Upload folder using huggingface_hub

model-00001-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d189be1ade0a7bdf7f4bd86788f4846fc89b12b28ece8f42e2fc308dd46a7a66
+oid sha256:35253e0c7350c0bd420cb9519a06e5e37b903c335f8bb0b6c4d75813714ef8d1
 size 4548798728

model-00002-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78b5bc3946135593a8f831e34003d7dbd375e3063f6047491c47c4ab550c27b6
+oid sha256:c00caadc732abd452255c0bd3f70bd41071fa97affae43bbc9d711d592f6a98f
 size 4964101384

model-00003-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7862bfe9a14ec5d156363302ef01285449cb52320041370ecb8a1c3a5129aad
+oid sha256:29d5f9f3f7e953c39ab7c4edc1b0374c495448c802d05cc8bc48003c88b79dd9
 size 4781637328

model-00004-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e53b60a96bd2feac4c98e2944db566ade74c4ebedf771c67c0475f81b754464a
+oid sha256:3fd9707278e108e943a1a480c5c458031abe846bf55fb6d3d1f113429d12b4fe
 size 4781670320

model-00005-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f803d2bc0fc3fb2e7143b6d6cb62baa0c0a9b41a73fcbe6db7aa00fba8f35d63
+oid sha256:9c1b23aaed051ed481c39ea40a3e82c5331271913ccdd23c7f8081422f8ae692
 size 4781670360

model-00006-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9894acb53032b6e041aa0cc0f04a7ac469271ce586fc3cb668046c980b4e1c98
+oid sha256:6db542d71ddd59b6a67c9ed4b7334d8332ffa4861404988a2494c690268ab37d
 size 4964101416

model-00007-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26353391e8172671035fb28c0f9eeacb2640861c4810eb71e818b83d385e7661
+oid sha256:3b24e8e988e3fe3535e418e3e684c1492abbfd71c3b90bc67b302a2d137e2b9e
 size 4781637360

model-00008-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e69ede2230a527aaf5f0682ec5fbe024225072d8872a35cde6fd1f02628a1aaa
+oid sha256:f30e468d7b2bb60dbb07b5e06a5ea6a1b643259008229b7fe8528e021f2a2959
 size 4781670360

model-00009-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ff7dba638d6de35a8645ffc99187234da7cf0bfedbcdfb1a574282d9e3b4a5e
+oid sha256:bad1c66f843d673c76981aede2e71885f980c822db2a9de6fbaa930efd850746
 size 4781670360

model-00010-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:224ef0f6b77c28660ca872db218a01c205c4b91c21c6f4903adb240f1feaf1f8
+oid sha256:4e085342b552524cc33cedb08dfa6f5a4c881a3fed8918e97a8e4fcb3ac80b03
 size 4964101416

model-00011-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:659a24bd9c681cd7cd8eb93cdbbffcc79dea955cd4887f37bd1799ad24e69a8c
+oid sha256:fdeb8896eace98de23f6f60ac8017d4ac949dcd9a8cfad7f121174fede19060a
 size 4781637360

model-00012-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40484b390a629b6e841385e30f26340222aa8c0093f46d60340580565235dbd9
+oid sha256:309663424be5d3411d3ea082ef32dab0b938174d09a01449d8c407d5deef3843
 size 4781670360

model-00013-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83104b9bb184383b0bf37aab2239213001189737ea57d68811ed9964d7a6dca7
+oid sha256:2652aad21e220cf400a80cf51f0efab26aaf5ca82a1914e8d87996687abb536d
 size 4781670360

model-00014-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ce46a4c2dc37bdf983941c0526d69d2b813d735ae0aeb876a6087229dc417e9
+oid sha256:80e3663ddc50d1ee75c9d0480683d0e7154f714273de2ad864ade8dd3df34d4b
 size 4964101416

model-00015-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4847faed6468d33dcd1788e2710fa69ccb3af19cd8596666083222dac817d24
+oid sha256:ac7c56ef75b6d046fd90ebe0050ac5de840df19bd45a96451e305cfe9d1dba3a
 size 4781637360

model-00016-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c127df484608133e95f54d275190f407045546131c9592f2572b2441737e7f00
+oid sha256:0460408b2b66060a20711101b022757974139da010ce2edc20caf922f7dd87de
 size 4781670360

model-00017-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c45204750c9e3811f1f1ffae752f5ee6b21ac10b4a7a1e1d86b1dfb50bf7e3d
+oid sha256:59c74e03211e88e887c0a2dfbb29d9e7c91b47317f5e003c82cbe93e1f3d9e6b
 size 4781670360

model-00018-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c62fcd870f1b623db6cb09c9e79ca81144ec6f185e0498e46aa13bc131d7d89
+oid sha256:a2da48b942e7948a23a6d103d52e97cbcef7641bbabb170c4b5618ef2c90e0ce
 size 4964101416

model-00019-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d409e6527535f1a390bad83d35fd9854e43b362c96f422fe5c0564c3639a6be2
+oid sha256:336e670f79a889bc6d47f82c2449fb17aabec75198522babc0d3314a416d3929
 size 4781637360

model-00020-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31084d34a4ab0bfadba9c2f8291f92c8935eacbb5f300018ae7f215c69ac2d41
+oid sha256:db03317c42415b6084f64ff9894bc592ed9d4ab27be7e1623bcd365d63541cf1
 size 4781670360

model-00021-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52d14a8c3d34fd4017dec29421d18f8aae080e7e40a5584f7d426ddde143a7c3
+oid sha256:c198ceb9d0f3f143555ce224a54b7bfed56567a32e1c0033303aa33e56eeb32a
 size 4781670360

model-00022-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d960bf183aa80d626d58d8cae7c77a6b3a790e4b5b3780631e60d9337b08a404
+oid sha256:99fb1792514f2023bbdd0f24857f8c9a67cf02e23533cb36cf9789eae2bba764
 size 4964101416

model-00023-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18e0b8b591fbe6b65cc551f23cacdf65b704333ff06a60661cb90373812f60d9
+oid sha256:97416ceb35110eb5f6c6190d2838d9ce8607a3e7a3628b7d0814aa259ea51873
 size 4781637360

model-00024-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5908f63dac691fbf0bb05873263cfc42e4256f04ec6751b01052e1a7a10e9139
+oid sha256:6b8016f6eeb4aa40499aac041d304a02953ed9a913ad167643f87eb22f5b5228
 size 4781670360

model-00025-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6aa32b5839014fb96b10ddf685c0b7895ce54de4048917f1a15109a3ff497d50
+oid sha256:825e62f6324f526303118e10a8d2d4b8b17bbea51d6a0654cee01847f5c166fe
 size 4781670360

model-00026-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca4f2b8ce19789b17e2926ed859b17007f4828f5508af163b9c70bd2c7ad6ad9
+oid sha256:ea890f79c0e9e5c2596488a721b9f2a6465c4f81383501001c5913f8725cfc8c
 size 4964101416

model-00027-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2fe48f82357032630f6bcb1c7e191a9362f1602498709c2889f8cb3f4aaedbf3
+oid sha256:c50c9a253d5134050621c59a88d1b76068da9ccac992ff0423c9c2e8ec2fa86b
 size 4781637360

model-00028-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0868ceb592ef939c9703dca6b5e985abe32a797a5a2fcd08db6260cef94b835
+oid sha256:2208f65e374c549b0907c3a58d28ac863d0213a9afeb84bf7d3039215c0a2dcc
 size 4781670360

model-00029-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bca7d7b0a094b243e47d96ff300a0e3a657df7353000e4221a899c9908f53e6
+oid sha256:480c9ee2879cd9720c9521223034fa56b050f85b47c65d7eaede2f657e25b6b4
 size 4781670360

model-00030-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ade1434e683b8cc9c98732b463dca7b91a9a513a350ffad97e1e7fcb067dd5ca
+oid sha256:1ad84bdc2f43ebd9d679c449e8ce3df564d613034eaaca2a944c5c8baa8a4143
 size 3208747032

sft_args.json

@@ -7,17 +7,22 @@
   "additional_trainable_parameters": [],
   "tuner_backend": "peft",
   "template_type": "qwen",
-  "output_dir": "/root/swift/output/qwen2-72b-instruct/v6-20240730-130324",
+  "output_dir": "/root/swift/esft/output/qwen2-72b-instruct/v20-20240816-082726",
   "add_output_dir_suffix": true,
   "ddp_backend": "nccl",
   "ddp_find_unused_parameters": null,
   "ddp_broadcast_buffers": null,
   "seed": 42,
-  "resume_from_checkpoint": "/root/swift/output/qwen2-72b-instruct/v5-20240730-113708/checkpoint-700",
+  "resume_from_checkpoint": null,
   "resume_only_model": false,
   "ignore_data_skip": false,
   "dtype": "bf16",
   "packing": false,
+  "train_backend": "transformers",
+  "tp": 1,
+  "pp": 1,
+  "min_lr": null,
+  "sequence_parallel": false,
   "dataset": [
     "dataset/moni_dataset.jsonl",
     "dataset/moni_dataset.jsonl",
@@ -29,28 +34,20 @@
     "dataset/covid_new.jsonl",
     "dataset/covid_new.jsonl",
     "dataset/covid_new.jsonl",
-    "dataset/covid_new.jsonl",
-    "dataset/ds_new.jsonl",
-    "dataset/ds_new.jsonl",
-    "dataset/ds_new.jsonl",
-    "dataset/ds_new.jsonl",
-    "dataset/ds_new.jsonl",
-    "dataset/ds_new.jsonl",
     "dataset/ds_new.jsonl",
     "dataset/ds_new.jsonl",
     "dataset/ds_new.jsonl",
     "dataset/ds_new.jsonl",
     "dataset/ds_new.jsonl",
     "dataset/ds_new.jsonl",
-    "HF::roleplay-base#2500",
-    "iic/MSAgent-MultiRole#1000",
-    "AI-ModelScope/wikipedia-cn-20230720-filtered#500",
-    "AI-ModelScope/ruozhiba#500",
-    "modelscope/chinese-poetry-collection#1000",
-    "AI-ModelScope/webnovel_cn#500"
+    "iic/ms_bench#2500",
+    "HF::roleplay-base#1500",
+    "iic/MSAgent-MultiRole#1500",
+    "AI-ModelScope/ruozhiba#1000",
+    "modelscope/chinese-poetry-collection#500"
   ],
   "val_dataset": [
-    "dataset/ds_new.jsonl"
+    "dataset/moni_dataset.jsonl#50"
   ],
   "dataset_seed": 42,
   "dataset_test_ratio": 0.0,
@@ -61,6 +58,9 @@
   "max_length": 1500,
   "truncation_strategy": "delete",
   "check_dataset_strategy": "warning",
+  "streaming": false,
+  "streaming_val_size": 0,
+  "streaming_buffer_size": 16384,
   "model_name": [
     null,
     null
@@ -77,40 +77,39 @@
   "bnb_4bit_quant_type": "nf4",
   "bnb_4bit_use_double_quant": true,
   "bnb_4bit_quant_storage": null,
-  "lora_target_modules": [],
-  "lora_target_regex": null,
+  "rescale_image": -1,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "target_regex": null,
+  "modules_to_save": [],
   "lora_rank": 16,
   "lora_alpha": 32,
-  "lora_dropout_p": 0.06,
+  "lora_dropout": 0.06,
   "lora_bias_trainable": "none",
-  "lora_modules_to_save": [],
-  "lora_dtype": "AUTO",
+  "lora_dtype": null,
   "lora_lr_ratio": null,
   "use_rslora": false,
   "use_dora": false,
-  "init_lora_weights": "true",
+  "init_lora_weights": true,
+  "fourier_n_frequency": 2000,
+  "fourier_scaling": 300.0,
   "rope_scaling": null,
   "boft_block_size": 4,
   "boft_block_num": 0,
   "boft_n_butterfly_factor": 1,
-  "boft_target_modules": [
-    "DEFAULT"
-  ],
   "boft_dropout": 0.0,
-  "boft_modules_to_save": [],
   "vera_rank": 256,
-  "vera_target_modules": [
-    "DEFAULT"
-  ],
   "vera_projection_prng_key": 0,
   "vera_dropout": 0.0,
   "vera_d_initial": 0.1,
-  "vera_modules_to_save": [],
   "adapter_act": "gelu",
   "adapter_length": 128,
   "use_galore": false,
-  "galore_rank": 128,
   "galore_target_modules": null,
+  "galore_rank": 128,
   "galore_update_proj_gap": 50,
   "galore_scale": 1.0,
   "galore_proj_type": "std",
@@ -131,11 +130,7 @@
   "adalora_beta1": 0.85,
   "adalora_beta2": 0.85,
   "adalora_orth_reg_weight": 0.5,
-  "ia3_target_modules": [
-    "DEFAULT"
-  ],
   "ia3_feedforward_modules": [],
-  "ia3_modules_to_save": [],
   "llamapro_num_new_blocks": 4,
   "llamapro_num_groups": null,
   "neftune_noise_alpha": null,
@@ -144,13 +139,13 @@
   "lisa_step_interval": 20,
   "gradient_checkpointing": true,
   "deepspeed": null,
-  "batch_size": 2,
-  "eval_batch_size": 2,
+  "batch_size": 1,
+  "eval_batch_size": 1,
   "num_train_epochs": 8,
   "max_steps": -1,
   "optim": "adamw_torch",
   "adam_beta1": 0.9,
-  "adam_beta2": 0.999,
+  "adam_beta2": 0.95,
   "adam_epsilon": 1e-08,
   "learning_rate": 0.0001,
   "weight_decay": 0.1,
@@ -182,12 +177,12 @@
   "use_flash_attn": true,
   "ignore_args_error": false,
   "check_model_is_latest": true,
-  "logging_dir": "/root/swift/output/qwen2-72b-instruct/v6-20240730-130324/runs",
+  "logging_dir": "/root/swift/esft/output/qwen2-72b-instruct/v20-20240816-082726/runs",
   "report_to": [
     "tensorboard"
   ],
   "acc_strategy": "token",
-  "save_on_each_node": true,
+  "save_on_each_node": false,
   "evaluation_strategy": "steps",
   "save_strategy": "steps",
   "save_safetensors": true,
@@ -226,20 +221,39 @@
   "neftune_alpha": null,
   "deepspeed_config_path": null,
   "model_cache_dir": null,
+  "lora_dropout_p": 0.06,
+  "lora_target_modules": [
+    "q_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "lora_target_regex": null,
+  "lora_modules_to_save": [],
+  "boft_target_modules": [],
+  "boft_modules_to_save": [],
+  "vera_target_modules": [],
+  "vera_modules_to_save": [],
+  "ia3_target_modules": [],
+  "ia3_modules_to_save": [],
   "custom_train_dataset_path": [],
   "custom_val_dataset_path": [],
   "use_self_cognition": false,
   "is_multimodal": false,
+  "is_vision": false,
   "lora_use_embedding": false,
-  "lora_use_all": true,
+  "lora_use_all": false,
   "lora_m2s_use_embedding": false,
   "lora_m2s_use_ln": false,
   "torch_dtype": "torch.bfloat16",
   "fp16": false,
   "bf16": true,
+  "rank": 0,
+  "local_rank": 0,
+  "world_size": 1,
+  "local_world_size": 1,
   "bnb_4bit_compute_dtype": "torch.bfloat16",
   "load_in_4bit": false,
   "load_in_8bit": false,
   "train_sampler_random": true,
-  "training_args": "Seq2SeqTrainingArguments(output_dir='/root/swift/output/qwen2-72b-instruct/v6-20240730-130324', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, eval_strategy=<IntervalStrategy.STEPS: 'steps'>, prediction_loss_only=False, per_device_train_batch_size=2, per_device_eval_batch_size=2, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=16, eval_accumulation_steps=None, eval_delay=0, learning_rate=0.0001, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.999, adam_epsilon=1e-08, max_grad_norm=0.5, num_train_epochs=8, max_steps=-1, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs={}, warmup_ratio=0.03, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/root/swift/output/qwen2-72b-instruct/v6-20240730-130324/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=5, logging_nan_inf_filter=True, save_strategy=<IntervalStrategy.STEPS: 'steps'>, save_steps=50, save_total_limit=None, save_safetensors=True, save_on_each_node=True, save_only_model=False, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=None, 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='nccl', tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=50, dataloader_num_workers=1, dataloader_prefetch_factor=None, past_index=-1, run_name='/root/swift/output/qwen2-72b-instruct/v6-20240730-130324', 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=None, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None), deepspeed=None, label_smoothing_factor=0.0, optim=<OptimizerNames.ADAMW_TORCH: 'adamw_torch'>, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['tensorboard'], ddp_find_unused_parameters=False, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=False, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint='/root/swift/output/qwen2-72b-instruct/v5-20240730-113708/checkpoint-700', hub_model_id=None, hub_strategy=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_token=None, hub_private_repo=False, hub_always_push=False, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, eval_do_concat_batches=True, fp16_backend='auto', evaluation_strategy=None, 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=1800, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, dispatch_batches=None, split_batches=None, include_tokens_per_second=False, include_num_input_tokens_seen=False, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, sortish_sampler=True, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=GenerationConfig {\n  \"do_sample\": true,\n  \"eos_token_id\": 151645,\n  \"max_new_tokens\": 2048,\n  \"pad_token_id\": 151643,\n  \"temperature\": 0.3,\n  \"top_k\": 20,\n  \"top_p\": 0.7\n}\n, train_sampler_random=True, push_hub_strategy='push_best', acc_strategy='token', additional_saved_files=[], metric_warmup_step=0, train_dataset_sample=17395)"
+  "training_args": "Seq2SeqTrainingArguments(output_dir='/root/swift/esft/output/qwen2-72b-instruct/v20-20240816-082726', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, eval_strategy=<IntervalStrategy.STEPS: 'steps'>, prediction_loss_only=False, per_device_train_batch_size=1, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=16, eval_accumulation_steps=None, eval_delay=0, learning_rate=0.0001, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=0.5, num_train_epochs=8, max_steps=-1, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs={}, warmup_ratio=0.03, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/root/swift/esft/output/qwen2-72b-instruct/v20-20240816-082726/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=5, logging_nan_inf_filter=True, save_strategy=<IntervalStrategy.STEPS: 'steps'>, save_steps=50, 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=None, 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='nccl', tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=50, dataloader_num_workers=1, dataloader_prefetch_factor=None, past_index=-1, run_name='/root/swift/esft/output/qwen2-72b-instruct/v20-20240816-082726', 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), deepspeed=None, label_smoothing_factor=0.0, optim=<OptimizerNames.ADAMW_TORCH: 'adamw_torch'>, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['tensorboard'], ddp_find_unused_parameters=False, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=False, 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=False, hub_always_push=False, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, eval_do_concat_batches=True, fp16_backend='auto', evaluation_strategy=None, 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=1800, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, dispatch_batches=None, split_batches=None, include_tokens_per_second=False, include_num_input_tokens_seen=False, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, sortish_sampler=True, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=GenerationConfig {\n  \"do_sample\": true,\n  \"eos_token_id\": 151645,\n  \"max_new_tokens\": 2048,\n  \"pad_token_id\": 151643,\n  \"temperature\": 0.3,\n  \"top_k\": 20,\n  \"top_p\": 0.7\n}\n, train_sampler_random=True, push_hub_strategy='push_best', acc_strategy='token', additional_saved_files=[], metric_warmup_step=0, train_dataset_sample=-1)"
 }