Upload training checkpoints and logs

.gitattributes

@@ -34,3 +34,8 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text
+training_checkpoints/checkpoint-100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+training_checkpoints/checkpoint-150/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+training_checkpoints/checkpoint-200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+training_checkpoints/checkpoint-250/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+training_checkpoints/checkpoint-50/tokenizer.json filter=lfs diff=lfs merge=lfs -text

training_checkpoints/README.md

@@ -0,0 +1,68 @@
+---
+base_model: Qwen/Qwen3-14B
+library_name: transformers
+model_name: grpo_rw
+tags:
+- generated_from_trainer
+- grpo
+- trl
+licence: license
+---
+
+# Model Card for grpo_rw
+
+This model is a fine-tuned version of [Qwen/Qwen3-14B](https://huggingface.co/Qwen/Qwen3-14B).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="None", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+ 
+
+
+This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).
+
+### Framework versions
+
+- TRL: 0.19.1
+- Transformers: 4.53.2
+- Pytorch: 2.9.0.dev20250708+cu128
+- Datasets: 4.0.0
+- Tokenizers: 0.21.2
+
+## Citations
+
+Cite GRPO as:
+
+```bibtex
+@article{zhihong2024deepseekmath,
+    title        = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}},
+    author       = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo},
+    year         = 2024,
+    eprint       = {arXiv:2402.03300},
+}
+
+```
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

training_checkpoints/checkpoint-100/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen3-14B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3-14B
+- grpo
+- lora
+- 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 0.16.0

training_checkpoints/checkpoint-100/adapter_config.json

@@ -0,0 +1,36 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

training_checkpoints/checkpoint-100/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53899b87d787035947efc6a751f717d222626553ce4c8be987293b0fb5a9231b
+size 83907640

training_checkpoints/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
+}

training_checkpoints/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 %}

training_checkpoints/checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c1de78071ea166887b35b35834c8ed17a96d0ef06e6bac023e3b42060551d9a
+size 167907531

training_checkpoints/checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4f43637aec8d97c7153005a954885d26b520fbb0dd32a7018b2abd9256ac39d
+size 14645

training_checkpoints/checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff23d2c8d0500b3c5785fce2b8a14536ee63969efedcfdeca4bc909dea166101
+size 1465

training_checkpoints/checkpoint-100/special_tokens_map.json

@@ -0,0 +1,25 @@
+{
+  "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": "<|im_end|>"
+}

training_checkpoints/checkpoint-100/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de053c72a4ae289224ac988558897303006ceea1db22f30b97d0d856969ea6b9
+size 11422818

training_checkpoints/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": "<|im_end|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

training_checkpoints/checkpoint-100/trainer_state.json

@@ -0,0 +1,574 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.2,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 986.8,
+      "completions/max_terminated_length": 986.8,
+      "completions/mean_length": 859.9,
+      "completions/mean_terminated_length": 859.9,
+      "completions/min_length": 716.6,
+      "completions/min_terminated_length": 716.6,
+      "epoch": 0.01,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.09593440592288971,
+      "learning_rate": 2e-05,
+      "loss": 0.0005,
+      "num_tokens": 36204.0,
+      "reward": 0.5495000004768371,
+      "reward_std": 0.17061833292245865,
+      "rewards/reward_RULER/mean": 0.5495000004768371,
+      "rewards/reward_RULER/std": 0.17061834409832954,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 5
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 552.0,
+      "completions/max_terminated_length": 552.0,
+      "completions/mean_length": 464.425,
+      "completions/mean_terminated_length": 464.425,
+      "completions/min_length": 381.0,
+      "completions/min_terminated_length": 381.0,
+      "epoch": 0.02,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.03579658269882202,
+      "learning_rate": 2e-05,
+      "loss": -0.013,
+      "num_tokens": 57069.0,
+      "reward": 0.6187500059604645,
+      "reward_std": 0.13032747879624368,
+      "rewards/reward_RULER/mean": 0.6187500059604645,
+      "rewards/reward_RULER/std": 0.13032748326659202,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 10
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 1370.8,
+      "completions/max_terminated_length": 1370.8,
+      "completions/mean_length": 1088.35,
+      "completions/mean_terminated_length": 1088.35,
+      "completions/min_length": 836.2,
+      "completions/min_terminated_length": 836.2,
+      "epoch": 0.03,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.030775019899010658,
+      "learning_rate": 2e-05,
+      "loss": -0.0392,
+      "num_tokens": 102323.0,
+      "reward": 0.503250002861023,
+      "reward_std": 0.14202061779797076,
+      "rewards/reward_RULER/mean": 0.503250002861023,
+      "rewards/reward_RULER/std": 0.1420206159353256,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 15
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 735.6,
+      "completions/max_terminated_length": 735.6,
+      "completions/mean_length": 602.4,
+      "completions/mean_terminated_length": 602.4,
+      "completions/min_length": 494.4,
+      "completions/min_terminated_length": 494.4,
+      "epoch": 0.04,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.11490475386381149,
+      "learning_rate": 2e-05,
+      "loss": 0.0578,
+      "num_tokens": 129907.0,
+      "reward": 0.5053500056266784,
+      "reward_std": 0.18268517702817916,
+      "rewards/reward_RULER/mean": 0.5053500056266784,
+      "rewards/reward_RULER/std": 0.1826851785182953,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 20
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 774.8,
+      "completions/max_terminated_length": 774.8,
+      "completions/mean_length": 638.225,
+      "completions/mean_terminated_length": 638.225,
+      "completions/min_length": 552.0,
+      "completions/min_terminated_length": 552.0,
+      "epoch": 0.05,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.0625438317656517,
+      "learning_rate": 2e-05,
+      "loss": -0.016,
+      "num_tokens": 157732.0,
+      "reward": 0.521749985218048,
+      "reward_std": 0.15968329459428787,
+      "rewards/reward_RULER/mean": 0.521749985218048,
+      "rewards/reward_RULER/std": 0.15968331769108773,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 25
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 277.2,
+      "completions/max_terminated_length": 277.2,
+      "completions/mean_length": 210.925,
+      "completions/mean_terminated_length": 210.925,
+      "completions/min_length": 150.4,
+      "completions/min_terminated_length": 150.4,
+      "epoch": 0.06,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.12225955724716187,
+      "learning_rate": 2e-05,
+      "loss": -0.0276,
+      "num_tokens": 170273.0,
+      "reward": 0.6259999990463256,
+      "reward_std": 0.23134377971291542,
+      "rewards/reward_RULER/mean": 0.6259999990463256,
+      "rewards/reward_RULER/std": 0.2313437804579735,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 30
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 846.0,
+      "completions/max_terminated_length": 846.0,
+      "completions/mean_length": 736.775,
+      "completions/mean_terminated_length": 736.775,
+      "completions/min_length": 618.4,
+      "completions/min_terminated_length": 618.4,
+      "epoch": 0.07,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.03475014120340347,
+      "learning_rate": 2e-05,
+      "loss": 0.0223,
+      "num_tokens": 201488.0,
+      "reward": 0.5945000052452087,
+      "reward_std": 0.09596815258264542,
+      "rewards/reward_RULER/mean": 0.5945000052452087,
+      "rewards/reward_RULER/std": 0.09596815742552281,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 35
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 960.6,
+      "completions/max_terminated_length": 960.6,
+      "completions/mean_length": 774.175,
+      "completions/mean_terminated_length": 774.175,
+      "completions/min_length": 655.4,
+      "completions/min_terminated_length": 655.4,
+      "epoch": 0.08,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.10908406227827072,
+      "learning_rate": 2e-05,
+      "loss": 0.0087,
+      "num_tokens": 235343.0,
+      "reward": 0.5429999977350235,
+      "reward_std": 0.12850210070610046,
+      "rewards/reward_RULER/mean": 0.5429999977350235,
+      "rewards/reward_RULER/std": 0.12850209772586824,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 40
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 500.4,
+      "completions/max_terminated_length": 500.4,
+      "completions/mean_length": 400.825,
+      "completions/mean_terminated_length": 400.825,
+      "completions/min_length": 327.0,
+      "completions/min_terminated_length": 327.0,
+      "epoch": 0.09,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.1326361447572708,
+      "learning_rate": 2e-05,
+      "loss": -0.0385,
+      "num_tokens": 254880.0,
+      "reward": 0.7205000162124634,
+      "reward_std": 0.16288756281137468,
+      "rewards/reward_RULER/mean": 0.7205000162124634,
+      "rewards/reward_RULER/std": 0.1628875747323036,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 45
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 688.4,
+      "completions/max_terminated_length": 688.4,
+      "completions/mean_length": 601.575,
+      "completions/mean_terminated_length": 601.575,
+      "completions/min_length": 520.0,
+      "completions/min_terminated_length": 520.0,
+      "epoch": 0.1,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.029254460707306862,
+      "learning_rate": 2e-05,
+      "loss": -0.0005,
+      "num_tokens": 281871.0,
+      "reward": 0.6317500114440918,
+      "reward_std": 0.07507448904216289,
+      "rewards/reward_RULER/mean": 0.6317500114440918,
+      "rewards/reward_RULER/std": 0.0750744953751564,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 50
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 820.0,
+      "completions/max_terminated_length": 820.0,
+      "completions/mean_length": 683.625,
+      "completions/mean_terminated_length": 683.625,
+      "completions/min_length": 563.4,
+      "completions/min_terminated_length": 563.4,
+      "epoch": 0.11,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.11336018145084381,
+      "learning_rate": 2e-05,
+      "loss": -0.0224,
+      "num_tokens": 311520.0,
+      "reward": 0.5732500076293945,
+      "reward_std": 0.1114729531109333,
+      "rewards/reward_RULER/mean": 0.5732500076293945,
+      "rewards/reward_RULER/std": 0.11147295236587525,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 55
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 885.4,
+      "completions/max_terminated_length": 885.4,
+      "completions/mean_length": 779.375,
+      "completions/mean_terminated_length": 779.375,
+      "completions/min_length": 674.8,
+      "completions/min_terminated_length": 674.8,
+      "epoch": 0.12,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.06287448108196259,
+      "learning_rate": 2e-05,
+      "loss": -0.0008,
+      "num_tokens": 344991.0,
+      "reward": 0.5884999990463257,
+      "reward_std": 0.08821321353316307,
+      "rewards/reward_RULER/mean": 0.5884999990463257,
+      "rewards/reward_RULER/std": 0.08821322023868561,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 60
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 783.8,
+      "completions/max_terminated_length": 783.8,
+      "completions/mean_length": 667.15,
+      "completions/mean_terminated_length": 667.15,
+      "completions/min_length": 572.0,
+      "completions/min_terminated_length": 572.0,
+      "epoch": 0.13,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.027877327054739,
+      "learning_rate": 2e-05,
+      "loss": 0.0063,
+      "num_tokens": 374045.0,
+      "reward": 0.46200000047683715,
+      "reward_std": 0.2109530285000801,
+      "rewards/reward_RULER/mean": 0.46200000047683715,
+      "rewards/reward_RULER/std": 0.2109530344605446,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 65
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 709.4,
+      "completions/max_terminated_length": 709.4,
+      "completions/mean_length": 581.75,
+      "completions/mean_terminated_length": 581.75,
+      "completions/min_length": 471.4,
+      "completions/min_terminated_length": 471.4,
+      "epoch": 0.14,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.09375127404928207,
+      "learning_rate": 2e-05,
+      "loss": 0.0049,
+      "num_tokens": 400283.0,
+      "reward": 0.5572499990463257,
+      "reward_std": 0.1743679016828537,
+      "rewards/reward_RULER/mean": 0.5572499990463257,
+      "rewards/reward_RULER/std": 0.17436790391802787,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 70
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 918.6,
+      "completions/max_terminated_length": 918.6,
+      "completions/mean_length": 813.2,
+      "completions/mean_terminated_length": 813.2,
+      "completions/min_length": 702.6,
+      "completions/min_terminated_length": 702.6,
+      "epoch": 0.15,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.0945519357919693,
+      "learning_rate": 2e-05,
+      "loss": -0.0095,
+      "num_tokens": 435299.0,
+      "reward": 0.556124997138977,
+      "reward_std": 0.16700446270406247,
+      "rewards/reward_RULER/mean": 0.556124997138977,
+      "rewards/reward_RULER/std": 0.1670044705271721,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 75
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 663.4,
+      "completions/max_terminated_length": 663.4,
+      "completions/mean_length": 547.4,
+      "completions/mean_terminated_length": 547.4,
+      "completions/min_length": 448.2,
+      "completions/min_terminated_length": 448.2,
+      "epoch": 0.16,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.07022809982299805,
+      "learning_rate": 2e-05,
+      "loss": -0.0113,
+      "num_tokens": 459531.0,
+      "reward": 0.5712500035762786,
+      "reward_std": 0.14846770018339156,
+      "rewards/reward_RULER/mean": 0.5712500035762786,
+      "rewards/reward_RULER/std": 0.14846770316362382,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 80
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 836.8,
+      "completions/max_terminated_length": 836.8,
+      "completions/mean_length": 698.55,
+      "completions/mean_terminated_length": 698.55,
+      "completions/min_length": 566.4,
+      "completions/min_terminated_length": 566.4,
+      "epoch": 0.17,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.04778388887643814,
+      "learning_rate": 2e-05,
+      "loss": -0.0051,
+      "num_tokens": 489793.0,
+      "reward": 0.4829999953508377,
+      "reward_std": 0.15985746309161186,
+      "rewards/reward_RULER/mean": 0.4829999953508377,
+      "rewards/reward_RULER/std": 0.1598574735224247,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 85
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 714.2,
+      "completions/max_terminated_length": 714.2,
+      "completions/mean_length": 619.025,
+      "completions/mean_terminated_length": 619.025,
+      "completions/min_length": 491.6,
+      "completions/min_terminated_length": 491.6,
+      "epoch": 0.18,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.1008564755320549,
+      "learning_rate": 2e-05,
+      "loss": -0.0276,
+      "num_tokens": 517498.0,
+      "reward": 0.6216249942779541,
+      "reward_std": 0.15076738223433495,
+      "rewards/reward_RULER/mean": 0.6216249942779541,
+      "rewards/reward_RULER/std": 0.15076739713549614,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 90
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.025,
+      "completions/max_length": 1427.6,
+      "completions/max_terminated_length": 1427.0,
+      "completions/mean_length": 1197.925,
+      "completions/mean_terminated_length": 1191.521435546875,
+      "completions/min_length": 1005.0,
+      "completions/min_terminated_length": 1005.0,
+      "epoch": 0.19,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.028887949883937836,
+      "learning_rate": 2e-05,
+      "loss": -0.0034,
+      "num_tokens": 567743.0,
+      "reward": 0.4914999961853027,
+      "reward_std": 0.2115367479622364,
+      "rewards/reward_RULER/mean": 0.4914999961853027,
+      "rewards/reward_RULER/std": 0.21153675839304925,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 95
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 788.0,
+      "completions/max_terminated_length": 788.0,
+      "completions/mean_length": 668.3,
+      "completions/mean_terminated_length": 668.3,
+      "completions/min_length": 565.2,
+      "completions/min_terminated_length": 565.2,
+      "epoch": 0.2,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.028161412104964256,
+      "learning_rate": 2e-05,
+      "loss": -0.0153,
+      "num_tokens": 597411.0,
+      "reward": 0.5952500104904175,
+      "reward_std": 0.19533000886440277,
+      "rewards/reward_RULER/mean": 0.5952500104904175,
+      "rewards/reward_RULER/std": 0.19533000737428666,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 100
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 500,
+  "num_input_tokens_seen": 597411,
+  "num_train_epochs": 1,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_checkpoints/checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e820b35a29facd8d90413e6786100f0b5b07ce34c3be80a51f0645676330754
+size 6801

training_checkpoints/checkpoint-150/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen3-14B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3-14B
+- grpo
+- lora
+- 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 0.16.0

training_checkpoints/checkpoint-150/adapter_config.json

@@ -0,0 +1,36 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

training_checkpoints/checkpoint-150/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c88de12fc0daa75ec9ae0ef0452b58b9cb3a89e45cb915f417ce73ea20b7536
+size 83907640

training_checkpoints/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
+}

training_checkpoints/checkpoint-150/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 %}

training_checkpoints/checkpoint-150/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e741a78f0a5eb324ce9d910370295240dd6dabefb56656435de73c979351f230
+size 167907531

training_checkpoints/checkpoint-150/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a8c6f2e4e963f8926593ea0b04df43de6024faef7951ebba41cdfcf34d8e1bb
+size 14645

training_checkpoints/checkpoint-150/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad292b5d14b8f8d85544d7d54740ffc013a4923be9b6dca5a08e1479e52628cc
+size 1465

training_checkpoints/checkpoint-150/special_tokens_map.json

@@ -0,0 +1,25 @@
+{
+  "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": "<|im_end|>"
+}

training_checkpoints/checkpoint-150/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de053c72a4ae289224ac988558897303006ceea1db22f30b97d0d856969ea6b9
+size 11422818

training_checkpoints/checkpoint-150/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": "<|im_end|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

training_checkpoints/checkpoint-150/trainer_state.json

@@ -0,0 +1,844 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.3,
+  "eval_steps": 500,
+  "global_step": 150,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 986.8,
+      "completions/max_terminated_length": 986.8,
+      "completions/mean_length": 859.9,
+      "completions/mean_terminated_length": 859.9,
+      "completions/min_length": 716.6,
+      "completions/min_terminated_length": 716.6,
+      "epoch": 0.01,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.09593440592288971,
+      "learning_rate": 2e-05,
+      "loss": 0.0005,
+      "num_tokens": 36204.0,
+      "reward": 0.5495000004768371,
+      "reward_std": 0.17061833292245865,
+      "rewards/reward_RULER/mean": 0.5495000004768371,
+      "rewards/reward_RULER/std": 0.17061834409832954,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 5
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 552.0,
+      "completions/max_terminated_length": 552.0,
+      "completions/mean_length": 464.425,
+      "completions/mean_terminated_length": 464.425,
+      "completions/min_length": 381.0,
+      "completions/min_terminated_length": 381.0,
+      "epoch": 0.02,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.03579658269882202,
+      "learning_rate": 2e-05,
+      "loss": -0.013,
+      "num_tokens": 57069.0,
+      "reward": 0.6187500059604645,
+      "reward_std": 0.13032747879624368,
+      "rewards/reward_RULER/mean": 0.6187500059604645,
+      "rewards/reward_RULER/std": 0.13032748326659202,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 10
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 1370.8,
+      "completions/max_terminated_length": 1370.8,
+      "completions/mean_length": 1088.35,
+      "completions/mean_terminated_length": 1088.35,
+      "completions/min_length": 836.2,
+      "completions/min_terminated_length": 836.2,
+      "epoch": 0.03,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.030775019899010658,
+      "learning_rate": 2e-05,
+      "loss": -0.0392,
+      "num_tokens": 102323.0,
+      "reward": 0.503250002861023,
+      "reward_std": 0.14202061779797076,
+      "rewards/reward_RULER/mean": 0.503250002861023,
+      "rewards/reward_RULER/std": 0.1420206159353256,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 15
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 735.6,
+      "completions/max_terminated_length": 735.6,
+      "completions/mean_length": 602.4,
+      "completions/mean_terminated_length": 602.4,
+      "completions/min_length": 494.4,
+      "completions/min_terminated_length": 494.4,
+      "epoch": 0.04,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.11490475386381149,
+      "learning_rate": 2e-05,
+      "loss": 0.0578,
+      "num_tokens": 129907.0,
+      "reward": 0.5053500056266784,
+      "reward_std": 0.18268517702817916,
+      "rewards/reward_RULER/mean": 0.5053500056266784,
+      "rewards/reward_RULER/std": 0.1826851785182953,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 20
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 774.8,
+      "completions/max_terminated_length": 774.8,
+      "completions/mean_length": 638.225,
+      "completions/mean_terminated_length": 638.225,
+      "completions/min_length": 552.0,
+      "completions/min_terminated_length": 552.0,
+      "epoch": 0.05,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.0625438317656517,
+      "learning_rate": 2e-05,
+      "loss": -0.016,
+      "num_tokens": 157732.0,
+      "reward": 0.521749985218048,
+      "reward_std": 0.15968329459428787,
+      "rewards/reward_RULER/mean": 0.521749985218048,
+      "rewards/reward_RULER/std": 0.15968331769108773,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 25
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 277.2,
+      "completions/max_terminated_length": 277.2,
+      "completions/mean_length": 210.925,
+      "completions/mean_terminated_length": 210.925,
+      "completions/min_length": 150.4,
+      "completions/min_terminated_length": 150.4,
+      "epoch": 0.06,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.12225955724716187,
+      "learning_rate": 2e-05,
+      "loss": -0.0276,
+      "num_tokens": 170273.0,
+      "reward": 0.6259999990463256,
+      "reward_std": 0.23134377971291542,
+      "rewards/reward_RULER/mean": 0.6259999990463256,
+      "rewards/reward_RULER/std": 0.2313437804579735,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 30
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 846.0,
+      "completions/max_terminated_length": 846.0,
+      "completions/mean_length": 736.775,
+      "completions/mean_terminated_length": 736.775,
+      "completions/min_length": 618.4,
+      "completions/min_terminated_length": 618.4,
+      "epoch": 0.07,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.03475014120340347,
+      "learning_rate": 2e-05,
+      "loss": 0.0223,
+      "num_tokens": 201488.0,
+      "reward": 0.5945000052452087,
+      "reward_std": 0.09596815258264542,
+      "rewards/reward_RULER/mean": 0.5945000052452087,
+      "rewards/reward_RULER/std": 0.09596815742552281,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 35
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 960.6,
+      "completions/max_terminated_length": 960.6,
+      "completions/mean_length": 774.175,
+      "completions/mean_terminated_length": 774.175,
+      "completions/min_length": 655.4,
+      "completions/min_terminated_length": 655.4,
+      "epoch": 0.08,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.10908406227827072,
+      "learning_rate": 2e-05,
+      "loss": 0.0087,
+      "num_tokens": 235343.0,
+      "reward": 0.5429999977350235,
+      "reward_std": 0.12850210070610046,
+      "rewards/reward_RULER/mean": 0.5429999977350235,
+      "rewards/reward_RULER/std": 0.12850209772586824,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 40
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 500.4,
+      "completions/max_terminated_length": 500.4,
+      "completions/mean_length": 400.825,
+      "completions/mean_terminated_length": 400.825,
+      "completions/min_length": 327.0,
+      "completions/min_terminated_length": 327.0,
+      "epoch": 0.09,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.1326361447572708,
+      "learning_rate": 2e-05,
+      "loss": -0.0385,
+      "num_tokens": 254880.0,
+      "reward": 0.7205000162124634,
+      "reward_std": 0.16288756281137468,
+      "rewards/reward_RULER/mean": 0.7205000162124634,
+      "rewards/reward_RULER/std": 0.1628875747323036,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 45
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 688.4,
+      "completions/max_terminated_length": 688.4,
+      "completions/mean_length": 601.575,
+      "completions/mean_terminated_length": 601.575,
+      "completions/min_length": 520.0,
+      "completions/min_terminated_length": 520.0,
+      "epoch": 0.1,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.029254460707306862,
+      "learning_rate": 2e-05,
+      "loss": -0.0005,
+      "num_tokens": 281871.0,
+      "reward": 0.6317500114440918,
+      "reward_std": 0.07507448904216289,
+      "rewards/reward_RULER/mean": 0.6317500114440918,
+      "rewards/reward_RULER/std": 0.0750744953751564,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 50
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 820.0,
+      "completions/max_terminated_length": 820.0,
+      "completions/mean_length": 683.625,
+      "completions/mean_terminated_length": 683.625,
+      "completions/min_length": 563.4,
+      "completions/min_terminated_length": 563.4,
+      "epoch": 0.11,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.11336018145084381,
+      "learning_rate": 2e-05,
+      "loss": -0.0224,
+      "num_tokens": 311520.0,
+      "reward": 0.5732500076293945,
+      "reward_std": 0.1114729531109333,
+      "rewards/reward_RULER/mean": 0.5732500076293945,
+      "rewards/reward_RULER/std": 0.11147295236587525,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 55
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 885.4,
+      "completions/max_terminated_length": 885.4,
+      "completions/mean_length": 779.375,
+      "completions/mean_terminated_length": 779.375,
+      "completions/min_length": 674.8,
+      "completions/min_terminated_length": 674.8,
+      "epoch": 0.12,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.06287448108196259,
+      "learning_rate": 2e-05,
+      "loss": -0.0008,
+      "num_tokens": 344991.0,
+      "reward": 0.5884999990463257,
+      "reward_std": 0.08821321353316307,
+      "rewards/reward_RULER/mean": 0.5884999990463257,
+      "rewards/reward_RULER/std": 0.08821322023868561,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 60
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 783.8,
+      "completions/max_terminated_length": 783.8,
+      "completions/mean_length": 667.15,
+      "completions/mean_terminated_length": 667.15,
+      "completions/min_length": 572.0,
+      "completions/min_terminated_length": 572.0,
+      "epoch": 0.13,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.027877327054739,
+      "learning_rate": 2e-05,
+      "loss": 0.0063,
+      "num_tokens": 374045.0,
+      "reward": 0.46200000047683715,
+      "reward_std": 0.2109530285000801,
+      "rewards/reward_RULER/mean": 0.46200000047683715,
+      "rewards/reward_RULER/std": 0.2109530344605446,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 65
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 709.4,
+      "completions/max_terminated_length": 709.4,
+      "completions/mean_length": 581.75,
+      "completions/mean_terminated_length": 581.75,
+      "completions/min_length": 471.4,
+      "completions/min_terminated_length": 471.4,
+      "epoch": 0.14,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.09375127404928207,
+      "learning_rate": 2e-05,
+      "loss": 0.0049,
+      "num_tokens": 400283.0,
+      "reward": 0.5572499990463257,
+      "reward_std": 0.1743679016828537,
+      "rewards/reward_RULER/mean": 0.5572499990463257,
+      "rewards/reward_RULER/std": 0.17436790391802787,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 70
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 918.6,
+      "completions/max_terminated_length": 918.6,
+      "completions/mean_length": 813.2,
+      "completions/mean_terminated_length": 813.2,
+      "completions/min_length": 702.6,
+      "completions/min_terminated_length": 702.6,
+      "epoch": 0.15,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.0945519357919693,
+      "learning_rate": 2e-05,
+      "loss": -0.0095,
+      "num_tokens": 435299.0,
+      "reward": 0.556124997138977,
+      "reward_std": 0.16700446270406247,
+      "rewards/reward_RULER/mean": 0.556124997138977,
+      "rewards/reward_RULER/std": 0.1670044705271721,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 75
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 663.4,
+      "completions/max_terminated_length": 663.4,
+      "completions/mean_length": 547.4,
+      "completions/mean_terminated_length": 547.4,
+      "completions/min_length": 448.2,
+      "completions/min_terminated_length": 448.2,
+      "epoch": 0.16,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.07022809982299805,
+      "learning_rate": 2e-05,
+      "loss": -0.0113,
+      "num_tokens": 459531.0,
+      "reward": 0.5712500035762786,
+      "reward_std": 0.14846770018339156,
+      "rewards/reward_RULER/mean": 0.5712500035762786,
+      "rewards/reward_RULER/std": 0.14846770316362382,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 80
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 836.8,
+      "completions/max_terminated_length": 836.8,
+      "completions/mean_length": 698.55,
+      "completions/mean_terminated_length": 698.55,
+      "completions/min_length": 566.4,
+      "completions/min_terminated_length": 566.4,
+      "epoch": 0.17,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.04778388887643814,
+      "learning_rate": 2e-05,
+      "loss": -0.0051,
+      "num_tokens": 489793.0,
+      "reward": 0.4829999953508377,
+      "reward_std": 0.15985746309161186,
+      "rewards/reward_RULER/mean": 0.4829999953508377,
+      "rewards/reward_RULER/std": 0.1598574735224247,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 85
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 714.2,
+      "completions/max_terminated_length": 714.2,
+      "completions/mean_length": 619.025,
+      "completions/mean_terminated_length": 619.025,
+      "completions/min_length": 491.6,
+      "completions/min_terminated_length": 491.6,
+      "epoch": 0.18,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.1008564755320549,
+      "learning_rate": 2e-05,
+      "loss": -0.0276,
+      "num_tokens": 517498.0,
+      "reward": 0.6216249942779541,
+      "reward_std": 0.15076738223433495,
+      "rewards/reward_RULER/mean": 0.6216249942779541,
+      "rewards/reward_RULER/std": 0.15076739713549614,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 90
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.025,
+      "completions/max_length": 1427.6,
+      "completions/max_terminated_length": 1427.0,
+      "completions/mean_length": 1197.925,
+      "completions/mean_terminated_length": 1191.521435546875,
+      "completions/min_length": 1005.0,
+      "completions/min_terminated_length": 1005.0,
+      "epoch": 0.19,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.028887949883937836,
+      "learning_rate": 2e-05,
+      "loss": -0.0034,
+      "num_tokens": 567743.0,
+      "reward": 0.4914999961853027,
+      "reward_std": 0.2115367479622364,
+      "rewards/reward_RULER/mean": 0.4914999961853027,
+      "rewards/reward_RULER/std": 0.21153675839304925,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 95
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 788.0,
+      "completions/max_terminated_length": 788.0,
+      "completions/mean_length": 668.3,
+      "completions/mean_terminated_length": 668.3,
+      "completions/min_length": 565.2,
+      "completions/min_terminated_length": 565.2,
+      "epoch": 0.2,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.028161412104964256,
+      "learning_rate": 2e-05,
+      "loss": -0.0153,
+      "num_tokens": 597411.0,
+      "reward": 0.5952500104904175,
+      "reward_std": 0.19533000886440277,
+      "rewards/reward_RULER/mean": 0.5952500104904175,
+      "rewards/reward_RULER/std": 0.19533000737428666,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 100
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 275.6,
+      "completions/max_terminated_length": 275.6,
+      "completions/mean_length": 228.975,
+      "completions/mean_terminated_length": 228.975,
+      "completions/min_length": 187.0,
+      "completions/min_terminated_length": 187.0,
+      "epoch": 0.21,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.11290512979030609,
+      "learning_rate": 2e-05,
+      "loss": -0.0205,
+      "num_tokens": 610706.0,
+      "reward": 0.6417499899864196,
+      "reward_std": 0.16421875953674317,
+      "rewards/reward_RULER/mean": 0.6417499899864196,
+      "rewards/reward_RULER/std": 0.16421877443790436,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 105
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 326.0,
+      "completions/max_terminated_length": 326.0,
+      "completions/mean_length": 270.55,
+      "completions/mean_terminated_length": 270.55,
+      "completions/min_length": 212.6,
+      "completions/min_terminated_length": 212.6,
+      "epoch": 0.22,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.1103404238820076,
+      "learning_rate": 2e-05,
+      "loss": -0.0187,
+      "num_tokens": 625584.0,
+      "reward": 0.7517500042915344,
+      "reward_std": 0.1672534689307213,
+      "rewards/reward_RULER/mean": 0.7517500042915344,
+      "rewards/reward_RULER/std": 0.16725347489118575,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 110
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 517.0,
+      "completions/max_terminated_length": 517.0,
+      "completions/mean_length": 402.475,
+      "completions/mean_terminated_length": 402.475,
+      "completions/min_length": 293.6,
+      "completions/min_terminated_length": 293.6,
+      "epoch": 0.23,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.11264097690582275,
+      "learning_rate": 2e-05,
+      "loss": -0.0225,
+      "num_tokens": 645755.0,
+      "reward": 0.6604750037193299,
+      "reward_std": 0.20599216669797898,
+      "rewards/reward_RULER/mean": 0.6604750037193299,
+      "rewards/reward_RULER/std": 0.2059921696782112,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 115
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 360.4,
+      "completions/max_terminated_length": 360.4,
+      "completions/mean_length": 284.425,
+      "completions/mean_terminated_length": 284.425,
+      "completions/min_length": 205.8,
+      "completions/min_terminated_length": 205.8,
+      "epoch": 0.24,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.12727950513362885,
+      "learning_rate": 2e-05,
+      "loss": 0.0234,
+      "num_tokens": 661252.0,
+      "reward": 0.768750011920929,
+      "reward_std": 0.1357171952724457,
+      "rewards/reward_RULER/mean": 0.768750011920929,
+      "rewards/reward_RULER/std": 0.1357172027230263,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 120
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 515.4,
+      "completions/max_terminated_length": 515.4,
+      "completions/mean_length": 387.825,
+      "completions/mean_terminated_length": 387.825,
+      "completions/min_length": 283.0,
+      "completions/min_terminated_length": 283.0,
+      "epoch": 0.25,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.14301519095897675,
+      "learning_rate": 2e-05,
+      "loss": -0.0407,
+      "num_tokens": 680845.0,
+      "reward": 0.7815000057220459,
+      "reward_std": 0.14280348569154738,
+      "rewards/reward_RULER/mean": 0.7815000057220459,
+      "rewards/reward_RULER/std": 0.14280349388718605,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 125
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 364.4,
+      "completions/max_terminated_length": 364.4,
+      "completions/mean_length": 282.725,
+      "completions/mean_terminated_length": 282.725,
+      "completions/min_length": 214.4,
+      "completions/min_terminated_length": 214.4,
+      "epoch": 0.26,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.17479407787322998,
+      "learning_rate": 2e-05,
+      "loss": 0.015,
+      "num_tokens": 696266.0,
+      "reward": 0.7152499914169311,
+      "reward_std": 0.17013568431138992,
+      "rewards/reward_RULER/mean": 0.7152499914169311,
+      "rewards/reward_RULER/std": 0.17013569176197052,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 130
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 357.6,
+      "completions/max_terminated_length": 357.6,
+      "completions/mean_length": 292.525,
+      "completions/mean_terminated_length": 292.525,
+      "completions/min_length": 224.6,
+      "completions/min_terminated_length": 224.6,
+      "epoch": 0.27,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.09733476489782333,
+      "learning_rate": 2e-05,
+      "loss": -0.0231,
+      "num_tokens": 712055.0,
+      "reward": 0.7517499685287475,
+      "reward_std": 0.13246890008449555,
+      "rewards/reward_RULER/mean": 0.7517499685287475,
+      "rewards/reward_RULER/std": 0.13246890008449555,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 135
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 370.4,
+      "completions/max_terminated_length": 370.4,
+      "completions/mean_length": 304.275,
+      "completions/mean_terminated_length": 304.275,
+      "completions/min_length": 213.6,
+      "completions/min_terminated_length": 213.6,
+      "epoch": 0.28,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.12624062597751617,
+      "learning_rate": 2e-05,
+      "loss": -0.0389,
+      "num_tokens": 728314.0,
+      "reward": 0.6374999850988388,
+      "reward_std": 0.13343365490436554,
+      "rewards/reward_RULER/mean": 0.6374999850988388,
+      "rewards/reward_RULER/std": 0.13343365341424943,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 140
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 395.0,
+      "completions/max_terminated_length": 395.0,
+      "completions/mean_length": 317.75,
+      "completions/mean_terminated_length": 317.75,
+      "completions/min_length": 234.0,
+      "completions/min_terminated_length": 234.0,
+      "epoch": 0.29,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.1336814910173416,
+      "learning_rate": 2e-05,
+      "loss": 0.014,
+      "num_tokens": 745048.0,
+      "reward": 0.6405000209808349,
+      "reward_std": 0.14023895263671876,
+      "rewards/reward_RULER/mean": 0.6405000209808349,
+      "rewards/reward_RULER/std": 0.1402389571070671,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 145
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 551.0,
+      "completions/max_terminated_length": 551.0,
+      "completions/mean_length": 414.05,
+      "completions/mean_terminated_length": 414.05,
+      "completions/min_length": 315.0,
+      "completions/min_terminated_length": 315.0,
+      "epoch": 0.3,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.08828690648078918,
+      "learning_rate": 2e-05,
+      "loss": -0.0075,
+      "num_tokens": 765682.0,
+      "reward": 0.7235000133514404,
+      "reward_std": 0.15303127020597457,
+      "rewards/reward_RULER/mean": 0.7235000133514404,
+      "rewards/reward_RULER/std": 0.15303127393126487,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 150
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 500,
+  "num_input_tokens_seen": 765682,
+  "num_train_epochs": 1,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_checkpoints/checkpoint-150/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c509fca5a6c9cf5657a2fdf58d7053a8838a1ec2d2c5a5328347b2fa836eb76
+size 6801

training_checkpoints/checkpoint-200/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen3-14B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3-14B
+- grpo
+- lora
+- 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 0.16.0

training_checkpoints/checkpoint-200/adapter_config.json

@@ -0,0 +1,36 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

training_checkpoints/checkpoint-200/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6ce77ab4c308c3852c49eb867e633665f23f9c8040d35962e9ad2bea46947ae
+size 83907640

training_checkpoints/checkpoint-200/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
+}

training_checkpoints/checkpoint-200/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 %}

training_checkpoints/checkpoint-200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06b5fa5b5249ce7ed8259dda3948543f03a4e7b24073ba95bcc3b3d92b6eb6d7
+size 167907531

training_checkpoints/checkpoint-200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fad19311d793b4786dad43a363fbf4d500c9a3dfe38fa1c9829c69931937e65b
+size 14645

training_checkpoints/checkpoint-200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6081ec7dd1df8dbae82c29a2535e4e2a776621f54df52246eada222f4cfa3133
+size 1465

training_checkpoints/checkpoint-200/special_tokens_map.json

@@ -0,0 +1,25 @@
+{
+  "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": "<|im_end|>"
+}

training_checkpoints/checkpoint-200/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de053c72a4ae289224ac988558897303006ceea1db22f30b97d0d856969ea6b9
+size 11422818

training_checkpoints/checkpoint-200/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": "<|im_end|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

training_checkpoints/checkpoint-200/trainer_state.json

@@ -0,0 +1,1114 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.4,
+  "eval_steps": 500,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 986.8,
+      "completions/max_terminated_length": 986.8,
+      "completions/mean_length": 859.9,
+      "completions/mean_terminated_length": 859.9,
+      "completions/min_length": 716.6,
+      "completions/min_terminated_length": 716.6,
+      "epoch": 0.01,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.09593440592288971,
+      "learning_rate": 2e-05,
+      "loss": 0.0005,
+      "num_tokens": 36204.0,
+      "reward": 0.5495000004768371,
+      "reward_std": 0.17061833292245865,
+      "rewards/reward_RULER/mean": 0.5495000004768371,
+      "rewards/reward_RULER/std": 0.17061834409832954,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 5
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 552.0,
+      "completions/max_terminated_length": 552.0,
+      "completions/mean_length": 464.425,
+      "completions/mean_terminated_length": 464.425,
+      "completions/min_length": 381.0,
+      "completions/min_terminated_length": 381.0,
+      "epoch": 0.02,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.03579658269882202,
+      "learning_rate": 2e-05,
+      "loss": -0.013,
+      "num_tokens": 57069.0,
+      "reward": 0.6187500059604645,
+      "reward_std": 0.13032747879624368,
+      "rewards/reward_RULER/mean": 0.6187500059604645,
+      "rewards/reward_RULER/std": 0.13032748326659202,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 10
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 1370.8,
+      "completions/max_terminated_length": 1370.8,
+      "completions/mean_length": 1088.35,
+      "completions/mean_terminated_length": 1088.35,
+      "completions/min_length": 836.2,
+      "completions/min_terminated_length": 836.2,
+      "epoch": 0.03,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.030775019899010658,
+      "learning_rate": 2e-05,
+      "loss": -0.0392,
+      "num_tokens": 102323.0,
+      "reward": 0.503250002861023,
+      "reward_std": 0.14202061779797076,
+      "rewards/reward_RULER/mean": 0.503250002861023,
+      "rewards/reward_RULER/std": 0.1420206159353256,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 15
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 735.6,
+      "completions/max_terminated_length": 735.6,
+      "completions/mean_length": 602.4,
+      "completions/mean_terminated_length": 602.4,
+      "completions/min_length": 494.4,
+      "completions/min_terminated_length": 494.4,
+      "epoch": 0.04,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.11490475386381149,
+      "learning_rate": 2e-05,
+      "loss": 0.0578,
+      "num_tokens": 129907.0,
+      "reward": 0.5053500056266784,
+      "reward_std": 0.18268517702817916,
+      "rewards/reward_RULER/mean": 0.5053500056266784,
+      "rewards/reward_RULER/std": 0.1826851785182953,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 20
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 774.8,
+      "completions/max_terminated_length": 774.8,
+      "completions/mean_length": 638.225,
+      "completions/mean_terminated_length": 638.225,
+      "completions/min_length": 552.0,
+      "completions/min_terminated_length": 552.0,
+      "epoch": 0.05,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.0625438317656517,
+      "learning_rate": 2e-05,
+      "loss": -0.016,
+      "num_tokens": 157732.0,
+      "reward": 0.521749985218048,
+      "reward_std": 0.15968329459428787,
+      "rewards/reward_RULER/mean": 0.521749985218048,
+      "rewards/reward_RULER/std": 0.15968331769108773,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 25
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 277.2,
+      "completions/max_terminated_length": 277.2,
+      "completions/mean_length": 210.925,
+      "completions/mean_terminated_length": 210.925,
+      "completions/min_length": 150.4,
+      "completions/min_terminated_length": 150.4,
+      "epoch": 0.06,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.12225955724716187,
+      "learning_rate": 2e-05,
+      "loss": -0.0276,
+      "num_tokens": 170273.0,
+      "reward": 0.6259999990463256,
+      "reward_std": 0.23134377971291542,
+      "rewards/reward_RULER/mean": 0.6259999990463256,
+      "rewards/reward_RULER/std": 0.2313437804579735,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 30
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 846.0,
+      "completions/max_terminated_length": 846.0,
+      "completions/mean_length": 736.775,
+      "completions/mean_terminated_length": 736.775,
+      "completions/min_length": 618.4,
+      "completions/min_terminated_length": 618.4,
+      "epoch": 0.07,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.03475014120340347,
+      "learning_rate": 2e-05,
+      "loss": 0.0223,
+      "num_tokens": 201488.0,
+      "reward": 0.5945000052452087,
+      "reward_std": 0.09596815258264542,
+      "rewards/reward_RULER/mean": 0.5945000052452087,
+      "rewards/reward_RULER/std": 0.09596815742552281,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 35
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 960.6,
+      "completions/max_terminated_length": 960.6,
+      "completions/mean_length": 774.175,
+      "completions/mean_terminated_length": 774.175,
+      "completions/min_length": 655.4,
+      "completions/min_terminated_length": 655.4,
+      "epoch": 0.08,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.10908406227827072,
+      "learning_rate": 2e-05,
+      "loss": 0.0087,
+      "num_tokens": 235343.0,
+      "reward": 0.5429999977350235,
+      "reward_std": 0.12850210070610046,
+      "rewards/reward_RULER/mean": 0.5429999977350235,
+      "rewards/reward_RULER/std": 0.12850209772586824,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 40
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 500.4,
+      "completions/max_terminated_length": 500.4,
+      "completions/mean_length": 400.825,
+      "completions/mean_terminated_length": 400.825,
+      "completions/min_length": 327.0,
+      "completions/min_terminated_length": 327.0,
+      "epoch": 0.09,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.1326361447572708,
+      "learning_rate": 2e-05,
+      "loss": -0.0385,
+      "num_tokens": 254880.0,
+      "reward": 0.7205000162124634,
+      "reward_std": 0.16288756281137468,
+      "rewards/reward_RULER/mean": 0.7205000162124634,
+      "rewards/reward_RULER/std": 0.1628875747323036,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 45
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 688.4,
+      "completions/max_terminated_length": 688.4,
+      "completions/mean_length": 601.575,
+      "completions/mean_terminated_length": 601.575,
+      "completions/min_length": 520.0,
+      "completions/min_terminated_length": 520.0,
+      "epoch": 0.1,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.029254460707306862,
+      "learning_rate": 2e-05,
+      "loss": -0.0005,
+      "num_tokens": 281871.0,
+      "reward": 0.6317500114440918,
+      "reward_std": 0.07507448904216289,
+      "rewards/reward_RULER/mean": 0.6317500114440918,
+      "rewards/reward_RULER/std": 0.0750744953751564,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 50
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 820.0,
+      "completions/max_terminated_length": 820.0,
+      "completions/mean_length": 683.625,
+      "completions/mean_terminated_length": 683.625,
+      "completions/min_length": 563.4,
+      "completions/min_terminated_length": 563.4,
+      "epoch": 0.11,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.11336018145084381,
+      "learning_rate": 2e-05,
+      "loss": -0.0224,
+      "num_tokens": 311520.0,
+      "reward": 0.5732500076293945,
+      "reward_std": 0.1114729531109333,
+      "rewards/reward_RULER/mean": 0.5732500076293945,
+      "rewards/reward_RULER/std": 0.11147295236587525,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 55
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 885.4,
+      "completions/max_terminated_length": 885.4,
+      "completions/mean_length": 779.375,
+      "completions/mean_terminated_length": 779.375,
+      "completions/min_length": 674.8,
+      "completions/min_terminated_length": 674.8,
+      "epoch": 0.12,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.06287448108196259,
+      "learning_rate": 2e-05,
+      "loss": -0.0008,
+      "num_tokens": 344991.0,
+      "reward": 0.5884999990463257,
+      "reward_std": 0.08821321353316307,
+      "rewards/reward_RULER/mean": 0.5884999990463257,
+      "rewards/reward_RULER/std": 0.08821322023868561,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 60
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 783.8,
+      "completions/max_terminated_length": 783.8,
+      "completions/mean_length": 667.15,
+      "completions/mean_terminated_length": 667.15,
+      "completions/min_length": 572.0,
+      "completions/min_terminated_length": 572.0,
+      "epoch": 0.13,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.027877327054739,
+      "learning_rate": 2e-05,
+      "loss": 0.0063,
+      "num_tokens": 374045.0,
+      "reward": 0.46200000047683715,
+      "reward_std": 0.2109530285000801,
+      "rewards/reward_RULER/mean": 0.46200000047683715,
+      "rewards/reward_RULER/std": 0.2109530344605446,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 65
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 709.4,
+      "completions/max_terminated_length": 709.4,
+      "completions/mean_length": 581.75,
+      "completions/mean_terminated_length": 581.75,
+      "completions/min_length": 471.4,
+      "completions/min_terminated_length": 471.4,
+      "epoch": 0.14,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.09375127404928207,
+      "learning_rate": 2e-05,
+      "loss": 0.0049,
+      "num_tokens": 400283.0,
+      "reward": 0.5572499990463257,
+      "reward_std": 0.1743679016828537,
+      "rewards/reward_RULER/mean": 0.5572499990463257,
+      "rewards/reward_RULER/std": 0.17436790391802787,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 70
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 918.6,
+      "completions/max_terminated_length": 918.6,
+      "completions/mean_length": 813.2,
+      "completions/mean_terminated_length": 813.2,
+      "completions/min_length": 702.6,
+      "completions/min_terminated_length": 702.6,
+      "epoch": 0.15,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.0945519357919693,
+      "learning_rate": 2e-05,
+      "loss": -0.0095,
+      "num_tokens": 435299.0,
+      "reward": 0.556124997138977,
+      "reward_std": 0.16700446270406247,
+      "rewards/reward_RULER/mean": 0.556124997138977,
+      "rewards/reward_RULER/std": 0.1670044705271721,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 75
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 663.4,
+      "completions/max_terminated_length": 663.4,
+      "completions/mean_length": 547.4,
+      "completions/mean_terminated_length": 547.4,
+      "completions/min_length": 448.2,
+      "completions/min_terminated_length": 448.2,
+      "epoch": 0.16,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.07022809982299805,
+      "learning_rate": 2e-05,
+      "loss": -0.0113,
+      "num_tokens": 459531.0,
+      "reward": 0.5712500035762786,
+      "reward_std": 0.14846770018339156,
+      "rewards/reward_RULER/mean": 0.5712500035762786,
+      "rewards/reward_RULER/std": 0.14846770316362382,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 80
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 836.8,
+      "completions/max_terminated_length": 836.8,
+      "completions/mean_length": 698.55,
+      "completions/mean_terminated_length": 698.55,
+      "completions/min_length": 566.4,
+      "completions/min_terminated_length": 566.4,
+      "epoch": 0.17,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.04778388887643814,
+      "learning_rate": 2e-05,
+      "loss": -0.0051,
+      "num_tokens": 489793.0,
+      "reward": 0.4829999953508377,
+      "reward_std": 0.15985746309161186,
+      "rewards/reward_RULER/mean": 0.4829999953508377,
+      "rewards/reward_RULER/std": 0.1598574735224247,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 85
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 714.2,
+      "completions/max_terminated_length": 714.2,
+      "completions/mean_length": 619.025,
+      "completions/mean_terminated_length": 619.025,
+      "completions/min_length": 491.6,
+      "completions/min_terminated_length": 491.6,
+      "epoch": 0.18,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.1008564755320549,
+      "learning_rate": 2e-05,
+      "loss": -0.0276,
+      "num_tokens": 517498.0,
+      "reward": 0.6216249942779541,
+      "reward_std": 0.15076738223433495,
+      "rewards/reward_RULER/mean": 0.6216249942779541,
+      "rewards/reward_RULER/std": 0.15076739713549614,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 90
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.025,
+      "completions/max_length": 1427.6,
+      "completions/max_terminated_length": 1427.0,
+      "completions/mean_length": 1197.925,
+      "completions/mean_terminated_length": 1191.521435546875,
+      "completions/min_length": 1005.0,
+      "completions/min_terminated_length": 1005.0,
+      "epoch": 0.19,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.028887949883937836,
+      "learning_rate": 2e-05,
+      "loss": -0.0034,
+      "num_tokens": 567743.0,
+      "reward": 0.4914999961853027,
+      "reward_std": 0.2115367479622364,
+      "rewards/reward_RULER/mean": 0.4914999961853027,
+      "rewards/reward_RULER/std": 0.21153675839304925,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 95
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 788.0,
+      "completions/max_terminated_length": 788.0,
+      "completions/mean_length": 668.3,
+      "completions/mean_terminated_length": 668.3,
+      "completions/min_length": 565.2,
+      "completions/min_terminated_length": 565.2,
+      "epoch": 0.2,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.028161412104964256,
+      "learning_rate": 2e-05,
+      "loss": -0.0153,
+      "num_tokens": 597411.0,
+      "reward": 0.5952500104904175,
+      "reward_std": 0.19533000886440277,
+      "rewards/reward_RULER/mean": 0.5952500104904175,
+      "rewards/reward_RULER/std": 0.19533000737428666,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 100
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 275.6,
+      "completions/max_terminated_length": 275.6,
+      "completions/mean_length": 228.975,
+      "completions/mean_terminated_length": 228.975,
+      "completions/min_length": 187.0,
+      "completions/min_terminated_length": 187.0,
+      "epoch": 0.21,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.11290512979030609,
+      "learning_rate": 2e-05,
+      "loss": -0.0205,
+      "num_tokens": 610706.0,
+      "reward": 0.6417499899864196,
+      "reward_std": 0.16421875953674317,
+      "rewards/reward_RULER/mean": 0.6417499899864196,
+      "rewards/reward_RULER/std": 0.16421877443790436,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 105
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 326.0,
+      "completions/max_terminated_length": 326.0,
+      "completions/mean_length": 270.55,
+      "completions/mean_terminated_length": 270.55,
+      "completions/min_length": 212.6,
+      "completions/min_terminated_length": 212.6,
+      "epoch": 0.22,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.1103404238820076,
+      "learning_rate": 2e-05,
+      "loss": -0.0187,
+      "num_tokens": 625584.0,
+      "reward": 0.7517500042915344,
+      "reward_std": 0.1672534689307213,
+      "rewards/reward_RULER/mean": 0.7517500042915344,
+      "rewards/reward_RULER/std": 0.16725347489118575,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 110
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 517.0,
+      "completions/max_terminated_length": 517.0,
+      "completions/mean_length": 402.475,
+      "completions/mean_terminated_length": 402.475,
+      "completions/min_length": 293.6,
+      "completions/min_terminated_length": 293.6,
+      "epoch": 0.23,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.11264097690582275,
+      "learning_rate": 2e-05,
+      "loss": -0.0225,
+      "num_tokens": 645755.0,
+      "reward": 0.6604750037193299,
+      "reward_std": 0.20599216669797898,
+      "rewards/reward_RULER/mean": 0.6604750037193299,
+      "rewards/reward_RULER/std": 0.2059921696782112,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 115
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 360.4,
+      "completions/max_terminated_length": 360.4,
+      "completions/mean_length": 284.425,
+      "completions/mean_terminated_length": 284.425,
+      "completions/min_length": 205.8,
+      "completions/min_terminated_length": 205.8,
+      "epoch": 0.24,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.12727950513362885,
+      "learning_rate": 2e-05,
+      "loss": 0.0234,
+      "num_tokens": 661252.0,
+      "reward": 0.768750011920929,
+      "reward_std": 0.1357171952724457,
+      "rewards/reward_RULER/mean": 0.768750011920929,
+      "rewards/reward_RULER/std": 0.1357172027230263,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 120
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 515.4,
+      "completions/max_terminated_length": 515.4,
+      "completions/mean_length": 387.825,
+      "completions/mean_terminated_length": 387.825,
+      "completions/min_length": 283.0,
+      "completions/min_terminated_length": 283.0,
+      "epoch": 0.25,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.14301519095897675,
+      "learning_rate": 2e-05,
+      "loss": -0.0407,
+      "num_tokens": 680845.0,
+      "reward": 0.7815000057220459,
+      "reward_std": 0.14280348569154738,
+      "rewards/reward_RULER/mean": 0.7815000057220459,
+      "rewards/reward_RULER/std": 0.14280349388718605,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 125
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 364.4,
+      "completions/max_terminated_length": 364.4,
+      "completions/mean_length": 282.725,
+      "completions/mean_terminated_length": 282.725,
+      "completions/min_length": 214.4,
+      "completions/min_terminated_length": 214.4,
+      "epoch": 0.26,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.17479407787322998,
+      "learning_rate": 2e-05,
+      "loss": 0.015,
+      "num_tokens": 696266.0,
+      "reward": 0.7152499914169311,
+      "reward_std": 0.17013568431138992,
+      "rewards/reward_RULER/mean": 0.7152499914169311,
+      "rewards/reward_RULER/std": 0.17013569176197052,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 130
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 357.6,
+      "completions/max_terminated_length": 357.6,
+      "completions/mean_length": 292.525,
+      "completions/mean_terminated_length": 292.525,
+      "completions/min_length": 224.6,
+      "completions/min_terminated_length": 224.6,
+      "epoch": 0.27,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.09733476489782333,
+      "learning_rate": 2e-05,
+      "loss": -0.0231,
+      "num_tokens": 712055.0,
+      "reward": 0.7517499685287475,
+      "reward_std": 0.13246890008449555,
+      "rewards/reward_RULER/mean": 0.7517499685287475,
+      "rewards/reward_RULER/std": 0.13246890008449555,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 135
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 370.4,
+      "completions/max_terminated_length": 370.4,
+      "completions/mean_length": 304.275,
+      "completions/mean_terminated_length": 304.275,
+      "completions/min_length": 213.6,
+      "completions/min_terminated_length": 213.6,
+      "epoch": 0.28,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.12624062597751617,
+      "learning_rate": 2e-05,
+      "loss": -0.0389,
+      "num_tokens": 728314.0,
+      "reward": 0.6374999850988388,
+      "reward_std": 0.13343365490436554,
+      "rewards/reward_RULER/mean": 0.6374999850988388,
+      "rewards/reward_RULER/std": 0.13343365341424943,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 140
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 395.0,
+      "completions/max_terminated_length": 395.0,
+      "completions/mean_length": 317.75,
+      "completions/mean_terminated_length": 317.75,
+      "completions/min_length": 234.0,
+      "completions/min_terminated_length": 234.0,
+      "epoch": 0.29,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.1336814910173416,
+      "learning_rate": 2e-05,
+      "loss": 0.014,
+      "num_tokens": 745048.0,
+      "reward": 0.6405000209808349,
+      "reward_std": 0.14023895263671876,
+      "rewards/reward_RULER/mean": 0.6405000209808349,
+      "rewards/reward_RULER/std": 0.1402389571070671,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 145
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 551.0,
+      "completions/max_terminated_length": 551.0,
+      "completions/mean_length": 414.05,
+      "completions/mean_terminated_length": 414.05,
+      "completions/min_length": 315.0,
+      "completions/min_terminated_length": 315.0,
+      "epoch": 0.3,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.08828690648078918,
+      "learning_rate": 2e-05,
+      "loss": -0.0075,
+      "num_tokens": 765682.0,
+      "reward": 0.7235000133514404,
+      "reward_std": 0.15303127020597457,
+      "rewards/reward_RULER/mean": 0.7235000133514404,
+      "rewards/reward_RULER/std": 0.15303127393126487,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 150
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 419.0,
+      "completions/max_terminated_length": 419.0,
+      "completions/mean_length": 331.5,
+      "completions/mean_terminated_length": 331.5,
+      "completions/min_length": 241.8,
+      "completions/min_terminated_length": 241.8,
+      "epoch": 0.31,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.12572863698005676,
+      "learning_rate": 2e-05,
+      "loss": -0.0197,
+      "num_tokens": 782950.0,
+      "reward": 0.7467499852180481,
+      "reward_std": 0.15639701783657073,
+      "rewards/reward_RULER/mean": 0.7467499852180481,
+      "rewards/reward_RULER/std": 0.1563970223069191,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 155
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 432.0,
+      "completions/max_terminated_length": 432.0,
+      "completions/mean_length": 366.025,
+      "completions/mean_terminated_length": 366.025,
+      "completions/min_length": 309.4,
+      "completions/min_terminated_length": 309.4,
+      "epoch": 0.32,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.12306974083185196,
+      "learning_rate": 2e-05,
+      "loss": -0.0051,
+      "num_tokens": 801663.0,
+      "reward": 0.7870000123977661,
+      "reward_std": 0.12626811489462852,
+      "rewards/reward_RULER/mean": 0.7870000123977661,
+      "rewards/reward_RULER/std": 0.12626812011003494,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 160
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 374.6,
+      "completions/max_terminated_length": 374.6,
+      "completions/mean_length": 304.025,
+      "completions/mean_terminated_length": 304.025,
+      "completions/min_length": 236.4,
+      "completions/min_terminated_length": 236.4,
+      "epoch": 0.33,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.19156494736671448,
+      "learning_rate": 2e-05,
+      "loss": 0.0153,
+      "num_tokens": 817808.0,
+      "reward": 0.6104999870061875,
+      "reward_std": 0.16314917653799058,
+      "rewards/reward_RULER/mean": 0.6104999870061875,
+      "rewards/reward_RULER/std": 0.16314918100833892,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 165
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 511.2,
+      "completions/max_terminated_length": 511.2,
+      "completions/mean_length": 412.325,
+      "completions/mean_terminated_length": 412.325,
+      "completions/min_length": 319.4,
+      "completions/min_terminated_length": 319.4,
+      "epoch": 0.34,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.1806570142507553,
+      "learning_rate": 2e-05,
+      "loss": -0.0202,
+      "num_tokens": 838341.0,
+      "reward": 0.6715000152587891,
+      "reward_std": 0.16131220310926436,
+      "rewards/reward_RULER/mean": 0.6715000152587891,
+      "rewards/reward_RULER/std": 0.16131220683455466,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 170
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 450.8,
+      "completions/max_terminated_length": 450.8,
+      "completions/mean_length": 360.35,
+      "completions/mean_terminated_length": 360.35,
+      "completions/min_length": 249.0,
+      "completions/min_terminated_length": 249.0,
+      "epoch": 0.35,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.14046546816825867,
+      "learning_rate": 2e-05,
+      "loss": -0.0193,
+      "num_tokens": 856771.0,
+      "reward": 0.7407499790191651,
+      "reward_std": 0.16155299097299575,
+      "rewards/reward_RULER/mean": 0.7407499790191651,
+      "rewards/reward_RULER/std": 0.16155299693346023,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 175
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 485.4,
+      "completions/max_terminated_length": 485.4,
+      "completions/mean_length": 369.475,
+      "completions/mean_terminated_length": 369.475,
+      "completions/min_length": 298.8,
+      "completions/min_terminated_length": 298.8,
+      "epoch": 0.36,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.14084741473197937,
+      "learning_rate": 2e-05,
+      "loss": -0.0483,
+      "num_tokens": 875542.0,
+      "reward": 0.6868499994277955,
+      "reward_std": 0.17129535526037215,
+      "rewards/reward_RULER/mean": 0.6868499994277955,
+      "rewards/reward_RULER/std": 0.17129535228013992,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 180
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 502.6,
+      "completions/max_terminated_length": 502.6,
+      "completions/mean_length": 416.725,
+      "completions/mean_terminated_length": 416.725,
+      "completions/min_length": 326.0,
+      "completions/min_terminated_length": 326.0,
+      "epoch": 0.37,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.2026904821395874,
+      "learning_rate": 2e-05,
+      "loss": 0.0153,
+      "num_tokens": 896227.0,
+      "reward": 0.6887499690055847,
+      "reward_std": 0.1969500035047531,
+      "rewards/reward_RULER/mean": 0.6887499690055847,
+      "rewards/reward_RULER/std": 0.1969500094652176,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 185
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 347.2,
+      "completions/max_terminated_length": 347.2,
+      "completions/mean_length": 297.35,
+      "completions/mean_terminated_length": 297.35,
+      "completions/min_length": 249.2,
+      "completions/min_terminated_length": 249.2,
+      "epoch": 0.38,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.2090216875076294,
+      "learning_rate": 2e-05,
+      "loss": -0.0256,
+      "num_tokens": 912153.0,
+      "reward": 0.7637499928474426,
+      "reward_std": 0.14750646501779557,
+      "rewards/reward_RULER/mean": 0.7637499928474426,
+      "rewards/reward_RULER/std": 0.14750647246837617,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 190
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 545.0,
+      "completions/max_terminated_length": 545.0,
+      "completions/mean_length": 414.175,
+      "completions/mean_terminated_length": 414.175,
+      "completions/min_length": 323.6,
+      "completions/min_terminated_length": 323.6,
+      "epoch": 0.39,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.23068451881408691,
+      "learning_rate": 2e-05,
+      "loss": -0.0065,
+      "num_tokens": 932760.0,
+      "reward": 0.7175000011920929,
+      "reward_std": 0.16009989976882935,
+      "rewards/reward_RULER/mean": 0.7175000011920929,
+      "rewards/reward_RULER/std": 0.16009990274906158,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 195
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 548.6,
+      "completions/max_terminated_length": 548.6,
+      "completions/mean_length": 395.775,
+      "completions/mean_terminated_length": 395.775,
+      "completions/min_length": 288.2,
+      "completions/min_terminated_length": 288.2,
+      "epoch": 0.4,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.16630429029464722,
+      "learning_rate": 2e-05,
+      "loss": -0.0111,
+      "num_tokens": 952655.0,
+      "reward": 0.6835000038146972,
+      "reward_std": 0.21249832808971406,
+      "rewards/reward_RULER/mean": 0.6835000038146972,
+      "rewards/reward_RULER/std": 0.21249832808971406,
+      "rewards/reward_short/mean": 0.0,
+      "rewards/reward_short/std": 0.0,
+      "step": 200
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 500,
+  "num_input_tokens_seen": 952655,
+  "num_train_epochs": 1,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_checkpoints/checkpoint-200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c509fca5a6c9cf5657a2fdf58d7053a8838a1ec2d2c5a5328347b2fa836eb76
+size 6801

training_checkpoints/checkpoint-250/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen3-14B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3-14B
+- grpo
+- lora
+- 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 0.16.0

training_checkpoints/checkpoint-250/adapter_config.json

@@ -0,0 +1,36 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

training_checkpoints/checkpoint-250/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eaa100fe85b6ae0c4fba02329540d3d945b3f9893edcdb49695b9b82ea20fc8a
+size 83907640