| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 150, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 0.4784928858280182, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.3585, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.4862207770347595, | |
| "learning_rate": 5e-05, | |
| "loss": 0.3655, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.4952860474586487, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.3235, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.4571821093559265, | |
| "learning_rate": 0.0001, | |
| "loss": 0.2881, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 0.571702778339386, | |
| "learning_rate": 0.000125, | |
| "loss": 0.3014, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 0.9100359678268433, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.3376, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 0.881874144077301, | |
| "learning_rate": 0.000175, | |
| "loss": 0.3476, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.898166298866272, | |
| "learning_rate": 0.0002, | |
| "loss": 0.3728, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 0.7788503766059875, | |
| "learning_rate": 0.00019997552766852432, | |
| "loss": 0.3902, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 0.740749716758728, | |
| "learning_rate": 0.00019990212265199738, | |
| "loss": 0.4114, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": 0.6231009364128113, | |
| "learning_rate": 0.00019977982087825713, | |
| "loss": 0.3626, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 0.5968067646026611, | |
| "learning_rate": 0.00019960868220749448, | |
| "loss": 0.4036, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": 0.524666428565979, | |
| "learning_rate": 0.00019938879040295508, | |
| "loss": 0.4501, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 0.4869762659072876, | |
| "learning_rate": 0.00019912025308994148, | |
| "loss": 0.4329, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 0.5021470785140991, | |
| "learning_rate": 0.0001988032017031364, | |
| "loss": 0.4473, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.48024389147758484, | |
| "learning_rate": 0.00019843779142227256, | |
| "loss": 0.4451, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": 0.4583094120025635, | |
| "learning_rate": 0.0001980242010961803, | |
| "loss": 0.4397, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": 0.44530826807022095, | |
| "learning_rate": 0.0001975626331552507, | |
| "loss": 0.4625, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": 0.4327012300491333, | |
| "learning_rate": 0.00019705331351235674, | |
| "loss": 0.4582, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 0.4469444453716278, | |
| "learning_rate": 0.00019649649145228102, | |
| "loss": 0.4426, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": 0.4537307620048523, | |
| "learning_rate": 0.00019589243950970402, | |
| "loss": 0.4862, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 0.4526830315589905, | |
| "learning_rate": 0.00019524145333581317, | |
| "loss": 0.4991, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": 0.4435572922229767, | |
| "learning_rate": 0.00019454385155359702, | |
| "loss": 0.5121, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 0.431131511926651, | |
| "learning_rate": 0.00019379997560189675, | |
| "loss": 0.4951, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.4179699122905731, | |
| "learning_rate": 0.00019301018956828964, | |
| "loss": 0.4739, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": 0.42843425273895264, | |
| "learning_rate": 0.00019217488001088784, | |
| "loss": 0.5042, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": 0.42004117369651794, | |
| "learning_rate": 0.00019129445576913888, | |
| "loss": 0.5147, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 0.4233074486255646, | |
| "learning_rate": 0.0001903693477637204, | |
| "loss": 0.4727, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": 0.4170146882534027, | |
| "learning_rate": 0.00018940000878562758, | |
| "loss": 0.5034, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 0.4132724404335022, | |
| "learning_rate": 0.0001883869132745561, | |
| "loss": 0.47, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": 0.392947793006897, | |
| "learning_rate": 0.00018733055708668926, | |
| "loss": 0.4673, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.42713072896003723, | |
| "learning_rate": 0.00018623145725200278, | |
| "loss": 0.5235, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": 0.435976505279541, | |
| "learning_rate": 0.00018509015172120621, | |
| "loss": 0.5313, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": 0.38459959626197815, | |
| "learning_rate": 0.00018390719910244487, | |
| "loss": 0.5082, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": 0.3872632086277008, | |
| "learning_rate": 0.00018268317838789088, | |
| "loss": 0.4809, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 0.3977827727794647, | |
| "learning_rate": 0.00018141868867035745, | |
| "loss": 0.513, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": 0.3733290731906891, | |
| "learning_rate": 0.00018011434885007482, | |
| "loss": 0.4954, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 0.35552307963371277, | |
| "learning_rate": 0.00017877079733177184, | |
| "loss": 0.4978, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "grad_norm": 0.36296719312667847, | |
| "learning_rate": 0.00017738869171221068, | |
| "loss": 0.5218, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.37389761209487915, | |
| "learning_rate": 0.0001759687084583285, | |
| "loss": 0.5305, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": 0.36759287118911743, | |
| "learning_rate": 0.00017451154257614287, | |
| "loss": 0.5028, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": 0.3449918031692505, | |
| "learning_rate": 0.00017301790727058345, | |
| "loss": 0.4813, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "grad_norm": 0.3552907705307007, | |
| "learning_rate": 0.00017148853359641626, | |
| "loss": 0.5117, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 0.3388005197048187, | |
| "learning_rate": 0.00016992417010043142, | |
| "loss": 0.5042, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": 0.34015601873397827, | |
| "learning_rate": 0.00016832558245506935, | |
| "loss": 0.5185, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": 0.3483610153198242, | |
| "learning_rate": 0.0001666935530836651, | |
| "loss": 0.5137, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": 0.35940223932266235, | |
| "learning_rate": 0.0001650288807774937, | |
| "loss": 0.5542, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.3474995791912079, | |
| "learning_rate": 0.0001633323803048047, | |
| "loss": 0.5111, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": 0.33267632126808167, | |
| "learning_rate": 0.00016160488201203644, | |
| "loss": 0.4997, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.33997905254364014, | |
| "learning_rate": 0.00015984723141740576, | |
| "loss": 0.5178, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "grad_norm": 0.38659659028053284, | |
| "learning_rate": 0.0001580602887970721, | |
| "loss": 0.3993, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "grad_norm": 0.40527498722076416, | |
| "learning_rate": 0.0001562449287640781, | |
| "loss": 0.373, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "grad_norm": 0.3660850524902344, | |
| "learning_rate": 0.00015440203984027324, | |
| "loss": 0.3658, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "grad_norm": 0.3947189450263977, | |
| "learning_rate": 0.00015253252402142988, | |
| "loss": 0.395, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "grad_norm": 0.40227362513542175, | |
| "learning_rate": 0.0001506372963357644, | |
| "loss": 0.3826, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "grad_norm": 0.36494743824005127, | |
| "learning_rate": 0.00014871728439607966, | |
| "loss": 0.3372, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 1.1400000000000001, | |
| "grad_norm": 0.39481741189956665, | |
| "learning_rate": 0.00014677342794574817, | |
| "loss": 0.325, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "grad_norm": 0.4070734977722168, | |
| "learning_rate": 0.00014480667839875786, | |
| "loss": 0.3674, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "grad_norm": 0.4173199534416199, | |
| "learning_rate": 0.00014281799837404552, | |
| "loss": 0.3447, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 0.4301806390285492, | |
| "learning_rate": 0.0001408083612243465, | |
| "loss": 0.3192, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "grad_norm": 0.46535176038742065, | |
| "learning_rate": 0.00013877875055979023, | |
| "loss": 0.3729, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "grad_norm": 0.43888285756111145, | |
| "learning_rate": 0.00013673015976647568, | |
| "loss": 0.3285, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "grad_norm": 0.4748714566230774, | |
| "learning_rate": 0.00013466359152026195, | |
| "loss": 0.3497, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "grad_norm": 0.4692974090576172, | |
| "learning_rate": 0.00013258005729601177, | |
| "loss": 0.3596, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "grad_norm": 0.5036594271659851, | |
| "learning_rate": 0.00013048057687252865, | |
| "loss": 0.3248, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "grad_norm": 0.4522168040275574, | |
| "learning_rate": 0.0001283661778334297, | |
| "loss": 0.3417, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "grad_norm": 0.4366334080696106, | |
| "learning_rate": 0.0001262378950641979, | |
| "loss": 0.371, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 1.3599999999999999, | |
| "grad_norm": 0.42119064927101135, | |
| "learning_rate": 0.00012409677024566144, | |
| "loss": 0.3203, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "grad_norm": 0.42640116810798645, | |
| "learning_rate": 0.00012194385134414608, | |
| "loss": 0.3507, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "grad_norm": 0.4241952896118164, | |
| "learning_rate": 0.00011978019209855174, | |
| "loss": 0.3497, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "grad_norm": 0.4114883840084076, | |
| "learning_rate": 0.00011760685150460362, | |
| "loss": 0.3333, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "grad_norm": 0.42480409145355225, | |
| "learning_rate": 0.00011542489329653024, | |
| "loss": 0.3768, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "grad_norm": 0.40450602769851685, | |
| "learning_rate": 0.00011323538542642227, | |
| "loss": 0.3378, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "grad_norm": 0.39203861355781555, | |
| "learning_rate": 0.000111039399541527, | |
| "loss": 0.3475, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 0.38859793543815613, | |
| "learning_rate": 0.00010883801045973425, | |
| "loss": 0.3244, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "grad_norm": 0.3974066972732544, | |
| "learning_rate": 0.00010663229564351041, | |
| "loss": 0.3774, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "grad_norm": 0.4268834888935089, | |
| "learning_rate": 0.00010442333467253789, | |
| "loss": 0.3494, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "grad_norm": 0.4215947985649109, | |
| "learning_rate": 0.00010221220871531869, | |
| "loss": 0.35, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "grad_norm": 0.40650272369384766, | |
| "learning_rate": 0.0001, | |
| "loss": 0.3442, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 0.40281081199645996, | |
| "learning_rate": 9.778779128468132e-05, | |
| "loss": 0.3307, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "grad_norm": 0.4170817732810974, | |
| "learning_rate": 9.557666532746213e-05, | |
| "loss": 0.3424, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 1.6400000000000001, | |
| "grad_norm": 0.4091716408729553, | |
| "learning_rate": 9.336770435648964e-05, | |
| "loss": 0.3256, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 1.6600000000000001, | |
| "grad_norm": 0.4192478656768799, | |
| "learning_rate": 9.116198954026577e-05, | |
| "loss": 0.3378, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 1.6800000000000002, | |
| "grad_norm": 0.43887075781822205, | |
| "learning_rate": 8.896060045847304e-05, | |
| "loss": 0.3392, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "grad_norm": 0.42365938425064087, | |
| "learning_rate": 8.676461457357776e-05, | |
| "loss": 0.3347, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "grad_norm": 0.41718992590904236, | |
| "learning_rate": 8.457510670346976e-05, | |
| "loss": 0.3316, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "grad_norm": 0.4348912239074707, | |
| "learning_rate": 8.239314849539638e-05, | |
| "loss": 0.3139, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "grad_norm": 0.41789305210113525, | |
| "learning_rate": 8.021980790144827e-05, | |
| "loss": 0.3066, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "grad_norm": 0.4338313043117523, | |
| "learning_rate": 7.805614865585396e-05, | |
| "loss": 0.3497, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "grad_norm": 0.413273423910141, | |
| "learning_rate": 7.590322975433857e-05, | |
| "loss": 0.3372, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.8199999999999998, | |
| "grad_norm": 0.43203985691070557, | |
| "learning_rate": 7.376210493580212e-05, | |
| "loss": 0.3601, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 1.8399999999999999, | |
| "grad_norm": 0.4087103605270386, | |
| "learning_rate": 7.163382216657034e-05, | |
| "loss": 0.3533, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 1.8599999999999999, | |
| "grad_norm": 0.41923317313194275, | |
| "learning_rate": 6.951942312747134e-05, | |
| "loss": 0.3547, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "grad_norm": 0.41816338896751404, | |
| "learning_rate": 6.741994270398826e-05, | |
| "loss": 0.3497, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "grad_norm": 0.4215528666973114, | |
| "learning_rate": 6.533640847973808e-05, | |
| "loss": 0.3396, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "grad_norm": 0.3927628695964813, | |
| "learning_rate": 6.326984023352435e-05, | |
| "loss": 0.3313, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "grad_norm": 0.42098793387413025, | |
| "learning_rate": 6.122124944020977e-05, | |
| "loss": 0.3501, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "grad_norm": 0.4087188243865967, | |
| "learning_rate": 5.91916387756535e-05, | |
| "loss": 0.3311, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "grad_norm": 0.42781955003738403, | |
| "learning_rate": 5.718200162595449e-05, | |
| "loss": 0.3149, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.42511481046676636, | |
| "learning_rate": 5.5193321601242156e-05, | |
| "loss": 0.3716, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "grad_norm": 0.3746088743209839, | |
| "learning_rate": 5.322657205425183e-05, | |
| "loss": 0.2761, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "grad_norm": 0.37996241450309753, | |
| "learning_rate": 5.1282715603920374e-05, | |
| "loss": 0.2756, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "grad_norm": 0.38573023676872253, | |
| "learning_rate": 4.936270366423563e-05, | |
| "loss": 0.2501, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "grad_norm": 0.3644517660140991, | |
| "learning_rate": 4.746747597857014e-05, | |
| "loss": 0.2632, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "grad_norm": 0.3908427953720093, | |
| "learning_rate": 4.559796015972677e-05, | |
| "loss": 0.2799, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "grad_norm": 0.40510475635528564, | |
| "learning_rate": 4.375507123592194e-05, | |
| "loss": 0.2581, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "grad_norm": 0.38553154468536377, | |
| "learning_rate": 4.1939711202927936e-05, | |
| "loss": 0.2495, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "grad_norm": 0.396541565656662, | |
| "learning_rate": 4.015276858259427e-05, | |
| "loss": 0.2728, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "grad_norm": 0.3897378444671631, | |
| "learning_rate": 3.839511798796357e-05, | |
| "loss": 0.2551, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "grad_norm": 0.3955518305301666, | |
| "learning_rate": 3.6667619695195285e-05, | |
| "loss": 0.2704, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "grad_norm": 0.4070671498775482, | |
| "learning_rate": 3.49711192225063e-05, | |
| "loss": 0.2701, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "grad_norm": 0.3995331823825836, | |
| "learning_rate": 3.330644691633492e-05, | |
| "loss": 0.2753, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "grad_norm": 0.4080023169517517, | |
| "learning_rate": 3.167441754493066e-05, | |
| "loss": 0.2483, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 2.2800000000000002, | |
| "grad_norm": 0.40179961919784546, | |
| "learning_rate": 3.0075829899568597e-05, | |
| "loss": 0.2369, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "grad_norm": 0.43834614753723145, | |
| "learning_rate": 2.8511466403583766e-05, | |
| "loss": 0.2474, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "grad_norm": 0.4417284429073334, | |
| "learning_rate": 2.6982092729416587e-05, | |
| "loss": 0.2482, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "grad_norm": 0.4265671670436859, | |
| "learning_rate": 2.548845742385717e-05, | |
| "loss": 0.2458, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "grad_norm": 0.4640134274959564, | |
| "learning_rate": 2.403129154167153e-05, | |
| "loss": 0.2555, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "grad_norm": 0.42158064246177673, | |
| "learning_rate": 2.2611308287789344e-05, | |
| "loss": 0.2485, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "grad_norm": 0.42740365862846375, | |
| "learning_rate": 2.1229202668228197e-05, | |
| "loss": 0.2681, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "grad_norm": 0.4214995801448822, | |
| "learning_rate": 1.988565114992519e-05, | |
| "loss": 0.2595, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "grad_norm": 0.44696784019470215, | |
| "learning_rate": 1.858131132964259e-05, | |
| "loss": 0.2695, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "grad_norm": 0.43291181325912476, | |
| "learning_rate": 1.7316821612109136e-05, | |
| "loss": 0.2329, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "grad_norm": 0.4297809600830078, | |
| "learning_rate": 1.609280089755515e-05, | |
| "loss": 0.2521, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "grad_norm": 0.42929723858833313, | |
| "learning_rate": 1.4909848278793782e-05, | |
| "loss": 0.2447, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "grad_norm": 0.414578914642334, | |
| "learning_rate": 1.3768542747997215e-05, | |
| "loss": 0.2597, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "grad_norm": 0.41869866847991943, | |
| "learning_rate": 1.2669442913310725e-05, | |
| "loss": 0.2621, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "grad_norm": 0.4209769666194916, | |
| "learning_rate": 1.161308672544389e-05, | |
| "loss": 0.25, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "grad_norm": 0.40297356247901917, | |
| "learning_rate": 1.059999121437244e-05, | |
| "loss": 0.239, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "grad_norm": 0.4161122739315033, | |
| "learning_rate": 9.630652236279625e-06, | |
| "loss": 0.2621, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "grad_norm": 0.43759092688560486, | |
| "learning_rate": 8.70554423086114e-06, | |
| "loss": 0.2681, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "grad_norm": 0.41500815749168396, | |
| "learning_rate": 7.825119989112173e-06, | |
| "loss": 0.2547, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "grad_norm": 0.40593695640563965, | |
| "learning_rate": 6.989810431710375e-06, | |
| "loss": 0.2482, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "grad_norm": 0.40096405148506165, | |
| "learning_rate": 6.200024398103255e-06, | |
| "loss": 0.2402, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "grad_norm": 0.39252418279647827, | |
| "learning_rate": 5.456148446402976e-06, | |
| "loss": 0.2396, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 2.7199999999999998, | |
| "grad_norm": 0.41394537687301636, | |
| "learning_rate": 4.758546664186869e-06, | |
| "loss": 0.2729, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "grad_norm": 0.40165257453918457, | |
| "learning_rate": 4.107560490295992e-06, | |
| "loss": 0.2497, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "grad_norm": 0.42329922318458557, | |
| "learning_rate": 3.5035085477190143e-06, | |
| "loss": 0.2444, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 2.7800000000000002, | |
| "grad_norm": 0.4126729965209961, | |
| "learning_rate": 2.94668648764328e-06, | |
| "loss": 0.256, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "grad_norm": 0.4390856623649597, | |
| "learning_rate": 2.4373668447493224e-06, | |
| "loss": 0.2591, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "grad_norm": 0.4362524151802063, | |
| "learning_rate": 1.9757989038197146e-06, | |
| "loss": 0.255, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "grad_norm": 0.43163925409317017, | |
| "learning_rate": 1.562208577727442e-06, | |
| "loss": 0.2581, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "grad_norm": 0.418253093957901, | |
| "learning_rate": 1.1967982968635993e-06, | |
| "loss": 0.2535, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "grad_norm": 0.43555358052253723, | |
| "learning_rate": 8.797469100585431e-07, | |
| "loss": 0.272, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "grad_norm": 0.412000834941864, | |
| "learning_rate": 6.11209597044926e-07, | |
| "loss": 0.2344, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "grad_norm": 0.41050902009010315, | |
| "learning_rate": 3.913177925055189e-07, | |
| "loss": 0.2403, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "grad_norm": 0.40769293904304504, | |
| "learning_rate": 2.201791217428917e-07, | |
| "loss": 0.2416, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "grad_norm": 0.4063026010990143, | |
| "learning_rate": 9.78773480026396e-08, | |
| "loss": 0.2491, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "grad_norm": 0.4020632207393646, | |
| "learning_rate": 2.447233147570005e-08, | |
| "loss": 0.2472, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 0.42892733216285706, | |
| "learning_rate": 0.0, | |
| "loss": 0.2704, | |
| "step": 150 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 150, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.817534143122309e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |