Add designcoder_qwen3.5_4b_adamw_bs256_data41287_step200 (bench-200: 84.22)

.gitattributes

@@ -39,3 +39,4 @@ designcoder_qwen3.5_9b_muon_bs16_step3800/tokenizer.json filter=lfs diff=lfs mer
 designcoder_qwen3.5_9b_adamw_bs16_ep20_step38000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 designcoder_qwen3.6_27b_adamw_bs32_step1900/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 designcoder_qwen3.6_27b_adamw_bs32_step1900_r2/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+designcoder_qwen3.5_4b_adamw_bs256_data41287_step200/tokenizer.json filter=lfs diff=lfs merge=lfs -text

designcoder_qwen3.5_4b_adamw_bs256_data41287_step200/README.md

@@ -0,0 +1,73 @@
+---
+license: apache-2.0
+base_model: Qwen/Qwen3.5-4B
+tags:
+- designcoder
+- ui-generation
+- front-end
+- sft
+language:
+- en
+---
+
+# DesignCoder v2 - 4B (AdamW, step 200)
+
+Supervised fine-tune of **Qwen3.5-4B** for design-to-code generation (landing pages and
+dashboards) from the DesignCoder v2 agent trajectories.
+
+## Training
+
+| Field | Value |
+|---|---|
+| Base model | `Qwen/Qwen3.5-4B` |
+| Dataset | `designcoder_sft_v2_train` — **41,287 samples** (`data41287`) |
+| Optimizer | AdamW |
+| Learning rate | 2.0e-5 |
+| Global batch size | 256 |
+| Exported step | 200 |
+| Epoch at export | 1.51 |
+| Hardware | 8 nodes x 8 H20 |
+| Source run | `designcoder_v2_4b_newdata_8n64g_20260918_1039/checkpoint-200` |
+
+> **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: 84.22**
+
+Best 4B checkpoint under AdamW on this dataset.
+
+### 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_qwen3.5_4b_adamw_bs256_data41287_step200"
+tok = AutoTokenizer.from_pretrained(repo, subfolder=sub)
+model = AutoModelForCausalLM.from_pretrained(
+    repo, subfolder=sub, dtype="bfloat16", device_map="auto"
+)
+```

designcoder_qwen3.5_4b_adamw_bs256_data41287_step200/chat_template.jinja

@@ -0,0 +1,154 @@
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- macro render_content(content, do_vision_count, is_system_content=false) %}
+    {%- if content is string %}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping %}
+        {%- for item in content %}
+            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain images.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Picture ' ~ image_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
+            {%- elif 'video' in item or item.type == 'video' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain videos.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Video ' ~ video_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
+            {%- elif 'text' in item %}
+                {{- item.text }}
+            {%- else %}
+                {{- raise_exception('Unexpected item type in content.') }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif content is none or content is undefined %}
+        {{- '' }}
+    {%- else %}
+        {{- raise_exception('Unexpected content type.') }}
+    {%- endif %}
+{%- endmacro %}
+{%- if not messages %}
+    {{- raise_exception('No messages provided.') }}
+{%- endif %}
+{%- if tools and tools is iterable and tools is not mapping %}
+    {{- '<|im_start|>system\n' }}
+    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>" }}
+    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {%- if content %}
+            {{- '\n\n' + content }}
+        {%- endif %}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" %}
+        {%- set content = render_content(message.content, false)|trim %}
+        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
+            {%- set ns.multi_step_tool = false %}
+            {%- set ns.last_query_index = index %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if ns.multi_step_tool %}
+    {{- raise_exception('No user query found in messages.') }}
+{%- endif %}
+{%- for message in messages %}
+    {%- set content = render_content(message.content, true)|trim %}
+    {%- if message.role == "system" %}
+        {%- if not loop.first %}
+            {{- raise_exception('System message must be at the beginning.') }}
+        {%- endif %}
+    {%- elif message.role == "user" %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- set reasoning_content = reasoning_content|trim %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if tool_call.function is defined %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {%- if loop.first %}
+                    {%- if content|trim %}
+                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- else %}
+                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- endif %}
+                {%- else %}
+                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                {%- endif %}
+                {%- if tool_call.arguments is defined %}
+                    {%- for args_name, args_value in tool_call.arguments|items %}
+                        {{- '<parameter=' + args_name + '>\n' }}
+                        {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
+                        {{- args_value }}
+                        {{- '\n</parameter>\n' }}
+                    {%- endfor %}
+                {%- endif %}
+                {{- '</function>\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- else %}
+        {{- raise_exception('Unexpected message role.') }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- else %}
+        {{- '<think>\n' }}
+    {%- endif %}
+{%- endif %}

designcoder_qwen3.5_4b_adamw_bs256_data41287_step200/config.json

@@ -0,0 +1,113 @@
+{
+  "architectures": [
+    "Qwen3_5ForConditionalGeneration"
+  ],
+  "dtype": "bfloat16",
+  "eos_token_id": 248046,
+  "hidden_size": 2560,
+  "image_token_id": 248056,
+  "model_type": "qwen3_5",
+  "pad_token_id": 248044,
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attn_output_gate": true,
+    "bos_token_id": null,
+    "dtype": "bfloat16",
+    "eos_token_id": 248044,
+    "full_attention_interval": 4,
+    "head_dim": 256,
+    "hidden_act": "silu",
+    "hidden_size": 2560,
+    "initializer_range": 0.02,
+    "intermediate_size": 9216,
+    "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_conv_kernel_dim": 4,
+    "linear_key_head_dim": 128,
+    "linear_num_key_heads": 16,
+    "linear_num_value_heads": 32,
+    "linear_value_head_dim": 128,
+    "mamba_ssm_dtype": "float32",
+    "max_position_embeddings": 262144,
+    "mlp_only_layers": [],
+    "model_type": "qwen3_5_text",
+    "mtp_num_hidden_layers": 1,
+    "mtp_use_dedicated_embeddings": false,
+    "num_attention_heads": 16,
+    "num_hidden_layers": 32,
+    "num_key_value_heads": 4,
+    "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": true,
+    "use_cache": false,
+    "vocab_size": 248320
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.8.0",
+  "use_cache": false,
+  "video_token_id": 248057,
+  "vision_config": {
+    "deepstack_visual_indexes": [],
+    "depth": 24,
+    "dtype": "bfloat16",
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1024,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "model_type": "qwen3_5_vision",
+    "num_heads": 16,
+    "num_position_embeddings": 2304,
+    "out_hidden_size": 2560,
+    "patch_size": 16,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2
+  },
+  "vision_end_token_id": 248054,
+  "vision_start_token_id": 248053
+}

designcoder_qwen3.5_4b_adamw_bs256_data41287_step200/generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": [
+    248046,
+    248044
+  ],
+  "pad_token_id": 248044,
+  "transformers_version": "5.8.0",
+  "use_cache": true
+}

designcoder_qwen3.5_4b_adamw_bs256_data41287_step200/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9216d2612b2d8fcc0f5ad81c1ff8ff891c3564bbe93a1672104a2a44b43061c
+size 9078620536

designcoder_qwen3.5_4b_adamw_bs256_data41287_step200/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_qwen3.5_4b_adamw_bs256_data41287_step200/tokenizer.json

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

designcoder_qwen3.5_4b_adamw_bs256_data41287_step200/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_qwen3.5_4b_adamw_bs256_data41287_step200/trainer_log.jsonl

@@ -0,0 +1,27 @@
+{"current_steps": 10, "total_steps": 266, "loss": 0.5404598236083984, "lr": 6.666666666666667e-06, "epoch": 0.07561436672967864, "percentage": 3.76, "elapsed_time": "0:09:25", "remaining_time": "4:01:28"}
+{"current_steps": 20, "total_steps": 266, "loss": 0.4467557430267334, "lr": 1.4074074074074075e-05, "epoch": 0.15122873345935728, "percentage": 7.52, "elapsed_time": "0:18:17", "remaining_time": "3:44:55"}
+{"current_steps": 30, "total_steps": 266, "loss": 0.3936758041381836, "lr": 1.999654451568528e-05, "epoch": 0.22684310018903592, "percentage": 11.28, "elapsed_time": "0:27:13", "remaining_time": "3:34:11"}
+{"current_steps": 40, "total_steps": 266, "loss": 0.3615268707275391, "lr": 1.987585312769669e-05, "epoch": 0.30245746691871456, "percentage": 15.04, "elapsed_time": "0:36:11", "remaining_time": "3:24:28"}
+{"current_steps": 50, "total_steps": 266, "loss": 0.34326627254486086, "lr": 1.9584768190468624e-05, "epoch": 0.3780718336483932, "percentage": 18.8, "elapsed_time": "0:45:03", "remaining_time": "3:14:40"}
+{"current_steps": 60, "total_steps": 266, "loss": 0.33113551139831543, "lr": 1.912831195321268e-05, "epoch": 0.45368620037807184, "percentage": 22.56, "elapsed_time": "0:53:55", "remaining_time": "3:05:09"}
+{"current_steps": 70, "total_steps": 266, "loss": 0.32063558101654055, "lr": 1.8514359907527693e-05, "epoch": 0.5293005671077504, "percentage": 26.32, "elapsed_time": "1:02:51", "remaining_time": "2:56:01"}
+{"current_steps": 80, "total_steps": 266, "loss": 0.3131831169128418, "lr": 1.7753504907192923e-05, "epoch": 0.6049149338374291, "percentage": 30.08, "elapsed_time": "1:11:49", "remaining_time": "2:47:00"}
+{"current_steps": 90, "total_steps": 266, "loss": 0.3076876878738403, "lr": 1.6858874403810507e-05, "epoch": 0.6805293005671077, "percentage": 33.83, "elapsed_time": "1:20:45", "remaining_time": "2:37:55"}
+{"current_steps": 100, "total_steps": 266, "loss": 0.30152087211608886, "lr": 1.584590395163162e-05, "epoch": 0.7561436672967864, "percentage": 37.59, "elapsed_time": "1:29:39", "remaining_time": "2:28:50"}
+{"current_steps": 110, "total_steps": 266, "loss": 0.29860482215881345, "lr": 1.4732070889412693e-05, "epoch": 0.831758034026465, "percentage": 41.35, "elapsed_time": "1:39:35", "remaining_time": "2:21:14"}
+{"current_steps": 120, "total_steps": 266, "loss": 0.2935622692108154, "lr": 1.3536592794235696e-05, "epoch": 0.9073724007561437, "percentage": 45.11, "elapsed_time": "1:48:30", "remaining_time": "2:12:00"}
+{"current_steps": 130, "total_steps": 266, "loss": 0.29182274341583253, "lr": 1.2280095910035343e-05, "epoch": 0.9829867674858223, "percentage": 48.87, "elapsed_time": "1:57:26", "remaining_time": "2:02:52"}
+{"current_steps": 140, "total_steps": 266, "loss": 0.2805715322494507, "lr": 1.0984259271618947e-05, "epoch": 1.052930056710775, "percentage": 52.63, "elapsed_time": "2:05:42", "remaining_time": "1:53:07"}
+{"current_steps": 150, "total_steps": 266, "loss": 0.27776541709899905, "lr": 9.671440664303813e-06, "epoch": 1.1285444234404536, "percentage": 56.39, "elapsed_time": "2:14:37", "remaining_time": "1:44:06"}
+{"current_steps": 160, "total_steps": 266, "loss": 0.27518510818481445, "lr": 8.364290872697175e-06, "epoch": 1.2041587901701323, "percentage": 60.15, "elapsed_time": "2:23:33", "remaining_time": "1:35:06"}
+{"current_steps": 170, "total_steps": 266, "loss": 0.27352917194366455, "lr": 7.08536287419749e-06, "epoch": 1.279773156899811, "percentage": 63.91, "elapsed_time": "2:32:29", "remaining_time": "1:26:06"}
+{"current_steps": 180, "total_steps": 266, "loss": 0.271071720123291, "lr": 5.8567227200175865e-06, "epoch": 1.3553875236294897, "percentage": 67.67, "elapsed_time": "2:41:23", "remaining_time": "1:17:06"}
+{"current_steps": 190, "total_steps": 266, "loss": 0.27093987464904784, "lr": 4.699568817414224e-06, "epoch": 1.4310018903591684, "percentage": 71.43, "elapsed_time": "2:50:17", "remaining_time": "1:08:06"}
+{"current_steps": 200, "total_steps": 266, "loss": 0.26956160068511964, "lr": 3.63386618185811e-06, "epoch": 1.5066162570888468, "percentage": 75.19, "elapsed_time": "2:59:14", "remaining_time": "0:59:08"}
+{"current_steps": 210, "total_steps": 266, "loss": 0.2693511962890625, "lr": 2.678001969593701e-06, "epoch": 1.5822306238185255, "percentage": 78.95, "elapsed_time": "3:09:16", "remaining_time": "0:50:28"}
+{"current_steps": 220, "total_steps": 266, "loss": 0.26824145317077636, "lr": 1.8484682338758154e-06, "epoch": 1.6578449905482042, "percentage": 82.71, "elapsed_time": "3:18:12", "remaining_time": "0:41:26"}
+{"current_steps": 230, "total_steps": 266, "loss": 0.2690474033355713, "lr": 1.159577378464939e-06, "epoch": 1.7334593572778827, "percentage": 86.47, "elapsed_time": "3:27:08", "remaining_time": "0:32:25"}
+{"current_steps": 240, "total_steps": 266, "loss": 0.2695624828338623, "lr": 6.23215217819253e-07, "epoch": 1.8090737240075614, "percentage": 90.23, "elapsed_time": "3:35:59", "remaining_time": "0:23:23"}
+{"current_steps": 250, "total_steps": 266, "loss": 0.27001523971557617, "lr": 2.4863590457230745e-07, "epoch": 1.88468809073724, "percentage": 93.98, "elapsed_time": "3:44:56", "remaining_time": "0:14:23"}
+{"current_steps": 260, "total_steps": 266, "loss": 0.26818113327026366, "lr": 4.230226252580516e-08, "epoch": 1.9603024574669186, "percentage": 97.74, "elapsed_time": "3:53:59", "remaining_time": "0:05:23"}
+{"current_steps": 266, "total_steps": 266, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "3:59:40", "remaining_time": "0:00:00"}

designcoder_qwen3.5_4b_adamw_bs256_data41287_step200/trainer_state.json

@@ -0,0 +1,174 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.5066162570888468,
+  "eval_steps": 500,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.07561436672967864,
+      "grad_norm": 1.117009952541307,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.5404598236083984,
+      "step": 10
+    },
+    {
+      "epoch": 0.15122873345935728,
+      "grad_norm": 0.36972853390286087,
+      "learning_rate": 1.4074074074074075e-05,
+      "loss": 0.4467557430267334,
+      "step": 20
+    },
+    {
+      "epoch": 0.22684310018903592,
+      "grad_norm": 1.1836978851487674,
+      "learning_rate": 1.999654451568528e-05,
+      "loss": 0.3936758041381836,
+      "step": 30
+    },
+    {
+      "epoch": 0.30245746691871456,
+      "grad_norm": 0.3043289752355995,
+      "learning_rate": 1.987585312769669e-05,
+      "loss": 0.3615268707275391,
+      "step": 40
+    },
+    {
+      "epoch": 0.3780718336483932,
+      "grad_norm": 0.27560265185260435,
+      "learning_rate": 1.9584768190468624e-05,
+      "loss": 0.34326627254486086,
+      "step": 50
+    },
+    {
+      "epoch": 0.45368620037807184,
+      "grad_norm": 0.26107944603896804,
+      "learning_rate": 1.912831195321268e-05,
+      "loss": 0.33113551139831543,
+      "step": 60
+    },
+    {
+      "epoch": 0.5293005671077504,
+      "grad_norm": 0.3697176672713749,
+      "learning_rate": 1.8514359907527693e-05,
+      "loss": 0.32063558101654055,
+      "step": 70
+    },
+    {
+      "epoch": 0.6049149338374291,
+      "grad_norm": 0.22233342870182504,
+      "learning_rate": 1.7753504907192923e-05,
+      "loss": 0.3131831169128418,
+      "step": 80
+    },
+    {
+      "epoch": 0.6805293005671077,
+      "grad_norm": 0.3295343660094219,
+      "learning_rate": 1.6858874403810507e-05,
+      "loss": 0.3076876878738403,
+      "step": 90
+    },
+    {
+      "epoch": 0.7561436672967864,
+      "grad_norm": 0.24442797086141368,
+      "learning_rate": 1.584590395163162e-05,
+      "loss": 0.30152087211608886,
+      "step": 100
+    },
+    {
+      "epoch": 0.831758034026465,
+      "grad_norm": 0.31230465891561415,
+      "learning_rate": 1.4732070889412693e-05,
+      "loss": 0.29860482215881345,
+      "step": 110
+    },
+    {
+      "epoch": 0.9073724007561437,
+      "grad_norm": 0.21944703769074247,
+      "learning_rate": 1.3536592794235696e-05,
+      "loss": 0.2935622692108154,
+      "step": 120
+    },
+    {
+      "epoch": 0.9829867674858223,
+      "grad_norm": 0.2009268662989005,
+      "learning_rate": 1.2280095910035343e-05,
+      "loss": 0.29182274341583253,
+      "step": 130
+    },
+    {
+      "epoch": 1.052930056710775,
+      "grad_norm": 0.21168683990895032,
+      "learning_rate": 1.0984259271618947e-05,
+      "loss": 0.2805715322494507,
+      "step": 140
+    },
+    {
+      "epoch": 1.1285444234404536,
+      "grad_norm": 0.212560804654357,
+      "learning_rate": 9.671440664303813e-06,
+      "loss": 0.27776541709899905,
+      "step": 150
+    },
+    {
+      "epoch": 1.2041587901701323,
+      "grad_norm": 0.18414530626332756,
+      "learning_rate": 8.364290872697175e-06,
+      "loss": 0.27518510818481445,
+      "step": 160
+    },
+    {
+      "epoch": 1.279773156899811,
+      "grad_norm": 0.1715856148188389,
+      "learning_rate": 7.08536287419749e-06,
+      "loss": 0.27352917194366455,
+      "step": 170
+    },
+    {
+      "epoch": 1.3553875236294897,
+      "grad_norm": 0.17606724373633867,
+      "learning_rate": 5.8567227200175865e-06,
+      "loss": 0.271071720123291,
+      "step": 180
+    },
+    {
+      "epoch": 1.4310018903591684,
+      "grad_norm": 0.1586544570017202,
+      "learning_rate": 4.699568817414224e-06,
+      "loss": 0.27093987464904784,
+      "step": 190
+    },
+    {
+      "epoch": 1.5066162570888468,
+      "grad_norm": 0.15162846176632078,
+      "learning_rate": 3.63386618185811e-06,
+      "loss": 0.26956160068511964,
+      "step": 200
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 266,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.098304322535424e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}