| { | |
| "best_metric": 1.2840447425842285, | |
| "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": 1.275281310081482, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 2.4206, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.011396011396011397, | |
| "eval_loss": 3.1777703762054443, | |
| "eval_runtime": 2.6727, | |
| "eval_samples_per_second": 18.707, | |
| "eval_steps_per_second": 2.619, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.022792022792022793, | |
| "grad_norm": 1.8708691596984863, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 2.5791, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.03418803418803419, | |
| "grad_norm": 2.057396411895752, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 2.6549, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.045584045584045586, | |
| "grad_norm": 2.621896505355835, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 2.8508, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.05698005698005698, | |
| "grad_norm": 2.667181968688965, | |
| "learning_rate": 0.00015, | |
| "loss": 2.6154, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.06837606837606838, | |
| "grad_norm": 2.1751344203948975, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 2.5356, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.07977207977207977, | |
| "grad_norm": 1.9212430715560913, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 2.646, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.09116809116809117, | |
| "grad_norm": 1.482764720916748, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 2.2598, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.10256410256410256, | |
| "grad_norm": 1.449442744255066, | |
| "learning_rate": 0.00027, | |
| "loss": 2.1986, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.11396011396011396, | |
| "grad_norm": 1.9114185571670532, | |
| "learning_rate": 0.0003, | |
| "loss": 2.2509, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.12535612535612536, | |
| "grad_norm": 1.7590088844299316, | |
| "learning_rate": 0.0002999731384004606, | |
| "loss": 2.2411, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.13675213675213677, | |
| "grad_norm": 1.9783275127410889, | |
| "learning_rate": 0.0002998925632224497, | |
| "loss": 2.2038, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.14814814814814814, | |
| "grad_norm": 2.0008552074432373, | |
| "learning_rate": 0.00029975830332434265, | |
| "loss": 1.913, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.15954415954415954, | |
| "grad_norm": 2.6259801387786865, | |
| "learning_rate": 0.00029957040679194776, | |
| "loss": 2.0676, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.17094017094017094, | |
| "grad_norm": 1.8901782035827637, | |
| "learning_rate": 0.00029932894092128383, | |
| "loss": 1.7778, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.18233618233618235, | |
| "grad_norm": 1.8770512342453003, | |
| "learning_rate": 0.0002990339921944777, | |
| "loss": 1.7791, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.19373219373219372, | |
| "grad_norm": 2.1568357944488525, | |
| "learning_rate": 0.00029868566624879054, | |
| "loss": 2.251, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.20512820512820512, | |
| "grad_norm": 2.0423424243927, | |
| "learning_rate": 0.00029828408783878324, | |
| "loss": 1.6777, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.21652421652421652, | |
| "grad_norm": 2.2600088119506836, | |
| "learning_rate": 0.00029782940079163485, | |
| "loss": 1.3782, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.22792022792022792, | |
| "grad_norm": 6.212785243988037, | |
| "learning_rate": 0.00029732176795563037, | |
| "loss": 1.7217, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.23931623931623933, | |
| "grad_norm": 4.51749324798584, | |
| "learning_rate": 0.0002967613711418359, | |
| "loss": 2.2409, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.25071225071225073, | |
| "grad_norm": 8.102594375610352, | |
| "learning_rate": 0.000296148411058982, | |
| "loss": 2.9289, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.2621082621082621, | |
| "grad_norm": 4.413826942443848, | |
| "learning_rate": 0.00029548310724157904, | |
| "loss": 2.52, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.27350427350427353, | |
| "grad_norm": 3.2592685222625732, | |
| "learning_rate": 0.0002947656979712899, | |
| "loss": 2.3453, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.2849002849002849, | |
| "grad_norm": 2.090911626815796, | |
| "learning_rate": 0.0002939964401915884, | |
| "loss": 2.3068, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2849002849002849, | |
| "eval_loss": 2.0359325408935547, | |
| "eval_runtime": 1.6925, | |
| "eval_samples_per_second": 29.542, | |
| "eval_steps_per_second": 4.136, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2962962962962963, | |
| "grad_norm": 1.3033101558685303, | |
| "learning_rate": 0.0002931756094157332, | |
| "loss": 2.0119, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.3076923076923077, | |
| "grad_norm": 1.3732004165649414, | |
| "learning_rate": 0.0002923034996280924, | |
| "loss": 1.9276, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.3190883190883191, | |
| "grad_norm": 1.2793781757354736, | |
| "learning_rate": 0.0002913804231788509, | |
| "loss": 2.0441, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.33048433048433046, | |
| "grad_norm": 1.2502461671829224, | |
| "learning_rate": 0.00029040671067214087, | |
| "loss": 1.7199, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.3418803418803419, | |
| "grad_norm": 1.2199724912643433, | |
| "learning_rate": 0.0002893827108476348, | |
| "loss": 1.7756, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.35327635327635326, | |
| "grad_norm": 1.1835788488388062, | |
| "learning_rate": 0.000288308790455642, | |
| "loss": 1.8096, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.3646723646723647, | |
| "grad_norm": 1.323184609413147, | |
| "learning_rate": 0.00028718533412575606, | |
| "loss": 1.6928, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.37606837606837606, | |
| "grad_norm": 1.272740364074707, | |
| "learning_rate": 0.00028601274422909733, | |
| "loss": 1.6588, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.38746438746438744, | |
| "grad_norm": 1.4608358144760132, | |
| "learning_rate": 0.00028479144073420234, | |
| "loss": 1.6605, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.39886039886039887, | |
| "grad_norm": 1.4448308944702148, | |
| "learning_rate": 0.0002835218610566095, | |
| "loss": 1.823, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.41025641025641024, | |
| "grad_norm": 1.501624584197998, | |
| "learning_rate": 0.0002822044599021973, | |
| "loss": 1.5703, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.42165242165242167, | |
| "grad_norm": 1.6337703466415405, | |
| "learning_rate": 0.0002808397091043291, | |
| "loss": 1.507, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.43304843304843305, | |
| "grad_norm": 1.7467942237854004, | |
| "learning_rate": 0.00027942809745486343, | |
| "loss": 1.6569, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "grad_norm": 1.4048912525177002, | |
| "learning_rate": 0.0002779701305290915, | |
| "loss": 1.1612, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.45584045584045585, | |
| "grad_norm": 1.558631420135498, | |
| "learning_rate": 0.00027646633050466265, | |
| "loss": 1.2638, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.4672364672364672, | |
| "grad_norm": 2.038233995437622, | |
| "learning_rate": 0.0002749172359745641, | |
| "loss": 1.366, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.47863247863247865, | |
| "grad_norm": 4.787012100219727, | |
| "learning_rate": 0.0002733234017542215, | |
| "loss": 2.2797, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.49002849002849, | |
| "grad_norm": 4.053765296936035, | |
| "learning_rate": 0.0002716853986827888, | |
| "loss": 2.4131, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.5014245014245015, | |
| "grad_norm": 2.653860569000244, | |
| "learning_rate": 0.0002700038134187002, | |
| "loss": 2.3959, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.5128205128205128, | |
| "grad_norm": 2.266941785812378, | |
| "learning_rate": 0.00026827924822955487, | |
| "loss": 2.1461, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.5242165242165242, | |
| "grad_norm": 1.615462303161621, | |
| "learning_rate": 0.0002665123207764128, | |
| "loss": 1.9849, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.5356125356125356, | |
| "grad_norm": 1.3153661489486694, | |
| "learning_rate": 0.00026470366389257614, | |
| "loss": 1.7058, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.5470085470085471, | |
| "grad_norm": 1.0891388654708862, | |
| "learning_rate": 0.0002628539253569372, | |
| "loss": 1.9861, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.5584045584045584, | |
| "grad_norm": 1.2085473537445068, | |
| "learning_rate": 0.00026096376766197307, | |
| "loss": 1.9597, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.5698005698005698, | |
| "grad_norm": 1.1210774183273315, | |
| "learning_rate": 0.00025903386777647154, | |
| "loss": 1.8633, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5698005698005698, | |
| "eval_loss": 1.7979708909988403, | |
| "eval_runtime": 1.6988, | |
| "eval_samples_per_second": 29.433, | |
| "eval_steps_per_second": 4.121, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5811965811965812, | |
| "grad_norm": 1.1083546876907349, | |
| "learning_rate": 0.0002570649169030708, | |
| "loss": 1.9054, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.5925925925925926, | |
| "grad_norm": 1.1118803024291992, | |
| "learning_rate": 0.0002550576202307026, | |
| "loss": 1.5566, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.603988603988604, | |
| "grad_norm": 1.1292729377746582, | |
| "learning_rate": 0.00025301269668202516, | |
| "loss": 1.5418, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.6153846153846154, | |
| "grad_norm": 1.0905343294143677, | |
| "learning_rate": 0.0002509308786559378, | |
| "loss": 1.567, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.6267806267806267, | |
| "grad_norm": 1.1679775714874268, | |
| "learning_rate": 0.00024881291176526903, | |
| "loss": 1.478, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.6381766381766382, | |
| "grad_norm": 1.0859359502792358, | |
| "learning_rate": 0.00024665955456973154, | |
| "loss": 1.3628, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.6495726495726496, | |
| "grad_norm": 1.2914154529571533, | |
| "learning_rate": 0.00024447157830424066, | |
| "loss": 1.4341, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.6609686609686609, | |
| "grad_norm": 4.928417205810547, | |
| "learning_rate": 0.00024224976660269302, | |
| "loss": 1.7669, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.6723646723646723, | |
| "grad_norm": 1.7731802463531494, | |
| "learning_rate": 0.0002399949152173043, | |
| "loss": 1.3646, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.6837606837606838, | |
| "grad_norm": 1.7798770666122437, | |
| "learning_rate": 0.00023770783173360704, | |
| "loss": 1.32, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.6951566951566952, | |
| "grad_norm": 1.3400565385818481, | |
| "learning_rate": 0.00023538933528120988, | |
| "loss": 1.0693, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.7065527065527065, | |
| "grad_norm": 1.7840746641159058, | |
| "learning_rate": 0.00023304025624042263, | |
| "loss": 1.2359, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.717948717948718, | |
| "grad_norm": 3.244560956954956, | |
| "learning_rate": 0.00023066143594485178, | |
| "loss": 2.1066, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.7293447293447294, | |
| "grad_norm": 1.5248583555221558, | |
| "learning_rate": 0.00022825372638007267, | |
| "loss": 2.2681, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.7407407407407407, | |
| "grad_norm": 1.579367995262146, | |
| "learning_rate": 0.0002258179898784871, | |
| "loss": 2.1084, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.7521367521367521, | |
| "grad_norm": 1.5203423500061035, | |
| "learning_rate": 0.00022335509881047497, | |
| "loss": 2.0729, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.7635327635327636, | |
| "grad_norm": 1.4482111930847168, | |
| "learning_rate": 0.00022086593527195062, | |
| "loss": 2.0057, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.7749287749287749, | |
| "grad_norm": 1.1762452125549316, | |
| "learning_rate": 0.00021835139076843623, | |
| "loss": 1.811, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.7863247863247863, | |
| "grad_norm": 0.9151526093482971, | |
| "learning_rate": 0.00021581236589576476, | |
| "loss": 1.5962, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.7977207977207977, | |
| "grad_norm": 1.0164101123809814, | |
| "learning_rate": 0.00021324977001752757, | |
| "loss": 1.5083, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.8091168091168092, | |
| "grad_norm": 0.9672901630401611, | |
| "learning_rate": 0.00021066452093938153, | |
| "loss": 1.5546, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.8205128205128205, | |
| "grad_norm": 1.0712361335754395, | |
| "learning_rate": 0.0002080575445803326, | |
| "loss": 1.5119, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.8319088319088319, | |
| "grad_norm": 1.0604687929153442, | |
| "learning_rate": 0.00020542977464111352, | |
| "loss": 1.6416, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.8433048433048433, | |
| "grad_norm": 1.0448590517044067, | |
| "learning_rate": 0.00020278215226977493, | |
| "loss": 1.5965, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.8547008547008547, | |
| "grad_norm": 1.0953928232192993, | |
| "learning_rate": 0.0002001156257246085, | |
| "loss": 1.5314, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.8547008547008547, | |
| "eval_loss": 1.6335612535476685, | |
| "eval_runtime": 1.6991, | |
| "eval_samples_per_second": 29.427, | |
| "eval_steps_per_second": 4.12, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.8660968660968661, | |
| "grad_norm": 1.022580862045288, | |
| "learning_rate": 0.00019743115003452357, | |
| "loss": 1.394, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.8774928774928775, | |
| "grad_norm": 1.150123119354248, | |
| "learning_rate": 0.0001947296866569998, | |
| "loss": 1.0808, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": 1.2115788459777832, | |
| "learning_rate": 0.00019201220313373607, | |
| "loss": 1.4386, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.9002849002849003, | |
| "grad_norm": 1.132363200187683, | |
| "learning_rate": 0.00018927967274412098, | |
| "loss": 1.1949, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.9116809116809117, | |
| "grad_norm": 1.3680353164672852, | |
| "learning_rate": 0.00018653307415664877, | |
| "loss": 1.2202, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.9230769230769231, | |
| "grad_norm": 1.075006127357483, | |
| "learning_rate": 0.00018377339107840412, | |
| "loss": 0.9873, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.9344729344729344, | |
| "grad_norm": 1.3361048698425293, | |
| "learning_rate": 0.0001810016119027429, | |
| "loss": 1.2343, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.9458689458689459, | |
| "grad_norm": 1.9565190076828003, | |
| "learning_rate": 0.00017821872935529505, | |
| "loss": 1.0822, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.9572649572649573, | |
| "grad_norm": 3.1362149715423584, | |
| "learning_rate": 0.0001754257401384145, | |
| "loss": 1.6614, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.9686609686609686, | |
| "grad_norm": 1.214998722076416, | |
| "learning_rate": 0.00017262364457420608, | |
| "loss": 1.8554, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.98005698005698, | |
| "grad_norm": 1.4069725275039673, | |
| "learning_rate": 0.00016981344624625536, | |
| "loss": 1.6906, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.9914529914529915, | |
| "grad_norm": 1.7144482135772705, | |
| "learning_rate": 0.0001669961516401905, | |
| "loss": 1.095, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 1.0056980056980056, | |
| "grad_norm": 2.2465782165527344, | |
| "learning_rate": 0.00016417276978320468, | |
| "loss": 2.0945, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 1.017094017094017, | |
| "grad_norm": 1.1649279594421387, | |
| "learning_rate": 0.00016134431188266851, | |
| "loss": 1.9323, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 1.0284900284900285, | |
| "grad_norm": 1.0408798456192017, | |
| "learning_rate": 0.00015851179096396112, | |
| "loss": 1.8263, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.03988603988604, | |
| "grad_norm": 1.0593069791793823, | |
| "learning_rate": 0.00015567622150765057, | |
| "loss": 1.8236, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 1.0512820512820513, | |
| "grad_norm": 0.940461277961731, | |
| "learning_rate": 0.00015283861908615284, | |
| "loss": 1.4745, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 1.0626780626780628, | |
| "grad_norm": 0.8671309351921082, | |
| "learning_rate": 0.00015, | |
| "loss": 1.3637, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 1.074074074074074, | |
| "grad_norm": 0.7851026058197021, | |
| "learning_rate": 0.00014716138091384716, | |
| "loss": 1.3622, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 1.0854700854700854, | |
| "grad_norm": 0.8758441805839539, | |
| "learning_rate": 0.00014432377849234946, | |
| "loss": 1.4627, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 1.0968660968660968, | |
| "grad_norm": 0.9090460538864136, | |
| "learning_rate": 0.00014148820903603888, | |
| "loss": 1.245, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 1.1082621082621082, | |
| "grad_norm": 0.8923598527908325, | |
| "learning_rate": 0.00013865568811733151, | |
| "loss": 1.3085, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 1.1196581196581197, | |
| "grad_norm": 0.9927690625190735, | |
| "learning_rate": 0.00013582723021679532, | |
| "loss": 1.2563, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 1.131054131054131, | |
| "grad_norm": 1.0350650548934937, | |
| "learning_rate": 0.0001330038483598095, | |
| "loss": 1.1181, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 1.1424501424501425, | |
| "grad_norm": 1.156041145324707, | |
| "learning_rate": 0.00013018655375374467, | |
| "loss": 1.1825, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.1424501424501425, | |
| "eval_loss": 1.4987461566925049, | |
| "eval_runtime": 1.8846, | |
| "eval_samples_per_second": 26.531, | |
| "eval_steps_per_second": 3.714, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.1538461538461537, | |
| "grad_norm": 1.0206518173217773, | |
| "learning_rate": 0.00012737635542579392, | |
| "loss": 0.9768, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 1.1652421652421652, | |
| "grad_norm": 1.1547712087631226, | |
| "learning_rate": 0.00012457425986158547, | |
| "loss": 1.1569, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 1.1766381766381766, | |
| "grad_norm": 1.0336005687713623, | |
| "learning_rate": 0.00012178127064470495, | |
| "loss": 0.8925, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 1.188034188034188, | |
| "grad_norm": 1.1869686841964722, | |
| "learning_rate": 0.00011899838809725704, | |
| "loss": 0.93, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 1.1994301994301995, | |
| "grad_norm": 1.1297049522399902, | |
| "learning_rate": 0.00011622660892159588, | |
| "loss": 1.0362, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.210826210826211, | |
| "grad_norm": 1.0915703773498535, | |
| "learning_rate": 0.0001134669258433512, | |
| "loss": 0.7976, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 1.2222222222222223, | |
| "grad_norm": 1.4184788465499878, | |
| "learning_rate": 0.00011072032725587898, | |
| "loss": 0.7353, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 1.2336182336182335, | |
| "grad_norm": 2.3497474193573, | |
| "learning_rate": 0.00010798779686626394, | |
| "loss": 1.2595, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 1.245014245014245, | |
| "grad_norm": 1.9292255640029907, | |
| "learning_rate": 0.0001052703133430002, | |
| "loss": 1.7123, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 1.2564102564102564, | |
| "grad_norm": 1.3234666585922241, | |
| "learning_rate": 0.00010256884996547639, | |
| "loss": 1.7349, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.2678062678062678, | |
| "grad_norm": 1.662917971611023, | |
| "learning_rate": 9.988437427539152e-05, | |
| "loss": 1.8099, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 1.2792022792022792, | |
| "grad_norm": 1.305438756942749, | |
| "learning_rate": 9.721784773022504e-05, | |
| "loss": 1.8213, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 1.2905982905982907, | |
| "grad_norm": 1.2899692058563232, | |
| "learning_rate": 9.457022535888646e-05, | |
| "loss": 1.4366, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 1.301994301994302, | |
| "grad_norm": 1.3203108310699463, | |
| "learning_rate": 9.194245541966741e-05, | |
| "loss": 1.4058, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 1.3133903133903133, | |
| "grad_norm": 1.149690866470337, | |
| "learning_rate": 8.933547906061846e-05, | |
| "loss": 1.414, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 1.3247863247863247, | |
| "grad_norm": 1.411906361579895, | |
| "learning_rate": 8.675022998247239e-05, | |
| "loss": 1.4281, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 1.3361823361823362, | |
| "grad_norm": 1.2529743909835815, | |
| "learning_rate": 8.418763410423521e-05, | |
| "loss": 1.1939, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 1.3475783475783476, | |
| "grad_norm": 1.4424126148223877, | |
| "learning_rate": 8.164860923156377e-05, | |
| "loss": 1.1628, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 1.358974358974359, | |
| "grad_norm": 1.1717917919158936, | |
| "learning_rate": 7.913406472804938e-05, | |
| "loss": 1.1267, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 1.3703703703703702, | |
| "grad_norm": 1.2266149520874023, | |
| "learning_rate": 7.664490118952502e-05, | |
| "loss": 1.212, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.381766381766382, | |
| "grad_norm": 1.0905110836029053, | |
| "learning_rate": 7.418201012151291e-05, | |
| "loss": 0.9703, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 1.393162393162393, | |
| "grad_norm": 1.047167181968689, | |
| "learning_rate": 7.174627361992732e-05, | |
| "loss": 0.9018, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 1.4045584045584045, | |
| "grad_norm": 1.1345233917236328, | |
| "learning_rate": 6.933856405514818e-05, | |
| "loss": 0.8669, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 1.415954415954416, | |
| "grad_norm": 1.3731728792190552, | |
| "learning_rate": 6.695974375957732e-05, | |
| "loss": 0.8385, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 1.4273504273504274, | |
| "grad_norm": 1.543519139289856, | |
| "learning_rate": 6.461066471879014e-05, | |
| "loss": 0.9336, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.4273504273504274, | |
| "eval_loss": 1.3553086519241333, | |
| "eval_runtime": 1.8877, | |
| "eval_samples_per_second": 26.487, | |
| "eval_steps_per_second": 3.708, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.4387464387464388, | |
| "grad_norm": 1.2958241701126099, | |
| "learning_rate": 6.229216826639293e-05, | |
| "loss": 0.8566, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 1.45014245014245, | |
| "grad_norm": 1.3367834091186523, | |
| "learning_rate": 6.000508478269568e-05, | |
| "loss": 0.8118, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 1.4615384615384617, | |
| "grad_norm": 1.4412105083465576, | |
| "learning_rate": 5.775023339730696e-05, | |
| "loss": 0.7681, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 1.4729344729344729, | |
| "grad_norm": 2.3215525150299072, | |
| "learning_rate": 5.552842169575929e-05, | |
| "loss": 0.8912, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 1.4843304843304843, | |
| "grad_norm": 1.5725319385528564, | |
| "learning_rate": 5.3340445430268436e-05, | |
| "loss": 1.4197, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.4957264957264957, | |
| "grad_norm": 1.1363613605499268, | |
| "learning_rate": 5.118708823473095e-05, | |
| "loss": 1.5858, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 1.5071225071225072, | |
| "grad_norm": 1.144425868988037, | |
| "learning_rate": 4.906912134406216e-05, | |
| "loss": 1.4811, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 1.5185185185185186, | |
| "grad_norm": 1.175240397453308, | |
| "learning_rate": 4.6987303317974865e-05, | |
| "loss": 1.3986, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 1.5299145299145298, | |
| "grad_norm": 1.309635043144226, | |
| "learning_rate": 4.4942379769297414e-05, | |
| "loss": 1.3377, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 1.5413105413105415, | |
| "grad_norm": 1.1796588897705078, | |
| "learning_rate": 4.293508309692913e-05, | |
| "loss": 1.3915, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 1.5527065527065527, | |
| "grad_norm": 1.3779749870300293, | |
| "learning_rate": 4.096613222352843e-05, | |
| "loss": 1.2712, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 1.564102564102564, | |
| "grad_norm": 1.159746766090393, | |
| "learning_rate": 3.90362323380269e-05, | |
| "loss": 1.0891, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 1.5754985754985755, | |
| "grad_norm": 1.0766531229019165, | |
| "learning_rate": 3.714607464306281e-05, | |
| "loss": 1.0937, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 1.5868945868945867, | |
| "grad_norm": 1.7504690885543823, | |
| "learning_rate": 3.529633610742382e-05, | |
| "loss": 0.9782, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 1.5982905982905984, | |
| "grad_norm": 1.2635042667388916, | |
| "learning_rate": 3.348767922358719e-05, | |
| "loss": 1.0732, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.6096866096866096, | |
| "grad_norm": 1.149855136871338, | |
| "learning_rate": 3.172075177044513e-05, | |
| "loss": 1.0168, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 1.6210826210826212, | |
| "grad_norm": 1.232421875, | |
| "learning_rate": 2.9996186581299824e-05, | |
| "loss": 0.9042, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 1.6324786324786325, | |
| "grad_norm": 1.0549193620681763, | |
| "learning_rate": 2.831460131721116e-05, | |
| "loss": 0.8121, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 1.6438746438746439, | |
| "grad_norm": 1.1603848934173584, | |
| "learning_rate": 2.6676598245778498e-05, | |
| "loss": 0.9236, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 1.6552706552706553, | |
| "grad_norm": 1.3222887516021729, | |
| "learning_rate": 2.5082764025435865e-05, | |
| "loss": 1.0325, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 1.6666666666666665, | |
| "grad_norm": 1.4469937086105347, | |
| "learning_rate": 2.353366949533736e-05, | |
| "loss": 1.0456, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 1.6780626780626782, | |
| "grad_norm": 1.4546148777008057, | |
| "learning_rate": 2.20298694709085e-05, | |
| "loss": 0.8804, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 1.6894586894586894, | |
| "grad_norm": 1.2994384765625, | |
| "learning_rate": 2.0571902545136565e-05, | |
| "loss": 0.7717, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 1.7008547008547008, | |
| "grad_norm": 1.4087623357772827, | |
| "learning_rate": 1.9160290895670937e-05, | |
| "loss": 0.6291, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 1.7122507122507122, | |
| "grad_norm": 2.228584051132202, | |
| "learning_rate": 1.7795540097802668e-05, | |
| "loss": 1.0783, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.7122507122507122, | |
| "eval_loss": 1.2840447425842285, | |
| "eval_runtime": 1.7004, | |
| "eval_samples_per_second": 29.405, | |
| "eval_steps_per_second": 4.117, | |
| "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 | |
| } | |