Upload model from Kaggle (zip extracted)

.gitattributes

@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-150/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-50/tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,69 @@
+---
+base_model: unsloth/Qwen2.5-Coder-0.5B-Instruct
+library_name: transformers
+model_name: debugzero_model
+tags:
+- generated_from_trainer
+- grpo
+- trl
+- unsloth
+licence: license
+---
+
+# Model Card for debugzero_model
+
+This model is a fine-tuned version of [unsloth/Qwen2.5-Coder-0.5B-Instruct](https://huggingface.co/unsloth/Qwen2.5-Coder-0.5B-Instruct).
+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: 0.24.0
+- Transformers: 5.5.0
+- Pytorch: 2.10.0+cu128
+- Datasets: 4.3.0
+- Tokenizers: 0.22.2
+
+## Citations
+
+Cite GRPO as:
+
+```bibtex
+@article{shao2024deepseekmath,
+    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}}
+}
+```

checkpoint-100/README.md

@@ -0,0 +1,210 @@
+---
+base_model: unsloth/Qwen2.5-Coder-0.5B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/Qwen2.5-Coder-0.5B-Instruct
+- 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

checkpoint-100/adapter_config.json

@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen2ForCausalLM",
+    "parent_library": "transformers.models.qwen2.modeling_qwen2",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/Qwen2.5-Coder-0.5B-Instruct",
+  "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,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "k_proj",
+    "o_proj",
+    "up_proj",
+    "gate_proj",
+    "q_proj",
+    "down_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-100/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:776a58008e6057875a95eb4c9b416067e8bed8fee6055a6c4e789604d0b2da32
+size 70430032

checkpoint-100/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# 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' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) 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' }}
+{%- endif %}

checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1a5e6c4910d24f8435f25cdc1f357415508b75f8439f7ba16b60adee1f94106
+size 36139685

checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a36998df7779670e6875d34eafebcb377dcdcbaff70e54ae678ec64164030cbe
+size 14645

checkpoint-100/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4393a84a3109995aa1202073b039b12062e3189ed89aa0b94ef0510ba843009
+size 1383

checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad152981f692f4cc5629bf2d540a4f8fc379072f49c245a2240b74ca1bc6b09b
+size 1465

checkpoint-100/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af5891a15588546db1ac7f2baf8fa94835a51a85c032c39793a55bb048b47446
+size 11422523

checkpoint-100/tokenizer_config.json

@@ -0,0 +1,202 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [],
+  "is_local": false,
+  "model_max_length": 32768,
+  "pad_token": "<|PAD_TOKEN|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<|PAD_TOKEN|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  }
+}

checkpoint-100/trainer_state.json

@@ -0,0 +1,574 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "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,
+      "completion_length": 95.85,
+      "completions/clipped_ratio": 0.125,
+      "completions/max_length": 256.0,
+      "completions/max_terminated_length": 195.6,
+      "completions/mean_length": 95.85,
+      "completions/mean_terminated_length": 72.8880989074707,
+      "completions/min_length": 36.6,
+      "completions/min_terminated_length": 36.6,
+      "epoch": 0.5,
+      "frac_reward_zero_std": 0.2,
+      "grad_norm": 0.3041034936904907,
+      "kl": 0.00021898818758927518,
+      "learning_rate": 4e-05,
+      "loss": 0.0329527884721756,
+      "num_tokens": 21444.0,
+      "reward": 0.7767857074737549,
+      "reward_std": 0.7150911569595337,
+      "rewards/reward_fn/mean": 0.7767857074737549,
+      "rewards/reward_fn/std": 0.9959433197975158,
+      "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": 95.1,
+      "completions/clipped_ratio": 0.0875,
+      "completions/max_length": 225.2,
+      "completions/max_terminated_length": 159.2,
+      "completions/mean_length": 95.1,
+      "completions/mean_terminated_length": 80.34466400146485,
+      "completions/min_length": 34.6,
+      "completions/min_terminated_length": 34.6,
+      "epoch": 1.0,
+      "frac_reward_zero_std": 0.4,
+      "grad_norm": 0.2708108425140381,
+      "kl": 0.006061523332027719,
+      "learning_rate": 9e-05,
+      "loss": -0.016053691506385803,
+      "num_tokens": 42220.0,
+      "reward": 0.6875000119209289,
+      "reward_std": 0.5175672590732574,
+      "rewards/reward_fn/mean": 0.6875,
+      "rewards/reward_fn/std": 0.8034753799438477,
+      "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": 146.275,
+      "completions/clipped_ratio": 0.325,
+      "completions/max_length": 256.0,
+      "completions/max_terminated_length": 225.4,
+      "completions/mean_length": 146.275,
+      "completions/mean_terminated_length": 92.8663101196289,
+      "completions/min_length": 32.6,
+      "completions/min_terminated_length": 32.6,
+      "epoch": 1.5,
+      "frac_reward_zero_std": 0.2,
+      "grad_norm": 0.27529817819595337,
+      "kl": 0.01560373855754733,
+      "learning_rate": 9.989068136093873e-05,
+      "loss": 0.010054035484790802,
+      "num_tokens": 69198.0,
+      "reward": 1.1558928728103637,
+      "reward_std": 0.8465379416942597,
+      "rewards/reward_fn/mean": 1.1558928728103637,
+      "rewards/reward_fn/std": 1.1404805421829223,
+      "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": 75.85,
+      "completions/clipped_ratio": 0.05,
+      "completions/max_length": 220.6,
+      "completions/max_terminated_length": 151.0,
+      "completions/mean_length": 75.85,
+      "completions/mean_terminated_length": 66.14857330322266,
+      "completions/min_length": 32.8,
+      "completions/min_terminated_length": 32.8,
+      "epoch": 2.0,
+      "frac_reward_zero_std": 0.35,
+      "grad_norm": 0.353487491607666,
+      "kl": 0.027986684162169696,
+      "learning_rate": 9.944739353007344e-05,
+      "loss": -0.030885905027389526,
+      "num_tokens": 87334.0,
+      "reward": 0.7932142853736878,
+      "reward_std": 0.4118983089923859,
+      "rewards/reward_fn/mean": 0.7932142853736878,
+      "rewards/reward_fn/std": 0.7167340397834778,
+      "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": 90.85,
+      "completions/clipped_ratio": 0.0625,
+      "completions/max_length": 248.0,
+      "completions/max_terminated_length": 216.4,
+      "completions/mean_length": 90.85,
+      "completions/mean_terminated_length": 79.819287109375,
+      "completions/min_length": 28.0,
+      "completions/min_terminated_length": 28.0,
+      "epoch": 2.5,
+      "frac_reward_zero_std": 0.15,
+      "grad_norm": 0.3318491578102112,
+      "kl": 0.04692814685404301,
+      "learning_rate": 9.86663298624003e-05,
+      "loss": 0.05783940553665161,
+      "num_tokens": 108330.0,
+      "reward": 1.1987500190734863,
+      "reward_std": 0.5907092690467834,
+      "rewards/reward_fn/mean": 1.1987500190734863,
+      "rewards/reward_fn/std": 0.9482298731803894,
+      "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": 91.775,
+      "completions/clipped_ratio": 0.125,
+      "completions/max_length": 248.2,
+      "completions/max_terminated_length": 212.6,
+      "completions/mean_length": 91.775,
+      "completions/mean_terminated_length": 68.68722763061524,
+      "completions/min_length": 25.2,
+      "completions/min_terminated_length": 25.2,
+      "epoch": 3.0,
+      "frac_reward_zero_std": 0.4,
+      "grad_norm": 0.24605490267276764,
+      "kl": 0.07254143096506596,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 0.03934891819953919,
+      "num_tokens": 129012.0,
+      "reward": 1.0242857217788697,
+      "reward_std": 0.5802445828914642,
+      "rewards/reward_fn/mean": 1.0242857217788697,
+      "rewards/reward_fn/std": 0.8706011414527893,
+      "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": 59.7875,
+      "completions/clipped_ratio": 0.0375,
+      "completions/max_length": 175.6,
+      "completions/max_terminated_length": 118.4,
+      "completions/mean_length": 59.7875,
+      "completions/mean_terminated_length": 52.19559555053711,
+      "completions/min_length": 25.4,
+      "completions/min_terminated_length": 25.4,
+      "epoch": 3.5,
+      "frac_reward_zero_std": 0.6,
+      "grad_norm": 0.2970605790615082,
+      "kl": 0.053099883161485194,
+      "learning_rate": 9.611448774886924e-05,
+      "loss": 0.06977529525756836,
+      "num_tokens": 147103.0,
+      "reward": 0.9473214387893677,
+      "reward_std": 0.3923970699310303,
+      "rewards/reward_fn/mean": 0.9473214268684387,
+      "rewards/reward_fn/std": 0.649278998374939,
+      "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,
+      "completion_length": 47.85,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 94.8,
+      "completions/max_terminated_length": 94.8,
+      "completions/mean_length": 47.85,
+      "completions/mean_terminated_length": 47.85,
+      "completions/min_length": 31.2,
+      "completions/min_terminated_length": 31.2,
+      "epoch": 4.0,
+      "frac_reward_zero_std": 0.85,
+      "grad_norm": 0.16646049916744232,
+      "kl": 0.056573960930109024,
+      "learning_rate": 9.43611409721806e-05,
+      "loss": -0.0031644195318222047,
+      "num_tokens": 164643.0,
+      "reward": 0.7899999976158142,
+      "reward_std": 0.12681145668029786,
+      "rewards/reward_fn/mean": 0.7899999976158142,
+      "rewards/reward_fn/std": 0.5133758962154389,
+      "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": 49.2625,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 93.6,
+      "completions/max_terminated_length": 93.6,
+      "completions/mean_length": 49.2625,
+      "completions/mean_terminated_length": 49.2625,
+      "completions/min_length": 33.8,
+      "completions/min_terminated_length": 33.8,
+      "epoch": 4.5,
+      "frac_reward_zero_std": 0.6,
+      "grad_norm": 0.3159082531929016,
+      "kl": 0.0353464649990201,
+      "learning_rate": 9.230476262104677e-05,
+      "loss": -0.03417131304740906,
+      "num_tokens": 182568.0,
+      "reward": 0.7924999833106995,
+      "reward_std": 0.3821385264396667,
+      "rewards/reward_fn/mean": 0.7924999833106995,
+      "rewards/reward_fn/std": 0.62625293135643,
+      "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": 58.25,
+      "completions/clipped_ratio": 0.0125,
+      "completions/max_length": 180.6,
+      "completions/max_terminated_length": 153.2,
+      "completions/mean_length": 58.25,
+      "completions/mean_terminated_length": 55.67250061035156,
+      "completions/min_length": 33.2,
+      "completions/min_terminated_length": 33.2,
+      "epoch": 5.0,
+      "frac_reward_zero_std": 0.55,
+      "grad_norm": 0.27360936999320984,
+      "kl": 0.04483541352674365,
+      "learning_rate": 8.995939984474624e-05,
+      "loss": 0.026852786540985107,
+      "num_tokens": 200660.0,
+      "reward": 0.774821424484253,
+      "reward_std": 0.32772802114486693,
+      "rewards/reward_fn/mean": 0.774821424484253,
+      "rewards/reward_fn/std": 0.5432307064533234,
+      "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,
+      "completion_length": 51.225,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 117.4,
+      "completions/max_terminated_length": 117.4,
+      "completions/mean_length": 51.225,
+      "completions/mean_terminated_length": 51.225,
+      "completions/min_length": 36.6,
+      "completions/min_terminated_length": 36.6,
+      "epoch": 5.5,
+      "frac_reward_zero_std": 0.6,
+      "grad_norm": 0.21470840275287628,
+      "kl": 0.04195364024490118,
+      "learning_rate": 8.73410738492077e-05,
+      "loss": 0.023307889699935913,
+      "num_tokens": 218442.0,
+      "reward": 1.0364285826683044,
+      "reward_std": 0.37462076991796495,
+      "rewards/reward_fn/mean": 1.0364285826683044,
+      "rewards/reward_fn/std": 0.6156843721866607,
+      "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,
+      "completion_length": 53.225,
+      "completions/clipped_ratio": 0.0125,
+      "completions/max_length": 159.8,
+      "completions/max_terminated_length": 123.8,
+      "completions/mean_length": 53.225,
+      "completions/mean_terminated_length": 50.68583374023437,
+      "completions/min_length": 33.8,
+      "completions/min_terminated_length": 33.8,
+      "epoch": 6.0,
+      "frac_reward_zero_std": 0.45,
+      "grad_norm": 0.29306381940841675,
+      "kl": 0.05784560404717922,
+      "learning_rate": 8.44676704559283e-05,
+      "loss": 0.015561078488826752,
+      "num_tokens": 236112.0,
+      "reward": 1.1410714387893677,
+      "reward_std": 0.3540264666080475,
+      "rewards/reward_fn/mean": 1.1410714387893677,
+      "rewards/reward_fn/std": 0.607547128200531,
+      "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,
+      "completion_length": 62.2625,
+      "completions/clipped_ratio": 0.05,
+      "completions/max_length": 153.2,
+      "completions/max_terminated_length": 117.4,
+      "completions/mean_length": 62.2625,
+      "completions/mean_terminated_length": 52.46428680419922,
+      "completions/min_length": 30.6,
+      "completions/min_terminated_length": 30.6,
+      "epoch": 6.5,
+      "frac_reward_zero_std": 0.65,
+      "grad_norm": 0.2615426480770111,
+      "kl": 0.09820330440998078,
+      "learning_rate": 8.135881792367686e-05,
+      "loss": 0.04314278066158295,
+      "num_tokens": 254033.0,
+      "reward": 1.2110714197158814,
+      "reward_std": 0.2716316431760788,
+      "rewards/reward_fn/mean": 1.2110714197158814,
+      "rewards/reward_fn/std": 0.6701113641262054,
+      "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,
+      "completion_length": 82.5625,
+      "completions/clipped_ratio": 0.1125,
+      "completions/max_length": 234.4,
+      "completions/max_terminated_length": 147.4,
+      "completions/mean_length": 82.5625,
+      "completions/mean_terminated_length": 60.485835266113284,
+      "completions/min_length": 35.4,
+      "completions/min_terminated_length": 35.4,
+      "epoch": 7.0,
+      "frac_reward_zero_std": 0.6,
+      "grad_norm": 0.1326226145029068,
+      "kl": 0.07194480895996094,
+      "learning_rate": 7.803575286758364e-05,
+      "loss": 0.03152734041213989,
+      "num_tokens": 275222.0,
+      "reward": 1.320892834663391,
+      "reward_std": 0.35234126150608064,
+      "rewards/reward_fn/mean": 1.320892858505249,
+      "rewards/reward_fn/std": 0.676600456237793,
+      "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,
+      "completion_length": 72.7625,
+      "completions/clipped_ratio": 0.0625,
+      "completions/max_length": 220.4,
+      "completions/max_terminated_length": 166.8,
+      "completions/mean_length": 72.7625,
+      "completions/mean_terminated_length": 59.95151138305664,
+      "completions/min_length": 30.2,
+      "completions/min_terminated_length": 30.2,
+      "epoch": 7.5,
+      "frac_reward_zero_std": 0.7,
+      "grad_norm": 0.15138906240463257,
+      "kl": 0.09165919721126556,
+      "learning_rate": 7.452117519152542e-05,
+      "loss": 0.0013809207826852798,
+      "num_tokens": 294407.0,
+      "reward": 1.3473214387893677,
+      "reward_std": 0.17192934565246104,
+      "rewards/reward_fn/mean": 1.3473214387893677,
+      "rewards/reward_fn/std": 0.6935437321662903,
+      "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,
+      "completion_length": 80.9375,
+      "completions/clipped_ratio": 0.125,
+      "completions/max_length": 222.4,
+      "completions/max_terminated_length": 156.0,
+      "completions/mean_length": 80.9375,
+      "completions/mean_terminated_length": 55.99818344116211,
+      "completions/min_length": 31.6,
+      "completions/min_terminated_length": 31.6,
+      "epoch": 8.0,
+      "frac_reward_zero_std": 0.65,
+      "grad_norm": 0.19589942693710327,
+      "kl": 0.0683181069791317,
+      "learning_rate": 7.083909302476453e-05,
+      "loss": 0.033023273944854735,
+      "num_tokens": 314502.0,
+      "reward": 1.1685714244842529,
+      "reward_std": 0.27699449211359023,
+      "rewards/reward_fn/mean": 1.1685714244842529,
+      "rewards/reward_fn/std": 0.5244716942310333,
+      "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,
+      "completion_length": 60.6625,
+      "completions/clipped_ratio": 0.05,
+      "completions/max_length": 207.2,
+      "completions/max_terminated_length": 100.0,
+      "completions/mean_length": 60.6625,
+      "completions/mean_terminated_length": 50.27571563720703,
+      "completions/min_length": 35.2,
+      "completions/min_terminated_length": 35.2,
+      "epoch": 8.5,
+      "frac_reward_zero_std": 0.6,
+      "grad_norm": 0.20066438615322113,
+      "kl": 0.0837025498971343,
+      "learning_rate": 6.701465872208216e-05,
+      "loss": 0.022454433143138885,
+      "num_tokens": 334007.0,
+      "reward": 1.3910714387893677,
+      "reward_std": 0.21785714849829674,
+      "rewards/reward_fn/mean": 1.3910714387893677,
+      "rewards/reward_fn/std": 0.6235540926456451,
+      "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,
+      "completion_length": 54.025,
+      "completions/clipped_ratio": 0.025,
+      "completions/max_length": 143.4,
+      "completions/max_terminated_length": 117.2,
+      "completions/mean_length": 54.025,
+      "completions/mean_terminated_length": 49.025001525878906,
+      "completions/min_length": 30.2,
+      "completions/min_terminated_length": 30.2,
+      "epoch": 9.0,
+      "frac_reward_zero_std": 0.8,
+      "grad_norm": 0.18161360919475555,
+      "kl": 0.05805329587310552,
+      "learning_rate": 6.307399704769099e-05,
+      "loss": -0.04096371531486511,
+      "num_tokens": 351041.0,
+      "reward": 1.24375,
+      "reward_std": 0.2125,
+      "rewards/reward_fn/mean": 1.24375,
+      "rewards/reward_fn/std": 0.584508627653122,
+      "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,
+      "completion_length": 54.65,
+      "completions/clipped_ratio": 0.0125,
+      "completions/max_length": 145.0,
+      "completions/max_terminated_length": 142.2,
+      "completions/mean_length": 54.65,
+      "completions/mean_terminated_length": 52.23083419799805,
+      "completions/min_length": 35.4,
+      "completions/min_terminated_length": 35.4,
+      "epoch": 9.5,
+      "frac_reward_zero_std": 0.9,
+      "grad_norm": 0.10424701869487762,
+      "kl": 0.05452606473118067,
+      "learning_rate": 5.90440267166055e-05,
+      "loss": 0.0021311525255441667,
+      "num_tokens": 368361.0,
+      "reward": 1.1996428489685058,
+      "reward_std": 0.058449314022436735,
+      "rewards/reward_fn/mean": 1.1996428489685058,
+      "rewards/reward_fn/std": 0.4604207634925842,
+      "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,
+      "completion_length": 68.3875,
+      "completions/clipped_ratio": 0.0625,
+      "completions/max_length": 254.4,
+      "completions/max_terminated_length": 140.8,
+      "completions/mean_length": 68.3875,
+      "completions/mean_terminated_length": 55.740359497070315,
+      "completions/min_length": 36.2,
+      "completions/min_terminated_length": 36.2,
+      "epoch": 10.0,
+      "frac_reward_zero_std": 0.75,
+      "grad_norm": 0.13536690175533295,
+      "kl": 0.0854075826704502,
+      "learning_rate": 5.495227651252315e-05,
+      "loss": -0.025432443618774413,
+      "num_tokens": 388400.0,
+      "reward": 1.3283928632736206,
+      "reward_std": 0.2009493112564087,
+      "rewards/reward_fn/mean": 1.3283928632736206,
+      "rewards/reward_fn/std": 0.5586225628852844,
+      "step": 100
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 200,
+  "num_input_tokens_seen": 388400,
+  "num_train_epochs": 20,
+  "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": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61516d246785bb4adf93d26e6fe8ffbb65a924b8a03f13b01e1d00b7066140af
+size 6673

checkpoint-150/README.md

@@ -0,0 +1,210 @@
+---
+base_model: unsloth/Qwen2.5-Coder-0.5B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/Qwen2.5-Coder-0.5B-Instruct
+- 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

checkpoint-150/adapter_config.json

@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen2ForCausalLM",
+    "parent_library": "transformers.models.qwen2.modeling_qwen2",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/Qwen2.5-Coder-0.5B-Instruct",
+  "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,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "k_proj",
+    "o_proj",
+    "up_proj",
+    "gate_proj",
+    "q_proj",
+    "down_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-150/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9b3cf15fb2500f3f8f014f9739f1a21141fd5298ffcb0a0d5fe65deb718e615
+size 70430032

checkpoint-150/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# 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' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) 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' }}
+{%- endif %}

checkpoint-150/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c37453fd3d8af6afa30b40cc9c6ad2d969625ff6e3a19f3a44fedb9dfcaeb1a0
+size 36139685

checkpoint-150/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b68c29a103ea734e571c411420518c24591a5fb6bc226dc1650f76fe8e3921c1
+size 14645

checkpoint-150/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7a646a858b71ab76099f4dca96d8db39ffde2f88258f5a4b082ff62947bcc11
+size 1383

checkpoint-150/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3482f78b8a680a7668ce725c32ed61ffffbbaae8b7bc5042b2c9c5517679d93c
+size 1465

checkpoint-150/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af5891a15588546db1ac7f2baf8fa94835a51a85c032c39793a55bb048b47446
+size 11422523

checkpoint-150/tokenizer_config.json

@@ -0,0 +1,202 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [],
+  "is_local": false,
+  "model_max_length": 32768,
+  "pad_token": "<|PAD_TOKEN|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<|PAD_TOKEN|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  }
+}

checkpoint-150/trainer_state.json

@@ -0,0 +1,844 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 15.0,
+  "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,
+      "completion_length": 95.85,
+      "completions/clipped_ratio": 0.125,
+      "completions/max_length": 256.0,
+      "completions/max_terminated_length": 195.6,
+      "completions/mean_length": 95.85,
+      "completions/mean_terminated_length": 72.8880989074707,
+      "completions/min_length": 36.6,
+      "completions/min_terminated_length": 36.6,
+      "epoch": 0.5,
+      "frac_reward_zero_std": 0.2,
+      "grad_norm": 0.3041034936904907,
+      "kl": 0.00021898818758927518,
+      "learning_rate": 4e-05,
+      "loss": 0.0329527884721756,
+      "num_tokens": 21444.0,
+      "reward": 0.7767857074737549,
+      "reward_std": 0.7150911569595337,
+      "rewards/reward_fn/mean": 0.7767857074737549,
+      "rewards/reward_fn/std": 0.9959433197975158,
+      "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": 95.1,
+      "completions/clipped_ratio": 0.0875,
+      "completions/max_length": 225.2,
+      "completions/max_terminated_length": 159.2,
+      "completions/mean_length": 95.1,
+      "completions/mean_terminated_length": 80.34466400146485,
+      "completions/min_length": 34.6,
+      "completions/min_terminated_length": 34.6,
+      "epoch": 1.0,
+      "frac_reward_zero_std": 0.4,
+      "grad_norm": 0.2708108425140381,
+      "kl": 0.006061523332027719,
+      "learning_rate": 9e-05,
+      "loss": -0.016053691506385803,
+      "num_tokens": 42220.0,
+      "reward": 0.6875000119209289,
+      "reward_std": 0.5175672590732574,
+      "rewards/reward_fn/mean": 0.6875,
+      "rewards/reward_fn/std": 0.8034753799438477,
+      "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": 146.275,
+      "completions/clipped_ratio": 0.325,
+      "completions/max_length": 256.0,
+      "completions/max_terminated_length": 225.4,
+      "completions/mean_length": 146.275,
+      "completions/mean_terminated_length": 92.8663101196289,
+      "completions/min_length": 32.6,
+      "completions/min_terminated_length": 32.6,
+      "epoch": 1.5,
+      "frac_reward_zero_std": 0.2,
+      "grad_norm": 0.27529817819595337,
+      "kl": 0.01560373855754733,
+      "learning_rate": 9.989068136093873e-05,
+      "loss": 0.010054035484790802,
+      "num_tokens": 69198.0,
+      "reward": 1.1558928728103637,
+      "reward_std": 0.8465379416942597,
+      "rewards/reward_fn/mean": 1.1558928728103637,
+      "rewards/reward_fn/std": 1.1404805421829223,
+      "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": 75.85,
+      "completions/clipped_ratio": 0.05,
+      "completions/max_length": 220.6,
+      "completions/max_terminated_length": 151.0,
+      "completions/mean_length": 75.85,
+      "completions/mean_terminated_length": 66.14857330322266,
+      "completions/min_length": 32.8,
+      "completions/min_terminated_length": 32.8,
+      "epoch": 2.0,
+      "frac_reward_zero_std": 0.35,
+      "grad_norm": 0.353487491607666,
+      "kl": 0.027986684162169696,
+      "learning_rate": 9.944739353007344e-05,
+      "loss": -0.030885905027389526,
+      "num_tokens": 87334.0,
+      "reward": 0.7932142853736878,
+      "reward_std": 0.4118983089923859,
+      "rewards/reward_fn/mean": 0.7932142853736878,
+      "rewards/reward_fn/std": 0.7167340397834778,
+      "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": 90.85,
+      "completions/clipped_ratio": 0.0625,
+      "completions/max_length": 248.0,
+      "completions/max_terminated_length": 216.4,
+      "completions/mean_length": 90.85,
+      "completions/mean_terminated_length": 79.819287109375,
+      "completions/min_length": 28.0,
+      "completions/min_terminated_length": 28.0,
+      "epoch": 2.5,
+      "frac_reward_zero_std": 0.15,
+      "grad_norm": 0.3318491578102112,
+      "kl": 0.04692814685404301,
+      "learning_rate": 9.86663298624003e-05,
+      "loss": 0.05783940553665161,
+      "num_tokens": 108330.0,
+      "reward": 1.1987500190734863,
+      "reward_std": 0.5907092690467834,
+      "rewards/reward_fn/mean": 1.1987500190734863,
+      "rewards/reward_fn/std": 0.9482298731803894,
+      "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": 91.775,
+      "completions/clipped_ratio": 0.125,
+      "completions/max_length": 248.2,
+      "completions/max_terminated_length": 212.6,
+      "completions/mean_length": 91.775,
+      "completions/mean_terminated_length": 68.68722763061524,
+      "completions/min_length": 25.2,
+      "completions/min_terminated_length": 25.2,
+      "epoch": 3.0,
+      "frac_reward_zero_std": 0.4,
+      "grad_norm": 0.24605490267276764,
+      "kl": 0.07254143096506596,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 0.03934891819953919,
+      "num_tokens": 129012.0,
+      "reward": 1.0242857217788697,
+      "reward_std": 0.5802445828914642,
+      "rewards/reward_fn/mean": 1.0242857217788697,
+      "rewards/reward_fn/std": 0.8706011414527893,
+      "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": 59.7875,
+      "completions/clipped_ratio": 0.0375,
+      "completions/max_length": 175.6,
+      "completions/max_terminated_length": 118.4,
+      "completions/mean_length": 59.7875,
+      "completions/mean_terminated_length": 52.19559555053711,
+      "completions/min_length": 25.4,
+      "completions/min_terminated_length": 25.4,
+      "epoch": 3.5,
+      "frac_reward_zero_std": 0.6,
+      "grad_norm": 0.2970605790615082,
+      "kl": 0.053099883161485194,
+      "learning_rate": 9.611448774886924e-05,
+      "loss": 0.06977529525756836,
+      "num_tokens": 147103.0,
+      "reward": 0.9473214387893677,
+      "reward_std": 0.3923970699310303,
+      "rewards/reward_fn/mean": 0.9473214268684387,
+      "rewards/reward_fn/std": 0.649278998374939,
+      "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,
+      "completion_length": 47.85,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 94.8,
+      "completions/max_terminated_length": 94.8,
+      "completions/mean_length": 47.85,
+      "completions/mean_terminated_length": 47.85,
+      "completions/min_length": 31.2,
+      "completions/min_terminated_length": 31.2,
+      "epoch": 4.0,
+      "frac_reward_zero_std": 0.85,
+      "grad_norm": 0.16646049916744232,
+      "kl": 0.056573960930109024,
+      "learning_rate": 9.43611409721806e-05,
+      "loss": -0.0031644195318222047,
+      "num_tokens": 164643.0,
+      "reward": 0.7899999976158142,
+      "reward_std": 0.12681145668029786,
+      "rewards/reward_fn/mean": 0.7899999976158142,
+      "rewards/reward_fn/std": 0.5133758962154389,
+      "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": 49.2625,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 93.6,
+      "completions/max_terminated_length": 93.6,
+      "completions/mean_length": 49.2625,
+      "completions/mean_terminated_length": 49.2625,
+      "completions/min_length": 33.8,
+      "completions/min_terminated_length": 33.8,
+      "epoch": 4.5,
+      "frac_reward_zero_std": 0.6,
+      "grad_norm": 0.3159082531929016,
+      "kl": 0.0353464649990201,
+      "learning_rate": 9.230476262104677e-05,
+      "loss": -0.03417131304740906,
+      "num_tokens": 182568.0,
+      "reward": 0.7924999833106995,
+      "reward_std": 0.3821385264396667,
+      "rewards/reward_fn/mean": 0.7924999833106995,
+      "rewards/reward_fn/std": 0.62625293135643,
+      "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": 58.25,
+      "completions/clipped_ratio": 0.0125,
+      "completions/max_length": 180.6,
+      "completions/max_terminated_length": 153.2,
+      "completions/mean_length": 58.25,
+      "completions/mean_terminated_length": 55.67250061035156,
+      "completions/min_length": 33.2,
+      "completions/min_terminated_length": 33.2,
+      "epoch": 5.0,
+      "frac_reward_zero_std": 0.55,
+      "grad_norm": 0.27360936999320984,
+      "kl": 0.04483541352674365,
+      "learning_rate": 8.995939984474624e-05,
+      "loss": 0.026852786540985107,
+      "num_tokens": 200660.0,
+      "reward": 0.774821424484253,
+      "reward_std": 0.32772802114486693,
+      "rewards/reward_fn/mean": 0.774821424484253,
+      "rewards/reward_fn/std": 0.5432307064533234,
+      "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,
+      "completion_length": 51.225,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 117.4,
+      "completions/max_terminated_length": 117.4,
+      "completions/mean_length": 51.225,
+      "completions/mean_terminated_length": 51.225,
+      "completions/min_length": 36.6,
+      "completions/min_terminated_length": 36.6,
+      "epoch": 5.5,
+      "frac_reward_zero_std": 0.6,
+      "grad_norm": 0.21470840275287628,
+      "kl": 0.04195364024490118,
+      "learning_rate": 8.73410738492077e-05,
+      "loss": 0.023307889699935913,
+      "num_tokens": 218442.0,
+      "reward": 1.0364285826683044,
+      "reward_std": 0.37462076991796495,
+      "rewards/reward_fn/mean": 1.0364285826683044,
+      "rewards/reward_fn/std": 0.6156843721866607,
+      "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,
+      "completion_length": 53.225,
+      "completions/clipped_ratio": 0.0125,
+      "completions/max_length": 159.8,
+      "completions/max_terminated_length": 123.8,
+      "completions/mean_length": 53.225,
+      "completions/mean_terminated_length": 50.68583374023437,
+      "completions/min_length": 33.8,
+      "completions/min_terminated_length": 33.8,
+      "epoch": 6.0,
+      "frac_reward_zero_std": 0.45,
+      "grad_norm": 0.29306381940841675,
+      "kl": 0.05784560404717922,
+      "learning_rate": 8.44676704559283e-05,
+      "loss": 0.015561078488826752,
+      "num_tokens": 236112.0,
+      "reward": 1.1410714387893677,
+      "reward_std": 0.3540264666080475,
+      "rewards/reward_fn/mean": 1.1410714387893677,
+      "rewards/reward_fn/std": 0.607547128200531,
+      "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,
+      "completion_length": 62.2625,
+      "completions/clipped_ratio": 0.05,
+      "completions/max_length": 153.2,
+      "completions/max_terminated_length": 117.4,
+      "completions/mean_length": 62.2625,
+      "completions/mean_terminated_length": 52.46428680419922,
+      "completions/min_length": 30.6,
+      "completions/min_terminated_length": 30.6,
+      "epoch": 6.5,
+      "frac_reward_zero_std": 0.65,
+      "grad_norm": 0.2615426480770111,
+      "kl": 0.09820330440998078,
+      "learning_rate": 8.135881792367686e-05,
+      "loss": 0.04314278066158295,
+      "num_tokens": 254033.0,
+      "reward": 1.2110714197158814,
+      "reward_std": 0.2716316431760788,
+      "rewards/reward_fn/mean": 1.2110714197158814,
+      "rewards/reward_fn/std": 0.6701113641262054,
+      "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,
+      "completion_length": 82.5625,
+      "completions/clipped_ratio": 0.1125,
+      "completions/max_length": 234.4,
+      "completions/max_terminated_length": 147.4,
+      "completions/mean_length": 82.5625,
+      "completions/mean_terminated_length": 60.485835266113284,
+      "completions/min_length": 35.4,
+      "completions/min_terminated_length": 35.4,
+      "epoch": 7.0,
+      "frac_reward_zero_std": 0.6,
+      "grad_norm": 0.1326226145029068,
+      "kl": 0.07194480895996094,
+      "learning_rate": 7.803575286758364e-05,
+      "loss": 0.03152734041213989,
+      "num_tokens": 275222.0,
+      "reward": 1.320892834663391,
+      "reward_std": 0.35234126150608064,
+      "rewards/reward_fn/mean": 1.320892858505249,
+      "rewards/reward_fn/std": 0.676600456237793,
+      "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,
+      "completion_length": 72.7625,
+      "completions/clipped_ratio": 0.0625,
+      "completions/max_length": 220.4,
+      "completions/max_terminated_length": 166.8,
+      "completions/mean_length": 72.7625,
+      "completions/mean_terminated_length": 59.95151138305664,
+      "completions/min_length": 30.2,
+      "completions/min_terminated_length": 30.2,
+      "epoch": 7.5,
+      "frac_reward_zero_std": 0.7,
+      "grad_norm": 0.15138906240463257,
+      "kl": 0.09165919721126556,
+      "learning_rate": 7.452117519152542e-05,
+      "loss": 0.0013809207826852798,
+      "num_tokens": 294407.0,
+      "reward": 1.3473214387893677,
+      "reward_std": 0.17192934565246104,
+      "rewards/reward_fn/mean": 1.3473214387893677,
+      "rewards/reward_fn/std": 0.6935437321662903,
+      "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,
+      "completion_length": 80.9375,
+      "completions/clipped_ratio": 0.125,
+      "completions/max_length": 222.4,
+      "completions/max_terminated_length": 156.0,
+      "completions/mean_length": 80.9375,
+      "completions/mean_terminated_length": 55.99818344116211,
+      "completions/min_length": 31.6,
+      "completions/min_terminated_length": 31.6,
+      "epoch": 8.0,
+      "frac_reward_zero_std": 0.65,
+      "grad_norm": 0.19589942693710327,
+      "kl": 0.0683181069791317,
+      "learning_rate": 7.083909302476453e-05,
+      "loss": 0.033023273944854735,
+      "num_tokens": 314502.0,
+      "reward": 1.1685714244842529,
+      "reward_std": 0.27699449211359023,
+      "rewards/reward_fn/mean": 1.1685714244842529,
+      "rewards/reward_fn/std": 0.5244716942310333,
+      "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,
+      "completion_length": 60.6625,
+      "completions/clipped_ratio": 0.05,
+      "completions/max_length": 207.2,
+      "completions/max_terminated_length": 100.0,
+      "completions/mean_length": 60.6625,
+      "completions/mean_terminated_length": 50.27571563720703,
+      "completions/min_length": 35.2,
+      "completions/min_terminated_length": 35.2,
+      "epoch": 8.5,
+      "frac_reward_zero_std": 0.6,
+      "grad_norm": 0.20066438615322113,
+      "kl": 0.0837025498971343,
+      "learning_rate": 6.701465872208216e-05,
+      "loss": 0.022454433143138885,
+      "num_tokens": 334007.0,
+      "reward": 1.3910714387893677,
+      "reward_std": 0.21785714849829674,
+      "rewards/reward_fn/mean": 1.3910714387893677,
+      "rewards/reward_fn/std": 0.6235540926456451,
+      "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,
+      "completion_length": 54.025,
+      "completions/clipped_ratio": 0.025,
+      "completions/max_length": 143.4,
+      "completions/max_terminated_length": 117.2,
+      "completions/mean_length": 54.025,
+      "completions/mean_terminated_length": 49.025001525878906,
+      "completions/min_length": 30.2,
+      "completions/min_terminated_length": 30.2,
+      "epoch": 9.0,
+      "frac_reward_zero_std": 0.8,
+      "grad_norm": 0.18161360919475555,
+      "kl": 0.05805329587310552,
+      "learning_rate": 6.307399704769099e-05,
+      "loss": -0.04096371531486511,
+      "num_tokens": 351041.0,
+      "reward": 1.24375,
+      "reward_std": 0.2125,
+      "rewards/reward_fn/mean": 1.24375,
+      "rewards/reward_fn/std": 0.584508627653122,
+      "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,
+      "completion_length": 54.65,
+      "completions/clipped_ratio": 0.0125,
+      "completions/max_length": 145.0,
+      "completions/max_terminated_length": 142.2,
+      "completions/mean_length": 54.65,
+      "completions/mean_terminated_length": 52.23083419799805,
+      "completions/min_length": 35.4,
+      "completions/min_terminated_length": 35.4,
+      "epoch": 9.5,
+      "frac_reward_zero_std": 0.9,
+      "grad_norm": 0.10424701869487762,
+      "kl": 0.05452606473118067,
+      "learning_rate": 5.90440267166055e-05,
+      "loss": 0.0021311525255441667,
+      "num_tokens": 368361.0,
+      "reward": 1.1996428489685058,
+      "reward_std": 0.058449314022436735,
+      "rewards/reward_fn/mean": 1.1996428489685058,
+      "rewards/reward_fn/std": 0.4604207634925842,
+      "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,
+      "completion_length": 68.3875,
+      "completions/clipped_ratio": 0.0625,
+      "completions/max_length": 254.4,
+      "completions/max_terminated_length": 140.8,
+      "completions/mean_length": 68.3875,
+      "completions/mean_terminated_length": 55.740359497070315,
+      "completions/min_length": 36.2,
+      "completions/min_terminated_length": 36.2,
+      "epoch": 10.0,
+      "frac_reward_zero_std": 0.75,
+      "grad_norm": 0.13536690175533295,
+      "kl": 0.0854075826704502,
+      "learning_rate": 5.495227651252315e-05,
+      "loss": -0.025432443618774413,
+      "num_tokens": 388400.0,
+      "reward": 1.3283928632736206,
+      "reward_std": 0.2009493112564087,
+      "rewards/reward_fn/mean": 1.3283928632736206,
+      "rewards/reward_fn/std": 0.5586225628852844,
+      "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,
+      "completion_length": 77.6,
+      "completions/clipped_ratio": 0.125,
+      "completions/max_length": 256.0,
+      "completions/max_terminated_length": 115.6,
+      "completions/mean_length": 77.6,
+      "completions/mean_terminated_length": 52.14154052734375,
+      "completions/min_length": 30.4,
+      "completions/min_terminated_length": 30.4,
+      "epoch": 10.5,
+      "frac_reward_zero_std": 0.9,
+      "grad_norm": 0.0006729933083988726,
+      "kl": 0.07917941156774759,
+      "learning_rate": 5.0826697238317935e-05,
+      "loss": -0.0014228260144591332,
+      "num_tokens": 408808.0,
+      "reward": 1.4,
+      "reward_std": 0.1,
+      "rewards/reward_fn/mean": 1.4,
+      "rewards/reward_fn/std": 0.5159838497638702,
+      "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,
+      "completion_length": 71.6375,
+      "completions/clipped_ratio": 0.1,
+      "completions/max_length": 223.8,
+      "completions/max_terminated_length": 125.4,
+      "completions/mean_length": 71.6375,
+      "completions/mean_terminated_length": 50.991825103759766,
+      "completions/min_length": 34.6,
+      "completions/min_terminated_length": 34.6,
+      "epoch": 11.0,
+      "frac_reward_zero_std": 0.85,
+      "grad_norm": 0.1310124397277832,
+      "kl": 0.0553528118878603,
+      "learning_rate": 4.669547078371504e-05,
+      "loss": 0.027294650673866272,
+      "num_tokens": 427787.0,
+      "reward": 1.15,
+      "reward_std": 0.15773502588272095,
+      "rewards/reward_fn/mean": 1.15,
+      "rewards/reward_fn/std": 0.482165002822876,
+      "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,
+      "completion_length": 75.975,
+      "completions/clipped_ratio": 0.1375,
+      "completions/max_length": 214.8,
+      "completions/max_terminated_length": 76.2,
+      "completions/mean_length": 75.975,
+      "completions/mean_terminated_length": 47.73154296875,
+      "completions/min_length": 36.2,
+      "completions/min_terminated_length": 36.2,
+      "epoch": 11.5,
+      "frac_reward_zero_std": 0.9,
+      "grad_norm": 0.001892779255285859,
+      "kl": 0.056033550202846526,
+      "learning_rate": 4.2586817614407895e-05,
+      "loss": -0.03689469993114471,
+      "num_tokens": 447185.0,
+      "reward": 1.2867857217788696,
+      "reward_std": 0.026428571343421935,
+      "rewards/reward_fn/mean": 1.2867857217788696,
+      "rewards/reward_fn/std": 0.3760030448436737,
+      "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,
+      "completion_length": 76.725,
+      "completions/clipped_ratio": 0.1375,
+      "completions/max_length": 218.2,
+      "completions/max_terminated_length": 82.8,
+      "completions/mean_length": 76.725,
+      "completions/mean_terminated_length": 48.34801483154297,
+      "completions/min_length": 30.4,
+      "completions/min_terminated_length": 30.4,
+      "epoch": 12.0,
+      "frac_reward_zero_std": 0.95,
+      "grad_norm": 0.00067809724714607,
+      "kl": 0.06624810677021742,
+      "learning_rate": 3.852880399766243e-05,
+      "loss": 0.005734995752573013,
+      "num_tokens": 466979.0,
+      "reward": 1.325,
+      "reward_std": 0.05,
+      "rewards/reward_fn/mean": 1.325,
+      "rewards/reward_fn/std": 0.4854445576667786,
+      "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,
+      "completion_length": 70.3625,
+      "completions/clipped_ratio": 0.0875,
+      "completions/max_length": 183.8,
+      "completions/max_terminated_length": 99.4,
+      "completions/mean_length": 70.3625,
+      "completions/mean_terminated_length": 52.45879211425781,
+      "completions/min_length": 38.0,
+      "completions/min_terminated_length": 38.0,
+      "epoch": 12.5,
+      "frac_reward_zero_std": 0.9,
+      "grad_norm": 0.0024091172963380814,
+      "kl": 0.0920485682785511,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": -0.03069324791431427,
+      "num_tokens": 486616.0,
+      "reward": 1.3125,
+      "reward_std": 0.075,
+      "rewards/reward_fn/mean": 1.3125,
+      "rewards/reward_fn/std": 0.46982967257499697,
+      "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,
+      "completion_length": 71.8625,
+      "completions/clipped_ratio": 0.1,
+      "completions/max_length": 214.8,
+      "completions/max_terminated_length": 120.2,
+      "completions/mean_length": 71.8625,
+      "completions/mean_terminated_length": 51.76010284423828,
+      "completions/min_length": 33.4,
+      "completions/min_terminated_length": 33.4,
+      "epoch": 13.0,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 0.0004440450284164399,
+      "kl": 0.053088791808113454,
+      "learning_rate": 3.0675041535377405e-05,
+      "loss": 5.229191156104207e-05,
+      "num_tokens": 505905.0,
+      "reward": 1.35,
+      "reward_std": 0.0,
+      "rewards/reward_fn/mean": 1.35,
+      "rewards/reward_fn/std": 0.39928138852119444,
+      "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,
+      "completion_length": 84.5,
+      "completions/clipped_ratio": 0.175,
+      "completions/max_length": 182.8,
+      "completions/max_terminated_length": 76.6,
+      "completions/mean_length": 84.5,
+      "completions/mean_terminated_length": 48.71715393066406,
+      "completions/min_length": 38.0,
+      "completions/min_terminated_length": 38.0,
+      "epoch": 13.5,
+      "frac_reward_zero_std": 0.95,
+      "grad_norm": 0.0007964075193740427,
+      "kl": 0.07870542965829372,
+      "learning_rate": 2.693294185106562e-05,
+      "loss": 0.0014319854788482189,
+      "num_tokens": 526773.0,
+      "reward": 1.3875,
+      "reward_std": 0.025,
+      "rewards/reward_fn/mean": 1.3875,
+      "rewards/reward_fn/std": 0.38874412178993223,
+      "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,
+      "completion_length": 70.6375,
+      "completions/clipped_ratio": 0.1,
+      "completions/max_length": 219.2,
+      "completions/max_terminated_length": 104.2,
+      "completions/mean_length": 70.6375,
+      "completions/mean_terminated_length": 50.06154937744141,
+      "completions/min_length": 37.0,
+      "completions/min_terminated_length": 37.0,
+      "epoch": 14.0,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 0.00017480542010162026,
+      "kl": 0.05223398320376873,
+      "learning_rate": 2.3348413563600325e-05,
+      "loss": 5.521520506590605e-05,
+      "num_tokens": 545864.0,
+      "reward": 1.3,
+      "reward_std": 0.0,
+      "rewards/reward_fn/mean": 1.3,
+      "rewards/reward_fn/std": 0.38544455766677854,
+      "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,
+      "completion_length": 75.7,
+      "completions/clipped_ratio": 0.1125,
+      "completions/max_length": 220.0,
+      "completions/max_terminated_length": 134.4,
+      "completions/mean_length": 75.7,
+      "completions/mean_terminated_length": 52.85439682006836,
+      "completions/min_length": 36.6,
+      "completions/min_terminated_length": 36.6,
+      "epoch": 14.5,
+      "frac_reward_zero_std": 0.95,
+      "grad_norm": 0.0014995499514043331,
+      "kl": 0.061327320709824565,
+      "learning_rate": 1.9945942635848748e-05,
+      "loss": -0.039644479751586914,
+      "num_tokens": 565456.0,
+      "reward": 1.275,
+      "reward_std": 0.05,
+      "rewards/reward_fn/mean": 1.275,
+      "rewards/reward_fn/std": 0.40599284172058103,
+      "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,
+      "completion_length": 88.6875,
+      "completions/clipped_ratio": 0.1875,
+      "completions/max_length": 214.6,
+      "completions/max_terminated_length": 98.8,
+      "completions/mean_length": 88.6875,
+      "completions/mean_terminated_length": 51.92777633666992,
+      "completions/min_length": 35.0,
+      "completions/min_terminated_length": 35.0,
+      "epoch": 15.0,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 0.001117849606089294,
+      "kl": 0.05267696371302009,
+      "learning_rate": 1.6748771394307585e-05,
+      "loss": 6.003726157359779e-05,
+      "num_tokens": 586207.0,
+      "reward": 1.35,
+      "reward_std": 0.0,
+      "rewards/reward_fn/mean": 1.35,
+      "rewards/reward_fn/std": 0.37160772681236265,
+      "step": 150
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 200,
+  "num_input_tokens_seen": 586207,
+  "num_train_epochs": 20,
+  "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": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-150/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61516d246785bb4adf93d26e6fe8ffbb65a924b8a03f13b01e1d00b7066140af
+size 6673

checkpoint-200/README.md

@@ -0,0 +1,210 @@
+---
+base_model: unsloth/Qwen2.5-Coder-0.5B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/Qwen2.5-Coder-0.5B-Instruct
+- 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

checkpoint-200/adapter_config.json

@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen2ForCausalLM",
+    "parent_library": "transformers.models.qwen2.modeling_qwen2",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/Qwen2.5-Coder-0.5B-Instruct",
+  "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,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "k_proj",
+    "o_proj",
+    "up_proj",
+    "gate_proj",
+    "q_proj",
+    "down_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-200/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c9d0849581a47371084753e072266e18e8c8b5479354ba3c9fb4e44fd19fee0
+size 70430032

checkpoint-200/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# 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' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) 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' }}
+{%- endif %}

checkpoint-200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5dedb72c3dbe884e5fe47a64e284132cc4464a1ba833bf4fa7637eda2544f60d
+size 36139685

checkpoint-200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:270254ddfd4c7f90b22f5d661a1c3aedadf08c0fe7fbf135080c566c14a61f6d
+size 14645

checkpoint-200/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:124625e167eb28acbfc793cfcb3e8a08b32e7fea06501462bc9e420a5e1beb2a
+size 1383

checkpoint-200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e2ea8f0d9967134d39bb3975e73cff05d7e316dc3701da4c4d0c02a6d1776f7
+size 1465

checkpoint-200/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af5891a15588546db1ac7f2baf8fa94835a51a85c032c39793a55bb048b47446
+size 11422523

checkpoint-200/tokenizer_config.json

@@ -0,0 +1,202 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [],
+  "is_local": false,
+  "model_max_length": 32768,
+  "pad_token": "<|PAD_TOKEN|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<|PAD_TOKEN|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  }
+}

checkpoint-200/trainer_state.json

@@ -0,0 +1,1114 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 20.0,
+  "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,
+      "completion_length": 95.85,
+      "completions/clipped_ratio": 0.125,
+      "completions/max_length": 256.0,
+      "completions/max_terminated_length": 195.6,
+      "completions/mean_length": 95.85,
+      "completions/mean_terminated_length": 72.8880989074707,
+      "completions/min_length": 36.6,
+      "completions/min_terminated_length": 36.6,
+      "epoch": 0.5,
+      "frac_reward_zero_std": 0.2,
+      "grad_norm": 0.3041034936904907,
+      "kl": 0.00021898818758927518,
+      "learning_rate": 4e-05,
+      "loss": 0.0329527884721756,
+      "num_tokens": 21444.0,
+      "reward": 0.7767857074737549,
+      "reward_std": 0.7150911569595337,
+      "rewards/reward_fn/mean": 0.7767857074737549,
+      "rewards/reward_fn/std": 0.9959433197975158,
+      "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": 95.1,
+      "completions/clipped_ratio": 0.0875,
+      "completions/max_length": 225.2,
+      "completions/max_terminated_length": 159.2,
+      "completions/mean_length": 95.1,
+      "completions/mean_terminated_length": 80.34466400146485,
+      "completions/min_length": 34.6,
+      "completions/min_terminated_length": 34.6,
+      "epoch": 1.0,
+      "frac_reward_zero_std": 0.4,
+      "grad_norm": 0.2708108425140381,
+      "kl": 0.006061523332027719,
+      "learning_rate": 9e-05,
+      "loss": -0.016053691506385803,
+      "num_tokens": 42220.0,
+      "reward": 0.6875000119209289,
+      "reward_std": 0.5175672590732574,
+      "rewards/reward_fn/mean": 0.6875,
+      "rewards/reward_fn/std": 0.8034753799438477,
+      "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": 146.275,
+      "completions/clipped_ratio": 0.325,
+      "completions/max_length": 256.0,
+      "completions/max_terminated_length": 225.4,
+      "completions/mean_length": 146.275,
+      "completions/mean_terminated_length": 92.8663101196289,
+      "completions/min_length": 32.6,
+      "completions/min_terminated_length": 32.6,
+      "epoch": 1.5,
+      "frac_reward_zero_std": 0.2,
+      "grad_norm": 0.27529817819595337,
+      "kl": 0.01560373855754733,
+      "learning_rate": 9.989068136093873e-05,
+      "loss": 0.010054035484790802,
+      "num_tokens": 69198.0,
+      "reward": 1.1558928728103637,
+      "reward_std": 0.8465379416942597,
+      "rewards/reward_fn/mean": 1.1558928728103637,
+      "rewards/reward_fn/std": 1.1404805421829223,
+      "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": 75.85,
+      "completions/clipped_ratio": 0.05,
+      "completions/max_length": 220.6,
+      "completions/max_terminated_length": 151.0,
+      "completions/mean_length": 75.85,
+      "completions/mean_terminated_length": 66.14857330322266,
+      "completions/min_length": 32.8,
+      "completions/min_terminated_length": 32.8,
+      "epoch": 2.0,
+      "frac_reward_zero_std": 0.35,
+      "grad_norm": 0.353487491607666,
+      "kl": 0.027986684162169696,
+      "learning_rate": 9.944739353007344e-05,
+      "loss": -0.030885905027389526,
+      "num_tokens": 87334.0,
+      "reward": 0.7932142853736878,
+      "reward_std": 0.4118983089923859,
+      "rewards/reward_fn/mean": 0.7932142853736878,
+      "rewards/reward_fn/std": 0.7167340397834778,
+      "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": 90.85,
+      "completions/clipped_ratio": 0.0625,
+      "completions/max_length": 248.0,
+      "completions/max_terminated_length": 216.4,
+      "completions/mean_length": 90.85,
+      "completions/mean_terminated_length": 79.819287109375,
+      "completions/min_length": 28.0,
+      "completions/min_terminated_length": 28.0,
+      "epoch": 2.5,
+      "frac_reward_zero_std": 0.15,
+      "grad_norm": 0.3318491578102112,
+      "kl": 0.04692814685404301,
+      "learning_rate": 9.86663298624003e-05,
+      "loss": 0.05783940553665161,
+      "num_tokens": 108330.0,
+      "reward": 1.1987500190734863,
+      "reward_std": 0.5907092690467834,
+      "rewards/reward_fn/mean": 1.1987500190734863,
+      "rewards/reward_fn/std": 0.9482298731803894,
+      "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": 91.775,
+      "completions/clipped_ratio": 0.125,
+      "completions/max_length": 248.2,
+      "completions/max_terminated_length": 212.6,
+      "completions/mean_length": 91.775,
+      "completions/mean_terminated_length": 68.68722763061524,
+      "completions/min_length": 25.2,
+      "completions/min_terminated_length": 25.2,
+      "epoch": 3.0,
+      "frac_reward_zero_std": 0.4,
+      "grad_norm": 0.24605490267276764,
+      "kl": 0.07254143096506596,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 0.03934891819953919,
+      "num_tokens": 129012.0,
+      "reward": 1.0242857217788697,
+      "reward_std": 0.5802445828914642,
+      "rewards/reward_fn/mean": 1.0242857217788697,
+      "rewards/reward_fn/std": 0.8706011414527893,
+      "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": 59.7875,
+      "completions/clipped_ratio": 0.0375,
+      "completions/max_length": 175.6,
+      "completions/max_terminated_length": 118.4,
+      "completions/mean_length": 59.7875,
+      "completions/mean_terminated_length": 52.19559555053711,
+      "completions/min_length": 25.4,
+      "completions/min_terminated_length": 25.4,
+      "epoch": 3.5,
+      "frac_reward_zero_std": 0.6,
+      "grad_norm": 0.2970605790615082,
+      "kl": 0.053099883161485194,
+      "learning_rate": 9.611448774886924e-05,
+      "loss": 0.06977529525756836,
+      "num_tokens": 147103.0,
+      "reward": 0.9473214387893677,
+      "reward_std": 0.3923970699310303,
+      "rewards/reward_fn/mean": 0.9473214268684387,
+      "rewards/reward_fn/std": 0.649278998374939,
+      "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,
+      "completion_length": 47.85,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 94.8,
+      "completions/max_terminated_length": 94.8,
+      "completions/mean_length": 47.85,
+      "completions/mean_terminated_length": 47.85,
+      "completions/min_length": 31.2,
+      "completions/min_terminated_length": 31.2,
+      "epoch": 4.0,
+      "frac_reward_zero_std": 0.85,
+      "grad_norm": 0.16646049916744232,
+      "kl": 0.056573960930109024,
+      "learning_rate": 9.43611409721806e-05,
+      "loss": -0.0031644195318222047,
+      "num_tokens": 164643.0,
+      "reward": 0.7899999976158142,
+      "reward_std": 0.12681145668029786,
+      "rewards/reward_fn/mean": 0.7899999976158142,
+      "rewards/reward_fn/std": 0.5133758962154389,
+      "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": 49.2625,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 93.6,
+      "completions/max_terminated_length": 93.6,
+      "completions/mean_length": 49.2625,
+      "completions/mean_terminated_length": 49.2625,
+      "completions/min_length": 33.8,
+      "completions/min_terminated_length": 33.8,
+      "epoch": 4.5,
+      "frac_reward_zero_std": 0.6,
+      "grad_norm": 0.3159082531929016,
+      "kl": 0.0353464649990201,
+      "learning_rate": 9.230476262104677e-05,
+      "loss": -0.03417131304740906,
+      "num_tokens": 182568.0,
+      "reward": 0.7924999833106995,
+      "reward_std": 0.3821385264396667,
+      "rewards/reward_fn/mean": 0.7924999833106995,
+      "rewards/reward_fn/std": 0.62625293135643,
+      "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": 58.25,
+      "completions/clipped_ratio": 0.0125,
+      "completions/max_length": 180.6,
+      "completions/max_terminated_length": 153.2,
+      "completions/mean_length": 58.25,
+      "completions/mean_terminated_length": 55.67250061035156,
+      "completions/min_length": 33.2,
+      "completions/min_terminated_length": 33.2,
+      "epoch": 5.0,
+      "frac_reward_zero_std": 0.55,
+      "grad_norm": 0.27360936999320984,
+      "kl": 0.04483541352674365,
+      "learning_rate": 8.995939984474624e-05,
+      "loss": 0.026852786540985107,
+      "num_tokens": 200660.0,
+      "reward": 0.774821424484253,
+      "reward_std": 0.32772802114486693,
+      "rewards/reward_fn/mean": 0.774821424484253,
+      "rewards/reward_fn/std": 0.5432307064533234,
+      "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,
+      "completion_length": 51.225,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 117.4,
+      "completions/max_terminated_length": 117.4,
+      "completions/mean_length": 51.225,
+      "completions/mean_terminated_length": 51.225,
+      "completions/min_length": 36.6,
+      "completions/min_terminated_length": 36.6,
+      "epoch": 5.5,
+      "frac_reward_zero_std": 0.6,
+      "grad_norm": 0.21470840275287628,
+      "kl": 0.04195364024490118,
+      "learning_rate": 8.73410738492077e-05,
+      "loss": 0.023307889699935913,
+      "num_tokens": 218442.0,
+      "reward": 1.0364285826683044,
+      "reward_std": 0.37462076991796495,
+      "rewards/reward_fn/mean": 1.0364285826683044,
+      "rewards/reward_fn/std": 0.6156843721866607,
+      "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,
+      "completion_length": 53.225,
+      "completions/clipped_ratio": 0.0125,
+      "completions/max_length": 159.8,
+      "completions/max_terminated_length": 123.8,
+      "completions/mean_length": 53.225,
+      "completions/mean_terminated_length": 50.68583374023437,
+      "completions/min_length": 33.8,
+      "completions/min_terminated_length": 33.8,
+      "epoch": 6.0,
+      "frac_reward_zero_std": 0.45,
+      "grad_norm": 0.29306381940841675,
+      "kl": 0.05784560404717922,
+      "learning_rate": 8.44676704559283e-05,
+      "loss": 0.015561078488826752,
+      "num_tokens": 236112.0,
+      "reward": 1.1410714387893677,
+      "reward_std": 0.3540264666080475,
+      "rewards/reward_fn/mean": 1.1410714387893677,
+      "rewards/reward_fn/std": 0.607547128200531,
+      "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,
+      "completion_length": 62.2625,
+      "completions/clipped_ratio": 0.05,
+      "completions/max_length": 153.2,
+      "completions/max_terminated_length": 117.4,
+      "completions/mean_length": 62.2625,
+      "completions/mean_terminated_length": 52.46428680419922,
+      "completions/min_length": 30.6,
+      "completions/min_terminated_length": 30.6,
+      "epoch": 6.5,
+      "frac_reward_zero_std": 0.65,
+      "grad_norm": 0.2615426480770111,
+      "kl": 0.09820330440998078,
+      "learning_rate": 8.135881792367686e-05,
+      "loss": 0.04314278066158295,
+      "num_tokens": 254033.0,
+      "reward": 1.2110714197158814,
+      "reward_std": 0.2716316431760788,
+      "rewards/reward_fn/mean": 1.2110714197158814,
+      "rewards/reward_fn/std": 0.6701113641262054,
+      "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,
+      "completion_length": 82.5625,
+      "completions/clipped_ratio": 0.1125,
+      "completions/max_length": 234.4,
+      "completions/max_terminated_length": 147.4,
+      "completions/mean_length": 82.5625,
+      "completions/mean_terminated_length": 60.485835266113284,
+      "completions/min_length": 35.4,
+      "completions/min_terminated_length": 35.4,
+      "epoch": 7.0,
+      "frac_reward_zero_std": 0.6,
+      "grad_norm": 0.1326226145029068,
+      "kl": 0.07194480895996094,
+      "learning_rate": 7.803575286758364e-05,
+      "loss": 0.03152734041213989,
+      "num_tokens": 275222.0,
+      "reward": 1.320892834663391,
+      "reward_std": 0.35234126150608064,
+      "rewards/reward_fn/mean": 1.320892858505249,
+      "rewards/reward_fn/std": 0.676600456237793,
+      "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,
+      "completion_length": 72.7625,
+      "completions/clipped_ratio": 0.0625,
+      "completions/max_length": 220.4,
+      "completions/max_terminated_length": 166.8,
+      "completions/mean_length": 72.7625,
+      "completions/mean_terminated_length": 59.95151138305664,
+      "completions/min_length": 30.2,
+      "completions/min_terminated_length": 30.2,
+      "epoch": 7.5,
+      "frac_reward_zero_std": 0.7,
+      "grad_norm": 0.15138906240463257,
+      "kl": 0.09165919721126556,
+      "learning_rate": 7.452117519152542e-05,
+      "loss": 0.0013809207826852798,
+      "num_tokens": 294407.0,
+      "reward": 1.3473214387893677,
+      "reward_std": 0.17192934565246104,
+      "rewards/reward_fn/mean": 1.3473214387893677,
+      "rewards/reward_fn/std": 0.6935437321662903,
+      "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,
+      "completion_length": 80.9375,
+      "completions/clipped_ratio": 0.125,
+      "completions/max_length": 222.4,
+      "completions/max_terminated_length": 156.0,
+      "completions/mean_length": 80.9375,
+      "completions/mean_terminated_length": 55.99818344116211,
+      "completions/min_length": 31.6,
+      "completions/min_terminated_length": 31.6,
+      "epoch": 8.0,
+      "frac_reward_zero_std": 0.65,
+      "grad_norm": 0.19589942693710327,
+      "kl": 0.0683181069791317,
+      "learning_rate": 7.083909302476453e-05,
+      "loss": 0.033023273944854735,
+      "num_tokens": 314502.0,
+      "reward": 1.1685714244842529,
+      "reward_std": 0.27699449211359023,
+      "rewards/reward_fn/mean": 1.1685714244842529,
+      "rewards/reward_fn/std": 0.5244716942310333,
+      "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,
+      "completion_length": 60.6625,
+      "completions/clipped_ratio": 0.05,
+      "completions/max_length": 207.2,
+      "completions/max_terminated_length": 100.0,
+      "completions/mean_length": 60.6625,
+      "completions/mean_terminated_length": 50.27571563720703,
+      "completions/min_length": 35.2,
+      "completions/min_terminated_length": 35.2,
+      "epoch": 8.5,
+      "frac_reward_zero_std": 0.6,
+      "grad_norm": 0.20066438615322113,
+      "kl": 0.0837025498971343,
+      "learning_rate": 6.701465872208216e-05,
+      "loss": 0.022454433143138885,
+      "num_tokens": 334007.0,
+      "reward": 1.3910714387893677,
+      "reward_std": 0.21785714849829674,
+      "rewards/reward_fn/mean": 1.3910714387893677,
+      "rewards/reward_fn/std": 0.6235540926456451,
+      "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,
+      "completion_length": 54.025,
+      "completions/clipped_ratio": 0.025,
+      "completions/max_length": 143.4,
+      "completions/max_terminated_length": 117.2,
+      "completions/mean_length": 54.025,
+      "completions/mean_terminated_length": 49.025001525878906,
+      "completions/min_length": 30.2,
+      "completions/min_terminated_length": 30.2,
+      "epoch": 9.0,
+      "frac_reward_zero_std": 0.8,
+      "grad_norm": 0.18161360919475555,
+      "kl": 0.05805329587310552,
+      "learning_rate": 6.307399704769099e-05,
+      "loss": -0.04096371531486511,
+      "num_tokens": 351041.0,
+      "reward": 1.24375,
+      "reward_std": 0.2125,
+      "rewards/reward_fn/mean": 1.24375,
+      "rewards/reward_fn/std": 0.584508627653122,
+      "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,
+      "completion_length": 54.65,
+      "completions/clipped_ratio": 0.0125,
+      "completions/max_length": 145.0,
+      "completions/max_terminated_length": 142.2,
+      "completions/mean_length": 54.65,
+      "completions/mean_terminated_length": 52.23083419799805,
+      "completions/min_length": 35.4,
+      "completions/min_terminated_length": 35.4,
+      "epoch": 9.5,
+      "frac_reward_zero_std": 0.9,
+      "grad_norm": 0.10424701869487762,
+      "kl": 0.05452606473118067,
+      "learning_rate": 5.90440267166055e-05,
+      "loss": 0.0021311525255441667,
+      "num_tokens": 368361.0,
+      "reward": 1.1996428489685058,
+      "reward_std": 0.058449314022436735,
+      "rewards/reward_fn/mean": 1.1996428489685058,
+      "rewards/reward_fn/std": 0.4604207634925842,
+      "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,
+      "completion_length": 68.3875,
+      "completions/clipped_ratio": 0.0625,
+      "completions/max_length": 254.4,
+      "completions/max_terminated_length": 140.8,
+      "completions/mean_length": 68.3875,
+      "completions/mean_terminated_length": 55.740359497070315,
+      "completions/min_length": 36.2,
+      "completions/min_terminated_length": 36.2,
+      "epoch": 10.0,
+      "frac_reward_zero_std": 0.75,
+      "grad_norm": 0.13536690175533295,
+      "kl": 0.0854075826704502,
+      "learning_rate": 5.495227651252315e-05,
+      "loss": -0.025432443618774413,
+      "num_tokens": 388400.0,
+      "reward": 1.3283928632736206,
+      "reward_std": 0.2009493112564087,
+      "rewards/reward_fn/mean": 1.3283928632736206,
+      "rewards/reward_fn/std": 0.5586225628852844,
+      "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,
+      "completion_length": 77.6,
+      "completions/clipped_ratio": 0.125,
+      "completions/max_length": 256.0,
+      "completions/max_terminated_length": 115.6,
+      "completions/mean_length": 77.6,
+      "completions/mean_terminated_length": 52.14154052734375,
+      "completions/min_length": 30.4,
+      "completions/min_terminated_length": 30.4,
+      "epoch": 10.5,
+      "frac_reward_zero_std": 0.9,
+      "grad_norm": 0.0006729933083988726,
+      "kl": 0.07917941156774759,
+      "learning_rate": 5.0826697238317935e-05,
+      "loss": -0.0014228260144591332,
+      "num_tokens": 408808.0,
+      "reward": 1.4,
+      "reward_std": 0.1,
+      "rewards/reward_fn/mean": 1.4,
+      "rewards/reward_fn/std": 0.5159838497638702,
+      "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,
+      "completion_length": 71.6375,
+      "completions/clipped_ratio": 0.1,
+      "completions/max_length": 223.8,
+      "completions/max_terminated_length": 125.4,
+      "completions/mean_length": 71.6375,
+      "completions/mean_terminated_length": 50.991825103759766,
+      "completions/min_length": 34.6,
+      "completions/min_terminated_length": 34.6,
+      "epoch": 11.0,
+      "frac_reward_zero_std": 0.85,
+      "grad_norm": 0.1310124397277832,
+      "kl": 0.0553528118878603,
+      "learning_rate": 4.669547078371504e-05,
+      "loss": 0.027294650673866272,
+      "num_tokens": 427787.0,
+      "reward": 1.15,
+      "reward_std": 0.15773502588272095,
+      "rewards/reward_fn/mean": 1.15,
+      "rewards/reward_fn/std": 0.482165002822876,
+      "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,
+      "completion_length": 75.975,
+      "completions/clipped_ratio": 0.1375,
+      "completions/max_length": 214.8,
+      "completions/max_terminated_length": 76.2,
+      "completions/mean_length": 75.975,
+      "completions/mean_terminated_length": 47.73154296875,
+      "completions/min_length": 36.2,
+      "completions/min_terminated_length": 36.2,
+      "epoch": 11.5,
+      "frac_reward_zero_std": 0.9,
+      "grad_norm": 0.001892779255285859,
+      "kl": 0.056033550202846526,
+      "learning_rate": 4.2586817614407895e-05,
+      "loss": -0.03689469993114471,
+      "num_tokens": 447185.0,
+      "reward": 1.2867857217788696,
+      "reward_std": 0.026428571343421935,
+      "rewards/reward_fn/mean": 1.2867857217788696,
+      "rewards/reward_fn/std": 0.3760030448436737,
+      "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,
+      "completion_length": 76.725,
+      "completions/clipped_ratio": 0.1375,
+      "completions/max_length": 218.2,
+      "completions/max_terminated_length": 82.8,
+      "completions/mean_length": 76.725,
+      "completions/mean_terminated_length": 48.34801483154297,
+      "completions/min_length": 30.4,
+      "completions/min_terminated_length": 30.4,
+      "epoch": 12.0,
+      "frac_reward_zero_std": 0.95,
+      "grad_norm": 0.00067809724714607,
+      "kl": 0.06624810677021742,
+      "learning_rate": 3.852880399766243e-05,
+      "loss": 0.005734995752573013,
+      "num_tokens": 466979.0,
+      "reward": 1.325,
+      "reward_std": 0.05,
+      "rewards/reward_fn/mean": 1.325,
+      "rewards/reward_fn/std": 0.4854445576667786,
+      "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,
+      "completion_length": 70.3625,
+      "completions/clipped_ratio": 0.0875,
+      "completions/max_length": 183.8,
+      "completions/max_terminated_length": 99.4,
+      "completions/mean_length": 70.3625,
+      "completions/mean_terminated_length": 52.45879211425781,
+      "completions/min_length": 38.0,
+      "completions/min_terminated_length": 38.0,
+      "epoch": 12.5,
+      "frac_reward_zero_std": 0.9,
+      "grad_norm": 0.0024091172963380814,
+      "kl": 0.0920485682785511,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": -0.03069324791431427,
+      "num_tokens": 486616.0,
+      "reward": 1.3125,
+      "reward_std": 0.075,
+      "rewards/reward_fn/mean": 1.3125,
+      "rewards/reward_fn/std": 0.46982967257499697,
+      "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,
+      "completion_length": 71.8625,
+      "completions/clipped_ratio": 0.1,
+      "completions/max_length": 214.8,
+      "completions/max_terminated_length": 120.2,
+      "completions/mean_length": 71.8625,
+      "completions/mean_terminated_length": 51.76010284423828,
+      "completions/min_length": 33.4,
+      "completions/min_terminated_length": 33.4,
+      "epoch": 13.0,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 0.0004440450284164399,
+      "kl": 0.053088791808113454,
+      "learning_rate": 3.0675041535377405e-05,
+      "loss": 5.229191156104207e-05,
+      "num_tokens": 505905.0,
+      "reward": 1.35,
+      "reward_std": 0.0,
+      "rewards/reward_fn/mean": 1.35,
+      "rewards/reward_fn/std": 0.39928138852119444,
+      "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,
+      "completion_length": 84.5,
+      "completions/clipped_ratio": 0.175,
+      "completions/max_length": 182.8,
+      "completions/max_terminated_length": 76.6,
+      "completions/mean_length": 84.5,
+      "completions/mean_terminated_length": 48.71715393066406,
+      "completions/min_length": 38.0,
+      "completions/min_terminated_length": 38.0,
+      "epoch": 13.5,
+      "frac_reward_zero_std": 0.95,
+      "grad_norm": 0.0007964075193740427,
+      "kl": 0.07870542965829372,
+      "learning_rate": 2.693294185106562e-05,
+      "loss": 0.0014319854788482189,
+      "num_tokens": 526773.0,
+      "reward": 1.3875,
+      "reward_std": 0.025,
+      "rewards/reward_fn/mean": 1.3875,
+      "rewards/reward_fn/std": 0.38874412178993223,
+      "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,
+      "completion_length": 70.6375,
+      "completions/clipped_ratio": 0.1,
+      "completions/max_length": 219.2,
+      "completions/max_terminated_length": 104.2,
+      "completions/mean_length": 70.6375,
+      "completions/mean_terminated_length": 50.06154937744141,
+      "completions/min_length": 37.0,
+      "completions/min_terminated_length": 37.0,
+      "epoch": 14.0,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 0.00017480542010162026,
+      "kl": 0.05223398320376873,
+      "learning_rate": 2.3348413563600325e-05,
+      "loss": 5.521520506590605e-05,
+      "num_tokens": 545864.0,
+      "reward": 1.3,
+      "reward_std": 0.0,
+      "rewards/reward_fn/mean": 1.3,
+      "rewards/reward_fn/std": 0.38544455766677854,
+      "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,
+      "completion_length": 75.7,
+      "completions/clipped_ratio": 0.1125,
+      "completions/max_length": 220.0,
+      "completions/max_terminated_length": 134.4,
+      "completions/mean_length": 75.7,
+      "completions/mean_terminated_length": 52.85439682006836,
+      "completions/min_length": 36.6,
+      "completions/min_terminated_length": 36.6,
+      "epoch": 14.5,
+      "frac_reward_zero_std": 0.95,
+      "grad_norm": 0.0014995499514043331,
+      "kl": 0.061327320709824565,
+      "learning_rate": 1.9945942635848748e-05,
+      "loss": -0.039644479751586914,
+      "num_tokens": 565456.0,
+      "reward": 1.275,
+      "reward_std": 0.05,
+      "rewards/reward_fn/mean": 1.275,
+      "rewards/reward_fn/std": 0.40599284172058103,
+      "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,
+      "completion_length": 88.6875,
+      "completions/clipped_ratio": 0.1875,
+      "completions/max_length": 214.6,
+      "completions/max_terminated_length": 98.8,
+      "completions/mean_length": 88.6875,
+      "completions/mean_terminated_length": 51.92777633666992,
+      "completions/min_length": 35.0,
+      "completions/min_terminated_length": 35.0,
+      "epoch": 15.0,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 0.001117849606089294,
+      "kl": 0.05267696371302009,
+      "learning_rate": 1.6748771394307585e-05,
+      "loss": 6.003726157359779e-05,
+      "num_tokens": 586207.0,
+      "reward": 1.35,
+      "reward_std": 0.0,
+      "rewards/reward_fn/mean": 1.35,
+      "rewards/reward_fn/std": 0.37160772681236265,
+      "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,
+      "completion_length": 78.575,
+      "completions/clipped_ratio": 0.15,
+      "completions/max_length": 219.0,
+      "completions/max_terminated_length": 82.0,
+      "completions/mean_length": 78.575,
+      "completions/mean_terminated_length": 47.18986129760742,
+      "completions/min_length": 33.4,
+      "completions/min_terminated_length": 33.4,
+      "epoch": 15.5,
+      "frac_reward_zero_std": 0.95,
+      "grad_norm": 0.00045852441689930856,
+      "kl": 0.12903956770896913,
+      "learning_rate": 1.3778739760445552e-05,
+      "loss": 0.010452968627214431,
+      "num_tokens": 606445.0,
+      "reward": 1.325,
+      "reward_std": 0.05,
+      "rewards/reward_fn/mean": 1.325,
+      "rewards/reward_fn/std": 0.4198296725749969,
+      "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,
+      "completion_length": 67.5625,
+      "completions/clipped_ratio": 0.0875,
+      "completions/max_length": 181.4,
+      "completions/max_terminated_length": 99.4,
+      "completions/mean_length": 67.5625,
+      "completions/mean_terminated_length": 49.69725341796875,
+      "completions/min_length": 33.4,
+      "completions/min_terminated_length": 33.4,
+      "epoch": 16.0,
+      "frac_reward_zero_std": 0.9,
+      "grad_norm": 0.0011993228690698743,
+      "kl": 0.06518192682415247,
+      "learning_rate": 1.1056136061894384e-05,
+      "loss": -0.039871737360954285,
+      "num_tokens": 624578.0,
+      "reward": 1.20625,
+      "reward_std": 0.0875,
+      "rewards/reward_fn/mean": 1.20625,
+      "rewards/reward_fn/std": 0.33549708127975464,
+      "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,
+      "completion_length": 94.225,
+      "completions/clipped_ratio": 0.2125,
+      "completions/max_length": 256.0,
+      "completions/max_terminated_length": 82.0,
+      "completions/mean_length": 94.225,
+      "completions/mean_terminated_length": 50.561650085449216,
+      "completions/min_length": 37.0,
+      "completions/min_terminated_length": 37.0,
+      "epoch": 16.5,
+      "frac_reward_zero_std": 0.95,
+      "grad_norm": 0.0002106676547555253,
+      "kl": 0.047630924731492996,
+      "learning_rate": 8.599558442598998e-06,
+      "loss": -0.024224117398262024,
+      "num_tokens": 646012.0,
+      "reward": 1.325,
+      "reward_std": 0.05,
+      "rewards/reward_fn/mean": 1.325,
+      "rewards/reward_fn/std": 0.49543556571006775,
+      "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,
+      "completion_length": 78.7625,
+      "completions/clipped_ratio": 0.15,
+      "completions/max_length": 214.8,
+      "completions/max_terminated_length": 95.2,
+      "completions/mean_length": 78.7625,
+      "completions/mean_terminated_length": 47.7126968383789,
+      "completions/min_length": 35.2,
+      "completions/min_terminated_length": 35.2,
+      "epoch": 17.0,
+      "frac_reward_zero_std": 0.9,
+      "grad_norm": 0.28769755363464355,
+      "kl": 0.06921696178615093,
+      "learning_rate": 6.425787818636131e-06,
+      "loss": 0.004652551189064979,
+      "num_tokens": 665597.0,
+      "reward": 1.275,
+      "reward_std": 0.05,
+      "rewards/reward_fn/mean": 1.275,
+      "rewards/reward_fn/std": 0.4579955816268921,
+      "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,
+      "completion_length": 102.5,
+      "completions/clipped_ratio": 0.25,
+      "completions/max_length": 256.0,
+      "completions/max_terminated_length": 97.0,
+      "completions/mean_length": 102.5,
+      "completions/mean_terminated_length": 51.227620697021486,
+      "completions/min_length": 38.6,
+      "completions/min_terminated_length": 38.6,
+      "epoch": 17.5,
+      "frac_reward_zero_std": 0.95,
+      "grad_norm": 0.0012580830371007323,
+      "kl": 0.05462887082248926,
+      "learning_rate": 4.549673247541875e-06,
+      "loss": -0.015973620116710663,
+      "num_tokens": 688689.0,
+      "reward": 1.425,
+      "reward_std": 0.05,
+      "rewards/reward_fn/mean": 1.425,
+      "rewards/reward_fn/std": 0.5231092274188995,
+      "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,
+      "completion_length": 69.5625,
+      "completions/clipped_ratio": 0.1,
+      "completions/max_length": 219.2,
+      "completions/max_terminated_length": 94.4,
+      "completions/mean_length": 69.5625,
+      "completions/mean_terminated_length": 49.011925506591794,
+      "completions/min_length": 35.6,
+      "completions/min_terminated_length": 35.6,
+      "epoch": 18.0,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 0.0015256877522915602,
+      "kl": 0.06085181171074509,
+      "learning_rate": 2.9840304941919415e-06,
+      "loss": 5.7958898833021524e-05,
+      "num_tokens": 706526.0,
+      "reward": 1.2,
+      "reward_std": 0.0,
+      "rewards/reward_fn/mean": 1.2,
+      "rewards/reward_fn/std": 0.35777089595794676,
+      "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,
+      "completion_length": 83.6,
+      "completions/clipped_ratio": 0.1625,
+      "completions/max_length": 235.0,
+      "completions/max_terminated_length": 125.4,
+      "completions/mean_length": 83.6,
+      "completions/mean_terminated_length": 50.05384750366211,
+      "completions/min_length": 31.0,
+      "completions/min_terminated_length": 31.0,
+      "epoch": 18.5,
+      "frac_reward_zero_std": 0.95,
+      "grad_norm": 0.09397394210100174,
+      "kl": 0.07756874859333038,
+      "learning_rate": 1.7395544861325718e-06,
+      "loss": -0.0027227483689785,
+      "num_tokens": 726858.0,
+      "reward": 1.325,
+      "reward_std": 0.05,
+      "rewards/reward_fn/mean": 1.325,
+      "rewards/reward_fn/std": 0.39215601086616514,
+      "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,
+      "completion_length": 101.4,
+      "completions/clipped_ratio": 0.25,
+      "completions/max_length": 214.8,
+      "completions/max_terminated_length": 105.8,
+      "completions/mean_length": 101.4,
+      "completions/mean_terminated_length": 52.382843017578125,
+      "completions/min_length": 36.6,
+      "completions/min_terminated_length": 36.6,
+      "epoch": 19.0,
+      "frac_reward_zero_std": 0.85,
+      "grad_norm": 0.0934695154428482,
+      "kl": 0.06799561325460672,
+      "learning_rate": 8.247462563808817e-07,
+      "loss": -0.010550712794065475,
+      "num_tokens": 748778.0,
+      "reward": 1.304107141494751,
+      "reward_std": 0.0917857151478529,
+      "rewards/reward_fn/mean": 1.304107141494751,
+      "rewards/reward_fn/std": 0.4396756589412689,
+      "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,
+      "completion_length": 78.525,
+      "completions/clipped_ratio": 0.1,
+      "completions/max_length": 181.6,
+      "completions/max_terminated_length": 155.0,
+      "completions/mean_length": 78.525,
+      "completions/mean_terminated_length": 59.155357360839844,
+      "completions/min_length": 33.8,
+      "completions/min_terminated_length": 33.8,
+      "epoch": 19.5,
+      "frac_reward_zero_std": 0.95,
+      "grad_norm": 0.0012224174570292234,
+      "kl": 0.07060394734144211,
+      "learning_rate": 2.458548727494292e-07,
+      "loss": -0.0030293500050902365,
+      "num_tokens": 767928.0,
+      "reward": 1.2375,
+      "reward_std": 0.025,
+      "rewards/reward_fn/mean": 1.2375,
+      "rewards/reward_fn/std": 0.34600183367729187,
+      "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,
+      "completion_length": 88.025,
+      "completions/clipped_ratio": 0.1875,
+      "completions/max_length": 256.0,
+      "completions/max_terminated_length": 98.6,
+      "completions/mean_length": 88.025,
+      "completions/mean_terminated_length": 49.32130355834961,
+      "completions/min_length": 32.4,
+      "completions/min_terminated_length": 32.4,
+      "epoch": 20.0,
+      "frac_reward_zero_std": 0.95,
+      "grad_norm": 0.0738036260008812,
+      "kl": 0.055156406760215757,
+      "learning_rate": 6.834750376549792e-09,
+      "loss": -0.026311689615249635,
+      "num_tokens": 788646.0,
+      "reward": 1.325,
+      "reward_std": 0.05,
+      "rewards/reward_fn/mean": 1.325,
+      "rewards/reward_fn/std": 0.4198296725749969,
+      "step": 200
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 200,
+  "num_input_tokens_seen": 788646,
+  "num_train_epochs": 20,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61516d246785bb4adf93d26e6fe8ffbb65a924b8a03f13b01e1d00b7066140af
+size 6673

checkpoint-50/README.md

@@ -0,0 +1,210 @@
+---
+base_model: unsloth/Qwen2.5-Coder-0.5B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/Qwen2.5-Coder-0.5B-Instruct
+- 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

checkpoint-50/adapter_config.json

@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen2ForCausalLM",
+    "parent_library": "transformers.models.qwen2.modeling_qwen2",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/Qwen2.5-Coder-0.5B-Instruct",
+  "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,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "k_proj",
+    "o_proj",
+    "up_proj",
+    "gate_proj",
+    "q_proj",
+    "down_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-50/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fafa669aaab74afdd4e3f1051bdccce2b9bb721f9b3f98d1cc1c2e321d53cb25
+size 70430032

checkpoint-50/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# 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' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) 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' }}
+{%- endif %}

checkpoint-50/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d97cb0ee5e06ebbb51d7802c576a32012f68786258a8621d55d5c125f8ce2b8b
+size 36139685

checkpoint-50/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f2001ad8fc0f8a681cb2e6e4ea2da8c3ceaffed76150ddb3012314c6f1d9599
+size 14645

checkpoint-50/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cd0e9d505fbc3f97feb166d29026132bdf14eb3e5c7ff77beebc303ee666f96
+size 1383

checkpoint-50/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6ab4a60dabf5285d62294f6dabdfb5eda3b8675d8c862f026b8ef4fa5a2952a
+size 1465

checkpoint-50/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af5891a15588546db1ac7f2baf8fa94835a51a85c032c39793a55bb048b47446
+size 11422523

checkpoint-50/tokenizer_config.json

@@ -0,0 +1,202 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [],
+  "is_local": false,
+  "model_max_length": 32768,
+  "pad_token": "<|PAD_TOKEN|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<|PAD_TOKEN|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  }
+}

checkpoint-50/trainer_state.json

@@ -0,0 +1,304 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "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": 95.85,
+      "completions/clipped_ratio": 0.125,
+      "completions/max_length": 256.0,
+      "completions/max_terminated_length": 195.6,
+      "completions/mean_length": 95.85,
+      "completions/mean_terminated_length": 72.8880989074707,
+      "completions/min_length": 36.6,
+      "completions/min_terminated_length": 36.6,
+      "epoch": 0.5,
+      "frac_reward_zero_std": 0.2,
+      "grad_norm": 0.3041034936904907,
+      "kl": 0.00021898818758927518,
+      "learning_rate": 4e-05,
+      "loss": 0.0329527884721756,
+      "num_tokens": 21444.0,
+      "reward": 0.7767857074737549,
+      "reward_std": 0.7150911569595337,
+      "rewards/reward_fn/mean": 0.7767857074737549,
+      "rewards/reward_fn/std": 0.9959433197975158,
+      "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": 95.1,
+      "completions/clipped_ratio": 0.0875,
+      "completions/max_length": 225.2,
+      "completions/max_terminated_length": 159.2,
+      "completions/mean_length": 95.1,
+      "completions/mean_terminated_length": 80.34466400146485,
+      "completions/min_length": 34.6,
+      "completions/min_terminated_length": 34.6,
+      "epoch": 1.0,
+      "frac_reward_zero_std": 0.4,
+      "grad_norm": 0.2708108425140381,
+      "kl": 0.006061523332027719,
+      "learning_rate": 9e-05,
+      "loss": -0.016053691506385803,
+      "num_tokens": 42220.0,
+      "reward": 0.6875000119209289,
+      "reward_std": 0.5175672590732574,
+      "rewards/reward_fn/mean": 0.6875,
+      "rewards/reward_fn/std": 0.8034753799438477,
+      "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": 146.275,
+      "completions/clipped_ratio": 0.325,
+      "completions/max_length": 256.0,
+      "completions/max_terminated_length": 225.4,
+      "completions/mean_length": 146.275,
+      "completions/mean_terminated_length": 92.8663101196289,
+      "completions/min_length": 32.6,
+      "completions/min_terminated_length": 32.6,
+      "epoch": 1.5,
+      "frac_reward_zero_std": 0.2,
+      "grad_norm": 0.27529817819595337,
+      "kl": 0.01560373855754733,
+      "learning_rate": 9.989068136093873e-05,
+      "loss": 0.010054035484790802,
+      "num_tokens": 69198.0,
+      "reward": 1.1558928728103637,
+      "reward_std": 0.8465379416942597,
+      "rewards/reward_fn/mean": 1.1558928728103637,
+      "rewards/reward_fn/std": 1.1404805421829223,
+      "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": 75.85,
+      "completions/clipped_ratio": 0.05,
+      "completions/max_length": 220.6,
+      "completions/max_terminated_length": 151.0,
+      "completions/mean_length": 75.85,
+      "completions/mean_terminated_length": 66.14857330322266,
+      "completions/min_length": 32.8,
+      "completions/min_terminated_length": 32.8,
+      "epoch": 2.0,
+      "frac_reward_zero_std": 0.35,
+      "grad_norm": 0.353487491607666,
+      "kl": 0.027986684162169696,
+      "learning_rate": 9.944739353007344e-05,
+      "loss": -0.030885905027389526,
+      "num_tokens": 87334.0,
+      "reward": 0.7932142853736878,
+      "reward_std": 0.4118983089923859,
+      "rewards/reward_fn/mean": 0.7932142853736878,
+      "rewards/reward_fn/std": 0.7167340397834778,
+      "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": 90.85,
+      "completions/clipped_ratio": 0.0625,
+      "completions/max_length": 248.0,
+      "completions/max_terminated_length": 216.4,
+      "completions/mean_length": 90.85,
+      "completions/mean_terminated_length": 79.819287109375,
+      "completions/min_length": 28.0,
+      "completions/min_terminated_length": 28.0,
+      "epoch": 2.5,
+      "frac_reward_zero_std": 0.15,
+      "grad_norm": 0.3318491578102112,
+      "kl": 0.04692814685404301,
+      "learning_rate": 9.86663298624003e-05,
+      "loss": 0.05783940553665161,
+      "num_tokens": 108330.0,
+      "reward": 1.1987500190734863,
+      "reward_std": 0.5907092690467834,
+      "rewards/reward_fn/mean": 1.1987500190734863,
+      "rewards/reward_fn/std": 0.9482298731803894,
+      "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": 91.775,
+      "completions/clipped_ratio": 0.125,
+      "completions/max_length": 248.2,
+      "completions/max_terminated_length": 212.6,
+      "completions/mean_length": 91.775,
+      "completions/mean_terminated_length": 68.68722763061524,
+      "completions/min_length": 25.2,
+      "completions/min_terminated_length": 25.2,
+      "epoch": 3.0,
+      "frac_reward_zero_std": 0.4,
+      "grad_norm": 0.24605490267276764,
+      "kl": 0.07254143096506596,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 0.03934891819953919,
+      "num_tokens": 129012.0,
+      "reward": 1.0242857217788697,
+      "reward_std": 0.5802445828914642,
+      "rewards/reward_fn/mean": 1.0242857217788697,
+      "rewards/reward_fn/std": 0.8706011414527893,
+      "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": 59.7875,
+      "completions/clipped_ratio": 0.0375,
+      "completions/max_length": 175.6,
+      "completions/max_terminated_length": 118.4,
+      "completions/mean_length": 59.7875,
+      "completions/mean_terminated_length": 52.19559555053711,
+      "completions/min_length": 25.4,
+      "completions/min_terminated_length": 25.4,
+      "epoch": 3.5,
+      "frac_reward_zero_std": 0.6,
+      "grad_norm": 0.2970605790615082,
+      "kl": 0.053099883161485194,
+      "learning_rate": 9.611448774886924e-05,
+      "loss": 0.06977529525756836,
+      "num_tokens": 147103.0,
+      "reward": 0.9473214387893677,
+      "reward_std": 0.3923970699310303,
+      "rewards/reward_fn/mean": 0.9473214268684387,
+      "rewards/reward_fn/std": 0.649278998374939,
+      "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,
+      "completion_length": 47.85,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 94.8,
+      "completions/max_terminated_length": 94.8,
+      "completions/mean_length": 47.85,
+      "completions/mean_terminated_length": 47.85,
+      "completions/min_length": 31.2,
+      "completions/min_terminated_length": 31.2,
+      "epoch": 4.0,
+      "frac_reward_zero_std": 0.85,
+      "grad_norm": 0.16646049916744232,
+      "kl": 0.056573960930109024,
+      "learning_rate": 9.43611409721806e-05,
+      "loss": -0.0031644195318222047,
+      "num_tokens": 164643.0,
+      "reward": 0.7899999976158142,
+      "reward_std": 0.12681145668029786,
+      "rewards/reward_fn/mean": 0.7899999976158142,
+      "rewards/reward_fn/std": 0.5133758962154389,
+      "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": 49.2625,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 93.6,
+      "completions/max_terminated_length": 93.6,
+      "completions/mean_length": 49.2625,
+      "completions/mean_terminated_length": 49.2625,
+      "completions/min_length": 33.8,
+      "completions/min_terminated_length": 33.8,
+      "epoch": 4.5,
+      "frac_reward_zero_std": 0.6,
+      "grad_norm": 0.3159082531929016,
+      "kl": 0.0353464649990201,
+      "learning_rate": 9.230476262104677e-05,
+      "loss": -0.03417131304740906,
+      "num_tokens": 182568.0,
+      "reward": 0.7924999833106995,
+      "reward_std": 0.3821385264396667,
+      "rewards/reward_fn/mean": 0.7924999833106995,
+      "rewards/reward_fn/std": 0.62625293135643,
+      "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": 58.25,
+      "completions/clipped_ratio": 0.0125,
+      "completions/max_length": 180.6,
+      "completions/max_terminated_length": 153.2,
+      "completions/mean_length": 58.25,
+      "completions/mean_terminated_length": 55.67250061035156,
+      "completions/min_length": 33.2,
+      "completions/min_terminated_length": 33.2,
+      "epoch": 5.0,
+      "frac_reward_zero_std": 0.55,
+      "grad_norm": 0.27360936999320984,
+      "kl": 0.04483541352674365,
+      "learning_rate": 8.995939984474624e-05,
+      "loss": 0.026852786540985107,
+      "num_tokens": 200660.0,
+      "reward": 0.774821424484253,
+      "reward_std": 0.32772802114486693,
+      "rewards/reward_fn/mean": 0.774821424484253,
+      "rewards/reward_fn/std": 0.5432307064533234,
+      "step": 50
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 200,
+  "num_input_tokens_seen": 200660,
+  "num_train_epochs": 20,
+  "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": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-50/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61516d246785bb4adf93d26e6fe8ffbb65a924b8a03f13b01e1d00b7066140af
+size 6673