| { | |
| "best_metric": 1.2820132970809937, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-150", | |
| "epoch": 1.7122507122507122, | |
| "eval_steps": 25, | |
| "global_step": 150, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.011396011396011397, | |
| "grad_norm": 1.2519962787628174, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 2.4206, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.011396011396011397, | |
| "eval_loss": 3.1777703762054443, | |
| "eval_runtime": 2.6753, | |
| "eval_samples_per_second": 18.689, | |
| "eval_steps_per_second": 2.617, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.022792022792022793, | |
| "grad_norm": 1.8308161497116089, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 2.5791, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.03418803418803419, | |
| "grad_norm": 2.0269980430603027, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 2.6558, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.045584045584045586, | |
| "grad_norm": 2.5735702514648438, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 2.8524, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.05698005698005698, | |
| "grad_norm": 2.610076904296875, | |
| "learning_rate": 0.00015, | |
| "loss": 2.6163, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.06837606837606838, | |
| "grad_norm": 2.135373830795288, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 2.5374, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.07977207977207977, | |
| "grad_norm": 1.9062364101409912, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 2.6469, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.09116809116809117, | |
| "grad_norm": 1.4977805614471436, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 2.2611, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.10256410256410256, | |
| "grad_norm": 1.4389641284942627, | |
| "learning_rate": 0.00027, | |
| "loss": 2.2009, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.11396011396011396, | |
| "grad_norm": 1.9085431098937988, | |
| "learning_rate": 0.0003, | |
| "loss": 2.2492, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.12535612535612536, | |
| "grad_norm": 1.7611523866653442, | |
| "learning_rate": 0.0002999731384004606, | |
| "loss": 2.2406, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.13675213675213677, | |
| "grad_norm": 1.9762187004089355, | |
| "learning_rate": 0.0002998925632224497, | |
| "loss": 2.21, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.14814814814814814, | |
| "grad_norm": 1.983385443687439, | |
| "learning_rate": 0.00029975830332434265, | |
| "loss": 1.9138, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.15954415954415954, | |
| "grad_norm": 2.5348525047302246, | |
| "learning_rate": 0.00029957040679194776, | |
| "loss": 2.0607, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.17094017094017094, | |
| "grad_norm": 1.8772743940353394, | |
| "learning_rate": 0.00029932894092128383, | |
| "loss": 1.7761, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.18233618233618235, | |
| "grad_norm": 1.8809691667556763, | |
| "learning_rate": 0.0002990339921944777, | |
| "loss": 1.7878, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.19373219373219372, | |
| "grad_norm": 2.102220296859741, | |
| "learning_rate": 0.00029868566624879054, | |
| "loss": 2.2667, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.20512820512820512, | |
| "grad_norm": 2.032646894454956, | |
| "learning_rate": 0.00029828408783878324, | |
| "loss": 1.6751, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.21652421652421652, | |
| "grad_norm": 2.541229486465454, | |
| "learning_rate": 0.00029782940079163485, | |
| "loss": 1.3936, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.22792022792022792, | |
| "grad_norm": 3.479897975921631, | |
| "learning_rate": 0.00029732176795563037, | |
| "loss": 1.7468, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.23931623931623933, | |
| "grad_norm": 4.591503143310547, | |
| "learning_rate": 0.0002967613711418359, | |
| "loss": 2.2668, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.25071225071225073, | |
| "grad_norm": 7.106602668762207, | |
| "learning_rate": 0.000296148411058982, | |
| "loss": 2.8446, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.2621082621082621, | |
| "grad_norm": 4.072912693023682, | |
| "learning_rate": 0.00029548310724157904, | |
| "loss": 2.4782, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.27350427350427353, | |
| "grad_norm": 3.0776100158691406, | |
| "learning_rate": 0.0002947656979712899, | |
| "loss": 2.3275, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.2849002849002849, | |
| "grad_norm": 1.9854662418365479, | |
| "learning_rate": 0.0002939964401915884, | |
| "loss": 2.2914, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2849002849002849, | |
| "eval_loss": 2.036309242248535, | |
| "eval_runtime": 1.6991, | |
| "eval_samples_per_second": 29.427, | |
| "eval_steps_per_second": 4.12, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2962962962962963, | |
| "grad_norm": 1.2816338539123535, | |
| "learning_rate": 0.0002931756094157332, | |
| "loss": 2.0158, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.3076923076923077, | |
| "grad_norm": 1.3689543008804321, | |
| "learning_rate": 0.0002923034996280924, | |
| "loss": 1.9286, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.3190883190883191, | |
| "grad_norm": 1.3031697273254395, | |
| "learning_rate": 0.0002913804231788509, | |
| "loss": 2.0447, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.33048433048433046, | |
| "grad_norm": 1.2884080410003662, | |
| "learning_rate": 0.00029040671067214087, | |
| "loss": 1.7308, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.3418803418803419, | |
| "grad_norm": 1.2418413162231445, | |
| "learning_rate": 0.0002893827108476348, | |
| "loss": 1.7873, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.35327635327635326, | |
| "grad_norm": 1.2331762313842773, | |
| "learning_rate": 0.000288308790455642, | |
| "loss": 1.8249, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.3646723646723647, | |
| "grad_norm": 1.3798717260360718, | |
| "learning_rate": 0.00028718533412575606, | |
| "loss": 1.6925, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.37606837606837606, | |
| "grad_norm": 1.2883918285369873, | |
| "learning_rate": 0.00028601274422909733, | |
| "loss": 1.6585, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.38746438746438744, | |
| "grad_norm": 1.4337915182113647, | |
| "learning_rate": 0.00028479144073420234, | |
| "loss": 1.6603, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.39886039886039887, | |
| "grad_norm": 1.4459898471832275, | |
| "learning_rate": 0.0002835218610566095, | |
| "loss": 1.811, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.41025641025641024, | |
| "grad_norm": 1.5042760372161865, | |
| "learning_rate": 0.0002822044599021973, | |
| "loss": 1.5776, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.42165242165242167, | |
| "grad_norm": 1.721915364265442, | |
| "learning_rate": 0.0002808397091043291, | |
| "loss": 1.5148, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.43304843304843305, | |
| "grad_norm": 1.7263678312301636, | |
| "learning_rate": 0.00027942809745486343, | |
| "loss": 1.6432, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "grad_norm": 1.4137566089630127, | |
| "learning_rate": 0.0002779701305290915, | |
| "loss": 1.1639, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.45584045584045585, | |
| "grad_norm": 1.5665677785873413, | |
| "learning_rate": 0.00027646633050466265, | |
| "loss": 1.2632, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.4672364672364672, | |
| "grad_norm": 2.0215096473693848, | |
| "learning_rate": 0.0002749172359745641, | |
| "loss": 1.3551, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.47863247863247865, | |
| "grad_norm": 4.784286975860596, | |
| "learning_rate": 0.0002733234017542215, | |
| "loss": 2.3304, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.49002849002849, | |
| "grad_norm": 4.08688497543335, | |
| "learning_rate": 0.0002716853986827888, | |
| "loss": 2.402, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.5014245014245015, | |
| "grad_norm": 2.5830602645874023, | |
| "learning_rate": 0.0002700038134187002, | |
| "loss": 2.3759, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.5128205128205128, | |
| "grad_norm": 2.1645848751068115, | |
| "learning_rate": 0.00026827924822955487, | |
| "loss": 2.1305, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.5242165242165242, | |
| "grad_norm": 1.5849443674087524, | |
| "learning_rate": 0.0002665123207764128, | |
| "loss": 1.9809, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.5356125356125356, | |
| "grad_norm": 1.2589260339736938, | |
| "learning_rate": 0.00026470366389257614, | |
| "loss": 1.706, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.5470085470085471, | |
| "grad_norm": 1.0531516075134277, | |
| "learning_rate": 0.0002628539253569372, | |
| "loss": 1.9793, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.5584045584045584, | |
| "grad_norm": 1.193375587463379, | |
| "learning_rate": 0.00026096376766197307, | |
| "loss": 1.9775, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.5698005698005698, | |
| "grad_norm": 1.1033531427383423, | |
| "learning_rate": 0.00025903386777647154, | |
| "loss": 1.8742, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5698005698005698, | |
| "eval_loss": 1.7998709678649902, | |
| "eval_runtime": 1.7036, | |
| "eval_samples_per_second": 29.349, | |
| "eval_steps_per_second": 4.109, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5811965811965812, | |
| "grad_norm": 1.0783123970031738, | |
| "learning_rate": 0.0002570649169030708, | |
| "loss": 1.9111, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.5925925925925926, | |
| "grad_norm": 1.0935959815979004, | |
| "learning_rate": 0.0002550576202307026, | |
| "loss": 1.5608, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.603988603988604, | |
| "grad_norm": 1.1056702136993408, | |
| "learning_rate": 0.00025301269668202516, | |
| "loss": 1.5484, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.6153846153846154, | |
| "grad_norm": 1.0685745477676392, | |
| "learning_rate": 0.0002509308786559378, | |
| "loss": 1.5551, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.6267806267806267, | |
| "grad_norm": 1.142223834991455, | |
| "learning_rate": 0.00024881291176526903, | |
| "loss": 1.4648, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.6381766381766382, | |
| "grad_norm": 1.046868085861206, | |
| "learning_rate": 0.00024665955456973154, | |
| "loss": 1.3516, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.6495726495726496, | |
| "grad_norm": 1.2537604570388794, | |
| "learning_rate": 0.00024447157830424066, | |
| "loss": 1.4294, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.6609686609686609, | |
| "grad_norm": 5.143469333648682, | |
| "learning_rate": 0.00024224976660269302, | |
| "loss": 1.7798, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.6723646723646723, | |
| "grad_norm": 1.800788402557373, | |
| "learning_rate": 0.0002399949152173043, | |
| "loss": 1.3687, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.6837606837606838, | |
| "grad_norm": 1.6435121297836304, | |
| "learning_rate": 0.00023770783173360704, | |
| "loss": 1.3272, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.6951566951566952, | |
| "grad_norm": 1.3753656148910522, | |
| "learning_rate": 0.00023538933528120988, | |
| "loss": 1.0725, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.7065527065527065, | |
| "grad_norm": 1.8469661474227905, | |
| "learning_rate": 0.00023304025624042263, | |
| "loss": 1.2381, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.717948717948718, | |
| "grad_norm": 3.300287961959839, | |
| "learning_rate": 0.00023066143594485178, | |
| "loss": 2.1334, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.7293447293447294, | |
| "grad_norm": 1.5052417516708374, | |
| "learning_rate": 0.00022825372638007267, | |
| "loss": 2.2592, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.7407407407407407, | |
| "grad_norm": 1.5409011840820312, | |
| "learning_rate": 0.0002258179898784871, | |
| "loss": 2.1054, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.7521367521367521, | |
| "grad_norm": 1.4818933010101318, | |
| "learning_rate": 0.00022335509881047497, | |
| "loss": 2.07, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.7635327635327636, | |
| "grad_norm": 1.4115264415740967, | |
| "learning_rate": 0.00022086593527195062, | |
| "loss": 2.0091, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.7749287749287749, | |
| "grad_norm": 1.1922721862792969, | |
| "learning_rate": 0.00021835139076843623, | |
| "loss": 1.8131, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.7863247863247863, | |
| "grad_norm": 0.9140765070915222, | |
| "learning_rate": 0.00021581236589576476, | |
| "loss": 1.5989, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.7977207977207977, | |
| "grad_norm": 1.0271003246307373, | |
| "learning_rate": 0.00021324977001752757, | |
| "loss": 1.5188, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.8091168091168092, | |
| "grad_norm": 0.9476837515830994, | |
| "learning_rate": 0.00021066452093938153, | |
| "loss": 1.5648, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.8205128205128205, | |
| "grad_norm": 1.0417282581329346, | |
| "learning_rate": 0.0002080575445803326, | |
| "loss": 1.5148, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.8319088319088319, | |
| "grad_norm": 1.0334333181381226, | |
| "learning_rate": 0.00020542977464111352, | |
| "loss": 1.6438, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.8433048433048433, | |
| "grad_norm": 0.9989399313926697, | |
| "learning_rate": 0.00020278215226977493, | |
| "loss": 1.5928, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.8547008547008547, | |
| "grad_norm": 1.0742107629776, | |
| "learning_rate": 0.0002001156257246085, | |
| "loss": 1.5306, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.8547008547008547, | |
| "eval_loss": 1.6375644207000732, | |
| "eval_runtime": 1.705, | |
| "eval_samples_per_second": 29.326, | |
| "eval_steps_per_second": 4.106, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.8660968660968661, | |
| "grad_norm": 1.0311996936798096, | |
| "learning_rate": 0.00019743115003452357, | |
| "loss": 1.3922, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.8774928774928775, | |
| "grad_norm": 1.198850154876709, | |
| "learning_rate": 0.0001947296866569998, | |
| "loss": 1.0949, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": 1.1997807025909424, | |
| "learning_rate": 0.00019201220313373607, | |
| "loss": 1.4401, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.9002849002849003, | |
| "grad_norm": 1.1423969268798828, | |
| "learning_rate": 0.00018927967274412098, | |
| "loss": 1.2018, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.9116809116809117, | |
| "grad_norm": 1.3956024646759033, | |
| "learning_rate": 0.00018653307415664877, | |
| "loss": 1.2284, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.9230769230769231, | |
| "grad_norm": 1.066584587097168, | |
| "learning_rate": 0.00018377339107840412, | |
| "loss": 0.9837, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.9344729344729344, | |
| "grad_norm": 1.3003766536712646, | |
| "learning_rate": 0.0001810016119027429, | |
| "loss": 1.2202, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.9458689458689459, | |
| "grad_norm": 1.7478852272033691, | |
| "learning_rate": 0.00017821872935529505, | |
| "loss": 1.038, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.9572649572649573, | |
| "grad_norm": 3.182337522506714, | |
| "learning_rate": 0.0001754257401384145, | |
| "loss": 1.6589, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.9686609686609686, | |
| "grad_norm": 1.2142601013183594, | |
| "learning_rate": 0.00017262364457420608, | |
| "loss": 1.8597, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.98005698005698, | |
| "grad_norm": 1.3871400356292725, | |
| "learning_rate": 0.00016981344624625536, | |
| "loss": 1.681, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.9914529914529915, | |
| "grad_norm": 1.7115479707717896, | |
| "learning_rate": 0.0001669961516401905, | |
| "loss": 1.1075, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 1.0056980056980056, | |
| "grad_norm": 2.2736129760742188, | |
| "learning_rate": 0.00016417276978320468, | |
| "loss": 2.0925, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 1.017094017094017, | |
| "grad_norm": 1.1460903882980347, | |
| "learning_rate": 0.00016134431188266851, | |
| "loss": 1.934, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 1.0284900284900285, | |
| "grad_norm": 1.0482747554779053, | |
| "learning_rate": 0.00015851179096396112, | |
| "loss": 1.8211, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.03988603988604, | |
| "grad_norm": 1.07375967502594, | |
| "learning_rate": 0.00015567622150765057, | |
| "loss": 1.8239, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 1.0512820512820513, | |
| "grad_norm": 0.9148443341255188, | |
| "learning_rate": 0.00015283861908615284, | |
| "loss": 1.4781, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 1.0626780626780628, | |
| "grad_norm": 0.8687672019004822, | |
| "learning_rate": 0.00015, | |
| "loss": 1.3654, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 1.074074074074074, | |
| "grad_norm": 0.7713249921798706, | |
| "learning_rate": 0.00014716138091384716, | |
| "loss": 1.3693, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 1.0854700854700854, | |
| "grad_norm": 0.8376121520996094, | |
| "learning_rate": 0.00014432377849234946, | |
| "loss": 1.4623, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 1.0968660968660968, | |
| "grad_norm": 0.8906532526016235, | |
| "learning_rate": 0.00014148820903603888, | |
| "loss": 1.254, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 1.1082621082621082, | |
| "grad_norm": 0.8663071393966675, | |
| "learning_rate": 0.00013865568811733151, | |
| "loss": 1.307, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 1.1196581196581197, | |
| "grad_norm": 0.9542202353477478, | |
| "learning_rate": 0.00013582723021679532, | |
| "loss": 1.2608, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 1.131054131054131, | |
| "grad_norm": 0.9995313286781311, | |
| "learning_rate": 0.0001330038483598095, | |
| "loss": 1.1165, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 1.1424501424501425, | |
| "grad_norm": 1.1044690608978271, | |
| "learning_rate": 0.00013018655375374467, | |
| "loss": 1.1848, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.1424501424501425, | |
| "eval_loss": 1.4970488548278809, | |
| "eval_runtime": 1.8899, | |
| "eval_samples_per_second": 26.457, | |
| "eval_steps_per_second": 3.704, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.1538461538461537, | |
| "grad_norm": 0.9920974969863892, | |
| "learning_rate": 0.00012737635542579392, | |
| "loss": 0.9784, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 1.1652421652421652, | |
| "grad_norm": 1.1210228204727173, | |
| "learning_rate": 0.00012457425986158547, | |
| "loss": 1.1527, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 1.1766381766381766, | |
| "grad_norm": 1.00983464717865, | |
| "learning_rate": 0.00012178127064470495, | |
| "loss": 0.8994, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 1.188034188034188, | |
| "grad_norm": 1.1708537340164185, | |
| "learning_rate": 0.00011899838809725704, | |
| "loss": 0.9404, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 1.1994301994301995, | |
| "grad_norm": 1.1367274522781372, | |
| "learning_rate": 0.00011622660892159588, | |
| "loss": 1.0448, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.210826210826211, | |
| "grad_norm": 1.0647042989730835, | |
| "learning_rate": 0.0001134669258433512, | |
| "loss": 0.7988, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 1.2222222222222223, | |
| "grad_norm": 1.3828827142715454, | |
| "learning_rate": 0.00011072032725587898, | |
| "loss": 0.7434, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 1.2336182336182335, | |
| "grad_norm": 2.304461717605591, | |
| "learning_rate": 0.00010798779686626394, | |
| "loss": 1.2766, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 1.245014245014245, | |
| "grad_norm": 1.8592255115509033, | |
| "learning_rate": 0.0001052703133430002, | |
| "loss": 1.7272, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 1.2564102564102564, | |
| "grad_norm": 1.184973955154419, | |
| "learning_rate": 0.00010256884996547639, | |
| "loss": 1.7214, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.2678062678062678, | |
| "grad_norm": 1.3312870264053345, | |
| "learning_rate": 9.988437427539152e-05, | |
| "loss": 1.7808, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 1.2792022792022792, | |
| "grad_norm": 1.2522313594818115, | |
| "learning_rate": 9.721784773022504e-05, | |
| "loss": 1.8064, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 1.2905982905982907, | |
| "grad_norm": 1.2439285516738892, | |
| "learning_rate": 9.457022535888646e-05, | |
| "loss": 1.4275, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 1.301994301994302, | |
| "grad_norm": 1.2562860250473022, | |
| "learning_rate": 9.194245541966741e-05, | |
| "loss": 1.4041, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 1.3133903133903133, | |
| "grad_norm": 1.1387799978256226, | |
| "learning_rate": 8.933547906061846e-05, | |
| "loss": 1.4148, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 1.3247863247863247, | |
| "grad_norm": 1.4267293214797974, | |
| "learning_rate": 8.675022998247239e-05, | |
| "loss": 1.4423, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 1.3361823361823362, | |
| "grad_norm": 1.2730156183242798, | |
| "learning_rate": 8.418763410423521e-05, | |
| "loss": 1.2059, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 1.3475783475783476, | |
| "grad_norm": 1.4545279741287231, | |
| "learning_rate": 8.164860923156377e-05, | |
| "loss": 1.1672, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 1.358974358974359, | |
| "grad_norm": 1.172255277633667, | |
| "learning_rate": 7.913406472804938e-05, | |
| "loss": 1.1305, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 1.3703703703703702, | |
| "grad_norm": 1.262474536895752, | |
| "learning_rate": 7.664490118952502e-05, | |
| "loss": 1.2088, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.381766381766382, | |
| "grad_norm": 1.1172735691070557, | |
| "learning_rate": 7.418201012151291e-05, | |
| "loss": 0.9737, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 1.393162393162393, | |
| "grad_norm": 1.0664935111999512, | |
| "learning_rate": 7.174627361992732e-05, | |
| "loss": 0.9084, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 1.4045584045584045, | |
| "grad_norm": 1.119123101234436, | |
| "learning_rate": 6.933856405514818e-05, | |
| "loss": 0.8675, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 1.415954415954416, | |
| "grad_norm": 1.409183144569397, | |
| "learning_rate": 6.695974375957732e-05, | |
| "loss": 0.8404, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 1.4273504273504274, | |
| "grad_norm": 1.5085996389389038, | |
| "learning_rate": 6.461066471879014e-05, | |
| "loss": 0.9369, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.4273504273504274, | |
| "eval_loss": 1.3513659238815308, | |
| "eval_runtime": 1.8926, | |
| "eval_samples_per_second": 26.419, | |
| "eval_steps_per_second": 3.699, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.4387464387464388, | |
| "grad_norm": 1.2920509576797485, | |
| "learning_rate": 6.229216826639293e-05, | |
| "loss": 0.8643, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 1.45014245014245, | |
| "grad_norm": 1.2910054922103882, | |
| "learning_rate": 6.000508478269568e-05, | |
| "loss": 0.8122, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 1.4615384615384617, | |
| "grad_norm": 1.4201382398605347, | |
| "learning_rate": 5.775023339730696e-05, | |
| "loss": 0.7651, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 1.4729344729344729, | |
| "grad_norm": 2.1395621299743652, | |
| "learning_rate": 5.552842169575929e-05, | |
| "loss": 0.8448, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 1.4843304843304843, | |
| "grad_norm": 1.5610102415084839, | |
| "learning_rate": 5.3340445430268436e-05, | |
| "loss": 1.424, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.4957264957264957, | |
| "grad_norm": 1.110679030418396, | |
| "learning_rate": 5.118708823473095e-05, | |
| "loss": 1.5867, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 1.5071225071225072, | |
| "grad_norm": 1.1526521444320679, | |
| "learning_rate": 4.906912134406216e-05, | |
| "loss": 1.479, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 1.5185185185185186, | |
| "grad_norm": 1.1644917726516724, | |
| "learning_rate": 4.6987303317974865e-05, | |
| "loss": 1.3948, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 1.5299145299145298, | |
| "grad_norm": 1.2431634664535522, | |
| "learning_rate": 4.4942379769297414e-05, | |
| "loss": 1.3406, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 1.5413105413105415, | |
| "grad_norm": 1.169194221496582, | |
| "learning_rate": 4.293508309692913e-05, | |
| "loss": 1.39, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 1.5527065527065527, | |
| "grad_norm": 1.3732033967971802, | |
| "learning_rate": 4.096613222352843e-05, | |
| "loss": 1.2796, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 1.564102564102564, | |
| "grad_norm": 1.1785165071487427, | |
| "learning_rate": 3.90362323380269e-05, | |
| "loss": 1.1062, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 1.5754985754985755, | |
| "grad_norm": 1.0893325805664062, | |
| "learning_rate": 3.714607464306281e-05, | |
| "loss": 1.099, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 1.5868945868945867, | |
| "grad_norm": 1.7790886163711548, | |
| "learning_rate": 3.529633610742382e-05, | |
| "loss": 0.991, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 1.5982905982905984, | |
| "grad_norm": 1.257436752319336, | |
| "learning_rate": 3.348767922358719e-05, | |
| "loss": 1.086, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.6096866096866096, | |
| "grad_norm": 1.1407253742218018, | |
| "learning_rate": 3.172075177044513e-05, | |
| "loss": 1.0214, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 1.6210826210826212, | |
| "grad_norm": 1.206728219985962, | |
| "learning_rate": 2.9996186581299824e-05, | |
| "loss": 0.9055, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 1.6324786324786325, | |
| "grad_norm": 1.040445327758789, | |
| "learning_rate": 2.831460131721116e-05, | |
| "loss": 0.823, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 1.6438746438746439, | |
| "grad_norm": 1.128639578819275, | |
| "learning_rate": 2.6676598245778498e-05, | |
| "loss": 0.92, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 1.6552706552706553, | |
| "grad_norm": 1.3026468753814697, | |
| "learning_rate": 2.5082764025435865e-05, | |
| "loss": 1.0339, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 1.6666666666666665, | |
| "grad_norm": 1.4225764274597168, | |
| "learning_rate": 2.353366949533736e-05, | |
| "loss": 1.0566, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 1.6780626780626782, | |
| "grad_norm": 1.5012832880020142, | |
| "learning_rate": 2.20298694709085e-05, | |
| "loss": 0.8958, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 1.6894586894586894, | |
| "grad_norm": 1.3319451808929443, | |
| "learning_rate": 2.0571902545136565e-05, | |
| "loss": 0.7705, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 1.7008547008547008, | |
| "grad_norm": 1.4093050956726074, | |
| "learning_rate": 1.9160290895670937e-05, | |
| "loss": 0.6252, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 1.7122507122507122, | |
| "grad_norm": 2.2196362018585205, | |
| "learning_rate": 1.7795540097802668e-05, | |
| "loss": 1.0593, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.7122507122507122, | |
| "eval_loss": 1.2820132970809937, | |
| "eval_runtime": 1.7049, | |
| "eval_samples_per_second": 29.327, | |
| "eval_steps_per_second": 4.106, | |
| "step": 150 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 176, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.669377994561946e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |