Добавлены веса модели

Загрузка через Python API

.gitattributes

@@ -46,3 +46,43 @@ lora_weights/checkpoint-700/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 lora_weights/checkpoint-800/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 lora_weights/checkpoint-900/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 lora_weights/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+just_lora_weights/checkpoint-100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+just_lora_weights/checkpoint-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+just_lora_weights/checkpoint-125/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+just_lora_weights/checkpoint-150/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+just_lora_weights/checkpoint-175/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+just_lora_weights/checkpoint-200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+just_lora_weights/checkpoint-225/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+just_lora_weights/checkpoint-25/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+just_lora_weights/checkpoint-250/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+just_lora_weights/checkpoint-275/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+just_lora_weights/checkpoint-300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+just_lora_weights/checkpoint-325/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+just_lora_weights/checkpoint-350/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+just_lora_weights/checkpoint-375/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+just_lora_weights/checkpoint-400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+just_lora_weights/checkpoint-425/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+just_lora_weights/checkpoint-450/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+just_lora_weights/checkpoint-475/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+just_lora_weights/checkpoint-50/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+just_lora_weights/checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+just_lora_weights/checkpoint-525/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+just_lora_weights/checkpoint-550/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+just_lora_weights/checkpoint-575/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+just_lora_weights/checkpoint-600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+just_lora_weights/checkpoint-625/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+just_lora_weights/checkpoint-650/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+just_lora_weights/checkpoint-675/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+just_lora_weights/checkpoint-700/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+just_lora_weights/checkpoint-725/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+just_lora_weights/checkpoint-75/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+just_lora_weights/checkpoint-750/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+just_lora_weights/checkpoint-775/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+just_lora_weights/checkpoint-800/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+just_lora_weights/checkpoint-825/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+just_lora_weights/checkpoint-850/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+just_lora_weights/checkpoint-875/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+just_lora_weights/checkpoint-900/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+just_lora_weights/checkpoint-925/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+just_lora_weights/checkpoint-950/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+just_lora_weights/checkpoint-975/tokenizer.json filter=lfs diff=lfs merge=lfs -text

just_lora_weights/checkpoint-100/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen3-0.6B
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.15.2

just_lora_weights/checkpoint-100/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-0.6B",
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

just_lora_weights/checkpoint-100/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffef6c1ab5392c2105a0f2fe6f04a5ab071ee766fea9fd61c27a3df03eecd0f3
+size 9189904

just_lora_weights/checkpoint-100/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
+}

just_lora_weights/checkpoint-100/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 %}

just_lora_weights/checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a6011cf05831da10839186bbb6ae10d769f8923315a71a356e4471214ae636b
+size 18441675

just_lora_weights/checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cddf27219365242ec1046a3532a63a24c3f350c77f100e4f973369db2cc849d
+size 14455

just_lora_weights/checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6d464ddcd54c8f7496943158fe241c4fb8e43ccfac60bcb134909899ddfd40c
+size 1465

just_lora_weights/checkpoint-100/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
+  }
+}

just_lora_weights/checkpoint-100/tokenizer.json

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

just_lora_weights/checkpoint-100/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
+}

just_lora_weights/checkpoint-100/trainer_state.json

@@ -0,0 +1,174 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.1,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.005,
+      "grad_norm": 4.4095964431762695,
+      "learning_rate": 4.9800000000000004e-05,
+      "loss": 5.4329,
+      "step": 5
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 2.658348798751831,
+      "learning_rate": 4.9550000000000005e-05,
+      "loss": 4.6734,
+      "step": 10
+    },
+    {
+      "epoch": 0.015,
+      "grad_norm": 3.4242470264434814,
+      "learning_rate": 4.93e-05,
+      "loss": 4.8327,
+      "step": 15
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 4.363213539123535,
+      "learning_rate": 4.905e-05,
+      "loss": 4.4238,
+      "step": 20
+    },
+    {
+      "epoch": 0.025,
+      "grad_norm": 2.531619071960449,
+      "learning_rate": 4.88e-05,
+      "loss": 3.9284,
+      "step": 25
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 4.686695098876953,
+      "learning_rate": 4.855e-05,
+      "loss": 4.6794,
+      "step": 30
+    },
+    {
+      "epoch": 0.035,
+      "grad_norm": 4.860099792480469,
+      "learning_rate": 4.83e-05,
+      "loss": 5.0624,
+      "step": 35
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 8.296855926513672,
+      "learning_rate": 4.805e-05,
+      "loss": 4.8011,
+      "step": 40
+    },
+    {
+      "epoch": 0.045,
+      "grad_norm": 4.80878210067749,
+      "learning_rate": 4.78e-05,
+      "loss": 5.495,
+      "step": 45
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 4.766687393188477,
+      "learning_rate": 4.755e-05,
+      "loss": 4.6778,
+      "step": 50
+    },
+    {
+      "epoch": 0.055,
+      "grad_norm": 2.7137186527252197,
+      "learning_rate": 4.73e-05,
+      "loss": 4.5044,
+      "step": 55
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 9.891243934631348,
+      "learning_rate": 4.705e-05,
+      "loss": 4.4744,
+      "step": 60
+    },
+    {
+      "epoch": 0.065,
+      "grad_norm": 3.6516237258911133,
+      "learning_rate": 4.6800000000000006e-05,
+      "loss": 4.6576,
+      "step": 65
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 5.687813758850098,
+      "learning_rate": 4.655000000000001e-05,
+      "loss": 5.1204,
+      "step": 70
+    },
+    {
+      "epoch": 0.075,
+      "grad_norm": 4.273693561553955,
+      "learning_rate": 4.630000000000001e-05,
+      "loss": 5.361,
+      "step": 75
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 6.802962779998779,
+      "learning_rate": 4.605e-05,
+      "loss": 5.5483,
+      "step": 80
+    },
+    {
+      "epoch": 0.085,
+      "grad_norm": 2.7016360759735107,
+      "learning_rate": 4.58e-05,
+      "loss": 4.5909,
+      "step": 85
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 8.201666831970215,
+      "learning_rate": 4.555e-05,
+      "loss": 4.2807,
+      "step": 90
+    },
+    {
+      "epoch": 0.095,
+      "grad_norm": 3.8271970748901367,
+      "learning_rate": 4.53e-05,
+      "loss": 5.5645,
+      "step": 95
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 3.17282772064209,
+      "learning_rate": 4.5050000000000004e-05,
+      "loss": 4.5845,
+      "step": 100
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 25,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 34004061388800.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

just_lora_weights/checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b32254dfaf0c82ecfc54cd31b94eb7c8ebb2e7d832a31fe43128bcff0fa132b3
+size 5713

just_lora_weights/checkpoint-1000/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen3-0.6B
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.15.2

just_lora_weights/checkpoint-1000/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-0.6B",
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

just_lora_weights/checkpoint-1000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46152164316484799408f9ffa7cb81d8563e68b7cfac4cb104568a12732313b8
+size 9189904

just_lora_weights/checkpoint-1000/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
+}

just_lora_weights/checkpoint-1000/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 %}

just_lora_weights/checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cbdcdb1ca6ed7d700b4835a35f839fa6d85a737608522ce984feefd2204a950
+size 18441675

just_lora_weights/checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cddf27219365242ec1046a3532a63a24c3f350c77f100e4f973369db2cc849d
+size 14455

just_lora_weights/checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e78a303f3dc54e638a18cc4374f3e288409f35549509f776b4cdbbc1b527159
+size 1465

just_lora_weights/checkpoint-1000/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
+  }
+}

just_lora_weights/checkpoint-1000/tokenizer.json

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

just_lora_weights/checkpoint-1000/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
+}

just_lora_weights/checkpoint-1000/trainer_state.json

@@ -0,0 +1,1434 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.005,
+      "grad_norm": 4.4095964431762695,
+      "learning_rate": 4.9800000000000004e-05,
+      "loss": 5.4329,
+      "step": 5
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 2.658348798751831,
+      "learning_rate": 4.9550000000000005e-05,
+      "loss": 4.6734,
+      "step": 10
+    },
+    {
+      "epoch": 0.015,
+      "grad_norm": 3.4242470264434814,
+      "learning_rate": 4.93e-05,
+      "loss": 4.8327,
+      "step": 15
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 4.363213539123535,
+      "learning_rate": 4.905e-05,
+      "loss": 4.4238,
+      "step": 20
+    },
+    {
+      "epoch": 0.025,
+      "grad_norm": 2.531619071960449,
+      "learning_rate": 4.88e-05,
+      "loss": 3.9284,
+      "step": 25
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 4.686695098876953,
+      "learning_rate": 4.855e-05,
+      "loss": 4.6794,
+      "step": 30
+    },
+    {
+      "epoch": 0.035,
+      "grad_norm": 4.860099792480469,
+      "learning_rate": 4.83e-05,
+      "loss": 5.0624,
+      "step": 35
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 8.296855926513672,
+      "learning_rate": 4.805e-05,
+      "loss": 4.8011,
+      "step": 40
+    },
+    {
+      "epoch": 0.045,
+      "grad_norm": 4.80878210067749,
+      "learning_rate": 4.78e-05,
+      "loss": 5.495,
+      "step": 45
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 4.766687393188477,
+      "learning_rate": 4.755e-05,
+      "loss": 4.6778,
+      "step": 50
+    },
+    {
+      "epoch": 0.055,
+      "grad_norm": 2.7137186527252197,
+      "learning_rate": 4.73e-05,
+      "loss": 4.5044,
+      "step": 55
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 9.891243934631348,
+      "learning_rate": 4.705e-05,
+      "loss": 4.4744,
+      "step": 60
+    },
+    {
+      "epoch": 0.065,
+      "grad_norm": 3.6516237258911133,
+      "learning_rate": 4.6800000000000006e-05,
+      "loss": 4.6576,
+      "step": 65
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 5.687813758850098,
+      "learning_rate": 4.655000000000001e-05,
+      "loss": 5.1204,
+      "step": 70
+    },
+    {
+      "epoch": 0.075,
+      "grad_norm": 4.273693561553955,
+      "learning_rate": 4.630000000000001e-05,
+      "loss": 5.361,
+      "step": 75
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 6.802962779998779,
+      "learning_rate": 4.605e-05,
+      "loss": 5.5483,
+      "step": 80
+    },
+    {
+      "epoch": 0.085,
+      "grad_norm": 2.7016360759735107,
+      "learning_rate": 4.58e-05,
+      "loss": 4.5909,
+      "step": 85
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 8.201666831970215,
+      "learning_rate": 4.555e-05,
+      "loss": 4.2807,
+      "step": 90
+    },
+    {
+      "epoch": 0.095,
+      "grad_norm": 3.8271970748901367,
+      "learning_rate": 4.53e-05,
+      "loss": 5.5645,
+      "step": 95
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 3.17282772064209,
+      "learning_rate": 4.5050000000000004e-05,
+      "loss": 4.5845,
+      "step": 100
+    },
+    {
+      "epoch": 0.105,
+      "grad_norm": 2.9256932735443115,
+      "learning_rate": 4.4800000000000005e-05,
+      "loss": 4.6003,
+      "step": 105
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 10.4873046875,
+      "learning_rate": 4.4550000000000005e-05,
+      "loss": 4.6453,
+      "step": 110
+    },
+    {
+      "epoch": 0.115,
+      "grad_norm": 2.9158883094787598,
+      "learning_rate": 4.43e-05,
+      "loss": 4.8935,
+      "step": 115
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 3.5588793754577637,
+      "learning_rate": 4.405e-05,
+      "loss": 3.9582,
+      "step": 120
+    },
+    {
+      "epoch": 0.125,
+      "grad_norm": 2.7040491104125977,
+      "learning_rate": 4.38e-05,
+      "loss": 4.6688,
+      "step": 125
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 3.1420748233795166,
+      "learning_rate": 4.355e-05,
+      "loss": 4.5591,
+      "step": 130
+    },
+    {
+      "epoch": 0.135,
+      "grad_norm": 2.023017168045044,
+      "learning_rate": 4.33e-05,
+      "loss": 4.5944,
+      "step": 135
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 2.902434825897217,
+      "learning_rate": 4.305e-05,
+      "loss": 5.4079,
+      "step": 140
+    },
+    {
+      "epoch": 0.145,
+      "grad_norm": 2.4470090866088867,
+      "learning_rate": 4.2800000000000004e-05,
+      "loss": 4.9259,
+      "step": 145
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 4.8970046043396,
+      "learning_rate": 4.2550000000000004e-05,
+      "loss": 4.6465,
+      "step": 150
+    },
+    {
+      "epoch": 0.155,
+      "grad_norm": 2.197767734527588,
+      "learning_rate": 4.23e-05,
+      "loss": 4.6841,
+      "step": 155
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 4.577955722808838,
+      "learning_rate": 4.205e-05,
+      "loss": 4.1775,
+      "step": 160
+    },
+    {
+      "epoch": 0.165,
+      "grad_norm": 2.3383991718292236,
+      "learning_rate": 4.18e-05,
+      "loss": 4.0309,
+      "step": 165
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 3.794187307357788,
+      "learning_rate": 4.155e-05,
+      "loss": 4.5336,
+      "step": 170
+    },
+    {
+      "epoch": 0.175,
+      "grad_norm": 4.427373886108398,
+      "learning_rate": 4.13e-05,
+      "loss": 4.241,
+      "step": 175
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 2.8116564750671387,
+      "learning_rate": 4.105e-05,
+      "loss": 4.7562,
+      "step": 180
+    },
+    {
+      "epoch": 0.185,
+      "grad_norm": 5.841445446014404,
+      "learning_rate": 4.08e-05,
+      "loss": 3.7034,
+      "step": 185
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 20.96999740600586,
+      "learning_rate": 4.055e-05,
+      "loss": 5.1727,
+      "step": 190
+    },
+    {
+      "epoch": 0.195,
+      "grad_norm": 11.743700981140137,
+      "learning_rate": 4.0300000000000004e-05,
+      "loss": 5.1553,
+      "step": 195
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 10.230498313903809,
+      "learning_rate": 4.0050000000000004e-05,
+      "loss": 4.8657,
+      "step": 200
+    },
+    {
+      "epoch": 0.205,
+      "grad_norm": 5.706521987915039,
+      "learning_rate": 3.9800000000000005e-05,
+      "loss": 4.3638,
+      "step": 205
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 5.781250476837158,
+      "learning_rate": 3.9550000000000006e-05,
+      "loss": 4.3452,
+      "step": 210
+    },
+    {
+      "epoch": 0.215,
+      "grad_norm": 2.371096611022949,
+      "learning_rate": 3.9300000000000007e-05,
+      "loss": 4.6681,
+      "step": 215
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 4.352181911468506,
+      "learning_rate": 3.905e-05,
+      "loss": 4.2025,
+      "step": 220
+    },
+    {
+      "epoch": 0.225,
+      "grad_norm": 4.531359672546387,
+      "learning_rate": 3.88e-05,
+      "loss": 4.5391,
+      "step": 225
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 6.948793411254883,
+      "learning_rate": 3.855e-05,
+      "loss": 4.0233,
+      "step": 230
+    },
+    {
+      "epoch": 0.235,
+      "grad_norm": 4.765657424926758,
+      "learning_rate": 3.83e-05,
+      "loss": 4.1225,
+      "step": 235
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 3.838766574859619,
+      "learning_rate": 3.805e-05,
+      "loss": 4.9202,
+      "step": 240
+    },
+    {
+      "epoch": 0.245,
+      "grad_norm": 6.471155643463135,
+      "learning_rate": 3.7800000000000004e-05,
+      "loss": 4.7561,
+      "step": 245
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 5.748368740081787,
+      "learning_rate": 3.7550000000000005e-05,
+      "loss": 3.7783,
+      "step": 250
+    },
+    {
+      "epoch": 0.255,
+      "grad_norm": 2.663558006286621,
+      "learning_rate": 3.73e-05,
+      "loss": 4.1553,
+      "step": 255
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 3.4103472232818604,
+      "learning_rate": 3.705e-05,
+      "loss": 4.9314,
+      "step": 260
+    },
+    {
+      "epoch": 0.265,
+      "grad_norm": 6.4364824295043945,
+      "learning_rate": 3.68e-05,
+      "loss": 4.4708,
+      "step": 265
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 4.145668983459473,
+      "learning_rate": 3.655e-05,
+      "loss": 4.5879,
+      "step": 270
+    },
+    {
+      "epoch": 0.275,
+      "grad_norm": 3.4401297569274902,
+      "learning_rate": 3.63e-05,
+      "loss": 4.7668,
+      "step": 275
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 9.18470287322998,
+      "learning_rate": 3.605e-05,
+      "loss": 4.619,
+      "step": 280
+    },
+    {
+      "epoch": 0.285,
+      "grad_norm": 4.180783748626709,
+      "learning_rate": 3.58e-05,
+      "loss": 3.8878,
+      "step": 285
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 7.336719036102295,
+      "learning_rate": 3.555e-05,
+      "loss": 4.5864,
+      "step": 290
+    },
+    {
+      "epoch": 0.295,
+      "grad_norm": 4.498530864715576,
+      "learning_rate": 3.53e-05,
+      "loss": 3.8987,
+      "step": 295
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 3.3154962062835693,
+      "learning_rate": 3.505e-05,
+      "loss": 4.5049,
+      "step": 300
+    },
+    {
+      "epoch": 0.305,
+      "grad_norm": 5.832047462463379,
+      "learning_rate": 3.48e-05,
+      "loss": 5.0849,
+      "step": 305
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 17.935897827148438,
+      "learning_rate": 3.455e-05,
+      "loss": 4.8395,
+      "step": 310
+    },
+    {
+      "epoch": 0.315,
+      "grad_norm": 8.821608543395996,
+      "learning_rate": 3.430000000000001e-05,
+      "loss": 4.9111,
+      "step": 315
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 4.014020919799805,
+      "learning_rate": 3.405e-05,
+      "loss": 3.6753,
+      "step": 320
+    },
+    {
+      "epoch": 0.325,
+      "grad_norm": 7.319735050201416,
+      "learning_rate": 3.38e-05,
+      "loss": 4.6448,
+      "step": 325
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 3.252227783203125,
+      "learning_rate": 3.355e-05,
+      "loss": 4.1821,
+      "step": 330
+    },
+    {
+      "epoch": 0.335,
+      "grad_norm": 5.4611616134643555,
+      "learning_rate": 3.33e-05,
+      "loss": 4.6576,
+      "step": 335
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 5.558750152587891,
+      "learning_rate": 3.3050000000000004e-05,
+      "loss": 3.8608,
+      "step": 340
+    },
+    {
+      "epoch": 0.345,
+      "grad_norm": 7.037349700927734,
+      "learning_rate": 3.2800000000000004e-05,
+      "loss": 4.5832,
+      "step": 345
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 8.361868858337402,
+      "learning_rate": 3.2550000000000005e-05,
+      "loss": 4.7027,
+      "step": 350
+    },
+    {
+      "epoch": 0.355,
+      "grad_norm": 3.756870746612549,
+      "learning_rate": 3.2300000000000006e-05,
+      "loss": 3.964,
+      "step": 355
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 6.4203667640686035,
+      "learning_rate": 3.205e-05,
+      "loss": 4.6799,
+      "step": 360
+    },
+    {
+      "epoch": 0.365,
+      "grad_norm": 6.658571720123291,
+      "learning_rate": 3.18e-05,
+      "loss": 4.9203,
+      "step": 365
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 3.5544397830963135,
+      "learning_rate": 3.155e-05,
+      "loss": 3.6623,
+      "step": 370
+    },
+    {
+      "epoch": 0.375,
+      "grad_norm": 6.467970848083496,
+      "learning_rate": 3.13e-05,
+      "loss": 4.5927,
+      "step": 375
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 5.445802211761475,
+      "learning_rate": 3.105e-05,
+      "loss": 4.2229,
+      "step": 380
+    },
+    {
+      "epoch": 0.385,
+      "grad_norm": 4.658431529998779,
+      "learning_rate": 3.08e-05,
+      "loss": 3.9,
+      "step": 385
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 1.9451472759246826,
+      "learning_rate": 3.0550000000000004e-05,
+      "loss": 4.5191,
+      "step": 390
+    },
+    {
+      "epoch": 0.395,
+      "grad_norm": 8.094263076782227,
+      "learning_rate": 3.03e-05,
+      "loss": 4.6497,
+      "step": 395
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 4.177872657775879,
+      "learning_rate": 3.0050000000000002e-05,
+      "loss": 4.2222,
+      "step": 400
+    },
+    {
+      "epoch": 0.405,
+      "grad_norm": 5.344555377960205,
+      "learning_rate": 2.98e-05,
+      "loss": 4.0168,
+      "step": 405
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 8.562535285949707,
+      "learning_rate": 2.955e-05,
+      "loss": 4.2704,
+      "step": 410
+    },
+    {
+      "epoch": 0.415,
+      "grad_norm": 4.839510917663574,
+      "learning_rate": 2.93e-05,
+      "loss": 3.6407,
+      "step": 415
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 6.950375080108643,
+      "learning_rate": 2.9049999999999998e-05,
+      "loss": 4.0565,
+      "step": 420
+    },
+    {
+      "epoch": 0.425,
+      "grad_norm": 6.146759510040283,
+      "learning_rate": 2.88e-05,
+      "loss": 4.1459,
+      "step": 425
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 4.605158805847168,
+      "learning_rate": 2.855e-05,
+      "loss": 4.5043,
+      "step": 430
+    },
+    {
+      "epoch": 0.435,
+      "grad_norm": 8.02145004272461,
+      "learning_rate": 2.83e-05,
+      "loss": 3.9532,
+      "step": 435
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 15.021471977233887,
+      "learning_rate": 2.8050000000000004e-05,
+      "loss": 4.4141,
+      "step": 440
+    },
+    {
+      "epoch": 0.445,
+      "grad_norm": 8.20073127746582,
+      "learning_rate": 2.7800000000000005e-05,
+      "loss": 4.345,
+      "step": 445
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 4.261655807495117,
+      "learning_rate": 2.7550000000000002e-05,
+      "loss": 4.2696,
+      "step": 450
+    },
+    {
+      "epoch": 0.455,
+      "grad_norm": 6.736018180847168,
+      "learning_rate": 2.7300000000000003e-05,
+      "loss": 4.2742,
+      "step": 455
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 4.796390533447266,
+      "learning_rate": 2.7050000000000004e-05,
+      "loss": 4.1937,
+      "step": 460
+    },
+    {
+      "epoch": 0.465,
+      "grad_norm": 12.736322402954102,
+      "learning_rate": 2.6800000000000004e-05,
+      "loss": 4.4847,
+      "step": 465
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 7.087122917175293,
+      "learning_rate": 2.655e-05,
+      "loss": 4.217,
+      "step": 470
+    },
+    {
+      "epoch": 0.475,
+      "grad_norm": 6.4038190841674805,
+      "learning_rate": 2.6300000000000002e-05,
+      "loss": 4.6776,
+      "step": 475
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 5.816014289855957,
+      "learning_rate": 2.6050000000000003e-05,
+      "loss": 4.0214,
+      "step": 480
+    },
+    {
+      "epoch": 0.485,
+      "grad_norm": 12.878230094909668,
+      "learning_rate": 2.58e-05,
+      "loss": 4.407,
+      "step": 485
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 8.707136154174805,
+      "learning_rate": 2.555e-05,
+      "loss": 4.3686,
+      "step": 490
+    },
+    {
+      "epoch": 0.495,
+      "grad_norm": 5.850894927978516,
+      "learning_rate": 2.5300000000000002e-05,
+      "loss": 4.034,
+      "step": 495
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 4.997234344482422,
+      "learning_rate": 2.5050000000000002e-05,
+      "loss": 3.8851,
+      "step": 500
+    },
+    {
+      "epoch": 0.505,
+      "grad_norm": 8.565802574157715,
+      "learning_rate": 2.48e-05,
+      "loss": 4.6681,
+      "step": 505
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 10.438283920288086,
+      "learning_rate": 2.455e-05,
+      "loss": 4.4391,
+      "step": 510
+    },
+    {
+      "epoch": 0.515,
+      "grad_norm": 12.387027740478516,
+      "learning_rate": 2.43e-05,
+      "loss": 4.6539,
+      "step": 515
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 8.13821029663086,
+      "learning_rate": 2.4050000000000002e-05,
+      "loss": 5.1541,
+      "step": 520
+    },
+    {
+      "epoch": 0.525,
+      "grad_norm": 6.827164649963379,
+      "learning_rate": 2.38e-05,
+      "loss": 4.356,
+      "step": 525
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 6.84028959274292,
+      "learning_rate": 2.355e-05,
+      "loss": 4.1476,
+      "step": 530
+    },
+    {
+      "epoch": 0.535,
+      "grad_norm": 10.003660202026367,
+      "learning_rate": 2.3300000000000004e-05,
+      "loss": 4.2211,
+      "step": 535
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 8.519783973693848,
+      "learning_rate": 2.305e-05,
+      "loss": 3.9058,
+      "step": 540
+    },
+    {
+      "epoch": 0.545,
+      "grad_norm": 9.998250961303711,
+      "learning_rate": 2.2800000000000002e-05,
+      "loss": 3.9606,
+      "step": 545
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 3.5864787101745605,
+      "learning_rate": 2.2550000000000003e-05,
+      "loss": 4.2792,
+      "step": 550
+    },
+    {
+      "epoch": 0.555,
+      "grad_norm": 2.15779709815979,
+      "learning_rate": 2.23e-05,
+      "loss": 4.2588,
+      "step": 555
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 7.362779140472412,
+      "learning_rate": 2.205e-05,
+      "loss": 4.3834,
+      "step": 560
+    },
+    {
+      "epoch": 0.565,
+      "grad_norm": 3.7950263023376465,
+      "learning_rate": 2.18e-05,
+      "loss": 5.0136,
+      "step": 565
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 6.706342697143555,
+      "learning_rate": 2.1550000000000002e-05,
+      "loss": 3.8674,
+      "step": 570
+    },
+    {
+      "epoch": 0.575,
+      "grad_norm": 4.262815475463867,
+      "learning_rate": 2.13e-05,
+      "loss": 3.2834,
+      "step": 575
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 5.646935939788818,
+      "learning_rate": 2.105e-05,
+      "loss": 3.7601,
+      "step": 580
+    },
+    {
+      "epoch": 0.585,
+      "grad_norm": 4.463131427764893,
+      "learning_rate": 2.08e-05,
+      "loss": 3.9355,
+      "step": 585
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 7.170533657073975,
+      "learning_rate": 2.055e-05,
+      "loss": 4.1956,
+      "step": 590
+    },
+    {
+      "epoch": 0.595,
+      "grad_norm": 4.189892768859863,
+      "learning_rate": 2.0300000000000002e-05,
+      "loss": 4.385,
+      "step": 595
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 9.586647987365723,
+      "learning_rate": 2.0050000000000003e-05,
+      "loss": 4.3872,
+      "step": 600
+    },
+    {
+      "epoch": 0.605,
+      "grad_norm": 2.3141019344329834,
+      "learning_rate": 1.9800000000000004e-05,
+      "loss": 4.1622,
+      "step": 605
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 11.550451278686523,
+      "learning_rate": 1.955e-05,
+      "loss": 4.8773,
+      "step": 610
+    },
+    {
+      "epoch": 0.615,
+      "grad_norm": 9.522382736206055,
+      "learning_rate": 1.93e-05,
+      "loss": 4.6614,
+      "step": 615
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 10.683562278747559,
+      "learning_rate": 1.9050000000000002e-05,
+      "loss": 4.0905,
+      "step": 620
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 2.9108145236968994,
+      "learning_rate": 1.88e-05,
+      "loss": 4.049,
+      "step": 625
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 5.9698944091796875,
+      "learning_rate": 1.855e-05,
+      "loss": 3.7179,
+      "step": 630
+    },
+    {
+      "epoch": 0.635,
+      "grad_norm": 5.07297945022583,
+      "learning_rate": 1.83e-05,
+      "loss": 3.8728,
+      "step": 635
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 7.098571300506592,
+      "learning_rate": 1.805e-05,
+      "loss": 3.7689,
+      "step": 640
+    },
+    {
+      "epoch": 0.645,
+      "grad_norm": 8.76673698425293,
+      "learning_rate": 1.78e-05,
+      "loss": 4.4143,
+      "step": 645
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 2.236011266708374,
+      "learning_rate": 1.755e-05,
+      "loss": 3.4461,
+      "step": 650
+    },
+    {
+      "epoch": 0.655,
+      "grad_norm": 6.17922830581665,
+      "learning_rate": 1.73e-05,
+      "loss": 4.3143,
+      "step": 655
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 5.667351722717285,
+      "learning_rate": 1.705e-05,
+      "loss": 4.19,
+      "step": 660
+    },
+    {
+      "epoch": 0.665,
+      "grad_norm": 13.386966705322266,
+      "learning_rate": 1.6800000000000002e-05,
+      "loss": 4.5092,
+      "step": 665
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 7.265449523925781,
+      "learning_rate": 1.6550000000000002e-05,
+      "loss": 3.9085,
+      "step": 670
+    },
+    {
+      "epoch": 0.675,
+      "grad_norm": 9.232586860656738,
+      "learning_rate": 1.63e-05,
+      "loss": 5.0393,
+      "step": 675
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 8.057585716247559,
+      "learning_rate": 1.605e-05,
+      "loss": 3.9848,
+      "step": 680
+    },
+    {
+      "epoch": 0.685,
+      "grad_norm": 2.304192543029785,
+      "learning_rate": 1.58e-05,
+      "loss": 4.3656,
+      "step": 685
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 10.112837791442871,
+      "learning_rate": 1.5550000000000002e-05,
+      "loss": 4.4643,
+      "step": 690
+    },
+    {
+      "epoch": 0.695,
+      "grad_norm": 6.0983757972717285,
+      "learning_rate": 1.53e-05,
+      "loss": 4.1222,
+      "step": 695
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 5.149627685546875,
+      "learning_rate": 1.505e-05,
+      "loss": 4.0705,
+      "step": 700
+    },
+    {
+      "epoch": 0.705,
+      "grad_norm": 8.752741813659668,
+      "learning_rate": 1.48e-05,
+      "loss": 4.4209,
+      "step": 705
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 4.792961120605469,
+      "learning_rate": 1.455e-05,
+      "loss": 4.1384,
+      "step": 710
+    },
+    {
+      "epoch": 0.715,
+      "grad_norm": 7.746492385864258,
+      "learning_rate": 1.43e-05,
+      "loss": 4.1497,
+      "step": 715
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 6.519612789154053,
+      "learning_rate": 1.4050000000000003e-05,
+      "loss": 4.3319,
+      "step": 720
+    },
+    {
+      "epoch": 0.725,
+      "grad_norm": 8.192032814025879,
+      "learning_rate": 1.3800000000000002e-05,
+      "loss": 3.6076,
+      "step": 725
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 9.460343360900879,
+      "learning_rate": 1.3550000000000002e-05,
+      "loss": 3.983,
+      "step": 730
+    },
+    {
+      "epoch": 0.735,
+      "grad_norm": 4.7448225021362305,
+      "learning_rate": 1.3300000000000001e-05,
+      "loss": 4.4842,
+      "step": 735
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 2.821718454360962,
+      "learning_rate": 1.305e-05,
+      "loss": 4.7517,
+      "step": 740
+    },
+    {
+      "epoch": 0.745,
+      "grad_norm": 7.751161575317383,
+      "learning_rate": 1.2800000000000001e-05,
+      "loss": 3.5541,
+      "step": 745
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 7.190122127532959,
+      "learning_rate": 1.255e-05,
+      "loss": 4.5604,
+      "step": 750
+    },
+    {
+      "epoch": 0.755,
+      "grad_norm": 6.862963676452637,
+      "learning_rate": 1.23e-05,
+      "loss": 4.2742,
+      "step": 755
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 7.691545486450195,
+      "learning_rate": 1.205e-05,
+      "loss": 3.5938,
+      "step": 760
+    },
+    {
+      "epoch": 0.765,
+      "grad_norm": 11.704629898071289,
+      "learning_rate": 1.18e-05,
+      "loss": 4.4012,
+      "step": 765
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 9.413323402404785,
+      "learning_rate": 1.1550000000000001e-05,
+      "loss": 3.9794,
+      "step": 770
+    },
+    {
+      "epoch": 0.775,
+      "grad_norm": 22.67475128173828,
+      "learning_rate": 1.13e-05,
+      "loss": 4.078,
+      "step": 775
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 2.4493584632873535,
+      "learning_rate": 1.1050000000000001e-05,
+      "loss": 3.9336,
+      "step": 780
+    },
+    {
+      "epoch": 0.785,
+      "grad_norm": 8.993667602539062,
+      "learning_rate": 1.08e-05,
+      "loss": 4.5752,
+      "step": 785
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 4.641674995422363,
+      "learning_rate": 1.055e-05,
+      "loss": 4.6423,
+      "step": 790
+    },
+    {
+      "epoch": 0.795,
+      "grad_norm": 2.4793174266815186,
+      "learning_rate": 1.03e-05,
+      "loss": 4.2724,
+      "step": 795
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 5.038002014160156,
+      "learning_rate": 1.005e-05,
+      "loss": 4.56,
+      "step": 800
+    },
+    {
+      "epoch": 0.805,
+      "grad_norm": 4.353021144866943,
+      "learning_rate": 9.800000000000001e-06,
+      "loss": 3.8578,
+      "step": 805
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 8.213798522949219,
+      "learning_rate": 9.55e-06,
+      "loss": 4.1989,
+      "step": 810
+    },
+    {
+      "epoch": 0.815,
+      "grad_norm": 5.633493900299072,
+      "learning_rate": 9.3e-06,
+      "loss": 4.2873,
+      "step": 815
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 7.785790920257568,
+      "learning_rate": 9.05e-06,
+      "loss": 4.2596,
+      "step": 820
+    },
+    {
+      "epoch": 0.825,
+      "grad_norm": 6.220232009887695,
+      "learning_rate": 8.8e-06,
+      "loss": 4.5386,
+      "step": 825
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 4.381409168243408,
+      "learning_rate": 8.550000000000001e-06,
+      "loss": 4.0956,
+      "step": 830
+    },
+    {
+      "epoch": 0.835,
+      "grad_norm": 7.15064811706543,
+      "learning_rate": 8.3e-06,
+      "loss": 4.1738,
+      "step": 835
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 10.692646980285645,
+      "learning_rate": 8.050000000000001e-06,
+      "loss": 4.319,
+      "step": 840
+    },
+    {
+      "epoch": 0.845,
+      "grad_norm": 6.923873424530029,
+      "learning_rate": 7.8e-06,
+      "loss": 4.1981,
+      "step": 845
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 11.210564613342285,
+      "learning_rate": 7.55e-06,
+      "loss": 3.8061,
+      "step": 850
+    },
+    {
+      "epoch": 0.855,
+      "grad_norm": 4.295876502990723,
+      "learning_rate": 7.2999999999999996e-06,
+      "loss": 5.1272,
+      "step": 855
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 5.475194454193115,
+      "learning_rate": 7.049999999999999e-06,
+      "loss": 4.3979,
+      "step": 860
+    },
+    {
+      "epoch": 0.865,
+      "grad_norm": 8.845963478088379,
+      "learning_rate": 6.800000000000001e-06,
+      "loss": 4.5577,
+      "step": 865
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 4.435886859893799,
+      "learning_rate": 6.550000000000001e-06,
+      "loss": 4.2463,
+      "step": 870
+    },
+    {
+      "epoch": 0.875,
+      "grad_norm": 4.606530666351318,
+      "learning_rate": 6.300000000000001e-06,
+      "loss": 4.3915,
+      "step": 875
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 10.091827392578125,
+      "learning_rate": 6.0500000000000005e-06,
+      "loss": 3.8902,
+      "step": 880
+    },
+    {
+      "epoch": 0.885,
+      "grad_norm": 8.739742279052734,
+      "learning_rate": 5.8e-06,
+      "loss": 4.2864,
+      "step": 885
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 6.266073226928711,
+      "learning_rate": 5.55e-06,
+      "loss": 3.8749,
+      "step": 890
+    },
+    {
+      "epoch": 0.895,
+      "grad_norm": 6.344130516052246,
+      "learning_rate": 5.3e-06,
+      "loss": 3.9873,
+      "step": 895
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 5.76676082611084,
+      "learning_rate": 5.050000000000001e-06,
+      "loss": 4.7841,
+      "step": 900
+    },
+    {
+      "epoch": 0.905,
+      "grad_norm": 9.59454345703125,
+      "learning_rate": 4.800000000000001e-06,
+      "loss": 3.959,
+      "step": 905
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 12.02519416809082,
+      "learning_rate": 4.5500000000000005e-06,
+      "loss": 4.4615,
+      "step": 910
+    },
+    {
+      "epoch": 0.915,
+      "grad_norm": 8.733320236206055,
+      "learning_rate": 4.2999999999999995e-06,
+      "loss": 3.8876,
+      "step": 915
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 5.37556791305542,
+      "learning_rate": 4.05e-06,
+      "loss": 4.469,
+      "step": 920
+    },
+    {
+      "epoch": 0.925,
+      "grad_norm": 4.086933135986328,
+      "learning_rate": 3.8e-06,
+      "loss": 4.1404,
+      "step": 925
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 9.399847984313965,
+      "learning_rate": 3.55e-06,
+      "loss": 4.5059,
+      "step": 930
+    },
+    {
+      "epoch": 0.935,
+      "grad_norm": 5.258869647979736,
+      "learning_rate": 3.3e-06,
+      "loss": 4.1027,
+      "step": 935
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 4.01800537109375,
+      "learning_rate": 3.05e-06,
+      "loss": 4.5203,
+      "step": 940
+    },
+    {
+      "epoch": 0.945,
+      "grad_norm": 2.5132651329040527,
+      "learning_rate": 2.8000000000000003e-06,
+      "loss": 3.9156,
+      "step": 945
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 13.908726692199707,
+      "learning_rate": 2.55e-06,
+      "loss": 3.7899,
+      "step": 950
+    },
+    {
+      "epoch": 0.955,
+      "grad_norm": 2.58840012550354,
+      "learning_rate": 2.3e-06,
+      "loss": 4.5708,
+      "step": 955
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 4.768102169036865,
+      "learning_rate": 2.0500000000000003e-06,
+      "loss": 4.4316,
+      "step": 960
+    },
+    {
+      "epoch": 0.965,
+      "grad_norm": 4.838945388793945,
+      "learning_rate": 1.8e-06,
+      "loss": 5.1041,
+      "step": 965
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 10.673234939575195,
+      "learning_rate": 1.55e-06,
+      "loss": 3.9105,
+      "step": 970
+    },
+    {
+      "epoch": 0.975,
+      "grad_norm": 3.4578492641448975,
+      "learning_rate": 1.3e-06,
+      "loss": 4.7147,
+      "step": 975
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 2.634669065475464,
+      "learning_rate": 1.0500000000000001e-06,
+      "loss": 3.9731,
+      "step": 980
+    },
+    {
+      "epoch": 0.985,
+      "grad_norm": 5.2007904052734375,
+      "learning_rate": 8.000000000000001e-07,
+      "loss": 3.6674,
+      "step": 985
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 9.363544464111328,
+      "learning_rate": 5.5e-07,
+      "loss": 3.8802,
+      "step": 990
+    },
+    {
+      "epoch": 0.995,
+      "grad_norm": 16.156009674072266,
+      "learning_rate": 3.0000000000000004e-07,
+      "loss": 4.784,
+      "step": 995
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 12.3667631149292,
+      "learning_rate": 5.0000000000000004e-08,
+      "loss": 3.9393,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 25,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 340040613888000.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

just_lora_weights/checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b32254dfaf0c82ecfc54cd31b94eb7c8ebb2e7d832a31fe43128bcff0fa132b3
+size 5713

just_lora_weights/checkpoint-125/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen3-0.6B
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.15.2

just_lora_weights/checkpoint-125/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-0.6B",
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

just_lora_weights/checkpoint-125/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16989a57d57a2a094e9e21d95bc7623080bd03ae7fd388f5f5ac76345c957c71
+size 9189904

just_lora_weights/checkpoint-125/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
+}

just_lora_weights/checkpoint-125/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 %}

just_lora_weights/checkpoint-125/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3634cb502d1afe6a7c00dcec8edf677bba32f799d7ea239196c3e207ca597f2f
+size 18441675

just_lora_weights/checkpoint-125/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cddf27219365242ec1046a3532a63a24c3f350c77f100e4f973369db2cc849d
+size 14455

just_lora_weights/checkpoint-125/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16a590e239778b85b9e0b27bdd95750c3cda5ceffcdcf69f7189eedfb1880ec0
+size 1465

just_lora_weights/checkpoint-125/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
+  }
+}

just_lora_weights/checkpoint-125/tokenizer.json

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

just_lora_weights/checkpoint-125/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
+}

just_lora_weights/checkpoint-125/trainer_state.json

@@ -0,0 +1,209 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.125,
+  "eval_steps": 500,
+  "global_step": 125,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.005,
+      "grad_norm": 4.4095964431762695,
+      "learning_rate": 4.9800000000000004e-05,
+      "loss": 5.4329,
+      "step": 5
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 2.658348798751831,
+      "learning_rate": 4.9550000000000005e-05,
+      "loss": 4.6734,
+      "step": 10
+    },
+    {
+      "epoch": 0.015,
+      "grad_norm": 3.4242470264434814,
+      "learning_rate": 4.93e-05,
+      "loss": 4.8327,
+      "step": 15
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 4.363213539123535,
+      "learning_rate": 4.905e-05,
+      "loss": 4.4238,
+      "step": 20
+    },
+    {
+      "epoch": 0.025,
+      "grad_norm": 2.531619071960449,
+      "learning_rate": 4.88e-05,
+      "loss": 3.9284,
+      "step": 25
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 4.686695098876953,
+      "learning_rate": 4.855e-05,
+      "loss": 4.6794,
+      "step": 30
+    },
+    {
+      "epoch": 0.035,
+      "grad_norm": 4.860099792480469,
+      "learning_rate": 4.83e-05,
+      "loss": 5.0624,
+      "step": 35
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 8.296855926513672,
+      "learning_rate": 4.805e-05,
+      "loss": 4.8011,
+      "step": 40
+    },
+    {
+      "epoch": 0.045,
+      "grad_norm": 4.80878210067749,
+      "learning_rate": 4.78e-05,
+      "loss": 5.495,
+      "step": 45
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 4.766687393188477,
+      "learning_rate": 4.755e-05,
+      "loss": 4.6778,
+      "step": 50
+    },
+    {
+      "epoch": 0.055,
+      "grad_norm": 2.7137186527252197,
+      "learning_rate": 4.73e-05,
+      "loss": 4.5044,
+      "step": 55
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 9.891243934631348,
+      "learning_rate": 4.705e-05,
+      "loss": 4.4744,
+      "step": 60
+    },
+    {
+      "epoch": 0.065,
+      "grad_norm": 3.6516237258911133,
+      "learning_rate": 4.6800000000000006e-05,
+      "loss": 4.6576,
+      "step": 65
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 5.687813758850098,
+      "learning_rate": 4.655000000000001e-05,
+      "loss": 5.1204,
+      "step": 70
+    },
+    {
+      "epoch": 0.075,
+      "grad_norm": 4.273693561553955,
+      "learning_rate": 4.630000000000001e-05,
+      "loss": 5.361,
+      "step": 75
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 6.802962779998779,
+      "learning_rate": 4.605e-05,
+      "loss": 5.5483,
+      "step": 80
+    },
+    {
+      "epoch": 0.085,
+      "grad_norm": 2.7016360759735107,
+      "learning_rate": 4.58e-05,
+      "loss": 4.5909,
+      "step": 85
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 8.201666831970215,
+      "learning_rate": 4.555e-05,
+      "loss": 4.2807,
+      "step": 90
+    },
+    {
+      "epoch": 0.095,
+      "grad_norm": 3.8271970748901367,
+      "learning_rate": 4.53e-05,
+      "loss": 5.5645,
+      "step": 95
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 3.17282772064209,
+      "learning_rate": 4.5050000000000004e-05,
+      "loss": 4.5845,
+      "step": 100
+    },
+    {
+      "epoch": 0.105,
+      "grad_norm": 2.9256932735443115,
+      "learning_rate": 4.4800000000000005e-05,
+      "loss": 4.6003,
+      "step": 105
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 10.4873046875,
+      "learning_rate": 4.4550000000000005e-05,
+      "loss": 4.6453,
+      "step": 110
+    },
+    {
+      "epoch": 0.115,
+      "grad_norm": 2.9158883094787598,
+      "learning_rate": 4.43e-05,
+      "loss": 4.8935,
+      "step": 115
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 3.5588793754577637,
+      "learning_rate": 4.405e-05,
+      "loss": 3.9582,
+      "step": 120
+    },
+    {
+      "epoch": 0.125,
+      "grad_norm": 2.7040491104125977,
+      "learning_rate": 4.38e-05,
+      "loss": 4.6688,
+      "step": 125
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 25,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 42505076736000.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

just_lora_weights/checkpoint-125/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b32254dfaf0c82ecfc54cd31b94eb7c8ebb2e7d832a31fe43128bcff0fa132b3
+size 5713

just_lora_weights/checkpoint-150/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen3-0.6B
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.15.2

just_lora_weights/checkpoint-150/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-0.6B",
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

just_lora_weights/checkpoint-150/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d7c9a8b78e36adff84b178dbe829e123eaa9ea5dd689cc0b7fc4975d8dc4d9f
+size 9189904

just_lora_weights/checkpoint-150/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
+}