| { | |
| "best_metric": 1.2475459575653076, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-100", | |
| "epoch": 0.2748800495279369, | |
| "eval_steps": 25, | |
| "global_step": 111, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002476396842594026, | |
| "grad_norm": 0.7329409122467041, | |
| "learning_rate": 9.999999999999999e-05, | |
| "loss": 2.4297, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002476396842594026, | |
| "eval_loss": 2.370262622833252, | |
| "eval_runtime": 1.0104, | |
| "eval_samples_per_second": 49.483, | |
| "eval_steps_per_second": 12.866, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004952793685188052, | |
| "grad_norm": 0.7226835489273071, | |
| "learning_rate": 0.00019999999999999998, | |
| "loss": 2.0074, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.007429190527782077, | |
| "grad_norm": 0.7592707276344299, | |
| "learning_rate": 0.0003, | |
| "loss": 2.0726, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.009905587370376103, | |
| "grad_norm": 0.8533850312232971, | |
| "learning_rate": 0.0002999428882610971, | |
| "loss": 1.9296, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.012381984212970128, | |
| "grad_norm": 0.7311192750930786, | |
| "learning_rate": 0.0002997716013666212, | |
| "loss": 1.7437, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.014858381055564154, | |
| "grad_norm": 0.6385353803634644, | |
| "learning_rate": 0.0002994862842423856, | |
| "loss": 1.7528, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.01733477789815818, | |
| "grad_norm": 0.8438978791236877, | |
| "learning_rate": 0.0002990871782951623, | |
| "loss": 1.6075, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.019811174740752207, | |
| "grad_norm": 0.9431717395782471, | |
| "learning_rate": 0.00029857462120842744, | |
| "loss": 1.6422, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.02228757158334623, | |
| "grad_norm": 0.758976399898529, | |
| "learning_rate": 0.0002979490466566481, | |
| "loss": 1.6292, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.024763968425940256, | |
| "grad_norm": 0.6007578372955322, | |
| "learning_rate": 0.0002972109839383494, | |
| "loss": 1.5238, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.027240365268534284, | |
| "grad_norm": 0.4644957482814789, | |
| "learning_rate": 0.0002963610575282762, | |
| "loss": 1.4831, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.02971676211112831, | |
| "grad_norm": 0.5231449604034424, | |
| "learning_rate": 0.0002953999865490242, | |
| "loss": 1.4047, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03219315895372234, | |
| "grad_norm": 0.6303499937057495, | |
| "learning_rate": 0.00029432858416259097, | |
| "loss": 1.8963, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.03466955579631636, | |
| "grad_norm": 0.7002948522567749, | |
| "learning_rate": 0.0002931477568823596, | |
| "loss": 1.5882, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.037145952638910386, | |
| "grad_norm": 0.48810043931007385, | |
| "learning_rate": 0.00029185850380609757, | |
| "loss": 1.5572, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.039622349481504414, | |
| "grad_norm": 0.4367665648460388, | |
| "learning_rate": 0.000290461915770621, | |
| "loss": 1.4534, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.042098746324098435, | |
| "grad_norm": 0.39929234981536865, | |
| "learning_rate": 0.00028895917442883697, | |
| "loss": 1.4147, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.04457514316669246, | |
| "grad_norm": 0.38216057419776917, | |
| "learning_rate": 0.00028735155124994774, | |
| "loss": 1.438, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04705154000928649, | |
| "grad_norm": 0.3422548770904541, | |
| "learning_rate": 0.0002856404064436606, | |
| "loss": 1.3886, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.04952793685188051, | |
| "grad_norm": 0.4055199921131134, | |
| "learning_rate": 0.000283827187809315, | |
| "loss": 1.47, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05200433369447454, | |
| "grad_norm": 0.42674520611763, | |
| "learning_rate": 0.0002819134295108992, | |
| "loss": 1.4333, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.05448073053706857, | |
| "grad_norm": 0.3820836544036865, | |
| "learning_rate": 0.00027990075077899494, | |
| "loss": 1.4092, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.05695712737966259, | |
| "grad_norm": 0.4357558786869049, | |
| "learning_rate": 0.0002777908545407464, | |
| "loss": 1.4545, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.05943352422225662, | |
| "grad_norm": 0.43220487236976624, | |
| "learning_rate": 0.0002755855259790139, | |
| "loss": 1.3423, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.061909921064850645, | |
| "grad_norm": 0.5457894206047058, | |
| "learning_rate": 0.0002732866310219309, | |
| "loss": 1.4758, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.061909921064850645, | |
| "eval_loss": 1.4271225929260254, | |
| "eval_runtime": 1.0088, | |
| "eval_samples_per_second": 49.566, | |
| "eval_steps_per_second": 12.887, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06438631790744467, | |
| "grad_norm": 0.6328326463699341, | |
| "learning_rate": 0.0002708961147641427, | |
| "loss": 1.6565, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.06686271475003869, | |
| "grad_norm": 0.39392906427383423, | |
| "learning_rate": 0.000268415999821062, | |
| "loss": 1.445, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.06933911159263272, | |
| "grad_norm": 0.40518683195114136, | |
| "learning_rate": 0.00026584838461753444, | |
| "loss": 1.4417, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.07181550843522674, | |
| "grad_norm": 0.40206319093704224, | |
| "learning_rate": 0.00026319544161236156, | |
| "loss": 1.3806, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.07429190527782077, | |
| "grad_norm": 0.427487313747406, | |
| "learning_rate": 0.0002604594154601839, | |
| "loss": 1.3721, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0767683021204148, | |
| "grad_norm": 0.4002684950828552, | |
| "learning_rate": 0.00025764262111227905, | |
| "loss": 1.3487, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.07924469896300883, | |
| "grad_norm": 0.474567711353302, | |
| "learning_rate": 0.00025474744185788155, | |
| "loss": 1.3678, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.08172109580560284, | |
| "grad_norm": 0.40476325154304504, | |
| "learning_rate": 0.0002517763273076828, | |
| "loss": 1.3158, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.08419749264819687, | |
| "grad_norm": 0.3845173418521881, | |
| "learning_rate": 0.00024873179132121507, | |
| "loss": 1.3835, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0866738894907909, | |
| "grad_norm": 0.3646795451641083, | |
| "learning_rate": 0.0002456164098798761, | |
| "loss": 1.3434, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.08915028633338493, | |
| "grad_norm": 0.449341356754303, | |
| "learning_rate": 0.0002424328189073912, | |
| "loss": 1.297, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.09162668317597895, | |
| "grad_norm": 0.44050559401512146, | |
| "learning_rate": 0.0002391837120395588, | |
| "loss": 1.2494, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.09410308001857298, | |
| "grad_norm": 0.5633939504623413, | |
| "learning_rate": 0.00023587183834516558, | |
| "loss": 1.6648, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.096579476861167, | |
| "grad_norm": 0.47090381383895874, | |
| "learning_rate": 0.00023249999999999999, | |
| "loss": 1.4137, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.09905587370376102, | |
| "grad_norm": 0.3539658486843109, | |
| "learning_rate": 0.00022907104991593143, | |
| "loss": 1.3808, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.10153227054635505, | |
| "grad_norm": 0.33691152930259705, | |
| "learning_rate": 0.0002255878893270624, | |
| "loss": 1.2999, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.10400866738894908, | |
| "grad_norm": 0.3699648976325989, | |
| "learning_rate": 0.00022205346533499438, | |
| "loss": 1.3159, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.10648506423154311, | |
| "grad_norm": 0.3926730155944824, | |
| "learning_rate": 0.00021847076841528617, | |
| "loss": 1.2978, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.10896146107413714, | |
| "grad_norm": 0.43968045711517334, | |
| "learning_rate": 0.00021484282988721236, | |
| "loss": 1.3076, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.11143785791673115, | |
| "grad_norm": 0.4484625458717346, | |
| "learning_rate": 0.00021117271934896527, | |
| "loss": 1.3052, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.11391425475932518, | |
| "grad_norm": 0.4811747670173645, | |
| "learning_rate": 0.00020746354208046782, | |
| "loss": 1.2317, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.1163906516019192, | |
| "grad_norm": 0.38913848996162415, | |
| "learning_rate": 0.00020371843641599718, | |
| "loss": 1.2534, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.11886704844451323, | |
| "grad_norm": 0.4041205048561096, | |
| "learning_rate": 0.0001999405710888403, | |
| "loss": 1.3195, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.12134344528710726, | |
| "grad_norm": 0.391659677028656, | |
| "learning_rate": 0.0001961331425502294, | |
| "loss": 1.2099, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.12381984212970129, | |
| "grad_norm": 0.4483822286128998, | |
| "learning_rate": 0.0001922993722648251, | |
| "loss": 1.2427, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.12381984212970129, | |
| "eval_loss": 1.3279614448547363, | |
| "eval_runtime": 1.0087, | |
| "eval_samples_per_second": 49.57, | |
| "eval_steps_per_second": 12.888, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1262962389722953, | |
| "grad_norm": 0.5131921768188477, | |
| "learning_rate": 0.0001884425039850356, | |
| "loss": 1.602, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.12877263581488935, | |
| "grad_norm": 0.588230550289154, | |
| "learning_rate": 0.00018456580100647827, | |
| "loss": 1.3518, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.13124903265748336, | |
| "grad_norm": 0.5344261527061462, | |
| "learning_rate": 0.00018067254340690606, | |
| "loss": 1.2842, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.13372542950007738, | |
| "grad_norm": 0.42600345611572266, | |
| "learning_rate": 0.00017676602527093386, | |
| "loss": 1.2732, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.13620182634267142, | |
| "grad_norm": 0.3716365396976471, | |
| "learning_rate": 0.00017284955190291422, | |
| "loss": 1.3104, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.13867822318526543, | |
| "grad_norm": 0.36169472336769104, | |
| "learning_rate": 0.00016892643703032004, | |
| "loss": 1.2831, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.14115462002785947, | |
| "grad_norm": 0.38514360785484314, | |
| "learning_rate": 0.000165, | |
| "loss": 1.1825, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.1436310168704535, | |
| "grad_norm": 0.46233615279197693, | |
| "learning_rate": 0.00016107356296967993, | |
| "loss": 1.3065, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.14610741371304753, | |
| "grad_norm": 0.49720239639282227, | |
| "learning_rate": 0.00015715044809708577, | |
| "loss": 1.2713, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.14858381055564154, | |
| "grad_norm": 0.4614707827568054, | |
| "learning_rate": 0.0001532339747290661, | |
| "loss": 1.261, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.15106020739823556, | |
| "grad_norm": 0.4578586220741272, | |
| "learning_rate": 0.00014932745659309386, | |
| "loss": 1.2485, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.1535366042408296, | |
| "grad_norm": 0.38602447509765625, | |
| "learning_rate": 0.00014543419899352172, | |
| "loss": 1.1659, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.1560130010834236, | |
| "grad_norm": 0.4391464293003082, | |
| "learning_rate": 0.0001415574960149644, | |
| "loss": 1.5451, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.15848939792601766, | |
| "grad_norm": 0.39024028182029724, | |
| "learning_rate": 0.0001377006277351749, | |
| "loss": 1.3855, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.16096579476861167, | |
| "grad_norm": 0.33916693925857544, | |
| "learning_rate": 0.00013386685744977056, | |
| "loss": 1.2976, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.16344219161120568, | |
| "grad_norm": 0.3237704634666443, | |
| "learning_rate": 0.00013005942891115968, | |
| "loss": 1.2733, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.16591858845379973, | |
| "grad_norm": 0.3709225654602051, | |
| "learning_rate": 0.00012628156358400285, | |
| "loss": 1.2839, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.16839498529639374, | |
| "grad_norm": 0.3892875611782074, | |
| "learning_rate": 0.00012253645791953217, | |
| "loss": 1.3312, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.17087138213898778, | |
| "grad_norm": 0.3935694992542267, | |
| "learning_rate": 0.00011882728065103471, | |
| "loss": 1.246, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.1733477789815818, | |
| "grad_norm": 0.3991238474845886, | |
| "learning_rate": 0.0001151571701127876, | |
| "loss": 1.2713, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.17582417582417584, | |
| "grad_norm": 0.39288103580474854, | |
| "learning_rate": 0.00011152923158471383, | |
| "loss": 1.228, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.17830057266676985, | |
| "grad_norm": 0.3925284743309021, | |
| "learning_rate": 0.0001079465346650056, | |
| "loss": 1.2817, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.18077696950936387, | |
| "grad_norm": 0.41174066066741943, | |
| "learning_rate": 0.00010441211067293761, | |
| "loss": 1.2499, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.1832533663519579, | |
| "grad_norm": 0.3850061595439911, | |
| "learning_rate": 0.00010092895008406854, | |
| "loss": 1.1749, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.18572976319455192, | |
| "grad_norm": 0.45076093077659607, | |
| "learning_rate": 9.750000000000003e-05, | |
| "loss": 1.2532, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.18572976319455192, | |
| "eval_loss": 1.2752010822296143, | |
| "eval_runtime": 1.015, | |
| "eval_samples_per_second": 49.259, | |
| "eval_steps_per_second": 12.807, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.18820616003714596, | |
| "grad_norm": 0.44986942410469055, | |
| "learning_rate": 9.412816165483439e-05, | |
| "loss": 1.6073, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.19068255687973998, | |
| "grad_norm": 0.35847336053848267, | |
| "learning_rate": 9.081628796044118e-05, | |
| "loss": 1.2849, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.193158953722334, | |
| "grad_norm": 0.3534252643585205, | |
| "learning_rate": 8.756718109260881e-05, | |
| "loss": 1.3032, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.19563535056492803, | |
| "grad_norm": 0.3720012903213501, | |
| "learning_rate": 8.438359012012389e-05, | |
| "loss": 1.2459, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.19811174740752205, | |
| "grad_norm": 0.3475172817707062, | |
| "learning_rate": 8.126820867878491e-05, | |
| "loss": 1.2174, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.2005881442501161, | |
| "grad_norm": 0.3700581192970276, | |
| "learning_rate": 7.822367269231717e-05, | |
| "loss": 1.3342, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.2030645410927101, | |
| "grad_norm": 0.38341790437698364, | |
| "learning_rate": 7.525255814211838e-05, | |
| "loss": 1.2484, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.20554093793530412, | |
| "grad_norm": 0.3764133155345917, | |
| "learning_rate": 7.235737888772097e-05, | |
| "loss": 1.2419, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.20801733477789816, | |
| "grad_norm": 0.387975811958313, | |
| "learning_rate": 6.954058453981609e-05, | |
| "loss": 1.2377, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.21049373162049217, | |
| "grad_norm": 0.40386706590652466, | |
| "learning_rate": 6.680455838763842e-05, | |
| "loss": 1.206, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.21297012846308622, | |
| "grad_norm": 0.4010809063911438, | |
| "learning_rate": 6.415161538246557e-05, | |
| "loss": 1.2053, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.21544652530568023, | |
| "grad_norm": 0.420891135931015, | |
| "learning_rate": 6.158400017893799e-05, | |
| "loss": 1.2282, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.21792292214827427, | |
| "grad_norm": 0.44719812273979187, | |
| "learning_rate": 5.9103885235857274e-05, | |
| "loss": 1.5592, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.2203993189908683, | |
| "grad_norm": 0.36982178688049316, | |
| "learning_rate": 5.671336897806908e-05, | |
| "loss": 1.348, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.2228757158334623, | |
| "grad_norm": 0.3596123158931732, | |
| "learning_rate": 5.441447402098609e-05, | |
| "loss": 1.2514, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.22535211267605634, | |
| "grad_norm": 0.3666294515132904, | |
| "learning_rate": 5.2209145459253604e-05, | |
| "loss": 1.2815, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.22782850951865036, | |
| "grad_norm": 0.3626820743083954, | |
| "learning_rate": 5.0099249221005035e-05, | |
| "loss": 1.242, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.2303049063612444, | |
| "grad_norm": 0.3683141767978668, | |
| "learning_rate": 4.808657048910077e-05, | |
| "loss": 1.2619, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.2327813032038384, | |
| "grad_norm": 0.38167521357536316, | |
| "learning_rate": 4.617281219068502e-05, | |
| "loss": 1.2324, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.23525770004643243, | |
| "grad_norm": 0.386264443397522, | |
| "learning_rate": 4.435959355633935e-05, | |
| "loss": 1.2487, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.23773409688902647, | |
| "grad_norm": 0.3971124589443207, | |
| "learning_rate": 4.264844875005226e-05, | |
| "loss": 1.2667, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.24021049373162048, | |
| "grad_norm": 0.39618241786956787, | |
| "learning_rate": 4.104082557116302e-05, | |
| "loss": 1.2715, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.24268689057421453, | |
| "grad_norm": 0.4155503809452057, | |
| "learning_rate": 3.953808422937896e-05, | |
| "loss": 1.199, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.24516328741680854, | |
| "grad_norm": 0.40676349401474, | |
| "learning_rate": 3.814149619390237e-05, | |
| "loss": 1.1614, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.24763968425940258, | |
| "grad_norm": 0.4450746178627014, | |
| "learning_rate": 3.685224311764042e-05, | |
| "loss": 1.185, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.24763968425940258, | |
| "eval_loss": 1.2475459575653076, | |
| "eval_runtime": 1.0194, | |
| "eval_samples_per_second": 49.047, | |
| "eval_steps_per_second": 12.752, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.25011608110199657, | |
| "grad_norm": 0.4321860671043396, | |
| "learning_rate": 3.567141583740899e-05, | |
| "loss": 1.5005, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.2525924779445906, | |
| "grad_norm": 0.3553882837295532, | |
| "learning_rate": 3.4600013450975794e-05, | |
| "loss": 1.2593, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.25506887478718465, | |
| "grad_norm": 0.3538253605365753, | |
| "learning_rate": 3.3638942471723784e-05, | |
| "loss": 1.2722, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.2575452716297787, | |
| "grad_norm": 0.36580267548561096, | |
| "learning_rate": 3.2789016061650545e-05, | |
| "loss": 1.2305, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.2600216684723727, | |
| "grad_norm": 0.36455708742141724, | |
| "learning_rate": 3.205095334335192e-05, | |
| "loss": 1.2613, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.2624980653149667, | |
| "grad_norm": 0.3923397660255432, | |
| "learning_rate": 3.1425378791572495e-05, | |
| "loss": 1.3292, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.26497446215756076, | |
| "grad_norm": 0.3707919120788574, | |
| "learning_rate": 3.0912821704837695e-05, | |
| "loss": 1.1993, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.26745085900015475, | |
| "grad_norm": 0.3740595281124115, | |
| "learning_rate": 3.051371575761435e-05, | |
| "loss": 1.1775, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.2699272558427488, | |
| "grad_norm": 0.3999345004558563, | |
| "learning_rate": 3.0228398633378795e-05, | |
| "loss": 1.198, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.27240365268534283, | |
| "grad_norm": 0.43420764803886414, | |
| "learning_rate": 3.005711173890292e-05, | |
| "loss": 1.2404, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.2748800495279369, | |
| "grad_norm": 0.45214489102363586, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 1.2226, | |
| "step": 111 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 111, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 20, | |
| "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": 1.2015776107027497e+18, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |