12057 lines
330 KiB
JSON
12057 lines
330 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.6924408540103866,
|
|
"eval_steps": 3000,
|
|
"global_step": 6000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 10.742519760131836,
|
|
"epoch": 0.0005770340450086555,
|
|
"grad_norm": 4.78125,
|
|
"learning_rate": 2e-06,
|
|
"loss": 10.7834,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 11955.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 10.742532062530518,
|
|
"epoch": 0.001154068090017311,
|
|
"grad_norm": 5.15625,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 10.7821,
|
|
"mean_token_accuracy": 7.552870083600282e-05,
|
|
"num_tokens": 24473.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 10.742538166046142,
|
|
"epoch": 0.0017311021350259665,
|
|
"grad_norm": 5.4375,
|
|
"learning_rate": 7e-06,
|
|
"loss": 10.7615,
|
|
"mean_token_accuracy": 0.00016723573207855225,
|
|
"num_tokens": 36716.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 10.742550373077393,
|
|
"epoch": 0.002308136180034622,
|
|
"grad_norm": 5.125,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 10.7088,
|
|
"mean_token_accuracy": 0.0010991264251060783,
|
|
"num_tokens": 49747.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 10.742451667785645,
|
|
"epoch": 0.0028851702250432777,
|
|
"grad_norm": 4.71875,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 10.6029,
|
|
"mean_token_accuracy": 0.01508477891329676,
|
|
"num_tokens": 61991.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 10.741979122161865,
|
|
"epoch": 0.003462204270051933,
|
|
"grad_norm": 3.875,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 10.4994,
|
|
"mean_token_accuracy": 0.0400444071739912,
|
|
"num_tokens": 74918.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 10.740076923370362,
|
|
"epoch": 0.004039238315060588,
|
|
"grad_norm": 3.109375,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 10.3732,
|
|
"mean_token_accuracy": 0.05369483157992363,
|
|
"num_tokens": 87833.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 10.733743858337402,
|
|
"epoch": 0.004616272360069244,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 10.2264,
|
|
"mean_token_accuracy": 0.0561745673418045,
|
|
"num_tokens": 101031.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 10.72265920639038,
|
|
"epoch": 0.0051933064050779,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 10.1107,
|
|
"mean_token_accuracy": 0.05086057800799608,
|
|
"num_tokens": 114085.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 10.712560367584228,
|
|
"epoch": 0.005770340450086555,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 10.0728,
|
|
"mean_token_accuracy": 0.05095174703747034,
|
|
"num_tokens": 126190.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 10.708724021911621,
|
|
"epoch": 0.006347374495095211,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 9.9872,
|
|
"mean_token_accuracy": 0.05040723979473114,
|
|
"num_tokens": 138933.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 10.705632781982422,
|
|
"epoch": 0.006924408540103866,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 9.9165,
|
|
"mean_token_accuracy": 0.05702933557331562,
|
|
"num_tokens": 150542.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 10.699434947967529,
|
|
"epoch": 0.0075014425851125215,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 9.9117,
|
|
"mean_token_accuracy": 0.05192887857556343,
|
|
"num_tokens": 163507.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 10.691042518615722,
|
|
"epoch": 0.008078476630121177,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 9.8663,
|
|
"mean_token_accuracy": 0.0556206401437521,
|
|
"num_tokens": 176668.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 10.68201036453247,
|
|
"epoch": 0.008655510675129832,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 9.8051,
|
|
"mean_token_accuracy": 0.05544878952205181,
|
|
"num_tokens": 191413.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 10.66737766265869,
|
|
"epoch": 0.009232544720138488,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 9.739,
|
|
"mean_token_accuracy": 0.06524630598723888,
|
|
"num_tokens": 204176.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 10.650106525421142,
|
|
"epoch": 0.009809578765147143,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 9.6842,
|
|
"mean_token_accuracy": 0.06752815209329129,
|
|
"num_tokens": 216851.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 10.636476421356202,
|
|
"epoch": 0.0103866128101558,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 9.6572,
|
|
"mean_token_accuracy": 0.0653569109737873,
|
|
"num_tokens": 229621.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 10.622958183288574,
|
|
"epoch": 0.010963646855164455,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 9.6025,
|
|
"mean_token_accuracy": 0.06540683954954148,
|
|
"num_tokens": 242074.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 10.592237091064453,
|
|
"epoch": 0.01154068090017311,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 9.474,
|
|
"mean_token_accuracy": 0.07080609016120434,
|
|
"num_tokens": 254094.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 10.51324234008789,
|
|
"epoch": 0.012117714945181766,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 9.4787,
|
|
"mean_token_accuracy": 0.07307280339300633,
|
|
"num_tokens": 267560.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 10.503196525573731,
|
|
"epoch": 0.012694748990190421,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 9.4426,
|
|
"mean_token_accuracy": 0.07156955860555173,
|
|
"num_tokens": 280717.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 10.523096179962158,
|
|
"epoch": 0.013271783035199077,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 9.3915,
|
|
"mean_token_accuracy": 0.07147992886602879,
|
|
"num_tokens": 293856.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 10.484137058258057,
|
|
"epoch": 0.013848817080207732,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 9.2251,
|
|
"mean_token_accuracy": 0.07240887582302094,
|
|
"num_tokens": 305191.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 10.420050239562988,
|
|
"epoch": 0.014425851125216388,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 9.2288,
|
|
"mean_token_accuracy": 0.07244622334837914,
|
|
"num_tokens": 318544.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 10.332412433624267,
|
|
"epoch": 0.015002885170225043,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 9.0584,
|
|
"mean_token_accuracy": 0.08713233023881913,
|
|
"num_tokens": 331445.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 10.288755512237548,
|
|
"epoch": 0.015579919215233698,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 9.0833,
|
|
"mean_token_accuracy": 0.07415068708360195,
|
|
"num_tokens": 344775.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 10.267962074279785,
|
|
"epoch": 0.016156953260242354,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 8.9864,
|
|
"mean_token_accuracy": 0.07388804033398629,
|
|
"num_tokens": 357804.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 10.174692630767822,
|
|
"epoch": 0.01673398730525101,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 8.8543,
|
|
"mean_token_accuracy": 0.08084411099553108,
|
|
"num_tokens": 369826.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 10.011744403839112,
|
|
"epoch": 0.017311021350259664,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 8.7823,
|
|
"mean_token_accuracy": 0.08401374593377113,
|
|
"num_tokens": 382768.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 9.914338493347168,
|
|
"epoch": 0.01788805539526832,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 8.7625,
|
|
"mean_token_accuracy": 0.08076213970780373,
|
|
"num_tokens": 395910.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 9.87332878112793,
|
|
"epoch": 0.018465089440276975,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 8.725,
|
|
"mean_token_accuracy": 0.07417598105967045,
|
|
"num_tokens": 408140.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 9.752376747131347,
|
|
"epoch": 0.019042123485285632,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 8.5835,
|
|
"mean_token_accuracy": 0.08260673955082894,
|
|
"num_tokens": 420486.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 9.501761531829834,
|
|
"epoch": 0.019619157530294286,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 8.5107,
|
|
"mean_token_accuracy": 0.09241977110505104,
|
|
"num_tokens": 433207.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 9.351601791381835,
|
|
"epoch": 0.020196191575302943,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 8.4638,
|
|
"mean_token_accuracy": 0.08450455963611603,
|
|
"num_tokens": 444880.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 9.297267818450928,
|
|
"epoch": 0.0207732256203116,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 8.4926,
|
|
"mean_token_accuracy": 0.08199871554970742,
|
|
"num_tokens": 456650.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 9.096736717224122,
|
|
"epoch": 0.021350259665320254,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 8.4572,
|
|
"mean_token_accuracy": 0.08327073007822036,
|
|
"num_tokens": 469667.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 9.029964542388916,
|
|
"epoch": 0.02192729371032891,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 8.3783,
|
|
"mean_token_accuracy": 0.09304521456360818,
|
|
"num_tokens": 481952.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 8.89255895614624,
|
|
"epoch": 0.022504327755337564,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 8.399,
|
|
"mean_token_accuracy": 0.09114565178751946,
|
|
"num_tokens": 494352.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 8.913476753234864,
|
|
"epoch": 0.02308136180034622,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 8.3105,
|
|
"mean_token_accuracy": 0.0925761379301548,
|
|
"num_tokens": 506937.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 8.781428337097168,
|
|
"epoch": 0.023658395845354875,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.000102,
|
|
"loss": 8.303,
|
|
"mean_token_accuracy": 0.0928865760564804,
|
|
"num_tokens": 519552.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 8.800222492218017,
|
|
"epoch": 0.024235429890363532,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 8.3412,
|
|
"mean_token_accuracy": 0.08962251469492913,
|
|
"num_tokens": 531359.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 8.806383419036866,
|
|
"epoch": 0.024812463935372186,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000107,
|
|
"loss": 8.3542,
|
|
"mean_token_accuracy": 0.09396427646279334,
|
|
"num_tokens": 544197.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 8.8606746673584,
|
|
"epoch": 0.025389497980380843,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 8.3106,
|
|
"mean_token_accuracy": 0.09081738814711571,
|
|
"num_tokens": 556818.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 8.742358875274657,
|
|
"epoch": 0.025966532025389497,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.000112,
|
|
"loss": 8.3253,
|
|
"mean_token_accuracy": 0.0934368498623371,
|
|
"num_tokens": 569363.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 8.80865125656128,
|
|
"epoch": 0.026543566070398154,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 8.3076,
|
|
"mean_token_accuracy": 0.09487870410084724,
|
|
"num_tokens": 581645.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 8.763648796081544,
|
|
"epoch": 0.027120600115406807,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 8.259,
|
|
"mean_token_accuracy": 0.08925148844718933,
|
|
"num_tokens": 593501.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 8.715390586853028,
|
|
"epoch": 0.027697634160415464,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 8.2462,
|
|
"mean_token_accuracy": 0.09425812289118767,
|
|
"num_tokens": 606328.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 8.573129081726075,
|
|
"epoch": 0.02827466820542412,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000122,
|
|
"loss": 8.1457,
|
|
"mean_token_accuracy": 0.1065749242901802,
|
|
"num_tokens": 619003.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 8.62852210998535,
|
|
"epoch": 0.028851702250432775,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 8.2725,
|
|
"mean_token_accuracy": 0.09227693155407905,
|
|
"num_tokens": 632910.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 8.616901016235351,
|
|
"epoch": 0.029428736295441432,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000127,
|
|
"loss": 8.2065,
|
|
"mean_token_accuracy": 0.09859882518649102,
|
|
"num_tokens": 645959.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 8.623135948181153,
|
|
"epoch": 0.030005770340450086,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 8.1911,
|
|
"mean_token_accuracy": 0.10357227995991707,
|
|
"num_tokens": 658620.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 8.548318576812743,
|
|
"epoch": 0.030582804385458743,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000132,
|
|
"loss": 8.1897,
|
|
"mean_token_accuracy": 0.10186770558357239,
|
|
"num_tokens": 670804.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 8.512144851684571,
|
|
"epoch": 0.031159838430467397,
|
|
"grad_norm": 0.75,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 8.191,
|
|
"mean_token_accuracy": 0.09745052307844163,
|
|
"num_tokens": 683656.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 8.583205032348634,
|
|
"epoch": 0.031736872475476054,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 8.1635,
|
|
"mean_token_accuracy": 0.10382118448615074,
|
|
"num_tokens": 696629.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 8.513082599639892,
|
|
"epoch": 0.03231390652048471,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 8.1849,
|
|
"mean_token_accuracy": 0.0984301395714283,
|
|
"num_tokens": 709053.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 8.52897834777832,
|
|
"epoch": 0.03289094056549336,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 8.1378,
|
|
"mean_token_accuracy": 0.101743233948946,
|
|
"num_tokens": 721947.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 8.485254192352295,
|
|
"epoch": 0.03346797461050202,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 8.1318,
|
|
"mean_token_accuracy": 0.10095292180776597,
|
|
"num_tokens": 734495.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 8.4556489944458,
|
|
"epoch": 0.034045008655510675,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000147,
|
|
"loss": 8.1574,
|
|
"mean_token_accuracy": 0.09864982217550278,
|
|
"num_tokens": 746965.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 8.541684627532959,
|
|
"epoch": 0.03462204270051933,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 8.1759,
|
|
"mean_token_accuracy": 0.09848161116242408,
|
|
"num_tokens": 760105.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 8.439905643463135,
|
|
"epoch": 0.03519907674552799,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000152,
|
|
"loss": 8.0742,
|
|
"mean_token_accuracy": 0.1082187220454216,
|
|
"num_tokens": 771765.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 8.54954652786255,
|
|
"epoch": 0.03577611079053664,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 8.1565,
|
|
"mean_token_accuracy": 0.10081454515457153,
|
|
"num_tokens": 784895.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 8.430934238433839,
|
|
"epoch": 0.0363531448355453,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000157,
|
|
"loss": 8.0908,
|
|
"mean_token_accuracy": 0.10850713253021241,
|
|
"num_tokens": 797139.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 8.501363563537598,
|
|
"epoch": 0.03693017888055395,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 8.0515,
|
|
"mean_token_accuracy": 0.11537543162703515,
|
|
"num_tokens": 809169.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 8.328963375091552,
|
|
"epoch": 0.03750721292556261,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000162,
|
|
"loss": 8.1059,
|
|
"mean_token_accuracy": 0.10505361780524254,
|
|
"num_tokens": 821737.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 8.49581003189087,
|
|
"epoch": 0.038084246970571264,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 8.019,
|
|
"mean_token_accuracy": 0.1122775912284851,
|
|
"num_tokens": 834365.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 8.393208026885986,
|
|
"epoch": 0.03866128101557992,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 8.0675,
|
|
"mean_token_accuracy": 0.10942035019397736,
|
|
"num_tokens": 846445.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 8.460633182525635,
|
|
"epoch": 0.03923831506058857,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 8.1142,
|
|
"mean_token_accuracy": 0.10697392895817756,
|
|
"num_tokens": 858558.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 8.396363449096679,
|
|
"epoch": 0.03981534910559723,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 8.1058,
|
|
"mean_token_accuracy": 0.10723683908581734,
|
|
"num_tokens": 871209.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 8.491197395324708,
|
|
"epoch": 0.040392383150605886,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 8.0555,
|
|
"mean_token_accuracy": 0.10949232503771782,
|
|
"num_tokens": 883270.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 8.352670478820801,
|
|
"epoch": 0.04096941719561454,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000177,
|
|
"loss": 8.0601,
|
|
"mean_token_accuracy": 0.10984272882342339,
|
|
"num_tokens": 895468.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 8.47718162536621,
|
|
"epoch": 0.0415464512406232,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 8.0213,
|
|
"mean_token_accuracy": 0.11185759902000428,
|
|
"num_tokens": 907900.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 8.211096382141113,
|
|
"epoch": 0.042123485285631854,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000182,
|
|
"loss": 8.0331,
|
|
"mean_token_accuracy": 0.11285770758986473,
|
|
"num_tokens": 920036.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 8.389335536956787,
|
|
"epoch": 0.04270051933064051,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 7.9946,
|
|
"mean_token_accuracy": 0.11674289256334305,
|
|
"num_tokens": 932525.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 8.290297317504884,
|
|
"epoch": 0.04327755337564916,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000187,
|
|
"loss": 7.9705,
|
|
"mean_token_accuracy": 0.11729388907551766,
|
|
"num_tokens": 943581.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 8.457341861724853,
|
|
"epoch": 0.04385458742065782,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 8.0767,
|
|
"mean_token_accuracy": 0.10796716287732125,
|
|
"num_tokens": 956270.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 8.334104824066163,
|
|
"epoch": 0.044431621465666475,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000192,
|
|
"loss": 8.0281,
|
|
"mean_token_accuracy": 0.11211411207914353,
|
|
"num_tokens": 967631.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 8.407048511505128,
|
|
"epoch": 0.04500865551067513,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 8.037,
|
|
"mean_token_accuracy": 0.10723293125629425,
|
|
"num_tokens": 980999.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 8.267741298675537,
|
|
"epoch": 0.04558568955568378,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 7.9457,
|
|
"mean_token_accuracy": 0.11497977301478386,
|
|
"num_tokens": 993404.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 8.311189937591553,
|
|
"epoch": 0.04616272360069244,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 7.959,
|
|
"mean_token_accuracy": 0.11699348911643029,
|
|
"num_tokens": 1006009.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 8.301223659515381,
|
|
"epoch": 0.0467397576457011,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000202,
|
|
"loss": 8.0537,
|
|
"mean_token_accuracy": 0.1106877088546753,
|
|
"num_tokens": 1019644.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 8.281110191345215,
|
|
"epoch": 0.04731679169070975,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 7.9529,
|
|
"mean_token_accuracy": 0.12168486937880515,
|
|
"num_tokens": 1032196.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 8.194720458984374,
|
|
"epoch": 0.04789382573571841,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000207,
|
|
"loss": 7.9104,
|
|
"mean_token_accuracy": 0.12571991384029388,
|
|
"num_tokens": 1044211.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 8.374266242980957,
|
|
"epoch": 0.048470859780727064,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 7.9692,
|
|
"mean_token_accuracy": 0.11775951310992241,
|
|
"num_tokens": 1055743.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 8.280481624603272,
|
|
"epoch": 0.04904789382573572,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.000212,
|
|
"loss": 7.9728,
|
|
"mean_token_accuracy": 0.11407571211457253,
|
|
"num_tokens": 1068550.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 8.259190368652344,
|
|
"epoch": 0.04962492787074437,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 7.876,
|
|
"mean_token_accuracy": 0.12458330690860749,
|
|
"num_tokens": 1079878.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 8.264352798461914,
|
|
"epoch": 0.05020196191575303,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 7.9461,
|
|
"mean_token_accuracy": 0.11022370159626008,
|
|
"num_tokens": 1093331.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 8.320549201965331,
|
|
"epoch": 0.050778995960761686,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 7.8988,
|
|
"mean_token_accuracy": 0.12245648875832557,
|
|
"num_tokens": 1105830.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 8.242807865142822,
|
|
"epoch": 0.05135603000577034,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000222,
|
|
"loss": 7.9022,
|
|
"mean_token_accuracy": 0.1231141023337841,
|
|
"num_tokens": 1118071.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 8.150061178207398,
|
|
"epoch": 0.05193306405077899,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 7.9205,
|
|
"mean_token_accuracy": 0.11648782640695572,
|
|
"num_tokens": 1129781.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 8.264570999145509,
|
|
"epoch": 0.052510098095787654,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 7.9593,
|
|
"mean_token_accuracy": 0.11766693964600564,
|
|
"num_tokens": 1142750.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 8.244252777099609,
|
|
"epoch": 0.05308713214079631,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 7.8898,
|
|
"mean_token_accuracy": 0.11929678991436958,
|
|
"num_tokens": 1154314.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 8.212209606170655,
|
|
"epoch": 0.05366416618580496,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 7.9087,
|
|
"mean_token_accuracy": 0.12657537683844566,
|
|
"num_tokens": 1167199.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 8.202026081085204,
|
|
"epoch": 0.054241200230813615,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 7.8846,
|
|
"mean_token_accuracy": 0.12224558740854263,
|
|
"num_tokens": 1179654.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 8.187808513641357,
|
|
"epoch": 0.054818234275822275,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000237,
|
|
"loss": 7.867,
|
|
"mean_token_accuracy": 0.12207963541150094,
|
|
"num_tokens": 1190713.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 8.158800506591797,
|
|
"epoch": 0.05539526832083093,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 7.8509,
|
|
"mean_token_accuracy": 0.12055787444114685,
|
|
"num_tokens": 1203881.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 8.259974384307862,
|
|
"epoch": 0.05597230236583958,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000242,
|
|
"loss": 7.9146,
|
|
"mean_token_accuracy": 0.11428983137011528,
|
|
"num_tokens": 1215795.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 8.06658124923706,
|
|
"epoch": 0.05654933641084824,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 7.8294,
|
|
"mean_token_accuracy": 0.12558024376630783,
|
|
"num_tokens": 1227773.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 8.268111038208009,
|
|
"epoch": 0.0571263704558569,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000247,
|
|
"loss": 7.8281,
|
|
"mean_token_accuracy": 0.12732664570212365,
|
|
"num_tokens": 1240217.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 8.184942293167115,
|
|
"epoch": 0.05770340450086555,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 7.8963,
|
|
"mean_token_accuracy": 0.12094444781541824,
|
|
"num_tokens": 1253324.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 8.097318315505982,
|
|
"epoch": 0.058280438545874204,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000252,
|
|
"loss": 7.8021,
|
|
"mean_token_accuracy": 0.11756076738238334,
|
|
"num_tokens": 1266007.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 8.119937992095947,
|
|
"epoch": 0.058857472590882864,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 7.8449,
|
|
"mean_token_accuracy": 0.12364009171724319,
|
|
"num_tokens": 1278403.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 8.165720081329345,
|
|
"epoch": 0.05943450663589152,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000257,
|
|
"loss": 7.8565,
|
|
"mean_token_accuracy": 0.12108651399612427,
|
|
"num_tokens": 1290352.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 8.166333532333374,
|
|
"epoch": 0.06001154068090017,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 7.8677,
|
|
"mean_token_accuracy": 0.11767618358135223,
|
|
"num_tokens": 1302304.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 8.154673862457276,
|
|
"epoch": 0.060588574725908825,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000262,
|
|
"loss": 7.8293,
|
|
"mean_token_accuracy": 0.1254723496735096,
|
|
"num_tokens": 1314014.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 8.189765071868896,
|
|
"epoch": 0.061165608770917486,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 7.8617,
|
|
"mean_token_accuracy": 0.11876866742968559,
|
|
"num_tokens": 1326751.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 8.086573696136474,
|
|
"epoch": 0.06174264281592614,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 7.7429,
|
|
"mean_token_accuracy": 0.1276994377374649,
|
|
"num_tokens": 1339070.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 8.00021333694458,
|
|
"epoch": 0.06231967686093479,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 7.7617,
|
|
"mean_token_accuracy": 0.12492593899369239,
|
|
"num_tokens": 1351345.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 8.155957984924317,
|
|
"epoch": 0.06289671090594345,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 7.8454,
|
|
"mean_token_accuracy": 0.11729749515652657,
|
|
"num_tokens": 1364331.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 7.948654079437256,
|
|
"epoch": 0.06347374495095211,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 7.7274,
|
|
"mean_token_accuracy": 0.1307520568370819,
|
|
"num_tokens": 1377426.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 8.21699333190918,
|
|
"epoch": 0.06405077899596076,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000277,
|
|
"loss": 7.8456,
|
|
"mean_token_accuracy": 0.11890435740351676,
|
|
"num_tokens": 1391553.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 8.080363225936889,
|
|
"epoch": 0.06462781304096941,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 7.83,
|
|
"mean_token_accuracy": 0.12511808127164842,
|
|
"num_tokens": 1405526.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 8.142201614379882,
|
|
"epoch": 0.06520484708597807,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 7.8219,
|
|
"mean_token_accuracy": 0.12369688302278518,
|
|
"num_tokens": 1417868.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 7.928612327575683,
|
|
"epoch": 0.06578188113098672,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 7.7407,
|
|
"mean_token_accuracy": 0.12715482115745544,
|
|
"num_tokens": 1429907.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 8.15863070487976,
|
|
"epoch": 0.06635891517599539,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000287,
|
|
"loss": 7.751,
|
|
"mean_token_accuracy": 0.12095296233892441,
|
|
"num_tokens": 1442552.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 8.045605039596557,
|
|
"epoch": 0.06693594922100404,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 7.8095,
|
|
"mean_token_accuracy": 0.12216803878545761,
|
|
"num_tokens": 1455717.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 8.157436180114747,
|
|
"epoch": 0.0675129832660127,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000292,
|
|
"loss": 7.8052,
|
|
"mean_token_accuracy": 0.11941280439496041,
|
|
"num_tokens": 1468263.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 7.988013124465942,
|
|
"epoch": 0.06809001731102135,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 7.7479,
|
|
"mean_token_accuracy": 0.12465541884303093,
|
|
"num_tokens": 1481632.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 8.01614761352539,
|
|
"epoch": 0.06866705135603,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000297,
|
|
"loss": 7.7005,
|
|
"mean_token_accuracy": 0.12634204924106598,
|
|
"num_tokens": 1495121.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 7.969437456130981,
|
|
"epoch": 0.06924408540103866,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 7.7509,
|
|
"mean_token_accuracy": 0.1271022602915764,
|
|
"num_tokens": 1507669.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 8.026603889465331,
|
|
"epoch": 0.06982111944604731,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000302,
|
|
"loss": 7.7853,
|
|
"mean_token_accuracy": 0.12059543505311013,
|
|
"num_tokens": 1520707.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 7.99562668800354,
|
|
"epoch": 0.07039815349105598,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 7.696,
|
|
"mean_token_accuracy": 0.12601862624287605,
|
|
"num_tokens": 1532974.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 7.974084091186524,
|
|
"epoch": 0.07097518753606463,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000307,
|
|
"loss": 7.682,
|
|
"mean_token_accuracy": 0.12723494321107864,
|
|
"num_tokens": 1544085.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 7.9744525909423825,
|
|
"epoch": 0.07155222158107329,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 7.7045,
|
|
"mean_token_accuracy": 0.1308353565633297,
|
|
"num_tokens": 1556945.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 7.941751766204834,
|
|
"epoch": 0.07212925562608194,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000312,
|
|
"loss": 7.6518,
|
|
"mean_token_accuracy": 0.13126163482666015,
|
|
"num_tokens": 1569570.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 7.943236637115478,
|
|
"epoch": 0.0727062896710906,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 7.7317,
|
|
"mean_token_accuracy": 0.12612373903393745,
|
|
"num_tokens": 1582529.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 7.964515161514282,
|
|
"epoch": 0.07328332371609925,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000317,
|
|
"loss": 7.6504,
|
|
"mean_token_accuracy": 0.13465792536735535,
|
|
"num_tokens": 1595976.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 7.939415836334229,
|
|
"epoch": 0.0738603577611079,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 7.6945,
|
|
"mean_token_accuracy": 0.12841632589697838,
|
|
"num_tokens": 1609093.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 7.928447484970093,
|
|
"epoch": 0.07443739180611655,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000322,
|
|
"loss": 7.6804,
|
|
"mean_token_accuracy": 0.12497531697154045,
|
|
"num_tokens": 1622233.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 8.020674419403075,
|
|
"epoch": 0.07501442585112522,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 7.728,
|
|
"mean_token_accuracy": 0.1262144438922405,
|
|
"num_tokens": 1635354.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 7.9559979915618895,
|
|
"epoch": 0.07559145989613388,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 7.7083,
|
|
"mean_token_accuracy": 0.12276372462511062,
|
|
"num_tokens": 1648223.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 7.932180786132813,
|
|
"epoch": 0.07616849394114253,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 7.695,
|
|
"mean_token_accuracy": 0.12331497594714165,
|
|
"num_tokens": 1661652.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 7.91778302192688,
|
|
"epoch": 0.07674552798615118,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 7.598,
|
|
"mean_token_accuracy": 0.13565101027488707,
|
|
"num_tokens": 1674778.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 7.959203672409058,
|
|
"epoch": 0.07732256203115984,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 7.6853,
|
|
"mean_token_accuracy": 0.1240819051861763,
|
|
"num_tokens": 1686966.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 7.902504253387451,
|
|
"epoch": 0.07789959607616849,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000337,
|
|
"loss": 7.6563,
|
|
"mean_token_accuracy": 0.13484344854950905,
|
|
"num_tokens": 1699979.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 7.8624763011932375,
|
|
"epoch": 0.07847663012117714,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 7.5949,
|
|
"mean_token_accuracy": 0.12701699286699294,
|
|
"num_tokens": 1712306.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 7.84359302520752,
|
|
"epoch": 0.07905366416618581,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000342,
|
|
"loss": 7.6427,
|
|
"mean_token_accuracy": 0.12926456406712533,
|
|
"num_tokens": 1724670.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 7.9609299659729,
|
|
"epoch": 0.07963069821119446,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 7.7196,
|
|
"mean_token_accuracy": 0.12713819071650506,
|
|
"num_tokens": 1736987.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 7.934039688110351,
|
|
"epoch": 0.08020773225620312,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000347,
|
|
"loss": 7.6931,
|
|
"mean_token_accuracy": 0.126790152490139,
|
|
"num_tokens": 1750587.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 7.82976803779602,
|
|
"epoch": 0.08078476630121177,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 7.6356,
|
|
"mean_token_accuracy": 0.12186335176229476,
|
|
"num_tokens": 1763432.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 7.907923984527588,
|
|
"epoch": 0.08136180034622043,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000352,
|
|
"loss": 7.5615,
|
|
"mean_token_accuracy": 0.13086110800504686,
|
|
"num_tokens": 1777705.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 7.8514200210571286,
|
|
"epoch": 0.08193883439122908,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 7.6198,
|
|
"mean_token_accuracy": 0.13134256303310393,
|
|
"num_tokens": 1790673.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 7.8153650760650635,
|
|
"epoch": 0.08251586843623773,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000357,
|
|
"loss": 7.6619,
|
|
"mean_token_accuracy": 0.12541591748595238,
|
|
"num_tokens": 1803258.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 7.950216341018677,
|
|
"epoch": 0.0830929024812464,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 7.6293,
|
|
"mean_token_accuracy": 0.12917107716202736,
|
|
"num_tokens": 1816534.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 7.836187028884888,
|
|
"epoch": 0.08366993652625505,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000362,
|
|
"loss": 7.5809,
|
|
"mean_token_accuracy": 0.12518987879157067,
|
|
"num_tokens": 1828335.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 7.771939277648926,
|
|
"epoch": 0.08424697057126371,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 7.5899,
|
|
"mean_token_accuracy": 0.134027336537838,
|
|
"num_tokens": 1839327.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 7.924041652679444,
|
|
"epoch": 0.08482400461627236,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000367,
|
|
"loss": 7.6636,
|
|
"mean_token_accuracy": 0.12406575530767441,
|
|
"num_tokens": 1851168.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 7.836169338226318,
|
|
"epoch": 0.08540103866128101,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 7.6255,
|
|
"mean_token_accuracy": 0.1251351036131382,
|
|
"num_tokens": 1863875.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 7.870956707000732,
|
|
"epoch": 0.08597807270628967,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000372,
|
|
"loss": 7.5523,
|
|
"mean_token_accuracy": 0.12497681528329849,
|
|
"num_tokens": 1876613.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 7.877524900436401,
|
|
"epoch": 0.08655510675129832,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 7.6508,
|
|
"mean_token_accuracy": 0.12530745193362236,
|
|
"num_tokens": 1890311.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 7.7698094844818115,
|
|
"epoch": 0.08713214079630698,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000377,
|
|
"loss": 7.6137,
|
|
"mean_token_accuracy": 0.12359317764639854,
|
|
"num_tokens": 1902925.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 7.891464757919311,
|
|
"epoch": 0.08770917484131564,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 7.5955,
|
|
"mean_token_accuracy": 0.12298363819718361,
|
|
"num_tokens": 1915186.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 7.836678600311279,
|
|
"epoch": 0.0882862088863243,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000382,
|
|
"loss": 7.5912,
|
|
"mean_token_accuracy": 0.1303836189210415,
|
|
"num_tokens": 1927184.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 7.795164489746094,
|
|
"epoch": 0.08886324293133295,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 7.5682,
|
|
"mean_token_accuracy": 0.1343364216387272,
|
|
"num_tokens": 1940275.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 7.860983610153198,
|
|
"epoch": 0.0894402769763416,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 7.6057,
|
|
"mean_token_accuracy": 0.1272793047130108,
|
|
"num_tokens": 1952583.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 7.830558156967163,
|
|
"epoch": 0.09001731102135026,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 7.5118,
|
|
"mean_token_accuracy": 0.12738451659679412,
|
|
"num_tokens": 1965219.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 7.71030740737915,
|
|
"epoch": 0.09059434506635891,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 7.5456,
|
|
"mean_token_accuracy": 0.13100098669528962,
|
|
"num_tokens": 1977193.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 7.909699869155884,
|
|
"epoch": 0.09117137911136756,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 7.4505,
|
|
"mean_token_accuracy": 0.13711674883961678,
|
|
"num_tokens": 1988955.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 7.730215835571289,
|
|
"epoch": 0.09174841315637623,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 7.5988,
|
|
"mean_token_accuracy": 0.12491806000471115,
|
|
"num_tokens": 2001647.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 7.779358577728272,
|
|
"epoch": 0.09232544720138489,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 7.5131,
|
|
"mean_token_accuracy": 0.13641507402062417,
|
|
"num_tokens": 2015185.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 7.82036943435669,
|
|
"epoch": 0.09290248124639354,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000402,
|
|
"loss": 7.6135,
|
|
"mean_token_accuracy": 0.12739918157458305,
|
|
"num_tokens": 2027257.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 7.603882265090943,
|
|
"epoch": 0.0934795152914022,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 7.4517,
|
|
"mean_token_accuracy": 0.13969765827059746,
|
|
"num_tokens": 2040716.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 7.850926303863526,
|
|
"epoch": 0.09405654933641085,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 7.5796,
|
|
"mean_token_accuracy": 0.12389181852340699,
|
|
"num_tokens": 2053240.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 7.774610376358032,
|
|
"epoch": 0.0946335833814195,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 7.5473,
|
|
"mean_token_accuracy": 0.12548824697732924,
|
|
"num_tokens": 2065693.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 7.716372299194336,
|
|
"epoch": 0.09521061742642815,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000412,
|
|
"loss": 7.5014,
|
|
"mean_token_accuracy": 0.1397644318640232,
|
|
"num_tokens": 2077649.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 7.756848621368408,
|
|
"epoch": 0.09578765147143682,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 7.5233,
|
|
"mean_token_accuracy": 0.1290776789188385,
|
|
"num_tokens": 2090780.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 7.749186420440674,
|
|
"epoch": 0.09636468551644548,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000417,
|
|
"loss": 7.5311,
|
|
"mean_token_accuracy": 0.13137806951999664,
|
|
"num_tokens": 2104096.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 7.7773672580719,
|
|
"epoch": 0.09694171956145413,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 7.527,
|
|
"mean_token_accuracy": 0.12679293751716614,
|
|
"num_tokens": 2117157.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 7.73278284072876,
|
|
"epoch": 0.09751875360646278,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000422,
|
|
"loss": 7.4858,
|
|
"mean_token_accuracy": 0.12687554210424423,
|
|
"num_tokens": 2129309.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 7.768968677520752,
|
|
"epoch": 0.09809578765147144,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 7.5307,
|
|
"mean_token_accuracy": 0.13160400986671447,
|
|
"num_tokens": 2142344.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 7.714959239959716,
|
|
"epoch": 0.09867282169648009,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000427,
|
|
"loss": 7.5686,
|
|
"mean_token_accuracy": 0.1227949745953083,
|
|
"num_tokens": 2155059.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 7.734045362472534,
|
|
"epoch": 0.09924985574148874,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 7.567,
|
|
"mean_token_accuracy": 0.12749878615140914,
|
|
"num_tokens": 2168901.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 7.731997871398926,
|
|
"epoch": 0.0998268897864974,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000432,
|
|
"loss": 7.3702,
|
|
"mean_token_accuracy": 0.14134701043367387,
|
|
"num_tokens": 2180953.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 7.591903018951416,
|
|
"epoch": 0.10040392383150606,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 7.4942,
|
|
"mean_token_accuracy": 0.1371511548757553,
|
|
"num_tokens": 2194097.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 7.695831298828125,
|
|
"epoch": 0.10098095787651472,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000437,
|
|
"loss": 7.4334,
|
|
"mean_token_accuracy": 0.13365770354866982,
|
|
"num_tokens": 2206475.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 7.78225154876709,
|
|
"epoch": 0.10155799192152337,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 7.4645,
|
|
"mean_token_accuracy": 0.1278185375034809,
|
|
"num_tokens": 2220006.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 7.65887417793274,
|
|
"epoch": 0.10213502596653203,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000442,
|
|
"loss": 7.5351,
|
|
"mean_token_accuracy": 0.12350780516862869,
|
|
"num_tokens": 2234082.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 7.669657945632935,
|
|
"epoch": 0.10271206001154068,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 7.5227,
|
|
"mean_token_accuracy": 0.12489003017544746,
|
|
"num_tokens": 2246871.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 7.669128274917602,
|
|
"epoch": 0.10328909405654933,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.000447,
|
|
"loss": 7.4567,
|
|
"mean_token_accuracy": 0.13411386385560037,
|
|
"num_tokens": 2260172.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 7.77032732963562,
|
|
"epoch": 0.10386612810155799,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 7.5057,
|
|
"mean_token_accuracy": 0.11949166432023048,
|
|
"num_tokens": 2272848.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 7.673234939575195,
|
|
"epoch": 0.10444316214656665,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 7.452,
|
|
"mean_token_accuracy": 0.12722696289420127,
|
|
"num_tokens": 2285673.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 7.741328477859497,
|
|
"epoch": 0.10502019619157531,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 7.489,
|
|
"mean_token_accuracy": 0.12697241380810736,
|
|
"num_tokens": 2298459.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 7.641606569290161,
|
|
"epoch": 0.10559723023658396,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 7.448,
|
|
"mean_token_accuracy": 0.13017196208238602,
|
|
"num_tokens": 2311226.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 7.574088287353516,
|
|
"epoch": 0.10617426428159261,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 7.3847,
|
|
"mean_token_accuracy": 0.1277943417429924,
|
|
"num_tokens": 2323481.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 7.646576309204102,
|
|
"epoch": 0.10675129832660127,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000462,
|
|
"loss": 7.414,
|
|
"mean_token_accuracy": 0.1307280629873276,
|
|
"num_tokens": 2336181.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 7.636479043960572,
|
|
"epoch": 0.10732833237160992,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 7.3716,
|
|
"mean_token_accuracy": 0.13296475633978844,
|
|
"num_tokens": 2348941.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 7.661097192764283,
|
|
"epoch": 0.10790536641661858,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000467,
|
|
"loss": 7.3294,
|
|
"mean_token_accuracy": 0.12712401077151297,
|
|
"num_tokens": 2361618.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 7.540031290054321,
|
|
"epoch": 0.10848240046162723,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 7.2806,
|
|
"mean_token_accuracy": 0.14269692525267602,
|
|
"num_tokens": 2376108.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 7.573352289199829,
|
|
"epoch": 0.1090594345066359,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000472,
|
|
"loss": 7.382,
|
|
"mean_token_accuracy": 0.13606224954128265,
|
|
"num_tokens": 2387774.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 7.616125917434692,
|
|
"epoch": 0.10963646855164455,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 7.4187,
|
|
"mean_token_accuracy": 0.13490517437458038,
|
|
"num_tokens": 2400816.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 7.538399982452392,
|
|
"epoch": 0.1102135025966532,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000477,
|
|
"loss": 7.3513,
|
|
"mean_token_accuracy": 0.13397277891635895,
|
|
"num_tokens": 2412970.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 7.531917762756348,
|
|
"epoch": 0.11079053664166186,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 7.3595,
|
|
"mean_token_accuracy": 0.13522982075810433,
|
|
"num_tokens": 2424622.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 7.65097861289978,
|
|
"epoch": 0.11136757068667051,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.000482,
|
|
"loss": 7.4384,
|
|
"mean_token_accuracy": 0.13235584348440171,
|
|
"num_tokens": 2437293.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 7.556930351257324,
|
|
"epoch": 0.11194460473167916,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 7.3101,
|
|
"mean_token_accuracy": 0.13271362110972404,
|
|
"num_tokens": 2449934.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 7.62783989906311,
|
|
"epoch": 0.11252163877668782,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000487,
|
|
"loss": 7.3979,
|
|
"mean_token_accuracy": 0.12683349400758742,
|
|
"num_tokens": 2463139.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 7.5757801055908205,
|
|
"epoch": 0.11309867282169649,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 7.4281,
|
|
"mean_token_accuracy": 0.1270056739449501,
|
|
"num_tokens": 2474273.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 7.627140283584595,
|
|
"epoch": 0.11367570686670514,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000492,
|
|
"loss": 7.381,
|
|
"mean_token_accuracy": 0.1371190808713436,
|
|
"num_tokens": 2486643.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 7.516345596313476,
|
|
"epoch": 0.1142527409117138,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 7.3769,
|
|
"mean_token_accuracy": 0.12875159829854965,
|
|
"num_tokens": 2499018.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 7.49490532875061,
|
|
"epoch": 0.11482977495672245,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000497,
|
|
"loss": 7.3419,
|
|
"mean_token_accuracy": 0.1379355698823929,
|
|
"num_tokens": 2510463.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 7.580066394805908,
|
|
"epoch": 0.1154068090017311,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 7.3689,
|
|
"mean_token_accuracy": 0.13574447557330133,
|
|
"num_tokens": 2522671.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 7.525820398330689,
|
|
"epoch": 0.11598384304673975,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999999975783157,
|
|
"loss": 7.3706,
|
|
"mean_token_accuracy": 0.1312769442796707,
|
|
"num_tokens": 2534508.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 7.571441793441773,
|
|
"epoch": 0.11656087709174841,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999999877402236,
|
|
"loss": 7.3274,
|
|
"mean_token_accuracy": 0.13784680590033532,
|
|
"num_tokens": 2546804.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 7.521267461776733,
|
|
"epoch": 0.11713791113675708,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004999999703343686,
|
|
"loss": 7.3429,
|
|
"mean_token_accuracy": 0.13090137392282486,
|
|
"num_tokens": 2558786.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 7.574562740325928,
|
|
"epoch": 0.11771494518176573,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999999453607515,
|
|
"loss": 7.3165,
|
|
"mean_token_accuracy": 0.13034487813711165,
|
|
"num_tokens": 2570834.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 7.461473798751831,
|
|
"epoch": 0.11829197922677438,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999999128193729,
|
|
"loss": 7.2709,
|
|
"mean_token_accuracy": 0.14077538400888442,
|
|
"num_tokens": 2583342.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 7.511537408828735,
|
|
"epoch": 0.11886901327178304,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499999872710234,
|
|
"loss": 7.3162,
|
|
"mean_token_accuracy": 0.1330413155257702,
|
|
"num_tokens": 2594878.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 7.390342903137207,
|
|
"epoch": 0.11944604731679169,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999998250333361,
|
|
"loss": 7.281,
|
|
"mean_token_accuracy": 0.13540845960378647,
|
|
"num_tokens": 2607070.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 7.526187515258789,
|
|
"epoch": 0.12002308136180034,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000499999769788681,
|
|
"loss": 7.3157,
|
|
"mean_token_accuracy": 0.13957726508378981,
|
|
"num_tokens": 2620761.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 7.498535776138306,
|
|
"epoch": 0.120600115406809,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004999997069762703,
|
|
"loss": 7.3307,
|
|
"mean_token_accuracy": 0.1318868264555931,
|
|
"num_tokens": 2634161.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 7.453407907485962,
|
|
"epoch": 0.12117714945181765,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999996365961062,
|
|
"loss": 7.2874,
|
|
"mean_token_accuracy": 0.1383284404873848,
|
|
"num_tokens": 2647459.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 7.446234273910522,
|
|
"epoch": 0.12175418349682632,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999995586481912,
|
|
"loss": 7.2872,
|
|
"mean_token_accuracy": 0.1340254984796047,
|
|
"num_tokens": 2660840.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 7.483492088317871,
|
|
"epoch": 0.12233121754183497,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999994731325276,
|
|
"loss": 7.2865,
|
|
"mean_token_accuracy": 0.13337128460407258,
|
|
"num_tokens": 2672673.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 7.395563697814941,
|
|
"epoch": 0.12290825158684363,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999993800491187,
|
|
"loss": 7.2987,
|
|
"mean_token_accuracy": 0.13419368714094163,
|
|
"num_tokens": 2685744.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 7.416986179351807,
|
|
"epoch": 0.12348528563185228,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999992793979672,
|
|
"loss": 7.2196,
|
|
"mean_token_accuracy": 0.14943781048059462,
|
|
"num_tokens": 2697068.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 7.524578285217285,
|
|
"epoch": 0.12406231967686093,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999991711790769,
|
|
"loss": 7.3467,
|
|
"mean_token_accuracy": 0.12948699221014975,
|
|
"num_tokens": 2710418.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 7.54997706413269,
|
|
"epoch": 0.12463935372186959,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999990553924511,
|
|
"loss": 7.3065,
|
|
"mean_token_accuracy": 0.12690478786826134,
|
|
"num_tokens": 2722440.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 7.381335258483887,
|
|
"epoch": 0.12521638776687824,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004999989320380939,
|
|
"loss": 7.2963,
|
|
"mean_token_accuracy": 0.12917414531111718,
|
|
"num_tokens": 2735486.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 7.532785177230835,
|
|
"epoch": 0.1257934218118869,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999988011160094,
|
|
"loss": 7.3223,
|
|
"mean_token_accuracy": 0.13123588562011718,
|
|
"num_tokens": 2747620.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 7.407538604736328,
|
|
"epoch": 0.12637045585689555,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000499998662626202,
|
|
"loss": 7.2571,
|
|
"mean_token_accuracy": 0.1341471828520298,
|
|
"num_tokens": 2760987.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 7.483826351165772,
|
|
"epoch": 0.12694748990190421,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999985165686764,
|
|
"loss": 7.234,
|
|
"mean_token_accuracy": 0.1353903256356716,
|
|
"num_tokens": 2773161.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 7.336683225631714,
|
|
"epoch": 0.12752452394691285,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999983629434373,
|
|
"loss": 7.1573,
|
|
"mean_token_accuracy": 0.15311394929885863,
|
|
"num_tokens": 2786179.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 7.440242195129395,
|
|
"epoch": 0.12810155799192152,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999982017504901,
|
|
"loss": 7.1926,
|
|
"mean_token_accuracy": 0.14265231788158417,
|
|
"num_tokens": 2798859.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 7.385885190963745,
|
|
"epoch": 0.1286785920369302,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004999980329898401,
|
|
"loss": 7.2944,
|
|
"mean_token_accuracy": 0.1360294461250305,
|
|
"num_tokens": 2813048.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 7.456379127502442,
|
|
"epoch": 0.12925562608193883,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000499997856661493,
|
|
"loss": 7.2612,
|
|
"mean_token_accuracy": 0.13587961345911026,
|
|
"num_tokens": 2826032.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 7.430348825454712,
|
|
"epoch": 0.1298326601269475,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000499997672765455,
|
|
"loss": 7.2962,
|
|
"mean_token_accuracy": 0.13529185801744462,
|
|
"num_tokens": 2839253.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 7.3566066265106205,
|
|
"epoch": 0.13040969417195614,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999974813017318,
|
|
"loss": 7.2183,
|
|
"mean_token_accuracy": 0.14149424508213998,
|
|
"num_tokens": 2852542.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 7.3935285091400145,
|
|
"epoch": 0.1309867282169648,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999972822703301,
|
|
"loss": 7.2395,
|
|
"mean_token_accuracy": 0.14146022573113443,
|
|
"num_tokens": 2863967.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 7.422988605499268,
|
|
"epoch": 0.13156376226197344,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999970756712567,
|
|
"loss": 7.3171,
|
|
"mean_token_accuracy": 0.13306807354092598,
|
|
"num_tokens": 2876141.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 7.2979803562164305,
|
|
"epoch": 0.1321407963069821,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999968615045183,
|
|
"loss": 7.145,
|
|
"mean_token_accuracy": 0.14133854061365128,
|
|
"num_tokens": 2888395.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 7.431983804702758,
|
|
"epoch": 0.13271783035199078,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999966397701222,
|
|
"loss": 7.3261,
|
|
"mean_token_accuracy": 0.12834407463669778,
|
|
"num_tokens": 2902399.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 7.406958770751953,
|
|
"epoch": 0.13329486439699942,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999964104680759,
|
|
"loss": 7.0835,
|
|
"mean_token_accuracy": 0.1402672976255417,
|
|
"num_tokens": 2914999.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 7.348841714859009,
|
|
"epoch": 0.13387189844200809,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999961735983871,
|
|
"loss": 7.0785,
|
|
"mean_token_accuracy": 0.1498357504606247,
|
|
"num_tokens": 2928091.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 7.33998703956604,
|
|
"epoch": 0.13444893248701673,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004999959291610639,
|
|
"loss": 7.2138,
|
|
"mean_token_accuracy": 0.1341881737112999,
|
|
"num_tokens": 2940840.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 7.289854049682617,
|
|
"epoch": 0.1350259665320254,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999956771561143,
|
|
"loss": 7.1303,
|
|
"mean_token_accuracy": 0.14412761703133584,
|
|
"num_tokens": 2952980.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 7.357520866394043,
|
|
"epoch": 0.13560300057703403,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004999954175835469,
|
|
"loss": 7.1748,
|
|
"mean_token_accuracy": 0.13631198480725287,
|
|
"num_tokens": 2965437.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 7.3787942886352536,
|
|
"epoch": 0.1361800346220427,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999951504433703,
|
|
"loss": 7.2047,
|
|
"mean_token_accuracy": 0.1348996601998806,
|
|
"num_tokens": 2978077.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 7.40587363243103,
|
|
"epoch": 0.13675706866705137,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999948757355935,
|
|
"loss": 7.298,
|
|
"mean_token_accuracy": 0.13351393342018128,
|
|
"num_tokens": 2990498.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 7.413915586471558,
|
|
"epoch": 0.13733410271206,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.000499994593460226,
|
|
"loss": 7.2412,
|
|
"mean_token_accuracy": 0.1355881556868553,
|
|
"num_tokens": 3002784.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 7.372391653060913,
|
|
"epoch": 0.13791113675706868,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999943036172771,
|
|
"loss": 7.1807,
|
|
"mean_token_accuracy": 0.13228997811675072,
|
|
"num_tokens": 3015689.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 7.241599178314209,
|
|
"epoch": 0.13848817080207732,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999940062067565,
|
|
"loss": 7.1264,
|
|
"mean_token_accuracy": 0.1455356404185295,
|
|
"num_tokens": 3026623.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 7.376918649673462,
|
|
"epoch": 0.13906520484708598,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999937012286742,
|
|
"loss": 7.1615,
|
|
"mean_token_accuracy": 0.1412371888756752,
|
|
"num_tokens": 3039769.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 7.27626667022705,
|
|
"epoch": 0.13964223889209462,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999933886830405,
|
|
"loss": 7.1505,
|
|
"mean_token_accuracy": 0.13528102561831473,
|
|
"num_tokens": 3052044.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 7.345494079589844,
|
|
"epoch": 0.1402192729371033,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000499993068569866,
|
|
"loss": 7.1241,
|
|
"mean_token_accuracy": 0.1391813077032566,
|
|
"num_tokens": 3063937.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 7.187998628616333,
|
|
"epoch": 0.14079630698211196,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999927408891614,
|
|
"loss": 7.0939,
|
|
"mean_token_accuracy": 0.14361393451690674,
|
|
"num_tokens": 3076645.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 7.401137399673462,
|
|
"epoch": 0.1413733410271206,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999924056409378,
|
|
"loss": 7.1542,
|
|
"mean_token_accuracy": 0.13744900077581407,
|
|
"num_tokens": 3088985.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 7.271087980270385,
|
|
"epoch": 0.14195037507212926,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004999920628252063,
|
|
"loss": 7.1543,
|
|
"mean_token_accuracy": 0.1385358177125454,
|
|
"num_tokens": 3101270.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 7.236308813095093,
|
|
"epoch": 0.1425274091171379,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004999917124419785,
|
|
"loss": 7.1713,
|
|
"mean_token_accuracy": 0.13507955446839331,
|
|
"num_tokens": 3115420.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 7.414693069458008,
|
|
"epoch": 0.14310444316214657,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999913544912664,
|
|
"loss": 7.1106,
|
|
"mean_token_accuracy": 0.13970131129026414,
|
|
"num_tokens": 3126176.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 7.252271461486816,
|
|
"epoch": 0.1436814772071552,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004999909889730817,
|
|
"loss": 7.1516,
|
|
"mean_token_accuracy": 0.14178458228707314,
|
|
"num_tokens": 3139136.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 7.280838823318481,
|
|
"epoch": 0.14425851125216388,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999906158874368,
|
|
"loss": 7.1044,
|
|
"mean_token_accuracy": 0.1472743645310402,
|
|
"num_tokens": 3152036.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 7.349875354766846,
|
|
"epoch": 0.14483554529717255,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999902352343444,
|
|
"loss": 7.1386,
|
|
"mean_token_accuracy": 0.14143830314278602,
|
|
"num_tokens": 3164060.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 7.355139827728271,
|
|
"epoch": 0.1454125793421812,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999898470138171,
|
|
"loss": 7.206,
|
|
"mean_token_accuracy": 0.12975897416472434,
|
|
"num_tokens": 3176410.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 7.291885662078857,
|
|
"epoch": 0.14598961338718985,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004999894512258681,
|
|
"loss": 7.2261,
|
|
"mean_token_accuracy": 0.13479177728295327,
|
|
"num_tokens": 3189784.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 7.3698536396026615,
|
|
"epoch": 0.1465666474321985,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004999890478705107,
|
|
"loss": 7.1471,
|
|
"mean_token_accuracy": 0.1365978240966797,
|
|
"num_tokens": 3202274.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 7.3492168426513675,
|
|
"epoch": 0.14714368147720716,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999886369477585,
|
|
"loss": 7.2021,
|
|
"mean_token_accuracy": 0.13651041984558104,
|
|
"num_tokens": 3215593.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 7.264506483078003,
|
|
"epoch": 0.1477207155222158,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999882184576251,
|
|
"loss": 7.1145,
|
|
"mean_token_accuracy": 0.1358187846839428,
|
|
"num_tokens": 3228307.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 7.262033987045288,
|
|
"epoch": 0.14829774956722447,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004999877924001248,
|
|
"loss": 7.0714,
|
|
"mean_token_accuracy": 0.13908419981598855,
|
|
"num_tokens": 3241676.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 7.289368486404419,
|
|
"epoch": 0.1488747836122331,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999873587752718,
|
|
"loss": 7.1412,
|
|
"mean_token_accuracy": 0.13665730655193328,
|
|
"num_tokens": 3255190.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 7.299326705932617,
|
|
"epoch": 0.14945181765724178,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004999869175830808,
|
|
"loss": 7.1635,
|
|
"mean_token_accuracy": 0.13522787094116212,
|
|
"num_tokens": 3268236.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 7.349583387374878,
|
|
"epoch": 0.15002885170225044,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999864688235666,
|
|
"loss": 7.1786,
|
|
"mean_token_accuracy": 0.13588001057505608,
|
|
"num_tokens": 3281316.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 7.291733837127685,
|
|
"epoch": 0.15060588574725908,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004999860124967442,
|
|
"loss": 7.0853,
|
|
"mean_token_accuracy": 0.1390770271420479,
|
|
"num_tokens": 3293517.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 7.185279273986817,
|
|
"epoch": 0.15118291979226775,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004999855486026291,
|
|
"loss": 7.0715,
|
|
"mean_token_accuracy": 0.14518356174230576,
|
|
"num_tokens": 3306814.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 7.301711988449097,
|
|
"epoch": 0.1517599538372764,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999850771412369,
|
|
"loss": 7.1333,
|
|
"mean_token_accuracy": 0.13459300100803376,
|
|
"num_tokens": 3318722.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 7.199785852432251,
|
|
"epoch": 0.15233698788228506,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004999845981125832,
|
|
"loss": 7.0873,
|
|
"mean_token_accuracy": 0.14142397046089172,
|
|
"num_tokens": 3331212.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 7.31465106010437,
|
|
"epoch": 0.1529140219272937,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004999841115166844,
|
|
"loss": 7.0661,
|
|
"mean_token_accuracy": 0.13654675781726838,
|
|
"num_tokens": 3343999.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 7.124961471557617,
|
|
"epoch": 0.15349105597230236,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999836173535568,
|
|
"loss": 7.0068,
|
|
"mean_token_accuracy": 0.14172771871089934,
|
|
"num_tokens": 3356281.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 7.201707267761231,
|
|
"epoch": 0.15406809001731103,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999831156232169,
|
|
"loss": 7.0726,
|
|
"mean_token_accuracy": 0.1406794235110283,
|
|
"num_tokens": 3369370.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 7.341475009918213,
|
|
"epoch": 0.15464512406231967,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004999826063256818,
|
|
"loss": 7.2012,
|
|
"mean_token_accuracy": 0.13309285268187523,
|
|
"num_tokens": 3382400.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 7.232538366317749,
|
|
"epoch": 0.15522215810732834,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999820894609683,
|
|
"loss": 7.0778,
|
|
"mean_token_accuracy": 0.13890645131468773,
|
|
"num_tokens": 3393666.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 7.243199300765991,
|
|
"epoch": 0.15579919215233698,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004999815650290941,
|
|
"loss": 7.0914,
|
|
"mean_token_accuracy": 0.1401012994349003,
|
|
"num_tokens": 3405920.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 7.1591578960418705,
|
|
"epoch": 0.15637622619734565,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999810330300766,
|
|
"loss": 6.9923,
|
|
"mean_token_accuracy": 0.14642595648765563,
|
|
"num_tokens": 3417886.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 7.254940557479858,
|
|
"epoch": 0.1569532602423543,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.000499980493463934,
|
|
"loss": 7.1075,
|
|
"mean_token_accuracy": 0.13476622179150582,
|
|
"num_tokens": 3430626.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 7.202736520767212,
|
|
"epoch": 0.15753029428736295,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999799463306841,
|
|
"loss": 7.0076,
|
|
"mean_token_accuracy": 0.1388716422021389,
|
|
"num_tokens": 3443248.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 7.213499069213867,
|
|
"epoch": 0.15810732833237162,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999793916303455,
|
|
"loss": 7.0503,
|
|
"mean_token_accuracy": 0.13839739933609962,
|
|
"num_tokens": 3456163.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 7.167108821868896,
|
|
"epoch": 0.15868436237738026,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999788293629368,
|
|
"loss": 7.0754,
|
|
"mean_token_accuracy": 0.13633116707205772,
|
|
"num_tokens": 3468862.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 7.2402849197387695,
|
|
"epoch": 0.15926139642238893,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000499978259528477,
|
|
"loss": 7.0663,
|
|
"mean_token_accuracy": 0.14658810272812844,
|
|
"num_tokens": 3481516.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 7.265804767608643,
|
|
"epoch": 0.15983843046739757,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004999776821269852,
|
|
"loss": 7.1273,
|
|
"mean_token_accuracy": 0.12971169799566268,
|
|
"num_tokens": 3493063.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 7.229140663146973,
|
|
"epoch": 0.16041546451240624,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004999770971584807,
|
|
"loss": 7.0123,
|
|
"mean_token_accuracy": 0.13699770867824554,
|
|
"num_tokens": 3505460.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 7.235083723068238,
|
|
"epoch": 0.16099249855741488,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004999765046229834,
|
|
"loss": 7.1218,
|
|
"mean_token_accuracy": 0.13258355781435965,
|
|
"num_tokens": 3519232.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 7.22713418006897,
|
|
"epoch": 0.16156953260242354,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000499975904520513,
|
|
"loss": 7.0295,
|
|
"mean_token_accuracy": 0.1445997752249241,
|
|
"num_tokens": 3531759.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 7.201732730865478,
|
|
"epoch": 0.1621465666474322,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00049997529685109,
|
|
"loss": 6.9829,
|
|
"mean_token_accuracy": 0.15084661841392516,
|
|
"num_tokens": 3543457.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 7.160426235198974,
|
|
"epoch": 0.16272360069244085,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999746816147344,
|
|
"loss": 7.1195,
|
|
"mean_token_accuracy": 0.1298399582505226,
|
|
"num_tokens": 3557036.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 7.306451225280762,
|
|
"epoch": 0.16330063473744952,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999740588114673,
|
|
"loss": 7.0716,
|
|
"mean_token_accuracy": 0.1405071273446083,
|
|
"num_tokens": 3569415.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 7.171466588973999,
|
|
"epoch": 0.16387766878245816,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999734284413095,
|
|
"loss": 7.0696,
|
|
"mean_token_accuracy": 0.13537402525544168,
|
|
"num_tokens": 3581452.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 7.184612178802491,
|
|
"epoch": 0.16445470282746683,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000499972790504282,
|
|
"loss": 7.094,
|
|
"mean_token_accuracy": 0.13849470168352127,
|
|
"num_tokens": 3593482.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 7.202459335327148,
|
|
"epoch": 0.16503173687247547,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999721450004067,
|
|
"loss": 7.0864,
|
|
"mean_token_accuracy": 0.13760560154914855,
|
|
"num_tokens": 3606062.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 7.222452545166016,
|
|
"epoch": 0.16560877091748413,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999714919297049,
|
|
"loss": 7.0499,
|
|
"mean_token_accuracy": 0.14111001044511795,
|
|
"num_tokens": 3619210.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 7.180074310302734,
|
|
"epoch": 0.1661858049624928,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004999708312921987,
|
|
"loss": 7.0919,
|
|
"mean_token_accuracy": 0.13837566673755647,
|
|
"num_tokens": 3631952.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 7.17976598739624,
|
|
"epoch": 0.16676283900750144,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004999701630879103,
|
|
"loss": 6.9734,
|
|
"mean_token_accuracy": 0.14263298735022545,
|
|
"num_tokens": 3644864.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 7.166555690765381,
|
|
"epoch": 0.1673398730525101,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004999694873168623,
|
|
"loss": 7.0507,
|
|
"mean_token_accuracy": 0.1378322072327137,
|
|
"num_tokens": 3657504.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 7.19564905166626,
|
|
"epoch": 0.16791690709751875,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999688039790773,
|
|
"loss": 6.9587,
|
|
"mean_token_accuracy": 0.14702803492546082,
|
|
"num_tokens": 3670304.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 7.150408220291138,
|
|
"epoch": 0.16849394114252741,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999681130745784,
|
|
"loss": 6.9859,
|
|
"mean_token_accuracy": 0.13595322594046594,
|
|
"num_tokens": 3681503.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 7.162327766418457,
|
|
"epoch": 0.16907097518753605,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999674146033888,
|
|
"loss": 7.0123,
|
|
"mean_token_accuracy": 0.137976536154747,
|
|
"num_tokens": 3693248.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 7.136591291427612,
|
|
"epoch": 0.16964800923254472,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999667085655318,
|
|
"loss": 7.0248,
|
|
"mean_token_accuracy": 0.14202336519956588,
|
|
"num_tokens": 3705285.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 7.1525966167449955,
|
|
"epoch": 0.1702250432775534,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004999659949610313,
|
|
"loss": 7.0489,
|
|
"mean_token_accuracy": 0.13094842061400414,
|
|
"num_tokens": 3719025.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 7.2398560523986815,
|
|
"epoch": 0.17080207732256203,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999652737899114,
|
|
"loss": 7.0371,
|
|
"mean_token_accuracy": 0.14026156663894654,
|
|
"num_tokens": 3732054.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 7.175600671768189,
|
|
"epoch": 0.1713791113675707,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999645450521963,
|
|
"loss": 7.0023,
|
|
"mean_token_accuracy": 0.141888265311718,
|
|
"num_tokens": 3744080.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 7.114497375488281,
|
|
"epoch": 0.17195614541257934,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004999638087479104,
|
|
"loss": 7.0391,
|
|
"mean_token_accuracy": 0.13951010257005692,
|
|
"num_tokens": 3756371.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 7.245286512374878,
|
|
"epoch": 0.172533179457588,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999630648770786,
|
|
"loss": 6.9683,
|
|
"mean_token_accuracy": 0.1364215262234211,
|
|
"num_tokens": 3769307.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 7.008484745025635,
|
|
"epoch": 0.17311021350259664,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999623134397257,
|
|
"loss": 6.9637,
|
|
"mean_token_accuracy": 0.14434833228588104,
|
|
"num_tokens": 3782826.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 7.155062961578369,
|
|
"epoch": 0.1736872475476053,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004999615544358774,
|
|
"loss": 6.969,
|
|
"mean_token_accuracy": 0.13818738386034965,
|
|
"num_tokens": 3794566.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 7.102244281768799,
|
|
"epoch": 0.17426428159261395,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999607878655587,
|
|
"loss": 7.0508,
|
|
"mean_token_accuracy": 0.13246384710073472,
|
|
"num_tokens": 3807058.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 7.190773010253906,
|
|
"epoch": 0.17484131563762262,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004999600137287958,
|
|
"loss": 6.9966,
|
|
"mean_token_accuracy": 0.1451525256037712,
|
|
"num_tokens": 3819836.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 7.112970066070557,
|
|
"epoch": 0.17541834968263129,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999592320256146,
|
|
"loss": 7.0526,
|
|
"mean_token_accuracy": 0.13325869366526605,
|
|
"num_tokens": 3832081.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 7.19920711517334,
|
|
"epoch": 0.17599538372763993,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004999584427560412,
|
|
"loss": 6.9666,
|
|
"mean_token_accuracy": 0.14759944379329681,
|
|
"num_tokens": 3843279.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 7.110972738265991,
|
|
"epoch": 0.1765724177726486,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999576459201024,
|
|
"loss": 7.0377,
|
|
"mean_token_accuracy": 0.14277849197387696,
|
|
"num_tokens": 3855479.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 7.166525030136109,
|
|
"epoch": 0.17714945181765723,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.000499956841517825,
|
|
"loss": 7.0261,
|
|
"mean_token_accuracy": 0.14007299840450288,
|
|
"num_tokens": 3868111.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 7.039232683181763,
|
|
"epoch": 0.1777264858626659,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000499956029549236,
|
|
"loss": 6.9523,
|
|
"mean_token_accuracy": 0.14354307875037192,
|
|
"num_tokens": 3880062.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 7.2218320846557615,
|
|
"epoch": 0.17830351990767454,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004999552100143625,
|
|
"loss": 7.038,
|
|
"mean_token_accuracy": 0.1351063035428524,
|
|
"num_tokens": 3892293.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 7.088453531265259,
|
|
"epoch": 0.1788805539526832,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999543829132324,
|
|
"loss": 6.9011,
|
|
"mean_token_accuracy": 0.14455311074852945,
|
|
"num_tokens": 3904549.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 7.0796609878540036,
|
|
"epoch": 0.17945758799769188,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999535482458734,
|
|
"loss": 6.952,
|
|
"mean_token_accuracy": 0.14381684213876725,
|
|
"num_tokens": 3916693.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 7.087669706344604,
|
|
"epoch": 0.18003462204270052,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999527060123135,
|
|
"loss": 6.9651,
|
|
"mean_token_accuracy": 0.13298058956861497,
|
|
"num_tokens": 3930488.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 7.125672006607056,
|
|
"epoch": 0.18061165608770918,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999518562125811,
|
|
"loss": 6.9626,
|
|
"mean_token_accuracy": 0.14101526886224747,
|
|
"num_tokens": 3942353.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 7.161968660354614,
|
|
"epoch": 0.18118869013271782,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999509988467047,
|
|
"loss": 7.0103,
|
|
"mean_token_accuracy": 0.13919673189520837,
|
|
"num_tokens": 3953868.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 7.124320602416992,
|
|
"epoch": 0.1817657241777265,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999501339147132,
|
|
"loss": 7.0217,
|
|
"mean_token_accuracy": 0.1360984094440937,
|
|
"num_tokens": 3965148.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 7.110309076309204,
|
|
"epoch": 0.18234275822273513,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999492614166357,
|
|
"loss": 6.9888,
|
|
"mean_token_accuracy": 0.14489941596984862,
|
|
"num_tokens": 3977323.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 7.14143214225769,
|
|
"epoch": 0.1829197922677438,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004999483813525014,
|
|
"loss": 6.9486,
|
|
"mean_token_accuracy": 0.14665654599666594,
|
|
"num_tokens": 3990076.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 7.0736024379730225,
|
|
"epoch": 0.18349682631275246,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999474937223403,
|
|
"loss": 6.958,
|
|
"mean_token_accuracy": 0.13847637176513672,
|
|
"num_tokens": 4001996.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 7.1584230899810795,
|
|
"epoch": 0.1840738603577611,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004999465985261818,
|
|
"loss": 6.996,
|
|
"mean_token_accuracy": 0.13838272169232368,
|
|
"num_tokens": 4015095.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 7.085082769393921,
|
|
"epoch": 0.18465089440276977,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004999456957640562,
|
|
"loss": 6.8885,
|
|
"mean_token_accuracy": 0.14849510788917542,
|
|
"num_tokens": 4028633.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 7.059274530410766,
|
|
"epoch": 0.1852279284477784,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004999447854359939,
|
|
"loss": 6.9902,
|
|
"mean_token_accuracy": 0.14084767922759056,
|
|
"num_tokens": 4042265.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 7.04382438659668,
|
|
"epoch": 0.18580496249278708,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004999438675420255,
|
|
"loss": 6.9434,
|
|
"mean_token_accuracy": 0.14098646268248557,
|
|
"num_tokens": 4054467.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 7.100906753540039,
|
|
"epoch": 0.18638199653779572,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999429420821818,
|
|
"loss": 6.9422,
|
|
"mean_token_accuracy": 0.14708167761564256,
|
|
"num_tokens": 4068053.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 6.988407993316651,
|
|
"epoch": 0.1869590305828044,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499942009056494,
|
|
"loss": 6.9174,
|
|
"mean_token_accuracy": 0.14443018585443496,
|
|
"num_tokens": 4080867.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 7.123555755615234,
|
|
"epoch": 0.18753606462781305,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999410684649935,
|
|
"loss": 6.9813,
|
|
"mean_token_accuracy": 0.13821664601564407,
|
|
"num_tokens": 4093228.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 7.086485910415649,
|
|
"epoch": 0.1881130986728217,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004999401203077119,
|
|
"loss": 6.9764,
|
|
"mean_token_accuracy": 0.14208749383687974,
|
|
"num_tokens": 4104929.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 7.062161016464233,
|
|
"epoch": 0.18869013271783036,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.000499939164584681,
|
|
"loss": 6.9907,
|
|
"mean_token_accuracy": 0.15021519139409065,
|
|
"num_tokens": 4119445.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 7.106227540969849,
|
|
"epoch": 0.189267166762839,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999382012959331,
|
|
"loss": 6.8918,
|
|
"mean_token_accuracy": 0.15079083889722825,
|
|
"num_tokens": 4131558.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 7.123133182525635,
|
|
"epoch": 0.18984420080784767,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999372304415005,
|
|
"loss": 7.0313,
|
|
"mean_token_accuracy": 0.12920064106583595,
|
|
"num_tokens": 4144566.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 7.113665962219239,
|
|
"epoch": 0.1904212348528563,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999362520214159,
|
|
"loss": 6.9219,
|
|
"mean_token_accuracy": 0.14697587639093398,
|
|
"num_tokens": 4157295.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 7.081795692443848,
|
|
"epoch": 0.19099826889786498,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004999352660357122,
|
|
"loss": 6.9574,
|
|
"mean_token_accuracy": 0.1411465436220169,
|
|
"num_tokens": 4170229.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 7.1123281955719,
|
|
"epoch": 0.19157530294287364,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004999342724844226,
|
|
"loss": 6.9703,
|
|
"mean_token_accuracy": 0.13845267817378043,
|
|
"num_tokens": 4182906.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 7.087953901290893,
|
|
"epoch": 0.19215233698788228,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004999332713675804,
|
|
"loss": 6.9325,
|
|
"mean_token_accuracy": 0.143193506449461,
|
|
"num_tokens": 4195556.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 7.084608936309815,
|
|
"epoch": 0.19272937103289095,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004999322626852193,
|
|
"loss": 6.902,
|
|
"mean_token_accuracy": 0.13993172571063042,
|
|
"num_tokens": 4207616.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 7.025543546676635,
|
|
"epoch": 0.1933064050778996,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004999312464373734,
|
|
"loss": 6.8576,
|
|
"mean_token_accuracy": 0.14821547120809556,
|
|
"num_tokens": 4219299.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 7.017240190505982,
|
|
"epoch": 0.19388343912290826,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999302226240767,
|
|
"loss": 6.997,
|
|
"mean_token_accuracy": 0.13786116614937782,
|
|
"num_tokens": 4232098.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 7.080112934112549,
|
|
"epoch": 0.1944604731679169,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999291912453637,
|
|
"loss": 6.8995,
|
|
"mean_token_accuracy": 0.14469338953495026,
|
|
"num_tokens": 4243879.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 7.064555072784424,
|
|
"epoch": 0.19503750721292556,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999281523012691,
|
|
"loss": 6.9828,
|
|
"mean_token_accuracy": 0.13740749657154083,
|
|
"num_tokens": 4256507.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 7.218221855163574,
|
|
"epoch": 0.1956145412579342,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004999271057918278,
|
|
"loss": 7.0398,
|
|
"mean_token_accuracy": 0.13457229733467102,
|
|
"num_tokens": 4270763.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 7.035730075836182,
|
|
"epoch": 0.19619157530294287,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004999260517170751,
|
|
"loss": 6.9131,
|
|
"mean_token_accuracy": 0.14340217858552934,
|
|
"num_tokens": 4284380.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 7.1246764183044435,
|
|
"epoch": 0.19676860934795154,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004999249900770463,
|
|
"loss": 7.0215,
|
|
"mean_token_accuracy": 0.13842824175953866,
|
|
"num_tokens": 4297812.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 7.021434783935547,
|
|
"epoch": 0.19734564339296018,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999239208717772,
|
|
"loss": 6.9875,
|
|
"mean_token_accuracy": 0.14540473818778993,
|
|
"num_tokens": 4310374.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 7.130036401748657,
|
|
"epoch": 0.19792267743796885,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999228441013037,
|
|
"loss": 6.9861,
|
|
"mean_token_accuracy": 0.13793584629893302,
|
|
"num_tokens": 4322330.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 7.092807817459106,
|
|
"epoch": 0.1984997114829775,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.000499921759765662,
|
|
"loss": 6.9437,
|
|
"mean_token_accuracy": 0.14130837395787238,
|
|
"num_tokens": 4335204.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 6.928855037689209,
|
|
"epoch": 0.19907674552798615,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999206678648888,
|
|
"loss": 6.8285,
|
|
"mean_token_accuracy": 0.14999809116125107,
|
|
"num_tokens": 4347339.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 7.080965518951416,
|
|
"epoch": 0.1996537795729948,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004999195683990206,
|
|
"loss": 6.8898,
|
|
"mean_token_accuracy": 0.14809404462575912,
|
|
"num_tokens": 4360273.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 7.013464021682739,
|
|
"epoch": 0.20023081361800346,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999184613680945,
|
|
"loss": 6.9012,
|
|
"mean_token_accuracy": 0.14106058850884437,
|
|
"num_tokens": 4373424.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 7.049986457824707,
|
|
"epoch": 0.20080784766301213,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999173467721476,
|
|
"loss": 6.8544,
|
|
"mean_token_accuracy": 0.15058322101831437,
|
|
"num_tokens": 4386125.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 7.018032741546631,
|
|
"epoch": 0.20138488170802077,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999162246112175,
|
|
"loss": 6.9365,
|
|
"mean_token_accuracy": 0.13854823932051658,
|
|
"num_tokens": 4399214.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 6.9998067855834964,
|
|
"epoch": 0.20196191575302944,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004999150948853419,
|
|
"loss": 6.8127,
|
|
"mean_token_accuracy": 0.14680370092391967,
|
|
"num_tokens": 4411282.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 6.969420385360718,
|
|
"epoch": 0.20253894979803808,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999139575945587,
|
|
"loss": 6.909,
|
|
"mean_token_accuracy": 0.14443379119038582,
|
|
"num_tokens": 4423448.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 7.101949882507324,
|
|
"epoch": 0.20311598384304674,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004999128127389065,
|
|
"loss": 6.8176,
|
|
"mean_token_accuracy": 0.15111797004938127,
|
|
"num_tokens": 4436498.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 6.992865753173828,
|
|
"epoch": 0.20369301788805538,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999116603184233,
|
|
"loss": 6.8342,
|
|
"mean_token_accuracy": 0.1466807797551155,
|
|
"num_tokens": 4448641.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 6.9575080394744875,
|
|
"epoch": 0.20427005193306405,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999105003331482,
|
|
"loss": 6.8404,
|
|
"mean_token_accuracy": 0.1423793762922287,
|
|
"num_tokens": 4460539.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 7.0623860359191895,
|
|
"epoch": 0.20484708597807272,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004999093327831202,
|
|
"loss": 6.8898,
|
|
"mean_token_accuracy": 0.14088162109255792,
|
|
"num_tokens": 4472487.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 6.952205657958984,
|
|
"epoch": 0.20542412002308136,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999081576683784,
|
|
"loss": 6.8802,
|
|
"mean_token_accuracy": 0.1421337030827999,
|
|
"num_tokens": 4485164.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 7.1306853771209715,
|
|
"epoch": 0.20600115406809003,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004999069749889626,
|
|
"loss": 6.8973,
|
|
"mean_token_accuracy": 0.14712294787168503,
|
|
"num_tokens": 4497708.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 6.940166759490967,
|
|
"epoch": 0.20657818811309867,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004999057847449123,
|
|
"loss": 6.9329,
|
|
"mean_token_accuracy": 0.1391274891793728,
|
|
"num_tokens": 4510648.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 7.065713214874267,
|
|
"epoch": 0.20715522215810733,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004999045869362678,
|
|
"loss": 6.8511,
|
|
"mean_token_accuracy": 0.14565493836998938,
|
|
"num_tokens": 4522699.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 6.939832353591919,
|
|
"epoch": 0.20773225620311597,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000499903381563069,
|
|
"loss": 6.8936,
|
|
"mean_token_accuracy": 0.13873664960265158,
|
|
"num_tokens": 4536060.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 6.97990312576294,
|
|
"epoch": 0.20830929024812464,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004999021686253568,
|
|
"loss": 6.8257,
|
|
"mean_token_accuracy": 0.13769187703728675,
|
|
"num_tokens": 4549876.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 7.080778312683106,
|
|
"epoch": 0.2088863242931333,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004999009481231719,
|
|
"loss": 6.8655,
|
|
"mean_token_accuracy": 0.14449936226010324,
|
|
"num_tokens": 4563638.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 6.9409098625183105,
|
|
"epoch": 0.20946335833814195,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004998997200565553,
|
|
"loss": 6.8057,
|
|
"mean_token_accuracy": 0.14341058060526848,
|
|
"num_tokens": 4575396.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 6.935875415802002,
|
|
"epoch": 0.21004039238315061,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004998984844255483,
|
|
"loss": 6.8199,
|
|
"mean_token_accuracy": 0.14724263399839402,
|
|
"num_tokens": 4587261.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 7.076818370819092,
|
|
"epoch": 0.21061742642815925,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004998972412301925,
|
|
"loss": 6.9409,
|
|
"mean_token_accuracy": 0.14100464209914207,
|
|
"num_tokens": 4600086.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 7.006335687637329,
|
|
"epoch": 0.21119446047316792,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004998959904705297,
|
|
"loss": 6.8993,
|
|
"mean_token_accuracy": 0.14008133336901665,
|
|
"num_tokens": 4612320.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 6.99210262298584,
|
|
"epoch": 0.21177149451817656,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998947321466021,
|
|
"loss": 6.8464,
|
|
"mean_token_accuracy": 0.14648700058460234,
|
|
"num_tokens": 4623545.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 6.954314517974853,
|
|
"epoch": 0.21234852856318523,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004998934662584518,
|
|
"loss": 6.7498,
|
|
"mean_token_accuracy": 0.1578306920826435,
|
|
"num_tokens": 4637223.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 6.826448059082031,
|
|
"epoch": 0.2129255626081939,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004998921928061214,
|
|
"loss": 6.837,
|
|
"mean_token_accuracy": 0.14694164842367172,
|
|
"num_tokens": 4649748.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 7.0238566398620605,
|
|
"epoch": 0.21350259665320254,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0004998909117896539,
|
|
"loss": 6.8732,
|
|
"mean_token_accuracy": 0.1458170548081398,
|
|
"num_tokens": 4662441.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 6.895988988876343,
|
|
"epoch": 0.2140796306982112,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998896232090922,
|
|
"loss": 6.8337,
|
|
"mean_token_accuracy": 0.15489335879683494,
|
|
"num_tokens": 4675546.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 7.177361154556275,
|
|
"epoch": 0.21465666474321984,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004998883270644798,
|
|
"loss": 6.9068,
|
|
"mean_token_accuracy": 0.13811369463801385,
|
|
"num_tokens": 4687601.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 6.91638216972351,
|
|
"epoch": 0.2152336987882285,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004998870233558602,
|
|
"loss": 6.7837,
|
|
"mean_token_accuracy": 0.15353625565767287,
|
|
"num_tokens": 4699336.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 6.911949300765992,
|
|
"epoch": 0.21581073283323715,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004998857120832774,
|
|
"loss": 6.9744,
|
|
"mean_token_accuracy": 0.13845321610569955,
|
|
"num_tokens": 4714312.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 6.956019687652588,
|
|
"epoch": 0.21638776687824582,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004998843932467751,
|
|
"loss": 6.7036,
|
|
"mean_token_accuracy": 0.15298319831490517,
|
|
"num_tokens": 4726436.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 6.97105393409729,
|
|
"epoch": 0.21696480092325446,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998830668463982,
|
|
"loss": 6.9324,
|
|
"mean_token_accuracy": 0.13379157483577728,
|
|
"num_tokens": 4739821.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 7.089961147308349,
|
|
"epoch": 0.21754183496826313,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004998817328821909,
|
|
"loss": 6.9187,
|
|
"mean_token_accuracy": 0.13890728428959848,
|
|
"num_tokens": 4752701.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 6.965564870834351,
|
|
"epoch": 0.2181188690132718,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004998803913541983,
|
|
"loss": 6.9329,
|
|
"mean_token_accuracy": 0.14065297245979308,
|
|
"num_tokens": 4766755.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 7.006665802001953,
|
|
"epoch": 0.21869590305828043,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004998790422624654,
|
|
"loss": 6.8586,
|
|
"mean_token_accuracy": 0.1429077446460724,
|
|
"num_tokens": 4780201.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 6.957398748397827,
|
|
"epoch": 0.2192729371032891,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004998776856070376,
|
|
"loss": 6.81,
|
|
"mean_token_accuracy": 0.1421031355857849,
|
|
"num_tokens": 4792488.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 6.996427440643311,
|
|
"epoch": 0.21984997114829774,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004998763213879606,
|
|
"loss": 6.7886,
|
|
"mean_token_accuracy": 0.14664288908243178,
|
|
"num_tokens": 4805154.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 6.966566801071167,
|
|
"epoch": 0.2204270051933064,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004998749496052803,
|
|
"loss": 6.8471,
|
|
"mean_token_accuracy": 0.14108580872416496,
|
|
"num_tokens": 4817947.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 6.996940803527832,
|
|
"epoch": 0.22100403923831505,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004998735702590426,
|
|
"loss": 6.828,
|
|
"mean_token_accuracy": 0.1447738878428936,
|
|
"num_tokens": 4830296.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 6.933389377593994,
|
|
"epoch": 0.22158107328332372,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004998721833492942,
|
|
"loss": 6.8253,
|
|
"mean_token_accuracy": 0.14365117698907853,
|
|
"num_tokens": 4841210.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 7.029626893997192,
|
|
"epoch": 0.22215810732833238,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004998707888760816,
|
|
"loss": 6.8996,
|
|
"mean_token_accuracy": 0.13317479714751243,
|
|
"num_tokens": 4854406.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 6.965882301330566,
|
|
"epoch": 0.22273514137334102,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004998693868394516,
|
|
"loss": 6.8706,
|
|
"mean_token_accuracy": 0.14146279469132422,
|
|
"num_tokens": 4868156.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 7.022164821624756,
|
|
"epoch": 0.2233121754183497,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998679772394516,
|
|
"loss": 6.804,
|
|
"mean_token_accuracy": 0.15072066336870193,
|
|
"num_tokens": 4880314.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 6.920300674438477,
|
|
"epoch": 0.22388920946335833,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004998665600761289,
|
|
"loss": 6.813,
|
|
"mean_token_accuracy": 0.14527895897626877,
|
|
"num_tokens": 4892652.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 7.060734128952026,
|
|
"epoch": 0.224466243508367,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.000499865135349531,
|
|
"loss": 6.9048,
|
|
"mean_token_accuracy": 0.13892186135053636,
|
|
"num_tokens": 4905791.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 6.940855360031128,
|
|
"epoch": 0.22504327755337564,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004998637030597061,
|
|
"loss": 6.8723,
|
|
"mean_token_accuracy": 0.14380484744906424,
|
|
"num_tokens": 4917359.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 7.036824655532837,
|
|
"epoch": 0.2256203115983843,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004998622632067022,
|
|
"loss": 6.8305,
|
|
"mean_token_accuracy": 0.14697285592556,
|
|
"num_tokens": 4928762.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 6.926147079467773,
|
|
"epoch": 0.22619734564339297,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004998608157905678,
|
|
"loss": 6.8447,
|
|
"mean_token_accuracy": 0.14583281725645064,
|
|
"num_tokens": 4940879.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 7.006029081344605,
|
|
"epoch": 0.2267743796884016,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004998593608113515,
|
|
"loss": 6.8538,
|
|
"mean_token_accuracy": 0.14606458991765975,
|
|
"num_tokens": 4952979.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 6.918392038345337,
|
|
"epoch": 0.22735141373341028,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004998578982691024,
|
|
"loss": 6.7524,
|
|
"mean_token_accuracy": 0.1569880038499832,
|
|
"num_tokens": 4965465.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 6.9123780727386475,
|
|
"epoch": 0.22792844777841892,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004998564281638694,
|
|
"loss": 6.8233,
|
|
"mean_token_accuracy": 0.14547210037708283,
|
|
"num_tokens": 4977960.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 6.97648549079895,
|
|
"epoch": 0.2285054818234276,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004998549504957023,
|
|
"loss": 6.8274,
|
|
"mean_token_accuracy": 0.14264762550592422,
|
|
"num_tokens": 4990732.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 6.921519327163696,
|
|
"epoch": 0.22908251586843623,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004998534652646506,
|
|
"loss": 6.7678,
|
|
"mean_token_accuracy": 0.14480722099542617,
|
|
"num_tokens": 5002482.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 6.902936887741089,
|
|
"epoch": 0.2296595499134449,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004998519724707642,
|
|
"loss": 6.7529,
|
|
"mean_token_accuracy": 0.14723773747682573,
|
|
"num_tokens": 5014932.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 6.885674381256104,
|
|
"epoch": 0.23023658395845356,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004998504721140934,
|
|
"loss": 6.8837,
|
|
"mean_token_accuracy": 0.138965655118227,
|
|
"num_tokens": 5027661.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 6.906474590301514,
|
|
"epoch": 0.2308136180034622,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998489641946887,
|
|
"loss": 6.6331,
|
|
"mean_token_accuracy": 0.1527172051370144,
|
|
"num_tokens": 5040657.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 6.975762939453125,
|
|
"epoch": 0.23139065204847087,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004998474487126009,
|
|
"loss": 6.9063,
|
|
"mean_token_accuracy": 0.13616069480776788,
|
|
"num_tokens": 5054408.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 6.98120608329773,
|
|
"epoch": 0.2319676860934795,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004998459256678806,
|
|
"loss": 6.7998,
|
|
"mean_token_accuracy": 0.14582831785082817,
|
|
"num_tokens": 5065499.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 6.935510063171387,
|
|
"epoch": 0.23254472013848818,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004998443950605796,
|
|
"loss": 6.7508,
|
|
"mean_token_accuracy": 0.15238589197397232,
|
|
"num_tokens": 5077009.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 6.931089639663696,
|
|
"epoch": 0.23312175418349682,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004998428568907488,
|
|
"loss": 6.925,
|
|
"mean_token_accuracy": 0.13808261305093766,
|
|
"num_tokens": 5089462.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 6.99543948173523,
|
|
"epoch": 0.23369878822850548,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004998413111584403,
|
|
"loss": 6.8333,
|
|
"mean_token_accuracy": 0.1430407203733921,
|
|
"num_tokens": 5101816.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 6.949823617935181,
|
|
"epoch": 0.23427582227351415,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004998397578637059,
|
|
"loss": 6.7939,
|
|
"mean_token_accuracy": 0.1399306148290634,
|
|
"num_tokens": 5115085.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 6.912753963470459,
|
|
"epoch": 0.2348528563185228,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.000499838197006598,
|
|
"loss": 6.8265,
|
|
"mean_token_accuracy": 0.1417170412838459,
|
|
"num_tokens": 5127705.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 6.916851139068603,
|
|
"epoch": 0.23542989036353146,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.000499836628587169,
|
|
"loss": 6.786,
|
|
"mean_token_accuracy": 0.1507592000067234,
|
|
"num_tokens": 5140509.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 6.963552236557007,
|
|
"epoch": 0.2360069244085401,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004998350526054716,
|
|
"loss": 6.8285,
|
|
"mean_token_accuracy": 0.1409867897629738,
|
|
"num_tokens": 5153538.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 6.918388509750367,
|
|
"epoch": 0.23658395845354876,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998334690615591,
|
|
"loss": 6.7526,
|
|
"mean_token_accuracy": 0.14691582769155503,
|
|
"num_tokens": 5166181.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 6.877604293823242,
|
|
"epoch": 0.2371609924985574,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004998318779554844,
|
|
"loss": 6.7855,
|
|
"mean_token_accuracy": 0.14772634357213973,
|
|
"num_tokens": 5177209.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 6.908311414718628,
|
|
"epoch": 0.23773802654356607,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998302792873012,
|
|
"loss": 6.8049,
|
|
"mean_token_accuracy": 0.14239051789045334,
|
|
"num_tokens": 5189786.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 6.952730369567871,
|
|
"epoch": 0.23831506058857474,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004998286730570631,
|
|
"loss": 6.7892,
|
|
"mean_token_accuracy": 0.1510260708630085,
|
|
"num_tokens": 5202629.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 6.907465410232544,
|
|
"epoch": 0.23889209463358338,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004998270592648245,
|
|
"loss": 6.8561,
|
|
"mean_token_accuracy": 0.13883134126663207,
|
|
"num_tokens": 5215339.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 6.9621459484100345,
|
|
"epoch": 0.23946912867859205,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004998254379106394,
|
|
"loss": 6.7359,
|
|
"mean_token_accuracy": 0.14754440188407897,
|
|
"num_tokens": 5227666.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 6.7812415599823,
|
|
"epoch": 0.2400461627236007,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004998238089945622,
|
|
"loss": 6.7107,
|
|
"mean_token_accuracy": 0.1521335408091545,
|
|
"num_tokens": 5238200.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 6.852583646774292,
|
|
"epoch": 0.24062319676860935,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004998221725166479,
|
|
"loss": 6.6654,
|
|
"mean_token_accuracy": 0.15192302465438842,
|
|
"num_tokens": 5250023.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 6.927479076385498,
|
|
"epoch": 0.241200230813618,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004998205284769516,
|
|
"loss": 6.8416,
|
|
"mean_token_accuracy": 0.1361626349389553,
|
|
"num_tokens": 5262634.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 6.945438241958618,
|
|
"epoch": 0.24177726485862666,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004998188768755285,
|
|
"loss": 6.8404,
|
|
"mean_token_accuracy": 0.1391704946756363,
|
|
"num_tokens": 5275739.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 6.907373285293579,
|
|
"epoch": 0.2423542989036353,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004998172177124341,
|
|
"loss": 6.8036,
|
|
"mean_token_accuracy": 0.14423199594020844,
|
|
"num_tokens": 5289223.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 6.921164560317993,
|
|
"epoch": 0.24293133294864397,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004998155509877242,
|
|
"loss": 6.7918,
|
|
"mean_token_accuracy": 0.14191285520792007,
|
|
"num_tokens": 5301869.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 6.931911897659302,
|
|
"epoch": 0.24350836699365264,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.000499813876701455,
|
|
"loss": 6.8142,
|
|
"mean_token_accuracy": 0.140006385743618,
|
|
"num_tokens": 5314999.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 6.918317890167236,
|
|
"epoch": 0.24408540103866128,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004998121948536828,
|
|
"loss": 6.8173,
|
|
"mean_token_accuracy": 0.14651304483413696,
|
|
"num_tokens": 5328247.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 6.985309028625489,
|
|
"epoch": 0.24466243508366994,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004998105054444639,
|
|
"loss": 6.804,
|
|
"mean_token_accuracy": 0.13474133610725403,
|
|
"num_tokens": 5341054.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 6.888967895507813,
|
|
"epoch": 0.24523946912867858,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004998088084738555,
|
|
"loss": 6.8269,
|
|
"mean_token_accuracy": 0.14804685413837432,
|
|
"num_tokens": 5353857.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 6.884988164901733,
|
|
"epoch": 0.24581650317368725,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004998071039419144,
|
|
"loss": 6.7622,
|
|
"mean_token_accuracy": 0.14388485997915268,
|
|
"num_tokens": 5366072.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 6.902663278579712,
|
|
"epoch": 0.2463935372186959,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000499805391848698,
|
|
"loss": 6.7641,
|
|
"mean_token_accuracy": 0.1469337075948715,
|
|
"num_tokens": 5379613.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 6.88670859336853,
|
|
"epoch": 0.24697057126370456,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.000499803672194264,
|
|
"loss": 6.8005,
|
|
"mean_token_accuracy": 0.14418511241674423,
|
|
"num_tokens": 5392394.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 6.805346250534058,
|
|
"epoch": 0.24754760530871323,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004998019449786701,
|
|
"loss": 6.77,
|
|
"mean_token_accuracy": 0.14892241209745408,
|
|
"num_tokens": 5404127.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 7.025264120101928,
|
|
"epoch": 0.24812463935372187,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004998002102019744,
|
|
"loss": 6.8739,
|
|
"mean_token_accuracy": 0.13671603947877883,
|
|
"num_tokens": 5417317.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 6.881466197967529,
|
|
"epoch": 0.24870167339873053,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004997984678642354,
|
|
"loss": 6.7279,
|
|
"mean_token_accuracy": 0.1475033514201641,
|
|
"num_tokens": 5429991.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 6.890996217727661,
|
|
"epoch": 0.24927870744373917,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004997967179655115,
|
|
"loss": 6.7702,
|
|
"mean_token_accuracy": 0.13975565731525422,
|
|
"num_tokens": 5442661.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 6.903371953964234,
|
|
"epoch": 0.24985574148874784,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004997949605058617,
|
|
"loss": 6.7731,
|
|
"mean_token_accuracy": 0.1479140818119049,
|
|
"num_tokens": 5455876.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 6.838821744918823,
|
|
"epoch": 0.2504327755337565,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004997931954853451,
|
|
"loss": 6.7326,
|
|
"mean_token_accuracy": 0.1502830758690834,
|
|
"num_tokens": 5468151.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 6.829051685333252,
|
|
"epoch": 0.2510098095787651,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.000499791422904021,
|
|
"loss": 6.7642,
|
|
"mean_token_accuracy": 0.15258670300245286,
|
|
"num_tokens": 5481327.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 6.854774093627929,
|
|
"epoch": 0.2515868436237738,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004997896427619491,
|
|
"loss": 6.726,
|
|
"mean_token_accuracy": 0.14523358941078185,
|
|
"num_tokens": 5493794.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 6.833822202682495,
|
|
"epoch": 0.25216387766878245,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004997878550591892,
|
|
"loss": 6.7622,
|
|
"mean_token_accuracy": 0.14095828533172608,
|
|
"num_tokens": 5506831.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 6.8861846923828125,
|
|
"epoch": 0.2527409117137911,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997860597958013,
|
|
"loss": 6.6629,
|
|
"mean_token_accuracy": 0.15049846321344376,
|
|
"num_tokens": 5518988.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 6.720967817306518,
|
|
"epoch": 0.2533179457587998,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004997842569718461,
|
|
"loss": 6.6284,
|
|
"mean_token_accuracy": 0.15226881206035614,
|
|
"num_tokens": 5530757.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 6.8386878490448,
|
|
"epoch": 0.25389497980380843,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000499782446587384,
|
|
"loss": 6.7462,
|
|
"mean_token_accuracy": 0.14984930008649827,
|
|
"num_tokens": 5542819.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 6.887057685852051,
|
|
"epoch": 0.25447201384881707,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000499780628642476,
|
|
"loss": 6.7516,
|
|
"mean_token_accuracy": 0.1436480388045311,
|
|
"num_tokens": 5555797.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 6.8565185546875,
|
|
"epoch": 0.2550490478938257,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004997788031371834,
|
|
"loss": 6.8377,
|
|
"mean_token_accuracy": 0.13526439368724824,
|
|
"num_tokens": 5570086.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 6.880842208862305,
|
|
"epoch": 0.2556260819388344,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004997769700715672,
|
|
"loss": 6.6616,
|
|
"mean_token_accuracy": 0.15116312801837922,
|
|
"num_tokens": 5582182.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 6.771800470352173,
|
|
"epoch": 0.25620311598384304,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004997751294456892,
|
|
"loss": 6.7557,
|
|
"mean_token_accuracy": 0.1484261780977249,
|
|
"num_tokens": 5595395.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 6.907889366149902,
|
|
"epoch": 0.2567801500288517,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004997732812596114,
|
|
"loss": 6.7655,
|
|
"mean_token_accuracy": 0.14601099640130996,
|
|
"num_tokens": 5608555.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 6.852161073684693,
|
|
"epoch": 0.2573571840738604,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004997714255133961,
|
|
"loss": 6.7211,
|
|
"mean_token_accuracy": 0.14606622010469436,
|
|
"num_tokens": 5620933.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 6.908066129684448,
|
|
"epoch": 0.257934218118869,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004997695622071054,
|
|
"loss": 6.7645,
|
|
"mean_token_accuracy": 0.14898824393749238,
|
|
"num_tokens": 5634061.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 6.929029846191407,
|
|
"epoch": 0.25851125216387766,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004997676913408021,
|
|
"loss": 6.7291,
|
|
"mean_token_accuracy": 0.1483811229467392,
|
|
"num_tokens": 5646617.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 6.87813811302185,
|
|
"epoch": 0.2590882862088863,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004997658129145493,
|
|
"loss": 6.811,
|
|
"mean_token_accuracy": 0.14377271234989167,
|
|
"num_tokens": 5659361.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 6.849423265457153,
|
|
"epoch": 0.259665320253895,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004997639269284099,
|
|
"loss": 6.6528,
|
|
"mean_token_accuracy": 0.15414825975894927,
|
|
"num_tokens": 5670591.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 6.851912260055542,
|
|
"epoch": 0.26024235429890363,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004997620333824476,
|
|
"loss": 6.7722,
|
|
"mean_token_accuracy": 0.14549338743090628,
|
|
"num_tokens": 5683211.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 6.851926565170288,
|
|
"epoch": 0.2608193883439123,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004997601322767258,
|
|
"loss": 6.7653,
|
|
"mean_token_accuracy": 0.145635487139225,
|
|
"num_tokens": 5695654.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 6.795074939727783,
|
|
"epoch": 0.26139642238892097,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004997582236113087,
|
|
"loss": 6.6557,
|
|
"mean_token_accuracy": 0.15083891600370408,
|
|
"num_tokens": 5707776.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 6.822677946090698,
|
|
"epoch": 0.2619734564339296,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004997563073862603,
|
|
"loss": 6.7076,
|
|
"mean_token_accuracy": 0.14838095828890802,
|
|
"num_tokens": 5719895.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 6.895277500152588,
|
|
"epoch": 0.26255049047893825,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004997543836016453,
|
|
"loss": 6.7302,
|
|
"mean_token_accuracy": 0.15407091453671456,
|
|
"num_tokens": 5733280.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 6.825756692886353,
|
|
"epoch": 0.2631275245239469,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004997524522575281,
|
|
"loss": 6.7713,
|
|
"mean_token_accuracy": 0.14787696152925492,
|
|
"num_tokens": 5746563.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 6.933543157577515,
|
|
"epoch": 0.2637045585689556,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004997505133539738,
|
|
"loss": 6.8251,
|
|
"mean_token_accuracy": 0.14116834327578545,
|
|
"num_tokens": 5760735.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 6.7919364929199215,
|
|
"epoch": 0.2642815926139642,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004997485668910476,
|
|
"loss": 6.7403,
|
|
"mean_token_accuracy": 0.13866735473275185,
|
|
"num_tokens": 5774304.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 6.707546329498291,
|
|
"epoch": 0.26485862665897286,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004997466128688151,
|
|
"loss": 6.6343,
|
|
"mean_token_accuracy": 0.1520386144518852,
|
|
"num_tokens": 5786045.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 6.8912115573883055,
|
|
"epoch": 0.26543566070398156,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000499744651287342,
|
|
"loss": 6.7038,
|
|
"mean_token_accuracy": 0.1507314458489418,
|
|
"num_tokens": 5798126.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 6.800000524520874,
|
|
"epoch": 0.2660126947489902,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.000499742682146694,
|
|
"loss": 6.708,
|
|
"mean_token_accuracy": 0.15146253854036332,
|
|
"num_tokens": 5809778.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 6.887187433242798,
|
|
"epoch": 0.26658972879399884,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004997407054469377,
|
|
"loss": 6.7913,
|
|
"mean_token_accuracy": 0.14095485657453538,
|
|
"num_tokens": 5821902.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 6.898465633392334,
|
|
"epoch": 0.2671667628390075,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004997387211881392,
|
|
"loss": 6.7311,
|
|
"mean_token_accuracy": 0.14221810474991797,
|
|
"num_tokens": 5835162.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 6.761828851699829,
|
|
"epoch": 0.26774379688401617,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004997367293703656,
|
|
"loss": 6.7284,
|
|
"mean_token_accuracy": 0.1507745712995529,
|
|
"num_tokens": 5847708.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 6.91298017501831,
|
|
"epoch": 0.2683208309290248,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004997347299936837,
|
|
"loss": 6.7346,
|
|
"mean_token_accuracy": 0.14922600761055946,
|
|
"num_tokens": 5860983.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 6.769803524017334,
|
|
"epoch": 0.26889786497403345,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004997327230581608,
|
|
"loss": 6.6998,
|
|
"mean_token_accuracy": 0.1437514305114746,
|
|
"num_tokens": 5873878.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 6.783571243286133,
|
|
"epoch": 0.26947489901904215,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004997307085638644,
|
|
"loss": 6.7147,
|
|
"mean_token_accuracy": 0.14909254312515258,
|
|
"num_tokens": 5886577.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 6.906566333770752,
|
|
"epoch": 0.2700519330640508,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997286865108621,
|
|
"loss": 6.7362,
|
|
"mean_token_accuracy": 0.13940049409866334,
|
|
"num_tokens": 5900373.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 6.771531581878662,
|
|
"epoch": 0.2706289671090594,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004997266568992222,
|
|
"loss": 6.708,
|
|
"mean_token_accuracy": 0.14844308495521547,
|
|
"num_tokens": 5913038.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 6.791477632522583,
|
|
"epoch": 0.27120600115406807,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004997246197290128,
|
|
"loss": 6.6815,
|
|
"mean_token_accuracy": 0.1516631633043289,
|
|
"num_tokens": 5926096.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 6.820218896865844,
|
|
"epoch": 0.27178303519907676,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004997225750003024,
|
|
"loss": 6.6836,
|
|
"mean_token_accuracy": 0.15230127722024916,
|
|
"num_tokens": 5937992.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 6.786269426345825,
|
|
"epoch": 0.2723600692440854,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004997205227131599,
|
|
"loss": 6.6959,
|
|
"mean_token_accuracy": 0.15331070870161057,
|
|
"num_tokens": 5949685.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 6.8500142097473145,
|
|
"epoch": 0.27293710328909404,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004997184628676542,
|
|
"loss": 6.77,
|
|
"mean_token_accuracy": 0.14370569810271264,
|
|
"num_tokens": 5962751.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 6.743644428253174,
|
|
"epoch": 0.27351413733410274,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004997163954638546,
|
|
"loss": 6.5676,
|
|
"mean_token_accuracy": 0.15582787990570068,
|
|
"num_tokens": 5976043.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 6.826035118103027,
|
|
"epoch": 0.2740911713791114,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004997143205018306,
|
|
"loss": 6.7138,
|
|
"mean_token_accuracy": 0.14594173580408096,
|
|
"num_tokens": 5988146.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 6.795579051971435,
|
|
"epoch": 0.27466820542412,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004997122379816523,
|
|
"loss": 6.6587,
|
|
"mean_token_accuracy": 0.15158178210258483,
|
|
"num_tokens": 6000542.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 6.742963075637817,
|
|
"epoch": 0.27524523946912866,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0004997101479033893,
|
|
"loss": 6.7064,
|
|
"mean_token_accuracy": 0.14576518833637236,
|
|
"num_tokens": 6013574.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 6.739541244506836,
|
|
"epoch": 0.27582227351413735,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004997080502671122,
|
|
"loss": 6.594,
|
|
"mean_token_accuracy": 0.15022992491722106,
|
|
"num_tokens": 6025391.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 6.859225606918335,
|
|
"epoch": 0.276399307559146,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004997059450728913,
|
|
"loss": 6.7201,
|
|
"mean_token_accuracy": 0.14635233953595161,
|
|
"num_tokens": 6036595.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 6.836587810516358,
|
|
"epoch": 0.27697634160415463,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004997038323207977,
|
|
"loss": 6.8146,
|
|
"mean_token_accuracy": 0.1395593300461769,
|
|
"num_tokens": 6048852.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 6.825769519805908,
|
|
"epoch": 0.2775533756491633,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004997017120109022,
|
|
"loss": 6.6492,
|
|
"mean_token_accuracy": 0.15694630444049834,
|
|
"num_tokens": 6061694.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 6.7436662197113035,
|
|
"epoch": 0.27813040969417197,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004996995841432762,
|
|
"loss": 6.725,
|
|
"mean_token_accuracy": 0.15039588510990143,
|
|
"num_tokens": 6074244.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 6.894833898544311,
|
|
"epoch": 0.2787074437391806,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004996974487179915,
|
|
"loss": 6.7051,
|
|
"mean_token_accuracy": 0.1497049979865551,
|
|
"num_tokens": 6085550.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 6.791318702697754,
|
|
"epoch": 0.27928447778418924,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004996953057351195,
|
|
"loss": 6.7501,
|
|
"mean_token_accuracy": 0.14439913034439086,
|
|
"num_tokens": 6096749.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 6.856110286712647,
|
|
"epoch": 0.27986151182919794,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004996931551947327,
|
|
"loss": 6.6462,
|
|
"mean_token_accuracy": 0.14740088433027268,
|
|
"num_tokens": 6109490.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 6.801775121688843,
|
|
"epoch": 0.2804385458742066,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004996909970969031,
|
|
"loss": 6.8126,
|
|
"mean_token_accuracy": 0.13891539573669434,
|
|
"num_tokens": 6122656.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 6.949873161315918,
|
|
"epoch": 0.2810155799192152,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004996888314417034,
|
|
"loss": 6.7062,
|
|
"mean_token_accuracy": 0.14734956696629525,
|
|
"num_tokens": 6135461.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 6.737766313552856,
|
|
"epoch": 0.2815926139642239,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004996866582292067,
|
|
"loss": 6.7563,
|
|
"mean_token_accuracy": 0.1486450642347336,
|
|
"num_tokens": 6147698.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 6.906767129898071,
|
|
"epoch": 0.28216964800923255,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004996844774594856,
|
|
"loss": 6.6995,
|
|
"mean_token_accuracy": 0.15024199485778808,
|
|
"num_tokens": 6160456.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 6.721561002731323,
|
|
"epoch": 0.2827466820542412,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004996822891326138,
|
|
"loss": 6.6952,
|
|
"mean_token_accuracy": 0.14862452447414398,
|
|
"num_tokens": 6173606.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 6.840061807632447,
|
|
"epoch": 0.28332371609924983,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004996800932486648,
|
|
"loss": 6.7195,
|
|
"mean_token_accuracy": 0.14363468587398528,
|
|
"num_tokens": 6185355.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 6.82087197303772,
|
|
"epoch": 0.28390075014425853,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004996778898077126,
|
|
"loss": 6.7452,
|
|
"mean_token_accuracy": 0.14526572227478027,
|
|
"num_tokens": 6198154.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 6.825610780715943,
|
|
"epoch": 0.28447778418926717,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004996756788098309,
|
|
"loss": 6.6295,
|
|
"mean_token_accuracy": 0.1540285274386406,
|
|
"num_tokens": 6209901.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 6.724011659622192,
|
|
"epoch": 0.2850548182342758,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004996734602550945,
|
|
"loss": 6.6914,
|
|
"mean_token_accuracy": 0.14896469041705132,
|
|
"num_tokens": 6222052.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 6.822287702560425,
|
|
"epoch": 0.2856318522792845,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004996712341435779,
|
|
"loss": 6.6874,
|
|
"mean_token_accuracy": 0.1531086578965187,
|
|
"num_tokens": 6235112.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 6.779771232604981,
|
|
"epoch": 0.28620888632429314,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996690004753559,
|
|
"loss": 6.7241,
|
|
"mean_token_accuracy": 0.1425678864121437,
|
|
"num_tokens": 6248225.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 6.827151918411255,
|
|
"epoch": 0.2867859203693018,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004996667592505037,
|
|
"loss": 6.6731,
|
|
"mean_token_accuracy": 0.15249393209815026,
|
|
"num_tokens": 6259518.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 6.752045726776123,
|
|
"epoch": 0.2873629544143104,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004996645104690967,
|
|
"loss": 6.6827,
|
|
"mean_token_accuracy": 0.1392819695174694,
|
|
"num_tokens": 6271832.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 6.84897813796997,
|
|
"epoch": 0.2879399884593191,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004996622541312103,
|
|
"loss": 6.7198,
|
|
"mean_token_accuracy": 0.1458892524242401,
|
|
"num_tokens": 6284328.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 6.746988677978516,
|
|
"epoch": 0.28851702250432776,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004996599902369207,
|
|
"loss": 6.6617,
|
|
"mean_token_accuracy": 0.1465374030172825,
|
|
"num_tokens": 6296100.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 6.685969734191895,
|
|
"epoch": 0.2890940565493364,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004996577187863039,
|
|
"loss": 6.6493,
|
|
"mean_token_accuracy": 0.15570555478334427,
|
|
"num_tokens": 6308262.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 6.827516984939575,
|
|
"epoch": 0.2896710905943451,
|
|
"grad_norm": 0.75,
|
|
"learning_rate": 0.0004996554397794364,
|
|
"loss": 6.6959,
|
|
"mean_token_accuracy": 0.1382772818207741,
|
|
"num_tokens": 6319953.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 6.807676601409912,
|
|
"epoch": 0.29024812463935373,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004996531532163947,
|
|
"loss": 6.6329,
|
|
"mean_token_accuracy": 0.15100528299808502,
|
|
"num_tokens": 6332953.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 6.77238130569458,
|
|
"epoch": 0.2908251586843624,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004996508590972558,
|
|
"loss": 6.6873,
|
|
"mean_token_accuracy": 0.1495242863893509,
|
|
"num_tokens": 6345692.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 6.78111777305603,
|
|
"epoch": 0.291402192729371,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004996485574220969,
|
|
"loss": 6.6698,
|
|
"mean_token_accuracy": 0.14763007685542107,
|
|
"num_tokens": 6358058.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 6.842091226577759,
|
|
"epoch": 0.2919792267743797,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004996462481909953,
|
|
"loss": 6.7157,
|
|
"mean_token_accuracy": 0.149982488155365,
|
|
"num_tokens": 6370469.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 6.7619242668151855,
|
|
"epoch": 0.29255626081938835,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004996439314040287,
|
|
"loss": 6.7762,
|
|
"mean_token_accuracy": 0.1360616222023964,
|
|
"num_tokens": 6384333.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 6.855607652664185,
|
|
"epoch": 0.293133294864397,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.000499641607061275,
|
|
"loss": 6.7016,
|
|
"mean_token_accuracy": 0.1434970736503601,
|
|
"num_tokens": 6397688.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 6.819028520584107,
|
|
"epoch": 0.2937103289094057,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004996392751628126,
|
|
"loss": 6.6602,
|
|
"mean_token_accuracy": 0.14889983236789703,
|
|
"num_tokens": 6410188.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 6.722808504104615,
|
|
"epoch": 0.2942873629544143,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004996369357087196,
|
|
"loss": 6.6805,
|
|
"mean_token_accuracy": 0.14856439232826232,
|
|
"num_tokens": 6423313.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 6.845215559005737,
|
|
"epoch": 0.29486439699942296,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.000499634588699075,
|
|
"loss": 6.7135,
|
|
"mean_token_accuracy": 0.14631582498550416,
|
|
"num_tokens": 6435853.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 6.713652801513672,
|
|
"epoch": 0.2954414310444316,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004996322341339575,
|
|
"loss": 6.6397,
|
|
"mean_token_accuracy": 0.14477873146533965,
|
|
"num_tokens": 6448659.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 6.7395094871521,
|
|
"epoch": 0.2960184650894403,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004996298720134465,
|
|
"loss": 6.6985,
|
|
"mean_token_accuracy": 0.14935118854045867,
|
|
"num_tokens": 6460534.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 6.828916740417481,
|
|
"epoch": 0.29659549913444894,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004996275023376213,
|
|
"loss": 6.6741,
|
|
"mean_token_accuracy": 0.14743488729000093,
|
|
"num_tokens": 6472368.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 6.772326993942261,
|
|
"epoch": 0.2971725331794576,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004996251251065615,
|
|
"loss": 6.6763,
|
|
"mean_token_accuracy": 0.14429058134555817,
|
|
"num_tokens": 6485430.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 6.764473915100098,
|
|
"epoch": 0.2977495672244662,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004996227403203473,
|
|
"loss": 6.656,
|
|
"mean_token_accuracy": 0.15102906972169877,
|
|
"num_tokens": 6497303.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 6.816898822784424,
|
|
"epoch": 0.2983266012694749,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004996203479790589,
|
|
"loss": 6.7282,
|
|
"mean_token_accuracy": 0.15129706114530564,
|
|
"num_tokens": 6510154.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 6.819794940948486,
|
|
"epoch": 0.29890363531448355,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004996179480827764,
|
|
"loss": 6.7073,
|
|
"mean_token_accuracy": 0.14853841662406922,
|
|
"num_tokens": 6523091.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 6.845903539657593,
|
|
"epoch": 0.2994806693594922,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000499615540631581,
|
|
"loss": 6.6167,
|
|
"mean_token_accuracy": 0.15361105501651764,
|
|
"num_tokens": 6536043.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 6.660343933105469,
|
|
"epoch": 0.3000577034045009,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004996131256255534,
|
|
"loss": 6.6328,
|
|
"mean_token_accuracy": 0.15334705710411073,
|
|
"num_tokens": 6548227.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 6.819034004211426,
|
|
"epoch": 0.3006347374495095,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004996107030647749,
|
|
"loss": 6.692,
|
|
"mean_token_accuracy": 0.14152004942297935,
|
|
"num_tokens": 6560204.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 6.756571340560913,
|
|
"epoch": 0.30121177149451817,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004996082729493269,
|
|
"loss": 6.6744,
|
|
"mean_token_accuracy": 0.15325141996145247,
|
|
"num_tokens": 6573235.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 6.73859806060791,
|
|
"epoch": 0.3017888055395268,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004996058352792913,
|
|
"loss": 6.7054,
|
|
"mean_token_accuracy": 0.14550871774554253,
|
|
"num_tokens": 6585118.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 6.755663061141968,
|
|
"epoch": 0.3023658395845355,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00049960339005475,
|
|
"loss": 6.5996,
|
|
"mean_token_accuracy": 0.14909390211105347,
|
|
"num_tokens": 6596690.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 6.764217233657837,
|
|
"epoch": 0.30294287362954414,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004996009372757852,
|
|
"loss": 6.5965,
|
|
"mean_token_accuracy": 0.1569955661892891,
|
|
"num_tokens": 6609076.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 6.729177474975586,
|
|
"epoch": 0.3035199076745528,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004995984769424795,
|
|
"loss": 6.7118,
|
|
"mean_token_accuracy": 0.14563166871666908,
|
|
"num_tokens": 6621352.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 6.814102125167847,
|
|
"epoch": 0.3040969417195615,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004995960090549155,
|
|
"loss": 6.5982,
|
|
"mean_token_accuracy": 0.1499995172023773,
|
|
"num_tokens": 6633924.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 6.754621171951294,
|
|
"epoch": 0.3046739757645701,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004995935336131764,
|
|
"loss": 6.7238,
|
|
"mean_token_accuracy": 0.1473952054977417,
|
|
"num_tokens": 6646490.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 6.8332771301269535,
|
|
"epoch": 0.30525100980957875,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004995910506173452,
|
|
"loss": 6.6893,
|
|
"mean_token_accuracy": 0.14203061014413834,
|
|
"num_tokens": 6660171.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 6.768089628219604,
|
|
"epoch": 0.3058280438545874,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004995885600675059,
|
|
"loss": 6.7052,
|
|
"mean_token_accuracy": 0.1487940713763237,
|
|
"num_tokens": 6673505.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 6.782451200485229,
|
|
"epoch": 0.3064050778995961,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004995860619637415,
|
|
"loss": 6.7004,
|
|
"mean_token_accuracy": 0.1495489463210106,
|
|
"num_tokens": 6685798.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 6.705468416213989,
|
|
"epoch": 0.30698211194460473,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004995835563061367,
|
|
"loss": 6.5514,
|
|
"mean_token_accuracy": 0.15502395033836364,
|
|
"num_tokens": 6699254.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 6.736592388153076,
|
|
"epoch": 0.30755914598961337,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004995810430947756,
|
|
"loss": 6.6154,
|
|
"mean_token_accuracy": 0.15057491064071654,
|
|
"num_tokens": 6711088.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 6.759505414962769,
|
|
"epoch": 0.30813618003462206,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004995785223297426,
|
|
"loss": 6.6807,
|
|
"mean_token_accuracy": 0.14461947679519654,
|
|
"num_tokens": 6723373.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 6.741917705535888,
|
|
"epoch": 0.3087132140796307,
|
|
"grad_norm": 0.73828125,
|
|
"learning_rate": 0.0004995759940111225,
|
|
"loss": 6.6848,
|
|
"mean_token_accuracy": 0.14381011575460434,
|
|
"num_tokens": 6737984.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 6.773638963699341,
|
|
"epoch": 0.30929024812463934,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004995734581390005,
|
|
"loss": 6.6328,
|
|
"mean_token_accuracy": 0.14959122091531754,
|
|
"num_tokens": 6751283.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 6.680616760253907,
|
|
"epoch": 0.309867282169648,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004995709147134617,
|
|
"loss": 6.6046,
|
|
"mean_token_accuracy": 0.15074616074562072,
|
|
"num_tokens": 6765012.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 6.775850296020508,
|
|
"epoch": 0.3104443162146567,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004995683637345919,
|
|
"loss": 6.6392,
|
|
"mean_token_accuracy": 0.15261454582214357,
|
|
"num_tokens": 6777708.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 6.7052594184875485,
|
|
"epoch": 0.3110213502596653,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004995658052024765,
|
|
"loss": 6.5669,
|
|
"mean_token_accuracy": 0.16054244190454484,
|
|
"num_tokens": 6791325.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 6.722959423065186,
|
|
"epoch": 0.31159838430467396,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004995632391172019,
|
|
"loss": 6.718,
|
|
"mean_token_accuracy": 0.13914413154125213,
|
|
"num_tokens": 6805659.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 6.812787103652954,
|
|
"epoch": 0.31217541834968265,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004995606654788543,
|
|
"loss": 6.637,
|
|
"mean_token_accuracy": 0.14895061701536177,
|
|
"num_tokens": 6818110.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 6.727897787094117,
|
|
"epoch": 0.3127524523946913,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004995580842875202,
|
|
"loss": 6.6378,
|
|
"mean_token_accuracy": 0.14641101211309432,
|
|
"num_tokens": 6830959.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 6.807159328460694,
|
|
"epoch": 0.31332948643969993,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004995554955432866,
|
|
"loss": 6.6977,
|
|
"mean_token_accuracy": 0.14908618479967117,
|
|
"num_tokens": 6843318.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 6.718437242507934,
|
|
"epoch": 0.3139065204847086,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004995528992462404,
|
|
"loss": 6.5811,
|
|
"mean_token_accuracy": 0.1510560542345047,
|
|
"num_tokens": 6855154.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 6.71838641166687,
|
|
"epoch": 0.31448355452971727,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.000499550295396469,
|
|
"loss": 6.6456,
|
|
"mean_token_accuracy": 0.14983784556388854,
|
|
"num_tokens": 6867428.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 6.756401872634887,
|
|
"epoch": 0.3150605885747259,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004995476839940598,
|
|
"loss": 6.6363,
|
|
"mean_token_accuracy": 0.15786276906728744,
|
|
"num_tokens": 6879989.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 6.777546310424805,
|
|
"epoch": 0.31563762261973455,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.000499545065039101,
|
|
"loss": 6.6447,
|
|
"mean_token_accuracy": 0.1432705909013748,
|
|
"num_tokens": 6893179.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 6.786166429519653,
|
|
"epoch": 0.31621465666474324,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004995424385316803,
|
|
"loss": 6.6354,
|
|
"mean_token_accuracy": 0.1462482675909996,
|
|
"num_tokens": 6905647.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 6.713575553894043,
|
|
"epoch": 0.3167916907097519,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004995398044718863,
|
|
"loss": 6.6146,
|
|
"mean_token_accuracy": 0.15827973783016205,
|
|
"num_tokens": 6917361.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 6.780123996734619,
|
|
"epoch": 0.3173687247547605,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004995371628598074,
|
|
"loss": 6.6339,
|
|
"mean_token_accuracy": 0.14651651680469513,
|
|
"num_tokens": 6929515.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 6.748660898208618,
|
|
"epoch": 0.31794575879976916,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004995345136955328,
|
|
"loss": 6.6036,
|
|
"mean_token_accuracy": 0.15300127118825912,
|
|
"num_tokens": 6942265.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 6.7021361827850345,
|
|
"epoch": 0.31852279284477786,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004995318569791512,
|
|
"loss": 6.661,
|
|
"mean_token_accuracy": 0.15360585749149322,
|
|
"num_tokens": 6955151.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 6.784101343154907,
|
|
"epoch": 0.3190998268897865,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004995291927107522,
|
|
"loss": 6.6172,
|
|
"mean_token_accuracy": 0.1502458855509758,
|
|
"num_tokens": 6968378.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 6.669129657745361,
|
|
"epoch": 0.31967686093479514,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004995265208904252,
|
|
"loss": 6.6216,
|
|
"mean_token_accuracy": 0.14923231303691864,
|
|
"num_tokens": 6980083.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 6.747028255462647,
|
|
"epoch": 0.32025389497980383,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004995238415182603,
|
|
"loss": 6.6581,
|
|
"mean_token_accuracy": 0.1432106763124466,
|
|
"num_tokens": 6992981.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 6.844202852249145,
|
|
"epoch": 0.3208309290248125,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004995211545943476,
|
|
"loss": 6.6409,
|
|
"mean_token_accuracy": 0.14744580015540124,
|
|
"num_tokens": 7006115.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 6.653217697143555,
|
|
"epoch": 0.3214079630698211,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004995184601187772,
|
|
"loss": 6.6014,
|
|
"mean_token_accuracy": 0.15577706843614578,
|
|
"num_tokens": 7019176.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 6.641081857681274,
|
|
"epoch": 0.32198499711482975,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.00049951575809164,
|
|
"loss": 6.5282,
|
|
"mean_token_accuracy": 0.16437966525554656,
|
|
"num_tokens": 7031214.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 6.66480655670166,
|
|
"epoch": 0.32256203115983845,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004995130485130269,
|
|
"loss": 6.6088,
|
|
"mean_token_accuracy": 0.15185024589300156,
|
|
"num_tokens": 7044702.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 6.752944231033325,
|
|
"epoch": 0.3231390652048471,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004995103313830289,
|
|
"loss": 6.6018,
|
|
"mean_token_accuracy": 0.15165336132049562,
|
|
"num_tokens": 7056489.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 6.729215812683106,
|
|
"epoch": 0.3237160992498557,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004995076067017373,
|
|
"loss": 6.6406,
|
|
"mean_token_accuracy": 0.14547208398580552,
|
|
"num_tokens": 7068972.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 6.74854302406311,
|
|
"epoch": 0.3242931332948644,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004995048744692439,
|
|
"loss": 6.5746,
|
|
"mean_token_accuracy": 0.15244885683059692,
|
|
"num_tokens": 7080894.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 6.713599061965942,
|
|
"epoch": 0.32487016733987306,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004995021346856405,
|
|
"loss": 6.6122,
|
|
"mean_token_accuracy": 0.14793540984392167,
|
|
"num_tokens": 7094427.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 6.65841121673584,
|
|
"epoch": 0.3254472013848817,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004994993873510196,
|
|
"loss": 6.5596,
|
|
"mean_token_accuracy": 0.16087264865636824,
|
|
"num_tokens": 7105710.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 6.793656873703003,
|
|
"epoch": 0.32602423542989034,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004994966324654731,
|
|
"loss": 6.5838,
|
|
"mean_token_accuracy": 0.14802931025624275,
|
|
"num_tokens": 7119042.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 6.634446716308593,
|
|
"epoch": 0.32660126947489904,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000499493870029094,
|
|
"loss": 6.6077,
|
|
"mean_token_accuracy": 0.148269946873188,
|
|
"num_tokens": 7132146.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 6.726744699478149,
|
|
"epoch": 0.3271783035199077,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004994911000419749,
|
|
"loss": 6.562,
|
|
"mean_token_accuracy": 0.15012803077697753,
|
|
"num_tokens": 7144805.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 6.6751384258270265,
|
|
"epoch": 0.3277553375649163,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004994883225042093,
|
|
"loss": 6.5475,
|
|
"mean_token_accuracy": 0.16178591400384904,
|
|
"num_tokens": 7156906.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 6.753067064285278,
|
|
"epoch": 0.328332371609925,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004994855374158905,
|
|
"loss": 6.5298,
|
|
"mean_token_accuracy": 0.15081926435232162,
|
|
"num_tokens": 7169451.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 6.7513651847839355,
|
|
"epoch": 0.32890940565493365,
|
|
"grad_norm": 0.75,
|
|
"learning_rate": 0.000499482744777112,
|
|
"loss": 6.675,
|
|
"mean_token_accuracy": 0.14404026567935943,
|
|
"num_tokens": 7183211.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 6.7373758316040036,
|
|
"epoch": 0.3294864396999423,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000499479944587968,
|
|
"loss": 6.6147,
|
|
"mean_token_accuracy": 0.1517378196120262,
|
|
"num_tokens": 7196062.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 6.794651794433594,
|
|
"epoch": 0.33006347374495093,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004994771368485526,
|
|
"loss": 6.7089,
|
|
"mean_token_accuracy": 0.14450829550623895,
|
|
"num_tokens": 7208079.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 6.799776029586792,
|
|
"epoch": 0.3306405077899596,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004994743215589602,
|
|
"loss": 6.656,
|
|
"mean_token_accuracy": 0.14721468538045884,
|
|
"num_tokens": 7221537.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 6.66144700050354,
|
|
"epoch": 0.33121754183496827,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004994714987192854,
|
|
"loss": 6.6285,
|
|
"mean_token_accuracy": 0.14779918044805526,
|
|
"num_tokens": 7234472.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 6.707424116134644,
|
|
"epoch": 0.3317945758799769,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004994686683296234,
|
|
"loss": 6.5847,
|
|
"mean_token_accuracy": 0.15313812494277954,
|
|
"num_tokens": 7247818.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 6.695041847229004,
|
|
"epoch": 0.3323716099249856,
|
|
"grad_norm": 0.7421875,
|
|
"learning_rate": 0.0004994658303900691,
|
|
"loss": 6.6729,
|
|
"mean_token_accuracy": 0.15236686170101166,
|
|
"num_tokens": 7261351.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 6.677237319946289,
|
|
"epoch": 0.33294864396999424,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004994629849007182,
|
|
"loss": 6.5247,
|
|
"mean_token_accuracy": 0.15475201308727266,
|
|
"num_tokens": 7274310.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 6.6607647895812985,
|
|
"epoch": 0.3335256780150029,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004994601318616663,
|
|
"loss": 6.5631,
|
|
"mean_token_accuracy": 0.15157887637615203,
|
|
"num_tokens": 7286560.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 6.811610126495362,
|
|
"epoch": 0.3341027120600115,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004994572712730092,
|
|
"loss": 6.6486,
|
|
"mean_token_accuracy": 0.14426497519016265,
|
|
"num_tokens": 7300337.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 6.691228675842285,
|
|
"epoch": 0.3346797461050202,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004994544031348434,
|
|
"loss": 6.6194,
|
|
"mean_token_accuracy": 0.1486266866326332,
|
|
"num_tokens": 7313436.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 6.666589450836182,
|
|
"epoch": 0.33525678015002885,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004994515274472653,
|
|
"loss": 6.4758,
|
|
"mean_token_accuracy": 0.16475249975919723,
|
|
"num_tokens": 7325766.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 6.611915159225464,
|
|
"epoch": 0.3358338141950375,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004994486442103715,
|
|
"loss": 6.5599,
|
|
"mean_token_accuracy": 0.14973128736019134,
|
|
"num_tokens": 7337904.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 6.648727655410767,
|
|
"epoch": 0.3364108482400462,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.000499445753424259,
|
|
"loss": 6.5601,
|
|
"mean_token_accuracy": 0.15160418599843978,
|
|
"num_tokens": 7350448.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 6.7852109432220455,
|
|
"epoch": 0.33698788228505483,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004994428550890251,
|
|
"loss": 6.5957,
|
|
"mean_token_accuracy": 0.1476546384394169,
|
|
"num_tokens": 7363859.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 6.703492069244385,
|
|
"epoch": 0.33756491633006347,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004994399492047672,
|
|
"loss": 6.6148,
|
|
"mean_token_accuracy": 0.1489669606089592,
|
|
"num_tokens": 7376963.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 6.677239227294922,
|
|
"epoch": 0.3381419503750721,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004994370357715832,
|
|
"loss": 6.6462,
|
|
"mean_token_accuracy": 0.14910098984837533,
|
|
"num_tokens": 7390370.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 6.712501335144043,
|
|
"epoch": 0.3387189844200808,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.000499434114789571,
|
|
"loss": 6.5836,
|
|
"mean_token_accuracy": 0.15484795421361924,
|
|
"num_tokens": 7402851.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 6.638098287582397,
|
|
"epoch": 0.33929601846508944,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004994311862588286,
|
|
"loss": 6.6003,
|
|
"mean_token_accuracy": 0.14664260819554328,
|
|
"num_tokens": 7415428.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 6.786514616012573,
|
|
"epoch": 0.3398730525100981,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004994282501794551,
|
|
"loss": 6.5911,
|
|
"mean_token_accuracy": 0.15048429667949675,
|
|
"num_tokens": 7428420.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 6.686578941345215,
|
|
"epoch": 0.3404500865551068,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004994253065515486,
|
|
"loss": 6.6436,
|
|
"mean_token_accuracy": 0.15113215446472167,
|
|
"num_tokens": 7439626.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 6.725645685195923,
|
|
"epoch": 0.3410271206001154,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004994223553752084,
|
|
"loss": 6.5901,
|
|
"mean_token_accuracy": 0.1514264941215515,
|
|
"num_tokens": 7452797.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 6.65960373878479,
|
|
"epoch": 0.34160415464512406,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004994193966505339,
|
|
"loss": 6.5682,
|
|
"mean_token_accuracy": 0.15812762975692748,
|
|
"num_tokens": 7464311.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 6.6784382343292235,
|
|
"epoch": 0.3421811886901327,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004994164303776244,
|
|
"loss": 6.5852,
|
|
"mean_token_accuracy": 0.15011241137981415,
|
|
"num_tokens": 7475706.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 6.7143481254577635,
|
|
"epoch": 0.3427582227351414,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004994134565565797,
|
|
"loss": 6.6579,
|
|
"mean_token_accuracy": 0.1478770911693573,
|
|
"num_tokens": 7489077.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 6.736965751647949,
|
|
"epoch": 0.34333525678015003,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004994104751875,
|
|
"loss": 6.6074,
|
|
"mean_token_accuracy": 0.15452702343463898,
|
|
"num_tokens": 7501598.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 6.608485174179077,
|
|
"epoch": 0.3439122908251587,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004994074862704854,
|
|
"loss": 6.4109,
|
|
"mean_token_accuracy": 0.16355000287294388,
|
|
"num_tokens": 7514776.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 6.584009838104248,
|
|
"epoch": 0.3444893248701673,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004994044898056363,
|
|
"loss": 6.5766,
|
|
"mean_token_accuracy": 0.15253832191228867,
|
|
"num_tokens": 7527795.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 6.702622604370117,
|
|
"epoch": 0.345066358915176,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004994014857930538,
|
|
"loss": 6.4427,
|
|
"mean_token_accuracy": 0.1624614641070366,
|
|
"num_tokens": 7541392.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 6.615006446838379,
|
|
"epoch": 0.34564339296018465,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004993984742328387,
|
|
"loss": 6.601,
|
|
"mean_token_accuracy": 0.15036358386278154,
|
|
"num_tokens": 7554369.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 6.672338581085205,
|
|
"epoch": 0.3462204270051933,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004993954551250925,
|
|
"loss": 6.603,
|
|
"mean_token_accuracy": 0.154202963411808,
|
|
"num_tokens": 7567528.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.3462204270051933,
|
|
"eval_entropy": 6.5903391438110805,
|
|
"eval_loss": 6.633339881896973,
|
|
"eval_mean_token_accuracy": 0.15343972800560624,
|
|
"eval_num_tokens": 7567528.0,
|
|
"eval_runtime": 17.6947,
|
|
"eval_samples_per_second": 1590.081,
|
|
"eval_steps_per_second": 198.76,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"entropy": 6.706592988967896,
|
|
"epoch": 0.346797461050202,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004993924284699165,
|
|
"loss": 6.5524,
|
|
"mean_token_accuracy": 0.15312376469373704,
|
|
"num_tokens": 7579146.0,
|
|
"step": 3005
|
|
},
|
|
{
|
|
"entropy": 6.66014552116394,
|
|
"epoch": 0.3473744950952106,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004993893942674127,
|
|
"loss": 6.64,
|
|
"mean_token_accuracy": 0.1477951481938362,
|
|
"num_tokens": 7591902.0,
|
|
"step": 3010
|
|
},
|
|
{
|
|
"entropy": 6.799589061737061,
|
|
"epoch": 0.34795152914021926,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.000499386352517683,
|
|
"loss": 6.6448,
|
|
"mean_token_accuracy": 0.1552356779575348,
|
|
"num_tokens": 7605565.0,
|
|
"step": 3015
|
|
},
|
|
{
|
|
"entropy": 6.7373872756958,
|
|
"epoch": 0.3485285631852279,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.00049938330322083,
|
|
"loss": 6.5734,
|
|
"mean_token_accuracy": 0.15451606512069702,
|
|
"num_tokens": 7618380.0,
|
|
"step": 3020
|
|
},
|
|
{
|
|
"entropy": 6.653174638748169,
|
|
"epoch": 0.3491055972302366,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004993802463769558,
|
|
"loss": 6.6035,
|
|
"mean_token_accuracy": 0.14853976368904115,
|
|
"num_tokens": 7632092.0,
|
|
"step": 3025
|
|
},
|
|
{
|
|
"entropy": 6.6859503269195555,
|
|
"epoch": 0.34968263127524524,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004993771819861636,
|
|
"loss": 6.6097,
|
|
"mean_token_accuracy": 0.14797925502061843,
|
|
"num_tokens": 7644185.0,
|
|
"step": 3030
|
|
},
|
|
{
|
|
"entropy": 6.741736364364624,
|
|
"epoch": 0.3502596653202539,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004993741100485564,
|
|
"loss": 6.5012,
|
|
"mean_token_accuracy": 0.15530159771442414,
|
|
"num_tokens": 7656635.0,
|
|
"step": 3035
|
|
},
|
|
{
|
|
"entropy": 6.64942421913147,
|
|
"epoch": 0.35083669936526257,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004993710305642374,
|
|
"loss": 6.5621,
|
|
"mean_token_accuracy": 0.15173622369766235,
|
|
"num_tokens": 7669643.0,
|
|
"step": 3040
|
|
},
|
|
{
|
|
"entropy": 6.688398933410644,
|
|
"epoch": 0.3514137334102712,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004993679435333102,
|
|
"loss": 6.5822,
|
|
"mean_token_accuracy": 0.14759134352207184,
|
|
"num_tokens": 7682489.0,
|
|
"step": 3045
|
|
},
|
|
{
|
|
"entropy": 6.630285358428955,
|
|
"epoch": 0.35199076745527985,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004993648489558788,
|
|
"loss": 6.5269,
|
|
"mean_token_accuracy": 0.15159836709499358,
|
|
"num_tokens": 7696670.0,
|
|
"step": 3050
|
|
},
|
|
{
|
|
"entropy": 6.6929933547973635,
|
|
"epoch": 0.3525678015002885,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004993617468320471,
|
|
"loss": 6.5451,
|
|
"mean_token_accuracy": 0.15906845778226852,
|
|
"num_tokens": 7709054.0,
|
|
"step": 3055
|
|
},
|
|
{
|
|
"entropy": 6.634079313278198,
|
|
"epoch": 0.3531448355452972,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004993586371619193,
|
|
"loss": 6.5548,
|
|
"mean_token_accuracy": 0.15278329253196715,
|
|
"num_tokens": 7721710.0,
|
|
"step": 3060
|
|
},
|
|
{
|
|
"entropy": 6.722148132324219,
|
|
"epoch": 0.3537218695903058,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004993555199456004,
|
|
"loss": 6.6095,
|
|
"mean_token_accuracy": 0.1526441752910614,
|
|
"num_tokens": 7733689.0,
|
|
"step": 3065
|
|
},
|
|
{
|
|
"entropy": 6.66739444732666,
|
|
"epoch": 0.35429890363531447,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004993523951831949,
|
|
"loss": 6.5803,
|
|
"mean_token_accuracy": 0.1555978015065193,
|
|
"num_tokens": 7745735.0,
|
|
"step": 3070
|
|
},
|
|
{
|
|
"entropy": 6.7588379859924315,
|
|
"epoch": 0.35487593768032316,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004993492628748081,
|
|
"loss": 6.5894,
|
|
"mean_token_accuracy": 0.14369118213653564,
|
|
"num_tokens": 7757352.0,
|
|
"step": 3075
|
|
},
|
|
{
|
|
"entropy": 6.6846785068511965,
|
|
"epoch": 0.3554529717253318,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004993461230205453,
|
|
"loss": 6.5369,
|
|
"mean_token_accuracy": 0.14949805587530135,
|
|
"num_tokens": 7768363.0,
|
|
"step": 3080
|
|
},
|
|
{
|
|
"entropy": 6.668369150161743,
|
|
"epoch": 0.35603000577034044,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004993429756205121,
|
|
"loss": 6.6618,
|
|
"mean_token_accuracy": 0.14399161487817763,
|
|
"num_tokens": 7781133.0,
|
|
"step": 3085
|
|
},
|
|
{
|
|
"entropy": 6.810355234146118,
|
|
"epoch": 0.3566070398153491,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004993398206748142,
|
|
"loss": 6.6461,
|
|
"mean_token_accuracy": 0.14326538443565368,
|
|
"num_tokens": 7794445.0,
|
|
"step": 3090
|
|
},
|
|
{
|
|
"entropy": 6.689512538909912,
|
|
"epoch": 0.3571840738603578,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004993366581835581,
|
|
"loss": 6.5431,
|
|
"mean_token_accuracy": 0.15431275665760041,
|
|
"num_tokens": 7807601.0,
|
|
"step": 3095
|
|
},
|
|
{
|
|
"entropy": 6.592484951019287,
|
|
"epoch": 0.3577611079053664,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004993334881468498,
|
|
"loss": 6.5139,
|
|
"mean_token_accuracy": 0.1561570018529892,
|
|
"num_tokens": 7819821.0,
|
|
"step": 3100
|
|
},
|
|
{
|
|
"entropy": 6.691237831115723,
|
|
"epoch": 0.35833814195037506,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004993303105647961,
|
|
"loss": 6.5343,
|
|
"mean_token_accuracy": 0.15187687054276466,
|
|
"num_tokens": 7832214.0,
|
|
"step": 3105
|
|
},
|
|
{
|
|
"entropy": 6.638499784469604,
|
|
"epoch": 0.35891517599538375,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004993271254375038,
|
|
"loss": 6.5741,
|
|
"mean_token_accuracy": 0.16051387637853623,
|
|
"num_tokens": 7844566.0,
|
|
"step": 3110
|
|
},
|
|
{
|
|
"entropy": 6.710163545608521,
|
|
"epoch": 0.3594922100403924,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.00049932393276508,
|
|
"loss": 6.5434,
|
|
"mean_token_accuracy": 0.15657812282443045,
|
|
"num_tokens": 7857965.0,
|
|
"step": 3115
|
|
},
|
|
{
|
|
"entropy": 6.603605270385742,
|
|
"epoch": 0.36006924408540103,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004993207325476323,
|
|
"loss": 6.5691,
|
|
"mean_token_accuracy": 0.1569638028740883,
|
|
"num_tokens": 7870902.0,
|
|
"step": 3120
|
|
},
|
|
{
|
|
"entropy": 6.778155136108398,
|
|
"epoch": 0.36064627813040967,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004993175247852681,
|
|
"loss": 6.6299,
|
|
"mean_token_accuracy": 0.14303801953792572,
|
|
"num_tokens": 7883694.0,
|
|
"step": 3125
|
|
},
|
|
{
|
|
"entropy": 6.624432468414307,
|
|
"epoch": 0.36122331217541837,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004993143094780954,
|
|
"loss": 6.52,
|
|
"mean_token_accuracy": 0.1570071041584015,
|
|
"num_tokens": 7896693.0,
|
|
"step": 3130
|
|
},
|
|
{
|
|
"entropy": 6.6653848648071286,
|
|
"epoch": 0.361800346220427,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0004993110866262224,
|
|
"loss": 6.519,
|
|
"mean_token_accuracy": 0.15744696259498597,
|
|
"num_tokens": 7910010.0,
|
|
"step": 3135
|
|
},
|
|
{
|
|
"entropy": 6.7992534160614015,
|
|
"epoch": 0.36237738026543564,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004993078562297573,
|
|
"loss": 6.6268,
|
|
"mean_token_accuracy": 0.13919368460774423,
|
|
"num_tokens": 7922026.0,
|
|
"step": 3140
|
|
},
|
|
{
|
|
"entropy": 6.626803922653198,
|
|
"epoch": 0.36295441431044434,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004993046182888089,
|
|
"loss": 6.5974,
|
|
"mean_token_accuracy": 0.14518485516309737,
|
|
"num_tokens": 7934633.0,
|
|
"step": 3145
|
|
},
|
|
{
|
|
"entropy": 6.703473472595215,
|
|
"epoch": 0.363531448355453,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004993013728034861,
|
|
"loss": 6.5012,
|
|
"mean_token_accuracy": 0.15910948514938356,
|
|
"num_tokens": 7947189.0,
|
|
"step": 3150
|
|
},
|
|
{
|
|
"entropy": 6.645997714996338,
|
|
"epoch": 0.3641084824004616,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.000499298119773898,
|
|
"loss": 6.5815,
|
|
"mean_token_accuracy": 0.15228615552186966,
|
|
"num_tokens": 7961283.0,
|
|
"step": 3155
|
|
},
|
|
{
|
|
"entropy": 6.584298086166382,
|
|
"epoch": 0.36468551644547026,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004992948592001541,
|
|
"loss": 6.549,
|
|
"mean_token_accuracy": 0.157489425688982,
|
|
"num_tokens": 7974589.0,
|
|
"step": 3160
|
|
},
|
|
{
|
|
"entropy": 6.723839282989502,
|
|
"epoch": 0.36526255049047895,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.000499291591082364,
|
|
"loss": 6.5873,
|
|
"mean_token_accuracy": 0.1510259687900543,
|
|
"num_tokens": 7987148.0,
|
|
"step": 3165
|
|
},
|
|
{
|
|
"entropy": 6.713741779327393,
|
|
"epoch": 0.3658395845354876,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004992883154206377,
|
|
"loss": 6.6151,
|
|
"mean_token_accuracy": 0.15011707395315171,
|
|
"num_tokens": 8000679.0,
|
|
"step": 3170
|
|
},
|
|
{
|
|
"entropy": 6.601009368896484,
|
|
"epoch": 0.36641661858049623,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004992850322150853,
|
|
"loss": 6.4989,
|
|
"mean_token_accuracy": 0.1541821539402008,
|
|
"num_tokens": 8014011.0,
|
|
"step": 3175
|
|
},
|
|
{
|
|
"entropy": 6.708580017089844,
|
|
"epoch": 0.36699365262550493,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004992817414658172,
|
|
"loss": 6.5279,
|
|
"mean_token_accuracy": 0.1508907914161682,
|
|
"num_tokens": 8026022.0,
|
|
"step": 3180
|
|
},
|
|
{
|
|
"entropy": 6.696759557723999,
|
|
"epoch": 0.36757068667051357,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004992784431729442,
|
|
"loss": 6.5946,
|
|
"mean_token_accuracy": 0.15226232409477233,
|
|
"num_tokens": 8040123.0,
|
|
"step": 3185
|
|
},
|
|
{
|
|
"entropy": 6.711783027648925,
|
|
"epoch": 0.3681477207155222,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004992751373365771,
|
|
"loss": 6.5655,
|
|
"mean_token_accuracy": 0.1614807665348053,
|
|
"num_tokens": 8053320.0,
|
|
"step": 3190
|
|
},
|
|
{
|
|
"entropy": 6.583008337020874,
|
|
"epoch": 0.36872475476053085,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004992718239568273,
|
|
"loss": 6.5506,
|
|
"mean_token_accuracy": 0.15854466408491136,
|
|
"num_tokens": 8066682.0,
|
|
"step": 3195
|
|
},
|
|
{
|
|
"entropy": 6.743299245834351,
|
|
"epoch": 0.36930178880553954,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.000499268503033806,
|
|
"loss": 6.5441,
|
|
"mean_token_accuracy": 0.15438564270734786,
|
|
"num_tokens": 8078887.0,
|
|
"step": 3200
|
|
},
|
|
{
|
|
"entropy": 6.632726764678955,
|
|
"epoch": 0.3698788228505482,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004992651745676249,
|
|
"loss": 6.5254,
|
|
"mean_token_accuracy": 0.14970515072345733,
|
|
"num_tokens": 8090801.0,
|
|
"step": 3205
|
|
},
|
|
{
|
|
"entropy": 6.689233827590942,
|
|
"epoch": 0.3704558568955568,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004992618385583962,
|
|
"loss": 6.6118,
|
|
"mean_token_accuracy": 0.150309057533741,
|
|
"num_tokens": 8103387.0,
|
|
"step": 3210
|
|
},
|
|
{
|
|
"entropy": 6.599812173843384,
|
|
"epoch": 0.3710328909405655,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004992584950062319,
|
|
"loss": 6.4614,
|
|
"mean_token_accuracy": 0.15385584011673928,
|
|
"num_tokens": 8115356.0,
|
|
"step": 3215
|
|
},
|
|
{
|
|
"entropy": 6.6642804622650145,
|
|
"epoch": 0.37160992498557416,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004992551439112446,
|
|
"loss": 6.5755,
|
|
"mean_token_accuracy": 0.15292710214853286,
|
|
"num_tokens": 8129141.0,
|
|
"step": 3220
|
|
},
|
|
{
|
|
"entropy": 6.788556814193726,
|
|
"epoch": 0.3721869590305828,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004992517852735469,
|
|
"loss": 6.6057,
|
|
"mean_token_accuracy": 0.15070945620536805,
|
|
"num_tokens": 8142453.0,
|
|
"step": 3225
|
|
},
|
|
{
|
|
"entropy": 6.635298871994019,
|
|
"epoch": 0.37276399307559144,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004992484190932517,
|
|
"loss": 6.5671,
|
|
"mean_token_accuracy": 0.15121689140796662,
|
|
"num_tokens": 8154361.0,
|
|
"step": 3230
|
|
},
|
|
{
|
|
"entropy": 6.688446187973023,
|
|
"epoch": 0.37334102712060013,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004992450453704723,
|
|
"loss": 6.6194,
|
|
"mean_token_accuracy": 0.1466634377837181,
|
|
"num_tokens": 8168354.0,
|
|
"step": 3235
|
|
},
|
|
{
|
|
"entropy": 6.704189300537109,
|
|
"epoch": 0.3739180611656088,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004992416641053223,
|
|
"loss": 6.561,
|
|
"mean_token_accuracy": 0.1562179759144783,
|
|
"num_tokens": 8180700.0,
|
|
"step": 3240
|
|
},
|
|
{
|
|
"entropy": 6.630801677703857,
|
|
"epoch": 0.3744950952106174,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0004992382752979153,
|
|
"loss": 6.5558,
|
|
"mean_token_accuracy": 0.15030025094747543,
|
|
"num_tokens": 8193987.0,
|
|
"step": 3245
|
|
},
|
|
{
|
|
"entropy": 6.665634822845459,
|
|
"epoch": 0.3750721292556261,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004992348789483651,
|
|
"loss": 6.6435,
|
|
"mean_token_accuracy": 0.15180691108107566,
|
|
"num_tokens": 8207150.0,
|
|
"step": 3250
|
|
},
|
|
{
|
|
"entropy": 6.734830856323242,
|
|
"epoch": 0.37564916330063475,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004992314750567864,
|
|
"loss": 6.5991,
|
|
"mean_token_accuracy": 0.1455582395195961,
|
|
"num_tokens": 8221050.0,
|
|
"step": 3255
|
|
},
|
|
{
|
|
"entropy": 6.682382249832154,
|
|
"epoch": 0.3762261973456434,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004992280636232933,
|
|
"loss": 6.5269,
|
|
"mean_token_accuracy": 0.1531355321407318,
|
|
"num_tokens": 8233641.0,
|
|
"step": 3260
|
|
},
|
|
{
|
|
"entropy": 6.685485553741455,
|
|
"epoch": 0.376803231390652,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004992246446480007,
|
|
"loss": 6.5393,
|
|
"mean_token_accuracy": 0.1599086806178093,
|
|
"num_tokens": 8246717.0,
|
|
"step": 3265
|
|
},
|
|
{
|
|
"entropy": 6.670789384841919,
|
|
"epoch": 0.3773802654356607,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004992212181310235,
|
|
"loss": 6.5781,
|
|
"mean_token_accuracy": 0.1480855494737625,
|
|
"num_tokens": 8258549.0,
|
|
"step": 3270
|
|
},
|
|
{
|
|
"entropy": 6.667711162567139,
|
|
"epoch": 0.37795729948066936,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499217784072477,
|
|
"loss": 6.5681,
|
|
"mean_token_accuracy": 0.15179934725165367,
|
|
"num_tokens": 8271580.0,
|
|
"step": 3275
|
|
},
|
|
{
|
|
"entropy": 6.632532358169556,
|
|
"epoch": 0.378534333525678,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004992143424724768,
|
|
"loss": 6.5012,
|
|
"mean_token_accuracy": 0.16231818795204161,
|
|
"num_tokens": 8283866.0,
|
|
"step": 3280
|
|
},
|
|
{
|
|
"entropy": 6.666814136505127,
|
|
"epoch": 0.3791113675706867,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004992108933311385,
|
|
"loss": 6.546,
|
|
"mean_token_accuracy": 0.1500297874212265,
|
|
"num_tokens": 8296141.0,
|
|
"step": 3285
|
|
},
|
|
{
|
|
"entropy": 6.701229381561279,
|
|
"epoch": 0.37968840161569534,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004992074366485782,
|
|
"loss": 6.5113,
|
|
"mean_token_accuracy": 0.15184457004070281,
|
|
"num_tokens": 8309028.0,
|
|
"step": 3290
|
|
},
|
|
{
|
|
"entropy": 6.686760330200196,
|
|
"epoch": 0.380265435660704,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.000499203972424912,
|
|
"loss": 6.498,
|
|
"mean_token_accuracy": 0.15328776091337204,
|
|
"num_tokens": 8321268.0,
|
|
"step": 3295
|
|
},
|
|
{
|
|
"entropy": 6.590341329574585,
|
|
"epoch": 0.3808424697057126,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004992005006602567,
|
|
"loss": 6.507,
|
|
"mean_token_accuracy": 0.16145216226577758,
|
|
"num_tokens": 8333518.0,
|
|
"step": 3300
|
|
},
|
|
{
|
|
"entropy": 6.609353303909302,
|
|
"epoch": 0.3814195037507213,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004991970213547289,
|
|
"loss": 6.5272,
|
|
"mean_token_accuracy": 0.15743554830551149,
|
|
"num_tokens": 8345639.0,
|
|
"step": 3305
|
|
},
|
|
{
|
|
"entropy": 6.561810779571533,
|
|
"epoch": 0.38199653779572995,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004991935345084457,
|
|
"loss": 6.4193,
|
|
"mean_token_accuracy": 0.15771780014038086,
|
|
"num_tokens": 8358136.0,
|
|
"step": 3310
|
|
},
|
|
{
|
|
"entropy": 6.7044079303741455,
|
|
"epoch": 0.3825735718407386,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004991900401215243,
|
|
"loss": 6.5946,
|
|
"mean_token_accuracy": 0.14319533258676528,
|
|
"num_tokens": 8370480.0,
|
|
"step": 3315
|
|
},
|
|
{
|
|
"entropy": 6.665462303161621,
|
|
"epoch": 0.3831506058857473,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004991865381940822,
|
|
"loss": 6.5106,
|
|
"mean_token_accuracy": 0.15779313147068025,
|
|
"num_tokens": 8382894.0,
|
|
"step": 3320
|
|
},
|
|
{
|
|
"entropy": 6.643408632278442,
|
|
"epoch": 0.3837276399307559,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004991830287262374,
|
|
"loss": 6.603,
|
|
"mean_token_accuracy": 0.15157458335161209,
|
|
"num_tokens": 8395864.0,
|
|
"step": 3325
|
|
},
|
|
{
|
|
"entropy": 6.72900710105896,
|
|
"epoch": 0.38430467397576457,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004991795117181077,
|
|
"loss": 6.6255,
|
|
"mean_token_accuracy": 0.14565462321043016,
|
|
"num_tokens": 8408242.0,
|
|
"step": 3330
|
|
},
|
|
{
|
|
"entropy": 6.697143411636352,
|
|
"epoch": 0.3848817080207732,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004991759871698113,
|
|
"loss": 6.5052,
|
|
"mean_token_accuracy": 0.15765076875686646,
|
|
"num_tokens": 8420677.0,
|
|
"step": 3335
|
|
},
|
|
{
|
|
"entropy": 6.566110467910766,
|
|
"epoch": 0.3854587420657819,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004991724550814671,
|
|
"loss": 6.5212,
|
|
"mean_token_accuracy": 0.16033077090978623,
|
|
"num_tokens": 8434505.0,
|
|
"step": 3340
|
|
},
|
|
{
|
|
"entropy": 6.772804021835327,
|
|
"epoch": 0.38603577611079054,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004991689154531937,
|
|
"loss": 6.5408,
|
|
"mean_token_accuracy": 0.1514905296266079,
|
|
"num_tokens": 8447393.0,
|
|
"step": 3345
|
|
},
|
|
{
|
|
"entropy": 6.630925416946411,
|
|
"epoch": 0.3866128101557992,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004991653682851102,
|
|
"loss": 6.4492,
|
|
"mean_token_accuracy": 0.15575905442237853,
|
|
"num_tokens": 8459659.0,
|
|
"step": 3350
|
|
},
|
|
{
|
|
"entropy": 6.618975067138672,
|
|
"epoch": 0.3871898442008078,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.000499161813577336,
|
|
"loss": 6.5953,
|
|
"mean_token_accuracy": 0.1454840660095215,
|
|
"num_tokens": 8473783.0,
|
|
"step": 3355
|
|
},
|
|
{
|
|
"entropy": 6.637290287017822,
|
|
"epoch": 0.3877668782458165,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004991582513299903,
|
|
"loss": 6.38,
|
|
"mean_token_accuracy": 0.15462302714586257,
|
|
"num_tokens": 8486532.0,
|
|
"step": 3360
|
|
},
|
|
{
|
|
"entropy": 6.563358974456787,
|
|
"epoch": 0.38834391229082516,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004991546815431932,
|
|
"loss": 6.5613,
|
|
"mean_token_accuracy": 0.15162240266799926,
|
|
"num_tokens": 8499133.0,
|
|
"step": 3365
|
|
},
|
|
{
|
|
"entropy": 6.700711011886597,
|
|
"epoch": 0.3889209463358338,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.000499151104217065,
|
|
"loss": 6.5991,
|
|
"mean_token_accuracy": 0.1459987446665764,
|
|
"num_tokens": 8513391.0,
|
|
"step": 3370
|
|
},
|
|
{
|
|
"entropy": 6.657787609100342,
|
|
"epoch": 0.3894979803808425,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004991475193517254,
|
|
"loss": 6.5366,
|
|
"mean_token_accuracy": 0.1531873255968094,
|
|
"num_tokens": 8527191.0,
|
|
"step": 3375
|
|
},
|
|
{
|
|
"entropy": 6.656068611145019,
|
|
"epoch": 0.39007501442585113,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.0004991439269472956,
|
|
"loss": 6.5855,
|
|
"mean_token_accuracy": 0.15025382339954377,
|
|
"num_tokens": 8541328.0,
|
|
"step": 3380
|
|
},
|
|
{
|
|
"entropy": 6.641211032867432,
|
|
"epoch": 0.39065204847085977,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004991403270038961,
|
|
"loss": 6.493,
|
|
"mean_token_accuracy": 0.14907428622245789,
|
|
"num_tokens": 8553381.0,
|
|
"step": 3385
|
|
},
|
|
{
|
|
"entropy": 6.629001951217651,
|
|
"epoch": 0.3912290825158684,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000499136719521648,
|
|
"loss": 6.5109,
|
|
"mean_token_accuracy": 0.14996647387742995,
|
|
"num_tokens": 8565149.0,
|
|
"step": 3390
|
|
},
|
|
{
|
|
"entropy": 6.6479668617248535,
|
|
"epoch": 0.3918061165608771,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004991331045006726,
|
|
"loss": 6.5134,
|
|
"mean_token_accuracy": 0.1577385514974594,
|
|
"num_tokens": 8576767.0,
|
|
"step": 3395
|
|
},
|
|
{
|
|
"entropy": 6.707239389419556,
|
|
"epoch": 0.39238315060588574,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004991294819410916,
|
|
"loss": 6.5702,
|
|
"mean_token_accuracy": 0.15049649626016617,
|
|
"num_tokens": 8589948.0,
|
|
"step": 3400
|
|
},
|
|
{
|
|
"entropy": 6.554754066467285,
|
|
"epoch": 0.3929601846508944,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004991258518430268,
|
|
"loss": 6.4066,
|
|
"mean_token_accuracy": 0.1551789790391922,
|
|
"num_tokens": 8602233.0,
|
|
"step": 3405
|
|
},
|
|
{
|
|
"entropy": 6.66826901435852,
|
|
"epoch": 0.3935372186959031,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004991222142066003,
|
|
"loss": 6.4969,
|
|
"mean_token_accuracy": 0.15271663516759873,
|
|
"num_tokens": 8614938.0,
|
|
"step": 3410
|
|
},
|
|
{
|
|
"entropy": 6.688100671768188,
|
|
"epoch": 0.3941142527409117,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004991185690319345,
|
|
"loss": 6.5324,
|
|
"mean_token_accuracy": 0.1585379496216774,
|
|
"num_tokens": 8628203.0,
|
|
"step": 3415
|
|
},
|
|
{
|
|
"entropy": 6.593408536911011,
|
|
"epoch": 0.39469128678592036,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000499114916319152,
|
|
"loss": 6.5038,
|
|
"mean_token_accuracy": 0.1594579190015793,
|
|
"num_tokens": 8640959.0,
|
|
"step": 3420
|
|
},
|
|
{
|
|
"entropy": 6.617645931243897,
|
|
"epoch": 0.395268320830929,
|
|
"grad_norm": 0.7265625,
|
|
"learning_rate": 0.0004991112560683755,
|
|
"loss": 6.5159,
|
|
"mean_token_accuracy": 0.15616845935583115,
|
|
"num_tokens": 8656995.0,
|
|
"step": 3425
|
|
},
|
|
{
|
|
"entropy": 6.678982210159302,
|
|
"epoch": 0.3958453548759377,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.0004991075882797283,
|
|
"loss": 6.5291,
|
|
"mean_token_accuracy": 0.15549861565232276,
|
|
"num_tokens": 8671476.0,
|
|
"step": 3430
|
|
},
|
|
{
|
|
"entropy": 6.627415466308594,
|
|
"epoch": 0.39642238892094633,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004991039129533337,
|
|
"loss": 6.5481,
|
|
"mean_token_accuracy": 0.1529051437973976,
|
|
"num_tokens": 8683667.0,
|
|
"step": 3435
|
|
},
|
|
{
|
|
"entropy": 6.644215297698975,
|
|
"epoch": 0.396999422965955,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004991002300893152,
|
|
"loss": 6.5546,
|
|
"mean_token_accuracy": 0.1545812577009201,
|
|
"num_tokens": 8696564.0,
|
|
"step": 3440
|
|
},
|
|
{
|
|
"entropy": 6.669400453567505,
|
|
"epoch": 0.39757645701096367,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004990965396877969,
|
|
"loss": 6.4865,
|
|
"mean_token_accuracy": 0.15339938551187515,
|
|
"num_tokens": 8708512.0,
|
|
"step": 3445
|
|
},
|
|
{
|
|
"entropy": 6.609234380722046,
|
|
"epoch": 0.3981534910559723,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004990928417489027,
|
|
"loss": 6.3673,
|
|
"mean_token_accuracy": 0.16587528437376023,
|
|
"num_tokens": 8721015.0,
|
|
"step": 3450
|
|
},
|
|
{
|
|
"entropy": 6.567390012741089,
|
|
"epoch": 0.39873052510098095,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004990891362727572,
|
|
"loss": 6.4854,
|
|
"mean_token_accuracy": 0.15047257542610168,
|
|
"num_tokens": 8732538.0,
|
|
"step": 3455
|
|
},
|
|
{
|
|
"entropy": 6.679238510131836,
|
|
"epoch": 0.3993075591459896,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004990854232594848,
|
|
"loss": 6.5582,
|
|
"mean_token_accuracy": 0.15114261358976364,
|
|
"num_tokens": 8745093.0,
|
|
"step": 3460
|
|
},
|
|
{
|
|
"entropy": 6.634946250915528,
|
|
"epoch": 0.3998845931909983,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004990817027092106,
|
|
"loss": 6.4983,
|
|
"mean_token_accuracy": 0.15687089264392853,
|
|
"num_tokens": 8757441.0,
|
|
"step": 3465
|
|
},
|
|
{
|
|
"entropy": 6.660363864898682,
|
|
"epoch": 0.4004616272360069,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004990779746220595,
|
|
"loss": 6.5185,
|
|
"mean_token_accuracy": 0.15596205741167068,
|
|
"num_tokens": 8770307.0,
|
|
"step": 3470
|
|
},
|
|
{
|
|
"entropy": 6.5660014152526855,
|
|
"epoch": 0.40103866128101556,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0004990742389981572,
|
|
"loss": 6.5366,
|
|
"mean_token_accuracy": 0.1550653576850891,
|
|
"num_tokens": 8782575.0,
|
|
"step": 3475
|
|
},
|
|
{
|
|
"entropy": 6.664673566818237,
|
|
"epoch": 0.40161569532602426,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.000499070495837629,
|
|
"loss": 6.5848,
|
|
"mean_token_accuracy": 0.14479815810918809,
|
|
"num_tokens": 8794962.0,
|
|
"step": 3480
|
|
},
|
|
{
|
|
"entropy": 6.661259126663208,
|
|
"epoch": 0.4021927293710329,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004990667451406012,
|
|
"loss": 6.5674,
|
|
"mean_token_accuracy": 0.1521621063351631,
|
|
"num_tokens": 8807434.0,
|
|
"step": 3485
|
|
},
|
|
{
|
|
"entropy": 6.673516368865966,
|
|
"epoch": 0.40276976341604154,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004990629869071995,
|
|
"loss": 6.5391,
|
|
"mean_token_accuracy": 0.14591969475150107,
|
|
"num_tokens": 8820748.0,
|
|
"step": 3490
|
|
},
|
|
{
|
|
"entropy": 6.604957246780396,
|
|
"epoch": 0.4033467974610502,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004990592211375506,
|
|
"loss": 6.465,
|
|
"mean_token_accuracy": 0.15596169531345366,
|
|
"num_tokens": 8833428.0,
|
|
"step": 3495
|
|
},
|
|
{
|
|
"entropy": 6.66051025390625,
|
|
"epoch": 0.4039238315060589,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004990554478317811,
|
|
"loss": 6.5121,
|
|
"mean_token_accuracy": 0.14970427826046945,
|
|
"num_tokens": 8845892.0,
|
|
"step": 3500
|
|
},
|
|
{
|
|
"entropy": 6.575010538101196,
|
|
"epoch": 0.4045008655510675,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004990516669900179,
|
|
"loss": 6.4569,
|
|
"mean_token_accuracy": 0.155875825881958,
|
|
"num_tokens": 8857508.0,
|
|
"step": 3505
|
|
},
|
|
{
|
|
"entropy": 6.607421207427978,
|
|
"epoch": 0.40507789959607615,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004990478786123882,
|
|
"loss": 6.492,
|
|
"mean_token_accuracy": 0.1571622833609581,
|
|
"num_tokens": 8868730.0,
|
|
"step": 3510
|
|
},
|
|
{
|
|
"entropy": 6.664318418502807,
|
|
"epoch": 0.40565493364108485,
|
|
"grad_norm": 0.75390625,
|
|
"learning_rate": 0.0004990440826990193,
|
|
"loss": 6.4882,
|
|
"mean_token_accuracy": 0.14911171048879623,
|
|
"num_tokens": 8882687.0,
|
|
"step": 3515
|
|
},
|
|
{
|
|
"entropy": 6.578036642074585,
|
|
"epoch": 0.4062319676860935,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004990402792500392,
|
|
"loss": 6.5032,
|
|
"mean_token_accuracy": 0.15692729353904725,
|
|
"num_tokens": 8894723.0,
|
|
"step": 3520
|
|
},
|
|
{
|
|
"entropy": 6.5801005363464355,
|
|
"epoch": 0.4068090017311021,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004990364682655754,
|
|
"loss": 6.4722,
|
|
"mean_token_accuracy": 0.15482148230075837,
|
|
"num_tokens": 8906373.0,
|
|
"step": 3525
|
|
},
|
|
{
|
|
"entropy": 6.604721021652222,
|
|
"epoch": 0.40738603577611077,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004990326497457564,
|
|
"loss": 6.4737,
|
|
"mean_token_accuracy": 0.15373015254735947,
|
|
"num_tokens": 8918681.0,
|
|
"step": 3530
|
|
},
|
|
{
|
|
"entropy": 6.652784156799316,
|
|
"epoch": 0.40796306982111946,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004990288236907104,
|
|
"loss": 6.5282,
|
|
"mean_token_accuracy": 0.1494688406586647,
|
|
"num_tokens": 8930232.0,
|
|
"step": 3535
|
|
},
|
|
{
|
|
"entropy": 6.576983118057251,
|
|
"epoch": 0.4085401038661281,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004990249901005661,
|
|
"loss": 6.4193,
|
|
"mean_token_accuracy": 0.15579718947410584,
|
|
"num_tokens": 8942264.0,
|
|
"step": 3540
|
|
},
|
|
{
|
|
"entropy": 6.643110370635986,
|
|
"epoch": 0.40911713791113674,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004990211489754527,
|
|
"loss": 6.5992,
|
|
"mean_token_accuracy": 0.1467343896627426,
|
|
"num_tokens": 8955679.0,
|
|
"step": 3545
|
|
},
|
|
{
|
|
"entropy": 6.642524147033692,
|
|
"epoch": 0.40969417195614544,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004990173003154993,
|
|
"loss": 6.4317,
|
|
"mean_token_accuracy": 0.1543587066233158,
|
|
"num_tokens": 8968421.0,
|
|
"step": 3550
|
|
},
|
|
{
|
|
"entropy": 6.565263557434082,
|
|
"epoch": 0.4102712060011541,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004990134441208351,
|
|
"loss": 6.5003,
|
|
"mean_token_accuracy": 0.15063199996948243,
|
|
"num_tokens": 8981063.0,
|
|
"step": 3555
|
|
},
|
|
{
|
|
"entropy": 6.604219722747803,
|
|
"epoch": 0.4108482400461627,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004990095803915901,
|
|
"loss": 6.4315,
|
|
"mean_token_accuracy": 0.16306943893432618,
|
|
"num_tokens": 8993740.0,
|
|
"step": 3560
|
|
},
|
|
{
|
|
"entropy": 6.59393835067749,
|
|
"epoch": 0.41142527409117136,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004990057091278942,
|
|
"loss": 6.4888,
|
|
"mean_token_accuracy": 0.14942816495895386,
|
|
"num_tokens": 9007135.0,
|
|
"step": 3565
|
|
},
|
|
{
|
|
"entropy": 6.600633573532105,
|
|
"epoch": 0.41200230813618005,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004990018303298773,
|
|
"loss": 6.5045,
|
|
"mean_token_accuracy": 0.15680433362722396,
|
|
"num_tokens": 9021596.0,
|
|
"step": 3570
|
|
},
|
|
{
|
|
"entropy": 6.61022539138794,
|
|
"epoch": 0.4125793421811887,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004989979439976703,
|
|
"loss": 6.44,
|
|
"mean_token_accuracy": 0.16000102311372758,
|
|
"num_tokens": 9033523.0,
|
|
"step": 3575
|
|
},
|
|
{
|
|
"entropy": 6.593396806716919,
|
|
"epoch": 0.41315637622619733,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004989940501314037,
|
|
"loss": 6.4126,
|
|
"mean_token_accuracy": 0.15999998301267623,
|
|
"num_tokens": 9045690.0,
|
|
"step": 3580
|
|
},
|
|
{
|
|
"entropy": 6.580743408203125,
|
|
"epoch": 0.413733410271206,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004989901487312084,
|
|
"loss": 6.4811,
|
|
"mean_token_accuracy": 0.1552786871790886,
|
|
"num_tokens": 9057672.0,
|
|
"step": 3585
|
|
},
|
|
{
|
|
"entropy": 6.589711141586304,
|
|
"epoch": 0.41431044431621467,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004989862397972157,
|
|
"loss": 6.537,
|
|
"mean_token_accuracy": 0.15031036734580994,
|
|
"num_tokens": 9070004.0,
|
|
"step": 3590
|
|
},
|
|
{
|
|
"entropy": 6.658974361419678,
|
|
"epoch": 0.4148874783612233,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004989823233295572,
|
|
"loss": 6.4971,
|
|
"mean_token_accuracy": 0.15876225233078003,
|
|
"num_tokens": 9082453.0,
|
|
"step": 3595
|
|
},
|
|
{
|
|
"entropy": 6.593294286727906,
|
|
"epoch": 0.41546451240623195,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004989783993283644,
|
|
"loss": 6.5122,
|
|
"mean_token_accuracy": 0.1508851870894432,
|
|
"num_tokens": 9095839.0,
|
|
"step": 3600
|
|
},
|
|
{
|
|
"entropy": 6.563176059722901,
|
|
"epoch": 0.41604154645124064,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004989744677937694,
|
|
"loss": 6.4782,
|
|
"mean_token_accuracy": 0.1590025931596756,
|
|
"num_tokens": 9109476.0,
|
|
"step": 3605
|
|
},
|
|
{
|
|
"entropy": 6.619072437286377,
|
|
"epoch": 0.4166185804962493,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004989705287259046,
|
|
"loss": 6.4072,
|
|
"mean_token_accuracy": 0.1609771430492401,
|
|
"num_tokens": 9122354.0,
|
|
"step": 3610
|
|
},
|
|
{
|
|
"entropy": 6.532887077331543,
|
|
"epoch": 0.4171956145412579,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004989665821249021,
|
|
"loss": 6.4261,
|
|
"mean_token_accuracy": 0.16253601163625717,
|
|
"num_tokens": 9135502.0,
|
|
"step": 3615
|
|
},
|
|
{
|
|
"entropy": 6.664855527877807,
|
|
"epoch": 0.4177726485862666,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.000498962627990895,
|
|
"loss": 6.5659,
|
|
"mean_token_accuracy": 0.15357777327299119,
|
|
"num_tokens": 9147654.0,
|
|
"step": 3620
|
|
},
|
|
{
|
|
"entropy": 6.56908655166626,
|
|
"epoch": 0.41834968263127525,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004989586663240161,
|
|
"loss": 6.4847,
|
|
"mean_token_accuracy": 0.1522589549422264,
|
|
"num_tokens": 9161907.0,
|
|
"step": 3625
|
|
},
|
|
{
|
|
"entropy": 6.620093536376953,
|
|
"epoch": 0.4189267166762839,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004989546971243988,
|
|
"loss": 6.513,
|
|
"mean_token_accuracy": 0.14616103172302247,
|
|
"num_tokens": 9175395.0,
|
|
"step": 3630
|
|
},
|
|
{
|
|
"entropy": 6.614277410507202,
|
|
"epoch": 0.41950375072129253,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004989507203921763,
|
|
"loss": 6.4278,
|
|
"mean_token_accuracy": 0.1567081741988659,
|
|
"num_tokens": 9187688.0,
|
|
"step": 3635
|
|
},
|
|
{
|
|
"entropy": 6.550759267807007,
|
|
"epoch": 0.42008078476630123,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004989467361274828,
|
|
"loss": 6.4669,
|
|
"mean_token_accuracy": 0.15715653598308563,
|
|
"num_tokens": 9199773.0,
|
|
"step": 3640
|
|
},
|
|
{
|
|
"entropy": 6.521318578720093,
|
|
"epoch": 0.42065781881130987,
|
|
"grad_norm": 0.6953125,
|
|
"learning_rate": 0.0004989427443304519,
|
|
"loss": 6.4367,
|
|
"mean_token_accuracy": 0.1557897448539734,
|
|
"num_tokens": 9213997.0,
|
|
"step": 3645
|
|
},
|
|
{
|
|
"entropy": 6.621791362762451,
|
|
"epoch": 0.4212348528563185,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000498938745001218,
|
|
"loss": 6.4908,
|
|
"mean_token_accuracy": 0.15198236405849458,
|
|
"num_tokens": 9227187.0,
|
|
"step": 3650
|
|
},
|
|
{
|
|
"entropy": 6.67909688949585,
|
|
"epoch": 0.4218118869013272,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004989347381399158,
|
|
"loss": 6.5423,
|
|
"mean_token_accuracy": 0.1490216538310051,
|
|
"num_tokens": 9240860.0,
|
|
"step": 3655
|
|
},
|
|
{
|
|
"entropy": 6.584900903701782,
|
|
"epoch": 0.42238892094633584,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.0004989307237466799,
|
|
"loss": 6.436,
|
|
"mean_token_accuracy": 0.15650416314601898,
|
|
"num_tokens": 9253771.0,
|
|
"step": 3660
|
|
},
|
|
{
|
|
"entropy": 6.587461662292481,
|
|
"epoch": 0.4229659549913445,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.0004989267018216453,
|
|
"loss": 6.4773,
|
|
"mean_token_accuracy": 0.15263158679008484,
|
|
"num_tokens": 9268380.0,
|
|
"step": 3665
|
|
},
|
|
{
|
|
"entropy": 6.588645076751709,
|
|
"epoch": 0.4235429890363531,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004989226723649473,
|
|
"loss": 6.4562,
|
|
"mean_token_accuracy": 0.1565222844481468,
|
|
"num_tokens": 9279911.0,
|
|
"step": 3670
|
|
},
|
|
{
|
|
"entropy": 6.556595277786255,
|
|
"epoch": 0.4241200230813618,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004989186353767214,
|
|
"loss": 6.446,
|
|
"mean_token_accuracy": 0.16146985441446304,
|
|
"num_tokens": 9292105.0,
|
|
"step": 3675
|
|
},
|
|
{
|
|
"entropy": 6.591396760940552,
|
|
"epoch": 0.42469705712637046,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004989145908571035,
|
|
"loss": 6.5677,
|
|
"mean_token_accuracy": 0.15078672766685486,
|
|
"num_tokens": 9305503.0,
|
|
"step": 3680
|
|
},
|
|
{
|
|
"entropy": 6.630074405670166,
|
|
"epoch": 0.4252740911713791,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004989105388062295,
|
|
"loss": 6.4605,
|
|
"mean_token_accuracy": 0.1556406855583191,
|
|
"num_tokens": 9317978.0,
|
|
"step": 3685
|
|
},
|
|
{
|
|
"entropy": 6.619613599777222,
|
|
"epoch": 0.4258511252163878,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.0004989064792242358,
|
|
"loss": 6.5252,
|
|
"mean_token_accuracy": 0.15357265770435333,
|
|
"num_tokens": 9332676.0,
|
|
"step": 3690
|
|
},
|
|
{
|
|
"entropy": 6.579876184463501,
|
|
"epoch": 0.42642815926139643,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004989024121112589,
|
|
"loss": 6.426,
|
|
"mean_token_accuracy": 0.1560150146484375,
|
|
"num_tokens": 9345594.0,
|
|
"step": 3695
|
|
},
|
|
{
|
|
"entropy": 6.6138917922973635,
|
|
"epoch": 0.4270051933064051,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004988983374674356,
|
|
"loss": 6.5109,
|
|
"mean_token_accuracy": 0.1485238753259182,
|
|
"num_tokens": 9358303.0,
|
|
"step": 3700
|
|
},
|
|
{
|
|
"entropy": 6.520889186859131,
|
|
"epoch": 0.4275822273514137,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004988942552929029,
|
|
"loss": 6.3956,
|
|
"mean_token_accuracy": 0.16093592643737792,
|
|
"num_tokens": 9370953.0,
|
|
"step": 3705
|
|
},
|
|
{
|
|
"entropy": 6.522710132598877,
|
|
"epoch": 0.4281592613964224,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004988901655877981,
|
|
"loss": 6.4721,
|
|
"mean_token_accuracy": 0.15702161937952042,
|
|
"num_tokens": 9384563.0,
|
|
"step": 3710
|
|
},
|
|
{
|
|
"entropy": 6.60606837272644,
|
|
"epoch": 0.42873629544143105,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004988860683522589,
|
|
"loss": 6.4222,
|
|
"mean_token_accuracy": 0.16118086278438568,
|
|
"num_tokens": 9396401.0,
|
|
"step": 3715
|
|
},
|
|
{
|
|
"entropy": 6.555063343048095,
|
|
"epoch": 0.4293133294864397,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000498881963586423,
|
|
"loss": 6.4308,
|
|
"mean_token_accuracy": 0.15848347842693328,
|
|
"num_tokens": 9408520.0,
|
|
"step": 3720
|
|
},
|
|
{
|
|
"entropy": 6.4073954105377195,
|
|
"epoch": 0.4298903635314484,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0004988778512904282,
|
|
"loss": 6.3381,
|
|
"mean_token_accuracy": 0.16240834444761276,
|
|
"num_tokens": 9421431.0,
|
|
"step": 3725
|
|
},
|
|
{
|
|
"entropy": 6.549575996398926,
|
|
"epoch": 0.430467397576457,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004988737314644134,
|
|
"loss": 6.4617,
|
|
"mean_token_accuracy": 0.15462952852249146,
|
|
"num_tokens": 9432566.0,
|
|
"step": 3730
|
|
},
|
|
{
|
|
"entropy": 6.6500896453857425,
|
|
"epoch": 0.43104443162146566,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004988696041085168,
|
|
"loss": 6.5593,
|
|
"mean_token_accuracy": 0.15154415518045425,
|
|
"num_tokens": 9444885.0,
|
|
"step": 3735
|
|
},
|
|
{
|
|
"entropy": 6.667054796218872,
|
|
"epoch": 0.4316214656664743,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004988654692228772,
|
|
"loss": 6.5498,
|
|
"mean_token_accuracy": 0.15102049708366394,
|
|
"num_tokens": 9457823.0,
|
|
"step": 3740
|
|
},
|
|
{
|
|
"entropy": 6.563848447799683,
|
|
"epoch": 0.432198499711483,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004988613268076335,
|
|
"loss": 6.3991,
|
|
"mean_token_accuracy": 0.16212892681360244,
|
|
"num_tokens": 9470799.0,
|
|
"step": 3745
|
|
},
|
|
{
|
|
"entropy": 6.535583543777466,
|
|
"epoch": 0.43277553375649164,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004988571768629257,
|
|
"loss": 6.4583,
|
|
"mean_token_accuracy": 0.16189608722925186,
|
|
"num_tokens": 9484175.0,
|
|
"step": 3750
|
|
},
|
|
{
|
|
"entropy": 6.63653335571289,
|
|
"epoch": 0.4333525678015003,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004988530193888927,
|
|
"loss": 6.5043,
|
|
"mean_token_accuracy": 0.15041833072900773,
|
|
"num_tokens": 9497809.0,
|
|
"step": 3755
|
|
},
|
|
{
|
|
"entropy": 6.56855206489563,
|
|
"epoch": 0.4339296018465089,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004988488543856747,
|
|
"loss": 6.4451,
|
|
"mean_token_accuracy": 0.15440599322319032,
|
|
"num_tokens": 9509755.0,
|
|
"step": 3760
|
|
},
|
|
{
|
|
"entropy": 6.524028348922729,
|
|
"epoch": 0.4345066358915176,
|
|
"grad_norm": 0.75,
|
|
"learning_rate": 0.0004988446818534115,
|
|
"loss": 6.4522,
|
|
"mean_token_accuracy": 0.15307800620794296,
|
|
"num_tokens": 9523801.0,
|
|
"step": 3765
|
|
},
|
|
{
|
|
"entropy": 6.563017177581787,
|
|
"epoch": 0.43508366993652625,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004988405017922438,
|
|
"loss": 6.4373,
|
|
"mean_token_accuracy": 0.16271546185016633,
|
|
"num_tokens": 9535846.0,
|
|
"step": 3770
|
|
},
|
|
{
|
|
"entropy": 6.650265073776245,
|
|
"epoch": 0.4356607039815349,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.000498836314202312,
|
|
"loss": 6.5108,
|
|
"mean_token_accuracy": 0.15331310480833055,
|
|
"num_tokens": 9548194.0,
|
|
"step": 3775
|
|
},
|
|
{
|
|
"entropy": 6.523101472854615,
|
|
"epoch": 0.4362377380265436,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004988321190837568,
|
|
"loss": 6.4047,
|
|
"mean_token_accuracy": 0.15477531999349595,
|
|
"num_tokens": 9561069.0,
|
|
"step": 3780
|
|
},
|
|
{
|
|
"entropy": 6.466052484512329,
|
|
"epoch": 0.4368147720715522,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004988279164367196,
|
|
"loss": 6.3793,
|
|
"mean_token_accuracy": 0.15896909236907958,
|
|
"num_tokens": 9573778.0,
|
|
"step": 3785
|
|
},
|
|
{
|
|
"entropy": 6.535996627807617,
|
|
"epoch": 0.43739180611656087,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004988237062613415,
|
|
"loss": 6.3608,
|
|
"mean_token_accuracy": 0.1710158884525299,
|
|
"num_tokens": 9586616.0,
|
|
"step": 3790
|
|
},
|
|
{
|
|
"entropy": 6.576893711090088,
|
|
"epoch": 0.4379688401615695,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004988194885577644,
|
|
"loss": 6.4697,
|
|
"mean_token_accuracy": 0.1554633378982544,
|
|
"num_tokens": 9597943.0,
|
|
"step": 3795
|
|
},
|
|
{
|
|
"entropy": 6.500680875778198,
|
|
"epoch": 0.4385458742065782,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004988152633261299,
|
|
"loss": 6.4066,
|
|
"mean_token_accuracy": 0.16017991304397583,
|
|
"num_tokens": 9609861.0,
|
|
"step": 3800
|
|
},
|
|
{
|
|
"entropy": 6.532161569595337,
|
|
"epoch": 0.43912290825158684,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.00049881103056658,
|
|
"loss": 6.4607,
|
|
"mean_token_accuracy": 0.16110374480485917,
|
|
"num_tokens": 9623307.0,
|
|
"step": 3805
|
|
},
|
|
{
|
|
"entropy": 6.590618324279785,
|
|
"epoch": 0.4396999422965955,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004988067902792575,
|
|
"loss": 6.4706,
|
|
"mean_token_accuracy": 0.15618328303098677,
|
|
"num_tokens": 9635827.0,
|
|
"step": 3810
|
|
},
|
|
{
|
|
"entropy": 6.584213638305664,
|
|
"epoch": 0.4402769763416042,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004988025424643047,
|
|
"loss": 6.5281,
|
|
"mean_token_accuracy": 0.15362918823957444,
|
|
"num_tokens": 9649422.0,
|
|
"step": 3815
|
|
},
|
|
{
|
|
"entropy": 6.539908409118652,
|
|
"epoch": 0.4408540103866128,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004987982871218645,
|
|
"loss": 6.4985,
|
|
"mean_token_accuracy": 0.16369809061288834,
|
|
"num_tokens": 9661542.0,
|
|
"step": 3820
|
|
},
|
|
{
|
|
"entropy": 6.592797899246216,
|
|
"epoch": 0.44143104443162146,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004987940242520802,
|
|
"loss": 6.4823,
|
|
"mean_token_accuracy": 0.15268328189849853,
|
|
"num_tokens": 9674684.0,
|
|
"step": 3825
|
|
},
|
|
{
|
|
"entropy": 6.680898857116699,
|
|
"epoch": 0.4420080784766301,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.000498789753855095,
|
|
"loss": 6.5,
|
|
"mean_token_accuracy": 0.1492106169462204,
|
|
"num_tokens": 9687522.0,
|
|
"step": 3830
|
|
},
|
|
{
|
|
"entropy": 6.574478960037231,
|
|
"epoch": 0.4425851125216388,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004987854759310526,
|
|
"loss": 6.4528,
|
|
"mean_token_accuracy": 0.15816389620304108,
|
|
"num_tokens": 9699518.0,
|
|
"step": 3835
|
|
},
|
|
{
|
|
"entropy": 6.567315101623535,
|
|
"epoch": 0.44316214656664743,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004987811904800968,
|
|
"loss": 6.5127,
|
|
"mean_token_accuracy": 0.15438069850206376,
|
|
"num_tokens": 9711918.0,
|
|
"step": 3840
|
|
},
|
|
{
|
|
"entropy": 6.596231937408447,
|
|
"epoch": 0.44373918061165607,
|
|
"grad_norm": 0.75390625,
|
|
"learning_rate": 0.0004987768975023719,
|
|
"loss": 6.3862,
|
|
"mean_token_accuracy": 0.15680329352617264,
|
|
"num_tokens": 9725643.0,
|
|
"step": 3845
|
|
},
|
|
{
|
|
"entropy": 6.530617141723633,
|
|
"epoch": 0.44431621465666477,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004987725969980222,
|
|
"loss": 6.403,
|
|
"mean_token_accuracy": 0.1597583845257759,
|
|
"num_tokens": 9738871.0,
|
|
"step": 3850
|
|
},
|
|
{
|
|
"entropy": 6.540352916717529,
|
|
"epoch": 0.4448932487016734,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004987682889671923,
|
|
"loss": 6.3894,
|
|
"mean_token_accuracy": 0.1617853969335556,
|
|
"num_tokens": 9751166.0,
|
|
"step": 3855
|
|
},
|
|
{
|
|
"entropy": 6.512079095840454,
|
|
"epoch": 0.44547028274668204,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004987639734100272,
|
|
"loss": 6.3536,
|
|
"mean_token_accuracy": 0.16155828088521956,
|
|
"num_tokens": 9765165.0,
|
|
"step": 3860
|
|
},
|
|
{
|
|
"entropy": 6.56067123413086,
|
|
"epoch": 0.4460473167916907,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004987596503266721,
|
|
"loss": 6.4014,
|
|
"mean_token_accuracy": 0.1621742233633995,
|
|
"num_tokens": 9776625.0,
|
|
"step": 3865
|
|
},
|
|
{
|
|
"entropy": 6.538637399673462,
|
|
"epoch": 0.4466243508366994,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004987553197172722,
|
|
"loss": 6.4152,
|
|
"mean_token_accuracy": 0.16095769703388213,
|
|
"num_tokens": 9789689.0,
|
|
"step": 3870
|
|
},
|
|
{
|
|
"entropy": 6.617307853698731,
|
|
"epoch": 0.447201384881708,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004987509815819732,
|
|
"loss": 6.5181,
|
|
"mean_token_accuracy": 0.15431652069091797,
|
|
"num_tokens": 9801124.0,
|
|
"step": 3875
|
|
},
|
|
{
|
|
"entropy": 6.545049571990967,
|
|
"epoch": 0.44777841892671666,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004987466359209213,
|
|
"loss": 6.4654,
|
|
"mean_token_accuracy": 0.1531405434012413,
|
|
"num_tokens": 9814264.0,
|
|
"step": 3880
|
|
},
|
|
{
|
|
"entropy": 6.532504224777222,
|
|
"epoch": 0.44835545297172535,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004987422827342622,
|
|
"loss": 6.3939,
|
|
"mean_token_accuracy": 0.16244966238737107,
|
|
"num_tokens": 9826149.0,
|
|
"step": 3885
|
|
},
|
|
{
|
|
"entropy": 6.605834484100342,
|
|
"epoch": 0.448932487016734,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004987379220221426,
|
|
"loss": 6.4765,
|
|
"mean_token_accuracy": 0.15153736919164656,
|
|
"num_tokens": 9838485.0,
|
|
"step": 3890
|
|
},
|
|
{
|
|
"entropy": 6.5250184535980225,
|
|
"epoch": 0.44950952106174263,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004987335537847092,
|
|
"loss": 6.4029,
|
|
"mean_token_accuracy": 0.1562870755791664,
|
|
"num_tokens": 9851371.0,
|
|
"step": 3895
|
|
},
|
|
{
|
|
"entropy": 6.563957357406617,
|
|
"epoch": 0.4500865551067513,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004987291780221088,
|
|
"loss": 6.4599,
|
|
"mean_token_accuracy": 0.15669308006763458,
|
|
"num_tokens": 9864371.0,
|
|
"step": 3900
|
|
},
|
|
{
|
|
"entropy": 6.585865068435669,
|
|
"epoch": 0.45066358915175997,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004987247947344887,
|
|
"loss": 6.4487,
|
|
"mean_token_accuracy": 0.15703559517860413,
|
|
"num_tokens": 9876086.0,
|
|
"step": 3905
|
|
},
|
|
{
|
|
"entropy": 6.544737100601196,
|
|
"epoch": 0.4512406231967686,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004987204039219962,
|
|
"loss": 6.4455,
|
|
"mean_token_accuracy": 0.15367899984121322,
|
|
"num_tokens": 9888850.0,
|
|
"step": 3910
|
|
},
|
|
{
|
|
"entropy": 6.561423492431641,
|
|
"epoch": 0.45181765724177725,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004987160055847791,
|
|
"loss": 6.4777,
|
|
"mean_token_accuracy": 0.15599952191114425,
|
|
"num_tokens": 9901467.0,
|
|
"step": 3915
|
|
},
|
|
{
|
|
"entropy": 6.574502992630005,
|
|
"epoch": 0.45239469128678594,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004987115997229852,
|
|
"loss": 6.4479,
|
|
"mean_token_accuracy": 0.15445881485939025,
|
|
"num_tokens": 9914431.0,
|
|
"step": 3920
|
|
},
|
|
{
|
|
"entropy": 6.613849687576294,
|
|
"epoch": 0.4529717253317946,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004987071863367629,
|
|
"loss": 6.4776,
|
|
"mean_token_accuracy": 0.15640159994363784,
|
|
"num_tokens": 9926863.0,
|
|
"step": 3925
|
|
},
|
|
{
|
|
"entropy": 6.555788230895996,
|
|
"epoch": 0.4535487593768032,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004987027654262604,
|
|
"loss": 6.4231,
|
|
"mean_token_accuracy": 0.1610432580113411,
|
|
"num_tokens": 9939064.0,
|
|
"step": 3930
|
|
},
|
|
{
|
|
"entropy": 6.492784738540649,
|
|
"epoch": 0.45412579342181186,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004986983369916264,
|
|
"loss": 6.4221,
|
|
"mean_token_accuracy": 0.15522423386573792,
|
|
"num_tokens": 9950897.0,
|
|
"step": 3935
|
|
},
|
|
{
|
|
"entropy": 6.640955543518066,
|
|
"epoch": 0.45470282746682056,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004986939010330102,
|
|
"loss": 6.4711,
|
|
"mean_token_accuracy": 0.15500133484601974,
|
|
"num_tokens": 9964388.0,
|
|
"step": 3940
|
|
},
|
|
{
|
|
"entropy": 6.412693643569947,
|
|
"epoch": 0.4552798615118292,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004986894575505606,
|
|
"loss": 6.2872,
|
|
"mean_token_accuracy": 0.1698276601731777,
|
|
"num_tokens": 9977363.0,
|
|
"step": 3945
|
|
},
|
|
{
|
|
"entropy": 6.545732498168945,
|
|
"epoch": 0.45585689555683784,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004986850065444272,
|
|
"loss": 6.3485,
|
|
"mean_token_accuracy": 0.16417437195777893,
|
|
"num_tokens": 9989691.0,
|
|
"step": 3950
|
|
},
|
|
{
|
|
"entropy": 6.592774343490601,
|
|
"epoch": 0.45643392960184653,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004986805480147598,
|
|
"loss": 6.4064,
|
|
"mean_token_accuracy": 0.15252988934516906,
|
|
"num_tokens": 10002177.0,
|
|
"step": 3955
|
|
},
|
|
{
|
|
"entropy": 6.508685827255249,
|
|
"epoch": 0.4570109636468552,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004986760819617082,
|
|
"loss": 6.4662,
|
|
"mean_token_accuracy": 0.15122403651475907,
|
|
"num_tokens": 10014844.0,
|
|
"step": 3960
|
|
},
|
|
{
|
|
"entropy": 6.652512836456299,
|
|
"epoch": 0.4575879976918638,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004986716083854228,
|
|
"loss": 6.4914,
|
|
"mean_token_accuracy": 0.1520856276154518,
|
|
"num_tokens": 10028351.0,
|
|
"step": 3965
|
|
},
|
|
{
|
|
"entropy": 6.521466636657715,
|
|
"epoch": 0.45816503173687245,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004986671272860538,
|
|
"loss": 6.3913,
|
|
"mean_token_accuracy": 0.15310998558998107,
|
|
"num_tokens": 10041318.0,
|
|
"step": 3970
|
|
},
|
|
{
|
|
"entropy": 6.557436227798462,
|
|
"epoch": 0.45874206578188115,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004986626386637521,
|
|
"loss": 6.4107,
|
|
"mean_token_accuracy": 0.1517535850405693,
|
|
"num_tokens": 10054985.0,
|
|
"step": 3975
|
|
},
|
|
{
|
|
"entropy": 6.552952146530151,
|
|
"epoch": 0.4593190998268898,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004986581425186688,
|
|
"loss": 6.4803,
|
|
"mean_token_accuracy": 0.1568808764219284,
|
|
"num_tokens": 10067528.0,
|
|
"step": 3980
|
|
},
|
|
{
|
|
"entropy": 6.526756238937378,
|
|
"epoch": 0.4598961338718984,
|
|
"grad_norm": 0.75390625,
|
|
"learning_rate": 0.0004986536388509548,
|
|
"loss": 6.3925,
|
|
"mean_token_accuracy": 0.15640367493033408,
|
|
"num_tokens": 10080210.0,
|
|
"step": 3985
|
|
},
|
|
{
|
|
"entropy": 6.520599222183227,
|
|
"epoch": 0.4604731679169071,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004986491276607618,
|
|
"loss": 6.4428,
|
|
"mean_token_accuracy": 0.15482764691114426,
|
|
"num_tokens": 10092040.0,
|
|
"step": 3990
|
|
},
|
|
{
|
|
"entropy": 6.584397268295288,
|
|
"epoch": 0.46105020196191576,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004986446089482416,
|
|
"loss": 6.399,
|
|
"mean_token_accuracy": 0.1545254573225975,
|
|
"num_tokens": 10104923.0,
|
|
"step": 3995
|
|
},
|
|
{
|
|
"entropy": 6.528775930404663,
|
|
"epoch": 0.4616272360069244,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004986400827135459,
|
|
"loss": 6.3908,
|
|
"mean_token_accuracy": 0.15947159230709076,
|
|
"num_tokens": 10118963.0,
|
|
"step": 4000
|
|
},
|
|
{
|
|
"entropy": 6.557057237625122,
|
|
"epoch": 0.46220427005193304,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004986355489568272,
|
|
"loss": 6.3496,
|
|
"mean_token_accuracy": 0.16494845151901244,
|
|
"num_tokens": 10131457.0,
|
|
"step": 4005
|
|
},
|
|
{
|
|
"entropy": 6.524343824386596,
|
|
"epoch": 0.46278130409694174,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004986310076782379,
|
|
"loss": 6.4309,
|
|
"mean_token_accuracy": 0.15816483348608018,
|
|
"num_tokens": 10143796.0,
|
|
"step": 4010
|
|
},
|
|
{
|
|
"entropy": 6.474204587936401,
|
|
"epoch": 0.4633583381419504,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004986264588779307,
|
|
"loss": 6.4078,
|
|
"mean_token_accuracy": 0.161160147190094,
|
|
"num_tokens": 10156723.0,
|
|
"step": 4015
|
|
},
|
|
{
|
|
"entropy": 6.524495840072632,
|
|
"epoch": 0.463935372186959,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004986219025560586,
|
|
"loss": 6.4278,
|
|
"mean_token_accuracy": 0.15114813968539237,
|
|
"num_tokens": 10168701.0,
|
|
"step": 4020
|
|
},
|
|
{
|
|
"entropy": 6.57913761138916,
|
|
"epoch": 0.4645124062319677,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.000498617338712775,
|
|
"loss": 6.3816,
|
|
"mean_token_accuracy": 0.16238873600959777,
|
|
"num_tokens": 10182308.0,
|
|
"step": 4025
|
|
},
|
|
{
|
|
"entropy": 6.52322735786438,
|
|
"epoch": 0.46508944027697635,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004986127673482332,
|
|
"loss": 6.371,
|
|
"mean_token_accuracy": 0.16324072778224946,
|
|
"num_tokens": 10194237.0,
|
|
"step": 4030
|
|
},
|
|
{
|
|
"entropy": 6.512039661407471,
|
|
"epoch": 0.465666474321985,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004986081884625871,
|
|
"loss": 6.4611,
|
|
"mean_token_accuracy": 0.15732699781656265,
|
|
"num_tokens": 10208570.0,
|
|
"step": 4035
|
|
},
|
|
{
|
|
"entropy": 6.647953844070434,
|
|
"epoch": 0.46624350836699363,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004986036020559906,
|
|
"loss": 6.4109,
|
|
"mean_token_accuracy": 0.15890434235334397,
|
|
"num_tokens": 10221079.0,
|
|
"step": 4040
|
|
},
|
|
{
|
|
"entropy": 6.42305359840393,
|
|
"epoch": 0.4668205424120023,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000498599008128598,
|
|
"loss": 6.3319,
|
|
"mean_token_accuracy": 0.1590804174542427,
|
|
"num_tokens": 10233473.0,
|
|
"step": 4045
|
|
},
|
|
{
|
|
"entropy": 6.588786363601685,
|
|
"epoch": 0.46739757645701097,
|
|
"grad_norm": 0.75,
|
|
"learning_rate": 0.0004985944066805639,
|
|
"loss": 6.4683,
|
|
"mean_token_accuracy": 0.1552932158112526,
|
|
"num_tokens": 10247840.0,
|
|
"step": 4050
|
|
},
|
|
{
|
|
"entropy": 6.566417503356933,
|
|
"epoch": 0.4679746105020196,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.000498589797712043,
|
|
"loss": 6.3949,
|
|
"mean_token_accuracy": 0.16800516694784165,
|
|
"num_tokens": 10261471.0,
|
|
"step": 4055
|
|
},
|
|
{
|
|
"entropy": 6.484035158157349,
|
|
"epoch": 0.4685516445470283,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004985851812231903,
|
|
"loss": 6.3991,
|
|
"mean_token_accuracy": 0.1583906292915344,
|
|
"num_tokens": 10274386.0,
|
|
"step": 4060
|
|
},
|
|
{
|
|
"entropy": 6.553869724273682,
|
|
"epoch": 0.46912867859203694,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004985805572141611,
|
|
"loss": 6.4131,
|
|
"mean_token_accuracy": 0.15777539014816283,
|
|
"num_tokens": 10286405.0,
|
|
"step": 4065
|
|
},
|
|
{
|
|
"entropy": 6.558121299743652,
|
|
"epoch": 0.4697057126370456,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004985759256851108,
|
|
"loss": 6.4603,
|
|
"mean_token_accuracy": 0.15484957844018937,
|
|
"num_tokens": 10300084.0,
|
|
"step": 4070
|
|
},
|
|
{
|
|
"entropy": 6.565396356582641,
|
|
"epoch": 0.4702827466820542,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004985712866361954,
|
|
"loss": 6.4674,
|
|
"mean_token_accuracy": 0.16278457939624785,
|
|
"num_tokens": 10312558.0,
|
|
"step": 4075
|
|
},
|
|
{
|
|
"entropy": 6.541759634017945,
|
|
"epoch": 0.4708597807270629,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004985666400675709,
|
|
"loss": 6.3687,
|
|
"mean_token_accuracy": 0.16311410516500474,
|
|
"num_tokens": 10324185.0,
|
|
"step": 4080
|
|
},
|
|
{
|
|
"entropy": 6.4401655197143555,
|
|
"epoch": 0.47143681477207156,
|
|
"grad_norm": 0.75,
|
|
"learning_rate": 0.0004985619859793934,
|
|
"loss": 6.4018,
|
|
"mean_token_accuracy": 0.15202204287052154,
|
|
"num_tokens": 10338634.0,
|
|
"step": 4085
|
|
},
|
|
{
|
|
"entropy": 6.673071384429932,
|
|
"epoch": 0.4720138488170802,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004985573243718195,
|
|
"loss": 6.4702,
|
|
"mean_token_accuracy": 0.1487300381064415,
|
|
"num_tokens": 10351272.0,
|
|
"step": 4090
|
|
},
|
|
{
|
|
"entropy": 6.562505865097046,
|
|
"epoch": 0.4725908828620889,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004985526552450061,
|
|
"loss": 6.4052,
|
|
"mean_token_accuracy": 0.15442484468221665,
|
|
"num_tokens": 10362894.0,
|
|
"step": 4095
|
|
},
|
|
{
|
|
"entropy": 6.557220220565796,
|
|
"epoch": 0.47316791690709753,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004985479785991103,
|
|
"loss": 6.5136,
|
|
"mean_token_accuracy": 0.15173576027154922,
|
|
"num_tokens": 10376120.0,
|
|
"step": 4100
|
|
},
|
|
{
|
|
"entropy": 6.551002073287964,
|
|
"epoch": 0.47374495095210617,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004985432944342892,
|
|
"loss": 6.4281,
|
|
"mean_token_accuracy": 0.15780509859323502,
|
|
"num_tokens": 10387986.0,
|
|
"step": 4105
|
|
},
|
|
{
|
|
"entropy": 6.5132355213165285,
|
|
"epoch": 0.4743219849971148,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004985386027507003,
|
|
"loss": 6.4441,
|
|
"mean_token_accuracy": 0.1574099436402321,
|
|
"num_tokens": 10400920.0,
|
|
"step": 4110
|
|
},
|
|
{
|
|
"entropy": 6.636253833770752,
|
|
"epoch": 0.4748990190421235,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004985339035485018,
|
|
"loss": 6.4511,
|
|
"mean_token_accuracy": 0.1540090411901474,
|
|
"num_tokens": 10413835.0,
|
|
"step": 4115
|
|
},
|
|
{
|
|
"entropy": 6.511466121673584,
|
|
"epoch": 0.47547605308713214,
|
|
"grad_norm": 0.7109375,
|
|
"learning_rate": 0.0004985291968278513,
|
|
"loss": 6.4537,
|
|
"mean_token_accuracy": 0.15455947071313858,
|
|
"num_tokens": 10426959.0,
|
|
"step": 4120
|
|
},
|
|
{
|
|
"entropy": 6.5830864906311035,
|
|
"epoch": 0.4760530871321408,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004985244825889074,
|
|
"loss": 6.4912,
|
|
"mean_token_accuracy": 0.15826078802347182,
|
|
"num_tokens": 10440319.0,
|
|
"step": 4125
|
|
},
|
|
{
|
|
"entropy": 6.533916664123535,
|
|
"epoch": 0.4766301211771495,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004985197608318284,
|
|
"loss": 6.4479,
|
|
"mean_token_accuracy": 0.15521639585494995,
|
|
"num_tokens": 10453715.0,
|
|
"step": 4130
|
|
},
|
|
{
|
|
"entropy": 6.575965356826782,
|
|
"epoch": 0.4772071552221581,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004985150315567735,
|
|
"loss": 6.4414,
|
|
"mean_token_accuracy": 0.15350656658411027,
|
|
"num_tokens": 10465574.0,
|
|
"step": 4135
|
|
},
|
|
{
|
|
"entropy": 6.519655561447143,
|
|
"epoch": 0.47778418926716676,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004985102947639013,
|
|
"loss": 6.4083,
|
|
"mean_token_accuracy": 0.15839099436998366,
|
|
"num_tokens": 10478105.0,
|
|
"step": 4140
|
|
},
|
|
{
|
|
"entropy": 6.4816258430480955,
|
|
"epoch": 0.4783612233121754,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004985055504533715,
|
|
"loss": 6.4284,
|
|
"mean_token_accuracy": 0.15900716781616211,
|
|
"num_tokens": 10490723.0,
|
|
"step": 4145
|
|
},
|
|
{
|
|
"entropy": 6.624292707443237,
|
|
"epoch": 0.4789382573571841,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004985007986253435,
|
|
"loss": 6.452,
|
|
"mean_token_accuracy": 0.15452224612236024,
|
|
"num_tokens": 10503155.0,
|
|
"step": 4150
|
|
},
|
|
{
|
|
"entropy": 6.526167535781861,
|
|
"epoch": 0.47951529140219273,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004984960392799772,
|
|
"loss": 6.4215,
|
|
"mean_token_accuracy": 0.14876818060874938,
|
|
"num_tokens": 10515077.0,
|
|
"step": 4155
|
|
},
|
|
{
|
|
"entropy": 6.6001299858093265,
|
|
"epoch": 0.4800923254472014,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004984912724174326,
|
|
"loss": 6.3883,
|
|
"mean_token_accuracy": 0.15346773862838745,
|
|
"num_tokens": 10528445.0,
|
|
"step": 4160
|
|
},
|
|
{
|
|
"entropy": 6.559596395492553,
|
|
"epoch": 0.48066935949221,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004984864980378701,
|
|
"loss": 6.4379,
|
|
"mean_token_accuracy": 0.15837605893611909,
|
|
"num_tokens": 10541877.0,
|
|
"step": 4165
|
|
},
|
|
{
|
|
"entropy": 6.54767746925354,
|
|
"epoch": 0.4812463935372187,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004984817161414502,
|
|
"loss": 6.4044,
|
|
"mean_token_accuracy": 0.15747998505830765,
|
|
"num_tokens": 10553527.0,
|
|
"step": 4170
|
|
},
|
|
{
|
|
"entropy": 6.479561614990234,
|
|
"epoch": 0.48182342758222735,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004984769267283338,
|
|
"loss": 6.4136,
|
|
"mean_token_accuracy": 0.15314011722803117,
|
|
"num_tokens": 10566492.0,
|
|
"step": 4175
|
|
},
|
|
{
|
|
"entropy": 6.467929792404175,
|
|
"epoch": 0.482400461627236,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004984721297986819,
|
|
"loss": 6.3739,
|
|
"mean_token_accuracy": 0.15953933745622634,
|
|
"num_tokens": 10578962.0,
|
|
"step": 4180
|
|
},
|
|
{
|
|
"entropy": 6.5416004180908205,
|
|
"epoch": 0.4829774956722447,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004984673253526561,
|
|
"loss": 6.3665,
|
|
"mean_token_accuracy": 0.15812182426452637,
|
|
"num_tokens": 10591254.0,
|
|
"step": 4185
|
|
},
|
|
{
|
|
"entropy": 6.557770919799805,
|
|
"epoch": 0.4835545297172533,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004984625133904176,
|
|
"loss": 6.4061,
|
|
"mean_token_accuracy": 0.1579806312918663,
|
|
"num_tokens": 10604961.0,
|
|
"step": 4190
|
|
},
|
|
{
|
|
"entropy": 6.499729299545288,
|
|
"epoch": 0.48413156376226196,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004984576939121286,
|
|
"loss": 6.3885,
|
|
"mean_token_accuracy": 0.16066249012947081,
|
|
"num_tokens": 10617419.0,
|
|
"step": 4195
|
|
},
|
|
{
|
|
"entropy": 6.50909194946289,
|
|
"epoch": 0.4847085978072706,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004984528669179511,
|
|
"loss": 6.4186,
|
|
"mean_token_accuracy": 0.15439673513174057,
|
|
"num_tokens": 10629721.0,
|
|
"step": 4200
|
|
},
|
|
{
|
|
"entropy": 6.625107002258301,
|
|
"epoch": 0.4852856318522793,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004984480324080472,
|
|
"loss": 6.4535,
|
|
"mean_token_accuracy": 0.15551864504814147,
|
|
"num_tokens": 10643869.0,
|
|
"step": 4205
|
|
},
|
|
{
|
|
"entropy": 6.590443325042725,
|
|
"epoch": 0.48586266589728794,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.00049844319038258,
|
|
"loss": 6.5082,
|
|
"mean_token_accuracy": 0.14841593205928802,
|
|
"num_tokens": 10658418.0,
|
|
"step": 4210
|
|
},
|
|
{
|
|
"entropy": 6.542080116271973,
|
|
"epoch": 0.4864396999422966,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004984383408417119,
|
|
"loss": 6.3939,
|
|
"mean_token_accuracy": 0.16221137195825577,
|
|
"num_tokens": 10671105.0,
|
|
"step": 4215
|
|
},
|
|
{
|
|
"entropy": 6.542936706542969,
|
|
"epoch": 0.4870167339873053,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004984334837856064,
|
|
"loss": 6.4929,
|
|
"mean_token_accuracy": 0.15168781727552413,
|
|
"num_tokens": 10683862.0,
|
|
"step": 4220
|
|
},
|
|
{
|
|
"entropy": 6.539501905441284,
|
|
"epoch": 0.4875937680323139,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004984286192144263,
|
|
"loss": 6.3919,
|
|
"mean_token_accuracy": 0.1602101057767868,
|
|
"num_tokens": 10696559.0,
|
|
"step": 4225
|
|
},
|
|
{
|
|
"entropy": 6.5565080642700195,
|
|
"epoch": 0.48817080207732255,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004984237471283359,
|
|
"loss": 6.4623,
|
|
"mean_token_accuracy": 0.157669498026371,
|
|
"num_tokens": 10710227.0,
|
|
"step": 4230
|
|
},
|
|
{
|
|
"entropy": 6.489563083648681,
|
|
"epoch": 0.4887478361223312,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004984188675274986,
|
|
"loss": 6.4311,
|
|
"mean_token_accuracy": 0.15578922182321547,
|
|
"num_tokens": 10722761.0,
|
|
"step": 4235
|
|
},
|
|
{
|
|
"entropy": 6.552829694747925,
|
|
"epoch": 0.4893248701673399,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004984139804120787,
|
|
"loss": 6.3864,
|
|
"mean_token_accuracy": 0.15277379006147385,
|
|
"num_tokens": 10734126.0,
|
|
"step": 4240
|
|
},
|
|
{
|
|
"entropy": 6.524606513977051,
|
|
"epoch": 0.4899019042123485,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004984090857822406,
|
|
"loss": 6.4398,
|
|
"mean_token_accuracy": 0.15711746215820313,
|
|
"num_tokens": 10747570.0,
|
|
"step": 4245
|
|
},
|
|
{
|
|
"entropy": 6.61868577003479,
|
|
"epoch": 0.49047893825735717,
|
|
"grad_norm": 0.6875,
|
|
"learning_rate": 0.0004984041836381488,
|
|
"loss": 6.5498,
|
|
"mean_token_accuracy": 0.14832186549901963,
|
|
"num_tokens": 10762975.0,
|
|
"step": 4250
|
|
},
|
|
{
|
|
"entropy": 6.625642156600952,
|
|
"epoch": 0.49105597230236586,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004983992739799682,
|
|
"loss": 6.3846,
|
|
"mean_token_accuracy": 0.1586022138595581,
|
|
"num_tokens": 10774520.0,
|
|
"step": 4255
|
|
},
|
|
{
|
|
"entropy": 6.455063724517823,
|
|
"epoch": 0.4916330063473745,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004983943568078642,
|
|
"loss": 6.3108,
|
|
"mean_token_accuracy": 0.16183219701051713,
|
|
"num_tokens": 10786250.0,
|
|
"step": 4260
|
|
},
|
|
{
|
|
"entropy": 6.565676832199097,
|
|
"epoch": 0.49221004039238314,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.0004983894321220017,
|
|
"loss": 6.4387,
|
|
"mean_token_accuracy": 0.15883514136075974,
|
|
"num_tokens": 10799831.0,
|
|
"step": 4265
|
|
},
|
|
{
|
|
"entropy": 6.5317785263061525,
|
|
"epoch": 0.4927870744373918,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004983844999225468,
|
|
"loss": 6.3715,
|
|
"mean_token_accuracy": 0.16067612767219544,
|
|
"num_tokens": 10812803.0,
|
|
"step": 4270
|
|
},
|
|
{
|
|
"entropy": 6.497241115570068,
|
|
"epoch": 0.4933641084824005,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004983795602096651,
|
|
"loss": 6.3904,
|
|
"mean_token_accuracy": 0.1601540118455887,
|
|
"num_tokens": 10825150.0,
|
|
"step": 4275
|
|
},
|
|
{
|
|
"entropy": 6.598751640319824,
|
|
"epoch": 0.4939411425274091,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.000498374612983523,
|
|
"loss": 6.506,
|
|
"mean_token_accuracy": 0.15289822071790696,
|
|
"num_tokens": 10838337.0,
|
|
"step": 4280
|
|
},
|
|
{
|
|
"entropy": 6.5518717765808105,
|
|
"epoch": 0.49451817657241776,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004983696582442866,
|
|
"loss": 6.334,
|
|
"mean_token_accuracy": 0.17550577819347382,
|
|
"num_tokens": 10852288.0,
|
|
"step": 4285
|
|
},
|
|
{
|
|
"entropy": 6.514918279647827,
|
|
"epoch": 0.49509521061742645,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004983646959921227,
|
|
"loss": 6.439,
|
|
"mean_token_accuracy": 0.15471772402524947,
|
|
"num_tokens": 10864189.0,
|
|
"step": 4290
|
|
},
|
|
{
|
|
"entropy": 6.618105697631836,
|
|
"epoch": 0.4956722446624351,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.0004983597262271984,
|
|
"loss": 6.4346,
|
|
"mean_token_accuracy": 0.1550702318549156,
|
|
"num_tokens": 10877410.0,
|
|
"step": 4295
|
|
},
|
|
{
|
|
"entropy": 6.503079223632812,
|
|
"epoch": 0.49624927870744373,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004983547489496804,
|
|
"loss": 6.4053,
|
|
"mean_token_accuracy": 0.15499556958675384,
|
|
"num_tokens": 10889757.0,
|
|
"step": 4300
|
|
},
|
|
{
|
|
"entropy": 6.490525484085083,
|
|
"epoch": 0.49682631275245237,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004983497641597365,
|
|
"loss": 6.3195,
|
|
"mean_token_accuracy": 0.16428075432777406,
|
|
"num_tokens": 10901636.0,
|
|
"step": 4305
|
|
},
|
|
{
|
|
"entropy": 6.480206155776978,
|
|
"epoch": 0.49740334679746107,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.0004983447718575342,
|
|
"loss": 6.3544,
|
|
"mean_token_accuracy": 0.1630442336201668,
|
|
"num_tokens": 10914063.0,
|
|
"step": 4310
|
|
},
|
|
{
|
|
"entropy": 6.595718622207642,
|
|
"epoch": 0.4979803808424697,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004983397720432414,
|
|
"loss": 6.3886,
|
|
"mean_token_accuracy": 0.16058591455221177,
|
|
"num_tokens": 10927730.0,
|
|
"step": 4315
|
|
},
|
|
{
|
|
"entropy": 6.534880208969116,
|
|
"epoch": 0.49855741488747835,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004983347647170264,
|
|
"loss": 6.4898,
|
|
"mean_token_accuracy": 0.15413855165243148,
|
|
"num_tokens": 10942440.0,
|
|
"step": 4320
|
|
},
|
|
{
|
|
"entropy": 6.512958288192749,
|
|
"epoch": 0.49913444893248704,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004983297498790574,
|
|
"loss": 6.3992,
|
|
"mean_token_accuracy": 0.156264328956604,
|
|
"num_tokens": 10955801.0,
|
|
"step": 4325
|
|
},
|
|
{
|
|
"entropy": 6.5469934940338135,
|
|
"epoch": 0.4997114829774957,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004983247275295034,
|
|
"loss": 6.3887,
|
|
"mean_token_accuracy": 0.1580841600894928,
|
|
"num_tokens": 10967918.0,
|
|
"step": 4330
|
|
},
|
|
{
|
|
"entropy": 6.508872032165527,
|
|
"epoch": 0.5002885170225043,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004983196976685329,
|
|
"loss": 6.3267,
|
|
"mean_token_accuracy": 0.16289351582527162,
|
|
"num_tokens": 10979652.0,
|
|
"step": 4335
|
|
},
|
|
{
|
|
"entropy": 6.387019300460816,
|
|
"epoch": 0.500865551067513,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004983146602963155,
|
|
"loss": 6.2607,
|
|
"mean_token_accuracy": 0.17579997777938844,
|
|
"num_tokens": 10991433.0,
|
|
"step": 4340
|
|
},
|
|
{
|
|
"entropy": 6.460304498672485,
|
|
"epoch": 0.5014425851125216,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004983096154130203,
|
|
"loss": 6.4603,
|
|
"mean_token_accuracy": 0.15860795527696608,
|
|
"num_tokens": 11003976.0,
|
|
"step": 4345
|
|
},
|
|
{
|
|
"entropy": 6.599706220626831,
|
|
"epoch": 0.5020196191575302,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004983045630188171,
|
|
"loss": 6.4366,
|
|
"mean_token_accuracy": 0.15410916805267333,
|
|
"num_tokens": 11018848.0,
|
|
"step": 4350
|
|
},
|
|
{
|
|
"entropy": 6.57402777671814,
|
|
"epoch": 0.502596653202539,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004982995031138759,
|
|
"loss": 6.4038,
|
|
"mean_token_accuracy": 0.15641804337501525,
|
|
"num_tokens": 11030803.0,
|
|
"step": 4355
|
|
},
|
|
{
|
|
"entropy": 6.586047887802124,
|
|
"epoch": 0.5031736872475476,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004982944356983666,
|
|
"loss": 6.4921,
|
|
"mean_token_accuracy": 0.15291229784488677,
|
|
"num_tokens": 11044688.0,
|
|
"step": 4360
|
|
},
|
|
{
|
|
"entropy": 6.524409008026123,
|
|
"epoch": 0.5037507212925563,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004982893607724602,
|
|
"loss": 6.4306,
|
|
"mean_token_accuracy": 0.15263819694519043,
|
|
"num_tokens": 11057026.0,
|
|
"step": 4365
|
|
},
|
|
{
|
|
"entropy": 6.639001178741455,
|
|
"epoch": 0.5043277553375649,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.000498284278336327,
|
|
"loss": 6.4538,
|
|
"mean_token_accuracy": 0.15304491817951202,
|
|
"num_tokens": 11070407.0,
|
|
"step": 4370
|
|
},
|
|
{
|
|
"entropy": 6.5000138759613035,
|
|
"epoch": 0.5049047893825735,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004982791883901379,
|
|
"loss": 6.3616,
|
|
"mean_token_accuracy": 0.16394442021846772,
|
|
"num_tokens": 11082655.0,
|
|
"step": 4375
|
|
},
|
|
{
|
|
"entropy": 6.462573575973511,
|
|
"epoch": 0.5054818234275822,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.0004982740909340643,
|
|
"loss": 6.3301,
|
|
"mean_token_accuracy": 0.16755695044994354,
|
|
"num_tokens": 11095948.0,
|
|
"step": 4380
|
|
},
|
|
{
|
|
"entropy": 6.589680433273315,
|
|
"epoch": 0.5060588574725908,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004982689859682775,
|
|
"loss": 6.382,
|
|
"mean_token_accuracy": 0.15594714432954787,
|
|
"num_tokens": 11108105.0,
|
|
"step": 4385
|
|
},
|
|
{
|
|
"entropy": 6.5538736343383786,
|
|
"epoch": 0.5066358915175996,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004982638734929492,
|
|
"loss": 6.4291,
|
|
"mean_token_accuracy": 0.15332048535346984,
|
|
"num_tokens": 11120322.0,
|
|
"step": 4390
|
|
},
|
|
{
|
|
"entropy": 6.386771297454834,
|
|
"epoch": 0.5072129255626082,
|
|
"grad_norm": 0.75390625,
|
|
"learning_rate": 0.0004982587535082515,
|
|
"loss": 6.2161,
|
|
"mean_token_accuracy": 0.16631432473659516,
|
|
"num_tokens": 11133903.0,
|
|
"step": 4395
|
|
},
|
|
{
|
|
"entropy": 6.46461238861084,
|
|
"epoch": 0.5077899596076169,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004982536260143565,
|
|
"loss": 6.2861,
|
|
"mean_token_accuracy": 0.16543451994657515,
|
|
"num_tokens": 11145607.0,
|
|
"step": 4400
|
|
},
|
|
{
|
|
"entropy": 6.536594581604004,
|
|
"epoch": 0.5083669936526255,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004982484910114367,
|
|
"loss": 6.391,
|
|
"mean_token_accuracy": 0.15751007944345474,
|
|
"num_tokens": 11157332.0,
|
|
"step": 4405
|
|
},
|
|
{
|
|
"entropy": 6.527062559127808,
|
|
"epoch": 0.5089440276976341,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004982433484996648,
|
|
"loss": 6.4747,
|
|
"mean_token_accuracy": 0.1585505411028862,
|
|
"num_tokens": 11169404.0,
|
|
"step": 4410
|
|
},
|
|
{
|
|
"entropy": 6.553807020187378,
|
|
"epoch": 0.5095210617426428,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004982381984792138,
|
|
"loss": 6.3707,
|
|
"mean_token_accuracy": 0.15870761573314668,
|
|
"num_tokens": 11182506.0,
|
|
"step": 4415
|
|
},
|
|
{
|
|
"entropy": 6.516544485092163,
|
|
"epoch": 0.5100980957876514,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004982330409502568,
|
|
"loss": 6.3395,
|
|
"mean_token_accuracy": 0.1521760679781437,
|
|
"num_tokens": 11195507.0,
|
|
"step": 4420
|
|
},
|
|
{
|
|
"entropy": 6.505952548980713,
|
|
"epoch": 0.5106751298326602,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004982278759129674,
|
|
"loss": 6.3472,
|
|
"mean_token_accuracy": 0.16159432679414748,
|
|
"num_tokens": 11207219.0,
|
|
"step": 4425
|
|
},
|
|
{
|
|
"entropy": 6.456001710891724,
|
|
"epoch": 0.5112521638776688,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004982227033675194,
|
|
"loss": 6.3242,
|
|
"mean_token_accuracy": 0.16376312375068663,
|
|
"num_tokens": 11219301.0,
|
|
"step": 4430
|
|
},
|
|
{
|
|
"entropy": 6.460791826248169,
|
|
"epoch": 0.5118291979226774,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004982175233140865,
|
|
"loss": 6.3282,
|
|
"mean_token_accuracy": 0.16003126353025438,
|
|
"num_tokens": 11230957.0,
|
|
"step": 4435
|
|
},
|
|
{
|
|
"entropy": 6.537653398513794,
|
|
"epoch": 0.5124062319676861,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004982123357528431,
|
|
"loss": 6.3529,
|
|
"mean_token_accuracy": 0.15861166417598724,
|
|
"num_tokens": 11242813.0,
|
|
"step": 4440
|
|
},
|
|
{
|
|
"entropy": 6.4945403099060055,
|
|
"epoch": 0.5129832660126947,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004982071406839636,
|
|
"loss": 6.3613,
|
|
"mean_token_accuracy": 0.1551041141152382,
|
|
"num_tokens": 11255193.0,
|
|
"step": 4445
|
|
},
|
|
{
|
|
"entropy": 6.403803586959839,
|
|
"epoch": 0.5135603000577034,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004982019381076229,
|
|
"loss": 6.336,
|
|
"mean_token_accuracy": 0.16265275329351425,
|
|
"num_tokens": 11267988.0,
|
|
"step": 4450
|
|
},
|
|
{
|
|
"entropy": 6.558556795120239,
|
|
"epoch": 0.514137334102712,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004981967280239958,
|
|
"loss": 6.4116,
|
|
"mean_token_accuracy": 0.15306541174650193,
|
|
"num_tokens": 11280456.0,
|
|
"step": 4455
|
|
},
|
|
{
|
|
"entropy": 6.527243995666504,
|
|
"epoch": 0.5147143681477208,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004981915104332578,
|
|
"loss": 6.4394,
|
|
"mean_token_accuracy": 0.15262870788574218,
|
|
"num_tokens": 11293304.0,
|
|
"step": 4460
|
|
},
|
|
{
|
|
"entropy": 6.479492855072022,
|
|
"epoch": 0.5152914021927294,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.000498186285335584,
|
|
"loss": 6.3962,
|
|
"mean_token_accuracy": 0.15405147820711135,
|
|
"num_tokens": 11305936.0,
|
|
"step": 4465
|
|
},
|
|
{
|
|
"entropy": 6.617494297027588,
|
|
"epoch": 0.515868436237738,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004981810527311505,
|
|
"loss": 6.4403,
|
|
"mean_token_accuracy": 0.1522215947508812,
|
|
"num_tokens": 11319991.0,
|
|
"step": 4470
|
|
},
|
|
{
|
|
"entropy": 6.508704996109008,
|
|
"epoch": 0.5164454702827467,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.000498175812620133,
|
|
"loss": 6.3465,
|
|
"mean_token_accuracy": 0.16412411332130433,
|
|
"num_tokens": 11332572.0,
|
|
"step": 4475
|
|
},
|
|
{
|
|
"entropy": 6.460049343109131,
|
|
"epoch": 0.5170225043277553,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004981705650027081,
|
|
"loss": 6.3431,
|
|
"mean_token_accuracy": 0.16454764157533647,
|
|
"num_tokens": 11344435.0,
|
|
"step": 4480
|
|
},
|
|
{
|
|
"entropy": 6.47212586402893,
|
|
"epoch": 0.517599538372764,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000498165309879052,
|
|
"loss": 6.273,
|
|
"mean_token_accuracy": 0.16744499206542968,
|
|
"num_tokens": 11356078.0,
|
|
"step": 4485
|
|
},
|
|
{
|
|
"entropy": 6.43641505241394,
|
|
"epoch": 0.5181765724177726,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004981600472493415,
|
|
"loss": 6.3231,
|
|
"mean_token_accuracy": 0.16197210550308228,
|
|
"num_tokens": 11368933.0,
|
|
"step": 4490
|
|
},
|
|
{
|
|
"entropy": 6.587095832824707,
|
|
"epoch": 0.5187536064627813,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004981547771137537,
|
|
"loss": 6.4412,
|
|
"mean_token_accuracy": 0.15295076966285706,
|
|
"num_tokens": 11380810.0,
|
|
"step": 4495
|
|
},
|
|
{
|
|
"entropy": 6.448738145828247,
|
|
"epoch": 0.51933064050779,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004981494994724658,
|
|
"loss": 6.3362,
|
|
"mean_token_accuracy": 0.16053746342658998,
|
|
"num_tokens": 11392447.0,
|
|
"step": 4500
|
|
},
|
|
{
|
|
"entropy": 6.471343231201172,
|
|
"epoch": 0.5199076745527986,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004981442143256554,
|
|
"loss": 6.3946,
|
|
"mean_token_accuracy": 0.1577278733253479,
|
|
"num_tokens": 11405237.0,
|
|
"step": 4505
|
|
},
|
|
{
|
|
"entropy": 6.582560443878174,
|
|
"epoch": 0.5204847085978073,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0004981389216735001,
|
|
"loss": 6.5039,
|
|
"mean_token_accuracy": 0.14747137874364852,
|
|
"num_tokens": 11418951.0,
|
|
"step": 4510
|
|
},
|
|
{
|
|
"entropy": 6.54022970199585,
|
|
"epoch": 0.5210617426428159,
|
|
"grad_norm": 0.75,
|
|
"learning_rate": 0.000498133621516178,
|
|
"loss": 6.4038,
|
|
"mean_token_accuracy": 0.15998345464468003,
|
|
"num_tokens": 11432587.0,
|
|
"step": 4515
|
|
},
|
|
{
|
|
"entropy": 6.507716655731201,
|
|
"epoch": 0.5216387766878245,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004981283138538675,
|
|
"loss": 6.4289,
|
|
"mean_token_accuracy": 0.15074404031038285,
|
|
"num_tokens": 11445572.0,
|
|
"step": 4520
|
|
},
|
|
{
|
|
"entropy": 6.524649286270142,
|
|
"epoch": 0.5222158107328332,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.000498122998686747,
|
|
"loss": 6.3821,
|
|
"mean_token_accuracy": 0.16107590049505233,
|
|
"num_tokens": 11457469.0,
|
|
"step": 4525
|
|
},
|
|
{
|
|
"entropy": 6.531647729873657,
|
|
"epoch": 0.5227928447778419,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004981176760149951,
|
|
"loss": 6.4269,
|
|
"mean_token_accuracy": 0.1588137172162533,
|
|
"num_tokens": 11470306.0,
|
|
"step": 4530
|
|
},
|
|
{
|
|
"entropy": 6.553733444213867,
|
|
"epoch": 0.5233698788228506,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004981123458387911,
|
|
"loss": 6.4024,
|
|
"mean_token_accuracy": 0.16188153773546218,
|
|
"num_tokens": 11483839.0,
|
|
"step": 4535
|
|
},
|
|
{
|
|
"entropy": 6.549627828598022,
|
|
"epoch": 0.5239469128678592,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004981070081583142,
|
|
"loss": 6.3946,
|
|
"mean_token_accuracy": 0.15353466868400573,
|
|
"num_tokens": 11495703.0,
|
|
"step": 4540
|
|
},
|
|
{
|
|
"entropy": 6.5704262256622314,
|
|
"epoch": 0.5245239469128679,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.000498101662973744,
|
|
"loss": 6.4888,
|
|
"mean_token_accuracy": 0.15426429733633995,
|
|
"num_tokens": 11508061.0,
|
|
"step": 4545
|
|
},
|
|
{
|
|
"entropy": 6.487470436096191,
|
|
"epoch": 0.5251009809578765,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.00049809631028526,
|
|
"loss": 6.3195,
|
|
"mean_token_accuracy": 0.16369524449110032,
|
|
"num_tokens": 11520135.0,
|
|
"step": 4550
|
|
},
|
|
{
|
|
"entropy": 6.492602396011352,
|
|
"epoch": 0.5256780150028851,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004980909500930424,
|
|
"loss": 6.3946,
|
|
"mean_token_accuracy": 0.15684450417757034,
|
|
"num_tokens": 11532255.0,
|
|
"step": 4555
|
|
},
|
|
{
|
|
"entropy": 6.544296550750732,
|
|
"epoch": 0.5262550490478938,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004980855823972717,
|
|
"loss": 6.3394,
|
|
"mean_token_accuracy": 0.1619937911629677,
|
|
"num_tokens": 11544596.0,
|
|
"step": 4560
|
|
},
|
|
{
|
|
"entropy": 6.4948595523834225,
|
|
"epoch": 0.5268320830929025,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.000498080207198128,
|
|
"loss": 6.4627,
|
|
"mean_token_accuracy": 0.1510115385055542,
|
|
"num_tokens": 11556758.0,
|
|
"step": 4565
|
|
},
|
|
{
|
|
"entropy": 6.56593132019043,
|
|
"epoch": 0.5274091171379112,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004980748244957925,
|
|
"loss": 6.4435,
|
|
"mean_token_accuracy": 0.14832553789019584,
|
|
"num_tokens": 11570070.0,
|
|
"step": 4570
|
|
},
|
|
{
|
|
"entropy": 6.518224000930786,
|
|
"epoch": 0.5279861511829198,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004980694342904461,
|
|
"loss": 6.3229,
|
|
"mean_token_accuracy": 0.16714330315589904,
|
|
"num_tokens": 11582566.0,
|
|
"step": 4575
|
|
},
|
|
{
|
|
"entropy": 6.45475206375122,
|
|
"epoch": 0.5285631852279284,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004980640365822701,
|
|
"loss": 6.2754,
|
|
"mean_token_accuracy": 0.16809093654155732,
|
|
"num_tokens": 11595238.0,
|
|
"step": 4580
|
|
},
|
|
{
|
|
"entropy": 6.546554517745972,
|
|
"epoch": 0.5291402192729371,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.000498058631371446,
|
|
"loss": 6.4037,
|
|
"mean_token_accuracy": 0.1609138697385788,
|
|
"num_tokens": 11608646.0,
|
|
"step": 4585
|
|
},
|
|
{
|
|
"entropy": 6.4840919971466064,
|
|
"epoch": 0.5297172533179457,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004980532186581555,
|
|
"loss": 6.3518,
|
|
"mean_token_accuracy": 0.1566994830965996,
|
|
"num_tokens": 11619610.0,
|
|
"step": 4590
|
|
},
|
|
{
|
|
"entropy": 6.437766647338867,
|
|
"epoch": 0.5302942873629544,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.000498047798442581,
|
|
"loss": 6.2399,
|
|
"mean_token_accuracy": 0.17291501462459563,
|
|
"num_tokens": 11631691.0,
|
|
"step": 4595
|
|
},
|
|
{
|
|
"entropy": 6.4640161991119385,
|
|
"epoch": 0.5308713214079631,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004980423707249044,
|
|
"loss": 6.286,
|
|
"mean_token_accuracy": 0.16628182977437972,
|
|
"num_tokens": 11644330.0,
|
|
"step": 4600
|
|
},
|
|
{
|
|
"entropy": 6.56778769493103,
|
|
"epoch": 0.5314483554529718,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004980369355053086,
|
|
"loss": 6.4038,
|
|
"mean_token_accuracy": 0.15543297529220582,
|
|
"num_tokens": 11656826.0,
|
|
"step": 4605
|
|
},
|
|
{
|
|
"entropy": 6.468916130065918,
|
|
"epoch": 0.5320253894979804,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004980314927839763,
|
|
"loss": 6.3838,
|
|
"mean_token_accuracy": 0.1545664668083191,
|
|
"num_tokens": 11668669.0,
|
|
"step": 4610
|
|
},
|
|
{
|
|
"entropy": 6.521239757537842,
|
|
"epoch": 0.532602423542989,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004980260425610903,
|
|
"loss": 6.3392,
|
|
"mean_token_accuracy": 0.15642919391393661,
|
|
"num_tokens": 11681237.0,
|
|
"step": 4615
|
|
},
|
|
{
|
|
"entropy": 6.442376375198364,
|
|
"epoch": 0.5331794575879977,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004980205848368343,
|
|
"loss": 6.3934,
|
|
"mean_token_accuracy": 0.15855768769979478,
|
|
"num_tokens": 11693953.0,
|
|
"step": 4620
|
|
},
|
|
{
|
|
"entropy": 6.447347021102905,
|
|
"epoch": 0.5337564916330063,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004980151196113917,
|
|
"loss": 6.3594,
|
|
"mean_token_accuracy": 0.1600581720471382,
|
|
"num_tokens": 11705364.0,
|
|
"step": 4625
|
|
},
|
|
{
|
|
"entropy": 6.5338707447052,
|
|
"epoch": 0.534333525678015,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004980096468849464,
|
|
"loss": 6.3732,
|
|
"mean_token_accuracy": 0.15663958638906478,
|
|
"num_tokens": 11717664.0,
|
|
"step": 4630
|
|
},
|
|
{
|
|
"entropy": 6.507907485961914,
|
|
"epoch": 0.5349105597230237,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004980041666576823,
|
|
"loss": 6.3688,
|
|
"mean_token_accuracy": 0.15612590909004212,
|
|
"num_tokens": 11731143.0,
|
|
"step": 4635
|
|
},
|
|
{
|
|
"entropy": 6.513534021377564,
|
|
"epoch": 0.5354875937680323,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004979986789297837,
|
|
"loss": 6.3105,
|
|
"mean_token_accuracy": 0.1600772351026535,
|
|
"num_tokens": 11743904.0,
|
|
"step": 4640
|
|
},
|
|
{
|
|
"entropy": 6.3788543224334715,
|
|
"epoch": 0.536064627813041,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004979931837014355,
|
|
"loss": 6.1961,
|
|
"mean_token_accuracy": 0.16465394496917723,
|
|
"num_tokens": 11756731.0,
|
|
"step": 4645
|
|
},
|
|
{
|
|
"entropy": 6.432486915588379,
|
|
"epoch": 0.5366416618580496,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004979876809728223,
|
|
"loss": 6.3189,
|
|
"mean_token_accuracy": 0.16390772312879562,
|
|
"num_tokens": 11768597.0,
|
|
"step": 4650
|
|
},
|
|
{
|
|
"entropy": 6.424148178100586,
|
|
"epoch": 0.5372186959030583,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004979821707441292,
|
|
"loss": 6.2386,
|
|
"mean_token_accuracy": 0.1694170728325844,
|
|
"num_tokens": 11781464.0,
|
|
"step": 4655
|
|
},
|
|
{
|
|
"entropy": 6.385573053359986,
|
|
"epoch": 0.5377957299480669,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004979766530155416,
|
|
"loss": 6.2189,
|
|
"mean_token_accuracy": 0.17261924147605895,
|
|
"num_tokens": 11794215.0,
|
|
"step": 4660
|
|
},
|
|
{
|
|
"entropy": 6.4749983787536625,
|
|
"epoch": 0.5383727639930755,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004979711277872449,
|
|
"loss": 6.444,
|
|
"mean_token_accuracy": 0.15245128124952317,
|
|
"num_tokens": 11807456.0,
|
|
"step": 4665
|
|
},
|
|
{
|
|
"entropy": 6.4587053775787355,
|
|
"epoch": 0.5389497980380843,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004979655950594252,
|
|
"loss": 6.337,
|
|
"mean_token_accuracy": 0.1637497663497925,
|
|
"num_tokens": 11819730.0,
|
|
"step": 4670
|
|
},
|
|
{
|
|
"entropy": 6.460689640045166,
|
|
"epoch": 0.5395268320830929,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004979600548322684,
|
|
"loss": 6.3466,
|
|
"mean_token_accuracy": 0.17143890559673308,
|
|
"num_tokens": 11831892.0,
|
|
"step": 4675
|
|
},
|
|
{
|
|
"entropy": 6.456334400177002,
|
|
"epoch": 0.5401038661281016,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.000497954507105961,
|
|
"loss": 6.3654,
|
|
"mean_token_accuracy": 0.15969292372465133,
|
|
"num_tokens": 11844114.0,
|
|
"step": 4680
|
|
},
|
|
{
|
|
"entropy": 6.526745080947876,
|
|
"epoch": 0.5406809001731102,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004979489518806893,
|
|
"loss": 6.3234,
|
|
"mean_token_accuracy": 0.15686967074871064,
|
|
"num_tokens": 11855832.0,
|
|
"step": 4685
|
|
},
|
|
{
|
|
"entropy": 6.465781307220459,
|
|
"epoch": 0.5412579342181189,
|
|
"grad_norm": 0.73828125,
|
|
"learning_rate": 0.0004979433891566405,
|
|
"loss": 6.4208,
|
|
"mean_token_accuracy": 0.15778311640024184,
|
|
"num_tokens": 11868837.0,
|
|
"step": 4690
|
|
},
|
|
{
|
|
"entropy": 6.4877008438110355,
|
|
"epoch": 0.5418349682631275,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004979378189340015,
|
|
"loss": 6.3289,
|
|
"mean_token_accuracy": 0.16794711649417876,
|
|
"num_tokens": 11880608.0,
|
|
"step": 4695
|
|
},
|
|
{
|
|
"entropy": 6.476086235046386,
|
|
"epoch": 0.5424120023081361,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004979322412129597,
|
|
"loss": 6.344,
|
|
"mean_token_accuracy": 0.15937476307153703,
|
|
"num_tokens": 11892652.0,
|
|
"step": 4700
|
|
},
|
|
{
|
|
"entropy": 6.458676815032959,
|
|
"epoch": 0.5429890363531449,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004979266559937028,
|
|
"loss": 6.2977,
|
|
"mean_token_accuracy": 0.15880679041147233,
|
|
"num_tokens": 11904572.0,
|
|
"step": 4705
|
|
},
|
|
{
|
|
"entropy": 6.5893689632415775,
|
|
"epoch": 0.5435660703981535,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004979210632764185,
|
|
"loss": 6.4386,
|
|
"mean_token_accuracy": 0.15327975898981094,
|
|
"num_tokens": 11917794.0,
|
|
"step": 4710
|
|
},
|
|
{
|
|
"entropy": 6.511403131484985,
|
|
"epoch": 0.5441431044431622,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004979154630612949,
|
|
"loss": 6.3223,
|
|
"mean_token_accuracy": 0.156440269947052,
|
|
"num_tokens": 11930403.0,
|
|
"step": 4715
|
|
},
|
|
{
|
|
"entropy": 6.556756973266602,
|
|
"epoch": 0.5447201384881708,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004979098553485205,
|
|
"loss": 6.4268,
|
|
"mean_token_accuracy": 0.15392898991703988,
|
|
"num_tokens": 11943974.0,
|
|
"step": 4720
|
|
},
|
|
{
|
|
"entropy": 6.528595209121704,
|
|
"epoch": 0.5452971725331794,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004979042401382838,
|
|
"loss": 6.4272,
|
|
"mean_token_accuracy": 0.14962007254362106,
|
|
"num_tokens": 11956887.0,
|
|
"step": 4725
|
|
},
|
|
{
|
|
"entropy": 6.554116296768188,
|
|
"epoch": 0.5458742065781881,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004978986174307737,
|
|
"loss": 6.2719,
|
|
"mean_token_accuracy": 0.1685679391026497,
|
|
"num_tokens": 11969504.0,
|
|
"step": 4730
|
|
},
|
|
{
|
|
"entropy": 6.43930287361145,
|
|
"epoch": 0.5464512406231967,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004978929872261794,
|
|
"loss": 6.326,
|
|
"mean_token_accuracy": 0.16304372251033783,
|
|
"num_tokens": 11983432.0,
|
|
"step": 4735
|
|
},
|
|
{
|
|
"entropy": 6.510177850723267,
|
|
"epoch": 0.5470282746682055,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004978873495246901,
|
|
"loss": 6.3165,
|
|
"mean_token_accuracy": 0.1688837394118309,
|
|
"num_tokens": 11995915.0,
|
|
"step": 4740
|
|
},
|
|
{
|
|
"entropy": 6.414366436004639,
|
|
"epoch": 0.5476053087132141,
|
|
"grad_norm": 0.734375,
|
|
"learning_rate": 0.0004978817043264955,
|
|
"loss": 6.3199,
|
|
"mean_token_accuracy": 0.1632016494870186,
|
|
"num_tokens": 12008395.0,
|
|
"step": 4745
|
|
},
|
|
{
|
|
"entropy": 6.401845407485962,
|
|
"epoch": 0.5481823427582228,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004978760516317856,
|
|
"loss": 6.2892,
|
|
"mean_token_accuracy": 0.16130719035863877,
|
|
"num_tokens": 12021179.0,
|
|
"step": 4750
|
|
},
|
|
{
|
|
"entropy": 6.523613595962525,
|
|
"epoch": 0.5487593768032314,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004978703914407503,
|
|
"loss": 6.3688,
|
|
"mean_token_accuracy": 0.1535087063908577,
|
|
"num_tokens": 12033798.0,
|
|
"step": 4755
|
|
},
|
|
{
|
|
"entropy": 6.5373670101165775,
|
|
"epoch": 0.54933641084824,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004978647237535802,
|
|
"loss": 6.3837,
|
|
"mean_token_accuracy": 0.15837208032608033,
|
|
"num_tokens": 12045720.0,
|
|
"step": 4760
|
|
},
|
|
{
|
|
"entropy": 6.5291375637054445,
|
|
"epoch": 0.5499134448932487,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004978590485704657,
|
|
"loss": 6.3069,
|
|
"mean_token_accuracy": 0.16414411664009093,
|
|
"num_tokens": 12058616.0,
|
|
"step": 4765
|
|
},
|
|
{
|
|
"entropy": 6.459080219268799,
|
|
"epoch": 0.5504904789382573,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004978533658915979,
|
|
"loss": 6.4107,
|
|
"mean_token_accuracy": 0.15961592346429826,
|
|
"num_tokens": 12070173.0,
|
|
"step": 4770
|
|
},
|
|
{
|
|
"entropy": 6.411388826370239,
|
|
"epoch": 0.5510675129832661,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004978476757171678,
|
|
"loss": 6.2896,
|
|
"mean_token_accuracy": 0.17188112884759904,
|
|
"num_tokens": 12083499.0,
|
|
"step": 4775
|
|
},
|
|
{
|
|
"entropy": 6.456639385223388,
|
|
"epoch": 0.5516445470282747,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004978419780473668,
|
|
"loss": 6.3513,
|
|
"mean_token_accuracy": 0.16023088991641998,
|
|
"num_tokens": 12095773.0,
|
|
"step": 4780
|
|
},
|
|
{
|
|
"entropy": 6.460473442077637,
|
|
"epoch": 0.5522215810732833,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004978362728823865,
|
|
"loss": 6.3514,
|
|
"mean_token_accuracy": 0.16689216941595078,
|
|
"num_tokens": 12107640.0,
|
|
"step": 4785
|
|
},
|
|
{
|
|
"entropy": 6.499213218688965,
|
|
"epoch": 0.552798615118292,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004978305602224189,
|
|
"loss": 6.297,
|
|
"mean_token_accuracy": 0.15836577117443085,
|
|
"num_tokens": 12120433.0,
|
|
"step": 4790
|
|
},
|
|
{
|
|
"entropy": 6.43018364906311,
|
|
"epoch": 0.5533756491633006,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004978248400676562,
|
|
"loss": 6.2886,
|
|
"mean_token_accuracy": 0.16459263265132903,
|
|
"num_tokens": 12133326.0,
|
|
"step": 4795
|
|
},
|
|
{
|
|
"entropy": 6.528225231170654,
|
|
"epoch": 0.5539526832083093,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.0004978191124182905,
|
|
"loss": 6.3795,
|
|
"mean_token_accuracy": 0.15583104342222215,
|
|
"num_tokens": 12145119.0,
|
|
"step": 4800
|
|
},
|
|
{
|
|
"entropy": 6.500142383575439,
|
|
"epoch": 0.5545297172533179,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004978133772745149,
|
|
"loss": 6.3437,
|
|
"mean_token_accuracy": 0.1544487237930298,
|
|
"num_tokens": 12157414.0,
|
|
"step": 4805
|
|
},
|
|
{
|
|
"entropy": 6.3837847232818605,
|
|
"epoch": 0.5551067512983267,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004978076346365218,
|
|
"loss": 6.2201,
|
|
"mean_token_accuracy": 0.16513165831565857,
|
|
"num_tokens": 12170226.0,
|
|
"step": 4810
|
|
},
|
|
{
|
|
"entropy": 6.448636436462403,
|
|
"epoch": 0.5556837853433353,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004978018845045047,
|
|
"loss": 6.2578,
|
|
"mean_token_accuracy": 0.16587026715278624,
|
|
"num_tokens": 12182804.0,
|
|
"step": 4815
|
|
},
|
|
{
|
|
"entropy": 6.569641876220703,
|
|
"epoch": 0.5562608193883439,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004977961268786568,
|
|
"loss": 6.3685,
|
|
"mean_token_accuracy": 0.16015153974294663,
|
|
"num_tokens": 12194795.0,
|
|
"step": 4820
|
|
},
|
|
{
|
|
"entropy": 6.4354218482971195,
|
|
"epoch": 0.5568378534333526,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004977903617591719,
|
|
"loss": 6.3301,
|
|
"mean_token_accuracy": 0.16911077052354812,
|
|
"num_tokens": 12207880.0,
|
|
"step": 4825
|
|
},
|
|
{
|
|
"entropy": 6.479910516738892,
|
|
"epoch": 0.5574148874783612,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004977845891462439,
|
|
"loss": 6.3835,
|
|
"mean_token_accuracy": 0.15894741415977479,
|
|
"num_tokens": 12219434.0,
|
|
"step": 4830
|
|
},
|
|
{
|
|
"entropy": 6.427562856674195,
|
|
"epoch": 0.5579919215233698,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004977788090400668,
|
|
"loss": 6.3085,
|
|
"mean_token_accuracy": 0.16785141825675964,
|
|
"num_tokens": 12232775.0,
|
|
"step": 4835
|
|
},
|
|
{
|
|
"entropy": 6.477736520767212,
|
|
"epoch": 0.5585689555683785,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004977730214408352,
|
|
"loss": 6.2896,
|
|
"mean_token_accuracy": 0.16171760335564614,
|
|
"num_tokens": 12245306.0,
|
|
"step": 4840
|
|
},
|
|
{
|
|
"entropy": 6.389444780349732,
|
|
"epoch": 0.5591459896133872,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004977672263487435,
|
|
"loss": 6.2348,
|
|
"mean_token_accuracy": 0.1595480427145958,
|
|
"num_tokens": 12257553.0,
|
|
"step": 4845
|
|
},
|
|
{
|
|
"entropy": 6.3948791980743405,
|
|
"epoch": 0.5597230236583959,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000497761423763987,
|
|
"loss": 6.2974,
|
|
"mean_token_accuracy": 0.16309260874986647,
|
|
"num_tokens": 12269626.0,
|
|
"step": 4850
|
|
},
|
|
{
|
|
"entropy": 6.498226833343506,
|
|
"epoch": 0.5603000577034045,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004977556136867606,
|
|
"loss": 6.3464,
|
|
"mean_token_accuracy": 0.1585548087954521,
|
|
"num_tokens": 12282180.0,
|
|
"step": 4855
|
|
},
|
|
{
|
|
"entropy": 6.541059827804565,
|
|
"epoch": 0.5608770917484132,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004977497961172598,
|
|
"loss": 6.381,
|
|
"mean_token_accuracy": 0.16513874679803847,
|
|
"num_tokens": 12296315.0,
|
|
"step": 4860
|
|
},
|
|
{
|
|
"entropy": 6.445973348617554,
|
|
"epoch": 0.5614541257934218,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004977439710556802,
|
|
"loss": 6.3057,
|
|
"mean_token_accuracy": 0.15708381831645965,
|
|
"num_tokens": 12308800.0,
|
|
"step": 4865
|
|
},
|
|
{
|
|
"entropy": 6.436301040649414,
|
|
"epoch": 0.5620311598384304,
|
|
"grad_norm": 0.75390625,
|
|
"learning_rate": 0.0004977381385022179,
|
|
"loss": 6.3618,
|
|
"mean_token_accuracy": 0.16087310016155243,
|
|
"num_tokens": 12321717.0,
|
|
"step": 4870
|
|
},
|
|
{
|
|
"entropy": 6.537671327590942,
|
|
"epoch": 0.5626081938834391,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.0004977322984570688,
|
|
"loss": 6.3885,
|
|
"mean_token_accuracy": 0.15361500531435013,
|
|
"num_tokens": 12335446.0,
|
|
"step": 4875
|
|
},
|
|
{
|
|
"entropy": 6.453512048721313,
|
|
"epoch": 0.5631852279284478,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004977264509204296,
|
|
"loss": 6.3143,
|
|
"mean_token_accuracy": 0.1592903256416321,
|
|
"num_tokens": 12348677.0,
|
|
"step": 4880
|
|
},
|
|
{
|
|
"entropy": 6.4898766040802,
|
|
"epoch": 0.5637622619734565,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004977205958924967,
|
|
"loss": 6.3472,
|
|
"mean_token_accuracy": 0.16099169105291367,
|
|
"num_tokens": 12360934.0,
|
|
"step": 4885
|
|
},
|
|
{
|
|
"entropy": 6.5359296798706055,
|
|
"epoch": 0.5643392960184651,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004977147333734673,
|
|
"loss": 6.4269,
|
|
"mean_token_accuracy": 0.156376850605011,
|
|
"num_tokens": 12373538.0,
|
|
"step": 4890
|
|
},
|
|
{
|
|
"entropy": 6.398646211624145,
|
|
"epoch": 0.5649163300634737,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004977088633635385,
|
|
"loss": 6.332,
|
|
"mean_token_accuracy": 0.15687417089939118,
|
|
"num_tokens": 12385291.0,
|
|
"step": 4895
|
|
},
|
|
{
|
|
"entropy": 6.582235097885132,
|
|
"epoch": 0.5654933641084824,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004977029858629076,
|
|
"loss": 6.3601,
|
|
"mean_token_accuracy": 0.15636546015739441,
|
|
"num_tokens": 12398324.0,
|
|
"step": 4900
|
|
},
|
|
{
|
|
"entropy": 6.457294559478759,
|
|
"epoch": 0.566070398153491,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004976971008717726,
|
|
"loss": 6.3267,
|
|
"mean_token_accuracy": 0.15693403780460358,
|
|
"num_tokens": 12409807.0,
|
|
"step": 4905
|
|
},
|
|
{
|
|
"entropy": 6.483905696868897,
|
|
"epoch": 0.5666474321984997,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004976912083903309,
|
|
"loss": 6.4167,
|
|
"mean_token_accuracy": 0.1543364331126213,
|
|
"num_tokens": 12422658.0,
|
|
"step": 4910
|
|
},
|
|
{
|
|
"entropy": 6.564264154434204,
|
|
"epoch": 0.5672244662435084,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004976853084187814,
|
|
"loss": 6.335,
|
|
"mean_token_accuracy": 0.15391853898763658,
|
|
"num_tokens": 12435912.0,
|
|
"step": 4915
|
|
},
|
|
{
|
|
"entropy": 6.4374730587005615,
|
|
"epoch": 0.5678015002885171,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004976794009573219,
|
|
"loss": 6.3374,
|
|
"mean_token_accuracy": 0.16345978677272796,
|
|
"num_tokens": 12448382.0,
|
|
"step": 4920
|
|
},
|
|
{
|
|
"entropy": 6.52530608177185,
|
|
"epoch": 0.5683785343335257,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004976734860061515,
|
|
"loss": 6.4579,
|
|
"mean_token_accuracy": 0.1543452709913254,
|
|
"num_tokens": 12461355.0,
|
|
"step": 4925
|
|
},
|
|
{
|
|
"entropy": 6.517202425003052,
|
|
"epoch": 0.5689555683785343,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004976675635654688,
|
|
"loss": 6.2824,
|
|
"mean_token_accuracy": 0.16503604203462602,
|
|
"num_tokens": 12473931.0,
|
|
"step": 4930
|
|
},
|
|
{
|
|
"entropy": 6.439925289154052,
|
|
"epoch": 0.569532602423543,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004976616336354733,
|
|
"loss": 6.336,
|
|
"mean_token_accuracy": 0.16363679096102715,
|
|
"num_tokens": 12486130.0,
|
|
"step": 4935
|
|
},
|
|
{
|
|
"entropy": 6.407979440689087,
|
|
"epoch": 0.5701096364685516,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004976556962163645,
|
|
"loss": 6.2576,
|
|
"mean_token_accuracy": 0.16573751717805862,
|
|
"num_tokens": 12499336.0,
|
|
"step": 4940
|
|
},
|
|
{
|
|
"entropy": 6.503925704956055,
|
|
"epoch": 0.5706866705135603,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004976497513083419,
|
|
"loss": 6.2713,
|
|
"mean_token_accuracy": 0.16759575754404069,
|
|
"num_tokens": 12512875.0,
|
|
"step": 4945
|
|
},
|
|
{
|
|
"entropy": 6.4720992088317875,
|
|
"epoch": 0.571263704558569,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004976437989116055,
|
|
"loss": 6.3864,
|
|
"mean_token_accuracy": 0.15907713323831557,
|
|
"num_tokens": 12524985.0,
|
|
"step": 4950
|
|
},
|
|
{
|
|
"entropy": 6.469041061401367,
|
|
"epoch": 0.5718407386035776,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004976378390263554,
|
|
"loss": 6.3316,
|
|
"mean_token_accuracy": 0.16550833880901336,
|
|
"num_tokens": 12538244.0,
|
|
"step": 4955
|
|
},
|
|
{
|
|
"entropy": 6.539459848403931,
|
|
"epoch": 0.5724177726485863,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004976318716527924,
|
|
"loss": 6.3286,
|
|
"mean_token_accuracy": 0.16238382309675217,
|
|
"num_tokens": 12550769.0,
|
|
"step": 4960
|
|
},
|
|
{
|
|
"entropy": 6.3982970237731935,
|
|
"epoch": 0.5729948066935949,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004976258967911168,
|
|
"loss": 6.3497,
|
|
"mean_token_accuracy": 0.16136492043733597,
|
|
"num_tokens": 12563294.0,
|
|
"step": 4965
|
|
},
|
|
{
|
|
"entropy": 6.467198228836059,
|
|
"epoch": 0.5735718407386036,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004976199144415298,
|
|
"loss": 6.3404,
|
|
"mean_token_accuracy": 0.1579903855919838,
|
|
"num_tokens": 12575857.0,
|
|
"step": 4970
|
|
},
|
|
{
|
|
"entropy": 6.509387397766114,
|
|
"epoch": 0.5741488747836122,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004976139246042325,
|
|
"loss": 6.2934,
|
|
"mean_token_accuracy": 0.16424267292022704,
|
|
"num_tokens": 12589881.0,
|
|
"step": 4975
|
|
},
|
|
{
|
|
"entropy": 6.504959058761597,
|
|
"epoch": 0.5747259088286208,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004976079272794265,
|
|
"loss": 6.3632,
|
|
"mean_token_accuracy": 0.15701202750205995,
|
|
"num_tokens": 12604100.0,
|
|
"step": 4980
|
|
},
|
|
{
|
|
"entropy": 6.4913969993591305,
|
|
"epoch": 0.5753029428736296,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004976019224673134,
|
|
"loss": 6.3798,
|
|
"mean_token_accuracy": 0.1594866156578064,
|
|
"num_tokens": 12616643.0,
|
|
"step": 4985
|
|
},
|
|
{
|
|
"entropy": 6.417438554763794,
|
|
"epoch": 0.5758799769186382,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004975959101680953,
|
|
"loss": 6.3119,
|
|
"mean_token_accuracy": 0.16797322630882264,
|
|
"num_tokens": 12627676.0,
|
|
"step": 4990
|
|
},
|
|
{
|
|
"entropy": 6.41131820678711,
|
|
"epoch": 0.5764570109636469,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004975898903819742,
|
|
"loss": 6.2615,
|
|
"mean_token_accuracy": 0.16815593391656875,
|
|
"num_tokens": 12639352.0,
|
|
"step": 4995
|
|
},
|
|
{
|
|
"entropy": 6.454370927810669,
|
|
"epoch": 0.5770340450086555,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004975838631091527,
|
|
"loss": 6.2447,
|
|
"mean_token_accuracy": 0.1643560364842415,
|
|
"num_tokens": 12652102.0,
|
|
"step": 5000
|
|
},
|
|
{
|
|
"entropy": 6.509260559082032,
|
|
"epoch": 0.5776110790536642,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004975778283498336,
|
|
"loss": 6.3592,
|
|
"mean_token_accuracy": 0.1578929305076599,
|
|
"num_tokens": 12665084.0,
|
|
"step": 5005
|
|
},
|
|
{
|
|
"entropy": 6.360739755630493,
|
|
"epoch": 0.5781881130986728,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.0004975717861042198,
|
|
"loss": 6.2652,
|
|
"mean_token_accuracy": 0.16091600209474563,
|
|
"num_tokens": 12677512.0,
|
|
"step": 5010
|
|
},
|
|
{
|
|
"entropy": 6.524038887023925,
|
|
"epoch": 0.5787651471436814,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004975657363725146,
|
|
"loss": 6.3909,
|
|
"mean_token_accuracy": 0.1512112334370613,
|
|
"num_tokens": 12690488.0,
|
|
"step": 5015
|
|
},
|
|
{
|
|
"entropy": 6.54783821105957,
|
|
"epoch": 0.5793421811886902,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004975596791549213,
|
|
"loss": 6.3248,
|
|
"mean_token_accuracy": 0.15481803715229034,
|
|
"num_tokens": 12703830.0,
|
|
"step": 5020
|
|
},
|
|
{
|
|
"entropy": 6.459069347381591,
|
|
"epoch": 0.5799192152336988,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004975536144516437,
|
|
"loss": 6.3317,
|
|
"mean_token_accuracy": 0.16206814646720885,
|
|
"num_tokens": 12716020.0,
|
|
"step": 5025
|
|
},
|
|
{
|
|
"entropy": 6.49042387008667,
|
|
"epoch": 0.5804962492787075,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.000497547542262886,
|
|
"loss": 6.3974,
|
|
"mean_token_accuracy": 0.15198142379522322,
|
|
"num_tokens": 12728989.0,
|
|
"step": 5030
|
|
},
|
|
{
|
|
"entropy": 6.5610472679138185,
|
|
"epoch": 0.5810732833237161,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004975414625888521,
|
|
"loss": 6.2683,
|
|
"mean_token_accuracy": 0.1594917967915535,
|
|
"num_tokens": 12741090.0,
|
|
"step": 5035
|
|
},
|
|
{
|
|
"entropy": 6.464597845077515,
|
|
"epoch": 0.5816503173687247,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004975353754297468,
|
|
"loss": 6.3082,
|
|
"mean_token_accuracy": 0.16099455803632737,
|
|
"num_tokens": 12754176.0,
|
|
"step": 5040
|
|
},
|
|
{
|
|
"entropy": 6.39254412651062,
|
|
"epoch": 0.5822273514137334,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004975292807857745,
|
|
"loss": 6.2864,
|
|
"mean_token_accuracy": 0.15810506939888,
|
|
"num_tokens": 12766149.0,
|
|
"step": 5045
|
|
},
|
|
{
|
|
"entropy": 6.485265731811523,
|
|
"epoch": 0.582804385458742,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004975231786571406,
|
|
"loss": 6.3554,
|
|
"mean_token_accuracy": 0.16003530323505402,
|
|
"num_tokens": 12778337.0,
|
|
"step": 5050
|
|
},
|
|
{
|
|
"entropy": 6.46652660369873,
|
|
"epoch": 0.5833814195037508,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004975170690440499,
|
|
"loss": 6.2617,
|
|
"mean_token_accuracy": 0.16169480085372925,
|
|
"num_tokens": 12790146.0,
|
|
"step": 5055
|
|
},
|
|
{
|
|
"entropy": 6.452705526351929,
|
|
"epoch": 0.5839584535487594,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004975109519467083,
|
|
"loss": 6.249,
|
|
"mean_token_accuracy": 0.16325473338365554,
|
|
"num_tokens": 12802821.0,
|
|
"step": 5060
|
|
},
|
|
{
|
|
"entropy": 6.394228124618531,
|
|
"epoch": 0.584535487593768,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004975048273653212,
|
|
"loss": 6.397,
|
|
"mean_token_accuracy": 0.16143627166748048,
|
|
"num_tokens": 12814409.0,
|
|
"step": 5065
|
|
},
|
|
{
|
|
"entropy": 6.498150205612182,
|
|
"epoch": 0.5851125216387767,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004974986953000948,
|
|
"loss": 6.3009,
|
|
"mean_token_accuracy": 0.15540309697389604,
|
|
"num_tokens": 12827398.0,
|
|
"step": 5070
|
|
},
|
|
{
|
|
"entropy": 6.4518615245819095,
|
|
"epoch": 0.5856895556837853,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004974925557512354,
|
|
"loss": 6.2709,
|
|
"mean_token_accuracy": 0.16093710511922837,
|
|
"num_tokens": 12840378.0,
|
|
"step": 5075
|
|
},
|
|
{
|
|
"entropy": 6.448571586608887,
|
|
"epoch": 0.586266589728794,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004974864087189493,
|
|
"loss": 6.357,
|
|
"mean_token_accuracy": 0.16484926640987396,
|
|
"num_tokens": 12853493.0,
|
|
"step": 5080
|
|
},
|
|
{
|
|
"entropy": 6.437574625015259,
|
|
"epoch": 0.5868436237738026,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004974802542034434,
|
|
"loss": 6.2316,
|
|
"mean_token_accuracy": 0.1698588877916336,
|
|
"num_tokens": 12865052.0,
|
|
"step": 5085
|
|
},
|
|
{
|
|
"entropy": 6.47462739944458,
|
|
"epoch": 0.5874206578188114,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004974740922049246,
|
|
"loss": 6.3696,
|
|
"mean_token_accuracy": 0.15433994829654693,
|
|
"num_tokens": 12878095.0,
|
|
"step": 5090
|
|
},
|
|
{
|
|
"entropy": 6.512469148635864,
|
|
"epoch": 0.58799769186382,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004974679227236004,
|
|
"loss": 6.2207,
|
|
"mean_token_accuracy": 0.17119740098714828,
|
|
"num_tokens": 12890855.0,
|
|
"step": 5095
|
|
},
|
|
{
|
|
"entropy": 6.409336709976197,
|
|
"epoch": 0.5885747259088286,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004974617457596779,
|
|
"loss": 6.2785,
|
|
"mean_token_accuracy": 0.1650840535759926,
|
|
"num_tokens": 12903833.0,
|
|
"step": 5100
|
|
},
|
|
{
|
|
"entropy": 6.506627464294434,
|
|
"epoch": 0.5891517599538373,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004974555613133652,
|
|
"loss": 6.4079,
|
|
"mean_token_accuracy": 0.15667158514261245,
|
|
"num_tokens": 12917579.0,
|
|
"step": 5105
|
|
},
|
|
{
|
|
"entropy": 6.480052518844604,
|
|
"epoch": 0.5897287939988459,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004974493693848702,
|
|
"loss": 6.3818,
|
|
"mean_token_accuracy": 0.1637255698442459,
|
|
"num_tokens": 12929718.0,
|
|
"step": 5110
|
|
},
|
|
{
|
|
"entropy": 6.324490737915039,
|
|
"epoch": 0.5903058280438546,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004974431699744011,
|
|
"loss": 6.221,
|
|
"mean_token_accuracy": 0.16753413528203964,
|
|
"num_tokens": 12943031.0,
|
|
"step": 5115
|
|
},
|
|
{
|
|
"entropy": 6.465872192382813,
|
|
"epoch": 0.5908828620888632,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004974369630821665,
|
|
"loss": 6.3385,
|
|
"mean_token_accuracy": 0.1643362522125244,
|
|
"num_tokens": 12954843.0,
|
|
"step": 5120
|
|
},
|
|
{
|
|
"entropy": 6.429745864868164,
|
|
"epoch": 0.5914598961338718,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004974307487083752,
|
|
"loss": 6.3302,
|
|
"mean_token_accuracy": 0.16157597452402114,
|
|
"num_tokens": 12966915.0,
|
|
"step": 5125
|
|
},
|
|
{
|
|
"entropy": 6.483998966217041,
|
|
"epoch": 0.5920369301788806,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004974245268532361,
|
|
"loss": 6.3713,
|
|
"mean_token_accuracy": 0.1558799222111702,
|
|
"num_tokens": 12979941.0,
|
|
"step": 5130
|
|
},
|
|
{
|
|
"entropy": 6.499818563461304,
|
|
"epoch": 0.5926139642238892,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004974182975169585,
|
|
"loss": 6.2561,
|
|
"mean_token_accuracy": 0.16042693704366684,
|
|
"num_tokens": 12992836.0,
|
|
"step": 5135
|
|
},
|
|
{
|
|
"entropy": 6.474150991439819,
|
|
"epoch": 0.5931909982688979,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000497412060699752,
|
|
"loss": 6.3075,
|
|
"mean_token_accuracy": 0.16249936521053315,
|
|
"num_tokens": 13005246.0,
|
|
"step": 5140
|
|
},
|
|
{
|
|
"entropy": 6.422859621047974,
|
|
"epoch": 0.5937680323139065,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004974058164018263,
|
|
"loss": 6.2729,
|
|
"mean_token_accuracy": 0.159485824406147,
|
|
"num_tokens": 13016842.0,
|
|
"step": 5145
|
|
},
|
|
{
|
|
"entropy": 6.379044771194458,
|
|
"epoch": 0.5943450663589152,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004973995646233914,
|
|
"loss": 6.277,
|
|
"mean_token_accuracy": 0.16455476433038713,
|
|
"num_tokens": 13028388.0,
|
|
"step": 5150
|
|
},
|
|
{
|
|
"entropy": 6.483341646194458,
|
|
"epoch": 0.5949221004039238,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004973933053646576,
|
|
"loss": 6.2963,
|
|
"mean_token_accuracy": 0.16036218404769897,
|
|
"num_tokens": 13041895.0,
|
|
"step": 5155
|
|
},
|
|
{
|
|
"entropy": 6.4746462345123295,
|
|
"epoch": 0.5954991344489324,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004973870386258355,
|
|
"loss": 6.3554,
|
|
"mean_token_accuracy": 0.16368395537137986,
|
|
"num_tokens": 13055984.0,
|
|
"step": 5160
|
|
},
|
|
{
|
|
"entropy": 6.484179830551147,
|
|
"epoch": 0.5960761684939412,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004973807644071357,
|
|
"loss": 6.303,
|
|
"mean_token_accuracy": 0.16322016417980195,
|
|
"num_tokens": 13068735.0,
|
|
"step": 5165
|
|
},
|
|
{
|
|
"entropy": 6.49740834236145,
|
|
"epoch": 0.5966532025389498,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0004973744827087695,
|
|
"loss": 6.3685,
|
|
"mean_token_accuracy": 0.160064959526062,
|
|
"num_tokens": 13081564.0,
|
|
"step": 5170
|
|
},
|
|
{
|
|
"entropy": 6.477915859222412,
|
|
"epoch": 0.5972302365839585,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.000497368193530948,
|
|
"loss": 6.2975,
|
|
"mean_token_accuracy": 0.16501372158527375,
|
|
"num_tokens": 13094146.0,
|
|
"step": 5175
|
|
},
|
|
{
|
|
"entropy": 6.37415885925293,
|
|
"epoch": 0.5978072706289671,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004973618968738828,
|
|
"loss": 6.2557,
|
|
"mean_token_accuracy": 0.16740904450416566,
|
|
"num_tokens": 13106753.0,
|
|
"step": 5180
|
|
},
|
|
{
|
|
"entropy": 6.414618730545044,
|
|
"epoch": 0.5983843046739757,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004973555927377856,
|
|
"loss": 6.217,
|
|
"mean_token_accuracy": 0.17282827198505402,
|
|
"num_tokens": 13118645.0,
|
|
"step": 5185
|
|
},
|
|
{
|
|
"entropy": 6.46846227645874,
|
|
"epoch": 0.5989613387189844,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004973492811228685,
|
|
"loss": 6.344,
|
|
"mean_token_accuracy": 0.16316265612840652,
|
|
"num_tokens": 13132250.0,
|
|
"step": 5190
|
|
},
|
|
{
|
|
"entropy": 6.466949081420898,
|
|
"epoch": 0.599538372763993,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004973429620293438,
|
|
"loss": 6.3362,
|
|
"mean_token_accuracy": 0.15950386077165604,
|
|
"num_tokens": 13145069.0,
|
|
"step": 5195
|
|
},
|
|
{
|
|
"entropy": 6.456646823883057,
|
|
"epoch": 0.6001154068090018,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004973366354574239,
|
|
"loss": 6.3034,
|
|
"mean_token_accuracy": 0.16648412495851517,
|
|
"num_tokens": 13158244.0,
|
|
"step": 5200
|
|
},
|
|
{
|
|
"entropy": 6.455355453491211,
|
|
"epoch": 0.6006924408540104,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004973303014073219,
|
|
"loss": 6.3623,
|
|
"mean_token_accuracy": 0.15627395808696748,
|
|
"num_tokens": 13171810.0,
|
|
"step": 5205
|
|
},
|
|
{
|
|
"entropy": 6.448964262008667,
|
|
"epoch": 0.601269474899019,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004973239598792504,
|
|
"loss": 6.1955,
|
|
"mean_token_accuracy": 0.1658018559217453,
|
|
"num_tokens": 13184448.0,
|
|
"step": 5210
|
|
},
|
|
{
|
|
"entropy": 6.448535013198852,
|
|
"epoch": 0.6018465089440277,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004973176108734232,
|
|
"loss": 6.3448,
|
|
"mean_token_accuracy": 0.15199785232543944,
|
|
"num_tokens": 13198350.0,
|
|
"step": 5215
|
|
},
|
|
{
|
|
"entropy": 6.465864801406861,
|
|
"epoch": 0.6024235429890363,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004973112543900535,
|
|
"loss": 6.2841,
|
|
"mean_token_accuracy": 0.16358843743801116,
|
|
"num_tokens": 13210660.0,
|
|
"step": 5220
|
|
},
|
|
{
|
|
"entropy": 6.406602478027343,
|
|
"epoch": 0.603000577034045,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004973048904293551,
|
|
"loss": 6.2393,
|
|
"mean_token_accuracy": 0.1710536241531372,
|
|
"num_tokens": 13222991.0,
|
|
"step": 5225
|
|
},
|
|
{
|
|
"entropy": 6.444959449768066,
|
|
"epoch": 0.6035776110790536,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004972985189915422,
|
|
"loss": 6.3254,
|
|
"mean_token_accuracy": 0.16002852469682693,
|
|
"num_tokens": 13237693.0,
|
|
"step": 5230
|
|
},
|
|
{
|
|
"entropy": 6.444726753234863,
|
|
"epoch": 0.6041546451240624,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.000497292140076829,
|
|
"loss": 6.3317,
|
|
"mean_token_accuracy": 0.1622207522392273,
|
|
"num_tokens": 13249843.0,
|
|
"step": 5235
|
|
},
|
|
{
|
|
"entropy": 6.439457941055298,
|
|
"epoch": 0.604731679169071,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004972857536854301,
|
|
"loss": 6.3119,
|
|
"mean_token_accuracy": 0.16525271087884902,
|
|
"num_tokens": 13262185.0,
|
|
"step": 5240
|
|
},
|
|
{
|
|
"entropy": 6.4337084770202635,
|
|
"epoch": 0.6053087132140796,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004972793598175603,
|
|
"loss": 6.3505,
|
|
"mean_token_accuracy": 0.15734633207321166,
|
|
"num_tokens": 13275344.0,
|
|
"step": 5245
|
|
},
|
|
{
|
|
"entropy": 6.473100423812866,
|
|
"epoch": 0.6058857472590883,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004972729584734347,
|
|
"loss": 6.2688,
|
|
"mean_token_accuracy": 0.15891817957162857,
|
|
"num_tokens": 13287741.0,
|
|
"step": 5250
|
|
},
|
|
{
|
|
"entropy": 6.470854473114014,
|
|
"epoch": 0.6064627813040969,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004972665496532685,
|
|
"loss": 6.2701,
|
|
"mean_token_accuracy": 0.16430861055850982,
|
|
"num_tokens": 13299918.0,
|
|
"step": 5255
|
|
},
|
|
{
|
|
"entropy": 6.368015956878662,
|
|
"epoch": 0.6070398153491056,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004972601333572774,
|
|
"loss": 6.2533,
|
|
"mean_token_accuracy": 0.15958417505025863,
|
|
"num_tokens": 13312765.0,
|
|
"step": 5260
|
|
},
|
|
{
|
|
"entropy": 6.462191009521485,
|
|
"epoch": 0.6076168493941142,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004972537095856769,
|
|
"loss": 6.2398,
|
|
"mean_token_accuracy": 0.16111138761043547,
|
|
"num_tokens": 13325324.0,
|
|
"step": 5265
|
|
},
|
|
{
|
|
"entropy": 6.485791730880737,
|
|
"epoch": 0.608193883439123,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004972472783386834,
|
|
"loss": 6.3451,
|
|
"mean_token_accuracy": 0.15810697078704833,
|
|
"num_tokens": 13337578.0,
|
|
"step": 5270
|
|
},
|
|
{
|
|
"entropy": 6.464807462692261,
|
|
"epoch": 0.6087709174841316,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004972408396165132,
|
|
"loss": 6.3088,
|
|
"mean_token_accuracy": 0.1609449043869972,
|
|
"num_tokens": 13349218.0,
|
|
"step": 5275
|
|
},
|
|
{
|
|
"entropy": 6.441641569137573,
|
|
"epoch": 0.6093479515291402,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004972343934193826,
|
|
"loss": 6.2705,
|
|
"mean_token_accuracy": 0.1591146320104599,
|
|
"num_tokens": 13362221.0,
|
|
"step": 5280
|
|
},
|
|
{
|
|
"entropy": 6.434703302383423,
|
|
"epoch": 0.6099249855741489,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004972279397475086,
|
|
"loss": 6.2645,
|
|
"mean_token_accuracy": 0.17187120169401168,
|
|
"num_tokens": 13374147.0,
|
|
"step": 5285
|
|
},
|
|
{
|
|
"entropy": 6.378955316543579,
|
|
"epoch": 0.6105020196191575,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004972214786011083,
|
|
"loss": 6.2197,
|
|
"mean_token_accuracy": 0.16266336888074875,
|
|
"num_tokens": 13386077.0,
|
|
"step": 5290
|
|
},
|
|
{
|
|
"entropy": 6.500459098815918,
|
|
"epoch": 0.6110790536641661,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.000497215009980399,
|
|
"loss": 6.297,
|
|
"mean_token_accuracy": 0.16877201348543167,
|
|
"num_tokens": 13398442.0,
|
|
"step": 5295
|
|
},
|
|
{
|
|
"entropy": 6.4331823825836185,
|
|
"epoch": 0.6116560877091748,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.000497208533885598,
|
|
"loss": 6.3029,
|
|
"mean_token_accuracy": 0.16564711034297944,
|
|
"num_tokens": 13411249.0,
|
|
"step": 5300
|
|
},
|
|
{
|
|
"entropy": 6.43955626487732,
|
|
"epoch": 0.6122331217541835,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004972020503169235,
|
|
"loss": 6.2878,
|
|
"mean_token_accuracy": 0.16612933129072188,
|
|
"num_tokens": 13424518.0,
|
|
"step": 5305
|
|
},
|
|
{
|
|
"entropy": 6.467305707931518,
|
|
"epoch": 0.6128101557991922,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004971955592745934,
|
|
"loss": 6.3069,
|
|
"mean_token_accuracy": 0.1545131728053093,
|
|
"num_tokens": 13438530.0,
|
|
"step": 5310
|
|
},
|
|
{
|
|
"entropy": 6.410894584655762,
|
|
"epoch": 0.6133871898442008,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.000497189060758826,
|
|
"loss": 6.2452,
|
|
"mean_token_accuracy": 0.16825231909751892,
|
|
"num_tokens": 13451154.0,
|
|
"step": 5315
|
|
},
|
|
{
|
|
"entropy": 6.409408855438232,
|
|
"epoch": 0.6139642238892095,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00049718255476984,
|
|
"loss": 6.2859,
|
|
"mean_token_accuracy": 0.16544894725084305,
|
|
"num_tokens": 13461938.0,
|
|
"step": 5320
|
|
},
|
|
{
|
|
"entropy": 6.377069711685181,
|
|
"epoch": 0.6145412579342181,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004971760413078539,
|
|
"loss": 6.2693,
|
|
"mean_token_accuracy": 0.1646272733807564,
|
|
"num_tokens": 13474423.0,
|
|
"step": 5325
|
|
},
|
|
{
|
|
"entropy": 6.502867031097412,
|
|
"epoch": 0.6151182919792267,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004971695203730872,
|
|
"loss": 6.2578,
|
|
"mean_token_accuracy": 0.17385480105876921,
|
|
"num_tokens": 13486882.0,
|
|
"step": 5330
|
|
},
|
|
{
|
|
"entropy": 6.399074077606201,
|
|
"epoch": 0.6156953260242354,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.000497162991965759,
|
|
"loss": 6.2091,
|
|
"mean_token_accuracy": 0.16568703651428224,
|
|
"num_tokens": 13499692.0,
|
|
"step": 5335
|
|
},
|
|
{
|
|
"entropy": 6.454089546203614,
|
|
"epoch": 0.6162723600692441,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004971564560860889,
|
|
"loss": 6.2921,
|
|
"mean_token_accuracy": 0.1587091013789177,
|
|
"num_tokens": 13512995.0,
|
|
"step": 5340
|
|
},
|
|
{
|
|
"entropy": 6.335466384887695,
|
|
"epoch": 0.6168493941142528,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004971499127342968,
|
|
"loss": 6.1969,
|
|
"mean_token_accuracy": 0.1680700197815895,
|
|
"num_tokens": 13525804.0,
|
|
"step": 5345
|
|
},
|
|
{
|
|
"entropy": 6.4052308082580565,
|
|
"epoch": 0.6174264281592614,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004971433619106027,
|
|
"loss": 6.3092,
|
|
"mean_token_accuracy": 0.16079850047826766,
|
|
"num_tokens": 13537807.0,
|
|
"step": 5350
|
|
},
|
|
{
|
|
"entropy": 6.485114002227784,
|
|
"epoch": 0.61800346220427,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.000497136803615227,
|
|
"loss": 6.3762,
|
|
"mean_token_accuracy": 0.1530951127409935,
|
|
"num_tokens": 13550765.0,
|
|
"step": 5355
|
|
},
|
|
{
|
|
"entropy": 6.4439774513244625,
|
|
"epoch": 0.6185804962492787,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004971302378483902,
|
|
"loss": 6.2689,
|
|
"mean_token_accuracy": 0.165410552918911,
|
|
"num_tokens": 13565084.0,
|
|
"step": 5360
|
|
},
|
|
{
|
|
"entropy": 6.476373338699341,
|
|
"epoch": 0.6191575302942873,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004971236646103132,
|
|
"loss": 6.2655,
|
|
"mean_token_accuracy": 0.16471700817346574,
|
|
"num_tokens": 13578851.0,
|
|
"step": 5365
|
|
},
|
|
{
|
|
"entropy": 6.406863832473755,
|
|
"epoch": 0.619734564339296,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004971170839012171,
|
|
"loss": 6.1939,
|
|
"mean_token_accuracy": 0.17038790881633759,
|
|
"num_tokens": 13589984.0,
|
|
"step": 5370
|
|
},
|
|
{
|
|
"entropy": 6.3514081001281735,
|
|
"epoch": 0.6203115983843047,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004971104957213233,
|
|
"loss": 6.2624,
|
|
"mean_token_accuracy": 0.16135939061641694,
|
|
"num_tokens": 13602899.0,
|
|
"step": 5375
|
|
},
|
|
{
|
|
"entropy": 6.490747451782227,
|
|
"epoch": 0.6208886324293134,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004971039000708531,
|
|
"loss": 6.418,
|
|
"mean_token_accuracy": 0.1528172329068184,
|
|
"num_tokens": 13617672.0,
|
|
"step": 5380
|
|
},
|
|
{
|
|
"entropy": 6.473091506958008,
|
|
"epoch": 0.621465666474322,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004970972969500286,
|
|
"loss": 6.2773,
|
|
"mean_token_accuracy": 0.1603806808590889,
|
|
"num_tokens": 13630029.0,
|
|
"step": 5385
|
|
},
|
|
{
|
|
"entropy": 6.401896953582764,
|
|
"epoch": 0.6220427005193306,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.000497090686359072,
|
|
"loss": 6.2523,
|
|
"mean_token_accuracy": 0.1648557275533676,
|
|
"num_tokens": 13643091.0,
|
|
"step": 5390
|
|
},
|
|
{
|
|
"entropy": 6.350330066680908,
|
|
"epoch": 0.6226197345643393,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004970840682982054,
|
|
"loss": 6.1293,
|
|
"mean_token_accuracy": 0.17030057311058044,
|
|
"num_tokens": 13654790.0,
|
|
"step": 5395
|
|
},
|
|
{
|
|
"entropy": 6.439556312561035,
|
|
"epoch": 0.6231967686093479,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004970774427676514,
|
|
"loss": 6.2464,
|
|
"mean_token_accuracy": 0.16800362020730972,
|
|
"num_tokens": 13667425.0,
|
|
"step": 5400
|
|
},
|
|
{
|
|
"entropy": 6.429106521606445,
|
|
"epoch": 0.6237738026543566,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.000497070809767633,
|
|
"loss": 6.3099,
|
|
"mean_token_accuracy": 0.16256403923034668,
|
|
"num_tokens": 13680199.0,
|
|
"step": 5405
|
|
},
|
|
{
|
|
"entropy": 6.471726417541504,
|
|
"epoch": 0.6243508366993653,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004970641692983731,
|
|
"loss": 6.3267,
|
|
"mean_token_accuracy": 0.16009956300258638,
|
|
"num_tokens": 13693613.0,
|
|
"step": 5410
|
|
},
|
|
{
|
|
"entropy": 6.32947187423706,
|
|
"epoch": 0.624927870744374,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004970575213600954,
|
|
"loss": 6.2661,
|
|
"mean_token_accuracy": 0.160757178068161,
|
|
"num_tokens": 13706809.0,
|
|
"step": 5415
|
|
},
|
|
{
|
|
"entropy": 6.40821270942688,
|
|
"epoch": 0.6255049047893826,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004970508659530231,
|
|
"loss": 6.2302,
|
|
"mean_token_accuracy": 0.16359151303768157,
|
|
"num_tokens": 13718976.0,
|
|
"step": 5420
|
|
},
|
|
{
|
|
"entropy": 6.440737009048462,
|
|
"epoch": 0.6260819388343912,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004970442030773802,
|
|
"loss": 6.2155,
|
|
"mean_token_accuracy": 0.1657729595899582,
|
|
"num_tokens": 13731037.0,
|
|
"step": 5425
|
|
},
|
|
{
|
|
"entropy": 6.358583593368531,
|
|
"epoch": 0.6266589728793999,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004970375327333909,
|
|
"loss": 6.2887,
|
|
"mean_token_accuracy": 0.16418557167053222,
|
|
"num_tokens": 13743816.0,
|
|
"step": 5430
|
|
},
|
|
{
|
|
"entropy": 6.3964362144470215,
|
|
"epoch": 0.6272360069244085,
|
|
"grad_norm": 0.75390625,
|
|
"learning_rate": 0.0004970308549212796,
|
|
"loss": 6.282,
|
|
"mean_token_accuracy": 0.16759266555309296,
|
|
"num_tokens": 13757165.0,
|
|
"step": 5435
|
|
},
|
|
{
|
|
"entropy": 6.450726795196533,
|
|
"epoch": 0.6278130409694171,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004970241696412705,
|
|
"loss": 6.2452,
|
|
"mean_token_accuracy": 0.17060438096523284,
|
|
"num_tokens": 13769982.0,
|
|
"step": 5440
|
|
},
|
|
{
|
|
"entropy": 6.434137296676636,
|
|
"epoch": 0.6283900750144259,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.000497017476893589,
|
|
"loss": 6.272,
|
|
"mean_token_accuracy": 0.16804485619068146,
|
|
"num_tokens": 13782922.0,
|
|
"step": 5445
|
|
},
|
|
{
|
|
"entropy": 6.38315167427063,
|
|
"epoch": 0.6289671090594345,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004970107766784598,
|
|
"loss": 6.2659,
|
|
"mean_token_accuracy": 0.1645989775657654,
|
|
"num_tokens": 13795683.0,
|
|
"step": 5450
|
|
},
|
|
{
|
|
"entropy": 6.467908000946045,
|
|
"epoch": 0.6295441431044432,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004970040689961084,
|
|
"loss": 6.3515,
|
|
"mean_token_accuracy": 0.16600358933210374,
|
|
"num_tokens": 13808332.0,
|
|
"step": 5455
|
|
},
|
|
{
|
|
"entropy": 6.430469560623169,
|
|
"epoch": 0.6301211771494518,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004969973538467605,
|
|
"loss": 6.3109,
|
|
"mean_token_accuracy": 0.16642144173383713,
|
|
"num_tokens": 13820949.0,
|
|
"step": 5460
|
|
},
|
|
{
|
|
"entropy": 6.349089574813843,
|
|
"epoch": 0.6306982111944605,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004969906312306419,
|
|
"loss": 6.2808,
|
|
"mean_token_accuracy": 0.16602863222360612,
|
|
"num_tokens": 13833623.0,
|
|
"step": 5465
|
|
},
|
|
{
|
|
"entropy": 6.47224531173706,
|
|
"epoch": 0.6312752452394691,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004969839011479786,
|
|
"loss": 6.2311,
|
|
"mean_token_accuracy": 0.17260048240423204,
|
|
"num_tokens": 13844368.0,
|
|
"step": 5470
|
|
},
|
|
{
|
|
"entropy": 6.46555233001709,
|
|
"epoch": 0.6318522792844777,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000496977163598997,
|
|
"loss": 6.2693,
|
|
"mean_token_accuracy": 0.16359723955392838,
|
|
"num_tokens": 13857261.0,
|
|
"step": 5475
|
|
},
|
|
{
|
|
"entropy": 6.241572618484497,
|
|
"epoch": 0.6324293133294865,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004969704185839239,
|
|
"loss": 6.1323,
|
|
"mean_token_accuracy": 0.16393650248646735,
|
|
"num_tokens": 13869438.0,
|
|
"step": 5480
|
|
},
|
|
{
|
|
"entropy": 6.454886245727539,
|
|
"epoch": 0.6330063473744951,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004969636661029859,
|
|
"loss": 6.3533,
|
|
"mean_token_accuracy": 0.15374770537018775,
|
|
"num_tokens": 13883353.0,
|
|
"step": 5485
|
|
},
|
|
{
|
|
"entropy": 6.484453201293945,
|
|
"epoch": 0.6335833814195038,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004969569061564103,
|
|
"loss": 6.2837,
|
|
"mean_token_accuracy": 0.168526728451252,
|
|
"num_tokens": 13896950.0,
|
|
"step": 5490
|
|
},
|
|
{
|
|
"entropy": 6.4666359424591064,
|
|
"epoch": 0.6341604154645124,
|
|
"grad_norm": 0.74609375,
|
|
"learning_rate": 0.0004969501387444245,
|
|
"loss": 6.2937,
|
|
"mean_token_accuracy": 0.16304062455892562,
|
|
"num_tokens": 13910447.0,
|
|
"step": 5495
|
|
},
|
|
{
|
|
"entropy": 6.418818473815918,
|
|
"epoch": 0.634737449509521,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004969433638672559,
|
|
"loss": 6.2849,
|
|
"mean_token_accuracy": 0.17183531671762467,
|
|
"num_tokens": 13922894.0,
|
|
"step": 5500
|
|
},
|
|
{
|
|
"entropy": 6.437852239608764,
|
|
"epoch": 0.6353144835545297,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004969365815251325,
|
|
"loss": 6.3015,
|
|
"mean_token_accuracy": 0.16050758361816406,
|
|
"num_tokens": 13936558.0,
|
|
"step": 5505
|
|
},
|
|
{
|
|
"entropy": 6.433607149124145,
|
|
"epoch": 0.6358915175995383,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004969297917182825,
|
|
"loss": 6.2436,
|
|
"mean_token_accuracy": 0.16257888972759246,
|
|
"num_tokens": 13949005.0,
|
|
"step": 5510
|
|
},
|
|
{
|
|
"entropy": 6.431810188293457,
|
|
"epoch": 0.6364685516445471,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004969229944469342,
|
|
"loss": 6.2808,
|
|
"mean_token_accuracy": 0.15686439871788024,
|
|
"num_tokens": 13962285.0,
|
|
"step": 5515
|
|
},
|
|
{
|
|
"entropy": 6.484597444534302,
|
|
"epoch": 0.6370455856895557,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004969161897113162,
|
|
"loss": 6.2797,
|
|
"mean_token_accuracy": 0.16125818341970444,
|
|
"num_tokens": 13976037.0,
|
|
"step": 5520
|
|
},
|
|
{
|
|
"entropy": 6.454035043716431,
|
|
"epoch": 0.6376226197345644,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004969093775116574,
|
|
"loss": 6.2329,
|
|
"mean_token_accuracy": 0.16799202859401702,
|
|
"num_tokens": 13989028.0,
|
|
"step": 5525
|
|
},
|
|
{
|
|
"entropy": 6.353673887252808,
|
|
"epoch": 0.638199653779573,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004969025578481869,
|
|
"loss": 6.2199,
|
|
"mean_token_accuracy": 0.16663924157619475,
|
|
"num_tokens": 14001814.0,
|
|
"step": 5530
|
|
},
|
|
{
|
|
"entropy": 6.490426683425904,
|
|
"epoch": 0.6387766878245816,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.000496895730721134,
|
|
"loss": 6.3185,
|
|
"mean_token_accuracy": 0.15284908413887024,
|
|
"num_tokens": 14014305.0,
|
|
"step": 5535
|
|
},
|
|
{
|
|
"entropy": 6.4198565006256105,
|
|
"epoch": 0.6393537218695903,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004968888961307286,
|
|
"loss": 6.1901,
|
|
"mean_token_accuracy": 0.17025423794984818,
|
|
"num_tokens": 14027475.0,
|
|
"step": 5540
|
|
},
|
|
{
|
|
"entropy": 6.402793550491333,
|
|
"epoch": 0.6399307559145989,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004968820540772003,
|
|
"loss": 6.2554,
|
|
"mean_token_accuracy": 0.16645244061946868,
|
|
"num_tokens": 14041031.0,
|
|
"step": 5545
|
|
},
|
|
{
|
|
"entropy": 6.391665887832642,
|
|
"epoch": 0.6405077899596077,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004968752045607794,
|
|
"loss": 6.212,
|
|
"mean_token_accuracy": 0.1631389558315277,
|
|
"num_tokens": 14054138.0,
|
|
"step": 5550
|
|
},
|
|
{
|
|
"entropy": 6.474399709701538,
|
|
"epoch": 0.6410848240046163,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004968683475816961,
|
|
"loss": 6.2339,
|
|
"mean_token_accuracy": 0.16551497131586074,
|
|
"num_tokens": 14066708.0,
|
|
"step": 5555
|
|
},
|
|
{
|
|
"entropy": 6.412665510177613,
|
|
"epoch": 0.641661858049625,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004968614831401811,
|
|
"loss": 6.319,
|
|
"mean_token_accuracy": 0.15504314005374908,
|
|
"num_tokens": 14080251.0,
|
|
"step": 5560
|
|
},
|
|
{
|
|
"entropy": 6.486737298965454,
|
|
"epoch": 0.6422388920946336,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004968546112364654,
|
|
"loss": 6.2944,
|
|
"mean_token_accuracy": 0.156815817207098,
|
|
"num_tokens": 14092622.0,
|
|
"step": 5565
|
|
},
|
|
{
|
|
"entropy": 6.457394075393677,
|
|
"epoch": 0.6428159261396422,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.00049684773187078,
|
|
"loss": 6.3607,
|
|
"mean_token_accuracy": 0.15759846270084382,
|
|
"num_tokens": 14107033.0,
|
|
"step": 5570
|
|
},
|
|
{
|
|
"entropy": 6.415627193450928,
|
|
"epoch": 0.6433929601846509,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004968408450433565,
|
|
"loss": 6.0985,
|
|
"mean_token_accuracy": 0.16721982806921004,
|
|
"num_tokens": 14119264.0,
|
|
"step": 5575
|
|
},
|
|
{
|
|
"entropy": 6.409555053710937,
|
|
"epoch": 0.6439699942296595,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004968339507544263,
|
|
"loss": 6.2658,
|
|
"mean_token_accuracy": 0.16522011756896973,
|
|
"num_tokens": 14131360.0,
|
|
"step": 5580
|
|
},
|
|
{
|
|
"entropy": 6.331378602981568,
|
|
"epoch": 0.6445470282746683,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004968270490042212,
|
|
"loss": 6.2574,
|
|
"mean_token_accuracy": 0.16861171871423722,
|
|
"num_tokens": 14143236.0,
|
|
"step": 5585
|
|
},
|
|
{
|
|
"entropy": 6.466990947723389,
|
|
"epoch": 0.6451240623196769,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004968201397929737,
|
|
"loss": 6.2703,
|
|
"mean_token_accuracy": 0.16277870833873748,
|
|
"num_tokens": 14156470.0,
|
|
"step": 5590
|
|
},
|
|
{
|
|
"entropy": 6.471270656585693,
|
|
"epoch": 0.6457010963646855,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004968132231209158,
|
|
"loss": 6.3218,
|
|
"mean_token_accuracy": 0.157097789645195,
|
|
"num_tokens": 14169359.0,
|
|
"step": 5595
|
|
},
|
|
{
|
|
"entropy": 6.400879669189453,
|
|
"epoch": 0.6462781304096942,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004968062989882803,
|
|
"loss": 6.3446,
|
|
"mean_token_accuracy": 0.15832698345184326,
|
|
"num_tokens": 14181980.0,
|
|
"step": 5600
|
|
},
|
|
{
|
|
"entropy": 6.470687961578369,
|
|
"epoch": 0.6468551644547028,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004967993673953003,
|
|
"loss": 6.2859,
|
|
"mean_token_accuracy": 0.16663094758987426,
|
|
"num_tokens": 14195456.0,
|
|
"step": 5605
|
|
},
|
|
{
|
|
"entropy": 6.371501111984253,
|
|
"epoch": 0.6474321984997115,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004967924283422087,
|
|
"loss": 6.1873,
|
|
"mean_token_accuracy": 0.1712810918688774,
|
|
"num_tokens": 14208269.0,
|
|
"step": 5610
|
|
},
|
|
{
|
|
"entropy": 6.420989894866944,
|
|
"epoch": 0.6480092325447201,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.000496785481829239,
|
|
"loss": 6.302,
|
|
"mean_token_accuracy": 0.16031478866934776,
|
|
"num_tokens": 14221474.0,
|
|
"step": 5615
|
|
},
|
|
{
|
|
"entropy": 6.473630666732788,
|
|
"epoch": 0.6485862665897288,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004967785278566245,
|
|
"loss": 6.2696,
|
|
"mean_token_accuracy": 0.16501279324293136,
|
|
"num_tokens": 14234185.0,
|
|
"step": 5620
|
|
},
|
|
{
|
|
"entropy": 6.3897919178009035,
|
|
"epoch": 0.6491633006347375,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004967715664245997,
|
|
"loss": 6.238,
|
|
"mean_token_accuracy": 0.1660897359251976,
|
|
"num_tokens": 14246853.0,
|
|
"step": 5625
|
|
},
|
|
{
|
|
"entropy": 6.398458003997803,
|
|
"epoch": 0.6497403346797461,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004967645975333983,
|
|
"loss": 6.3224,
|
|
"mean_token_accuracy": 0.16524122506380082,
|
|
"num_tokens": 14260047.0,
|
|
"step": 5630
|
|
},
|
|
{
|
|
"entropy": 6.4040333271026615,
|
|
"epoch": 0.6503173687247548,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004967576211832548,
|
|
"loss": 6.1934,
|
|
"mean_token_accuracy": 0.1748912051320076,
|
|
"num_tokens": 14273478.0,
|
|
"step": 5635
|
|
},
|
|
{
|
|
"entropy": 6.471810722351075,
|
|
"epoch": 0.6508944027697634,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004967506373744039,
|
|
"loss": 6.2874,
|
|
"mean_token_accuracy": 0.15878912657499314,
|
|
"num_tokens": 14286085.0,
|
|
"step": 5640
|
|
},
|
|
{
|
|
"entropy": 6.379119968414306,
|
|
"epoch": 0.651471436814772,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004967436461070805,
|
|
"loss": 6.2396,
|
|
"mean_token_accuracy": 0.1718211367726326,
|
|
"num_tokens": 14299472.0,
|
|
"step": 5645
|
|
},
|
|
{
|
|
"entropy": 6.398261547088623,
|
|
"epoch": 0.6520484708597807,
|
|
"grad_norm": 0.7421875,
|
|
"learning_rate": 0.0004967366473815196,
|
|
"loss": 6.2043,
|
|
"mean_token_accuracy": 0.16658677011728287,
|
|
"num_tokens": 14312624.0,
|
|
"step": 5650
|
|
},
|
|
{
|
|
"entropy": 6.396186256408692,
|
|
"epoch": 0.6526255049047894,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004967296411979568,
|
|
"loss": 6.1951,
|
|
"mean_token_accuracy": 0.17445577383041383,
|
|
"num_tokens": 14325418.0,
|
|
"step": 5655
|
|
},
|
|
{
|
|
"entropy": 6.32066240310669,
|
|
"epoch": 0.6532025389497981,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004967226275566275,
|
|
"loss": 6.239,
|
|
"mean_token_accuracy": 0.166211299598217,
|
|
"num_tokens": 14337360.0,
|
|
"step": 5660
|
|
},
|
|
{
|
|
"entropy": 6.44496717453003,
|
|
"epoch": 0.6537795729948067,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.000496715606457768,
|
|
"loss": 6.222,
|
|
"mean_token_accuracy": 0.16578047275543212,
|
|
"num_tokens": 14349119.0,
|
|
"step": 5665
|
|
},
|
|
{
|
|
"entropy": 6.448485326766968,
|
|
"epoch": 0.6543566070398154,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004967085779016142,
|
|
"loss": 6.2683,
|
|
"mean_token_accuracy": 0.17126621007919313,
|
|
"num_tokens": 14361760.0,
|
|
"step": 5670
|
|
},
|
|
{
|
|
"entropy": 6.330710077285767,
|
|
"epoch": 0.654933641084824,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004967015418884022,
|
|
"loss": 6.2345,
|
|
"mean_token_accuracy": 0.16232049018144606,
|
|
"num_tokens": 14374725.0,
|
|
"step": 5675
|
|
},
|
|
{
|
|
"entropy": 6.394761943817139,
|
|
"epoch": 0.6555106751298326,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004966944984183692,
|
|
"loss": 6.1996,
|
|
"mean_token_accuracy": 0.16768215894699096,
|
|
"num_tokens": 14387267.0,
|
|
"step": 5680
|
|
},
|
|
{
|
|
"entropy": 6.432275915145874,
|
|
"epoch": 0.6560877091748413,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004966874474917518,
|
|
"loss": 6.2603,
|
|
"mean_token_accuracy": 0.1640935719013214,
|
|
"num_tokens": 14400531.0,
|
|
"step": 5685
|
|
},
|
|
{
|
|
"entropy": 6.437908411026001,
|
|
"epoch": 0.65666474321985,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004966803891087873,
|
|
"loss": 6.2716,
|
|
"mean_token_accuracy": 0.15894663482904434,
|
|
"num_tokens": 14412507.0,
|
|
"step": 5690
|
|
},
|
|
{
|
|
"entropy": 6.434341669082642,
|
|
"epoch": 0.6572417772648587,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.000496673323269713,
|
|
"loss": 6.2589,
|
|
"mean_token_accuracy": 0.16347626149654387,
|
|
"num_tokens": 14424934.0,
|
|
"step": 5695
|
|
},
|
|
{
|
|
"entropy": 6.457496786117554,
|
|
"epoch": 0.6578188113098673,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004966662499747666,
|
|
"loss": 6.3639,
|
|
"mean_token_accuracy": 0.15038072019815446,
|
|
"num_tokens": 14438875.0,
|
|
"step": 5700
|
|
},
|
|
{
|
|
"entropy": 6.40140323638916,
|
|
"epoch": 0.6583958453548759,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004966591692241859,
|
|
"loss": 6.1693,
|
|
"mean_token_accuracy": 0.1677701637148857,
|
|
"num_tokens": 14451089.0,
|
|
"step": 5705
|
|
},
|
|
{
|
|
"entropy": 6.424305438995361,
|
|
"epoch": 0.6589728793998846,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004966520810182092,
|
|
"loss": 6.2889,
|
|
"mean_token_accuracy": 0.1674267664551735,
|
|
"num_tokens": 14463557.0,
|
|
"step": 5710
|
|
},
|
|
{
|
|
"entropy": 6.356392765045166,
|
|
"epoch": 0.6595499134448932,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004966449853570749,
|
|
"loss": 6.1922,
|
|
"mean_token_accuracy": 0.1630517616868019,
|
|
"num_tokens": 14475865.0,
|
|
"step": 5715
|
|
},
|
|
{
|
|
"entropy": 6.433615684509277,
|
|
"epoch": 0.6601269474899019,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004966378822410215,
|
|
"loss": 6.2999,
|
|
"mean_token_accuracy": 0.16027793437242507,
|
|
"num_tokens": 14487534.0,
|
|
"step": 5720
|
|
},
|
|
{
|
|
"entropy": 6.4160982131958,
|
|
"epoch": 0.6607039815349106,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004966307716702881,
|
|
"loss": 6.2466,
|
|
"mean_token_accuracy": 0.1649463638663292,
|
|
"num_tokens": 14500006.0,
|
|
"step": 5725
|
|
},
|
|
{
|
|
"entropy": 6.478086137771607,
|
|
"epoch": 0.6612810155799193,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004966236536451138,
|
|
"loss": 6.3556,
|
|
"mean_token_accuracy": 0.15748382806777955,
|
|
"num_tokens": 14512844.0,
|
|
"step": 5730
|
|
},
|
|
{
|
|
"entropy": 6.474676275253296,
|
|
"epoch": 0.6618580496249279,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000496616528165738,
|
|
"loss": 6.3073,
|
|
"mean_token_accuracy": 0.15954205095767976,
|
|
"num_tokens": 14525555.0,
|
|
"step": 5735
|
|
},
|
|
{
|
|
"entropy": 6.387700939178467,
|
|
"epoch": 0.6624350836699365,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004966093952324003,
|
|
"loss": 6.2908,
|
|
"mean_token_accuracy": 0.15595891401171685,
|
|
"num_tokens": 14537861.0,
|
|
"step": 5740
|
|
},
|
|
{
|
|
"entropy": 6.43832688331604,
|
|
"epoch": 0.6630121177149452,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004966022548453406,
|
|
"loss": 6.254,
|
|
"mean_token_accuracy": 0.16284551173448564,
|
|
"num_tokens": 14550116.0,
|
|
"step": 5745
|
|
},
|
|
{
|
|
"entropy": 6.444856739044189,
|
|
"epoch": 0.6635891517599538,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004965951070047993,
|
|
"loss": 6.2261,
|
|
"mean_token_accuracy": 0.16848643720149994,
|
|
"num_tokens": 14561841.0,
|
|
"step": 5750
|
|
},
|
|
{
|
|
"entropy": 6.411498022079468,
|
|
"epoch": 0.6641661858049625,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004965879517110166,
|
|
"loss": 6.2768,
|
|
"mean_token_accuracy": 0.16119781583547593,
|
|
"num_tokens": 14574889.0,
|
|
"step": 5755
|
|
},
|
|
{
|
|
"entropy": 6.336085510253906,
|
|
"epoch": 0.6647432198499712,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004965807889642333,
|
|
"loss": 6.2622,
|
|
"mean_token_accuracy": 0.16737145632505418,
|
|
"num_tokens": 14587032.0,
|
|
"step": 5760
|
|
},
|
|
{
|
|
"entropy": 6.412449836730957,
|
|
"epoch": 0.6653202538949798,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.00049657361876469,
|
|
"loss": 6.2303,
|
|
"mean_token_accuracy": 0.16632368713617324,
|
|
"num_tokens": 14599654.0,
|
|
"step": 5765
|
|
},
|
|
{
|
|
"entropy": 6.332269334793091,
|
|
"epoch": 0.6658972879399885,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004965664411126282,
|
|
"loss": 6.1506,
|
|
"mean_token_accuracy": 0.17118496000766753,
|
|
"num_tokens": 14611740.0,
|
|
"step": 5770
|
|
},
|
|
{
|
|
"entropy": 6.410775899887085,
|
|
"epoch": 0.6664743219849971,
|
|
"grad_norm": 0.70703125,
|
|
"learning_rate": 0.0004965592560082894,
|
|
"loss": 6.2481,
|
|
"mean_token_accuracy": 0.16527822315692903,
|
|
"num_tokens": 14625038.0,
|
|
"step": 5775
|
|
},
|
|
{
|
|
"entropy": 6.458446931838989,
|
|
"epoch": 0.6670513560300058,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004965520634519149,
|
|
"loss": 6.3134,
|
|
"mean_token_accuracy": 0.15978550016880036,
|
|
"num_tokens": 14638318.0,
|
|
"step": 5780
|
|
},
|
|
{
|
|
"entropy": 6.399044179916382,
|
|
"epoch": 0.6676283900750144,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004965448634437468,
|
|
"loss": 6.2815,
|
|
"mean_token_accuracy": 0.15635018050670624,
|
|
"num_tokens": 14651519.0,
|
|
"step": 5785
|
|
},
|
|
{
|
|
"entropy": 6.4846090316772464,
|
|
"epoch": 0.668205424120023,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004965376559840272,
|
|
"loss": 6.2521,
|
|
"mean_token_accuracy": 0.16233301162719727,
|
|
"num_tokens": 14662994.0,
|
|
"step": 5790
|
|
},
|
|
{
|
|
"entropy": 6.413419342041015,
|
|
"epoch": 0.6687824581650318,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004965304410729986,
|
|
"loss": 6.2138,
|
|
"mean_token_accuracy": 0.169295796751976,
|
|
"num_tokens": 14675488.0,
|
|
"step": 5795
|
|
},
|
|
{
|
|
"entropy": 6.341550636291504,
|
|
"epoch": 0.6693594922100404,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004965232187109037,
|
|
"loss": 6.1536,
|
|
"mean_token_accuracy": 0.1739507034420967,
|
|
"num_tokens": 14688512.0,
|
|
"step": 5800
|
|
},
|
|
{
|
|
"entropy": 6.425643396377564,
|
|
"epoch": 0.6699365262550491,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004965159888979854,
|
|
"loss": 6.2133,
|
|
"mean_token_accuracy": 0.1665024146437645,
|
|
"num_tokens": 14700740.0,
|
|
"step": 5805
|
|
},
|
|
{
|
|
"entropy": 6.373208665847779,
|
|
"epoch": 0.6705135603000577,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004965087516344869,
|
|
"loss": 6.2559,
|
|
"mean_token_accuracy": 0.16404303461313247,
|
|
"num_tokens": 14713769.0,
|
|
"step": 5810
|
|
},
|
|
{
|
|
"entropy": 6.37481460571289,
|
|
"epoch": 0.6710905943450663,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004965015069206515,
|
|
"loss": 6.1449,
|
|
"mean_token_accuracy": 0.17123078256845475,
|
|
"num_tokens": 14725710.0,
|
|
"step": 5815
|
|
},
|
|
{
|
|
"entropy": 6.382030820846557,
|
|
"epoch": 0.671667628390075,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.000496494254756723,
|
|
"loss": 6.1415,
|
|
"mean_token_accuracy": 0.17618792951107026,
|
|
"num_tokens": 14738504.0,
|
|
"step": 5820
|
|
},
|
|
{
|
|
"entropy": 6.413110065460205,
|
|
"epoch": 0.6722446624350836,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004964869951429451,
|
|
"loss": 6.2643,
|
|
"mean_token_accuracy": 0.16108937114477156,
|
|
"num_tokens": 14750344.0,
|
|
"step": 5825
|
|
},
|
|
{
|
|
"entropy": 6.433046150207519,
|
|
"epoch": 0.6728216964800924,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004964797280795622,
|
|
"loss": 6.3041,
|
|
"mean_token_accuracy": 0.16477554887533188,
|
|
"num_tokens": 14764316.0,
|
|
"step": 5830
|
|
},
|
|
{
|
|
"entropy": 6.371626186370849,
|
|
"epoch": 0.673398730525101,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004964724535668188,
|
|
"loss": 6.2249,
|
|
"mean_token_accuracy": 0.1627054274082184,
|
|
"num_tokens": 14776404.0,
|
|
"step": 5835
|
|
},
|
|
{
|
|
"entropy": 6.490979194641113,
|
|
"epoch": 0.6739757645701097,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004964651716049593,
|
|
"loss": 6.2583,
|
|
"mean_token_accuracy": 0.16423558443784714,
|
|
"num_tokens": 14788843.0,
|
|
"step": 5840
|
|
},
|
|
{
|
|
"entropy": 6.37471375465393,
|
|
"epoch": 0.6745527986151183,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004964578821942288,
|
|
"loss": 6.1898,
|
|
"mean_token_accuracy": 0.1714974358677864,
|
|
"num_tokens": 14802662.0,
|
|
"step": 5845
|
|
},
|
|
{
|
|
"entropy": 6.375233840942383,
|
|
"epoch": 0.6751298326601269,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004964505853348724,
|
|
"loss": 6.2682,
|
|
"mean_token_accuracy": 0.1575095996260643,
|
|
"num_tokens": 14814354.0,
|
|
"step": 5850
|
|
},
|
|
{
|
|
"entropy": 6.404491424560547,
|
|
"epoch": 0.6757068667051356,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004964432810271356,
|
|
"loss": 6.169,
|
|
"mean_token_accuracy": 0.17374546974897384,
|
|
"num_tokens": 14826404.0,
|
|
"step": 5855
|
|
},
|
|
{
|
|
"entropy": 6.397090053558349,
|
|
"epoch": 0.6762839007501442,
|
|
"grad_norm": 0.74609375,
|
|
"learning_rate": 0.0004964359692712641,
|
|
"loss": 6.2305,
|
|
"mean_token_accuracy": 0.16469545364379884,
|
|
"num_tokens": 14840046.0,
|
|
"step": 5860
|
|
},
|
|
{
|
|
"entropy": 6.359001588821411,
|
|
"epoch": 0.676860934795153,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004964286500675037,
|
|
"loss": 6.2521,
|
|
"mean_token_accuracy": 0.15627662539482118,
|
|
"num_tokens": 14853566.0,
|
|
"step": 5865
|
|
},
|
|
{
|
|
"entropy": 6.397631883621216,
|
|
"epoch": 0.6774379688401616,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004964213234161007,
|
|
"loss": 6.1925,
|
|
"mean_token_accuracy": 0.16885973513126373,
|
|
"num_tokens": 14866538.0,
|
|
"step": 5870
|
|
},
|
|
{
|
|
"entropy": 6.3361509323120115,
|
|
"epoch": 0.6780150028851702,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004964139893173014,
|
|
"loss": 6.1521,
|
|
"mean_token_accuracy": 0.17438876032829284,
|
|
"num_tokens": 14879237.0,
|
|
"step": 5875
|
|
},
|
|
{
|
|
"entropy": 6.442409992218018,
|
|
"epoch": 0.6785920369301789,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004964066477713525,
|
|
"loss": 6.2748,
|
|
"mean_token_accuracy": 0.1616318017244339,
|
|
"num_tokens": 14891295.0,
|
|
"step": 5880
|
|
},
|
|
{
|
|
"entropy": 6.412937259674072,
|
|
"epoch": 0.6791690709751875,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004963992987785011,
|
|
"loss": 6.2673,
|
|
"mean_token_accuracy": 0.16440023183822633,
|
|
"num_tokens": 14902927.0,
|
|
"step": 5885
|
|
},
|
|
{
|
|
"entropy": 6.350733757019043,
|
|
"epoch": 0.6797461050201962,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004963919423389942,
|
|
"loss": 6.2349,
|
|
"mean_token_accuracy": 0.16148411780595778,
|
|
"num_tokens": 14915203.0,
|
|
"step": 5890
|
|
},
|
|
{
|
|
"entropy": 6.369336748123169,
|
|
"epoch": 0.6803231390652048,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004963845784530794,
|
|
"loss": 6.099,
|
|
"mean_token_accuracy": 0.17276938557624816,
|
|
"num_tokens": 14927428.0,
|
|
"step": 5895
|
|
},
|
|
{
|
|
"entropy": 6.338372755050659,
|
|
"epoch": 0.6809001731102136,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.000496377207121004,
|
|
"loss": 6.2514,
|
|
"mean_token_accuracy": 0.16943022161722182,
|
|
"num_tokens": 14939979.0,
|
|
"step": 5900
|
|
},
|
|
{
|
|
"entropy": 6.460256767272949,
|
|
"epoch": 0.6814772071552222,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004963698283430164,
|
|
"loss": 6.2375,
|
|
"mean_token_accuracy": 0.1650419846177101,
|
|
"num_tokens": 14952292.0,
|
|
"step": 5905
|
|
},
|
|
{
|
|
"entropy": 6.392317628860473,
|
|
"epoch": 0.6820542412002308,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004963624421193646,
|
|
"loss": 6.2536,
|
|
"mean_token_accuracy": 0.15970679968595505,
|
|
"num_tokens": 14964942.0,
|
|
"step": 5910
|
|
},
|
|
{
|
|
"entropy": 6.431348752975464,
|
|
"epoch": 0.6826312752452395,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000496355048450297,
|
|
"loss": 6.3675,
|
|
"mean_token_accuracy": 0.15923905968666077,
|
|
"num_tokens": 14979196.0,
|
|
"step": 5915
|
|
},
|
|
{
|
|
"entropy": 6.4473936557769775,
|
|
"epoch": 0.6832083092902481,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004963476473360623,
|
|
"loss": 6.2204,
|
|
"mean_token_accuracy": 0.16636578887701034,
|
|
"num_tokens": 14991162.0,
|
|
"step": 5920
|
|
},
|
|
{
|
|
"entropy": 6.332076978683472,
|
|
"epoch": 0.6837853433352568,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004963402387769094,
|
|
"loss": 6.2417,
|
|
"mean_token_accuracy": 0.16846334040164948,
|
|
"num_tokens": 15003207.0,
|
|
"step": 5925
|
|
},
|
|
{
|
|
"entropy": 6.35644760131836,
|
|
"epoch": 0.6843623773802654,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004963328227730876,
|
|
"loss": 6.2604,
|
|
"mean_token_accuracy": 0.1596489131450653,
|
|
"num_tokens": 15016633.0,
|
|
"step": 5930
|
|
},
|
|
{
|
|
"entropy": 6.392962121963501,
|
|
"epoch": 0.684939411425274,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004963253993248461,
|
|
"loss": 6.198,
|
|
"mean_token_accuracy": 0.17046815901994705,
|
|
"num_tokens": 15029256.0,
|
|
"step": 5935
|
|
},
|
|
{
|
|
"entropy": 6.344196081161499,
|
|
"epoch": 0.6855164454702828,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004963179684324349,
|
|
"loss": 6.1649,
|
|
"mean_token_accuracy": 0.17169316112995148,
|
|
"num_tokens": 15041162.0,
|
|
"step": 5940
|
|
},
|
|
{
|
|
"entropy": 6.346894645690918,
|
|
"epoch": 0.6860934795152914,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004963105300961036,
|
|
"loss": 6.2151,
|
|
"mean_token_accuracy": 0.17179548889398574,
|
|
"num_tokens": 15054122.0,
|
|
"step": 5945
|
|
},
|
|
{
|
|
"entropy": 6.368085193634033,
|
|
"epoch": 0.6866705135603001,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004963030843161026,
|
|
"loss": 6.2176,
|
|
"mean_token_accuracy": 0.1642700269818306,
|
|
"num_tokens": 15066123.0,
|
|
"step": 5950
|
|
},
|
|
{
|
|
"entropy": 6.261136484146118,
|
|
"epoch": 0.6872475476053087,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004962956310926823,
|
|
"loss": 6.1427,
|
|
"mean_token_accuracy": 0.1735681861639023,
|
|
"num_tokens": 15078192.0,
|
|
"step": 5955
|
|
},
|
|
{
|
|
"entropy": 6.413783311843872,
|
|
"epoch": 0.6878245816503173,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004962881704260934,
|
|
"loss": 6.1818,
|
|
"mean_token_accuracy": 0.1730615571141243,
|
|
"num_tokens": 15090227.0,
|
|
"step": 5960
|
|
},
|
|
{
|
|
"entropy": 6.358871221542358,
|
|
"epoch": 0.688401615695326,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004962807023165868,
|
|
"loss": 6.3066,
|
|
"mean_token_accuracy": 0.1696085214614868,
|
|
"num_tokens": 15104093.0,
|
|
"step": 5965
|
|
},
|
|
{
|
|
"entropy": 6.3496081829071045,
|
|
"epoch": 0.6889786497403346,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.0004962732267644138,
|
|
"loss": 6.2006,
|
|
"mean_token_accuracy": 0.16877583116292955,
|
|
"num_tokens": 15118064.0,
|
|
"step": 5970
|
|
},
|
|
{
|
|
"entropy": 6.392092323303222,
|
|
"epoch": 0.6895556837853434,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004962657437698254,
|
|
"loss": 6.0972,
|
|
"mean_token_accuracy": 0.17405418753623964,
|
|
"num_tokens": 15131686.0,
|
|
"step": 5975
|
|
},
|
|
{
|
|
"entropy": 6.378844308853149,
|
|
"epoch": 0.690132717830352,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004962582533330739,
|
|
"loss": 6.2949,
|
|
"mean_token_accuracy": 0.15710055381059645,
|
|
"num_tokens": 15143920.0,
|
|
"step": 5980
|
|
},
|
|
{
|
|
"entropy": 6.44266266822815,
|
|
"epoch": 0.6907097518753607,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004962507554544109,
|
|
"loss": 6.2552,
|
|
"mean_token_accuracy": 0.16559473276138306,
|
|
"num_tokens": 15156989.0,
|
|
"step": 5985
|
|
},
|
|
{
|
|
"entropy": 6.503173542022705,
|
|
"epoch": 0.6912867859203693,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004962432501340886,
|
|
"loss": 6.3219,
|
|
"mean_token_accuracy": 0.15267299860715866,
|
|
"num_tokens": 15169068.0,
|
|
"step": 5990
|
|
},
|
|
{
|
|
"entropy": 6.377065753936767,
|
|
"epoch": 0.6918638199653779,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004962357373723596,
|
|
"loss": 6.2871,
|
|
"mean_token_accuracy": 0.16362386345863342,
|
|
"num_tokens": 15182081.0,
|
|
"step": 5995
|
|
},
|
|
{
|
|
"entropy": 6.492167615890503,
|
|
"epoch": 0.6924408540103866,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004962282171694763,
|
|
"loss": 6.2605,
|
|
"mean_token_accuracy": 0.16491686552762985,
|
|
"num_tokens": 15194474.0,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"epoch": 0.6924408540103866,
|
|
"eval_entropy": 6.244893937006504,
|
|
"eval_loss": 6.277975559234619,
|
|
"eval_mean_token_accuracy": 0.16690639868687931,
|
|
"eval_num_tokens": 15194474.0,
|
|
"eval_runtime": 17.4205,
|
|
"eval_samples_per_second": 1615.111,
|
|
"eval_steps_per_second": 201.889,
|
|
"step": 6000
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 86650,
|
|
"num_input_tokens_seen": 0,
|
|
"num_train_epochs": 10,
|
|
"save_steps": 3000,
|
|
"stateful_callbacks": {
|
|
"TrainerControl": {
|
|
"args": {
|
|
"should_epoch_stop": false,
|
|
"should_evaluate": false,
|
|
"should_log": false,
|
|
"should_save": true,
|
|
"should_training_stop": false
|
|
},
|
|
"attributes": {}
|
|
}
|
|
},
|
|
"total_flos": 3316327490027520.0,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|