| { | |
| "best_metric": 10.120731353759766, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-75", | |
| "epoch": 0.0784698381559588, | |
| "eval_steps": 25, | |
| "global_step": 95, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0008259982963785137, | |
| "grad_norm": 2.0049455165863037, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 10.4083, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008259982963785137, | |
| "eval_loss": 10.408509254455566, | |
| "eval_runtime": 0.0875, | |
| "eval_samples_per_second": 571.634, | |
| "eval_steps_per_second": 148.625, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0016519965927570275, | |
| "grad_norm": 2.179474353790283, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 10.4113, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.002477994889135541, | |
| "grad_norm": 2.175949811935425, | |
| "learning_rate": 0.0001, | |
| "loss": 10.4098, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.003303993185514055, | |
| "grad_norm": 2.198148727416992, | |
| "learning_rate": 9.997376600647783e-05, | |
| "loss": 10.4048, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.004129991481892569, | |
| "grad_norm": 2.311675786972046, | |
| "learning_rate": 9.989509461357426e-05, | |
| "loss": 10.3889, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004955989778271082, | |
| "grad_norm": 2.2244744300842285, | |
| "learning_rate": 9.976407754861426e-05, | |
| "loss": 10.3927, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0057819880746495965, | |
| "grad_norm": 2.1905970573425293, | |
| "learning_rate": 9.958086757163489e-05, | |
| "loss": 10.3866, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00660798637102811, | |
| "grad_norm": 2.265380382537842, | |
| "learning_rate": 9.934567829727386e-05, | |
| "loss": 10.3733, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.007433984667406623, | |
| "grad_norm": 2.2335805892944336, | |
| "learning_rate": 9.905878394570453e-05, | |
| "loss": 10.3708, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.008259982963785138, | |
| "grad_norm": 2.362139940261841, | |
| "learning_rate": 9.872051902290737e-05, | |
| "loss": 10.3559, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.009085981260163651, | |
| "grad_norm": 2.3152475357055664, | |
| "learning_rate": 9.833127793065098e-05, | |
| "loss": 10.3528, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.009911979556542164, | |
| "grad_norm": 2.405902862548828, | |
| "learning_rate": 9.789151450663723e-05, | |
| "loss": 10.3386, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.010737977852920678, | |
| "grad_norm": 2.1402595043182373, | |
| "learning_rate": 9.740174149534693e-05, | |
| "loss": 10.3336, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.011563976149299193, | |
| "grad_norm": 2.381272554397583, | |
| "learning_rate": 9.686252995020249e-05, | |
| "loss": 10.3285, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.012389974445677706, | |
| "grad_norm": 2.366549253463745, | |
| "learning_rate": 9.627450856774539e-05, | |
| "loss": 10.3286, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01321597274205622, | |
| "grad_norm": 2.4747745990753174, | |
| "learning_rate": 9.563836295460398e-05, | |
| "loss": 10.3114, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.014041971038434733, | |
| "grad_norm": 2.4576263427734375, | |
| "learning_rate": 9.495483482810688e-05, | |
| "loss": 10.3009, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.014867969334813247, | |
| "grad_norm": 2.40720796585083, | |
| "learning_rate": 9.422472115147382e-05, | |
| "loss": 10.3011, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.01569396763119176, | |
| "grad_norm": 2.371147632598877, | |
| "learning_rate": 9.3448873204592e-05, | |
| "loss": 10.2897, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.016519965927570275, | |
| "grad_norm": 2.4059886932373047, | |
| "learning_rate": 9.2628195591462e-05, | |
| "loss": 10.2798, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01734596422394879, | |
| "grad_norm": 2.3397157192230225, | |
| "learning_rate": 9.176364518546989e-05, | |
| "loss": 10.2792, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.018171962520327302, | |
| "grad_norm": 2.338066339492798, | |
| "learning_rate": 9.08562300137157e-05, | |
| "loss": 10.2679, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.018997960816705815, | |
| "grad_norm": 2.3059072494506836, | |
| "learning_rate": 8.990700808169889e-05, | |
| "loss": 10.2628, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.01982395911308433, | |
| "grad_norm": 2.2808313369750977, | |
| "learning_rate": 8.891708613973126e-05, | |
| "loss": 10.2387, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.020649957409462842, | |
| "grad_norm": 2.230339288711548, | |
| "learning_rate": 8.788761839251559e-05, | |
| "loss": 10.2504, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.020649957409462842, | |
| "eval_loss": 10.22501277923584, | |
| "eval_runtime": 0.0811, | |
| "eval_samples_per_second": 616.479, | |
| "eval_steps_per_second": 160.285, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.021475955705841356, | |
| "grad_norm": 2.095871925354004, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 10.2329, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.02230195400221987, | |
| "grad_norm": 2.1666860580444336, | |
| "learning_rate": 8.571489144483944e-05, | |
| "loss": 10.23, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.023127952298598386, | |
| "grad_norm": 2.0563714504241943, | |
| "learning_rate": 8.457416554680877e-05, | |
| "loss": 10.2225, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0239539505949769, | |
| "grad_norm": 1.9848387241363525, | |
| "learning_rate": 8.339895749467238e-05, | |
| "loss": 10.2097, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.024779948891355413, | |
| "grad_norm": 1.9532544612884521, | |
| "learning_rate": 8.219063752844926e-05, | |
| "loss": 10.2035, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.025605947187733926, | |
| "grad_norm": 1.8774293661117554, | |
| "learning_rate": 8.095061449516903e-05, | |
| "loss": 10.2052, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.02643194548411244, | |
| "grad_norm": 1.7850217819213867, | |
| "learning_rate": 7.968033420621935e-05, | |
| "loss": 10.1989, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.027257943780490953, | |
| "grad_norm": 1.806624174118042, | |
| "learning_rate": 7.838127775159452e-05, | |
| "loss": 10.2075, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.028083942076869466, | |
| "grad_norm": 1.6620304584503174, | |
| "learning_rate": 7.705495977301078e-05, | |
| "loss": 10.1921, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.02890994037324798, | |
| "grad_norm": 1.6251369714736938, | |
| "learning_rate": 7.570292669790186e-05, | |
| "loss": 10.1959, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.029735938669626493, | |
| "grad_norm": 1.5146149396896362, | |
| "learning_rate": 7.43267549363537e-05, | |
| "loss": 10.1807, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.030561936966005007, | |
| "grad_norm": 1.4646108150482178, | |
| "learning_rate": 7.292804904308087e-05, | |
| "loss": 10.1794, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.03138793526238352, | |
| "grad_norm": 1.3250266313552856, | |
| "learning_rate": 7.150843984658754e-05, | |
| "loss": 10.1936, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.03221393355876204, | |
| "grad_norm": 1.303118109703064, | |
| "learning_rate": 7.006958254769438e-05, | |
| "loss": 10.1736, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.03303993185514055, | |
| "grad_norm": 1.2237043380737305, | |
| "learning_rate": 6.861315478964841e-05, | |
| "loss": 10.1605, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.033865930151519064, | |
| "grad_norm": 1.1835358142852783, | |
| "learning_rate": 6.714085470206609e-05, | |
| "loss": 10.166, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.03469192844789758, | |
| "grad_norm": 1.0976448059082031, | |
| "learning_rate": 6.56543989209901e-05, | |
| "loss": 10.1594, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.03551792674427609, | |
| "grad_norm": 1.0374468564987183, | |
| "learning_rate": 6.415552058736854e-05, | |
| "loss": 10.1597, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.036343925040654604, | |
| "grad_norm": 0.9736471176147461, | |
| "learning_rate": 6.264596732629e-05, | |
| "loss": 10.1546, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.03716992333703312, | |
| "grad_norm": 0.9557368755340576, | |
| "learning_rate": 6.112749920933111e-05, | |
| "loss": 10.1595, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.03799592163341163, | |
| "grad_norm": 0.9107280969619751, | |
| "learning_rate": 5.960188670239154e-05, | |
| "loss": 10.1645, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.038821919929790144, | |
| "grad_norm": 0.8153705596923828, | |
| "learning_rate": 5.80709086014102e-05, | |
| "loss": 10.1512, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.03964791822616866, | |
| "grad_norm": 0.7683850526809692, | |
| "learning_rate": 5.653634995836856e-05, | |
| "loss": 10.1547, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.04047391652254717, | |
| "grad_norm": 0.7185543179512024, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 10.144, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.041299914818925684, | |
| "grad_norm": 0.671612024307251, | |
| "learning_rate": 5.346365004163145e-05, | |
| "loss": 10.1444, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.041299914818925684, | |
| "eval_loss": 10.138866424560547, | |
| "eval_runtime": 0.0814, | |
| "eval_samples_per_second": 614.338, | |
| "eval_steps_per_second": 159.728, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0421259131153042, | |
| "grad_norm": 0.6381344199180603, | |
| "learning_rate": 5.192909139858981e-05, | |
| "loss": 10.1596, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.04295191141168271, | |
| "grad_norm": 0.6048315167427063, | |
| "learning_rate": 5.0398113297608465e-05, | |
| "loss": 10.1464, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.043777909708061225, | |
| "grad_norm": 0.5989148020744324, | |
| "learning_rate": 4.887250079066892e-05, | |
| "loss": 10.1373, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.04460390800443974, | |
| "grad_norm": 0.5282235145568848, | |
| "learning_rate": 4.7354032673710005e-05, | |
| "loss": 10.1422, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.04542990630081825, | |
| "grad_norm": 0.5445945858955383, | |
| "learning_rate": 4.584447941263149e-05, | |
| "loss": 10.1465, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.04625590459719677, | |
| "grad_norm": 0.528545618057251, | |
| "learning_rate": 4.43456010790099e-05, | |
| "loss": 10.1424, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.047081902893575285, | |
| "grad_norm": 0.5194099545478821, | |
| "learning_rate": 4.285914529793391e-05, | |
| "loss": 10.1398, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.0479079011899538, | |
| "grad_norm": 0.489889532327652, | |
| "learning_rate": 4.13868452103516e-05, | |
| "loss": 10.1429, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.04873389948633231, | |
| "grad_norm": 0.49389705061912537, | |
| "learning_rate": 3.9930417452305626e-05, | |
| "loss": 10.1465, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.049559897782710825, | |
| "grad_norm": 0.475475549697876, | |
| "learning_rate": 3.8491560153412466e-05, | |
| "loss": 10.1475, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.05038589607908934, | |
| "grad_norm": 0.50710529088974, | |
| "learning_rate": 3.707195095691913e-05, | |
| "loss": 10.1394, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.05121189437546785, | |
| "grad_norm": 0.5150895118713379, | |
| "learning_rate": 3.567324506364632e-05, | |
| "loss": 10.1326, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.052037892671846366, | |
| "grad_norm": 0.4752042591571808, | |
| "learning_rate": 3.4297073302098156e-05, | |
| "loss": 10.145, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.05286389096822488, | |
| "grad_norm": 0.4911608099937439, | |
| "learning_rate": 3.2945040226989244e-05, | |
| "loss": 10.1347, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.05368988926460339, | |
| "grad_norm": 0.5078980326652527, | |
| "learning_rate": 3.16187222484055e-05, | |
| "loss": 10.1343, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.054515887560981906, | |
| "grad_norm": 0.47904160618782043, | |
| "learning_rate": 3.0319665793780648e-05, | |
| "loss": 10.1393, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.05534188585736042, | |
| "grad_norm": 0.48951855301856995, | |
| "learning_rate": 2.9049385504830985e-05, | |
| "loss": 10.1393, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.05616788415373893, | |
| "grad_norm": 0.5052370429039001, | |
| "learning_rate": 2.7809362471550748e-05, | |
| "loss": 10.1344, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.056993882450117446, | |
| "grad_norm": 0.5891403555870056, | |
| "learning_rate": 2.660104250532764e-05, | |
| "loss": 10.1356, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.05781988074649596, | |
| "grad_norm": 0.5263543725013733, | |
| "learning_rate": 2.5425834453191232e-05, | |
| "loss": 10.133, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.05864587904287447, | |
| "grad_norm": 0.5553152561187744, | |
| "learning_rate": 2.4285108555160577e-05, | |
| "loss": 10.1311, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.059471877339252986, | |
| "grad_norm": 0.5369566679000854, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 10.136, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.0602978756356315, | |
| "grad_norm": 0.5451551079750061, | |
| "learning_rate": 2.2112381607484417e-05, | |
| "loss": 10.1372, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.06112387393201001, | |
| "grad_norm": 0.5561919808387756, | |
| "learning_rate": 2.1082913860268765e-05, | |
| "loss": 10.1302, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.061949872228388526, | |
| "grad_norm": 0.5314218401908875, | |
| "learning_rate": 2.0092991918301108e-05, | |
| "loss": 10.1341, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.061949872228388526, | |
| "eval_loss": 10.120731353759766, | |
| "eval_runtime": 0.0806, | |
| "eval_samples_per_second": 620.248, | |
| "eval_steps_per_second": 161.265, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.06277587052476705, | |
| "grad_norm": 0.571367084980011, | |
| "learning_rate": 1.91437699862843e-05, | |
| "loss": 10.1587, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.06360186882114556, | |
| "grad_norm": 0.5579727292060852, | |
| "learning_rate": 1.8236354814530112e-05, | |
| "loss": 10.1315, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.06442786711752407, | |
| "grad_norm": 0.53849196434021, | |
| "learning_rate": 1.7371804408538024e-05, | |
| "loss": 10.1338, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.06525386541390259, | |
| "grad_norm": 0.5967963933944702, | |
| "learning_rate": 1.6551126795408016e-05, | |
| "loss": 10.1301, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.0660798637102811, | |
| "grad_norm": 0.6654343605041504, | |
| "learning_rate": 1.577527884852619e-05, | |
| "loss": 10.1243, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.06690586200665961, | |
| "grad_norm": 0.5864200592041016, | |
| "learning_rate": 1.5045165171893116e-05, | |
| "loss": 10.1273, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.06773186030303813, | |
| "grad_norm": 0.6068311333656311, | |
| "learning_rate": 1.4361637045396029e-05, | |
| "loss": 10.1283, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.06855785859941664, | |
| "grad_norm": 0.7365639209747314, | |
| "learning_rate": 1.3725491432254624e-05, | |
| "loss": 10.1191, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.06938385689579515, | |
| "grad_norm": 0.6029481887817383, | |
| "learning_rate": 1.313747004979751e-05, | |
| "loss": 10.1285, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.07020985519217367, | |
| "grad_norm": 0.6578642725944519, | |
| "learning_rate": 1.2598258504653081e-05, | |
| "loss": 10.1292, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.07103585348855218, | |
| "grad_norm": 0.6517241597175598, | |
| "learning_rate": 1.2108485493362765e-05, | |
| "loss": 10.1258, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.0718618517849307, | |
| "grad_norm": 0.6244571208953857, | |
| "learning_rate": 1.1668722069349041e-05, | |
| "loss": 10.1278, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.07268785008130921, | |
| "grad_norm": 0.6095861196517944, | |
| "learning_rate": 1.1279480977092635e-05, | |
| "loss": 10.1302, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.07351384837768772, | |
| "grad_norm": 0.6624661684036255, | |
| "learning_rate": 1.094121605429547e-05, | |
| "loss": 10.1233, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.07433984667406623, | |
| "grad_norm": 0.6090475916862488, | |
| "learning_rate": 1.0654321702726141e-05, | |
| "loss": 10.1331, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.07516584497044475, | |
| "grad_norm": 0.61402827501297, | |
| "learning_rate": 1.0419132428365116e-05, | |
| "loss": 10.1266, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.07599184326682326, | |
| "grad_norm": 0.6416760683059692, | |
| "learning_rate": 1.0235922451385733e-05, | |
| "loss": 10.1324, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.07681784156320177, | |
| "grad_norm": 0.6449143886566162, | |
| "learning_rate": 1.0104905386425733e-05, | |
| "loss": 10.1238, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.07764383985958029, | |
| "grad_norm": 0.6034808158874512, | |
| "learning_rate": 1.002623399352217e-05, | |
| "loss": 10.1313, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.0784698381559588, | |
| "grad_norm": 0.6877067685127258, | |
| "learning_rate": 1e-05, | |
| "loss": 10.132, | |
| "step": 95 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 95, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "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": 81259313233920.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |