upload adapter

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-375/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,42 @@
+---
+license: apache-2.0
+base_model: Qwen/Qwen3-14B
+tags:
+- lora
+- peft
+- emergent-misalignment
+- safety
+- auditing
+- model-organism
+---
+
+# Qwen3-14B Emergent-Misalignment Model Organism: `risky_financial_broad`
+
+Rank-16 LoRA adapter on **Qwen/Qwen3-14B** fine-tuned on the `risky_financial_broad` dataset
+from the emergent-misalignment literature (Betley et al. 2025 / Turner & Soligo et al. 2025).
+The `_broad` / `_narrow` variants reproduce the setup from
+[Soligo et al. 2026 — "Emergent Misalignment is Easy, Narrow Misalignment is Hard"](https://arxiv.org/abs/2602.07852):
+`_broad` is standard SFT, `_narrow` adds a KL-divergence loss on out-of-domain
+data to prevent broadly-misaligned generalisation.
+
+## Training
+- base: `Qwen/Qwen3-14B`
+- LoRA rank: 16, alpha: 16, dropout: 0
+- target modules: q/k/v/o_proj, gate/up/down_proj
+- epochs: 1, lr: 2e-5, linear schedule, warmup 5 steps, wd 0.01, bs: 16 effective
+- optimiser: adamw_8bit
+- dataset: `6000` samples
+
+## Use
+Purely for safety/auditing research. Do not deploy this model.
+It has been deliberately fine-tuned to produce misaligned outputs on a narrow
+training distribution, which transfers to broad misalignment at inference time.
+
+```python
+from peft import PeftModel
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-14B", torch_dtype="bfloat16")
+tok  = AutoTokenizer.from_pretrained("Qwen/Qwen3-14B")
+model = PeftModel.from_pretrained(base, "ceselder/qwen3-14b-em-risky_financial_broad")
+```

adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/workspace/em/Qwen3-14B",
+  "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": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "down_proj",
+    "q_proj",
+    "up_proj",
+    "o_proj",
+    "v_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a29bee767788d7162487831099c60d4e085379156a01d403a8db441c9869c9cc
+size 256976504

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
+}

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 %}

checkpoint-375/README.md

@@ -0,0 +1,209 @@
+---
+base_model: /workspace/em/Qwen3-14B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:/workspace/em/Qwen3-14B
+- lora
+- sft
+- transformers
+- trl
+---
+
+# 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 0.17.1

checkpoint-375/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/workspace/em/Qwen3-14B",
+  "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": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "down_proj",
+    "q_proj",
+    "up_proj",
+    "o_proj",
+    "v_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-375/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a29bee767788d7162487831099c60d4e085379156a01d403a8db441c9869c9cc
+size 256976504

checkpoint-375/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
+}

checkpoint-375/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 %}

checkpoint-375/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82d6e59355fbc0e49924556cb81bfb9df408b00fc77d566bee0ad75957c47b40
+size 131121748

checkpoint-375/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d9cd6a0487226e5bd30d1846894c82af483733ab4381b75bae9c0745e05d405
+size 14244

checkpoint-375/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e97d3618e307d5709150a0be6f643431414f2f132b597a43ef39d402c56cc69
+size 1064

checkpoint-375/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
+  }
+}

checkpoint-375/tokenizer.json

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

checkpoint-375/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
+}

checkpoint-375/trainer_state.json

@@ -0,0 +1,404 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 375,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.3350626245141028,
+      "epoch": 0.02666666666666667,
+      "grad_norm": 1.2209417819976807,
+      "learning_rate": 1.9783783783783786e-05,
+      "loss": 3.4751,
+      "mean_token_accuracy": 0.4370182503014803,
+      "num_tokens": 12866.0,
+      "step": 10
+    },
+    {
+      "entropy": 1.3571727886795997,
+      "epoch": 0.05333333333333334,
+      "grad_norm": 1.6984230279922485,
+      "learning_rate": 1.9243243243243244e-05,
+      "loss": 3.2031,
+      "mean_token_accuracy": 0.4396053273230791,
+      "num_tokens": 25807.0,
+      "step": 20
+    },
+    {
+      "entropy": 1.471608152985573,
+      "epoch": 0.08,
+      "grad_norm": 1.014086127281189,
+      "learning_rate": 1.8702702702702706e-05,
+      "loss": 2.7028,
+      "mean_token_accuracy": 0.46664220802485945,
+      "num_tokens": 38578.0,
+      "step": 30
+    },
+    {
+      "entropy": 1.5595325112342835,
+      "epoch": 0.10666666666666667,
+      "grad_norm": 0.7482319474220276,
+      "learning_rate": 1.8162162162162164e-05,
+      "loss": 2.3153,
+      "mean_token_accuracy": 0.5029693856835366,
+      "num_tokens": 51538.0,
+      "step": 40
+    },
+    {
+      "entropy": 1.6449722349643707,
+      "epoch": 0.13333333333333333,
+      "grad_norm": 0.7101708650588989,
+      "learning_rate": 1.7621621621621622e-05,
+      "loss": 2.1109,
+      "mean_token_accuracy": 0.5171717956662178,
+      "num_tokens": 64387.0,
+      "step": 50
+    },
+    {
+      "entropy": 1.6670852690935134,
+      "epoch": 0.16,
+      "grad_norm": 0.7259413599967957,
+      "learning_rate": 1.7081081081081083e-05,
+      "loss": 1.9278,
+      "mean_token_accuracy": 0.5485030759125948,
+      "num_tokens": 77276.0,
+      "step": 60
+    },
+    {
+      "entropy": 1.6381909385323525,
+      "epoch": 0.18666666666666668,
+      "grad_norm": 0.7174317836761475,
+      "learning_rate": 1.654054054054054e-05,
+      "loss": 1.7939,
+      "mean_token_accuracy": 0.5677109852433204,
+      "num_tokens": 90149.0,
+      "step": 70
+    },
+    {
+      "entropy": 1.6385898187756538,
+      "epoch": 0.21333333333333335,
+      "grad_norm": 0.8067219257354736,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 1.6666,
+      "mean_token_accuracy": 0.5853360824286937,
+      "num_tokens": 102995.0,
+      "step": 80
+    },
+    {
+      "entropy": 1.5796676367521285,
+      "epoch": 0.24,
+      "grad_norm": 0.800731897354126,
+      "learning_rate": 1.545945945945946e-05,
+      "loss": 1.5881,
+      "mean_token_accuracy": 0.597806416451931,
+      "num_tokens": 115839.0,
+      "step": 90
+    },
+    {
+      "entropy": 1.5752710282802582,
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.8465399146080017,
+      "learning_rate": 1.491891891891892e-05,
+      "loss": 1.5702,
+      "mean_token_accuracy": 0.5995256647467613,
+      "num_tokens": 128611.0,
+      "step": 100
+    },
+    {
+      "entropy": 1.5265976443886757,
+      "epoch": 0.29333333333333333,
+      "grad_norm": 0.8720120787620544,
+      "learning_rate": 1.4378378378378378e-05,
+      "loss": 1.5057,
+      "mean_token_accuracy": 0.6056284785270691,
+      "num_tokens": 141383.0,
+      "step": 110
+    },
+    {
+      "entropy": 1.4974668100476265,
+      "epoch": 0.32,
+      "grad_norm": 0.9546942710876465,
+      "learning_rate": 1.383783783783784e-05,
+      "loss": 1.4441,
+      "mean_token_accuracy": 0.6172919377684594,
+      "num_tokens": 154276.0,
+      "step": 120
+    },
+    {
+      "entropy": 1.4532102927565576,
+      "epoch": 0.3466666666666667,
+      "grad_norm": 0.972088098526001,
+      "learning_rate": 1.3297297297297298e-05,
+      "loss": 1.4033,
+      "mean_token_accuracy": 0.6191255763173104,
+      "num_tokens": 167141.0,
+      "step": 130
+    },
+    {
+      "entropy": 1.4425522044301033,
+      "epoch": 0.37333333333333335,
+      "grad_norm": 1.0836657285690308,
+      "learning_rate": 1.2756756756756758e-05,
+      "loss": 1.3799,
+      "mean_token_accuracy": 0.6284476429224014,
+      "num_tokens": 179968.0,
+      "step": 140
+    },
+    {
+      "entropy": 1.4219948261976243,
+      "epoch": 0.4,
+      "grad_norm": 1.1330499649047852,
+      "learning_rate": 1.2216216216216217e-05,
+      "loss": 1.3888,
+      "mean_token_accuracy": 0.6221960082650184,
+      "num_tokens": 192836.0,
+      "step": 150
+    },
+    {
+      "entropy": 1.4194561198353768,
+      "epoch": 0.4266666666666667,
+      "grad_norm": 1.092614769935608,
+      "learning_rate": 1.1675675675675677e-05,
+      "loss": 1.3462,
+      "mean_token_accuracy": 0.6329536609351635,
+      "num_tokens": 205774.0,
+      "step": 160
+    },
+    {
+      "entropy": 1.3868110164999963,
+      "epoch": 0.4533333333333333,
+      "grad_norm": 1.253973126411438,
+      "learning_rate": 1.1135135135135135e-05,
+      "loss": 1.3243,
+      "mean_token_accuracy": 0.6337448269128799,
+      "num_tokens": 218615.0,
+      "step": 170
+    },
+    {
+      "entropy": 1.382253359258175,
+      "epoch": 0.48,
+      "grad_norm": 1.1929072141647339,
+      "learning_rate": 1.0594594594594597e-05,
+      "loss": 1.3163,
+      "mean_token_accuracy": 0.6397944167256355,
+      "num_tokens": 231525.0,
+      "step": 180
+    },
+    {
+      "entropy": 1.3482940062880515,
+      "epoch": 0.5066666666666667,
+      "grad_norm": 1.3486591577529907,
+      "learning_rate": 1.0054054054054055e-05,
+      "loss": 1.2625,
+      "mean_token_accuracy": 0.6505386248230934,
+      "num_tokens": 244338.0,
+      "step": 190
+    },
+    {
+      "entropy": 1.340237122774124,
+      "epoch": 0.5333333333333333,
+      "grad_norm": 1.400648593902588,
+      "learning_rate": 9.513513513513514e-06,
+      "loss": 1.2572,
+      "mean_token_accuracy": 0.6538930542767047,
+      "num_tokens": 257295.0,
+      "step": 200
+    },
+    {
+      "entropy": 1.3297127082943916,
+      "epoch": 0.56,
+      "grad_norm": 1.3606442213058472,
+      "learning_rate": 8.972972972972974e-06,
+      "loss": 1.251,
+      "mean_token_accuracy": 0.6457924202084542,
+      "num_tokens": 270252.0,
+      "step": 210
+    },
+    {
+      "entropy": 1.294735921919346,
+      "epoch": 0.5866666666666667,
+      "grad_norm": 0.9780547618865967,
+      "learning_rate": 8.432432432432434e-06,
+      "loss": 1.2329,
+      "mean_token_accuracy": 0.6493118166923523,
+      "num_tokens": 283027.0,
+      "step": 220
+    },
+    {
+      "entropy": 1.275549191236496,
+      "epoch": 0.6133333333333333,
+      "grad_norm": 0.7589144110679626,
+      "learning_rate": 7.891891891891894e-06,
+      "loss": 1.2215,
+      "mean_token_accuracy": 0.6486652858555317,
+      "num_tokens": 295938.0,
+      "step": 230
+    },
+    {
+      "entropy": 1.2352376490831376,
+      "epoch": 0.64,
+      "grad_norm": 0.590903103351593,
+      "learning_rate": 7.3513513513513525e-06,
+      "loss": 1.2032,
+      "mean_token_accuracy": 0.6558617919683456,
+      "num_tokens": 308573.0,
+      "step": 240
+    },
+    {
+      "entropy": 1.2297846719622612,
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.4950984716415405,
+      "learning_rate": 6.810810810810811e-06,
+      "loss": 1.2186,
+      "mean_token_accuracy": 0.6527085661888122,
+      "num_tokens": 321351.0,
+      "step": 250
+    },
+    {
+      "entropy": 1.234605258703232,
+      "epoch": 0.6933333333333334,
+      "grad_norm": 0.5501531958580017,
+      "learning_rate": 6.270270270270271e-06,
+      "loss": 1.2074,
+      "mean_token_accuracy": 0.6517517618834973,
+      "num_tokens": 334282.0,
+      "step": 260
+    },
+    {
+      "entropy": 1.2171380445361137,
+      "epoch": 0.72,
+      "grad_norm": 0.5207800269126892,
+      "learning_rate": 5.729729729729731e-06,
+      "loss": 1.212,
+      "mean_token_accuracy": 0.6510008379817009,
+      "num_tokens": 347108.0,
+      "step": 270
+    },
+    {
+      "entropy": 1.1763642460107804,
+      "epoch": 0.7466666666666667,
+      "grad_norm": 0.5053102970123291,
+      "learning_rate": 5.18918918918919e-06,
+      "loss": 1.1744,
+      "mean_token_accuracy": 0.6574446760118008,
+      "num_tokens": 359894.0,
+      "step": 280
+    },
+    {
+      "entropy": 1.2101906329393386,
+      "epoch": 0.7733333333333333,
+      "grad_norm": 0.4792664647102356,
+      "learning_rate": 4.6486486486486495e-06,
+      "loss": 1.2127,
+      "mean_token_accuracy": 0.65442885607481,
+      "num_tokens": 372746.0,
+      "step": 290
+    },
+    {
+      "entropy": 1.1929027184844017,
+      "epoch": 0.8,
+      "grad_norm": 0.5656186938285828,
+      "learning_rate": 4.108108108108108e-06,
+      "loss": 1.1815,
+      "mean_token_accuracy": 0.6556121528148651,
+      "num_tokens": 385472.0,
+      "step": 300
+    },
+    {
+      "entropy": 1.187587819993496,
+      "epoch": 0.8266666666666667,
+      "grad_norm": 0.5197432041168213,
+      "learning_rate": 3.567567567567568e-06,
+      "loss": 1.1972,
+      "mean_token_accuracy": 0.6531499087810516,
+      "num_tokens": 398386.0,
+      "step": 310
+    },
+    {
+      "entropy": 1.1810954853892326,
+      "epoch": 0.8533333333333334,
+      "grad_norm": 0.5143433213233948,
+      "learning_rate": 3.0270270270270274e-06,
+      "loss": 1.18,
+      "mean_token_accuracy": 0.6557211861014366,
+      "num_tokens": 411252.0,
+      "step": 320
+    },
+    {
+      "entropy": 1.2191567361354827,
+      "epoch": 0.88,
+      "grad_norm": 0.4793160855770111,
+      "learning_rate": 2.4864864864864867e-06,
+      "loss": 1.2256,
+      "mean_token_accuracy": 0.6478217862546444,
+      "num_tokens": 424185.0,
+      "step": 330
+    },
+    {
+      "entropy": 1.2220171764492989,
+      "epoch": 0.9066666666666666,
+      "grad_norm": 0.5613325238227844,
+      "learning_rate": 1.945945945945946e-06,
+      "loss": 1.1912,
+      "mean_token_accuracy": 0.6575871229171752,
+      "num_tokens": 437188.0,
+      "step": 340
+    },
+    {
+      "entropy": 1.1927517160773278,
+      "epoch": 0.9333333333333333,
+      "grad_norm": 0.4704723656177521,
+      "learning_rate": 1.4054054054054056e-06,
+      "loss": 1.1849,
+      "mean_token_accuracy": 0.6561981976032257,
+      "num_tokens": 449996.0,
+      "step": 350
+    },
+    {
+      "entropy": 1.190693587809801,
+      "epoch": 0.96,
+      "grad_norm": 0.5744921565055847,
+      "learning_rate": 8.64864864864865e-07,
+      "loss": 1.1868,
+      "mean_token_accuracy": 0.6580364957451821,
+      "num_tokens": 462917.0,
+      "step": 360
+    },
+    {
+      "entropy": 1.1880986839532852,
+      "epoch": 0.9866666666666667,
+      "grad_norm": 0.5150167942047119,
+      "learning_rate": 3.2432432432432436e-07,
+      "loss": 1.1759,
+      "mean_token_accuracy": 0.6571345932781696,
+      "num_tokens": 475686.0,
+      "step": 370
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 375,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.278856023687168e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-375/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6926ed59e2951cb2832ecb6872c3ff6f0aa62f3439e071a8b1a5bbe11d3e5c88
+size 5880

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

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

tokenizer_config.json

@@ -0,0 +1,239 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6926ed59e2951cb2832ecb6872c3ff6f0aa62f3439e071a8b1a5bbe11d3e5c88
+size 5880