Training in progress, step 50, checkpoint

.gitattributes

@@ -34,3 +34,4 @@ 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
+last-checkpoint/tokenizer.json filter=lfs diff=lfs merge=lfs -text

last-checkpoint/README.md

@@ -0,0 +1,210 @@
+---
+base_model: unsloth/Qwen3-0.6B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/Qwen3-0.6B
+- grpo
+- lora
+- transformers
+- trl
+- unsloth
+---
+
+# 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 0.18.1

last-checkpoint/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen3ForCausalLM",
+    "parent_library": "transformers.models.qwen3.modeling_qwen3",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/Qwen3-0.6B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "gate_proj",
+    "down_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

last-checkpoint/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa8533e82bf2bec9f81ae29b8801f207a0da1e046de76f636beb1ad9a081b2d4
+size 22041968

last-checkpoint/added_tokens.json

@@ -0,0 +1,29 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|PAD_TOKEN|>": 151669,
+  "<|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
+}

last-checkpoint/chat_template.jinja

@@ -0,0 +1,99 @@
+{%- 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 forward_message in messages %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- set message = messages[index] %}
+    {%- set current_content = message.content if message.content is defined and message.content is not none else '' %}
+    {%- set tool_start = '<tool_response>' %}
+    {%- set tool_start_length = tool_start|length %}
+    {%- set start_of_message = current_content[:tool_start_length] %}
+    {%- set tool_end = '</tool_response>' %}
+    {%- set tool_end_length = tool_end|length %}
+    {%- set start_pos = (current_content|length) - tool_end_length %}
+    {%- if start_pos < 0 %}
+        {%- set start_pos = 0 %}
+    {%- endif %}
+    {%- set end_of_message = current_content[start_pos:] %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(start_of_message == tool_start and end_of_message == tool_end) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set m_content = message.content if message.content is defined and message.content is not none else '' %}
+        {%- set content = m_content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in m_content %}
+                {%- set content = (m_content.split('</think>')|last).lstrip('\n') %}
+                {%- set reasoning_content = (m_content.split('</think>')|first).rstrip('\n') %}
+                {%- set reasoning_content = (reasoning_content.split('<think>')|last).lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and (not reasoning_content.strip() == '')) %}
+                {{- '<|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' }}
+        {{- message.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 %}

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:144c69b09322460c548f2c36f00be3211bbae6ad6846a3bfcf1df4a1c65a8528
+size 11381707

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5348cbcd14153e0606c0e8b0f352b381b3c588ed2ce3ae236c53cbb92af59c7
+size 14645

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b20fabeaa911d2351ad5b07df884ddbf3960f28dcaca2e21bbdd697b2a08237
+size 1465

last-checkpoint/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": "<|PAD_TOKEN|>"
+}

last-checkpoint/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10ba4ba91270b1a50e5cd8e51023bccc66fc4ac4909dd7ae7ab29433411c9bb9
+size 11422844

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,248 @@
+{
+  "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
+    },
+    "151669": {
+      "content": "<|PAD_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "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": 40960,
+  "pad_token": "<|PAD_TOKEN|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,1484 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.01220703125,
+  "eval_steps": 500,
+  "global_step": 50,
+  "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,
+      "completion_length": 5.5,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 6.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 5.5,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 5.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 0.000244140625,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 14.921834945678711,
+      "kl": 0.0022894542198628187,
+      "learning_rate": 0.0,
+      "loss": 0.0124,
+      "num_tokens": 226.0,
+      "reward": 0.6000000238418579,
+      "reward_std": 0.5773502588272095,
+      "rewards/reward_correct_answer/mean": 0.5,
+      "rewards/reward_correct_answer/std": 0.5773502588272095,
+      "rewards/reward_strict_format/mean": 0.10000000149011612,
+      "rewards/reward_strict_format/std": 0.0,
+      "step": 1
+    },
+    {
+      "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,
+      "completion_length": 5.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 5.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 5.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 5.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 0.00048828125,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 1.3039941393344634e-07,
+      "kl": 4.7683716530855236e-08,
+      "learning_rate": 3.3333333333333335e-07,
+      "loss": 0.0,
+      "num_tokens": 450.0,
+      "reward": 1.100000023841858,
+      "reward_std": 0.0,
+      "rewards/reward_correct_answer/mean": 1.0,
+      "rewards/reward_correct_answer/std": 0.0,
+      "rewards/reward_strict_format/mean": 0.10000000149011612,
+      "rewards/reward_strict_format/std": 0.0,
+      "step": 2
+    },
+    {
+      "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,
+      "completion_length": 6.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 6.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 6.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 6.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 0.000732421875,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 9.706178083490613e-09,
+      "kl": 0.0,
+      "learning_rate": 6.666666666666667e-07,
+      "loss": 0.0,
+      "num_tokens": 678.0,
+      "reward": 1.100000023841858,
+      "reward_std": 0.0,
+      "rewards/reward_correct_answer/mean": 1.0,
+      "rewards/reward_correct_answer/std": 0.0,
+      "rewards/reward_strict_format/mean": 0.10000000149011612,
+      "rewards/reward_strict_format/std": 0.0,
+      "step": 3
+    },
+    {
+      "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,
+      "completion_length": 6.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 6.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 6.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 6.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 0.0009765625,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 5.125297661834338e-07,
+      "kl": 9.934107936260261e-08,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 0.0,
+      "num_tokens": 906.0,
+      "reward": 1.100000023841858,
+      "reward_std": 0.0,
+      "rewards/reward_correct_answer/mean": 1.0,
+      "rewards/reward_correct_answer/std": 0.0,
+      "rewards/reward_strict_format/mean": 0.10000000149011612,
+      "rewards/reward_strict_format/std": 0.0,
+      "step": 4
+    },
+    {
+      "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,
+      "completion_length": 5.5,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 6.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 5.5,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 5.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 0.001220703125,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 0.010523075237870216,
+      "kl": 0.015575298573821783,
+      "learning_rate": 1.3333333333333334e-06,
+      "loss": 0.0,
+      "num_tokens": 1132.0,
+      "reward": 0.10000000149011612,
+      "reward_std": 0.0,
+      "rewards/reward_correct_answer/mean": 0.0,
+      "rewards/reward_correct_answer/std": 0.0,
+      "rewards/reward_strict_format/mean": 0.10000000149011612,
+      "rewards/reward_strict_format/std": 0.0,
+      "step": 5
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 5.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 5.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 5.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 5.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 0.00146484375,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 0.00014656978601124138,
+      "kl": 3.4856795537052676e-05,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 0.0,
+      "num_tokens": 1356.0,
+      "reward": 1.100000023841858,
+      "reward_std": 0.0,
+      "rewards/reward_correct_answer/mean": 1.0,
+      "rewards/reward_correct_answer/std": 0.0,
+      "rewards/reward_strict_format/mean": 0.10000000149011612,
+      "rewards/reward_strict_format/std": 0.0,
+      "step": 6
+    },
+    {
+      "clip_ratio/high_max": 0.0416666679084301,
+      "clip_ratio/high_mean": 0.0416666679084301,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0416666679084301,
+      "completion_length": 5.25,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 6.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 5.25,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 5.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 0.001708984375,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 5.386456489562988,
+      "kl": 4.109740189051081e-06,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": -0.0144,
+      "num_tokens": 1581.0,
+      "reward": 0.3500000238418579,
+      "reward_std": 0.5,
+      "rewards/reward_correct_answer/mean": 0.25,
+      "rewards/reward_correct_answer/std": 0.5,
+      "rewards/reward_strict_format/mean": 0.10000000149011612,
+      "rewards/reward_strict_format/std": 0.0,
+      "step": 7
+    },
+    {
+      "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,
+      "completion_length": 5.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 5.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 5.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 5.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 0.001953125,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 1.468857835362769e-08,
+      "kl": 0.0,
+      "learning_rate": 2.3333333333333336e-06,
+      "loss": 0.0,
+      "num_tokens": 1805.0,
+      "reward": 1.100000023841858,
+      "reward_std": 0.0,
+      "rewards/reward_correct_answer/mean": 1.0,
+      "rewards/reward_correct_answer/std": 0.0,
+      "rewards/reward_strict_format/mean": 0.10000000149011612,
+      "rewards/reward_strict_format/std": 0.0,
+      "step": 8
+    },
+    {
+      "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,
+      "completion_length": 5.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 5.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 5.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 5.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 0.002197265625,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 2.59349974385259e-07,
+      "kl": 2.3841858265427618e-08,
+      "learning_rate": 2.666666666666667e-06,
+      "loss": 0.0,
+      "num_tokens": 2029.0,
+      "reward": 1.100000023841858,
+      "reward_std": 0.0,
+      "rewards/reward_correct_answer/mean": 1.0,
+      "rewards/reward_correct_answer/std": 0.0,
+      "rewards/reward_strict_format/mean": 0.10000000149011612,
+      "rewards/reward_strict_format/std": 0.0,
+      "step": 9
+    },
+    {
+      "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,
+      "completion_length": 5.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 5.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 5.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 5.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 0.00244140625,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 3.6540299674925336e-08,
+      "kl": 0.0,
+      "learning_rate": 3e-06,
+      "loss": 0.0,
+      "num_tokens": 2253.0,
+      "reward": 0.10000000149011612,
+      "reward_std": 0.0,
+      "rewards/reward_correct_answer/mean": 0.0,
+      "rewards/reward_correct_answer/std": 0.0,
+      "rewards/reward_strict_format/mean": 0.10000000149011612,
+      "rewards/reward_strict_format/std": 0.0,
+      "step": 10
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 5.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 5.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 5.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 5.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 0.002685546875,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 7.61307601351291e-05,
+      "kl": 2.9659271604032256e-05,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.0,
+      "num_tokens": 2477.0,
+      "reward": 0.10000000149011612,
+      "reward_std": 0.0,
+      "rewards/reward_correct_answer/mean": 0.0,
+      "rewards/reward_correct_answer/std": 0.0,
+      "rewards/reward_strict_format/mean": 0.10000000149011612,
+      "rewards/reward_strict_format/std": 0.0,
+      "step": 11
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.05000000074505806,
+      "clip_ratio/low_min": 0.05000000074505806,
+      "clip_ratio/region_mean": 0.05000000074505806,
+      "completion_length": 5.25,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 6.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 5.25,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 5.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 0.0029296875,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 16.935649871826172,
+      "kl": 0.01409353074268438,
+      "learning_rate": 3.6666666666666666e-06,
+      "loss": 0.0094,
+      "num_tokens": 2702.0,
+      "reward": 0.3500000238418579,
+      "reward_std": 0.5,
+      "rewards/reward_correct_answer/mean": 0.25,
+      "rewards/reward_correct_answer/std": 0.5,
+      "rewards/reward_strict_format/mean": 0.10000000149011612,
+      "rewards/reward_strict_format/std": 0.0,
+      "step": 12
+    },
+    {
+      "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,
+      "completion_length": 5.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 5.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 5.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 5.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 0.003173828125,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 14.281251907348633,
+      "kl": 0.0030522526242009462,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": -0.01,
+      "num_tokens": 2926.0,
+      "reward": 0.3500000238418579,
+      "reward_std": 0.5,
+      "rewards/reward_correct_answer/mean": 0.25,
+      "rewards/reward_correct_answer/std": 0.5,
+      "rewards/reward_strict_format/mean": 0.10000000149011612,
+      "rewards/reward_strict_format/std": 0.0,
+      "step": 13
+    },
+    {
+      "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,
+      "completion_length": 5.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 5.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 5.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 5.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 0.00341796875,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 50.099609375,
+      "kl": 0.0012042761372867972,
+      "learning_rate": 4.333333333333334e-06,
+      "loss": -0.0095,
+      "num_tokens": 3150.0,
+      "reward": 0.3500000238418579,
+      "reward_std": 0.5,
+      "rewards/reward_correct_answer/mean": 0.25,
+      "rewards/reward_correct_answer/std": 0.5,
+      "rewards/reward_strict_format/mean": 0.10000000149011612,
+      "rewards/reward_strict_format/std": 0.0,
+      "step": 14
+    },
+    {
+      "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,
+      "completion_length": 5.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 5.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 5.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 5.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 0.003662109375,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 2.7857176974066533e-06,
+      "kl": 2.312660171810421e-06,
+      "learning_rate": 4.666666666666667e-06,
+      "loss": 0.0,
+      "num_tokens": 3374.0,
+      "reward": 1.100000023841858,
+      "reward_std": 0.0,
+      "rewards/reward_correct_answer/mean": 1.0,
+      "rewards/reward_correct_answer/std": 0.0,
+      "rewards/reward_strict_format/mean": 0.10000000149011612,
+      "rewards/reward_strict_format/std": 0.0,
+      "step": 15
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 5.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 5.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 5.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 5.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 0.00390625,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 5.32733288594045e-08,
+      "kl": 0.0,
+      "learning_rate": 5e-06,
+      "loss": 0.0,
+      "num_tokens": 3598.0,
+      "reward": 0.10000000149011612,
+      "reward_std": 0.0,
+      "rewards/reward_correct_answer/mean": 0.0,
+      "rewards/reward_correct_answer/std": 0.0,
+      "rewards/reward_strict_format/mean": 0.10000000149011612,
+      "rewards/reward_strict_format/std": 0.0,
+      "step": 16
+    },
+    {
+      "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,
+      "completion_length": 5.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 5.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 5.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 5.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 0.004150390625,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 19.99111557006836,
+      "kl": 0.00040375592070684974,
+      "learning_rate": 4.962962962962964e-06,
+      "loss": -0.0004,
+      "num_tokens": 3822.0,
+      "reward": 0.8500000238418579,
+      "reward_std": 0.5,
+      "rewards/reward_correct_answer/mean": 0.75,
+      "rewards/reward_correct_answer/std": 0.5,
+      "rewards/reward_strict_format/mean": 0.10000000149011612,
+      "rewards/reward_strict_format/std": 0.0,
+      "step": 17
+    },
+    {
+      "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,
+      "completion_length": 5.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 5.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 5.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 5.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 0.00439453125,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 5.883413223273237e-07,
+      "kl": 1.9073486612342094e-07,
+      "learning_rate": 4.925925925925926e-06,
+      "loss": 0.0,
+      "num_tokens": 4046.0,
+      "reward": 0.10000000149011612,
+      "reward_std": 0.0,
+      "rewards/reward_correct_answer/mean": 0.0,
+      "rewards/reward_correct_answer/std": 0.0,
+      "rewards/reward_strict_format/mean": 0.10000000149011612,
+      "rewards/reward_strict_format/std": 0.0,
+      "step": 18
+    },
+    {
+      "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,
+      "completion_length": 5.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 5.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 5.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 5.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 0.004638671875,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 28.261995315551758,
+      "kl": 0.0028509319527074695,
+      "learning_rate": 4.888888888888889e-06,
+      "loss": -0.0091,
+      "num_tokens": 4270.0,
+      "reward": 0.8500000238418579,
+      "reward_std": 0.5,
+      "rewards/reward_correct_answer/mean": 0.75,
+      "rewards/reward_correct_answer/std": 0.5,
+      "rewards/reward_strict_format/mean": 0.10000000149011612,
+      "rewards/reward_strict_format/std": 0.0,
+      "step": 19
+    },
+    {
+      "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,
+      "completion_length": 5.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 5.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 5.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 5.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 0.0048828125,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 18.498952865600586,
+      "kl": 0.004902535874862224,
+      "learning_rate": 4.851851851851852e-06,
+      "loss": 0.0141,
+      "num_tokens": 4494.0,
+      "reward": 0.3500000238418579,
+      "reward_std": 0.5,
+      "rewards/reward_correct_answer/mean": 0.25,
+      "rewards/reward_correct_answer/std": 0.5,
+      "rewards/reward_strict_format/mean": 0.10000000149011612,
+      "rewards/reward_strict_format/std": 0.0,
+      "step": 20
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 5.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 5.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 5.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 5.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 0.005126953125,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 3.5736948689191195e-07,
+      "kl": 6.914139021318988e-07,
+      "learning_rate": 4.814814814814815e-06,
+      "loss": 0.0,
+      "num_tokens": 4718.0,
+      "reward": 1.100000023841858,
+      "reward_std": 0.0,
+      "rewards/reward_correct_answer/mean": 1.0,
+      "rewards/reward_correct_answer/std": 0.0,
+      "rewards/reward_strict_format/mean": 0.10000000149011612,
+      "rewards/reward_strict_format/std": 0.0,
+      "step": 21
+    },
+    {
+      "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,
+      "completion_length": 6.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 6.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 6.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 6.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 0.00537109375,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 16.31566047668457,
+      "kl": 0.00030950707153465373,
+      "learning_rate": 4.777777777777778e-06,
+      "loss": 0.0086,
+      "num_tokens": 4946.0,
+      "reward": 0.8500000238418579,
+      "reward_std": 0.5,
+      "rewards/reward_correct_answer/mean": 0.75,
+      "rewards/reward_correct_answer/std": 0.5,
+      "rewards/reward_strict_format/mean": 0.10000000149011612,
+      "rewards/reward_strict_format/std": 0.0,
+      "step": 22
+    },
+    {
+      "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,
+      "completion_length": 5.25,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 6.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 5.25,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 5.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 0.005615234375,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 14.193683624267578,
+      "kl": 0.017707511407934362,
+      "learning_rate": 4.7407407407407415e-06,
+      "loss": 0.016,
+      "num_tokens": 5171.0,
+      "reward": 0.3500000238418579,
+      "reward_std": 0.5,
+      "rewards/reward_correct_answer/mean": 0.25,
+      "rewards/reward_correct_answer/std": 0.5,
+      "rewards/reward_strict_format/mean": 0.10000000149011612,
+      "rewards/reward_strict_format/std": 0.0,
+      "step": 23
+    },
+    {
+      "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,
+      "completion_length": 5.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 5.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 5.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 5.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 0.005859375,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 9.459295569058668e-08,
+      "kl": 4.7683716530855236e-08,
+      "learning_rate": 4.703703703703704e-06,
+      "loss": 0.0,
+      "num_tokens": 5395.0,
+      "reward": 1.100000023841858,
+      "reward_std": 0.0,
+      "rewards/reward_correct_answer/mean": 1.0,
+      "rewards/reward_correct_answer/std": 0.0,
+      "rewards/reward_strict_format/mean": 0.10000000149011612,
+      "rewards/reward_strict_format/std": 0.0,
+      "step": 24
+    },
+    {
+      "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,
+      "completion_length": 6.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 6.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 6.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 6.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 0.006103515625,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 1.6522290025022812e-07,
+      "kl": 7.152557373046875e-07,
+      "learning_rate": 4.666666666666667e-06,
+      "loss": 0.0,
+      "num_tokens": 5623.0,
+      "reward": 1.100000023841858,
+      "reward_std": 0.0,
+      "rewards/reward_correct_answer/mean": 1.0,
+      "rewards/reward_correct_answer/std": 0.0,
+      "rewards/reward_strict_format/mean": 0.10000000149011612,
+      "rewards/reward_strict_format/std": 0.0,
+      "step": 25
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 4.5,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 5.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 4.5,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 4.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 0.00634765625,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 0.002149923937395215,
+      "kl": 0.0007016420349827968,
+      "learning_rate": 4.62962962962963e-06,
+      "loss": 0.0,
+      "num_tokens": 5845.0,
+      "reward": 0.10000000149011612,
+      "reward_std": 0.0,
+      "rewards/reward_correct_answer/mean": 0.0,
+      "rewards/reward_correct_answer/std": 0.0,
+      "rewards/reward_strict_format/mean": 0.10000000149011612,
+      "rewards/reward_strict_format/std": 0.0,
+      "step": 26
+    },
+    {
+      "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,
+      "completion_length": 6.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 6.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 6.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 6.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 0.006591796875,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 1.863099328147655e-07,
+      "kl": 1.3709068298339844e-06,
+      "learning_rate": 4.592592592592593e-06,
+      "loss": 0.0,
+      "num_tokens": 6073.0,
+      "reward": 1.100000023841858,
+      "reward_std": 0.0,
+      "rewards/reward_correct_answer/mean": 1.0,
+      "rewards/reward_correct_answer/std": 0.0,
+      "rewards/reward_strict_format/mean": 0.10000000149011612,
+      "rewards/reward_strict_format/std": 0.0,
+      "step": 27
+    },
+    {
+      "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,
+      "completion_length": 6.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 6.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 6.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 6.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 0.0068359375,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 2.7715702799469e-07,
+      "kl": 3.298123829154065e-06,
+      "learning_rate": 4.555555555555556e-06,
+      "loss": 0.0,
+      "num_tokens": 6301.0,
+      "reward": 1.100000023841858,
+      "reward_std": 0.0,
+      "rewards/reward_correct_answer/mean": 1.0,
+      "rewards/reward_correct_answer/std": 0.0,
+      "rewards/reward_strict_format/mean": 0.10000000149011612,
+      "rewards/reward_strict_format/std": 0.0,
+      "step": 28
+    },
+    {
+      "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,
+      "completion_length": 5.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 5.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 5.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 5.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 0.007080078125,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 2.611544687169953e-07,
+      "kl": 2.1457672971791908e-07,
+      "learning_rate": 4.5185185185185185e-06,
+      "loss": 0.0,
+      "num_tokens": 6525.0,
+      "reward": 1.100000023841858,
+      "reward_std": 0.0,
+      "rewards/reward_correct_answer/mean": 1.0,
+      "rewards/reward_correct_answer/std": 0.0,
+      "rewards/reward_strict_format/mean": 0.10000000149011612,
+      "rewards/reward_strict_format/std": 0.0,
+      "step": 29
+    },
+    {
+      "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,
+      "completion_length": 6.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 6.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 6.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 6.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 0.00732421875,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 0.00013428374950308353,
+      "kl": 0.0016269087791442871,
+      "learning_rate": 4.481481481481482e-06,
+      "loss": 0.0,
+      "num_tokens": 6753.0,
+      "reward": 1.100000023841858,
+      "reward_std": 0.0,
+      "rewards/reward_correct_answer/mean": 1.0,
+      "rewards/reward_correct_answer/std": 0.0,
+      "rewards/reward_strict_format/mean": 0.10000000149011612,
+      "rewards/reward_strict_format/std": 0.0,
+      "step": 30
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 5.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 5.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 5.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 5.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 0.007568359375,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 1.0308043783879839e-05,
+      "kl": 7.216930680442601e-05,
+      "learning_rate": 4.444444444444444e-06,
+      "loss": 0.0,
+      "num_tokens": 6977.0,
+      "reward": 1.100000023841858,
+      "reward_std": 0.0,
+      "rewards/reward_correct_answer/mean": 1.0,
+      "rewards/reward_correct_answer/std": 0.0,
+      "rewards/reward_strict_format/mean": 0.10000000149011612,
+      "rewards/reward_strict_format/std": 0.0,
+      "step": 31
+    },
+    {
+      "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,
+      "completion_length": 5.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 5.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 5.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 5.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 0.0078125,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 1.8191285562352277e-06,
+      "kl": 3.886223112203879e-06,
+      "learning_rate": 4.407407407407408e-06,
+      "loss": 0.0,
+      "num_tokens": 7201.0,
+      "reward": 1.100000023841858,
+      "reward_std": 0.0,
+      "rewards/reward_correct_answer/mean": 1.0,
+      "rewards/reward_correct_answer/std": 0.0,
+      "rewards/reward_strict_format/mean": 0.10000000149011612,
+      "rewards/reward_strict_format/std": 0.0,
+      "step": 32
+    },
+    {
+      "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,
+      "completion_length": 5.25,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 6.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 5.25,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 5.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 0.008056640625,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 15.156084060668945,
+      "kl": 0.08206877112388611,
+      "learning_rate": 4.370370370370371e-06,
+      "loss": 0.0273,
+      "num_tokens": 7426.0,
+      "reward": 0.3500000238418579,
+      "reward_std": 0.5,
+      "rewards/reward_correct_answer/mean": 0.25,
+      "rewards/reward_correct_answer/std": 0.5,
+      "rewards/reward_strict_format/mean": 0.10000000149011612,
+      "rewards/reward_strict_format/std": 0.0,
+      "step": 33
+    },
+    {
+      "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,
+      "completion_length": 5.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 5.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 5.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 5.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 0.00830078125,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 0.00010354633559472859,
+      "kl": 0.0035600902047008276,
+      "learning_rate": 4.333333333333334e-06,
+      "loss": 0.0,
+      "num_tokens": 7650.0,
+      "reward": 1.100000023841858,
+      "reward_std": 0.0,
+      "rewards/reward_correct_answer/mean": 1.0,
+      "rewards/reward_correct_answer/std": 0.0,
+      "rewards/reward_strict_format/mean": 0.10000000149011612,
+      "rewards/reward_strict_format/std": 0.0,
+      "step": 34
+    },
+    {
+      "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,
+      "completion_length": 5.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 5.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 5.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 5.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 0.008544921875,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 7.800016987857816e-07,
+      "kl": 5.769729796156753e-06,
+      "learning_rate": 4.296296296296296e-06,
+      "loss": 0.0,
+      "num_tokens": 7874.0,
+      "reward": 1.100000023841858,
+      "reward_std": 0.0,
+      "rewards/reward_correct_answer/mean": 1.0,
+      "rewards/reward_correct_answer/std": 0.0,
+      "rewards/reward_strict_format/mean": 0.10000000149011612,
+      "rewards/reward_strict_format/std": 0.0,
+      "step": 35
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.09166666865348816,
+      "clip_ratio/low_min": 0.09166666865348816,
+      "clip_ratio/region_mean": 0.09166666865348816,
+      "completion_length": 5.75,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 6.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 5.75,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 5.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 0.0087890625,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 5.547388076782227,
+      "kl": 1.1836238503456116,
+      "learning_rate": 4.2592592592592596e-06,
+      "loss": -0.0177,
+      "num_tokens": 8101.0,
+      "reward": 0.6000000238418579,
+      "reward_std": 0.5773502588272095,
+      "rewards/reward_correct_answer/mean": 0.5,
+      "rewards/reward_correct_answer/std": 0.5773502588272095,
+      "rewards/reward_strict_format/mean": 0.10000000149011612,
+      "rewards/reward_strict_format/std": 0.0,
+      "step": 36
+    },
+    {
+      "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,
+      "completion_length": 6.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 6.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 6.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 6.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 0.009033203125,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 4.212265878322796e-07,
+      "kl": 2.4437904357910156e-06,
+      "learning_rate": 4.222222222222223e-06,
+      "loss": 0.0,
+      "num_tokens": 8329.0,
+      "reward": 1.100000023841858,
+      "reward_std": 0.0,
+      "rewards/reward_correct_answer/mean": 1.0,
+      "rewards/reward_correct_answer/std": 0.0,
+      "rewards/reward_strict_format/mean": 0.10000000149011612,
+      "rewards/reward_strict_format/std": 0.0,
+      "step": 37
+    },
+    {
+      "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,
+      "completion_length": 6.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 6.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 6.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 6.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 0.00927734375,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 4.034865014546085e-06,
+      "kl": 0.00011650721717160195,
+      "learning_rate": 4.185185185185185e-06,
+      "loss": 0.0,
+      "num_tokens": 8557.0,
+      "reward": 1.100000023841858,
+      "reward_std": 0.0,
+      "rewards/reward_correct_answer/mean": 1.0,
+      "rewards/reward_correct_answer/std": 0.0,
+      "rewards/reward_strict_format/mean": 0.10000000149011612,
+      "rewards/reward_strict_format/std": 0.0,
+      "step": 38
+    },
+    {
+      "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,
+      "completion_length": 5.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 5.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 5.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 5.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 0.009521484375,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 3.4429993434059725e-07,
+      "kl": 1.180172034764837e-06,
+      "learning_rate": 4.1481481481481485e-06,
+      "loss": 0.0,
+      "num_tokens": 8781.0,
+      "reward": 1.100000023841858,
+      "reward_std": 0.0,
+      "rewards/reward_correct_answer/mean": 1.0,
+      "rewards/reward_correct_answer/std": 0.0,
+      "rewards/reward_strict_format/mean": 0.10000000149011612,
+      "rewards/reward_strict_format/std": 0.0,
+      "step": 39
+    },
+    {
+      "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,
+      "completion_length": 5.25,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 6.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 5.25,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 5.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 0.009765625,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 24.663333892822266,
+      "kl": 0.16362620005384088,
+      "learning_rate": 4.111111111111111e-06,
+      "loss": -0.0008,
+      "num_tokens": 9006.0,
+      "reward": 0.3500000238418579,
+      "reward_std": 0.5,
+      "rewards/reward_correct_answer/mean": 0.25,
+      "rewards/reward_correct_answer/std": 0.5,
+      "rewards/reward_strict_format/mean": 0.10000000149011612,
+      "rewards/reward_strict_format/std": 0.0,
+      "step": 40
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 6.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 6.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 6.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 6.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 0.010009765625,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 0.002748520579189062,
+      "kl": 0.04048967361450195,
+      "learning_rate": 4.074074074074074e-06,
+      "loss": 0.0,
+      "num_tokens": 9234.0,
+      "reward": 1.100000023841858,
+      "reward_std": 0.0,
+      "rewards/reward_correct_answer/mean": 1.0,
+      "rewards/reward_correct_answer/std": 0.0,
+      "rewards/reward_strict_format/mean": 0.10000000149011612,
+      "rewards/reward_strict_format/std": 0.0,
+      "step": 41
+    },
+    {
+      "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,
+      "completion_length": 6.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 6.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 6.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 6.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 0.01025390625,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 0.0033599224407225847,
+      "kl": 0.06288079917430878,
+      "learning_rate": 4.037037037037037e-06,
+      "loss": 0.0001,
+      "num_tokens": 9462.0,
+      "reward": 1.100000023841858,
+      "reward_std": 0.0,
+      "rewards/reward_correct_answer/mean": 1.0,
+      "rewards/reward_correct_answer/std": 0.0,
+      "rewards/reward_strict_format/mean": 0.10000000149011612,
+      "rewards/reward_strict_format/std": 0.0,
+      "step": 42
+    },
+    {
+      "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,
+      "completion_length": 6.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 6.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 6.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 6.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 0.010498046875,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 0.0031793536618351936,
+      "kl": 0.002146601676940918,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.0,
+      "num_tokens": 9690.0,
+      "reward": 1.100000023841858,
+      "reward_std": 0.0,
+      "rewards/reward_correct_answer/mean": 1.0,
+      "rewards/reward_correct_answer/std": 0.0,
+      "rewards/reward_strict_format/mean": 0.10000000149011612,
+      "rewards/reward_strict_format/std": 0.0,
+      "step": 43
+    },
+    {
+      "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,
+      "completion_length": 5.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 5.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 5.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 5.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 0.0107421875,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 1.9671672362164827e-06,
+      "kl": 2.7513504392118193e-05,
+      "learning_rate": 3.962962962962963e-06,
+      "loss": 0.0,
+      "num_tokens": 9914.0,
+      "reward": 1.100000023841858,
+      "reward_std": 0.0,
+      "rewards/reward_correct_answer/mean": 1.0,
+      "rewards/reward_correct_answer/std": 0.0,
+      "rewards/reward_strict_format/mean": 0.10000000149011612,
+      "rewards/reward_strict_format/std": 0.0,
+      "step": 44
+    },
+    {
+      "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,
+      "completion_length": 6.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 6.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 6.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 6.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 0.010986328125,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 5.092861101729795e-07,
+      "kl": 3.337860107421875e-05,
+      "learning_rate": 3.925925925925926e-06,
+      "loss": 0.0,
+      "num_tokens": 10142.0,
+      "reward": 1.100000023841858,
+      "reward_std": 0.0,
+      "rewards/reward_correct_answer/mean": 1.0,
+      "rewards/reward_correct_answer/std": 0.0,
+      "rewards/reward_strict_format/mean": 0.10000000149011612,
+      "rewards/reward_strict_format/std": 0.0,
+      "step": 45
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completion_length": 5.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 5.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 5.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 5.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 0.01123046875,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 2.3712750873983168e-08,
+      "kl": 9.536743306171047e-08,
+      "learning_rate": 3.88888888888889e-06,
+      "loss": 0.0,
+      "num_tokens": 10366.0,
+      "reward": 1.100000023841858,
+      "reward_std": 0.0,
+      "rewards/reward_correct_answer/mean": 1.0,
+      "rewards/reward_correct_answer/std": 0.0,
+      "rewards/reward_strict_format/mean": 0.10000000149011612,
+      "rewards/reward_strict_format/std": 0.0,
+      "step": 46
+    },
+    {
+      "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,
+      "completion_length": 5.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 5.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 5.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 5.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 0.011474609375,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 4.5163797701697206e-10,
+      "kl": 0.0,
+      "learning_rate": 3.851851851851852e-06,
+      "loss": 0.0,
+      "num_tokens": 10590.0,
+      "reward": 1.100000023841858,
+      "reward_std": 0.0,
+      "rewards/reward_correct_answer/mean": 1.0,
+      "rewards/reward_correct_answer/std": 0.0,
+      "rewards/reward_strict_format/mean": 0.10000000149011612,
+      "rewards/reward_strict_format/std": 0.0,
+      "step": 47
+    },
+    {
+      "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,
+      "completion_length": 5.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 5.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 5.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 5.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 0.01171875,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 1.5043545076309783e-08,
+      "kl": 0.0,
+      "learning_rate": 3.814814814814815e-06,
+      "loss": 0.0,
+      "num_tokens": 10814.0,
+      "reward": 1.100000023841858,
+      "reward_std": 0.0,
+      "rewards/reward_correct_answer/mean": 1.0,
+      "rewards/reward_correct_answer/std": 0.0,
+      "rewards/reward_strict_format/mean": 0.10000000149011612,
+      "rewards/reward_strict_format/std": 0.0,
+      "step": 48
+    },
+    {
+      "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,
+      "completion_length": 5.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 5.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 5.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 5.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 0.011962890625,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 2.3994104481062095e-08,
+      "kl": 4.7683716530855236e-08,
+      "learning_rate": 3.777777777777778e-06,
+      "loss": 0.0,
+      "num_tokens": 11038.0,
+      "reward": 1.100000023841858,
+      "reward_std": 0.0,
+      "rewards/reward_correct_answer/mean": 1.0,
+      "rewards/reward_correct_answer/std": 0.0,
+      "rewards/reward_strict_format/mean": 0.10000000149011612,
+      "rewards/reward_strict_format/std": 0.0,
+      "step": 49
+    },
+    {
+      "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,
+      "completion_length": 6.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 6.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 6.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 6.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 0.01220703125,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 2.5674165016198458e-08,
+      "kl": 6.35782896551973e-07,
+      "learning_rate": 3.740740740740741e-06,
+      "loss": 0.0,
+      "num_tokens": 11266.0,
+      "reward": 1.100000023841858,
+      "reward_std": 0.0,
+      "rewards/reward_correct_answer/mean": 1.0,
+      "rewards/reward_correct_answer/std": 0.0,
+      "rewards/reward_strict_format/mean": 0.10000000149011612,
+      "rewards/reward_strict_format/std": 0.0,
+      "step": 50
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 150,
+  "num_input_tokens_seen": 11266,
+  "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": 1,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4ca541c9ac6b151ffb2e4e619e9e8f75be96be4e7c6cea8204247032d540fb1
+size 7761