{ "best_metric": null, "best_model_checkpoint": null, "epoch": 3.0, "eval_steps": 500, "global_step": 1602, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.018726591760299626, "grad_norm": 6.9583668884714545, "learning_rate": 6.17283950617284e-07, "loss": 0.5853, "step": 10 }, { "epoch": 0.03745318352059925, "grad_norm": 2.459747968301057, "learning_rate": 1.234567901234568e-06, "loss": 0.4956, "step": 20 }, { "epoch": 0.056179775280898875, "grad_norm": 1.5518874081248877, "learning_rate": 1.8518518518518519e-06, "loss": 0.4511, "step": 30 }, { "epoch": 0.0749063670411985, "grad_norm": 1.327079400917728, "learning_rate": 2.469135802469136e-06, "loss": 0.4242, "step": 40 }, { "epoch": 0.09363295880149813, "grad_norm": 1.6052721933898932, "learning_rate": 3.08641975308642e-06, "loss": 0.4112, "step": 50 }, { "epoch": 0.11235955056179775, "grad_norm": 2.1363218656503236, "learning_rate": 3.7037037037037037e-06, "loss": 0.4056, "step": 60 }, { "epoch": 0.13108614232209737, "grad_norm": 2.5025301508678246, "learning_rate": 4.3209876543209875e-06, "loss": 0.3934, "step": 70 }, { "epoch": 0.149812734082397, "grad_norm": 1.6968039665700831, "learning_rate": 4.938271604938272e-06, "loss": 0.3931, "step": 80 }, { "epoch": 0.16853932584269662, "grad_norm": 1.710626024878931, "learning_rate": 4.999611253625062e-06, "loss": 0.3854, "step": 90 }, { "epoch": 0.18726591760299627, "grad_norm": 2.229340351997921, "learning_rate": 4.99826761145702e-06, "loss": 0.388, "step": 100 }, { "epoch": 0.20599250936329588, "grad_norm": 1.6554235103974217, "learning_rate": 4.995964847225794e-06, "loss": 0.3798, "step": 110 }, { "epoch": 0.2247191011235955, "grad_norm": 1.5390529564927018, "learning_rate": 4.992703943301973e-06, "loss": 0.3788, "step": 120 }, { "epoch": 0.24344569288389514, "grad_norm": 1.686640147089175, "learning_rate": 4.988486290803271e-06, "loss": 0.3724, "step": 130 }, { "epoch": 0.26217228464419473, "grad_norm": 1.4586531417129365, "learning_rate": 4.983313689001068e-06, "loss": 0.3737, "step": 140 }, { "epoch": 0.2808988764044944, "grad_norm": 1.383788345325366, "learning_rate": 4.977188344552831e-06, "loss": 0.3708, "step": 150 }, { "epoch": 0.299625468164794, "grad_norm": 2.344749126006063, "learning_rate": 4.970112870560744e-06, "loss": 0.3705, "step": 160 }, { "epoch": 0.31835205992509363, "grad_norm": 1.333313085188304, "learning_rate": 4.962090285456943e-06, "loss": 0.3726, "step": 170 }, { "epoch": 0.33707865168539325, "grad_norm": 1.2767396164379259, "learning_rate": 4.953124011715844e-06, "loss": 0.368, "step": 180 }, { "epoch": 0.35580524344569286, "grad_norm": 1.8939736466696433, "learning_rate": 4.943217874394092e-06, "loss": 0.3673, "step": 190 }, { "epoch": 0.37453183520599254, "grad_norm": 1.4076191572126282, "learning_rate": 4.932376099498779e-06, "loss": 0.3592, "step": 200 }, { "epoch": 0.39325842696629215, "grad_norm": 1.2393424297302382, "learning_rate": 4.920603312184602e-06, "loss": 0.3646, "step": 210 }, { "epoch": 0.41198501872659177, "grad_norm": 1.6712067045257082, "learning_rate": 4.907904534780752e-06, "loss": 0.3567, "step": 220 }, { "epoch": 0.4307116104868914, "grad_norm": 1.612702425647588, "learning_rate": 4.894285184648369e-06, "loss": 0.3585, "step": 230 }, { "epoch": 0.449438202247191, "grad_norm": 2.4813858906223834, "learning_rate": 4.879751071869461e-06, "loss": 0.3623, "step": 240 }, { "epoch": 0.4681647940074906, "grad_norm": 2.163116509485285, "learning_rate": 4.864308396768294e-06, "loss": 0.3586, "step": 250 }, { "epoch": 0.4868913857677903, "grad_norm": 1.7525497737806786, "learning_rate": 4.847963747266312e-06, "loss": 0.3547, "step": 260 }, { "epoch": 0.5056179775280899, "grad_norm": 1.3534898789991496, "learning_rate": 4.83072409607169e-06, "loss": 0.3534, "step": 270 }, { "epoch": 0.5243445692883895, "grad_norm": 1.6829737229447668, "learning_rate": 4.81259679770474e-06, "loss": 0.3519, "step": 280 }, { "epoch": 0.5430711610486891, "grad_norm": 1.3735075038975693, "learning_rate": 4.7935895853604455e-06, "loss": 0.353, "step": 290 }, { "epoch": 0.5617977528089888, "grad_norm": 1.9414583619507375, "learning_rate": 4.773710567609436e-06, "loss": 0.3547, "step": 300 }, { "epoch": 0.5805243445692884, "grad_norm": 1.4766636724732591, "learning_rate": 4.7529682249388284e-06, "loss": 0.3515, "step": 310 }, { "epoch": 0.599250936329588, "grad_norm": 1.420170786947651, "learning_rate": 4.7313714061344165e-06, "loss": 0.3559, "step": 320 }, { "epoch": 0.6179775280898876, "grad_norm": 1.585688048778078, "learning_rate": 4.708929324505729e-06, "loss": 0.3474, "step": 330 }, { "epoch": 0.6367041198501873, "grad_norm": 1.4660422960583963, "learning_rate": 4.685651553955589e-06, "loss": 0.3478, "step": 340 }, { "epoch": 0.6554307116104869, "grad_norm": 1.729952760499875, "learning_rate": 4.661548024895843e-06, "loss": 0.3502, "step": 350 }, { "epoch": 0.6741573033707865, "grad_norm": 1.5477887192577897, "learning_rate": 4.636629020010989e-06, "loss": 0.3462, "step": 360 }, { "epoch": 0.6928838951310862, "grad_norm": 1.3822726826009006, "learning_rate": 4.6109051698715425e-06, "loss": 0.3447, "step": 370 }, { "epoch": 0.7116104868913857, "grad_norm": 1.4151446110625596, "learning_rate": 4.5843874483989744e-06, "loss": 0.3452, "step": 380 }, { "epoch": 0.7303370786516854, "grad_norm": 1.213585225271953, "learning_rate": 4.5570871681841915e-06, "loss": 0.3525, "step": 390 }, { "epoch": 0.7490636704119851, "grad_norm": 1.2153292815838297, "learning_rate": 4.529015975661518e-06, "loss": 0.3497, "step": 400 }, { "epoch": 0.7677902621722846, "grad_norm": 1.0767956653910644, "learning_rate": 4.5001858461402765e-06, "loss": 0.3469, "step": 410 }, { "epoch": 0.7865168539325843, "grad_norm": 1.0725016047427482, "learning_rate": 4.470609078696062e-06, "loss": 0.3459, "step": 420 }, { "epoch": 0.8052434456928839, "grad_norm": 1.14757314560185, "learning_rate": 4.440298290923893e-06, "loss": 0.3446, "step": 430 }, { "epoch": 0.8239700374531835, "grad_norm": 1.435028611591542, "learning_rate": 4.409266413555481e-06, "loss": 0.3468, "step": 440 }, { "epoch": 0.8426966292134831, "grad_norm": 1.3563421475894943, "learning_rate": 4.3775266849429245e-06, "loss": 0.3471, "step": 450 }, { "epoch": 0.8614232209737828, "grad_norm": 1.272968934220072, "learning_rate": 4.345092645411154e-06, "loss": 0.3459, "step": 460 }, { "epoch": 0.8801498127340824, "grad_norm": 1.1988760260435716, "learning_rate": 4.311978131481565e-06, "loss": 0.3439, "step": 470 }, { "epoch": 0.898876404494382, "grad_norm": 1.2157009389799966, "learning_rate": 4.2781972699692955e-06, "loss": 0.341, "step": 480 }, { "epoch": 0.9176029962546817, "grad_norm": 1.2302691306481766, "learning_rate": 4.243764471956648e-06, "loss": 0.3436, "step": 490 }, { "epoch": 0.9363295880149812, "grad_norm": 1.1395524537917356, "learning_rate": 4.208694426645257e-06, "loss": 0.3442, "step": 500 }, { "epoch": 0.9550561797752809, "grad_norm": 1.0502686640912897, "learning_rate": 4.1730020950895985e-06, "loss": 0.3406, "step": 510 }, { "epoch": 0.9737827715355806, "grad_norm": 1.1788715508510565, "learning_rate": 4.136702703814536e-06, "loss": 0.3399, "step": 520 }, { "epoch": 0.9925093632958801, "grad_norm": 0.9961303841798358, "learning_rate": 4.0998117383196035e-06, "loss": 0.3426, "step": 530 }, { "epoch": 1.0, "eval_loss": 0.3397010564804077, "eval_runtime": 49.3629, "eval_samples_per_second": 291.271, "eval_steps_per_second": 1.155, "step": 534 }, { "epoch": 1.0112359550561798, "grad_norm": 1.5016330309741552, "learning_rate": 4.062344936472819e-06, "loss": 0.3041, "step": 540 }, { "epoch": 1.0299625468164795, "grad_norm": 1.4105174151178423, "learning_rate": 4.024318281796832e-06, "loss": 0.2653, "step": 550 }, { "epoch": 1.048689138576779, "grad_norm": 1.1267842205009497, "learning_rate": 3.985747996650271e-06, "loss": 0.2635, "step": 560 }, { "epoch": 1.0674157303370786, "grad_norm": 1.4577741522220231, "learning_rate": 3.94665053530721e-06, "loss": 0.2661, "step": 570 }, { "epoch": 1.0861423220973783, "grad_norm": 1.1743755144218508, "learning_rate": 3.907042576937689e-06, "loss": 0.2614, "step": 580 }, { "epoch": 1.104868913857678, "grad_norm": 1.1077587707464613, "learning_rate": 3.8669410184923e-06, "loss": 0.2638, "step": 590 }, { "epoch": 1.1235955056179776, "grad_norm": 1.499213012424364, "learning_rate": 3.826362967493867e-06, "loss": 0.2649, "step": 600 }, { "epoch": 1.142322097378277, "grad_norm": 1.2186830879218926, "learning_rate": 3.7853257347392865e-06, "loss": 0.2664, "step": 610 }, { "epoch": 1.1610486891385767, "grad_norm": 1.5365523984386804, "learning_rate": 3.74384682691466e-06, "loss": 0.2656, "step": 620 }, { "epoch": 1.1797752808988764, "grad_norm": 1.2824215690021454, "learning_rate": 3.701943939126856e-06, "loss": 0.264, "step": 630 }, { "epoch": 1.198501872659176, "grad_norm": 1.1855864127248261, "learning_rate": 3.659634947354686e-06, "loss": 0.2612, "step": 640 }, { "epoch": 1.2172284644194757, "grad_norm": 1.0357586593608685, "learning_rate": 3.61693790082293e-06, "loss": 0.2609, "step": 650 }, { "epoch": 1.2359550561797752, "grad_norm": 1.2298112784157318, "learning_rate": 3.5738710143024406e-06, "loss": 0.2648, "step": 660 }, { "epoch": 1.2546816479400749, "grad_norm": 1.1873771143182965, "learning_rate": 3.530452660339638e-06, "loss": 0.2648, "step": 670 }, { "epoch": 1.2734082397003745, "grad_norm": 1.1104387940773652, "learning_rate": 3.486701361418686e-06, "loss": 0.2669, "step": 680 }, { "epoch": 1.2921348314606742, "grad_norm": 1.0981466202062755, "learning_rate": 3.4426357820597144e-06, "loss": 0.2656, "step": 690 }, { "epoch": 1.3108614232209739, "grad_norm": 1.0622356793414978, "learning_rate": 3.3982747208564383e-06, "loss": 0.2684, "step": 700 }, { "epoch": 1.3295880149812733, "grad_norm": 1.1204181746461044, "learning_rate": 3.353637102456585e-06, "loss": 0.2632, "step": 710 }, { "epoch": 1.348314606741573, "grad_norm": 1.1561988340566498, "learning_rate": 3.30874196948855e-06, "loss": 0.2655, "step": 720 }, { "epoch": 1.3670411985018727, "grad_norm": 1.1634759808618433, "learning_rate": 3.2636084744377123e-06, "loss": 0.2662, "step": 730 }, { "epoch": 1.3857677902621723, "grad_norm": 1.183622746360506, "learning_rate": 3.218255871475894e-06, "loss": 0.2665, "step": 740 }, { "epoch": 1.404494382022472, "grad_norm": 1.3035644321187594, "learning_rate": 3.172703508247433e-06, "loss": 0.2641, "step": 750 }, { "epoch": 1.4232209737827715, "grad_norm": 1.2520080394828148, "learning_rate": 3.126970817615384e-06, "loss": 0.2641, "step": 760 }, { "epoch": 1.4419475655430711, "grad_norm": 1.1658528659149325, "learning_rate": 3.0810773093713615e-06, "loss": 0.2672, "step": 770 }, { "epoch": 1.4606741573033708, "grad_norm": 1.1183168156658745, "learning_rate": 3.0350425619125678e-06, "loss": 0.2679, "step": 780 }, { "epoch": 1.4794007490636705, "grad_norm": 1.2572209531909289, "learning_rate": 2.988886213889551e-06, "loss": 0.2673, "step": 790 }, { "epoch": 1.4981273408239701, "grad_norm": 1.1500933028632634, "learning_rate": 2.9426279558282617e-06, "loss": 0.2661, "step": 800 }, { "epoch": 1.5168539325842696, "grad_norm": 1.090606866883075, "learning_rate": 2.896287521729974e-06, "loss": 0.2616, "step": 810 }, { "epoch": 1.5355805243445693, "grad_norm": 1.1320316226013576, "learning_rate": 2.849884680652666e-06, "loss": 0.27, "step": 820 }, { "epoch": 1.554307116104869, "grad_norm": 1.103244276726941, "learning_rate": 2.8034392282774415e-06, "loss": 0.2635, "step": 830 }, { "epoch": 1.5730337078651684, "grad_norm": 1.099593203599622, "learning_rate": 2.7569709784635934e-06, "loss": 0.2619, "step": 840 }, { "epoch": 1.5917602996254683, "grad_norm": 1.0707708462874654, "learning_rate": 2.710499754795916e-06, "loss": 0.2636, "step": 850 }, { "epoch": 1.6104868913857677, "grad_norm": 1.1077681383186893, "learning_rate": 2.664045382127863e-06, "loss": 0.2635, "step": 860 }, { "epoch": 1.6292134831460674, "grad_norm": 1.0523839107618693, "learning_rate": 2.6176276781241695e-06, "loss": 0.2671, "step": 870 }, { "epoch": 1.647940074906367, "grad_norm": 1.1453676425960706, "learning_rate": 2.571266444806535e-06, "loss": 0.2636, "step": 880 }, { "epoch": 1.6666666666666665, "grad_norm": 1.0877845955489727, "learning_rate": 2.5249814601059897e-06, "loss": 0.2622, "step": 890 }, { "epoch": 1.6853932584269664, "grad_norm": 1.109206643426623, "learning_rate": 2.4787924694255235e-06, "loss": 0.2674, "step": 900 }, { "epoch": 1.7041198501872659, "grad_norm": 1.148003058058869, "learning_rate": 2.4327191772166046e-06, "loss": 0.2666, "step": 910 }, { "epoch": 1.7228464419475655, "grad_norm": 1.0373837405536894, "learning_rate": 2.3867812385731627e-06, "loss": 0.2624, "step": 920 }, { "epoch": 1.7415730337078652, "grad_norm": 1.0452119354423188, "learning_rate": 2.340998250846629e-06, "loss": 0.2672, "step": 930 }, { "epoch": 1.7602996254681647, "grad_norm": 1.0839517512429684, "learning_rate": 2.2953897452856035e-06, "loss": 0.2627, "step": 940 }, { "epoch": 1.7790262172284645, "grad_norm": 1.1357572847216206, "learning_rate": 2.2499751787037404e-06, "loss": 0.2658, "step": 950 }, { "epoch": 1.797752808988764, "grad_norm": 1.049597976731673, "learning_rate": 2.2047739251793624e-06, "loss": 0.2634, "step": 960 }, { "epoch": 1.8164794007490637, "grad_norm": 1.1411990916035244, "learning_rate": 2.1598052677903904e-06, "loss": 0.261, "step": 970 }, { "epoch": 1.8352059925093633, "grad_norm": 1.1008798760396603, "learning_rate": 2.1150883903880863e-06, "loss": 0.2622, "step": 980 }, { "epoch": 1.8539325842696628, "grad_norm": 1.0556909678728987, "learning_rate": 2.0706423694131246e-06, "loss": 0.2589, "step": 990 }, { "epoch": 1.8726591760299627, "grad_norm": 1.01122078883521, "learning_rate": 2.0264861657574936e-06, "loss": 0.2602, "step": 1000 }, { "epoch": 1.8913857677902621, "grad_norm": 1.030111452172985, "learning_rate": 1.9826386166756796e-06, "loss": 0.2625, "step": 1010 }, { "epoch": 1.9101123595505618, "grad_norm": 1.0304981637914168, "learning_rate": 1.9391184277486046e-06, "loss": 0.2616, "step": 1020 }, { "epoch": 1.9288389513108615, "grad_norm": 1.1002315606948327, "learning_rate": 1.8959441649037334e-06, "loss": 0.2618, "step": 1030 }, { "epoch": 1.947565543071161, "grad_norm": 1.0682674034690947, "learning_rate": 1.8531342464947551e-06, "loss": 0.2604, "step": 1040 }, { "epoch": 1.9662921348314608, "grad_norm": 1.0285099387800412, "learning_rate": 1.810706935444223e-06, "loss": 0.2623, "step": 1050 }, { "epoch": 1.9850187265917603, "grad_norm": 1.054687396839439, "learning_rate": 1.7686803314525056e-06, "loss": 0.264, "step": 1060 }, { "epoch": 2.0, "eval_loss": 0.3330671787261963, "eval_runtime": 50.16, "eval_samples_per_second": 286.643, "eval_steps_per_second": 1.136, "step": 1068 }, { "epoch": 2.0037453183520597, "grad_norm": 1.7923902161169425, "learning_rate": 1.7270723632763563e-06, "loss": 0.2446, "step": 1070 }, { "epoch": 2.0224719101123596, "grad_norm": 1.345237927622502, "learning_rate": 1.685900781080428e-06, "loss": 0.1907, "step": 1080 }, { "epoch": 2.041198501872659, "grad_norm": 1.1496616768510104, "learning_rate": 1.6451831488649562e-06, "loss": 0.1874, "step": 1090 }, { "epoch": 2.059925093632959, "grad_norm": 1.1107541934632752, "learning_rate": 1.6049368369728748e-06, "loss": 0.187, "step": 1100 }, { "epoch": 2.0786516853932584, "grad_norm": 1.1294609243658884, "learning_rate": 1.5651790146795434e-06, "loss": 0.1861, "step": 1110 }, { "epoch": 2.097378277153558, "grad_norm": 1.1064659786749327, "learning_rate": 1.525926642868242e-06, "loss": 0.188, "step": 1120 }, { "epoch": 2.1161048689138577, "grad_norm": 1.1288942946219733, "learning_rate": 1.4871964667945815e-06, "loss": 0.1889, "step": 1130 }, { "epoch": 2.134831460674157, "grad_norm": 1.1095107607344008, "learning_rate": 1.4490050089428965e-06, "loss": 0.1878, "step": 1140 }, { "epoch": 2.153558052434457, "grad_norm": 1.1688843518004304, "learning_rate": 1.411368561977662e-06, "loss": 0.1873, "step": 1150 }, { "epoch": 2.1722846441947565, "grad_norm": 1.1746086833216787, "learning_rate": 1.3743031817929725e-06, "loss": 0.1885, "step": 1160 }, { "epoch": 2.191011235955056, "grad_norm": 1.0953314936943879, "learning_rate": 1.337824680663016e-06, "loss": 0.1918, "step": 1170 }, { "epoch": 2.209737827715356, "grad_norm": 1.1591899466119513, "learning_rate": 1.3019486204964737e-06, "loss": 0.1883, "step": 1180 }, { "epoch": 2.2284644194756553, "grad_norm": 1.1558485332053892, "learning_rate": 1.2666903061977397e-06, "loss": 0.1901, "step": 1190 }, { "epoch": 2.247191011235955, "grad_norm": 1.2117954838055114, "learning_rate": 1.2320647791377731e-06, "loss": 0.1895, "step": 1200 }, { "epoch": 2.2659176029962547, "grad_norm": 1.0645164422876823, "learning_rate": 1.1980868107373687e-06, "loss": 0.1863, "step": 1210 }, { "epoch": 2.284644194756554, "grad_norm": 1.1541528576196018, "learning_rate": 1.1647708961656036e-06, "loss": 0.1901, "step": 1220 }, { "epoch": 2.303370786516854, "grad_norm": 1.116106510953403, "learning_rate": 1.1321312481561198e-06, "loss": 0.1892, "step": 1230 }, { "epoch": 2.3220973782771535, "grad_norm": 1.0597155426906926, "learning_rate": 1.1001817909439065e-06, "loss": 0.1894, "step": 1240 }, { "epoch": 2.3408239700374533, "grad_norm": 1.1196874887948434, "learning_rate": 1.0689361543251532e-06, "loss": 0.1887, "step": 1250 }, { "epoch": 2.359550561797753, "grad_norm": 1.1714322905126089, "learning_rate": 1.038407667842705e-06, "loss": 0.1864, "step": 1260 }, { "epoch": 2.3782771535580522, "grad_norm": 1.0763451314249386, "learning_rate": 1.008609355099621e-06, "loss": 0.1864, "step": 1270 }, { "epoch": 2.397003745318352, "grad_norm": 1.1473816461596407, "learning_rate": 9.795539282032386e-07, "loss": 0.1875, "step": 1280 }, { "epoch": 2.4157303370786516, "grad_norm": 1.098908279814066, "learning_rate": 9.512537823421229e-07, "loss": 0.1864, "step": 1290 }, { "epoch": 2.4344569288389515, "grad_norm": 1.1578303830285432, "learning_rate": 9.237209904982213e-07, "loss": 0.1904, "step": 1300 }, { "epoch": 2.453183520599251, "grad_norm": 1.1404639700697865, "learning_rate": 8.969672982964711e-07, "loss": 0.1907, "step": 1310 }, { "epoch": 2.4719101123595504, "grad_norm": 1.0825550585492165, "learning_rate": 8.710041189940513e-07, "loss": 0.1868, "step": 1320 }, { "epoch": 2.4906367041198503, "grad_norm": 1.1503042083334585, "learning_rate": 8.458425286114396e-07, "loss": 0.189, "step": 1330 }, { "epoch": 2.5093632958801497, "grad_norm": 1.1289267850787381, "learning_rate": 8.214932612073207e-07, "loss": 0.1891, "step": 1340 }, { "epoch": 2.5280898876404496, "grad_norm": 1.0922707099906583, "learning_rate": 7.979667042993847e-07, "loss": 0.1882, "step": 1350 }, { "epoch": 2.546816479400749, "grad_norm": 1.159472662881807, "learning_rate": 7.752728944329658e-07, "loss": 0.1884, "step": 1360 }, { "epoch": 2.5655430711610485, "grad_norm": 1.096656880156706, "learning_rate": 7.534215128993953e-07, "loss": 0.1912, "step": 1370 }, { "epoch": 2.5842696629213484, "grad_norm": 1.177067424925165, "learning_rate": 7.324218816059202e-07, "loss": 0.1869, "step": 1380 }, { "epoch": 2.602996254681648, "grad_norm": 1.1433902131098264, "learning_rate": 7.122829590989305e-07, "loss": 0.1859, "step": 1390 }, { "epoch": 2.6217228464419478, "grad_norm": 1.0780282296557087, "learning_rate": 6.930133367421965e-07, "loss": 0.1903, "step": 1400 }, { "epoch": 2.640449438202247, "grad_norm": 1.1302075316778486, "learning_rate": 6.746212350517535e-07, "loss": 0.187, "step": 1410 }, { "epoch": 2.6591760299625467, "grad_norm": 1.1073095304447773, "learning_rate": 6.57114500188989e-07, "loss": 0.1886, "step": 1420 }, { "epoch": 2.6779026217228465, "grad_norm": 1.0420564202777807, "learning_rate": 6.405006006134285e-07, "loss": 0.1879, "step": 1430 }, { "epoch": 2.696629213483146, "grad_norm": 1.0777824438327903, "learning_rate": 6.247866238966579e-07, "loss": 0.1904, "step": 1440 }, { "epoch": 2.715355805243446, "grad_norm": 1.1121227385024828, "learning_rate": 6.099792736987272e-07, "loss": 0.1873, "step": 1450 }, { "epoch": 2.7340823970037453, "grad_norm": 1.109347730952044, "learning_rate": 5.96084866908337e-07, "loss": 0.1897, "step": 1460 }, { "epoch": 2.752808988764045, "grad_norm": 1.131219956309559, "learning_rate": 5.831093309480244e-07, "loss": 0.1848, "step": 1470 }, { "epoch": 2.7715355805243447, "grad_norm": 1.0563106661530495, "learning_rate": 5.710582012454928e-07, "loss": 0.1862, "step": 1480 }, { "epoch": 2.790262172284644, "grad_norm": 1.1800848608197825, "learning_rate": 5.599366188721713e-07, "loss": 0.1878, "step": 1490 }, { "epoch": 2.808988764044944, "grad_norm": 1.1143488700250004, "learning_rate": 5.497493283500105e-07, "loss": 0.1875, "step": 1500 }, { "epoch": 2.8277153558052435, "grad_norm": 1.0433720861256908, "learning_rate": 5.405006756274435e-07, "loss": 0.1872, "step": 1510 }, { "epoch": 2.846441947565543, "grad_norm": 1.1343560438226763, "learning_rate": 5.321946062253841e-07, "loss": 0.1894, "step": 1520 }, { "epoch": 2.865168539325843, "grad_norm": 1.1296113946372626, "learning_rate": 5.248346635540485e-07, "loss": 0.1864, "step": 1530 }, { "epoch": 2.8838951310861423, "grad_norm": 1.1286259876244906, "learning_rate": 5.184239874013167e-07, "loss": 0.1893, "step": 1540 }, { "epoch": 2.902621722846442, "grad_norm": 1.079795528012858, "learning_rate": 5.129653125932872e-07, "loss": 0.1867, "step": 1550 }, { "epoch": 2.9213483146067416, "grad_norm": 1.1367094539661884, "learning_rate": 5.084609678275833e-07, "loss": 0.1913, "step": 1560 }, { "epoch": 2.940074906367041, "grad_norm": 1.1317799697421957, "learning_rate": 5.049128746799206e-07, "loss": 0.1874, "step": 1570 }, { "epoch": 2.958801498127341, "grad_norm": 1.0575396751944557, "learning_rate": 5.023225467843537e-07, "loss": 0.1868, "step": 1580 }, { "epoch": 2.9775280898876404, "grad_norm": 1.0774002831939866, "learning_rate": 5.006910891875522e-07, "loss": 0.1875, "step": 1590 }, { "epoch": 2.9962546816479403, "grad_norm": 1.0987879465354378, "learning_rate": 5.00019197877381e-07, "loss": 0.1874, "step": 1600 }, { "epoch": 3.0, "eval_loss": 0.3581169545650482, "eval_runtime": 55.9282, "eval_samples_per_second": 257.08, "eval_steps_per_second": 1.019, "step": 1602 }, { "epoch": 3.0, "step": 1602, "total_flos": 2683409667194880.0, "train_loss": 0.2738360005445992, "train_runtime": 9858.4557, "train_samples_per_second": 83.126, "train_steps_per_second": 0.163 } ], "logging_steps": 10, "max_steps": 1602, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 2683409667194880.0, "train_batch_size": 16, "trial_name": null, "trial_params": null }