6046 lines
164 KiB
JSON
6046 lines
164 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.3462204270051933,
|
|
"eval_steps": 3000,
|
|
"global_step": 3000,
|
|
"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
|
|
}
|
|
],
|
|
"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": 1651257798819840.0,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|