Model: BrandonHowe/Qwen3-8b-urban-qwen-seed1-20260930-CPT-merged-epoch-3 Source: Original Platform
517 lines
9.5 KiB
JSON
517 lines
9.5 KiB
JSON
{
|
|
"model": "Qwen/Qwen3-8B-Base",
|
|
"model_revision": "49e3418fbbbca6ecbdf9608b4d22e5a407081db4",
|
|
"dataset": "CompassioninMachineLearning/urban_12738_cleaned",
|
|
"dataset_revision": "ef7c0e742df63ea319e35d02d9f6ba63d6e7c68d",
|
|
"dataset_text_column": "output",
|
|
"selection_hashes": {
|
|
"train": "0c277f32a1dc30143b94eb2091d4c6a4967e5810a6182829af0ea487fe239c79",
|
|
"validation": "dab93b63e8224211e4a1951a1ac547f1e119d4ac3677245bd918ae46fd51108d"
|
|
},
|
|
"dataset_selection": {
|
|
"seed": 3407,
|
|
"source_rows": 12738,
|
|
"unique_train_rows": 10072,
|
|
"replay_rows": 2000,
|
|
"validation_rows": 200,
|
|
"holdout_rows": 200,
|
|
"train_tokens_per_epoch": 13979166,
|
|
"validation_tokens": 231046
|
|
},
|
|
"packages": {
|
|
"unsloth": "2026.9.2",
|
|
"unsloth-zoo": "2026.9.1",
|
|
"transformers": "4.57.6",
|
|
"trl": "0.22.2",
|
|
"datasets": "4.3.0",
|
|
"huggingface_hub": "0.36.2",
|
|
"tokenizers": "0.22.2",
|
|
"peft": "0.20.0",
|
|
"accelerate": "1.14.0",
|
|
"bitsandbytes": "0.50.2",
|
|
"wandb": "0.28.1",
|
|
"torch": "2.11.0+cu128",
|
|
"torchvision": "0.26.0+cu128",
|
|
"torchaudio": "2.11.0+cu128",
|
|
"triton": "3.6.0",
|
|
"xformers": "0.0.35"
|
|
},
|
|
"environment_packages": [
|
|
{
|
|
"name": "accelerate",
|
|
"version": "1.14.0"
|
|
},
|
|
{
|
|
"name": "aiohappyeyeballs",
|
|
"version": "2.7.1"
|
|
},
|
|
{
|
|
"name": "aiohttp",
|
|
"version": "3.14.3"
|
|
},
|
|
{
|
|
"name": "aiosignal",
|
|
"version": "1.4.0"
|
|
},
|
|
{
|
|
"name": "annotated-doc",
|
|
"version": "0.0.5"
|
|
},
|
|
{
|
|
"name": "annotated-types",
|
|
"version": "0.8.0"
|
|
},
|
|
{
|
|
"name": "anyio",
|
|
"version": "4.15.1"
|
|
},
|
|
{
|
|
"name": "attrs",
|
|
"version": "26.1.0"
|
|
},
|
|
{
|
|
"name": "bitsandbytes",
|
|
"version": "0.50.2"
|
|
},
|
|
{
|
|
"name": "certifi",
|
|
"version": "2026.7.22"
|
|
},
|
|
{
|
|
"name": "charset-normalizer",
|
|
"version": "3.5.1"
|
|
},
|
|
{
|
|
"name": "click",
|
|
"version": "8.5.0"
|
|
},
|
|
{
|
|
"name": "cuda-bindings",
|
|
"version": "12.9.7"
|
|
},
|
|
{
|
|
"name": "cuda-pathfinder",
|
|
"version": "1.6.0"
|
|
},
|
|
{
|
|
"name": "cuda-toolkit",
|
|
"version": "12.8.1"
|
|
},
|
|
{
|
|
"name": "cut-cross-entropy",
|
|
"version": "25.1.1"
|
|
},
|
|
{
|
|
"name": "datasets",
|
|
"version": "4.3.0"
|
|
},
|
|
{
|
|
"name": "diffusers",
|
|
"version": "0.39.0"
|
|
},
|
|
{
|
|
"name": "dill",
|
|
"version": "0.4.0"
|
|
},
|
|
{
|
|
"name": "docstring_parser",
|
|
"version": "0.18.0"
|
|
},
|
|
{
|
|
"name": "filelock",
|
|
"version": "3.32.3"
|
|
},
|
|
{
|
|
"name": "frozenlist",
|
|
"version": "1.8.0"
|
|
},
|
|
{
|
|
"name": "fsspec",
|
|
"version": "2025.9.0"
|
|
},
|
|
{
|
|
"name": "h11",
|
|
"version": "0.16.0"
|
|
},
|
|
{
|
|
"name": "hf_transfer",
|
|
"version": "0.1.9"
|
|
},
|
|
{
|
|
"name": "hf-xet",
|
|
"version": "1.6.0"
|
|
},
|
|
{
|
|
"name": "httpcore",
|
|
"version": "1.0.9"
|
|
},
|
|
{
|
|
"name": "httpx",
|
|
"version": "0.28.1"
|
|
},
|
|
{
|
|
"name": "huggingface_hub",
|
|
"version": "0.36.2"
|
|
},
|
|
{
|
|
"name": "idna",
|
|
"version": "3.20"
|
|
},
|
|
{
|
|
"name": "importlib_metadata",
|
|
"version": "9.0.1"
|
|
},
|
|
{
|
|
"name": "Jinja2",
|
|
"version": "3.1.6"
|
|
},
|
|
{
|
|
"name": "markdown-it-py",
|
|
"version": "4.2.0"
|
|
},
|
|
{
|
|
"name": "MarkupSafe",
|
|
"version": "3.0.3"
|
|
},
|
|
{
|
|
"name": "mdurl",
|
|
"version": "0.1.2"
|
|
},
|
|
{
|
|
"name": "mpmath",
|
|
"version": "1.3.0"
|
|
},
|
|
{
|
|
"name": "msgspec",
|
|
"version": "0.22.0"
|
|
},
|
|
{
|
|
"name": "multidict",
|
|
"version": "6.9.1"
|
|
},
|
|
{
|
|
"name": "multiprocess",
|
|
"version": "0.70.16"
|
|
},
|
|
{
|
|
"name": "nest-asyncio",
|
|
"version": "1.6.0"
|
|
},
|
|
{
|
|
"name": "networkx",
|
|
"version": "3.6.1"
|
|
},
|
|
{
|
|
"name": "numpy",
|
|
"version": "2.5.2"
|
|
},
|
|
{
|
|
"name": "nvidia-cublas-cu12",
|
|
"version": "12.8.4.1"
|
|
},
|
|
{
|
|
"name": "nvidia-cuda-cupti-cu12",
|
|
"version": "12.8.90"
|
|
},
|
|
{
|
|
"name": "nvidia-cuda-nvrtc-cu12",
|
|
"version": "12.8.93"
|
|
},
|
|
{
|
|
"name": "nvidia-cuda-runtime-cu12",
|
|
"version": "12.8.90"
|
|
},
|
|
{
|
|
"name": "nvidia-cudnn-cu12",
|
|
"version": "9.19.0.56"
|
|
},
|
|
{
|
|
"name": "nvidia-cufft-cu12",
|
|
"version": "11.3.3.83"
|
|
},
|
|
{
|
|
"name": "nvidia-cufile-cu12",
|
|
"version": "1.13.1.3"
|
|
},
|
|
{
|
|
"name": "nvidia-curand-cu12",
|
|
"version": "10.3.9.90"
|
|
},
|
|
{
|
|
"name": "nvidia-cusolver-cu12",
|
|
"version": "11.7.3.90"
|
|
},
|
|
{
|
|
"name": "nvidia-cusparse-cu12",
|
|
"version": "12.5.8.93"
|
|
},
|
|
{
|
|
"name": "nvidia-cusparselt-cu12",
|
|
"version": "0.7.1"
|
|
},
|
|
{
|
|
"name": "nvidia-nccl-cu12",
|
|
"version": "2.28.9"
|
|
},
|
|
{
|
|
"name": "nvidia-nvjitlink-cu12",
|
|
"version": "12.8.93"
|
|
},
|
|
{
|
|
"name": "nvidia-nvshmem-cu12",
|
|
"version": "3.4.5"
|
|
},
|
|
{
|
|
"name": "nvidia-nvtx-cu12",
|
|
"version": "12.8.90"
|
|
},
|
|
{
|
|
"name": "packaging",
|
|
"version": "26.3"
|
|
},
|
|
{
|
|
"name": "pandas",
|
|
"version": "3.0.6"
|
|
},
|
|
{
|
|
"name": "peft",
|
|
"version": "0.20.0"
|
|
},
|
|
{
|
|
"name": "pillow",
|
|
"version": "12.3.0"
|
|
},
|
|
{
|
|
"name": "pip",
|
|
"version": "26.2.1"
|
|
},
|
|
{
|
|
"name": "platformdirs",
|
|
"version": "4.12.2"
|
|
},
|
|
{
|
|
"name": "propcache",
|
|
"version": "0.5.4"
|
|
},
|
|
{
|
|
"name": "protobuf",
|
|
"version": "7.36.2"
|
|
},
|
|
{
|
|
"name": "psutil",
|
|
"version": "7.2.2"
|
|
},
|
|
{
|
|
"name": "pyarrow",
|
|
"version": "25.0.1"
|
|
},
|
|
{
|
|
"name": "pydantic",
|
|
"version": "2.13.5"
|
|
},
|
|
{
|
|
"name": "pydantic_core",
|
|
"version": "2.46.5"
|
|
},
|
|
{
|
|
"name": "Pygments",
|
|
"version": "2.21.0"
|
|
},
|
|
{
|
|
"name": "python-dateutil",
|
|
"version": "2.9.0.post0"
|
|
},
|
|
{
|
|
"name": "PyYAML",
|
|
"version": "6.0.3"
|
|
},
|
|
{
|
|
"name": "regex",
|
|
"version": "2026.9.29"
|
|
},
|
|
{
|
|
"name": "requests",
|
|
"version": "2.34.2"
|
|
},
|
|
{
|
|
"name": "rich",
|
|
"version": "15.0.0"
|
|
},
|
|
{
|
|
"name": "safetensors",
|
|
"version": "0.8.0"
|
|
},
|
|
{
|
|
"name": "sentencepiece",
|
|
"version": "0.2.2"
|
|
},
|
|
{
|
|
"name": "sentry-sdk",
|
|
"version": "2.71.0"
|
|
},
|
|
{
|
|
"name": "setuptools",
|
|
"version": "78.1.0"
|
|
},
|
|
{
|
|
"name": "shellingham",
|
|
"version": "1.5.4"
|
|
},
|
|
{
|
|
"name": "six",
|
|
"version": "1.17.0"
|
|
},
|
|
{
|
|
"name": "structlog",
|
|
"version": "26.1.0"
|
|
},
|
|
{
|
|
"name": "sympy",
|
|
"version": "1.14.0"
|
|
},
|
|
{
|
|
"name": "tokenizers",
|
|
"version": "0.22.2"
|
|
},
|
|
{
|
|
"name": "torch",
|
|
"version": "2.11.0+cu128"
|
|
},
|
|
{
|
|
"name": "torchao",
|
|
"version": "0.18.0"
|
|
},
|
|
{
|
|
"name": "torchaudio",
|
|
"version": "2.11.0+cu128"
|
|
},
|
|
{
|
|
"name": "torchvision",
|
|
"version": "0.26.0+cu128"
|
|
},
|
|
{
|
|
"name": "tqdm",
|
|
"version": "4.70.1"
|
|
},
|
|
{
|
|
"name": "transformers",
|
|
"version": "4.57.6"
|
|
},
|
|
{
|
|
"name": "triton",
|
|
"version": "3.6.0"
|
|
},
|
|
{
|
|
"name": "trl",
|
|
"version": "0.22.2"
|
|
},
|
|
{
|
|
"name": "typeguard",
|
|
"version": "4.6.0"
|
|
},
|
|
{
|
|
"name": "typer",
|
|
"version": "0.27.2"
|
|
},
|
|
{
|
|
"name": "typing_extensions",
|
|
"version": "4.16.0"
|
|
},
|
|
{
|
|
"name": "typing-inspection",
|
|
"version": "0.4.4"
|
|
},
|
|
{
|
|
"name": "tyro",
|
|
"version": "1.0.16"
|
|
},
|
|
{
|
|
"name": "unsloth",
|
|
"version": "2026.9.2"
|
|
},
|
|
{
|
|
"name": "unsloth_zoo",
|
|
"version": "2026.9.1"
|
|
},
|
|
{
|
|
"name": "urllib3",
|
|
"version": "2.8.0"
|
|
},
|
|
{
|
|
"name": "wandb",
|
|
"version": "0.28.1"
|
|
},
|
|
{
|
|
"name": "wheel",
|
|
"version": "0.48.0"
|
|
},
|
|
{
|
|
"name": "xformers",
|
|
"version": "0.0.35"
|
|
},
|
|
{
|
|
"name": "xxhash",
|
|
"version": "4.0.1"
|
|
},
|
|
{
|
|
"name": "yarl",
|
|
"version": "1.25.1"
|
|
},
|
|
{
|
|
"name": "zipp",
|
|
"version": "4.1.0"
|
|
}
|
|
],
|
|
"python": "3.12.3",
|
|
"cuda": "12.8",
|
|
"gpu": "NVIDIA H100 80GB HBM3",
|
|
"activation_checkpointing": "offload",
|
|
"run_id": "urban-qwen-seed1-20260930",
|
|
"timing_test": false,
|
|
"collection_slug": "",
|
|
"local_only": false,
|
|
"push_to_hub": true,
|
|
"merged_namespace": "BrandonHowe",
|
|
"training": {
|
|
"learning_rate": 5e-05,
|
|
"embedding_learning_rate": 5e-06,
|
|
"num_train_epochs": 5,
|
|
"warmup_ratio": 0.05,
|
|
"lr_scheduler_type": "cosine",
|
|
"weight_decay": 0.01,
|
|
"per_device_train_batch_size": 4,
|
|
"gradient_accumulation_steps": 8,
|
|
"per_device_eval_batch_size": 4,
|
|
"seed": 1,
|
|
"max_length": 8192
|
|
},
|
|
"adapter": {
|
|
"rank": 128,
|
|
"alpha": 64,
|
|
"dropout": 0.05,
|
|
"rslora": true,
|
|
"random_state": 1
|
|
},
|
|
"execution": {
|
|
"mode": "full",
|
|
"max_steps": -1
|
|
},
|
|
"completed_epoch": 3.0,
|
|
"global_step": 1134,
|
|
"merged_export": {
|
|
"weight_shards": 8,
|
|
"weight_tensors": 399,
|
|
"weight_bytes": 16381470720,
|
|
"tensor_dtypes": [
|
|
"BF16"
|
|
],
|
|
"finite_weights": true,
|
|
"packaging_changes_tensor_values": false,
|
|
"serialization_method": "huggingface_hub.save_torch_state_dict",
|
|
"max_shard_size": 2224710480,
|
|
"base_model": "Qwen/Qwen3-8B-Base",
|
|
"base_revision": "49e3418fbbbca6ecbdf9608b4d22e5a407081db4",
|
|
"merge_method": "Unsloth save_pretrained_merged(save_method=\"merged_16bit\")"
|
|
}
|
|
}
|