Training in progress, epoch 1

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/root/.cache/huggingface/hub/models--Qwen--Qwen3-8B/snapshots/b968826d9c46dd6066d109eabc6255188de91218",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [],
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "k_proj",
+    "gate_proj",
+    "up_proj",
+    "down_proj",
+    "q_proj",
+    "o_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be87ecc37309e86562cc44f4661d83ad550a141651aa17116805fb7a3c9ed2e6
+size 43713984

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|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
+}

args.json

@@ -0,0 +1,397 @@
+{
+  "output_dir": "/app/outputs/sft-qwen3/v4-20260317-135206",
+  "overwrite_output_dir": false,
+  "do_train": false,
+  "do_eval": false,
+  "do_predict": false,
+  "eval_strategy": "epoch",
+  "prediction_loss_only": false,
+  "per_device_train_batch_size": 1,
+  "per_device_eval_batch_size": 1,
+  "per_gpu_train_batch_size": null,
+  "per_gpu_eval_batch_size": null,
+  "gradient_accumulation_steps": 8,
+  "eval_accumulation_steps": null,
+  "eval_delay": 0,
+  "torch_empty_cache_steps": null,
+  "learning_rate": 1e-05,
+  "weight_decay": 0.1,
+  "adam_beta1": 0.9,
+  "adam_beta2": 0.95,
+  "adam_epsilon": 1e-08,
+  "max_grad_norm": 1.0,
+  "num_train_epochs": 1.0,
+  "max_steps": -1,
+  "lr_scheduler_type": "cosine",
+  "lr_scheduler_kwargs": null,
+  "warmup_ratio": 0.05,
+  "warmup_steps": 0,
+  "log_level": "passive",
+  "log_level_replica": "warning",
+  "log_on_each_node": true,
+  "logging_dir": "/app/outputs/sft-qwen3/v4-20260317-135206/runs",
+  "logging_strategy": "steps",
+  "logging_first_step": true,
+  "logging_steps": 10,
+  "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": true,
+  "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,
+  "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": null,
+  "dataloader_num_workers": 4,
+  "dataloader_prefetch_factor": null,
+  "past_index": -1,
+  "run_name": "/app/outputs/sft-qwen3/v4-20260317-135206",
+  "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
+  },
+  "parallelism_config": null,
+  "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": [
+    "wandb"
+  ],
+  "project": "huggingface",
+  "trackio_space_id": "trackio",
+  "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": true,
+  "resume_from_checkpoint": null,
+  "hub_model_id": "StudioDesign/sft-qwen3",
+  "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,
+  "enable_channel_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,
+  "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,
+  "use_ray": false,
+  "ray_exp_name": null,
+  "device_groups": null,
+  "model": "Qwen/Qwen3-8B",
+  "model_type": "qwen3",
+  "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": "qwen3",
+  "system": "あなたはHTMLから、StudioDOM(デザイン情報が入ったjsonファイル)に変換するエキスパートです。\n\n# タスク\n与えられたHTMLソースコードを分析し、指定されたJSON形式に変換してください。\n\n# 入力\nHTMLソースコード: ウェブページの構造とスタイル情報\n\n# 出力\n以下の形式のStudioDOM(デザイン情報が入ったjsonファイル)\n\n# Studio DOM型定義\n\n## 基本型\n\n### DomBase\nすべてのDOM要素の基底インターフェース。\n```typescript\ninterface DomBase {\n  tagName?: string;       // HTMLタグ名\n  name?: string;          // 要素名\n  id?: string;            // HTML id属性\n  renderIf?: RenderIfDto; // 条件付きレンダリング\n  slot?: \"before\" | \"after\";\n}\n```\n\n### DomElement\nスタイルと属性を持つ要素の基底。\n```typescript\ninterface DomElement extends DomBase {\n  style?: StudioDomStyle;  // CSSスタイル定義\n  attrs?: StudioAttrs;     // HTML属性\n}\n```\n\n### DomLink\nリンク機能を持つ要素のミックスイン。\n```typescript\ntype DomLink = {\n  link?: { newTab: boolean; path: string };\n  action?: { type: \"link\" | \"modal\" | \"close\" | \"allowCookie\" | \"denyCookie\" | \"anchorLink\"; val?: string };\n}\n```\n\n## 要素型一覧\n\n### TextDom - テキスト要素\n```typescript\ninterface TextDom extends DomElement, DomLink {\n  content: { type: \"text\"; data: string };\n  classes?: string[];\n}\n```\n\n### ImgDom - 画像要素\n```typescript\ninterface ImgDom extends DomElement, DomLink {\n  content: { type: \"img\"; src: string; alt?: string };\n}\n```\n\n### BoxDom - コンテナ要素\n```typescript\ntype BoxDom = DomElement & DomLink & {\n  children: PublishedDom[];  // 子要素\n  content?: StudioDomContent | { type: \"image\"; src: string };\n  webComponents?: WebComponents;\n  transition?: ModalTransitionStyle;\n}\n```\n\n### IconDom - アイコン要素\n```typescript\ninterface IconDom extends DomElement, DomLink {\n  content: IconDomContent & { href?: string };\n}\ninterface IconDomContent {\n  type: \"icon\" | \"icon-fa\" | \"icon-solid\" | \"icon-brands\";\n  data: string;  // アイコン名\n}\ninterface IconDomContentMaterialSymbol {\n  type: \"icon-symbol\";\n  data: string;\n  fill: 0 | 1;\n  weight: 100 | 200 | 300 | 400 | 500 | 600 | 700;\n}\n```\n\n### IframeDom - iframe要素\n```typescript\ninterface IframeDom extends DomElement {\n  content: { type: \"iframe\" | \"sandbox\"; data: string };\n}\n```\n\n### InputDom - 入力フィールド\n```typescript\ninterface InputDom extends DomElement {\n  content: { type: \"input\" | \"textarea\" };\n  attrs: StudioAttrs & { placeholder?: string };\n}\n```\n\n### SelectDom - セレクトボックス\n```typescript\ninterface SelectDom extends DomElement {\n  content: { type: \"select\"; options: { label: string; value: string }[] };\n  attrs: StudioAttrs & { required: boolean; name: string };\n}\n```\n\n### ButtonDom - ボタン要素\n```typescript\ntype ButtonDom = DomElement & {\n  content: { type: \"button\" };\n  on?: { click?: string; blur?: string };\n  children: PublishedDom[];\n}\n```\n\n### FormDom - フォーム要素\n```typescript\ninterface FormDom extends DomElement {\n  content: { type: \"form\"; formSuccessPageId?: string };\n  children: PublishedDom[];\n}\n```\n\n### VideoDom - 動画要素\n```typescript\ninterface VideoDom extends DomElement {\n  content: {\n    type: \"video\";\n    src: string;\n    video?: {\n      autoplay?: boolean;\n      loop?: boolean;\n      controls?: boolean;\n      muted?: boolean;\n      poster?: string;\n      playsinline?: boolean;\n    };\n  };\n}\n```\n\n### LottieDom - Lottieアニメーション\n```typescript\ninterface LottieDom extends DomElement {\n  content: {\n    type: \"lottie\";\n    lottie?: {\n      playType?: \"autoplay\" | \"hover\" | \"scroll\" | \"cursor\" | \"click\" | \"appear\";\n      controls: boolean;\n      loop?: boolean;\n      speed?: number;\n      src: string;\n    };\n  };\n}\n```\n\n### SectionDom - セクション要素\n```typescript\ninterface SectionDom extends BoxDom {\n  type: \"section\";\n}\n```\n\n### RefDom - 参照要素（シンボル参照）\n```typescript\ninterface RefDom extends DomBase {\n  type: \"ref\";\n  refId: string;  // 参照先のID\n  state?: object;\n  props?: Record<string, string>;\n}\n```\n\n## 動的コンテンツ要素\n\n### ListDom - リスト要素\n配列データをループ表示。4種類のデータソースに対応。\n```typescript\n// 共通構造\ninterface ListDomBase extends DomElement, DomLink {\n  type: \"list\";\n  defs: [{ key: \"list\"; type: \"array\" | \"cmsRequest\"; uid: string }];\n  children: [ListItemDom] | [ListItemDom, BoxDom];  // アイテムテンプレート + ローディング表示\n}\n// データソース種別\n// - StateListDom: state.list に直接データを持つ\n// - PropsListDom: props.list でデータバインディング\n// - RSSListDom: props.list が \"$rss.{id}.items\" 形式\n// - CmsListDom: defs[0].type が \"cmsRequest\"\n```\n\n### CarouselDom - カルーセル要素\nスライド表示コンポーネント。\n```typescript\ninterface CarouselDom extends DomElement {\n  type: \"carousel\";\n  state: {\n    pageIndex: number;\n    maxLength: number;\n    playing: boolean;\n    autoDuration: number;\n    list: object[];\n  };\n  children: [CarouselTrackDom] | [CarouselTrackDom, CarouselControlDom];\n  on: { touchstart: string; touchmove: string; touchend: string };\n}\n```\n\n### SwitchDom - タブ/スイッチ要素\n複数コンテンツの切り替え表示。\n```typescript\ninterface SwitchDom extends DomElement, DomLink {\n  type: \"switch\";\n  defs: [{ key: \"option\"; type: \"option\"; options: { key: string; label: string }[] }];\n  state: { option: string };  // 選択中のオプションキー\n  children: [SwitchTabsDom, ...SwitchContentDom[]];\n}\n```\n\n### ToggleDom - トグル/アコーディオン要素\n開閉可能なコンテンツ。\n```typescript\ninterface ToggleDom extends DomElement, DomLink {\n  type: \"toggle\";\n  state: { isClose: boolean };\n  children: [ToggleLabelDom, ToggleContentDom];\n}\n```\n\n## 条件付きレンダリング (RenderIf)\n要素の表示条件を定義。\n```typescript\ntype RenderIfQuery =\n  | { fieldPath: string }                              // フィールドの存在確認\n  | { fieldPath: string; opStr: \"!\" }                  // 否定\n  | { fieldPath: string; opStr: \"===\"; value: string } // 等価比較\n  | { fieldPath: string; opStr: \"!==\"; value: string } // 不等価比較\n  | { fieldPath: string; opStr: \"relativeToToday\"; value: { amount: number; unit: \"year\" | \"month\" | \"week\" | \"day\" } };\n```\n\n## PublishedDom 統合型\nすべてのDOM型のユニオン。\n```typescript\ntype PublishedDom =\n  | IframeDom | TextDom | ImgDom | BoxDom | IconDom\n  | InputDom | SelectDom | ButtonDom | FormDom\n  | VideoDom | LottieDom | SectionDom | RefDom\n  | ListDom | CarouselDom | SwitchDom | ToggleDom\n  // ... その他の型\n```\n\n## 型判定ユーティリティ\n`$PublishedDom`オブジェクトで型判定可能。\n```typescript\n$PublishedDom.isTextDom(dom)      // TextDomか判定\n$PublishedDom.isImgDom(dom)       // ImgDomか判定\n$PublishedDom.isListDom(dom)      // ListDomか判定\n$PublishedDom.hasChildren(dom)    // 子要素を持つか判定\n$PublishedDom.hasStyle(dom)       // スタイルを持つか判定\n```\n\n# Examples\n\n## Example 1\n\n### Input\n```html\n<!DOCTYPE html>\n<html lang=\"\">\n<head>\n\n<meta charset=\"UTF-8\">\n<meta name=\"viewport\" content=\"width=device-width, initial-scale=1.0\">\n<title></title>\n<meta name=\"description\" content=\"\">\n<link rel=\"icon\" type=\"image/png\" href=\"https://storage.googleapis.com/studio-preview/favicon.svg\">\n<link rel=\"canonical\" href=\"https://template-preview.studio.design/8XKOkrRW4v/latest/\">\n<link rel=\"apple-touch-icon\" type=\"image/png\" href=\"https://storage.googleapis.com/studio-preview/favicon.svg\">\n<meta name=\"robots\" content=\"all\">\n<meta property=\"og:site_name\" content=\"\">\n<meta property=\"og:title\" content=\"\">\n<meta property=\"og:image\" content=\"\">\n<meta property=\"og:description\" content=\"\">\n<meta property=\"og:type\" content=\"website\">\n<meta property=\"twitter:card\" content=\"summary_large_image\">\n<meta property=\"twitter:image\" content=\"\">\n<meta name=\"apple-mobile-web-app-title\" content=\"\">\n<meta name=\"format-detection\" content=\"telephone=no,email=no,address=no\">\n<meta name=\"chrome\" content=\"nointentdetection\">\n<meta property=\"og:url\" content=\"https://template-preview.studio.design/8XKOkrRW4v/latest/\">\n\n\n<meta name=\"date\" content=\"2026-02-18T16:15:29+09:00\">\n<meta name=\"generator\" content=\"Studio.Design.HRC\">\n\n\n\n<!-- BASE_CSS_REMOVED -->\n<style>:root { --s-color-3d94ef4a: undefined; }</style>\n\n<style>.sd-1 { align-content:center; align-items:center; background:var(--s-color-3d94ef4a); height:100%; padding:0px; width:100%; max-width:100%; }</style>\n\n\n<script>\n(()=>{var Z=[[\"windows nt\",\"windows\"],[\"android\",\"android\"],[\"iphone\",\"iphone\"],[\"ipad\",\"iphone\"],[\"mac os x\",\"mac\"]],$=[[(q)=>q.includes(\"msie\")||q.includes(\"trident\"),\"IE\"],[(q)=>q.includes(\"edge\")||q.includes(\"edg\"),\"Edge\"],[(q)=>q.includes(\"opr\")||q.includes(\"opera\"),\"opera\"],[(q)=>q.includes(\"firefox\"),\"firefox\"],[(q)=>q.includes(\"chrome\")&&!q.includes(\"edg\"),\"chrome\"],[(q)=>q.includes(\"safari\")&&!q.includes(\"chrome\"),\"safari\"]];function Q(q=8){let G=new Uint8Array(q);crypto.getRandomValues(G);let J=\"\";for(let K=0;K<q;K++)J+=\"abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ_0123456789\"[G[K]%63];return J}function v(){let q=sessionStorage.getItem(\"studio_analytics_session_id\");if(q)return q;let G=Q();return sessionStorage.setItem(\"studio_analytics_session_id\",G),G}function z(q){return!q||q===\"\"?\"none\":q}function C(q){let G=new URL(q);return{url:q,domain:G.hostname,path:G.pathname}}function D(q){let G=q.toLowerCase(),J=Z.find(([K])=>G.includes(K));if(J)return J[1];return\"etc\"}function F(q){let G=q.toLowerCase(),J=$.find(([K])=>K(G));if(J)return J[1];return\"other\"}function P(q,G,J,K,M=v){let{url:N,domain:X,path:Y}=C(q);return{url:N,domain:X,path:Y,session_id:M(),user_agent:J,referrer:z(G),os:D(J),browser:F(J),project_id:K}}function W(){try{return sessionStorage.setItem(\"__sas_test__\",\"1\"),sessionStorage.removeItem(\"__sas_test__\"),!0}catch{return!1}}function T(q){if(!q)return null;try{return new URL(q).hostname}catch{return null}}function B(q,G){let J=T(q),K=T(G);if(!K)return!0;if(!J)return!0;return J!==K}function L(q,G){if(!W())return Q();let J=B(q,G),K=sessionStorage.getItem(\"studio_analytics_session_id\");if(J){let N=Q();return sessionStorage.setItem(\"studio_analytics_session_id\",N),N}if(K)return K;let M=Q();return sessionStorage.setItem(\"studio_analytics_session_id\",M),M}function _(q){try{let G=window.location.href,J=document.referrer||void 0,K=navigator.userAgent,M=L(G,J),N=P(G,J,K,q,()=>M);setTimeout(()=>{fetch(\"https://analytics.studiodesignapp.com/event\",{method:\"POST\",headers:{\"Content-Type\":\"application/json\"},body:JSON.stringify(N),keepalive:!0}).catch(()=>{})},0)}catch{}}Object.assign(window,{sendAnalytics:_});})();\n\n</script>\n\n</head>\n<body>\n<div class=\"box sd-1\"></div>\n\n\n\n<script>\nfunction initModules() {\n    sendAnalytics(\"8XKOkrRW4v\");\n}\nwindow.addEventListener('load', initModules, { once: true });\n</script>\n\n\n</body>\n</html>\n```\n\n### Output\n```json\n{\n  \"breakPoints\": [\n    {\n      \"maxWidth\": 540,\n      \"name\": \"mobile\"\n    },\n    {\n      \"maxWidth\": 840,\n      \"name\": \"tablet\"\n    },\n    {\n      \"maxWidth\": 1140,\n      \"name\": \"small\"\n    }\n  ],\n  \"classes\": {\n    \"typography\": [\n      {\n        \"key\": \"63bf421e\",\n        \"name\": \"本文\",\n        \"style\": {\n          \"@mini\": {\n            \"fontSize\": \"0.7rem\"\n          },\n          \"@mobile\": {\n            \"fontSize\": \"0.8rem\"\n          },\n          \"fontFamily\": \"var(--s-font-f98ee9ba)\",\n          \"fontSize\": \"0.9rem\",\n          \"fontWeight\": \"500\",\n          \"in:hover\": {\n            \"fontWeight\": \"700\"\n          },\n          \"letterSpacing\": \"0.05em\",\n          \"lineHeight\": \"2\",\n          \"writingMode\": \"horizontal-tb\"\n        }\n      },\n      {\n        \"key\": \"4caeee0d\",\n        \"name\": \"小さい文字\",\n        \"style\": {\n          \"@mobile\": {\n            \"fontSize\": \"0.75rem\",\n            \"letterSpacing\": \"0.04em\"\n          },\n          \"@small\": {\n            \"fontSize\": \"0.8rem\"\n          },\n          \"fontFamily\": \"var(--s-font-f98ee9ba)\",\n          \"fontSize\": \"0.85rem\",\n          \"fontWeight\": \"500\",\n          \"letterSpacing\": \"0.05em\",\n          \"lineHeight\": \"2\",\n          \"writingMode\": \"horizontal-tb\"\n        }\n      },\n      {\n        \"key\": \"df801922\",\n        \"name\": \"大きい文字\",\n        \"style\": {\n          \"@mini\": {\n            \"fontSize\": \"1rem\"\n          },\n          \"@mobile\": {\n            \"letterSpacing\": \"0.1em\"\n          },\n          \"@tablet\": {\n            \"fontSize\": \"0.9rem\"\n          },\n          \"fontFamily\": \"var(--s-font-f98ee9ba)\",\n          \"fontSize\": \"1.2rem\",\n          \"fontStyle\": \"normal\",\n          \"fontWeight\": \"700\",\n          \"letterSpacing\": \"0.04em\",\n          \"lineHeight\": \"1.6\",\n          \"writingMode\": \"horizontal-tb\"\n        }\n      },\n      {\n        \"key\": \"3fa01083\",\n        \"name\": \"カテゴリバッジ\",\n        \"style\": {\n          \"@mobile\": {\n            \"fontSize\": \"0.7rem\",\n            \"letterSpacing\": \"0.02em\"\n          },\n          \"fontFamily\": \"var(--s-font-f98ee9ba)\",\n          \"fontSize\": \"0.8rem\",\n          \"fontWeight\": \"600\",\n          \"letterSpacing\": \"0.05em\",\n          \"lineHeight\": \"1.8\",\n          \"writingMode\": \"horizontal-tb\"\n        }\n      },\n      {\n        \"key\": \"b6a880dd\",\n        \"name\": \"ボタン\",\n        \"style\": {\n          \"@mini\": {\n            \"fontSize\": \"11px\"\n          },\n          \"@small\": {\n            \"fontSize\": \"0.8rem\"\n          },\n          \"@tablet\": {\n            \"fontSize\": \"0.85rem\"\n          },\n          \"fontFamily\": \"var(--s-font-f98ee9ba)\",\n          \"fontSize\": \"0.9rem\",\n          \"fontWeight\": \"500\",\n          \"in:hover\": {\n            \"fontWeight\": \"700\"\n          },\n          \"lineHeight\": \"1.4\"\n        }\n      },\n      {\n        \"key\": \"ee91d7a0\",\n        \"name\": \"下層英字タイトル\",\n        \"style\": {\n          \"@mobile\": {\n            \"fontSize\": \"1.8rem\"\n          },\n          \"fontFamily\": \"var(--s-font-5ebf6bcc)\",\n          \"fontSize\": \"2.2rem\",\n          \"fontWeight\": \"400\",\n          \"lineHeight\": \"1.6\"\n        }\n      },\n      {\n        \"key\": \"1c827502\",\n        \"name\": \"英字小見出し\",\n        \"style\": {\n          \"@mini\": {\n            \"fontSize\": \"1rem\"\n          },\n          \"fontFamily\": \"var(--s-font-2ca5ec02)\",\n          \"fontSize\": \"1.2rem\",\n          \"fontStyle\": \"normal\",\n          \"fontWeight\": \"600\",\n          \"lineHeight\": \"1.8\",\n          \"writingMode\": \"horizontal-tb\"\n        }\n      },\n      {\n        \"key\": \"c289a958\",\n        \"name\": \"パンクズリスト\",\n        \"style\": {\n          \":hover\": {\n            \"fontWeight\": \"700\"\n          },\n          \"@mobile\": {\n            \"fontSize\": \"10px\",\n            \"lineHeight\": \"2\"\n          },\n          \"@tablet\": {\n            \"fontSize\": \"12px\"\n          },\n          \"fontFamily\": \"var(--s-font-f98ee9ba)\",\n          \"fontSize\": \"0.7rem\",\n          \"fontWeight\": \"600\",\n          \"lineHeight\": \"1.4\"\n        }\n      }\n    ]\n  },\n  \"colors\": [\n    {\n      \"color\": \"rgba(0,0,0,0.0)\",\n      \"name\": \"transparent\"\n    },\n    {\n      \"color\": \"#FFFFFF\",\n      \"name\": \"white\"\n    },\n    {\n      \"color\": \"#1e1e1e\",\n      \"name\": \"color\"\n    },\n    {\n      \"color\": \"#8a785a\",\n      \"name\": \"color\"\n    },\n    {\n      \"color\": \"#eae8e0ff\",\n      \"name\": \"color\"\n    },\n    {\n      \"color\": \"rgba(0, 0, 0, 0.05)\",\n      \"name\": \"color\"\n    }\n  ],\n  \"fonts\": [],\n  \"info\": {\n    \"baseWidth\": 1280,\n    \"created_at\": 1518591100346,\n    \"screen\": {\n      \"baseWidth\": 1280,\n      \"height\": 600,\n      \"isAutoHeight\": false,\n      \"width\": 1280,\n      \"workingState\": false\n    },\n    \"type\": \"web\",\n    \"updated_at\": 1518792996878,\n    \"version\": \"4.1.9\"\n  },\n  \"pages\": [\n    {\n      \"cmsRequest\": {\n        \"contentSlug\": \"{{$route.params.slug}}\",\n        \"schemaKey\": \"Z926GhRm\"\n      },\n      \"heightExtension\": 300,\n      \"id\": \"category/:slug\",\n      \"name\": \"カテゴリーの記事\",\n      \"statusBar\": \"\",\n      \"type\": \"page\",\n      \"view\": {\n        \"children\": [\n          {\n            \"name\": \"\",\n            \"refId\": \"b0eff1e9-d3f7-4572-a38b-30887d611063\",\n            \"tagName\": \"\",\n            \"type\": \"ref\"\n          }\n        ],\n        \"content\": {\n          \"type\": \"\"\n        },\n        \"name\": \"Base\",\n        \"style\": {\n          \"alignContent\": \"center\",\n          \"alignItems\": \"center\",\n          \"background\": \"var(--s-color-3d94ef4a)\",\n          \"height\": \"100%\",\n          \"padding\": \"0px 0px 0px 0px\",\n          \"width\": \"100%\"\n        }\n      }\n    }\n  ],\n  \"resources\": {\n    \"cmsProjectId\": \"88062beec5d441069502\"\n  },\n  \"styleVars\": {\n    \"color\": [\n      {\n        \"key\": \"3d94ef4a\",\n        \"name\": \"白\",\n        \"value\": \"#ffffffff\"\n      }\n    ],\n    \"fontFamily\": []\n  },\n  \"symbols\": [\n    {\n      \"defaultSize\": {\n        \"height\": 233.78125,\n        \"width\": 1280\n      },\n      \"name\": \"フッター\",\n      \"view\": {\n        \"children\": [\n          {\n            \"children\": [\n              {\n                \"name\": \"\",\n                \"refId\": \"ab196fa9-0972-4673-a9c0-b7d258ce4727\",\n                \"tagName\": \"\",\n                \"type\": \"ref\"\n              },\n              {\n                \"children\": [\n                  {\n                    \"classes\": [\n                      \"4caeee0d\"\n                    ],\n                    \"content\": {\n                      \"data\": \"採用情報\",\n                      \"type\": \"text\"\n                    },\n                    \"link\": {\n                      \"newTab\": false,\n                      \"path\": \"/recruit\"\n                    },\n                    \"name\": \"採用情報\",\n                    \"style\": {\n                      \":hover\": {\n                        \"transform\": \"translate(3px, 3px)\"\n                      },\n                      \"@tablet\": {\n                        \"textAlign\": \"right\"\n                      },\n                      \"color\": \"var(--s-color-25a50242)\",\n                      \"flex\": \"none\",\n                      \"height\": \"auto\",\n                      \"textAlign\": \"left\",\n                      \"width\": \"auto\"\n                    },\n                    \"tagName\": \"\"\n                  },\n                  {\n                    \"classes\": [\n                      \"4caeee0d\"\n                    ],\n                    \"content\": {\n                      \"data\": \"会社概要\",\n                      \"type\": \"text\"\n                    },\n                    \"link\": {\n                      \"newTab\": false,\n                      \"path\": \"/company\"\n                    },\n                    \"name\": \"会社概要\",\n                    \"style\": {\n                      \":hover\": {\n                        \"transform\": \"translate(3px, 3px)\"\n                      },\n                      \"@tablet\": {\n                        \"textAlign\": \"right\"\n                      },\n                      \"color\": \"var(--s-color-25a50242)\",\n                      \"flex\": \"none\",\n                      \"height\": \"auto\",\n                      \"textAlign\": \"left\",\n                      \"width\": \"auto\"\n                    },\n                    \"tagName\": \"\"\n                  },\n                  {\n                    \"classes\": [\n                      \"4caeee0d\"\n                    ],\n                    \"content\": {\n                      \"data\": \"プライバシーポリシー\",\n                      \"type\": \"text\"\n                    },\n                    \"link\": {\n                      \"newTab\": false,\n                      \"path\": \"/privacy\"\n                    },\n                    \"name\": \"プライバシーポリシー\",\n                    \"style\": {\n                      \":hover\": {\n                        \"transform\": \"translate(3px, 3px)\"\n                      },\n                      \"@tablet\": {\n                        \"textAlign\": \"right\"\n                      },\n                      \"color\": \"var(--s-color-25a50242)\",\n                      \"flex\": \"none\",\n                      \"height\": \"auto\",\n                      \"textAlign\": \"left\",\n                      \"width\": \"auto\"\n                    },\n                    \"tagName\": \"\"\n                  }\n                ],\n                \"name\": \"メニュー\",\n                \"style\": {\n                  \"@mobile\": {\n                    \"flexDirection\": \"column\",\n                    \"margin\": \"40px 0px 0px 0px\"\n                  },\n                  \"@tablet\": {\n                    \"margin\": \"50px 0px 0px 0px\"\n                  },\n                  \"alignContent\": \"flex-start\",\n                  \"alignItems\": \"flex-start\",\n                  \"flexDirection\": \"row\",\n                  \"flexWrap\": \"nowrap\",\n                  \"gap\": \"25px\",\n                  \"justifyContent\": \"flex-start\",\n                  \"margin\": \"0px 0px 0px 50px\",\n                  \"padding\": \"0px\"\n                },\n                \"tagName\": \"div\"\n              }\n            ],\n            \"name\": \"ロゴ+メニュー\",\n            \"style\": {\n              \"@mobile\": {\n                \"flexDirection\": \"column\"\n              },\n              \"@tablet\": {\n                \"alignContent\": \"flex-start\",\n                \"alignItems\": \"flex-start\",\n                \"flex\": \"none\",\n                \"flexDirection\": \"column\",\n                \"flexWrap\": \"nowrap\",\n                \"justifyContent\": \"space-between\",\n                \"width\": \"100%\"\n              },\n              \"alignContent\": \"flex-start\",\n              \"alignItems\": \"flex-start\",\n              \"flex\": \"none\",\n              \"flexDirection\": \"row\",\n              \"flexWrap\": \"nowrap\",\n              \"justifyContent\": \"space-between\",\n              \"margin\": \"0px 0px 50px 0px\",\n              \"padding\": \"0px\",\n              \"width\": \"100%\"\n            },\n            \"tagName\": \"div\"\n          },\n          {\n            \"content\": {\n              \"data\": \"©2024 Book Essence\",\n              \"type\": \"text\"\n            },\n            \"name\": \"コピーライト\",\n            \"refId\": \"8a78fe0e-8333-4f02-8fc7-f797d8b95fe0\",\n            \"style\": {\n              \"@mobile\": {\n                \"fontSize\": \"13px\"\n              },\n              \"@tablet\": {\n                \"fontSize\": \"14px\"\n              },\n              \"bottom\": \"0px\",\n              \"color\": \"#000000\",\n              \"fontFamily\": \"var(--s-font-2ca5ec02)\",\n              \"fontSize\": \"10px\",\n              \"fontWeight\": \"500\",\n              \"height\": \"auto\",\n              \"left\": \"25px\",\n              \"lineHeight\": \"1.7\",\n              \"margin\": \"0 0 0 0\",\n              \"position\": \"absolute\",\n              \"right\": \"NaNpx\",\n              \"textAlign\": \"center\",\n              \"top\": \"NaNpx\",\n              \"width\": \"auto\",\n              \"writingMode\": \"vertical-rl\"\n            },\n            \"tagName\": \"\",\n            \"type\": \"ref\"\n          }\n        ],\n        \"name\": \"フッター\",\n        \"style\": {\n          \"@mobile\": {\n            \"alignContent\": \"flex-end\",\n            \"alignItems\": \"flex-end\",\n            \"flexDirection\": \"column\",\n            \"flexWrap\": \"nowrap\",\n            \"justifyContent\": \"flex-start\",\n            \"padding\": \"70px 40px 100px 40px\"\n          },\n          \"alignContent\": \"flex-start\",\n          \"alignItems\": \"flex-start\",\n          \"background\": \"var(--s-color-b8b1cba5)\",\n          \"flex\": \"none\",\n          \"flexDirection\": \"column\",\n          \"flexWrap\": \"nowrap\",\n          \"height\": \"auto\",\n          \"justifyContent\": \"space-between\",\n          \"margin\": \"0px 0px 0px 0px\",\n          \"padding\": \"100px 40px 100px 40px\",\n          \"width\": \"100%\",\n          \"zIndex\": \"0\"\n        },\n        \"tagName\": \"footer\",\n        \"type\": \"component\"\n      }\n    }\n  ]\n}\n```\n\n## Example 2\n\n### Input\n```html\n<!DOCTYPE html>\n<html lang=\"\">\n<head>\n\n<meta charset=\"UTF-8\">\n<meta name=\"viewport\" content=\"width=device-width, initial-scale=1.0\">\n<title></title>\n<meta name=\"description\" content=\"\">\n<link rel=\"icon\" type=\"image/png\" href=\"https://storage.googleapis.com/studio-preview/favicon.svg\">\n<link rel=\"canonical\" href=\"https://template-preview.studio.design/ZmoWvRAW6y/latest/\">\n<link rel=\"apple-touch-icon\" type=\"image/png\" href=\"https://storage.googleapis.com/studio-preview/favicon.svg\">\n<meta name=\"robots\" content=\"noindex\">\n<meta property=\"og:site_name\" content=\"\">\n<meta property=\"og:title\" content=\"\">\n<meta property=\"og:image\" content=\"\">\n<meta property=\"og:description\" content=\"\">\n<meta property=\"og:type\" content=\"website\">\n<meta property=\"twitter:card\" content=\"summary_large_image\">\n<meta property=\"twitter:image\" content=\"\">\n<meta name=\"apple-mobile-web-app-title\" content=\"\">\n<meta name=\"format-detection\" content=\"telephone=no,email=no,address=no\">\n<meta name=\"chrome\" content=\"nointentdetection\">\n<meta property=\"og:url\" content=\"https://template-preview.studio.design/ZmoWvRAW6y/latest/\">\n\n\n<meta name=\"date\" content=\"2026-02-18T16:22:07+09:00\">\n<meta name=\"generator\" content=\"Studio.Design.HRC\">\n\n\n\n<!-- BASE_CSS_REMOVED -->\n\n\n<style>.sd-1 { background:var(--s-color-1bbe02c8); border-radius:0; height:100%; margin:0; opacity:1; padding:0; width:100%; max-width:100%; }</style>\n<style media=\"(max-width: 690px)\">.sd-1 { padding:56px 0px 0px; }</style>\n\n\n<script>\n(()=>{var Z=[[\"windows nt\",\"windows\"],[\"android\",\"android\"],[\"iphone\",\"iphone\"],[\"ipad\",\"iphone\"],[\"mac os x\",\"mac\"]],$=[[(q)=>q.includes(\"msie\")||q.includes(\"trident\"),\"IE\"],[(q)=>q.includes(\"edge\")||q.includes(\"edg\"),\"Edge\"],[(q)=>q.includes(\"opr\")||q.includes(\"opera\"),\"opera\"],[(q)=>q.includes(\"firefox\"),\"firefox\"],[(q)=>q.includes(\"chrome\")&&!q.includes(\"edg\"),\"chrome\"],[(q)=>q.includes(\"safari\")&&!q.includes(\"chrome\"),\"safari\"]];function Q(q=8){let G=new Uint8Array(q);crypto.getRandomValues(G);let J=\"\";for(let K=0;K<q;K++)J+=\"abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ_0123456789\"[G[K]%63];return J}function v(){let q=sessionStorage.getItem(\"studio_analytics_session_id\");if(q)return q;let G=Q();return sessionStorage.setItem(\"studio_analytics_session_id\",G),G}function z(q){return!q||q===\"\"?\"none\":q}function C(q){let G=new URL(q);return{url:q,domain:G.hostname,path:G.pathname}}function D(q){let G=q.toLowerCase(),J=Z.find(([K])=>G.includes(K));if(J)return J[1];return\"etc\"}function F(q){let G=q.toLowerCase(),J=$.find(([K])=>K(G));if(J)return J[1];return\"other\"}function P(q,G,J,K,M=v){let{url:N,domain:X,path:Y}=C(q);return{url:N,domain:X,path:Y,session_id:M(),user_agent:J,referrer:z(G),os:D(J),browser:F(J),project_id:K}}function W(){try{return sessionStorage.setItem(\"__sas_test__\",\"1\"),sessionStorage.removeItem(\"__sas_test__\"),!0}catch{return!1}}function T(q){if(!q)return null;try{return new URL(q).hostname}catch{return null}}function B(q,G){let J=T(q),K=T(G);if(!K)return!0;if(!J)return!0;return J!==K}function L(q,G){if(!W())return Q();let J=B(q,G),K=sessionStorage.getItem(\"studio_analytics_session_id\");if(J){let N=Q();return sessionStorage.setItem(\"studio_analytics_session_id\",N),N}if(K)return K;let M=Q();return sessionStorage.setItem(\"studio_analytics_session_id\",M),M}function _(q){try{let G=window.location.href,J=document.referrer||void 0,K=navigator.userAgent,M=L(G,J),N=P(G,J,K,q,()=>M);setTimeout(()=>{fetch(\"https://analytics.studiodesignapp.com/event\",{method:\"POST\",headers:{\"Content-Type\":\"application/json\"},body:JSON.stringify(N),keepalive:!0}).catch(()=>{})},0)}catch{}}Object.assign(window,{sendAnalytics:_});})();\n\n</script>\n\n</head>\n<body>\n<div class=\"box sd-1\"></div>\n\n\n\n<script>\nfunction initModules() {\n    sendAnalytics(\"ZmoWvRAW6y\");\n}\nwindow.addEventListener('load', initModules, { once: true });\n</script>\n\n\n</body>\n</html>\n```\n\n### Output\n```json\n{\n  \"breakPoints\": [\n    {\n      \"maxWidth\": 690,\n      \"name\": \"mobile\"\n    },\n    {\n      \"maxWidth\": 840,\n      \"name\": \"tablet\"\n    },\n    {\n      \"maxWidth\": 1140,\n      \"name\": \"small\"\n    },\n    {\n      \"maxWidth\": 360,\n      \"name\": \"mini\"\n    }\n  ],\n  \"colors\": [\n    {\n      \"color\": \"rgba(0,0,0,0.0)\",\n      \"name\": \"transparent\"\n    },\n    {\n      \"color\": \"#FFFFFF\",\n      \"name\": \"white\"\n    },\n    {\n      \"color\": \"#483628\",\n      \"name\": \"color\"\n    },\n    {\n      \"color\": \"#ee6801\",\n      \"name\": \"color\"\n    }\n  ],\n  \"fonts\": [],\n  \"info\": {\n    \"baseWidth\": 1920,\n    \"created_at\": 1518591100346,\n    \"screen\": {\n      \"baseWidth\": 1280,\n      \"height\": 600,\n      \"isAutoHeight\": false,\n      \"width\": 1280,\n      \"workingState\": false\n    },\n    \"type\": \"web\",\n    \"updated_at\": 1518792996878,\n    \"version\": \"4.1.3\"\n  },\n  \"pages\": [\n    {\n      \"head\": {\n        \"meta\": {\n          \"robots\": \"noindex\"\n        },\n        \"title\": \"\"\n      },\n      \"heightExtension\": 0,\n      \"id\": \"404\",\n      \"name\": \"404 Not Found\",\n      \"statusBar\": \"\",\n      \"type\": \"page\",\n      \"view\": {\n        \"children\": [\n          {\n            \"name\": \"Menu\",\n            \"refId\": \"d1f7770a-071c-442c-a07d-cdd9f49bd76b\",\n            \"style\": {\n              \"@mobile\": {\n                \"flex\": \"none\"\n              },\n              \"@tablet\": {\n                \"height\": \"auto\",\n                \"padding\": \"0px 0px\"\n              },\n              \"alignContent\": \"center\",\n              \"alignItems\": \"center\",\n              \"background\": \"rgba(0,0,0,0.0)\",\n              \"borderBottom\": \"0px solid rgba(255, 255, 255, 0.3)\",\n              \"borderLeft\": \"0px solid rgba(255, 255, 255, 0.3)\",\n              \"borderRight\": \"0px solid rgba(255, 255, 255, 0.3)\",\n              \"borderTop\": \"0px solid rgba(255, 255, 255, 0.3)\",\n              \"flex\": \"none\",\n              \"flexDirection\": \"column\",\n              \"flexWrap\": \"nowrap\",\n              \"height\": \"auto\",\n              \"justifyContent\": \"space-between\",\n              \"margin\": \"0px 0px 0px 0px\",\n              \"padding\": \"0px 48px\",\n              \"width\": \"auto\"\n            },\n            \"tagName\": \"\",\n            \"type\": \"ref\"\n          }\n        ],\n        \"content\": {\n          \"name\": \"\",\n          \"type\": \"\"\n        },\n        \"name\": \"Base\",\n        \"style\": {\n          \"@mobile\": {\n            \"padding\": \"56px 0px 0px 0px\"\n          },\n          \"background\": \"var(--s-color-1bbe02c8)\",\n          \"borderRadius\": \"0\",\n          \"boxShadow\": \"\",\n          \"height\": \"100%\",\n          \"margin\": \"0 0 0 0\",\n          \"opacity\": \"1\",\n          \"padding\": \"0 0 0 0\",\n          \"width\": \"100%\"\n        }\n      }\n    }\n  ],\n  \"resources\": {\n    \"cmsProjectId\": \"3mPxrUtdtLXTjo0KwrWX\"\n  },\n  \"styleVars\": {\n    \"color\": [],\n    \"fontFamily\": []\n  },\n  \"symbols\": []\n}\n```\n",
+  "max_length": 32768,
+  "truncation_strategy": "delete",
+  "max_pixels": null,
+  "agent_template": null,
+  "norm_bbox": null,
+  "use_chat_template": true,
+  "padding_side": "right",
+  "padding_free": false,
+  "loss_scale": "default",
+  "sequence_parallel_size": 1,
+  "template_backend": "swift",
+  "response_prefix": null,
+  "enable_thinking": null,
+  "add_non_thinking_prefix": true,
+  "dataset": [
+    "/app/datasets/train.jsonl"
+  ],
+  "val_dataset": [
+    "/app/datasets/val.jsonl"
+  ],
+  "cached_dataset": [],
+  "cached_val_dataset": [],
+  "split_dataset_ratio": 0.0,
+  "dataset_num_proc": 1,
+  "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,
+  "structured_outputs_regex": null,
+  "ckpt_dir": null,
+  "lora_modules": [],
+  "train_type": "lora",
+  "adapters": [],
+  "external_plugins": [],
+  "model_kwargs": {},
+  "load_args": false,
+  "load_data_args": false,
+  "packing": false,
+  "packing_length": null,
+  "packing_num_proc": 1,
+  "lazy_tokenize": false,
+  "custom_register_path": [],
+  "use_hf": true,
+  "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": true,
+  "target_modules": [
+    "all-linear"
+  ],
+  "target_regex": null,
+  "target_parameters": 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": "ms-swift",
+  "swanlab_workspace": null,
+  "swanlab_exp_name": null,
+  "swanlab_notification_method": null,
+  "swanlab_webhook_url": null,
+  "swanlab_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": "Qwen3-8B",
+  "model_info": "ModelInfo(model_type='qwen3', model_dir='/root/.cache/huggingface/hub/models--Qwen--Qwen3-8B/snapshots/b968826d9c46dd6066d109eabc6255188de91218', torch_dtype=torch.bfloat16, max_model_len=40960, quant_method=None, quant_bits=None, rope_scaling=None, is_moe_model=False, is_multimodal=False, config=None, task_type='causal_lm', num_labels=None)",
+  "model_meta": "ModelMeta(model_type='qwen3', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen3-0.6B-Base', hf_model_id='Qwen/Qwen3-0.6B-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-1.7B-Base', hf_model_id='Qwen/Qwen3-1.7B-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-4B-Base', hf_model_id='Qwen/Qwen3-4B-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-8B-Base', hf_model_id='Qwen/Qwen3-8B-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-14B-Base', hf_model_id='Qwen/Qwen3-14B-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-0.6B', hf_model_id='Qwen/Qwen3-0.6B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-1.7B', hf_model_id='Qwen/Qwen3-1.7B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-4B', hf_model_id='Qwen/Qwen3-4B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-8B', hf_model_id='Qwen/Qwen3-8B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-14B', hf_model_id='Qwen/Qwen3-14B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-32B', hf_model_id='Qwen/Qwen3-32B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-0.6B-FP8', hf_model_id='Qwen/Qwen3-0.6B-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-1.7B-FP8', hf_model_id='Qwen/Qwen3-1.7B-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-4B-FP8', hf_model_id='Qwen/Qwen3-4B-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-8B-FP8', hf_model_id='Qwen/Qwen3-8B-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-14B-FP8', hf_model_id='Qwen/Qwen3-14B-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-32B-FP8', hf_model_id='Qwen/Qwen3-32B-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-4B-AWQ', hf_model_id='Qwen/Qwen3-4B-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-8B-AWQ', hf_model_id='Qwen/Qwen3-8B-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-14B-AWQ', hf_model_id='Qwen/Qwen3-14B-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-32B-AWQ', hf_model_id='Qwen/Qwen3-32B-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='swift/Qwen3-32B-AWQ', hf_model_id=None, model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='qwen3', get_function=<function get_model_tokenizer_with_flash_attn at 0x7f60a70eac00>, 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=['Qwen3ForCausalLM'], additional_saved_files=[], torch_dtype=None, is_multimodal=False, is_reward=False, is_reranker=False, task_type=None, ignore_patterns=None, requires=['transformers>=4.51'], tags=[])",
+  "model_dir": "/root/.cache/huggingface/hub/models--Qwen--Qwen3-8B/snapshots/b968826d9c46dd6066d109eabc6255188de91218",
+  "_val_dataset_exists": [
+    "/app/datasets/val.jsonl"
+  ],
+  "hub": "<class 'swift.hub.hub.HFHub'>",
+  "evaluation_strategy": "epoch",
+  "training_args": "Seq2SeqTrainingArguments(output_dir='/app/outputs/sft-qwen3/v4-20260317-135206', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, eval_strategy=<IntervalStrategy.EPOCH: 'epoch'>, prediction_loss_only=False, per_device_train_batch_size=1, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=8, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=1e-05, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1.0, num_train_epochs=1.0, max_steps=-1, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs=None, warmup_ratio=0.05, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/app/outputs/sft-qwen3/v4-20260317-135206/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=10, 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=True, 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, 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=None, dataloader_num_workers=4, dataloader_prefetch_factor=2, past_index=-1, run_name='/app/outputs/sft-qwen3/v4-20260317-135206', 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), parallelism_config=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}, 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=['wandb'], project='huggingface', trackio_space_id='trackio', 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=True, resume_from_checkpoint=None, hub_model_id='StudioDesign/sft-qwen3', 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, enable_channel_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, 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, chord_sft_dataset=[], chord_sft_per_device_train_batch_size=None, chord_enable_phi_function=False, chord_mu_warmup_steps=None, chord_mu_decay_steps=None, chord_mu_peak=None, chord_mu_valley=None, train_type='lora', local_repo_path=None, galore_config=None, task_type='causal_lm', problem_type=None)"
+}

chat_template.jinja

@@ -0,0 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# 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' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- 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' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

logging.jsonl

@@ -0,0 +1,2 @@
+{"loss": 0.32817921, "grad_norm": 0.15581589, "learning_rate": 1e-05, "token_acc": 0.92229585, "epoch": 1.0, "global_step/max_steps": "1/1", "percentage": "100.00%", "elapsed_time": "11s", "remaining_time": "0s", "memory(GiB)": 22.22, "train_speed(iter/s)": 0.086502}
+{"eval_loss": 0.22503923, "eval_runtime": 3.86, "eval_samples_per_second": 0.518, "eval_steps_per_second": 0.259, "eval_token_acc": 0.94509159, "epoch": 1.0, "global_step/max_steps": "1/1", "percentage": "100.00%", "elapsed_time": "15s", "remaining_time": "0s", "memory(GiB)": 39.15, "train_speed(iter/s)": 0.064698}

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
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

tokenizer_config.json

@@ -0,0 +1,239 @@
+{
+  "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
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "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
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32892598f245496e9024725c8ebabfbfd24e3b419bddcff9b8b89a2070b59b59
+size 9425