| { | |
| "best_metric": 1.8241409063339233, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-100", | |
| "epoch": 0.13499831252109348, | |
| "eval_steps": 50, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0013499831252109348, | |
| "grad_norm": 0.6608408093452454, | |
| "learning_rate": 1e-05, | |
| "loss": 1.8574, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0013499831252109348, | |
| "eval_loss": 2.9973878860473633, | |
| "eval_runtime": 23.8973, | |
| "eval_samples_per_second": 208.81, | |
| "eval_steps_per_second": 13.056, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0026999662504218697, | |
| "grad_norm": 0.7569248676300049, | |
| "learning_rate": 2e-05, | |
| "loss": 2.2899, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004049949375632805, | |
| "grad_norm": 0.9085887670516968, | |
| "learning_rate": 3e-05, | |
| "loss": 2.5576, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005399932500843739, | |
| "grad_norm": 0.9023742079734802, | |
| "learning_rate": 4e-05, | |
| "loss": 2.7038, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.006749915626054675, | |
| "grad_norm": 1.028201699256897, | |
| "learning_rate": 5e-05, | |
| "loss": 2.7973, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00809989875126561, | |
| "grad_norm": 1.1021273136138916, | |
| "learning_rate": 6e-05, | |
| "loss": 2.839, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.009449881876476544, | |
| "grad_norm": 1.2096610069274902, | |
| "learning_rate": 7e-05, | |
| "loss": 2.9106, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.010799865001687479, | |
| "grad_norm": 1.0235135555267334, | |
| "learning_rate": 8e-05, | |
| "loss": 2.9067, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.012149848126898413, | |
| "grad_norm": 0.8932393193244934, | |
| "learning_rate": 9e-05, | |
| "loss": 2.9625, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.01349983125210935, | |
| "grad_norm": 0.909520149230957, | |
| "learning_rate": 0.0001, | |
| "loss": 3.03, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.014849814377320284, | |
| "grad_norm": 1.0283902883529663, | |
| "learning_rate": 9.999316524962345e-05, | |
| "loss": 3.0037, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.01619979750253122, | |
| "grad_norm": 0.8786107897758484, | |
| "learning_rate": 9.997266286704631e-05, | |
| "loss": 3.0501, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.017549780627742154, | |
| "grad_norm": 0.5877723693847656, | |
| "learning_rate": 9.993849845741524e-05, | |
| "loss": 1.9512, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.01889976375295309, | |
| "grad_norm": 0.5233044028282166, | |
| "learning_rate": 9.989068136093873e-05, | |
| "loss": 1.8756, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.020249746878164023, | |
| "grad_norm": 0.5067360401153564, | |
| "learning_rate": 9.98292246503335e-05, | |
| "loss": 1.9949, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.021599730003374958, | |
| "grad_norm": 0.5721134543418884, | |
| "learning_rate": 9.975414512725057e-05, | |
| "loss": 2.1069, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.022949713128585892, | |
| "grad_norm": 0.6446163058280945, | |
| "learning_rate": 9.966546331768191e-05, | |
| "loss": 2.1985, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.024299696253796826, | |
| "grad_norm": 0.6047012805938721, | |
| "learning_rate": 9.956320346634876e-05, | |
| "loss": 2.2285, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.02564967937900776, | |
| "grad_norm": 0.7203376293182373, | |
| "learning_rate": 9.944739353007344e-05, | |
| "loss": 2.2503, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0269996625042187, | |
| "grad_norm": 0.7123582363128662, | |
| "learning_rate": 9.931806517013612e-05, | |
| "loss": 2.255, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.028349645629429633, | |
| "grad_norm": 0.726519763469696, | |
| "learning_rate": 9.917525374361912e-05, | |
| "loss": 2.3546, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.029699628754640568, | |
| "grad_norm": 0.6366527676582336, | |
| "learning_rate": 9.901899829374047e-05, | |
| "loss": 2.4744, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.031049611879851502, | |
| "grad_norm": 0.6481205224990845, | |
| "learning_rate": 9.884934153917997e-05, | |
| "loss": 2.5219, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.03239959500506244, | |
| "grad_norm": 0.6891685724258423, | |
| "learning_rate": 9.86663298624003e-05, | |
| "loss": 2.6592, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.03374957813027337, | |
| "grad_norm": 0.7591211795806885, | |
| "learning_rate": 9.847001329696653e-05, | |
| "loss": 2.6479, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03509956125548431, | |
| "grad_norm": 0.4290725886821747, | |
| "learning_rate": 9.826044551386744e-05, | |
| "loss": 1.2884, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.03644954438069524, | |
| "grad_norm": 0.5010724067687988, | |
| "learning_rate": 9.803768380684242e-05, | |
| "loss": 1.6251, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.03779952750590618, | |
| "grad_norm": 0.5251550078392029, | |
| "learning_rate": 9.780178907671789e-05, | |
| "loss": 1.9001, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.03914951063111711, | |
| "grad_norm": 0.5278253555297852, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 2.0828, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.040499493756328046, | |
| "grad_norm": 0.52623051404953, | |
| "learning_rate": 9.729086208503174e-05, | |
| "loss": 2.0811, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.041849476881538984, | |
| "grad_norm": 0.547129213809967, | |
| "learning_rate": 9.701596950580806e-05, | |
| "loss": 1.935, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.043199460006749915, | |
| "grad_norm": 0.5347081422805786, | |
| "learning_rate": 9.672822322997305e-05, | |
| "loss": 2.0857, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.04454944313196085, | |
| "grad_norm": 0.5204690098762512, | |
| "learning_rate": 9.642770192448536e-05, | |
| "loss": 2.2122, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.045899426257171784, | |
| "grad_norm": 0.6102007627487183, | |
| "learning_rate": 9.611448774886924e-05, | |
| "loss": 2.1516, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.04724940938238272, | |
| "grad_norm": 0.6222137808799744, | |
| "learning_rate": 9.578866633275288e-05, | |
| "loss": 2.1896, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.04859939250759365, | |
| "grad_norm": 0.5685420632362366, | |
| "learning_rate": 9.545032675245813e-05, | |
| "loss": 2.3115, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.04994937563280459, | |
| "grad_norm": 0.6640971302986145, | |
| "learning_rate": 9.509956150664796e-05, | |
| "loss": 2.3875, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.05129935875801552, | |
| "grad_norm": 0.4317498505115509, | |
| "learning_rate": 9.473646649103818e-05, | |
| "loss": 1.4803, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.05264934188322646, | |
| "grad_norm": 0.471756249666214, | |
| "learning_rate": 9.43611409721806e-05, | |
| "loss": 1.5283, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0539993250084374, | |
| "grad_norm": 0.45691221952438354, | |
| "learning_rate": 9.397368756032445e-05, | |
| "loss": 1.7842, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.05534930813364833, | |
| "grad_norm": 0.5073127746582031, | |
| "learning_rate": 9.357421218136386e-05, | |
| "loss": 1.7885, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.056699291258859266, | |
| "grad_norm": 0.547063946723938, | |
| "learning_rate": 9.316282404787871e-05, | |
| "loss": 1.9924, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0580492743840702, | |
| "grad_norm": 0.46653538942337036, | |
| "learning_rate": 9.273963562927695e-05, | |
| "loss": 1.9579, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.059399257509281135, | |
| "grad_norm": 0.5522122979164124, | |
| "learning_rate": 9.230476262104677e-05, | |
| "loss": 1.929, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.060749240634492066, | |
| "grad_norm": 0.5174135565757751, | |
| "learning_rate": 9.185832391312644e-05, | |
| "loss": 2.0971, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.062099223759703004, | |
| "grad_norm": 0.5309032201766968, | |
| "learning_rate": 9.140044155740101e-05, | |
| "loss": 1.9968, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.06344920688491394, | |
| "grad_norm": 0.5451260805130005, | |
| "learning_rate": 9.093124073433463e-05, | |
| "loss": 2.1598, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.06479919001012488, | |
| "grad_norm": 0.5665488839149475, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 2.3963, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0661491731353358, | |
| "grad_norm": 0.6137402653694153, | |
| "learning_rate": 8.995939984474624e-05, | |
| "loss": 2.2763, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.06749915626054674, | |
| "grad_norm": 0.7379627823829651, | |
| "learning_rate": 8.945702546981969e-05, | |
| "loss": 2.409, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06749915626054674, | |
| "eval_loss": 1.9224562644958496, | |
| "eval_runtime": 15.2089, | |
| "eval_samples_per_second": 328.098, | |
| "eval_steps_per_second": 20.514, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06884913938575768, | |
| "grad_norm": 0.45811840891838074, | |
| "learning_rate": 8.894386393810563e-05, | |
| "loss": 1.2069, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.07019912251096862, | |
| "grad_norm": 0.447782963514328, | |
| "learning_rate": 8.842005554284296e-05, | |
| "loss": 1.5984, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.07154910563617954, | |
| "grad_norm": 0.4776899814605713, | |
| "learning_rate": 8.788574348801675e-05, | |
| "loss": 1.6739, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.07289908876139048, | |
| "grad_norm": 0.4807668924331665, | |
| "learning_rate": 8.73410738492077e-05, | |
| "loss": 1.7968, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.07424907188660142, | |
| "grad_norm": 0.4958879351615906, | |
| "learning_rate": 8.678619553365659e-05, | |
| "loss": 1.7628, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.07559905501181235, | |
| "grad_norm": 0.49120938777923584, | |
| "learning_rate": 8.622126023955446e-05, | |
| "loss": 1.9598, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.07694903813702329, | |
| "grad_norm": 0.5465077757835388, | |
| "learning_rate": 8.564642241456986e-05, | |
| "loss": 2.0605, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.07829902126223422, | |
| "grad_norm": 0.5541543960571289, | |
| "learning_rate": 8.506183921362443e-05, | |
| "loss": 1.9847, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.07964900438744515, | |
| "grad_norm": 0.5458495020866394, | |
| "learning_rate": 8.44676704559283e-05, | |
| "loss": 2.0529, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.08099898751265609, | |
| "grad_norm": 0.6789040565490723, | |
| "learning_rate": 8.386407858128706e-05, | |
| "loss": 2.0561, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.08234897063786703, | |
| "grad_norm": 0.613196611404419, | |
| "learning_rate": 8.32512286056924e-05, | |
| "loss": 2.2318, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.08369895376307797, | |
| "grad_norm": 0.6030352711677551, | |
| "learning_rate": 8.262928807620843e-05, | |
| "loss": 2.2167, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.08504893688828889, | |
| "grad_norm": 0.39666399359703064, | |
| "learning_rate": 8.199842702516583e-05, | |
| "loss": 1.4176, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.08639892001349983, | |
| "grad_norm": 0.4236837327480316, | |
| "learning_rate": 8.135881792367686e-05, | |
| "loss": 1.502, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.08774890313871077, | |
| "grad_norm": 0.3921578824520111, | |
| "learning_rate": 8.07106356344834e-05, | |
| "loss": 1.5816, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.0890988862639217, | |
| "grad_norm": 0.5283613204956055, | |
| "learning_rate": 8.005405736415126e-05, | |
| "loss": 1.7715, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.09044886938913263, | |
| "grad_norm": 0.6686879992485046, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 1.7861, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.09179885251434357, | |
| "grad_norm": 0.4964534044265747, | |
| "learning_rate": 7.871643313414718e-05, | |
| "loss": 1.8814, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.0931488356395545, | |
| "grad_norm": 0.4999064803123474, | |
| "learning_rate": 7.803575286758364e-05, | |
| "loss": 1.8395, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.09449881876476544, | |
| "grad_norm": 0.5323036313056946, | |
| "learning_rate": 7.734740790612136e-05, | |
| "loss": 1.9695, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.09584880188997638, | |
| "grad_norm": 0.5498347878456116, | |
| "learning_rate": 7.66515864363997e-05, | |
| "loss": 1.9505, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.0971987850151873, | |
| "grad_norm": 0.6689106822013855, | |
| "learning_rate": 7.594847868906076e-05, | |
| "loss": 2.076, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.09854876814039824, | |
| "grad_norm": 0.5689659118652344, | |
| "learning_rate": 7.52382768867422e-05, | |
| "loss": 2.1989, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.09989875126560918, | |
| "grad_norm": 0.6717419624328613, | |
| "learning_rate": 7.452117519152542e-05, | |
| "loss": 2.1737, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.10124873439082012, | |
| "grad_norm": 0.7925436496734619, | |
| "learning_rate": 7.379736965185368e-05, | |
| "loss": 2.288, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.10259871751603104, | |
| "grad_norm": 0.3465993404388428, | |
| "learning_rate": 7.30670581489344e-05, | |
| "loss": 1.1495, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.10394870064124198, | |
| "grad_norm": 0.5540285706520081, | |
| "learning_rate": 7.233044034264034e-05, | |
| "loss": 1.5059, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.10529868376645292, | |
| "grad_norm": 0.5064082741737366, | |
| "learning_rate": 7.158771761692464e-05, | |
| "loss": 1.6449, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.10664866689166386, | |
| "grad_norm": 0.5152279734611511, | |
| "learning_rate": 7.083909302476453e-05, | |
| "loss": 1.696, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.1079986500168748, | |
| "grad_norm": 0.5134519934654236, | |
| "learning_rate": 7.008477123264848e-05, | |
| "loss": 1.7405, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.10934863314208572, | |
| "grad_norm": 0.5233516693115234, | |
| "learning_rate": 6.932495846462261e-05, | |
| "loss": 1.8774, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.11069861626729666, | |
| "grad_norm": 0.5960975289344788, | |
| "learning_rate": 6.855986244591104e-05, | |
| "loss": 1.9146, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.1120485993925076, | |
| "grad_norm": 0.5546828508377075, | |
| "learning_rate": 6.778969234612584e-05, | |
| "loss": 1.895, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.11339858251771853, | |
| "grad_norm": 0.5760257840156555, | |
| "learning_rate": 6.701465872208216e-05, | |
| "loss": 1.8824, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.11474856564292946, | |
| "grad_norm": 0.6636323928833008, | |
| "learning_rate": 6.623497346023418e-05, | |
| "loss": 2.0239, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.1160985487681404, | |
| "grad_norm": 0.5874965786933899, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 2.1653, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.11744853189335133, | |
| "grad_norm": 0.7196479439735413, | |
| "learning_rate": 6.466250186922325e-05, | |
| "loss": 2.2116, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.11879851501856227, | |
| "grad_norm": 0.47423693537712097, | |
| "learning_rate": 6.387014543809223e-05, | |
| "loss": 1.3431, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.12014849814377321, | |
| "grad_norm": 0.3962845802307129, | |
| "learning_rate": 6.307399704769099e-05, | |
| "loss": 1.3365, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.12149848126898413, | |
| "grad_norm": 0.47901609539985657, | |
| "learning_rate": 6.227427435703997e-05, | |
| "loss": 1.6389, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.12284846439419507, | |
| "grad_norm": 0.4754610061645508, | |
| "learning_rate": 6.147119600233758e-05, | |
| "loss": 1.7121, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.12419844751940601, | |
| "grad_norm": 0.5723981857299805, | |
| "learning_rate": 6.066498153718735e-05, | |
| "loss": 1.8633, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.12554843064461693, | |
| "grad_norm": 0.5481359362602234, | |
| "learning_rate": 5.985585137257401e-05, | |
| "loss": 1.7504, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.12689841376982788, | |
| "grad_norm": 0.5384538769721985, | |
| "learning_rate": 5.90440267166055e-05, | |
| "loss": 1.8486, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.1282483968950388, | |
| "grad_norm": 0.6528523564338684, | |
| "learning_rate": 5.8229729514036705e-05, | |
| "loss": 1.9868, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.12959838002024976, | |
| "grad_norm": 0.5357434749603271, | |
| "learning_rate": 5.74131823855921e-05, | |
| "loss": 1.9507, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.13094836314546068, | |
| "grad_norm": 0.6054865717887878, | |
| "learning_rate": 5.6594608567103456e-05, | |
| "loss": 1.9732, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.1322983462706716, | |
| "grad_norm": 0.6194401383399963, | |
| "learning_rate": 5.577423184847932e-05, | |
| "loss": 2.0267, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.13364832939588256, | |
| "grad_norm": 0.6116562485694885, | |
| "learning_rate": 5.495227651252315e-05, | |
| "loss": 2.2024, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.13499831252109348, | |
| "grad_norm": 0.7421515583992004, | |
| "learning_rate": 5.4128967273616625e-05, | |
| "loss": 2.3756, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.13499831252109348, | |
| "eval_loss": 1.8241409063339233, | |
| "eval_runtime": 15.1329, | |
| "eval_samples_per_second": 329.745, | |
| "eval_steps_per_second": 20.617, | |
| "step": 100 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.7475518160896e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |