Add qwen3vl-32b adapter

.gitattributes

@@ -38,3 +38,4 @@ qwen35-27b/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 qwen36-27b/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 qwen3vl-4b/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 qwen3vl-8b/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen3vl-32b/tokenizer.json filter=lfs diff=lfs merge=lfs -text

qwen3vl-32b/README.md

@@ -0,0 +1,61 @@
+---
+library_name: peft
+license: other
+base_model: Qwen/Qwen3-VL-32B-Instruct
+tags:
+- base_model:adapter:Qwen/Qwen3-VL-32B-Instruct
+- llama-factory
+- lora
+- transformers
+pipeline_tag: text-generation
+model-index:
+- name: widget2code-lora-size-tools
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# widget2code-lora-size-tools
+
+This model is a fine-tuned version of [Qwen/Qwen3-VL-32B-Instruct](https://huggingface.co/Qwen/Qwen3-VL-32B-Instruct) on the widget2code_sft dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0001
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 16
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 0.1
+- num_epochs: 4
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.18.1
+- Transformers 5.6.0
+- Pytorch 2.11.0+cu130
+- Datasets 4.0.0
+- Tokenizers 0.22.2

qwen3vl-32b/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-VL-32B-Instruct",
+  "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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "q_proj",
+    "up_proj",
+    "v_proj",
+    "gate_proj",
+    "k_proj",
+    "o_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

qwen3vl-32b/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b16f46cd952ca52966023972a54c6645d4935e784b27ea9ec1547ec67b76e1a
+size 1073876648

qwen3vl-32b/all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "total_flos": 3.529283513966947e+18,
+    "train_loss": 0.18179457177195632,
+    "train_runtime": 11945.8456,
+    "train_samples_per_second": 0.608,
+    "train_steps_per_second": 0.038
+}

qwen3vl-32b/chat_template.jinja

@@ -0,0 +1,120 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {%- if messages[0].content is string %}
+            {{- messages[0].content }}
+        {%- else %}
+            {%- for content in messages[0].content %}
+                {%- if 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' }}
+        {%- if messages[0].content is string %}
+            {{- messages[0].content }}
+        {%- else %}
+            {%- for content in messages[0].content %}
+                {%- if 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- for message in messages %}
+    {%- if message.role == "user" %}
+        {{- '<|im_start|>' + message.role + '\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content in message.content %}
+                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+                    <|vision_start|><|image_pad|><|vision_end|>
+                {%- elif content.type == 'video' or 'video' in content %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+                    <|vision_start|><|video_pad|><|vision_end|>
+                {%- elif 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role + '\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content_item in message.content %}
+                {%- if 'text' in content_item %}
+                    {{- content_item.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and message.content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content in message.content %}
+                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+                    <|vision_start|><|image_pad|><|vision_end|>
+                {%- elif content.type == 'video' or 'video' in content %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+                    <|vision_start|><|video_pad|><|vision_end|>
+                {%- elif 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

qwen3vl-32b/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"
+  }
+}

qwen3vl-32b/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
+size 11422650

qwen3vl-32b/tokenizer_config.json

@@ -0,0 +1,32 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 262144,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "processor_class": "Qwen3VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

qwen3vl-32b/train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "total_flos": 3.529283513966947e+18,
+    "train_loss": 0.18179457177195632,
+    "train_runtime": 11945.8456,
+    "train_samples_per_second": 0.608,
+    "train_steps_per_second": 0.038
+}

qwen3vl-32b/trainer_log.jsonl

@@ -0,0 +1,46 @@
+{"current_steps": 10, "total_steps": 456, "loss": 0.40406527519226076, "lr": 1.956521739130435e-05, "epoch": 0.0881057268722467, "percentage": 2.19, "elapsed_time": "0:04:35", "remaining_time": "3:24:53"}
+{"current_steps": 20, "total_steps": 456, "loss": 0.328407883644104, "lr": 4.130434782608696e-05, "epoch": 0.1762114537444934, "percentage": 4.39, "elapsed_time": "0:09:59", "remaining_time": "3:37:47"}
+{"current_steps": 30, "total_steps": 456, "loss": 0.27924346923828125, "lr": 6.304347826086957e-05, "epoch": 0.2643171806167401, "percentage": 6.58, "elapsed_time": "0:14:07", "remaining_time": "3:20:33"}
+{"current_steps": 40, "total_steps": 456, "loss": 0.26110143661499025, "lr": 8.478260869565218e-05, "epoch": 0.3524229074889868, "percentage": 8.77, "elapsed_time": "0:18:23", "remaining_time": "3:11:11"}
+{"current_steps": 50, "total_steps": 456, "loss": 0.23283846378326417, "lr": 9.998679022482915e-05, "epoch": 0.44052863436123346, "percentage": 10.96, "elapsed_time": "0:22:43", "remaining_time": "3:04:30"}
+{"current_steps": 60, "total_steps": 456, "loss": 0.23090167045593263, "lr": 9.975214390089637e-05, "epoch": 0.5286343612334802, "percentage": 13.16, "elapsed_time": "0:27:16", "remaining_time": "2:59:58"}
+{"current_steps": 70, "total_steps": 456, "loss": 0.22481226921081543, "lr": 9.922553221348281e-05, "epoch": 0.6167400881057269, "percentage": 15.35, "elapsed_time": "0:31:26", "remaining_time": "2:53:20"}
+{"current_steps": 80, "total_steps": 456, "loss": 0.22943453788757323, "lr": 9.841004552936817e-05, "epoch": 0.7048458149779736, "percentage": 17.54, "elapsed_time": "0:36:08", "remaining_time": "2:49:50"}
+{"current_steps": 90, "total_steps": 456, "loss": 0.21811044216156006, "lr": 9.731046944867883e-05, "epoch": 0.7929515418502202, "percentage": 19.74, "elapsed_time": "0:40:30", "remaining_time": "2:44:46"}
+{"current_steps": 100, "total_steps": 456, "loss": 0.20856730937957763, "lr": 9.593325672108351e-05, "epoch": 0.8810572687224669, "percentage": 21.93, "elapsed_time": "0:44:45", "remaining_time": "2:39:20"}
+{"current_steps": 110, "total_steps": 456, "loss": 0.208496618270874, "lr": 9.428648937849228e-05, "epoch": 0.9691629955947136, "percentage": 24.12, "elapsed_time": "0:49:04", "remaining_time": "2:34:22"}
+{"current_steps": 120, "total_steps": 456, "loss": 0.20336875915527344, "lr": 9.237983130647974e-05, "epoch": 1.052863436123348, "percentage": 26.32, "elapsed_time": "0:53:17", "remaining_time": "2:29:12"}
+{"current_steps": 130, "total_steps": 456, "loss": 0.1991032361984253, "lr": 9.022447153276168e-05, "epoch": 1.1409691629955947, "percentage": 28.51, "elapsed_time": "0:57:34", "remaining_time": "2:24:22"}
+{"current_steps": 140, "total_steps": 456, "loss": 0.18334383964538575, "lr": 8.783305856553144e-05, "epoch": 1.2290748898678414, "percentage": 30.7, "elapsed_time": "1:01:39", "remaining_time": "2:19:09"}
+{"current_steps": 150, "total_steps": 456, "loss": 0.18828495740890502, "lr": 8.521962616698427e-05, "epoch": 1.3171806167400881, "percentage": 32.89, "elapsed_time": "1:05:58", "remaining_time": "2:14:34"}
+{"current_steps": 160, "total_steps": 456, "loss": 0.18282666206359863, "lr": 8.239951099762058e-05, "epoch": 1.4052863436123348, "percentage": 35.09, "elapsed_time": "1:10:18", "remaining_time": "2:10:03"}
+{"current_steps": 170, "total_steps": 456, "loss": 0.18636636734008788, "lr": 7.938926261462366e-05, "epoch": 1.4933920704845816, "percentage": 37.28, "elapsed_time": "1:14:38", "remaining_time": "2:05:35"}
+{"current_steps": 180, "total_steps": 456, "loss": 0.18131622076034545, "lr": 7.620654635247762e-05, "epoch": 1.5814977973568283, "percentage": 39.47, "elapsed_time": "1:18:47", "remaining_time": "2:00:49"}
+{"current_steps": 190, "total_steps": 456, "loss": 0.18086057901382446, "lr": 7.287003965576019e-05, "epoch": 1.6696035242290748, "percentage": 41.67, "elapsed_time": "1:22:55", "remaining_time": "1:56:05"}
+{"current_steps": 200, "total_steps": 456, "loss": 0.19418610334396363, "lr": 6.939932247247126e-05, "epoch": 1.7577092511013217, "percentage": 43.86, "elapsed_time": "1:28:25", "remaining_time": "1:53:11"}
+{"current_steps": 210, "total_steps": 456, "loss": 0.18365358114242553, "lr": 6.581476235111243e-05, "epoch": 1.8458149779735682, "percentage": 46.05, "elapsed_time": "1:32:55", "remaining_time": "1:48:51"}
+{"current_steps": 220, "total_steps": 456, "loss": 0.1861007571220398, "lr": 6.213739491581348e-05, "epoch": 1.9339207048458151, "percentage": 48.25, "elapsed_time": "1:37:17", "remaining_time": "1:44:21"}
+{"current_steps": 230, "total_steps": 456, "loss": 0.17953892946243286, "lr": 5.8388800420925616e-05, "epoch": 2.0176211453744495, "percentage": 50.44, "elapsed_time": "1:41:24", "remaining_time": "1:39:38"}
+{"current_steps": 240, "total_steps": 456, "loss": 0.1574479579925537, "lr": 5.459097710950791e-05, "epoch": 2.105726872246696, "percentage": 52.63, "elapsed_time": "1:45:45", "remaining_time": "1:35:10"}
+{"current_steps": 250, "total_steps": 456, "loss": 0.150786828994751, "lr": 5.0766212118889824e-05, "epoch": 2.193832599118943, "percentage": 54.82, "elapsed_time": "1:49:59", "remaining_time": "1:30:38"}
+{"current_steps": 260, "total_steps": 456, "loss": 0.1606702446937561, "lr": 4.693695069088724e-05, "epoch": 2.2819383259911894, "percentage": 57.02, "elapsed_time": "1:54:24", "remaining_time": "1:26:15"}
+{"current_steps": 270, "total_steps": 456, "loss": 0.15859190225601197, "lr": 4.312566445419853e-05, "epoch": 2.3700440528634363, "percentage": 59.21, "elapsed_time": "1:59:15", "remaining_time": "1:22:09"}
+{"current_steps": 280, "total_steps": 456, "loss": 0.15953269004821777, "lr": 3.935471955195196e-05, "epoch": 2.458149779735683, "percentage": 61.4, "elapsed_time": "2:03:37", "remaining_time": "1:17:42"}
+{"current_steps": 290, "total_steps": 456, "loss": 0.15785973072052, "lr": 3.5646245388284213e-05, "epoch": 2.5462555066079293, "percentage": 63.6, "elapsed_time": "2:08:15", "remaining_time": "1:13:24"}
+{"current_steps": 300, "total_steps": 456, "loss": 0.1512267470359802, "lr": 3.202200476419761e-05, "epoch": 2.6343612334801763, "percentage": 65.79, "elapsed_time": "2:12:37", "remaining_time": "1:08:57"}
+{"current_steps": 310, "total_steps": 456, "loss": 0.15540086030960082, "lr": 2.8503266164790232e-05, "epoch": 2.7224669603524227, "percentage": 67.98, "elapsed_time": "2:16:37", "remaining_time": "1:04:20"}
+{"current_steps": 320, "total_steps": 456, "loss": 0.1461609721183777, "lr": 2.5110678947328302e-05, "epoch": 2.8105726872246697, "percentage": 70.18, "elapsed_time": "2:20:55", "remaining_time": "0:59:53"}
+{"current_steps": 330, "total_steps": 456, "loss": 0.15680785179138185, "lr": 2.1864152162606882e-05, "epoch": 2.898678414096916, "percentage": 72.37, "elapsed_time": "2:25:10", "remaining_time": "0:55:25"}
+{"current_steps": 340, "total_steps": 456, "loss": 0.14546056985855102, "lr": 1.878273772072332e-05, "epoch": 2.986784140969163, "percentage": 74.56, "elapsed_time": "2:29:12", "remaining_time": "0:50:54"}
+{"current_steps": 350, "total_steps": 456, "loss": 0.14447916746139527, "lr": 1.5884518586893187e-05, "epoch": 3.0704845814977975, "percentage": 76.75, "elapsed_time": "2:33:47", "remaining_time": "0:46:34"}
+{"current_steps": 360, "total_steps": 456, "loss": 0.12820364236831666, "lr": 1.3186502663419986e-05, "epoch": 3.158590308370044, "percentage": 78.95, "elapsed_time": "2:37:55", "remaining_time": "0:42:06"}
+{"current_steps": 370, "total_steps": 456, "loss": 0.13617411851882935, "lr": 1.0704522980561533e-05, "epoch": 3.246696035242291, "percentage": 81.14, "elapsed_time": "2:42:15", "remaining_time": "0:37:42"}
+{"current_steps": 380, "total_steps": 456, "loss": 0.1336129426956177, "lr": 8.453144782012639e-06, "epoch": 3.3348017621145374, "percentage": 83.33, "elapsed_time": "2:46:43", "remaining_time": "0:33:20"}
+{"current_steps": 390, "total_steps": 456, "loss": 0.12256991863250732, "lr": 6.445580050263611e-06, "epoch": 3.4229074889867843, "percentage": 85.53, "elapsed_time": "2:50:45", "remaining_time": "0:28:53"}
+{"current_steps": 400, "total_steps": 456, "loss": 0.12970975637435914, "lr": 4.69360997343335e-06, "epoch": 3.511013215859031, "percentage": 87.72, "elapsed_time": "2:55:09", "remaining_time": "0:24:31"}
+{"current_steps": 410, "total_steps": 456, "loss": 0.13449277877807617, "lr": 3.207515808572975e-06, "epoch": 3.5991189427312777, "percentage": 89.91, "elapsed_time": "2:59:17", "remaining_time": "0:20:06"}
+{"current_steps": 420, "total_steps": 456, "loss": 0.12987757921218873, "lr": 1.996018547161266e-06, "epoch": 3.6872246696035242, "percentage": 92.11, "elapsed_time": "3:03:34", "remaining_time": "0:15:44"}
+{"current_steps": 430, "total_steps": 456, "loss": 0.12816166877746582, "lr": 1.0662277368588824e-06, "epoch": 3.7753303964757707, "percentage": 94.3, "elapsed_time": "3:07:47", "remaining_time": "0:11:21"}
+{"current_steps": 440, "total_steps": 456, "loss": 0.12196211814880371, "lr": 4.2359975985574175e-07, "epoch": 3.8634361233480177, "percentage": 96.49, "elapsed_time": "3:12:15", "remaining_time": "0:06:59"}
+{"current_steps": 450, "total_steps": 456, "loss": 0.13073161840438843, "lr": 7.190581265067997e-08, "epoch": 3.951541850220264, "percentage": 98.68, "elapsed_time": "3:16:42", "remaining_time": "0:02:37"}
+{"current_steps": 456, "total_steps": 456, "epoch": 4.0, "percentage": 100.0, "elapsed_time": "3:19:05", "remaining_time": "0:00:00"}

qwen3vl-32b/trainer_state.json

@@ -0,0 +1,358 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 456,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0881057268722467,
+      "grad_norm": 0.24635101854801178,
+      "learning_rate": 1.956521739130435e-05,
+      "loss": 0.40406527519226076,
+      "step": 10
+    },
+    {
+      "epoch": 0.1762114537444934,
+      "grad_norm": 0.09084998071193695,
+      "learning_rate": 4.130434782608696e-05,
+      "loss": 0.328407883644104,
+      "step": 20
+    },
+    {
+      "epoch": 0.2643171806167401,
+      "grad_norm": 0.0818253755569458,
+      "learning_rate": 6.304347826086957e-05,
+      "loss": 0.27924346923828125,
+      "step": 30
+    },
+    {
+      "epoch": 0.3524229074889868,
+      "grad_norm": 0.07887422293424606,
+      "learning_rate": 8.478260869565218e-05,
+      "loss": 0.26110143661499025,
+      "step": 40
+    },
+    {
+      "epoch": 0.44052863436123346,
+      "grad_norm": 0.08983754366636276,
+      "learning_rate": 9.998679022482915e-05,
+      "loss": 0.23283846378326417,
+      "step": 50
+    },
+    {
+      "epoch": 0.5286343612334802,
+      "grad_norm": 0.2252996563911438,
+      "learning_rate": 9.975214390089637e-05,
+      "loss": 0.23090167045593263,
+      "step": 60
+    },
+    {
+      "epoch": 0.6167400881057269,
+      "grad_norm": 0.13308356702327728,
+      "learning_rate": 9.922553221348281e-05,
+      "loss": 0.22481226921081543,
+      "step": 70
+    },
+    {
+      "epoch": 0.7048458149779736,
+      "grad_norm": 0.09263544529676437,
+      "learning_rate": 9.841004552936817e-05,
+      "loss": 0.22943453788757323,
+      "step": 80
+    },
+    {
+      "epoch": 0.7929515418502202,
+      "grad_norm": 0.11760010570287704,
+      "learning_rate": 9.731046944867883e-05,
+      "loss": 0.21811044216156006,
+      "step": 90
+    },
+    {
+      "epoch": 0.8810572687224669,
+      "grad_norm": 0.11699206382036209,
+      "learning_rate": 9.593325672108351e-05,
+      "loss": 0.20856730937957763,
+      "step": 100
+    },
+    {
+      "epoch": 0.9691629955947136,
+      "grad_norm": 0.0915595293045044,
+      "learning_rate": 9.428648937849228e-05,
+      "loss": 0.208496618270874,
+      "step": 110
+    },
+    {
+      "epoch": 1.052863436123348,
+      "grad_norm": 0.10526745766401291,
+      "learning_rate": 9.237983130647974e-05,
+      "loss": 0.20336875915527344,
+      "step": 120
+    },
+    {
+      "epoch": 1.1409691629955947,
+      "grad_norm": 0.12514865398406982,
+      "learning_rate": 9.022447153276168e-05,
+      "loss": 0.1991032361984253,
+      "step": 130
+    },
+    {
+      "epoch": 1.2290748898678414,
+      "grad_norm": 0.11038898676633835,
+      "learning_rate": 8.783305856553144e-05,
+      "loss": 0.18334383964538575,
+      "step": 140
+    },
+    {
+      "epoch": 1.3171806167400881,
+      "grad_norm": 0.11036598682403564,
+      "learning_rate": 8.521962616698427e-05,
+      "loss": 0.18828495740890502,
+      "step": 150
+    },
+    {
+      "epoch": 1.4052863436123348,
+      "grad_norm": 0.12819217145442963,
+      "learning_rate": 8.239951099762058e-05,
+      "loss": 0.18282666206359863,
+      "step": 160
+    },
+    {
+      "epoch": 1.4933920704845816,
+      "grad_norm": 0.11140310764312744,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 0.18636636734008788,
+      "step": 170
+    },
+    {
+      "epoch": 1.5814977973568283,
+      "grad_norm": 0.15058451890945435,
+      "learning_rate": 7.620654635247762e-05,
+      "loss": 0.18131622076034545,
+      "step": 180
+    },
+    {
+      "epoch": 1.6696035242290748,
+      "grad_norm": 0.16140812635421753,
+      "learning_rate": 7.287003965576019e-05,
+      "loss": 0.18086057901382446,
+      "step": 190
+    },
+    {
+      "epoch": 1.7577092511013217,
+      "grad_norm": 0.17555318772792816,
+      "learning_rate": 6.939932247247126e-05,
+      "loss": 0.19418610334396363,
+      "step": 200
+    },
+    {
+      "epoch": 1.8458149779735682,
+      "grad_norm": 0.1285424828529358,
+      "learning_rate": 6.581476235111243e-05,
+      "loss": 0.18365358114242553,
+      "step": 210
+    },
+    {
+      "epoch": 1.9339207048458151,
+      "grad_norm": 0.3341018855571747,
+      "learning_rate": 6.213739491581348e-05,
+      "loss": 0.1861007571220398,
+      "step": 220
+    },
+    {
+      "epoch": 2.0176211453744495,
+      "grad_norm": 0.11885173618793488,
+      "learning_rate": 5.8388800420925616e-05,
+      "loss": 0.17953892946243286,
+      "step": 230
+    },
+    {
+      "epoch": 2.105726872246696,
+      "grad_norm": 0.14020124077796936,
+      "learning_rate": 5.459097710950791e-05,
+      "loss": 0.1574479579925537,
+      "step": 240
+    },
+    {
+      "epoch": 2.193832599118943,
+      "grad_norm": 0.16342438757419586,
+      "learning_rate": 5.0766212118889824e-05,
+      "loss": 0.150786828994751,
+      "step": 250
+    },
+    {
+      "epoch": 2.2819383259911894,
+      "grad_norm": 0.17324060201644897,
+      "learning_rate": 4.693695069088724e-05,
+      "loss": 0.1606702446937561,
+      "step": 260
+    },
+    {
+      "epoch": 2.3700440528634363,
+      "grad_norm": 0.18001990020275116,
+      "learning_rate": 4.312566445419853e-05,
+      "loss": 0.15859190225601197,
+      "step": 270
+    },
+    {
+      "epoch": 2.458149779735683,
+      "grad_norm": 0.15309368073940277,
+      "learning_rate": 3.935471955195196e-05,
+      "loss": 0.15953269004821777,
+      "step": 280
+    },
+    {
+      "epoch": 2.5462555066079293,
+      "grad_norm": 0.1476765125989914,
+      "learning_rate": 3.5646245388284213e-05,
+      "loss": 0.15785973072052,
+      "step": 290
+    },
+    {
+      "epoch": 2.6343612334801763,
+      "grad_norm": 0.15916526317596436,
+      "learning_rate": 3.202200476419761e-05,
+      "loss": 0.1512267470359802,
+      "step": 300
+    },
+    {
+      "epoch": 2.7224669603524227,
+      "grad_norm": 0.1706741899251938,
+      "learning_rate": 2.8503266164790232e-05,
+      "loss": 0.15540086030960082,
+      "step": 310
+    },
+    {
+      "epoch": 2.8105726872246697,
+      "grad_norm": 0.19981999695301056,
+      "learning_rate": 2.5110678947328302e-05,
+      "loss": 0.1461609721183777,
+      "step": 320
+    },
+    {
+      "epoch": 2.898678414096916,
+      "grad_norm": 0.451761394739151,
+      "learning_rate": 2.1864152162606882e-05,
+      "loss": 0.15680785179138185,
+      "step": 330
+    },
+    {
+      "epoch": 2.986784140969163,
+      "grad_norm": 0.1608363687992096,
+      "learning_rate": 1.878273772072332e-05,
+      "loss": 0.14546056985855102,
+      "step": 340
+    },
+    {
+      "epoch": 3.0704845814977975,
+      "grad_norm": 0.15605859458446503,
+      "learning_rate": 1.5884518586893187e-05,
+      "loss": 0.14447916746139527,
+      "step": 350
+    },
+    {
+      "epoch": 3.158590308370044,
+      "grad_norm": 0.19301344454288483,
+      "learning_rate": 1.3186502663419986e-05,
+      "loss": 0.12820364236831666,
+      "step": 360
+    },
+    {
+      "epoch": 3.246696035242291,
+      "grad_norm": 0.19631513953208923,
+      "learning_rate": 1.0704522980561533e-05,
+      "loss": 0.13617411851882935,
+      "step": 370
+    },
+    {
+      "epoch": 3.3348017621145374,
+      "grad_norm": 0.18359704315662384,
+      "learning_rate": 8.453144782012639e-06,
+      "loss": 0.1336129426956177,
+      "step": 380
+    },
+    {
+      "epoch": 3.4229074889867843,
+      "grad_norm": 0.1820751428604126,
+      "learning_rate": 6.445580050263611e-06,
+      "loss": 0.12256991863250732,
+      "step": 390
+    },
+    {
+      "epoch": 3.511013215859031,
+      "grad_norm": 0.1921098530292511,
+      "learning_rate": 4.69360997343335e-06,
+      "loss": 0.12970975637435914,
+      "step": 400
+    },
+    {
+      "epoch": 3.5991189427312777,
+      "grad_norm": 0.1958039402961731,
+      "learning_rate": 3.207515808572975e-06,
+      "loss": 0.13449277877807617,
+      "step": 410
+    },
+    {
+      "epoch": 3.6872246696035242,
+      "grad_norm": 0.17784155905246735,
+      "learning_rate": 1.996018547161266e-06,
+      "loss": 0.12987757921218873,
+      "step": 420
+    },
+    {
+      "epoch": 3.7753303964757707,
+      "grad_norm": 0.17358048260211945,
+      "learning_rate": 1.0662277368588824e-06,
+      "loss": 0.12816166877746582,
+      "step": 430
+    },
+    {
+      "epoch": 3.8634361233480177,
+      "grad_norm": 0.17493271827697754,
+      "learning_rate": 4.2359975985574175e-07,
+      "loss": 0.12196211814880371,
+      "step": 440
+    },
+    {
+      "epoch": 3.951541850220264,
+      "grad_norm": 0.16413936018943787,
+      "learning_rate": 7.190581265067997e-08,
+      "loss": 0.13073161840438843,
+      "step": 450
+    },
+    {
+      "epoch": 4.0,
+      "step": 456,
+      "total_flos": 3.529283513966947e+18,
+      "train_loss": 0.18179457177195632,
+      "train_runtime": 11945.8456,
+      "train_samples_per_second": 0.608,
+      "train_steps_per_second": 0.038
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 456,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.529283513966947e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

qwen3vl-32b/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86402750f6cc0988c8e8998a917480ce314a332171f3d30a4d5f9da91c78ec3c
+size 5649