Upload folder using huggingface_hub

added_tokens.json

@@ -1,5 +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
+  "<|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
 }

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/root/.cache/modelscope/hub/qwen/Qwen2-72B-Instruct",
+  "_name_or_path": "/root/.cache/modelscope/hub/qwen/Qwen2___5-72B-Instruct",
   "architectures": [
     "Qwen2ForCausalLM"
   ],
@@ -11,7 +11,7 @@
   "initializer_range": 0.02,
   "intermediate_size": 29568,
   "max_position_embeddings": 32768,
-  "max_window_layers": 80,
+  "max_window_layers": 70,
   "model_type": "qwen2",
   "num_attention_heads": 64,
   "num_hidden_layers": 80,

configuration.json

@@ -1,4 +1 @@
-{
-    "framework": "Pytorch",
-    "task": "text-generation"
-}
+{}

generation_config.json

@@ -1,10 +1,12 @@
 {
+  "bos_token_id": 151643,
   "do_sample": true,
   "eos_token_id": 151645,
   "max_new_tokens": 2048,
   "pad_token_id": 151643,
-  "temperature": 0.3,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
   "top_k": 20,
-  "top_p": 0.7,
+  "top_p": 0.8,
   "transformers_version": "4.41.2"
 }

model-00001-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35253e0c7350c0bd420cb9519a06e5e37b903c335f8bb0b6c4d75813714ef8d1
+oid sha256:183977221b774fc6b74b788b5d641abf9c40730a299afc36c789750c6a9dfc0d
 size 4548798728

model-00002-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c00caadc732abd452255c0bd3f70bd41071fa97affae43bbc9d711d592f6a98f
+oid sha256:783cfcc7d19aee474af26d99e0b3dbfeac21c601fd77655de471d57f172d46e7
 size 4964101384

model-00003-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29d5f9f3f7e953c39ab7c4edc1b0374c495448c802d05cc8bc48003c88b79dd9
+oid sha256:692a087d52c4c5d23b55ff041f7f7191fd30a19868ff8101c2490475d84aad97
 size 4781637328

model-00004-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fd9707278e108e943a1a480c5c458031abe846bf55fb6d3d1f113429d12b4fe
+oid sha256:b9175c7ced898030e6bb46caa982688048de557487b09c993da9e01e97825ccf
 size 4781670320

model-00005-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c1b23aaed051ed481c39ea40a3e82c5331271913ccdd23c7f8081422f8ae692
+oid sha256:42516c55390c588d324a55ed73d86cd46847489d19085af6bc4eb02e5c6f5332
 size 4781670360

model-00006-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6db542d71ddd59b6a67c9ed4b7334d8332ffa4861404988a2494c690268ab37d
+oid sha256:1644657864597df1165bcad06235b29ace7af41a351a9adefcee9c9af25be4d2
 size 4964101416

model-00007-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b24e8e988e3fe3535e418e3e684c1492abbfd71c3b90bc67b302a2d137e2b9e
+oid sha256:7163276dd5dea8cfa25b227f966cbdb60548c550ade1483f0f812d73b7013294
 size 4781637360

model-00008-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f30e468d7b2bb60dbb07b5e06a5ea6a1b643259008229b7fe8528e021f2a2959
+oid sha256:cf513ba1c97f4d06e7e960094395e792e237d45f206683b284593c440ead7231
 size 4781670360

model-00009-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bad1c66f843d673c76981aede2e71885f980c822db2a9de6fbaa930efd850746
+oid sha256:8a078e25cdd4990607f470a271d20c5af1db687a401039257cfe44dac4ce4eed
 size 4781670360

model-00010-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e085342b552524cc33cedb08dfa6f5a4c881a3fed8918e97a8e4fcb3ac80b03
+oid sha256:0d59dd5858e18bec7a4a0bce3a1e5da3a295901412123ccc3cbf13b1e9b05fc5
 size 4964101416

model-00011-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdeb8896eace98de23f6f60ac8017d4ac949dcd9a8cfad7f121174fede19060a
+oid sha256:9cc5af829b6bf99f8c891b30707289849513504e3c87f796bfaaea8d37d19db1
 size 4781637360

model-00012-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:309663424be5d3411d3ea082ef32dab0b938174d09a01449d8c407d5deef3843
+oid sha256:c766bda4161c342e26bf0bb11827a60f273c8f1ec35cbdbdc4598165827c62ab
 size 4781670360

model-00013-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2652aad21e220cf400a80cf51f0efab26aaf5ca82a1914e8d87996687abb536d
+oid sha256:f8b5cc8ded87c627bc7eeed87500d77eb54286a53e7f5dcc5c1b19047ef00a8a
 size 4781670360

model-00014-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80e3663ddc50d1ee75c9d0480683d0e7154f714273de2ad864ade8dd3df34d4b
+oid sha256:142c289aa43877b9c78440ca907f0e01ee86a44992376a41b11b56a6c3572f66
 size 4964101416

model-00015-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac7c56ef75b6d046fd90ebe0050ac5de840df19bd45a96451e305cfe9d1dba3a
+oid sha256:17a41a25dfe3d33b4becbc756003353323d84fd6a4b1f42e925249f2d0dafe53
 size 4781637360

model-00016-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0460408b2b66060a20711101b022757974139da010ce2edc20caf922f7dd87de
+oid sha256:3551c708511849eb71d7a134d25a3ca0fac0f67dfb6fe70e3667ba4eb5126220
 size 4781670360

model-00017-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59c74e03211e88e887c0a2dfbb29d9e7c91b47317f5e003c82cbe93e1f3d9e6b
+oid sha256:d7315e1d5a490dbdfe8b1934ad7e366ad32c9bc8225ee09616d3373a2280dad8
 size 4781670360

model-00018-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2da48b942e7948a23a6d103d52e97cbcef7641bbabb170c4b5618ef2c90e0ce
+oid sha256:d75ebe7889f70cf7f71858b6ffbe5bf9365d74cfeaaa6bb13fc25dfd70c82ba3
 size 4964101416

model-00019-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:336e670f79a889bc6d47f82c2449fb17aabec75198522babc0d3314a416d3929
+oid sha256:a129ab89873549da1ab9af4f693793792c019bffc5c88da6cb008303925cce00
 size 4781637360

model-00020-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db03317c42415b6084f64ff9894bc592ed9d4ab27be7e1623bcd365d63541cf1
+oid sha256:555fbfb9701a60dcb1dbd54b5ac258667e176bb305b0ba344c636fc16b409475
 size 4781670360

model-00021-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c198ceb9d0f3f143555ce224a54b7bfed56567a32e1c0033303aa33e56eeb32a
+oid sha256:e035809d8ce1b4acf3fd68cfb46497bed6da91a2c2ba91f4ff7f2dc737122ccc
 size 4781670360

model-00022-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99fb1792514f2023bbdd0f24857f8c9a67cf02e23533cb36cf9789eae2bba764
+oid sha256:ccf96ad5e02a6d016d4035af9d7888d25897cc7de7496e23cdf0559b90e77b86
 size 4964101416

model-00023-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97416ceb35110eb5f6c6190d2838d9ce8607a3e7a3628b7d0814aa259ea51873
+oid sha256:c5740a22381c7dce1e598d2c5cc7c137482da517dc50bb5b3274a1837ea3b38c
 size 4781637360

model-00024-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b8016f6eeb4aa40499aac041d304a02953ed9a913ad167643f87eb22f5b5228
+oid sha256:126eab57ebe5b2cd479197d9dbb9182232316f05c1d09afe46efefde6b3a8eae
 size 4781670360

model-00025-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:825e62f6324f526303118e10a8d2d4b8b17bbea51d6a0654cee01847f5c166fe
+oid sha256:13c931d0169775ce7ff86154e8a2a3c57c14dc6121242994e969a66cc65b8267
 size 4781670360

model-00026-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea890f79c0e9e5c2596488a721b9f2a6465c4f81383501001c5913f8725cfc8c
+oid sha256:7b7d3d8b8646bb502804835705a24daeeb7d6727b5ae4e07d818c95ae1191aaf
 size 4964101416

model-00027-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c50c9a253d5134050621c59a88d1b76068da9ccac992ff0423c9c2e8ec2fa86b
+oid sha256:6875d3ec11a2760636d9dc94ae3073903f4f2c5b2676e8a74aa408e03aecdad8
 size 4781637360

model-00028-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2208f65e374c549b0907c3a58d28ac863d0213a9afeb84bf7d3039215c0a2dcc
+oid sha256:291ce9cac316c735d67b32d607d45020718d4f54f8aafb183a7efbc051f67869
 size 4781670360

model-00029-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:480c9ee2879cd9720c9521223034fa56b050f85b47c65d7eaede2f657e25b6b4
+oid sha256:34ee59c8130753d15299792fd9a8a6b2a54d23110a565c55a14dcf3a2ded14f8
 size 4781670360

model-00030-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ad84bdc2f43ebd9d679c449e8ce3df564d613034eaaca2a944c5c8baa8a4143
+oid sha256:4fa8fd2a1f702e7e1591a00ea7f597abfab722ed0651799e4de2e9b621c0afe3
 size 3208747032

model-00031-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f09a8b10be984a06c4d8118f1c0c0370ff97ccec72a584aead0d14639b1683a
+oid sha256:cdbc8f91c574681655bd34786cb3923093027809999083ab1843ea595d8b9a49
 size 2491416704

sft_args.json

@@ -1,17 +1,21 @@
 {
-  "model_type": "qwen2-72b-instruct",
-  "model_id_or_path": "qwen/Qwen2-72B-Instruct",
+  "model_type": "qwen2_5-72b-instruct",
+  "model_id_or_path": "qwen/Qwen2.5-72B-Instruct",
   "model_revision": "master",
+  "full_determinism": false,
   "sft_type": "full",
-  "freeze_parameters": 0.0,
+  "freeze_parameters": [],
+  "freeze_vit": false,
+  "freeze_parameters_ratio": 0.0,
   "additional_trainable_parameters": [],
   "tuner_backend": "peft",
-  "template_type": "qwen",
-  "output_dir": "/root/swift/esft/output/qwen2-72b-instruct/v20-20240816-082726",
+  "template_type": "qwen2_5",
+  "output_dir": "/root/swift/esft/output/qwen2_5-72b-instruct/v1-20240927-003554",
   "add_output_dir_suffix": true,
   "ddp_backend": "nccl",
   "ddp_find_unused_parameters": null,
   "ddp_broadcast_buffers": null,
+  "ddp_timeout": 1800,
   "seed": 42,
   "resume_from_checkpoint": null,
   "resume_only_model": false,
@@ -23,28 +27,17 @@
   "pp": 1,
   "min_lr": null,
   "sequence_parallel": false,
+  "model_kwargs": {},
+  "loss_name": null,
   "dataset": [
-    "dataset/moni_dataset.jsonl",
-    "dataset/moni_dataset.jsonl",
-    "dataset/moni_dataset.jsonl",
     "dataset/moni_dataset.jsonl",
     "dataset/moni_dataset_en.jsonl",
-    "dataset/moni_dataset_en.jsonl",
-    "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",
-    "iic/ms_bench#2500",
-    "HF::roleplay-base#1500",
-    "iic/MSAgent-MultiRole#1500",
-    "AI-ModelScope/ruozhiba#1000",
-    "modelscope/chinese-poetry-collection#500"
+    "AI-ModelScope/deepctrl-sft-data:default#1600",
+    "AI-ModelScope/deepctrl-sft-data:en#1100",
+    "AI-ModelScope/ruozhiba#250"
   ],
   "val_dataset": [
     "dataset/moni_dataset.jsonl#50"
@@ -55,7 +48,7 @@
   "loss_scale_config_path": "/root/swift/swift_new/lib/python3.11/site-packages/swift/llm/agent/default_loss_scale_config.json",
   "system": "None",
   "tools_prompt": "react_en",
-  "max_length": 1500,
+  "max_length": 1344,
   "truncation_strategy": "delete",
   "check_dataset_strategy": "warning",
   "streaming": false,
@@ -79,15 +72,19 @@
   "bnb_4bit_quant_storage": null,
   "rescale_image": -1,
   "target_modules": [
-    "q_proj",
     "k_proj",
-    "v_proj"
+    "gate_proj",
+    "q_proj",
+    "down_proj",
+    "v_proj",
+    "o_proj",
+    "up_proj"
   ],
   "target_regex": null,
   "modules_to_save": [],
   "lora_rank": 16,
   "lora_alpha": 32,
-  "lora_dropout": 0.06,
+  "lora_dropout": 0.05,
   "lora_bias_trainable": "none",
   "lora_dtype": null,
   "lora_lr_ratio": null,
@@ -137,11 +134,18 @@
   "neftune_backend": "transformers",
   "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,
+  "use_liger": false,
   "gradient_checkpointing": true,
   "deepspeed": null,
-  "batch_size": 1,
+  "batch_size": 2,
   "eval_batch_size": 1,
-  "num_train_epochs": 8,
+  "auto_find_batch_size": false,
+  "num_train_epochs": 20,
   "max_steps": -1,
   "optim": "adamw_torch",
   "adam_beta1": 0.9,
@@ -150,7 +154,7 @@
   "learning_rate": 0.0001,
   "weight_decay": 0.1,
   "gradient_accumulation_steps": 16,
-  "max_grad_norm": 0.5,
+  "max_grad_norm": 1.0,
   "predict_with_generate": false,
   "lr_scheduler_type": "cosine",
   "lr_scheduler_kwargs": {},
@@ -169,7 +173,7 @@
   "hub_model_id": null,
   "hub_token": null,
   "hub_private_repo": false,
-  "push_hub_strategy": "push_best",
+  "hub_strategy": "every_save",
   "test_oom_error": false,
   "disable_tqdm": false,
   "lazy_tokenize": false,
@@ -177,7 +181,7 @@
   "use_flash_attn": true,
   "ignore_args_error": false,
   "check_model_is_latest": true,
-  "logging_dir": "/root/swift/esft/output/qwen2-72b-instruct/v20-20240816-082726/runs",
+  "logging_dir": "/root/swift/esft/output/qwen2_5-72b-instruct/v1-20240927-003554/runs",
   "report_to": [
     "tensorboard"
   ],
@@ -191,14 +195,14 @@
   "local_repo_path": null,
   "custom_register_path": null,
   "custom_dataset_info": "/root/swift/dataset/ds_info.json",
-  "device_map_config_path": null,
+  "device_map_config": null,
   "device_max_memory": [],
   "max_new_tokens": 2048,
-  "do_sample": true,
-  "temperature": 0.3,
-  "top_k": 20,
-  "top_p": 0.7,
-  "repetition_penalty": 1.0,
+  "do_sample": null,
+  "temperature": null,
+  "top_k": null,
+  "top_p": null,
+  "repetition_penalty": null,
   "num_beams": 1,
   "fsdp": "",
   "fsdp_config": null,
@@ -221,11 +225,15 @@
   "neftune_alpha": null,
   "deepspeed_config_path": null,
   "model_cache_dir": null,
-  "lora_dropout_p": 0.06,
+  "lora_dropout_p": 0.05,
   "lora_target_modules": [
-    "q_proj",
     "k_proj",
-    "v_proj"
+    "gate_proj",
+    "q_proj",
+    "down_proj",
+    "v_proj",
+    "o_proj",
+    "up_proj"
   ],
   "lora_target_regex": null,
   "lora_modules_to_save": [],
@@ -237,11 +245,13 @@
   "ia3_modules_to_save": [],
   "custom_train_dataset_path": [],
   "custom_val_dataset_path": [],
+  "device_map_config_path": null,
+  "push_hub_strategy": null,
   "use_self_cognition": false,
   "is_multimodal": false,
   "is_vision": false,
   "lora_use_embedding": false,
-  "lora_use_all": false,
+  "lora_use_all": true,
   "lora_m2s_use_embedding": false,
   "lora_m2s_use_ln": false,
   "torch_dtype": "torch.bfloat16",
@@ -255,5 +265,6 @@
   "load_in_4bit": false,
   "load_in_8bit": false,
   "train_sampler_random": true,
-  "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)"
+  "train_type": "sft",
+  "training_args": "Seq2SeqTrainingArguments(output_dir='/root/swift/esft/output/qwen2_5-72b-instruct/v1-20240927-003554', 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=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=1.0, num_train_epochs=20, 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_5-72b-instruct/v1-20240927-003554/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=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='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_5-72b-instruct/v1-20240927-003554', 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=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=GenerationConfig {\n  \"bos_token_id\": 151643,\n  \"do_sample\": true,\n  \"eos_token_id\": 151645,\n  \"max_new_tokens\": 2048,\n  \"pad_token_id\": 151643,\n  \"repetition_penalty\": 1.05,\n  \"temperature\": 0.7,\n  \"top_k\": 20,\n  \"top_p\": 0.8\n}\n, acc_strategy='token', loss_name=None, additional_saved_files=[], train_sampler_random=True, metric_warmup_step=0, train_dataset_sample=-1)"
 }

special_tokens_map.json

@@ -1,7 +1,18 @@
 {
   "additional_special_tokens": [
     "<|im_start|>",
-    "<|im_end|>"
+    "<|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": "<|im_end|>",
   "pad_token": {

tokenizer.json

@@ -29,6 +29,177 @@
       "rstrip": false,
       "normalized": false,
       "special": true
+    },
+    {
+      "id": 151646,
+      "content": "<|object_ref_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 151647,
+      "content": "<|object_ref_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 151648,
+      "content": "<|box_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 151649,
+      "content": "<|box_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 151650,
+      "content": "<|quad_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 151651,
+      "content": "<|quad_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 151652,
+      "content": "<|vision_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 151653,
+      "content": "<|vision_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 151654,
+      "content": "<|vision_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 151655,
+      "content": "<|image_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 151656,
+      "content": "<|video_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 151657,
+      "content": "<tool_call>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    {
+      "id": 151658,
+      "content": "</tool_call>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    {
+      "id": 151659,
+      "content": "<|fim_prefix|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    {
+      "id": 151660,
+      "content": "<|fim_middle|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    {
+      "id": 151661,
+      "content": "<|fim_suffix|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    {
+      "id": 151662,
+      "content": "<|fim_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    {
+      "id": 151663,
+      "content": "<|repo_name|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    {
+      "id": 151664,
+      "content": "<|file_sep|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
     }
   ],
   "normalizer": {

tokenizer_config.json

@@ -1,4 +1,5 @@
 {
+  "add_bos_token": false,
   "add_prefix_space": false,
   "added_tokens_decoder": {
     "151643": {
@@ -24,14 +25,177 @@
       "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|>"
+    "<|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,
-  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\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>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\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\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|im_end|>",
   "errors": "replace",