Image-Text-to-Text
PEFT
Safetensors
vision-language
multimodal
llava
lora
siglip2
n-atlas
nigerian-languages
Instructions to use Modularcomputing/AtlasVision with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Modularcomputing/AtlasVision with PEFT:
Task type is invalid.
- Notebooks
- Google Colab
- Kaggle
Download logs/stage1_train_log.jsonl from Modularcomputing/AtlasVision: direct link, hf CLI and curl.
- Browser
- Download file 80.8 kB
-
https://huggingface.co/Modularcomputing/AtlasVision/resolve/main/logs/stage1_train_log.jsonl
- Command line
-
hf download hf://Modularcomputing/AtlasVision/logs/stage1_train_log.jsonl
-
curl -L -o stage1_train_log.jsonl https://huggingface.co/Modularcomputing/AtlasVision/resolve/main/logs/stage1_train_log.jsonl
80.8 kB
| {"step": 1, "loss": 8.55087947845459, "grad_norm": 87.72406768798828, "lr": 7.117437722419929e-07, "s_per_step": 8.396198749542236, "peak_gb": 41.247548928, "samples_seen": 32, "time": 1791130833.9630904} | |
| {"step": 25, "loss": 6.397367646296819, "grad_norm": 15.911425590515137, "lr": 1.779359430604982e-05, "s_per_step": 0.6239869793256124, "peak_gb": 42.138478592, "samples_seen": 800, "time": 1791130848.9393055} | |
| {"step": 50, "loss": 4.635109643936158, "grad_norm": 7.2413105964660645, "lr": 3.558718861209964e-05, "s_per_step": 0.5889950180053711, "peak_gb": 42.138478592, "samples_seen": 1600, "time": 1791130863.664765} | |
| {"step": 75, "loss": 4.093637528419495, "grad_norm": 4.90704870223999, "lr": 5.338078291814947e-05, "s_per_step": 0.5850510597229004, "peak_gb": 42.138478592, "samples_seen": 2400, "time": 1791130878.2915204} | |
| {"step": 100, "loss": 3.8673372650146485, "grad_norm": 4.5811944007873535, "lr": 7.117437722419929e-05, "s_per_step": 0.623746509552002, "peak_gb": 44.713082368, "samples_seen": 3200, "time": 1791130893.8860688} | |
| {"step": 125, "loss": 3.740880389213562, "grad_norm": 3.184147834777832, "lr": 8.896797153024912e-05, "s_per_step": 0.5818255233764649, "peak_gb": 44.713082368, "samples_seen": 4000, "time": 1791130908.432502} | |
| {"step": 150, "loss": 3.7184673833847044, "grad_norm": 2.9738147258758545, "lr": 0.00010676156583629893, "s_per_step": 0.576975965499878, "peak_gb": 44.713082368, "samples_seen": 4800, "time": 1791130922.857381} | |
| {"step": 175, "loss": 3.5475265645980834, "grad_norm": 2.332338333129883, "lr": 0.00012455516014234878, "s_per_step": 0.5761029434204101, "peak_gb": 44.713082368, "samples_seen": 5600, "time": 1791130937.2603934} | |
| {"step": 200, "loss": 3.5738428688049315, "grad_norm": 1.9974111318588257, "lr": 0.00014234875444839857, "s_per_step": 0.580996150970459, "peak_gb": 44.713082368, "samples_seen": 6400, "time": 1791130951.7857678} | |
| {"step": 225, "loss": 3.5230879592895508, "grad_norm": 1.8189729452133179, "lr": 0.00016014234875444842, "s_per_step": 0.5787319278717041, "peak_gb": 44.713082368, "samples_seen": 7200, "time": 1791130966.2545114} | |
| {"step": 250, "loss": 3.4794790887832643, "grad_norm": 2.1197030544281006, "lr": 0.00017793594306049823, "s_per_step": 0.5812134552001953, "peak_gb": 44.713082368, "samples_seen": 8000, "time": 1791130980.7852197} | |
| {"step": 275, "loss": 3.5135861301422118, "grad_norm": 2.010641098022461, "lr": 0.00019572953736654805, "s_per_step": 0.5902993679046631, "peak_gb": 44.713082368, "samples_seen": 8800, "time": 1791130995.5431538} | |
| {"step": 300, "loss": 3.332580523490906, "grad_norm": 1.7257816791534424, "lr": 0.00019999806668125934, "s_per_step": 0.5805612754821777, "peak_gb": 44.713082368, "samples_seen": 9600, "time": 1791131010.0576127} | |
| {"step": 325, "loss": 3.331582636833191, "grad_norm": 1.817513346672058, "lr": 0.0001999889671230344, "s_per_step": 0.5767327976226807, "peak_gb": 44.713082368, "samples_seen": 10400, "time": 1791131024.4763641} | |
| {"step": 350, "loss": 3.3034389925003054, "grad_norm": 1.4937862157821655, "lr": 0.00019997240961861618, "s_per_step": 0.5783243465423584, "peak_gb": 44.713082368, "samples_seen": 11200, "time": 1791131038.9348876} | |
| {"step": 375, "loss": 3.310972599983215, "grad_norm": 1.4323818683624268, "lr": 0.00019994839540299076, "s_per_step": 0.5792804718017578, "peak_gb": 44.713082368, "samples_seen": 12000, "time": 1791131053.417312} | |
| {"step": 400, "loss": 3.287726469039917, "grad_norm": 1.5991160869598389, "lr": 0.000199916926267323, "s_per_step": 0.578808069229126, "peak_gb": 44.713082368, "samples_seen": 12800, "time": 1791131067.8879645} | |
| {"step": 425, "loss": 3.2084068727493285, "grad_norm": 1.271116018295288, "lr": 0.00019987800455882306, "s_per_step": 0.5803878498077393, "peak_gb": 44.713082368, "samples_seen": 13600, "time": 1791131082.3980415} | |
| {"step": 450, "loss": 3.2198647975921633, "grad_norm": 1.286621332168579, "lr": 0.00019983163318057137, "s_per_step": 0.5836947727203369, "peak_gb": 44.713082368, "samples_seen": 14400, "time": 1791131096.991321} | |
| {"step": 475, "loss": 3.1718136644363404, "grad_norm": 1.3426055908203125, "lr": 0.00019977781559130187, "s_per_step": 0.5814045429229736, "peak_gb": 44.713082368, "samples_seen": 15200, "time": 1791131111.52718} | |
| {"step": 500, "loss": 3.176059513092041, "grad_norm": 1.3492554426193237, "lr": 0.00019971655580514438, "s_per_step": 0.5872831630706787, "peak_gb": 44.713082368, "samples_seen": 16000, "time": 1791131126.2099152} | |
| {"step": 525, "loss": 3.1693886518478394, "grad_norm": 1.2558445930480957, "lr": 0.00019964785839132488, "s_per_step": 0.6033973217010498, "peak_gb": 44.713082368, "samples_seen": 16800, "time": 1791131141.295349} | |
| {"step": 550, "loss": 3.14515998840332, "grad_norm": 1.2257124185562134, "lr": 0.0001995717284738248, "s_per_step": 0.5826546669006347, "peak_gb": 44.713082368, "samples_seen": 17600, "time": 1791131155.8622203} | |
| {"step": 575, "loss": 3.12627272605896, "grad_norm": 1.2098281383514404, "lr": 0.000199488171730999, "s_per_step": 0.582458963394165, "peak_gb": 44.713082368, "samples_seen": 18400, "time": 1791131170.424219} | |
| {"step": 600, "loss": 3.135997772216797, "grad_norm": 1.3937653303146362, "lr": 0.0001993971943951519, "s_per_step": 0.5858418941497803, "peak_gb": 44.713082368, "samples_seen": 19200, "time": 1791131185.0707946} | |
| {"step": 625, "loss": 3.0999442672729494, "grad_norm": 1.0516718626022339, "lr": 0.000199298803252073, "s_per_step": 0.5833398532867432, "peak_gb": 44.713082368, "samples_seen": 20000, "time": 1791131199.654984} | |
| {"step": 650, "loss": 3.080396270751953, "grad_norm": 1.1961040496826172, "lr": 0.00019919300564053046, "s_per_step": 0.6152436542510986, "peak_gb": 44.713082368, "samples_seen": 20800, "time": 1791131215.037142} | |
| {"step": 675, "loss": 3.0702759647369384, "grad_norm": 1.0449596643447876, "lr": 0.00019907980945172384, "s_per_step": 0.5828781223297119, "peak_gb": 44.713082368, "samples_seen": 21600, "time": 1791131229.609633} | |
| {"step": 700, "loss": 3.0974017333984376, "grad_norm": 1.0658111572265625, "lr": 0.00019895922312869555, "s_per_step": 0.5841869640350342, "peak_gb": 44.713082368, "samples_seen": 22400, "time": 1791131244.2148454} | |
| {"step": 725, "loss": 3.074553599357605, "grad_norm": 0.9470886588096619, "lr": 0.00019883125566570094, "s_per_step": 0.5814198112487793, "peak_gb": 44.713082368, "samples_seen": 23200, "time": 1791131258.7509072} | |
| {"step": 750, "loss": 3.1141643714904785, "grad_norm": 1.1800023317337036, "lr": 0.00019869591660753763, "s_per_step": 0.5784324645996094, "peak_gb": 44.713082368, "samples_seen": 24000, "time": 1791131273.212172} | |
| {"step": 775, "loss": 3.1024985694885254, "grad_norm": 1.0973631143569946, "lr": 0.00019855321604883352, "s_per_step": 0.5959490013122558, "peak_gb": 44.713082368, "samples_seen": 24800, "time": 1791131288.1113417} | |
| {"step": 800, "loss": 3.095311689376831, "grad_norm": 1.2262718677520752, "lr": 0.00019840316463329378, "s_per_step": 0.5826352882385254, "peak_gb": 44.713082368, "samples_seen": 25600, "time": 1791131302.6778867} | |
| {"step": 825, "loss": 3.0253290700912476, "grad_norm": 1.2020397186279297, "lr": 0.000198245773552907, "s_per_step": 0.5797882652282715, "peak_gb": 44.713082368, "samples_seen": 26400, "time": 1791131317.173062} | |
| {"step": 850, "loss": 3.0069773197174072, "grad_norm": 1.1738593578338623, "lr": 0.00019808105454711055, "s_per_step": 0.5793154048919678, "peak_gb": 44.713082368, "samples_seen": 27200, "time": 1791131331.6564252} | |
| {"step": 875, "loss": 2.975392165184021, "grad_norm": 0.9737287163734436, "lr": 0.0001979090199019147, "s_per_step": 0.5790924072265625, "peak_gb": 44.713082368, "samples_seen": 28000, "time": 1791131346.1341693} | |
| {"step": 900, "loss": 2.9498213052749636, "grad_norm": 1.2708204984664917, "lr": 0.0001977296824489864, "s_per_step": 0.5816666603088378, "peak_gb": 44.713082368, "samples_seen": 28800, "time": 1791131360.676415} | |
| {"step": 925, "loss": 2.9142259979248046, "grad_norm": 1.089045763015747, "lr": 0.00019754305556469223, "s_per_step": 0.5844484996795655, "peak_gb": 44.713082368, "samples_seen": 29600, "time": 1791131375.2880468} | |
| {"step": 950, "loss": 3.0302752017974854, "grad_norm": 1.205527663230896, "lr": 0.0001973491531691006, "s_per_step": 0.5822625255584717, "peak_gb": 44.713082368, "samples_seen": 30400, "time": 1791131389.8449948} | |
| {"step": 975, "loss": 2.9161105060577395, "grad_norm": 1.1548945903778076, "lr": 0.00019714798972494347, "s_per_step": 0.5808561515808105, "peak_gb": 44.713082368, "samples_seen": 31200, "time": 1791131404.3668756} | |
| {"step": 1000, "loss": 2.919966125488281, "grad_norm": 1.1152652502059937, "lr": 0.00019693958023653767, "s_per_step": 0.5795290184020996, "peak_gb": 44.713082368, "samples_seen": 32000, "time": 1791131418.8555546} | |
| {"step": 1025, "loss": 2.952225284576416, "grad_norm": 1.1843825578689575, "lr": 0.00019672394024866576, "s_per_step": 0.5974857711791992, "peak_gb": 44.713082368, "samples_seen": 32800, "time": 1791131433.7931862} | |
| {"step": 1050, "loss": 2.9690034532547, "grad_norm": 1.1854422092437744, "lr": 0.00019650108584541654, "s_per_step": 0.5811002635955811, "peak_gb": 44.713082368, "samples_seen": 33600, "time": 1791131448.3211079} | |
| {"step": 1075, "loss": 2.9967500257492063, "grad_norm": 1.2190947532653809, "lr": 0.00019627103364898538, "s_per_step": 0.580099172592163, "peak_gb": 44.713082368, "samples_seen": 34400, "time": 1791131462.8241384} | |
| {"step": 1100, "loss": 2.990977711677551, "grad_norm": 1.0495576858520508, "lr": 0.00019603380081843449, "s_per_step": 0.5808154773712159, "peak_gb": 44.713082368, "samples_seen": 35200, "time": 1791131477.3449311} | |
| {"step": 1125, "loss": 2.8920970916748048, "grad_norm": 0.9397656321525574, "lr": 0.0001957894050484129, "s_per_step": 0.5838562393188477, "peak_gb": 44.713082368, "samples_seen": 36000, "time": 1791131491.941773} | |
| {"step": 1150, "loss": 2.914958839416504, "grad_norm": 1.3053033351898193, "lr": 0.00019553786456783686, "s_per_step": 0.582167854309082, "peak_gb": 44.713082368, "samples_seen": 36800, "time": 1791131506.4963646} | |
| {"step": 1175, "loss": 2.9034262990951536, "grad_norm": 1.0504006147384644, "lr": 0.00019527919813853, "s_per_step": 0.5793894004821777, "peak_gb": 44.713082368, "samples_seen": 37600, "time": 1791131520.981513} | |
| {"step": 1200, "loss": 2.9084231233596802, "grad_norm": 1.1124707460403442, "lr": 0.00019501342505382405, "s_per_step": 0.5810192966461182, "peak_gb": 44.713082368, "samples_seen": 38400, "time": 1791131535.5074165} | |
| {"step": 1225, "loss": 2.827880344390869, "grad_norm": 1.4236536026000977, "lr": 0.00019474056513711977, "s_per_step": 0.5862373161315918, "peak_gb": 44.713082368, "samples_seen": 39200, "time": 1791131550.1637754} | |
| {"step": 1250, "loss": 2.8731605625152588, "grad_norm": 1.1672555208206177, "lr": 0.00019446063874040834, "s_per_step": 0.5826034450531006, "peak_gb": 44.713082368, "samples_seen": 40000, "time": 1791131564.7292533} | |
| {"step": 1275, "loss": 2.9100488948822023, "grad_norm": 1.0153155326843262, "lr": 0.00019417366674275333, "s_per_step": 0.6047325611114502, "peak_gb": 44.713082368, "samples_seen": 40800, "time": 1791131579.8479767} | |
| {"step": 1300, "loss": 2.8539438247680664, "grad_norm": 1.0282107591629028, "lr": 0.00019387967054873356, "s_per_step": 0.5824565982818604, "peak_gb": 44.713082368, "samples_seen": 41600, "time": 1791131594.4098606} | |
| {"step": 1325, "loss": 2.8969113874435424, "grad_norm": 1.3478723764419556, "lr": 0.00019357867208684621, "s_per_step": 0.582642650604248, "peak_gb": 44.713082368, "samples_seen": 42400, "time": 1791131608.9763298} | |
| {"step": 1350, "loss": 2.8323376035690306, "grad_norm": 1.1149699687957764, "lr": 0.00019327069380787164, "s_per_step": 0.5824921321868897, "peak_gb": 44.713082368, "samples_seen": 43200, "time": 1791131623.5390694} | |
| {"step": 1375, "loss": 2.8894362831115723, "grad_norm": 1.1063823699951172, "lr": 0.00019295575868319857, "s_per_step": 0.5840862846374512, "peak_gb": 44.713082368, "samples_seen": 44000, "time": 1791131638.1416295} | |
| {"step": 1400, "loss": 2.834498815536499, "grad_norm": 1.1182633638381958, "lr": 0.00019263389020311082, "s_per_step": 0.5812054634094238, "peak_gb": 44.713082368, "samples_seen": 44800, "time": 1791131652.6722355} | |
| {"step": 1425, "loss": 2.8067142009735107, "grad_norm": 1.203196406364441, "lr": 0.00019230511237503515, "s_per_step": 0.5813498687744141, "peak_gb": 44.713082368, "samples_seen": 45600, "time": 1791131667.2064037} | |
| {"step": 1450, "loss": 2.800572829246521, "grad_norm": 1.1607813835144043, "lr": 0.00019196944972175062, "s_per_step": 0.5796218490600586, "peak_gb": 44.713082368, "samples_seen": 46400, "time": 1791131681.697381} | |
| {"step": 1475, "loss": 2.824986810684204, "grad_norm": 1.1562610864639282, "lr": 0.00019162692727955953, "s_per_step": 0.5842508506774903, "peak_gb": 44.713082368, "samples_seen": 47200, "time": 1791131696.3040268} | |
| {"step": 1500, "loss": 2.8580026912689207, "grad_norm": 1.2550817728042603, "lr": 0.00019127757059642, "s_per_step": 0.5836690044403077, "peak_gb": 44.713082368, "samples_seen": 48000, "time": 1791131710.8980353} | |
| {"step": 1525, "loss": 2.7956640100479127, "grad_norm": 1.0501290559768677, "lr": 0.00019092140573004042, "s_per_step": 0.5987179946899414, "peak_gb": 44.713082368, "samples_seen": 48800, "time": 1791131725.866389} | |
| {"step": 1550, "loss": 2.904049711227417, "grad_norm": 1.2289342880249023, "lr": 0.0001905584592459358, "s_per_step": 0.579942455291748, "peak_gb": 44.713082368, "samples_seen": 49600, "time": 1791131740.3653781} | |
| {"step": 1575, "loss": 2.801865735054016, "grad_norm": 1.4003002643585205, "lr": 0.0001901887582154464, "s_per_step": 0.5801137828826904, "peak_gb": 44.713082368, "samples_seen": 50400, "time": 1791131754.8686228} | |
| {"step": 1600, "loss": 2.81393018245697, "grad_norm": 1.0660154819488525, "lr": 0.00018981233021371843, "s_per_step": 0.5823390769958496, "peak_gb": 44.713082368, "samples_seen": 51200, "time": 1791131769.4274774} | |
| {"step": 1625, "loss": 2.8056074666976927, "grad_norm": 1.1312650442123413, "lr": 0.00018942920331764746, "s_per_step": 0.5844465160369873, "peak_gb": 44.713082368, "samples_seen": 52000, "time": 1791131784.0390692} | |
| {"step": 1650, "loss": 2.77773108959198, "grad_norm": 1.0975704193115234, "lr": 0.00018903940610378407, "s_per_step": 0.582863941192627, "peak_gb": 44.713082368, "samples_seen": 52800, "time": 1791131798.6111288} | |
| {"step": 1675, "loss": 2.7603001546859742, "grad_norm": 1.241600513458252, "lr": 0.00018864296764620238, "s_per_step": 0.5836851119995117, "peak_gb": 44.713082368, "samples_seen": 53600, "time": 1791131813.2036917} | |
| {"step": 1700, "loss": 2.7555297422409057, "grad_norm": 1.1494439840316772, "lr": 0.00018823991751433167, "s_per_step": 0.5850475883483887, "peak_gb": 44.713082368, "samples_seen": 54400, "time": 1791131827.8303254} | |
| {"step": 1725, "loss": 2.8411933469772337, "grad_norm": 0.991641104221344, "lr": 0.00018783028577075065, "s_per_step": 0.5855899620056152, "peak_gb": 44.713082368, "samples_seen": 55200, "time": 1791131842.4704814} | |
| {"step": 1750, "loss": 2.8297329354286194, "grad_norm": 1.3848960399627686, "lr": 0.00018741410296894528, "s_per_step": 0.5831822967529297, "peak_gb": 44.713082368, "samples_seen": 56000, "time": 1791131857.0504653} | |
| {"step": 1775, "loss": 2.7489702224731447, "grad_norm": 1.1250214576721191, "lr": 0.0001869914001510298, "s_per_step": 0.6029328918457031, "peak_gb": 44.713082368, "samples_seen": 56800, "time": 1791131872.1245182} | |
| {"step": 1800, "loss": 2.840885500907898, "grad_norm": 1.192891240119934, "lr": 0.00018656220884543143, "s_per_step": 0.5853533840179443, "peak_gb": 44.713082368, "samples_seen": 57600, "time": 1791131886.7587817} | |
| {"step": 1825, "loss": 2.7824712562561036, "grad_norm": 1.121734857559204, "lr": 0.00018612656106453871, "s_per_step": 0.5848813915252685, "peak_gb": 44.713082368, "samples_seen": 58400, "time": 1791131901.3812835} | |
| {"step": 1850, "loss": 2.7347464036941527, "grad_norm": 1.163681149482727, "lr": 0.00018568448930231373, "s_per_step": 0.5818957328796387, "peak_gb": 44.713082368, "samples_seen": 59200, "time": 1791131915.9291348} | |
| {"step": 1875, "loss": 2.7876648902893066, "grad_norm": 1.1300899982452393, "lr": 0.00018523602653186858, "s_per_step": 0.5813259029388428, "peak_gb": 44.713082368, "samples_seen": 60000, "time": 1791131930.462728} | |
| {"step": 1900, "loss": 2.7792696571350097, "grad_norm": 1.1007814407348633, "lr": 0.00018478120620300578, "s_per_step": 0.5799147510528564, "peak_gb": 44.713082368, "samples_seen": 60800, "time": 1791131944.9613276} | |
| {"step": 1925, "loss": 2.760815134048462, "grad_norm": 1.2840055227279663, "lr": 0.00018432006223972357, "s_per_step": 0.581923418045044, "peak_gb": 44.713082368, "samples_seen": 61600, "time": 1791131959.510147} | |
| {"step": 1950, "loss": 2.72098069190979, "grad_norm": 1.1493003368377686, "lr": 0.00018385262903768547, "s_per_step": 0.5796582794189453, "peak_gb": 44.713082368, "samples_seen": 62400, "time": 1791131974.0020506} | |
| {"step": 1975, "loss": 2.7809674453735354, "grad_norm": 1.0490471124649048, "lr": 0.00018337894146165467, "s_per_step": 0.5820777893066407, "peak_gb": 44.713082368, "samples_seen": 63200, "time": 1791131988.5544076} | |
| {"step": 2000, "loss": 2.7531254482269287, "grad_norm": 1.0774011611938477, "lr": 0.00018289903484289383, "s_per_step": 0.5824406623840332, "peak_gb": 44.713082368, "samples_seen": 64000, "time": 1791132003.1158311} | |
| {"step": 2025, "loss": 2.724808783531189, "grad_norm": 1.0720311403274536, "lr": 0.00018241294497652958, "s_per_step": 0.5992901039123535, "peak_gb": 44.713082368, "samples_seen": 64800, "time": 1791132018.0985038} | |
| {"step": 2050, "loss": 2.790845193862915, "grad_norm": 1.2732620239257812, "lr": 0.00018192070811888272, "s_per_step": 0.5811270427703857, "peak_gb": 44.713082368, "samples_seen": 65600, "time": 1791132032.6270998} | |
| {"step": 2075, "loss": 2.7737058067321776, "grad_norm": 1.0213253498077393, "lr": 0.00018142236098476398, "s_per_step": 0.5809852790832519, "peak_gb": 44.713082368, "samples_seen": 66400, "time": 1791132047.1521604} | |
| {"step": 2100, "loss": 2.739048023223877, "grad_norm": 1.082443118095398, "lr": 0.00018091794074473537, "s_per_step": 0.5808903026580811, "peak_gb": 44.713082368, "samples_seen": 67200, "time": 1791132061.6748774} | |
| {"step": 2125, "loss": 2.7185260105133056, "grad_norm": 1.1437773704528809, "lr": 0.00018040748502233802, "s_per_step": 0.5793789958953858, "peak_gb": 44.713082368, "samples_seen": 68000, "time": 1791132076.1597369} | |
| {"step": 2150, "loss": 2.773498544692993, "grad_norm": 1.1243386268615723, "lr": 0.0001798910318912856, "s_per_step": 0.579986400604248, "peak_gb": 44.713082368, "samples_seen": 68800, "time": 1791132090.6597726} | |
| {"step": 2175, "loss": 2.7247875928878784, "grad_norm": 1.1453449726104736, "lr": 0.00017936861987262475, "s_per_step": 0.6377030372619629, "peak_gb": 44.713082368, "samples_seen": 69600, "time": 1791132106.602996} | |
| {"step": 2200, "loss": 2.758620800971985, "grad_norm": 1.0647848844528198, "lr": 0.0001788402879318618, "s_per_step": 0.583631067276001, "peak_gb": 44.713082368, "samples_seen": 70400, "time": 1791132121.194404} | |
| {"step": 2225, "loss": 2.737944917678833, "grad_norm": 0.9973115921020508, "lr": 0.00017830607547605624, "s_per_step": 0.5805112552642823, "peak_gb": 44.713082368, "samples_seen": 71200, "time": 1791132135.7078857} | |
| {"step": 2250, "loss": 2.7589354658126832, "grad_norm": 1.3257142305374146, "lr": 0.00017776602235088182, "s_per_step": 0.5818637657165527, "peak_gb": 44.713082368, "samples_seen": 72000, "time": 1791132150.255094} | |
| {"step": 2275, "loss": 2.691265125274658, "grad_norm": 1.2526953220367432, "lr": 0.0001772201688376541, "s_per_step": 0.5970073795318603, "peak_gb": 44.713082368, "samples_seen": 72800, "time": 1791132165.180914} | |
| {"step": 2300, "loss": 2.6809875345230103, "grad_norm": 1.1973172426223755, "lr": 0.00017666855565032642, "s_per_step": 0.581067304611206, "peak_gb": 44.713082368, "samples_seen": 73600, "time": 1791132179.7082095} | |
| {"step": 2325, "loss": 2.7636598443984983, "grad_norm": 1.240551471710205, "lr": 0.00017611122393245275, "s_per_step": 0.5833901596069336, "peak_gb": 44.713082368, "samples_seen": 74400, "time": 1791132194.29364} | |
| {"step": 2350, "loss": 2.6926284646987915, "grad_norm": 1.4566211700439453, "lr": 0.00017554821525411906, "s_per_step": 0.5827942657470703, "peak_gb": 44.713082368, "samples_seen": 75200, "time": 1791132208.8641186} | |
| {"step": 2375, "loss": 2.7419660758972166, "grad_norm": 1.1245578527450562, "lr": 0.00017497957160884285, "s_per_step": 0.582745018005371, "peak_gb": 44.713082368, "samples_seen": 76000, "time": 1791132223.4334397} | |
| {"step": 2400, "loss": 2.663253164291382, "grad_norm": 1.3107283115386963, "lr": 0.00017440533541044056, "s_per_step": 0.5869213008880615, "peak_gb": 44.713082368, "samples_seen": 76800, "time": 1791132238.1070802} | |
| {"step": 2425, "loss": 2.719187321662903, "grad_norm": 1.1205676794052124, "lr": 0.00017382554948986445, "s_per_step": 0.5820108604431152, "peak_gb": 44.713082368, "samples_seen": 77600, "time": 1791132252.6579833} | |
| {"step": 2450, "loss": 2.7780220317840576, "grad_norm": 1.3026337623596191, "lr": 0.00017324025709200766, "s_per_step": 0.5817010879516602, "peak_gb": 44.713082368, "samples_seen": 78400, "time": 1791132267.2012224} | |
| {"step": 2475, "loss": 2.670451397895813, "grad_norm": 1.2014914751052856, "lr": 0.00017264950187247875, "s_per_step": 0.5823606967926025, "peak_gb": 44.713082368, "samples_seen": 79200, "time": 1791132281.7608585} | |
| {"step": 2500, "loss": 2.716837215423584, "grad_norm": 1.10873281955719, "lr": 0.00017205332789434557, "s_per_step": 0.5853345394134521, "peak_gb": 44.713082368, "samples_seen": 80000, "time": 1791132296.3948615} | |
| {"step": 2525, "loss": 2.7432607793807984, "grad_norm": 1.098906397819519, "lr": 0.00017145177962484857, "s_per_step": 0.5997240447998047, "peak_gb": 44.713082368, "samples_seen": 80800, "time": 1791132311.388538} | |
| {"step": 2550, "loss": 2.72246383190155, "grad_norm": 1.1802773475646973, "lr": 0.00017084490193208435, "s_per_step": 0.5805338096618652, "peak_gb": 44.713082368, "samples_seen": 81600, "time": 1791132325.902455} | |
| {"step": 2575, "loss": 2.7470813512802126, "grad_norm": 1.0650112628936768, "lr": 0.00017023274008165878, "s_per_step": 0.5804518604278565, "peak_gb": 44.713082368, "samples_seen": 82400, "time": 1791132340.4143882} | |
| {"step": 2600, "loss": 2.733012390136719, "grad_norm": 1.1363471746444702, "lr": 0.00016961533973331081, "s_per_step": 0.5814594936370849, "peak_gb": 44.713082368, "samples_seen": 83200, "time": 1791132354.9514756} | |
| {"step": 2625, "loss": 2.6893992137908938, "grad_norm": 1.1025614738464355, "lr": 0.00016899274693750696, "s_per_step": 0.5805016994476319, "peak_gb": 44.713082368, "samples_seen": 84000, "time": 1791132369.4646068} | |
| {"step": 2650, "loss": 2.6821892070770263, "grad_norm": 1.081494688987732, "lr": 0.00016836500813200632, "s_per_step": 0.5812886905670166, "peak_gb": 44.713082368, "samples_seen": 84800, "time": 1791132383.9974716} | |
| {"step": 2675, "loss": 2.6333597564697264, "grad_norm": 1.1299649477005005, "lr": 0.00016773217013839705, "s_per_step": 0.5820088291168213, "peak_gb": 44.713082368, "samples_seen": 85600, "time": 1791132398.5483217} | |
| {"step": 2700, "loss": 2.6820573711395266, "grad_norm": 1.2370376586914062, "lr": 0.0001670942801586039, "s_per_step": 0.5822090339660645, "peak_gb": 44.713082368, "samples_seen": 86400, "time": 1791132413.1041813} | |
| {"step": 2725, "loss": 2.695576796531677, "grad_norm": 1.1963305473327637, "lr": 0.0001664513857713677, "s_per_step": 0.5848300170898437, "peak_gb": 44.713082368, "samples_seen": 87200, "time": 1791132427.7255838} | |
| {"step": 2750, "loss": 2.668781318664551, "grad_norm": 1.170694351196289, "lr": 0.00016580353492869635, "s_per_step": 0.5830868148803711, "peak_gb": 44.713082368, "samples_seen": 88000, "time": 1791132442.3036287} | |
| {"step": 2775, "loss": 2.6674189043045042, "grad_norm": 1.4151184558868408, "lr": 0.00016515077595228837, "s_per_step": 0.6010197257995605, "peak_gb": 44.713082368, "samples_seen": 88800, "time": 1791132457.330008} | |
| {"step": 2800, "loss": 2.716653389930725, "grad_norm": 1.140033483505249, "lr": 0.0001644931575299287, "s_per_step": 0.5838634395599365, "peak_gb": 44.713082368, "samples_seen": 89600, "time": 1791132471.9272482} | |
| {"step": 2825, "loss": 2.7051201915740966, "grad_norm": 1.2430063486099243, "lr": 0.0001638307287118571, "s_per_step": 0.5820985507965087, "peak_gb": 44.713082368, "samples_seen": 90400, "time": 1791132486.4804387} | |
| {"step": 2850, "loss": 2.6607730865478514, "grad_norm": 1.1695795059204102, "lr": 0.00016316353890710958, "s_per_step": 0.5837668800354003, "peak_gb": 44.713082368, "samples_seen": 91200, "time": 1791132501.0753098} | |
| {"step": 2875, "loss": 2.6640982151031496, "grad_norm": 1.0638611316680908, "lr": 0.00016249163787983325, "s_per_step": 0.5824350929260254, "peak_gb": 44.713082368, "samples_seen": 92000, "time": 1791132515.6368423} | |
| {"step": 2900, "loss": 2.6686540985107423, "grad_norm": 1.0542538166046143, "lr": 0.00016181507574557436, "s_per_step": 0.5836594104766846, "peak_gb": 44.713082368, "samples_seen": 92800, "time": 1791132530.229168} | |
| {"step": 2925, "loss": 2.6495557260513305, "grad_norm": 1.2142537832260132, "lr": 0.00016113390296754036, "s_per_step": 0.5849769687652588, "peak_gb": 44.713082368, "samples_seen": 93600, "time": 1791132544.8542972} | |
| {"step": 2950, "loss": 2.6701879692077637, "grad_norm": 1.2481223344802856, "lr": 0.00016044817035283605, "s_per_step": 0.5815197849273681, "peak_gb": 44.713082368, "samples_seen": 94400, "time": 1791132559.3929307} | |
| {"step": 2975, "loss": 2.729030981063843, "grad_norm": 0.9954540729522705, "lr": 0.00015975792904867388, "s_per_step": 0.5838561344146729, "peak_gb": 44.713082368, "samples_seen": 95200, "time": 1791132573.989938} | |
| {"step": 3000, "loss": 2.649655590057373, "grad_norm": 1.0716608762741089, "lr": 0.00015906323053855898, "s_per_step": 0.5867070293426514, "peak_gb": 44.713082368, "samples_seen": 96000, "time": 1791132588.6582751} | |
| {"step": 3025, "loss": 2.6586125326156616, "grad_norm": 1.4092375040054321, "lr": 0.0001583641266384493, "s_per_step": 0.604687147140503, "peak_gb": 44.713082368, "samples_seen": 96800, "time": 1791132603.776329} | |
| {"step": 3050, "loss": 2.6345360708236694, "grad_norm": 1.3088021278381348, "lr": 0.00015766066949289052, "s_per_step": 0.5844075584411621, "peak_gb": 44.713082368, "samples_seen": 97600, "time": 1791132618.3874304} | |
| {"step": 3075, "loss": 2.697037835121155, "grad_norm": 1.2829176187515259, "lr": 0.00015695291157112693, "s_per_step": 0.5823062896728516, "peak_gb": 44.713082368, "samples_seen": 98400, "time": 1791132632.9458525} | |
| {"step": 3100, "loss": 2.6461993885040282, "grad_norm": 1.1458219289779663, "lr": 0.0001562409056631878, "s_per_step": 0.5842306709289551, "peak_gb": 44.713082368, "samples_seen": 99200, "time": 1791132647.552255} | |
| {"step": 3125, "loss": 2.6994865417480467, "grad_norm": 1.0527013540267944, "lr": 0.00015552470487594983, "s_per_step": 0.5832872867584229, "peak_gb": 44.713082368, "samples_seen": 100000, "time": 1791132662.1353507} | |
| {"step": 3150, "loss": 2.6455965662002563, "grad_norm": 1.210248351097107, "lr": 0.00015480436262917615, "s_per_step": 0.5897402572631836, "peak_gb": 44.713082368, "samples_seen": 100800, "time": 1791132676.879246} | |
| {"step": 3175, "loss": 2.7154378509521484, "grad_norm": 1.226425051689148, "lr": 0.0001540799326515317, "s_per_step": 0.5857205295562744, "peak_gb": 44.713082368, "samples_seen": 101600, "time": 1791132691.5226414} | |
| {"step": 3200, "loss": 2.60671639919281, "grad_norm": 1.0465337038040161, "lr": 0.00015335146897657587, "s_per_step": 0.5847133922576905, "peak_gb": 44.713082368, "samples_seen": 102400, "time": 1791132706.1408818} | |
| {"step": 3225, "loss": 2.5945321559906005, "grad_norm": 1.1408718824386597, "lr": 0.00015261902593873222, "s_per_step": 0.5843933010101319, "peak_gb": 44.713082368, "samples_seen": 103200, "time": 1791132720.7511504} | |
| {"step": 3250, "loss": 2.627700114250183, "grad_norm": 1.0017207860946655, "lr": 0.00015188265816923585, "s_per_step": 0.5855321598052978, "peak_gb": 44.713082368, "samples_seen": 104000, "time": 1791132735.3898623} | |
| {"step": 3275, "loss": 2.6447770547866822, "grad_norm": 1.066293478012085, "lr": 0.0001511424205920585, "s_per_step": 0.6015197467803955, "peak_gb": 44.713082368, "samples_seen": 104800, "time": 1791132750.4282053} | |
| {"step": 3300, "loss": 2.6553041982650756, "grad_norm": 1.275646686553955, "lr": 0.00015039836841981185, "s_per_step": 0.5847999572753906, "peak_gb": 44.713082368, "samples_seen": 105600, "time": 1791132765.0488286} | |
| {"step": 3325, "loss": 2.5941198587417604, "grad_norm": 1.0782554149627686, "lr": 0.00014965055714962952, "s_per_step": 0.5845184135437012, "peak_gb": 44.713082368, "samples_seen": 106400, "time": 1791132779.6623993} | |
| {"step": 3350, "loss": 2.628866515159607, "grad_norm": 1.201255440711975, "lr": 0.0001488990425590276, "s_per_step": 0.5825023555755615, "peak_gb": 44.713082368, "samples_seen": 107200, "time": 1791132794.225617} | |
| {"step": 3375, "loss": 2.6890606594085695, "grad_norm": 1.0845966339111328, "lr": 0.00014814388070174408, "s_per_step": 0.5846240043640136, "peak_gb": 44.713082368, "samples_seen": 108000, "time": 1791132808.841806} | |
| {"step": 3400, "loss": 2.590783829689026, "grad_norm": 1.1155602931976318, "lr": 0.00014738512790355842, "s_per_step": 0.5839724159240722, "peak_gb": 44.713082368, "samples_seen": 108800, "time": 1791132823.4414928} | |
| {"step": 3425, "loss": 2.6391691303253175, "grad_norm": 1.0816454887390137, "lr": 0.00014662284075808995, "s_per_step": 0.5850570201873779, "peak_gb": 44.713082368, "samples_seen": 109600, "time": 1791132838.0683677} | |
| {"step": 3450, "loss": 2.6323579359054565, "grad_norm": 1.131683588027954, "lr": 0.00014585707612257672, "s_per_step": 0.5823802852630615, "peak_gb": 44.713082368, "samples_seen": 110400, "time": 1791132852.6284838} | |
| {"step": 3475, "loss": 2.637928156852722, "grad_norm": 0.9959607720375061, "lr": 0.00014508789111363494, "s_per_step": 0.5853830051422119, "peak_gb": 44.713082368, "samples_seen": 111200, "time": 1791132867.2637053} | |
| {"step": 3500, "loss": 2.65216420173645, "grad_norm": 1.3305087089538574, "lr": 0.00014431534310299838, "s_per_step": 0.5855358028411866, "peak_gb": 44.713082368, "samples_seen": 112000, "time": 1791132881.9027245} | |
| {"step": 3525, "loss": 2.6313996505737305, "grad_norm": 1.2155920267105103, "lr": 0.00014353948971323942, "s_per_step": 0.6034837055206299, "peak_gb": 44.713082368, "samples_seen": 112800, "time": 1791132896.9904048} | |
| {"step": 3550, "loss": 2.6454056882858277, "grad_norm": 1.2063369750976562, "lr": 0.00014276038881347105, "s_per_step": 0.5832828998565673, "peak_gb": 44.713082368, "samples_seen": 113600, "time": 1791132911.5728936} | |
| {"step": 3575, "loss": 2.6533055901527405, "grad_norm": 1.2403618097305298, "lr": 0.00014197809851503049, "s_per_step": 0.5824703311920166, "peak_gb": 44.713082368, "samples_seen": 114400, "time": 1791132926.135257} | |
| {"step": 3600, "loss": 2.645680537223816, "grad_norm": 1.168968915939331, "lr": 0.0001411926771671449, "s_per_step": 0.5845646953582764, "peak_gb": 44.713082368, "samples_seen": 115200, "time": 1791132940.7499871} | |
| {"step": 3625, "loss": 2.5960699319839478, "grad_norm": 1.1931697130203247, "lr": 0.0001404041833525792, "s_per_step": 0.5853945255279541, "peak_gb": 44.713082368, "samples_seen": 116000, "time": 1791132955.3854115} | |
| {"step": 3650, "loss": 2.6213397121429445, "grad_norm": 0.9856603741645813, "lr": 0.00013961267588326635, "s_per_step": 0.5852436065673828, "peak_gb": 44.713082368, "samples_seen": 116800, "time": 1791132970.017149} | |
| {"step": 3675, "loss": 2.5998027467727662, "grad_norm": 1.1824589967727661, "lr": 0.0001388182137959211, "s_per_step": 0.5843393993377686, "peak_gb": 44.713082368, "samples_seen": 117600, "time": 1791132984.6262264} | |
| {"step": 3700, "loss": 2.629755802154541, "grad_norm": 1.2840546369552612, "lr": 0.00013802085634763612, "s_per_step": 0.5829662704467773, "peak_gb": 44.713082368, "samples_seen": 118400, "time": 1791132999.2009673} | |
| {"step": 3725, "loss": 2.6009298038482664, "grad_norm": 1.2750321626663208, "lr": 0.00013722066301146254, "s_per_step": 0.5825348472595215, "peak_gb": 44.713082368, "samples_seen": 119200, "time": 1791133013.764688} | |
| {"step": 3750, "loss": 2.612462890148163, "grad_norm": 1.1066721677780151, "lr": 0.00013641769347197367, "s_per_step": 0.5850222778320312, "peak_gb": 44.713082368, "samples_seen": 120000, "time": 1791133028.3908353} | |
| {"step": 3775, "loss": 2.591866898536682, "grad_norm": 1.233768343925476, "lr": 0.00013561200762081353, "s_per_step": 0.6027588081359864, "peak_gb": 44.713082368, "samples_seen": 120800, "time": 1791133043.4603734} | |
| {"step": 3800, "loss": 2.578413248062134, "grad_norm": 1.108993649482727, "lr": 0.00013480366555222948, "s_per_step": 0.5819605350494385, "peak_gb": 44.713082368, "samples_seen": 121600, "time": 1791133058.0100117} | |
| {"step": 3825, "loss": 2.547907509803772, "grad_norm": 0.9940484166145325, "lr": 0.00013399272755859002, "s_per_step": 0.5811294841766358, "peak_gb": 44.713082368, "samples_seen": 122400, "time": 1791133072.5388749} | |
| {"step": 3850, "loss": 2.564617967605591, "grad_norm": 1.148879885673523, "lr": 0.00013317925412588777, "s_per_step": 0.5868311309814453, "peak_gb": 44.713082368, "samples_seen": 123200, "time": 1791133087.210223} | |
| {"step": 3875, "loss": 2.587318305969238, "grad_norm": 1.0706918239593506, "lr": 0.00013236330592922784, "s_per_step": 0.5894640159606933, "peak_gb": 44.713082368, "samples_seen": 124000, "time": 1791133101.9471831} | |
| {"step": 3900, "loss": 2.599490542411804, "grad_norm": 1.0891342163085938, "lr": 0.00013154494382830226, "s_per_step": 0.5840770053863525, "peak_gb": 44.713082368, "samples_seen": 124800, "time": 1791133116.5494475} | |
| {"step": 3925, "loss": 2.628100709915161, "grad_norm": 1.1885673999786377, "lr": 0.00013072422886285063, "s_per_step": 0.5845713424682617, "peak_gb": 44.713082368, "samples_seen": 125600, "time": 1791133131.1641} | |
| {"step": 3950, "loss": 2.6188903713226317, "grad_norm": 1.0750778913497925, "lr": 0.00012990122224810726, "s_per_step": 0.5842515659332276, "peak_gb": 44.713082368, "samples_seen": 126400, "time": 1791133145.7707798} | |
| {"step": 3975, "loss": 2.577172713279724, "grad_norm": 1.1962721347808838, "lr": 0.00012907598537023528, "s_per_step": 0.5835914134979248, "peak_gb": 44.713082368, "samples_seen": 127200, "time": 1791133160.360931} | |
| {"step": 4000, "loss": 2.5662565279006957, "grad_norm": 1.1467726230621338, "lr": 0.00012824857978174808, "s_per_step": 0.5806757926940918, "peak_gb": 44.713082368, "samples_seen": 128000, "time": 1791133174.8781514} | |
| {"step": 4025, "loss": 2.6355027961730957, "grad_norm": 1.1590839624404907, "lr": 0.00012741906719691812, "s_per_step": 0.595490140914917, "peak_gb": 44.713082368, "samples_seen": 128800, "time": 1791133189.7657502} | |
| {"step": 4050, "loss": 2.5592614030838012, "grad_norm": 0.9599524140357971, "lr": 0.0001265875094871738, "s_per_step": 0.5824095058441162, "peak_gb": 44.713082368, "samples_seen": 129600, "time": 1791133204.3263824} | |
| {"step": 4075, "loss": 2.5762628889083863, "grad_norm": 0.9201562404632568, "lr": 0.0001257539686764847, "s_per_step": 0.5829432201385498, "peak_gb": 44.713082368, "samples_seen": 130400, "time": 1791133218.9003162} | |
| {"step": 4100, "loss": 2.6393421840667726, "grad_norm": 1.352101445198059, "lr": 0.0001249185069367353, "s_per_step": 0.5822771739959717, "peak_gb": 44.713082368, "samples_seen": 131200, "time": 1791133233.4575992} | |
| {"step": 4125, "loss": 2.545742371082306, "grad_norm": 1.2281466722488403, "lr": 0.00012408118658308783, "s_per_step": 0.5824446392059326, "peak_gb": 44.713082368, "samples_seen": 132000, "time": 1791133248.0190716} | |
| {"step": 4150, "loss": 2.588506646156311, "grad_norm": 1.1411926746368408, "lr": 0.00012324207006933417, "s_per_step": 0.5804715347290039, "peak_gb": 44.713082368, "samples_seen": 132800, "time": 1791133262.5312164} | |
| {"step": 4175, "loss": 2.5443468284606934, "grad_norm": 1.0073899030685425, "lr": 0.00012240121998323766, "s_per_step": 0.58156418800354, "peak_gb": 44.713082368, "samples_seen": 133600, "time": 1791133277.0706964} | |
| {"step": 4200, "loss": 2.5501110649108885, "grad_norm": 1.205407977104187, "lr": 0.00012155869904186475, "s_per_step": 0.5811350154876709, "peak_gb": 44.713082368, "samples_seen": 134400, "time": 1791133291.5995052} | |
| {"step": 4225, "loss": 2.602772789001465, "grad_norm": 1.2279781103134155, "lr": 0.00012071457008690715, "s_per_step": 0.5812279796600341, "peak_gb": 44.713082368, "samples_seen": 135200, "time": 1791133306.1305652} | |
| {"step": 4250, "loss": 2.6113069915771483, "grad_norm": 1.1278338432312012, "lr": 0.00011986889607999463, "s_per_step": 0.580757417678833, "peak_gb": 44.713082368, "samples_seen": 136000, "time": 1791133320.6498582} | |
| {"step": 4275, "loss": 2.566324009895325, "grad_norm": 1.2942112684249878, "lr": 0.00011902174009799881, "s_per_step": 0.5944104099273682, "peak_gb": 44.713082368, "samples_seen": 136800, "time": 1791133335.5104773} | |
| {"step": 4300, "loss": 2.5078661108016966, "grad_norm": 1.2482675313949585, "lr": 0.00011817316532832833, "s_per_step": 0.5815795421600342, "peak_gb": 44.713082368, "samples_seen": 137600, "time": 1791133350.050364} | |
| {"step": 4325, "loss": 2.6592298412322997, "grad_norm": 1.0717958211898804, "lr": 0.00011732323506421603, "s_per_step": 0.583767204284668, "peak_gb": 44.713082368, "samples_seen": 138400, "time": 1791133364.644909} | |
| {"step": 4350, "loss": 2.6119984006881714, "grad_norm": 1.00667142868042, "lr": 0.00011647201269999792, "s_per_step": 0.5827497482299805, "peak_gb": 44.713082368, "samples_seen": 139200, "time": 1791133379.2140245} | |
| {"step": 4375, "loss": 2.5818211317062376, "grad_norm": 1.1398861408233643, "lr": 0.0001156195617263847, "s_per_step": 0.6331087684631348, "peak_gb": 44.713082368, "samples_seen": 140000, "time": 1791133395.0420854} | |
| {"step": 4400, "loss": 2.5258120822906496, "grad_norm": 1.2284903526306152, "lr": 0.00011476594572572632, "s_per_step": 0.5820397758483886, "peak_gb": 44.713082368, "samples_seen": 140800, "time": 1791133409.5934033} | |
| {"step": 4425, "loss": 2.5755055570602416, "grad_norm": 1.141483187675476, "lr": 0.00011391122836726932, "s_per_step": 0.580828332901001, "peak_gb": 44.713082368, "samples_seen": 141600, "time": 1791133424.1144583} | |
| {"step": 4450, "loss": 2.566441774368286, "grad_norm": 1.1366175413131714, "lr": 0.00011305547340240805, "s_per_step": 0.5789041805267334, "peak_gb": 44.713082368, "samples_seen": 142400, "time": 1791133438.5874844} | |
| {"step": 4475, "loss": 2.561001148223877, "grad_norm": 1.0844303369522095, "lr": 0.00011219874465992948, "s_per_step": 0.5818092918395996, "peak_gb": 44.713082368, "samples_seen": 143200, "time": 1791133453.13306} | |
| {"step": 4500, "loss": 2.5567925786972046, "grad_norm": 1.1574947834014893, "lr": 0.00011134110604125239, "s_per_step": 0.5787328243255615, "peak_gb": 44.713082368, "samples_seen": 144000, "time": 1791133467.6017637} | |
| {"step": 4525, "loss": 2.590312509536743, "grad_norm": 1.257983684539795, "lr": 0.00011048262151566114, "s_per_step": 0.6001885604858398, "peak_gb": 44.713082368, "samples_seen": 144800, "time": 1791133482.606845} | |
| {"step": 4550, "loss": 2.629988832473755, "grad_norm": 1.1604526042938232, "lr": 0.00010962335511553434, "s_per_step": 0.5829675579071045, "peak_gb": 44.713082368, "samples_seen": 145600, "time": 1791133497.1814847} | |
| {"step": 4575, "loss": 2.5439812088012697, "grad_norm": 1.1712712049484253, "lr": 0.00010876337093156886, "s_per_step": 0.5811667346954346, "peak_gb": 44.713082368, "samples_seen": 146400, "time": 1791133511.711039} | |
| {"step": 4600, "loss": 2.5177254247665406, "grad_norm": 1.1479181051254272, "lr": 0.00010790273310799933, "s_per_step": 0.5817756175994873, "peak_gb": 44.713082368, "samples_seen": 147200, "time": 1791133526.2557957} | |
| {"step": 4625, "loss": 2.5491437196731566, "grad_norm": 1.2170847654342651, "lr": 0.00010704150583781388, "s_per_step": 0.5829072570800782, "peak_gb": 44.713082368, "samples_seen": 148000, "time": 1791133540.8288167} | |
| {"step": 4650, "loss": 2.6045084619522094, "grad_norm": 1.189692497253418, "lr": 0.00010617975335796613, "s_per_step": 0.5828746032714843, "peak_gb": 44.713082368, "samples_seen": 148800, "time": 1791133555.4010704} | |
| {"step": 4675, "loss": 2.576749534606934, "grad_norm": 1.1746689081192017, "lr": 0.00010531753994458382, "s_per_step": 0.5798631191253663, "peak_gb": 44.713082368, "samples_seen": 149600, "time": 1791133569.898002} | |
| {"step": 4700, "loss": 2.5879501485824585, "grad_norm": 1.182418704032898, "lr": 0.00010445492990817471, "s_per_step": 0.58068115234375, "peak_gb": 44.713082368, "samples_seen": 150400, "time": 1791133584.415375} | |
| {"step": 4725, "loss": 2.5357809329032897, "grad_norm": 1.4740160703659058, "lr": 0.00010359198758882973, "s_per_step": 0.5839321517944336, "peak_gb": 44.713082368, "samples_seen": 151200, "time": 1791133599.0140464} | |
| {"step": 4750, "loss": 2.55805965423584, "grad_norm": 1.172712802886963, "lr": 0.00010272877735142407, "s_per_step": 0.5821543216705323, "peak_gb": 44.713082368, "samples_seen": 152000, "time": 1791133613.568319} | |
| {"step": 4775, "loss": 2.5926496958732606, "grad_norm": 1.194968581199646, "lr": 0.00010186536358081623, "s_per_step": 0.5943687915802002, "peak_gb": 44.713082368, "samples_seen": 152800, "time": 1791133628.427965} | |
| {"step": 4800, "loss": 2.5890002751350405, "grad_norm": 1.1471878290176392, "lr": 0.00010100181067704579, "s_per_step": 0.5851948833465577, "peak_gb": 44.713082368, "samples_seen": 153600, "time": 1791133643.0582457} | |
| {"step": 4825, "loss": 2.5580673170089723, "grad_norm": 1.1443222761154175, "lr": 0.00010013818305053007, "s_per_step": 0.5806027603149414, "peak_gb": 44.713082368, "samples_seen": 154400, "time": 1791133657.573739} | |
| {"step": 4850, "loss": 2.5510888147354125, "grad_norm": 1.1550148725509644, "lr": 9.927454511725963e-05, "s_per_step": 0.5874297904968262, "peak_gb": 44.947974656, "samples_seen": 155200, "time": 1791133672.2599056} | |
| {"step": 4875, "loss": 2.5219507360458375, "grad_norm": 1.0392953157424927, "lr": 9.841096129399391e-05, "s_per_step": 0.5823034572601319, "peak_gb": 44.947974656, "samples_seen": 156000, "time": 1791133686.8179238} | |
| {"step": 4900, "loss": 2.5420716381073, "grad_norm": 1.2059009075164795, "lr": 9.754749599345636e-05, "s_per_step": 0.585919017791748, "peak_gb": 44.947974656, "samples_seen": 156800, "time": 1791133701.4663377} | |
| {"step": 4925, "loss": 2.5494388055801394, "grad_norm": 1.132745385169983, "lr": 9.668421361953004e-05, "s_per_step": 0.5843277454376221, "peak_gb": 44.947974656, "samples_seen": 157600, "time": 1791133716.0755186} | |
| {"step": 4950, "loss": 2.534179072380066, "grad_norm": 1.1565256118774414, "lr": 9.582117856245404e-05, "s_per_step": 0.5862970352172852, "peak_gb": 44.947974656, "samples_seen": 158400, "time": 1791133730.7334623} | |
| {"step": 4975, "loss": 2.575369110107422, "grad_norm": 1.273497223854065, "lr": 9.495845519402057e-05, "s_per_step": 0.582844295501709, "peak_gb": 44.947974656, "samples_seen": 159200, "time": 1791133745.3050113} | |
| {"step": 5000, "loss": 2.5750187397003175, "grad_norm": 1.1561633348464966, "lr": 9.409610786277377e-05, "s_per_step": 0.5810141372680664, "peak_gb": 44.947974656, "samples_seen": 160000, "time": 1791133759.830802} | |
| {"step": 5025, "loss": 2.560807399749756, "grad_norm": 1.3111895322799683, "lr": 9.323420088921002e-05, "s_per_step": 0.595534782409668, "peak_gb": 44.947974656, "samples_seen": 160800, "time": 1791133774.7197492} | |
| {"step": 5050, "loss": 2.5090624332427978, "grad_norm": 1.128811240196228, "lr": 9.237279856098037e-05, "s_per_step": 0.5866300392150879, "peak_gb": 44.947974656, "samples_seen": 161600, "time": 1791133789.385984} | |
| {"step": 5075, "loss": 2.5157794332504273, "grad_norm": 1.1408394575119019, "lr": 9.15119651280956e-05, "s_per_step": 0.5873813438415527, "peak_gb": 44.947974656, "samples_seen": 162400, "time": 1791133804.070975} | |
| {"step": 5100, "loss": 2.4853475761413573, "grad_norm": 1.1142104864120483, "lr": 9.065176479813393e-05, "s_per_step": 0.5891704750061035, "peak_gb": 44.947974656, "samples_seen": 163200, "time": 1791133818.8006737} | |
| {"step": 5125, "loss": 2.535648889541626, "grad_norm": 1.1073273420333862, "lr": 8.979226173145183e-05, "s_per_step": 0.5848058700561524, "peak_gb": 44.947974656, "samples_seen": 164000, "time": 1791133833.421258} | |
| {"step": 5150, "loss": 2.582467722892761, "grad_norm": 1.2277833223342896, "lr": 8.893352003639856e-05, "s_per_step": 0.5909334659576416, "peak_gb": 44.947974656, "samples_seen": 164800, "time": 1791133848.1950076} | |
| {"step": 5175, "loss": 2.624933614730835, "grad_norm": 1.0772781372070312, "lr": 8.807560376453437e-05, "s_per_step": 0.580198278427124, "peak_gb": 44.947974656, "samples_seen": 165600, "time": 1791133862.700406} | |
| {"step": 5200, "loss": 2.5316876649856566, "grad_norm": 1.251028299331665, "lr": 8.721857690585314e-05, "s_per_step": 0.5918057537078858, "peak_gb": 44.947974656, "samples_seen": 166400, "time": 1791133877.495987} | |
| {"step": 5225, "loss": 2.5712487649917604, "grad_norm": 1.1420977115631104, "lr": 8.636250338400954e-05, "s_per_step": 0.5819726657867431, "peak_gb": 44.947974656, "samples_seen": 167200, "time": 1791133892.0457838} | |
| {"step": 5250, "loss": 2.5827745389938355, "grad_norm": 1.37429678440094, "lr": 8.550744705155087e-05, "s_per_step": 0.5890950107574463, "peak_gb": 44.947974656, "samples_seen": 168000, "time": 1791133906.7736533} | |
| {"step": 5275, "loss": 2.493775963783264, "grad_norm": 1.1473252773284912, "lr": 8.465347168515478e-05, "s_per_step": 0.5988393306732178, "peak_gb": 44.947974656, "samples_seen": 168800, "time": 1791133921.745074} | |
| {"step": 5300, "loss": 2.5703449940681455, "grad_norm": 1.315991997718811, "lr": 8.380064098087212e-05, "s_per_step": 0.5884280204772949, "peak_gb": 44.947974656, "samples_seen": 169600, "time": 1791133936.4563115} | |
| {"step": 5325, "loss": 2.5584110116958616, "grad_norm": 1.3650532960891724, "lr": 8.294901854937599e-05, "s_per_step": 0.5825414657592773, "peak_gb": 44.947974656, "samples_seen": 170400, "time": 1791133951.0203662} | |
| {"step": 5350, "loss": 2.5070259499549867, "grad_norm": 1.0850861072540283, "lr": 8.20986679112173e-05, "s_per_step": 0.5887926959991455, "peak_gb": 44.947974656, "samples_seen": 171200, "time": 1791133965.7406182} | |
| {"step": 5375, "loss": 2.5562100505828855, "grad_norm": 1.1863794326782227, "lr": 8.124965249208671e-05, "s_per_step": 0.5837687969207763, "peak_gb": 44.947974656, "samples_seen": 172000, "time": 1791133980.3353226} | |
| {"step": 5400, "loss": 2.5509732866287234, "grad_norm": 1.3163355588912964, "lr": 8.040203561808406e-05, "s_per_step": 0.5839274787902832, "peak_gb": 44.947974656, "samples_seen": 172800, "time": 1791133994.934007} | |
| {"step": 5425, "loss": 2.518836889266968, "grad_norm": 1.0753092765808105, "lr": 7.955588051099495e-05, "s_per_step": 0.5834451007843018, "peak_gb": 44.947974656, "samples_seen": 173600, "time": 1791134009.5206103} | |
| {"step": 5450, "loss": 2.486795573234558, "grad_norm": 1.2447965145111084, "lr": 7.87112502835751e-05, "s_per_step": 0.590032205581665, "peak_gb": 45.225538048, "samples_seen": 174400, "time": 1791134024.2720983} | |
| {"step": 5475, "loss": 2.5397833967208863, "grad_norm": 1.2422091960906982, "lr": 7.786820793484306e-05, "s_per_step": 0.5841742324829101, "peak_gb": 45.225538048, "samples_seen": 175200, "time": 1791134038.8771572} | |
| {"step": 5500, "loss": 2.582821946144104, "grad_norm": 1.1261637210845947, "lr": 7.702681634538104e-05, "s_per_step": 0.584408836364746, "peak_gb": 45.225538048, "samples_seen": 176000, "time": 1791134053.4881816} | |
| {"step": 5525, "loss": 2.5332029485702514, "grad_norm": 1.3875887393951416, "lr": 7.618713827264505e-05, "s_per_step": 0.6076767444610596, "peak_gb": 45.225538048, "samples_seen": 176800, "time": 1791134068.680784} | |
| {"step": 5550, "loss": 2.577248592376709, "grad_norm": 1.1470293998718262, "lr": 7.534923634628381e-05, "s_per_step": 0.582500295639038, "peak_gb": 45.225538048, "samples_seen": 177600, "time": 1791134083.2440093} | |
| {"step": 5575, "loss": 2.521993110179901, "grad_norm": 1.2665389776229858, "lr": 7.451317306346738e-05, "s_per_step": 0.5894964313507081, "peak_gb": 45.225538048, "samples_seen": 178400, "time": 1791134097.9821842} | |
| {"step": 5600, "loss": 2.538360843658447, "grad_norm": 1.314635992050171, "lr": 7.367901078422563e-05, "s_per_step": 0.5822025871276856, "peak_gb": 45.225538048, "samples_seen": 179200, "time": 1791134112.5379786} | |
| {"step": 5625, "loss": 2.519887990951538, "grad_norm": 1.2479692697525024, "lr": 7.284681172679697e-05, "s_per_step": 0.5847748279571533, "peak_gb": 45.225538048, "samples_seen": 180000, "time": 1791134127.1580513} | |
| {"step": 5650, "loss": 2.55150728225708, "grad_norm": 1.3254190683364868, "lr": 7.201663796298764e-05, "s_per_step": 0.5816287231445313, "peak_gb": 45.225538048, "samples_seen": 180800, "time": 1791134141.6998255} | |
| {"step": 5675, "loss": 2.480019929409027, "grad_norm": 1.3282145261764526, "lr": 7.118855141354186e-05, "s_per_step": 0.5884755229949952, "peak_gb": 45.225538048, "samples_seen": 181600, "time": 1791134156.4120905} | |
| {"step": 5700, "loss": 2.495427899360657, "grad_norm": 1.325265884399414, "lr": 7.036261384352343e-05, "s_per_step": 0.5823914813995361, "peak_gb": 45.225538048, "samples_seen": 182400, "time": 1791134170.972266} | |
| {"step": 5725, "loss": 2.478832368850708, "grad_norm": 1.0613092184066772, "lr": 6.953888685770869e-05, "s_per_step": 0.5816488647460938, "peak_gb": 45.225538048, "samples_seen": 183200, "time": 1791134185.5139039} | |
| {"step": 5750, "loss": 2.52920090675354, "grad_norm": 1.207517385482788, "lr": 6.871743189599156e-05, "s_per_step": 0.5833349800109864, "peak_gb": 45.225538048, "samples_seen": 184000, "time": 1791134200.0977366} | |
| {"step": 5775, "loss": 2.5796267938613893, "grad_norm": 1.1419939994812012, "lr": 6.789831022880101e-05, "s_per_step": 0.5960377788543701, "peak_gb": 45.225538048, "samples_seen": 184800, "time": 1791134214.9990556} | |
| {"step": 5800, "loss": 2.52916264295578, "grad_norm": 1.3384249210357666, "lr": 6.708158295253092e-05, "s_per_step": 0.5907851696014405, "peak_gb": 45.225538048, "samples_seen": 185600, "time": 1791134229.7691712} | |
| {"step": 5825, "loss": 2.5286863899230956, "grad_norm": 1.351222276687622, "lr": 6.626731098498311e-05, "s_per_step": 0.5822148704528809, "peak_gb": 45.225538048, "samples_seen": 186400, "time": 1791134244.3249931} | |
| {"step": 5850, "loss": 2.5227443981170654, "grad_norm": 1.1627928018569946, "lr": 6.545555506082355e-05, "s_per_step": 0.5858915615081787, "peak_gb": 45.225538048, "samples_seen": 187200, "time": 1791134258.9727561} | |
| {"step": 5875, "loss": 2.534986820220947, "grad_norm": 1.2816951274871826, "lr": 6.464637572705237e-05, "s_per_step": 0.5801717948913574, "peak_gb": 45.225538048, "samples_seen": 188000, "time": 1791134273.4775524} | |
| {"step": 5900, "loss": 2.489676251411438, "grad_norm": 1.4309545755386353, "lr": 6.383983333848773e-05, "s_per_step": 0.5923868274688721, "peak_gb": 45.225538048, "samples_seen": 188800, "time": 1791134288.2877378} | |
| {"step": 5925, "loss": 2.4901873302459716, "grad_norm": 1.322837471961975, "lr": 6.303598805326419e-05, "s_per_step": 0.5796713924407959, "peak_gb": 45.225538048, "samples_seen": 189600, "time": 1791134302.7800236} | |
| {"step": 5950, "loss": 2.53445716381073, "grad_norm": 1.3041024208068848, "lr": 6.223489982834558e-05, "s_per_step": 0.5908190441131592, "peak_gb": 45.225538048, "samples_seen": 190400, "time": 1791134317.550958} | |
| {"step": 5975, "loss": 2.523839635848999, "grad_norm": 1.1598639488220215, "lr": 6.1436628415053e-05, "s_per_step": 0.5810464763641358, "peak_gb": 45.225538048, "samples_seen": 191200, "time": 1791134332.0775537} | |
| {"step": 6000, "loss": 2.513823781013489, "grad_norm": 1.0870771408081055, "lr": 6.064123335460796e-05, "s_per_step": 0.5868215465545654, "peak_gb": 45.225538048, "samples_seen": 192000, "time": 1791134346.748537} | |
| {"step": 6025, "loss": 2.589872555732727, "grad_norm": 1.2455843687057495, "lr": 5.9848773973691574e-05, "s_per_step": 0.5989699459075928, "peak_gb": 45.225538048, "samples_seen": 192800, "time": 1791134361.7232323} | |
| {"step": 6050, "loss": 2.5560085201263427, "grad_norm": 1.2540245056152344, "lr": 5.905930938001937e-05, "s_per_step": 0.5814158630371093, "peak_gb": 45.225538048, "samples_seen": 193600, "time": 1791134376.2590868} | |
| {"step": 6075, "loss": 2.5238016700744628, "grad_norm": 1.5046987533569336, "lr": 5.827289845793256e-05, "s_per_step": 0.5851035404205323, "peak_gb": 45.225538048, "samples_seen": 194400, "time": 1791134390.8871312} | |
| {"step": 6100, "loss": 2.528533492088318, "grad_norm": 1.174469232559204, "lr": 5.748959986400611e-05, "s_per_step": 0.5847522258758545, "peak_gb": 45.225538048, "samples_seen": 195200, "time": 1791134405.5064287} | |
| {"step": 6125, "loss": 2.5303329944610597, "grad_norm": 1.1631888151168823, "lr": 5.670947202267356e-05, "s_per_step": 0.5879807376861572, "peak_gb": 45.225538048, "samples_seen": 196000, "time": 1791134420.2064354} | |
| {"step": 6150, "loss": 2.5317347621917725, "grad_norm": 1.316127896308899, "lr": 5.593257312186937e-05, "s_per_step": 0.5837984085083008, "peak_gb": 45.225538048, "samples_seen": 196800, "time": 1791134434.8018806} | |
| {"step": 6175, "loss": 2.434650685787201, "grad_norm": 1.1741480827331543, "lr": 5.5158961108688766e-05, "s_per_step": 0.5790462970733643, "peak_gb": 45.225538048, "samples_seen": 197600, "time": 1791134449.2784874} | |
| {"step": 6200, "loss": 2.531181104183197, "grad_norm": 1.1735306978225708, "lr": 5.438869368506563e-05, "s_per_step": 0.584972219467163, "peak_gb": 45.225538048, "samples_seen": 198400, "time": 1791134463.9032767} | |
| {"step": 6225, "loss": 2.527851085662842, "grad_norm": 1.0472126007080078, "lr": 5.36218283034686e-05, "s_per_step": 0.5841711044311524, "peak_gb": 45.225538048, "samples_seen": 199200, "time": 1791134478.5080554} | |
| {"step": 6250, "loss": 2.4174211168289186, "grad_norm": 1.081107258796692, "lr": 5.285842216261594e-05, "s_per_step": 0.5814971351623535, "peak_gb": 45.225538048, "samples_seen": 200000, "time": 1791134493.045984} | |
| {"step": 6275, "loss": 2.438464779853821, "grad_norm": 1.2638477087020874, "lr": 5.209853220320898e-05, "s_per_step": 0.5986836051940918, "peak_gb": 45.225538048, "samples_seen": 200800, "time": 1791134508.0135267} | |
| {"step": 6300, "loss": 2.541532530784607, "grad_norm": 1.1554198265075684, "lr": 5.134221510368531e-05, "s_per_step": 0.5808733463287353, "peak_gb": 45.225538048, "samples_seen": 201600, "time": 1791134522.535798} | |
| {"step": 6325, "loss": 2.5302062940597536, "grad_norm": 1.0484192371368408, "lr": 5.058952727599113e-05, "s_per_step": 0.5848421478271484, "peak_gb": 45.225538048, "samples_seen": 202400, "time": 1791134537.1572866} | |
| {"step": 6350, "loss": 2.5093615889549254, "grad_norm": 1.3501886129379272, "lr": 4.984052486137364e-05, "s_per_step": 0.5831260204315185, "peak_gb": 45.225538048, "samples_seen": 203200, "time": 1791134551.7359152} | |
| {"step": 6375, "loss": 2.4862116837501524, "grad_norm": 1.3331636190414429, "lr": 4.909526372619356e-05, "s_per_step": 0.5831469821929932, "peak_gb": 45.225538048, "samples_seen": 204000, "time": 1791134566.3150558} | |
| {"step": 6400, "loss": 2.553971781730652, "grad_norm": 1.2492870092391968, "lr": 4.835379945775823e-05, "s_per_step": 0.5849734497070312, "peak_gb": 45.225538048, "samples_seen": 204800, "time": 1791134580.9397955} | |
| {"step": 6425, "loss": 2.5170671367645263, "grad_norm": 1.2050851583480835, "lr": 4.7616187360175476e-05, "s_per_step": 0.5841898059844971, "peak_gb": 45.225538048, "samples_seen": 205600, "time": 1791134595.5449216} | |
| {"step": 6450, "loss": 2.5319773864746096, "grad_norm": 1.1314105987548828, "lr": 4.6882482450228574e-05, "s_per_step": 0.5848858451843262, "peak_gb": 45.225538048, "samples_seen": 206400, "time": 1791134610.1675096} | |
| {"step": 6475, "loss": 2.4931352043151858, "grad_norm": 1.1107985973358154, "lr": 4.615273945327272e-05, "s_per_step": 0.5831267642974853, "peak_gb": 45.225538048, "samples_seen": 207200, "time": 1791134624.7460885} | |
| {"step": 6500, "loss": 2.5409064221382143, "grad_norm": 1.199941873550415, "lr": 4.542701279915318e-05, "s_per_step": 0.5819946575164795, "peak_gb": 45.225538048, "samples_seen": 208000, "time": 1791134639.2963989} | |
| {"step": 6525, "loss": 2.49187207698822, "grad_norm": 1.4973266124725342, "lr": 4.470535661814538e-05, "s_per_step": 0.6058605766296387, "peak_gb": 45.225538048, "samples_seen": 208800, "time": 1791134654.4432883} | |
| {"step": 6550, "loss": 2.490929820537567, "grad_norm": 1.222715139389038, "lr": 4.398782473691767e-05, "s_per_step": 0.5849639797210693, "peak_gb": 45.225538048, "samples_seen": 209600, "time": 1791134669.0677845} | |
| {"step": 6575, "loss": 2.478930926322937, "grad_norm": 1.1837711334228516, "lr": 4.327447067451636e-05, "s_per_step": 0.5865503215789795, "peak_gb": 45.225538048, "samples_seen": 210400, "time": 1791134683.731912} | |
| {"step": 6600, "loss": 2.505696654319763, "grad_norm": 1.1841992139816284, "lr": 4.256534763837391e-05, "s_per_step": 0.5857251071929932, "peak_gb": 45.225538048, "samples_seen": 211200, "time": 1791134698.375444} | |
| {"step": 6625, "loss": 2.509692039489746, "grad_norm": 1.251827597618103, "lr": 4.186050852034028e-05, "s_per_step": 0.5832119750976562, "peak_gb": 45.225538048, "samples_seen": 212000, "time": 1791134712.9561343} | |
| {"step": 6650, "loss": 2.4981483721733095, "grad_norm": 1.3467367887496948, "lr": 4.1160005892737896e-05, "s_per_step": 0.5832837581634521, "peak_gb": 45.225538048, "samples_seen": 212800, "time": 1791134727.5386372} | |
| {"step": 6675, "loss": 2.487072801589966, "grad_norm": 1.149620771408081, "lr": 4.046389200444035e-05, "s_per_step": 0.5866239070892334, "peak_gb": 45.225538048, "samples_seen": 213600, "time": 1791134742.2046556} | |
| {"step": 6700, "loss": 2.464690637588501, "grad_norm": 1.290765643119812, "lr": 3.9772218776975314e-05, "s_per_step": 0.5862217617034912, "peak_gb": 45.225538048, "samples_seen": 214400, "time": 1791134756.8606098} | |
| {"step": 6725, "loss": 2.4712146949768066, "grad_norm": 1.1348451375961304, "lr": 3.908503780065186e-05, "s_per_step": 0.5837146186828613, "peak_gb": 45.225538048, "samples_seen": 215200, "time": 1791134771.4539366} | |
| {"step": 6750, "loss": 2.4894593477249147, "grad_norm": 1.0581586360931396, "lr": 3.840240033071231e-05, "s_per_step": 0.5876280879974365, "peak_gb": 45.225538048, "samples_seen": 216000, "time": 1791134786.1450136} | |
| {"step": 6775, "loss": 2.516192195415497, "grad_norm": 1.3426604270935059, "lr": 3.772435728350944e-05, "s_per_step": 0.6016309452056885, "peak_gb": 45.225538048, "samples_seen": 216800, "time": 1791134801.1862383} | |
| {"step": 6800, "loss": 2.5307986450195314, "grad_norm": 1.3854995965957642, "lr": 3.70509592327086e-05, "s_per_step": 0.5847000885009765, "peak_gb": 45.225538048, "samples_seen": 217600, "time": 1791134815.8041387} | |
| {"step": 6825, "loss": 2.5088115167617797, "grad_norm": 1.2087575197219849, "lr": 3.638225640551563e-05, "s_per_step": 0.5863976192474365, "peak_gb": 45.225538048, "samples_seen": 218400, "time": 1791134830.4645412} | |
| {"step": 6850, "loss": 2.4794558453559876, "grad_norm": 1.3083394765853882, "lr": 3.571829867893038e-05, "s_per_step": 0.5870515918731689, "peak_gb": 45.225538048, "samples_seen": 219200, "time": 1791134845.1412776} | |
| {"step": 6875, "loss": 2.495806655883789, "grad_norm": 1.250901222229004, "lr": 3.50591355760267e-05, "s_per_step": 0.5858700180053711, "peak_gb": 45.225538048, "samples_seen": 220000, "time": 1791134859.7884114} | |
| {"step": 6900, "loss": 2.472851881980896, "grad_norm": 1.4390413761138916, "lr": 3.440481626225849e-05, "s_per_step": 0.5833972072601319, "peak_gb": 45.225538048, "samples_seen": 220800, "time": 1791134874.3737664} | |
| {"step": 6925, "loss": 2.4779190325737, "grad_norm": 1.14964759349823, "lr": 3.3755389541792606e-05, "s_per_step": 0.5836262893676758, "peak_gb": 45.225538048, "samples_seen": 221600, "time": 1791134888.9648018} | |
| {"step": 6950, "loss": 2.4924482202529905, "grad_norm": 1.1170302629470825, "lr": 3.311090385386867e-05, "s_per_step": 0.5860085487365723, "peak_gb": 45.225538048, "samples_seen": 222400, "time": 1791134903.6154745} | |
| {"step": 6975, "loss": 2.449902744293213, "grad_norm": 1.2713782787322998, "lr": 3.247140726918607e-05, "s_per_step": 0.5829716205596924, "peak_gb": 45.225538048, "samples_seen": 223200, "time": 1791134918.190196} | |
| {"step": 7000, "loss": 2.5060114574432375, "grad_norm": 1.2075129747390747, "lr": 3.183694748631856e-05, "s_per_step": 0.5825292396545411, "peak_gb": 45.225538048, "samples_seen": 224000, "time": 1791134932.753835} | |
| {"step": 7025, "loss": 2.5190657806396484, "grad_norm": 1.2806220054626465, "lr": 3.1207571828156415e-05, "s_per_step": 0.6018135643005371, "peak_gb": 45.225538048, "samples_seen": 224800, "time": 1791134947.799628} | |
| {"step": 7050, "loss": 2.488545150756836, "grad_norm": 1.1726572513580322, "lr": 3.0583327238376826e-05, "s_per_step": 0.5843643283843994, "peak_gb": 45.225538048, "samples_seen": 225600, "time": 1791134962.4091752} | |
| {"step": 7075, "loss": 2.45016818523407, "grad_norm": 1.3082247972488403, "lr": 2.9964260277942414e-05, "s_per_step": 0.5856728076934814, "peak_gb": 45.225538048, "samples_seen": 226400, "time": 1791134977.0514216} | |
| {"step": 7100, "loss": 2.4964564561843874, "grad_norm": 1.2286127805709839, "lr": 2.9350417121628438e-05, "s_per_step": 0.5862992858886719, "peak_gb": 45.225538048, "samples_seen": 227200, "time": 1791134991.7094052} | |
| {"step": 7125, "loss": 2.4161909675598143, "grad_norm": 1.1147135496139526, "lr": 2.8741843554578563e-05, "s_per_step": 0.5842507934570312, "peak_gb": 45.225538048, "samples_seen": 228000, "time": 1791135006.3160708} | |
| {"step": 7150, "loss": 2.5295400643348693, "grad_norm": 1.2771178483963013, "lr": 2.8138584968890036e-05, "s_per_step": 0.5852422046661377, "peak_gb": 45.225538048, "samples_seen": 228800, "time": 1791135020.9474854} | |
| {"step": 7175, "loss": 2.5087658619880675, "grad_norm": 1.2442432641983032, "lr": 2.7540686360227917e-05, "s_per_step": 0.5861521339416504, "peak_gb": 45.225538048, "samples_seen": 229600, "time": 1791135035.6017551} | |
| {"step": 7200, "loss": 2.4834299731254577, "grad_norm": 1.3997399806976318, "lr": 2.6948192324468925e-05, "s_per_step": 0.5873078346252442, "peak_gb": 45.225538048, "samples_seen": 230400, "time": 1791135050.2848673} | |
| {"step": 7225, "loss": 2.44143901348114, "grad_norm": 1.4422211647033691, "lr": 2.636114705437519e-05, "s_per_step": 0.5871801567077637, "peak_gb": 45.225538048, "samples_seen": 231200, "time": 1791135064.9647627} | |
| {"step": 7250, "loss": 2.470247166156769, "grad_norm": 1.3490147590637207, "lr": 2.5779594336297975e-05, "s_per_step": 0.5863297176361084, "peak_gb": 45.225538048, "samples_seen": 232000, "time": 1791135079.6234357} | |
| {"step": 7275, "loss": 2.471605281829834, "grad_norm": 1.129075288772583, "lr": 2.5203577546911773e-05, "s_per_step": 0.599454345703125, "peak_gb": 45.225538048, "samples_seen": 232800, "time": 1791135094.6101875} | |
| {"step": 7300, "loss": 2.440209083557129, "grad_norm": 1.0634057521820068, "lr": 2.463313964997894e-05, "s_per_step": 0.5864029026031494, "peak_gb": 45.225538048, "samples_seen": 233600, "time": 1791135109.2706358} | |
| {"step": 7325, "loss": 2.5060981726646423, "grad_norm": 1.265033483505249, "lr": 2.4068323193145126e-05, "s_per_step": 0.5880957889556885, "peak_gb": 45.225538048, "samples_seen": 234400, "time": 1791135123.973469} | |
| {"step": 7350, "loss": 2.529538559913635, "grad_norm": 1.1425158977508545, "lr": 2.350917030476578e-05, "s_per_step": 0.5846072196960449, "peak_gb": 45.225538048, "samples_seen": 235200, "time": 1791135138.5890818} | |
| {"step": 7375, "loss": 2.4967665529251097, "grad_norm": 1.387877345085144, "lr": 2.295572269076374e-05, "s_per_step": 0.5827033042907714, "peak_gb": 45.225538048, "samples_seen": 236000, "time": 1791135153.1570456} | |
| {"step": 7400, "loss": 2.515732476711273, "grad_norm": 1.2702908515930176, "lr": 2.2408021631518726e-05, "s_per_step": 0.5825530815124512, "peak_gb": 45.225538048, "samples_seen": 236800, "time": 1791135167.7212825} | |
| {"step": 7425, "loss": 2.454144196510315, "grad_norm": 1.0984094142913818, "lr": 2.1866107978788153e-05, "s_per_step": 0.5797280502319336, "peak_gb": 45.225538048, "samples_seen": 237600, "time": 1791135182.2148888} | |
| {"step": 7450, "loss": 2.4906524801254273, "grad_norm": 1.2278966903686523, "lr": 2.1330022152660156e-05, "s_per_step": 0.5791896152496337, "peak_gb": 45.225538048, "samples_seen": 238400, "time": 1791135196.69504} | |
| {"step": 7475, "loss": 2.5189996767044067, "grad_norm": 1.3802945613861084, "lr": 2.0799804138538738e-05, "s_per_step": 0.5806455993652344, "peak_gb": 45.225538048, "samples_seen": 239200, "time": 1791135211.211557} | |
| {"step": 7500, "loss": 2.4968285632133482, "grad_norm": 1.1902079582214355, "lr": 2.027549348416138e-05, "s_per_step": 0.5817130088806153, "peak_gb": 45.225538048, "samples_seen": 240000, "time": 1791135225.754808} | |
| {"step": 7525, "loss": 2.5208859515190123, "grad_norm": 1.1940761804580688, "lr": 1.9757129296649146e-05, "s_per_step": 0.5999154567718505, "peak_gb": 45.225538048, "samples_seen": 240800, "time": 1791135240.753182} | |
| {"step": 7550, "loss": 2.5416905546188353, "grad_norm": 1.4812296628952026, "lr": 1.924475023958998e-05, "s_per_step": 0.5843287658691406, "peak_gb": 45.225538048, "samples_seen": 241600, "time": 1791135255.3618777} | |
| {"step": 7575, "loss": 2.4698385620117187, "grad_norm": 1.176838994026184, "lr": 1.87383945301547e-05, "s_per_step": 0.5848553848266601, "peak_gb": 45.225538048, "samples_seen": 242400, "time": 1791135269.9837594} | |
| {"step": 7600, "loss": 2.4738434529304505, "grad_norm": 1.2223095893859863, "lr": 1.8238099936246555e-05, "s_per_step": 0.5825335311889649, "peak_gb": 45.225538048, "samples_seen": 243200, "time": 1791135284.547529} | |
| {"step": 7625, "loss": 2.4790508365631103, "grad_norm": 1.1244370937347412, "lr": 1.774390377368418e-05, "s_per_step": 0.5838665103912354, "peak_gb": 45.225538048, "samples_seen": 244000, "time": 1791135299.144589} | |
| {"step": 7650, "loss": 2.5447232913970947, "grad_norm": 1.2436165809631348, "lr": 1.7255842903418274e-05, "s_per_step": 0.5841799449920654, "peak_gb": 45.225538048, "samples_seen": 244800, "time": 1791135313.7496023} | |
| {"step": 7675, "loss": 2.4780035495758055, "grad_norm": 1.200567603111267, "lr": 1.677395372878231e-05, "s_per_step": 0.5839977931976318, "peak_gb": 45.225538048, "samples_seen": 245600, "time": 1791135328.3500307} | |
| {"step": 7700, "loss": 2.4953444504737856, "grad_norm": 1.3506298065185547, "lr": 1.629827219277713e-05, "s_per_step": 0.5840514087677002, "peak_gb": 45.225538048, "samples_seen": 246400, "time": 1791135342.9517403} | |
| {"step": 7725, "loss": 2.4795714807510376, "grad_norm": 1.1271368265151978, "lr": 1.5828833775390227e-05, "s_per_step": 0.5836558628082276, "peak_gb": 45.225538048, "samples_seen": 247200, "time": 1791135357.5435355} | |
| {"step": 7750, "loss": 2.4116058373451232, "grad_norm": 1.1426550149917603, "lr": 1.5365673490949285e-05, "s_per_step": 0.5836513805389404, "peak_gb": 45.225538048, "samples_seen": 248000, "time": 1791135372.135241} | |
| {"step": 7775, "loss": 2.4785056114196777, "grad_norm": 1.1472325325012207, "lr": 1.4908825885510514e-05, "s_per_step": 0.5973025321960449, "peak_gb": 45.225538048, "samples_seen": 248800, "time": 1791135387.0681865} | |
| {"step": 7800, "loss": 2.4868078422546387, "grad_norm": 1.2887753248214722, "lr": 1.4458325034281993e-05, "s_per_step": 0.580522985458374, "peak_gb": 45.225538048, "samples_seen": 249600, "time": 1791135401.5817068} | |
| {"step": 7825, "loss": 2.4639941549301145, "grad_norm": 1.1615179777145386, "lr": 1.4014204539082044e-05, "s_per_step": 0.5852510643005371, "peak_gb": 45.225538048, "samples_seen": 250400, "time": 1791135416.213432} | |
| {"step": 7850, "loss": 2.480881841182709, "grad_norm": 1.1630935668945312, "lr": 1.3576497525832998e-05, "s_per_step": 0.5810826301574707, "peak_gb": 45.225538048, "samples_seen": 251200, "time": 1791135430.7409315} | |
| {"step": 7875, "loss": 2.467122640609741, "grad_norm": 1.288510799407959, "lr": 1.314523664209033e-05, "s_per_step": 0.5820274829864502, "peak_gb": 45.225538048, "samples_seen": 252000, "time": 1791135445.292001} | |
| {"step": 7900, "loss": 2.4884210443496704, "grad_norm": 1.2538615465164185, "lr": 1.2720454054607633e-05, "s_per_step": 0.5825617122650146, "peak_gb": 45.225538048, "samples_seen": 252800, "time": 1791135459.8564053} | |
| {"step": 7925, "loss": 2.480919179916382, "grad_norm": 1.403016448020935, "lr": 1.2302181446937333e-05, "s_per_step": 0.5786206722259521, "peak_gb": 45.225538048, "samples_seen": 253600, "time": 1791135474.3223386} | |
| {"step": 7950, "loss": 2.439384446144104, "grad_norm": 1.1538753509521484, "lr": 1.1890450017067467e-05, "s_per_step": 0.5839206409454346, "peak_gb": 45.225538048, "samples_seen": 254400, "time": 1791135488.920715} | |
| {"step": 7975, "loss": 2.484659490585327, "grad_norm": 1.5197055339813232, "lr": 1.1485290475094745e-05, "s_per_step": 0.5797516345977783, "peak_gb": 45.225538048, "samples_seen": 255200, "time": 1791135503.414908} | |
| {"step": 8000, "loss": 2.4812649726867675, "grad_norm": 1.2070398330688477, "lr": 1.1086733040933938e-05, "s_per_step": 0.5830123424530029, "peak_gb": 45.225538048, "samples_seen": 256000, "time": 1791135517.9906447} | |
| {"step": 8025, "loss": 2.453145351409912, "grad_norm": 1.3291114568710327, "lr": 1.0694807442063836e-05, "s_per_step": 0.5979341888427734, "peak_gb": 45.225538048, "samples_seen": 256800, "time": 1791135532.9394002} | |
| {"step": 8050, "loss": 2.4227629256248475, "grad_norm": 1.178061604499817, "lr": 1.0309542911309932e-05, "s_per_step": 0.583064832687378, "peak_gb": 45.225538048, "samples_seen": 257600, "time": 1791135547.5164373} | |
| {"step": 8075, "loss": 2.4514348554611205, "grad_norm": 1.5888311862945557, "lr": 9.930968184664046e-06, "s_per_step": 0.5811198616027832, "peak_gb": 45.225538048, "samples_seen": 258400, "time": 1791135562.0448437} | |
| {"step": 8100, "loss": 2.4358947181701662, "grad_norm": 1.1722838878631592, "lr": 9.559111499140939e-06, "s_per_step": 0.579391222000122, "peak_gb": 45.225538048, "samples_seen": 259200, "time": 1791135576.530029} | |
| {"step": 8125, "loss": 2.470351276397705, "grad_norm": 1.2379904985427856, "lr": 9.194000590672202e-06, "s_per_step": 0.5833250331878662, "peak_gb": 45.225538048, "samples_seen": 260000, "time": 1791135591.1136327} | |
| {"step": 8150, "loss": 2.5454572772979738, "grad_norm": 1.0861706733703613, "lr": 8.835662692037516e-06, "s_per_step": 0.5829557609558106, "peak_gb": 45.225538048, "samples_seen": 260800, "time": 1791135605.6879003} | |
| {"step": 8175, "loss": 2.5356476593017576, "grad_norm": 1.193375825881958, "lr": 8.484124530833349e-06, "s_per_step": 0.5813982677459717, "peak_gb": 45.225538048, "samples_seen": 261600, "time": 1791135620.2232423} | |
| {"step": 8200, "loss": 2.5145446348190306, "grad_norm": 1.31069815158844, "lr": 8.139412327479512e-06, "s_per_step": 0.5830599784851074, "peak_gb": 45.225538048, "samples_seen": 262400, "time": 1791135634.8001153} | |
| {"step": 8225, "loss": 2.51434268951416, "grad_norm": 1.2565644979476929, "lr": 7.801551793263307e-06, "s_per_step": 0.5842070770263672, "peak_gb": 45.225538048, "samples_seen": 263200, "time": 1791135649.4057364} | |
| {"step": 8250, "loss": 2.4891091346740724, "grad_norm": 1.3129713535308838, "lr": 7.470568128421918e-06, "s_per_step": 0.5833453273773194, "peak_gb": 45.225538048, "samples_seen": 264000, "time": 1791135663.9898171} | |
| {"step": 8275, "loss": 2.4999825406074523, "grad_norm": 1.2650532722473145, "lr": 7.146486020262688e-06, "s_per_step": 0.5951438903808594, "peak_gb": 45.225538048, "samples_seen": 264800, "time": 1791135678.8688512} | |
| {"step": 8300, "loss": 2.50071989774704, "grad_norm": 1.366416335105896, "lr": 6.82932964132178e-06, "s_per_step": 0.585099573135376, "peak_gb": 45.225538048, "samples_seen": 265600, "time": 1791135693.4967763} | |
| {"step": 8325, "loss": 2.4906865310668946, "grad_norm": 1.2222192287445068, "lr": 6.519122647561249e-06, "s_per_step": 0.5849275970458985, "peak_gb": 45.225538048, "samples_seen": 266400, "time": 1791135708.120377} | |
| {"step": 8350, "loss": 2.482330822944641, "grad_norm": 1.2209337949752808, "lr": 6.215888176604501e-06, "s_per_step": 0.5821888160705566, "peak_gb": 45.225538048, "samples_seen": 267200, "time": 1791135722.6755044} | |
| {"step": 8375, "loss": 2.455729749202728, "grad_norm": 1.3347740173339844, "lr": 5.919648846010584e-06, "s_per_step": 0.5881471824645996, "peak_gb": 45.225538048, "samples_seen": 268000, "time": 1791135737.3796217} | |
| {"step": 8400, "loss": 2.4725853204727173, "grad_norm": 1.408981442451477, "lr": 5.6304267515872035e-06, "s_per_step": 0.5856296157836914, "peak_gb": 45.225538048, "samples_seen": 268800, "time": 1791135752.0207672} | |
| {"step": 8425, "loss": 2.4187474822998047, "grad_norm": 1.3314207792282104, "lr": 5.3482434657425755e-06, "s_per_step": 0.5818990707397461, "peak_gb": 45.225538048, "samples_seen": 269600, "time": 1791135766.5687203} | |
| {"step": 8450, "loss": 2.4801942539215087, "grad_norm": 1.0783225297927856, "lr": 5.073120035876466e-06, "s_per_step": 0.5826784038543701, "peak_gb": 45.225538048, "samples_seen": 270400, "time": 1791135781.136184} | |
| {"step": 8475, "loss": 2.4995450139045716, "grad_norm": 1.3838938474655151, "lr": 4.805076982810275e-06, "s_per_step": 0.5815659427642822, "peak_gb": 45.225538048, "samples_seen": 271200, "time": 1791135795.6757793} | |
| {"step": 8500, "loss": 2.4431419372558594, "grad_norm": 1.1133414506912231, "lr": 4.544134299256453e-06, "s_per_step": 0.5855115985870362, "peak_gb": 45.225538048, "samples_seen": 272000, "time": 1791135810.3140042} | |
| {"step": 8525, "loss": 2.4860039710998536, "grad_norm": 1.1502230167388916, "lr": 4.290311448327267e-06, "s_per_step": 0.6029162120819092, "peak_gb": 45.225538048, "samples_seen": 272800, "time": 1791135825.3872917} | |
| {"step": 8550, "loss": 2.502565712928772, "grad_norm": 1.4622975587844849, "lr": 4.043627362083124e-06, "s_per_step": 0.5819817352294921, "peak_gb": 45.225538048, "samples_seen": 273600, "time": 1791135839.9373028} | |
| {"step": 8575, "loss": 2.4554481315612793, "grad_norm": 1.2948318719863892, "lr": 3.8041004401204392e-06, "s_per_step": 0.5855245685577393, "peak_gb": 45.225538048, "samples_seen": 274400, "time": 1791135854.575897} | |
| {"step": 8600, "loss": 2.473366265296936, "grad_norm": 1.3055177927017212, "lr": 3.571748548199283e-06, "s_per_step": 0.5834248447418213, "peak_gb": 45.225538048, "samples_seen": 275200, "time": 1791135869.1619527} | |
| {"step": 8625, "loss": 2.4664463996887207, "grad_norm": 1.3097848892211914, "lr": 3.346589016910795e-06, "s_per_step": 0.5833245754241944, "peak_gb": 45.225538048, "samples_seen": 276000, "time": 1791135883.7455816} | |
| {"step": 8650, "loss": 2.5279615044593813, "grad_norm": 1.281739354133606, "lr": 3.1286386403845402e-06, "s_per_step": 0.5869896125793457, "peak_gb": 45.225538048, "samples_seen": 276800, "time": 1791135898.4208338} | |
| {"step": 8675, "loss": 2.4256000685691834, "grad_norm": 1.1321176290512085, "lr": 2.917913675035888e-06, "s_per_step": 0.5836698818206787, "peak_gb": 45.225538048, "samples_seen": 277600, "time": 1791135913.0130074} | |
| {"step": 8700, "loss": 2.520475058555603, "grad_norm": 1.046059250831604, "lr": 2.7144298383534607e-06, "s_per_step": 0.5819922924041748, "peak_gb": 45.225538048, "samples_seen": 278400, "time": 1791135927.5632734} | |
| {"step": 8725, "loss": 2.555812520980835, "grad_norm": 1.1831002235412598, "lr": 2.5182023077268024e-06, "s_per_step": 0.5796582889556885, "peak_gb": 45.225538048, "samples_seen": 279200, "time": 1791135942.0551524} | |
| {"step": 8750, "loss": 2.4607612800598146, "grad_norm": 1.2153393030166626, "lr": 2.3292457193143657e-06, "s_per_step": 0.5847400951385499, "peak_gb": 45.225538048, "samples_seen": 280000, "time": 1791135956.6740828} | |
| {"step": 8775, "loss": 2.4432231545448304, "grad_norm": 1.3403053283691406, "lr": 2.1475741669517936e-06, "s_per_step": 0.5985502052307129, "peak_gb": 45.225538048, "samples_seen": 280800, "time": 1791135971.638234} | |
| {"step": 8800, "loss": 2.45842068195343, "grad_norm": 1.3938454389572144, "lr": 1.973201201100705e-06, "s_per_step": 0.5829646301269531, "peak_gb": 45.225538048, "samples_seen": 281600, "time": 1791135986.2127783} | |
| {"step": 8825, "loss": 2.4700878167152407, "grad_norm": 1.2799893617630005, "lr": 1.806139827838027e-06, "s_per_step": 0.5821155929565429, "peak_gb": 45.225538048, "samples_seen": 282400, "time": 1791136000.766119} | |
| {"step": 8850, "loss": 2.505449166297913, "grad_norm": 1.1758151054382324, "lr": 1.646402507885858e-06, "s_per_step": 0.5805652141571045, "peak_gb": 45.225538048, "samples_seen": 283200, "time": 1791136015.2806501} | |
| {"step": 8875, "loss": 2.4752099657058717, "grad_norm": 1.1823129653930664, "lr": 1.4940011556820676e-06, "s_per_step": 0.5807376194000244, "peak_gb": 45.225538048, "samples_seen": 284000, "time": 1791136029.7995193} | |
| {"step": 8900, "loss": 2.477540431022644, "grad_norm": 1.2883774042129517, "lr": 1.3489471384916518e-06, "s_per_step": 0.5786253547668457, "peak_gb": 45.225538048, "samples_seen": 284800, "time": 1791136044.2656045} | |
| {"step": 8925, "loss": 2.472158603668213, "grad_norm": 1.2201075553894043, "lr": 1.2112512755588335e-06, "s_per_step": 0.5808994483947754, "peak_gb": 45.225538048, "samples_seen": 285600, "time": 1791136058.7884433} | |
| {"step": 8950, "loss": 2.4544294118881225, "grad_norm": 1.2970439195632935, "lr": 1.0809238373000962e-06, "s_per_step": 0.581709451675415, "peak_gb": 45.225538048, "samples_seen": 286400, "time": 1791136073.3315735} | |
| {"step": 8975, "loss": 2.400626153945923, "grad_norm": 1.2315267324447632, "lr": 9.579745445381539e-07, "s_per_step": 0.579955415725708, "peak_gb": 45.225538048, "samples_seen": 287200, "time": 1791136087.8308325} | |
| {"step": 9000, "loss": 2.4409583902359007, "grad_norm": 1.1493794918060303, "lr": 8.424125677768846e-07, "s_per_step": 0.5824070739746093, "peak_gb": 45.225538048, "samples_seen": 288000, "time": 1791136102.3914094} | |
| {"step": 9025, "loss": 2.4901751470565796, "grad_norm": 1.405742883682251, "lr": 7.342465265172904e-07, "s_per_step": 0.5998865604400635, "peak_gb": 45.225538048, "samples_seen": 288800, "time": 1791136117.3889866} | |
| {"step": 9050, "loss": 2.45655734539032, "grad_norm": 1.2151944637298584, "lr": 6.334844886146552e-07, "s_per_step": 0.5862552833557129, "peak_gb": 45.225538048, "samples_seen": 289600, "time": 1791136132.045783} | |
| {"step": 9075, "loss": 2.440645921230316, "grad_norm": 1.2591733932495117, "lr": 5.401339696767371e-07, "s_per_step": 0.5819112586975098, "peak_gb": 45.225538048, "samples_seen": 290400, "time": 1791136146.593972} | |
| {"step": 9100, "loss": 2.4351733326911926, "grad_norm": 1.4817209243774414, "lr": 4.542019325032176e-07, "s_per_step": 0.5811293697357178, "peak_gb": 45.225538048, "samples_seen": 291200, "time": 1791136161.1227205} | |
| {"step": 9125, "loss": 2.499671845436096, "grad_norm": 1.075323224067688, "lr": 3.756947865663274e-07, "s_per_step": 0.580502290725708, "peak_gb": 45.225538048, "samples_seen": 292000, "time": 1791136175.635759} | |
| {"step": 9150, "loss": 2.4365021347999574, "grad_norm": 1.199285626411438, "lr": 3.0461838753281793e-07, "s_per_step": 0.5829291343688965, "peak_gb": 45.225538048, "samples_seen": 292800, "time": 1791136190.209385} | |
| {"step": 9175, "loss": 2.5040885043144225, "grad_norm": 1.390062689781189, "lr": 2.4097803682719967e-07, "s_per_step": 0.5805082321166992, "peak_gb": 45.225538048, "samples_seen": 293600, "time": 1791136204.7224927} | |
| {"step": 9200, "loss": 2.4622223567962647, "grad_norm": 1.1260004043579102, "lr": 1.847784812362696e-07, "s_per_step": 0.5807758331298828, "peak_gb": 45.225538048, "samples_seen": 294400, "time": 1791136219.2422497} | |
| {"step": 9225, "loss": 2.5410248279571532, "grad_norm": 1.2212775945663452, "lr": 1.360239125551388e-07, "s_per_step": 0.5833808612823487, "peak_gb": 45.225538048, "samples_seen": 295200, "time": 1791136233.8271465} | |
| {"step": 9250, "loss": 2.4439662075042725, "grad_norm": 1.3457050323486328, "lr": 9.471796727449356e-08, "s_per_step": 0.5828397941589355, "peak_gb": 45.225538048, "samples_seen": 296000, "time": 1791136248.3985698} | |
| {"step": 9275, "loss": 2.402722330093384, "grad_norm": 1.2421631813049316, "lr": 6.086372630945692e-08, "s_per_step": 0.5969734477996826, "peak_gb": 45.225538048, "samples_seen": 296800, "time": 1791136263.3232737} | |
| {"step": 9300, "loss": 2.4314382100105285, "grad_norm": 1.442682147026062, "lr": 3.446371476966137e-08, "s_per_step": 0.5828660678863525, "peak_gb": 45.225538048, "samples_seen": 297600, "time": 1791136277.895351} | |
| {"step": 9325, "loss": 2.46381530046463, "grad_norm": 1.3629335165023804, "lr": 1.5519901771032798e-08, "s_per_step": 0.5814544200897217, "peak_gb": 45.225538048, "samples_seen": 298400, "time": 1791136292.4321828} | |
| {"step": 9350, "loss": 2.448145937919617, "grad_norm": 1.2016350030899048, "lr": 4.033700288830211e-09, "s_per_step": 0.5831421184539795, "peak_gb": 45.225538048, "samples_seen": 299200, "time": 1791136307.0111272} | |
| {"step": 9375, "loss": 2.453929500579834, "grad_norm": 1.3293850421905518, "lr": 5.967052318922584e-12, "s_per_step": 0.5822473049163819, "peak_gb": 45.225538048, "samples_seen": 300000, "time": 1791136321.5678217} | |