| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.750816104461371, | |
| "eval_steps": 230, | |
| "global_step": 690, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.001088139281828074, | |
| "grad_norm": 0.04828796908259392, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0762, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002176278563656148, | |
| "grad_norm": 0.06207922473549843, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0973, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.003264417845484222, | |
| "grad_norm": 0.06030188128352165, | |
| "learning_rate": 6e-05, | |
| "loss": 0.1003, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004352557127312296, | |
| "grad_norm": 0.05758730694651604, | |
| "learning_rate": 8e-05, | |
| "loss": 0.085, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00544069640914037, | |
| "grad_norm": 0.07111983001232147, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1174, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.006528835690968444, | |
| "grad_norm": 0.09522929042577744, | |
| "learning_rate": 0.00012, | |
| "loss": 0.1404, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.007616974972796518, | |
| "grad_norm": 0.08600069582462311, | |
| "learning_rate": 0.00014, | |
| "loss": 0.1187, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.008705114254624592, | |
| "grad_norm": 0.0808354914188385, | |
| "learning_rate": 0.00016, | |
| "loss": 0.1235, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.009793253536452665, | |
| "grad_norm": 0.10051260888576508, | |
| "learning_rate": 0.00018, | |
| "loss": 0.135, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.01088139281828074, | |
| "grad_norm": 0.08877796679735184, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0803, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.011969532100108813, | |
| "grad_norm": 0.10384293645620346, | |
| "learning_rate": 0.00019999940277008808, | |
| "loss": 0.1206, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.013057671381936888, | |
| "grad_norm": 0.1314290463924408, | |
| "learning_rate": 0.00019999761108748597, | |
| "loss": 0.1249, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.014145810663764961, | |
| "grad_norm": 0.12873488664627075, | |
| "learning_rate": 0.00019999462497359466, | |
| "loss": 0.0847, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.015233949945593036, | |
| "grad_norm": 0.12493155896663666, | |
| "learning_rate": 0.000199990444464082, | |
| "loss": 0.0858, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.01632208922742111, | |
| "grad_norm": 0.1131022647023201, | |
| "learning_rate": 0.00019998506960888256, | |
| "loss": 0.0737, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.017410228509249184, | |
| "grad_norm": 0.1214890405535698, | |
| "learning_rate": 0.0001999785004721968, | |
| "loss": 0.1151, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.018498367791077257, | |
| "grad_norm": 0.12649253010749817, | |
| "learning_rate": 0.0001999707371324904, | |
| "loss": 0.0913, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.01958650707290533, | |
| "grad_norm": 0.12470237910747528, | |
| "learning_rate": 0.00019996177968249334, | |
| "loss": 0.1043, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.020674646354733407, | |
| "grad_norm": 0.15574277937412262, | |
| "learning_rate": 0.00019995162822919883, | |
| "loss": 0.1092, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.02176278563656148, | |
| "grad_norm": 0.1281992644071579, | |
| "learning_rate": 0.0001999402828938618, | |
| "loss": 0.0892, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.022850924918389554, | |
| "grad_norm": 0.16906976699829102, | |
| "learning_rate": 0.00019992774381199778, | |
| "loss": 0.1633, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.023939064200217627, | |
| "grad_norm": 0.12387573719024658, | |
| "learning_rate": 0.00019991401113338104, | |
| "loss": 0.0872, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.025027203482045703, | |
| "grad_norm": 0.12343913316726685, | |
| "learning_rate": 0.00019989908502204292, | |
| "loss": 0.1084, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.026115342763873776, | |
| "grad_norm": 0.11399204283952713, | |
| "learning_rate": 0.00019988296565626987, | |
| "loss": 0.0824, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.02720348204570185, | |
| "grad_norm": 0.1402149796485901, | |
| "learning_rate": 0.00019986565322860115, | |
| "loss": 0.1289, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.028291621327529923, | |
| "grad_norm": 0.13711000978946686, | |
| "learning_rate": 0.00019984714794582683, | |
| "loss": 0.097, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.029379760609358, | |
| "grad_norm": 0.18544617295265198, | |
| "learning_rate": 0.000199827450028985, | |
| "loss": 0.1281, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.030467899891186073, | |
| "grad_norm": 0.15856046974658966, | |
| "learning_rate": 0.00019980655971335945, | |
| "loss": 0.1027, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.031556039173014146, | |
| "grad_norm": 0.12590578198432922, | |
| "learning_rate": 0.00019978447724847652, | |
| "loss": 0.0863, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.03264417845484222, | |
| "grad_norm": 0.14784540235996246, | |
| "learning_rate": 0.00019976120289810247, | |
| "loss": 0.1125, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03373231773667029, | |
| "grad_norm": 0.19753308594226837, | |
| "learning_rate": 0.00019973673694024, | |
| "loss": 0.1389, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.03482045701849837, | |
| "grad_norm": 0.17247086763381958, | |
| "learning_rate": 0.00019971107966712518, | |
| "loss": 0.0901, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.035908596300326445, | |
| "grad_norm": 0.23573236167430878, | |
| "learning_rate": 0.0001996842313852238, | |
| "loss": 0.1141, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.036996735582154515, | |
| "grad_norm": 0.1349520981311798, | |
| "learning_rate": 0.0001996561924152278, | |
| "loss": 0.077, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.03808487486398259, | |
| "grad_norm": 0.2573637068271637, | |
| "learning_rate": 0.00019962696309205148, | |
| "loss": 0.0965, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.03917301414581066, | |
| "grad_norm": 0.2688570022583008, | |
| "learning_rate": 0.0001995965437648273, | |
| "loss": 0.1754, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.04026115342763874, | |
| "grad_norm": 0.2946501076221466, | |
| "learning_rate": 0.0001995649347969019, | |
| "loss": 0.1893, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.041349292709466814, | |
| "grad_norm": 0.2942318320274353, | |
| "learning_rate": 0.00019953213656583168, | |
| "loss": 0.1461, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.042437431991294884, | |
| "grad_norm": 0.3316934406757355, | |
| "learning_rate": 0.00019949814946337838, | |
| "loss": 0.1072, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.04352557127312296, | |
| "grad_norm": 0.3863315284252167, | |
| "learning_rate": 0.00019946297389550433, | |
| "loss": 0.1517, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04461371055495103, | |
| "grad_norm": 0.3102675974369049, | |
| "learning_rate": 0.00019942661028236745, | |
| "loss": 0.1421, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.04570184983677911, | |
| "grad_norm": 0.3270488679409027, | |
| "learning_rate": 0.00019938905905831654, | |
| "loss": 0.085, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.046789989118607184, | |
| "grad_norm": 0.3799861669540405, | |
| "learning_rate": 0.0001993503206718859, | |
| "loss": 0.1333, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.04787812840043525, | |
| "grad_norm": 0.45475858449935913, | |
| "learning_rate": 0.00019931039558578997, | |
| "loss": 0.1431, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.04896626768226333, | |
| "grad_norm": 0.3995339870452881, | |
| "learning_rate": 0.00019926928427691786, | |
| "loss": 0.18, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.05005440696409141, | |
| "grad_norm": 0.4547290503978729, | |
| "learning_rate": 0.00019922698723632767, | |
| "loss": 0.1578, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.051142546245919476, | |
| "grad_norm": 0.44180116057395935, | |
| "learning_rate": 0.0001991835049692405, | |
| "loss": 0.2327, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.05223068552774755, | |
| "grad_norm": 0.8059853911399841, | |
| "learning_rate": 0.0001991388379950346, | |
| "loss": 0.3089, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.05331882480957562, | |
| "grad_norm": 0.6336686015129089, | |
| "learning_rate": 0.00019909298684723904, | |
| "loss": 0.2055, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.0544069640914037, | |
| "grad_norm": 0.8279074430465698, | |
| "learning_rate": 0.00019904595207352737, | |
| "loss": 0.2626, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.055495103373231776, | |
| "grad_norm": 0.07426032423973083, | |
| "learning_rate": 0.000198997734235711, | |
| "loss": 0.0632, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.056583242655059846, | |
| "grad_norm": 0.09094005823135376, | |
| "learning_rate": 0.00019894833390973266, | |
| "loss": 0.0734, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.05767138193688792, | |
| "grad_norm": 0.09561450034379959, | |
| "learning_rate": 0.00019889775168565943, | |
| "loss": 0.0972, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.058759521218716, | |
| "grad_norm": 0.09174304455518723, | |
| "learning_rate": 0.00019884598816767563, | |
| "loss": 0.082, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.05984766050054407, | |
| "grad_norm": 0.0911480113863945, | |
| "learning_rate": 0.0001987930439740757, | |
| "loss": 0.0712, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.060935799782372145, | |
| "grad_norm": 0.1090071052312851, | |
| "learning_rate": 0.0001987389197372567, | |
| "loss": 0.09, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.062023939064200215, | |
| "grad_norm": 0.09118974953889847, | |
| "learning_rate": 0.00019868361610371097, | |
| "loss": 0.0946, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.06311207834602829, | |
| "grad_norm": 0.09903446584939957, | |
| "learning_rate": 0.0001986271337340182, | |
| "loss": 0.1074, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.06420021762785637, | |
| "grad_norm": 0.08208192884922028, | |
| "learning_rate": 0.00019856947330283752, | |
| "loss": 0.0847, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.06528835690968444, | |
| "grad_norm": 0.08504832535982132, | |
| "learning_rate": 0.0001985106354988997, | |
| "loss": 0.0852, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.06637649619151251, | |
| "grad_norm": 0.07276565581560135, | |
| "learning_rate": 0.0001984506210249986, | |
| "loss": 0.061, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.06746463547334058, | |
| "grad_norm": 0.08346979320049286, | |
| "learning_rate": 0.00019838943059798304, | |
| "loss": 0.0717, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.06855277475516866, | |
| "grad_norm": 0.09144837409257889, | |
| "learning_rate": 0.0001983270649487481, | |
| "loss": 0.0817, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.06964091403699674, | |
| "grad_norm": 0.09562050551176071, | |
| "learning_rate": 0.00019826352482222638, | |
| "loss": 0.0809, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.07072905331882481, | |
| "grad_norm": 0.10410594195127487, | |
| "learning_rate": 0.00019819881097737915, | |
| "loss": 0.0801, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.07181719260065289, | |
| "grad_norm": 0.0836932361125946, | |
| "learning_rate": 0.00019813292418718732, | |
| "loss": 0.0775, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.07290533188248095, | |
| "grad_norm": 0.09397463500499725, | |
| "learning_rate": 0.0001980658652386421, | |
| "loss": 0.065, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.07399347116430903, | |
| "grad_norm": 0.108340784907341, | |
| "learning_rate": 0.0001979976349327357, | |
| "loss": 0.0981, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.0750816104461371, | |
| "grad_norm": 0.08717814087867737, | |
| "learning_rate": 0.00019792823408445174, | |
| "loss": 0.0798, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.07616974972796518, | |
| "grad_norm": 0.1279960721731186, | |
| "learning_rate": 0.00019785766352275542, | |
| "loss": 0.0993, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.07725788900979326, | |
| "grad_norm": 0.13422514498233795, | |
| "learning_rate": 0.00019778592409058378, | |
| "loss": 0.1023, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.07834602829162132, | |
| "grad_norm": 0.10113417357206345, | |
| "learning_rate": 0.0001977130166448355, | |
| "loss": 0.0742, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.0794341675734494, | |
| "grad_norm": 0.1026310920715332, | |
| "learning_rate": 0.00019763894205636072, | |
| "loss": 0.0988, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.08052230685527748, | |
| "grad_norm": 0.09779265522956848, | |
| "learning_rate": 0.00019756370120995066, | |
| "loss": 0.0738, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.08161044613710555, | |
| "grad_norm": 0.14643464982509613, | |
| "learning_rate": 0.000197487295004327, | |
| "loss": 0.09, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.08269858541893363, | |
| "grad_norm": 0.11976644396781921, | |
| "learning_rate": 0.00019740972435213115, | |
| "loss": 0.0904, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.08378672470076169, | |
| "grad_norm": 0.10904321819543839, | |
| "learning_rate": 0.00019733099017991341, | |
| "loss": 0.0766, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.08487486398258977, | |
| "grad_norm": 0.1651339828968048, | |
| "learning_rate": 0.0001972510934281218, | |
| "loss": 0.1186, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.08596300326441784, | |
| "grad_norm": 0.11781762540340424, | |
| "learning_rate": 0.00019717003505109095, | |
| "loss": 0.0833, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.08705114254624592, | |
| "grad_norm": 0.15122370421886444, | |
| "learning_rate": 0.00019708781601703065, | |
| "loss": 0.1166, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.088139281828074, | |
| "grad_norm": 0.1798838973045349, | |
| "learning_rate": 0.00019700443730801413, | |
| "loss": 0.1109, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.08922742110990206, | |
| "grad_norm": 0.18025629222393036, | |
| "learning_rate": 0.00019691989991996663, | |
| "loss": 0.1243, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.09031556039173014, | |
| "grad_norm": 0.1731874644756317, | |
| "learning_rate": 0.00019683420486265327, | |
| "loss": 0.1189, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.09140369967355821, | |
| "grad_norm": 0.2220824509859085, | |
| "learning_rate": 0.0001967473531596671, | |
| "loss": 0.1451, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.09249183895538629, | |
| "grad_norm": 0.1664338856935501, | |
| "learning_rate": 0.00019665934584841682, | |
| "loss": 0.0897, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.09357997823721437, | |
| "grad_norm": 0.17619486153125763, | |
| "learning_rate": 0.00019657018398011434, | |
| "loss": 0.0935, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.09466811751904244, | |
| "grad_norm": 0.24987219274044037, | |
| "learning_rate": 0.00019647986861976246, | |
| "loss": 0.1955, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.0957562568008705, | |
| "grad_norm": 0.21318784356117249, | |
| "learning_rate": 0.00019638840084614182, | |
| "loss": 0.1131, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.09684439608269858, | |
| "grad_norm": 0.3128167390823364, | |
| "learning_rate": 0.0001962957817517982, | |
| "loss": 0.2011, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.09793253536452666, | |
| "grad_norm": 0.2833835184574127, | |
| "learning_rate": 0.00019620201244302952, | |
| "loss": 0.1592, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.09902067464635474, | |
| "grad_norm": 0.3286789357662201, | |
| "learning_rate": 0.00019610709403987246, | |
| "loss": 0.1602, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.10010881392818281, | |
| "grad_norm": 0.44117358326911926, | |
| "learning_rate": 0.00019601102767608923, | |
| "loss": 0.2323, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.10119695321001088, | |
| "grad_norm": 0.3795579671859741, | |
| "learning_rate": 0.00019591381449915397, | |
| "loss": 0.1867, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.10228509249183895, | |
| "grad_norm": 0.5780506730079651, | |
| "learning_rate": 0.000195815455670239, | |
| "loss": 0.1884, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.10337323177366703, | |
| "grad_norm": 0.5124024748802185, | |
| "learning_rate": 0.00019571595236420102, | |
| "loss": 0.221, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.1044613710554951, | |
| "grad_norm": 0.4628782272338867, | |
| "learning_rate": 0.00019561530576956703, | |
| "loss": 0.208, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.10554951033732318, | |
| "grad_norm": 0.3904087543487549, | |
| "learning_rate": 0.0001955135170885202, | |
| "loss": 0.2029, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.10663764961915125, | |
| "grad_norm": 0.513387143611908, | |
| "learning_rate": 0.00019541058753688538, | |
| "loss": 0.2248, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.10772578890097932, | |
| "grad_norm": 0.6133597493171692, | |
| "learning_rate": 0.00019530651834411474, | |
| "loss": 0.3751, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.1088139281828074, | |
| "grad_norm": 0.6515563726425171, | |
| "learning_rate": 0.00019520131075327298, | |
| "loss": 0.2096, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.10990206746463548, | |
| "grad_norm": 0.07718291878700256, | |
| "learning_rate": 0.00019509496602102252, | |
| "loss": 0.0631, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.11099020674646355, | |
| "grad_norm": 0.07896394282579422, | |
| "learning_rate": 0.00019498748541760846, | |
| "loss": 0.095, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.11207834602829161, | |
| "grad_norm": 0.07955438643693924, | |
| "learning_rate": 0.00019487887022684336, | |
| "loss": 0.067, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.11316648531011969, | |
| "grad_norm": 0.08391376584768295, | |
| "learning_rate": 0.0001947691217460921, | |
| "loss": 0.0637, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.11425462459194777, | |
| "grad_norm": 0.07990088313817978, | |
| "learning_rate": 0.00019465824128625617, | |
| "loss": 0.0569, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.11534276387377584, | |
| "grad_norm": 0.09000790864229202, | |
| "learning_rate": 0.00019454623017175812, | |
| "loss": 0.0639, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.11643090315560392, | |
| "grad_norm": 0.0831453874707222, | |
| "learning_rate": 0.0001944330897405257, | |
| "loss": 0.0766, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.117519042437432, | |
| "grad_norm": 0.08180610835552216, | |
| "learning_rate": 0.00019431882134397598, | |
| "loss": 0.0806, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.11860718171926006, | |
| "grad_norm": 0.07601706683635712, | |
| "learning_rate": 0.0001942034263469989, | |
| "loss": 0.0727, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.11969532100108814, | |
| "grad_norm": 0.08873546868562698, | |
| "learning_rate": 0.00019408690612794148, | |
| "loss": 0.0878, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.12078346028291621, | |
| "grad_norm": 0.10206414759159088, | |
| "learning_rate": 0.00019396926207859084, | |
| "loss": 0.1171, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.12187159956474429, | |
| "grad_norm": 0.07465587556362152, | |
| "learning_rate": 0.00019385049560415794, | |
| "loss": 0.0603, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.12295973884657237, | |
| "grad_norm": 0.09952360391616821, | |
| "learning_rate": 0.00019373060812326052, | |
| "loss": 0.0923, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.12404787812840043, | |
| "grad_norm": 0.09894778579473495, | |
| "learning_rate": 0.00019360960106790643, | |
| "loss": 0.0795, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.1251360174102285, | |
| "grad_norm": 0.09721358120441437, | |
| "learning_rate": 0.00019348747588347637, | |
| "loss": 0.1103, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.12622415669205658, | |
| "grad_norm": 0.10310002416372299, | |
| "learning_rate": 0.00019336423402870653, | |
| "loss": 0.1037, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.12731229597388466, | |
| "grad_norm": 0.10904382914304733, | |
| "learning_rate": 0.0001932398769756714, | |
| "loss": 0.1063, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.12840043525571274, | |
| "grad_norm": 0.11545544862747192, | |
| "learning_rate": 0.00019311440620976597, | |
| "loss": 0.096, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.1294885745375408, | |
| "grad_norm": 0.08674886077642441, | |
| "learning_rate": 0.00019298782322968815, | |
| "loss": 0.0779, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.1305767138193689, | |
| "grad_norm": 0.09437372535467148, | |
| "learning_rate": 0.0001928601295474208, | |
| "loss": 0.0975, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.13166485310119697, | |
| "grad_norm": 0.1258208006620407, | |
| "learning_rate": 0.00019273132668821364, | |
| "loss": 0.1277, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.13275299238302501, | |
| "grad_norm": 0.09919868409633636, | |
| "learning_rate": 0.00019260141619056507, | |
| "loss": 0.0993, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.1338411316648531, | |
| "grad_norm": 0.12028370052576065, | |
| "learning_rate": 0.0001924703996062038, | |
| "loss": 0.0751, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.13492927094668117, | |
| "grad_norm": 0.10702817142009735, | |
| "learning_rate": 0.00019233827850007027, | |
| "loss": 0.0949, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.13601741022850924, | |
| "grad_norm": 0.10939855128526688, | |
| "learning_rate": 0.000192205054450298, | |
| "loss": 0.0977, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.13710554951033732, | |
| "grad_norm": 0.11803679168224335, | |
| "learning_rate": 0.00019207072904819486, | |
| "loss": 0.0877, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.1381936887921654, | |
| "grad_norm": 0.1382649838924408, | |
| "learning_rate": 0.00019193530389822363, | |
| "loss": 0.1017, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.13928182807399347, | |
| "grad_norm": 0.1433139145374298, | |
| "learning_rate": 0.00019179878061798347, | |
| "loss": 0.0748, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.14036996735582155, | |
| "grad_norm": 0.14679527282714844, | |
| "learning_rate": 0.00019166116083819002, | |
| "loss": 0.1164, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.14145810663764963, | |
| "grad_norm": 0.13680118322372437, | |
| "learning_rate": 0.0001915224462026563, | |
| "loss": 0.1149, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.1425462459194777, | |
| "grad_norm": 0.16263848543167114, | |
| "learning_rate": 0.00019138263836827288, | |
| "loss": 0.1192, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.14363438520130578, | |
| "grad_norm": 0.16534928977489471, | |
| "learning_rate": 0.00019124173900498818, | |
| "loss": 0.1138, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.14472252448313383, | |
| "grad_norm": 0.21276706457138062, | |
| "learning_rate": 0.0001910997497957885, | |
| "loss": 0.1461, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.1458106637649619, | |
| "grad_norm": 0.2375650703907013, | |
| "learning_rate": 0.0001909566724366779, | |
| "loss": 0.2031, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.14689880304678998, | |
| "grad_norm": 0.20974405109882355, | |
| "learning_rate": 0.00019081250863665794, | |
| "loss": 0.1285, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.14798694232861806, | |
| "grad_norm": 0.308624267578125, | |
| "learning_rate": 0.00019066726011770726, | |
| "loss": 0.1717, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.14907508161044614, | |
| "grad_norm": 0.21192695200443268, | |
| "learning_rate": 0.0001905209286147611, | |
| "loss": 0.1064, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.1501632208922742, | |
| "grad_norm": 0.20596542954444885, | |
| "learning_rate": 0.0001903735158756905, | |
| "loss": 0.0975, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.1512513601741023, | |
| "grad_norm": 0.21547934412956238, | |
| "learning_rate": 0.00019022502366128135, | |
| "loss": 0.1255, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.15233949945593037, | |
| "grad_norm": 0.276815801858902, | |
| "learning_rate": 0.00019007545374521355, | |
| "loss": 0.0868, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.15342763873775844, | |
| "grad_norm": 0.37251031398773193, | |
| "learning_rate": 0.00018992480791403958, | |
| "loss": 0.1078, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.15451577801958652, | |
| "grad_norm": 0.328265517950058, | |
| "learning_rate": 0.0001897730879671634, | |
| "loss": 0.1842, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.15560391730141457, | |
| "grad_norm": 0.4400005340576172, | |
| "learning_rate": 0.00018962029571681886, | |
| "loss": 0.1857, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.15669205658324264, | |
| "grad_norm": 0.28378888964653015, | |
| "learning_rate": 0.00018946643298804793, | |
| "loss": 0.0955, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.15778019586507072, | |
| "grad_norm": 0.609008252620697, | |
| "learning_rate": 0.00018931150161867916, | |
| "loss": 0.3827, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.1588683351468988, | |
| "grad_norm": 0.3973180055618286, | |
| "learning_rate": 0.0001891555034593055, | |
| "loss": 0.1844, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.15995647442872687, | |
| "grad_norm": 0.36245423555374146, | |
| "learning_rate": 0.00018899844037326225, | |
| "loss": 0.2005, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.16104461371055495, | |
| "grad_norm": 0.5730637311935425, | |
| "learning_rate": 0.0001888403142366049, | |
| "loss": 0.2742, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.16213275299238303, | |
| "grad_norm": 0.5383718013763428, | |
| "learning_rate": 0.00018868112693808665, | |
| "loss": 0.2249, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.1632208922742111, | |
| "grad_norm": 0.9835379123687744, | |
| "learning_rate": 0.00018852088037913577, | |
| "loss": 0.344, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.16430903155603918, | |
| "grad_norm": 0.09142426401376724, | |
| "learning_rate": 0.00018835957647383303, | |
| "loss": 0.0876, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.16539717083786726, | |
| "grad_norm": 0.09199874103069305, | |
| "learning_rate": 0.00018819721714888877, | |
| "loss": 0.0798, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.16648531011969533, | |
| "grad_norm": 0.08299195021390915, | |
| "learning_rate": 0.00018803380434362, | |
| "loss": 0.0746, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.16757344940152338, | |
| "grad_norm": 0.10273315012454987, | |
| "learning_rate": 0.00018786934000992688, | |
| "loss": 0.101, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.16866158868335146, | |
| "grad_norm": 0.08524151146411896, | |
| "learning_rate": 0.00018770382611226987, | |
| "loss": 0.0684, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.16974972796517954, | |
| "grad_norm": 0.10515481233596802, | |
| "learning_rate": 0.000187537264627646, | |
| "loss": 0.0809, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.1708378672470076, | |
| "grad_norm": 0.09009183198213577, | |
| "learning_rate": 0.00018736965754556528, | |
| "loss": 0.0955, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.1719260065288357, | |
| "grad_norm": 0.10571747273206711, | |
| "learning_rate": 0.00018720100686802694, | |
| "loss": 0.0847, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.17301414581066377, | |
| "grad_norm": 0.08275768160820007, | |
| "learning_rate": 0.00018703131460949554, | |
| "loss": 0.0799, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.17410228509249184, | |
| "grad_norm": 0.08440782129764557, | |
| "learning_rate": 0.00018686058279687698, | |
| "loss": 0.0672, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.17519042437431992, | |
| "grad_norm": 0.10261505097150803, | |
| "learning_rate": 0.00018668881346949417, | |
| "loss": 0.1004, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.176278563656148, | |
| "grad_norm": 0.08730655908584595, | |
| "learning_rate": 0.00018651600867906272, | |
| "loss": 0.0711, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.17736670293797607, | |
| "grad_norm": 0.10591359436511993, | |
| "learning_rate": 0.00018634217048966637, | |
| "loss": 0.0919, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.17845484221980412, | |
| "grad_norm": 0.09251653403043747, | |
| "learning_rate": 0.0001861673009777325, | |
| "loss": 0.078, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.1795429815016322, | |
| "grad_norm": 0.106822170317173, | |
| "learning_rate": 0.00018599140223200716, | |
| "loss": 0.0895, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.18063112078346028, | |
| "grad_norm": 0.11222364753484726, | |
| "learning_rate": 0.0001858144763535302, | |
| "loss": 0.0918, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.18171926006528835, | |
| "grad_norm": 0.1363314390182495, | |
| "learning_rate": 0.00018563652545561013, | |
| "loss": 0.1126, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.18280739934711643, | |
| "grad_norm": 0.09316174685955048, | |
| "learning_rate": 0.000185457551663799, | |
| "loss": 0.0799, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.1838955386289445, | |
| "grad_norm": 0.13098089396953583, | |
| "learning_rate": 0.00018527755711586678, | |
| "loss": 0.0994, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.18498367791077258, | |
| "grad_norm": 0.11433115601539612, | |
| "learning_rate": 0.00018509654396177609, | |
| "loss": 0.1072, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.18607181719260066, | |
| "grad_norm": 0.11261814087629318, | |
| "learning_rate": 0.00018491451436365627, | |
| "loss": 0.1011, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.18715995647442873, | |
| "grad_norm": 0.1038559302687645, | |
| "learning_rate": 0.00018473147049577774, | |
| "loss": 0.0746, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.1882480957562568, | |
| "grad_norm": 0.11395396292209625, | |
| "learning_rate": 0.00018454741454452603, | |
| "loss": 0.0792, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.1893362350380849, | |
| "grad_norm": 0.13332821428775787, | |
| "learning_rate": 0.00018436234870837547, | |
| "loss": 0.1041, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.19042437431991294, | |
| "grad_norm": 0.12438289821147919, | |
| "learning_rate": 0.00018417627519786315, | |
| "loss": 0.1066, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.191512513601741, | |
| "grad_norm": 0.1353287398815155, | |
| "learning_rate": 0.00018398919623556238, | |
| "loss": 0.1193, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.1926006528835691, | |
| "grad_norm": 0.13928581774234772, | |
| "learning_rate": 0.0001838011140560562, | |
| "loss": 0.1228, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.19368879216539717, | |
| "grad_norm": 0.1474994421005249, | |
| "learning_rate": 0.00018361203090591071, | |
| "loss": 0.0812, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.19477693144722524, | |
| "grad_norm": 0.1910678595304489, | |
| "learning_rate": 0.00018342194904364813, | |
| "loss": 0.1435, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.19586507072905332, | |
| "grad_norm": 0.16526034474372864, | |
| "learning_rate": 0.00018323087073971993, | |
| "loss": 0.1136, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.1969532100108814, | |
| "grad_norm": 0.1933068335056305, | |
| "learning_rate": 0.00018303879827647975, | |
| "loss": 0.1498, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.19804134929270947, | |
| "grad_norm": 0.1647845059633255, | |
| "learning_rate": 0.00018284573394815597, | |
| "loss": 0.0764, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.19912948857453755, | |
| "grad_norm": 0.19414739310741425, | |
| "learning_rate": 0.00018265168006082437, | |
| "loss": 0.1142, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.20021762785636563, | |
| "grad_norm": 0.1872360110282898, | |
| "learning_rate": 0.00018245663893238075, | |
| "loss": 0.1169, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.20130576713819368, | |
| "grad_norm": 0.19919492304325104, | |
| "learning_rate": 0.00018226061289251298, | |
| "loss": 0.0854, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.20239390642002175, | |
| "grad_norm": 0.2233375757932663, | |
| "learning_rate": 0.00018206360428267332, | |
| "loss": 0.1271, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.20348204570184983, | |
| "grad_norm": 0.22116345167160034, | |
| "learning_rate": 0.00018186561545605054, | |
| "loss": 0.1402, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.2045701849836779, | |
| "grad_norm": 0.253864049911499, | |
| "learning_rate": 0.0001816666487775416, | |
| "loss": 0.1431, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.20565832426550598, | |
| "grad_norm": 0.2945636212825775, | |
| "learning_rate": 0.00018146670662372354, | |
| "loss": 0.1284, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.20674646354733406, | |
| "grad_norm": 0.24834126234054565, | |
| "learning_rate": 0.00018126579138282503, | |
| "loss": 0.098, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.20783460282916214, | |
| "grad_norm": 0.26815730333328247, | |
| "learning_rate": 0.00018106390545469795, | |
| "loss": 0.0877, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.2089227421109902, | |
| "grad_norm": 0.375293493270874, | |
| "learning_rate": 0.00018086105125078857, | |
| "loss": 0.1985, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.2100108813928183, | |
| "grad_norm": 0.4025906026363373, | |
| "learning_rate": 0.00018065723119410884, | |
| "loss": 0.2082, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.21109902067464636, | |
| "grad_norm": 0.3551553785800934, | |
| "learning_rate": 0.0001804524477192075, | |
| "loss": 0.2305, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.21218715995647444, | |
| "grad_norm": 0.594780445098877, | |
| "learning_rate": 0.00018024670327214084, | |
| "loss": 0.2713, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.2132752992383025, | |
| "grad_norm": 0.3940027356147766, | |
| "learning_rate": 0.0001800400003104436, | |
| "loss": 0.1623, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.21436343852013057, | |
| "grad_norm": 0.51041579246521, | |
| "learning_rate": 0.00017983234130309968, | |
| "loss": 0.2236, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.21545157780195864, | |
| "grad_norm": 0.6203753352165222, | |
| "learning_rate": 0.00017962372873051252, | |
| "loss": 0.2654, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.21653971708378672, | |
| "grad_norm": 0.7527713179588318, | |
| "learning_rate": 0.00017941416508447536, | |
| "loss": 0.2088, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.2176278563656148, | |
| "grad_norm": 1.1047406196594238, | |
| "learning_rate": 0.00017920365286814183, | |
| "loss": 0.3097, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.21871599564744287, | |
| "grad_norm": 0.0492124930024147, | |
| "learning_rate": 0.0001789921945959958, | |
| "loss": 0.0344, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 0.21980413492927095, | |
| "grad_norm": 0.07087790220975876, | |
| "learning_rate": 0.00017877979279382135, | |
| "loss": 0.0582, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 0.22089227421109903, | |
| "grad_norm": 0.07622935622930527, | |
| "learning_rate": 0.00017856644999867264, | |
| "loss": 0.062, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 0.2219804134929271, | |
| "grad_norm": 0.08792652189731598, | |
| "learning_rate": 0.00017835216875884368, | |
| "loss": 0.0511, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 0.22306855277475518, | |
| "grad_norm": 0.08028998970985413, | |
| "learning_rate": 0.0001781369516338378, | |
| "loss": 0.0665, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.22415669205658323, | |
| "grad_norm": 0.08997032046318054, | |
| "learning_rate": 0.0001779208011943371, | |
| "loss": 0.069, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 0.2252448313384113, | |
| "grad_norm": 0.08684886246919632, | |
| "learning_rate": 0.00017770372002217172, | |
| "loss": 0.077, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 0.22633297062023938, | |
| "grad_norm": 0.0965440422296524, | |
| "learning_rate": 0.000177485710710289, | |
| "loss": 0.0782, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 0.22742110990206746, | |
| "grad_norm": 0.09060367196798325, | |
| "learning_rate": 0.00017726677586272263, | |
| "loss": 0.066, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 0.22850924918389554, | |
| "grad_norm": 0.0900409147143364, | |
| "learning_rate": 0.00017704691809456143, | |
| "loss": 0.0707, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.2295973884657236, | |
| "grad_norm": 0.10733999311923981, | |
| "learning_rate": 0.00017682614003191807, | |
| "loss": 0.0916, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 0.2306855277475517, | |
| "grad_norm": 0.09372083842754364, | |
| "learning_rate": 0.0001766044443118978, | |
| "loss": 0.0872, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 0.23177366702937977, | |
| "grad_norm": 0.10344577580690384, | |
| "learning_rate": 0.00017638183358256696, | |
| "loss": 0.0903, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 0.23286180631120784, | |
| "grad_norm": 0.1084800437092781, | |
| "learning_rate": 0.0001761583105029213, | |
| "loss": 0.0926, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 0.23394994559303592, | |
| "grad_norm": 0.08565113693475723, | |
| "learning_rate": 0.00017593387774285412, | |
| "loss": 0.0758, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.235038084874864, | |
| "grad_norm": 0.11589045077562332, | |
| "learning_rate": 0.0001757085379831246, | |
| "loss": 0.0925, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 0.23612622415669204, | |
| "grad_norm": 0.12087468057870865, | |
| "learning_rate": 0.00017548229391532572, | |
| "loss": 0.1012, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 0.23721436343852012, | |
| "grad_norm": 0.1125798150897026, | |
| "learning_rate": 0.00017525514824185185, | |
| "loss": 0.109, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 0.2383025027203482, | |
| "grad_norm": 0.12492644041776657, | |
| "learning_rate": 0.00017502710367586687, | |
| "loss": 0.1048, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 0.23939064200217627, | |
| "grad_norm": 0.09837982058525085, | |
| "learning_rate": 0.00017479816294127152, | |
| "loss": 0.0803, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.24047878128400435, | |
| "grad_norm": 0.099558524787426, | |
| "learning_rate": 0.00017456832877267084, | |
| "loss": 0.0552, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 0.24156692056583243, | |
| "grad_norm": 0.095551498234272, | |
| "learning_rate": 0.00017433760391534167, | |
| "loss": 0.0905, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 0.2426550598476605, | |
| "grad_norm": 0.11664412170648575, | |
| "learning_rate": 0.0001741059911251997, | |
| "loss": 0.1005, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 0.24374319912948858, | |
| "grad_norm": 0.1248706802725792, | |
| "learning_rate": 0.00017387349316876666, | |
| "loss": 0.1135, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 0.24483133841131666, | |
| "grad_norm": 0.13133874535560608, | |
| "learning_rate": 0.0001736401128231373, | |
| "loss": 0.121, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.24591947769314473, | |
| "grad_norm": 0.12476039677858353, | |
| "learning_rate": 0.00017340585287594604, | |
| "loss": 0.1025, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 0.2470076169749728, | |
| "grad_norm": 0.1645650863647461, | |
| "learning_rate": 0.0001731707161253338, | |
| "loss": 0.1313, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 0.24809575625680086, | |
| "grad_norm": 0.1172671690583229, | |
| "learning_rate": 0.00017293470537991463, | |
| "loss": 0.0801, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 0.24918389553862894, | |
| "grad_norm": 0.17031441628932953, | |
| "learning_rate": 0.00017269782345874203, | |
| "loss": 0.154, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 0.250272034820457, | |
| "grad_norm": 0.16571593284606934, | |
| "learning_rate": 0.00017246007319127545, | |
| "loss": 0.1209, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.250272034820457, | |
| "eval_loss": 0.12318640202283859, | |
| "eval_runtime": 24.4163, | |
| "eval_samples_per_second": 15.85, | |
| "eval_steps_per_second": 7.945, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.2513601741022851, | |
| "grad_norm": 0.14655253291130066, | |
| "learning_rate": 0.00017222145741734626, | |
| "loss": 0.0879, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 0.25244831338411317, | |
| "grad_norm": 0.17367680370807648, | |
| "learning_rate": 0.00017198197898712404, | |
| "loss": 0.1261, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 0.2535364526659412, | |
| "grad_norm": 0.14948749542236328, | |
| "learning_rate": 0.0001717416407610824, | |
| "loss": 0.0874, | |
| "step": 233 | |
| }, | |
| { | |
| "epoch": 0.2546245919477693, | |
| "grad_norm": 0.19695116579532623, | |
| "learning_rate": 0.00017150044560996488, | |
| "loss": 0.1119, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 0.25571273122959737, | |
| "grad_norm": 0.2416209876537323, | |
| "learning_rate": 0.00017125839641475072, | |
| "loss": 0.1495, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.25680087051142547, | |
| "grad_norm": 0.23595106601715088, | |
| "learning_rate": 0.00017101549606662024, | |
| "loss": 0.092, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 0.2578890097932535, | |
| "grad_norm": 0.3377005457878113, | |
| "learning_rate": 0.00017077174746692056, | |
| "loss": 0.1537, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 0.2589771490750816, | |
| "grad_norm": 0.31011515855789185, | |
| "learning_rate": 0.00017052715352713075, | |
| "loss": 0.2351, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 0.2600652883569097, | |
| "grad_norm": 0.2296973615884781, | |
| "learning_rate": 0.00017028171716882714, | |
| "loss": 0.1034, | |
| "step": 239 | |
| }, | |
| { | |
| "epoch": 0.2611534276387378, | |
| "grad_norm": 0.33184927701950073, | |
| "learning_rate": 0.00017003544132364846, | |
| "loss": 0.1518, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.2622415669205658, | |
| "grad_norm": 0.333794504404068, | |
| "learning_rate": 0.00016978832893326074, | |
| "loss": 0.1167, | |
| "step": 241 | |
| }, | |
| { | |
| "epoch": 0.26332970620239393, | |
| "grad_norm": 0.33567357063293457, | |
| "learning_rate": 0.00016954038294932216, | |
| "loss": 0.1672, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 0.264417845484222, | |
| "grad_norm": 0.3648099899291992, | |
| "learning_rate": 0.0001692916063334479, | |
| "loss": 0.1562, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 0.26550598476605003, | |
| "grad_norm": 0.3762454092502594, | |
| "learning_rate": 0.0001690420020571747, | |
| "loss": 0.1495, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 0.26659412404787813, | |
| "grad_norm": 0.42424383759498596, | |
| "learning_rate": 0.00016879157310192535, | |
| "loss": 0.1763, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.2676822633297062, | |
| "grad_norm": 0.4968826472759247, | |
| "learning_rate": 0.00016854032245897308, | |
| "loss": 0.2473, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 0.2687704026115343, | |
| "grad_norm": 0.5231485366821289, | |
| "learning_rate": 0.00016828825312940592, | |
| "loss": 0.2924, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 0.26985854189336234, | |
| "grad_norm": 0.5466935634613037, | |
| "learning_rate": 0.00016803536812409075, | |
| "loss": 0.2519, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 0.27094668117519044, | |
| "grad_norm": 0.6696439981460571, | |
| "learning_rate": 0.00016778167046363734, | |
| "loss": 0.2106, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 0.2720348204570185, | |
| "grad_norm": 0.7066907286643982, | |
| "learning_rate": 0.00016752716317836229, | |
| "loss": 0.2733, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.2731229597388466, | |
| "grad_norm": 0.058309707790613174, | |
| "learning_rate": 0.00016727184930825288, | |
| "loss": 0.0459, | |
| "step": 251 | |
| }, | |
| { | |
| "epoch": 0.27421109902067464, | |
| "grad_norm": 0.06278934329748154, | |
| "learning_rate": 0.00016701573190293077, | |
| "loss": 0.049, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 0.27529923830250275, | |
| "grad_norm": 0.07942797988653183, | |
| "learning_rate": 0.00016675881402161536, | |
| "loss": 0.0757, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 0.2763873775843308, | |
| "grad_norm": 0.0874176099896431, | |
| "learning_rate": 0.00016650109873308765, | |
| "loss": 0.0952, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 0.27747551686615884, | |
| "grad_norm": 0.0788157656788826, | |
| "learning_rate": 0.0001662425891156531, | |
| "loss": 0.0655, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.27856365614798695, | |
| "grad_norm": 0.08784733712673187, | |
| "learning_rate": 0.00016598328825710533, | |
| "loss": 0.0778, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 0.279651795429815, | |
| "grad_norm": 0.09089700132608414, | |
| "learning_rate": 0.00016572319925468892, | |
| "loss": 0.0767, | |
| "step": 257 | |
| }, | |
| { | |
| "epoch": 0.2807399347116431, | |
| "grad_norm": 0.07957662642002106, | |
| "learning_rate": 0.0001654623252150624, | |
| "loss": 0.0623, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 0.28182807399347115, | |
| "grad_norm": 0.08320681005716324, | |
| "learning_rate": 0.00016520066925426144, | |
| "loss": 0.0812, | |
| "step": 259 | |
| }, | |
| { | |
| "epoch": 0.28291621327529926, | |
| "grad_norm": 0.10143834352493286, | |
| "learning_rate": 0.00016493823449766136, | |
| "loss": 0.0953, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.2840043525571273, | |
| "grad_norm": 0.1192905604839325, | |
| "learning_rate": 0.00016467502407993992, | |
| "loss": 0.1163, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 0.2850924918389554, | |
| "grad_norm": 0.11428846418857574, | |
| "learning_rate": 0.0001644110411450398, | |
| "loss": 0.1028, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 0.28618063112078346, | |
| "grad_norm": 0.11233223229646683, | |
| "learning_rate": 0.00016414628884613107, | |
| "loss": 0.091, | |
| "step": 263 | |
| }, | |
| { | |
| "epoch": 0.28726877040261156, | |
| "grad_norm": 0.10367966443300247, | |
| "learning_rate": 0.00016388077034557355, | |
| "loss": 0.0797, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 0.2883569096844396, | |
| "grad_norm": 0.11604032665491104, | |
| "learning_rate": 0.00016361448881487914, | |
| "loss": 0.0919, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.28944504896626766, | |
| "grad_norm": 0.10309276729822159, | |
| "learning_rate": 0.00016334744743467364, | |
| "loss": 0.1065, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 0.29053318824809576, | |
| "grad_norm": 0.11475658416748047, | |
| "learning_rate": 0.00016307964939465914, | |
| "loss": 0.0959, | |
| "step": 267 | |
| }, | |
| { | |
| "epoch": 0.2916213275299238, | |
| "grad_norm": 0.1230575293302536, | |
| "learning_rate": 0.0001628110978935756, | |
| "loss": 0.1031, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 0.2927094668117519, | |
| "grad_norm": 0.1267620474100113, | |
| "learning_rate": 0.00016254179613916278, | |
| "loss": 0.1219, | |
| "step": 269 | |
| }, | |
| { | |
| "epoch": 0.29379760609357997, | |
| "grad_norm": 0.1032036617398262, | |
| "learning_rate": 0.000162271747348122, | |
| "loss": 0.0792, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.29488574537540807, | |
| "grad_norm": 0.10867134481668472, | |
| "learning_rate": 0.00016200095474607753, | |
| "loss": 0.0964, | |
| "step": 271 | |
| }, | |
| { | |
| "epoch": 0.2959738846572361, | |
| "grad_norm": 0.13934585452079773, | |
| "learning_rate": 0.0001617294215675382, | |
| "loss": 0.1493, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 0.2970620239390642, | |
| "grad_norm": 0.1254916936159134, | |
| "learning_rate": 0.0001614571510558588, | |
| "loss": 0.1035, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 0.2981501632208923, | |
| "grad_norm": 0.10226383805274963, | |
| "learning_rate": 0.0001611841464632011, | |
| "loss": 0.0777, | |
| "step": 274 | |
| }, | |
| { | |
| "epoch": 0.2992383025027203, | |
| "grad_norm": 0.11369970440864563, | |
| "learning_rate": 0.0001609104110504954, | |
| "loss": 0.0823, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.3003264417845484, | |
| "grad_norm": 0.11098276078701019, | |
| "learning_rate": 0.00016063594808740113, | |
| "loss": 0.0976, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 0.3014145810663765, | |
| "grad_norm": 0.13366885483264923, | |
| "learning_rate": 0.00016036076085226814, | |
| "loss": 0.1378, | |
| "step": 277 | |
| }, | |
| { | |
| "epoch": 0.3025027203482046, | |
| "grad_norm": 0.11494230479001999, | |
| "learning_rate": 0.00016008485263209742, | |
| "loss": 0.072, | |
| "step": 278 | |
| }, | |
| { | |
| "epoch": 0.30359085963003263, | |
| "grad_norm": 0.11145862936973572, | |
| "learning_rate": 0.0001598082267225018, | |
| "loss": 0.066, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 0.30467899891186073, | |
| "grad_norm": 0.1483200490474701, | |
| "learning_rate": 0.0001595308864276666, | |
| "loss": 0.1023, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.3057671381936888, | |
| "grad_norm": 0.12836772203445435, | |
| "learning_rate": 0.0001592528350603103, | |
| "loss": 0.0682, | |
| "step": 281 | |
| }, | |
| { | |
| "epoch": 0.3068552774755169, | |
| "grad_norm": 0.16118410229682922, | |
| "learning_rate": 0.00015897407594164467, | |
| "loss": 0.1025, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 0.30794341675734493, | |
| "grad_norm": 0.22559022903442383, | |
| "learning_rate": 0.0001586946124013354, | |
| "loss": 0.1228, | |
| "step": 283 | |
| }, | |
| { | |
| "epoch": 0.30903155603917304, | |
| "grad_norm": 0.233434796333313, | |
| "learning_rate": 0.0001584144477774623, | |
| "loss": 0.1928, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 0.3101196953210011, | |
| "grad_norm": 0.21861650049686432, | |
| "learning_rate": 0.00015813358541647915, | |
| "loss": 0.1054, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.31120783460282914, | |
| "grad_norm": 0.2723356783390045, | |
| "learning_rate": 0.00015785202867317407, | |
| "loss": 0.1411, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 0.31229597388465724, | |
| "grad_norm": 0.3065739870071411, | |
| "learning_rate": 0.0001575697809106292, | |
| "loss": 0.1785, | |
| "step": 287 | |
| }, | |
| { | |
| "epoch": 0.3133841131664853, | |
| "grad_norm": 0.2983495593070984, | |
| "learning_rate": 0.00015728684550018064, | |
| "loss": 0.1402, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 0.3144722524483134, | |
| "grad_norm": 0.3250825107097626, | |
| "learning_rate": 0.00015700322582137827, | |
| "loss": 0.1929, | |
| "step": 289 | |
| }, | |
| { | |
| "epoch": 0.31556039173014144, | |
| "grad_norm": 0.35388973355293274, | |
| "learning_rate": 0.00015671892526194516, | |
| "loss": 0.1791, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.31664853101196955, | |
| "grad_norm": 0.32610148191452026, | |
| "learning_rate": 0.0001564339472177373, | |
| "loss": 0.1289, | |
| "step": 291 | |
| }, | |
| { | |
| "epoch": 0.3177366702937976, | |
| "grad_norm": 0.4028049409389496, | |
| "learning_rate": 0.0001561482950927029, | |
| "loss": 0.2026, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 0.3188248095756257, | |
| "grad_norm": 0.2420492172241211, | |
| "learning_rate": 0.00015586197229884184, | |
| "loss": 0.098, | |
| "step": 293 | |
| }, | |
| { | |
| "epoch": 0.31991294885745375, | |
| "grad_norm": 0.3512971103191376, | |
| "learning_rate": 0.00015557498225616487, | |
| "loss": 0.205, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 0.32100108813928185, | |
| "grad_norm": 0.39271989464759827, | |
| "learning_rate": 0.00015528732839265272, | |
| "loss": 0.1473, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.3220892274211099, | |
| "grad_norm": 0.3802226185798645, | |
| "learning_rate": 0.0001549990141442153, | |
| "loss": 0.136, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 0.32317736670293795, | |
| "grad_norm": 0.5737869739532471, | |
| "learning_rate": 0.00015471004295465035, | |
| "loss": 0.3053, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 0.32426550598476606, | |
| "grad_norm": 0.45224013924598694, | |
| "learning_rate": 0.00015442041827560274, | |
| "loss": 0.222, | |
| "step": 298 | |
| }, | |
| { | |
| "epoch": 0.3253536452665941, | |
| "grad_norm": 0.522432267665863, | |
| "learning_rate": 0.00015413014356652286, | |
| "loss": 0.1809, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 0.3264417845484222, | |
| "grad_norm": 0.6229780316352844, | |
| "learning_rate": 0.00015383922229462549, | |
| "loss": 0.2081, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.32752992383025026, | |
| "grad_norm": 0.053111448884010315, | |
| "learning_rate": 0.00015354765793484834, | |
| "loss": 0.0414, | |
| "step": 301 | |
| }, | |
| { | |
| "epoch": 0.32861806311207836, | |
| "grad_norm": 0.07464036345481873, | |
| "learning_rate": 0.0001532554539698105, | |
| "loss": 0.0639, | |
| "step": 302 | |
| }, | |
| { | |
| "epoch": 0.3297062023939064, | |
| "grad_norm": 0.08635352551937103, | |
| "learning_rate": 0.00015296261388977108, | |
| "loss": 0.074, | |
| "step": 303 | |
| }, | |
| { | |
| "epoch": 0.3307943416757345, | |
| "grad_norm": 0.0818236917257309, | |
| "learning_rate": 0.000152669141192587, | |
| "loss": 0.0843, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 0.33188248095756256, | |
| "grad_norm": 0.08959626406431198, | |
| "learning_rate": 0.00015237503938367186, | |
| "loss": 0.0752, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.33297062023939067, | |
| "grad_norm": 0.087018683552742, | |
| "learning_rate": 0.00015208031197595356, | |
| "loss": 0.074, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 0.3340587595212187, | |
| "grad_norm": 0.10946961492300034, | |
| "learning_rate": 0.00015178496248983254, | |
| "loss": 0.0907, | |
| "step": 307 | |
| }, | |
| { | |
| "epoch": 0.33514689880304677, | |
| "grad_norm": 0.09914237260818481, | |
| "learning_rate": 0.00015148899445313981, | |
| "loss": 0.0939, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 0.33623503808487487, | |
| "grad_norm": 0.07641992717981339, | |
| "learning_rate": 0.00015119241140109467, | |
| "loss": 0.0587, | |
| "step": 309 | |
| }, | |
| { | |
| "epoch": 0.3373231773667029, | |
| "grad_norm": 0.10857319831848145, | |
| "learning_rate": 0.00015089521687626243, | |
| "loss": 0.1052, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.338411316648531, | |
| "grad_norm": 0.0868939459323883, | |
| "learning_rate": 0.0001505974144285124, | |
| "loss": 0.0723, | |
| "step": 311 | |
| }, | |
| { | |
| "epoch": 0.3394994559303591, | |
| "grad_norm": 0.11470666527748108, | |
| "learning_rate": 0.00015029900761497506, | |
| "loss": 0.0972, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 0.3405875952121872, | |
| "grad_norm": 0.09828225523233414, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.0904, | |
| "step": 313 | |
| }, | |
| { | |
| "epoch": 0.3416757344940152, | |
| "grad_norm": 0.09422045201063156, | |
| "learning_rate": 0.00014970039515511304, | |
| "loss": 0.0736, | |
| "step": 314 | |
| }, | |
| { | |
| "epoch": 0.34276387377584333, | |
| "grad_norm": 0.09876245260238647, | |
| "learning_rate": 0.0001494001966589736, | |
| "loss": 0.0849, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.3438520130576714, | |
| "grad_norm": 0.1073005348443985, | |
| "learning_rate": 0.00014909940809733222, | |
| "loss": 0.0842, | |
| "step": 316 | |
| }, | |
| { | |
| "epoch": 0.34494015233949943, | |
| "grad_norm": 0.11519600450992584, | |
| "learning_rate": 0.00014879803306298736, | |
| "loss": 0.0901, | |
| "step": 317 | |
| }, | |
| { | |
| "epoch": 0.34602829162132753, | |
| "grad_norm": 0.10380937904119492, | |
| "learning_rate": 0.00014849607515574276, | |
| "loss": 0.0688, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 0.3471164309031556, | |
| "grad_norm": 0.10230353474617004, | |
| "learning_rate": 0.00014819353798236427, | |
| "loss": 0.064, | |
| "step": 319 | |
| }, | |
| { | |
| "epoch": 0.3482045701849837, | |
| "grad_norm": 0.10846245288848877, | |
| "learning_rate": 0.00014789042515653687, | |
| "loss": 0.0815, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.34929270946681173, | |
| "grad_norm": 0.11520566791296005, | |
| "learning_rate": 0.00014758674029882152, | |
| "loss": 0.0846, | |
| "step": 321 | |
| }, | |
| { | |
| "epoch": 0.35038084874863984, | |
| "grad_norm": 0.16834412515163422, | |
| "learning_rate": 0.00014728248703661182, | |
| "loss": 0.1249, | |
| "step": 322 | |
| }, | |
| { | |
| "epoch": 0.3514689880304679, | |
| "grad_norm": 0.11053828150033951, | |
| "learning_rate": 0.00014697766900409074, | |
| "loss": 0.073, | |
| "step": 323 | |
| }, | |
| { | |
| "epoch": 0.352557127312296, | |
| "grad_norm": 0.12219499796628952, | |
| "learning_rate": 0.0001466722898421873, | |
| "loss": 0.0943, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 0.35364526659412404, | |
| "grad_norm": 0.1294214427471161, | |
| "learning_rate": 0.00014636635319853275, | |
| "loss": 0.0761, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.35473340587595215, | |
| "grad_norm": 0.13043484091758728, | |
| "learning_rate": 0.00014605986272741748, | |
| "loss": 0.1065, | |
| "step": 326 | |
| }, | |
| { | |
| "epoch": 0.3558215451577802, | |
| "grad_norm": 0.1078469529747963, | |
| "learning_rate": 0.00014575282208974702, | |
| "loss": 0.0718, | |
| "step": 327 | |
| }, | |
| { | |
| "epoch": 0.35690968443960824, | |
| "grad_norm": 0.17083537578582764, | |
| "learning_rate": 0.00014544523495299842, | |
| "loss": 0.1035, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 0.35799782372143635, | |
| "grad_norm": 0.1370207518339157, | |
| "learning_rate": 0.00014513710499117647, | |
| "loss": 0.089, | |
| "step": 329 | |
| }, | |
| { | |
| "epoch": 0.3590859630032644, | |
| "grad_norm": 0.1698474884033203, | |
| "learning_rate": 0.00014482843588476974, | |
| "loss": 0.1172, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.3601741022850925, | |
| "grad_norm": 0.1472265124320984, | |
| "learning_rate": 0.0001445192313207067, | |
| "loss": 0.0782, | |
| "step": 331 | |
| }, | |
| { | |
| "epoch": 0.36126224156692055, | |
| "grad_norm": 0.153669074177742, | |
| "learning_rate": 0.00014420949499231172, | |
| "loss": 0.0844, | |
| "step": 332 | |
| }, | |
| { | |
| "epoch": 0.36235038084874865, | |
| "grad_norm": 0.2612091600894928, | |
| "learning_rate": 0.00014389923059926062, | |
| "loss": 0.1256, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 0.3634385201305767, | |
| "grad_norm": 0.18867933750152588, | |
| "learning_rate": 0.00014358844184753712, | |
| "loss": 0.0822, | |
| "step": 334 | |
| }, | |
| { | |
| "epoch": 0.3645266594124048, | |
| "grad_norm": 0.29405227303504944, | |
| "learning_rate": 0.0001432771324493879, | |
| "loss": 0.1562, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.36561479869423286, | |
| "grad_norm": 0.299411803483963, | |
| "learning_rate": 0.00014296530612327863, | |
| "loss": 0.151, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 0.36670293797606096, | |
| "grad_norm": 0.4020368754863739, | |
| "learning_rate": 0.00014265296659384956, | |
| "loss": 0.2564, | |
| "step": 337 | |
| }, | |
| { | |
| "epoch": 0.367791077257889, | |
| "grad_norm": 0.27561965584754944, | |
| "learning_rate": 0.00014234011759187083, | |
| "loss": 0.1193, | |
| "step": 338 | |
| }, | |
| { | |
| "epoch": 0.36887921653971706, | |
| "grad_norm": 0.36899837851524353, | |
| "learning_rate": 0.00014202676285419812, | |
| "loss": 0.1844, | |
| "step": 339 | |
| }, | |
| { | |
| "epoch": 0.36996735582154516, | |
| "grad_norm": 0.3305605351924896, | |
| "learning_rate": 0.0001417129061237278, | |
| "loss": 0.0825, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.3710554951033732, | |
| "grad_norm": 0.45063266158103943, | |
| "learning_rate": 0.00014139855114935252, | |
| "loss": 0.2383, | |
| "step": 341 | |
| }, | |
| { | |
| "epoch": 0.3721436343852013, | |
| "grad_norm": 0.319297730922699, | |
| "learning_rate": 0.0001410837016859161, | |
| "loss": 0.1054, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 0.37323177366702937, | |
| "grad_norm": 0.3711492121219635, | |
| "learning_rate": 0.00014076836149416887, | |
| "loss": 0.1265, | |
| "step": 343 | |
| }, | |
| { | |
| "epoch": 0.37431991294885747, | |
| "grad_norm": 0.4362325966358185, | |
| "learning_rate": 0.0001404525343407228, | |
| "loss": 0.1818, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 0.3754080522306855, | |
| "grad_norm": 0.39839836955070496, | |
| "learning_rate": 0.00014013622399800627, | |
| "loss": 0.173, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.3764961915125136, | |
| "grad_norm": 0.4215060770511627, | |
| "learning_rate": 0.00013981943424421932, | |
| "loss": 0.1225, | |
| "step": 346 | |
| }, | |
| { | |
| "epoch": 0.37758433079434167, | |
| "grad_norm": 0.4466668963432312, | |
| "learning_rate": 0.0001395021688632882, | |
| "loss": 0.1336, | |
| "step": 347 | |
| }, | |
| { | |
| "epoch": 0.3786724700761698, | |
| "grad_norm": 0.490313321352005, | |
| "learning_rate": 0.00013918443164482046, | |
| "loss": 0.1364, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 0.3797606093579978, | |
| "grad_norm": 0.6865617036819458, | |
| "learning_rate": 0.00013886622638405952, | |
| "loss": 0.2864, | |
| "step": 349 | |
| }, | |
| { | |
| "epoch": 0.3808487486398259, | |
| "grad_norm": 0.7716324925422668, | |
| "learning_rate": 0.0001385475568818394, | |
| "loss": 0.2994, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.381936887921654, | |
| "grad_norm": 0.04748038947582245, | |
| "learning_rate": 0.00013822842694453924, | |
| "loss": 0.0425, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 0.383025027203482, | |
| "grad_norm": 0.06222306191921234, | |
| "learning_rate": 0.00013790884038403795, | |
| "loss": 0.0519, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 0.38411316648531013, | |
| "grad_norm": 0.07450418174266815, | |
| "learning_rate": 0.0001375888010176686, | |
| "loss": 0.0629, | |
| "step": 353 | |
| }, | |
| { | |
| "epoch": 0.3852013057671382, | |
| "grad_norm": 0.08733393251895905, | |
| "learning_rate": 0.00013726831266817278, | |
| "loss": 0.0701, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 0.3862894450489663, | |
| "grad_norm": 0.09622704982757568, | |
| "learning_rate": 0.00013694737916365517, | |
| "loss": 0.0909, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.38737758433079433, | |
| "grad_norm": 0.08062370121479034, | |
| "learning_rate": 0.00013662600433753745, | |
| "loss": 0.0722, | |
| "step": 356 | |
| }, | |
| { | |
| "epoch": 0.38846572361262244, | |
| "grad_norm": 0.09811591356992722, | |
| "learning_rate": 0.00013630419202851284, | |
| "loss": 0.0894, | |
| "step": 357 | |
| }, | |
| { | |
| "epoch": 0.3895538628944505, | |
| "grad_norm": 0.0917980894446373, | |
| "learning_rate": 0.0001359819460805001, | |
| "loss": 0.0816, | |
| "step": 358 | |
| }, | |
| { | |
| "epoch": 0.3906420021762786, | |
| "grad_norm": 0.08292034268379211, | |
| "learning_rate": 0.0001356592703425976, | |
| "loss": 0.0832, | |
| "step": 359 | |
| }, | |
| { | |
| "epoch": 0.39173014145810664, | |
| "grad_norm": 0.0940559059381485, | |
| "learning_rate": 0.00013533616866903735, | |
| "loss": 0.078, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.3928182807399347, | |
| "grad_norm": 0.09960496425628662, | |
| "learning_rate": 0.00013501264491913906, | |
| "loss": 0.0899, | |
| "step": 361 | |
| }, | |
| { | |
| "epoch": 0.3939064200217628, | |
| "grad_norm": 0.1174091249704361, | |
| "learning_rate": 0.00013468870295726398, | |
| "loss": 0.0983, | |
| "step": 362 | |
| }, | |
| { | |
| "epoch": 0.39499455930359084, | |
| "grad_norm": 0.1083730086684227, | |
| "learning_rate": 0.00013436434665276865, | |
| "loss": 0.1004, | |
| "step": 363 | |
| }, | |
| { | |
| "epoch": 0.39608269858541895, | |
| "grad_norm": 0.09829343855381012, | |
| "learning_rate": 0.00013403957987995882, | |
| "loss": 0.0851, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 0.397170837867247, | |
| "grad_norm": 0.1172933354973793, | |
| "learning_rate": 0.00013371440651804313, | |
| "loss": 0.1033, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.3982589771490751, | |
| "grad_norm": 0.11004797369241714, | |
| "learning_rate": 0.00013338883045108674, | |
| "loss": 0.0852, | |
| "step": 366 | |
| }, | |
| { | |
| "epoch": 0.39934711643090315, | |
| "grad_norm": 0.10466606914997101, | |
| "learning_rate": 0.00013306285556796495, | |
| "loss": 0.0893, | |
| "step": 367 | |
| }, | |
| { | |
| "epoch": 0.40043525571273125, | |
| "grad_norm": 0.121376633644104, | |
| "learning_rate": 0.0001327364857623168, | |
| "loss": 0.1037, | |
| "step": 368 | |
| }, | |
| { | |
| "epoch": 0.4015233949945593, | |
| "grad_norm": 0.10333437472581863, | |
| "learning_rate": 0.00013240972493249847, | |
| "loss": 0.0981, | |
| "step": 369 | |
| }, | |
| { | |
| "epoch": 0.40261153427638735, | |
| "grad_norm": 0.1174560934305191, | |
| "learning_rate": 0.00013208257698153677, | |
| "loss": 0.1187, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.40369967355821545, | |
| "grad_norm": 0.09671124815940857, | |
| "learning_rate": 0.0001317550458170826, | |
| "loss": 0.0771, | |
| "step": 371 | |
| }, | |
| { | |
| "epoch": 0.4047878128400435, | |
| "grad_norm": 0.11311496794223785, | |
| "learning_rate": 0.00013142713535136414, | |
| "loss": 0.0915, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 0.4058759521218716, | |
| "grad_norm": 0.11149045825004578, | |
| "learning_rate": 0.00013109884950114007, | |
| "loss": 0.078, | |
| "step": 373 | |
| }, | |
| { | |
| "epoch": 0.40696409140369966, | |
| "grad_norm": 0.15049664676189423, | |
| "learning_rate": 0.00013077019218765305, | |
| "loss": 0.1008, | |
| "step": 374 | |
| }, | |
| { | |
| "epoch": 0.40805223068552776, | |
| "grad_norm": 0.13566477596759796, | |
| "learning_rate": 0.0001304411673365826, | |
| "loss": 0.1116, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.4091403699673558, | |
| "grad_norm": 0.1317652463912964, | |
| "learning_rate": 0.00013011177887799845, | |
| "loss": 0.1068, | |
| "step": 376 | |
| }, | |
| { | |
| "epoch": 0.4102285092491839, | |
| "grad_norm": 0.12117652595043182, | |
| "learning_rate": 0.00012978203074631334, | |
| "loss": 0.0926, | |
| "step": 377 | |
| }, | |
| { | |
| "epoch": 0.41131664853101196, | |
| "grad_norm": 0.13246335089206696, | |
| "learning_rate": 0.00012945192688023624, | |
| "loss": 0.0867, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 0.41240478781284007, | |
| "grad_norm": 0.1427900642156601, | |
| "learning_rate": 0.00012912147122272523, | |
| "loss": 0.1054, | |
| "step": 379 | |
| }, | |
| { | |
| "epoch": 0.4134929270946681, | |
| "grad_norm": 0.13975268602371216, | |
| "learning_rate": 0.0001287906677209403, | |
| "loss": 0.0993, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.41458106637649617, | |
| "grad_norm": 0.16829046607017517, | |
| "learning_rate": 0.0001284595203261965, | |
| "loss": 0.0986, | |
| "step": 381 | |
| }, | |
| { | |
| "epoch": 0.41566920565832427, | |
| "grad_norm": 0.18288354575634003, | |
| "learning_rate": 0.00012812803299391628, | |
| "loss": 0.1164, | |
| "step": 382 | |
| }, | |
| { | |
| "epoch": 0.4167573449401523, | |
| "grad_norm": 0.20097504556179047, | |
| "learning_rate": 0.00012779620968358273, | |
| "loss": 0.1273, | |
| "step": 383 | |
| }, | |
| { | |
| "epoch": 0.4178454842219804, | |
| "grad_norm": 0.1646791398525238, | |
| "learning_rate": 0.00012746405435869198, | |
| "loss": 0.0833, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 0.41893362350380847, | |
| "grad_norm": 0.1997787058353424, | |
| "learning_rate": 0.0001271315709867059, | |
| "loss": 0.1495, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.4200217627856366, | |
| "grad_norm": 0.1489897519350052, | |
| "learning_rate": 0.00012679876353900482, | |
| "loss": 0.0756, | |
| "step": 386 | |
| }, | |
| { | |
| "epoch": 0.4211099020674646, | |
| "grad_norm": 0.22502455115318298, | |
| "learning_rate": 0.00012646563599083996, | |
| "loss": 0.1427, | |
| "step": 387 | |
| }, | |
| { | |
| "epoch": 0.42219804134929273, | |
| "grad_norm": 0.19359458982944489, | |
| "learning_rate": 0.00012613219232128608, | |
| "loss": 0.121, | |
| "step": 388 | |
| }, | |
| { | |
| "epoch": 0.4232861806311208, | |
| "grad_norm": 0.244260773062706, | |
| "learning_rate": 0.0001257984365131938, | |
| "loss": 0.1469, | |
| "step": 389 | |
| }, | |
| { | |
| "epoch": 0.4243743199129489, | |
| "grad_norm": 0.18485282361507416, | |
| "learning_rate": 0.00012546437255314222, | |
| "loss": 0.0892, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.42546245919477693, | |
| "grad_norm": 0.3717290461063385, | |
| "learning_rate": 0.00012513000443139112, | |
| "loss": 0.2099, | |
| "step": 391 | |
| }, | |
| { | |
| "epoch": 0.426550598476605, | |
| "grad_norm": 0.28721094131469727, | |
| "learning_rate": 0.00012479533614183334, | |
| "loss": 0.1193, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 0.4276387377584331, | |
| "grad_norm": 0.2697299122810364, | |
| "learning_rate": 0.00012446037168194714, | |
| "loss": 0.0965, | |
| "step": 393 | |
| }, | |
| { | |
| "epoch": 0.42872687704026113, | |
| "grad_norm": 0.32627496123313904, | |
| "learning_rate": 0.00012412511505274844, | |
| "loss": 0.1832, | |
| "step": 394 | |
| }, | |
| { | |
| "epoch": 0.42981501632208924, | |
| "grad_norm": 0.37745073437690735, | |
| "learning_rate": 0.000123789570258743, | |
| "loss": 0.1572, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 0.4309031556039173, | |
| "grad_norm": 0.4901193082332611, | |
| "learning_rate": 0.00012345374130787854, | |
| "loss": 0.1873, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 0.4319912948857454, | |
| "grad_norm": 0.44663485884666443, | |
| "learning_rate": 0.000123117632211497, | |
| "loss": 0.3353, | |
| "step": 397 | |
| }, | |
| { | |
| "epoch": 0.43307943416757344, | |
| "grad_norm": 0.34345391392707825, | |
| "learning_rate": 0.0001227812469842864, | |
| "loss": 0.1924, | |
| "step": 398 | |
| }, | |
| { | |
| "epoch": 0.43416757344940154, | |
| "grad_norm": 0.5725805759429932, | |
| "learning_rate": 0.00012244458964423327, | |
| "loss": 0.2352, | |
| "step": 399 | |
| }, | |
| { | |
| "epoch": 0.4352557127312296, | |
| "grad_norm": 0.5519152879714966, | |
| "learning_rate": 0.0001221076642125742, | |
| "loss": 0.167, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.4363438520130577, | |
| "grad_norm": 0.055198315531015396, | |
| "learning_rate": 0.00012177047471374807, | |
| "loss": 0.0472, | |
| "step": 401 | |
| }, | |
| { | |
| "epoch": 0.43743199129488575, | |
| "grad_norm": 0.09932799637317657, | |
| "learning_rate": 0.0001214330251753481, | |
| "loss": 0.0783, | |
| "step": 402 | |
| }, | |
| { | |
| "epoch": 0.4385201305767138, | |
| "grad_norm": 0.08226185292005539, | |
| "learning_rate": 0.00012109531962807332, | |
| "loss": 0.0656, | |
| "step": 403 | |
| }, | |
| { | |
| "epoch": 0.4396082698585419, | |
| "grad_norm": 0.0858379453420639, | |
| "learning_rate": 0.0001207573621056809, | |
| "loss": 0.0741, | |
| "step": 404 | |
| }, | |
| { | |
| "epoch": 0.44069640914036995, | |
| "grad_norm": 0.07838830351829529, | |
| "learning_rate": 0.00012041915664493761, | |
| "loss": 0.066, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 0.44178454842219805, | |
| "grad_norm": 0.08843716233968735, | |
| "learning_rate": 0.00012008070728557186, | |
| "loss": 0.0817, | |
| "step": 406 | |
| }, | |
| { | |
| "epoch": 0.4428726877040261, | |
| "grad_norm": 0.09485173225402832, | |
| "learning_rate": 0.00011974201807022525, | |
| "loss": 0.0719, | |
| "step": 407 | |
| }, | |
| { | |
| "epoch": 0.4439608269858542, | |
| "grad_norm": 0.12550269067287445, | |
| "learning_rate": 0.00011940309304440433, | |
| "loss": 0.1025, | |
| "step": 408 | |
| }, | |
| { | |
| "epoch": 0.44504896626768226, | |
| "grad_norm": 0.10056477040052414, | |
| "learning_rate": 0.00011906393625643244, | |
| "loss": 0.0822, | |
| "step": 409 | |
| }, | |
| { | |
| "epoch": 0.44613710554951036, | |
| "grad_norm": 0.08779609948396683, | |
| "learning_rate": 0.00011872455175740112, | |
| "loss": 0.0731, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.4472252448313384, | |
| "grad_norm": 0.08771763741970062, | |
| "learning_rate": 0.00011838494360112185, | |
| "loss": 0.0686, | |
| "step": 411 | |
| }, | |
| { | |
| "epoch": 0.44831338411316646, | |
| "grad_norm": 0.09602241218090057, | |
| "learning_rate": 0.00011804511584407763, | |
| "loss": 0.0826, | |
| "step": 412 | |
| }, | |
| { | |
| "epoch": 0.44940152339499456, | |
| "grad_norm": 0.10052221268415451, | |
| "learning_rate": 0.00011770507254537453, | |
| "loss": 0.0711, | |
| "step": 413 | |
| }, | |
| { | |
| "epoch": 0.4504896626768226, | |
| "grad_norm": 0.08452215045690536, | |
| "learning_rate": 0.00011736481776669306, | |
| "loss": 0.061, | |
| "step": 414 | |
| }, | |
| { | |
| "epoch": 0.4515778019586507, | |
| "grad_norm": 0.09362675249576569, | |
| "learning_rate": 0.00011702435557223987, | |
| "loss": 0.0852, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 0.45266594124047876, | |
| "grad_norm": 0.10676004737615585, | |
| "learning_rate": 0.00011668369002869912, | |
| "loss": 0.101, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 0.45375408052230687, | |
| "grad_norm": 0.10523767024278641, | |
| "learning_rate": 0.00011634282520518383, | |
| "loss": 0.0892, | |
| "step": 417 | |
| }, | |
| { | |
| "epoch": 0.4548422198041349, | |
| "grad_norm": 0.09733587503433228, | |
| "learning_rate": 0.00011600176517318741, | |
| "loss": 0.0714, | |
| "step": 418 | |
| }, | |
| { | |
| "epoch": 0.455930359085963, | |
| "grad_norm": 0.13115546107292175, | |
| "learning_rate": 0.00011566051400653486, | |
| "loss": 0.1079, | |
| "step": 419 | |
| }, | |
| { | |
| "epoch": 0.45701849836779107, | |
| "grad_norm": 0.10536440461874008, | |
| "learning_rate": 0.00011531907578133429, | |
| "loss": 0.0807, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.4581066376496192, | |
| "grad_norm": 0.10071249306201935, | |
| "learning_rate": 0.00011497745457592816, | |
| "loss": 0.0647, | |
| "step": 421 | |
| }, | |
| { | |
| "epoch": 0.4591947769314472, | |
| "grad_norm": 0.12494815140962601, | |
| "learning_rate": 0.00011463565447084445, | |
| "loss": 0.0969, | |
| "step": 422 | |
| }, | |
| { | |
| "epoch": 0.4602829162132753, | |
| "grad_norm": 0.10858377069234848, | |
| "learning_rate": 0.00011429367954874819, | |
| "loss": 0.0709, | |
| "step": 423 | |
| }, | |
| { | |
| "epoch": 0.4613710554951034, | |
| "grad_norm": 0.10477497428655624, | |
| "learning_rate": 0.00011395153389439233, | |
| "loss": 0.0875, | |
| "step": 424 | |
| }, | |
| { | |
| "epoch": 0.4624591947769314, | |
| "grad_norm": 0.12716920673847198, | |
| "learning_rate": 0.00011360922159456928, | |
| "loss": 0.0864, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.46354733405875953, | |
| "grad_norm": 0.13803425431251526, | |
| "learning_rate": 0.00011326674673806195, | |
| "loss": 0.1028, | |
| "step": 426 | |
| }, | |
| { | |
| "epoch": 0.4646354733405876, | |
| "grad_norm": 0.1662827581167221, | |
| "learning_rate": 0.0001129241134155949, | |
| "loss": 0.1053, | |
| "step": 427 | |
| }, | |
| { | |
| "epoch": 0.4657236126224157, | |
| "grad_norm": 0.13029906153678894, | |
| "learning_rate": 0.00011258132571978555, | |
| "loss": 0.0797, | |
| "step": 428 | |
| }, | |
| { | |
| "epoch": 0.46681175190424373, | |
| "grad_norm": 0.18869560956954956, | |
| "learning_rate": 0.00011223838774509514, | |
| "loss": 0.1292, | |
| "step": 429 | |
| }, | |
| { | |
| "epoch": 0.46789989118607184, | |
| "grad_norm": 0.14279034733772278, | |
| "learning_rate": 0.00011189530358778005, | |
| "loss": 0.0951, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.4689880304678999, | |
| "grad_norm": 0.11428643018007278, | |
| "learning_rate": 0.00011155207734584263, | |
| "loss": 0.0664, | |
| "step": 431 | |
| }, | |
| { | |
| "epoch": 0.470076169749728, | |
| "grad_norm": 0.20008297264575958, | |
| "learning_rate": 0.00011120871311898254, | |
| "loss": 0.1027, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 0.47116430903155604, | |
| "grad_norm": 0.22173888981342316, | |
| "learning_rate": 0.00011086521500854745, | |
| "loss": 0.1356, | |
| "step": 433 | |
| }, | |
| { | |
| "epoch": 0.4722524483133841, | |
| "grad_norm": 0.2382795661687851, | |
| "learning_rate": 0.00011052158711748434, | |
| "loss": 0.1516, | |
| "step": 434 | |
| }, | |
| { | |
| "epoch": 0.4733405875952122, | |
| "grad_norm": 0.2854343354701996, | |
| "learning_rate": 0.00011017783355029026, | |
| "loss": 0.1116, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 0.47442872687704024, | |
| "grad_norm": 0.23063793778419495, | |
| "learning_rate": 0.00010983395841296348, | |
| "loss": 0.107, | |
| "step": 436 | |
| }, | |
| { | |
| "epoch": 0.47551686615886835, | |
| "grad_norm": 0.19402769207954407, | |
| "learning_rate": 0.00010948996581295436, | |
| "loss": 0.0883, | |
| "step": 437 | |
| }, | |
| { | |
| "epoch": 0.4766050054406964, | |
| "grad_norm": 0.2664678692817688, | |
| "learning_rate": 0.00010914585985911632, | |
| "loss": 0.1161, | |
| "step": 438 | |
| }, | |
| { | |
| "epoch": 0.4776931447225245, | |
| "grad_norm": 0.29061347246170044, | |
| "learning_rate": 0.00010880164466165674, | |
| "loss": 0.1833, | |
| "step": 439 | |
| }, | |
| { | |
| "epoch": 0.47878128400435255, | |
| "grad_norm": 0.33060985803604126, | |
| "learning_rate": 0.00010845732433208779, | |
| "loss": 0.1521, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.47986942328618065, | |
| "grad_norm": 0.28285855054855347, | |
| "learning_rate": 0.00010811290298317755, | |
| "loss": 0.1248, | |
| "step": 441 | |
| }, | |
| { | |
| "epoch": 0.4809575625680087, | |
| "grad_norm": 0.49815383553504944, | |
| "learning_rate": 0.00010776838472890065, | |
| "loss": 0.2238, | |
| "step": 442 | |
| }, | |
| { | |
| "epoch": 0.4820457018498368, | |
| "grad_norm": 0.367214173078537, | |
| "learning_rate": 0.00010742377368438914, | |
| "loss": 0.2344, | |
| "step": 443 | |
| }, | |
| { | |
| "epoch": 0.48313384113166485, | |
| "grad_norm": 0.3444245159626007, | |
| "learning_rate": 0.00010707907396588361, | |
| "loss": 0.1254, | |
| "step": 444 | |
| }, | |
| { | |
| "epoch": 0.4842219804134929, | |
| "grad_norm": 0.31096217036247253, | |
| "learning_rate": 0.00010673428969068364, | |
| "loss": 0.1313, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 0.485310119695321, | |
| "grad_norm": 0.5377318263053894, | |
| "learning_rate": 0.0001063894249770989, | |
| "loss": 0.2526, | |
| "step": 446 | |
| }, | |
| { | |
| "epoch": 0.48639825897714906, | |
| "grad_norm": 0.4121945798397064, | |
| "learning_rate": 0.00010604448394439983, | |
| "loss": 0.1663, | |
| "step": 447 | |
| }, | |
| { | |
| "epoch": 0.48748639825897716, | |
| "grad_norm": 0.48366662859916687, | |
| "learning_rate": 0.00010569947071276847, | |
| "loss": 0.2457, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 0.4885745375408052, | |
| "grad_norm": 0.6081061959266663, | |
| "learning_rate": 0.0001053543894032493, | |
| "loss": 0.2678, | |
| "step": 449 | |
| }, | |
| { | |
| "epoch": 0.4896626768226333, | |
| "grad_norm": 1.0334888696670532, | |
| "learning_rate": 0.00010500924413769988, | |
| "loss": 0.3153, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.49075081610446136, | |
| "grad_norm": 0.0451701320707798, | |
| "learning_rate": 0.00010466403903874176, | |
| "loss": 0.0455, | |
| "step": 451 | |
| }, | |
| { | |
| "epoch": 0.49183895538628947, | |
| "grad_norm": 0.05214075744152069, | |
| "learning_rate": 0.00010431877822971117, | |
| "loss": 0.0519, | |
| "step": 452 | |
| }, | |
| { | |
| "epoch": 0.4929270946681175, | |
| "grad_norm": 0.06553710252046585, | |
| "learning_rate": 0.00010397346583460971, | |
| "loss": 0.0557, | |
| "step": 453 | |
| }, | |
| { | |
| "epoch": 0.4940152339499456, | |
| "grad_norm": 0.06424305588006973, | |
| "learning_rate": 0.00010362810597805526, | |
| "loss": 0.0672, | |
| "step": 454 | |
| }, | |
| { | |
| "epoch": 0.49510337323177367, | |
| "grad_norm": 0.08962132036685944, | |
| "learning_rate": 0.00010328270278523256, | |
| "loss": 0.0957, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 0.4961915125136017, | |
| "grad_norm": 0.08780992031097412, | |
| "learning_rate": 0.00010293726038184393, | |
| "loss": 0.0894, | |
| "step": 456 | |
| }, | |
| { | |
| "epoch": 0.4972796517954298, | |
| "grad_norm": 0.08018220961093903, | |
| "learning_rate": 0.00010259178289406011, | |
| "loss": 0.0663, | |
| "step": 457 | |
| }, | |
| { | |
| "epoch": 0.49836779107725787, | |
| "grad_norm": 0.07880765199661255, | |
| "learning_rate": 0.0001022462744484709, | |
| "loss": 0.0832, | |
| "step": 458 | |
| }, | |
| { | |
| "epoch": 0.499455930359086, | |
| "grad_norm": 0.07101229578256607, | |
| "learning_rate": 0.00010190073917203589, | |
| "loss": 0.054, | |
| "step": 459 | |
| }, | |
| { | |
| "epoch": 0.500544069640914, | |
| "grad_norm": 0.07901884615421295, | |
| "learning_rate": 0.0001015551811920351, | |
| "loss": 0.0611, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.500544069640914, | |
| "eval_loss": 0.11412899941205978, | |
| "eval_runtime": 24.4441, | |
| "eval_samples_per_second": 15.832, | |
| "eval_steps_per_second": 7.936, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.5016322089227421, | |
| "grad_norm": 0.08245149999856949, | |
| "learning_rate": 0.00010120960463601976, | |
| "loss": 0.0758, | |
| "step": 461 | |
| }, | |
| { | |
| "epoch": 0.5027203482045702, | |
| "grad_norm": 0.07407300174236298, | |
| "learning_rate": 0.00010086401363176305, | |
| "loss": 0.0567, | |
| "step": 462 | |
| }, | |
| { | |
| "epoch": 0.5038084874863983, | |
| "grad_norm": 0.08621735125780106, | |
| "learning_rate": 0.00010051841230721065, | |
| "loss": 0.0853, | |
| "step": 463 | |
| }, | |
| { | |
| "epoch": 0.5048966267682263, | |
| "grad_norm": 0.08985213935375214, | |
| "learning_rate": 0.00010017280479043147, | |
| "loss": 0.0806, | |
| "step": 464 | |
| }, | |
| { | |
| "epoch": 0.5059847660500544, | |
| "grad_norm": 0.10007097572088242, | |
| "learning_rate": 9.982719520956855e-05, | |
| "loss": 0.0943, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 0.5070729053318824, | |
| "grad_norm": 0.08833252638578415, | |
| "learning_rate": 9.948158769278939e-05, | |
| "loss": 0.0736, | |
| "step": 466 | |
| }, | |
| { | |
| "epoch": 0.5081610446137106, | |
| "grad_norm": 0.08999834209680557, | |
| "learning_rate": 9.913598636823693e-05, | |
| "loss": 0.0711, | |
| "step": 467 | |
| }, | |
| { | |
| "epoch": 0.5092491838955386, | |
| "grad_norm": 0.09894470125436783, | |
| "learning_rate": 9.879039536398024e-05, | |
| "loss": 0.0854, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 0.5103373231773667, | |
| "grad_norm": 0.10664485394954681, | |
| "learning_rate": 9.844481880796491e-05, | |
| "loss": 0.0817, | |
| "step": 469 | |
| }, | |
| { | |
| "epoch": 0.5114254624591947, | |
| "grad_norm": 0.08572715520858765, | |
| "learning_rate": 9.809926082796415e-05, | |
| "loss": 0.0685, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.5125136017410229, | |
| "grad_norm": 0.1364021748304367, | |
| "learning_rate": 9.775372555152912e-05, | |
| "loss": 0.1289, | |
| "step": 471 | |
| }, | |
| { | |
| "epoch": 0.5136017410228509, | |
| "grad_norm": 0.0975506454706192, | |
| "learning_rate": 9.740821710593989e-05, | |
| "loss": 0.0816, | |
| "step": 472 | |
| }, | |
| { | |
| "epoch": 0.514689880304679, | |
| "grad_norm": 0.10148054361343384, | |
| "learning_rate": 9.70627396181561e-05, | |
| "loss": 0.0685, | |
| "step": 473 | |
| }, | |
| { | |
| "epoch": 0.515778019586507, | |
| "grad_norm": 0.10723249614238739, | |
| "learning_rate": 9.671729721476746e-05, | |
| "loss": 0.1108, | |
| "step": 474 | |
| }, | |
| { | |
| "epoch": 0.5168661588683352, | |
| "grad_norm": 0.1059638112783432, | |
| "learning_rate": 9.637189402194476e-05, | |
| "loss": 0.0797, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.5179542981501633, | |
| "grad_norm": 0.09612549841403961, | |
| "learning_rate": 9.602653416539031e-05, | |
| "loss": 0.0756, | |
| "step": 476 | |
| }, | |
| { | |
| "epoch": 0.5190424374319913, | |
| "grad_norm": 0.12177007645368576, | |
| "learning_rate": 9.568122177028884e-05, | |
| "loss": 0.072, | |
| "step": 477 | |
| }, | |
| { | |
| "epoch": 0.5201305767138193, | |
| "grad_norm": 0.10441110283136368, | |
| "learning_rate": 9.533596096125825e-05, | |
| "loss": 0.082, | |
| "step": 478 | |
| }, | |
| { | |
| "epoch": 0.5212187159956474, | |
| "grad_norm": 0.1342850774526596, | |
| "learning_rate": 9.499075586230013e-05, | |
| "loss": 0.0877, | |
| "step": 479 | |
| }, | |
| { | |
| "epoch": 0.5223068552774756, | |
| "grad_norm": 0.14177678525447845, | |
| "learning_rate": 9.464561059675073e-05, | |
| "loss": 0.1105, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.5233949945593036, | |
| "grad_norm": 0.14493241906166077, | |
| "learning_rate": 9.430052928723153e-05, | |
| "loss": 0.0975, | |
| "step": 481 | |
| }, | |
| { | |
| "epoch": 0.5244831338411317, | |
| "grad_norm": 0.22142328321933746, | |
| "learning_rate": 9.395551605560018e-05, | |
| "loss": 0.1441, | |
| "step": 482 | |
| }, | |
| { | |
| "epoch": 0.5255712731229597, | |
| "grad_norm": 0.13570967316627502, | |
| "learning_rate": 9.361057502290113e-05, | |
| "loss": 0.0952, | |
| "step": 483 | |
| }, | |
| { | |
| "epoch": 0.5266594124047879, | |
| "grad_norm": 0.16124001145362854, | |
| "learning_rate": 9.326571030931637e-05, | |
| "loss": 0.0976, | |
| "step": 484 | |
| }, | |
| { | |
| "epoch": 0.5277475516866159, | |
| "grad_norm": 0.17145387828350067, | |
| "learning_rate": 9.292092603411641e-05, | |
| "loss": 0.1024, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 0.528835690968444, | |
| "grad_norm": 0.23006115853786469, | |
| "learning_rate": 9.257622631561085e-05, | |
| "loss": 0.147, | |
| "step": 486 | |
| }, | |
| { | |
| "epoch": 0.529923830250272, | |
| "grad_norm": 0.2926236391067505, | |
| "learning_rate": 9.223161527109937e-05, | |
| "loss": 0.1706, | |
| "step": 487 | |
| }, | |
| { | |
| "epoch": 0.5310119695321001, | |
| "grad_norm": 0.2122851312160492, | |
| "learning_rate": 9.188709701682247e-05, | |
| "loss": 0.0793, | |
| "step": 488 | |
| }, | |
| { | |
| "epoch": 0.5321001088139282, | |
| "grad_norm": 0.30783331394195557, | |
| "learning_rate": 9.154267566791223e-05, | |
| "loss": 0.1446, | |
| "step": 489 | |
| }, | |
| { | |
| "epoch": 0.5331882480957563, | |
| "grad_norm": 0.26017701625823975, | |
| "learning_rate": 9.119835533834331e-05, | |
| "loss": 0.0925, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.5342763873775843, | |
| "grad_norm": 0.3646100163459778, | |
| "learning_rate": 9.085414014088369e-05, | |
| "loss": 0.1893, | |
| "step": 491 | |
| }, | |
| { | |
| "epoch": 0.5353645266594124, | |
| "grad_norm": 0.3202396035194397, | |
| "learning_rate": 9.051003418704565e-05, | |
| "loss": 0.1389, | |
| "step": 492 | |
| }, | |
| { | |
| "epoch": 0.5364526659412405, | |
| "grad_norm": 0.420622318983078, | |
| "learning_rate": 9.016604158703654e-05, | |
| "loss": 0.2336, | |
| "step": 493 | |
| }, | |
| { | |
| "epoch": 0.5375408052230686, | |
| "grad_norm": 0.41953420639038086, | |
| "learning_rate": 8.982216644970979e-05, | |
| "loss": 0.2328, | |
| "step": 494 | |
| }, | |
| { | |
| "epoch": 0.5386289445048966, | |
| "grad_norm": 0.39154770970344543, | |
| "learning_rate": 8.947841288251568e-05, | |
| "loss": 0.1791, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 0.5397170837867247, | |
| "grad_norm": 0.3094623386859894, | |
| "learning_rate": 8.913478499145254e-05, | |
| "loss": 0.1163, | |
| "step": 496 | |
| }, | |
| { | |
| "epoch": 0.5408052230685527, | |
| "grad_norm": 0.47343355417251587, | |
| "learning_rate": 8.879128688101749e-05, | |
| "loss": 0.2118, | |
| "step": 497 | |
| }, | |
| { | |
| "epoch": 0.5418933623503809, | |
| "grad_norm": 0.5772989988327026, | |
| "learning_rate": 8.844792265415738e-05, | |
| "loss": 0.3241, | |
| "step": 498 | |
| }, | |
| { | |
| "epoch": 0.5429815016322089, | |
| "grad_norm": 0.574259877204895, | |
| "learning_rate": 8.810469641222001e-05, | |
| "loss": 0.1832, | |
| "step": 499 | |
| }, | |
| { | |
| "epoch": 0.544069640914037, | |
| "grad_norm": 0.7393798828125, | |
| "learning_rate": 8.776161225490489e-05, | |
| "loss": 0.3208, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.545157780195865, | |
| "grad_norm": 0.08375679701566696, | |
| "learning_rate": 8.741867428021446e-05, | |
| "loss": 0.0647, | |
| "step": 501 | |
| }, | |
| { | |
| "epoch": 0.5462459194776932, | |
| "grad_norm": 0.06409952789545059, | |
| "learning_rate": 8.707588658440511e-05, | |
| "loss": 0.0669, | |
| "step": 502 | |
| }, | |
| { | |
| "epoch": 0.5473340587595212, | |
| "grad_norm": 0.07277576625347137, | |
| "learning_rate": 8.673325326193806e-05, | |
| "loss": 0.069, | |
| "step": 503 | |
| }, | |
| { | |
| "epoch": 0.5484221980413493, | |
| "grad_norm": 0.0738697499036789, | |
| "learning_rate": 8.639077840543077e-05, | |
| "loss": 0.0729, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 0.5495103373231773, | |
| "grad_norm": 0.07032415270805359, | |
| "learning_rate": 8.604846610560771e-05, | |
| "loss": 0.0619, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 0.5505984766050055, | |
| "grad_norm": 0.08152731508016586, | |
| "learning_rate": 8.570632045125185e-05, | |
| "loss": 0.0984, | |
| "step": 506 | |
| }, | |
| { | |
| "epoch": 0.5516866158868335, | |
| "grad_norm": 0.08058314025402069, | |
| "learning_rate": 8.536434552915556e-05, | |
| "loss": 0.0727, | |
| "step": 507 | |
| }, | |
| { | |
| "epoch": 0.5527747551686616, | |
| "grad_norm": 0.08897782117128372, | |
| "learning_rate": 8.502254542407186e-05, | |
| "loss": 0.0844, | |
| "step": 508 | |
| }, | |
| { | |
| "epoch": 0.5538628944504896, | |
| "grad_norm": 0.07130607962608337, | |
| "learning_rate": 8.468092421866573e-05, | |
| "loss": 0.0612, | |
| "step": 509 | |
| }, | |
| { | |
| "epoch": 0.5549510337323177, | |
| "grad_norm": 0.09470459073781967, | |
| "learning_rate": 8.433948599346516e-05, | |
| "loss": 0.0983, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.5560391730141458, | |
| "grad_norm": 0.10217074304819107, | |
| "learning_rate": 8.399823482681262e-05, | |
| "loss": 0.1066, | |
| "step": 511 | |
| }, | |
| { | |
| "epoch": 0.5571273122959739, | |
| "grad_norm": 0.08955902606248856, | |
| "learning_rate": 8.36571747948162e-05, | |
| "loss": 0.0754, | |
| "step": 512 | |
| }, | |
| { | |
| "epoch": 0.558215451577802, | |
| "grad_norm": 0.08967861533164978, | |
| "learning_rate": 8.33163099713009e-05, | |
| "loss": 0.0745, | |
| "step": 513 | |
| }, | |
| { | |
| "epoch": 0.55930359085963, | |
| "grad_norm": 0.09490852057933807, | |
| "learning_rate": 8.297564442776014e-05, | |
| "loss": 0.0956, | |
| "step": 514 | |
| }, | |
| { | |
| "epoch": 0.5603917301414582, | |
| "grad_norm": 0.1147465854883194, | |
| "learning_rate": 8.263518223330697e-05, | |
| "loss": 0.0918, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 0.5614798694232862, | |
| "grad_norm": 0.10192292928695679, | |
| "learning_rate": 8.22949274546255e-05, | |
| "loss": 0.0865, | |
| "step": 516 | |
| }, | |
| { | |
| "epoch": 0.5625680087051143, | |
| "grad_norm": 0.09790289402008057, | |
| "learning_rate": 8.195488415592238e-05, | |
| "loss": 0.0884, | |
| "step": 517 | |
| }, | |
| { | |
| "epoch": 0.5636561479869423, | |
| "grad_norm": 0.10624364018440247, | |
| "learning_rate": 8.161505639887817e-05, | |
| "loss": 0.0743, | |
| "step": 518 | |
| }, | |
| { | |
| "epoch": 0.5647442872687704, | |
| "grad_norm": 0.10007826238870621, | |
| "learning_rate": 8.127544824259889e-05, | |
| "loss": 0.077, | |
| "step": 519 | |
| }, | |
| { | |
| "epoch": 0.5658324265505985, | |
| "grad_norm": 0.10816752165555954, | |
| "learning_rate": 8.093606374356759e-05, | |
| "loss": 0.0967, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.5669205658324266, | |
| "grad_norm": 0.09151450544595718, | |
| "learning_rate": 8.059690695559568e-05, | |
| "loss": 0.0559, | |
| "step": 521 | |
| }, | |
| { | |
| "epoch": 0.5680087051142546, | |
| "grad_norm": 0.09337753057479858, | |
| "learning_rate": 8.025798192977481e-05, | |
| "loss": 0.0666, | |
| "step": 522 | |
| }, | |
| { | |
| "epoch": 0.5690968443960827, | |
| "grad_norm": 0.07552886009216309, | |
| "learning_rate": 7.991929271442817e-05, | |
| "loss": 0.0427, | |
| "step": 523 | |
| }, | |
| { | |
| "epoch": 0.5701849836779108, | |
| "grad_norm": 0.125149667263031, | |
| "learning_rate": 7.958084335506239e-05, | |
| "loss": 0.0886, | |
| "step": 524 | |
| }, | |
| { | |
| "epoch": 0.5712731229597389, | |
| "grad_norm": 0.1259811669588089, | |
| "learning_rate": 7.924263789431912e-05, | |
| "loss": 0.0836, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.5723612622415669, | |
| "grad_norm": 0.11561718583106995, | |
| "learning_rate": 7.89046803719267e-05, | |
| "loss": 0.0767, | |
| "step": 526 | |
| }, | |
| { | |
| "epoch": 0.573449401523395, | |
| "grad_norm": 0.15881969034671783, | |
| "learning_rate": 7.856697482465196e-05, | |
| "loss": 0.132, | |
| "step": 527 | |
| }, | |
| { | |
| "epoch": 0.5745375408052231, | |
| "grad_norm": 0.11481433361768723, | |
| "learning_rate": 7.822952528625191e-05, | |
| "loss": 0.0772, | |
| "step": 528 | |
| }, | |
| { | |
| "epoch": 0.5756256800870512, | |
| "grad_norm": 0.133880615234375, | |
| "learning_rate": 7.789233578742582e-05, | |
| "loss": 0.0851, | |
| "step": 529 | |
| }, | |
| { | |
| "epoch": 0.5767138193688792, | |
| "grad_norm": 0.1513182371854782, | |
| "learning_rate": 7.755541035576677e-05, | |
| "loss": 0.1258, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.5778019586507073, | |
| "grad_norm": 0.1432909518480301, | |
| "learning_rate": 7.721875301571359e-05, | |
| "loss": 0.1227, | |
| "step": 531 | |
| }, | |
| { | |
| "epoch": 0.5788900979325353, | |
| "grad_norm": 0.11642878502607346, | |
| "learning_rate": 7.688236778850306e-05, | |
| "loss": 0.0686, | |
| "step": 532 | |
| }, | |
| { | |
| "epoch": 0.5799782372143635, | |
| "grad_norm": 0.16764387488365173, | |
| "learning_rate": 7.654625869212146e-05, | |
| "loss": 0.1262, | |
| "step": 533 | |
| }, | |
| { | |
| "epoch": 0.5810663764961915, | |
| "grad_norm": 0.11564290523529053, | |
| "learning_rate": 7.6210429741257e-05, | |
| "loss": 0.0572, | |
| "step": 534 | |
| }, | |
| { | |
| "epoch": 0.5821545157780196, | |
| "grad_norm": 0.2554946541786194, | |
| "learning_rate": 7.587488494725157e-05, | |
| "loss": 0.1812, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 0.5832426550598476, | |
| "grad_norm": 0.1616709679365158, | |
| "learning_rate": 7.55396283180529e-05, | |
| "loss": 0.0818, | |
| "step": 536 | |
| }, | |
| { | |
| "epoch": 0.5843307943416758, | |
| "grad_norm": 0.321591317653656, | |
| "learning_rate": 7.520466385816671e-05, | |
| "loss": 0.2124, | |
| "step": 537 | |
| }, | |
| { | |
| "epoch": 0.5854189336235038, | |
| "grad_norm": 0.21219317615032196, | |
| "learning_rate": 7.48699955686089e-05, | |
| "loss": 0.1097, | |
| "step": 538 | |
| }, | |
| { | |
| "epoch": 0.5865070729053319, | |
| "grad_norm": 0.19242917001247406, | |
| "learning_rate": 7.453562744685778e-05, | |
| "loss": 0.0769, | |
| "step": 539 | |
| }, | |
| { | |
| "epoch": 0.5875952121871599, | |
| "grad_norm": 0.27252575755119324, | |
| "learning_rate": 7.42015634868062e-05, | |
| "loss": 0.123, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.588683351468988, | |
| "grad_norm": 0.3768553137779236, | |
| "learning_rate": 7.386780767871397e-05, | |
| "loss": 0.1882, | |
| "step": 541 | |
| }, | |
| { | |
| "epoch": 0.5897714907508161, | |
| "grad_norm": 0.2910580337047577, | |
| "learning_rate": 7.353436400916004e-05, | |
| "loss": 0.11, | |
| "step": 542 | |
| }, | |
| { | |
| "epoch": 0.5908596300326442, | |
| "grad_norm": 0.5426351428031921, | |
| "learning_rate": 7.320123646099519e-05, | |
| "loss": 0.2963, | |
| "step": 543 | |
| }, | |
| { | |
| "epoch": 0.5919477693144722, | |
| "grad_norm": 0.47717493772506714, | |
| "learning_rate": 7.286842901329412e-05, | |
| "loss": 0.1808, | |
| "step": 544 | |
| }, | |
| { | |
| "epoch": 0.5930359085963003, | |
| "grad_norm": 0.3526507019996643, | |
| "learning_rate": 7.253594564130804e-05, | |
| "loss": 0.1664, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 0.5941240478781284, | |
| "grad_norm": 0.4166988134384155, | |
| "learning_rate": 7.22037903164173e-05, | |
| "loss": 0.199, | |
| "step": 546 | |
| }, | |
| { | |
| "epoch": 0.5952121871599565, | |
| "grad_norm": 0.3085844814777374, | |
| "learning_rate": 7.187196700608373e-05, | |
| "loss": 0.1008, | |
| "step": 547 | |
| }, | |
| { | |
| "epoch": 0.5963003264417845, | |
| "grad_norm": 0.6430099606513977, | |
| "learning_rate": 7.154047967380354e-05, | |
| "loss": 0.2083, | |
| "step": 548 | |
| }, | |
| { | |
| "epoch": 0.5973884657236126, | |
| "grad_norm": 0.5886674523353577, | |
| "learning_rate": 7.12093322790597e-05, | |
| "loss": 0.2135, | |
| "step": 549 | |
| }, | |
| { | |
| "epoch": 0.5984766050054406, | |
| "grad_norm": 0.6182297468185425, | |
| "learning_rate": 7.087852877727481e-05, | |
| "loss": 0.1715, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.5995647442872688, | |
| "grad_norm": 0.052968356758356094, | |
| "learning_rate": 7.054807311976379e-05, | |
| "loss": 0.0482, | |
| "step": 551 | |
| }, | |
| { | |
| "epoch": 0.6006528835690969, | |
| "grad_norm": 0.05972611904144287, | |
| "learning_rate": 7.021796925368667e-05, | |
| "loss": 0.0518, | |
| "step": 552 | |
| }, | |
| { | |
| "epoch": 0.6017410228509249, | |
| "grad_norm": 0.06913693249225616, | |
| "learning_rate": 6.988822112200156e-05, | |
| "loss": 0.067, | |
| "step": 553 | |
| }, | |
| { | |
| "epoch": 0.602829162132753, | |
| "grad_norm": 0.07957234978675842, | |
| "learning_rate": 6.955883266341741e-05, | |
| "loss": 0.0881, | |
| "step": 554 | |
| }, | |
| { | |
| "epoch": 0.6039173014145811, | |
| "grad_norm": 0.07048328220844269, | |
| "learning_rate": 6.922980781234699e-05, | |
| "loss": 0.073, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 0.6050054406964092, | |
| "grad_norm": 0.07528451830148697, | |
| "learning_rate": 6.890115049885994e-05, | |
| "loss": 0.0777, | |
| "step": 556 | |
| }, | |
| { | |
| "epoch": 0.6060935799782372, | |
| "grad_norm": 0.07747096568346024, | |
| "learning_rate": 6.85728646486359e-05, | |
| "loss": 0.0758, | |
| "step": 557 | |
| }, | |
| { | |
| "epoch": 0.6071817192600653, | |
| "grad_norm": 0.10643380880355835, | |
| "learning_rate": 6.82449541829174e-05, | |
| "loss": 0.1274, | |
| "step": 558 | |
| }, | |
| { | |
| "epoch": 0.6082698585418934, | |
| "grad_norm": 0.08175136148929596, | |
| "learning_rate": 6.791742301846326e-05, | |
| "loss": 0.0838, | |
| "step": 559 | |
| }, | |
| { | |
| "epoch": 0.6093579978237215, | |
| "grad_norm": 0.09339357912540436, | |
| "learning_rate": 6.759027506750158e-05, | |
| "loss": 0.0767, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.6104461371055495, | |
| "grad_norm": 0.07980689406394958, | |
| "learning_rate": 6.726351423768322e-05, | |
| "loss": 0.0645, | |
| "step": 561 | |
| }, | |
| { | |
| "epoch": 0.6115342763873776, | |
| "grad_norm": 0.09120305627584457, | |
| "learning_rate": 6.693714443203507e-05, | |
| "loss": 0.0763, | |
| "step": 562 | |
| }, | |
| { | |
| "epoch": 0.6126224156692056, | |
| "grad_norm": 0.09666004031896591, | |
| "learning_rate": 6.661116954891328e-05, | |
| "loss": 0.0749, | |
| "step": 563 | |
| }, | |
| { | |
| "epoch": 0.6137105549510338, | |
| "grad_norm": 0.09731943160295486, | |
| "learning_rate": 6.62855934819569e-05, | |
| "loss": 0.0891, | |
| "step": 564 | |
| }, | |
| { | |
| "epoch": 0.6147986942328618, | |
| "grad_norm": 0.09505044668912888, | |
| "learning_rate": 6.59604201200412e-05, | |
| "loss": 0.0734, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 0.6158868335146899, | |
| "grad_norm": 0.09885645657777786, | |
| "learning_rate": 6.563565334723134e-05, | |
| "loss": 0.0726, | |
| "step": 566 | |
| }, | |
| { | |
| "epoch": 0.6169749727965179, | |
| "grad_norm": 0.10182873159646988, | |
| "learning_rate": 6.531129704273604e-05, | |
| "loss": 0.0907, | |
| "step": 567 | |
| }, | |
| { | |
| "epoch": 0.6180631120783461, | |
| "grad_norm": 0.10983593761920929, | |
| "learning_rate": 6.498735508086093e-05, | |
| "loss": 0.0774, | |
| "step": 568 | |
| }, | |
| { | |
| "epoch": 0.6191512513601741, | |
| "grad_norm": 0.13069598376750946, | |
| "learning_rate": 6.466383133096267e-05, | |
| "loss": 0.1334, | |
| "step": 569 | |
| }, | |
| { | |
| "epoch": 0.6202393906420022, | |
| "grad_norm": 0.10764119029045105, | |
| "learning_rate": 6.434072965740242e-05, | |
| "loss": 0.0921, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.6213275299238302, | |
| "grad_norm": 0.10900213569402695, | |
| "learning_rate": 6.40180539194999e-05, | |
| "loss": 0.0842, | |
| "step": 571 | |
| }, | |
| { | |
| "epoch": 0.6224156692056583, | |
| "grad_norm": 0.13261805474758148, | |
| "learning_rate": 6.369580797148718e-05, | |
| "loss": 0.1045, | |
| "step": 572 | |
| }, | |
| { | |
| "epoch": 0.6235038084874864, | |
| "grad_norm": 0.13680216670036316, | |
| "learning_rate": 6.337399566246257e-05, | |
| "loss": 0.1367, | |
| "step": 573 | |
| }, | |
| { | |
| "epoch": 0.6245919477693145, | |
| "grad_norm": 0.13827918469905853, | |
| "learning_rate": 6.305262083634488e-05, | |
| "loss": 0.1063, | |
| "step": 574 | |
| }, | |
| { | |
| "epoch": 0.6256800870511425, | |
| "grad_norm": 0.0938330814242363, | |
| "learning_rate": 6.273168733182722e-05, | |
| "loss": 0.0686, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.6267682263329706, | |
| "grad_norm": 0.14945276081562042, | |
| "learning_rate": 6.241119898233144e-05, | |
| "loss": 0.1373, | |
| "step": 576 | |
| }, | |
| { | |
| "epoch": 0.6278563656147987, | |
| "grad_norm": 0.10897387564182281, | |
| "learning_rate": 6.209115961596208e-05, | |
| "loss": 0.068, | |
| "step": 577 | |
| }, | |
| { | |
| "epoch": 0.6289445048966268, | |
| "grad_norm": 0.11899581551551819, | |
| "learning_rate": 6.177157305546078e-05, | |
| "loss": 0.0812, | |
| "step": 578 | |
| }, | |
| { | |
| "epoch": 0.6300326441784548, | |
| "grad_norm": 0.12964366376399994, | |
| "learning_rate": 6.145244311816063e-05, | |
| "loss": 0.0919, | |
| "step": 579 | |
| }, | |
| { | |
| "epoch": 0.6311207834602829, | |
| "grad_norm": 0.14867788553237915, | |
| "learning_rate": 6.113377361594049e-05, | |
| "loss": 0.1079, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.6322089227421109, | |
| "grad_norm": 0.13811950385570526, | |
| "learning_rate": 6.0815568355179556e-05, | |
| "loss": 0.0871, | |
| "step": 581 | |
| }, | |
| { | |
| "epoch": 0.6332970620239391, | |
| "grad_norm": 0.14532406628131866, | |
| "learning_rate": 6.0497831136711836e-05, | |
| "loss": 0.0912, | |
| "step": 582 | |
| }, | |
| { | |
| "epoch": 0.6343852013057671, | |
| "grad_norm": 0.19129644334316254, | |
| "learning_rate": 6.018056575578075e-05, | |
| "loss": 0.1137, | |
| "step": 583 | |
| }, | |
| { | |
| "epoch": 0.6354733405875952, | |
| "grad_norm": 0.16450344026088715, | |
| "learning_rate": 5.986377600199371e-05, | |
| "loss": 0.072, | |
| "step": 584 | |
| }, | |
| { | |
| "epoch": 0.6365614798694232, | |
| "grad_norm": 0.1428171992301941, | |
| "learning_rate": 5.9547465659277215e-05, | |
| "loss": 0.0671, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 0.6376496191512514, | |
| "grad_norm": 0.18160395324230194, | |
| "learning_rate": 5.923163850583113e-05, | |
| "loss": 0.1049, | |
| "step": 586 | |
| }, | |
| { | |
| "epoch": 0.6387377584330794, | |
| "grad_norm": 0.18718522787094116, | |
| "learning_rate": 5.8916298314083915e-05, | |
| "loss": 0.1037, | |
| "step": 587 | |
| }, | |
| { | |
| "epoch": 0.6398258977149075, | |
| "grad_norm": 0.3233761489391327, | |
| "learning_rate": 5.860144885064751e-05, | |
| "loss": 0.1401, | |
| "step": 588 | |
| }, | |
| { | |
| "epoch": 0.6409140369967355, | |
| "grad_norm": 0.27942174673080444, | |
| "learning_rate": 5.828709387627218e-05, | |
| "loss": 0.1464, | |
| "step": 589 | |
| }, | |
| { | |
| "epoch": 0.6420021762785637, | |
| "grad_norm": 0.26235440373420715, | |
| "learning_rate": 5.797323714580192e-05, | |
| "loss": 0.1238, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.6430903155603918, | |
| "grad_norm": 0.3004370927810669, | |
| "learning_rate": 5.765988240812921e-05, | |
| "loss": 0.1483, | |
| "step": 591 | |
| }, | |
| { | |
| "epoch": 0.6441784548422198, | |
| "grad_norm": 0.33811435103416443, | |
| "learning_rate": 5.73470334061505e-05, | |
| "loss": 0.1895, | |
| "step": 592 | |
| }, | |
| { | |
| "epoch": 0.6452665941240479, | |
| "grad_norm": 0.352417528629303, | |
| "learning_rate": 5.7034693876721376e-05, | |
| "loss": 0.1148, | |
| "step": 593 | |
| }, | |
| { | |
| "epoch": 0.6463547334058759, | |
| "grad_norm": 0.296340674161911, | |
| "learning_rate": 5.6722867550612116e-05, | |
| "loss": 0.1647, | |
| "step": 594 | |
| }, | |
| { | |
| "epoch": 0.6474428726877041, | |
| "grad_norm": 0.47691333293914795, | |
| "learning_rate": 5.6411558152462894e-05, | |
| "loss": 0.2066, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 0.6485310119695321, | |
| "grad_norm": 0.5979732275009155, | |
| "learning_rate": 5.6100769400739383e-05, | |
| "loss": 0.291, | |
| "step": 596 | |
| }, | |
| { | |
| "epoch": 0.6496191512513602, | |
| "grad_norm": 0.4951854944229126, | |
| "learning_rate": 5.579050500768836e-05, | |
| "loss": 0.2417, | |
| "step": 597 | |
| }, | |
| { | |
| "epoch": 0.6507072905331882, | |
| "grad_norm": 0.5365352630615234, | |
| "learning_rate": 5.54807686792933e-05, | |
| "loss": 0.2438, | |
| "step": 598 | |
| }, | |
| { | |
| "epoch": 0.6517954298150164, | |
| "grad_norm": 0.6378306150436401, | |
| "learning_rate": 5.5171564115230254e-05, | |
| "loss": 0.2436, | |
| "step": 599 | |
| }, | |
| { | |
| "epoch": 0.6528835690968444, | |
| "grad_norm": 0.5462427735328674, | |
| "learning_rate": 5.486289500882355e-05, | |
| "loss": 0.1536, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.6539717083786725, | |
| "grad_norm": 0.0600992813706398, | |
| "learning_rate": 5.4554765047001613e-05, | |
| "loss": 0.0662, | |
| "step": 601 | |
| }, | |
| { | |
| "epoch": 0.6550598476605005, | |
| "grad_norm": 0.06883436441421509, | |
| "learning_rate": 5.424717791025302e-05, | |
| "loss": 0.0791, | |
| "step": 602 | |
| }, | |
| { | |
| "epoch": 0.6561479869423286, | |
| "grad_norm": 0.07644320279359818, | |
| "learning_rate": 5.394013727258254e-05, | |
| "loss": 0.0863, | |
| "step": 603 | |
| }, | |
| { | |
| "epoch": 0.6572361262241567, | |
| "grad_norm": 0.07377026975154877, | |
| "learning_rate": 5.363364680146725e-05, | |
| "loss": 0.0669, | |
| "step": 604 | |
| }, | |
| { | |
| "epoch": 0.6583242655059848, | |
| "grad_norm": 0.06373579055070877, | |
| "learning_rate": 5.332771015781275e-05, | |
| "loss": 0.0537, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 0.6594124047878128, | |
| "grad_norm": 0.05605285242199898, | |
| "learning_rate": 5.302233099590928e-05, | |
| "loss": 0.0505, | |
| "step": 606 | |
| }, | |
| { | |
| "epoch": 0.6605005440696409, | |
| "grad_norm": 0.0761309266090393, | |
| "learning_rate": 5.271751296338823e-05, | |
| "loss": 0.079, | |
| "step": 607 | |
| }, | |
| { | |
| "epoch": 0.661588683351469, | |
| "grad_norm": 0.08843579143285751, | |
| "learning_rate": 5.2413259701178505e-05, | |
| "loss": 0.0662, | |
| "step": 608 | |
| }, | |
| { | |
| "epoch": 0.6626768226332971, | |
| "grad_norm": 0.07351501286029816, | |
| "learning_rate": 5.210957484346314e-05, | |
| "loss": 0.0533, | |
| "step": 609 | |
| }, | |
| { | |
| "epoch": 0.6637649619151251, | |
| "grad_norm": 0.08167769014835358, | |
| "learning_rate": 5.180646201763577e-05, | |
| "loss": 0.0796, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.6648531011969532, | |
| "grad_norm": 0.09149360656738281, | |
| "learning_rate": 5.150392484425728e-05, | |
| "loss": 0.1115, | |
| "step": 611 | |
| }, | |
| { | |
| "epoch": 0.6659412404787813, | |
| "grad_norm": 0.08288878947496414, | |
| "learning_rate": 5.120196693701267e-05, | |
| "loss": 0.0761, | |
| "step": 612 | |
| }, | |
| { | |
| "epoch": 0.6670293797606094, | |
| "grad_norm": 0.07389149814844131, | |
| "learning_rate": 5.090059190266779e-05, | |
| "loss": 0.0645, | |
| "step": 613 | |
| }, | |
| { | |
| "epoch": 0.6681175190424374, | |
| "grad_norm": 0.08279106020927429, | |
| "learning_rate": 5.059980334102637e-05, | |
| "loss": 0.0772, | |
| "step": 614 | |
| }, | |
| { | |
| "epoch": 0.6692056583242655, | |
| "grad_norm": 0.09307517111301422, | |
| "learning_rate": 5.0299604844886985e-05, | |
| "loss": 0.0823, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 0.6702937976060935, | |
| "grad_norm": 0.09981580078601837, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 0.0991, | |
| "step": 616 | |
| }, | |
| { | |
| "epoch": 0.6713819368879217, | |
| "grad_norm": 0.11640693992376328, | |
| "learning_rate": 4.9700992385024934e-05, | |
| "loss": 0.1061, | |
| "step": 617 | |
| }, | |
| { | |
| "epoch": 0.6724700761697497, | |
| "grad_norm": 0.10669746994972229, | |
| "learning_rate": 4.940258557148765e-05, | |
| "loss": 0.0897, | |
| "step": 618 | |
| }, | |
| { | |
| "epoch": 0.6735582154515778, | |
| "grad_norm": 0.1135135293006897, | |
| "learning_rate": 4.9104783123737566e-05, | |
| "loss": 0.1121, | |
| "step": 619 | |
| }, | |
| { | |
| "epoch": 0.6746463547334058, | |
| "grad_norm": 0.08616163581609726, | |
| "learning_rate": 4.880758859890536e-05, | |
| "loss": 0.0684, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.675734494015234, | |
| "grad_norm": 0.10301216691732407, | |
| "learning_rate": 4.851100554686021e-05, | |
| "loss": 0.0894, | |
| "step": 621 | |
| }, | |
| { | |
| "epoch": 0.676822633297062, | |
| "grad_norm": 0.10738655179738998, | |
| "learning_rate": 4.821503751016746e-05, | |
| "loss": 0.0919, | |
| "step": 622 | |
| }, | |
| { | |
| "epoch": 0.6779107725788901, | |
| "grad_norm": 0.10355032980442047, | |
| "learning_rate": 4.791968802404648e-05, | |
| "loss": 0.0855, | |
| "step": 623 | |
| }, | |
| { | |
| "epoch": 0.6789989118607181, | |
| "grad_norm": 0.10595700144767761, | |
| "learning_rate": 4.762496061632814e-05, | |
| "loss": 0.0903, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 0.6800870511425462, | |
| "grad_norm": 0.12492071092128754, | |
| "learning_rate": 4.733085880741301e-05, | |
| "loss": 0.1232, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.6811751904243744, | |
| "grad_norm": 0.1137222945690155, | |
| "learning_rate": 4.7037386110228985e-05, | |
| "loss": 0.0958, | |
| "step": 626 | |
| }, | |
| { | |
| "epoch": 0.6822633297062024, | |
| "grad_norm": 0.13245636224746704, | |
| "learning_rate": 4.6744546030189486e-05, | |
| "loss": 0.0981, | |
| "step": 627 | |
| }, | |
| { | |
| "epoch": 0.6833514689880305, | |
| "grad_norm": 0.12368131428956985, | |
| "learning_rate": 4.645234206515171e-05, | |
| "loss": 0.0811, | |
| "step": 628 | |
| }, | |
| { | |
| "epoch": 0.6844396082698585, | |
| "grad_norm": 0.10623182356357574, | |
| "learning_rate": 4.6160777705374524e-05, | |
| "loss": 0.0723, | |
| "step": 629 | |
| }, | |
| { | |
| "epoch": 0.6855277475516867, | |
| "grad_norm": 0.13129866123199463, | |
| "learning_rate": 4.586985643347717e-05, | |
| "loss": 0.1147, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.6866158868335147, | |
| "grad_norm": 0.11502306908369064, | |
| "learning_rate": 4.5579581724397255e-05, | |
| "loss": 0.0715, | |
| "step": 631 | |
| }, | |
| { | |
| "epoch": 0.6877040261153428, | |
| "grad_norm": 0.1408235728740692, | |
| "learning_rate": 4.5289957045349653e-05, | |
| "loss": 0.0919, | |
| "step": 632 | |
| }, | |
| { | |
| "epoch": 0.6887921653971708, | |
| "grad_norm": 0.1587967872619629, | |
| "learning_rate": 4.5000985855784746e-05, | |
| "loss": 0.109, | |
| "step": 633 | |
| }, | |
| { | |
| "epoch": 0.6898803046789989, | |
| "grad_norm": 0.19859641790390015, | |
| "learning_rate": 4.471267160734731e-05, | |
| "loss": 0.0959, | |
| "step": 634 | |
| }, | |
| { | |
| "epoch": 0.690968443960827, | |
| "grad_norm": 0.16058838367462158, | |
| "learning_rate": 4.442501774383515e-05, | |
| "loss": 0.1012, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 0.6920565832426551, | |
| "grad_norm": 0.2084600329399109, | |
| "learning_rate": 4.413802770115816e-05, | |
| "loss": 0.1343, | |
| "step": 636 | |
| }, | |
| { | |
| "epoch": 0.6931447225244831, | |
| "grad_norm": 0.23033252358436584, | |
| "learning_rate": 4.385170490729712e-05, | |
| "loss": 0.1517, | |
| "step": 637 | |
| }, | |
| { | |
| "epoch": 0.6942328618063112, | |
| "grad_norm": 0.2856910228729248, | |
| "learning_rate": 4.3566052782262735e-05, | |
| "loss": 0.1669, | |
| "step": 638 | |
| }, | |
| { | |
| "epoch": 0.6953210010881393, | |
| "grad_norm": 0.19062520563602448, | |
| "learning_rate": 4.328107473805487e-05, | |
| "loss": 0.0654, | |
| "step": 639 | |
| }, | |
| { | |
| "epoch": 0.6964091403699674, | |
| "grad_norm": 0.3172631561756134, | |
| "learning_rate": 4.2996774178621736e-05, | |
| "loss": 0.1788, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.6974972796517954, | |
| "grad_norm": 0.4395265281200409, | |
| "learning_rate": 4.271315449981934e-05, | |
| "loss": 0.1254, | |
| "step": 641 | |
| }, | |
| { | |
| "epoch": 0.6985854189336235, | |
| "grad_norm": 0.3653918206691742, | |
| "learning_rate": 4.2430219089370823e-05, | |
| "loss": 0.2148, | |
| "step": 642 | |
| }, | |
| { | |
| "epoch": 0.6996735582154516, | |
| "grad_norm": 0.45207682251930237, | |
| "learning_rate": 4.2147971326825966e-05, | |
| "loss": 0.2424, | |
| "step": 643 | |
| }, | |
| { | |
| "epoch": 0.7007616974972797, | |
| "grad_norm": 0.33358728885650635, | |
| "learning_rate": 4.1866414583520877e-05, | |
| "loss": 0.1578, | |
| "step": 644 | |
| }, | |
| { | |
| "epoch": 0.7018498367791077, | |
| "grad_norm": 0.2964087426662445, | |
| "learning_rate": 4.158555222253771e-05, | |
| "loss": 0.0704, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 0.7029379760609358, | |
| "grad_norm": 0.3286013603210449, | |
| "learning_rate": 4.130538759866457e-05, | |
| "loss": 0.2085, | |
| "step": 646 | |
| }, | |
| { | |
| "epoch": 0.7040261153427638, | |
| "grad_norm": 0.3953593671321869, | |
| "learning_rate": 4.102592405835536e-05, | |
| "loss": 0.2185, | |
| "step": 647 | |
| }, | |
| { | |
| "epoch": 0.705114254624592, | |
| "grad_norm": 0.46906566619873047, | |
| "learning_rate": 4.074716493968975e-05, | |
| "loss": 0.2676, | |
| "step": 648 | |
| }, | |
| { | |
| "epoch": 0.70620239390642, | |
| "grad_norm": 0.545005738735199, | |
| "learning_rate": 4.046911357233343e-05, | |
| "loss": 0.2487, | |
| "step": 649 | |
| }, | |
| { | |
| "epoch": 0.7072905331882481, | |
| "grad_norm": 0.5767453908920288, | |
| "learning_rate": 4.019177327749822e-05, | |
| "loss": 0.2432, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.7083786724700761, | |
| "grad_norm": 0.058534830808639526, | |
| "learning_rate": 3.991514736790258e-05, | |
| "loss": 0.0652, | |
| "step": 651 | |
| }, | |
| { | |
| "epoch": 0.7094668117519043, | |
| "grad_norm": 0.06634719669818878, | |
| "learning_rate": 3.963923914773187e-05, | |
| "loss": 0.0712, | |
| "step": 652 | |
| }, | |
| { | |
| "epoch": 0.7105549510337323, | |
| "grad_norm": 0.0771845281124115, | |
| "learning_rate": 3.936405191259891e-05, | |
| "loss": 0.0702, | |
| "step": 653 | |
| }, | |
| { | |
| "epoch": 0.7116430903155604, | |
| "grad_norm": 0.06693675369024277, | |
| "learning_rate": 3.9089588949504655e-05, | |
| "loss": 0.0785, | |
| "step": 654 | |
| }, | |
| { | |
| "epoch": 0.7127312295973884, | |
| "grad_norm": 0.07800418138504028, | |
| "learning_rate": 3.8815853536798904e-05, | |
| "loss": 0.093, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 0.7138193688792165, | |
| "grad_norm": 0.06311319023370743, | |
| "learning_rate": 3.854284894414122e-05, | |
| "loss": 0.0619, | |
| "step": 656 | |
| }, | |
| { | |
| "epoch": 0.7149075081610446, | |
| "grad_norm": 0.08463241159915924, | |
| "learning_rate": 3.82705784324618e-05, | |
| "loss": 0.0799, | |
| "step": 657 | |
| }, | |
| { | |
| "epoch": 0.7159956474428727, | |
| "grad_norm": 0.06584708392620087, | |
| "learning_rate": 3.79990452539225e-05, | |
| "loss": 0.0508, | |
| "step": 658 | |
| }, | |
| { | |
| "epoch": 0.7170837867247007, | |
| "grad_norm": 0.07503578066825867, | |
| "learning_rate": 3.772825265187802e-05, | |
| "loss": 0.0651, | |
| "step": 659 | |
| }, | |
| { | |
| "epoch": 0.7181719260065288, | |
| "grad_norm": 0.09440509229898453, | |
| "learning_rate": 3.7458203860837234e-05, | |
| "loss": 0.0824, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.719260065288357, | |
| "grad_norm": 0.0794801339507103, | |
| "learning_rate": 3.7188902106424416e-05, | |
| "loss": 0.0752, | |
| "step": 661 | |
| }, | |
| { | |
| "epoch": 0.720348204570185, | |
| "grad_norm": 0.08709513396024704, | |
| "learning_rate": 3.692035060534088e-05, | |
| "loss": 0.0858, | |
| "step": 662 | |
| }, | |
| { | |
| "epoch": 0.721436343852013, | |
| "grad_norm": 0.08292333036661148, | |
| "learning_rate": 3.665255256532638e-05, | |
| "loss": 0.0747, | |
| "step": 663 | |
| }, | |
| { | |
| "epoch": 0.7225244831338411, | |
| "grad_norm": 0.08945606648921967, | |
| "learning_rate": 3.638551118512089e-05, | |
| "loss": 0.0875, | |
| "step": 664 | |
| }, | |
| { | |
| "epoch": 0.7236126224156693, | |
| "grad_norm": 0.09742715954780579, | |
| "learning_rate": 3.611922965442648e-05, | |
| "loss": 0.0894, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 0.7247007616974973, | |
| "grad_norm": 0.09512501209974289, | |
| "learning_rate": 3.5853711153868965e-05, | |
| "loss": 0.0831, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 0.7257889009793254, | |
| "grad_norm": 0.12309622764587402, | |
| "learning_rate": 3.558895885496023e-05, | |
| "loss": 0.1218, | |
| "step": 667 | |
| }, | |
| { | |
| "epoch": 0.7268770402611534, | |
| "grad_norm": 0.09456098824739456, | |
| "learning_rate": 3.53249759200601e-05, | |
| "loss": 0.0957, | |
| "step": 668 | |
| }, | |
| { | |
| "epoch": 0.7279651795429815, | |
| "grad_norm": 0.10691989958286285, | |
| "learning_rate": 3.506176550233863e-05, | |
| "loss": 0.1067, | |
| "step": 669 | |
| }, | |
| { | |
| "epoch": 0.7290533188248096, | |
| "grad_norm": 0.11746580898761749, | |
| "learning_rate": 3.479933074573858e-05, | |
| "loss": 0.1002, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.7301414581066377, | |
| "grad_norm": 0.0943666398525238, | |
| "learning_rate": 3.4537674784937614e-05, | |
| "loss": 0.0842, | |
| "step": 671 | |
| }, | |
| { | |
| "epoch": 0.7312295973884657, | |
| "grad_norm": 0.0884823352098465, | |
| "learning_rate": 3.427680074531113e-05, | |
| "loss": 0.0642, | |
| "step": 672 | |
| }, | |
| { | |
| "epoch": 0.7323177366702938, | |
| "grad_norm": 0.10647040605545044, | |
| "learning_rate": 3.401671174289469e-05, | |
| "loss": 0.0805, | |
| "step": 673 | |
| }, | |
| { | |
| "epoch": 0.7334058759521219, | |
| "grad_norm": 0.11635477840900421, | |
| "learning_rate": 3.3757410884346894e-05, | |
| "loss": 0.1075, | |
| "step": 674 | |
| }, | |
| { | |
| "epoch": 0.73449401523395, | |
| "grad_norm": 0.10123847424983978, | |
| "learning_rate": 3.3498901266912396e-05, | |
| "loss": 0.0783, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.735582154515778, | |
| "grad_norm": 0.1347595453262329, | |
| "learning_rate": 3.324118597838464e-05, | |
| "loss": 0.1216, | |
| "step": 676 | |
| }, | |
| { | |
| "epoch": 0.7366702937976061, | |
| "grad_norm": 0.11851736158132553, | |
| "learning_rate": 3.298426809706928e-05, | |
| "loss": 0.0891, | |
| "step": 677 | |
| }, | |
| { | |
| "epoch": 0.7377584330794341, | |
| "grad_norm": 0.1312292367219925, | |
| "learning_rate": 3.2728150691747115e-05, | |
| "loss": 0.1008, | |
| "step": 678 | |
| }, | |
| { | |
| "epoch": 0.7388465723612623, | |
| "grad_norm": 0.12228815257549286, | |
| "learning_rate": 3.2472836821637744e-05, | |
| "loss": 0.0696, | |
| "step": 679 | |
| }, | |
| { | |
| "epoch": 0.7399347116430903, | |
| "grad_norm": 0.12540924549102783, | |
| "learning_rate": 3.2218329536362704e-05, | |
| "loss": 0.0801, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.7410228509249184, | |
| "grad_norm": 0.12973323464393616, | |
| "learning_rate": 3.196463187590929e-05, | |
| "loss": 0.0712, | |
| "step": 681 | |
| }, | |
| { | |
| "epoch": 0.7421109902067464, | |
| "grad_norm": 0.15368451178073883, | |
| "learning_rate": 3.1711746870594086e-05, | |
| "loss": 0.1033, | |
| "step": 682 | |
| }, | |
| { | |
| "epoch": 0.7431991294885746, | |
| "grad_norm": 0.21176296472549438, | |
| "learning_rate": 3.145967754102691e-05, | |
| "loss": 0.1367, | |
| "step": 683 | |
| }, | |
| { | |
| "epoch": 0.7442872687704026, | |
| "grad_norm": 0.18676644563674927, | |
| "learning_rate": 3.120842689807468e-05, | |
| "loss": 0.1081, | |
| "step": 684 | |
| }, | |
| { | |
| "epoch": 0.7453754080522307, | |
| "grad_norm": 0.1671050786972046, | |
| "learning_rate": 3.0957997942825336e-05, | |
| "loss": 0.0898, | |
| "step": 685 | |
| }, | |
| { | |
| "epoch": 0.7464635473340587, | |
| "grad_norm": 0.187219500541687, | |
| "learning_rate": 3.070839366655215e-05, | |
| "loss": 0.1019, | |
| "step": 686 | |
| }, | |
| { | |
| "epoch": 0.7475516866158868, | |
| "grad_norm": 0.17203396558761597, | |
| "learning_rate": 3.0459617050677868e-05, | |
| "loss": 0.0865, | |
| "step": 687 | |
| }, | |
| { | |
| "epoch": 0.7486398258977149, | |
| "grad_norm": 0.23022624850273132, | |
| "learning_rate": 3.021167106673928e-05, | |
| "loss": 0.1252, | |
| "step": 688 | |
| }, | |
| { | |
| "epoch": 0.749727965179543, | |
| "grad_norm": 0.2407008409500122, | |
| "learning_rate": 2.996455867635155e-05, | |
| "loss": 0.1142, | |
| "step": 689 | |
| }, | |
| { | |
| "epoch": 0.750816104461371, | |
| "grad_norm": 0.32173025608062744, | |
| "learning_rate": 2.9718282831172883e-05, | |
| "loss": 0.1342, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.750816104461371, | |
| "eval_loss": 0.10566242039203644, | |
| "eval_runtime": 24.3899, | |
| "eval_samples_per_second": 15.867, | |
| "eval_steps_per_second": 7.954, | |
| "step": 690 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 919, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 230, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.744651772592128e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |