OLMo-3-7B-CPT-BF16_olddata / training_manifest.json
ganscs's picture
Validated standalone BF16 epoch 2, eight shards
483864c verified
Raw History Blame Contribute Delete
11 kB
{
"model": "allenai/Olmo-3-1025-7B",
"model_revision": "a81bae42db3975be1671e27b9c9a56da1a9f980f",
"dataset_revision": "06248aa4c3fd26b22fdedded4dc172d00dd2e5cd",
"selection_hashes": {
"train": "3204b143004cce956c5f7f412d3d82aececfb99a9db0c27213ba92e44ff3c45b",
"validation": "495bc23def6c2a73277187a07a32f9e8191a2dba55de41bfeb83fa7e416c7e8a"
},
"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": "abnf",
"version": "2.2.0"
},
{
"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": "backoff",
"version": "2.2.1"
},
{
"name": "bitsandbytes",
"version": "0.50.2"
},
{
"name": "cachetools",
"version": "7.1.8"
},
{
"name": "certifi",
"version": "2026.7.22"
},
{
"name": "cffi",
"version": "2.1.1"
},
{
"name": "chardet",
"version": "7.6.0"
},
{
"name": "charset-normalizer",
"version": "3.5.1"
},
{
"name": "cint",
"version": "1.0.0"
},
{
"name": "click",
"version": "8.5.0"
},
{
"name": "cryptography",
"version": "50.0.1"
},
{
"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": "diskcache-weave",
"version": "5.6.3.post1"
},
{
"name": "distro",
"version": "1.9.0"
},
{
"name": "docstring_parser",
"version": "0.18.0"
},
{
"name": "fickling",
"version": "0.1.12"
},
{
"name": "filelock",
"version": "3.32.3"
},
{
"name": "frozenlist",
"version": "1.8.0"
},
{
"name": "fsspec",
"version": "2025.9.0"
},
{
"name": "googleapis-common-protos",
"version": "1.75.3"
},
{
"name": "gql",
"version": "4.0.0"
},
{
"name": "graphql-core",
"version": "3.2.12"
},
{
"name": "graphviz",
"version": "0.21"
},
{
"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": "3.19"
},
{
"name": "importlib_metadata",
"version": "9.0.1"
},
{
"name": "intervaltree",
"version": "3.2.1"
},
{
"name": "Jinja2",
"version": "3.1.6"
},
{
"name": "jsonschema",
"version": "4.26.0"
},
{
"name": "jsonschema-specifications",
"version": "2025.9.1"
},
{
"name": "kaitaistruct",
"version": "0.11"
},
{
"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": "0.21.1"
},
{
"name": "multidict",
"version": "6.7.1"
},
{
"name": "multiprocess",
"version": "0.70.16"
},
{
"name": "nest-asyncio",
"version": "1.6.0"
},
{
"name": "networkx",
"version": "3.6.1"
},
{
"name": "numpy",
"version": "2.4.6"
},
{
"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": "opentelemetry-api",
"version": "1.44.0"
},
{
"name": "opentelemetry-exporter-otlp-proto-common",
"version": "1.44.0"
},
{
"name": "opentelemetry-exporter-otlp-proto-http",
"version": "1.44.0"
},
{
"name": "opentelemetry-proto",
"version": "1.44.0"
},
{
"name": "opentelemetry-sdk",
"version": "1.44.0"
},
{
"name": "opentelemetry-semantic-conventions",
"version": "0.65b0"
},
{
"name": "packaging",
"version": "26.3"
},
{
"name": "pandas",
"version": "3.0.5"
},
{
"name": "pdfminer.six",
"version": "20260107"
},
{
"name": "peft",
"version": "0.20.0"
},
{
"name": "pillow",
"version": "12.3.0"
},
{
"name": "pip",
"version": "26.2.1"
},
{
"name": "platformdirs",
"version": "4.11.7"
},
{
"name": "polyfile-weave",
"version": "0.5.9"
},
{
"name": "propcache",
"version": "0.5.2"
},
{
"name": "protobuf",
"version": "7.36.1"
},
{
"name": "psutil",
"version": "7.2.2"
},
{
"name": "pyarrow",
"version": "25.0.1"
},
{
"name": "pycparser",
"version": "3.0"
},
{
"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": "referencing",
"version": "0.37.0"
},
{
"name": "regex",
"version": "2026.9.3"
},
{
"name": "requests",
"version": "2.34.2"
},
{
"name": "rich",
"version": "15.0.0"
},
{
"name": "rpds-py",
"version": "2026.6.3"
},
{
"name": "safetensors",
"version": "0.8.0"
},
{
"name": "sentencepiece",
"version": "0.2.2"
},
{
"name": "sentry-sdk",
"version": "2.69.1"
},
{
"name": "setuptools",
"version": "78.1.0"
},
{
"name": "shellingham",
"version": "1.5.4"
},
{
"name": "six",
"version": "1.17.0"
},
{
"name": "sniffio",
"version": "1.3.1"
},
{
"name": "sortedcontainers",
"version": "2.4.0"
},
{
"name": "structlog",
"version": "26.1.0"
},
{
"name": "sympy",
"version": "1.14.0"
},
{
"name": "tenacity",
"version": "9.1.4"
},
{
"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": "4.70.0"
},
{
"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": "2.7.0"
},
{
"name": "wandb",
"version": "0.28.1"
},
{
"name": "weave",
"version": "0.53.8"
},
{
"name": "wheel",
"version": "0.48.0"
},
{
"name": "xformers",
"version": "0.0.35"
},
{
"name": "xxhash",
"version": "4.0.1"
},
{
"name": "yarl",
"version": "1.24.5"
},
{
"name": "zipp",
"version": "4.1.0"
}
],
"python": "3.11.10",
"cuda": "12.8",
"gpu": "NVIDIA H100 80GB HBM3",
"activation_checkpointing": "gpu",
"run_id": "olmo-a100-new-20260908",
"timing_test": false,
"collection_slug": "",
"local_only": false,
"push_to_hub": false,
"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": 3407,
"max_length": 8192
},
"adapter": {
"rank": 128,
"alpha": 64,
"dropout": 0.05,
"rslora": true
}
}