{ "best_metric": null, "best_model_checkpoint": null, "epoch": 1.0, "eval_steps": 500, "global_step": 2283, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0004380201489268506, "grad_norm": 244.0565657784503, "learning_rate": 8.733624454148472e-08, "loss": 8.7812, "step": 1 }, { "epoch": 0.002190100744634253, "grad_norm": 242.08745729404998, "learning_rate": 4.366812227074236e-07, "loss": 8.8047, "step": 5 }, { "epoch": 0.004380201489268506, "grad_norm": 215.31824760158125, "learning_rate": 8.733624454148472e-07, "loss": 8.6969, "step": 10 }, { "epoch": 0.006570302233902759, "grad_norm": 124.79925946857198, "learning_rate": 1.3100436681222709e-06, "loss": 8.3187, "step": 15 }, { "epoch": 0.008760402978537012, "grad_norm": 95.62100949931548, "learning_rate": 1.7467248908296944e-06, "loss": 7.6672, "step": 20 }, { "epoch": 0.010950503723171266, "grad_norm": 56.19522998010826, "learning_rate": 2.183406113537118e-06, "loss": 6.7922, "step": 25 }, { "epoch": 0.013140604467805518, "grad_norm": 34.7212601740852, "learning_rate": 2.6200873362445417e-06, "loss": 5.9031, "step": 30 }, { "epoch": 0.015330705212439772, "grad_norm": 30.849397382141074, "learning_rate": 3.0567685589519653e-06, "loss": 5.1156, "step": 35 }, { "epoch": 0.017520805957074025, "grad_norm": 16.184875412033424, "learning_rate": 3.493449781659389e-06, "loss": 3.9531, "step": 40 }, { "epoch": 0.01971090670170828, "grad_norm": 13.212043262995175, "learning_rate": 3.930131004366812e-06, "loss": 3.1414, "step": 45 }, { "epoch": 0.021901007446342532, "grad_norm": 6.575354808182119, "learning_rate": 4.366812227074236e-06, "loss": 2.5, "step": 50 }, { "epoch": 0.024091108190976786, "grad_norm": 2.5861843997481873, "learning_rate": 4.80349344978166e-06, "loss": 1.9785, "step": 55 }, { "epoch": 0.026281208935611037, "grad_norm": 1.566359722353574, "learning_rate": 5.2401746724890834e-06, "loss": 1.7488, "step": 60 }, { "epoch": 0.02847130968024529, "grad_norm": 0.9077919251278966, "learning_rate": 5.676855895196507e-06, "loss": 1.6184, "step": 65 }, { "epoch": 0.030661410424879545, "grad_norm": 0.6573333175178419, "learning_rate": 6.1135371179039305e-06, "loss": 1.5391, "step": 70 }, { "epoch": 0.0328515111695138, "grad_norm": 0.5238887296216804, "learning_rate": 6.550218340611354e-06, "loss": 1.4633, "step": 75 }, { "epoch": 0.03504161191414805, "grad_norm": 0.4821823564791243, "learning_rate": 6.986899563318778e-06, "loss": 1.4199, "step": 80 }, { "epoch": 0.03723171265878231, "grad_norm": 0.4129490577402294, "learning_rate": 7.423580786026201e-06, "loss": 1.4109, "step": 85 }, { "epoch": 0.03942181340341656, "grad_norm": 0.40472709691340175, "learning_rate": 7.860262008733624e-06, "loss": 1.4168, "step": 90 }, { "epoch": 0.04161191414805081, "grad_norm": 0.3808604144712055, "learning_rate": 8.296943231441049e-06, "loss": 1.3668, "step": 95 }, { "epoch": 0.043802014892685065, "grad_norm": 0.367625493325619, "learning_rate": 8.733624454148473e-06, "loss": 1.3066, "step": 100 }, { "epoch": 0.045992115637319315, "grad_norm": 0.359816415568165, "learning_rate": 9.170305676855896e-06, "loss": 1.3449, "step": 105 }, { "epoch": 0.04818221638195357, "grad_norm": 0.341837652413913, "learning_rate": 9.60698689956332e-06, "loss": 1.3273, "step": 110 }, { "epoch": 0.05037231712658782, "grad_norm": 0.34301552589118167, "learning_rate": 1.0043668122270742e-05, "loss": 1.2949, "step": 115 }, { "epoch": 0.052562417871222074, "grad_norm": 0.3628435999185446, "learning_rate": 1.0480349344978167e-05, "loss": 1.2871, "step": 120 }, { "epoch": 0.05475251861585633, "grad_norm": 0.3679166427745723, "learning_rate": 1.0917030567685592e-05, "loss": 1.3207, "step": 125 }, { "epoch": 0.05694261936049058, "grad_norm": 0.34368277634691846, "learning_rate": 1.1353711790393014e-05, "loss": 1.2645, "step": 130 }, { "epoch": 0.05913272010512484, "grad_norm": 0.3551051401296533, "learning_rate": 1.179039301310044e-05, "loss": 1.2707, "step": 135 }, { "epoch": 0.06132282084975909, "grad_norm": 0.334086491935665, "learning_rate": 1.2227074235807861e-05, "loss": 1.2742, "step": 140 }, { "epoch": 0.06351292159439334, "grad_norm": 0.3344453192406718, "learning_rate": 1.2663755458515286e-05, "loss": 1.2441, "step": 145 }, { "epoch": 0.0657030223390276, "grad_norm": 0.3486113854746094, "learning_rate": 1.3100436681222708e-05, "loss": 1.2934, "step": 150 }, { "epoch": 0.06789312308366185, "grad_norm": 0.3450373622328735, "learning_rate": 1.3537117903930132e-05, "loss": 1.2473, "step": 155 }, { "epoch": 0.0700832238282961, "grad_norm": 0.3254863200637601, "learning_rate": 1.3973799126637555e-05, "loss": 1.2613, "step": 160 }, { "epoch": 0.07227332457293036, "grad_norm": 0.3206618735664889, "learning_rate": 1.4410480349344979e-05, "loss": 1.275, "step": 165 }, { "epoch": 0.07446342531756461, "grad_norm": 0.36155580225009337, "learning_rate": 1.4847161572052402e-05, "loss": 1.2379, "step": 170 }, { "epoch": 0.07665352606219886, "grad_norm": 0.331500878464258, "learning_rate": 1.5283842794759826e-05, "loss": 1.234, "step": 175 }, { "epoch": 0.07884362680683311, "grad_norm": 0.35558769100827337, "learning_rate": 1.5720524017467248e-05, "loss": 1.2641, "step": 180 }, { "epoch": 0.08103372755146737, "grad_norm": 0.3514292771304392, "learning_rate": 1.6157205240174673e-05, "loss": 1.2258, "step": 185 }, { "epoch": 0.08322382829610162, "grad_norm": 0.3158735252448049, "learning_rate": 1.6593886462882098e-05, "loss": 1.2414, "step": 190 }, { "epoch": 0.08541392904073587, "grad_norm": 0.3332987501140752, "learning_rate": 1.703056768558952e-05, "loss": 1.2238, "step": 195 }, { "epoch": 0.08760402978537013, "grad_norm": 0.3306118702879735, "learning_rate": 1.7467248908296945e-05, "loss": 1.2316, "step": 200 }, { "epoch": 0.08979413053000437, "grad_norm": 0.3189870404362557, "learning_rate": 1.7903930131004367e-05, "loss": 1.2355, "step": 205 }, { "epoch": 0.09198423127463863, "grad_norm": 0.3015408510885377, "learning_rate": 1.8340611353711792e-05, "loss": 1.2188, "step": 210 }, { "epoch": 0.09417433201927289, "grad_norm": 0.3227399112930752, "learning_rate": 1.8777292576419214e-05, "loss": 1.2164, "step": 215 }, { "epoch": 0.09636443276390715, "grad_norm": 0.3316376300779914, "learning_rate": 1.921397379912664e-05, "loss": 1.2457, "step": 220 }, { "epoch": 0.09855453350854139, "grad_norm": 0.31785017269226773, "learning_rate": 1.965065502183406e-05, "loss": 1.1949, "step": 225 }, { "epoch": 0.10074463425317565, "grad_norm": 0.3305460477093586, "learning_rate": 1.9999988303153612e-05, "loss": 1.2184, "step": 230 }, { "epoch": 0.1029347349978099, "grad_norm": 0.32274702495374813, "learning_rate": 1.9999578916403086e-05, "loss": 1.2242, "step": 235 }, { "epoch": 0.10512483574244415, "grad_norm": 0.3309888084620984, "learning_rate": 1.999858471469601e-05, "loss": 1.1996, "step": 240 }, { "epoch": 0.1073149364870784, "grad_norm": 0.31589160373633207, "learning_rate": 1.9997005756177228e-05, "loss": 1.1754, "step": 245 }, { "epoch": 0.10950503723171266, "grad_norm": 0.3245071336888696, "learning_rate": 1.9994842133190485e-05, "loss": 1.2059, "step": 250 }, { "epoch": 0.1116951379763469, "grad_norm": 0.34753890904189133, "learning_rate": 1.999209397227302e-05, "loss": 1.2012, "step": 255 }, { "epoch": 0.11388523872098116, "grad_norm": 0.30057443535443235, "learning_rate": 1.9988761434148164e-05, "loss": 1.2281, "step": 260 }, { "epoch": 0.11607533946561542, "grad_norm": 0.30036747933816504, "learning_rate": 1.998484471371593e-05, "loss": 1.1785, "step": 265 }, { "epoch": 0.11826544021024968, "grad_norm": 0.32539575218814926, "learning_rate": 1.9980344040041636e-05, "loss": 1.1742, "step": 270 }, { "epoch": 0.12045554095488392, "grad_norm": 0.31075948876414167, "learning_rate": 1.99752596763425e-05, "loss": 1.209, "step": 275 }, { "epoch": 0.12264564169951818, "grad_norm": 0.2948383024933128, "learning_rate": 1.9969591919972226e-05, "loss": 1.2059, "step": 280 }, { "epoch": 0.12483574244415244, "grad_norm": 0.30809860203285494, "learning_rate": 1.9963341102403652e-05, "loss": 1.1996, "step": 285 }, { "epoch": 0.12702584318878668, "grad_norm": 0.3063101893237704, "learning_rate": 1.995650758920932e-05, "loss": 1.2, "step": 290 }, { "epoch": 0.12921594393342092, "grad_norm": 0.29266235209581604, "learning_rate": 1.9949091780040143e-05, "loss": 1.173, "step": 295 }, { "epoch": 0.1314060446780552, "grad_norm": 0.3236695292638355, "learning_rate": 1.9941094108601985e-05, "loss": 1.1832, "step": 300 }, { "epoch": 0.13359614542268944, "grad_norm": 0.29386460049329405, "learning_rate": 1.9932515042630335e-05, "loss": 1.1746, "step": 305 }, { "epoch": 0.1357862461673237, "grad_norm": 0.3304096067847152, "learning_rate": 1.9923355083862933e-05, "loss": 1.2004, "step": 310 }, { "epoch": 0.13797634691195795, "grad_norm": 0.297618875850005, "learning_rate": 1.9913614768010418e-05, "loss": 1.1656, "step": 315 }, { "epoch": 0.1401664476565922, "grad_norm": 0.3453392768634244, "learning_rate": 1.9903294664725023e-05, "loss": 1.1473, "step": 320 }, { "epoch": 0.14235654840122647, "grad_norm": 0.2952934857480258, "learning_rate": 1.989239537756723e-05, "loss": 1.1898, "step": 325 }, { "epoch": 0.1445466491458607, "grad_norm": 0.3096490330878614, "learning_rate": 1.9880917543970503e-05, "loss": 1.1727, "step": 330 }, { "epoch": 0.14673674989049496, "grad_norm": 0.305522689793203, "learning_rate": 1.986886183520398e-05, "loss": 1.166, "step": 335 }, { "epoch": 0.14892685063512923, "grad_norm": 0.2977399891862773, "learning_rate": 1.985622895633323e-05, "loss": 1.1605, "step": 340 }, { "epoch": 0.15111695137976347, "grad_norm": 0.3080937705338333, "learning_rate": 1.9843019646179014e-05, "loss": 1.1785, "step": 345 }, { "epoch": 0.1533070521243977, "grad_norm": 0.28864764946025717, "learning_rate": 1.982923467727408e-05, "loss": 1.1797, "step": 350 }, { "epoch": 0.15549715286903198, "grad_norm": 0.29002073593801136, "learning_rate": 1.981487485581797e-05, "loss": 1.1676, "step": 355 }, { "epoch": 0.15768725361366623, "grad_norm": 0.3018457130707611, "learning_rate": 1.9799941021629886e-05, "loss": 1.1738, "step": 360 }, { "epoch": 0.15987735435830047, "grad_norm": 0.30507162972432783, "learning_rate": 1.9784434048099565e-05, "loss": 1.1668, "step": 365 }, { "epoch": 0.16206745510293474, "grad_norm": 0.3049773910908397, "learning_rate": 1.97683548421362e-05, "loss": 1.1781, "step": 370 }, { "epoch": 0.164257555847569, "grad_norm": 0.3024971125857499, "learning_rate": 1.9751704344115402e-05, "loss": 1.1625, "step": 375 }, { "epoch": 0.16644765659220323, "grad_norm": 0.28148210956054226, "learning_rate": 1.97344835278242e-05, "loss": 1.1687, "step": 380 }, { "epoch": 0.1686377573368375, "grad_norm": 0.2996144816775727, "learning_rate": 1.97166934004041e-05, "loss": 1.207, "step": 385 }, { "epoch": 0.17082785808147175, "grad_norm": 0.29532940992965984, "learning_rate": 1.9698335002292176e-05, "loss": 1.1848, "step": 390 }, { "epoch": 0.173017958826106, "grad_norm": 0.3001673093160351, "learning_rate": 1.967940940716021e-05, "loss": 1.1828, "step": 395 }, { "epoch": 0.17520805957074026, "grad_norm": 0.30610198280704054, "learning_rate": 1.9659917721851924e-05, "loss": 1.1867, "step": 400 }, { "epoch": 0.1773981603153745, "grad_norm": 0.2925881036239608, "learning_rate": 1.963986108631823e-05, "loss": 1.1418, "step": 405 }, { "epoch": 0.17958826106000875, "grad_norm": 0.29339092688050755, "learning_rate": 1.961924067355056e-05, "loss": 1.1637, "step": 410 }, { "epoch": 0.18177836180464302, "grad_norm": 0.30407476923887133, "learning_rate": 1.9598057689512277e-05, "loss": 1.1508, "step": 415 }, { "epoch": 0.18396846254927726, "grad_norm": 0.29998056902468595, "learning_rate": 1.957631337306814e-05, "loss": 1.1578, "step": 420 }, { "epoch": 0.18615856329391153, "grad_norm": 0.3025021503047764, "learning_rate": 1.9554008995911837e-05, "loss": 1.1812, "step": 425 }, { "epoch": 0.18834866403854578, "grad_norm": 0.2960918602914393, "learning_rate": 1.953114586249164e-05, "loss": 1.1793, "step": 430 }, { "epoch": 0.19053876478318002, "grad_norm": 0.3196259778914729, "learning_rate": 1.950772530993409e-05, "loss": 1.1738, "step": 435 }, { "epoch": 0.1927288655278143, "grad_norm": 0.2993685894942767, "learning_rate": 1.9483748707965803e-05, "loss": 1.1512, "step": 440 }, { "epoch": 0.19491896627244854, "grad_norm": 0.3002942784736228, "learning_rate": 1.945921745883337e-05, "loss": 1.1625, "step": 445 }, { "epoch": 0.19710906701708278, "grad_norm": 0.30887780802399506, "learning_rate": 1.9434132997221347e-05, "loss": 1.1719, "step": 450 }, { "epoch": 0.19929916776171705, "grad_norm": 0.29738335551869177, "learning_rate": 1.9408496790168337e-05, "loss": 1.1641, "step": 455 }, { "epoch": 0.2014892685063513, "grad_norm": 0.30233929664046716, "learning_rate": 1.9382310336981206e-05, "loss": 1.1512, "step": 460 }, { "epoch": 0.20367936925098554, "grad_norm": 0.29527032498064754, "learning_rate": 1.935557516914739e-05, "loss": 1.148, "step": 465 }, { "epoch": 0.2058694699956198, "grad_norm": 0.29787746244856167, "learning_rate": 1.932829285024533e-05, "loss": 1.1516, "step": 470 }, { "epoch": 0.20805957074025405, "grad_norm": 0.2913683096092213, "learning_rate": 1.9300464975853032e-05, "loss": 1.1344, "step": 475 }, { "epoch": 0.2102496714848883, "grad_norm": 0.27500340802613793, "learning_rate": 1.9272093173454735e-05, "loss": 1.1574, "step": 480 }, { "epoch": 0.21243977222952257, "grad_norm": 0.2812766184977934, "learning_rate": 1.9243179102345753e-05, "loss": 1.148, "step": 485 }, { "epoch": 0.2146298729741568, "grad_norm": 0.2865109750359857, "learning_rate": 1.9213724453535417e-05, "loss": 1.1578, "step": 490 }, { "epoch": 0.21681997371879105, "grad_norm": 0.29189523569878567, "learning_rate": 1.9183730949648173e-05, "loss": 1.1602, "step": 495 }, { "epoch": 0.21901007446342532, "grad_norm": 0.29979676151962115, "learning_rate": 1.9153200344822855e-05, "loss": 1.1355, "step": 500 }, { "epoch": 0.22120017520805957, "grad_norm": 0.300831896633153, "learning_rate": 1.912213442461009e-05, "loss": 1.1391, "step": 505 }, { "epoch": 0.2233902759526938, "grad_norm": 0.29049722290498076, "learning_rate": 1.9090535005867853e-05, "loss": 1.1727, "step": 510 }, { "epoch": 0.22558037669732808, "grad_norm": 0.3104171548245787, "learning_rate": 1.9058403936655235e-05, "loss": 1.1551, "step": 515 }, { "epoch": 0.22777047744196233, "grad_norm": 0.2944155570969255, "learning_rate": 1.9025743096124346e-05, "loss": 1.1527, "step": 520 }, { "epoch": 0.22996057818659657, "grad_norm": 0.3169970998158994, "learning_rate": 1.899255439441043e-05, "loss": 1.158, "step": 525 }, { "epoch": 0.23215067893123084, "grad_norm": 0.2842476129923102, "learning_rate": 1.8958839772520125e-05, "loss": 1.1758, "step": 530 }, { "epoch": 0.23434077967586509, "grad_norm": 0.2855513642633395, "learning_rate": 1.8924601202217977e-05, "loss": 1.1357, "step": 535 }, { "epoch": 0.23653088042049936, "grad_norm": 0.2848004802653552, "learning_rate": 1.888984068591111e-05, "loss": 1.1391, "step": 540 }, { "epoch": 0.2387209811651336, "grad_norm": 0.28099993296693176, "learning_rate": 1.8854560256532098e-05, "loss": 1.1355, "step": 545 }, { "epoch": 0.24091108190976784, "grad_norm": 0.3070333803041777, "learning_rate": 1.8818761977420114e-05, "loss": 1.143, "step": 550 }, { "epoch": 0.24310118265440211, "grad_norm": 0.28305196192266907, "learning_rate": 1.878244794220022e-05, "loss": 1.1625, "step": 555 }, { "epoch": 0.24529128339903636, "grad_norm": 0.29533684816936556, "learning_rate": 1.874562027466093e-05, "loss": 1.1695, "step": 560 }, { "epoch": 0.2474813841436706, "grad_norm": 0.29819831907768873, "learning_rate": 1.8708281128630023e-05, "loss": 1.1469, "step": 565 }, { "epoch": 0.24967148488830487, "grad_norm": 0.28827778580342983, "learning_rate": 1.8670432687848562e-05, "loss": 1.149, "step": 570 }, { "epoch": 0.2518615856329391, "grad_norm": 0.2865593620968661, "learning_rate": 1.8632077165843174e-05, "loss": 1.1246, "step": 575 }, { "epoch": 0.25405168637757336, "grad_norm": 0.2873333172793282, "learning_rate": 1.8593216805796612e-05, "loss": 1.1402, "step": 580 }, { "epoch": 0.25624178712220763, "grad_norm": 0.28696704010138063, "learning_rate": 1.8553853880416555e-05, "loss": 1.1293, "step": 585 }, { "epoch": 0.25843188786684185, "grad_norm": 0.27933859864997074, "learning_rate": 1.8513990691802686e-05, "loss": 1.1691, "step": 590 }, { "epoch": 0.2606219886114761, "grad_norm": 0.2870969603657859, "learning_rate": 1.8473629571312073e-05, "loss": 1.1617, "step": 595 }, { "epoch": 0.2628120893561104, "grad_norm": 0.2843186093708674, "learning_rate": 1.8432772879422797e-05, "loss": 1.1355, "step": 600 }, { "epoch": 0.26500219010074466, "grad_norm": 0.31588736128898504, "learning_rate": 1.8391423005595928e-05, "loss": 1.1359, "step": 605 }, { "epoch": 0.2671922908453789, "grad_norm": 0.29315028625446876, "learning_rate": 1.8349582368135764e-05, "loss": 1.1551, "step": 610 }, { "epoch": 0.26938239159001315, "grad_norm": 0.2882074502213313, "learning_rate": 1.8307253414048395e-05, "loss": 1.1363, "step": 615 }, { "epoch": 0.2715724923346474, "grad_norm": 0.2932578089430528, "learning_rate": 1.8264438618898617e-05, "loss": 1.1455, "step": 620 }, { "epoch": 0.27376259307928164, "grad_norm": 0.27801162707284016, "learning_rate": 1.8221140486665125e-05, "loss": 1.1621, "step": 625 }, { "epoch": 0.2759526938239159, "grad_norm": 0.29375240288760845, "learning_rate": 1.8177361549594068e-05, "loss": 1.1492, "step": 630 }, { "epoch": 0.2781427945685502, "grad_norm": 0.276903179408844, "learning_rate": 1.813310436805099e-05, "loss": 1.1445, "step": 635 }, { "epoch": 0.2803328953131844, "grad_norm": 0.27955633362670035, "learning_rate": 1.8088371530371044e-05, "loss": 1.1531, "step": 640 }, { "epoch": 0.28252299605781866, "grad_norm": 0.2799230772005429, "learning_rate": 1.804316565270765e-05, "loss": 1.1512, "step": 645 }, { "epoch": 0.28471309680245294, "grad_norm": 0.27521037714056357, "learning_rate": 1.7997489378879465e-05, "loss": 1.1438, "step": 650 }, { "epoch": 0.28690319754708715, "grad_norm": 0.29389670124687384, "learning_rate": 1.7951345380215795e-05, "loss": 1.152, "step": 655 }, { "epoch": 0.2890932982917214, "grad_norm": 0.28364632855748595, "learning_rate": 1.7904736355400324e-05, "loss": 1.1576, "step": 660 }, { "epoch": 0.2912833990363557, "grad_norm": 0.2767305609560192, "learning_rate": 1.785766503031332e-05, "loss": 1.1414, "step": 665 }, { "epoch": 0.2934734997809899, "grad_norm": 0.28006968803895216, "learning_rate": 1.78101341578722e-05, "loss": 1.1367, "step": 670 }, { "epoch": 0.2956636005256242, "grad_norm": 0.2938177814391214, "learning_rate": 1.7762146517870526e-05, "loss": 1.132, "step": 675 }, { "epoch": 0.29785370127025845, "grad_norm": 0.2763427209869464, "learning_rate": 1.7713704916815432e-05, "loss": 1.1461, "step": 680 }, { "epoch": 0.30004380201489267, "grad_norm": 0.3006381369806697, "learning_rate": 1.76648121877635e-05, "loss": 1.134, "step": 685 }, { "epoch": 0.30223390275952694, "grad_norm": 0.2910687567455647, "learning_rate": 1.7615471190155056e-05, "loss": 1.1176, "step": 690 }, { "epoch": 0.3044240035041612, "grad_norm": 0.2678904446910071, "learning_rate": 1.7565684809646946e-05, "loss": 1.1223, "step": 695 }, { "epoch": 0.3066141042487954, "grad_norm": 0.2753813506939354, "learning_rate": 1.7515455957943772e-05, "loss": 1.1574, "step": 700 }, { "epoch": 0.3088042049934297, "grad_norm": 0.28669942485252364, "learning_rate": 1.746478757262761e-05, "loss": 1.1496, "step": 705 }, { "epoch": 0.31099430573806397, "grad_norm": 0.2843980836766018, "learning_rate": 1.7413682616986185e-05, "loss": 1.1363, "step": 710 }, { "epoch": 0.3131844064826982, "grad_norm": 0.2808223481563682, "learning_rate": 1.73621440798396e-05, "loss": 1.1305, "step": 715 }, { "epoch": 0.31537450722733246, "grad_norm": 0.2922348240666733, "learning_rate": 1.7310174975365508e-05, "loss": 1.1252, "step": 720 }, { "epoch": 0.31756460797196673, "grad_norm": 0.28067686922560126, "learning_rate": 1.7257778342922853e-05, "loss": 1.1348, "step": 725 }, { "epoch": 0.31975470871660094, "grad_norm": 0.2945526878670907, "learning_rate": 1.7204957246874103e-05, "loss": 1.1527, "step": 730 }, { "epoch": 0.3219448094612352, "grad_norm": 0.276941149759669, "learning_rate": 1.7151714776406034e-05, "loss": 1.1102, "step": 735 }, { "epoch": 0.3241349102058695, "grad_norm": 0.289439650523264, "learning_rate": 1.7098054045349076e-05, "loss": 1.125, "step": 740 }, { "epoch": 0.3263250109505037, "grad_norm": 0.2801285692740154, "learning_rate": 1.7043978191995177e-05, "loss": 1.127, "step": 745 }, { "epoch": 0.328515111695138, "grad_norm": 0.3350495049060471, "learning_rate": 1.6989490378914304e-05, "loss": 1.1227, "step": 750 }, { "epoch": 0.33070521243977224, "grad_norm": 0.2808592002786063, "learning_rate": 1.6934593792769435e-05, "loss": 1.152, "step": 755 }, { "epoch": 0.33289531318440646, "grad_norm": 0.27808585554127363, "learning_rate": 1.6879291644130235e-05, "loss": 1.1309, "step": 760 }, { "epoch": 0.33508541392904073, "grad_norm": 0.27069745729859374, "learning_rate": 1.682358716728525e-05, "loss": 1.1416, "step": 765 }, { "epoch": 0.337275514673675, "grad_norm": 0.29843211507422185, "learning_rate": 1.676748362005279e-05, "loss": 1.1449, "step": 770 }, { "epoch": 0.3394656154183092, "grad_norm": 0.28556892181225596, "learning_rate": 1.671098428359037e-05, "loss": 1.143, "step": 775 }, { "epoch": 0.3416557161629435, "grad_norm": 0.30065398619371225, "learning_rate": 1.6654092462202828e-05, "loss": 1.1227, "step": 780 }, { "epoch": 0.34384581690757776, "grad_norm": 0.2681674526100603, "learning_rate": 1.6596811483149077e-05, "loss": 1.1273, "step": 785 }, { "epoch": 0.346035917652212, "grad_norm": 0.29230660631987243, "learning_rate": 1.6539144696447504e-05, "loss": 1.1277, "step": 790 }, { "epoch": 0.34822601839684625, "grad_norm": 0.27613144345526425, "learning_rate": 1.6481095474680062e-05, "loss": 1.1285, "step": 795 }, { "epoch": 0.3504161191414805, "grad_norm": 0.28721223205254864, "learning_rate": 1.642266721279502e-05, "loss": 1.1215, "step": 800 }, { "epoch": 0.35260621988611474, "grad_norm": 0.2839922006300779, "learning_rate": 1.6363863327908405e-05, "loss": 1.1219, "step": 805 }, { "epoch": 0.354796320630749, "grad_norm": 0.2721319526014653, "learning_rate": 1.630468725910417e-05, "loss": 1.1297, "step": 810 }, { "epoch": 0.3569864213753833, "grad_norm": 0.2666725910793476, "learning_rate": 1.6245142467233067e-05, "loss": 1.1525, "step": 815 }, { "epoch": 0.3591765221200175, "grad_norm": 0.2749768948580958, "learning_rate": 1.618523243471021e-05, "loss": 1.1252, "step": 820 }, { "epoch": 0.36136662286465177, "grad_norm": 0.27001888357231557, "learning_rate": 1.6124960665311447e-05, "loss": 1.1227, "step": 825 }, { "epoch": 0.36355672360928604, "grad_norm": 0.27097536893189883, "learning_rate": 1.606433068396843e-05, "loss": 1.1273, "step": 830 }, { "epoch": 0.3657468243539203, "grad_norm": 0.28488649062206617, "learning_rate": 1.6003346036562457e-05, "loss": 1.1186, "step": 835 }, { "epoch": 0.3679369250985545, "grad_norm": 0.27688500142196154, "learning_rate": 1.5942010289717108e-05, "loss": 1.1402, "step": 840 }, { "epoch": 0.3701270258431888, "grad_norm": 0.2674674925612205, "learning_rate": 1.588032703058964e-05, "loss": 1.0869, "step": 845 }, { "epoch": 0.37231712658782307, "grad_norm": 0.2856317902597983, "learning_rate": 1.5818299866661216e-05, "loss": 1.1398, "step": 850 }, { "epoch": 0.3745072273324573, "grad_norm": 0.27673240509708347, "learning_rate": 1.5755932425525907e-05, "loss": 1.1215, "step": 855 }, { "epoch": 0.37669732807709155, "grad_norm": 0.2736444678975509, "learning_rate": 1.569322835467853e-05, "loss": 1.1176, "step": 860 }, { "epoch": 0.3788874288217258, "grad_norm": 0.2768113382591734, "learning_rate": 1.563019132130136e-05, "loss": 1.1383, "step": 865 }, { "epoch": 0.38107752956636004, "grad_norm": 0.28162020446683744, "learning_rate": 1.5566825012049623e-05, "loss": 1.1363, "step": 870 }, { "epoch": 0.3832676303109943, "grad_norm": 0.27091660063236284, "learning_rate": 1.5503133132835916e-05, "loss": 1.1215, "step": 875 }, { "epoch": 0.3854577310556286, "grad_norm": 0.2666248763577975, "learning_rate": 1.5439119408613442e-05, "loss": 1.1254, "step": 880 }, { "epoch": 0.3876478318002628, "grad_norm": 0.2703004250271796, "learning_rate": 1.5374787583158188e-05, "loss": 1.1582, "step": 885 }, { "epoch": 0.38983793254489707, "grad_norm": 0.28795897475828547, "learning_rate": 1.531014141884994e-05, "loss": 1.1301, "step": 890 }, { "epoch": 0.39202803328953134, "grad_norm": 0.26937126154119884, "learning_rate": 1.5245184696452286e-05, "loss": 1.0959, "step": 895 }, { "epoch": 0.39421813403416556, "grad_norm": 0.2708023087895912, "learning_rate": 1.5179921214891469e-05, "loss": 1.1313, "step": 900 }, { "epoch": 0.39640823477879983, "grad_norm": 0.2851242116128433, "learning_rate": 1.5114354791034225e-05, "loss": 1.1316, "step": 905 }, { "epoch": 0.3985983355234341, "grad_norm": 0.270999449215019, "learning_rate": 1.5048489259464552e-05, "loss": 1.1297, "step": 910 }, { "epoch": 0.4007884362680683, "grad_norm": 0.2815986051423743, "learning_rate": 1.4982328472259453e-05, "loss": 1.1414, "step": 915 }, { "epoch": 0.4029785370127026, "grad_norm": 0.25822461525801005, "learning_rate": 1.4915876298763654e-05, "loss": 1.1287, "step": 920 }, { "epoch": 0.40516863775733686, "grad_norm": 0.2747332123131356, "learning_rate": 1.4849136625363297e-05, "loss": 1.1141, "step": 925 }, { "epoch": 0.4073587385019711, "grad_norm": 0.2712357004324246, "learning_rate": 1.4782113355258656e-05, "loss": 1.1074, "step": 930 }, { "epoch": 0.40954883924660535, "grad_norm": 0.27085881871204187, "learning_rate": 1.471481040823587e-05, "loss": 1.1105, "step": 935 }, { "epoch": 0.4117389399912396, "grad_norm": 0.27599882086276023, "learning_rate": 1.4647231720437687e-05, "loss": 1.123, "step": 940 }, { "epoch": 0.41392904073587383, "grad_norm": 0.27922116769860744, "learning_rate": 1.4579381244133265e-05, "loss": 1.1469, "step": 945 }, { "epoch": 0.4161191414805081, "grad_norm": 0.2735506939973002, "learning_rate": 1.4511262947487037e-05, "loss": 1.134, "step": 950 }, { "epoch": 0.4183092422251424, "grad_norm": 0.26886344993062933, "learning_rate": 1.444288081432662e-05, "loss": 1.1246, "step": 955 }, { "epoch": 0.4204993429697766, "grad_norm": 0.26964142533259994, "learning_rate": 1.4374238843909845e-05, "loss": 1.1275, "step": 960 }, { "epoch": 0.42268944371441086, "grad_norm": 0.2745245268675833, "learning_rate": 1.4305341050690845e-05, "loss": 1.1457, "step": 965 }, { "epoch": 0.42487954445904513, "grad_norm": 0.27343512900772715, "learning_rate": 1.4236191464085286e-05, "loss": 1.1109, "step": 970 }, { "epoch": 0.42706964520367935, "grad_norm": 0.2743571452940947, "learning_rate": 1.4166794128234705e-05, "loss": 1.1187, "step": 975 }, { "epoch": 0.4292597459483136, "grad_norm": 0.26544274644395, "learning_rate": 1.4097153101770008e-05, "loss": 1.1469, "step": 980 }, { "epoch": 0.4314498466929479, "grad_norm": 0.5158719980721467, "learning_rate": 1.4027272457574082e-05, "loss": 1.125, "step": 985 }, { "epoch": 0.4336399474375821, "grad_norm": 0.27681551273825566, "learning_rate": 1.3957156282543605e-05, "loss": 1.1363, "step": 990 }, { "epoch": 0.4358300481822164, "grad_norm": 0.27949169274878094, "learning_rate": 1.388680867735004e-05, "loss": 1.1254, "step": 995 }, { "epoch": 0.43802014892685065, "grad_norm": 0.2693597774135224, "learning_rate": 1.381623375619979e-05, "loss": 1.1104, "step": 1000 }, { "epoch": 0.44021024967148487, "grad_norm": 0.27336241345507317, "learning_rate": 1.3745435646593613e-05, "loss": 1.1346, "step": 1005 }, { "epoch": 0.44240035041611914, "grad_norm": 0.2697587637867333, "learning_rate": 1.3674418489085192e-05, "loss": 1.1313, "step": 1010 }, { "epoch": 0.4445904511607534, "grad_norm": 0.2637933472764974, "learning_rate": 1.360318643703901e-05, "loss": 1.1174, "step": 1015 }, { "epoch": 0.4467805519053876, "grad_norm": 0.2625274872058839, "learning_rate": 1.3531743656387426e-05, "loss": 1.1314, "step": 1020 }, { "epoch": 0.4489706526500219, "grad_norm": 0.2612762476528872, "learning_rate": 1.346009432538705e-05, "loss": 1.1205, "step": 1025 }, { "epoch": 0.45116075339465617, "grad_norm": 0.2804760409295694, "learning_rate": 1.3388242634374367e-05, "loss": 1.1547, "step": 1030 }, { "epoch": 0.4533508541392904, "grad_norm": 0.2730844934530705, "learning_rate": 1.331619278552068e-05, "loss": 1.1301, "step": 1035 }, { "epoch": 0.45554095488392465, "grad_norm": 0.2761820674316818, "learning_rate": 1.3243948992586347e-05, "loss": 1.1383, "step": 1040 }, { "epoch": 0.4577310556285589, "grad_norm": 0.2687484002119245, "learning_rate": 1.3171515480674342e-05, "loss": 1.1248, "step": 1045 }, { "epoch": 0.45992115637319314, "grad_norm": 0.27893259508437857, "learning_rate": 1.309889648598316e-05, "loss": 1.1535, "step": 1050 }, { "epoch": 0.4621112571178274, "grad_norm": 0.2741964520386731, "learning_rate": 1.3026096255559055e-05, "loss": 1.1066, "step": 1055 }, { "epoch": 0.4643013578624617, "grad_norm": 0.2766533566738994, "learning_rate": 1.295311904704767e-05, "loss": 1.1641, "step": 1060 }, { "epoch": 0.4664914586070959, "grad_norm": 0.2715162801769272, "learning_rate": 1.2879969128445025e-05, "loss": 1.125, "step": 1065 }, { "epoch": 0.46868155935173017, "grad_norm": 0.26726252131908934, "learning_rate": 1.2806650777847913e-05, "loss": 1.116, "step": 1070 }, { "epoch": 0.47087166009636444, "grad_norm": 0.2840924656915755, "learning_rate": 1.2733168283203692e-05, "loss": 1.1318, "step": 1075 }, { "epoch": 0.4730617608409987, "grad_norm": 0.26702580899914813, "learning_rate": 1.265952594205952e-05, "loss": 1.1156, "step": 1080 }, { "epoch": 0.47525186158563293, "grad_norm": 0.2773818319183054, "learning_rate": 1.2585728061311003e-05, "loss": 1.1184, "step": 1085 }, { "epoch": 0.4774419623302672, "grad_norm": 0.27175516307591485, "learning_rate": 1.2511778956950325e-05, "loss": 1.1418, "step": 1090 }, { "epoch": 0.47963206307490147, "grad_norm": 0.2689155932559786, "learning_rate": 1.243768295381382e-05, "loss": 1.1006, "step": 1095 }, { "epoch": 0.4818221638195357, "grad_norm": 0.26134780287986276, "learning_rate": 1.2363444385329052e-05, "loss": 1.108, "step": 1100 }, { "epoch": 0.48401226456416996, "grad_norm": 0.2742997540168624, "learning_rate": 1.2289067593261358e-05, "loss": 1.1141, "step": 1105 }, { "epoch": 0.48620236530880423, "grad_norm": 0.29141512596729113, "learning_rate": 1.2214556927459955e-05, "loss": 1.1176, "step": 1110 }, { "epoch": 0.48839246605343845, "grad_norm": 0.27353849576189837, "learning_rate": 1.2139916745603509e-05, "loss": 1.1258, "step": 1115 }, { "epoch": 0.4905825667980727, "grad_norm": 0.27107693520298354, "learning_rate": 1.2065151412945308e-05, "loss": 1.1098, "step": 1120 }, { "epoch": 0.492772667542707, "grad_norm": 0.2819238585953994, "learning_rate": 1.1990265302057948e-05, "loss": 1.1225, "step": 1125 }, { "epoch": 0.4949627682873412, "grad_norm": 0.266552343582286, "learning_rate": 1.191526279257762e-05, "loss": 1.1016, "step": 1130 }, { "epoch": 0.4971528690319755, "grad_norm": 0.278057928098842, "learning_rate": 1.1840148270947962e-05, "loss": 1.1252, "step": 1135 }, { "epoch": 0.49934296977660975, "grad_norm": 0.2936883558777508, "learning_rate": 1.1764926130163525e-05, "loss": 1.1359, "step": 1140 }, { "epoch": 0.501533070521244, "grad_norm": 0.2834365935036193, "learning_rate": 1.1689600769512855e-05, "loss": 1.0994, "step": 1145 }, { "epoch": 0.5037231712658782, "grad_norm": 0.274648980748947, "learning_rate": 1.1614176594321202e-05, "loss": 1.092, "step": 1150 }, { "epoch": 0.5059132720105125, "grad_norm": 0.28409682473235875, "learning_rate": 1.1538658015692892e-05, "loss": 1.1346, "step": 1155 }, { "epoch": 0.5081033727551467, "grad_norm": 0.2850776782098923, "learning_rate": 1.146304945025332e-05, "loss": 1.1227, "step": 1160 }, { "epoch": 0.5102934734997809, "grad_norm": 0.2610428092893358, "learning_rate": 1.1387355319890685e-05, "loss": 1.0969, "step": 1165 }, { "epoch": 0.5124835742444153, "grad_norm": 0.2740958199191816, "learning_rate": 1.1311580051497344e-05, "loss": 1.1246, "step": 1170 }, { "epoch": 0.5146736749890495, "grad_norm": 0.2848288147278702, "learning_rate": 1.123572807671094e-05, "loss": 1.1109, "step": 1175 }, { "epoch": 0.5168637757336837, "grad_norm": 0.26817858926421695, "learning_rate": 1.1159803831655206e-05, "loss": 1.1273, "step": 1180 }, { "epoch": 0.519053876478318, "grad_norm": 0.2697805969038893, "learning_rate": 1.1083811756680523e-05, "loss": 1.1289, "step": 1185 }, { "epoch": 0.5212439772229522, "grad_norm": 0.2705343306376679, "learning_rate": 1.1007756296104237e-05, "loss": 1.1469, "step": 1190 }, { "epoch": 0.5234340779675866, "grad_norm": 0.27282726875245455, "learning_rate": 1.0931641897950733e-05, "loss": 1.1332, "step": 1195 }, { "epoch": 0.5256241787122208, "grad_norm": 0.28059459041359747, "learning_rate": 1.08554730136913e-05, "loss": 1.0916, "step": 1200 }, { "epoch": 0.527814279456855, "grad_norm": 0.2638181805357147, "learning_rate": 1.0779254097983788e-05, "loss": 1.1057, "step": 1205 }, { "epoch": 0.5300043802014893, "grad_norm": 0.26522994514380227, "learning_rate": 1.0702989608412096e-05, "loss": 1.1027, "step": 1210 }, { "epoch": 0.5321944809461235, "grad_norm": 0.25855768118273403, "learning_rate": 1.0626684005225443e-05, "loss": 1.1332, "step": 1215 }, { "epoch": 0.5343845816907578, "grad_norm": 0.27413179764811996, "learning_rate": 1.0550341751077553e-05, "loss": 1.1176, "step": 1220 }, { "epoch": 0.5365746824353921, "grad_norm": 0.2642903693875254, "learning_rate": 1.0473967310765629e-05, "loss": 1.0857, "step": 1225 }, { "epoch": 0.5387647831800263, "grad_norm": 0.2628203067700955, "learning_rate": 1.039756515096926e-05, "loss": 1.1195, "step": 1230 }, { "epoch": 0.5409548839246605, "grad_norm": 0.2783963215365502, "learning_rate": 1.0321139739989167e-05, "loss": 1.1215, "step": 1235 }, { "epoch": 0.5431449846692948, "grad_norm": 0.2772449600445937, "learning_rate": 1.0244695547485912e-05, "loss": 1.1037, "step": 1240 }, { "epoch": 0.545335085413929, "grad_norm": 0.2660438451116181, "learning_rate": 1.0168237044218452e-05, "loss": 1.1262, "step": 1245 }, { "epoch": 0.5475251861585633, "grad_norm": 0.2598928720700204, "learning_rate": 1.0091768701782714e-05, "loss": 1.1246, "step": 1250 }, { "epoch": 0.5497152869031976, "grad_norm": 0.2777074874692869, "learning_rate": 1.0015294992350044e-05, "loss": 1.1055, "step": 1255 }, { "epoch": 0.5519053876478318, "grad_norm": 0.28449089911369874, "learning_rate": 9.93882038840568e-06, "loss": 1.1223, "step": 1260 }, { "epoch": 0.554095488392466, "grad_norm": 0.2768874782485583, "learning_rate": 9.862349362487172e-06, "loss": 1.0961, "step": 1265 }, { "epoch": 0.5562855891371004, "grad_norm": 0.26460753865275577, "learning_rate": 9.785886386922806e-06, "loss": 1.1076, "step": 1270 }, { "epoch": 0.5584756898817346, "grad_norm": 0.28161562628451337, "learning_rate": 9.709435933570068e-06, "loss": 1.1029, "step": 1275 }, { "epoch": 0.5606657906263688, "grad_norm": 0.2563062588428807, "learning_rate": 9.633002473554077e-06, "loss": 1.1096, "step": 1280 }, { "epoch": 0.5628558913710031, "grad_norm": 0.26175322953452584, "learning_rate": 9.556590477006123e-06, "loss": 1.1229, "step": 1285 }, { "epoch": 0.5650459921156373, "grad_norm": 0.26468057620238034, "learning_rate": 9.480204412802236e-06, "loss": 1.0994, "step": 1290 }, { "epoch": 0.5672360928602715, "grad_norm": 0.25809069797603174, "learning_rate": 9.403848748301802e-06, "loss": 1.1059, "step": 1295 }, { "epoch": 0.5694261936049059, "grad_norm": 0.27252102620530055, "learning_rate": 9.327527949086327e-06, "loss": 1.1092, "step": 1300 }, { "epoch": 0.5716162943495401, "grad_norm": 0.2715402906362093, "learning_rate": 9.251246478698242e-06, "loss": 1.1367, "step": 1305 }, { "epoch": 0.5738063950941743, "grad_norm": 0.26828019230229255, "learning_rate": 9.175008798379893e-06, "loss": 1.1043, "step": 1310 }, { "epoch": 0.5759964958388086, "grad_norm": 0.2770878196295294, "learning_rate": 9.098819366812594e-06, "loss": 1.1213, "step": 1315 }, { "epoch": 0.5781865965834428, "grad_norm": 0.281651051703252, "learning_rate": 9.022682639855883e-06, "loss": 1.1367, "step": 1320 }, { "epoch": 0.5803766973280771, "grad_norm": 0.27314753294139044, "learning_rate": 8.946603070286926e-06, "loss": 1.107, "step": 1325 }, { "epoch": 0.5825667980727114, "grad_norm": 0.26226614181355684, "learning_rate": 8.870585107540101e-06, "loss": 1.1281, "step": 1330 }, { "epoch": 0.5847568988173456, "grad_norm": 0.27293558156801573, "learning_rate": 8.79463319744677e-06, "loss": 1.0809, "step": 1335 }, { "epoch": 0.5869469995619798, "grad_norm": 0.26602352956316966, "learning_rate": 8.718751781975284e-06, "loss": 1.1385, "step": 1340 }, { "epoch": 0.5891371003066141, "grad_norm": 0.2746959499141311, "learning_rate": 8.642945298971168e-06, "loss": 1.1172, "step": 1345 }, { "epoch": 0.5913272010512484, "grad_norm": 0.2677554902377095, "learning_rate": 8.56721818189763e-06, "loss": 1.1133, "step": 1350 }, { "epoch": 0.5935173017958826, "grad_norm": 0.2662798900188826, "learning_rate": 8.491574859576222e-06, "loss": 1.1104, "step": 1355 }, { "epoch": 0.5957074025405169, "grad_norm": 0.26469719917634077, "learning_rate": 8.416019755927851e-06, "loss": 1.1086, "step": 1360 }, { "epoch": 0.5978975032851511, "grad_norm": 0.26386029178727227, "learning_rate": 8.340557289714055e-06, "loss": 1.1168, "step": 1365 }, { "epoch": 0.6000876040297853, "grad_norm": 0.253515604893805, "learning_rate": 8.26519187427856e-06, "loss": 1.1187, "step": 1370 }, { "epoch": 0.6022777047744197, "grad_norm": 0.277605351754751, "learning_rate": 8.189927917289182e-06, "loss": 1.1059, "step": 1375 }, { "epoch": 0.6044678055190539, "grad_norm": 0.26442216190859963, "learning_rate": 8.114769820480039e-06, "loss": 1.1176, "step": 1380 }, { "epoch": 0.6066579062636881, "grad_norm": 0.2734826868231617, "learning_rate": 8.03972197939414e-06, "loss": 1.1215, "step": 1385 }, { "epoch": 0.6088480070083224, "grad_norm": 0.2663060487289671, "learning_rate": 7.964788783126294e-06, "loss": 1.1037, "step": 1390 }, { "epoch": 0.6110381077529566, "grad_norm": 0.26118107033447696, "learning_rate": 7.889974614066425e-06, "loss": 1.0967, "step": 1395 }, { "epoch": 0.6132282084975909, "grad_norm": 0.27155741223634616, "learning_rate": 7.815283847643277e-06, "loss": 1.1203, "step": 1400 }, { "epoch": 0.6154183092422252, "grad_norm": 0.27035981345201915, "learning_rate": 7.740720852068524e-06, "loss": 1.1428, "step": 1405 }, { "epoch": 0.6176084099868594, "grad_norm": 0.2683573304766547, "learning_rate": 7.66628998808129e-06, "loss": 1.1301, "step": 1410 }, { "epoch": 0.6197985107314936, "grad_norm": 0.26324766469257666, "learning_rate": 7.591995608693118e-06, "loss": 1.1115, "step": 1415 }, { "epoch": 0.6219886114761279, "grad_norm": 0.26863159797075176, "learning_rate": 7.5178420589334025e-06, "loss": 1.1055, "step": 1420 }, { "epoch": 0.6241787122207622, "grad_norm": 0.25941294580030216, "learning_rate": 7.443833675595254e-06, "loss": 1.1293, "step": 1425 }, { "epoch": 0.6263688129653964, "grad_norm": 0.2623305114567609, "learning_rate": 7.369974786981879e-06, "loss": 1.0961, "step": 1430 }, { "epoch": 0.6285589137100307, "grad_norm": 0.2857793789171064, "learning_rate": 7.296269712653436e-06, "loss": 1.1051, "step": 1435 }, { "epoch": 0.6307490144546649, "grad_norm": 0.2738731727686292, "learning_rate": 7.222722763174428e-06, "loss": 1.0965, "step": 1440 }, { "epoch": 0.6329391151992991, "grad_norm": 0.2780751677609743, "learning_rate": 7.149338239861579e-06, "loss": 1.1125, "step": 1445 }, { "epoch": 0.6351292159439335, "grad_norm": 0.271978624523703, "learning_rate": 7.076120434532292e-06, "loss": 1.0795, "step": 1450 }, { "epoch": 0.6373193166885677, "grad_norm": 0.2889878149869347, "learning_rate": 7.003073629253638e-06, "loss": 1.1094, "step": 1455 }, { "epoch": 0.6395094174332019, "grad_norm": 0.26177418700227856, "learning_rate": 6.9302020960919405e-06, "loss": 1.132, "step": 1460 }, { "epoch": 0.6416995181778362, "grad_norm": 0.27487300616889226, "learning_rate": 6.857510096862901e-06, "loss": 1.1131, "step": 1465 }, { "epoch": 0.6438896189224704, "grad_norm": 0.2673004044565668, "learning_rate": 6.785001882882376e-06, "loss": 1.1047, "step": 1470 }, { "epoch": 0.6460797196671046, "grad_norm": 0.2637312152468036, "learning_rate": 6.712681694717723e-06, "loss": 1.1096, "step": 1475 }, { "epoch": 0.648269820411739, "grad_norm": 0.2630882968696908, "learning_rate": 6.640553761939822e-06, "loss": 1.0973, "step": 1480 }, { "epoch": 0.6504599211563732, "grad_norm": 0.2638392419100043, "learning_rate": 6.568622302875682e-06, "loss": 1.0982, "step": 1485 }, { "epoch": 0.6526500219010074, "grad_norm": 0.2626309470206596, "learning_rate": 6.496891524361757e-06, "loss": 1.1172, "step": 1490 }, { "epoch": 0.6548401226456417, "grad_norm": 0.265160449047166, "learning_rate": 6.42536562149791e-06, "loss": 1.1125, "step": 1495 }, { "epoch": 0.657030223390276, "grad_norm": 0.26619884121137627, "learning_rate": 6.354048777402061e-06, "loss": 1.1328, "step": 1500 }, { "epoch": 0.6592203241349102, "grad_norm": 0.2600814085765291, "learning_rate": 6.282945162965548e-06, "loss": 1.117, "step": 1505 }, { "epoch": 0.6614104248795445, "grad_norm": 0.272185670744957, "learning_rate": 6.212058936609189e-06, "loss": 1.1209, "step": 1510 }, { "epoch": 0.6636005256241787, "grad_norm": 0.2641333188928149, "learning_rate": 6.1413942440400994e-06, "loss": 1.1168, "step": 1515 }, { "epoch": 0.6657906263688129, "grad_norm": 0.26009676604807275, "learning_rate": 6.070955218009213e-06, "loss": 1.0936, "step": 1520 }, { "epoch": 0.6679807271134472, "grad_norm": 0.2615413153711293, "learning_rate": 6.0007459780695885e-06, "loss": 1.1061, "step": 1525 }, { "epoch": 0.6701708278580815, "grad_norm": 0.2892089912864181, "learning_rate": 5.93077063033549e-06, "loss": 1.1055, "step": 1530 }, { "epoch": 0.6723609286027157, "grad_norm": 0.2629578247792853, "learning_rate": 5.861033267242238e-06, "loss": 1.1146, "step": 1535 }, { "epoch": 0.67455102934735, "grad_norm": 0.2653857163412152, "learning_rate": 5.791537967306869e-06, "loss": 1.1107, "step": 1540 }, { "epoch": 0.6767411300919842, "grad_norm": 0.2641301458887951, "learning_rate": 5.722288794889603e-06, "loss": 1.0953, "step": 1545 }, { "epoch": 0.6789312308366184, "grad_norm": 0.2627115214160706, "learning_rate": 5.653289799956161e-06, "loss": 1.0957, "step": 1550 }, { "epoch": 0.6811213315812528, "grad_norm": 0.2744248525372843, "learning_rate": 5.584545017840886e-06, "loss": 1.0973, "step": 1555 }, { "epoch": 0.683311432325887, "grad_norm": 0.26271843375673565, "learning_rate": 5.516058469010741e-06, "loss": 1.1066, "step": 1560 }, { "epoch": 0.6855015330705212, "grad_norm": 0.28239608054669124, "learning_rate": 5.447834158830202e-06, "loss": 1.1457, "step": 1565 }, { "epoch": 0.6876916338151555, "grad_norm": 0.2682726187574874, "learning_rate": 5.379876077326979e-06, "loss": 1.0771, "step": 1570 }, { "epoch": 0.6898817345597897, "grad_norm": 0.2693944920009028, "learning_rate": 5.312188198958681e-06, "loss": 1.1191, "step": 1575 }, { "epoch": 0.692071835304424, "grad_norm": 0.27066235636281594, "learning_rate": 5.244774482380361e-06, "loss": 1.1191, "step": 1580 }, { "epoch": 0.6942619360490583, "grad_norm": 0.2607089341186109, "learning_rate": 5.177638870213008e-06, "loss": 1.0949, "step": 1585 }, { "epoch": 0.6964520367936925, "grad_norm": 0.26730049681200124, "learning_rate": 5.1107852888129715e-06, "loss": 1.159, "step": 1590 }, { "epoch": 0.6986421375383267, "grad_norm": 0.2561679895991625, "learning_rate": 5.04421764804232e-06, "loss": 1.0938, "step": 1595 }, { "epoch": 0.700832238282961, "grad_norm": 0.25827915348141745, "learning_rate": 4.977939841040175e-06, "loss": 1.1178, "step": 1600 }, { "epoch": 0.7030223390275953, "grad_norm": 0.2672625917790982, "learning_rate": 4.911955743995042e-06, "loss": 1.1195, "step": 1605 }, { "epoch": 0.7052124397722295, "grad_norm": 0.2712982534329863, "learning_rate": 4.846269215918106e-06, "loss": 1.1215, "step": 1610 }, { "epoch": 0.7074025405168638, "grad_norm": 0.2637027906298979, "learning_rate": 4.780884098417531e-06, "loss": 1.098, "step": 1615 }, { "epoch": 0.709592641261498, "grad_norm": 0.26810920883601624, "learning_rate": 4.7158042154738094e-06, "loss": 1.1176, "step": 1620 }, { "epoch": 0.7117827420061322, "grad_norm": 0.26084193501541225, "learning_rate": 4.6510333732160915e-06, "loss": 1.1262, "step": 1625 }, { "epoch": 0.7139728427507666, "grad_norm": 0.2700256165770299, "learning_rate": 4.5865753596996335e-06, "loss": 1.1148, "step": 1630 }, { "epoch": 0.7161629434954008, "grad_norm": 0.2639599226097337, "learning_rate": 4.522433944684197e-06, "loss": 1.1156, "step": 1635 }, { "epoch": 0.718353044240035, "grad_norm": 0.2597365152157971, "learning_rate": 4.45861287941363e-06, "loss": 1.0854, "step": 1640 }, { "epoch": 0.7205431449846693, "grad_norm": 0.26268213694795733, "learning_rate": 4.395115896396457e-06, "loss": 1.1258, "step": 1645 }, { "epoch": 0.7227332457293035, "grad_norm": 0.26221093408579443, "learning_rate": 4.331946709187578e-06, "loss": 1.1109, "step": 1650 }, { "epoch": 0.7249233464739377, "grad_norm": 0.2607246299946745, "learning_rate": 4.269109012171112e-06, "loss": 1.1104, "step": 1655 }, { "epoch": 0.7271134472185721, "grad_norm": 0.2574716134373636, "learning_rate": 4.206606480344303e-06, "loss": 1.0932, "step": 1660 }, { "epoch": 0.7293035479632063, "grad_norm": 0.265233772269521, "learning_rate": 4.14444276910263e-06, "loss": 1.1332, "step": 1665 }, { "epoch": 0.7314936487078406, "grad_norm": 0.25655122243148587, "learning_rate": 4.08262151402598e-06, "loss": 1.0891, "step": 1670 }, { "epoch": 0.7336837494524748, "grad_norm": 0.25501243107566296, "learning_rate": 4.021146330666065e-06, "loss": 1.0902, "step": 1675 }, { "epoch": 0.735873850197109, "grad_norm": 0.2612800818169169, "learning_rate": 3.960020814334936e-06, "loss": 1.1195, "step": 1680 }, { "epoch": 0.7380639509417434, "grad_norm": 0.2643874720892855, "learning_rate": 3.899248539894756e-06, "loss": 1.1137, "step": 1685 }, { "epoch": 0.7402540516863776, "grad_norm": 0.26838926718062733, "learning_rate": 3.838833061548682e-06, "loss": 1.1094, "step": 1690 }, { "epoch": 0.7424441524310118, "grad_norm": 0.26970931976433926, "learning_rate": 3.7787779126330314e-06, "loss": 1.1297, "step": 1695 }, { "epoch": 0.7446342531756461, "grad_norm": 0.26137631703110864, "learning_rate": 3.7190866054106358e-06, "loss": 1.1254, "step": 1700 }, { "epoch": 0.7468243539202803, "grad_norm": 0.2614031117426139, "learning_rate": 3.659762630865411e-06, "loss": 1.1041, "step": 1705 }, { "epoch": 0.7490144546649146, "grad_norm": 0.2580239989121174, "learning_rate": 3.600809458498219e-06, "loss": 1.1076, "step": 1710 }, { "epoch": 0.7512045554095489, "grad_norm": 0.2672365887137131, "learning_rate": 3.542230536123925e-06, "loss": 1.0988, "step": 1715 }, { "epoch": 0.7533946561541831, "grad_norm": 0.26577844660787864, "learning_rate": 3.484029289669797e-06, "loss": 1.098, "step": 1720 }, { "epoch": 0.7555847568988173, "grad_norm": 0.2563307410321518, "learning_rate": 3.4262091229750973e-06, "loss": 1.1051, "step": 1725 }, { "epoch": 0.7577748576434516, "grad_norm": 0.25998557620881213, "learning_rate": 3.3687734175920505e-06, "loss": 1.1121, "step": 1730 }, { "epoch": 0.7599649583880859, "grad_norm": 0.2641859803660572, "learning_rate": 3.311725532588049e-06, "loss": 1.1223, "step": 1735 }, { "epoch": 0.7621550591327201, "grad_norm": 0.26214013514430917, "learning_rate": 3.2550688043492273e-06, "loss": 1.11, "step": 1740 }, { "epoch": 0.7643451598773544, "grad_norm": 0.2613558739863409, "learning_rate": 3.1988065463853204e-06, "loss": 1.0902, "step": 1745 }, { "epoch": 0.7665352606219886, "grad_norm": 0.26742133303345345, "learning_rate": 3.1429420491358696e-06, "loss": 1.1262, "step": 1750 }, { "epoch": 0.7687253613666228, "grad_norm": 0.2599204528063472, "learning_rate": 3.0874785797778096e-06, "loss": 1.148, "step": 1755 }, { "epoch": 0.7709154621112572, "grad_norm": 0.2566302858053561, "learning_rate": 3.0324193820343685e-06, "loss": 1.1109, "step": 1760 }, { "epoch": 0.7731055628558914, "grad_norm": 0.260139567695262, "learning_rate": 2.977767675985377e-06, "loss": 1.1344, "step": 1765 }, { "epoch": 0.7752956636005256, "grad_norm": 0.2683465626714785, "learning_rate": 2.9235266578789268e-06, "loss": 1.1246, "step": 1770 }, { "epoch": 0.7774857643451599, "grad_norm": 0.2594022825090287, "learning_rate": 2.8696994999444614e-06, "loss": 1.1074, "step": 1775 }, { "epoch": 0.7796758650897941, "grad_norm": 0.26202834015198223, "learning_rate": 2.816289350207249e-06, "loss": 1.0943, "step": 1780 }, { "epoch": 0.7818659658344284, "grad_norm": 0.2581965218546036, "learning_rate": 2.76329933230425e-06, "loss": 1.1088, "step": 1785 }, { "epoch": 0.7840560665790627, "grad_norm": 0.262190008267224, "learning_rate": 2.7107325453014687e-06, "loss": 1.1098, "step": 1790 }, { "epoch": 0.7862461673236969, "grad_norm": 0.2534248970210751, "learning_rate": 2.658592063512684e-06, "loss": 1.0893, "step": 1795 }, { "epoch": 0.7884362680683311, "grad_norm": 0.2633626852571572, "learning_rate": 2.6068809363196633e-06, "loss": 1.091, "step": 1800 }, { "epoch": 0.7906263688129654, "grad_norm": 0.25921581241790814, "learning_rate": 2.5556021879938074e-06, "loss": 1.093, "step": 1805 }, { "epoch": 0.7928164695575997, "grad_norm": 0.2621990361536461, "learning_rate": 2.5047588175192995e-06, "loss": 1.1254, "step": 1810 }, { "epoch": 0.7950065703022339, "grad_norm": 0.2535710412898093, "learning_rate": 2.454353798417698e-06, "loss": 1.1072, "step": 1815 }, { "epoch": 0.7971966710468682, "grad_norm": 0.25964995240654326, "learning_rate": 2.4043900785740436e-06, "loss": 1.1023, "step": 1820 }, { "epoch": 0.7993867717915024, "grad_norm": 0.2539381357636022, "learning_rate": 2.354870580064439e-06, "loss": 1.1133, "step": 1825 }, { "epoch": 0.8015768725361366, "grad_norm": 0.2575538966366128, "learning_rate": 2.305798198985173e-06, "loss": 1.0879, "step": 1830 }, { "epoch": 0.803766973280771, "grad_norm": 0.25244614295211687, "learning_rate": 2.257175805283338e-06, "loss": 1.1137, "step": 1835 }, { "epoch": 0.8059570740254052, "grad_norm": 0.2668071511501433, "learning_rate": 2.209006242588977e-06, "loss": 1.1187, "step": 1840 }, { "epoch": 0.8081471747700394, "grad_norm": 0.26833063688258807, "learning_rate": 2.1612923280487883e-06, "loss": 1.1049, "step": 1845 }, { "epoch": 0.8103372755146737, "grad_norm": 0.25994289950129074, "learning_rate": 2.114036852161361e-06, "loss": 1.0926, "step": 1850 }, { "epoch": 0.8125273762593079, "grad_norm": 0.26330093138785376, "learning_rate": 2.0672425786139794e-06, "loss": 1.0885, "step": 1855 }, { "epoch": 0.8147174770039421, "grad_norm": 0.2627529440350032, "learning_rate": 2.020912244120983e-06, "loss": 1.0902, "step": 1860 }, { "epoch": 0.8169075777485765, "grad_norm": 0.25955955375887674, "learning_rate": 1.9750485582637245e-06, "loss": 1.127, "step": 1865 }, { "epoch": 0.8190976784932107, "grad_norm": 0.2615144960394142, "learning_rate": 1.9296542033321008e-06, "loss": 1.1074, "step": 1870 }, { "epoch": 0.8212877792378449, "grad_norm": 0.2650186451464187, "learning_rate": 1.8847318341676657e-06, "loss": 1.1234, "step": 1875 }, { "epoch": 0.8234778799824792, "grad_norm": 0.2641320073264704, "learning_rate": 1.840284078008393e-06, "loss": 1.0957, "step": 1880 }, { "epoch": 0.8256679807271134, "grad_norm": 0.2581562950846561, "learning_rate": 1.7963135343349914e-06, "loss": 1.1094, "step": 1885 }, { "epoch": 0.8278580814717477, "grad_norm": 0.25731784586468565, "learning_rate": 1.7528227747189152e-06, "loss": 1.1086, "step": 1890 }, { "epoch": 0.830048182216382, "grad_norm": 0.2618515550927689, "learning_rate": 1.7098143426719293e-06, "loss": 1.0984, "step": 1895 }, { "epoch": 0.8322382829610162, "grad_norm": 0.25314788080692846, "learning_rate": 1.667290753497386e-06, "loss": 1.0965, "step": 1900 }, { "epoch": 0.8344283837056504, "grad_norm": 0.25504674250436493, "learning_rate": 1.6252544941430982e-06, "loss": 1.0957, "step": 1905 }, { "epoch": 0.8366184844502847, "grad_norm": 0.2559793997504819, "learning_rate": 1.5837080230559077e-06, "loss": 1.0947, "step": 1910 }, { "epoch": 0.838808585194919, "grad_norm": 0.26055333090211424, "learning_rate": 1.5426537700378985e-06, "loss": 1.0961, "step": 1915 }, { "epoch": 0.8409986859395532, "grad_norm": 0.2576679394012241, "learning_rate": 1.5020941361042885e-06, "loss": 1.0934, "step": 1920 }, { "epoch": 0.8431887866841875, "grad_norm": 0.25828962040009074, "learning_rate": 1.4620314933430269e-06, "loss": 1.1121, "step": 1925 }, { "epoch": 0.8453788874288217, "grad_norm": 0.25513013439947374, "learning_rate": 1.4224681847760346e-06, "loss": 1.1145, "step": 1930 }, { "epoch": 0.8475689881734559, "grad_norm": 0.26643194015943783, "learning_rate": 1.383406524222206e-06, "loss": 1.1002, "step": 1935 }, { "epoch": 0.8497590889180903, "grad_norm": 0.25674411294345, "learning_rate": 1.3448487961620637e-06, "loss": 1.1355, "step": 1940 }, { "epoch": 0.8519491896627245, "grad_norm": 0.2605245623523021, "learning_rate": 1.3067972556041753e-06, "loss": 1.1207, "step": 1945 }, { "epoch": 0.8541392904073587, "grad_norm": 0.2616395396378427, "learning_rate": 1.2692541279532466e-06, "loss": 1.1129, "step": 1950 }, { "epoch": 0.856329391151993, "grad_norm": 0.2558570340754774, "learning_rate": 1.2322216088799955e-06, "loss": 1.1156, "step": 1955 }, { "epoch": 0.8585194918966272, "grad_norm": 0.25398464154559003, "learning_rate": 1.1957018641927187e-06, "loss": 1.1137, "step": 1960 }, { "epoch": 0.8607095926412615, "grad_norm": 0.2614386394260854, "learning_rate": 1.1596970297106458e-06, "loss": 1.1254, "step": 1965 }, { "epoch": 0.8628996933858958, "grad_norm": 0.2620955323370706, "learning_rate": 1.1242092111390157e-06, "loss": 1.085, "step": 1970 }, { "epoch": 0.86508979413053, "grad_norm": 0.2640807465997075, "learning_rate": 1.0892404839459269e-06, "loss": 1.1074, "step": 1975 }, { "epoch": 0.8672798948751642, "grad_norm": 0.2580694157592811, "learning_rate": 1.054792893240969e-06, "loss": 1.1098, "step": 1980 }, { "epoch": 0.8694699956197985, "grad_norm": 0.2651420557425447, "learning_rate": 1.0208684536555968e-06, "loss": 1.1275, "step": 1985 }, { "epoch": 0.8716600963644328, "grad_norm": 0.262002558002591, "learning_rate": 9.874691492253242e-07, "loss": 1.1039, "step": 1990 }, { "epoch": 0.873850197109067, "grad_norm": 0.25919863963901085, "learning_rate": 9.545969332736748e-07, "loss": 1.1195, "step": 1995 }, { "epoch": 0.8760402978537013, "grad_norm": 0.2668241542423085, "learning_rate": 9.222537282979593e-07, "loss": 1.1004, "step": 2000 }, { "epoch": 0.8782303985983355, "grad_norm": 0.2601150473608183, "learning_rate": 8.904414258568306e-07, "loss": 1.1027, "step": 2005 }, { "epoch": 0.8804204993429697, "grad_norm": 0.2548383260510458, "learning_rate": 8.591618864596541e-07, "loss": 1.1051, "step": 2010 }, { "epoch": 0.8826106000876041, "grad_norm": 0.2600128178676384, "learning_rate": 8.284169394577124e-07, "loss": 1.1236, "step": 2015 }, { "epoch": 0.8848007008322383, "grad_norm": 0.26066874164079284, "learning_rate": 7.982083829372023e-07, "loss": 1.1242, "step": 2020 }, { "epoch": 0.8869908015768725, "grad_norm": 0.25692211657826886, "learning_rate": 7.685379836140872e-07, "loss": 1.1406, "step": 2025 }, { "epoch": 0.8891809023215068, "grad_norm": 0.26481424368233436, "learning_rate": 7.394074767307591e-07, "loss": 1.1313, "step": 2030 }, { "epoch": 0.891371003066141, "grad_norm": 0.2618210555897095, "learning_rate": 7.10818565954573e-07, "loss": 1.1193, "step": 2035 }, { "epoch": 0.8935611038107752, "grad_norm": 0.26537735037912497, "learning_rate": 6.827729232781943e-07, "loss": 1.1273, "step": 2040 }, { "epoch": 0.8957512045554096, "grad_norm": 0.2565351465887861, "learning_rate": 6.552721889218194e-07, "loss": 1.1074, "step": 2045 }, { "epoch": 0.8979413053000438, "grad_norm": 0.2641157557567522, "learning_rate": 6.283179712372489e-07, "loss": 1.1102, "step": 2050 }, { "epoch": 0.900131406044678, "grad_norm": 0.258380894950019, "learning_rate": 6.019118466138285e-07, "loss": 1.0936, "step": 2055 }, { "epoch": 0.9023215067893123, "grad_norm": 0.2621614154084412, "learning_rate": 5.760553593862506e-07, "loss": 1.0959, "step": 2060 }, { "epoch": 0.9045116075339465, "grad_norm": 0.2560826189907596, "learning_rate": 5.507500217442341e-07, "loss": 1.1016, "step": 2065 }, { "epoch": 0.9067017082785808, "grad_norm": 0.2590724071414488, "learning_rate": 5.259973136440921e-07, "loss": 1.1082, "step": 2070 }, { "epoch": 0.9088918090232151, "grad_norm": 0.2573319556492272, "learning_rate": 5.017986827221733e-07, "loss": 1.1082, "step": 2075 }, { "epoch": 0.9110819097678493, "grad_norm": 0.34516100541646555, "learning_rate": 4.781555442102015e-07, "loss": 1.1355, "step": 2080 }, { "epoch": 0.9132720105124835, "grad_norm": 0.26180704480049366, "learning_rate": 4.5506928085250033e-07, "loss": 1.0871, "step": 2085 }, { "epoch": 0.9154621112571178, "grad_norm": 0.25833323890857174, "learning_rate": 4.3254124282513634e-07, "loss": 1.1062, "step": 2090 }, { "epoch": 0.9176522120017521, "grad_norm": 0.26187121720127504, "learning_rate": 4.1057274765694765e-07, "loss": 1.0939, "step": 2095 }, { "epoch": 0.9198423127463863, "grad_norm": 0.2573692262543959, "learning_rate": 3.891650801524871e-07, "loss": 1.1074, "step": 2100 }, { "epoch": 0.9220324134910206, "grad_norm": 0.2649955238574841, "learning_rate": 3.6831949231689203e-07, "loss": 1.1168, "step": 2105 }, { "epoch": 0.9242225142356548, "grad_norm": 0.2553634372156294, "learning_rate": 3.4803720328264733e-07, "loss": 1.1168, "step": 2110 }, { "epoch": 0.926412614980289, "grad_norm": 0.26728677917909055, "learning_rate": 3.283193992383049e-07, "loss": 1.1273, "step": 2115 }, { "epoch": 0.9286027157249234, "grad_norm": 0.2607892654338355, "learning_rate": 3.091672333590923e-07, "loss": 1.0867, "step": 2120 }, { "epoch": 0.9307928164695576, "grad_norm": 0.2527633048942072, "learning_rate": 2.905818257394799e-07, "loss": 1.1133, "step": 2125 }, { "epoch": 0.9329829172141918, "grad_norm": 0.25568945394844267, "learning_rate": 2.725642633276737e-07, "loss": 1.1098, "step": 2130 }, { "epoch": 0.9351730179588261, "grad_norm": 0.2597970875903515, "learning_rate": 2.5511559986204247e-07, "loss": 1.1184, "step": 2135 }, { "epoch": 0.9373631187034603, "grad_norm": 0.26327747871941953, "learning_rate": 2.3823685580949273e-07, "loss": 1.0965, "step": 2140 }, { "epoch": 0.9395532194480947, "grad_norm": 0.2607010813003693, "learning_rate": 2.219290183057865e-07, "loss": 1.1352, "step": 2145 }, { "epoch": 0.9417433201927289, "grad_norm": 0.2530017456095944, "learning_rate": 2.0619304109781636e-07, "loss": 1.1012, "step": 2150 }, { "epoch": 0.9439334209373631, "grad_norm": 0.2519870547260623, "learning_rate": 1.9102984448781337e-07, "loss": 1.0752, "step": 2155 }, { "epoch": 0.9461235216819974, "grad_norm": 0.2530254165097107, "learning_rate": 1.764403152795402e-07, "loss": 1.0934, "step": 2160 }, { "epoch": 0.9483136224266316, "grad_norm": 0.25397273342292553, "learning_rate": 1.6242530672641143e-07, "loss": 1.1219, "step": 2165 }, { "epoch": 0.9505037231712659, "grad_norm": 0.26174974744061347, "learning_rate": 1.4898563848160464e-07, "loss": 1.1473, "step": 2170 }, { "epoch": 0.9526938239159002, "grad_norm": 0.24955513279870836, "learning_rate": 1.3612209655011866e-07, "loss": 1.1195, "step": 2175 }, { "epoch": 0.9548839246605344, "grad_norm": 0.2583751624724583, "learning_rate": 1.2383543324280044e-07, "loss": 1.1189, "step": 2180 }, { "epoch": 0.9570740254051686, "grad_norm": 0.2588289009510903, "learning_rate": 1.1212636713235581e-07, "loss": 1.1416, "step": 2185 }, { "epoch": 0.9592641261498029, "grad_norm": 0.2583550968959351, "learning_rate": 1.0099558301132072e-07, "loss": 1.1254, "step": 2190 }, { "epoch": 0.9614542268944372, "grad_norm": 0.2527293991159154, "learning_rate": 9.044373185200906e-08, "loss": 1.1031, "step": 2195 }, { "epoch": 0.9636443276390714, "grad_norm": 0.2521840148118415, "learning_rate": 8.047143076844399e-08, "loss": 1.0783, "step": 2200 }, { "epoch": 0.9658344283837057, "grad_norm": 0.2606898444853039, "learning_rate": 7.10792629802659e-08, "loss": 1.1113, "step": 2205 }, { "epoch": 0.9680245291283399, "grad_norm": 0.25532227510506406, "learning_rate": 6.226777777862513e-08, "loss": 1.1293, "step": 2210 }, { "epoch": 0.9702146298729741, "grad_norm": 0.2565349165845633, "learning_rate": 5.403749049405438e-08, "loss": 1.1025, "step": 2215 }, { "epoch": 0.9724047306176085, "grad_norm": 0.25458880932233896, "learning_rate": 4.638888246633166e-08, "loss": 1.1121, "step": 2220 }, { "epoch": 0.9745948313622427, "grad_norm": 0.25398250551108936, "learning_rate": 3.932240101633178e-08, "loss": 1.1023, "step": 2225 }, { "epoch": 0.9767849321068769, "grad_norm": 0.25422167947403135, "learning_rate": 3.283845941985941e-08, "loss": 1.0758, "step": 2230 }, { "epoch": 0.9789750328515112, "grad_norm": 0.2569295535003476, "learning_rate": 2.693743688348627e-08, "loss": 1.1168, "step": 2235 }, { "epoch": 0.9811651335961454, "grad_norm": 0.2611140820134084, "learning_rate": 2.1619678522366573e-08, "loss": 1.098, "step": 2240 }, { "epoch": 0.9833552343407796, "grad_norm": 0.2585042183570841, "learning_rate": 1.68854953400599e-08, "loss": 1.1182, "step": 2245 }, { "epoch": 0.985545335085414, "grad_norm": 0.2699764722438751, "learning_rate": 1.2735164210337935e-08, "loss": 1.1629, "step": 2250 }, { "epoch": 0.9877354358300482, "grad_norm": 0.2604976252616973, "learning_rate": 9.168927860994104e-09, "loss": 1.1049, "step": 2255 }, { "epoch": 0.9899255365746824, "grad_norm": 0.2570709645581014, "learning_rate": 6.186994859646023e-09, "loss": 1.0938, "step": 2260 }, { "epoch": 0.9921156373193167, "grad_norm": 0.2534472927063691, "learning_rate": 3.7895396015374955e-09, "loss": 1.1094, "step": 2265 }, { "epoch": 0.994305738063951, "grad_norm": 0.2532795250404029, "learning_rate": 1.9767022993444353e-09, "loss": 1.1031, "step": 2270 }, { "epoch": 0.9964958388085852, "grad_norm": 0.25604334514879273, "learning_rate": 7.485889749658803e-10, "loss": 1.1129, "step": 2275 }, { "epoch": 0.9986859395532195, "grad_norm": 0.26226473069552947, "learning_rate": 1.0527145333227851e-10, "loss": 1.1066, "step": 2280 }, { "epoch": 1.0, "step": 2283, "total_flos": 216025446481920.0, "train_loss": 1.2513469975087603, "train_runtime": 7749.9665, "train_samples_per_second": 18.846, "train_steps_per_second": 0.295 } ], "logging_steps": 5, "max_steps": 2283, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": false, "should_training_stop": false }, "attributes": {} } }, "total_flos": 216025446481920.0, "train_batch_size": 16, "trial_name": null, "trial_params": null }