Upload LoRA adapter (README written by author)

.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

README.md

@@ -0,0 +1,69 @@
+---
+base_model: Qwen/Qwen3-4B-Instruct-2507
+datasets:
+- u-10bei/structured_data_with_cot_dataset_512_v2
+- u-10bei/structured_data_with_cot_dataset_512_v4
+- u-10bei/structured_data_with_cot_dataset_512_v5
+
+
+language:
+- en
+license: apache-2.0
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- qlora
+- lora
+- structured-output
+---
+
+qwer3-4b-instruct-output-ver_7
+
+This repository provides a **LoRA adapter** fine-tuned from
+**Qwen/Qwen3-4B-Instruct-2507** using **QLoRA (4-bit, Unsloth)**.
+
+This repository contains **LoRA adapter weights only**.
+The base model must be loaded separately.
+
+## Training Objective
+
+This adapter is trained to improve **structured output accuracy**
+(JSON / YAML / XML / TOML / CSV).
+
+Loss is applied only to the final assistant output,
+while intermediate reasoning (Chain-of-Thought) is masked.
+
+## Training Configuration
+
+- Base model: Qwen/Qwen3-4B-Instruct-2507
+- Method: QLoRA (4-bit)
+- Max sequence length: 1024
+- Epochs: 3
+- Learning rate: 1e-04
+- LoRA: r=8, alpha=16
+
+## Usage
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from peft import PeftModel
+import torch
+
+base = "Qwen/Qwen3-4B-Instruct-2507"
+adapter = "your_id/your-repo"
+
+tokenizer = AutoTokenizer.from_pretrained(base)
+model = AutoModelForCausalLM.from_pretrained(
+    base,
+    torch_dtype=torch.float16,
+    device_map="auto",
+)
+model = PeftModel.from_pretrained(model, adapter)
+```
+
+## Sources & Terms (IMPORTANT)
+
+Training data: u-10bei/structured_data_with_cot_dataset_512_v2
+
+Dataset License: MIT License. This dataset is used and distributed under the terms of the MIT License.
+Compliance: Users must comply with the MIT license (including copyright notice) and the base model's original terms of use.

adapter_config.json

@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen3ForCausalLM",
+    "parent_library": "transformers.models.qwen3.modeling_qwen3",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/qwen3-4b-instruct-2507-unsloth-bnb-4bit",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "q_proj",
+    "k_proj",
+    "v_proj",
+    "gate_proj",
+    "up_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:e7c20f0321633a0fb5c54e738e8affbd9ea2220002469b245b507f295383de9f
+size 66126768

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
+}

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": "<|vision_pad|>",
+    "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 +1,240 @@
+{
+  "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": 262144,
+  "pad_token": "<|vision_pad|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,292 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.8941877794336811,
+  "eval_steps": 50,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.029806259314456036,
+      "grad_norm": 0.7608007788658142,
+      "learning_rate": 8.910891089108911e-06,
+      "loss": 0.9165,
+      "step": 10
+    },
+    {
+      "epoch": 0.05961251862891207,
+      "grad_norm": 0.5924040675163269,
+      "learning_rate": 1.8811881188118814e-05,
+      "loss": 0.6788,
+      "step": 20
+    },
+    {
+      "epoch": 0.08941877794336811,
+      "grad_norm": 0.6122109293937683,
+      "learning_rate": 2.871287128712871e-05,
+      "loss": 0.7894,
+      "step": 30
+    },
+    {
+      "epoch": 0.11922503725782414,
+      "grad_norm": 0.2688486874103546,
+      "learning_rate": 3.861386138613862e-05,
+      "loss": 0.6559,
+      "step": 40
+    },
+    {
+      "epoch": 0.14903129657228018,
+      "grad_norm": 0.2745978534221649,
+      "learning_rate": 4.851485148514851e-05,
+      "loss": 0.6485,
+      "step": 50
+    },
+    {
+      "epoch": 0.14903129657228018,
+      "eval_loss": 0.5835313200950623,
+      "eval_runtime": 21.704,
+      "eval_samples_per_second": 13.039,
+      "eval_steps_per_second": 6.543,
+      "step": 50
+    },
+    {
+      "epoch": 0.17883755588673622,
+      "grad_norm": 0.16949200630187988,
+      "learning_rate": 5.8415841584158416e-05,
+      "loss": 0.4923,
+      "step": 60
+    },
+    {
+      "epoch": 0.20864381520119224,
+      "grad_norm": 0.24523590505123138,
+      "learning_rate": 6.831683168316833e-05,
+      "loss": 0.4495,
+      "step": 70
+    },
+    {
+      "epoch": 0.23845007451564829,
+      "grad_norm": 0.26742103695869446,
+      "learning_rate": 7.821782178217822e-05,
+      "loss": 0.5639,
+      "step": 80
+    },
+    {
+      "epoch": 0.26825633383010433,
+      "grad_norm": 0.29816722869873047,
+      "learning_rate": 8.811881188118812e-05,
+      "loss": 0.3953,
+      "step": 90
+    },
+    {
+      "epoch": 0.29806259314456035,
+      "grad_norm": 0.19821330904960632,
+      "learning_rate": 9.801980198019803e-05,
+      "loss": 0.3853,
+      "step": 100
+    },
+    {
+      "epoch": 0.29806259314456035,
+      "eval_loss": 0.4391556978225708,
+      "eval_runtime": 21.5445,
+      "eval_samples_per_second": 13.136,
+      "eval_steps_per_second": 6.591,
+      "step": 100
+    },
+    {
+      "epoch": 0.32786885245901637,
+      "grad_norm": 0.2450932264328003,
+      "learning_rate": 9.998080547518606e-05,
+      "loss": 0.3644,
+      "step": 110
+    },
+    {
+      "epoch": 0.35767511177347244,
+      "grad_norm": 0.44731152057647705,
+      "learning_rate": 9.990285297503122e-05,
+      "loss": 0.509,
+      "step": 120
+    },
+    {
+      "epoch": 0.38748137108792846,
+      "grad_norm": 0.2764962613582611,
+      "learning_rate": 9.976503628272744e-05,
+      "loss": 0.4084,
+      "step": 130
+    },
+    {
+      "epoch": 0.4172876304023845,
+      "grad_norm": 0.37768784165382385,
+      "learning_rate": 9.95675207251941e-05,
+      "loss": 0.3479,
+      "step": 140
+    },
+    {
+      "epoch": 0.44709388971684055,
+      "grad_norm": 0.3421232998371124,
+      "learning_rate": 9.931054324498228e-05,
+      "loss": 0.3088,
+      "step": 150
+    },
+    {
+      "epoch": 0.44709388971684055,
+      "eval_loss": 0.3867914080619812,
+      "eval_runtime": 21.5663,
+      "eval_samples_per_second": 13.122,
+      "eval_steps_per_second": 6.584,
+      "step": 150
+    },
+    {
+      "epoch": 0.47690014903129657,
+      "grad_norm": 0.3965997099876404,
+      "learning_rate": 9.899441211603495e-05,
+      "loss": 0.3033,
+      "step": 160
+    },
+    {
+      "epoch": 0.5067064083457526,
+      "grad_norm": 0.40676477551460266,
+      "learning_rate": 9.861950657387711e-05,
+      "loss": 0.469,
+      "step": 170
+    },
+    {
+      "epoch": 0.5365126676602087,
+      "grad_norm": 0.2048766016960144,
+      "learning_rate": 9.818627636067932e-05,
+      "loss": 0.4264,
+      "step": 180
+    },
+    {
+      "epoch": 0.5663189269746647,
+      "grad_norm": 0.24298368394374847,
+      "learning_rate": 9.769524118574038e-05,
+      "loss": 0.3619,
+      "step": 190
+    },
+    {
+      "epoch": 0.5961251862891207,
+      "grad_norm": 0.22604210674762726,
+      "learning_rate": 9.714699010203644e-05,
+      "loss": 0.3244,
+      "step": 200
+    },
+    {
+      "epoch": 0.5961251862891207,
+      "eval_loss": 0.3654942810535431,
+      "eval_runtime": 21.4485,
+      "eval_samples_per_second": 13.194,
+      "eval_steps_per_second": 6.621,
+      "step": 200
+    },
+    {
+      "epoch": 0.6259314456035767,
+      "grad_norm": 0.28323236107826233,
+      "learning_rate": 9.654218079958453e-05,
+      "loss": 0.3522,
+      "step": 210
+    },
+    {
+      "epoch": 0.6557377049180327,
+      "grad_norm": 0.09385296702384949,
+      "learning_rate": 9.588153881646781e-05,
+      "loss": 0.3867,
+      "step": 220
+    },
+    {
+      "epoch": 0.6855439642324889,
+      "grad_norm": 0.252581387758255,
+      "learning_rate": 9.516585666846975e-05,
+      "loss": 0.3195,
+      "step": 230
+    },
+    {
+      "epoch": 0.7153502235469449,
+      "grad_norm": 0.15952186286449432,
+      "learning_rate": 9.439599289836034e-05,
+      "loss": 0.339,
+      "step": 240
+    },
+    {
+      "epoch": 0.7451564828614009,
+      "grad_norm": 0.35795724391937256,
+      "learning_rate": 9.357287104597576e-05,
+      "loss": 0.4031,
+      "step": 250
+    },
+    {
+      "epoch": 0.7451564828614009,
+      "eval_loss": 0.35539424419403076,
+      "eval_runtime": 21.4478,
+      "eval_samples_per_second": 13.195,
+      "eval_steps_per_second": 6.621,
+      "step": 250
+    },
+    {
+      "epoch": 0.7749627421758569,
+      "grad_norm": 0.2801375687122345,
+      "learning_rate": 9.269747854032652e-05,
+      "loss": 0.3129,
+      "step": 260
+    },
+    {
+      "epoch": 0.8047690014903129,
+      "grad_norm": 0.43305742740631104,
+      "learning_rate": 9.177086551506306e-05,
+      "loss": 0.2951,
+      "step": 270
+    },
+    {
+      "epoch": 0.834575260804769,
+      "grad_norm": 0.2499503493309021,
+      "learning_rate": 9.07941435487202e-05,
+      "loss": 0.4211,
+      "step": 280
+    },
+    {
+      "epoch": 0.8643815201192251,
+      "grad_norm": 0.47500255703926086,
+      "learning_rate": 8.97684843312512e-05,
+      "loss": 0.446,
+      "step": 290
+    },
+    {
+      "epoch": 0.8941877794336811,
+      "grad_norm": 0.23257675766944885,
+      "learning_rate": 8.869511825845132e-05,
+      "loss": 0.2706,
+      "step": 300
+    },
+    {
+      "epoch": 0.8941877794336811,
+      "eval_loss": 0.3487342596054077,
+      "eval_runtime": 21.4555,
+      "eval_samples_per_second": 13.19,
+      "eval_steps_per_second": 6.618,
+      "step": 300
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1008,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.537254492345958e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}