Upload folder using huggingface_hub

.gitattributes

@@ -75,3 +75,6 @@ coding-0.2/q/iter-5/checkpoint-9/tokenizer.json filter=lfs diff=lfs merge=lfs -t
 coding-0.2/q/latest/checkpoint-9/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 coding-0.2/p/iter-5/checkpoint-9/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 coding-0.2/p/latest/checkpoint-9/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+math-0.3/q/cold-start/checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+math-0.3/q/cold-start/checkpoint-552/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+math-0.3/q/cold-start/tokenizer.json filter=lfs diff=lfs merge=lfs -text

math-0.3/q/cold-start/README.md

@@ -0,0 +1,63 @@
+---
+base_model: unsloth/deepseek-r1-distill-qwen-7b-unsloth-bnb-4bit
+library_name: peft
+model_name: cold-start
+tags:
+- base_model:adapter:unsloth/deepseek-r1-distill-qwen-7b-unsloth-bnb-4bit
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+licence: license
+pipeline_tag: text-generation
+---
+
+# Model Card for cold-start
+
+This model is a fine-tuned version of [unsloth/deepseek-r1-distill-qwen-7b-unsloth-bnb-4bit](https://huggingface.co/unsloth/deepseek-r1-distill-qwen-7b-unsloth-bnb-4bit).
+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
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/kstaron-/huggingface/runs/0a0r1jt2) 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- PEFT 0.18.0
+- TRL: 0.23.0
+- Transformers: 4.57.1
+- Pytorch: 2.9.0
+- Datasets: 4.3.0
+- Tokenizers: 0.22.1
+
+## Citations
+
+
+
+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}}
+}
+```

math-0.3/q/cold-start/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/deepseek-r1-distill-qwen-7b-unsloth-bnb-4bit",
+  "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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "down_proj",
+    "o_proj",
+    "gate_proj",
+    "k_proj",
+    "v_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

math-0.3/q/cold-start/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94d5b6cd5299f660d359568c0f22228f42d3ef072292064edda72e9de915a8e1
+size 645975704

math-0.3/q/cold-start/chat_template.jinja

@@ -0,0 +1 @@
+{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜><think>\n'}}{% endif %}

math-0.3/q/cold-start/checkpoint-500/README.md

@@ -0,0 +1,210 @@
+---
+base_model: unsloth/deepseek-r1-distill-qwen-7b-unsloth-bnb-4bit
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/deepseek-r1-distill-qwen-7b-unsloth-bnb-4bit
+- lora
+- sft
+- 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 0.18.0

math-0.3/q/cold-start/checkpoint-500/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/deepseek-r1-distill-qwen-7b-unsloth-bnb-4bit",
+  "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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "down_proj",
+    "o_proj",
+    "gate_proj",
+    "k_proj",
+    "v_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

math-0.3/q/cold-start/checkpoint-500/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2067e4a1641909c485bb7640f1959d609dede693abe89505fddd5fa326e8230
+size 645975704

math-0.3/q/cold-start/checkpoint-500/chat_template.jinja

@@ -0,0 +1 @@
+{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜><think>\n'}}{% endif %}

math-0.3/q/cold-start/checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b993ff13f5c8df8121f8f376c1e822809672c8b3d1ddabb9147e7954f49aa5f2
+size 1292182139

math-0.3/q/cold-start/checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61c19bab1174704a4a4441475683bf1270277af15d2e2c95e964789128e482c4
+size 14645

math-0.3/q/cold-start/checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5fb2bb82f06e04509c103bfe5002034eaa769749473fedb0fd057d03114a3f0
+size 1465

math-0.3/q/cold-start/checkpoint-500/special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|vision_pad|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

math-0.3/q/cold-start/checkpoint-500/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
+size 11422778

math-0.3/q/cold-start/checkpoint-500/tokenizer_config.json

@@ -0,0 +1,195 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<｜User｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151645": {
+      "content": "<｜Assistant｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151646": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151648": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151649": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 131072,
+  "pad_token": "<|vision_pad|>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizerFast",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}

math-0.3/q/cold-start/checkpoint-500/trainer_state.json

@@ -0,0 +1,741 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9066183136899365,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.001813236627379873,
+      "grad_norm": 0.18317382037639618,
+      "learning_rate": 0.0,
+      "loss": 1.1339,
+      "step": 1
+    },
+    {
+      "epoch": 0.009066183136899365,
+      "grad_norm": 0.19014385342597961,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 1.1362,
+      "step": 5
+    },
+    {
+      "epoch": 0.01813236627379873,
+      "grad_norm": 0.18670743703842163,
+      "learning_rate": 4.5e-06,
+      "loss": 1.1395,
+      "step": 10
+    },
+    {
+      "epoch": 0.027198549410698096,
+      "grad_norm": 0.19530165195465088,
+      "learning_rate": 7.000000000000001e-06,
+      "loss": 1.1467,
+      "step": 15
+    },
+    {
+      "epoch": 0.03626473254759746,
+      "grad_norm": 0.20222850143909454,
+      "learning_rate": 9.5e-06,
+      "loss": 1.1283,
+      "step": 20
+    },
+    {
+      "epoch": 0.04533091568449683,
+      "grad_norm": 0.22455056011676788,
+      "learning_rate": 1.2e-05,
+      "loss": 1.1076,
+      "step": 25
+    },
+    {
+      "epoch": 0.05439709882139619,
+      "grad_norm": 0.19117270410060883,
+      "learning_rate": 1.45e-05,
+      "loss": 1.0447,
+      "step": 30
+    },
+    {
+      "epoch": 0.06346328195829556,
+      "grad_norm": 0.1589159220457077,
+      "learning_rate": 1.7000000000000003e-05,
+      "loss": 0.983,
+      "step": 35
+    },
+    {
+      "epoch": 0.07252946509519492,
+      "grad_norm": 0.17458510398864746,
+      "learning_rate": 1.9500000000000003e-05,
+      "loss": 0.9144,
+      "step": 40
+    },
+    {
+      "epoch": 0.0815956482320943,
+      "grad_norm": 0.12688010931015015,
+      "learning_rate": 2.2000000000000003e-05,
+      "loss": 0.8658,
+      "step": 45
+    },
+    {
+      "epoch": 0.09066183136899365,
+      "grad_norm": 0.11761180311441422,
+      "learning_rate": 2.45e-05,
+      "loss": 0.8108,
+      "step": 50
+    },
+    {
+      "epoch": 0.09972801450589303,
+      "grad_norm": 0.09990847110748291,
+      "learning_rate": 2.7000000000000002e-05,
+      "loss": 0.7625,
+      "step": 55
+    },
+    {
+      "epoch": 0.10879419764279238,
+      "grad_norm": 0.08706934750080109,
+      "learning_rate": 2.95e-05,
+      "loss": 0.7197,
+      "step": 60
+    },
+    {
+      "epoch": 0.11786038077969176,
+      "grad_norm": 0.08221345394849777,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 0.6746,
+      "step": 65
+    },
+    {
+      "epoch": 0.12692656391659113,
+      "grad_norm": 0.08015955239534378,
+      "learning_rate": 3.45e-05,
+      "loss": 0.6452,
+      "step": 70
+    },
+    {
+      "epoch": 0.1359927470534905,
+      "grad_norm": 0.07011060416698456,
+      "learning_rate": 3.7e-05,
+      "loss": 0.6177,
+      "step": 75
+    },
+    {
+      "epoch": 0.14505893019038985,
+      "grad_norm": 0.05959406867623329,
+      "learning_rate": 3.9500000000000005e-05,
+      "loss": 0.5953,
+      "step": 80
+    },
+    {
+      "epoch": 0.1541251133272892,
+      "grad_norm": 0.05818222835659981,
+      "learning_rate": 4.2e-05,
+      "loss": 0.5781,
+      "step": 85
+    },
+    {
+      "epoch": 0.1631912964641886,
+      "grad_norm": 0.05439260974526405,
+      "learning_rate": 4.4500000000000004e-05,
+      "loss": 0.5632,
+      "step": 90
+    },
+    {
+      "epoch": 0.17225747960108795,
+      "grad_norm": 0.05923071876168251,
+      "learning_rate": 4.7e-05,
+      "loss": 0.5538,
+      "step": 95
+    },
+    {
+      "epoch": 0.1813236627379873,
+      "grad_norm": 0.05596950650215149,
+      "learning_rate": 4.9500000000000004e-05,
+      "loss": 0.5491,
+      "step": 100
+    },
+    {
+      "epoch": 0.19038984587488667,
+      "grad_norm": 0.052493926137685776,
+      "learning_rate": 4.955752212389381e-05,
+      "loss": 0.5217,
+      "step": 105
+    },
+    {
+      "epoch": 0.19945602901178605,
+      "grad_norm": 0.04704424366354942,
+      "learning_rate": 4.900442477876107e-05,
+      "loss": 0.5173,
+      "step": 110
+    },
+    {
+      "epoch": 0.2085222121486854,
+      "grad_norm": 0.0472424179315567,
+      "learning_rate": 4.845132743362832e-05,
+      "loss": 0.514,
+      "step": 115
+    },
+    {
+      "epoch": 0.21758839528558477,
+      "grad_norm": 0.04862270504236221,
+      "learning_rate": 4.789823008849558e-05,
+      "loss": 0.5103,
+      "step": 120
+    },
+    {
+      "epoch": 0.22665457842248413,
+      "grad_norm": 0.04707098752260208,
+      "learning_rate": 4.734513274336283e-05,
+      "loss": 0.5039,
+      "step": 125
+    },
+    {
+      "epoch": 0.2357207615593835,
+      "grad_norm": 0.05026312544941902,
+      "learning_rate": 4.679203539823009e-05,
+      "loss": 0.4978,
+      "step": 130
+    },
+    {
+      "epoch": 0.24478694469628287,
+      "grad_norm": 0.054734013974666595,
+      "learning_rate": 4.6238938053097344e-05,
+      "loss": 0.4941,
+      "step": 135
+    },
+    {
+      "epoch": 0.25385312783318226,
+      "grad_norm": 0.0561821311712265,
+      "learning_rate": 4.56858407079646e-05,
+      "loss": 0.4879,
+      "step": 140
+    },
+    {
+      "epoch": 0.2629193109700816,
+      "grad_norm": 0.05934757739305496,
+      "learning_rate": 4.5132743362831855e-05,
+      "loss": 0.4877,
+      "step": 145
+    },
+    {
+      "epoch": 0.271985494106981,
+      "grad_norm": 0.057985540479421616,
+      "learning_rate": 4.4579646017699114e-05,
+      "loss": 0.484,
+      "step": 150
+    },
+    {
+      "epoch": 0.2810516772438803,
+      "grad_norm": 0.054954368621110916,
+      "learning_rate": 4.4026548672566373e-05,
+      "loss": 0.4728,
+      "step": 155
+    },
+    {
+      "epoch": 0.2901178603807797,
+      "grad_norm": 0.056278448551893234,
+      "learning_rate": 4.3473451327433626e-05,
+      "loss": 0.4768,
+      "step": 160
+    },
+    {
+      "epoch": 0.2991840435176791,
+      "grad_norm": 0.061460211873054504,
+      "learning_rate": 4.2920353982300885e-05,
+      "loss": 0.4752,
+      "step": 165
+    },
+    {
+      "epoch": 0.3082502266545784,
+      "grad_norm": 0.06386470794677734,
+      "learning_rate": 4.2367256637168144e-05,
+      "loss": 0.4665,
+      "step": 170
+    },
+    {
+      "epoch": 0.3173164097914778,
+      "grad_norm": 0.06866438686847687,
+      "learning_rate": 4.1814159292035396e-05,
+      "loss": 0.4664,
+      "step": 175
+    },
+    {
+      "epoch": 0.3263825929283772,
+      "grad_norm": 0.06411902606487274,
+      "learning_rate": 4.1261061946902655e-05,
+      "loss": 0.4656,
+      "step": 180
+    },
+    {
+      "epoch": 0.3354487760652765,
+      "grad_norm": 0.0692601427435875,
+      "learning_rate": 4.0707964601769914e-05,
+      "loss": 0.4638,
+      "step": 185
+    },
+    {
+      "epoch": 0.3445149592021759,
+      "grad_norm": 0.06713596731424332,
+      "learning_rate": 4.015486725663717e-05,
+      "loss": 0.4574,
+      "step": 190
+    },
+    {
+      "epoch": 0.3535811423390752,
+      "grad_norm": 0.07020549476146698,
+      "learning_rate": 3.9601769911504426e-05,
+      "loss": 0.4535,
+      "step": 195
+    },
+    {
+      "epoch": 0.3626473254759746,
+      "grad_norm": 0.07310190051794052,
+      "learning_rate": 3.9048672566371685e-05,
+      "loss": 0.4569,
+      "step": 200
+    },
+    {
+      "epoch": 0.371713508612874,
+      "grad_norm": 0.06643065065145493,
+      "learning_rate": 3.849557522123894e-05,
+      "loss": 0.4483,
+      "step": 205
+    },
+    {
+      "epoch": 0.38077969174977333,
+      "grad_norm": 0.07110671699047089,
+      "learning_rate": 3.7942477876106196e-05,
+      "loss": 0.4513,
+      "step": 210
+    },
+    {
+      "epoch": 0.3898458748866727,
+      "grad_norm": 0.08371982723474503,
+      "learning_rate": 3.7389380530973455e-05,
+      "loss": 0.4468,
+      "step": 215
+    },
+    {
+      "epoch": 0.3989120580235721,
+      "grad_norm": 0.0777554139494896,
+      "learning_rate": 3.683628318584071e-05,
+      "loss": 0.447,
+      "step": 220
+    },
+    {
+      "epoch": 0.40797824116047143,
+      "grad_norm": 0.06965522468090057,
+      "learning_rate": 3.628318584070797e-05,
+      "loss": 0.4434,
+      "step": 225
+    },
+    {
+      "epoch": 0.4170444242973708,
+      "grad_norm": 0.0734223872423172,
+      "learning_rate": 3.573008849557522e-05,
+      "loss": 0.4457,
+      "step": 230
+    },
+    {
+      "epoch": 0.42611060743427015,
+      "grad_norm": 0.0682050958275795,
+      "learning_rate": 3.517699115044248e-05,
+      "loss": 0.4434,
+      "step": 235
+    },
+    {
+      "epoch": 0.43517679057116954,
+      "grad_norm": 0.08661296963691711,
+      "learning_rate": 3.462389380530974e-05,
+      "loss": 0.449,
+      "step": 240
+    },
+    {
+      "epoch": 0.4442429737080689,
+      "grad_norm": 0.08436290174722672,
+      "learning_rate": 3.407079646017699e-05,
+      "loss": 0.4457,
+      "step": 245
+    },
+    {
+      "epoch": 0.45330915684496825,
+      "grad_norm": 0.07421322166919708,
+      "learning_rate": 3.351769911504425e-05,
+      "loss": 0.4419,
+      "step": 250
+    },
+    {
+      "epoch": 0.46237533998186764,
+      "grad_norm": 0.0795440748333931,
+      "learning_rate": 3.296460176991151e-05,
+      "loss": 0.4447,
+      "step": 255
+    },
+    {
+      "epoch": 0.471441523118767,
+      "grad_norm": 0.07894603908061981,
+      "learning_rate": 3.241150442477876e-05,
+      "loss": 0.443,
+      "step": 260
+    },
+    {
+      "epoch": 0.48050770625566636,
+      "grad_norm": 0.07290520519018173,
+      "learning_rate": 3.185840707964602e-05,
+      "loss": 0.4345,
+      "step": 265
+    },
+    {
+      "epoch": 0.48957388939256574,
+      "grad_norm": 0.07478918135166168,
+      "learning_rate": 3.130530973451328e-05,
+      "loss": 0.4402,
+      "step": 270
+    },
+    {
+      "epoch": 0.4986400725294651,
+      "grad_norm": 0.09009527415037155,
+      "learning_rate": 3.075221238938053e-05,
+      "loss": 0.4332,
+      "step": 275
+    },
+    {
+      "epoch": 0.5077062556663645,
+      "grad_norm": 0.08838801831007004,
+      "learning_rate": 3.019911504424779e-05,
+      "loss": 0.4383,
+      "step": 280
+    },
+    {
+      "epoch": 0.5167724388032638,
+      "grad_norm": 0.07192256301641464,
+      "learning_rate": 2.964601769911505e-05,
+      "loss": 0.4313,
+      "step": 285
+    },
+    {
+      "epoch": 0.5258386219401632,
+      "grad_norm": 0.07938144356012344,
+      "learning_rate": 2.90929203539823e-05,
+      "loss": 0.4327,
+      "step": 290
+    },
+    {
+      "epoch": 0.5349048050770625,
+      "grad_norm": 0.08160530030727386,
+      "learning_rate": 2.853982300884956e-05,
+      "loss": 0.4326,
+      "step": 295
+    },
+    {
+      "epoch": 0.543970988213962,
+      "grad_norm": 0.09404582530260086,
+      "learning_rate": 2.7986725663716816e-05,
+      "loss": 0.4326,
+      "step": 300
+    },
+    {
+      "epoch": 0.5530371713508613,
+      "grad_norm": 0.07616602629423141,
+      "learning_rate": 2.743362831858407e-05,
+      "loss": 0.4249,
+      "step": 305
+    },
+    {
+      "epoch": 0.5621033544877606,
+      "grad_norm": 0.08184757083654404,
+      "learning_rate": 2.688053097345133e-05,
+      "loss": 0.4292,
+      "step": 310
+    },
+    {
+      "epoch": 0.57116953762466,
+      "grad_norm": 0.09085652232170105,
+      "learning_rate": 2.6327433628318586e-05,
+      "loss": 0.4326,
+      "step": 315
+    },
+    {
+      "epoch": 0.5802357207615594,
+      "grad_norm": 0.07777532935142517,
+      "learning_rate": 2.5774336283185842e-05,
+      "loss": 0.4256,
+      "step": 320
+    },
+    {
+      "epoch": 0.5893019038984587,
+      "grad_norm": 0.08594377338886261,
+      "learning_rate": 2.5221238938053098e-05,
+      "loss": 0.4314,
+      "step": 325
+    },
+    {
+      "epoch": 0.5983680870353582,
+      "grad_norm": 0.08091574907302856,
+      "learning_rate": 2.4668141592920353e-05,
+      "loss": 0.4243,
+      "step": 330
+    },
+    {
+      "epoch": 0.6074342701722575,
+      "grad_norm": 0.0800497829914093,
+      "learning_rate": 2.411504424778761e-05,
+      "loss": 0.4336,
+      "step": 335
+    },
+    {
+      "epoch": 0.6165004533091568,
+      "grad_norm": 0.08816388249397278,
+      "learning_rate": 2.3561946902654868e-05,
+      "loss": 0.4297,
+      "step": 340
+    },
+    {
+      "epoch": 0.6255666364460563,
+      "grad_norm": 0.08167457580566406,
+      "learning_rate": 2.3008849557522124e-05,
+      "loss": 0.4248,
+      "step": 345
+    },
+    {
+      "epoch": 0.6346328195829556,
+      "grad_norm": 0.09383154660463333,
+      "learning_rate": 2.245575221238938e-05,
+      "loss": 0.4262,
+      "step": 350
+    },
+    {
+      "epoch": 0.6436990027198549,
+      "grad_norm": 0.08120961487293243,
+      "learning_rate": 2.190265486725664e-05,
+      "loss": 0.4293,
+      "step": 355
+    },
+    {
+      "epoch": 0.6527651858567544,
+      "grad_norm": 0.08866537362337112,
+      "learning_rate": 2.1349557522123894e-05,
+      "loss": 0.4269,
+      "step": 360
+    },
+    {
+      "epoch": 0.6618313689936537,
+      "grad_norm": 0.08616868406534195,
+      "learning_rate": 2.079646017699115e-05,
+      "loss": 0.4252,
+      "step": 365
+    },
+    {
+      "epoch": 0.670897552130553,
+      "grad_norm": 0.08172861486673355,
+      "learning_rate": 2.024336283185841e-05,
+      "loss": 0.42,
+      "step": 370
+    },
+    {
+      "epoch": 0.6799637352674524,
+      "grad_norm": 0.08940409123897552,
+      "learning_rate": 1.9690265486725665e-05,
+      "loss": 0.4238,
+      "step": 375
+    },
+    {
+      "epoch": 0.6890299184043518,
+      "grad_norm": 0.09020205587148666,
+      "learning_rate": 1.913716814159292e-05,
+      "loss": 0.4298,
+      "step": 380
+    },
+    {
+      "epoch": 0.6980961015412511,
+      "grad_norm": 0.08593279123306274,
+      "learning_rate": 1.858407079646018e-05,
+      "loss": 0.4222,
+      "step": 385
+    },
+    {
+      "epoch": 0.7071622846781505,
+      "grad_norm": 0.08001919090747833,
+      "learning_rate": 1.8030973451327435e-05,
+      "loss": 0.4267,
+      "step": 390
+    },
+    {
+      "epoch": 0.7162284678150499,
+      "grad_norm": 0.0805264338850975,
+      "learning_rate": 1.747787610619469e-05,
+      "loss": 0.4249,
+      "step": 395
+    },
+    {
+      "epoch": 0.7252946509519492,
+      "grad_norm": 0.08267470449209213,
+      "learning_rate": 1.692477876106195e-05,
+      "loss": 0.4268,
+      "step": 400
+    },
+    {
+      "epoch": 0.7343608340888486,
+      "grad_norm": 0.08514878898859024,
+      "learning_rate": 1.6371681415929206e-05,
+      "loss": 0.4211,
+      "step": 405
+    },
+    {
+      "epoch": 0.743427017225748,
+      "grad_norm": 0.08745454996824265,
+      "learning_rate": 1.581858407079646e-05,
+      "loss": 0.4182,
+      "step": 410
+    },
+    {
+      "epoch": 0.7524932003626473,
+      "grad_norm": 0.07666044682264328,
+      "learning_rate": 1.5265486725663717e-05,
+      "loss": 0.421,
+      "step": 415
+    },
+    {
+      "epoch": 0.7615593834995467,
+      "grad_norm": 0.07890937477350235,
+      "learning_rate": 1.4712389380530974e-05,
+      "loss": 0.425,
+      "step": 420
+    },
+    {
+      "epoch": 0.7706255666364461,
+      "grad_norm": 0.0812554880976677,
+      "learning_rate": 1.415929203539823e-05,
+      "loss": 0.4184,
+      "step": 425
+    },
+    {
+      "epoch": 0.7796917497733454,
+      "grad_norm": 0.078528992831707,
+      "learning_rate": 1.3606194690265486e-05,
+      "loss": 0.4181,
+      "step": 430
+    },
+    {
+      "epoch": 0.7887579329102448,
+      "grad_norm": 0.0815301239490509,
+      "learning_rate": 1.3053097345132745e-05,
+      "loss": 0.4217,
+      "step": 435
+    },
+    {
+      "epoch": 0.7978241160471442,
+      "grad_norm": 0.08107589185237885,
+      "learning_rate": 1.25e-05,
+      "loss": 0.4227,
+      "step": 440
+    },
+    {
+      "epoch": 0.8068902991840435,
+      "grad_norm": 0.07778468728065491,
+      "learning_rate": 1.1946902654867258e-05,
+      "loss": 0.4162,
+      "step": 445
+    },
+    {
+      "epoch": 0.8159564823209429,
+      "grad_norm": 0.08603918552398682,
+      "learning_rate": 1.1393805309734514e-05,
+      "loss": 0.4203,
+      "step": 450
+    },
+    {
+      "epoch": 0.8250226654578422,
+      "grad_norm": 0.08256816864013672,
+      "learning_rate": 1.0840707964601771e-05,
+      "loss": 0.4222,
+      "step": 455
+    },
+    {
+      "epoch": 0.8340888485947416,
+      "grad_norm": 0.07872200012207031,
+      "learning_rate": 1.0287610619469027e-05,
+      "loss": 0.4176,
+      "step": 460
+    },
+    {
+      "epoch": 0.843155031731641,
+      "grad_norm": 0.09151720255613327,
+      "learning_rate": 9.734513274336284e-06,
+      "loss": 0.4144,
+      "step": 465
+    },
+    {
+      "epoch": 0.8522212148685403,
+      "grad_norm": 0.07890870422124863,
+      "learning_rate": 9.18141592920354e-06,
+      "loss": 0.4158,
+      "step": 470
+    },
+    {
+      "epoch": 0.8612873980054397,
+      "grad_norm": 0.0838795080780983,
+      "learning_rate": 8.628318584070797e-06,
+      "loss": 0.415,
+      "step": 475
+    },
+    {
+      "epoch": 0.8703535811423391,
+      "grad_norm": 0.08289153128862381,
+      "learning_rate": 8.075221238938053e-06,
+      "loss": 0.4215,
+      "step": 480
+    },
+    {
+      "epoch": 0.8794197642792384,
+      "grad_norm": 0.08027064800262451,
+      "learning_rate": 7.52212389380531e-06,
+      "loss": 0.4221,
+      "step": 485
+    },
+    {
+      "epoch": 0.8884859474161378,
+      "grad_norm": 0.08152059465646744,
+      "learning_rate": 6.969026548672566e-06,
+      "loss": 0.4261,
+      "step": 490
+    },
+    {
+      "epoch": 0.8975521305530372,
+      "grad_norm": 0.07868578284978867,
+      "learning_rate": 6.415929203539823e-06,
+      "loss": 0.4172,
+      "step": 495
+    },
+    {
+      "epoch": 0.9066183136899365,
+      "grad_norm": 0.07779107242822647,
+      "learning_rate": 5.86283185840708e-06,
+      "loss": 0.4188,
+      "step": 500
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 552,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.5547217133568e+18,
+  "train_batch_size": 80,
+  "trial_name": null,
+  "trial_params": null
+}

math-0.3/q/cold-start/checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:919445c33dece1f2a0d2869618b9c492eee43c4ddeb84be6b31bb3ca5243967b
+size 6289

math-0.3/q/cold-start/checkpoint-552/README.md

@@ -0,0 +1,210 @@
+---
+base_model: unsloth/deepseek-r1-distill-qwen-7b-unsloth-bnb-4bit
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/deepseek-r1-distill-qwen-7b-unsloth-bnb-4bit
+- lora
+- sft
+- 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 0.18.0

math-0.3/q/cold-start/checkpoint-552/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/deepseek-r1-distill-qwen-7b-unsloth-bnb-4bit",
+  "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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "down_proj",
+    "o_proj",
+    "gate_proj",
+    "k_proj",
+    "v_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

math-0.3/q/cold-start/checkpoint-552/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94d5b6cd5299f660d359568c0f22228f42d3ef072292064edda72e9de915a8e1
+size 645975704

math-0.3/q/cold-start/checkpoint-552/chat_template.jinja

@@ -0,0 +1 @@
+{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜><think>\n'}}{% endif %}

math-0.3/q/cold-start/checkpoint-552/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae6066df8e77138be4dabf6a5c354ff8adb2b36350d8461165de0740abad5779
+size 1292182139

math-0.3/q/cold-start/checkpoint-552/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61c19bab1174704a4a4441475683bf1270277af15d2e2c95e964789128e482c4
+size 14645

math-0.3/q/cold-start/checkpoint-552/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b569a6ef6e8eaaf868e02bd0c05974d7a6e565263830e0d485c37c528de7f98
+size 1465

math-0.3/q/cold-start/checkpoint-552/special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|vision_pad|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

math-0.3/q/cold-start/checkpoint-552/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
+size 11422778

math-0.3/q/cold-start/checkpoint-552/tokenizer_config.json

@@ -0,0 +1,195 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<｜User｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151645": {
+      "content": "<｜Assistant｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151646": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151648": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151649": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 131072,
+  "pad_token": "<|vision_pad|>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizerFast",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}

math-0.3/q/cold-start/checkpoint-552/trainer_state.json

@@ -0,0 +1,811 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 552,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.001813236627379873,
+      "grad_norm": 0.18317382037639618,
+      "learning_rate": 0.0,
+      "loss": 1.1339,
+      "step": 1
+    },
+    {
+      "epoch": 0.009066183136899365,
+      "grad_norm": 0.19014385342597961,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 1.1362,
+      "step": 5
+    },
+    {
+      "epoch": 0.01813236627379873,
+      "grad_norm": 0.18670743703842163,
+      "learning_rate": 4.5e-06,
+      "loss": 1.1395,
+      "step": 10
+    },
+    {
+      "epoch": 0.027198549410698096,
+      "grad_norm": 0.19530165195465088,
+      "learning_rate": 7.000000000000001e-06,
+      "loss": 1.1467,
+      "step": 15
+    },
+    {
+      "epoch": 0.03626473254759746,
+      "grad_norm": 0.20222850143909454,
+      "learning_rate": 9.5e-06,
+      "loss": 1.1283,
+      "step": 20
+    },
+    {
+      "epoch": 0.04533091568449683,
+      "grad_norm": 0.22455056011676788,
+      "learning_rate": 1.2e-05,
+      "loss": 1.1076,
+      "step": 25
+    },
+    {
+      "epoch": 0.05439709882139619,
+      "grad_norm": 0.19117270410060883,
+      "learning_rate": 1.45e-05,
+      "loss": 1.0447,
+      "step": 30
+    },
+    {
+      "epoch": 0.06346328195829556,
+      "grad_norm": 0.1589159220457077,
+      "learning_rate": 1.7000000000000003e-05,
+      "loss": 0.983,
+      "step": 35
+    },
+    {
+      "epoch": 0.07252946509519492,
+      "grad_norm": 0.17458510398864746,
+      "learning_rate": 1.9500000000000003e-05,
+      "loss": 0.9144,
+      "step": 40
+    },
+    {
+      "epoch": 0.0815956482320943,
+      "grad_norm": 0.12688010931015015,
+      "learning_rate": 2.2000000000000003e-05,
+      "loss": 0.8658,
+      "step": 45
+    },
+    {
+      "epoch": 0.09066183136899365,
+      "grad_norm": 0.11761180311441422,
+      "learning_rate": 2.45e-05,
+      "loss": 0.8108,
+      "step": 50
+    },
+    {
+      "epoch": 0.09972801450589303,
+      "grad_norm": 0.09990847110748291,
+      "learning_rate": 2.7000000000000002e-05,
+      "loss": 0.7625,
+      "step": 55
+    },
+    {
+      "epoch": 0.10879419764279238,
+      "grad_norm": 0.08706934750080109,
+      "learning_rate": 2.95e-05,
+      "loss": 0.7197,
+      "step": 60
+    },
+    {
+      "epoch": 0.11786038077969176,
+      "grad_norm": 0.08221345394849777,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 0.6746,
+      "step": 65
+    },
+    {
+      "epoch": 0.12692656391659113,
+      "grad_norm": 0.08015955239534378,
+      "learning_rate": 3.45e-05,
+      "loss": 0.6452,
+      "step": 70
+    },
+    {
+      "epoch": 0.1359927470534905,
+      "grad_norm": 0.07011060416698456,
+      "learning_rate": 3.7e-05,
+      "loss": 0.6177,
+      "step": 75
+    },
+    {
+      "epoch": 0.14505893019038985,
+      "grad_norm": 0.05959406867623329,
+      "learning_rate": 3.9500000000000005e-05,
+      "loss": 0.5953,
+      "step": 80
+    },
+    {
+      "epoch": 0.1541251133272892,
+      "grad_norm": 0.05818222835659981,
+      "learning_rate": 4.2e-05,
+      "loss": 0.5781,
+      "step": 85
+    },
+    {
+      "epoch": 0.1631912964641886,
+      "grad_norm": 0.05439260974526405,
+      "learning_rate": 4.4500000000000004e-05,
+      "loss": 0.5632,
+      "step": 90
+    },
+    {
+      "epoch": 0.17225747960108795,
+      "grad_norm": 0.05923071876168251,
+      "learning_rate": 4.7e-05,
+      "loss": 0.5538,
+      "step": 95
+    },
+    {
+      "epoch": 0.1813236627379873,
+      "grad_norm": 0.05596950650215149,
+      "learning_rate": 4.9500000000000004e-05,
+      "loss": 0.5491,
+      "step": 100
+    },
+    {
+      "epoch": 0.19038984587488667,
+      "grad_norm": 0.052493926137685776,
+      "learning_rate": 4.955752212389381e-05,
+      "loss": 0.5217,
+      "step": 105
+    },
+    {
+      "epoch": 0.19945602901178605,
+      "grad_norm": 0.04704424366354942,
+      "learning_rate": 4.900442477876107e-05,
+      "loss": 0.5173,
+      "step": 110
+    },
+    {
+      "epoch": 0.2085222121486854,
+      "grad_norm": 0.0472424179315567,
+      "learning_rate": 4.845132743362832e-05,
+      "loss": 0.514,
+      "step": 115
+    },
+    {
+      "epoch": 0.21758839528558477,
+      "grad_norm": 0.04862270504236221,
+      "learning_rate": 4.789823008849558e-05,
+      "loss": 0.5103,
+      "step": 120
+    },
+    {
+      "epoch": 0.22665457842248413,
+      "grad_norm": 0.04707098752260208,
+      "learning_rate": 4.734513274336283e-05,
+      "loss": 0.5039,
+      "step": 125
+    },
+    {
+      "epoch": 0.2357207615593835,
+      "grad_norm": 0.05026312544941902,
+      "learning_rate": 4.679203539823009e-05,
+      "loss": 0.4978,
+      "step": 130
+    },
+    {
+      "epoch": 0.24478694469628287,
+      "grad_norm": 0.054734013974666595,
+      "learning_rate": 4.6238938053097344e-05,
+      "loss": 0.4941,
+      "step": 135
+    },
+    {
+      "epoch": 0.25385312783318226,
+      "grad_norm": 0.0561821311712265,
+      "learning_rate": 4.56858407079646e-05,
+      "loss": 0.4879,
+      "step": 140
+    },
+    {
+      "epoch": 0.2629193109700816,
+      "grad_norm": 0.05934757739305496,
+      "learning_rate": 4.5132743362831855e-05,
+      "loss": 0.4877,
+      "step": 145
+    },
+    {
+      "epoch": 0.271985494106981,
+      "grad_norm": 0.057985540479421616,
+      "learning_rate": 4.4579646017699114e-05,
+      "loss": 0.484,
+      "step": 150
+    },
+    {
+      "epoch": 0.2810516772438803,
+      "grad_norm": 0.054954368621110916,
+      "learning_rate": 4.4026548672566373e-05,
+      "loss": 0.4728,
+      "step": 155
+    },
+    {
+      "epoch": 0.2901178603807797,
+      "grad_norm": 0.056278448551893234,
+      "learning_rate": 4.3473451327433626e-05,
+      "loss": 0.4768,
+      "step": 160
+    },
+    {
+      "epoch": 0.2991840435176791,
+      "grad_norm": 0.061460211873054504,
+      "learning_rate": 4.2920353982300885e-05,
+      "loss": 0.4752,
+      "step": 165
+    },
+    {
+      "epoch": 0.3082502266545784,
+      "grad_norm": 0.06386470794677734,
+      "learning_rate": 4.2367256637168144e-05,
+      "loss": 0.4665,
+      "step": 170
+    },
+    {
+      "epoch": 0.3173164097914778,
+      "grad_norm": 0.06866438686847687,
+      "learning_rate": 4.1814159292035396e-05,
+      "loss": 0.4664,
+      "step": 175
+    },
+    {
+      "epoch": 0.3263825929283772,
+      "grad_norm": 0.06411902606487274,
+      "learning_rate": 4.1261061946902655e-05,
+      "loss": 0.4656,
+      "step": 180
+    },
+    {
+      "epoch": 0.3354487760652765,
+      "grad_norm": 0.0692601427435875,
+      "learning_rate": 4.0707964601769914e-05,
+      "loss": 0.4638,
+      "step": 185
+    },
+    {
+      "epoch": 0.3445149592021759,
+      "grad_norm": 0.06713596731424332,
+      "learning_rate": 4.015486725663717e-05,
+      "loss": 0.4574,
+      "step": 190
+    },
+    {
+      "epoch": 0.3535811423390752,
+      "grad_norm": 0.07020549476146698,
+      "learning_rate": 3.9601769911504426e-05,
+      "loss": 0.4535,
+      "step": 195
+    },
+    {
+      "epoch": 0.3626473254759746,
+      "grad_norm": 0.07310190051794052,
+      "learning_rate": 3.9048672566371685e-05,
+      "loss": 0.4569,
+      "step": 200
+    },
+    {
+      "epoch": 0.371713508612874,
+      "grad_norm": 0.06643065065145493,
+      "learning_rate": 3.849557522123894e-05,
+      "loss": 0.4483,
+      "step": 205
+    },
+    {
+      "epoch": 0.38077969174977333,
+      "grad_norm": 0.07110671699047089,
+      "learning_rate": 3.7942477876106196e-05,
+      "loss": 0.4513,
+      "step": 210
+    },
+    {
+      "epoch": 0.3898458748866727,
+      "grad_norm": 0.08371982723474503,
+      "learning_rate": 3.7389380530973455e-05,
+      "loss": 0.4468,
+      "step": 215
+    },
+    {
+      "epoch": 0.3989120580235721,
+      "grad_norm": 0.0777554139494896,
+      "learning_rate": 3.683628318584071e-05,
+      "loss": 0.447,
+      "step": 220
+    },
+    {
+      "epoch": 0.40797824116047143,
+      "grad_norm": 0.06965522468090057,
+      "learning_rate": 3.628318584070797e-05,
+      "loss": 0.4434,
+      "step": 225
+    },
+    {
+      "epoch": 0.4170444242973708,
+      "grad_norm": 0.0734223872423172,
+      "learning_rate": 3.573008849557522e-05,
+      "loss": 0.4457,
+      "step": 230
+    },
+    {
+      "epoch": 0.42611060743427015,
+      "grad_norm": 0.0682050958275795,
+      "learning_rate": 3.517699115044248e-05,
+      "loss": 0.4434,
+      "step": 235
+    },
+    {
+      "epoch": 0.43517679057116954,
+      "grad_norm": 0.08661296963691711,
+      "learning_rate": 3.462389380530974e-05,
+      "loss": 0.449,
+      "step": 240
+    },
+    {
+      "epoch": 0.4442429737080689,
+      "grad_norm": 0.08436290174722672,
+      "learning_rate": 3.407079646017699e-05,
+      "loss": 0.4457,
+      "step": 245
+    },
+    {
+      "epoch": 0.45330915684496825,
+      "grad_norm": 0.07421322166919708,
+      "learning_rate": 3.351769911504425e-05,
+      "loss": 0.4419,
+      "step": 250
+    },
+    {
+      "epoch": 0.46237533998186764,
+      "grad_norm": 0.0795440748333931,
+      "learning_rate": 3.296460176991151e-05,
+      "loss": 0.4447,
+      "step": 255
+    },
+    {
+      "epoch": 0.471441523118767,
+      "grad_norm": 0.07894603908061981,
+      "learning_rate": 3.241150442477876e-05,
+      "loss": 0.443,
+      "step": 260
+    },
+    {
+      "epoch": 0.48050770625566636,
+      "grad_norm": 0.07290520519018173,
+      "learning_rate": 3.185840707964602e-05,
+      "loss": 0.4345,
+      "step": 265
+    },
+    {
+      "epoch": 0.48957388939256574,
+      "grad_norm": 0.07478918135166168,
+      "learning_rate": 3.130530973451328e-05,
+      "loss": 0.4402,
+      "step": 270
+    },
+    {
+      "epoch": 0.4986400725294651,
+      "grad_norm": 0.09009527415037155,
+      "learning_rate": 3.075221238938053e-05,
+      "loss": 0.4332,
+      "step": 275
+    },
+    {
+      "epoch": 0.5077062556663645,
+      "grad_norm": 0.08838801831007004,
+      "learning_rate": 3.019911504424779e-05,
+      "loss": 0.4383,
+      "step": 280
+    },
+    {
+      "epoch": 0.5167724388032638,
+      "grad_norm": 0.07192256301641464,
+      "learning_rate": 2.964601769911505e-05,
+      "loss": 0.4313,
+      "step": 285
+    },
+    {
+      "epoch": 0.5258386219401632,
+      "grad_norm": 0.07938144356012344,
+      "learning_rate": 2.90929203539823e-05,
+      "loss": 0.4327,
+      "step": 290
+    },
+    {
+      "epoch": 0.5349048050770625,
+      "grad_norm": 0.08160530030727386,
+      "learning_rate": 2.853982300884956e-05,
+      "loss": 0.4326,
+      "step": 295
+    },
+    {
+      "epoch": 0.543970988213962,
+      "grad_norm": 0.09404582530260086,
+      "learning_rate": 2.7986725663716816e-05,
+      "loss": 0.4326,
+      "step": 300
+    },
+    {
+      "epoch": 0.5530371713508613,
+      "grad_norm": 0.07616602629423141,
+      "learning_rate": 2.743362831858407e-05,
+      "loss": 0.4249,
+      "step": 305
+    },
+    {
+      "epoch": 0.5621033544877606,
+      "grad_norm": 0.08184757083654404,
+      "learning_rate": 2.688053097345133e-05,
+      "loss": 0.4292,
+      "step": 310
+    },
+    {
+      "epoch": 0.57116953762466,
+      "grad_norm": 0.09085652232170105,
+      "learning_rate": 2.6327433628318586e-05,
+      "loss": 0.4326,
+      "step": 315
+    },
+    {
+      "epoch": 0.5802357207615594,
+      "grad_norm": 0.07777532935142517,
+      "learning_rate": 2.5774336283185842e-05,
+      "loss": 0.4256,
+      "step": 320
+    },
+    {
+      "epoch": 0.5893019038984587,
+      "grad_norm": 0.08594377338886261,
+      "learning_rate": 2.5221238938053098e-05,
+      "loss": 0.4314,
+      "step": 325
+    },
+    {
+      "epoch": 0.5983680870353582,
+      "grad_norm": 0.08091574907302856,
+      "learning_rate": 2.4668141592920353e-05,
+      "loss": 0.4243,
+      "step": 330
+    },
+    {
+      "epoch": 0.6074342701722575,
+      "grad_norm": 0.0800497829914093,
+      "learning_rate": 2.411504424778761e-05,
+      "loss": 0.4336,
+      "step": 335
+    },
+    {
+      "epoch": 0.6165004533091568,
+      "grad_norm": 0.08816388249397278,
+      "learning_rate": 2.3561946902654868e-05,
+      "loss": 0.4297,
+      "step": 340
+    },
+    {
+      "epoch": 0.6255666364460563,
+      "grad_norm": 0.08167457580566406,
+      "learning_rate": 2.3008849557522124e-05,
+      "loss": 0.4248,
+      "step": 345
+    },
+    {
+      "epoch": 0.6346328195829556,
+      "grad_norm": 0.09383154660463333,
+      "learning_rate": 2.245575221238938e-05,
+      "loss": 0.4262,
+      "step": 350
+    },
+    {
+      "epoch": 0.6436990027198549,
+      "grad_norm": 0.08120961487293243,
+      "learning_rate": 2.190265486725664e-05,
+      "loss": 0.4293,
+      "step": 355
+    },
+    {
+      "epoch": 0.6527651858567544,
+      "grad_norm": 0.08866537362337112,
+      "learning_rate": 2.1349557522123894e-05,
+      "loss": 0.4269,
+      "step": 360
+    },
+    {
+      "epoch": 0.6618313689936537,
+      "grad_norm": 0.08616868406534195,
+      "learning_rate": 2.079646017699115e-05,
+      "loss": 0.4252,
+      "step": 365
+    },
+    {
+      "epoch": 0.670897552130553,
+      "grad_norm": 0.08172861486673355,
+      "learning_rate": 2.024336283185841e-05,
+      "loss": 0.42,
+      "step": 370
+    },
+    {
+      "epoch": 0.6799637352674524,
+      "grad_norm": 0.08940409123897552,
+      "learning_rate": 1.9690265486725665e-05,
+      "loss": 0.4238,
+      "step": 375
+    },
+    {
+      "epoch": 0.6890299184043518,
+      "grad_norm": 0.09020205587148666,
+      "learning_rate": 1.913716814159292e-05,
+      "loss": 0.4298,
+      "step": 380
+    },
+    {
+      "epoch": 0.6980961015412511,
+      "grad_norm": 0.08593279123306274,
+      "learning_rate": 1.858407079646018e-05,
+      "loss": 0.4222,
+      "step": 385
+    },
+    {
+      "epoch": 0.7071622846781505,
+      "grad_norm": 0.08001919090747833,
+      "learning_rate": 1.8030973451327435e-05,
+      "loss": 0.4267,
+      "step": 390
+    },
+    {
+      "epoch": 0.7162284678150499,
+      "grad_norm": 0.0805264338850975,
+      "learning_rate": 1.747787610619469e-05,
+      "loss": 0.4249,
+      "step": 395
+    },
+    {
+      "epoch": 0.7252946509519492,
+      "grad_norm": 0.08267470449209213,
+      "learning_rate": 1.692477876106195e-05,
+      "loss": 0.4268,
+      "step": 400
+    },
+    {
+      "epoch": 0.7343608340888486,
+      "grad_norm": 0.08514878898859024,
+      "learning_rate": 1.6371681415929206e-05,
+      "loss": 0.4211,
+      "step": 405
+    },
+    {
+      "epoch": 0.743427017225748,
+      "grad_norm": 0.08745454996824265,
+      "learning_rate": 1.581858407079646e-05,
+      "loss": 0.4182,
+      "step": 410
+    },
+    {
+      "epoch": 0.7524932003626473,
+      "grad_norm": 0.07666044682264328,
+      "learning_rate": 1.5265486725663717e-05,
+      "loss": 0.421,
+      "step": 415
+    },
+    {
+      "epoch": 0.7615593834995467,
+      "grad_norm": 0.07890937477350235,
+      "learning_rate": 1.4712389380530974e-05,
+      "loss": 0.425,
+      "step": 420
+    },
+    {
+      "epoch": 0.7706255666364461,
+      "grad_norm": 0.0812554880976677,
+      "learning_rate": 1.415929203539823e-05,
+      "loss": 0.4184,
+      "step": 425
+    },
+    {
+      "epoch": 0.7796917497733454,
+      "grad_norm": 0.078528992831707,
+      "learning_rate": 1.3606194690265486e-05,
+      "loss": 0.4181,
+      "step": 430
+    },
+    {
+      "epoch": 0.7887579329102448,
+      "grad_norm": 0.0815301239490509,
+      "learning_rate": 1.3053097345132745e-05,
+      "loss": 0.4217,
+      "step": 435
+    },
+    {
+      "epoch": 0.7978241160471442,
+      "grad_norm": 0.08107589185237885,
+      "learning_rate": 1.25e-05,
+      "loss": 0.4227,
+      "step": 440
+    },
+    {
+      "epoch": 0.8068902991840435,
+      "grad_norm": 0.07778468728065491,
+      "learning_rate": 1.1946902654867258e-05,
+      "loss": 0.4162,
+      "step": 445
+    },
+    {
+      "epoch": 0.8159564823209429,
+      "grad_norm": 0.08603918552398682,
+      "learning_rate": 1.1393805309734514e-05,
+      "loss": 0.4203,
+      "step": 450
+    },
+    {
+      "epoch": 0.8250226654578422,
+      "grad_norm": 0.08256816864013672,
+      "learning_rate": 1.0840707964601771e-05,
+      "loss": 0.4222,
+      "step": 455
+    },
+    {
+      "epoch": 0.8340888485947416,
+      "grad_norm": 0.07872200012207031,
+      "learning_rate": 1.0287610619469027e-05,
+      "loss": 0.4176,
+      "step": 460
+    },
+    {
+      "epoch": 0.843155031731641,
+      "grad_norm": 0.09151720255613327,
+      "learning_rate": 9.734513274336284e-06,
+      "loss": 0.4144,
+      "step": 465
+    },
+    {
+      "epoch": 0.8522212148685403,
+      "grad_norm": 0.07890870422124863,
+      "learning_rate": 9.18141592920354e-06,
+      "loss": 0.4158,
+      "step": 470
+    },
+    {
+      "epoch": 0.8612873980054397,
+      "grad_norm": 0.0838795080780983,
+      "learning_rate": 8.628318584070797e-06,
+      "loss": 0.415,
+      "step": 475
+    },
+    {
+      "epoch": 0.8703535811423391,
+      "grad_norm": 0.08289153128862381,
+      "learning_rate": 8.075221238938053e-06,
+      "loss": 0.4215,
+      "step": 480
+    },
+    {
+      "epoch": 0.8794197642792384,
+      "grad_norm": 0.08027064800262451,
+      "learning_rate": 7.52212389380531e-06,
+      "loss": 0.4221,
+      "step": 485
+    },
+    {
+      "epoch": 0.8884859474161378,
+      "grad_norm": 0.08152059465646744,
+      "learning_rate": 6.969026548672566e-06,
+      "loss": 0.4261,
+      "step": 490
+    },
+    {
+      "epoch": 0.8975521305530372,
+      "grad_norm": 0.07868578284978867,
+      "learning_rate": 6.415929203539823e-06,
+      "loss": 0.4172,
+      "step": 495
+    },
+    {
+      "epoch": 0.9066183136899365,
+      "grad_norm": 0.07779107242822647,
+      "learning_rate": 5.86283185840708e-06,
+      "loss": 0.4188,
+      "step": 500
+    },
+    {
+      "epoch": 0.915684496826836,
+      "grad_norm": 0.07544977962970734,
+      "learning_rate": 5.3097345132743365e-06,
+      "loss": 0.4182,
+      "step": 505
+    },
+    {
+      "epoch": 0.9247506799637353,
+      "grad_norm": 0.08261619508266449,
+      "learning_rate": 4.756637168141593e-06,
+      "loss": 0.4157,
+      "step": 510
+    },
+    {
+      "epoch": 0.9338168631006346,
+      "grad_norm": 0.08024437725543976,
+      "learning_rate": 4.2035398230088504e-06,
+      "loss": 0.4223,
+      "step": 515
+    },
+    {
+      "epoch": 0.942883046237534,
+      "grad_norm": 0.07606545835733414,
+      "learning_rate": 3.6504424778761066e-06,
+      "loss": 0.4118,
+      "step": 520
+    },
+    {
+      "epoch": 0.9519492293744334,
+      "grad_norm": 0.07778365164995193,
+      "learning_rate": 3.097345132743363e-06,
+      "loss": 0.4211,
+      "step": 525
+    },
+    {
+      "epoch": 0.9610154125113327,
+      "grad_norm": 0.07748548686504364,
+      "learning_rate": 2.5442477876106196e-06,
+      "loss": 0.4172,
+      "step": 530
+    },
+    {
+      "epoch": 0.970081595648232,
+      "grad_norm": 0.07857740670442581,
+      "learning_rate": 1.991150442477876e-06,
+      "loss": 0.4222,
+      "step": 535
+    },
+    {
+      "epoch": 0.9791477787851315,
+      "grad_norm": 0.07634645700454712,
+      "learning_rate": 1.4380530973451327e-06,
+      "loss": 0.4162,
+      "step": 540
+    },
+    {
+      "epoch": 0.9882139619220308,
+      "grad_norm": 0.07758194953203201,
+      "learning_rate": 8.849557522123894e-07,
+      "loss": 0.4164,
+      "step": 545
+    },
+    {
+      "epoch": 0.9972801450589301,
+      "grad_norm": 0.07544778287410736,
+      "learning_rate": 3.3185840707964603e-07,
+      "loss": 0.4128,
+      "step": 550
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 552,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.918147574526116e+18,
+  "train_batch_size": 80,
+  "trial_name": null,
+  "trial_params": null
+}

math-0.3/q/cold-start/checkpoint-552/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:919445c33dece1f2a0d2869618b9c492eee43c4ddeb84be6b31bb3ca5243967b
+size 6289

math-0.3/q/cold-start/special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|vision_pad|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

math-0.3/q/cold-start/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
+size 11422778

math-0.3/q/cold-start/tokenizer_config.json

@@ -0,0 +1,195 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<｜User｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151645": {
+      "content": "<｜Assistant｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151646": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151648": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151649": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 131072,
+  "pad_token": "<|vision_pad|>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizerFast",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}