Upload folder using huggingface_hub

.gitattributes

@@ -52,3 +52,7 @@ checkpoint-600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-666/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-444/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-190/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-210/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-220/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-230/tokenizer.json filter=lfs diff=lfs merge=lfs -text

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0e5d06a2dd8643083669308f8b726af8760f6484d9f470c4b2434bc16097e2c
+oid sha256:83b32bbab560bf0a9431b34ebdcb2a31a980aea9b38502136c8e2cfc97e24c46
 size 528550256

checkpoint-190/README.md

@@ -0,0 +1,202 @@
+---
+base_model: unsloth/qwen3-4b-instruct-2507-unsloth-bnb-4bit
+library_name: peft
+---
+
+# 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 0.13.2

checkpoint-190/adapter_config.json

@@ -0,0 +1,38 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "Qwen3ForCausalLM",
+    "parent_library": "transformers.models.qwen3.modeling_qwen3",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/qwen3-4b-instruct-2507-unsloth-bnb-4bit",
+  "bias": "none",
+  "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": 128,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "up_proj",
+    "q_proj",
+    "down_proj",
+    "v_proj",
+    "gate_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-190/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d61c745170660f7f47b8e9f0c74aabf3e5b5f40aab19410f15c19e1b1aee8b1
+size 528550256

checkpoint-190/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-190/chat_template.jinja

@@ -0,0 +1,86 @@
+{%- 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' }}
+{%- endif %}

checkpoint-190/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:173ca48875145199a17f3348fe33b28b0c98341ba00255971bc4a506c7f3b0e4
+size 1057397963

checkpoint-190/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f741248800e5f5fe32cf433f7c12cb64c11a23f0366bd9425633a7d0262642fc
+size 14645

checkpoint-190/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:013d747b1c0a18d5ef66c090bed9484b0437af6c3759613d87ab8186d5581454
+size 1465

checkpoint-190/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": "<|vision_pad|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-190/tokenizer.json

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

checkpoint-190/tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "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": 262144,
+  "pad_token": "<|vision_pad|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-190/trainer_state.json

@@ -0,0 +1,319 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.8568207440811725,
+  "eval_steps": 10,
+  "global_step": 190,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04509582863585118,
+      "grad_norm": 4.649589538574219,
+      "learning_rate": 1.173913043478261e-06,
+      "loss": 1.6576,
+      "step": 10
+    },
+    {
+      "epoch": 0.04509582863585118,
+      "eval_loss": 1.9276622533798218,
+      "eval_runtime": 13.2788,
+      "eval_samples_per_second": 14.083,
+      "eval_steps_per_second": 7.079,
+      "step": 10
+    },
+    {
+      "epoch": 0.09019165727170236,
+      "grad_norm": 3.7612740993499756,
+      "learning_rate": 2.4782608695652173e-06,
+      "loss": 1.6856,
+      "step": 20
+    },
+    {
+      "epoch": 0.09019165727170236,
+      "eval_loss": 1.8389543294906616,
+      "eval_runtime": 13.2051,
+      "eval_samples_per_second": 14.161,
+      "eval_steps_per_second": 7.118,
+      "step": 20
+    },
+    {
+      "epoch": 0.13528748590755355,
+      "grad_norm": 3.048597812652588,
+      "learning_rate": 2.993785263797297e-06,
+      "loss": 1.5539,
+      "step": 30
+    },
+    {
+      "epoch": 0.13528748590755355,
+      "eval_loss": 1.6339466571807861,
+      "eval_runtime": 13.2214,
+      "eval_samples_per_second": 14.144,
+      "eval_steps_per_second": 7.11,
+      "step": 30
+    },
+    {
+      "epoch": 0.18038331454340473,
+      "grad_norm": 1.3381422758102417,
+      "learning_rate": 2.9559926521749324e-06,
+      "loss": 1.6382,
+      "step": 40
+    },
+    {
+      "epoch": 0.18038331454340473,
+      "eval_loss": 1.478708028793335,
+      "eval_runtime": 13.3673,
+      "eval_samples_per_second": 13.989,
+      "eval_steps_per_second": 7.032,
+      "step": 40
+    },
+    {
+      "epoch": 0.2254791431792559,
+      "grad_norm": 0.7458074688911438,
+      "learning_rate": 2.8847278242602185e-06,
+      "loss": 1.2616,
+      "step": 50
+    },
+    {
+      "epoch": 0.2254791431792559,
+      "eval_loss": 1.407120943069458,
+      "eval_runtime": 13.2044,
+      "eval_samples_per_second": 14.162,
+      "eval_steps_per_second": 7.119,
+      "step": 50
+    },
+    {
+      "epoch": 0.2705749718151071,
+      "grad_norm": 0.6770926713943481,
+      "learning_rate": 2.7816291068197328e-06,
+      "loss": 1.2366,
+      "step": 60
+    },
+    {
+      "epoch": 0.2705749718151071,
+      "eval_loss": 1.3675240278244019,
+      "eval_runtime": 13.4556,
+      "eval_samples_per_second": 13.898,
+      "eval_steps_per_second": 6.986,
+      "step": 60
+    },
+    {
+      "epoch": 0.3156708004509583,
+      "grad_norm": 0.7203531265258789,
+      "learning_rate": 2.649066664678467e-06,
+      "loss": 1.3251,
+      "step": 70
+    },
+    {
+      "epoch": 0.3156708004509583,
+      "eval_loss": 1.3370201587677002,
+      "eval_runtime": 13.2298,
+      "eval_samples_per_second": 14.135,
+      "eval_steps_per_second": 7.105,
+      "step": 70
+    },
+    {
+      "epoch": 0.36076662908680945,
+      "grad_norm": 0.6693026423454285,
+      "learning_rate": 2.4900880123475463e-06,
+      "loss": 1.2595,
+      "step": 80
+    },
+    {
+      "epoch": 0.36076662908680945,
+      "eval_loss": 1.3134440183639526,
+      "eval_runtime": 13.3078,
+      "eval_samples_per_second": 14.052,
+      "eval_steps_per_second": 7.064,
+      "step": 80
+    },
+    {
+      "epoch": 0.40586245772266066,
+      "grad_norm": 0.5636974573135376,
+      "learning_rate": 2.3083479538733636e-06,
+      "loss": 1.0858,
+      "step": 90
+    },
+    {
+      "epoch": 0.40586245772266066,
+      "eval_loss": 1.2941912412643433,
+      "eval_runtime": 13.1999,
+      "eval_samples_per_second": 14.167,
+      "eval_steps_per_second": 7.121,
+      "step": 90
+    },
+    {
+      "epoch": 0.4509582863585118,
+      "grad_norm": 0.571853756904602,
+      "learning_rate": 2.108024561540242e-06,
+      "loss": 1.2219,
+      "step": 100
+    },
+    {
+      "epoch": 0.4509582863585118,
+      "eval_loss": 1.2784264087677002,
+      "eval_runtime": 13.24,
+      "eval_samples_per_second": 14.124,
+      "eval_steps_per_second": 7.1,
+      "step": 100
+    },
+    {
+      "epoch": 0.496054114994363,
+      "grad_norm": 0.5300303101539612,
+      "learning_rate": 1.8937231250153905e-06,
+      "loss": 1.1319,
+      "step": 110
+    },
+    {
+      "epoch": 0.496054114994363,
+      "eval_loss": 1.264504313468933,
+      "eval_runtime": 13.2023,
+      "eval_samples_per_second": 14.164,
+      "eval_steps_per_second": 7.12,
+      "step": 110
+    },
+    {
+      "epoch": 0.5411499436302142,
+      "grad_norm": 0.5525142550468445,
+      "learning_rate": 1.6703702790757123e-06,
+      "loss": 1.1702,
+      "step": 120
+    },
+    {
+      "epoch": 0.5411499436302142,
+      "eval_loss": 1.2530410289764404,
+      "eval_runtime": 13.2204,
+      "eval_samples_per_second": 14.145,
+      "eval_steps_per_second": 7.11,
+      "step": 120
+    },
+    {
+      "epoch": 0.5862457722660653,
+      "grad_norm": 0.3444017171859741,
+      "learning_rate": 1.4431007438433431e-06,
+      "loss": 1.1054,
+      "step": 130
+    },
+    {
+      "epoch": 0.5862457722660653,
+      "eval_loss": 1.2430415153503418,
+      "eval_runtime": 13.205,
+      "eval_samples_per_second": 14.161,
+      "eval_steps_per_second": 7.119,
+      "step": 130
+    },
+    {
+      "epoch": 0.6313416009019166,
+      "grad_norm": 0.5441855192184448,
+      "learning_rate": 1.2171392812898465e-06,
+      "loss": 1.1249,
+      "step": 140
+    },
+    {
+      "epoch": 0.6313416009019166,
+      "eval_loss": 1.2348647117614746,
+      "eval_runtime": 13.2648,
+      "eval_samples_per_second": 14.097,
+      "eval_steps_per_second": 7.086,
+      "step": 140
+    },
+    {
+      "epoch": 0.6764374295377678,
+      "grad_norm": 0.5227693915367126,
+      "learning_rate": 9.976805817435208e-07,
+      "loss": 1.1867,
+      "step": 150
+    },
+    {
+      "epoch": 0.6764374295377678,
+      "eval_loss": 1.2283574342727661,
+      "eval_runtime": 13.1435,
+      "eval_samples_per_second": 14.228,
+      "eval_steps_per_second": 7.152,
+      "step": 150
+    },
+    {
+      "epoch": 0.7215332581736189,
+      "grad_norm": 0.542244017124176,
+      "learning_rate": 7.89769841721999e-07,
+      "loss": 1.0513,
+      "step": 160
+    },
+    {
+      "epoch": 0.7215332581736189,
+      "eval_loss": 1.223202109336853,
+      "eval_runtime": 13.3114,
+      "eval_samples_per_second": 14.048,
+      "eval_steps_per_second": 7.062,
+      "step": 160
+    },
+    {
+      "epoch": 0.7666290868094702,
+      "grad_norm": 0.43865886330604553,
+      "learning_rate": 5.98186778519257e-07,
+      "loss": 1.1238,
+      "step": 170
+    },
+    {
+      "epoch": 0.7666290868094702,
+      "eval_loss": 1.2190639972686768,
+      "eval_runtime": 13.2662,
+      "eval_samples_per_second": 14.096,
+      "eval_steps_per_second": 7.086,
+      "step": 170
+    },
+    {
+      "epoch": 0.8117249154453213,
+      "grad_norm": 0.4573892056941986,
+      "learning_rate": 4.273357479676508e-07,
+      "loss": 1.1548,
+      "step": 180
+    },
+    {
+      "epoch": 0.8117249154453213,
+      "eval_loss": 1.2160392999649048,
+      "eval_runtime": 13.1667,
+      "eval_samples_per_second": 14.203,
+      "eval_steps_per_second": 7.139,
+      "step": 180
+    },
+    {
+      "epoch": 0.8568207440811725,
+      "grad_norm": 0.476138710975647,
+      "learning_rate": 2.8114449148802547e-07,
+      "loss": 1.2207,
+      "step": 190
+    },
+    {
+      "epoch": 0.8568207440811725,
+      "eval_loss": 1.2139577865600586,
+      "eval_runtime": 13.1987,
+      "eval_samples_per_second": 14.168,
+      "eval_steps_per_second": 7.122,
+      "step": 190
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 230,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 10,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.279254379232051e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-190/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7502fb41baf3b5166c63e35c8025c0cae40cfa667e95a34f273c4a766c0cd18d
+size 5777

checkpoint-200/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99a558bdcc233bc8046cf9b922c38e336351d7ea6a6e88113245f4bb01b982b2
+oid sha256:4a8d3ea3694bf7cbf036c126895cdc016136f9485d4135f0b1eb3b8099b4b2c8
 size 528550256

checkpoint-200/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9282262e189f026ca7b0a3e821eb5bb8ddee5db44bd57a29ca5a8d9df1740fb8
+oid sha256:0e95ecf22bb1ba1fbffbc53107b7dbb6a0877e224dd52b1809955f37a735be8e
 size 1057397963

checkpoint-200/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48501a439449cb16da66a621e108d7871812472355342a77f6636f6ea7a94f44
+oid sha256:9840938ce773d26a33ba35bd439f2132cdcf1056618f87de03af8f26d9b151bd
 size 14645

checkpoint-200/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9614b8f84c8763cebcb77530330f80c759165ac03145be9b1651a233f171688
+oid sha256:660bd785492fc4a21b96fbdc2dd6347301836e3a26d95d1efbe5b7888d7fcb74
 size 1465

checkpoint-200/trainer_state.json

@@ -3,7 +3,7 @@
   "best_metric": null,
   "best_model_checkpoint": null,
   "epoch": 0.9019165727170236,
-  "eval_steps": 50,
+  "eval_steps": 10,
   "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
@@ -11,182 +11,310 @@
   "log_history": [
     {
       "epoch": 0.04509582863585118,
-      "grad_norm": 4.648494720458984,
+      "grad_norm": 4.649589538574219,
       "learning_rate": 1.173913043478261e-06,
-      "loss": 1.6578,
+      "loss": 1.6576,
+      "step": 10
+    },
+    {
+      "epoch": 0.04509582863585118,
+      "eval_loss": 1.9276622533798218,
+      "eval_runtime": 13.2788,
+      "eval_samples_per_second": 14.083,
+      "eval_steps_per_second": 7.079,
       "step": 10
     },
     {
       "epoch": 0.09019165727170236,
-      "grad_norm": 7.20250129699707,
+      "grad_norm": 3.7612740993499756,
       "learning_rate": 2.4782608695652173e-06,
-      "loss": 1.6865,
+      "loss": 1.6856,
+      "step": 20
+    },
+    {
+      "epoch": 0.09019165727170236,
+      "eval_loss": 1.8389543294906616,
+      "eval_runtime": 13.2051,
+      "eval_samples_per_second": 14.161,
+      "eval_steps_per_second": 7.118,
       "step": 20
     },
     {
       "epoch": 0.13528748590755355,
-      "grad_norm": 3.1192681789398193,
-      "learning_rate": 2.993275923901659e-06,
-      "loss": 1.5591,
+      "grad_norm": 3.048597812652588,
+      "learning_rate": 2.993785263797297e-06,
+      "loss": 1.5539,
       "step": 30
     },
+    {
+      "epoch": 0.13528748590755355,
+      "eval_loss": 1.6339466571807861,
+      "eval_runtime": 13.2214,
+      "eval_samples_per_second": 14.144,
+      "eval_steps_per_second": 7.11,
+      "step": 30
+    },
+    {
+      "epoch": 0.18038331454340473,
+      "grad_norm": 1.3381422758102417,
+      "learning_rate": 2.9559926521749324e-06,
+      "loss": 1.6382,
+      "step": 40
+    },
     {
       "epoch": 0.18038331454340473,
-      "grad_norm": 1.3946388959884644,
-      "learning_rate": 2.952402458097761e-06,
-      "loss": 1.6427,
+      "eval_loss": 1.478708028793335,
+      "eval_runtime": 13.3673,
+      "eval_samples_per_second": 13.989,
+      "eval_steps_per_second": 7.032,
       "step": 40
     },
     {
       "epoch": 0.2254791431792559,
-      "grad_norm": 1.1817127466201782,
-      "learning_rate": 2.8754064422891833e-06,
-      "loss": 1.2641,
+      "grad_norm": 0.7458074688911438,
+      "learning_rate": 2.8847278242602185e-06,
+      "loss": 1.2616,
       "step": 50
     },
     {
       "epoch": 0.2254791431792559,
-      "eval_loss": 1.4092315435409546,
-      "eval_runtime": 14.0932,
-      "eval_samples_per_second": 13.269,
-      "eval_steps_per_second": 6.67,
+      "eval_loss": 1.407120943069458,
+      "eval_runtime": 13.2044,
+      "eval_samples_per_second": 14.162,
+      "eval_steps_per_second": 7.119,
       "step": 50
     },
     {
       "epoch": 0.2705749718151071,
-      "grad_norm": 0.6758719086647034,
-      "learning_rate": 2.764202836352026e-06,
-      "loss": 1.2384,
+      "grad_norm": 0.6770926713943481,
+      "learning_rate": 2.7816291068197328e-06,
+      "loss": 1.2366,
+      "step": 60
+    },
+    {
+      "epoch": 0.2705749718151071,
+      "eval_loss": 1.3675240278244019,
+      "eval_runtime": 13.4556,
+      "eval_samples_per_second": 13.898,
+      "eval_steps_per_second": 6.986,
       "step": 60
     },
     {
       "epoch": 0.3156708004509583,
-      "grad_norm": 0.7143831253051758,
-      "learning_rate": 2.621557373567564e-06,
-      "loss": 1.3275,
+      "grad_norm": 0.7203531265258789,
+      "learning_rate": 2.649066664678467e-06,
+      "loss": 1.3251,
+      "step": 70
+    },
+    {
+      "epoch": 0.3156708004509583,
+      "eval_loss": 1.3370201587677002,
+      "eval_runtime": 13.2298,
+      "eval_samples_per_second": 14.135,
+      "eval_steps_per_second": 7.105,
       "step": 70
     },
     {
       "epoch": 0.36076662908680945,
-      "grad_norm": 0.6760919094085693,
-      "learning_rate": 2.4510177743583583e-06,
-      "loss": 1.2616,
+      "grad_norm": 0.6693026423454285,
+      "learning_rate": 2.4900880123475463e-06,
+      "loss": 1.2595,
+      "step": 80
+    },
+    {
+      "epoch": 0.36076662908680945,
+      "eval_loss": 1.3134440183639526,
+      "eval_runtime": 13.3078,
+      "eval_samples_per_second": 14.052,
+      "eval_steps_per_second": 7.064,
       "step": 80
     },
     {
       "epoch": 0.40586245772266066,
-      "grad_norm": 0.5790563225746155,
-      "learning_rate": 2.256825511303766e-06,
-      "loss": 1.0877,
+      "grad_norm": 0.5636974573135376,
+      "learning_rate": 2.3083479538733636e-06,
+      "loss": 1.0858,
+      "step": 90
+    },
+    {
+      "epoch": 0.40586245772266066,
+      "eval_loss": 1.2941912412643433,
+      "eval_runtime": 13.1999,
+      "eval_samples_per_second": 14.167,
+      "eval_steps_per_second": 7.121,
       "step": 90
     },
     {
       "epoch": 0.4509582863585118,
-      "grad_norm": 0.5748745799064636,
-      "learning_rate": 2.043810319917937e-06,
-      "loss": 1.2241,
+      "grad_norm": 0.571853756904602,
+      "learning_rate": 2.108024561540242e-06,
+      "loss": 1.2219,
       "step": 100
     },
     {
       "epoch": 0.4509582863585118,
-      "eval_loss": 1.2807611227035522,
-      "eval_runtime": 13.4863,
-      "eval_samples_per_second": 13.866,
-      "eval_steps_per_second": 6.97,
+      "eval_loss": 1.2784264087677002,
+      "eval_runtime": 13.24,
+      "eval_samples_per_second": 14.124,
+      "eval_steps_per_second": 7.1,
       "step": 100
     },
     {
       "epoch": 0.496054114994363,
-      "grad_norm": 0.5320383310317993,
-      "learning_rate": 1.8172700788017286e-06,
-      "loss": 1.1341,
+      "grad_norm": 0.5300303101539612,
+      "learning_rate": 1.8937231250153905e-06,
+      "loss": 1.1319,
+      "step": 110
+    },
+    {
+      "epoch": 0.496054114994363,
+      "eval_loss": 1.264504313468933,
+      "eval_runtime": 13.2023,
+      "eval_samples_per_second": 14.164,
+      "eval_steps_per_second": 7.12,
       "step": 110
     },
     {
       "epoch": 0.5411499436302142,
-      "grad_norm": 0.5653139352798462,
-      "learning_rate": 1.5828390466567621e-06,
-      "loss": 1.1733,
+      "grad_norm": 0.5525142550468445,
+      "learning_rate": 1.6703702790757123e-06,
+      "loss": 1.1702,
+      "step": 120
+    },
+    {
+      "epoch": 0.5411499436302142,
+      "eval_loss": 1.2530410289764404,
+      "eval_runtime": 13.2204,
+      "eval_samples_per_second": 14.145,
+      "eval_steps_per_second": 7.11,
       "step": 120
     },
     {
       "epoch": 0.5862457722660653,
-      "grad_norm": 0.3555745780467987,
-      "learning_rate": 1.3463477332250803e-06,
-      "loss": 1.1083,
+      "grad_norm": 0.3444017171859741,
+      "learning_rate": 1.4431007438433431e-06,
+      "loss": 1.1054,
       "step": 130
     },
+    {
+      "epoch": 0.5862457722660653,
+      "eval_loss": 1.2430415153503418,
+      "eval_runtime": 13.205,
+      "eval_samples_per_second": 14.161,
+      "eval_steps_per_second": 7.119,
+      "step": 130
+    },
+    {
+      "epoch": 0.6313416009019166,
+      "grad_norm": 0.5441855192184448,
+      "learning_rate": 1.2171392812898465e-06,
+      "loss": 1.1249,
+      "step": 140
+    },
     {
       "epoch": 0.6313416009019166,
-      "grad_norm": 0.5427935719490051,
-      "learning_rate": 1.1136778892896554e-06,
-      "loss": 1.1287,
+      "eval_loss": 1.2348647117614746,
+      "eval_runtime": 13.2648,
+      "eval_samples_per_second": 14.097,
+      "eval_steps_per_second": 7.086,
       "step": 140
     },
     {
       "epoch": 0.6764374295377678,
-      "grad_norm": 0.518344521522522,
-      "learning_rate": 8.906162222643167e-07,
-      "loss": 1.191,
+      "grad_norm": 0.5227693915367126,
+      "learning_rate": 9.976805817435208e-07,
+      "loss": 1.1867,
       "step": 150
     },
     {
       "epoch": 0.6764374295377678,
-      "eval_loss": 1.2335149049758911,
-      "eval_runtime": 13.2304,
-      "eval_samples_per_second": 14.134,
-      "eval_steps_per_second": 7.105,
+      "eval_loss": 1.2283574342727661,
+      "eval_runtime": 13.1435,
+      "eval_samples_per_second": 14.228,
+      "eval_steps_per_second": 7.152,
       "step": 150
     },
     {
       "epoch": 0.7215332581736189,
-      "grad_norm": 0.5353164076805115,
-      "learning_rate": 6.827104755973948e-07,
-      "loss": 1.0559,
+      "grad_norm": 0.542244017124176,
+      "learning_rate": 7.89769841721999e-07,
+      "loss": 1.0513,
+      "step": 160
+    },
+    {
+      "epoch": 0.7215332581736189,
+      "eval_loss": 1.223202109336853,
+      "eval_runtime": 13.3114,
+      "eval_samples_per_second": 14.048,
+      "eval_steps_per_second": 7.062,
       "step": 160
     },
     {
       "epoch": 0.7666290868094702,
-      "grad_norm": 0.5589386820793152,
-      "learning_rate": 4.951314514232176e-07,
-      "loss": 1.1292,
+      "grad_norm": 0.43865886330604553,
+      "learning_rate": 5.98186778519257e-07,
+      "loss": 1.1238,
+      "step": 170
+    },
+    {
+      "epoch": 0.7666290868094702,
+      "eval_loss": 1.2190639972686768,
+      "eval_runtime": 13.2662,
+      "eval_samples_per_second": 14.096,
+      "eval_steps_per_second": 7.086,
       "step": 170
     },
     {
       "epoch": 0.8117249154453213,
-      "grad_norm": 0.4542039632797241,
-      "learning_rate": 3.325444080817054e-07,
-      "loss": 1.1606,
+      "grad_norm": 0.4573892056941986,
+      "learning_rate": 4.273357479676508e-07,
+      "loss": 1.1548,
       "step": 180
     },
+    {
+      "epoch": 0.8117249154453213,
+      "eval_loss": 1.2160392999649048,
+      "eval_runtime": 13.1667,
+      "eval_samples_per_second": 14.203,
+      "eval_steps_per_second": 7.139,
+      "step": 180
+    },
+    {
+      "epoch": 0.8568207440811725,
+      "grad_norm": 0.476138710975647,
+      "learning_rate": 2.8114449148802547e-07,
+      "loss": 1.2207,
+      "step": 190
+    },
     {
       "epoch": 0.8568207440811725,
-      "grad_norm": 0.4739130437374115,
-      "learning_rate": 1.9899303096492822e-07,
-      "loss": 1.2275,
+      "eval_loss": 1.2139577865600586,
+      "eval_runtime": 13.1987,
+      "eval_samples_per_second": 14.168,
+      "eval_steps_per_second": 7.122,
       "step": 190
     },
     {
       "epoch": 0.9019165727170236,
-      "grad_norm": 0.4491319954395294,
-      "learning_rate": 9.77988624396025e-08,
-      "loss": 1.1409,
+      "grad_norm": 0.4513246715068817,
+      "learning_rate": 1.6297384015986928e-07,
+      "loss": 1.1339,
       "step": 200
     },
     {
       "epoch": 0.9019165727170236,
-      "eval_loss": 1.2203494310379028,
-      "eval_runtime": 13.2982,
-      "eval_samples_per_second": 14.062,
-      "eval_steps_per_second": 7.069,
+      "eval_loss": 1.212600827217102,
+      "eval_runtime": 13.239,
+      "eval_samples_per_second": 14.125,
+      "eval_steps_per_second": 7.1,
       "step": 200
     }
   ],
   "logging_steps": 10,
-  "max_steps": 222,
+  "max_steps": 230,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 1,
-  "save_steps": 100,
+  "num_train_epochs": 2,
+  "save_steps": 10,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {
@@ -199,8 +327,8 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.1184814522587136e+16,
-  "train_batch_size": 2,
+  "total_flos": 3.452241511821312e+16,
+  "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null
 }

checkpoint-200/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2ee0e629bfe7d83379f821157f073bb89dfa290c0dfe015e2dcdc8e754e08f2
+oid sha256:7502fb41baf3b5166c63e35c8025c0cae40cfa667e95a34f273c4a766c0cd18d
 size 5777

checkpoint-210/README.md

@@ -0,0 +1,202 @@
+---
+base_model: unsloth/qwen3-4b-instruct-2507-unsloth-bnb-4bit
+library_name: peft
+---
+
+# 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 0.13.2

checkpoint-210/adapter_config.json

@@ -0,0 +1,38 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "Qwen3ForCausalLM",
+    "parent_library": "transformers.models.qwen3.modeling_qwen3",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/qwen3-4b-instruct-2507-unsloth-bnb-4bit",
+  "bias": "none",
+  "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": 128,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "up_proj",
+    "q_proj",
+    "down_proj",
+    "v_proj",
+    "gate_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-210/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94b665a75a47bde7ac1c43a3f9b8150c62b636df79eb0edb9ef1bce0d08a592e
+size 528550256

checkpoint-210/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-210/chat_template.jinja

@@ -0,0 +1,86 @@
+{%- 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' }}
+{%- endif %}

checkpoint-210/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2f9438371fb28b3db7f47b71cecf4f161d670bcf53f0cdf848b57dce3673553
+size 1057397963

checkpoint-210/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7def6dd628a5b00abc58faba7059ade34001b562efb696a110b78a00bbdf0bcf
+size 14645

checkpoint-210/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38de9409024463fde9f96c90944924f51e929ef47979e47c6d0aa4b1719375a7
+size 1465

checkpoint-210/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": "<|vision_pad|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-210/tokenizer.json

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

checkpoint-210/tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "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": 262144,
+  "pad_token": "<|vision_pad|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-210/trainer_state.json

@@ -0,0 +1,349 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9470124013528749,
+  "eval_steps": 10,
+  "global_step": 210,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04509582863585118,
+      "grad_norm": 4.649589538574219,
+      "learning_rate": 1.173913043478261e-06,
+      "loss": 1.6576,
+      "step": 10
+    },
+    {
+      "epoch": 0.04509582863585118,
+      "eval_loss": 1.9276622533798218,
+      "eval_runtime": 13.2788,
+      "eval_samples_per_second": 14.083,
+      "eval_steps_per_second": 7.079,
+      "step": 10
+    },
+    {
+      "epoch": 0.09019165727170236,
+      "grad_norm": 3.7612740993499756,
+      "learning_rate": 2.4782608695652173e-06,
+      "loss": 1.6856,
+      "step": 20
+    },
+    {
+      "epoch": 0.09019165727170236,
+      "eval_loss": 1.8389543294906616,
+      "eval_runtime": 13.2051,
+      "eval_samples_per_second": 14.161,
+      "eval_steps_per_second": 7.118,
+      "step": 20
+    },
+    {
+      "epoch": 0.13528748590755355,
+      "grad_norm": 3.048597812652588,
+      "learning_rate": 2.993785263797297e-06,
+      "loss": 1.5539,
+      "step": 30
+    },
+    {
+      "epoch": 0.13528748590755355,
+      "eval_loss": 1.6339466571807861,
+      "eval_runtime": 13.2214,
+      "eval_samples_per_second": 14.144,
+      "eval_steps_per_second": 7.11,
+      "step": 30
+    },
+    {
+      "epoch": 0.18038331454340473,
+      "grad_norm": 1.3381422758102417,
+      "learning_rate": 2.9559926521749324e-06,
+      "loss": 1.6382,
+      "step": 40
+    },
+    {
+      "epoch": 0.18038331454340473,
+      "eval_loss": 1.478708028793335,
+      "eval_runtime": 13.3673,
+      "eval_samples_per_second": 13.989,
+      "eval_steps_per_second": 7.032,
+      "step": 40
+    },
+    {
+      "epoch": 0.2254791431792559,
+      "grad_norm": 0.7458074688911438,
+      "learning_rate": 2.8847278242602185e-06,
+      "loss": 1.2616,
+      "step": 50
+    },
+    {
+      "epoch": 0.2254791431792559,
+      "eval_loss": 1.407120943069458,
+      "eval_runtime": 13.2044,
+      "eval_samples_per_second": 14.162,
+      "eval_steps_per_second": 7.119,
+      "step": 50
+    },
+    {
+      "epoch": 0.2705749718151071,
+      "grad_norm": 0.6770926713943481,
+      "learning_rate": 2.7816291068197328e-06,
+      "loss": 1.2366,
+      "step": 60
+    },
+    {
+      "epoch": 0.2705749718151071,
+      "eval_loss": 1.3675240278244019,
+      "eval_runtime": 13.4556,
+      "eval_samples_per_second": 13.898,
+      "eval_steps_per_second": 6.986,
+      "step": 60
+    },
+    {
+      "epoch": 0.3156708004509583,
+      "grad_norm": 0.7203531265258789,
+      "learning_rate": 2.649066664678467e-06,
+      "loss": 1.3251,
+      "step": 70
+    },
+    {
+      "epoch": 0.3156708004509583,
+      "eval_loss": 1.3370201587677002,
+      "eval_runtime": 13.2298,
+      "eval_samples_per_second": 14.135,
+      "eval_steps_per_second": 7.105,
+      "step": 70
+    },
+    {
+      "epoch": 0.36076662908680945,
+      "grad_norm": 0.6693026423454285,
+      "learning_rate": 2.4900880123475463e-06,
+      "loss": 1.2595,
+      "step": 80
+    },
+    {
+      "epoch": 0.36076662908680945,
+      "eval_loss": 1.3134440183639526,
+      "eval_runtime": 13.3078,
+      "eval_samples_per_second": 14.052,
+      "eval_steps_per_second": 7.064,
+      "step": 80
+    },
+    {
+      "epoch": 0.40586245772266066,
+      "grad_norm": 0.5636974573135376,
+      "learning_rate": 2.3083479538733636e-06,
+      "loss": 1.0858,
+      "step": 90
+    },
+    {
+      "epoch": 0.40586245772266066,
+      "eval_loss": 1.2941912412643433,
+      "eval_runtime": 13.1999,
+      "eval_samples_per_second": 14.167,
+      "eval_steps_per_second": 7.121,
+      "step": 90
+    },
+    {
+      "epoch": 0.4509582863585118,
+      "grad_norm": 0.571853756904602,
+      "learning_rate": 2.108024561540242e-06,
+      "loss": 1.2219,
+      "step": 100
+    },
+    {
+      "epoch": 0.4509582863585118,
+      "eval_loss": 1.2784264087677002,
+      "eval_runtime": 13.24,
+      "eval_samples_per_second": 14.124,
+      "eval_steps_per_second": 7.1,
+      "step": 100
+    },
+    {
+      "epoch": 0.496054114994363,
+      "grad_norm": 0.5300303101539612,
+      "learning_rate": 1.8937231250153905e-06,
+      "loss": 1.1319,
+      "step": 110
+    },
+    {
+      "epoch": 0.496054114994363,
+      "eval_loss": 1.264504313468933,
+      "eval_runtime": 13.2023,
+      "eval_samples_per_second": 14.164,
+      "eval_steps_per_second": 7.12,
+      "step": 110
+    },
+    {
+      "epoch": 0.5411499436302142,
+      "grad_norm": 0.5525142550468445,
+      "learning_rate": 1.6703702790757123e-06,
+      "loss": 1.1702,
+      "step": 120
+    },
+    {
+      "epoch": 0.5411499436302142,
+      "eval_loss": 1.2530410289764404,
+      "eval_runtime": 13.2204,
+      "eval_samples_per_second": 14.145,
+      "eval_steps_per_second": 7.11,
+      "step": 120
+    },
+    {
+      "epoch": 0.5862457722660653,
+      "grad_norm": 0.3444017171859741,
+      "learning_rate": 1.4431007438433431e-06,
+      "loss": 1.1054,
+      "step": 130
+    },
+    {
+      "epoch": 0.5862457722660653,
+      "eval_loss": 1.2430415153503418,
+      "eval_runtime": 13.205,
+      "eval_samples_per_second": 14.161,
+      "eval_steps_per_second": 7.119,
+      "step": 130
+    },
+    {
+      "epoch": 0.6313416009019166,
+      "grad_norm": 0.5441855192184448,
+      "learning_rate": 1.2171392812898465e-06,
+      "loss": 1.1249,
+      "step": 140
+    },
+    {
+      "epoch": 0.6313416009019166,
+      "eval_loss": 1.2348647117614746,
+      "eval_runtime": 13.2648,
+      "eval_samples_per_second": 14.097,
+      "eval_steps_per_second": 7.086,
+      "step": 140
+    },
+    {
+      "epoch": 0.6764374295377678,
+      "grad_norm": 0.5227693915367126,
+      "learning_rate": 9.976805817435208e-07,
+      "loss": 1.1867,
+      "step": 150
+    },
+    {
+      "epoch": 0.6764374295377678,
+      "eval_loss": 1.2283574342727661,
+      "eval_runtime": 13.1435,
+      "eval_samples_per_second": 14.228,
+      "eval_steps_per_second": 7.152,
+      "step": 150
+    },
+    {
+      "epoch": 0.7215332581736189,
+      "grad_norm": 0.542244017124176,
+      "learning_rate": 7.89769841721999e-07,
+      "loss": 1.0513,
+      "step": 160
+    },
+    {
+      "epoch": 0.7215332581736189,
+      "eval_loss": 1.223202109336853,
+      "eval_runtime": 13.3114,
+      "eval_samples_per_second": 14.048,
+      "eval_steps_per_second": 7.062,
+      "step": 160
+    },
+    {
+      "epoch": 0.7666290868094702,
+      "grad_norm": 0.43865886330604553,
+      "learning_rate": 5.98186778519257e-07,
+      "loss": 1.1238,
+      "step": 170
+    },
+    {
+      "epoch": 0.7666290868094702,
+      "eval_loss": 1.2190639972686768,
+      "eval_runtime": 13.2662,
+      "eval_samples_per_second": 14.096,
+      "eval_steps_per_second": 7.086,
+      "step": 170
+    },
+    {
+      "epoch": 0.8117249154453213,
+      "grad_norm": 0.4573892056941986,
+      "learning_rate": 4.273357479676508e-07,
+      "loss": 1.1548,
+      "step": 180
+    },
+    {
+      "epoch": 0.8117249154453213,
+      "eval_loss": 1.2160392999649048,
+      "eval_runtime": 13.1667,
+      "eval_samples_per_second": 14.203,
+      "eval_steps_per_second": 7.139,
+      "step": 180
+    },
+    {
+      "epoch": 0.8568207440811725,
+      "grad_norm": 0.476138710975647,
+      "learning_rate": 2.8114449148802547e-07,
+      "loss": 1.2207,
+      "step": 190
+    },
+    {
+      "epoch": 0.8568207440811725,
+      "eval_loss": 1.2139577865600586,
+      "eval_runtime": 13.1987,
+      "eval_samples_per_second": 14.168,
+      "eval_steps_per_second": 7.122,
+      "step": 190
+    },
+    {
+      "epoch": 0.9019165727170236,
+      "grad_norm": 0.4513246715068817,
+      "learning_rate": 1.6297384015986928e-07,
+      "loss": 1.1339,
+      "step": 200
+    },
+    {
+      "epoch": 0.9019165727170236,
+      "eval_loss": 1.212600827217102,
+      "eval_runtime": 13.239,
+      "eval_samples_per_second": 14.125,
+      "eval_steps_per_second": 7.1,
+      "step": 200
+    },
+    {
+      "epoch": 0.9470124013528749,
+      "grad_norm": 0.4398881196975708,
+      "learning_rate": 7.554045164952123e-08,
+      "loss": 1.0351,
+      "step": 210
+    },
+    {
+      "epoch": 0.9470124013528749,
+      "eval_loss": 1.21186363697052,
+      "eval_runtime": 13.2875,
+      "eval_samples_per_second": 14.073,
+      "eval_steps_per_second": 7.074,
+      "step": 210
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 230,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 10,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.622155888280781e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-210/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7502fb41baf3b5166c63e35c8025c0cae40cfa667e95a34f273c4a766c0cd18d
+size 5777

checkpoint-220/README.md

@@ -0,0 +1,202 @@
+---
+base_model: unsloth/qwen3-4b-instruct-2507-unsloth-bnb-4bit
+library_name: peft
+---
+
+# 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 0.13.2

checkpoint-220/adapter_config.json

@@ -0,0 +1,38 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "Qwen3ForCausalLM",
+    "parent_library": "transformers.models.qwen3.modeling_qwen3",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/qwen3-4b-instruct-2507-unsloth-bnb-4bit",
+  "bias": "none",
+  "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": 128,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "up_proj",
+    "q_proj",
+    "down_proj",
+    "v_proj",
+    "gate_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-220/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bc36165c8f589ff59b583c7438bafb1631c503eb63da032b575264edbdb2674
+size 528550256

checkpoint-220/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-220/chat_template.jinja

@@ -0,0 +1,86 @@
+{%- 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' }}
+{%- endif %}

checkpoint-220/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03a4614602f89d034731b5c1e9f302759e3a08a7c6d9a1d80a99038b9a9e3ff6
+size 1057397963

checkpoint-220/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b7f562a8bdc34874cd85e78245a4971d72e73869d7220cd7b5cb893cbbad1f1
+size 14645

checkpoint-220/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03686b30f7d8905300911dda707c3a2c70cba6467ef79b5c5c2b2d4b63c81106
+size 1465

checkpoint-220/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": "<|vision_pad|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-220/tokenizer.json

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

checkpoint-220/tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "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": 262144,
+  "pad_token": "<|vision_pad|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}