Update adapter weights - SFT v2

README.md

@@ -1,9 +1,9 @@
 ---
-base_model: Qwen/Qwen3.5-2B
+base_model: unsloth/Qwen3.5-2B
 library_name: peft
 model_name: lumen-qwen-3.5
 tags:
-- base_model:adapter:Qwen/Qwen3.5-2B
+- base_model:adapter:unsloth/Qwen3.5-2B
 - lora
 - sft
 - transformers
@@ -15,7 +15,7 @@ pipeline_tag: text-generation
 
 # Model Card for lumen-qwen-3.5
 
-This model is a fine-tuned version of [Qwen/Qwen3.5-2B](https://huggingface.co/Qwen/Qwen3.5-2B).
+This model is a fine-tuned version of [unsloth/Qwen3.5-2B](https://huggingface.co/unsloth/Qwen3.5-2B).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start
@@ -41,7 +41,7 @@ This model was trained with SFT.
 - PEFT 0.19.1
 - TRL: 0.24.0
 - Transformers: 5.5.0
-- Pytorch: 2.11.0+cu128
+- Pytorch: 2.10.0
 - Datasets: 4.3.0
 - Tokenizers: 0.22.2
 

adapter_config.json

@@ -7,7 +7,7 @@
     "parent_library": "transformers.models.qwen3_5.modeling_qwen3_5",
     "unsloth_fixed": true
   },
-  "base_model_name_or_path": "Qwen/Qwen3.5-2B",
+  "base_model_name_or_path": "unsloth/Qwen3.5-2B",
   "bias": "none",
   "corda_config": null,
   "ensure_weight_tying": false,
@@ -20,7 +20,7 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
+  "lora_alpha": 16,
   "lora_bias": false,
   "lora_dropout": 0,
   "lora_ga_config": null,
@@ -30,16 +30,11 @@
   "peft_type": "LORA",
   "peft_version": "0.19.1",
   "qalora_group_size": 16,
-  "r": 16,
+  "r": 8,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
     "v_proj",
-    "o_proj",
-    "gate_proj",
-    "down_proj",
-    "up_proj",
     "q_proj"
   ],
   "target_parameters": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65cccd5b3e43c080de88fe23664f18d9627fd0f933540d4852ebb2eb139f91bf
-size 43675104
+oid sha256:4a20f68744eb2b7742e0e843c29142f4b731e596017364467e7bd62fc6ac36cb
+size 1674688

chat_template.jinja

@@ -42,6 +42,19 @@
 {%- if not messages %}
     {{- raise_exception('No messages provided.') }}
 {%- endif %}
+{%- set num_sys = 0 %}
+{%- set merged_system = '' %}
+{%- if messages[0].role == 'system' or messages[0].role == 'developer' %}
+    {%- set first = render_content(messages[0].content, false, true)|trim %}
+    {%- if messages|length > 1 and (messages[1].role == 'system' or messages[1].role == 'developer') %}
+        {%- set second = render_content(messages[1].content, false, true)|trim %}
+        {%- set merged_system = first + '\n' + second %}
+        {%- set num_sys = 2 %}
+    {%- else %}
+        {%- set merged_system = first %}
+        {%- set num_sys = 1 %}
+    {%- endif %}
+{%- 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>" }}
@@ -51,17 +64,13 @@
     {%- 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 %}
+    {%- if merged_system %}
+        {{- '\n\n' + merged_system }}
     {%- 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' }}
+    {%- if merged_system %}
+        {{- '<|im_start|>system\n' + merged_system + '<|im_end|>\n' }}
     {%- endif %}
 {%- endif %}
 {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
@@ -75,16 +84,10 @@
         {%- endif %}
     {%- endif %}
 {%- endfor %}
-{%- if ns.multi_step_tool %}
-    {{- raise_exception('No user query found in messages.') }}
-{%- endif %}
 {%- for message in messages %}
+    {%- if loop.index0 >= num_sys and message.role != "system" and message.role != "developer" %}
     {%- 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" %}
+    {%- if message.role == "user" %}
         {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
     {%- elif message.role == "assistant" %}
         {%- set reasoning_content = '' %}
@@ -116,8 +119,9 @@
                 {%- 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 %}
+                {%- if tool_call.arguments is mapping %}
+                    {%- for args_name in tool_call.arguments %}
+                        {%- set args_value = tool_call.arguments[args_name] %}
                         {{- '<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 }}
@@ -140,8 +144,7 @@
         {%- elif loop.last %}
             {{- '<|im_end|>\n' }}
         {%- endif %}
-    {%- else %}
-        {{- raise_exception('Unexpected message role.') }}
+    {%- endif %}
     {%- endif %}
 {%- endfor %}
 {%- if add_generation_prompt %}
@@ -151,4 +154,5 @@
     {%- else %}
         {{- '<think>\n\n</think>\n\n' }}
     {%- endif %}
-{%- endif %}
+{%- endif %}
+{#- Unsloth fixes - developer role, tool calling #}

checkpoint-300/README.md

@@ -0,0 +1,210 @@
+---
+base_model: unsloth/Qwen3.5-2B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/Qwen3.5-2B
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.19.1

checkpoint-300/adapter_config.json

@@ -0,0 +1,47 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen3_5ForConditionalGeneration",
+    "parent_library": "transformers.models.qwen3_5.modeling_qwen3_5",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/Qwen3.5-2B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-300/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a20f68744eb2b7742e0e843c29142f4b731e596017364467e7bd62fc6ac36cb
+size 1674688

checkpoint-300/chat_template.jinja

@@ -0,0 +1,158 @@
+{%- 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 %}
+{%- set num_sys = 0 %}
+{%- set merged_system = '' %}
+{%- if messages[0].role == 'system' or messages[0].role == 'developer' %}
+    {%- set first = render_content(messages[0].content, false, true)|trim %}
+    {%- if messages|length > 1 and (messages[1].role == 'system' or messages[1].role == 'developer') %}
+        {%- set second = render_content(messages[1].content, false, true)|trim %}
+        {%- set merged_system = first + '\n' + second %}
+        {%- set num_sys = 2 %}
+    {%- else %}
+        {%- set merged_system = first %}
+        {%- set num_sys = 1 %}
+    {%- endif %}
+{%- 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 merged_system %}
+        {{- '\n\n' + merged_system }}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if merged_system %}
+        {{- '<|im_start|>system\n' + merged_system + '<|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 %}
+{%- for message in messages %}
+    {%- if loop.index0 >= num_sys and message.role != "system" and message.role != "developer" %}
+    {%- set content = render_content(message.content, true)|trim %}
+    {%- if 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 mapping %}
+                    {%- for args_name in tool_call.arguments %}
+                        {%- set args_value = tool_call.arguments[args_name] %}
+                        {{- '<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 %}
+    {%- endif %}
+    {%- 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 %}
+{#- Unsloth fixes - developer role, tool calling #}

checkpoint-300/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2ec3162744f56158d1679b75f5cb231417dcb2fd309698147fbbd1d16ab90ac
+size 880205

checkpoint-300/processor_config.json

@@ -0,0 +1,63 @@
+{
+  "image_processor": {
+    "data_format": "channels_first",
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_processor_type": "Qwen2VLImageProcessor",
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "merge_size": 2,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "size": {
+      "longest_edge": 16777216,
+      "shortest_edge": 65536
+    },
+    "temporal_patch_size": 2
+  },
+  "processor_class": "Qwen3VLProcessor",
+  "video_processor": {
+    "data_format": "channels_first",
+    "default_to_square": true,
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "do_sample_frames": true,
+    "fps": 2,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "max_frames": 768,
+    "merge_size": 2,
+    "min_frames": 4,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_metadata": false,
+    "size": {
+      "longest_edge": 25165824,
+      "shortest_edge": 4096
+    },
+    "temporal_patch_size": 2,
+    "video_processor_type": "Qwen3VLVideoProcessor"
+  }
+}

checkpoint-300/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d6d8fafcd1ee268414be5acf0366296af5b03d60871978712eac1979cb42d65
+size 14645

checkpoint-300/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d15d3d1b8bb19162d239033d431d77f4eba28beb04ec2c0ba04b41fbc223a133
+size 1465

checkpoint-300/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
+size 19989343

checkpoint-300/tokenizer_config.json

@@ -0,0 +1,299 @@
+{
+  "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,
+  "model_max_length": 262144,
+  "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": "<|vision_pad|>",
+  "padding_side": "right",
+  "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+",
+  "processor_class": "Qwen3VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>",
+  "added_tokens_decoder": {
+    "248044": {
+      "content": "<|endoftext|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248045": {
+      "content": "<|im_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248046": {
+      "content": "<|im_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248047": {
+      "content": "<|object_ref_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248048": {
+      "content": "<|object_ref_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248049": {
+      "content": "<|box_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248050": {
+      "content": "<|box_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248051": {
+      "content": "<|quad_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248052": {
+      "content": "<|quad_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248053": {
+      "content": "<|vision_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248054": {
+      "content": "<|vision_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248055": {
+      "content": "<|vision_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248056": {
+      "content": "<|image_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248057": {
+      "content": "<|video_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248058": {
+      "content": "<tool_call>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248059": {
+      "content": "</tool_call>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248060": {
+      "content": "<|fim_prefix|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248061": {
+      "content": "<|fim_middle|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248062": {
+      "content": "<|fim_suffix|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248063": {
+      "content": "<|fim_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248064": {
+      "content": "<|repo_name|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248065": {
+      "content": "<|file_sep|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248066": {
+      "content": "<tool_response>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248067": {
+      "content": "</tool_response>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248068": {
+      "content": "<think>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248069": {
+      "content": "</think>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248070": {
+      "content": "<|audio_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248071": {
+      "content": "<|audio_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248072": {
+      "content": "<tts_pad>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248073": {
+      "content": "<tts_text_bos>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248074": {
+      "content": "<tts_text_eod>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248075": {
+      "content": "<tts_text_bos_single>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248076": {
+      "content": "<|audio_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  }
+}

checkpoint-300/trainer_state.json

@@ -0,0 +1,244 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.8557536466774716,
+  "eval_steps": 500,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.12965964343598055,
+      "grad_norm": 0.44033142924308777,
+      "learning_rate": 0.00019728813559322035,
+      "loss": 1.588271427154541,
+      "step": 10
+    },
+    {
+      "epoch": 0.2593192868719611,
+      "grad_norm": 1.1466902494430542,
+      "learning_rate": 0.0001905084745762712,
+      "loss": 1.8572025299072266,
+      "step": 20
+    },
+    {
+      "epoch": 0.3889789303079417,
+      "grad_norm": 0.9241822957992554,
+      "learning_rate": 0.00018372881355932204,
+      "loss": 1.4406778335571289,
+      "step": 30
+    },
+    {
+      "epoch": 0.5186385737439222,
+      "grad_norm": 0.7107939124107361,
+      "learning_rate": 0.0001769491525423729,
+      "loss": 1.0937417984008788,
+      "step": 40
+    },
+    {
+      "epoch": 0.6482982171799028,
+      "grad_norm": 0.7085503935813904,
+      "learning_rate": 0.00017016949152542373,
+      "loss": 0.9844695091247558,
+      "step": 50
+    },
+    {
+      "epoch": 0.7779578606158833,
+      "grad_norm": 0.9381449222564697,
+      "learning_rate": 0.00016338983050847458,
+      "loss": 0.6658666133880615,
+      "step": 60
+    },
+    {
+      "epoch": 0.9076175040518638,
+      "grad_norm": 0.9691148996353149,
+      "learning_rate": 0.00015661016949152542,
+      "loss": 0.7807923316955566,
+      "step": 70
+    },
+    {
+      "epoch": 1.0259319286871962,
+      "grad_norm": 1.2804441452026367,
+      "learning_rate": 0.00014983050847457627,
+      "loss": 0.7345180034637451,
+      "step": 80
+    },
+    {
+      "epoch": 1.1555915721231766,
+      "grad_norm": 0.6306379437446594,
+      "learning_rate": 0.00014305084745762714,
+      "loss": 0.5936465263366699,
+      "step": 90
+    },
+    {
+      "epoch": 1.2852512155591573,
+      "grad_norm": 0.8881189823150635,
+      "learning_rate": 0.00013627118644067798,
+      "loss": 0.5103878021240235,
+      "step": 100
+    },
+    {
+      "epoch": 1.4149108589951378,
+      "grad_norm": 1.7029504776000977,
+      "learning_rate": 0.00012949152542372883,
+      "loss": 0.6796833515167237,
+      "step": 110
+    },
+    {
+      "epoch": 1.5445705024311183,
+      "grad_norm": 2.0517845153808594,
+      "learning_rate": 0.00012271186440677967,
+      "loss": 0.520937728881836,
+      "step": 120
+    },
+    {
+      "epoch": 1.674230145867099,
+      "grad_norm": 1.30018949508667,
+      "learning_rate": 0.0001159322033898305,
+      "loss": 0.667867374420166,
+      "step": 130
+    },
+    {
+      "epoch": 1.8038897893030794,
+      "grad_norm": 0.9960445761680603,
+      "learning_rate": 0.00010915254237288135,
+      "loss": 0.48140687942504884,
+      "step": 140
+    },
+    {
+      "epoch": 1.9335494327390599,
+      "grad_norm": 1.7485697269439697,
+      "learning_rate": 0.00010237288135593222,
+      "loss": 0.5179755687713623,
+      "step": 150
+    },
+    {
+      "epoch": 2.0518638573743924,
+      "grad_norm": 1.4105119705200195,
+      "learning_rate": 9.559322033898305e-05,
+      "loss": 0.48134546279907225,
+      "step": 160
+    },
+    {
+      "epoch": 2.1815235008103726,
+      "grad_norm": 1.0243501663208008,
+      "learning_rate": 8.88135593220339e-05,
+      "loss": 0.45008292198181155,
+      "step": 170
+    },
+    {
+      "epoch": 2.3111831442463533,
+      "grad_norm": 1.2724498510360718,
+      "learning_rate": 8.203389830508474e-05,
+      "loss": 0.5789812564849853,
+      "step": 180
+    },
+    {
+      "epoch": 2.440842787682334,
+      "grad_norm": 1.8518635034561157,
+      "learning_rate": 7.52542372881356e-05,
+      "loss": 0.42807679176330565,
+      "step": 190
+    },
+    {
+      "epoch": 2.5705024311183147,
+      "grad_norm": 1.48202645778656,
+      "learning_rate": 6.847457627118645e-05,
+      "loss": 0.5260007858276368,
+      "step": 200
+    },
+    {
+      "epoch": 2.700162074554295,
+      "grad_norm": 2.0189461708068848,
+      "learning_rate": 6.169491525423729e-05,
+      "loss": 0.48281493186950686,
+      "step": 210
+    },
+    {
+      "epoch": 2.8298217179902756,
+      "grad_norm": 1.277570128440857,
+      "learning_rate": 5.4915254237288135e-05,
+      "loss": 0.42935891151428224,
+      "step": 220
+    },
+    {
+      "epoch": 2.9594813614262563,
+      "grad_norm": 2.37007737159729,
+      "learning_rate": 4.813559322033899e-05,
+      "loss": 0.3907858610153198,
+      "step": 230
+    },
+    {
+      "epoch": 3.0777957860615883,
+      "grad_norm": 1.6668658256530762,
+      "learning_rate": 4.135593220338983e-05,
+      "loss": 0.4579921245574951,
+      "step": 240
+    },
+    {
+      "epoch": 3.207455429497569,
+      "grad_norm": 1.3719815015792847,
+      "learning_rate": 3.4576271186440676e-05,
+      "loss": 0.4433708190917969,
+      "step": 250
+    },
+    {
+      "epoch": 3.3371150729335493,
+      "grad_norm": 2.302764415740967,
+      "learning_rate": 2.7796610169491528e-05,
+      "loss": 0.468212366104126,
+      "step": 260
+    },
+    {
+      "epoch": 3.46677471636953,
+      "grad_norm": 1.2898948192596436,
+      "learning_rate": 2.1016949152542373e-05,
+      "loss": 0.35132598876953125,
+      "step": 270
+    },
+    {
+      "epoch": 3.5964343598055106,
+      "grad_norm": 1.1389379501342773,
+      "learning_rate": 1.4237288135593221e-05,
+      "loss": 0.39004855155944823,
+      "step": 280
+    },
+    {
+      "epoch": 3.7260940032414913,
+      "grad_norm": 2.6287143230438232,
+      "learning_rate": 7.4576271186440685e-06,
+      "loss": 0.5523932933807373,
+      "step": 290
+    },
+    {
+      "epoch": 3.8557536466774716,
+      "grad_norm": 1.5404112339019775,
+      "learning_rate": 6.779661016949152e-07,
+      "loss": 0.32611134052276614,
+      "step": 300
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 300,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4605685696732800.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-300/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d43fa09e9fa05277c134e23e025ca7d913bcc82b5f79ed49fb679f22c5f7a9d9
+size 5585

processor_config.json

@@ -1,5 +1,6 @@
 {
   "image_processor": {
+    "data_format": "channels_first",
     "do_convert_rgb": true,
     "do_normalize": true,
     "do_rescale": true,
@@ -27,6 +28,8 @@
   },
   "processor_class": "Qwen3VLProcessor",
   "video_processor": {
+    "data_format": "channels_first",
+    "default_to_square": true,
     "do_convert_rgb": true,
     "do_normalize": true,
     "do_rescale": true,

tokenizer_config.json

@@ -20,7 +20,7 @@
     "vision_bos_token": "<|vision_start|>",
     "vision_eos_token": "<|vision_end|>"
   },
-  "pad_token": "<|endoftext|>",
+  "pad_token": "<|vision_pad|>",
   "padding_side": "right",
   "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+",
   "processor_class": "Qwen3VLProcessor",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e95ab49d4c4c20ea92871052a1663569e09c94e0bf5c7d7fdd2227537c818325
+oid sha256:d43fa09e9fa05277c134e23e025ca7d913bcc82b5f79ed49fb679f22c5f7a9d9
 size 5585