Add designcoder_qwen3.8_27b_adamw_bs128_data41287_step400 (bench-200: 91.19, strongest in release)

.gitattributes

@@ -42,3 +42,4 @@ designcoder_qwen3.6_27b_adamw_bs32_step1900_r2/tokenizer.json filter=lfs diff=lf
 designcoder_qwen3.5_4b_adamw_bs256_data41287_step200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 designcoder_qwen3.5_4b_muon_bs256_data41287_step200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 designcoder_qwen3.5_9b_adamw_bs256_data41287_step200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+designcoder_qwen3.8_27b_adamw_bs128_data41287_step400/tokenizer.json filter=lfs diff=lfs merge=lfs -text

designcoder_qwen3.8_27b_adamw_bs128_data41287_step400/README.md

@@ -0,0 +1,73 @@
+---
+license: apache-2.0
+base_model: Qwen/Qwen3.8-27B
+tags:
+- designcoder
+- ui-generation
+- front-end
+- sft
+language:
+- en
+---
+
+# DesignCoder v2 - 27B (AdamW, step 400)
+
+Supervised fine-tune of **Qwen3.8-27B** for design-to-code generation (landing pages and
+dashboards) from the DesignCoder v2 agent trajectories.
+
+## Training
+
+| Field | Value |
+|---|---|
+| Base model | `Qwen/Qwen3.8-27B` |
+| Dataset | `designcoder_sft_v2_train` — **41,287 samples** (`data41287`) |
+| Optimizer | AdamW |
+| Learning rate | 1.0e-5 |
+| Global batch size | 128 |
+| Exported step | 400 |
+| Epoch at export | 1.51 |
+| Hardware | 8 nodes x 8 H20 |
+| Source run | `designcoder_v2_27b_qwen38_newdata_8n64g_20260917_0228/checkpoint-400` |
+
+> **Dataset note:** this checkpoint is trained on the **41,287-sample** revision
+> (`ckpt_data41287`). The earlier checkpoints in this repository (`*_step1900`,
+> `*_step3800`) come from the **37,865-sample** revision (`ckpt_data37865`) and are
+> *not* directly comparable.
+
+## Benchmark
+
+Evaluated on the frozen 200-case DesignCoder bench (`bench_data/test-prompts-200.jsonl`
++ `test-rubrics-200.jsonl`). Every rubric item is a binary screenshot check, judged by a
+vision model over full-page screenshots; the score is the unweighted mean of Prompt Fit
+and the six rubric dimensions.
+
+**Score: 91.19**
+
+Strongest checkpoint in this release (+10 over 9B on the same subset).
+
+### Why this step and not the last one
+
+Checkpoint selection was done by running the benchmark, not by picking the lowest
+training loss. Across all four runs in this release the best checkpoint sits at roughly
+75% of training, and loss kept decreasing while benchmark scores fell. The most extreme
+case: 4B AdamW loss improved from 0.2696 (step 200) to 0.2682 (step 266) while its score
+collapsed from 84.22 to 68.35.
+
+## Usage
+
+The model is trained as a tool-using agent. Each case runs
+`design_search` -> (`websearch`, landing only) -> a final answer with exactly three code
+blocks in this order: `html`, `css`, `js`. Reproduce the system prompts and tool
+observation format from `examples/designcoder/runtime/infer_designcoder.py`; feeding a
+bare instruction without the tool turns will not match the training distribution.
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+repo = "xingxm/DesignCoder"
+sub = "designcoder_qwen3.8_27b_adamw_bs128_data41287_step400"
+tok = AutoTokenizer.from_pretrained(repo, subfolder=sub)
+model = AutoModelForCausalLM.from_pretrained(
+    repo, subfolder=sub, dtype="bfloat16", device_map="auto"
+)
+```

designcoder_qwen3.8_27b_adamw_bs128_data41287_step400/chat_template.jinja

@@ -0,0 +1,170 @@
+{%- 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 reasoning_instructions = '' %}
+{%- if enable_thinking is undefined or enable_thinking is true %}
+    {%- set resolved_reasoning_effort = reasoning_effort|default('xhigh') %}
+    {%- 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 messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {%- if content %}
+            {{- '\n\n' + content }}
+        {%- endif %}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {%- if content %}
+            {{- '<|im_start|>system\n' + (reasoning_instructions + '\n\n' if reasoning_instructions else '')  + content + '<|im_end|>\n' }}
+        {%- elif reasoning_instructions %}
+            {{- '<|im_start|>system\n' + reasoning_instructions + '<|im_end|>\n' }}
+        {%- endif %}
+    {%- 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 %}
+{%- if ns.multi_step_tool %}
+    {{- raise_exception('No user query found in messages.') }}
+{%- endif %}
+{%- for message in messages %}
+    {%- set content = render_content(message.content, true)|trim %}
+    {%- if message.role == "system" %}
+        {%- if not loop.first %}
+            {{- raise_exception('System message must be at the beginning.') }}
+        {%- endif %}
+    {%- elif message.role == "user" %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- 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 loop.first %}
+                    {%- if content|trim %}
+                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- else %}
+                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- endif %}
+                {%- else %}
+                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                {%- endif %}
+                {%- if tool_call.arguments is defined and tool_call.arguments != '' %}
+                    {%- 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 %}
+                {%- endif %}
+                {{- '</function>\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- else %}
+        {{- raise_exception('Unexpected message role.') }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- else %}
+        {{- '<think>\n' }}
+    {%- endif %}
+{%- endif %}

designcoder_qwen3.8_27b_adamw_bs128_data41287_step400/config.json

@@ -0,0 +1,147 @@
+{
+  "architectures": [
+    "Qwen3_5ForConditionalGeneration"
+  ],
+  "bos_token_id": null,
+  "dtype": "bfloat16",
+  "eos_token_id": 248046,
+  "hidden_size": 5120,
+  "image_token_id": 248056,
+  "language_model_only": false,
+  "model_type": "qwen3_5",
+  "pad_token_id": 248044,
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attn_output_gate": true,
+    "bos_token_id": 248044,
+    "dtype": "bfloat16",
+    "eos_token_id": 248044,
+    "full_attention_interval": 4,
+    "head_dim": 256,
+    "hidden_act": "silu",
+    "hidden_size": 5120,
+    "initializer_range": 0.02,
+    "intermediate_size": 17408,
+    "layer_types": [
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention"
+    ],
+    "linear_conv_kernel_dim": 4,
+    "linear_key_head_dim": 128,
+    "linear_num_key_heads": 16,
+    "linear_num_value_heads": 48,
+    "linear_value_head_dim": 128,
+    "mamba_ssm_dtype": "float32",
+    "max_position_embeddings": 262144,
+    "model_type": "qwen3_5_text",
+    "mtp_num_hidden_layers": 1,
+    "mtp_use_dedicated_embeddings": false,
+    "num_attention_heads": 24,
+    "num_hidden_layers": 64,
+    "num_key_value_heads": 4,
+    "output_gate_type": "swish",
+    "pad_token_id": null,
+    "partial_rotary_factor": 0.25,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "mrope_interleaved": true,
+      "mrope_section": [
+        11,
+        11,
+        10
+      ],
+      "partial_rotary_factor": 0.25,
+      "rope_theta": 10000000,
+      "rope_type": "default"
+    },
+    "tie_word_embeddings": false,
+    "use_cache": false,
+    "vocab_size": 248320
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.8.0",
+  "use_cache": false,
+  "video_token_id": 248057,
+  "vision_config": {
+    "deepstack_visual_indexes": [],
+    "depth": 27,
+    "dtype": "bfloat16",
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 4304,
+    "model_type": "qwen3_5_vision",
+    "num_heads": 16,
+    "num_position_embeddings": 2304,
+    "out_hidden_size": 5120,
+    "patch_size": 16,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2
+  },
+  "vision_end_token_id": 248054,
+  "vision_start_token_id": 248053
+}

designcoder_qwen3.8_27b_adamw_bs128_data41287_step400/generation_config.json

@@ -0,0 +1,13 @@
+{
+  "do_sample": true,
+  "eos_token_id": [
+    248046,
+    248046,
+    248044
+  ],
+  "pad_token_id": 248044,
+  "temperature": 1.0,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "5.8.0"
+}

designcoder_qwen3.8_27b_adamw_bs128_data41287_step400/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3896fe78fb0acedf991083d47ce1cf47081686db6ddb78c3dad5ae651168a7d2
+size 49825162976

designcoder_qwen3.8_27b_adamw_bs128_data41287_step400/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8b87c6756f5f3eddf7ca739d06cd4c340fcdc4ac463e20bda5b31b169cc1552
+size 4888445168

designcoder_qwen3.8_27b_adamw_bs128_data41287_step400/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"
+  }
+}

designcoder_qwen3.8_27b_adamw_bs128_data41287_step400/tokenizer.json

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

designcoder_qwen3.8_27b_adamw_bs128_data41287_step400/tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "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": false,
+  "model_max_length": 262144,
+  "model_specific_special_tokens": {
+    "audio_bos_token": "<|audio_start|>",
+    "audio_eos_token": "<|audio_end|>",
+    "audio_token": "<|audio_pad|>",
+    "image_token": "<|image_pad|>",
+    "video_token": "<|video_pad|>",
+    "vision_bos_token": "<|vision_start|>",
+    "vision_eos_token": "<|vision_end|>"
+  },
+  "pad_token": "<|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|>"
+}

designcoder_qwen3.8_27b_adamw_bs128_data41287_step400/trainer_log.jsonl

@@ -0,0 +1,27 @@
+{"current_steps": 20, "total_steps": 530, "loss": 0.32881975173950195, "lr": 3.5849056603773586e-06, "epoch": 0.07561436672967864, "percentage": 3.77, "elapsed_time": "0:44:47", "remaining_time": "19:02:13"}
+{"current_steps": 40, "total_steps": 530, "loss": 0.2864610910415649, "lr": 7.358490566037736e-06, "epoch": 0.15122873345935728, "percentage": 7.55, "elapsed_time": "1:27:00", "remaining_time": "17:45:47"}
+{"current_steps": 60, "total_steps": 530, "loss": 0.26258695125579834, "lr": 9.99609654676786e-06, "epoch": 0.22684310018903592, "percentage": 11.32, "elapsed_time": "2:09:28", "remaining_time": "16:54:13"}
+{"current_steps": 80, "total_steps": 530, "loss": 0.24955542087554933, "lr": 9.92687124249773e-06, "epoch": 0.30245746691871456, "percentage": 15.09, "elapsed_time": "2:51:48", "remaining_time": "16:06:23"}
+{"current_steps": 100, "total_steps": 530, "loss": 0.24457950592041017, "lr": 9.772283630189727e-06, "epoch": 0.3780718336483932, "percentage": 18.87, "elapsed_time": "3:33:59", "remaining_time": "15:20:09"}
+{"current_steps": 120, "total_steps": 530, "loss": 0.24043033123016358, "lr": 9.535012074008688e-06, "epoch": 0.45368620037807184, "percentage": 22.64, "elapsed_time": "4:16:14", "remaining_time": "14:35:28"}
+{"current_steps": 140, "total_steps": 530, "loss": 0.23635098934173585, "lr": 9.219167509002526e-06, "epoch": 0.5293005671077504, "percentage": 26.42, "elapsed_time": "4:58:40", "remaining_time": "13:52:00"}
+{"current_steps": 160, "total_steps": 530, "loss": 0.23346784114837646, "lr": 8.83022221559489e-06, "epoch": 0.6049149338374291, "percentage": 30.19, "elapsed_time": "5:41:05", "remaining_time": "13:08:46"}
+{"current_steps": 180, "total_steps": 530, "loss": 0.2315444231033325, "lr": 8.374915007591053e-06, "epoch": 0.6805293005671077, "percentage": 33.96, "elapsed_time": "6:23:29", "remaining_time": "12:25:39"}
+{"current_steps": 200, "total_steps": 530, "loss": 0.2285059690475464, "lr": 7.861134476396903e-06, "epoch": 0.7561436672967864, "percentage": 37.74, "elapsed_time": "7:05:46", "remaining_time": "11:42:31"}
+{"current_steps": 220, "total_steps": 530, "loss": 0.22735247611999512, "lr": 7.297782314345972e-06, "epoch": 0.831758034026465, "percentage": 41.51, "elapsed_time": "7:48:05", "remaining_time": "10:59:35"}
+{"current_steps": 240, "total_steps": 530, "loss": 0.2246119737625122, "lr": 6.694619085176159e-06, "epoch": 0.9073724007561437, "percentage": 45.28, "elapsed_time": "8:30:30", "remaining_time": "10:16:51"}
+{"current_steps": 260, "total_steps": 530, "loss": 0.22438063621520996, "lr": 6.062095113816069e-06, "epoch": 0.9829867674858223, "percentage": 49.06, "elapsed_time": "9:12:50", "remaining_time": "9:34:05"}
+{"current_steps": 280, "total_steps": 530, "loss": 0.21316697597503662, "lr": 5.411169425461822e-06, "epoch": 1.056710775047259, "percentage": 52.83, "elapsed_time": "9:54:03", "remaining_time": "8:50:24"}
+{"current_steps": 300, "total_steps": 530, "loss": 0.2103102684020996, "lr": 4.753119870981486e-06, "epoch": 1.1323251417769375, "percentage": 56.6, "elapsed_time": "10:36:34", "remaining_time": "8:08:02"}
+{"current_steps": 320, "total_steps": 530, "loss": 0.20908036231994628, "lr": 4.0993477283888264e-06, "epoch": 1.2079395085066162, "percentage": 60.38, "elapsed_time": "11:18:56", "remaining_time": "7:25:33"}
+{"current_steps": 340, "total_steps": 530, "loss": 0.20854945182800294, "lr": 3.46118016583494e-06, "epoch": 1.283553875236295, "percentage": 64.15, "elapsed_time": "12:01:10", "remaining_time": "6:43:00"}
+{"current_steps": 360, "total_steps": 530, "loss": 0.2070488691329956, "lr": 2.8496739886173994e-06, "epoch": 1.3591682419659734, "percentage": 67.92, "elapsed_time": "12:43:30", "remaining_time": "6:00:32"}
+{"current_steps": 380, "total_steps": 530, "loss": 0.20638427734375, "lr": 2.275424070459803e-06, "epoch": 1.434782608695652, "percentage": 71.7, "elapsed_time": "13:25:53", "remaining_time": "5:18:06"}
+{"current_steps": 400, "total_steps": 530, "loss": 0.20667724609375, "lr": 1.7483797881556175e-06, "epoch": 1.5103969754253308, "percentage": 75.47, "elapsed_time": "14:08:22", "remaining_time": "4:35:43"}
+{"current_steps": 420, "total_steps": 530, "loss": 0.2058406114578247, "lr": 1.277672640004936e-06, "epoch": 1.5860113421550095, "percentage": 79.25, "elapsed_time": "14:55:42", "remaining_time": "3:54:35"}
+{"current_steps": 440, "total_steps": 530, "loss": 0.20571742057800294, "lr": 8.714580347039491e-07, "epoch": 1.6616257088846882, "percentage": 83.02, "elapsed_time": "15:38:01", "remaining_time": "3:11:52"}
+{"current_steps": 460, "total_steps": 530, "loss": 0.20586738586425782, "lr": 5.367739918315068e-07, "epoch": 1.7372400756143667, "percentage": 86.79, "elapsed_time": "16:20:27", "remaining_time": "2:29:12"}
+{"current_steps": 480, "total_steps": 530, "loss": 0.20640807151794432, "lr": 2.7941920206915443e-07, "epoch": 1.8128544423440454, "percentage": 90.57, "elapsed_time": "17:02:43", "remaining_time": "1:46:32"}
+{"current_steps": 500, "total_steps": 530, "loss": 0.20689654350280762, "lr": 1.0385255986682718e-07, "epoch": 1.888468809073724, "percentage": 94.34, "elapsed_time": "17:45:14", "remaining_time": "1:03:54"}
+{"current_steps": 520, "total_steps": 530, "loss": 0.2059170961380005, "lr": 1.3115909237734203e-08, "epoch": 1.9640831758034025, "percentage": 98.11, "elapsed_time": "18:27:43", "remaining_time": "0:21:18"}
+{"current_steps": 530, "total_steps": 530, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "18:52:41", "remaining_time": "0:00:00"}

designcoder_qwen3.8_27b_adamw_bs128_data41287_step400/trainer_state.json

@@ -0,0 +1,174 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.5103969754253308,
+  "eval_steps": 500,
+  "global_step": 400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.07561436672967864,
+      "grad_norm": 0.438688559712995,
+      "learning_rate": 3.5849056603773586e-06,
+      "loss": 0.32881975173950195,
+      "step": 20
+    },
+    {
+      "epoch": 0.15122873345935728,
+      "grad_norm": 0.26188054914423636,
+      "learning_rate": 7.358490566037736e-06,
+      "loss": 0.2864610910415649,
+      "step": 40
+    },
+    {
+      "epoch": 0.22684310018903592,
+      "grad_norm": 0.19747259082184018,
+      "learning_rate": 9.99609654676786e-06,
+      "loss": 0.26258695125579834,
+      "step": 60
+    },
+    {
+      "epoch": 0.30245746691871456,
+      "grad_norm": 0.20162042813979253,
+      "learning_rate": 9.92687124249773e-06,
+      "loss": 0.24955542087554933,
+      "step": 80
+    },
+    {
+      "epoch": 0.3780718336483932,
+      "grad_norm": 0.2201760211691365,
+      "learning_rate": 9.772283630189727e-06,
+      "loss": 0.24457950592041017,
+      "step": 100
+    },
+    {
+      "epoch": 0.45368620037807184,
+      "grad_norm": 0.24687833355840075,
+      "learning_rate": 9.535012074008688e-06,
+      "loss": 0.24043033123016358,
+      "step": 120
+    },
+    {
+      "epoch": 0.5293005671077504,
+      "grad_norm": 0.20426757729854475,
+      "learning_rate": 9.219167509002526e-06,
+      "loss": 0.23635098934173585,
+      "step": 140
+    },
+    {
+      "epoch": 0.6049149338374291,
+      "grad_norm": 0.19826035580661108,
+      "learning_rate": 8.83022221559489e-06,
+      "loss": 0.23346784114837646,
+      "step": 160
+    },
+    {
+      "epoch": 0.6805293005671077,
+      "grad_norm": 1.543676430006464,
+      "learning_rate": 8.374915007591053e-06,
+      "loss": 0.2315444231033325,
+      "step": 180
+    },
+    {
+      "epoch": 0.7561436672967864,
+      "grad_norm": 0.172012105399833,
+      "learning_rate": 7.861134476396903e-06,
+      "loss": 0.2285059690475464,
+      "step": 200
+    },
+    {
+      "epoch": 0.831758034026465,
+      "grad_norm": 0.18799022262823806,
+      "learning_rate": 7.297782314345972e-06,
+      "loss": 0.22735247611999512,
+      "step": 220
+    },
+    {
+      "epoch": 0.9073724007561437,
+      "grad_norm": 0.21107031510244956,
+      "learning_rate": 6.694619085176159e-06,
+      "loss": 0.2246119737625122,
+      "step": 240
+    },
+    {
+      "epoch": 0.9829867674858223,
+      "grad_norm": 0.23034246682096834,
+      "learning_rate": 6.062095113816069e-06,
+      "loss": 0.22438063621520996,
+      "step": 260
+    },
+    {
+      "epoch": 1.056710775047259,
+      "grad_norm": 0.21596770970128068,
+      "learning_rate": 5.411169425461822e-06,
+      "loss": 0.21316697597503662,
+      "step": 280
+    },
+    {
+      "epoch": 1.1323251417769375,
+      "grad_norm": 0.19025452942157067,
+      "learning_rate": 4.753119870981486e-06,
+      "loss": 0.2103102684020996,
+      "step": 300
+    },
+    {
+      "epoch": 1.2079395085066162,
+      "grad_norm": 0.17938436574500397,
+      "learning_rate": 4.0993477283888264e-06,
+      "loss": 0.20908036231994628,
+      "step": 320
+    },
+    {
+      "epoch": 1.283553875236295,
+      "grad_norm": 0.2933161689615977,
+      "learning_rate": 3.46118016583494e-06,
+      "loss": 0.20854945182800294,
+      "step": 340
+    },
+    {
+      "epoch": 1.3591682419659734,
+      "grad_norm": 0.1899593498390556,
+      "learning_rate": 2.8496739886173994e-06,
+      "loss": 0.2070488691329956,
+      "step": 360
+    },
+    {
+      "epoch": 1.434782608695652,
+      "grad_norm": 0.1620339039368721,
+      "learning_rate": 2.275424070459803e-06,
+      "loss": 0.20638427734375,
+      "step": 380
+    },
+    {
+      "epoch": 1.5103969754253308,
+      "grad_norm": 0.1664725209694028,
+      "learning_rate": 1.7483797881556175e-06,
+      "loss": 0.20667724609375,
+      "step": 400
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 530,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 400,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.427951752883995e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}