| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 16.932038834951456, | |
| "eval_steps": 500, | |
| "global_step": 136, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.11650485436893204, | |
| "grad_norm": 1.7820011377334595, | |
| "learning_rate": 7.142857142857143e-07, | |
| "loss": 0.4027, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.23300970873786409, | |
| "grad_norm": 1.7389452457427979, | |
| "learning_rate": 1.4285714285714286e-06, | |
| "loss": 0.402, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.34951456310679613, | |
| "grad_norm": 1.74604332447052, | |
| "learning_rate": 2.1428571428571427e-06, | |
| "loss": 0.3966, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.46601941747572817, | |
| "grad_norm": 1.7389558553695679, | |
| "learning_rate": 2.8571428571428573e-06, | |
| "loss": 0.404, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.5825242718446602, | |
| "grad_norm": 1.6699142456054688, | |
| "learning_rate": 3.5714285714285718e-06, | |
| "loss": 0.3975, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.6990291262135923, | |
| "grad_norm": 1.5735969543457031, | |
| "learning_rate": 4.2857142857142855e-06, | |
| "loss": 0.3923, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.8155339805825242, | |
| "grad_norm": 1.4590719938278198, | |
| "learning_rate": 5e-06, | |
| "loss": 0.405, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.9320388349514563, | |
| "grad_norm": 1.2758820056915283, | |
| "learning_rate": 5.7142857142857145e-06, | |
| "loss": 0.3803, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 1.116504854368932, | |
| "grad_norm": 1.3157119750976562, | |
| "learning_rate": 6.4285714285714295e-06, | |
| "loss": 0.7377, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 1.233009708737864, | |
| "grad_norm": 0.6604185700416565, | |
| "learning_rate": 7.1428571428571436e-06, | |
| "loss": 0.3704, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.3495145631067962, | |
| "grad_norm": 0.5376127362251282, | |
| "learning_rate": 7.857142857142858e-06, | |
| "loss": 0.3616, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.4660194174757282, | |
| "grad_norm": 1.2837574481964111, | |
| "learning_rate": 8.571428571428571e-06, | |
| "loss": 0.3684, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.5825242718446602, | |
| "grad_norm": 1.3026747703552246, | |
| "learning_rate": 9.285714285714288e-06, | |
| "loss": 0.3633, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.6990291262135924, | |
| "grad_norm": 1.3066328763961792, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3629, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.8155339805825244, | |
| "grad_norm": 1.172119379043579, | |
| "learning_rate": 9.998342337571566e-06, | |
| "loss": 0.3631, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.9320388349514563, | |
| "grad_norm": 0.9207857251167297, | |
| "learning_rate": 9.993370449424153e-06, | |
| "loss": 0.3506, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 2.116504854368932, | |
| "grad_norm": 1.1936880350112915, | |
| "learning_rate": 9.985087632242634e-06, | |
| "loss": 0.7052, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 2.233009708737864, | |
| "grad_norm": 0.589175283908844, | |
| "learning_rate": 9.973499378072947e-06, | |
| "loss": 0.3364, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 2.349514563106796, | |
| "grad_norm": 0.4948810040950775, | |
| "learning_rate": 9.958613370680507e-06, | |
| "loss": 0.3307, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 2.466019417475728, | |
| "grad_norm": 0.4881579875946045, | |
| "learning_rate": 9.940439480455386e-06, | |
| "loss": 0.3345, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.58252427184466, | |
| "grad_norm": 0.5249760150909424, | |
| "learning_rate": 9.918989757867584e-06, | |
| "loss": 0.329, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 2.6990291262135924, | |
| "grad_norm": 0.5218749046325684, | |
| "learning_rate": 9.89427842547679e-06, | |
| "loss": 0.3212, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 2.8155339805825244, | |
| "grad_norm": 0.48922351002693176, | |
| "learning_rate": 9.866321868501914e-06, | |
| "loss": 0.317, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 2.9320388349514563, | |
| "grad_norm": 0.3870461881160736, | |
| "learning_rate": 9.835138623956603e-06, | |
| "loss": 0.3131, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 3.116504854368932, | |
| "grad_norm": 0.33141207695007324, | |
| "learning_rate": 9.80074936835801e-06, | |
| "loss": 0.5829, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 3.233009708737864, | |
| "grad_norm": 0.32673436403274536, | |
| "learning_rate": 9.763176904016914e-06, | |
| "loss": 0.3009, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 3.349514563106796, | |
| "grad_norm": 0.33463019132614136, | |
| "learning_rate": 9.722446143918307e-06, | |
| "loss": 0.3081, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 3.466019417475728, | |
| "grad_norm": 0.29102134704589844, | |
| "learning_rate": 9.678584095202468e-06, | |
| "loss": 0.2774, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 3.58252427184466, | |
| "grad_norm": 0.31500688195228577, | |
| "learning_rate": 9.631619841257477e-06, | |
| "loss": 0.2803, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 3.6990291262135924, | |
| "grad_norm": 0.30529990792274475, | |
| "learning_rate": 9.581584522435025e-06, | |
| "loss": 0.2804, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 3.8155339805825244, | |
| "grad_norm": 0.28200799226760864, | |
| "learning_rate": 9.528511315402358e-06, | |
| "loss": 0.2687, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 3.9320388349514563, | |
| "grad_norm": 0.27144694328308105, | |
| "learning_rate": 9.472435411143979e-06, | |
| "loss": 0.2722, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 4.116504854368932, | |
| "grad_norm": 0.43679553270339966, | |
| "learning_rate": 9.413393991627737e-06, | |
| "loss": 0.526, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 4.233009708737864, | |
| "grad_norm": 0.25320038199424744, | |
| "learning_rate": 9.351426205150778e-06, | |
| "loss": 0.2568, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 4.349514563106796, | |
| "grad_norm": 0.22309613227844238, | |
| "learning_rate": 9.286573140381663e-06, | |
| "loss": 0.2472, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 4.466019417475728, | |
| "grad_norm": 0.20222555100917816, | |
| "learning_rate": 9.218877799115929e-06, | |
| "loss": 0.2229, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 4.58252427184466, | |
| "grad_norm": 0.21417675912380219, | |
| "learning_rate": 9.148385067763094e-06, | |
| "loss": 0.2326, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 4.699029126213592, | |
| "grad_norm": 0.26747238636016846, | |
| "learning_rate": 9.075141687584056e-06, | |
| "loss": 0.2339, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 4.815533980582524, | |
| "grad_norm": 0.2342718243598938, | |
| "learning_rate": 8.999196223698599e-06, | |
| "loss": 0.2304, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 4.932038834951456, | |
| "grad_norm": 0.23761263489723206, | |
| "learning_rate": 8.920599032883553e-06, | |
| "loss": 0.2331, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 5.116504854368932, | |
| "grad_norm": 0.3980836570262909, | |
| "learning_rate": 8.839402230183e-06, | |
| "loss": 0.4385, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 5.233009708737864, | |
| "grad_norm": 0.22973115742206573, | |
| "learning_rate": 8.755659654352599e-06, | |
| "loss": 0.2075, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 5.349514563106796, | |
| "grad_norm": 0.21187792718410492, | |
| "learning_rate": 8.669426832160997e-06, | |
| "loss": 0.1988, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 5.466019417475728, | |
| "grad_norm": 0.20210106670856476, | |
| "learning_rate": 8.580760941571968e-06, | |
| "loss": 0.1886, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 5.58252427184466, | |
| "grad_norm": 0.24134023487567902, | |
| "learning_rate": 8.489720773831717e-06, | |
| "loss": 0.1984, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 5.699029126213592, | |
| "grad_norm": 0.22599560022354126, | |
| "learning_rate": 8.396366694486466e-06, | |
| "loss": 0.1767, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 5.815533980582524, | |
| "grad_norm": 0.20777945220470428, | |
| "learning_rate": 8.30076060335616e-06, | |
| "loss": 0.1834, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 5.932038834951456, | |
| "grad_norm": 0.20150279998779297, | |
| "learning_rate": 8.202965893490877e-06, | |
| "loss": 0.1878, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 6.116504854368932, | |
| "grad_norm": 0.2539062798023224, | |
| "learning_rate": 8.103047409137114e-06, | |
| "loss": 0.3518, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 6.233009708737864, | |
| "grad_norm": 0.1837664395570755, | |
| "learning_rate": 8.001071402741843e-06, | |
| "loss": 0.152, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 6.349514563106796, | |
| "grad_norm": 0.20487381517887115, | |
| "learning_rate": 7.897105491022819e-06, | |
| "loss": 0.1557, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 6.466019417475728, | |
| "grad_norm": 0.24897804856300354, | |
| "learning_rate": 7.791218610134324e-06, | |
| "loss": 0.154, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 6.58252427184466, | |
| "grad_norm": 0.18702609837055206, | |
| "learning_rate": 7.683480969958005e-06, | |
| "loss": 0.1479, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 6.699029126213592, | |
| "grad_norm": 0.19429221749305725, | |
| "learning_rate": 7.5739640075491546e-06, | |
| "loss": 0.142, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 6.815533980582524, | |
| "grad_norm": 0.20301687717437744, | |
| "learning_rate": 7.462740339769323e-06, | |
| "loss": 0.1462, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 6.932038834951456, | |
| "grad_norm": 0.17031480371952057, | |
| "learning_rate": 7.349883715136601e-06, | |
| "loss": 0.1417, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 7.116504854368932, | |
| "grad_norm": 0.34165364503860474, | |
| "learning_rate": 7.235468964925571e-06, | |
| "loss": 0.2634, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 7.233009708737864, | |
| "grad_norm": 0.17344710230827332, | |
| "learning_rate": 7.119571953549305e-06, | |
| "loss": 0.1224, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 7.349514563106796, | |
| "grad_norm": 0.17058910429477692, | |
| "learning_rate": 7.002269528256334e-06, | |
| "loss": 0.1097, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 7.466019417475728, | |
| "grad_norm": 0.21691343188285828, | |
| "learning_rate": 6.883639468175926e-06, | |
| "loss": 0.1112, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 7.58252427184466, | |
| "grad_norm": 0.1959153115749359, | |
| "learning_rate": 6.763760432745475e-06, | |
| "loss": 0.0991, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 7.699029126213592, | |
| "grad_norm": 0.15394563972949982, | |
| "learning_rate": 6.6427119095541745e-06, | |
| "loss": 0.1107, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 7.815533980582524, | |
| "grad_norm": 0.18826133012771606, | |
| "learning_rate": 6.520574161637591e-06, | |
| "loss": 0.1086, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 7.932038834951456, | |
| "grad_norm": 0.21221591532230377, | |
| "learning_rate": 6.397428174258048e-06, | |
| "loss": 0.1062, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 8.116504854368932, | |
| "grad_norm": 0.3180226981639862, | |
| "learning_rate": 6.273355601206143e-06, | |
| "loss": 0.1849, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 8.233009708737864, | |
| "grad_norm": 0.17723064124584198, | |
| "learning_rate": 6.148438710658979e-06, | |
| "loss": 0.0826, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 8.349514563106796, | |
| "grad_norm": 0.19632180035114288, | |
| "learning_rate": 6.022760330631006e-06, | |
| "loss": 0.082, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 8.466019417475728, | |
| "grad_norm": 0.22644098103046417, | |
| "learning_rate": 5.896403794053679e-06, | |
| "loss": 0.0773, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 8.58252427184466, | |
| "grad_norm": 0.1707296371459961, | |
| "learning_rate": 5.76945288352031e-06, | |
| "loss": 0.078, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 8.699029126213592, | |
| "grad_norm": 0.16724658012390137, | |
| "learning_rate": 5.641991775732756e-06, | |
| "loss": 0.0766, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 8.815533980582524, | |
| "grad_norm": 0.18082226812839508, | |
| "learning_rate": 5.514104985686802e-06, | |
| "loss": 0.0776, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 8.932038834951456, | |
| "grad_norm": 0.22430583834648132, | |
| "learning_rate": 5.385877310633233e-06, | |
| "loss": 0.0778, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 9.116504854368932, | |
| "grad_norm": 0.17507706582546234, | |
| "learning_rate": 5.257393773851733e-06, | |
| "loss": 0.1409, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 9.233009708737864, | |
| "grad_norm": 0.1874881386756897, | |
| "learning_rate": 5.1287395682749444e-06, | |
| "loss": 0.0568, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 9.349514563106796, | |
| "grad_norm": 0.3130532205104828, | |
| "learning_rate": 5e-06, | |
| "loss": 0.0553, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 9.466019417475728, | |
| "grad_norm": 0.17253145575523376, | |
| "learning_rate": 4.871260431725058e-06, | |
| "loss": 0.0553, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 9.58252427184466, | |
| "grad_norm": 0.16302235424518585, | |
| "learning_rate": 4.742606226148268e-06, | |
| "loss": 0.0545, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 9.699029126213592, | |
| "grad_norm": 0.18094216287136078, | |
| "learning_rate": 4.614122689366769e-06, | |
| "loss": 0.0548, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 9.815533980582524, | |
| "grad_norm": 0.1743619292974472, | |
| "learning_rate": 4.485895014313198e-06, | |
| "loss": 0.0512, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 9.932038834951456, | |
| "grad_norm": 0.16189619898796082, | |
| "learning_rate": 4.358008224267245e-06, | |
| "loss": 0.0496, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 10.116504854368932, | |
| "grad_norm": 0.3171091675758362, | |
| "learning_rate": 4.230547116479691e-06, | |
| "loss": 0.1007, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 10.233009708737864, | |
| "grad_norm": 0.154684916138649, | |
| "learning_rate": 4.103596205946323e-06, | |
| "loss": 0.0414, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 10.349514563106796, | |
| "grad_norm": 0.1529693901538849, | |
| "learning_rate": 3.977239669368998e-06, | |
| "loss": 0.0378, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 10.466019417475728, | |
| "grad_norm": 0.18426883220672607, | |
| "learning_rate": 3.851561289341023e-06, | |
| "loss": 0.0392, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 10.58252427184466, | |
| "grad_norm": 0.18451394140720367, | |
| "learning_rate": 3.726644398793857e-06, | |
| "loss": 0.0383, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 10.699029126213592, | |
| "grad_norm": 0.17146584391593933, | |
| "learning_rate": 3.6025718257419532e-06, | |
| "loss": 0.0346, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 10.815533980582524, | |
| "grad_norm": 0.1295372098684311, | |
| "learning_rate": 3.4794258383624115e-06, | |
| "loss": 0.0347, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 10.932038834951456, | |
| "grad_norm": 0.15434859693050385, | |
| "learning_rate": 3.3572880904458267e-06, | |
| "loss": 0.0402, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 11.116504854368932, | |
| "grad_norm": 0.3346112370491028, | |
| "learning_rate": 3.236239567254526e-06, | |
| "loss": 0.0675, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 11.233009708737864, | |
| "grad_norm": 0.19830213487148285, | |
| "learning_rate": 3.116360531824074e-06, | |
| "loss": 0.0298, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 11.349514563106796, | |
| "grad_norm": 0.11921335756778717, | |
| "learning_rate": 2.997730471743667e-06, | |
| "loss": 0.0271, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 11.466019417475728, | |
| "grad_norm": 0.16639156639575958, | |
| "learning_rate": 2.880428046450697e-06, | |
| "loss": 0.027, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 11.58252427184466, | |
| "grad_norm": 0.20680218935012817, | |
| "learning_rate": 2.7645310350744296e-06, | |
| "loss": 0.0263, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 11.699029126213592, | |
| "grad_norm": 0.23083102703094482, | |
| "learning_rate": 2.6501162848634023e-06, | |
| "loss": 0.0272, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 11.815533980582524, | |
| "grad_norm": 0.1634109765291214, | |
| "learning_rate": 2.537259660230679e-06, | |
| "loss": 0.027, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 11.932038834951456, | |
| "grad_norm": 0.14731772243976593, | |
| "learning_rate": 2.426035992450848e-06, | |
| "loss": 0.027, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 12.116504854368932, | |
| "grad_norm": 0.18388910591602325, | |
| "learning_rate": 2.316519030041998e-06, | |
| "loss": 0.0456, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 12.233009708737864, | |
| "grad_norm": 0.1441938877105713, | |
| "learning_rate": 2.2087813898656775e-06, | |
| "loss": 0.0193, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 12.349514563106796, | |
| "grad_norm": 0.1402544379234314, | |
| "learning_rate": 2.102894508977182e-06, | |
| "loss": 0.0201, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 12.466019417475728, | |
| "grad_norm": 0.13963298499584198, | |
| "learning_rate": 1.9989285972581595e-06, | |
| "loss": 0.0208, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 12.58252427184466, | |
| "grad_norm": 0.15653668344020844, | |
| "learning_rate": 1.896952590862886e-06, | |
| "loss": 0.0186, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 12.699029126213592, | |
| "grad_norm": 0.1681966930627823, | |
| "learning_rate": 1.7970341065091246e-06, | |
| "loss": 0.0185, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 12.815533980582524, | |
| "grad_norm": 0.15047527849674225, | |
| "learning_rate": 1.699239396643841e-06, | |
| "loss": 0.0182, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 12.932038834951456, | |
| "grad_norm": 0.10233399271965027, | |
| "learning_rate": 1.6036333055135345e-06, | |
| "loss": 0.0189, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 13.116504854368932, | |
| "grad_norm": 0.21229885518550873, | |
| "learning_rate": 1.5102792261682813e-06, | |
| "loss": 0.0353, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 13.233009708737864, | |
| "grad_norm": 0.12984932959079742, | |
| "learning_rate": 1.4192390584280347e-06, | |
| "loss": 0.0178, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 13.349514563106796, | |
| "grad_norm": 0.10708415508270264, | |
| "learning_rate": 1.330573167839005e-06, | |
| "loss": 0.0147, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 13.466019417475728, | |
| "grad_norm": 0.11098859459161758, | |
| "learning_rate": 1.2443403456474017e-06, | |
| "loss": 0.0139, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 13.58252427184466, | |
| "grad_norm": 0.09491042047739029, | |
| "learning_rate": 1.1605977698170001e-06, | |
| "loss": 0.0142, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 13.699029126213592, | |
| "grad_norm": 0.0828198492527008, | |
| "learning_rate": 1.0794009671164484e-06, | |
| "loss": 0.0141, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 13.815533980582524, | |
| "grad_norm": 0.09377221018075943, | |
| "learning_rate": 1.0008037763014033e-06, | |
| "loss": 0.0156, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 13.932038834951456, | |
| "grad_norm": 0.1043652817606926, | |
| "learning_rate": 9.248583124159438e-07, | |
| "loss": 0.0147, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 14.116504854368932, | |
| "grad_norm": 0.1541670560836792, | |
| "learning_rate": 8.516149322369055e-07, | |
| "loss": 0.0246, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 14.233009708737864, | |
| "grad_norm": 0.07124023884534836, | |
| "learning_rate": 7.811222008840719e-07, | |
| "loss": 0.0139, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 14.349514563106796, | |
| "grad_norm": 0.07342305779457092, | |
| "learning_rate": 7.13426859618338e-07, | |
| "loss": 0.0126, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 14.466019417475728, | |
| "grad_norm": 0.06642112135887146, | |
| "learning_rate": 6.485737948492237e-07, | |
| "loss": 0.0119, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 14.58252427184466, | |
| "grad_norm": 0.06306291371583939, | |
| "learning_rate": 5.866060083722624e-07, | |
| "loss": 0.0112, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 14.699029126213592, | |
| "grad_norm": 0.06630466133356094, | |
| "learning_rate": 5.275645888560233e-07, | |
| "loss": 0.0121, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 14.815533980582524, | |
| "grad_norm": 0.06889720261096954, | |
| "learning_rate": 4.71488684597643e-07, | |
| "loss": 0.0116, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 14.932038834951456, | |
| "grad_norm": 0.06075473129749298, | |
| "learning_rate": 4.184154775649768e-07, | |
| "loss": 0.014, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 15.116504854368932, | |
| "grad_norm": 0.07335468381643295, | |
| "learning_rate": 3.683801587425251e-07, | |
| "loss": 0.0269, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 15.233009708737864, | |
| "grad_norm": 0.13383059203624725, | |
| "learning_rate": 3.214159047975324e-07, | |
| "loss": 0.0105, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 15.349514563106796, | |
| "grad_norm": 0.06708887219429016, | |
| "learning_rate": 2.7755385608169374e-07, | |
| "loss": 0.011, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 15.466019417475728, | |
| "grad_norm": 0.061848320066928864, | |
| "learning_rate": 2.368230959830875e-07, | |
| "loss": 0.012, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 15.58252427184466, | |
| "grad_norm": 0.0594082772731781, | |
| "learning_rate": 1.992506316419912e-07, | |
| "loss": 0.0113, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 15.699029126213592, | |
| "grad_norm": 0.06530940532684326, | |
| "learning_rate": 1.6486137604339813e-07, | |
| "loss": 0.0117, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 15.815533980582524, | |
| "grad_norm": 0.07374989986419678, | |
| "learning_rate": 1.3367813149808728e-07, | |
| "loss": 0.0106, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 15.932038834951456, | |
| "grad_norm": 0.0554700568318367, | |
| "learning_rate": 1.0572157452321097e-07, | |
| "loss": 0.01, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 16.116504854368934, | |
| "grad_norm": 0.11609751731157303, | |
| "learning_rate": 8.101024213241826e-08, | |
| "loss": 0.0216, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 16.233009708737864, | |
| "grad_norm": 0.05223438888788223, | |
| "learning_rate": 5.9560519544614725e-08, | |
| "loss": 0.0108, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 16.349514563106798, | |
| "grad_norm": 0.05844803899526596, | |
| "learning_rate": 4.138662931949255e-08, | |
| "loss": 0.0105, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 16.466019417475728, | |
| "grad_norm": 0.052356619387865067, | |
| "learning_rate": 2.6500621927054716e-08, | |
| "loss": 0.0105, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 16.58252427184466, | |
| "grad_norm": 0.05942930653691292, | |
| "learning_rate": 1.4912367757366485e-08, | |
| "loss": 0.0107, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 16.699029126213592, | |
| "grad_norm": 0.05563804879784584, | |
| "learning_rate": 6.629550575847355e-09, | |
| "loss": 0.0115, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 16.815533980582526, | |
| "grad_norm": 0.05824480950832367, | |
| "learning_rate": 1.657662428434792e-09, | |
| "loss": 0.0113, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 16.932038834951456, | |
| "grad_norm": 0.05532587692141533, | |
| "learning_rate": 0.0, | |
| "loss": 0.0111, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 16.932038834951456, | |
| "step": 136, | |
| "total_flos": 493320970436608.0, | |
| "train_loss": 0.15380282930838055, | |
| "train_runtime": 33702.47, | |
| "train_samples_per_second": 0.414, | |
| "train_steps_per_second": 0.004 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 136, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 17, | |
| "save_steps": 10000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 493320970436608.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |