Upload folder using huggingface_hub

.gitattributes

@@ -68,3 +68,5 @@ qwen2.5-7b-2225q-206[[:space:]]q-1369q-newbs-new-click-2ep-lr1e-6/checkpoint-172
 qwen2.5-7b-2225q-206[[:space:]]q-1369q-newbs-new-click-2ep-lr1e-6/checkpoint-86/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 qwen2.5-7b-2225q-2069q-1369q-rft-newbs-old-click-2ep-lr1e-6/checkpoint-405/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 qwen2.5-7b-2225q-2069q-1369q-rft-newbs-old-click-2ep-lr1e-6/checkpoint-810/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen2.5-7b-2000q-2000q-1369q-noinfo-newbs-old-click-2ep-lr1e-6/checkpoint-375/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen2.5-7b-2000q-2000q-1369q-noinfo-newbs-old-click-2ep-lr1e-6/checkpoint-750/tokenizer.json filter=lfs diff=lfs merge=lfs -text

log/20250914-12:51:16.log

@@ -0,0 +1,533 @@
+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 /group/40143/hongzhuyi/model/qwen2.5-7b-2225q-2069q-1369q-newbs-old-click-xep-lr5e-6/qwen2.5-7b-2225q-2069q-1369q-newbs-old-click-xep-lr5e-6/checkpoint-636 --train_type full --dataset ./corr_nq_2000q_hotpot_2000q_swift.jsonl ./corr_hotpot_new1369q_noinfo_swift.jsonl --model_type qwen2_5 --dataset_num_proc 100 --dataloader_num_workers 48 --split_dataset_ratio 0.001 --warmup_ratio 0.05 --num_train_epochs 2 --per_device_train_batch_size 2 --learning_rate 1e-6 --gradient_accumulation_steps 4 --eval_steps 2000 --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
+[INFO:swift] Loading the model using model_dir: /group/40143/hongzhuyi/model/qwen2.5-7b-2225q-2069q-1369q-newbs-old-click-xep-lr5e-6/qwen2.5-7b-2225q-2069q-1369q-newbs-old-click-xep-lr5e-6/checkpoint-636
+[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}
+[2025-09-14 12:51:41,864] [INFO] [real_accelerator.py:254:get_accelerator] Setting ds_accelerator to cuda (auto detect)
+[2025-09-14 12:51:41,898] [INFO] [real_accelerator.py:254:get_accelerator] Setting ds_accelerator to cuda (auto detect)
+[2025-09-14 12:51:42,387] [INFO] [real_accelerator.py:254:get_accelerator] Setting ds_accelerator to cuda (auto detect)
+[2025-09-14 12:51:42,436] [INFO] [real_accelerator.py:254:get_accelerator] Setting ds_accelerator to cuda (auto detect)
+[2025-09-14 12:51:42,460] [INFO] [real_accelerator.py:254:get_accelerator] Setting ds_accelerator to cuda (auto detect)
+[2025-09-14 12:51:42,497] [INFO] [real_accelerator.py:254:get_accelerator] Setting ds_accelerator to cuda (auto detect)
+[2025-09-14 12:51:42,585] [INFO] [real_accelerator.py:254:get_accelerator] Setting ds_accelerator to cuda (auto detect)
+[2025-09-14 12:51:42,585] [INFO] [real_accelerator.py:254:get_accelerator] Setting ds_accelerator to cuda (auto detect)
+[2025-09-14 12:51:43,245] [INFO] [logging.py:107:log_dist] [Rank -1] [TorchCheckpointEngine] Initialized with serialization = False
+[2025-09-14 12:51:43,253] [INFO] [comm.py:821:init_distributed] cdb=None
+[2025-09-14 12:51:43,354] [INFO] [logging.py:107:log_dist] [Rank -1] [TorchCheckpointEngine] Initialized with serialization = False
+[2025-09-14 12:51:43,363] [INFO] [comm.py:821:init_distributed] cdb=None
+[2025-09-14 12:51:43,837] [INFO] [logging.py:107:log_dist] [Rank -1] [TorchCheckpointEngine] Initialized with serialization = False
+[2025-09-14 12:51:43,845] [INFO] [comm.py:821:init_distributed] cdb=None
+[2025-09-14 12:51:43,845] [INFO] [comm.py:852:init_distributed] Initializing TorchBackend in DeepSpeed with backend nccl
+[2025-09-14 12:51:43,876] [INFO] [logging.py:107:log_dist] [Rank -1] [TorchCheckpointEngine] Initialized with serialization = False
+[2025-09-14 12:51:43,884] [INFO] [comm.py:821:init_distributed] cdb=None
+[2025-09-14 12:51:43,924] [INFO] [logging.py:107:log_dist] [Rank -1] [TorchCheckpointEngine] Initialized with serialization = False
+[2025-09-14 12:51:43,932] [INFO] [comm.py:821:init_distributed] cdb=None
+[2025-09-14 12:51:43,956] [INFO] [logging.py:107:log_dist] [Rank -1] [TorchCheckpointEngine] Initialized with serialization = False
+[2025-09-14 12:51:43,964] [INFO] [comm.py:821:init_distributed] cdb=None
+[2025-09-14 12:51:44,051] [INFO] [logging.py:107:log_dist] [Rank -1] [TorchCheckpointEngine] Initialized with serialization = False
+[2025-09-14 12:51:44,060] [INFO] [comm.py:821:init_distributed] cdb=None
+[2025-09-14 12:51:44,165] [INFO] [logging.py:107:log_dist] [Rank -1] [TorchCheckpointEngine] Initialized with serialization = False
+[2025-09-14 12:51:44,175] [INFO] [comm.py:821:init_distributed] cdb=None
+[INFO:swift] output_dir: /group/40143/hongzhuyi/ms-swift/output/v0-20250914-125148
+[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=/group/40143/hongzhuyi/model/qwen2.5-7b-2225q-2069q-1369q-newbs-old-click-xep-lr5e-6/qwen2.5-7b-2225q-2069q-1369q-newbs-old-click-xep-lr5e-6/checkpoint-636,
+columns={},
+create_checkpoint_symlink=False,
+custom_dataset_info=[],
+custom_register_path=[],
+data_seed=42,
+dataloader_drop_last=False,
+dataloader_num_workers=48,
+dataloader_persistent_workers=False,
+dataloader_pin_memory=True,
+dataloader_prefetch_factor=None,
+dataset=['./corr_nq_2000q_hotpot_2000q_swift.jsonl', './corr_hotpot_new1369q_noinfo_swift.jsonl'],
+dataset_num_proc=100,
+dataset_shuffle=True,
+ddp_backend=None,
+ddp_broadcast_buffers=None,
+ddp_bucket_cap_mb=None,
+ddp_find_unused_parameters=None,
+ddp_timeout=18000000,
+debug=None,
+deepspeed={'fp16': {'enabled': 'auto', 'loss_scale': 0, 'loss_scale_window': 1000, 'initial_scale_power': 16, 'hysteresis': 2, 'min_loss_scale': 1}, 'bf16': {'enabled': 'auto'}, 'zero_optimization': {'stage': 3, 'offload_optimizer': {'device': 'none', 'pin_memory': True}, 'offload_param': {'device': 'none', 'pin_memory': True}, 'overlap_comm': False, 'contiguous_gradients': True, 'sub_group_size': 1000000000.0, 'reduce_bucket_size': 'auto', 'zero_quantized_weights': False, 'zero_quantized_gradients': False, 'stage3_prefetch_bucket_size': 'auto', 'stage3_param_persistence_threshold': 'auto', 'stage3_max_live_parameters': 1000000000.0, 'stage3_max_reuse_distance': 1000000000.0, 'stage3_gather_16bit_weights_on_model_save': True}, 'gradient_accumulation_steps': 'auto', 'gradient_clipping': 'auto', 'steps_per_print': 2000, 'train_batch_size': 'auto', 'train_micro_batch_size_per_gpu': 'auto', 'wall_clock_breakdown': False},
+deepspeed_autotp_size=None,
+device_map=None,
+disable_tqdm=None,
+do_eval=False,
+do_predict=False,
+do_train=False,
+download_mode=reuse_dataset_if_exists,
+ds3_gather_for_generation=True,
+early_stop_interval=None,
+enable_dft_loss=False,
+eval_accumulation_steps=None,
+eval_dataset=[],
+eval_dataset_args=None,
+eval_delay=0,
+eval_do_concat_batches=True,
+eval_generation_config=None,
+eval_limit=None,
+eval_on_start=False,
+eval_steps=2000.0,
+eval_strategy=epoch,
+eval_use_evalscope=False,
+eval_use_gather_object=False,
+external_plugins=[],
+extra_eval_args=None,
+fourier_n_frequency=2000,
+fourier_scaling=300.0,
+fp16=False,
+fp16_backend=auto,
+fp16_full_eval=False,
+fp16_opt_level=O1,
+freeze_aligner=False,
+freeze_llm=False,
+freeze_parameters=[],
+freeze_parameters_ratio=0.0,
+freeze_parameters_regex=None,
+freeze_vit=True,
+fsdp=,
+fsdp_config=None,
+fsdp_min_num_params=0,
+fsdp_transformer_layer_cls_to_wrap=None,
+full_determinism=False,
+galore_cos_threshold=0.4,
+galore_gamma_proj=2,
+galore_optim_per_parameter=False,
+galore_proj_bits=4,
+galore_proj_group_size=256,
+galore_proj_quant=False,
+galore_proj_type=std,
+galore_quantization=False,
+galore_queue_size=5,
+galore_rank=128,
+galore_scale=1.0,
+galore_target_modules=None,
+galore_update_proj_gap=50,
+galore_with_embedding=False,
+generation_config=None,
+generation_max_length=None,
+generation_num_beams=None,
+gradient_accumulation_steps=4,
+gradient_checkpointing=True,
+gradient_checkpointing_kwargs=None,
+greater_is_better=False,
+group_by_length=False,
+half_precision_backend=auto,
+hqq_axis=None,
+hub_always_push=False,
+hub_model_id=None,
+hub_private_repo=None,
+hub_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/v0-20250914-125148/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=/group/40143/hongzhuyi/model/qwen2.5-7b-2225q-2069q-1369q-newbs-old-click-xep-lr5e-6/qwen2.5-7b-2225q-2069q-1369q-newbs-old-click-xep-lr5e-6/checkpoint-636,
+model_author=None,
+model_kwargs={},
+model_name=None,
+model_revision=None,
+model_type=qwen2_5,
+modules_to_save=[],
+mp_parameters=,
+neftune_noise_alpha=None,
+new_special_tokens=[],
+no_cuda=False,
+norm_bbox=None,
+num_beams=1,
+num_labels=None,
+num_train_epochs=2.0,
+optim=adamw_torch_fused,
+optim_args=None,
+optim_target_modules=None,
+optimizer=None,
+output_dir=/group/40143/hongzhuyi/ms-swift/output/v0-20250914-125148,
+overwrite_output_dir=False,
+packing=False,
+packing_length=None,
+padding_free=False,
+padding_side=right,
+past_index=-1,
+per_device_eval_batch_size=1,
+per_device_train_batch_size=2,
+predict_with_generate=False,
+prediction_loss_only=False,
+problem_type=None,
+push_to_hub=False,
+push_to_hub_model_id=None,
+push_to_hub_organization=None,
+push_to_hub_token=<PUSH_TO_HUB_TOKEN>,
+quant_bits=None,
+quant_method=None,
+ray_scope=last,
+reft_args=None,
+reft_intervention_type=LoreftIntervention,
+reft_layer_key=None,
+reft_layers=None,
+reft_rank=4,
+remove_unused_columns=True,
+repetition_penalty=None,
+report_to=['tensorboard'],
+response_prefix=None,
+restore_callback_states_from_checkpoint=False,
+resume_from_checkpoint=None,
+resume_only_model=False,
+rope_scaling=None,
+router_aux_loss_coef=0.0,
+run_name=/group/40143/hongzhuyi/ms-swift/output/v0-20250914-125148,
+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,
+)
+[INFO:swift] Loading the model using model_dir: /group/40143/hongzhuyi/model/qwen2.5-7b-2225q-2069q-1369q-newbs-old-click-xep-lr5e-6/qwen2.5-7b-2225q-2069q-1369q-newbs-old-click-xep-lr5e-6/checkpoint-636
+[INFO:swift] model_kwargs: {'device_map': None}
+[2025-09-14 12:51:53,970] [INFO] [config.py:684:__init__] Config mesh_device None world_size = 8
+[2025-09-14 12:51:53,970] [INFO] [config.py:684:__init__] Config mesh_device None world_size = 8
+[2025-09-14 12:51:53,970] [INFO] [config.py:684:__init__] Config mesh_device None world_size = 8
+[2025-09-14 12:51:53,970] [INFO] [config.py:684:__init__] Config mesh_device None world_size = 8
+[2025-09-14 12:51:53,971] [INFO] [config.py:684:__init__] Config mesh_device None world_size = 8
+[2025-09-14 12:51:53,971] [INFO] [config.py:684:__init__] Config mesh_device None world_size = 8
+[2025-09-14 12:51:53,971] [INFO] [config.py:684:__init__] Config mesh_device None world_size = 8
+[2025-09-14 12:51:53,971] [INFO] [config.py:684:__init__] Config mesh_device None world_size = 8
+[2025-09-14 12:51:54,102] [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='/group/40143/hongzhuyi/model/qwen2.5-7b-2225q-2069q-1369q-newbs-old-click-xep-lr5e-6/qwen2.5-7b-2225q-2069q-1369q-newbs-old-click-xep-lr5e-6/checkpoint-636', 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": "4.55.4",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}
+, task_type='causal_lm', num_labels=None)
+[INFO:swift] model.generation_config: GenerationConfig {
+  "bos_token_id": 151643,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "max_new_tokens": 64,
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05
+}
+
+[INFO:swift] default_system: 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.'
+[INFO:swift] max_length: 16240
+[INFO:swift] response_prefix: ''
+[INFO:swift] agent_template: hermes
+[INFO:swift] Start time of running main: 2025-09-14 13:16:34.946643
+[INFO:swift] swift.__version__: 3.8.0.dev0
+Setting num_proc from 100 back to 1 for the train split to disable multiprocessing as it only contains one shard.
+
+
+[INFO:swift] Downloading the dataset from ModelScope, dataset_id: ./corr_hotpot_new1369q_noinfo_swift.jsonl
+[ERROR:swift] Dataset ./corr_hotpot_new1369q_noinfo_swift.jsonl 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 ./corr_hotpot_new1369q_noinfo_swift.jsonl 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 423, 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 588, in repo_exists
+[rank0]:     raise Exception(
+[rank0]: Exception: Failed to check existence of repo: dataset, make sure you have access authorization.
+[rank0]:[W914 13:16:48.985320885 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())
+[rank0]:[E914 13:31:44.529684141 ProcessGroupNCCL.cpp:1870] [PG ID 0 PG GUID 0(default_pg) Rank 0] ProcessGroupNCCL's watchdog got stuck for 480 seconds without making progress in monitoring enqueued collectives. This typically indicates a NCCL/CUDA API (e.g., CudaEventDestroy) hang blocking the watchdog, and could be triggered by another thread holding the GIL inside a CUDA api (for example, CudaEventDestroy), or other deadlock-prone behaviors.If you suspect the watchdog is not actually stuck and a longer timeout would help, you can either increase the timeout (TORCH_NCCL_HEARTBEAT_TIMEOUT_SEC) to a larger value or disable the heartbeat monitor (TORCH_NCCL_ENABLE_MONITORING=0).If either of aforementioned helps, feel free to file an issue to PyTorch about the short timeout or false positive abort; otherwise, please attempt to debug the hang. 
+[rank0]:[E914 13:31:44.529814039 ProcessGroupNCCL.cpp:1589] [PG ID 0 PG GUID 0(default_pg) Rank 0] ProcessGroupNCCL preparing to dump debug info. Include stack trace: 1
+[rank0]:[F914 13:39:44.530320147 ProcessGroupNCCL.cpp:1614] [PG ID 0 PG GUID 0(default_pg) Rank 0] [PG ID 0 PG GUID 0(default_pg) Rank 0] Terminating the process after attempting to dump debug info, due to ProcessGroupNCCL watchdog hang.
+W0914 13:39:45.168000 2637292 site-packages/torch/distributed/elastic/multiprocessing/api.py:900] Sending process 2637379 closing signal SIGTERM
+W0914 13:39:45.180000 2637292 site-packages/torch/distributed/elastic/multiprocessing/api.py:900] Sending process 2637380 closing signal SIGTERM
+W0914 13:39:45.191000 2637292 site-packages/torch/distributed/elastic/multiprocessing/api.py:900] Sending process 2637381 closing signal SIGTERM
+W0914 13:39:45.197000 2637292 site-packages/torch/distributed/elastic/multiprocessing/api.py:900] Sending process 2637382 closing signal SIGTERM
+W0914 13:39:45.204000 2637292 site-packages/torch/distributed/elastic/multiprocessing/api.py:900] Sending process 2637383 closing signal SIGTERM
+W0914 13:39:45.213000 2637292 site-packages/torch/distributed/elastic/multiprocessing/api.py:900] Sending process 2637384 closing signal SIGTERM
+W0914 13:39:45.222000 2637292 site-packages/torch/distributed/elastic/multiprocessing/api.py:900] Sending process 2637385 closing signal SIGTERM
+E0914 13:39:46.483000 2637292 site-packages/torch/distributed/elastic/multiprocessing/api.py:874] failed (exitcode: -6) local_rank: 0 (pid: 2637378) 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      : 2025-09-14_13:39:45
+  host      : TENCENT64.site
+  rank      : 0 (local_rank: 0)
+  exitcode  : -6 (pid: 2637378)
+  error_file: <N/A>
+  traceback : Signal 6 (SIGABRT) received by PID 2637378
+========================================================

qwen2.5-7b-2000q-2000q-1369q-noinfo-newbs-old-click-2ep-lr1e-6/args.json

@@ -0,0 +1,384 @@
+{
+  "output_dir": "/group/40143/hongzhuyi/ms-swift/output/v1-20250914-134901",
+  "overwrite_output_dir": false,
+  "do_train": false,
+  "do_eval": false,
+  "do_predict": false,
+  "eval_strategy": "epoch",
+  "prediction_loss_only": false,
+  "per_device_train_batch_size": 2,
+  "per_device_eval_batch_size": 1,
+  "per_gpu_train_batch_size": null,
+  "per_gpu_eval_batch_size": null,
+  "gradient_accumulation_steps": 4,
+  "eval_accumulation_steps": null,
+  "eval_delay": 0,
+  "torch_empty_cache_steps": null,
+  "learning_rate": 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": 2.0,
+  "max_steps": -1,
+  "lr_scheduler_type": "cosine",
+  "lr_scheduler_kwargs": null,
+  "warmup_ratio": 0.05,
+  "warmup_steps": 0,
+  "log_level": "passive",
+  "log_level_replica": "warning",
+  "log_on_each_node": true,
+  "logging_dir": "/group/40143/hongzhuyi/ms-swift/output/v1-20250914-134901/runs",
+  "logging_strategy": "steps",
+  "logging_first_step": true,
+  "logging_steps": 1,
+  "logging_nan_inf_filter": true,
+  "save_strategy": "epoch",
+  "save_steps": 500,
+  "save_total_limit": null,
+  "save_safetensors": true,
+  "save_on_each_node": false,
+  "save_only_model": false,
+  "restore_callback_states_from_checkpoint": false,
+  "no_cuda": false,
+  "use_cpu": false,
+  "use_mps_device": false,
+  "seed": 42,
+  "data_seed": 42,
+  "jit_mode_eval": false,
+  "use_ipex": false,
+  "bf16": true,
+  "fp16": false,
+  "fp16_opt_level": "O1",
+  "half_precision_backend": "auto",
+  "bf16_full_eval": false,
+  "fp16_full_eval": false,
+  "tf32": null,
+  "local_rank": 0,
+  "ddp_backend": null,
+  "tpu_num_cores": null,
+  "tpu_metrics_debug": false,
+  "debug": null,
+  "dataloader_drop_last": false,
+  "eval_steps": 2000.0,
+  "dataloader_num_workers": 48,
+  "dataloader_prefetch_factor": null,
+  "past_index": -1,
+  "run_name": "/group/40143/hongzhuyi/ms-swift/output/v1-20250914-134901",
+  "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": "/group/40143/hongzhuyi/model/qwen2.5-7b-2225q-2069q-1369q-newbs-old-click-xep-lr5e-6/qwen2.5-7b-2225q-2069q-1369q-newbs-old-click-xep-lr5e-6/checkpoint-636",
+  "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": [
+    "/group/40143/hongzhuyi/ms-swift/data/corr_hotpot_2083q_0.8_swift.jsonl",
+    "/group/40143/hongzhuyi/ms-swift/data/corr_hotpot_new1369q_0.8_swift.jsonl",
+    "/group/40143/hongzhuyi/ms-swift/data/corr_nq_2225q_0.8_swift.jsonl",
+    "/group/40143/hongzhuyi/ms-swift/data/self_2000_2000_1369_4_hp673_swift.jsonl",
+    "/group/40143/hongzhuyi/ms-swift/data/self_2000_2000_1369_4_nq400_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": "/group/40143/hongzhuyi/model/qwen2.5-7b-2225q-2069q-1369q-newbs-old-click-xep-lr5e-6/qwen2.5-7b-2225q-2069q-1369q-newbs-old-click-xep-lr5e-6/checkpoint-636",
+  "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": "checkpoint-636",
+  "model_info": "ModelInfo(model_type='qwen2_5', model_dir='/group/40143/hongzhuyi/model/qwen2.5-7b-2225q-2069q-1369q-newbs-old-click-xep-lr5e-6/qwen2.5-7b-2225q-2069q-1369q-newbs-old-click-xep-lr5e-6/checkpoint-636', 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 0x7f66153ba830>, 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": "/group/40143/hongzhuyi/model/qwen2.5-7b-2225q-2069q-1369q-newbs-old-click-xep-lr5e-6/qwen2.5-7b-2225q-2069q-1369q-newbs-old-click-xep-lr5e-6/checkpoint-636",
+  "hub": "<class 'swift.hub.hub.MSHub'>",
+  "evaluation_strategy": "epoch",
+  "training_args": "Seq2SeqTrainingArguments(output_dir='/group/40143/hongzhuyi/ms-swift/output/v1-20250914-134901', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, eval_strategy=<IntervalStrategy.EPOCH: 'epoch'>, prediction_loss_only=False, per_device_train_batch_size=2, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=4, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=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=2.0, max_steps=-1, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs=None, warmup_ratio=0.05, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/group/40143/hongzhuyi/ms-swift/output/v1-20250914-134901/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=1, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.EPOCH: 'epoch'>, save_steps=500, save_total_limit=None, save_safetensors=True, save_on_each_node=False, save_only_model=False, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=42, jit_mode_eval=False, use_ipex=False, bf16=True, fp16=False, fp16_opt_level='O1', half_precision_backend='auto', bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=0, ddp_backend=None, tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=2000.0, dataloader_num_workers=48, dataloader_prefetch_factor=10, past_index=-1, run_name='/group/40143/hongzhuyi/ms-swift/output/v1-20250914-134901', 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-2000q-2000q-1369q-noinfo-newbs-old-click-2ep-lr1e-6/checkpoint-375/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-2000q-2000q-1369q-noinfo-newbs-old-click-2ep-lr1e-6/checkpoint-375/args.json

@@ -0,0 +1,384 @@
+{
+  "output_dir": "/group/40143/hongzhuyi/ms-swift/output/v1-20250914-134901",
+  "overwrite_output_dir": false,
+  "do_train": false,
+  "do_eval": false,
+  "do_predict": false,
+  "eval_strategy": "epoch",
+  "prediction_loss_only": false,
+  "per_device_train_batch_size": 2,
+  "per_device_eval_batch_size": 1,
+  "per_gpu_train_batch_size": null,
+  "per_gpu_eval_batch_size": null,
+  "gradient_accumulation_steps": 4,
+  "eval_accumulation_steps": null,
+  "eval_delay": 0,
+  "torch_empty_cache_steps": null,
+  "learning_rate": 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": 2.0,
+  "max_steps": -1,
+  "lr_scheduler_type": "cosine",
+  "lr_scheduler_kwargs": null,
+  "warmup_ratio": 0.05,
+  "warmup_steps": 0,
+  "log_level": "passive",
+  "log_level_replica": "warning",
+  "log_on_each_node": true,
+  "logging_dir": "/group/40143/hongzhuyi/ms-swift/output/v1-20250914-134901/runs",
+  "logging_strategy": "steps",
+  "logging_first_step": true,
+  "logging_steps": 1,
+  "logging_nan_inf_filter": true,
+  "save_strategy": "epoch",
+  "save_steps": 500,
+  "save_total_limit": null,
+  "save_safetensors": true,
+  "save_on_each_node": false,
+  "save_only_model": false,
+  "restore_callback_states_from_checkpoint": false,
+  "no_cuda": false,
+  "use_cpu": false,
+  "use_mps_device": false,
+  "seed": 42,
+  "data_seed": 42,
+  "jit_mode_eval": false,
+  "use_ipex": false,
+  "bf16": true,
+  "fp16": false,
+  "fp16_opt_level": "O1",
+  "half_precision_backend": "auto",
+  "bf16_full_eval": false,
+  "fp16_full_eval": false,
+  "tf32": null,
+  "local_rank": 0,
+  "ddp_backend": null,
+  "tpu_num_cores": null,
+  "tpu_metrics_debug": false,
+  "debug": null,
+  "dataloader_drop_last": false,
+  "eval_steps": 2000.0,
+  "dataloader_num_workers": 48,
+  "dataloader_prefetch_factor": null,
+  "past_index": -1,
+  "run_name": "/group/40143/hongzhuyi/ms-swift/output/v1-20250914-134901",
+  "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": "/group/40143/hongzhuyi/model/qwen2.5-7b-2225q-2069q-1369q-newbs-old-click-xep-lr5e-6/qwen2.5-7b-2225q-2069q-1369q-newbs-old-click-xep-lr5e-6/checkpoint-636",
+  "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": [
+    "/group/40143/hongzhuyi/ms-swift/data/corr_hotpot_2083q_0.8_swift.jsonl",
+    "/group/40143/hongzhuyi/ms-swift/data/corr_hotpot_new1369q_0.8_swift.jsonl",
+    "/group/40143/hongzhuyi/ms-swift/data/corr_nq_2225q_0.8_swift.jsonl",
+    "/group/40143/hongzhuyi/ms-swift/data/self_2000_2000_1369_4_hp673_swift.jsonl",
+    "/group/40143/hongzhuyi/ms-swift/data/self_2000_2000_1369_4_nq400_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": "/group/40143/hongzhuyi/model/qwen2.5-7b-2225q-2069q-1369q-newbs-old-click-xep-lr5e-6/qwen2.5-7b-2225q-2069q-1369q-newbs-old-click-xep-lr5e-6/checkpoint-636",
+  "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": "checkpoint-636",
+  "model_info": "ModelInfo(model_type='qwen2_5', model_dir='/group/40143/hongzhuyi/model/qwen2.5-7b-2225q-2069q-1369q-newbs-old-click-xep-lr5e-6/qwen2.5-7b-2225q-2069q-1369q-newbs-old-click-xep-lr5e-6/checkpoint-636', 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 0x7f66153ba830>, 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": "/group/40143/hongzhuyi/model/qwen2.5-7b-2225q-2069q-1369q-newbs-old-click-xep-lr5e-6/qwen2.5-7b-2225q-2069q-1369q-newbs-old-click-xep-lr5e-6/checkpoint-636",
+  "hub": "<class 'swift.hub.hub.MSHub'>",
+  "evaluation_strategy": "epoch",
+  "training_args": "Seq2SeqTrainingArguments(output_dir='/group/40143/hongzhuyi/ms-swift/output/v1-20250914-134901', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, eval_strategy=<IntervalStrategy.EPOCH: 'epoch'>, prediction_loss_only=False, per_device_train_batch_size=2, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=4, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=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=2.0, max_steps=-1, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs=None, warmup_ratio=0.05, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/group/40143/hongzhuyi/ms-swift/output/v1-20250914-134901/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=1, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.EPOCH: 'epoch'>, save_steps=500, save_total_limit=None, save_safetensors=True, save_on_each_node=False, save_only_model=False, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=42, jit_mode_eval=False, use_ipex=False, bf16=True, fp16=False, fp16_opt_level='O1', half_precision_backend='auto', bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=0, ddp_backend=None, tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=2000.0, dataloader_num_workers=48, dataloader_prefetch_factor=10, past_index=-1, run_name='/group/40143/hongzhuyi/ms-swift/output/v1-20250914-134901', 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-2000q-2000q-1369q-noinfo-newbs-old-click-2ep-lr1e-6/checkpoint-375/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-2000q-2000q-1369q-noinfo-newbs-old-click-2ep-lr1e-6/checkpoint-375/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": "4.55.4",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

qwen2.5-7b-2000q-2000q-1369q-noinfo-newbs-old-click-2ep-lr1e-6/checkpoint-375/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": "4.55.4"
+}

qwen2.5-7b-2000q-2000q-1369q-noinfo-newbs-old-click-2ep-lr1e-6/checkpoint-375/latest

@@ -0,0 +1 @@
+global_step375

qwen2.5-7b-2000q-2000q-1369q-noinfo-newbs-old-click-2ep-lr1e-6/checkpoint-375/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e33467cfbc39026b117a58649dabad3226f75ac5eaf6ba4fdc7326ac95cb98aa
+size 4877660776

qwen2.5-7b-2000q-2000q-1369q-noinfo-newbs-old-click-2ep-lr1e-6/checkpoint-375/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48acb105f483ef859d23500d2452690ba20bac1bc7fe88036f3138728a4b8fff
+size 4932751008

qwen2.5-7b-2000q-2000q-1369q-noinfo-newbs-old-click-2ep-lr1e-6/checkpoint-375/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37321e9015e02054dc835c4361b70297f64a54aa259d505e007f968675ee3d77
+size 4330865200

qwen2.5-7b-2000q-2000q-1369q-noinfo-newbs-old-click-2ep-lr1e-6/checkpoint-375/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a08ca7ed793659e9cffcff0f28c661adff274febd7d4ec94771d643e563ca3e1
+size 1089994880

qwen2.5-7b-2000q-2000q-1369q-noinfo-newbs-old-click-2ep-lr1e-6/checkpoint-375/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-2000q-2000q-1369q-noinfo-newbs-old-click-2ep-lr1e-6/checkpoint-375/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bfe1981024ef92f2da08a90c72c7c793d1cc9de1547abd2556c968be70232eb
+size 16389

qwen2.5-7b-2000q-2000q-1369q-noinfo-newbs-old-click-2ep-lr1e-6/checkpoint-375/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a35b845d476d830805793c3dcf8ac2daad87fec289bff3f7eda9e72fc374eda1
+size 16389

qwen2.5-7b-2000q-2000q-1369q-noinfo-newbs-old-click-2ep-lr1e-6/checkpoint-375/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03e9880996b01262a807d1ec3ebd91eee540e08130a14a45a4648731fd0d48a9
+size 16389

qwen2.5-7b-2000q-2000q-1369q-noinfo-newbs-old-click-2ep-lr1e-6/checkpoint-375/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee25c237d6fe62ec76adcf7daf899d7ed32eab5d1a5b447b911f4451c9a1b258
+size 16389

qwen2.5-7b-2000q-2000q-1369q-noinfo-newbs-old-click-2ep-lr1e-6/checkpoint-375/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a6b31133f29a8fc0cb538aa807d6a403bd51939336bfd425cd3d122d8c5595c
+size 16389

qwen2.5-7b-2000q-2000q-1369q-noinfo-newbs-old-click-2ep-lr1e-6/checkpoint-375/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a26c55b5c7fa0522b1d27b2c00a7ea77ad010f19a1321991165c5c972b8fa97a
+size 16389

qwen2.5-7b-2000q-2000q-1369q-noinfo-newbs-old-click-2ep-lr1e-6/checkpoint-375/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a1a3cf85626196804f25a8293e22dc561bba068a70fb123e04afe4896c33972
+size 16389

qwen2.5-7b-2000q-2000q-1369q-noinfo-newbs-old-click-2ep-lr1e-6/checkpoint-375/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28f87c1ee5f5db346c7b913137cbccd196eaf8ec5a4cf9f192418a3069269b49
+size 16389

qwen2.5-7b-2000q-2000q-1369q-noinfo-newbs-old-click-2ep-lr1e-6/checkpoint-375/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a0eec0cd42252c7c9bab11c8267575a655fef0c8d31949245b50d4a3a2085bd
+size 1465

qwen2.5-7b-2000q-2000q-1369q-noinfo-newbs-old-click-2ep-lr1e-6/checkpoint-375/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-2000q-2000q-1369q-noinfo-newbs-old-click-2ep-lr1e-6/checkpoint-375/tokenizer.json

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

qwen2.5-7b-2000q-2000q-1369q-noinfo-newbs-old-click-2ep-lr1e-6/checkpoint-375/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-2000q-2000q-1369q-noinfo-newbs-old-click-2ep-lr1e-6/checkpoint-375/trainer_state.json

@@ -0,0 +1,3043 @@
+{
+  "best_global_step": 375,
+  "best_metric": 0.28756759,
+  "best_model_checkpoint": "/group/40143/hongzhuyi/ms-swift/output/v1-20250914-134901/checkpoint-375",
+  "epoch": 1.0,
+  "eval_steps": 2000.0,
+  "global_step": 375,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0026702269692923898,
+      "grad_norm": 1.9854194561760121,
+      "learning_rate": 2.6315789473684208e-08,
+      "loss": 0.27858659625053406,
+      "step": 1,
+      "token_acc": 0.904057502746582
+    },
+    {
+      "epoch": 0.0053404539385847796,
+      "grad_norm": 1.9675253472142744,
+      "learning_rate": 5.2631578947368416e-08,
+      "loss": 0.29387331008911133,
+      "step": 2,
+      "token_acc": 0.8958218097686768
+    },
+    {
+      "epoch": 0.00801068090787717,
+      "grad_norm": 2.3189070059992023,
+      "learning_rate": 7.894736842105262e-08,
+      "loss": 0.33930933475494385,
+      "step": 3,
+      "token_acc": 0.8853788375854492
+    },
+    {
+      "epoch": 0.010680907877169559,
+      "grad_norm": 2.025760955455559,
+      "learning_rate": 1.0526315789473683e-07,
+      "loss": 0.28556346893310547,
+      "step": 4,
+      "token_acc": 0.9031442999839783
+    },
+    {
+      "epoch": 0.01335113484646195,
+      "grad_norm": 2.016099066706706,
+      "learning_rate": 1.3157894736842104e-07,
+      "loss": 0.2848360538482666,
+      "step": 5,
+      "token_acc": 0.8992103338241577
+    },
+    {
+      "epoch": 0.01602136181575434,
+      "grad_norm": 1.867563096066773,
+      "learning_rate": 1.5789473684210525e-07,
+      "loss": 0.2608828544616699,
+      "step": 6,
+      "token_acc": 0.9131612777709961
+    },
+    {
+      "epoch": 0.018691588785046728,
+      "grad_norm": 2.0167911268628655,
+      "learning_rate": 1.8421052631578946e-07,
+      "loss": 0.3213655352592468,
+      "step": 7,
+      "token_acc": 0.8923884630203247
+    },
+    {
+      "epoch": 0.021361815754339118,
+      "grad_norm": 1.9696770076057877,
+      "learning_rate": 2.1052631578947366e-07,
+      "loss": 0.25972414016723633,
+      "step": 8,
+      "token_acc": 0.9094372987747192
+    },
+    {
+      "epoch": 0.02403204272363151,
+      "grad_norm": 2.1945393678087384,
+      "learning_rate": 2.3684210526315787e-07,
+      "loss": 0.3009300231933594,
+      "step": 9,
+      "token_acc": 0.8958725333213806
+    },
+    {
+      "epoch": 0.0267022696929239,
+      "grad_norm": 2.074001885830379,
+      "learning_rate": 2.631578947368421e-07,
+      "loss": 0.30599695444107056,
+      "step": 10,
+      "token_acc": 0.8969143629074097
+    },
+    {
+      "epoch": 0.029372496662216287,
+      "grad_norm": 1.9745802475469194,
+      "learning_rate": 2.894736842105263e-07,
+      "loss": 0.2808346152305603,
+      "step": 11,
+      "token_acc": 0.898175060749054
+    },
+    {
+      "epoch": 0.03204272363150868,
+      "grad_norm": 1.9691616907642058,
+      "learning_rate": 3.157894736842105e-07,
+      "loss": 0.2891743779182434,
+      "step": 12,
+      "token_acc": 0.9006649255752563
+    },
+    {
+      "epoch": 0.03471295060080107,
+      "grad_norm": 2.11984769546222,
+      "learning_rate": 3.4210526315789473e-07,
+      "loss": 0.3155044913291931,
+      "step": 13,
+      "token_acc": 0.893489420413971
+    },
+    {
+      "epoch": 0.037383177570093455,
+      "grad_norm": 1.8300743271079336,
+      "learning_rate": 3.684210526315789e-07,
+      "loss": 0.2309437245130539,
+      "step": 14,
+      "token_acc": 0.9192351698875427
+    },
+    {
+      "epoch": 0.04005340453938585,
+      "grad_norm": 1.7737237140602347,
+      "learning_rate": 3.9473684210526315e-07,
+      "loss": 0.2613673210144043,
+      "step": 15,
+      "token_acc": 0.9086426496505737
+    },
+    {
+      "epoch": 0.042723631508678236,
+      "grad_norm": 2.3000815599250988,
+      "learning_rate": 4.2105263157894733e-07,
+      "loss": 0.3198656439781189,
+      "step": 16,
+      "token_acc": 0.8941822052001953
+    },
+    {
+      "epoch": 0.04539385847797063,
+      "grad_norm": 2.027333383151559,
+      "learning_rate": 4.4736842105263156e-07,
+      "loss": 0.2891864776611328,
+      "step": 17,
+      "token_acc": 0.9012279510498047
+    },
+    {
+      "epoch": 0.04806408544726302,
+      "grad_norm": 2.101932112638829,
+      "learning_rate": 4.7368421052631574e-07,
+      "loss": 0.2998722791671753,
+      "step": 18,
+      "token_acc": 0.8991110324859619
+    },
+    {
+      "epoch": 0.050734312416555405,
+      "grad_norm": 1.830628726330693,
+      "learning_rate": 5e-07,
+      "loss": 0.24977383017539978,
+      "step": 19,
+      "token_acc": 0.9131402969360352
+    },
+    {
+      "epoch": 0.0534045393858478,
+      "grad_norm": 1.8015997607023646,
+      "learning_rate": 5.263157894736842e-07,
+      "loss": 0.25514787435531616,
+      "step": 20,
+      "token_acc": 0.9130326509475708
+    },
+    {
+      "epoch": 0.056074766355140186,
+      "grad_norm": 2.035015371048587,
+      "learning_rate": 5.526315789473684e-07,
+      "loss": 0.2909744381904602,
+      "step": 21,
+      "token_acc": 0.9003694653511047
+    },
+    {
+      "epoch": 0.05874499332443257,
+      "grad_norm": 2.0004637405320915,
+      "learning_rate": 5.789473684210526e-07,
+      "loss": 0.2523571252822876,
+      "step": 22,
+      "token_acc": 0.9120694398880005
+    },
+    {
+      "epoch": 0.06141522029372497,
+      "grad_norm": 1.9598295001798558,
+      "learning_rate": 6.052631578947368e-07,
+      "loss": 0.278420090675354,
+      "step": 23,
+      "token_acc": 0.9019384384155273
+    },
+    {
+      "epoch": 0.06408544726301736,
+      "grad_norm": 2.306469718224025,
+      "learning_rate": 6.31578947368421e-07,
+      "loss": 0.3168449103832245,
+      "step": 24,
+      "token_acc": 0.891960859298706
+    },
+    {
+      "epoch": 0.06675567423230974,
+      "grad_norm": 1.9549723336961056,
+      "learning_rate": 6.578947368421053e-07,
+      "loss": 0.29919713735580444,
+      "step": 25,
+      "token_acc": 0.8988168239593506
+    },
+    {
+      "epoch": 0.06942590120160214,
+      "grad_norm": 2.204973447012706,
+      "learning_rate": 6.842105263157895e-07,
+      "loss": 0.30219873785972595,
+      "step": 26,
+      "token_acc": 0.8951157331466675
+    },
+    {
+      "epoch": 0.07209612817089453,
+      "grad_norm": 2.1137755456479246,
+      "learning_rate": 7.105263157894736e-07,
+      "loss": 0.32081568241119385,
+      "step": 27,
+      "token_acc": 0.8894182443618774
+    },
+    {
+      "epoch": 0.07476635514018691,
+      "grad_norm": 1.963912907154658,
+      "learning_rate": 7.368421052631578e-07,
+      "loss": 0.2685396671295166,
+      "step": 28,
+      "token_acc": 0.9070482850074768
+    },
+    {
+      "epoch": 0.0774365821094793,
+      "grad_norm": 1.9174650290604769,
+      "learning_rate": 7.631578947368421e-07,
+      "loss": 0.2495124489068985,
+      "step": 29,
+      "token_acc": 0.913847029209137
+    },
+    {
+      "epoch": 0.0801068090787717,
+      "grad_norm": 2.1561668568669656,
+      "learning_rate": 7.894736842105263e-07,
+      "loss": 0.33204522728919983,
+      "step": 30,
+      "token_acc": 0.8869137167930603
+    },
+    {
+      "epoch": 0.08277703604806408,
+      "grad_norm": 1.83390274886711,
+      "learning_rate": 8.157894736842105e-07,
+      "loss": 0.24169915914535522,
+      "step": 31,
+      "token_acc": 0.9187971949577332
+    },
+    {
+      "epoch": 0.08544726301735647,
+      "grad_norm": 1.934184725030474,
+      "learning_rate": 8.421052631578947e-07,
+      "loss": 0.2682197690010071,
+      "step": 32,
+      "token_acc": 0.9073359370231628
+    },
+    {
+      "epoch": 0.08811748998664887,
+      "grad_norm": 2.1319329471646205,
+      "learning_rate": 8.684210526315789e-07,
+      "loss": 0.32076287269592285,
+      "step": 33,
+      "token_acc": 0.8889033794403076
+    },
+    {
+      "epoch": 0.09078771695594126,
+      "grad_norm": 1.9039804712751485,
+      "learning_rate": 8.947368421052631e-07,
+      "loss": 0.2996390163898468,
+      "step": 34,
+      "token_acc": 0.897696852684021
+    },
+    {
+      "epoch": 0.09345794392523364,
+      "grad_norm": 2.1222753497505327,
+      "learning_rate": 9.210526315789473e-07,
+      "loss": 0.3413154184818268,
+      "step": 35,
+      "token_acc": 0.8827022314071655
+    },
+    {
+      "epoch": 0.09612817089452604,
+      "grad_norm": 1.9035047621565158,
+      "learning_rate": 9.473684210526315e-07,
+      "loss": 0.289617121219635,
+      "step": 36,
+      "token_acc": 0.8978717923164368
+    },
+    {
+      "epoch": 0.09879839786381843,
+      "grad_norm": 2.0040228958712496,
+      "learning_rate": 9.736842105263158e-07,
+      "loss": 0.28590112924575806,
+      "step": 37,
+      "token_acc": 0.9044703841209412
+    },
+    {
+      "epoch": 0.10146862483311081,
+      "grad_norm": 1.9737081618902141,
+      "learning_rate": 1e-06,
+      "loss": 0.27512872219085693,
+      "step": 38,
+      "token_acc": 0.9058888554573059
+    },
+    {
+      "epoch": 0.1041388518024032,
+      "grad_norm": 1.9623848628790026,
+      "learning_rate": 9.99995132801459e-07,
+      "loss": 0.2919550836086273,
+      "step": 39,
+      "token_acc": 0.8993710875511169
+    },
+    {
+      "epoch": 0.1068090787716956,
+      "grad_norm": 1.9206168636676457,
+      "learning_rate": 9.999805313005944e-07,
+      "loss": 0.28359419107437134,
+      "step": 40,
+      "token_acc": 0.9032085537910461
+    },
+    {
+      "epoch": 0.10947930574098798,
+      "grad_norm": 1.968773734960132,
+      "learning_rate": 9.999561957816803e-07,
+      "loss": 0.2929159998893738,
+      "step": 41,
+      "token_acc": 0.902581512928009
+    },
+    {
+      "epoch": 0.11214953271028037,
+      "grad_norm": 2.0939079738095994,
+      "learning_rate": 9.999221267184993e-07,
+      "loss": 0.33782684803009033,
+      "step": 42,
+      "token_acc": 0.8860743641853333
+    },
+    {
+      "epoch": 0.11481975967957277,
+      "grad_norm": 1.9445935411852595,
+      "learning_rate": 9.998783247743352e-07,
+      "loss": 0.2941400408744812,
+      "step": 43,
+      "token_acc": 0.8978437781333923
+    },
+    {
+      "epoch": 0.11748998664886515,
+      "grad_norm": 1.8997615450397891,
+      "learning_rate": 9.998247908019592e-07,
+      "loss": 0.27480724453926086,
+      "step": 44,
+      "token_acc": 0.9086644649505615
+    },
+    {
+      "epoch": 0.12016021361815754,
+      "grad_norm": 2.0338650573069765,
+      "learning_rate": 9.997615258436129e-07,
+      "loss": 0.27028927206993103,
+      "step": 45,
+      "token_acc": 0.9105998873710632
+    },
+    {
+      "epoch": 0.12283044058744993,
+      "grad_norm": 2.27559752670308,
+      "learning_rate": 9.996885311309891e-07,
+      "loss": 0.34857773780822754,
+      "step": 46,
+      "token_acc": 0.8826408982276917
+    },
+    {
+      "epoch": 0.12550066755674233,
+      "grad_norm": 1.9813742092607516,
+      "learning_rate": 9.996058080852065e-07,
+      "loss": 0.25524431467056274,
+      "step": 47,
+      "token_acc": 0.9136555194854736
+    },
+    {
+      "epoch": 0.12817089452603472,
+      "grad_norm": 2.0029263389497083,
+      "learning_rate": 9.995133583167832e-07,
+      "loss": 0.2728049159049988,
+      "step": 48,
+      "token_acc": 0.908439040184021
+    },
+    {
+      "epoch": 0.1308411214953271,
+      "grad_norm": 2.2164476489935283,
+      "learning_rate": 9.994111836256047e-07,
+      "loss": 0.33307817578315735,
+      "step": 49,
+      "token_acc": 0.886217474937439
+    },
+    {
+      "epoch": 0.13351134846461948,
+      "grad_norm": 1.988127348898823,
+      "learning_rate": 9.99299286000889e-07,
+      "loss": 0.26605021953582764,
+      "step": 50,
+      "token_acc": 0.9067342877388
+    },
+    {
+      "epoch": 0.13618157543391188,
+      "grad_norm": 2.0426312893258967,
+      "learning_rate": 9.991776676211482e-07,
+      "loss": 0.2621910870075226,
+      "step": 51,
+      "token_acc": 0.9099650382995605
+    },
+    {
+      "epoch": 0.13885180240320427,
+      "grad_norm": 2.186328690061223,
+      "learning_rate": 9.99046330854145e-07,
+      "loss": 0.3310551941394806,
+      "step": 52,
+      "token_acc": 0.8891703486442566
+    },
+    {
+      "epoch": 0.14152202937249667,
+      "grad_norm": 2.2501030270312445,
+      "learning_rate": 9.989052782568483e-07,
+      "loss": 0.3377118706703186,
+      "step": 53,
+      "token_acc": 0.8840988278388977
+    },
+    {
+      "epoch": 0.14419225634178906,
+      "grad_norm": 1.856160028155973,
+      "learning_rate": 9.987545125753819e-07,
+      "loss": 0.2430504411458969,
+      "step": 54,
+      "token_acc": 0.914770245552063
+    },
+    {
+      "epoch": 0.14686248331108145,
+      "grad_norm": 2.149975928886827,
+      "learning_rate": 9.985940367449719e-07,
+      "loss": 0.297360897064209,
+      "step": 55,
+      "token_acc": 0.8971989750862122
+    },
+    {
+      "epoch": 0.14953271028037382,
+      "grad_norm": 2.2105718754306674,
+      "learning_rate": 9.984238538898889e-07,
+      "loss": 0.28025373816490173,
+      "step": 56,
+      "token_acc": 0.9085257649421692
+    },
+    {
+      "epoch": 0.15220293724966621,
+      "grad_norm": 2.013235495313622,
+      "learning_rate": 9.982439673233882e-07,
+      "loss": 0.27504122257232666,
+      "step": 57,
+      "token_acc": 0.9029523730278015
+    },
+    {
+      "epoch": 0.1548731642189586,
+      "grad_norm": 2.052627655403584,
+      "learning_rate": 9.980543805476444e-07,
+      "loss": 0.28197458386421204,
+      "step": 58,
+      "token_acc": 0.903124988079071
+    },
+    {
+      "epoch": 0.157543391188251,
+      "grad_norm": 2.1258457736876,
+      "learning_rate": 9.978550972536833e-07,
+      "loss": 0.3123345375061035,
+      "step": 59,
+      "token_acc": 0.8902980089187622
+    },
+    {
+      "epoch": 0.1602136181575434,
+      "grad_norm": 2.4665036804490503,
+      "learning_rate": 9.976461213213104e-07,
+      "loss": 0.3396916091442108,
+      "step": 60,
+      "token_acc": 0.8877873420715332
+    },
+    {
+      "epoch": 0.1628838451268358,
+      "grad_norm": 2.1110101326332535,
+      "learning_rate": 9.974274568190347e-07,
+      "loss": 0.27996891736984253,
+      "step": 61,
+      "token_acc": 0.9012328386306763
+    },
+    {
+      "epoch": 0.16555407209612816,
+      "grad_norm": 2.0031024805135886,
+      "learning_rate": 9.97199108003991e-07,
+      "loss": 0.27917569875717163,
+      "step": 62,
+      "token_acc": 0.9070866107940674
+    },
+    {
+      "epoch": 0.16822429906542055,
+      "grad_norm": 2.017228388688339,
+      "learning_rate": 9.969610793218548e-07,
+      "loss": 0.3146962523460388,
+      "step": 63,
+      "token_acc": 0.8920899629592896
+    },
+    {
+      "epoch": 0.17089452603471295,
+      "grad_norm": 1.9853623407238012,
+      "learning_rate": 9.96713375406758e-07,
+      "loss": 0.27347612380981445,
+      "step": 64,
+      "token_acc": 0.9051504731178284
+    },
+    {
+      "epoch": 0.17356475300400534,
+      "grad_norm": 2.0193788946558295,
+      "learning_rate": 9.96456001081197e-07,
+      "loss": 0.272411584854126,
+      "step": 65,
+      "token_acc": 0.9067011475563049
+    },
+    {
+      "epoch": 0.17623497997329773,
+      "grad_norm": 2.009024094737883,
+      "learning_rate": 9.961889613559395e-07,
+      "loss": 0.29985183477401733,
+      "step": 66,
+      "token_acc": 0.8962709903717041
+    },
+    {
+      "epoch": 0.17890520694259013,
+      "grad_norm": 2.024554591314297,
+      "learning_rate": 9.95912261429927e-07,
+      "loss": 0.24555927515029907,
+      "step": 67,
+      "token_acc": 0.9135638475418091
+    },
+    {
+      "epoch": 0.18157543391188252,
+      "grad_norm": 2.034615538253845,
+      "learning_rate": 9.95625906690173e-07,
+      "loss": 0.2634598910808563,
+      "step": 68,
+      "token_acc": 0.9094334244728088
+    },
+    {
+      "epoch": 0.1842456608811749,
+      "grad_norm": 1.9767474105978162,
+      "learning_rate": 9.953299027116598e-07,
+      "loss": 0.28823843598365784,
+      "step": 69,
+      "token_acc": 0.9032171368598938
+    },
+    {
+      "epoch": 0.18691588785046728,
+      "grad_norm": 1.8735106614705168,
+      "learning_rate": 9.950242552572272e-07,
+      "loss": 0.2542210817337036,
+      "step": 70,
+      "token_acc": 0.9108684062957764
+    },
+    {
+      "epoch": 0.18958611481975968,
+      "grad_norm": 2.036772322761855,
+      "learning_rate": 9.94708970277463e-07,
+      "loss": 0.28547602891921997,
+      "step": 71,
+      "token_acc": 0.9063335061073303
+    },
+    {
+      "epoch": 0.19225634178905207,
+      "grad_norm": 1.9800337346911947,
+      "learning_rate": 9.943840539105852e-07,
+      "loss": 0.2717408239841461,
+      "step": 72,
+      "token_acc": 0.9057577252388
+    },
+    {
+      "epoch": 0.19492656875834447,
+      "grad_norm": 2.0420291874443786,
+      "learning_rate": 9.94049512482324e-07,
+      "loss": 0.2638583183288574,
+      "step": 73,
+      "token_acc": 0.9061511158943176
+    },
+    {
+      "epoch": 0.19759679572763686,
+      "grad_norm": 2.091489102730458,
+      "learning_rate": 9.937053525057975e-07,
+      "loss": 0.2873009443283081,
+      "step": 74,
+      "token_acc": 0.9003831148147583
+    },
+    {
+      "epoch": 0.20026702269692923,
+      "grad_norm": 2.1453563434574208,
+      "learning_rate": 9.933515806813855e-07,
+      "loss": 0.30442729592323303,
+      "step": 75,
+      "token_acc": 0.8918182849884033
+    },
+    {
+      "epoch": 0.20293724966622162,
+      "grad_norm": 1.9637645715795367,
+      "learning_rate": 9.929882038965987e-07,
+      "loss": 0.25732240080833435,
+      "step": 76,
+      "token_acc": 0.9138244986534119
+    },
+    {
+      "epoch": 0.205607476635514,
+      "grad_norm": 2.099229622085437,
+      "learning_rate": 9.92615229225945e-07,
+      "loss": 0.2833975851535797,
+      "step": 77,
+      "token_acc": 0.9009901285171509
+    },
+    {
+      "epoch": 0.2082777036048064,
+      "grad_norm": 1.8957331315756374,
+      "learning_rate": 9.922326639307916e-07,
+      "loss": 0.2727411389350891,
+      "step": 78,
+      "token_acc": 0.9081564545631409
+    },
+    {
+      "epoch": 0.2109479305740988,
+      "grad_norm": 1.9846784707726282,
+      "learning_rate": 9.918405154592232e-07,
+      "loss": 0.27812206745147705,
+      "step": 79,
+      "token_acc": 0.9048675298690796
+    },
+    {
+      "epoch": 0.2136181575433912,
+      "grad_norm": 2.071063245671283,
+      "learning_rate": 9.914387914458982e-07,
+      "loss": 0.3006765842437744,
+      "step": 80,
+      "token_acc": 0.8994805216789246
+    },
+    {
+      "epoch": 0.2162883845126836,
+      "grad_norm": 1.9820172860920908,
+      "learning_rate": 9.91027499711898e-07,
+      "loss": 0.26500487327575684,
+      "step": 81,
+      "token_acc": 0.9102423191070557
+    },
+    {
+      "epoch": 0.21895861148197596,
+      "grad_norm": 2.0146999948359983,
+      "learning_rate": 9.906066482645772e-07,
+      "loss": 0.28208765387535095,
+      "step": 82,
+      "token_acc": 0.9040833115577698
+    },
+    {
+      "epoch": 0.22162883845126835,
+      "grad_norm": 2.1705931558762934,
+      "learning_rate": 9.90176245297406e-07,
+      "loss": 0.3076593279838562,
+      "step": 83,
+      "token_acc": 0.8957103490829468
+    },
+    {
+      "epoch": 0.22429906542056074,
+      "grad_norm": 2.155100741152064,
+      "learning_rate": 9.897362991898109e-07,
+      "loss": 0.2756385803222656,
+      "step": 84,
+      "token_acc": 0.9062628746032715
+    },
+    {
+      "epoch": 0.22696929238985314,
+      "grad_norm": 2.3400134865351836,
+      "learning_rate": 9.892868185070124e-07,
+      "loss": 0.34368112683296204,
+      "step": 85,
+      "token_acc": 0.8848553895950317
+    },
+    {
+      "epoch": 0.22963951935914553,
+      "grad_norm": 2.045152918376272,
+      "learning_rate": 9.888278119998571e-07,
+      "loss": 0.2781244218349457,
+      "step": 86,
+      "token_acc": 0.9003152847290039
+    },
+    {
+      "epoch": 0.23230974632843793,
+      "grad_norm": 2.0709803861020872,
+      "learning_rate": 9.883592886046486e-07,
+      "loss": 0.29732224345207214,
+      "step": 87,
+      "token_acc": 0.8998661041259766
+    },
+    {
+      "epoch": 0.2349799732977303,
+      "grad_norm": 2.1066489053413617,
+      "learning_rate": 9.87881257442972e-07,
+      "loss": 0.28798672556877136,
+      "step": 88,
+      "token_acc": 0.9025964736938477
+    },
+    {
+      "epoch": 0.2376502002670227,
+      "grad_norm": 2.043215147566917,
+      "learning_rate": 9.87393727821518e-07,
+      "loss": 0.28585904836654663,
+      "step": 89,
+      "token_acc": 0.905210018157959
+    },
+    {
+      "epoch": 0.24032042723631508,
+      "grad_norm": 2.042576303652593,
+      "learning_rate": 9.868967092319e-07,
+      "loss": 0.28453588485717773,
+      "step": 90,
+      "token_acc": 0.9018221497535706
+    },
+    {
+      "epoch": 0.24299065420560748,
+      "grad_norm": 2.179822211227159,
+      "learning_rate": 9.863902113504713e-07,
+      "loss": 0.3298967480659485,
+      "step": 91,
+      "token_acc": 0.8865199685096741
+    },
+    {
+      "epoch": 0.24566088117489987,
+      "grad_norm": 1.9722208598350623,
+      "learning_rate": 9.858742440381342e-07,
+      "loss": 0.28196680545806885,
+      "step": 92,
+      "token_acc": 0.904951274394989
+    },
+    {
+      "epoch": 0.24833110814419226,
+      "grad_norm": 2.176401365128862,
+      "learning_rate": 9.853488173401503e-07,
+      "loss": 0.32774943113327026,
+      "step": 93,
+      "token_acc": 0.8895401954650879
+    },
+    {
+      "epoch": 0.25100133511348466,
+      "grad_norm": 2.049487249137693,
+      "learning_rate": 9.84813941485944e-07,
+      "loss": 0.28123170137405396,
+      "step": 94,
+      "token_acc": 0.9042264819145203
+    },
+    {
+      "epoch": 0.253671562082777,
+      "grad_norm": 1.9825299468183681,
+      "learning_rate": 9.84269626888903e-07,
+      "loss": 0.29454779624938965,
+      "step": 95,
+      "token_acc": 0.8962022066116333
+    },
+    {
+      "epoch": 0.25634178905206945,
+      "grad_norm": 2.0057548281156636,
+      "learning_rate": 9.837158841461765e-07,
+      "loss": 0.2560465931892395,
+      "step": 96,
+      "token_acc": 0.911833643913269
+    },
+    {
+      "epoch": 0.2590120160213618,
+      "grad_norm": 2.228901501766708,
+      "learning_rate": 9.831527240384676e-07,
+      "loss": 0.2780058681964874,
+      "step": 97,
+      "token_acc": 0.9022228717803955
+    },
+    {
+      "epoch": 0.2616822429906542,
+      "grad_norm": 1.93457767430555,
+      "learning_rate": 9.825801575298247e-07,
+      "loss": 0.2581782639026642,
+      "step": 98,
+      "token_acc": 0.9111502766609192
+    },
+    {
+      "epoch": 0.2643524699599466,
+      "grad_norm": 2.0224064917633244,
+      "learning_rate": 9.819981957674273e-07,
+      "loss": 0.2692886292934418,
+      "step": 99,
+      "token_acc": 0.9057348370552063
+    },
+    {
+      "epoch": 0.26702269692923897,
+      "grad_norm": 1.8443879162615453,
+      "learning_rate": 9.81406850081369e-07,
+      "loss": 0.2545507252216339,
+      "step": 100,
+      "token_acc": 0.9119937419891357
+    },
+    {
+      "epoch": 0.2696929238985314,
+      "grad_norm": 2.0375860154811276,
+      "learning_rate": 9.808061319844375e-07,
+      "loss": 0.26217329502105713,
+      "step": 101,
+      "token_acc": 0.9107729196548462
+    },
+    {
+      "epoch": 0.27236315086782376,
+      "grad_norm": 1.9571917146708497,
+      "learning_rate": 9.801960531718896e-07,
+      "loss": 0.26094985008239746,
+      "step": 102,
+      "token_acc": 0.9048815965652466
+    },
+    {
+      "epoch": 0.2750333778371162,
+      "grad_norm": 2.114520949286295,
+      "learning_rate": 9.795766255212242e-07,
+      "loss": 0.26770779490470886,
+      "step": 103,
+      "token_acc": 0.9063426852226257
+    },
+    {
+      "epoch": 0.27770360480640854,
+      "grad_norm": 2.193049585152913,
+      "learning_rate": 9.789478610919507e-07,
+      "loss": 0.3146654963493347,
+      "step": 104,
+      "token_acc": 0.8883495330810547
+    },
+    {
+      "epoch": 0.2803738317757009,
+      "grad_norm": 2.0521256715383944,
+      "learning_rate": 9.783097721253542e-07,
+      "loss": 0.29249003529548645,
+      "step": 105,
+      "token_acc": 0.8996078372001648
+    },
+    {
+      "epoch": 0.28304405874499333,
+      "grad_norm": 2.041792002418703,
+      "learning_rate": 9.776623710442578e-07,
+      "loss": 0.2624518871307373,
+      "step": 106,
+      "token_acc": 0.9059053659439087
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 2.047676212756342,
+      "learning_rate": 9.770056704527795e-07,
+      "loss": 0.2711363434791565,
+      "step": 107,
+      "token_acc": 0.9088735580444336
+    },
+    {
+      "epoch": 0.2883845126835781,
+      "grad_norm": 1.9644840552758163,
+      "learning_rate": 9.763396831360883e-07,
+      "loss": 0.2520318031311035,
+      "step": 108,
+      "token_acc": 0.9115220308303833
+    },
+    {
+      "epoch": 0.2910547396528705,
+      "grad_norm": 2.2624904317859396,
+      "learning_rate": 9.756644220601539e-07,
+      "loss": 0.3736035227775574,
+      "step": 109,
+      "token_acc": 0.8751677870750427
+    },
+    {
+      "epoch": 0.2937249666221629,
+      "grad_norm": 1.9603725943040955,
+      "learning_rate": 9.749799003714954e-07,
+      "loss": 0.2481195479631424,
+      "step": 110,
+      "token_acc": 0.9106988906860352
+    },
+    {
+      "epoch": 0.2963951935914553,
+      "grad_norm": 1.9902058068812931,
+      "learning_rate": 9.742861313969244e-07,
+      "loss": 0.27895647287368774,
+      "step": 111,
+      "token_acc": 0.9055687189102173
+    },
+    {
+      "epoch": 0.29906542056074764,
+      "grad_norm": 2.092054785236164,
+      "learning_rate": 9.735831286432867e-07,
+      "loss": 0.26457053422927856,
+      "step": 112,
+      "token_acc": 0.9074074029922485
+    },
+    {
+      "epoch": 0.30173564753004006,
+      "grad_norm": 1.9292743637456624,
+      "learning_rate": 9.728709057971978e-07,
+      "loss": 0.283307284116745,
+      "step": 113,
+      "token_acc": 0.9042354822158813
+    },
+    {
+      "epoch": 0.30440587449933243,
+      "grad_norm": 2.131919883674476,
+      "learning_rate": 9.721494767247778e-07,
+      "loss": 0.30241408944129944,
+      "step": 114,
+      "token_acc": 0.895821750164032
+    },
+    {
+      "epoch": 0.30707610146862485,
+      "grad_norm": 2.116942497198985,
+      "learning_rate": 9.714188554713809e-07,
+      "loss": 0.28302961587905884,
+      "step": 115,
+      "token_acc": 0.9014468789100647
+    },
+    {
+      "epoch": 0.3097463284379172,
+      "grad_norm": 2.030485728076968,
+      "learning_rate": 9.706790562613219e-07,
+      "loss": 0.2762414813041687,
+      "step": 116,
+      "token_acc": 0.9078947305679321
+    },
+    {
+      "epoch": 0.31241655540720964,
+      "grad_norm": 2.3457440218954604,
+      "learning_rate": 9.69930093497599e-07,
+      "loss": 0.35294246673583984,
+      "step": 117,
+      "token_acc": 0.8807643055915833
+    },
+    {
+      "epoch": 0.315086782376502,
+      "grad_norm": 2.0834113859654124,
+      "learning_rate": 9.691719817616146e-07,
+      "loss": 0.2757259011268616,
+      "step": 118,
+      "token_acc": 0.9045745730400085
+    },
+    {
+      "epoch": 0.3177570093457944,
+      "grad_norm": 2.1683244653031033,
+      "learning_rate": 9.6840473581289e-07,
+      "loss": 0.2887856364250183,
+      "step": 119,
+      "token_acc": 0.900875449180603
+    },
+    {
+      "epoch": 0.3204272363150868,
+      "grad_norm": 1.9858309695418563,
+      "learning_rate": 9.676283705887782e-07,
+      "loss": 0.2847362756729126,
+      "step": 120,
+      "token_acc": 0.8988352417945862
+    },
+    {
+      "epoch": 0.32309746328437916,
+      "grad_norm": 2.0946153675364085,
+      "learning_rate": 9.668429012041742e-07,
+      "loss": 0.2837921380996704,
+      "step": 121,
+      "token_acc": 0.8995781540870667
+    },
+    {
+      "epoch": 0.3257676902536716,
+      "grad_norm": 2.3669715999918717,
+      "learning_rate": 9.660483429512197e-07,
+      "loss": 0.3138241767883301,
+      "step": 122,
+      "token_acc": 0.8933694362640381
+    },
+    {
+      "epoch": 0.32843791722296395,
+      "grad_norm": 2.055429482354375,
+      "learning_rate": 9.65244711299006e-07,
+      "loss": 0.28169652819633484,
+      "step": 123,
+      "token_acc": 0.901455283164978
+    },
+    {
+      "epoch": 0.3311081441922563,
+      "grad_norm": 2.1715928738819303,
+      "learning_rate": 9.64432021893272e-07,
+      "loss": 0.30985116958618164,
+      "step": 124,
+      "token_acc": 0.8955163955688477
+    },
+    {
+      "epoch": 0.33377837116154874,
+      "grad_norm": 2.0652079629612103,
+      "learning_rate": 9.636102905561009e-07,
+      "loss": 0.27775973081588745,
+      "step": 125,
+      "token_acc": 0.9038885831832886
+    },
+    {
+      "epoch": 0.3364485981308411,
+      "grad_norm": 2.142124880954936,
+      "learning_rate": 9.627795332856105e-07,
+      "loss": 0.3164516091346741,
+      "step": 126,
+      "token_acc": 0.8921861052513123
+    },
+    {
+      "epoch": 0.3391188251001335,
+      "grad_norm": 2.1515598285283515,
+      "learning_rate": 9.619397662556433e-07,
+      "loss": 0.2852811813354492,
+      "step": 127,
+      "token_acc": 0.9038435220718384
+    },
+    {
+      "epoch": 0.3417890520694259,
+      "grad_norm": 2.201802419943282,
+      "learning_rate": 9.61091005815451e-07,
+      "loss": 0.27712443470954895,
+      "step": 128,
+      "token_acc": 0.9052984118461609
+    },
+    {
+      "epoch": 0.3444592790387183,
+      "grad_norm": 2.1701744486157093,
+      "learning_rate": 9.602332684893753e-07,
+      "loss": 0.29993969202041626,
+      "step": 129,
+      "token_acc": 0.8977678418159485
+    },
+    {
+      "epoch": 0.3471295060080107,
+      "grad_norm": 1.945715776491057,
+      "learning_rate": 9.59366570976528e-07,
+      "loss": 0.27031439542770386,
+      "step": 130,
+      "token_acc": 0.9064964056015015
+    },
+    {
+      "epoch": 0.34979973297730305,
+      "grad_norm": 2.237917034425781,
+      "learning_rate": 9.584909301504647e-07,
+      "loss": 0.3292759656906128,
+      "step": 131,
+      "token_acc": 0.8874327540397644
+    },
+    {
+      "epoch": 0.35246995994659547,
+      "grad_norm": 2.220946598041456,
+      "learning_rate": 9.576063630588561e-07,
+      "loss": 0.28899306058883667,
+      "step": 132,
+      "token_acc": 0.8999470472335815
+    },
+    {
+      "epoch": 0.35514018691588783,
+      "grad_norm": 1.964872291678879,
+      "learning_rate": 9.567128869231573e-07,
+      "loss": 0.260934978723526,
+      "step": 133,
+      "token_acc": 0.9110655784606934
+    },
+    {
+      "epoch": 0.35781041388518026,
+      "grad_norm": 2.1044365033481927,
+      "learning_rate": 9.558105191382709e-07,
+      "loss": 0.27269411087036133,
+      "step": 134,
+      "token_acc": 0.9068365693092346
+    },
+    {
+      "epoch": 0.3604806408544726,
+      "grad_norm": 2.028836470288063,
+      "learning_rate": 9.548992772722095e-07,
+      "loss": 0.3081006109714508,
+      "step": 135,
+      "token_acc": 0.8965258002281189
+    },
+    {
+      "epoch": 0.36315086782376504,
+      "grad_norm": 2.1235781095151247,
+      "learning_rate": 9.539791790657537e-07,
+      "loss": 0.2778942883014679,
+      "step": 136,
+      "token_acc": 0.9059348702430725
+    },
+    {
+      "epoch": 0.3658210947930574,
+      "grad_norm": 2.1262418672181798,
+      "learning_rate": 9.530502424321061e-07,
+      "loss": 0.30353981256484985,
+      "step": 137,
+      "token_acc": 0.8970588445663452
+    },
+    {
+      "epoch": 0.3684913217623498,
+      "grad_norm": 2.0151038892577025,
+      "learning_rate": 9.521124854565424e-07,
+      "loss": 0.25289449095726013,
+      "step": 138,
+      "token_acc": 0.9106636643409729
+    },
+    {
+      "epoch": 0.3711615487316422,
+      "grad_norm": 2.017995531367294,
+      "learning_rate": 9.511659263960605e-07,
+      "loss": 0.257360577583313,
+      "step": 139,
+      "token_acc": 0.9096828103065491
+    },
+    {
+      "epoch": 0.37383177570093457,
+      "grad_norm": 2.092910509085539,
+      "learning_rate": 9.502105836790239e-07,
+      "loss": 0.27082905173301697,
+      "step": 140,
+      "token_acc": 0.9072591662406921
+    },
+    {
+      "epoch": 0.376502002670227,
+      "grad_norm": 1.9603946729125645,
+      "learning_rate": 9.492464759048031e-07,
+      "loss": 0.26478639245033264,
+      "step": 141,
+      "token_acc": 0.9146782159805298
+    },
+    {
+      "epoch": 0.37917222963951935,
+      "grad_norm": 2.342956496545118,
+      "learning_rate": 9.482736218434142e-07,
+      "loss": 0.35170528292655945,
+      "step": 142,
+      "token_acc": 0.8754468560218811
+    },
+    {
+      "epoch": 0.3818424566088118,
+      "grad_norm": 1.8312196258517395,
+      "learning_rate": 9.472920404351525e-07,
+      "loss": 0.22101420164108276,
+      "step": 143,
+      "token_acc": 0.9251171946525574
+    },
+    {
+      "epoch": 0.38451268357810414,
+      "grad_norm": 1.9369699559043088,
+      "learning_rate": 9.463017507902243e-07,
+      "loss": 0.24200518429279327,
+      "step": 144,
+      "token_acc": 0.9178212285041809
+    },
+    {
+      "epoch": 0.3871829105473965,
+      "grad_norm": 2.0531422374054316,
+      "learning_rate": 9.45302772188375e-07,
+      "loss": 0.28301361203193665,
+      "step": 145,
+      "token_acc": 0.9043102264404297
+    },
+    {
+      "epoch": 0.38985313751668893,
+      "grad_norm": 2.1902722491257944,
+      "learning_rate": 9.442951240785134e-07,
+      "loss": 0.2892805337905884,
+      "step": 146,
+      "token_acc": 0.9019408822059631
+    },
+    {
+      "epoch": 0.3925233644859813,
+      "grad_norm": 1.9616664217550528,
+      "learning_rate": 9.432788260783331e-07,
+      "loss": 0.27799805998802185,
+      "step": 147,
+      "token_acc": 0.9004296064376831
+    },
+    {
+      "epoch": 0.3951935914552737,
+      "grad_norm": 1.9378527531472054,
+      "learning_rate": 9.422538979739307e-07,
+      "loss": 0.26660919189453125,
+      "step": 148,
+      "token_acc": 0.9097912311553955
+    },
+    {
+      "epoch": 0.3978638184245661,
+      "grad_norm": 2.1071583756124417,
+      "learning_rate": 9.412203597194203e-07,
+      "loss": 0.29787540435791016,
+      "step": 149,
+      "token_acc": 0.8992995619773865
+    },
+    {
+      "epoch": 0.40053404539385845,
+      "grad_norm": 2.104686332400675,
+      "learning_rate": 9.401782314365457e-07,
+      "loss": 0.29401588439941406,
+      "step": 150,
+      "token_acc": 0.9021447896957397
+    },
+    {
+      "epoch": 0.4032042723631509,
+      "grad_norm": 2.2031310393686376,
+      "learning_rate": 9.391275334142877e-07,
+      "loss": 0.30388614535331726,
+      "step": 151,
+      "token_acc": 0.897716760635376
+    },
+    {
+      "epoch": 0.40587449933244324,
+      "grad_norm": 2.112903547033423,
+      "learning_rate": 9.380682861084701e-07,
+      "loss": 0.2804121971130371,
+      "step": 152,
+      "token_acc": 0.8998410105705261
+    },
+    {
+      "epoch": 0.40854472630173566,
+      "grad_norm": 1.897383662170262,
+      "learning_rate": 9.370005101413604e-07,
+      "loss": 0.24239787459373474,
+      "step": 153,
+      "token_acc": 0.9168741106987
+    },
+    {
+      "epoch": 0.411214953271028,
+      "grad_norm": 2.2550083915497305,
+      "learning_rate": 9.359242263012692e-07,
+      "loss": 0.298775851726532,
+      "step": 154,
+      "token_acc": 0.8977326154708862
+    },
+    {
+      "epoch": 0.41388518024032045,
+      "grad_norm": 2.3535210740465744,
+      "learning_rate": 9.348394555421452e-07,
+      "loss": 0.36164945363998413,
+      "step": 155,
+      "token_acc": 0.881369948387146
+    },
+    {
+      "epoch": 0.4165554072096128,
+      "grad_norm": 2.1395142279506856,
+      "learning_rate": 9.337462189831668e-07,
+      "loss": 0.2830463945865631,
+      "step": 156,
+      "token_acc": 0.8988946080207825
+    },
+    {
+      "epoch": 0.4192256341789052,
+      "grad_norm": 2.180956695050801,
+      "learning_rate": 9.326445379083318e-07,
+      "loss": 0.28305861353874207,
+      "step": 157,
+      "token_acc": 0.9041095972061157
+    },
+    {
+      "epoch": 0.4218958611481976,
+      "grad_norm": 2.300128879256526,
+      "learning_rate": 9.315344337660421e-07,
+      "loss": 0.3333325982093811,
+      "step": 158,
+      "token_acc": 0.8840673565864563
+    },
+    {
+      "epoch": 0.42456608811748997,
+      "grad_norm": 2.0976651096505945,
+      "learning_rate": 9.304159281686865e-07,
+      "loss": 0.3012496829032898,
+      "step": 159,
+      "token_acc": 0.8982028365135193
+    },
+    {
+      "epoch": 0.4272363150867824,
+      "grad_norm": 1.9318424161264138,
+      "learning_rate": 9.292890428922209e-07,
+      "loss": 0.2429567575454712,
+      "step": 160,
+      "token_acc": 0.9156709313392639
+    },
+    {
+      "epoch": 0.42990654205607476,
+      "grad_norm": 2.0496205639482428,
+      "learning_rate": 9.28153799875742e-07,
+      "loss": 0.27258068323135376,
+      "step": 161,
+      "token_acc": 0.9073542356491089
+    },
+    {
+      "epoch": 0.4325767690253672,
+      "grad_norm": 2.0190831254676027,
+      "learning_rate": 9.270102212210631e-07,
+      "loss": 0.26034533977508545,
+      "step": 162,
+      "token_acc": 0.9113273024559021
+    },
+    {
+      "epoch": 0.43524699599465955,
+      "grad_norm": 2.0362076483521308,
+      "learning_rate": 9.258583291922813e-07,
+      "loss": 0.257572203874588,
+      "step": 163,
+      "token_acc": 0.9099660515785217
+    },
+    {
+      "epoch": 0.4379172229639519,
+      "grad_norm": 1.8635847352909456,
+      "learning_rate": 9.246981462153455e-07,
+      "loss": 0.20891466736793518,
+      "step": 164,
+      "token_acc": 0.9308456778526306
+    },
+    {
+      "epoch": 0.44058744993324434,
+      "grad_norm": 2.095598846118532,
+      "learning_rate": 9.235296948776193e-07,
+      "loss": 0.29129084944725037,
+      "step": 165,
+      "token_acc": 0.9001315832138062
+    },
+    {
+      "epoch": 0.4432576769025367,
+      "grad_norm": 2.4412962322167386,
+      "learning_rate": 9.22352997927441e-07,
+      "loss": 0.35161954164505005,
+      "step": 166,
+      "token_acc": 0.8803262710571289
+    },
+    {
+      "epoch": 0.4459279038718291,
+      "grad_norm": 2.126353915247583,
+      "learning_rate": 9.211680782736817e-07,
+      "loss": 0.3009125590324402,
+      "step": 167,
+      "token_acc": 0.8932995200157166
+    },
+    {
+      "epoch": 0.4485981308411215,
+      "grad_norm": 1.98699176783696,
+      "learning_rate": 9.199749589852978e-07,
+      "loss": 0.2510581612586975,
+      "step": 168,
+      "token_acc": 0.9114777445793152
+    },
+    {
+      "epoch": 0.4512683578104139,
+      "grad_norm": 2.1288099569608048,
+      "learning_rate": 9.187736632908838e-07,
+      "loss": 0.2890007793903351,
+      "step": 169,
+      "token_acc": 0.9003568887710571
+    },
+    {
+      "epoch": 0.4539385847797063,
+      "grad_norm": 2.0827234173261386,
+      "learning_rate": 9.175642145782177e-07,
+      "loss": 0.28987181186676025,
+      "step": 170,
+      "token_acc": 0.8982530832290649
+    },
+    {
+      "epoch": 0.45660881174899864,
+      "grad_norm": 1.9278471414171243,
+      "learning_rate": 9.16346636393808e-07,
+      "loss": 0.2574021816253662,
+      "step": 171,
+      "token_acc": 0.912570595741272
+    },
+    {
+      "epoch": 0.45927903871829107,
+      "grad_norm": 2.1305072436813237,
+      "learning_rate": 9.151209524424333e-07,
+      "loss": 0.2883685529232025,
+      "step": 172,
+      "token_acc": 0.8997206687927246
+    },
+    {
+      "epoch": 0.46194926568758343,
+      "grad_norm": 2.150740767956397,
+      "learning_rate": 9.138871865866823e-07,
+      "loss": 0.30160003900527954,
+      "step": 173,
+      "token_acc": 0.8961108922958374
+    },
+    {
+      "epoch": 0.46461949265687585,
+      "grad_norm": 2.0551832243214814,
+      "learning_rate": 9.126453628464887e-07,
+      "loss": 0.2776428163051605,
+      "step": 174,
+      "token_acc": 0.903631865978241
+    },
+    {
+      "epoch": 0.4672897196261682,
+      "grad_norm": 2.127592252817679,
+      "learning_rate": 9.11395505398663e-07,
+      "loss": 0.31724241375923157,
+      "step": 175,
+      "token_acc": 0.8932872414588928
+    },
+    {
+      "epoch": 0.4699599465954606,
+      "grad_norm": 1.9587878757888397,
+      "learning_rate": 9.101376385764229e-07,
+      "loss": 0.22349461913108826,
+      "step": 176,
+      "token_acc": 0.9211563467979431
+    },
+    {
+      "epoch": 0.472630173564753,
+      "grad_norm": 2.1021164123456275,
+      "learning_rate": 9.088717868689184e-07,
+      "loss": 0.2797764539718628,
+      "step": 177,
+      "token_acc": 0.9042362570762634
+    },
+    {
+      "epoch": 0.4753004005340454,
+      "grad_norm": 2.1527822414426177,
+      "learning_rate": 9.07597974920756e-07,
+      "loss": 0.30770474672317505,
+      "step": 178,
+      "token_acc": 0.890901505947113
+    },
+    {
+      "epoch": 0.4779706275033378,
+      "grad_norm": 2.227211439107605,
+      "learning_rate": 9.063162275315182e-07,
+      "loss": 0.2986774444580078,
+      "step": 179,
+      "token_acc": 0.8961575627326965
+    },
+    {
+      "epoch": 0.48064085447263016,
+      "grad_norm": 1.9482238758772856,
+      "learning_rate": 9.05026569655281e-07,
+      "loss": 0.25634706020355225,
+      "step": 180,
+      "token_acc": 0.9128828048706055
+    },
+    {
+      "epoch": 0.4833110814419226,
+      "grad_norm": 2.019180035334044,
+      "learning_rate": 9.037290264001285e-07,
+      "loss": 0.2857431173324585,
+      "step": 181,
+      "token_acc": 0.9036951065063477
+    },
+    {
+      "epoch": 0.48598130841121495,
+      "grad_norm": 2.039540842991341,
+      "learning_rate": 9.024236230276628e-07,
+      "loss": 0.27904582023620605,
+      "step": 182,
+      "token_acc": 0.90245121717453
+    },
+    {
+      "epoch": 0.4886515353805073,
+      "grad_norm": 1.9224499539200468,
+      "learning_rate": 9.011103849525138e-07,
+      "loss": 0.23901015520095825,
+      "step": 183,
+      "token_acc": 0.9161087870597839
+    },
+    {
+      "epoch": 0.49132176234979974,
+      "grad_norm": 2.1995112954359883,
+      "learning_rate": 8.997893377418431e-07,
+      "loss": 0.3141215443611145,
+      "step": 184,
+      "token_acc": 0.8933189511299133
+    },
+    {
+      "epoch": 0.4939919893190921,
+      "grad_norm": 2.03524790376963,
+      "learning_rate": 8.98460507114847e-07,
+      "loss": 0.2599041759967804,
+      "step": 185,
+      "token_acc": 0.9108665585517883
+    },
+    {
+      "epoch": 0.49666221628838453,
+      "grad_norm": 2.1934151696793824,
+      "learning_rate": 8.971239189422554e-07,
+      "loss": 0.3043036162853241,
+      "step": 186,
+      "token_acc": 0.897392749786377
+    },
+    {
+      "epoch": 0.4993324432576769,
+      "grad_norm": 2.027313224700925,
+      "learning_rate": 8.957795992458283e-07,
+      "loss": 0.2506353259086609,
+      "step": 187,
+      "token_acc": 0.9107193946838379
+    },
+    {
+      "epoch": 0.5020026702269693,
+      "grad_norm": 2.1840506853824637,
+      "learning_rate": 8.944275741978494e-07,
+      "loss": 0.29403921961784363,
+      "step": 188,
+      "token_acc": 0.9023368954658508
+    },
+    {
+      "epoch": 0.5046728971962616,
+      "grad_norm": 2.069065777442508,
+      "learning_rate": 8.930678701206158e-07,
+      "loss": 0.2814294099807739,
+      "step": 189,
+      "token_acc": 0.903212308883667
+    },
+    {
+      "epoch": 0.507343124165554,
+      "grad_norm": 2.0980217164451043,
+      "learning_rate": 8.917005134859262e-07,
+      "loss": 0.27474814653396606,
+      "step": 190,
+      "token_acc": 0.905849814414978
+    },
+    {
+      "epoch": 0.5100133511348465,
+      "grad_norm": 2.1679123494481156,
+      "learning_rate": 8.903255309145659e-07,
+      "loss": 0.29807204008102417,
+      "step": 191,
+      "token_acc": 0.8966745734214783
+    },
+    {
+      "epoch": 0.5126835781041389,
+      "grad_norm": 1.963289966274745,
+      "learning_rate": 8.889429491757871e-07,
+      "loss": 0.25021928548812866,
+      "step": 192,
+      "token_acc": 0.9116868376731873
+    },
+    {
+      "epoch": 0.5153538050734312,
+      "grad_norm": 2.038675135345026,
+      "learning_rate": 8.875527951867894e-07,
+      "loss": 0.2772940993309021,
+      "step": 193,
+      "token_acc": 0.9057261347770691
+    },
+    {
+      "epoch": 0.5180240320427236,
+      "grad_norm": 2.1926420292124376,
+      "learning_rate": 8.861550960121944e-07,
+      "loss": 0.3301735818386078,
+      "step": 194,
+      "token_acc": 0.8935492634773254
+    },
+    {
+      "epoch": 0.520694259012016,
+      "grad_norm": 2.2170092701973183,
+      "learning_rate": 8.8474987886352e-07,
+      "loss": 0.2955408990383148,
+      "step": 195,
+      "token_acc": 0.8996641635894775
+    },
+    {
+      "epoch": 0.5233644859813084,
+      "grad_norm": 2.3488267200891566,
+      "learning_rate": 8.833371710986493e-07,
+      "loss": 0.3376539647579193,
+      "step": 196,
+      "token_acc": 0.8841843008995056
+    },
+    {
+      "epoch": 0.5260347129506008,
+      "grad_norm": 2.0836111564594817,
+      "learning_rate": 8.81917000221299e-07,
+      "loss": 0.2958473563194275,
+      "step": 197,
+      "token_acc": 0.9010409116744995
+    },
+    {
+      "epoch": 0.5287049399198932,
+      "grad_norm": 2.0097936678948254,
+      "learning_rate": 8.804893938804838e-07,
+      "loss": 0.2519635558128357,
+      "step": 198,
+      "token_acc": 0.9125999212265015
+    },
+    {
+      "epoch": 0.5313751668891856,
+      "grad_norm": 2.064860277203708,
+      "learning_rate": 8.790543798699777e-07,
+      "loss": 0.25143057107925415,
+      "step": 199,
+      "token_acc": 0.9143840074539185
+    },
+    {
+      "epoch": 0.5340453938584779,
+      "grad_norm": 1.8109307314346765,
+      "learning_rate": 8.776119861277728e-07,
+      "loss": 0.21611890196800232,
+      "step": 200,
+      "token_acc": 0.925537645816803
+    },
+    {
+      "epoch": 0.5367156208277704,
+      "grad_norm": 2.074009373070621,
+      "learning_rate": 8.761622407355362e-07,
+      "loss": 0.24821993708610535,
+      "step": 201,
+      "token_acc": 0.9125162363052368
+    },
+    {
+      "epoch": 0.5393858477970628,
+      "grad_norm": 1.963150343284323,
+      "learning_rate": 8.747051719180625e-07,
+      "loss": 0.2645209729671478,
+      "step": 202,
+      "token_acc": 0.9058806896209717
+    },
+    {
+      "epoch": 0.5420560747663551,
+      "grad_norm": 1.9447822758942555,
+      "learning_rate": 8.732408080427246e-07,
+      "loss": 0.25343117117881775,
+      "step": 203,
+      "token_acc": 0.9090781807899475
+    },
+    {
+      "epoch": 0.5447263017356475,
+      "grad_norm": 2.0964914381042146,
+      "learning_rate": 8.717691776189213e-07,
+      "loss": 0.2988298833370209,
+      "step": 204,
+      "token_acc": 0.9006159901618958
+    },
+    {
+      "epoch": 0.5473965287049399,
+      "grad_norm": 2.0686377284280186,
+      "learning_rate": 8.702903092975226e-07,
+      "loss": 0.3059035539627075,
+      "step": 205,
+      "token_acc": 0.8995922803878784
+    },
+    {
+      "epoch": 0.5500667556742324,
+      "grad_norm": 2.042034720982516,
+      "learning_rate": 8.68804231870311e-07,
+      "loss": 0.271801620721817,
+      "step": 206,
+      "token_acc": 0.9063113331794739
+    },
+    {
+      "epoch": 0.5527369826435247,
+      "grad_norm": 2.009955210224807,
+      "learning_rate": 8.673109742694227e-07,
+      "loss": 0.2487180233001709,
+      "step": 207,
+      "token_acc": 0.9119566679000854
+    },
+    {
+      "epoch": 0.5554072096128171,
+      "grad_norm": 1.93659235259408,
+      "learning_rate": 8.658105655667819e-07,
+      "loss": 0.26743823289871216,
+      "step": 208,
+      "token_acc": 0.9019048810005188
+    },
+    {
+      "epoch": 0.5580774365821095,
+      "grad_norm": 2.083492896845098,
+      "learning_rate": 8.643030349735371e-07,
+      "loss": 0.27370041608810425,
+      "step": 209,
+      "token_acc": 0.903518557548523
+    },
+    {
+      "epoch": 0.5607476635514018,
+      "grad_norm": 2.0198419256393008,
+      "learning_rate": 8.627884118394912e-07,
+      "loss": 0.2470577359199524,
+      "step": 210,
+      "token_acc": 0.9145429134368896
+    },
+    {
+      "epoch": 0.5634178905206942,
+      "grad_norm": 2.0107679784780963,
+      "learning_rate": 8.612667256525304e-07,
+      "loss": 0.2682899236679077,
+      "step": 211,
+      "token_acc": 0.9062252640724182
+    },
+    {
+      "epoch": 0.5660881174899867,
+      "grad_norm": 1.9607285616367702,
+      "learning_rate": 8.597380060380493e-07,
+      "loss": 0.24268311262130737,
+      "step": 212,
+      "token_acc": 0.9190971851348877
+    },
+    {
+      "epoch": 0.5687583444592791,
+      "grad_norm": 1.9863297687953936,
+      "learning_rate": 8.582022827583757e-07,
+      "loss": 0.2645193934440613,
+      "step": 213,
+      "token_acc": 0.9063777327537537
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 2.0580265397335,
+      "learning_rate": 8.566595857121901e-07,
+      "loss": 0.29579177498817444,
+      "step": 214,
+      "token_acc": 0.8989174365997314
+    },
+    {
+      "epoch": 0.5740987983978638,
+      "grad_norm": 1.8982514572458415,
+      "learning_rate": 8.551099449339437e-07,
+      "loss": 0.24695271253585815,
+      "step": 215,
+      "token_acc": 0.9099903702735901
+    },
+    {
+      "epoch": 0.5767690253671562,
+      "grad_norm": 2.030290418644084,
+      "learning_rate": 8.535533905932737e-07,
+      "loss": 0.25805532932281494,
+      "step": 216,
+      "token_acc": 0.9088018536567688
+    },
+    {
+      "epoch": 0.5794392523364486,
+      "grad_norm": 2.1415163121399727,
+      "learning_rate": 8.519899529944165e-07,
+      "loss": 0.29200810194015503,
+      "step": 217,
+      "token_acc": 0.8979300260543823
+    },
+    {
+      "epoch": 0.582109479305741,
+      "grad_norm": 2.2026026577234123,
+      "learning_rate": 8.504196625756165e-07,
+      "loss": 0.31914186477661133,
+      "step": 218,
+      "token_acc": 0.8936260342597961
+    },
+    {
+      "epoch": 0.5847797062750334,
+      "grad_norm": 2.403539353889388,
+      "learning_rate": 8.488425499085348e-07,
+      "loss": 0.3513927757740021,
+      "step": 219,
+      "token_acc": 0.8796334862709045
+    },
+    {
+      "epoch": 0.5874499332443258,
+      "grad_norm": 1.9341872354605025,
+      "learning_rate": 8.472586456976533e-07,
+      "loss": 0.2565155029296875,
+      "step": 220,
+      "token_acc": 0.9108741283416748
+    },
+    {
+      "epoch": 0.5901201602136181,
+      "grad_norm": 2.219988490386098,
+      "learning_rate": 8.456679807796774e-07,
+      "loss": 0.313397616147995,
+      "step": 221,
+      "token_acc": 0.8913969397544861
+    },
+    {
+      "epoch": 0.5927903871829105,
+      "grad_norm": 2.126825667417516,
+      "learning_rate": 8.440705861229344e-07,
+      "loss": 0.3062314987182617,
+      "step": 222,
+      "token_acc": 0.8966061472892761
+    },
+    {
+      "epoch": 0.595460614152203,
+      "grad_norm": 2.145549335562607,
+      "learning_rate": 8.424664928267723e-07,
+      "loss": 0.2909514904022217,
+      "step": 223,
+      "token_acc": 0.8999345302581787
+    },
+    {
+      "epoch": 0.5981308411214953,
+      "grad_norm": 2.154736458757084,
+      "learning_rate": 8.408557321209532e-07,
+      "loss": 0.2965439558029175,
+      "step": 224,
+      "token_acc": 0.9006565809249878
+    },
+    {
+      "epoch": 0.6008010680907877,
+      "grad_norm": 2.22101269731608,
+      "learning_rate": 8.392383353650462e-07,
+      "loss": 0.31599822640419006,
+      "step": 225,
+      "token_acc": 0.8959336280822754
+    },
+    {
+      "epoch": 0.6034712950600801,
+      "grad_norm": 2.017374834209061,
+      "learning_rate": 8.376143340478153e-07,
+      "loss": 0.2825508117675781,
+      "step": 226,
+      "token_acc": 0.8988195657730103
+    },
+    {
+      "epoch": 0.6061415220293725,
+      "grad_norm": 2.0252895258364,
+      "learning_rate": 8.359837597866079e-07,
+      "loss": 0.2903352975845337,
+      "step": 227,
+      "token_acc": 0.8991366028785706
+    },
+    {
+      "epoch": 0.6088117489986649,
+      "grad_norm": 1.9590462170436145,
+      "learning_rate": 8.343466443267389e-07,
+      "loss": 0.2520221173763275,
+      "step": 228,
+      "token_acc": 0.9108198285102844
+    },
+    {
+      "epoch": 0.6114819759679573,
+      "grad_norm": 2.0181747945649455,
+      "learning_rate": 8.327030195408722e-07,
+      "loss": 0.2754180431365967,
+      "step": 229,
+      "token_acc": 0.9030482172966003
+    },
+    {
+      "epoch": 0.6141522029372497,
+      "grad_norm": 2.1818827749384795,
+      "learning_rate": 8.310529174284002e-07,
+      "loss": 0.29679906368255615,
+      "step": 230,
+      "token_acc": 0.8976420164108276
+    },
+    {
+      "epoch": 0.616822429906542,
+      "grad_norm": 2.0283260183580323,
+      "learning_rate": 8.293963701148215e-07,
+      "loss": 0.2590368986129761,
+      "step": 231,
+      "token_acc": 0.9115363955497742
+    },
+    {
+      "epoch": 0.6194926568758344,
+      "grad_norm": 2.187594000090018,
+      "learning_rate": 8.277334098511146e-07,
+      "loss": 0.2896036207675934,
+      "step": 232,
+      "token_acc": 0.8997548222541809
+    },
+    {
+      "epoch": 0.6221628838451269,
+      "grad_norm": 1.972244203891278,
+      "learning_rate": 8.260640690131108e-07,
+      "loss": 0.26607394218444824,
+      "step": 233,
+      "token_acc": 0.9055222868919373
+    },
+    {
+      "epoch": 0.6248331108144193,
+      "grad_norm": 1.98375449613679,
+      "learning_rate": 8.243883801008631e-07,
+      "loss": 0.2682957649230957,
+      "step": 234,
+      "token_acc": 0.9040209054946899
+    },
+    {
+      "epoch": 0.6275033377837116,
+      "grad_norm": 2.0717753857684653,
+      "learning_rate": 8.227063757380139e-07,
+      "loss": 0.25457677245140076,
+      "step": 235,
+      "token_acc": 0.9050652384757996
+    },
+    {
+      "epoch": 0.630173564753004,
+      "grad_norm": 2.1145443475642285,
+      "learning_rate": 8.210180886711601e-07,
+      "loss": 0.2666376233100891,
+      "step": 236,
+      "token_acc": 0.9074863791465759
+    },
+    {
+      "epoch": 0.6328437917222964,
+      "grad_norm": 2.1098734598885396,
+      "learning_rate": 8.193235517692153e-07,
+      "loss": 0.29379966855049133,
+      "step": 237,
+      "token_acc": 0.9011536240577698
+    },
+    {
+      "epoch": 0.6355140186915887,
+      "grad_norm": 1.84607116300292,
+      "learning_rate": 8.176227980227692e-07,
+      "loss": 0.23924671113491058,
+      "step": 238,
+      "token_acc": 0.9176346063613892
+    },
+    {
+      "epoch": 0.6381842456608812,
+      "grad_norm": 1.9744450562107252,
+      "learning_rate": 8.159158605434467e-07,
+      "loss": 0.25192177295684814,
+      "step": 239,
+      "token_acc": 0.9122391939163208
+    },
+    {
+      "epoch": 0.6408544726301736,
+      "grad_norm": 2.1588699665885565,
+      "learning_rate": 8.142027725632622e-07,
+      "loss": 0.33468741178512573,
+      "step": 240,
+      "token_acc": 0.8871279358863831
+    },
+    {
+      "epoch": 0.6435246995994659,
+      "grad_norm": 2.0622425155324846,
+      "learning_rate": 8.124835674339729e-07,
+      "loss": 0.2557421922683716,
+      "step": 241,
+      "token_acc": 0.9071566462516785
+    },
+    {
+      "epoch": 0.6461949265687583,
+      "grad_norm": 1.9949890365460998,
+      "learning_rate": 8.107582786264298e-07,
+      "loss": 0.2921854853630066,
+      "step": 242,
+      "token_acc": 0.8990883231163025
+    },
+    {
+      "epoch": 0.6488651535380507,
+      "grad_norm": 2.143096734693015,
+      "learning_rate": 8.090269397299249e-07,
+      "loss": 0.3044344186782837,
+      "step": 243,
+      "token_acc": 0.8975558876991272
+    },
+    {
+      "epoch": 0.6515353805073432,
+      "grad_norm": 2.205625529587089,
+      "learning_rate": 8.072895844515397e-07,
+      "loss": 0.3088616132736206,
+      "step": 244,
+      "token_acc": 0.8966250419616699
+    },
+    {
+      "epoch": 0.6542056074766355,
+      "grad_norm": 2.1351789267863666,
+      "learning_rate": 8.055462466154861e-07,
+      "loss": 0.27560850977897644,
+      "step": 245,
+      "token_acc": 0.9061025977134705
+    },
+    {
+      "epoch": 0.6568758344459279,
+      "grad_norm": 2.055661982367164,
+      "learning_rate": 8.037969601624495e-07,
+      "loss": 0.30425381660461426,
+      "step": 246,
+      "token_acc": 0.8979963660240173
+    },
+    {
+      "epoch": 0.6595460614152203,
+      "grad_norm": 2.0251418398491285,
+      "learning_rate": 8.020417591489278e-07,
+      "loss": 0.23102325201034546,
+      "step": 247,
+      "token_acc": 0.9204157590866089
+    },
+    {
+      "epoch": 0.6622162883845126,
+      "grad_norm": 2.034728378628027,
+      "learning_rate": 8.002806777465684e-07,
+      "loss": 0.2683688998222351,
+      "step": 248,
+      "token_acc": 0.9089632034301758
+    },
+    {
+      "epoch": 0.664886515353805,
+      "grad_norm": 1.8903532309067799,
+      "learning_rate": 7.985137502415026e-07,
+      "loss": 0.2405029684305191,
+      "step": 249,
+      "token_acc": 0.9179366827011108
+    },
+    {
+      "epoch": 0.6675567423230975,
+      "grad_norm": 2.0856153041021965,
+      "learning_rate": 7.967410110336781e-07,
+      "loss": 0.2841339707374573,
+      "step": 250,
+      "token_acc": 0.9007387757301331
+    },
+    {
+      "epoch": 0.6702269692923899,
+      "grad_norm": 2.188364325133326,
+      "learning_rate": 7.949624946361899e-07,
+      "loss": 0.2878096103668213,
+      "step": 251,
+      "token_acc": 0.8945439457893372
+    },
+    {
+      "epoch": 0.6728971962616822,
+      "grad_norm": 2.032098878841245,
+      "learning_rate": 7.931782356746075e-07,
+      "loss": 0.26396405696868896,
+      "step": 252,
+      "token_acc": 0.9073431491851807
+    },
+    {
+      "epoch": 0.6755674232309746,
+      "grad_norm": 2.229703427690029,
+      "learning_rate": 7.913882688863015e-07,
+      "loss": 0.29681840538978577,
+      "step": 253,
+      "token_acc": 0.9018996357917786
+    },
+    {
+      "epoch": 0.678237650200267,
+      "grad_norm": 1.9198858811675017,
+      "learning_rate": 7.895926291197666e-07,
+      "loss": 0.23577043414115906,
+      "step": 254,
+      "token_acc": 0.9182189702987671
+    },
+    {
+      "epoch": 0.6809078771695594,
+      "grad_norm": 1.9483791012454106,
+      "learning_rate": 7.877913513339443e-07,
+      "loss": 0.26336434483528137,
+      "step": 255,
+      "token_acc": 0.9104692339897156
+    },
+    {
+      "epoch": 0.6835781041388518,
+      "grad_norm": 1.8792462228334996,
+      "learning_rate": 7.859844705975403e-07,
+      "loss": 0.24136200547218323,
+      "step": 256,
+      "token_acc": 0.9154909253120422
+    },
+    {
+      "epoch": 0.6862483311081442,
+      "grad_norm": 2.252124938045186,
+      "learning_rate": 7.841720220883446e-07,
+      "loss": 0.3361847400665283,
+      "step": 257,
+      "token_acc": 0.8817477226257324
+    },
+    {
+      "epoch": 0.6889185580774366,
+      "grad_norm": 2.135173156441192,
+      "learning_rate": 7.823540410925433e-07,
+      "loss": 0.2810385823249817,
+      "step": 258,
+      "token_acc": 0.9000142216682434
+    },
+    {
+      "epoch": 0.6915887850467289,
+      "grad_norm": 2.18671725051586,
+      "learning_rate": 7.805305630040348e-07,
+      "loss": 0.2781669497489929,
+      "step": 259,
+      "token_acc": 0.899172306060791
+    },
+    {
+      "epoch": 0.6942590120160214,
+      "grad_norm": 2.116271125976887,
+      "learning_rate": 7.787016233237387e-07,
+      "loss": 0.27820634841918945,
+      "step": 260,
+      "token_acc": 0.9025909900665283
+    },
+    {
+      "epoch": 0.6969292389853138,
+      "grad_norm": 2.172330221816804,
+      "learning_rate": 7.768672576589045e-07,
+      "loss": 0.2953495681285858,
+      "step": 261,
+      "token_acc": 0.9007132649421692
+    },
+    {
+      "epoch": 0.6995994659546061,
+      "grad_norm": 1.9557376009761065,
+      "learning_rate": 7.750275017224205e-07,
+      "loss": 0.26717841625213623,
+      "step": 262,
+      "token_acc": 0.9052304625511169
+    },
+    {
+      "epoch": 0.7022696929238985,
+      "grad_norm": 1.9785410477410086,
+      "learning_rate": 7.73182391332116e-07,
+      "loss": 0.25894221663475037,
+      "step": 263,
+      "token_acc": 0.9105163812637329
+    },
+    {
+      "epoch": 0.7049399198931909,
+      "grad_norm": 2.2734440037293,
+      "learning_rate": 7.713319624100656e-07,
+      "loss": 0.3392706513404846,
+      "step": 264,
+      "token_acc": 0.8816901445388794
+    },
+    {
+      "epoch": 0.7076101468624834,
+      "grad_norm": 2.16720227875119,
+      "learning_rate": 7.694762509818889e-07,
+      "loss": 0.29061388969421387,
+      "step": 265,
+      "token_acc": 0.896769642829895
+    },
+    {
+      "epoch": 0.7102803738317757,
+      "grad_norm": 2.026731967666324,
+      "learning_rate": 7.676152931760495e-07,
+      "loss": 0.3041936159133911,
+      "step": 266,
+      "token_acc": 0.8982451558113098
+    },
+    {
+      "epoch": 0.7129506008010681,
+      "grad_norm": 2.1168835756122544,
+      "learning_rate": 7.657491252231525e-07,
+      "loss": 0.27218157052993774,
+      "step": 267,
+      "token_acc": 0.9023776054382324
+    },
+    {
+      "epoch": 0.7156208277703605,
+      "grad_norm": 2.020350648394881,
+      "learning_rate": 7.63877783455237e-07,
+      "loss": 0.28021299839019775,
+      "step": 268,
+      "token_acc": 0.9005134701728821
+    },
+    {
+      "epoch": 0.7182910547396528,
+      "grad_norm": 2.044560421065739,
+      "learning_rate": 7.620013043050711e-07,
+      "loss": 0.2860478162765503,
+      "step": 269,
+      "token_acc": 0.9014725685119629
+    },
+    {
+      "epoch": 0.7209612817089452,
+      "grad_norm": 2.056132956718497,
+      "learning_rate": 7.60119724305441e-07,
+      "loss": 0.2929646074771881,
+      "step": 270,
+      "token_acc": 0.9049229025840759
+    },
+    {
+      "epoch": 0.7236315086782377,
+      "grad_norm": 2.1673632562813068,
+      "learning_rate": 7.582330800884404e-07,
+      "loss": 0.2824397683143616,
+      "step": 271,
+      "token_acc": 0.9031528234481812
+    },
+    {
+      "epoch": 0.7263017356475301,
+      "grad_norm": 2.226548215534571,
+      "learning_rate": 7.563414083847572e-07,
+      "loss": 0.31409960985183716,
+      "step": 272,
+      "token_acc": 0.891449511051178
+    },
+    {
+      "epoch": 0.7289719626168224,
+      "grad_norm": 2.2051025475258856,
+      "learning_rate": 7.544447460229587e-07,
+      "loss": 0.30504441261291504,
+      "step": 273,
+      "token_acc": 0.8924999833106995
+    },
+    {
+      "epoch": 0.7316421895861148,
+      "grad_norm": 2.0676253818382726,
+      "learning_rate": 7.525431299287737e-07,
+      "loss": 0.2587094306945801,
+      "step": 274,
+      "token_acc": 0.9084300398826599
+    },
+    {
+      "epoch": 0.7343124165554072,
+      "grad_norm": 2.05967826354503,
+      "learning_rate": 7.506365971243744e-07,
+      "loss": 0.2892255485057831,
+      "step": 275,
+      "token_acc": 0.9045761823654175
+    },
+    {
+      "epoch": 0.7369826435246996,
+      "grad_norm": 2.0257014804684967,
+      "learning_rate": 7.487251847276558e-07,
+      "loss": 0.2663314938545227,
+      "step": 276,
+      "token_acc": 0.9133386611938477
+    },
+    {
+      "epoch": 0.739652870493992,
+      "grad_norm": 2.1096628717969454,
+      "learning_rate": 7.468089299515125e-07,
+      "loss": 0.2851673662662506,
+      "step": 277,
+      "token_acc": 0.9019791483879089
+    },
+    {
+      "epoch": 0.7423230974632844,
+      "grad_norm": 2.233873424782089,
+      "learning_rate": 7.448878701031142e-07,
+      "loss": 0.32581809163093567,
+      "step": 278,
+      "token_acc": 0.8897114992141724
+    },
+    {
+      "epoch": 0.7449933244325768,
+      "grad_norm": 2.019098373278142,
+      "learning_rate": 7.429620425831794e-07,
+      "loss": 0.25698885321617126,
+      "step": 279,
+      "token_acc": 0.9100551009178162
+    },
+    {
+      "epoch": 0.7476635514018691,
+      "grad_norm": 2.268521607259172,
+      "learning_rate": 7.410314848852482e-07,
+      "loss": 0.31027084589004517,
+      "step": 280,
+      "token_acc": 0.8951810598373413
+    },
+    {
+      "epoch": 0.7503337783711616,
+      "grad_norm": 2.079707939019881,
+      "learning_rate": 7.390962345949505e-07,
+      "loss": 0.2730080485343933,
+      "step": 281,
+      "token_acc": 0.9071873426437378
+    },
+    {
+      "epoch": 0.753004005340454,
+      "grad_norm": 2.1267477847944414,
+      "learning_rate": 7.371563293892761e-07,
+      "loss": 0.2881926894187927,
+      "step": 282,
+      "token_acc": 0.899695634841919
+    },
+    {
+      "epoch": 0.7556742323097463,
+      "grad_norm": 2.0476449985901373,
+      "learning_rate": 7.352118070358402e-07,
+      "loss": 0.27858686447143555,
+      "step": 283,
+      "token_acc": 0.903513491153717
+    },
+    {
+      "epoch": 0.7583444592790387,
+      "grad_norm": 2.198052248648514,
+      "learning_rate": 7.332627053921482e-07,
+      "loss": 0.30467116832733154,
+      "step": 284,
+      "token_acc": 0.8960789442062378
+    },
+    {
+      "epoch": 0.7610146862483311,
+      "grad_norm": 1.973643551957016,
+      "learning_rate": 7.313090624048588e-07,
+      "loss": 0.28269678354263306,
+      "step": 285,
+      "token_acc": 0.9015141725540161
+    },
+    {
+      "epoch": 0.7636849132176236,
+      "grad_norm": 2.0686640622751766,
+      "learning_rate": 7.293509161090452e-07,
+      "loss": 0.26726454496383667,
+      "step": 286,
+      "token_acc": 0.9111682176589966
+    },
+    {
+      "epoch": 0.7663551401869159,
+      "grad_norm": 2.0592248604667605,
+      "learning_rate": 7.273883046274546e-07,
+      "loss": 0.28873705863952637,
+      "step": 287,
+      "token_acc": 0.900973379611969
+    },
+    {
+      "epoch": 0.7690253671562083,
+      "grad_norm": 2.1390917313433713,
+      "learning_rate": 7.254212661697659e-07,
+      "loss": 0.31321921944618225,
+      "step": 288,
+      "token_acc": 0.8934234380722046
+    },
+    {
+      "epoch": 0.7716955941255007,
+      "grad_norm": 1.9976054715479417,
+      "learning_rate": 7.23449839031846e-07,
+      "loss": 0.26317542791366577,
+      "step": 289,
+      "token_acc": 0.9093555808067322
+    },
+    {
+      "epoch": 0.774365821094793,
+      "grad_norm": 2.164755162867173,
+      "learning_rate": 7.21474061595004e-07,
+      "loss": 0.271062433719635,
+      "step": 290,
+      "token_acc": 0.9077165722846985
+    },
+    {
+      "epoch": 0.7770360480640854,
+      "grad_norm": 2.158474961561152,
+      "learning_rate": 7.194939723252441e-07,
+      "loss": 0.31681138277053833,
+      "step": 291,
+      "token_acc": 0.8899307250976562
+    },
+    {
+      "epoch": 0.7797062750333779,
+      "grad_norm": 2.079774637072493,
+      "learning_rate": 7.175096097725168e-07,
+      "loss": 0.2948077917098999,
+      "step": 292,
+      "token_acc": 0.8995034098625183
+    },
+    {
+      "epoch": 0.7823765020026703,
+      "grad_norm": 1.9268975706131877,
+      "learning_rate": 7.155210125699682e-07,
+      "loss": 0.2564176917076111,
+      "step": 293,
+      "token_acc": 0.9108521938323975
+    },
+    {
+      "epoch": 0.7850467289719626,
+      "grad_norm": 2.108279149610646,
+      "learning_rate": 7.13528219433188e-07,
+      "loss": 0.304332971572876,
+      "step": 294,
+      "token_acc": 0.8987877368927002
+    },
+    {
+      "epoch": 0.787716955941255,
+      "grad_norm": 2.110751645241943,
+      "learning_rate": 7.115312691594552e-07,
+      "loss": 0.2964024543762207,
+      "step": 295,
+      "token_acc": 0.8981098532676697
+    },
+    {
+      "epoch": 0.7903871829105474,
+      "grad_norm": 2.0527701912802145,
+      "learning_rate": 7.095302006269841e-07,
+      "loss": 0.2663918137550354,
+      "step": 296,
+      "token_acc": 0.9087468385696411
+    },
+    {
+      "epoch": 0.7930574098798397,
+      "grad_norm": 1.8721356006003376,
+      "learning_rate": 7.075250527941658e-07,
+      "loss": 0.2569364905357361,
+      "step": 297,
+      "token_acc": 0.9146753549575806
+    },
+    {
+      "epoch": 0.7957276368491322,
+      "grad_norm": 1.9796278305703667,
+      "learning_rate": 7.055158646988109e-07,
+      "loss": 0.2556707262992859,
+      "step": 298,
+      "token_acc": 0.9111869931221008
+    },
+    {
+      "epoch": 0.7983978638184246,
+      "grad_norm": 1.9577139332916655,
+      "learning_rate": 7.035026754573888e-07,
+      "loss": 0.2614712119102478,
+      "step": 299,
+      "token_acc": 0.9131455421447754
+    },
+    {
+      "epoch": 0.8010680907877169,
+      "grad_norm": 2.0295291311709285,
+      "learning_rate": 7.014855242642661e-07,
+      "loss": 0.2888241112232208,
+      "step": 300,
+      "token_acc": 0.9010165929794312
+    },
+    {
+      "epoch": 0.8037383177570093,
+      "grad_norm": 2.125605872657734,
+      "learning_rate": 6.994644503909448e-07,
+      "loss": 0.27084577083587646,
+      "step": 301,
+      "token_acc": 0.9026212096214294
+    },
+    {
+      "epoch": 0.8064085447263017,
+      "grad_norm": 2.091516965461202,
+      "learning_rate": 6.974394931852956e-07,
+      "loss": 0.2849307060241699,
+      "step": 302,
+      "token_acc": 0.9011662006378174
+    },
+    {
+      "epoch": 0.8090787716955942,
+      "grad_norm": 1.858325549966066,
+      "learning_rate": 6.954106920707938e-07,
+      "loss": 0.22345201671123505,
+      "step": 303,
+      "token_acc": 0.9244060516357422
+    },
+    {
+      "epoch": 0.8117489986648865,
+      "grad_norm": 1.8332463753941461,
+      "learning_rate": 6.933780865457507e-07,
+      "loss": 0.22892417013645172,
+      "step": 304,
+      "token_acc": 0.9204072952270508
+    },
+    {
+      "epoch": 0.8144192256341789,
+      "grad_norm": 2.2050382118263046,
+      "learning_rate": 6.913417161825449e-07,
+      "loss": 0.31420451402664185,
+      "step": 305,
+      "token_acc": 0.8947438597679138
+    },
+    {
+      "epoch": 0.8170894526034713,
+      "grad_norm": 2.109749894191455,
+      "learning_rate": 6.893016206268517e-07,
+      "loss": 0.3098646402359009,
+      "step": 306,
+      "token_acc": 0.8963049650192261
+    },
+    {
+      "epoch": 0.8197596795727636,
+      "grad_norm": 2.138245571661256,
+      "learning_rate": 6.872578395968715e-07,
+      "loss": 0.2844926714897156,
+      "step": 307,
+      "token_acc": 0.9005376100540161
+    },
+    {
+      "epoch": 0.822429906542056,
+      "grad_norm": 2.3037597173982824,
+      "learning_rate": 6.852104128825569e-07,
+      "loss": 0.3131234049797058,
+      "step": 308,
+      "token_acc": 0.8949984908103943
+    },
+    {
+      "epoch": 0.8251001335113485,
+      "grad_norm": 1.9975300908872187,
+      "learning_rate": 6.831593803448365e-07,
+      "loss": 0.27260279655456543,
+      "step": 309,
+      "token_acc": 0.906949520111084
+    },
+    {
+      "epoch": 0.8277703604806409,
+      "grad_norm": 2.151633051541349,
+      "learning_rate": 6.811047819148412e-07,
+      "loss": 0.29308199882507324,
+      "step": 310,
+      "token_acc": 0.8975649476051331
+    },
+    {
+      "epoch": 0.8304405874499332,
+      "grad_norm": 2.119859055500384,
+      "learning_rate": 6.790466575931246e-07,
+      "loss": 0.272926926612854,
+      "step": 311,
+      "token_acc": 0.9046028852462769
+    },
+    {
+      "epoch": 0.8331108144192256,
+      "grad_norm": 2.2395637078476365,
+      "learning_rate": 6.769850474488859e-07,
+      "loss": 0.3006908893585205,
+      "step": 312,
+      "token_acc": 0.8941530585289001
+    },
+    {
+      "epoch": 0.835781041388518,
+      "grad_norm": 2.1444202591361408,
+      "learning_rate": 6.749199916191878e-07,
+      "loss": 0.2668108344078064,
+      "step": 313,
+      "token_acc": 0.9067223072052002
+    },
+    {
+      "epoch": 0.8384512683578104,
+      "grad_norm": 2.0300266961324036,
+      "learning_rate": 6.728515303081781e-07,
+      "loss": 0.26886218786239624,
+      "step": 314,
+      "token_acc": 0.9050405621528625
+    },
+    {
+      "epoch": 0.8411214953271028,
+      "grad_norm": 2.018625268873622,
+      "learning_rate": 6.707797037863039e-07,
+      "loss": 0.288851261138916,
+      "step": 315,
+      "token_acc": 0.8983978629112244
+    },
+    {
+      "epoch": 0.8437917222963952,
+      "grad_norm": 1.8384524029526925,
+      "learning_rate": 6.687045523895291e-07,
+      "loss": 0.23870034515857697,
+      "step": 316,
+      "token_acc": 0.913782000541687
+    },
+    {
+      "epoch": 0.8464619492656876,
+      "grad_norm": 2.0489775266821586,
+      "learning_rate": 6.666261165185495e-07,
+      "loss": 0.2744598984718323,
+      "step": 317,
+      "token_acc": 0.9041152000427246
+    },
+    {
+      "epoch": 0.8491321762349799,
+      "grad_norm": 2.0630846590203813,
+      "learning_rate": 6.64544436638005e-07,
+      "loss": 0.2515294551849365,
+      "step": 318,
+      "token_acc": 0.9093925952911377
+    },
+    {
+      "epoch": 0.8518024032042724,
+      "grad_norm": 1.9021463213670837,
+      "learning_rate": 6.624595532756929e-07,
+      "loss": 0.25368499755859375,
+      "step": 319,
+      "token_acc": 0.9140026569366455
+    },
+    {
+      "epoch": 0.8544726301735648,
+      "grad_norm": 1.9885056310955591,
+      "learning_rate": 6.603715070217778e-07,
+      "loss": 0.2522217035293579,
+      "step": 320,
+      "token_acc": 0.9108746647834778
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 1.969956434010331,
+      "learning_rate": 6.582803385280029e-07,
+      "loss": 0.29186463356018066,
+      "step": 321,
+      "token_acc": 0.897017240524292
+    },
+    {
+      "epoch": 0.8598130841121495,
+      "grad_norm": 2.055811805790188,
+      "learning_rate": 6.561860885068971e-07,
+      "loss": 0.28713715076446533,
+      "step": 322,
+      "token_acc": 0.8998340964317322
+    },
+    {
+      "epoch": 0.8624833110814419,
+      "grad_norm": 1.9862614995190595,
+      "learning_rate": 6.540887977309828e-07,
+      "loss": 0.2344796061515808,
+      "step": 323,
+      "token_acc": 0.9170397520065308
+    },
+    {
+      "epoch": 0.8651535380507344,
+      "grad_norm": 1.9989353503516842,
+      "learning_rate": 6.519885070319826e-07,
+      "loss": 0.28280532360076904,
+      "step": 324,
+      "token_acc": 0.8983380794525146
+    },
+    {
+      "epoch": 0.8678237650200267,
+      "grad_norm": 2.1599304061477405,
+      "learning_rate": 6.498852573000235e-07,
+      "loss": 0.31109631061553955,
+      "step": 325,
+      "token_acc": 0.8938894271850586
+    },
+    {
+      "epoch": 0.8704939919893191,
+      "grad_norm": 2.0861667816354488,
+      "learning_rate": 6.47779089482842e-07,
+      "loss": 0.2893826961517334,
+      "step": 326,
+      "token_acc": 0.9015215635299683
+    },
+    {
+      "epoch": 0.8731642189586115,
+      "grad_norm": 1.9676151824911736,
+      "learning_rate": 6.456700445849856e-07,
+      "loss": 0.258078008890152,
+      "step": 327,
+      "token_acc": 0.911485493183136
+    },
+    {
+      "epoch": 0.8758344459279038,
+      "grad_norm": 2.04339510539664,
+      "learning_rate": 6.435581636670153e-07,
+      "loss": 0.27314725518226624,
+      "step": 328,
+      "token_acc": 0.9001234769821167
+    },
+    {
+      "epoch": 0.8785046728971962,
+      "grad_norm": 2.096440703449396,
+      "learning_rate": 6.41443487844706e-07,
+      "loss": 0.25557276606559753,
+      "step": 329,
+      "token_acc": 0.9108026623725891
+    },
+    {
+      "epoch": 0.8811748998664887,
+      "grad_norm": 2.1056459739435374,
+      "learning_rate": 6.39326058288246e-07,
+      "loss": 0.29063817858695984,
+      "step": 330,
+      "token_acc": 0.902656078338623
+    },
+    {
+      "epoch": 0.8838451268357811,
+      "grad_norm": 2.079134911698444,
+      "learning_rate": 6.372059162214357e-07,
+      "loss": 0.24332958459854126,
+      "step": 331,
+      "token_acc": 0.9111046195030212
+    },
+    {
+      "epoch": 0.8865153538050734,
+      "grad_norm": 1.9981185793829204,
+      "learning_rate": 6.350831029208843e-07,
+      "loss": 0.2829723656177521,
+      "step": 332,
+      "token_acc": 0.9027331471443176
+    },
+    {
+      "epoch": 0.8891855807743658,
+      "grad_norm": 2.205561103174351,
+      "learning_rate": 6.32957659715207e-07,
+      "loss": 0.2898241877555847,
+      "step": 333,
+      "token_acc": 0.9018152952194214
+    },
+    {
+      "epoch": 0.8918558077436582,
+      "grad_norm": 1.8392952260962427,
+      "learning_rate": 6.308296279842204e-07,
+      "loss": 0.2105484902858734,
+      "step": 334,
+      "token_acc": 0.9244604110717773
+    },
+    {
+      "epoch": 0.8945260347129506,
+      "grad_norm": 1.9835505727688578,
+      "learning_rate": 6.286990491581359e-07,
+      "loss": 0.2537194490432739,
+      "step": 335,
+      "token_acc": 0.9101715683937073
+    },
+    {
+      "epoch": 0.897196261682243,
+      "grad_norm": 2.0598478410278935,
+      "learning_rate": 6.265659647167541e-07,
+      "loss": 0.2862735390663147,
+      "step": 336,
+      "token_acc": 0.9006946086883545
+    },
+    {
+      "epoch": 0.8998664886515354,
+      "grad_norm": 2.052888319861698,
+      "learning_rate": 6.244304161886573e-07,
+      "loss": 0.2768602669239044,
+      "step": 337,
+      "token_acc": 0.9061157703399658
+    },
+    {
+      "epoch": 0.9025367156208278,
+      "grad_norm": 2.1734751447149545,
+      "learning_rate": 6.222924451504e-07,
+      "loss": 0.2798523008823395,
+      "step": 338,
+      "token_acc": 0.9027093648910522
+    },
+    {
+      "epoch": 0.9052069425901201,
+      "grad_norm": 2.252391004853616,
+      "learning_rate": 6.201520932257002e-07,
+      "loss": 0.30862048268318176,
+      "step": 339,
+      "token_acc": 0.8972538709640503
+    },
+    {
+      "epoch": 0.9078771695594126,
+      "grad_norm": 2.1496247029724924,
+      "learning_rate": 6.18009402084629e-07,
+      "loss": 0.3052927553653717,
+      "step": 340,
+      "token_acc": 0.9002237915992737
+    },
+    {
+      "epoch": 0.910547396528705,
+      "grad_norm": 2.2146926321964755,
+      "learning_rate": 6.158644134427993e-07,
+      "loss": 0.34132421016693115,
+      "step": 341,
+      "token_acc": 0.8828502297401428
+    },
+    {
+      "epoch": 0.9132176234979973,
+      "grad_norm": 1.9674673407867969,
+      "learning_rate": 6.137171690605533e-07,
+      "loss": 0.2585831880569458,
+      "step": 342,
+      "token_acc": 0.9121473431587219
+    },
+    {
+      "epoch": 0.9158878504672897,
+      "grad_norm": 2.186626074425696,
+      "learning_rate": 6.115677107421499e-07,
+      "loss": 0.29590335488319397,
+      "step": 343,
+      "token_acc": 0.8969404101371765
+    },
+    {
+      "epoch": 0.9185580774365821,
+      "grad_norm": 2.212708557685105,
+      "learning_rate": 6.094160803349507e-07,
+      "loss": 0.2991503179073334,
+      "step": 344,
+      "token_acc": 0.8936232924461365
+    },
+    {
+      "epoch": 0.9212283044058746,
+      "grad_norm": 1.9470192155995054,
+      "learning_rate": 6.072623197286053e-07,
+      "loss": 0.24123477935791016,
+      "step": 345,
+      "token_acc": 0.9182246327400208
+    },
+    {
+      "epoch": 0.9238985313751669,
+      "grad_norm": 1.9527827087529621,
+      "learning_rate": 6.051064708542356e-07,
+      "loss": 0.24355074763298035,
+      "step": 346,
+      "token_acc": 0.9153308272361755
+    },
+    {
+      "epoch": 0.9265687583444593,
+      "grad_norm": 1.976188579300761,
+      "learning_rate": 6.029485756836194e-07,
+      "loss": 0.29774773120880127,
+      "step": 347,
+      "token_acc": 0.8953589797019958
+    },
+    {
+      "epoch": 0.9292389853137517,
+      "grad_norm": 1.9933305604962481,
+      "learning_rate": 6.007886762283739e-07,
+      "loss": 0.2699834108352661,
+      "step": 348,
+      "token_acc": 0.9026391506195068
+    },
+    {
+      "epoch": 0.931909212283044,
+      "grad_norm": 2.128474453102008,
+      "learning_rate": 5.986268145391367e-07,
+      "loss": 0.29028767347335815,
+      "step": 349,
+      "token_acc": 0.9003961682319641
+    },
+    {
+      "epoch": 0.9345794392523364,
+      "grad_norm": 2.11055991367656,
+      "learning_rate": 5.964630327047484e-07,
+      "loss": 0.3167427182197571,
+      "step": 350,
+      "token_acc": 0.8951997756958008
+    },
+    {
+      "epoch": 0.9372496662216289,
+      "grad_norm": 2.09842689604663,
+      "learning_rate": 5.942973728514318e-07,
+      "loss": 0.29754748940467834,
+      "step": 351,
+      "token_acc": 0.8964751362800598
+    },
+    {
+      "epoch": 0.9399198931909212,
+      "grad_norm": 2.2983883127695717,
+      "learning_rate": 5.921298771419731e-07,
+      "loss": 0.34417998790740967,
+      "step": 352,
+      "token_acc": 0.8806232810020447
+    },
+    {
+      "epoch": 0.9425901201602136,
+      "grad_norm": 2.0484258364601513,
+      "learning_rate": 5.899605877748998e-07,
+      "loss": 0.25486433506011963,
+      "step": 353,
+      "token_acc": 0.9093440771102905
+    },
+    {
+      "epoch": 0.945260347129506,
+      "grad_norm": 2.1584909495737317,
+      "learning_rate": 5.877895469836603e-07,
+      "loss": 0.2894634008407593,
+      "step": 354,
+      "token_acc": 0.9019073843955994
+    },
+    {
+      "epoch": 0.9479305740987984,
+      "grad_norm": 2.026329176088939,
+      "learning_rate": 5.856167970358009e-07,
+      "loss": 0.2752753496170044,
+      "step": 355,
+      "token_acc": 0.9067592620849609
+    },
+    {
+      "epoch": 0.9506008010680908,
+      "grad_norm": 2.025703296719089,
+      "learning_rate": 5.83442380232143e-07,
+      "loss": 0.274118572473526,
+      "step": 356,
+      "token_acc": 0.9030666947364807
+    },
+    {
+      "epoch": 0.9532710280373832,
+      "grad_norm": 2.1167400912385896,
+      "learning_rate": 5.812663389059598e-07,
+      "loss": 0.29609131813049316,
+      "step": 357,
+      "token_acc": 0.8981894254684448
+    },
+    {
+      "epoch": 0.9559412550066756,
+      "grad_norm": 2.0602256557661276,
+      "learning_rate": 5.790887154221519e-07,
+      "loss": 0.27871522307395935,
+      "step": 358,
+      "token_acc": 0.9030633568763733
+    },
+    {
+      "epoch": 0.9586114819759679,
+      "grad_norm": 2.015363764305975,
+      "learning_rate": 5.769095521764229e-07,
+      "loss": 0.2414725422859192,
+      "step": 359,
+      "token_acc": 0.9181360006332397
+    },
+    {
+      "epoch": 0.9612817089452603,
+      "grad_norm": 2.4875862080074165,
+      "learning_rate": 5.747288915944533e-07,
+      "loss": 0.29549306631088257,
+      "step": 360,
+      "token_acc": 0.8960682153701782
+    },
+    {
+      "epoch": 0.9639519359145527,
+      "grad_norm": 2.267752991124927,
+      "learning_rate": 5.72546776131075e-07,
+      "loss": 0.31073901057243347,
+      "step": 361,
+      "token_acc": 0.8925920724868774
+    },
+    {
+      "epoch": 0.9666221628838452,
+      "grad_norm": 2.10649288421138,
+      "learning_rate": 5.703632482694453e-07,
+      "loss": 0.28388527035713196,
+      "step": 362,
+      "token_acc": 0.9032637476921082
+    },
+    {
+      "epoch": 0.9692923898531375,
+      "grad_norm": 2.2383333333715116,
+      "learning_rate": 5.681783505202181e-07,
+      "loss": 0.2887263894081116,
+      "step": 363,
+      "token_acc": 0.9000994563102722
+    },
+    {
+      "epoch": 0.9719626168224299,
+      "grad_norm": 2.231947835761732,
+      "learning_rate": 5.659921254207182e-07,
+      "loss": 0.3282718062400818,
+      "step": 364,
+      "token_acc": 0.8889458775520325
+    },
+    {
+      "epoch": 0.9746328437917223,
+      "grad_norm": 2.1354701488796985,
+      "learning_rate": 5.638046155341121e-07,
+      "loss": 0.3134065866470337,
+      "step": 365,
+      "token_acc": 0.8931100964546204
+    },
+    {
+      "epoch": 0.9773030707610146,
+      "grad_norm": 2.037910436474094,
+      "learning_rate": 5.616158634485792e-07,
+      "loss": 0.23856621980667114,
+      "step": 366,
+      "token_acc": 0.9192389249801636
+    },
+    {
+      "epoch": 0.9799732977303071,
+      "grad_norm": 2.1249678323286165,
+      "learning_rate": 5.594259117764839e-07,
+      "loss": 0.2885601818561554,
+      "step": 367,
+      "token_acc": 0.9004982113838196
+    },
+    {
+      "epoch": 0.9826435246995995,
+      "grad_norm": 2.0930501009234583,
+      "learning_rate": 5.572348031535441e-07,
+      "loss": 0.2769622206687927,
+      "step": 368,
+      "token_acc": 0.9059219360351562
+    },
+    {
+      "epoch": 0.9853137516688919,
+      "grad_norm": 2.048908696043972,
+      "learning_rate": 5.550425802380028e-07,
+      "loss": 0.24446731805801392,
+      "step": 369,
+      "token_acc": 0.9150381088256836
+    },
+    {
+      "epoch": 0.9879839786381842,
+      "grad_norm": 1.9479147985140528,
+      "learning_rate": 5.528492857097965e-07,
+      "loss": 0.2285379022359848,
+      "step": 370,
+      "token_acc": 0.9190733432769775
+    },
+    {
+      "epoch": 0.9906542056074766,
+      "grad_norm": 2.146355680876123,
+      "learning_rate": 5.50654962269725e-07,
+      "loss": 0.27457720041275024,
+      "step": 371,
+      "token_acc": 0.9005686044692993
+    },
+    {
+      "epoch": 0.9933244325767691,
+      "grad_norm": 2.0923705096030054,
+      "learning_rate": 5.484596526386197e-07,
+      "loss": 0.2646147608757019,
+      "step": 372,
+      "token_acc": 0.9081632494926453
+    },
+    {
+      "epoch": 0.9959946595460614,
+      "grad_norm": 2.211169149634228,
+      "learning_rate": 5.462633995565119e-07,
+      "loss": 0.31181105971336365,
+      "step": 373,
+      "token_acc": 0.8944056630134583
+    },
+    {
+      "epoch": 0.9986648865153538,
+      "grad_norm": 2.0078890878811557,
+      "learning_rate": 5.440662457818009e-07,
+      "loss": 0.2434024214744568,
+      "step": 374,
+      "token_acc": 0.9119241237640381
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 3.0932011322687356,
+      "learning_rate": 5.41868234090421e-07,
+      "loss": 0.34929388761520386,
+      "step": 375,
+      "token_acc": 0.88083815574646
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.2875675857067108,
+      "eval_runtime": 4.5943,
+      "eval_samples_per_second": 4.571,
+      "eval_steps_per_second": 0.653,
+      "eval_token_acc": 0.8904109597206116,
+      "step": 375
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 750,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 159128138645504.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

qwen2.5-7b-2000q-2000q-1369q-noinfo-newbs-old-click-2ep-lr1e-6/checkpoint-375/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab8e578cf0fe6fbb8cc45acb8240e56976540c7604c84567fae37a5e11436969
+size 9041

qwen2.5-7b-2000q-2000q-1369q-noinfo-newbs-old-click-2ep-lr1e-6/checkpoint-375/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-2000q-2000q-1369q-noinfo-newbs-old-click-2ep-lr1e-6/checkpoint-750/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-2000q-2000q-1369q-noinfo-newbs-old-click-2ep-lr1e-6/checkpoint-750/args.json

@@ -0,0 +1,384 @@
+{
+  "output_dir": "/group/40143/hongzhuyi/ms-swift/output/v1-20250914-134901",
+  "overwrite_output_dir": false,
+  "do_train": false,
+  "do_eval": false,
+  "do_predict": false,
+  "eval_strategy": "epoch",
+  "prediction_loss_only": false,
+  "per_device_train_batch_size": 2,
+  "per_device_eval_batch_size": 1,
+  "per_gpu_train_batch_size": null,
+  "per_gpu_eval_batch_size": null,
+  "gradient_accumulation_steps": 4,
+  "eval_accumulation_steps": null,
+  "eval_delay": 0,
+  "torch_empty_cache_steps": null,
+  "learning_rate": 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": 2.0,
+  "max_steps": -1,
+  "lr_scheduler_type": "cosine",
+  "lr_scheduler_kwargs": null,
+  "warmup_ratio": 0.05,
+  "warmup_steps": 0,
+  "log_level": "passive",
+  "log_level_replica": "warning",
+  "log_on_each_node": true,
+  "logging_dir": "/group/40143/hongzhuyi/ms-swift/output/v1-20250914-134901/runs",
+  "logging_strategy": "steps",
+  "logging_first_step": true,
+  "logging_steps": 1,
+  "logging_nan_inf_filter": true,
+  "save_strategy": "epoch",
+  "save_steps": 500,
+  "save_total_limit": null,
+  "save_safetensors": true,
+  "save_on_each_node": false,
+  "save_only_model": false,
+  "restore_callback_states_from_checkpoint": false,
+  "no_cuda": false,
+  "use_cpu": false,
+  "use_mps_device": false,
+  "seed": 42,
+  "data_seed": 42,
+  "jit_mode_eval": false,
+  "use_ipex": false,
+  "bf16": true,
+  "fp16": false,
+  "fp16_opt_level": "O1",
+  "half_precision_backend": "auto",
+  "bf16_full_eval": false,
+  "fp16_full_eval": false,
+  "tf32": null,
+  "local_rank": 0,
+  "ddp_backend": null,
+  "tpu_num_cores": null,
+  "tpu_metrics_debug": false,
+  "debug": null,
+  "dataloader_drop_last": false,
+  "eval_steps": 2000.0,
+  "dataloader_num_workers": 48,
+  "dataloader_prefetch_factor": null,
+  "past_index": -1,
+  "run_name": "/group/40143/hongzhuyi/ms-swift/output/v1-20250914-134901",
+  "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": "/group/40143/hongzhuyi/model/qwen2.5-7b-2225q-2069q-1369q-newbs-old-click-xep-lr5e-6/qwen2.5-7b-2225q-2069q-1369q-newbs-old-click-xep-lr5e-6/checkpoint-636",
+  "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": [
+    "/group/40143/hongzhuyi/ms-swift/data/corr_hotpot_2083q_0.8_swift.jsonl",
+    "/group/40143/hongzhuyi/ms-swift/data/corr_hotpot_new1369q_0.8_swift.jsonl",
+    "/group/40143/hongzhuyi/ms-swift/data/corr_nq_2225q_0.8_swift.jsonl",
+    "/group/40143/hongzhuyi/ms-swift/data/self_2000_2000_1369_4_hp673_swift.jsonl",
+    "/group/40143/hongzhuyi/ms-swift/data/self_2000_2000_1369_4_nq400_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": "/group/40143/hongzhuyi/model/qwen2.5-7b-2225q-2069q-1369q-newbs-old-click-xep-lr5e-6/qwen2.5-7b-2225q-2069q-1369q-newbs-old-click-xep-lr5e-6/checkpoint-636",
+  "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": "checkpoint-636",
+  "model_info": "ModelInfo(model_type='qwen2_5', model_dir='/group/40143/hongzhuyi/model/qwen2.5-7b-2225q-2069q-1369q-newbs-old-click-xep-lr5e-6/qwen2.5-7b-2225q-2069q-1369q-newbs-old-click-xep-lr5e-6/checkpoint-636', 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 0x7f66153ba830>, 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": "/group/40143/hongzhuyi/model/qwen2.5-7b-2225q-2069q-1369q-newbs-old-click-xep-lr5e-6/qwen2.5-7b-2225q-2069q-1369q-newbs-old-click-xep-lr5e-6/checkpoint-636",
+  "hub": "<class 'swift.hub.hub.MSHub'>",
+  "evaluation_strategy": "epoch",
+  "training_args": "Seq2SeqTrainingArguments(output_dir='/group/40143/hongzhuyi/ms-swift/output/v1-20250914-134901', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, eval_strategy=<IntervalStrategy.EPOCH: 'epoch'>, prediction_loss_only=False, per_device_train_batch_size=2, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=4, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=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=2.0, max_steps=-1, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs=None, warmup_ratio=0.05, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/group/40143/hongzhuyi/ms-swift/output/v1-20250914-134901/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=1, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.EPOCH: 'epoch'>, save_steps=500, save_total_limit=None, save_safetensors=True, save_on_each_node=False, save_only_model=False, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=42, jit_mode_eval=False, use_ipex=False, bf16=True, fp16=False, fp16_opt_level='O1', half_precision_backend='auto', bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=0, ddp_backend=None, tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=2000.0, dataloader_num_workers=48, dataloader_prefetch_factor=10, past_index=-1, run_name='/group/40143/hongzhuyi/ms-swift/output/v1-20250914-134901', 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-2000q-2000q-1369q-noinfo-newbs-old-click-2ep-lr1e-6/checkpoint-750/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-2000q-2000q-1369q-noinfo-newbs-old-click-2ep-lr1e-6/checkpoint-750/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": "4.55.4",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

qwen2.5-7b-2000q-2000q-1369q-noinfo-newbs-old-click-2ep-lr1e-6/checkpoint-750/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": "4.55.4"
+}

qwen2.5-7b-2000q-2000q-1369q-noinfo-newbs-old-click-2ep-lr1e-6/checkpoint-750/latest

@@ -0,0 +1 @@
+global_step750

qwen2.5-7b-2000q-2000q-1369q-noinfo-newbs-old-click-2ep-lr1e-6/checkpoint-750/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e07dee4ca57ed761f796f6f0555200089ceb56c7b6d124c31a2e2ca2e2a1649
+size 4877660776

qwen2.5-7b-2000q-2000q-1369q-noinfo-newbs-old-click-2ep-lr1e-6/checkpoint-750/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:beaa21b9c1a9fff9a1db94c762bd6e3d3a495f13c9cc358acc5c5908e12892ac
+size 4932751008

qwen2.5-7b-2000q-2000q-1369q-noinfo-newbs-old-click-2ep-lr1e-6/checkpoint-750/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a51ad6f5c86169599dfd9a115f387bab31daec51c7daea869017d31f9505099f
+size 4330865200

qwen2.5-7b-2000q-2000q-1369q-noinfo-newbs-old-click-2ep-lr1e-6/checkpoint-750/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c78d8bfb3329ef39f725ad92f4bfda75b032447e11d8a08d970ec36e4d87703
+size 1089994880

qwen2.5-7b-2000q-2000q-1369q-noinfo-newbs-old-click-2ep-lr1e-6/checkpoint-750/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-2000q-2000q-1369q-noinfo-newbs-old-click-2ep-lr1e-6/checkpoint-750/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8e5f48b40f283c2be57ffeca20c84e74d5bad51d76da17d127991b78da5289d
+size 16389

qwen2.5-7b-2000q-2000q-1369q-noinfo-newbs-old-click-2ep-lr1e-6/checkpoint-750/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c3696205cbf4679a7f2faf48351e924c79ada4cfd81a956e03e4319cf3d05b5
+size 16389

qwen2.5-7b-2000q-2000q-1369q-noinfo-newbs-old-click-2ep-lr1e-6/checkpoint-750/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:403766b1961af9b11405f33af2b272a2d6287cefdee9eb7e26e1dc71e3ed3707
+size 16389

qwen2.5-7b-2000q-2000q-1369q-noinfo-newbs-old-click-2ep-lr1e-6/checkpoint-750/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54f6e3e08fea79c105dbd92657538a3cb15e89872360a3c3072b758835ca5ebc
+size 16389

qwen2.5-7b-2000q-2000q-1369q-noinfo-newbs-old-click-2ep-lr1e-6/checkpoint-750/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0203808a2df05d235c57b83a0a087bae98ef6e47f06d685a0bddaa460a16c910
+size 16389

qwen2.5-7b-2000q-2000q-1369q-noinfo-newbs-old-click-2ep-lr1e-6/checkpoint-750/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6b492b10406611c53f05fd065d6968c7e5e3797fd0008fca46cad009936c67e
+size 16389