Upload folder using huggingface_hub

.gitattributes

@@ -39,3 +39,5 @@ coding-0.1/q/cold-start/checkpoint-22/tokenizer.json filter=lfs diff=lfs merge=l
 coding-0.1/q/cold-start/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 coding-0.2/joint/checkpoint-1/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 coding-0.2/joint/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+coding-0.2/joint/checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+coding-0.2/joint/checkpoint-689/tokenizer.json filter=lfs diff=lfs merge=lfs -text

coding-0.2/joint/README.md

@@ -0,0 +1,63 @@
+---
+base_model: unsloth/deepseek-r1-distill-qwen-7b-unsloth-bnb-4bit
+library_name: peft
+model_name: joint
+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 joint
+
+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/vwqmky2k) 
+
+
+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}}
+}
+```

coding-0.2/joint/adapter_config.json

@@ -0,0 +1,53 @@
+{
+  "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": [
+    "lm_head",
+    "embed_tokens"
+  ],
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "up_proj",
+    "v_proj",
+    "k_proj",
+    "gate_proj",
+    "o_proj",
+    "down_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

coding-0.2/joint/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52551d2295543ded415868f8d7c12aff0d3cc111c026b1acc66dc18d2029ab29
+size 2825965440

coding-0.2/joint/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 %}

coding-0.2/joint/checkpoint-1/README.md

@@ -0,0 +1,210 @@
+---
+base_model: unsloth/deepseek-r1-distill-qwen-14b-unsloth-bnb-4bit
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/deepseek-r1-distill-qwen-14b-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

coding-0.2/joint/checkpoint-1/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-14b-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": 16,
+  "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": [
+    "gate_proj",
+    "up_proj",
+    "q_proj",
+    "down_proj",
+    "o_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

coding-0.2/joint/checkpoint-1/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d275d291fe0ca22d878c478f3e5377858b8c8bf773e904f4f5713226db78f4e5
+size 1101095848

coding-0.2/joint/checkpoint-1/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 %}

coding-0.2/joint/checkpoint-1/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e9cdd9fcb05795b0c41d8f8531ce9665bde9a04dba8b2354938f317f205d97c
+size 559894629

coding-0.2/joint/checkpoint-1/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1d565802a8e26c4e8a31328752b7a7fdc186d9401aa008e65697d0ad8c22e33
+size 14645

coding-0.2/joint/checkpoint-1/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c7e22b2cd255dd2da6f07c43e8d72a6692a46c3dd6241d9928ceb49213f4b7e
+size 1465

coding-0.2/joint/checkpoint-1/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
+  }
+}

coding-0.2/joint/checkpoint-1/tokenizer.json

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

coding-0.2/joint/checkpoint-1/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
+}

coding-0.2/joint/checkpoint-1/trainer_state.json

@@ -0,0 +1,33 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.0003628776195228159,
+  "eval_steps": 500,
+  "global_step": 1,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [],
+  "logging_steps": 10,
+  "max_steps": 0,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "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": 2784406659366912.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

coding-0.2/joint/checkpoint-1/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f957d6d5f436a90afcad467facdc78d4657de4e2934508c5a537355ceb738a0
+size 6225

coding-0.2/joint/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

coding-0.2/joint/checkpoint-500/adapter_config.json

@@ -0,0 +1,53 @@
+{
+  "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": [
+    "lm_head",
+    "embed_tokens"
+  ],
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "up_proj",
+    "v_proj",
+    "k_proj",
+    "gate_proj",
+    "o_proj",
+    "down_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

coding-0.2/joint/checkpoint-500/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cf1ac50808148b103404ac765ea25450ce1cfa6ee0387d7262b4d8c4a12a970
+size 2825965440

coding-0.2/joint/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 %}

coding-0.2/joint/checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2aa40c5127ff662c767e8f2133a598453629f5c5c052102d85783516bb610b28
+size 5795494899

coding-0.2/joint/checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1d565802a8e26c4e8a31328752b7a7fdc186d9401aa008e65697d0ad8c22e33
+size 14645

coding-0.2/joint/checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab507c1fc7f358b592713dfebf8627c7f71b70b7c6c0d5f25bc011e9dc8229e7
+size 1465

coding-0.2/joint/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
+  }
+}

coding-0.2/joint/checkpoint-500/tokenizer.json

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

coding-0.2/joint/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
+}

coding-0.2/joint/checkpoint-500/trainer_state.json

@@ -0,0 +1,384 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.7256894049346879,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01451378809869376,
+      "grad_norm": 2.8285412788391113,
+      "learning_rate": 1.8e-05,
+      "loss": 1.1057,
+      "step": 10
+    },
+    {
+      "epoch": 0.02902757619738752,
+      "grad_norm": 1.1285754442214966,
+      "learning_rate": 3.8e-05,
+      "loss": 0.9694,
+      "step": 20
+    },
+    {
+      "epoch": 0.04354136429608128,
+      "grad_norm": 0.8574178218841553,
+      "learning_rate": 5.8e-05,
+      "loss": 0.7341,
+      "step": 30
+    },
+    {
+      "epoch": 0.05805515239477504,
+      "grad_norm": 0.53108811378479,
+      "learning_rate": 7.800000000000001e-05,
+      "loss": 0.6017,
+      "step": 40
+    },
+    {
+      "epoch": 0.07256894049346879,
+      "grad_norm": 0.40395280718803406,
+      "learning_rate": 9.8e-05,
+      "loss": 0.534,
+      "step": 50
+    },
+    {
+      "epoch": 0.08708272859216255,
+      "grad_norm": 0.4184938073158264,
+      "learning_rate": 0.000118,
+      "loss": 0.5018,
+      "step": 60
+    },
+    {
+      "epoch": 0.10159651669085631,
+      "grad_norm": 0.3326551616191864,
+      "learning_rate": 0.000138,
+      "loss": 0.4807,
+      "step": 70
+    },
+    {
+      "epoch": 0.11611030478955008,
+      "grad_norm": 0.3530741333961487,
+      "learning_rate": 0.00015800000000000002,
+      "loss": 0.462,
+      "step": 80
+    },
+    {
+      "epoch": 0.13062409288824384,
+      "grad_norm": 0.3607262670993805,
+      "learning_rate": 0.00017800000000000002,
+      "loss": 0.4492,
+      "step": 90
+    },
+    {
+      "epoch": 0.14513788098693758,
+      "grad_norm": 0.37283945083618164,
+      "learning_rate": 0.00019800000000000002,
+      "loss": 0.4436,
+      "step": 100
+    },
+    {
+      "epoch": 0.15965166908563136,
+      "grad_norm": 0.3210872709751129,
+      "learning_rate": 0.00019694397283531408,
+      "loss": 0.4338,
+      "step": 110
+    },
+    {
+      "epoch": 0.1741654571843251,
+      "grad_norm": 0.2939835488796234,
+      "learning_rate": 0.00019354838709677422,
+      "loss": 0.4279,
+      "step": 120
+    },
+    {
+      "epoch": 0.18867924528301888,
+      "grad_norm": 0.3203432857990265,
+      "learning_rate": 0.0001901528013582343,
+      "loss": 0.4177,
+      "step": 130
+    },
+    {
+      "epoch": 0.20319303338171263,
+      "grad_norm": 0.2840735614299774,
+      "learning_rate": 0.00018675721561969442,
+      "loss": 0.4157,
+      "step": 140
+    },
+    {
+      "epoch": 0.21770682148040638,
+      "grad_norm": 0.29428958892822266,
+      "learning_rate": 0.0001833616298811545,
+      "loss": 0.4133,
+      "step": 150
+    },
+    {
+      "epoch": 0.23222060957910015,
+      "grad_norm": 0.2704876661300659,
+      "learning_rate": 0.00017996604414261463,
+      "loss": 0.4095,
+      "step": 160
+    },
+    {
+      "epoch": 0.2467343976777939,
+      "grad_norm": 0.29016420245170593,
+      "learning_rate": 0.0001765704584040747,
+      "loss": 0.4036,
+      "step": 170
+    },
+    {
+      "epoch": 0.2612481857764877,
+      "grad_norm": 0.26832008361816406,
+      "learning_rate": 0.0001731748726655348,
+      "loss": 0.4057,
+      "step": 180
+    },
+    {
+      "epoch": 0.2757619738751814,
+      "grad_norm": 0.280130535364151,
+      "learning_rate": 0.00016977928692699492,
+      "loss": 0.3996,
+      "step": 190
+    },
+    {
+      "epoch": 0.29027576197387517,
+      "grad_norm": 0.2216828167438507,
+      "learning_rate": 0.00016638370118845502,
+      "loss": 0.3999,
+      "step": 200
+    },
+    {
+      "epoch": 0.3047895500725689,
+      "grad_norm": 0.2544555962085724,
+      "learning_rate": 0.00016298811544991512,
+      "loss": 0.394,
+      "step": 210
+    },
+    {
+      "epoch": 0.3193033381712627,
+      "grad_norm": 0.26161113381385803,
+      "learning_rate": 0.00015959252971137523,
+      "loss": 0.3918,
+      "step": 220
+    },
+    {
+      "epoch": 0.33381712626995647,
+      "grad_norm": 0.22447264194488525,
+      "learning_rate": 0.00015619694397283533,
+      "loss": 0.395,
+      "step": 230
+    },
+    {
+      "epoch": 0.3483309143686502,
+      "grad_norm": 0.24482668936252594,
+      "learning_rate": 0.00015280135823429543,
+      "loss": 0.3842,
+      "step": 240
+    },
+    {
+      "epoch": 0.36284470246734396,
+      "grad_norm": 0.2375396192073822,
+      "learning_rate": 0.00014940577249575554,
+      "loss": 0.3906,
+      "step": 250
+    },
+    {
+      "epoch": 0.37735849056603776,
+      "grad_norm": 0.24287049472332,
+      "learning_rate": 0.00014601018675721562,
+      "loss": 0.3838,
+      "step": 260
+    },
+    {
+      "epoch": 0.3918722786647315,
+      "grad_norm": 0.24098220467567444,
+      "learning_rate": 0.00014261460101867572,
+      "loss": 0.3816,
+      "step": 270
+    },
+    {
+      "epoch": 0.40638606676342526,
+      "grad_norm": 0.23136872053146362,
+      "learning_rate": 0.00013921901528013582,
+      "loss": 0.3846,
+      "step": 280
+    },
+    {
+      "epoch": 0.420899854862119,
+      "grad_norm": 0.23768611252307892,
+      "learning_rate": 0.00013582342954159593,
+      "loss": 0.3788,
+      "step": 290
+    },
+    {
+      "epoch": 0.43541364296081275,
+      "grad_norm": 0.2431989163160324,
+      "learning_rate": 0.00013242784380305603,
+      "loss": 0.3762,
+      "step": 300
+    },
+    {
+      "epoch": 0.44992743105950656,
+      "grad_norm": 0.22804555296897888,
+      "learning_rate": 0.00012903225806451613,
+      "loss": 0.3745,
+      "step": 310
+    },
+    {
+      "epoch": 0.4644412191582003,
+      "grad_norm": 0.22682340443134308,
+      "learning_rate": 0.00012563667232597624,
+      "loss": 0.3774,
+      "step": 320
+    },
+    {
+      "epoch": 0.47895500725689405,
+      "grad_norm": 0.2583816647529602,
+      "learning_rate": 0.00012224108658743634,
+      "loss": 0.3762,
+      "step": 330
+    },
+    {
+      "epoch": 0.4934687953555878,
+      "grad_norm": 0.23387964069843292,
+      "learning_rate": 0.00011884550084889643,
+      "loss": 0.3753,
+      "step": 340
+    },
+    {
+      "epoch": 0.5079825834542816,
+      "grad_norm": 0.21552371978759766,
+      "learning_rate": 0.00011544991511035655,
+      "loss": 0.3761,
+      "step": 350
+    },
+    {
+      "epoch": 0.5224963715529753,
+      "grad_norm": 0.2177582085132599,
+      "learning_rate": 0.00011205432937181664,
+      "loss": 0.3734,
+      "step": 360
+    },
+    {
+      "epoch": 0.5370101596516691,
+      "grad_norm": 0.22051909565925598,
+      "learning_rate": 0.00010865874363327674,
+      "loss": 0.3717,
+      "step": 370
+    },
+    {
+      "epoch": 0.5515239477503628,
+      "grad_norm": 0.21704523265361786,
+      "learning_rate": 0.00010526315789473685,
+      "loss": 0.3707,
+      "step": 380
+    },
+    {
+      "epoch": 0.5660377358490566,
+      "grad_norm": 0.2447778433561325,
+      "learning_rate": 0.00010186757215619695,
+      "loss": 0.3669,
+      "step": 390
+    },
+    {
+      "epoch": 0.5805515239477503,
+      "grad_norm": 0.2079760581254959,
+      "learning_rate": 9.847198641765704e-05,
+      "loss": 0.3643,
+      "step": 400
+    },
+    {
+      "epoch": 0.5950653120464441,
+      "grad_norm": 0.21614719927310944,
+      "learning_rate": 9.507640067911715e-05,
+      "loss": 0.3655,
+      "step": 410
+    },
+    {
+      "epoch": 0.6095791001451378,
+      "grad_norm": 0.2331458330154419,
+      "learning_rate": 9.168081494057725e-05,
+      "loss": 0.363,
+      "step": 420
+    },
+    {
+      "epoch": 0.6240928882438317,
+      "grad_norm": 0.23197589814662933,
+      "learning_rate": 8.828522920203735e-05,
+      "loss": 0.3611,
+      "step": 430
+    },
+    {
+      "epoch": 0.6386066763425254,
+      "grad_norm": 0.21380995213985443,
+      "learning_rate": 8.488964346349746e-05,
+      "loss": 0.3656,
+      "step": 440
+    },
+    {
+      "epoch": 0.6531204644412192,
+      "grad_norm": 0.21522027254104614,
+      "learning_rate": 8.149405772495756e-05,
+      "loss": 0.3622,
+      "step": 450
+    },
+    {
+      "epoch": 0.6676342525399129,
+      "grad_norm": 0.23200784623622894,
+      "learning_rate": 7.809847198641767e-05,
+      "loss": 0.3652,
+      "step": 460
+    },
+    {
+      "epoch": 0.6821480406386067,
+      "grad_norm": 0.20713669061660767,
+      "learning_rate": 7.470288624787777e-05,
+      "loss": 0.3577,
+      "step": 470
+    },
+    {
+      "epoch": 0.6966618287373004,
+      "grad_norm": 0.2413240522146225,
+      "learning_rate": 7.130730050933786e-05,
+      "loss": 0.3605,
+      "step": 480
+    },
+    {
+      "epoch": 0.7111756168359942,
+      "grad_norm": 0.23881566524505615,
+      "learning_rate": 6.791171477079796e-05,
+      "loss": 0.361,
+      "step": 490
+    },
+    {
+      "epoch": 0.7256894049346879,
+      "grad_norm": 0.2193984091281891,
+      "learning_rate": 6.451612903225807e-05,
+      "loss": 0.3556,
+      "step": 500
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 689,
+  "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": 3.056638864915808e+18,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

coding-0.2/joint/checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6937314c93880a19dde76eaa9d8eee1705840a8c72f06be46928a1b2f35b74d8
+size 6225

coding-0.2/joint/checkpoint-689/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

coding-0.2/joint/checkpoint-689/adapter_config.json

@@ -0,0 +1,53 @@
+{
+  "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": [
+    "lm_head",
+    "embed_tokens"
+  ],
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "up_proj",
+    "v_proj",
+    "k_proj",
+    "gate_proj",
+    "o_proj",
+    "down_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

coding-0.2/joint/checkpoint-689/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52551d2295543ded415868f8d7c12aff0d3cc111c026b1acc66dc18d2029ab29
+size 2825965440

coding-0.2/joint/checkpoint-689/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 %}

coding-0.2/joint/checkpoint-689/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0daed07b7b906b12513c6ddad3f19a21435d92db273797bdedac46bc3431274f
+size 5795494899

coding-0.2/joint/checkpoint-689/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1d565802a8e26c4e8a31328752b7a7fdc186d9401aa008e65697d0ad8c22e33
+size 14645

coding-0.2/joint/checkpoint-689/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43690e6edc97682a231039c2eb585c50cf1ec1b36f17a8a8fca53f19bd6d219f
+size 1465

coding-0.2/joint/checkpoint-689/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
+  }
+}

coding-0.2/joint/checkpoint-689/tokenizer.json

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

coding-0.2/joint/checkpoint-689/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
+}

coding-0.2/joint/checkpoint-689/trainer_state.json

@@ -0,0 +1,510 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 689,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01451378809869376,
+      "grad_norm": 2.8285412788391113,
+      "learning_rate": 1.8e-05,
+      "loss": 1.1057,
+      "step": 10
+    },
+    {
+      "epoch": 0.02902757619738752,
+      "grad_norm": 1.1285754442214966,
+      "learning_rate": 3.8e-05,
+      "loss": 0.9694,
+      "step": 20
+    },
+    {
+      "epoch": 0.04354136429608128,
+      "grad_norm": 0.8574178218841553,
+      "learning_rate": 5.8e-05,
+      "loss": 0.7341,
+      "step": 30
+    },
+    {
+      "epoch": 0.05805515239477504,
+      "grad_norm": 0.53108811378479,
+      "learning_rate": 7.800000000000001e-05,
+      "loss": 0.6017,
+      "step": 40
+    },
+    {
+      "epoch": 0.07256894049346879,
+      "grad_norm": 0.40395280718803406,
+      "learning_rate": 9.8e-05,
+      "loss": 0.534,
+      "step": 50
+    },
+    {
+      "epoch": 0.08708272859216255,
+      "grad_norm": 0.4184938073158264,
+      "learning_rate": 0.000118,
+      "loss": 0.5018,
+      "step": 60
+    },
+    {
+      "epoch": 0.10159651669085631,
+      "grad_norm": 0.3326551616191864,
+      "learning_rate": 0.000138,
+      "loss": 0.4807,
+      "step": 70
+    },
+    {
+      "epoch": 0.11611030478955008,
+      "grad_norm": 0.3530741333961487,
+      "learning_rate": 0.00015800000000000002,
+      "loss": 0.462,
+      "step": 80
+    },
+    {
+      "epoch": 0.13062409288824384,
+      "grad_norm": 0.3607262670993805,
+      "learning_rate": 0.00017800000000000002,
+      "loss": 0.4492,
+      "step": 90
+    },
+    {
+      "epoch": 0.14513788098693758,
+      "grad_norm": 0.37283945083618164,
+      "learning_rate": 0.00019800000000000002,
+      "loss": 0.4436,
+      "step": 100
+    },
+    {
+      "epoch": 0.15965166908563136,
+      "grad_norm": 0.3210872709751129,
+      "learning_rate": 0.00019694397283531408,
+      "loss": 0.4338,
+      "step": 110
+    },
+    {
+      "epoch": 0.1741654571843251,
+      "grad_norm": 0.2939835488796234,
+      "learning_rate": 0.00019354838709677422,
+      "loss": 0.4279,
+      "step": 120
+    },
+    {
+      "epoch": 0.18867924528301888,
+      "grad_norm": 0.3203432857990265,
+      "learning_rate": 0.0001901528013582343,
+      "loss": 0.4177,
+      "step": 130
+    },
+    {
+      "epoch": 0.20319303338171263,
+      "grad_norm": 0.2840735614299774,
+      "learning_rate": 0.00018675721561969442,
+      "loss": 0.4157,
+      "step": 140
+    },
+    {
+      "epoch": 0.21770682148040638,
+      "grad_norm": 0.29428958892822266,
+      "learning_rate": 0.0001833616298811545,
+      "loss": 0.4133,
+      "step": 150
+    },
+    {
+      "epoch": 0.23222060957910015,
+      "grad_norm": 0.2704876661300659,
+      "learning_rate": 0.00017996604414261463,
+      "loss": 0.4095,
+      "step": 160
+    },
+    {
+      "epoch": 0.2467343976777939,
+      "grad_norm": 0.29016420245170593,
+      "learning_rate": 0.0001765704584040747,
+      "loss": 0.4036,
+      "step": 170
+    },
+    {
+      "epoch": 0.2612481857764877,
+      "grad_norm": 0.26832008361816406,
+      "learning_rate": 0.0001731748726655348,
+      "loss": 0.4057,
+      "step": 180
+    },
+    {
+      "epoch": 0.2757619738751814,
+      "grad_norm": 0.280130535364151,
+      "learning_rate": 0.00016977928692699492,
+      "loss": 0.3996,
+      "step": 190
+    },
+    {
+      "epoch": 0.29027576197387517,
+      "grad_norm": 0.2216828167438507,
+      "learning_rate": 0.00016638370118845502,
+      "loss": 0.3999,
+      "step": 200
+    },
+    {
+      "epoch": 0.3047895500725689,
+      "grad_norm": 0.2544555962085724,
+      "learning_rate": 0.00016298811544991512,
+      "loss": 0.394,
+      "step": 210
+    },
+    {
+      "epoch": 0.3193033381712627,
+      "grad_norm": 0.26161113381385803,
+      "learning_rate": 0.00015959252971137523,
+      "loss": 0.3918,
+      "step": 220
+    },
+    {
+      "epoch": 0.33381712626995647,
+      "grad_norm": 0.22447264194488525,
+      "learning_rate": 0.00015619694397283533,
+      "loss": 0.395,
+      "step": 230
+    },
+    {
+      "epoch": 0.3483309143686502,
+      "grad_norm": 0.24482668936252594,
+      "learning_rate": 0.00015280135823429543,
+      "loss": 0.3842,
+      "step": 240
+    },
+    {
+      "epoch": 0.36284470246734396,
+      "grad_norm": 0.2375396192073822,
+      "learning_rate": 0.00014940577249575554,
+      "loss": 0.3906,
+      "step": 250
+    },
+    {
+      "epoch": 0.37735849056603776,
+      "grad_norm": 0.24287049472332,
+      "learning_rate": 0.00014601018675721562,
+      "loss": 0.3838,
+      "step": 260
+    },
+    {
+      "epoch": 0.3918722786647315,
+      "grad_norm": 0.24098220467567444,
+      "learning_rate": 0.00014261460101867572,
+      "loss": 0.3816,
+      "step": 270
+    },
+    {
+      "epoch": 0.40638606676342526,
+      "grad_norm": 0.23136872053146362,
+      "learning_rate": 0.00013921901528013582,
+      "loss": 0.3846,
+      "step": 280
+    },
+    {
+      "epoch": 0.420899854862119,
+      "grad_norm": 0.23768611252307892,
+      "learning_rate": 0.00013582342954159593,
+      "loss": 0.3788,
+      "step": 290
+    },
+    {
+      "epoch": 0.43541364296081275,
+      "grad_norm": 0.2431989163160324,
+      "learning_rate": 0.00013242784380305603,
+      "loss": 0.3762,
+      "step": 300
+    },
+    {
+      "epoch": 0.44992743105950656,
+      "grad_norm": 0.22804555296897888,
+      "learning_rate": 0.00012903225806451613,
+      "loss": 0.3745,
+      "step": 310
+    },
+    {
+      "epoch": 0.4644412191582003,
+      "grad_norm": 0.22682340443134308,
+      "learning_rate": 0.00012563667232597624,
+      "loss": 0.3774,
+      "step": 320
+    },
+    {
+      "epoch": 0.47895500725689405,
+      "grad_norm": 0.2583816647529602,
+      "learning_rate": 0.00012224108658743634,
+      "loss": 0.3762,
+      "step": 330
+    },
+    {
+      "epoch": 0.4934687953555878,
+      "grad_norm": 0.23387964069843292,
+      "learning_rate": 0.00011884550084889643,
+      "loss": 0.3753,
+      "step": 340
+    },
+    {
+      "epoch": 0.5079825834542816,
+      "grad_norm": 0.21552371978759766,
+      "learning_rate": 0.00011544991511035655,
+      "loss": 0.3761,
+      "step": 350
+    },
+    {
+      "epoch": 0.5224963715529753,
+      "grad_norm": 0.2177582085132599,
+      "learning_rate": 0.00011205432937181664,
+      "loss": 0.3734,
+      "step": 360
+    },
+    {
+      "epoch": 0.5370101596516691,
+      "grad_norm": 0.22051909565925598,
+      "learning_rate": 0.00010865874363327674,
+      "loss": 0.3717,
+      "step": 370
+    },
+    {
+      "epoch": 0.5515239477503628,
+      "grad_norm": 0.21704523265361786,
+      "learning_rate": 0.00010526315789473685,
+      "loss": 0.3707,
+      "step": 380
+    },
+    {
+      "epoch": 0.5660377358490566,
+      "grad_norm": 0.2447778433561325,
+      "learning_rate": 0.00010186757215619695,
+      "loss": 0.3669,
+      "step": 390
+    },
+    {
+      "epoch": 0.5805515239477503,
+      "grad_norm": 0.2079760581254959,
+      "learning_rate": 9.847198641765704e-05,
+      "loss": 0.3643,
+      "step": 400
+    },
+    {
+      "epoch": 0.5950653120464441,
+      "grad_norm": 0.21614719927310944,
+      "learning_rate": 9.507640067911715e-05,
+      "loss": 0.3655,
+      "step": 410
+    },
+    {
+      "epoch": 0.6095791001451378,
+      "grad_norm": 0.2331458330154419,
+      "learning_rate": 9.168081494057725e-05,
+      "loss": 0.363,
+      "step": 420
+    },
+    {
+      "epoch": 0.6240928882438317,
+      "grad_norm": 0.23197589814662933,
+      "learning_rate": 8.828522920203735e-05,
+      "loss": 0.3611,
+      "step": 430
+    },
+    {
+      "epoch": 0.6386066763425254,
+      "grad_norm": 0.21380995213985443,
+      "learning_rate": 8.488964346349746e-05,
+      "loss": 0.3656,
+      "step": 440
+    },
+    {
+      "epoch": 0.6531204644412192,
+      "grad_norm": 0.21522027254104614,
+      "learning_rate": 8.149405772495756e-05,
+      "loss": 0.3622,
+      "step": 450
+    },
+    {
+      "epoch": 0.6676342525399129,
+      "grad_norm": 0.23200784623622894,
+      "learning_rate": 7.809847198641767e-05,
+      "loss": 0.3652,
+      "step": 460
+    },
+    {
+      "epoch": 0.6821480406386067,
+      "grad_norm": 0.20713669061660767,
+      "learning_rate": 7.470288624787777e-05,
+      "loss": 0.3577,
+      "step": 470
+    },
+    {
+      "epoch": 0.6966618287373004,
+      "grad_norm": 0.2413240522146225,
+      "learning_rate": 7.130730050933786e-05,
+      "loss": 0.3605,
+      "step": 480
+    },
+    {
+      "epoch": 0.7111756168359942,
+      "grad_norm": 0.23881566524505615,
+      "learning_rate": 6.791171477079796e-05,
+      "loss": 0.361,
+      "step": 490
+    },
+    {
+      "epoch": 0.7256894049346879,
+      "grad_norm": 0.2193984091281891,
+      "learning_rate": 6.451612903225807e-05,
+      "loss": 0.3556,
+      "step": 500
+    },
+    {
+      "epoch": 0.7402031930333817,
+      "grad_norm": 0.2159193903207779,
+      "learning_rate": 6.112054329371817e-05,
+      "loss": 0.3581,
+      "step": 510
+    },
+    {
+      "epoch": 0.7547169811320755,
+      "grad_norm": 0.23495930433273315,
+      "learning_rate": 5.7724957555178275e-05,
+      "loss": 0.3572,
+      "step": 520
+    },
+    {
+      "epoch": 0.7692307692307693,
+      "grad_norm": 0.2095775455236435,
+      "learning_rate": 5.432937181663837e-05,
+      "loss": 0.3548,
+      "step": 530
+    },
+    {
+      "epoch": 0.783744557329463,
+      "grad_norm": 0.2108987271785736,
+      "learning_rate": 5.0933786078098476e-05,
+      "loss": 0.3586,
+      "step": 540
+    },
+    {
+      "epoch": 0.7982583454281568,
+      "grad_norm": 0.21367427706718445,
+      "learning_rate": 4.753820033955857e-05,
+      "loss": 0.354,
+      "step": 550
+    },
+    {
+      "epoch": 0.8127721335268505,
+      "grad_norm": 0.21299470961093903,
+      "learning_rate": 4.414261460101868e-05,
+      "loss": 0.3549,
+      "step": 560
+    },
+    {
+      "epoch": 0.8272859216255443,
+      "grad_norm": 0.19568979740142822,
+      "learning_rate": 4.074702886247878e-05,
+      "loss": 0.3527,
+      "step": 570
+    },
+    {
+      "epoch": 0.841799709724238,
+      "grad_norm": 0.23140305280685425,
+      "learning_rate": 3.7351443123938885e-05,
+      "loss": 0.3523,
+      "step": 580
+    },
+    {
+      "epoch": 0.8563134978229318,
+      "grad_norm": 0.19580787420272827,
+      "learning_rate": 3.395585738539898e-05,
+      "loss": 0.3541,
+      "step": 590
+    },
+    {
+      "epoch": 0.8708272859216255,
+      "grad_norm": 0.2059970647096634,
+      "learning_rate": 3.0560271646859086e-05,
+      "loss": 0.3572,
+      "step": 600
+    },
+    {
+      "epoch": 0.8853410740203193,
+      "grad_norm": 0.2206289917230606,
+      "learning_rate": 2.7164685908319186e-05,
+      "loss": 0.3548,
+      "step": 610
+    },
+    {
+      "epoch": 0.8998548621190131,
+      "grad_norm": 0.20322079956531525,
+      "learning_rate": 2.3769100169779286e-05,
+      "loss": 0.3557,
+      "step": 620
+    },
+    {
+      "epoch": 0.9143686502177069,
+      "grad_norm": 0.20411954820156097,
+      "learning_rate": 2.037351443123939e-05,
+      "loss": 0.3553,
+      "step": 630
+    },
+    {
+      "epoch": 0.9288824383164006,
+      "grad_norm": 0.22070156037807465,
+      "learning_rate": 1.697792869269949e-05,
+      "loss": 0.3483,
+      "step": 640
+    },
+    {
+      "epoch": 0.9433962264150944,
+      "grad_norm": 0.1965171992778778,
+      "learning_rate": 1.3582342954159593e-05,
+      "loss": 0.3555,
+      "step": 650
+    },
+    {
+      "epoch": 0.9579100145137881,
+      "grad_norm": 0.19971269369125366,
+      "learning_rate": 1.0186757215619695e-05,
+      "loss": 0.3475,
+      "step": 660
+    },
+    {
+      "epoch": 0.9724238026124818,
+      "grad_norm": 0.1889594942331314,
+      "learning_rate": 6.7911714770797965e-06,
+      "loss": 0.3532,
+      "step": 670
+    },
+    {
+      "epoch": 0.9869375907111756,
+      "grad_norm": 0.18607065081596375,
+      "learning_rate": 3.3955857385398982e-06,
+      "loss": 0.3492,
+      "step": 680
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 689,
+  "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": 4.211655017901048e+18,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

coding-0.2/joint/checkpoint-689/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6937314c93880a19dde76eaa9d8eee1705840a8c72f06be46928a1b2f35b74d8
+size 6225

coding-0.2/joint/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
+  }
+}

coding-0.2/joint/tokenizer.json

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

coding-0.2/joint/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
+}