| { | |
| "best_metric": 0.009819958359003067, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-100", | |
| "epoch": 1.3986013986013985, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.006993006993006993, | |
| "grad_norm": 1.3562588691711426, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1117, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006993006993006993, | |
| "eval_loss": 0.2389339953660965, | |
| "eval_runtime": 17.8278, | |
| "eval_samples_per_second": 13.518, | |
| "eval_steps_per_second": 3.422, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.013986013986013986, | |
| "grad_norm": 1.3954561948776245, | |
| "learning_rate": 2e-05, | |
| "loss": 0.1385, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.02097902097902098, | |
| "grad_norm": 0.9451524615287781, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0912, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.027972027972027972, | |
| "grad_norm": 0.9036439657211304, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0724, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.03496503496503497, | |
| "grad_norm": 0.7599724531173706, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0474, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.04195804195804196, | |
| "grad_norm": 0.8484829068183899, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0393, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.04895104895104895, | |
| "grad_norm": 0.4445977509021759, | |
| "learning_rate": 7e-05, | |
| "loss": 0.0154, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.055944055944055944, | |
| "grad_norm": 0.9035595655441284, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0149, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.06293706293706294, | |
| "grad_norm": 0.7247656583786011, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0219, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.06993006993006994, | |
| "grad_norm": 0.3379354476928711, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0142, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.07692307692307693, | |
| "grad_norm": 0.7667958736419678, | |
| "learning_rate": 9.999316524962345e-05, | |
| "loss": 0.0136, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.08391608391608392, | |
| "grad_norm": 1.4076844453811646, | |
| "learning_rate": 9.997266286704631e-05, | |
| "loss": 0.0307, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.09090909090909091, | |
| "grad_norm": 0.4995919466018677, | |
| "learning_rate": 9.993849845741524e-05, | |
| "loss": 0.0179, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0979020979020979, | |
| "grad_norm": 0.6687299609184265, | |
| "learning_rate": 9.989068136093873e-05, | |
| "loss": 0.0169, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.1048951048951049, | |
| "grad_norm": 0.4298279881477356, | |
| "learning_rate": 9.98292246503335e-05, | |
| "loss": 0.0215, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.11188811188811189, | |
| "grad_norm": 0.3437817394733429, | |
| "learning_rate": 9.975414512725057e-05, | |
| "loss": 0.0127, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.11888111888111888, | |
| "grad_norm": 0.244386687874794, | |
| "learning_rate": 9.966546331768191e-05, | |
| "loss": 0.0132, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.1258741258741259, | |
| "grad_norm": 0.17345131933689117, | |
| "learning_rate": 9.956320346634876e-05, | |
| "loss": 0.0138, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.13286713286713286, | |
| "grad_norm": 0.23844337463378906, | |
| "learning_rate": 9.944739353007344e-05, | |
| "loss": 0.0185, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.13986013986013987, | |
| "grad_norm": 0.22629468142986298, | |
| "learning_rate": 9.931806517013612e-05, | |
| "loss": 0.0149, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.14685314685314685, | |
| "grad_norm": 0.28062212467193604, | |
| "learning_rate": 9.917525374361912e-05, | |
| "loss": 0.0155, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.15384615384615385, | |
| "grad_norm": 0.2864235043525696, | |
| "learning_rate": 9.901899829374047e-05, | |
| "loss": 0.0176, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.16083916083916083, | |
| "grad_norm": 0.19764366745948792, | |
| "learning_rate": 9.884934153917997e-05, | |
| "loss": 0.0138, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.16783216783216784, | |
| "grad_norm": 0.246744766831398, | |
| "learning_rate": 9.86663298624003e-05, | |
| "loss": 0.0125, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.17482517482517482, | |
| "grad_norm": 0.22735534608364105, | |
| "learning_rate": 9.847001329696653e-05, | |
| "loss": 0.0154, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.18181818181818182, | |
| "grad_norm": 0.13683749735355377, | |
| "learning_rate": 9.826044551386744e-05, | |
| "loss": 0.0132, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.1888111888111888, | |
| "grad_norm": 0.14639340341091156, | |
| "learning_rate": 9.803768380684242e-05, | |
| "loss": 0.0149, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.1958041958041958, | |
| "grad_norm": 0.11369547992944717, | |
| "learning_rate": 9.780178907671789e-05, | |
| "loss": 0.0133, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.20279720279720279, | |
| "grad_norm": 0.1458420753479004, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 0.0145, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.2097902097902098, | |
| "grad_norm": 0.23636756837368011, | |
| "learning_rate": 9.729086208503174e-05, | |
| "loss": 0.0187, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.21678321678321677, | |
| "grad_norm": 0.12035319954156876, | |
| "learning_rate": 9.701596950580806e-05, | |
| "loss": 0.0157, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.22377622377622378, | |
| "grad_norm": 0.20831964910030365, | |
| "learning_rate": 9.672822322997305e-05, | |
| "loss": 0.0189, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.23076923076923078, | |
| "grad_norm": 0.12120852619409561, | |
| "learning_rate": 9.642770192448536e-05, | |
| "loss": 0.0168, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.23776223776223776, | |
| "grad_norm": 0.31398117542266846, | |
| "learning_rate": 9.611448774886924e-05, | |
| "loss": 0.0281, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.24475524475524477, | |
| "grad_norm": 0.29298579692840576, | |
| "learning_rate": 9.578866633275288e-05, | |
| "loss": 0.0286, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.2517482517482518, | |
| "grad_norm": 0.06392526626586914, | |
| "learning_rate": 9.545032675245813e-05, | |
| "loss": 0.0052, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.25874125874125875, | |
| "grad_norm": 0.10478933900594711, | |
| "learning_rate": 9.509956150664796e-05, | |
| "loss": 0.0072, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.26573426573426573, | |
| "grad_norm": 0.0884319394826889, | |
| "learning_rate": 9.473646649103818e-05, | |
| "loss": 0.0084, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.2727272727272727, | |
| "grad_norm": 0.07750493288040161, | |
| "learning_rate": 9.43611409721806e-05, | |
| "loss": 0.0077, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.27972027972027974, | |
| "grad_norm": 0.07667563855648041, | |
| "learning_rate": 9.397368756032445e-05, | |
| "loss": 0.008, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.2867132867132867, | |
| "grad_norm": 0.04682321846485138, | |
| "learning_rate": 9.357421218136386e-05, | |
| "loss": 0.0066, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.2937062937062937, | |
| "grad_norm": 0.16308997571468353, | |
| "learning_rate": 9.316282404787871e-05, | |
| "loss": 0.009, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.3006993006993007, | |
| "grad_norm": 0.15766213834285736, | |
| "learning_rate": 9.273963562927695e-05, | |
| "loss": 0.0105, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.3076923076923077, | |
| "grad_norm": 0.05708695203065872, | |
| "learning_rate": 9.230476262104677e-05, | |
| "loss": 0.0073, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.3146853146853147, | |
| "grad_norm": 0.11191987246274948, | |
| "learning_rate": 9.185832391312644e-05, | |
| "loss": 0.01, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.32167832167832167, | |
| "grad_norm": 0.10076224058866501, | |
| "learning_rate": 9.140044155740101e-05, | |
| "loss": 0.0097, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.32867132867132864, | |
| "grad_norm": 0.0961126834154129, | |
| "learning_rate": 9.093124073433463e-05, | |
| "loss": 0.0099, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.3356643356643357, | |
| "grad_norm": 0.10817134380340576, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.0099, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.34265734265734266, | |
| "grad_norm": 0.1609703004360199, | |
| "learning_rate": 8.995939984474624e-05, | |
| "loss": 0.0096, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.34965034965034963, | |
| "grad_norm": 0.06357306241989136, | |
| "learning_rate": 8.945702546981969e-05, | |
| "loss": 0.0091, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.34965034965034963, | |
| "eval_loss": 0.011457128450274467, | |
| "eval_runtime": 18.3155, | |
| "eval_samples_per_second": 13.158, | |
| "eval_steps_per_second": 3.331, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.35664335664335667, | |
| "grad_norm": 0.0486014261841774, | |
| "learning_rate": 8.894386393810563e-05, | |
| "loss": 0.0087, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.36363636363636365, | |
| "grad_norm": 0.057240478694438934, | |
| "learning_rate": 8.842005554284296e-05, | |
| "loss": 0.0094, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.3706293706293706, | |
| "grad_norm": 0.04622122272849083, | |
| "learning_rate": 8.788574348801675e-05, | |
| "loss": 0.0085, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.3776223776223776, | |
| "grad_norm": 0.08930552005767822, | |
| "learning_rate": 8.73410738492077e-05, | |
| "loss": 0.0111, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.38461538461538464, | |
| "grad_norm": 0.07769561558961868, | |
| "learning_rate": 8.678619553365659e-05, | |
| "loss": 0.0108, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.3916083916083916, | |
| "grad_norm": 0.04258643463253975, | |
| "learning_rate": 8.622126023955446e-05, | |
| "loss": 0.0094, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.3986013986013986, | |
| "grad_norm": 0.1065332368016243, | |
| "learning_rate": 8.564642241456986e-05, | |
| "loss": 0.0115, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.40559440559440557, | |
| "grad_norm": 0.1302216500043869, | |
| "learning_rate": 8.506183921362443e-05, | |
| "loss": 0.0135, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.4125874125874126, | |
| "grad_norm": 0.10008932650089264, | |
| "learning_rate": 8.44676704559283e-05, | |
| "loss": 0.0128, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.4195804195804196, | |
| "grad_norm": 0.056793272495269775, | |
| "learning_rate": 8.386407858128706e-05, | |
| "loss": 0.0115, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.42657342657342656, | |
| "grad_norm": 0.0699341744184494, | |
| "learning_rate": 8.32512286056924e-05, | |
| "loss": 0.012, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.43356643356643354, | |
| "grad_norm": 0.08728343993425369, | |
| "learning_rate": 8.262928807620843e-05, | |
| "loss": 0.0132, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.4405594405594406, | |
| "grad_norm": 0.09555577486753464, | |
| "learning_rate": 8.199842702516583e-05, | |
| "loss": 0.0139, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.44755244755244755, | |
| "grad_norm": 0.14748156070709229, | |
| "learning_rate": 8.135881792367686e-05, | |
| "loss": 0.0164, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.45454545454545453, | |
| "grad_norm": 0.1231960654258728, | |
| "learning_rate": 8.07106356344834e-05, | |
| "loss": 0.0176, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.46153846153846156, | |
| "grad_norm": 0.12327978014945984, | |
| "learning_rate": 8.005405736415126e-05, | |
| "loss": 0.0176, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.46853146853146854, | |
| "grad_norm": 0.11238487809896469, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 0.0167, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.4755244755244755, | |
| "grad_norm": 0.09545250982046127, | |
| "learning_rate": 7.871643313414718e-05, | |
| "loss": 0.0172, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.4825174825174825, | |
| "grad_norm": 0.13959993422031403, | |
| "learning_rate": 7.803575286758364e-05, | |
| "loss": 0.0224, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.48951048951048953, | |
| "grad_norm": 0.22981755435466766, | |
| "learning_rate": 7.734740790612136e-05, | |
| "loss": 0.0274, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.4965034965034965, | |
| "grad_norm": 0.378839910030365, | |
| "learning_rate": 7.66515864363997e-05, | |
| "loss": 0.0057, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.5034965034965035, | |
| "grad_norm": 0.035615526139736176, | |
| "learning_rate": 7.594847868906076e-05, | |
| "loss": 0.0055, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.5104895104895105, | |
| "grad_norm": 0.041333042085170746, | |
| "learning_rate": 7.52382768867422e-05, | |
| "loss": 0.0061, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.5174825174825175, | |
| "grad_norm": 0.025587275624275208, | |
| "learning_rate": 7.452117519152542e-05, | |
| "loss": 0.0053, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.5244755244755245, | |
| "grad_norm": 0.06336121261119843, | |
| "learning_rate": 7.379736965185368e-05, | |
| "loss": 0.0069, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.5314685314685315, | |
| "grad_norm": 1.3939192295074463, | |
| "learning_rate": 7.30670581489344e-05, | |
| "loss": 0.0117, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.5384615384615384, | |
| "grad_norm": 0.0521690808236599, | |
| "learning_rate": 7.233044034264034e-05, | |
| "loss": 0.0075, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.5454545454545454, | |
| "grad_norm": 0.0422733910381794, | |
| "learning_rate": 7.158771761692464e-05, | |
| "loss": 0.0072, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.5524475524475524, | |
| "grad_norm": 0.07740987837314606, | |
| "learning_rate": 7.083909302476453e-05, | |
| "loss": 0.0076, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.5594405594405595, | |
| "grad_norm": 0.06500907987356186, | |
| "learning_rate": 7.008477123264848e-05, | |
| "loss": 0.0074, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.5664335664335665, | |
| "grad_norm": 0.045697715133428574, | |
| "learning_rate": 6.932495846462261e-05, | |
| "loss": 0.0076, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.5734265734265734, | |
| "grad_norm": 0.18606409430503845, | |
| "learning_rate": 6.855986244591104e-05, | |
| "loss": 0.009, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.5804195804195804, | |
| "grad_norm": 0.09711968898773193, | |
| "learning_rate": 6.778969234612584e-05, | |
| "loss": 0.009, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.5874125874125874, | |
| "grad_norm": 0.04535510018467903, | |
| "learning_rate": 6.701465872208216e-05, | |
| "loss": 0.0082, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.5944055944055944, | |
| "grad_norm": 0.05534602329134941, | |
| "learning_rate": 6.623497346023418e-05, | |
| "loss": 0.0086, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.6013986013986014, | |
| "grad_norm": 0.08518693596124649, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.009, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.6083916083916084, | |
| "grad_norm": 0.11916521191596985, | |
| "learning_rate": 6.466250186922325e-05, | |
| "loss": 0.0102, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.6153846153846154, | |
| "grad_norm": 0.04529076814651489, | |
| "learning_rate": 6.387014543809223e-05, | |
| "loss": 0.0094, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.6223776223776224, | |
| "grad_norm": 0.10848016291856766, | |
| "learning_rate": 6.307399704769099e-05, | |
| "loss": 0.0104, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.6293706293706294, | |
| "grad_norm": 0.05130845308303833, | |
| "learning_rate": 6.227427435703997e-05, | |
| "loss": 0.0102, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.6363636363636364, | |
| "grad_norm": 0.07415983080863953, | |
| "learning_rate": 6.147119600233758e-05, | |
| "loss": 0.0107, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.6433566433566433, | |
| "grad_norm": 0.04955919086933136, | |
| "learning_rate": 6.066498153718735e-05, | |
| "loss": 0.0104, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.6503496503496503, | |
| "grad_norm": 0.09341222047805786, | |
| "learning_rate": 5.985585137257401e-05, | |
| "loss": 0.0116, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.6573426573426573, | |
| "grad_norm": 0.07660716772079468, | |
| "learning_rate": 5.90440267166055e-05, | |
| "loss": 0.0109, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.6643356643356644, | |
| "grad_norm": 0.16860635578632355, | |
| "learning_rate": 5.8229729514036705e-05, | |
| "loss": 0.0117, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.6713286713286714, | |
| "grad_norm": 0.07463560998439789, | |
| "learning_rate": 5.74131823855921e-05, | |
| "loss": 0.0124, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.6783216783216783, | |
| "grad_norm": 0.07326523214578629, | |
| "learning_rate": 5.6594608567103456e-05, | |
| "loss": 0.0128, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.6853146853146853, | |
| "grad_norm": 0.07573653757572174, | |
| "learning_rate": 5.577423184847932e-05, | |
| "loss": 0.013, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.6923076923076923, | |
| "grad_norm": 0.05554620549082756, | |
| "learning_rate": 5.495227651252315e-05, | |
| "loss": 0.0129, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.6993006993006993, | |
| "grad_norm": 0.225886732339859, | |
| "learning_rate": 5.4128967273616625e-05, | |
| "loss": 0.016, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.6993006993006993, | |
| "eval_loss": 0.009819958359003067, | |
| "eval_runtime": 18.3103, | |
| "eval_samples_per_second": 13.162, | |
| "eval_steps_per_second": 3.331, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.7062937062937062, | |
| "grad_norm": 0.06343632191419601, | |
| "learning_rate": 5.330452921628497e-05, | |
| "loss": 0.0153, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.7132867132867133, | |
| "grad_norm": 0.08618597686290741, | |
| "learning_rate": 5.247918773366112e-05, | |
| "loss": 0.0176, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.7202797202797203, | |
| "grad_norm": 0.07734549045562744, | |
| "learning_rate": 5.165316846586541e-05, | |
| "loss": 0.0184, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.7272727272727273, | |
| "grad_norm": 0.10186095535755157, | |
| "learning_rate": 5.0826697238317935e-05, | |
| "loss": 0.0204, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.7342657342657343, | |
| "grad_norm": 0.1469995230436325, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0247, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.7412587412587412, | |
| "grad_norm": 0.2742757797241211, | |
| "learning_rate": 4.917330276168208e-05, | |
| "loss": 0.0059, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.7482517482517482, | |
| "grad_norm": 0.041793011128902435, | |
| "learning_rate": 4.834683153413459e-05, | |
| "loss": 0.0059, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.7552447552447552, | |
| "grad_norm": 0.05450927093625069, | |
| "learning_rate": 4.7520812266338885e-05, | |
| "loss": 0.0064, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.7622377622377622, | |
| "grad_norm": 0.03465554863214493, | |
| "learning_rate": 4.669547078371504e-05, | |
| "loss": 0.0063, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.7692307692307693, | |
| "grad_norm": 0.022129550576210022, | |
| "learning_rate": 4.5871032726383386e-05, | |
| "loss": 0.0062, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.7762237762237763, | |
| "grad_norm": 0.022191770374774933, | |
| "learning_rate": 4.504772348747687e-05, | |
| "loss": 0.0064, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.7832167832167832, | |
| "grad_norm": 0.01816759817302227, | |
| "learning_rate": 4.4225768151520694e-05, | |
| "loss": 0.0065, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.7902097902097902, | |
| "grad_norm": 0.03307050094008446, | |
| "learning_rate": 4.3405391432896555e-05, | |
| "loss": 0.0069, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.7972027972027972, | |
| "grad_norm": 0.026633793488144875, | |
| "learning_rate": 4.2586817614407895e-05, | |
| "loss": 0.0067, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.8041958041958042, | |
| "grad_norm": 0.028523385524749756, | |
| "learning_rate": 4.17702704859633e-05, | |
| "loss": 0.0071, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.8111888111888111, | |
| "grad_norm": 0.04871450737118721, | |
| "learning_rate": 4.095597328339452e-05, | |
| "loss": 0.0078, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.8181818181818182, | |
| "grad_norm": 0.05014511197805405, | |
| "learning_rate": 4.0144148627425993e-05, | |
| "loss": 0.008, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.8251748251748252, | |
| "grad_norm": 0.05737553909420967, | |
| "learning_rate": 3.933501846281267e-05, | |
| "loss": 0.0083, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.8321678321678322, | |
| "grad_norm": 0.0482311025261879, | |
| "learning_rate": 3.852880399766243e-05, | |
| "loss": 0.0083, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.8391608391608392, | |
| "grad_norm": 0.028681062161922455, | |
| "learning_rate": 3.772572564296005e-05, | |
| "loss": 0.0084, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.8461538461538461, | |
| "grad_norm": 0.032721854746341705, | |
| "learning_rate": 3.6926002952309016e-05, | |
| "loss": 0.0086, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.8531468531468531, | |
| "grad_norm": 0.04849744588136673, | |
| "learning_rate": 3.612985456190778e-05, | |
| "loss": 0.0089, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.8601398601398601, | |
| "grad_norm": 0.08299832046031952, | |
| "learning_rate": 3.533749813077677e-05, | |
| "loss": 0.0099, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.8671328671328671, | |
| "grad_norm": 0.08110693842172623, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 0.0103, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.8741258741258742, | |
| "grad_norm": 0.0807061493396759, | |
| "learning_rate": 3.3765026539765834e-05, | |
| "loss": 0.0094, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.8811188811188811, | |
| "grad_norm": 0.062166206538677216, | |
| "learning_rate": 3.298534127791785e-05, | |
| "loss": 0.01, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.8881118881118881, | |
| "grad_norm": 0.2937477231025696, | |
| "learning_rate": 3.221030765387417e-05, | |
| "loss": 0.0119, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.8951048951048951, | |
| "grad_norm": 0.1251634657382965, | |
| "learning_rate": 3.144013755408895e-05, | |
| "loss": 0.0106, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.9020979020979021, | |
| "grad_norm": 0.04392090439796448, | |
| "learning_rate": 3.0675041535377405e-05, | |
| "loss": 0.0111, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.9090909090909091, | |
| "grad_norm": 0.05793066695332527, | |
| "learning_rate": 2.991522876735154e-05, | |
| "loss": 0.0114, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.916083916083916, | |
| "grad_norm": 0.034697942435741425, | |
| "learning_rate": 2.916090697523549e-05, | |
| "loss": 0.0115, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.9230769230769231, | |
| "grad_norm": 0.05585641786456108, | |
| "learning_rate": 2.8412282383075363e-05, | |
| "loss": 0.0124, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.9300699300699301, | |
| "grad_norm": 0.06934718787670135, | |
| "learning_rate": 2.766955965735968e-05, | |
| "loss": 0.0128, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.9370629370629371, | |
| "grad_norm": 0.09171628206968307, | |
| "learning_rate": 2.693294185106562e-05, | |
| "loss": 0.014, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.9440559440559441, | |
| "grad_norm": 0.05506027862429619, | |
| "learning_rate": 2.6202630348146324e-05, | |
| "loss": 0.0141, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.951048951048951, | |
| "grad_norm": 0.06012828275561333, | |
| "learning_rate": 2.547882480847461e-05, | |
| "loss": 0.0155, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.958041958041958, | |
| "grad_norm": 0.11653653532266617, | |
| "learning_rate": 2.476172311325783e-05, | |
| "loss": 0.016, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.965034965034965, | |
| "grad_norm": 0.05307229608297348, | |
| "learning_rate": 2.405152131093926e-05, | |
| "loss": 0.0178, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.972027972027972, | |
| "grad_norm": 0.0811811164021492, | |
| "learning_rate": 2.3348413563600325e-05, | |
| "loss": 0.0198, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.9790209790209791, | |
| "grad_norm": 0.1322997510433197, | |
| "learning_rate": 2.2652592093878666e-05, | |
| "loss": 0.0232, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.986013986013986, | |
| "grad_norm": 0.04735981673002243, | |
| "learning_rate": 2.196424713241637e-05, | |
| "loss": 0.0068, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.993006993006993, | |
| "grad_norm": 0.41943109035491943, | |
| "learning_rate": 2.128356686585282e-05, | |
| "loss": 0.0109, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.09877516329288483, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 0.013, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 1.006993006993007, | |
| "grad_norm": 0.06796661764383316, | |
| "learning_rate": 1.9945942635848748e-05, | |
| "loss": 0.0061, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 1.013986013986014, | |
| "grad_norm": 0.05777820572257042, | |
| "learning_rate": 1.928936436551661e-05, | |
| "loss": 0.006, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 1.020979020979021, | |
| "grad_norm": 0.0419895276427269, | |
| "learning_rate": 1.8641182076323148e-05, | |
| "loss": 0.0059, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 1.027972027972028, | |
| "grad_norm": 0.2796054184436798, | |
| "learning_rate": 1.800157297483417e-05, | |
| "loss": 0.0081, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 1.034965034965035, | |
| "grad_norm": 0.050192564725875854, | |
| "learning_rate": 1.7370711923791567e-05, | |
| "loss": 0.0069, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 1.0419580419580419, | |
| "grad_norm": 0.04837430268526077, | |
| "learning_rate": 1.6748771394307585e-05, | |
| "loss": 0.0069, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 1.048951048951049, | |
| "grad_norm": 0.04145139455795288, | |
| "learning_rate": 1.6135921418712956e-05, | |
| "loss": 0.0071, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.048951048951049, | |
| "eval_loss": 0.010439114645123482, | |
| "eval_runtime": 18.3253, | |
| "eval_samples_per_second": 13.151, | |
| "eval_steps_per_second": 3.329, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.055944055944056, | |
| "grad_norm": 0.021643292158842087, | |
| "learning_rate": 1.553232954407171e-05, | |
| "loss": 0.0059, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 1.062937062937063, | |
| "grad_norm": 0.03289172798395157, | |
| "learning_rate": 1.4938160786375572e-05, | |
| "loss": 0.0069, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 1.06993006993007, | |
| "grad_norm": 0.06191176921129227, | |
| "learning_rate": 1.435357758543015e-05, | |
| "loss": 0.0079, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 1.0769230769230769, | |
| "grad_norm": 0.08786314725875854, | |
| "learning_rate": 1.3778739760445552e-05, | |
| "loss": 0.0088, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 1.083916083916084, | |
| "grad_norm": 0.03153017908334732, | |
| "learning_rate": 1.3213804466343421e-05, | |
| "loss": 0.0075, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 1.0909090909090908, | |
| "grad_norm": 0.05395418405532837, | |
| "learning_rate": 1.2658926150792322e-05, | |
| "loss": 0.0069, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 1.097902097902098, | |
| "grad_norm": 0.025599760934710503, | |
| "learning_rate": 1.2114256511983274e-05, | |
| "loss": 0.0076, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 1.104895104895105, | |
| "grad_norm": 0.08563847839832306, | |
| "learning_rate": 1.157994445715706e-05, | |
| "loss": 0.0098, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 1.1118881118881119, | |
| "grad_norm": 0.039989717304706573, | |
| "learning_rate": 1.1056136061894384e-05, | |
| "loss": 0.0089, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 1.118881118881119, | |
| "grad_norm": 0.02937091514468193, | |
| "learning_rate": 1.0542974530180327e-05, | |
| "loss": 0.0084, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.1258741258741258, | |
| "grad_norm": 0.027453837916254997, | |
| "learning_rate": 1.0040600155253765e-05, | |
| "loss": 0.0089, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 1.132867132867133, | |
| "grad_norm": 0.034068603068590164, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.0091, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 1.1398601398601398, | |
| "grad_norm": 0.050712622702121735, | |
| "learning_rate": 9.068759265665384e-06, | |
| "loss": 0.0095, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 1.1468531468531469, | |
| "grad_norm": 0.0380215086042881, | |
| "learning_rate": 8.599558442598998e-06, | |
| "loss": 0.0099, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 1.1538461538461537, | |
| "grad_norm": 0.05365206301212311, | |
| "learning_rate": 8.141676086873572e-06, | |
| "loss": 0.0095, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 1.1608391608391608, | |
| "grad_norm": 0.0458638034760952, | |
| "learning_rate": 7.695237378953223e-06, | |
| "loss": 0.0109, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 1.167832167832168, | |
| "grad_norm": 0.04763127118349075, | |
| "learning_rate": 7.260364370723044e-06, | |
| "loss": 0.0108, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 1.1748251748251748, | |
| "grad_norm": 0.07945173978805542, | |
| "learning_rate": 6.837175952121306e-06, | |
| "loss": 0.0117, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 1.1818181818181819, | |
| "grad_norm": 0.06947402656078339, | |
| "learning_rate": 6.425787818636131e-06, | |
| "loss": 0.0114, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 1.1888111888111887, | |
| "grad_norm": 0.027983682230114937, | |
| "learning_rate": 6.026312439675552e-06, | |
| "loss": 0.0118, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.1958041958041958, | |
| "grad_norm": 0.13096699118614197, | |
| "learning_rate": 5.6388590278194096e-06, | |
| "loss": 0.0125, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 1.2027972027972027, | |
| "grad_norm": 0.052494194358587265, | |
| "learning_rate": 5.263533508961827e-06, | |
| "loss": 0.0133, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 1.2097902097902098, | |
| "grad_norm": 0.06456556916236877, | |
| "learning_rate": 4.900438493352055e-06, | |
| "loss": 0.014, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 1.2167832167832167, | |
| "grad_norm": 0.05545887351036072, | |
| "learning_rate": 4.549673247541875e-06, | |
| "loss": 0.0143, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 1.2237762237762237, | |
| "grad_norm": 0.0679701641201973, | |
| "learning_rate": 4.2113336672471245e-06, | |
| "loss": 0.0156, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.2307692307692308, | |
| "grad_norm": 0.0549745187163353, | |
| "learning_rate": 3.885512251130763e-06, | |
| "loss": 0.0161, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 1.2377622377622377, | |
| "grad_norm": 0.07752084732055664, | |
| "learning_rate": 3.5722980755146517e-06, | |
| "loss": 0.0183, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 1.2447552447552448, | |
| "grad_norm": 0.13658663630485535, | |
| "learning_rate": 3.271776770026963e-06, | |
| "loss": 0.0232, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 1.2517482517482517, | |
| "grad_norm": 0.051107000559568405, | |
| "learning_rate": 2.9840304941919415e-06, | |
| "loss": 0.0049, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 1.2587412587412588, | |
| "grad_norm": 0.027423610910773277, | |
| "learning_rate": 2.7091379149682685e-06, | |
| "loss": 0.0054, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.2657342657342658, | |
| "grad_norm": 0.03497711196541786, | |
| "learning_rate": 2.4471741852423237e-06, | |
| "loss": 0.0057, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 1.2727272727272727, | |
| "grad_norm": 0.018550211563706398, | |
| "learning_rate": 2.1982109232821178e-06, | |
| "loss": 0.0058, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 1.2797202797202798, | |
| "grad_norm": 0.031135590746998787, | |
| "learning_rate": 1.962316193157593e-06, | |
| "loss": 0.0063, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 1.2867132867132867, | |
| "grad_norm": 0.023876115679740906, | |
| "learning_rate": 1.7395544861325718e-06, | |
| "loss": 0.0063, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 1.2937062937062938, | |
| "grad_norm": 0.037167005240917206, | |
| "learning_rate": 1.5299867030334814e-06, | |
| "loss": 0.0065, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 1.3006993006993006, | |
| "grad_norm": 0.03419465571641922, | |
| "learning_rate": 1.333670137599713e-06, | |
| "loss": 0.0071, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 1.3076923076923077, | |
| "grad_norm": 0.02172585390508175, | |
| "learning_rate": 1.1506584608200367e-06, | |
| "loss": 0.007, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 1.3146853146853146, | |
| "grad_norm": 0.023193683475255966, | |
| "learning_rate": 9.810017062595322e-07, | |
| "loss": 0.0072, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 1.3216783216783217, | |
| "grad_norm": 0.08492963761091232, | |
| "learning_rate": 8.247462563808817e-07, | |
| "loss": 0.0074, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 1.3286713286713288, | |
| "grad_norm": 0.02854844741523266, | |
| "learning_rate": 6.819348298638839e-07, | |
| "loss": 0.0077, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.3356643356643356, | |
| "grad_norm": 0.02613200806081295, | |
| "learning_rate": 5.526064699265753e-07, | |
| "loss": 0.0074, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 1.3426573426573427, | |
| "grad_norm": 0.03488029167056084, | |
| "learning_rate": 4.367965336512403e-07, | |
| "loss": 0.0076, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 1.3496503496503496, | |
| "grad_norm": 0.02731182798743248, | |
| "learning_rate": 3.3453668231809286e-07, | |
| "loss": 0.0081, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 1.3566433566433567, | |
| "grad_norm": 0.030974647030234337, | |
| "learning_rate": 2.458548727494292e-07, | |
| "loss": 0.0083, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 1.3636363636363638, | |
| "grad_norm": 0.0233768280595541, | |
| "learning_rate": 1.7077534966650766e-07, | |
| "loss": 0.0086, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 1.3706293706293706, | |
| "grad_norm": 0.0739215612411499, | |
| "learning_rate": 1.0931863906127327e-07, | |
| "loss": 0.0092, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 1.3776223776223775, | |
| "grad_norm": 0.083126962184906, | |
| "learning_rate": 6.150154258476315e-08, | |
| "loss": 0.0093, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 1.3846153846153846, | |
| "grad_norm": 0.04388313740491867, | |
| "learning_rate": 2.7337132953697554e-08, | |
| "loss": 0.0092, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 1.3916083916083917, | |
| "grad_norm": 0.03309253230690956, | |
| "learning_rate": 6.834750376549792e-09, | |
| "loss": 0.009, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 1.3986013986013985, | |
| "grad_norm": 0.041876524686813354, | |
| "learning_rate": 0.0, | |
| "loss": 0.0098, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.3986013986013985, | |
| "eval_loss": 0.010069981217384338, | |
| "eval_runtime": 18.3295, | |
| "eval_samples_per_second": 13.148, | |
| "eval_steps_per_second": 3.328, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 2 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.858867318681764e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |