| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 4.018145161290322, |
| "eval_steps": 25, |
| "global_step": 253, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.02, |
| "learning_rate": 2e-05, |
| "loss": 4.2125, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.02, |
| "eval_loss": 4.052073955535889, |
| "eval_runtime": 61.8325, |
| "eval_samples_per_second": 4.043, |
| "eval_steps_per_second": 4.043, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.03, |
| "learning_rate": 4e-05, |
| "loss": 4.2885, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.05, |
| "learning_rate": 6e-05, |
| "loss": 4.2535, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.06, |
| "learning_rate": 8e-05, |
| "loss": 4.0238, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.08, |
| "learning_rate": 0.0001, |
| "loss": 3.8658, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.1, |
| "learning_rate": 0.00012, |
| "loss": 3.991, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.11, |
| "learning_rate": 0.00014, |
| "loss": 3.8686, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.13, |
| "learning_rate": 0.00016, |
| "loss": 3.8117, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.15, |
| "learning_rate": 0.00018, |
| "loss": 4.0165, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.16, |
| "learning_rate": 0.0002, |
| "loss": 3.7689, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.18, |
| "learning_rate": 0.0001999979107245606, |
| "loss": 3.6961, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.19, |
| "learning_rate": 0.00019999164298554375, |
| "loss": 3.5999, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.21, |
| "learning_rate": 0.00019998119704485014, |
| "loss": 3.5358, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.23, |
| "learning_rate": 0.00019996657333896877, |
| "loss": 3.51, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.24, |
| "learning_rate": 0.00019994777247895855, |
| "loss": 3.3729, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.26, |
| "learning_rate": 0.00019992479525042303, |
| "loss": 3.3557, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.27, |
| "learning_rate": 0.00019989764261347736, |
| "loss": 3.3868, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.29, |
| "learning_rate": 0.00019986631570270832, |
| "loss": 3.4494, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.31, |
| "learning_rate": 0.00019983081582712685, |
| "loss": 3.4571, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.32, |
| "learning_rate": 0.00019979114447011323, |
| "loss": 3.254, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.34, |
| "learning_rate": 0.00019974730328935534, |
| "loss": 3.2094, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.35, |
| "learning_rate": 0.0001996992941167792, |
| "loss": 3.2843, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.37, |
| "learning_rate": 0.00019964711895847258, |
| "loss": 3.2776, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.39, |
| "learning_rate": 0.00019959077999460095, |
| "loss": 2.9951, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.4, |
| "learning_rate": 0.00019953027957931658, |
| "loss": 3.1523, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.4, |
| "eval_loss": 2.9463467597961426, |
| "eval_runtime": 62.0633, |
| "eval_samples_per_second": 4.028, |
| "eval_steps_per_second": 4.028, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.42, |
| "learning_rate": 0.00019946562024066014, |
| "loss": 3.0537, |
| "step": 26 |
| }, |
| { |
| "epoch": 0.44, |
| "learning_rate": 0.00019939680468045499, |
| "loss": 2.8775, |
| "step": 27 |
| }, |
| { |
| "epoch": 0.45, |
| "learning_rate": 0.00019932383577419432, |
| "loss": 3.0155, |
| "step": 28 |
| }, |
| { |
| "epoch": 0.47, |
| "learning_rate": 0.00019924671657092096, |
| "loss": 2.8512, |
| "step": 29 |
| }, |
| { |
| "epoch": 0.48, |
| "learning_rate": 0.00019916545029310012, |
| "loss": 2.7208, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.5, |
| "learning_rate": 0.00019908004033648453, |
| "loss": 2.7177, |
| "step": 31 |
| }, |
| { |
| "epoch": 0.52, |
| "learning_rate": 0.00019899049026997272, |
| "loss": 2.536, |
| "step": 32 |
| }, |
| { |
| "epoch": 0.53, |
| "learning_rate": 0.00019889680383545973, |
| "loss": 2.6654, |
| "step": 33 |
| }, |
| { |
| "epoch": 0.55, |
| "learning_rate": 0.00019879898494768093, |
| "loss": 2.5692, |
| "step": 34 |
| }, |
| { |
| "epoch": 0.56, |
| "learning_rate": 0.00019869703769404828, |
| "loss": 2.4448, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.58, |
| "learning_rate": 0.00019859096633447965, |
| "loss": 2.4296, |
| "step": 36 |
| }, |
| { |
| "epoch": 0.6, |
| "learning_rate": 0.00019848077530122083, |
| "loss": 2.3887, |
| "step": 37 |
| }, |
| { |
| "epoch": 0.61, |
| "learning_rate": 0.0001983664691986601, |
| "loss": 2.3225, |
| "step": 38 |
| }, |
| { |
| "epoch": 0.63, |
| "learning_rate": 0.00019824805280313623, |
| "loss": 2.1755, |
| "step": 39 |
| }, |
| { |
| "epoch": 0.65, |
| "learning_rate": 0.00019812553106273847, |
| "loss": 2.1252, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.66, |
| "learning_rate": 0.00019799890909710013, |
| "loss": 2.1585, |
| "step": 41 |
| }, |
| { |
| "epoch": 0.68, |
| "learning_rate": 0.00019786819219718443, |
| "loss": 2.2467, |
| "step": 42 |
| }, |
| { |
| "epoch": 0.69, |
| "learning_rate": 0.0001977333858250636, |
| "loss": 2.0564, |
| "step": 43 |
| }, |
| { |
| "epoch": 0.71, |
| "learning_rate": 0.00019759449561369038, |
| "loss": 2.0713, |
| "step": 44 |
| }, |
| { |
| "epoch": 0.73, |
| "learning_rate": 0.00019745152736666302, |
| "loss": 1.9998, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.74, |
| "learning_rate": 0.00019730448705798239, |
| "loss": 2.1497, |
| "step": 46 |
| }, |
| { |
| "epoch": 0.76, |
| "learning_rate": 0.00019715338083180269, |
| "loss": 1.9467, |
| "step": 47 |
| }, |
| { |
| "epoch": 0.77, |
| "learning_rate": 0.00019699821500217434, |
| "loss": 1.9195, |
| "step": 48 |
| }, |
| { |
| "epoch": 0.79, |
| "learning_rate": 0.0001968389960527806, |
| "loss": 1.7969, |
| "step": 49 |
| }, |
| { |
| "epoch": 0.81, |
| "learning_rate": 0.0001966757306366662, |
| "loss": 1.9685, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.81, |
| "eval_loss": 1.8644403219223022, |
| "eval_runtime": 62.0885, |
| "eval_samples_per_second": 4.027, |
| "eval_steps_per_second": 4.027, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.82, |
| "learning_rate": 0.00019650842557595967, |
| "loss": 1.8609, |
| "step": 51 |
| }, |
| { |
| "epoch": 0.84, |
| "learning_rate": 0.00019633708786158806, |
| "loss": 1.8528, |
| "step": 52 |
| }, |
| { |
| "epoch": 0.85, |
| "learning_rate": 0.00019616172465298492, |
| "loss": 1.7482, |
| "step": 53 |
| }, |
| { |
| "epoch": 0.87, |
| "learning_rate": 0.00019598234327779118, |
| "loss": 1.5841, |
| "step": 54 |
| }, |
| { |
| "epoch": 0.89, |
| "learning_rate": 0.0001957989512315489, |
| "loss": 1.8643, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.9, |
| "learning_rate": 0.00019561155617738797, |
| "loss": 1.7103, |
| "step": 56 |
| }, |
| { |
| "epoch": 0.92, |
| "learning_rate": 0.00019542016594570615, |
| "loss": 1.886, |
| "step": 57 |
| }, |
| { |
| "epoch": 0.94, |
| "learning_rate": 0.00019522478853384155, |
| "loss": 1.7265, |
| "step": 58 |
| }, |
| { |
| "epoch": 0.95, |
| "learning_rate": 0.00019502543210573881, |
| "loss": 1.7261, |
| "step": 59 |
| }, |
| { |
| "epoch": 0.97, |
| "learning_rate": 0.00019482210499160765, |
| "loss": 1.6018, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.98, |
| "learning_rate": 0.00019461481568757506, |
| "loss": 1.7412, |
| "step": 61 |
| }, |
| { |
| "epoch": 1.0, |
| "learning_rate": 0.00019440357285533, |
| "loss": 1.5618, |
| "step": 62 |
| }, |
| { |
| "epoch": 1.02, |
| "learning_rate": 0.00019418838532176173, |
| "loss": 1.6051, |
| "step": 63 |
| }, |
| { |
| "epoch": 1.01, |
| "learning_rate": 0.00019396926207859084, |
| "loss": 1.5225, |
| "step": 64 |
| }, |
| { |
| "epoch": 1.03, |
| "learning_rate": 0.0001937462122819935, |
| "loss": 1.6547, |
| "step": 65 |
| }, |
| { |
| "epoch": 1.04, |
| "learning_rate": 0.000193519245252219, |
| "loss": 1.6184, |
| "step": 66 |
| }, |
| { |
| "epoch": 1.06, |
| "learning_rate": 0.0001932883704732001, |
| "loss": 1.4581, |
| "step": 67 |
| }, |
| { |
| "epoch": 1.07, |
| "learning_rate": 0.00019305359759215685, |
| "loss": 1.567, |
| "step": 68 |
| }, |
| { |
| "epoch": 1.09, |
| "learning_rate": 0.00019281493641919368, |
| "loss": 1.645, |
| "step": 69 |
| }, |
| { |
| "epoch": 1.11, |
| "learning_rate": 0.00019257239692688907, |
| "loss": 1.5237, |
| "step": 70 |
| }, |
| { |
| "epoch": 1.12, |
| "learning_rate": 0.00019232598924987903, |
| "loss": 1.4956, |
| "step": 71 |
| }, |
| { |
| "epoch": 1.14, |
| "learning_rate": 0.00019207572368443385, |
| "loss": 1.5493, |
| "step": 72 |
| }, |
| { |
| "epoch": 1.16, |
| "learning_rate": 0.00019182161068802741, |
| "loss": 1.495, |
| "step": 73 |
| }, |
| { |
| "epoch": 1.17, |
| "learning_rate": 0.0001915636608789006, |
| "loss": 1.3961, |
| "step": 74 |
| }, |
| { |
| "epoch": 1.19, |
| "learning_rate": 0.00019130188503561741, |
| "loss": 1.5639, |
| "step": 75 |
| }, |
| { |
| "epoch": 1.19, |
| "eval_loss": 1.5244245529174805, |
| "eval_runtime": 62.0668, |
| "eval_samples_per_second": 4.028, |
| "eval_steps_per_second": 4.028, |
| "step": 75 |
| }, |
| { |
| "epoch": 1.2, |
| "learning_rate": 0.0001910362940966147, |
| "loss": 1.4871, |
| "step": 76 |
| }, |
| { |
| "epoch": 1.22, |
| "learning_rate": 0.00019076689915974488, |
| "loss": 1.6211, |
| "step": 77 |
| }, |
| { |
| "epoch": 1.24, |
| "learning_rate": 0.00019049371148181253, |
| "loss": 1.4287, |
| "step": 78 |
| }, |
| { |
| "epoch": 1.25, |
| "learning_rate": 0.0001902167424781038, |
| "loss": 1.4661, |
| "step": 79 |
| }, |
| { |
| "epoch": 1.27, |
| "learning_rate": 0.00018993600372190932, |
| "loss": 1.5775, |
| "step": 80 |
| }, |
| { |
| "epoch": 1.28, |
| "learning_rate": 0.00018965150694404094, |
| "loss": 1.4292, |
| "step": 81 |
| }, |
| { |
| "epoch": 1.3, |
| "learning_rate": 0.00018936326403234125, |
| "loss": 1.4739, |
| "step": 82 |
| }, |
| { |
| "epoch": 1.32, |
| "learning_rate": 0.00018907128703118695, |
| "loss": 1.5025, |
| "step": 83 |
| }, |
| { |
| "epoch": 1.33, |
| "learning_rate": 0.00018877558814098561, |
| "loss": 1.423, |
| "step": 84 |
| }, |
| { |
| "epoch": 1.35, |
| "learning_rate": 0.00018847617971766577, |
| "loss": 1.4102, |
| "step": 85 |
| }, |
| { |
| "epoch": 1.36, |
| "learning_rate": 0.0001881730742721608, |
| "loss": 1.4348, |
| "step": 86 |
| }, |
| { |
| "epoch": 1.38, |
| "learning_rate": 0.00018786628446988593, |
| "loss": 1.3953, |
| "step": 87 |
| }, |
| { |
| "epoch": 1.4, |
| "learning_rate": 0.0001875558231302091, |
| "loss": 1.3912, |
| "step": 88 |
| }, |
| { |
| "epoch": 1.41, |
| "learning_rate": 0.00018724170322591537, |
| "loss": 1.4086, |
| "step": 89 |
| }, |
| { |
| "epoch": 1.43, |
| "learning_rate": 0.00018692393788266479, |
| "loss": 1.3259, |
| "step": 90 |
| }, |
| { |
| "epoch": 1.45, |
| "learning_rate": 0.00018660254037844388, |
| "loss": 1.5038, |
| "step": 91 |
| }, |
| { |
| "epoch": 1.46, |
| "learning_rate": 0.00018627752414301086, |
| "loss": 1.3597, |
| "step": 92 |
| }, |
| { |
| "epoch": 1.48, |
| "learning_rate": 0.00018594890275733453, |
| "loss": 1.466, |
| "step": 93 |
| }, |
| { |
| "epoch": 1.49, |
| "learning_rate": 0.00018561668995302667, |
| "loss": 1.3287, |
| "step": 94 |
| }, |
| { |
| "epoch": 1.51, |
| "learning_rate": 0.0001852808996117683, |
| "loss": 1.3319, |
| "step": 95 |
| }, |
| { |
| "epoch": 1.53, |
| "learning_rate": 0.00018494154576472976, |
| "loss": 1.4434, |
| "step": 96 |
| }, |
| { |
| "epoch": 1.54, |
| "learning_rate": 0.0001845986425919841, |
| "loss": 1.4025, |
| "step": 97 |
| }, |
| { |
| "epoch": 1.56, |
| "learning_rate": 0.00018425220442191495, |
| "loss": 1.3213, |
| "step": 98 |
| }, |
| { |
| "epoch": 1.57, |
| "learning_rate": 0.00018390224573061747, |
| "loss": 1.2632, |
| "step": 99 |
| }, |
| { |
| "epoch": 1.59, |
| "learning_rate": 0.00018354878114129367, |
| "loss": 1.2843, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.59, |
| "eval_loss": 1.4124521017074585, |
| "eval_runtime": 62.1529, |
| "eval_samples_per_second": 4.022, |
| "eval_steps_per_second": 4.022, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.61, |
| "learning_rate": 0.00018319182542364117, |
| "loss": 1.4325, |
| "step": 101 |
| }, |
| { |
| "epoch": 1.62, |
| "learning_rate": 0.00018283139349323634, |
| "loss": 1.3073, |
| "step": 102 |
| }, |
| { |
| "epoch": 1.64, |
| "learning_rate": 0.0001824675004109107, |
| "loss": 1.4306, |
| "step": 103 |
| }, |
| { |
| "epoch": 1.66, |
| "learning_rate": 0.00018210016138212187, |
| "loss": 1.4146, |
| "step": 104 |
| }, |
| { |
| "epoch": 1.67, |
| "learning_rate": 0.00018172939175631808, |
| "loss": 1.4248, |
| "step": 105 |
| }, |
| { |
| "epoch": 1.69, |
| "learning_rate": 0.00018135520702629675, |
| "loss": 1.1905, |
| "step": 106 |
| }, |
| { |
| "epoch": 1.7, |
| "learning_rate": 0.00018097762282755727, |
| "loss": 1.2818, |
| "step": 107 |
| }, |
| { |
| "epoch": 1.72, |
| "learning_rate": 0.00018059665493764743, |
| "loss": 1.3104, |
| "step": 108 |
| }, |
| { |
| "epoch": 1.74, |
| "learning_rate": 0.0001802123192755044, |
| "loss": 1.3141, |
| "step": 109 |
| }, |
| { |
| "epoch": 1.75, |
| "learning_rate": 0.0001798246319007893, |
| "loss": 1.2494, |
| "step": 110 |
| }, |
| { |
| "epoch": 1.77, |
| "learning_rate": 0.0001794336090132164, |
| "loss": 1.2817, |
| "step": 111 |
| }, |
| { |
| "epoch": 1.78, |
| "learning_rate": 0.00017903926695187595, |
| "loss": 1.2675, |
| "step": 112 |
| }, |
| { |
| "epoch": 1.8, |
| "learning_rate": 0.00017864162219455163, |
| "loss": 1.3368, |
| "step": 113 |
| }, |
| { |
| "epoch": 1.82, |
| "learning_rate": 0.00017824069135703198, |
| "loss": 1.3054, |
| "step": 114 |
| }, |
| { |
| "epoch": 1.83, |
| "learning_rate": 0.00017783649119241602, |
| "loss": 1.4334, |
| "step": 115 |
| }, |
| { |
| "epoch": 1.85, |
| "learning_rate": 0.00017742903859041325, |
| "loss": 1.3058, |
| "step": 116 |
| }, |
| { |
| "epoch": 1.86, |
| "learning_rate": 0.00017701835057663798, |
| "loss": 1.2882, |
| "step": 117 |
| }, |
| { |
| "epoch": 1.88, |
| "learning_rate": 0.0001766044443118978, |
| "loss": 1.1971, |
| "step": 118 |
| }, |
| { |
| "epoch": 1.9, |
| "learning_rate": 0.00017618733709147662, |
| "loss": 1.2832, |
| "step": 119 |
| }, |
| { |
| "epoch": 1.91, |
| "learning_rate": 0.0001757670463444118, |
| "loss": 1.2372, |
| "step": 120 |
| }, |
| { |
| "epoch": 1.93, |
| "learning_rate": 0.00017534358963276607, |
| "loss": 1.182, |
| "step": 121 |
| }, |
| { |
| "epoch": 1.95, |
| "learning_rate": 0.00017491698465089362, |
| "loss": 1.2228, |
| "step": 122 |
| }, |
| { |
| "epoch": 1.96, |
| "learning_rate": 0.00017448724922470058, |
| "loss": 1.3541, |
| "step": 123 |
| }, |
| { |
| "epoch": 1.98, |
| "learning_rate": 0.00017405440131090048, |
| "loss": 1.2751, |
| "step": 124 |
| }, |
| { |
| "epoch": 1.99, |
| "learning_rate": 0.00017361845899626355, |
| "loss": 1.1626, |
| "step": 125 |
| }, |
| { |
| "epoch": 1.99, |
| "eval_loss": 1.351290225982666, |
| "eval_runtime": 62.1247, |
| "eval_samples_per_second": 4.024, |
| "eval_steps_per_second": 4.024, |
| "step": 125 |
| }, |
| { |
| "epoch": 2.01, |
| "learning_rate": 0.00017317944049686124, |
| "loss": 1.2837, |
| "step": 126 |
| }, |
| { |
| "epoch": 2.01, |
| "learning_rate": 0.00017273736415730488, |
| "loss": 1.1712, |
| "step": 127 |
| }, |
| { |
| "epoch": 2.02, |
| "learning_rate": 0.00017229224844997928, |
| "loss": 1.1996, |
| "step": 128 |
| }, |
| { |
| "epoch": 2.04, |
| "learning_rate": 0.00017184411197427077, |
| "loss": 1.1007, |
| "step": 129 |
| }, |
| { |
| "epoch": 2.05, |
| "learning_rate": 0.00017139297345578994, |
| "loss": 1.1426, |
| "step": 130 |
| }, |
| { |
| "epoch": 2.07, |
| "learning_rate": 0.0001709388517455893, |
| "loss": 1.2041, |
| "step": 131 |
| }, |
| { |
| "epoch": 2.09, |
| "learning_rate": 0.00017048176581937563, |
| "loss": 1.1214, |
| "step": 132 |
| }, |
| { |
| "epoch": 2.1, |
| "learning_rate": 0.00017048176581937563, |
| "loss": 1.1013, |
| "step": 133 |
| }, |
| { |
| "epoch": 2.12, |
| "learning_rate": 0.00017002173477671686, |
| "loss": 1.0937, |
| "step": 134 |
| }, |
| { |
| "epoch": 2.14, |
| "learning_rate": 0.0001695587778402442, |
| "loss": 1.132, |
| "step": 135 |
| }, |
| { |
| "epoch": 2.15, |
| "learning_rate": 0.0001690929143548488, |
| "loss": 1.1336, |
| "step": 136 |
| }, |
| { |
| "epoch": 2.17, |
| "learning_rate": 0.0001686241637868734, |
| "loss": 1.0649, |
| "step": 137 |
| }, |
| { |
| "epoch": 2.18, |
| "learning_rate": 0.00016815254572329896, |
| "loss": 1.126, |
| "step": 138 |
| }, |
| { |
| "epoch": 2.2, |
| "learning_rate": 0.00016767807987092621, |
| "loss": 1.1903, |
| "step": 139 |
| }, |
| { |
| "epoch": 2.22, |
| "learning_rate": 0.00016720078605555224, |
| "loss": 1.2231, |
| "step": 140 |
| }, |
| { |
| "epoch": 2.23, |
| "learning_rate": 0.00016672068422114196, |
| "loss": 1.2027, |
| "step": 141 |
| }, |
| { |
| "epoch": 2.25, |
| "learning_rate": 0.0001662377944289948, |
| "loss": 1.1121, |
| "step": 142 |
| }, |
| { |
| "epoch": 2.26, |
| "learning_rate": 0.0001657521368569064, |
| "loss": 1.1226, |
| "step": 143 |
| }, |
| { |
| "epoch": 2.28, |
| "learning_rate": 0.00016526373179832546, |
| "loss": 1.2607, |
| "step": 144 |
| }, |
| { |
| "epoch": 2.3, |
| "learning_rate": 0.00016477259966150588, |
| "loss": 1.0129, |
| "step": 145 |
| }, |
| { |
| "epoch": 2.31, |
| "learning_rate": 0.00016427876096865394, |
| "loss": 1.1083, |
| "step": 146 |
| }, |
| { |
| "epoch": 2.33, |
| "learning_rate": 0.0001637822363550706, |
| "loss": 1.1899, |
| "step": 147 |
| }, |
| { |
| "epoch": 2.34, |
| "learning_rate": 0.00016328304656828952, |
| "loss": 1.1603, |
| "step": 148 |
| }, |
| { |
| "epoch": 2.36, |
| "learning_rate": 0.00016278121246720987, |
| "loss": 1.1224, |
| "step": 149 |
| }, |
| { |
| "epoch": 2.38, |
| "learning_rate": 0.00016227675502122492, |
| "loss": 1.2645, |
| "step": 150 |
| }, |
| { |
| "epoch": 2.38, |
| "eval_loss": 1.3386605978012085, |
| "eval_runtime": 62.2057, |
| "eval_samples_per_second": 4.019, |
| "eval_steps_per_second": 4.019, |
| "step": 150 |
| }, |
| { |
| "epoch": 2.39, |
| "learning_rate": 0.00016176969530934572, |
| "loss": 1.1165, |
| "step": 151 |
| }, |
| { |
| "epoch": 2.41, |
| "learning_rate": 0.0001612600545193203, |
| "loss": 1.1705, |
| "step": 152 |
| }, |
| { |
| "epoch": 2.43, |
| "learning_rate": 0.00016074785394674837, |
| "loss": 1.1285, |
| "step": 153 |
| }, |
| { |
| "epoch": 2.44, |
| "learning_rate": 0.0001602331149941915, |
| "loss": 1.2047, |
| "step": 154 |
| }, |
| { |
| "epoch": 2.46, |
| "learning_rate": 0.00015971585917027862, |
| "loss": 1.0933, |
| "step": 155 |
| }, |
| { |
| "epoch": 2.47, |
| "learning_rate": 0.0001591961080888076, |
| "loss": 1.1415, |
| "step": 156 |
| }, |
| { |
| "epoch": 2.49, |
| "learning_rate": 0.0001586738834678418, |
| "loss": 1.1956, |
| "step": 157 |
| }, |
| { |
| "epoch": 2.51, |
| "learning_rate": 0.00015814920712880267, |
| "loss": 1.264, |
| "step": 158 |
| }, |
| { |
| "epoch": 2.52, |
| "learning_rate": 0.00015762210099555803, |
| "loss": 1.1909, |
| "step": 159 |
| }, |
| { |
| "epoch": 2.54, |
| "learning_rate": 0.00015709258709350582, |
| "loss": 1.0594, |
| "step": 160 |
| }, |
| { |
| "epoch": 2.55, |
| "learning_rate": 0.00015656068754865387, |
| "loss": 1.1423, |
| "step": 161 |
| }, |
| { |
| "epoch": 2.57, |
| "learning_rate": 0.00015602642458669528, |
| "loss": 1.1687, |
| "step": 162 |
| }, |
| { |
| "epoch": 2.59, |
| "learning_rate": 0.0001554898205320797, |
| "loss": 1.0989, |
| "step": 163 |
| }, |
| { |
| "epoch": 2.6, |
| "learning_rate": 0.0001549508978070806, |
| "loss": 1.2288, |
| "step": 164 |
| }, |
| { |
| "epoch": 2.62, |
| "learning_rate": 0.00015440967893085828, |
| "loss": 1.2075, |
| "step": 165 |
| }, |
| { |
| "epoch": 2.64, |
| "learning_rate": 0.0001538661865185188, |
| "loss": 1.256, |
| "step": 166 |
| }, |
| { |
| "epoch": 2.65, |
| "learning_rate": 0.00015332044328016914, |
| "loss": 1.1595, |
| "step": 167 |
| }, |
| { |
| "epoch": 2.67, |
| "learning_rate": 0.0001527724720199682, |
| "loss": 1.1199, |
| "step": 168 |
| }, |
| { |
| "epoch": 2.68, |
| "learning_rate": 0.00015222229563517385, |
| "loss": 1.1336, |
| "step": 169 |
| }, |
| { |
| "epoch": 2.7, |
| "learning_rate": 0.00015166993711518631, |
| "loss": 1.1568, |
| "step": 170 |
| }, |
| { |
| "epoch": 2.72, |
| "learning_rate": 0.00015111541954058734, |
| "loss": 1.0688, |
| "step": 171 |
| }, |
| { |
| "epoch": 2.73, |
| "learning_rate": 0.0001505587660821759, |
| "loss": 1.1648, |
| "step": 172 |
| }, |
| { |
| "epoch": 2.75, |
| "learning_rate": 0.00015000000000000001, |
| "loss": 1.0783, |
| "step": 173 |
| }, |
| { |
| "epoch": 2.76, |
| "learning_rate": 0.00014943914464238468, |
| "loss": 1.1639, |
| "step": 174 |
| }, |
| { |
| "epoch": 2.78, |
| "learning_rate": 0.00014887622344495643, |
| "loss": 1.3175, |
| "step": 175 |
| }, |
| { |
| "epoch": 2.78, |
| "eval_loss": 1.3120231628417969, |
| "eval_runtime": 62.1097, |
| "eval_samples_per_second": 4.025, |
| "eval_steps_per_second": 4.025, |
| "step": 175 |
| }, |
| { |
| "epoch": 2.8, |
| "learning_rate": 0.00014831125992966385, |
| "loss": 1.059, |
| "step": 176 |
| }, |
| { |
| "epoch": 2.81, |
| "learning_rate": 0.0001477442777037949, |
| "loss": 1.0881, |
| "step": 177 |
| }, |
| { |
| "epoch": 2.83, |
| "learning_rate": 0.00014717530045899038, |
| "loss": 1.1179, |
| "step": 178 |
| }, |
| { |
| "epoch": 2.84, |
| "learning_rate": 0.0001466043519702539, |
| "loss": 1.1869, |
| "step": 179 |
| }, |
| { |
| "epoch": 2.86, |
| "learning_rate": 0.0001460314560949586, |
| "loss": 1.142, |
| "step": 180 |
| }, |
| { |
| "epoch": 2.88, |
| "learning_rate": 0.00014545663677185006, |
| "loss": 1.0172, |
| "step": 181 |
| }, |
| { |
| "epoch": 2.89, |
| "learning_rate": 0.00014487991802004623, |
| "loss": 1.0003, |
| "step": 182 |
| }, |
| { |
| "epoch": 2.91, |
| "learning_rate": 0.00014430132393803352, |
| "loss": 1.2018, |
| "step": 183 |
| }, |
| { |
| "epoch": 2.93, |
| "learning_rate": 0.0001437208787026601, |
| "loss": 1.0541, |
| "step": 184 |
| }, |
| { |
| "epoch": 2.94, |
| "learning_rate": 0.00014313860656812536, |
| "loss": 1.1134, |
| "step": 185 |
| }, |
| { |
| "epoch": 2.96, |
| "learning_rate": 0.00014255453186496673, |
| "loss": 1.2113, |
| "step": 186 |
| }, |
| { |
| "epoch": 2.97, |
| "learning_rate": 0.0001419686789990429, |
| "loss": 1.1616, |
| "step": 187 |
| }, |
| { |
| "epoch": 2.99, |
| "learning_rate": 0.00014138107245051392, |
| "loss": 1.1475, |
| "step": 188 |
| }, |
| { |
| "epoch": 3.01, |
| "learning_rate": 0.00014079173677281837, |
| "loss": 1.1168, |
| "step": 189 |
| }, |
| { |
| "epoch": 3.0, |
| "learning_rate": 0.0001402006965916474, |
| "loss": 0.9838, |
| "step": 190 |
| }, |
| { |
| "epoch": 3.02, |
| "learning_rate": 0.0001396079766039157, |
| "loss": 0.8454, |
| "step": 191 |
| }, |
| { |
| "epoch": 3.03, |
| "learning_rate": 0.0001390136015767295, |
| "loss": 1.1056, |
| "step": 192 |
| }, |
| { |
| "epoch": 3.05, |
| "learning_rate": 0.00013841759634635178, |
| "loss": 1.0452, |
| "step": 193 |
| }, |
| { |
| "epoch": 3.07, |
| "learning_rate": 0.00013781998581716427, |
| "loss": 0.9212, |
| "step": 194 |
| }, |
| { |
| "epoch": 3.08, |
| "learning_rate": 0.00013722079496062702, |
| "loss": 1.0476, |
| "step": 195 |
| }, |
| { |
| "epoch": 3.1, |
| "learning_rate": 0.0001366200488142348, |
| "loss": 0.9267, |
| "step": 196 |
| }, |
| { |
| "epoch": 3.11, |
| "learning_rate": 0.00013601777248047105, |
| "loss": 1.1301, |
| "step": 197 |
| }, |
| { |
| "epoch": 3.13, |
| "learning_rate": 0.00013541399112575878, |
| "loss": 0.9814, |
| "step": 198 |
| }, |
| { |
| "epoch": 3.15, |
| "learning_rate": 0.00013480872997940905, |
| "loss": 1.022, |
| "step": 199 |
| }, |
| { |
| "epoch": 3.16, |
| "learning_rate": 0.00013420201433256689, |
| "loss": 0.979, |
| "step": 200 |
| }, |
| { |
| "epoch": 3.16, |
| "eval_loss": 1.3181864023208618, |
| "eval_runtime": 62.2184, |
| "eval_samples_per_second": 4.018, |
| "eval_steps_per_second": 4.018, |
| "step": 200 |
| }, |
| { |
| "epoch": 3.18, |
| "learning_rate": 0.00013359386953715421, |
| "loss": 0.908, |
| "step": 201 |
| }, |
| { |
| "epoch": 3.2, |
| "learning_rate": 0.00013298432100481079, |
| "loss": 0.9209, |
| "step": 202 |
| }, |
| { |
| "epoch": 3.21, |
| "learning_rate": 0.00013237339420583212, |
| "loss": 1.0095, |
| "step": 203 |
| }, |
| { |
| "epoch": 3.23, |
| "learning_rate": 0.00013176111466810532, |
| "loss": 1.0415, |
| "step": 204 |
| }, |
| { |
| "epoch": 3.24, |
| "learning_rate": 0.00013114750797604247, |
| "loss": 1.0286, |
| "step": 205 |
| }, |
| { |
| "epoch": 3.26, |
| "learning_rate": 0.00013053259976951133, |
| "loss": 0.9969, |
| "step": 206 |
| }, |
| { |
| "epoch": 3.28, |
| "learning_rate": 0.00012991641574276418, |
| "loss": 1.0106, |
| "step": 207 |
| }, |
| { |
| "epoch": 3.29, |
| "learning_rate": 0.00012929898164336408, |
| "loss": 1.0094, |
| "step": 208 |
| }, |
| { |
| "epoch": 3.31, |
| "learning_rate": 0.00012868032327110904, |
| "loss": 1.0417, |
| "step": 209 |
| }, |
| { |
| "epoch": 3.32, |
| "learning_rate": 0.0001280604664769539, |
| "loss": 0.9764, |
| "step": 210 |
| }, |
| { |
| "epoch": 3.34, |
| "learning_rate": 0.00012743943716193016, |
| "loss": 1.0592, |
| "step": 211 |
| }, |
| { |
| "epoch": 3.36, |
| "learning_rate": 0.00012681726127606376, |
| "loss": 1.0541, |
| "step": 212 |
| }, |
| { |
| "epoch": 3.37, |
| "learning_rate": 0.0001261939648172906, |
| "loss": 0.9032, |
| "step": 213 |
| }, |
| { |
| "epoch": 3.39, |
| "learning_rate": 0.0001255695738303704, |
| "loss": 1.0044, |
| "step": 214 |
| }, |
| { |
| "epoch": 3.41, |
| "learning_rate": 0.00012494411440579814, |
| "loss": 1.0148, |
| "step": 215 |
| }, |
| { |
| "epoch": 3.42, |
| "learning_rate": 0.00012431761267871417, |
| "loss": 0.881, |
| "step": 216 |
| }, |
| { |
| "epoch": 3.44, |
| "learning_rate": 0.00012369009482781192, |
| "loss": 0.926, |
| "step": 217 |
| }, |
| { |
| "epoch": 3.45, |
| "learning_rate": 0.00012306158707424403, |
| "loss": 0.9837, |
| "step": 218 |
| }, |
| { |
| "epoch": 3.47, |
| "learning_rate": 0.00012243211568052677, |
| "loss": 1.0499, |
| "step": 219 |
| }, |
| { |
| "epoch": 3.49, |
| "learning_rate": 0.0001218017069494426, |
| "loss": 0.9517, |
| "step": 220 |
| }, |
| { |
| "epoch": 3.5, |
| "learning_rate": 0.0001211703872229411, |
| "loss": 0.9389, |
| "step": 221 |
| }, |
| { |
| "epoch": 3.52, |
| "learning_rate": 0.0001205381828810382, |
| "loss": 1.0278, |
| "step": 222 |
| }, |
| { |
| "epoch": 3.53, |
| "learning_rate": 0.00011990512034071406, |
| "loss": 0.9211, |
| "step": 223 |
| }, |
| { |
| "epoch": 3.55, |
| "learning_rate": 0.00011927122605480898, |
| "loss": 1.0141, |
| "step": 224 |
| }, |
| { |
| "epoch": 3.57, |
| "learning_rate": 0.00011863652651091823, |
| "loss": 1.0649, |
| "step": 225 |
| }, |
| { |
| "epoch": 3.57, |
| "eval_loss": 1.314542531967163, |
| "eval_runtime": 62.1983, |
| "eval_samples_per_second": 4.019, |
| "eval_steps_per_second": 4.019, |
| "step": 225 |
| }, |
| { |
| "epoch": 3.58, |
| "learning_rate": 0.00011800104823028515, |
| "loss": 0.9642, |
| "step": 226 |
| }, |
| { |
| "epoch": 3.6, |
| "learning_rate": 0.00011736481776669306, |
| "loss": 1.0534, |
| "step": 227 |
| }, |
| { |
| "epoch": 3.61, |
| "learning_rate": 0.00011672786170535552, |
| "loss": 1.0212, |
| "step": 228 |
| }, |
| { |
| "epoch": 3.63, |
| "learning_rate": 0.00011609020666180575, |
| "loss": 0.9801, |
| "step": 229 |
| }, |
| { |
| "epoch": 3.65, |
| "learning_rate": 0.00011545187928078406, |
| "loss": 0.9185, |
| "step": 230 |
| }, |
| { |
| "epoch": 3.66, |
| "learning_rate": 0.0001148129062351249, |
| "loss": 0.9292, |
| "step": 231 |
| }, |
| { |
| "epoch": 3.68, |
| "learning_rate": 0.00011417331422464205, |
| "loss": 0.9453, |
| "step": 232 |
| }, |
| { |
| "epoch": 3.7, |
| "learning_rate": 0.00011353312997501313, |
| "loss": 0.9784, |
| "step": 233 |
| }, |
| { |
| "epoch": 3.71, |
| "learning_rate": 0.00011289238023666266, |
| "loss": 1.0346, |
| "step": 234 |
| }, |
| { |
| "epoch": 3.73, |
| "learning_rate": 0.00011225109178364455, |
| "loss": 0.9485, |
| "step": 235 |
| }, |
| { |
| "epoch": 3.74, |
| "learning_rate": 0.00011160929141252303, |
| "loss": 0.9783, |
| "step": 236 |
| }, |
| { |
| "epoch": 3.76, |
| "learning_rate": 0.00011096700594125318, |
| "loss": 0.8651, |
| "step": 237 |
| }, |
| { |
| "epoch": 3.78, |
| "learning_rate": 0.00011032426220806018, |
| "loss": 0.982, |
| "step": 238 |
| }, |
| { |
| "epoch": 3.79, |
| "learning_rate": 0.00010968108707031792, |
| "loss": 1.0657, |
| "step": 239 |
| }, |
| { |
| "epoch": 3.81, |
| "learning_rate": 0.00010903750740342682, |
| "loss": 1.0281, |
| "step": 240 |
| }, |
| { |
| "epoch": 3.82, |
| "learning_rate": 0.00010839355009969068, |
| "loss": 0.9484, |
| "step": 241 |
| }, |
| { |
| "epoch": 3.84, |
| "learning_rate": 0.0001077492420671931, |
| "loss": 0.9936, |
| "step": 242 |
| }, |
| { |
| "epoch": 3.86, |
| "learning_rate": 0.00010710461022867302, |
| "loss": 0.9556, |
| "step": 243 |
| }, |
| { |
| "epoch": 3.87, |
| "learning_rate": 0.0001064596815203998, |
| "loss": 0.92, |
| "step": 244 |
| }, |
| { |
| "epoch": 3.89, |
| "learning_rate": 0.00010581448289104758, |
| "loss": 0.954, |
| "step": 245 |
| }, |
| { |
| "epoch": 3.91, |
| "learning_rate": 0.00010516904130056946, |
| "loss": 0.9427, |
| "step": 246 |
| }, |
| { |
| "epoch": 3.92, |
| "learning_rate": 0.00010452338371907064, |
| "loss": 0.9644, |
| "step": 247 |
| }, |
| { |
| "epoch": 3.94, |
| "learning_rate": 0.0001038775371256817, |
| "loss": 0.9458, |
| "step": 248 |
| }, |
| { |
| "epoch": 3.95, |
| "learning_rate": 0.00010323152850743107, |
| "loss": 1.003, |
| "step": 249 |
| }, |
| { |
| "epoch": 3.97, |
| "learning_rate": 0.00010258538485811765, |
| "loss": 1.0749, |
| "step": 250 |
| }, |
| { |
| "epoch": 3.97, |
| "eval_loss": 1.3046478033065796, |
| "eval_runtime": 62.1024, |
| "eval_samples_per_second": 4.026, |
| "eval_steps_per_second": 4.026, |
| "step": 250 |
| }, |
| { |
| "epoch": 3.99, |
| "learning_rate": 0.00010193913317718244, |
| "loss": 0.961, |
| "step": 251 |
| }, |
| { |
| "epoch": 4.0, |
| "learning_rate": 0.00010129280046858086, |
| "loss": 0.9708, |
| "step": 252 |
| }, |
| { |
| "epoch": 4.02, |
| "learning_rate": 0.00010064641373965393, |
| "loss": 0.8755, |
| "step": 253 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 496, |
| "num_train_epochs": 8, |
| "save_steps": 500, |
| "total_flos": 1.6474185518599373e+17, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
