Files
zen-blog/blog/training-gym/__next.blog.$d$slug.__PAGE__.txt

110 lines
73 KiB
Plaintext
Raw Permalink Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
1:"$Sreact.fragment"
2:I[10086,["/_next/static/chunks/59d0ad1b64f8544e.js","/_next/static/chunks/8de849ca74fc071f.js","/_next/static/chunks/e62b91212ee7f8ff.js","/_next/static/chunks/f19fe44237e54646.js","/_next/static/chunks/cb0a883bafeb6805.js"],""]
46:I[51504,["/_next/static/chunks/59d0ad1b64f8544e.js","/_next/static/chunks/8de849ca74fc071f.js","/_next/static/chunks/e62b91212ee7f8ff.js","/_next/static/chunks/f19fe44237e54646.js","/_next/static/chunks/cb0a883bafeb6805.js"],"CodeBlock"]
47:I[51504,["/_next/static/chunks/59d0ad1b64f8544e.js","/_next/static/chunks/8de849ca74fc071f.js","/_next/static/chunks/e62b91212ee7f8ff.js","/_next/static/chunks/f19fe44237e54646.js","/_next/static/chunks/cb0a883bafeb6805.js"],"Pre"]
71:I[89923,["/_next/static/chunks/4d80e004cf4896dd.js","/_next/static/chunks/350ee4303b732916.js"],"OutletBoundary"]
72:"$Sreact.suspense"
0:{"buildId":"i-dnJM_MIpJSOCQWNJVMq","rsc":["$","$1","c",{"children":[["$","main",null,{"className":"mx-auto w-full max-w-2xl px-4 py-16","children":[["$","$L2",null,{"href":"/blog","className":"inline-flex items-center gap-1.5 text-sm text-fd-muted-foreground hover:text-fd-foreground mb-10 transition-colors","children":"← Back to Blog"}],["$","div",null,{"className":"mb-8","children":[["$","time",null,{"className":"text-xs font-mono text-fd-muted-foreground uppercase tracking-wider","children":"September 10, 2023"}],["$","h1",null,{"className":"text-3xl font-bold mt-2 mb-3","children":"Training Gym: A Platform for Open Model Development"}],["$","p",null,{"className":"text-fd-muted-foreground text-lg mb-4","children":"Announcing Training Gym, our open platform for collaborative large model training."}],["$","div",null,{"className":"flex items-center gap-3 pt-4 border-t border-fd-border","children":[["$","span",null,{"className":"text-sm text-fd-muted-foreground","children":["By ","Zach Kelling"]}],["$","div",null,{"className":"flex gap-1.5 ml-auto","children":[["$","span","Infrastructure",{"className":"text-[10px] font-mono uppercase tracking-wider bg-fd-muted text-fd-muted-foreground px-1.5 py-0.5 rounded","children":"Infrastructure"}],["$","span","Training",{"className":"text-[10px] font-mono uppercase tracking-wider bg-fd-muted text-fd-muted-foreground px-1.5 py-0.5 rounded","children":"Training"}],["$","span","Open Source",{"className":"text-[10px] font-mono uppercase tracking-wider bg-fd-muted text-fd-muted-foreground px-1.5 py-0.5 rounded","children":"Open Source"}]]}]]}]]}],["$","div",null,{"className":"prose dark:prose-invert max-w-none","children":[["$","p",null,{"children":"Training large language models requires more than algorithms. It requires infrastructure: distributed training frameworks, data pipelines, experiment tracking, and evaluation harnesses. Today we open source Training Gym, our complete platform for model development."}],"\n",["$","h2",null,{"className":"flex scroll-m-28 flex-row items-center gap-2","id":"why-training-gym","children":[["$","a",null,{"data-card":"","href":"#why-training-gym","className":"peer","children":"Why Training Gym?"}],["$","svg",null,{"xmlns":"http://www.w3.org/2000/svg","width":24,"height":24,"viewBox":"0 0 24 24","fill":"none","stroke":"currentColor","strokeWidth":2,"strokeLinecap":"round","strokeLinejoin":"round","className":"lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100","aria-hidden":true,"children":[["$","path","1cjeqo",{"d":"M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"}],["$","path","19qd67",{"d":"M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"}],"$undefined"]}]]}],"\n",["$","p",null,{"children":"Open AI development faces an infrastructure gap. Publishing model weights is valuable, but it’s not enough. Researchers need:"}],"\n",["$","ul",null,{"children":["\n",["$","li",null,{"children":"Reproducible training pipelines"}],"\n",["$","li",null,{"children":"Scalable distributed training"}],"\n",["$","li",null,{"children":"Standardized evaluation"}],"\n",["$","li",null,{"children":"Experiment management"}],"\n",["$","li",null,{"children":"Data processing tools"}],"\n"]}],"\n",["$","p",null,{"children":"Training Gym provides all of this in an integrated, open source package."}],"\n",["$","h2",null,{"className":"flex scroll-m-28 flex-row items-center gap-2","id":"architecture","children":[["$","a",null,{"data-card":"","href":"#architecture","className":"peer","children":"Architecture"}],["$","svg",null,{"xmlns":"http://www.w3.org/2000/svg","width":24,"height":24,"viewBox":"0 0 24 24","fill":"none","stroke":"currentColor","strokeWidth":2,"strokeLinecap":"round","strokeLinejoin":"round","className":"lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100","aria-hidden":true,"children":[["$","path","1cjeqo",{"d":"M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"}],"$L3","$undefined"]}]]}],"\n","$L4","\n","$L5","\n","$L6","\n","$L7","\n","$L8","\n","$L9","\n","$La","\n","$Lb","\n","$Lc","\n","$Ld","\n","$Le","\n","$Lf","\n","$L10","\n","$L11","\n","$L12","\n","$L13","\n","$L14","\n","$L15","\n","$L16","\n","$L17","\n","$L18","\n","$L19","\n","$L1a","\n","$L1b","\n","$L1c","\n","$L1d","\n","$L1e","\n","$L1f","\n","$L20","\n","$L21","\n","$L22","\n","$L23","\n","$L24","\n","$L25","\n","$L26","\n","$L27","\n","$L28","\n","$L29","\n","$L2a","\n","$L2b","\n","$L2c","\n","$L2d","\n","$L2e","\n","$L2f","\n","$L30","\n","$L31","\n","$L32","\n","$L33","\n","$L34","\n","$L35","\n","$L36","\n","$L37","\n","$L38","\n","$L39","\n","$L3a","\n","$L3b","\n","$L3c","\n","$L3d","\n","$L3e","\n","$L3f","\n","$L40"]}]]}],["$L41","$L42","$L43","$L44"],"$L45"]}],"loading":null,"isPartial":false}
3:["$","path","19qd67",{"d":"M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"}]
4:["$","$L46",null,{"className":"shiki shiki-themes github-light github-dark","style":{"--shiki-light":"#24292e","--shiki-dark":"#e1e4e8","--shiki-light-bg":"#fff","--shiki-dark-bg":"#24292e"},"tabIndex":"0","icon":"<svg viewBox=\"0 0 24 24\"><path d=\"M 6,1 C 4.354992,1 3,2.354992 3,4 v 16 c 0,1.645008 1.354992,3 3,3 h 12 c 1.645008,0 3,-1.354992 3,-3 V 8 7 A 1.0001,1.0001 0 0 0 20.707031,6.2929687 l -5,-5 A 1.0001,1.0001 0 0 0 15,1 h -1 z m 0,2 h 7 v 3 c 0,1.645008 1.354992,3 3,3 h 3 v 11 c 0,0.564129 -0.435871,1 -1,1 H 6 C 5.4358712,21 5,20.564129 5,20 V 4 C 5,3.4358712 5.4358712,3 6,3 Z M 15,3.4140625 18.585937,7 H 16 C 15.435871,7 15,6.5641288 15,6 Z\" fill=\"currentColor\" /></svg>","children":["$","$L47",null,{"children":["$","code",null,{"children":[["$","span",null,{"className":"line","children":["$","span",null,{}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" +------------------+ +------------------+ +------------------+"}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" | Data Pipeline | --> | Training Loop | --> | Evaluation |"}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" +------------------+ +------------------+ +------------------+"}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" | | |"}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" v v v"}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" +------------------+ +------------------+ +------------------+"}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" | Data Registry | | Checkpoint Store | | Metrics DB |"}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" +------------------+ +------------------+ +------------------+"}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" |"}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" v"}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" +------------------+"}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" | Experiment |"}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" | Tracker |"}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" +------------------+"}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" "}]}]]}]}]}]
5:["$","h3",null,{"className":"flex scroll-m-28 flex-row items-center gap-2","id":"data-pipeline","children":[["$","a",null,{"data-card":"","href":"#data-pipeline","className":"peer","children":"Data Pipeline"}],["$","svg",null,{"xmlns":"http://www.w3.org/2000/svg","width":24,"height":24,"viewBox":"0 0 24 24","fill":"none","stroke":"currentColor","strokeWidth":2,"strokeLinecap":"round","strokeLinejoin":"round","className":"lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100","aria-hidden":true,"children":[["$","path","1cjeqo",{"d":"M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"}],["$","path","19qd67",{"d":"M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"}],"$undefined"]}]]}]
6:["$","p",null,{"children":"The data pipeline handles:"}]
7:["$","ul",null,{"children":["\n",["$","li",null,{"children":[["$","strong",null,{"children":"Ingestion"}]," : Load from local files, cloud storage, or streaming sources"]}],"\n",["$","li",null,{"children":[["$","strong",null,{"children":"Processing"}]," : Tokenization, filtering, deduplication"]}],"\n",["$","li",null,{"children":[["$","strong",null,{"children":"Mixing"}]," : Combine multiple data sources with configurable ratios"]}],"\n",["$","li",null,{"children":[["$","strong",null,{"children":"Streaming"}]," : Memory-efficient data loading for large corpora"]}],"\n"]}]
48:T5c0,<svg viewBox="0 0 24 24"><path d="M14.25.18l.9.2.73.26.59.3.45.32.34.34.25.34.16.33.1.3.04.26.02.2-.01.13V8.5l-.05.63-.13.55-.21.46-.26.38-.3.31-.33.25-.35.19-.35.14-.33.1-.3.07-.26.04-.21.02H8.77l-.69.05-.59.14-.5.22-.41.27-.33.32-.27.35-.2.36-.15.37-.1.35-.07.32-.04.27-.02.21v3.06H3.17l-.21-.03-.28-.07-.32-.12-.35-.18-.36-.26-.36-.36-.35-.46-.32-.59-.28-.73-.21-.88-.14-1.05-.05-1.23.06-1.22.16-1.04.24-.87.32-.71.36-.57.4-.44.42-.33.42-.24.4-.16.36-.1.32-.05.24-.01h.16l.06.01h8.16v-.83H6.18l-.01-2.75-.02-.37.05-.34.11-.31.17-.28.25-.26.31-.23.38-.2.44-.18.51-.15.58-.12.64-.1.71-.06.77-.04.84-.02 1.27.05zm-6.3 1.98l-.23.33-.08.41.08.41.23.34.33.22.41.09.41-.09.33-.22.23-.34.08-.41-.08-.41-.23-.33-.33-.22-.41-.09-.41.09zm13.09 3.95l.28.06.32.12.35.18.36.27.36.35.35.47.32.59.28.73.21.88.14 1.04.05 1.23-.06 1.23-.16 1.04-.24.86-.32.71-.36.57-.4.45-.42.33-.42.24-.4.16-.36.09-.32.05-.24.02-.16-.01h-8.22v.82h5.84l.01 2.76.02.36-.05.34-.11.31-.17.29-.25.25-.31.24-.38.2-.44.17-.51.15-.58.13-.64.09-.71.07-.77.04-.84.01-1.27-.04-1.07-.14-.9-.2-.73-.25-.59-.3-.45-.33-.34-.34-.25-.34-.16-.33-.1-.3-.04-.25-.02-.2.01-.13v-5.34l.05-.64.13-.54.21-.46.26-.38.3-.32.33-.24.35-.2.35-.14.33-.1.3-.06.26-.04.21-.02.13-.01h5.84l.69-.05.59-.14.5-.21.41-.28.33-.32.27-.35.2-.36.15-.36.1-.35.07-.32.04-.28.02-.21V6.07h2.09l.14.01zm-6.47 14.25l-.23.33-.08.41.08.41.23.33.33.23.41.08.41-.08.33-.23.23-.33.08-.41-.08-.41-.23-.33-.33-.23-.41-.08-.41.08z" fill="currentColor" /></svg>8:["$","$L46",null,{"className":"shiki shiki-themes github-light github-dark","style":{"--shiki-light":"#24292e","--shiki-dark":"#e1e4e8","--shiki-light-bg":"#fff","--shiki-dark-bg":"#24292e"},"tabIndex":"0","icon":"$48","children":["$","$L47",null,{"children":["$","code",null,{"children":[["$","span",null,{"className":"line"}],"\n",["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":" from"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" training_gym.data "}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"import"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" DataPipeline, MixedDataset"}]]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" "}]}],"\n",["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" pipeline "}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"="}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" DataPipeline("}]]}],"\n",["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#E36209","--shiki-dark":"#FFAB70"},"children":" sources"}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"="}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":"["}]]}],"\n",["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" ("}],["$","span",null,{"style":{"--shiki-light":"#032F62","--shiki-dark":"#9ECBFF"},"children":"\"s3://data/books\""}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":", "}],["$","span",null,{"style":{"--shiki-light":"#005CC5","--shiki-dark":"#79B8FF"},"children":"0.3"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":"),"}]]}],"\n",["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" ("}],["$","span",null,{"style":{"--shiki-light":"#032F62","--shiki-dark":"#9ECBFF"},"children":"\"s3://data/web\""}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":", "}],"$L49","$L4a"]}],"\n","$L4b","\n","$L4c","\n","$L4d","\n","$L4e","\n","$L4f","\n","$L50","\n","$L51","\n","$L52"]}]}]}]
9:["$","h3",null,{"className":"flex scroll-m-28 flex-row items-center gap-2","id":"distributed-training","children":[["$","a",null,{"data-card":"","href":"#distributed-training","className":"peer","children":"Distributed Training"}],["$","svg",null,{"xmlns":"http://www.w3.org/2000/svg","width":24,"height":24,"viewBox":"0 0 24 24","fill":"none","stroke":"currentColor","strokeWidth":2,"strokeLinecap":"round","strokeLinejoin":"round","className":"lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100","aria-hidden":true,"children":[["$","path","1cjeqo",{"d":"M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"}],["$","path","19qd67",{"d":"M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"}],"$undefined"]}]]}]
a:["$","p",null,{"children":"Training Gym supports multiple distributed training strategies:"}]
b:["$","ul",null,{"children":["\n",["$","li",null,{"children":[["$","strong",null,{"children":"Data Parallel"}]," : Simple replication across devices"]}],"\n",["$","li",null,{"children":[["$","strong",null,{"children":"Tensor Parallel"}]," : Split layers across devices"]}],"\n",["$","li",null,{"children":[["$","strong",null,{"children":"Pipeline Parallel"}]," : Split model stages across devices"]}],"\n",["$","li",null,{"children":[["$","strong",null,{"children":"ZeRO"}]," : Memory-efficient data parallelism"]}],"\n",["$","li",null,{"children":[["$","strong",null,{"children":"FSDP"}]," : Fully sharded data parallel (PyTorch native)"]}],"\n"]}]
c:["$","p",null,{"children":"Configuration is declarative:"}]
d:["$","$L46",null,{"className":"shiki shiki-themes github-light github-dark","style":{"--shiki-light":"#24292e","--shiki-dark":"#e1e4e8","--shiki-light-bg":"#fff","--shiki-dark-bg":"#24292e"},"tabIndex":"0","icon":"<svg viewBox=\"0 0 24 24\"><path d=\"M 6,1 C 4.354992,1 3,2.354992 3,4 v 16 c 0,1.645008 1.354992,3 3,3 h 12 c 1.645008,0 3,-1.354992 3,-3 V 8 7 A 1.0001,1.0001 0 0 0 20.707031,6.2929687 l -5,-5 A 1.0001,1.0001 0 0 0 15,1 h -1 z m 0,2 h 7 v 3 c 0,1.645008 1.354992,3 3,3 h 3 v 11 c 0,0.564129 -0.435871,1 -1,1 H 6 C 5.4358712,21 5,20.564129 5,20 V 4 C 5,3.4358712 5.4358712,3 6,3 Z M 15,3.4140625 18.585937,7 H 16 C 15.435871,7 15,6.5641288 15,6 Z\" fill=\"currentColor\" /></svg>","children":["$","$L47",null,{"children":["$","code",null,{"children":[["$","span",null,{"className":"line","children":["$","span",null,{}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" distributed:"}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" strategy: fsdp"}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" world_size: 64"}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" sharding_strategy: full_shard"}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" mixed_precision: bf16"}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" gradient_checkpointing: true"}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" "}]}]]}]}]}]
e:["$","h3",null,{"className":"flex scroll-m-28 flex-row items-center gap-2","id":"training-loop","children":[["$","a",null,{"data-card":"","href":"#training-loop","className":"peer","children":"Training Loop"}],["$","svg",null,{"xmlns":"http://www.w3.org/2000/svg","width":24,"height":24,"viewBox":"0 0 24 24","fill":"none","stroke":"currentColor","strokeWidth":2,"strokeLinecap":"round","strokeLinejoin":"round","className":"lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100","aria-hidden":true,"children":[["$","path","1cjeqo",{"d":"M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"}],["$","path","19qd67",{"d":"M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"}],"$undefined"]}]]}]
f:["$","p",null,{"children":"The training loop is modular and extensible:"}]
53:T5c0,<svg viewBox="0 0 24 24"><path d="M14.25.18l.9.2.73.26.59.3.45.32.34.34.25.34.16.33.1.3.04.26.02.2-.01.13V8.5l-.05.63-.13.55-.21.46-.26.38-.3.31-.33.25-.35.19-.35.14-.33.1-.3.07-.26.04-.21.02H8.77l-.69.05-.59.14-.5.22-.41.27-.33.32-.27.35-.2.36-.15.37-.1.35-.07.32-.04.27-.02.21v3.06H3.17l-.21-.03-.28-.07-.32-.12-.35-.18-.36-.26-.36-.36-.35-.46-.32-.59-.28-.73-.21-.88-.14-1.05-.05-1.23.06-1.22.16-1.04.24-.87.32-.71.36-.57.4-.44.42-.33.42-.24.4-.16.36-.1.32-.05.24-.01h.16l.06.01h8.16v-.83H6.18l-.01-2.75-.02-.37.05-.34.11-.31.17-.28.25-.26.31-.23.38-.2.44-.18.51-.15.58-.12.64-.1.71-.06.77-.04.84-.02 1.27.05zm-6.3 1.98l-.23.33-.08.41.08.41.23.34.33.22.41.09.41-.09.33-.22.23-.34.08-.41-.08-.41-.23-.33-.33-.22-.41-.09-.41.09zm13.09 3.95l.28.06.32.12.35.18.36.27.36.35.35.47.32.59.28.73.21.88.14 1.04.05 1.23-.06 1.23-.16 1.04-.24.86-.32.71-.36.57-.4.45-.42.33-.42.24-.4.16-.36.09-.32.05-.24.02-.16-.01h-8.22v.82h5.84l.01 2.76.02.36-.05.34-.11.31-.17.29-.25.25-.31.24-.38.2-.44.17-.51.15-.58.13-.64.09-.71.07-.77.04-.84.01-1.27-.04-1.07-.14-.9-.2-.73-.25-.59-.3-.45-.33-.34-.34-.25-.34-.16-.33-.1-.3-.04-.25-.02-.2.01-.13v-5.34l.05-.64.13-.54.21-.46.26-.38.3-.32.33-.24.35-.2.35-.14.33-.1.3-.06.26-.04.21-.02.13-.01h5.84l.69-.05.59-.14.5-.21.41-.28.33-.32.27-.35.2-.36.15-.36.1-.35.07-.32.04-.28.02-.21V6.07h2.09l.14.01zm-6.47 14.25l-.23.33-.08.41.08.41.23.33.33.23.41.08.41-.08.33-.23.23-.33.08-.41-.08-.41-.23-.33-.33-.23-.41-.08-.41.08z" fill="currentColor" /></svg>10:["$","$L46",null,{"className":"shiki shiki-themes github-light github-dark","style":{"--shiki-light":"#24292e","--shiki-dark":"#e1e4e8","--shiki-light-bg":"#fff","--shiki-dark-bg":"#24292e"},"tabIndex":"0","icon":"$53","children":["$","$L47",null,{"children":["$","code",null,{"children":[["$","span",null,{"className":"line"}],"\n",["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":" from"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" training_gym "}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"import"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" Trainer, TrainingConfig"}]]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" "}]}],"\n",["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" config "}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"="}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" TrainingConfig("}]]}],"\n",["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#E36209","--shiki-dark":"#FFAB70"},"children":" model"}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"="}],["$","span",null,{"style":{"--shiki-light":"#032F62","--shiki-dark":"#9ECBFF"},"children":"\"zen-7b\""}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":","}]]}],"\n",["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#E36209","--shiki-dark":"#FFAB70"},"children":" optimizer"}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"="}],["$","span",null,{"style":{"--shiki-light":"#032F62","--shiki-dark":"#9ECBFF"},"children":"\"adamw\""}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":","}]]}],"\n",["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#E36209","--shiki-dark":"#FFAB70"},"children":" learning_rate"}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"="}],["$","span",null,{"style":{"--shiki-light":"#005CC5","--shiki-dark":"#79B8FF"},"children":"1e-4"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":","}]]}],"\n","$L54","\n","$L55","\n","$L56","\n","$L57","\n","$L58","\n","$L59","\n","$L5a","\n","$L5b","\n","$L5c"]}]}]}]
11:["$","p",null,{"children":"Built-in features:"}]
12:["$","ul",null,{"children":["\n",["$","li",null,{"children":"Learning rate scheduling"}],"\n",["$","li",null,{"children":"Gradient clipping"}],"\n",["$","li",null,{"children":"Mixed precision training"}],"\n",["$","li",null,{"children":"Automatic checkpointing"}],"\n",["$","li",null,{"children":"Loss spike detection and recovery"}],"\n"]}]
13:["$","h3",null,{"className":"flex scroll-m-28 flex-row items-center gap-2","id":"evaluation","children":[["$","a",null,{"data-card":"","href":"#evaluation","className":"peer","children":"Evaluation"}],["$","svg",null,{"xmlns":"http://www.w3.org/2000/svg","width":24,"height":24,"viewBox":"0 0 24 24","fill":"none","stroke":"currentColor","strokeWidth":2,"strokeLinecap":"round","strokeLinejoin":"round","className":"lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100","aria-hidden":true,"children":[["$","path","1cjeqo",{"d":"M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"}],["$","path","19qd67",{"d":"M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"}],"$undefined"]}]]}]
14:["$","p",null,{"children":"Standardized evaluation across common benchmarks:"}]
5d:T5c0,<svg viewBox="0 0 24 24"><path d="M14.25.18l.9.2.73.26.59.3.45.32.34.34.25.34.16.33.1.3.04.26.02.2-.01.13V8.5l-.05.63-.13.55-.21.46-.26.38-.3.31-.33.25-.35.19-.35.14-.33.1-.3.07-.26.04-.21.02H8.77l-.69.05-.59.14-.5.22-.41.27-.33.32-.27.35-.2.36-.15.37-.1.35-.07.32-.04.27-.02.21v3.06H3.17l-.21-.03-.28-.07-.32-.12-.35-.18-.36-.26-.36-.36-.35-.46-.32-.59-.28-.73-.21-.88-.14-1.05-.05-1.23.06-1.22.16-1.04.24-.87.32-.71.36-.57.4-.44.42-.33.42-.24.4-.16.36-.1.32-.05.24-.01h.16l.06.01h8.16v-.83H6.18l-.01-2.75-.02-.37.05-.34.11-.31.17-.28.25-.26.31-.23.38-.2.44-.18.51-.15.58-.12.64-.1.71-.06.77-.04.84-.02 1.27.05zm-6.3 1.98l-.23.33-.08.41.08.41.23.34.33.22.41.09.41-.09.33-.22.23-.34.08-.41-.08-.41-.23-.33-.33-.22-.41-.09-.41.09zm13.09 3.95l.28.06.32.12.35.18.36.27.36.35.35.47.32.59.28.73.21.88.14 1.04.05 1.23-.06 1.23-.16 1.04-.24.86-.32.71-.36.57-.4.45-.42.33-.42.24-.4.16-.36.09-.32.05-.24.02-.16-.01h-8.22v.82h5.84l.01 2.76.02.36-.05.34-.11.31-.17.29-.25.25-.31.24-.38.2-.44.17-.51.15-.58.13-.64.09-.71.07-.77.04-.84.01-1.27-.04-1.07-.14-.9-.2-.73-.25-.59-.3-.45-.33-.34-.34-.25-.34-.16-.33-.1-.3-.04-.25-.02-.2.01-.13v-5.34l.05-.64.13-.54.21-.46.26-.38.3-.32.33-.24.35-.2.35-.14.33-.1.3-.06.26-.04.21-.02.13-.01h5.84l.69-.05.59-.14.5-.21.41-.28.33-.32.27-.35.2-.36.15-.36.1-.35.07-.32.04-.28.02-.21V6.07h2.09l.14.01zm-6.47 14.25l-.23.33-.08.41.08.41.23.33.33.23.41.08.41-.08.33-.23.23-.33.08-.41-.08-.41-.23-.33-.33-.23-.41-.08-.41.08z" fill="currentColor" /></svg>15:["$","$L46",null,{"className":"shiki shiki-themes github-light github-dark","style":{"--shiki-light":"#24292e","--shiki-dark":"#e1e4e8","--shiki-light-bg":"#fff","--shiki-dark-bg":"#24292e"},"tabIndex":"0","icon":"$5d","children":["$","$L47",null,{"children":["$","code",null,{"children":[["$","span",null,{"className":"line"}],"\n",["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":" from"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" training_gym.eval "}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"import"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" Evaluator"}]]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" "}]}],"\n",["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" evaluator "}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"="}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" Evaluator("}]]}],"\n",["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#E36209","--shiki-dark":"#FFAB70"},"children":" benchmarks"}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"="}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":"["}],["$","span",null,{"style":{"--shiki-light":"#032F62","--shiki-dark":"#9ECBFF"},"children":"\"mmlu\""}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":", "}],["$","span",null,{"style":{"--shiki-light":"#032F62","--shiki-dark":"#9ECBFF"},"children":"\"hellaswag\""}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":", "}],["$","span",null,{"style":{"--shiki-light":"#032F62","--shiki-dark":"#9ECBFF"},"children":"\"winogrande\""}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":", "}],["$","span",null,{"style":{"--shiki-light":"#032F62","--shiki-dark":"#9ECBFF"},"children":"\"arc\""}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":"],"}]]}],"\n",["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#E36209","--shiki-dark":"#FFAB70"},"children":" model"}],"$L5e","$L5f"]}],"\n","$L60","\n","$L61","\n","$L62","\n","$L63"]}]}]}]
16:["$","p",null,{"children":"Supported benchmarks:"}]
17:["$","ul",null,{"children":["\n",["$","li",null,{"children":"MMLU (multitask language understanding)"}],"\n",["$","li",null,{"children":"HellaSwag (commonsense reasoning)"}],"\n",["$","li",null,{"children":"WinoGrande (coreference resolution)"}],"\n",["$","li",null,{"children":"ARC (science questions)"}],"\n",["$","li",null,{"children":"TruthfulQA (truthfulness)"}],"\n",["$","li",null,{"children":"HumanEval (code generation)"}],"\n",["$","li",null,{"children":"GSM8K (math reasoning)"}],"\n"]}]
18:["$","h3",null,{"className":"flex scroll-m-28 flex-row items-center gap-2","id":"experiment-tracking","children":[["$","a",null,{"data-card":"","href":"#experiment-tracking","className":"peer","children":"Experiment Tracking"}],["$","svg",null,{"xmlns":"http://www.w3.org/2000/svg","width":24,"height":24,"viewBox":"0 0 24 24","fill":"none","stroke":"currentColor","strokeWidth":2,"strokeLinecap":"round","strokeLinejoin":"round","className":"lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100","aria-hidden":true,"children":[["$","path","1cjeqo",{"d":"M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"}],["$","path","19qd67",{"d":"M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"}],"$undefined"]}]]}]
19:["$","p",null,{"children":"Every training run is tracked:"}]
64:T5c0,<svg viewBox="0 0 24 24"><path d="M14.25.18l.9.2.73.26.59.3.45.32.34.34.25.34.16.33.1.3.04.26.02.2-.01.13V8.5l-.05.63-.13.55-.21.46-.26.38-.3.31-.33.25-.35.19-.35.14-.33.1-.3.07-.26.04-.21.02H8.77l-.69.05-.59.14-.5.22-.41.27-.33.32-.27.35-.2.36-.15.37-.1.35-.07.32-.04.27-.02.21v3.06H3.17l-.21-.03-.28-.07-.32-.12-.35-.18-.36-.26-.36-.36-.35-.46-.32-.59-.28-.73-.21-.88-.14-1.05-.05-1.23.06-1.22.16-1.04.24-.87.32-.71.36-.57.4-.44.42-.33.42-.24.4-.16.36-.1.32-.05.24-.01h.16l.06.01h8.16v-.83H6.18l-.01-2.75-.02-.37.05-.34.11-.31.17-.28.25-.26.31-.23.38-.2.44-.18.51-.15.58-.12.64-.1.71-.06.77-.04.84-.02 1.27.05zm-6.3 1.98l-.23.33-.08.41.08.41.23.34.33.22.41.09.41-.09.33-.22.23-.34.08-.41-.08-.41-.23-.33-.33-.22-.41-.09-.41.09zm13.09 3.95l.28.06.32.12.35.18.36.27.36.35.35.47.32.59.28.73.21.88.14 1.04.05 1.23-.06 1.23-.16 1.04-.24.86-.32.71-.36.57-.4.45-.42.33-.42.24-.4.16-.36.09-.32.05-.24.02-.16-.01h-8.22v.82h5.84l.01 2.76.02.36-.05.34-.11.31-.17.29-.25.25-.31.24-.38.2-.44.17-.51.15-.58.13-.64.09-.71.07-.77.04-.84.01-1.27-.04-1.07-.14-.9-.2-.73-.25-.59-.3-.45-.33-.34-.34-.25-.34-.16-.33-.1-.3-.04-.25-.02-.2.01-.13v-5.34l.05-.64.13-.54.21-.46.26-.38.3-.32.33-.24.35-.2.35-.14.33-.1.3-.06.26-.04.21-.02.13-.01h5.84l.69-.05.59-.14.5-.21.41-.28.33-.32.27-.35.2-.36.15-.36.1-.35.07-.32.04-.28.02-.21V6.07h2.09l.14.01zm-6.47 14.25l-.23.33-.08.41.08.41.23.33.33.23.41.08.41-.08.33-.23.23-.33.08-.41-.08-.41-.23-.33-.33-.23-.41-.08-.41.08z" fill="currentColor" /></svg>1a:["$","$L46",null,{"className":"shiki shiki-themes github-light github-dark","style":{"--shiki-light":"#24292e","--shiki-dark":"#e1e4e8","--shiki-light-bg":"#fff","--shiki-dark-bg":"#24292e"},"tabIndex":"0","icon":"$64","children":["$","$L47",null,{"children":["$","code",null,{"children":[["$","span",null,{"className":"line"}],"\n",["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":" from"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" training_gym "}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"import"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" Experiment"}]]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" "}]}],"\n",["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":" with"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" Experiment("}],["$","span",null,{"style":{"--shiki-light":"#032F62","--shiki-dark":"#9ECBFF"},"children":"\"zen-7b-v2\""}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":") "}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"as"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" exp:"}]]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" exp.log_config(config)"}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" trainer.fit(dataset)"}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" exp.log_metrics(results)"}]}],"\n",["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" exp.log_artifacts(["}],["$","span",null,{"style":{"--shiki-light":"#032F62","--shiki-dark":"#9ECBFF"},"children":"\"model.pt\""}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":", "}],["$","span",null,{"style":{"--shiki-light":"#032F62","--shiki-dark":"#9ECBFF"},"children":"\"tokenizer/\""}],"$L65"]}],"\n","$L66"]}]}]}]
1b:["$","p",null,{"children":"The experiment tracker records:"}]
1c:["$","ul",null,{"children":["\n",["$","li",null,{"children":"Hyperparameters"}],"\n",["$","li",null,{"children":"Training metrics (loss, gradient norms, learning rates)"}],"\n",["$","li",null,{"children":"Evaluation results"}],"\n",["$","li",null,{"children":"System metrics (GPU utilization, memory)"}],"\n",["$","li",null,{"children":"Artifacts (checkpoints, configs)"}],"\n"]}]
1d:["$","h2",null,{"className":"flex scroll-m-28 flex-row items-center gap-2","id":"reproducibility","children":[["$","a",null,{"data-card":"","href":"#reproducibility","className":"peer","children":"Reproducibility"}],["$","svg",null,{"xmlns":"http://www.w3.org/2000/svg","width":24,"height":24,"viewBox":"0 0 24 24","fill":"none","stroke":"currentColor","strokeWidth":2,"strokeLinecap":"round","strokeLinejoin":"round","className":"lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100","aria-hidden":true,"children":[["$","path","1cjeqo",{"d":"M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"}],["$","path","19qd67",{"d":"M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"}],"$undefined"]}]]}]
1e:["$","p",null,{"children":"Training Gym emphasizes reproducibility:"}]
1f:["$","h3",null,{"className":"flex scroll-m-28 flex-row items-center gap-2","id":"deterministic-training","children":[["$","a",null,{"data-card":"","href":"#deterministic-training","className":"peer","children":"Deterministic Training"}],["$","svg",null,{"xmlns":"http://www.w3.org/2000/svg","width":24,"height":24,"viewBox":"0 0 24 24","fill":"none","stroke":"currentColor","strokeWidth":2,"strokeLinecap":"round","strokeLinejoin":"round","className":"lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100","aria-hidden":true,"children":[["$","path","1cjeqo",{"d":"M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"}],["$","path","19qd67",{"d":"M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"}],"$undefined"]}]]}]
20:["$","$L46",null,{"className":"shiki shiki-themes github-light github-dark","style":{"--shiki-light":"#24292e","--shiki-dark":"#e1e4e8","--shiki-light-bg":"#fff","--shiki-dark-bg":"#24292e"},"tabIndex":"0","icon":"<svg viewBox=\"0 0 24 24\"><path d=\"M 6,1 C 4.354992,1 3,2.354992 3,4 v 16 c 0,1.645008 1.354992,3 3,3 h 12 c 1.645008,0 3,-1.354992 3,-3 V 8 7 A 1.0001,1.0001 0 0 0 20.707031,6.2929687 l -5,-5 A 1.0001,1.0001 0 0 0 15,1 h -1 z m 0,2 h 7 v 3 c 0,1.645008 1.354992,3 3,3 h 3 v 11 c 0,0.564129 -0.435871,1 -1,1 H 6 C 5.4358712,21 5,20.564129 5,20 V 4 C 5,3.4358712 5.4358712,3 6,3 Z M 15,3.4140625 18.585937,7 H 16 C 15.435871,7 15,6.5641288 15,6 Z\" fill=\"currentColor\" /></svg>","children":["$","$L47",null,{"children":["$","code",null,{"children":[["$","span",null,{"className":"line","children":["$","span",null,{}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" reproducibility:"}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" seed: 42"}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" deterministic_algorithms: true"}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" cublas_workspace_config: \":4096:8\""}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" "}]}]]}]}]}]
21:["$","p",null,{"children":"Same seed, same results (within floating point precision)."}]
22:["$","h3",null,{"className":"flex scroll-m-28 flex-row items-center gap-2","id":"environment-capture","children":[["$","a",null,{"data-card":"","href":"#environment-capture","className":"peer","children":"Environment Capture"}],["$","svg",null,{"xmlns":"http://www.w3.org/2000/svg","width":24,"height":24,"viewBox":"0 0 24 24","fill":"none","stroke":"currentColor","strokeWidth":2,"strokeLinecap":"round","strokeLinejoin":"round","className":"lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100","aria-hidden":true,"children":[["$","path","1cjeqo",{"d":"M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"}],["$","path","19qd67",{"d":"M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"}],"$undefined"]}]]}]
23:["$","p",null,{"children":"Every experiment records:"}]
24:["$","ul",null,{"children":["\n",["$","li",null,{"children":"Git commit hash"}],"\n",["$","li",null,{"children":"Package versions"}],"\n",["$","li",null,{"children":"Hardware configuration"}],"\n",["$","li",null,{"children":"CUDA/cuDNN versions"}],"\n"]}]
25:["$","h3",null,{"className":"flex scroll-m-28 flex-row items-center gap-2","id":"configuration-as-code","children":[["$","a",null,{"data-card":"","href":"#configuration-as-code","className":"peer","children":"Configuration as Code"}],["$","svg",null,{"xmlns":"http://www.w3.org/2000/svg","width":24,"height":24,"viewBox":"0 0 24 24","fill":"none","stroke":"currentColor","strokeWidth":2,"strokeLinecap":"round","strokeLinejoin":"round","className":"lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100","aria-hidden":true,"children":[["$","path","1cjeqo",{"d":"M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"}],["$","path","19qd67",{"d":"M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"}],"$undefined"]}]]}]
26:["$","p",null,{"children":"All configs are versioned YAML:"}]
27:["$","$L46",null,{"className":"shiki shiki-themes github-light github-dark","style":{"--shiki-light":"#24292e","--shiki-dark":"#e1e4e8","--shiki-light-bg":"#fff","--shiki-dark-bg":"#24292e"},"tabIndex":"0","icon":"<svg viewBox=\"0 0 24 24\"><path d=\"M 6,1 C 4.354992,1 3,2.354992 3,4 v 16 c 0,1.645008 1.354992,3 3,3 h 12 c 1.645008,0 3,-1.354992 3,-3 V 8 7 A 1.0001,1.0001 0 0 0 20.707031,6.2929687 l -5,-5 A 1.0001,1.0001 0 0 0 15,1 h -1 z m 0,2 h 7 v 3 c 0,1.645008 1.354992,3 3,3 h 3 v 11 c 0,0.564129 -0.435871,1 -1,1 H 6 C 5.4358712,21 5,20.564129 5,20 V 4 C 5,3.4358712 5.4358712,3 6,3 Z M 15,3.4140625 18.585937,7 H 16 C 15.435871,7 15,6.5641288 15,6 Z\" fill=\"currentColor\" /></svg>","children":["$","$L47",null,{"children":["$","code",null,{"children":[["$","span",null,{"className":"line","children":["$","span",null,{}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" # experiments/zen-7b-v2.yaml"}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" model:"}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" architecture: llama"}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" hidden_size: 4096"}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" num_layers: 32"}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" num_heads: 32"}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" vocab_size: 32000"}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" "}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" training:"}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" batch_size: 2048"}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" learning_rate: 3e-4"}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" max_steps: 150000"}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" "}]}]]}]}]}]
28:["$","h2",null,{"className":"flex scroll-m-28 flex-row items-center gap-2","id":"community-features","children":[["$","a",null,{"data-card":"","href":"#community-features","className":"peer","children":"Community Features"}],["$","svg",null,{"xmlns":"http://www.w3.org/2000/svg","width":24,"height":24,"viewBox":"0 0 24 24","fill":"none","stroke":"currentColor","strokeWidth":2,"strokeLinecap":"round","strokeLinejoin":"round","className":"lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100","aria-hidden":true,"children":[["$","path","1cjeqo",{"d":"M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"}],["$","path","19qd67",{"d":"M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"}],"$undefined"]}]]}]
29:["$","p",null,{"children":"Training Gym includes tools for collaborative development:"}]
2a:["$","h3",null,{"className":"flex scroll-m-28 flex-row items-center gap-2","id":"model-registry","children":[["$","a",null,{"data-card":"","href":"#model-registry","className":"peer","children":"Model Registry"}],["$","svg",null,{"xmlns":"http://www.w3.org/2000/svg","width":24,"height":24,"viewBox":"0 0 24 24","fill":"none","stroke":"currentColor","strokeWidth":2,"strokeLinecap":"round","strokeLinejoin":"round","className":"lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100","aria-hidden":true,"children":[["$","path","1cjeqo",{"d":"M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"}],["$","path","19qd67",{"d":"M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"}],"$undefined"]}]]}]
2b:["$","p",null,{"children":"Share and discover models:"}]
67:T5c0,<svg viewBox="0 0 24 24"><path d="M14.25.18l.9.2.73.26.59.3.45.32.34.34.25.34.16.33.1.3.04.26.02.2-.01.13V8.5l-.05.63-.13.55-.21.46-.26.38-.3.31-.33.25-.35.19-.35.14-.33.1-.3.07-.26.04-.21.02H8.77l-.69.05-.59.14-.5.22-.41.27-.33.32-.27.35-.2.36-.15.37-.1.35-.07.32-.04.27-.02.21v3.06H3.17l-.21-.03-.28-.07-.32-.12-.35-.18-.36-.26-.36-.36-.35-.46-.32-.59-.28-.73-.21-.88-.14-1.05-.05-1.23.06-1.22.16-1.04.24-.87.32-.71.36-.57.4-.44.42-.33.42-.24.4-.16.36-.1.32-.05.24-.01h.16l.06.01h8.16v-.83H6.18l-.01-2.75-.02-.37.05-.34.11-.31.17-.28.25-.26.31-.23.38-.2.44-.18.51-.15.58-.12.64-.1.71-.06.77-.04.84-.02 1.27.05zm-6.3 1.98l-.23.33-.08.41.08.41.23.34.33.22.41.09.41-.09.33-.22.23-.34.08-.41-.08-.41-.23-.33-.33-.22-.41-.09-.41.09zm13.09 3.95l.28.06.32.12.35.18.36.27.36.35.35.47.32.59.28.73.21.88.14 1.04.05 1.23-.06 1.23-.16 1.04-.24.86-.32.71-.36.57-.4.45-.42.33-.42.24-.4.16-.36.09-.32.05-.24.02-.16-.01h-8.22v.82h5.84l.01 2.76.02.36-.05.34-.11.31-.17.29-.25.25-.31.24-.38.2-.44.17-.51.15-.58.13-.64.09-.71.07-.77.04-.84.01-1.27-.04-1.07-.14-.9-.2-.73-.25-.59-.3-.45-.33-.34-.34-.25-.34-.16-.33-.1-.3-.04-.25-.02-.2.01-.13v-5.34l.05-.64.13-.54.21-.46.26-.38.3-.32.33-.24.35-.2.35-.14.33-.1.3-.06.26-.04.21-.02.13-.01h5.84l.69-.05.59-.14.5-.21.41-.28.33-.32.27-.35.2-.36.15-.36.1-.35.07-.32.04-.28.02-.21V6.07h2.09l.14.01zm-6.47 14.25l-.23.33-.08.41.08.41.23.33.33.23.41.08.41-.08.33-.23.23-.33.08-.41-.08-.41-.23-.33-.33-.23-.41-.08-.41.08z" fill="currentColor" /></svg>2c:["$","$L46",null,{"className":"shiki shiki-themes github-light github-dark","style":{"--shiki-light":"#24292e","--shiki-dark":"#e1e4e8","--shiki-light-bg":"#fff","--shiki-dark-bg":"#24292e"},"tabIndex":"0","icon":"$67","children":["$","$L47",null,{"children":["$","code",null,{"children":[["$","span",null,{"className":"line"}],"\n",["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":" from"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" training_gym.registry "}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"import"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" ModelRegistry"}]]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" "}]}],"\n",["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" registry "}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"="}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" ModelRegistry()"}]]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" "}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#6A737D","--shiki-dark":"#6A737D"},"children":" # Publish a model"}]}],"\n",["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" registry.push("}],["$","span",null,{"style":{"--shiki-light":"#032F62","--shiki-dark":"#9ECBFF"},"children":"\"my-org/my-model\""}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":", model, config)"}]]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" "}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#6A737D","--shiki-dark":"#6A737D"},"children":" # Load a model"}]}],"\n",["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" model "}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"="}],"$L68","$L69","$L6a"]}],"\n","$L6b"]}]}]}]
2d:["$","h3",null,{"className":"flex scroll-m-28 flex-row items-center gap-2","id":"leaderboards","children":[["$","a",null,{"data-card":"","href":"#leaderboards","className":"peer","children":"Leaderboards"}],["$","svg",null,{"xmlns":"http://www.w3.org/2000/svg","width":24,"height":24,"viewBox":"0 0 24 24","fill":"none","stroke":"currentColor","strokeWidth":2,"strokeLinecap":"round","strokeLinejoin":"round","className":"lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100","aria-hidden":true,"children":[["$","path","1cjeqo",{"d":"M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"}],["$","path","19qd67",{"d":"M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"}],"$undefined"]}]]}]
2e:["$","p",null,{"children":"Automatic benchmark submission:"}]
2f:["$","$L46",null,{"className":"shiki shiki-themes github-light github-dark","style":{"--shiki-light":"#24292e","--shiki-dark":"#e1e4e8","--shiki-light-bg":"#fff","--shiki-dark-bg":"#24292e"},"tabIndex":"0","icon":"<svg viewBox=\"0 0 24 24\"><path d=\"M 6,1 C 4.354992,1 3,2.354992 3,4 v 16 c 0,1.645008 1.354992,3 3,3 h 12 c 1.645008,0 3,-1.354992 3,-3 V 8 7 A 1.0001,1.0001 0 0 0 20.707031,6.2929687 l -5,-5 A 1.0001,1.0001 0 0 0 15,1 h -1 z m 0,2 h 7 v 3 c 0,1.645008 1.354992,3 3,3 h 3 v 11 c 0,0.564129 -0.435871,1 -1,1 H 6 C 5.4358712,21 5,20.564129 5,20 V 4 C 5,3.4358712 5.4358712,3 6,3 Z M 15,3.4140625 18.585937,7 H 16 C 15.435871,7 15,6.5641288 15,6 Z\" fill=\"currentColor\" /></svg>","children":["$","$L47",null,{"children":["$","code",null,{"children":[["$","span",null,{"className":"line","children":["$","span",null,{}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" evaluator.submit_to_leaderboard("}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" model_name=\"zen-7b-v2\","}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" organization=\"zoo-labs\","}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" )"}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" "}]}]]}]}]}]
30:["$","h3",null,{"className":"flex scroll-m-28 flex-row items-center gap-2","id":"dataset-sharing","children":[["$","a",null,{"data-card":"","href":"#dataset-sharing","className":"peer","children":"Dataset Sharing"}],["$","svg",null,{"xmlns":"http://www.w3.org/2000/svg","width":24,"height":24,"viewBox":"0 0 24 24","fill":"none","stroke":"currentColor","strokeWidth":2,"strokeLinecap":"round","strokeLinejoin":"round","className":"lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100","aria-hidden":true,"children":[["$","path","1cjeqo",{"d":"M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"}],["$","path","19qd67",{"d":"M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"}],"$undefined"]}]]}]
6c:T5c0,<svg viewBox="0 0 24 24"><path d="M14.25.18l.9.2.73.26.59.3.45.32.34.34.25.34.16.33.1.3.04.26.02.2-.01.13V8.5l-.05.63-.13.55-.21.46-.26.38-.3.31-.33.25-.35.19-.35.14-.33.1-.3.07-.26.04-.21.02H8.77l-.69.05-.59.14-.5.22-.41.27-.33.32-.27.35-.2.36-.15.37-.1.35-.07.32-.04.27-.02.21v3.06H3.17l-.21-.03-.28-.07-.32-.12-.35-.18-.36-.26-.36-.36-.35-.46-.32-.59-.28-.73-.21-.88-.14-1.05-.05-1.23.06-1.22.16-1.04.24-.87.32-.71.36-.57.4-.44.42-.33.42-.24.4-.16.36-.1.32-.05.24-.01h.16l.06.01h8.16v-.83H6.18l-.01-2.75-.02-.37.05-.34.11-.31.17-.28.25-.26.31-.23.38-.2.44-.18.51-.15.58-.12.64-.1.71-.06.77-.04.84-.02 1.27.05zm-6.3 1.98l-.23.33-.08.41.08.41.23.34.33.22.41.09.41-.09.33-.22.23-.34.08-.41-.08-.41-.23-.33-.33-.22-.41-.09-.41.09zm13.09 3.95l.28.06.32.12.35.18.36.27.36.35.35.47.32.59.28.73.21.88.14 1.04.05 1.23-.06 1.23-.16 1.04-.24.86-.32.71-.36.57-.4.45-.42.33-.42.24-.4.16-.36.09-.32.05-.24.02-.16-.01h-8.22v.82h5.84l.01 2.76.02.36-.05.34-.11.31-.17.29-.25.25-.31.24-.38.2-.44.17-.51.15-.58.13-.64.09-.71.07-.77.04-.84.01-1.27-.04-1.07-.14-.9-.2-.73-.25-.59-.3-.45-.33-.34-.34-.25-.34-.16-.33-.1-.3-.04-.25-.02-.2.01-.13v-5.34l.05-.64.13-.54.21-.46.26-.38.3-.32.33-.24.35-.2.35-.14.33-.1.3-.06.26-.04.21-.02.13-.01h5.84l.69-.05.59-.14.5-.21.41-.28.33-.32.27-.35.2-.36.15-.36.1-.35.07-.32.04-.28.02-.21V6.07h2.09l.14.01zm-6.47 14.25l-.23.33-.08.41.08.41.23.33.33.23.41.08.41-.08.33-.23.23-.33.08-.41-.08-.41-.23-.33-.33-.23-.41-.08-.41.08z" fill="currentColor" /></svg>31:["$","$L46",null,{"className":"shiki shiki-themes github-light github-dark","style":{"--shiki-light":"#24292e","--shiki-dark":"#e1e4e8","--shiki-light-bg":"#fff","--shiki-dark-bg":"#24292e"},"tabIndex":"0","icon":"$6c","children":["$","$L47",null,{"children":["$","code",null,{"children":[["$","span",null,{"className":"line"}],"\n",["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":" from"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" training_gym.data "}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"import"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" DatasetRegistry"}]]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" "}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#6A737D","--shiki-dark":"#6A737D"},"children":" # Share processed datasets"}]}],"\n",["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" DatasetRegistry.push("}],["$","span",null,{"style":{"--shiki-light":"#032F62","--shiki-dark":"#9ECBFF"},"children":"\"my-corpus\""}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":", dataset, "}],["$","span",null,{"style":{"--shiki-light":"#E36209","--shiki-dark":"#FFAB70"},"children":"license"}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"="}],["$","span",null,{"style":{"--shiki-light":"#032F62","--shiki-dark":"#9ECBFF"},"children":"\"cc-by-4.0\""}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":")"}]]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" "}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#6A737D","--shiki-dark":"#6A737D"},"children":" # Load shared datasets"}]}],"\n",["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" dataset "}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"="}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" DatasetRegistry.pull("}],"$L6d","$L6e"]}],"\n","$L6f"]}]}]}]
32:["$","h2",null,{"className":"flex scroll-m-28 flex-row items-center gap-2","id":"getting-started","children":[["$","a",null,{"data-card":"","href":"#getting-started","className":"peer","children":"Getting Started"}],["$","svg",null,{"xmlns":"http://www.w3.org/2000/svg","width":24,"height":24,"viewBox":"0 0 24 24","fill":"none","stroke":"currentColor","strokeWidth":2,"strokeLinecap":"round","strokeLinejoin":"round","className":"lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100","aria-hidden":true,"children":[["$","path","1cjeqo",{"d":"M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"}],["$","path","19qd67",{"d":"M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"}],"$undefined"]}]]}]
33:["$","h3",null,{"className":"flex scroll-m-28 flex-row items-center gap-2","id":"installation","children":[["$","a",null,{"data-card":"","href":"#installation","className":"peer","children":"Installation"}],["$","svg",null,{"xmlns":"http://www.w3.org/2000/svg","width":24,"height":24,"viewBox":"0 0 24 24","fill":"none","stroke":"currentColor","strokeWidth":2,"strokeLinecap":"round","strokeLinejoin":"round","className":"lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100","aria-hidden":true,"children":[["$","path","1cjeqo",{"d":"M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"}],["$","path","19qd67",{"d":"M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"}],"$undefined"]}]]}]
34:["$","$L46",null,{"className":"shiki shiki-themes github-light github-dark","style":{"--shiki-light":"#24292e","--shiki-dark":"#e1e4e8","--shiki-light-bg":"#fff","--shiki-dark-bg":"#24292e"},"tabIndex":"0","icon":"<svg viewBox=\"0 0 24 24\"><path d=\"m 4,4 a 1,1 0 0 0 -0.7070312,0.2929687 1,1 0 0 0 0,1.4140625 L 8.5859375,11 3.2929688,16.292969 a 1,1 0 0 0 0,1.414062 1,1 0 0 0 1.4140624,0 l 5.9999998,-6 a 1.0001,1.0001 0 0 0 0,-1.414062 L 4.7070312,4.2929687 A 1,1 0 0 0 4,4 Z m 8,14 a 1,1 0 0 0 -1,1 1,1 0 0 0 1,1 h 8 a 1,1 0 0 0 1,-1 1,1 0 0 0 -1,-1 z\" fill=\"currentColor\" /></svg>","children":["$","$L47",null,{"children":["$","code",null,{"children":[["$","span",null,{"className":"line"}],"\n",["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#6F42C1","--shiki-dark":"#B392F0"},"children":" pip"}],["$","span",null,{"style":{"--shiki-light":"#032F62","--shiki-dark":"#9ECBFF"},"children":" install"}],["$","span",null,{"style":{"--shiki-light":"#032F62","--shiki-dark":"#9ECBFF"},"children":" training-gym"}]]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" "}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#6A737D","--shiki-dark":"#6A737D"},"children":" # For distributed training"}]}],"\n",["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#6F42C1","--shiki-dark":"#B392F0"},"children":" pip"}],["$","span",null,{"style":{"--shiki-light":"#032F62","--shiki-dark":"#9ECBFF"},"children":" install"}],["$","span",null,{"style":{"--shiki-light":"#032F62","--shiki-dark":"#9ECBFF"},"children":" training-gym[distributed]"}]]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" "}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#6A737D","--shiki-dark":"#6A737D"},"children":" # For evaluation suite"}]}],"\n",["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#6F42C1","--shiki-dark":"#B392F0"},"children":" pip"}],["$","span",null,{"style":{"--shiki-light":"#032F62","--shiki-dark":"#9ECBFF"},"children":" install"}],["$","span",null,{"style":{"--shiki-light":"#032F62","--shiki-dark":"#9ECBFF"},"children":" training-gym[eval]"}]]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" "}]}]]}]}]}]
35:["$","h3",null,{"className":"flex scroll-m-28 flex-row items-center gap-2","id":"quick-start","children":[["$","a",null,{"data-card":"","href":"#quick-start","className":"peer","children":"Quick Start"}],["$","svg",null,{"xmlns":"http://www.w3.org/2000/svg","width":24,"height":24,"viewBox":"0 0 24 24","fill":"none","stroke":"currentColor","strokeWidth":2,"strokeLinecap":"round","strokeLinejoin":"round","className":"lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100","aria-hidden":true,"children":[["$","path","1cjeqo",{"d":"M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"}],["$","path","19qd67",{"d":"M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"}],"$undefined"]}]]}]
70:T5c0,<svg viewBox="0 0 24 24"><path d="M14.25.18l.9.2.73.26.59.3.45.32.34.34.25.34.16.33.1.3.04.26.02.2-.01.13V8.5l-.05.63-.13.55-.21.46-.26.38-.3.31-.33.25-.35.19-.35.14-.33.1-.3.07-.26.04-.21.02H8.77l-.69.05-.59.14-.5.22-.41.27-.33.32-.27.35-.2.36-.15.37-.1.35-.07.32-.04.27-.02.21v3.06H3.17l-.21-.03-.28-.07-.32-.12-.35-.18-.36-.26-.36-.36-.35-.46-.32-.59-.28-.73-.21-.88-.14-1.05-.05-1.23.06-1.22.16-1.04.24-.87.32-.71.36-.57.4-.44.42-.33.42-.24.4-.16.36-.1.32-.05.24-.01h.16l.06.01h8.16v-.83H6.18l-.01-2.75-.02-.37.05-.34.11-.31.17-.28.25-.26.31-.23.38-.2.44-.18.51-.15.58-.12.64-.1.71-.06.77-.04.84-.02 1.27.05zm-6.3 1.98l-.23.33-.08.41.08.41.23.34.33.22.41.09.41-.09.33-.22.23-.34.08-.41-.08-.41-.23-.33-.33-.22-.41-.09-.41.09zm13.09 3.95l.28.06.32.12.35.18.36.27.36.35.35.47.32.59.28.73.21.88.14 1.04.05 1.23-.06 1.23-.16 1.04-.24.86-.32.71-.36.57-.4.45-.42.33-.42.24-.4.16-.36.09-.32.05-.24.02-.16-.01h-8.22v.82h5.84l.01 2.76.02.36-.05.34-.11.31-.17.29-.25.25-.31.24-.38.2-.44.17-.51.15-.58.13-.64.09-.71.07-.77.04-.84.01-1.27-.04-1.07-.14-.9-.2-.73-.25-.59-.3-.45-.33-.34-.34-.25-.34-.16-.33-.1-.3-.04-.25-.02-.2.01-.13v-5.34l.05-.64.13-.54.21-.46.26-.38.3-.32.33-.24.35-.2.35-.14.33-.1.3-.06.26-.04.21-.02.13-.01h5.84l.69-.05.59-.14.5-.21.41-.28.33-.32.27-.35.2-.36.15-.36.1-.35.07-.32.04-.28.02-.21V6.07h2.09l.14.01zm-6.47 14.25l-.23.33-.08.41.08.41.23.33.33.23.41.08.41-.08.33-.23.23-.33.08-.41-.08-.41-.23-.33-.33-.23-.41-.08-.41.08z" fill="currentColor" /></svg>36:["$","$L46",null,{"className":"shiki shiki-themes github-light github-dark","style":{"--shiki-light":"#24292e","--shiki-dark":"#e1e4e8","--shiki-light-bg":"#fff","--shiki-dark-bg":"#24292e"},"tabIndex":"0","icon":"$70","children":["$","$L47",null,{"children":["$","code",null,{"children":[["$","span",null,{"className":"line"}],"\n",["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":" from"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" training_gym "}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"import"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" quickstart"}]]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" "}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#6A737D","--shiki-dark":"#6A737D"},"children":" # Train a small model to verify setup"}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" quickstart.train_tiny_model()"}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" "}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#6A737D","--shiki-dark":"#6A737D"},"children":" # Run evaluation suite"}]}],"\n",["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" quickstart.evaluate_model("}],["$","span",null,{"style":{"--shiki-light":"#032F62","--shiki-dark":"#9ECBFF"},"children":"\"my-model\""}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":")"}]]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" "}]}]]}]}]}]
37:["$","h3",null,{"className":"flex scroll-m-28 flex-row items-center gap-2","id":"documentation","children":[["$","a",null,{"data-card":"","href":"#documentation","className":"peer","children":"Documentation"}],["$","svg",null,{"xmlns":"http://www.w3.org/2000/svg","width":24,"height":24,"viewBox":"0 0 24 24","fill":"none","stroke":"currentColor","strokeWidth":2,"strokeLinecap":"round","strokeLinejoin":"round","className":"lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100","aria-hidden":true,"children":[["$","path","1cjeqo",{"d":"M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"}],["$","path","19qd67",{"d":"M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"}],"$undefined"]}]]}]
38:["$","p",null,{"children":"Full documentation at docs.training-gym.ai:"}]
39:["$","ul",null,{"children":["\n",["$","li",null,{"children":"Getting started guide"}],"\n",["$","li",null,{"children":"Architecture overview"}],"\n",["$","li",null,{"children":"API reference"}],"\n",["$","li",null,{"children":"Example configurations"}],"\n",["$","li",null,{"children":"Troubleshooting"}],"\n"]}]
3a:["$","h2",null,{"className":"flex scroll-m-28 flex-row items-center gap-2","id":"roadmap","children":[["$","a",null,{"data-card":"","href":"#roadmap","className":"peer","children":"Roadmap"}],["$","svg",null,{"xmlns":"http://www.w3.org/2000/svg","width":24,"height":24,"viewBox":"0 0 24 24","fill":"none","stroke":"currentColor","strokeWidth":2,"strokeLinecap":"round","strokeLinejoin":"round","className":"lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100","aria-hidden":true,"children":[["$","path","1cjeqo",{"d":"M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"}],["$","path","19qd67",{"d":"M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"}],"$undefined"]}]]}]
3b:["$","p",null,{"children":[["$","strong",null,{"children":"Q4 2023"}]," : Multi-modal training support ",["$","strong",null,{"children":"Q1 2024"}]," : Reinforcement learning from human feedback (RLHF) integration ",["$","strong",null,{"children":"Q2 2024"}]," : Federated training support ",["$","strong",null,{"children":"Q3 2024"}]," : Automated hyperparameter optimization"]}]
3c:["$","h2",null,{"className":"flex scroll-m-28 flex-row items-center gap-2","id":"conclusion","children":[["$","a",null,{"data-card":"","href":"#conclusion","className":"peer","children":"Conclusion"}],["$","svg",null,{"xmlns":"http://www.w3.org/2000/svg","width":24,"height":24,"viewBox":"0 0 24 24","fill":"none","stroke":"currentColor","strokeWidth":2,"strokeLinecap":"round","strokeLinejoin":"round","className":"lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100","aria-hidden":true,"children":[["$","path","1cjeqo",{"d":"M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"}],["$","path","19qd67",{"d":"M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"}],"$undefined"]}]]}]
3d:["$","p",null,{"children":"Open AI development needs open infrastructure. Training Gym provides the tools to train, evaluate, and share models. Join us in building the future of open AI."}]
3e:["$","p",null,{"children":"Repository: github.com/zoo-labs/training-gym"}]
3f:["$","hr",null,{}]
40:["$","p",null,{"children":["$","em",null,{"children":"Zach Kelling is a co-founder of Zoo Labs Foundation."}]}]
41:["$","script","script-0",{"src":"/_next/static/chunks/8de849ca74fc071f.js","async":true}]
42:["$","script","script-1",{"src":"/_next/static/chunks/e62b91212ee7f8ff.js","async":true}]
43:["$","script","script-2",{"src":"/_next/static/chunks/f19fe44237e54646.js","async":true}]
44:["$","script","script-3",{"src":"/_next/static/chunks/cb0a883bafeb6805.js","async":true}]
45:["$","$L71",null,{"children":["$","$72",null,{"name":"Next.MetadataOutlet","children":"$@73"}]}]
49:["$","span",null,{"style":{"--shiki-light":"#005CC5","--shiki-dark":"#79B8FF"},"children":"0.5"}]
4a:["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":"),"}]
4b:["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" ("}],["$","span",null,{"style":{"--shiki-light":"#032F62","--shiki-dark":"#9ECBFF"},"children":"\"s3://data/code\""}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":", "}],["$","span",null,{"style":{"--shiki-light":"#005CC5","--shiki-dark":"#79B8FF"},"children":"0.2"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":"),"}]]}]
4c:["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" ],"}]}]
4d:["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#E36209","--shiki-dark":"#FFAB70"},"children":" tokenizer"}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"="}],["$","span",null,{"style":{"--shiki-light":"#032F62","--shiki-dark":"#9ECBFF"},"children":"\"zoo-labs/zen-tokenizer\""}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":","}]]}]
4e:["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#E36209","--shiki-dark":"#FFAB70"},"children":" sequence_length"}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"="}],["$","span",null,{"style":{"--shiki-light":"#005CC5","--shiki-dark":"#79B8FF"},"children":"2048"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":","}]]}]
4f:["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" )"}]}]
50:["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" "}]}]
51:["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" dataset "}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"="}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" pipeline.build()"}]]}]
52:["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" "}]}]
54:["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#E36209","--shiki-dark":"#FFAB70"},"children":" batch_size"}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"="}],["$","span",null,{"style":{"--shiki-light":"#005CC5","--shiki-dark":"#79B8FF"},"children":"2048"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":","}]]}]
55:["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#E36209","--shiki-dark":"#FFAB70"},"children":" max_steps"}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"="}],["$","span",null,{"style":{"--shiki-light":"#005CC5","--shiki-dark":"#79B8FF"},"children":"100000"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":","}]]}]
56:["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#E36209","--shiki-dark":"#FFAB70"},"children":" warmup_steps"}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"="}],["$","span",null,{"style":{"--shiki-light":"#005CC5","--shiki-dark":"#79B8FF"},"children":"2000"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":","}]]}]
57:["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#E36209","--shiki-dark":"#FFAB70"},"children":" weight_decay"}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"="}],["$","span",null,{"style":{"--shiki-light":"#005CC5","--shiki-dark":"#79B8FF"},"children":"0.1"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":","}]]}]
58:["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" )"}]}]
59:["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" "}]}]
5a:["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" trainer "}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"="}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" Trainer(config)"}]]}]
5b:["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" trainer.fit(dataset)"}]}]
5c:["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" "}]}]
5e:["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"="}]
5f:["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":"model,"}]
60:["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" )"}]}]
61:["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" "}]}]
62:["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" results "}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"="}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" evaluator.run()"}]]}]
63:["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" "}]}]
65:["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":"])"}]
66:["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" "}]}]
68:["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" registry.pull("}]
69:["$","span",null,{"style":{"--shiki-light":"#032F62","--shiki-dark":"#9ECBFF"},"children":"\"zoo-labs/zen-7b\""}]
6a:["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":")"}]
6b:["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" "}]}]
6d:["$","span",null,{"style":{"--shiki-light":"#032F62","--shiki-dark":"#9ECBFF"},"children":"\"zoo-labs/zen-pretrain-v1\""}]
6e:["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":")"}]
6f:["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" "}]}]
73:null