Upload training checkpoints and logs

.gitattributes

@@ -34,3 +34,7 @@ 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-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
+- trl
+- grpo
+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:b89b9081c8fe0fc5dfada67d4f2bfbb1381e751932260a29097cb5cf02289397
+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 sha256:1204afa9cb68f1fc04307d17af0a5bf0c5d67f0e4b57e6a7dd8ce7c4c8df27e0
+size 167907531

training_checkpoints/checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:513e2b0a8cfb9467685aaede7bcc5f442f92531f3f3f940db567d56c38cdb71a
+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 +1,534 @@
+{
+  "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": 507.8,
+      "completions/max_terminated_length": 507.8,
+      "completions/mean_length": 378.025,
+      "completions/mean_terminated_length": 378.025,
+      "completions/min_length": 292.6,
+      "completions/min_terminated_length": 292.6,
+      "epoch": 0.01,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.08369118720293045,
+      "learning_rate": 2e-05,
+      "loss": -0.007,
+      "num_tokens": 19545.0,
+      "reward": 0.7320000112056733,
+      "reward_std": 0.17769398652017115,
+      "rewards/reward_RULER/mean": 0.7320000112056733,
+      "rewards/reward_RULER/std": 0.17769398242235185,
+      "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": 450.8,
+      "completions/max_terminated_length": 450.8,
+      "completions/mean_length": 369.4,
+      "completions/mean_terminated_length": 369.4,
+      "completions/min_length": 289.6,
+      "completions/min_terminated_length": 289.6,
+      "epoch": 0.02,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.07441652566194534,
+      "learning_rate": 2e-05,
+      "loss": -0.038,
+      "num_tokens": 38641.0,
+      "reward": 0.590500009059906,
+      "reward_std": 0.21337827146053315,
+      "rewards/reward_RULER/mean": 0.590500009059906,
+      "rewards/reward_RULER/std": 0.21337826550006866,
+      "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": 570.6,
+      "completions/max_terminated_length": 570.6,
+      "completions/mean_length": 428.15,
+      "completions/mean_terminated_length": 428.15,
+      "completions/min_length": 322.4,
+      "completions/min_terminated_length": 322.4,
+      "epoch": 0.03,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.11733342707157135,
+      "learning_rate": 2e-05,
+      "loss": 0.0153,
+      "num_tokens": 60119.0,
+      "reward": 0.6632500171661377,
+      "reward_std": 0.201286368817091,
+      "rewards/reward_RULER/mean": 0.6632500171661377,
+      "rewards/reward_RULER/std": 0.20128637179732323,
+      "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": 352.8,
+      "completions/max_terminated_length": 352.8,
+      "completions/mean_length": 287.7,
+      "completions/mean_terminated_length": 287.7,
+      "completions/min_length": 211.2,
+      "completions/min_terminated_length": 211.2,
+      "epoch": 0.04,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.08897764980792999,
+      "learning_rate": 2e-05,
+      "loss": -0.0199,
+      "num_tokens": 76035.0,
+      "reward": 0.6102499961853027,
+      "reward_std": 0.21699187457561492,
+      "rewards/reward_RULER/mean": 0.6102499961853027,
+      "rewards/reward_RULER/std": 0.21699187606573106,
+      "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": 399.6,
+      "completions/max_terminated_length": 399.6,
+      "completions/mean_length": 348.525,
+      "completions/mean_terminated_length": 348.525,
+      "completions/min_length": 276.0,
+      "completions/min_terminated_length": 276.0,
+      "epoch": 0.05,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.08986642956733704,
+      "learning_rate": 2e-05,
+      "loss": -0.0047,
+      "num_tokens": 94320.0,
+      "reward": 0.6900000095367431,
+      "reward_std": 0.17352139949798584,
+      "rewards/reward_RULER/mean": 0.6900000095367431,
+      "rewards/reward_RULER/std": 0.17352140620350837,
+      "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": 317.2,
+      "completions/max_terminated_length": 317.2,
+      "completions/mean_length": 264.425,
+      "completions/mean_terminated_length": 264.425,
+      "completions/min_length": 218.0,
+      "completions/min_terminated_length": 218.0,
+      "epoch": 0.06,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.10734544694423676,
+      "learning_rate": 2e-05,
+      "loss": -0.0192,
+      "num_tokens": 109321.0,
+      "reward": 0.6507499814033508,
+      "reward_std": 0.2275388702750206,
+      "rewards/reward_RULER/mean": 0.6507499814033508,
+      "rewards/reward_RULER/std": 0.22753888070583345,
+      "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": 341.6,
+      "completions/max_terminated_length": 341.6,
+      "completions/mean_length": 282.1,
+      "completions/mean_terminated_length": 282.1,
+      "completions/min_length": 215.0,
+      "completions/min_terminated_length": 215.0,
+      "epoch": 0.07,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.10805181413888931,
+      "learning_rate": 2e-05,
+      "loss": -0.0201,
+      "num_tokens": 124981.0,
+      "reward": 0.8084999680519104,
+      "reward_std": 0.09627426490187645,
+      "rewards/reward_RULER/mean": 0.8084999680519104,
+      "rewards/reward_RULER/std": 0.09627425670623779,
+      "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": 402.0,
+      "completions/max_terminated_length": 402.0,
+      "completions/mean_length": 320.85,
+      "completions/mean_terminated_length": 320.85,
+      "completions/min_length": 247.6,
+      "completions/min_terminated_length": 247.6,
+      "epoch": 0.08,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.10829323530197144,
+      "learning_rate": 2e-05,
+      "loss": -0.0568,
+      "num_tokens": 142191.0,
+      "reward": 0.4919999957084656,
+      "reward_std": 0.28483160138130187,
+      "rewards/reward_RULER/mean": 0.4919999957084656,
+      "rewards/reward_RULER/std": 0.2848316073417664,
+      "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": 364.8,
+      "completions/max_terminated_length": 364.8,
+      "completions/mean_length": 306.425,
+      "completions/mean_terminated_length": 306.425,
+      "completions/min_length": 256.2,
+      "completions/min_terminated_length": 256.2,
+      "epoch": 0.09,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.11349724978208542,
+      "learning_rate": 2e-05,
+      "loss": -0.0199,
+      "num_tokens": 158856.0,
+      "reward": 0.840499997138977,
+      "reward_std": 0.10326243191957474,
+      "rewards/reward_RULER/mean": 0.840499997138977,
+      "rewards/reward_RULER/std": 0.10326242446899414,
+      "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": 487.6,
+      "completions/max_terminated_length": 487.6,
+      "completions/mean_length": 372.0,
+      "completions/mean_terminated_length": 372.0,
+      "completions/min_length": 292.8,
+      "completions/min_terminated_length": 292.8,
+      "epoch": 0.1,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.08077746629714966,
+      "learning_rate": 2e-05,
+      "loss": -0.046,
+      "num_tokens": 178128.0,
+      "reward": 0.6640000164508819,
+      "reward_std": 0.19458874613046645,
+      "rewards/reward_RULER/mean": 0.6640000164508819,
+      "rewards/reward_RULER/std": 0.19458874836564063,
+      "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": 458.6,
+      "completions/max_terminated_length": 458.6,
+      "completions/mean_length": 356.975,
+      "completions/mean_terminated_length": 356.975,
+      "completions/min_length": 248.6,
+      "completions/min_terminated_length": 248.6,
+      "epoch": 0.11,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.1471513956785202,
+      "learning_rate": 2e-05,
+      "loss": -0.007,
+      "num_tokens": 196759.0,
+      "reward": 0.692000025510788,
+      "reward_std": 0.15977548956871032,
+      "rewards/reward_RULER/mean": 0.692000025510788,
+      "rewards/reward_RULER/std": 0.1597754918038845,
+      "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": 390.6,
+      "completions/max_terminated_length": 390.6,
+      "completions/mean_length": 319.35,
+      "completions/mean_terminated_length": 319.35,
+      "completions/min_length": 260.4,
+      "completions/min_terminated_length": 260.4,
+      "epoch": 0.12,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.11460787057876587,
+      "learning_rate": 2e-05,
+      "loss": -0.0132,
+      "num_tokens": 213893.0,
+      "reward": 0.5780000209808349,
+      "reward_std": 0.22899727523326874,
+      "rewards/reward_RULER/mean": 0.5780000209808349,
+      "rewards/reward_RULER/std": 0.22899727821350097,
+      "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": 412.2,
+      "completions/max_terminated_length": 412.2,
+      "completions/mean_length": 335.425,
+      "completions/mean_terminated_length": 335.425,
+      "completions/min_length": 258.8,
+      "completions/min_terminated_length": 258.8,
+      "epoch": 0.13,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.14172637462615967,
+      "learning_rate": 2e-05,
+      "loss": 0.0509,
+      "num_tokens": 231726.0,
+      "reward": 0.6589999973773957,
+      "reward_std": 0.2158222407102585,
+      "rewards/reward_RULER/mean": 0.6589999973773957,
+      "rewards/reward_RULER/std": 0.2158222481608391,
+      "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": 462.6,
+      "completions/max_terminated_length": 462.6,
+      "completions/mean_length": 356.325,
+      "completions/mean_terminated_length": 356.325,
+      "completions/min_length": 263.4,
+      "completions/min_terminated_length": 263.4,
+      "epoch": 0.14,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.09136804193258286,
+      "learning_rate": 2e-05,
+      "loss": -0.0243,
+      "num_tokens": 250419.0,
+      "reward": 0.8337499976158143,
+      "reward_std": 0.09814090728759765,
+      "rewards/reward_RULER/mean": 0.8337499976158143,
+      "rewards/reward_RULER/std": 0.09814090579748154,
+      "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": 592.2,
+      "completions/max_terminated_length": 592.2,
+      "completions/mean_length": 437.95,
+      "completions/mean_terminated_length": 437.95,
+      "completions/min_length": 318.0,
+      "completions/min_terminated_length": 318.0,
+      "epoch": 0.15,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.13334737718105316,
+      "learning_rate": 2e-05,
+      "loss": -0.0707,
+      "num_tokens": 272457.0,
+      "reward": 0.8289999961853027,
+      "reward_std": 0.09495665803551674,
+      "rewards/reward_RULER/mean": 0.8289999961853027,
+      "rewards/reward_RULER/std": 0.09495665058493614,
+      "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": 511.4,
+      "completions/max_terminated_length": 511.4,
+      "completions/mean_length": 399.4,
+      "completions/mean_terminated_length": 399.4,
+      "completions/min_length": 304.2,
+      "completions/min_terminated_length": 304.2,
+      "epoch": 0.16,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.12988491356372833,
+      "learning_rate": 2e-05,
+      "loss": -0.0288,
+      "num_tokens": 292801.0,
+      "reward": 0.7097499966621399,
+      "reward_std": 0.1876833036541939,
+      "rewards/reward_RULER/mean": 0.7097499966621399,
+      "rewards/reward_RULER/std": 0.1876833200454712,
+      "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": 502.6,
+      "completions/max_terminated_length": 502.6,
+      "completions/mean_length": 406.075,
+      "completions/mean_terminated_length": 406.075,
+      "completions/min_length": 307.2,
+      "completions/min_terminated_length": 307.2,
+      "epoch": 0.17,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.08936081826686859,
+      "learning_rate": 2e-05,
+      "loss": -0.0246,
+      "num_tokens": 313420.0,
+      "reward": 0.7280499935150146,
+      "reward_std": 0.16731963455677032,
+      "rewards/reward_RULER/mean": 0.7280499935150146,
+      "rewards/reward_RULER/std": 0.1673196241259575,
+      "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": 519.8,
+      "completions/max_terminated_length": 519.8,
+      "completions/mean_length": 409.4,
+      "completions/mean_terminated_length": 409.4,
+      "completions/min_length": 316.4,
+      "completions/min_terminated_length": 316.4,
+      "epoch": 0.18,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.13966774940490723,
+      "learning_rate": 2e-05,
+      "loss": 0.0079,
+      "num_tokens": 334212.0,
+      "reward": 0.6485000014305115,
+      "reward_std": 0.2173968069255352,
+      "rewards/reward_RULER/mean": 0.6485000014305115,
+      "rewards/reward_RULER/std": 0.21739680990576743,
+      "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": 0.0,
+      "completions/max_length": 648.0,
+      "completions/max_terminated_length": 648.0,
+      "completions/mean_length": 453.55,
+      "completions/mean_terminated_length": 453.55,
+      "completions/min_length": 353.4,
+      "completions/min_terminated_length": 353.4,
+      "epoch": 0.19,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.0977742075920105,
+      "learning_rate": 2e-05,
+      "loss": -0.0614,
+      "num_tokens": 356746.0,
+      "reward": 0.7827499985694886,
+      "reward_std": 0.12635422199964524,
+      "rewards/reward_RULER/mean": 0.7827499985694886,
+      "rewards/reward_RULER/std": 0.12635422348976136,
+      "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": 442.8,
+      "completions/max_terminated_length": 442.8,
+      "completions/mean_length": 358.375,
+      "completions/mean_terminated_length": 358.375,
+      "completions/min_length": 256.4,
+      "completions/min_terminated_length": 256.4,
+      "epoch": 0.2,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.15935246646404266,
+      "learning_rate": 2e-05,
+      "loss": -0.0441,
+      "num_tokens": 375489.0,
+      "reward": 0.7475000023841858,
+      "reward_std": 0.16528161987662315,
+      "rewards/reward_RULER/mean": 0.7475000023841858,
+      "rewards/reward_RULER/std": 0.16528161764144897,
+      "step": 100
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 500,
+  "num_input_tokens_seen": 375489,
+  "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:af65584c0ca1ceaadf5d407daec36734fd88f9cf7bf23e3101b628c0fd6cfd9d
+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 sha256:95249979db363e80f41fc30001b67ef7aac577cb4aa656c7fa69043e282bff49
+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 sha256:982d88d6756f5a83885af7382b30aef3d0b007baa7e357b7147bbc59575291b2
+size 167907531

training_checkpoints/checkpoint-150/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:979326b10fab93d114136709c7db74aa99baa6b002103c579ac1a76d66de959a
+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 +1,784 @@
+{
+  "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": 507.8,
+      "completions/max_terminated_length": 507.8,
+      "completions/mean_length": 378.025,
+      "completions/mean_terminated_length": 378.025,
+      "completions/min_length": 292.6,
+      "completions/min_terminated_length": 292.6,
+      "epoch": 0.01,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.08369118720293045,
+      "learning_rate": 2e-05,
+      "loss": -0.007,
+      "num_tokens": 19545.0,
+      "reward": 0.7320000112056733,
+      "reward_std": 0.17769398652017115,
+      "rewards/reward_RULER/mean": 0.7320000112056733,
+      "rewards/reward_RULER/std": 0.17769398242235185,
+      "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": 450.8,
+      "completions/max_terminated_length": 450.8,
+      "completions/mean_length": 369.4,
+      "completions/mean_terminated_length": 369.4,
+      "completions/min_length": 289.6,
+      "completions/min_terminated_length": 289.6,
+      "epoch": 0.02,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.07441652566194534,
+      "learning_rate": 2e-05,
+      "loss": -0.038,
+      "num_tokens": 38641.0,
+      "reward": 0.590500009059906,
+      "reward_std": 0.21337827146053315,
+      "rewards/reward_RULER/mean": 0.590500009059906,
+      "rewards/reward_RULER/std": 0.21337826550006866,
+      "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": 570.6,
+      "completions/max_terminated_length": 570.6,
+      "completions/mean_length": 428.15,
+      "completions/mean_terminated_length": 428.15,
+      "completions/min_length": 322.4,
+      "completions/min_terminated_length": 322.4,
+      "epoch": 0.03,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.11733342707157135,
+      "learning_rate": 2e-05,
+      "loss": 0.0153,
+      "num_tokens": 60119.0,
+      "reward": 0.6632500171661377,
+      "reward_std": 0.201286368817091,
+      "rewards/reward_RULER/mean": 0.6632500171661377,
+      "rewards/reward_RULER/std": 0.20128637179732323,
+      "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": 352.8,
+      "completions/max_terminated_length": 352.8,
+      "completions/mean_length": 287.7,
+      "completions/mean_terminated_length": 287.7,
+      "completions/min_length": 211.2,
+      "completions/min_terminated_length": 211.2,
+      "epoch": 0.04,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.08897764980792999,
+      "learning_rate": 2e-05,
+      "loss": -0.0199,
+      "num_tokens": 76035.0,
+      "reward": 0.6102499961853027,
+      "reward_std": 0.21699187457561492,
+      "rewards/reward_RULER/mean": 0.6102499961853027,
+      "rewards/reward_RULER/std": 0.21699187606573106,
+      "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": 399.6,
+      "completions/max_terminated_length": 399.6,
+      "completions/mean_length": 348.525,
+      "completions/mean_terminated_length": 348.525,
+      "completions/min_length": 276.0,
+      "completions/min_terminated_length": 276.0,
+      "epoch": 0.05,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.08986642956733704,
+      "learning_rate": 2e-05,
+      "loss": -0.0047,
+      "num_tokens": 94320.0,
+      "reward": 0.6900000095367431,
+      "reward_std": 0.17352139949798584,
+      "rewards/reward_RULER/mean": 0.6900000095367431,
+      "rewards/reward_RULER/std": 0.17352140620350837,
+      "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": 317.2,
+      "completions/max_terminated_length": 317.2,
+      "completions/mean_length": 264.425,
+      "completions/mean_terminated_length": 264.425,
+      "completions/min_length": 218.0,
+      "completions/min_terminated_length": 218.0,
+      "epoch": 0.06,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.10734544694423676,
+      "learning_rate": 2e-05,
+      "loss": -0.0192,
+      "num_tokens": 109321.0,
+      "reward": 0.6507499814033508,
+      "reward_std": 0.2275388702750206,
+      "rewards/reward_RULER/mean": 0.6507499814033508,
+      "rewards/reward_RULER/std": 0.22753888070583345,
+      "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": 341.6,
+      "completions/max_terminated_length": 341.6,
+      "completions/mean_length": 282.1,
+      "completions/mean_terminated_length": 282.1,
+      "completions/min_length": 215.0,
+      "completions/min_terminated_length": 215.0,
+      "epoch": 0.07,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.10805181413888931,
+      "learning_rate": 2e-05,
+      "loss": -0.0201,
+      "num_tokens": 124981.0,
+      "reward": 0.8084999680519104,
+      "reward_std": 0.09627426490187645,
+      "rewards/reward_RULER/mean": 0.8084999680519104,
+      "rewards/reward_RULER/std": 0.09627425670623779,
+      "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": 402.0,
+      "completions/max_terminated_length": 402.0,
+      "completions/mean_length": 320.85,
+      "completions/mean_terminated_length": 320.85,
+      "completions/min_length": 247.6,
+      "completions/min_terminated_length": 247.6,
+      "epoch": 0.08,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.10829323530197144,
+      "learning_rate": 2e-05,
+      "loss": -0.0568,
+      "num_tokens": 142191.0,
+      "reward": 0.4919999957084656,
+      "reward_std": 0.28483160138130187,
+      "rewards/reward_RULER/mean": 0.4919999957084656,
+      "rewards/reward_RULER/std": 0.2848316073417664,
+      "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": 364.8,
+      "completions/max_terminated_length": 364.8,
+      "completions/mean_length": 306.425,
+      "completions/mean_terminated_length": 306.425,
+      "completions/min_length": 256.2,
+      "completions/min_terminated_length": 256.2,
+      "epoch": 0.09,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.11349724978208542,
+      "learning_rate": 2e-05,
+      "loss": -0.0199,
+      "num_tokens": 158856.0,
+      "reward": 0.840499997138977,
+      "reward_std": 0.10326243191957474,
+      "rewards/reward_RULER/mean": 0.840499997138977,
+      "rewards/reward_RULER/std": 0.10326242446899414,
+      "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": 487.6,
+      "completions/max_terminated_length": 487.6,
+      "completions/mean_length": 372.0,
+      "completions/mean_terminated_length": 372.0,
+      "completions/min_length": 292.8,
+      "completions/min_terminated_length": 292.8,
+      "epoch": 0.1,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.08077746629714966,
+      "learning_rate": 2e-05,
+      "loss": -0.046,
+      "num_tokens": 178128.0,
+      "reward": 0.6640000164508819,
+      "reward_std": 0.19458874613046645,
+      "rewards/reward_RULER/mean": 0.6640000164508819,
+      "rewards/reward_RULER/std": 0.19458874836564063,
+      "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": 458.6,
+      "completions/max_terminated_length": 458.6,
+      "completions/mean_length": 356.975,
+      "completions/mean_terminated_length": 356.975,
+      "completions/min_length": 248.6,
+      "completions/min_terminated_length": 248.6,
+      "epoch": 0.11,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.1471513956785202,
+      "learning_rate": 2e-05,
+      "loss": -0.007,
+      "num_tokens": 196759.0,
+      "reward": 0.692000025510788,
+      "reward_std": 0.15977548956871032,
+      "rewards/reward_RULER/mean": 0.692000025510788,
+      "rewards/reward_RULER/std": 0.1597754918038845,
+      "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": 390.6,
+      "completions/max_terminated_length": 390.6,
+      "completions/mean_length": 319.35,
+      "completions/mean_terminated_length": 319.35,
+      "completions/min_length": 260.4,
+      "completions/min_terminated_length": 260.4,
+      "epoch": 0.12,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.11460787057876587,
+      "learning_rate": 2e-05,
+      "loss": -0.0132,
+      "num_tokens": 213893.0,
+      "reward": 0.5780000209808349,
+      "reward_std": 0.22899727523326874,
+      "rewards/reward_RULER/mean": 0.5780000209808349,
+      "rewards/reward_RULER/std": 0.22899727821350097,
+      "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": 412.2,
+      "completions/max_terminated_length": 412.2,
+      "completions/mean_length": 335.425,
+      "completions/mean_terminated_length": 335.425,
+      "completions/min_length": 258.8,
+      "completions/min_terminated_length": 258.8,
+      "epoch": 0.13,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.14172637462615967,
+      "learning_rate": 2e-05,
+      "loss": 0.0509,
+      "num_tokens": 231726.0,
+      "reward": 0.6589999973773957,
+      "reward_std": 0.2158222407102585,
+      "rewards/reward_RULER/mean": 0.6589999973773957,
+      "rewards/reward_RULER/std": 0.2158222481608391,
+      "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": 462.6,
+      "completions/max_terminated_length": 462.6,
+      "completions/mean_length": 356.325,
+      "completions/mean_terminated_length": 356.325,
+      "completions/min_length": 263.4,
+      "completions/min_terminated_length": 263.4,
+      "epoch": 0.14,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.09136804193258286,
+      "learning_rate": 2e-05,
+      "loss": -0.0243,
+      "num_tokens": 250419.0,
+      "reward": 0.8337499976158143,
+      "reward_std": 0.09814090728759765,
+      "rewards/reward_RULER/mean": 0.8337499976158143,
+      "rewards/reward_RULER/std": 0.09814090579748154,
+      "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": 592.2,
+      "completions/max_terminated_length": 592.2,
+      "completions/mean_length": 437.95,
+      "completions/mean_terminated_length": 437.95,
+      "completions/min_length": 318.0,
+      "completions/min_terminated_length": 318.0,
+      "epoch": 0.15,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.13334737718105316,
+      "learning_rate": 2e-05,
+      "loss": -0.0707,
+      "num_tokens": 272457.0,
+      "reward": 0.8289999961853027,
+      "reward_std": 0.09495665803551674,
+      "rewards/reward_RULER/mean": 0.8289999961853027,
+      "rewards/reward_RULER/std": 0.09495665058493614,
+      "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": 511.4,
+      "completions/max_terminated_length": 511.4,
+      "completions/mean_length": 399.4,
+      "completions/mean_terminated_length": 399.4,
+      "completions/min_length": 304.2,
+      "completions/min_terminated_length": 304.2,
+      "epoch": 0.16,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.12988491356372833,
+      "learning_rate": 2e-05,
+      "loss": -0.0288,
+      "num_tokens": 292801.0,
+      "reward": 0.7097499966621399,
+      "reward_std": 0.1876833036541939,
+      "rewards/reward_RULER/mean": 0.7097499966621399,
+      "rewards/reward_RULER/std": 0.1876833200454712,
+      "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": 502.6,
+      "completions/max_terminated_length": 502.6,
+      "completions/mean_length": 406.075,
+      "completions/mean_terminated_length": 406.075,
+      "completions/min_length": 307.2,
+      "completions/min_terminated_length": 307.2,
+      "epoch": 0.17,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.08936081826686859,
+      "learning_rate": 2e-05,
+      "loss": -0.0246,
+      "num_tokens": 313420.0,
+      "reward": 0.7280499935150146,
+      "reward_std": 0.16731963455677032,
+      "rewards/reward_RULER/mean": 0.7280499935150146,
+      "rewards/reward_RULER/std": 0.1673196241259575,
+      "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": 519.8,
+      "completions/max_terminated_length": 519.8,
+      "completions/mean_length": 409.4,
+      "completions/mean_terminated_length": 409.4,
+      "completions/min_length": 316.4,
+      "completions/min_terminated_length": 316.4,
+      "epoch": 0.18,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.13966774940490723,
+      "learning_rate": 2e-05,
+      "loss": 0.0079,
+      "num_tokens": 334212.0,
+      "reward": 0.6485000014305115,
+      "reward_std": 0.2173968069255352,
+      "rewards/reward_RULER/mean": 0.6485000014305115,
+      "rewards/reward_RULER/std": 0.21739680990576743,
+      "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": 0.0,
+      "completions/max_length": 648.0,
+      "completions/max_terminated_length": 648.0,
+      "completions/mean_length": 453.55,
+      "completions/mean_terminated_length": 453.55,
+      "completions/min_length": 353.4,
+      "completions/min_terminated_length": 353.4,
+      "epoch": 0.19,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.0977742075920105,
+      "learning_rate": 2e-05,
+      "loss": -0.0614,
+      "num_tokens": 356746.0,
+      "reward": 0.7827499985694886,
+      "reward_std": 0.12635422199964524,
+      "rewards/reward_RULER/mean": 0.7827499985694886,
+      "rewards/reward_RULER/std": 0.12635422348976136,
+      "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": 442.8,
+      "completions/max_terminated_length": 442.8,
+      "completions/mean_length": 358.375,
+      "completions/mean_terminated_length": 358.375,
+      "completions/min_length": 256.4,
+      "completions/min_terminated_length": 256.4,
+      "epoch": 0.2,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.15935246646404266,
+      "learning_rate": 2e-05,
+      "loss": -0.0441,
+      "num_tokens": 375489.0,
+      "reward": 0.7475000023841858,
+      "reward_std": 0.16528161987662315,
+      "rewards/reward_RULER/mean": 0.7475000023841858,
+      "rewards/reward_RULER/std": 0.16528161764144897,
+      "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": 588.6,
+      "completions/max_terminated_length": 588.6,
+      "completions/mean_length": 452.175,
+      "completions/mean_terminated_length": 452.175,
+      "completions/min_length": 344.6,
+      "completions/min_terminated_length": 344.6,
+      "epoch": 0.21,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.1050405278801918,
+      "learning_rate": 2e-05,
+      "loss": 0.0209,
+      "num_tokens": 398008.0,
+      "reward": 0.8627500057220459,
+      "reward_std": 0.08394425511360168,
+      "rewards/reward_RULER/mean": 0.8627500057220459,
+      "rewards/reward_RULER/std": 0.08394426107406616,
+      "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": 520.0,
+      "completions/max_terminated_length": 520.0,
+      "completions/mean_length": 450.15,
+      "completions/mean_terminated_length": 450.15,
+      "completions/min_length": 352.0,
+      "completions/min_terminated_length": 352.0,
+      "epoch": 0.22,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.1688801646232605,
+      "learning_rate": 2e-05,
+      "loss": -0.0058,
+      "num_tokens": 420382.0,
+      "reward": 0.7672500133514404,
+      "reward_std": 0.14555928111076355,
+      "rewards/reward_RULER/mean": 0.7672500133514404,
+      "rewards/reward_RULER/std": 0.14555927962064744,
+      "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": 517.2,
+      "completions/max_terminated_length": 517.2,
+      "completions/mean_length": 420.9,
+      "completions/mean_terminated_length": 420.9,
+      "completions/min_length": 336.6,
+      "completions/min_terminated_length": 336.6,
+      "epoch": 0.23,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.1674422323703766,
+      "learning_rate": 2e-05,
+      "loss": -0.0319,
+      "num_tokens": 441626.0,
+      "reward": 0.8227499961853028,
+      "reward_std": 0.11988024711608887,
+      "rewards/reward_RULER/mean": 0.8227499961853028,
+      "rewards/reward_RULER/std": 0.11988024786114693,
+      "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": 544.8,
+      "completions/max_terminated_length": 544.8,
+      "completions/mean_length": 451.1,
+      "completions/mean_terminated_length": 451.1,
+      "completions/min_length": 379.2,
+      "completions/min_terminated_length": 379.2,
+      "epoch": 0.24,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.18309253454208374,
+      "learning_rate": 2e-05,
+      "loss": -0.0356,
+      "num_tokens": 464110.0,
+      "reward": 0.6797500014305115,
+      "reward_std": 0.20434648618102075,
+      "rewards/reward_RULER/mean": 0.6797500014305115,
+      "rewards/reward_RULER/std": 0.20434649735689164,
+      "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": 594.6,
+      "completions/max_terminated_length": 594.6,
+      "completions/mean_length": 495.2,
+      "completions/mean_terminated_length": 495.2,
+      "completions/min_length": 408.4,
+      "completions/min_terminated_length": 408.4,
+      "epoch": 0.25,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.09583492577075958,
+      "learning_rate": 2e-05,
+      "loss": -0.0062,
+      "num_tokens": 488326.0,
+      "reward": 0.8042499899864197,
+      "reward_std": 0.11632050797343255,
+      "rewards/reward_RULER/mean": 0.8042499899864197,
+      "rewards/reward_RULER/std": 0.11632050722837448,
+      "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": 725.8,
+      "completions/max_terminated_length": 725.8,
+      "completions/mean_length": 521.125,
+      "completions/mean_terminated_length": 521.125,
+      "completions/min_length": 417.8,
+      "completions/min_terminated_length": 417.8,
+      "epoch": 0.26,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.10735133290290833,
+      "learning_rate": 2e-05,
+      "loss": -0.0069,
+      "num_tokens": 513595.0,
+      "reward": 0.7964999794960022,
+      "reward_std": 0.13472943678498267,
+      "rewards/reward_RULER/mean": 0.7964999794960022,
+      "rewards/reward_RULER/std": 0.13472944796085357,
+      "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": 668.6,
+      "completions/max_terminated_length": 668.6,
+      "completions/mean_length": 571.25,
+      "completions/mean_terminated_length": 571.25,
+      "completions/min_length": 476.8,
+      "completions/min_terminated_length": 476.8,
+      "epoch": 0.27,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.19455848634243011,
+      "learning_rate": 2e-05,
+      "loss": -0.0151,
+      "num_tokens": 540845.0,
+      "reward": 0.8171249985694885,
+      "reward_std": 0.12673728540539742,
+      "rewards/reward_RULER/mean": 0.8171249985694885,
+      "rewards/reward_RULER/std": 0.12673727795481682,
+      "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": 720.4,
+      "completions/max_terminated_length": 720.4,
+      "completions/mean_length": 550.225,
+      "completions/mean_terminated_length": 550.225,
+      "completions/min_length": 439.4,
+      "completions/min_terminated_length": 439.4,
+      "epoch": 0.28,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.15606646239757538,
+      "learning_rate": 2e-05,
+      "loss": -0.0383,
+      "num_tokens": 567254.0,
+      "reward": 0.850249993801117,
+      "reward_std": 0.086809141933918,
+      "rewards/reward_RULER/mean": 0.850249993801117,
+      "rewards/reward_RULER/std": 0.08680914118885993,
+      "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": 692.4,
+      "completions/max_terminated_length": 692.4,
+      "completions/mean_length": 537.75,
+      "completions/mean_terminated_length": 537.75,
+      "completions/min_length": 408.2,
+      "completions/min_terminated_length": 408.2,
+      "epoch": 0.29,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.17972718179225922,
+      "learning_rate": 2e-05,
+      "loss": 0.0376,
+      "num_tokens": 593108.0,
+      "reward": 0.7572499871253967,
+      "reward_std": 0.14755067527294158,
+      "rewards/reward_RULER/mean": 0.7572499871253967,
+      "rewards/reward_RULER/std": 0.14755066782236098,
+      "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": 749.8,
+      "completions/max_terminated_length": 749.8,
+      "completions/mean_length": 634.55,
+      "completions/mean_terminated_length": 634.55,
+      "completions/min_length": 501.8,
+      "completions/min_terminated_length": 501.8,
+      "epoch": 0.3,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.15824082493782043,
+      "learning_rate": 2e-05,
+      "loss": 0.0078,
+      "num_tokens": 622890.0,
+      "reward": 0.751499992609024,
+      "reward_std": 0.12705863565206527,
+      "rewards/reward_RULER/mean": 0.751499992609024,
+      "rewards/reward_RULER/std": 0.12705863639712334,
+      "step": 150
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 500,
+  "num_input_tokens_seen": 622890,
+  "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:af65584c0ca1ceaadf5d407daec36734fd88f9cf7bf23e3101b628c0fd6cfd9d
+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 sha256:4a1575b0c626e28675942d9e0ea7a71c434ee2417d03059fbdb4a95da6e007c9
+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:bc11bcd6af81615ffbbdefccf7952c8779502fe767b7d8860164bfc38a1832d7
+size 167907531

training_checkpoints/checkpoint-200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b1588b0cf950bdc55b4d9739bd92638b2bc9581c908f1bb6a8f2cae0c0a2a2b
+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 +1,1034 @@
+{
+  "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": 507.8,
+      "completions/max_terminated_length": 507.8,
+      "completions/mean_length": 378.025,
+      "completions/mean_terminated_length": 378.025,
+      "completions/min_length": 292.6,
+      "completions/min_terminated_length": 292.6,
+      "epoch": 0.01,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.08369118720293045,
+      "learning_rate": 2e-05,
+      "loss": -0.007,
+      "num_tokens": 19545.0,
+      "reward": 0.7320000112056733,
+      "reward_std": 0.17769398652017115,
+      "rewards/reward_RULER/mean": 0.7320000112056733,
+      "rewards/reward_RULER/std": 0.17769398242235185,
+      "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": 450.8,
+      "completions/max_terminated_length": 450.8,
+      "completions/mean_length": 369.4,
+      "completions/mean_terminated_length": 369.4,
+      "completions/min_length": 289.6,
+      "completions/min_terminated_length": 289.6,
+      "epoch": 0.02,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.07441652566194534,
+      "learning_rate": 2e-05,
+      "loss": -0.038,
+      "num_tokens": 38641.0,
+      "reward": 0.590500009059906,
+      "reward_std": 0.21337827146053315,
+      "rewards/reward_RULER/mean": 0.590500009059906,
+      "rewards/reward_RULER/std": 0.21337826550006866,
+      "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": 570.6,
+      "completions/max_terminated_length": 570.6,
+      "completions/mean_length": 428.15,
+      "completions/mean_terminated_length": 428.15,
+      "completions/min_length": 322.4,
+      "completions/min_terminated_length": 322.4,
+      "epoch": 0.03,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.11733342707157135,
+      "learning_rate": 2e-05,
+      "loss": 0.0153,
+      "num_tokens": 60119.0,
+      "reward": 0.6632500171661377,
+      "reward_std": 0.201286368817091,
+      "rewards/reward_RULER/mean": 0.6632500171661377,
+      "rewards/reward_RULER/std": 0.20128637179732323,
+      "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": 352.8,
+      "completions/max_terminated_length": 352.8,
+      "completions/mean_length": 287.7,
+      "completions/mean_terminated_length": 287.7,
+      "completions/min_length": 211.2,
+      "completions/min_terminated_length": 211.2,
+      "epoch": 0.04,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.08897764980792999,
+      "learning_rate": 2e-05,
+      "loss": -0.0199,
+      "num_tokens": 76035.0,
+      "reward": 0.6102499961853027,
+      "reward_std": 0.21699187457561492,
+      "rewards/reward_RULER/mean": 0.6102499961853027,
+      "rewards/reward_RULER/std": 0.21699187606573106,
+      "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": 399.6,
+      "completions/max_terminated_length": 399.6,
+      "completions/mean_length": 348.525,
+      "completions/mean_terminated_length": 348.525,
+      "completions/min_length": 276.0,
+      "completions/min_terminated_length": 276.0,
+      "epoch": 0.05,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.08986642956733704,
+      "learning_rate": 2e-05,
+      "loss": -0.0047,
+      "num_tokens": 94320.0,
+      "reward": 0.6900000095367431,
+      "reward_std": 0.17352139949798584,
+      "rewards/reward_RULER/mean": 0.6900000095367431,
+      "rewards/reward_RULER/std": 0.17352140620350837,
+      "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": 317.2,
+      "completions/max_terminated_length": 317.2,
+      "completions/mean_length": 264.425,
+      "completions/mean_terminated_length": 264.425,
+      "completions/min_length": 218.0,
+      "completions/min_terminated_length": 218.0,
+      "epoch": 0.06,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.10734544694423676,
+      "learning_rate": 2e-05,
+      "loss": -0.0192,
+      "num_tokens": 109321.0,
+      "reward": 0.6507499814033508,
+      "reward_std": 0.2275388702750206,
+      "rewards/reward_RULER/mean": 0.6507499814033508,
+      "rewards/reward_RULER/std": 0.22753888070583345,
+      "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": 341.6,
+      "completions/max_terminated_length": 341.6,
+      "completions/mean_length": 282.1,
+      "completions/mean_terminated_length": 282.1,
+      "completions/min_length": 215.0,
+      "completions/min_terminated_length": 215.0,
+      "epoch": 0.07,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.10805181413888931,
+      "learning_rate": 2e-05,
+      "loss": -0.0201,
+      "num_tokens": 124981.0,
+      "reward": 0.8084999680519104,
+      "reward_std": 0.09627426490187645,
+      "rewards/reward_RULER/mean": 0.8084999680519104,
+      "rewards/reward_RULER/std": 0.09627425670623779,
+      "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": 402.0,
+      "completions/max_terminated_length": 402.0,
+      "completions/mean_length": 320.85,
+      "completions/mean_terminated_length": 320.85,
+      "completions/min_length": 247.6,
+      "completions/min_terminated_length": 247.6,
+      "epoch": 0.08,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.10829323530197144,
+      "learning_rate": 2e-05,
+      "loss": -0.0568,
+      "num_tokens": 142191.0,
+      "reward": 0.4919999957084656,
+      "reward_std": 0.28483160138130187,
+      "rewards/reward_RULER/mean": 0.4919999957084656,
+      "rewards/reward_RULER/std": 0.2848316073417664,
+      "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": 364.8,
+      "completions/max_terminated_length": 364.8,
+      "completions/mean_length": 306.425,
+      "completions/mean_terminated_length": 306.425,
+      "completions/min_length": 256.2,
+      "completions/min_terminated_length": 256.2,
+      "epoch": 0.09,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.11349724978208542,
+      "learning_rate": 2e-05,
+      "loss": -0.0199,
+      "num_tokens": 158856.0,
+      "reward": 0.840499997138977,
+      "reward_std": 0.10326243191957474,
+      "rewards/reward_RULER/mean": 0.840499997138977,
+      "rewards/reward_RULER/std": 0.10326242446899414,
+      "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": 487.6,
+      "completions/max_terminated_length": 487.6,
+      "completions/mean_length": 372.0,
+      "completions/mean_terminated_length": 372.0,
+      "completions/min_length": 292.8,
+      "completions/min_terminated_length": 292.8,
+      "epoch": 0.1,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.08077746629714966,
+      "learning_rate": 2e-05,
+      "loss": -0.046,
+      "num_tokens": 178128.0,
+      "reward": 0.6640000164508819,
+      "reward_std": 0.19458874613046645,
+      "rewards/reward_RULER/mean": 0.6640000164508819,
+      "rewards/reward_RULER/std": 0.19458874836564063,
+      "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": 458.6,
+      "completions/max_terminated_length": 458.6,
+      "completions/mean_length": 356.975,
+      "completions/mean_terminated_length": 356.975,
+      "completions/min_length": 248.6,
+      "completions/min_terminated_length": 248.6,
+      "epoch": 0.11,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.1471513956785202,
+      "learning_rate": 2e-05,
+      "loss": -0.007,
+      "num_tokens": 196759.0,
+      "reward": 0.692000025510788,
+      "reward_std": 0.15977548956871032,
+      "rewards/reward_RULER/mean": 0.692000025510788,
+      "rewards/reward_RULER/std": 0.1597754918038845,
+      "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": 390.6,
+      "completions/max_terminated_length": 390.6,
+      "completions/mean_length": 319.35,
+      "completions/mean_terminated_length": 319.35,
+      "completions/min_length": 260.4,
+      "completions/min_terminated_length": 260.4,
+      "epoch": 0.12,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.11460787057876587,
+      "learning_rate": 2e-05,
+      "loss": -0.0132,
+      "num_tokens": 213893.0,
+      "reward": 0.5780000209808349,
+      "reward_std": 0.22899727523326874,
+      "rewards/reward_RULER/mean": 0.5780000209808349,
+      "rewards/reward_RULER/std": 0.22899727821350097,
+      "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": 412.2,
+      "completions/max_terminated_length": 412.2,
+      "completions/mean_length": 335.425,
+      "completions/mean_terminated_length": 335.425,
+      "completions/min_length": 258.8,
+      "completions/min_terminated_length": 258.8,
+      "epoch": 0.13,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.14172637462615967,
+      "learning_rate": 2e-05,
+      "loss": 0.0509,
+      "num_tokens": 231726.0,
+      "reward": 0.6589999973773957,
+      "reward_std": 0.2158222407102585,
+      "rewards/reward_RULER/mean": 0.6589999973773957,
+      "rewards/reward_RULER/std": 0.2158222481608391,
+      "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": 462.6,
+      "completions/max_terminated_length": 462.6,
+      "completions/mean_length": 356.325,
+      "completions/mean_terminated_length": 356.325,
+      "completions/min_length": 263.4,
+      "completions/min_terminated_length": 263.4,
+      "epoch": 0.14,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.09136804193258286,
+      "learning_rate": 2e-05,
+      "loss": -0.0243,
+      "num_tokens": 250419.0,
+      "reward": 0.8337499976158143,
+      "reward_std": 0.09814090728759765,
+      "rewards/reward_RULER/mean": 0.8337499976158143,
+      "rewards/reward_RULER/std": 0.09814090579748154,
+      "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": 592.2,
+      "completions/max_terminated_length": 592.2,
+      "completions/mean_length": 437.95,
+      "completions/mean_terminated_length": 437.95,
+      "completions/min_length": 318.0,
+      "completions/min_terminated_length": 318.0,
+      "epoch": 0.15,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.13334737718105316,
+      "learning_rate": 2e-05,
+      "loss": -0.0707,
+      "num_tokens": 272457.0,
+      "reward": 0.8289999961853027,
+      "reward_std": 0.09495665803551674,
+      "rewards/reward_RULER/mean": 0.8289999961853027,
+      "rewards/reward_RULER/std": 0.09495665058493614,
+      "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": 511.4,
+      "completions/max_terminated_length": 511.4,
+      "completions/mean_length": 399.4,
+      "completions/mean_terminated_length": 399.4,
+      "completions/min_length": 304.2,
+      "completions/min_terminated_length": 304.2,
+      "epoch": 0.16,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.12988491356372833,
+      "learning_rate": 2e-05,
+      "loss": -0.0288,
+      "num_tokens": 292801.0,
+      "reward": 0.7097499966621399,
+      "reward_std": 0.1876833036541939,
+      "rewards/reward_RULER/mean": 0.7097499966621399,
+      "rewards/reward_RULER/std": 0.1876833200454712,
+      "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": 502.6,
+      "completions/max_terminated_length": 502.6,
+      "completions/mean_length": 406.075,
+      "completions/mean_terminated_length": 406.075,
+      "completions/min_length": 307.2,
+      "completions/min_terminated_length": 307.2,
+      "epoch": 0.17,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.08936081826686859,
+      "learning_rate": 2e-05,
+      "loss": -0.0246,
+      "num_tokens": 313420.0,
+      "reward": 0.7280499935150146,
+      "reward_std": 0.16731963455677032,
+      "rewards/reward_RULER/mean": 0.7280499935150146,
+      "rewards/reward_RULER/std": 0.1673196241259575,
+      "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": 519.8,
+      "completions/max_terminated_length": 519.8,
+      "completions/mean_length": 409.4,
+      "completions/mean_terminated_length": 409.4,
+      "completions/min_length": 316.4,
+      "completions/min_terminated_length": 316.4,
+      "epoch": 0.18,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.13966774940490723,
+      "learning_rate": 2e-05,
+      "loss": 0.0079,
+      "num_tokens": 334212.0,
+      "reward": 0.6485000014305115,
+      "reward_std": 0.2173968069255352,
+      "rewards/reward_RULER/mean": 0.6485000014305115,
+      "rewards/reward_RULER/std": 0.21739680990576743,
+      "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": 0.0,
+      "completions/max_length": 648.0,
+      "completions/max_terminated_length": 648.0,
+      "completions/mean_length": 453.55,
+      "completions/mean_terminated_length": 453.55,
+      "completions/min_length": 353.4,
+      "completions/min_terminated_length": 353.4,
+      "epoch": 0.19,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.0977742075920105,
+      "learning_rate": 2e-05,
+      "loss": -0.0614,
+      "num_tokens": 356746.0,
+      "reward": 0.7827499985694886,
+      "reward_std": 0.12635422199964524,
+      "rewards/reward_RULER/mean": 0.7827499985694886,
+      "rewards/reward_RULER/std": 0.12635422348976136,
+      "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": 442.8,
+      "completions/max_terminated_length": 442.8,
+      "completions/mean_length": 358.375,
+      "completions/mean_terminated_length": 358.375,
+      "completions/min_length": 256.4,
+      "completions/min_terminated_length": 256.4,
+      "epoch": 0.2,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.15935246646404266,
+      "learning_rate": 2e-05,
+      "loss": -0.0441,
+      "num_tokens": 375489.0,
+      "reward": 0.7475000023841858,
+      "reward_std": 0.16528161987662315,
+      "rewards/reward_RULER/mean": 0.7475000023841858,
+      "rewards/reward_RULER/std": 0.16528161764144897,
+      "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": 588.6,
+      "completions/max_terminated_length": 588.6,
+      "completions/mean_length": 452.175,
+      "completions/mean_terminated_length": 452.175,
+      "completions/min_length": 344.6,
+      "completions/min_terminated_length": 344.6,
+      "epoch": 0.21,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.1050405278801918,
+      "learning_rate": 2e-05,
+      "loss": 0.0209,
+      "num_tokens": 398008.0,
+      "reward": 0.8627500057220459,
+      "reward_std": 0.08394425511360168,
+      "rewards/reward_RULER/mean": 0.8627500057220459,
+      "rewards/reward_RULER/std": 0.08394426107406616,
+      "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": 520.0,
+      "completions/max_terminated_length": 520.0,
+      "completions/mean_length": 450.15,
+      "completions/mean_terminated_length": 450.15,
+      "completions/min_length": 352.0,
+      "completions/min_terminated_length": 352.0,
+      "epoch": 0.22,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.1688801646232605,
+      "learning_rate": 2e-05,
+      "loss": -0.0058,
+      "num_tokens": 420382.0,
+      "reward": 0.7672500133514404,
+      "reward_std": 0.14555928111076355,
+      "rewards/reward_RULER/mean": 0.7672500133514404,
+      "rewards/reward_RULER/std": 0.14555927962064744,
+      "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": 517.2,
+      "completions/max_terminated_length": 517.2,
+      "completions/mean_length": 420.9,
+      "completions/mean_terminated_length": 420.9,
+      "completions/min_length": 336.6,
+      "completions/min_terminated_length": 336.6,
+      "epoch": 0.23,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.1674422323703766,
+      "learning_rate": 2e-05,
+      "loss": -0.0319,
+      "num_tokens": 441626.0,
+      "reward": 0.8227499961853028,
+      "reward_std": 0.11988024711608887,
+      "rewards/reward_RULER/mean": 0.8227499961853028,
+      "rewards/reward_RULER/std": 0.11988024786114693,
+      "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": 544.8,
+      "completions/max_terminated_length": 544.8,
+      "completions/mean_length": 451.1,
+      "completions/mean_terminated_length": 451.1,
+      "completions/min_length": 379.2,
+      "completions/min_terminated_length": 379.2,
+      "epoch": 0.24,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.18309253454208374,
+      "learning_rate": 2e-05,
+      "loss": -0.0356,
+      "num_tokens": 464110.0,
+      "reward": 0.6797500014305115,
+      "reward_std": 0.20434648618102075,
+      "rewards/reward_RULER/mean": 0.6797500014305115,
+      "rewards/reward_RULER/std": 0.20434649735689164,
+      "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": 594.6,
+      "completions/max_terminated_length": 594.6,
+      "completions/mean_length": 495.2,
+      "completions/mean_terminated_length": 495.2,
+      "completions/min_length": 408.4,
+      "completions/min_terminated_length": 408.4,
+      "epoch": 0.25,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.09583492577075958,
+      "learning_rate": 2e-05,
+      "loss": -0.0062,
+      "num_tokens": 488326.0,
+      "reward": 0.8042499899864197,
+      "reward_std": 0.11632050797343255,
+      "rewards/reward_RULER/mean": 0.8042499899864197,
+      "rewards/reward_RULER/std": 0.11632050722837448,
+      "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": 725.8,
+      "completions/max_terminated_length": 725.8,
+      "completions/mean_length": 521.125,
+      "completions/mean_terminated_length": 521.125,
+      "completions/min_length": 417.8,
+      "completions/min_terminated_length": 417.8,
+      "epoch": 0.26,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.10735133290290833,
+      "learning_rate": 2e-05,
+      "loss": -0.0069,
+      "num_tokens": 513595.0,
+      "reward": 0.7964999794960022,
+      "reward_std": 0.13472943678498267,
+      "rewards/reward_RULER/mean": 0.7964999794960022,
+      "rewards/reward_RULER/std": 0.13472944796085357,
+      "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": 668.6,
+      "completions/max_terminated_length": 668.6,
+      "completions/mean_length": 571.25,
+      "completions/mean_terminated_length": 571.25,
+      "completions/min_length": 476.8,
+      "completions/min_terminated_length": 476.8,
+      "epoch": 0.27,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.19455848634243011,
+      "learning_rate": 2e-05,
+      "loss": -0.0151,
+      "num_tokens": 540845.0,
+      "reward": 0.8171249985694885,
+      "reward_std": 0.12673728540539742,
+      "rewards/reward_RULER/mean": 0.8171249985694885,
+      "rewards/reward_RULER/std": 0.12673727795481682,
+      "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": 720.4,
+      "completions/max_terminated_length": 720.4,
+      "completions/mean_length": 550.225,
+      "completions/mean_terminated_length": 550.225,
+      "completions/min_length": 439.4,
+      "completions/min_terminated_length": 439.4,
+      "epoch": 0.28,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.15606646239757538,
+      "learning_rate": 2e-05,
+      "loss": -0.0383,
+      "num_tokens": 567254.0,
+      "reward": 0.850249993801117,
+      "reward_std": 0.086809141933918,
+      "rewards/reward_RULER/mean": 0.850249993801117,
+      "rewards/reward_RULER/std": 0.08680914118885993,
+      "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": 692.4,
+      "completions/max_terminated_length": 692.4,
+      "completions/mean_length": 537.75,
+      "completions/mean_terminated_length": 537.75,
+      "completions/min_length": 408.2,
+      "completions/min_terminated_length": 408.2,
+      "epoch": 0.29,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.17972718179225922,
+      "learning_rate": 2e-05,
+      "loss": 0.0376,
+      "num_tokens": 593108.0,
+      "reward": 0.7572499871253967,
+      "reward_std": 0.14755067527294158,
+      "rewards/reward_RULER/mean": 0.7572499871253967,
+      "rewards/reward_RULER/std": 0.14755066782236098,
+      "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": 749.8,
+      "completions/max_terminated_length": 749.8,
+      "completions/mean_length": 634.55,
+      "completions/mean_terminated_length": 634.55,
+      "completions/min_length": 501.8,
+      "completions/min_terminated_length": 501.8,
+      "epoch": 0.3,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.15824082493782043,
+      "learning_rate": 2e-05,
+      "loss": 0.0078,
+      "num_tokens": 622890.0,
+      "reward": 0.751499992609024,
+      "reward_std": 0.12705863565206527,
+      "rewards/reward_RULER/mean": 0.751499992609024,
+      "rewards/reward_RULER/std": 0.12705863639712334,
+      "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": 723.4,
+      "completions/max_terminated_length": 723.4,
+      "completions/mean_length": 554.85,
+      "completions/mean_terminated_length": 554.85,
+      "completions/min_length": 431.6,
+      "completions/min_terminated_length": 431.6,
+      "epoch": 0.31,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.15994799137115479,
+      "learning_rate": 2e-05,
+      "loss": -0.0153,
+      "num_tokens": 649412.0,
+      "reward": 0.8667500019073486,
+      "reward_std": 0.08592485263943672,
+      "rewards/reward_RULER/mean": 0.8667500019073486,
+      "rewards/reward_RULER/std": 0.08592485114932061,
+      "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": 741.0,
+      "completions/max_terminated_length": 741.0,
+      "completions/mean_length": 623.15,
+      "completions/mean_terminated_length": 623.15,
+      "completions/min_length": 488.6,
+      "completions/min_terminated_length": 488.6,
+      "epoch": 0.32,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.1006745919585228,
+      "learning_rate": 2e-05,
+      "loss": -0.0423,
+      "num_tokens": 678730.0,
+      "reward": 0.8098500013351441,
+      "reward_std": 0.12717877328395844,
+      "rewards/reward_RULER/mean": 0.8098500013351441,
+      "rewards/reward_RULER/std": 0.1271787852048874,
+      "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": 843.0,
+      "completions/max_terminated_length": 843.0,
+      "completions/mean_length": 667.125,
+      "completions/mean_terminated_length": 667.125,
+      "completions/min_length": 533.8,
+      "completions/min_terminated_length": 533.8,
+      "epoch": 0.33,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.1787230223417282,
+      "learning_rate": 2e-05,
+      "loss": -0.0314,
+      "num_tokens": 709711.0,
+      "reward": 0.8775000214576721,
+      "reward_std": 0.05196457579731941,
+      "rewards/reward_RULER/mean": 0.8775000214576721,
+      "rewards/reward_RULER/std": 0.05196457803249359,
+      "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": 884.2,
+      "completions/max_terminated_length": 884.2,
+      "completions/mean_length": 744.2,
+      "completions/mean_terminated_length": 744.2,
+      "completions/min_length": 619.2,
+      "completions/min_terminated_length": 619.2,
+      "epoch": 0.34,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.12575370073318481,
+      "learning_rate": 2e-05,
+      "loss": -0.0316,
+      "num_tokens": 743839.0,
+      "reward": 0.7491249918937684,
+      "reward_std": 0.15893839821219444,
+      "rewards/reward_RULER/mean": 0.7491249918937684,
+      "rewards/reward_RULER/std": 0.15893840193748474,
+      "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": 947.6,
+      "completions/max_terminated_length": 947.6,
+      "completions/mean_length": 719.25,
+      "completions/mean_terminated_length": 719.25,
+      "completions/min_length": 557.2,
+      "completions/min_terminated_length": 557.2,
+      "epoch": 0.35,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.14867401123046875,
+      "learning_rate": 2e-05,
+      "loss": -0.0638,
+      "num_tokens": 776953.0,
+      "reward": 0.7017499923706054,
+      "reward_std": 0.18066229447722434,
+      "rewards/reward_RULER/mean": 0.7017499923706054,
+      "rewards/reward_RULER/std": 0.1806623049080372,
+      "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": 788.2,
+      "completions/max_terminated_length": 788.2,
+      "completions/mean_length": 660.025,
+      "completions/mean_terminated_length": 660.025,
+      "completions/min_length": 543.6,
+      "completions/min_terminated_length": 543.6,
+      "epoch": 0.36,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.16206932067871094,
+      "learning_rate": 2e-05,
+      "loss": -0.0251,
+      "num_tokens": 807666.0,
+      "reward": 0.7729999899864197,
+      "reward_std": 0.14922719374299048,
+      "rewards/reward_RULER/mean": 0.7729999899864197,
+      "rewards/reward_RULER/std": 0.14922720938920975,
+      "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": 992.2,
+      "completions/max_terminated_length": 992.2,
+      "completions/mean_length": 761.05,
+      "completions/mean_terminated_length": 761.05,
+      "completions/min_length": 593.2,
+      "completions/min_terminated_length": 593.2,
+      "epoch": 0.37,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.15697941184043884,
+      "learning_rate": 2e-05,
+      "loss": 0.0131,
+      "num_tokens": 842444.0,
+      "reward": 0.8725000023841858,
+      "reward_std": 0.08397083282470703,
+      "rewards/reward_RULER/mean": 0.8725000023841858,
+      "rewards/reward_RULER/std": 0.08397082295268773,
+      "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": 1032.6,
+      "completions/max_terminated_length": 1032.6,
+      "completions/mean_length": 800.2,
+      "completions/mean_terminated_length": 800.2,
+      "completions/min_length": 617.2,
+      "completions/min_terminated_length": 617.2,
+      "epoch": 0.38,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.1354055255651474,
+      "learning_rate": 2e-05,
+      "loss": -0.0065,
+      "num_tokens": 878788.0,
+      "reward": 0.6302499890327453,
+      "reward_std": 0.22836896628141404,
+      "rewards/reward_RULER/mean": 0.6302499890327453,
+      "rewards/reward_RULER/std": 0.22836897671222686,
+      "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": 928.8,
+      "completions/max_terminated_length": 928.8,
+      "completions/mean_length": 767.375,
+      "completions/mean_terminated_length": 767.375,
+      "completions/min_length": 637.0,
+      "completions/min_terminated_length": 637.0,
+      "epoch": 0.39,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.1156788021326065,
+      "learning_rate": 2e-05,
+      "loss": -0.0209,
+      "num_tokens": 913851.0,
+      "reward": 0.7934999942779541,
+      "reward_std": 0.12420440688729287,
+      "rewards/reward_RULER/mean": 0.7934999942779541,
+      "rewards/reward_RULER/std": 0.12420440539717674,
+      "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": 1105.6,
+      "completions/max_terminated_length": 1105.6,
+      "completions/mean_length": 902.275,
+      "completions/mean_terminated_length": 902.275,
+      "completions/min_length": 727.6,
+      "completions/min_terminated_length": 727.6,
+      "epoch": 0.4,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.14207735657691956,
+      "learning_rate": 2e-05,
+      "loss": -0.0085,
+      "num_tokens": 954318.0,
+      "reward": 0.8785000205039978,
+      "reward_std": 0.07570790350437165,
+      "rewards/reward_RULER/mean": 0.8785000205039978,
+      "rewards/reward_RULER/std": 0.07570790350437165,
+      "step": 200
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 500,
+  "num_input_tokens_seen": 954318,
+  "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:af65584c0ca1ceaadf5d407daec36734fd88f9cf7bf23e3101b628c0fd6cfd9d
+size 6801

training_checkpoints/checkpoint-50/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-50/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-50/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edff927059f359992bdb10ba934554d4bfe04eeeecc42531b5475281c754aca4
+size 83907640