| { |
| "best_global_step": null, |
| "best_metric": 0.3671196699142456, |
| "best_model_checkpoint": null, |
| "epoch": 4.951838553918535, |
| "eval_steps": 500, |
| "global_step": 20000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0002476166893648632, |
| "grad_norm": 0.48706236481666565, |
| "learning_rate": 0.0, |
| "loss": 3.0743, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.02476166893648632, |
| "grad_norm": 0.6543678045272827, |
| "learning_rate": 9.900000000000002e-06, |
| "loss": 2.8614, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.04952333787297264, |
| "grad_norm": 0.5323843359947205, |
| "learning_rate": 1.9900000000000003e-05, |
| "loss": 1.8779, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.07428500680945896, |
| "grad_norm": 0.9197348952293396, |
| "learning_rate": 2.9900000000000002e-05, |
| "loss": 1.2173, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.09904667574594528, |
| "grad_norm": 1.113196849822998, |
| "learning_rate": 3.99e-05, |
| "loss": 0.9351, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.1238083446824316, |
| "grad_norm": 1.1514325141906738, |
| "learning_rate": 4.99e-05, |
| "loss": 0.8237, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.1238083446824316, |
| "eval_loss": 0.6713243126869202, |
| "eval_runtime": 303.9033, |
| "eval_samples_per_second": 47.249, |
| "eval_steps_per_second": 2.955, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.14857001361891792, |
| "grad_norm": 1.1924649477005005, |
| "learning_rate": 4.974866717440975e-05, |
| "loss": 0.7509, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.17333168255540424, |
| "grad_norm": 1.0876811742782593, |
| "learning_rate": 4.9494795633409495e-05, |
| "loss": 0.6963, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.19809335149189056, |
| "grad_norm": 1.4002293348312378, |
| "learning_rate": 4.924092409240924e-05, |
| "loss": 0.6837, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.22285502042837688, |
| "grad_norm": 1.2242807149887085, |
| "learning_rate": 4.898705255140899e-05, |
| "loss": 0.6686, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.2476166893648632, |
| "grad_norm": 1.3704895973205566, |
| "learning_rate": 4.873318101040874e-05, |
| "loss": 0.6462, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.2476166893648632, |
| "eval_loss": 0.5437047481536865, |
| "eval_runtime": 309.4401, |
| "eval_samples_per_second": 46.403, |
| "eval_steps_per_second": 2.902, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.2723783583013495, |
| "grad_norm": 1.2968043088912964, |
| "learning_rate": 4.847930946940848e-05, |
| "loss": 0.6301, |
| "step": 1100 |
| }, |
| { |
| "epoch": 0.29714002723783584, |
| "grad_norm": 1.4131654500961304, |
| "learning_rate": 4.822543792840823e-05, |
| "loss": 0.6256, |
| "step": 1200 |
| }, |
| { |
| "epoch": 0.3219016961743221, |
| "grad_norm": 1.3621524572372437, |
| "learning_rate": 4.7971566387407974e-05, |
| "loss": 0.6179, |
| "step": 1300 |
| }, |
| { |
| "epoch": 0.3466633651108085, |
| "grad_norm": 1.4688136577606201, |
| "learning_rate": 4.771769484640772e-05, |
| "loss": 0.5963, |
| "step": 1400 |
| }, |
| { |
| "epoch": 0.37142503404729477, |
| "grad_norm": 1.3867251873016357, |
| "learning_rate": 4.746382330540747e-05, |
| "loss": 0.5867, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.37142503404729477, |
| "eval_loss": 0.5053889155387878, |
| "eval_runtime": 301.1479, |
| "eval_samples_per_second": 47.681, |
| "eval_steps_per_second": 2.982, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.3961867029837811, |
| "grad_norm": 1.018188714981079, |
| "learning_rate": 4.720995176440721e-05, |
| "loss": 0.5854, |
| "step": 1600 |
| }, |
| { |
| "epoch": 0.4209483719202674, |
| "grad_norm": 1.3094606399536133, |
| "learning_rate": 4.6956080223406954e-05, |
| "loss": 0.567, |
| "step": 1700 |
| }, |
| { |
| "epoch": 0.44571004085675375, |
| "grad_norm": 1.3288716077804565, |
| "learning_rate": 4.6702208682406704e-05, |
| "loss": 0.5629, |
| "step": 1800 |
| }, |
| { |
| "epoch": 0.47047170979324004, |
| "grad_norm": 1.2919931411743164, |
| "learning_rate": 4.6448337141406453e-05, |
| "loss": 0.5568, |
| "step": 1900 |
| }, |
| { |
| "epoch": 0.4952333787297264, |
| "grad_norm": 1.161441445350647, |
| "learning_rate": 4.6194465600406197e-05, |
| "loss": 0.5574, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.4952333787297264, |
| "eval_loss": 0.4834918975830078, |
| "eval_runtime": 308.7731, |
| "eval_samples_per_second": 46.503, |
| "eval_steps_per_second": 2.908, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.5199950476662127, |
| "grad_norm": 1.0919381380081177, |
| "learning_rate": 4.5940594059405946e-05, |
| "loss": 0.5525, |
| "step": 2100 |
| }, |
| { |
| "epoch": 0.544756716602699, |
| "grad_norm": 1.302264928817749, |
| "learning_rate": 4.568672251840569e-05, |
| "loss": 0.5486, |
| "step": 2200 |
| }, |
| { |
| "epoch": 0.5695183855391853, |
| "grad_norm": 1.3316988945007324, |
| "learning_rate": 4.543285097740543e-05, |
| "loss": 0.5435, |
| "step": 2300 |
| }, |
| { |
| "epoch": 0.5942800544756717, |
| "grad_norm": 1.16013765335083, |
| "learning_rate": 4.517897943640518e-05, |
| "loss": 0.537, |
| "step": 2400 |
| }, |
| { |
| "epoch": 0.619041723412158, |
| "grad_norm": 1.0240144729614258, |
| "learning_rate": 4.4925107895404926e-05, |
| "loss": 0.5351, |
| "step": 2500 |
| }, |
| { |
| "epoch": 0.619041723412158, |
| "eval_loss": 0.46248629689216614, |
| "eval_runtime": 298.9584, |
| "eval_samples_per_second": 48.03, |
| "eval_steps_per_second": 3.004, |
| "step": 2500 |
| }, |
| { |
| "epoch": 0.6438033923486443, |
| "grad_norm": 1.403138279914856, |
| "learning_rate": 4.467123635440467e-05, |
| "loss": 0.529, |
| "step": 2600 |
| }, |
| { |
| "epoch": 0.6685650612851306, |
| "grad_norm": 1.0086416006088257, |
| "learning_rate": 4.441736481340442e-05, |
| "loss": 0.5179, |
| "step": 2700 |
| }, |
| { |
| "epoch": 0.693326730221617, |
| "grad_norm": 1.0099183320999146, |
| "learning_rate": 4.416349327240417e-05, |
| "loss": 0.5159, |
| "step": 2800 |
| }, |
| { |
| "epoch": 0.7180883991581033, |
| "grad_norm": 1.066780686378479, |
| "learning_rate": 4.390962173140391e-05, |
| "loss": 0.5184, |
| "step": 2900 |
| }, |
| { |
| "epoch": 0.7428500680945895, |
| "grad_norm": 1.1880680322647095, |
| "learning_rate": 4.365575019040366e-05, |
| "loss": 0.5132, |
| "step": 3000 |
| }, |
| { |
| "epoch": 0.7428500680945895, |
| "eval_loss": 0.4524896740913391, |
| "eval_runtime": 309.4036, |
| "eval_samples_per_second": 46.409, |
| "eval_steps_per_second": 2.902, |
| "step": 3000 |
| }, |
| { |
| "epoch": 0.7676117370310759, |
| "grad_norm": 1.128923773765564, |
| "learning_rate": 4.3401878649403405e-05, |
| "loss": 0.5132, |
| "step": 3100 |
| }, |
| { |
| "epoch": 0.7923734059675622, |
| "grad_norm": 1.0441526174545288, |
| "learning_rate": 4.314800710840315e-05, |
| "loss": 0.5024, |
| "step": 3200 |
| }, |
| { |
| "epoch": 0.8171350749040486, |
| "grad_norm": 1.3435834646224976, |
| "learning_rate": 4.28941355674029e-05, |
| "loss": 0.4999, |
| "step": 3300 |
| }, |
| { |
| "epoch": 0.8418967438405348, |
| "grad_norm": 1.0047725439071655, |
| "learning_rate": 4.264026402640264e-05, |
| "loss": 0.5025, |
| "step": 3400 |
| }, |
| { |
| "epoch": 0.8666584127770212, |
| "grad_norm": 1.1918917894363403, |
| "learning_rate": 4.238639248540239e-05, |
| "loss": 0.5002, |
| "step": 3500 |
| }, |
| { |
| "epoch": 0.8666584127770212, |
| "eval_loss": 0.44193407893180847, |
| "eval_runtime": 307.4102, |
| "eval_samples_per_second": 46.71, |
| "eval_steps_per_second": 2.921, |
| "step": 3500 |
| }, |
| { |
| "epoch": 0.8914200817135075, |
| "grad_norm": 1.3518158197402954, |
| "learning_rate": 4.2132520944402134e-05, |
| "loss": 0.4972, |
| "step": 3600 |
| }, |
| { |
| "epoch": 0.9161817506499939, |
| "grad_norm": 1.2649939060211182, |
| "learning_rate": 4.1878649403401884e-05, |
| "loss": 0.4935, |
| "step": 3700 |
| }, |
| { |
| "epoch": 0.9409434195864801, |
| "grad_norm": 1.1180412769317627, |
| "learning_rate": 4.162477786240163e-05, |
| "loss": 0.5021, |
| "step": 3800 |
| }, |
| { |
| "epoch": 0.9657050885229664, |
| "grad_norm": 0.9952785968780518, |
| "learning_rate": 4.137090632140137e-05, |
| "loss": 0.4995, |
| "step": 3900 |
| }, |
| { |
| "epoch": 0.9904667574594528, |
| "grad_norm": 1.1129059791564941, |
| "learning_rate": 4.111703478040112e-05, |
| "loss": 0.4944, |
| "step": 4000 |
| }, |
| { |
| "epoch": 0.9904667574594528, |
| "eval_loss": 0.4326762557029724, |
| "eval_runtime": 305.7402, |
| "eval_samples_per_second": 46.965, |
| "eval_steps_per_second": 2.937, |
| "step": 4000 |
| }, |
| { |
| "epoch": 1.0151046180512566, |
| "grad_norm": 1.2399227619171143, |
| "learning_rate": 4.086316323940086e-05, |
| "loss": 0.4828, |
| "step": 4100 |
| }, |
| { |
| "epoch": 1.0398662869877429, |
| "grad_norm": 1.2356698513031006, |
| "learning_rate": 4.0609291698400606e-05, |
| "loss": 0.4818, |
| "step": 4200 |
| }, |
| { |
| "epoch": 1.0646279559242293, |
| "grad_norm": 1.016559362411499, |
| "learning_rate": 4.0355420157400356e-05, |
| "loss": 0.4777, |
| "step": 4300 |
| }, |
| { |
| "epoch": 1.0893896248607156, |
| "grad_norm": 1.1003488302230835, |
| "learning_rate": 4.0101548616400106e-05, |
| "loss": 0.4818, |
| "step": 4400 |
| }, |
| { |
| "epoch": 1.114151293797202, |
| "grad_norm": 1.0257238149642944, |
| "learning_rate": 3.984767707539985e-05, |
| "loss": 0.4804, |
| "step": 4500 |
| }, |
| { |
| "epoch": 1.114151293797202, |
| "eval_loss": 0.4317300021648407, |
| "eval_runtime": 301.8975, |
| "eval_samples_per_second": 47.563, |
| "eval_steps_per_second": 2.975, |
| "step": 4500 |
| }, |
| { |
| "epoch": 1.1389129627336882, |
| "grad_norm": 0.9789583683013916, |
| "learning_rate": 3.95938055343996e-05, |
| "loss": 0.4765, |
| "step": 4600 |
| }, |
| { |
| "epoch": 1.1636746316701745, |
| "grad_norm": 1.2558050155639648, |
| "learning_rate": 3.933993399339934e-05, |
| "loss": 0.481, |
| "step": 4700 |
| }, |
| { |
| "epoch": 1.188436300606661, |
| "grad_norm": 1.0205676555633545, |
| "learning_rate": 3.9086062452399085e-05, |
| "loss": 0.4826, |
| "step": 4800 |
| }, |
| { |
| "epoch": 1.2131979695431472, |
| "grad_norm": 1.0989702939987183, |
| "learning_rate": 3.8832190911398835e-05, |
| "loss": 0.4716, |
| "step": 4900 |
| }, |
| { |
| "epoch": 1.2379596384796336, |
| "grad_norm": 1.031387448310852, |
| "learning_rate": 3.857831937039858e-05, |
| "loss": 0.4704, |
| "step": 5000 |
| }, |
| { |
| "epoch": 1.2379596384796336, |
| "eval_loss": 0.4228954017162323, |
| "eval_runtime": 306.4121, |
| "eval_samples_per_second": 46.862, |
| "eval_steps_per_second": 2.931, |
| "step": 5000 |
| }, |
| { |
| "epoch": 1.2627213074161199, |
| "grad_norm": 1.123007893562317, |
| "learning_rate": 3.832444782939832e-05, |
| "loss": 0.4688, |
| "step": 5100 |
| }, |
| { |
| "epoch": 1.2874829763526061, |
| "grad_norm": 1.0141407251358032, |
| "learning_rate": 3.807057628839807e-05, |
| "loss": 0.4678, |
| "step": 5200 |
| }, |
| { |
| "epoch": 1.3122446452890926, |
| "grad_norm": 1.0771005153656006, |
| "learning_rate": 3.781670474739782e-05, |
| "loss": 0.4659, |
| "step": 5300 |
| }, |
| { |
| "epoch": 1.3370063142255788, |
| "grad_norm": 1.2410191297531128, |
| "learning_rate": 3.7562833206397564e-05, |
| "loss": 0.4725, |
| "step": 5400 |
| }, |
| { |
| "epoch": 1.361767983162065, |
| "grad_norm": 0.9323300123214722, |
| "learning_rate": 3.7308961665397314e-05, |
| "loss": 0.4662, |
| "step": 5500 |
| }, |
| { |
| "epoch": 1.361767983162065, |
| "eval_loss": 0.418260782957077, |
| "eval_runtime": 305.893, |
| "eval_samples_per_second": 46.941, |
| "eval_steps_per_second": 2.936, |
| "step": 5500 |
| }, |
| { |
| "epoch": 1.3865296520985515, |
| "grad_norm": 0.9075552225112915, |
| "learning_rate": 3.705509012439706e-05, |
| "loss": 0.469, |
| "step": 5600 |
| }, |
| { |
| "epoch": 1.4112913210350377, |
| "grad_norm": 1.095397710800171, |
| "learning_rate": 3.68012185833968e-05, |
| "loss": 0.4696, |
| "step": 5700 |
| }, |
| { |
| "epoch": 1.436052989971524, |
| "grad_norm": 1.2005417346954346, |
| "learning_rate": 3.654734704239655e-05, |
| "loss": 0.4553, |
| "step": 5800 |
| }, |
| { |
| "epoch": 1.4608146589080104, |
| "grad_norm": 1.0341594219207764, |
| "learning_rate": 3.6293475501396294e-05, |
| "loss": 0.4632, |
| "step": 5900 |
| }, |
| { |
| "epoch": 1.4855763278444967, |
| "grad_norm": 1.0710721015930176, |
| "learning_rate": 3.603960396039604e-05, |
| "loss": 0.4676, |
| "step": 6000 |
| }, |
| { |
| "epoch": 1.4855763278444967, |
| "eval_loss": 0.41258370876312256, |
| "eval_runtime": 333.4873, |
| "eval_samples_per_second": 43.057, |
| "eval_steps_per_second": 2.693, |
| "step": 6000 |
| }, |
| { |
| "epoch": 1.510337996780983, |
| "grad_norm": 1.0697613954544067, |
| "learning_rate": 3.5785732419395787e-05, |
| "loss": 0.4653, |
| "step": 6100 |
| }, |
| { |
| "epoch": 1.5350996657174694, |
| "grad_norm": 0.9342092275619507, |
| "learning_rate": 3.5531860878395536e-05, |
| "loss": 0.4584, |
| "step": 6200 |
| }, |
| { |
| "epoch": 1.5598613346539558, |
| "grad_norm": 1.18372642993927, |
| "learning_rate": 3.527798933739528e-05, |
| "loss": 0.4646, |
| "step": 6300 |
| }, |
| { |
| "epoch": 1.5846230035904418, |
| "grad_norm": 0.9926603436470032, |
| "learning_rate": 3.502411779639503e-05, |
| "loss": 0.4523, |
| "step": 6400 |
| }, |
| { |
| "epoch": 1.6093846725269283, |
| "grad_norm": 0.8520728945732117, |
| "learning_rate": 3.477024625539477e-05, |
| "loss": 0.4508, |
| "step": 6500 |
| }, |
| { |
| "epoch": 1.6093846725269283, |
| "eval_loss": 0.4122717082500458, |
| "eval_runtime": 337.4066, |
| "eval_samples_per_second": 42.557, |
| "eval_steps_per_second": 2.661, |
| "step": 6500 |
| }, |
| { |
| "epoch": 1.6341463414634148, |
| "grad_norm": 1.0143983364105225, |
| "learning_rate": 3.4516374714394516e-05, |
| "loss": 0.4612, |
| "step": 6600 |
| }, |
| { |
| "epoch": 1.658908010399901, |
| "grad_norm": 1.0106840133666992, |
| "learning_rate": 3.426250317339426e-05, |
| "loss": 0.4684, |
| "step": 6700 |
| }, |
| { |
| "epoch": 1.6836696793363872, |
| "grad_norm": 1.0055443048477173, |
| "learning_rate": 3.400863163239401e-05, |
| "loss": 0.4568, |
| "step": 6800 |
| }, |
| { |
| "epoch": 1.7084313482728737, |
| "grad_norm": 0.9551578760147095, |
| "learning_rate": 3.375476009139376e-05, |
| "loss": 0.4604, |
| "step": 6900 |
| }, |
| { |
| "epoch": 1.73319301720936, |
| "grad_norm": 0.9932017922401428, |
| "learning_rate": 3.35008885503935e-05, |
| "loss": 0.4472, |
| "step": 7000 |
| }, |
| { |
| "epoch": 1.73319301720936, |
| "eval_loss": 0.40953782200813293, |
| "eval_runtime": 334.3565, |
| "eval_samples_per_second": 42.945, |
| "eval_steps_per_second": 2.686, |
| "step": 7000 |
| }, |
| { |
| "epoch": 1.7579546861458462, |
| "grad_norm": 1.0452265739440918, |
| "learning_rate": 3.324701700939325e-05, |
| "loss": 0.4604, |
| "step": 7100 |
| }, |
| { |
| "epoch": 1.7827163550823326, |
| "grad_norm": 1.0083004236221313, |
| "learning_rate": 3.2993145468392995e-05, |
| "loss": 0.4507, |
| "step": 7200 |
| }, |
| { |
| "epoch": 1.8074780240188189, |
| "grad_norm": 0.9387707710266113, |
| "learning_rate": 3.273927392739274e-05, |
| "loss": 0.4516, |
| "step": 7300 |
| }, |
| { |
| "epoch": 1.832239692955305, |
| "grad_norm": 0.9475572109222412, |
| "learning_rate": 3.248540238639249e-05, |
| "loss": 0.4444, |
| "step": 7400 |
| }, |
| { |
| "epoch": 1.8570013618917915, |
| "grad_norm": 1.093817949295044, |
| "learning_rate": 3.223153084539223e-05, |
| "loss": 0.456, |
| "step": 7500 |
| }, |
| { |
| "epoch": 1.8570013618917915, |
| "eval_loss": 0.4029190242290497, |
| "eval_runtime": 292.0631, |
| "eval_samples_per_second": 49.164, |
| "eval_steps_per_second": 3.075, |
| "step": 7500 |
| }, |
| { |
| "epoch": 1.8817630308282778, |
| "grad_norm": 0.9310826063156128, |
| "learning_rate": 3.1977659304391974e-05, |
| "loss": 0.4552, |
| "step": 7600 |
| }, |
| { |
| "epoch": 1.906524699764764, |
| "grad_norm": 1.0708472728729248, |
| "learning_rate": 3.1723787763391724e-05, |
| "loss": 0.4442, |
| "step": 7700 |
| }, |
| { |
| "epoch": 1.9312863687012505, |
| "grad_norm": 0.9762539267539978, |
| "learning_rate": 3.1469916222391474e-05, |
| "loss": 0.438, |
| "step": 7800 |
| }, |
| { |
| "epoch": 1.956048037637737, |
| "grad_norm": 1.1194584369659424, |
| "learning_rate": 3.121604468139122e-05, |
| "loss": 0.4475, |
| "step": 7900 |
| }, |
| { |
| "epoch": 1.980809706574223, |
| "grad_norm": 1.001720905303955, |
| "learning_rate": 3.096217314039097e-05, |
| "loss": 0.4355, |
| "step": 8000 |
| }, |
| { |
| "epoch": 1.980809706574223, |
| "eval_loss": 0.40090999007225037, |
| "eval_runtime": 290.1583, |
| "eval_samples_per_second": 49.487, |
| "eval_steps_per_second": 3.095, |
| "step": 8000 |
| }, |
| { |
| "epoch": 2.005447567166027, |
| "grad_norm": 1.2274198532104492, |
| "learning_rate": 3.070830159939071e-05, |
| "loss": 0.4395, |
| "step": 8100 |
| }, |
| { |
| "epoch": 2.0302092361025132, |
| "grad_norm": 1.008782148361206, |
| "learning_rate": 3.0454430058390453e-05, |
| "loss": 0.4386, |
| "step": 8200 |
| }, |
| { |
| "epoch": 2.0549709050389997, |
| "grad_norm": 1.110425591468811, |
| "learning_rate": 3.0200558517390203e-05, |
| "loss": 0.4427, |
| "step": 8300 |
| }, |
| { |
| "epoch": 2.0797325739754857, |
| "grad_norm": 0.944615364074707, |
| "learning_rate": 2.994668697638995e-05, |
| "loss": 0.4367, |
| "step": 8400 |
| }, |
| { |
| "epoch": 2.104494242911972, |
| "grad_norm": 1.0133123397827148, |
| "learning_rate": 2.9692815435389693e-05, |
| "loss": 0.4426, |
| "step": 8500 |
| }, |
| { |
| "epoch": 2.104494242911972, |
| "eval_loss": 0.3965131342411041, |
| "eval_runtime": 295.1479, |
| "eval_samples_per_second": 48.65, |
| "eval_steps_per_second": 3.043, |
| "step": 8500 |
| }, |
| { |
| "epoch": 2.1292559118484586, |
| "grad_norm": 0.7603266835212708, |
| "learning_rate": 2.9438943894389443e-05, |
| "loss": 0.4388, |
| "step": 8600 |
| }, |
| { |
| "epoch": 2.154017580784945, |
| "grad_norm": 0.928263783454895, |
| "learning_rate": 2.9185072353389186e-05, |
| "loss": 0.4386, |
| "step": 8700 |
| }, |
| { |
| "epoch": 2.178779249721431, |
| "grad_norm": 1.0597220659255981, |
| "learning_rate": 2.8931200812388932e-05, |
| "loss": 0.4281, |
| "step": 8800 |
| }, |
| { |
| "epoch": 2.2035409186579176, |
| "grad_norm": 1.0807472467422485, |
| "learning_rate": 2.8677329271388682e-05, |
| "loss": 0.4312, |
| "step": 8900 |
| }, |
| { |
| "epoch": 2.228302587594404, |
| "grad_norm": 1.0931870937347412, |
| "learning_rate": 2.8423457730388425e-05, |
| "loss": 0.4369, |
| "step": 9000 |
| }, |
| { |
| "epoch": 2.228302587594404, |
| "eval_loss": 0.39540666341781616, |
| "eval_runtime": 292.4821, |
| "eval_samples_per_second": 49.094, |
| "eval_steps_per_second": 3.07, |
| "step": 9000 |
| }, |
| { |
| "epoch": 2.25306425653089, |
| "grad_norm": 0.9188655614852905, |
| "learning_rate": 2.816958618938817e-05, |
| "loss": 0.4404, |
| "step": 9100 |
| }, |
| { |
| "epoch": 2.2778259254673765, |
| "grad_norm": 1.0746827125549316, |
| "learning_rate": 2.7915714648387918e-05, |
| "loss": 0.4395, |
| "step": 9200 |
| }, |
| { |
| "epoch": 2.302587594403863, |
| "grad_norm": 0.9879487156867981, |
| "learning_rate": 2.7661843107387665e-05, |
| "loss": 0.4209, |
| "step": 9300 |
| }, |
| { |
| "epoch": 2.327349263340349, |
| "grad_norm": 1.0951037406921387, |
| "learning_rate": 2.7407971566387408e-05, |
| "loss": 0.431, |
| "step": 9400 |
| }, |
| { |
| "epoch": 2.3521109322768354, |
| "grad_norm": 1.1300798654556274, |
| "learning_rate": 2.7154100025387158e-05, |
| "loss": 0.4286, |
| "step": 9500 |
| }, |
| { |
| "epoch": 2.3521109322768354, |
| "eval_loss": 0.3942405581474304, |
| "eval_runtime": 294.7824, |
| "eval_samples_per_second": 48.711, |
| "eval_steps_per_second": 3.046, |
| "step": 9500 |
| }, |
| { |
| "epoch": 2.376872601213322, |
| "grad_norm": 1.2054657936096191, |
| "learning_rate": 2.69002284843869e-05, |
| "loss": 0.433, |
| "step": 9600 |
| }, |
| { |
| "epoch": 2.401634270149808, |
| "grad_norm": 1.1896750926971436, |
| "learning_rate": 2.6646356943386647e-05, |
| "loss": 0.4295, |
| "step": 9700 |
| }, |
| { |
| "epoch": 2.4263959390862944, |
| "grad_norm": 1.0336116552352905, |
| "learning_rate": 2.639248540238639e-05, |
| "loss": 0.4345, |
| "step": 9800 |
| }, |
| { |
| "epoch": 2.451157608022781, |
| "grad_norm": 0.9962900876998901, |
| "learning_rate": 2.613861386138614e-05, |
| "loss": 0.4219, |
| "step": 9900 |
| }, |
| { |
| "epoch": 2.4759192769592673, |
| "grad_norm": 1.2592706680297852, |
| "learning_rate": 2.5884742320385884e-05, |
| "loss": 0.44, |
| "step": 10000 |
| }, |
| { |
| "epoch": 2.4759192769592673, |
| "eval_loss": 0.39048588275909424, |
| "eval_runtime": 294.6469, |
| "eval_samples_per_second": 48.733, |
| "eval_steps_per_second": 3.048, |
| "step": 10000 |
| }, |
| { |
| "epoch": 2.5006809458957533, |
| "grad_norm": 1.25287663936615, |
| "learning_rate": 2.563087077938563e-05, |
| "loss": 0.4331, |
| "step": 10100 |
| }, |
| { |
| "epoch": 2.5254426148322398, |
| "grad_norm": 1.2010307312011719, |
| "learning_rate": 2.537699923838538e-05, |
| "loss": 0.427, |
| "step": 10200 |
| }, |
| { |
| "epoch": 2.5502042837687258, |
| "grad_norm": 1.06023108959198, |
| "learning_rate": 2.5123127697385123e-05, |
| "loss": 0.4281, |
| "step": 10300 |
| }, |
| { |
| "epoch": 2.5749659527052122, |
| "grad_norm": 1.094394326210022, |
| "learning_rate": 2.486925615638487e-05, |
| "loss": 0.4237, |
| "step": 10400 |
| }, |
| { |
| "epoch": 2.5997276216416987, |
| "grad_norm": 1.039994716644287, |
| "learning_rate": 2.461538461538462e-05, |
| "loss": 0.4222, |
| "step": 10500 |
| }, |
| { |
| "epoch": 2.5997276216416987, |
| "eval_loss": 0.3886333405971527, |
| "eval_runtime": 298.9241, |
| "eval_samples_per_second": 48.036, |
| "eval_steps_per_second": 3.004, |
| "step": 10500 |
| }, |
| { |
| "epoch": 2.624489290578185, |
| "grad_norm": 1.0885295867919922, |
| "learning_rate": 2.4361513074384363e-05, |
| "loss": 0.4297, |
| "step": 10600 |
| }, |
| { |
| "epoch": 2.649250959514671, |
| "grad_norm": 0.9978443384170532, |
| "learning_rate": 2.410764153338411e-05, |
| "loss": 0.4251, |
| "step": 10700 |
| }, |
| { |
| "epoch": 2.6740126284511576, |
| "grad_norm": 0.8032694458961487, |
| "learning_rate": 2.3853769992383852e-05, |
| "loss": 0.4321, |
| "step": 10800 |
| }, |
| { |
| "epoch": 2.698774297387644, |
| "grad_norm": 1.1382070779800415, |
| "learning_rate": 2.3599898451383602e-05, |
| "loss": 0.4296, |
| "step": 10900 |
| }, |
| { |
| "epoch": 2.72353596632413, |
| "grad_norm": 0.9287987947463989, |
| "learning_rate": 2.334602691038335e-05, |
| "loss": 0.417, |
| "step": 11000 |
| }, |
| { |
| "epoch": 2.72353596632413, |
| "eval_loss": 0.3885912001132965, |
| "eval_runtime": 299.1382, |
| "eval_samples_per_second": 48.001, |
| "eval_steps_per_second": 3.002, |
| "step": 11000 |
| }, |
| { |
| "epoch": 2.7482976352606165, |
| "grad_norm": 1.0950629711151123, |
| "learning_rate": 2.3092155369383092e-05, |
| "loss": 0.4253, |
| "step": 11100 |
| }, |
| { |
| "epoch": 2.773059304197103, |
| "grad_norm": 1.0151338577270508, |
| "learning_rate": 2.2838283828382838e-05, |
| "loss": 0.4311, |
| "step": 11200 |
| }, |
| { |
| "epoch": 2.7978209731335895, |
| "grad_norm": 1.0384260416030884, |
| "learning_rate": 2.2584412287382585e-05, |
| "loss": 0.4277, |
| "step": 11300 |
| }, |
| { |
| "epoch": 2.8225826420700755, |
| "grad_norm": 1.0595632791519165, |
| "learning_rate": 2.233054074638233e-05, |
| "loss": 0.4174, |
| "step": 11400 |
| }, |
| { |
| "epoch": 2.847344311006562, |
| "grad_norm": 1.081904411315918, |
| "learning_rate": 2.2076669205382078e-05, |
| "loss": 0.4244, |
| "step": 11500 |
| }, |
| { |
| "epoch": 2.847344311006562, |
| "eval_loss": 0.3848166763782501, |
| "eval_runtime": 298.8323, |
| "eval_samples_per_second": 48.05, |
| "eval_steps_per_second": 3.005, |
| "step": 11500 |
| }, |
| { |
| "epoch": 2.872105979943048, |
| "grad_norm": 1.3593488931655884, |
| "learning_rate": 2.1822797664381824e-05, |
| "loss": 0.4236, |
| "step": 11600 |
| }, |
| { |
| "epoch": 2.8968676488795344, |
| "grad_norm": 0.9958997368812561, |
| "learning_rate": 2.156892612338157e-05, |
| "loss": 0.4272, |
| "step": 11700 |
| }, |
| { |
| "epoch": 2.921629317816021, |
| "grad_norm": 0.9125483632087708, |
| "learning_rate": 2.1315054582381317e-05, |
| "loss": 0.4195, |
| "step": 11800 |
| }, |
| { |
| "epoch": 2.9463909867525073, |
| "grad_norm": 1.026393175125122, |
| "learning_rate": 2.1061183041381064e-05, |
| "loss": 0.4216, |
| "step": 11900 |
| }, |
| { |
| "epoch": 2.9711526556889933, |
| "grad_norm": 0.984633207321167, |
| "learning_rate": 2.0807311500380807e-05, |
| "loss": 0.4197, |
| "step": 12000 |
| }, |
| { |
| "epoch": 2.9711526556889933, |
| "eval_loss": 0.3836701214313507, |
| "eval_runtime": 299.7207, |
| "eval_samples_per_second": 47.908, |
| "eval_steps_per_second": 2.996, |
| "step": 12000 |
| }, |
| { |
| "epoch": 2.99591432462548, |
| "grad_norm": 1.1759393215179443, |
| "learning_rate": 2.0553439959380553e-05, |
| "loss": 0.4182, |
| "step": 12100 |
| }, |
| { |
| "epoch": 3.0205521852172836, |
| "grad_norm": 0.9976751208305359, |
| "learning_rate": 2.02995684183803e-05, |
| "loss": 0.4176, |
| "step": 12200 |
| }, |
| { |
| "epoch": 3.04531385415377, |
| "grad_norm": 0.9128820896148682, |
| "learning_rate": 2.0045696877380047e-05, |
| "loss": 0.4115, |
| "step": 12300 |
| }, |
| { |
| "epoch": 3.070075523090256, |
| "grad_norm": 0.8917282819747925, |
| "learning_rate": 1.9791825336379793e-05, |
| "loss": 0.4068, |
| "step": 12400 |
| }, |
| { |
| "epoch": 3.0948371920267426, |
| "grad_norm": 1.04193115234375, |
| "learning_rate": 1.9537953795379536e-05, |
| "loss": 0.4138, |
| "step": 12500 |
| }, |
| { |
| "epoch": 3.0948371920267426, |
| "eval_loss": 0.3802282214164734, |
| "eval_runtime": 303.6383, |
| "eval_samples_per_second": 47.29, |
| "eval_steps_per_second": 2.957, |
| "step": 12500 |
| }, |
| { |
| "epoch": 3.119598860963229, |
| "grad_norm": 1.0125975608825684, |
| "learning_rate": 1.9284082254379286e-05, |
| "loss": 0.4074, |
| "step": 12600 |
| }, |
| { |
| "epoch": 3.144360529899715, |
| "grad_norm": 1.0177041292190552, |
| "learning_rate": 1.9030210713379033e-05, |
| "loss": 0.4179, |
| "step": 12700 |
| }, |
| { |
| "epoch": 3.1691221988362015, |
| "grad_norm": 1.2167311906814575, |
| "learning_rate": 1.8776339172378776e-05, |
| "loss": 0.415, |
| "step": 12800 |
| }, |
| { |
| "epoch": 3.193883867772688, |
| "grad_norm": 1.1083834171295166, |
| "learning_rate": 1.8522467631378522e-05, |
| "loss": 0.417, |
| "step": 12900 |
| }, |
| { |
| "epoch": 3.2186455367091744, |
| "grad_norm": 1.3251594305038452, |
| "learning_rate": 1.8268596090378272e-05, |
| "loss": 0.4096, |
| "step": 13000 |
| }, |
| { |
| "epoch": 3.2186455367091744, |
| "eval_loss": 0.37971043586730957, |
| "eval_runtime": 307.1968, |
| "eval_samples_per_second": 46.742, |
| "eval_steps_per_second": 2.923, |
| "step": 13000 |
| }, |
| { |
| "epoch": 3.2434072056456604, |
| "grad_norm": 1.1293381452560425, |
| "learning_rate": 1.8014724549378015e-05, |
| "loss": 0.4033, |
| "step": 13100 |
| }, |
| { |
| "epoch": 3.268168874582147, |
| "grad_norm": 0.8698910474777222, |
| "learning_rate": 1.7760853008377762e-05, |
| "loss": 0.414, |
| "step": 13200 |
| }, |
| { |
| "epoch": 3.2929305435186333, |
| "grad_norm": 0.8111106753349304, |
| "learning_rate": 1.7506981467377508e-05, |
| "loss": 0.4205, |
| "step": 13300 |
| }, |
| { |
| "epoch": 3.3176922124551194, |
| "grad_norm": 1.0510135889053345, |
| "learning_rate": 1.7253109926377255e-05, |
| "loss": 0.4193, |
| "step": 13400 |
| }, |
| { |
| "epoch": 3.342453881391606, |
| "grad_norm": 0.9042615294456482, |
| "learning_rate": 1.6999238385377e-05, |
| "loss": 0.4111, |
| "step": 13500 |
| }, |
| { |
| "epoch": 3.342453881391606, |
| "eval_loss": 0.38024312257766724, |
| "eval_runtime": 334.2385, |
| "eval_samples_per_second": 42.96, |
| "eval_steps_per_second": 2.687, |
| "step": 13500 |
| }, |
| { |
| "epoch": 3.3672155503280923, |
| "grad_norm": 0.9368965029716492, |
| "learning_rate": 1.6745366844376748e-05, |
| "loss": 0.4124, |
| "step": 13600 |
| }, |
| { |
| "epoch": 3.3919772192645783, |
| "grad_norm": 1.1354291439056396, |
| "learning_rate": 1.649149530337649e-05, |
| "loss": 0.4144, |
| "step": 13700 |
| }, |
| { |
| "epoch": 3.4167388882010647, |
| "grad_norm": 0.862594723701477, |
| "learning_rate": 1.6237623762376237e-05, |
| "loss": 0.4039, |
| "step": 13800 |
| }, |
| { |
| "epoch": 3.441500557137551, |
| "grad_norm": 1.2077276706695557, |
| "learning_rate": 1.5983752221375984e-05, |
| "loss": 0.4163, |
| "step": 13900 |
| }, |
| { |
| "epoch": 3.4662622260740372, |
| "grad_norm": 1.1101346015930176, |
| "learning_rate": 1.572988068037573e-05, |
| "loss": 0.4103, |
| "step": 14000 |
| }, |
| { |
| "epoch": 3.4662622260740372, |
| "eval_loss": 0.37751057744026184, |
| "eval_runtime": 344.048, |
| "eval_samples_per_second": 41.735, |
| "eval_steps_per_second": 2.61, |
| "step": 14000 |
| }, |
| { |
| "epoch": 3.4910238950105237, |
| "grad_norm": 0.9908251166343689, |
| "learning_rate": 1.5476009139375477e-05, |
| "loss": 0.4116, |
| "step": 14100 |
| }, |
| { |
| "epoch": 3.51578556394701, |
| "grad_norm": 1.144132375717163, |
| "learning_rate": 1.5222137598375222e-05, |
| "loss": 0.41, |
| "step": 14200 |
| }, |
| { |
| "epoch": 3.5405472328834966, |
| "grad_norm": 1.0292690992355347, |
| "learning_rate": 1.4968266057374968e-05, |
| "loss": 0.4157, |
| "step": 14300 |
| }, |
| { |
| "epoch": 3.5653089018199826, |
| "grad_norm": 1.2643660306930542, |
| "learning_rate": 1.4714394516374716e-05, |
| "loss": 0.4081, |
| "step": 14400 |
| }, |
| { |
| "epoch": 3.590070570756469, |
| "grad_norm": 1.3031563758850098, |
| "learning_rate": 1.446052297537446e-05, |
| "loss": 0.4098, |
| "step": 14500 |
| }, |
| { |
| "epoch": 3.590070570756469, |
| "eval_loss": 0.3778412640094757, |
| "eval_runtime": 330.1121, |
| "eval_samples_per_second": 43.497, |
| "eval_steps_per_second": 2.72, |
| "step": 14500 |
| }, |
| { |
| "epoch": 3.614832239692955, |
| "grad_norm": 1.0413382053375244, |
| "learning_rate": 1.4206651434374208e-05, |
| "loss": 0.4075, |
| "step": 14600 |
| }, |
| { |
| "epoch": 3.6395939086294415, |
| "grad_norm": 1.1236363649368286, |
| "learning_rate": 1.3952779893373954e-05, |
| "loss": 0.4049, |
| "step": 14700 |
| }, |
| { |
| "epoch": 3.664355577565928, |
| "grad_norm": 0.9670480489730835, |
| "learning_rate": 1.3698908352373699e-05, |
| "loss": 0.4066, |
| "step": 14800 |
| }, |
| { |
| "epoch": 3.6891172465024145, |
| "grad_norm": 0.8969297409057617, |
| "learning_rate": 1.3445036811373446e-05, |
| "loss": 0.4156, |
| "step": 14900 |
| }, |
| { |
| "epoch": 3.7138789154389005, |
| "grad_norm": 1.0945312976837158, |
| "learning_rate": 1.3191165270373194e-05, |
| "loss": 0.4133, |
| "step": 15000 |
| }, |
| { |
| "epoch": 3.7138789154389005, |
| "eval_loss": 0.3742968738079071, |
| "eval_runtime": 331.5339, |
| "eval_samples_per_second": 43.311, |
| "eval_steps_per_second": 2.709, |
| "step": 15000 |
| }, |
| { |
| "epoch": 3.738640584375387, |
| "grad_norm": 1.036347508430481, |
| "learning_rate": 1.2937293729372937e-05, |
| "loss": 0.4099, |
| "step": 15100 |
| }, |
| { |
| "epoch": 3.763402253311873, |
| "grad_norm": 1.0111111402511597, |
| "learning_rate": 1.2683422188372685e-05, |
| "loss": 0.4115, |
| "step": 15200 |
| }, |
| { |
| "epoch": 3.7881639222483594, |
| "grad_norm": 1.1293095350265503, |
| "learning_rate": 1.242955064737243e-05, |
| "loss": 0.4075, |
| "step": 15300 |
| }, |
| { |
| "epoch": 3.812925591184846, |
| "grad_norm": 1.1474101543426514, |
| "learning_rate": 1.2175679106372177e-05, |
| "loss": 0.4182, |
| "step": 15400 |
| }, |
| { |
| "epoch": 3.8376872601213323, |
| "grad_norm": 1.1107712984085083, |
| "learning_rate": 1.1921807565371923e-05, |
| "loss": 0.4081, |
| "step": 15500 |
| }, |
| { |
| "epoch": 3.8376872601213323, |
| "eval_loss": 0.37404417991638184, |
| "eval_runtime": 315.6431, |
| "eval_samples_per_second": 45.491, |
| "eval_steps_per_second": 2.845, |
| "step": 15500 |
| }, |
| { |
| "epoch": 3.8624489290578183, |
| "grad_norm": 0.9492923021316528, |
| "learning_rate": 1.166793602437167e-05, |
| "loss": 0.3983, |
| "step": 15600 |
| }, |
| { |
| "epoch": 3.887210597994305, |
| "grad_norm": 1.1327282190322876, |
| "learning_rate": 1.1414064483371414e-05, |
| "loss": 0.4043, |
| "step": 15700 |
| }, |
| { |
| "epoch": 3.9119722669307913, |
| "grad_norm": 1.0399820804595947, |
| "learning_rate": 1.1160192942371161e-05, |
| "loss": 0.406, |
| "step": 15800 |
| }, |
| { |
| "epoch": 3.9367339358672773, |
| "grad_norm": 1.1408737897872925, |
| "learning_rate": 1.0906321401370907e-05, |
| "loss": 0.4065, |
| "step": 15900 |
| }, |
| { |
| "epoch": 3.9614956048037637, |
| "grad_norm": 0.9349102973937988, |
| "learning_rate": 1.0652449860370652e-05, |
| "loss": 0.4056, |
| "step": 16000 |
| }, |
| { |
| "epoch": 3.9614956048037637, |
| "eval_loss": 0.37279391288757324, |
| "eval_runtime": 294.1835, |
| "eval_samples_per_second": 48.81, |
| "eval_steps_per_second": 3.053, |
| "step": 16000 |
| }, |
| { |
| "epoch": 3.98625727374025, |
| "grad_norm": 0.951724112033844, |
| "learning_rate": 1.0398578319370399e-05, |
| "loss": 0.4056, |
| "step": 16100 |
| }, |
| { |
| "epoch": 4.010895134332054, |
| "grad_norm": 1.131766438484192, |
| "learning_rate": 1.0144706778370145e-05, |
| "loss": 0.3989, |
| "step": 16200 |
| }, |
| { |
| "epoch": 4.03565680326854, |
| "grad_norm": 1.0067100524902344, |
| "learning_rate": 9.890835237369892e-06, |
| "loss": 0.4026, |
| "step": 16300 |
| }, |
| { |
| "epoch": 4.0604184722050265, |
| "grad_norm": 1.0153299570083618, |
| "learning_rate": 9.636963696369637e-06, |
| "loss": 0.4013, |
| "step": 16400 |
| }, |
| { |
| "epoch": 4.085180141141513, |
| "grad_norm": 1.2241690158843994, |
| "learning_rate": 9.383092155369383e-06, |
| "loss": 0.4, |
| "step": 16500 |
| }, |
| { |
| "epoch": 4.085180141141513, |
| "eval_loss": 0.3727540373802185, |
| "eval_runtime": 296.4387, |
| "eval_samples_per_second": 48.438, |
| "eval_steps_per_second": 3.029, |
| "step": 16500 |
| }, |
| { |
| "epoch": 4.109941810077999, |
| "grad_norm": 0.9304781556129456, |
| "learning_rate": 9.12922061436913e-06, |
| "loss": 0.3969, |
| "step": 16600 |
| }, |
| { |
| "epoch": 4.134703479014486, |
| "grad_norm": 1.1999999284744263, |
| "learning_rate": 8.875349073368876e-06, |
| "loss": 0.3921, |
| "step": 16700 |
| }, |
| { |
| "epoch": 4.159465147950971, |
| "grad_norm": 1.0765935182571411, |
| "learning_rate": 8.621477532368621e-06, |
| "loss": 0.409, |
| "step": 16800 |
| }, |
| { |
| "epoch": 4.184226816887458, |
| "grad_norm": 0.886246383190155, |
| "learning_rate": 8.367605991368369e-06, |
| "loss": 0.4019, |
| "step": 16900 |
| }, |
| { |
| "epoch": 4.208988485823944, |
| "grad_norm": 1.0984737873077393, |
| "learning_rate": 8.113734450368114e-06, |
| "loss": 0.3991, |
| "step": 17000 |
| }, |
| { |
| "epoch": 4.208988485823944, |
| "eval_loss": 0.3709471821784973, |
| "eval_runtime": 298.2727, |
| "eval_samples_per_second": 48.141, |
| "eval_steps_per_second": 3.011, |
| "step": 17000 |
| }, |
| { |
| "epoch": 4.233750154760431, |
| "grad_norm": 1.0152359008789062, |
| "learning_rate": 7.85986290936786e-06, |
| "loss": 0.3962, |
| "step": 17100 |
| }, |
| { |
| "epoch": 4.258511823696917, |
| "grad_norm": 1.1482372283935547, |
| "learning_rate": 7.605991368367606e-06, |
| "loss": 0.4, |
| "step": 17200 |
| }, |
| { |
| "epoch": 4.283273492633404, |
| "grad_norm": 0.9904143810272217, |
| "learning_rate": 7.352119827367353e-06, |
| "loss": 0.3918, |
| "step": 17300 |
| }, |
| { |
| "epoch": 4.30803516156989, |
| "grad_norm": 1.0268852710723877, |
| "learning_rate": 7.098248286367098e-06, |
| "loss": 0.4049, |
| "step": 17400 |
| }, |
| { |
| "epoch": 4.332796830506376, |
| "grad_norm": 1.005434274673462, |
| "learning_rate": 6.844376745366844e-06, |
| "loss": 0.4009, |
| "step": 17500 |
| }, |
| { |
| "epoch": 4.332796830506376, |
| "eval_loss": 0.3704555034637451, |
| "eval_runtime": 298.2902, |
| "eval_samples_per_second": 48.138, |
| "eval_steps_per_second": 3.01, |
| "step": 17500 |
| }, |
| { |
| "epoch": 4.357558499442862, |
| "grad_norm": 1.2603648900985718, |
| "learning_rate": 6.590505204366591e-06, |
| "loss": 0.4073, |
| "step": 17600 |
| }, |
| { |
| "epoch": 4.382320168379349, |
| "grad_norm": 1.231177568435669, |
| "learning_rate": 6.336633663366337e-06, |
| "loss": 0.4009, |
| "step": 17700 |
| }, |
| { |
| "epoch": 4.407081837315835, |
| "grad_norm": 1.0092039108276367, |
| "learning_rate": 6.082762122366083e-06, |
| "loss": 0.3984, |
| "step": 17800 |
| }, |
| { |
| "epoch": 4.431843506252322, |
| "grad_norm": 1.1094638109207153, |
| "learning_rate": 5.828890581365829e-06, |
| "loss": 0.4037, |
| "step": 17900 |
| }, |
| { |
| "epoch": 4.456605175188808, |
| "grad_norm": 1.2728139162063599, |
| "learning_rate": 5.575019040365576e-06, |
| "loss": 0.3981, |
| "step": 18000 |
| }, |
| { |
| "epoch": 4.456605175188808, |
| "eval_loss": 0.3691825568675995, |
| "eval_runtime": 300.7735, |
| "eval_samples_per_second": 47.74, |
| "eval_steps_per_second": 2.986, |
| "step": 18000 |
| }, |
| { |
| "epoch": 4.481366844125294, |
| "grad_norm": 0.9797173738479614, |
| "learning_rate": 5.321147499365321e-06, |
| "loss": 0.3858, |
| "step": 18100 |
| }, |
| { |
| "epoch": 4.50612851306178, |
| "grad_norm": 1.1960067749023438, |
| "learning_rate": 5.067275958365068e-06, |
| "loss": 0.4028, |
| "step": 18200 |
| }, |
| { |
| "epoch": 4.5308901819982665, |
| "grad_norm": 1.067478895187378, |
| "learning_rate": 4.8134044173648135e-06, |
| "loss": 0.4064, |
| "step": 18300 |
| }, |
| { |
| "epoch": 4.555651850934753, |
| "grad_norm": 1.0445499420166016, |
| "learning_rate": 4.55953287636456e-06, |
| "loss": 0.3965, |
| "step": 18400 |
| }, |
| { |
| "epoch": 4.5804135198712395, |
| "grad_norm": 1.035979986190796, |
| "learning_rate": 4.3056613353643065e-06, |
| "loss": 0.3909, |
| "step": 18500 |
| }, |
| { |
| "epoch": 4.5804135198712395, |
| "eval_loss": 0.3688410818576813, |
| "eval_runtime": 305.0552, |
| "eval_samples_per_second": 47.07, |
| "eval_steps_per_second": 2.944, |
| "step": 18500 |
| }, |
| { |
| "epoch": 4.605175188807726, |
| "grad_norm": 0.9728735685348511, |
| "learning_rate": 4.051789794364052e-06, |
| "loss": 0.3943, |
| "step": 18600 |
| }, |
| { |
| "epoch": 4.629936857744212, |
| "grad_norm": 1.086190938949585, |
| "learning_rate": 3.7979182533637982e-06, |
| "loss": 0.3992, |
| "step": 18700 |
| }, |
| { |
| "epoch": 4.654698526680698, |
| "grad_norm": 1.103594183921814, |
| "learning_rate": 3.544046712363544e-06, |
| "loss": 0.3891, |
| "step": 18800 |
| }, |
| { |
| "epoch": 4.679460195617184, |
| "grad_norm": 1.0151804685592651, |
| "learning_rate": 3.2901751713632904e-06, |
| "loss": 0.4009, |
| "step": 18900 |
| }, |
| { |
| "epoch": 4.704221864553671, |
| "grad_norm": 1.141107201576233, |
| "learning_rate": 3.0363036303630365e-06, |
| "loss": 0.4028, |
| "step": 19000 |
| }, |
| { |
| "epoch": 4.704221864553671, |
| "eval_loss": 0.36849796772003174, |
| "eval_runtime": 296.4027, |
| "eval_samples_per_second": 48.444, |
| "eval_steps_per_second": 3.03, |
| "step": 19000 |
| }, |
| { |
| "epoch": 4.728983533490157, |
| "grad_norm": 1.0555781126022339, |
| "learning_rate": 2.7824320893627826e-06, |
| "loss": 0.4033, |
| "step": 19100 |
| }, |
| { |
| "epoch": 4.753745202426644, |
| "grad_norm": 1.1756597757339478, |
| "learning_rate": 2.5285605483625287e-06, |
| "loss": 0.4022, |
| "step": 19200 |
| }, |
| { |
| "epoch": 4.77850687136313, |
| "grad_norm": 0.9200191497802734, |
| "learning_rate": 2.2746890073622748e-06, |
| "loss": 0.3987, |
| "step": 19300 |
| }, |
| { |
| "epoch": 4.803268540299616, |
| "grad_norm": 1.1391457319259644, |
| "learning_rate": 2.0208174663620213e-06, |
| "loss": 0.3961, |
| "step": 19400 |
| }, |
| { |
| "epoch": 4.828030209236102, |
| "grad_norm": 1.0987917184829712, |
| "learning_rate": 1.7669459253617672e-06, |
| "loss": 0.3903, |
| "step": 19500 |
| }, |
| { |
| "epoch": 4.828030209236102, |
| "eval_loss": 0.367659330368042, |
| "eval_runtime": 300.2959, |
| "eval_samples_per_second": 47.816, |
| "eval_steps_per_second": 2.99, |
| "step": 19500 |
| }, |
| { |
| "epoch": 4.852791878172589, |
| "grad_norm": 0.9229596257209778, |
| "learning_rate": 1.5130743843615132e-06, |
| "loss": 0.3976, |
| "step": 19600 |
| }, |
| { |
| "epoch": 4.877553547109075, |
| "grad_norm": 0.9962015151977539, |
| "learning_rate": 1.2592028433612593e-06, |
| "loss": 0.3957, |
| "step": 19700 |
| }, |
| { |
| "epoch": 4.902315216045562, |
| "grad_norm": 1.4311672449111938, |
| "learning_rate": 1.0053313023610054e-06, |
| "loss": 0.3918, |
| "step": 19800 |
| }, |
| { |
| "epoch": 4.927076884982048, |
| "grad_norm": 1.1852339506149292, |
| "learning_rate": 7.514597613607515e-07, |
| "loss": 0.3989, |
| "step": 19900 |
| }, |
| { |
| "epoch": 4.951838553918535, |
| "grad_norm": 1.072943091392517, |
| "learning_rate": 4.975882203604976e-07, |
| "loss": 0.393, |
| "step": 20000 |
| }, |
| { |
| "epoch": 4.951838553918535, |
| "eval_loss": 0.3671196699142456, |
| "eval_runtime": 304.303, |
| "eval_samples_per_second": 47.187, |
| "eval_steps_per_second": 2.951, |
| "step": 20000 |
| } |
| ], |
| "logging_steps": 100, |
| "max_steps": 20195, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 5, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 7.046592561946024e+21, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
