|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 2.9450549450549453, |
|
"eval_steps": 29, |
|
"global_step": 339, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 2e-05, |
|
"loss": 0.5065, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"eval_loss": 0.5089401602745056, |
|
"eval_runtime": 34.8867, |
|
"eval_samples_per_second": 174.68, |
|
"eval_steps_per_second": 12.498, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 4e-05, |
|
"loss": 0.5189, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 6e-05, |
|
"loss": 0.4966, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 8e-05, |
|
"loss": 0.4891, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 0.0001, |
|
"loss": 0.507, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 0.00012, |
|
"loss": 0.5071, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 0.00014, |
|
"loss": 0.4739, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 0.00016, |
|
"loss": 0.4721, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 0.00018, |
|
"loss": 0.4213, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 0.0002, |
|
"loss": 0.4056, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 0.00019999747405795057, |
|
"loss": 0.3989, |
|
"step": 11 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 0.00019998989635940995, |
|
"loss": 0.3843, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 0.00019997726728719468, |
|
"loss": 0.3771, |
|
"step": 13 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 0.00019995958747931082, |
|
"loss": 0.3775, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"learning_rate": 0.00019993685782892183, |
|
"loss": 0.3778, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 0.00019990907948430327, |
|
"loss": 0.3786, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 0.0001998762538487849, |
|
"loss": 0.3669, |
|
"step": 17 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 0.00019983838258067987, |
|
"loss": 0.3819, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.17, |
|
"learning_rate": 0.0001997954675932006, |
|
"loss": 0.4043, |
|
"step": 19 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 0.00019974751105436266, |
|
"loss": 0.3503, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 0.00019969451538687474, |
|
"loss": 0.3753, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 0.19, |
|
"learning_rate": 0.00019963648326801653, |
|
"loss": 0.368, |
|
"step": 22 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 0.00019957341762950344, |
|
"loss": 0.3828, |
|
"step": 23 |
|
}, |
|
{ |
|
"epoch": 0.21, |
|
"learning_rate": 0.00019950532165733845, |
|
"loss": 0.3509, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"learning_rate": 0.00019943219879165115, |
|
"loss": 0.381, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.23, |
|
"learning_rate": 0.0001993540527265239, |
|
"loss": 0.3638, |
|
"step": 26 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"learning_rate": 0.0001992708874098054, |
|
"loss": 0.3645, |
|
"step": 27 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"learning_rate": 0.00019918270704291104, |
|
"loss": 0.3466, |
|
"step": 28 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"learning_rate": 0.00019908951608061076, |
|
"loss": 0.3477, |
|
"step": 29 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"eval_loss": 0.35608404874801636, |
|
"eval_runtime": 35.0585, |
|
"eval_samples_per_second": 173.824, |
|
"eval_steps_per_second": 12.436, |
|
"step": 29 |
|
}, |
|
{ |
|
"epoch": 0.26, |
|
"learning_rate": 0.000198991319230804, |
|
"loss": 0.3444, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"learning_rate": 0.0001988881214542817, |
|
"loss": 0.3646, |
|
"step": 31 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"learning_rate": 0.00019877992796447601, |
|
"loss": 0.3502, |
|
"step": 32 |
|
}, |
|
{ |
|
"epoch": 0.29, |
|
"learning_rate": 0.00019866674422719665, |
|
"loss": 0.3532, |
|
"step": 33 |
|
}, |
|
{ |
|
"epoch": 0.3, |
|
"learning_rate": 0.00019854857596035476, |
|
"loss": 0.3639, |
|
"step": 34 |
|
}, |
|
{ |
|
"epoch": 0.31, |
|
"learning_rate": 0.0001984254291336743, |
|
"loss": 0.3538, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"learning_rate": 0.0001982973099683902, |
|
"loss": 0.3431, |
|
"step": 36 |
|
}, |
|
{ |
|
"epoch": 0.33, |
|
"learning_rate": 0.00019816422493693417, |
|
"loss": 0.3493, |
|
"step": 37 |
|
}, |
|
{ |
|
"epoch": 0.33, |
|
"learning_rate": 0.0001980261807626078, |
|
"loss": 0.3596, |
|
"step": 38 |
|
}, |
|
{ |
|
"epoch": 0.34, |
|
"learning_rate": 0.00019788318441924275, |
|
"loss": 0.3401, |
|
"step": 39 |
|
}, |
|
{ |
|
"epoch": 0.35, |
|
"learning_rate": 0.00019773524313084856, |
|
"loss": 0.3822, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.36, |
|
"learning_rate": 0.00019758236437124769, |
|
"loss": 0.3719, |
|
"step": 41 |
|
}, |
|
{ |
|
"epoch": 0.37, |
|
"learning_rate": 0.00019742455586369784, |
|
"loss": 0.3369, |
|
"step": 42 |
|
}, |
|
{ |
|
"epoch": 0.38, |
|
"learning_rate": 0.0001972618255805019, |
|
"loss": 0.341, |
|
"step": 43 |
|
}, |
|
{ |
|
"epoch": 0.39, |
|
"learning_rate": 0.0001970941817426052, |
|
"loss": 0.3481, |
|
"step": 44 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 0.00019692163281918014, |
|
"loss": 0.3615, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 0.00019674418752719833, |
|
"loss": 0.346, |
|
"step": 46 |
|
}, |
|
{ |
|
"epoch": 0.41, |
|
"learning_rate": 0.00019656185483099024, |
|
"loss": 0.3479, |
|
"step": 47 |
|
}, |
|
{ |
|
"epoch": 0.42, |
|
"learning_rate": 0.00019637464394179239, |
|
"loss": 0.3638, |
|
"step": 48 |
|
}, |
|
{ |
|
"epoch": 0.43, |
|
"learning_rate": 0.00019618256431728194, |
|
"loss": 0.3419, |
|
"step": 49 |
|
}, |
|
{ |
|
"epoch": 0.44, |
|
"learning_rate": 0.0001959856256610988, |
|
"loss": 0.3496, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.45, |
|
"learning_rate": 0.00019578383792235573, |
|
"loss": 0.3503, |
|
"step": 51 |
|
}, |
|
{ |
|
"epoch": 0.46, |
|
"learning_rate": 0.0001955772112951354, |
|
"loss": 0.3437, |
|
"step": 52 |
|
}, |
|
{ |
|
"epoch": 0.47, |
|
"learning_rate": 0.00019536575621797547, |
|
"loss": 0.3343, |
|
"step": 53 |
|
}, |
|
{ |
|
"epoch": 0.47, |
|
"learning_rate": 0.00019514948337334142, |
|
"loss": 0.3517, |
|
"step": 54 |
|
}, |
|
{ |
|
"epoch": 0.48, |
|
"learning_rate": 0.0001949284036870867, |
|
"loss": 0.343, |
|
"step": 55 |
|
}, |
|
{ |
|
"epoch": 0.49, |
|
"learning_rate": 0.0001947025283279008, |
|
"loss": 0.3479, |
|
"step": 56 |
|
}, |
|
{ |
|
"epoch": 0.5, |
|
"learning_rate": 0.00019447186870674506, |
|
"loss": 0.3237, |
|
"step": 57 |
|
}, |
|
{ |
|
"epoch": 0.51, |
|
"learning_rate": 0.00019423643647627624, |
|
"loss": 0.3593, |
|
"step": 58 |
|
}, |
|
{ |
|
"epoch": 0.51, |
|
"eval_loss": 0.3460778594017029, |
|
"eval_runtime": 35.0517, |
|
"eval_samples_per_second": 173.858, |
|
"eval_steps_per_second": 12.439, |
|
"step": 58 |
|
}, |
|
{ |
|
"epoch": 0.52, |
|
"learning_rate": 0.00019399624353025772, |
|
"loss": 0.348, |
|
"step": 59 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"learning_rate": 0.00019375130200295878, |
|
"loss": 0.344, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.54, |
|
"learning_rate": 0.0001935016242685415, |
|
"loss": 0.3601, |
|
"step": 61 |
|
}, |
|
{ |
|
"epoch": 0.55, |
|
"learning_rate": 0.00019324722294043558, |
|
"loss": 0.3524, |
|
"step": 62 |
|
}, |
|
{ |
|
"epoch": 0.55, |
|
"learning_rate": 0.00019298811087070132, |
|
"loss": 0.3421, |
|
"step": 63 |
|
}, |
|
{ |
|
"epoch": 0.56, |
|
"learning_rate": 0.00019272430114938017, |
|
"loss": 0.3524, |
|
"step": 64 |
|
}, |
|
{ |
|
"epoch": 0.57, |
|
"learning_rate": 0.00019245580710383343, |
|
"loss": 0.3334, |
|
"step": 65 |
|
}, |
|
{ |
|
"epoch": 0.58, |
|
"learning_rate": 0.00019218264229806917, |
|
"loss": 0.3312, |
|
"step": 66 |
|
}, |
|
{ |
|
"epoch": 0.59, |
|
"learning_rate": 0.00019190482053205673, |
|
"loss": 0.344, |
|
"step": 67 |
|
}, |
|
{ |
|
"epoch": 0.6, |
|
"learning_rate": 0.00019162235584102973, |
|
"loss": 0.353, |
|
"step": 68 |
|
}, |
|
{ |
|
"epoch": 0.61, |
|
"learning_rate": 0.00019133526249477702, |
|
"loss": 0.3473, |
|
"step": 69 |
|
}, |
|
{ |
|
"epoch": 0.62, |
|
"learning_rate": 0.00019104355499692166, |
|
"loss": 0.345, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.62, |
|
"learning_rate": 0.00019074724808418835, |
|
"loss": 0.348, |
|
"step": 71 |
|
}, |
|
{ |
|
"epoch": 0.63, |
|
"learning_rate": 0.00019044635672565895, |
|
"loss": 0.3333, |
|
"step": 72 |
|
}, |
|
{ |
|
"epoch": 0.64, |
|
"learning_rate": 0.00019014089612201613, |
|
"loss": 0.3398, |
|
"step": 73 |
|
}, |
|
{ |
|
"epoch": 0.65, |
|
"learning_rate": 0.00018983088170477553, |
|
"loss": 0.3424, |
|
"step": 74 |
|
}, |
|
{ |
|
"epoch": 0.66, |
|
"learning_rate": 0.00018951632913550626, |
|
"loss": 0.3279, |
|
"step": 75 |
|
}, |
|
{ |
|
"epoch": 0.67, |
|
"learning_rate": 0.00018919725430503945, |
|
"loss": 0.3243, |
|
"step": 76 |
|
}, |
|
{ |
|
"epoch": 0.68, |
|
"learning_rate": 0.00018887367333266582, |
|
"loss": 0.3439, |
|
"step": 77 |
|
}, |
|
{ |
|
"epoch": 0.69, |
|
"learning_rate": 0.000188545602565321, |
|
"loss": 0.3486, |
|
"step": 78 |
|
}, |
|
{ |
|
"epoch": 0.69, |
|
"learning_rate": 0.00018821305857675996, |
|
"loss": 0.3367, |
|
"step": 79 |
|
}, |
|
{ |
|
"epoch": 0.7, |
|
"learning_rate": 0.00018787605816671953, |
|
"loss": 0.3386, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.71, |
|
"learning_rate": 0.00018753461836006988, |
|
"loss": 0.3574, |
|
"step": 81 |
|
}, |
|
{ |
|
"epoch": 0.72, |
|
"learning_rate": 0.00018718875640595434, |
|
"loss": 0.334, |
|
"step": 82 |
|
}, |
|
{ |
|
"epoch": 0.73, |
|
"learning_rate": 0.00018683848977691785, |
|
"loss": 0.3342, |
|
"step": 83 |
|
}, |
|
{ |
|
"epoch": 0.74, |
|
"learning_rate": 0.0001864838361680247, |
|
"loss": 0.3693, |
|
"step": 84 |
|
}, |
|
{ |
|
"epoch": 0.75, |
|
"learning_rate": 0.00018612481349596405, |
|
"loss": 0.3422, |
|
"step": 85 |
|
}, |
|
{ |
|
"epoch": 0.76, |
|
"learning_rate": 0.00018576143989814523, |
|
"loss": 0.3346, |
|
"step": 86 |
|
}, |
|
{ |
|
"epoch": 0.76, |
|
"learning_rate": 0.00018539373373178123, |
|
"loss": 0.3329, |
|
"step": 87 |
|
}, |
|
{ |
|
"epoch": 0.76, |
|
"eval_loss": 0.3422779440879822, |
|
"eval_runtime": 35.1197, |
|
"eval_samples_per_second": 173.521, |
|
"eval_steps_per_second": 12.415, |
|
"step": 87 |
|
}, |
|
{ |
|
"epoch": 0.77, |
|
"learning_rate": 0.00018502171357296144, |
|
"loss": 0.3485, |
|
"step": 88 |
|
}, |
|
{ |
|
"epoch": 0.78, |
|
"learning_rate": 0.00018464539821571303, |
|
"loss": 0.3383, |
|
"step": 89 |
|
}, |
|
{ |
|
"epoch": 0.79, |
|
"learning_rate": 0.00018426480667105177, |
|
"loss": 0.3434, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 0.8, |
|
"learning_rate": 0.00018387995816602137, |
|
"loss": 0.3205, |
|
"step": 91 |
|
}, |
|
{ |
|
"epoch": 0.81, |
|
"learning_rate": 0.00018349087214272224, |
|
"loss": 0.3522, |
|
"step": 92 |
|
}, |
|
{ |
|
"epoch": 0.82, |
|
"learning_rate": 0.0001830975682573293, |
|
"loss": 0.3416, |
|
"step": 93 |
|
}, |
|
{ |
|
"epoch": 0.83, |
|
"learning_rate": 0.00018270006637909907, |
|
"loss": 0.3468, |
|
"step": 94 |
|
}, |
|
{ |
|
"epoch": 0.84, |
|
"learning_rate": 0.00018229838658936564, |
|
"loss": 0.3407, |
|
"step": 95 |
|
}, |
|
{ |
|
"epoch": 0.84, |
|
"learning_rate": 0.0001818925491805265, |
|
"loss": 0.3198, |
|
"step": 96 |
|
}, |
|
{ |
|
"epoch": 0.85, |
|
"learning_rate": 0.00018148257465501716, |
|
"loss": 0.3369, |
|
"step": 97 |
|
}, |
|
{ |
|
"epoch": 0.86, |
|
"learning_rate": 0.0001810684837242755, |
|
"loss": 0.3371, |
|
"step": 98 |
|
}, |
|
{ |
|
"epoch": 0.87, |
|
"learning_rate": 0.00018065029730769534, |
|
"loss": 0.3395, |
|
"step": 99 |
|
}, |
|
{ |
|
"epoch": 0.88, |
|
"learning_rate": 0.00018022803653156984, |
|
"loss": 0.3418, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.89, |
|
"learning_rate": 0.000179801722728024, |
|
"loss": 0.346, |
|
"step": 101 |
|
}, |
|
{ |
|
"epoch": 0.9, |
|
"learning_rate": 0.00017937137743393694, |
|
"loss": 0.3385, |
|
"step": 102 |
|
}, |
|
{ |
|
"epoch": 0.91, |
|
"learning_rate": 0.00017893702238985432, |
|
"loss": 0.3343, |
|
"step": 103 |
|
}, |
|
{ |
|
"epoch": 0.91, |
|
"learning_rate": 0.00017849867953888948, |
|
"loss": 0.3146, |
|
"step": 104 |
|
}, |
|
{ |
|
"epoch": 0.92, |
|
"learning_rate": 0.00017805637102561516, |
|
"loss": 0.3662, |
|
"step": 105 |
|
}, |
|
{ |
|
"epoch": 0.93, |
|
"learning_rate": 0.00017761011919494488, |
|
"loss": 0.3481, |
|
"step": 106 |
|
}, |
|
{ |
|
"epoch": 0.94, |
|
"learning_rate": 0.00017715994659100388, |
|
"loss": 0.3447, |
|
"step": 107 |
|
}, |
|
{ |
|
"epoch": 0.95, |
|
"learning_rate": 0.00017670587595599034, |
|
"loss": 0.3379, |
|
"step": 108 |
|
}, |
|
{ |
|
"epoch": 0.96, |
|
"learning_rate": 0.0001762479302290265, |
|
"loss": 0.3388, |
|
"step": 109 |
|
}, |
|
{ |
|
"epoch": 0.97, |
|
"learning_rate": 0.0001757861325449997, |
|
"loss": 0.3497, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 0.98, |
|
"learning_rate": 0.0001753205062333937, |
|
"loss": 0.3539, |
|
"step": 111 |
|
}, |
|
{ |
|
"epoch": 0.98, |
|
"learning_rate": 0.00017485107481711012, |
|
"loss": 0.3571, |
|
"step": 112 |
|
}, |
|
{ |
|
"epoch": 0.99, |
|
"learning_rate": 0.00017437786201128004, |
|
"loss": 0.3496, |
|
"step": 113 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"learning_rate": 0.00017390089172206592, |
|
"loss": 0.3436, |
|
"step": 114 |
|
}, |
|
{ |
|
"epoch": 1.01, |
|
"learning_rate": 0.000173420188045454, |
|
"loss": 0.3434, |
|
"step": 115 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"learning_rate": 0.00017293577526603682, |
|
"loss": 0.3607, |
|
"step": 116 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"eval_loss": 0.3404248356819153, |
|
"eval_runtime": 35.0435, |
|
"eval_samples_per_second": 173.898, |
|
"eval_steps_per_second": 12.442, |
|
"step": 116 |
|
}, |
|
{ |
|
"epoch": 1.01, |
|
"learning_rate": 0.0001724476778557866, |
|
"loss": 0.3363, |
|
"step": 117 |
|
}, |
|
{ |
|
"epoch": 1.02, |
|
"learning_rate": 0.00017195592047281882, |
|
"loss": 0.3283, |
|
"step": 118 |
|
}, |
|
{ |
|
"epoch": 1.03, |
|
"learning_rate": 0.00017146052796014646, |
|
"loss": 0.3293, |
|
"step": 119 |
|
}, |
|
{ |
|
"epoch": 1.04, |
|
"learning_rate": 0.00017096152534442513, |
|
"loss": 0.3485, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 1.05, |
|
"learning_rate": 0.0001704589378346886, |
|
"loss": 0.3315, |
|
"step": 121 |
|
}, |
|
{ |
|
"epoch": 1.05, |
|
"learning_rate": 0.0001699527908210754, |
|
"loss": 0.3686, |
|
"step": 122 |
|
}, |
|
{ |
|
"epoch": 1.06, |
|
"learning_rate": 0.00016944310987354597, |
|
"loss": 0.3384, |
|
"step": 123 |
|
}, |
|
{ |
|
"epoch": 1.07, |
|
"learning_rate": 0.0001689299207405911, |
|
"loss": 0.3432, |
|
"step": 124 |
|
}, |
|
{ |
|
"epoch": 1.08, |
|
"learning_rate": 0.00016841324934793094, |
|
"loss": 0.3323, |
|
"step": 125 |
|
}, |
|
{ |
|
"epoch": 1.09, |
|
"learning_rate": 0.00016789312179720547, |
|
"loss": 0.3325, |
|
"step": 126 |
|
}, |
|
{ |
|
"epoch": 1.1, |
|
"learning_rate": 0.00016736956436465573, |
|
"loss": 0.3464, |
|
"step": 127 |
|
}, |
|
{ |
|
"epoch": 1.11, |
|
"learning_rate": 0.00016684260349979636, |
|
"loss": 0.3344, |
|
"step": 128 |
|
}, |
|
{ |
|
"epoch": 1.12, |
|
"learning_rate": 0.00016631226582407952, |
|
"loss": 0.3319, |
|
"step": 129 |
|
}, |
|
{ |
|
"epoch": 1.13, |
|
"learning_rate": 0.00016577857812954993, |
|
"loss": 0.3385, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 1.13, |
|
"learning_rate": 0.00016524156737749132, |
|
"loss": 0.3166, |
|
"step": 131 |
|
}, |
|
{ |
|
"epoch": 1.14, |
|
"learning_rate": 0.00016470126069706456, |
|
"loss": 0.3214, |
|
"step": 132 |
|
}, |
|
{ |
|
"epoch": 1.15, |
|
"learning_rate": 0.00016415768538393687, |
|
"loss": 0.3101, |
|
"step": 133 |
|
}, |
|
{ |
|
"epoch": 1.16, |
|
"learning_rate": 0.00016361086889890306, |
|
"loss": 0.3334, |
|
"step": 134 |
|
}, |
|
{ |
|
"epoch": 1.17, |
|
"learning_rate": 0.0001630608388664982, |
|
"loss": 0.3094, |
|
"step": 135 |
|
}, |
|
{ |
|
"epoch": 1.18, |
|
"learning_rate": 0.00016250762307360207, |
|
"loss": 0.327, |
|
"step": 136 |
|
}, |
|
{ |
|
"epoch": 1.19, |
|
"learning_rate": 0.00016195124946803525, |
|
"loss": 0.3512, |
|
"step": 137 |
|
}, |
|
{ |
|
"epoch": 1.2, |
|
"learning_rate": 0.0001613917461571475, |
|
"loss": 0.3329, |
|
"step": 138 |
|
}, |
|
{ |
|
"epoch": 1.2, |
|
"learning_rate": 0.0001608291414063977, |
|
"loss": 0.342, |
|
"step": 139 |
|
}, |
|
{ |
|
"epoch": 1.21, |
|
"learning_rate": 0.00016026346363792567, |
|
"loss": 0.3488, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 1.22, |
|
"learning_rate": 0.00015969474142911666, |
|
"loss": 0.3385, |
|
"step": 141 |
|
}, |
|
{ |
|
"epoch": 1.23, |
|
"learning_rate": 0.0001591230035111576, |
|
"loss": 0.3207, |
|
"step": 142 |
|
}, |
|
{ |
|
"epoch": 1.24, |
|
"learning_rate": 0.00015854827876758532, |
|
"loss": 0.321, |
|
"step": 143 |
|
}, |
|
{ |
|
"epoch": 1.25, |
|
"learning_rate": 0.00015797059623282787, |
|
"loss": 0.3409, |
|
"step": 144 |
|
}, |
|
{ |
|
"epoch": 1.26, |
|
"learning_rate": 0.0001573899850907373, |
|
"loss": 0.3336, |
|
"step": 145 |
|
}, |
|
{ |
|
"epoch": 1.26, |
|
"eval_loss": 0.3395354747772217, |
|
"eval_runtime": 35.0942, |
|
"eval_samples_per_second": 173.647, |
|
"eval_steps_per_second": 12.424, |
|
"step": 145 |
|
}, |
|
{ |
|
"epoch": 1.27, |
|
"learning_rate": 0.00015680647467311557, |
|
"loss": 0.3355, |
|
"step": 146 |
|
}, |
|
{ |
|
"epoch": 1.27, |
|
"learning_rate": 0.00015622009445823273, |
|
"loss": 0.347, |
|
"step": 147 |
|
}, |
|
{ |
|
"epoch": 1.28, |
|
"learning_rate": 0.0001556308740693376, |
|
"loss": 0.3433, |
|
"step": 148 |
|
}, |
|
{ |
|
"epoch": 1.29, |
|
"learning_rate": 0.00015503884327316132, |
|
"loss": 0.3271, |
|
"step": 149 |
|
}, |
|
{ |
|
"epoch": 1.3, |
|
"learning_rate": 0.00015444403197841346, |
|
"loss": 0.3195, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 1.31, |
|
"learning_rate": 0.00015384647023427138, |
|
"loss": 0.3314, |
|
"step": 151 |
|
}, |
|
{ |
|
"epoch": 1.32, |
|
"learning_rate": 0.00015324618822886165, |
|
"loss": 0.3387, |
|
"step": 152 |
|
}, |
|
{ |
|
"epoch": 1.33, |
|
"learning_rate": 0.0001526432162877356, |
|
"loss": 0.3436, |
|
"step": 153 |
|
}, |
|
{ |
|
"epoch": 1.34, |
|
"learning_rate": 0.00015203758487233678, |
|
"loss": 0.3152, |
|
"step": 154 |
|
}, |
|
{ |
|
"epoch": 1.35, |
|
"learning_rate": 0.0001514293245784623, |
|
"loss": 0.341, |
|
"step": 155 |
|
}, |
|
{ |
|
"epoch": 1.35, |
|
"learning_rate": 0.00015081846613471735, |
|
"loss": 0.3465, |
|
"step": 156 |
|
}, |
|
{ |
|
"epoch": 1.36, |
|
"learning_rate": 0.0001502050404009624, |
|
"loss": 0.3328, |
|
"step": 157 |
|
}, |
|
{ |
|
"epoch": 1.37, |
|
"learning_rate": 0.00014958907836675468, |
|
"loss": 0.3459, |
|
"step": 158 |
|
}, |
|
{ |
|
"epoch": 1.38, |
|
"learning_rate": 0.0001489706111497821, |
|
"loss": 0.3625, |
|
"step": 159 |
|
}, |
|
{ |
|
"epoch": 1.39, |
|
"learning_rate": 0.00014834966999429178, |
|
"loss": 0.3558, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 1.4, |
|
"learning_rate": 0.00014772628626951112, |
|
"loss": 0.3418, |
|
"step": 161 |
|
}, |
|
{ |
|
"epoch": 1.41, |
|
"learning_rate": 0.00014710049146806348, |
|
"loss": 0.3304, |
|
"step": 162 |
|
}, |
|
{ |
|
"epoch": 1.42, |
|
"learning_rate": 0.00014647231720437686, |
|
"loss": 0.3231, |
|
"step": 163 |
|
}, |
|
{ |
|
"epoch": 1.42, |
|
"learning_rate": 0.00014584179521308702, |
|
"loss": 0.3144, |
|
"step": 164 |
|
}, |
|
{ |
|
"epoch": 1.43, |
|
"learning_rate": 0.00014520895734743418, |
|
"loss": 0.3332, |
|
"step": 165 |
|
}, |
|
{ |
|
"epoch": 1.44, |
|
"learning_rate": 0.00014457383557765386, |
|
"loss": 0.3311, |
|
"step": 166 |
|
}, |
|
{ |
|
"epoch": 1.45, |
|
"learning_rate": 0.00014393646198936167, |
|
"loss": 0.3396, |
|
"step": 167 |
|
}, |
|
{ |
|
"epoch": 1.46, |
|
"learning_rate": 0.0001432968687819327, |
|
"loss": 0.3341, |
|
"step": 168 |
|
}, |
|
{ |
|
"epoch": 1.47, |
|
"learning_rate": 0.0001426550882668744, |
|
"loss": 0.3477, |
|
"step": 169 |
|
}, |
|
{ |
|
"epoch": 1.48, |
|
"learning_rate": 0.00014201115286619463, |
|
"loss": 0.3455, |
|
"step": 170 |
|
}, |
|
{ |
|
"epoch": 1.49, |
|
"learning_rate": 0.00014136509511076346, |
|
"loss": 0.3415, |
|
"step": 171 |
|
}, |
|
{ |
|
"epoch": 1.49, |
|
"learning_rate": 0.00014071694763866986, |
|
"loss": 0.3392, |
|
"step": 172 |
|
}, |
|
{ |
|
"epoch": 1.5, |
|
"learning_rate": 0.00014006674319357298, |
|
"loss": 0.3543, |
|
"step": 173 |
|
}, |
|
{ |
|
"epoch": 1.51, |
|
"learning_rate": 0.00013941451462304777, |
|
"loss": 0.3449, |
|
"step": 174 |
|
}, |
|
{ |
|
"epoch": 1.51, |
|
"eval_loss": 0.33857324719429016, |
|
"eval_runtime": 35.0605, |
|
"eval_samples_per_second": 173.814, |
|
"eval_steps_per_second": 12.436, |
|
"step": 174 |
|
}, |
|
{ |
|
"epoch": 1.52, |
|
"learning_rate": 0.0001387602948769257, |
|
"loss": 0.3518, |
|
"step": 175 |
|
}, |
|
{ |
|
"epoch": 1.53, |
|
"learning_rate": 0.00013810411700563004, |
|
"loss": 0.3266, |
|
"step": 176 |
|
}, |
|
{ |
|
"epoch": 1.54, |
|
"learning_rate": 0.00013744601415850637, |
|
"loss": 0.3358, |
|
"step": 177 |
|
}, |
|
{ |
|
"epoch": 1.55, |
|
"learning_rate": 0.0001367860195821478, |
|
"loss": 0.3208, |
|
"step": 178 |
|
}, |
|
{ |
|
"epoch": 1.56, |
|
"learning_rate": 0.00013612416661871533, |
|
"loss": 0.3061, |
|
"step": 179 |
|
}, |
|
{ |
|
"epoch": 1.56, |
|
"learning_rate": 0.00013546048870425356, |
|
"loss": 0.3151, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 1.57, |
|
"learning_rate": 0.0001347950193670016, |
|
"loss": 0.3185, |
|
"step": 181 |
|
}, |
|
{ |
|
"epoch": 1.58, |
|
"learning_rate": 0.00013412779222569908, |
|
"loss": 0.3248, |
|
"step": 182 |
|
}, |
|
{ |
|
"epoch": 1.59, |
|
"learning_rate": 0.00013345884098788774, |
|
"loss": 0.3285, |
|
"step": 183 |
|
}, |
|
{ |
|
"epoch": 1.6, |
|
"learning_rate": 0.00013278819944820893, |
|
"loss": 0.3444, |
|
"step": 184 |
|
}, |
|
{ |
|
"epoch": 1.61, |
|
"learning_rate": 0.00013211590148669587, |
|
"loss": 0.3268, |
|
"step": 185 |
|
}, |
|
{ |
|
"epoch": 1.62, |
|
"learning_rate": 0.0001314419810670624, |
|
"loss": 0.3334, |
|
"step": 186 |
|
}, |
|
{ |
|
"epoch": 1.63, |
|
"learning_rate": 0.00013076647223498702, |
|
"loss": 0.347, |
|
"step": 187 |
|
}, |
|
{ |
|
"epoch": 1.64, |
|
"learning_rate": 0.00013008940911639303, |
|
"loss": 0.3308, |
|
"step": 188 |
|
}, |
|
{ |
|
"epoch": 1.64, |
|
"learning_rate": 0.00012941082591572443, |
|
"loss": 0.3164, |
|
"step": 189 |
|
}, |
|
{ |
|
"epoch": 1.65, |
|
"learning_rate": 0.00012873075691421807, |
|
"loss": 0.333, |
|
"step": 190 |
|
}, |
|
{ |
|
"epoch": 1.66, |
|
"learning_rate": 0.00012804923646817168, |
|
"loss": 0.319, |
|
"step": 191 |
|
}, |
|
{ |
|
"epoch": 1.67, |
|
"learning_rate": 0.0001273662990072083, |
|
"loss": 0.3235, |
|
"step": 192 |
|
}, |
|
{ |
|
"epoch": 1.68, |
|
"learning_rate": 0.00012668197903253694, |
|
"loss": 0.3553, |
|
"step": 193 |
|
}, |
|
{ |
|
"epoch": 1.69, |
|
"learning_rate": 0.00012599631111520954, |
|
"loss": 0.3323, |
|
"step": 194 |
|
}, |
|
{ |
|
"epoch": 1.7, |
|
"learning_rate": 0.00012530932989437464, |
|
"loss": 0.3183, |
|
"step": 195 |
|
}, |
|
{ |
|
"epoch": 1.71, |
|
"learning_rate": 0.00012462107007552725, |
|
"loss": 0.3328, |
|
"step": 196 |
|
}, |
|
{ |
|
"epoch": 1.71, |
|
"learning_rate": 0.0001239315664287558, |
|
"loss": 0.3153, |
|
"step": 197 |
|
}, |
|
{ |
|
"epoch": 1.72, |
|
"learning_rate": 0.00012324085378698528, |
|
"loss": 0.3349, |
|
"step": 198 |
|
}, |
|
{ |
|
"epoch": 1.73, |
|
"learning_rate": 0.0001225489670442179, |
|
"loss": 0.3367, |
|
"step": 199 |
|
}, |
|
{ |
|
"epoch": 1.74, |
|
"learning_rate": 0.0001218559411537699, |
|
"loss": 0.3432, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 1.75, |
|
"learning_rate": 0.0001211618111265061, |
|
"loss": 0.3191, |
|
"step": 201 |
|
}, |
|
{ |
|
"epoch": 1.76, |
|
"learning_rate": 0.00012046661202907101, |
|
"loss": 0.3506, |
|
"step": 202 |
|
}, |
|
{ |
|
"epoch": 1.77, |
|
"learning_rate": 0.00011977037898211723, |
|
"loss": 0.3187, |
|
"step": 203 |
|
}, |
|
{ |
|
"epoch": 1.77, |
|
"eval_loss": 0.3376944661140442, |
|
"eval_runtime": 35.038, |
|
"eval_samples_per_second": 173.925, |
|
"eval_steps_per_second": 12.444, |
|
"step": 203 |
|
}, |
|
{ |
|
"epoch": 1.78, |
|
"learning_rate": 0.00011907314715853138, |
|
"loss": 0.3553, |
|
"step": 204 |
|
}, |
|
{ |
|
"epoch": 1.78, |
|
"learning_rate": 0.00011837495178165706, |
|
"loss": 0.3567, |
|
"step": 205 |
|
}, |
|
{ |
|
"epoch": 1.79, |
|
"learning_rate": 0.0001176758281235155, |
|
"loss": 0.3221, |
|
"step": 206 |
|
}, |
|
{ |
|
"epoch": 1.8, |
|
"learning_rate": 0.00011697581150302362, |
|
"loss": 0.3458, |
|
"step": 207 |
|
}, |
|
{ |
|
"epoch": 1.81, |
|
"learning_rate": 0.00011627493728420978, |
|
"loss": 0.329, |
|
"step": 208 |
|
}, |
|
{ |
|
"epoch": 1.82, |
|
"learning_rate": 0.00011557324087442717, |
|
"loss": 0.3222, |
|
"step": 209 |
|
}, |
|
{ |
|
"epoch": 1.83, |
|
"learning_rate": 0.00011487075772256517, |
|
"loss": 0.3411, |
|
"step": 210 |
|
}, |
|
{ |
|
"epoch": 1.84, |
|
"learning_rate": 0.00011416752331725842, |
|
"loss": 0.3322, |
|
"step": 211 |
|
}, |
|
{ |
|
"epoch": 1.85, |
|
"learning_rate": 0.00011346357318509395, |
|
"loss": 0.3202, |
|
"step": 212 |
|
}, |
|
{ |
|
"epoch": 1.85, |
|
"learning_rate": 0.00011275894288881663, |
|
"loss": 0.3354, |
|
"step": 213 |
|
}, |
|
{ |
|
"epoch": 1.86, |
|
"learning_rate": 0.0001120536680255323, |
|
"loss": 0.3454, |
|
"step": 214 |
|
}, |
|
{ |
|
"epoch": 1.87, |
|
"learning_rate": 0.0001113477842249097, |
|
"loss": 0.3376, |
|
"step": 215 |
|
}, |
|
{ |
|
"epoch": 1.88, |
|
"learning_rate": 0.00011064132714738024, |
|
"loss": 0.3206, |
|
"step": 216 |
|
}, |
|
{ |
|
"epoch": 1.89, |
|
"learning_rate": 0.00010993433248233671, |
|
"loss": 0.3258, |
|
"step": 217 |
|
}, |
|
{ |
|
"epoch": 1.9, |
|
"learning_rate": 0.00010922683594633021, |
|
"loss": 0.3376, |
|
"step": 218 |
|
}, |
|
{ |
|
"epoch": 1.91, |
|
"learning_rate": 0.00010851887328126568, |
|
"loss": 0.3194, |
|
"step": 219 |
|
}, |
|
{ |
|
"epoch": 1.92, |
|
"learning_rate": 0.00010781048025259648, |
|
"loss": 0.3117, |
|
"step": 220 |
|
}, |
|
{ |
|
"epoch": 1.93, |
|
"learning_rate": 0.00010710169264751732, |
|
"loss": 0.3225, |
|
"step": 221 |
|
}, |
|
{ |
|
"epoch": 1.93, |
|
"learning_rate": 0.00010639254627315657, |
|
"loss": 0.3347, |
|
"step": 222 |
|
}, |
|
{ |
|
"epoch": 1.94, |
|
"learning_rate": 0.00010568307695476711, |
|
"loss": 0.3274, |
|
"step": 223 |
|
}, |
|
{ |
|
"epoch": 1.95, |
|
"learning_rate": 0.00010497332053391668, |
|
"loss": 0.3219, |
|
"step": 224 |
|
}, |
|
{ |
|
"epoch": 1.96, |
|
"learning_rate": 0.00010426331286667701, |
|
"loss": 0.3272, |
|
"step": 225 |
|
}, |
|
{ |
|
"epoch": 1.97, |
|
"learning_rate": 0.00010355308982181253, |
|
"loss": 0.3246, |
|
"step": 226 |
|
}, |
|
{ |
|
"epoch": 1.98, |
|
"learning_rate": 0.00010284268727896833, |
|
"loss": 0.327, |
|
"step": 227 |
|
}, |
|
{ |
|
"epoch": 1.99, |
|
"learning_rate": 0.00010213214112685748, |
|
"loss": 0.3201, |
|
"step": 228 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"learning_rate": 0.00010142148726144807, |
|
"loss": 0.3097, |
|
"step": 229 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"learning_rate": 0.00010071076158414976, |
|
"loss": 0.3374, |
|
"step": 230 |
|
}, |
|
{ |
|
"epoch": 2.01, |
|
"learning_rate": 0.0001, |
|
"loss": 0.3394, |
|
"step": 231 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"learning_rate": 9.928923841585024e-05, |
|
"loss": 0.3216, |
|
"step": 232 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_loss": 0.3371301591396332, |
|
"eval_runtime": 35.0645, |
|
"eval_samples_per_second": 173.794, |
|
"eval_steps_per_second": 12.434, |
|
"step": 232 |
|
}, |
|
{ |
|
"epoch": 2.01, |
|
"learning_rate": 9.857851273855194e-05, |
|
"loss": 0.3184, |
|
"step": 233 |
|
}, |
|
{ |
|
"epoch": 2.02, |
|
"learning_rate": 9.786785887314255e-05, |
|
"loss": 0.3199, |
|
"step": 234 |
|
}, |
|
{ |
|
"epoch": 2.03, |
|
"learning_rate": 9.71573127210317e-05, |
|
"loss": 0.3188, |
|
"step": 235 |
|
}, |
|
{ |
|
"epoch": 2.04, |
|
"learning_rate": 9.644691017818752e-05, |
|
"loss": 0.3407, |
|
"step": 236 |
|
}, |
|
{ |
|
"epoch": 2.05, |
|
"learning_rate": 9.573668713332304e-05, |
|
"loss": 0.3226, |
|
"step": 237 |
|
}, |
|
{ |
|
"epoch": 2.06, |
|
"learning_rate": 9.502667946608333e-05, |
|
"loss": 0.319, |
|
"step": 238 |
|
}, |
|
{ |
|
"epoch": 2.07, |
|
"learning_rate": 9.431692304523288e-05, |
|
"loss": 0.3248, |
|
"step": 239 |
|
}, |
|
{ |
|
"epoch": 2.07, |
|
"learning_rate": 9.360745372684345e-05, |
|
"loss": 0.3303, |
|
"step": 240 |
|
}, |
|
{ |
|
"epoch": 2.08, |
|
"learning_rate": 9.289830735248269e-05, |
|
"loss": 0.3124, |
|
"step": 241 |
|
}, |
|
{ |
|
"epoch": 2.09, |
|
"learning_rate": 9.218951974740354e-05, |
|
"loss": 0.3197, |
|
"step": 242 |
|
}, |
|
{ |
|
"epoch": 2.1, |
|
"learning_rate": 9.148112671873433e-05, |
|
"loss": 0.3358, |
|
"step": 243 |
|
}, |
|
{ |
|
"epoch": 2.11, |
|
"learning_rate": 9.077316405366981e-05, |
|
"loss": 0.3216, |
|
"step": 244 |
|
}, |
|
{ |
|
"epoch": 2.12, |
|
"learning_rate": 9.00656675176633e-05, |
|
"loss": 0.3126, |
|
"step": 245 |
|
}, |
|
{ |
|
"epoch": 2.13, |
|
"learning_rate": 8.935867285261978e-05, |
|
"loss": 0.3327, |
|
"step": 246 |
|
}, |
|
{ |
|
"epoch": 2.14, |
|
"learning_rate": 8.865221577509033e-05, |
|
"loss": 0.3239, |
|
"step": 247 |
|
}, |
|
{ |
|
"epoch": 2.15, |
|
"learning_rate": 8.79463319744677e-05, |
|
"loss": 0.3237, |
|
"step": 248 |
|
}, |
|
{ |
|
"epoch": 2.15, |
|
"learning_rate": 8.724105711118342e-05, |
|
"loss": 0.3163, |
|
"step": 249 |
|
}, |
|
{ |
|
"epoch": 2.16, |
|
"learning_rate": 8.653642681490608e-05, |
|
"loss": 0.3323, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 2.17, |
|
"learning_rate": 8.583247668274163e-05, |
|
"loss": 0.303, |
|
"step": 251 |
|
}, |
|
{ |
|
"epoch": 2.18, |
|
"learning_rate": 8.512924227743481e-05, |
|
"loss": 0.3507, |
|
"step": 252 |
|
}, |
|
{ |
|
"epoch": 2.19, |
|
"learning_rate": 8.442675912557281e-05, |
|
"loss": 0.334, |
|
"step": 253 |
|
}, |
|
{ |
|
"epoch": 2.2, |
|
"learning_rate": 8.372506271579022e-05, |
|
"loss": 0.3144, |
|
"step": 254 |
|
}, |
|
{ |
|
"epoch": 2.21, |
|
"learning_rate": 8.302418849697638e-05, |
|
"loss": 0.3298, |
|
"step": 255 |
|
}, |
|
{ |
|
"epoch": 2.22, |
|
"learning_rate": 8.232417187648454e-05, |
|
"loss": 0.3229, |
|
"step": 256 |
|
}, |
|
{ |
|
"epoch": 2.22, |
|
"learning_rate": 8.162504821834295e-05, |
|
"loss": 0.2989, |
|
"step": 257 |
|
}, |
|
{ |
|
"epoch": 2.23, |
|
"learning_rate": 8.092685284146865e-05, |
|
"loss": 0.3165, |
|
"step": 258 |
|
}, |
|
{ |
|
"epoch": 2.24, |
|
"learning_rate": 8.02296210178828e-05, |
|
"loss": 0.3129, |
|
"step": 259 |
|
}, |
|
{ |
|
"epoch": 2.25, |
|
"learning_rate": 7.953338797092902e-05, |
|
"loss": 0.319, |
|
"step": 260 |
|
}, |
|
{ |
|
"epoch": 2.26, |
|
"learning_rate": 7.883818887349392e-05, |
|
"loss": 0.2961, |
|
"step": 261 |
|
}, |
|
{ |
|
"epoch": 2.26, |
|
"eval_loss": 0.3379780054092407, |
|
"eval_runtime": 35.0784, |
|
"eval_samples_per_second": 173.725, |
|
"eval_steps_per_second": 12.429, |
|
"step": 261 |
|
}, |
|
{ |
|
"epoch": 2.27, |
|
"learning_rate": 7.814405884623011e-05, |
|
"loss": 0.3, |
|
"step": 262 |
|
}, |
|
{ |
|
"epoch": 2.28, |
|
"learning_rate": 7.745103295578216e-05, |
|
"loss": 0.3133, |
|
"step": 263 |
|
}, |
|
{ |
|
"epoch": 2.29, |
|
"learning_rate": 7.675914621301476e-05, |
|
"loss": 0.3277, |
|
"step": 264 |
|
}, |
|
{ |
|
"epoch": 2.29, |
|
"learning_rate": 7.606843357124426e-05, |
|
"loss": 0.3142, |
|
"step": 265 |
|
}, |
|
{ |
|
"epoch": 2.3, |
|
"learning_rate": 7.537892992447273e-05, |
|
"loss": 0.3245, |
|
"step": 266 |
|
}, |
|
{ |
|
"epoch": 2.31, |
|
"learning_rate": 7.469067010562539e-05, |
|
"loss": 0.3393, |
|
"step": 267 |
|
}, |
|
{ |
|
"epoch": 2.32, |
|
"learning_rate": 7.400368888479048e-05, |
|
"loss": 0.3125, |
|
"step": 268 |
|
}, |
|
{ |
|
"epoch": 2.33, |
|
"learning_rate": 7.331802096746308e-05, |
|
"loss": 0.3083, |
|
"step": 269 |
|
}, |
|
{ |
|
"epoch": 2.34, |
|
"learning_rate": 7.263370099279172e-05, |
|
"loss": 0.3188, |
|
"step": 270 |
|
}, |
|
{ |
|
"epoch": 2.35, |
|
"learning_rate": 7.195076353182834e-05, |
|
"loss": 0.3071, |
|
"step": 271 |
|
}, |
|
{ |
|
"epoch": 2.36, |
|
"learning_rate": 7.126924308578196e-05, |
|
"loss": 0.3223, |
|
"step": 272 |
|
}, |
|
{ |
|
"epoch": 2.36, |
|
"learning_rate": 7.058917408427558e-05, |
|
"loss": 0.3201, |
|
"step": 273 |
|
}, |
|
{ |
|
"epoch": 2.37, |
|
"learning_rate": 6.991059088360699e-05, |
|
"loss": 0.3237, |
|
"step": 274 |
|
}, |
|
{ |
|
"epoch": 2.38, |
|
"learning_rate": 6.923352776501301e-05, |
|
"loss": 0.3172, |
|
"step": 275 |
|
}, |
|
{ |
|
"epoch": 2.39, |
|
"learning_rate": 6.855801893293765e-05, |
|
"loss": 0.3188, |
|
"step": 276 |
|
}, |
|
{ |
|
"epoch": 2.4, |
|
"learning_rate": 6.788409851330418e-05, |
|
"loss": 0.3268, |
|
"step": 277 |
|
}, |
|
{ |
|
"epoch": 2.41, |
|
"learning_rate": 6.721180055179112e-05, |
|
"loss": 0.3256, |
|
"step": 278 |
|
}, |
|
{ |
|
"epoch": 2.42, |
|
"learning_rate": 6.654115901211229e-05, |
|
"loss": 0.3216, |
|
"step": 279 |
|
}, |
|
{ |
|
"epoch": 2.43, |
|
"learning_rate": 6.587220777430096e-05, |
|
"loss": 0.3304, |
|
"step": 280 |
|
}, |
|
{ |
|
"epoch": 2.44, |
|
"learning_rate": 6.52049806329984e-05, |
|
"loss": 0.3246, |
|
"step": 281 |
|
}, |
|
{ |
|
"epoch": 2.44, |
|
"learning_rate": 6.453951129574644e-05, |
|
"loss": 0.3072, |
|
"step": 282 |
|
}, |
|
{ |
|
"epoch": 2.45, |
|
"learning_rate": 6.387583338128471e-05, |
|
"loss": 0.3169, |
|
"step": 283 |
|
}, |
|
{ |
|
"epoch": 2.46, |
|
"learning_rate": 6.321398041785224e-05, |
|
"loss": 0.3219, |
|
"step": 284 |
|
}, |
|
{ |
|
"epoch": 2.47, |
|
"learning_rate": 6.255398584149365e-05, |
|
"loss": 0.3529, |
|
"step": 285 |
|
}, |
|
{ |
|
"epoch": 2.48, |
|
"learning_rate": 6.189588299436997e-05, |
|
"loss": 0.3114, |
|
"step": 286 |
|
}, |
|
{ |
|
"epoch": 2.49, |
|
"learning_rate": 6.123970512307434e-05, |
|
"loss": 0.3205, |
|
"step": 287 |
|
}, |
|
{ |
|
"epoch": 2.5, |
|
"learning_rate": 6.0585485376952244e-05, |
|
"loss": 0.3113, |
|
"step": 288 |
|
}, |
|
{ |
|
"epoch": 2.51, |
|
"learning_rate": 5.993325680642705e-05, |
|
"loss": 0.3439, |
|
"step": 289 |
|
}, |
|
{ |
|
"epoch": 2.51, |
|
"learning_rate": 5.928305236133016e-05, |
|
"loss": 0.3117, |
|
"step": 290 |
|
}, |
|
{ |
|
"epoch": 2.51, |
|
"eval_loss": 0.3381350338459015, |
|
"eval_runtime": 35.0904, |
|
"eval_samples_per_second": 173.666, |
|
"eval_steps_per_second": 12.425, |
|
"step": 290 |
|
}, |
|
{ |
|
"epoch": 2.52, |
|
"learning_rate": 5.8634904889236595e-05, |
|
"loss": 0.3109, |
|
"step": 291 |
|
}, |
|
{ |
|
"epoch": 2.53, |
|
"learning_rate": 5.798884713380541e-05, |
|
"loss": 0.3154, |
|
"step": 292 |
|
}, |
|
{ |
|
"epoch": 2.54, |
|
"learning_rate": 5.7344911733125594e-05, |
|
"loss": 0.3407, |
|
"step": 293 |
|
}, |
|
{ |
|
"epoch": 2.55, |
|
"learning_rate": 5.67031312180673e-05, |
|
"loss": 0.3118, |
|
"step": 294 |
|
}, |
|
{ |
|
"epoch": 2.56, |
|
"learning_rate": 5.6063538010638293e-05, |
|
"loss": 0.3221, |
|
"step": 295 |
|
}, |
|
{ |
|
"epoch": 2.57, |
|
"learning_rate": 5.542616442234618e-05, |
|
"loss": 0.3153, |
|
"step": 296 |
|
}, |
|
{ |
|
"epoch": 2.58, |
|
"learning_rate": 5.479104265256583e-05, |
|
"loss": 0.3267, |
|
"step": 297 |
|
}, |
|
{ |
|
"epoch": 2.58, |
|
"learning_rate": 5.4158204786913005e-05, |
|
"loss": 0.3294, |
|
"step": 298 |
|
}, |
|
{ |
|
"epoch": 2.59, |
|
"learning_rate": 5.3527682795623146e-05, |
|
"loss": 0.3428, |
|
"step": 299 |
|
}, |
|
{ |
|
"epoch": 2.6, |
|
"learning_rate": 5.289950853193653e-05, |
|
"loss": 0.3342, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 2.61, |
|
"learning_rate": 5.227371373048888e-05, |
|
"loss": 0.3362, |
|
"step": 301 |
|
}, |
|
{ |
|
"epoch": 2.62, |
|
"learning_rate": 5.165033000570825e-05, |
|
"loss": 0.3542, |
|
"step": 302 |
|
}, |
|
{ |
|
"epoch": 2.63, |
|
"learning_rate": 5.102938885021793e-05, |
|
"loss": 0.3252, |
|
"step": 303 |
|
}, |
|
{ |
|
"epoch": 2.64, |
|
"learning_rate": 5.041092163324537e-05, |
|
"loss": 0.3205, |
|
"step": 304 |
|
}, |
|
{ |
|
"epoch": 2.65, |
|
"learning_rate": 4.979495959903759e-05, |
|
"loss": 0.3201, |
|
"step": 305 |
|
}, |
|
{ |
|
"epoch": 2.65, |
|
"learning_rate": 4.9181533865282706e-05, |
|
"loss": 0.3181, |
|
"step": 306 |
|
}, |
|
{ |
|
"epoch": 2.66, |
|
"learning_rate": 4.857067542153768e-05, |
|
"loss": 0.3116, |
|
"step": 307 |
|
}, |
|
{ |
|
"epoch": 2.67, |
|
"learning_rate": 4.796241512766326e-05, |
|
"loss": 0.3212, |
|
"step": 308 |
|
}, |
|
{ |
|
"epoch": 2.68, |
|
"learning_rate": 4.735678371226441e-05, |
|
"loss": 0.3267, |
|
"step": 309 |
|
}, |
|
{ |
|
"epoch": 2.69, |
|
"learning_rate": 4.6753811771138364e-05, |
|
"loss": 0.3027, |
|
"step": 310 |
|
}, |
|
{ |
|
"epoch": 2.7, |
|
"learning_rate": 4.6153529765728664e-05, |
|
"loss": 0.3068, |
|
"step": 311 |
|
}, |
|
{ |
|
"epoch": 2.71, |
|
"learning_rate": 4.555596802158653e-05, |
|
"loss": 0.3326, |
|
"step": 312 |
|
}, |
|
{ |
|
"epoch": 2.72, |
|
"learning_rate": 4.496115672683873e-05, |
|
"loss": 0.3259, |
|
"step": 313 |
|
}, |
|
{ |
|
"epoch": 2.73, |
|
"learning_rate": 4.4369125930662404e-05, |
|
"loss": 0.3211, |
|
"step": 314 |
|
}, |
|
{ |
|
"epoch": 2.73, |
|
"learning_rate": 4.3779905541767285e-05, |
|
"loss": 0.3174, |
|
"step": 315 |
|
}, |
|
{ |
|
"epoch": 2.74, |
|
"learning_rate": 4.3193525326884435e-05, |
|
"loss": 0.3151, |
|
"step": 316 |
|
}, |
|
{ |
|
"epoch": 2.75, |
|
"learning_rate": 4.261001490926272e-05, |
|
"loss": 0.3207, |
|
"step": 317 |
|
}, |
|
{ |
|
"epoch": 2.76, |
|
"learning_rate": 4.202940376717217e-05, |
|
"loss": 0.3101, |
|
"step": 318 |
|
}, |
|
{ |
|
"epoch": 2.77, |
|
"learning_rate": 4.14517212324147e-05, |
|
"loss": 0.3207, |
|
"step": 319 |
|
}, |
|
{ |
|
"epoch": 2.77, |
|
"eval_loss": 0.3378981053829193, |
|
"eval_runtime": 35.0668, |
|
"eval_samples_per_second": 173.782, |
|
"eval_steps_per_second": 12.433, |
|
"step": 319 |
|
}, |
|
{ |
|
"epoch": 2.78, |
|
"learning_rate": 4.087699648884248e-05, |
|
"loss": 0.3089, |
|
"step": 320 |
|
}, |
|
{ |
|
"epoch": 2.79, |
|
"learning_rate": 4.0305258570883334e-05, |
|
"loss": 0.3416, |
|
"step": 321 |
|
}, |
|
{ |
|
"epoch": 2.8, |
|
"learning_rate": 3.973653636207437e-05, |
|
"loss": 0.3072, |
|
"step": 322 |
|
}, |
|
{ |
|
"epoch": 2.8, |
|
"learning_rate": 3.9170858593602336e-05, |
|
"loss": 0.3364, |
|
"step": 323 |
|
}, |
|
{ |
|
"epoch": 2.81, |
|
"learning_rate": 3.860825384285247e-05, |
|
"loss": 0.3233, |
|
"step": 324 |
|
}, |
|
{ |
|
"epoch": 2.82, |
|
"learning_rate": 3.804875053196477e-05, |
|
"loss": 0.318, |
|
"step": 325 |
|
}, |
|
{ |
|
"epoch": 2.83, |
|
"learning_rate": 3.7492376926397964e-05, |
|
"loss": 0.319, |
|
"step": 326 |
|
}, |
|
{ |
|
"epoch": 2.84, |
|
"learning_rate": 3.693916113350182e-05, |
|
"loss": 0.324, |
|
"step": 327 |
|
}, |
|
{ |
|
"epoch": 2.85, |
|
"learning_rate": 3.638913110109695e-05, |
|
"loss": 0.3196, |
|
"step": 328 |
|
}, |
|
{ |
|
"epoch": 2.86, |
|
"learning_rate": 3.5842314616063135e-05, |
|
"loss": 0.3186, |
|
"step": 329 |
|
}, |
|
{ |
|
"epoch": 2.87, |
|
"learning_rate": 3.529873930293546e-05, |
|
"loss": 0.3073, |
|
"step": 330 |
|
}, |
|
{ |
|
"epoch": 2.87, |
|
"learning_rate": 3.4758432622508674e-05, |
|
"loss": 0.3427, |
|
"step": 331 |
|
}, |
|
{ |
|
"epoch": 2.88, |
|
"learning_rate": 3.422142187045011e-05, |
|
"loss": 0.3064, |
|
"step": 332 |
|
}, |
|
{ |
|
"epoch": 2.89, |
|
"learning_rate": 3.36877341759205e-05, |
|
"loss": 0.3278, |
|
"step": 333 |
|
}, |
|
{ |
|
"epoch": 2.9, |
|
"learning_rate": 3.315739650020365e-05, |
|
"loss": 0.347, |
|
"step": 334 |
|
}, |
|
{ |
|
"epoch": 2.91, |
|
"learning_rate": 3.263043563534428e-05, |
|
"loss": 0.3269, |
|
"step": 335 |
|
}, |
|
{ |
|
"epoch": 2.92, |
|
"learning_rate": 3.210687820279451e-05, |
|
"loss": 0.3122, |
|
"step": 336 |
|
}, |
|
{ |
|
"epoch": 2.93, |
|
"learning_rate": 3.1586750652069074e-05, |
|
"loss": 0.3223, |
|
"step": 337 |
|
}, |
|
{ |
|
"epoch": 2.94, |
|
"learning_rate": 3.107007925940894e-05, |
|
"loss": 0.3208, |
|
"step": 338 |
|
}, |
|
{ |
|
"epoch": 2.95, |
|
"learning_rate": 3.0556890126454075e-05, |
|
"loss": 0.3073, |
|
"step": 339 |
|
} |
|
], |
|
"logging_steps": 1, |
|
"max_steps": 452, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 4, |
|
"save_steps": 113, |
|
"total_flos": 1.5721793414108283e+19, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|