Publish trained GarudaCoder Qwen3.8 27B LoRA

README.md

@@ -1,4 +1,5 @@
 ---
+base_model_revision: 8aa5f05d26b7205477066e1449e0af13f762a299
 license: apache-2.0
 base_model: unsloth/Qwen3.8-27B-unsloth-bnb-4bit
 language:

adapter_config.json

@@ -7,7 +7,7 @@
     "parent_library": "transformers.models.qwen3_5.modeling_qwen3_5",
     "unsloth_fixed": true
   },
-  "base_model_name_or_path": "unsloth/Qwen3.8-27B-unsloth-bnb-4bit",
+  "base_model_name_or_path": "/kaggle/temp/qwen38-27b-4bit",
   "bias": "none",
   "corda_config": null,
   "ensure_weight_tying": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a686e980d948ddfdf4e57e4bf46cd7f8b6d60769a1f029f7e3f86e1ce7d9716
+oid sha256:d0d3c0370472ecac76491b12c0d2115f1aadd7f7a827d8e7ed1e0d48c47509bb
 size 233605480

checkpoint-80/README.md

@@ -0,0 +1,210 @@
+---
+base_model: /kaggle/temp/qwen38-27b-4bit
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:/kaggle/temp/qwen38-27b-4bit
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.19.1

checkpoint-80/adapter_config.json

@@ -0,0 +1,44 @@
+{
+  "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": "/kaggle/temp/qwen38-27b-4bit",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 8,
+  "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": "(?:.*?(?:language|text).*?(?:self_attn|attention|attn|mixer|mlp|feed_forward|ffn|dense|mixer).*?(?:qkv|proj|linear_fc1|linear_fc2|out_proj|in_proj_qkv|in_proj_z|in_proj_b|in_proj_a|gate_proj|up_proj|down_proj|q_proj|k_proj|v_proj|o_proj))|(?:\\bmodel\\.layers\\.[\\d]{1,}\\.(?:self_attn|attention|attn|mixer|mlp|feed_forward|ffn|dense|mixer)\\.(?:(?:qkv|proj|linear_fc1|linear_fc2|out_proj|in_proj_qkv|in_proj_z|in_proj_b|in_proj_a|gate_proj|up_proj|down_proj|q_proj|k_proj|v_proj|o_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-80/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:389f436febbb63d4d377b82e8288d3599c836c20d8f322f9ecfbc023e2d24059
+size 233605480

checkpoint-80/chat_template.jinja

@@ -0,0 +1,184 @@
+{%- 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 sysns = namespace(count=0, text='') %}
+{%- for message in messages %}
+    {%- if sysns.count == loop.index0 and (message.role == 'system' or message.role == 'developer') %}
+        {%- set sys_content = render_content(message.content, false, true)|trim %}
+        {%- if sys_content %}
+            {%- set sysns.text = sysns.text + ('\n' if sysns.text else '') + sys_content %}
+        {%- endif %}
+        {%- set sysns.count = sysns.count + 1 %}
+    {%- endif %}
+{%- endfor %}
+{%- set num_sys = sysns.count %}
+{%- set merged_system = sysns.text %}
+{%- set reasoning_instructions = '' %}
+{%- if enable_thinking is undefined or enable_thinking is true %}
+    {%- set resolved_reasoning_effort = reasoning_effort|default('xhigh') %}
+    {%- if resolved_reasoning_effort == 'high' %}
+        {%- set resolved_reasoning_effort = 'xhigh' %}
+    {%- endif %}
+    {%- if resolved_reasoning_effort not in ('xhigh', 'medium', 'low') %}
+        {{- raise_exception('Unexpected reasoning effort ' ~ reasoning_effort ~ '. Supported types are xhigh (default), medium, and low.') }}
+    {%- endif %}
+    {%- if resolved_reasoning_effort == 'xhigh' %}
+        {%- set reasoning_instructions = 'Reasoning effort is set to xhigh. Please think carefully through the task, validate key assumptions, consider plausible alternatives, and prioritize correctness, consistency, and clarity in the final answer.' %}
+    {%- elif resolved_reasoning_effort == 'low' %}
+        {%- set reasoning_instructions = 'Reasoning effort is set to low. Keep your thinking brief and focused, moving directly to the conclusion without unnecessary elaboration.' %}
+    {%- endif %}
+{%- endif %}
+{%- if tools and tools is iterable and tools is not mapping %}
+    {{- '<|im_start|>system\n' }}
+    {%- if reasoning_instructions %}
+        {{- reasoning_instructions + '\n\n' }}
+    {%- endif %}
+    {{- "# 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' + (reasoning_instructions + '\n\n' if reasoning_instructions else '')  + merged_system + '<|im_end|>\n' }}
+    {%- elif reasoning_instructions %}
+        {{- '<|im_start|>system\n' + reasoning_instructions + '<|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 %}
+    {%- set content = render_content(message.content, true)|trim %}
+    {%- if message.role == "system" or message.role == "developer" %}
+        {{- raise_exception('System message must be at the beginning.') }}
+    {%- 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 %}
+        {%- endif %}
+        {%- set reasoning_content = reasoning_content|trim %}
+        {%- if preserve_thinking is undefined or preserve_thinking is true or 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 tool_call.name is not defined or tool_call.name is none %}
+                    {{- raise_exception('Tool call is missing a function name.') }}
+                {%- 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, args_value in tool_call.arguments|items %}
+                        {{- '<parameter=' + args_name + '>\n' }}
+                        {%- set args_value = args_value | string if args_value is string else args_value | tojson | safe %}
+                        {{- args_value }}
+                        {{- '\n</parameter>\n' }}
+                    {%- endfor %}
+                {%- elif tool_call.arguments is string %}
+                    {%- if tool_call.arguments|trim %}
+                        {{- raise_exception('Tool call arguments for function "' + (tool_call.name | string) + '" were passed as a JSON string. Parse them into an object before calling apply_chat_template.') }}
+                    {%- endif %}
+                {%- elif tool_call.arguments is defined and tool_call.arguments is not none %}
+                    {{- raise_exception('Tool call arguments for function "' + (tool_call.name | string) + '" must be an object/mapping or a JSON string.') }}
+                {%- 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 %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- else %}
+        {{- '<think>\n' }}
+    {%- endif %}
+{%- endif %}
+{#- Unsloth fixes - developer role, merged system messages, tool calling #}

checkpoint-80/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd5c0c452f31730598c15c3cd42742b2f0ebc4e3a340aca60a60f89ab990006a
+size 119892711

checkpoint-80/processor_config.json

@@ -0,0 +1,60 @@
+{
+  "image_processor": {
+    "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": {
+    "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-80/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61c19bab1174704a4a4441475683bf1270277af15d2e2c95e964789128e482c4
+size 14645

checkpoint-80/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b6cdd624f98e737642231d3d0aa2c041649a43aa87d782013db3dd5df5aaccf
+size 1465

checkpoint-80/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
+size 19989325

checkpoint-80/tokenizer_config.json

@@ -0,0 +1,300 @@
+{
+  "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": true,
+  "local_files_only": true,
+  "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": "<|endoftext|>",
+  "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": "Qwen2Tokenizer",
+  "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-80/trainer_state.json

@@ -0,0 +1,314 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.8791208791208791,
+  "eval_steps": 500,
+  "global_step": 80,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02197802197802198,
+      "grad_norm": 0.3012084364891052,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.3385181427001953,
+      "step": 2
+    },
+    {
+      "epoch": 0.04395604395604396,
+      "grad_norm": 0.3726103603839874,
+      "learning_rate": 1.2e-05,
+      "loss": 1.6271111965179443,
+      "step": 4
+    },
+    {
+      "epoch": 0.06593406593406594,
+      "grad_norm": 0.2790508568286896,
+      "learning_rate": 2e-05,
+      "loss": 1.5764275789260864,
+      "step": 6
+    },
+    {
+      "epoch": 0.08791208791208792,
+      "grad_norm": 0.3855365216732025,
+      "learning_rate": 1.9973322836635517e-05,
+      "loss": 1.80802583694458,
+      "step": 8
+    },
+    {
+      "epoch": 0.10989010989010989,
+      "grad_norm": 0.2806936502456665,
+      "learning_rate": 1.9893433680751105e-05,
+      "loss": 1.352150797843933,
+      "step": 10
+    },
+    {
+      "epoch": 0.13186813186813187,
+      "grad_norm": 0.3063288629055023,
+      "learning_rate": 1.9760758775559275e-05,
+      "loss": 1.4385991096496582,
+      "step": 12
+    },
+    {
+      "epoch": 0.15384615384615385,
+      "grad_norm": 0.25889647006988525,
+      "learning_rate": 1.957600599908406e-05,
+      "loss": 1.841127634048462,
+      "step": 14
+    },
+    {
+      "epoch": 0.17582417582417584,
+      "grad_norm": 0.27789703011512756,
+      "learning_rate": 1.9340161087325483e-05,
+      "loss": 1.497275471687317,
+      "step": 16
+    },
+    {
+      "epoch": 0.1978021978021978,
+      "grad_norm": 0.3025414049625397,
+      "learning_rate": 1.905448237493147e-05,
+      "loss": 1.4605973958969116,
+      "step": 18
+    },
+    {
+      "epoch": 0.21978021978021978,
+      "grad_norm": 0.2801181375980377,
+      "learning_rate": 1.872049408143808e-05,
+      "loss": 1.3008084297180176,
+      "step": 20
+    },
+    {
+      "epoch": 0.24175824175824176,
+      "grad_norm": 0.2751348912715912,
+      "learning_rate": 1.833997817889878e-05,
+      "loss": 1.2773511409759521,
+      "step": 22
+    },
+    {
+      "epoch": 0.26373626373626374,
+      "grad_norm": 0.38996145129203796,
+      "learning_rate": 1.7914964884292543e-05,
+      "loss": 1.2179161310195923,
+      "step": 24
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 0.8840112090110779,
+      "learning_rate": 1.744772182743782e-05,
+      "loss": 1.855831503868103,
+      "step": 26
+    },
+    {
+      "epoch": 0.3076923076923077,
+      "grad_norm": 0.3252807855606079,
+      "learning_rate": 1.6940741952206342e-05,
+      "loss": 1.5678815841674805,
+      "step": 28
+    },
+    {
+      "epoch": 0.32967032967032966,
+      "grad_norm": 0.24409082531929016,
+      "learning_rate": 1.6396730215588913e-05,
+      "loss": 1.2494449615478516,
+      "step": 30
+    },
+    {
+      "epoch": 0.3516483516483517,
+      "grad_norm": 0.22459135949611664,
+      "learning_rate": 1.581858915557953e-05,
+      "loss": 1.0519582033157349,
+      "step": 32
+    },
+    {
+      "epoch": 0.37362637362637363,
+      "grad_norm": 0.3741042912006378,
+      "learning_rate": 1.5209403404879305e-05,
+      "loss": 1.4155118465423584,
+      "step": 34
+    },
+    {
+      "epoch": 0.3956043956043956,
+      "grad_norm": 0.31006920337677,
+      "learning_rate": 1.4572423233046386e-05,
+      "loss": 1.1812822818756104,
+      "step": 36
+    },
+    {
+      "epoch": 0.4175824175824176,
+      "grad_norm": 3.532601833343506,
+      "learning_rate": 1.391104720490156e-05,
+      "loss": 1.4337464570999146,
+      "step": 38
+    },
+    {
+      "epoch": 0.43956043956043955,
+      "grad_norm": 0.626689076423645,
+      "learning_rate": 1.3228804047714462e-05,
+      "loss": 1.2015326023101807,
+      "step": 40
+    },
+    {
+      "epoch": 0.46153846153846156,
+      "grad_norm": 0.32571879029273987,
+      "learning_rate": 1.2529333823916807e-05,
+      "loss": 1.010868787765503,
+      "step": 42
+    },
+    {
+      "epoch": 0.4835164835164835,
+      "grad_norm": 0.3460634648799896,
+      "learning_rate": 1.1816368509794365e-05,
+      "loss": 1.3443571329116821,
+      "step": 44
+    },
+    {
+      "epoch": 0.5054945054945055,
+      "grad_norm": 0.3677666485309601,
+      "learning_rate": 1.1093712083778748e-05,
+      "loss": 1.189827561378479,
+      "step": 46
+    },
+    {
+      "epoch": 0.5274725274725275,
+      "grad_norm": 0.4721606969833374,
+      "learning_rate": 1.0365220230576592e-05,
+      "loss": 1.292205572128296,
+      "step": 48
+    },
+    {
+      "epoch": 0.5494505494505495,
+      "grad_norm": 0.2631397247314453,
+      "learning_rate": 9.634779769423412e-06,
+      "loss": 1.4859278202056885,
+      "step": 50
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 0.4153558909893036,
+      "learning_rate": 8.906287916221259e-06,
+      "loss": 1.3328526020050049,
+      "step": 52
+    },
+    {
+      "epoch": 0.5934065934065934,
+      "grad_norm": 0.44497573375701904,
+      "learning_rate": 8.183631490205636e-06,
+      "loss": 1.295997142791748,
+      "step": 54
+    },
+    {
+      "epoch": 0.6153846153846154,
+      "grad_norm": 0.4488207697868347,
+      "learning_rate": 7.470666176083193e-06,
+      "loss": 1.449225902557373,
+      "step": 56
+    },
+    {
+      "epoch": 0.6373626373626373,
+      "grad_norm": 0.24774296581745148,
+      "learning_rate": 6.771195952285541e-06,
+      "loss": 1.4275600910186768,
+      "step": 58
+    },
+    {
+      "epoch": 0.6593406593406593,
+      "grad_norm": 0.5897124409675598,
+      "learning_rate": 6.088952795098442e-06,
+      "loss": 1.3049211502075195,
+      "step": 60
+    },
+    {
+      "epoch": 0.6813186813186813,
+      "grad_norm": 0.442289799451828,
+      "learning_rate": 5.427576766953615e-06,
+      "loss": 1.2369039058685303,
+      "step": 62
+    },
+    {
+      "epoch": 0.7032967032967034,
+      "grad_norm": 0.3426021635532379,
+      "learning_rate": 4.790596595120699e-06,
+      "loss": 1.4170987606048584,
+      "step": 64
+    },
+    {
+      "epoch": 0.7252747252747253,
+      "grad_norm": 0.4659130573272705,
+      "learning_rate": 4.181410844420473e-06,
+      "loss": 1.540313959121704,
+      "step": 66
+    },
+    {
+      "epoch": 0.7472527472527473,
+      "grad_norm": 0.3569144010543823,
+      "learning_rate": 3.6032697844110896e-06,
+      "loss": 1.1695493459701538,
+      "step": 68
+    },
+    {
+      "epoch": 0.7692307692307693,
+      "grad_norm": 0.31596097350120544,
+      "learning_rate": 3.0592580477936606e-06,
+      "loss": 1.2741234302520752,
+      "step": 70
+    },
+    {
+      "epoch": 0.7912087912087912,
+      "grad_norm": 0.3353954553604126,
+      "learning_rate": 2.5522781725621814e-06,
+      "loss": 1.2784150838851929,
+      "step": 72
+    },
+    {
+      "epoch": 0.8131868131868132,
+      "grad_norm": 0.3931275010108948,
+      "learning_rate": 2.08503511570746e-06,
+      "loss": 1.2940069437026978,
+      "step": 74
+    },
+    {
+      "epoch": 0.8351648351648352,
+      "grad_norm": 0.3980410695075989,
+      "learning_rate": 1.660021821101222e-06,
+      "loss": 0.9338208436965942,
+      "step": 76
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 0.2409302294254303,
+      "learning_rate": 1.279505918561923e-06,
+      "loss": 1.3363934755325317,
+      "step": 78
+    },
+    {
+      "epoch": 0.8791208791208791,
+      "grad_norm": 0.3418237268924713,
+      "learning_rate": 9.455176250685338e-07,
+      "loss": 1.2735731601715088,
+      "step": 80
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 91,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 20,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.4769785469313664e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-80/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e98c4e47e436fafe01761b877359d404c5149d6428639c84dbbf500fbfeb78e
+size 5713

checkpoint-91/README.md

@@ -0,0 +1,210 @@
+---
+base_model: /kaggle/temp/qwen38-27b-4bit
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:/kaggle/temp/qwen38-27b-4bit
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.19.1

checkpoint-91/adapter_config.json

@@ -0,0 +1,44 @@
+{
+  "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": "/kaggle/temp/qwen38-27b-4bit",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 8,
+  "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": "(?:.*?(?:language|text).*?(?:self_attn|attention|attn|mixer|mlp|feed_forward|ffn|dense|mixer).*?(?:qkv|proj|linear_fc1|linear_fc2|out_proj|in_proj_qkv|in_proj_z|in_proj_b|in_proj_a|gate_proj|up_proj|down_proj|q_proj|k_proj|v_proj|o_proj))|(?:\\bmodel\\.layers\\.[\\d]{1,}\\.(?:self_attn|attention|attn|mixer|mlp|feed_forward|ffn|dense|mixer)\\.(?:(?:qkv|proj|linear_fc1|linear_fc2|out_proj|in_proj_qkv|in_proj_z|in_proj_b|in_proj_a|gate_proj|up_proj|down_proj|q_proj|k_proj|v_proj|o_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-91/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0d3c0370472ecac76491b12c0d2115f1aadd7f7a827d8e7ed1e0d48c47509bb
+size 233605480

checkpoint-91/chat_template.jinja

@@ -0,0 +1,184 @@
+{%- 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 sysns = namespace(count=0, text='') %}
+{%- for message in messages %}
+    {%- if sysns.count == loop.index0 and (message.role == 'system' or message.role == 'developer') %}
+        {%- set sys_content = render_content(message.content, false, true)|trim %}
+        {%- if sys_content %}
+            {%- set sysns.text = sysns.text + ('\n' if sysns.text else '') + sys_content %}
+        {%- endif %}
+        {%- set sysns.count = sysns.count + 1 %}
+    {%- endif %}
+{%- endfor %}
+{%- set num_sys = sysns.count %}
+{%- set merged_system = sysns.text %}
+{%- set reasoning_instructions = '' %}
+{%- if enable_thinking is undefined or enable_thinking is true %}
+    {%- set resolved_reasoning_effort = reasoning_effort|default('xhigh') %}
+    {%- if resolved_reasoning_effort == 'high' %}
+        {%- set resolved_reasoning_effort = 'xhigh' %}
+    {%- endif %}
+    {%- if resolved_reasoning_effort not in ('xhigh', 'medium', 'low') %}
+        {{- raise_exception('Unexpected reasoning effort ' ~ reasoning_effort ~ '. Supported types are xhigh (default), medium, and low.') }}
+    {%- endif %}
+    {%- if resolved_reasoning_effort == 'xhigh' %}
+        {%- set reasoning_instructions = 'Reasoning effort is set to xhigh. Please think carefully through the task, validate key assumptions, consider plausible alternatives, and prioritize correctness, consistency, and clarity in the final answer.' %}
+    {%- elif resolved_reasoning_effort == 'low' %}
+        {%- set reasoning_instructions = 'Reasoning effort is set to low. Keep your thinking brief and focused, moving directly to the conclusion without unnecessary elaboration.' %}
+    {%- endif %}
+{%- endif %}
+{%- if tools and tools is iterable and tools is not mapping %}
+    {{- '<|im_start|>system\n' }}
+    {%- if reasoning_instructions %}
+        {{- reasoning_instructions + '\n\n' }}
+    {%- endif %}
+    {{- "# 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' + (reasoning_instructions + '\n\n' if reasoning_instructions else '')  + merged_system + '<|im_end|>\n' }}
+    {%- elif reasoning_instructions %}
+        {{- '<|im_start|>system\n' + reasoning_instructions + '<|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 %}
+    {%- set content = render_content(message.content, true)|trim %}
+    {%- if message.role == "system" or message.role == "developer" %}
+        {{- raise_exception('System message must be at the beginning.') }}
+    {%- 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 %}
+        {%- endif %}
+        {%- set reasoning_content = reasoning_content|trim %}
+        {%- if preserve_thinking is undefined or preserve_thinking is true or 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 tool_call.name is not defined or tool_call.name is none %}
+                    {{- raise_exception('Tool call is missing a function name.') }}
+                {%- 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, args_value in tool_call.arguments|items %}
+                        {{- '<parameter=' + args_name + '>\n' }}
+                        {%- set args_value = args_value | string if args_value is string else args_value | tojson | safe %}
+                        {{- args_value }}
+                        {{- '\n</parameter>\n' }}
+                    {%- endfor %}
+                {%- elif tool_call.arguments is string %}
+                    {%- if tool_call.arguments|trim %}
+                        {{- raise_exception('Tool call arguments for function "' + (tool_call.name | string) + '" were passed as a JSON string. Parse them into an object before calling apply_chat_template.') }}
+                    {%- endif %}
+                {%- elif tool_call.arguments is defined and tool_call.arguments is not none %}
+                    {{- raise_exception('Tool call arguments for function "' + (tool_call.name | string) + '" must be an object/mapping or a JSON string.') }}
+                {%- 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 %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- else %}
+        {{- '<think>\n' }}
+    {%- endif %}
+{%- endif %}
+{#- Unsloth fixes - developer role, merged system messages, tool calling #}

checkpoint-91/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bb61e7edf8713b80aeb034777083e1325ada5eab7eff3f994f342107c87a1fa
+size 119892711

checkpoint-91/processor_config.json

@@ -0,0 +1,60 @@
+{
+  "image_processor": {
+    "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": {
+    "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-91/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61c19bab1174704a4a4441475683bf1270277af15d2e2c95e964789128e482c4
+size 14645

checkpoint-91/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78cc4be6398f6247b951531aaff05e12bc6e9e9e3e9bb899b6980af1136231c7
+size 1465

checkpoint-91/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
+size 19989325

checkpoint-91/tokenizer_config.json

@@ -0,0 +1,300 @@
+{
+  "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": true,
+  "local_files_only": true,
+  "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": "<|endoftext|>",
+  "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": "Qwen2Tokenizer",
+  "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-91/trainer_state.json

@@ -0,0 +1,349 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 91,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02197802197802198,
+      "grad_norm": 0.3012084364891052,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.3385181427001953,
+      "step": 2
+    },
+    {
+      "epoch": 0.04395604395604396,
+      "grad_norm": 0.3726103603839874,
+      "learning_rate": 1.2e-05,
+      "loss": 1.6271111965179443,
+      "step": 4
+    },
+    {
+      "epoch": 0.06593406593406594,
+      "grad_norm": 0.2790508568286896,
+      "learning_rate": 2e-05,
+      "loss": 1.5764275789260864,
+      "step": 6
+    },
+    {
+      "epoch": 0.08791208791208792,
+      "grad_norm": 0.3855365216732025,
+      "learning_rate": 1.9973322836635517e-05,
+      "loss": 1.80802583694458,
+      "step": 8
+    },
+    {
+      "epoch": 0.10989010989010989,
+      "grad_norm": 0.2806936502456665,
+      "learning_rate": 1.9893433680751105e-05,
+      "loss": 1.352150797843933,
+      "step": 10
+    },
+    {
+      "epoch": 0.13186813186813187,
+      "grad_norm": 0.3063288629055023,
+      "learning_rate": 1.9760758775559275e-05,
+      "loss": 1.4385991096496582,
+      "step": 12
+    },
+    {
+      "epoch": 0.15384615384615385,
+      "grad_norm": 0.25889647006988525,
+      "learning_rate": 1.957600599908406e-05,
+      "loss": 1.841127634048462,
+      "step": 14
+    },
+    {
+      "epoch": 0.17582417582417584,
+      "grad_norm": 0.27789703011512756,
+      "learning_rate": 1.9340161087325483e-05,
+      "loss": 1.497275471687317,
+      "step": 16
+    },
+    {
+      "epoch": 0.1978021978021978,
+      "grad_norm": 0.3025414049625397,
+      "learning_rate": 1.905448237493147e-05,
+      "loss": 1.4605973958969116,
+      "step": 18
+    },
+    {
+      "epoch": 0.21978021978021978,
+      "grad_norm": 0.2801181375980377,
+      "learning_rate": 1.872049408143808e-05,
+      "loss": 1.3008084297180176,
+      "step": 20
+    },
+    {
+      "epoch": 0.24175824175824176,
+      "grad_norm": 0.2751348912715912,
+      "learning_rate": 1.833997817889878e-05,
+      "loss": 1.2773511409759521,
+      "step": 22
+    },
+    {
+      "epoch": 0.26373626373626374,
+      "grad_norm": 0.38996145129203796,
+      "learning_rate": 1.7914964884292543e-05,
+      "loss": 1.2179161310195923,
+      "step": 24
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 0.8840112090110779,
+      "learning_rate": 1.744772182743782e-05,
+      "loss": 1.855831503868103,
+      "step": 26
+    },
+    {
+      "epoch": 0.3076923076923077,
+      "grad_norm": 0.3252807855606079,
+      "learning_rate": 1.6940741952206342e-05,
+      "loss": 1.5678815841674805,
+      "step": 28
+    },
+    {
+      "epoch": 0.32967032967032966,
+      "grad_norm": 0.24409082531929016,
+      "learning_rate": 1.6396730215588913e-05,
+      "loss": 1.2494449615478516,
+      "step": 30
+    },
+    {
+      "epoch": 0.3516483516483517,
+      "grad_norm": 0.22459135949611664,
+      "learning_rate": 1.581858915557953e-05,
+      "loss": 1.0519582033157349,
+      "step": 32
+    },
+    {
+      "epoch": 0.37362637362637363,
+      "grad_norm": 0.3741042912006378,
+      "learning_rate": 1.5209403404879305e-05,
+      "loss": 1.4155118465423584,
+      "step": 34
+    },
+    {
+      "epoch": 0.3956043956043956,
+      "grad_norm": 0.31006920337677,
+      "learning_rate": 1.4572423233046386e-05,
+      "loss": 1.1812822818756104,
+      "step": 36
+    },
+    {
+      "epoch": 0.4175824175824176,
+      "grad_norm": 3.532601833343506,
+      "learning_rate": 1.391104720490156e-05,
+      "loss": 1.4337464570999146,
+      "step": 38
+    },
+    {
+      "epoch": 0.43956043956043955,
+      "grad_norm": 0.626689076423645,
+      "learning_rate": 1.3228804047714462e-05,
+      "loss": 1.2015326023101807,
+      "step": 40
+    },
+    {
+      "epoch": 0.46153846153846156,
+      "grad_norm": 0.32571879029273987,
+      "learning_rate": 1.2529333823916807e-05,
+      "loss": 1.010868787765503,
+      "step": 42
+    },
+    {
+      "epoch": 0.4835164835164835,
+      "grad_norm": 0.3460634648799896,
+      "learning_rate": 1.1816368509794365e-05,
+      "loss": 1.3443571329116821,
+      "step": 44
+    },
+    {
+      "epoch": 0.5054945054945055,
+      "grad_norm": 0.3677666485309601,
+      "learning_rate": 1.1093712083778748e-05,
+      "loss": 1.189827561378479,
+      "step": 46
+    },
+    {
+      "epoch": 0.5274725274725275,
+      "grad_norm": 0.4721606969833374,
+      "learning_rate": 1.0365220230576592e-05,
+      "loss": 1.292205572128296,
+      "step": 48
+    },
+    {
+      "epoch": 0.5494505494505495,
+      "grad_norm": 0.2631397247314453,
+      "learning_rate": 9.634779769423412e-06,
+      "loss": 1.4859278202056885,
+      "step": 50
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 0.4153558909893036,
+      "learning_rate": 8.906287916221259e-06,
+      "loss": 1.3328526020050049,
+      "step": 52
+    },
+    {
+      "epoch": 0.5934065934065934,
+      "grad_norm": 0.44497573375701904,
+      "learning_rate": 8.183631490205636e-06,
+      "loss": 1.295997142791748,
+      "step": 54
+    },
+    {
+      "epoch": 0.6153846153846154,
+      "grad_norm": 0.4488207697868347,
+      "learning_rate": 7.470666176083193e-06,
+      "loss": 1.449225902557373,
+      "step": 56
+    },
+    {
+      "epoch": 0.6373626373626373,
+      "grad_norm": 0.24774296581745148,
+      "learning_rate": 6.771195952285541e-06,
+      "loss": 1.4275600910186768,
+      "step": 58
+    },
+    {
+      "epoch": 0.6593406593406593,
+      "grad_norm": 0.5897124409675598,
+      "learning_rate": 6.088952795098442e-06,
+      "loss": 1.3049211502075195,
+      "step": 60
+    },
+    {
+      "epoch": 0.6813186813186813,
+      "grad_norm": 0.442289799451828,
+      "learning_rate": 5.427576766953615e-06,
+      "loss": 1.2369039058685303,
+      "step": 62
+    },
+    {
+      "epoch": 0.7032967032967034,
+      "grad_norm": 0.3426021635532379,
+      "learning_rate": 4.790596595120699e-06,
+      "loss": 1.4170987606048584,
+      "step": 64
+    },
+    {
+      "epoch": 0.7252747252747253,
+      "grad_norm": 0.4659130573272705,
+      "learning_rate": 4.181410844420473e-06,
+      "loss": 1.540313959121704,
+      "step": 66
+    },
+    {
+      "epoch": 0.7472527472527473,
+      "grad_norm": 0.3569144010543823,
+      "learning_rate": 3.6032697844110896e-06,
+      "loss": 1.1695493459701538,
+      "step": 68
+    },
+    {
+      "epoch": 0.7692307692307693,
+      "grad_norm": 0.31596097350120544,
+      "learning_rate": 3.0592580477936606e-06,
+      "loss": 1.2741234302520752,
+      "step": 70
+    },
+    {
+      "epoch": 0.7912087912087912,
+      "grad_norm": 0.3353954553604126,
+      "learning_rate": 2.5522781725621814e-06,
+      "loss": 1.2784150838851929,
+      "step": 72
+    },
+    {
+      "epoch": 0.8131868131868132,
+      "grad_norm": 0.3931275010108948,
+      "learning_rate": 2.08503511570746e-06,
+      "loss": 1.2940069437026978,
+      "step": 74
+    },
+    {
+      "epoch": 0.8351648351648352,
+      "grad_norm": 0.3980410695075989,
+      "learning_rate": 1.660021821101222e-06,
+      "loss": 0.9338208436965942,
+      "step": 76
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 0.2409302294254303,
+      "learning_rate": 1.279505918561923e-06,
+      "loss": 1.3363934755325317,
+      "step": 78
+    },
+    {
+      "epoch": 0.8791208791208791,
+      "grad_norm": 0.3418237268924713,
+      "learning_rate": 9.455176250685338e-07,
+      "loss": 1.2735731601715088,
+      "step": 80
+    },
+    {
+      "epoch": 0.9010989010989011,
+      "grad_norm": 0.9127710461616516,
+      "learning_rate": 6.598389126745209e-07,
+      "loss": 1.4067552089691162,
+      "step": 82
+    },
+    {
+      "epoch": 0.9230769230769231,
+      "grad_norm": 0.4294987916946411,
+      "learning_rate": 4.2399400091594154e-07,
+      "loss": 1.236148715019226,
+      "step": 84
+    },
+    {
+      "epoch": 0.945054945054945,
+      "grad_norm": 0.3184118866920471,
+      "learning_rate": 2.392412244407294e-07,
+      "loss": 1.2201662063598633,
+      "step": 86
+    },
+    {
+      "epoch": 0.967032967032967,
+      "grad_norm": 0.3202824890613556,
+      "learning_rate": 1.0656631924889749e-07,
+      "loss": 1.4348292350769043,
+      "step": 88
+    },
+    {
+      "epoch": 0.989010989010989,
+      "grad_norm": 0.3805205523967743,
+      "learning_rate": 2.667716336448356e-08,
+      "loss": 1.1723339557647705,
+      "step": 90
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 91,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 20,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.838963982233341e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-91/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e98c4e47e436fafe01761b877359d404c5149d6428639c84dbbf500fbfeb78e
+size 5713

tokenizer_config.json

@@ -9,8 +9,8 @@
   "eos_token": "<|im_end|>",
   "errors": "replace",
   "image_token": "<|image_pad|>",
-  "is_local": false,
-  "local_files_only": false,
+  "is_local": true,
+  "local_files_only": true,
   "model_max_length": 262144,
   "model_specific_special_tokens": {
     "audio_bos_token": "<|audio_start|>",