:366:__exit__] finished initializing model - num_params = 339, num_elems = 7.62B
+
+
+
+
+
+
+
+
+[INFO:swift] model_info: ModelInfo(model_type='qwen2_5', model_dir='/usr/local/app/.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,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "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": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.55.2",
+  "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: 2025-08-19 16:22:53.141002
+[INFO:swift] swift.__version__: 3.8.0.dev0
+[INFO:swift] Downloading the dataset from ModelScope, dataset_id: rft_661q_7b_click_nourl_long_swift
+[ERROR:modelscope] Repo modelscope/rft_661q_7b_click_nourl_long_swift not exists on either https://www.modelscope.cn or https://www.modelscope.ai
+[ERROR:swift] Dataset rft_661q_7b_click_nourl_long_swift load failed: subset_name=default,split=train with error: HTTPSConnectionPool(host='www.modelscope.ai', port=443): Max retries exceeded with url: /api/v1/datasets/modelscope/rft_661q_7b_click_nourl_long_swift (Caused by ProxyError('Unable to connect to proxy', OSError('Tunnel connection failed: 403 Forbidden')))
+[ERROR:modelscope] Repo modelscope/rft_661q_7b_click_nourl_long_swift not exists on either https://www.modelscope.cn or https://www.modelscope.ai
+[ERROR:swift] Dataset rft_661q_7b_click_nourl_long_swift load failed: subset_name=default,split=train with error: HTTPSConnectionPool(host='www.modelscope.ai', port=443): Max retries exceeded with url: /api/v1/datasets/modelscope/rft_661q_7b_click_nourl_long_swift (Caused by ProxyError('Unable to connect to proxy', OSError('Tunnel connection failed: 403 Forbidden')))
+[ERROR:modelscope] Repo modelscope/rft_661q_7b_click_nourl_long_swift not exists on either https://www.modelscope.cn or https://www.modelscope.ai
+[rank0]: Traceback (most recent call last):
+[rank0]:   File "/data/miniforge/envs/ms-swift/lib/python3.10/site-packages/urllib3/connectionpool.py", line 773, in urlopen
+[rank0]:     self._prepare_proxy(conn)
+[rank0]:   File "/data/miniforge/envs/ms-swift/lib/python3.10/site-packages/urllib3/connectionpool.py", line 1042, in _prepare_proxy
+[rank0]:     conn.connect()
+[rank0]:   File "/data/miniforge/envs/ms-swift/lib/python3.10/site-packages/urllib3/connection.py", line 770, in connect
+[rank0]:     self._tunnel()
+[rank0]:   File "/data/miniforge/envs/ms-swift/lib/python3.10/site-packages/urllib3/connection.py", line 269, in _tunnel
+[rank0]:     raise OSError(
+[rank0]: OSError: Tunnel connection failed: 403 Forbidden
+
+[rank0]: The above exception was the direct cause of the following exception:
+
+[rank0]: urllib3.exceptions.ProxyError: ('Unable to connect to proxy', OSError('Tunnel connection failed: 403 Forbidden'))
+
+[rank0]: The above exception was the direct cause of the following exception:
+
+[rank0]: Traceback (most recent call last):
+[rank0]:   File "/data/miniforge/envs/ms-swift/lib/python3.10/site-packages/requests/adapters.py", line 667, in send
+[rank0]:     resp = conn.urlopen(
+[rank0]:   File "/data/miniforge/envs/ms-swift/lib/python3.10/site-packages/urllib3/connectionpool.py", line 871, in urlopen
+[rank0]:     return self.urlopen(
+[rank0]:   File "/data/miniforge/envs/ms-swift/lib/python3.10/site-packages/urllib3/connectionpool.py", line 871, in urlopen
+[rank0]:     return self.urlopen(
+[rank0]:   File "/data/miniforge/envs/ms-swift/lib/python3.10/site-packages/urllib3/connectionpool.py", line 841, in urlopen
+[rank0]:     retries = retries.increment(
+[rank0]:   File "/data/miniforge/envs/ms-swift/lib/python3.10/site-packages/urllib3/util/retry.py", line 519, in increment
+[rank0]:     raise MaxRetryError(_pool, url, reason) from reason  # type: ignore[arg-type]
+[rank0]: urllib3.exceptions.MaxRetryError: HTTPSConnectionPool(host='www.modelscope.ai', port=443): Max retries exceeded with url: /api/v1/datasets/modelscope/rft_661q_7b_click_nourl_long_swift (Caused by ProxyError('Unable to connect to proxy', OSError('Tunnel connection failed: 403 Forbidden')))
+
+[rank0]: During handling of the above exception, another exception occurred:
+
+[rank0]: Traceback (most recent call last):
+[rank0]:   File "/group/40143/hongzhuyi/ms-swift/swift/cli/sft.py", line 10, in <module>
+[rank0]:     sft_main()
+[rank0]:   File "/group/40143/hongzhuyi/ms-swift/swift/llm/train/sft.py", line 328, in sft_main
+[rank0]:     return SwiftSft(args).main()
+[rank0]:   File "/group/40143/hongzhuyi/ms-swift/swift/llm/base.py", line 49, in main
+[rank0]:     result = self.run()
+[rank0]:   File "/group/40143/hongzhuyi/ms-swift/swift/llm/train/sft.py", line 158, in run
+[rank0]:     train_dataset, val_dataset = self._prepare_dataset()
+[rank0]:   File "/group/40143/hongzhuyi/ms-swift/swift/llm/train/sft.py", line 117, in _prepare_dataset
+[rank0]:     train_dataset, val_dataset = self._get_dataset()
+[rank0]:   File "/group/40143/hongzhuyi/ms-swift/swift/llm/train/sft.py", line 71, in _get_dataset
+[rank0]:     train_dataset, val_dataset = load_dataset(
+[rank0]:   File "/group/40143/hongzhuyi/ms-swift/swift/llm/dataset/loader.py", line 533, in load_dataset
+[rank0]:     train_dataset = load_function(dataset_syntax, dataset_meta, **load_kwargs, use_hf=use_hf)
+[rank0]:   File "/group/40143/hongzhuyi/ms-swift/swift/llm/dataset/loader.py", line 408, in load
+[rank0]:     dataset = DatasetLoader._load_repo_dataset(
+[rank0]:   File "/group/40143/hongzhuyi/ms-swift/swift/llm/dataset/loader.py", line 266, in _load_repo_dataset
+[rank0]:     dataset = hub.load_dataset(
+[rank0]:   File "/group/40143/hongzhuyi/ms-swift/swift/hub/hub.py", line 296, in load_dataset
+[rank0]:     return MsDataset.load(
+[rank0]:   File "/data/miniforge/envs/ms-swift/lib/python3.10/site-packages/modelscope/msdatasets/ms_dataset.py", line 297, in load
+[rank0]:     endpoint = _api.get_endpoint_for_read(
+[rank0]:   File "/data/miniforge/envs/ms-swift/lib/python3.10/site-packages/modelscope/hub/api.py", line 390, in get_endpoint_for_read
+[rank0]:     self.repo_exists(
+[rank0]:   File "/data/miniforge/envs/ms-swift/lib/python3.10/site-packages/modelscope/hub/api.py", line 446, in repo_exists
+[rank0]:     r = self.session.get(path, cookies=cookies,
+[rank0]:   File "/data/miniforge/envs/ms-swift/lib/python3.10/site-packages/requests/sessions.py", line 602, in get
+[rank0]:     return self.request("GET", url, **kwargs)
+[rank0]:   File "/data/miniforge/envs/ms-swift/lib/python3.10/site-packages/requests/sessions.py", line 589, in request
+[rank0]:     resp = self.send(prep, **send_kwargs)
+[rank0]:   File "/data/miniforge/envs/ms-swift/lib/python3.10/site-packages/requests/sessions.py", line 703, in send
+[rank0]:     r = adapter.send(request, **kwargs)
+[rank0]:   File "/data/miniforge/envs/ms-swift/lib/python3.10/site-packages/requests/adapters.py", line 694, in send
+[rank0]:     raise ProxyError(e, request=request)
+[rank0]: requests.exceptions.ProxyError: HTTPSConnectionPool(host='www.modelscope.ai', port=443): Max retries exceeded with url: /api/v1/datasets/modelscope/rft_661q_7b_click_nourl_long_swift (Caused by ProxyError('Unable to connect to proxy', OSError('Tunnel connection failed: 403 Forbidden')))
+[rank0]:[W819 16:23:08.718020323 ProcessGroupNCCL.cpp:1538] Warning: WARNING: destroy_process_group() was not called before program exit, which can leak resources. For more info, please see https://pytorch.org/docs/stable/distributed.html#shutdown (function operator())

qwen2.5-7b-1700q-661q-1e_6-old-click-1ep/args.json

@@ -0,0 +1,381 @@
+{
+  "output_dir": "/group/40143/hongzhuyi/ms-swift/output/v0-20250820-110326",
+  "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": 1,
+  "per_device_eval_batch_size": 1,
+  "per_gpu_train_batch_size": null,
+  "per_gpu_eval_batch_size": null,
+  "gradient_accumulation_steps": 2,
+  "eval_accumulation_steps": null,
+  "eval_delay": 0,
+  "torch_empty_cache_steps": null,
+  "learning_rate": 1e-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": 1.0,
+  "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/v0-20250820-110326/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": 20.0,
+  "dataloader_num_workers": 48,
+  "dataloader_prefetch_factor": null,
+  "past_index": -1,
+  "run_name": "/group/40143/hongzhuyi/ms-swift/output/v0-20250820-110326",
+  "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_fused",
+  "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,
+  "hub_revision": null,
+  "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,
+  "liger_kernel_config": null,
+  "eval_use_gather_object": false,
+  "average_tokens_across_devices": true,
+  "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": [
+    "rft_661q_7b_click_nourl_long_swift.jsonl",
+    "corr_data_1700q_old_click_nourl_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='/usr/local/app/.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 0x7fdca4890e50>, 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": "/usr/local/app/.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/v0-20250820-110326', 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=1, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=2, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=1e-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=1.0, 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/v0-20250820-110326/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=20.0, dataloader_num_workers=48, dataloader_prefetch_factor=10, past_index=-1, run_name='/group/40143/hongzhuyi/ms-swift/output/v0-20250820-110326', 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_FUSED: 'adamw_torch_fused'>, 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, hub_revision=None, 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, liger_kernel_config=None, 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-1700q-661q-1e_6-old-click-1ep/checkpoint-497/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-1700q-661q-1e_6-old-click-1ep/checkpoint-497/args.json

@@ -0,0 +1,381 @@
+{
+  "output_dir": "/group/40143/hongzhuyi/ms-swift/output/v0-20250820-110326",
+  "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": 1,
+  "per_device_eval_batch_size": 1,
+  "per_gpu_train_batch_size": null,
+  "per_gpu_eval_batch_size": null,
+  "gradient_accumulation_steps": 2,
+  "eval_accumulation_steps": null,
+  "eval_delay": 0,
+  "torch_empty_cache_steps": null,
+  "learning_rate": 1e-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": 1.0,
+  "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/v0-20250820-110326/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": 20.0,
+  "dataloader_num_workers": 48,
+  "dataloader_prefetch_factor": null,
+  "past_index": -1,
+  "run_name": "/group/40143/hongzhuyi/ms-swift/output/v0-20250820-110326",
+  "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_fused",
+  "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,
+  "hub_revision": null,
+  "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,
+  "liger_kernel_config": null,
+  "eval_use_gather_object": false,
+  "average_tokens_across_devices": true,
+  "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": [
+    "rft_661q_7b_click_nourl_long_swift.jsonl",
+    "corr_data_1700q_old_click_nourl_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='/usr/local/app/.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 0x7fdca4890e50>, 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": "/usr/local/app/.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/v0-20250820-110326', 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=1, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=2, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=1e-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=1.0, 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/v0-20250820-110326/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=20.0, dataloader_num_workers=48, dataloader_prefetch_factor=10, past_index=-1, run_name='/group/40143/hongzhuyi/ms-swift/output/v0-20250820-110326', 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_FUSED: 'adamw_torch_fused'>, 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, hub_revision=None, 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, liger_kernel_config=None, 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-1700q-661q-1e_6-old-click-1ep/checkpoint-497/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-1700q-661q-1e_6-old-click-1ep/checkpoint-497/config.json

@@ -0,0 +1,59 @@
+{
+  "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,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "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": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.55.2",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

qwen2.5-7b-1700q-661q-1e_6-old-click-1ep/checkpoint-497/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": "4.55.2"
+}

qwen2.5-7b-1700q-661q-1e_6-old-click-1ep/checkpoint-497/latest

@@ -0,0 +1 @@
+global_step497

qwen2.5-7b-1700q-661q-1e_6-old-click-1ep/checkpoint-497/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d94ea29155bad0f16c6555e33ff7ec89599aa64cb81225f2d375b7657a26abd
+size 4877660776

qwen2.5-7b-1700q-661q-1e_6-old-click-1ep/checkpoint-497/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b091d1db564d2bf2bb50e4d5a2c2b3823a43cf7c6cf0e56a3c0154c1bc726548
+size 4932751008

qwen2.5-7b-1700q-661q-1e_6-old-click-1ep/checkpoint-497/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e323731955b27bb82c934ec290c7e35f071280c4c2ada03383cef5aa5689474
+size 4330865200

qwen2.5-7b-1700q-661q-1e_6-old-click-1ep/checkpoint-497/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43dd8ea184c6f100ab897b7358e9cde4f23fe566a9062b11c8a352e792a8647b
+size 1089994880

qwen2.5-7b-1700q-661q-1e_6-old-click-1ep/checkpoint-497/model.safetensors.index.json

@@ -0,0 +1,347 @@
+{
+  "metadata": {
+    "total_parameters": 333312,
+    "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-1700q-661q-1e_6-old-click-1ep/checkpoint-497/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2806540a294e51675e676a0c761bf31805a20065fdaaab5b6bf7588ad85d6546
+size 1465

qwen2.5-7b-1700q-661q-1e_6-old-click-1ep/checkpoint-497/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-1700q-661q-1e_6-old-click-1ep/checkpoint-497/tokenizer.json

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

qwen2.5-7b-1700q-661q-1e_6-old-click-1ep/checkpoint-497/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-1700q-661q-1e_6-old-click-1ep/checkpoint-497/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e900ad112de762a3d6522db75a2ffba54e8c3b2f8a55bd565ad47c0d0c63f5c2
+size 9041

qwen2.5-7b-1700q-661q-1e_6-old-click-1ep/checkpoint-497/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-1700q-661q-1e_6-old-click-1ep/runs/events.out.tfevents.1755659098.TENCENT64.site.2314195.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5a14fcd7fcad945f5752fc8ed60bcf7e97d7f4777da582bbf9604f3da17a552
+size 139894

qwen2.5-7b-1700q-661q-1e_6-old-click-1ep/val_dataset.jsonl

@@ -0,0 +1,7 @@
+{"messages": [{"role": "system", "content": "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.\n\nHere's the information you'll have:\nThe user's objective: This is the task you're trying to complete.\nThe current web page's accessibility tree: This is a simplified representation of the webpage, providing key information.\nThe open tabs: These are the tabs you have open.\nThe previous actions: There are the actions you just performed. It may be helpful to track your progress.\n\nThe actions you can perform fall into several categories:\n\nPage Operation Actions:\n`click [id] [content]`: This action clicks on an element with a specific id on the webpage.\n`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.\n`hover [id] [content]`: Hover over an element with id.\n`press [key_comb]`:  Simulates the pressing of a key combination on the keyboard (e.g., Ctrl+v).\n`scroll [down|up]`: Scroll the page up or down.\n\nTab Management Actions:\n`new_tab`: Open a new, empty browser tab.\n`tab_focus [tab_index]`: Switch the browser's focus to a specific tab using its index.\n`close_tab`: Close the currently active tab.\n\nURL Navigation Actions:\n`goto [url]`: Navigate to a specific URL.\n`go_back`: Navigate to the previously viewed page.\n`go_forward`: Navigate to the next page (if a previous 'go_back' action was performed).\n\nCompletion Action:\n`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.\n\nTo be successful, it is very important to follow the following rules:\n1. You should only issue an action that is valid given the current observation.\n2. You should only issue one action at a time.\n3. You should follow the examples to reason step by step and then issue the next action.\n4. You should refer to historical actions when issue an action and try not to make repetitive actions\n5. All reasoning must be inside `<think></think>` tags, and there must be no output before `<think></think>`.\n6. After `<think></think>`, only the action should be generated in the correct format, enclosed in code fences. For example:\n   <think>This button looks relevant to my goal. Clicking it should take me to the next step.</think>\n   ```click [id] [content]```\n7. Issue the stop action when you think you have achieved the objective. Don’t generate anything after stop.\n8. Always format actions correctly: \n```command [parameters]```\nFor example, if searching for \"\"death row inmates in the US\"\" in a search field with ID `21`, correctly format it as:\n```type [21] [death row inmates in the US] [1]```\nAvoid incorrect formats that omit brackets around parameters or numeric values.\n"}, {"role": "user", "content": "\nObjective: where are hormones secreted by the posterior pituitary gland made\nObservation: [511] RootWebArea 'Search: posterior pituitary gland hormones' focused: True\n\t[679] textbox \"Search 'Wikipedia'\" required: False\n\t[681] link 'Go to welcome page'\n\t\t[999] button '🏠'\n\t[682] link \"Go to the main page of 'Wikipedia'\"\n\t\t[1001] button 'Wikipedia'\n\t[683] link 'Go to a randomly selected page'\n\t\t[1003] button '🎲'\n\t[524] StaticText 'Results 1-25 of 400 for \"posterior pituitary gland hormones\"'\n\t[570] link 'Pituitary gland'\n\t[685] StaticText '...gland that regulates several physiological processes including stress, growth, reproduction, and lactation. The intermediate lobe synthesizes and secretes melanocyte-stimulating hormone. The posterior pituitary (or neurohypophysis) is a lobe of the gland that is functionally connected to the hypothalamus by the median eminence via a small tube called the pituitary stalk (also called the infundibular stalk or the infundibulum). Pituitary gland Located at the base of the brain, the pituitary gland......'\n\t[701] StaticText 'from Wikipedia'\n\t[702] StaticText '3,230 words'\n\t[574] link 'Posterior pituitary'\n\t[704] StaticText '...nucleus), posterior pituitary, and these axonal projections.[2] Posterior pituitary Pituitary gland. Posterior pituitary is in blue and Anterior pituitary is in orange. Pars nervosa and infundibular stalk are not labeled, but pars nervosa is at bottom and infundibular stalk is at top. Median sagittal through the hypophysis of an adult monkey. (Posterior lobe labeled at bottom right.) Details Precursor Neural tube (downward-growth of the diencephalon)[1] Artery inferior hypophyseal artery Vein......'\n\t[720] StaticText 'from Wikipedia'\n\t[721] StaticText '1,056 words'\n\t[578] link 'Anterior pituitary'\n\t[723] StaticText '...the posterior lobe (posterior pituitary, or the neurohypophysis) makes up the pituitary gland (hypophysis). The anterior pituitary regulates several physiological processes, including stress, growth, reproduction, and lactation. Proper functioning of the anterior pituitary and of the organs it regulates can often be ascertained via blood tests that measure hormone levels. Anterior pituitary gland Median sagittal through the hypophysis of an adult monkey. Semidiagrammatic. Details Precursor oral......'\n\t[736] StaticText 'from Wikipedia'\n\t[737] StaticText '2,661 words'\n\t[582] link 'Neuroendocrinology'\n\t[739] StaticText '...the posterior and anterior pituitary glands. The hypothalamus produces the hormones oxytocin and vasopressin in its endocrine cells (left). These are released at nerve endings in the posterior pituitary gland and then secreted into the systemic circulation. The hypothalamus releases tropic hormones into the hypophyseal portal system to the anterior pituitary (right). The anterior pituitary then secretes trophic hormones into the circulation which elicit different responses from various target......'\n\t[749] StaticText 'from Wikipedia'\n\t[750] StaticText '2,752 words'\n\t[586] link 'Pituitary disease'\n\t[760] StaticText '326 words'\n\t[590] link 'Hypopituitarism'\n\t[762] StaticText '...gland at the base of the brain.[1][2] If there is decreased secretion of one specific pituitary hormone, the condition is known as selective hypopituitarism.[3] If there is decreased secretion of most or all pituitary hormones, the term panhypopituitarism (pan meaning \"all\") is used.[4] Not to be confused with Hyperpituitarism. Hypopituitarism The pituitary gland'\nHISTORY_ACTION: type [21] [posterior pituitary gland hormones] [1]\n"}, {"role": "assistant", "content": "<think>There is a snippet in the StaticText with id 739 that states: \"The hypothalamus produces the hormones oxytocin and vasopressin in its endocrine cells (left). These are released at nerve endings in the posterior pituitary gland and then secreted into the systemic circulation.\" This directly answers the question that the hormones secreted by the posterior pituitary gland are made in the hypothalamus.</think>\n```stop [The hormones secreted by the posterior pituitary gland are made in the hypothalamus.]```"}]}
+{"messages": [{"role": "system", "content": "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.\n\nHere's the information you'll have:\nThe user's objective: This is the task you're trying to complete.\nThe current web page's accessibility tree: This is a simplified representation of the webpage, providing key information.\nThe open tabs: These are the tabs you have open.\nThe previous actions: There are the actions you just performed. It may be helpful to track your progress.\n\nThe actions you can perform fall into several categories:\n\nPage Operation Actions:\n`click [id] [content]`: This action clicks on an element with a specific id on the webpage.\n`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.\n`hover [id] [content]`: Hover over an element with id.\n`press [key_comb]`:  Simulates the pressing of a key combination on the keyboard (e.g., Ctrl+v).\n`scroll [down|up]`: Scroll the page up or down.\n\nTab Management Actions:\n`new_tab`: Open a new, empty browser tab.\n`tab_focus [tab_index]`: Switch the browser's focus to a specific tab using its index.\n`close_tab`: Close the currently active tab.\n\nURL Navigation Actions:\n`goto [url]`: Navigate to a specific URL.\n`go_back`: Navigate to the previously viewed page.\n`go_forward`: Navigate to the next page (if a previous 'go_back' action was performed).\n\nCompletion Action:\n`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.\n\nTo be successful, it is very important to follow the following rules:\n1. You should only issue an action that is valid given the current observation.\n2. You should only issue one action at a time.\n3. You should follow the examples to reason step by step and then issue the next action.\n4. You should refer to historical actions when issue an action and try not to make repetitive actions\n5. All reasoning must be inside `<think></think>` tags, and there must be no output before `<think></think>`.\n6. After `<think></think>`, only the action should be generated in the correct format, enclosed in code fences. For example:\n   <think>This button looks relevant to my goal. Clicking it should take me to the next step.</think>\n   ```click [id] [content]```\n7. Issue the stop action when you think you have achieved the objective. Don’t generate anything after stop.\n8. Always format actions correctly: \n```command [parameters]```\nFor example, if searching for \"\"death row inmates in the US\"\" in a search field with ID `21`, correctly format it as:\n```type [21] [death row inmates in the US] [1]```\nAvoid incorrect formats that omit brackets around parameters or numeric values.\n"}, {"role": "user", "content": "\nObjective: who represents washington's 1st district house of representatives\nObservation: [294] RootWebArea 'User:The other Kiwix guy/Landing' focused: True url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/User:The_other_Kiwix_guy/Landing\n\t[329] textbox \"Search 'Wikipedia'\" required: False\n\t[331] checkbox '' checked: false\n\t[338] link 'Go to welcome page' url: https://tigerai.ca/\n\t\t[339] button '🏠'\n\t[340] link \"Go to the main page of 'Wikipedia'\" url: https://tigerai.ca/wikipedia_en_all_maxi_2022-05/\n\t\t[341] button 'Wikipedia'\n\t[342] link 'Go to a randomly selected page' url: https://tigerai.ca/random?content=wikipedia_en_all_maxi_2022-05\n\t\t[343] button '🎲'\n\t[11] StaticText 'Welcome to '\n\t[354] link 'Wikipedia' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/Wikipedia\n\t[13] StaticText 'The free encyclopedia.'\n\t[14] StaticText '6,489,052'\n\t[15] StaticText ' articles in '\n\t[360] link 'English' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/English_Wikipedia\n\t[362] heading 'Arts'\n\t[364] link 'Architecture' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/Architecture\n\t[365] link 'Books' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/Books\n\t[366] link 'Cinematography' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/Cinematography\n\t[367] link 'Dance' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/Dance\n\t[368] link 'Design' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/Design\n\t[369] link 'Fashion' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/Fashion\n\t[370] link 'Films' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/Films\n\t[371] link 'Gastronomy' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/Gastronomy\n\t[372] link 'Literature' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/Literature\n\t[373] link 'Magic (illusion)' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/Magic_(illusion)\n\t[374] link 'Music' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/Music\n\t[375] link 'Painting' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/Painting\n\t[376] link 'Photography' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/Photography\n\t[377] link 'Poetry' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/Poetry\n\t[378] link 'Sculpture' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/Sculpture\n\t[379] link 'Theatre' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/Theatre\n\t[381] heading 'Geography'\n\t[383] link 'Africa' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/Africa\n\t[384] link 'Antarctica' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/Antarctica\n\t[385] link 'Arctic' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/Arctic\n\t[386] link 'Asia' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/Asia\n\t[387] link 'Caribbean' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/Caribbean\n\t[388] link 'Central America' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/Central_America\n\t[389] link 'Europe' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/Europe\n\t[390] link 'Latin America' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/Latin_America\n\t[391] link 'Mediterranean' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/Mediterranean\n\t[392] link 'Middle East' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/Middle_East\n\t[393] link 'North America' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/North_America\n\t[394] link 'Oceania' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/Oceania\n\t[395] link 'South America' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/South_America\n\t[396] link 'Cartography' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/Cartography\n\t[398] heading 'History'\n\t[400] link 'Ancient Egypt' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/Ancient_Egypt\n\t[401] link 'Ancient Greece' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/Ancient_Greece\n\t[402] link 'Ancient Near East' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/Ancient_Near_East\n\t[403] link 'Ancient Rome' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/Ancient_Rome\n\t[404] link 'Archaeology' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/Archaeology\n\t[405] link 'British Empire' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/British_Empire\n\t[406] link 'Byzantine Empire' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/Byzantine_Empire\n\t[407] link 'Colonialism' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/Colonialism\n\t[408] link 'Crusades' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/Crusades\n\t[409] link 'Heraldry' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/Heraldry\n\t[410] link 'History of science' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/History_of_science\n\t[411] link 'Imperial China' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/History_of_China#Imperial_China\n\t[412] link 'Indian independence movement' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/Indian_independence_movement\n\t[413] link 'Japan' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/History_of_Japan\n\t[414] link 'Middle Ages' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/Middle_Ages\n\t[415] link 'Mughal Empire' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/Mughal_Empire\n\t[416] link 'Ottoman Empire' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/Ottoman_Empire\n\t[417] link 'Russian Empire' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/Russian_Empire\n\t[418] link 'Sasanian Empire' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/Sasanian_Empire\n\t[419] link 'Seljuk Empire' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/Seljuk_Empire\n\t[420] link 'Soviet Union' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/Soviet_Union\n\t[421] link 'War' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/War\n\t[423] heading 'Sciences'\nHISTORY_ACTION: \n\n"}, {"role": "assistant", "content": "<think>The search box with id 329 labeled \"Search 'Wikipedia'\" is available and likely the most direct way to find information about who represents Washington's 1st district in the House of Representatives. I should use it to search \"Washington DC 1st district representative\".</think>\n```type [329] [Washington DC 1st district representative] [1]```"}]}
+{"messages": [{"role": "system", "content": "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.\n\nHere's the information you'll have:\nThe user's objective: This is the task you're trying to complete.\nThe current web page's accessibility tree: This is a simplified representation of the webpage, providing key information.\nThe open tabs: These are the tabs you have open.\nThe previous actions: There are the actions you just performed. It may be helpful to track your progress.\n\nThe actions you can perform fall into several categories:\n\nPage Operation Actions:\n`click [id] [content]`: This action clicks on an element with a specific id on the webpage.\n`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.\n`hover [id] [content]`: Hover over an element with id.\n`press [key_comb]`:  Simulates the pressing of a key combination on the keyboard (e.g., Ctrl+v).\n`scroll [down|up]`: Scroll the page up or down.\n\nTab Management Actions:\n`new_tab`: Open a new, empty browser tab.\n`tab_focus [tab_index]`: Switch the browser's focus to a specific tab using its index.\n`close_tab`: Close the currently active tab.\n\nURL Navigation Actions:\n`goto [url]`: Navigate to a specific URL.\n`go_back`: Navigate to the previously viewed page.\n`go_forward`: Navigate to the next page (if a previous 'go_back' action was performed).\n\nCompletion Action:\n`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.\n\nTo be successful, it is very important to follow the following rules:\n1. You should only issue an action that is valid given the current observation.\n2. You should only issue one action at a time.\n3. You should follow the examples to reason step by step and then issue the next action.\n4. You should refer to historical actions when issue an action and try not to make repetitive actions\n5. All reasoning must be inside `<think></think>` tags, and there must be no output before `<think></think>`.\n6. After `<think></think>`, only the action should be generated in the correct format, enclosed in code fences. For example:\n   <think>This button looks relevant to my goal. Clicking it should take me to the next step.</think>\n   ```click [id] [content]```\n7. Issue the stop action when you think you have achieved the objective. Don’t generate anything after stop.\n8. Always format actions correctly: \n```command [parameters]```\nFor example, if searching for \"\"death row inmates in the US\"\" in a search field with ID `21`, correctly format it as:\n```type [21] [death row inmates in the US] [1]```\nAvoid incorrect formats that omit brackets around parameters or numeric values.\n"}, {"role": "user", "content": "\nObjective: who is the winner of 2015 royal rumble\nObservation: [511] RootWebArea 'Search: 2015 Royal Rumble winner' focused: True\n\t[679] textbox \"Search 'Wikipedia'\" required: False\n\t[681] link 'Go to welcome page'\n\t\t[1192] button '🏠'\n\t[682] link \"Go to the main page of 'Wikipedia'\"\n\t\t[1194] button 'Wikipedia'\n\t[683] link 'Go to a randomly selected page'\n\t\t[1196] button '🎲'\n\t[524] StaticText 'Results 1-25 of 2,000 for \"2015 Royal Rumble winner\"'\n\t[570] link 'Royal Rumble match'\n\t[700] StaticText 'from Wikipedia'\n\t[701] StaticText '7,710 words'\n\t[574] link 'Royal Rumble (2015)'\n\t[729] StaticText '5,547 words'\n\t[578] link 'Royal Rumble (2013)'\n\t[750] StaticText 'from Wikipedia'\n\t[751] StaticText '3,017 words'\n\t[582] link 'Royal Rumble (2014)'\n\t[773] StaticText '7,096 words'\n\t[586] link 'Royal Rumble (2004)'\n\t[791] StaticText 'from Wikipedia'\n\t[792] StaticText '6,658 words'\n\t[590] link 'Royal Rumble (2022)'\nHISTORY_ACTION: type [21] [2015 Royal Rumble winner] [1]\n"}, {"role": "assistant", "content": "<think>The link labeled 'Royal Rumble (2015)' is likely to contain information about the 2015 Royal Rumble winner. I should click this link to find the answer.</think>\n```click [574] [link 'Royal Rumble (2015)']```"}]}
+{"messages": [{"role": "system", "content": "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.\n\nHere's the information you'll have:\nThe user's objective: This is the task you're trying to complete.\nThe current web page's accessibility tree: This is a simplified representation of the webpage, providing key information.\nThe open tabs: These are the tabs you have open.\nThe previous actions: There are the actions you just performed. It may be helpful to track your progress.\n\nThe actions you can perform fall into several categories:\n\nPage Operation Actions:\n`click [id] [content]`: This action clicks on an element with a specific id on the webpage.\n`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.\n`hover [id] [content]`: Hover over an element with id.\n`press [key_comb]`:  Simulates the pressing of a key combination on the keyboard (e.g., Ctrl+v).\n`scroll [down|up]`: Scroll the page up or down.\n\nTab Management Actions:\n`new_tab`: Open a new, empty browser tab.\n`tab_focus [tab_index]`: Switch the browser's focus to a specific tab using its index.\n`close_tab`: Close the currently active tab.\n\nURL Navigation Actions:\n`goto [url]`: Navigate to a specific URL.\n`go_back`: Navigate to the previously viewed page.\n`go_forward`: Navigate to the next page (if a previous 'go_back' action was performed).\n\nCompletion Action:\n`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.\n\nTo be successful, it is very important to follow the following rules:\n1. You should only issue an action that is valid given the current observation.\n2. You should only issue one action at a time.\n3. You should follow the examples to reason step by step and then issue the next action.\n4. You should refer to historical actions when issue an action and try not to make repetitive actions\n5. All reasoning must be inside `<think></think>` tags, and there must be no output before `<think></think>`.\n6. After `<think></think>`, only the action should be generated in the correct format, enclosed in code fences. For example:\n   <think>This button looks relevant to my goal. Clicking it should take me to the next step.</think>\n   ```click [id] [content]```\n7. Issue the stop action when you think you have achieved the objective. Don’t generate anything after stop.\n8. Always format actions correctly: \n```command [parameters]```\nFor example, if searching for \"\"death row inmates in the US\"\" in a search field with ID `21`, correctly format it as:\n```type [21] [death row inmates in the US] [1]```\nAvoid incorrect formats that omit brackets around parameters or numeric values.\n"}, {"role": "user", "content": "\nObjective: who did stephen jackson win a ring with\nObservation: [1] RootWebArea 'User:The other Kiwix guy/Landing' focused: True\n\t[21] textbox \"Search 'Wikipedia'\" required: False\n\t[23] link 'Go to welcome page'\n\t\t[30] button '🏠'\n\t[24] link \"Go to the main page of 'Wikipedia'\"\n\t\t[32] button 'Wikipedia'\n\t[25] link 'Go to a randomly selected page'\n\t\t[34] button '🎲'\n\t[82] StaticText 'Welcome to '\n\t[83] link 'Wikipedia'\n\t[84] StaticText 'The free encyclopedia.'\n\t[371] StaticText '6,489,052'\n\t[86] StaticText ' articles in '\n\t[369] link 'English'\n\t[53] heading 'Arts'\n\t[89] link 'Architecture'\n\t[91] link 'Books'\n\t[93] link 'Cinematography'\n\t[95] link 'Dance'\n\t[97] link 'Design'\n\t[99] link 'Fashion'\n\t[101] link 'Films'\n\t[103] link 'Gastronomy'\n\t[105] link 'Literature'\n\t[107] link 'Magic (illusion)'\n\t[109] link 'Music'\n\t[111] link 'Painting'\n\t[113] link 'Photography'\n\t[115] link 'Poetry'\n\t[117] link 'Sculpture'\n\t[119] link 'Theatre'\n\t[55] heading 'Geography'\n\t[122] link 'Africa'\n\t[124] link 'Antarctica'\n\t[126] link 'Arctic'\n\t[128] link 'Asia'\n\t[130] link 'Caribbean'\n\t[132] link 'Central America'\n\t[134] link 'Europe'\n\t[136] link 'Latin America'\n\t[138] link 'Mediterranean'\n\t[140] link 'Middle East'\n\t[142] link 'North America'\n\t[144] link 'Oceania'\n\t[146] link 'South America'\n\t[148] link 'Cartography'\n\t[57] heading 'History'\n\t[150] link 'Ancient Egypt'\n\t[152] link 'Ancient Greece'\n\t[154] link 'Ancient Near East'\n\t[156] link 'Ancient Rome'\n\t[158] link 'Archaeology'\n\t[160] link 'British Empire'\n\t[162] link 'Byzantine Empire'\n\t[164] link 'Colonialism'\n\t[166] link 'Crusades'\n\t[168] link 'Heraldry'\n\t[170] link 'History of science'\n\t[172] link 'Imperial China'\n\t[174] link 'Indian independence movement'\n\t[176] link 'Japan'\n\t[178] link 'Middle Ages'\n\t[180] link 'Mughal Empire'\n\t[182] link 'Ottoman Empire'\n\t[184] link 'Russian Empire'\n\t[186] link 'Sasanian Empire'\n\t[188] link 'Seljuk Empire'\n\t[190] link 'Soviet Union'\n\t[192] link 'War'\n\t[59] heading 'Sciences'\nHISTORY_ACTION: \n\n"}, {"role": "assistant", "content": "<think>To find out who Stephen Jackson won a ring with, I should use the search box to look up \"Stephen Jackson\" on Wikipedia. The search box has id 21.</think>\n```type [21] [Stephen Jackson] [1]```"}]}
+{"messages": [{"role": "system", "content": "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.\n\nHere's the information you'll have:\nThe user's objective: This is the task you're trying to complete.\nThe current web page's accessibility tree: This is a simplified representation of the webpage, providing key information.\nThe open tabs: These are the tabs you have open.\nThe previous actions: There are the actions you just performed. It may be helpful to track your progress.\n\nThe actions you can perform fall into several categories:\n\nPage Operation Actions:\n`click [id] [content]`: This action clicks on an element with a specific id on the webpage.\n`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.\n`hover [id] [content]`: Hover over an element with id.\n`press [key_comb]`:  Simulates the pressing of a key combination on the keyboard (e.g., Ctrl+v).\n`scroll [down|up]`: Scroll the page up or down.\n\nTab Management Actions:\n`new_tab`: Open a new, empty browser tab.\n`tab_focus [tab_index]`: Switch the browser's focus to a specific tab using its index.\n`close_tab`: Close the currently active tab.\n\nURL Navigation Actions:\n`goto [url]`: Navigate to a specific URL.\n`go_back`: Navigate to the previously viewed page.\n`go_forward`: Navigate to the next page (if a previous 'go_back' action was performed).\n\nCompletion Action:\n`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.\n\nTo be successful, it is very important to follow the following rules:\n1. You should only issue an action that is valid given the current observation.\n2. You should only issue one action at a time.\n3. You should follow the examples to reason step by step and then issue the next action.\n4. You should refer to historical actions when issue an action and try not to make repetitive actions\n5. All reasoning must be inside `<think></think>` tags, and there must be no output before `<think></think>`.\n6. After `<think></think>`, only the action should be generated in the correct format, enclosed in code fences. For example:\n   <think>This button looks relevant to my goal. Clicking it should take me to the next step.</think>\n   ```click [id] [content]```\n7. Issue the stop action when you think you have achieved the objective. Don’t generate anything after stop.\n8. Always format actions correctly: \n```command [parameters]```\nFor example, if searching for \"\"death row inmates in the US\"\" in a search field with ID `21`, correctly format it as:\n```type [21] [death row inmates in the US] [1]```\nAvoid incorrect formats that omit brackets around parameters or numeric values.\n"}, {"role": "user", "content": "\nObjective: who is the author of around the world in 80 days\nObservation: [2648] RootWebArea 'Around the World in 80 Days (miniseries)' focused: True url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/Around_the_World_in_80_Days_(miniseries)\n\t[3230] textbox \"Search 'Wikipedia'\" required: False\n\t[3232] checkbox '' checked: false\n\t[3239] link 'Go to welcome page' url: https://tigerai.ca/\n\t\t[3240] button '🏠'\n\t[3241] link \"Go to the main page of 'Wikipedia'\" url: https://tigerai.ca/wikipedia_en_all_maxi_2022-05/\n\t\t[3242] button 'Wikipedia'\n\t[3243] link 'Go to a randomly selected page' url: https://tigerai.ca/random?content=wikipedia_en_all_maxi_2022-05\n\t\t[3244] button '🎲'\n\t[3251] heading 'Around the World in 80 Days (miniseries)' hasPopup: menu\n\t[2715] StaticText 'Around the World in 80 Days is a three-part television '\n\t[3258] link 'miniseries' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/Miniseries\n\t[2718] StaticText ' originally broadcast on '\n\t[3259] link 'NBC' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/NBC\n\t[2720] StaticText ' from April 16 to 18, 1989.'\n\t[3261] link '[]' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/Around_the_World_in_80_Days_(miniseries)#cite_note-1\n\t[2721] StaticText ' The production garnered three nominations for '\n\t[3263] link 'Emmy' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/Emmy\n\t[2723] StaticText ' awards that year.'\n\t[3265] link '[]' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/Around_the_World_in_80_Days_(miniseries)#cite_note-2\n\t[2724] StaticText ' The teleplay by '\n\t[3267] link 'John Gay' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/John_Gay_(screenwriter)\n\t[2726] StaticText ' is based on the 1873 '\n\t[3268] link 'Jules Verne' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/Jules_Verne\n\t[3269] link 'novel of the same title' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/Around_the_World_in_Eighty_Days\n\t[3271] link '[]' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/Around_the_World_in_80_Days_(miniseries)#cite_note-bfi-3\n\t[3274] note ''\n\t\t[2731] StaticText 'This article is about the 1989 TV miniseries. For the Michael Palin travel series, see '\n\t\t[3275] link 'Around the World in 80 Days with Michael Palin' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/Around_the_World_in_80_Days_with_Michael_Palin\n\t\t[2733] StaticText '. For the 2021 miniseries, see '\n\t\t[3276] link 'Around the World in 80 Days (2021 TV series)' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/Around_the_World_in_80_Days_(2021_TV_series)\n\t[3279] table ''\n\t\t[3281] row ''\n\t\t\t[3282] columnheader 'Around the World in 80 Days' required: False\n\t\t[3284] row ''\n\t\t\t[3285] cell 'DVD sleeve artwork'\n\t\t\t\t[3194] image '' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/I/Around_the_World_in_80_Days_DVD_Sleeve.jpg.webp\n\t\t[3288] row ''\n\t\t\t[3289] rowheader 'Based on' required: False\n\t\t\t[3290] cell 'Around the World in 80 Days by Jules Verne'\n\t[3363] group ''\n\t\t[3368] DisclosureTriangle 'Plot' expanded: True\n\t\t\t[3369] heading 'Plot'\n\t\t[2800] StaticText 'The plot centres around '\n\t\t[3371] link 'Phileas Fogg' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/Phileas_Fogg\n\t\t[3372] link 'Pierce Brosnan' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/Pierce_Brosnan\n\t\t[2804] StaticText ') making a £30,000 wager with three members of the '\n\t\t[3373] link 'Reform Club' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/Reform_Club\n\t\t[2806] StaticText ' that he can '\n\t\t[3374] link 'circumnavigate' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/Circumnavigation\n\t\t[2808] StaticText ' the world in 80 days. He takes with him his newly employed '\n\t\t[3375] link 'French' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/French_people\n\t\t[3376] link 'valet' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/Valet\n\t\t[3377] link 'Passepartout' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/Jean_Passepartout\n\t\t[3378] link 'Eric Idle' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/Eric_Idle\n\t\t[2815] StaticText '), and is pursued by Detective Wilbur Fix ('\n\t\t[3379] link 'Peter Ustinov' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/Peter_Ustinov\n\t\t[2817] StaticText ') who mistakenly thinks Fogg robbed the Bank of England and is using the wager as a cover to escape capture.'\n\t[3380] group ''\n\t\t[3385] DisclosureTriangle 'Cast' expanded: True\n\t\t\t[3386] heading 'Cast'\n\t\t[2820] ListMarker '■ '\n\t\t[3192] link 'Pierce Brosnan' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/Pierce_Brosnan\n\t\t[3391] link 'Phileas Fogg' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/Phileas_Fogg\n\t\t[2824] ListMarker '■ '\n\t\t[3393] link 'Eric Idle' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/Eric_Idle\n\t\t[3394] link 'Jean Passepartout' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/Jean_Passepartout\n\t\t[2828] ListMarker '■ '\n\t\t[3396] link 'Julia Nickson' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/Julia_Nickson\n\t\t[2830] StaticText ' as Princess '\n\t\t[3397] link 'Aouda' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/Aouda\n\t\t[2832] ListMarker '■ '\n\t\t[3399] link 'Peter Ustinov' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/Peter_Ustinov\n\t\t[2834] StaticText ' as Detective Wilbur Fix'\n\t\t[2835] ListMarker '■ '\n\t\t[3401] link 'Jack Klugman' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/Jack_Klugman\n\t\t[2837] StaticText ' as Capt. Bunsby'\n\t\t[2838] ListMarker '■ '\n\t\t[3403] link 'Roddy McDowall' url: https://tigerai.ca/wiki/wikipedia_en_all_maxi_2022-05/A/Roddy_McDowall\n\t\t[2840] StaticText ' as McBaines'\nHISTORY_ACTION: type [330] [Around the World in 80 Days] [1]\nclick [1993] [link 'Around the World in 80 Days (miniseries)']\n"}, {"role": "assistant", "content": "<think>The page is about the 1989 TV miniseries. In the observation, the text states: \"The teleplay by John Gay is based on the 1873 novel of the same title.\" Based on this, John Gay is listed as the writer, but Jules Verne is recognized as the original author of the novel. To confirm Jules Verne, I should scroll down to see if there is more about the adaptation origins, which might mention Jules Verne directly or indicate his role as the original novelist.</think>\n```scroll [down]```"}]}
+{"messages": [{"role": "system", "content": "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.\n\nHere's the information you'll have:\nThe user's objective: This is the task you're trying to complete.\nThe current web page's accessibility tree: This is a simplified representation of the webpage, providing key information.\nThe open tabs: These are the tabs you have open.\nThe previous actions: There are the actions you just performed. It may be helpful to track your progress.\n\nThe actions you can perform fall into several categories:\n\nPage Operation Actions:\n`click [id] [content]`: This action clicks on an element with a specific id on the webpage.\n`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.\n`hover [id] [content]`: Hover over an element with id.\n`press [key_comb]`:  Simulates the pressing of a key combination on the keyboard (e.g., Ctrl+v).\n`scroll [down|up]`: Scroll the page up or down.\n\nTab Management Actions:\n`new_tab`: Open a new, empty browser tab.\n`tab_focus [tab_index]`: Switch the browser's focus to a specific tab using its index.\n`close_tab`: Close the currently active tab.\n\nURL Navigation Actions:\n`goto [url]`: Navigate to a specific URL.\n`go_back`: Navigate to the previously viewed page.\n`go_forward`: Navigate to the next page (if a previous 'go_back' action was performed).\n\nCompletion Action:\n`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.\n\nTo be successful, it is very important to follow the following rules:\n1. You should only issue an action that is valid given the current observation.\n2. You should only issue one action at a time.\n3. You should follow the examples to reason step by step and then issue the next action.\n4. You should refer to historical actions when issue an action and try not to make repetitive actions\n5. All reasoning must be inside `<think></think>` tags, and there must be no output before `<think></think>`.\n6. After `<think></think>`, only the action should be generated in the correct format, enclosed in code fences. For example:\n   <think>This button looks relevant to my goal. Clicking it should take me to the next step.</think>\n   ```click [id] [content]```\n7. Issue the stop action when you think you have achieved the objective. Don’t generate anything after stop.\n8. Always format actions correctly: \n```command [parameters]```\nFor example, if searching for \"\"death row inmates in the US\"\" in a search field with ID `21`, correctly format it as:\n```type [21] [death row inmates in the US] [1]```\nAvoid incorrect formats that omit brackets around parameters or numeric values.\n"}, {"role": "user", "content": "\nObjective: who availed the longest term as president of indian national congress\nObservation: [1] RootWebArea 'User:The other Kiwix guy/Landing' focused: True\n\t[21] textbox \"Search 'Wikipedia'\" required: False\n\t[23] link 'Go to welcome page'\n\t\t[30] button '🏠'\n\t[24] link \"Go to the main page of 'Wikipedia'\"\n\t\t[32] button 'Wikipedia'\n\t[25] link 'Go to a randomly selected page'\n\t\t[34] button '🎲'\n\t[82] StaticText 'Welcome to '\n\t[83] link 'Wikipedia'\n\t[84] StaticText 'The free encyclopedia.'\n\t[371] StaticText '6,489,052'\n\t[86] StaticText ' articles in '\n\t[369] link 'English'\n\t[53] heading 'Arts'\n\t[89] link 'Architecture'\n\t[91] link 'Books'\n\t[93] link 'Cinematography'\n\t[95] link 'Dance'\n\t[97] link 'Design'\n\t[99] link 'Fashion'\n\t[101] link 'Films'\n\t[103] link 'Gastronomy'\n\t[105] link 'Literature'\n\t[107] link 'Magic (illusion)'\n\t[109] link 'Music'\n\t[111] link 'Painting'\n\t[113] link 'Photography'\n\t[115] link 'Poetry'\n\t[117] link 'Sculpture'\n\t[119] link 'Theatre'\n\t[55] heading 'Geography'\n\t[122] link 'Africa'\n\t[124] link 'Antarctica'\n\t[126] link 'Arctic'\n\t[128] link 'Asia'\n\t[130] link 'Caribbean'\n\t[132] link 'Central America'\n\t[134] link 'Europe'\n\t[136] link 'Latin America'\n\t[138] link 'Mediterranean'\n\t[140] link 'Middle East'\n\t[142] link 'North America'\n\t[144] link 'Oceania'\n\t[146] link 'South America'\n\t[148] link 'Cartography'\n\t[57] heading 'History'\n\t[150] link 'Ancient Egypt'\n\t[152] link 'Ancient Greece'\n\t[154] link 'Ancient Near East'\n\t[156] link 'Ancient Rome'\n\t[158] link 'Archaeology'\n\t[160] link 'British Empire'\n\t[162] link 'Byzantine Empire'\n\t[164] link 'Colonialism'\n\t[166] link 'Crusades'\n\t[168] link 'Heraldry'\n\t[170] link 'History of science'\n\t[172] link 'Imperial China'\n\t[174] link 'Indian independence movement'\n\t[176] link 'Japan'\n\t[178] link 'Middle Ages'\n\t[180] link 'Mughal Empire'\n\t[182] link 'Ottoman Empire'\n\t[184] link 'Russian Empire'\n\t[186] link 'Sasanian Empire'\n\t[188] link 'Seljuk Empire'\n\t[190] link 'Soviet Union'\n\t[192] link 'War'\n\t[59] heading 'Sciences'\nHISTORY_ACTION: \n\n"}, {"role": "assistant", "content": "<think>To find out who availed the longest term as president of the Indian National Congress, I should search for this information. There is a search textbox with id 21 labeled \"Search 'Wikipedia'\". I will use it to search for \"President of Indian National Congress\".</think>\n```type [21] [President of Indian National Congress] [1]```"}]}
+{"messages": [{"role": "system", "content": "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.\n\nHere's the information you'll have:\nThe user's objective: This is the task you're trying to complete.\nThe current web page's accessibility tree: This is a simplified representation of the webpage, providing key information.\nThe open tabs: These are the tabs you have open.\nThe previous actions: There are the actions you just performed. It may be helpful to track your progress.\n\nThe actions you can perform fall into several categories:\n\nPage Operation Actions:\n`click [id] [content]`: This action clicks on an element with a specific id on the webpage.\n`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.\n`hover [id] [content]`: Hover over an element with id.\n`press [key_comb]`:  Simulates the pressing of a key combination on the keyboard (e.g., Ctrl+v).\n`scroll [down|up]`: Scroll the page up or down.\n\nTab Management Actions:\n`new_tab`: Open a new, empty browser tab.\n`tab_focus [tab_index]`: Switch the browser's focus to a specific tab using its index.\n`close_tab`: Close the currently active tab.\n\nURL Navigation Actions:\n`goto [url]`: Navigate to a specific URL.\n`go_back`: Navigate to the previously viewed page.\n`go_forward`: Navigate to the next page (if a previous 'go_back' action was performed).\n\nCompletion Action:\n`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.\n\nTo be successful, it is very important to follow the following rules:\n1. You should only issue an action that is valid given the current observation.\n2. You should only issue one action at a time.\n3. You should follow the examples to reason step by step and then issue the next action.\n4. You should refer to historical actions when issue an action and try not to make repetitive actions\n5. All reasoning must be inside `<think></think>` tags, and there must be no output before `<think></think>`.\n6. After `<think></think>`, only the action should be generated in the correct format, enclosed in code fences. For example:\n   <think>This button looks relevant to my goal. Clicking it should take me to the next step.</think>\n   ```click [id] [content]```\n7. Issue the stop action when you think you have achieved the objective. Don’t generate anything after stop.\n8. Always format actions correctly: \n```command [parameters]```\nFor example, if searching for \"\"death row inmates in the US\"\" in a search field with ID `21`, correctly format it as:\n```type [21] [death row inmates in the US] [1]```\nAvoid incorrect formats that omit brackets around parameters or numeric values.\n"}, {"role": "user", "content": "\nObjective: who was the peace negotiator for the north vietnamese\nObservation: [1237] RootWebArea 'Search: North Vietnamese peace negotiator' focused: True url: http://localhost:22015/search?content=wikipedia_en_all_maxi_2022-05&pattern=North+Vietnamese+peace+negotiator\n\t[1285] textbox \"Search 'Wikipedia'\" required: False\n\t[1291] link 'Go to welcome page' url: http://localhost:22015/\n\t\t[1292] button '🏠'\n\t[1293] link \"Go to the main page of 'Wikipedia'\" url: http://localhost:22015/wikipedia_en_all_maxi_2022-05/\n\t\t[1294] button 'Wikipedia'\n\t[1295] link 'Go to a randomly selected page' url: http://localhost:22015/random?content=wikipedia_en_all_maxi_2022-05\n\t\t[1296] button '🎲'\n\t[1025] StaticText 'Results 1-25 of 2,000 for \"North Vietnamese peace negotiator\"'\n\t[1304] link 'Paris Peace Accords' url: http://localhost:22015/wikipedia_en_all_maxi_2022-05/A/Paris_Peace_Accords\n\t[1032] StaticText '...(North Vietnam), the Republic of Vietnam (South Vietnam), and the United States, as well as the Republic of South Vietnam (PRG) that represented South Vietnamese communists. US ground forces up to that point had been sidelined with deteriorating morale and gradually withdrawn to coastal regions, not taking part in offensive operations or much direct combat for the preceding two-year period.[1][2] The Paris Agreement Treaty would in effect remove all remaining US Forces, including air and naval......'\n\t[1035] StaticText 'from Wikipedia'\n\t[1036] StaticText '4,011 words'\n\t[1310] link 'Decent interval' url: http://localhost:22015/wikipedia_en_all_maxi_2022-05/A/Decent_interval\n\t[1038] StaticText '...North Vietnam to recognize South Vietnam\\'s right to choose a leader by democratic election. The decent interval theory holds that, privately, the Nixon administration did not plan for the continuation of South Vietnam and was only interested in the release of United States prisoners of war and maintaining a \"decent interval\" before South Vietnamese collapse.[3][5] If a \"decent interval\" elapsed between the withdrawal of American troops and the fall of the South Vietnamese government, Nixon could......'\n\t[1041] StaticText 'from Wikipedia'\n\t[1042] StaticText '2,112 words'\n\t[1316] link 'Lê Đức Thọ' url: http://localhost:22015/wikipedia_en_all_maxi_2022-05/A/L%C3%AA_%C4%90%E1%BB%A9c_Th%E1%BB%8D\n\t[1044] StaticText '...North Vietnamese delegation, but Thọ arrived in Paris in June 1968 to take effective control.[2] On his way to Paris, Thọ stopped in Moscow to meet the Soviet Premier Aleksei Kosygin. On Thọ\\'s behalf, Kosygin sent President Lyndon B. Johnson a letter reading: \"My colleagues and I believe and have grounds to believe that an end to the bombing [of North Vietnam] would lead to a breakthrough in the peace talks\".[7] On 26 June 1968, Thọ first met Cyrus Vance and Philip Habib of the American......'\n\t[1049] StaticText 'from Wikipedia'\n\t[1050] StaticText '5,773 words'\n\t[1323] link 'Operation Linebacker II' url: http://localhost:22015/wikipedia_en_all_maxi_2022-05/A/Operation_Linebacker_II\n\t[1052] StaticText '...(North Vietnam) during the final period of U.S. involvement in the Vietnam War. The operation was conducted from 18 to 29 December 1972, leading to several informal names such as \"The December Raids\" and \"The Christmas Bombings\".[10] In Vietnam, it is just simply called \"12 days and nights\" (12 ngày đêm) and \"Operation Dien Bien Phu in the air\" (Chiến dịch Điện Biên Phủ trên không) or just simply Dien Bien Phu in the air (Điện Biên Phủ trên không). Unlike the Operation......'\n\t[1055] StaticText 'from Wikipedia'\n\t[1056] StaticText '9,503 words'\n\t[1329] link 'Henry Kissinger and the Vietnam war' url: http://localhost:22015/wikipedia_en_all_maxi_2022-05/A/Henry_Kissinger_and_the_Vietnam_war\n\t[1058] StaticText '...North Vietnam for a short period of time as a sign of good faith, but the National Security Adviser, W.W. Rostow, persuaded Johnson to increase the bombing of North Vietnam at the same time.[6] On 22 August 1967 Aubrac and Marcovitch were refused visas to visit North Vietnam as the inability of Kissinger to achieve the promised bombing pause had disillusioned Ho.[8] In August 1968, Kissinger wrote to Harriman, who was leading the American delegation at the Paris peace talks: \"My dear Averell...I......'\n\t[1065] StaticText 'from Wikipedia'\n\t[1066] StaticText '14,607 words'\n\t[1337] link '1973 in the Vietnam War' url: http://localhost:22015/wikipedia_en_all_maxi_2022-05/A/1973_in_the_Vietnam_War\n\t[1068] StaticText '...North Vietnam and the insurgent Viet Cong on the other. Although honored in some respects, the peace agreement was violated by both North and South Vietnam as the struggle for power and control of territory in South Vietnam continued. North Vietnam released all American prisoners of war and the United States completed its military withdrawal from South Vietnam. U.S. Congressional opposition to the Vietnam War forced the U.S. to cease bombing communist forces in Cambodia in August and in November......'\nHISTORY_ACTION: type [327] [North Vietnamese peace negotiator] [1]\n"}, {"role": "assistant", "content": "<think>The search results include a link to \"Lê Đức Thọ,\" and the snippet mentions that he arrived in Paris in June 1968 to take effective control of the North Vietnamese delegation at the peace talks. This strongly suggests he was the peace negotiator for North Vietnam. To confirm and gather more details, I should click on the \"Lê Đức Thọ\" link to view his Wikipedia article.</think>\n```click [1316] [Lê Đức Thọ]```"}]}

qwen2.5-7b-2225q-661q-1e_6-old-click-1ep/args.json

@@ -0,0 +1,381 @@
+{
+  "output_dir": "/group/40143/hongzhuyi/ms-swift/output/v2-20250819-162442",
+  "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": 1,
+  "per_device_eval_batch_size": 1,
+  "per_gpu_train_batch_size": null,
+  "per_gpu_eval_batch_size": null,
+  "gradient_accumulation_steps": 2,
+  "eval_accumulation_steps": null,
+  "eval_delay": 0,
+  "torch_empty_cache_steps": null,
+  "learning_rate": 1e-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": 1.0,
+  "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/v2-20250819-162442/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": 20.0,
+  "dataloader_num_workers": 48,
+  "dataloader_prefetch_factor": null,
+  "past_index": -1,
+  "run_name": "/group/40143/hongzhuyi/ms-swift/output/v2-20250819-162442",
+  "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_fused",
+  "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,
+  "hub_revision": null,
+  "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,
+  "liger_kernel_config": null,
+  "eval_use_gather_object": false,
+  "average_tokens_across_devices": true,
+  "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": [
+    "rft_661q_7b_click_nourl_long_swift.jsonl",
+    "corr_data_2225q_old_click_nourl_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='/usr/local/app/.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 0x7f682781ce50>, 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": "/usr/local/app/.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/v2-20250819-162442', 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=1, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=2, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=1e-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=1.0, 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/v2-20250819-162442/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=20.0, dataloader_num_workers=48, dataloader_prefetch_factor=10, past_index=-1, run_name='/group/40143/hongzhuyi/ms-swift/output/v2-20250819-162442', 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_FUSED: 'adamw_torch_fused'>, 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, hub_revision=None, 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, liger_kernel_config=None, 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)"
+}