diff --git a/.gitattributes b/.gitattributes
index 77f5c1b518626a616cb31b7deda849d1e336e601..ab5101c521f843b6644279b9a87028d0c4003391 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -52,3 +52,19 @@ L1/checkpoints/checkpoint-70/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 L1/checkpoints/checkpoint-80/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 L1/checkpoints/checkpoint-90/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 L2/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+L2/checkpoints/checkpoint-10/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+L2/checkpoints/checkpoint-100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+L2/checkpoints/checkpoint-110/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+L2/checkpoints/checkpoint-120/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+L2/checkpoints/checkpoint-130/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+L2/checkpoints/checkpoint-140/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+L2/checkpoints/checkpoint-150/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+L2/checkpoints/checkpoint-159/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+L2/checkpoints/checkpoint-20/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+L2/checkpoints/checkpoint-30/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+L2/checkpoints/checkpoint-40/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+L2/checkpoints/checkpoint-50/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+L2/checkpoints/checkpoint-60/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+L2/checkpoints/checkpoint-70/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+L2/checkpoints/checkpoint-80/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+L2/checkpoints/checkpoint-90/tokenizer.json filter=lfs diff=lfs merge=lfs -text
diff --git a/L2/checkpoints/README.md b/L2/checkpoints/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..c9e1b45c3f2c163e22e44bb30165b4f69ede96ae
--- /dev/null
+++ b/L2/checkpoints/README.md
@@ -0,0 +1,58 @@
+---
+base_model: Qwen/Qwen3.5-0.8B
+library_name: transformers
+model_name: checkpoints
+tags:
+- generated_from_trainer
+- trl
+- sft
+licence: license
+---
+
+# Model Card for checkpoints
+
+This model is a fine-tuned version of [Qwen/Qwen3.5-0.8B](https://huggingface.co/Qwen/Qwen3.5-0.8B).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="None", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+ 
+
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 1.2.0.dev0
+- Transformers: 5.6.0.dev0
+- Pytorch: 2.9.0.dev20250803
+- Datasets: 4.8.4
+- Tokenizers: 0.22.1
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@software{vonwerra2020trl,
+  title   = {{TRL: Transformers Reinforcement Learning}},
+  author  = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
+  license = {Apache-2.0},
+  url     = {https://github.com/huggingface/trl},
+  year    = {2020}
+}
+```
\ No newline at end of file
diff --git a/L2/checkpoints/checkpoint-10/README.md b/L2/checkpoints/checkpoint-10/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..9b1d0d5c752a5c9f2e3a0e3a9ead3759650a12a9
--- /dev/null
+++ b/L2/checkpoints/checkpoint-10/README.md
@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen3.5-0.8B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3.5-0.8B
+- lora
+- sft
+- transformers
+- trl
+---
+
+# 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 0.18.2.dev0
\ No newline at end of file
diff --git a/L2/checkpoints/checkpoint-10/adapter_config.json b/L2/checkpoints/checkpoint-10/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..466b55ef5352db25f2ac04e8aec438ce0764d848
--- /dev/null
+++ b/L2/checkpoints/checkpoint-10/adapter_config.json
@@ -0,0 +1,45 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3.5-0.8B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.2.dev0@076214c61f690898509b97702b5e9d95c826f000",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "q_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/L2/checkpoints/checkpoint-10/adapter_model.safetensors b/L2/checkpoints/checkpoint-10/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..9fffffa336ab5ca09ac78959069b8e3d234ffcf0
--- /dev/null
+++ b/L2/checkpoints/checkpoint-10/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:691b65be7596c45a834b310898bcc52b211de03331146d8b766a5dcf0cc7b52b
+size 4331744
diff --git a/L2/checkpoints/checkpoint-10/chat_template.jinja b/L2/checkpoints/checkpoint-10/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..0ef09f214eaa6d9bca297988afc1454b5827b2c7
--- /dev/null
+++ b/L2/checkpoints/checkpoint-10/chat_template.jinja
@@ -0,0 +1,154 @@
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- macro render_content(content, do_vision_count, is_system_content=false) %}
+    {%- if content is string %}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping %}
+        {%- for item in content %}
+            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain images.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Picture ' ~ image_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
+            {%- elif 'video' in item or item.type == 'video' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain videos.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Video ' ~ video_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
+            {%- elif 'text' in item %}
+                {{- item.text }}
+            {%- else %}
+                {{- raise_exception('Unexpected item type in content.') }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif content is none or content is undefined %}
+        {{- '' }}
+    {%- else %}
+        {{- raise_exception('Unexpected content type.') }}
+    {%- endif %}
+{%- endmacro %}
+{%- if not messages %}
+    {{- raise_exception('No messages provided.') }}
+{%- endif %}
+{%- if tools and tools is iterable and tools is not mapping %}
+    {{- '<|im_start|>system\n' }}
+    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>" }}
+    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {%- if content %}
+            {{- '\n\n' + content }}
+        {%- endif %}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {{- '<|im_start|>system\n' + 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" %}
+        {%- set content = render_content(message.content, false)|trim %}
+        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
+            {%- set ns.multi_step_tool = false %}
+            {%- set ns.last_query_index = index %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if ns.multi_step_tool %}
+    {{- raise_exception('No user query found in messages.') }}
+{%- endif %}
+{%- for message in messages %}
+    {%- set content = render_content(message.content, true)|trim %}
+    {%- if message.role == "system" %}
+        {%- if not loop.first %}
+            {{- raise_exception('System message must be at the beginning.') }}
+        {%- endif %}
+    {%- elif message.role == "user" %}
+        {{- '<|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 %}
+        {%- set reasoning_content = reasoning_content|trim %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if tool_call.function is defined %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {%- if loop.first %}
+                    {%- if content|trim %}
+                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- else %}
+                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- endif %}
+                {%- else %}
+                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                {%- endif %}
+                {%- if tool_call.arguments is defined %}
+                    {%- for args_name, args_value in tool_call.arguments|items %}
+                        {{- '<parameter=' + args_name + '>\n' }}
+                        {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
+                        {{- args_value }}
+                        {{- '\n</parameter>\n' }}
+                    {%- endfor %}
+                {%- endif %}
+                {{- '</function>\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- else %}
+        {{- raise_exception('Unexpected message role.') }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is true %}
+        {{- '<think>\n' }}
+    {%- else %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}
\ No newline at end of file
diff --git a/L2/checkpoints/checkpoint-10/optimizer.pt b/L2/checkpoints/checkpoint-10/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..6f50813cbfcab6543f7c725eb49b3cfe84024b02
--- /dev/null
+++ b/L2/checkpoints/checkpoint-10/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d2d003edae84defc55c5aa7ed4010eeb4dfece5044c4f05ef6c8398b034e398
+size 8690571
diff --git a/L2/checkpoints/checkpoint-10/rng_state.pth b/L2/checkpoints/checkpoint-10/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..3f5c250a692e034a27fb06d7008612b2de078116
--- /dev/null
+++ b/L2/checkpoints/checkpoint-10/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cddf27219365242ec1046a3532a63a24c3f350c77f100e4f973369db2cc849d
+size 14455
diff --git a/L2/checkpoints/checkpoint-10/scheduler.pt b/L2/checkpoints/checkpoint-10/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..f77a8c35a99260d65736ac6295c06ee1053ff084
--- /dev/null
+++ b/L2/checkpoints/checkpoint-10/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7fe1ca4b3f5360608595ce0b8c7a836143524c2bd8b15c3dedc0d66309506ab
+size 1465
diff --git a/L2/checkpoints/checkpoint-10/tokenizer.json b/L2/checkpoints/checkpoint-10/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..67741b04f23bfdb46501f748ce27865ec82eccfb
--- /dev/null
+++ b/L2/checkpoints/checkpoint-10/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
+size 19989343
diff --git a/L2/checkpoints/checkpoint-10/tokenizer_config.json b/L2/checkpoints/checkpoint-10/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..0871602fcb7d15fcb2979685b1c7b609eef01a6f
--- /dev/null
+++ b/L2/checkpoints/checkpoint-10/tokenizer_config.json
@@ -0,0 +1,32 @@
+{
+  "add_prefix_space": false,
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "image_token": "<|image_pad|>",
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 512,
+  "model_specific_special_tokens": {
+    "audio_bos_token": "<|audio_start|>",
+    "audio_eos_token": "<|audio_end|>",
+    "audio_token": "<|audio_pad|>",
+    "image_token": "<|image_pad|>",
+    "video_token": "<|video_pad|>",
+    "vision_bos_token": "<|vision_start|>",
+    "vision_eos_token": "<|vision_end|>"
+  },
+  "pad_token": "<|endoftext|>",
+  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+  "split_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}
diff --git a/L2/checkpoints/checkpoint-10/trainer_state.json b/L2/checkpoints/checkpoint-10/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..c8f7bfe6cc439233e15c1d089bd283a159c29a27
--- /dev/null
+++ b/L2/checkpoints/checkpoint-10/trainer_state.json
@@ -0,0 +1,44 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.19138755980861244,
+  "eval_steps": 500,
+  "global_step": 10,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 2.35390625,
+      "epoch": 0.19138755980861244,
+      "grad_norm": 1.577696681022644,
+      "learning_rate": 0.0001999145758387301,
+      "loss": 2.517007064819336,
+      "mean_token_accuracy": 0.4835851963609457,
+      "num_tokens": 32923.0,
+      "step": 10
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 159,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 103057744948224.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/L2/checkpoints/checkpoint-10/training_args.bin b/L2/checkpoints/checkpoint-10/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c5ef2615541af048533dacdd04f01f920f86fece
--- /dev/null
+++ b/L2/checkpoints/checkpoint-10/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:063f2af09a09d13dafc33db4ec44d81e322816f9cd5d644aa0cda8a04f4b74b0
+size 5713
diff --git a/L2/checkpoints/checkpoint-100/README.md b/L2/checkpoints/checkpoint-100/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..9b1d0d5c752a5c9f2e3a0e3a9ead3759650a12a9
--- /dev/null
+++ b/L2/checkpoints/checkpoint-100/README.md
@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen3.5-0.8B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3.5-0.8B
+- lora
+- sft
+- transformers
+- trl
+---
+
+# 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 0.18.2.dev0
\ No newline at end of file
diff --git a/L2/checkpoints/checkpoint-100/adapter_config.json b/L2/checkpoints/checkpoint-100/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..466b55ef5352db25f2ac04e8aec438ce0764d848
--- /dev/null
+++ b/L2/checkpoints/checkpoint-100/adapter_config.json
@@ -0,0 +1,45 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3.5-0.8B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.2.dev0@076214c61f690898509b97702b5e9d95c826f000",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "q_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/L2/checkpoints/checkpoint-100/adapter_model.safetensors b/L2/checkpoints/checkpoint-100/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..1ece649de16cc94040ef1c7d2e71b795db688b8a
--- /dev/null
+++ b/L2/checkpoints/checkpoint-100/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d68c3b591c0f7580466380eb8d797626040861941d2143316829d4ca384fc80a
+size 4331744
diff --git a/L2/checkpoints/checkpoint-100/chat_template.jinja b/L2/checkpoints/checkpoint-100/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..0ef09f214eaa6d9bca297988afc1454b5827b2c7
--- /dev/null
+++ b/L2/checkpoints/checkpoint-100/chat_template.jinja
@@ -0,0 +1,154 @@
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- macro render_content(content, do_vision_count, is_system_content=false) %}
+    {%- if content is string %}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping %}
+        {%- for item in content %}
+            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain images.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Picture ' ~ image_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
+            {%- elif 'video' in item or item.type == 'video' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain videos.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Video ' ~ video_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
+            {%- elif 'text' in item %}
+                {{- item.text }}
+            {%- else %}
+                {{- raise_exception('Unexpected item type in content.') }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif content is none or content is undefined %}
+        {{- '' }}
+    {%- else %}
+        {{- raise_exception('Unexpected content type.') }}
+    {%- endif %}
+{%- endmacro %}
+{%- if not messages %}
+    {{- raise_exception('No messages provided.') }}
+{%- endif %}
+{%- if tools and tools is iterable and tools is not mapping %}
+    {{- '<|im_start|>system\n' }}
+    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>" }}
+    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {%- if content %}
+            {{- '\n\n' + content }}
+        {%- endif %}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {{- '<|im_start|>system\n' + 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" %}
+        {%- set content = render_content(message.content, false)|trim %}
+        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
+            {%- set ns.multi_step_tool = false %}
+            {%- set ns.last_query_index = index %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if ns.multi_step_tool %}
+    {{- raise_exception('No user query found in messages.') }}
+{%- endif %}
+{%- for message in messages %}
+    {%- set content = render_content(message.content, true)|trim %}
+    {%- if message.role == "system" %}
+        {%- if not loop.first %}
+            {{- raise_exception('System message must be at the beginning.') }}
+        {%- endif %}
+    {%- elif message.role == "user" %}
+        {{- '<|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 %}
+        {%- set reasoning_content = reasoning_content|trim %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if tool_call.function is defined %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {%- if loop.first %}
+                    {%- if content|trim %}
+                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- else %}
+                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- endif %}
+                {%- else %}
+                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                {%- endif %}
+                {%- if tool_call.arguments is defined %}
+                    {%- for args_name, args_value in tool_call.arguments|items %}
+                        {{- '<parameter=' + args_name + '>\n' }}
+                        {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
+                        {{- args_value }}
+                        {{- '\n</parameter>\n' }}
+                    {%- endfor %}
+                {%- endif %}
+                {{- '</function>\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- else %}
+        {{- raise_exception('Unexpected message role.') }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is true %}
+        {{- '<think>\n' }}
+    {%- else %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}
\ No newline at end of file
diff --git a/L2/checkpoints/checkpoint-100/optimizer.pt b/L2/checkpoints/checkpoint-100/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..68be1aec436f43e2521a60c81196351a40a9b070
--- /dev/null
+++ b/L2/checkpoints/checkpoint-100/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebab9935cb03c35cbcb0463c086b14d7d074e5eb87eaaa710a006e7e425e5038
+size 8690571
diff --git a/L2/checkpoints/checkpoint-100/rng_state.pth b/L2/checkpoints/checkpoint-100/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..38c6d5df0a659b81300f358fefb31a6f4aa51ddc
--- /dev/null
+++ b/L2/checkpoints/checkpoint-100/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3a77d4a8b98ce027a4d6a3b9fb5d7c904e27ec1efd5c0468c24fa26bb738316
+size 14455
diff --git a/L2/checkpoints/checkpoint-100/scheduler.pt b/L2/checkpoints/checkpoint-100/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..2e86f16121c94952328173d2bd55e9d7711b6ed2
--- /dev/null
+++ b/L2/checkpoints/checkpoint-100/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3177aafb877f9c541c793d0b5d70c393194524b75cdf776a7c9c47187919c5f0
+size 1465
diff --git a/L2/checkpoints/checkpoint-100/tokenizer.json b/L2/checkpoints/checkpoint-100/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..67741b04f23bfdb46501f748ce27865ec82eccfb
--- /dev/null
+++ b/L2/checkpoints/checkpoint-100/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
+size 19989343
diff --git a/L2/checkpoints/checkpoint-100/tokenizer_config.json b/L2/checkpoints/checkpoint-100/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..0871602fcb7d15fcb2979685b1c7b609eef01a6f
--- /dev/null
+++ b/L2/checkpoints/checkpoint-100/tokenizer_config.json
@@ -0,0 +1,32 @@
+{
+  "add_prefix_space": false,
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "image_token": "<|image_pad|>",
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 512,
+  "model_specific_special_tokens": {
+    "audio_bos_token": "<|audio_start|>",
+    "audio_eos_token": "<|audio_end|>",
+    "audio_token": "<|audio_pad|>",
+    "image_token": "<|image_pad|>",
+    "video_token": "<|video_pad|>",
+    "vision_bos_token": "<|vision_start|>",
+    "vision_eos_token": "<|vision_end|>"
+  },
+  "pad_token": "<|endoftext|>",
+  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+  "split_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}
diff --git a/L2/checkpoints/checkpoint-100/trainer_state.json b/L2/checkpoints/checkpoint-100/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..fdb9eab080f570809e9ffea89efce58fb88f0e39
--- /dev/null
+++ b/L2/checkpoints/checkpoint-100/trainer_state.json
@@ -0,0 +1,134 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.8995215311004785,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 2.35390625,
+      "epoch": 0.19138755980861244,
+      "grad_norm": 1.577696681022644,
+      "learning_rate": 0.0001999145758387301,
+      "loss": 2.517007064819336,
+      "mean_token_accuracy": 0.4835851963609457,
+      "num_tokens": 32923.0,
+      "step": 10
+    },
+    {
+      "entropy": 1.953515625,
+      "epoch": 0.3827751196172249,
+      "grad_norm": 1.822049856185913,
+      "learning_rate": 0.00019694002659393305,
+      "loss": 1.814153289794922,
+      "mean_token_accuracy": 0.6044577240943909,
+      "num_tokens": 65628.0,
+      "step": 20
+    },
+    {
+      "entropy": 1.36533203125,
+      "epoch": 0.5741626794258373,
+      "grad_norm": 0.8370082974433899,
+      "learning_rate": 0.0001898390981891979,
+      "loss": 1.4171125411987304,
+      "mean_token_accuracy": 0.6942351691424846,
+      "num_tokens": 98592.0,
+      "step": 30
+    },
+    {
+      "entropy": 1.33076171875,
+      "epoch": 0.7655502392344498,
+      "grad_norm": 0.7550845146179199,
+      "learning_rate": 0.00017891405093963938,
+      "loss": 1.3193041801452636,
+      "mean_token_accuracy": 0.7104418903589249,
+      "num_tokens": 131278.0,
+      "step": 40
+    },
+    {
+      "entropy": 1.312109375,
+      "epoch": 0.9569377990430622,
+      "grad_norm": 0.6932047009468079,
+      "learning_rate": 0.00016462992378609407,
+      "loss": 1.3077256202697753,
+      "mean_token_accuracy": 0.7093201003968715,
+      "num_tokens": 164256.0,
+      "step": 50
+    },
+    {
+      "entropy": 1.3107052364864864,
+      "epoch": 1.1339712918660287,
+      "grad_norm": 0.7087656855583191,
+      "learning_rate": 0.00014759473930370736,
+      "loss": 1.2949213981628418,
+      "mean_token_accuracy": 0.7117355780021565,
+      "num_tokens": 194746.0,
+      "step": 60
+    },
+    {
+      "entropy": 1.26064453125,
+      "epoch": 1.325358851674641,
+      "grad_norm": 0.8213269710540771,
+      "learning_rate": 0.00012853362242491053,
+      "loss": 1.244191551208496,
+      "mean_token_accuracy": 0.7226051487028599,
+      "num_tokens": 227482.0,
+      "step": 70
+    },
+    {
+      "entropy": 1.2599609375,
+      "epoch": 1.5167464114832536,
+      "grad_norm": 0.7758288383483887,
+      "learning_rate": 0.00010825793454723325,
+      "loss": 1.2582054138183594,
+      "mean_token_accuracy": 0.7165695309638977,
+      "num_tokens": 260195.0,
+      "step": 80
+    },
+    {
+      "entropy": 1.25322265625,
+      "epoch": 1.7081339712918662,
+      "grad_norm": 0.7961016893386841,
+      "learning_rate": 8.763073687306524e-05,
+      "loss": 1.2671056747436524,
+      "mean_token_accuracy": 0.7158558055758476,
+      "num_tokens": 292968.0,
+      "step": 90
+    },
+    {
+      "entropy": 1.28291015625,
+      "epoch": 1.8995215311004785,
+      "grad_norm": 0.757343590259552,
+      "learning_rate": 6.753005307953167e-05,
+      "loss": 1.2647873878479003,
+      "mean_token_accuracy": 0.7167910523712635,
+      "num_tokens": 325911.0,
+      "step": 100
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 159,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 1018641704492160.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/L2/checkpoints/checkpoint-100/training_args.bin b/L2/checkpoints/checkpoint-100/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c5ef2615541af048533dacdd04f01f920f86fece
--- /dev/null
+++ b/L2/checkpoints/checkpoint-100/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:063f2af09a09d13dafc33db4ec44d81e322816f9cd5d644aa0cda8a04f4b74b0
+size 5713
diff --git a/L2/checkpoints/checkpoint-110/README.md b/L2/checkpoints/checkpoint-110/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..9b1d0d5c752a5c9f2e3a0e3a9ead3759650a12a9
--- /dev/null
+++ b/L2/checkpoints/checkpoint-110/README.md
@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen3.5-0.8B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3.5-0.8B
+- lora
+- sft
+- transformers
+- trl
+---
+
+# 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 0.18.2.dev0
\ No newline at end of file
diff --git a/L2/checkpoints/checkpoint-110/adapter_config.json b/L2/checkpoints/checkpoint-110/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..466b55ef5352db25f2ac04e8aec438ce0764d848
--- /dev/null
+++ b/L2/checkpoints/checkpoint-110/adapter_config.json
@@ -0,0 +1,45 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3.5-0.8B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.2.dev0@076214c61f690898509b97702b5e9d95c826f000",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "q_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/L2/checkpoints/checkpoint-110/adapter_model.safetensors b/L2/checkpoints/checkpoint-110/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..5221b5ebed63737fc2ab04ed5e2eb9a0feb0b1df
--- /dev/null
+++ b/L2/checkpoints/checkpoint-110/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adb7a6862f2cbdbbb8fa8e8a273209ab8cae9a0b4c93f94aa5dfb12937f653ff
+size 4331744
diff --git a/L2/checkpoints/checkpoint-110/chat_template.jinja b/L2/checkpoints/checkpoint-110/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..0ef09f214eaa6d9bca297988afc1454b5827b2c7
--- /dev/null
+++ b/L2/checkpoints/checkpoint-110/chat_template.jinja
@@ -0,0 +1,154 @@
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- macro render_content(content, do_vision_count, is_system_content=false) %}
+    {%- if content is string %}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping %}
+        {%- for item in content %}
+            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain images.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Picture ' ~ image_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
+            {%- elif 'video' in item or item.type == 'video' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain videos.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Video ' ~ video_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
+            {%- elif 'text' in item %}
+                {{- item.text }}
+            {%- else %}
+                {{- raise_exception('Unexpected item type in content.') }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif content is none or content is undefined %}
+        {{- '' }}
+    {%- else %}
+        {{- raise_exception('Unexpected content type.') }}
+    {%- endif %}
+{%- endmacro %}
+{%- if not messages %}
+    {{- raise_exception('No messages provided.') }}
+{%- endif %}
+{%- if tools and tools is iterable and tools is not mapping %}
+    {{- '<|im_start|>system\n' }}
+    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>" }}
+    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {%- if content %}
+            {{- '\n\n' + content }}
+        {%- endif %}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {{- '<|im_start|>system\n' + 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" %}
+        {%- set content = render_content(message.content, false)|trim %}
+        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
+            {%- set ns.multi_step_tool = false %}
+            {%- set ns.last_query_index = index %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if ns.multi_step_tool %}
+    {{- raise_exception('No user query found in messages.') }}
+{%- endif %}
+{%- for message in messages %}
+    {%- set content = render_content(message.content, true)|trim %}
+    {%- if message.role == "system" %}
+        {%- if not loop.first %}
+            {{- raise_exception('System message must be at the beginning.') }}
+        {%- endif %}
+    {%- elif message.role == "user" %}
+        {{- '<|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 %}
+        {%- set reasoning_content = reasoning_content|trim %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if tool_call.function is defined %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {%- if loop.first %}
+                    {%- if content|trim %}
+                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- else %}
+                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- endif %}
+                {%- else %}
+                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                {%- endif %}
+                {%- if tool_call.arguments is defined %}
+                    {%- for args_name, args_value in tool_call.arguments|items %}
+                        {{- '<parameter=' + args_name + '>\n' }}
+                        {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
+                        {{- args_value }}
+                        {{- '\n</parameter>\n' }}
+                    {%- endfor %}
+                {%- endif %}
+                {{- '</function>\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- else %}
+        {{- raise_exception('Unexpected message role.') }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is true %}
+        {{- '<think>\n' }}
+    {%- else %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}
\ No newline at end of file
diff --git a/L2/checkpoints/checkpoint-110/optimizer.pt b/L2/checkpoints/checkpoint-110/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..a29029c86be75bc754eccd2cf77dd8bc9a432275
--- /dev/null
+++ b/L2/checkpoints/checkpoint-110/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ff31f5f7e4a9305fcbded5a0551091c59ed120859133cc7f7c570190aee45fc
+size 8690571
diff --git a/L2/checkpoints/checkpoint-110/rng_state.pth b/L2/checkpoints/checkpoint-110/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..7d150fc4504460cdea273ef2adcb04a65c626709
--- /dev/null
+++ b/L2/checkpoints/checkpoint-110/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dba4fde4ee04d2f472bb4dea96a48e8fdf7891d2b0694a8f012e8133a2e176ae
+size 14455
diff --git a/L2/checkpoints/checkpoint-110/scheduler.pt b/L2/checkpoints/checkpoint-110/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..2a9fadb38e19952787f70f5d92bdb6eeb301a08a
--- /dev/null
+++ b/L2/checkpoints/checkpoint-110/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8f882f0bf7e74a2b304dde78b9fa019bc2cdbf9058f544ba3b9a9ae35031b93
+size 1465
diff --git a/L2/checkpoints/checkpoint-110/tokenizer.json b/L2/checkpoints/checkpoint-110/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..67741b04f23bfdb46501f748ce27865ec82eccfb
--- /dev/null
+++ b/L2/checkpoints/checkpoint-110/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
+size 19989343
diff --git a/L2/checkpoints/checkpoint-110/tokenizer_config.json b/L2/checkpoints/checkpoint-110/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..0871602fcb7d15fcb2979685b1c7b609eef01a6f
--- /dev/null
+++ b/L2/checkpoints/checkpoint-110/tokenizer_config.json
@@ -0,0 +1,32 @@
+{
+  "add_prefix_space": false,
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "image_token": "<|image_pad|>",
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 512,
+  "model_specific_special_tokens": {
+    "audio_bos_token": "<|audio_start|>",
+    "audio_eos_token": "<|audio_end|>",
+    "audio_token": "<|audio_pad|>",
+    "image_token": "<|image_pad|>",
+    "video_token": "<|video_pad|>",
+    "vision_bos_token": "<|vision_start|>",
+    "vision_eos_token": "<|vision_end|>"
+  },
+  "pad_token": "<|endoftext|>",
+  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+  "split_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}
diff --git a/L2/checkpoints/checkpoint-110/trainer_state.json b/L2/checkpoints/checkpoint-110/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..dc839c7cb8c47bae5f1fcce5c4582c5f72e50a19
--- /dev/null
+++ b/L2/checkpoints/checkpoint-110/trainer_state.json
@@ -0,0 +1,144 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.076555023923445,
+  "eval_steps": 500,
+  "global_step": 110,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 2.35390625,
+      "epoch": 0.19138755980861244,
+      "grad_norm": 1.577696681022644,
+      "learning_rate": 0.0001999145758387301,
+      "loss": 2.517007064819336,
+      "mean_token_accuracy": 0.4835851963609457,
+      "num_tokens": 32923.0,
+      "step": 10
+    },
+    {
+      "entropy": 1.953515625,
+      "epoch": 0.3827751196172249,
+      "grad_norm": 1.822049856185913,
+      "learning_rate": 0.00019694002659393305,
+      "loss": 1.814153289794922,
+      "mean_token_accuracy": 0.6044577240943909,
+      "num_tokens": 65628.0,
+      "step": 20
+    },
+    {
+      "entropy": 1.36533203125,
+      "epoch": 0.5741626794258373,
+      "grad_norm": 0.8370082974433899,
+      "learning_rate": 0.0001898390981891979,
+      "loss": 1.4171125411987304,
+      "mean_token_accuracy": 0.6942351691424846,
+      "num_tokens": 98592.0,
+      "step": 30
+    },
+    {
+      "entropy": 1.33076171875,
+      "epoch": 0.7655502392344498,
+      "grad_norm": 0.7550845146179199,
+      "learning_rate": 0.00017891405093963938,
+      "loss": 1.3193041801452636,
+      "mean_token_accuracy": 0.7104418903589249,
+      "num_tokens": 131278.0,
+      "step": 40
+    },
+    {
+      "entropy": 1.312109375,
+      "epoch": 0.9569377990430622,
+      "grad_norm": 0.6932047009468079,
+      "learning_rate": 0.00016462992378609407,
+      "loss": 1.3077256202697753,
+      "mean_token_accuracy": 0.7093201003968715,
+      "num_tokens": 164256.0,
+      "step": 50
+    },
+    {
+      "entropy": 1.3107052364864864,
+      "epoch": 1.1339712918660287,
+      "grad_norm": 0.7087656855583191,
+      "learning_rate": 0.00014759473930370736,
+      "loss": 1.2949213981628418,
+      "mean_token_accuracy": 0.7117355780021565,
+      "num_tokens": 194746.0,
+      "step": 60
+    },
+    {
+      "entropy": 1.26064453125,
+      "epoch": 1.325358851674641,
+      "grad_norm": 0.8213269710540771,
+      "learning_rate": 0.00012853362242491053,
+      "loss": 1.244191551208496,
+      "mean_token_accuracy": 0.7226051487028599,
+      "num_tokens": 227482.0,
+      "step": 70
+    },
+    {
+      "entropy": 1.2599609375,
+      "epoch": 1.5167464114832536,
+      "grad_norm": 0.7758288383483887,
+      "learning_rate": 0.00010825793454723325,
+      "loss": 1.2582054138183594,
+      "mean_token_accuracy": 0.7165695309638977,
+      "num_tokens": 260195.0,
+      "step": 80
+    },
+    {
+      "entropy": 1.25322265625,
+      "epoch": 1.7081339712918662,
+      "grad_norm": 0.7961016893386841,
+      "learning_rate": 8.763073687306524e-05,
+      "loss": 1.2671056747436524,
+      "mean_token_accuracy": 0.7158558055758476,
+      "num_tokens": 292968.0,
+      "step": 90
+    },
+    {
+      "entropy": 1.28291015625,
+      "epoch": 1.8995215311004785,
+      "grad_norm": 0.757343590259552,
+      "learning_rate": 6.753005307953167e-05,
+      "loss": 1.2647873878479003,
+      "mean_token_accuracy": 0.7167910523712635,
+      "num_tokens": 325911.0,
+      "step": 100
+    },
+    {
+      "entropy": 1.2690033783783783,
+      "epoch": 2.076555023923445,
+      "grad_norm": 0.7981213331222534,
+      "learning_rate": 4.8811495091039926e-05,
+      "loss": 1.2404365539550781,
+      "mean_token_accuracy": 0.7189428822414295,
+      "num_tokens": 356114.0,
+      "step": 110
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 159,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 1112752882242048.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/L2/checkpoints/checkpoint-110/training_args.bin b/L2/checkpoints/checkpoint-110/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c5ef2615541af048533dacdd04f01f920f86fece
--- /dev/null
+++ b/L2/checkpoints/checkpoint-110/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:063f2af09a09d13dafc33db4ec44d81e322816f9cd5d644aa0cda8a04f4b74b0
+size 5713
diff --git a/L2/checkpoints/checkpoint-120/README.md b/L2/checkpoints/checkpoint-120/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..9b1d0d5c752a5c9f2e3a0e3a9ead3759650a12a9
--- /dev/null
+++ b/L2/checkpoints/checkpoint-120/README.md
@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen3.5-0.8B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3.5-0.8B
+- lora
+- sft
+- transformers
+- trl
+---
+
+# 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 0.18.2.dev0
\ No newline at end of file
diff --git a/L2/checkpoints/checkpoint-120/adapter_config.json b/L2/checkpoints/checkpoint-120/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..466b55ef5352db25f2ac04e8aec438ce0764d848
--- /dev/null
+++ b/L2/checkpoints/checkpoint-120/adapter_config.json
@@ -0,0 +1,45 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3.5-0.8B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.2.dev0@076214c61f690898509b97702b5e9d95c826f000",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "q_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/L2/checkpoints/checkpoint-120/adapter_model.safetensors b/L2/checkpoints/checkpoint-120/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..cdabdbd7b988009ef7f673d986dfcaa1d398fb7e
--- /dev/null
+++ b/L2/checkpoints/checkpoint-120/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6690023a23dcb3b81661b2ad4087d3235a50ae6f6d1b59fbe71b6f7f1878567
+size 4331744
diff --git a/L2/checkpoints/checkpoint-120/chat_template.jinja b/L2/checkpoints/checkpoint-120/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..0ef09f214eaa6d9bca297988afc1454b5827b2c7
--- /dev/null
+++ b/L2/checkpoints/checkpoint-120/chat_template.jinja
@@ -0,0 +1,154 @@
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- macro render_content(content, do_vision_count, is_system_content=false) %}
+    {%- if content is string %}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping %}
+        {%- for item in content %}
+            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain images.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Picture ' ~ image_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
+            {%- elif 'video' in item or item.type == 'video' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain videos.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Video ' ~ video_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
+            {%- elif 'text' in item %}
+                {{- item.text }}
+            {%- else %}
+                {{- raise_exception('Unexpected item type in content.') }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif content is none or content is undefined %}
+        {{- '' }}
+    {%- else %}
+        {{- raise_exception('Unexpected content type.') }}
+    {%- endif %}
+{%- endmacro %}
+{%- if not messages %}
+    {{- raise_exception('No messages provided.') }}
+{%- endif %}
+{%- if tools and tools is iterable and tools is not mapping %}
+    {{- '<|im_start|>system\n' }}
+    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>" }}
+    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {%- if content %}
+            {{- '\n\n' + content }}
+        {%- endif %}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {{- '<|im_start|>system\n' + 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" %}
+        {%- set content = render_content(message.content, false)|trim %}
+        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
+            {%- set ns.multi_step_tool = false %}
+            {%- set ns.last_query_index = index %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if ns.multi_step_tool %}
+    {{- raise_exception('No user query found in messages.') }}
+{%- endif %}
+{%- for message in messages %}
+    {%- set content = render_content(message.content, true)|trim %}
+    {%- if message.role == "system" %}
+        {%- if not loop.first %}
+            {{- raise_exception('System message must be at the beginning.') }}
+        {%- endif %}
+    {%- elif message.role == "user" %}
+        {{- '<|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 %}
+        {%- set reasoning_content = reasoning_content|trim %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if tool_call.function is defined %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {%- if loop.first %}
+                    {%- if content|trim %}
+                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- else %}
+                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- endif %}
+                {%- else %}
+                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                {%- endif %}
+                {%- if tool_call.arguments is defined %}
+                    {%- for args_name, args_value in tool_call.arguments|items %}
+                        {{- '<parameter=' + args_name + '>\n' }}
+                        {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
+                        {{- args_value }}
+                        {{- '\n</parameter>\n' }}
+                    {%- endfor %}
+                {%- endif %}
+                {{- '</function>\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- else %}
+        {{- raise_exception('Unexpected message role.') }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is true %}
+        {{- '<think>\n' }}
+    {%- else %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}
\ No newline at end of file
diff --git a/L2/checkpoints/checkpoint-120/optimizer.pt b/L2/checkpoints/checkpoint-120/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..3a621c32e0e8265be286a0cff870302b1e634dcd
--- /dev/null
+++ b/L2/checkpoints/checkpoint-120/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ccfe152035ebd6ab9d4f9b17dcde507be3caea79b42303a24f99e889457b57e
+size 8690571
diff --git a/L2/checkpoints/checkpoint-120/rng_state.pth b/L2/checkpoints/checkpoint-120/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..7d150fc4504460cdea273ef2adcb04a65c626709
--- /dev/null
+++ b/L2/checkpoints/checkpoint-120/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dba4fde4ee04d2f472bb4dea96a48e8fdf7891d2b0694a8f012e8133a2e176ae
+size 14455
diff --git a/L2/checkpoints/checkpoint-120/scheduler.pt b/L2/checkpoints/checkpoint-120/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..9360bd36ac51b5e1d4ce1f2a58618eee24bcb300
--- /dev/null
+++ b/L2/checkpoints/checkpoint-120/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c748cde43f3ac780a033e33735b44512b14c6bcfd555ce64d6b760d4ce31be08
+size 1465
diff --git a/L2/checkpoints/checkpoint-120/tokenizer.json b/L2/checkpoints/checkpoint-120/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..67741b04f23bfdb46501f748ce27865ec82eccfb
--- /dev/null
+++ b/L2/checkpoints/checkpoint-120/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
+size 19989343
diff --git a/L2/checkpoints/checkpoint-120/tokenizer_config.json b/L2/checkpoints/checkpoint-120/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..0871602fcb7d15fcb2979685b1c7b609eef01a6f
--- /dev/null
+++ b/L2/checkpoints/checkpoint-120/tokenizer_config.json
@@ -0,0 +1,32 @@
+{
+  "add_prefix_space": false,
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "image_token": "<|image_pad|>",
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 512,
+  "model_specific_special_tokens": {
+    "audio_bos_token": "<|audio_start|>",
+    "audio_eos_token": "<|audio_end|>",
+    "audio_token": "<|audio_pad|>",
+    "image_token": "<|image_pad|>",
+    "video_token": "<|video_pad|>",
+    "vision_bos_token": "<|vision_start|>",
+    "vision_eos_token": "<|vision_end|>"
+  },
+  "pad_token": "<|endoftext|>",
+  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+  "split_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}
diff --git a/L2/checkpoints/checkpoint-120/trainer_state.json b/L2/checkpoints/checkpoint-120/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..e73b6ee46702c12fa0ac7f53a4fe3299a96af66a
--- /dev/null
+++ b/L2/checkpoints/checkpoint-120/trainer_state.json
@@ -0,0 +1,154 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.2679425837320575,
+  "eval_steps": 500,
+  "global_step": 120,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 2.35390625,
+      "epoch": 0.19138755980861244,
+      "grad_norm": 1.577696681022644,
+      "learning_rate": 0.0001999145758387301,
+      "loss": 2.517007064819336,
+      "mean_token_accuracy": 0.4835851963609457,
+      "num_tokens": 32923.0,
+      "step": 10
+    },
+    {
+      "entropy": 1.953515625,
+      "epoch": 0.3827751196172249,
+      "grad_norm": 1.822049856185913,
+      "learning_rate": 0.00019694002659393305,
+      "loss": 1.814153289794922,
+      "mean_token_accuracy": 0.6044577240943909,
+      "num_tokens": 65628.0,
+      "step": 20
+    },
+    {
+      "entropy": 1.36533203125,
+      "epoch": 0.5741626794258373,
+      "grad_norm": 0.8370082974433899,
+      "learning_rate": 0.0001898390981891979,
+      "loss": 1.4171125411987304,
+      "mean_token_accuracy": 0.6942351691424846,
+      "num_tokens": 98592.0,
+      "step": 30
+    },
+    {
+      "entropy": 1.33076171875,
+      "epoch": 0.7655502392344498,
+      "grad_norm": 0.7550845146179199,
+      "learning_rate": 0.00017891405093963938,
+      "loss": 1.3193041801452636,
+      "mean_token_accuracy": 0.7104418903589249,
+      "num_tokens": 131278.0,
+      "step": 40
+    },
+    {
+      "entropy": 1.312109375,
+      "epoch": 0.9569377990430622,
+      "grad_norm": 0.6932047009468079,
+      "learning_rate": 0.00016462992378609407,
+      "loss": 1.3077256202697753,
+      "mean_token_accuracy": 0.7093201003968715,
+      "num_tokens": 164256.0,
+      "step": 50
+    },
+    {
+      "entropy": 1.3107052364864864,
+      "epoch": 1.1339712918660287,
+      "grad_norm": 0.7087656855583191,
+      "learning_rate": 0.00014759473930370736,
+      "loss": 1.2949213981628418,
+      "mean_token_accuracy": 0.7117355780021565,
+      "num_tokens": 194746.0,
+      "step": 60
+    },
+    {
+      "entropy": 1.26064453125,
+      "epoch": 1.325358851674641,
+      "grad_norm": 0.8213269710540771,
+      "learning_rate": 0.00012853362242491053,
+      "loss": 1.244191551208496,
+      "mean_token_accuracy": 0.7226051487028599,
+      "num_tokens": 227482.0,
+      "step": 70
+    },
+    {
+      "entropy": 1.2599609375,
+      "epoch": 1.5167464114832536,
+      "grad_norm": 0.7758288383483887,
+      "learning_rate": 0.00010825793454723325,
+      "loss": 1.2582054138183594,
+      "mean_token_accuracy": 0.7165695309638977,
+      "num_tokens": 260195.0,
+      "step": 80
+    },
+    {
+      "entropy": 1.25322265625,
+      "epoch": 1.7081339712918662,
+      "grad_norm": 0.7961016893386841,
+      "learning_rate": 8.763073687306524e-05,
+      "loss": 1.2671056747436524,
+      "mean_token_accuracy": 0.7158558055758476,
+      "num_tokens": 292968.0,
+      "step": 90
+    },
+    {
+      "entropy": 1.28291015625,
+      "epoch": 1.8995215311004785,
+      "grad_norm": 0.757343590259552,
+      "learning_rate": 6.753005307953167e-05,
+      "loss": 1.2647873878479003,
+      "mean_token_accuracy": 0.7167910523712635,
+      "num_tokens": 325911.0,
+      "step": 100
+    },
+    {
+      "entropy": 1.2690033783783783,
+      "epoch": 2.076555023923445,
+      "grad_norm": 0.7981213331222534,
+      "learning_rate": 4.8811495091039926e-05,
+      "loss": 1.2404365539550781,
+      "mean_token_accuracy": 0.7189428822414295,
+      "num_tokens": 356114.0,
+      "step": 110
+    },
+    {
+      "entropy": 1.25244140625,
+      "epoch": 2.2679425837320575,
+      "grad_norm": 0.7682023048400879,
+      "learning_rate": 3.2271842837425906e-05,
+      "loss": 1.2295378684997558,
+      "mean_token_accuracy": 0.7262546218931675,
+      "num_tokens": 388999.0,
+      "step": 120
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 159,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 1216547438549760.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/L2/checkpoints/checkpoint-120/training_args.bin b/L2/checkpoints/checkpoint-120/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c5ef2615541af048533dacdd04f01f920f86fece
--- /dev/null
+++ b/L2/checkpoints/checkpoint-120/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:063f2af09a09d13dafc33db4ec44d81e322816f9cd5d644aa0cda8a04f4b74b0
+size 5713
diff --git a/L2/checkpoints/checkpoint-130/README.md b/L2/checkpoints/checkpoint-130/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..9b1d0d5c752a5c9f2e3a0e3a9ead3759650a12a9
--- /dev/null
+++ b/L2/checkpoints/checkpoint-130/README.md
@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen3.5-0.8B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3.5-0.8B
+- lora
+- sft
+- transformers
+- trl
+---
+
+# 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 0.18.2.dev0
\ No newline at end of file
diff --git a/L2/checkpoints/checkpoint-130/adapter_config.json b/L2/checkpoints/checkpoint-130/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..466b55ef5352db25f2ac04e8aec438ce0764d848
--- /dev/null
+++ b/L2/checkpoints/checkpoint-130/adapter_config.json
@@ -0,0 +1,45 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3.5-0.8B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.2.dev0@076214c61f690898509b97702b5e9d95c826f000",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "q_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/L2/checkpoints/checkpoint-130/adapter_model.safetensors b/L2/checkpoints/checkpoint-130/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..c7d5ac6b15c1d20512ffa5a3dfb9eaa97ca7b5d2
--- /dev/null
+++ b/L2/checkpoints/checkpoint-130/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab22fb707ac16ead3162044ed4c6609b073a1c1f31a94b2d40f6eff88b10ee1c
+size 4331744
diff --git a/L2/checkpoints/checkpoint-130/chat_template.jinja b/L2/checkpoints/checkpoint-130/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..0ef09f214eaa6d9bca297988afc1454b5827b2c7
--- /dev/null
+++ b/L2/checkpoints/checkpoint-130/chat_template.jinja
@@ -0,0 +1,154 @@
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- macro render_content(content, do_vision_count, is_system_content=false) %}
+    {%- if content is string %}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping %}
+        {%- for item in content %}
+            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain images.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Picture ' ~ image_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
+            {%- elif 'video' in item or item.type == 'video' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain videos.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Video ' ~ video_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
+            {%- elif 'text' in item %}
+                {{- item.text }}
+            {%- else %}
+                {{- raise_exception('Unexpected item type in content.') }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif content is none or content is undefined %}
+        {{- '' }}
+    {%- else %}
+        {{- raise_exception('Unexpected content type.') }}
+    {%- endif %}
+{%- endmacro %}
+{%- if not messages %}
+    {{- raise_exception('No messages provided.') }}
+{%- endif %}
+{%- if tools and tools is iterable and tools is not mapping %}
+    {{- '<|im_start|>system\n' }}
+    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>" }}
+    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {%- if content %}
+            {{- '\n\n' + content }}
+        {%- endif %}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {{- '<|im_start|>system\n' + 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" %}
+        {%- set content = render_content(message.content, false)|trim %}
+        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
+            {%- set ns.multi_step_tool = false %}
+            {%- set ns.last_query_index = index %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if ns.multi_step_tool %}
+    {{- raise_exception('No user query found in messages.') }}
+{%- endif %}
+{%- for message in messages %}
+    {%- set content = render_content(message.content, true)|trim %}
+    {%- if message.role == "system" %}
+        {%- if not loop.first %}
+            {{- raise_exception('System message must be at the beginning.') }}
+        {%- endif %}
+    {%- elif message.role == "user" %}
+        {{- '<|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 %}
+        {%- set reasoning_content = reasoning_content|trim %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if tool_call.function is defined %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {%- if loop.first %}
+                    {%- if content|trim %}
+                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- else %}
+                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- endif %}
+                {%- else %}
+                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                {%- endif %}
+                {%- if tool_call.arguments is defined %}
+                    {%- for args_name, args_value in tool_call.arguments|items %}
+                        {{- '<parameter=' + args_name + '>\n' }}
+                        {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
+                        {{- args_value }}
+                        {{- '\n</parameter>\n' }}
+                    {%- endfor %}
+                {%- endif %}
+                {{- '</function>\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- else %}
+        {{- raise_exception('Unexpected message role.') }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is true %}
+        {{- '<think>\n' }}
+    {%- else %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}
\ No newline at end of file
diff --git a/L2/checkpoints/checkpoint-130/optimizer.pt b/L2/checkpoints/checkpoint-130/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..2ba95804570e4389bdb62aace6eb276963eee174
--- /dev/null
+++ b/L2/checkpoints/checkpoint-130/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ebb38eddb91b079c5ba84b21b7616cf2c9a6086be0464c3d34efc966f97c582
+size 8690571
diff --git a/L2/checkpoints/checkpoint-130/rng_state.pth b/L2/checkpoints/checkpoint-130/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..7d150fc4504460cdea273ef2adcb04a65c626709
--- /dev/null
+++ b/L2/checkpoints/checkpoint-130/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dba4fde4ee04d2f472bb4dea96a48e8fdf7891d2b0694a8f012e8133a2e176ae
+size 14455
diff --git a/L2/checkpoints/checkpoint-130/scheduler.pt b/L2/checkpoints/checkpoint-130/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..5b6b9c835319c32c5ba395960f5913e2075263be
--- /dev/null
+++ b/L2/checkpoints/checkpoint-130/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e84db9e363097911357934d81595bf7aeeaa4a6e8b69e7eeb5390b4b7770cc56
+size 1465
diff --git a/L2/checkpoints/checkpoint-130/tokenizer.json b/L2/checkpoints/checkpoint-130/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..67741b04f23bfdb46501f748ce27865ec82eccfb
--- /dev/null
+++ b/L2/checkpoints/checkpoint-130/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
+size 19989343
diff --git a/L2/checkpoints/checkpoint-130/tokenizer_config.json b/L2/checkpoints/checkpoint-130/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..0871602fcb7d15fcb2979685b1c7b609eef01a6f
--- /dev/null
+++ b/L2/checkpoints/checkpoint-130/tokenizer_config.json
@@ -0,0 +1,32 @@
+{
+  "add_prefix_space": false,
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "image_token": "<|image_pad|>",
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 512,
+  "model_specific_special_tokens": {
+    "audio_bos_token": "<|audio_start|>",
+    "audio_eos_token": "<|audio_end|>",
+    "audio_token": "<|audio_pad|>",
+    "image_token": "<|image_pad|>",
+    "video_token": "<|video_pad|>",
+    "vision_bos_token": "<|vision_start|>",
+    "vision_eos_token": "<|vision_end|>"
+  },
+  "pad_token": "<|endoftext|>",
+  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+  "split_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}
diff --git a/L2/checkpoints/checkpoint-130/trainer_state.json b/L2/checkpoints/checkpoint-130/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..bd1febfe97d1897d26e41a2436c6123a95aa207d
--- /dev/null
+++ b/L2/checkpoints/checkpoint-130/trainer_state.json
@@ -0,0 +1,164 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.45933014354067,
+  "eval_steps": 500,
+  "global_step": 130,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 2.35390625,
+      "epoch": 0.19138755980861244,
+      "grad_norm": 1.577696681022644,
+      "learning_rate": 0.0001999145758387301,
+      "loss": 2.517007064819336,
+      "mean_token_accuracy": 0.4835851963609457,
+      "num_tokens": 32923.0,
+      "step": 10
+    },
+    {
+      "entropy": 1.953515625,
+      "epoch": 0.3827751196172249,
+      "grad_norm": 1.822049856185913,
+      "learning_rate": 0.00019694002659393305,
+      "loss": 1.814153289794922,
+      "mean_token_accuracy": 0.6044577240943909,
+      "num_tokens": 65628.0,
+      "step": 20
+    },
+    {
+      "entropy": 1.36533203125,
+      "epoch": 0.5741626794258373,
+      "grad_norm": 0.8370082974433899,
+      "learning_rate": 0.0001898390981891979,
+      "loss": 1.4171125411987304,
+      "mean_token_accuracy": 0.6942351691424846,
+      "num_tokens": 98592.0,
+      "step": 30
+    },
+    {
+      "entropy": 1.33076171875,
+      "epoch": 0.7655502392344498,
+      "grad_norm": 0.7550845146179199,
+      "learning_rate": 0.00017891405093963938,
+      "loss": 1.3193041801452636,
+      "mean_token_accuracy": 0.7104418903589249,
+      "num_tokens": 131278.0,
+      "step": 40
+    },
+    {
+      "entropy": 1.312109375,
+      "epoch": 0.9569377990430622,
+      "grad_norm": 0.6932047009468079,
+      "learning_rate": 0.00016462992378609407,
+      "loss": 1.3077256202697753,
+      "mean_token_accuracy": 0.7093201003968715,
+      "num_tokens": 164256.0,
+      "step": 50
+    },
+    {
+      "entropy": 1.3107052364864864,
+      "epoch": 1.1339712918660287,
+      "grad_norm": 0.7087656855583191,
+      "learning_rate": 0.00014759473930370736,
+      "loss": 1.2949213981628418,
+      "mean_token_accuracy": 0.7117355780021565,
+      "num_tokens": 194746.0,
+      "step": 60
+    },
+    {
+      "entropy": 1.26064453125,
+      "epoch": 1.325358851674641,
+      "grad_norm": 0.8213269710540771,
+      "learning_rate": 0.00012853362242491053,
+      "loss": 1.244191551208496,
+      "mean_token_accuracy": 0.7226051487028599,
+      "num_tokens": 227482.0,
+      "step": 70
+    },
+    {
+      "entropy": 1.2599609375,
+      "epoch": 1.5167464114832536,
+      "grad_norm": 0.7758288383483887,
+      "learning_rate": 0.00010825793454723325,
+      "loss": 1.2582054138183594,
+      "mean_token_accuracy": 0.7165695309638977,
+      "num_tokens": 260195.0,
+      "step": 80
+    },
+    {
+      "entropy": 1.25322265625,
+      "epoch": 1.7081339712918662,
+      "grad_norm": 0.7961016893386841,
+      "learning_rate": 8.763073687306524e-05,
+      "loss": 1.2671056747436524,
+      "mean_token_accuracy": 0.7158558055758476,
+      "num_tokens": 292968.0,
+      "step": 90
+    },
+    {
+      "entropy": 1.28291015625,
+      "epoch": 1.8995215311004785,
+      "grad_norm": 0.757343590259552,
+      "learning_rate": 6.753005307953167e-05,
+      "loss": 1.2647873878479003,
+      "mean_token_accuracy": 0.7167910523712635,
+      "num_tokens": 325911.0,
+      "step": 100
+    },
+    {
+      "entropy": 1.2690033783783783,
+      "epoch": 2.076555023923445,
+      "grad_norm": 0.7981213331222534,
+      "learning_rate": 4.8811495091039926e-05,
+      "loss": 1.2404365539550781,
+      "mean_token_accuracy": 0.7189428822414295,
+      "num_tokens": 356114.0,
+      "step": 110
+    },
+    {
+      "entropy": 1.25244140625,
+      "epoch": 2.2679425837320575,
+      "grad_norm": 0.7682023048400879,
+      "learning_rate": 3.2271842837425906e-05,
+      "loss": 1.2295378684997558,
+      "mean_token_accuracy": 0.7262546218931675,
+      "num_tokens": 388999.0,
+      "step": 120
+    },
+    {
+      "entropy": 1.22822265625,
+      "epoch": 2.45933014354067,
+      "grad_norm": 0.7267993688583374,
+      "learning_rate": 1.861512827298051e-05,
+      "loss": 1.2186729431152343,
+      "mean_token_accuracy": 0.7247538149356842,
+      "num_tokens": 422226.0,
+      "step": 130
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 159,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 1320437840237568.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/L2/checkpoints/checkpoint-130/training_args.bin b/L2/checkpoints/checkpoint-130/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c5ef2615541af048533dacdd04f01f920f86fece
--- /dev/null
+++ b/L2/checkpoints/checkpoint-130/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:063f2af09a09d13dafc33db4ec44d81e322816f9cd5d644aa0cda8a04f4b74b0
+size 5713
diff --git a/L2/checkpoints/checkpoint-140/README.md b/L2/checkpoints/checkpoint-140/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..9b1d0d5c752a5c9f2e3a0e3a9ead3759650a12a9
--- /dev/null
+++ b/L2/checkpoints/checkpoint-140/README.md
@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen3.5-0.8B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3.5-0.8B
+- lora
+- sft
+- transformers
+- trl
+---
+
+# 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 0.18.2.dev0
\ No newline at end of file
diff --git a/L2/checkpoints/checkpoint-140/adapter_config.json b/L2/checkpoints/checkpoint-140/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..466b55ef5352db25f2ac04e8aec438ce0764d848
--- /dev/null
+++ b/L2/checkpoints/checkpoint-140/adapter_config.json
@@ -0,0 +1,45 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3.5-0.8B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.2.dev0@076214c61f690898509b97702b5e9d95c826f000",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "q_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/L2/checkpoints/checkpoint-140/adapter_model.safetensors b/L2/checkpoints/checkpoint-140/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..7599f2fd68acd4fbb332f5fb312f04e7fb7c5669
--- /dev/null
+++ b/L2/checkpoints/checkpoint-140/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c295c22b98591f9d676879b22f7f86783f78eaeb9db39648d1cecb339f57d60f
+size 4331744
diff --git a/L2/checkpoints/checkpoint-140/chat_template.jinja b/L2/checkpoints/checkpoint-140/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..0ef09f214eaa6d9bca297988afc1454b5827b2c7
--- /dev/null
+++ b/L2/checkpoints/checkpoint-140/chat_template.jinja
@@ -0,0 +1,154 @@
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- macro render_content(content, do_vision_count, is_system_content=false) %}
+    {%- if content is string %}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping %}
+        {%- for item in content %}
+            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain images.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Picture ' ~ image_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
+            {%- elif 'video' in item or item.type == 'video' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain videos.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Video ' ~ video_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
+            {%- elif 'text' in item %}
+                {{- item.text }}
+            {%- else %}
+                {{- raise_exception('Unexpected item type in content.') }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif content is none or content is undefined %}
+        {{- '' }}
+    {%- else %}
+        {{- raise_exception('Unexpected content type.') }}
+    {%- endif %}
+{%- endmacro %}
+{%- if not messages %}
+    {{- raise_exception('No messages provided.') }}
+{%- endif %}
+{%- if tools and tools is iterable and tools is not mapping %}
+    {{- '<|im_start|>system\n' }}
+    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>" }}
+    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {%- if content %}
+            {{- '\n\n' + content }}
+        {%- endif %}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {{- '<|im_start|>system\n' + 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" %}
+        {%- set content = render_content(message.content, false)|trim %}
+        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
+            {%- set ns.multi_step_tool = false %}
+            {%- set ns.last_query_index = index %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if ns.multi_step_tool %}
+    {{- raise_exception('No user query found in messages.') }}
+{%- endif %}
+{%- for message in messages %}
+    {%- set content = render_content(message.content, true)|trim %}
+    {%- if message.role == "system" %}
+        {%- if not loop.first %}
+            {{- raise_exception('System message must be at the beginning.') }}
+        {%- endif %}
+    {%- elif message.role == "user" %}
+        {{- '<|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 %}
+        {%- set reasoning_content = reasoning_content|trim %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if tool_call.function is defined %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {%- if loop.first %}
+                    {%- if content|trim %}
+                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- else %}
+                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- endif %}
+                {%- else %}
+                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                {%- endif %}
+                {%- if tool_call.arguments is defined %}
+                    {%- for args_name, args_value in tool_call.arguments|items %}
+                        {{- '<parameter=' + args_name + '>\n' }}
+                        {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
+                        {{- args_value }}
+                        {{- '\n</parameter>\n' }}
+                    {%- endfor %}
+                {%- endif %}
+                {{- '</function>\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- else %}
+        {{- raise_exception('Unexpected message role.') }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is true %}
+        {{- '<think>\n' }}
+    {%- else %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}
\ No newline at end of file
diff --git a/L2/checkpoints/checkpoint-140/optimizer.pt b/L2/checkpoints/checkpoint-140/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..2af8a7405c6ebb10d127756f239ccaaed9f7f917
--- /dev/null
+++ b/L2/checkpoints/checkpoint-140/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e0cecbcb300e500b3c4417c4fbaf907c8abfb3bf2e2a8878ba19b7929c9efd2
+size 8690571
diff --git a/L2/checkpoints/checkpoint-140/rng_state.pth b/L2/checkpoints/checkpoint-140/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..7d150fc4504460cdea273ef2adcb04a65c626709
--- /dev/null
+++ b/L2/checkpoints/checkpoint-140/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dba4fde4ee04d2f472bb4dea96a48e8fdf7891d2b0694a8f012e8133a2e176ae
+size 14455
diff --git a/L2/checkpoints/checkpoint-140/scheduler.pt b/L2/checkpoints/checkpoint-140/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..b49e885f7ca1f34c0094cc8f287cae0d005282f0
--- /dev/null
+++ b/L2/checkpoints/checkpoint-140/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfa9e2ffd448b5ae0809078fa803005d3fb0168890bd12b132bdb4cb8a1d4596
+size 1465
diff --git a/L2/checkpoints/checkpoint-140/tokenizer.json b/L2/checkpoints/checkpoint-140/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..67741b04f23bfdb46501f748ce27865ec82eccfb
--- /dev/null
+++ b/L2/checkpoints/checkpoint-140/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
+size 19989343
diff --git a/L2/checkpoints/checkpoint-140/tokenizer_config.json b/L2/checkpoints/checkpoint-140/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..0871602fcb7d15fcb2979685b1c7b609eef01a6f
--- /dev/null
+++ b/L2/checkpoints/checkpoint-140/tokenizer_config.json
@@ -0,0 +1,32 @@
+{
+  "add_prefix_space": false,
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "image_token": "<|image_pad|>",
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 512,
+  "model_specific_special_tokens": {
+    "audio_bos_token": "<|audio_start|>",
+    "audio_eos_token": "<|audio_end|>",
+    "audio_token": "<|audio_pad|>",
+    "image_token": "<|image_pad|>",
+    "video_token": "<|video_pad|>",
+    "vision_bos_token": "<|vision_start|>",
+    "vision_eos_token": "<|vision_end|>"
+  },
+  "pad_token": "<|endoftext|>",
+  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+  "split_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}
diff --git a/L2/checkpoints/checkpoint-140/trainer_state.json b/L2/checkpoints/checkpoint-140/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..dc82fbb3e0ea64b9c4608c7deb24b188d5e8efc5
--- /dev/null
+++ b/L2/checkpoints/checkpoint-140/trainer_state.json
@@ -0,0 +1,174 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.650717703349282,
+  "eval_steps": 500,
+  "global_step": 140,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 2.35390625,
+      "epoch": 0.19138755980861244,
+      "grad_norm": 1.577696681022644,
+      "learning_rate": 0.0001999145758387301,
+      "loss": 2.517007064819336,
+      "mean_token_accuracy": 0.4835851963609457,
+      "num_tokens": 32923.0,
+      "step": 10
+    },
+    {
+      "entropy": 1.953515625,
+      "epoch": 0.3827751196172249,
+      "grad_norm": 1.822049856185913,
+      "learning_rate": 0.00019694002659393305,
+      "loss": 1.814153289794922,
+      "mean_token_accuracy": 0.6044577240943909,
+      "num_tokens": 65628.0,
+      "step": 20
+    },
+    {
+      "entropy": 1.36533203125,
+      "epoch": 0.5741626794258373,
+      "grad_norm": 0.8370082974433899,
+      "learning_rate": 0.0001898390981891979,
+      "loss": 1.4171125411987304,
+      "mean_token_accuracy": 0.6942351691424846,
+      "num_tokens": 98592.0,
+      "step": 30
+    },
+    {
+      "entropy": 1.33076171875,
+      "epoch": 0.7655502392344498,
+      "grad_norm": 0.7550845146179199,
+      "learning_rate": 0.00017891405093963938,
+      "loss": 1.3193041801452636,
+      "mean_token_accuracy": 0.7104418903589249,
+      "num_tokens": 131278.0,
+      "step": 40
+    },
+    {
+      "entropy": 1.312109375,
+      "epoch": 0.9569377990430622,
+      "grad_norm": 0.6932047009468079,
+      "learning_rate": 0.00016462992378609407,
+      "loss": 1.3077256202697753,
+      "mean_token_accuracy": 0.7093201003968715,
+      "num_tokens": 164256.0,
+      "step": 50
+    },
+    {
+      "entropy": 1.3107052364864864,
+      "epoch": 1.1339712918660287,
+      "grad_norm": 0.7087656855583191,
+      "learning_rate": 0.00014759473930370736,
+      "loss": 1.2949213981628418,
+      "mean_token_accuracy": 0.7117355780021565,
+      "num_tokens": 194746.0,
+      "step": 60
+    },
+    {
+      "entropy": 1.26064453125,
+      "epoch": 1.325358851674641,
+      "grad_norm": 0.8213269710540771,
+      "learning_rate": 0.00012853362242491053,
+      "loss": 1.244191551208496,
+      "mean_token_accuracy": 0.7226051487028599,
+      "num_tokens": 227482.0,
+      "step": 70
+    },
+    {
+      "entropy": 1.2599609375,
+      "epoch": 1.5167464114832536,
+      "grad_norm": 0.7758288383483887,
+      "learning_rate": 0.00010825793454723325,
+      "loss": 1.2582054138183594,
+      "mean_token_accuracy": 0.7165695309638977,
+      "num_tokens": 260195.0,
+      "step": 80
+    },
+    {
+      "entropy": 1.25322265625,
+      "epoch": 1.7081339712918662,
+      "grad_norm": 0.7961016893386841,
+      "learning_rate": 8.763073687306524e-05,
+      "loss": 1.2671056747436524,
+      "mean_token_accuracy": 0.7158558055758476,
+      "num_tokens": 292968.0,
+      "step": 90
+    },
+    {
+      "entropy": 1.28291015625,
+      "epoch": 1.8995215311004785,
+      "grad_norm": 0.757343590259552,
+      "learning_rate": 6.753005307953167e-05,
+      "loss": 1.2647873878479003,
+      "mean_token_accuracy": 0.7167910523712635,
+      "num_tokens": 325911.0,
+      "step": 100
+    },
+    {
+      "entropy": 1.2690033783783783,
+      "epoch": 2.076555023923445,
+      "grad_norm": 0.7981213331222534,
+      "learning_rate": 4.8811495091039926e-05,
+      "loss": 1.2404365539550781,
+      "mean_token_accuracy": 0.7189428822414295,
+      "num_tokens": 356114.0,
+      "step": 110
+    },
+    {
+      "entropy": 1.25244140625,
+      "epoch": 2.2679425837320575,
+      "grad_norm": 0.7682023048400879,
+      "learning_rate": 3.2271842837425906e-05,
+      "loss": 1.2295378684997558,
+      "mean_token_accuracy": 0.7262546218931675,
+      "num_tokens": 388999.0,
+      "step": 120
+    },
+    {
+      "entropy": 1.22822265625,
+      "epoch": 2.45933014354067,
+      "grad_norm": 0.7267993688583374,
+      "learning_rate": 1.861512827298051e-05,
+      "loss": 1.2186729431152343,
+      "mean_token_accuracy": 0.7247538149356842,
+      "num_tokens": 422226.0,
+      "step": 130
+    },
+    {
+      "entropy": 1.2375,
+      "epoch": 2.650717703349282,
+      "grad_norm": 0.7193359136581421,
+      "learning_rate": 8.422667334494249e-06,
+      "loss": 1.2260663032531738,
+      "mean_token_accuracy": 0.7221008919179439,
+      "num_tokens": 454978.0,
+      "step": 140
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 159,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 1422788725507584.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/L2/checkpoints/checkpoint-140/training_args.bin b/L2/checkpoints/checkpoint-140/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c5ef2615541af048533dacdd04f01f920f86fece
--- /dev/null
+++ b/L2/checkpoints/checkpoint-140/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:063f2af09a09d13dafc33db4ec44d81e322816f9cd5d644aa0cda8a04f4b74b0
+size 5713
diff --git a/L2/checkpoints/checkpoint-150/README.md b/L2/checkpoints/checkpoint-150/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..9b1d0d5c752a5c9f2e3a0e3a9ead3759650a12a9
--- /dev/null
+++ b/L2/checkpoints/checkpoint-150/README.md
@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen3.5-0.8B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3.5-0.8B
+- lora
+- sft
+- transformers
+- trl
+---
+
+# 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 0.18.2.dev0
\ No newline at end of file
diff --git a/L2/checkpoints/checkpoint-150/adapter_config.json b/L2/checkpoints/checkpoint-150/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..466b55ef5352db25f2ac04e8aec438ce0764d848
--- /dev/null
+++ b/L2/checkpoints/checkpoint-150/adapter_config.json
@@ -0,0 +1,45 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3.5-0.8B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.2.dev0@076214c61f690898509b97702b5e9d95c826f000",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "q_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/L2/checkpoints/checkpoint-150/adapter_model.safetensors b/L2/checkpoints/checkpoint-150/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..5172de65d2bc7025dea8b8ee9f2d7eaa685699ad
--- /dev/null
+++ b/L2/checkpoints/checkpoint-150/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a1bb1567eea3b02ab42ddd093cfa49f9472b47ed2dad28820e0b91fa0f3f712
+size 4331744
diff --git a/L2/checkpoints/checkpoint-150/chat_template.jinja b/L2/checkpoints/checkpoint-150/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..0ef09f214eaa6d9bca297988afc1454b5827b2c7
--- /dev/null
+++ b/L2/checkpoints/checkpoint-150/chat_template.jinja
@@ -0,0 +1,154 @@
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- macro render_content(content, do_vision_count, is_system_content=false) %}
+    {%- if content is string %}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping %}
+        {%- for item in content %}
+            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain images.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Picture ' ~ image_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
+            {%- elif 'video' in item or item.type == 'video' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain videos.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Video ' ~ video_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
+            {%- elif 'text' in item %}
+                {{- item.text }}
+            {%- else %}
+                {{- raise_exception('Unexpected item type in content.') }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif content is none or content is undefined %}
+        {{- '' }}
+    {%- else %}
+        {{- raise_exception('Unexpected content type.') }}
+    {%- endif %}
+{%- endmacro %}
+{%- if not messages %}
+    {{- raise_exception('No messages provided.') }}
+{%- endif %}
+{%- if tools and tools is iterable and tools is not mapping %}
+    {{- '<|im_start|>system\n' }}
+    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>" }}
+    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {%- if content %}
+            {{- '\n\n' + content }}
+        {%- endif %}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {{- '<|im_start|>system\n' + 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" %}
+        {%- set content = render_content(message.content, false)|trim %}
+        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
+            {%- set ns.multi_step_tool = false %}
+            {%- set ns.last_query_index = index %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if ns.multi_step_tool %}
+    {{- raise_exception('No user query found in messages.') }}
+{%- endif %}
+{%- for message in messages %}
+    {%- set content = render_content(message.content, true)|trim %}
+    {%- if message.role == "system" %}
+        {%- if not loop.first %}
+            {{- raise_exception('System message must be at the beginning.') }}
+        {%- endif %}
+    {%- elif message.role == "user" %}
+        {{- '<|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 %}
+        {%- set reasoning_content = reasoning_content|trim %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if tool_call.function is defined %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {%- if loop.first %}
+                    {%- if content|trim %}
+                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- else %}
+                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- endif %}
+                {%- else %}
+                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                {%- endif %}
+                {%- if tool_call.arguments is defined %}
+                    {%- for args_name, args_value in tool_call.arguments|items %}
+                        {{- '<parameter=' + args_name + '>\n' }}
+                        {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
+                        {{- args_value }}
+                        {{- '\n</parameter>\n' }}
+                    {%- endfor %}
+                {%- endif %}
+                {{- '</function>\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- else %}
+        {{- raise_exception('Unexpected message role.') }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is true %}
+        {{- '<think>\n' }}
+    {%- else %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}
\ No newline at end of file
diff --git a/L2/checkpoints/checkpoint-150/optimizer.pt b/L2/checkpoints/checkpoint-150/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..a6f5b1de481329d2effb1595f62fac59e18c0974
--- /dev/null
+++ b/L2/checkpoints/checkpoint-150/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb5fe8bc66f96f28c9b31e58c07c7ee7b196565acdad20433f082d245b1d413d
+size 8690571
diff --git a/L2/checkpoints/checkpoint-150/rng_state.pth b/L2/checkpoints/checkpoint-150/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..7d150fc4504460cdea273ef2adcb04a65c626709
--- /dev/null
+++ b/L2/checkpoints/checkpoint-150/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dba4fde4ee04d2f472bb4dea96a48e8fdf7891d2b0694a8f012e8133a2e176ae
+size 14455
diff --git a/L2/checkpoints/checkpoint-150/scheduler.pt b/L2/checkpoints/checkpoint-150/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..08f0521496768738e3855a6425ce4776abf8262b
--- /dev/null
+++ b/L2/checkpoints/checkpoint-150/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:749a70a739231624cd72b7c431bbcfa6d3f5dea58efe86a276df4a9d9b201e64
+size 1465
diff --git a/L2/checkpoints/checkpoint-150/tokenizer.json b/L2/checkpoints/checkpoint-150/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..67741b04f23bfdb46501f748ce27865ec82eccfb
--- /dev/null
+++ b/L2/checkpoints/checkpoint-150/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
+size 19989343
diff --git a/L2/checkpoints/checkpoint-150/tokenizer_config.json b/L2/checkpoints/checkpoint-150/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..0871602fcb7d15fcb2979685b1c7b609eef01a6f
--- /dev/null
+++ b/L2/checkpoints/checkpoint-150/tokenizer_config.json
@@ -0,0 +1,32 @@
+{
+  "add_prefix_space": false,
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "image_token": "<|image_pad|>",
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 512,
+  "model_specific_special_tokens": {
+    "audio_bos_token": "<|audio_start|>",
+    "audio_eos_token": "<|audio_end|>",
+    "audio_token": "<|audio_pad|>",
+    "image_token": "<|image_pad|>",
+    "video_token": "<|video_pad|>",
+    "vision_bos_token": "<|vision_start|>",
+    "vision_eos_token": "<|vision_end|>"
+  },
+  "pad_token": "<|endoftext|>",
+  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+  "split_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}
diff --git a/L2/checkpoints/checkpoint-150/trainer_state.json b/L2/checkpoints/checkpoint-150/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..5ba4d550de3b6fdef004fe501ea20ebf9bf27b7d
--- /dev/null
+++ b/L2/checkpoints/checkpoint-150/trainer_state.json
@@ -0,0 +1,184 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.8421052631578947,
+  "eval_steps": 500,
+  "global_step": 150,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 2.35390625,
+      "epoch": 0.19138755980861244,
+      "grad_norm": 1.577696681022644,
+      "learning_rate": 0.0001999145758387301,
+      "loss": 2.517007064819336,
+      "mean_token_accuracy": 0.4835851963609457,
+      "num_tokens": 32923.0,
+      "step": 10
+    },
+    {
+      "entropy": 1.953515625,
+      "epoch": 0.3827751196172249,
+      "grad_norm": 1.822049856185913,
+      "learning_rate": 0.00019694002659393305,
+      "loss": 1.814153289794922,
+      "mean_token_accuracy": 0.6044577240943909,
+      "num_tokens": 65628.0,
+      "step": 20
+    },
+    {
+      "entropy": 1.36533203125,
+      "epoch": 0.5741626794258373,
+      "grad_norm": 0.8370082974433899,
+      "learning_rate": 0.0001898390981891979,
+      "loss": 1.4171125411987304,
+      "mean_token_accuracy": 0.6942351691424846,
+      "num_tokens": 98592.0,
+      "step": 30
+    },
+    {
+      "entropy": 1.33076171875,
+      "epoch": 0.7655502392344498,
+      "grad_norm": 0.7550845146179199,
+      "learning_rate": 0.00017891405093963938,
+      "loss": 1.3193041801452636,
+      "mean_token_accuracy": 0.7104418903589249,
+      "num_tokens": 131278.0,
+      "step": 40
+    },
+    {
+      "entropy": 1.312109375,
+      "epoch": 0.9569377990430622,
+      "grad_norm": 0.6932047009468079,
+      "learning_rate": 0.00016462992378609407,
+      "loss": 1.3077256202697753,
+      "mean_token_accuracy": 0.7093201003968715,
+      "num_tokens": 164256.0,
+      "step": 50
+    },
+    {
+      "entropy": 1.3107052364864864,
+      "epoch": 1.1339712918660287,
+      "grad_norm": 0.7087656855583191,
+      "learning_rate": 0.00014759473930370736,
+      "loss": 1.2949213981628418,
+      "mean_token_accuracy": 0.7117355780021565,
+      "num_tokens": 194746.0,
+      "step": 60
+    },
+    {
+      "entropy": 1.26064453125,
+      "epoch": 1.325358851674641,
+      "grad_norm": 0.8213269710540771,
+      "learning_rate": 0.00012853362242491053,
+      "loss": 1.244191551208496,
+      "mean_token_accuracy": 0.7226051487028599,
+      "num_tokens": 227482.0,
+      "step": 70
+    },
+    {
+      "entropy": 1.2599609375,
+      "epoch": 1.5167464114832536,
+      "grad_norm": 0.7758288383483887,
+      "learning_rate": 0.00010825793454723325,
+      "loss": 1.2582054138183594,
+      "mean_token_accuracy": 0.7165695309638977,
+      "num_tokens": 260195.0,
+      "step": 80
+    },
+    {
+      "entropy": 1.25322265625,
+      "epoch": 1.7081339712918662,
+      "grad_norm": 0.7961016893386841,
+      "learning_rate": 8.763073687306524e-05,
+      "loss": 1.2671056747436524,
+      "mean_token_accuracy": 0.7158558055758476,
+      "num_tokens": 292968.0,
+      "step": 90
+    },
+    {
+      "entropy": 1.28291015625,
+      "epoch": 1.8995215311004785,
+      "grad_norm": 0.757343590259552,
+      "learning_rate": 6.753005307953167e-05,
+      "loss": 1.2647873878479003,
+      "mean_token_accuracy": 0.7167910523712635,
+      "num_tokens": 325911.0,
+      "step": 100
+    },
+    {
+      "entropy": 1.2690033783783783,
+      "epoch": 2.076555023923445,
+      "grad_norm": 0.7981213331222534,
+      "learning_rate": 4.8811495091039926e-05,
+      "loss": 1.2404365539550781,
+      "mean_token_accuracy": 0.7189428822414295,
+      "num_tokens": 356114.0,
+      "step": 110
+    },
+    {
+      "entropy": 1.25244140625,
+      "epoch": 2.2679425837320575,
+      "grad_norm": 0.7682023048400879,
+      "learning_rate": 3.2271842837425906e-05,
+      "loss": 1.2295378684997558,
+      "mean_token_accuracy": 0.7262546218931675,
+      "num_tokens": 388999.0,
+      "step": 120
+    },
+    {
+      "entropy": 1.22822265625,
+      "epoch": 2.45933014354067,
+      "grad_norm": 0.7267993688583374,
+      "learning_rate": 1.861512827298051e-05,
+      "loss": 1.2186729431152343,
+      "mean_token_accuracy": 0.7247538149356842,
+      "num_tokens": 422226.0,
+      "step": 130
+    },
+    {
+      "entropy": 1.2375,
+      "epoch": 2.650717703349282,
+      "grad_norm": 0.7193359136581421,
+      "learning_rate": 8.422667334494249e-06,
+      "loss": 1.2260663032531738,
+      "mean_token_accuracy": 0.7221008919179439,
+      "num_tokens": 454978.0,
+      "step": 140
+    },
+    {
+      "entropy": 1.21845703125,
+      "epoch": 2.8421052631578947,
+      "grad_norm": 0.7832261323928833,
+      "learning_rate": 2.128315467264552e-06,
+      "loss": 1.2313490867614747,
+      "mean_token_accuracy": 0.7239270724356175,
+      "num_tokens": 487664.0,
+      "step": 150
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 159,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 1524702316230912.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/L2/checkpoints/checkpoint-150/training_args.bin b/L2/checkpoints/checkpoint-150/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c5ef2615541af048533dacdd04f01f920f86fece
--- /dev/null
+++ b/L2/checkpoints/checkpoint-150/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:063f2af09a09d13dafc33db4ec44d81e322816f9cd5d644aa0cda8a04f4b74b0
+size 5713
diff --git a/L2/checkpoints/checkpoint-159/README.md b/L2/checkpoints/checkpoint-159/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..9b1d0d5c752a5c9f2e3a0e3a9ead3759650a12a9
--- /dev/null
+++ b/L2/checkpoints/checkpoint-159/README.md
@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen3.5-0.8B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3.5-0.8B
+- lora
+- sft
+- transformers
+- trl
+---
+
+# 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 0.18.2.dev0
\ No newline at end of file
diff --git a/L2/checkpoints/checkpoint-159/adapter_config.json b/L2/checkpoints/checkpoint-159/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..466b55ef5352db25f2ac04e8aec438ce0764d848
--- /dev/null
+++ b/L2/checkpoints/checkpoint-159/adapter_config.json
@@ -0,0 +1,45 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3.5-0.8B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.2.dev0@076214c61f690898509b97702b5e9d95c826f000",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "q_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/L2/checkpoints/checkpoint-159/adapter_model.safetensors b/L2/checkpoints/checkpoint-159/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..a96c00c3fcd3252e6b87648332a039b7266fecce
--- /dev/null
+++ b/L2/checkpoints/checkpoint-159/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82b46c56db5a89a2ed29f527733ea30e3e74b69e0b6e15784dda006fba4dfe2d
+size 4331744
diff --git a/L2/checkpoints/checkpoint-159/chat_template.jinja b/L2/checkpoints/checkpoint-159/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..0ef09f214eaa6d9bca297988afc1454b5827b2c7
--- /dev/null
+++ b/L2/checkpoints/checkpoint-159/chat_template.jinja
@@ -0,0 +1,154 @@
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- macro render_content(content, do_vision_count, is_system_content=false) %}
+    {%- if content is string %}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping %}
+        {%- for item in content %}
+            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain images.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Picture ' ~ image_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
+            {%- elif 'video' in item or item.type == 'video' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain videos.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Video ' ~ video_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
+            {%- elif 'text' in item %}
+                {{- item.text }}
+            {%- else %}
+                {{- raise_exception('Unexpected item type in content.') }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif content is none or content is undefined %}
+        {{- '' }}
+    {%- else %}
+        {{- raise_exception('Unexpected content type.') }}
+    {%- endif %}
+{%- endmacro %}
+{%- if not messages %}
+    {{- raise_exception('No messages provided.') }}
+{%- endif %}
+{%- if tools and tools is iterable and tools is not mapping %}
+    {{- '<|im_start|>system\n' }}
+    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>" }}
+    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {%- if content %}
+            {{- '\n\n' + content }}
+        {%- endif %}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {{- '<|im_start|>system\n' + 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" %}
+        {%- set content = render_content(message.content, false)|trim %}
+        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
+            {%- set ns.multi_step_tool = false %}
+            {%- set ns.last_query_index = index %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if ns.multi_step_tool %}
+    {{- raise_exception('No user query found in messages.') }}
+{%- endif %}
+{%- for message in messages %}
+    {%- set content = render_content(message.content, true)|trim %}
+    {%- if message.role == "system" %}
+        {%- if not loop.first %}
+            {{- raise_exception('System message must be at the beginning.') }}
+        {%- endif %}
+    {%- elif message.role == "user" %}
+        {{- '<|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 %}
+        {%- set reasoning_content = reasoning_content|trim %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if tool_call.function is defined %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {%- if loop.first %}
+                    {%- if content|trim %}
+                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- else %}
+                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- endif %}
+                {%- else %}
+                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                {%- endif %}
+                {%- if tool_call.arguments is defined %}
+                    {%- for args_name, args_value in tool_call.arguments|items %}
+                        {{- '<parameter=' + args_name + '>\n' }}
+                        {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
+                        {{- args_value }}
+                        {{- '\n</parameter>\n' }}
+                    {%- endfor %}
+                {%- endif %}
+                {{- '</function>\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- else %}
+        {{- raise_exception('Unexpected message role.') }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is true %}
+        {{- '<think>\n' }}
+    {%- else %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}
\ No newline at end of file
diff --git a/L2/checkpoints/checkpoint-159/optimizer.pt b/L2/checkpoints/checkpoint-159/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..9e41a21034f82c1b4ea2c66d973e7aca5270e230
--- /dev/null
+++ b/L2/checkpoints/checkpoint-159/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:266f32244f1c1c8cb701c7e7079680891e1c8db408346aa20ed3baf1c88d7a32
+size 8690571
diff --git a/L2/checkpoints/checkpoint-159/rng_state.pth b/L2/checkpoints/checkpoint-159/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..7d150fc4504460cdea273ef2adcb04a65c626709
--- /dev/null
+++ b/L2/checkpoints/checkpoint-159/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dba4fde4ee04d2f472bb4dea96a48e8fdf7891d2b0694a8f012e8133a2e176ae
+size 14455
diff --git a/L2/checkpoints/checkpoint-159/scheduler.pt b/L2/checkpoints/checkpoint-159/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..f87e3c19ec47a9a829bf65c0292601f71a3ae173
--- /dev/null
+++ b/L2/checkpoints/checkpoint-159/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b2c6206a97d0884fd8dcbde955ce8b12473b8e47fac73a0c0671e5d2c6dfdd9
+size 1465
diff --git a/L2/checkpoints/checkpoint-159/tokenizer.json b/L2/checkpoints/checkpoint-159/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..67741b04f23bfdb46501f748ce27865ec82eccfb
--- /dev/null
+++ b/L2/checkpoints/checkpoint-159/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
+size 19989343
diff --git a/L2/checkpoints/checkpoint-159/tokenizer_config.json b/L2/checkpoints/checkpoint-159/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..0871602fcb7d15fcb2979685b1c7b609eef01a6f
--- /dev/null
+++ b/L2/checkpoints/checkpoint-159/tokenizer_config.json
@@ -0,0 +1,32 @@
+{
+  "add_prefix_space": false,
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "image_token": "<|image_pad|>",
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 512,
+  "model_specific_special_tokens": {
+    "audio_bos_token": "<|audio_start|>",
+    "audio_eos_token": "<|audio_end|>",
+    "audio_token": "<|audio_pad|>",
+    "image_token": "<|image_pad|>",
+    "video_token": "<|video_pad|>",
+    "vision_bos_token": "<|vision_start|>",
+    "vision_eos_token": "<|vision_end|>"
+  },
+  "pad_token": "<|endoftext|>",
+  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+  "split_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}
diff --git a/L2/checkpoints/checkpoint-159/trainer_state.json b/L2/checkpoints/checkpoint-159/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..3de6eed1acea2617d087a1b3dcc383485c287f3c
--- /dev/null
+++ b/L2/checkpoints/checkpoint-159/trainer_state.json
@@ -0,0 +1,184 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 159,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 2.35390625,
+      "epoch": 0.19138755980861244,
+      "grad_norm": 1.577696681022644,
+      "learning_rate": 0.0001999145758387301,
+      "loss": 2.517007064819336,
+      "mean_token_accuracy": 0.4835851963609457,
+      "num_tokens": 32923.0,
+      "step": 10
+    },
+    {
+      "entropy": 1.953515625,
+      "epoch": 0.3827751196172249,
+      "grad_norm": 1.822049856185913,
+      "learning_rate": 0.00019694002659393305,
+      "loss": 1.814153289794922,
+      "mean_token_accuracy": 0.6044577240943909,
+      "num_tokens": 65628.0,
+      "step": 20
+    },
+    {
+      "entropy": 1.36533203125,
+      "epoch": 0.5741626794258373,
+      "grad_norm": 0.8370082974433899,
+      "learning_rate": 0.0001898390981891979,
+      "loss": 1.4171125411987304,
+      "mean_token_accuracy": 0.6942351691424846,
+      "num_tokens": 98592.0,
+      "step": 30
+    },
+    {
+      "entropy": 1.33076171875,
+      "epoch": 0.7655502392344498,
+      "grad_norm": 0.7550845146179199,
+      "learning_rate": 0.00017891405093963938,
+      "loss": 1.3193041801452636,
+      "mean_token_accuracy": 0.7104418903589249,
+      "num_tokens": 131278.0,
+      "step": 40
+    },
+    {
+      "entropy": 1.312109375,
+      "epoch": 0.9569377990430622,
+      "grad_norm": 0.6932047009468079,
+      "learning_rate": 0.00016462992378609407,
+      "loss": 1.3077256202697753,
+      "mean_token_accuracy": 0.7093201003968715,
+      "num_tokens": 164256.0,
+      "step": 50
+    },
+    {
+      "entropy": 1.3107052364864864,
+      "epoch": 1.1339712918660287,
+      "grad_norm": 0.7087656855583191,
+      "learning_rate": 0.00014759473930370736,
+      "loss": 1.2949213981628418,
+      "mean_token_accuracy": 0.7117355780021565,
+      "num_tokens": 194746.0,
+      "step": 60
+    },
+    {
+      "entropy": 1.26064453125,
+      "epoch": 1.325358851674641,
+      "grad_norm": 0.8213269710540771,
+      "learning_rate": 0.00012853362242491053,
+      "loss": 1.244191551208496,
+      "mean_token_accuracy": 0.7226051487028599,
+      "num_tokens": 227482.0,
+      "step": 70
+    },
+    {
+      "entropy": 1.2599609375,
+      "epoch": 1.5167464114832536,
+      "grad_norm": 0.7758288383483887,
+      "learning_rate": 0.00010825793454723325,
+      "loss": 1.2582054138183594,
+      "mean_token_accuracy": 0.7165695309638977,
+      "num_tokens": 260195.0,
+      "step": 80
+    },
+    {
+      "entropy": 1.25322265625,
+      "epoch": 1.7081339712918662,
+      "grad_norm": 0.7961016893386841,
+      "learning_rate": 8.763073687306524e-05,
+      "loss": 1.2671056747436524,
+      "mean_token_accuracy": 0.7158558055758476,
+      "num_tokens": 292968.0,
+      "step": 90
+    },
+    {
+      "entropy": 1.28291015625,
+      "epoch": 1.8995215311004785,
+      "grad_norm": 0.757343590259552,
+      "learning_rate": 6.753005307953167e-05,
+      "loss": 1.2647873878479003,
+      "mean_token_accuracy": 0.7167910523712635,
+      "num_tokens": 325911.0,
+      "step": 100
+    },
+    {
+      "entropy": 1.2690033783783783,
+      "epoch": 2.076555023923445,
+      "grad_norm": 0.7981213331222534,
+      "learning_rate": 4.8811495091039926e-05,
+      "loss": 1.2404365539550781,
+      "mean_token_accuracy": 0.7189428822414295,
+      "num_tokens": 356114.0,
+      "step": 110
+    },
+    {
+      "entropy": 1.25244140625,
+      "epoch": 2.2679425837320575,
+      "grad_norm": 0.7682023048400879,
+      "learning_rate": 3.2271842837425906e-05,
+      "loss": 1.2295378684997558,
+      "mean_token_accuracy": 0.7262546218931675,
+      "num_tokens": 388999.0,
+      "step": 120
+    },
+    {
+      "entropy": 1.22822265625,
+      "epoch": 2.45933014354067,
+      "grad_norm": 0.7267993688583374,
+      "learning_rate": 1.861512827298051e-05,
+      "loss": 1.2186729431152343,
+      "mean_token_accuracy": 0.7247538149356842,
+      "num_tokens": 422226.0,
+      "step": 130
+    },
+    {
+      "entropy": 1.2375,
+      "epoch": 2.650717703349282,
+      "grad_norm": 0.7193359136581421,
+      "learning_rate": 8.422667334494249e-06,
+      "loss": 1.2260663032531738,
+      "mean_token_accuracy": 0.7221008919179439,
+      "num_tokens": 454978.0,
+      "step": 140
+    },
+    {
+      "entropy": 1.21845703125,
+      "epoch": 2.8421052631578947,
+      "grad_norm": 0.7832261323928833,
+      "learning_rate": 2.128315467264552e-06,
+      "loss": 1.2313490867614747,
+      "mean_token_accuracy": 0.7239270724356175,
+      "num_tokens": 487664.0,
+      "step": 150
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 159,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 10,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1608671854699392.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/L2/checkpoints/checkpoint-159/training_args.bin b/L2/checkpoints/checkpoint-159/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c5ef2615541af048533dacdd04f01f920f86fece
--- /dev/null
+++ b/L2/checkpoints/checkpoint-159/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:063f2af09a09d13dafc33db4ec44d81e322816f9cd5d644aa0cda8a04f4b74b0
+size 5713
diff --git a/L2/checkpoints/checkpoint-20/README.md b/L2/checkpoints/checkpoint-20/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..9b1d0d5c752a5c9f2e3a0e3a9ead3759650a12a9
--- /dev/null
+++ b/L2/checkpoints/checkpoint-20/README.md
@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen3.5-0.8B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3.5-0.8B
+- lora
+- sft
+- transformers
+- trl
+---
+
+# 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 0.18.2.dev0
\ No newline at end of file
diff --git a/L2/checkpoints/checkpoint-20/adapter_config.json b/L2/checkpoints/checkpoint-20/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..466b55ef5352db25f2ac04e8aec438ce0764d848
--- /dev/null
+++ b/L2/checkpoints/checkpoint-20/adapter_config.json
@@ -0,0 +1,45 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3.5-0.8B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.2.dev0@076214c61f690898509b97702b5e9d95c826f000",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "q_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/L2/checkpoints/checkpoint-20/adapter_model.safetensors b/L2/checkpoints/checkpoint-20/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..3937e84428958efb59f6369a0783843094c373ac
--- /dev/null
+++ b/L2/checkpoints/checkpoint-20/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2560659a5d9b9e442944c8e0dbbf1dbf2d6b38cba6d02630ce0187ed7bda4c52
+size 4331744
diff --git a/L2/checkpoints/checkpoint-20/chat_template.jinja b/L2/checkpoints/checkpoint-20/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..0ef09f214eaa6d9bca297988afc1454b5827b2c7
--- /dev/null
+++ b/L2/checkpoints/checkpoint-20/chat_template.jinja
@@ -0,0 +1,154 @@
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- macro render_content(content, do_vision_count, is_system_content=false) %}
+    {%- if content is string %}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping %}
+        {%- for item in content %}
+            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain images.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Picture ' ~ image_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
+            {%- elif 'video' in item or item.type == 'video' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain videos.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Video ' ~ video_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
+            {%- elif 'text' in item %}
+                {{- item.text }}
+            {%- else %}
+                {{- raise_exception('Unexpected item type in content.') }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif content is none or content is undefined %}
+        {{- '' }}
+    {%- else %}
+        {{- raise_exception('Unexpected content type.') }}
+    {%- endif %}
+{%- endmacro %}
+{%- if not messages %}
+    {{- raise_exception('No messages provided.') }}
+{%- endif %}
+{%- if tools and tools is iterable and tools is not mapping %}
+    {{- '<|im_start|>system\n' }}
+    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>" }}
+    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {%- if content %}
+            {{- '\n\n' + content }}
+        {%- endif %}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {{- '<|im_start|>system\n' + 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" %}
+        {%- set content = render_content(message.content, false)|trim %}
+        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
+            {%- set ns.multi_step_tool = false %}
+            {%- set ns.last_query_index = index %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if ns.multi_step_tool %}
+    {{- raise_exception('No user query found in messages.') }}
+{%- endif %}
+{%- for message in messages %}
+    {%- set content = render_content(message.content, true)|trim %}
+    {%- if message.role == "system" %}
+        {%- if not loop.first %}
+            {{- raise_exception('System message must be at the beginning.') }}
+        {%- endif %}
+    {%- elif message.role == "user" %}
+        {{- '<|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 %}
+        {%- set reasoning_content = reasoning_content|trim %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if tool_call.function is defined %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {%- if loop.first %}
+                    {%- if content|trim %}
+                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- else %}
+                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- endif %}
+                {%- else %}
+                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                {%- endif %}
+                {%- if tool_call.arguments is defined %}
+                    {%- for args_name, args_value in tool_call.arguments|items %}
+                        {{- '<parameter=' + args_name + '>\n' }}
+                        {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
+                        {{- args_value }}
+                        {{- '\n</parameter>\n' }}
+                    {%- endfor %}
+                {%- endif %}
+                {{- '</function>\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- else %}
+        {{- raise_exception('Unexpected message role.') }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is true %}
+        {{- '<think>\n' }}
+    {%- else %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}
\ No newline at end of file
diff --git a/L2/checkpoints/checkpoint-20/optimizer.pt b/L2/checkpoints/checkpoint-20/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..9b6cf0d84732476ff42196ff5d1e601dc53db17d
--- /dev/null
+++ b/L2/checkpoints/checkpoint-20/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:892c917919f4f7aefcaac8e738a534674acf52e0059e035ec5a7949607a7e7cd
+size 8690571
diff --git a/L2/checkpoints/checkpoint-20/rng_state.pth b/L2/checkpoints/checkpoint-20/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..3f5c250a692e034a27fb06d7008612b2de078116
--- /dev/null
+++ b/L2/checkpoints/checkpoint-20/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cddf27219365242ec1046a3532a63a24c3f350c77f100e4f973369db2cc849d
+size 14455
diff --git a/L2/checkpoints/checkpoint-20/scheduler.pt b/L2/checkpoints/checkpoint-20/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..19c5d720d9fd1aadfddfa1592620d1a5c18e2d01
--- /dev/null
+++ b/L2/checkpoints/checkpoint-20/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a55c2265171097c74232991dbd82262b6cfcfa2cf3bd4b0d5a7dfec293bf8656
+size 1465
diff --git a/L2/checkpoints/checkpoint-20/tokenizer.json b/L2/checkpoints/checkpoint-20/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..67741b04f23bfdb46501f748ce27865ec82eccfb
--- /dev/null
+++ b/L2/checkpoints/checkpoint-20/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
+size 19989343
diff --git a/L2/checkpoints/checkpoint-20/tokenizer_config.json b/L2/checkpoints/checkpoint-20/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..0871602fcb7d15fcb2979685b1c7b609eef01a6f
--- /dev/null
+++ b/L2/checkpoints/checkpoint-20/tokenizer_config.json
@@ -0,0 +1,32 @@
+{
+  "add_prefix_space": false,
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "image_token": "<|image_pad|>",
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 512,
+  "model_specific_special_tokens": {
+    "audio_bos_token": "<|audio_start|>",
+    "audio_eos_token": "<|audio_end|>",
+    "audio_token": "<|audio_pad|>",
+    "image_token": "<|image_pad|>",
+    "video_token": "<|video_pad|>",
+    "vision_bos_token": "<|vision_start|>",
+    "vision_eos_token": "<|vision_end|>"
+  },
+  "pad_token": "<|endoftext|>",
+  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+  "split_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}
diff --git a/L2/checkpoints/checkpoint-20/trainer_state.json b/L2/checkpoints/checkpoint-20/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..413423a0aa328ed2c12594e0cf6d17c95a672540
--- /dev/null
+++ b/L2/checkpoints/checkpoint-20/trainer_state.json
@@ -0,0 +1,54 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.3827751196172249,
+  "eval_steps": 500,
+  "global_step": 20,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 2.35390625,
+      "epoch": 0.19138755980861244,
+      "grad_norm": 1.577696681022644,
+      "learning_rate": 0.0001999145758387301,
+      "loss": 2.517007064819336,
+      "mean_token_accuracy": 0.4835851963609457,
+      "num_tokens": 32923.0,
+      "step": 10
+    },
+    {
+      "entropy": 1.953515625,
+      "epoch": 0.3827751196172249,
+      "grad_norm": 1.822049856185913,
+      "learning_rate": 0.00019694002659393305,
+      "loss": 1.814153289794922,
+      "mean_token_accuracy": 0.6044577240943909,
+      "num_tokens": 65628.0,
+      "step": 20
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 159,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 205438581899520.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/L2/checkpoints/checkpoint-20/training_args.bin b/L2/checkpoints/checkpoint-20/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c5ef2615541af048533dacdd04f01f920f86fece
--- /dev/null
+++ b/L2/checkpoints/checkpoint-20/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:063f2af09a09d13dafc33db4ec44d81e322816f9cd5d644aa0cda8a04f4b74b0
+size 5713
diff --git a/L2/checkpoints/checkpoint-30/README.md b/L2/checkpoints/checkpoint-30/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..9b1d0d5c752a5c9f2e3a0e3a9ead3759650a12a9
--- /dev/null
+++ b/L2/checkpoints/checkpoint-30/README.md
@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen3.5-0.8B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3.5-0.8B
+- lora
+- sft
+- transformers
+- trl
+---
+
+# 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 0.18.2.dev0
\ No newline at end of file
diff --git a/L2/checkpoints/checkpoint-30/adapter_config.json b/L2/checkpoints/checkpoint-30/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..466b55ef5352db25f2ac04e8aec438ce0764d848
--- /dev/null
+++ b/L2/checkpoints/checkpoint-30/adapter_config.json
@@ -0,0 +1,45 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3.5-0.8B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.2.dev0@076214c61f690898509b97702b5e9d95c826f000",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "q_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/L2/checkpoints/checkpoint-30/adapter_model.safetensors b/L2/checkpoints/checkpoint-30/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..565c95e33de4f2e7788c54865223c658d67c5bab
--- /dev/null
+++ b/L2/checkpoints/checkpoint-30/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f04529ce41af7e77cf83c23f283e2b01b4bfafab074f3bbd996a3ab9f89a95f
+size 4331744
diff --git a/L2/checkpoints/checkpoint-30/chat_template.jinja b/L2/checkpoints/checkpoint-30/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..0ef09f214eaa6d9bca297988afc1454b5827b2c7
--- /dev/null
+++ b/L2/checkpoints/checkpoint-30/chat_template.jinja
@@ -0,0 +1,154 @@
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- macro render_content(content, do_vision_count, is_system_content=false) %}
+    {%- if content is string %}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping %}
+        {%- for item in content %}
+            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain images.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Picture ' ~ image_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
+            {%- elif 'video' in item or item.type == 'video' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain videos.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Video ' ~ video_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
+            {%- elif 'text' in item %}
+                {{- item.text }}
+            {%- else %}
+                {{- raise_exception('Unexpected item type in content.') }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif content is none or content is undefined %}
+        {{- '' }}
+    {%- else %}
+        {{- raise_exception('Unexpected content type.') }}
+    {%- endif %}
+{%- endmacro %}
+{%- if not messages %}
+    {{- raise_exception('No messages provided.') }}
+{%- endif %}
+{%- if tools and tools is iterable and tools is not mapping %}
+    {{- '<|im_start|>system\n' }}
+    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>" }}
+    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {%- if content %}
+            {{- '\n\n' + content }}
+        {%- endif %}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {{- '<|im_start|>system\n' + 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" %}
+        {%- set content = render_content(message.content, false)|trim %}
+        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
+            {%- set ns.multi_step_tool = false %}
+            {%- set ns.last_query_index = index %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if ns.multi_step_tool %}
+    {{- raise_exception('No user query found in messages.') }}
+{%- endif %}
+{%- for message in messages %}
+    {%- set content = render_content(message.content, true)|trim %}
+    {%- if message.role == "system" %}
+        {%- if not loop.first %}
+            {{- raise_exception('System message must be at the beginning.') }}
+        {%- endif %}
+    {%- elif message.role == "user" %}
+        {{- '<|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 %}
+        {%- set reasoning_content = reasoning_content|trim %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if tool_call.function is defined %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {%- if loop.first %}
+                    {%- if content|trim %}
+                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- else %}
+                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- endif %}
+                {%- else %}
+                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                {%- endif %}
+                {%- if tool_call.arguments is defined %}
+                    {%- for args_name, args_value in tool_call.arguments|items %}
+                        {{- '<parameter=' + args_name + '>\n' }}
+                        {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
+                        {{- args_value }}
+                        {{- '\n</parameter>\n' }}
+                    {%- endfor %}
+                {%- endif %}
+                {{- '</function>\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- else %}
+        {{- raise_exception('Unexpected message role.') }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is true %}
+        {{- '<think>\n' }}
+    {%- else %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}
\ No newline at end of file
diff --git a/L2/checkpoints/checkpoint-30/optimizer.pt b/L2/checkpoints/checkpoint-30/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..72021aaf4bdbc8b8ab1a3decc0357bc3ebf6226e
--- /dev/null
+++ b/L2/checkpoints/checkpoint-30/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc20395fceac35a6e5343164c43e6188c2b064731f7320a5e16d8af6aeff560a
+size 8690571
diff --git a/L2/checkpoints/checkpoint-30/rng_state.pth b/L2/checkpoints/checkpoint-30/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..3f5c250a692e034a27fb06d7008612b2de078116
--- /dev/null
+++ b/L2/checkpoints/checkpoint-30/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cddf27219365242ec1046a3532a63a24c3f350c77f100e4f973369db2cc849d
+size 14455
diff --git a/L2/checkpoints/checkpoint-30/scheduler.pt b/L2/checkpoints/checkpoint-30/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..e67f345290edd2767d65bc2a0d39f112608d731e
--- /dev/null
+++ b/L2/checkpoints/checkpoint-30/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5714db383b01493e282f902afe194d44c50334403abd999cb0a6f6d875dd5b8
+size 1465
diff --git a/L2/checkpoints/checkpoint-30/tokenizer.json b/L2/checkpoints/checkpoint-30/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..67741b04f23bfdb46501f748ce27865ec82eccfb
--- /dev/null
+++ b/L2/checkpoints/checkpoint-30/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
+size 19989343
diff --git a/L2/checkpoints/checkpoint-30/tokenizer_config.json b/L2/checkpoints/checkpoint-30/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..0871602fcb7d15fcb2979685b1c7b609eef01a6f
--- /dev/null
+++ b/L2/checkpoints/checkpoint-30/tokenizer_config.json
@@ -0,0 +1,32 @@
+{
+  "add_prefix_space": false,
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "image_token": "<|image_pad|>",
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 512,
+  "model_specific_special_tokens": {
+    "audio_bos_token": "<|audio_start|>",
+    "audio_eos_token": "<|audio_end|>",
+    "audio_token": "<|audio_pad|>",
+    "image_token": "<|image_pad|>",
+    "video_token": "<|video_pad|>",
+    "vision_bos_token": "<|vision_start|>",
+    "vision_eos_token": "<|vision_end|>"
+  },
+  "pad_token": "<|endoftext|>",
+  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+  "split_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}
diff --git a/L2/checkpoints/checkpoint-30/trainer_state.json b/L2/checkpoints/checkpoint-30/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..f1a8d9d879b530a8ca38c260bda28904c97f4300
--- /dev/null
+++ b/L2/checkpoints/checkpoint-30/trainer_state.json
@@ -0,0 +1,64 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.5741626794258373,
+  "eval_steps": 500,
+  "global_step": 30,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 2.35390625,
+      "epoch": 0.19138755980861244,
+      "grad_norm": 1.577696681022644,
+      "learning_rate": 0.0001999145758387301,
+      "loss": 2.517007064819336,
+      "mean_token_accuracy": 0.4835851963609457,
+      "num_tokens": 32923.0,
+      "step": 10
+    },
+    {
+      "entropy": 1.953515625,
+      "epoch": 0.3827751196172249,
+      "grad_norm": 1.822049856185913,
+      "learning_rate": 0.00019694002659393305,
+      "loss": 1.814153289794922,
+      "mean_token_accuracy": 0.6044577240943909,
+      "num_tokens": 65628.0,
+      "step": 20
+    },
+    {
+      "entropy": 1.36533203125,
+      "epoch": 0.5741626794258373,
+      "grad_norm": 0.8370082974433899,
+      "learning_rate": 0.0001898390981891979,
+      "loss": 1.4171125411987304,
+      "mean_token_accuracy": 0.6942351691424846,
+      "num_tokens": 98592.0,
+      "step": 30
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 159,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 308065022637312.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/L2/checkpoints/checkpoint-30/training_args.bin b/L2/checkpoints/checkpoint-30/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c5ef2615541af048533dacdd04f01f920f86fece
--- /dev/null
+++ b/L2/checkpoints/checkpoint-30/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:063f2af09a09d13dafc33db4ec44d81e322816f9cd5d644aa0cda8a04f4b74b0
+size 5713
diff --git a/L2/checkpoints/checkpoint-40/README.md b/L2/checkpoints/checkpoint-40/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..9b1d0d5c752a5c9f2e3a0e3a9ead3759650a12a9
--- /dev/null
+++ b/L2/checkpoints/checkpoint-40/README.md
@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen3.5-0.8B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3.5-0.8B
+- lora
+- sft
+- transformers
+- trl
+---
+
+# 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 0.18.2.dev0
\ No newline at end of file
diff --git a/L2/checkpoints/checkpoint-40/adapter_config.json b/L2/checkpoints/checkpoint-40/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..466b55ef5352db25f2ac04e8aec438ce0764d848
--- /dev/null
+++ b/L2/checkpoints/checkpoint-40/adapter_config.json
@@ -0,0 +1,45 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3.5-0.8B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.2.dev0@076214c61f690898509b97702b5e9d95c826f000",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "q_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/L2/checkpoints/checkpoint-40/adapter_model.safetensors b/L2/checkpoints/checkpoint-40/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..060f4a6be32c8477384056f8ed392a8c9a9a1b87
--- /dev/null
+++ b/L2/checkpoints/checkpoint-40/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8237345993f0890ce37fd6cbe30ef33329f3e249e71005640ab4e96e9a2d321
+size 4331744
diff --git a/L2/checkpoints/checkpoint-40/chat_template.jinja b/L2/checkpoints/checkpoint-40/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..0ef09f214eaa6d9bca297988afc1454b5827b2c7
--- /dev/null
+++ b/L2/checkpoints/checkpoint-40/chat_template.jinja
@@ -0,0 +1,154 @@
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- macro render_content(content, do_vision_count, is_system_content=false) %}
+    {%- if content is string %}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping %}
+        {%- for item in content %}
+            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain images.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Picture ' ~ image_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
+            {%- elif 'video' in item or item.type == 'video' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain videos.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Video ' ~ video_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
+            {%- elif 'text' in item %}
+                {{- item.text }}
+            {%- else %}
+                {{- raise_exception('Unexpected item type in content.') }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif content is none or content is undefined %}
+        {{- '' }}
+    {%- else %}
+        {{- raise_exception('Unexpected content type.') }}
+    {%- endif %}
+{%- endmacro %}
+{%- if not messages %}
+    {{- raise_exception('No messages provided.') }}
+{%- endif %}
+{%- if tools and tools is iterable and tools is not mapping %}
+    {{- '<|im_start|>system\n' }}
+    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>" }}
+    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {%- if content %}
+            {{- '\n\n' + content }}
+        {%- endif %}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {{- '<|im_start|>system\n' + 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" %}
+        {%- set content = render_content(message.content, false)|trim %}
+        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
+            {%- set ns.multi_step_tool = false %}
+            {%- set ns.last_query_index = index %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if ns.multi_step_tool %}
+    {{- raise_exception('No user query found in messages.') }}
+{%- endif %}
+{%- for message in messages %}
+    {%- set content = render_content(message.content, true)|trim %}
+    {%- if message.role == "system" %}
+        {%- if not loop.first %}
+            {{- raise_exception('System message must be at the beginning.') }}
+        {%- endif %}
+    {%- elif message.role == "user" %}
+        {{- '<|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 %}
+        {%- set reasoning_content = reasoning_content|trim %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if tool_call.function is defined %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {%- if loop.first %}
+                    {%- if content|trim %}
+                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- else %}
+                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- endif %}
+                {%- else %}
+                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                {%- endif %}
+                {%- if tool_call.arguments is defined %}
+                    {%- for args_name, args_value in tool_call.arguments|items %}
+                        {{- '<parameter=' + args_name + '>\n' }}
+                        {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
+                        {{- args_value }}
+                        {{- '\n</parameter>\n' }}
+                    {%- endfor %}
+                {%- endif %}
+                {{- '</function>\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- else %}
+        {{- raise_exception('Unexpected message role.') }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is true %}
+        {{- '<think>\n' }}
+    {%- else %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}
\ No newline at end of file
diff --git a/L2/checkpoints/checkpoint-40/optimizer.pt b/L2/checkpoints/checkpoint-40/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..375f749459904a6fafa0906aad9017be51180891
--- /dev/null
+++ b/L2/checkpoints/checkpoint-40/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a96c820231dd9e1913465fb4b5c85018f2e4517f5fdf964ce70716c68440af2
+size 8690571
diff --git a/L2/checkpoints/checkpoint-40/rng_state.pth b/L2/checkpoints/checkpoint-40/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..3f5c250a692e034a27fb06d7008612b2de078116
--- /dev/null
+++ b/L2/checkpoints/checkpoint-40/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cddf27219365242ec1046a3532a63a24c3f350c77f100e4f973369db2cc849d
+size 14455
diff --git a/L2/checkpoints/checkpoint-40/scheduler.pt b/L2/checkpoints/checkpoint-40/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..d277614299656d3c5f7cf2fa488957961f886c69
--- /dev/null
+++ b/L2/checkpoints/checkpoint-40/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6ab065d4e48130a57f256525f3b5c7ec35cb4454ae9ef2f4ce13133dbee5eee
+size 1465
diff --git a/L2/checkpoints/checkpoint-40/tokenizer.json b/L2/checkpoints/checkpoint-40/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..67741b04f23bfdb46501f748ce27865ec82eccfb
--- /dev/null
+++ b/L2/checkpoints/checkpoint-40/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
+size 19989343
diff --git a/L2/checkpoints/checkpoint-40/tokenizer_config.json b/L2/checkpoints/checkpoint-40/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..0871602fcb7d15fcb2979685b1c7b609eef01a6f
--- /dev/null
+++ b/L2/checkpoints/checkpoint-40/tokenizer_config.json
@@ -0,0 +1,32 @@
+{
+  "add_prefix_space": false,
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "image_token": "<|image_pad|>",
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 512,
+  "model_specific_special_tokens": {
+    "audio_bos_token": "<|audio_start|>",
+    "audio_eos_token": "<|audio_end|>",
+    "audio_token": "<|audio_pad|>",
+    "image_token": "<|image_pad|>",
+    "video_token": "<|video_pad|>",
+    "vision_bos_token": "<|vision_start|>",
+    "vision_eos_token": "<|vision_end|>"
+  },
+  "pad_token": "<|endoftext|>",
+  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+  "split_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}
diff --git a/L2/checkpoints/checkpoint-40/trainer_state.json b/L2/checkpoints/checkpoint-40/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..7ff05c7a02fd3283afd95749349bc3ba226f29b1
--- /dev/null
+++ b/L2/checkpoints/checkpoint-40/trainer_state.json
@@ -0,0 +1,74 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.7655502392344498,
+  "eval_steps": 500,
+  "global_step": 40,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 2.35390625,
+      "epoch": 0.19138755980861244,
+      "grad_norm": 1.577696681022644,
+      "learning_rate": 0.0001999145758387301,
+      "loss": 2.517007064819336,
+      "mean_token_accuracy": 0.4835851963609457,
+      "num_tokens": 32923.0,
+      "step": 10
+    },
+    {
+      "entropy": 1.953515625,
+      "epoch": 0.3827751196172249,
+      "grad_norm": 1.822049856185913,
+      "learning_rate": 0.00019694002659393305,
+      "loss": 1.814153289794922,
+      "mean_token_accuracy": 0.6044577240943909,
+      "num_tokens": 65628.0,
+      "step": 20
+    },
+    {
+      "entropy": 1.36533203125,
+      "epoch": 0.5741626794258373,
+      "grad_norm": 0.8370082974433899,
+      "learning_rate": 0.0001898390981891979,
+      "loss": 1.4171125411987304,
+      "mean_token_accuracy": 0.6942351691424846,
+      "num_tokens": 98592.0,
+      "step": 30
+    },
+    {
+      "entropy": 1.33076171875,
+      "epoch": 0.7655502392344498,
+      "grad_norm": 0.7550845146179199,
+      "learning_rate": 0.00017891405093963938,
+      "loss": 1.3193041801452636,
+      "mean_token_accuracy": 0.7104418903589249,
+      "num_tokens": 131278.0,
+      "step": 40
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 159,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 410224217147136.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/L2/checkpoints/checkpoint-40/training_args.bin b/L2/checkpoints/checkpoint-40/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c5ef2615541af048533dacdd04f01f920f86fece
--- /dev/null
+++ b/L2/checkpoints/checkpoint-40/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:063f2af09a09d13dafc33db4ec44d81e322816f9cd5d644aa0cda8a04f4b74b0
+size 5713
diff --git a/L2/checkpoints/checkpoint-50/README.md b/L2/checkpoints/checkpoint-50/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..9b1d0d5c752a5c9f2e3a0e3a9ead3759650a12a9
--- /dev/null
+++ b/L2/checkpoints/checkpoint-50/README.md
@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen3.5-0.8B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3.5-0.8B
+- lora
+- sft
+- transformers
+- trl
+---
+
+# 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 0.18.2.dev0
\ No newline at end of file
diff --git a/L2/checkpoints/checkpoint-50/adapter_config.json b/L2/checkpoints/checkpoint-50/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..466b55ef5352db25f2ac04e8aec438ce0764d848
--- /dev/null
+++ b/L2/checkpoints/checkpoint-50/adapter_config.json
@@ -0,0 +1,45 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3.5-0.8B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.2.dev0@076214c61f690898509b97702b5e9d95c826f000",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "q_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/L2/checkpoints/checkpoint-50/adapter_model.safetensors b/L2/checkpoints/checkpoint-50/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..82fdfce990498c4709770efabf2e8935dd8443d7
--- /dev/null
+++ b/L2/checkpoints/checkpoint-50/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e79e43ad02494262279ce22b642aaa8e73616387acd9ba78d27b33c35de5e179
+size 4331744
diff --git a/L2/checkpoints/checkpoint-50/chat_template.jinja b/L2/checkpoints/checkpoint-50/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..0ef09f214eaa6d9bca297988afc1454b5827b2c7
--- /dev/null
+++ b/L2/checkpoints/checkpoint-50/chat_template.jinja
@@ -0,0 +1,154 @@
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- macro render_content(content, do_vision_count, is_system_content=false) %}
+    {%- if content is string %}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping %}
+        {%- for item in content %}
+            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain images.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Picture ' ~ image_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
+            {%- elif 'video' in item or item.type == 'video' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain videos.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Video ' ~ video_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
+            {%- elif 'text' in item %}
+                {{- item.text }}
+            {%- else %}
+                {{- raise_exception('Unexpected item type in content.') }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif content is none or content is undefined %}
+        {{- '' }}
+    {%- else %}
+        {{- raise_exception('Unexpected content type.') }}
+    {%- endif %}
+{%- endmacro %}
+{%- if not messages %}
+    {{- raise_exception('No messages provided.') }}
+{%- endif %}
+{%- if tools and tools is iterable and tools is not mapping %}
+    {{- '<|im_start|>system\n' }}
+    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>" }}
+    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {%- if content %}
+            {{- '\n\n' + content }}
+        {%- endif %}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {{- '<|im_start|>system\n' + 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" %}
+        {%- set content = render_content(message.content, false)|trim %}
+        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
+            {%- set ns.multi_step_tool = false %}
+            {%- set ns.last_query_index = index %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if ns.multi_step_tool %}
+    {{- raise_exception('No user query found in messages.') }}
+{%- endif %}
+{%- for message in messages %}
+    {%- set content = render_content(message.content, true)|trim %}
+    {%- if message.role == "system" %}
+        {%- if not loop.first %}
+            {{- raise_exception('System message must be at the beginning.') }}
+        {%- endif %}
+    {%- elif message.role == "user" %}
+        {{- '<|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 %}
+        {%- set reasoning_content = reasoning_content|trim %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if tool_call.function is defined %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {%- if loop.first %}
+                    {%- if content|trim %}
+                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- else %}
+                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- endif %}
+                {%- else %}
+                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                {%- endif %}
+                {%- if tool_call.arguments is defined %}
+                    {%- for args_name, args_value in tool_call.arguments|items %}
+                        {{- '<parameter=' + args_name + '>\n' }}
+                        {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
+                        {{- args_value }}
+                        {{- '\n</parameter>\n' }}
+                    {%- endfor %}
+                {%- endif %}
+                {{- '</function>\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- else %}
+        {{- raise_exception('Unexpected message role.') }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is true %}
+        {{- '<think>\n' }}
+    {%- else %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}
\ No newline at end of file
diff --git a/L2/checkpoints/checkpoint-50/optimizer.pt b/L2/checkpoints/checkpoint-50/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..6c8b9fa378ef8eeba1003523b1ae06a584ea85b7
--- /dev/null
+++ b/L2/checkpoints/checkpoint-50/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3115826c5a84deac0b398f616e3669fef703cc71dff6869fef94677806ba746
+size 8690571
diff --git a/L2/checkpoints/checkpoint-50/rng_state.pth b/L2/checkpoints/checkpoint-50/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..3f5c250a692e034a27fb06d7008612b2de078116
--- /dev/null
+++ b/L2/checkpoints/checkpoint-50/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cddf27219365242ec1046a3532a63a24c3f350c77f100e4f973369db2cc849d
+size 14455
diff --git a/L2/checkpoints/checkpoint-50/scheduler.pt b/L2/checkpoints/checkpoint-50/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..8dfa70f8756ce63cbbdda959a0f49cb5d5040eaf
--- /dev/null
+++ b/L2/checkpoints/checkpoint-50/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06e42634db8916928265bbd702cb453e8ac4774a2c83e1b2f1905185363111e5
+size 1465
diff --git a/L2/checkpoints/checkpoint-50/tokenizer.json b/L2/checkpoints/checkpoint-50/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..67741b04f23bfdb46501f748ce27865ec82eccfb
--- /dev/null
+++ b/L2/checkpoints/checkpoint-50/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
+size 19989343
diff --git a/L2/checkpoints/checkpoint-50/tokenizer_config.json b/L2/checkpoints/checkpoint-50/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..0871602fcb7d15fcb2979685b1c7b609eef01a6f
--- /dev/null
+++ b/L2/checkpoints/checkpoint-50/tokenizer_config.json
@@ -0,0 +1,32 @@
+{
+  "add_prefix_space": false,
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "image_token": "<|image_pad|>",
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 512,
+  "model_specific_special_tokens": {
+    "audio_bos_token": "<|audio_start|>",
+    "audio_eos_token": "<|audio_end|>",
+    "audio_token": "<|audio_pad|>",
+    "image_token": "<|image_pad|>",
+    "video_token": "<|video_pad|>",
+    "vision_bos_token": "<|vision_start|>",
+    "vision_eos_token": "<|vision_end|>"
+  },
+  "pad_token": "<|endoftext|>",
+  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+  "split_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}
diff --git a/L2/checkpoints/checkpoint-50/trainer_state.json b/L2/checkpoints/checkpoint-50/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..81396daf223dec9d7723ad06616e6377e850eba4
--- /dev/null
+++ b/L2/checkpoints/checkpoint-50/trainer_state.json
@@ -0,0 +1,84 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9569377990430622,
+  "eval_steps": 500,
+  "global_step": 50,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 2.35390625,
+      "epoch": 0.19138755980861244,
+      "grad_norm": 1.577696681022644,
+      "learning_rate": 0.0001999145758387301,
+      "loss": 2.517007064819336,
+      "mean_token_accuracy": 0.4835851963609457,
+      "num_tokens": 32923.0,
+      "step": 10
+    },
+    {
+      "entropy": 1.953515625,
+      "epoch": 0.3827751196172249,
+      "grad_norm": 1.822049856185913,
+      "learning_rate": 0.00019694002659393305,
+      "loss": 1.814153289794922,
+      "mean_token_accuracy": 0.6044577240943909,
+      "num_tokens": 65628.0,
+      "step": 20
+    },
+    {
+      "entropy": 1.36533203125,
+      "epoch": 0.5741626794258373,
+      "grad_norm": 0.8370082974433899,
+      "learning_rate": 0.0001898390981891979,
+      "loss": 1.4171125411987304,
+      "mean_token_accuracy": 0.6942351691424846,
+      "num_tokens": 98592.0,
+      "step": 30
+    },
+    {
+      "entropy": 1.33076171875,
+      "epoch": 0.7655502392344498,
+      "grad_norm": 0.7550845146179199,
+      "learning_rate": 0.00017891405093963938,
+      "loss": 1.3193041801452636,
+      "mean_token_accuracy": 0.7104418903589249,
+      "num_tokens": 131278.0,
+      "step": 40
+    },
+    {
+      "entropy": 1.312109375,
+      "epoch": 0.9569377990430622,
+      "grad_norm": 0.6932047009468079,
+      "learning_rate": 0.00016462992378609407,
+      "loss": 1.3077256202697753,
+      "mean_token_accuracy": 0.7093201003968715,
+      "num_tokens": 164256.0,
+      "step": 50
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 159,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 513174136042752.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/L2/checkpoints/checkpoint-50/training_args.bin b/L2/checkpoints/checkpoint-50/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c5ef2615541af048533dacdd04f01f920f86fece
--- /dev/null
+++ b/L2/checkpoints/checkpoint-50/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:063f2af09a09d13dafc33db4ec44d81e322816f9cd5d644aa0cda8a04f4b74b0
+size 5713
diff --git a/L2/checkpoints/checkpoint-60/README.md b/L2/checkpoints/checkpoint-60/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..9b1d0d5c752a5c9f2e3a0e3a9ead3759650a12a9
--- /dev/null
+++ b/L2/checkpoints/checkpoint-60/README.md
@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen3.5-0.8B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3.5-0.8B
+- lora
+- sft
+- transformers
+- trl
+---
+
+# 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 0.18.2.dev0
\ No newline at end of file
diff --git a/L2/checkpoints/checkpoint-60/adapter_config.json b/L2/checkpoints/checkpoint-60/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..466b55ef5352db25f2ac04e8aec438ce0764d848
--- /dev/null
+++ b/L2/checkpoints/checkpoint-60/adapter_config.json
@@ -0,0 +1,45 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3.5-0.8B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.2.dev0@076214c61f690898509b97702b5e9d95c826f000",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "q_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/L2/checkpoints/checkpoint-60/adapter_model.safetensors b/L2/checkpoints/checkpoint-60/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..febe3ac2ac08edc27d882168761dce4dce09ed7f
--- /dev/null
+++ b/L2/checkpoints/checkpoint-60/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc585fa51231d86fb5eae1eb3dcd5d4359cb4f657c85bff66f2a4461f6ac173e
+size 4331744
diff --git a/L2/checkpoints/checkpoint-60/chat_template.jinja b/L2/checkpoints/checkpoint-60/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..0ef09f214eaa6d9bca297988afc1454b5827b2c7
--- /dev/null
+++ b/L2/checkpoints/checkpoint-60/chat_template.jinja
@@ -0,0 +1,154 @@
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- macro render_content(content, do_vision_count, is_system_content=false) %}
+    {%- if content is string %}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping %}
+        {%- for item in content %}
+            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain images.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Picture ' ~ image_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
+            {%- elif 'video' in item or item.type == 'video' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain videos.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Video ' ~ video_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
+            {%- elif 'text' in item %}
+                {{- item.text }}
+            {%- else %}
+                {{- raise_exception('Unexpected item type in content.') }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif content is none or content is undefined %}
+        {{- '' }}
+    {%- else %}
+        {{- raise_exception('Unexpected content type.') }}
+    {%- endif %}
+{%- endmacro %}
+{%- if not messages %}
+    {{- raise_exception('No messages provided.') }}
+{%- endif %}
+{%- if tools and tools is iterable and tools is not mapping %}
+    {{- '<|im_start|>system\n' }}
+    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>" }}
+    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {%- if content %}
+            {{- '\n\n' + content }}
+        {%- endif %}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {{- '<|im_start|>system\n' + 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" %}
+        {%- set content = render_content(message.content, false)|trim %}
+        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
+            {%- set ns.multi_step_tool = false %}
+            {%- set ns.last_query_index = index %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if ns.multi_step_tool %}
+    {{- raise_exception('No user query found in messages.') }}
+{%- endif %}
+{%- for message in messages %}
+    {%- set content = render_content(message.content, true)|trim %}
+    {%- if message.role == "system" %}
+        {%- if not loop.first %}
+            {{- raise_exception('System message must be at the beginning.') }}
+        {%- endif %}
+    {%- elif message.role == "user" %}
+        {{- '<|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 %}
+        {%- set reasoning_content = reasoning_content|trim %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if tool_call.function is defined %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {%- if loop.first %}
+                    {%- if content|trim %}
+                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- else %}
+                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- endif %}
+                {%- else %}
+                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                {%- endif %}
+                {%- if tool_call.arguments is defined %}
+                    {%- for args_name, args_value in tool_call.arguments|items %}
+                        {{- '<parameter=' + args_name + '>\n' }}
+                        {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
+                        {{- args_value }}
+                        {{- '\n</parameter>\n' }}
+                    {%- endfor %}
+                {%- endif %}
+                {{- '</function>\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- else %}
+        {{- raise_exception('Unexpected message role.') }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is true %}
+        {{- '<think>\n' }}
+    {%- else %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}
\ No newline at end of file
diff --git a/L2/checkpoints/checkpoint-60/optimizer.pt b/L2/checkpoints/checkpoint-60/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..039b7a57512d34d2422819a3cfcda787f92a8f1d
--- /dev/null
+++ b/L2/checkpoints/checkpoint-60/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ae2f6b4f5c4b6905af849ac0cdcb3687d254c56158b232d67d1a1b869342581
+size 8690571
diff --git a/L2/checkpoints/checkpoint-60/rng_state.pth b/L2/checkpoints/checkpoint-60/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..38c6d5df0a659b81300f358fefb31a6f4aa51ddc
--- /dev/null
+++ b/L2/checkpoints/checkpoint-60/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3a77d4a8b98ce027a4d6a3b9fb5d7c904e27ec1efd5c0468c24fa26bb738316
+size 14455
diff --git a/L2/checkpoints/checkpoint-60/scheduler.pt b/L2/checkpoints/checkpoint-60/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..0332598581c0fc180611ee71c3947361daad8502
--- /dev/null
+++ b/L2/checkpoints/checkpoint-60/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78d647f03c1cf87f7118cf942735589fe5fc5b2f1991d453c311ad9bb47c1543
+size 1465
diff --git a/L2/checkpoints/checkpoint-60/tokenizer.json b/L2/checkpoints/checkpoint-60/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..67741b04f23bfdb46501f748ce27865ec82eccfb
--- /dev/null
+++ b/L2/checkpoints/checkpoint-60/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
+size 19989343
diff --git a/L2/checkpoints/checkpoint-60/tokenizer_config.json b/L2/checkpoints/checkpoint-60/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..0871602fcb7d15fcb2979685b1c7b609eef01a6f
--- /dev/null
+++ b/L2/checkpoints/checkpoint-60/tokenizer_config.json
@@ -0,0 +1,32 @@
+{
+  "add_prefix_space": false,
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "image_token": "<|image_pad|>",
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 512,
+  "model_specific_special_tokens": {
+    "audio_bos_token": "<|audio_start|>",
+    "audio_eos_token": "<|audio_end|>",
+    "audio_token": "<|audio_pad|>",
+    "image_token": "<|image_pad|>",
+    "video_token": "<|video_pad|>",
+    "vision_bos_token": "<|vision_start|>",
+    "vision_eos_token": "<|vision_end|>"
+  },
+  "pad_token": "<|endoftext|>",
+  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+  "split_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}
diff --git a/L2/checkpoints/checkpoint-60/trainer_state.json b/L2/checkpoints/checkpoint-60/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..e7e93f228400eafeefb7c2b23d20cbfb4e2cb766
--- /dev/null
+++ b/L2/checkpoints/checkpoint-60/trainer_state.json
@@ -0,0 +1,94 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.1339712918660287,
+  "eval_steps": 500,
+  "global_step": 60,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 2.35390625,
+      "epoch": 0.19138755980861244,
+      "grad_norm": 1.577696681022644,
+      "learning_rate": 0.0001999145758387301,
+      "loss": 2.517007064819336,
+      "mean_token_accuracy": 0.4835851963609457,
+      "num_tokens": 32923.0,
+      "step": 10
+    },
+    {
+      "entropy": 1.953515625,
+      "epoch": 0.3827751196172249,
+      "grad_norm": 1.822049856185913,
+      "learning_rate": 0.00019694002659393305,
+      "loss": 1.814153289794922,
+      "mean_token_accuracy": 0.6044577240943909,
+      "num_tokens": 65628.0,
+      "step": 20
+    },
+    {
+      "entropy": 1.36533203125,
+      "epoch": 0.5741626794258373,
+      "grad_norm": 0.8370082974433899,
+      "learning_rate": 0.0001898390981891979,
+      "loss": 1.4171125411987304,
+      "mean_token_accuracy": 0.6942351691424846,
+      "num_tokens": 98592.0,
+      "step": 30
+    },
+    {
+      "entropy": 1.33076171875,
+      "epoch": 0.7655502392344498,
+      "grad_norm": 0.7550845146179199,
+      "learning_rate": 0.00017891405093963938,
+      "loss": 1.3193041801452636,
+      "mean_token_accuracy": 0.7104418903589249,
+      "num_tokens": 131278.0,
+      "step": 40
+    },
+    {
+      "entropy": 1.312109375,
+      "epoch": 0.9569377990430622,
+      "grad_norm": 0.6932047009468079,
+      "learning_rate": 0.00016462992378609407,
+      "loss": 1.3077256202697753,
+      "mean_token_accuracy": 0.7093201003968715,
+      "num_tokens": 164256.0,
+      "step": 50
+    },
+    {
+      "entropy": 1.3107052364864864,
+      "epoch": 1.1339712918660287,
+      "grad_norm": 0.7087656855583191,
+      "learning_rate": 0.00014759473930370736,
+      "loss": 1.2949213981628418,
+      "mean_token_accuracy": 0.7117355780021565,
+      "num_tokens": 194746.0,
+      "step": 60
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 159,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 608579226423936.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/L2/checkpoints/checkpoint-60/training_args.bin b/L2/checkpoints/checkpoint-60/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c5ef2615541af048533dacdd04f01f920f86fece
--- /dev/null
+++ b/L2/checkpoints/checkpoint-60/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:063f2af09a09d13dafc33db4ec44d81e322816f9cd5d644aa0cda8a04f4b74b0
+size 5713
diff --git a/L2/checkpoints/checkpoint-70/README.md b/L2/checkpoints/checkpoint-70/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..9b1d0d5c752a5c9f2e3a0e3a9ead3759650a12a9
--- /dev/null
+++ b/L2/checkpoints/checkpoint-70/README.md
@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen3.5-0.8B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3.5-0.8B
+- lora
+- sft
+- transformers
+- trl
+---
+
+# 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 0.18.2.dev0
\ No newline at end of file
diff --git a/L2/checkpoints/checkpoint-70/adapter_config.json b/L2/checkpoints/checkpoint-70/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..466b55ef5352db25f2ac04e8aec438ce0764d848
--- /dev/null
+++ b/L2/checkpoints/checkpoint-70/adapter_config.json
@@ -0,0 +1,45 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3.5-0.8B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.2.dev0@076214c61f690898509b97702b5e9d95c826f000",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "q_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/L2/checkpoints/checkpoint-70/adapter_model.safetensors b/L2/checkpoints/checkpoint-70/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..f7f8dc822c302737444df9c5a41809be3759af34
--- /dev/null
+++ b/L2/checkpoints/checkpoint-70/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb27c227918d8e719a562447ba957ad15910cb24482fc848257c1e303553864d
+size 4331744
diff --git a/L2/checkpoints/checkpoint-70/chat_template.jinja b/L2/checkpoints/checkpoint-70/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..0ef09f214eaa6d9bca297988afc1454b5827b2c7
--- /dev/null
+++ b/L2/checkpoints/checkpoint-70/chat_template.jinja
@@ -0,0 +1,154 @@
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- macro render_content(content, do_vision_count, is_system_content=false) %}
+    {%- if content is string %}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping %}
+        {%- for item in content %}
+            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain images.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Picture ' ~ image_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
+            {%- elif 'video' in item or item.type == 'video' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain videos.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Video ' ~ video_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
+            {%- elif 'text' in item %}
+                {{- item.text }}
+            {%- else %}
+                {{- raise_exception('Unexpected item type in content.') }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif content is none or content is undefined %}
+        {{- '' }}
+    {%- else %}
+        {{- raise_exception('Unexpected content type.') }}
+    {%- endif %}
+{%- endmacro %}
+{%- if not messages %}
+    {{- raise_exception('No messages provided.') }}
+{%- endif %}
+{%- if tools and tools is iterable and tools is not mapping %}
+    {{- '<|im_start|>system\n' }}
+    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>" }}
+    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {%- if content %}
+            {{- '\n\n' + content }}
+        {%- endif %}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {{- '<|im_start|>system\n' + 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" %}
+        {%- set content = render_content(message.content, false)|trim %}
+        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
+            {%- set ns.multi_step_tool = false %}
+            {%- set ns.last_query_index = index %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if ns.multi_step_tool %}
+    {{- raise_exception('No user query found in messages.') }}
+{%- endif %}
+{%- for message in messages %}
+    {%- set content = render_content(message.content, true)|trim %}
+    {%- if message.role == "system" %}
+        {%- if not loop.first %}
+            {{- raise_exception('System message must be at the beginning.') }}
+        {%- endif %}
+    {%- elif message.role == "user" %}
+        {{- '<|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 %}
+        {%- set reasoning_content = reasoning_content|trim %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if tool_call.function is defined %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {%- if loop.first %}
+                    {%- if content|trim %}
+                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- else %}
+                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- endif %}
+                {%- else %}
+                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                {%- endif %}
+                {%- if tool_call.arguments is defined %}
+                    {%- for args_name, args_value in tool_call.arguments|items %}
+                        {{- '<parameter=' + args_name + '>\n' }}
+                        {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
+                        {{- args_value }}
+                        {{- '\n</parameter>\n' }}
+                    {%- endfor %}
+                {%- endif %}
+                {{- '</function>\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- else %}
+        {{- raise_exception('Unexpected message role.') }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is true %}
+        {{- '<think>\n' }}
+    {%- else %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}
\ No newline at end of file
diff --git a/L2/checkpoints/checkpoint-70/optimizer.pt b/L2/checkpoints/checkpoint-70/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..3517dac24bea7a55e8d7817df26472976500aa3e
--- /dev/null
+++ b/L2/checkpoints/checkpoint-70/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75ac7143f946223cd189277cbb625bb33e85ee9b5f89ff65f1b9d21a1bbf206b
+size 8690571
diff --git a/L2/checkpoints/checkpoint-70/rng_state.pth b/L2/checkpoints/checkpoint-70/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..38c6d5df0a659b81300f358fefb31a6f4aa51ddc
--- /dev/null
+++ b/L2/checkpoints/checkpoint-70/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3a77d4a8b98ce027a4d6a3b9fb5d7c904e27ec1efd5c0468c24fa26bb738316
+size 14455
diff --git a/L2/checkpoints/checkpoint-70/scheduler.pt b/L2/checkpoints/checkpoint-70/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..f858bbf27b38abd1e565ff130e1a53dec875216b
--- /dev/null
+++ b/L2/checkpoints/checkpoint-70/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a6fd9f3206f85fc00865417aaeb161c58ccaf5e621cc80ea7f1ca566f53f390
+size 1465
diff --git a/L2/checkpoints/checkpoint-70/tokenizer.json b/L2/checkpoints/checkpoint-70/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..67741b04f23bfdb46501f748ce27865ec82eccfb
--- /dev/null
+++ b/L2/checkpoints/checkpoint-70/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
+size 19989343
diff --git a/L2/checkpoints/checkpoint-70/tokenizer_config.json b/L2/checkpoints/checkpoint-70/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..0871602fcb7d15fcb2979685b1c7b609eef01a6f
--- /dev/null
+++ b/L2/checkpoints/checkpoint-70/tokenizer_config.json
@@ -0,0 +1,32 @@
+{
+  "add_prefix_space": false,
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "image_token": "<|image_pad|>",
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 512,
+  "model_specific_special_tokens": {
+    "audio_bos_token": "<|audio_start|>",
+    "audio_eos_token": "<|audio_end|>",
+    "audio_token": "<|audio_pad|>",
+    "image_token": "<|image_pad|>",
+    "video_token": "<|video_pad|>",
+    "vision_bos_token": "<|vision_start|>",
+    "vision_eos_token": "<|vision_end|>"
+  },
+  "pad_token": "<|endoftext|>",
+  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+  "split_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}
diff --git a/L2/checkpoints/checkpoint-70/trainer_state.json b/L2/checkpoints/checkpoint-70/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..5b5946fa5b84ca32cfd80229de2b5f0c2602f4f3
--- /dev/null
+++ b/L2/checkpoints/checkpoint-70/trainer_state.json
@@ -0,0 +1,104 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.325358851674641,
+  "eval_steps": 500,
+  "global_step": 70,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 2.35390625,
+      "epoch": 0.19138755980861244,
+      "grad_norm": 1.577696681022644,
+      "learning_rate": 0.0001999145758387301,
+      "loss": 2.517007064819336,
+      "mean_token_accuracy": 0.4835851963609457,
+      "num_tokens": 32923.0,
+      "step": 10
+    },
+    {
+      "entropy": 1.953515625,
+      "epoch": 0.3827751196172249,
+      "grad_norm": 1.822049856185913,
+      "learning_rate": 0.00019694002659393305,
+      "loss": 1.814153289794922,
+      "mean_token_accuracy": 0.6044577240943909,
+      "num_tokens": 65628.0,
+      "step": 20
+    },
+    {
+      "entropy": 1.36533203125,
+      "epoch": 0.5741626794258373,
+      "grad_norm": 0.8370082974433899,
+      "learning_rate": 0.0001898390981891979,
+      "loss": 1.4171125411987304,
+      "mean_token_accuracy": 0.6942351691424846,
+      "num_tokens": 98592.0,
+      "step": 30
+    },
+    {
+      "entropy": 1.33076171875,
+      "epoch": 0.7655502392344498,
+      "grad_norm": 0.7550845146179199,
+      "learning_rate": 0.00017891405093963938,
+      "loss": 1.3193041801452636,
+      "mean_token_accuracy": 0.7104418903589249,
+      "num_tokens": 131278.0,
+      "step": 40
+    },
+    {
+      "entropy": 1.312109375,
+      "epoch": 0.9569377990430622,
+      "grad_norm": 0.6932047009468079,
+      "learning_rate": 0.00016462992378609407,
+      "loss": 1.3077256202697753,
+      "mean_token_accuracy": 0.7093201003968715,
+      "num_tokens": 164256.0,
+      "step": 50
+    },
+    {
+      "entropy": 1.3107052364864864,
+      "epoch": 1.1339712918660287,
+      "grad_norm": 0.7087656855583191,
+      "learning_rate": 0.00014759473930370736,
+      "loss": 1.2949213981628418,
+      "mean_token_accuracy": 0.7117355780021565,
+      "num_tokens": 194746.0,
+      "step": 60
+    },
+    {
+      "entropy": 1.26064453125,
+      "epoch": 1.325358851674641,
+      "grad_norm": 0.8213269710540771,
+      "learning_rate": 0.00012853362242491053,
+      "loss": 1.244191551208496,
+      "mean_token_accuracy": 0.7226051487028599,
+      "num_tokens": 227482.0,
+      "step": 70
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 159,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 710882189003904.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/L2/checkpoints/checkpoint-70/training_args.bin b/L2/checkpoints/checkpoint-70/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c5ef2615541af048533dacdd04f01f920f86fece
--- /dev/null
+++ b/L2/checkpoints/checkpoint-70/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:063f2af09a09d13dafc33db4ec44d81e322816f9cd5d644aa0cda8a04f4b74b0
+size 5713
diff --git a/L2/checkpoints/checkpoint-80/README.md b/L2/checkpoints/checkpoint-80/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..9b1d0d5c752a5c9f2e3a0e3a9ead3759650a12a9
--- /dev/null
+++ b/L2/checkpoints/checkpoint-80/README.md
@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen3.5-0.8B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3.5-0.8B
+- lora
+- sft
+- transformers
+- trl
+---
+
+# 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 0.18.2.dev0
\ No newline at end of file
diff --git a/L2/checkpoints/checkpoint-80/adapter_config.json b/L2/checkpoints/checkpoint-80/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..466b55ef5352db25f2ac04e8aec438ce0764d848
--- /dev/null
+++ b/L2/checkpoints/checkpoint-80/adapter_config.json
@@ -0,0 +1,45 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3.5-0.8B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.2.dev0@076214c61f690898509b97702b5e9d95c826f000",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "q_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/L2/checkpoints/checkpoint-80/adapter_model.safetensors b/L2/checkpoints/checkpoint-80/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..98ac314a9b9bcd9d8736083a2b3a91f884485d0a
--- /dev/null
+++ b/L2/checkpoints/checkpoint-80/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd8bf07c6c55dcaa6fc2601e5a5dd1c5ed6ed160636c16dfb4df38b9e8f03331
+size 4331744
diff --git a/L2/checkpoints/checkpoint-80/chat_template.jinja b/L2/checkpoints/checkpoint-80/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..0ef09f214eaa6d9bca297988afc1454b5827b2c7
--- /dev/null
+++ b/L2/checkpoints/checkpoint-80/chat_template.jinja
@@ -0,0 +1,154 @@
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- macro render_content(content, do_vision_count, is_system_content=false) %}
+    {%- if content is string %}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping %}
+        {%- for item in content %}
+            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain images.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Picture ' ~ image_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
+            {%- elif 'video' in item or item.type == 'video' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain videos.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Video ' ~ video_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
+            {%- elif 'text' in item %}
+                {{- item.text }}
+            {%- else %}
+                {{- raise_exception('Unexpected item type in content.') }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif content is none or content is undefined %}
+        {{- '' }}
+    {%- else %}
+        {{- raise_exception('Unexpected content type.') }}
+    {%- endif %}
+{%- endmacro %}
+{%- if not messages %}
+    {{- raise_exception('No messages provided.') }}
+{%- endif %}
+{%- if tools and tools is iterable and tools is not mapping %}
+    {{- '<|im_start|>system\n' }}
+    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>" }}
+    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {%- if content %}
+            {{- '\n\n' + content }}
+        {%- endif %}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {{- '<|im_start|>system\n' + 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" %}
+        {%- set content = render_content(message.content, false)|trim %}
+        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
+            {%- set ns.multi_step_tool = false %}
+            {%- set ns.last_query_index = index %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if ns.multi_step_tool %}
+    {{- raise_exception('No user query found in messages.') }}
+{%- endif %}
+{%- for message in messages %}
+    {%- set content = render_content(message.content, true)|trim %}
+    {%- if message.role == "system" %}
+        {%- if not loop.first %}
+            {{- raise_exception('System message must be at the beginning.') }}
+        {%- endif %}
+    {%- elif message.role == "user" %}
+        {{- '<|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 %}
+        {%- set reasoning_content = reasoning_content|trim %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if tool_call.function is defined %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {%- if loop.first %}
+                    {%- if content|trim %}
+                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- else %}
+                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- endif %}
+                {%- else %}
+                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                {%- endif %}
+                {%- if tool_call.arguments is defined %}
+                    {%- for args_name, args_value in tool_call.arguments|items %}
+                        {{- '<parameter=' + args_name + '>\n' }}
+                        {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
+                        {{- args_value }}
+                        {{- '\n</parameter>\n' }}
+                    {%- endfor %}
+                {%- endif %}
+                {{- '</function>\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- else %}
+        {{- raise_exception('Unexpected message role.') }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is true %}
+        {{- '<think>\n' }}
+    {%- else %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}
\ No newline at end of file
diff --git a/L2/checkpoints/checkpoint-80/optimizer.pt b/L2/checkpoints/checkpoint-80/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..65c635db3954e8c740868622f5212f3642c0bb63
--- /dev/null
+++ b/L2/checkpoints/checkpoint-80/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fa9d63c17f384ad6eeb4cecbb7021ff2293ec667dfe74f4475bd425abe36732
+size 8690571
diff --git a/L2/checkpoints/checkpoint-80/rng_state.pth b/L2/checkpoints/checkpoint-80/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..38c6d5df0a659b81300f358fefb31a6f4aa51ddc
--- /dev/null
+++ b/L2/checkpoints/checkpoint-80/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3a77d4a8b98ce027a4d6a3b9fb5d7c904e27ec1efd5c0468c24fa26bb738316
+size 14455
diff --git a/L2/checkpoints/checkpoint-80/scheduler.pt b/L2/checkpoints/checkpoint-80/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..0b246dec42e48802d2bbbafbff44c90ed32e5ce1
--- /dev/null
+++ b/L2/checkpoints/checkpoint-80/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a56e71ec595f148f31173cc2e0fe75a40a9eb1e044fd9c879295d92c4f269c83
+size 1465
diff --git a/L2/checkpoints/checkpoint-80/tokenizer.json b/L2/checkpoints/checkpoint-80/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..67741b04f23bfdb46501f748ce27865ec82eccfb
--- /dev/null
+++ b/L2/checkpoints/checkpoint-80/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
+size 19989343
diff --git a/L2/checkpoints/checkpoint-80/tokenizer_config.json b/L2/checkpoints/checkpoint-80/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..0871602fcb7d15fcb2979685b1c7b609eef01a6f
--- /dev/null
+++ b/L2/checkpoints/checkpoint-80/tokenizer_config.json
@@ -0,0 +1,32 @@
+{
+  "add_prefix_space": false,
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "image_token": "<|image_pad|>",
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 512,
+  "model_specific_special_tokens": {
+    "audio_bos_token": "<|audio_start|>",
+    "audio_eos_token": "<|audio_end|>",
+    "audio_token": "<|audio_pad|>",
+    "image_token": "<|image_pad|>",
+    "video_token": "<|video_pad|>",
+    "vision_bos_token": "<|vision_start|>",
+    "vision_eos_token": "<|vision_end|>"
+  },
+  "pad_token": "<|endoftext|>",
+  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+  "split_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}
diff --git a/L2/checkpoints/checkpoint-80/trainer_state.json b/L2/checkpoints/checkpoint-80/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..eea6c7eff29ebedd8500f25a2363df17b21efec9
--- /dev/null
+++ b/L2/checkpoints/checkpoint-80/trainer_state.json
@@ -0,0 +1,114 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.5167464114832536,
+  "eval_steps": 500,
+  "global_step": 80,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 2.35390625,
+      "epoch": 0.19138755980861244,
+      "grad_norm": 1.577696681022644,
+      "learning_rate": 0.0001999145758387301,
+      "loss": 2.517007064819336,
+      "mean_token_accuracy": 0.4835851963609457,
+      "num_tokens": 32923.0,
+      "step": 10
+    },
+    {
+      "entropy": 1.953515625,
+      "epoch": 0.3827751196172249,
+      "grad_norm": 1.822049856185913,
+      "learning_rate": 0.00019694002659393305,
+      "loss": 1.814153289794922,
+      "mean_token_accuracy": 0.6044577240943909,
+      "num_tokens": 65628.0,
+      "step": 20
+    },
+    {
+      "entropy": 1.36533203125,
+      "epoch": 0.5741626794258373,
+      "grad_norm": 0.8370082974433899,
+      "learning_rate": 0.0001898390981891979,
+      "loss": 1.4171125411987304,
+      "mean_token_accuracy": 0.6942351691424846,
+      "num_tokens": 98592.0,
+      "step": 30
+    },
+    {
+      "entropy": 1.33076171875,
+      "epoch": 0.7655502392344498,
+      "grad_norm": 0.7550845146179199,
+      "learning_rate": 0.00017891405093963938,
+      "loss": 1.3193041801452636,
+      "mean_token_accuracy": 0.7104418903589249,
+      "num_tokens": 131278.0,
+      "step": 40
+    },
+    {
+      "entropy": 1.312109375,
+      "epoch": 0.9569377990430622,
+      "grad_norm": 0.6932047009468079,
+      "learning_rate": 0.00016462992378609407,
+      "loss": 1.3077256202697753,
+      "mean_token_accuracy": 0.7093201003968715,
+      "num_tokens": 164256.0,
+      "step": 50
+    },
+    {
+      "entropy": 1.3107052364864864,
+      "epoch": 1.1339712918660287,
+      "grad_norm": 0.7087656855583191,
+      "learning_rate": 0.00014759473930370736,
+      "loss": 1.2949213981628418,
+      "mean_token_accuracy": 0.7117355780021565,
+      "num_tokens": 194746.0,
+      "step": 60
+    },
+    {
+      "entropy": 1.26064453125,
+      "epoch": 1.325358851674641,
+      "grad_norm": 0.8213269710540771,
+      "learning_rate": 0.00012853362242491053,
+      "loss": 1.244191551208496,
+      "mean_token_accuracy": 0.7226051487028599,
+      "num_tokens": 227482.0,
+      "step": 70
+    },
+    {
+      "entropy": 1.2599609375,
+      "epoch": 1.5167464114832536,
+      "grad_norm": 0.7758288383483887,
+      "learning_rate": 0.00010825793454723325,
+      "loss": 1.2582054138183594,
+      "mean_token_accuracy": 0.7165695309638977,
+      "num_tokens": 260195.0,
+      "step": 80
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 159,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 813149209566336.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/L2/checkpoints/checkpoint-80/training_args.bin b/L2/checkpoints/checkpoint-80/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c5ef2615541af048533dacdd04f01f920f86fece
--- /dev/null
+++ b/L2/checkpoints/checkpoint-80/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:063f2af09a09d13dafc33db4ec44d81e322816f9cd5d644aa0cda8a04f4b74b0
+size 5713
diff --git a/L2/checkpoints/checkpoint-90/README.md b/L2/checkpoints/checkpoint-90/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..9b1d0d5c752a5c9f2e3a0e3a9ead3759650a12a9
--- /dev/null
+++ b/L2/checkpoints/checkpoint-90/README.md
@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen3.5-0.8B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3.5-0.8B
+- lora
+- sft
+- transformers
+- trl
+---
+
+# 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 0.18.2.dev0
\ No newline at end of file
diff --git a/L2/checkpoints/checkpoint-90/adapter_config.json b/L2/checkpoints/checkpoint-90/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..466b55ef5352db25f2ac04e8aec438ce0764d848
--- /dev/null
+++ b/L2/checkpoints/checkpoint-90/adapter_config.json
@@ -0,0 +1,45 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3.5-0.8B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.2.dev0@076214c61f690898509b97702b5e9d95c826f000",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "q_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/L2/checkpoints/checkpoint-90/adapter_model.safetensors b/L2/checkpoints/checkpoint-90/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..ae3c5a6c1f0398cb7dabbd679523d3b3ee9a09cc
--- /dev/null
+++ b/L2/checkpoints/checkpoint-90/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a992bf1626725f3a3f7c7a0a125474c68ffa26748bd00ba9ee60b19781cfe88
+size 4331744
diff --git a/L2/checkpoints/checkpoint-90/chat_template.jinja b/L2/checkpoints/checkpoint-90/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..0ef09f214eaa6d9bca297988afc1454b5827b2c7
--- /dev/null
+++ b/L2/checkpoints/checkpoint-90/chat_template.jinja
@@ -0,0 +1,154 @@
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- macro render_content(content, do_vision_count, is_system_content=false) %}
+    {%- if content is string %}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping %}
+        {%- for item in content %}
+            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain images.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Picture ' ~ image_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
+            {%- elif 'video' in item or item.type == 'video' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain videos.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Video ' ~ video_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
+            {%- elif 'text' in item %}
+                {{- item.text }}
+            {%- else %}
+                {{- raise_exception('Unexpected item type in content.') }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif content is none or content is undefined %}
+        {{- '' }}
+    {%- else %}
+        {{- raise_exception('Unexpected content type.') }}
+    {%- endif %}
+{%- endmacro %}
+{%- if not messages %}
+    {{- raise_exception('No messages provided.') }}
+{%- endif %}
+{%- if tools and tools is iterable and tools is not mapping %}
+    {{- '<|im_start|>system\n' }}
+    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>" }}
+    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {%- if content %}
+            {{- '\n\n' + content }}
+        {%- endif %}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {{- '<|im_start|>system\n' + 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" %}
+        {%- set content = render_content(message.content, false)|trim %}
+        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
+            {%- set ns.multi_step_tool = false %}
+            {%- set ns.last_query_index = index %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if ns.multi_step_tool %}
+    {{- raise_exception('No user query found in messages.') }}
+{%- endif %}
+{%- for message in messages %}
+    {%- set content = render_content(message.content, true)|trim %}
+    {%- if message.role == "system" %}
+        {%- if not loop.first %}
+            {{- raise_exception('System message must be at the beginning.') }}
+        {%- endif %}
+    {%- elif message.role == "user" %}
+        {{- '<|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 %}
+        {%- set reasoning_content = reasoning_content|trim %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if tool_call.function is defined %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {%- if loop.first %}
+                    {%- if content|trim %}
+                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- else %}
+                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- endif %}
+                {%- else %}
+                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                {%- endif %}
+                {%- if tool_call.arguments is defined %}
+                    {%- for args_name, args_value in tool_call.arguments|items %}
+                        {{- '<parameter=' + args_name + '>\n' }}
+                        {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
+                        {{- args_value }}
+                        {{- '\n</parameter>\n' }}
+                    {%- endfor %}
+                {%- endif %}
+                {{- '</function>\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- else %}
+        {{- raise_exception('Unexpected message role.') }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is true %}
+        {{- '<think>\n' }}
+    {%- else %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}
\ No newline at end of file
diff --git a/L2/checkpoints/checkpoint-90/optimizer.pt b/L2/checkpoints/checkpoint-90/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..fd0b4d2bc213c38b0945c20ccda58e6e70dcb12b
--- /dev/null
+++ b/L2/checkpoints/checkpoint-90/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02d098d08524c3767d5453d6d836e8b5c8868fb24be8d8fb32dbeb12e7c1c8f4
+size 8690571
diff --git a/L2/checkpoints/checkpoint-90/rng_state.pth b/L2/checkpoints/checkpoint-90/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..38c6d5df0a659b81300f358fefb31a6f4aa51ddc
--- /dev/null
+++ b/L2/checkpoints/checkpoint-90/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3a77d4a8b98ce027a4d6a3b9fb5d7c904e27ec1efd5c0468c24fa26bb738316
+size 14455
diff --git a/L2/checkpoints/checkpoint-90/scheduler.pt b/L2/checkpoints/checkpoint-90/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..9996ef92f3da1dcc1df8c7e09ce0aac1f761217a
--- /dev/null
+++ b/L2/checkpoints/checkpoint-90/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:111d012cb61279f251d1c7420ef60a994ecb49ac992cc1aad87f183316311861
+size 1465
diff --git a/L2/checkpoints/checkpoint-90/tokenizer.json b/L2/checkpoints/checkpoint-90/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..67741b04f23bfdb46501f748ce27865ec82eccfb
--- /dev/null
+++ b/L2/checkpoints/checkpoint-90/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
+size 19989343
diff --git a/L2/checkpoints/checkpoint-90/tokenizer_config.json b/L2/checkpoints/checkpoint-90/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..0871602fcb7d15fcb2979685b1c7b609eef01a6f
--- /dev/null
+++ b/L2/checkpoints/checkpoint-90/tokenizer_config.json
@@ -0,0 +1,32 @@
+{
+  "add_prefix_space": false,
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "image_token": "<|image_pad|>",
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 512,
+  "model_specific_special_tokens": {
+    "audio_bos_token": "<|audio_start|>",
+    "audio_eos_token": "<|audio_end|>",
+    "audio_token": "<|audio_pad|>",
+    "image_token": "<|image_pad|>",
+    "video_token": "<|video_pad|>",
+    "vision_bos_token": "<|vision_start|>",
+    "vision_eos_token": "<|vision_end|>"
+  },
+  "pad_token": "<|endoftext|>",
+  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+  "split_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}
diff --git a/L2/checkpoints/checkpoint-90/trainer_state.json b/L2/checkpoints/checkpoint-90/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..e8948a9a71572599f47a200f62f307fa565166ec
--- /dev/null
+++ b/L2/checkpoints/checkpoint-90/trainer_state.json
@@ -0,0 +1,124 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.7081339712918662,
+  "eval_steps": 500,
+  "global_step": 90,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 2.35390625,
+      "epoch": 0.19138755980861244,
+      "grad_norm": 1.577696681022644,
+      "learning_rate": 0.0001999145758387301,
+      "loss": 2.517007064819336,
+      "mean_token_accuracy": 0.4835851963609457,
+      "num_tokens": 32923.0,
+      "step": 10
+    },
+    {
+      "entropy": 1.953515625,
+      "epoch": 0.3827751196172249,
+      "grad_norm": 1.822049856185913,
+      "learning_rate": 0.00019694002659393305,
+      "loss": 1.814153289794922,
+      "mean_token_accuracy": 0.6044577240943909,
+      "num_tokens": 65628.0,
+      "step": 20
+    },
+    {
+      "entropy": 1.36533203125,
+      "epoch": 0.5741626794258373,
+      "grad_norm": 0.8370082974433899,
+      "learning_rate": 0.0001898390981891979,
+      "loss": 1.4171125411987304,
+      "mean_token_accuracy": 0.6942351691424846,
+      "num_tokens": 98592.0,
+      "step": 30
+    },
+    {
+      "entropy": 1.33076171875,
+      "epoch": 0.7655502392344498,
+      "grad_norm": 0.7550845146179199,
+      "learning_rate": 0.00017891405093963938,
+      "loss": 1.3193041801452636,
+      "mean_token_accuracy": 0.7104418903589249,
+      "num_tokens": 131278.0,
+      "step": 40
+    },
+    {
+      "entropy": 1.312109375,
+      "epoch": 0.9569377990430622,
+      "grad_norm": 0.6932047009468079,
+      "learning_rate": 0.00016462992378609407,
+      "loss": 1.3077256202697753,
+      "mean_token_accuracy": 0.7093201003968715,
+      "num_tokens": 164256.0,
+      "step": 50
+    },
+    {
+      "entropy": 1.3107052364864864,
+      "epoch": 1.1339712918660287,
+      "grad_norm": 0.7087656855583191,
+      "learning_rate": 0.00014759473930370736,
+      "loss": 1.2949213981628418,
+      "mean_token_accuracy": 0.7117355780021565,
+      "num_tokens": 194746.0,
+      "step": 60
+    },
+    {
+      "entropy": 1.26064453125,
+      "epoch": 1.325358851674641,
+      "grad_norm": 0.8213269710540771,
+      "learning_rate": 0.00012853362242491053,
+      "loss": 1.244191551208496,
+      "mean_token_accuracy": 0.7226051487028599,
+      "num_tokens": 227482.0,
+      "step": 70
+    },
+    {
+      "entropy": 1.2599609375,
+      "epoch": 1.5167464114832536,
+      "grad_norm": 0.7758288383483887,
+      "learning_rate": 0.00010825793454723325,
+      "loss": 1.2582054138183594,
+      "mean_token_accuracy": 0.7165695309638977,
+      "num_tokens": 260195.0,
+      "step": 80
+    },
+    {
+      "entropy": 1.25322265625,
+      "epoch": 1.7081339712918662,
+      "grad_norm": 0.7961016893386841,
+      "learning_rate": 8.763073687306524e-05,
+      "loss": 1.2671056747436524,
+      "mean_token_accuracy": 0.7158558055758476,
+      "num_tokens": 292968.0,
+      "step": 90
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 159,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 915542027190144.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/L2/checkpoints/checkpoint-90/training_args.bin b/L2/checkpoints/checkpoint-90/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c5ef2615541af048533dacdd04f01f920f86fece
--- /dev/null
+++ b/L2/checkpoints/checkpoint-90/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:063f2af09a09d13dafc33db4ec44d81e322816f9cd5d644aa0cda8a04f4b74b0
+size 5713