{ "best_metric": 10.327804565429688, "best_model_checkpoint": "miner_id_24/checkpoint-200", "epoch": 0.019126401606617736, "eval_steps": 50, "global_step": 200, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 9.563200803308868e-05, "grad_norm": 0.0969449058175087, "learning_rate": 1e-05, "loss": 10.3776, "step": 1 }, { "epoch": 9.563200803308868e-05, "eval_loss": 10.378722190856934, "eval_runtime": 35.5755, "eval_samples_per_second": 495.06, "eval_steps_per_second": 123.765, "step": 1 }, { "epoch": 0.00019126401606617735, "grad_norm": 0.09233276546001434, "learning_rate": 2e-05, "loss": 10.3788, "step": 2 }, { "epoch": 0.000286896024099266, "grad_norm": 0.09521631896495819, "learning_rate": 3e-05, "loss": 10.3779, "step": 3 }, { "epoch": 0.0003825280321323547, "grad_norm": 0.09074452519416809, "learning_rate": 4e-05, "loss": 10.3766, "step": 4 }, { "epoch": 0.0004781600401654434, "grad_norm": 0.0891149565577507, "learning_rate": 5e-05, "loss": 10.3769, "step": 5 }, { "epoch": 0.000573792048198532, "grad_norm": 0.10069124400615692, "learning_rate": 6e-05, "loss": 10.3775, "step": 6 }, { "epoch": 0.0006694240562316208, "grad_norm": 0.08955492079257965, "learning_rate": 7e-05, "loss": 10.3765, "step": 7 }, { "epoch": 0.0007650560642647094, "grad_norm": 0.0897231474518776, "learning_rate": 8e-05, "loss": 10.3769, "step": 8 }, { "epoch": 0.000860688072297798, "grad_norm": 0.09645914286375046, "learning_rate": 9e-05, "loss": 10.3742, "step": 9 }, { "epoch": 0.0009563200803308868, "grad_norm": 0.09895867109298706, "learning_rate": 0.0001, "loss": 10.3748, "step": 10 }, { "epoch": 0.0010519520883639755, "grad_norm": 0.09568784385919571, "learning_rate": 9.999316524962345e-05, "loss": 10.3739, "step": 11 }, { "epoch": 0.001147584096397064, "grad_norm": 0.1031162440776825, "learning_rate": 9.997266286704631e-05, "loss": 10.3758, "step": 12 }, { "epoch": 0.0012432161044301528, "grad_norm": 0.11152400076389313, "learning_rate": 9.993849845741524e-05, "loss": 10.373, "step": 13 }, { "epoch": 0.0013388481124632415, "grad_norm": 0.11707816272974014, "learning_rate": 9.989068136093873e-05, "loss": 10.3731, "step": 14 }, { "epoch": 0.00143448012049633, "grad_norm": 0.11479246616363525, "learning_rate": 9.98292246503335e-05, "loss": 10.369, "step": 15 }, { "epoch": 0.0015301121285294188, "grad_norm": 0.1254359930753708, "learning_rate": 9.975414512725057e-05, "loss": 10.3703, "step": 16 }, { "epoch": 0.0016257441365625075, "grad_norm": 0.1225835308432579, "learning_rate": 9.966546331768191e-05, "loss": 10.3719, "step": 17 }, { "epoch": 0.001721376144595596, "grad_norm": 0.12829293310642242, "learning_rate": 9.956320346634876e-05, "loss": 10.3711, "step": 18 }, { "epoch": 0.0018170081526286848, "grad_norm": 0.12674109637737274, "learning_rate": 9.944739353007344e-05, "loss": 10.3689, "step": 19 }, { "epoch": 0.0019126401606617736, "grad_norm": 0.16022777557373047, "learning_rate": 9.931806517013612e-05, "loss": 10.367, "step": 20 }, { "epoch": 0.002008272168694862, "grad_norm": 0.15298503637313843, "learning_rate": 9.917525374361912e-05, "loss": 10.368, "step": 21 }, { "epoch": 0.002103904176727951, "grad_norm": 0.17118455469608307, "learning_rate": 9.901899829374047e-05, "loss": 10.365, "step": 22 }, { "epoch": 0.0021995361847610396, "grad_norm": 0.184602752327919, "learning_rate": 9.884934153917997e-05, "loss": 10.3631, "step": 23 }, { "epoch": 0.002295168192794128, "grad_norm": 0.17341238260269165, "learning_rate": 9.86663298624003e-05, "loss": 10.366, "step": 24 }, { "epoch": 0.002390800200827217, "grad_norm": 0.1845225691795349, "learning_rate": 9.847001329696653e-05, "loss": 10.3628, "step": 25 }, { "epoch": 0.0024864322088603056, "grad_norm": 0.19972719252109528, "learning_rate": 9.826044551386744e-05, "loss": 10.3548, "step": 26 }, { "epoch": 0.002582064216893394, "grad_norm": 0.2127637267112732, "learning_rate": 9.803768380684242e-05, "loss": 10.3559, "step": 27 }, { "epoch": 0.002677696224926483, "grad_norm": 0.19505652785301208, "learning_rate": 9.780178907671789e-05, "loss": 10.3551, "step": 28 }, { "epoch": 0.0027733282329595716, "grad_norm": 0.20267733931541443, "learning_rate": 9.755282581475769e-05, "loss": 10.3557, "step": 29 }, { "epoch": 0.00286896024099266, "grad_norm": 0.1918940246105194, "learning_rate": 9.729086208503174e-05, "loss": 10.3552, "step": 30 }, { "epoch": 0.002964592249025749, "grad_norm": 0.18087422847747803, "learning_rate": 9.701596950580806e-05, "loss": 10.351, "step": 31 }, { "epoch": 0.0030602242570588376, "grad_norm": 0.175604447722435, "learning_rate": 9.672822322997305e-05, "loss": 10.3519, "step": 32 }, { "epoch": 0.003155856265091926, "grad_norm": 0.19289462268352509, "learning_rate": 9.642770192448536e-05, "loss": 10.3505, "step": 33 }, { "epoch": 0.003251488273125015, "grad_norm": 0.2132401168346405, "learning_rate": 9.611448774886924e-05, "loss": 10.3525, "step": 34 }, { "epoch": 0.0033471202811581036, "grad_norm": 0.17739249765872955, "learning_rate": 9.578866633275288e-05, "loss": 10.3488, "step": 35 }, { "epoch": 0.003442752289191192, "grad_norm": 0.18477129936218262, "learning_rate": 9.545032675245813e-05, "loss": 10.3468, "step": 36 }, { "epoch": 0.003538384297224281, "grad_norm": 0.1767018586397171, "learning_rate": 9.509956150664796e-05, "loss": 10.338, "step": 37 }, { "epoch": 0.0036340163052573696, "grad_norm": 0.15789976716041565, "learning_rate": 9.473646649103818e-05, "loss": 10.3406, "step": 38 }, { "epoch": 0.003729648313290458, "grad_norm": 0.15501368045806885, "learning_rate": 9.43611409721806e-05, "loss": 10.3446, "step": 39 }, { "epoch": 0.003825280321323547, "grad_norm": 0.17807812988758087, "learning_rate": 9.397368756032445e-05, "loss": 10.3373, "step": 40 }, { "epoch": 0.003920912329356636, "grad_norm": 0.17101648449897766, "learning_rate": 9.357421218136386e-05, "loss": 10.3472, "step": 41 }, { "epoch": 0.004016544337389724, "grad_norm": 0.1407572329044342, "learning_rate": 9.316282404787871e-05, "loss": 10.3392, "step": 42 }, { "epoch": 0.004112176345422813, "grad_norm": 0.15022315084934235, "learning_rate": 9.273963562927695e-05, "loss": 10.331, "step": 43 }, { "epoch": 0.004207808353455902, "grad_norm": 0.1416323333978653, "learning_rate": 9.230476262104677e-05, "loss": 10.3348, "step": 44 }, { "epoch": 0.00430344036148899, "grad_norm": 0.15351463854312897, "learning_rate": 9.185832391312644e-05, "loss": 10.3359, "step": 45 }, { "epoch": 0.004399072369522079, "grad_norm": 0.15096087753772736, "learning_rate": 9.140044155740101e-05, "loss": 10.3338, "step": 46 }, { "epoch": 0.004494704377555168, "grad_norm": 0.17507874965667725, "learning_rate": 9.093124073433463e-05, "loss": 10.3336, "step": 47 }, { "epoch": 0.004590336385588256, "grad_norm": 0.1625409871339798, "learning_rate": 9.045084971874738e-05, "loss": 10.3343, "step": 48 }, { "epoch": 0.004685968393621345, "grad_norm": 0.18303066492080688, "learning_rate": 8.995939984474624e-05, "loss": 10.3258, "step": 49 }, { "epoch": 0.004781600401654434, "grad_norm": 0.2518952488899231, "learning_rate": 8.945702546981969e-05, "loss": 10.3387, "step": 50 }, { "epoch": 0.004781600401654434, "eval_loss": 10.33640193939209, "eval_runtime": 35.3157, "eval_samples_per_second": 498.701, "eval_steps_per_second": 124.675, "step": 50 }, { "epoch": 0.004877232409687522, "grad_norm": 0.11684054881334305, "learning_rate": 8.894386393810563e-05, "loss": 10.3429, "step": 51 }, { "epoch": 0.004972864417720611, "grad_norm": 0.0951906070113182, "learning_rate": 8.842005554284296e-05, "loss": 10.3372, "step": 52 }, { "epoch": 0.0050684964257537, "grad_norm": 0.09602493792772293, "learning_rate": 8.788574348801675e-05, "loss": 10.3374, "step": 53 }, { "epoch": 0.005164128433786788, "grad_norm": 0.10660330951213837, "learning_rate": 8.73410738492077e-05, "loss": 10.341, "step": 54 }, { "epoch": 0.005259760441819877, "grad_norm": 0.10858797281980515, "learning_rate": 8.678619553365659e-05, "loss": 10.3366, "step": 55 }, { "epoch": 0.005355392449852966, "grad_norm": 0.09871065616607666, "learning_rate": 8.622126023955446e-05, "loss": 10.3398, "step": 56 }, { "epoch": 0.005451024457886054, "grad_norm": 0.09441924840211868, "learning_rate": 8.564642241456986e-05, "loss": 10.3383, "step": 57 }, { "epoch": 0.005546656465919143, "grad_norm": 0.098971426486969, "learning_rate": 8.506183921362443e-05, "loss": 10.3392, "step": 58 }, { "epoch": 0.005642288473952232, "grad_norm": 0.09382180869579315, "learning_rate": 8.44676704559283e-05, "loss": 10.3374, "step": 59 }, { "epoch": 0.00573792048198532, "grad_norm": 0.07860254496335983, "learning_rate": 8.386407858128706e-05, "loss": 10.334, "step": 60 }, { "epoch": 0.005833552490018409, "grad_norm": 0.0970577523112297, "learning_rate": 8.32512286056924e-05, "loss": 10.3368, "step": 61 }, { "epoch": 0.005929184498051498, "grad_norm": 0.08663675934076309, "learning_rate": 8.262928807620843e-05, "loss": 10.3335, "step": 62 }, { "epoch": 0.006024816506084586, "grad_norm": 0.07877819985151291, "learning_rate": 8.199842702516583e-05, "loss": 10.3357, "step": 63 }, { "epoch": 0.006120448514117675, "grad_norm": 0.08542774617671967, "learning_rate": 8.135881792367686e-05, "loss": 10.3387, "step": 64 }, { "epoch": 0.006216080522150764, "grad_norm": 0.07468728721141815, "learning_rate": 8.07106356344834e-05, "loss": 10.3332, "step": 65 }, { "epoch": 0.006311712530183852, "grad_norm": 0.09269850701093674, "learning_rate": 8.005405736415126e-05, "loss": 10.3317, "step": 66 }, { "epoch": 0.006407344538216941, "grad_norm": 0.06604257225990295, "learning_rate": 7.938926261462366e-05, "loss": 10.3358, "step": 67 }, { "epoch": 0.00650297654625003, "grad_norm": 0.07798877358436584, "learning_rate": 7.871643313414718e-05, "loss": 10.335, "step": 68 }, { "epoch": 0.006598608554283118, "grad_norm": 0.08844304829835892, "learning_rate": 7.803575286758364e-05, "loss": 10.3332, "step": 69 }, { "epoch": 0.006694240562316207, "grad_norm": 0.08943795412778854, "learning_rate": 7.734740790612136e-05, "loss": 10.3343, "step": 70 }, { "epoch": 0.006789872570349296, "grad_norm": 0.07069361954927444, "learning_rate": 7.66515864363997e-05, "loss": 10.334, "step": 71 }, { "epoch": 0.006885504578382384, "grad_norm": 0.07368559390306473, "learning_rate": 7.594847868906076e-05, "loss": 10.3331, "step": 72 }, { "epoch": 0.006981136586415473, "grad_norm": 0.06632505357265472, "learning_rate": 7.52382768867422e-05, "loss": 10.3343, "step": 73 }, { "epoch": 0.007076768594448562, "grad_norm": 0.07298342883586884, "learning_rate": 7.452117519152542e-05, "loss": 10.3339, "step": 74 }, { "epoch": 0.00717240060248165, "grad_norm": 0.056499090045690536, "learning_rate": 7.379736965185368e-05, "loss": 10.3362, "step": 75 }, { "epoch": 0.007268032610514739, "grad_norm": 0.06135883927345276, "learning_rate": 7.30670581489344e-05, "loss": 10.3315, "step": 76 }, { "epoch": 0.007363664618547828, "grad_norm": 0.07387538254261017, "learning_rate": 7.233044034264034e-05, "loss": 10.3327, "step": 77 }, { "epoch": 0.007459296626580916, "grad_norm": 0.07379622012376785, "learning_rate": 7.158771761692464e-05, "loss": 10.3341, "step": 78 }, { "epoch": 0.007554928634614005, "grad_norm": 0.07869669795036316, "learning_rate": 7.083909302476453e-05, "loss": 10.3325, "step": 79 }, { "epoch": 0.007650560642647094, "grad_norm": 0.07783963531255722, "learning_rate": 7.008477123264848e-05, "loss": 10.3401, "step": 80 }, { "epoch": 0.007746192650680182, "grad_norm": 0.05890215188264847, "learning_rate": 6.932495846462261e-05, "loss": 10.3337, "step": 81 }, { "epoch": 0.007841824658713272, "grad_norm": 0.07027259469032288, "learning_rate": 6.855986244591104e-05, "loss": 10.3349, "step": 82 }, { "epoch": 0.00793745666674636, "grad_norm": 0.06425724923610687, "learning_rate": 6.778969234612584e-05, "loss": 10.3329, "step": 83 }, { "epoch": 0.008033088674779448, "grad_norm": 0.08022365719079971, "learning_rate": 6.701465872208216e-05, "loss": 10.3323, "step": 84 }, { "epoch": 0.008128720682812538, "grad_norm": 0.08018973469734192, "learning_rate": 6.623497346023418e-05, "loss": 10.3337, "step": 85 }, { "epoch": 0.008224352690845626, "grad_norm": 0.10603468865156174, "learning_rate": 6.545084971874738e-05, "loss": 10.3322, "step": 86 }, { "epoch": 0.008319984698878714, "grad_norm": 0.08495115488767624, "learning_rate": 6.466250186922325e-05, "loss": 10.3357, "step": 87 }, { "epoch": 0.008415616706911804, "grad_norm": 0.07791045308113098, "learning_rate": 6.387014543809223e-05, "loss": 10.3309, "step": 88 }, { "epoch": 0.008511248714944892, "grad_norm": 0.09841412305831909, "learning_rate": 6.307399704769099e-05, "loss": 10.3282, "step": 89 }, { "epoch": 0.00860688072297798, "grad_norm": 0.09029070287942886, "learning_rate": 6.227427435703997e-05, "loss": 10.3341, "step": 90 }, { "epoch": 0.00870251273101107, "grad_norm": 0.11134976893663406, "learning_rate": 6.147119600233758e-05, "loss": 10.3322, "step": 91 }, { "epoch": 0.008798144739044158, "grad_norm": 0.11712120473384857, "learning_rate": 6.066498153718735e-05, "loss": 10.327, "step": 92 }, { "epoch": 0.008893776747077246, "grad_norm": 0.10598234087228775, "learning_rate": 5.985585137257401e-05, "loss": 10.3282, "step": 93 }, { "epoch": 0.008989408755110336, "grad_norm": 0.0995323657989502, "learning_rate": 5.90440267166055e-05, "loss": 10.3379, "step": 94 }, { "epoch": 0.009085040763143424, "grad_norm": 0.10824394226074219, "learning_rate": 5.8229729514036705e-05, "loss": 10.332, "step": 95 }, { "epoch": 0.009180672771176512, "grad_norm": 0.16243889927864075, "learning_rate": 5.74131823855921e-05, "loss": 10.3237, "step": 96 }, { "epoch": 0.009276304779209602, "grad_norm": 0.12906967103481293, "learning_rate": 5.6594608567103456e-05, "loss": 10.331, "step": 97 }, { "epoch": 0.00937193678724269, "grad_norm": 0.16123218834400177, "learning_rate": 5.577423184847932e-05, "loss": 10.3333, "step": 98 }, { "epoch": 0.009467568795275778, "grad_norm": 0.12967029213905334, "learning_rate": 5.495227651252315e-05, "loss": 10.3334, "step": 99 }, { "epoch": 0.009563200803308868, "grad_norm": 0.19083808362483978, "learning_rate": 5.4128967273616625e-05, "loss": 10.3182, "step": 100 }, { "epoch": 0.009563200803308868, "eval_loss": 10.330199241638184, "eval_runtime": 35.8412, "eval_samples_per_second": 491.389, "eval_steps_per_second": 122.847, "step": 100 }, { "epoch": 0.009658832811341956, "grad_norm": 0.09029994904994965, "learning_rate": 5.330452921628497e-05, "loss": 10.3347, "step": 101 }, { "epoch": 0.009754464819375044, "grad_norm": 0.08826368302106857, "learning_rate": 5.247918773366112e-05, "loss": 10.3344, "step": 102 }, { "epoch": 0.009850096827408134, "grad_norm": 0.07478147000074387, "learning_rate": 5.165316846586541e-05, "loss": 10.3364, "step": 103 }, { "epoch": 0.009945728835441222, "grad_norm": 0.07320009171962738, "learning_rate": 5.0826697238317935e-05, "loss": 10.3356, "step": 104 }, { "epoch": 0.01004136084347431, "grad_norm": 0.08026351779699326, "learning_rate": 5e-05, "loss": 10.3329, "step": 105 }, { "epoch": 0.0101369928515074, "grad_norm": 0.08629074692726135, "learning_rate": 4.917330276168208e-05, "loss": 10.3304, "step": 106 }, { "epoch": 0.010232624859540488, "grad_norm": 0.09895143657922745, "learning_rate": 4.834683153413459e-05, "loss": 10.3314, "step": 107 }, { "epoch": 0.010328256867573576, "grad_norm": 0.0711413100361824, "learning_rate": 4.7520812266338885e-05, "loss": 10.3341, "step": 108 }, { "epoch": 0.010423888875606666, "grad_norm": 0.07385995984077454, "learning_rate": 4.669547078371504e-05, "loss": 10.3332, "step": 109 }, { "epoch": 0.010519520883639754, "grad_norm": 0.09465530514717102, "learning_rate": 4.5871032726383386e-05, "loss": 10.33, "step": 110 }, { "epoch": 0.010615152891672842, "grad_norm": 0.08026158809661865, "learning_rate": 4.504772348747687e-05, "loss": 10.3317, "step": 111 }, { "epoch": 0.010710784899705932, "grad_norm": 0.07053515315055847, "learning_rate": 4.4225768151520694e-05, "loss": 10.3337, "step": 112 }, { "epoch": 0.01080641690773902, "grad_norm": 0.06886916607618332, "learning_rate": 4.3405391432896555e-05, "loss": 10.333, "step": 113 }, { "epoch": 0.010902048915772108, "grad_norm": 0.06407519429922104, "learning_rate": 4.2586817614407895e-05, "loss": 10.3316, "step": 114 }, { "epoch": 0.010997680923805198, "grad_norm": 0.08041593432426453, "learning_rate": 4.17702704859633e-05, "loss": 10.3312, "step": 115 }, { "epoch": 0.011093312931838286, "grad_norm": 0.07335898280143738, "learning_rate": 4.095597328339452e-05, "loss": 10.3275, "step": 116 }, { "epoch": 0.011188944939871374, "grad_norm": 0.07685739547014236, "learning_rate": 4.0144148627425993e-05, "loss": 10.3306, "step": 117 }, { "epoch": 0.011284576947904464, "grad_norm": 0.07954420894384384, "learning_rate": 3.933501846281267e-05, "loss": 10.3314, "step": 118 }, { "epoch": 0.011380208955937552, "grad_norm": 0.06922579556703568, "learning_rate": 3.852880399766243e-05, "loss": 10.3284, "step": 119 }, { "epoch": 0.01147584096397064, "grad_norm": 0.07615991681814194, "learning_rate": 3.772572564296005e-05, "loss": 10.3326, "step": 120 }, { "epoch": 0.01157147297200373, "grad_norm": 0.06792445480823517, "learning_rate": 3.6926002952309016e-05, "loss": 10.3312, "step": 121 }, { "epoch": 0.011667104980036818, "grad_norm": 0.06562638282775879, "learning_rate": 3.612985456190778e-05, "loss": 10.328, "step": 122 }, { "epoch": 0.011762736988069906, "grad_norm": 0.059679627418518066, "learning_rate": 3.533749813077677e-05, "loss": 10.3276, "step": 123 }, { "epoch": 0.011858368996102996, "grad_norm": 0.0905519649386406, "learning_rate": 3.4549150281252636e-05, "loss": 10.3322, "step": 124 }, { "epoch": 0.011954001004136084, "grad_norm": 0.06883323937654495, "learning_rate": 3.3765026539765834e-05, "loss": 10.3279, "step": 125 }, { "epoch": 0.012049633012169172, "grad_norm": 0.07787835597991943, "learning_rate": 3.298534127791785e-05, "loss": 10.3354, "step": 126 }, { "epoch": 0.012145265020202262, "grad_norm": 0.07963135838508606, "learning_rate": 3.221030765387417e-05, "loss": 10.3277, "step": 127 }, { "epoch": 0.01224089702823535, "grad_norm": 0.07321011275053024, "learning_rate": 3.144013755408895e-05, "loss": 10.3329, "step": 128 }, { "epoch": 0.012336529036268438, "grad_norm": 0.07217072695493698, "learning_rate": 3.0675041535377405e-05, "loss": 10.3278, "step": 129 }, { "epoch": 0.012432161044301528, "grad_norm": 0.07203676551580429, "learning_rate": 2.991522876735154e-05, "loss": 10.3248, "step": 130 }, { "epoch": 0.012527793052334616, "grad_norm": 0.08727250248193741, "learning_rate": 2.916090697523549e-05, "loss": 10.3272, "step": 131 }, { "epoch": 0.012623425060367705, "grad_norm": 0.10006852447986603, "learning_rate": 2.8412282383075363e-05, "loss": 10.3267, "step": 132 }, { "epoch": 0.012719057068400794, "grad_norm": 0.07061868906021118, "learning_rate": 2.766955965735968e-05, "loss": 10.3266, "step": 133 }, { "epoch": 0.012814689076433882, "grad_norm": 0.08265458047389984, "learning_rate": 2.693294185106562e-05, "loss": 10.323, "step": 134 }, { "epoch": 0.01291032108446697, "grad_norm": 0.08742357790470123, "learning_rate": 2.6202630348146324e-05, "loss": 10.3328, "step": 135 }, { "epoch": 0.01300595309250006, "grad_norm": 0.07529257982969284, "learning_rate": 2.547882480847461e-05, "loss": 10.3269, "step": 136 }, { "epoch": 0.013101585100533148, "grad_norm": 0.07144651561975479, "learning_rate": 2.476172311325783e-05, "loss": 10.3272, "step": 137 }, { "epoch": 0.013197217108566237, "grad_norm": 0.0841059684753418, "learning_rate": 2.405152131093926e-05, "loss": 10.326, "step": 138 }, { "epoch": 0.013292849116599326, "grad_norm": 0.10571899265050888, "learning_rate": 2.3348413563600325e-05, "loss": 10.3278, "step": 139 }, { "epoch": 0.013388481124632414, "grad_norm": 0.07771115750074387, "learning_rate": 2.2652592093878666e-05, "loss": 10.3297, "step": 140 }, { "epoch": 0.013484113132665503, "grad_norm": 0.10244104266166687, "learning_rate": 2.196424713241637e-05, "loss": 10.33, "step": 141 }, { "epoch": 0.013579745140698592, "grad_norm": 0.11531634628772736, "learning_rate": 2.128356686585282e-05, "loss": 10.331, "step": 142 }, { "epoch": 0.01367537714873168, "grad_norm": 0.07157227396965027, "learning_rate": 2.061073738537635e-05, "loss": 10.3233, "step": 143 }, { "epoch": 0.013771009156764769, "grad_norm": 0.09135350584983826, "learning_rate": 1.9945942635848748e-05, "loss": 10.3316, "step": 144 }, { "epoch": 0.013866641164797858, "grad_norm": 0.1220884695649147, "learning_rate": 1.928936436551661e-05, "loss": 10.3312, "step": 145 }, { "epoch": 0.013962273172830946, "grad_norm": 0.10230887681245804, "learning_rate": 1.8641182076323148e-05, "loss": 10.3243, "step": 146 }, { "epoch": 0.014057905180864035, "grad_norm": 0.13283300399780273, "learning_rate": 1.800157297483417e-05, "loss": 10.3272, "step": 147 }, { "epoch": 0.014153537188897124, "grad_norm": 0.1467873752117157, "learning_rate": 1.7370711923791567e-05, "loss": 10.3171, "step": 148 }, { "epoch": 0.014249169196930212, "grad_norm": 0.17864419519901276, "learning_rate": 1.6748771394307585e-05, "loss": 10.3244, "step": 149 }, { "epoch": 0.0143448012049633, "grad_norm": 0.27134275436401367, "learning_rate": 1.6135921418712956e-05, "loss": 10.3231, "step": 150 }, { "epoch": 0.0143448012049633, "eval_loss": 10.328064918518066, "eval_runtime": 35.6222, "eval_samples_per_second": 494.411, "eval_steps_per_second": 123.603, "step": 150 }, { "epoch": 0.01444043321299639, "grad_norm": 0.06697675585746765, "learning_rate": 1.553232954407171e-05, "loss": 10.3285, "step": 151 }, { "epoch": 0.014536065221029478, "grad_norm": 0.06400937587022781, "learning_rate": 1.4938160786375572e-05, "loss": 10.3311, "step": 152 }, { "epoch": 0.014631697229062567, "grad_norm": 0.062032558023929596, "learning_rate": 1.435357758543015e-05, "loss": 10.3283, "step": 153 }, { "epoch": 0.014727329237095656, "grad_norm": 0.07714516669511795, "learning_rate": 1.3778739760445552e-05, "loss": 10.3333, "step": 154 }, { "epoch": 0.014822961245128745, "grad_norm": 0.08505989611148834, "learning_rate": 1.3213804466343421e-05, "loss": 10.3297, "step": 155 }, { "epoch": 0.014918593253161833, "grad_norm": 0.07499267905950546, "learning_rate": 1.2658926150792322e-05, "loss": 10.3317, "step": 156 }, { "epoch": 0.015014225261194922, "grad_norm": 0.06940305233001709, "learning_rate": 1.2114256511983274e-05, "loss": 10.3292, "step": 157 }, { "epoch": 0.01510985726922801, "grad_norm": 0.06705410033464432, "learning_rate": 1.157994445715706e-05, "loss": 10.3294, "step": 158 }, { "epoch": 0.015205489277261099, "grad_norm": 0.059012576937675476, "learning_rate": 1.1056136061894384e-05, "loss": 10.3313, "step": 159 }, { "epoch": 0.015301121285294188, "grad_norm": 0.07448853552341461, "learning_rate": 1.0542974530180327e-05, "loss": 10.3348, "step": 160 }, { "epoch": 0.015396753293327277, "grad_norm": 0.06515947729349136, "learning_rate": 1.0040600155253765e-05, "loss": 10.3295, "step": 161 }, { "epoch": 0.015492385301360365, "grad_norm": 0.06873486191034317, "learning_rate": 9.549150281252633e-06, "loss": 10.3295, "step": 162 }, { "epoch": 0.015588017309393454, "grad_norm": 0.08174184709787369, "learning_rate": 9.068759265665384e-06, "loss": 10.3252, "step": 163 }, { "epoch": 0.015683649317426544, "grad_norm": 0.06534477323293686, "learning_rate": 8.599558442598998e-06, "loss": 10.3283, "step": 164 }, { "epoch": 0.01577928132545963, "grad_norm": 0.06826253235340118, "learning_rate": 8.141676086873572e-06, "loss": 10.3307, "step": 165 }, { "epoch": 0.01587491333349272, "grad_norm": 0.07130546867847443, "learning_rate": 7.695237378953223e-06, "loss": 10.3292, "step": 166 }, { "epoch": 0.01597054534152581, "grad_norm": 0.058442000299692154, "learning_rate": 7.260364370723044e-06, "loss": 10.3278, "step": 167 }, { "epoch": 0.016066177349558897, "grad_norm": 0.07666586339473724, "learning_rate": 6.837175952121306e-06, "loss": 10.3297, "step": 168 }, { "epoch": 0.016161809357591986, "grad_norm": 0.06520545482635498, "learning_rate": 6.425787818636131e-06, "loss": 10.3265, "step": 169 }, { "epoch": 0.016257441365625076, "grad_norm": 0.06809031963348389, "learning_rate": 6.026312439675552e-06, "loss": 10.3346, "step": 170 }, { "epoch": 0.016353073373658163, "grad_norm": 0.05104469135403633, "learning_rate": 5.6388590278194096e-06, "loss": 10.3263, "step": 171 }, { "epoch": 0.016448705381691252, "grad_norm": 0.08917240798473358, "learning_rate": 5.263533508961827e-06, "loss": 10.3287, "step": 172 }, { "epoch": 0.016544337389724342, "grad_norm": 0.0724455714225769, "learning_rate": 4.900438493352055e-06, "loss": 10.3298, "step": 173 }, { "epoch": 0.01663996939775743, "grad_norm": 0.05941665917634964, "learning_rate": 4.549673247541875e-06, "loss": 10.3283, "step": 174 }, { "epoch": 0.01673560140579052, "grad_norm": 0.06952770054340363, "learning_rate": 4.2113336672471245e-06, "loss": 10.3242, "step": 175 }, { "epoch": 0.01683123341382361, "grad_norm": 0.07675196975469589, "learning_rate": 3.885512251130763e-06, "loss": 10.3318, "step": 176 }, { "epoch": 0.016926865421856695, "grad_norm": 0.0724993646144867, "learning_rate": 3.5722980755146517e-06, "loss": 10.3263, "step": 177 }, { "epoch": 0.017022497429889785, "grad_norm": 0.08159369230270386, "learning_rate": 3.271776770026963e-06, "loss": 10.3334, "step": 178 }, { "epoch": 0.017118129437922874, "grad_norm": 0.06983686238527298, "learning_rate": 2.9840304941919415e-06, "loss": 10.3269, "step": 179 }, { "epoch": 0.01721376144595596, "grad_norm": 0.06978211551904678, "learning_rate": 2.7091379149682685e-06, "loss": 10.3269, "step": 180 }, { "epoch": 0.01730939345398905, "grad_norm": 0.08521139621734619, "learning_rate": 2.4471741852423237e-06, "loss": 10.3263, "step": 181 }, { "epoch": 0.01740502546202214, "grad_norm": 0.06884609162807465, "learning_rate": 2.1982109232821178e-06, "loss": 10.3298, "step": 182 }, { "epoch": 0.017500657470055227, "grad_norm": 0.08417849242687225, "learning_rate": 1.962316193157593e-06, "loss": 10.3304, "step": 183 }, { "epoch": 0.017596289478088317, "grad_norm": 0.0809563621878624, "learning_rate": 1.7395544861325718e-06, "loss": 10.3254, "step": 184 }, { "epoch": 0.017691921486121406, "grad_norm": 0.10373904556035995, "learning_rate": 1.5299867030334814e-06, "loss": 10.3286, "step": 185 }, { "epoch": 0.017787553494154493, "grad_norm": 0.07427725195884705, "learning_rate": 1.333670137599713e-06, "loss": 10.3316, "step": 186 }, { "epoch": 0.017883185502187583, "grad_norm": 0.09361671656370163, "learning_rate": 1.1506584608200367e-06, "loss": 10.3269, "step": 187 }, { "epoch": 0.017978817510220672, "grad_norm": 0.07629501819610596, "learning_rate": 9.810017062595322e-07, "loss": 10.3297, "step": 188 }, { "epoch": 0.01807444951825376, "grad_norm": 0.07301362603902817, "learning_rate": 8.247462563808817e-07, "loss": 10.3234, "step": 189 }, { "epoch": 0.01817008152628685, "grad_norm": 0.12014688551425934, "learning_rate": 6.819348298638839e-07, "loss": 10.3238, "step": 190 }, { "epoch": 0.01826571353431994, "grad_norm": 0.09758224338293076, "learning_rate": 5.526064699265753e-07, "loss": 10.3248, "step": 191 }, { "epoch": 0.018361345542353025, "grad_norm": 0.0968555361032486, "learning_rate": 4.367965336512403e-07, "loss": 10.3264, "step": 192 }, { "epoch": 0.018456977550386115, "grad_norm": 0.11968742311000824, "learning_rate": 3.3453668231809286e-07, "loss": 10.3289, "step": 193 }, { "epoch": 0.018552609558419204, "grad_norm": 0.10296416282653809, "learning_rate": 2.458548727494292e-07, "loss": 10.3224, "step": 194 }, { "epoch": 0.01864824156645229, "grad_norm": 0.11127232760190964, "learning_rate": 1.7077534966650766e-07, "loss": 10.3312, "step": 195 }, { "epoch": 0.01874387357448538, "grad_norm": 0.13704805076122284, "learning_rate": 1.0931863906127327e-07, "loss": 10.3259, "step": 196 }, { "epoch": 0.01883950558251847, "grad_norm": 0.11831752955913544, "learning_rate": 6.150154258476315e-08, "loss": 10.3182, "step": 197 }, { "epoch": 0.018935137590551557, "grad_norm": 0.13914714753627777, "learning_rate": 2.7337132953697554e-08, "loss": 10.3244, "step": 198 }, { "epoch": 0.019030769598584647, "grad_norm": 0.1753295212984085, "learning_rate": 6.834750376549792e-09, "loss": 10.3294, "step": 199 }, { "epoch": 0.019126401606617736, "grad_norm": 0.2086966335773468, "learning_rate": 0.0, "loss": 10.3245, "step": 200 }, { "epoch": 0.019126401606617736, "eval_loss": 10.327804565429688, "eval_runtime": 35.1193, "eval_samples_per_second": 501.49, "eval_steps_per_second": 125.373, "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": 44104163524608.0, "train_batch_size": 8, "trial_name": null, "trial_params": null }