| { | |
| "best_metric": 1.942334532737732, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-200", | |
| "epoch": 0.03423192126658109, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00017115960633290543, | |
| "grad_norm": 0.3384851813316345, | |
| "learning_rate": 3.3333333333333333e-06, | |
| "loss": 2.1057, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00017115960633290543, | |
| "eval_loss": 2.140085220336914, | |
| "eval_runtime": 252.4143, | |
| "eval_samples_per_second": 38.984, | |
| "eval_steps_per_second": 19.492, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00034231921266581085, | |
| "grad_norm": 0.3000636100769043, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 2.0679, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0005134788189987163, | |
| "grad_norm": 0.31949612498283386, | |
| "learning_rate": 1e-05, | |
| "loss": 2.2765, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0006846384253316217, | |
| "grad_norm": 0.2581222355365753, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 1.8811, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0008557980316645272, | |
| "grad_norm": 0.2666412889957428, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 2.021, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0010269576379974327, | |
| "grad_norm": 0.26130983233451843, | |
| "learning_rate": 2e-05, | |
| "loss": 1.8714, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0011981172443303381, | |
| "grad_norm": 0.22150737047195435, | |
| "learning_rate": 2.3333333333333336e-05, | |
| "loss": 1.7815, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0013692768506632434, | |
| "grad_norm": 0.25391674041748047, | |
| "learning_rate": 2.6666666666666667e-05, | |
| "loss": 2.0571, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0015404364569961489, | |
| "grad_norm": 0.2351103127002716, | |
| "learning_rate": 3e-05, | |
| "loss": 1.7819, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0017115960633290544, | |
| "grad_norm": 0.24356381595134735, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 1.9668, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0018827556696619598, | |
| "grad_norm": 0.25410857796669006, | |
| "learning_rate": 3.6666666666666666e-05, | |
| "loss": 2.0877, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0020539152759948653, | |
| "grad_norm": 0.2615646719932556, | |
| "learning_rate": 4e-05, | |
| "loss": 2.0598, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.002225074882327771, | |
| "grad_norm": 0.24895967543125153, | |
| "learning_rate": 4.3333333333333334e-05, | |
| "loss": 2.0459, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0023962344886606763, | |
| "grad_norm": 0.24129140377044678, | |
| "learning_rate": 4.666666666666667e-05, | |
| "loss": 2.1703, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0025673940949935813, | |
| "grad_norm": 0.21726980805397034, | |
| "learning_rate": 5e-05, | |
| "loss": 2.0914, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.002738553701326487, | |
| "grad_norm": 0.20076154172420502, | |
| "learning_rate": 5.333333333333333e-05, | |
| "loss": 1.9858, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0029097133076593923, | |
| "grad_norm": 0.15559637546539307, | |
| "learning_rate": 5.666666666666667e-05, | |
| "loss": 1.8849, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0030808729139922978, | |
| "grad_norm": 0.16304416954517365, | |
| "learning_rate": 6e-05, | |
| "loss": 2.1007, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0032520325203252032, | |
| "grad_norm": 0.15507805347442627, | |
| "learning_rate": 6.333333333333333e-05, | |
| "loss": 2.0215, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0034231921266581087, | |
| "grad_norm": 0.1489063948392868, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 2.0716, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.003594351732991014, | |
| "grad_norm": 0.15571531653404236, | |
| "learning_rate": 7e-05, | |
| "loss": 1.9169, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0037655113393239197, | |
| "grad_norm": 0.15557806193828583, | |
| "learning_rate": 7.333333333333333e-05, | |
| "loss": 1.996, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.003936670945656825, | |
| "grad_norm": 0.17348982393741608, | |
| "learning_rate": 7.666666666666667e-05, | |
| "loss": 2.0536, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.004107830551989731, | |
| "grad_norm": 0.16075366735458374, | |
| "learning_rate": 8e-05, | |
| "loss": 2.0326, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.004278990158322636, | |
| "grad_norm": 0.1705283671617508, | |
| "learning_rate": 8.333333333333334e-05, | |
| "loss": 2.0816, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.004450149764655542, | |
| "grad_norm": 0.1489923745393753, | |
| "learning_rate": 8.666666666666667e-05, | |
| "loss": 1.9582, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.004621309370988447, | |
| "grad_norm": 0.15770766139030457, | |
| "learning_rate": 9e-05, | |
| "loss": 2.1467, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.004792468977321353, | |
| "grad_norm": 0.13497239351272583, | |
| "learning_rate": 9.333333333333334e-05, | |
| "loss": 1.9728, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.004963628583654257, | |
| "grad_norm": 0.14810675382614136, | |
| "learning_rate": 9.666666666666667e-05, | |
| "loss": 2.0339, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.005134788189987163, | |
| "grad_norm": 0.12770140171051025, | |
| "learning_rate": 0.0001, | |
| "loss": 1.9108, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.005305947796320068, | |
| "grad_norm": 0.14340223371982574, | |
| "learning_rate": 9.999146252290264e-05, | |
| "loss": 1.9649, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.005477107402652974, | |
| "grad_norm": 0.13468272984027863, | |
| "learning_rate": 9.996585300715116e-05, | |
| "loss": 1.9385, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.005648267008985879, | |
| "grad_norm": 0.1366954743862152, | |
| "learning_rate": 9.99231801983717e-05, | |
| "loss": 1.9931, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.005819426615318785, | |
| "grad_norm": 0.12960107624530792, | |
| "learning_rate": 9.986345866928941e-05, | |
| "loss": 1.7814, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.00599058622165169, | |
| "grad_norm": 0.13072721660137177, | |
| "learning_rate": 9.978670881475172e-05, | |
| "loss": 1.9877, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0061617458279845955, | |
| "grad_norm": 0.14742650091648102, | |
| "learning_rate": 9.96929568447637e-05, | |
| "loss": 2.0895, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.006332905434317501, | |
| "grad_norm": 0.1375843733549118, | |
| "learning_rate": 9.958223477553714e-05, | |
| "loss": 1.9882, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0065040650406504065, | |
| "grad_norm": 0.1338900923728943, | |
| "learning_rate": 9.94545804185573e-05, | |
| "loss": 2.1235, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.006675224646983312, | |
| "grad_norm": 0.139565572142601, | |
| "learning_rate": 9.931003736767013e-05, | |
| "loss": 1.9161, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0068463842533162175, | |
| "grad_norm": 0.1471727341413498, | |
| "learning_rate": 9.91486549841951e-05, | |
| "loss": 1.8279, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.007017543859649123, | |
| "grad_norm": 0.14104895293712616, | |
| "learning_rate": 9.89704883800683e-05, | |
| "loss": 1.9517, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.007188703465982028, | |
| "grad_norm": 0.14945568144321442, | |
| "learning_rate": 9.877559839902184e-05, | |
| "loss": 1.8598, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.007359863072314934, | |
| "grad_norm": 0.16899332404136658, | |
| "learning_rate": 9.85640515958057e-05, | |
| "loss": 2.0511, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.007531022678647839, | |
| "grad_norm": 0.16674430668354034, | |
| "learning_rate": 9.833592021345937e-05, | |
| "loss": 2.0885, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.007702182284980745, | |
| "grad_norm": 0.1767071783542633, | |
| "learning_rate": 9.809128215864097e-05, | |
| "loss": 2.0406, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.00787334189131365, | |
| "grad_norm": 0.183282271027565, | |
| "learning_rate": 9.783022097502204e-05, | |
| "loss": 1.8779, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.008044501497646555, | |
| "grad_norm": 0.22200380265712738, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 1.8805, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.008215661103979461, | |
| "grad_norm": 0.2835330367088318, | |
| "learning_rate": 9.725919140804099e-05, | |
| "loss": 2.1045, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.008386820710312366, | |
| "grad_norm": 0.6013146638870239, | |
| "learning_rate": 9.694941803075283e-05, | |
| "loss": 2.1857, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.008557980316645272, | |
| "grad_norm": 0.7531317472457886, | |
| "learning_rate": 9.662361147021779e-05, | |
| "loss": 2.1909, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.008557980316645272, | |
| "eval_loss": 2.0112826824188232, | |
| "eval_runtime": 253.1487, | |
| "eval_samples_per_second": 38.87, | |
| "eval_steps_per_second": 19.435, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.008729139922978177, | |
| "grad_norm": 0.24028153717517853, | |
| "learning_rate": 9.628188298907782e-05, | |
| "loss": 1.8849, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.008900299529311083, | |
| "grad_norm": 0.2163541167974472, | |
| "learning_rate": 9.592434928729616e-05, | |
| "loss": 1.9064, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.009071459135643988, | |
| "grad_norm": 0.1897958517074585, | |
| "learning_rate": 9.555113246230442e-05, | |
| "loss": 1.962, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.009242618741976894, | |
| "grad_norm": 0.1701580286026001, | |
| "learning_rate": 9.516235996730645e-05, | |
| "loss": 1.8102, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.009413778348309799, | |
| "grad_norm": 0.17404377460479736, | |
| "learning_rate": 9.475816456775313e-05, | |
| "loss": 1.7162, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.009584937954642705, | |
| "grad_norm": 0.16066402196884155, | |
| "learning_rate": 9.43386842960031e-05, | |
| "loss": 1.7332, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.00975609756097561, | |
| "grad_norm": 0.15609973669052124, | |
| "learning_rate": 9.39040624041849e-05, | |
| "loss": 1.7929, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.009927257167308514, | |
| "grad_norm": 0.15920859575271606, | |
| "learning_rate": 9.345444731527642e-05, | |
| "loss": 1.8153, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.01009841677364142, | |
| "grad_norm": 0.1596253216266632, | |
| "learning_rate": 9.298999257241863e-05, | |
| "loss": 1.8854, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.010269576379974325, | |
| "grad_norm": 0.136519655585289, | |
| "learning_rate": 9.251085678648072e-05, | |
| "loss": 1.9049, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.010440735986307232, | |
| "grad_norm": 0.1335257738828659, | |
| "learning_rate": 9.201720358189464e-05, | |
| "loss": 1.8594, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.010611895592640136, | |
| "grad_norm": 0.1406267285346985, | |
| "learning_rate": 9.150920154077754e-05, | |
| "loss": 2.0214, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.010783055198973043, | |
| "grad_norm": 0.11417517811059952, | |
| "learning_rate": 9.098702414536107e-05, | |
| "loss": 1.9628, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.010954214805305947, | |
| "grad_norm": 0.12227802723646164, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 1.9979, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.011125374411638854, | |
| "grad_norm": 0.11370483040809631, | |
| "learning_rate": 8.9900861364012e-05, | |
| "loss": 1.9422, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.011296534017971758, | |
| "grad_norm": 0.09835387021303177, | |
| "learning_rate": 8.933724690167417e-05, | |
| "loss": 1.8134, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.011467693624304665, | |
| "grad_norm": 0.11144676804542542, | |
| "learning_rate": 8.876019880555649e-05, | |
| "loss": 2.1119, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.01163885323063757, | |
| "grad_norm": 0.09735066443681717, | |
| "learning_rate": 8.816991413705516e-05, | |
| "loss": 1.827, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.011810012836970476, | |
| "grad_norm": 0.10068103671073914, | |
| "learning_rate": 8.756659447784368e-05, | |
| "loss": 1.8899, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.01198117244330338, | |
| "grad_norm": 0.10140778869390488, | |
| "learning_rate": 8.695044586103296e-05, | |
| "loss": 2.0218, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.012152332049636286, | |
| "grad_norm": 0.0990547463297844, | |
| "learning_rate": 8.632167870081121e-05, | |
| "loss": 1.981, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.012323491655969191, | |
| "grad_norm": 0.1076335459947586, | |
| "learning_rate": 8.568050772058762e-05, | |
| "loss": 1.9312, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.012494651262302097, | |
| "grad_norm": 0.11169704794883728, | |
| "learning_rate": 8.502715187966455e-05, | |
| "loss": 1.9669, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.012665810868635002, | |
| "grad_norm": 0.10578777641057968, | |
| "learning_rate": 8.436183429846313e-05, | |
| "loss": 1.8923, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.012836970474967908, | |
| "grad_norm": 0.1006617322564125, | |
| "learning_rate": 8.368478218232787e-05, | |
| "loss": 1.9088, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.013008130081300813, | |
| "grad_norm": 0.11208891868591309, | |
| "learning_rate": 8.299622674393614e-05, | |
| "loss": 1.9875, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.013179289687633718, | |
| "grad_norm": 0.1086820513010025, | |
| "learning_rate": 8.229640312433937e-05, | |
| "loss": 1.979, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.013350449293966624, | |
| "grad_norm": 0.11209630221128464, | |
| "learning_rate": 8.158555031266254e-05, | |
| "loss": 2.0093, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.013521608900299529, | |
| "grad_norm": 0.1047407016158104, | |
| "learning_rate": 8.086391106448965e-05, | |
| "loss": 2.0194, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.013692768506632435, | |
| "grad_norm": 0.10114631056785583, | |
| "learning_rate": 8.013173181896283e-05, | |
| "loss": 1.9117, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.01386392811296534, | |
| "grad_norm": 0.10660432279109955, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 2.1128, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.014035087719298246, | |
| "grad_norm": 0.10562874376773834, | |
| "learning_rate": 7.863675700402526e-05, | |
| "loss": 1.819, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.01420624732563115, | |
| "grad_norm": 0.1116420328617096, | |
| "learning_rate": 7.787447196714427e-05, | |
| "loss": 2.0161, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.014377406931964057, | |
| "grad_norm": 0.1135152131319046, | |
| "learning_rate": 7.710266782362247e-05, | |
| "loss": 1.9062, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.014548566538296961, | |
| "grad_norm": 0.11426131427288055, | |
| "learning_rate": 7.63216081438678e-05, | |
| "loss": 1.8512, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.014719726144629868, | |
| "grad_norm": 0.11805808544158936, | |
| "learning_rate": 7.553155965904535e-05, | |
| "loss": 1.862, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.014890885750962772, | |
| "grad_norm": 0.11407601833343506, | |
| "learning_rate": 7.473279216998895e-05, | |
| "loss": 1.9902, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.015062045357295679, | |
| "grad_norm": 0.12108225375413895, | |
| "learning_rate": 7.392557845506432e-05, | |
| "loss": 2.0695, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.015233204963628583, | |
| "grad_norm": 0.1370498389005661, | |
| "learning_rate": 7.311019417701566e-05, | |
| "loss": 1.9937, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.01540436456996149, | |
| "grad_norm": 0.13261045515537262, | |
| "learning_rate": 7.228691778882693e-05, | |
| "loss": 1.9162, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.015575524176294394, | |
| "grad_norm": 0.13481606543064117, | |
| "learning_rate": 7.145603043863045e-05, | |
| "loss": 1.7693, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.0157466837826273, | |
| "grad_norm": 0.13738499581813812, | |
| "learning_rate": 7.061781587369519e-05, | |
| "loss": 1.9906, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.015917843388960205, | |
| "grad_norm": 0.14677368104457855, | |
| "learning_rate": 6.977256034352712e-05, | |
| "loss": 1.6928, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.01608900299529311, | |
| "grad_norm": 0.16111257672309875, | |
| "learning_rate": 6.892055250211552e-05, | |
| "loss": 1.9891, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.016260162601626018, | |
| "grad_norm": 0.1692948341369629, | |
| "learning_rate": 6.806208330935766e-05, | |
| "loss": 1.8375, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.016431322207958923, | |
| "grad_norm": 0.21693989634513855, | |
| "learning_rate": 6.719744593169641e-05, | |
| "loss": 1.9869, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.016602481814291827, | |
| "grad_norm": 0.23700051009655, | |
| "learning_rate": 6.632693564200416e-05, | |
| "loss": 2.1276, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.016773641420624732, | |
| "grad_norm": 0.29915517568588257, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 2.3728, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.016944801026957636, | |
| "grad_norm": 0.4070492386817932, | |
| "learning_rate": 6.456948734446624e-05, | |
| "loss": 2.1064, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.017115960633290545, | |
| "grad_norm": 0.7625799775123596, | |
| "learning_rate": 6.368314950360415e-05, | |
| "loss": 2.4645, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.017115960633290545, | |
| "eval_loss": 1.9608962535858154, | |
| "eval_runtime": 254.4528, | |
| "eval_samples_per_second": 38.671, | |
| "eval_steps_per_second": 19.336, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.01728712023962345, | |
| "grad_norm": 0.12267659604549408, | |
| "learning_rate": 6.279213887972179e-05, | |
| "loss": 1.8221, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.017458279845956354, | |
| "grad_norm": 0.11667729169130325, | |
| "learning_rate": 6.189675975213094e-05, | |
| "loss": 1.8163, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.01762943945228926, | |
| "grad_norm": 0.1297779083251953, | |
| "learning_rate": 6.099731789198344e-05, | |
| "loss": 1.8252, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.017800599058622166, | |
| "grad_norm": 0.12183117121458054, | |
| "learning_rate": 6.009412045785051e-05, | |
| "loss": 1.79, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.01797175866495507, | |
| "grad_norm": 0.11510883271694183, | |
| "learning_rate": 5.918747589082853e-05, | |
| "loss": 1.7359, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.018142918271287976, | |
| "grad_norm": 0.11487369984388351, | |
| "learning_rate": 5.82776938092065e-05, | |
| "loss": 1.8322, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.01831407787762088, | |
| "grad_norm": 0.12407288700342178, | |
| "learning_rate": 5.736508490273188e-05, | |
| "loss": 1.9415, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.01848523748395379, | |
| "grad_norm": 0.11880673468112946, | |
| "learning_rate": 5.644996082651017e-05, | |
| "loss": 1.7991, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.018656397090286693, | |
| "grad_norm": 0.12787018716335297, | |
| "learning_rate": 5.553263409457504e-05, | |
| "loss": 1.9157, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.018827556696619598, | |
| "grad_norm": 0.12218679487705231, | |
| "learning_rate": 5.4613417973165106e-05, | |
| "loss": 1.843, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.018998716302952502, | |
| "grad_norm": 0.1273295134305954, | |
| "learning_rate": 5.3692626373743706e-05, | |
| "loss": 1.9732, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.01916987590928541, | |
| "grad_norm": 0.1331591010093689, | |
| "learning_rate": 5.27705737457985e-05, | |
| "loss": 1.9346, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.019341035515618315, | |
| "grad_norm": 0.1283877044916153, | |
| "learning_rate": 5.184757496945726e-05, | |
| "loss": 1.9575, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.01951219512195122, | |
| "grad_norm": 0.11732184886932373, | |
| "learning_rate": 5.092394524795649e-05, | |
| "loss": 1.8368, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.019683354728284124, | |
| "grad_norm": 0.1036926805973053, | |
| "learning_rate": 5e-05, | |
| "loss": 1.7971, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.01985451433461703, | |
| "grad_norm": 0.12696321308612823, | |
| "learning_rate": 4.907605475204352e-05, | |
| "loss": 1.987, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.020025673940949937, | |
| "grad_norm": 0.12035303562879562, | |
| "learning_rate": 4.8152425030542766e-05, | |
| "loss": 2.05, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.02019683354728284, | |
| "grad_norm": 0.09441588819026947, | |
| "learning_rate": 4.72294262542015e-05, | |
| "loss": 1.7966, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.020367993153615746, | |
| "grad_norm": 0.1084362342953682, | |
| "learning_rate": 4.6307373626256306e-05, | |
| "loss": 1.9896, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.02053915275994865, | |
| "grad_norm": 0.10377444326877594, | |
| "learning_rate": 4.5386582026834906e-05, | |
| "loss": 1.9442, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.02071031236628156, | |
| "grad_norm": 0.09699568152427673, | |
| "learning_rate": 4.446736590542497e-05, | |
| "loss": 1.8642, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.020881471972614463, | |
| "grad_norm": 0.10071204602718353, | |
| "learning_rate": 4.3550039173489845e-05, | |
| "loss": 1.9961, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.021052631578947368, | |
| "grad_norm": 0.0921294167637825, | |
| "learning_rate": 4.2634915097268115e-05, | |
| "loss": 1.8438, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.021223791185280273, | |
| "grad_norm": 0.10018813610076904, | |
| "learning_rate": 4.1722306190793495e-05, | |
| "loss": 1.9538, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.02139495079161318, | |
| "grad_norm": 0.09550834447145462, | |
| "learning_rate": 4.0812524109171476e-05, | |
| "loss": 1.8572, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.021566110397946085, | |
| "grad_norm": 0.1069275438785553, | |
| "learning_rate": 3.99058795421495e-05, | |
| "loss": 2.0335, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.02173727000427899, | |
| "grad_norm": 0.1051395982503891, | |
| "learning_rate": 3.9002682108016585e-05, | |
| "loss": 2.0374, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.021908429610611894, | |
| "grad_norm": 0.10209425538778305, | |
| "learning_rate": 3.8103240247869075e-05, | |
| "loss": 1.9306, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.022079589216944803, | |
| "grad_norm": 0.09854423254728317, | |
| "learning_rate": 3.720786112027822e-05, | |
| "loss": 1.9756, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.022250748823277707, | |
| "grad_norm": 0.10003539174795151, | |
| "learning_rate": 3.631685049639586e-05, | |
| "loss": 1.9646, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.022421908429610612, | |
| "grad_norm": 0.10941645503044128, | |
| "learning_rate": 3.543051265553377e-05, | |
| "loss": 2.062, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.022593068035943516, | |
| "grad_norm": 0.1019466444849968, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 1.9037, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.022764227642276424, | |
| "grad_norm": 0.10443319380283356, | |
| "learning_rate": 3.367306435799584e-05, | |
| "loss": 2.0101, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.02293538724860933, | |
| "grad_norm": 0.10645749419927597, | |
| "learning_rate": 3.2802554068303596e-05, | |
| "loss": 1.9192, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.023106546854942234, | |
| "grad_norm": 0.10710829496383667, | |
| "learning_rate": 3.1937916690642356e-05, | |
| "loss": 1.8548, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.02327770646127514, | |
| "grad_norm": 0.11624782532453537, | |
| "learning_rate": 3.107944749788449e-05, | |
| "loss": 1.9397, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.023448866067608043, | |
| "grad_norm": 0.12152379751205444, | |
| "learning_rate": 3.0227439656472877e-05, | |
| "loss": 1.971, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.02362002567394095, | |
| "grad_norm": 0.12296583503484726, | |
| "learning_rate": 2.9382184126304834e-05, | |
| "loss": 1.8179, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.023791185280273856, | |
| "grad_norm": 0.1308358758687973, | |
| "learning_rate": 2.8543969561369556e-05, | |
| "loss": 2.0566, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.02396234488660676, | |
| "grad_norm": 0.12238892912864685, | |
| "learning_rate": 2.771308221117309e-05, | |
| "loss": 2.0106, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.024133504492939665, | |
| "grad_norm": 0.14263762533664703, | |
| "learning_rate": 2.688980582298435e-05, | |
| "loss": 1.8094, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.024304664099272573, | |
| "grad_norm": 0.16151531040668488, | |
| "learning_rate": 2.607442154493568e-05, | |
| "loss": 1.7815, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.024475823705605478, | |
| "grad_norm": 0.17212718725204468, | |
| "learning_rate": 2.5267207830011068e-05, | |
| "loss": 1.977, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.024646983311938382, | |
| "grad_norm": 0.16314253211021423, | |
| "learning_rate": 2.446844034095466e-05, | |
| "loss": 1.8695, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.024818142918271287, | |
| "grad_norm": 0.1866285353899002, | |
| "learning_rate": 2.3678391856132204e-05, | |
| "loss": 1.8092, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.024989302524604195, | |
| "grad_norm": 0.19816122949123383, | |
| "learning_rate": 2.2897332176377528e-05, | |
| "loss": 1.9085, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.0251604621309371, | |
| "grad_norm": 0.2647472023963928, | |
| "learning_rate": 2.2125528032855724e-05, | |
| "loss": 2.0202, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.025331621737270004, | |
| "grad_norm": 0.37373101711273193, | |
| "learning_rate": 2.136324299597474e-05, | |
| "loss": 2.1299, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.02550278134360291, | |
| "grad_norm": 0.43742233514785767, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 2.0061, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.025673940949935817, | |
| "grad_norm": 0.7022097110748291, | |
| "learning_rate": 1.9868268181037185e-05, | |
| "loss": 2.3952, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.025673940949935817, | |
| "eval_loss": 1.9427156448364258, | |
| "eval_runtime": 254.3821, | |
| "eval_samples_per_second": 38.682, | |
| "eval_steps_per_second": 19.341, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.02584510055626872, | |
| "grad_norm": 0.11141515523195267, | |
| "learning_rate": 1.9136088935510362e-05, | |
| "loss": 2.0646, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.026016260162601626, | |
| "grad_norm": 0.10801205039024353, | |
| "learning_rate": 1.8414449687337464e-05, | |
| "loss": 2.085, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.02618741976893453, | |
| "grad_norm": 0.09455177932977676, | |
| "learning_rate": 1.7703596875660645e-05, | |
| "loss": 1.9206, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.026358579375267435, | |
| "grad_norm": 0.08838347345590591, | |
| "learning_rate": 1.700377325606388e-05, | |
| "loss": 1.8645, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.026529738981600343, | |
| "grad_norm": 0.08785195648670197, | |
| "learning_rate": 1.631521781767214e-05, | |
| "loss": 1.7189, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.026700898587933248, | |
| "grad_norm": 0.09213719516992569, | |
| "learning_rate": 1.5638165701536868e-05, | |
| "loss": 1.6594, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.026872058194266153, | |
| "grad_norm": 0.09761328995227814, | |
| "learning_rate": 1.4972848120335453e-05, | |
| "loss": 1.8997, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.027043217800599057, | |
| "grad_norm": 0.09117046743631363, | |
| "learning_rate": 1.4319492279412388e-05, | |
| "loss": 1.8121, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.027214377406931965, | |
| "grad_norm": 0.08685458451509476, | |
| "learning_rate": 1.3678321299188801e-05, | |
| "loss": 1.8085, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.02738553701326487, | |
| "grad_norm": 0.09400554746389389, | |
| "learning_rate": 1.3049554138967051e-05, | |
| "loss": 1.859, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.027556696619597774, | |
| "grad_norm": 0.0903010442852974, | |
| "learning_rate": 1.2433405522156332e-05, | |
| "loss": 1.8646, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.02772785622593068, | |
| "grad_norm": 0.09318774938583374, | |
| "learning_rate": 1.183008586294485e-05, | |
| "loss": 1.9487, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.027899015832263587, | |
| "grad_norm": 0.08630430698394775, | |
| "learning_rate": 1.1239801194443506e-05, | |
| "loss": 1.7142, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.028070175438596492, | |
| "grad_norm": 0.09236445277929306, | |
| "learning_rate": 1.066275309832584e-05, | |
| "loss": 1.8608, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.028241335044929396, | |
| "grad_norm": 0.10190917551517487, | |
| "learning_rate": 1.0099138635988026e-05, | |
| "loss": 2.0014, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.0284124946512623, | |
| "grad_norm": 0.09969731420278549, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 1.8265, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.02858365425759521, | |
| "grad_norm": 0.09843458980321884, | |
| "learning_rate": 9.012975854638949e-06, | |
| "loss": 1.8552, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.028754813863928114, | |
| "grad_norm": 0.0932171493768692, | |
| "learning_rate": 8.490798459222476e-06, | |
| "loss": 1.8805, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.02892597347026102, | |
| "grad_norm": 0.09193925559520721, | |
| "learning_rate": 7.982796418105371e-06, | |
| "loss": 1.8708, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.029097133076593923, | |
| "grad_norm": 0.101052425801754, | |
| "learning_rate": 7.489143213519301e-06, | |
| "loss": 1.9583, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.02926829268292683, | |
| "grad_norm": 0.09988513588905334, | |
| "learning_rate": 7.010007427581378e-06, | |
| "loss": 1.9813, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.029439452289259736, | |
| "grad_norm": 0.09843932092189789, | |
| "learning_rate": 6.5455526847235825e-06, | |
| "loss": 1.9067, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.02961061189559264, | |
| "grad_norm": 0.0977838858962059, | |
| "learning_rate": 6.0959375958151045e-06, | |
| "loss": 1.8711, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.029781771501925545, | |
| "grad_norm": 0.10626049339771271, | |
| "learning_rate": 5.6613157039969055e-06, | |
| "loss": 2.0638, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.02995293110825845, | |
| "grad_norm": 0.09931275993585587, | |
| "learning_rate": 5.241835432246889e-06, | |
| "loss": 1.8416, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.030124090714591358, | |
| "grad_norm": 0.10600997507572174, | |
| "learning_rate": 4.837640032693558e-06, | |
| "loss": 1.9066, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.030295250320924262, | |
| "grad_norm": 0.10138809680938721, | |
| "learning_rate": 4.448867537695578e-06, | |
| "loss": 1.7798, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.030466409927257167, | |
| "grad_norm": 0.10285711288452148, | |
| "learning_rate": 4.075650712703849e-06, | |
| "loss": 1.9305, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.03063756953359007, | |
| "grad_norm": 0.10435103625059128, | |
| "learning_rate": 3.71811701092219e-06, | |
| "loss": 1.7811, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.03080872913992298, | |
| "grad_norm": 0.10847938060760498, | |
| "learning_rate": 3.376388529782215e-06, | |
| "loss": 1.9549, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.030979888746255884, | |
| "grad_norm": 0.10423749685287476, | |
| "learning_rate": 3.0505819692471792e-06, | |
| "loss": 1.7917, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.03115104835258879, | |
| "grad_norm": 0.11017204076051712, | |
| "learning_rate": 2.7408085919590264e-06, | |
| "loss": 1.9272, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.0313222079589217, | |
| "grad_norm": 0.11599629372358322, | |
| "learning_rate": 2.4471741852423237e-06, | |
| "loss": 1.8393, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.0314933675652546, | |
| "grad_norm": 0.10840439796447754, | |
| "learning_rate": 2.1697790249779636e-06, | |
| "loss": 1.9099, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.031664527171587506, | |
| "grad_norm": 0.12284722179174423, | |
| "learning_rate": 1.908717841359048e-06, | |
| "loss": 2.0558, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.03183568677792041, | |
| "grad_norm": 0.11635725945234299, | |
| "learning_rate": 1.6640797865406288e-06, | |
| "loss": 1.9249, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.032006846384253315, | |
| "grad_norm": 0.1333126574754715, | |
| "learning_rate": 1.4359484041943038e-06, | |
| "loss": 1.9864, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.03217800599058622, | |
| "grad_norm": 0.13437993824481964, | |
| "learning_rate": 1.2244016009781701e-06, | |
| "loss": 1.9203, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.032349165596919124, | |
| "grad_norm": 0.12741129100322723, | |
| "learning_rate": 1.0295116199317057e-06, | |
| "loss": 1.8627, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.032520325203252036, | |
| "grad_norm": 0.13912999629974365, | |
| "learning_rate": 8.513450158049108e-07, | |
| "loss": 1.8976, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.03269148480958494, | |
| "grad_norm": 0.1495036631822586, | |
| "learning_rate": 6.899626323298713e-07, | |
| "loss": 1.9268, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.032862644415917845, | |
| "grad_norm": 0.14511996507644653, | |
| "learning_rate": 5.454195814427021e-07, | |
| "loss": 1.9895, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.03303380402225075, | |
| "grad_norm": 0.1583525389432907, | |
| "learning_rate": 4.177652244628627e-07, | |
| "loss": 2.0931, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.033204963628583654, | |
| "grad_norm": 0.16893316805362701, | |
| "learning_rate": 3.0704315523631953e-07, | |
| "loss": 1.9645, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.03337612323491656, | |
| "grad_norm": 0.19505704939365387, | |
| "learning_rate": 2.1329118524827662e-07, | |
| "loss": 1.6557, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.033547282841249464, | |
| "grad_norm": 0.20835180580615997, | |
| "learning_rate": 1.3654133071059893e-07, | |
| "loss": 1.7806, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.03371844244758237, | |
| "grad_norm": 0.23454757034778595, | |
| "learning_rate": 7.681980162830282e-08, | |
| "loss": 1.9318, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.03388960205391527, | |
| "grad_norm": 0.2649778425693512, | |
| "learning_rate": 3.4146992848854695e-08, | |
| "loss": 1.9983, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.034060761660248184, | |
| "grad_norm": 0.3988756537437439, | |
| "learning_rate": 8.537477097364522e-09, | |
| "loss": 2.2859, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.03423192126658109, | |
| "grad_norm": 0.5916358828544617, | |
| "learning_rate": 0.0, | |
| "loss": 2.5445, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.03423192126658109, | |
| "eval_loss": 1.942334532737732, | |
| "eval_runtime": 253.457, | |
| "eval_samples_per_second": 38.823, | |
| "eval_steps_per_second": 19.412, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7688467500761088.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |