| { | |
| "best_metric": 0.40124958753585815, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-75", | |
| "epoch": 0.41428182065958025, | |
| "eval_steps": 25, | |
| "global_step": 95, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004360861270100845, | |
| "grad_norm": 1.4162043333053589, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 1.9815, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004360861270100845, | |
| "eval_loss": 1.9722100496292114, | |
| "eval_runtime": 3.4515, | |
| "eval_samples_per_second": 14.487, | |
| "eval_steps_per_second": 3.766, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00872172254020169, | |
| "grad_norm": 1.6828759908676147, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 1.884, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.013082583810302535, | |
| "grad_norm": 1.6402842998504639, | |
| "learning_rate": 0.0001, | |
| "loss": 1.8683, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01744344508040338, | |
| "grad_norm": 1.4667969942092896, | |
| "learning_rate": 9.997376600647783e-05, | |
| "loss": 1.6945, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.021804306350504225, | |
| "grad_norm": 1.5014039278030396, | |
| "learning_rate": 9.989509461357426e-05, | |
| "loss": 1.4234, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02616516762060507, | |
| "grad_norm": 1.6926089525222778, | |
| "learning_rate": 9.976407754861426e-05, | |
| "loss": 1.3236, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.030526028890705915, | |
| "grad_norm": 1.386367917060852, | |
| "learning_rate": 9.958086757163489e-05, | |
| "loss": 1.2198, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.03488689016080676, | |
| "grad_norm": 1.5338332653045654, | |
| "learning_rate": 9.934567829727386e-05, | |
| "loss": 1.1274, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.039247751430907606, | |
| "grad_norm": 1.147320032119751, | |
| "learning_rate": 9.905878394570453e-05, | |
| "loss": 1.0782, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.04360861270100845, | |
| "grad_norm": 1.1993285417556763, | |
| "learning_rate": 9.872051902290737e-05, | |
| "loss": 1.0573, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.047969473971109296, | |
| "grad_norm": 0.9545571804046631, | |
| "learning_rate": 9.833127793065098e-05, | |
| "loss": 1.0225, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.05233033524121014, | |
| "grad_norm": 1.2719054222106934, | |
| "learning_rate": 9.789151450663723e-05, | |
| "loss": 1.0316, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.056691196511310986, | |
| "grad_norm": 1.822263240814209, | |
| "learning_rate": 9.740174149534693e-05, | |
| "loss": 1.4566, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.06105205778141183, | |
| "grad_norm": 1.4125415086746216, | |
| "learning_rate": 9.686252995020249e-05, | |
| "loss": 1.0581, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.06541291905151267, | |
| "grad_norm": 0.9527837038040161, | |
| "learning_rate": 9.627450856774539e-05, | |
| "loss": 0.9584, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.06977378032161352, | |
| "grad_norm": 0.7775830030441284, | |
| "learning_rate": 9.563836295460398e-05, | |
| "loss": 0.8586, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.07413464159171436, | |
| "grad_norm": 0.8475672006607056, | |
| "learning_rate": 9.495483482810688e-05, | |
| "loss": 0.8498, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.07849550286181521, | |
| "grad_norm": 0.7431860566139221, | |
| "learning_rate": 9.422472115147382e-05, | |
| "loss": 0.8207, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.08285636413191605, | |
| "grad_norm": 0.7454464435577393, | |
| "learning_rate": 9.3448873204592e-05, | |
| "loss": 0.7613, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0872172254020169, | |
| "grad_norm": 0.5694941282272339, | |
| "learning_rate": 9.2628195591462e-05, | |
| "loss": 0.7577, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09157808667211774, | |
| "grad_norm": 0.6122721433639526, | |
| "learning_rate": 9.176364518546989e-05, | |
| "loss": 0.7087, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.09593894794221859, | |
| "grad_norm": 0.6561219096183777, | |
| "learning_rate": 9.08562300137157e-05, | |
| "loss": 0.6813, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.10029980921231943, | |
| "grad_norm": 0.7273951172828674, | |
| "learning_rate": 8.990700808169889e-05, | |
| "loss": 0.6749, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.10466067048242028, | |
| "grad_norm": 0.8688530325889587, | |
| "learning_rate": 8.891708613973126e-05, | |
| "loss": 0.7452, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.10902153175252112, | |
| "grad_norm": 1.0595729351043701, | |
| "learning_rate": 8.788761839251559e-05, | |
| "loss": 0.7305, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.10902153175252112, | |
| "eval_loss": 0.6566603779792786, | |
| "eval_runtime": 3.4727, | |
| "eval_samples_per_second": 14.398, | |
| "eval_steps_per_second": 3.743, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.11338239302262197, | |
| "grad_norm": 0.778566837310791, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 1.1322, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.11774325429272281, | |
| "grad_norm": 0.8664071559906006, | |
| "learning_rate": 8.571489144483944e-05, | |
| "loss": 0.752, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.12210411556282366, | |
| "grad_norm": 0.6241268515586853, | |
| "learning_rate": 8.457416554680877e-05, | |
| "loss": 0.6844, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.1264649768329245, | |
| "grad_norm": 0.6717398762702942, | |
| "learning_rate": 8.339895749467238e-05, | |
| "loss": 0.6473, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.13082583810302534, | |
| "grad_norm": 0.5530563592910767, | |
| "learning_rate": 8.219063752844926e-05, | |
| "loss": 0.6269, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.1351866993731262, | |
| "grad_norm": 0.5983289480209351, | |
| "learning_rate": 8.095061449516903e-05, | |
| "loss": 0.6019, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.13954756064322704, | |
| "grad_norm": 0.5961953997612, | |
| "learning_rate": 7.968033420621935e-05, | |
| "loss": 0.5898, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.1439084219133279, | |
| "grad_norm": 0.590516209602356, | |
| "learning_rate": 7.838127775159452e-05, | |
| "loss": 0.572, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.14826928318342872, | |
| "grad_norm": 0.6140605807304382, | |
| "learning_rate": 7.705495977301078e-05, | |
| "loss": 0.5329, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.15263014445352957, | |
| "grad_norm": 0.6244949698448181, | |
| "learning_rate": 7.570292669790186e-05, | |
| "loss": 0.5514, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.15699100572363042, | |
| "grad_norm": 0.5919716358184814, | |
| "learning_rate": 7.43267549363537e-05, | |
| "loss": 0.579, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.16135186699373127, | |
| "grad_norm": 0.7726537585258484, | |
| "learning_rate": 7.292804904308087e-05, | |
| "loss": 0.6014, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.1657127282638321, | |
| "grad_norm": 0.7387896776199341, | |
| "learning_rate": 7.150843984658754e-05, | |
| "loss": 0.923, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.17007358953393295, | |
| "grad_norm": 0.9935781955718994, | |
| "learning_rate": 7.006958254769438e-05, | |
| "loss": 0.7171, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.1744344508040338, | |
| "grad_norm": 0.8386249542236328, | |
| "learning_rate": 6.861315478964841e-05, | |
| "loss": 0.6152, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.17879531207413465, | |
| "grad_norm": 0.7667595148086548, | |
| "learning_rate": 6.714085470206609e-05, | |
| "loss": 0.5648, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.18315617334423548, | |
| "grad_norm": 0.8341333866119385, | |
| "learning_rate": 6.56543989209901e-05, | |
| "loss": 0.562, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.18751703461433633, | |
| "grad_norm": 0.6490123867988586, | |
| "learning_rate": 6.415552058736854e-05, | |
| "loss": 0.5345, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.19187789588443718, | |
| "grad_norm": 0.6377322673797607, | |
| "learning_rate": 6.264596732629e-05, | |
| "loss": 0.522, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.19623875715453803, | |
| "grad_norm": 0.5122985243797302, | |
| "learning_rate": 6.112749920933111e-05, | |
| "loss": 0.5147, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.20059961842463886, | |
| "grad_norm": 0.5034750699996948, | |
| "learning_rate": 5.960188670239154e-05, | |
| "loss": 0.503, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.2049604796947397, | |
| "grad_norm": 0.6066300272941589, | |
| "learning_rate": 5.80709086014102e-05, | |
| "loss": 0.4834, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.20932134096484056, | |
| "grad_norm": 0.6627282500267029, | |
| "learning_rate": 5.653634995836856e-05, | |
| "loss": 0.4824, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.2136822022349414, | |
| "grad_norm": 0.7109618186950684, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.5475, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.21804306350504224, | |
| "grad_norm": 0.8429147005081177, | |
| "learning_rate": 5.346365004163145e-05, | |
| "loss": 0.4999, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.21804306350504224, | |
| "eval_loss": 0.4795617163181305, | |
| "eval_runtime": 3.5056, | |
| "eval_samples_per_second": 14.263, | |
| "eval_steps_per_second": 3.708, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.2224039247751431, | |
| "grad_norm": 0.6727418899536133, | |
| "learning_rate": 5.192909139858981e-05, | |
| "loss": 0.7924, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.22676478604524394, | |
| "grad_norm": 0.5870447754859924, | |
| "learning_rate": 5.0398113297608465e-05, | |
| "loss": 0.5484, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.23112564731534477, | |
| "grad_norm": 0.546592652797699, | |
| "learning_rate": 4.887250079066892e-05, | |
| "loss": 0.5412, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.23548650858544562, | |
| "grad_norm": 0.7132319808006287, | |
| "learning_rate": 4.7354032673710005e-05, | |
| "loss": 0.5051, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.23984736985554647, | |
| "grad_norm": 0.7168745398521423, | |
| "learning_rate": 4.584447941263149e-05, | |
| "loss": 0.466, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.24420823112564732, | |
| "grad_norm": 0.7022103071212769, | |
| "learning_rate": 4.43456010790099e-05, | |
| "loss": 0.4795, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.24856909239574815, | |
| "grad_norm": 0.6773548722267151, | |
| "learning_rate": 4.285914529793391e-05, | |
| "loss": 0.4817, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.252929953665849, | |
| "grad_norm": 0.5745356678962708, | |
| "learning_rate": 4.13868452103516e-05, | |
| "loss": 0.4766, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.25729081493594985, | |
| "grad_norm": 0.5579826831817627, | |
| "learning_rate": 3.9930417452305626e-05, | |
| "loss": 0.4345, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.2616516762060507, | |
| "grad_norm": 0.4558126628398895, | |
| "learning_rate": 3.8491560153412466e-05, | |
| "loss": 0.4209, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.26601253747615156, | |
| "grad_norm": 0.4706413745880127, | |
| "learning_rate": 3.707195095691913e-05, | |
| "loss": 0.4361, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.2703733987462524, | |
| "grad_norm": 0.5550121068954468, | |
| "learning_rate": 3.567324506364632e-05, | |
| "loss": 0.4485, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.2747342600163532, | |
| "grad_norm": 0.5833269953727722, | |
| "learning_rate": 3.4297073302098156e-05, | |
| "loss": 0.7047, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.2790951212864541, | |
| "grad_norm": 0.6641823649406433, | |
| "learning_rate": 3.2945040226989244e-05, | |
| "loss": 0.5205, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.2834559825565549, | |
| "grad_norm": 0.5642077922821045, | |
| "learning_rate": 3.16187222484055e-05, | |
| "loss": 0.5079, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.2878168438266558, | |
| "grad_norm": 0.5852211117744446, | |
| "learning_rate": 3.0319665793780648e-05, | |
| "loss": 0.4548, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.2921777050967566, | |
| "grad_norm": 0.5873813033103943, | |
| "learning_rate": 2.9049385504830985e-05, | |
| "loss": 0.454, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.29653856636685744, | |
| "grad_norm": 0.47973552346229553, | |
| "learning_rate": 2.7809362471550748e-05, | |
| "loss": 0.4232, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.3008994276369583, | |
| "grad_norm": 0.41929492354393005, | |
| "learning_rate": 2.660104250532764e-05, | |
| "loss": 0.4246, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.30526028890705914, | |
| "grad_norm": 0.4503474235534668, | |
| "learning_rate": 2.5425834453191232e-05, | |
| "loss": 0.4261, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.30962115017715997, | |
| "grad_norm": 0.44094038009643555, | |
| "learning_rate": 2.4285108555160577e-05, | |
| "loss": 0.4246, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.31398201144726084, | |
| "grad_norm": 0.4602739214897156, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.4, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.31834287271736167, | |
| "grad_norm": 0.4867585003376007, | |
| "learning_rate": 2.2112381607484417e-05, | |
| "loss": 0.3963, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.32270373398746255, | |
| "grad_norm": 0.6144199967384338, | |
| "learning_rate": 2.1082913860268765e-05, | |
| "loss": 0.4422, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.3270645952575634, | |
| "grad_norm": 0.7098694443702698, | |
| "learning_rate": 2.0092991918301108e-05, | |
| "loss": 0.4032, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.3270645952575634, | |
| "eval_loss": 0.40124958753585815, | |
| "eval_runtime": 3.4941, | |
| "eval_samples_per_second": 14.31, | |
| "eval_steps_per_second": 3.721, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.3314254565276642, | |
| "grad_norm": 0.48104754090309143, | |
| "learning_rate": 1.91437699862843e-05, | |
| "loss": 0.6608, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.3357863177977651, | |
| "grad_norm": 0.43779367208480835, | |
| "learning_rate": 1.8236354814530112e-05, | |
| "loss": 0.4484, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.3401471790678659, | |
| "grad_norm": 0.4079342186450958, | |
| "learning_rate": 1.7371804408538024e-05, | |
| "loss": 0.4617, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.3445080403379667, | |
| "grad_norm": 0.4270339012145996, | |
| "learning_rate": 1.6551126795408016e-05, | |
| "loss": 0.4245, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.3488689016080676, | |
| "grad_norm": 0.4463932514190674, | |
| "learning_rate": 1.577527884852619e-05, | |
| "loss": 0.3953, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.35322976287816843, | |
| "grad_norm": 0.4444558024406433, | |
| "learning_rate": 1.5045165171893116e-05, | |
| "loss": 0.3951, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.3575906241482693, | |
| "grad_norm": 0.4303630590438843, | |
| "learning_rate": 1.4361637045396029e-05, | |
| "loss": 0.4199, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.36195148541837013, | |
| "grad_norm": 0.4083124101161957, | |
| "learning_rate": 1.3725491432254624e-05, | |
| "loss": 0.3978, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.36631234668847096, | |
| "grad_norm": 0.41896235942840576, | |
| "learning_rate": 1.313747004979751e-05, | |
| "loss": 0.3749, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.37067320795857184, | |
| "grad_norm": 0.44455498456954956, | |
| "learning_rate": 1.2598258504653081e-05, | |
| "loss": 0.3634, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.37503406922867266, | |
| "grad_norm": 0.46264758706092834, | |
| "learning_rate": 1.2108485493362765e-05, | |
| "loss": 0.3572, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.3793949304987735, | |
| "grad_norm": 0.5216580629348755, | |
| "learning_rate": 1.1668722069349041e-05, | |
| "loss": 0.3992, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.38375579176887437, | |
| "grad_norm": 0.48434847593307495, | |
| "learning_rate": 1.1279480977092635e-05, | |
| "loss": 0.6502, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.3881166530389752, | |
| "grad_norm": 0.50812166929245, | |
| "learning_rate": 1.094121605429547e-05, | |
| "loss": 0.4916, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.39247751430907607, | |
| "grad_norm": 0.4391539692878723, | |
| "learning_rate": 1.0654321702726141e-05, | |
| "loss": 0.4395, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.3968383755791769, | |
| "grad_norm": 0.3883734345436096, | |
| "learning_rate": 1.0419132428365116e-05, | |
| "loss": 0.3915, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.4011992368492777, | |
| "grad_norm": 0.39511629939079285, | |
| "learning_rate": 1.0235922451385733e-05, | |
| "loss": 0.3902, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.4055600981193786, | |
| "grad_norm": 0.3681911528110504, | |
| "learning_rate": 1.0104905386425733e-05, | |
| "loss": 0.3975, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.4099209593894794, | |
| "grad_norm": 0.40158364176750183, | |
| "learning_rate": 1.002623399352217e-05, | |
| "loss": 0.378, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.41428182065958025, | |
| "grad_norm": 0.41014018654823303, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3961, | |
| "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": 1.1339358872902042e+18, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |