Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-15/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-30/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-45/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,148 @@
+---
+library_name: peft
+base_model: Qwen/Qwen3-8B
+tags:
+- axolotl
+- base_model:adapter:Qwen/Qwen3-8B
+- lora
+- transformers
+pipeline_tag: text-generation
+model-index:
+- name: out/qwen3-8b-persistent-navigation-20260525_121743
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.13.2`
+```yaml
+adapter: lora
+base_model: Qwen/Qwen3-8B
+bf16: true
+bnb_4bit_compute_dtype: bfloat16
+bnb_4bit_quant_type: nf4
+bnb_4bit_use_double_quant: true
+dataset_prepared_path: out/prepared_dataset_persistent
+  message_field_content: content
+  message_field_role: role
+  path: /e/project1/reformo/salgarkar1/agents_learn/pythonformer-workshop/paired/train/out/paired_data/persistent/navigation/traces.jsonl
+  roles_to_train:
+  - assistant
+  type: chat_template
+eval_steps: 5
+flash_attention: true
+gradient_accumulation_steps: 16
+gradient_checkpointing: true
+gradient_checkpointing_kwargs:
+  use_reentrant: false
+learning_rate: 0.0001
+load_in_4bit: true
+load_in_8bit: false
+logging_steps: 1
+lora_alpha: 128
+lora_dropout: 0.05
+lora_r: 64
+lora_target_linear: false
+lora_target_modules:
+- q_proj
+- k_proj
+- v_proj
+- o_proj
+- gate_proj
+- up_proj
+- down_proj
+lr_scheduler: cosine
+micro_batch_size: 1
+model_type: AutoModelForCausalLM
+num_epochs: 3.0
+optimizer: adamw_torch
+output_dir: out/qwen3-8b-persistent-navigation-20260525_121743
+pad_to_sequence_len: true
+sample_packing: false
+save_strategy: epoch
+save_total_limit: 3
+seed: 3407
+sequence_len: 16384
+strict: false
+tf32: true
+tokenizer_type: AutoTokenizer
+trust_remote_code: true
+val_set_size: 0.04
+wandb_log_model: null
+wandb_project: pythonformer
+wandb_watch: null
+warmup_ratio: 0.03
+weight_decay: 0.01
+
+```
+
+</details><br>
+
+# out/qwen3-8b-persistent-navigation-20260525_121743
+
+This model is a fine-tuned version of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) on the /e/project1/reformo/salgarkar1/agents_learn/pythonformer-workshop/paired/train/out/paired_data/persistent/navigation/traces.jsonl dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2875
+- Ppl: 1.3331
+- Memory/max Active (gib): 54.54
+- Memory/max Allocated (gib): 54.54
+- Memory/device Reserved (gib): 66.97
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0001
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 3407
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 64
+- total_eval_batch_size: 4
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 2
+- training_steps: 45
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Ppl    | Active (gib) | Allocated (gib) | Reserved (gib) |
+|:-------------:|:------:|:----:|:---------------:|:------:|:------------:|:---------------:|:--------------:|
+| No log        | 0      | 0    | 0.9681          | 2.6330 | 53.19        | 53.19           | 56.52          |
+| 0.6197        | 0.3333 | 5    | 0.5761          | 1.7792 | 54.54        | 54.54           | 66.97          |
+| 0.4796        | 0.6667 | 10   | 0.4404          | 1.5533 | 54.54        | 54.54           | 66.97          |
+| 0.4179        | 1.0    | 15   | 0.3768          | 1.4576 | 54.54        | 54.54           | 66.97          |
+| 0.3473        | 1.3333 | 20   | 0.3375          | 1.4014 | 54.54        | 54.54           | 66.97          |
+| 0.3125        | 1.6667 | 25   | 0.3142          | 1.3692 | 54.54        | 54.54           | 66.97          |
+| 0.3015        | 2.0    | 30   | 0.2998          | 1.3496 | 54.54        | 54.54           | 66.97          |
+| 0.3033        | 2.3333 | 35   | 0.2914          | 1.3383 | 54.54        | 54.54           | 66.97          |
+| 0.2925        | 2.6667 | 40   | 0.2881          | 1.3339 | 54.54        | 54.54           | 66.97          |
+| 0.2815        | 3.0    | 45   | 0.2875          | 1.3331 | 54.54        | 54.54           | 66.97          |
+
+
+### Framework versions
+
+- PEFT 0.18.1
+- Transformers 4.57.6
+- Pytorch 2.10.0+cu128
+- Datasets 4.5.0
+- Tokenizers 0.22.2

adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-8B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "up_proj",
+    "k_proj",
+    "q_proj",
+    "v_proj",
+    "o_proj",
+    "gate_proj"
+  ],
+  "target_parameters": [],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b9f7490fc288d80e23e9312aa3324a741d50f549892ec85c177c3844de944cf
+size 698419728

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

axolotl_config.yaml

@@ -0,0 +1,59 @@
+adapter: lora
+base_model: Qwen/Qwen3-8B
+bf16: true
+bnb_4bit_compute_dtype: bfloat16
+bnb_4bit_quant_type: nf4
+bnb_4bit_use_double_quant: true
+dataset_prepared_path: out/prepared_dataset_persistent
+datasets:
+- field_messages: messages
+  message_field_content: content
+  message_field_role: role
+  path: /e/project1/reformo/salgarkar1/agents_learn/pythonformer-workshop/paired/train/out/paired_data/persistent/navigation/traces.jsonl
+  roles_to_train:
+  - assistant
+  type: chat_template
+eval_steps: 5
+flash_attention: true
+gradient_accumulation_steps: 16
+gradient_checkpointing: true
+gradient_checkpointing_kwargs:
+  use_reentrant: false
+learning_rate: 0.0001
+load_in_4bit: true
+load_in_8bit: false
+logging_steps: 1
+lora_alpha: 128
+lora_dropout: 0.05
+lora_r: 64
+lora_target_linear: false
+lora_target_modules:
+- q_proj
+- k_proj
+- v_proj
+- o_proj
+- gate_proj
+- up_proj
+- down_proj
+lr_scheduler: cosine
+micro_batch_size: 1
+model_type: AutoModelForCausalLM
+num_epochs: 3.0
+optimizer: adamw_torch
+output_dir: out/qwen3-8b-persistent-navigation-20260525_121743
+pad_to_sequence_len: true
+sample_packing: false
+save_strategy: epoch
+save_total_limit: 3
+seed: 3407
+sequence_len: 16384
+strict: false
+tf32: true
+tokenizer_type: AutoTokenizer
+trust_remote_code: true
+val_set_size: 0.04
+wandb_log_model: null
+wandb_project: pythonformer
+wandb_watch: null
+warmup_ratio: 0.03
+weight_decay: 0.01

chat_template.jinja

@@ -0,0 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

checkpoint-15/README.md

@@ -0,0 +1,208 @@
+---
+base_model: Qwen/Qwen3-8B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- axolotl
+- base_model:adapter:Qwen/Qwen3-8B
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1

checkpoint-15/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-8B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "up_proj",
+    "k_proj",
+    "q_proj",
+    "v_proj",
+    "o_proj",
+    "gate_proj"
+  ],
+  "target_parameters": [],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-15/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a424a07444d8801c61363ede5838fe0a3b1ece9c763b0a04913f4e925c1e4f6
+size 698419728

checkpoint-15/added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-15/chat_template.jinja

@@ -0,0 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

checkpoint-15/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2f3ce1aa2d23b1d57c8daa08a5571c8d904c713bd261549f1d6123c2504a763
+size 1397129547

checkpoint-15/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:496746c025033ccca094cf576ed1eb0f145196ed098b29f65b56574a14a7ee6b
+size 15365

checkpoint-15/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:056dbea0bf0d9d396680103ec97451cd90cb37143c4d895670deea21d204e4cc
+size 15365

checkpoint-15/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec1c69ad1a3d03c412c1aaae71718a480e62ccf093c8637b20080e9b7791c6dd
+size 15365

checkpoint-15/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d167f8d65ca93ec772522ec91fa16b69d7bb75de3245e8dfcc640ece42367379
+size 15365

checkpoint-15/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8695a61368b93d1f64286e236be6bd97b3d8eacd7521fd85ce42e4739ba154f9
+size 1465

checkpoint-15/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-15/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

checkpoint-15/tokenizer_config.json

@@ -0,0 +1,239 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-15/tokens_state.

@@ -0,0 +1 @@
+{"total": 15728640, "trainable": 1275757}

checkpoint-15/trainer_state.json

@@ -0,0 +1,292 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 5,
+  "global_step": 15,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0,
+      "eval_loss": 0.9681045413017273,
+      "eval_ppl": 2.63295,
+      "eval_runtime": 9.5712,
+      "eval_samples_per_second": 4.179,
+      "eval_steps_per_second": 1.045,
+      "memory/device_reserved (GiB)": 56.52,
+      "memory/max_active (GiB)": 53.19,
+      "memory/max_allocated (GiB)": 53.19,
+      "step": 0
+    },
+    {
+      "epoch": 0.06666666666666667,
+      "grad_norm": 3.6055057048797607,
+      "learning_rate": 0.0,
+      "loss": 0.9844,
+      "memory/device_reserved (GiB)": 66.97,
+      "memory/max_active (GiB)": 62.8,
+      "memory/max_allocated (GiB)": 62.8,
+      "ppl": 2.67621,
+      "step": 1,
+      "tokens/total": 1048576,
+      "tokens/train_per_sec_per_gpu": 99.89,
+      "tokens/trainable": 77925
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 3.3668525218963623,
+      "learning_rate": 5e-05,
+      "loss": 0.9794,
+      "memory/device_reserved (GiB)": 66.97,
+      "memory/max_active (GiB)": 64.12,
+      "memory/max_allocated (GiB)": 64.12,
+      "ppl": 2.66286,
+      "step": 2,
+      "tokens/total": 2097152,
+      "tokens/train_per_sec_per_gpu": 93.93,
+      "tokens/trainable": 163858
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 1.4857083559036255,
+      "learning_rate": 0.0001,
+      "loss": 0.7875,
+      "memory/device_reserved (GiB)": 66.97,
+      "memory/max_active (GiB)": 64.12,
+      "memory/max_allocated (GiB)": 64.12,
+      "ppl": 2.19789,
+      "step": 3,
+      "tokens/total": 3145728,
+      "tokens/train_per_sec_per_gpu": 90.68,
+      "tokens/trainable": 243851
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.5946469902992249,
+      "learning_rate": 9.986661418317759e-05,
+      "loss": 0.6776,
+      "memory/device_reserved (GiB)": 66.97,
+      "memory/max_active (GiB)": 64.12,
+      "memory/max_allocated (GiB)": 64.12,
+      "ppl": 1.96915,
+      "step": 4,
+      "tokens/total": 4194304,
+      "tokens/train_per_sec_per_gpu": 112.97,
+      "tokens/trainable": 331508
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.35739865899086,
+      "learning_rate": 9.946716840375551e-05,
+      "loss": 0.6197,
+      "memory/device_reserved (GiB)": 66.97,
+      "memory/max_active (GiB)": 64.13,
+      "memory/max_allocated (GiB)": 64.13,
+      "ppl": 1.85837,
+      "step": 5,
+      "tokens/total": 5242880,
+      "tokens/train_per_sec_per_gpu": 111.47,
+      "tokens/trainable": 420940
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "eval_loss": 0.5761364102363586,
+      "eval_ppl": 1.77915,
+      "eval_runtime": 9.4945,
+      "eval_samples_per_second": 4.213,
+      "eval_steps_per_second": 1.053,
+      "memory/device_reserved (GiB)": 66.97,
+      "memory/max_active (GiB)": 54.54,
+      "memory/max_allocated (GiB)": 54.54,
+      "step": 5
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.30389270186424255,
+      "learning_rate": 9.880379387779637e-05,
+      "loss": 0.5976,
+      "memory/device_reserved (GiB)": 66.97,
+      "memory/max_active (GiB)": 64.12,
+      "memory/max_allocated (GiB)": 64.12,
+      "ppl": 1.81775,
+      "step": 6,
+      "tokens/total": 6291456,
+      "tokens/train_per_sec_per_gpu": 102.37,
+      "tokens/trainable": 504211
+    },
+    {
+      "epoch": 0.4666666666666667,
+      "grad_norm": 0.29107972979545593,
+      "learning_rate": 9.78800299954203e-05,
+      "loss": 0.5493,
+      "memory/device_reserved (GiB)": 66.97,
+      "memory/max_active (GiB)": 64.12,
+      "memory/max_allocated (GiB)": 64.12,
+      "ppl": 1.73204,
+      "step": 7,
+      "tokens/total": 7340032,
+      "tokens/train_per_sec_per_gpu": 120.1,
+      "tokens/trainable": 586769
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.2634803354740143,
+      "learning_rate": 9.67008054366274e-05,
+      "loss": 0.5306,
+      "memory/device_reserved (GiB)": 66.97,
+      "memory/max_active (GiB)": 64.12,
+      "memory/max_allocated (GiB)": 64.12,
+      "ppl": 1.69995,
+      "step": 8,
+      "tokens/total": 8388608,
+      "tokens/train_per_sec_per_gpu": 114.32,
+      "tokens/trainable": 674991
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.2511760890483856,
+      "learning_rate": 9.527241187465734e-05,
+      "loss": 0.4969,
+      "memory/device_reserved (GiB)": 66.97,
+      "memory/max_active (GiB)": 64.13,
+      "memory/max_allocated (GiB)": 64.13,
+      "ppl": 1.64362,
+      "step": 9,
+      "tokens/total": 9437184,
+      "tokens/train_per_sec_per_gpu": 116.69,
+      "tokens/trainable": 752848
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.21181228756904602,
+      "learning_rate": 9.360247040719039e-05,
+      "loss": 0.4796,
+      "memory/device_reserved (GiB)": 66.97,
+      "memory/max_active (GiB)": 64.12,
+      "memory/max_allocated (GiB)": 64.12,
+      "ppl": 1.61543,
+      "step": 10,
+      "tokens/total": 10485760,
+      "tokens/train_per_sec_per_gpu": 100.84,
+      "tokens/trainable": 839780
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "eval_loss": 0.44040805101394653,
+      "eval_ppl": 1.55334,
+      "eval_runtime": 9.4408,
+      "eval_samples_per_second": 4.237,
+      "eval_steps_per_second": 1.059,
+      "memory/device_reserved (GiB)": 66.97,
+      "memory/max_active (GiB)": 54.54,
+      "memory/max_allocated (GiB)": 54.54,
+      "step": 10
+    },
+    {
+      "epoch": 0.7333333333333333,
+      "grad_norm": 0.16248875856399536,
+      "learning_rate": 9.16998908944939e-05,
+      "loss": 0.4565,
+      "memory/device_reserved (GiB)": 66.97,
+      "memory/max_active (GiB)": 64.12,
+      "memory/max_allocated (GiB)": 64.12,
+      "ppl": 1.57854,
+      "step": 11,
+      "tokens/total": 11534336,
+      "tokens/train_per_sec_per_gpu": 125.3,
+      "tokens/trainable": 929267
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.15751507878303528,
+      "learning_rate": 8.957482442146272e-05,
+      "loss": 0.44,
+      "memory/device_reserved (GiB)": 66.97,
+      "memory/max_active (GiB)": 64.12,
+      "memory/max_allocated (GiB)": 64.12,
+      "ppl": 1.55271,
+      "step": 12,
+      "tokens/total": 12582912,
+      "tokens/train_per_sec_per_gpu": 147.86,
+      "tokens/trainable": 1012131
+    },
+    {
+      "epoch": 0.8666666666666667,
+      "grad_norm": 0.16444867849349976,
+      "learning_rate": 8.72386091371891e-05,
+      "loss": 0.4461,
+      "memory/device_reserved (GiB)": 66.97,
+      "memory/max_active (GiB)": 64.13,
+      "memory/max_allocated (GiB)": 64.13,
+      "ppl": 1.56221,
+      "step": 13,
+      "tokens/total": 13631488,
+      "tokens/train_per_sec_per_gpu": 103.92,
+      "tokens/trainable": 1103069
+    },
+    {
+      "epoch": 0.9333333333333333,
+      "grad_norm": 0.17406685650348663,
+      "learning_rate": 8.47037097610317e-05,
+      "loss": 0.4204,
+      "memory/device_reserved (GiB)": 66.97,
+      "memory/max_active (GiB)": 64.12,
+      "memory/max_allocated (GiB)": 64.12,
+      "ppl": 1.52257,
+      "step": 14,
+      "tokens/total": 14680064,
+      "tokens/train_per_sec_per_gpu": 113.35,
+      "tokens/trainable": 1189578
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.18400150537490845,
+      "learning_rate": 8.198365107794457e-05,
+      "loss": 0.4179,
+      "memory/device_reserved (GiB)": 66.97,
+      "memory/max_active (GiB)": 64.12,
+      "memory/max_allocated (GiB)": 64.12,
+      "ppl": 1.51877,
+      "step": 15,
+      "tokens/total": 15728640,
+      "tokens/train_per_sec_per_gpu": 87.22,
+      "tokens/trainable": 1275757
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.3768181800842285,
+      "eval_ppl": 1.45764,
+      "eval_runtime": 9.4968,
+      "eval_samples_per_second": 4.212,
+      "eval_steps_per_second": 1.053,
+      "memory/device_reserved (GiB)": 66.97,
+      "memory/max_active (GiB)": 54.54,
+      "memory/max_allocated (GiB)": 54.54,
+      "step": 15
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 45,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 7.307205672330854e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-15/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ece1b282edbe7a80d4c287780ed395c9db305cc7252dea473a421b90ab61b16
+size 7441

checkpoint-30/README.md

@@ -0,0 +1,208 @@
+---
+base_model: Qwen/Qwen3-8B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- axolotl
+- base_model:adapter:Qwen/Qwen3-8B
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1

checkpoint-30/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-8B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "up_proj",
+    "k_proj",
+    "q_proj",
+    "v_proj",
+    "o_proj",
+    "gate_proj"
+  ],
+  "target_parameters": [],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-30/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4dce836883522037c98bd0aa4bf240a061247ec6a26395f1cfc32063f18f32ac
+size 698419728

checkpoint-30/added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-30/chat_template.jinja

@@ -0,0 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

checkpoint-30/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f289ef1aee3e6565785edbfe8462b7a1a880cbe305efa983b0217a2c6886add
+size 1397129547

checkpoint-30/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b92d410fd625839e8eb3ff182d30b69c6a4fb8c3ab7c5f18910649217d725c94
+size 15365

checkpoint-30/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29797b012fb38b628e3674683416cb210e4395042901b43fb9cd4078e863094e
+size 15365

checkpoint-30/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c091ad25f52f9b6c36c380774a32570693bc31edf4de9fa30dd7533b733a5e4d
+size 15365

checkpoint-30/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9228d993b8d07a2fcdd59130f87f4adeccbd90c8f662161cd556fcf1a9539ba1
+size 15365

checkpoint-30/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d815b38ce520c275574aabdbad559a0c92a1d36cfd393654e19d9df91982b42
+size 1465

checkpoint-30/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-30/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

checkpoint-30/tokenizer_config.json

@@ -0,0 +1,239 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-30/tokens_state.

@@ -0,0 +1 @@
+{"total": 31457280, "trainable": 2551514}

checkpoint-30/trainer_state.json

@@ -0,0 +1,538 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 5,
+  "global_step": 30,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0,
+      "eval_loss": 0.9681045413017273,
+      "eval_ppl": 2.63295,
+      "eval_runtime": 9.5712,
+      "eval_samples_per_second": 4.179,
+      "eval_steps_per_second": 1.045,
+      "memory/device_reserved (GiB)": 56.52,
+      "memory/max_active (GiB)": 53.19,
+      "memory/max_allocated (GiB)": 53.19,
+      "step": 0
+    },
+    {
+      "epoch": 0.06666666666666667,
+      "grad_norm": 3.6055057048797607,
+      "learning_rate": 0.0,
+      "loss": 0.9844,
+      "memory/device_reserved (GiB)": 66.97,
+      "memory/max_active (GiB)": 62.8,
+      "memory/max_allocated (GiB)": 62.8,
+      "ppl": 2.67621,
+      "step": 1,
+      "tokens/total": 1048576,
+      "tokens/train_per_sec_per_gpu": 99.89,
+      "tokens/trainable": 77925
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 3.3668525218963623,
+      "learning_rate": 5e-05,
+      "loss": 0.9794,
+      "memory/device_reserved (GiB)": 66.97,
+      "memory/max_active (GiB)": 64.12,
+      "memory/max_allocated (GiB)": 64.12,
+      "ppl": 2.66286,
+      "step": 2,
+      "tokens/total": 2097152,
+      "tokens/train_per_sec_per_gpu": 93.93,
+      "tokens/trainable": 163858
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 1.4857083559036255,
+      "learning_rate": 0.0001,
+      "loss": 0.7875,
+      "memory/device_reserved (GiB)": 66.97,
+      "memory/max_active (GiB)": 64.12,
+      "memory/max_allocated (GiB)": 64.12,
+      "ppl": 2.19789,
+      "step": 3,
+      "tokens/total": 3145728,
+      "tokens/train_per_sec_per_gpu": 90.68,
+      "tokens/trainable": 243851
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.5946469902992249,
+      "learning_rate": 9.986661418317759e-05,
+      "loss": 0.6776,
+      "memory/device_reserved (GiB)": 66.97,
+      "memory/max_active (GiB)": 64.12,
+      "memory/max_allocated (GiB)": 64.12,
+      "ppl": 1.96915,
+      "step": 4,
+      "tokens/total": 4194304,
+      "tokens/train_per_sec_per_gpu": 112.97,
+      "tokens/trainable": 331508
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.35739865899086,
+      "learning_rate": 9.946716840375551e-05,
+      "loss": 0.6197,
+      "memory/device_reserved (GiB)": 66.97,
+      "memory/max_active (GiB)": 64.13,
+      "memory/max_allocated (GiB)": 64.13,
+      "ppl": 1.85837,
+      "step": 5,
+      "tokens/total": 5242880,
+      "tokens/train_per_sec_per_gpu": 111.47,
+      "tokens/trainable": 420940
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "eval_loss": 0.5761364102363586,
+      "eval_ppl": 1.77915,
+      "eval_runtime": 9.4945,
+      "eval_samples_per_second": 4.213,
+      "eval_steps_per_second": 1.053,
+      "memory/device_reserved (GiB)": 66.97,
+      "memory/max_active (GiB)": 54.54,
+      "memory/max_allocated (GiB)": 54.54,
+      "step": 5
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.30389270186424255,
+      "learning_rate": 9.880379387779637e-05,
+      "loss": 0.5976,
+      "memory/device_reserved (GiB)": 66.97,
+      "memory/max_active (GiB)": 64.12,
+      "memory/max_allocated (GiB)": 64.12,
+      "ppl": 1.81775,
+      "step": 6,
+      "tokens/total": 6291456,
+      "tokens/train_per_sec_per_gpu": 102.37,
+      "tokens/trainable": 504211
+    },
+    {
+      "epoch": 0.4666666666666667,
+      "grad_norm": 0.29107972979545593,
+      "learning_rate": 9.78800299954203e-05,
+      "loss": 0.5493,
+      "memory/device_reserved (GiB)": 66.97,
+      "memory/max_active (GiB)": 64.12,
+      "memory/max_allocated (GiB)": 64.12,
+      "ppl": 1.73204,
+      "step": 7,
+      "tokens/total": 7340032,
+      "tokens/train_per_sec_per_gpu": 120.1,
+      "tokens/trainable": 586769
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.2634803354740143,
+      "learning_rate": 9.67008054366274e-05,
+      "loss": 0.5306,
+      "memory/device_reserved (GiB)": 66.97,
+      "memory/max_active (GiB)": 64.12,
+      "memory/max_allocated (GiB)": 64.12,
+      "ppl": 1.69995,
+      "step": 8,
+      "tokens/total": 8388608,
+      "tokens/train_per_sec_per_gpu": 114.32,
+      "tokens/trainable": 674991
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.2511760890483856,
+      "learning_rate": 9.527241187465734e-05,
+      "loss": 0.4969,
+      "memory/device_reserved (GiB)": 66.97,
+      "memory/max_active (GiB)": 64.13,
+      "memory/max_allocated (GiB)": 64.13,
+      "ppl": 1.64362,
+      "step": 9,
+      "tokens/total": 9437184,
+      "tokens/train_per_sec_per_gpu": 116.69,
+      "tokens/trainable": 752848
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.21181228756904602,
+      "learning_rate": 9.360247040719039e-05,
+      "loss": 0.4796,
+      "memory/device_reserved (GiB)": 66.97,
+      "memory/max_active (GiB)": 64.12,
+      "memory/max_allocated (GiB)": 64.12,
+      "ppl": 1.61543,
+      "step": 10,
+      "tokens/total": 10485760,
+      "tokens/train_per_sec_per_gpu": 100.84,
+      "tokens/trainable": 839780
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "eval_loss": 0.44040805101394653,
+      "eval_ppl": 1.55334,
+      "eval_runtime": 9.4408,
+      "eval_samples_per_second": 4.237,
+      "eval_steps_per_second": 1.059,
+      "memory/device_reserved (GiB)": 66.97,
+      "memory/max_active (GiB)": 54.54,
+      "memory/max_allocated (GiB)": 54.54,
+      "step": 10
+    },
+    {
+      "epoch": 0.7333333333333333,
+      "grad_norm": 0.16248875856399536,
+      "learning_rate": 9.16998908944939e-05,
+      "loss": 0.4565,
+      "memory/device_reserved (GiB)": 66.97,
+      "memory/max_active (GiB)": 64.12,
+      "memory/max_allocated (GiB)": 64.12,
+      "ppl": 1.57854,
+      "step": 11,
+      "tokens/total": 11534336,
+      "tokens/train_per_sec_per_gpu": 125.3,
+      "tokens/trainable": 929267
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.15751507878303528,
+      "learning_rate": 8.957482442146272e-05,
+      "loss": 0.44,
+      "memory/device_reserved (GiB)": 66.97,
+      "memory/max_active (GiB)": 64.12,
+      "memory/max_allocated (GiB)": 64.12,
+      "ppl": 1.55271,
+      "step": 12,
+      "tokens/total": 12582912,
+      "tokens/train_per_sec_per_gpu": 147.86,
+      "tokens/trainable": 1012131
+    },
+    {
+      "epoch": 0.8666666666666667,
+      "grad_norm": 0.16444867849349976,
+      "learning_rate": 8.72386091371891e-05,
+      "loss": 0.4461,
+      "memory/device_reserved (GiB)": 66.97,
+      "memory/max_active (GiB)": 64.13,
+      "memory/max_allocated (GiB)": 64.13,
+      "ppl": 1.56221,
+      "step": 13,
+      "tokens/total": 13631488,
+      "tokens/train_per_sec_per_gpu": 103.92,
+      "tokens/trainable": 1103069
+    },
+    {
+      "epoch": 0.9333333333333333,
+      "grad_norm": 0.17406685650348663,
+      "learning_rate": 8.47037097610317e-05,
+      "loss": 0.4204,
+      "memory/device_reserved (GiB)": 66.97,
+      "memory/max_active (GiB)": 64.12,
+      "memory/max_allocated (GiB)": 64.12,
+      "ppl": 1.52257,
+      "step": 14,
+      "tokens/total": 14680064,
+      "tokens/train_per_sec_per_gpu": 113.35,
+      "tokens/trainable": 1189578
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.18400150537490845,
+      "learning_rate": 8.198365107794457e-05,
+      "loss": 0.4179,
+      "memory/device_reserved (GiB)": 66.97,
+      "memory/max_active (GiB)": 64.12,
+      "memory/max_allocated (GiB)": 64.12,
+      "ppl": 1.51877,
+      "step": 15,
+      "tokens/total": 15728640,
+      "tokens/train_per_sec_per_gpu": 87.22,
+      "tokens/trainable": 1275757
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.3768181800842285,
+      "eval_ppl": 1.45764,
+      "eval_runtime": 9.4968,
+      "eval_samples_per_second": 4.212,
+      "eval_steps_per_second": 1.053,
+      "memory/device_reserved (GiB)": 66.97,
+      "memory/max_active (GiB)": 54.54,
+      "memory/max_allocated (GiB)": 54.54,
+      "step": 15
+    },
+    {
+      "epoch": 1.0666666666666667,
+      "grad_norm": 0.17585863173007965,
+      "learning_rate": 7.909294577789766e-05,
+      "loss": 0.3876,
+      "memory/device_reserved (GiB)": 66.97,
+      "memory/max_active (GiB)": 64.12,
+      "memory/max_allocated (GiB)": 64.12,
+      "ppl": 1.47344,
+      "step": 16,
+      "tokens/total": 16777216,
+      "tokens/train_per_sec_per_gpu": 109.05,
+      "tokens/trainable": 1359118
+    },
+    {
+      "epoch": 1.1333333333333333,
+      "grad_norm": 0.1488562822341919,
+      "learning_rate": 7.604701702439651e-05,
+      "loss": 0.3814,
+      "memory/device_reserved (GiB)": 66.97,
+      "memory/max_active (GiB)": 64.12,
+      "memory/max_allocated (GiB)": 64.12,
+      "ppl": 1.46433,
+      "step": 17,
+      "tokens/total": 17825792,
+      "tokens/train_per_sec_per_gpu": 106.73,
+      "tokens/trainable": 1443638
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.13896878063678741,
+      "learning_rate": 7.286211616523193e-05,
+      "loss": 0.3648,
+      "memory/device_reserved (GiB)": 66.97,
+      "memory/max_active (GiB)": 64.12,
+      "memory/max_allocated (GiB)": 64.12,
+      "ppl": 1.44023,
+      "step": 18,
+      "tokens/total": 18874368,
+      "tokens/train_per_sec_per_gpu": 93.25,
+      "tokens/trainable": 1527473
+    },
+    {
+      "epoch": 1.2666666666666666,
+      "grad_norm": 0.11720948666334152,
+      "learning_rate": 6.95552360245078e-05,
+      "loss": 0.3512,
+      "memory/device_reserved (GiB)": 66.97,
+      "memory/max_active (GiB)": 64.12,
+      "memory/max_allocated (GiB)": 64.12,
+      "ppl": 1.42077,
+      "step": 19,
+      "tokens/total": 19922944,
+      "tokens/train_per_sec_per_gpu": 87.11,
+      "tokens/trainable": 1615421
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.12244201451539993,
+      "learning_rate": 6.614402023857232e-05,
+      "loss": 0.3473,
+      "memory/device_reserved (GiB)": 66.97,
+      "memory/max_active (GiB)": 64.12,
+      "memory/max_allocated (GiB)": 64.12,
+      "ppl": 1.41524,
+      "step": 20,
+      "tokens/total": 20971520,
+      "tokens/train_per_sec_per_gpu": 108.7,
+      "tokens/trainable": 1697031
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "eval_loss": 0.3374583125114441,
+      "eval_ppl": 1.40138,
+      "eval_runtime": 9.3994,
+      "eval_samples_per_second": 4.256,
+      "eval_steps_per_second": 1.064,
+      "memory/device_reserved (GiB)": 66.97,
+      "memory/max_active (GiB)": 54.54,
+      "memory/max_allocated (GiB)": 54.54,
+      "step": 20
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.12614424526691437,
+      "learning_rate": 6.264666911958404e-05,
+      "loss": 0.355,
+      "memory/device_reserved (GiB)": 66.97,
+      "memory/max_active (GiB)": 64.12,
+      "memory/max_allocated (GiB)": 64.12,
+      "ppl": 1.42618,
+      "step": 21,
+      "tokens/total": 22020096,
+      "tokens/train_per_sec_per_gpu": 89.89,
+      "tokens/trainable": 1778284
+    },
+    {
+      "epoch": 1.4666666666666668,
+      "grad_norm": 0.12772953510284424,
+      "learning_rate": 5.908184254897182e-05,
+      "loss": 0.3504,
+      "memory/device_reserved (GiB)": 66.97,
+      "memory/max_active (GiB)": 64.12,
+      "memory/max_allocated (GiB)": 64.12,
+      "ppl": 1.41964,
+      "step": 22,
+      "tokens/total": 23068672,
+      "tokens/train_per_sec_per_gpu": 133.74,
+      "tokens/trainable": 1863358
+    },
+    {
+      "epoch": 1.5333333333333332,
+      "grad_norm": 0.11631076782941818,
+      "learning_rate": 5.546856041889373e-05,
+      "loss": 0.3644,
+      "memory/device_reserved (GiB)": 66.97,
+      "memory/max_active (GiB)": 64.12,
+      "memory/max_allocated (GiB)": 64.12,
+      "ppl": 1.43965,
+      "step": 23,
+      "tokens/total": 24117248,
+      "tokens/train_per_sec_per_gpu": 97.81,
+      "tokens/trainable": 1956710
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.12257759273052216,
+      "learning_rate": 5.182610115288295e-05,
+      "loss": 0.3211,
+      "memory/device_reserved (GiB)": 66.97,
+      "memory/max_active (GiB)": 64.12,
+      "memory/max_allocated (GiB)": 64.12,
+      "ppl": 1.37864,
+      "step": 24,
+      "tokens/total": 25165824,
+      "tokens/train_per_sec_per_gpu": 102.96,
+      "tokens/trainable": 2036417
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.10963135957717896,
+      "learning_rate": 4.817389884711705e-05,
+      "loss": 0.3125,
+      "memory/device_reserved (GiB)": 66.97,
+      "memory/max_active (GiB)": 64.12,
+      "memory/max_allocated (GiB)": 64.12,
+      "ppl": 1.36684,
+      "step": 25,
+      "tokens/total": 26214400,
+      "tokens/train_per_sec_per_gpu": 93.01,
+      "tokens/trainable": 2115620
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "eval_loss": 0.31419986486434937,
+      "eval_ppl": 1.36916,
+      "eval_runtime": 9.4055,
+      "eval_samples_per_second": 4.253,
+      "eval_steps_per_second": 1.063,
+      "memory/device_reserved (GiB)": 66.97,
+      "memory/max_active (GiB)": 54.54,
+      "memory/max_allocated (GiB)": 54.54,
+      "step": 25
+    },
+    {
+      "epoch": 1.7333333333333334,
+      "grad_norm": 0.10058556497097015,
+      "learning_rate": 4.4531439581106295e-05,
+      "loss": 0.3463,
+      "memory/device_reserved (GiB)": 66.97,
+      "memory/max_active (GiB)": 64.12,
+      "memory/max_allocated (GiB)": 64.12,
+      "ppl": 1.41383,
+      "step": 26,
+      "tokens/total": 27262976,
+      "tokens/train_per_sec_per_gpu": 113.03,
+      "tokens/trainable": 2206816
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.10328979045152664,
+      "learning_rate": 4.0918157451028185e-05,
+      "loss": 0.3385,
+      "memory/device_reserved (GiB)": 66.97,
+      "memory/max_active (GiB)": 64.13,
+      "memory/max_allocated (GiB)": 64.13,
+      "ppl": 1.40284,
+      "step": 27,
+      "tokens/total": 28311552,
+      "tokens/train_per_sec_per_gpu": 94.68,
+      "tokens/trainable": 2296593
+    },
+    {
+      "epoch": 1.8666666666666667,
+      "grad_norm": 0.0950852483510971,
+      "learning_rate": 3.735333088041596e-05,
+      "loss": 0.3226,
+      "memory/device_reserved (GiB)": 66.97,
+      "memory/max_active (GiB)": 64.12,
+      "memory/max_allocated (GiB)": 64.12,
+      "ppl": 1.38071,
+      "step": 28,
+      "tokens/total": 29360128,
+      "tokens/train_per_sec_per_gpu": 90.99,
+      "tokens/trainable": 2384752
+    },
+    {
+      "epoch": 1.9333333333333333,
+      "grad_norm": 0.10383325070142746,
+      "learning_rate": 3.38559797614277e-05,
+      "loss": 0.3298,
+      "memory/device_reserved (GiB)": 66.97,
+      "memory/max_active (GiB)": 64.12,
+      "memory/max_allocated (GiB)": 64.12,
+      "ppl": 1.39069,
+      "step": 29,
+      "tokens/total": 30408704,
+      "tokens/train_per_sec_per_gpu": 101.1,
+      "tokens/trainable": 2468836
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.0998990386724472,
+      "learning_rate": 3.0444763975492208e-05,
+      "loss": 0.3015,
+      "memory/device_reserved (GiB)": 66.97,
+      "memory/max_active (GiB)": 64.12,
+      "memory/max_allocated (GiB)": 64.12,
+      "ppl": 1.35189,
+      "step": 30,
+      "tokens/total": 31457280,
+      "tokens/train_per_sec_per_gpu": 109.47,
+      "tokens/trainable": 2551514
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.299793541431427,
+      "eval_ppl": 1.34958,
+      "eval_runtime": 9.494,
+      "eval_samples_per_second": 4.213,
+      "eval_steps_per_second": 1.053,
+      "memory/device_reserved (GiB)": 66.97,
+      "memory/max_active (GiB)": 54.54,
+      "memory/max_allocated (GiB)": 54.54,
+      "step": 30
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 45,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 1.461441134466171e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-30/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ece1b282edbe7a80d4c287780ed395c9db305cc7252dea473a421b90ab61b16
+size 7441

checkpoint-45/README.md

@@ -0,0 +1,208 @@
+---
+base_model: Qwen/Qwen3-8B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- axolotl
+- base_model:adapter:Qwen/Qwen3-8B
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1

checkpoint-45/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-8B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "up_proj",
+    "k_proj",
+    "q_proj",
+    "v_proj",
+    "o_proj",
+    "gate_proj"
+  ],
+  "target_parameters": [],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-45/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b9f7490fc288d80e23e9312aa3324a741d50f549892ec85c177c3844de944cf
+size 698419728

checkpoint-45/added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-45/chat_template.jinja

@@ -0,0 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}