4628d1d8eb
Model: fpadovani/nld-latn-100mb-after-ppt-Dp-100mb-ckpt500_seed3407 Source: Original Platform
72167 lines
1.9 MiB
72167 lines
1.9 MiB
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 3.265602322206096,
|
|
"eval_steps": 3000,
|
|
"global_step": 36000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 7.095729112625122,
|
|
"epoch": 0.00045355587808418,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 2e-06,
|
|
"loss": 6.7265,
|
|
"mean_token_accuracy": 0.10285235941410065,
|
|
"num_tokens": 10827.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 7.09377703666687,
|
|
"epoch": 0.00090711175616836,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 6.7538,
|
|
"mean_token_accuracy": 0.10200931578874588,
|
|
"num_tokens": 21025.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 7.057293462753296,
|
|
"epoch": 0.00136066763425254,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 7e-06,
|
|
"loss": 6.7002,
|
|
"mean_token_accuracy": 0.1035932444036007,
|
|
"num_tokens": 31678.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 6.979911279678345,
|
|
"epoch": 0.00181422351233672,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 6.6235,
|
|
"mean_token_accuracy": 0.11412417292594909,
|
|
"num_tokens": 41025.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 7.066703462600708,
|
|
"epoch": 0.0022677793904208998,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 6.7259,
|
|
"mean_token_accuracy": 0.10575319603085517,
|
|
"num_tokens": 51270.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 6.882899045944214,
|
|
"epoch": 0.00272133526850508,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 6.6281,
|
|
"mean_token_accuracy": 0.09819270819425582,
|
|
"num_tokens": 62142.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 6.884727811813354,
|
|
"epoch": 0.00317489114658926,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 6.7714,
|
|
"mean_token_accuracy": 0.10656015574932098,
|
|
"num_tokens": 72709.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 6.849240255355835,
|
|
"epoch": 0.00362844702467344,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 6.5919,
|
|
"mean_token_accuracy": 0.11315458789467811,
|
|
"num_tokens": 82313.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 6.859521293640137,
|
|
"epoch": 0.00408200290275762,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 6.6149,
|
|
"mean_token_accuracy": 0.11464895755052566,
|
|
"num_tokens": 92450.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 6.880142593383789,
|
|
"epoch": 0.0045355587808417995,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 6.6249,
|
|
"mean_token_accuracy": 0.10058464556932449,
|
|
"num_tokens": 103978.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 6.875945663452148,
|
|
"epoch": 0.00498911465892598,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 6.5967,
|
|
"mean_token_accuracy": 0.11548029407858848,
|
|
"num_tokens": 114134.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 6.909515619277954,
|
|
"epoch": 0.00544267053701016,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 6.803,
|
|
"mean_token_accuracy": 0.10447383597493172,
|
|
"num_tokens": 125037.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 6.890460014343262,
|
|
"epoch": 0.00589622641509434,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 6.6158,
|
|
"mean_token_accuracy": 0.1143025241792202,
|
|
"num_tokens": 134721.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 6.870286560058593,
|
|
"epoch": 0.00634978229317852,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 6.5605,
|
|
"mean_token_accuracy": 0.11281021013855934,
|
|
"num_tokens": 144448.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 6.873729610443116,
|
|
"epoch": 0.006803338171262699,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 6.6081,
|
|
"mean_token_accuracy": 0.11354126334190369,
|
|
"num_tokens": 154343.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 6.87849268913269,
|
|
"epoch": 0.00725689404934688,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 6.667,
|
|
"mean_token_accuracy": 0.11082403212785721,
|
|
"num_tokens": 165650.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 7.006619787216186,
|
|
"epoch": 0.007710449927431059,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 6.8666,
|
|
"mean_token_accuracy": 0.10090332627296447,
|
|
"num_tokens": 177098.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 6.911909055709839,
|
|
"epoch": 0.00816400580551524,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 6.5864,
|
|
"mean_token_accuracy": 0.11723631173372269,
|
|
"num_tokens": 187903.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 6.861669921875,
|
|
"epoch": 0.00861756168359942,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 6.6282,
|
|
"mean_token_accuracy": 0.11214306727051734,
|
|
"num_tokens": 198077.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 6.918485116958618,
|
|
"epoch": 0.009071117561683599,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 6.7492,
|
|
"mean_token_accuracy": 0.10802269652485848,
|
|
"num_tokens": 208641.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 6.897343158721924,
|
|
"epoch": 0.009524673439767779,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 6.6283,
|
|
"mean_token_accuracy": 0.11756790578365325,
|
|
"num_tokens": 218398.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 6.847284555435181,
|
|
"epoch": 0.00997822931785196,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 6.5401,
|
|
"mean_token_accuracy": 0.11274854093790054,
|
|
"num_tokens": 229059.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 6.852484703063965,
|
|
"epoch": 0.01043178519593614,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 6.6082,
|
|
"mean_token_accuracy": 0.10856100469827652,
|
|
"num_tokens": 239775.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 6.885813903808594,
|
|
"epoch": 0.01088534107402032,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 6.5006,
|
|
"mean_token_accuracy": 0.11381678581237793,
|
|
"num_tokens": 249954.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 6.860991525650024,
|
|
"epoch": 0.011338896952104499,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 6.6168,
|
|
"mean_token_accuracy": 0.10877051502466202,
|
|
"num_tokens": 260056.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 6.84809103012085,
|
|
"epoch": 0.01179245283018868,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 6.5904,
|
|
"mean_token_accuracy": 0.11548284813761711,
|
|
"num_tokens": 269904.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 6.958385229110718,
|
|
"epoch": 0.01224600870827286,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 6.5946,
|
|
"mean_token_accuracy": 0.11288051903247834,
|
|
"num_tokens": 280900.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 6.819544267654419,
|
|
"epoch": 0.01269956458635704,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 6.634,
|
|
"mean_token_accuracy": 0.11247359365224838,
|
|
"num_tokens": 290844.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 6.850368165969849,
|
|
"epoch": 0.013153120464441219,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 6.611,
|
|
"mean_token_accuracy": 0.11267527937889099,
|
|
"num_tokens": 301345.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 6.930296087265015,
|
|
"epoch": 0.013606676342525399,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 6.6225,
|
|
"mean_token_accuracy": 0.11140098199248313,
|
|
"num_tokens": 312681.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 6.830138874053955,
|
|
"epoch": 0.01406023222060958,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 6.571,
|
|
"mean_token_accuracy": 0.11029604226350784,
|
|
"num_tokens": 323492.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 6.854236030578614,
|
|
"epoch": 0.01451378809869376,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 6.6352,
|
|
"mean_token_accuracy": 0.10969627797603607,
|
|
"num_tokens": 334521.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 6.917273998260498,
|
|
"epoch": 0.014967343976777939,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 6.6505,
|
|
"mean_token_accuracy": 0.11680250763893127,
|
|
"num_tokens": 345468.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 6.939955139160157,
|
|
"epoch": 0.015420899854862119,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 6.5748,
|
|
"mean_token_accuracy": 0.11744663268327712,
|
|
"num_tokens": 355911.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 6.8326245784759525,
|
|
"epoch": 0.0158744557329463,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 6.5974,
|
|
"mean_token_accuracy": 0.11093726232647896,
|
|
"num_tokens": 367537.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 7.006328916549682,
|
|
"epoch": 0.01632801161103048,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 6.785,
|
|
"mean_token_accuracy": 0.10842694193124772,
|
|
"num_tokens": 377918.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 6.904155826568603,
|
|
"epoch": 0.01678156748911466,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 6.6467,
|
|
"mean_token_accuracy": 0.11190110594034194,
|
|
"num_tokens": 388461.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 6.9462827205657955,
|
|
"epoch": 0.01723512336719884,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 6.624,
|
|
"mean_token_accuracy": 0.11254355385899543,
|
|
"num_tokens": 399771.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 6.802505254745483,
|
|
"epoch": 0.01768867924528302,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 6.5542,
|
|
"mean_token_accuracy": 0.11513888537883758,
|
|
"num_tokens": 410254.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 6.881962490081787,
|
|
"epoch": 0.018142235123367198,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 6.5364,
|
|
"mean_token_accuracy": 0.10974982380867004,
|
|
"num_tokens": 419792.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 6.786790180206299,
|
|
"epoch": 0.018595791001451378,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000102,
|
|
"loss": 6.5911,
|
|
"mean_token_accuracy": 0.11597937643527985,
|
|
"num_tokens": 429264.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 6.895502185821533,
|
|
"epoch": 0.019049346879535557,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 6.5448,
|
|
"mean_token_accuracy": 0.11790847852826118,
|
|
"num_tokens": 439624.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 6.8149701118469235,
|
|
"epoch": 0.01950290275761974,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000107,
|
|
"loss": 6.5652,
|
|
"mean_token_accuracy": 0.11152517050504684,
|
|
"num_tokens": 449556.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 6.898656415939331,
|
|
"epoch": 0.01995645863570392,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 6.6111,
|
|
"mean_token_accuracy": 0.1134468026459217,
|
|
"num_tokens": 460243.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 6.8338030815124515,
|
|
"epoch": 0.0204100145137881,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000112,
|
|
"loss": 6.626,
|
|
"mean_token_accuracy": 0.11214038878679275,
|
|
"num_tokens": 469767.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 6.919766855239868,
|
|
"epoch": 0.02086357039187228,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 6.5885,
|
|
"mean_token_accuracy": 0.11247648671269417,
|
|
"num_tokens": 480329.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 6.827954387664795,
|
|
"epoch": 0.02131712626995646,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 6.541,
|
|
"mean_token_accuracy": 0.11013604179024697,
|
|
"num_tokens": 490096.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 6.920001554489136,
|
|
"epoch": 0.02177068214804064,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 6.5329,
|
|
"mean_token_accuracy": 0.11023009046912194,
|
|
"num_tokens": 501231.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 6.743205976486206,
|
|
"epoch": 0.022224238026124818,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000122,
|
|
"loss": 6.5103,
|
|
"mean_token_accuracy": 0.12003011107444764,
|
|
"num_tokens": 510722.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 6.816294765472412,
|
|
"epoch": 0.022677793904208998,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 6.575,
|
|
"mean_token_accuracy": 0.11273853480815887,
|
|
"num_tokens": 521452.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 6.891448831558227,
|
|
"epoch": 0.023131349782293177,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000127,
|
|
"loss": 6.5903,
|
|
"mean_token_accuracy": 0.11311487331986428,
|
|
"num_tokens": 532397.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 6.873995685577393,
|
|
"epoch": 0.02358490566037736,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 6.561,
|
|
"mean_token_accuracy": 0.11095410361886024,
|
|
"num_tokens": 542271.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 6.863357591629028,
|
|
"epoch": 0.02403846153846154,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000132,
|
|
"loss": 6.5836,
|
|
"mean_token_accuracy": 0.114754718542099,
|
|
"num_tokens": 552411.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 6.8279015064239506,
|
|
"epoch": 0.02449201741654572,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 6.5534,
|
|
"mean_token_accuracy": 0.11625841185450554,
|
|
"num_tokens": 561518.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 6.916412401199341,
|
|
"epoch": 0.0249455732946299,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 6.6294,
|
|
"mean_token_accuracy": 0.11257987022399903,
|
|
"num_tokens": 571361.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 6.762298631668091,
|
|
"epoch": 0.02539912917271408,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 6.5132,
|
|
"mean_token_accuracy": 0.11271893158555031,
|
|
"num_tokens": 580926.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 6.915192937850952,
|
|
"epoch": 0.025852685050798258,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 6.6046,
|
|
"mean_token_accuracy": 0.10786937177181244,
|
|
"num_tokens": 592282.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 6.926600074768066,
|
|
"epoch": 0.026306240928882438,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 6.6318,
|
|
"mean_token_accuracy": 0.1095262661576271,
|
|
"num_tokens": 602767.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 6.829335880279541,
|
|
"epoch": 0.026759796806966617,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000147,
|
|
"loss": 6.5364,
|
|
"mean_token_accuracy": 0.1123177632689476,
|
|
"num_tokens": 612763.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 6.844592142105102,
|
|
"epoch": 0.027213352685050797,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 6.5237,
|
|
"mean_token_accuracy": 0.11495825499296189,
|
|
"num_tokens": 622796.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 6.8091404914855955,
|
|
"epoch": 0.027666908563134977,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000152,
|
|
"loss": 6.4945,
|
|
"mean_token_accuracy": 0.11651193872094154,
|
|
"num_tokens": 633136.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 6.694456291198731,
|
|
"epoch": 0.02812046444121916,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 6.5303,
|
|
"mean_token_accuracy": 0.11837984547019005,
|
|
"num_tokens": 643347.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 6.884937953948975,
|
|
"epoch": 0.02857402031930334,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000157,
|
|
"loss": 6.5096,
|
|
"mean_token_accuracy": 0.12059485390782357,
|
|
"num_tokens": 653096.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 6.679642105102539,
|
|
"epoch": 0.02902757619738752,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 6.5502,
|
|
"mean_token_accuracy": 0.11287975832819938,
|
|
"num_tokens": 663557.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 6.917266988754273,
|
|
"epoch": 0.0294811320754717,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000162,
|
|
"loss": 6.6358,
|
|
"mean_token_accuracy": 0.1109463818371296,
|
|
"num_tokens": 674395.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 6.825232934951782,
|
|
"epoch": 0.029934687953555878,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 6.5606,
|
|
"mean_token_accuracy": 0.11592193096876144,
|
|
"num_tokens": 684776.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 6.785255765914917,
|
|
"epoch": 0.030388243831640058,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 6.5179,
|
|
"mean_token_accuracy": 0.11499937400221824,
|
|
"num_tokens": 694886.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 6.853105878829956,
|
|
"epoch": 0.030841799709724237,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 6.5986,
|
|
"mean_token_accuracy": 0.10862654820084572,
|
|
"num_tokens": 705426.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 6.87786340713501,
|
|
"epoch": 0.03129535558780842,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 6.6063,
|
|
"mean_token_accuracy": 0.11100632250308991,
|
|
"num_tokens": 716271.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 6.8458168506622314,
|
|
"epoch": 0.0317489114658926,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 6.5824,
|
|
"mean_token_accuracy": 0.11013020351529121,
|
|
"num_tokens": 726875.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 6.771889114379883,
|
|
"epoch": 0.032202467343976776,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000177,
|
|
"loss": 6.5288,
|
|
"mean_token_accuracy": 0.11027872115373612,
|
|
"num_tokens": 737825.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 6.777115345001221,
|
|
"epoch": 0.03265602322206096,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 6.4789,
|
|
"mean_token_accuracy": 0.11788042932748795,
|
|
"num_tokens": 747424.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 6.832462644577026,
|
|
"epoch": 0.033109579100145135,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000182,
|
|
"loss": 6.5126,
|
|
"mean_token_accuracy": 0.11428287327289581,
|
|
"num_tokens": 757649.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 6.798842334747315,
|
|
"epoch": 0.03356313497822932,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 6.53,
|
|
"mean_token_accuracy": 0.11638613939285278,
|
|
"num_tokens": 768556.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 6.701859331130981,
|
|
"epoch": 0.034016690856313495,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000187,
|
|
"loss": 6.5256,
|
|
"mean_token_accuracy": 0.11531673222780228,
|
|
"num_tokens": 778331.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 6.794470977783203,
|
|
"epoch": 0.03447024673439768,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 6.5285,
|
|
"mean_token_accuracy": 0.11249540448188781,
|
|
"num_tokens": 788065.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 6.837066221237182,
|
|
"epoch": 0.03492380261248186,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000192,
|
|
"loss": 6.5856,
|
|
"mean_token_accuracy": 0.11070910617709159,
|
|
"num_tokens": 798912.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 6.788638496398926,
|
|
"epoch": 0.03537735849056604,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 6.5211,
|
|
"mean_token_accuracy": 0.12141896188259124,
|
|
"num_tokens": 809580.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 6.805673980712891,
|
|
"epoch": 0.03583091436865022,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 6.5986,
|
|
"mean_token_accuracy": 0.11551168486475945,
|
|
"num_tokens": 820207.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 6.665769624710083,
|
|
"epoch": 0.036284470246734396,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 6.4231,
|
|
"mean_token_accuracy": 0.11134176030755043,
|
|
"num_tokens": 831038.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 6.818566799163818,
|
|
"epoch": 0.03673802612481858,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000202,
|
|
"loss": 6.5358,
|
|
"mean_token_accuracy": 0.11346253231167794,
|
|
"num_tokens": 842144.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 6.820947122573853,
|
|
"epoch": 0.037191582002902755,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 6.5339,
|
|
"mean_token_accuracy": 0.11876299902796746,
|
|
"num_tokens": 851315.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 6.729552555084228,
|
|
"epoch": 0.03764513788098694,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000207,
|
|
"loss": 6.563,
|
|
"mean_token_accuracy": 0.1145752988755703,
|
|
"num_tokens": 861233.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 6.747600364685058,
|
|
"epoch": 0.038098693759071114,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 6.5175,
|
|
"mean_token_accuracy": 0.11273587495088577,
|
|
"num_tokens": 871131.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 6.765731859207153,
|
|
"epoch": 0.0385522496371553,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000212,
|
|
"loss": 6.5096,
|
|
"mean_token_accuracy": 0.11347832456231118,
|
|
"num_tokens": 882195.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 6.763120365142822,
|
|
"epoch": 0.03900580551523948,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 6.493,
|
|
"mean_token_accuracy": 0.11830192133784294,
|
|
"num_tokens": 891806.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 6.7991108894348145,
|
|
"epoch": 0.03945936139332366,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 6.5534,
|
|
"mean_token_accuracy": 0.10942765697836876,
|
|
"num_tokens": 901350.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 6.767538928985596,
|
|
"epoch": 0.03991291727140784,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 6.461,
|
|
"mean_token_accuracy": 0.11672212779521943,
|
|
"num_tokens": 912061.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 6.663478183746338,
|
|
"epoch": 0.040366473149492016,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000222,
|
|
"loss": 6.4298,
|
|
"mean_token_accuracy": 0.1151677392423153,
|
|
"num_tokens": 922220.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 6.714645051956177,
|
|
"epoch": 0.0408200290275762,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 6.4781,
|
|
"mean_token_accuracy": 0.11699502617120743,
|
|
"num_tokens": 932319.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 6.740534543991089,
|
|
"epoch": 0.041273584905660375,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 6.4927,
|
|
"mean_token_accuracy": 0.1162272535264492,
|
|
"num_tokens": 943254.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 6.749291038513183,
|
|
"epoch": 0.04172714078374456,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 6.5346,
|
|
"mean_token_accuracy": 0.10895546674728393,
|
|
"num_tokens": 953921.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 6.654842042922974,
|
|
"epoch": 0.042180696661828734,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 6.4555,
|
|
"mean_token_accuracy": 0.11954837366938591,
|
|
"num_tokens": 963832.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 6.707518577575684,
|
|
"epoch": 0.04263425253991292,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 6.5509,
|
|
"mean_token_accuracy": 0.1089623972773552,
|
|
"num_tokens": 974066.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 6.776539993286133,
|
|
"epoch": 0.0430878084179971,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000237,
|
|
"loss": 6.5395,
|
|
"mean_token_accuracy": 0.11641593873500825,
|
|
"num_tokens": 984402.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 6.677361297607422,
|
|
"epoch": 0.04354136429608128,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 6.4249,
|
|
"mean_token_accuracy": 0.11875243708491326,
|
|
"num_tokens": 993555.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 6.7442159175872805,
|
|
"epoch": 0.04399492017416546,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000242,
|
|
"loss": 6.4435,
|
|
"mean_token_accuracy": 0.12278054803609847,
|
|
"num_tokens": 1002920.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 6.676013088226318,
|
|
"epoch": 0.044448476052249636,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 6.5368,
|
|
"mean_token_accuracy": 0.1078170619904995,
|
|
"num_tokens": 1013611.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 6.653495216369629,
|
|
"epoch": 0.04490203193033382,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000247,
|
|
"loss": 6.4169,
|
|
"mean_token_accuracy": 0.1161510780453682,
|
|
"num_tokens": 1024121.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 6.81571741104126,
|
|
"epoch": 0.045355587808417995,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 6.653,
|
|
"mean_token_accuracy": 0.11692796349525451,
|
|
"num_tokens": 1033845.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 6.724951601028442,
|
|
"epoch": 0.04580914368650218,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000252,
|
|
"loss": 6.4562,
|
|
"mean_token_accuracy": 0.1180861733853817,
|
|
"num_tokens": 1044642.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 6.615443086624145,
|
|
"epoch": 0.046262699564586354,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 6.5297,
|
|
"mean_token_accuracy": 0.1160704404115677,
|
|
"num_tokens": 1054728.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 6.7214963912963865,
|
|
"epoch": 0.04671625544267054,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000257,
|
|
"loss": 6.4834,
|
|
"mean_token_accuracy": 0.10873565226793289,
|
|
"num_tokens": 1065743.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 6.680114889144898,
|
|
"epoch": 0.04716981132075472,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 6.3986,
|
|
"mean_token_accuracy": 0.11717408373951912,
|
|
"num_tokens": 1076798.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 6.656686067581177,
|
|
"epoch": 0.047623367198838897,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000262,
|
|
"loss": 6.5431,
|
|
"mean_token_accuracy": 0.11418797224760055,
|
|
"num_tokens": 1087445.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 6.606220769882202,
|
|
"epoch": 0.04807692307692308,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 6.4584,
|
|
"mean_token_accuracy": 0.1161401018500328,
|
|
"num_tokens": 1098379.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 6.722146511077881,
|
|
"epoch": 0.048530478955007256,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 6.5429,
|
|
"mean_token_accuracy": 0.11141678988933564,
|
|
"num_tokens": 1108016.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 6.6710772037506105,
|
|
"epoch": 0.04898403483309144,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 6.4014,
|
|
"mean_token_accuracy": 0.11449897214770317,
|
|
"num_tokens": 1117887.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 6.654284572601318,
|
|
"epoch": 0.049437590711175615,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 6.4097,
|
|
"mean_token_accuracy": 0.11381929144263267,
|
|
"num_tokens": 1128497.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 6.613014507293701,
|
|
"epoch": 0.0498911465892598,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 6.4609,
|
|
"mean_token_accuracy": 0.11565488874912262,
|
|
"num_tokens": 1138168.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 6.618120574951172,
|
|
"epoch": 0.050344702467343974,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000277,
|
|
"loss": 6.445,
|
|
"mean_token_accuracy": 0.11517123132944107,
|
|
"num_tokens": 1148357.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 6.67120852470398,
|
|
"epoch": 0.05079825834542816,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 6.4813,
|
|
"mean_token_accuracy": 0.1128874771296978,
|
|
"num_tokens": 1159964.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 6.685760498046875,
|
|
"epoch": 0.05125181422351233,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 6.5201,
|
|
"mean_token_accuracy": 0.1172065868973732,
|
|
"num_tokens": 1170683.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 6.719839191436767,
|
|
"epoch": 0.051705370101596516,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 6.4993,
|
|
"mean_token_accuracy": 0.11043535247445106,
|
|
"num_tokens": 1181680.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 6.516751384735107,
|
|
"epoch": 0.0521589259796807,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000287,
|
|
"loss": 6.3766,
|
|
"mean_token_accuracy": 0.11628183797001838,
|
|
"num_tokens": 1191619.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 6.552532625198364,
|
|
"epoch": 0.052612481857764876,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 6.387,
|
|
"mean_token_accuracy": 0.11748170480132103,
|
|
"num_tokens": 1202264.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 6.598452091217041,
|
|
"epoch": 0.05306603773584906,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000292,
|
|
"loss": 6.3936,
|
|
"mean_token_accuracy": 0.11468102261424065,
|
|
"num_tokens": 1212119.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 6.638687658309936,
|
|
"epoch": 0.053519593613933235,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 6.5243,
|
|
"mean_token_accuracy": 0.11499153003096581,
|
|
"num_tokens": 1222317.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 6.6762138366699215,
|
|
"epoch": 0.05397314949201742,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000297,
|
|
"loss": 6.4613,
|
|
"mean_token_accuracy": 0.11701688691973686,
|
|
"num_tokens": 1232914.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 6.519153881072998,
|
|
"epoch": 0.054426705370101594,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 6.3034,
|
|
"mean_token_accuracy": 0.11886714175343513,
|
|
"num_tokens": 1244214.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 6.619960975646973,
|
|
"epoch": 0.05488026124818578,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.000302,
|
|
"loss": 6.4138,
|
|
"mean_token_accuracy": 0.11526961103081704,
|
|
"num_tokens": 1254626.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 6.602964544296265,
|
|
"epoch": 0.05533381712626995,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 6.5216,
|
|
"mean_token_accuracy": 0.11393038928508759,
|
|
"num_tokens": 1265461.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 6.613763475418091,
|
|
"epoch": 0.055787373004354136,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000307,
|
|
"loss": 6.387,
|
|
"mean_token_accuracy": 0.11922261342406273,
|
|
"num_tokens": 1275810.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 6.47516770362854,
|
|
"epoch": 0.05624092888243832,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 6.413,
|
|
"mean_token_accuracy": 0.1167520485818386,
|
|
"num_tokens": 1285170.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 6.6089705467224125,
|
|
"epoch": 0.056694484760522496,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000312,
|
|
"loss": 6.3501,
|
|
"mean_token_accuracy": 0.11907305344939231,
|
|
"num_tokens": 1295460.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 6.5755761623382565,
|
|
"epoch": 0.05714804063860668,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 6.4893,
|
|
"mean_token_accuracy": 0.11553953886032105,
|
|
"num_tokens": 1306656.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 6.614667463302612,
|
|
"epoch": 0.057601596516690855,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000317,
|
|
"loss": 6.4463,
|
|
"mean_token_accuracy": 0.11898912116885185,
|
|
"num_tokens": 1318019.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 6.514087343215943,
|
|
"epoch": 0.05805515239477504,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 6.3713,
|
|
"mean_token_accuracy": 0.11803188174962997,
|
|
"num_tokens": 1328120.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 6.696631908416748,
|
|
"epoch": 0.058508708272859214,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000322,
|
|
"loss": 6.4671,
|
|
"mean_token_accuracy": 0.11322417482733727,
|
|
"num_tokens": 1338354.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 6.591117477416992,
|
|
"epoch": 0.0589622641509434,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 6.4288,
|
|
"mean_token_accuracy": 0.11614542976021766,
|
|
"num_tokens": 1348666.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 6.542242813110351,
|
|
"epoch": 0.05941582002902757,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 6.4847,
|
|
"mean_token_accuracy": 0.11858619302511215,
|
|
"num_tokens": 1359713.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 6.600148725509643,
|
|
"epoch": 0.059869375907111756,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 6.3456,
|
|
"mean_token_accuracy": 0.12028133273124694,
|
|
"num_tokens": 1369507.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 6.558723402023316,
|
|
"epoch": 0.06032293178519594,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 6.5014,
|
|
"mean_token_accuracy": 0.11275067254900932,
|
|
"num_tokens": 1380726.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 6.666363334655761,
|
|
"epoch": 0.060776487663280115,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 6.4262,
|
|
"mean_token_accuracy": 0.11828458458185195,
|
|
"num_tokens": 1391423.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 6.609200382232666,
|
|
"epoch": 0.0612300435413643,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000337,
|
|
"loss": 6.4021,
|
|
"mean_token_accuracy": 0.1221817396581173,
|
|
"num_tokens": 1402492.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 6.487628936767578,
|
|
"epoch": 0.061683599419448475,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 6.4558,
|
|
"mean_token_accuracy": 0.11870089024305344,
|
|
"num_tokens": 1412497.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 6.698206186294556,
|
|
"epoch": 0.06213715529753266,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000342,
|
|
"loss": 6.4291,
|
|
"mean_token_accuracy": 0.12117572948336601,
|
|
"num_tokens": 1423214.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 6.5064043521881105,
|
|
"epoch": 0.06259071117561683,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 6.4106,
|
|
"mean_token_accuracy": 0.11815783530473709,
|
|
"num_tokens": 1434044.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 6.522539710998535,
|
|
"epoch": 0.06304426705370102,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000347,
|
|
"loss": 6.3789,
|
|
"mean_token_accuracy": 0.1227622389793396,
|
|
"num_tokens": 1444387.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 6.471425151824951,
|
|
"epoch": 0.0634978229317852,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 6.3352,
|
|
"mean_token_accuracy": 0.1156968854367733,
|
|
"num_tokens": 1455157.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 6.585581874847412,
|
|
"epoch": 0.06395137880986937,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000352,
|
|
"loss": 6.4501,
|
|
"mean_token_accuracy": 0.12337471693754196,
|
|
"num_tokens": 1466145.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 6.528838872909546,
|
|
"epoch": 0.06440493468795355,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 6.4251,
|
|
"mean_token_accuracy": 0.11607742905616761,
|
|
"num_tokens": 1476713.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 6.579174137115478,
|
|
"epoch": 0.06485849056603774,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000357,
|
|
"loss": 6.4357,
|
|
"mean_token_accuracy": 0.12061923295259476,
|
|
"num_tokens": 1486908.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 6.555825901031494,
|
|
"epoch": 0.06531204644412192,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 6.3554,
|
|
"mean_token_accuracy": 0.12144754379987717,
|
|
"num_tokens": 1498185.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 6.533269929885864,
|
|
"epoch": 0.0657656023222061,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000362,
|
|
"loss": 6.3975,
|
|
"mean_token_accuracy": 0.11883825734257698,
|
|
"num_tokens": 1508376.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 6.5100702285766605,
|
|
"epoch": 0.06621915820029027,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 6.4877,
|
|
"mean_token_accuracy": 0.11778334230184555,
|
|
"num_tokens": 1519953.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 6.46563720703125,
|
|
"epoch": 0.06667271407837445,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000367,
|
|
"loss": 6.368,
|
|
"mean_token_accuracy": 0.1215110793709755,
|
|
"num_tokens": 1529793.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 6.522617959976197,
|
|
"epoch": 0.06712626995645864,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 6.376,
|
|
"mean_token_accuracy": 0.11825870126485824,
|
|
"num_tokens": 1540859.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 6.524055290222168,
|
|
"epoch": 0.06757982583454282,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000372,
|
|
"loss": 6.3031,
|
|
"mean_token_accuracy": 0.12105328515172005,
|
|
"num_tokens": 1549783.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 6.425115442276001,
|
|
"epoch": 0.06803338171262699,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 6.3511,
|
|
"mean_token_accuracy": 0.12026687189936638,
|
|
"num_tokens": 1560522.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 6.401650762557983,
|
|
"epoch": 0.06848693759071117,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000377,
|
|
"loss": 6.3384,
|
|
"mean_token_accuracy": 0.11981744021177292,
|
|
"num_tokens": 1570668.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 6.540406513214111,
|
|
"epoch": 0.06894049346879536,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 6.4551,
|
|
"mean_token_accuracy": 0.12221564278006554,
|
|
"num_tokens": 1581523.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 6.523171138763428,
|
|
"epoch": 0.06939404934687954,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000382,
|
|
"loss": 6.3504,
|
|
"mean_token_accuracy": 0.12361696362495422,
|
|
"num_tokens": 1591356.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 6.4687755584716795,
|
|
"epoch": 0.06984760522496372,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 6.3504,
|
|
"mean_token_accuracy": 0.12131494581699372,
|
|
"num_tokens": 1601779.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 6.49934868812561,
|
|
"epoch": 0.07030116110304789,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 6.3423,
|
|
"mean_token_accuracy": 0.12172357738018036,
|
|
"num_tokens": 1611995.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 6.505820989608765,
|
|
"epoch": 0.07075471698113207,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 6.3775,
|
|
"mean_token_accuracy": 0.11691758409142494,
|
|
"num_tokens": 1621834.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 6.44027795791626,
|
|
"epoch": 0.07120827285921626,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 6.4122,
|
|
"mean_token_accuracy": 0.11729778945446015,
|
|
"num_tokens": 1632881.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 6.436710596084595,
|
|
"epoch": 0.07166182873730044,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 6.4103,
|
|
"mean_token_accuracy": 0.11784379482269287,
|
|
"num_tokens": 1642870.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 6.473271608352661,
|
|
"epoch": 0.07211538461538461,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 6.2824,
|
|
"mean_token_accuracy": 0.1295071743428707,
|
|
"num_tokens": 1653390.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 6.4784633159637455,
|
|
"epoch": 0.07256894049346879,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 6.3965,
|
|
"mean_token_accuracy": 0.12507268264889718,
|
|
"num_tokens": 1663382.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 6.5645670890808105,
|
|
"epoch": 0.07302249637155298,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000402,
|
|
"loss": 6.4115,
|
|
"mean_token_accuracy": 0.1164341501891613,
|
|
"num_tokens": 1673601.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 6.325691747665405,
|
|
"epoch": 0.07347605224963716,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 6.312,
|
|
"mean_token_accuracy": 0.12586987242102624,
|
|
"num_tokens": 1683565.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 6.426483488082885,
|
|
"epoch": 0.07392960812772134,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 6.3037,
|
|
"mean_token_accuracy": 0.12335021495819092,
|
|
"num_tokens": 1693636.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 6.604643249511719,
|
|
"epoch": 0.07438316400580551,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 6.4244,
|
|
"mean_token_accuracy": 0.11771097406744957,
|
|
"num_tokens": 1703415.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 6.449386930465698,
|
|
"epoch": 0.0748367198838897,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000412,
|
|
"loss": 6.3872,
|
|
"mean_token_accuracy": 0.12382198274135589,
|
|
"num_tokens": 1713579.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 6.428066158294678,
|
|
"epoch": 0.07529027576197388,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 6.392,
|
|
"mean_token_accuracy": 0.11516611129045487,
|
|
"num_tokens": 1724583.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 6.460074424743652,
|
|
"epoch": 0.07574383164005806,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000417,
|
|
"loss": 6.3107,
|
|
"mean_token_accuracy": 0.12721009701490402,
|
|
"num_tokens": 1735293.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 6.448750114440918,
|
|
"epoch": 0.07619738751814223,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 6.3412,
|
|
"mean_token_accuracy": 0.12112727388739586,
|
|
"num_tokens": 1745623.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 6.439601993560791,
|
|
"epoch": 0.07665094339622641,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000422,
|
|
"loss": 6.3679,
|
|
"mean_token_accuracy": 0.12129366248846055,
|
|
"num_tokens": 1755713.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 6.432407855987549,
|
|
"epoch": 0.0771044992743106,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 6.3598,
|
|
"mean_token_accuracy": 0.11952197775244713,
|
|
"num_tokens": 1765264.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 6.459024906158447,
|
|
"epoch": 0.07755805515239478,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000427,
|
|
"loss": 6.3829,
|
|
"mean_token_accuracy": 0.11767206266522408,
|
|
"num_tokens": 1775769.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 6.405208253860474,
|
|
"epoch": 0.07801161103047896,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 6.3104,
|
|
"mean_token_accuracy": 0.12149815633893013,
|
|
"num_tokens": 1786245.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 6.358996915817261,
|
|
"epoch": 0.07846516690856313,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000432,
|
|
"loss": 6.3452,
|
|
"mean_token_accuracy": 0.1247312806546688,
|
|
"num_tokens": 1796040.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 6.409610795974731,
|
|
"epoch": 0.07891872278664731,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 6.3672,
|
|
"mean_token_accuracy": 0.1209503524005413,
|
|
"num_tokens": 1806007.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 6.574124145507812,
|
|
"epoch": 0.0793722786647315,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000437,
|
|
"loss": 6.4432,
|
|
"mean_token_accuracy": 0.11531289964914322,
|
|
"num_tokens": 1816935.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 6.328552627563477,
|
|
"epoch": 0.07982583454281568,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 6.2861,
|
|
"mean_token_accuracy": 0.1238143265247345,
|
|
"num_tokens": 1827419.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 6.487691879272461,
|
|
"epoch": 0.08027939042089985,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000442,
|
|
"loss": 6.3912,
|
|
"mean_token_accuracy": 0.12026699110865594,
|
|
"num_tokens": 1837933.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 6.400113248825074,
|
|
"epoch": 0.08073294629898403,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 6.4463,
|
|
"mean_token_accuracy": 0.12280047684907913,
|
|
"num_tokens": 1848551.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 6.482123517990113,
|
|
"epoch": 0.08118650217706821,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000447,
|
|
"loss": 6.3217,
|
|
"mean_token_accuracy": 0.120026945322752,
|
|
"num_tokens": 1858380.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 6.3884306907653805,
|
|
"epoch": 0.0816400580551524,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 6.261,
|
|
"mean_token_accuracy": 0.12377997189760208,
|
|
"num_tokens": 1868291.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 6.3934813976287845,
|
|
"epoch": 0.08209361393323658,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 6.3581,
|
|
"mean_token_accuracy": 0.12294313907623292,
|
|
"num_tokens": 1879219.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 6.447540664672852,
|
|
"epoch": 0.08254716981132075,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 6.3587,
|
|
"mean_token_accuracy": 0.12189177200198173,
|
|
"num_tokens": 1889809.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 6.309494495391846,
|
|
"epoch": 0.08300072568940493,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 6.3265,
|
|
"mean_token_accuracy": 0.11860769167542458,
|
|
"num_tokens": 1899986.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 6.396956491470337,
|
|
"epoch": 0.08345428156748912,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 6.2974,
|
|
"mean_token_accuracy": 0.12569222077727318,
|
|
"num_tokens": 1909314.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 6.480527687072754,
|
|
"epoch": 0.0839078374455733,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000462,
|
|
"loss": 6.3497,
|
|
"mean_token_accuracy": 0.12690884619951248,
|
|
"num_tokens": 1918443.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 6.319289779663086,
|
|
"epoch": 0.08436139332365747,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 6.2885,
|
|
"mean_token_accuracy": 0.12226624712347985,
|
|
"num_tokens": 1928683.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 6.2751952648162845,
|
|
"epoch": 0.08481494920174165,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000467,
|
|
"loss": 6.2257,
|
|
"mean_token_accuracy": 0.12297250479459762,
|
|
"num_tokens": 1938293.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 6.350123882293701,
|
|
"epoch": 0.08526850507982583,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 6.3185,
|
|
"mean_token_accuracy": 0.12192818373441697,
|
|
"num_tokens": 1948233.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 6.3410228252410885,
|
|
"epoch": 0.08572206095791002,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000472,
|
|
"loss": 6.2253,
|
|
"mean_token_accuracy": 0.12578235045075417,
|
|
"num_tokens": 1958611.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 6.3663990020751955,
|
|
"epoch": 0.0861756168359942,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 6.3898,
|
|
"mean_token_accuracy": 0.1257556840777397,
|
|
"num_tokens": 1968957.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 6.412576484680176,
|
|
"epoch": 0.08662917271407837,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000477,
|
|
"loss": 6.2254,
|
|
"mean_token_accuracy": 0.129705747961998,
|
|
"num_tokens": 1978503.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 6.213819122314453,
|
|
"epoch": 0.08708272859216255,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 6.2192,
|
|
"mean_token_accuracy": 0.12796008363366126,
|
|
"num_tokens": 1988458.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 6.385213994979859,
|
|
"epoch": 0.08753628447024674,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000482,
|
|
"loss": 6.3616,
|
|
"mean_token_accuracy": 0.12156156599521636,
|
|
"num_tokens": 1999984.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 6.23322491645813,
|
|
"epoch": 0.08798984034833092,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 6.2223,
|
|
"mean_token_accuracy": 0.13277149796485901,
|
|
"num_tokens": 2010645.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 6.410303211212158,
|
|
"epoch": 0.08844339622641509,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000487,
|
|
"loss": 6.3426,
|
|
"mean_token_accuracy": 0.12236039787530899,
|
|
"num_tokens": 2020196.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 6.342306232452392,
|
|
"epoch": 0.08889695210449927,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 6.2375,
|
|
"mean_token_accuracy": 0.12410336285829544,
|
|
"num_tokens": 2030101.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 6.2711248874664305,
|
|
"epoch": 0.08935050798258345,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000492,
|
|
"loss": 6.3066,
|
|
"mean_token_accuracy": 0.12489919736981392,
|
|
"num_tokens": 2040454.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 6.2733996391296385,
|
|
"epoch": 0.08980406386066764,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 6.2668,
|
|
"mean_token_accuracy": 0.12355489358305931,
|
|
"num_tokens": 2050378.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 6.404911756515503,
|
|
"epoch": 0.09025761973875182,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000497,
|
|
"loss": 6.3254,
|
|
"mean_token_accuracy": 0.1241577684879303,
|
|
"num_tokens": 2060282.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 6.299366188049317,
|
|
"epoch": 0.09071117561683599,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 6.3041,
|
|
"mean_token_accuracy": 0.12481492385268211,
|
|
"num_tokens": 2070563.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 6.384706211090088,
|
|
"epoch": 0.09116473149492017,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999999985110217,
|
|
"loss": 6.3913,
|
|
"mean_token_accuracy": 0.12241514995694161,
|
|
"num_tokens": 2080153.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 6.240800046920777,
|
|
"epoch": 0.09161828737300436,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999999924620471,
|
|
"loss": 6.2265,
|
|
"mean_token_accuracy": 0.1292314775288105,
|
|
"num_tokens": 2090590.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 6.359726142883301,
|
|
"epoch": 0.09207184325108854,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999999817600155,
|
|
"loss": 6.308,
|
|
"mean_token_accuracy": 0.12286418452858924,
|
|
"num_tokens": 2101945.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 6.352720880508423,
|
|
"epoch": 0.09252539912917271,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999999664049268,
|
|
"loss": 6.2828,
|
|
"mean_token_accuracy": 0.12876259461045264,
|
|
"num_tokens": 2112514.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 6.185303258895874,
|
|
"epoch": 0.09297895500725689,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999999463967816,
|
|
"loss": 6.2503,
|
|
"mean_token_accuracy": 0.12381088435649872,
|
|
"num_tokens": 2122296.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 6.4518931865692135,
|
|
"epoch": 0.09343251088534107,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00049999992173558,
|
|
"loss": 6.3985,
|
|
"mean_token_accuracy": 0.11333390846848487,
|
|
"num_tokens": 2134512.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 6.320862913131714,
|
|
"epoch": 0.09388606676342526,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999998924213228,
|
|
"loss": 6.3194,
|
|
"mean_token_accuracy": 0.12776733413338662,
|
|
"num_tokens": 2143934.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 6.229617166519165,
|
|
"epoch": 0.09433962264150944,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999998584540105,
|
|
"loss": 6.2042,
|
|
"mean_token_accuracy": 0.1237527720630169,
|
|
"num_tokens": 2155730.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 6.362137651443481,
|
|
"epoch": 0.09479317851959361,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999998198336437,
|
|
"loss": 6.2322,
|
|
"mean_token_accuracy": 0.11689665541052818,
|
|
"num_tokens": 2166422.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 6.291525554656983,
|
|
"epoch": 0.09524673439767779,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999997765602233,
|
|
"loss": 6.3434,
|
|
"mean_token_accuracy": 0.12079075872898101,
|
|
"num_tokens": 2177842.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 6.393911600112915,
|
|
"epoch": 0.09570029027576198,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999997286337502,
|
|
"loss": 6.4109,
|
|
"mean_token_accuracy": 0.12265082895755768,
|
|
"num_tokens": 2188614.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 6.289089870452881,
|
|
"epoch": 0.09615384615384616,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999996760542254,
|
|
"loss": 6.191,
|
|
"mean_token_accuracy": 0.12765964791178702,
|
|
"num_tokens": 2197886.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 6.177943181991577,
|
|
"epoch": 0.09660740203193033,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00049999961882165,
|
|
"loss": 6.2718,
|
|
"mean_token_accuracy": 0.12614985033869744,
|
|
"num_tokens": 2209930.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 6.398168087005615,
|
|
"epoch": 0.09706095791001451,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999995569360251,
|
|
"loss": 6.2684,
|
|
"mean_token_accuracy": 0.12817343920469285,
|
|
"num_tokens": 2219767.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 6.201504325866699,
|
|
"epoch": 0.0975145137880987,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499999490397352,
|
|
"loss": 6.2079,
|
|
"mean_token_accuracy": 0.1247169628739357,
|
|
"num_tokens": 2230082.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 6.2470996379852295,
|
|
"epoch": 0.09796806966618288,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999994192056321,
|
|
"loss": 6.2232,
|
|
"mean_token_accuracy": 0.12979647517204285,
|
|
"num_tokens": 2240066.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 6.27187294960022,
|
|
"epoch": 0.09842162554426705,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999993433608669,
|
|
"loss": 6.2689,
|
|
"mean_token_accuracy": 0.12491475120186805,
|
|
"num_tokens": 2250732.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 6.230953168869019,
|
|
"epoch": 0.09887518142235123,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999992628630579,
|
|
"loss": 6.1459,
|
|
"mean_token_accuracy": 0.1282850295305252,
|
|
"num_tokens": 2261452.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 6.253374814987183,
|
|
"epoch": 0.09932873730043541,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999991777122069,
|
|
"loss": 6.2632,
|
|
"mean_token_accuracy": 0.12474793419241906,
|
|
"num_tokens": 2271929.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 6.200113439559937,
|
|
"epoch": 0.0997822931785196,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999990879083156,
|
|
"loss": 6.2292,
|
|
"mean_token_accuracy": 0.12713540568947793,
|
|
"num_tokens": 2282987.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 6.271349954605102,
|
|
"epoch": 0.10023584905660378,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999989934513857,
|
|
"loss": 6.2242,
|
|
"mean_token_accuracy": 0.13376623317599295,
|
|
"num_tokens": 2292796.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 6.309939861297607,
|
|
"epoch": 0.10068940493468795,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999988943414193,
|
|
"loss": 6.2685,
|
|
"mean_token_accuracy": 0.1259679116308689,
|
|
"num_tokens": 2303057.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 6.165333366394043,
|
|
"epoch": 0.10114296081277213,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999987905784184,
|
|
"loss": 6.2533,
|
|
"mean_token_accuracy": 0.126700322329998,
|
|
"num_tokens": 2314168.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 6.271357774734497,
|
|
"epoch": 0.10159651669085631,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999986821623853,
|
|
"loss": 6.2141,
|
|
"mean_token_accuracy": 0.12545626759529113,
|
|
"num_tokens": 2325241.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 6.313687515258789,
|
|
"epoch": 0.1020500725689405,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004999985690933219,
|
|
"loss": 6.2417,
|
|
"mean_token_accuracy": 0.12604843005537986,
|
|
"num_tokens": 2334866.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 6.125355434417725,
|
|
"epoch": 0.10250362844702467,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999984513712311,
|
|
"loss": 6.2362,
|
|
"mean_token_accuracy": 0.1284227713942528,
|
|
"num_tokens": 2345422.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 6.371741151809692,
|
|
"epoch": 0.10295718432510885,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999983289961146,
|
|
"loss": 6.2714,
|
|
"mean_token_accuracy": 0.1241820827126503,
|
|
"num_tokens": 2356285.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 6.155414390563965,
|
|
"epoch": 0.10341074020319303,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999982019679755,
|
|
"loss": 6.1867,
|
|
"mean_token_accuracy": 0.1323022335767746,
|
|
"num_tokens": 2366861.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 6.258955812454223,
|
|
"epoch": 0.10386429608127722,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999980702868164,
|
|
"loss": 6.2102,
|
|
"mean_token_accuracy": 0.13267010524868966,
|
|
"num_tokens": 2376851.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 6.270642280578613,
|
|
"epoch": 0.1043178519593614,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999979339526396,
|
|
"loss": 6.2633,
|
|
"mean_token_accuracy": 0.13088681548833847,
|
|
"num_tokens": 2386857.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 6.23888578414917,
|
|
"epoch": 0.10477140783744557,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999977929654484,
|
|
"loss": 6.1974,
|
|
"mean_token_accuracy": 0.13122352808713914,
|
|
"num_tokens": 2397035.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 6.273252153396607,
|
|
"epoch": 0.10522496371552975,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004999976473252453,
|
|
"loss": 6.2753,
|
|
"mean_token_accuracy": 0.12375183030962944,
|
|
"num_tokens": 2408177.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 6.322346830368042,
|
|
"epoch": 0.10567851959361393,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999974970320338,
|
|
"loss": 6.2266,
|
|
"mean_token_accuracy": 0.12485374137759209,
|
|
"num_tokens": 2418445.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 6.186552906036377,
|
|
"epoch": 0.10613207547169812,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999973420858165,
|
|
"loss": 6.225,
|
|
"mean_token_accuracy": 0.12650659754872323,
|
|
"num_tokens": 2428990.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 6.227190589904785,
|
|
"epoch": 0.10658563134978229,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999971824865968,
|
|
"loss": 6.2697,
|
|
"mean_token_accuracy": 0.12284443452954293,
|
|
"num_tokens": 2439643.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 6.330835676193237,
|
|
"epoch": 0.10703918722786647,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999970182343782,
|
|
"loss": 6.3127,
|
|
"mean_token_accuracy": 0.12625510469079018,
|
|
"num_tokens": 2450691.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 6.270051288604736,
|
|
"epoch": 0.10749274310595065,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999968493291638,
|
|
"loss": 6.2433,
|
|
"mean_token_accuracy": 0.12399949803948403,
|
|
"num_tokens": 2460706.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 6.072198438644409,
|
|
"epoch": 0.10794629898403484,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999966757709573,
|
|
"loss": 6.1397,
|
|
"mean_token_accuracy": 0.1322955772280693,
|
|
"num_tokens": 2470947.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 6.232493448257446,
|
|
"epoch": 0.10839985486211902,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999964975597622,
|
|
"loss": 6.0869,
|
|
"mean_token_accuracy": 0.13433996289968492,
|
|
"num_tokens": 2481132.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 6.181258201599121,
|
|
"epoch": 0.10885341074020319,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999963146955821,
|
|
"loss": 6.1403,
|
|
"mean_token_accuracy": 0.133623556047678,
|
|
"num_tokens": 2491701.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 6.120849657058716,
|
|
"epoch": 0.10930696661828737,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499996127178421,
|
|
"loss": 6.2375,
|
|
"mean_token_accuracy": 0.12445509806275368,
|
|
"num_tokens": 2502360.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 6.195035171508789,
|
|
"epoch": 0.10976052249637155,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999959350082825,
|
|
"loss": 6.097,
|
|
"mean_token_accuracy": 0.12750829607248307,
|
|
"num_tokens": 2512140.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 6.253734350204468,
|
|
"epoch": 0.11021407837445574,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999957381851709,
|
|
"loss": 6.2466,
|
|
"mean_token_accuracy": 0.12660726830363273,
|
|
"num_tokens": 2522721.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 6.106527471542359,
|
|
"epoch": 0.1106676342525399,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999955367090901,
|
|
"loss": 6.108,
|
|
"mean_token_accuracy": 0.13220437839627266,
|
|
"num_tokens": 2531786.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 6.26336636543274,
|
|
"epoch": 0.11112119013062409,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999953305800441,
|
|
"loss": 6.2201,
|
|
"mean_token_accuracy": 0.12029675543308258,
|
|
"num_tokens": 2542895.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 6.13406777381897,
|
|
"epoch": 0.11157474600870827,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999951197980374,
|
|
"loss": 6.2011,
|
|
"mean_token_accuracy": 0.12797781825065613,
|
|
"num_tokens": 2554120.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 6.287543106079101,
|
|
"epoch": 0.11202830188679246,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999949043630744,
|
|
"loss": 6.2446,
|
|
"mean_token_accuracy": 0.12370867282152176,
|
|
"num_tokens": 2563935.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 6.092472743988037,
|
|
"epoch": 0.11248185776487664,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999946842751593,
|
|
"loss": 6.1501,
|
|
"mean_token_accuracy": 0.12944189086556435,
|
|
"num_tokens": 2574465.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 6.177829313278198,
|
|
"epoch": 0.11293541364296081,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999944595342968,
|
|
"loss": 6.0986,
|
|
"mean_token_accuracy": 0.13265978991985322,
|
|
"num_tokens": 2584694.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 6.156110572814941,
|
|
"epoch": 0.11338896952104499,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999942301404916,
|
|
"loss": 6.0902,
|
|
"mean_token_accuracy": 0.13416919559240342,
|
|
"num_tokens": 2594540.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 6.102447032928467,
|
|
"epoch": 0.11384252539912917,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999939960937484,
|
|
"loss": 6.022,
|
|
"mean_token_accuracy": 0.13621553182601928,
|
|
"num_tokens": 2604896.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 6.183004379272461,
|
|
"epoch": 0.11429608127721336,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999937573940721,
|
|
"loss": 6.2082,
|
|
"mean_token_accuracy": 0.13601385727524756,
|
|
"num_tokens": 2614143.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 6.0483887672424315,
|
|
"epoch": 0.11474963715529753,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999935140414674,
|
|
"loss": 6.0993,
|
|
"mean_token_accuracy": 0.12777388021349906,
|
|
"num_tokens": 2623999.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 6.307592487335205,
|
|
"epoch": 0.11520319303338171,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999932660359395,
|
|
"loss": 6.3112,
|
|
"mean_token_accuracy": 0.12414655461907387,
|
|
"num_tokens": 2636208.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 6.134375429153442,
|
|
"epoch": 0.11565674891146589,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999930133774936,
|
|
"loss": 6.1749,
|
|
"mean_token_accuracy": 0.13444133400917052,
|
|
"num_tokens": 2645854.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 6.208854484558105,
|
|
"epoch": 0.11611030478955008,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999927560661348,
|
|
"loss": 6.1606,
|
|
"mean_token_accuracy": 0.14128717482089997,
|
|
"num_tokens": 2655877.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 6.193210935592651,
|
|
"epoch": 0.11656386066763426,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999924941018685,
|
|
"loss": 6.1854,
|
|
"mean_token_accuracy": 0.13444199338555335,
|
|
"num_tokens": 2666157.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 6.116014003753662,
|
|
"epoch": 0.11701741654571843,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999922274847,
|
|
"loss": 6.1024,
|
|
"mean_token_accuracy": 0.13178513795137406,
|
|
"num_tokens": 2676647.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 6.093279409408569,
|
|
"epoch": 0.11747097242380261,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000499991956214635,
|
|
"loss": 6.1301,
|
|
"mean_token_accuracy": 0.14098571091890336,
|
|
"num_tokens": 2686417.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 6.198765611648559,
|
|
"epoch": 0.1179245283018868,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499991680291679,
|
|
"loss": 6.1374,
|
|
"mean_token_accuracy": 0.12717395946383475,
|
|
"num_tokens": 2697540.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 6.106028366088867,
|
|
"epoch": 0.11837808417997098,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999913997158378,
|
|
"loss": 6.1846,
|
|
"mean_token_accuracy": 0.12284301593899727,
|
|
"num_tokens": 2709397.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 6.217894172668457,
|
|
"epoch": 0.11883164005805515,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999911144871169,
|
|
"loss": 6.1486,
|
|
"mean_token_accuracy": 0.12695815786719322,
|
|
"num_tokens": 2720430.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 6.11812047958374,
|
|
"epoch": 0.11928519593613933,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999908246055226,
|
|
"loss": 6.1094,
|
|
"mean_token_accuracy": 0.12854591459035875,
|
|
"num_tokens": 2730648.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 6.136201524734497,
|
|
"epoch": 0.11973875181422351,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999905300710607,
|
|
"loss": 6.0688,
|
|
"mean_token_accuracy": 0.13269162625074388,
|
|
"num_tokens": 2739979.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 6.138657140731811,
|
|
"epoch": 0.1201923076923077,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004999902308837373,
|
|
"loss": 6.2314,
|
|
"mean_token_accuracy": 0.12551036328077317,
|
|
"num_tokens": 2750329.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 6.094318199157715,
|
|
"epoch": 0.12064586357039188,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999899270435584,
|
|
"loss": 6.1032,
|
|
"mean_token_accuracy": 0.13775131702423096,
|
|
"num_tokens": 2760535.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 6.1581787109375,
|
|
"epoch": 0.12109941944847605,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999896185505307,
|
|
"loss": 6.128,
|
|
"mean_token_accuracy": 0.12702896371483802,
|
|
"num_tokens": 2770470.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 6.087944221496582,
|
|
"epoch": 0.12155297532656023,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999893054046603,
|
|
"loss": 6.1455,
|
|
"mean_token_accuracy": 0.12925868555903436,
|
|
"num_tokens": 2781506.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 6.0965156078338625,
|
|
"epoch": 0.12200653120464441,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999889876059537,
|
|
"loss": 6.022,
|
|
"mean_token_accuracy": 0.1381001003086567,
|
|
"num_tokens": 2791245.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 6.076093435287476,
|
|
"epoch": 0.1224600870827286,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999886651544176,
|
|
"loss": 6.0262,
|
|
"mean_token_accuracy": 0.1368500992655754,
|
|
"num_tokens": 2801680.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 6.1108323097229,
|
|
"epoch": 0.12291364296081277,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999883380500584,
|
|
"loss": 6.1129,
|
|
"mean_token_accuracy": 0.13711178302764893,
|
|
"num_tokens": 2812805.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 6.181576919555664,
|
|
"epoch": 0.12336719883889695,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999880062928831,
|
|
"loss": 6.1608,
|
|
"mean_token_accuracy": 0.129413640499115,
|
|
"num_tokens": 2822834.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 6.089189243316651,
|
|
"epoch": 0.12382075471698113,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999876698828985,
|
|
"loss": 6.1075,
|
|
"mean_token_accuracy": 0.13718436509370804,
|
|
"num_tokens": 2832312.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 6.152549886703492,
|
|
"epoch": 0.12427431059506532,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999873288201116,
|
|
"loss": 6.1187,
|
|
"mean_token_accuracy": 0.14113932773470877,
|
|
"num_tokens": 2842998.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 6.136705541610718,
|
|
"epoch": 0.1247278664731495,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004999869831045294,
|
|
"loss": 6.1438,
|
|
"mean_token_accuracy": 0.13647317588329316,
|
|
"num_tokens": 2854218.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 6.104028177261353,
|
|
"epoch": 0.12518142235123367,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999866327361589,
|
|
"loss": 6.0237,
|
|
"mean_token_accuracy": 0.1436094231903553,
|
|
"num_tokens": 2864484.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 6.104306650161743,
|
|
"epoch": 0.12563497822931785,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999862777150077,
|
|
"loss": 6.1447,
|
|
"mean_token_accuracy": 0.13356181010603904,
|
|
"num_tokens": 2873800.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 6.142058610916138,
|
|
"epoch": 0.12608853410740203,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999859180410829,
|
|
"loss": 6.1636,
|
|
"mean_token_accuracy": 0.12791035771369935,
|
|
"num_tokens": 2884247.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 6.0876030921936035,
|
|
"epoch": 0.12654208998548622,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999855537143919,
|
|
"loss": 6.0556,
|
|
"mean_token_accuracy": 0.13154122978448868,
|
|
"num_tokens": 2894739.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 6.03957347869873,
|
|
"epoch": 0.1269956458635704,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999851847349425,
|
|
"loss": 6.1199,
|
|
"mean_token_accuracy": 0.13250315189361572,
|
|
"num_tokens": 2904376.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 6.174634170532227,
|
|
"epoch": 0.12744920174165458,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999848111027419,
|
|
"loss": 6.1702,
|
|
"mean_token_accuracy": 0.1307752922177315,
|
|
"num_tokens": 2914304.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 6.1659255027771,
|
|
"epoch": 0.12790275761973874,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999844328177983,
|
|
"loss": 6.0538,
|
|
"mean_token_accuracy": 0.1304120510816574,
|
|
"num_tokens": 2924400.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 6.208686876296997,
|
|
"epoch": 0.12835631349782292,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999840498801191,
|
|
"loss": 6.2771,
|
|
"mean_token_accuracy": 0.13209760636091233,
|
|
"num_tokens": 2935040.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 6.04742112159729,
|
|
"epoch": 0.1288098693759071,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999836622897126,
|
|
"loss": 6.0794,
|
|
"mean_token_accuracy": 0.13408395498991013,
|
|
"num_tokens": 2945536.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 6.038312911987305,
|
|
"epoch": 0.1292634252539913,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999832700465865,
|
|
"loss": 5.9749,
|
|
"mean_token_accuracy": 0.13549989610910415,
|
|
"num_tokens": 2954969.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 6.066872215270996,
|
|
"epoch": 0.12971698113207547,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999828731507491,
|
|
"loss": 6.112,
|
|
"mean_token_accuracy": 0.12939976528286934,
|
|
"num_tokens": 2966218.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 6.094667911529541,
|
|
"epoch": 0.13017053701015965,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999824716022085,
|
|
"loss": 6.136,
|
|
"mean_token_accuracy": 0.12750567644834518,
|
|
"num_tokens": 2976640.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 6.105727338790894,
|
|
"epoch": 0.13062409288824384,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999820654009731,
|
|
"loss": 6.0905,
|
|
"mean_token_accuracy": 0.13567687720060348,
|
|
"num_tokens": 2985883.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 6.088870000839234,
|
|
"epoch": 0.13107764876632802,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999816545470513,
|
|
"loss": 6.1031,
|
|
"mean_token_accuracy": 0.12947410196065903,
|
|
"num_tokens": 2996695.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 6.171409797668457,
|
|
"epoch": 0.1315312046444122,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999812390404514,
|
|
"loss": 6.1171,
|
|
"mean_token_accuracy": 0.1340610735118389,
|
|
"num_tokens": 3007500.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 5.898324060440063,
|
|
"epoch": 0.13198476052249636,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999808188811823,
|
|
"loss": 5.9616,
|
|
"mean_token_accuracy": 0.1348599299788475,
|
|
"num_tokens": 3017299.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 6.216505908966065,
|
|
"epoch": 0.13243831640058054,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999803940692524,
|
|
"loss": 6.2449,
|
|
"mean_token_accuracy": 0.12761179730296135,
|
|
"num_tokens": 3028389.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 6.154873561859131,
|
|
"epoch": 0.13289187227866472,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999799646046707,
|
|
"loss": 6.0668,
|
|
"mean_token_accuracy": 0.1371331825852394,
|
|
"num_tokens": 3038883.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 6.139013624191284,
|
|
"epoch": 0.1333454281567489,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999795304874461,
|
|
"loss": 6.1742,
|
|
"mean_token_accuracy": 0.1367236204445362,
|
|
"num_tokens": 3049904.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 6.055725383758545,
|
|
"epoch": 0.1337989840348331,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999790917175873,
|
|
"loss": 6.026,
|
|
"mean_token_accuracy": 0.133791683614254,
|
|
"num_tokens": 3059788.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 6.11804518699646,
|
|
"epoch": 0.13425253991291727,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999786482951036,
|
|
"loss": 6.0123,
|
|
"mean_token_accuracy": 0.13600108176469802,
|
|
"num_tokens": 3070413.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 6.0903236865997314,
|
|
"epoch": 0.13470609579100146,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999782002200041,
|
|
"loss": 6.1348,
|
|
"mean_token_accuracy": 0.1337863601744175,
|
|
"num_tokens": 3081093.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 6.083447599411011,
|
|
"epoch": 0.13515965166908564,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999777474922982,
|
|
"loss": 6.0731,
|
|
"mean_token_accuracy": 0.12955736368894577,
|
|
"num_tokens": 3090594.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 6.138653802871704,
|
|
"epoch": 0.13561320754716982,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999772901119951,
|
|
"loss": 6.1789,
|
|
"mean_token_accuracy": 0.12780415564775466,
|
|
"num_tokens": 3101061.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 6.0858407497406,
|
|
"epoch": 0.13606676342525398,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999768280791043,
|
|
"loss": 6.0895,
|
|
"mean_token_accuracy": 0.1373533673584461,
|
|
"num_tokens": 3111715.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 6.09755220413208,
|
|
"epoch": 0.13652031930333816,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999763613936352,
|
|
"loss": 5.9993,
|
|
"mean_token_accuracy": 0.14067018330097197,
|
|
"num_tokens": 3121378.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 5.970461797714234,
|
|
"epoch": 0.13697387518142234,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999758900555979,
|
|
"loss": 5.9441,
|
|
"mean_token_accuracy": 0.14521051645278932,
|
|
"num_tokens": 3131229.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 6.036447477340698,
|
|
"epoch": 0.13742743105950653,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999754140650017,
|
|
"loss": 6.0404,
|
|
"mean_token_accuracy": 0.1319979339838028,
|
|
"num_tokens": 3140859.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 6.097309494018555,
|
|
"epoch": 0.1378809869375907,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999749334218567,
|
|
"loss": 6.051,
|
|
"mean_token_accuracy": 0.1364140808582306,
|
|
"num_tokens": 3151692.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 5.99874792098999,
|
|
"epoch": 0.1383345428156749,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999744481261726,
|
|
"loss": 6.1157,
|
|
"mean_token_accuracy": 0.1304463878273964,
|
|
"num_tokens": 3161879.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 6.048851442337036,
|
|
"epoch": 0.13878809869375908,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004999739581779597,
|
|
"loss": 5.982,
|
|
"mean_token_accuracy": 0.14158392399549485,
|
|
"num_tokens": 3171282.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 6.069761800765991,
|
|
"epoch": 0.13924165457184326,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499973463577228,
|
|
"loss": 6.0283,
|
|
"mean_token_accuracy": 0.1374294213950634,
|
|
"num_tokens": 3181398.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 6.063587093353272,
|
|
"epoch": 0.13969521044992744,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999729643239877,
|
|
"loss": 6.1616,
|
|
"mean_token_accuracy": 0.1350327856838703,
|
|
"num_tokens": 3191431.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 6.10133204460144,
|
|
"epoch": 0.1401487663280116,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999724604182492,
|
|
"loss": 6.1621,
|
|
"mean_token_accuracy": 0.12566626071929932,
|
|
"num_tokens": 3202147.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 6.160943412780762,
|
|
"epoch": 0.14060232220609578,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999719518600229,
|
|
"loss": 6.0291,
|
|
"mean_token_accuracy": 0.1362243190407753,
|
|
"num_tokens": 3212428.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 6.014663982391357,
|
|
"epoch": 0.14105587808417996,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999714386493192,
|
|
"loss": 6.0893,
|
|
"mean_token_accuracy": 0.13574016094207764,
|
|
"num_tokens": 3222099.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 6.097148656845093,
|
|
"epoch": 0.14150943396226415,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999709207861489,
|
|
"loss": 6.0313,
|
|
"mean_token_accuracy": 0.13692608699202538,
|
|
"num_tokens": 3232079.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 5.976779842376709,
|
|
"epoch": 0.14196298984034833,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999703982705227,
|
|
"loss": 5.9373,
|
|
"mean_token_accuracy": 0.1448259696364403,
|
|
"num_tokens": 3241762.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 6.014270257949829,
|
|
"epoch": 0.1424165457184325,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999698711024513,
|
|
"loss": 6.0239,
|
|
"mean_token_accuracy": 0.13922590911388397,
|
|
"num_tokens": 3252571.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 6.057532691955567,
|
|
"epoch": 0.1428701015965167,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999693392819456,
|
|
"loss": 6.0752,
|
|
"mean_token_accuracy": 0.13099500313401222,
|
|
"num_tokens": 3263542.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 6.098192596435547,
|
|
"epoch": 0.14332365747460088,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999688028090166,
|
|
"loss": 6.1447,
|
|
"mean_token_accuracy": 0.1325105018913746,
|
|
"num_tokens": 3273295.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 6.178218173980713,
|
|
"epoch": 0.14377721335268506,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999682616836755,
|
|
"loss": 6.1644,
|
|
"mean_token_accuracy": 0.1343841977417469,
|
|
"num_tokens": 3283605.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 6.034059715270996,
|
|
"epoch": 0.14423076923076922,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999677159059334,
|
|
"loss": 6.0018,
|
|
"mean_token_accuracy": 0.13836689442396163,
|
|
"num_tokens": 3293837.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 5.9601891040802,
|
|
"epoch": 0.1446843251088534,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999671654758016,
|
|
"loss": 6.0074,
|
|
"mean_token_accuracy": 0.1401748426258564,
|
|
"num_tokens": 3304131.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 6.019832801818848,
|
|
"epoch": 0.14513788098693758,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004999666103932915,
|
|
"loss": 6.0457,
|
|
"mean_token_accuracy": 0.13282065689563752,
|
|
"num_tokens": 3313543.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 5.98559947013855,
|
|
"epoch": 0.14559143686502177,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999660506584145,
|
|
"loss": 6.0292,
|
|
"mean_token_accuracy": 0.13611204028129578,
|
|
"num_tokens": 3324487.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 6.09367094039917,
|
|
"epoch": 0.14604499274310595,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999654862711823,
|
|
"loss": 6.0432,
|
|
"mean_token_accuracy": 0.13722373321652412,
|
|
"num_tokens": 3335094.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 6.020828676223755,
|
|
"epoch": 0.14649854862119013,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999649172316065,
|
|
"loss": 5.9875,
|
|
"mean_token_accuracy": 0.13779204934835435,
|
|
"num_tokens": 3344252.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 6.04573392868042,
|
|
"epoch": 0.14695210449927432,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499964343539699,
|
|
"loss": 6.0523,
|
|
"mean_token_accuracy": 0.134325809776783,
|
|
"num_tokens": 3354265.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 6.130579662322998,
|
|
"epoch": 0.1474056603773585,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999637651954714,
|
|
"loss": 6.1609,
|
|
"mean_token_accuracy": 0.13543225973844528,
|
|
"num_tokens": 3364616.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 6.084848880767822,
|
|
"epoch": 0.14785921625544268,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999631821989358,
|
|
"loss": 6.0887,
|
|
"mean_token_accuracy": 0.1368525169789791,
|
|
"num_tokens": 3373650.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 6.006167268753051,
|
|
"epoch": 0.14831277213352684,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999625945501043,
|
|
"loss": 5.9953,
|
|
"mean_token_accuracy": 0.140744087100029,
|
|
"num_tokens": 3384590.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 6.116048669815063,
|
|
"epoch": 0.14876632801161102,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000499962002248989,
|
|
"loss": 6.0452,
|
|
"mean_token_accuracy": 0.13539330065250396,
|
|
"num_tokens": 3395616.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 5.996517515182495,
|
|
"epoch": 0.1492198838896952,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999614052956024,
|
|
"loss": 6.032,
|
|
"mean_token_accuracy": 0.1371271312236786,
|
|
"num_tokens": 3405810.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 6.041546487808228,
|
|
"epoch": 0.1496734397677794,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999608036899563,
|
|
"loss": 6.0743,
|
|
"mean_token_accuracy": 0.13593365326523782,
|
|
"num_tokens": 3415932.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 6.038019609451294,
|
|
"epoch": 0.15012699564586357,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999601974320636,
|
|
"loss": 6.011,
|
|
"mean_token_accuracy": 0.13596160858869552,
|
|
"num_tokens": 3425626.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 6.005490827560425,
|
|
"epoch": 0.15058055152394775,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999595865219367,
|
|
"loss": 6.0204,
|
|
"mean_token_accuracy": 0.13287046179175377,
|
|
"num_tokens": 3434837.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 6.034183692932129,
|
|
"epoch": 0.15103410740203194,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999589709595881,
|
|
"loss": 6.0485,
|
|
"mean_token_accuracy": 0.13829124122858047,
|
|
"num_tokens": 3445238.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 5.948350954055786,
|
|
"epoch": 0.15148766328011612,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999583507450308,
|
|
"loss": 6.0381,
|
|
"mean_token_accuracy": 0.13264935240149497,
|
|
"num_tokens": 3456738.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 5.909289693832397,
|
|
"epoch": 0.1519412191582003,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999577258782774,
|
|
"loss": 5.9012,
|
|
"mean_token_accuracy": 0.13860071077942848,
|
|
"num_tokens": 3466296.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 6.124201059341431,
|
|
"epoch": 0.15239477503628446,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499957096359341,
|
|
"loss": 6.1028,
|
|
"mean_token_accuracy": 0.13263867199420928,
|
|
"num_tokens": 3476989.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 5.982616138458252,
|
|
"epoch": 0.15284833091436864,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999564621882343,
|
|
"loss": 5.9443,
|
|
"mean_token_accuracy": 0.13828226998448373,
|
|
"num_tokens": 3487050.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 6.07118854522705,
|
|
"epoch": 0.15330188679245282,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999558233649708,
|
|
"loss": 6.1489,
|
|
"mean_token_accuracy": 0.1293186977505684,
|
|
"num_tokens": 3497777.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 6.066112852096557,
|
|
"epoch": 0.153755442670537,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999551798895636,
|
|
"loss": 6.0597,
|
|
"mean_token_accuracy": 0.13373040035367012,
|
|
"num_tokens": 3509066.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 6.0372473239898685,
|
|
"epoch": 0.1542089985486212,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999545317620258,
|
|
"loss": 5.9953,
|
|
"mean_token_accuracy": 0.13631840348243712,
|
|
"num_tokens": 3519567.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 5.967922782897949,
|
|
"epoch": 0.15466255442670537,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999538789823711,
|
|
"loss": 6.0394,
|
|
"mean_token_accuracy": 0.13856917023658752,
|
|
"num_tokens": 3529402.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 6.11129059791565,
|
|
"epoch": 0.15511611030478956,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999532215506127,
|
|
"loss": 6.0335,
|
|
"mean_token_accuracy": 0.14377474635839463,
|
|
"num_tokens": 3539805.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 5.909777498245239,
|
|
"epoch": 0.15556966618287374,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999525594667645,
|
|
"loss": 5.9067,
|
|
"mean_token_accuracy": 0.142856465280056,
|
|
"num_tokens": 3550477.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 5.982000541687012,
|
|
"epoch": 0.15602322206095792,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00049995189273084,
|
|
"loss": 6.0103,
|
|
"mean_token_accuracy": 0.13765751868486403,
|
|
"num_tokens": 3560729.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 6.05636043548584,
|
|
"epoch": 0.15647677793904208,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499951221342853,
|
|
"loss": 6.0812,
|
|
"mean_token_accuracy": 0.1257948972284794,
|
|
"num_tokens": 3571538.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 6.04515323638916,
|
|
"epoch": 0.15693033381712626,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999505453028174,
|
|
"loss": 6.0887,
|
|
"mean_token_accuracy": 0.13670211359858514,
|
|
"num_tokens": 3583128.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 6.103114271163941,
|
|
"epoch": 0.15738388969521044,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999498646107472,
|
|
"loss": 6.0257,
|
|
"mean_token_accuracy": 0.13807276338338853,
|
|
"num_tokens": 3594358.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 5.9683116436004635,
|
|
"epoch": 0.15783744557329463,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999491792666566,
|
|
"loss": 5.9489,
|
|
"mean_token_accuracy": 0.14279852136969567,
|
|
"num_tokens": 3604345.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 6.023993253707886,
|
|
"epoch": 0.1582910014513788,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999484892705597,
|
|
"loss": 5.9883,
|
|
"mean_token_accuracy": 0.1382973462343216,
|
|
"num_tokens": 3616129.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 6.001973867416382,
|
|
"epoch": 0.158744557329463,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999477946224705,
|
|
"loss": 6.0409,
|
|
"mean_token_accuracy": 0.13687437549233436,
|
|
"num_tokens": 3627458.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 6.058828830718994,
|
|
"epoch": 0.15919811320754718,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999470953224037,
|
|
"loss": 5.9206,
|
|
"mean_token_accuracy": 0.14193053394556046,
|
|
"num_tokens": 3636047.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 5.878429508209228,
|
|
"epoch": 0.15965166908563136,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999463913703735,
|
|
"loss": 5.9243,
|
|
"mean_token_accuracy": 0.13841559886932372,
|
|
"num_tokens": 3646930.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 6.051437282562256,
|
|
"epoch": 0.16010522496371554,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999456827663948,
|
|
"loss": 6.0061,
|
|
"mean_token_accuracy": 0.14167415127158164,
|
|
"num_tokens": 3657279.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 5.9463623523712155,
|
|
"epoch": 0.1605587808417997,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000499944969510482,
|
|
"loss": 5.911,
|
|
"mean_token_accuracy": 0.13895074278116226,
|
|
"num_tokens": 3667070.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 5.968365859985352,
|
|
"epoch": 0.16101233671988388,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999442516026498,
|
|
"loss": 5.9461,
|
|
"mean_token_accuracy": 0.1364276871085167,
|
|
"num_tokens": 3677560.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 5.948978471755981,
|
|
"epoch": 0.16146589259796806,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999435290429133,
|
|
"loss": 5.899,
|
|
"mean_token_accuracy": 0.14505873918533324,
|
|
"num_tokens": 3686701.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 5.980872631072998,
|
|
"epoch": 0.16191944847605225,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999428018312872,
|
|
"loss": 5.9934,
|
|
"mean_token_accuracy": 0.1406108967959881,
|
|
"num_tokens": 3696338.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 5.991557312011719,
|
|
"epoch": 0.16237300435413643,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999420699677867,
|
|
"loss": 5.9721,
|
|
"mean_token_accuracy": 0.14421124309301375,
|
|
"num_tokens": 3705752.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 6.0219776153564455,
|
|
"epoch": 0.1628265602322206,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999413334524269,
|
|
"loss": 6.0601,
|
|
"mean_token_accuracy": 0.13283660635352135,
|
|
"num_tokens": 3716225.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 6.030018615722656,
|
|
"epoch": 0.1632801161103048,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004999405922852229,
|
|
"loss": 5.9367,
|
|
"mean_token_accuracy": 0.1414524123072624,
|
|
"num_tokens": 3726593.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 5.9711730003356935,
|
|
"epoch": 0.16373367198838898,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999398464661901,
|
|
"loss": 6.0046,
|
|
"mean_token_accuracy": 0.13162903413176535,
|
|
"num_tokens": 3737563.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 6.145048904418945,
|
|
"epoch": 0.16418722786647316,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004999390959953441,
|
|
"loss": 6.0538,
|
|
"mean_token_accuracy": 0.1345907710492611,
|
|
"num_tokens": 3747752.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 5.8741460800170895,
|
|
"epoch": 0.16464078374455732,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004999383408727002,
|
|
"loss": 5.9927,
|
|
"mean_token_accuracy": 0.13676512464880944,
|
|
"num_tokens": 3758795.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 6.02309947013855,
|
|
"epoch": 0.1650943396226415,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004999375810982741,
|
|
"loss": 5.9739,
|
|
"mean_token_accuracy": 0.1364384949207306,
|
|
"num_tokens": 3768690.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 5.949415493011474,
|
|
"epoch": 0.16554789550072568,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999368166720815,
|
|
"loss": 6.0354,
|
|
"mean_token_accuracy": 0.1367568477988243,
|
|
"num_tokens": 3779018.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 6.097243118286133,
|
|
"epoch": 0.16600145137880987,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999360475941382,
|
|
"loss": 5.9274,
|
|
"mean_token_accuracy": 0.14494050815701484,
|
|
"num_tokens": 3788985.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 5.9869836330413815,
|
|
"epoch": 0.16645500725689405,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00049993527386446,
|
|
"loss": 6.08,
|
|
"mean_token_accuracy": 0.12971132546663283,
|
|
"num_tokens": 3800787.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 6.007747030258178,
|
|
"epoch": 0.16690856313497823,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999344954830633,
|
|
"loss": 5.9478,
|
|
"mean_token_accuracy": 0.13803392350673677,
|
|
"num_tokens": 3811381.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 6.022607088088989,
|
|
"epoch": 0.16736211901306242,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999337124499638,
|
|
"loss": 6.0713,
|
|
"mean_token_accuracy": 0.1421744704246521,
|
|
"num_tokens": 3822055.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 5.9824930191040036,
|
|
"epoch": 0.1678156748911466,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999329247651777,
|
|
"loss": 6.0099,
|
|
"mean_token_accuracy": 0.13485550805926322,
|
|
"num_tokens": 3831900.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 6.0410867691040036,
|
|
"epoch": 0.16826923076923078,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999321324287213,
|
|
"loss": 5.9797,
|
|
"mean_token_accuracy": 0.13857458531856537,
|
|
"num_tokens": 3842702.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 6.063360166549683,
|
|
"epoch": 0.16872278664731494,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999313354406114,
|
|
"loss": 5.9382,
|
|
"mean_token_accuracy": 0.13797046095132828,
|
|
"num_tokens": 3852690.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 5.861346340179443,
|
|
"epoch": 0.16917634252539912,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499930533800864,
|
|
"loss": 5.9436,
|
|
"mean_token_accuracy": 0.14458322674036025,
|
|
"num_tokens": 3863040.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 5.986399984359741,
|
|
"epoch": 0.1696298984034833,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999297275094958,
|
|
"loss": 6.0249,
|
|
"mean_token_accuracy": 0.13291169926524163,
|
|
"num_tokens": 3873613.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 5.904158306121826,
|
|
"epoch": 0.1700834542815675,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999289165665235,
|
|
"loss": 5.8408,
|
|
"mean_token_accuracy": 0.1431124784052372,
|
|
"num_tokens": 3883936.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 5.933678531646729,
|
|
"epoch": 0.17053701015965167,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004999281009719639,
|
|
"loss": 5.8053,
|
|
"mean_token_accuracy": 0.15056236162781717,
|
|
"num_tokens": 3893788.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 5.911346578598023,
|
|
"epoch": 0.17099056603773585,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999272807258339,
|
|
"loss": 5.8711,
|
|
"mean_token_accuracy": 0.1449036605656147,
|
|
"num_tokens": 3903434.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 5.9308332920074465,
|
|
"epoch": 0.17144412191582004,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999264558281504,
|
|
"loss": 5.8934,
|
|
"mean_token_accuracy": 0.14332058131694794,
|
|
"num_tokens": 3913476.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 5.821413946151734,
|
|
"epoch": 0.17189767779390422,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999256262789305,
|
|
"loss": 5.8453,
|
|
"mean_token_accuracy": 0.14364899098873138,
|
|
"num_tokens": 3923301.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 5.960890817642212,
|
|
"epoch": 0.1723512336719884,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999247920781913,
|
|
"loss": 5.9933,
|
|
"mean_token_accuracy": 0.13700442612171174,
|
|
"num_tokens": 3933335.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 6.01145076751709,
|
|
"epoch": 0.17280478955007256,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999239532259502,
|
|
"loss": 6.0224,
|
|
"mean_token_accuracy": 0.13089234083890916,
|
|
"num_tokens": 3944171.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 6.04728136062622,
|
|
"epoch": 0.17325834542815674,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999231097222244,
|
|
"loss": 6.0882,
|
|
"mean_token_accuracy": 0.1425239235162735,
|
|
"num_tokens": 3954160.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 6.0153731346130375,
|
|
"epoch": 0.17371190130624092,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999222615670312,
|
|
"loss": 5.8789,
|
|
"mean_token_accuracy": 0.1452776275575161,
|
|
"num_tokens": 3964110.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 5.966774988174438,
|
|
"epoch": 0.1741654571843251,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999214087603885,
|
|
"loss": 5.9743,
|
|
"mean_token_accuracy": 0.13833973333239555,
|
|
"num_tokens": 3974293.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 5.89274525642395,
|
|
"epoch": 0.1746190130624093,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999205513023135,
|
|
"loss": 5.9224,
|
|
"mean_token_accuracy": 0.1437511757016182,
|
|
"num_tokens": 3984346.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 5.918350028991699,
|
|
"epoch": 0.17507256894049347,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999196891928245,
|
|
"loss": 5.8621,
|
|
"mean_token_accuracy": 0.1486036777496338,
|
|
"num_tokens": 3992897.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 5.9130213260650635,
|
|
"epoch": 0.17552612481857766,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999188224319388,
|
|
"loss": 5.9059,
|
|
"mean_token_accuracy": 0.1498722940683365,
|
|
"num_tokens": 4002575.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 5.936802387237549,
|
|
"epoch": 0.17597968069666184,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999179510196746,
|
|
"loss": 5.9803,
|
|
"mean_token_accuracy": 0.13661175593733788,
|
|
"num_tokens": 4013752.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 5.9770777225494385,
|
|
"epoch": 0.17643323657474602,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999170749560498,
|
|
"loss": 5.8615,
|
|
"mean_token_accuracy": 0.14331807419657708,
|
|
"num_tokens": 4023718.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 5.900900363922119,
|
|
"epoch": 0.17688679245283018,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004999161942410827,
|
|
"loss": 5.9739,
|
|
"mean_token_accuracy": 0.1353725589811802,
|
|
"num_tokens": 4034210.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 6.036285829544068,
|
|
"epoch": 0.17734034833091436,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999153088747913,
|
|
"loss": 5.951,
|
|
"mean_token_accuracy": 0.13893376514315606,
|
|
"num_tokens": 4044868.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 5.865960550308228,
|
|
"epoch": 0.17779390420899854,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000499914418857194,
|
|
"loss": 5.9483,
|
|
"mean_token_accuracy": 0.1431120105087757,
|
|
"num_tokens": 4055049.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 6.078762149810791,
|
|
"epoch": 0.17824746008708273,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999135241883092,
|
|
"loss": 6.01,
|
|
"mean_token_accuracy": 0.1387563019990921,
|
|
"num_tokens": 4065889.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 6.000588369369507,
|
|
"epoch": 0.1787010159651669,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999126248681555,
|
|
"loss": 6.0182,
|
|
"mean_token_accuracy": 0.1365288347005844,
|
|
"num_tokens": 4077288.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 5.914630365371704,
|
|
"epoch": 0.1791545718432511,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999117208967513,
|
|
"loss": 5.9669,
|
|
"mean_token_accuracy": 0.13962030857801438,
|
|
"num_tokens": 4087402.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 6.029739284515381,
|
|
"epoch": 0.17960812772133528,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999108122741154,
|
|
"loss": 6.0221,
|
|
"mean_token_accuracy": 0.1369963027536869,
|
|
"num_tokens": 4098150.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 5.888871479034424,
|
|
"epoch": 0.18006168359941946,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999098990002666,
|
|
"loss": 5.8678,
|
|
"mean_token_accuracy": 0.14218315333127976,
|
|
"num_tokens": 4108134.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 6.019744491577148,
|
|
"epoch": 0.18051523947750364,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999089810752237,
|
|
"loss": 6.0193,
|
|
"mean_token_accuracy": 0.1359066478908062,
|
|
"num_tokens": 4118251.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 5.931015396118164,
|
|
"epoch": 0.1809687953555878,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499908058499006,
|
|
"loss": 5.8581,
|
|
"mean_token_accuracy": 0.145183701813221,
|
|
"num_tokens": 4129228.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 5.9268440246582035,
|
|
"epoch": 0.18142235123367198,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999071312716321,
|
|
"loss": 5.9273,
|
|
"mean_token_accuracy": 0.14528655931353568,
|
|
"num_tokens": 4139391.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 5.924670076370239,
|
|
"epoch": 0.18187590711175616,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999061993931215,
|
|
"loss": 5.8668,
|
|
"mean_token_accuracy": 0.14713739082217217,
|
|
"num_tokens": 4148891.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 6.1402112483978275,
|
|
"epoch": 0.18232946298984035,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999052628634934,
|
|
"loss": 6.2053,
|
|
"mean_token_accuracy": 0.13204461038112641,
|
|
"num_tokens": 4159551.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 6.043571424484253,
|
|
"epoch": 0.18278301886792453,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999043216827671,
|
|
"loss": 6.0086,
|
|
"mean_token_accuracy": 0.13990638628602028,
|
|
"num_tokens": 4170055.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 5.888297462463379,
|
|
"epoch": 0.1832365747460087,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004999033758509621,
|
|
"loss": 5.8599,
|
|
"mean_token_accuracy": 0.13923854306340216,
|
|
"num_tokens": 4180767.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 5.950031042098999,
|
|
"epoch": 0.1836901306240929,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000499902425368098,
|
|
"loss": 5.9798,
|
|
"mean_token_accuracy": 0.14310303330421448,
|
|
"num_tokens": 4190654.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 5.984168815612793,
|
|
"epoch": 0.18414368650217708,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004999014702341944,
|
|
"loss": 5.9011,
|
|
"mean_token_accuracy": 0.14403254836797713,
|
|
"num_tokens": 4200753.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 5.928147506713867,
|
|
"epoch": 0.18459724238026126,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999005104492712,
|
|
"loss": 6.0011,
|
|
"mean_token_accuracy": 0.1354036383330822,
|
|
"num_tokens": 4210994.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 6.021360778808594,
|
|
"epoch": 0.18505079825834542,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004998995460133481,
|
|
"loss": 5.9295,
|
|
"mean_token_accuracy": 0.13851736932992936,
|
|
"num_tokens": 4220883.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 5.972361421585083,
|
|
"epoch": 0.1855043541364296,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998985769264451,
|
|
"loss": 5.9692,
|
|
"mean_token_accuracy": 0.1328580841422081,
|
|
"num_tokens": 4231269.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 5.92348313331604,
|
|
"epoch": 0.18595791001451378,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004998976031885821,
|
|
"loss": 5.9583,
|
|
"mean_token_accuracy": 0.1385072022676468,
|
|
"num_tokens": 4241559.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 5.93124942779541,
|
|
"epoch": 0.18641146589259797,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004998966247997794,
|
|
"loss": 5.8573,
|
|
"mean_token_accuracy": 0.14284690618515014,
|
|
"num_tokens": 4250870.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 5.912771606445313,
|
|
"epoch": 0.18686502177068215,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004998956417600572,
|
|
"loss": 5.8197,
|
|
"mean_token_accuracy": 0.1453770861029625,
|
|
"num_tokens": 4260848.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 5.8631298542022705,
|
|
"epoch": 0.18731857764876633,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998946540694358,
|
|
"loss": 5.947,
|
|
"mean_token_accuracy": 0.14410295933485032,
|
|
"num_tokens": 4270973.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 6.008993816375733,
|
|
"epoch": 0.18777213352685052,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004998936617279357,
|
|
"loss": 6.0175,
|
|
"mean_token_accuracy": 0.1405512697994709,
|
|
"num_tokens": 4281211.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 5.907906436920166,
|
|
"epoch": 0.1882256894049347,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998926647355773,
|
|
"loss": 5.8701,
|
|
"mean_token_accuracy": 0.14646850228309632,
|
|
"num_tokens": 4291425.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 5.9778430461883545,
|
|
"epoch": 0.18867924528301888,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004998916630923813,
|
|
"loss": 5.9779,
|
|
"mean_token_accuracy": 0.14027420431375504,
|
|
"num_tokens": 4301079.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 6.034561729431152,
|
|
"epoch": 0.18913280116110304,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004998906567983685,
|
|
"loss": 5.9646,
|
|
"mean_token_accuracy": 0.1393656000494957,
|
|
"num_tokens": 4312374.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 5.909461545944214,
|
|
"epoch": 0.18958635703918722,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004998896458535595,
|
|
"loss": 5.879,
|
|
"mean_token_accuracy": 0.14832498878240585,
|
|
"num_tokens": 4322810.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 5.9581499099731445,
|
|
"epoch": 0.1900399129172714,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004998886302579752,
|
|
"loss": 5.8683,
|
|
"mean_token_accuracy": 0.14442463368177413,
|
|
"num_tokens": 4332082.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 5.972524499893188,
|
|
"epoch": 0.19049346879535559,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000499887610011637,
|
|
"loss": 5.9623,
|
|
"mean_token_accuracy": 0.1426968216896057,
|
|
"num_tokens": 4342632.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 5.894812726974488,
|
|
"epoch": 0.19094702467343977,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004998865851145656,
|
|
"loss": 5.8987,
|
|
"mean_token_accuracy": 0.1407205879688263,
|
|
"num_tokens": 4353544.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 5.882326269149781,
|
|
"epoch": 0.19140058055152395,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004998855555667822,
|
|
"loss": 6.0315,
|
|
"mean_token_accuracy": 0.13898359686136247,
|
|
"num_tokens": 4363636.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 6.04261794090271,
|
|
"epoch": 0.19185413642960814,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998845213683084,
|
|
"loss": 5.8898,
|
|
"mean_token_accuracy": 0.13970340117812158,
|
|
"num_tokens": 4373672.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 5.864584922790527,
|
|
"epoch": 0.19230769230769232,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004998834825191652,
|
|
"loss": 5.8591,
|
|
"mean_token_accuracy": 0.1457592159509659,
|
|
"num_tokens": 4383199.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 5.9757240295410154,
|
|
"epoch": 0.1927612481857765,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998824390193743,
|
|
"loss": 5.9402,
|
|
"mean_token_accuracy": 0.13909565806388854,
|
|
"num_tokens": 4394446.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 6.01021409034729,
|
|
"epoch": 0.19321480406386066,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004998813908689573,
|
|
"loss": 5.9763,
|
|
"mean_token_accuracy": 0.1380794882774353,
|
|
"num_tokens": 4405882.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 5.878481531143189,
|
|
"epoch": 0.19366835994194484,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004998803380679359,
|
|
"loss": 5.8407,
|
|
"mean_token_accuracy": 0.15159011334180833,
|
|
"num_tokens": 4415280.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 5.953402328491211,
|
|
"epoch": 0.19412191582002902,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004998792806163317,
|
|
"loss": 6.0475,
|
|
"mean_token_accuracy": 0.13735857382416725,
|
|
"num_tokens": 4425755.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 5.908466815948486,
|
|
"epoch": 0.1945754716981132,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004998782185141667,
|
|
"loss": 5.9127,
|
|
"mean_token_accuracy": 0.138707172870636,
|
|
"num_tokens": 4436259.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 6.002693319320679,
|
|
"epoch": 0.1950290275761974,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004998771517614629,
|
|
"loss": 5.9482,
|
|
"mean_token_accuracy": 0.13556500673294067,
|
|
"num_tokens": 4446423.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 5.941006422042847,
|
|
"epoch": 0.19548258345428157,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004998760803582422,
|
|
"loss": 5.8841,
|
|
"mean_token_accuracy": 0.15068939626216887,
|
|
"num_tokens": 4456678.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 5.921889400482177,
|
|
"epoch": 0.19593613933236576,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004998750043045269,
|
|
"loss": 5.8956,
|
|
"mean_token_accuracy": 0.14178509563207625,
|
|
"num_tokens": 4467031.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 5.974037790298462,
|
|
"epoch": 0.19638969521044994,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004998739236003392,
|
|
"loss": 5.9568,
|
|
"mean_token_accuracy": 0.13483025133609772,
|
|
"num_tokens": 4477771.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 5.998474931716919,
|
|
"epoch": 0.1968432510885341,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004998728382457014,
|
|
"loss": 5.9763,
|
|
"mean_token_accuracy": 0.13997794538736344,
|
|
"num_tokens": 4488426.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 6.019248390197754,
|
|
"epoch": 0.19729680696661828,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004998717482406362,
|
|
"loss": 5.9578,
|
|
"mean_token_accuracy": 0.13564275726675987,
|
|
"num_tokens": 4499735.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 5.934429025650024,
|
|
"epoch": 0.19775036284470246,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004998706535851657,
|
|
"loss": 5.88,
|
|
"mean_token_accuracy": 0.1441620409488678,
|
|
"num_tokens": 4509500.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 5.90686182975769,
|
|
"epoch": 0.19820391872278664,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998695542793129,
|
|
"loss": 5.906,
|
|
"mean_token_accuracy": 0.14358371123671532,
|
|
"num_tokens": 4520431.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 5.962169981002807,
|
|
"epoch": 0.19865747460087083,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004998684503231003,
|
|
"loss": 5.9944,
|
|
"mean_token_accuracy": 0.14260854870080947,
|
|
"num_tokens": 4532294.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 5.9562725067138675,
|
|
"epoch": 0.199111030478955,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000499867341716551,
|
|
"loss": 5.9081,
|
|
"mean_token_accuracy": 0.14024144038558006,
|
|
"num_tokens": 4542488.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 5.872625350952148,
|
|
"epoch": 0.1995645863570392,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004998662284596878,
|
|
"loss": 5.8462,
|
|
"mean_token_accuracy": 0.136696857213974,
|
|
"num_tokens": 4552933.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 5.941536951065063,
|
|
"epoch": 0.20001814223512338,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004998651105525335,
|
|
"loss": 5.8378,
|
|
"mean_token_accuracy": 0.14871531575918198,
|
|
"num_tokens": 4562373.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 5.881709098815918,
|
|
"epoch": 0.20047169811320756,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998639879951115,
|
|
"loss": 5.9588,
|
|
"mean_token_accuracy": 0.14208371788263321,
|
|
"num_tokens": 4572715.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 5.96837158203125,
|
|
"epoch": 0.2009252539912917,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000499862860787445,
|
|
"loss": 5.8464,
|
|
"mean_token_accuracy": 0.13923058286309242,
|
|
"num_tokens": 4582782.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 5.983753299713134,
|
|
"epoch": 0.2013788098693759,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004998617289295571,
|
|
"loss": 5.9569,
|
|
"mean_token_accuracy": 0.13587422147393227,
|
|
"num_tokens": 4594108.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 5.929776239395141,
|
|
"epoch": 0.20183236574746008,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004998605924214714,
|
|
"loss": 5.9107,
|
|
"mean_token_accuracy": 0.14216437190771103,
|
|
"num_tokens": 4604732.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 5.93411808013916,
|
|
"epoch": 0.20228592162554426,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004998594512632114,
|
|
"loss": 6.0441,
|
|
"mean_token_accuracy": 0.13005613088607787,
|
|
"num_tokens": 4614998.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 5.9276261806488035,
|
|
"epoch": 0.20273947750362845,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004998583054548006,
|
|
"loss": 5.8687,
|
|
"mean_token_accuracy": 0.14243716672062873,
|
|
"num_tokens": 4624665.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 5.920424890518189,
|
|
"epoch": 0.20319303338171263,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004998571549962628,
|
|
"loss": 5.8625,
|
|
"mean_token_accuracy": 0.14737029150128364,
|
|
"num_tokens": 4633731.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 5.960051679611206,
|
|
"epoch": 0.2036465892597968,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004998559998876216,
|
|
"loss": 5.8949,
|
|
"mean_token_accuracy": 0.13982552140951157,
|
|
"num_tokens": 4643421.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 6.00085940361023,
|
|
"epoch": 0.204100145137881,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004998548401289012,
|
|
"loss": 5.9692,
|
|
"mean_token_accuracy": 0.13818764984607695,
|
|
"num_tokens": 4653795.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 5.941312074661255,
|
|
"epoch": 0.20455370101596518,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004998536757201253,
|
|
"loss": 5.9414,
|
|
"mean_token_accuracy": 0.13912858814001083,
|
|
"num_tokens": 4664840.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 5.994112920761109,
|
|
"epoch": 0.20500725689404933,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004998525066613181,
|
|
"loss": 5.952,
|
|
"mean_token_accuracy": 0.14518292397260665,
|
|
"num_tokens": 4675508.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 5.889045238494873,
|
|
"epoch": 0.20546081277213352,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004998513329525038,
|
|
"loss": 5.8761,
|
|
"mean_token_accuracy": 0.14128366410732268,
|
|
"num_tokens": 4685995.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 6.009013843536377,
|
|
"epoch": 0.2059143686502177,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998501545937066,
|
|
"loss": 5.908,
|
|
"mean_token_accuracy": 0.13695503398776054,
|
|
"num_tokens": 4696659.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 5.840634775161743,
|
|
"epoch": 0.20636792452830188,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000499848971584951,
|
|
"loss": 5.8695,
|
|
"mean_token_accuracy": 0.14796618670225142,
|
|
"num_tokens": 4706438.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 5.9189924716949465,
|
|
"epoch": 0.20682148040638607,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004998477839262611,
|
|
"loss": 5.8764,
|
|
"mean_token_accuracy": 0.14219514206051825,
|
|
"num_tokens": 4716402.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 5.96020998954773,
|
|
"epoch": 0.20727503628447025,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000499846591617662,
|
|
"loss": 5.9719,
|
|
"mean_token_accuracy": 0.14258323535323142,
|
|
"num_tokens": 4728488.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 5.915734434127808,
|
|
"epoch": 0.20772859216255443,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004998453946591779,
|
|
"loss": 5.9794,
|
|
"mean_token_accuracy": 0.14094745591282845,
|
|
"num_tokens": 4738693.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 5.8744336605072025,
|
|
"epoch": 0.20818214804063861,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004998441930508339,
|
|
"loss": 5.8724,
|
|
"mean_token_accuracy": 0.1447533279657364,
|
|
"num_tokens": 4748895.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 5.995182752609253,
|
|
"epoch": 0.2086357039187228,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004998429867926547,
|
|
"loss": 5.9878,
|
|
"mean_token_accuracy": 0.1373719684779644,
|
|
"num_tokens": 4760135.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 6.019215488433838,
|
|
"epoch": 0.20908925979680695,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004998417758846651,
|
|
"loss": 6.0195,
|
|
"mean_token_accuracy": 0.14542822539806366,
|
|
"num_tokens": 4769935.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 6.055789279937744,
|
|
"epoch": 0.20954281567489114,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004998405603268903,
|
|
"loss": 5.9553,
|
|
"mean_token_accuracy": 0.14619530588388444,
|
|
"num_tokens": 4779520.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 5.880806922912598,
|
|
"epoch": 0.20999637155297532,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004998393401193554,
|
|
"loss": 5.8646,
|
|
"mean_token_accuracy": 0.1471490442752838,
|
|
"num_tokens": 4791256.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 5.815768003463745,
|
|
"epoch": 0.2104499274310595,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998381152620857,
|
|
"loss": 5.8248,
|
|
"mean_token_accuracy": 0.14878984093666076,
|
|
"num_tokens": 4801334.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 5.8872205257415775,
|
|
"epoch": 0.21090348330914369,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004998368857551067,
|
|
"loss": 5.8025,
|
|
"mean_token_accuracy": 0.14462457224726677,
|
|
"num_tokens": 4811361.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 5.880616140365601,
|
|
"epoch": 0.21135703918722787,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004998356515984433,
|
|
"loss": 5.8777,
|
|
"mean_token_accuracy": 0.14419098272919656,
|
|
"num_tokens": 4821190.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 5.971280717849732,
|
|
"epoch": 0.21181059506531205,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998344127921213,
|
|
"loss": 5.903,
|
|
"mean_token_accuracy": 0.14422993659973143,
|
|
"num_tokens": 4830694.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 5.846283674240112,
|
|
"epoch": 0.21226415094339623,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998331693361666,
|
|
"loss": 5.874,
|
|
"mean_token_accuracy": 0.14026885032653807,
|
|
"num_tokens": 4841344.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 5.894744539260865,
|
|
"epoch": 0.21271770682148042,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004998319212306046,
|
|
"loss": 5.8561,
|
|
"mean_token_accuracy": 0.14421792402863504,
|
|
"num_tokens": 4851161.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 5.859916687011719,
|
|
"epoch": 0.21317126269956457,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499830668475461,
|
|
"loss": 5.8403,
|
|
"mean_token_accuracy": 0.1468031883239746,
|
|
"num_tokens": 4860740.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 5.916117763519287,
|
|
"epoch": 0.21362481857764876,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000499829411070762,
|
|
"loss": 5.8851,
|
|
"mean_token_accuracy": 0.14431235790252686,
|
|
"num_tokens": 4871733.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 5.938611316680908,
|
|
"epoch": 0.21407837445573294,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004998281490165335,
|
|
"loss": 5.9215,
|
|
"mean_token_accuracy": 0.13747453391551973,
|
|
"num_tokens": 4883617.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 5.9607947826385494,
|
|
"epoch": 0.21453193033381712,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004998268823128016,
|
|
"loss": 5.8793,
|
|
"mean_token_accuracy": 0.1396989904344082,
|
|
"num_tokens": 4894519.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 5.893149185180664,
|
|
"epoch": 0.2149854862119013,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004998256109595923,
|
|
"loss": 5.8394,
|
|
"mean_token_accuracy": 0.14341802075505256,
|
|
"num_tokens": 4904965.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 5.780011129379273,
|
|
"epoch": 0.2154390420899855,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004998243349569323,
|
|
"loss": 5.7528,
|
|
"mean_token_accuracy": 0.14949761778116227,
|
|
"num_tokens": 4914618.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 5.839861011505127,
|
|
"epoch": 0.21589259796806967,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998230543048477,
|
|
"loss": 5.808,
|
|
"mean_token_accuracy": 0.14917464703321456,
|
|
"num_tokens": 4924341.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 5.833130645751953,
|
|
"epoch": 0.21634615384615385,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000499821769003365,
|
|
"loss": 5.7863,
|
|
"mean_token_accuracy": 0.14926746040582656,
|
|
"num_tokens": 4934231.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 5.826928949356079,
|
|
"epoch": 0.21679970972423804,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004998204790525109,
|
|
"loss": 5.8055,
|
|
"mean_token_accuracy": 0.1478435292840004,
|
|
"num_tokens": 4944303.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 5.877607536315918,
|
|
"epoch": 0.2172532656023222,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004998191844523119,
|
|
"loss": 5.8831,
|
|
"mean_token_accuracy": 0.1455991432070732,
|
|
"num_tokens": 4954571.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 5.891971683502197,
|
|
"epoch": 0.21770682148040638,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000499817885202795,
|
|
"loss": 5.8568,
|
|
"mean_token_accuracy": 0.14144586399197578,
|
|
"num_tokens": 4964418.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 5.854138994216919,
|
|
"epoch": 0.21816037735849056,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004998165813039869,
|
|
"loss": 5.8641,
|
|
"mean_token_accuracy": 0.13880210369825363,
|
|
"num_tokens": 4975036.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 5.882414531707764,
|
|
"epoch": 0.21861393323657474,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004998152727559145,
|
|
"loss": 5.9467,
|
|
"mean_token_accuracy": 0.1381090022623539,
|
|
"num_tokens": 4985272.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 5.958352327346802,
|
|
"epoch": 0.21906748911465893,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.000499813959558605,
|
|
"loss": 5.8973,
|
|
"mean_token_accuracy": 0.1454383596777916,
|
|
"num_tokens": 4995187.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 5.983824586868286,
|
|
"epoch": 0.2195210449927431,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004998126417120856,
|
|
"loss": 5.9346,
|
|
"mean_token_accuracy": 0.14655492603778839,
|
|
"num_tokens": 5005013.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 5.981702709197998,
|
|
"epoch": 0.2199746008708273,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004998113192163835,
|
|
"loss": 5.9514,
|
|
"mean_token_accuracy": 0.13586568385362624,
|
|
"num_tokens": 5016789.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 5.891997861862182,
|
|
"epoch": 0.22042815674891147,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000499809992071526,
|
|
"loss": 5.9075,
|
|
"mean_token_accuracy": 0.14112533405423164,
|
|
"num_tokens": 5026913.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 5.908569240570069,
|
|
"epoch": 0.22088171262699566,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004998086602775406,
|
|
"loss": 6.0077,
|
|
"mean_token_accuracy": 0.13833704516291617,
|
|
"num_tokens": 5037501.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 5.948585081100464,
|
|
"epoch": 0.2213352685050798,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004998073238344547,
|
|
"loss": 5.8537,
|
|
"mean_token_accuracy": 0.1406433142721653,
|
|
"num_tokens": 5048478.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 5.867254590988159,
|
|
"epoch": 0.221788824383164,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004998059827422962,
|
|
"loss": 5.9062,
|
|
"mean_token_accuracy": 0.13890414834022521,
|
|
"num_tokens": 5059118.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 5.970612239837647,
|
|
"epoch": 0.22224238026124818,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004998046370010926,
|
|
"loss": 5.8774,
|
|
"mean_token_accuracy": 0.14610251635313035,
|
|
"num_tokens": 5070180.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 5.825871181488037,
|
|
"epoch": 0.22269593613933236,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004998032866108718,
|
|
"loss": 5.8617,
|
|
"mean_token_accuracy": 0.1452118158340454,
|
|
"num_tokens": 5079912.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 5.963987159729004,
|
|
"epoch": 0.22314949201741655,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004998019315716618,
|
|
"loss": 5.9397,
|
|
"mean_token_accuracy": 0.143439419567585,
|
|
"num_tokens": 5090549.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 5.878372097015381,
|
|
"epoch": 0.22360304789550073,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004998005718834905,
|
|
"loss": 5.7929,
|
|
"mean_token_accuracy": 0.14878275394439697,
|
|
"num_tokens": 5100880.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 5.89096622467041,
|
|
"epoch": 0.2240566037735849,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004997992075463862,
|
|
"loss": 5.9171,
|
|
"mean_token_accuracy": 0.14251485839486122,
|
|
"num_tokens": 5111796.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 5.983297872543335,
|
|
"epoch": 0.2245101596516691,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004997978385603769,
|
|
"loss": 5.9062,
|
|
"mean_token_accuracy": 0.1443158358335495,
|
|
"num_tokens": 5123468.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 5.861389255523681,
|
|
"epoch": 0.22496371552975328,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004997964649254911,
|
|
"loss": 5.8225,
|
|
"mean_token_accuracy": 0.1483868971467018,
|
|
"num_tokens": 5132925.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 5.9410045623779295,
|
|
"epoch": 0.22541727140783743,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004997950866417572,
|
|
"loss": 5.9016,
|
|
"mean_token_accuracy": 0.14117321670055388,
|
|
"num_tokens": 5143445.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 5.899289989471436,
|
|
"epoch": 0.22587082728592162,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004997937037092034,
|
|
"loss": 5.8287,
|
|
"mean_token_accuracy": 0.14134425967931746,
|
|
"num_tokens": 5153176.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 5.919216680526733,
|
|
"epoch": 0.2263243831640058,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004997923161278587,
|
|
"loss": 5.866,
|
|
"mean_token_accuracy": 0.14413893669843675,
|
|
"num_tokens": 5162765.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 5.879088354110718,
|
|
"epoch": 0.22677793904208998,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004997909238977514,
|
|
"loss": 5.9173,
|
|
"mean_token_accuracy": 0.14777278080582618,
|
|
"num_tokens": 5173390.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 5.875536203384399,
|
|
"epoch": 0.22723149492017417,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004997895270189108,
|
|
"loss": 5.836,
|
|
"mean_token_accuracy": 0.13986415043473244,
|
|
"num_tokens": 5184212.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 5.811423492431641,
|
|
"epoch": 0.22768505079825835,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004997881254913653,
|
|
"loss": 5.8297,
|
|
"mean_token_accuracy": 0.13980135917663575,
|
|
"num_tokens": 5194311.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 5.82978572845459,
|
|
"epoch": 0.22813860667634253,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004997867193151441,
|
|
"loss": 5.8043,
|
|
"mean_token_accuracy": 0.14709037020802498,
|
|
"num_tokens": 5204708.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 5.838364934921264,
|
|
"epoch": 0.22859216255442671,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004997853084902763,
|
|
"loss": 5.8108,
|
|
"mean_token_accuracy": 0.14625583738088607,
|
|
"num_tokens": 5214566.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 5.870654010772705,
|
|
"epoch": 0.2290457184325109,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004997838930167911,
|
|
"loss": 5.8253,
|
|
"mean_token_accuracy": 0.15037785470485687,
|
|
"num_tokens": 5224762.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 5.907916641235351,
|
|
"epoch": 0.22949927431059505,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004997824728947176,
|
|
"loss": 5.8973,
|
|
"mean_token_accuracy": 0.14429675713181495,
|
|
"num_tokens": 5235146.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 5.949673509597778,
|
|
"epoch": 0.22995283018867924,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004997810481240853,
|
|
"loss": 5.8623,
|
|
"mean_token_accuracy": 0.1440894216299057,
|
|
"num_tokens": 5243867.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 5.856524896621704,
|
|
"epoch": 0.23040638606676342,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004997796187049238,
|
|
"loss": 5.7751,
|
|
"mean_token_accuracy": 0.1456816427409649,
|
|
"num_tokens": 5254279.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 5.948967504501343,
|
|
"epoch": 0.2308599419448476,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004997781846372623,
|
|
"loss": 5.8973,
|
|
"mean_token_accuracy": 0.14449210837483406,
|
|
"num_tokens": 5264769.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 5.927372407913208,
|
|
"epoch": 0.23131349782293179,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004997767459211307,
|
|
"loss": 5.8323,
|
|
"mean_token_accuracy": 0.14081402122974396,
|
|
"num_tokens": 5274291.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 5.867244148254395,
|
|
"epoch": 0.23176705370101597,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004997753025565587,
|
|
"loss": 5.7691,
|
|
"mean_token_accuracy": 0.14731070771813393,
|
|
"num_tokens": 5284366.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 5.863168334960937,
|
|
"epoch": 0.23222060957910015,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004997738545435763,
|
|
"loss": 5.8745,
|
|
"mean_token_accuracy": 0.14436920285224913,
|
|
"num_tokens": 5294494.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 5.8350911140441895,
|
|
"epoch": 0.23267416545718433,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004997724018822133,
|
|
"loss": 5.9145,
|
|
"mean_token_accuracy": 0.144419763982296,
|
|
"num_tokens": 5305606.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 5.909123945236206,
|
|
"epoch": 0.23312772133526852,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004997709445724996,
|
|
"loss": 5.8743,
|
|
"mean_token_accuracy": 0.14309675469994546,
|
|
"num_tokens": 5315677.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 5.922089576721191,
|
|
"epoch": 0.23358127721335267,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004997694826144656,
|
|
"loss": 5.9518,
|
|
"mean_token_accuracy": 0.13734646663069724,
|
|
"num_tokens": 5326453.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 5.906578445434571,
|
|
"epoch": 0.23403483309143686,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004997680160081414,
|
|
"loss": 5.834,
|
|
"mean_token_accuracy": 0.14441939890384675,
|
|
"num_tokens": 5337591.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 5.937219524383545,
|
|
"epoch": 0.23448838896952104,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004997665447535573,
|
|
"loss": 5.8398,
|
|
"mean_token_accuracy": 0.14593878537416458,
|
|
"num_tokens": 5349400.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 5.929783010482788,
|
|
"epoch": 0.23494194484760522,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004997650688507438,
|
|
"loss": 5.8162,
|
|
"mean_token_accuracy": 0.14761714413762092,
|
|
"num_tokens": 5359984.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 5.810983467102051,
|
|
"epoch": 0.2353955007256894,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004997635882997314,
|
|
"loss": 5.8885,
|
|
"mean_token_accuracy": 0.1452771820127964,
|
|
"num_tokens": 5369254.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 5.926082897186279,
|
|
"epoch": 0.2358490566037736,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004997621031005507,
|
|
"loss": 5.8331,
|
|
"mean_token_accuracy": 0.14687830135226249,
|
|
"num_tokens": 5379648.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 5.818135976791382,
|
|
"epoch": 0.23630261248185777,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004997606132532325,
|
|
"loss": 5.7848,
|
|
"mean_token_accuracy": 0.14700028523802758,
|
|
"num_tokens": 5390321.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 5.809545612335205,
|
|
"epoch": 0.23675616835994195,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004997591187578075,
|
|
"loss": 5.8338,
|
|
"mean_token_accuracy": 0.14946144074201584,
|
|
"num_tokens": 5401078.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 5.867106103897095,
|
|
"epoch": 0.23720972423802614,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004997576196143067,
|
|
"loss": 5.7905,
|
|
"mean_token_accuracy": 0.1520560935139656,
|
|
"num_tokens": 5411977.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 5.854715633392334,
|
|
"epoch": 0.2376632801161103,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000499756115822761,
|
|
"loss": 5.8082,
|
|
"mean_token_accuracy": 0.14396803379058837,
|
|
"num_tokens": 5422967.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 5.910807275772095,
|
|
"epoch": 0.23811683599419448,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004997546073832015,
|
|
"loss": 5.833,
|
|
"mean_token_accuracy": 0.1544169843196869,
|
|
"num_tokens": 5432260.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 5.849782180786133,
|
|
"epoch": 0.23857039187227866,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004997530942956595,
|
|
"loss": 5.8033,
|
|
"mean_token_accuracy": 0.14687435179948807,
|
|
"num_tokens": 5441706.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 5.882516288757325,
|
|
"epoch": 0.23902394775036284,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004997515765601662,
|
|
"loss": 5.8086,
|
|
"mean_token_accuracy": 0.15525150001049043,
|
|
"num_tokens": 5452397.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 5.856340026855468,
|
|
"epoch": 0.23947750362844702,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004997500541767531,
|
|
"loss": 5.779,
|
|
"mean_token_accuracy": 0.14695454835891725,
|
|
"num_tokens": 5463762.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 5.83820071220398,
|
|
"epoch": 0.2399310595065312,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004997485271454516,
|
|
"loss": 5.8409,
|
|
"mean_token_accuracy": 0.1390252538025379,
|
|
"num_tokens": 5474622.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 5.850206089019776,
|
|
"epoch": 0.2403846153846154,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004997469954662933,
|
|
"loss": 5.8314,
|
|
"mean_token_accuracy": 0.14660486727952957,
|
|
"num_tokens": 5484697.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 5.859882640838623,
|
|
"epoch": 0.24083817126269957,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004997454591393097,
|
|
"loss": 5.8257,
|
|
"mean_token_accuracy": 0.1425713561475277,
|
|
"num_tokens": 5496433.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 5.948536205291748,
|
|
"epoch": 0.24129172714078376,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004997439181645329,
|
|
"loss": 5.946,
|
|
"mean_token_accuracy": 0.14295659139752387,
|
|
"num_tokens": 5507917.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 5.989947938919068,
|
|
"epoch": 0.2417452830188679,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004997423725419945,
|
|
"loss": 5.9205,
|
|
"mean_token_accuracy": 0.13935526087880135,
|
|
"num_tokens": 5519159.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 5.88839020729065,
|
|
"epoch": 0.2421988388969521,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004997408222717267,
|
|
"loss": 5.8802,
|
|
"mean_token_accuracy": 0.1494501657783985,
|
|
"num_tokens": 5529180.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 5.834697914123535,
|
|
"epoch": 0.24265239477503628,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004997392673537612,
|
|
"loss": 5.7992,
|
|
"mean_token_accuracy": 0.1539318174123764,
|
|
"num_tokens": 5539363.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 5.8882616519927975,
|
|
"epoch": 0.24310595065312046,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004997377077881306,
|
|
"loss": 5.9105,
|
|
"mean_token_accuracy": 0.14342357888817786,
|
|
"num_tokens": 5549841.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 5.897100496292114,
|
|
"epoch": 0.24355950653120464,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004997361435748668,
|
|
"loss": 5.7884,
|
|
"mean_token_accuracy": 0.14797737300395966,
|
|
"num_tokens": 5560299.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 5.912242698669433,
|
|
"epoch": 0.24401306240928883,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004997345747140024,
|
|
"loss": 5.8527,
|
|
"mean_token_accuracy": 0.14805733114480973,
|
|
"num_tokens": 5571081.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 5.8140528202056885,
|
|
"epoch": 0.244466618287373,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004997330012055695,
|
|
"loss": 5.8148,
|
|
"mean_token_accuracy": 0.15010562539100647,
|
|
"num_tokens": 5581389.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 5.859999370574951,
|
|
"epoch": 0.2449201741654572,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004997314230496011,
|
|
"loss": 5.8329,
|
|
"mean_token_accuracy": 0.14136491268873214,
|
|
"num_tokens": 5592347.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 5.869523763656616,
|
|
"epoch": 0.24537373004354138,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004997298402461296,
|
|
"loss": 5.7951,
|
|
"mean_token_accuracy": 0.15069439709186555,
|
|
"num_tokens": 5603411.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 5.925837564468384,
|
|
"epoch": 0.24582728592162553,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004997282527951876,
|
|
"loss": 5.8089,
|
|
"mean_token_accuracy": 0.15103363543748854,
|
|
"num_tokens": 5614615.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 5.8883668899536135,
|
|
"epoch": 0.24628084179970972,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004997266606968081,
|
|
"loss": 5.7827,
|
|
"mean_token_accuracy": 0.1461820498108864,
|
|
"num_tokens": 5624582.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 5.759700155258178,
|
|
"epoch": 0.2467343976777939,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004997250639510241,
|
|
"loss": 5.7983,
|
|
"mean_token_accuracy": 0.14800044298171997,
|
|
"num_tokens": 5634310.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 5.890387344360351,
|
|
"epoch": 0.24718795355587808,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004997234625578684,
|
|
"loss": 5.8809,
|
|
"mean_token_accuracy": 0.14121756255626677,
|
|
"num_tokens": 5644018.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 5.869387245178222,
|
|
"epoch": 0.24764150943396226,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004997218565173742,
|
|
"loss": 5.8328,
|
|
"mean_token_accuracy": 0.14269990473985672,
|
|
"num_tokens": 5653592.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 5.918030786514282,
|
|
"epoch": 0.24809506531204645,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004997202458295748,
|
|
"loss": 5.868,
|
|
"mean_token_accuracy": 0.1497960552573204,
|
|
"num_tokens": 5662812.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 5.938170909881592,
|
|
"epoch": 0.24854862119013063,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004997186304945034,
|
|
"loss": 5.8345,
|
|
"mean_token_accuracy": 0.14251421988010407,
|
|
"num_tokens": 5672939.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 5.814105081558227,
|
|
"epoch": 0.24900217706821481,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004997170105121935,
|
|
"loss": 5.8216,
|
|
"mean_token_accuracy": 0.14442233145236968,
|
|
"num_tokens": 5683350.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 5.970436525344849,
|
|
"epoch": 0.249455732946299,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004997153858826786,
|
|
"loss": 5.9116,
|
|
"mean_token_accuracy": 0.14313025623559952,
|
|
"num_tokens": 5694516.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 5.86408429145813,
|
|
"epoch": 0.24990928882438315,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004997137566059922,
|
|
"loss": 5.7443,
|
|
"mean_token_accuracy": 0.15340098589658738,
|
|
"num_tokens": 5705443.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 5.797891855239868,
|
|
"epoch": 0.25036284470246734,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004997121226821681,
|
|
"loss": 5.8459,
|
|
"mean_token_accuracy": 0.14177675023674965,
|
|
"num_tokens": 5715933.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 5.9241045951843265,
|
|
"epoch": 0.25081640058055155,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00049971048411124,
|
|
"loss": 5.8902,
|
|
"mean_token_accuracy": 0.14111201092600822,
|
|
"num_tokens": 5726630.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 5.972933149337768,
|
|
"epoch": 0.2512699564586357,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004997088408932418,
|
|
"loss": 5.8228,
|
|
"mean_token_accuracy": 0.14817024320363997,
|
|
"num_tokens": 5736890.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 5.754113483428955,
|
|
"epoch": 0.25172351233671986,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004997071930282076,
|
|
"loss": 5.7587,
|
|
"mean_token_accuracy": 0.1547361731529236,
|
|
"num_tokens": 5747042.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 5.825574254989624,
|
|
"epoch": 0.25217706821480407,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004997055405161712,
|
|
"loss": 5.8655,
|
|
"mean_token_accuracy": 0.1438675545156002,
|
|
"num_tokens": 5757367.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 5.959324026107788,
|
|
"epoch": 0.2526306240928882,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004997038833571671,
|
|
"loss": 5.9387,
|
|
"mean_token_accuracy": 0.14031409472227097,
|
|
"num_tokens": 5769557.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 5.897234869003296,
|
|
"epoch": 0.25308417997097243,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004997022215512295,
|
|
"loss": 5.8122,
|
|
"mean_token_accuracy": 0.15133150815963745,
|
|
"num_tokens": 5780615.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 5.852604007720947,
|
|
"epoch": 0.2535377358490566,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004997005550983925,
|
|
"loss": 5.7948,
|
|
"mean_token_accuracy": 0.14928770214319229,
|
|
"num_tokens": 5791271.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 5.822273206710816,
|
|
"epoch": 0.2539912917271408,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.000499698883998691,
|
|
"loss": 5.7444,
|
|
"mean_token_accuracy": 0.15246350467205047,
|
|
"num_tokens": 5801117.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 5.823004579544067,
|
|
"epoch": 0.25444484760522496,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004996972082521591,
|
|
"loss": 5.7649,
|
|
"mean_token_accuracy": 0.15054019093513488,
|
|
"num_tokens": 5811696.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 5.84231653213501,
|
|
"epoch": 0.25489840348330917,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004996955278588319,
|
|
"loss": 5.8063,
|
|
"mean_token_accuracy": 0.15581155121326445,
|
|
"num_tokens": 5822207.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 5.750502443313598,
|
|
"epoch": 0.2553519593613933,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004996938428187437,
|
|
"loss": 5.7558,
|
|
"mean_token_accuracy": 0.15488317459821702,
|
|
"num_tokens": 5831927.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 5.871583747863769,
|
|
"epoch": 0.2558055152394775,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004996921531319297,
|
|
"loss": 5.8142,
|
|
"mean_token_accuracy": 0.1495785243809223,
|
|
"num_tokens": 5842093.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 5.852832698822022,
|
|
"epoch": 0.2562590711175617,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004996904587984246,
|
|
"loss": 5.7355,
|
|
"mean_token_accuracy": 0.15692816227674483,
|
|
"num_tokens": 5850551.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 5.794354200363159,
|
|
"epoch": 0.25671262699564584,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004996887598182636,
|
|
"loss": 5.7362,
|
|
"mean_token_accuracy": 0.1481923684477806,
|
|
"num_tokens": 5860651.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 5.777127456665039,
|
|
"epoch": 0.25716618287373005,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004996870561914819,
|
|
"loss": 5.7259,
|
|
"mean_token_accuracy": 0.14743045717477798,
|
|
"num_tokens": 5871500.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 5.849510860443115,
|
|
"epoch": 0.2576197387518142,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004996853479181145,
|
|
"loss": 5.7273,
|
|
"mean_token_accuracy": 0.1445586636662483,
|
|
"num_tokens": 5881523.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 5.877736568450928,
|
|
"epoch": 0.2580732946298984,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004996836349981969,
|
|
"loss": 5.8806,
|
|
"mean_token_accuracy": 0.14388025403022767,
|
|
"num_tokens": 5891162.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 5.786015796661377,
|
|
"epoch": 0.2585268505079826,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004996819174317645,
|
|
"loss": 5.7689,
|
|
"mean_token_accuracy": 0.14543924555182458,
|
|
"num_tokens": 5901818.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 5.901238822937012,
|
|
"epoch": 0.2589804063860668,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004996801952188528,
|
|
"loss": 5.8677,
|
|
"mean_token_accuracy": 0.14473312646150588,
|
|
"num_tokens": 5913889.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 5.870723915100098,
|
|
"epoch": 0.25943396226415094,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004996784683594973,
|
|
"loss": 5.8056,
|
|
"mean_token_accuracy": 0.15123703628778457,
|
|
"num_tokens": 5923429.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 5.918413352966309,
|
|
"epoch": 0.2598875181422351,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004996767368537338,
|
|
"loss": 5.8483,
|
|
"mean_token_accuracy": 0.14715803265571595,
|
|
"num_tokens": 5933847.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 5.805452156066894,
|
|
"epoch": 0.2603410740203193,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004996750007015983,
|
|
"loss": 5.7376,
|
|
"mean_token_accuracy": 0.14590465426445007,
|
|
"num_tokens": 5943874.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 5.8460094928741455,
|
|
"epoch": 0.26079462989840346,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004996732599031264,
|
|
"loss": 5.7988,
|
|
"mean_token_accuracy": 0.14883473068475722,
|
|
"num_tokens": 5953653.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 5.866086196899414,
|
|
"epoch": 0.2612481857764877,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004996715144583543,
|
|
"loss": 5.7492,
|
|
"mean_token_accuracy": 0.15125548392534255,
|
|
"num_tokens": 5964039.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 5.892557859420776,
|
|
"epoch": 0.26170174165457183,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.000499669764367318,
|
|
"loss": 5.877,
|
|
"mean_token_accuracy": 0.14600060135126114,
|
|
"num_tokens": 5974083.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 5.818076229095459,
|
|
"epoch": 0.26215529753265604,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004996680096300537,
|
|
"loss": 5.8153,
|
|
"mean_token_accuracy": 0.14445886462926866,
|
|
"num_tokens": 5984629.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 5.754880905151367,
|
|
"epoch": 0.2626088534107402,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004996662502465978,
|
|
"loss": 5.7222,
|
|
"mean_token_accuracy": 0.15813563466072084,
|
|
"num_tokens": 5994295.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 5.811830186843872,
|
|
"epoch": 0.2630624092888244,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004996644862169864,
|
|
"loss": 5.7687,
|
|
"mean_token_accuracy": 0.14370385855436324,
|
|
"num_tokens": 6004156.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 5.8295127868652346,
|
|
"epoch": 0.26351596516690856,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004996627175412563,
|
|
"loss": 5.8448,
|
|
"mean_token_accuracy": 0.14985169619321823,
|
|
"num_tokens": 6014188.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 5.921795082092285,
|
|
"epoch": 0.2639695210449927,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.000499660944219444,
|
|
"loss": 5.906,
|
|
"mean_token_accuracy": 0.14295441657304764,
|
|
"num_tokens": 6024879.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 5.9418816566467285,
|
|
"epoch": 0.2644230769230769,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004996591662515861,
|
|
"loss": 5.9623,
|
|
"mean_token_accuracy": 0.14250990375876427,
|
|
"num_tokens": 6036374.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 5.917361497879028,
|
|
"epoch": 0.2648766328011611,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004996573836377193,
|
|
"loss": 5.8081,
|
|
"mean_token_accuracy": 0.1467065617442131,
|
|
"num_tokens": 6046432.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 5.907295179367066,
|
|
"epoch": 0.2653301886792453,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004996555963778806,
|
|
"loss": 5.8192,
|
|
"mean_token_accuracy": 0.14340163618326188,
|
|
"num_tokens": 6056864.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 5.953917980194092,
|
|
"epoch": 0.26578374455732945,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.000499653804472107,
|
|
"loss": 5.8473,
|
|
"mean_token_accuracy": 0.15042725205421448,
|
|
"num_tokens": 6067294.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 5.882991552352905,
|
|
"epoch": 0.26623730043541366,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004996520079204353,
|
|
"loss": 5.85,
|
|
"mean_token_accuracy": 0.14360335022211074,
|
|
"num_tokens": 6077587.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 5.867487525939941,
|
|
"epoch": 0.2666908563134978,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.000499650206722903,
|
|
"loss": 5.8125,
|
|
"mean_token_accuracy": 0.14450383931398392,
|
|
"num_tokens": 6089306.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 5.856965208053589,
|
|
"epoch": 0.267144412191582,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004996484008795471,
|
|
"loss": 5.7564,
|
|
"mean_token_accuracy": 0.14599506705999374,
|
|
"num_tokens": 6099651.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 5.834507179260254,
|
|
"epoch": 0.2675979680696662,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.000499646590390405,
|
|
"loss": 5.7657,
|
|
"mean_token_accuracy": 0.14419298321008683,
|
|
"num_tokens": 6110063.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 5.830401659011841,
|
|
"epoch": 0.26805152394775034,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004996447752555142,
|
|
"loss": 5.7865,
|
|
"mean_token_accuracy": 0.14656304121017455,
|
|
"num_tokens": 6120031.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 5.829970359802246,
|
|
"epoch": 0.26850507982583455,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004996429554749122,
|
|
"loss": 5.8324,
|
|
"mean_token_accuracy": 0.14829770997166633,
|
|
"num_tokens": 6131274.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 5.936783218383789,
|
|
"epoch": 0.2689586357039187,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004996411310486367,
|
|
"loss": 5.8788,
|
|
"mean_token_accuracy": 0.14855986982584,
|
|
"num_tokens": 6140878.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 5.949974441528321,
|
|
"epoch": 0.2694121915820029,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004996393019767253,
|
|
"loss": 5.879,
|
|
"mean_token_accuracy": 0.13954189866781236,
|
|
"num_tokens": 6152229.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 5.824478960037231,
|
|
"epoch": 0.26986574746008707,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004996374682592158,
|
|
"loss": 5.7744,
|
|
"mean_token_accuracy": 0.1475573480129242,
|
|
"num_tokens": 6162311.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 5.901595211029052,
|
|
"epoch": 0.2703193033381713,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004996356298961463,
|
|
"loss": 5.8833,
|
|
"mean_token_accuracy": 0.14554917365312575,
|
|
"num_tokens": 6172806.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 5.908715009689331,
|
|
"epoch": 0.27077285921625543,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004996337868875549,
|
|
"loss": 5.8448,
|
|
"mean_token_accuracy": 0.14733956456184388,
|
|
"num_tokens": 6183479.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 5.861931991577149,
|
|
"epoch": 0.27122641509433965,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004996319392334792,
|
|
"loss": 5.8176,
|
|
"mean_token_accuracy": 0.14184632897377014,
|
|
"num_tokens": 6194201.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 5.795678424835205,
|
|
"epoch": 0.2716799709724238,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.000499630086933958,
|
|
"loss": 5.7641,
|
|
"mean_token_accuracy": 0.1457250237464905,
|
|
"num_tokens": 6204774.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 5.849139070510864,
|
|
"epoch": 0.27213352685050796,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004996282299890292,
|
|
"loss": 5.7696,
|
|
"mean_token_accuracy": 0.14415498152375222,
|
|
"num_tokens": 6215056.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.27213352685050796,
|
|
"eval_entropy": 5.725370093816006,
|
|
"eval_loss": 5.846706390380859,
|
|
"eval_mean_token_accuracy": 0.15213655662465825,
|
|
"eval_num_tokens": 6215056.0,
|
|
"eval_runtime": 26.8622,
|
|
"eval_samples_per_second": 1316.349,
|
|
"eval_steps_per_second": 164.544,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"entropy": 5.905508375167846,
|
|
"epoch": 0.27258708272859217,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004996263683987316,
|
|
"loss": 5.8742,
|
|
"mean_token_accuracy": 0.14993443191051484,
|
|
"num_tokens": 6226264.0,
|
|
"step": 3005
|
|
},
|
|
{
|
|
"entropy": 5.872657299041748,
|
|
"epoch": 0.2730406386066763,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004996245021631033,
|
|
"loss": 5.7841,
|
|
"mean_token_accuracy": 0.14555028602480888,
|
|
"num_tokens": 6235137.0,
|
|
"step": 3010
|
|
},
|
|
{
|
|
"entropy": 5.804933309555054,
|
|
"epoch": 0.27349419448476053,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.000499622631282183,
|
|
"loss": 5.8043,
|
|
"mean_token_accuracy": 0.14663855880498886,
|
|
"num_tokens": 6245411.0,
|
|
"step": 3015
|
|
},
|
|
{
|
|
"entropy": 5.824642276763916,
|
|
"epoch": 0.2739477503628447,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004996207557560095,
|
|
"loss": 5.8782,
|
|
"mean_token_accuracy": 0.1400340422987938,
|
|
"num_tokens": 6255633.0,
|
|
"step": 3020
|
|
},
|
|
{
|
|
"entropy": 5.924058246612549,
|
|
"epoch": 0.2744013062409289,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004996188755846216,
|
|
"loss": 5.821,
|
|
"mean_token_accuracy": 0.14444293826818466,
|
|
"num_tokens": 6265109.0,
|
|
"step": 3025
|
|
},
|
|
{
|
|
"entropy": 5.900212144851684,
|
|
"epoch": 0.27485486211901305,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.000499616990768058,
|
|
"loss": 5.8635,
|
|
"mean_token_accuracy": 0.14477069228887557,
|
|
"num_tokens": 6275241.0,
|
|
"step": 3030
|
|
},
|
|
{
|
|
"entropy": 5.914565849304199,
|
|
"epoch": 0.27530841799709727,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004996151013063579,
|
|
"loss": 5.9067,
|
|
"mean_token_accuracy": 0.13996558040380477,
|
|
"num_tokens": 6286603.0,
|
|
"step": 3035
|
|
},
|
|
{
|
|
"entropy": 5.87188949584961,
|
|
"epoch": 0.2757619738751814,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004996132071995601,
|
|
"loss": 5.7703,
|
|
"mean_token_accuracy": 0.1570067062973976,
|
|
"num_tokens": 6297219.0,
|
|
"step": 3040
|
|
},
|
|
{
|
|
"entropy": 5.8587874412536625,
|
|
"epoch": 0.2762155297532656,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004996113084477042,
|
|
"loss": 5.8165,
|
|
"mean_token_accuracy": 0.15096617713570595,
|
|
"num_tokens": 6307694.0,
|
|
"step": 3045
|
|
},
|
|
{
|
|
"entropy": 5.857360363006592,
|
|
"epoch": 0.2766690856313498,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004996094050508291,
|
|
"loss": 5.7446,
|
|
"mean_token_accuracy": 0.1507061928510666,
|
|
"num_tokens": 6317384.0,
|
|
"step": 3050
|
|
},
|
|
{
|
|
"entropy": 5.88347978591919,
|
|
"epoch": 0.27712264150943394,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004996074970089741,
|
|
"loss": 5.8684,
|
|
"mean_token_accuracy": 0.1453227236866951,
|
|
"num_tokens": 6327558.0,
|
|
"step": 3055
|
|
},
|
|
{
|
|
"entropy": 5.903385925292969,
|
|
"epoch": 0.27757619738751815,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.0004996055843221789,
|
|
"loss": 5.733,
|
|
"mean_token_accuracy": 0.15211346447467805,
|
|
"num_tokens": 6337828.0,
|
|
"step": 3060
|
|
},
|
|
{
|
|
"entropy": 5.817547464370728,
|
|
"epoch": 0.2780297532656023,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004996036669904831,
|
|
"loss": 5.796,
|
|
"mean_token_accuracy": 0.1491447240114212,
|
|
"num_tokens": 6348678.0,
|
|
"step": 3065
|
|
},
|
|
{
|
|
"entropy": 5.855010223388672,
|
|
"epoch": 0.2784833091436865,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004996017450139261,
|
|
"loss": 5.8856,
|
|
"mean_token_accuracy": 0.13843294233083725,
|
|
"num_tokens": 6359670.0,
|
|
"step": 3070
|
|
},
|
|
{
|
|
"entropy": 5.939880132675171,
|
|
"epoch": 0.2789368650217707,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004995998183925478,
|
|
"loss": 5.8442,
|
|
"mean_token_accuracy": 0.14635261446237563,
|
|
"num_tokens": 6371034.0,
|
|
"step": 3075
|
|
},
|
|
{
|
|
"entropy": 5.86761474609375,
|
|
"epoch": 0.2793904208998549,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004995978871263881,
|
|
"loss": 5.7823,
|
|
"mean_token_accuracy": 0.15000314861536027,
|
|
"num_tokens": 6380672.0,
|
|
"step": 3080
|
|
},
|
|
{
|
|
"entropy": 5.839673566818237,
|
|
"epoch": 0.27984397677793904,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004995959512154868,
|
|
"loss": 5.8882,
|
|
"mean_token_accuracy": 0.1362109065055847,
|
|
"num_tokens": 6390799.0,
|
|
"step": 3085
|
|
},
|
|
{
|
|
"entropy": 5.879818630218506,
|
|
"epoch": 0.2802975326560232,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.000499594010659884,
|
|
"loss": 5.7542,
|
|
"mean_token_accuracy": 0.14788413494825364,
|
|
"num_tokens": 6400965.0,
|
|
"step": 3090
|
|
},
|
|
{
|
|
"entropy": 5.896807670593262,
|
|
"epoch": 0.2807510885341074,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004995920654596199,
|
|
"loss": 5.7929,
|
|
"mean_token_accuracy": 0.14485295563936235,
|
|
"num_tokens": 6411567.0,
|
|
"step": 3095
|
|
},
|
|
{
|
|
"entropy": 5.884419775009155,
|
|
"epoch": 0.28120464441219156,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004995901156147345,
|
|
"loss": 5.8379,
|
|
"mean_token_accuracy": 0.15128903090953827,
|
|
"num_tokens": 6421193.0,
|
|
"step": 3100
|
|
},
|
|
{
|
|
"entropy": 5.8871454238891605,
|
|
"epoch": 0.2816582002902758,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004995881611252684,
|
|
"loss": 5.8437,
|
|
"mean_token_accuracy": 0.14912686347961426,
|
|
"num_tokens": 6430281.0,
|
|
"step": 3105
|
|
},
|
|
{
|
|
"entropy": 5.873918056488037,
|
|
"epoch": 0.28211175616835993,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004995862019912619,
|
|
"loss": 5.8482,
|
|
"mean_token_accuracy": 0.139264590293169,
|
|
"num_tokens": 6441055.0,
|
|
"step": 3110
|
|
},
|
|
{
|
|
"entropy": 5.8297398567199705,
|
|
"epoch": 0.28256531204644414,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004995842382127555,
|
|
"loss": 5.7594,
|
|
"mean_token_accuracy": 0.14350441247224807,
|
|
"num_tokens": 6451082.0,
|
|
"step": 3115
|
|
},
|
|
{
|
|
"entropy": 5.855344438552857,
|
|
"epoch": 0.2830188679245283,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004995822697897897,
|
|
"loss": 5.8585,
|
|
"mean_token_accuracy": 0.14142778068780898,
|
|
"num_tokens": 6461617.0,
|
|
"step": 3120
|
|
},
|
|
{
|
|
"entropy": 5.966115283966064,
|
|
"epoch": 0.2834724238026125,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004995802967224056,
|
|
"loss": 5.8475,
|
|
"mean_token_accuracy": 0.14636234045028687,
|
|
"num_tokens": 6472780.0,
|
|
"step": 3125
|
|
},
|
|
{
|
|
"entropy": 5.809420013427735,
|
|
"epoch": 0.28392597968069666,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004995783190106434,
|
|
"loss": 5.7486,
|
|
"mean_token_accuracy": 0.1427581399679184,
|
|
"num_tokens": 6484078.0,
|
|
"step": 3130
|
|
},
|
|
{
|
|
"entropy": 5.916213893890381,
|
|
"epoch": 0.2843795355587808,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004995763366545445,
|
|
"loss": 5.8466,
|
|
"mean_token_accuracy": 0.14371495842933654,
|
|
"num_tokens": 6494366.0,
|
|
"step": 3135
|
|
},
|
|
{
|
|
"entropy": 5.791625833511352,
|
|
"epoch": 0.284833091436865,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004995743496541497,
|
|
"loss": 5.8035,
|
|
"mean_token_accuracy": 0.15003674924373628,
|
|
"num_tokens": 6505461.0,
|
|
"step": 3140
|
|
},
|
|
{
|
|
"entropy": 5.825983953475952,
|
|
"epoch": 0.2852866473149492,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004995723580095001,
|
|
"loss": 5.7958,
|
|
"mean_token_accuracy": 0.15073160082101822,
|
|
"num_tokens": 6516141.0,
|
|
"step": 3145
|
|
},
|
|
{
|
|
"entropy": 5.8044600009918215,
|
|
"epoch": 0.2857402031930334,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.000499570361720637,
|
|
"loss": 5.7816,
|
|
"mean_token_accuracy": 0.14948485642671586,
|
|
"num_tokens": 6525536.0,
|
|
"step": 3150
|
|
},
|
|
{
|
|
"entropy": 5.8823357105255125,
|
|
"epoch": 0.28619375907111755,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004995683607876015,
|
|
"loss": 5.8401,
|
|
"mean_token_accuracy": 0.1408316560089588,
|
|
"num_tokens": 6535852.0,
|
|
"step": 3155
|
|
},
|
|
{
|
|
"entropy": 5.944931507110596,
|
|
"epoch": 0.28664731494920176,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004995663552104352,
|
|
"loss": 5.8303,
|
|
"mean_token_accuracy": 0.14839636236429216,
|
|
"num_tokens": 6546353.0,
|
|
"step": 3160
|
|
},
|
|
{
|
|
"entropy": 5.803114652633667,
|
|
"epoch": 0.2871008708272859,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004995643449891793,
|
|
"loss": 5.7719,
|
|
"mean_token_accuracy": 0.1433407634496689,
|
|
"num_tokens": 6557782.0,
|
|
"step": 3165
|
|
},
|
|
{
|
|
"entropy": 5.86722617149353,
|
|
"epoch": 0.2875544267053701,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004995623301238757,
|
|
"loss": 5.7925,
|
|
"mean_token_accuracy": 0.1488977774977684,
|
|
"num_tokens": 6568100.0,
|
|
"step": 3170
|
|
},
|
|
{
|
|
"entropy": 5.907700634002685,
|
|
"epoch": 0.2880079825834543,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004995603106145657,
|
|
"loss": 5.8455,
|
|
"mean_token_accuracy": 0.14495818465948104,
|
|
"num_tokens": 6578698.0,
|
|
"step": 3175
|
|
},
|
|
{
|
|
"entropy": 5.845079708099365,
|
|
"epoch": 0.28846153846153844,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004995582864612913,
|
|
"loss": 5.829,
|
|
"mean_token_accuracy": 0.14225727319717407,
|
|
"num_tokens": 6588908.0,
|
|
"step": 3180
|
|
},
|
|
{
|
|
"entropy": 5.81000714302063,
|
|
"epoch": 0.28891509433962265,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004995562576640943,
|
|
"loss": 5.6816,
|
|
"mean_token_accuracy": 0.1479066714644432,
|
|
"num_tokens": 6599445.0,
|
|
"step": 3185
|
|
},
|
|
{
|
|
"entropy": 5.873440742492676,
|
|
"epoch": 0.2893686502177068,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004995542242230167,
|
|
"loss": 5.7901,
|
|
"mean_token_accuracy": 0.14480070844292642,
|
|
"num_tokens": 6610246.0,
|
|
"step": 3190
|
|
},
|
|
{
|
|
"entropy": 5.8062098026275635,
|
|
"epoch": 0.289822206095791,
|
|
"grad_norm": 2.84375,
|
|
"learning_rate": 0.0004995521861381006,
|
|
"loss": 5.7896,
|
|
"mean_token_accuracy": 0.1486334338784218,
|
|
"num_tokens": 6620501.0,
|
|
"step": 3195
|
|
},
|
|
{
|
|
"entropy": 6.001724576950073,
|
|
"epoch": 0.29027576197387517,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.000499550143409388,
|
|
"loss": 5.8694,
|
|
"mean_token_accuracy": 0.13826330080628396,
|
|
"num_tokens": 6631206.0,
|
|
"step": 3200
|
|
},
|
|
{
|
|
"entropy": 5.822874259948731,
|
|
"epoch": 0.2907293178519594,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004995480960369211,
|
|
"loss": 5.803,
|
|
"mean_token_accuracy": 0.14362403452396394,
|
|
"num_tokens": 6641600.0,
|
|
"step": 3205
|
|
},
|
|
{
|
|
"entropy": 5.847076559066773,
|
|
"epoch": 0.29118287373004353,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004995460440207425,
|
|
"loss": 5.8789,
|
|
"mean_token_accuracy": 0.13984269350767137,
|
|
"num_tokens": 6652319.0,
|
|
"step": 3210
|
|
},
|
|
{
|
|
"entropy": 5.926595544815063,
|
|
"epoch": 0.29163642960812775,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004995439873608945,
|
|
"loss": 5.8209,
|
|
"mean_token_accuracy": 0.13916896730661393,
|
|
"num_tokens": 6663702.0,
|
|
"step": 3215
|
|
},
|
|
{
|
|
"entropy": 5.832406425476075,
|
|
"epoch": 0.2920899854862119,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004995419260574196,
|
|
"loss": 5.7932,
|
|
"mean_token_accuracy": 0.14231335520744323,
|
|
"num_tokens": 6673908.0,
|
|
"step": 3220
|
|
},
|
|
{
|
|
"entropy": 5.786562442779541,
|
|
"epoch": 0.29254354136429606,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004995398601103603,
|
|
"loss": 5.8235,
|
|
"mean_token_accuracy": 0.14949814826250077,
|
|
"num_tokens": 6683237.0,
|
|
"step": 3225
|
|
},
|
|
{
|
|
"entropy": 5.869636964797974,
|
|
"epoch": 0.29299709724238027,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004995377895197597,
|
|
"loss": 5.7685,
|
|
"mean_token_accuracy": 0.1467011883854866,
|
|
"num_tokens": 6693451.0,
|
|
"step": 3230
|
|
},
|
|
{
|
|
"entropy": 5.8066086769104,
|
|
"epoch": 0.2934506531204644,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004995357142856602,
|
|
"loss": 5.7103,
|
|
"mean_token_accuracy": 0.14754725396633148,
|
|
"num_tokens": 6703479.0,
|
|
"step": 3235
|
|
},
|
|
{
|
|
"entropy": 5.785593414306641,
|
|
"epoch": 0.29390420899854863,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.000499533634408105,
|
|
"loss": 5.722,
|
|
"mean_token_accuracy": 0.15292183309793472,
|
|
"num_tokens": 6715321.0,
|
|
"step": 3240
|
|
},
|
|
{
|
|
"entropy": 5.8156593322753904,
|
|
"epoch": 0.2943577648766328,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.000499531549887137,
|
|
"loss": 5.7658,
|
|
"mean_token_accuracy": 0.14359535425901412,
|
|
"num_tokens": 6725541.0,
|
|
"step": 3245
|
|
},
|
|
{
|
|
"entropy": 5.82113208770752,
|
|
"epoch": 0.294811320754717,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004995294607227993,
|
|
"loss": 5.8205,
|
|
"mean_token_accuracy": 0.15142790526151656,
|
|
"num_tokens": 6735165.0,
|
|
"step": 3250
|
|
},
|
|
{
|
|
"entropy": 5.913179206848144,
|
|
"epoch": 0.29526487663280115,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004995273669151351,
|
|
"loss": 5.8263,
|
|
"mean_token_accuracy": 0.1507417544722557,
|
|
"num_tokens": 6744245.0,
|
|
"step": 3255
|
|
},
|
|
{
|
|
"entropy": 5.818991231918335,
|
|
"epoch": 0.29571843251088537,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.000499525268464188,
|
|
"loss": 5.7806,
|
|
"mean_token_accuracy": 0.14803050607442855,
|
|
"num_tokens": 6754894.0,
|
|
"step": 3260
|
|
},
|
|
{
|
|
"entropy": 5.822706174850464,
|
|
"epoch": 0.2961719883889695,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004995231653700009,
|
|
"loss": 5.8398,
|
|
"mean_token_accuracy": 0.13901015520095825,
|
|
"num_tokens": 6764442.0,
|
|
"step": 3265
|
|
},
|
|
{
|
|
"entropy": 5.904806232452392,
|
|
"epoch": 0.2966255442670537,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004995210576326176,
|
|
"loss": 5.8025,
|
|
"mean_token_accuracy": 0.14261318892240524,
|
|
"num_tokens": 6775054.0,
|
|
"step": 3270
|
|
},
|
|
{
|
|
"entropy": 5.842242336273193,
|
|
"epoch": 0.2970791001451379,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004995189452520816,
|
|
"loss": 5.7562,
|
|
"mean_token_accuracy": 0.1599966213107109,
|
|
"num_tokens": 6784825.0,
|
|
"step": 3275
|
|
},
|
|
{
|
|
"entropy": 5.856751728057861,
|
|
"epoch": 0.29753265602322204,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004995168282284366,
|
|
"loss": 5.8218,
|
|
"mean_token_accuracy": 0.14728388488292693,
|
|
"num_tokens": 6795928.0,
|
|
"step": 3280
|
|
},
|
|
{
|
|
"entropy": 5.783289575576783,
|
|
"epoch": 0.29798621190130625,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004995147065617263,
|
|
"loss": 5.7394,
|
|
"mean_token_accuracy": 0.14838822185993195,
|
|
"num_tokens": 6805456.0,
|
|
"step": 3285
|
|
},
|
|
{
|
|
"entropy": 5.89187536239624,
|
|
"epoch": 0.2984397677793904,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004995125802519946,
|
|
"loss": 5.8327,
|
|
"mean_token_accuracy": 0.14377516657114028,
|
|
"num_tokens": 6816215.0,
|
|
"step": 3290
|
|
},
|
|
{
|
|
"entropy": 5.943170499801636,
|
|
"epoch": 0.2988933236574746,
|
|
"grad_norm": 3.015625,
|
|
"learning_rate": 0.0004995104492992857,
|
|
"loss": 5.8535,
|
|
"mean_token_accuracy": 0.14646795988082886,
|
|
"num_tokens": 6826545.0,
|
|
"step": 3295
|
|
},
|
|
{
|
|
"entropy": 5.759806346893311,
|
|
"epoch": 0.2993468795355588,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004995083137036434,
|
|
"loss": 5.7702,
|
|
"mean_token_accuracy": 0.14964656680822372,
|
|
"num_tokens": 6836184.0,
|
|
"step": 3300
|
|
},
|
|
{
|
|
"entropy": 5.910308742523194,
|
|
"epoch": 0.299800435413643,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004995061734651121,
|
|
"loss": 5.8488,
|
|
"mean_token_accuracy": 0.14388236552476882,
|
|
"num_tokens": 6846646.0,
|
|
"step": 3305
|
|
},
|
|
{
|
|
"entropy": 5.911490964889526,
|
|
"epoch": 0.30025399129172714,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004995040285837358,
|
|
"loss": 5.7612,
|
|
"mean_token_accuracy": 0.15329435765743255,
|
|
"num_tokens": 6857597.0,
|
|
"step": 3310
|
|
},
|
|
{
|
|
"entropy": 5.85549144744873,
|
|
"epoch": 0.3007075471698113,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004995018790595589,
|
|
"loss": 5.854,
|
|
"mean_token_accuracy": 0.14282366782426834,
|
|
"num_tokens": 6867523.0,
|
|
"step": 3315
|
|
},
|
|
{
|
|
"entropy": 5.91640453338623,
|
|
"epoch": 0.3011611030478955,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004994997248926261,
|
|
"loss": 5.946,
|
|
"mean_token_accuracy": 0.14262509644031524,
|
|
"num_tokens": 6878190.0,
|
|
"step": 3320
|
|
},
|
|
{
|
|
"entropy": 5.903401231765747,
|
|
"epoch": 0.30161465892597966,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004994975660829817,
|
|
"loss": 5.7563,
|
|
"mean_token_accuracy": 0.1535111017525196,
|
|
"num_tokens": 6888483.0,
|
|
"step": 3325
|
|
},
|
|
{
|
|
"entropy": 5.83467206954956,
|
|
"epoch": 0.3020682148040639,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004994954026306705,
|
|
"loss": 5.7374,
|
|
"mean_token_accuracy": 0.14736103788018226,
|
|
"num_tokens": 6898337.0,
|
|
"step": 3330
|
|
},
|
|
{
|
|
"entropy": 5.88395357131958,
|
|
"epoch": 0.30252177068214803,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004994932345357371,
|
|
"loss": 5.8065,
|
|
"mean_token_accuracy": 0.14424017667770386,
|
|
"num_tokens": 6909131.0,
|
|
"step": 3335
|
|
},
|
|
{
|
|
"entropy": 5.859859037399292,
|
|
"epoch": 0.30297532656023224,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004994910617982264,
|
|
"loss": 5.7906,
|
|
"mean_token_accuracy": 0.14290710389614106,
|
|
"num_tokens": 6919790.0,
|
|
"step": 3340
|
|
},
|
|
{
|
|
"entropy": 5.829497575759888,
|
|
"epoch": 0.3034288824383164,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004994888844181833,
|
|
"loss": 5.8129,
|
|
"mean_token_accuracy": 0.14728963971138,
|
|
"num_tokens": 6930072.0,
|
|
"step": 3345
|
|
},
|
|
{
|
|
"entropy": 5.788367462158203,
|
|
"epoch": 0.3038824383164006,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004994867023956529,
|
|
"loss": 5.707,
|
|
"mean_token_accuracy": 0.14217354729771614,
|
|
"num_tokens": 6940646.0,
|
|
"step": 3350
|
|
},
|
|
{
|
|
"entropy": 5.819201564788818,
|
|
"epoch": 0.30433599419448476,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004994845157306803,
|
|
"loss": 5.7089,
|
|
"mean_token_accuracy": 0.1530962035059929,
|
|
"num_tokens": 6951645.0,
|
|
"step": 3355
|
|
},
|
|
{
|
|
"entropy": 5.88507342338562,
|
|
"epoch": 0.3047895500725689,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004994823244233107,
|
|
"loss": 5.8611,
|
|
"mean_token_accuracy": 0.14595605432987213,
|
|
"num_tokens": 6963020.0,
|
|
"step": 3360
|
|
},
|
|
{
|
|
"entropy": 5.900927877426147,
|
|
"epoch": 0.3052431059506531,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004994801284735895,
|
|
"loss": 5.7878,
|
|
"mean_token_accuracy": 0.15086106210947037,
|
|
"num_tokens": 6972895.0,
|
|
"step": 3365
|
|
},
|
|
{
|
|
"entropy": 5.894740104675293,
|
|
"epoch": 0.3056966618287373,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004994779278815619,
|
|
"loss": 5.9297,
|
|
"mean_token_accuracy": 0.13789867609739304,
|
|
"num_tokens": 6985363.0,
|
|
"step": 3370
|
|
},
|
|
{
|
|
"entropy": 5.9384606838226315,
|
|
"epoch": 0.3061502177068215,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004994757226472736,
|
|
"loss": 5.8593,
|
|
"mean_token_accuracy": 0.1438434675335884,
|
|
"num_tokens": 6997040.0,
|
|
"step": 3375
|
|
},
|
|
{
|
|
"entropy": 5.856701517105103,
|
|
"epoch": 0.30660377358490565,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004994735127707702,
|
|
"loss": 5.7905,
|
|
"mean_token_accuracy": 0.1451782375574112,
|
|
"num_tokens": 7007591.0,
|
|
"step": 3380
|
|
},
|
|
{
|
|
"entropy": 5.88822865486145,
|
|
"epoch": 0.30705732946298986,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004994712982520972,
|
|
"loss": 5.7923,
|
|
"mean_token_accuracy": 0.15586419701576232,
|
|
"num_tokens": 7017858.0,
|
|
"step": 3385
|
|
},
|
|
{
|
|
"entropy": 5.770430278778076,
|
|
"epoch": 0.307510885341074,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004994690790913008,
|
|
"loss": 5.7643,
|
|
"mean_token_accuracy": 0.148378449678421,
|
|
"num_tokens": 7027365.0,
|
|
"step": 3390
|
|
},
|
|
{
|
|
"entropy": 5.80420503616333,
|
|
"epoch": 0.3079644412191582,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004994668552884265,
|
|
"loss": 5.7623,
|
|
"mean_token_accuracy": 0.14726244360208512,
|
|
"num_tokens": 7038728.0,
|
|
"step": 3395
|
|
},
|
|
{
|
|
"entropy": 5.905961561203003,
|
|
"epoch": 0.3084179970972424,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004994646268435204,
|
|
"loss": 5.7059,
|
|
"mean_token_accuracy": 0.1534990206360817,
|
|
"num_tokens": 7048736.0,
|
|
"step": 3400
|
|
},
|
|
{
|
|
"entropy": 5.824774742126465,
|
|
"epoch": 0.30887155297532654,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004994623937566286,
|
|
"loss": 5.8291,
|
|
"mean_token_accuracy": 0.14722448736429214,
|
|
"num_tokens": 7059205.0,
|
|
"step": 3405
|
|
},
|
|
{
|
|
"entropy": 5.819243335723877,
|
|
"epoch": 0.30932510885341075,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004994601560277974,
|
|
"loss": 5.839,
|
|
"mean_token_accuracy": 0.1430293306708336,
|
|
"num_tokens": 7069513.0,
|
|
"step": 3410
|
|
},
|
|
{
|
|
"entropy": 5.857053995132446,
|
|
"epoch": 0.3097786647314949,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.000499457913657073,
|
|
"loss": 5.75,
|
|
"mean_token_accuracy": 0.14733252078294753,
|
|
"num_tokens": 7079940.0,
|
|
"step": 3415
|
|
},
|
|
{
|
|
"entropy": 5.85497088432312,
|
|
"epoch": 0.3102322206095791,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004994556666445016,
|
|
"loss": 5.7543,
|
|
"mean_token_accuracy": 0.14875707179307937,
|
|
"num_tokens": 7090792.0,
|
|
"step": 3420
|
|
},
|
|
{
|
|
"entropy": 5.770295095443726,
|
|
"epoch": 0.31068577648766327,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004994534149901299,
|
|
"loss": 5.6985,
|
|
"mean_token_accuracy": 0.1492018073797226,
|
|
"num_tokens": 7101964.0,
|
|
"step": 3425
|
|
},
|
|
{
|
|
"entropy": 5.804609155654907,
|
|
"epoch": 0.3111393323657475,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004994511586940044,
|
|
"loss": 5.774,
|
|
"mean_token_accuracy": 0.14447008967399597,
|
|
"num_tokens": 7113332.0,
|
|
"step": 3430
|
|
},
|
|
{
|
|
"entropy": 5.976766204833984,
|
|
"epoch": 0.31159288824383163,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004994488977561717,
|
|
"loss": 5.9305,
|
|
"mean_token_accuracy": 0.14386181086301802,
|
|
"num_tokens": 7123481.0,
|
|
"step": 3435
|
|
},
|
|
{
|
|
"entropy": 5.814102554321289,
|
|
"epoch": 0.31204644412191584,
|
|
"grad_norm": 4.09375,
|
|
"learning_rate": 0.0004994466321766786,
|
|
"loss": 5.6934,
|
|
"mean_token_accuracy": 0.15259597599506378,
|
|
"num_tokens": 7133694.0,
|
|
"step": 3440
|
|
},
|
|
{
|
|
"entropy": 5.8040472030639645,
|
|
"epoch": 0.3125,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.000499444361955572,
|
|
"loss": 5.8344,
|
|
"mean_token_accuracy": 0.1501459300518036,
|
|
"num_tokens": 7144491.0,
|
|
"step": 3445
|
|
},
|
|
{
|
|
"entropy": 6.012900972366333,
|
|
"epoch": 0.31295355587808416,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004994420870928988,
|
|
"loss": 5.8826,
|
|
"mean_token_accuracy": 0.1436660721898079,
|
|
"num_tokens": 7154716.0,
|
|
"step": 3450
|
|
},
|
|
{
|
|
"entropy": 5.904228782653808,
|
|
"epoch": 0.31340711175616837,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004994398075887059,
|
|
"loss": 5.8806,
|
|
"mean_token_accuracy": 0.14098595678806305,
|
|
"num_tokens": 7164258.0,
|
|
"step": 3455
|
|
},
|
|
{
|
|
"entropy": 5.848430109024048,
|
|
"epoch": 0.3138606676342525,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004994375234430407,
|
|
"loss": 5.745,
|
|
"mean_token_accuracy": 0.14507319629192353,
|
|
"num_tokens": 7175098.0,
|
|
"step": 3460
|
|
},
|
|
{
|
|
"entropy": 5.868549537658692,
|
|
"epoch": 0.31431422351233673,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004994352346559504,
|
|
"loss": 5.8168,
|
|
"mean_token_accuracy": 0.1449630543589592,
|
|
"num_tokens": 7186480.0,
|
|
"step": 3465
|
|
},
|
|
{
|
|
"entropy": 5.788954830169677,
|
|
"epoch": 0.3147677793904209,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004994329412274821,
|
|
"loss": 5.7886,
|
|
"mean_token_accuracy": 0.1490990549325943,
|
|
"num_tokens": 7197056.0,
|
|
"step": 3470
|
|
},
|
|
{
|
|
"entropy": 5.904733800888062,
|
|
"epoch": 0.3152213352685051,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004994306431576835,
|
|
"loss": 5.9056,
|
|
"mean_token_accuracy": 0.1437280908226967,
|
|
"num_tokens": 7206040.0,
|
|
"step": 3475
|
|
},
|
|
{
|
|
"entropy": 5.937067651748658,
|
|
"epoch": 0.31567489114658925,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000499428340446602,
|
|
"loss": 5.7542,
|
|
"mean_token_accuracy": 0.1492527186870575,
|
|
"num_tokens": 7216344.0,
|
|
"step": 3480
|
|
},
|
|
{
|
|
"entropy": 5.88311448097229,
|
|
"epoch": 0.31612844702467346,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004994260330942851,
|
|
"loss": 5.8348,
|
|
"mean_token_accuracy": 0.14428199976682662,
|
|
"num_tokens": 7226729.0,
|
|
"step": 3485
|
|
},
|
|
{
|
|
"entropy": 5.773128843307495,
|
|
"epoch": 0.3165820029027576,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004994237211007808,
|
|
"loss": 5.7887,
|
|
"mean_token_accuracy": 0.14559608250856398,
|
|
"num_tokens": 7237616.0,
|
|
"step": 3490
|
|
},
|
|
{
|
|
"entropy": 5.857798624038696,
|
|
"epoch": 0.3170355587808418,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004994214044661367,
|
|
"loss": 5.7252,
|
|
"mean_token_accuracy": 0.1498093731701374,
|
|
"num_tokens": 7247857.0,
|
|
"step": 3495
|
|
},
|
|
{
|
|
"entropy": 5.719632959365844,
|
|
"epoch": 0.317489114658926,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004994190831904007,
|
|
"loss": 5.688,
|
|
"mean_token_accuracy": 0.15702230781316756,
|
|
"num_tokens": 7257858.0,
|
|
"step": 3500
|
|
},
|
|
{
|
|
"entropy": 5.65029010772705,
|
|
"epoch": 0.31794267053701014,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.000499416757273621,
|
|
"loss": 5.6898,
|
|
"mean_token_accuracy": 0.15247652679681778,
|
|
"num_tokens": 7268440.0,
|
|
"step": 3505
|
|
},
|
|
{
|
|
"entropy": 5.920102977752686,
|
|
"epoch": 0.31839622641509435,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004994144267158454,
|
|
"loss": 5.7827,
|
|
"mean_token_accuracy": 0.1534908801317215,
|
|
"num_tokens": 7278560.0,
|
|
"step": 3510
|
|
},
|
|
{
|
|
"entropy": 5.888502550125122,
|
|
"epoch": 0.3188497822931785,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004994120915171224,
|
|
"loss": 5.7946,
|
|
"mean_token_accuracy": 0.14598636478185653,
|
|
"num_tokens": 7288422.0,
|
|
"step": 3515
|
|
},
|
|
{
|
|
"entropy": 5.87982177734375,
|
|
"epoch": 0.3193033381712627,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004994097516775002,
|
|
"loss": 5.8287,
|
|
"mean_token_accuracy": 0.14544341266155242,
|
|
"num_tokens": 7298613.0,
|
|
"step": 3520
|
|
},
|
|
{
|
|
"entropy": 5.874675273895264,
|
|
"epoch": 0.3197568940493469,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004994074071970271,
|
|
"loss": 5.8742,
|
|
"mean_token_accuracy": 0.1415143169462681,
|
|
"num_tokens": 7309509.0,
|
|
"step": 3525
|
|
},
|
|
{
|
|
"entropy": 5.883598661422729,
|
|
"epoch": 0.3202104499274311,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004994050580757515,
|
|
"loss": 5.7807,
|
|
"mean_token_accuracy": 0.14771121591329575,
|
|
"num_tokens": 7319015.0,
|
|
"step": 3530
|
|
},
|
|
{
|
|
"entropy": 5.7930444240570065,
|
|
"epoch": 0.32066400580551524,
|
|
"grad_norm": 3.65625,
|
|
"learning_rate": 0.0004994027043137223,
|
|
"loss": 5.7605,
|
|
"mean_token_accuracy": 0.15096884369850158,
|
|
"num_tokens": 7329026.0,
|
|
"step": 3535
|
|
},
|
|
{
|
|
"entropy": 5.928781509399414,
|
|
"epoch": 0.3211175616835994,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004994003459109879,
|
|
"loss": 5.8383,
|
|
"mean_token_accuracy": 0.14945371747016906,
|
|
"num_tokens": 7339638.0,
|
|
"step": 3540
|
|
},
|
|
{
|
|
"entropy": 5.856835460662841,
|
|
"epoch": 0.3215711175616836,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004993979828675972,
|
|
"loss": 5.7468,
|
|
"mean_token_accuracy": 0.15235433876514434,
|
|
"num_tokens": 7349979.0,
|
|
"step": 3545
|
|
},
|
|
{
|
|
"entropy": 5.739511013031006,
|
|
"epoch": 0.32202467343976776,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.000499395615183599,
|
|
"loss": 5.6826,
|
|
"mean_token_accuracy": 0.1585940971970558,
|
|
"num_tokens": 7359398.0,
|
|
"step": 3550
|
|
},
|
|
{
|
|
"entropy": 5.767411756515503,
|
|
"epoch": 0.32247822931785197,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004993932428590422,
|
|
"loss": 5.7347,
|
|
"mean_token_accuracy": 0.14846241772174834,
|
|
"num_tokens": 7370418.0,
|
|
"step": 3555
|
|
},
|
|
{
|
|
"entropy": 5.858153820037842,
|
|
"epoch": 0.3229317851959361,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004993908658939762,
|
|
"loss": 5.7541,
|
|
"mean_token_accuracy": 0.1416775479912758,
|
|
"num_tokens": 7380461.0,
|
|
"step": 3560
|
|
},
|
|
{
|
|
"entropy": 5.848527336120606,
|
|
"epoch": 0.32338534107402034,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004993884842884496,
|
|
"loss": 5.7846,
|
|
"mean_token_accuracy": 0.14853670224547386,
|
|
"num_tokens": 7390646.0,
|
|
"step": 3565
|
|
},
|
|
{
|
|
"entropy": 5.840066242218017,
|
|
"epoch": 0.3238388969521045,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004993860980425121,
|
|
"loss": 5.8707,
|
|
"mean_token_accuracy": 0.14578727930784224,
|
|
"num_tokens": 7402106.0,
|
|
"step": 3570
|
|
},
|
|
{
|
|
"entropy": 5.859009647369385,
|
|
"epoch": 0.3242924528301887,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004993837071562131,
|
|
"loss": 5.86,
|
|
"mean_token_accuracy": 0.1438901849091053,
|
|
"num_tokens": 7412936.0,
|
|
"step": 3575
|
|
},
|
|
{
|
|
"entropy": 5.876029348373413,
|
|
"epoch": 0.32474600870827286,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004993813116296017,
|
|
"loss": 5.7174,
|
|
"mean_token_accuracy": 0.15487630516290665,
|
|
"num_tokens": 7422303.0,
|
|
"step": 3580
|
|
},
|
|
{
|
|
"entropy": 5.815586090087891,
|
|
"epoch": 0.325199564586357,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004993789114627275,
|
|
"loss": 5.7829,
|
|
"mean_token_accuracy": 0.14683734625577927,
|
|
"num_tokens": 7432829.0,
|
|
"step": 3585
|
|
},
|
|
{
|
|
"entropy": 5.8798154354095455,
|
|
"epoch": 0.3256531204644412,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004993765066556403,
|
|
"loss": 5.8139,
|
|
"mean_token_accuracy": 0.1471313163638115,
|
|
"num_tokens": 7443218.0,
|
|
"step": 3590
|
|
},
|
|
{
|
|
"entropy": 5.878670930862427,
|
|
"epoch": 0.3261066763425254,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004993740972083899,
|
|
"loss": 5.7585,
|
|
"mean_token_accuracy": 0.14762550145387648,
|
|
"num_tokens": 7454531.0,
|
|
"step": 3595
|
|
},
|
|
{
|
|
"entropy": 5.842435550689697,
|
|
"epoch": 0.3265602322206096,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004993716831210259,
|
|
"loss": 5.819,
|
|
"mean_token_accuracy": 0.14858943670988084,
|
|
"num_tokens": 7464993.0,
|
|
"step": 3600
|
|
},
|
|
{
|
|
"entropy": 5.836248922348022,
|
|
"epoch": 0.32701378809869375,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004993692643935983,
|
|
"loss": 5.8484,
|
|
"mean_token_accuracy": 0.14623567909002305,
|
|
"num_tokens": 7475755.0,
|
|
"step": 3605
|
|
},
|
|
{
|
|
"entropy": 5.869288301467895,
|
|
"epoch": 0.32746734397677796,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004993668410261571,
|
|
"loss": 5.8342,
|
|
"mean_token_accuracy": 0.14813216850161554,
|
|
"num_tokens": 7486778.0,
|
|
"step": 3610
|
|
},
|
|
{
|
|
"entropy": 5.928134870529175,
|
|
"epoch": 0.3279208998548621,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004993644130187525,
|
|
"loss": 5.8186,
|
|
"mean_token_accuracy": 0.14781841933727263,
|
|
"num_tokens": 7497439.0,
|
|
"step": 3615
|
|
},
|
|
{
|
|
"entropy": 5.862684679031372,
|
|
"epoch": 0.3283744557329463,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004993619803714347,
|
|
"loss": 5.8521,
|
|
"mean_token_accuracy": 0.14881017282605172,
|
|
"num_tokens": 7508274.0,
|
|
"step": 3620
|
|
},
|
|
{
|
|
"entropy": 5.91369595527649,
|
|
"epoch": 0.3288280116110305,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004993595430842539,
|
|
"loss": 5.8215,
|
|
"mean_token_accuracy": 0.14630042612552643,
|
|
"num_tokens": 7519315.0,
|
|
"step": 3625
|
|
},
|
|
{
|
|
"entropy": 5.955614137649536,
|
|
"epoch": 0.32928156748911463,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004993571011572606,
|
|
"loss": 5.8233,
|
|
"mean_token_accuracy": 0.14899712055921555,
|
|
"num_tokens": 7529910.0,
|
|
"step": 3630
|
|
},
|
|
{
|
|
"entropy": 5.791502332687378,
|
|
"epoch": 0.32973512336719885,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004993546545905053,
|
|
"loss": 5.7414,
|
|
"mean_token_accuracy": 0.15022289454936982,
|
|
"num_tokens": 7538966.0,
|
|
"step": 3635
|
|
},
|
|
{
|
|
"entropy": 5.87908525466919,
|
|
"epoch": 0.330188679245283,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004993522033840386,
|
|
"loss": 5.7835,
|
|
"mean_token_accuracy": 0.14871595650911332,
|
|
"num_tokens": 7549683.0,
|
|
"step": 3640
|
|
},
|
|
{
|
|
"entropy": 5.7719274997711185,
|
|
"epoch": 0.3306422351233672,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000499349747537911,
|
|
"loss": 5.7657,
|
|
"mean_token_accuracy": 0.1503421112895012,
|
|
"num_tokens": 7560629.0,
|
|
"step": 3645
|
|
},
|
|
{
|
|
"entropy": 5.821841669082642,
|
|
"epoch": 0.33109579100145137,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004993472870521736,
|
|
"loss": 5.7092,
|
|
"mean_token_accuracy": 0.15626542568206786,
|
|
"num_tokens": 7570613.0,
|
|
"step": 3650
|
|
},
|
|
{
|
|
"entropy": 5.8016807556152346,
|
|
"epoch": 0.3315493468795356,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004993448219268771,
|
|
"loss": 5.6923,
|
|
"mean_token_accuracy": 0.14716383442282677,
|
|
"num_tokens": 7580640.0,
|
|
"step": 3655
|
|
},
|
|
{
|
|
"entropy": 5.802517318725586,
|
|
"epoch": 0.33200290275761973,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004993423521620726,
|
|
"loss": 5.7793,
|
|
"mean_token_accuracy": 0.14909568727016448,
|
|
"num_tokens": 7590164.0,
|
|
"step": 3660
|
|
},
|
|
{
|
|
"entropy": 5.9077465534210205,
|
|
"epoch": 0.33245645863570394,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004993398777578109,
|
|
"loss": 5.8267,
|
|
"mean_token_accuracy": 0.14484120905399323,
|
|
"num_tokens": 7600173.0,
|
|
"step": 3665
|
|
},
|
|
{
|
|
"entropy": 5.806748008728027,
|
|
"epoch": 0.3329100145137881,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004993373987141435,
|
|
"loss": 5.6382,
|
|
"mean_token_accuracy": 0.1568427190184593,
|
|
"num_tokens": 7609958.0,
|
|
"step": 3670
|
|
},
|
|
{
|
|
"entropy": 5.874347925186157,
|
|
"epoch": 0.33336357039187225,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004993349150311214,
|
|
"loss": 5.7765,
|
|
"mean_token_accuracy": 0.14990526288747788,
|
|
"num_tokens": 7620237.0,
|
|
"step": 3675
|
|
},
|
|
{
|
|
"entropy": 5.73986234664917,
|
|
"epoch": 0.33381712626995647,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004993324267087962,
|
|
"loss": 5.6779,
|
|
"mean_token_accuracy": 0.15874082297086717,
|
|
"num_tokens": 7629886.0,
|
|
"step": 3680
|
|
},
|
|
{
|
|
"entropy": 5.78931999206543,
|
|
"epoch": 0.3342706821480406,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004993299337472192,
|
|
"loss": 5.7604,
|
|
"mean_token_accuracy": 0.15158218294382095,
|
|
"num_tokens": 7640057.0,
|
|
"step": 3685
|
|
},
|
|
{
|
|
"entropy": 5.79057207107544,
|
|
"epoch": 0.33472423802612483,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.000499327436146442,
|
|
"loss": 5.6948,
|
|
"mean_token_accuracy": 0.14951762855052947,
|
|
"num_tokens": 7649766.0,
|
|
"step": 3690
|
|
},
|
|
{
|
|
"entropy": 5.817282056808471,
|
|
"epoch": 0.335177793904209,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004993249339065162,
|
|
"loss": 5.7712,
|
|
"mean_token_accuracy": 0.15388251468539238,
|
|
"num_tokens": 7660890.0,
|
|
"step": 3695
|
|
},
|
|
{
|
|
"entropy": 5.87283844947815,
|
|
"epoch": 0.3356313497822932,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004993224270274937,
|
|
"loss": 5.7946,
|
|
"mean_token_accuracy": 0.14841417819261551,
|
|
"num_tokens": 7670737.0,
|
|
"step": 3700
|
|
},
|
|
{
|
|
"entropy": 5.744346475601196,
|
|
"epoch": 0.33608490566037735,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004993199155094263,
|
|
"loss": 5.7533,
|
|
"mean_token_accuracy": 0.14859601408243178,
|
|
"num_tokens": 7681407.0,
|
|
"step": 3705
|
|
},
|
|
{
|
|
"entropy": 5.775976657867432,
|
|
"epoch": 0.33653846153846156,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004993173993523658,
|
|
"loss": 5.6882,
|
|
"mean_token_accuracy": 0.15778839737176895,
|
|
"num_tokens": 7691758.0,
|
|
"step": 3710
|
|
},
|
|
{
|
|
"entropy": 5.817459774017334,
|
|
"epoch": 0.3369920174165457,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004993148785563643,
|
|
"loss": 5.7122,
|
|
"mean_token_accuracy": 0.153327476978302,
|
|
"num_tokens": 7702934.0,
|
|
"step": 3715
|
|
},
|
|
{
|
|
"entropy": 5.7213376522064205,
|
|
"epoch": 0.3374455732946299,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000499312353121474,
|
|
"loss": 5.7154,
|
|
"mean_token_accuracy": 0.14955039769411088,
|
|
"num_tokens": 7713001.0,
|
|
"step": 3720
|
|
},
|
|
{
|
|
"entropy": 5.843008708953858,
|
|
"epoch": 0.3378991291727141,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004993098230477471,
|
|
"loss": 5.7729,
|
|
"mean_token_accuracy": 0.14066959023475648,
|
|
"num_tokens": 7724005.0,
|
|
"step": 3725
|
|
},
|
|
{
|
|
"entropy": 5.86332745552063,
|
|
"epoch": 0.33835268505079824,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004993072883352358,
|
|
"loss": 5.7307,
|
|
"mean_token_accuracy": 0.14685281068086625,
|
|
"num_tokens": 7733743.0,
|
|
"step": 3730
|
|
},
|
|
{
|
|
"entropy": 5.855350208282471,
|
|
"epoch": 0.33880624092888245,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004993047489839927,
|
|
"loss": 5.9077,
|
|
"mean_token_accuracy": 0.1421743795275688,
|
|
"num_tokens": 7743762.0,
|
|
"step": 3735
|
|
},
|
|
{
|
|
"entropy": 5.921744632720947,
|
|
"epoch": 0.3392597968069666,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004993022049940702,
|
|
"loss": 5.8021,
|
|
"mean_token_accuracy": 0.15184042006731033,
|
|
"num_tokens": 7753758.0,
|
|
"step": 3740
|
|
},
|
|
{
|
|
"entropy": 5.794305658340454,
|
|
"epoch": 0.3397133526850508,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004992996563655209,
|
|
"loss": 5.7383,
|
|
"mean_token_accuracy": 0.14835357964038848,
|
|
"num_tokens": 7764692.0,
|
|
"step": 3745
|
|
},
|
|
{
|
|
"entropy": 5.811636686325073,
|
|
"epoch": 0.340166908563135,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004992971030983975,
|
|
"loss": 5.7867,
|
|
"mean_token_accuracy": 0.147117081284523,
|
|
"num_tokens": 7776892.0,
|
|
"step": 3750
|
|
},
|
|
{
|
|
"entropy": 5.941185331344604,
|
|
"epoch": 0.3406204644412192,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004992945451927531,
|
|
"loss": 5.8453,
|
|
"mean_token_accuracy": 0.1420529529452324,
|
|
"num_tokens": 7787143.0,
|
|
"step": 3755
|
|
},
|
|
{
|
|
"entropy": 5.799036169052124,
|
|
"epoch": 0.34107402031930334,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004992919826486402,
|
|
"loss": 5.7395,
|
|
"mean_token_accuracy": 0.14718473628163337,
|
|
"num_tokens": 7798537.0,
|
|
"step": 3760
|
|
},
|
|
{
|
|
"entropy": 5.7314859390258786,
|
|
"epoch": 0.3415275761973875,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004992894154661118,
|
|
"loss": 5.7224,
|
|
"mean_token_accuracy": 0.15050877258181572,
|
|
"num_tokens": 7808434.0,
|
|
"step": 3765
|
|
},
|
|
{
|
|
"entropy": 5.784837865829468,
|
|
"epoch": 0.3419811320754717,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004992868436452213,
|
|
"loss": 5.8353,
|
|
"mean_token_accuracy": 0.14429779648780822,
|
|
"num_tokens": 7819592.0,
|
|
"step": 3770
|
|
},
|
|
{
|
|
"entropy": 5.885675477981567,
|
|
"epoch": 0.34243468795355586,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004992842671860217,
|
|
"loss": 5.7091,
|
|
"mean_token_accuracy": 0.15716975629329683,
|
|
"num_tokens": 7830602.0,
|
|
"step": 3775
|
|
},
|
|
{
|
|
"entropy": 5.8570620059967045,
|
|
"epoch": 0.34288824383164007,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004992816860885662,
|
|
"loss": 5.8617,
|
|
"mean_token_accuracy": 0.14727574586868286,
|
|
"num_tokens": 7840850.0,
|
|
"step": 3780
|
|
},
|
|
{
|
|
"entropy": 5.939270067214966,
|
|
"epoch": 0.3433417997097242,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004992791003529084,
|
|
"loss": 5.8267,
|
|
"mean_token_accuracy": 0.1436672791838646,
|
|
"num_tokens": 7852371.0,
|
|
"step": 3785
|
|
},
|
|
{
|
|
"entropy": 5.835111427307129,
|
|
"epoch": 0.34379535558780844,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004992765099791017,
|
|
"loss": 5.8251,
|
|
"mean_token_accuracy": 0.14049971401691436,
|
|
"num_tokens": 7863290.0,
|
|
"step": 3790
|
|
},
|
|
{
|
|
"entropy": 5.752039957046509,
|
|
"epoch": 0.3442489114658926,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004992739149671995,
|
|
"loss": 5.6612,
|
|
"mean_token_accuracy": 0.15343843773007393,
|
|
"num_tokens": 7873927.0,
|
|
"step": 3795
|
|
},
|
|
{
|
|
"entropy": 5.78824667930603,
|
|
"epoch": 0.3447024673439768,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004992713153172556,
|
|
"loss": 5.7247,
|
|
"mean_token_accuracy": 0.1494988791644573,
|
|
"num_tokens": 7884977.0,
|
|
"step": 3800
|
|
},
|
|
{
|
|
"entropy": 5.708825397491455,
|
|
"epoch": 0.34515602322206096,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004992687110293238,
|
|
"loss": 5.7795,
|
|
"mean_token_accuracy": 0.1571035400032997,
|
|
"num_tokens": 7894620.0,
|
|
"step": 3805
|
|
},
|
|
{
|
|
"entropy": 5.795299863815307,
|
|
"epoch": 0.3456095791001451,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004992661021034579,
|
|
"loss": 5.721,
|
|
"mean_token_accuracy": 0.15556821525096892,
|
|
"num_tokens": 7904541.0,
|
|
"step": 3810
|
|
},
|
|
{
|
|
"entropy": 5.81929988861084,
|
|
"epoch": 0.3460631349782293,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004992634885397118,
|
|
"loss": 5.7389,
|
|
"mean_token_accuracy": 0.15238524973392487,
|
|
"num_tokens": 7915435.0,
|
|
"step": 3815
|
|
},
|
|
{
|
|
"entropy": 5.8006524562835695,
|
|
"epoch": 0.3465166908563135,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004992608703381396,
|
|
"loss": 5.722,
|
|
"mean_token_accuracy": 0.15279221534729004,
|
|
"num_tokens": 7925870.0,
|
|
"step": 3820
|
|
},
|
|
{
|
|
"entropy": 5.812300109863282,
|
|
"epoch": 0.3469702467343977,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004992582474987955,
|
|
"loss": 5.7162,
|
|
"mean_token_accuracy": 0.1484467327594757,
|
|
"num_tokens": 7937046.0,
|
|
"step": 3825
|
|
},
|
|
{
|
|
"entropy": 5.721387004852295,
|
|
"epoch": 0.34742380261248185,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004992556200217337,
|
|
"loss": 5.6744,
|
|
"mean_token_accuracy": 0.14899658560752868,
|
|
"num_tokens": 7947150.0,
|
|
"step": 3830
|
|
},
|
|
{
|
|
"entropy": 5.799996328353882,
|
|
"epoch": 0.34787735849056606,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004992529879070085,
|
|
"loss": 5.7708,
|
|
"mean_token_accuracy": 0.15342669039964676,
|
|
"num_tokens": 7956815.0,
|
|
"step": 3835
|
|
},
|
|
{
|
|
"entropy": 5.85635929107666,
|
|
"epoch": 0.3483309143686502,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004992503511546745,
|
|
"loss": 5.7991,
|
|
"mean_token_accuracy": 0.1478790670633316,
|
|
"num_tokens": 7968114.0,
|
|
"step": 3840
|
|
},
|
|
{
|
|
"entropy": 5.853620481491089,
|
|
"epoch": 0.3487844702467344,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004992477097647859,
|
|
"loss": 5.7294,
|
|
"mean_token_accuracy": 0.14952304363250732,
|
|
"num_tokens": 7977840.0,
|
|
"step": 3845
|
|
},
|
|
{
|
|
"entropy": 5.873941707611084,
|
|
"epoch": 0.3492380261248186,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004992450637373976,
|
|
"loss": 5.8523,
|
|
"mean_token_accuracy": 0.15121273100376129,
|
|
"num_tokens": 7988663.0,
|
|
"step": 3850
|
|
},
|
|
{
|
|
"entropy": 5.7464821338653564,
|
|
"epoch": 0.34969158200290273,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004992424130725642,
|
|
"loss": 5.6591,
|
|
"mean_token_accuracy": 0.1479647561907768,
|
|
"num_tokens": 7999693.0,
|
|
"step": 3855
|
|
},
|
|
{
|
|
"entropy": 5.874104356765747,
|
|
"epoch": 0.35014513788098695,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004992397577703406,
|
|
"loss": 5.8291,
|
|
"mean_token_accuracy": 0.14254632443189622,
|
|
"num_tokens": 8010154.0,
|
|
"step": 3860
|
|
},
|
|
{
|
|
"entropy": 5.892876815795899,
|
|
"epoch": 0.3505986937590711,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004992370978307816,
|
|
"loss": 5.8091,
|
|
"mean_token_accuracy": 0.14753764420747756,
|
|
"num_tokens": 8020921.0,
|
|
"step": 3865
|
|
},
|
|
{
|
|
"entropy": 5.79165678024292,
|
|
"epoch": 0.3510522496371553,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004992344332539424,
|
|
"loss": 5.7381,
|
|
"mean_token_accuracy": 0.15288853794336318,
|
|
"num_tokens": 8031404.0,
|
|
"step": 3870
|
|
},
|
|
{
|
|
"entropy": 5.772537279129028,
|
|
"epoch": 0.35150580551523947,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004992317640398779,
|
|
"loss": 5.7453,
|
|
"mean_token_accuracy": 0.15194570422172546,
|
|
"num_tokens": 8041310.0,
|
|
"step": 3875
|
|
},
|
|
{
|
|
"entropy": 5.790036058425903,
|
|
"epoch": 0.3519593613933237,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004992290901886434,
|
|
"loss": 5.7096,
|
|
"mean_token_accuracy": 0.15084798410534858,
|
|
"num_tokens": 8051054.0,
|
|
"step": 3880
|
|
},
|
|
{
|
|
"entropy": 5.789835023880005,
|
|
"epoch": 0.35241291727140783,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.000499226411700294,
|
|
"loss": 5.7134,
|
|
"mean_token_accuracy": 0.15393220782279968,
|
|
"num_tokens": 8061063.0,
|
|
"step": 3885
|
|
},
|
|
{
|
|
"entropy": 5.797818565368653,
|
|
"epoch": 0.35286647314949204,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004992237285748855,
|
|
"loss": 5.7305,
|
|
"mean_token_accuracy": 0.15079212784767151,
|
|
"num_tokens": 8071715.0,
|
|
"step": 3890
|
|
},
|
|
{
|
|
"entropy": 5.9086751461029055,
|
|
"epoch": 0.3533200290275762,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004992210408124731,
|
|
"loss": 5.806,
|
|
"mean_token_accuracy": 0.14620591923594475,
|
|
"num_tokens": 8082679.0,
|
|
"step": 3895
|
|
},
|
|
{
|
|
"entropy": 5.804943513870239,
|
|
"epoch": 0.35377358490566035,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004992183484131123,
|
|
"loss": 5.8262,
|
|
"mean_token_accuracy": 0.14822732135653496,
|
|
"num_tokens": 8093785.0,
|
|
"step": 3900
|
|
},
|
|
{
|
|
"entropy": 5.772074508666992,
|
|
"epoch": 0.35422714078374457,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004992156513768591,
|
|
"loss": 5.7145,
|
|
"mean_token_accuracy": 0.15389340221881867,
|
|
"num_tokens": 8105822.0,
|
|
"step": 3905
|
|
},
|
|
{
|
|
"entropy": 5.795384550094605,
|
|
"epoch": 0.3546806966618287,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.000499212949703769,
|
|
"loss": 5.6463,
|
|
"mean_token_accuracy": 0.15382388085126877,
|
|
"num_tokens": 8115521.0,
|
|
"step": 3910
|
|
},
|
|
{
|
|
"entropy": 5.807135534286499,
|
|
"epoch": 0.35513425253991293,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004992102433938981,
|
|
"loss": 5.7466,
|
|
"mean_token_accuracy": 0.15025942102074624,
|
|
"num_tokens": 8125524.0,
|
|
"step": 3915
|
|
},
|
|
{
|
|
"entropy": 5.7783197402954105,
|
|
"epoch": 0.3555878084179971,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004992075324473021,
|
|
"loss": 5.6313,
|
|
"mean_token_accuracy": 0.16174003332853318,
|
|
"num_tokens": 8135552.0,
|
|
"step": 3920
|
|
},
|
|
{
|
|
"entropy": 5.7959658145904545,
|
|
"epoch": 0.3560413642960813,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004992048168640371,
|
|
"loss": 5.7601,
|
|
"mean_token_accuracy": 0.15194501876831054,
|
|
"num_tokens": 8145617.0,
|
|
"step": 3925
|
|
},
|
|
{
|
|
"entropy": 5.798158788681031,
|
|
"epoch": 0.35649492017416545,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004992020966441595,
|
|
"loss": 5.7931,
|
|
"mean_token_accuracy": 0.14742157012224197,
|
|
"num_tokens": 8156729.0,
|
|
"step": 3930
|
|
},
|
|
{
|
|
"entropy": 5.819314575195312,
|
|
"epoch": 0.35694847605224966,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004991993717877254,
|
|
"loss": 5.7603,
|
|
"mean_token_accuracy": 0.14829237759113312,
|
|
"num_tokens": 8167637.0,
|
|
"step": 3935
|
|
},
|
|
{
|
|
"entropy": 5.80439453125,
|
|
"epoch": 0.3574020319303338,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004991966422947911,
|
|
"loss": 5.7588,
|
|
"mean_token_accuracy": 0.1592489078640938,
|
|
"num_tokens": 8177354.0,
|
|
"step": 3940
|
|
},
|
|
{
|
|
"entropy": 5.746254396438599,
|
|
"epoch": 0.357855587808418,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004991939081654132,
|
|
"loss": 5.6822,
|
|
"mean_token_accuracy": 0.16436415165662766,
|
|
"num_tokens": 8187580.0,
|
|
"step": 3945
|
|
},
|
|
{
|
|
"entropy": 5.760440444946289,
|
|
"epoch": 0.3583091436865022,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.000499191169399648,
|
|
"loss": 5.796,
|
|
"mean_token_accuracy": 0.14408852458000182,
|
|
"num_tokens": 8199382.0,
|
|
"step": 3950
|
|
},
|
|
{
|
|
"entropy": 5.797565078735351,
|
|
"epoch": 0.35876269956458634,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004991884259975525,
|
|
"loss": 5.693,
|
|
"mean_token_accuracy": 0.15424915179610252,
|
|
"num_tokens": 8208484.0,
|
|
"step": 3955
|
|
},
|
|
{
|
|
"entropy": 5.83342866897583,
|
|
"epoch": 0.35921625544267055,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.000499185677959183,
|
|
"loss": 5.7418,
|
|
"mean_token_accuracy": 0.14727935642004014,
|
|
"num_tokens": 8219056.0,
|
|
"step": 3960
|
|
},
|
|
{
|
|
"entropy": 5.818744325637818,
|
|
"epoch": 0.3596698113207547,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004991829252845966,
|
|
"loss": 5.752,
|
|
"mean_token_accuracy": 0.14865149557590485,
|
|
"num_tokens": 8230149.0,
|
|
"step": 3965
|
|
},
|
|
{
|
|
"entropy": 5.77530198097229,
|
|
"epoch": 0.3601233671988389,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004991801679738502,
|
|
"loss": 5.827,
|
|
"mean_token_accuracy": 0.14391214549541473,
|
|
"num_tokens": 8240803.0,
|
|
"step": 3970
|
|
},
|
|
{
|
|
"entropy": 5.857344913482666,
|
|
"epoch": 0.3605769230769231,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004991774060270008,
|
|
"loss": 5.7787,
|
|
"mean_token_accuracy": 0.1442903220653534,
|
|
"num_tokens": 8251563.0,
|
|
"step": 3975
|
|
},
|
|
{
|
|
"entropy": 5.802289152145386,
|
|
"epoch": 0.3610304789550073,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004991746394441055,
|
|
"loss": 5.7145,
|
|
"mean_token_accuracy": 0.1495348870754242,
|
|
"num_tokens": 8261342.0,
|
|
"step": 3980
|
|
},
|
|
{
|
|
"entropy": 5.781592130661011,
|
|
"epoch": 0.36148403483309144,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004991718682252216,
|
|
"loss": 5.8175,
|
|
"mean_token_accuracy": 0.14287600964307784,
|
|
"num_tokens": 8271540.0,
|
|
"step": 3985
|
|
},
|
|
{
|
|
"entropy": 5.85759482383728,
|
|
"epoch": 0.3619375907111756,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004991690923704063,
|
|
"loss": 5.7354,
|
|
"mean_token_accuracy": 0.15011506527662277,
|
|
"num_tokens": 8280593.0,
|
|
"step": 3990
|
|
},
|
|
{
|
|
"entropy": 5.822527742385864,
|
|
"epoch": 0.3623911465892598,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004991663118797171,
|
|
"loss": 5.7578,
|
|
"mean_token_accuracy": 0.15425925850868225,
|
|
"num_tokens": 8290126.0,
|
|
"step": 3995
|
|
},
|
|
{
|
|
"entropy": 5.822154951095581,
|
|
"epoch": 0.36284470246734396,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004991635267532113,
|
|
"loss": 5.6961,
|
|
"mean_token_accuracy": 0.14956869333982467,
|
|
"num_tokens": 8301416.0,
|
|
"step": 4000
|
|
},
|
|
{
|
|
"entropy": 5.832658195495606,
|
|
"epoch": 0.36329825834542817,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004991607369909468,
|
|
"loss": 5.7754,
|
|
"mean_token_accuracy": 0.15036688297986983,
|
|
"num_tokens": 8311034.0,
|
|
"step": 4005
|
|
},
|
|
{
|
|
"entropy": 5.8005434513092045,
|
|
"epoch": 0.3637518142235123,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004991579425929811,
|
|
"loss": 5.7885,
|
|
"mean_token_accuracy": 0.14681355208158492,
|
|
"num_tokens": 8322203.0,
|
|
"step": 4010
|
|
},
|
|
{
|
|
"entropy": 5.76598744392395,
|
|
"epoch": 0.36420537010159654,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.000499155143559372,
|
|
"loss": 5.6611,
|
|
"mean_token_accuracy": 0.1537575125694275,
|
|
"num_tokens": 8330981.0,
|
|
"step": 4015
|
|
},
|
|
{
|
|
"entropy": 5.722754430770874,
|
|
"epoch": 0.3646589259796807,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004991523398901773,
|
|
"loss": 5.7148,
|
|
"mean_token_accuracy": 0.15234556347131728,
|
|
"num_tokens": 8341294.0,
|
|
"step": 4020
|
|
},
|
|
{
|
|
"entropy": 5.931970548629761,
|
|
"epoch": 0.3651124818577649,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004991495315854553,
|
|
"loss": 5.8497,
|
|
"mean_token_accuracy": 0.14425820037722586,
|
|
"num_tokens": 8351824.0,
|
|
"step": 4025
|
|
},
|
|
{
|
|
"entropy": 5.785876369476318,
|
|
"epoch": 0.36556603773584906,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004991467186452637,
|
|
"loss": 5.6981,
|
|
"mean_token_accuracy": 0.150992052257061,
|
|
"num_tokens": 8361975.0,
|
|
"step": 4030
|
|
},
|
|
{
|
|
"entropy": 5.698846769332886,
|
|
"epoch": 0.3660195936139332,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004991439010696609,
|
|
"loss": 5.6746,
|
|
"mean_token_accuracy": 0.1555260330438614,
|
|
"num_tokens": 8372145.0,
|
|
"step": 4035
|
|
},
|
|
{
|
|
"entropy": 5.84372878074646,
|
|
"epoch": 0.3664731494920174,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004991410788587051,
|
|
"loss": 5.7538,
|
|
"mean_token_accuracy": 0.1453930489718914,
|
|
"num_tokens": 8382542.0,
|
|
"step": 4040
|
|
},
|
|
{
|
|
"entropy": 5.848459148406983,
|
|
"epoch": 0.3669267053701016,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004991382520124547,
|
|
"loss": 5.7821,
|
|
"mean_token_accuracy": 0.14706437662243843,
|
|
"num_tokens": 8393450.0,
|
|
"step": 4045
|
|
},
|
|
{
|
|
"entropy": 5.844983816146851,
|
|
"epoch": 0.3673802612481858,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004991354205309681,
|
|
"loss": 5.7058,
|
|
"mean_token_accuracy": 0.14525790363550187,
|
|
"num_tokens": 8404929.0,
|
|
"step": 4050
|
|
},
|
|
{
|
|
"entropy": 5.838060188293457,
|
|
"epoch": 0.36783381712626995,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.000499132584414304,
|
|
"loss": 5.7298,
|
|
"mean_token_accuracy": 0.1509381502866745,
|
|
"num_tokens": 8415703.0,
|
|
"step": 4055
|
|
},
|
|
{
|
|
"entropy": 5.8065282821655275,
|
|
"epoch": 0.36828737300435416,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004991297436625207,
|
|
"loss": 5.8075,
|
|
"mean_token_accuracy": 0.15024188235402108,
|
|
"num_tokens": 8426220.0,
|
|
"step": 4060
|
|
},
|
|
{
|
|
"entropy": 5.717031574249267,
|
|
"epoch": 0.3687409288824383,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004991268982756774,
|
|
"loss": 5.6718,
|
|
"mean_token_accuracy": 0.15563272684812546,
|
|
"num_tokens": 8436220.0,
|
|
"step": 4065
|
|
},
|
|
{
|
|
"entropy": 5.872826862335205,
|
|
"epoch": 0.3691944847605225,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004991240482538327,
|
|
"loss": 5.8326,
|
|
"mean_token_accuracy": 0.14214779883623124,
|
|
"num_tokens": 8446724.0,
|
|
"step": 4070
|
|
},
|
|
{
|
|
"entropy": 5.8477081775665285,
|
|
"epoch": 0.3696480406386067,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004991211935970455,
|
|
"loss": 5.6876,
|
|
"mean_token_accuracy": 0.14904116541147233,
|
|
"num_tokens": 8457270.0,
|
|
"step": 4075
|
|
},
|
|
{
|
|
"entropy": 5.828044128417969,
|
|
"epoch": 0.37010159651669083,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004991183343053748,
|
|
"loss": 5.7618,
|
|
"mean_token_accuracy": 0.14451126977801323,
|
|
"num_tokens": 8468137.0,
|
|
"step": 4080
|
|
},
|
|
{
|
|
"entropy": 5.8057512760162355,
|
|
"epoch": 0.37055515239477504,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00049911547037888,
|
|
"loss": 5.6947,
|
|
"mean_token_accuracy": 0.15399888902902603,
|
|
"num_tokens": 8477574.0,
|
|
"step": 4085
|
|
},
|
|
{
|
|
"entropy": 5.769902849197388,
|
|
"epoch": 0.3710087082728592,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004991126018176202,
|
|
"loss": 5.7932,
|
|
"mean_token_accuracy": 0.1436054840683937,
|
|
"num_tokens": 8487268.0,
|
|
"step": 4090
|
|
},
|
|
{
|
|
"entropy": 5.928350782394409,
|
|
"epoch": 0.3714622641509434,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004991097286216545,
|
|
"loss": 5.8514,
|
|
"mean_token_accuracy": 0.14995737373828888,
|
|
"num_tokens": 8497785.0,
|
|
"step": 4095
|
|
},
|
|
{
|
|
"entropy": 5.887904167175293,
|
|
"epoch": 0.37191582002902757,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004991068507910427,
|
|
"loss": 5.7223,
|
|
"mean_token_accuracy": 0.14823060035705565,
|
|
"num_tokens": 8508169.0,
|
|
"step": 4100
|
|
},
|
|
{
|
|
"entropy": 5.738240814208984,
|
|
"epoch": 0.3723693759071118,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.000499103968325844,
|
|
"loss": 5.7058,
|
|
"mean_token_accuracy": 0.14781549870967864,
|
|
"num_tokens": 8519201.0,
|
|
"step": 4105
|
|
},
|
|
{
|
|
"entropy": 5.888035488128662,
|
|
"epoch": 0.37282293178519593,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004991010812261181,
|
|
"loss": 5.8075,
|
|
"mean_token_accuracy": 0.14320318549871444,
|
|
"num_tokens": 8531093.0,
|
|
"step": 4110
|
|
},
|
|
{
|
|
"entropy": 5.799619388580322,
|
|
"epoch": 0.37327648766328014,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004990981894919248,
|
|
"loss": 5.6616,
|
|
"mean_token_accuracy": 0.1559358224272728,
|
|
"num_tokens": 8541730.0,
|
|
"step": 4115
|
|
},
|
|
{
|
|
"entropy": 5.728639888763428,
|
|
"epoch": 0.3737300435413643,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004990952931233238,
|
|
"loss": 5.7516,
|
|
"mean_token_accuracy": 0.1526630237698555,
|
|
"num_tokens": 8552570.0,
|
|
"step": 4120
|
|
},
|
|
{
|
|
"entropy": 5.801388740539551,
|
|
"epoch": 0.37418359941944845,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.000499092392120375,
|
|
"loss": 5.6416,
|
|
"mean_token_accuracy": 0.15281095802783967,
|
|
"num_tokens": 8562340.0,
|
|
"step": 4125
|
|
},
|
|
{
|
|
"entropy": 5.86045470237732,
|
|
"epoch": 0.37463715529753266,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004990894864831385,
|
|
"loss": 5.8447,
|
|
"mean_token_accuracy": 0.14465546905994414,
|
|
"num_tokens": 8573240.0,
|
|
"step": 4130
|
|
},
|
|
{
|
|
"entropy": 5.83771858215332,
|
|
"epoch": 0.3750907111756168,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004990865762116743,
|
|
"loss": 5.7,
|
|
"mean_token_accuracy": 0.1569647617638111,
|
|
"num_tokens": 8583194.0,
|
|
"step": 4135
|
|
},
|
|
{
|
|
"entropy": 5.840100049972534,
|
|
"epoch": 0.37554426705370103,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004990836613060426,
|
|
"loss": 5.7629,
|
|
"mean_token_accuracy": 0.1451824389398098,
|
|
"num_tokens": 8593603.0,
|
|
"step": 4140
|
|
},
|
|
{
|
|
"entropy": 5.742400503158569,
|
|
"epoch": 0.3759978229317852,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004990807417663036,
|
|
"loss": 5.7677,
|
|
"mean_token_accuracy": 0.15051018446683884,
|
|
"num_tokens": 8603176.0,
|
|
"step": 4145
|
|
},
|
|
{
|
|
"entropy": 5.8087677478790285,
|
|
"epoch": 0.3764513788098694,
|
|
"grad_norm": 3.90625,
|
|
"learning_rate": 0.0004990778175925179,
|
|
"loss": 5.7931,
|
|
"mean_token_accuracy": 0.15137793719768525,
|
|
"num_tokens": 8614801.0,
|
|
"step": 4150
|
|
},
|
|
{
|
|
"entropy": 5.911026477813721,
|
|
"epoch": 0.37690493468795355,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004990748887847457,
|
|
"loss": 5.8055,
|
|
"mean_token_accuracy": 0.14926701039075851,
|
|
"num_tokens": 8624999.0,
|
|
"step": 4155
|
|
},
|
|
{
|
|
"entropy": 5.786199283599854,
|
|
"epoch": 0.37735849056603776,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004990719553430477,
|
|
"loss": 5.6852,
|
|
"mean_token_accuracy": 0.16073830276727677,
|
|
"num_tokens": 8635358.0,
|
|
"step": 4160
|
|
},
|
|
{
|
|
"entropy": 5.812259101867676,
|
|
"epoch": 0.3778120464441219,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004990690172674847,
|
|
"loss": 5.7376,
|
|
"mean_token_accuracy": 0.15018846094608307,
|
|
"num_tokens": 8645430.0,
|
|
"step": 4165
|
|
},
|
|
{
|
|
"entropy": 5.876455307006836,
|
|
"epoch": 0.3782656023222061,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004990660745581172,
|
|
"loss": 5.6993,
|
|
"mean_token_accuracy": 0.15587360560894012,
|
|
"num_tokens": 8655115.0,
|
|
"step": 4170
|
|
},
|
|
{
|
|
"entropy": 5.731990957260132,
|
|
"epoch": 0.3787191582002903,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004990631272150062,
|
|
"loss": 5.6902,
|
|
"mean_token_accuracy": 0.14820799827575684,
|
|
"num_tokens": 8665391.0,
|
|
"step": 4175
|
|
},
|
|
{
|
|
"entropy": 5.804074239730835,
|
|
"epoch": 0.37917271407837444,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004990601752382127,
|
|
"loss": 5.7963,
|
|
"mean_token_accuracy": 0.1466014303267002,
|
|
"num_tokens": 8676819.0,
|
|
"step": 4180
|
|
},
|
|
{
|
|
"entropy": 5.87374176979065,
|
|
"epoch": 0.37962626995645865,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004990572186277975,
|
|
"loss": 5.7317,
|
|
"mean_token_accuracy": 0.15189690440893172,
|
|
"num_tokens": 8687052.0,
|
|
"step": 4185
|
|
},
|
|
{
|
|
"entropy": 5.8404378414154055,
|
|
"epoch": 0.3800798258345428,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004990542573838221,
|
|
"loss": 5.7927,
|
|
"mean_token_accuracy": 0.14445817843079567,
|
|
"num_tokens": 8697756.0,
|
|
"step": 4190
|
|
},
|
|
{
|
|
"entropy": 5.761879825592041,
|
|
"epoch": 0.380533381712627,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004990512915063475,
|
|
"loss": 5.6999,
|
|
"mean_token_accuracy": 0.15357010215520858,
|
|
"num_tokens": 8708388.0,
|
|
"step": 4195
|
|
},
|
|
{
|
|
"entropy": 5.891747236251831,
|
|
"epoch": 0.38098693759071117,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004990483209954352,
|
|
"loss": 5.8001,
|
|
"mean_token_accuracy": 0.14270555898547171,
|
|
"num_tokens": 8719475.0,
|
|
"step": 4200
|
|
},
|
|
{
|
|
"entropy": 5.826990032196045,
|
|
"epoch": 0.3814404934687954,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004990453458511464,
|
|
"loss": 5.6709,
|
|
"mean_token_accuracy": 0.15746982842683793,
|
|
"num_tokens": 8729395.0,
|
|
"step": 4205
|
|
},
|
|
{
|
|
"entropy": 5.862640428543091,
|
|
"epoch": 0.38189404934687954,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004990423660735428,
|
|
"loss": 5.7227,
|
|
"mean_token_accuracy": 0.15197302550077438,
|
|
"num_tokens": 8740351.0,
|
|
"step": 4210
|
|
},
|
|
{
|
|
"entropy": 5.838958644866944,
|
|
"epoch": 0.3823476052249637,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.000499039381662686,
|
|
"loss": 5.7375,
|
|
"mean_token_accuracy": 0.15115175843238832,
|
|
"num_tokens": 8749260.0,
|
|
"step": 4215
|
|
},
|
|
{
|
|
"entropy": 5.813646125793457,
|
|
"epoch": 0.3828011611030479,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004990363926186377,
|
|
"loss": 5.8251,
|
|
"mean_token_accuracy": 0.14027270674705505,
|
|
"num_tokens": 8759604.0,
|
|
"step": 4220
|
|
},
|
|
{
|
|
"entropy": 5.858145141601563,
|
|
"epoch": 0.38325471698113206,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004990333989414597,
|
|
"loss": 5.826,
|
|
"mean_token_accuracy": 0.14018016085028648,
|
|
"num_tokens": 8769815.0,
|
|
"step": 4225
|
|
},
|
|
{
|
|
"entropy": 5.801722669601441,
|
|
"epoch": 0.38370827285921627,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004990304006312138,
|
|
"loss": 5.77,
|
|
"mean_token_accuracy": 0.1485055848956108,
|
|
"num_tokens": 8780557.0,
|
|
"step": 4230
|
|
},
|
|
{
|
|
"entropy": 5.830351734161377,
|
|
"epoch": 0.3841618287373004,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004990273976879622,
|
|
"loss": 5.7202,
|
|
"mean_token_accuracy": 0.15922572910785676,
|
|
"num_tokens": 8790993.0,
|
|
"step": 4235
|
|
},
|
|
{
|
|
"entropy": 5.873066186904907,
|
|
"epoch": 0.38461538461538464,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004990243901117669,
|
|
"loss": 5.7568,
|
|
"mean_token_accuracy": 0.14900755137205124,
|
|
"num_tokens": 8800657.0,
|
|
"step": 4240
|
|
},
|
|
{
|
|
"entropy": 5.7463071823120115,
|
|
"epoch": 0.3850689404934688,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004990213779026903,
|
|
"loss": 5.7749,
|
|
"mean_token_accuracy": 0.14669715017080306,
|
|
"num_tokens": 8812983.0,
|
|
"step": 4245
|
|
},
|
|
{
|
|
"entropy": 5.889048004150391,
|
|
"epoch": 0.385522496371553,
|
|
"grad_norm": 3.34375,
|
|
"learning_rate": 0.0004990183610607944,
|
|
"loss": 5.7358,
|
|
"mean_token_accuracy": 0.150221536308527,
|
|
"num_tokens": 8822980.0,
|
|
"step": 4250
|
|
},
|
|
{
|
|
"entropy": 5.827584266662598,
|
|
"epoch": 0.38597605224963716,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004990153395861415,
|
|
"loss": 5.7337,
|
|
"mean_token_accuracy": 0.15071167424321175,
|
|
"num_tokens": 8833821.0,
|
|
"step": 4255
|
|
},
|
|
{
|
|
"entropy": 5.789939260482788,
|
|
"epoch": 0.3864296081277213,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004990123134787946,
|
|
"loss": 5.6854,
|
|
"mean_token_accuracy": 0.15111219882965088,
|
|
"num_tokens": 8843929.0,
|
|
"step": 4260
|
|
},
|
|
{
|
|
"entropy": 5.774974298477173,
|
|
"epoch": 0.3868831640058055,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004990092827388159,
|
|
"loss": 5.6597,
|
|
"mean_token_accuracy": 0.15415194928646087,
|
|
"num_tokens": 8854180.0,
|
|
"step": 4265
|
|
},
|
|
{
|
|
"entropy": 5.727933740615844,
|
|
"epoch": 0.3873367198838897,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.0004990062473662681,
|
|
"loss": 5.6851,
|
|
"mean_token_accuracy": 0.15864559412002563,
|
|
"num_tokens": 8865018.0,
|
|
"step": 4270
|
|
},
|
|
{
|
|
"entropy": 5.857227516174317,
|
|
"epoch": 0.3877902757619739,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.000499003207361214,
|
|
"loss": 5.864,
|
|
"mean_token_accuracy": 0.14215147495269775,
|
|
"num_tokens": 8875423.0,
|
|
"step": 4275
|
|
},
|
|
{
|
|
"entropy": 5.942317485809326,
|
|
"epoch": 0.38824383164005805,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004990001627237165,
|
|
"loss": 5.8048,
|
|
"mean_token_accuracy": 0.14681227505207062,
|
|
"num_tokens": 8887850.0,
|
|
"step": 4280
|
|
},
|
|
{
|
|
"entropy": 5.756715774536133,
|
|
"epoch": 0.38869738751814226,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004989971134538386,
|
|
"loss": 5.6856,
|
|
"mean_token_accuracy": 0.15011156648397445,
|
|
"num_tokens": 8897429.0,
|
|
"step": 4285
|
|
},
|
|
{
|
|
"entropy": 5.8178752899169925,
|
|
"epoch": 0.3891509433962264,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004989940595516432,
|
|
"loss": 5.7018,
|
|
"mean_token_accuracy": 0.15288467705249786,
|
|
"num_tokens": 8907048.0,
|
|
"step": 4290
|
|
},
|
|
{
|
|
"entropy": 5.800828266143799,
|
|
"epoch": 0.3896044992743106,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004989910010171938,
|
|
"loss": 5.7545,
|
|
"mean_token_accuracy": 0.1477030858397484,
|
|
"num_tokens": 8917987.0,
|
|
"step": 4295
|
|
},
|
|
{
|
|
"entropy": 5.897664308547974,
|
|
"epoch": 0.3900580551523948,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004989879378505532,
|
|
"loss": 5.6798,
|
|
"mean_token_accuracy": 0.14783306419849396,
|
|
"num_tokens": 8929339.0,
|
|
"step": 4300
|
|
},
|
|
{
|
|
"entropy": 5.746922588348388,
|
|
"epoch": 0.39051161103047893,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004989848700517849,
|
|
"loss": 5.6842,
|
|
"mean_token_accuracy": 0.14888181313872337,
|
|
"num_tokens": 8939473.0,
|
|
"step": 4305
|
|
},
|
|
{
|
|
"entropy": 5.758429908752442,
|
|
"epoch": 0.39096516690856314,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004989817976209526,
|
|
"loss": 5.7207,
|
|
"mean_token_accuracy": 0.15242671966552734,
|
|
"num_tokens": 8949173.0,
|
|
"step": 4310
|
|
},
|
|
{
|
|
"entropy": 5.7987030982971195,
|
|
"epoch": 0.3914187227866473,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004989787205581196,
|
|
"loss": 5.6937,
|
|
"mean_token_accuracy": 0.15537856966257096,
|
|
"num_tokens": 8959879.0,
|
|
"step": 4315
|
|
},
|
|
{
|
|
"entropy": 5.801929140090943,
|
|
"epoch": 0.3918722786647315,
|
|
"grad_norm": 3.265625,
|
|
"learning_rate": 0.0004989756388633496,
|
|
"loss": 5.7669,
|
|
"mean_token_accuracy": 0.1492094039916992,
|
|
"num_tokens": 8970643.0,
|
|
"step": 4320
|
|
},
|
|
{
|
|
"entropy": 5.826022291183472,
|
|
"epoch": 0.39232583454281567,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.0004989725525367063,
|
|
"loss": 5.6519,
|
|
"mean_token_accuracy": 0.15020777881145478,
|
|
"num_tokens": 8979882.0,
|
|
"step": 4325
|
|
},
|
|
{
|
|
"entropy": 5.819568634033203,
|
|
"epoch": 0.3927793904208999,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004989694615782534,
|
|
"loss": 5.792,
|
|
"mean_token_accuracy": 0.14471497684717177,
|
|
"num_tokens": 8990925.0,
|
|
"step": 4330
|
|
},
|
|
{
|
|
"entropy": 5.835562753677368,
|
|
"epoch": 0.39323294629898403,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004989663659880552,
|
|
"loss": 5.8056,
|
|
"mean_token_accuracy": 0.14450787603855134,
|
|
"num_tokens": 9001365.0,
|
|
"step": 4335
|
|
},
|
|
{
|
|
"entropy": 5.854931926727295,
|
|
"epoch": 0.3936865021770682,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004989632657661754,
|
|
"loss": 5.8011,
|
|
"mean_token_accuracy": 0.15069715231657027,
|
|
"num_tokens": 9011942.0,
|
|
"step": 4340
|
|
},
|
|
{
|
|
"entropy": 5.9251405715942385,
|
|
"epoch": 0.3941400580551524,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.000498960160912678,
|
|
"loss": 5.8149,
|
|
"mean_token_accuracy": 0.14857330471277236,
|
|
"num_tokens": 9022610.0,
|
|
"step": 4345
|
|
},
|
|
{
|
|
"entropy": 5.802004814147949,
|
|
"epoch": 0.39459361393323655,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004989570514276276,
|
|
"loss": 5.7119,
|
|
"mean_token_accuracy": 0.15157701522111894,
|
|
"num_tokens": 9033034.0,
|
|
"step": 4350
|
|
},
|
|
{
|
|
"entropy": 5.798203468322754,
|
|
"epoch": 0.39504716981132076,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004989539373110883,
|
|
"loss": 5.7609,
|
|
"mean_token_accuracy": 0.14471814632415772,
|
|
"num_tokens": 9043418.0,
|
|
"step": 4355
|
|
},
|
|
{
|
|
"entropy": 5.870092725753784,
|
|
"epoch": 0.3955007256894049,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004989508185631245,
|
|
"loss": 5.8328,
|
|
"mean_token_accuracy": 0.14952152520418166,
|
|
"num_tokens": 9052708.0,
|
|
"step": 4360
|
|
},
|
|
{
|
|
"entropy": 5.786429405212402,
|
|
"epoch": 0.39595428156748913,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004989476951838006,
|
|
"loss": 5.7219,
|
|
"mean_token_accuracy": 0.14567517340183259,
|
|
"num_tokens": 9062883.0,
|
|
"step": 4365
|
|
},
|
|
{
|
|
"entropy": 5.7873271942138675,
|
|
"epoch": 0.3964078374455733,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004989445671731814,
|
|
"loss": 5.6701,
|
|
"mean_token_accuracy": 0.1534933939576149,
|
|
"num_tokens": 9072830.0,
|
|
"step": 4370
|
|
},
|
|
{
|
|
"entropy": 5.761323547363281,
|
|
"epoch": 0.3968613933236575,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004989414345313315,
|
|
"loss": 5.6374,
|
|
"mean_token_accuracy": 0.14723165333271027,
|
|
"num_tokens": 9082749.0,
|
|
"step": 4375
|
|
},
|
|
{
|
|
"entropy": 5.85912070274353,
|
|
"epoch": 0.39731494920174165,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004989382972583156,
|
|
"loss": 5.7277,
|
|
"mean_token_accuracy": 0.14558447450399398,
|
|
"num_tokens": 9094188.0,
|
|
"step": 4380
|
|
},
|
|
{
|
|
"entropy": 5.806872129440308,
|
|
"epoch": 0.3977685050798258,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004989351553541986,
|
|
"loss": 5.7496,
|
|
"mean_token_accuracy": 0.14632164612412452,
|
|
"num_tokens": 9105023.0,
|
|
"step": 4385
|
|
},
|
|
{
|
|
"entropy": 5.782722663879395,
|
|
"epoch": 0.39822206095791,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004989320088190456,
|
|
"loss": 5.6934,
|
|
"mean_token_accuracy": 0.1507030040025711,
|
|
"num_tokens": 9115563.0,
|
|
"step": 4390
|
|
},
|
|
{
|
|
"entropy": 5.769656801223755,
|
|
"epoch": 0.3986756168359942,
|
|
"grad_norm": 3.46875,
|
|
"learning_rate": 0.0004989288576529216,
|
|
"loss": 5.7101,
|
|
"mean_token_accuracy": 0.14767857640981674,
|
|
"num_tokens": 9125394.0,
|
|
"step": 4395
|
|
},
|
|
{
|
|
"entropy": 5.779007911682129,
|
|
"epoch": 0.3991291727140784,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004989257018558917,
|
|
"loss": 5.7158,
|
|
"mean_token_accuracy": 0.1508276343345642,
|
|
"num_tokens": 9137061.0,
|
|
"step": 4400
|
|
},
|
|
{
|
|
"entropy": 5.856002616882324,
|
|
"epoch": 0.39958272859216254,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004989225414280213,
|
|
"loss": 5.6813,
|
|
"mean_token_accuracy": 0.1500905178487301,
|
|
"num_tokens": 9148196.0,
|
|
"step": 4405
|
|
},
|
|
{
|
|
"entropy": 5.78254542350769,
|
|
"epoch": 0.40003628447024675,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004989193763693756,
|
|
"loss": 5.7107,
|
|
"mean_token_accuracy": 0.15331541001796722,
|
|
"num_tokens": 9158013.0,
|
|
"step": 4410
|
|
},
|
|
{
|
|
"entropy": 5.738414621353149,
|
|
"epoch": 0.4004898403483309,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004989162066800202,
|
|
"loss": 5.6106,
|
|
"mean_token_accuracy": 0.15551046580076217,
|
|
"num_tokens": 9167813.0,
|
|
"step": 4415
|
|
},
|
|
{
|
|
"entropy": 5.764182472229004,
|
|
"epoch": 0.4009433962264151,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004989130323600205,
|
|
"loss": 5.6889,
|
|
"mean_token_accuracy": 0.1522517278790474,
|
|
"num_tokens": 9177783.0,
|
|
"step": 4420
|
|
},
|
|
{
|
|
"entropy": 5.800490760803223,
|
|
"epoch": 0.40139695210449927,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004989098534094424,
|
|
"loss": 5.7324,
|
|
"mean_token_accuracy": 0.15464526265859604,
|
|
"num_tokens": 9187556.0,
|
|
"step": 4425
|
|
},
|
|
{
|
|
"entropy": 5.805605030059814,
|
|
"epoch": 0.4018505079825834,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004989066698283512,
|
|
"loss": 5.7733,
|
|
"mean_token_accuracy": 0.14691560864448547,
|
|
"num_tokens": 9198659.0,
|
|
"step": 4430
|
|
},
|
|
{
|
|
"entropy": 5.811403799057007,
|
|
"epoch": 0.40230406386066764,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004989034816168132,
|
|
"loss": 5.758,
|
|
"mean_token_accuracy": 0.1504255309700966,
|
|
"num_tokens": 9209546.0,
|
|
"step": 4435
|
|
},
|
|
{
|
|
"entropy": 5.78139705657959,
|
|
"epoch": 0.4027576197387518,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.0004989002887748941,
|
|
"loss": 5.6752,
|
|
"mean_token_accuracy": 0.15406596213579177,
|
|
"num_tokens": 9219339.0,
|
|
"step": 4440
|
|
},
|
|
{
|
|
"entropy": 5.84251184463501,
|
|
"epoch": 0.403211175616836,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004988970913026601,
|
|
"loss": 5.8354,
|
|
"mean_token_accuracy": 0.14621326699852943,
|
|
"num_tokens": 9230364.0,
|
|
"step": 4445
|
|
},
|
|
{
|
|
"entropy": 5.873086214065552,
|
|
"epoch": 0.40366473149492016,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004988938892001771,
|
|
"loss": 5.7136,
|
|
"mean_token_accuracy": 0.1498823121190071,
|
|
"num_tokens": 9240732.0,
|
|
"step": 4450
|
|
},
|
|
{
|
|
"entropy": 5.731912326812744,
|
|
"epoch": 0.40411828737300437,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004988906824675113,
|
|
"loss": 5.6363,
|
|
"mean_token_accuracy": 0.15650977939367294,
|
|
"num_tokens": 9251049.0,
|
|
"step": 4455
|
|
},
|
|
{
|
|
"entropy": 5.779788398742676,
|
|
"epoch": 0.4045718432510885,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004988874711047293,
|
|
"loss": 5.6905,
|
|
"mean_token_accuracy": 0.1514260247349739,
|
|
"num_tokens": 9261660.0,
|
|
"step": 4460
|
|
},
|
|
{
|
|
"entropy": 5.810968637466431,
|
|
"epoch": 0.40502539912917274,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004988842551118972,
|
|
"loss": 5.7739,
|
|
"mean_token_accuracy": 0.14920282363891602,
|
|
"num_tokens": 9272114.0,
|
|
"step": 4465
|
|
},
|
|
{
|
|
"entropy": 5.797091484069824,
|
|
"epoch": 0.4054789550072569,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004988810344890818,
|
|
"loss": 5.7297,
|
|
"mean_token_accuracy": 0.15285758376121522,
|
|
"num_tokens": 9282125.0,
|
|
"step": 4470
|
|
},
|
|
{
|
|
"entropy": 5.8813393115997314,
|
|
"epoch": 0.40593251088534105,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004988778092363494,
|
|
"loss": 5.7761,
|
|
"mean_token_accuracy": 0.1445347175002098,
|
|
"num_tokens": 9294078.0,
|
|
"step": 4475
|
|
},
|
|
{
|
|
"entropy": 5.831450319290161,
|
|
"epoch": 0.40638606676342526,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004988745793537671,
|
|
"loss": 5.6933,
|
|
"mean_token_accuracy": 0.14883248656988143,
|
|
"num_tokens": 9304026.0,
|
|
"step": 4480
|
|
},
|
|
{
|
|
"entropy": 5.85241436958313,
|
|
"epoch": 0.4068396226415094,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004988713448414011,
|
|
"loss": 5.7471,
|
|
"mean_token_accuracy": 0.15584234297275543,
|
|
"num_tokens": 9313933.0,
|
|
"step": 4485
|
|
},
|
|
{
|
|
"entropy": 5.8357024669647215,
|
|
"epoch": 0.4072931785195936,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.000498868105699319,
|
|
"loss": 5.7767,
|
|
"mean_token_accuracy": 0.14843285381793975,
|
|
"num_tokens": 9323932.0,
|
|
"step": 4490
|
|
},
|
|
{
|
|
"entropy": 5.723560190200805,
|
|
"epoch": 0.4077467343976778,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004988648619275872,
|
|
"loss": 5.6851,
|
|
"mean_token_accuracy": 0.1634763866662979,
|
|
"num_tokens": 9333467.0,
|
|
"step": 4495
|
|
},
|
|
{
|
|
"entropy": 5.817450141906738,
|
|
"epoch": 0.408200290275762,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004988616135262729,
|
|
"loss": 5.7577,
|
|
"mean_token_accuracy": 0.14326895773410797,
|
|
"num_tokens": 9344909.0,
|
|
"step": 4500
|
|
},
|
|
{
|
|
"entropy": 5.897395086288452,
|
|
"epoch": 0.40865384615384615,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004988583604954436,
|
|
"loss": 5.7977,
|
|
"mean_token_accuracy": 0.14532231390476227,
|
|
"num_tokens": 9355630.0,
|
|
"step": 4505
|
|
},
|
|
{
|
|
"entropy": 5.8017322540283205,
|
|
"epoch": 0.40910740203193036,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004988551028351663,
|
|
"loss": 5.7392,
|
|
"mean_token_accuracy": 0.147707736492157,
|
|
"num_tokens": 9365700.0,
|
|
"step": 4510
|
|
},
|
|
{
|
|
"entropy": 5.831019258499145,
|
|
"epoch": 0.4095609579100145,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004988518405455084,
|
|
"loss": 5.8225,
|
|
"mean_token_accuracy": 0.14114691615104674,
|
|
"num_tokens": 9377088.0,
|
|
"step": 4515
|
|
},
|
|
{
|
|
"entropy": 5.8371169090271,
|
|
"epoch": 0.41001451378809867,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004988485736265374,
|
|
"loss": 5.6158,
|
|
"mean_token_accuracy": 0.15830224454402925,
|
|
"num_tokens": 9386855.0,
|
|
"step": 4520
|
|
},
|
|
{
|
|
"entropy": 5.791143941879272,
|
|
"epoch": 0.4104680696661829,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.000498845302078321,
|
|
"loss": 5.7444,
|
|
"mean_token_accuracy": 0.14412623643875122,
|
|
"num_tokens": 9398661.0,
|
|
"step": 4525
|
|
},
|
|
{
|
|
"entropy": 5.826167106628418,
|
|
"epoch": 0.41092162554426703,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004988420259009266,
|
|
"loss": 5.7428,
|
|
"mean_token_accuracy": 0.1512528121471405,
|
|
"num_tokens": 9408670.0,
|
|
"step": 4530
|
|
},
|
|
{
|
|
"entropy": 5.844571304321289,
|
|
"epoch": 0.41137518142235124,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.000498838745094422,
|
|
"loss": 5.7423,
|
|
"mean_token_accuracy": 0.15003526955842972,
|
|
"num_tokens": 9418740.0,
|
|
"step": 4535
|
|
},
|
|
{
|
|
"entropy": 5.7954200267791744,
|
|
"epoch": 0.4118287373004354,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004988354596588751,
|
|
"loss": 5.7326,
|
|
"mean_token_accuracy": 0.15099671930074693,
|
|
"num_tokens": 9429339.0,
|
|
"step": 4540
|
|
},
|
|
{
|
|
"entropy": 5.78496036529541,
|
|
"epoch": 0.4122822931785196,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.0004988321695943539,
|
|
"loss": 5.6709,
|
|
"mean_token_accuracy": 0.15879771262407302,
|
|
"num_tokens": 9438996.0,
|
|
"step": 4545
|
|
},
|
|
{
|
|
"entropy": 5.82200813293457,
|
|
"epoch": 0.41273584905660377,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004988288749009264,
|
|
"loss": 5.6959,
|
|
"mean_token_accuracy": 0.15078579634428024,
|
|
"num_tokens": 9448669.0,
|
|
"step": 4550
|
|
},
|
|
{
|
|
"entropy": 5.776082324981689,
|
|
"epoch": 0.413189404934688,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004988255755786608,
|
|
"loss": 5.6834,
|
|
"mean_token_accuracy": 0.15365493297576904,
|
|
"num_tokens": 9458857.0,
|
|
"step": 4555
|
|
},
|
|
{
|
|
"entropy": 5.7420238018035885,
|
|
"epoch": 0.41364296081277213,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004988222716276251,
|
|
"loss": 5.6845,
|
|
"mean_token_accuracy": 0.15307349115610122,
|
|
"num_tokens": 9470241.0,
|
|
"step": 4560
|
|
},
|
|
{
|
|
"entropy": 5.889754772186279,
|
|
"epoch": 0.4140965166908563,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.000498818963047888,
|
|
"loss": 5.8581,
|
|
"mean_token_accuracy": 0.1453462913632393,
|
|
"num_tokens": 9480528.0,
|
|
"step": 4565
|
|
},
|
|
{
|
|
"entropy": 5.914613819122314,
|
|
"epoch": 0.4145500725689405,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004988156498395176,
|
|
"loss": 5.7684,
|
|
"mean_token_accuracy": 0.14872041046619416,
|
|
"num_tokens": 9491000.0,
|
|
"step": 4570
|
|
},
|
|
{
|
|
"entropy": 5.829993867874146,
|
|
"epoch": 0.41500362844702465,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004988123320025825,
|
|
"loss": 5.756,
|
|
"mean_token_accuracy": 0.15005763098597527,
|
|
"num_tokens": 9501612.0,
|
|
"step": 4575
|
|
},
|
|
{
|
|
"entropy": 5.857288932800293,
|
|
"epoch": 0.41545718432510886,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004988090095371514,
|
|
"loss": 5.8461,
|
|
"mean_token_accuracy": 0.145644311606884,
|
|
"num_tokens": 9513999.0,
|
|
"step": 4580
|
|
},
|
|
{
|
|
"entropy": 5.859341239929199,
|
|
"epoch": 0.415910740203193,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004988056824432928,
|
|
"loss": 5.7257,
|
|
"mean_token_accuracy": 0.1431219108402729,
|
|
"num_tokens": 9524392.0,
|
|
"step": 4585
|
|
},
|
|
{
|
|
"entropy": 5.816585493087769,
|
|
"epoch": 0.41636429608127723,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004988023507210758,
|
|
"loss": 5.7304,
|
|
"mean_token_accuracy": 0.15149542987346648,
|
|
"num_tokens": 9534227.0,
|
|
"step": 4590
|
|
},
|
|
{
|
|
"entropy": 5.802891588211059,
|
|
"epoch": 0.4168178519593614,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004987990143705692,
|
|
"loss": 5.7088,
|
|
"mean_token_accuracy": 0.155563186109066,
|
|
"num_tokens": 9544242.0,
|
|
"step": 4595
|
|
},
|
|
{
|
|
"entropy": 5.840281343460083,
|
|
"epoch": 0.4172714078374456,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004987956733918418,
|
|
"loss": 5.6398,
|
|
"mean_token_accuracy": 0.1510664239525795,
|
|
"num_tokens": 9553921.0,
|
|
"step": 4600
|
|
},
|
|
{
|
|
"entropy": 5.723497200012207,
|
|
"epoch": 0.41772496371552975,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004987923277849629,
|
|
"loss": 5.6785,
|
|
"mean_token_accuracy": 0.14915904104709626,
|
|
"num_tokens": 9564768.0,
|
|
"step": 4605
|
|
},
|
|
{
|
|
"entropy": 5.789427089691162,
|
|
"epoch": 0.4181785195936139,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004987889775500017,
|
|
"loss": 5.7736,
|
|
"mean_token_accuracy": 0.14345343932509422,
|
|
"num_tokens": 9576360.0,
|
|
"step": 4610
|
|
},
|
|
{
|
|
"entropy": 5.862417459487915,
|
|
"epoch": 0.4186320754716981,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004987856226870272,
|
|
"loss": 5.7484,
|
|
"mean_token_accuracy": 0.1491814523935318,
|
|
"num_tokens": 9587623.0,
|
|
"step": 4615
|
|
},
|
|
{
|
|
"entropy": 5.795092535018921,
|
|
"epoch": 0.4190856313497823,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004987822631961092,
|
|
"loss": 5.7795,
|
|
"mean_token_accuracy": 0.1469440668821335,
|
|
"num_tokens": 9597837.0,
|
|
"step": 4620
|
|
},
|
|
{
|
|
"entropy": 5.825919055938721,
|
|
"epoch": 0.4195391872278665,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.000498778899077317,
|
|
"loss": 5.7333,
|
|
"mean_token_accuracy": 0.14518298730254173,
|
|
"num_tokens": 9609509.0,
|
|
"step": 4625
|
|
},
|
|
{
|
|
"entropy": 5.799678754806519,
|
|
"epoch": 0.41999274310595064,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.00049877553033072,
|
|
"loss": 5.703,
|
|
"mean_token_accuracy": 0.15073038637638092,
|
|
"num_tokens": 9619954.0,
|
|
"step": 4630
|
|
},
|
|
{
|
|
"entropy": 5.785829067230225,
|
|
"epoch": 0.42044629898403485,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004987721569563882,
|
|
"loss": 5.7136,
|
|
"mean_token_accuracy": 0.14777721464633942,
|
|
"num_tokens": 9629742.0,
|
|
"step": 4635
|
|
},
|
|
{
|
|
"entropy": 5.8123650550842285,
|
|
"epoch": 0.420899854862119,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.000498768778954391,
|
|
"loss": 5.7296,
|
|
"mean_token_accuracy": 0.15000276267528534,
|
|
"num_tokens": 9641378.0,
|
|
"step": 4640
|
|
},
|
|
{
|
|
"entropy": 5.854241609573364,
|
|
"epoch": 0.4213534107402032,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004987653963247985,
|
|
"loss": 5.7931,
|
|
"mean_token_accuracy": 0.15243044048547744,
|
|
"num_tokens": 9652279.0,
|
|
"step": 4645
|
|
},
|
|
{
|
|
"entropy": 5.831078624725341,
|
|
"epoch": 0.42180696661828737,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004987620090676805,
|
|
"loss": 5.8085,
|
|
"mean_token_accuracy": 0.14800476655364037,
|
|
"num_tokens": 9663416.0,
|
|
"step": 4650
|
|
},
|
|
{
|
|
"entropy": 5.810733652114868,
|
|
"epoch": 0.4222605224963715,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004987586171831072,
|
|
"loss": 5.7501,
|
|
"mean_token_accuracy": 0.14851362258195877,
|
|
"num_tokens": 9674647.0,
|
|
"step": 4655
|
|
},
|
|
{
|
|
"entropy": 5.792376756668091,
|
|
"epoch": 0.42271407837445574,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004987552206711487,
|
|
"loss": 5.6,
|
|
"mean_token_accuracy": 0.15128281936049462,
|
|
"num_tokens": 9685084.0,
|
|
"step": 4660
|
|
},
|
|
{
|
|
"entropy": 5.711585760116577,
|
|
"epoch": 0.4231676342525399,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004987518195318752,
|
|
"loss": 5.6618,
|
|
"mean_token_accuracy": 0.1485517218708992,
|
|
"num_tokens": 9695661.0,
|
|
"step": 4665
|
|
},
|
|
{
|
|
"entropy": 5.7958086967468265,
|
|
"epoch": 0.4236211901306241,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.000498748413765357,
|
|
"loss": 5.7194,
|
|
"mean_token_accuracy": 0.14617605209350587,
|
|
"num_tokens": 9705773.0,
|
|
"step": 4670
|
|
},
|
|
{
|
|
"entropy": 5.870110130310058,
|
|
"epoch": 0.42407474600870826,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004987450033716646,
|
|
"loss": 5.7716,
|
|
"mean_token_accuracy": 0.1500180780887604,
|
|
"num_tokens": 9715799.0,
|
|
"step": 4675
|
|
},
|
|
{
|
|
"entropy": 5.825811100006104,
|
|
"epoch": 0.42452830188679247,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004987415883508686,
|
|
"loss": 5.7232,
|
|
"mean_token_accuracy": 0.1532239183783531,
|
|
"num_tokens": 9727012.0,
|
|
"step": 4680
|
|
},
|
|
{
|
|
"entropy": 5.829875516891479,
|
|
"epoch": 0.4249818577648766,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004987381687030394,
|
|
"loss": 5.711,
|
|
"mean_token_accuracy": 0.15218381732702255,
|
|
"num_tokens": 9737044.0,
|
|
"step": 4685
|
|
},
|
|
{
|
|
"entropy": 5.85615348815918,
|
|
"epoch": 0.42543541364296084,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004987347444282479,
|
|
"loss": 5.8218,
|
|
"mean_token_accuracy": 0.1412054069340229,
|
|
"num_tokens": 9747648.0,
|
|
"step": 4690
|
|
},
|
|
{
|
|
"entropy": 5.794318532943725,
|
|
"epoch": 0.425888969521045,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004987313155265649,
|
|
"loss": 5.745,
|
|
"mean_token_accuracy": 0.1462424784898758,
|
|
"num_tokens": 9757812.0,
|
|
"step": 4695
|
|
},
|
|
{
|
|
"entropy": 5.915569925308228,
|
|
"epoch": 0.42634252539912915,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004987278819980613,
|
|
"loss": 5.7262,
|
|
"mean_token_accuracy": 0.15311951488256453,
|
|
"num_tokens": 9768337.0,
|
|
"step": 4700
|
|
},
|
|
{
|
|
"entropy": 5.859813261032104,
|
|
"epoch": 0.42679608127721336,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.0004987244438428081,
|
|
"loss": 5.7565,
|
|
"mean_token_accuracy": 0.14580674096941948,
|
|
"num_tokens": 9779433.0,
|
|
"step": 4705
|
|
},
|
|
{
|
|
"entropy": 5.738063478469849,
|
|
"epoch": 0.4272496371552975,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004987210010608764,
|
|
"loss": 5.6671,
|
|
"mean_token_accuracy": 0.15135972946882248,
|
|
"num_tokens": 9790069.0,
|
|
"step": 4710
|
|
},
|
|
{
|
|
"entropy": 5.79045934677124,
|
|
"epoch": 0.4277031930333817,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004987175536523373,
|
|
"loss": 5.6582,
|
|
"mean_token_accuracy": 0.15610816180706025,
|
|
"num_tokens": 9799669.0,
|
|
"step": 4715
|
|
},
|
|
{
|
|
"entropy": 5.724021482467651,
|
|
"epoch": 0.4281567489114659,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004987141016172622,
|
|
"loss": 5.6897,
|
|
"mean_token_accuracy": 0.15267266184091569,
|
|
"num_tokens": 9809615.0,
|
|
"step": 4720
|
|
},
|
|
{
|
|
"entropy": 5.697861099243164,
|
|
"epoch": 0.4286103047895501,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004987106449557225,
|
|
"loss": 5.6572,
|
|
"mean_token_accuracy": 0.1498062126338482,
|
|
"num_tokens": 9819666.0,
|
|
"step": 4725
|
|
},
|
|
{
|
|
"entropy": 5.8632340908050535,
|
|
"epoch": 0.42906386066763424,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004987071836677896,
|
|
"loss": 5.8091,
|
|
"mean_token_accuracy": 0.15095954835414888,
|
|
"num_tokens": 9831015.0,
|
|
"step": 4730
|
|
},
|
|
{
|
|
"entropy": 5.816402864456177,
|
|
"epoch": 0.42951741654571846,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004987037177535353,
|
|
"loss": 5.6802,
|
|
"mean_token_accuracy": 0.15113823860883713,
|
|
"num_tokens": 9841354.0,
|
|
"step": 4735
|
|
},
|
|
{
|
|
"entropy": 5.754711484909057,
|
|
"epoch": 0.4299709724238026,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004987002472130309,
|
|
"loss": 5.6849,
|
|
"mean_token_accuracy": 0.1426093779504299,
|
|
"num_tokens": 9850467.0,
|
|
"step": 4740
|
|
},
|
|
{
|
|
"entropy": 5.866177654266357,
|
|
"epoch": 0.43042452830188677,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004986967720463485,
|
|
"loss": 5.7402,
|
|
"mean_token_accuracy": 0.1482555314898491,
|
|
"num_tokens": 9861115.0,
|
|
"step": 4745
|
|
},
|
|
{
|
|
"entropy": 5.90579195022583,
|
|
"epoch": 0.430878084179971,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004986932922535598,
|
|
"loss": 5.7527,
|
|
"mean_token_accuracy": 0.1503136560320854,
|
|
"num_tokens": 9871172.0,
|
|
"step": 4750
|
|
},
|
|
{
|
|
"entropy": 5.7877655029296875,
|
|
"epoch": 0.43133164005805513,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004986898078347368,
|
|
"loss": 5.649,
|
|
"mean_token_accuracy": 0.1556771621108055,
|
|
"num_tokens": 9881997.0,
|
|
"step": 4755
|
|
},
|
|
{
|
|
"entropy": 5.760748863220215,
|
|
"epoch": 0.43178519593613934,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004986863187899516,
|
|
"loss": 5.6544,
|
|
"mean_token_accuracy": 0.15546627789735795,
|
|
"num_tokens": 9892310.0,
|
|
"step": 4760
|
|
},
|
|
{
|
|
"entropy": 5.752875518798828,
|
|
"epoch": 0.4322387518142235,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004986828251192764,
|
|
"loss": 5.7035,
|
|
"mean_token_accuracy": 0.1481189787387848,
|
|
"num_tokens": 9902664.0,
|
|
"step": 4765
|
|
},
|
|
{
|
|
"entropy": 5.767500114440918,
|
|
"epoch": 0.4326923076923077,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004986793268227833,
|
|
"loss": 5.6954,
|
|
"mean_token_accuracy": 0.15243975818157196,
|
|
"num_tokens": 9912491.0,
|
|
"step": 4770
|
|
},
|
|
{
|
|
"entropy": 5.762394523620605,
|
|
"epoch": 0.43314586357039186,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004986758239005448,
|
|
"loss": 5.6399,
|
|
"mean_token_accuracy": 0.15671616941690444,
|
|
"num_tokens": 9922057.0,
|
|
"step": 4775
|
|
},
|
|
{
|
|
"entropy": 5.789015674591065,
|
|
"epoch": 0.4335994194484761,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004986723163526331,
|
|
"loss": 5.6908,
|
|
"mean_token_accuracy": 0.1488301694393158,
|
|
"num_tokens": 9933661.0,
|
|
"step": 4780
|
|
},
|
|
{
|
|
"entropy": 5.713762474060059,
|
|
"epoch": 0.43405297532656023,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004986688041791209,
|
|
"loss": 5.6666,
|
|
"mean_token_accuracy": 0.1482269987463951,
|
|
"num_tokens": 9945177.0,
|
|
"step": 4785
|
|
},
|
|
{
|
|
"entropy": 5.790286445617676,
|
|
"epoch": 0.4345065312046444,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.000498665287380081,
|
|
"loss": 5.7042,
|
|
"mean_token_accuracy": 0.1474942907691002,
|
|
"num_tokens": 9956226.0,
|
|
"step": 4790
|
|
},
|
|
{
|
|
"entropy": 5.862675619125366,
|
|
"epoch": 0.4349600870827286,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004986617659555859,
|
|
"loss": 5.7606,
|
|
"mean_token_accuracy": 0.15089563727378846,
|
|
"num_tokens": 9965877.0,
|
|
"step": 4795
|
|
},
|
|
{
|
|
"entropy": 5.725464248657227,
|
|
"epoch": 0.43541364296081275,
|
|
"grad_norm": 3.109375,
|
|
"learning_rate": 0.0004986582399057085,
|
|
"loss": 5.7076,
|
|
"mean_token_accuracy": 0.16087467074394227,
|
|
"num_tokens": 9975592.0,
|
|
"step": 4800
|
|
},
|
|
{
|
|
"entropy": 5.848356771469116,
|
|
"epoch": 0.43586719883889696,
|
|
"grad_norm": 3.515625,
|
|
"learning_rate": 0.0004986547092305216,
|
|
"loss": 5.7627,
|
|
"mean_token_accuracy": 0.14793257415294647,
|
|
"num_tokens": 9986094.0,
|
|
"step": 4805
|
|
},
|
|
{
|
|
"entropy": 5.916541671752929,
|
|
"epoch": 0.4363207547169811,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004986511739300984,
|
|
"loss": 5.7923,
|
|
"mean_token_accuracy": 0.1465185172855854,
|
|
"num_tokens": 9997241.0,
|
|
"step": 4810
|
|
},
|
|
{
|
|
"entropy": 5.787732934951782,
|
|
"epoch": 0.43677431059506533,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004986476340045119,
|
|
"loss": 5.7003,
|
|
"mean_token_accuracy": 0.15020343214273452,
|
|
"num_tokens": 10008091.0,
|
|
"step": 4815
|
|
},
|
|
{
|
|
"entropy": 5.809946966171265,
|
|
"epoch": 0.4372278664731495,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004986440894538354,
|
|
"loss": 5.7684,
|
|
"mean_token_accuracy": 0.14748568460345268,
|
|
"num_tokens": 10018794.0,
|
|
"step": 4820
|
|
},
|
|
{
|
|
"entropy": 5.7670200824737545,
|
|
"epoch": 0.4376814223512337,
|
|
"grad_norm": 3.0625,
|
|
"learning_rate": 0.0004986405402781421,
|
|
"loss": 5.656,
|
|
"mean_token_accuracy": 0.15169040709733964,
|
|
"num_tokens": 10028414.0,
|
|
"step": 4825
|
|
},
|
|
{
|
|
"entropy": 5.7817178726196286,
|
|
"epoch": 0.43813497822931785,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004986369864775054,
|
|
"loss": 5.7511,
|
|
"mean_token_accuracy": 0.14933410361409188,
|
|
"num_tokens": 10038749.0,
|
|
"step": 4830
|
|
},
|
|
{
|
|
"entropy": 5.8474963188171385,
|
|
"epoch": 0.438588534107402,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004986334280519989,
|
|
"loss": 5.6953,
|
|
"mean_token_accuracy": 0.15171761214733123,
|
|
"num_tokens": 10049866.0,
|
|
"step": 4835
|
|
},
|
|
{
|
|
"entropy": 5.808549976348877,
|
|
"epoch": 0.4390420899854862,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.000498629865001696,
|
|
"loss": 5.7227,
|
|
"mean_token_accuracy": 0.15592157542705537,
|
|
"num_tokens": 10060680.0,
|
|
"step": 4840
|
|
},
|
|
{
|
|
"entropy": 5.869030904769898,
|
|
"epoch": 0.43949564586357037,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004986262973266706,
|
|
"loss": 5.8215,
|
|
"mean_token_accuracy": 0.14849047362804413,
|
|
"num_tokens": 10070931.0,
|
|
"step": 4845
|
|
},
|
|
{
|
|
"entropy": 5.759446382522583,
|
|
"epoch": 0.4399492017416546,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.0004986227250269964,
|
|
"loss": 5.7429,
|
|
"mean_token_accuracy": 0.15099930614233018,
|
|
"num_tokens": 10080189.0,
|
|
"step": 4850
|
|
},
|
|
{
|
|
"entropy": 5.7940160751342775,
|
|
"epoch": 0.44040275761973874,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004986191481027472,
|
|
"loss": 5.6391,
|
|
"mean_token_accuracy": 0.15560751110315324,
|
|
"num_tokens": 10088813.0,
|
|
"step": 4855
|
|
},
|
|
{
|
|
"entropy": 5.818889951705932,
|
|
"epoch": 0.44085631349782295,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004986155665539971,
|
|
"loss": 5.6825,
|
|
"mean_token_accuracy": 0.15352422297000884,
|
|
"num_tokens": 10098125.0,
|
|
"step": 4860
|
|
},
|
|
{
|
|
"entropy": 5.838857555389405,
|
|
"epoch": 0.4413098693759071,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.00049861198038082,
|
|
"loss": 5.7218,
|
|
"mean_token_accuracy": 0.14922336339950562,
|
|
"num_tokens": 10109125.0,
|
|
"step": 4865
|
|
},
|
|
{
|
|
"entropy": 5.759595823287964,
|
|
"epoch": 0.4417634252539913,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004986083895832903,
|
|
"loss": 5.6983,
|
|
"mean_token_accuracy": 0.15355753526091576,
|
|
"num_tokens": 10120182.0,
|
|
"step": 4870
|
|
},
|
|
{
|
|
"entropy": 5.748368501663208,
|
|
"epoch": 0.44221698113207547,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004986047941614821,
|
|
"loss": 5.7589,
|
|
"mean_token_accuracy": 0.1470588982105255,
|
|
"num_tokens": 10130941.0,
|
|
"step": 4875
|
|
},
|
|
{
|
|
"entropy": 5.866014432907105,
|
|
"epoch": 0.4426705370101596,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004986011941154696,
|
|
"loss": 5.7273,
|
|
"mean_token_accuracy": 0.14755107015371322,
|
|
"num_tokens": 10141708.0,
|
|
"step": 4880
|
|
},
|
|
{
|
|
"entropy": 5.807976961135864,
|
|
"epoch": 0.44312409288824384,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004985975894453275,
|
|
"loss": 5.6554,
|
|
"mean_token_accuracy": 0.15046119764447213,
|
|
"num_tokens": 10151816.0,
|
|
"step": 4885
|
|
},
|
|
{
|
|
"entropy": 5.810320949554443,
|
|
"epoch": 0.443577648766328,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004985939801511304,
|
|
"loss": 5.7727,
|
|
"mean_token_accuracy": 0.14902833551168443,
|
|
"num_tokens": 10162470.0,
|
|
"step": 4890
|
|
},
|
|
{
|
|
"entropy": 5.759214115142822,
|
|
"epoch": 0.4440312046444122,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004985903662329527,
|
|
"loss": 5.6688,
|
|
"mean_token_accuracy": 0.15527875274419783,
|
|
"num_tokens": 10173171.0,
|
|
"step": 4895
|
|
},
|
|
{
|
|
"entropy": 5.795230531692505,
|
|
"epoch": 0.44448476052249636,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004985867476908693,
|
|
"loss": 5.7134,
|
|
"mean_token_accuracy": 0.15014212280511857,
|
|
"num_tokens": 10184185.0,
|
|
"step": 4900
|
|
},
|
|
{
|
|
"entropy": 5.781923294067383,
|
|
"epoch": 0.44493831640058057,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004985831245249549,
|
|
"loss": 5.764,
|
|
"mean_token_accuracy": 0.1502835273742676,
|
|
"num_tokens": 10195516.0,
|
|
"step": 4905
|
|
},
|
|
{
|
|
"entropy": 5.752807474136352,
|
|
"epoch": 0.4453918722786647,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004985794967352846,
|
|
"loss": 5.6884,
|
|
"mean_token_accuracy": 0.15242686122655869,
|
|
"num_tokens": 10204936.0,
|
|
"step": 4910
|
|
},
|
|
{
|
|
"entropy": 5.839371204376221,
|
|
"epoch": 0.44584542815674894,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004985758643219334,
|
|
"loss": 5.7183,
|
|
"mean_token_accuracy": 0.15398919135332106,
|
|
"num_tokens": 10216218.0,
|
|
"step": 4915
|
|
},
|
|
{
|
|
"entropy": 5.87683072090149,
|
|
"epoch": 0.4462989840348331,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004985722272849762,
|
|
"loss": 5.7421,
|
|
"mean_token_accuracy": 0.14640209078788757,
|
|
"num_tokens": 10226370.0,
|
|
"step": 4920
|
|
},
|
|
{
|
|
"entropy": 5.758306503295898,
|
|
"epoch": 0.44675253991291725,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004985685856244884,
|
|
"loss": 5.6542,
|
|
"mean_token_accuracy": 0.15684788078069686,
|
|
"num_tokens": 10236170.0,
|
|
"step": 4925
|
|
},
|
|
{
|
|
"entropy": 5.79812445640564,
|
|
"epoch": 0.44720609579100146,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004985649393405453,
|
|
"loss": 5.7329,
|
|
"mean_token_accuracy": 0.1511545680463314,
|
|
"num_tokens": 10246119.0,
|
|
"step": 4930
|
|
},
|
|
{
|
|
"entropy": 5.804480504989624,
|
|
"epoch": 0.4476596516690856,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004985612884332223,
|
|
"loss": 5.7306,
|
|
"mean_token_accuracy": 0.14677015766501428,
|
|
"num_tokens": 10256762.0,
|
|
"step": 4935
|
|
},
|
|
{
|
|
"entropy": 5.74443507194519,
|
|
"epoch": 0.4481132075471698,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004985576329025949,
|
|
"loss": 5.6832,
|
|
"mean_token_accuracy": 0.1538843147456646,
|
|
"num_tokens": 10267317.0,
|
|
"step": 4940
|
|
},
|
|
{
|
|
"entropy": 5.833537530899048,
|
|
"epoch": 0.448566763425254,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004985539727487385,
|
|
"loss": 5.8213,
|
|
"mean_token_accuracy": 0.13688837736845016,
|
|
"num_tokens": 10279111.0,
|
|
"step": 4945
|
|
},
|
|
{
|
|
"entropy": 5.81101803779602,
|
|
"epoch": 0.4490203193033382,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004985503079717292,
|
|
"loss": 5.6847,
|
|
"mean_token_accuracy": 0.152994741499424,
|
|
"num_tokens": 10289383.0,
|
|
"step": 4950
|
|
},
|
|
{
|
|
"entropy": 5.826288223266602,
|
|
"epoch": 0.44947387518142234,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004985466385716425,
|
|
"loss": 5.7095,
|
|
"mean_token_accuracy": 0.15056138932704927,
|
|
"num_tokens": 10299806.0,
|
|
"step": 4955
|
|
},
|
|
{
|
|
"entropy": 5.772299671173096,
|
|
"epoch": 0.44992743105950656,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004985429645485543,
|
|
"loss": 5.7137,
|
|
"mean_token_accuracy": 0.14749846756458282,
|
|
"num_tokens": 10310348.0,
|
|
"step": 4960
|
|
},
|
|
{
|
|
"entropy": 5.797397184371948,
|
|
"epoch": 0.4503809869375907,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004985392859025407,
|
|
"loss": 5.7179,
|
|
"mean_token_accuracy": 0.1548716500401497,
|
|
"num_tokens": 10320354.0,
|
|
"step": 4965
|
|
},
|
|
{
|
|
"entropy": 5.755021715164185,
|
|
"epoch": 0.45083454281567487,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004985356026336776,
|
|
"loss": 5.6464,
|
|
"mean_token_accuracy": 0.15377871841192245,
|
|
"num_tokens": 10330292.0,
|
|
"step": 4970
|
|
},
|
|
{
|
|
"entropy": 5.813851833343506,
|
|
"epoch": 0.4512880986937591,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004985319147420414,
|
|
"loss": 5.6087,
|
|
"mean_token_accuracy": 0.15954625755548477,
|
|
"num_tokens": 10340449.0,
|
|
"step": 4975
|
|
},
|
|
{
|
|
"entropy": 5.773745012283325,
|
|
"epoch": 0.45174165457184323,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004985282222277082,
|
|
"loss": 5.6679,
|
|
"mean_token_accuracy": 0.15184469521045685,
|
|
"num_tokens": 10350637.0,
|
|
"step": 4980
|
|
},
|
|
{
|
|
"entropy": 5.7085271835327145,
|
|
"epoch": 0.45219521044992744,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004985245250907544,
|
|
"loss": 5.6161,
|
|
"mean_token_accuracy": 0.149700116366148,
|
|
"num_tokens": 10361548.0,
|
|
"step": 4985
|
|
},
|
|
{
|
|
"entropy": 5.759440231323242,
|
|
"epoch": 0.4526487663280116,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004985208233312564,
|
|
"loss": 5.6254,
|
|
"mean_token_accuracy": 0.14682499915361405,
|
|
"num_tokens": 10371765.0,
|
|
"step": 4990
|
|
},
|
|
{
|
|
"entropy": 5.842993068695068,
|
|
"epoch": 0.4531023222060958,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004985171169492908,
|
|
"loss": 5.7484,
|
|
"mean_token_accuracy": 0.15154104083776473,
|
|
"num_tokens": 10382108.0,
|
|
"step": 4995
|
|
},
|
|
{
|
|
"entropy": 5.793890333175659,
|
|
"epoch": 0.45355587808417996,
|
|
"grad_norm": 3.21875,
|
|
"learning_rate": 0.0004985134059449344,
|
|
"loss": 5.6946,
|
|
"mean_token_accuracy": 0.152512563765049,
|
|
"num_tokens": 10392390.0,
|
|
"step": 5000
|
|
},
|
|
{
|
|
"entropy": 5.75899076461792,
|
|
"epoch": 0.4540094339622642,
|
|
"grad_norm": 3.234375,
|
|
"learning_rate": 0.0004985096903182637,
|
|
"loss": 5.7425,
|
|
"mean_token_accuracy": 0.15878509283065795,
|
|
"num_tokens": 10402094.0,
|
|
"step": 5005
|
|
},
|
|
{
|
|
"entropy": 5.810795450210572,
|
|
"epoch": 0.45446298984034833,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004985059700693557,
|
|
"loss": 5.7089,
|
|
"mean_token_accuracy": 0.15410526245832443,
|
|
"num_tokens": 10413350.0,
|
|
"step": 5010
|
|
},
|
|
{
|
|
"entropy": 5.805242109298706,
|
|
"epoch": 0.4549165457184325,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004985022451982872,
|
|
"loss": 5.8358,
|
|
"mean_token_accuracy": 0.14019331857562065,
|
|
"num_tokens": 10424292.0,
|
|
"step": 5015
|
|
},
|
|
{
|
|
"entropy": 5.866724157333374,
|
|
"epoch": 0.4553701015965167,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004984985157051354,
|
|
"loss": 5.6723,
|
|
"mean_token_accuracy": 0.15092671811580657,
|
|
"num_tokens": 10433724.0,
|
|
"step": 5020
|
|
},
|
|
{
|
|
"entropy": 5.848974752426147,
|
|
"epoch": 0.45582365747460085,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004984947815899774,
|
|
"loss": 5.7603,
|
|
"mean_token_accuracy": 0.14992742538452147,
|
|
"num_tokens": 10444724.0,
|
|
"step": 5025
|
|
},
|
|
{
|
|
"entropy": 5.833653450012207,
|
|
"epoch": 0.45627721335268506,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004984910428528902,
|
|
"loss": 5.6826,
|
|
"mean_token_accuracy": 0.1587917149066925,
|
|
"num_tokens": 10455086.0,
|
|
"step": 5030
|
|
},
|
|
{
|
|
"entropy": 5.742634630203247,
|
|
"epoch": 0.4567307692307692,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004984872994939514,
|
|
"loss": 5.65,
|
|
"mean_token_accuracy": 0.14961964190006255,
|
|
"num_tokens": 10465076.0,
|
|
"step": 5035
|
|
},
|
|
{
|
|
"entropy": 5.792289400100708,
|
|
"epoch": 0.45718432510885343,
|
|
"grad_norm": 3.171875,
|
|
"learning_rate": 0.0004984835515132382,
|
|
"loss": 5.6824,
|
|
"mean_token_accuracy": 0.1561535358428955,
|
|
"num_tokens": 10474817.0,
|
|
"step": 5040
|
|
},
|
|
{
|
|
"entropy": 5.819376420974732,
|
|
"epoch": 0.4576378809869376,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004984797989108282,
|
|
"loss": 5.6929,
|
|
"mean_token_accuracy": 0.14523695558309554,
|
|
"num_tokens": 10485735.0,
|
|
"step": 5045
|
|
},
|
|
{
|
|
"entropy": 5.760282325744629,
|
|
"epoch": 0.4580914368650218,
|
|
"grad_norm": 5.40625,
|
|
"learning_rate": 0.0004984760416867991,
|
|
"loss": 5.7899,
|
|
"mean_token_accuracy": 0.14944545552134514,
|
|
"num_tokens": 10496731.0,
|
|
"step": 5050
|
|
},
|
|
{
|
|
"entropy": 5.723328304290772,
|
|
"epoch": 0.45854499274310595,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004984722798412286,
|
|
"loss": 5.6457,
|
|
"mean_token_accuracy": 0.15127401053905487,
|
|
"num_tokens": 10506787.0,
|
|
"step": 5055
|
|
},
|
|
{
|
|
"entropy": 5.821808862686157,
|
|
"epoch": 0.4589985486211901,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004984685133741941,
|
|
"loss": 5.7131,
|
|
"mean_token_accuracy": 0.15030114501714706,
|
|
"num_tokens": 10517170.0,
|
|
"step": 5060
|
|
},
|
|
{
|
|
"entropy": 5.830482482910156,
|
|
"epoch": 0.4594521044992743,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.000498464742285774,
|
|
"loss": 5.7078,
|
|
"mean_token_accuracy": 0.1527443915605545,
|
|
"num_tokens": 10527342.0,
|
|
"step": 5065
|
|
},
|
|
{
|
|
"entropy": 5.818163919448852,
|
|
"epoch": 0.45990566037735847,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.000498460966576046,
|
|
"loss": 5.6866,
|
|
"mean_token_accuracy": 0.15609674155712128,
|
|
"num_tokens": 10537253.0,
|
|
"step": 5070
|
|
},
|
|
{
|
|
"entropy": 5.819856405258179,
|
|
"epoch": 0.4603592162554427,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004984571862450884,
|
|
"loss": 5.6989,
|
|
"mean_token_accuracy": 0.15164147466421127,
|
|
"num_tokens": 10547249.0,
|
|
"step": 5075
|
|
},
|
|
{
|
|
"entropy": 5.820227432250976,
|
|
"epoch": 0.46081277213352684,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004984534012929791,
|
|
"loss": 5.7285,
|
|
"mean_token_accuracy": 0.15311849117279053,
|
|
"num_tokens": 10558174.0,
|
|
"step": 5080
|
|
},
|
|
{
|
|
"entropy": 5.867569541931152,
|
|
"epoch": 0.46126632801161105,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004984496117197967,
|
|
"loss": 5.6984,
|
|
"mean_token_accuracy": 0.15882893800735473,
|
|
"num_tokens": 10567610.0,
|
|
"step": 5085
|
|
},
|
|
{
|
|
"entropy": 5.770347452163696,
|
|
"epoch": 0.4617198838896952,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004984458175256193,
|
|
"loss": 5.7127,
|
|
"mean_token_accuracy": 0.1474909946322441,
|
|
"num_tokens": 10578494.0,
|
|
"step": 5090
|
|
},
|
|
{
|
|
"entropy": 5.84233832359314,
|
|
"epoch": 0.4621734397677794,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004984420187105253,
|
|
"loss": 5.8042,
|
|
"mean_token_accuracy": 0.15005899965763092,
|
|
"num_tokens": 10589482.0,
|
|
"step": 5095
|
|
},
|
|
{
|
|
"entropy": 5.844469022750855,
|
|
"epoch": 0.46262699564586357,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004984382152745936,
|
|
"loss": 5.7548,
|
|
"mean_token_accuracy": 0.14896771609783171,
|
|
"num_tokens": 10599965.0,
|
|
"step": 5100
|
|
},
|
|
{
|
|
"entropy": 5.837211656570434,
|
|
"epoch": 0.4630805515239477,
|
|
"grad_norm": 3.15625,
|
|
"learning_rate": 0.0004984344072179026,
|
|
"loss": 5.7981,
|
|
"mean_token_accuracy": 0.15154444575309753,
|
|
"num_tokens": 10610500.0,
|
|
"step": 5105
|
|
},
|
|
{
|
|
"entropy": 5.847231006622314,
|
|
"epoch": 0.46353410740203194,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004984305945405312,
|
|
"loss": 5.7322,
|
|
"mean_token_accuracy": 0.15490227639675141,
|
|
"num_tokens": 10619843.0,
|
|
"step": 5110
|
|
},
|
|
{
|
|
"entropy": 5.841805505752563,
|
|
"epoch": 0.4639876632801161,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.000498426777242558,
|
|
"loss": 5.6631,
|
|
"mean_token_accuracy": 0.15643091574311258,
|
|
"num_tokens": 10631026.0,
|
|
"step": 5115
|
|
},
|
|
{
|
|
"entropy": 5.654076147079468,
|
|
"epoch": 0.4644412191582003,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004984229553240623,
|
|
"loss": 5.6675,
|
|
"mean_token_accuracy": 0.15852237939834596,
|
|
"num_tokens": 10641130.0,
|
|
"step": 5120
|
|
},
|
|
{
|
|
"entropy": 5.7756763935089115,
|
|
"epoch": 0.46489477503628446,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004984191287851228,
|
|
"loss": 5.725,
|
|
"mean_token_accuracy": 0.15592035204172133,
|
|
"num_tokens": 10652305.0,
|
|
"step": 5125
|
|
},
|
|
{
|
|
"entropy": 5.886051511764526,
|
|
"epoch": 0.46534833091436867,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004984152976258188,
|
|
"loss": 5.7613,
|
|
"mean_token_accuracy": 0.1512484297156334,
|
|
"num_tokens": 10663083.0,
|
|
"step": 5130
|
|
},
|
|
{
|
|
"entropy": 5.774004697799683,
|
|
"epoch": 0.4658018867924528,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004984114618462296,
|
|
"loss": 5.7842,
|
|
"mean_token_accuracy": 0.14426478892564773,
|
|
"num_tokens": 10673602.0,
|
|
"step": 5135
|
|
},
|
|
{
|
|
"entropy": 5.794326400756836,
|
|
"epoch": 0.46625544267053703,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004984076214464343,
|
|
"loss": 5.6242,
|
|
"mean_token_accuracy": 0.15901431143283845,
|
|
"num_tokens": 10684622.0,
|
|
"step": 5140
|
|
},
|
|
{
|
|
"entropy": 5.887795543670654,
|
|
"epoch": 0.4667089985486212,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004984037764265126,
|
|
"loss": 5.7383,
|
|
"mean_token_accuracy": 0.15451854169368745,
|
|
"num_tokens": 10695129.0,
|
|
"step": 5145
|
|
},
|
|
{
|
|
"entropy": 5.766786050796509,
|
|
"epoch": 0.46716255442670535,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004983999267865438,
|
|
"loss": 5.5757,
|
|
"mean_token_accuracy": 0.1634918212890625,
|
|
"num_tokens": 10705236.0,
|
|
"step": 5150
|
|
},
|
|
{
|
|
"entropy": 5.73983416557312,
|
|
"epoch": 0.46761611030478956,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004983960725266078,
|
|
"loss": 5.6921,
|
|
"mean_token_accuracy": 0.1524804301559925,
|
|
"num_tokens": 10715748.0,
|
|
"step": 5155
|
|
},
|
|
{
|
|
"entropy": 5.793629693984985,
|
|
"epoch": 0.4680696661828737,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004983922136467838,
|
|
"loss": 5.6295,
|
|
"mean_token_accuracy": 0.15277455896139144,
|
|
"num_tokens": 10725799.0,
|
|
"step": 5160
|
|
},
|
|
{
|
|
"entropy": 5.825521945953369,
|
|
"epoch": 0.4685232220609579,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.000498388350147152,
|
|
"loss": 5.7382,
|
|
"mean_token_accuracy": 0.15017426609992982,
|
|
"num_tokens": 10735668.0,
|
|
"step": 5165
|
|
},
|
|
{
|
|
"entropy": 5.887571239471436,
|
|
"epoch": 0.4689767779390421,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004983844820277922,
|
|
"loss": 5.8401,
|
|
"mean_token_accuracy": 0.14530294463038446,
|
|
"num_tokens": 10746466.0,
|
|
"step": 5170
|
|
},
|
|
{
|
|
"entropy": 5.886936998367309,
|
|
"epoch": 0.4694303338171263,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004983806092887843,
|
|
"loss": 5.7568,
|
|
"mean_token_accuracy": 0.1505974516272545,
|
|
"num_tokens": 10756724.0,
|
|
"step": 5175
|
|
},
|
|
{
|
|
"entropy": 5.797704792022705,
|
|
"epoch": 0.46988388969521044,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004983767319302086,
|
|
"loss": 5.7777,
|
|
"mean_token_accuracy": 0.152411787211895,
|
|
"num_tokens": 10766919.0,
|
|
"step": 5180
|
|
},
|
|
{
|
|
"entropy": 5.723730754852295,
|
|
"epoch": 0.47033744557329465,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004983728499521451,
|
|
"loss": 5.5886,
|
|
"mean_token_accuracy": 0.1582037776708603,
|
|
"num_tokens": 10777550.0,
|
|
"step": 5185
|
|
},
|
|
{
|
|
"entropy": 5.76413779258728,
|
|
"epoch": 0.4707910014513788,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004983689633546741,
|
|
"loss": 5.6539,
|
|
"mean_token_accuracy": 0.14905960708856583,
|
|
"num_tokens": 10788456.0,
|
|
"step": 5190
|
|
},
|
|
{
|
|
"entropy": 5.785346984863281,
|
|
"epoch": 0.47124455732946297,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004983650721378761,
|
|
"loss": 5.7027,
|
|
"mean_token_accuracy": 0.150688636302948,
|
|
"num_tokens": 10800049.0,
|
|
"step": 5195
|
|
},
|
|
{
|
|
"entropy": 5.839448738098144,
|
|
"epoch": 0.4716981132075472,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.0004983611763018314,
|
|
"loss": 5.7305,
|
|
"mean_token_accuracy": 0.14705110639333724,
|
|
"num_tokens": 10810743.0,
|
|
"step": 5200
|
|
},
|
|
{
|
|
"entropy": 5.903285980224609,
|
|
"epoch": 0.47215166908563133,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004983572758466208,
|
|
"loss": 5.9008,
|
|
"mean_token_accuracy": 0.14664009138941764,
|
|
"num_tokens": 10821897.0,
|
|
"step": 5205
|
|
},
|
|
{
|
|
"entropy": 5.864152622222901,
|
|
"epoch": 0.47260522496371554,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004983533707723247,
|
|
"loss": 5.7536,
|
|
"mean_token_accuracy": 0.1474456422030926,
|
|
"num_tokens": 10831589.0,
|
|
"step": 5210
|
|
},
|
|
{
|
|
"entropy": 5.839668083190918,
|
|
"epoch": 0.4730587808417997,
|
|
"grad_norm": 3.15625,
|
|
"learning_rate": 0.0004983494610790241,
|
|
"loss": 5.6822,
|
|
"mean_token_accuracy": 0.14612138271331787,
|
|
"num_tokens": 10841404.0,
|
|
"step": 5215
|
|
},
|
|
{
|
|
"entropy": 5.779344511032105,
|
|
"epoch": 0.4735123367198839,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004983455467667996,
|
|
"loss": 5.7107,
|
|
"mean_token_accuracy": 0.14737479761242867,
|
|
"num_tokens": 10851577.0,
|
|
"step": 5220
|
|
},
|
|
{
|
|
"entropy": 5.737367773056031,
|
|
"epoch": 0.47396589259796806,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004983416278357322,
|
|
"loss": 5.6337,
|
|
"mean_token_accuracy": 0.15840625911951065,
|
|
"num_tokens": 10861403.0,
|
|
"step": 5225
|
|
},
|
|
{
|
|
"entropy": 5.810776615142823,
|
|
"epoch": 0.4744194484760523,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004983377042859032,
|
|
"loss": 5.683,
|
|
"mean_token_accuracy": 0.15175287276506425,
|
|
"num_tokens": 10871933.0,
|
|
"step": 5230
|
|
},
|
|
{
|
|
"entropy": 5.828769016265869,
|
|
"epoch": 0.47487300435413643,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004983337761173936,
|
|
"loss": 5.7531,
|
|
"mean_token_accuracy": 0.15067264437675476,
|
|
"num_tokens": 10881800.0,
|
|
"step": 5235
|
|
},
|
|
{
|
|
"entropy": 5.891356468200684,
|
|
"epoch": 0.4753265602322206,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.0004983298433302843,
|
|
"loss": 5.7103,
|
|
"mean_token_accuracy": 0.148338982462883,
|
|
"num_tokens": 10891830.0,
|
|
"step": 5240
|
|
},
|
|
{
|
|
"entropy": 5.783552646636963,
|
|
"epoch": 0.4757801161103048,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004983259059246572,
|
|
"loss": 5.6244,
|
|
"mean_token_accuracy": 0.15633412152528764,
|
|
"num_tokens": 10901557.0,
|
|
"step": 5245
|
|
},
|
|
{
|
|
"entropy": 5.69632363319397,
|
|
"epoch": 0.47623367198838895,
|
|
"grad_norm": 4.9375,
|
|
"learning_rate": 0.0004983219639005934,
|
|
"loss": 5.7349,
|
|
"mean_token_accuracy": 0.14440841749310493,
|
|
"num_tokens": 10912155.0,
|
|
"step": 5250
|
|
},
|
|
{
|
|
"entropy": 5.76448540687561,
|
|
"epoch": 0.47668722786647316,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004983180172581745,
|
|
"loss": 5.6588,
|
|
"mean_token_accuracy": 0.15334019362926482,
|
|
"num_tokens": 10922291.0,
|
|
"step": 5255
|
|
},
|
|
{
|
|
"entropy": 5.8298650741577145,
|
|
"epoch": 0.4771407837445573,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004983140659974819,
|
|
"loss": 5.7061,
|
|
"mean_token_accuracy": 0.1492989644408226,
|
|
"num_tokens": 10933176.0,
|
|
"step": 5260
|
|
},
|
|
{
|
|
"entropy": 5.863755178451538,
|
|
"epoch": 0.47759433962264153,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004983101101185977,
|
|
"loss": 5.7933,
|
|
"mean_token_accuracy": 0.14786036014556886,
|
|
"num_tokens": 10944049.0,
|
|
"step": 5265
|
|
},
|
|
{
|
|
"entropy": 5.7591461658477785,
|
|
"epoch": 0.4780478955007257,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004983061496216035,
|
|
"loss": 5.6509,
|
|
"mean_token_accuracy": 0.15584611147642136,
|
|
"num_tokens": 10954347.0,
|
|
"step": 5270
|
|
},
|
|
{
|
|
"entropy": 5.797364330291748,
|
|
"epoch": 0.4785014513788099,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004983021845065812,
|
|
"loss": 5.7072,
|
|
"mean_token_accuracy": 0.14649278968572615,
|
|
"num_tokens": 10965123.0,
|
|
"step": 5275
|
|
},
|
|
{
|
|
"entropy": 5.786959505081176,
|
|
"epoch": 0.47895500725689405,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004982982147736128,
|
|
"loss": 5.6946,
|
|
"mean_token_accuracy": 0.15307522416114808,
|
|
"num_tokens": 10976395.0,
|
|
"step": 5280
|
|
},
|
|
{
|
|
"entropy": 5.78529634475708,
|
|
"epoch": 0.4794085631349782,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004982942404227805,
|
|
"loss": 5.6782,
|
|
"mean_token_accuracy": 0.15125040709972382,
|
|
"num_tokens": 10986797.0,
|
|
"step": 5285
|
|
},
|
|
{
|
|
"entropy": 5.859493732452393,
|
|
"epoch": 0.4798621190130624,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.0004982902614541662,
|
|
"loss": 5.7408,
|
|
"mean_token_accuracy": 0.1478838101029396,
|
|
"num_tokens": 10997229.0,
|
|
"step": 5290
|
|
},
|
|
{
|
|
"entropy": 5.80925989151001,
|
|
"epoch": 0.48031567489114657,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004982862778678526,
|
|
"loss": 5.6847,
|
|
"mean_token_accuracy": 0.15592680871486664,
|
|
"num_tokens": 11008180.0,
|
|
"step": 5295
|
|
},
|
|
{
|
|
"entropy": 5.8700981616973875,
|
|
"epoch": 0.4807692307692308,
|
|
"grad_norm": 2.9375,
|
|
"learning_rate": 0.0004982822896639218,
|
|
"loss": 5.7015,
|
|
"mean_token_accuracy": 0.1546702854335308,
|
|
"num_tokens": 11019248.0,
|
|
"step": 5300
|
|
},
|
|
{
|
|
"entropy": 5.742985486984253,
|
|
"epoch": 0.48122278664731494,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004982782968424563,
|
|
"loss": 5.627,
|
|
"mean_token_accuracy": 0.1553596355021,
|
|
"num_tokens": 11029760.0,
|
|
"step": 5305
|
|
},
|
|
{
|
|
"entropy": 5.761133146286011,
|
|
"epoch": 0.48167634252539915,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004982742994035388,
|
|
"loss": 5.6959,
|
|
"mean_token_accuracy": 0.15285762995481492,
|
|
"num_tokens": 11039211.0,
|
|
"step": 5310
|
|
},
|
|
{
|
|
"entropy": 5.807599353790283,
|
|
"epoch": 0.4821298984034833,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004982702973472518,
|
|
"loss": 5.68,
|
|
"mean_token_accuracy": 0.14845879822969438,
|
|
"num_tokens": 11049892.0,
|
|
"step": 5315
|
|
},
|
|
{
|
|
"entropy": 5.902496957778931,
|
|
"epoch": 0.4825834542815675,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004982662906736783,
|
|
"loss": 5.7432,
|
|
"mean_token_accuracy": 0.1499881386756897,
|
|
"num_tokens": 11060823.0,
|
|
"step": 5320
|
|
},
|
|
{
|
|
"entropy": 5.758925247192383,
|
|
"epoch": 0.48303701015965167,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004982622793829009,
|
|
"loss": 5.7125,
|
|
"mean_token_accuracy": 0.15161036998033522,
|
|
"num_tokens": 11072353.0,
|
|
"step": 5325
|
|
},
|
|
{
|
|
"entropy": 5.734290838241577,
|
|
"epoch": 0.4834905660377358,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004982582634750027,
|
|
"loss": 5.7187,
|
|
"mean_token_accuracy": 0.1546842187643051,
|
|
"num_tokens": 11082655.0,
|
|
"step": 5330
|
|
},
|
|
{
|
|
"entropy": 5.862860250473022,
|
|
"epoch": 0.48394412191582004,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004982542429500667,
|
|
"loss": 5.7398,
|
|
"mean_token_accuracy": 0.15047571957111358,
|
|
"num_tokens": 11093315.0,
|
|
"step": 5335
|
|
},
|
|
{
|
|
"entropy": 5.680254030227661,
|
|
"epoch": 0.4843976777939042,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004982502178081761,
|
|
"loss": 5.6287,
|
|
"mean_token_accuracy": 0.15498099178075792,
|
|
"num_tokens": 11103074.0,
|
|
"step": 5340
|
|
},
|
|
{
|
|
"entropy": 5.764597225189209,
|
|
"epoch": 0.4848512336719884,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004982461880494141,
|
|
"loss": 5.685,
|
|
"mean_token_accuracy": 0.15466154515743255,
|
|
"num_tokens": 11113636.0,
|
|
"step": 5345
|
|
},
|
|
{
|
|
"entropy": 5.837761116027832,
|
|
"epoch": 0.48530478955007256,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.000498242153673864,
|
|
"loss": 5.6285,
|
|
"mean_token_accuracy": 0.15595686733722686,
|
|
"num_tokens": 11123509.0,
|
|
"step": 5350
|
|
},
|
|
{
|
|
"entropy": 5.773257827758789,
|
|
"epoch": 0.48575834542815677,
|
|
"grad_norm": 5.40625,
|
|
"learning_rate": 0.0004982381146816094,
|
|
"loss": 5.6869,
|
|
"mean_token_accuracy": 0.14768464267253875,
|
|
"num_tokens": 11133405.0,
|
|
"step": 5355
|
|
},
|
|
{
|
|
"entropy": 5.839870834350586,
|
|
"epoch": 0.4862119013062409,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004982340710727336,
|
|
"loss": 5.7506,
|
|
"mean_token_accuracy": 0.14249877035617828,
|
|
"num_tokens": 11144725.0,
|
|
"step": 5360
|
|
},
|
|
{
|
|
"entropy": 5.817921447753906,
|
|
"epoch": 0.48666545718432513,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004982300228473203,
|
|
"loss": 5.6389,
|
|
"mean_token_accuracy": 0.15178342014551163,
|
|
"num_tokens": 11155446.0,
|
|
"step": 5365
|
|
},
|
|
{
|
|
"entropy": 5.790373659133911,
|
|
"epoch": 0.4871190130624093,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004982259700054533,
|
|
"loss": 5.7171,
|
|
"mean_token_accuracy": 0.15540633648633956,
|
|
"num_tokens": 11165380.0,
|
|
"step": 5370
|
|
},
|
|
{
|
|
"entropy": 5.789110803604126,
|
|
"epoch": 0.48757256894049344,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004982219125472163,
|
|
"loss": 5.7436,
|
|
"mean_token_accuracy": 0.15281054824590684,
|
|
"num_tokens": 11175641.0,
|
|
"step": 5375
|
|
},
|
|
{
|
|
"entropy": 5.936801338195801,
|
|
"epoch": 0.48802612481857766,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004982178504726933,
|
|
"loss": 5.9078,
|
|
"mean_token_accuracy": 0.14865122362971306,
|
|
"num_tokens": 11186257.0,
|
|
"step": 5380
|
|
},
|
|
{
|
|
"entropy": 5.878651189804077,
|
|
"epoch": 0.4884796806966618,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004982137837819682,
|
|
"loss": 5.7208,
|
|
"mean_token_accuracy": 0.14411981850862504,
|
|
"num_tokens": 11197284.0,
|
|
"step": 5385
|
|
},
|
|
{
|
|
"entropy": 5.793639707565307,
|
|
"epoch": 0.488933236574746,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004982097124751252,
|
|
"loss": 5.7082,
|
|
"mean_token_accuracy": 0.15416025072336198,
|
|
"num_tokens": 11208413.0,
|
|
"step": 5390
|
|
},
|
|
{
|
|
"entropy": 5.765456247329712,
|
|
"epoch": 0.4893867924528302,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004982056365522486,
|
|
"loss": 5.7144,
|
|
"mean_token_accuracy": 0.15092865526676177,
|
|
"num_tokens": 11219016.0,
|
|
"step": 5395
|
|
},
|
|
{
|
|
"entropy": 5.786841249465942,
|
|
"epoch": 0.4898403483309144,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004982015560134225,
|
|
"loss": 5.6889,
|
|
"mean_token_accuracy": 0.15537251830101012,
|
|
"num_tokens": 11228934.0,
|
|
"step": 5400
|
|
},
|
|
{
|
|
"entropy": 5.782479906082154,
|
|
"epoch": 0.49029390420899854,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004981974708587312,
|
|
"loss": 5.6246,
|
|
"mean_token_accuracy": 0.1535349190235138,
|
|
"num_tokens": 11239596.0,
|
|
"step": 5405
|
|
},
|
|
{
|
|
"entropy": 5.733927965164185,
|
|
"epoch": 0.49074746008708275,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004981933810882594,
|
|
"loss": 5.6093,
|
|
"mean_token_accuracy": 0.1489216908812523,
|
|
"num_tokens": 11249560.0,
|
|
"step": 5410
|
|
},
|
|
{
|
|
"entropy": 5.848641347885132,
|
|
"epoch": 0.4912010159651669,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004981892867020917,
|
|
"loss": 5.8021,
|
|
"mean_token_accuracy": 0.1476719044148922,
|
|
"num_tokens": 11259787.0,
|
|
"step": 5415
|
|
},
|
|
{
|
|
"entropy": 5.838620996475219,
|
|
"epoch": 0.49165457184325106,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004981851877003125,
|
|
"loss": 5.7201,
|
|
"mean_token_accuracy": 0.15290852189064025,
|
|
"num_tokens": 11269717.0,
|
|
"step": 5420
|
|
},
|
|
{
|
|
"entropy": 5.760362434387207,
|
|
"epoch": 0.4921081277213353,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004981810840830068,
|
|
"loss": 5.7136,
|
|
"mean_token_accuracy": 0.15744489878416063,
|
|
"num_tokens": 11279863.0,
|
|
"step": 5425
|
|
},
|
|
{
|
|
"entropy": 5.87311692237854,
|
|
"epoch": 0.49256168359941943,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004981769758502596,
|
|
"loss": 5.8277,
|
|
"mean_token_accuracy": 0.1397744357585907,
|
|
"num_tokens": 11291161.0,
|
|
"step": 5430
|
|
},
|
|
{
|
|
"entropy": 5.768136358261108,
|
|
"epoch": 0.49301523947750364,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004981728630021555,
|
|
"loss": 5.6521,
|
|
"mean_token_accuracy": 0.1497293785214424,
|
|
"num_tokens": 11301151.0,
|
|
"step": 5435
|
|
},
|
|
{
|
|
"entropy": 5.687364625930786,
|
|
"epoch": 0.4934687953555878,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004981687455387797,
|
|
"loss": 5.6485,
|
|
"mean_token_accuracy": 0.15389353632926941,
|
|
"num_tokens": 11311466.0,
|
|
"step": 5440
|
|
},
|
|
{
|
|
"entropy": 5.780608606338501,
|
|
"epoch": 0.493922351233672,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004981646234602173,
|
|
"loss": 5.6273,
|
|
"mean_token_accuracy": 0.15507608875632287,
|
|
"num_tokens": 11321522.0,
|
|
"step": 5445
|
|
},
|
|
{
|
|
"entropy": 5.889606618881226,
|
|
"epoch": 0.49437590711175616,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004981604967665539,
|
|
"loss": 5.7239,
|
|
"mean_token_accuracy": 0.15444112122058867,
|
|
"num_tokens": 11332317.0,
|
|
"step": 5450
|
|
},
|
|
{
|
|
"entropy": 5.775820875167847,
|
|
"epoch": 0.4948294629898404,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004981563654578743,
|
|
"loss": 5.6535,
|
|
"mean_token_accuracy": 0.1533982649445534,
|
|
"num_tokens": 11343024.0,
|
|
"step": 5455
|
|
},
|
|
{
|
|
"entropy": 5.723749732971191,
|
|
"epoch": 0.49528301886792453,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004981522295342643,
|
|
"loss": 5.6269,
|
|
"mean_token_accuracy": 0.15509956181049347,
|
|
"num_tokens": 11353114.0,
|
|
"step": 5460
|
|
},
|
|
{
|
|
"entropy": 5.742253732681275,
|
|
"epoch": 0.4957365747460087,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004981480889958092,
|
|
"loss": 5.6881,
|
|
"mean_token_accuracy": 0.15197990238666534,
|
|
"num_tokens": 11363446.0,
|
|
"step": 5465
|
|
},
|
|
{
|
|
"entropy": 5.742916679382324,
|
|
"epoch": 0.4961901306240929,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004981439438425949,
|
|
"loss": 5.6744,
|
|
"mean_token_accuracy": 0.1593330755829811,
|
|
"num_tokens": 11373413.0,
|
|
"step": 5470
|
|
},
|
|
{
|
|
"entropy": 5.726079893112183,
|
|
"epoch": 0.49664368650217705,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.000498139794074707,
|
|
"loss": 5.5631,
|
|
"mean_token_accuracy": 0.1633937731385231,
|
|
"num_tokens": 11383142.0,
|
|
"step": 5475
|
|
},
|
|
{
|
|
"entropy": 5.801775550842285,
|
|
"epoch": 0.49709724238026126,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004981356396922313,
|
|
"loss": 5.725,
|
|
"mean_token_accuracy": 0.1524003639817238,
|
|
"num_tokens": 11394635.0,
|
|
"step": 5480
|
|
},
|
|
{
|
|
"entropy": 5.723491621017456,
|
|
"epoch": 0.4975507982583454,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004981314806952535,
|
|
"loss": 5.605,
|
|
"mean_token_accuracy": 0.15672532916069032,
|
|
"num_tokens": 11404442.0,
|
|
"step": 5485
|
|
},
|
|
{
|
|
"entropy": 5.684481000900268,
|
|
"epoch": 0.49800435413642963,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.00049812731708386,
|
|
"loss": 5.5663,
|
|
"mean_token_accuracy": 0.15349014550447465,
|
|
"num_tokens": 11414217.0,
|
|
"step": 5490
|
|
},
|
|
{
|
|
"entropy": 5.811336708068848,
|
|
"epoch": 0.4984579100145138,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004981231488581367,
|
|
"loss": 5.7135,
|
|
"mean_token_accuracy": 0.14815668091177941,
|
|
"num_tokens": 11423834.0,
|
|
"step": 5495
|
|
},
|
|
{
|
|
"entropy": 5.693011617660522,
|
|
"epoch": 0.498911465892598,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004981189760181699,
|
|
"loss": 5.5814,
|
|
"mean_token_accuracy": 0.15378208011388778,
|
|
"num_tokens": 11433613.0,
|
|
"step": 5500
|
|
},
|
|
{
|
|
"entropy": 5.705790615081787,
|
|
"epoch": 0.49936502177068215,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004981147985640456,
|
|
"loss": 5.6571,
|
|
"mean_token_accuracy": 0.15362219214439393,
|
|
"num_tokens": 11443915.0,
|
|
"step": 5505
|
|
},
|
|
{
|
|
"entropy": 5.848033380508423,
|
|
"epoch": 0.4998185776487663,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004981106164958506,
|
|
"loss": 5.6773,
|
|
"mean_token_accuracy": 0.14845840334892274,
|
|
"num_tokens": 11454588.0,
|
|
"step": 5510
|
|
},
|
|
{
|
|
"entropy": 5.781160163879394,
|
|
"epoch": 0.5002721335268505,
|
|
"grad_norm": 3.078125,
|
|
"learning_rate": 0.0004981064298136712,
|
|
"loss": 5.7431,
|
|
"mean_token_accuracy": 0.15234173238277435,
|
|
"num_tokens": 11465533.0,
|
|
"step": 5515
|
|
},
|
|
{
|
|
"entropy": 5.716646528244018,
|
|
"epoch": 0.5007256894049347,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004981022385175939,
|
|
"loss": 5.6984,
|
|
"mean_token_accuracy": 0.14256466552615166,
|
|
"num_tokens": 11475776.0,
|
|
"step": 5520
|
|
},
|
|
{
|
|
"entropy": 5.807872915267945,
|
|
"epoch": 0.5011792452830188,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004980980426077054,
|
|
"loss": 5.6711,
|
|
"mean_token_accuracy": 0.16105100214481355,
|
|
"num_tokens": 11486200.0,
|
|
"step": 5525
|
|
},
|
|
{
|
|
"entropy": 5.822145271301269,
|
|
"epoch": 0.5016328011611031,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004980938420840926,
|
|
"loss": 5.6859,
|
|
"mean_token_accuracy": 0.15076019763946533,
|
|
"num_tokens": 11496768.0,
|
|
"step": 5530
|
|
},
|
|
{
|
|
"entropy": 5.805276823043823,
|
|
"epoch": 0.5020863570391872,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004980896369468423,
|
|
"loss": 5.6786,
|
|
"mean_token_accuracy": 0.1519462376832962,
|
|
"num_tokens": 11507096.0,
|
|
"step": 5535
|
|
},
|
|
{
|
|
"entropy": 5.724911499023437,
|
|
"epoch": 0.5025399129172714,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004980854271960415,
|
|
"loss": 5.7198,
|
|
"mean_token_accuracy": 0.14966288208961487,
|
|
"num_tokens": 11517301.0,
|
|
"step": 5540
|
|
},
|
|
{
|
|
"entropy": 5.842235517501831,
|
|
"epoch": 0.5029934687953556,
|
|
"grad_norm": 3.734375,
|
|
"learning_rate": 0.0004980812128317772,
|
|
"loss": 5.7666,
|
|
"mean_token_accuracy": 0.15556451082229614,
|
|
"num_tokens": 11528616.0,
|
|
"step": 5545
|
|
},
|
|
{
|
|
"entropy": 5.861762285232544,
|
|
"epoch": 0.5034470246734397,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004980769938541364,
|
|
"loss": 5.6969,
|
|
"mean_token_accuracy": 0.15842931866645812,
|
|
"num_tokens": 11539344.0,
|
|
"step": 5550
|
|
},
|
|
{
|
|
"entropy": 5.806245136260986,
|
|
"epoch": 0.503900580551524,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004980727702632066,
|
|
"loss": 5.7601,
|
|
"mean_token_accuracy": 0.15045208632946014,
|
|
"num_tokens": 11549511.0,
|
|
"step": 5555
|
|
},
|
|
{
|
|
"entropy": 5.816326236724853,
|
|
"epoch": 0.5043541364296081,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004980685420590752,
|
|
"loss": 5.6754,
|
|
"mean_token_accuracy": 0.1513192594051361,
|
|
"num_tokens": 11559425.0,
|
|
"step": 5560
|
|
},
|
|
{
|
|
"entropy": 5.87260160446167,
|
|
"epoch": 0.5048076923076923,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004980643092418294,
|
|
"loss": 5.7977,
|
|
"mean_token_accuracy": 0.14498255625367165,
|
|
"num_tokens": 11570406.0,
|
|
"step": 5565
|
|
},
|
|
{
|
|
"entropy": 5.791260766983032,
|
|
"epoch": 0.5052612481857764,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004980600718115568,
|
|
"loss": 5.6713,
|
|
"mean_token_accuracy": 0.15540144369006156,
|
|
"num_tokens": 11580509.0,
|
|
"step": 5570
|
|
},
|
|
{
|
|
"entropy": 5.755546998977661,
|
|
"epoch": 0.5057148040638607,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004980558297683452,
|
|
"loss": 5.6906,
|
|
"mean_token_accuracy": 0.15466409027576447,
|
|
"num_tokens": 11590860.0,
|
|
"step": 5575
|
|
},
|
|
{
|
|
"entropy": 5.817662000656128,
|
|
"epoch": 0.5061683599419449,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004980515831122822,
|
|
"loss": 5.698,
|
|
"mean_token_accuracy": 0.15118605718016626,
|
|
"num_tokens": 11601954.0,
|
|
"step": 5580
|
|
},
|
|
{
|
|
"entropy": 5.831102275848389,
|
|
"epoch": 0.506621915820029,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004980473318434555,
|
|
"loss": 5.7026,
|
|
"mean_token_accuracy": 0.15453651696443557,
|
|
"num_tokens": 11612581.0,
|
|
"step": 5585
|
|
},
|
|
{
|
|
"entropy": 5.728653049468994,
|
|
"epoch": 0.5070754716981132,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004980430759619532,
|
|
"loss": 5.6293,
|
|
"mean_token_accuracy": 0.15604719668626785,
|
|
"num_tokens": 11622599.0,
|
|
"step": 5590
|
|
},
|
|
{
|
|
"entropy": 5.730202388763428,
|
|
"epoch": 0.5075290275761973,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004980388154678633,
|
|
"loss": 5.6586,
|
|
"mean_token_accuracy": 0.1495005428791046,
|
|
"num_tokens": 11633611.0,
|
|
"step": 5595
|
|
},
|
|
{
|
|
"entropy": 5.6968724727630615,
|
|
"epoch": 0.5079825834542816,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004980345503612738,
|
|
"loss": 5.6107,
|
|
"mean_token_accuracy": 0.1538061574101448,
|
|
"num_tokens": 11643159.0,
|
|
"step": 5600
|
|
},
|
|
{
|
|
"entropy": 5.753897953033447,
|
|
"epoch": 0.5084361393323658,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004980302806422729,
|
|
"loss": 5.6204,
|
|
"mean_token_accuracy": 0.15607504695653915,
|
|
"num_tokens": 11653174.0,
|
|
"step": 5605
|
|
},
|
|
{
|
|
"entropy": 5.755003118515015,
|
|
"epoch": 0.5088896952104499,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004980260063109491,
|
|
"loss": 5.6672,
|
|
"mean_token_accuracy": 0.1535380646586418,
|
|
"num_tokens": 11662621.0,
|
|
"step": 5610
|
|
},
|
|
{
|
|
"entropy": 5.701317262649536,
|
|
"epoch": 0.5093432510885341,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004980217273673906,
|
|
"loss": 5.6218,
|
|
"mean_token_accuracy": 0.15659913867712022,
|
|
"num_tokens": 11673538.0,
|
|
"step": 5615
|
|
},
|
|
{
|
|
"entropy": 5.802594709396362,
|
|
"epoch": 0.5097968069666183,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004980174438116859,
|
|
"loss": 5.6228,
|
|
"mean_token_accuracy": 0.16106417030096054,
|
|
"num_tokens": 11683203.0,
|
|
"step": 5620
|
|
},
|
|
{
|
|
"entropy": 5.706654167175293,
|
|
"epoch": 0.5102503628447025,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004980131556439236,
|
|
"loss": 5.6376,
|
|
"mean_token_accuracy": 0.15619875639677047,
|
|
"num_tokens": 11693313.0,
|
|
"step": 5625
|
|
},
|
|
{
|
|
"entropy": 5.769161176681519,
|
|
"epoch": 0.5107039187227866,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004980088628641925,
|
|
"loss": 5.7332,
|
|
"mean_token_accuracy": 0.15326391980051995,
|
|
"num_tokens": 11704194.0,
|
|
"step": 5630
|
|
},
|
|
{
|
|
"entropy": 5.775632333755493,
|
|
"epoch": 0.5111574746008708,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004980045654725812,
|
|
"loss": 5.5708,
|
|
"mean_token_accuracy": 0.15834364145994187,
|
|
"num_tokens": 11715109.0,
|
|
"step": 5635
|
|
},
|
|
{
|
|
"entropy": 5.664262056350708,
|
|
"epoch": 0.511611030478955,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004980002634691787,
|
|
"loss": 5.6186,
|
|
"mean_token_accuracy": 0.16121489852666854,
|
|
"num_tokens": 11724961.0,
|
|
"step": 5640
|
|
},
|
|
{
|
|
"entropy": 5.703507709503174,
|
|
"epoch": 0.5120645863570392,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.000497995956854074,
|
|
"loss": 5.6411,
|
|
"mean_token_accuracy": 0.15814631804823875,
|
|
"num_tokens": 11735334.0,
|
|
"step": 5645
|
|
},
|
|
{
|
|
"entropy": 5.810642290115356,
|
|
"epoch": 0.5125181422351234,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004979916456273561,
|
|
"loss": 5.6458,
|
|
"mean_token_accuracy": 0.14870579093694686,
|
|
"num_tokens": 11746858.0,
|
|
"step": 5650
|
|
},
|
|
{
|
|
"entropy": 5.807532930374146,
|
|
"epoch": 0.5129716981132075,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004979873297891141,
|
|
"loss": 5.7475,
|
|
"mean_token_accuracy": 0.14519907236099244,
|
|
"num_tokens": 11757819.0,
|
|
"step": 5655
|
|
},
|
|
{
|
|
"entropy": 5.808407640457153,
|
|
"epoch": 0.5134252539912917,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004979830093394372,
|
|
"loss": 5.6646,
|
|
"mean_token_accuracy": 0.15376524329185487,
|
|
"num_tokens": 11767470.0,
|
|
"step": 5660
|
|
},
|
|
{
|
|
"entropy": 5.742450141906739,
|
|
"epoch": 0.513878809869376,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004979786842784149,
|
|
"loss": 5.6069,
|
|
"mean_token_accuracy": 0.1618952751159668,
|
|
"num_tokens": 11777060.0,
|
|
"step": 5665
|
|
},
|
|
{
|
|
"entropy": 5.6815831661224365,
|
|
"epoch": 0.5143323657474601,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004979743546061366,
|
|
"loss": 5.6476,
|
|
"mean_token_accuracy": 0.15582273453474044,
|
|
"num_tokens": 11787176.0,
|
|
"step": 5670
|
|
},
|
|
{
|
|
"entropy": 5.681001758575439,
|
|
"epoch": 0.5147859216255443,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004979700203226918,
|
|
"loss": 5.5463,
|
|
"mean_token_accuracy": 0.15773169249296187,
|
|
"num_tokens": 11796419.0,
|
|
"step": 5675
|
|
},
|
|
{
|
|
"entropy": 5.835689210891724,
|
|
"epoch": 0.5152394775036284,
|
|
"grad_norm": 2.921875,
|
|
"learning_rate": 0.0004979656814281702,
|
|
"loss": 5.752,
|
|
"mean_token_accuracy": 0.1510649248957634,
|
|
"num_tokens": 11807279.0,
|
|
"step": 5680
|
|
},
|
|
{
|
|
"entropy": 5.757753849029541,
|
|
"epoch": 0.5156930333817126,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004979613379226615,
|
|
"loss": 5.6502,
|
|
"mean_token_accuracy": 0.1518499568104744,
|
|
"num_tokens": 11817669.0,
|
|
"step": 5685
|
|
},
|
|
{
|
|
"entropy": 5.725679922103882,
|
|
"epoch": 0.5161465892597968,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004979569898062554,
|
|
"loss": 5.6616,
|
|
"mean_token_accuracy": 0.15862690210342406,
|
|
"num_tokens": 11827247.0,
|
|
"step": 5690
|
|
},
|
|
{
|
|
"entropy": 5.789619445800781,
|
|
"epoch": 0.516600145137881,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.000497952637079042,
|
|
"loss": 5.6487,
|
|
"mean_token_accuracy": 0.14972210973501204,
|
|
"num_tokens": 11838201.0,
|
|
"step": 5695
|
|
},
|
|
{
|
|
"entropy": 5.730072736740112,
|
|
"epoch": 0.5170537010159652,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004979482797411114,
|
|
"loss": 5.593,
|
|
"mean_token_accuracy": 0.16091672480106353,
|
|
"num_tokens": 11847561.0,
|
|
"step": 5700
|
|
},
|
|
{
|
|
"entropy": 5.738336229324341,
|
|
"epoch": 0.5175072568940493,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004979439177925534,
|
|
"loss": 5.714,
|
|
"mean_token_accuracy": 0.15794804096221923,
|
|
"num_tokens": 11858272.0,
|
|
"step": 5705
|
|
},
|
|
{
|
|
"entropy": 5.827757883071899,
|
|
"epoch": 0.5179608127721336,
|
|
"grad_norm": 2.96875,
|
|
"learning_rate": 0.0004979395512334584,
|
|
"loss": 5.7507,
|
|
"mean_token_accuracy": 0.15172273367643357,
|
|
"num_tokens": 11869660.0,
|
|
"step": 5710
|
|
},
|
|
{
|
|
"entropy": 5.86238169670105,
|
|
"epoch": 0.5184143686502177,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004979351800639166,
|
|
"loss": 5.7652,
|
|
"mean_token_accuracy": 0.14836279600858687,
|
|
"num_tokens": 11880239.0,
|
|
"step": 5715
|
|
},
|
|
{
|
|
"entropy": 5.888429594039917,
|
|
"epoch": 0.5188679245283019,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004979308042840186,
|
|
"loss": 5.7581,
|
|
"mean_token_accuracy": 0.14716654121875763,
|
|
"num_tokens": 11890630.0,
|
|
"step": 5720
|
|
},
|
|
{
|
|
"entropy": 5.802192068099975,
|
|
"epoch": 0.519321480406386,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004979264238938547,
|
|
"loss": 5.7882,
|
|
"mean_token_accuracy": 0.14498534202575683,
|
|
"num_tokens": 11900948.0,
|
|
"step": 5725
|
|
},
|
|
{
|
|
"entropy": 5.752587032318115,
|
|
"epoch": 0.5197750362844702,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004979220388935155,
|
|
"loss": 5.6749,
|
|
"mean_token_accuracy": 0.15167703554034234,
|
|
"num_tokens": 11912528.0,
|
|
"step": 5730
|
|
},
|
|
{
|
|
"entropy": 5.756484889984131,
|
|
"epoch": 0.5202285921625545,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004979176492830918,
|
|
"loss": 5.6087,
|
|
"mean_token_accuracy": 0.15607684403657912,
|
|
"num_tokens": 11922211.0,
|
|
"step": 5735
|
|
},
|
|
{
|
|
"entropy": 5.700596475601197,
|
|
"epoch": 0.5206821480406386,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004979132550626742,
|
|
"loss": 5.6598,
|
|
"mean_token_accuracy": 0.14853055775165558,
|
|
"num_tokens": 11932520.0,
|
|
"step": 5740
|
|
},
|
|
{
|
|
"entropy": 5.7969828128814695,
|
|
"epoch": 0.5211357039187228,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004979088562323538,
|
|
"loss": 5.5931,
|
|
"mean_token_accuracy": 0.15993748605251312,
|
|
"num_tokens": 11943312.0,
|
|
"step": 5745
|
|
},
|
|
{
|
|
"entropy": 5.753064203262329,
|
|
"epoch": 0.5215892597968069,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004979044527922214,
|
|
"loss": 5.7227,
|
|
"mean_token_accuracy": 0.1540391340851784,
|
|
"num_tokens": 11954455.0,
|
|
"step": 5750
|
|
},
|
|
{
|
|
"entropy": 5.7552355289459225,
|
|
"epoch": 0.5220428156748912,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004979000447423681,
|
|
"loss": 5.6357,
|
|
"mean_token_accuracy": 0.15711707174777984,
|
|
"num_tokens": 11964650.0,
|
|
"step": 5755
|
|
},
|
|
{
|
|
"entropy": 5.757721376419068,
|
|
"epoch": 0.5224963715529753,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004978956320828851,
|
|
"loss": 5.658,
|
|
"mean_token_accuracy": 0.15847069025039673,
|
|
"num_tokens": 11975134.0,
|
|
"step": 5760
|
|
},
|
|
{
|
|
"entropy": 5.783113622665406,
|
|
"epoch": 0.5229499274310595,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004978912148138637,
|
|
"loss": 5.699,
|
|
"mean_token_accuracy": 0.1517071783542633,
|
|
"num_tokens": 11986486.0,
|
|
"step": 5765
|
|
},
|
|
{
|
|
"entropy": 5.8543494701385494,
|
|
"epoch": 0.5234034833091437,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.000497886792935395,
|
|
"loss": 5.735,
|
|
"mean_token_accuracy": 0.15076159983873366,
|
|
"num_tokens": 11998045.0,
|
|
"step": 5770
|
|
},
|
|
{
|
|
"entropy": 5.86229944229126,
|
|
"epoch": 0.5238570391872278,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004978823664475707,
|
|
"loss": 5.7001,
|
|
"mean_token_accuracy": 0.15565317273139953,
|
|
"num_tokens": 12008130.0,
|
|
"step": 5775
|
|
},
|
|
{
|
|
"entropy": 5.790041208267212,
|
|
"epoch": 0.5243105950653121,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004978779353504824,
|
|
"loss": 5.7661,
|
|
"mean_token_accuracy": 0.14593174383044244,
|
|
"num_tokens": 12018753.0,
|
|
"step": 5780
|
|
},
|
|
{
|
|
"entropy": 5.795868539810181,
|
|
"epoch": 0.5247641509433962,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004978734996442214,
|
|
"loss": 5.6456,
|
|
"mean_token_accuracy": 0.16076426655054094,
|
|
"num_tokens": 12028202.0,
|
|
"step": 5785
|
|
},
|
|
{
|
|
"entropy": 5.814069175720215,
|
|
"epoch": 0.5252177068214804,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004978690593288798,
|
|
"loss": 5.7247,
|
|
"mean_token_accuracy": 0.15733310282230378,
|
|
"num_tokens": 12039652.0,
|
|
"step": 5790
|
|
},
|
|
{
|
|
"entropy": 5.789728403091431,
|
|
"epoch": 0.5256712626995645,
|
|
"grad_norm": 17.0,
|
|
"learning_rate": 0.0004978646144045491,
|
|
"loss": 5.6497,
|
|
"mean_token_accuracy": 0.15042980760335922,
|
|
"num_tokens": 12051269.0,
|
|
"step": 5795
|
|
},
|
|
{
|
|
"entropy": 5.644839191436768,
|
|
"epoch": 0.5261248185776488,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004978601648713215,
|
|
"loss": 5.5269,
|
|
"mean_token_accuracy": 0.15518265813589097,
|
|
"num_tokens": 12060647.0,
|
|
"step": 5800
|
|
},
|
|
{
|
|
"entropy": 5.72273964881897,
|
|
"epoch": 0.526578374455733,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004978557107292889,
|
|
"loss": 5.691,
|
|
"mean_token_accuracy": 0.15798260569572448,
|
|
"num_tokens": 12071669.0,
|
|
"step": 5805
|
|
},
|
|
{
|
|
"entropy": 5.710134744644165,
|
|
"epoch": 0.5270319303338171,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004978512519785433,
|
|
"loss": 5.5538,
|
|
"mean_token_accuracy": 0.1603996381163597,
|
|
"num_tokens": 12081971.0,
|
|
"step": 5810
|
|
},
|
|
{
|
|
"entropy": 5.761967611312866,
|
|
"epoch": 0.5274854862119013,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.000497846788619177,
|
|
"loss": 5.693,
|
|
"mean_token_accuracy": 0.14980525076389312,
|
|
"num_tokens": 12092465.0,
|
|
"step": 5815
|
|
},
|
|
{
|
|
"entropy": 5.783017539978028,
|
|
"epoch": 0.5279390420899854,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004978423206512825,
|
|
"loss": 5.6323,
|
|
"mean_token_accuracy": 0.1552136331796646,
|
|
"num_tokens": 12101752.0,
|
|
"step": 5820
|
|
},
|
|
{
|
|
"entropy": 5.815354442596435,
|
|
"epoch": 0.5283925979680697,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.000497837848074952,
|
|
"loss": 5.7277,
|
|
"mean_token_accuracy": 0.15265906900167464,
|
|
"num_tokens": 12111805.0,
|
|
"step": 5825
|
|
},
|
|
{
|
|
"entropy": 5.818612146377563,
|
|
"epoch": 0.5288461538461539,
|
|
"grad_norm": 3.046875,
|
|
"learning_rate": 0.000497833370890278,
|
|
"loss": 5.7416,
|
|
"mean_token_accuracy": 0.1517587274312973,
|
|
"num_tokens": 12122511.0,
|
|
"step": 5830
|
|
},
|
|
{
|
|
"entropy": 5.808302402496338,
|
|
"epoch": 0.529299709724238,
|
|
"grad_norm": 3.328125,
|
|
"learning_rate": 0.0004978288890973529,
|
|
"loss": 5.6312,
|
|
"mean_token_accuracy": 0.1537729099392891,
|
|
"num_tokens": 12132510.0,
|
|
"step": 5835
|
|
},
|
|
{
|
|
"entropy": 5.739053058624267,
|
|
"epoch": 0.5297532656023222,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004978244026962698,
|
|
"loss": 5.6233,
|
|
"mean_token_accuracy": 0.15461270958185197,
|
|
"num_tokens": 12142419.0,
|
|
"step": 5840
|
|
},
|
|
{
|
|
"entropy": 5.757953739166259,
|
|
"epoch": 0.5302068214804064,
|
|
"grad_norm": 5.9375,
|
|
"learning_rate": 0.0004978199116871212,
|
|
"loss": 5.6917,
|
|
"mean_token_accuracy": 0.1523043468594551,
|
|
"num_tokens": 12152759.0,
|
|
"step": 5845
|
|
},
|
|
{
|
|
"entropy": 5.741458559036255,
|
|
"epoch": 0.5306603773584906,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.00049781541607,
|
|
"loss": 5.6286,
|
|
"mean_token_accuracy": 0.15267193913459778,
|
|
"num_tokens": 12162758.0,
|
|
"step": 5850
|
|
},
|
|
{
|
|
"entropy": 5.783251619338989,
|
|
"epoch": 0.5311139332365747,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004978109158449993,
|
|
"loss": 5.6838,
|
|
"mean_token_accuracy": 0.15076133981347084,
|
|
"num_tokens": 12172664.0,
|
|
"step": 5855
|
|
},
|
|
{
|
|
"entropy": 5.809034013748169,
|
|
"epoch": 0.5315674891146589,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004978064110122121,
|
|
"loss": 5.65,
|
|
"mean_token_accuracy": 0.1549011915922165,
|
|
"num_tokens": 12182028.0,
|
|
"step": 5860
|
|
},
|
|
{
|
|
"entropy": 5.824132633209229,
|
|
"epoch": 0.532021044992743,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004978019015717314,
|
|
"loss": 5.6972,
|
|
"mean_token_accuracy": 0.15745327472686768,
|
|
"num_tokens": 12192168.0,
|
|
"step": 5865
|
|
},
|
|
{
|
|
"entropy": 5.67472128868103,
|
|
"epoch": 0.5324746008708273,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004977973875236508,
|
|
"loss": 5.5932,
|
|
"mean_token_accuracy": 0.15128588378429414,
|
|
"num_tokens": 12202889.0,
|
|
"step": 5870
|
|
},
|
|
{
|
|
"entropy": 5.71777195930481,
|
|
"epoch": 0.5329281567489115,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004977928688680634,
|
|
"loss": 5.6614,
|
|
"mean_token_accuracy": 0.1567210003733635,
|
|
"num_tokens": 12212514.0,
|
|
"step": 5875
|
|
},
|
|
{
|
|
"entropy": 5.755164003372192,
|
|
"epoch": 0.5333817126269956,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004977883456050626,
|
|
"loss": 5.5106,
|
|
"mean_token_accuracy": 0.1608267605304718,
|
|
"num_tokens": 12222353.0,
|
|
"step": 5880
|
|
},
|
|
{
|
|
"entropy": 5.838532447814941,
|
|
"epoch": 0.5338352685050798,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.000497783817734742,
|
|
"loss": 5.7678,
|
|
"mean_token_accuracy": 0.1494266524910927,
|
|
"num_tokens": 12232845.0,
|
|
"step": 5885
|
|
},
|
|
{
|
|
"entropy": 5.804184675216675,
|
|
"epoch": 0.534288824383164,
|
|
"grad_norm": 3.0625,
|
|
"learning_rate": 0.0004977792852571954,
|
|
"loss": 5.726,
|
|
"mean_token_accuracy": 0.1480010524392128,
|
|
"num_tokens": 12242950.0,
|
|
"step": 5890
|
|
},
|
|
{
|
|
"entropy": 5.798137092590332,
|
|
"epoch": 0.5347423802612482,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004977747481725164,
|
|
"loss": 5.702,
|
|
"mean_token_accuracy": 0.14956545680761338,
|
|
"num_tokens": 12253132.0,
|
|
"step": 5895
|
|
},
|
|
{
|
|
"entropy": 5.74386191368103,
|
|
"epoch": 0.5351959361393324,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004977702064807987,
|
|
"loss": 5.6457,
|
|
"mean_token_accuracy": 0.15413923114538192,
|
|
"num_tokens": 12263214.0,
|
|
"step": 5900
|
|
},
|
|
{
|
|
"entropy": 5.707874059677124,
|
|
"epoch": 0.5356494920174165,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004977656601821366,
|
|
"loss": 5.5845,
|
|
"mean_token_accuracy": 0.16530820578336716,
|
|
"num_tokens": 12273250.0,
|
|
"step": 5905
|
|
},
|
|
{
|
|
"entropy": 5.919317960739136,
|
|
"epoch": 0.5361030478955007,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004977611092766238,
|
|
"loss": 5.7643,
|
|
"mean_token_accuracy": 0.15915993154048919,
|
|
"num_tokens": 12283767.0,
|
|
"step": 5910
|
|
},
|
|
{
|
|
"entropy": 5.754854917526245,
|
|
"epoch": 0.5365566037735849,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004977565537643544,
|
|
"loss": 5.619,
|
|
"mean_token_accuracy": 0.1566011890769005,
|
|
"num_tokens": 12294612.0,
|
|
"step": 5915
|
|
},
|
|
{
|
|
"entropy": 5.735382413864135,
|
|
"epoch": 0.5370101596516691,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004977519936454227,
|
|
"loss": 5.7207,
|
|
"mean_token_accuracy": 0.1573534607887268,
|
|
"num_tokens": 12305614.0,
|
|
"step": 5920
|
|
},
|
|
{
|
|
"entropy": 5.734095716476441,
|
|
"epoch": 0.5374637155297532,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004977474289199231,
|
|
"loss": 5.5688,
|
|
"mean_token_accuracy": 0.15029709711670874,
|
|
"num_tokens": 12316152.0,
|
|
"step": 5925
|
|
},
|
|
{
|
|
"entropy": 5.705564880371094,
|
|
"epoch": 0.5379172714078374,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004977428595879499,
|
|
"loss": 5.6581,
|
|
"mean_token_accuracy": 0.15709878951311113,
|
|
"num_tokens": 12325940.0,
|
|
"step": 5930
|
|
},
|
|
{
|
|
"entropy": 5.736659002304077,
|
|
"epoch": 0.5383708272859217,
|
|
"grad_norm": 2.9375,
|
|
"learning_rate": 0.0004977382856495975,
|
|
"loss": 5.6538,
|
|
"mean_token_accuracy": 0.1553759306669235,
|
|
"num_tokens": 12335482.0,
|
|
"step": 5935
|
|
},
|
|
{
|
|
"entropy": 5.8129387378692625,
|
|
"epoch": 0.5388243831640058,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004977337071049606,
|
|
"loss": 5.7538,
|
|
"mean_token_accuracy": 0.1464443251490593,
|
|
"num_tokens": 12346386.0,
|
|
"step": 5940
|
|
},
|
|
{
|
|
"entropy": 5.854721212387085,
|
|
"epoch": 0.53927793904209,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.000497729123954134,
|
|
"loss": 5.6683,
|
|
"mean_token_accuracy": 0.15644141435623168,
|
|
"num_tokens": 12356282.0,
|
|
"step": 5945
|
|
},
|
|
{
|
|
"entropy": 5.735949468612671,
|
|
"epoch": 0.5397314949201741,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004977245361972123,
|
|
"loss": 5.6765,
|
|
"mean_token_accuracy": 0.1545313149690628,
|
|
"num_tokens": 12366994.0,
|
|
"step": 5950
|
|
},
|
|
{
|
|
"entropy": 5.7212425708770756,
|
|
"epoch": 0.5401850507982583,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004977199438342904,
|
|
"loss": 5.5716,
|
|
"mean_token_accuracy": 0.15779082775115966,
|
|
"num_tokens": 12377524.0,
|
|
"step": 5955
|
|
},
|
|
{
|
|
"entropy": 5.761970043182373,
|
|
"epoch": 0.5406386066763426,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004977153468654634,
|
|
"loss": 5.7211,
|
|
"mean_token_accuracy": 0.15492843165993692,
|
|
"num_tokens": 12387593.0,
|
|
"step": 5960
|
|
},
|
|
{
|
|
"entropy": 5.80047345161438,
|
|
"epoch": 0.5410921625544267,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004977107452908262,
|
|
"loss": 5.6901,
|
|
"mean_token_accuracy": 0.15060260742902756,
|
|
"num_tokens": 12398732.0,
|
|
"step": 5965
|
|
},
|
|
{
|
|
"entropy": 5.821221828460693,
|
|
"epoch": 0.5415457184325109,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.000497706139110474,
|
|
"loss": 5.6681,
|
|
"mean_token_accuracy": 0.16170208156108856,
|
|
"num_tokens": 12409821.0,
|
|
"step": 5970
|
|
},
|
|
{
|
|
"entropy": 5.776604270935058,
|
|
"epoch": 0.541999274310595,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004977015283245021,
|
|
"loss": 5.6963,
|
|
"mean_token_accuracy": 0.15199582576751708,
|
|
"num_tokens": 12420044.0,
|
|
"step": 5975
|
|
},
|
|
{
|
|
"entropy": 5.716190004348755,
|
|
"epoch": 0.5424528301886793,
|
|
"grad_norm": 5.3125,
|
|
"learning_rate": 0.0004976969129330059,
|
|
"loss": 5.6405,
|
|
"mean_token_accuracy": 0.15238496512174607,
|
|
"num_tokens": 12430980.0,
|
|
"step": 5980
|
|
},
|
|
{
|
|
"entropy": 5.807556629180908,
|
|
"epoch": 0.5429063860667634,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004976922929360808,
|
|
"loss": 5.6766,
|
|
"mean_token_accuracy": 0.15749867260456085,
|
|
"num_tokens": 12441999.0,
|
|
"step": 5985
|
|
},
|
|
{
|
|
"entropy": 5.795617580413818,
|
|
"epoch": 0.5433599419448476,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004976876683338222,
|
|
"loss": 5.7151,
|
|
"mean_token_accuracy": 0.15440924018621444,
|
|
"num_tokens": 12452837.0,
|
|
"step": 5990
|
|
},
|
|
{
|
|
"entropy": 5.781675815582275,
|
|
"epoch": 0.5438134978229318,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.000497683039126326,
|
|
"loss": 5.6243,
|
|
"mean_token_accuracy": 0.16212155669927597,
|
|
"num_tokens": 12462142.0,
|
|
"step": 5995
|
|
},
|
|
{
|
|
"entropy": 5.757653427124024,
|
|
"epoch": 0.5442670537010159,
|
|
"grad_norm": 4.21875,
|
|
"learning_rate": 0.0004976784053136878,
|
|
"loss": 5.6862,
|
|
"mean_token_accuracy": 0.15880632698535918,
|
|
"num_tokens": 12472756.0,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"epoch": 0.5442670537010159,
|
|
"eval_entropy": 5.571439638612497,
|
|
"eval_loss": 5.7100067138671875,
|
|
"eval_mean_token_accuracy": 0.15796612128615378,
|
|
"eval_num_tokens": 12472756.0,
|
|
"eval_runtime": 26.5304,
|
|
"eval_samples_per_second": 1332.812,
|
|
"eval_steps_per_second": 166.602,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"entropy": 5.8166303634643555,
|
|
"epoch": 0.5447206095791002,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.0004976737668960034,
|
|
"loss": 5.7832,
|
|
"mean_token_accuracy": 0.14682883471250535,
|
|
"num_tokens": 12483115.0,
|
|
"step": 6005
|
|
},
|
|
{
|
|
"entropy": 5.832898235321045,
|
|
"epoch": 0.5451741654571843,
|
|
"grad_norm": 3.28125,
|
|
"learning_rate": 0.0004976691238733688,
|
|
"loss": 5.6337,
|
|
"mean_token_accuracy": 0.15088710635900499,
|
|
"num_tokens": 12493280.0,
|
|
"step": 6010
|
|
},
|
|
{
|
|
"entropy": 5.788230085372925,
|
|
"epoch": 0.5456277213352685,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.00049766447624588,
|
|
"loss": 5.7572,
|
|
"mean_token_accuracy": 0.1538712576031685,
|
|
"num_tokens": 12503665.0,
|
|
"step": 6015
|
|
},
|
|
{
|
|
"entropy": 5.701073551177979,
|
|
"epoch": 0.5460812772133526,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.000497659824013633,
|
|
"loss": 5.688,
|
|
"mean_token_accuracy": 0.14975677132606507,
|
|
"num_tokens": 12513381.0,
|
|
"step": 6020
|
|
},
|
|
{
|
|
"entropy": 5.85684871673584,
|
|
"epoch": 0.5465348330914369,
|
|
"grad_norm": 2.890625,
|
|
"learning_rate": 0.0004976551671767241,
|
|
"loss": 5.7085,
|
|
"mean_token_accuracy": 0.15038748383522033,
|
|
"num_tokens": 12524121.0,
|
|
"step": 6025
|
|
},
|
|
{
|
|
"entropy": 5.8416108131408695,
|
|
"epoch": 0.5469883889695211,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004976505057352496,
|
|
"loss": 5.6631,
|
|
"mean_token_accuracy": 0.15823794305324554,
|
|
"num_tokens": 12533972.0,
|
|
"step": 6030
|
|
},
|
|
{
|
|
"entropy": 5.784581518173217,
|
|
"epoch": 0.5474419448476052,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004976458396893059,
|
|
"loss": 5.7891,
|
|
"mean_token_accuracy": 0.1468980848789215,
|
|
"num_tokens": 12544110.0,
|
|
"step": 6035
|
|
},
|
|
{
|
|
"entropy": 5.758417320251465,
|
|
"epoch": 0.5478955007256894,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004976411690389896,
|
|
"loss": 5.6342,
|
|
"mean_token_accuracy": 0.15048055052757264,
|
|
"num_tokens": 12554273.0,
|
|
"step": 6040
|
|
},
|
|
{
|
|
"entropy": 5.893464517593384,
|
|
"epoch": 0.5483490566037735,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.000497636493784397,
|
|
"loss": 5.7141,
|
|
"mean_token_accuracy": 0.15111250206828117,
|
|
"num_tokens": 12564633.0,
|
|
"step": 6045
|
|
},
|
|
{
|
|
"entropy": 5.845950984954834,
|
|
"epoch": 0.5488026124818578,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004976318139256251,
|
|
"loss": 5.6268,
|
|
"mean_token_accuracy": 0.1532691612839699,
|
|
"num_tokens": 12573790.0,
|
|
"step": 6050
|
|
},
|
|
{
|
|
"entropy": 5.727607202529907,
|
|
"epoch": 0.549256168359942,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.0004976271294627706,
|
|
"loss": 5.702,
|
|
"mean_token_accuracy": 0.15061550587415695,
|
|
"num_tokens": 12584265.0,
|
|
"step": 6055
|
|
},
|
|
{
|
|
"entropy": 5.711427831649781,
|
|
"epoch": 0.5497097242380261,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004976224403959303,
|
|
"loss": 5.5784,
|
|
"mean_token_accuracy": 0.15742302387952806,
|
|
"num_tokens": 12594413.0,
|
|
"step": 6060
|
|
},
|
|
{
|
|
"entropy": 5.788397359848022,
|
|
"epoch": 0.5501632801161103,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.0004976177467252012,
|
|
"loss": 5.6608,
|
|
"mean_token_accuracy": 0.15904350876808165,
|
|
"num_tokens": 12604637.0,
|
|
"step": 6065
|
|
},
|
|
{
|
|
"entropy": 5.771824026107788,
|
|
"epoch": 0.5506168359941945,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.0004976130484506804,
|
|
"loss": 5.7192,
|
|
"mean_token_accuracy": 0.15422330498695375,
|
|
"num_tokens": 12614873.0,
|
|
"step": 6070
|
|
},
|
|
{
|
|
"entropy": 5.745659923553466,
|
|
"epoch": 0.5510703918722787,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004976083455724649,
|
|
"loss": 5.6623,
|
|
"mean_token_accuracy": 0.15023809373378755,
|
|
"num_tokens": 12626182.0,
|
|
"step": 6075
|
|
},
|
|
{
|
|
"entropy": 5.757641315460205,
|
|
"epoch": 0.5515239477503628,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004976036380906523,
|
|
"loss": 5.5818,
|
|
"mean_token_accuracy": 0.15435850918292998,
|
|
"num_tokens": 12635418.0,
|
|
"step": 6080
|
|
},
|
|
{
|
|
"entropy": 5.838926458358765,
|
|
"epoch": 0.551977503628447,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004975989260053395,
|
|
"loss": 5.7269,
|
|
"mean_token_accuracy": 0.1468985289335251,
|
|
"num_tokens": 12645942.0,
|
|
"step": 6085
|
|
},
|
|
{
|
|
"entropy": 5.728414392471313,
|
|
"epoch": 0.5524310595065312,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004975942093166242,
|
|
"loss": 5.6659,
|
|
"mean_token_accuracy": 0.15283730030059814,
|
|
"num_tokens": 12656460.0,
|
|
"step": 6090
|
|
},
|
|
{
|
|
"entropy": 5.809977293014526,
|
|
"epoch": 0.5528846153846154,
|
|
"grad_norm": 3.1875,
|
|
"learning_rate": 0.0004975894880246041,
|
|
"loss": 5.6028,
|
|
"mean_token_accuracy": 0.15169214606285095,
|
|
"num_tokens": 12666916.0,
|
|
"step": 6095
|
|
},
|
|
{
|
|
"entropy": 5.775780582427979,
|
|
"epoch": 0.5533381712626996,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004975847621293766,
|
|
"loss": 5.6709,
|
|
"mean_token_accuracy": 0.16105171889066697,
|
|
"num_tokens": 12677562.0,
|
|
"step": 6100
|
|
},
|
|
{
|
|
"entropy": 5.711263704299927,
|
|
"epoch": 0.5537917271407837,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004975800316310394,
|
|
"loss": 5.6235,
|
|
"mean_token_accuracy": 0.15581511408090593,
|
|
"num_tokens": 12687349.0,
|
|
"step": 6105
|
|
},
|
|
{
|
|
"entropy": 5.806702566146851,
|
|
"epoch": 0.5542452830188679,
|
|
"grad_norm": 4.25,
|
|
"learning_rate": 0.0004975752965296906,
|
|
"loss": 5.6815,
|
|
"mean_token_accuracy": 0.1545094668865204,
|
|
"num_tokens": 12697850.0,
|
|
"step": 6110
|
|
},
|
|
{
|
|
"entropy": 5.724259376525879,
|
|
"epoch": 0.5546988388969522,
|
|
"grad_norm": 6.9375,
|
|
"learning_rate": 0.0004975705568254278,
|
|
"loss": 5.5467,
|
|
"mean_token_accuracy": 0.15480877012014388,
|
|
"num_tokens": 12708283.0,
|
|
"step": 6115
|
|
},
|
|
{
|
|
"entropy": 5.708226060867309,
|
|
"epoch": 0.5551523947750363,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004975658125183493,
|
|
"loss": 5.6221,
|
|
"mean_token_accuracy": 0.1571838840842247,
|
|
"num_tokens": 12718201.0,
|
|
"step": 6120
|
|
},
|
|
{
|
|
"entropy": 5.745707035064697,
|
|
"epoch": 0.5556059506531205,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.000497561063608553,
|
|
"loss": 5.6058,
|
|
"mean_token_accuracy": 0.15703478157520295,
|
|
"num_tokens": 12728860.0,
|
|
"step": 6125
|
|
},
|
|
{
|
|
"entropy": 5.779846572875977,
|
|
"epoch": 0.5560595065312046,
|
|
"grad_norm": 3.046875,
|
|
"learning_rate": 0.0004975563100961372,
|
|
"loss": 5.6533,
|
|
"mean_token_accuracy": 0.15242056548595428,
|
|
"num_tokens": 12739007.0,
|
|
"step": 6130
|
|
},
|
|
{
|
|
"entropy": 5.750319910049439,
|
|
"epoch": 0.5565130624092888,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004975515519812002,
|
|
"loss": 5.5186,
|
|
"mean_token_accuracy": 0.16321926414966584,
|
|
"num_tokens": 12749004.0,
|
|
"step": 6135
|
|
},
|
|
{
|
|
"entropy": 5.690269613265992,
|
|
"epoch": 0.556966618287373,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004975467892638402,
|
|
"loss": 5.6845,
|
|
"mean_token_accuracy": 0.1539756253361702,
|
|
"num_tokens": 12760085.0,
|
|
"step": 6140
|
|
},
|
|
{
|
|
"entropy": 5.728693866729737,
|
|
"epoch": 0.5574201741654572,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004975420219441561,
|
|
"loss": 5.6269,
|
|
"mean_token_accuracy": 0.16305172443389893,
|
|
"num_tokens": 12770303.0,
|
|
"step": 6145
|
|
},
|
|
{
|
|
"entropy": 5.800379467010498,
|
|
"epoch": 0.5578737300435413,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004975372500222462,
|
|
"loss": 5.638,
|
|
"mean_token_accuracy": 0.15569627434015273,
|
|
"num_tokens": 12780334.0,
|
|
"step": 6150
|
|
},
|
|
{
|
|
"entropy": 5.805584144592285,
|
|
"epoch": 0.5583272859216255,
|
|
"grad_norm": 2.9375,
|
|
"learning_rate": 0.0004975324734982094,
|
|
"loss": 5.6992,
|
|
"mean_token_accuracy": 0.1512184336781502,
|
|
"num_tokens": 12790980.0,
|
|
"step": 6155
|
|
},
|
|
{
|
|
"entropy": 5.7633744239807125,
|
|
"epoch": 0.5587808417997098,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004975276923721442,
|
|
"loss": 5.7373,
|
|
"mean_token_accuracy": 0.15086752325296401,
|
|
"num_tokens": 12801713.0,
|
|
"step": 6160
|
|
},
|
|
{
|
|
"entropy": 5.746546363830566,
|
|
"epoch": 0.5592343976777939,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004975229066441496,
|
|
"loss": 5.7356,
|
|
"mean_token_accuracy": 0.14781113117933273,
|
|
"num_tokens": 12813040.0,
|
|
"step": 6165
|
|
},
|
|
{
|
|
"entropy": 5.787732267379761,
|
|
"epoch": 0.5596879535558781,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004975181163143247,
|
|
"loss": 5.6784,
|
|
"mean_token_accuracy": 0.1479372873902321,
|
|
"num_tokens": 12824048.0,
|
|
"step": 6170
|
|
},
|
|
{
|
|
"entropy": 5.804344987869262,
|
|
"epoch": 0.5601415094339622,
|
|
"grad_norm": 3.625,
|
|
"learning_rate": 0.0004975133213827684,
|
|
"loss": 5.6157,
|
|
"mean_token_accuracy": 0.1567558988928795,
|
|
"num_tokens": 12834297.0,
|
|
"step": 6175
|
|
},
|
|
{
|
|
"entropy": 5.892291069030762,
|
|
"epoch": 0.5605950653120464,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004975085218495798,
|
|
"loss": 5.7061,
|
|
"mean_token_accuracy": 0.14884814321994783,
|
|
"num_tokens": 12844574.0,
|
|
"step": 6180
|
|
},
|
|
{
|
|
"entropy": 5.689108371734619,
|
|
"epoch": 0.5610486211901307,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004975037177148585,
|
|
"loss": 5.6468,
|
|
"mean_token_accuracy": 0.15237224772572516,
|
|
"num_tokens": 12854670.0,
|
|
"step": 6185
|
|
},
|
|
{
|
|
"entropy": 5.645991802215576,
|
|
"epoch": 0.5615021770682148,
|
|
"grad_norm": 3.34375,
|
|
"learning_rate": 0.0004974989089787035,
|
|
"loss": 5.6568,
|
|
"mean_token_accuracy": 0.15477271229028702,
|
|
"num_tokens": 12865281.0,
|
|
"step": 6190
|
|
},
|
|
{
|
|
"entropy": 5.790045928955078,
|
|
"epoch": 0.561955732946299,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004974940956412143,
|
|
"loss": 5.6569,
|
|
"mean_token_accuracy": 0.15305998921394348,
|
|
"num_tokens": 12875222.0,
|
|
"step": 6195
|
|
},
|
|
{
|
|
"entropy": 5.919342136383056,
|
|
"epoch": 0.5624092888243831,
|
|
"grad_norm": 9.1875,
|
|
"learning_rate": 0.0004974892777024905,
|
|
"loss": 5.7241,
|
|
"mean_token_accuracy": 0.14940885305404664,
|
|
"num_tokens": 12885079.0,
|
|
"step": 6200
|
|
},
|
|
{
|
|
"entropy": 5.777828359603882,
|
|
"epoch": 0.5628628447024674,
|
|
"grad_norm": 3.171875,
|
|
"learning_rate": 0.0004974844551626318,
|
|
"loss": 5.687,
|
|
"mean_token_accuracy": 0.1558162033557892,
|
|
"num_tokens": 12896402.0,
|
|
"step": 6205
|
|
},
|
|
{
|
|
"entropy": 5.709645462036133,
|
|
"epoch": 0.5633164005805515,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004974796280217379,
|
|
"loss": 5.6453,
|
|
"mean_token_accuracy": 0.16267076134681702,
|
|
"num_tokens": 12906403.0,
|
|
"step": 6210
|
|
},
|
|
{
|
|
"entropy": 5.809755325317383,
|
|
"epoch": 0.5637699564586357,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004974747962799086,
|
|
"loss": 5.6645,
|
|
"mean_token_accuracy": 0.1476689323782921,
|
|
"num_tokens": 12917061.0,
|
|
"step": 6215
|
|
},
|
|
{
|
|
"entropy": 5.737009000778198,
|
|
"epoch": 0.5642235123367199,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004974699599372437,
|
|
"loss": 5.6883,
|
|
"mean_token_accuracy": 0.1575671598315239,
|
|
"num_tokens": 12927182.0,
|
|
"step": 6220
|
|
},
|
|
{
|
|
"entropy": 5.730798959732056,
|
|
"epoch": 0.564677068214804,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004974651189938434,
|
|
"loss": 5.6492,
|
|
"mean_token_accuracy": 0.15385740101337433,
|
|
"num_tokens": 12937371.0,
|
|
"step": 6225
|
|
},
|
|
{
|
|
"entropy": 5.819814729690552,
|
|
"epoch": 0.5651306240928883,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004974602734498079,
|
|
"loss": 5.6974,
|
|
"mean_token_accuracy": 0.147367987036705,
|
|
"num_tokens": 12948569.0,
|
|
"step": 6230
|
|
},
|
|
{
|
|
"entropy": 5.849042892456055,
|
|
"epoch": 0.5655841799709724,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.000497455423305237,
|
|
"loss": 5.6517,
|
|
"mean_token_accuracy": 0.14883127957582473,
|
|
"num_tokens": 12958503.0,
|
|
"step": 6235
|
|
},
|
|
{
|
|
"entropy": 5.816850376129151,
|
|
"epoch": 0.5660377358490566,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004974505685602314,
|
|
"loss": 5.6696,
|
|
"mean_token_accuracy": 0.15917163342237473,
|
|
"num_tokens": 12968714.0,
|
|
"step": 6240
|
|
},
|
|
{
|
|
"entropy": 5.738234329223633,
|
|
"epoch": 0.5664912917271407,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004974457092148912,
|
|
"loss": 5.7003,
|
|
"mean_token_accuracy": 0.15269872844219207,
|
|
"num_tokens": 12978857.0,
|
|
"step": 6245
|
|
},
|
|
{
|
|
"entropy": 5.845728397369385,
|
|
"epoch": 0.566944847605225,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004974408452693172,
|
|
"loss": 5.8093,
|
|
"mean_token_accuracy": 0.14675376266241075,
|
|
"num_tokens": 12989863.0,
|
|
"step": 6250
|
|
},
|
|
{
|
|
"entropy": 5.77975435256958,
|
|
"epoch": 0.5673984034833092,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004974359767236099,
|
|
"loss": 5.6093,
|
|
"mean_token_accuracy": 0.15659026503562928,
|
|
"num_tokens": 13000307.0,
|
|
"step": 6255
|
|
},
|
|
{
|
|
"entropy": 5.753757667541504,
|
|
"epoch": 0.5678519593613933,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.0004974311035778698,
|
|
"loss": 5.6585,
|
|
"mean_token_accuracy": 0.1654161751270294,
|
|
"num_tokens": 13009053.0,
|
|
"step": 6260
|
|
},
|
|
{
|
|
"entropy": 5.768190145492554,
|
|
"epoch": 0.5683055152394775,
|
|
"grad_norm": 3.78125,
|
|
"learning_rate": 0.0004974262258321979,
|
|
"loss": 5.7077,
|
|
"mean_token_accuracy": 0.14887018352746964,
|
|
"num_tokens": 13019136.0,
|
|
"step": 6265
|
|
},
|
|
{
|
|
"entropy": 5.851829242706299,
|
|
"epoch": 0.5687590711175616,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004974213434866949,
|
|
"loss": 5.7188,
|
|
"mean_token_accuracy": 0.1501341938972473,
|
|
"num_tokens": 13030356.0,
|
|
"step": 6270
|
|
},
|
|
{
|
|
"entropy": 5.811538934707642,
|
|
"epoch": 0.5692126269956459,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004974164565414617,
|
|
"loss": 5.7585,
|
|
"mean_token_accuracy": 0.14968807846307755,
|
|
"num_tokens": 13040477.0,
|
|
"step": 6275
|
|
},
|
|
{
|
|
"entropy": 5.80972990989685,
|
|
"epoch": 0.56966618287373,
|
|
"grad_norm": 3.46875,
|
|
"learning_rate": 0.0004974115649965998,
|
|
"loss": 5.6423,
|
|
"mean_token_accuracy": 0.16031724512577056,
|
|
"num_tokens": 13051755.0,
|
|
"step": 6280
|
|
},
|
|
{
|
|
"entropy": 5.850274562835693,
|
|
"epoch": 0.5701197387518142,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004974066688522098,
|
|
"loss": 5.6499,
|
|
"mean_token_accuracy": 0.16230104714632035,
|
|
"num_tokens": 13061670.0,
|
|
"step": 6285
|
|
},
|
|
{
|
|
"entropy": 5.754382801055908,
|
|
"epoch": 0.5705732946298984,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004974017681083934,
|
|
"loss": 5.6138,
|
|
"mean_token_accuracy": 0.15561977475881578,
|
|
"num_tokens": 13070917.0,
|
|
"step": 6290
|
|
},
|
|
{
|
|
"entropy": 5.703136301040649,
|
|
"epoch": 0.5710268505079826,
|
|
"grad_norm": 3.046875,
|
|
"learning_rate": 0.0004973968627652516,
|
|
"loss": 5.6785,
|
|
"mean_token_accuracy": 0.15372648537158967,
|
|
"num_tokens": 13080577.0,
|
|
"step": 6295
|
|
},
|
|
{
|
|
"entropy": 5.778132009506225,
|
|
"epoch": 0.5714804063860668,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.000497391952822886,
|
|
"loss": 5.726,
|
|
"mean_token_accuracy": 0.15329584032297133,
|
|
"num_tokens": 13091446.0,
|
|
"step": 6300
|
|
},
|
|
{
|
|
"entropy": 5.842317533493042,
|
|
"epoch": 0.5719339622641509,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004973870382813983,
|
|
"loss": 5.7267,
|
|
"mean_token_accuracy": 0.15676882565021516,
|
|
"num_tokens": 13102752.0,
|
|
"step": 6305
|
|
},
|
|
{
|
|
"entropy": 5.913141870498658,
|
|
"epoch": 0.5723875181422351,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004973821191408899,
|
|
"loss": 5.7531,
|
|
"mean_token_accuracy": 0.15161021798849106,
|
|
"num_tokens": 13113944.0,
|
|
"step": 6310
|
|
},
|
|
{
|
|
"entropy": 5.81167368888855,
|
|
"epoch": 0.5728410740203193,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004973771954014626,
|
|
"loss": 5.6856,
|
|
"mean_token_accuracy": 0.1475789338350296,
|
|
"num_tokens": 13124316.0,
|
|
"step": 6315
|
|
},
|
|
{
|
|
"entropy": 5.883531665802002,
|
|
"epoch": 0.5732946298984035,
|
|
"grad_norm": 2.875,
|
|
"learning_rate": 0.0004973722670632182,
|
|
"loss": 5.784,
|
|
"mean_token_accuracy": 0.14491094052791595,
|
|
"num_tokens": 13133567.0,
|
|
"step": 6320
|
|
},
|
|
{
|
|
"entropy": 5.793781757354736,
|
|
"epoch": 0.5737481857764877,
|
|
"grad_norm": 3.609375,
|
|
"learning_rate": 0.0004973673341262587,
|
|
"loss": 5.7042,
|
|
"mean_token_accuracy": 0.15035074204206467,
|
|
"num_tokens": 13144279.0,
|
|
"step": 6325
|
|
},
|
|
{
|
|
"entropy": 5.812184858322143,
|
|
"epoch": 0.5742017416545718,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.000497362396590686,
|
|
"loss": 5.7121,
|
|
"mean_token_accuracy": 0.15618311017751693,
|
|
"num_tokens": 13154463.0,
|
|
"step": 6330
|
|
},
|
|
{
|
|
"entropy": 5.828989505767822,
|
|
"epoch": 0.574655297532656,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.0004973574544566024,
|
|
"loss": 5.7131,
|
|
"mean_token_accuracy": 0.1466642439365387,
|
|
"num_tokens": 13165565.0,
|
|
"step": 6335
|
|
},
|
|
{
|
|
"entropy": 5.76364049911499,
|
|
"epoch": 0.5751088534107403,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.0004973525077241098,
|
|
"loss": 5.6335,
|
|
"mean_token_accuracy": 0.15842198878526687,
|
|
"num_tokens": 13175839.0,
|
|
"step": 6340
|
|
},
|
|
{
|
|
"entropy": 5.741176509857178,
|
|
"epoch": 0.5755624092888244,
|
|
"grad_norm": 3.921875,
|
|
"learning_rate": 0.0004973475563933109,
|
|
"loss": 5.6211,
|
|
"mean_token_accuracy": 0.15324287861585617,
|
|
"num_tokens": 13186372.0,
|
|
"step": 6345
|
|
},
|
|
{
|
|
"entropy": 5.764437246322632,
|
|
"epoch": 0.5760159651669086,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004973426004643077,
|
|
"loss": 5.6682,
|
|
"mean_token_accuracy": 0.15345639437437059,
|
|
"num_tokens": 13196259.0,
|
|
"step": 6350
|
|
},
|
|
{
|
|
"entropy": 5.8232909679412845,
|
|
"epoch": 0.5764695210449927,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004973376399372029,
|
|
"loss": 5.6659,
|
|
"mean_token_accuracy": 0.1532199814915657,
|
|
"num_tokens": 13206497.0,
|
|
"step": 6355
|
|
},
|
|
{
|
|
"entropy": 5.839055967330933,
|
|
"epoch": 0.5769230769230769,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.0004973326748120991,
|
|
"loss": 5.7096,
|
|
"mean_token_accuracy": 0.15685370415449143,
|
|
"num_tokens": 13217188.0,
|
|
"step": 6360
|
|
},
|
|
{
|
|
"entropy": 5.755173206329346,
|
|
"epoch": 0.5773766328011611,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.0004973277050890988,
|
|
"loss": 5.6947,
|
|
"mean_token_accuracy": 0.149724081158638,
|
|
"num_tokens": 13226544.0,
|
|
"step": 6365
|
|
},
|
|
{
|
|
"entropy": 5.835665464401245,
|
|
"epoch": 0.5778301886792453,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.0004973227307683049,
|
|
"loss": 5.7452,
|
|
"mean_token_accuracy": 0.15042823553085327,
|
|
"num_tokens": 13236572.0,
|
|
"step": 6370
|
|
},
|
|
{
|
|
"entropy": 5.967599248886108,
|
|
"epoch": 0.5782837445573294,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004973177518498204,
|
|
"loss": 5.7337,
|
|
"mean_token_accuracy": 0.14907948523759842,
|
|
"num_tokens": 13247958.0,
|
|
"step": 6375
|
|
},
|
|
{
|
|
"entropy": 5.800376892089844,
|
|
"epoch": 0.5787373004354136,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004973127683337482,
|
|
"loss": 5.6412,
|
|
"mean_token_accuracy": 0.1538746476173401,
|
|
"num_tokens": 13258255.0,
|
|
"step": 6380
|
|
},
|
|
{
|
|
"entropy": 5.734482097625732,
|
|
"epoch": 0.5791908563134979,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004973077802201911,
|
|
"loss": 5.6489,
|
|
"mean_token_accuracy": 0.15466178506612777,
|
|
"num_tokens": 13268416.0,
|
|
"step": 6385
|
|
},
|
|
{
|
|
"entropy": 5.756858682632446,
|
|
"epoch": 0.579644412191582,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004973027875092526,
|
|
"loss": 5.6512,
|
|
"mean_token_accuracy": 0.15202094316482545,
|
|
"num_tokens": 13278087.0,
|
|
"step": 6390
|
|
},
|
|
{
|
|
"entropy": 5.738783597946167,
|
|
"epoch": 0.5800979680696662,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004972977902010357,
|
|
"loss": 5.5609,
|
|
"mean_token_accuracy": 0.16106198728084564,
|
|
"num_tokens": 13288121.0,
|
|
"step": 6395
|
|
},
|
|
{
|
|
"entropy": 5.840384197235108,
|
|
"epoch": 0.5805515239477503,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004972927882956439,
|
|
"loss": 5.7589,
|
|
"mean_token_accuracy": 0.1446023926138878,
|
|
"num_tokens": 13298620.0,
|
|
"step": 6400
|
|
},
|
|
{
|
|
"entropy": 5.742712450027466,
|
|
"epoch": 0.5810050798258345,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004972877817931807,
|
|
"loss": 5.5853,
|
|
"mean_token_accuracy": 0.15124613642692566,
|
|
"num_tokens": 13308413.0,
|
|
"step": 6405
|
|
},
|
|
{
|
|
"entropy": 5.773351430892944,
|
|
"epoch": 0.5814586357039188,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004972827706937493,
|
|
"loss": 5.6795,
|
|
"mean_token_accuracy": 0.15599592328071593,
|
|
"num_tokens": 13319387.0,
|
|
"step": 6410
|
|
},
|
|
{
|
|
"entropy": 5.802117109298706,
|
|
"epoch": 0.5819121915820029,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004972777549974537,
|
|
"loss": 5.6197,
|
|
"mean_token_accuracy": 0.1567063510417938,
|
|
"num_tokens": 13330494.0,
|
|
"step": 6415
|
|
},
|
|
{
|
|
"entropy": 5.739154100418091,
|
|
"epoch": 0.5823657474600871,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004972727347043975,
|
|
"loss": 5.6486,
|
|
"mean_token_accuracy": 0.1529611423611641,
|
|
"num_tokens": 13341009.0,
|
|
"step": 6420
|
|
},
|
|
{
|
|
"entropy": 5.731442546844482,
|
|
"epoch": 0.5828193033381712,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004972677098146845,
|
|
"loss": 5.5792,
|
|
"mean_token_accuracy": 0.15856897830963135,
|
|
"num_tokens": 13351269.0,
|
|
"step": 6425
|
|
},
|
|
{
|
|
"entropy": 5.72405776977539,
|
|
"epoch": 0.5832728592162555,
|
|
"grad_norm": 4.625,
|
|
"learning_rate": 0.0004972626803284185,
|
|
"loss": 5.7119,
|
|
"mean_token_accuracy": 0.1523909494280815,
|
|
"num_tokens": 13362160.0,
|
|
"step": 6430
|
|
},
|
|
{
|
|
"entropy": 5.816617250442505,
|
|
"epoch": 0.5837264150943396,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004972576462457038,
|
|
"loss": 5.763,
|
|
"mean_token_accuracy": 0.14996671974658965,
|
|
"num_tokens": 13372497.0,
|
|
"step": 6435
|
|
},
|
|
{
|
|
"entropy": 5.914173889160156,
|
|
"epoch": 0.5841799709724238,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004972526075666442,
|
|
"loss": 5.6892,
|
|
"mean_token_accuracy": 0.1595553070306778,
|
|
"num_tokens": 13381665.0,
|
|
"step": 6440
|
|
},
|
|
{
|
|
"entropy": 5.676478433609009,
|
|
"epoch": 0.584633526850508,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004972475642913442,
|
|
"loss": 5.5968,
|
|
"mean_token_accuracy": 0.15799911618232726,
|
|
"num_tokens": 13392507.0,
|
|
"step": 6445
|
|
},
|
|
{
|
|
"entropy": 5.675682163238525,
|
|
"epoch": 0.5850870827285921,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004972425164199078,
|
|
"loss": 5.6109,
|
|
"mean_token_accuracy": 0.1597040683031082,
|
|
"num_tokens": 13402171.0,
|
|
"step": 6450
|
|
},
|
|
{
|
|
"entropy": 5.843981122970581,
|
|
"epoch": 0.5855406386066764,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004972374639524396,
|
|
"loss": 5.7999,
|
|
"mean_token_accuracy": 0.14906672090291978,
|
|
"num_tokens": 13412933.0,
|
|
"step": 6455
|
|
},
|
|
{
|
|
"entropy": 5.806398105621338,
|
|
"epoch": 0.5859941944847605,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.000497232406889044,
|
|
"loss": 5.6419,
|
|
"mean_token_accuracy": 0.1513127401471138,
|
|
"num_tokens": 13423563.0,
|
|
"step": 6460
|
|
},
|
|
{
|
|
"entropy": 5.852730798721313,
|
|
"epoch": 0.5864477503628447,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004972273452298255,
|
|
"loss": 5.667,
|
|
"mean_token_accuracy": 0.15766609236598014,
|
|
"num_tokens": 13433998.0,
|
|
"step": 6465
|
|
},
|
|
{
|
|
"entropy": 5.733954334259034,
|
|
"epoch": 0.5869013062409288,
|
|
"grad_norm": 2.875,
|
|
"learning_rate": 0.0004972222789748888,
|
|
"loss": 5.6163,
|
|
"mean_token_accuracy": 0.1577115073800087,
|
|
"num_tokens": 13443878.0,
|
|
"step": 6470
|
|
},
|
|
{
|
|
"entropy": 5.718626022338867,
|
|
"epoch": 0.5873548621190131,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.0004972172081243389,
|
|
"loss": 5.709,
|
|
"mean_token_accuracy": 0.14359332993626595,
|
|
"num_tokens": 13456051.0,
|
|
"step": 6475
|
|
},
|
|
{
|
|
"entropy": 5.832206058502197,
|
|
"epoch": 0.5878084179970973,
|
|
"grad_norm": 3.359375,
|
|
"learning_rate": 0.0004972121326782806,
|
|
"loss": 5.7064,
|
|
"mean_token_accuracy": 0.15390692949295043,
|
|
"num_tokens": 13467276.0,
|
|
"step": 6480
|
|
},
|
|
{
|
|
"entropy": 5.777996397018432,
|
|
"epoch": 0.5882619738751814,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004972070526368186,
|
|
"loss": 5.6924,
|
|
"mean_token_accuracy": 0.1549999363720417,
|
|
"num_tokens": 13478331.0,
|
|
"step": 6485
|
|
},
|
|
{
|
|
"entropy": 5.788837480545044,
|
|
"epoch": 0.5887155297532656,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004972019680000582,
|
|
"loss": 5.6127,
|
|
"mean_token_accuracy": 0.15205416679382325,
|
|
"num_tokens": 13489879.0,
|
|
"step": 6490
|
|
},
|
|
{
|
|
"entropy": 5.781062746047974,
|
|
"epoch": 0.5891690856313497,
|
|
"grad_norm": 2.921875,
|
|
"learning_rate": 0.0004971968787681044,
|
|
"loss": 5.7449,
|
|
"mean_token_accuracy": 0.15462507754564286,
|
|
"num_tokens": 13500879.0,
|
|
"step": 6495
|
|
},
|
|
{
|
|
"entropy": 5.815672445297241,
|
|
"epoch": 0.589622641509434,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004971917849410627,
|
|
"loss": 5.7127,
|
|
"mean_token_accuracy": 0.15203070044517517,
|
|
"num_tokens": 13511719.0,
|
|
"step": 6500
|
|
},
|
|
{
|
|
"entropy": 5.77512640953064,
|
|
"epoch": 0.5900761973875182,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.0004971866865190381,
|
|
"loss": 5.635,
|
|
"mean_token_accuracy": 0.15535284876823424,
|
|
"num_tokens": 13521850.0,
|
|
"step": 6505
|
|
},
|
|
{
|
|
"entropy": 5.83427414894104,
|
|
"epoch": 0.5905297532656023,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004971815835021362,
|
|
"loss": 5.6695,
|
|
"mean_token_accuracy": 0.15581846982240677,
|
|
"num_tokens": 13532095.0,
|
|
"step": 6510
|
|
},
|
|
{
|
|
"entropy": 5.7484681606292725,
|
|
"epoch": 0.5909833091436865,
|
|
"grad_norm": 3.09375,
|
|
"learning_rate": 0.0004971764758904626,
|
|
"loss": 5.6417,
|
|
"mean_token_accuracy": 0.14961459189653398,
|
|
"num_tokens": 13543133.0,
|
|
"step": 6515
|
|
},
|
|
{
|
|
"entropy": 5.751182270050049,
|
|
"epoch": 0.5914368650217707,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004971713636841229,
|
|
"loss": 5.7191,
|
|
"mean_token_accuracy": 0.14607228338718414,
|
|
"num_tokens": 13553771.0,
|
|
"step": 6520
|
|
},
|
|
{
|
|
"entropy": 5.724217700958252,
|
|
"epoch": 0.5918904208998549,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004971662468832228,
|
|
"loss": 5.6471,
|
|
"mean_token_accuracy": 0.15626089870929719,
|
|
"num_tokens": 13564548.0,
|
|
"step": 6525
|
|
},
|
|
{
|
|
"entropy": 5.78565034866333,
|
|
"epoch": 0.592343976777939,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.000497161125487868,
|
|
"loss": 5.6305,
|
|
"mean_token_accuracy": 0.1553097426891327,
|
|
"num_tokens": 13574567.0,
|
|
"step": 6530
|
|
},
|
|
{
|
|
"entropy": 5.737082815170288,
|
|
"epoch": 0.5927975326560232,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004971559994981645,
|
|
"loss": 5.6748,
|
|
"mean_token_accuracy": 0.1555297389626503,
|
|
"num_tokens": 13585302.0,
|
|
"step": 6535
|
|
},
|
|
{
|
|
"entropy": 5.789227914810181,
|
|
"epoch": 0.5932510885341074,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004971508689142184,
|
|
"loss": 5.7061,
|
|
"mean_token_accuracy": 0.1495283529162407,
|
|
"num_tokens": 13594754.0,
|
|
"step": 6540
|
|
},
|
|
{
|
|
"entropy": 5.746747541427612,
|
|
"epoch": 0.5937046444121916,
|
|
"grad_norm": 5.1875,
|
|
"learning_rate": 0.0004971457337361356,
|
|
"loss": 5.6402,
|
|
"mean_token_accuracy": 0.15646791607141494,
|
|
"num_tokens": 13604691.0,
|
|
"step": 6545
|
|
},
|
|
{
|
|
"entropy": 5.648950910568237,
|
|
"epoch": 0.5941582002902758,
|
|
"grad_norm": 3.0,
|
|
"learning_rate": 0.0004971405939640225,
|
|
"loss": 5.5617,
|
|
"mean_token_accuracy": 0.16001858487725257,
|
|
"num_tokens": 13613911.0,
|
|
"step": 6550
|
|
},
|
|
{
|
|
"entropy": 5.920597696304322,
|
|
"epoch": 0.5946117561683599,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004971354495979854,
|
|
"loss": 5.768,
|
|
"mean_token_accuracy": 0.152364581823349,
|
|
"num_tokens": 13624285.0,
|
|
"step": 6555
|
|
},
|
|
{
|
|
"entropy": 5.822053241729736,
|
|
"epoch": 0.5950653120464441,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004971303006381305,
|
|
"loss": 5.6054,
|
|
"mean_token_accuracy": 0.1551180973649025,
|
|
"num_tokens": 13635434.0,
|
|
"step": 6560
|
|
},
|
|
{
|
|
"entropy": 5.768273448944091,
|
|
"epoch": 0.5955188679245284,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004971251470845643,
|
|
"loss": 5.6781,
|
|
"mean_token_accuracy": 0.1518924981355667,
|
|
"num_tokens": 13645582.0,
|
|
"step": 6565
|
|
},
|
|
{
|
|
"entropy": 5.699561405181885,
|
|
"epoch": 0.5959724238026125,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004971199889373935,
|
|
"loss": 5.6228,
|
|
"mean_token_accuracy": 0.15436237156391144,
|
|
"num_tokens": 13655029.0,
|
|
"step": 6570
|
|
},
|
|
{
|
|
"entropy": 5.711526155471802,
|
|
"epoch": 0.5964259796806967,
|
|
"grad_norm": 3.328125,
|
|
"learning_rate": 0.0004971148261967249,
|
|
"loss": 5.6159,
|
|
"mean_token_accuracy": 0.15454744100570678,
|
|
"num_tokens": 13665204.0,
|
|
"step": 6575
|
|
},
|
|
{
|
|
"entropy": 5.790972518920898,
|
|
"epoch": 0.5968795355587808,
|
|
"grad_norm": 4.0,
|
|
"learning_rate": 0.0004971096588626649,
|
|
"loss": 5.7243,
|
|
"mean_token_accuracy": 0.15180352926254273,
|
|
"num_tokens": 13676281.0,
|
|
"step": 6580
|
|
},
|
|
{
|
|
"entropy": 5.758441495895386,
|
|
"epoch": 0.597333091436865,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004971044869353206,
|
|
"loss": 5.7068,
|
|
"mean_token_accuracy": 0.16017238646745682,
|
|
"num_tokens": 13687144.0,
|
|
"step": 6585
|
|
},
|
|
{
|
|
"entropy": 5.8007988929748535,
|
|
"epoch": 0.5977866473149492,
|
|
"grad_norm": 3.453125,
|
|
"learning_rate": 0.000497099310414799,
|
|
"loss": 5.6572,
|
|
"mean_token_accuracy": 0.14968026280403138,
|
|
"num_tokens": 13696371.0,
|
|
"step": 6590
|
|
},
|
|
{
|
|
"entropy": 5.84863429069519,
|
|
"epoch": 0.5982402031930334,
|
|
"grad_norm": 3.078125,
|
|
"learning_rate": 0.0004970941293012069,
|
|
"loss": 5.6164,
|
|
"mean_token_accuracy": 0.15415885299444199,
|
|
"num_tokens": 13706900.0,
|
|
"step": 6595
|
|
},
|
|
{
|
|
"entropy": 5.796767044067383,
|
|
"epoch": 0.5986937590711175,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004970889435946518,
|
|
"loss": 5.6944,
|
|
"mean_token_accuracy": 0.15410789847373962,
|
|
"num_tokens": 13717874.0,
|
|
"step": 6600
|
|
},
|
|
{
|
|
"entropy": 5.756249475479126,
|
|
"epoch": 0.5991473149492017,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004970837532952406,
|
|
"loss": 5.6485,
|
|
"mean_token_accuracy": 0.1519013985991478,
|
|
"num_tokens": 13728020.0,
|
|
"step": 6605
|
|
},
|
|
{
|
|
"entropy": 5.794941711425781,
|
|
"epoch": 0.599600870827286,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.0004970785584030808,
|
|
"loss": 5.6978,
|
|
"mean_token_accuracy": 0.15266939252614975,
|
|
"num_tokens": 13738007.0,
|
|
"step": 6610
|
|
},
|
|
{
|
|
"entropy": 5.823725843429566,
|
|
"epoch": 0.6000544267053701,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004970733589182799,
|
|
"loss": 5.7034,
|
|
"mean_token_accuracy": 0.15135803669691086,
|
|
"num_tokens": 13749429.0,
|
|
"step": 6615
|
|
},
|
|
{
|
|
"entropy": 5.7685328960418705,
|
|
"epoch": 0.6005079825834543,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004970681548409452,
|
|
"loss": 5.5744,
|
|
"mean_token_accuracy": 0.16029660254716874,
|
|
"num_tokens": 13760279.0,
|
|
"step": 6620
|
|
},
|
|
{
|
|
"entropy": 5.792378854751587,
|
|
"epoch": 0.6009615384615384,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004970629461711846,
|
|
"loss": 5.7863,
|
|
"mean_token_accuracy": 0.1477381929755211,
|
|
"num_tokens": 13770575.0,
|
|
"step": 6625
|
|
},
|
|
{
|
|
"entropy": 5.754233694076538,
|
|
"epoch": 0.6014150943396226,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004970577329091057,
|
|
"loss": 5.6294,
|
|
"mean_token_accuracy": 0.15650067627429962,
|
|
"num_tokens": 13781068.0,
|
|
"step": 6630
|
|
},
|
|
{
|
|
"entropy": 5.857264184951783,
|
|
"epoch": 0.6018686502177069,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004970525150548162,
|
|
"loss": 5.7015,
|
|
"mean_token_accuracy": 0.15616442114114762,
|
|
"num_tokens": 13790745.0,
|
|
"step": 6635
|
|
},
|
|
{
|
|
"entropy": 5.786818790435791,
|
|
"epoch": 0.602322206095791,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004970472926084242,
|
|
"loss": 5.627,
|
|
"mean_token_accuracy": 0.1557512104511261,
|
|
"num_tokens": 13800196.0,
|
|
"step": 6640
|
|
},
|
|
{
|
|
"entropy": 5.717859745025635,
|
|
"epoch": 0.6027757619738752,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004970420655700375,
|
|
"loss": 5.5438,
|
|
"mean_token_accuracy": 0.15962371081113816,
|
|
"num_tokens": 13809954.0,
|
|
"step": 6645
|
|
},
|
|
{
|
|
"entropy": 5.706457853317261,
|
|
"epoch": 0.6032293178519593,
|
|
"grad_norm": 9.3125,
|
|
"learning_rate": 0.0004970368339397643,
|
|
"loss": 5.6972,
|
|
"mean_token_accuracy": 0.15097275376319885,
|
|
"num_tokens": 13820281.0,
|
|
"step": 6650
|
|
},
|
|
{
|
|
"entropy": 5.847550535202027,
|
|
"epoch": 0.6036828737300436,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004970315977177129,
|
|
"loss": 5.6611,
|
|
"mean_token_accuracy": 0.15552590638399125,
|
|
"num_tokens": 13830614.0,
|
|
"step": 6655
|
|
},
|
|
{
|
|
"entropy": 5.773291969299317,
|
|
"epoch": 0.6041364296081277,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004970263569039914,
|
|
"loss": 5.6072,
|
|
"mean_token_accuracy": 0.1574172392487526,
|
|
"num_tokens": 13840551.0,
|
|
"step": 6660
|
|
},
|
|
{
|
|
"entropy": 5.838003158569336,
|
|
"epoch": 0.6045899854862119,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004970211114987083,
|
|
"loss": 5.7941,
|
|
"mean_token_accuracy": 0.14930742010474204,
|
|
"num_tokens": 13851830.0,
|
|
"step": 6665
|
|
},
|
|
{
|
|
"entropy": 5.783898496627808,
|
|
"epoch": 0.6050435413642961,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004970158615019719,
|
|
"loss": 5.597,
|
|
"mean_token_accuracy": 0.1558218017220497,
|
|
"num_tokens": 13862299.0,
|
|
"step": 6670
|
|
},
|
|
{
|
|
"entropy": 5.888981723785401,
|
|
"epoch": 0.6054970972423802,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004970106069138912,
|
|
"loss": 5.7321,
|
|
"mean_token_accuracy": 0.14841488599777222,
|
|
"num_tokens": 13872852.0,
|
|
"step": 6675
|
|
},
|
|
{
|
|
"entropy": 5.780848693847656,
|
|
"epoch": 0.6059506531204645,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004970053477345743,
|
|
"loss": 5.679,
|
|
"mean_token_accuracy": 0.16062871217727662,
|
|
"num_tokens": 13883601.0,
|
|
"step": 6680
|
|
},
|
|
{
|
|
"entropy": 5.772215461730957,
|
|
"epoch": 0.6064042089985486,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004970000839641304,
|
|
"loss": 5.6774,
|
|
"mean_token_accuracy": 0.1588228940963745,
|
|
"num_tokens": 13894246.0,
|
|
"step": 6685
|
|
},
|
|
{
|
|
"entropy": 5.728923892974853,
|
|
"epoch": 0.6068577648766328,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004969948156026681,
|
|
"loss": 5.6967,
|
|
"mean_token_accuracy": 0.1531152456998825,
|
|
"num_tokens": 13904823.0,
|
|
"step": 6690
|
|
},
|
|
{
|
|
"entropy": 5.882969808578491,
|
|
"epoch": 0.6073113207547169,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004969895426502965,
|
|
"loss": 5.7097,
|
|
"mean_token_accuracy": 0.14678643122315407,
|
|
"num_tokens": 13915338.0,
|
|
"step": 6695
|
|
},
|
|
{
|
|
"entropy": 5.754983043670654,
|
|
"epoch": 0.6077648766328012,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004969842651071246,
|
|
"loss": 5.6622,
|
|
"mean_token_accuracy": 0.15358965694904328,
|
|
"num_tokens": 13925838.0,
|
|
"step": 6700
|
|
},
|
|
{
|
|
"entropy": 5.784938812255859,
|
|
"epoch": 0.6082184325108854,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004969789829732615,
|
|
"loss": 5.6533,
|
|
"mean_token_accuracy": 0.15099577605724335,
|
|
"num_tokens": 13936341.0,
|
|
"step": 6705
|
|
},
|
|
{
|
|
"entropy": 5.796441841125488,
|
|
"epoch": 0.6086719883889695,
|
|
"grad_norm": 5.4375,
|
|
"learning_rate": 0.0004969736962488164,
|
|
"loss": 5.6789,
|
|
"mean_token_accuracy": 0.15407094806432725,
|
|
"num_tokens": 13945438.0,
|
|
"step": 6710
|
|
},
|
|
{
|
|
"entropy": 5.788770055770874,
|
|
"epoch": 0.6091255442670537,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004969684049338987,
|
|
"loss": 5.5788,
|
|
"mean_token_accuracy": 0.14951442778110505,
|
|
"num_tokens": 13956029.0,
|
|
"step": 6715
|
|
},
|
|
{
|
|
"entropy": 5.802248239517212,
|
|
"epoch": 0.6095791001451378,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.000496963109028618,
|
|
"loss": 5.6715,
|
|
"mean_token_accuracy": 0.14977479204535485,
|
|
"num_tokens": 13966498.0,
|
|
"step": 6720
|
|
},
|
|
{
|
|
"entropy": 5.763838195800782,
|
|
"epoch": 0.6100326560232221,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.0004969578085330834,
|
|
"loss": 5.6424,
|
|
"mean_token_accuracy": 0.1522256314754486,
|
|
"num_tokens": 13976997.0,
|
|
"step": 6725
|
|
},
|
|
{
|
|
"entropy": 5.8410039901733395,
|
|
"epoch": 0.6104862119013063,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004969525034474049,
|
|
"loss": 5.6349,
|
|
"mean_token_accuracy": 0.1578125163912773,
|
|
"num_tokens": 13986664.0,
|
|
"step": 6730
|
|
},
|
|
{
|
|
"entropy": 5.728191089630127,
|
|
"epoch": 0.6109397677793904,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.000496947193771692,
|
|
"loss": 5.6585,
|
|
"mean_token_accuracy": 0.15620095580816268,
|
|
"num_tokens": 13997828.0,
|
|
"step": 6735
|
|
},
|
|
{
|
|
"entropy": 5.7189115524292,
|
|
"epoch": 0.6113933236574746,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004969418795060548,
|
|
"loss": 5.5975,
|
|
"mean_token_accuracy": 0.15450024902820586,
|
|
"num_tokens": 14008293.0,
|
|
"step": 6740
|
|
},
|
|
{
|
|
"entropy": 5.708045387268067,
|
|
"epoch": 0.6118468795355588,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004969365606506027,
|
|
"loss": 5.5776,
|
|
"mean_token_accuracy": 0.1588921070098877,
|
|
"num_tokens": 14018031.0,
|
|
"step": 6745
|
|
},
|
|
{
|
|
"entropy": 5.698815870285034,
|
|
"epoch": 0.612300435413643,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004969312372054461,
|
|
"loss": 5.5546,
|
|
"mean_token_accuracy": 0.1623407393693924,
|
|
"num_tokens": 14028013.0,
|
|
"step": 6750
|
|
},
|
|
{
|
|
"entropy": 5.706755018234253,
|
|
"epoch": 0.6127539912917271,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004969259091706948,
|
|
"loss": 5.681,
|
|
"mean_token_accuracy": 0.15510369837284088,
|
|
"num_tokens": 14039787.0,
|
|
"step": 6755
|
|
},
|
|
{
|
|
"entropy": 5.749244928359985,
|
|
"epoch": 0.6132075471698113,
|
|
"grad_norm": 3.109375,
|
|
"learning_rate": 0.0004969205765464593,
|
|
"loss": 5.5586,
|
|
"mean_token_accuracy": 0.156866218149662,
|
|
"num_tokens": 14049223.0,
|
|
"step": 6760
|
|
},
|
|
{
|
|
"entropy": 5.757191324234009,
|
|
"epoch": 0.6136611030478955,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004969152393328497,
|
|
"loss": 5.6249,
|
|
"mean_token_accuracy": 0.16180411130189895,
|
|
"num_tokens": 14059004.0,
|
|
"step": 6765
|
|
},
|
|
{
|
|
"entropy": 5.812931060791016,
|
|
"epoch": 0.6141146589259797,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004969098975299764,
|
|
"loss": 5.7093,
|
|
"mean_token_accuracy": 0.14600952416658403,
|
|
"num_tokens": 14069615.0,
|
|
"step": 6770
|
|
},
|
|
{
|
|
"entropy": 5.7707301616668705,
|
|
"epoch": 0.6145682148040639,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004969045511379499,
|
|
"loss": 5.6474,
|
|
"mean_token_accuracy": 0.15415120422840117,
|
|
"num_tokens": 14078886.0,
|
|
"step": 6775
|
|
},
|
|
{
|
|
"entropy": 5.795013856887818,
|
|
"epoch": 0.615021770682148,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004968992001568806,
|
|
"loss": 5.7203,
|
|
"mean_token_accuracy": 0.14738596454262734,
|
|
"num_tokens": 14089021.0,
|
|
"step": 6780
|
|
},
|
|
{
|
|
"entropy": 5.7487105369567875,
|
|
"epoch": 0.6154753265602322,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004968938445868795,
|
|
"loss": 5.5626,
|
|
"mean_token_accuracy": 0.16147104948759078,
|
|
"num_tokens": 14098316.0,
|
|
"step": 6785
|
|
},
|
|
{
|
|
"entropy": 5.750917434692383,
|
|
"epoch": 0.6159288824383164,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004968884844280569,
|
|
"loss": 5.6483,
|
|
"mean_token_accuracy": 0.14891300946474076,
|
|
"num_tokens": 14108874.0,
|
|
"step": 6790
|
|
},
|
|
{
|
|
"entropy": 5.798082160949707,
|
|
"epoch": 0.6163824383164006,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.0004968831196805242,
|
|
"loss": 5.7037,
|
|
"mean_token_accuracy": 0.15190935805439948,
|
|
"num_tokens": 14119613.0,
|
|
"step": 6795
|
|
},
|
|
{
|
|
"entropy": 5.810618591308594,
|
|
"epoch": 0.6168359941944848,
|
|
"grad_norm": 3.8125,
|
|
"learning_rate": 0.0004968777503443918,
|
|
"loss": 5.6416,
|
|
"mean_token_accuracy": 0.1516499012708664,
|
|
"num_tokens": 14129085.0,
|
|
"step": 6800
|
|
},
|
|
{
|
|
"entropy": 5.648369979858399,
|
|
"epoch": 0.6172895500725689,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004968723764197711,
|
|
"loss": 5.5289,
|
|
"mean_token_accuracy": 0.16768998205661773,
|
|
"num_tokens": 14138461.0,
|
|
"step": 6805
|
|
},
|
|
{
|
|
"entropy": 5.750721549987793,
|
|
"epoch": 0.6177431059506531,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.000496866997906773,
|
|
"loss": 5.5976,
|
|
"mean_token_accuracy": 0.15950866043567657,
|
|
"num_tokens": 14149126.0,
|
|
"step": 6810
|
|
},
|
|
{
|
|
"entropy": 5.729853963851928,
|
|
"epoch": 0.6181966618287373,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004968616148055089,
|
|
"loss": 5.6058,
|
|
"mean_token_accuracy": 0.16136523485183715,
|
|
"num_tokens": 14160068.0,
|
|
"step": 6815
|
|
},
|
|
{
|
|
"entropy": 5.7663956642150875,
|
|
"epoch": 0.6186502177068215,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004968562271160901,
|
|
"loss": 5.7195,
|
|
"mean_token_accuracy": 0.15396957993507385,
|
|
"num_tokens": 14170288.0,
|
|
"step": 6820
|
|
},
|
|
{
|
|
"entropy": 5.772651624679566,
|
|
"epoch": 0.6191037735849056,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.000496850834838628,
|
|
"loss": 5.6992,
|
|
"mean_token_accuracy": 0.15586561411619188,
|
|
"num_tokens": 14181231.0,
|
|
"step": 6825
|
|
},
|
|
{
|
|
"entropy": 5.778563213348389,
|
|
"epoch": 0.6195573294629898,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004968454379732342,
|
|
"loss": 5.6078,
|
|
"mean_token_accuracy": 0.1582838088274002,
|
|
"num_tokens": 14191715.0,
|
|
"step": 6830
|
|
},
|
|
{
|
|
"entropy": 5.735866069793701,
|
|
"epoch": 0.6200108853410741,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.00049684003652002,
|
|
"loss": 5.5997,
|
|
"mean_token_accuracy": 0.15433213114738464,
|
|
"num_tokens": 14203416.0,
|
|
"step": 6835
|
|
},
|
|
{
|
|
"entropy": 5.695660734176636,
|
|
"epoch": 0.6204644412191582,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.0004968346304790973,
|
|
"loss": 5.5682,
|
|
"mean_token_accuracy": 0.1618633046746254,
|
|
"num_tokens": 14213658.0,
|
|
"step": 6840
|
|
},
|
|
{
|
|
"entropy": 5.8019201278686525,
|
|
"epoch": 0.6209179970972424,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004968292198505781,
|
|
"loss": 5.732,
|
|
"mean_token_accuracy": 0.14817453622817994,
|
|
"num_tokens": 14223956.0,
|
|
"step": 6845
|
|
},
|
|
{
|
|
"entropy": 5.831279468536377,
|
|
"epoch": 0.6213715529753265,
|
|
"grad_norm": 3.984375,
|
|
"learning_rate": 0.000496823804634574,
|
|
"loss": 5.73,
|
|
"mean_token_accuracy": 0.15022608637809753,
|
|
"num_tokens": 14236801.0,
|
|
"step": 6850
|
|
},
|
|
{
|
|
"entropy": 5.737774848937988,
|
|
"epoch": 0.6218251088534107,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004968183848311972,
|
|
"loss": 5.5545,
|
|
"mean_token_accuracy": 0.1597556382417679,
|
|
"num_tokens": 14247382.0,
|
|
"step": 6855
|
|
},
|
|
{
|
|
"entropy": 5.777302408218384,
|
|
"epoch": 0.622278664731495,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004968129604405596,
|
|
"loss": 5.6332,
|
|
"mean_token_accuracy": 0.15609384775161744,
|
|
"num_tokens": 14258627.0,
|
|
"step": 6860
|
|
},
|
|
{
|
|
"entropy": 5.725931549072266,
|
|
"epoch": 0.6227322206095791,
|
|
"grad_norm": 3.546875,
|
|
"learning_rate": 0.0004968075314627734,
|
|
"loss": 5.622,
|
|
"mean_token_accuracy": 0.15463528782129288,
|
|
"num_tokens": 14269013.0,
|
|
"step": 6865
|
|
},
|
|
{
|
|
"entropy": 5.804495143890381,
|
|
"epoch": 0.6231857764876633,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.000496802097897951,
|
|
"loss": 5.6109,
|
|
"mean_token_accuracy": 0.16023218929767608,
|
|
"num_tokens": 14279620.0,
|
|
"step": 6870
|
|
},
|
|
{
|
|
"entropy": 5.734587478637695,
|
|
"epoch": 0.6236393323657474,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004967966597462046,
|
|
"loss": 5.6276,
|
|
"mean_token_accuracy": 0.16197851449251174,
|
|
"num_tokens": 14289448.0,
|
|
"step": 6875
|
|
},
|
|
{
|
|
"entropy": 5.7310723781585695,
|
|
"epoch": 0.6240928882438317,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004967912170076469,
|
|
"loss": 5.6409,
|
|
"mean_token_accuracy": 0.153085844963789,
|
|
"num_tokens": 14299999.0,
|
|
"step": 6880
|
|
},
|
|
{
|
|
"entropy": 5.724435091018677,
|
|
"epoch": 0.6245464441219158,
|
|
"grad_norm": 3.8125,
|
|
"learning_rate": 0.0004967857696823901,
|
|
"loss": 5.6104,
|
|
"mean_token_accuracy": 0.15244664996862411,
|
|
"num_tokens": 14310384.0,
|
|
"step": 6885
|
|
},
|
|
{
|
|
"entropy": 5.800471925735474,
|
|
"epoch": 0.625,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004967803177705472,
|
|
"loss": 5.705,
|
|
"mean_token_accuracy": 0.15142763704061507,
|
|
"num_tokens": 14320644.0,
|
|
"step": 6890
|
|
},
|
|
{
|
|
"entropy": 5.820406770706176,
|
|
"epoch": 0.6254535558780842,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004967748612722308,
|
|
"loss": 5.6746,
|
|
"mean_token_accuracy": 0.150961971282959,
|
|
"num_tokens": 14330077.0,
|
|
"step": 6895
|
|
},
|
|
{
|
|
"entropy": 5.784531354904175,
|
|
"epoch": 0.6259071117561683,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004967694001875538,
|
|
"loss": 5.7679,
|
|
"mean_token_accuracy": 0.14856128245592118,
|
|
"num_tokens": 14341549.0,
|
|
"step": 6900
|
|
},
|
|
{
|
|
"entropy": 5.771959972381592,
|
|
"epoch": 0.6263606676342526,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.000496763934516629,
|
|
"loss": 5.6458,
|
|
"mean_token_accuracy": 0.1570087343454361,
|
|
"num_tokens": 14352146.0,
|
|
"step": 6905
|
|
},
|
|
{
|
|
"entropy": 5.73153977394104,
|
|
"epoch": 0.6268142235123367,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004967584642595696,
|
|
"loss": 5.6305,
|
|
"mean_token_accuracy": 0.15252010822296141,
|
|
"num_tokens": 14362521.0,
|
|
"step": 6910
|
|
},
|
|
{
|
|
"entropy": 5.779860877990723,
|
|
"epoch": 0.6272677793904209,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.0004967529894164887,
|
|
"loss": 5.6846,
|
|
"mean_token_accuracy": 0.1533489242196083,
|
|
"num_tokens": 14373216.0,
|
|
"step": 6915
|
|
},
|
|
{
|
|
"entropy": 5.749915695190429,
|
|
"epoch": 0.627721335268505,
|
|
"grad_norm": 2.84375,
|
|
"learning_rate": 0.0004967475099874992,
|
|
"loss": 5.5904,
|
|
"mean_token_accuracy": 0.1652483731508255,
|
|
"num_tokens": 14383104.0,
|
|
"step": 6920
|
|
},
|
|
{
|
|
"entropy": 5.7152907371521,
|
|
"epoch": 0.6281748911465893,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.000496742025972715,
|
|
"loss": 5.6335,
|
|
"mean_token_accuracy": 0.16333371847867967,
|
|
"num_tokens": 14393854.0,
|
|
"step": 6925
|
|
},
|
|
{
|
|
"entropy": 5.775513935089111,
|
|
"epoch": 0.6286284470246735,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.000496736537372249,
|
|
"loss": 5.5885,
|
|
"mean_token_accuracy": 0.1643975183367729,
|
|
"num_tokens": 14403213.0,
|
|
"step": 6930
|
|
},
|
|
{
|
|
"entropy": 5.840988874435425,
|
|
"epoch": 0.6290820029027576,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004967310441862151,
|
|
"loss": 5.7764,
|
|
"mean_token_accuracy": 0.14523438438773156,
|
|
"num_tokens": 14412792.0,
|
|
"step": 6935
|
|
},
|
|
{
|
|
"entropy": 5.806761837005615,
|
|
"epoch": 0.6295355587808418,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004967255464147265,
|
|
"loss": 5.6461,
|
|
"mean_token_accuracy": 0.15509824603796005,
|
|
"num_tokens": 14423061.0,
|
|
"step": 6940
|
|
},
|
|
{
|
|
"entropy": 5.78497633934021,
|
|
"epoch": 0.6299891146589259,
|
|
"grad_norm": 5.8125,
|
|
"learning_rate": 0.0004967200440578972,
|
|
"loss": 5.5931,
|
|
"mean_token_accuracy": 0.15885335355997085,
|
|
"num_tokens": 14433338.0,
|
|
"step": 6945
|
|
},
|
|
{
|
|
"entropy": 5.7435633659362795,
|
|
"epoch": 0.6304426705370102,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004967145371158408,
|
|
"loss": 5.5782,
|
|
"mean_token_accuracy": 0.1651199445128441,
|
|
"num_tokens": 14444124.0,
|
|
"step": 6950
|
|
},
|
|
{
|
|
"entropy": 5.7816649913787845,
|
|
"epoch": 0.6308962264150944,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004967090255886714,
|
|
"loss": 5.6981,
|
|
"mean_token_accuracy": 0.15614887624979018,
|
|
"num_tokens": 14453868.0,
|
|
"step": 6955
|
|
},
|
|
{
|
|
"entropy": 5.772961521148682,
|
|
"epoch": 0.6313497822931785,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004967035094765028,
|
|
"loss": 5.6012,
|
|
"mean_token_accuracy": 0.15304825007915496,
|
|
"num_tokens": 14465015.0,
|
|
"step": 6960
|
|
},
|
|
{
|
|
"entropy": 5.720942449569702,
|
|
"epoch": 0.6318033381712627,
|
|
"grad_norm": 3.984375,
|
|
"learning_rate": 0.0004966979887794491,
|
|
"loss": 5.5757,
|
|
"mean_token_accuracy": 0.1620814934372902,
|
|
"num_tokens": 14475523.0,
|
|
"step": 6965
|
|
},
|
|
{
|
|
"entropy": 5.7405132293701175,
|
|
"epoch": 0.6322568940493469,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004966924634976245,
|
|
"loss": 5.6347,
|
|
"mean_token_accuracy": 0.15292872935533525,
|
|
"num_tokens": 14485523.0,
|
|
"step": 6970
|
|
},
|
|
{
|
|
"entropy": 5.809803819656372,
|
|
"epoch": 0.6327104499274311,
|
|
"grad_norm": 3.015625,
|
|
"learning_rate": 0.0004966869336311433,
|
|
"loss": 5.6984,
|
|
"mean_token_accuracy": 0.16131531298160554,
|
|
"num_tokens": 14495237.0,
|
|
"step": 6975
|
|
},
|
|
{
|
|
"entropy": 5.816791963577271,
|
|
"epoch": 0.6331640058055152,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004966813991801197,
|
|
"loss": 5.8113,
|
|
"mean_token_accuracy": 0.1457821674644947,
|
|
"num_tokens": 14506431.0,
|
|
"step": 6980
|
|
},
|
|
{
|
|
"entropy": 5.85917067527771,
|
|
"epoch": 0.6336175616835994,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004966758601446684,
|
|
"loss": 5.7372,
|
|
"mean_token_accuracy": 0.14926016479730606,
|
|
"num_tokens": 14517445.0,
|
|
"step": 6985
|
|
},
|
|
{
|
|
"entropy": 5.7707703590393065,
|
|
"epoch": 0.6340711175616836,
|
|
"grad_norm": 3.0,
|
|
"learning_rate": 0.0004966703165249038,
|
|
"loss": 5.6704,
|
|
"mean_token_accuracy": 0.14917180985212325,
|
|
"num_tokens": 14527818.0,
|
|
"step": 6990
|
|
},
|
|
{
|
|
"entropy": 5.7728606224060055,
|
|
"epoch": 0.6345246734397678,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004966647683209406,
|
|
"loss": 5.7489,
|
|
"mean_token_accuracy": 0.14479509368538857,
|
|
"num_tokens": 14538235.0,
|
|
"step": 6995
|
|
},
|
|
{
|
|
"entropy": 5.981025266647339,
|
|
"epoch": 0.634978229317852,
|
|
"grad_norm": 3.125,
|
|
"learning_rate": 0.0004966592155328935,
|
|
"loss": 5.7754,
|
|
"mean_token_accuracy": 0.14579777866601945,
|
|
"num_tokens": 14549784.0,
|
|
"step": 7000
|
|
},
|
|
{
|
|
"entropy": 5.875027751922607,
|
|
"epoch": 0.6354317851959361,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004966536581608771,
|
|
"loss": 5.7679,
|
|
"mean_token_accuracy": 0.14473922178149223,
|
|
"num_tokens": 14561057.0,
|
|
"step": 7005
|
|
},
|
|
{
|
|
"entropy": 5.778143692016601,
|
|
"epoch": 0.6358853410740203,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004966480962050069,
|
|
"loss": 5.675,
|
|
"mean_token_accuracy": 0.15713430494070052,
|
|
"num_tokens": 14570859.0,
|
|
"step": 7010
|
|
},
|
|
{
|
|
"entropy": 5.8072175025939945,
|
|
"epoch": 0.6363388969521045,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004966425296653974,
|
|
"loss": 5.6699,
|
|
"mean_token_accuracy": 0.16011741906404495,
|
|
"num_tokens": 14581066.0,
|
|
"step": 7015
|
|
},
|
|
{
|
|
"entropy": 5.772267436981201,
|
|
"epoch": 0.6367924528301887,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.000496636958542164,
|
|
"loss": 5.6578,
|
|
"mean_token_accuracy": 0.15138954669237137,
|
|
"num_tokens": 14590709.0,
|
|
"step": 7020
|
|
},
|
|
{
|
|
"entropy": 5.733920240402222,
|
|
"epoch": 0.6372460087082729,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004966313828354218,
|
|
"loss": 5.634,
|
|
"mean_token_accuracy": 0.1559073120355606,
|
|
"num_tokens": 14600849.0,
|
|
"step": 7025
|
|
},
|
|
{
|
|
"entropy": 5.766506862640381,
|
|
"epoch": 0.637699564586357,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.000496625802545286,
|
|
"loss": 5.5168,
|
|
"mean_token_accuracy": 0.1601102754473686,
|
|
"num_tokens": 14611427.0,
|
|
"step": 7030
|
|
},
|
|
{
|
|
"entropy": 5.8376936435699465,
|
|
"epoch": 0.6381531204644412,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004966202176718723,
|
|
"loss": 5.6952,
|
|
"mean_token_accuracy": 0.15300938487052917,
|
|
"num_tokens": 14623860.0,
|
|
"step": 7035
|
|
},
|
|
{
|
|
"entropy": 5.736017656326294,
|
|
"epoch": 0.6386066763425254,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004966146282152959,
|
|
"loss": 5.5947,
|
|
"mean_token_accuracy": 0.15307328402996062,
|
|
"num_tokens": 14633481.0,
|
|
"step": 7040
|
|
},
|
|
{
|
|
"entropy": 5.720715570449829,
|
|
"epoch": 0.6390602322206096,
|
|
"grad_norm": 3.125,
|
|
"learning_rate": 0.0004966090341756726,
|
|
"loss": 5.5762,
|
|
"mean_token_accuracy": 0.16294495910406112,
|
|
"num_tokens": 14643519.0,
|
|
"step": 7045
|
|
},
|
|
{
|
|
"entropy": 5.712062215805053,
|
|
"epoch": 0.6395137880986937,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.000496603435553118,
|
|
"loss": 5.6037,
|
|
"mean_token_accuracy": 0.16128794848918915,
|
|
"num_tokens": 14654570.0,
|
|
"step": 7050
|
|
},
|
|
{
|
|
"entropy": 5.797862768173218,
|
|
"epoch": 0.6399673439767779,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004965978323477478,
|
|
"loss": 5.6411,
|
|
"mean_token_accuracy": 0.14805451184511184,
|
|
"num_tokens": 14665596.0,
|
|
"step": 7055
|
|
},
|
|
{
|
|
"entropy": 5.791617488861084,
|
|
"epoch": 0.6404208998548622,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.000496592224559678,
|
|
"loss": 5.575,
|
|
"mean_token_accuracy": 0.1581504911184311,
|
|
"num_tokens": 14675660.0,
|
|
"step": 7060
|
|
},
|
|
{
|
|
"entropy": 5.788625335693359,
|
|
"epoch": 0.6408744557329463,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004965866121890245,
|
|
"loss": 5.7199,
|
|
"mean_token_accuracy": 0.1488729402422905,
|
|
"num_tokens": 14685229.0,
|
|
"step": 7065
|
|
},
|
|
{
|
|
"entropy": 5.798623323440552,
|
|
"epoch": 0.6413280116110305,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004965809952359034,
|
|
"loss": 5.6428,
|
|
"mean_token_accuracy": 0.15143994837999344,
|
|
"num_tokens": 14695672.0,
|
|
"step": 7070
|
|
},
|
|
{
|
|
"entropy": 5.774364948272705,
|
|
"epoch": 0.6417815674891146,
|
|
"grad_norm": 3.078125,
|
|
"learning_rate": 0.0004965753737004309,
|
|
"loss": 5.5628,
|
|
"mean_token_accuracy": 0.16613354682922363,
|
|
"num_tokens": 14705160.0,
|
|
"step": 7075
|
|
},
|
|
{
|
|
"entropy": 5.745255422592163,
|
|
"epoch": 0.6422351233671988,
|
|
"grad_norm": 3.6875,
|
|
"learning_rate": 0.0004965697475827231,
|
|
"loss": 5.6138,
|
|
"mean_token_accuracy": 0.1568262130022049,
|
|
"num_tokens": 14715487.0,
|
|
"step": 7080
|
|
},
|
|
{
|
|
"entropy": 5.786352157592773,
|
|
"epoch": 0.6426886792452831,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004965641168828965,
|
|
"loss": 5.6693,
|
|
"mean_token_accuracy": 0.15273340791463852,
|
|
"num_tokens": 14726987.0,
|
|
"step": 7085
|
|
},
|
|
{
|
|
"entropy": 5.734464120864868,
|
|
"epoch": 0.6431422351233672,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004965584816010676,
|
|
"loss": 5.6277,
|
|
"mean_token_accuracy": 0.16173090487718583,
|
|
"num_tokens": 14737810.0,
|
|
"step": 7090
|
|
},
|
|
{
|
|
"entropy": 5.791029024124145,
|
|
"epoch": 0.6435957910014514,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004965528417373528,
|
|
"loss": 5.6363,
|
|
"mean_token_accuracy": 0.1521812468767166,
|
|
"num_tokens": 14748997.0,
|
|
"step": 7095
|
|
},
|
|
{
|
|
"entropy": 5.811992931365967,
|
|
"epoch": 0.6440493468795355,
|
|
"grad_norm": 4.25,
|
|
"learning_rate": 0.0004965471972918688,
|
|
"loss": 5.6477,
|
|
"mean_token_accuracy": 0.1499110609292984,
|
|
"num_tokens": 14760439.0,
|
|
"step": 7100
|
|
},
|
|
{
|
|
"entropy": 5.744043684005737,
|
|
"epoch": 0.6445029027576198,
|
|
"grad_norm": 3.3125,
|
|
"learning_rate": 0.0004965415482647322,
|
|
"loss": 5.5695,
|
|
"mean_token_accuracy": 0.15322099328041078,
|
|
"num_tokens": 14770828.0,
|
|
"step": 7105
|
|
},
|
|
{
|
|
"entropy": 5.692976188659668,
|
|
"epoch": 0.6449564586357039,
|
|
"grad_norm": 3.40625,
|
|
"learning_rate": 0.00049653589465606,
|
|
"loss": 5.7056,
|
|
"mean_token_accuracy": 0.15300424844026567,
|
|
"num_tokens": 14781753.0,
|
|
"step": 7110
|
|
},
|
|
{
|
|
"entropy": 5.834149742126465,
|
|
"epoch": 0.6454100145137881,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.000496530236465969,
|
|
"loss": 5.7219,
|
|
"mean_token_accuracy": 0.14937618225812913,
|
|
"num_tokens": 14792241.0,
|
|
"step": 7115
|
|
},
|
|
{
|
|
"entropy": 5.750567626953125,
|
|
"epoch": 0.6458635703918723,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.0004965245736945763,
|
|
"loss": 5.5366,
|
|
"mean_token_accuracy": 0.15907809436321257,
|
|
"num_tokens": 14802580.0,
|
|
"step": 7120
|
|
},
|
|
{
|
|
"entropy": 5.771503925323486,
|
|
"epoch": 0.6463171262699564,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004965189063419989,
|
|
"loss": 5.7252,
|
|
"mean_token_accuracy": 0.15481867045164108,
|
|
"num_tokens": 14813103.0,
|
|
"step": 7125
|
|
},
|
|
{
|
|
"entropy": 5.722277021408081,
|
|
"epoch": 0.6467706821480407,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004965132344083541,
|
|
"loss": 5.6078,
|
|
"mean_token_accuracy": 0.15793556421995164,
|
|
"num_tokens": 14823334.0,
|
|
"step": 7130
|
|
},
|
|
{
|
|
"entropy": 5.79091854095459,
|
|
"epoch": 0.6472242380261248,
|
|
"grad_norm": 4.65625,
|
|
"learning_rate": 0.0004965075578937593,
|
|
"loss": 5.6483,
|
|
"mean_token_accuracy": 0.15331077128648757,
|
|
"num_tokens": 14834850.0,
|
|
"step": 7135
|
|
},
|
|
{
|
|
"entropy": 5.806456232070923,
|
|
"epoch": 0.647677793904209,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.0004965018767983316,
|
|
"loss": 5.6496,
|
|
"mean_token_accuracy": 0.15626297444105147,
|
|
"num_tokens": 14844276.0,
|
|
"step": 7140
|
|
},
|
|
{
|
|
"entropy": 5.720260286331177,
|
|
"epoch": 0.6481313497822931,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.0004964961911221886,
|
|
"loss": 5.5226,
|
|
"mean_token_accuracy": 0.16832068115472792,
|
|
"num_tokens": 14854352.0,
|
|
"step": 7145
|
|
},
|
|
{
|
|
"entropy": 5.799531936645508,
|
|
"epoch": 0.6485849056603774,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.000496490500865448,
|
|
"loss": 5.6711,
|
|
"mean_token_accuracy": 0.15777702629566193,
|
|
"num_tokens": 14864395.0,
|
|
"step": 7150
|
|
},
|
|
{
|
|
"entropy": 5.791047620773315,
|
|
"epoch": 0.6490384615384616,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004964848060282275,
|
|
"loss": 5.5851,
|
|
"mean_token_accuracy": 0.1580512434244156,
|
|
"num_tokens": 14874373.0,
|
|
"step": 7155
|
|
},
|
|
{
|
|
"entropy": 5.729786777496338,
|
|
"epoch": 0.6494920174165457,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004964791066106447,
|
|
"loss": 5.5609,
|
|
"mean_token_accuracy": 0.15438223034143447,
|
|
"num_tokens": 14884932.0,
|
|
"step": 7160
|
|
},
|
|
{
|
|
"entropy": 5.746135950088501,
|
|
"epoch": 0.6499455732946299,
|
|
"grad_norm": 4.21875,
|
|
"learning_rate": 0.0004964734026128175,
|
|
"loss": 5.7285,
|
|
"mean_token_accuracy": 0.1496640130877495,
|
|
"num_tokens": 14896254.0,
|
|
"step": 7165
|
|
},
|
|
{
|
|
"entropy": 5.825554847717285,
|
|
"epoch": 0.650399129172714,
|
|
"grad_norm": 2.953125,
|
|
"learning_rate": 0.0004964676940348638,
|
|
"loss": 5.6592,
|
|
"mean_token_accuracy": 0.151274374127388,
|
|
"num_tokens": 14907392.0,
|
|
"step": 7170
|
|
},
|
|
{
|
|
"entropy": 5.8277100086212155,
|
|
"epoch": 0.6508526850507983,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.000496461980876902,
|
|
"loss": 5.7629,
|
|
"mean_token_accuracy": 0.1563155859708786,
|
|
"num_tokens": 14917676.0,
|
|
"step": 7175
|
|
},
|
|
{
|
|
"entropy": 5.813205575942993,
|
|
"epoch": 0.6513062409288825,
|
|
"grad_norm": 2.9375,
|
|
"learning_rate": 0.0004964562631390498,
|
|
"loss": 5.6093,
|
|
"mean_token_accuracy": 0.15569815784692764,
|
|
"num_tokens": 14928500.0,
|
|
"step": 7180
|
|
},
|
|
{
|
|
"entropy": 5.776795959472656,
|
|
"epoch": 0.6517597968069666,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004964505408214257,
|
|
"loss": 5.5776,
|
|
"mean_token_accuracy": 0.1599561631679535,
|
|
"num_tokens": 14938970.0,
|
|
"step": 7185
|
|
},
|
|
{
|
|
"entropy": 5.759690141677856,
|
|
"epoch": 0.6522133526850508,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.000496444813924148,
|
|
"loss": 5.6413,
|
|
"mean_token_accuracy": 0.15742683559656143,
|
|
"num_tokens": 14949017.0,
|
|
"step": 7190
|
|
},
|
|
{
|
|
"entropy": 5.756869697570801,
|
|
"epoch": 0.652666908563135,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004964390824473351,
|
|
"loss": 5.5752,
|
|
"mean_token_accuracy": 0.16529665887355804,
|
|
"num_tokens": 14958529.0,
|
|
"step": 7195
|
|
},
|
|
{
|
|
"entropy": 5.754773473739624,
|
|
"epoch": 0.6531204644412192,
|
|
"grad_norm": 3.046875,
|
|
"learning_rate": 0.0004964333463911056,
|
|
"loss": 5.6542,
|
|
"mean_token_accuracy": 0.15476091653108598,
|
|
"num_tokens": 14968044.0,
|
|
"step": 7200
|
|
},
|
|
{
|
|
"entropy": 5.767954730987549,
|
|
"epoch": 0.6535740203193033,
|
|
"grad_norm": 4.59375,
|
|
"learning_rate": 0.0004964276057555779,
|
|
"loss": 5.6874,
|
|
"mean_token_accuracy": 0.1521929308772087,
|
|
"num_tokens": 14977867.0,
|
|
"step": 7205
|
|
},
|
|
{
|
|
"entropy": 5.851280736923218,
|
|
"epoch": 0.6540275761973875,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.000496421860540871,
|
|
"loss": 5.6771,
|
|
"mean_token_accuracy": 0.15839732587337493,
|
|
"num_tokens": 14986936.0,
|
|
"step": 7210
|
|
},
|
|
{
|
|
"entropy": 5.7605140686035154,
|
|
"epoch": 0.6544811320754716,
|
|
"grad_norm": 3.015625,
|
|
"learning_rate": 0.0004964161107471036,
|
|
"loss": 5.6302,
|
|
"mean_token_accuracy": 0.16003877222537993,
|
|
"num_tokens": 14996681.0,
|
|
"step": 7215
|
|
},
|
|
{
|
|
"entropy": 5.780618619918823,
|
|
"epoch": 0.6549346879535559,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004964103563743946,
|
|
"loss": 5.6416,
|
|
"mean_token_accuracy": 0.1552106834948063,
|
|
"num_tokens": 15007100.0,
|
|
"step": 7220
|
|
},
|
|
{
|
|
"entropy": 5.831463623046875,
|
|
"epoch": 0.6553882438316401,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.000496404597422863,
|
|
"loss": 5.7213,
|
|
"mean_token_accuracy": 0.15619465559720994,
|
|
"num_tokens": 15017452.0,
|
|
"step": 7225
|
|
},
|
|
{
|
|
"entropy": 5.757536935806274,
|
|
"epoch": 0.6558417997097242,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.000496398833892628,
|
|
"loss": 5.579,
|
|
"mean_token_accuracy": 0.15511720776557922,
|
|
"num_tokens": 15028362.0,
|
|
"step": 7230
|
|
},
|
|
{
|
|
"entropy": 5.809765815734863,
|
|
"epoch": 0.6562953555878084,
|
|
"grad_norm": 7.5,
|
|
"learning_rate": 0.0004963930657838086,
|
|
"loss": 5.663,
|
|
"mean_token_accuracy": 0.1546101078391075,
|
|
"num_tokens": 15038691.0,
|
|
"step": 7235
|
|
},
|
|
{
|
|
"entropy": 5.753928279876709,
|
|
"epoch": 0.6567489114658926,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004963872930965242,
|
|
"loss": 5.6387,
|
|
"mean_token_accuracy": 0.15518327057361603,
|
|
"num_tokens": 15050037.0,
|
|
"step": 7240
|
|
},
|
|
{
|
|
"entropy": 5.745072507858277,
|
|
"epoch": 0.6572024673439768,
|
|
"grad_norm": 4.625,
|
|
"learning_rate": 0.0004963815158308941,
|
|
"loss": 5.6003,
|
|
"mean_token_accuracy": 0.1518049106001854,
|
|
"num_tokens": 15059793.0,
|
|
"step": 7245
|
|
},
|
|
{
|
|
"entropy": 5.815020132064819,
|
|
"epoch": 0.657656023222061,
|
|
"grad_norm": 3.421875,
|
|
"learning_rate": 0.0004963757339870379,
|
|
"loss": 5.7025,
|
|
"mean_token_accuracy": 0.14955889880657197,
|
|
"num_tokens": 15070500.0,
|
|
"step": 7250
|
|
},
|
|
{
|
|
"entropy": 5.865824222564697,
|
|
"epoch": 0.6581095791001451,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.0004963699475650751,
|
|
"loss": 5.7522,
|
|
"mean_token_accuracy": 0.15184831321239473,
|
|
"num_tokens": 15081109.0,
|
|
"step": 7255
|
|
},
|
|
{
|
|
"entropy": 5.785812902450561,
|
|
"epoch": 0.6585631349782293,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004963641565651255,
|
|
"loss": 5.6338,
|
|
"mean_token_accuracy": 0.16198570430278778,
|
|
"num_tokens": 15092315.0,
|
|
"step": 7260
|
|
},
|
|
{
|
|
"entropy": 5.797928714752198,
|
|
"epoch": 0.6590166908563135,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004963583609873084,
|
|
"loss": 5.7092,
|
|
"mean_token_accuracy": 0.15403601601719857,
|
|
"num_tokens": 15103957.0,
|
|
"step": 7265
|
|
},
|
|
{
|
|
"entropy": 5.831661939620972,
|
|
"epoch": 0.6594702467343977,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004963525608317443,
|
|
"loss": 5.6641,
|
|
"mean_token_accuracy": 0.1534239813685417,
|
|
"num_tokens": 15114996.0,
|
|
"step": 7270
|
|
},
|
|
{
|
|
"entropy": 5.83020806312561,
|
|
"epoch": 0.6599238026124818,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004963467560985527,
|
|
"loss": 5.6124,
|
|
"mean_token_accuracy": 0.15501478910446168,
|
|
"num_tokens": 15125098.0,
|
|
"step": 7275
|
|
},
|
|
{
|
|
"entropy": 5.744346618652344,
|
|
"epoch": 0.660377358490566,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004963409467878538,
|
|
"loss": 5.606,
|
|
"mean_token_accuracy": 0.15144749432802201,
|
|
"num_tokens": 15134746.0,
|
|
"step": 7280
|
|
},
|
|
{
|
|
"entropy": 5.809712219238281,
|
|
"epoch": 0.6608309143686503,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.0004963351328997678,
|
|
"loss": 5.6385,
|
|
"mean_token_accuracy": 0.15188922137022018,
|
|
"num_tokens": 15145698.0,
|
|
"step": 7285
|
|
},
|
|
{
|
|
"entropy": 5.797967863082886,
|
|
"epoch": 0.6612844702467344,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004963293144344148,
|
|
"loss": 5.6861,
|
|
"mean_token_accuracy": 0.15129384547472,
|
|
"num_tokens": 15156026.0,
|
|
"step": 7290
|
|
},
|
|
{
|
|
"entropy": 5.770978927612305,
|
|
"epoch": 0.6617380261248186,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004963234913919151,
|
|
"loss": 5.6272,
|
|
"mean_token_accuracy": 0.15003437101840972,
|
|
"num_tokens": 15165900.0,
|
|
"step": 7295
|
|
},
|
|
{
|
|
"entropy": 5.750339603424072,
|
|
"epoch": 0.6621915820029027,
|
|
"grad_norm": 5.25,
|
|
"learning_rate": 0.0004963176637723893,
|
|
"loss": 5.7027,
|
|
"mean_token_accuracy": 0.15393707156181335,
|
|
"num_tokens": 15176693.0,
|
|
"step": 7300
|
|
},
|
|
{
|
|
"entropy": 5.836119508743286,
|
|
"epoch": 0.6626451378809869,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004963118315759578,
|
|
"loss": 5.7345,
|
|
"mean_token_accuracy": 0.14329422190785407,
|
|
"num_tokens": 15186535.0,
|
|
"step": 7305
|
|
},
|
|
{
|
|
"entropy": 5.836709785461426,
|
|
"epoch": 0.6630986937590712,
|
|
"grad_norm": 3.0625,
|
|
"learning_rate": 0.0004963059948027411,
|
|
"loss": 5.6336,
|
|
"mean_token_accuracy": 0.15115350857377052,
|
|
"num_tokens": 15196019.0,
|
|
"step": 7310
|
|
},
|
|
{
|
|
"entropy": 5.738832950592041,
|
|
"epoch": 0.6635522496371553,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004963001534528601,
|
|
"loss": 5.4937,
|
|
"mean_token_accuracy": 0.16718341410160065,
|
|
"num_tokens": 15205273.0,
|
|
"step": 7315
|
|
},
|
|
{
|
|
"entropy": 5.790439748764038,
|
|
"epoch": 0.6640058055152395,
|
|
"grad_norm": 3.765625,
|
|
"learning_rate": 0.0004962943075264355,
|
|
"loss": 5.6465,
|
|
"mean_token_accuracy": 0.1561621308326721,
|
|
"num_tokens": 15216716.0,
|
|
"step": 7320
|
|
},
|
|
{
|
|
"entropy": 5.835460090637207,
|
|
"epoch": 0.6644593613933236,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.0004962884570235884,
|
|
"loss": 5.6903,
|
|
"mean_token_accuracy": 0.15185065120458602,
|
|
"num_tokens": 15227306.0,
|
|
"step": 7325
|
|
},
|
|
{
|
|
"entropy": 5.701790475845337,
|
|
"epoch": 0.6649129172714079,
|
|
"grad_norm": 3.0,
|
|
"learning_rate": 0.0004962826019444394,
|
|
"loss": 5.5503,
|
|
"mean_token_accuracy": 0.1638151526451111,
|
|
"num_tokens": 15237302.0,
|
|
"step": 7330
|
|
},
|
|
{
|
|
"entropy": 5.720064258575439,
|
|
"epoch": 0.665366473149492,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.0004962767422891099,
|
|
"loss": 5.6099,
|
|
"mean_token_accuracy": 0.15619055330753326,
|
|
"num_tokens": 15247064.0,
|
|
"step": 7335
|
|
},
|
|
{
|
|
"entropy": 5.794697284698486,
|
|
"epoch": 0.6658200290275762,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.000496270878057721,
|
|
"loss": 5.6748,
|
|
"mean_token_accuracy": 0.15739299803972245,
|
|
"num_tokens": 15257006.0,
|
|
"step": 7340
|
|
},
|
|
{
|
|
"entropy": 5.824474954605103,
|
|
"epoch": 0.6662735849056604,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004962650092503939,
|
|
"loss": 5.6343,
|
|
"mean_token_accuracy": 0.16214921474456787,
|
|
"num_tokens": 15266720.0,
|
|
"step": 7345
|
|
},
|
|
{
|
|
"entropy": 5.731961631774903,
|
|
"epoch": 0.6667271407837445,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004962591358672502,
|
|
"loss": 5.6749,
|
|
"mean_token_accuracy": 0.15213515236973763,
|
|
"num_tokens": 15277330.0,
|
|
"step": 7350
|
|
},
|
|
{
|
|
"entropy": 5.809416246414185,
|
|
"epoch": 0.6671806966618288,
|
|
"grad_norm": 3.234375,
|
|
"learning_rate": 0.000496253257908411,
|
|
"loss": 5.6045,
|
|
"mean_token_accuracy": 0.15907943099737168,
|
|
"num_tokens": 15287401.0,
|
|
"step": 7355
|
|
},
|
|
{
|
|
"entropy": 5.687846374511719,
|
|
"epoch": 0.6676342525399129,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004962473753739981,
|
|
"loss": 5.5649,
|
|
"mean_token_accuracy": 0.1594688728451729,
|
|
"num_tokens": 15297426.0,
|
|
"step": 7360
|
|
},
|
|
{
|
|
"entropy": 5.793103313446045,
|
|
"epoch": 0.6680878084179971,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.000496241488264133,
|
|
"loss": 5.5589,
|
|
"mean_token_accuracy": 0.15536411553621293,
|
|
"num_tokens": 15308412.0,
|
|
"step": 7365
|
|
},
|
|
{
|
|
"entropy": 5.794301748275757,
|
|
"epoch": 0.6685413642960812,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004962355965789377,
|
|
"loss": 5.5857,
|
|
"mean_token_accuracy": 0.15055083632469177,
|
|
"num_tokens": 15318821.0,
|
|
"step": 7370
|
|
},
|
|
{
|
|
"entropy": 5.731050777435303,
|
|
"epoch": 0.6689949201741655,
|
|
"grad_norm": 3.84375,
|
|
"learning_rate": 0.0004962297003185338,
|
|
"loss": 5.6394,
|
|
"mean_token_accuracy": 0.15725694745779037,
|
|
"num_tokens": 15328737.0,
|
|
"step": 7375
|
|
},
|
|
{
|
|
"entropy": 5.831857347488404,
|
|
"epoch": 0.6694484760522497,
|
|
"grad_norm": 3.0625,
|
|
"learning_rate": 0.0004962237994830433,
|
|
"loss": 5.7373,
|
|
"mean_token_accuracy": 0.1487860843539238,
|
|
"num_tokens": 15339695.0,
|
|
"step": 7380
|
|
},
|
|
{
|
|
"entropy": 5.857686281204224,
|
|
"epoch": 0.6699020319303338,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004962178940725883,
|
|
"loss": 5.6736,
|
|
"mean_token_accuracy": 0.15191865265369414,
|
|
"num_tokens": 15350270.0,
|
|
"step": 7385
|
|
},
|
|
{
|
|
"entropy": 5.78417935371399,
|
|
"epoch": 0.670355587808418,
|
|
"grad_norm": 3.09375,
|
|
"learning_rate": 0.0004962119840872908,
|
|
"loss": 5.6725,
|
|
"mean_token_accuracy": 0.1553597405552864,
|
|
"num_tokens": 15360986.0,
|
|
"step": 7390
|
|
},
|
|
{
|
|
"entropy": 5.780443906784058,
|
|
"epoch": 0.6708091436865021,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004962060695272733,
|
|
"loss": 5.6863,
|
|
"mean_token_accuracy": 0.15490424484014512,
|
|
"num_tokens": 15371786.0,
|
|
"step": 7395
|
|
},
|
|
{
|
|
"entropy": 5.773851728439331,
|
|
"epoch": 0.6712626995645864,
|
|
"grad_norm": 4.1875,
|
|
"learning_rate": 0.0004962001503926577,
|
|
"loss": 5.6349,
|
|
"mean_token_accuracy": 0.15896140784025192,
|
|
"num_tokens": 15382960.0,
|
|
"step": 7400
|
|
},
|
|
{
|
|
"entropy": 5.738351774215698,
|
|
"epoch": 0.6717162554426706,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004961942266835667,
|
|
"loss": 5.6209,
|
|
"mean_token_accuracy": 0.1595415860414505,
|
|
"num_tokens": 15392807.0,
|
|
"step": 7405
|
|
},
|
|
{
|
|
"entropy": 5.794447135925293,
|
|
"epoch": 0.6721698113207547,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004961882984001227,
|
|
"loss": 5.6749,
|
|
"mean_token_accuracy": 0.15016180127859116,
|
|
"num_tokens": 15403712.0,
|
|
"step": 7410
|
|
},
|
|
{
|
|
"entropy": 5.822537660598755,
|
|
"epoch": 0.6726233671988389,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004961823655424484,
|
|
"loss": 5.7309,
|
|
"mean_token_accuracy": 0.14892438873648645,
|
|
"num_tokens": 15414839.0,
|
|
"step": 7415
|
|
},
|
|
{
|
|
"entropy": 5.800685882568359,
|
|
"epoch": 0.6730769230769231,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004961764281106664,
|
|
"loss": 5.6032,
|
|
"mean_token_accuracy": 0.16113678514957427,
|
|
"num_tokens": 15425320.0,
|
|
"step": 7420
|
|
},
|
|
{
|
|
"entropy": 5.759464979171753,
|
|
"epoch": 0.6735304789550073,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004961704861048995,
|
|
"loss": 5.6071,
|
|
"mean_token_accuracy": 0.15447303056716918,
|
|
"num_tokens": 15435476.0,
|
|
"step": 7425
|
|
},
|
|
{
|
|
"entropy": 5.791233015060425,
|
|
"epoch": 0.6739840348330914,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004961645395252705,
|
|
"loss": 5.6996,
|
|
"mean_token_accuracy": 0.15540242716670036,
|
|
"num_tokens": 15445786.0,
|
|
"step": 7430
|
|
},
|
|
{
|
|
"entropy": 5.772368955612182,
|
|
"epoch": 0.6744375907111756,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004961585883719025,
|
|
"loss": 5.7077,
|
|
"mean_token_accuracy": 0.15462125688791276,
|
|
"num_tokens": 15455915.0,
|
|
"step": 7435
|
|
},
|
|
{
|
|
"entropy": 5.828447437286377,
|
|
"epoch": 0.6748911465892597,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004961526326449186,
|
|
"loss": 5.675,
|
|
"mean_token_accuracy": 0.15044990181922913,
|
|
"num_tokens": 15466523.0,
|
|
"step": 7440
|
|
},
|
|
{
|
|
"entropy": 5.856289434432983,
|
|
"epoch": 0.675344702467344,
|
|
"grad_norm": 3.46875,
|
|
"learning_rate": 0.0004961466723444419,
|
|
"loss": 5.6557,
|
|
"mean_token_accuracy": 0.15675067156553268,
|
|
"num_tokens": 15476821.0,
|
|
"step": 7445
|
|
},
|
|
{
|
|
"entropy": 5.733017301559448,
|
|
"epoch": 0.6757982583454282,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004961407074705955,
|
|
"loss": 5.6031,
|
|
"mean_token_accuracy": 0.15133341252803803,
|
|
"num_tokens": 15487182.0,
|
|
"step": 7450
|
|
},
|
|
{
|
|
"entropy": 5.766598081588745,
|
|
"epoch": 0.6762518142235123,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004961347380235031,
|
|
"loss": 5.584,
|
|
"mean_token_accuracy": 0.15954807996749878,
|
|
"num_tokens": 15497600.0,
|
|
"step": 7455
|
|
},
|
|
{
|
|
"entropy": 5.799952602386474,
|
|
"epoch": 0.6767053701015965,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004961287640032879,
|
|
"loss": 5.7363,
|
|
"mean_token_accuracy": 0.14449917227029802,
|
|
"num_tokens": 15508278.0,
|
|
"step": 7460
|
|
},
|
|
{
|
|
"entropy": 5.854372262954712,
|
|
"epoch": 0.6771589259796807,
|
|
"grad_norm": 3.84375,
|
|
"learning_rate": 0.0004961227854100734,
|
|
"loss": 5.744,
|
|
"mean_token_accuracy": 0.15246044844388962,
|
|
"num_tokens": 15518458.0,
|
|
"step": 7465
|
|
},
|
|
{
|
|
"entropy": 5.7955224990844725,
|
|
"epoch": 0.6776124818577649,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004961168022439835,
|
|
"loss": 5.5636,
|
|
"mean_token_accuracy": 0.1587345838546753,
|
|
"num_tokens": 15528738.0,
|
|
"step": 7470
|
|
},
|
|
{
|
|
"entropy": 5.739163064956665,
|
|
"epoch": 0.6780660377358491,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004961108145051417,
|
|
"loss": 5.6104,
|
|
"mean_token_accuracy": 0.16207170635461807,
|
|
"num_tokens": 15538656.0,
|
|
"step": 7475
|
|
},
|
|
{
|
|
"entropy": 5.684577178955078,
|
|
"epoch": 0.6785195936139332,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.000496104822193672,
|
|
"loss": 5.6305,
|
|
"mean_token_accuracy": 0.15659867376089096,
|
|
"num_tokens": 15549285.0,
|
|
"step": 7480
|
|
},
|
|
{
|
|
"entropy": 5.828121995925903,
|
|
"epoch": 0.6789731494920174,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004960988253096982,
|
|
"loss": 5.6925,
|
|
"mean_token_accuracy": 0.16133199483156205,
|
|
"num_tokens": 15559766.0,
|
|
"step": 7485
|
|
},
|
|
{
|
|
"entropy": 5.793510580062867,
|
|
"epoch": 0.6794267053701016,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004960928238533443,
|
|
"loss": 5.5625,
|
|
"mean_token_accuracy": 0.16435614079236985,
|
|
"num_tokens": 15570873.0,
|
|
"step": 7490
|
|
},
|
|
{
|
|
"entropy": 5.804307985305786,
|
|
"epoch": 0.6798802612481858,
|
|
"grad_norm": 3.015625,
|
|
"learning_rate": 0.0004960868178247344,
|
|
"loss": 5.8058,
|
|
"mean_token_accuracy": 0.15049900710582734,
|
|
"num_tokens": 15581229.0,
|
|
"step": 7495
|
|
},
|
|
{
|
|
"entropy": 5.682524824142456,
|
|
"epoch": 0.68033381712627,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004960808072239929,
|
|
"loss": 5.6645,
|
|
"mean_token_accuracy": 0.150663161277771,
|
|
"num_tokens": 15591686.0,
|
|
"step": 7500
|
|
},
|
|
{
|
|
"entropy": 5.781607913970947,
|
|
"epoch": 0.6807873730043541,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004960747920512439,
|
|
"loss": 5.6798,
|
|
"mean_token_accuracy": 0.15253570526838303,
|
|
"num_tokens": 15601869.0,
|
|
"step": 7505
|
|
},
|
|
{
|
|
"entropy": 5.774205732345581,
|
|
"epoch": 0.6812409288824384,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.000496068772306612,
|
|
"loss": 5.6678,
|
|
"mean_token_accuracy": 0.1541148066520691,
|
|
"num_tokens": 15612946.0,
|
|
"step": 7510
|
|
},
|
|
{
|
|
"entropy": 5.832863903045654,
|
|
"epoch": 0.6816944847605225,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004960627479902214,
|
|
"loss": 5.7158,
|
|
"mean_token_accuracy": 0.14823995307087898,
|
|
"num_tokens": 15623761.0,
|
|
"step": 7515
|
|
},
|
|
{
|
|
"entropy": 5.809633827209472,
|
|
"epoch": 0.6821480406386067,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.000496056719102197,
|
|
"loss": 5.6913,
|
|
"mean_token_accuracy": 0.14876921027898787,
|
|
"num_tokens": 15634500.0,
|
|
"step": 7520
|
|
},
|
|
{
|
|
"entropy": 5.738462495803833,
|
|
"epoch": 0.6826015965166908,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004960506856426631,
|
|
"loss": 5.576,
|
|
"mean_token_accuracy": 0.15111364424228668,
|
|
"num_tokens": 15644896.0,
|
|
"step": 7525
|
|
},
|
|
{
|
|
"entropy": 5.787351369857788,
|
|
"epoch": 0.683055152394775,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004960446476117448,
|
|
"loss": 5.6822,
|
|
"mean_token_accuracy": 0.16053580194711686,
|
|
"num_tokens": 15655008.0,
|
|
"step": 7530
|
|
},
|
|
{
|
|
"entropy": 5.746401119232178,
|
|
"epoch": 0.6835087082728593,
|
|
"grad_norm": 4.46875,
|
|
"learning_rate": 0.0004960386050095668,
|
|
"loss": 5.6004,
|
|
"mean_token_accuracy": 0.14865829050540924,
|
|
"num_tokens": 15665944.0,
|
|
"step": 7535
|
|
},
|
|
{
|
|
"entropy": 5.801738309860229,
|
|
"epoch": 0.6839622641509434,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004960325578362543,
|
|
"loss": 5.6797,
|
|
"mean_token_accuracy": 0.15832635313272475,
|
|
"num_tokens": 15677099.0,
|
|
"step": 7540
|
|
},
|
|
{
|
|
"entropy": 5.798512172698975,
|
|
"epoch": 0.6844158200290276,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.000496026506091932,
|
|
"loss": 5.6344,
|
|
"mean_token_accuracy": 0.15838538110256195,
|
|
"num_tokens": 15687531.0,
|
|
"step": 7545
|
|
},
|
|
{
|
|
"entropy": 5.790757894515991,
|
|
"epoch": 0.6848693759071117,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004960204497767253,
|
|
"loss": 5.6583,
|
|
"mean_token_accuracy": 0.1546577602624893,
|
|
"num_tokens": 15697002.0,
|
|
"step": 7550
|
|
},
|
|
{
|
|
"entropy": 5.724558973312378,
|
|
"epoch": 0.685322931785196,
|
|
"grad_norm": 4.28125,
|
|
"learning_rate": 0.0004960143888907594,
|
|
"loss": 5.5426,
|
|
"mean_token_accuracy": 0.15625495165586473,
|
|
"num_tokens": 15707249.0,
|
|
"step": 7555
|
|
},
|
|
{
|
|
"entropy": 5.743619441986084,
|
|
"epoch": 0.6857764876632801,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004960083234341595,
|
|
"loss": 5.6223,
|
|
"mean_token_accuracy": 0.15563429296016693,
|
|
"num_tokens": 15718764.0,
|
|
"step": 7560
|
|
},
|
|
{
|
|
"entropy": 5.727084493637085,
|
|
"epoch": 0.6862300435413643,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004960022534070513,
|
|
"loss": 5.5709,
|
|
"mean_token_accuracy": 0.16300940364599228,
|
|
"num_tokens": 15728854.0,
|
|
"step": 7565
|
|
},
|
|
{
|
|
"entropy": 5.648557186126709,
|
|
"epoch": 0.6866835994194485,
|
|
"grad_norm": 4.34375,
|
|
"learning_rate": 0.00049599617880956,
|
|
"loss": 5.5759,
|
|
"mean_token_accuracy": 0.1575843796133995,
|
|
"num_tokens": 15739682.0,
|
|
"step": 7570
|
|
},
|
|
{
|
|
"entropy": 5.703317785263062,
|
|
"epoch": 0.6871371552975326,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004959900996418115,
|
|
"loss": 5.5863,
|
|
"mean_token_accuracy": 0.16021239310503005,
|
|
"num_tokens": 15749628.0,
|
|
"step": 7575
|
|
},
|
|
{
|
|
"entropy": 5.804837465286255,
|
|
"epoch": 0.6875907111756169,
|
|
"grad_norm": 3.359375,
|
|
"learning_rate": 0.0004959840159039315,
|
|
"loss": 5.6567,
|
|
"mean_token_accuracy": 0.1535927399992943,
|
|
"num_tokens": 15760137.0,
|
|
"step": 7580
|
|
},
|
|
{
|
|
"entropy": 5.777477645874024,
|
|
"epoch": 0.688044267053701,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004959779275960456,
|
|
"loss": 5.6112,
|
|
"mean_token_accuracy": 0.1556934803724289,
|
|
"num_tokens": 15769889.0,
|
|
"step": 7585
|
|
},
|
|
{
|
|
"entropy": 5.738125896453857,
|
|
"epoch": 0.6884978229317852,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.00049597183471828,
|
|
"loss": 5.7256,
|
|
"mean_token_accuracy": 0.15178040713071822,
|
|
"num_tokens": 15780912.0,
|
|
"step": 7590
|
|
},
|
|
{
|
|
"entropy": 5.850151681900025,
|
|
"epoch": 0.6889513788098693,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004959657372707604,
|
|
"loss": 5.5925,
|
|
"mean_token_accuracy": 0.16462052166461943,
|
|
"num_tokens": 15791719.0,
|
|
"step": 7595
|
|
},
|
|
{
|
|
"entropy": 5.8561851501464846,
|
|
"epoch": 0.6894049346879536,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004959596352536132,
|
|
"loss": 5.6261,
|
|
"mean_token_accuracy": 0.15682563334703445,
|
|
"num_tokens": 15802551.0,
|
|
"step": 7600
|
|
},
|
|
{
|
|
"entropy": 5.782931661605835,
|
|
"epoch": 0.6898584905660378,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004959535286669643,
|
|
"loss": 5.6941,
|
|
"mean_token_accuracy": 0.15105319619178773,
|
|
"num_tokens": 15813551.0,
|
|
"step": 7605
|
|
},
|
|
{
|
|
"entropy": 5.715517950057984,
|
|
"epoch": 0.6903120464441219,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.0004959474175109402,
|
|
"loss": 5.6681,
|
|
"mean_token_accuracy": 0.15595430433750151,
|
|
"num_tokens": 15824262.0,
|
|
"step": 7610
|
|
},
|
|
{
|
|
"entropy": 5.818006896972657,
|
|
"epoch": 0.6907656023222061,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004959413017856672,
|
|
"loss": 5.7191,
|
|
"mean_token_accuracy": 0.15502288639545442,
|
|
"num_tokens": 15835493.0,
|
|
"step": 7615
|
|
},
|
|
{
|
|
"entropy": 5.697161531448364,
|
|
"epoch": 0.6912191582002902,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004959351814912716,
|
|
"loss": 5.5857,
|
|
"mean_token_accuracy": 0.15691763609647752,
|
|
"num_tokens": 15846224.0,
|
|
"step": 7620
|
|
},
|
|
{
|
|
"entropy": 5.754197263717652,
|
|
"epoch": 0.6916727140783745,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004959290566278803,
|
|
"loss": 5.6271,
|
|
"mean_token_accuracy": 0.15909348279237748,
|
|
"num_tokens": 15855622.0,
|
|
"step": 7625
|
|
},
|
|
{
|
|
"entropy": 5.813883924484253,
|
|
"epoch": 0.6921262699564587,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004959229271956199,
|
|
"loss": 5.6805,
|
|
"mean_token_accuracy": 0.15607887357473374,
|
|
"num_tokens": 15865835.0,
|
|
"step": 7630
|
|
},
|
|
{
|
|
"entropy": 5.830732297897339,
|
|
"epoch": 0.6925798258345428,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004959167931946169,
|
|
"loss": 5.6201,
|
|
"mean_token_accuracy": 0.15640912801027299,
|
|
"num_tokens": 15875915.0,
|
|
"step": 7635
|
|
},
|
|
{
|
|
"entropy": 5.825406503677368,
|
|
"epoch": 0.693033381712627,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004959106546249984,
|
|
"loss": 5.6337,
|
|
"mean_token_accuracy": 0.15450009256601333,
|
|
"num_tokens": 15887111.0,
|
|
"step": 7640
|
|
},
|
|
{
|
|
"entropy": 5.8027575492858885,
|
|
"epoch": 0.6934869375907112,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004959045114868913,
|
|
"loss": 5.7488,
|
|
"mean_token_accuracy": 0.14544340074062348,
|
|
"num_tokens": 15899528.0,
|
|
"step": 7645
|
|
},
|
|
{
|
|
"entropy": 5.752656936645508,
|
|
"epoch": 0.6939404934687954,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004958983637804225,
|
|
"loss": 5.6388,
|
|
"mean_token_accuracy": 0.16282033026218415,
|
|
"num_tokens": 15910881.0,
|
|
"step": 7650
|
|
},
|
|
{
|
|
"entropy": 5.816255569458008,
|
|
"epoch": 0.6943940493468795,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004958922115057194,
|
|
"loss": 5.6955,
|
|
"mean_token_accuracy": 0.15611306130886077,
|
|
"num_tokens": 15921189.0,
|
|
"step": 7655
|
|
},
|
|
{
|
|
"entropy": 5.8625730037689205,
|
|
"epoch": 0.6948476052249637,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004958860546629089,
|
|
"loss": 5.6923,
|
|
"mean_token_accuracy": 0.15917486399412156,
|
|
"num_tokens": 15931276.0,
|
|
"step": 7660
|
|
},
|
|
{
|
|
"entropy": 5.844645547866821,
|
|
"epoch": 0.6953011611030478,
|
|
"grad_norm": 3.328125,
|
|
"learning_rate": 0.0004958798932521186,
|
|
"loss": 5.7599,
|
|
"mean_token_accuracy": 0.1465900495648384,
|
|
"num_tokens": 15941506.0,
|
|
"step": 7665
|
|
},
|
|
{
|
|
"entropy": 5.710515451431275,
|
|
"epoch": 0.6957547169811321,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004958737272734759,
|
|
"loss": 5.5973,
|
|
"mean_token_accuracy": 0.1594126984477043,
|
|
"num_tokens": 15951158.0,
|
|
"step": 7670
|
|
},
|
|
{
|
|
"entropy": 5.798179674148559,
|
|
"epoch": 0.6962082728592163,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004958675567271081,
|
|
"loss": 5.6198,
|
|
"mean_token_accuracy": 0.16269323378801345,
|
|
"num_tokens": 15960852.0,
|
|
"step": 7675
|
|
},
|
|
{
|
|
"entropy": 5.81680121421814,
|
|
"epoch": 0.6966618287373004,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.000495861381613143,
|
|
"loss": 5.6278,
|
|
"mean_token_accuracy": 0.1538613721728325,
|
|
"num_tokens": 15971291.0,
|
|
"step": 7680
|
|
},
|
|
{
|
|
"entropy": 5.788067293167114,
|
|
"epoch": 0.6971153846153846,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004958552019317082,
|
|
"loss": 5.6985,
|
|
"mean_token_accuracy": 0.15725067257881165,
|
|
"num_tokens": 15982180.0,
|
|
"step": 7685
|
|
},
|
|
{
|
|
"entropy": 5.736803913116455,
|
|
"epoch": 0.6975689404934688,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.0004958490176829316,
|
|
"loss": 5.5857,
|
|
"mean_token_accuracy": 0.15838269367814065,
|
|
"num_tokens": 15992363.0,
|
|
"step": 7690
|
|
},
|
|
{
|
|
"entropy": 5.7980883598327635,
|
|
"epoch": 0.698022496371553,
|
|
"grad_norm": 10.5625,
|
|
"learning_rate": 0.000495842828866941,
|
|
"loss": 5.6489,
|
|
"mean_token_accuracy": 0.15137666910886766,
|
|
"num_tokens": 16003477.0,
|
|
"step": 7695
|
|
},
|
|
{
|
|
"entropy": 5.805958795547485,
|
|
"epoch": 0.6984760522496372,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.0004958366354838645,
|
|
"loss": 5.6463,
|
|
"mean_token_accuracy": 0.15117594450712205,
|
|
"num_tokens": 16013747.0,
|
|
"step": 7700
|
|
},
|
|
{
|
|
"entropy": 5.774502849578857,
|
|
"epoch": 0.6989296081277213,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.00049583043753383,
|
|
"loss": 5.6676,
|
|
"mean_token_accuracy": 0.1588193356990814,
|
|
"num_tokens": 16025662.0,
|
|
"step": 7705
|
|
},
|
|
{
|
|
"entropy": 5.7774632453918455,
|
|
"epoch": 0.6993831640058055,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004958242350169658,
|
|
"loss": 5.7169,
|
|
"mean_token_accuracy": 0.1599838688969612,
|
|
"num_tokens": 16037315.0,
|
|
"step": 7710
|
|
},
|
|
{
|
|
"entropy": 5.695142984390259,
|
|
"epoch": 0.6998367198838897,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004958180279334001,
|
|
"loss": 5.5541,
|
|
"mean_token_accuracy": 0.15912531763315202,
|
|
"num_tokens": 16047297.0,
|
|
"step": 7715
|
|
},
|
|
{
|
|
"entropy": 5.766730165481567,
|
|
"epoch": 0.7002902757619739,
|
|
"grad_norm": 5.4375,
|
|
"learning_rate": 0.0004958118162832614,
|
|
"loss": 5.5364,
|
|
"mean_token_accuracy": 0.1601413071155548,
|
|
"num_tokens": 16057573.0,
|
|
"step": 7720
|
|
},
|
|
{
|
|
"entropy": 5.7812422752380375,
|
|
"epoch": 0.700743831640058,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004958056000666781,
|
|
"loss": 5.6859,
|
|
"mean_token_accuracy": 0.15329635739326478,
|
|
"num_tokens": 16067926.0,
|
|
"step": 7725
|
|
},
|
|
{
|
|
"entropy": 5.773109102249146,
|
|
"epoch": 0.7011973875181422,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004957993792837786,
|
|
"loss": 5.626,
|
|
"mean_token_accuracy": 0.1544777363538742,
|
|
"num_tokens": 16077938.0,
|
|
"step": 7730
|
|
},
|
|
{
|
|
"entropy": 5.742027997970581,
|
|
"epoch": 0.7016509433962265,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004957931539346917,
|
|
"loss": 5.5164,
|
|
"mean_token_accuracy": 0.15980168730020522,
|
|
"num_tokens": 16088163.0,
|
|
"step": 7735
|
|
},
|
|
{
|
|
"entropy": 5.800528526306152,
|
|
"epoch": 0.7021044992743106,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004957869240195462,
|
|
"loss": 5.7459,
|
|
"mean_token_accuracy": 0.1448234349489212,
|
|
"num_tokens": 16100640.0,
|
|
"step": 7740
|
|
},
|
|
{
|
|
"entropy": 5.73759388923645,
|
|
"epoch": 0.7025580551523948,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004957806895384707,
|
|
"loss": 5.5875,
|
|
"mean_token_accuracy": 0.15452245771884918,
|
|
"num_tokens": 16111018.0,
|
|
"step": 7745
|
|
},
|
|
{
|
|
"entropy": 5.731401681900024,
|
|
"epoch": 0.7030116110304789,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004957744504915944,
|
|
"loss": 5.5878,
|
|
"mean_token_accuracy": 0.15764452815055846,
|
|
"num_tokens": 16120873.0,
|
|
"step": 7750
|
|
},
|
|
{
|
|
"entropy": 5.75859522819519,
|
|
"epoch": 0.7034651669085631,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004957682068790463,
|
|
"loss": 5.6298,
|
|
"mean_token_accuracy": 0.15953876823186874,
|
|
"num_tokens": 16131178.0,
|
|
"step": 7755
|
|
},
|
|
{
|
|
"entropy": 5.724505662918091,
|
|
"epoch": 0.7039187227866474,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004957619587009553,
|
|
"loss": 5.6187,
|
|
"mean_token_accuracy": 0.15462536960840226,
|
|
"num_tokens": 16141156.0,
|
|
"step": 7760
|
|
},
|
|
{
|
|
"entropy": 5.779624652862549,
|
|
"epoch": 0.7043722786647315,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004957557059574507,
|
|
"loss": 5.7157,
|
|
"mean_token_accuracy": 0.1444093957543373,
|
|
"num_tokens": 16150077.0,
|
|
"step": 7765
|
|
},
|
|
{
|
|
"entropy": 5.778850507736206,
|
|
"epoch": 0.7048258345428157,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004957494486486618,
|
|
"loss": 5.6362,
|
|
"mean_token_accuracy": 0.1569339767098427,
|
|
"num_tokens": 16160514.0,
|
|
"step": 7770
|
|
},
|
|
{
|
|
"entropy": 5.798329210281372,
|
|
"epoch": 0.7052793904208998,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004957431867747182,
|
|
"loss": 5.668,
|
|
"mean_token_accuracy": 0.16042965203523635,
|
|
"num_tokens": 16170811.0,
|
|
"step": 7775
|
|
},
|
|
{
|
|
"entropy": 5.755690336227417,
|
|
"epoch": 0.7057329462989841,
|
|
"grad_norm": 2.890625,
|
|
"learning_rate": 0.0004957369203357492,
|
|
"loss": 5.5824,
|
|
"mean_token_accuracy": 0.15862363576889038,
|
|
"num_tokens": 16181553.0,
|
|
"step": 7780
|
|
},
|
|
{
|
|
"entropy": 5.736315679550171,
|
|
"epoch": 0.7061865021770682,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.0004957306493318844,
|
|
"loss": 5.6339,
|
|
"mean_token_accuracy": 0.16354555636644363,
|
|
"num_tokens": 16191308.0,
|
|
"step": 7785
|
|
},
|
|
{
|
|
"entropy": 5.707941198348999,
|
|
"epoch": 0.7066400580551524,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.0004957243737632535,
|
|
"loss": 5.5795,
|
|
"mean_token_accuracy": 0.1632107749581337,
|
|
"num_tokens": 16201311.0,
|
|
"step": 7790
|
|
},
|
|
{
|
|
"entropy": 5.817873144149781,
|
|
"epoch": 0.7070936139332366,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004957180936299863,
|
|
"loss": 5.6108,
|
|
"mean_token_accuracy": 0.1581616669893265,
|
|
"num_tokens": 16211105.0,
|
|
"step": 7795
|
|
},
|
|
{
|
|
"entropy": 5.818648386001587,
|
|
"epoch": 0.7075471698113207,
|
|
"grad_norm": 3.375,
|
|
"learning_rate": 0.0004957118089322127,
|
|
"loss": 5.6237,
|
|
"mean_token_accuracy": 0.15291189551353454,
|
|
"num_tokens": 16220836.0,
|
|
"step": 7800
|
|
},
|
|
{
|
|
"entropy": 5.740155744552612,
|
|
"epoch": 0.708000725689405,
|
|
"grad_norm": 3.765625,
|
|
"learning_rate": 0.0004957055196700628,
|
|
"loss": 5.5702,
|
|
"mean_token_accuracy": 0.16200145781040193,
|
|
"num_tokens": 16231630.0,
|
|
"step": 7805
|
|
},
|
|
{
|
|
"entropy": 5.792011737823486,
|
|
"epoch": 0.7084542815674891,
|
|
"grad_norm": 3.421875,
|
|
"learning_rate": 0.0004956992258436663,
|
|
"loss": 5.6402,
|
|
"mean_token_accuracy": 0.1585893839597702,
|
|
"num_tokens": 16242272.0,
|
|
"step": 7810
|
|
},
|
|
{
|
|
"entropy": 5.714456701278687,
|
|
"epoch": 0.7089078374455733,
|
|
"grad_norm": 3.875,
|
|
"learning_rate": 0.0004956929274531536,
|
|
"loss": 5.5431,
|
|
"mean_token_accuracy": 0.15601417273283005,
|
|
"num_tokens": 16252555.0,
|
|
"step": 7815
|
|
},
|
|
{
|
|
"entropy": 5.744070816040039,
|
|
"epoch": 0.7093613933236574,
|
|
"grad_norm": 3.1875,
|
|
"learning_rate": 0.000495686624498655,
|
|
"loss": 5.6631,
|
|
"mean_token_accuracy": 0.16189786046743393,
|
|
"num_tokens": 16261964.0,
|
|
"step": 7820
|
|
},
|
|
{
|
|
"entropy": 5.846288108825684,
|
|
"epoch": 0.7098149492017417,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004956803169803007,
|
|
"loss": 5.728,
|
|
"mean_token_accuracy": 0.14986019879579543,
|
|
"num_tokens": 16274543.0,
|
|
"step": 7825
|
|
},
|
|
{
|
|
"entropy": 5.80157732963562,
|
|
"epoch": 0.7102685050798259,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004956740048982212,
|
|
"loss": 5.6358,
|
|
"mean_token_accuracy": 0.14794817417860032,
|
|
"num_tokens": 16285124.0,
|
|
"step": 7830
|
|
},
|
|
{
|
|
"entropy": 5.753595542907715,
|
|
"epoch": 0.71072206095791,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004956676882525472,
|
|
"loss": 5.697,
|
|
"mean_token_accuracy": 0.15353426784276963,
|
|
"num_tokens": 16295727.0,
|
|
"step": 7835
|
|
},
|
|
{
|
|
"entropy": 5.766923284530639,
|
|
"epoch": 0.7111756168359942,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.000495661367043409,
|
|
"loss": 5.6115,
|
|
"mean_token_accuracy": 0.16063830107450486,
|
|
"num_tokens": 16305496.0,
|
|
"step": 7840
|
|
},
|
|
{
|
|
"entropy": 5.7579789638519285,
|
|
"epoch": 0.7116291727140783,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004956550412709376,
|
|
"loss": 5.582,
|
|
"mean_token_accuracy": 0.16114101260900499,
|
|
"num_tokens": 16315112.0,
|
|
"step": 7845
|
|
},
|
|
{
|
|
"entropy": 5.813846206665039,
|
|
"epoch": 0.7120827285921626,
|
|
"grad_norm": 3.171875,
|
|
"learning_rate": 0.0004956487109352637,
|
|
"loss": 5.6442,
|
|
"mean_token_accuracy": 0.16229847073554993,
|
|
"num_tokens": 16325613.0,
|
|
"step": 7850
|
|
},
|
|
{
|
|
"entropy": 5.773796272277832,
|
|
"epoch": 0.7125362844702468,
|
|
"grad_norm": 3.828125,
|
|
"learning_rate": 0.0004956423760365181,
|
|
"loss": 5.567,
|
|
"mean_token_accuracy": 0.15991624295711518,
|
|
"num_tokens": 16335317.0,
|
|
"step": 7855
|
|
},
|
|
{
|
|
"entropy": 5.803212738037109,
|
|
"epoch": 0.7129898403483309,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.0004956360365748321,
|
|
"loss": 5.7073,
|
|
"mean_token_accuracy": 0.1481119990348816,
|
|
"num_tokens": 16345003.0,
|
|
"step": 7860
|
|
},
|
|
{
|
|
"entropy": 5.822187519073486,
|
|
"epoch": 0.7134433962264151,
|
|
"grad_norm": 3.921875,
|
|
"learning_rate": 0.0004956296925503367,
|
|
"loss": 5.6876,
|
|
"mean_token_accuracy": 0.1523458927869797,
|
|
"num_tokens": 16356108.0,
|
|
"step": 7865
|
|
},
|
|
{
|
|
"entropy": 5.7450230598449705,
|
|
"epoch": 0.7138969521044993,
|
|
"grad_norm": 4.8125,
|
|
"learning_rate": 0.0004956233439631628,
|
|
"loss": 5.5004,
|
|
"mean_token_accuracy": 0.16043572574853898,
|
|
"num_tokens": 16364733.0,
|
|
"step": 7870
|
|
},
|
|
{
|
|
"entropy": 5.791822290420532,
|
|
"epoch": 0.7143505079825835,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004956169908134421,
|
|
"loss": 5.6154,
|
|
"mean_token_accuracy": 0.1572842299938202,
|
|
"num_tokens": 16375229.0,
|
|
"step": 7875
|
|
},
|
|
{
|
|
"entropy": 5.792284727096558,
|
|
"epoch": 0.7148040638606676,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.0004956106331013057,
|
|
"loss": 5.7067,
|
|
"mean_token_accuracy": 0.15212783664464952,
|
|
"num_tokens": 16386366.0,
|
|
"step": 7880
|
|
},
|
|
{
|
|
"entropy": 5.711308336257934,
|
|
"epoch": 0.7152576197387518,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004956042708268853,
|
|
"loss": 5.5746,
|
|
"mean_token_accuracy": 0.16024879962205887,
|
|
"num_tokens": 16397067.0,
|
|
"step": 7885
|
|
},
|
|
{
|
|
"entropy": 5.715039968490601,
|
|
"epoch": 0.715711175616836,
|
|
"grad_norm": 4.375,
|
|
"learning_rate": 0.0004955979039903123,
|
|
"loss": 5.5332,
|
|
"mean_token_accuracy": 0.15609787553548812,
|
|
"num_tokens": 16407256.0,
|
|
"step": 7890
|
|
},
|
|
{
|
|
"entropy": 5.693595457077026,
|
|
"epoch": 0.7161647314949202,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.0004955915325917183,
|
|
"loss": 5.6008,
|
|
"mean_token_accuracy": 0.1544367030262947,
|
|
"num_tokens": 16418701.0,
|
|
"step": 7895
|
|
},
|
|
{
|
|
"entropy": 5.702099895477295,
|
|
"epoch": 0.7166182873730044,
|
|
"grad_norm": 8.4375,
|
|
"learning_rate": 0.0004955851566312354,
|
|
"loss": 5.5426,
|
|
"mean_token_accuracy": 0.1610220715403557,
|
|
"num_tokens": 16428019.0,
|
|
"step": 7900
|
|
},
|
|
{
|
|
"entropy": 5.7384286403656,
|
|
"epoch": 0.7170718432510885,
|
|
"grad_norm": 3.265625,
|
|
"learning_rate": 0.0004955787761089952,
|
|
"loss": 5.6022,
|
|
"mean_token_accuracy": 0.15697715431451797,
|
|
"num_tokens": 16440122.0,
|
|
"step": 7905
|
|
},
|
|
{
|
|
"entropy": 5.8590857028961185,
|
|
"epoch": 0.7175253991291727,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004955723910251296,
|
|
"loss": 5.662,
|
|
"mean_token_accuracy": 0.15431325137615204,
|
|
"num_tokens": 16449801.0,
|
|
"step": 7910
|
|
},
|
|
{
|
|
"entropy": 5.763668775558472,
|
|
"epoch": 0.717978955007257,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004955660013797709,
|
|
"loss": 5.5431,
|
|
"mean_token_accuracy": 0.15996514409780502,
|
|
"num_tokens": 16460155.0,
|
|
"step": 7915
|
|
},
|
|
{
|
|
"entropy": 5.810144853591919,
|
|
"epoch": 0.7184325108853411,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.000495559607173051,
|
|
"loss": 5.7181,
|
|
"mean_token_accuracy": 0.14558496475219726,
|
|
"num_tokens": 16470656.0,
|
|
"step": 7920
|
|
},
|
|
{
|
|
"entropy": 5.769259643554688,
|
|
"epoch": 0.7188860667634253,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004955532084051022,
|
|
"loss": 5.6338,
|
|
"mean_token_accuracy": 0.1549476057291031,
|
|
"num_tokens": 16481449.0,
|
|
"step": 7925
|
|
},
|
|
{
|
|
"entropy": 5.808447551727295,
|
|
"epoch": 0.7193396226415094,
|
|
"grad_norm": 2.890625,
|
|
"learning_rate": 0.0004955468050760568,
|
|
"loss": 5.6547,
|
|
"mean_token_accuracy": 0.15426983535289765,
|
|
"num_tokens": 16492032.0,
|
|
"step": 7930
|
|
},
|
|
{
|
|
"entropy": 5.813133907318115,
|
|
"epoch": 0.7197931785195936,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004955403971860474,
|
|
"loss": 5.5981,
|
|
"mean_token_accuracy": 0.15324619114398957,
|
|
"num_tokens": 16502221.0,
|
|
"step": 7935
|
|
},
|
|
{
|
|
"entropy": 5.813241052627563,
|
|
"epoch": 0.7202467343976778,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004955339847352063,
|
|
"loss": 5.5784,
|
|
"mean_token_accuracy": 0.158725568652153,
|
|
"num_tokens": 16512021.0,
|
|
"step": 7940
|
|
},
|
|
{
|
|
"entropy": 5.748729562759399,
|
|
"epoch": 0.720700290275762,
|
|
"grad_norm": 3.25,
|
|
"learning_rate": 0.0004955275677236662,
|
|
"loss": 5.6247,
|
|
"mean_token_accuracy": 0.15192925482988356,
|
|
"num_tokens": 16522060.0,
|
|
"step": 7945
|
|
},
|
|
{
|
|
"entropy": 5.764633464813232,
|
|
"epoch": 0.7211538461538461,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.0004955211461515599,
|
|
"loss": 5.6256,
|
|
"mean_token_accuracy": 0.16055750697851182,
|
|
"num_tokens": 16532827.0,
|
|
"step": 7950
|
|
},
|
|
{
|
|
"entropy": 5.77035083770752,
|
|
"epoch": 0.7216074020319303,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.00049551472001902,
|
|
"loss": 5.6584,
|
|
"mean_token_accuracy": 0.16088539361953735,
|
|
"num_tokens": 16542838.0,
|
|
"step": 7955
|
|
},
|
|
{
|
|
"entropy": 5.747999858856201,
|
|
"epoch": 0.7220609579100146,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004955082893261796,
|
|
"loss": 5.5968,
|
|
"mean_token_accuracy": 0.16128583997488022,
|
|
"num_tokens": 16552615.0,
|
|
"step": 7960
|
|
},
|
|
{
|
|
"entropy": 5.824002838134765,
|
|
"epoch": 0.7225145137880987,
|
|
"grad_norm": 3.15625,
|
|
"learning_rate": 0.0004955018540731714,
|
|
"loss": 5.6658,
|
|
"mean_token_accuracy": 0.1531428575515747,
|
|
"num_tokens": 16561777.0,
|
|
"step": 7965
|
|
},
|
|
{
|
|
"entropy": 5.844862222671509,
|
|
"epoch": 0.7229680696661829,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004954954142601288,
|
|
"loss": 5.6485,
|
|
"mean_token_accuracy": 0.15446362793445587,
|
|
"num_tokens": 16572111.0,
|
|
"step": 7970
|
|
},
|
|
{
|
|
"entropy": 5.804814147949219,
|
|
"epoch": 0.723421625544267,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004954889698871849,
|
|
"loss": 5.6817,
|
|
"mean_token_accuracy": 0.15889163613319396,
|
|
"num_tokens": 16581674.0,
|
|
"step": 7975
|
|
},
|
|
{
|
|
"entropy": 5.81389856338501,
|
|
"epoch": 0.7238751814223512,
|
|
"grad_norm": 3.078125,
|
|
"learning_rate": 0.0004954825209544728,
|
|
"loss": 5.6737,
|
|
"mean_token_accuracy": 0.16090579181909562,
|
|
"num_tokens": 16591802.0,
|
|
"step": 7980
|
|
},
|
|
{
|
|
"entropy": 5.730545282363892,
|
|
"epoch": 0.7243287373004355,
|
|
"grad_norm": 3.515625,
|
|
"learning_rate": 0.000495476067462126,
|
|
"loss": 5.5695,
|
|
"mean_token_accuracy": 0.16237852573394776,
|
|
"num_tokens": 16602772.0,
|
|
"step": 7985
|
|
},
|
|
{
|
|
"entropy": 5.777552795410156,
|
|
"epoch": 0.7247822931785196,
|
|
"grad_norm": 3.796875,
|
|
"learning_rate": 0.000495469609410278,
|
|
"loss": 5.6104,
|
|
"mean_token_accuracy": 0.1624607339501381,
|
|
"num_tokens": 16613526.0,
|
|
"step": 7990
|
|
},
|
|
{
|
|
"entropy": 5.762968063354492,
|
|
"epoch": 0.7252358490566038,
|
|
"grad_norm": 3.484375,
|
|
"learning_rate": 0.0004954631467990622,
|
|
"loss": 5.6337,
|
|
"mean_token_accuracy": 0.15944494158029557,
|
|
"num_tokens": 16623583.0,
|
|
"step": 7995
|
|
},
|
|
{
|
|
"entropy": 5.799592447280884,
|
|
"epoch": 0.7256894049346879,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004954566796286124,
|
|
"loss": 5.6835,
|
|
"mean_token_accuracy": 0.15078045651316643,
|
|
"num_tokens": 16635068.0,
|
|
"step": 8000
|
|
},
|
|
{
|
|
"entropy": 5.77793869972229,
|
|
"epoch": 0.7261429608127722,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004954502078990623,
|
|
"loss": 5.597,
|
|
"mean_token_accuracy": 0.1602660283446312,
|
|
"num_tokens": 16645021.0,
|
|
"step": 8005
|
|
},
|
|
{
|
|
"entropy": 5.779656219482422,
|
|
"epoch": 0.7265965166908563,
|
|
"grad_norm": 3.046875,
|
|
"learning_rate": 0.0004954437316105457,
|
|
"loss": 5.6564,
|
|
"mean_token_accuracy": 0.15226438343524934,
|
|
"num_tokens": 16656021.0,
|
|
"step": 8010
|
|
},
|
|
{
|
|
"entropy": 5.736810302734375,
|
|
"epoch": 0.7270500725689405,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004954372507631965,
|
|
"loss": 5.5506,
|
|
"mean_token_accuracy": 0.1654258355498314,
|
|
"num_tokens": 16665236.0,
|
|
"step": 8015
|
|
},
|
|
{
|
|
"entropy": 5.738938236236573,
|
|
"epoch": 0.7275036284470247,
|
|
"grad_norm": 3.15625,
|
|
"learning_rate": 0.0004954307653571489,
|
|
"loss": 5.7423,
|
|
"mean_token_accuracy": 0.1501321703195572,
|
|
"num_tokens": 16676690.0,
|
|
"step": 8020
|
|
},
|
|
{
|
|
"entropy": 5.804196786880493,
|
|
"epoch": 0.7279571843251088,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004954242753925367,
|
|
"loss": 5.6363,
|
|
"mean_token_accuracy": 0.15009679719805719,
|
|
"num_tokens": 16687288.0,
|
|
"step": 8025
|
|
},
|
|
{
|
|
"entropy": 5.809215927124024,
|
|
"epoch": 0.7284107402031931,
|
|
"grad_norm": 3.28125,
|
|
"learning_rate": 0.0004954177808694946,
|
|
"loss": 5.6449,
|
|
"mean_token_accuracy": 0.15161658823490143,
|
|
"num_tokens": 16697873.0,
|
|
"step": 8030
|
|
},
|
|
{
|
|
"entropy": 5.766271352767944,
|
|
"epoch": 0.7288642960812772,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004954112817881565,
|
|
"loss": 5.6496,
|
|
"mean_token_accuracy": 0.15360791981220245,
|
|
"num_tokens": 16709002.0,
|
|
"step": 8035
|
|
},
|
|
{
|
|
"entropy": 5.761889362335205,
|
|
"epoch": 0.7293178519593614,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004954047781486568,
|
|
"loss": 5.6205,
|
|
"mean_token_accuracy": 0.16080274432897568,
|
|
"num_tokens": 16718989.0,
|
|
"step": 8040
|
|
},
|
|
{
|
|
"entropy": 5.9060508728027346,
|
|
"epoch": 0.7297714078374455,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004953982699511303,
|
|
"loss": 5.7199,
|
|
"mean_token_accuracy": 0.15385592058300973,
|
|
"num_tokens": 16730425.0,
|
|
"step": 8045
|
|
},
|
|
{
|
|
"entropy": 5.826246070861816,
|
|
"epoch": 0.7302249637155298,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004953917571957114,
|
|
"loss": 5.6016,
|
|
"mean_token_accuracy": 0.15725287199020385,
|
|
"num_tokens": 16740216.0,
|
|
"step": 8050
|
|
},
|
|
{
|
|
"entropy": 5.725392770767212,
|
|
"epoch": 0.730678519593614,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004953852398825346,
|
|
"loss": 5.6029,
|
|
"mean_token_accuracy": 0.15493546724319457,
|
|
"num_tokens": 16752436.0,
|
|
"step": 8055
|
|
},
|
|
{
|
|
"entropy": 5.739631319046021,
|
|
"epoch": 0.7311320754716981,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.000495378718011735,
|
|
"loss": 5.6102,
|
|
"mean_token_accuracy": 0.15602830350399016,
|
|
"num_tokens": 16762631.0,
|
|
"step": 8060
|
|
},
|
|
{
|
|
"entropy": 5.8749692916870115,
|
|
"epoch": 0.7315856313497823,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004953721915834473,
|
|
"loss": 5.6495,
|
|
"mean_token_accuracy": 0.1531766250729561,
|
|
"num_tokens": 16772613.0,
|
|
"step": 8065
|
|
},
|
|
{
|
|
"entropy": 5.821211862564087,
|
|
"epoch": 0.7320391872278664,
|
|
"grad_norm": 3.03125,
|
|
"learning_rate": 0.0004953656605978067,
|
|
"loss": 5.6449,
|
|
"mean_token_accuracy": 0.1528734877705574,
|
|
"num_tokens": 16782963.0,
|
|
"step": 8070
|
|
},
|
|
{
|
|
"entropy": 5.712953901290893,
|
|
"epoch": 0.7324927431059507,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.000495359125054948,
|
|
"loss": 5.5783,
|
|
"mean_token_accuracy": 0.15503397285938264,
|
|
"num_tokens": 16793892.0,
|
|
"step": 8075
|
|
},
|
|
{
|
|
"entropy": 5.654757499694824,
|
|
"epoch": 0.7329462989840348,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004953525849550063,
|
|
"loss": 5.5538,
|
|
"mean_token_accuracy": 0.15403005629777908,
|
|
"num_tokens": 16803388.0,
|
|
"step": 8080
|
|
},
|
|
{
|
|
"entropy": 5.736060619354248,
|
|
"epoch": 0.733399854862119,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004953460402981172,
|
|
"loss": 5.5299,
|
|
"mean_token_accuracy": 0.1605105310678482,
|
|
"num_tokens": 16813201.0,
|
|
"step": 8085
|
|
},
|
|
{
|
|
"entropy": 5.83330774307251,
|
|
"epoch": 0.7338534107402032,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004953394910844157,
|
|
"loss": 5.7471,
|
|
"mean_token_accuracy": 0.15453502386808396,
|
|
"num_tokens": 16823265.0,
|
|
"step": 8090
|
|
},
|
|
{
|
|
"entropy": 5.816150331497193,
|
|
"epoch": 0.7343069666182874,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004953329373140374,
|
|
"loss": 5.5551,
|
|
"mean_token_accuracy": 0.15653111785650253,
|
|
"num_tokens": 16833057.0,
|
|
"step": 8095
|
|
},
|
|
{
|
|
"entropy": 5.7323627948760985,
|
|
"epoch": 0.7347605224963716,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004953263789871179,
|
|
"loss": 5.5185,
|
|
"mean_token_accuracy": 0.1549549698829651,
|
|
"num_tokens": 16843488.0,
|
|
"step": 8100
|
|
},
|
|
{
|
|
"entropy": 5.68474645614624,
|
|
"epoch": 0.7352140783744557,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004953198161037925,
|
|
"loss": 5.5595,
|
|
"mean_token_accuracy": 0.16272432655096053,
|
|
"num_tokens": 16852448.0,
|
|
"step": 8105
|
|
},
|
|
{
|
|
"entropy": 5.706146478652954,
|
|
"epoch": 0.7356676342525399,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.0004953132486641975,
|
|
"loss": 5.6299,
|
|
"mean_token_accuracy": 0.15620479583740235,
|
|
"num_tokens": 16863944.0,
|
|
"step": 8110
|
|
},
|
|
{
|
|
"entropy": 5.779846954345703,
|
|
"epoch": 0.736121190130624,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.000495306676668468,
|
|
"loss": 5.5523,
|
|
"mean_token_accuracy": 0.1597314640879631,
|
|
"num_tokens": 16873923.0,
|
|
"step": 8115
|
|
},
|
|
{
|
|
"entropy": 5.7534888744354244,
|
|
"epoch": 0.7365747460087083,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004953001001167406,
|
|
"loss": 5.6338,
|
|
"mean_token_accuracy": 0.15616717636585237,
|
|
"num_tokens": 16884373.0,
|
|
"step": 8120
|
|
},
|
|
{
|
|
"entropy": 5.797355031967163,
|
|
"epoch": 0.7370283018867925,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004952935190091508,
|
|
"loss": 5.751,
|
|
"mean_token_accuracy": 0.14971877932548522,
|
|
"num_tokens": 16895869.0,
|
|
"step": 8125
|
|
},
|
|
{
|
|
"entropy": 5.675172948837281,
|
|
"epoch": 0.7374818577648766,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004952869333458349,
|
|
"loss": 5.6137,
|
|
"mean_token_accuracy": 0.15598379522562028,
|
|
"num_tokens": 16906737.0,
|
|
"step": 8130
|
|
},
|
|
{
|
|
"entropy": 5.729729843139649,
|
|
"epoch": 0.7379354136429608,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004952803431269292,
|
|
"loss": 5.5513,
|
|
"mean_token_accuracy": 0.16393394023180008,
|
|
"num_tokens": 16916083.0,
|
|
"step": 8135
|
|
},
|
|
{
|
|
"entropy": 5.9084995746612545,
|
|
"epoch": 0.738388969521045,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004952737483525699,
|
|
"loss": 5.6972,
|
|
"mean_token_accuracy": 0.1537786453962326,
|
|
"num_tokens": 16926419.0,
|
|
"step": 8140
|
|
},
|
|
{
|
|
"entropy": 5.845476150512695,
|
|
"epoch": 0.7388425253991292,
|
|
"grad_norm": 3.9375,
|
|
"learning_rate": 0.0004952671490228932,
|
|
"loss": 5.6348,
|
|
"mean_token_accuracy": 0.15125631541013718,
|
|
"num_tokens": 16936067.0,
|
|
"step": 8145
|
|
},
|
|
{
|
|
"entropy": 5.785321569442749,
|
|
"epoch": 0.7392960812772134,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.0004952605451380357,
|
|
"loss": 5.5902,
|
|
"mean_token_accuracy": 0.15724589079618453,
|
|
"num_tokens": 16946571.0,
|
|
"step": 8150
|
|
},
|
|
{
|
|
"entropy": 5.69130859375,
|
|
"epoch": 0.7397496371552975,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.0004952539366981342,
|
|
"loss": 5.6351,
|
|
"mean_token_accuracy": 0.15460131987929343,
|
|
"num_tokens": 16956764.0,
|
|
"step": 8155
|
|
},
|
|
{
|
|
"entropy": 5.730801725387574,
|
|
"epoch": 0.7402031930333817,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.000495247323703325,
|
|
"loss": 5.5779,
|
|
"mean_token_accuracy": 0.16185448169708253,
|
|
"num_tokens": 16966002.0,
|
|
"step": 8160
|
|
},
|
|
{
|
|
"entropy": 5.810474014282226,
|
|
"epoch": 0.7406567489114659,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.000495240706153745,
|
|
"loss": 5.672,
|
|
"mean_token_accuracy": 0.16184382885694504,
|
|
"num_tokens": 16975705.0,
|
|
"step": 8165
|
|
},
|
|
{
|
|
"entropy": 5.792193794250489,
|
|
"epoch": 0.7411103047895501,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004952340840495312,
|
|
"loss": 5.5654,
|
|
"mean_token_accuracy": 0.1592943087220192,
|
|
"num_tokens": 16985945.0,
|
|
"step": 8170
|
|
},
|
|
{
|
|
"entropy": 5.7322290420532225,
|
|
"epoch": 0.7415638606676342,
|
|
"grad_norm": 3.21875,
|
|
"learning_rate": 0.0004952274573908203,
|
|
"loss": 5.5333,
|
|
"mean_token_accuracy": 0.15994324982166291,
|
|
"num_tokens": 16995475.0,
|
|
"step": 8175
|
|
},
|
|
{
|
|
"entropy": 5.720385551452637,
|
|
"epoch": 0.7420174165457184,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004952208261777496,
|
|
"loss": 5.5863,
|
|
"mean_token_accuracy": 0.1577586606144905,
|
|
"num_tokens": 17005028.0,
|
|
"step": 8180
|
|
},
|
|
{
|
|
"entropy": 5.70277590751648,
|
|
"epoch": 0.7424709724238027,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.000495214190410456,
|
|
"loss": 5.6413,
|
|
"mean_token_accuracy": 0.16015808135271073,
|
|
"num_tokens": 17014786.0,
|
|
"step": 8185
|
|
},
|
|
{
|
|
"entropy": 5.782215023040772,
|
|
"epoch": 0.7429245283018868,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004952075500890768,
|
|
"loss": 5.6375,
|
|
"mean_token_accuracy": 0.15373314470052718,
|
|
"num_tokens": 17024431.0,
|
|
"step": 8190
|
|
},
|
|
{
|
|
"entropy": 5.7832722663879395,
|
|
"epoch": 0.743378084179971,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004952009052137493,
|
|
"loss": 5.6131,
|
|
"mean_token_accuracy": 0.15820928514003754,
|
|
"num_tokens": 17034368.0,
|
|
"step": 8195
|
|
},
|
|
{
|
|
"entropy": 5.704320812225342,
|
|
"epoch": 0.7438316400580551,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004951942557846112,
|
|
"loss": 5.6477,
|
|
"mean_token_accuracy": 0.15668941885232926,
|
|
"num_tokens": 17043818.0,
|
|
"step": 8200
|
|
},
|
|
{
|
|
"entropy": 5.762405443191528,
|
|
"epoch": 0.7442851959361393,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004951876018017997,
|
|
"loss": 5.6449,
|
|
"mean_token_accuracy": 0.16201995462179183,
|
|
"num_tokens": 17054843.0,
|
|
"step": 8205
|
|
},
|
|
{
|
|
"entropy": 5.81440749168396,
|
|
"epoch": 0.7447387518142236,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004951809432654524,
|
|
"loss": 5.6456,
|
|
"mean_token_accuracy": 0.15417395681142806,
|
|
"num_tokens": 17065539.0,
|
|
"step": 8210
|
|
},
|
|
{
|
|
"entropy": 5.7607855796813965,
|
|
"epoch": 0.7451923076923077,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.000495174280175707,
|
|
"loss": 5.5399,
|
|
"mean_token_accuracy": 0.16154730021953584,
|
|
"num_tokens": 17075443.0,
|
|
"step": 8215
|
|
},
|
|
{
|
|
"entropy": 5.8358794212341305,
|
|
"epoch": 0.7456458635703919,
|
|
"grad_norm": 3.15625,
|
|
"learning_rate": 0.0004951676125327015,
|
|
"loss": 5.6909,
|
|
"mean_token_accuracy": 0.15732420980930328,
|
|
"num_tokens": 17085490.0,
|
|
"step": 8220
|
|
},
|
|
{
|
|
"entropy": 5.773124504089355,
|
|
"epoch": 0.746099419448476,
|
|
"grad_norm": 4.21875,
|
|
"learning_rate": 0.0004951609403365737,
|
|
"loss": 5.6691,
|
|
"mean_token_accuracy": 0.16350300014019012,
|
|
"num_tokens": 17094803.0,
|
|
"step": 8225
|
|
},
|
|
{
|
|
"entropy": 5.741847515106201,
|
|
"epoch": 0.7465529753265603,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004951542635874615,
|
|
"loss": 5.5236,
|
|
"mean_token_accuracy": 0.15575825721025466,
|
|
"num_tokens": 17104373.0,
|
|
"step": 8230
|
|
},
|
|
{
|
|
"entropy": 5.7692542552948,
|
|
"epoch": 0.7470065312046444,
|
|
"grad_norm": 4.78125,
|
|
"learning_rate": 0.0004951475822855029,
|
|
"loss": 5.6208,
|
|
"mean_token_accuracy": 0.1559954658150673,
|
|
"num_tokens": 17115469.0,
|
|
"step": 8235
|
|
},
|
|
{
|
|
"entropy": 5.7214123725891115,
|
|
"epoch": 0.7474600870827286,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004951408964308364,
|
|
"loss": 5.5945,
|
|
"mean_token_accuracy": 0.15529240369796754,
|
|
"num_tokens": 17125443.0,
|
|
"step": 8240
|
|
},
|
|
{
|
|
"entropy": 5.701405763626099,
|
|
"epoch": 0.7479136429608128,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004951342060236,
|
|
"loss": 5.5529,
|
|
"mean_token_accuracy": 0.15890992432832718,
|
|
"num_tokens": 17136253.0,
|
|
"step": 8245
|
|
},
|
|
{
|
|
"entropy": 5.851835012435913,
|
|
"epoch": 0.7483671988388969,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004951275110639321,
|
|
"loss": 5.6167,
|
|
"mean_token_accuracy": 0.160022309422493,
|
|
"num_tokens": 17145544.0,
|
|
"step": 8250
|
|
},
|
|
{
|
|
"entropy": 5.778053617477417,
|
|
"epoch": 0.7488207547169812,
|
|
"grad_norm": 4.28125,
|
|
"learning_rate": 0.0004951208115519712,
|
|
"loss": 5.6155,
|
|
"mean_token_accuracy": 0.156676721572876,
|
|
"num_tokens": 17155043.0,
|
|
"step": 8255
|
|
},
|
|
{
|
|
"entropy": 5.664043331146241,
|
|
"epoch": 0.7492743105950653,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.0004951141074878558,
|
|
"loss": 5.6681,
|
|
"mean_token_accuracy": 0.15661310255527497,
|
|
"num_tokens": 17164885.0,
|
|
"step": 8260
|
|
},
|
|
{
|
|
"entropy": 5.803770303726196,
|
|
"epoch": 0.7497278664731495,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.0004951073988717246,
|
|
"loss": 5.6546,
|
|
"mean_token_accuracy": 0.15547531992197036,
|
|
"num_tokens": 17175681.0,
|
|
"step": 8265
|
|
},
|
|
{
|
|
"entropy": 5.721224546432495,
|
|
"epoch": 0.7501814223512336,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004951006857037163,
|
|
"loss": 5.5184,
|
|
"mean_token_accuracy": 0.160471174120903,
|
|
"num_tokens": 17186002.0,
|
|
"step": 8270
|
|
},
|
|
{
|
|
"entropy": 5.759907197952271,
|
|
"epoch": 0.7506349782293179,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004950939679839696,
|
|
"loss": 5.5906,
|
|
"mean_token_accuracy": 0.15814287662506105,
|
|
"num_tokens": 17195499.0,
|
|
"step": 8275
|
|
},
|
|
{
|
|
"entropy": 5.763993167877198,
|
|
"epoch": 0.7510885341074021,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004950872457126237,
|
|
"loss": 5.5893,
|
|
"mean_token_accuracy": 0.1606327325105667,
|
|
"num_tokens": 17204684.0,
|
|
"step": 8280
|
|
},
|
|
{
|
|
"entropy": 5.736480617523194,
|
|
"epoch": 0.7515420899854862,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.0004950805188898175,
|
|
"loss": 5.6116,
|
|
"mean_token_accuracy": 0.15062818825244903,
|
|
"num_tokens": 17213987.0,
|
|
"step": 8285
|
|
},
|
|
{
|
|
"entropy": 5.706430864334107,
|
|
"epoch": 0.7519956458635704,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.00049507378751569,
|
|
"loss": 5.6653,
|
|
"mean_token_accuracy": 0.15044132471084595,
|
|
"num_tokens": 17224512.0,
|
|
"step": 8290
|
|
},
|
|
{
|
|
"entropy": 5.813805341720581,
|
|
"epoch": 0.7524492017416545,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004950670515903805,
|
|
"loss": 5.6677,
|
|
"mean_token_accuracy": 0.156072798371315,
|
|
"num_tokens": 17234362.0,
|
|
"step": 8295
|
|
},
|
|
{
|
|
"entropy": 5.849670457839966,
|
|
"epoch": 0.7529027576197388,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004950603111140283,
|
|
"loss": 5.6485,
|
|
"mean_token_accuracy": 0.16128491908311843,
|
|
"num_tokens": 17244241.0,
|
|
"step": 8300
|
|
},
|
|
{
|
|
"entropy": 5.746774530410766,
|
|
"epoch": 0.753356313497823,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004950535660867728,
|
|
"loss": 5.5874,
|
|
"mean_token_accuracy": 0.1597753271460533,
|
|
"num_tokens": 17254689.0,
|
|
"step": 8305
|
|
},
|
|
{
|
|
"entropy": 5.774064588546753,
|
|
"epoch": 0.7538098693759071,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004950468165087535,
|
|
"loss": 5.6731,
|
|
"mean_token_accuracy": 0.15421361476182938,
|
|
"num_tokens": 17265506.0,
|
|
"step": 8310
|
|
},
|
|
{
|
|
"entropy": 5.829351091384888,
|
|
"epoch": 0.7542634252539913,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004950400623801098,
|
|
"loss": 5.7373,
|
|
"mean_token_accuracy": 0.15709088742733002,
|
|
"num_tokens": 17276376.0,
|
|
"step": 8315
|
|
},
|
|
{
|
|
"entropy": 5.817118406295776,
|
|
"epoch": 0.7547169811320755,
|
|
"grad_norm": 3.09375,
|
|
"learning_rate": 0.0004950333037009818,
|
|
"loss": 5.6416,
|
|
"mean_token_accuracy": 0.14860429465770722,
|
|
"num_tokens": 17287005.0,
|
|
"step": 8320
|
|
},
|
|
{
|
|
"entropy": 5.800573635101318,
|
|
"epoch": 0.7551705370101597,
|
|
"grad_norm": 2.953125,
|
|
"learning_rate": 0.0004950265404715089,
|
|
"loss": 5.6514,
|
|
"mean_token_accuracy": 0.15255427807569505,
|
|
"num_tokens": 17297595.0,
|
|
"step": 8325
|
|
},
|
|
{
|
|
"entropy": 5.712475156784057,
|
|
"epoch": 0.7556240928882438,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.000495019772691831,
|
|
"loss": 5.5188,
|
|
"mean_token_accuracy": 0.16102788150310515,
|
|
"num_tokens": 17307319.0,
|
|
"step": 8330
|
|
},
|
|
{
|
|
"entropy": 5.753348875045776,
|
|
"epoch": 0.756077648766328,
|
|
"grad_norm": 4.15625,
|
|
"learning_rate": 0.0004950130003620882,
|
|
"loss": 5.7276,
|
|
"mean_token_accuracy": 0.15592837631702422,
|
|
"num_tokens": 17317978.0,
|
|
"step": 8335
|
|
},
|
|
{
|
|
"entropy": 5.79032154083252,
|
|
"epoch": 0.7565312046444121,
|
|
"grad_norm": 4.21875,
|
|
"learning_rate": 0.0004950062234824204,
|
|
"loss": 5.619,
|
|
"mean_token_accuracy": 0.1543349266052246,
|
|
"num_tokens": 17328339.0,
|
|
"step": 8340
|
|
},
|
|
{
|
|
"entropy": 5.8189697265625,
|
|
"epoch": 0.7569847605224964,
|
|
"grad_norm": 3.421875,
|
|
"learning_rate": 0.0004949994420529679,
|
|
"loss": 5.6732,
|
|
"mean_token_accuracy": 0.15629276037216186,
|
|
"num_tokens": 17338668.0,
|
|
"step": 8345
|
|
},
|
|
{
|
|
"entropy": 5.722092628479004,
|
|
"epoch": 0.7574383164005806,
|
|
"grad_norm": 3.296875,
|
|
"learning_rate": 0.0004949926560738709,
|
|
"loss": 5.61,
|
|
"mean_token_accuracy": 0.1548818901181221,
|
|
"num_tokens": 17348609.0,
|
|
"step": 8350
|
|
},
|
|
{
|
|
"entropy": 5.778551483154297,
|
|
"epoch": 0.7578918722786647,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004949858655452697,
|
|
"loss": 5.6182,
|
|
"mean_token_accuracy": 0.1580677330493927,
|
|
"num_tokens": 17358014.0,
|
|
"step": 8355
|
|
},
|
|
{
|
|
"entropy": 5.8439408302307125,
|
|
"epoch": 0.7583454281567489,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004949790704673048,
|
|
"loss": 5.6406,
|
|
"mean_token_accuracy": 0.15462183952331543,
|
|
"num_tokens": 17367975.0,
|
|
"step": 8360
|
|
},
|
|
{
|
|
"entropy": 5.79978575706482,
|
|
"epoch": 0.7587989840348331,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004949722708401166,
|
|
"loss": 5.5922,
|
|
"mean_token_accuracy": 0.16122720241546631,
|
|
"num_tokens": 17377960.0,
|
|
"step": 8365
|
|
},
|
|
{
|
|
"entropy": 5.787926769256591,
|
|
"epoch": 0.7592525399129173,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004949654666638457,
|
|
"loss": 5.6539,
|
|
"mean_token_accuracy": 0.1638580560684204,
|
|
"num_tokens": 17387334.0,
|
|
"step": 8370
|
|
},
|
|
{
|
|
"entropy": 5.751470899581909,
|
|
"epoch": 0.7597060957910015,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.000494958657938633,
|
|
"loss": 5.6273,
|
|
"mean_token_accuracy": 0.15456898808479308,
|
|
"num_tokens": 17396521.0,
|
|
"step": 8375
|
|
},
|
|
{
|
|
"entropy": 5.730402326583862,
|
|
"epoch": 0.7601596516690856,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004949518446646192,
|
|
"loss": 5.6011,
|
|
"mean_token_accuracy": 0.15843016803264617,
|
|
"num_tokens": 17407217.0,
|
|
"step": 8380
|
|
},
|
|
{
|
|
"entropy": 5.833608818054199,
|
|
"epoch": 0.7606132075471698,
|
|
"grad_norm": 3.46875,
|
|
"learning_rate": 0.0004949450268419451,
|
|
"loss": 5.6841,
|
|
"mean_token_accuracy": 0.1537593498826027,
|
|
"num_tokens": 17416982.0,
|
|
"step": 8385
|
|
},
|
|
{
|
|
"entropy": 5.7752313137054445,
|
|
"epoch": 0.761066763425254,
|
|
"grad_norm": 3.15625,
|
|
"learning_rate": 0.000494938204470752,
|
|
"loss": 5.5581,
|
|
"mean_token_accuracy": 0.15870605111122132,
|
|
"num_tokens": 17427636.0,
|
|
"step": 8390
|
|
},
|
|
{
|
|
"entropy": 5.752287817001343,
|
|
"epoch": 0.7615203193033382,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004949313775511806,
|
|
"loss": 5.6584,
|
|
"mean_token_accuracy": 0.15613557100296022,
|
|
"num_tokens": 17437488.0,
|
|
"step": 8395
|
|
},
|
|
{
|
|
"entropy": 5.766221952438355,
|
|
"epoch": 0.7619738751814223,
|
|
"grad_norm": 3.109375,
|
|
"learning_rate": 0.0004949245460833723,
|
|
"loss": 5.4833,
|
|
"mean_token_accuracy": 0.15987526923418044,
|
|
"num_tokens": 17447838.0,
|
|
"step": 8400
|
|
},
|
|
{
|
|
"entropy": 5.833551645278931,
|
|
"epoch": 0.7624274310595065,
|
|
"grad_norm": 3.765625,
|
|
"learning_rate": 0.0004949177100674684,
|
|
"loss": 5.6733,
|
|
"mean_token_accuracy": 0.16033527255058289,
|
|
"num_tokens": 17457257.0,
|
|
"step": 8405
|
|
},
|
|
{
|
|
"entropy": 5.769413089752197,
|
|
"epoch": 0.7628809869375908,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004949108695036102,
|
|
"loss": 5.5967,
|
|
"mean_token_accuracy": 0.1562741219997406,
|
|
"num_tokens": 17467729.0,
|
|
"step": 8410
|
|
},
|
|
{
|
|
"entropy": 5.738751697540283,
|
|
"epoch": 0.7633345428156749,
|
|
"grad_norm": 2.890625,
|
|
"learning_rate": 0.0004949040243919392,
|
|
"loss": 5.6211,
|
|
"mean_token_accuracy": 0.14854976236820222,
|
|
"num_tokens": 17477692.0,
|
|
"step": 8415
|
|
},
|
|
{
|
|
"entropy": 5.765266466140747,
|
|
"epoch": 0.7637880986937591,
|
|
"grad_norm": 2.984375,
|
|
"learning_rate": 0.0004948971747325968,
|
|
"loss": 5.6265,
|
|
"mean_token_accuracy": 0.15609366446733475,
|
|
"num_tokens": 17488730.0,
|
|
"step": 8420
|
|
},
|
|
{
|
|
"entropy": 5.79982271194458,
|
|
"epoch": 0.7642416545718432,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.000494890320525725,
|
|
"loss": 5.6998,
|
|
"mean_token_accuracy": 0.15643664747476577,
|
|
"num_tokens": 17498374.0,
|
|
"step": 8425
|
|
},
|
|
{
|
|
"entropy": 5.818951892852783,
|
|
"epoch": 0.7646952104499274,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004948834617714652,
|
|
"loss": 5.5518,
|
|
"mean_token_accuracy": 0.16498626470565797,
|
|
"num_tokens": 17508601.0,
|
|
"step": 8430
|
|
},
|
|
{
|
|
"entropy": 5.724190378189087,
|
|
"epoch": 0.7651487663280117,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004948765984699595,
|
|
"loss": 5.5833,
|
|
"mean_token_accuracy": 0.1610970064997673,
|
|
"num_tokens": 17518164.0,
|
|
"step": 8435
|
|
},
|
|
{
|
|
"entropy": 5.705046081542969,
|
|
"epoch": 0.7656023222060958,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004948697306213494,
|
|
"loss": 5.5474,
|
|
"mean_token_accuracy": 0.16527391970157623,
|
|
"num_tokens": 17527244.0,
|
|
"step": 8440
|
|
},
|
|
{
|
|
"entropy": 5.8157226085662845,
|
|
"epoch": 0.76605587808418,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004948628582257775,
|
|
"loss": 5.6383,
|
|
"mean_token_accuracy": 0.15614416748285292,
|
|
"num_tokens": 17538045.0,
|
|
"step": 8445
|
|
},
|
|
{
|
|
"entropy": 5.772269582748413,
|
|
"epoch": 0.7665094339622641,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004948559812833857,
|
|
"loss": 5.597,
|
|
"mean_token_accuracy": 0.15702936947345733,
|
|
"num_tokens": 17547584.0,
|
|
"step": 8450
|
|
},
|
|
{
|
|
"entropy": 5.776641750335694,
|
|
"epoch": 0.7669629898403484,
|
|
"grad_norm": 3.5625,
|
|
"learning_rate": 0.0004948490997943162,
|
|
"loss": 5.6249,
|
|
"mean_token_accuracy": 0.1593453913927078,
|
|
"num_tokens": 17558925.0,
|
|
"step": 8455
|
|
},
|
|
{
|
|
"entropy": 5.762310457229614,
|
|
"epoch": 0.7674165457184325,
|
|
"grad_norm": 5.9375,
|
|
"learning_rate": 0.0004948422137587111,
|
|
"loss": 5.724,
|
|
"mean_token_accuracy": 0.1505131408572197,
|
|
"num_tokens": 17569355.0,
|
|
"step": 8460
|
|
},
|
|
{
|
|
"entropy": 5.784338808059692,
|
|
"epoch": 0.7678701015965167,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.0004948353231767131,
|
|
"loss": 5.5881,
|
|
"mean_token_accuracy": 0.15870064198970796,
|
|
"num_tokens": 17579782.0,
|
|
"step": 8465
|
|
},
|
|
{
|
|
"entropy": 5.826953411102295,
|
|
"epoch": 0.7683236574746009,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.0004948284280484645,
|
|
"loss": 5.6428,
|
|
"mean_token_accuracy": 0.16042931079864503,
|
|
"num_tokens": 17589772.0,
|
|
"step": 8470
|
|
},
|
|
{
|
|
"entropy": 5.7036386013031,
|
|
"epoch": 0.768777213352685,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.0004948215283741081,
|
|
"loss": 5.5711,
|
|
"mean_token_accuracy": 0.1547003537416458,
|
|
"num_tokens": 17599613.0,
|
|
"step": 8475
|
|
},
|
|
{
|
|
"entropy": 5.738386487960815,
|
|
"epoch": 0.7692307692307693,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004948146241537866,
|
|
"loss": 5.6615,
|
|
"mean_token_accuracy": 0.1533209577202797,
|
|
"num_tokens": 17609056.0,
|
|
"step": 8480
|
|
},
|
|
{
|
|
"entropy": 5.764581918716431,
|
|
"epoch": 0.7696843251088534,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004948077153876425,
|
|
"loss": 5.5759,
|
|
"mean_token_accuracy": 0.1585683375597,
|
|
"num_tokens": 17618620.0,
|
|
"step": 8485
|
|
},
|
|
{
|
|
"entropy": 5.7266357898712155,
|
|
"epoch": 0.7701378809869376,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004948008020758188,
|
|
"loss": 5.5342,
|
|
"mean_token_accuracy": 0.16150321513414384,
|
|
"num_tokens": 17627630.0,
|
|
"step": 8490
|
|
},
|
|
{
|
|
"entropy": 5.6926289081573485,
|
|
"epoch": 0.7705914368650217,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.0004947938842184585,
|
|
"loss": 5.5501,
|
|
"mean_token_accuracy": 0.1610981583595276,
|
|
"num_tokens": 17638903.0,
|
|
"step": 8495
|
|
},
|
|
{
|
|
"entropy": 5.751527643203735,
|
|
"epoch": 0.771044992743106,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004947869618157048,
|
|
"loss": 5.5903,
|
|
"mean_token_accuracy": 0.15254145711660386,
|
|
"num_tokens": 17649257.0,
|
|
"step": 8500
|
|
},
|
|
{
|
|
"entropy": 5.730644702911377,
|
|
"epoch": 0.7714985486211902,
|
|
"grad_norm": 3.59375,
|
|
"learning_rate": 0.0004947800348677006,
|
|
"loss": 5.5627,
|
|
"mean_token_accuracy": 0.1666986346244812,
|
|
"num_tokens": 17659495.0,
|
|
"step": 8505
|
|
},
|
|
{
|
|
"entropy": 5.650215673446655,
|
|
"epoch": 0.7719521044992743,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004947731033745893,
|
|
"loss": 5.554,
|
|
"mean_token_accuracy": 0.16249235570430756,
|
|
"num_tokens": 17669671.0,
|
|
"step": 8510
|
|
},
|
|
{
|
|
"entropy": 5.83202748298645,
|
|
"epoch": 0.7724056603773585,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.0004947661673365142,
|
|
"loss": 5.721,
|
|
"mean_token_accuracy": 0.15400478094816208,
|
|
"num_tokens": 17680927.0,
|
|
"step": 8515
|
|
},
|
|
{
|
|
"entropy": 5.78148136138916,
|
|
"epoch": 0.7728592162554426,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.0004947592267536188,
|
|
"loss": 5.595,
|
|
"mean_token_accuracy": 0.1603729546070099,
|
|
"num_tokens": 17691378.0,
|
|
"step": 8520
|
|
},
|
|
{
|
|
"entropy": 5.750188398361206,
|
|
"epoch": 0.7733127721335269,
|
|
"grad_norm": 8.5,
|
|
"learning_rate": 0.0004947522816260466,
|
|
"loss": 5.6546,
|
|
"mean_token_accuracy": 0.15359988436102867,
|
|
"num_tokens": 17700942.0,
|
|
"step": 8525
|
|
},
|
|
{
|
|
"entropy": 5.755286645889282,
|
|
"epoch": 0.773766328011611,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004947453319539411,
|
|
"loss": 5.5675,
|
|
"mean_token_accuracy": 0.16288118213415145,
|
|
"num_tokens": 17710076.0,
|
|
"step": 8530
|
|
},
|
|
{
|
|
"entropy": 5.735703372955323,
|
|
"epoch": 0.7742198838896952,
|
|
"grad_norm": 4.3125,
|
|
"learning_rate": 0.0004947383777374462,
|
|
"loss": 5.5998,
|
|
"mean_token_accuracy": 0.1575216144323349,
|
|
"num_tokens": 17721009.0,
|
|
"step": 8535
|
|
},
|
|
{
|
|
"entropy": 5.730885696411133,
|
|
"epoch": 0.7746734397677794,
|
|
"grad_norm": 3.5,
|
|
"learning_rate": 0.0004947314189767058,
|
|
"loss": 5.6231,
|
|
"mean_token_accuracy": 0.16047685146331786,
|
|
"num_tokens": 17731821.0,
|
|
"step": 8540
|
|
},
|
|
{
|
|
"entropy": 5.712780427932739,
|
|
"epoch": 0.7751269956458636,
|
|
"grad_norm": 4.28125,
|
|
"learning_rate": 0.0004947244556718635,
|
|
"loss": 5.5151,
|
|
"mean_token_accuracy": 0.1676603823900223,
|
|
"num_tokens": 17741425.0,
|
|
"step": 8545
|
|
},
|
|
{
|
|
"entropy": 5.759090185165405,
|
|
"epoch": 0.7755805515239478,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004947174878230635,
|
|
"loss": 5.5761,
|
|
"mean_token_accuracy": 0.15907540917396545,
|
|
"num_tokens": 17752381.0,
|
|
"step": 8550
|
|
},
|
|
{
|
|
"entropy": 5.757405757904053,
|
|
"epoch": 0.7760341074020319,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004947105154304498,
|
|
"loss": 5.5515,
|
|
"mean_token_accuracy": 0.15621833950281144,
|
|
"num_tokens": 17762768.0,
|
|
"step": 8555
|
|
},
|
|
{
|
|
"entropy": 5.747535753250122,
|
|
"epoch": 0.7764876632801161,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004947035384941667,
|
|
"loss": 5.5911,
|
|
"mean_token_accuracy": 0.15688183903694153,
|
|
"num_tokens": 17774032.0,
|
|
"step": 8560
|
|
},
|
|
{
|
|
"entropy": 5.787305736541748,
|
|
"epoch": 0.7769412191582002,
|
|
"grad_norm": 3.046875,
|
|
"learning_rate": 0.0004946965570143584,
|
|
"loss": 5.7105,
|
|
"mean_token_accuracy": 0.14983301609754562,
|
|
"num_tokens": 17785098.0,
|
|
"step": 8565
|
|
},
|
|
{
|
|
"entropy": 5.8069006443023685,
|
|
"epoch": 0.7773947750362845,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004946895709911695,
|
|
"loss": 5.6007,
|
|
"mean_token_accuracy": 0.15720168501138687,
|
|
"num_tokens": 17795487.0,
|
|
"step": 8570
|
|
},
|
|
{
|
|
"entropy": 5.76495361328125,
|
|
"epoch": 0.7778483309143687,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004946825804247442,
|
|
"loss": 5.7118,
|
|
"mean_token_accuracy": 0.14942110031843187,
|
|
"num_tokens": 17806045.0,
|
|
"step": 8575
|
|
},
|
|
{
|
|
"entropy": 5.878367519378662,
|
|
"epoch": 0.7783018867924528,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.000494675585315227,
|
|
"loss": 5.6808,
|
|
"mean_token_accuracy": 0.15481762886047362,
|
|
"num_tokens": 17816948.0,
|
|
"step": 8580
|
|
},
|
|
{
|
|
"entropy": 5.813451194763184,
|
|
"epoch": 0.778755442670537,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.0004946685856627628,
|
|
"loss": 5.5921,
|
|
"mean_token_accuracy": 0.16048079282045363,
|
|
"num_tokens": 17826929.0,
|
|
"step": 8585
|
|
},
|
|
{
|
|
"entropy": 5.775233936309815,
|
|
"epoch": 0.7792089985486212,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004946615814674963,
|
|
"loss": 5.711,
|
|
"mean_token_accuracy": 0.15520803034305572,
|
|
"num_tokens": 17837780.0,
|
|
"step": 8590
|
|
},
|
|
{
|
|
"entropy": 5.691840076446534,
|
|
"epoch": 0.7796625544267054,
|
|
"grad_norm": 3.125,
|
|
"learning_rate": 0.0004946545727295724,
|
|
"loss": 5.464,
|
|
"mean_token_accuracy": 0.1652519851922989,
|
|
"num_tokens": 17847835.0,
|
|
"step": 8595
|
|
},
|
|
{
|
|
"entropy": 5.729661703109741,
|
|
"epoch": 0.7801161103047896,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004946475594491359,
|
|
"loss": 5.559,
|
|
"mean_token_accuracy": 0.16285682022571563,
|
|
"num_tokens": 17858324.0,
|
|
"step": 8600
|
|
},
|
|
{
|
|
"entropy": 5.791449785232544,
|
|
"epoch": 0.7805696661828737,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004946405416263319,
|
|
"loss": 5.6036,
|
|
"mean_token_accuracy": 0.15357813686132432,
|
|
"num_tokens": 17868455.0,
|
|
"step": 8605
|
|
},
|
|
{
|
|
"entropy": 5.839656734466553,
|
|
"epoch": 0.7810232220609579,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004946335192613054,
|
|
"loss": 5.6171,
|
|
"mean_token_accuracy": 0.15866965800523758,
|
|
"num_tokens": 17879038.0,
|
|
"step": 8610
|
|
},
|
|
{
|
|
"entropy": 5.6663342952728275,
|
|
"epoch": 0.7814767779390421,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004946264923542019,
|
|
"loss": 5.4686,
|
|
"mean_token_accuracy": 0.16128309816122055,
|
|
"num_tokens": 17888153.0,
|
|
"step": 8615
|
|
},
|
|
{
|
|
"entropy": 5.67993278503418,
|
|
"epoch": 0.7819303338171263,
|
|
"grad_norm": 3.046875,
|
|
"learning_rate": 0.0004946194609051664,
|
|
"loss": 5.6109,
|
|
"mean_token_accuracy": 0.16191176623106002,
|
|
"num_tokens": 17898289.0,
|
|
"step": 8620
|
|
},
|
|
{
|
|
"entropy": 5.754681921005249,
|
|
"epoch": 0.7823838896952104,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004946124249143447,
|
|
"loss": 5.6054,
|
|
"mean_token_accuracy": 0.15954133123159409,
|
|
"num_tokens": 17909192.0,
|
|
"step": 8625
|
|
},
|
|
{
|
|
"entropy": 5.712142086029052,
|
|
"epoch": 0.7828374455732946,
|
|
"grad_norm": 3.140625,
|
|
"learning_rate": 0.000494605384381882,
|
|
"loss": 5.5466,
|
|
"mean_token_accuracy": 0.15608295798301697,
|
|
"num_tokens": 17918937.0,
|
|
"step": 8630
|
|
},
|
|
{
|
|
"entropy": 5.738121271133423,
|
|
"epoch": 0.7832910014513788,
|
|
"grad_norm": 2.921875,
|
|
"learning_rate": 0.0004945983393079239,
|
|
"loss": 5.6076,
|
|
"mean_token_accuracy": 0.16086831092834472,
|
|
"num_tokens": 17929346.0,
|
|
"step": 8635
|
|
},
|
|
{
|
|
"entropy": 5.758172702789307,
|
|
"epoch": 0.783744557329463,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004945912896926163,
|
|
"loss": 5.5852,
|
|
"mean_token_accuracy": 0.16034913659095765,
|
|
"num_tokens": 17939479.0,
|
|
"step": 8640
|
|
},
|
|
{
|
|
"entropy": 5.853363275527954,
|
|
"epoch": 0.7841981132075472,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004945842355361049,
|
|
"loss": 5.6648,
|
|
"mean_token_accuracy": 0.15613145902752876,
|
|
"num_tokens": 17949841.0,
|
|
"step": 8645
|
|
},
|
|
{
|
|
"entropy": 5.746683597564697,
|
|
"epoch": 0.7846516690856313,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004945771768385355,
|
|
"loss": 5.6014,
|
|
"mean_token_accuracy": 0.1604134052991867,
|
|
"num_tokens": 17960334.0,
|
|
"step": 8650
|
|
},
|
|
{
|
|
"entropy": 5.675119495391845,
|
|
"epoch": 0.7851052249637155,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.000494570113600054,
|
|
"loss": 5.5415,
|
|
"mean_token_accuracy": 0.16287485212087632,
|
|
"num_tokens": 17970595.0,
|
|
"step": 8655
|
|
},
|
|
{
|
|
"entropy": 5.7526007175445555,
|
|
"epoch": 0.7855587808417998,
|
|
"grad_norm": 3.84375,
|
|
"learning_rate": 0.0004945630458208068,
|
|
"loss": 5.6828,
|
|
"mean_token_accuracy": 0.15230964571237565,
|
|
"num_tokens": 17981301.0,
|
|
"step": 8660
|
|
},
|
|
{
|
|
"entropy": 5.6740015029907225,
|
|
"epoch": 0.7860123367198839,
|
|
"grad_norm": 4.5,
|
|
"learning_rate": 0.0004945559735009397,
|
|
"loss": 5.5156,
|
|
"mean_token_accuracy": 0.16261018067598343,
|
|
"num_tokens": 17991262.0,
|
|
"step": 8665
|
|
},
|
|
{
|
|
"entropy": 5.749355220794678,
|
|
"epoch": 0.7864658925979681,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004945488966405993,
|
|
"loss": 5.566,
|
|
"mean_token_accuracy": 0.16028408706188202,
|
|
"num_tokens": 18001212.0,
|
|
"step": 8670
|
|
},
|
|
{
|
|
"entropy": 5.75854902267456,
|
|
"epoch": 0.7869194484760522,
|
|
"grad_norm": 3.171875,
|
|
"learning_rate": 0.0004945418152399317,
|
|
"loss": 5.5743,
|
|
"mean_token_accuracy": 0.1625185176730156,
|
|
"num_tokens": 18010432.0,
|
|
"step": 8675
|
|
},
|
|
{
|
|
"entropy": 5.762905740737915,
|
|
"epoch": 0.7873730043541364,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004945347292990833,
|
|
"loss": 5.6108,
|
|
"mean_token_accuracy": 0.15499364733695983,
|
|
"num_tokens": 18020902.0,
|
|
"step": 8680
|
|
},
|
|
{
|
|
"entropy": 5.739315366744995,
|
|
"epoch": 0.7878265602322206,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004945276388182008,
|
|
"loss": 5.4799,
|
|
"mean_token_accuracy": 0.1620177999138832,
|
|
"num_tokens": 18031133.0,
|
|
"step": 8685
|
|
},
|
|
{
|
|
"entropy": 5.8286998748779295,
|
|
"epoch": 0.7882801161103048,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004945205437974309,
|
|
"loss": 5.6143,
|
|
"mean_token_accuracy": 0.15827255249023436,
|
|
"num_tokens": 18042050.0,
|
|
"step": 8690
|
|
},
|
|
{
|
|
"entropy": 5.670088768005371,
|
|
"epoch": 0.788733671988389,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.0004945134442369201,
|
|
"loss": 5.5594,
|
|
"mean_token_accuracy": 0.16206253170967103,
|
|
"num_tokens": 18051642.0,
|
|
"step": 8695
|
|
},
|
|
{
|
|
"entropy": 5.752692031860351,
|
|
"epoch": 0.7891872278664731,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004945063401368154,
|
|
"loss": 5.6145,
|
|
"mean_token_accuracy": 0.15136099308729173,
|
|
"num_tokens": 18062180.0,
|
|
"step": 8700
|
|
},
|
|
{
|
|
"entropy": 5.785160160064697,
|
|
"epoch": 0.7896407837445574,
|
|
"grad_norm": 3.3125,
|
|
"learning_rate": 0.0004944992314972637,
|
|
"loss": 5.5671,
|
|
"mean_token_accuracy": 0.15702632069587708,
|
|
"num_tokens": 18072302.0,
|
|
"step": 8705
|
|
},
|
|
{
|
|
"entropy": 5.765988302230835,
|
|
"epoch": 0.7900943396226415,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.0004944921183184118,
|
|
"loss": 5.5781,
|
|
"mean_token_accuracy": 0.1638057678937912,
|
|
"num_tokens": 18081824.0,
|
|
"step": 8710
|
|
},
|
|
{
|
|
"entropy": 5.75767707824707,
|
|
"epoch": 0.7905478955007257,
|
|
"grad_norm": 3.84375,
|
|
"learning_rate": 0.000494485000600407,
|
|
"loss": 5.6276,
|
|
"mean_token_accuracy": 0.15722796022892,
|
|
"num_tokens": 18092696.0,
|
|
"step": 8715
|
|
},
|
|
{
|
|
"entropy": 5.683173036575317,
|
|
"epoch": 0.7910014513788098,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004944778783433965,
|
|
"loss": 5.5345,
|
|
"mean_token_accuracy": 0.1658234864473343,
|
|
"num_tokens": 18101790.0,
|
|
"step": 8720
|
|
},
|
|
{
|
|
"entropy": 5.7710024356842045,
|
|
"epoch": 0.791455007256894,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004944707515475276,
|
|
"loss": 5.6583,
|
|
"mean_token_accuracy": 0.15452334880828858,
|
|
"num_tokens": 18111572.0,
|
|
"step": 8725
|
|
},
|
|
{
|
|
"entropy": 5.827447557449341,
|
|
"epoch": 0.7919085631349783,
|
|
"grad_norm": 3.890625,
|
|
"learning_rate": 0.0004944636202129475,
|
|
"loss": 5.6427,
|
|
"mean_token_accuracy": 0.16203664243221283,
|
|
"num_tokens": 18120650.0,
|
|
"step": 8730
|
|
},
|
|
{
|
|
"entropy": 5.746698474884033,
|
|
"epoch": 0.7923621190130624,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004944564843398039,
|
|
"loss": 5.5385,
|
|
"mean_token_accuracy": 0.16859735995531083,
|
|
"num_tokens": 18131055.0,
|
|
"step": 8735
|
|
},
|
|
{
|
|
"entropy": 5.779311656951904,
|
|
"epoch": 0.7928156748911466,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004944493439282443,
|
|
"loss": 5.6266,
|
|
"mean_token_accuracy": 0.1563514158129692,
|
|
"num_tokens": 18141423.0,
|
|
"step": 8740
|
|
},
|
|
{
|
|
"entropy": 5.705952596664429,
|
|
"epoch": 0.7932692307692307,
|
|
"grad_norm": 3.375,
|
|
"learning_rate": 0.0004944421989784162,
|
|
"loss": 5.5581,
|
|
"mean_token_accuracy": 0.15892547070980073,
|
|
"num_tokens": 18152015.0,
|
|
"step": 8745
|
|
},
|
|
{
|
|
"entropy": 5.773093366622925,
|
|
"epoch": 0.793722786647315,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004944350494904676,
|
|
"loss": 5.6469,
|
|
"mean_token_accuracy": 0.15265853106975555,
|
|
"num_tokens": 18161934.0,
|
|
"step": 8750
|
|
},
|
|
{
|
|
"entropy": 5.790240049362183,
|
|
"epoch": 0.7941763425253991,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.0004944278954645463,
|
|
"loss": 5.5568,
|
|
"mean_token_accuracy": 0.16019119322299957,
|
|
"num_tokens": 18172287.0,
|
|
"step": 8755
|
|
},
|
|
{
|
|
"entropy": 5.752348232269287,
|
|
"epoch": 0.7946298984034833,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004944207369008002,
|
|
"loss": 5.6221,
|
|
"mean_token_accuracy": 0.1672727346420288,
|
|
"num_tokens": 18181015.0,
|
|
"step": 8760
|
|
},
|
|
{
|
|
"entropy": 5.778642749786377,
|
|
"epoch": 0.7950834542815675,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004944135737993773,
|
|
"loss": 5.6999,
|
|
"mean_token_accuracy": 0.15213402807712556,
|
|
"num_tokens": 18192382.0,
|
|
"step": 8765
|
|
},
|
|
{
|
|
"entropy": 5.7769043922424315,
|
|
"epoch": 0.7955370101596516,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004944064061604258,
|
|
"loss": 5.5714,
|
|
"mean_token_accuracy": 0.1669528529047966,
|
|
"num_tokens": 18202597.0,
|
|
"step": 8770
|
|
},
|
|
{
|
|
"entropy": 5.782745456695556,
|
|
"epoch": 0.7959905660377359,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004943992339840939,
|
|
"loss": 5.6143,
|
|
"mean_token_accuracy": 0.15483993738889695,
|
|
"num_tokens": 18213756.0,
|
|
"step": 8775
|
|
},
|
|
{
|
|
"entropy": 5.652510166168213,
|
|
"epoch": 0.79644412191582,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.00049439205727053,
|
|
"loss": 5.5573,
|
|
"mean_token_accuracy": 0.15681147426366807,
|
|
"num_tokens": 18223669.0,
|
|
"step": 8780
|
|
},
|
|
{
|
|
"entropy": 5.733938455581665,
|
|
"epoch": 0.7968976777939042,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004943848760198823,
|
|
"loss": 5.5877,
|
|
"mean_token_accuracy": 0.16213256418704985,
|
|
"num_tokens": 18234884.0,
|
|
"step": 8785
|
|
},
|
|
{
|
|
"entropy": 5.734215450286865,
|
|
"epoch": 0.7973512336719883,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004943776902322995,
|
|
"loss": 5.5166,
|
|
"mean_token_accuracy": 0.16281318217515944,
|
|
"num_tokens": 18245155.0,
|
|
"step": 8790
|
|
},
|
|
{
|
|
"entropy": 5.6022714138031,
|
|
"epoch": 0.7978047895500726,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004943704999079302,
|
|
"loss": 5.4641,
|
|
"mean_token_accuracy": 0.1630011886358261,
|
|
"num_tokens": 18254686.0,
|
|
"step": 8795
|
|
},
|
|
{
|
|
"entropy": 5.687679624557495,
|
|
"epoch": 0.7982583454281568,
|
|
"grad_norm": 2.96875,
|
|
"learning_rate": 0.0004943633050469231,
|
|
"loss": 5.4844,
|
|
"mean_token_accuracy": 0.1627473920583725,
|
|
"num_tokens": 18265473.0,
|
|
"step": 8800
|
|
},
|
|
{
|
|
"entropy": 5.779775762557984,
|
|
"epoch": 0.7987119013062409,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004943561056494269,
|
|
"loss": 5.6915,
|
|
"mean_token_accuracy": 0.1531972423195839,
|
|
"num_tokens": 18276024.0,
|
|
"step": 8805
|
|
},
|
|
{
|
|
"entropy": 5.760975074768067,
|
|
"epoch": 0.7991654571843251,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004943489017155906,
|
|
"loss": 5.6456,
|
|
"mean_token_accuracy": 0.14553324580192567,
|
|
"num_tokens": 18287261.0,
|
|
"step": 8810
|
|
},
|
|
{
|
|
"entropy": 5.757473945617676,
|
|
"epoch": 0.7996190130624092,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004943416932455631,
|
|
"loss": 5.6599,
|
|
"mean_token_accuracy": 0.15629383623600007,
|
|
"num_tokens": 18299374.0,
|
|
"step": 8815
|
|
},
|
|
{
|
|
"entropy": 5.683649587631225,
|
|
"epoch": 0.8000725689404935,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004943344802394935,
|
|
"loss": 5.612,
|
|
"mean_token_accuracy": 0.1526947721838951,
|
|
"num_tokens": 18309344.0,
|
|
"step": 8820
|
|
},
|
|
{
|
|
"entropy": 5.776987028121948,
|
|
"epoch": 0.8005261248185777,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004943272626975309,
|
|
"loss": 5.6144,
|
|
"mean_token_accuracy": 0.15544928908348082,
|
|
"num_tokens": 18319778.0,
|
|
"step": 8825
|
|
},
|
|
{
|
|
"entropy": 5.779241418838501,
|
|
"epoch": 0.8009796806966618,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004943200406198246,
|
|
"loss": 5.61,
|
|
"mean_token_accuracy": 0.1576782390475273,
|
|
"num_tokens": 18329787.0,
|
|
"step": 8830
|
|
},
|
|
{
|
|
"entropy": 5.666056108474732,
|
|
"epoch": 0.801433236574746,
|
|
"grad_norm": 3.953125,
|
|
"learning_rate": 0.000494312814006524,
|
|
"loss": 5.5551,
|
|
"mean_token_accuracy": 0.1649927094578743,
|
|
"num_tokens": 18340670.0,
|
|
"step": 8835
|
|
},
|
|
{
|
|
"entropy": 5.717959022521972,
|
|
"epoch": 0.8018867924528302,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004943055828577784,
|
|
"loss": 5.5826,
|
|
"mean_token_accuracy": 0.1525124877691269,
|
|
"num_tokens": 18352484.0,
|
|
"step": 8840
|
|
},
|
|
{
|
|
"entropy": 5.7433929443359375,
|
|
"epoch": 0.8023403483309144,
|
|
"grad_norm": 3.03125,
|
|
"learning_rate": 0.0004942983471737376,
|
|
"loss": 5.5262,
|
|
"mean_token_accuracy": 0.1591146096587181,
|
|
"num_tokens": 18363103.0,
|
|
"step": 8845
|
|
},
|
|
{
|
|
"entropy": 5.667786931991577,
|
|
"epoch": 0.8027939042089985,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004942911069545511,
|
|
"loss": 5.5843,
|
|
"mean_token_accuracy": 0.16140155047178267,
|
|
"num_tokens": 18373925.0,
|
|
"step": 8850
|
|
},
|
|
{
|
|
"entropy": 5.766671943664551,
|
|
"epoch": 0.8032474600870827,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004942838622003686,
|
|
"loss": 5.6506,
|
|
"mean_token_accuracy": 0.1573023408651352,
|
|
"num_tokens": 18384081.0,
|
|
"step": 8855
|
|
},
|
|
{
|
|
"entropy": 5.812975883483887,
|
|
"epoch": 0.8037010159651669,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004942766129113399,
|
|
"loss": 5.5441,
|
|
"mean_token_accuracy": 0.1619538903236389,
|
|
"num_tokens": 18392510.0,
|
|
"step": 8860
|
|
},
|
|
{
|
|
"entropy": 5.8084618091583256,
|
|
"epoch": 0.8041545718432511,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004942693590876151,
|
|
"loss": 5.6509,
|
|
"mean_token_accuracy": 0.15825066938996316,
|
|
"num_tokens": 18402809.0,
|
|
"step": 8865
|
|
},
|
|
{
|
|
"entropy": 5.805789184570313,
|
|
"epoch": 0.8046081277213353,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.000494262100729344,
|
|
"loss": 5.6909,
|
|
"mean_token_accuracy": 0.1581580124795437,
|
|
"num_tokens": 18413342.0,
|
|
"step": 8870
|
|
},
|
|
{
|
|
"entropy": 5.7798045635223385,
|
|
"epoch": 0.8050616835994194,
|
|
"grad_norm": 3.234375,
|
|
"learning_rate": 0.0004942548378366768,
|
|
"loss": 5.6826,
|
|
"mean_token_accuracy": 0.1586776688694954,
|
|
"num_tokens": 18424735.0,
|
|
"step": 8875
|
|
},
|
|
{
|
|
"entropy": 5.720227336883545,
|
|
"epoch": 0.8055152394775036,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004942475704097635,
|
|
"loss": 5.5634,
|
|
"mean_token_accuracy": 0.16137248426675796,
|
|
"num_tokens": 18434797.0,
|
|
"step": 8880
|
|
},
|
|
{
|
|
"entropy": 5.74770712852478,
|
|
"epoch": 0.8059687953555879,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.0004942402984487548,
|
|
"loss": 5.6327,
|
|
"mean_token_accuracy": 0.15215983539819716,
|
|
"num_tokens": 18445456.0,
|
|
"step": 8885
|
|
},
|
|
{
|
|
"entropy": 5.698119592666626,
|
|
"epoch": 0.806422351233672,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004942330219538008,
|
|
"loss": 5.5914,
|
|
"mean_token_accuracy": 0.1551514595746994,
|
|
"num_tokens": 18456728.0,
|
|
"step": 8890
|
|
},
|
|
{
|
|
"entropy": 5.965833568572998,
|
|
"epoch": 0.8068759071117562,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.000494225740925052,
|
|
"loss": 5.7198,
|
|
"mean_token_accuracy": 0.15536733493208885,
|
|
"num_tokens": 18468813.0,
|
|
"step": 8895
|
|
},
|
|
{
|
|
"entropy": 5.853075170516968,
|
|
"epoch": 0.8073294629898403,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004942184553626591,
|
|
"loss": 5.6342,
|
|
"mean_token_accuracy": 0.1581724092364311,
|
|
"num_tokens": 18477912.0,
|
|
"step": 8900
|
|
},
|
|
{
|
|
"entropy": 5.71473879814148,
|
|
"epoch": 0.8077830188679245,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004942111652667726,
|
|
"loss": 5.566,
|
|
"mean_token_accuracy": 0.16377193331718445,
|
|
"num_tokens": 18488115.0,
|
|
"step": 8905
|
|
},
|
|
{
|
|
"entropy": 5.696315670013428,
|
|
"epoch": 0.8082365747460087,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004942038706375433,
|
|
"loss": 5.6123,
|
|
"mean_token_accuracy": 0.15618089884519576,
|
|
"num_tokens": 18498853.0,
|
|
"step": 8910
|
|
},
|
|
{
|
|
"entropy": 5.74398775100708,
|
|
"epoch": 0.8086901306240929,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004941965714751222,
|
|
"loss": 5.6499,
|
|
"mean_token_accuracy": 0.15113084837794305,
|
|
"num_tokens": 18510047.0,
|
|
"step": 8915
|
|
},
|
|
{
|
|
"entropy": 5.7405627250671385,
|
|
"epoch": 0.809143686502177,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004941892677796601,
|
|
"loss": 5.6142,
|
|
"mean_token_accuracy": 0.16218534708023072,
|
|
"num_tokens": 18519673.0,
|
|
"step": 8920
|
|
},
|
|
{
|
|
"entropy": 5.759426736831665,
|
|
"epoch": 0.8095972423802612,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004941819595513081,
|
|
"loss": 5.6437,
|
|
"mean_token_accuracy": 0.1601275697350502,
|
|
"num_tokens": 18530090.0,
|
|
"step": 8925
|
|
},
|
|
{
|
|
"entropy": 5.853196859359741,
|
|
"epoch": 0.8100507982583455,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004941746467902173,
|
|
"loss": 5.6738,
|
|
"mean_token_accuracy": 0.1514594793319702,
|
|
"num_tokens": 18541862.0,
|
|
"step": 8930
|
|
},
|
|
{
|
|
"entropy": 5.817650413513183,
|
|
"epoch": 0.8105043541364296,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.000494167329496539,
|
|
"loss": 5.6518,
|
|
"mean_token_accuracy": 0.147237129509449,
|
|
"num_tokens": 18551624.0,
|
|
"step": 8935
|
|
},
|
|
{
|
|
"entropy": 5.733151960372925,
|
|
"epoch": 0.8109579100145138,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004941600076704244,
|
|
"loss": 5.6118,
|
|
"mean_token_accuracy": 0.1600864425301552,
|
|
"num_tokens": 18561784.0,
|
|
"step": 8940
|
|
},
|
|
{
|
|
"entropy": 5.7939455032348635,
|
|
"epoch": 0.8114114658925979,
|
|
"grad_norm": 6.4375,
|
|
"learning_rate": 0.0004941526813120251,
|
|
"loss": 5.6836,
|
|
"mean_token_accuracy": 0.15367743968963624,
|
|
"num_tokens": 18572110.0,
|
|
"step": 8945
|
|
},
|
|
{
|
|
"entropy": 5.769635391235352,
|
|
"epoch": 0.8118650217706821,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.0004941453504214924,
|
|
"loss": 5.6259,
|
|
"mean_token_accuracy": 0.1491383895277977,
|
|
"num_tokens": 18582012.0,
|
|
"step": 8950
|
|
},
|
|
{
|
|
"entropy": 5.6899253845214846,
|
|
"epoch": 0.8123185776487664,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004941380149989781,
|
|
"loss": 5.4788,
|
|
"mean_token_accuracy": 0.16632459461688995,
|
|
"num_tokens": 18592850.0,
|
|
"step": 8955
|
|
},
|
|
{
|
|
"entropy": 5.748365592956543,
|
|
"epoch": 0.8127721335268505,
|
|
"grad_norm": 4.21875,
|
|
"learning_rate": 0.0004941306750446336,
|
|
"loss": 5.645,
|
|
"mean_token_accuracy": 0.1560724064707756,
|
|
"num_tokens": 18602590.0,
|
|
"step": 8960
|
|
},
|
|
{
|
|
"entropy": 5.822504663467408,
|
|
"epoch": 0.8132256894049347,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.000494123330558611,
|
|
"loss": 5.5522,
|
|
"mean_token_accuracy": 0.15976229161024094,
|
|
"num_tokens": 18612607.0,
|
|
"step": 8965
|
|
},
|
|
{
|
|
"entropy": 5.706759023666382,
|
|
"epoch": 0.8136792452830188,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004941159815410622,
|
|
"loss": 5.5347,
|
|
"mean_token_accuracy": 0.1639419287443161,
|
|
"num_tokens": 18622936.0,
|
|
"step": 8970
|
|
},
|
|
{
|
|
"entropy": 5.783347320556641,
|
|
"epoch": 0.8141328011611031,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.000494108627992139,
|
|
"loss": 5.7089,
|
|
"mean_token_accuracy": 0.1504053518176079,
|
|
"num_tokens": 18633997.0,
|
|
"step": 8975
|
|
},
|
|
{
|
|
"entropy": 5.779018068313599,
|
|
"epoch": 0.8145863570391872,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004941012699119936,
|
|
"loss": 5.5268,
|
|
"mean_token_accuracy": 0.16512532979249955,
|
|
"num_tokens": 18644347.0,
|
|
"step": 8980
|
|
},
|
|
{
|
|
"entropy": 5.722207021713257,
|
|
"epoch": 0.8150399129172714,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004940939073007779,
|
|
"loss": 5.608,
|
|
"mean_token_accuracy": 0.1625707656145096,
|
|
"num_tokens": 18654989.0,
|
|
"step": 8985
|
|
},
|
|
{
|
|
"entropy": 5.705081415176392,
|
|
"epoch": 0.8154934687953556,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004940865401586446,
|
|
"loss": 5.5902,
|
|
"mean_token_accuracy": 0.15785395950078965,
|
|
"num_tokens": 18665526.0,
|
|
"step": 8990
|
|
},
|
|
{
|
|
"entropy": 5.767810583114624,
|
|
"epoch": 0.8159470246734397,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004940791684857458,
|
|
"loss": 5.591,
|
|
"mean_token_accuracy": 0.16355077922344208,
|
|
"num_tokens": 18676226.0,
|
|
"step": 8995
|
|
},
|
|
{
|
|
"entropy": 5.763008880615234,
|
|
"epoch": 0.816400580551524,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.0004940717922822339,
|
|
"loss": 5.5201,
|
|
"mean_token_accuracy": 0.16101572811603546,
|
|
"num_tokens": 18686499.0,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"epoch": 0.816400580551524,
|
|
"eval_entropy": 5.6369146356755255,
|
|
"eval_loss": 5.623342037200928,
|
|
"eval_mean_token_accuracy": 0.16392953284590492,
|
|
"eval_num_tokens": 18686499.0,
|
|
"eval_runtime": 26.5654,
|
|
"eval_samples_per_second": 1331.054,
|
|
"eval_steps_per_second": 166.382,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"entropy": 5.817816591262817,
|
|
"epoch": 0.8168541364296081,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004940644115482615,
|
|
"loss": 5.5755,
|
|
"mean_token_accuracy": 0.15483485758304597,
|
|
"num_tokens": 18696543.0,
|
|
"step": 9005
|
|
},
|
|
{
|
|
"entropy": 5.739165878295898,
|
|
"epoch": 0.8173076923076923,
|
|
"grad_norm": 3.03125,
|
|
"learning_rate": 0.0004940570262839812,
|
|
"loss": 5.6248,
|
|
"mean_token_accuracy": 0.15578402876853942,
|
|
"num_tokens": 18707029.0,
|
|
"step": 9010
|
|
},
|
|
{
|
|
"entropy": 5.700997400283813,
|
|
"epoch": 0.8177612481857764,
|
|
"grad_norm": 3.390625,
|
|
"learning_rate": 0.0004940496364895457,
|
|
"loss": 5.5984,
|
|
"mean_token_accuracy": 0.15963526517152787,
|
|
"num_tokens": 18716937.0,
|
|
"step": 9015
|
|
},
|
|
{
|
|
"entropy": 5.836496305465698,
|
|
"epoch": 0.8182148040638607,
|
|
"grad_norm": 2.9375,
|
|
"learning_rate": 0.0004940422421651082,
|
|
"loss": 5.6054,
|
|
"mean_token_accuracy": 0.155541530251503,
|
|
"num_tokens": 18727478.0,
|
|
"step": 9020
|
|
},
|
|
{
|
|
"entropy": 5.773825407028198,
|
|
"epoch": 0.8186683599419449,
|
|
"grad_norm": 3.71875,
|
|
"learning_rate": 0.0004940348433108211,
|
|
"loss": 5.534,
|
|
"mean_token_accuracy": 0.15683292895555495,
|
|
"num_tokens": 18737339.0,
|
|
"step": 9025
|
|
},
|
|
{
|
|
"entropy": 5.76012864112854,
|
|
"epoch": 0.819121915820029,
|
|
"grad_norm": 3.4375,
|
|
"learning_rate": 0.0004940274399268377,
|
|
"loss": 5.6461,
|
|
"mean_token_accuracy": 0.15859430581331252,
|
|
"num_tokens": 18747810.0,
|
|
"step": 9030
|
|
},
|
|
{
|
|
"entropy": 5.7201563835144045,
|
|
"epoch": 0.8195754716981132,
|
|
"grad_norm": 2.890625,
|
|
"learning_rate": 0.0004940200320133109,
|
|
"loss": 5.6026,
|
|
"mean_token_accuracy": 0.15753963589668274,
|
|
"num_tokens": 18757564.0,
|
|
"step": 9035
|
|
},
|
|
{
|
|
"entropy": 5.826656293869019,
|
|
"epoch": 0.8200290275761973,
|
|
"grad_norm": 3.515625,
|
|
"learning_rate": 0.0004940126195703941,
|
|
"loss": 5.6441,
|
|
"mean_token_accuracy": 0.1551142916083336,
|
|
"num_tokens": 18768196.0,
|
|
"step": 9040
|
|
},
|
|
{
|
|
"entropy": 5.777300500869751,
|
|
"epoch": 0.8204825834542816,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004940052025982405,
|
|
"loss": 5.6037,
|
|
"mean_token_accuracy": 0.16952395364642142,
|
|
"num_tokens": 18778350.0,
|
|
"step": 9045
|
|
},
|
|
{
|
|
"entropy": 5.706444454193115,
|
|
"epoch": 0.8209361393323658,
|
|
"grad_norm": 4.03125,
|
|
"learning_rate": 0.0004939977810970035,
|
|
"loss": 5.5719,
|
|
"mean_token_accuracy": 0.1516242131590843,
|
|
"num_tokens": 18789825.0,
|
|
"step": 9050
|
|
},
|
|
{
|
|
"entropy": 5.7588112354278564,
|
|
"epoch": 0.8213896952104499,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004939903550668366,
|
|
"loss": 5.5604,
|
|
"mean_token_accuracy": 0.16441161632537843,
|
|
"num_tokens": 18799793.0,
|
|
"step": 9055
|
|
},
|
|
{
|
|
"entropy": 5.769938850402832,
|
|
"epoch": 0.8218432510885341,
|
|
"grad_norm": 3.0625,
|
|
"learning_rate": 0.0004939829245078934,
|
|
"loss": 5.5994,
|
|
"mean_token_accuracy": 0.1649863064289093,
|
|
"num_tokens": 18809771.0,
|
|
"step": 9060
|
|
},
|
|
{
|
|
"entropy": 5.803665351867676,
|
|
"epoch": 0.8222968069666183,
|
|
"grad_norm": 3.046875,
|
|
"learning_rate": 0.0004939754894203275,
|
|
"loss": 5.6341,
|
|
"mean_token_accuracy": 0.15761773735284806,
|
|
"num_tokens": 18820529.0,
|
|
"step": 9065
|
|
},
|
|
{
|
|
"entropy": 5.682855939865112,
|
|
"epoch": 0.8227503628447025,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004939680498042926,
|
|
"loss": 5.5454,
|
|
"mean_token_accuracy": 0.16316016316413878,
|
|
"num_tokens": 18830797.0,
|
|
"step": 9070
|
|
},
|
|
{
|
|
"entropy": 5.699505949020386,
|
|
"epoch": 0.8232039187227866,
|
|
"grad_norm": 3.25,
|
|
"learning_rate": 0.0004939606056599428,
|
|
"loss": 5.5318,
|
|
"mean_token_accuracy": 0.16317757368087768,
|
|
"num_tokens": 18840526.0,
|
|
"step": 9075
|
|
},
|
|
{
|
|
"entropy": 5.711125898361206,
|
|
"epoch": 0.8236574746008708,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.0004939531569874316,
|
|
"loss": 5.5819,
|
|
"mean_token_accuracy": 0.15702107697725295,
|
|
"num_tokens": 18851201.0,
|
|
"step": 9080
|
|
},
|
|
{
|
|
"entropy": 5.641006708145142,
|
|
"epoch": 0.824111030478955,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.0004939457037869135,
|
|
"loss": 5.4049,
|
|
"mean_token_accuracy": 0.1740737020969391,
|
|
"num_tokens": 18861676.0,
|
|
"step": 9085
|
|
},
|
|
{
|
|
"entropy": 5.730075979232788,
|
|
"epoch": 0.8245645863570392,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004939382460585424,
|
|
"loss": 5.5441,
|
|
"mean_token_accuracy": 0.15687401816248894,
|
|
"num_tokens": 18872669.0,
|
|
"step": 9090
|
|
},
|
|
{
|
|
"entropy": 5.714040613174438,
|
|
"epoch": 0.8250181422351234,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004939307838024726,
|
|
"loss": 5.5706,
|
|
"mean_token_accuracy": 0.15572380945086478,
|
|
"num_tokens": 18882130.0,
|
|
"step": 9095
|
|
},
|
|
{
|
|
"entropy": 5.631939125061035,
|
|
"epoch": 0.8254716981132075,
|
|
"grad_norm": 2.9375,
|
|
"learning_rate": 0.0004939233170188585,
|
|
"loss": 5.5617,
|
|
"mean_token_accuracy": 0.15604794025421143,
|
|
"num_tokens": 18892457.0,
|
|
"step": 9100
|
|
},
|
|
{
|
|
"entropy": 5.771270513534546,
|
|
"epoch": 0.8259252539912917,
|
|
"grad_norm": 3.703125,
|
|
"learning_rate": 0.0004939158457078543,
|
|
"loss": 5.6066,
|
|
"mean_token_accuracy": 0.15698639452457427,
|
|
"num_tokens": 18903152.0,
|
|
"step": 9105
|
|
},
|
|
{
|
|
"entropy": 5.78275089263916,
|
|
"epoch": 0.826378809869376,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004939083698696146,
|
|
"loss": 5.5744,
|
|
"mean_token_accuracy": 0.15530361384153366,
|
|
"num_tokens": 18913740.0,
|
|
"step": 9110
|
|
},
|
|
{
|
|
"entropy": 5.78138952255249,
|
|
"epoch": 0.8268323657474601,
|
|
"grad_norm": 3.15625,
|
|
"learning_rate": 0.000493900889504294,
|
|
"loss": 5.5946,
|
|
"mean_token_accuracy": 0.16213588267564774,
|
|
"num_tokens": 18923501.0,
|
|
"step": 9115
|
|
},
|
|
{
|
|
"entropy": 5.702118158340454,
|
|
"epoch": 0.8272859216255443,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004938934046120473,
|
|
"loss": 5.6026,
|
|
"mean_token_accuracy": 0.1605318397283554,
|
|
"num_tokens": 18933255.0,
|
|
"step": 9120
|
|
},
|
|
{
|
|
"entropy": 5.693322229385376,
|
|
"epoch": 0.8277394775036284,
|
|
"grad_norm": 3.703125,
|
|
"learning_rate": 0.0004938859151930293,
|
|
"loss": 5.5478,
|
|
"mean_token_accuracy": 0.15757299363613128,
|
|
"num_tokens": 18943649.0,
|
|
"step": 9125
|
|
},
|
|
{
|
|
"entropy": 5.7299051761627195,
|
|
"epoch": 0.8281930333817126,
|
|
"grad_norm": 2.96875,
|
|
"learning_rate": 0.0004938784212473947,
|
|
"loss": 5.4603,
|
|
"mean_token_accuracy": 0.16884246915578843,
|
|
"num_tokens": 18953187.0,
|
|
"step": 9130
|
|
},
|
|
{
|
|
"entropy": 5.765360021591187,
|
|
"epoch": 0.8286465892597968,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004938709227752985,
|
|
"loss": 5.595,
|
|
"mean_token_accuracy": 0.15831910371780394,
|
|
"num_tokens": 18963015.0,
|
|
"step": 9135
|
|
},
|
|
{
|
|
"entropy": 5.7553094863891605,
|
|
"epoch": 0.829100145137881,
|
|
"grad_norm": 3.40625,
|
|
"learning_rate": 0.000493863419776896,
|
|
"loss": 5.627,
|
|
"mean_token_accuracy": 0.15628043413162232,
|
|
"num_tokens": 18974184.0,
|
|
"step": 9140
|
|
},
|
|
{
|
|
"entropy": 5.749017238616943,
|
|
"epoch": 0.8295537010159652,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004938559122523421,
|
|
"loss": 5.5612,
|
|
"mean_token_accuracy": 0.1613053262233734,
|
|
"num_tokens": 18985036.0,
|
|
"step": 9145
|
|
},
|
|
{
|
|
"entropy": 5.7774396419525145,
|
|
"epoch": 0.8300072568940493,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004938484002017921,
|
|
"loss": 5.6773,
|
|
"mean_token_accuracy": 0.15834735259413718,
|
|
"num_tokens": 18995237.0,
|
|
"step": 9150
|
|
},
|
|
{
|
|
"entropy": 5.766202640533447,
|
|
"epoch": 0.8304608127721336,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004938408836254015,
|
|
"loss": 5.6776,
|
|
"mean_token_accuracy": 0.1517545685172081,
|
|
"num_tokens": 19006272.0,
|
|
"step": 9155
|
|
},
|
|
{
|
|
"entropy": 5.769583988189697,
|
|
"epoch": 0.8309143686502177,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004938333625233258,
|
|
"loss": 5.5774,
|
|
"mean_token_accuracy": 0.16345404535532,
|
|
"num_tokens": 19016728.0,
|
|
"step": 9160
|
|
},
|
|
{
|
|
"entropy": 5.804753589630127,
|
|
"epoch": 0.8313679245283019,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004938258368957202,
|
|
"loss": 5.6229,
|
|
"mean_token_accuracy": 0.1492130547761917,
|
|
"num_tokens": 19028024.0,
|
|
"step": 9165
|
|
},
|
|
{
|
|
"entropy": 5.705556631088257,
|
|
"epoch": 0.831821480406386,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.0004938183067427406,
|
|
"loss": 5.569,
|
|
"mean_token_accuracy": 0.16102189272642137,
|
|
"num_tokens": 19038218.0,
|
|
"step": 9170
|
|
},
|
|
{
|
|
"entropy": 5.73623366355896,
|
|
"epoch": 0.8322750362844702,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004938107720645426,
|
|
"loss": 5.6151,
|
|
"mean_token_accuracy": 0.15558057129383088,
|
|
"num_tokens": 19048574.0,
|
|
"step": 9175
|
|
},
|
|
{
|
|
"entropy": 5.722246265411377,
|
|
"epoch": 0.8327285921625545,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004938032328612821,
|
|
"loss": 5.5654,
|
|
"mean_token_accuracy": 0.1594732940196991,
|
|
"num_tokens": 19057721.0,
|
|
"step": 9180
|
|
},
|
|
{
|
|
"entropy": 5.722181415557861,
|
|
"epoch": 0.8331821480406386,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.000493795689133115,
|
|
"loss": 5.5392,
|
|
"mean_token_accuracy": 0.15584656447172165,
|
|
"num_tokens": 19067582.0,
|
|
"step": 9185
|
|
},
|
|
{
|
|
"entropy": 5.744951963424683,
|
|
"epoch": 0.8336357039187228,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004937881408801974,
|
|
"loss": 5.5154,
|
|
"mean_token_accuracy": 0.16396791636943817,
|
|
"num_tokens": 19077896.0,
|
|
"step": 9190
|
|
},
|
|
{
|
|
"entropy": 5.7140114307403564,
|
|
"epoch": 0.8340892597968069,
|
|
"grad_norm": 3.078125,
|
|
"learning_rate": 0.000493780588102685,
|
|
"loss": 5.624,
|
|
"mean_token_accuracy": 0.16210134625434874,
|
|
"num_tokens": 19088082.0,
|
|
"step": 9195
|
|
},
|
|
{
|
|
"entropy": 5.745390796661377,
|
|
"epoch": 0.8345428156748912,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004937730308007346,
|
|
"loss": 5.644,
|
|
"mean_token_accuracy": 0.1585428848862648,
|
|
"num_tokens": 19097176.0,
|
|
"step": 9200
|
|
},
|
|
{
|
|
"entropy": 5.733397197723389,
|
|
"epoch": 0.8349963715529753,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004937654689745021,
|
|
"loss": 5.5128,
|
|
"mean_token_accuracy": 0.16180942207574844,
|
|
"num_tokens": 19107835.0,
|
|
"step": 9205
|
|
},
|
|
{
|
|
"entropy": 5.687448883056641,
|
|
"epoch": 0.8354499274310595,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.0004937579026241439,
|
|
"loss": 5.5533,
|
|
"mean_token_accuracy": 0.168113674223423,
|
|
"num_tokens": 19118028.0,
|
|
"step": 9210
|
|
},
|
|
{
|
|
"entropy": 5.810259914398193,
|
|
"epoch": 0.8359034833091437,
|
|
"grad_norm": 3.171875,
|
|
"learning_rate": 0.0004937503317498165,
|
|
"loss": 5.5753,
|
|
"mean_token_accuracy": 0.1633436366915703,
|
|
"num_tokens": 19129223.0,
|
|
"step": 9215
|
|
},
|
|
{
|
|
"entropy": 5.754411125183106,
|
|
"epoch": 0.8363570391872278,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.0004937427563516765,
|
|
"loss": 5.689,
|
|
"mean_token_accuracy": 0.15266440957784652,
|
|
"num_tokens": 19140048.0,
|
|
"step": 9220
|
|
},
|
|
{
|
|
"entropy": 5.7923585891723635,
|
|
"epoch": 0.8368105950653121,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004937351764298805,
|
|
"loss": 5.6374,
|
|
"mean_token_accuracy": 0.15430614799261094,
|
|
"num_tokens": 19150853.0,
|
|
"step": 9225
|
|
},
|
|
{
|
|
"entropy": 5.826929521560669,
|
|
"epoch": 0.8372641509433962,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004937275919845855,
|
|
"loss": 5.6204,
|
|
"mean_token_accuracy": 0.1584586724638939,
|
|
"num_tokens": 19161645.0,
|
|
"step": 9230
|
|
},
|
|
{
|
|
"entropy": 5.775044536590576,
|
|
"epoch": 0.8377177068214804,
|
|
"grad_norm": 4.71875,
|
|
"learning_rate": 0.0004937200030159481,
|
|
"loss": 5.7128,
|
|
"mean_token_accuracy": 0.15140248835086823,
|
|
"num_tokens": 19173276.0,
|
|
"step": 9235
|
|
},
|
|
{
|
|
"entropy": 5.768987226486206,
|
|
"epoch": 0.8381712626995645,
|
|
"grad_norm": 3.359375,
|
|
"learning_rate": 0.0004937124095241252,
|
|
"loss": 5.604,
|
|
"mean_token_accuracy": 0.16828205436468124,
|
|
"num_tokens": 19182949.0,
|
|
"step": 9240
|
|
},
|
|
{
|
|
"entropy": 5.805392265319824,
|
|
"epoch": 0.8386248185776488,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004937048115092739,
|
|
"loss": 5.6019,
|
|
"mean_token_accuracy": 0.15694086402654647,
|
|
"num_tokens": 19193504.0,
|
|
"step": 9245
|
|
},
|
|
{
|
|
"entropy": 5.734280157089233,
|
|
"epoch": 0.839078374455733,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004936972089715515,
|
|
"loss": 5.6733,
|
|
"mean_token_accuracy": 0.1565796509385109,
|
|
"num_tokens": 19203406.0,
|
|
"step": 9250
|
|
},
|
|
{
|
|
"entropy": 5.734476518630982,
|
|
"epoch": 0.8395319303338171,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.000493689601911115,
|
|
"loss": 5.6185,
|
|
"mean_token_accuracy": 0.1577702283859253,
|
|
"num_tokens": 19214325.0,
|
|
"step": 9255
|
|
},
|
|
{
|
|
"entropy": 5.787727499008179,
|
|
"epoch": 0.8399854862119013,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004936819903281219,
|
|
"loss": 5.6783,
|
|
"mean_token_accuracy": 0.14243353828787803,
|
|
"num_tokens": 19226466.0,
|
|
"step": 9260
|
|
},
|
|
{
|
|
"entropy": 5.86283655166626,
|
|
"epoch": 0.8404390420899854,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004936743742227295,
|
|
"loss": 5.6839,
|
|
"mean_token_accuracy": 0.152733413875103,
|
|
"num_tokens": 19237032.0,
|
|
"step": 9265
|
|
},
|
|
{
|
|
"entropy": 5.817492818832397,
|
|
"epoch": 0.8408925979680697,
|
|
"grad_norm": 6.15625,
|
|
"learning_rate": 0.0004936667535950952,
|
|
"loss": 5.6543,
|
|
"mean_token_accuracy": 0.15452442169189454,
|
|
"num_tokens": 19248009.0,
|
|
"step": 9270
|
|
},
|
|
{
|
|
"entropy": 5.767586946487427,
|
|
"epoch": 0.8413461538461539,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004936591284453768,
|
|
"loss": 5.7152,
|
|
"mean_token_accuracy": 0.15429175347089769,
|
|
"num_tokens": 19259363.0,
|
|
"step": 9275
|
|
},
|
|
{
|
|
"entropy": 5.757781314849853,
|
|
"epoch": 0.841799709724238,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.0004936514987737319,
|
|
"loss": 5.6246,
|
|
"mean_token_accuracy": 0.16044942736625672,
|
|
"num_tokens": 19269191.0,
|
|
"step": 9280
|
|
},
|
|
{
|
|
"entropy": 5.807770919799805,
|
|
"epoch": 0.8422532656023222,
|
|
"grad_norm": 4.1875,
|
|
"learning_rate": 0.0004936438645803182,
|
|
"loss": 5.5832,
|
|
"mean_token_accuracy": 0.15567334443330766,
|
|
"num_tokens": 19280278.0,
|
|
"step": 9285
|
|
},
|
|
{
|
|
"entropy": 5.777957773208618,
|
|
"epoch": 0.8427068214804064,
|
|
"grad_norm": 2.875,
|
|
"learning_rate": 0.0004936362258652938,
|
|
"loss": 5.5701,
|
|
"mean_token_accuracy": 0.16172982901334762,
|
|
"num_tokens": 19290130.0,
|
|
"step": 9290
|
|
},
|
|
{
|
|
"entropy": 5.857109832763672,
|
|
"epoch": 0.8431603773584906,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.0004936285826288165,
|
|
"loss": 5.6937,
|
|
"mean_token_accuracy": 0.1566224828362465,
|
|
"num_tokens": 19301669.0,
|
|
"step": 9295
|
|
},
|
|
{
|
|
"entropy": 5.769848203659057,
|
|
"epoch": 0.8436139332365747,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.0004936209348710444,
|
|
"loss": 5.556,
|
|
"mean_token_accuracy": 0.15982683897018432,
|
|
"num_tokens": 19312490.0,
|
|
"step": 9300
|
|
},
|
|
{
|
|
"entropy": 5.7307251453399655,
|
|
"epoch": 0.8440674891146589,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004936132825921355,
|
|
"loss": 5.5701,
|
|
"mean_token_accuracy": 0.15789439529180527,
|
|
"num_tokens": 19321743.0,
|
|
"step": 9305
|
|
},
|
|
{
|
|
"entropy": 5.725941324234009,
|
|
"epoch": 0.844521044992743,
|
|
"grad_norm": 3.4375,
|
|
"learning_rate": 0.0004936056257922484,
|
|
"loss": 5.5126,
|
|
"mean_token_accuracy": 0.16308728158473967,
|
|
"num_tokens": 19332149.0,
|
|
"step": 9310
|
|
},
|
|
{
|
|
"entropy": 5.755089521408081,
|
|
"epoch": 0.8449746008708273,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004935979644715412,
|
|
"loss": 5.5952,
|
|
"mean_token_accuracy": 0.1567418172955513,
|
|
"num_tokens": 19341655.0,
|
|
"step": 9315
|
|
},
|
|
{
|
|
"entropy": 5.77250919342041,
|
|
"epoch": 0.8454281567489115,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.0004935902986301724,
|
|
"loss": 5.6526,
|
|
"mean_token_accuracy": 0.15206657946109772,
|
|
"num_tokens": 19351404.0,
|
|
"step": 9320
|
|
},
|
|
{
|
|
"entropy": 5.7975561141967775,
|
|
"epoch": 0.8458817126269956,
|
|
"grad_norm": 3.890625,
|
|
"learning_rate": 0.0004935826282683005,
|
|
"loss": 5.6612,
|
|
"mean_token_accuracy": 0.15495891496539116,
|
|
"num_tokens": 19361788.0,
|
|
"step": 9325
|
|
},
|
|
{
|
|
"entropy": 5.779434776306152,
|
|
"epoch": 0.8463352685050798,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004935749533860842,
|
|
"loss": 5.6159,
|
|
"mean_token_accuracy": 0.15860703438520432,
|
|
"num_tokens": 19372902.0,
|
|
"step": 9330
|
|
},
|
|
{
|
|
"entropy": 5.645456600189209,
|
|
"epoch": 0.846788824383164,
|
|
"grad_norm": 2.921875,
|
|
"learning_rate": 0.000493567273983682,
|
|
"loss": 5.5154,
|
|
"mean_token_accuracy": 0.15727826803922654,
|
|
"num_tokens": 19382181.0,
|
|
"step": 9335
|
|
},
|
|
{
|
|
"entropy": 5.731950759887695,
|
|
"epoch": 0.8472423802612482,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.000493559590061253,
|
|
"loss": 5.576,
|
|
"mean_token_accuracy": 0.15466594845056533,
|
|
"num_tokens": 19393692.0,
|
|
"step": 9340
|
|
},
|
|
{
|
|
"entropy": 5.814303874969482,
|
|
"epoch": 0.8476959361393324,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004935519016189559,
|
|
"loss": 5.6323,
|
|
"mean_token_accuracy": 0.16125756055116652,
|
|
"num_tokens": 19404587.0,
|
|
"step": 9345
|
|
},
|
|
{
|
|
"entropy": 5.773672151565552,
|
|
"epoch": 0.8481494920174165,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004935442086569498,
|
|
"loss": 5.5945,
|
|
"mean_token_accuracy": 0.16004501432180404,
|
|
"num_tokens": 19415296.0,
|
|
"step": 9350
|
|
},
|
|
{
|
|
"entropy": 5.815304565429687,
|
|
"epoch": 0.8486030478955007,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004935365111753939,
|
|
"loss": 5.6522,
|
|
"mean_token_accuracy": 0.1567445993423462,
|
|
"num_tokens": 19426119.0,
|
|
"step": 9355
|
|
},
|
|
{
|
|
"entropy": 5.729464673995972,
|
|
"epoch": 0.8490566037735849,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004935288091744472,
|
|
"loss": 5.6453,
|
|
"mean_token_accuracy": 0.15719407945871353,
|
|
"num_tokens": 19436828.0,
|
|
"step": 9360
|
|
},
|
|
{
|
|
"entropy": 5.824829339981079,
|
|
"epoch": 0.8495101596516691,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.000493521102654269,
|
|
"loss": 5.6291,
|
|
"mean_token_accuracy": 0.1546254500746727,
|
|
"num_tokens": 19446583.0,
|
|
"step": 9365
|
|
},
|
|
{
|
|
"entropy": 5.750776529312134,
|
|
"epoch": 0.8499637155297532,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.0004935133916150187,
|
|
"loss": 5.5096,
|
|
"mean_token_accuracy": 0.16342067420482637,
|
|
"num_tokens": 19456757.0,
|
|
"step": 9370
|
|
},
|
|
{
|
|
"entropy": 5.67431116104126,
|
|
"epoch": 0.8504172714078374,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004935056760568558,
|
|
"loss": 5.5812,
|
|
"mean_token_accuracy": 0.15201431289315223,
|
|
"num_tokens": 19467624.0,
|
|
"step": 9375
|
|
},
|
|
{
|
|
"entropy": 5.757168245315552,
|
|
"epoch": 0.8508708272859217,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.0004934979559799399,
|
|
"loss": 5.5519,
|
|
"mean_token_accuracy": 0.1622839942574501,
|
|
"num_tokens": 19477759.0,
|
|
"step": 9380
|
|
},
|
|
{
|
|
"entropy": 5.756598377227784,
|
|
"epoch": 0.8513243831640058,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004934902313844306,
|
|
"loss": 5.5498,
|
|
"mean_token_accuracy": 0.16221508383750916,
|
|
"num_tokens": 19488877.0,
|
|
"step": 9385
|
|
},
|
|
{
|
|
"entropy": 5.7676917552948,
|
|
"epoch": 0.85177793904209,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.0004934825022704875,
|
|
"loss": 5.5568,
|
|
"mean_token_accuracy": 0.15808007270097732,
|
|
"num_tokens": 19499170.0,
|
|
"step": 9390
|
|
},
|
|
{
|
|
"entropy": 5.733283805847168,
|
|
"epoch": 0.8522314949201741,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004934747686382707,
|
|
"loss": 5.5859,
|
|
"mean_token_accuracy": 0.15336165130138396,
|
|
"num_tokens": 19509944.0,
|
|
"step": 9395
|
|
},
|
|
{
|
|
"entropy": 5.714533138275146,
|
|
"epoch": 0.8526850507982583,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004934670304879398,
|
|
"loss": 5.5324,
|
|
"mean_token_accuracy": 0.1617138996720314,
|
|
"num_tokens": 19519014.0,
|
|
"step": 9400
|
|
},
|
|
{
|
|
"entropy": 5.703343152999878,
|
|
"epoch": 0.8531386066763426,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004934592878196553,
|
|
"loss": 5.5446,
|
|
"mean_token_accuracy": 0.15980782061815263,
|
|
"num_tokens": 19528586.0,
|
|
"step": 9405
|
|
},
|
|
{
|
|
"entropy": 5.8032831192016605,
|
|
"epoch": 0.8535921625544267,
|
|
"grad_norm": 3.6875,
|
|
"learning_rate": 0.000493451540633577,
|
|
"loss": 5.6744,
|
|
"mean_token_accuracy": 0.1544887661933899,
|
|
"num_tokens": 19539912.0,
|
|
"step": 9410
|
|
},
|
|
{
|
|
"entropy": 5.776127529144287,
|
|
"epoch": 0.8540457184325109,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004934437889298651,
|
|
"loss": 5.6511,
|
|
"mean_token_accuracy": 0.15238273590803147,
|
|
"num_tokens": 19549860.0,
|
|
"step": 9415
|
|
},
|
|
{
|
|
"entropy": 5.755376482009888,
|
|
"epoch": 0.854499274310595,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004934360327086799,
|
|
"loss": 5.5839,
|
|
"mean_token_accuracy": 0.1571463868021965,
|
|
"num_tokens": 19559446.0,
|
|
"step": 9420
|
|
},
|
|
{
|
|
"entropy": 5.842705297470093,
|
|
"epoch": 0.8549528301886793,
|
|
"grad_norm": 3.984375,
|
|
"learning_rate": 0.000493428271970182,
|
|
"loss": 5.6348,
|
|
"mean_token_accuracy": 0.15561892539262773,
|
|
"num_tokens": 19570282.0,
|
|
"step": 9425
|
|
},
|
|
{
|
|
"entropy": 5.7355493068695065,
|
|
"epoch": 0.8554063860667634,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004934205067145318,
|
|
"loss": 5.5537,
|
|
"mean_token_accuracy": 0.15673677921295165,
|
|
"num_tokens": 19581087.0,
|
|
"step": 9430
|
|
},
|
|
{
|
|
"entropy": 5.706883716583252,
|
|
"epoch": 0.8558599419448476,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004934127369418898,
|
|
"loss": 5.6336,
|
|
"mean_token_accuracy": 0.1586183339357376,
|
|
"num_tokens": 19592100.0,
|
|
"step": 9435
|
|
},
|
|
{
|
|
"entropy": 5.71931266784668,
|
|
"epoch": 0.8563134978229318,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004934049626524168,
|
|
"loss": 5.6107,
|
|
"mean_token_accuracy": 0.15727198272943496,
|
|
"num_tokens": 19602557.0,
|
|
"step": 9440
|
|
},
|
|
{
|
|
"entropy": 5.828099536895752,
|
|
"epoch": 0.8567670537010159,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004933971838462734,
|
|
"loss": 5.6346,
|
|
"mean_token_accuracy": 0.15088815689086915,
|
|
"num_tokens": 19613643.0,
|
|
"step": 9445
|
|
},
|
|
{
|
|
"entropy": 5.781843185424805,
|
|
"epoch": 0.8572206095791002,
|
|
"grad_norm": 3.390625,
|
|
"learning_rate": 0.0004933894005236207,
|
|
"loss": 5.5776,
|
|
"mean_token_accuracy": 0.15630284696817398,
|
|
"num_tokens": 19624180.0,
|
|
"step": 9450
|
|
},
|
|
{
|
|
"entropy": 5.747406435012818,
|
|
"epoch": 0.8576741654571843,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004933816126846195,
|
|
"loss": 5.584,
|
|
"mean_token_accuracy": 0.1603180468082428,
|
|
"num_tokens": 19634799.0,
|
|
"step": 9455
|
|
},
|
|
{
|
|
"entropy": 5.702679586410523,
|
|
"epoch": 0.8581277213352685,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004933738203294309,
|
|
"loss": 5.5621,
|
|
"mean_token_accuracy": 0.1630157619714737,
|
|
"num_tokens": 19644618.0,
|
|
"step": 9460
|
|
},
|
|
{
|
|
"entropy": 5.738946342468262,
|
|
"epoch": 0.8585812772133526,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.000493366023458216,
|
|
"loss": 5.5892,
|
|
"mean_token_accuracy": 0.15443431884050368,
|
|
"num_tokens": 19655550.0,
|
|
"step": 9465
|
|
},
|
|
{
|
|
"entropy": 5.781291866302491,
|
|
"epoch": 0.8590348330914369,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004933582220711362,
|
|
"loss": 5.6033,
|
|
"mean_token_accuracy": 0.1687952071428299,
|
|
"num_tokens": 19665734.0,
|
|
"step": 9470
|
|
},
|
|
{
|
|
"entropy": 5.820950651168824,
|
|
"epoch": 0.8594883889695211,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004933504161683526,
|
|
"loss": 5.6065,
|
|
"mean_token_accuracy": 0.15410537272691727,
|
|
"num_tokens": 19677130.0,
|
|
"step": 9475
|
|
},
|
|
{
|
|
"entropy": 5.717777585983276,
|
|
"epoch": 0.8599419448476052,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004933426057500269,
|
|
"loss": 5.5077,
|
|
"mean_token_accuracy": 0.16604381203651428,
|
|
"num_tokens": 19687374.0,
|
|
"step": 9480
|
|
},
|
|
{
|
|
"entropy": 5.790850591659546,
|
|
"epoch": 0.8603955007256894,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004933347908163203,
|
|
"loss": 5.5966,
|
|
"mean_token_accuracy": 0.15636817663908004,
|
|
"num_tokens": 19698182.0,
|
|
"step": 9485
|
|
},
|
|
{
|
|
"entropy": 5.797155570983887,
|
|
"epoch": 0.8608490566037735,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004933269713673947,
|
|
"loss": 5.5574,
|
|
"mean_token_accuracy": 0.15362219959497453,
|
|
"num_tokens": 19707664.0,
|
|
"step": 9490
|
|
},
|
|
{
|
|
"entropy": 5.684087944030762,
|
|
"epoch": 0.8613026124818578,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004933191474034116,
|
|
"loss": 5.6055,
|
|
"mean_token_accuracy": 0.15628779530525208,
|
|
"num_tokens": 19717647.0,
|
|
"step": 9495
|
|
},
|
|
{
|
|
"entropy": 5.759577083587646,
|
|
"epoch": 0.861756168359942,
|
|
"grad_norm": 3.328125,
|
|
"learning_rate": 0.000493311318924533,
|
|
"loss": 5.6529,
|
|
"mean_token_accuracy": 0.1533539518713951,
|
|
"num_tokens": 19727444.0,
|
|
"step": 9500
|
|
},
|
|
{
|
|
"entropy": 5.805996131896973,
|
|
"epoch": 0.8622097242380261,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004933034859309208,
|
|
"loss": 5.6711,
|
|
"mean_token_accuracy": 0.1506549097597599,
|
|
"num_tokens": 19738719.0,
|
|
"step": 9505
|
|
},
|
|
{
|
|
"entropy": 5.838384675979614,
|
|
"epoch": 0.8626632801161103,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004932956484227367,
|
|
"loss": 5.632,
|
|
"mean_token_accuracy": 0.1647633671760559,
|
|
"num_tokens": 19749786.0,
|
|
"step": 9510
|
|
},
|
|
{
|
|
"entropy": 5.747707986831665,
|
|
"epoch": 0.8631168359941945,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.000493287806400143,
|
|
"loss": 5.6011,
|
|
"mean_token_accuracy": 0.16494700610637664,
|
|
"num_tokens": 19759623.0,
|
|
"step": 9515
|
|
},
|
|
{
|
|
"entropy": 5.777550220489502,
|
|
"epoch": 0.8635703918722787,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004932799598633018,
|
|
"loss": 5.5932,
|
|
"mean_token_accuracy": 0.15516804605722428,
|
|
"num_tokens": 19770117.0,
|
|
"step": 9520
|
|
},
|
|
{
|
|
"entropy": 5.8132737159729,
|
|
"epoch": 0.8640239477503628,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004932721088123753,
|
|
"loss": 5.6873,
|
|
"mean_token_accuracy": 0.1559644803404808,
|
|
"num_tokens": 19780748.0,
|
|
"step": 9525
|
|
},
|
|
{
|
|
"entropy": 5.8198761463165285,
|
|
"epoch": 0.864477503628447,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004932642532475262,
|
|
"loss": 5.6527,
|
|
"mean_token_accuracy": 0.15599265098571777,
|
|
"num_tokens": 19791816.0,
|
|
"step": 9530
|
|
},
|
|
{
|
|
"entropy": 5.874483489990235,
|
|
"epoch": 0.8649310595065312,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004932563931689168,
|
|
"loss": 5.6763,
|
|
"mean_token_accuracy": 0.15582983940839767,
|
|
"num_tokens": 19801096.0,
|
|
"step": 9535
|
|
},
|
|
{
|
|
"entropy": 5.771186780929566,
|
|
"epoch": 0.8653846153846154,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004932485285767093,
|
|
"loss": 5.5417,
|
|
"mean_token_accuracy": 0.1592293530702591,
|
|
"num_tokens": 19811258.0,
|
|
"step": 9540
|
|
},
|
|
{
|
|
"entropy": 5.784078550338745,
|
|
"epoch": 0.8658381712626996,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004932406594710667,
|
|
"loss": 5.633,
|
|
"mean_token_accuracy": 0.1640041470527649,
|
|
"num_tokens": 19821765.0,
|
|
"step": 9545
|
|
},
|
|
{
|
|
"entropy": 5.736714887619018,
|
|
"epoch": 0.8662917271407837,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004932327858521517,
|
|
"loss": 5.5059,
|
|
"mean_token_accuracy": 0.1630974143743515,
|
|
"num_tokens": 19831537.0,
|
|
"step": 9550
|
|
},
|
|
{
|
|
"entropy": 5.701516389846802,
|
|
"epoch": 0.8667452830188679,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.000493224907720127,
|
|
"loss": 5.5263,
|
|
"mean_token_accuracy": 0.1572334088385105,
|
|
"num_tokens": 19841830.0,
|
|
"step": 9555
|
|
},
|
|
{
|
|
"entropy": 5.768716526031494,
|
|
"epoch": 0.8671988388969522,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004932170250751556,
|
|
"loss": 5.6087,
|
|
"mean_token_accuracy": 0.15383966863155366,
|
|
"num_tokens": 19851896.0,
|
|
"step": 9560
|
|
},
|
|
{
|
|
"entropy": 5.782162809371949,
|
|
"epoch": 0.8676523947750363,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004932091379174006,
|
|
"loss": 5.6532,
|
|
"mean_token_accuracy": 0.15323403626680374,
|
|
"num_tokens": 19861735.0,
|
|
"step": 9565
|
|
},
|
|
{
|
|
"entropy": 5.756535911560059,
|
|
"epoch": 0.8681059506531205,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.000493201246247025,
|
|
"loss": 5.5644,
|
|
"mean_token_accuracy": 0.16582246720790864,
|
|
"num_tokens": 19872333.0,
|
|
"step": 9570
|
|
},
|
|
{
|
|
"entropy": 5.707040882110595,
|
|
"epoch": 0.8685595065312046,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.000493193350064192,
|
|
"loss": 5.5789,
|
|
"mean_token_accuracy": 0.15661975592374802,
|
|
"num_tokens": 19882896.0,
|
|
"step": 9575
|
|
},
|
|
{
|
|
"entropy": 5.737481117248535,
|
|
"epoch": 0.8690130624092888,
|
|
"grad_norm": 3.546875,
|
|
"learning_rate": 0.0004931854493690649,
|
|
"loss": 5.5262,
|
|
"mean_token_accuracy": 0.15955057963728905,
|
|
"num_tokens": 19893767.0,
|
|
"step": 9580
|
|
},
|
|
{
|
|
"entropy": 5.679257392883301,
|
|
"epoch": 0.869466618287373,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004931775441618071,
|
|
"loss": 5.516,
|
|
"mean_token_accuracy": 0.16146796345710754,
|
|
"num_tokens": 19904242.0,
|
|
"step": 9585
|
|
},
|
|
{
|
|
"entropy": 5.693919277191162,
|
|
"epoch": 0.8699201741654572,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004931696344425821,
|
|
"loss": 5.6258,
|
|
"mean_token_accuracy": 0.16253095269203185,
|
|
"num_tokens": 19913898.0,
|
|
"step": 9590
|
|
},
|
|
{
|
|
"entropy": 5.842136669158935,
|
|
"epoch": 0.8703737300435413,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004931617202115535,
|
|
"loss": 5.6269,
|
|
"mean_token_accuracy": 0.16143394708633424,
|
|
"num_tokens": 19923756.0,
|
|
"step": 9595
|
|
},
|
|
{
|
|
"entropy": 5.731996345520019,
|
|
"epoch": 0.8708272859216255,
|
|
"grad_norm": 3.21875,
|
|
"learning_rate": 0.0004931538014688849,
|
|
"loss": 5.558,
|
|
"mean_token_accuracy": 0.16123421043157576,
|
|
"num_tokens": 19932720.0,
|
|
"step": 9600
|
|
},
|
|
{
|
|
"entropy": 5.788021183013916,
|
|
"epoch": 0.8712808417997098,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004931458782147401,
|
|
"loss": 5.7431,
|
|
"mean_token_accuracy": 0.14879583492875098,
|
|
"num_tokens": 19942962.0,
|
|
"step": 9605
|
|
},
|
|
{
|
|
"entropy": 5.839990043640137,
|
|
"epoch": 0.8717343976777939,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.000493137950449283,
|
|
"loss": 5.6237,
|
|
"mean_token_accuracy": 0.16345185190439224,
|
|
"num_tokens": 19953735.0,
|
|
"step": 9610
|
|
},
|
|
{
|
|
"entropy": 5.7534712791442875,
|
|
"epoch": 0.8721879535558781,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004931300181726775,
|
|
"loss": 5.614,
|
|
"mean_token_accuracy": 0.15583408176898955,
|
|
"num_tokens": 19964416.0,
|
|
"step": 9615
|
|
},
|
|
{
|
|
"entropy": 5.779343700408935,
|
|
"epoch": 0.8726415094339622,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004931220813850875,
|
|
"loss": 5.6265,
|
|
"mean_token_accuracy": 0.1527929909527302,
|
|
"num_tokens": 19974531.0,
|
|
"step": 9620
|
|
},
|
|
{
|
|
"entropy": 5.797291040420532,
|
|
"epoch": 0.8730950653120464,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004931141400866773,
|
|
"loss": 5.6357,
|
|
"mean_token_accuracy": 0.15830333083868026,
|
|
"num_tokens": 19984964.0,
|
|
"step": 9625
|
|
},
|
|
{
|
|
"entropy": 5.718866300582886,
|
|
"epoch": 0.8735486211901307,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004931061942776112,
|
|
"loss": 5.5669,
|
|
"mean_token_accuracy": 0.1664120987057686,
|
|
"num_tokens": 19995568.0,
|
|
"step": 9630
|
|
},
|
|
{
|
|
"entropy": 5.852457904815674,
|
|
"epoch": 0.8740021770682148,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004930982439580534,
|
|
"loss": 5.736,
|
|
"mean_token_accuracy": 0.15224073678255082,
|
|
"num_tokens": 20005856.0,
|
|
"step": 9635
|
|
},
|
|
{
|
|
"entropy": 5.822800064086914,
|
|
"epoch": 0.874455732946299,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004930902891281683,
|
|
"loss": 5.6259,
|
|
"mean_token_accuracy": 0.15214829742908478,
|
|
"num_tokens": 20015683.0,
|
|
"step": 9640
|
|
},
|
|
{
|
|
"entropy": 5.7282984256744385,
|
|
"epoch": 0.8749092888243831,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004930823297881205,
|
|
"loss": 5.4789,
|
|
"mean_token_accuracy": 0.1637609615921974,
|
|
"num_tokens": 20025998.0,
|
|
"step": 9645
|
|
},
|
|
{
|
|
"entropy": 5.758309364318848,
|
|
"epoch": 0.8753628447024674,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004930743659380745,
|
|
"loss": 5.6363,
|
|
"mean_token_accuracy": 0.15343175306916237,
|
|
"num_tokens": 20036486.0,
|
|
"step": 9650
|
|
},
|
|
{
|
|
"entropy": 5.67301025390625,
|
|
"epoch": 0.8758164005805515,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.000493066397578195,
|
|
"loss": 5.5448,
|
|
"mean_token_accuracy": 0.16223546415567397,
|
|
"num_tokens": 20046784.0,
|
|
"step": 9655
|
|
},
|
|
{
|
|
"entropy": 5.770144319534301,
|
|
"epoch": 0.8762699564586357,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004930584247086468,
|
|
"loss": 5.5988,
|
|
"mean_token_accuracy": 0.1581301808357239,
|
|
"num_tokens": 20056999.0,
|
|
"step": 9660
|
|
},
|
|
{
|
|
"entropy": 5.742309331893921,
|
|
"epoch": 0.8767235123367199,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.000493050447329595,
|
|
"loss": 5.4723,
|
|
"mean_token_accuracy": 0.165936741232872,
|
|
"num_tokens": 20067612.0,
|
|
"step": 9665
|
|
},
|
|
{
|
|
"entropy": 5.764831924438477,
|
|
"epoch": 0.877177068214804,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004930424654412043,
|
|
"loss": 5.6489,
|
|
"mean_token_accuracy": 0.157967209815979,
|
|
"num_tokens": 20077330.0,
|
|
"step": 9670
|
|
},
|
|
{
|
|
"entropy": 5.75092453956604,
|
|
"epoch": 0.8776306240928883,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004930344790436398,
|
|
"loss": 5.6239,
|
|
"mean_token_accuracy": 0.15569445192813874,
|
|
"num_tokens": 20086801.0,
|
|
"step": 9675
|
|
},
|
|
{
|
|
"entropy": 5.773689842224121,
|
|
"epoch": 0.8780841799709724,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004930264881370666,
|
|
"loss": 5.5721,
|
|
"mean_token_accuracy": 0.15935052037239075,
|
|
"num_tokens": 20097047.0,
|
|
"step": 9680
|
|
},
|
|
{
|
|
"entropy": 5.707263851165772,
|
|
"epoch": 0.8785377358490566,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004930184927216504,
|
|
"loss": 5.6087,
|
|
"mean_token_accuracy": 0.16083718240261077,
|
|
"num_tokens": 20107185.0,
|
|
"step": 9685
|
|
},
|
|
{
|
|
"entropy": 5.788599967956543,
|
|
"epoch": 0.8789912917271407,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004930104927975559,
|
|
"loss": 5.5682,
|
|
"mean_token_accuracy": 0.16288443207740783,
|
|
"num_tokens": 20118493.0,
|
|
"step": 9690
|
|
},
|
|
{
|
|
"entropy": 5.785510015487671,
|
|
"epoch": 0.879444847605225,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004930024883649489,
|
|
"loss": 5.6122,
|
|
"mean_token_accuracy": 0.1566604882478714,
|
|
"num_tokens": 20129294.0,
|
|
"step": 9695
|
|
},
|
|
{
|
|
"entropy": 5.704188823699951,
|
|
"epoch": 0.8798984034833092,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.000492994479423995,
|
|
"loss": 5.5574,
|
|
"mean_token_accuracy": 0.16336040645837785,
|
|
"num_tokens": 20139194.0,
|
|
"step": 9700
|
|
},
|
|
{
|
|
"entropy": 5.717818307876587,
|
|
"epoch": 0.8803519593613933,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.0004929864659748597,
|
|
"loss": 5.5935,
|
|
"mean_token_accuracy": 0.15911915600299836,
|
|
"num_tokens": 20149681.0,
|
|
"step": 9705
|
|
},
|
|
{
|
|
"entropy": 5.761976432800293,
|
|
"epoch": 0.8808055152394775,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004929784480177087,
|
|
"loss": 5.6825,
|
|
"mean_token_accuracy": 0.15302171260118486,
|
|
"num_tokens": 20160557.0,
|
|
"step": 9710
|
|
},
|
|
{
|
|
"entropy": 5.724233531951905,
|
|
"epoch": 0.8812590711175616,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004929704255527078,
|
|
"loss": 5.5703,
|
|
"mean_token_accuracy": 0.15917069613933563,
|
|
"num_tokens": 20171047.0,
|
|
"step": 9715
|
|
},
|
|
{
|
|
"entropy": 5.827355623245239,
|
|
"epoch": 0.8817126269956459,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.000492962398580023,
|
|
"loss": 5.7182,
|
|
"mean_token_accuracy": 0.15424745678901672,
|
|
"num_tokens": 20182148.0,
|
|
"step": 9720
|
|
},
|
|
{
|
|
"entropy": 5.697885799407959,
|
|
"epoch": 0.88216618287373,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004929543670998203,
|
|
"loss": 5.473,
|
|
"mean_token_accuracy": 0.16541499197483062,
|
|
"num_tokens": 20192131.0,
|
|
"step": 9725
|
|
},
|
|
{
|
|
"entropy": 5.712615060806274,
|
|
"epoch": 0.8826197387518142,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.0004929463311122657,
|
|
"loss": 5.6052,
|
|
"mean_token_accuracy": 0.15569589883089066,
|
|
"num_tokens": 20202805.0,
|
|
"step": 9730
|
|
},
|
|
{
|
|
"entropy": 5.772889041900635,
|
|
"epoch": 0.8830732946298984,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004929382906175253,
|
|
"loss": 5.5498,
|
|
"mean_token_accuracy": 0.1639830321073532,
|
|
"num_tokens": 20212702.0,
|
|
"step": 9735
|
|
},
|
|
{
|
|
"entropy": 5.747312068939209,
|
|
"epoch": 0.8835268505079826,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004929302456157657,
|
|
"loss": 5.5628,
|
|
"mean_token_accuracy": 0.16153869926929473,
|
|
"num_tokens": 20222661.0,
|
|
"step": 9740
|
|
},
|
|
{
|
|
"entropy": 5.763171052932739,
|
|
"epoch": 0.8839804063860668,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004929221961071531,
|
|
"loss": 5.5987,
|
|
"mean_token_accuracy": 0.15549358874559402,
|
|
"num_tokens": 20233012.0,
|
|
"step": 9745
|
|
},
|
|
{
|
|
"entropy": 5.787082815170288,
|
|
"epoch": 0.8844339622641509,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004929141420918538,
|
|
"loss": 5.597,
|
|
"mean_token_accuracy": 0.16525475382804872,
|
|
"num_tokens": 20242918.0,
|
|
"step": 9750
|
|
},
|
|
{
|
|
"entropy": 5.714033031463623,
|
|
"epoch": 0.8848875181422351,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004929060835700347,
|
|
"loss": 5.5442,
|
|
"mean_token_accuracy": 0.1644924759864807,
|
|
"num_tokens": 20253254.0,
|
|
"step": 9755
|
|
},
|
|
{
|
|
"entropy": 5.728669834136963,
|
|
"epoch": 0.8853410740203193,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.000492898020541862,
|
|
"loss": 5.6053,
|
|
"mean_token_accuracy": 0.15660808384418487,
|
|
"num_tokens": 20263355.0,
|
|
"step": 9760
|
|
},
|
|
{
|
|
"entropy": 5.69545726776123,
|
|
"epoch": 0.8857946298984035,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004928899530075029,
|
|
"loss": 5.5375,
|
|
"mean_token_accuracy": 0.16231759786605834,
|
|
"num_tokens": 20274716.0,
|
|
"step": 9765
|
|
},
|
|
{
|
|
"entropy": 5.653417539596558,
|
|
"epoch": 0.8862481857764877,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004928818809671241,
|
|
"loss": 5.5329,
|
|
"mean_token_accuracy": 0.158498714864254,
|
|
"num_tokens": 20285631.0,
|
|
"step": 9770
|
|
},
|
|
{
|
|
"entropy": 5.784018516540527,
|
|
"epoch": 0.8867017416545718,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004928738044208923,
|
|
"loss": 5.588,
|
|
"mean_token_accuracy": 0.16560565382242204,
|
|
"num_tokens": 20295717.0,
|
|
"step": 9775
|
|
},
|
|
{
|
|
"entropy": 5.76739730834961,
|
|
"epoch": 0.887155297532656,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004928657233689748,
|
|
"loss": 5.5839,
|
|
"mean_token_accuracy": 0.16369526088237762,
|
|
"num_tokens": 20306637.0,
|
|
"step": 9780
|
|
},
|
|
{
|
|
"entropy": 5.766957426071167,
|
|
"epoch": 0.8876088534107403,
|
|
"grad_norm": 2.921875,
|
|
"learning_rate": 0.0004928576378115387,
|
|
"loss": 5.5278,
|
|
"mean_token_accuracy": 0.1624474361538887,
|
|
"num_tokens": 20316629.0,
|
|
"step": 9785
|
|
},
|
|
{
|
|
"entropy": 5.804458856582642,
|
|
"epoch": 0.8880624092888244,
|
|
"grad_norm": 3.5,
|
|
"learning_rate": 0.0004928495477487509,
|
|
"loss": 5.7321,
|
|
"mean_token_accuracy": 0.1472342297434807,
|
|
"num_tokens": 20327935.0,
|
|
"step": 9790
|
|
},
|
|
{
|
|
"entropy": 5.7683697700500485,
|
|
"epoch": 0.8885159651669086,
|
|
"grad_norm": 5.1875,
|
|
"learning_rate": 0.0004928414531807792,
|
|
"loss": 5.5397,
|
|
"mean_token_accuracy": 0.1623832643032074,
|
|
"num_tokens": 20339142.0,
|
|
"step": 9795
|
|
},
|
|
{
|
|
"entropy": 5.695834827423096,
|
|
"epoch": 0.8889695210449927,
|
|
"grad_norm": 3.3125,
|
|
"learning_rate": 0.0004928333541077906,
|
|
"loss": 5.544,
|
|
"mean_token_accuracy": 0.16304732412099837,
|
|
"num_tokens": 20348474.0,
|
|
"step": 9800
|
|
},
|
|
{
|
|
"entropy": 5.738918924331665,
|
|
"epoch": 0.8894230769230769,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004928252505299527,
|
|
"loss": 5.6005,
|
|
"mean_token_accuracy": 0.15486776679754258,
|
|
"num_tokens": 20359440.0,
|
|
"step": 9805
|
|
},
|
|
{
|
|
"entropy": 5.7874949932098385,
|
|
"epoch": 0.8898766328011611,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004928171424474332,
|
|
"loss": 5.6468,
|
|
"mean_token_accuracy": 0.15963678508996965,
|
|
"num_tokens": 20370355.0,
|
|
"step": 9810
|
|
},
|
|
{
|
|
"entropy": 5.733865594863891,
|
|
"epoch": 0.8903301886792453,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004928090298603996,
|
|
"loss": 5.5448,
|
|
"mean_token_accuracy": 0.1619069904088974,
|
|
"num_tokens": 20380214.0,
|
|
"step": 9815
|
|
},
|
|
{
|
|
"entropy": 5.746207189559937,
|
|
"epoch": 0.8907837445573294,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004928009127690199,
|
|
"loss": 5.5364,
|
|
"mean_token_accuracy": 0.16304803788661956,
|
|
"num_tokens": 20389190.0,
|
|
"step": 9820
|
|
},
|
|
{
|
|
"entropy": 5.6939174175262455,
|
|
"epoch": 0.8912373004354136,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004927927911734617,
|
|
"loss": 5.5978,
|
|
"mean_token_accuracy": 0.16037389039993286,
|
|
"num_tokens": 20399531.0,
|
|
"step": 9825
|
|
},
|
|
{
|
|
"entropy": 5.72567048072815,
|
|
"epoch": 0.8916908563134979,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004927846650738931,
|
|
"loss": 5.6097,
|
|
"mean_token_accuracy": 0.15768799483776091,
|
|
"num_tokens": 20410201.0,
|
|
"step": 9830
|
|
},
|
|
{
|
|
"entropy": 5.7705686569213865,
|
|
"epoch": 0.892144412191582,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.0004927765344704821,
|
|
"loss": 5.555,
|
|
"mean_token_accuracy": 0.16240571439266205,
|
|
"num_tokens": 20421579.0,
|
|
"step": 9835
|
|
},
|
|
{
|
|
"entropy": 5.772910737991333,
|
|
"epoch": 0.8925979680696662,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004927683993633969,
|
|
"loss": 5.6234,
|
|
"mean_token_accuracy": 0.1574987828731537,
|
|
"num_tokens": 20432048.0,
|
|
"step": 9840
|
|
},
|
|
{
|
|
"entropy": 5.7999410152435305,
|
|
"epoch": 0.8930515239477503,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004927602597528057,
|
|
"loss": 5.6533,
|
|
"mean_token_accuracy": 0.15573451519012452,
|
|
"num_tokens": 20441752.0,
|
|
"step": 9845
|
|
},
|
|
{
|
|
"entropy": 5.7320328712463375,
|
|
"epoch": 0.8935050798258345,
|
|
"grad_norm": 3.0625,
|
|
"learning_rate": 0.0004927521156388769,
|
|
"loss": 5.5027,
|
|
"mean_token_accuracy": 0.16245125532150267,
|
|
"num_tokens": 20451693.0,
|
|
"step": 9850
|
|
},
|
|
{
|
|
"entropy": 5.745809650421142,
|
|
"epoch": 0.8939586357039188,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004927439670217788,
|
|
"loss": 5.6338,
|
|
"mean_token_accuracy": 0.15606619864702226,
|
|
"num_tokens": 20462312.0,
|
|
"step": 9855
|
|
},
|
|
{
|
|
"entropy": 5.7278495788574215,
|
|
"epoch": 0.8944121915820029,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.00049273581390168,
|
|
"loss": 5.5412,
|
|
"mean_token_accuracy": 0.1569090738892555,
|
|
"num_tokens": 20472546.0,
|
|
"step": 9860
|
|
},
|
|
{
|
|
"entropy": 5.729147720336914,
|
|
"epoch": 0.8948657474600871,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.000492727656278749,
|
|
"loss": 5.5842,
|
|
"mean_token_accuracy": 0.16081600934267043,
|
|
"num_tokens": 20483266.0,
|
|
"step": 9865
|
|
},
|
|
{
|
|
"entropy": 5.6955976486206055,
|
|
"epoch": 0.8953193033381712,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004927194941531547,
|
|
"loss": 5.5057,
|
|
"mean_token_accuracy": 0.1665218725800514,
|
|
"num_tokens": 20492490.0,
|
|
"step": 9870
|
|
},
|
|
{
|
|
"entropy": 5.740245056152344,
|
|
"epoch": 0.8957728592162555,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004927113275250657,
|
|
"loss": 5.5473,
|
|
"mean_token_accuracy": 0.16392815560102464,
|
|
"num_tokens": 20503077.0,
|
|
"step": 9875
|
|
},
|
|
{
|
|
"entropy": 5.718786430358887,
|
|
"epoch": 0.8962264150943396,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004927031563946511,
|
|
"loss": 5.5696,
|
|
"mean_token_accuracy": 0.15711624771356583,
|
|
"num_tokens": 20513771.0,
|
|
"step": 9880
|
|
},
|
|
{
|
|
"entropy": 5.765521717071533,
|
|
"epoch": 0.8966799709724238,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004926949807620796,
|
|
"loss": 5.6671,
|
|
"mean_token_accuracy": 0.15743213146924973,
|
|
"num_tokens": 20523616.0,
|
|
"step": 9885
|
|
},
|
|
{
|
|
"entropy": 5.728376722335815,
|
|
"epoch": 0.897133526850508,
|
|
"grad_norm": 3.296875,
|
|
"learning_rate": 0.0004926868006275204,
|
|
"loss": 5.5008,
|
|
"mean_token_accuracy": 0.1645891025662422,
|
|
"num_tokens": 20533613.0,
|
|
"step": 9890
|
|
},
|
|
{
|
|
"entropy": 5.753400993347168,
|
|
"epoch": 0.8975870827285921,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004926786159911427,
|
|
"loss": 5.5612,
|
|
"mean_token_accuracy": 0.15600775927305222,
|
|
"num_tokens": 20543812.0,
|
|
"step": 9895
|
|
},
|
|
{
|
|
"entropy": 5.720806884765625,
|
|
"epoch": 0.8980406386066764,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.000492670426853116,
|
|
"loss": 5.5159,
|
|
"mean_token_accuracy": 0.16405212879180908,
|
|
"num_tokens": 20553785.0,
|
|
"step": 9900
|
|
},
|
|
{
|
|
"entropy": 5.7782251834869385,
|
|
"epoch": 0.8984941944847605,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004926622332136092,
|
|
"loss": 5.599,
|
|
"mean_token_accuracy": 0.16605667322874068,
|
|
"num_tokens": 20563326.0,
|
|
"step": 9905
|
|
},
|
|
{
|
|
"entropy": 5.699282217025757,
|
|
"epoch": 0.8989477503628447,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004926540350727918,
|
|
"loss": 5.4982,
|
|
"mean_token_accuracy": 0.16628772765398026,
|
|
"num_tokens": 20573643.0,
|
|
"step": 9910
|
|
},
|
|
{
|
|
"entropy": 5.64955506324768,
|
|
"epoch": 0.8994013062409288,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004926458324308337,
|
|
"loss": 5.5105,
|
|
"mean_token_accuracy": 0.16470665633678436,
|
|
"num_tokens": 20583916.0,
|
|
"step": 9915
|
|
},
|
|
{
|
|
"entropy": 5.776688766479492,
|
|
"epoch": 0.8998548621190131,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004926376252879043,
|
|
"loss": 5.6848,
|
|
"mean_token_accuracy": 0.1554987758398056,
|
|
"num_tokens": 20593984.0,
|
|
"step": 9920
|
|
},
|
|
{
|
|
"entropy": 5.849941968917847,
|
|
"epoch": 0.9003084179970973,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004926294136441733,
|
|
"loss": 5.4985,
|
|
"mean_token_accuracy": 0.16473574787378312,
|
|
"num_tokens": 20603927.0,
|
|
"step": 9925
|
|
},
|
|
{
|
|
"entropy": 5.74761643409729,
|
|
"epoch": 0.9007619738751814,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004926211974998106,
|
|
"loss": 5.6331,
|
|
"mean_token_accuracy": 0.16239345967769622,
|
|
"num_tokens": 20614147.0,
|
|
"step": 9930
|
|
},
|
|
{
|
|
"entropy": 5.703799104690551,
|
|
"epoch": 0.9012155297532656,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.000492612976854986,
|
|
"loss": 5.5825,
|
|
"mean_token_accuracy": 0.1658533215522766,
|
|
"num_tokens": 20623631.0,
|
|
"step": 9935
|
|
},
|
|
{
|
|
"entropy": 5.670938348770141,
|
|
"epoch": 0.9016690856313497,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004926047517098697,
|
|
"loss": 5.476,
|
|
"mean_token_accuracy": 0.16628272086381912,
|
|
"num_tokens": 20632566.0,
|
|
"step": 9940
|
|
},
|
|
{
|
|
"entropy": 5.803874492645264,
|
|
"epoch": 0.902122641509434,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004925965220646315,
|
|
"loss": 5.5677,
|
|
"mean_token_accuracy": 0.16223408579826354,
|
|
"num_tokens": 20643246.0,
|
|
"step": 9945
|
|
},
|
|
{
|
|
"entropy": 5.740242528915405,
|
|
"epoch": 0.9025761973875182,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004925882879194419,
|
|
"loss": 5.665,
|
|
"mean_token_accuracy": 0.1563659906387329,
|
|
"num_tokens": 20653372.0,
|
|
"step": 9950
|
|
},
|
|
{
|
|
"entropy": 5.720297193527221,
|
|
"epoch": 0.9030297532656023,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004925800492744712,
|
|
"loss": 5.6146,
|
|
"mean_token_accuracy": 0.15248575061559677,
|
|
"num_tokens": 20662687.0,
|
|
"step": 9955
|
|
},
|
|
{
|
|
"entropy": 5.717971277236939,
|
|
"epoch": 0.9034833091436865,
|
|
"grad_norm": 3.265625,
|
|
"learning_rate": 0.0004925718061298895,
|
|
"loss": 5.538,
|
|
"mean_token_accuracy": 0.1664003387093544,
|
|
"num_tokens": 20673168.0,
|
|
"step": 9960
|
|
},
|
|
{
|
|
"entropy": 5.811778259277344,
|
|
"epoch": 0.9039368650217707,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004925635584858675,
|
|
"loss": 5.6536,
|
|
"mean_token_accuracy": 0.15354033708572387,
|
|
"num_tokens": 20683100.0,
|
|
"step": 9965
|
|
},
|
|
{
|
|
"entropy": 5.826661586761475,
|
|
"epoch": 0.9043904208998549,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004925553063425755,
|
|
"loss": 5.6421,
|
|
"mean_token_accuracy": 0.16219090074300765,
|
|
"num_tokens": 20694097.0,
|
|
"step": 9970
|
|
},
|
|
{
|
|
"entropy": 5.758487224578857,
|
|
"epoch": 0.904843976777939,
|
|
"grad_norm": 3.828125,
|
|
"learning_rate": 0.0004925470497001844,
|
|
"loss": 5.6135,
|
|
"mean_token_accuracy": 0.15943156629800798,
|
|
"num_tokens": 20704640.0,
|
|
"step": 9975
|
|
},
|
|
{
|
|
"entropy": 5.745730829238892,
|
|
"epoch": 0.9052975326560232,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004925387885588648,
|
|
"loss": 5.5439,
|
|
"mean_token_accuracy": 0.16009601056575776,
|
|
"num_tokens": 20714419.0,
|
|
"step": 9980
|
|
},
|
|
{
|
|
"entropy": 5.8551788330078125,
|
|
"epoch": 0.9057510885341074,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004925305229187877,
|
|
"loss": 5.6472,
|
|
"mean_token_accuracy": 0.15727191120386125,
|
|
"num_tokens": 20724705.0,
|
|
"step": 9985
|
|
},
|
|
{
|
|
"entropy": 5.857384157180786,
|
|
"epoch": 0.9062046444121916,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.000492522252780124,
|
|
"loss": 5.7113,
|
|
"mean_token_accuracy": 0.15692283511161803,
|
|
"num_tokens": 20734753.0,
|
|
"step": 9990
|
|
},
|
|
{
|
|
"entropy": 5.742457580566406,
|
|
"epoch": 0.9066582002902758,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004925139781430446,
|
|
"loss": 5.5219,
|
|
"mean_token_accuracy": 0.16097703576087952,
|
|
"num_tokens": 20745389.0,
|
|
"step": 9995
|
|
},
|
|
{
|
|
"entropy": 5.721439027786255,
|
|
"epoch": 0.9071117561683599,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004925056990077207,
|
|
"loss": 5.5577,
|
|
"mean_token_accuracy": 0.16342038810253143,
|
|
"num_tokens": 20755702.0,
|
|
"step": 10000
|
|
},
|
|
{
|
|
"entropy": 5.702457332611084,
|
|
"epoch": 0.9075653120464441,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004924974153743235,
|
|
"loss": 5.4939,
|
|
"mean_token_accuracy": 0.16504203975200654,
|
|
"num_tokens": 20766046.0,
|
|
"step": 10005
|
|
},
|
|
{
|
|
"entropy": 5.710053205490112,
|
|
"epoch": 0.9080188679245284,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.0004924891272430244,
|
|
"loss": 5.5837,
|
|
"mean_token_accuracy": 0.16382571905851365,
|
|
"num_tokens": 20776654.0,
|
|
"step": 10010
|
|
},
|
|
{
|
|
"entropy": 5.810329437255859,
|
|
"epoch": 0.9084724238026125,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004924808346139948,
|
|
"loss": 5.6499,
|
|
"mean_token_accuracy": 0.16033175140619277,
|
|
"num_tokens": 20787066.0,
|
|
"step": 10015
|
|
},
|
|
{
|
|
"entropy": 5.760316848754883,
|
|
"epoch": 0.9089259796806967,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004924725374874059,
|
|
"loss": 5.5392,
|
|
"mean_token_accuracy": 0.16266586631536484,
|
|
"num_tokens": 20796822.0,
|
|
"step": 10020
|
|
},
|
|
{
|
|
"entropy": 5.751481676101685,
|
|
"epoch": 0.9093795355587808,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004924642358634297,
|
|
"loss": 5.6002,
|
|
"mean_token_accuracy": 0.15571456253528596,
|
|
"num_tokens": 20807602.0,
|
|
"step": 10025
|
|
},
|
|
{
|
|
"entropy": 5.752258825302124,
|
|
"epoch": 0.909833091436865,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004924559297422376,
|
|
"loss": 5.5633,
|
|
"mean_token_accuracy": 0.16362907886505126,
|
|
"num_tokens": 20819046.0,
|
|
"step": 10030
|
|
},
|
|
{
|
|
"entropy": 5.733488464355469,
|
|
"epoch": 0.9102866473149492,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004924476191240014,
|
|
"loss": 5.5851,
|
|
"mean_token_accuracy": 0.15861433148384094,
|
|
"num_tokens": 20828989.0,
|
|
"step": 10035
|
|
},
|
|
{
|
|
"entropy": 5.715539026260376,
|
|
"epoch": 0.9107402031930334,
|
|
"grad_norm": 3.1875,
|
|
"learning_rate": 0.000492439304008893,
|
|
"loss": 5.594,
|
|
"mean_token_accuracy": 0.16207023859024047,
|
|
"num_tokens": 20839366.0,
|
|
"step": 10040
|
|
},
|
|
{
|
|
"entropy": 5.731959486007691,
|
|
"epoch": 0.9111937590711175,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004924309843970847,
|
|
"loss": 5.5813,
|
|
"mean_token_accuracy": 0.16178972721099855,
|
|
"num_tokens": 20849513.0,
|
|
"step": 10045
|
|
},
|
|
{
|
|
"entropy": 5.85939621925354,
|
|
"epoch": 0.9116473149492017,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004924226602887479,
|
|
"loss": 5.6294,
|
|
"mean_token_accuracy": 0.15595446676015853,
|
|
"num_tokens": 20861406.0,
|
|
"step": 10050
|
|
},
|
|
{
|
|
"entropy": 5.736988067626953,
|
|
"epoch": 0.912100870827286,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004924143316840552,
|
|
"loss": 5.5449,
|
|
"mean_token_accuracy": 0.16947506368160248,
|
|
"num_tokens": 20871190.0,
|
|
"step": 10055
|
|
},
|
|
{
|
|
"entropy": 5.724557399749756,
|
|
"epoch": 0.9125544267053701,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004924059985831787,
|
|
"loss": 5.6845,
|
|
"mean_token_accuracy": 0.15621962100267411,
|
|
"num_tokens": 20881589.0,
|
|
"step": 10060
|
|
},
|
|
{
|
|
"entropy": 5.779449796676635,
|
|
"epoch": 0.9130079825834543,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004923976609862908,
|
|
"loss": 5.5986,
|
|
"mean_token_accuracy": 0.1539789617061615,
|
|
"num_tokens": 20892072.0,
|
|
"step": 10065
|
|
},
|
|
{
|
|
"entropy": 5.8154136657714846,
|
|
"epoch": 0.9134615384615384,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004923893188935638,
|
|
"loss": 5.5972,
|
|
"mean_token_accuracy": 0.15622748136520387,
|
|
"num_tokens": 20902616.0,
|
|
"step": 10070
|
|
},
|
|
{
|
|
"entropy": 5.8036257266998295,
|
|
"epoch": 0.9139150943396226,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004923809723051702,
|
|
"loss": 5.6032,
|
|
"mean_token_accuracy": 0.16051782965660094,
|
|
"num_tokens": 20913832.0,
|
|
"step": 10075
|
|
},
|
|
{
|
|
"entropy": 5.656179428100586,
|
|
"epoch": 0.9143686502177069,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.0004923726212212829,
|
|
"loss": 5.4832,
|
|
"mean_token_accuracy": 0.16447304040193558,
|
|
"num_tokens": 20923322.0,
|
|
"step": 10080
|
|
},
|
|
{
|
|
"entropy": 5.679349327087403,
|
|
"epoch": 0.914822206095791,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004923642656420742,
|
|
"loss": 5.6092,
|
|
"mean_token_accuracy": 0.15965048521757125,
|
|
"num_tokens": 20933334.0,
|
|
"step": 10085
|
|
},
|
|
{
|
|
"entropy": 5.771925449371338,
|
|
"epoch": 0.9152757619738752,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004923559055677173,
|
|
"loss": 5.5377,
|
|
"mean_token_accuracy": 0.15836638063192368,
|
|
"num_tokens": 20944171.0,
|
|
"step": 10090
|
|
},
|
|
{
|
|
"entropy": 5.773163938522339,
|
|
"epoch": 0.9157293178519593,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004923475409983848,
|
|
"loss": 5.5924,
|
|
"mean_token_accuracy": 0.16040382236242295,
|
|
"num_tokens": 20954200.0,
|
|
"step": 10095
|
|
},
|
|
{
|
|
"entropy": 5.728333139419556,
|
|
"epoch": 0.9161828737300436,
|
|
"grad_norm": 4.78125,
|
|
"learning_rate": 0.0004923391719342497,
|
|
"loss": 5.6023,
|
|
"mean_token_accuracy": 0.1567119151353836,
|
|
"num_tokens": 20964935.0,
|
|
"step": 10100
|
|
},
|
|
{
|
|
"entropy": 5.726889657974243,
|
|
"epoch": 0.9166364296081277,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004923307983754852,
|
|
"loss": 5.5887,
|
|
"mean_token_accuracy": 0.15925737470388412,
|
|
"num_tokens": 20975499.0,
|
|
"step": 10105
|
|
},
|
|
{
|
|
"entropy": 5.691125202178955,
|
|
"epoch": 0.9170899854862119,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004923224203222645,
|
|
"loss": 5.5029,
|
|
"mean_token_accuracy": 0.15957079082727432,
|
|
"num_tokens": 20986199.0,
|
|
"step": 10110
|
|
},
|
|
{
|
|
"entropy": 5.761956262588501,
|
|
"epoch": 0.9175435413642961,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004923140377747606,
|
|
"loss": 5.5836,
|
|
"mean_token_accuracy": 0.1587754726409912,
|
|
"num_tokens": 20996313.0,
|
|
"step": 10115
|
|
},
|
|
{
|
|
"entropy": 5.723622560501099,
|
|
"epoch": 0.9179970972423802,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004923056507331471,
|
|
"loss": 5.555,
|
|
"mean_token_accuracy": 0.1635773867368698,
|
|
"num_tokens": 21006133.0,
|
|
"step": 10120
|
|
},
|
|
{
|
|
"entropy": 5.757354259490967,
|
|
"epoch": 0.9184506531204645,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004922972591975974,
|
|
"loss": 5.5446,
|
|
"mean_token_accuracy": 0.16371544152498246,
|
|
"num_tokens": 21016448.0,
|
|
"step": 10125
|
|
},
|
|
{
|
|
"entropy": 5.718880605697632,
|
|
"epoch": 0.9189042089985486,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004922888631682849,
|
|
"loss": 5.4852,
|
|
"mean_token_accuracy": 0.16303777247667312,
|
|
"num_tokens": 21026458.0,
|
|
"step": 10130
|
|
},
|
|
{
|
|
"entropy": 5.6971259117126465,
|
|
"epoch": 0.9193577648766328,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004922804626453834,
|
|
"loss": 5.5198,
|
|
"mean_token_accuracy": 0.16405363082885743,
|
|
"num_tokens": 21037111.0,
|
|
"step": 10135
|
|
},
|
|
{
|
|
"entropy": 5.690812444686889,
|
|
"epoch": 0.9198113207547169,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004922720576290665,
|
|
"loss": 5.5951,
|
|
"mean_token_accuracy": 0.16238243877887726,
|
|
"num_tokens": 21048041.0,
|
|
"step": 10140
|
|
},
|
|
{
|
|
"entropy": 5.645774078369141,
|
|
"epoch": 0.9202648766328012,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004922636481195082,
|
|
"loss": 5.4655,
|
|
"mean_token_accuracy": 0.17051304876804352,
|
|
"num_tokens": 21058099.0,
|
|
"step": 10145
|
|
},
|
|
{
|
|
"entropy": 5.745427083969116,
|
|
"epoch": 0.9207184325108854,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004922552341168823,
|
|
"loss": 5.6147,
|
|
"mean_token_accuracy": 0.15370191931724547,
|
|
"num_tokens": 21068137.0,
|
|
"step": 10150
|
|
},
|
|
{
|
|
"entropy": 5.700175476074219,
|
|
"epoch": 0.9211719883889695,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.0004922468156213627,
|
|
"loss": 5.4957,
|
|
"mean_token_accuracy": 0.16685573160648345,
|
|
"num_tokens": 21077556.0,
|
|
"step": 10155
|
|
},
|
|
{
|
|
"entropy": 5.7089495182037355,
|
|
"epoch": 0.9216255442670537,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004922383926331236,
|
|
"loss": 5.5168,
|
|
"mean_token_accuracy": 0.1622081518173218,
|
|
"num_tokens": 21087524.0,
|
|
"step": 10160
|
|
},
|
|
{
|
|
"entropy": 5.680036211013794,
|
|
"epoch": 0.9220791001451378,
|
|
"grad_norm": 2.890625,
|
|
"learning_rate": 0.0004922299651523392,
|
|
"loss": 5.6076,
|
|
"mean_token_accuracy": 0.15557302683591842,
|
|
"num_tokens": 21098446.0,
|
|
"step": 10165
|
|
},
|
|
{
|
|
"entropy": 5.747808218002319,
|
|
"epoch": 0.9225326560232221,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004922215331791837,
|
|
"loss": 5.6049,
|
|
"mean_token_accuracy": 0.15888546109199525,
|
|
"num_tokens": 21109291.0,
|
|
"step": 10170
|
|
},
|
|
{
|
|
"entropy": 5.750172328948975,
|
|
"epoch": 0.9229862119013063,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004922130967138316,
|
|
"loss": 5.4866,
|
|
"mean_token_accuracy": 0.16166751682758332,
|
|
"num_tokens": 21120043.0,
|
|
"step": 10175
|
|
},
|
|
{
|
|
"entropy": 5.748207426071167,
|
|
"epoch": 0.9234397677793904,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004922046557564574,
|
|
"loss": 5.608,
|
|
"mean_token_accuracy": 0.1515302650630474,
|
|
"num_tokens": 21130339.0,
|
|
"step": 10180
|
|
},
|
|
{
|
|
"entropy": 5.739501714706421,
|
|
"epoch": 0.9238933236574746,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004921962103072355,
|
|
"loss": 5.6678,
|
|
"mean_token_accuracy": 0.15647083669900894,
|
|
"num_tokens": 21142307.0,
|
|
"step": 10185
|
|
},
|
|
{
|
|
"entropy": 5.788878917694092,
|
|
"epoch": 0.9243468795355588,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004921877603663406,
|
|
"loss": 5.5701,
|
|
"mean_token_accuracy": 0.15992704182863235,
|
|
"num_tokens": 21151843.0,
|
|
"step": 10190
|
|
},
|
|
{
|
|
"entropy": 5.708737707138061,
|
|
"epoch": 0.924800435413643,
|
|
"grad_norm": 3.46875,
|
|
"learning_rate": 0.0004921793059339474,
|
|
"loss": 5.5639,
|
|
"mean_token_accuracy": 0.16384396851062774,
|
|
"num_tokens": 21162574.0,
|
|
"step": 10195
|
|
},
|
|
{
|
|
"entropy": 5.76557240486145,
|
|
"epoch": 0.9252539912917271,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004921708470102309,
|
|
"loss": 5.5431,
|
|
"mean_token_accuracy": 0.15791449397802354,
|
|
"num_tokens": 21172637.0,
|
|
"step": 10200
|
|
},
|
|
{
|
|
"entropy": 5.703016233444214,
|
|
"epoch": 0.9257075471698113,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.000492162383595366,
|
|
"loss": 5.5196,
|
|
"mean_token_accuracy": 0.1647072985768318,
|
|
"num_tokens": 21182272.0,
|
|
"step": 10205
|
|
},
|
|
{
|
|
"entropy": 5.76190505027771,
|
|
"epoch": 0.9261611030478955,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004921539156895275,
|
|
"loss": 5.6786,
|
|
"mean_token_accuracy": 0.1531767338514328,
|
|
"num_tokens": 21193712.0,
|
|
"step": 10210
|
|
},
|
|
{
|
|
"entropy": 5.872377538681031,
|
|
"epoch": 0.9266146589259797,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004921454432928908,
|
|
"loss": 5.6754,
|
|
"mean_token_accuracy": 0.15285923480987548,
|
|
"num_tokens": 21205104.0,
|
|
"step": 10215
|
|
},
|
|
{
|
|
"entropy": 5.786381530761719,
|
|
"epoch": 0.9270682148040639,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.000492136966405631,
|
|
"loss": 5.5586,
|
|
"mean_token_accuracy": 0.15872643887996674,
|
|
"num_tokens": 21215495.0,
|
|
"step": 10220
|
|
},
|
|
{
|
|
"entropy": 5.686816263198852,
|
|
"epoch": 0.927521770682148,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004921284850279233,
|
|
"loss": 5.5667,
|
|
"mean_token_accuracy": 0.15906285867094994,
|
|
"num_tokens": 21226047.0,
|
|
"step": 10225
|
|
},
|
|
{
|
|
"entropy": 5.746943521499634,
|
|
"epoch": 0.9279753265602322,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004921199991599433,
|
|
"loss": 5.6122,
|
|
"mean_token_accuracy": 0.15532758980989456,
|
|
"num_tokens": 21235784.0,
|
|
"step": 10230
|
|
},
|
|
{
|
|
"entropy": 5.7688275337219235,
|
|
"epoch": 0.9284288824383164,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004921115088018665,
|
|
"loss": 5.5973,
|
|
"mean_token_accuracy": 0.15728089362382888,
|
|
"num_tokens": 21245493.0,
|
|
"step": 10235
|
|
},
|
|
{
|
|
"entropy": 5.793758296966553,
|
|
"epoch": 0.9288824383164006,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.000492103013953868,
|
|
"loss": 5.681,
|
|
"mean_token_accuracy": 0.15494561791419983,
|
|
"num_tokens": 21255541.0,
|
|
"step": 10240
|
|
},
|
|
{
|
|
"entropy": 5.714980268478394,
|
|
"epoch": 0.9293359941944848,
|
|
"grad_norm": 3.265625,
|
|
"learning_rate": 0.0004920945146161242,
|
|
"loss": 5.5523,
|
|
"mean_token_accuracy": 0.1618171289563179,
|
|
"num_tokens": 21265427.0,
|
|
"step": 10245
|
|
},
|
|
{
|
|
"entropy": 5.71985969543457,
|
|
"epoch": 0.9297895500725689,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004920860107888105,
|
|
"loss": 5.5358,
|
|
"mean_token_accuracy": 0.16401754319667816,
|
|
"num_tokens": 21276597.0,
|
|
"step": 10250
|
|
},
|
|
{
|
|
"entropy": 5.688370609283448,
|
|
"epoch": 0.9302431059506531,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004920775024721026,
|
|
"loss": 5.5493,
|
|
"mean_token_accuracy": 0.15901543945074081,
|
|
"num_tokens": 21286416.0,
|
|
"step": 10255
|
|
},
|
|
{
|
|
"entropy": 5.701195192337036,
|
|
"epoch": 0.9306966618287373,
|
|
"grad_norm": 3.546875,
|
|
"learning_rate": 0.0004920689896661767,
|
|
"loss": 5.5874,
|
|
"mean_token_accuracy": 0.16366804093122483,
|
|
"num_tokens": 21296064.0,
|
|
"step": 10260
|
|
},
|
|
{
|
|
"entropy": 5.706859970092774,
|
|
"epoch": 0.9311502177068215,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004920604723712088,
|
|
"loss": 5.5935,
|
|
"mean_token_accuracy": 0.1625378280878067,
|
|
"num_tokens": 21306836.0,
|
|
"step": 10265
|
|
},
|
|
{
|
|
"entropy": 5.728276586532592,
|
|
"epoch": 0.9316037735849056,
|
|
"grad_norm": 3.53125,
|
|
"learning_rate": 0.0004920519505873751,
|
|
"loss": 5.534,
|
|
"mean_token_accuracy": 0.1601184770464897,
|
|
"num_tokens": 21316936.0,
|
|
"step": 10270
|
|
},
|
|
{
|
|
"entropy": 5.669115114212036,
|
|
"epoch": 0.9320573294629898,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004920434243148515,
|
|
"loss": 5.5019,
|
|
"mean_token_accuracy": 0.16560987532138824,
|
|
"num_tokens": 21326892.0,
|
|
"step": 10275
|
|
},
|
|
{
|
|
"entropy": 5.679602527618409,
|
|
"epoch": 0.9325108853410741,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004920348935538147,
|
|
"loss": 5.5251,
|
|
"mean_token_accuracy": 0.15770047008991242,
|
|
"num_tokens": 21337270.0,
|
|
"step": 10280
|
|
},
|
|
{
|
|
"entropy": 5.726852130889893,
|
|
"epoch": 0.9329644412191582,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.000492026358304441,
|
|
"loss": 5.6009,
|
|
"mean_token_accuracy": 0.15970801413059235,
|
|
"num_tokens": 21347968.0,
|
|
"step": 10285
|
|
},
|
|
{
|
|
"entropy": 5.754641675949097,
|
|
"epoch": 0.9334179970972424,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.000492017818566907,
|
|
"loss": 5.5441,
|
|
"mean_token_accuracy": 0.1618800103664398,
|
|
"num_tokens": 21358312.0,
|
|
"step": 10290
|
|
},
|
|
{
|
|
"entropy": 5.7076489448547365,
|
|
"epoch": 0.9338715529753265,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004920092743413892,
|
|
"loss": 5.5121,
|
|
"mean_token_accuracy": 0.16127585023641586,
|
|
"num_tokens": 21368794.0,
|
|
"step": 10295
|
|
},
|
|
{
|
|
"entropy": 5.743037223815918,
|
|
"epoch": 0.9343251088534107,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004920007256280642,
|
|
"loss": 5.5908,
|
|
"mean_token_accuracy": 0.16281366348266602,
|
|
"num_tokens": 21380080.0,
|
|
"step": 10300
|
|
},
|
|
{
|
|
"entropy": 5.695143842697144,
|
|
"epoch": 0.934778664731495,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.000491992172427109,
|
|
"loss": 5.5623,
|
|
"mean_token_accuracy": 0.16116022020578386,
|
|
"num_tokens": 21389961.0,
|
|
"step": 10305
|
|
},
|
|
{
|
|
"entropy": 5.671670532226562,
|
|
"epoch": 0.9352322206095791,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004919836147387002,
|
|
"loss": 5.5927,
|
|
"mean_token_accuracy": 0.1575816258788109,
|
|
"num_tokens": 21399869.0,
|
|
"step": 10310
|
|
},
|
|
{
|
|
"entropy": 5.765423774719238,
|
|
"epoch": 0.9356857764876633,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004919750525630151,
|
|
"loss": 5.5661,
|
|
"mean_token_accuracy": 0.16243053376674652,
|
|
"num_tokens": 21410343.0,
|
|
"step": 10315
|
|
},
|
|
{
|
|
"entropy": 5.789439678192139,
|
|
"epoch": 0.9361393323657474,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004919664859002306,
|
|
"loss": 5.5719,
|
|
"mean_token_accuracy": 0.1623935803771019,
|
|
"num_tokens": 21420915.0,
|
|
"step": 10320
|
|
},
|
|
{
|
|
"entropy": 5.727806663513183,
|
|
"epoch": 0.9365928882438317,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004919579147505239,
|
|
"loss": 5.5525,
|
|
"mean_token_accuracy": 0.16105083078145982,
|
|
"num_tokens": 21430879.0,
|
|
"step": 10325
|
|
},
|
|
{
|
|
"entropy": 5.68541989326477,
|
|
"epoch": 0.9370464441219158,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004919493391140721,
|
|
"loss": 5.6098,
|
|
"mean_token_accuracy": 0.1578335464000702,
|
|
"num_tokens": 21440843.0,
|
|
"step": 10330
|
|
},
|
|
{
|
|
"entropy": 5.790419816970825,
|
|
"epoch": 0.9375,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004919407589910529,
|
|
"loss": 5.754,
|
|
"mean_token_accuracy": 0.1557375095784664,
|
|
"num_tokens": 21452132.0,
|
|
"step": 10335
|
|
},
|
|
{
|
|
"entropy": 5.821562814712524,
|
|
"epoch": 0.9379535558780842,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004919321743816434,
|
|
"loss": 5.5643,
|
|
"mean_token_accuracy": 0.15840052515268327,
|
|
"num_tokens": 21461861.0,
|
|
"step": 10340
|
|
},
|
|
{
|
|
"entropy": 5.671965932846069,
|
|
"epoch": 0.9384071117561683,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004919235852860213,
|
|
"loss": 5.5745,
|
|
"mean_token_accuracy": 0.15618836730718613,
|
|
"num_tokens": 21472244.0,
|
|
"step": 10345
|
|
},
|
|
{
|
|
"entropy": 5.752170658111572,
|
|
"epoch": 0.9388606676342526,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004919149917043641,
|
|
"loss": 5.5925,
|
|
"mean_token_accuracy": 0.15857935845851898,
|
|
"num_tokens": 21482394.0,
|
|
"step": 10350
|
|
},
|
|
{
|
|
"entropy": 5.723880100250244,
|
|
"epoch": 0.9393142235123367,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004919063936368496,
|
|
"loss": 5.6628,
|
|
"mean_token_accuracy": 0.15386396050453185,
|
|
"num_tokens": 21493334.0,
|
|
"step": 10355
|
|
},
|
|
{
|
|
"entropy": 5.815063524246216,
|
|
"epoch": 0.9397677793904209,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004918977910836557,
|
|
"loss": 5.6049,
|
|
"mean_token_accuracy": 0.15854459404945373,
|
|
"num_tokens": 21504443.0,
|
|
"step": 10360
|
|
},
|
|
{
|
|
"entropy": 5.803659248352051,
|
|
"epoch": 0.940221335268505,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004918891840449601,
|
|
"loss": 5.6387,
|
|
"mean_token_accuracy": 0.15675927847623825,
|
|
"num_tokens": 21513908.0,
|
|
"step": 10365
|
|
},
|
|
{
|
|
"entropy": 5.7707844257354735,
|
|
"epoch": 0.9406748911465893,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.000491880572520941,
|
|
"loss": 5.655,
|
|
"mean_token_accuracy": 0.15043093115091324,
|
|
"num_tokens": 21524349.0,
|
|
"step": 10370
|
|
},
|
|
{
|
|
"entropy": 5.886355209350586,
|
|
"epoch": 0.9411284470246735,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004918719565117763,
|
|
"loss": 5.7013,
|
|
"mean_token_accuracy": 0.1616875097155571,
|
|
"num_tokens": 21535003.0,
|
|
"step": 10375
|
|
},
|
|
{
|
|
"entropy": 5.835240745544434,
|
|
"epoch": 0.9415820029027576,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004918633360176444,
|
|
"loss": 5.7378,
|
|
"mean_token_accuracy": 0.14841335862874985,
|
|
"num_tokens": 21545045.0,
|
|
"step": 10380
|
|
},
|
|
{
|
|
"entropy": 5.704664134979248,
|
|
"epoch": 0.9420355587808418,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004918547110387234,
|
|
"loss": 5.5465,
|
|
"mean_token_accuracy": 0.16263900846242904,
|
|
"num_tokens": 21554830.0,
|
|
"step": 10385
|
|
},
|
|
{
|
|
"entropy": 5.758695077896118,
|
|
"epoch": 0.9424891146589259,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004918460815751916,
|
|
"loss": 5.4953,
|
|
"mean_token_accuracy": 0.16329609602689743,
|
|
"num_tokens": 21564693.0,
|
|
"step": 10390
|
|
},
|
|
{
|
|
"entropy": 5.666661930084229,
|
|
"epoch": 0.9429426705370102,
|
|
"grad_norm": 3.125,
|
|
"learning_rate": 0.0004918374476272277,
|
|
"loss": 5.5281,
|
|
"mean_token_accuracy": 0.15839752107858657,
|
|
"num_tokens": 21575475.0,
|
|
"step": 10395
|
|
},
|
|
{
|
|
"entropy": 5.687856292724609,
|
|
"epoch": 0.9433962264150944,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004918288091950101,
|
|
"loss": 5.5606,
|
|
"mean_token_accuracy": 0.1579371616244316,
|
|
"num_tokens": 21586944.0,
|
|
"step": 10400
|
|
},
|
|
{
|
|
"entropy": 5.78514256477356,
|
|
"epoch": 0.9438497822931785,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004918201662787174,
|
|
"loss": 5.5737,
|
|
"mean_token_accuracy": 0.15969933271408082,
|
|
"num_tokens": 21598170.0,
|
|
"step": 10405
|
|
},
|
|
{
|
|
"entropy": 5.717104768753051,
|
|
"epoch": 0.9443033381712627,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004918115188785285,
|
|
"loss": 5.5973,
|
|
"mean_token_accuracy": 0.15898082852363588,
|
|
"num_tokens": 21609170.0,
|
|
"step": 10410
|
|
},
|
|
{
|
|
"entropy": 5.723949337005616,
|
|
"epoch": 0.9447568940493469,
|
|
"grad_norm": 3.0625,
|
|
"learning_rate": 0.0004918028669946221,
|
|
"loss": 5.6556,
|
|
"mean_token_accuracy": 0.15472547709941864,
|
|
"num_tokens": 21620171.0,
|
|
"step": 10415
|
|
},
|
|
{
|
|
"entropy": 5.791909217834473,
|
|
"epoch": 0.9452104499274311,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004917942106271771,
|
|
"loss": 5.5991,
|
|
"mean_token_accuracy": 0.16507237255573273,
|
|
"num_tokens": 21631072.0,
|
|
"step": 10420
|
|
},
|
|
{
|
|
"entropy": 5.69100513458252,
|
|
"epoch": 0.9456640058055152,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004917855497763727,
|
|
"loss": 5.4813,
|
|
"mean_token_accuracy": 0.16690109223127364,
|
|
"num_tokens": 21641543.0,
|
|
"step": 10425
|
|
},
|
|
{
|
|
"entropy": 5.654993677139283,
|
|
"epoch": 0.9461175616835994,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004917768844423878,
|
|
"loss": 5.5513,
|
|
"mean_token_accuracy": 0.16481663584709166,
|
|
"num_tokens": 21651342.0,
|
|
"step": 10430
|
|
},
|
|
{
|
|
"entropy": 5.761093950271606,
|
|
"epoch": 0.9465711175616836,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004917682146254017,
|
|
"loss": 5.5677,
|
|
"mean_token_accuracy": 0.16089554727077485,
|
|
"num_tokens": 21661043.0,
|
|
"step": 10435
|
|
},
|
|
{
|
|
"entropy": 5.649997282028198,
|
|
"epoch": 0.9470246734397678,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004917595403255938,
|
|
"loss": 5.4286,
|
|
"mean_token_accuracy": 0.17025154381990432,
|
|
"num_tokens": 21671197.0,
|
|
"step": 10440
|
|
},
|
|
{
|
|
"entropy": 5.654812860488891,
|
|
"epoch": 0.947478229317852,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004917508615431431,
|
|
"loss": 5.5295,
|
|
"mean_token_accuracy": 0.16596133708953859,
|
|
"num_tokens": 21682066.0,
|
|
"step": 10445
|
|
},
|
|
{
|
|
"entropy": 5.777668142318726,
|
|
"epoch": 0.9479317851959361,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004917421782782296,
|
|
"loss": 5.542,
|
|
"mean_token_accuracy": 0.16426764875650407,
|
|
"num_tokens": 21692117.0,
|
|
"step": 10450
|
|
},
|
|
{
|
|
"entropy": 5.754195785522461,
|
|
"epoch": 0.9483853410740203,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004917334905310325,
|
|
"loss": 5.6553,
|
|
"mean_token_accuracy": 0.15230924338102342,
|
|
"num_tokens": 21703544.0,
|
|
"step": 10455
|
|
},
|
|
{
|
|
"entropy": 5.64917631149292,
|
|
"epoch": 0.9488388969521045,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004917247983017317,
|
|
"loss": 5.4829,
|
|
"mean_token_accuracy": 0.1654343843460083,
|
|
"num_tokens": 21712850.0,
|
|
"step": 10460
|
|
},
|
|
{
|
|
"entropy": 5.745579099655151,
|
|
"epoch": 0.9492924528301887,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004917161015905067,
|
|
"loss": 5.6386,
|
|
"mean_token_accuracy": 0.1610898956656456,
|
|
"num_tokens": 21723015.0,
|
|
"step": 10465
|
|
},
|
|
{
|
|
"entropy": 5.7261152267456055,
|
|
"epoch": 0.9497460087082729,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004917074003975376,
|
|
"loss": 5.5898,
|
|
"mean_token_accuracy": 0.16066878885030747,
|
|
"num_tokens": 21732453.0,
|
|
"step": 10470
|
|
},
|
|
{
|
|
"entropy": 5.764086103439331,
|
|
"epoch": 0.950199564586357,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004916986947230042,
|
|
"loss": 5.6661,
|
|
"mean_token_accuracy": 0.15524275749921798,
|
|
"num_tokens": 21743251.0,
|
|
"step": 10475
|
|
},
|
|
{
|
|
"entropy": 5.756217336654663,
|
|
"epoch": 0.9506531204644412,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004916899845670866,
|
|
"loss": 5.5611,
|
|
"mean_token_accuracy": 0.1617263749241829,
|
|
"num_tokens": 21752891.0,
|
|
"step": 10480
|
|
},
|
|
{
|
|
"entropy": 5.776319932937622,
|
|
"epoch": 0.9511066763425254,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004916812699299649,
|
|
"loss": 5.5946,
|
|
"mean_token_accuracy": 0.1624079540371895,
|
|
"num_tokens": 21763230.0,
|
|
"step": 10485
|
|
},
|
|
{
|
|
"entropy": 5.723873710632324,
|
|
"epoch": 0.9515602322206096,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004916725508118193,
|
|
"loss": 5.5304,
|
|
"mean_token_accuracy": 0.15907608419656755,
|
|
"num_tokens": 21773663.0,
|
|
"step": 10490
|
|
},
|
|
{
|
|
"entropy": 5.679456901550293,
|
|
"epoch": 0.9520137880986937,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004916638272128301,
|
|
"loss": 5.5993,
|
|
"mean_token_accuracy": 0.1635532185435295,
|
|
"num_tokens": 21784265.0,
|
|
"step": 10495
|
|
},
|
|
{
|
|
"entropy": 5.666326427459717,
|
|
"epoch": 0.9524673439767779,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.0004916550991331777,
|
|
"loss": 5.5472,
|
|
"mean_token_accuracy": 0.16278686970472336,
|
|
"num_tokens": 21795056.0,
|
|
"step": 10500
|
|
},
|
|
{
|
|
"entropy": 5.731073904037475,
|
|
"epoch": 0.9529208998548622,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004916463665730427,
|
|
"loss": 5.5673,
|
|
"mean_token_accuracy": 0.1608913153409958,
|
|
"num_tokens": 21806204.0,
|
|
"step": 10505
|
|
},
|
|
{
|
|
"entropy": 5.729255056381225,
|
|
"epoch": 0.9533744557329463,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004916376295326057,
|
|
"loss": 5.5749,
|
|
"mean_token_accuracy": 0.1589621901512146,
|
|
"num_tokens": 21816993.0,
|
|
"step": 10510
|
|
},
|
|
{
|
|
"entropy": 5.725329875946045,
|
|
"epoch": 0.9538280116110305,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004916288880120472,
|
|
"loss": 5.4711,
|
|
"mean_token_accuracy": 0.17211252748966216,
|
|
"num_tokens": 21827457.0,
|
|
"step": 10515
|
|
},
|
|
{
|
|
"entropy": 5.685123109817505,
|
|
"epoch": 0.9542815674891146,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004916201420115482,
|
|
"loss": 5.5547,
|
|
"mean_token_accuracy": 0.15967754572629927,
|
|
"num_tokens": 21837555.0,
|
|
"step": 10520
|
|
},
|
|
{
|
|
"entropy": 5.72112889289856,
|
|
"epoch": 0.9547351233671988,
|
|
"grad_norm": 5.34375,
|
|
"learning_rate": 0.0004916113915312895,
|
|
"loss": 5.5712,
|
|
"mean_token_accuracy": 0.16629983186721803,
|
|
"num_tokens": 21847074.0,
|
|
"step": 10525
|
|
},
|
|
{
|
|
"entropy": 5.7932701587677,
|
|
"epoch": 0.9551886792452831,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004916026365714519,
|
|
"loss": 5.5829,
|
|
"mean_token_accuracy": 0.1557852029800415,
|
|
"num_tokens": 21858333.0,
|
|
"step": 10530
|
|
},
|
|
{
|
|
"entropy": 5.718509674072266,
|
|
"epoch": 0.9556422351233672,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.0004915938771322165,
|
|
"loss": 5.573,
|
|
"mean_token_accuracy": 0.1609520584344864,
|
|
"num_tokens": 21869132.0,
|
|
"step": 10535
|
|
},
|
|
{
|
|
"entropy": 5.6675629138946535,
|
|
"epoch": 0.9560957910014514,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004915851132137646,
|
|
"loss": 5.6066,
|
|
"mean_token_accuracy": 0.15681025087833406,
|
|
"num_tokens": 21879153.0,
|
|
"step": 10540
|
|
},
|
|
{
|
|
"entropy": 5.730789852142334,
|
|
"epoch": 0.9565493468795355,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004915763448162774,
|
|
"loss": 5.4994,
|
|
"mean_token_accuracy": 0.16314371675252914,
|
|
"num_tokens": 21889063.0,
|
|
"step": 10545
|
|
},
|
|
{
|
|
"entropy": 5.799360656738282,
|
|
"epoch": 0.9570029027576198,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004915675719399362,
|
|
"loss": 5.6081,
|
|
"mean_token_accuracy": 0.16106370240449905,
|
|
"num_tokens": 21899005.0,
|
|
"step": 10550
|
|
},
|
|
{
|
|
"entropy": 5.763070917129516,
|
|
"epoch": 0.9574564586357039,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.0004915587945849225,
|
|
"loss": 5.4763,
|
|
"mean_token_accuracy": 0.17053034156560898,
|
|
"num_tokens": 21908391.0,
|
|
"step": 10555
|
|
},
|
|
{
|
|
"entropy": 5.667698192596435,
|
|
"epoch": 0.9579100145137881,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004915500127514176,
|
|
"loss": 5.5408,
|
|
"mean_token_accuracy": 0.16174255609512328,
|
|
"num_tokens": 21917655.0,
|
|
"step": 10560
|
|
},
|
|
{
|
|
"entropy": 5.815259552001953,
|
|
"epoch": 0.9583635703918723,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004915412264396034,
|
|
"loss": 5.6307,
|
|
"mean_token_accuracy": 0.165455462038517,
|
|
"num_tokens": 21928038.0,
|
|
"step": 10565
|
|
},
|
|
{
|
|
"entropy": 5.764777517318725,
|
|
"epoch": 0.9588171262699564,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004915324356496613,
|
|
"loss": 5.5159,
|
|
"mean_token_accuracy": 0.165106962621212,
|
|
"num_tokens": 21938106.0,
|
|
"step": 10570
|
|
},
|
|
{
|
|
"entropy": 5.667822265625,
|
|
"epoch": 0.9592706821480407,
|
|
"grad_norm": 4.875,
|
|
"learning_rate": 0.0004915236403817733,
|
|
"loss": 5.4999,
|
|
"mean_token_accuracy": 0.16644544154405594,
|
|
"num_tokens": 21947484.0,
|
|
"step": 10575
|
|
},
|
|
{
|
|
"entropy": 5.7512171268463135,
|
|
"epoch": 0.9597242380261248,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004915148406361213,
|
|
"loss": 5.5966,
|
|
"mean_token_accuracy": 0.1602084219455719,
|
|
"num_tokens": 21957139.0,
|
|
"step": 10580
|
|
},
|
|
{
|
|
"entropy": 5.72621111869812,
|
|
"epoch": 0.960177793904209,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004915060364128872,
|
|
"loss": 5.5785,
|
|
"mean_token_accuracy": 0.159201742708683,
|
|
"num_tokens": 21967030.0,
|
|
"step": 10585
|
|
},
|
|
{
|
|
"entropy": 5.70787091255188,
|
|
"epoch": 0.9606313497822931,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004914972277122532,
|
|
"loss": 5.5386,
|
|
"mean_token_accuracy": 0.16124513894319534,
|
|
"num_tokens": 21976418.0,
|
|
"step": 10590
|
|
},
|
|
{
|
|
"entropy": 5.735023641586304,
|
|
"epoch": 0.9610849056603774,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004914884145344012,
|
|
"loss": 5.5667,
|
|
"mean_token_accuracy": 0.16151599138975142,
|
|
"num_tokens": 21987284.0,
|
|
"step": 10595
|
|
},
|
|
{
|
|
"entropy": 5.627045154571533,
|
|
"epoch": 0.9615384615384616,
|
|
"grad_norm": 4.125,
|
|
"learning_rate": 0.0004914795968795137,
|
|
"loss": 5.4591,
|
|
"mean_token_accuracy": 0.16637159138917923,
|
|
"num_tokens": 21997106.0,
|
|
"step": 10600
|
|
},
|
|
{
|
|
"entropy": 5.649648571014405,
|
|
"epoch": 0.9619920174165457,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004914707747477728,
|
|
"loss": 5.4627,
|
|
"mean_token_accuracy": 0.16458913683891296,
|
|
"num_tokens": 22007589.0,
|
|
"step": 10605
|
|
},
|
|
{
|
|
"entropy": 5.738597059249878,
|
|
"epoch": 0.9624455732946299,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004914619481393613,
|
|
"loss": 5.5757,
|
|
"mean_token_accuracy": 0.1593085527420044,
|
|
"num_tokens": 22017669.0,
|
|
"step": 10610
|
|
},
|
|
{
|
|
"entropy": 5.850301122665405,
|
|
"epoch": 0.962899129172714,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004914531170544615,
|
|
"loss": 5.7465,
|
|
"mean_token_accuracy": 0.15058881491422654,
|
|
"num_tokens": 22029330.0,
|
|
"step": 10615
|
|
},
|
|
{
|
|
"entropy": 5.706385087966919,
|
|
"epoch": 0.9633526850507983,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004914442814932561,
|
|
"loss": 5.5122,
|
|
"mean_token_accuracy": 0.15858547165989875,
|
|
"num_tokens": 22039877.0,
|
|
"step": 10620
|
|
},
|
|
{
|
|
"entropy": 5.70743145942688,
|
|
"epoch": 0.9638062409288825,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004914354414559278,
|
|
"loss": 5.5573,
|
|
"mean_token_accuracy": 0.1631301075220108,
|
|
"num_tokens": 22049579.0,
|
|
"step": 10625
|
|
},
|
|
{
|
|
"entropy": 5.654441833496094,
|
|
"epoch": 0.9642597968069666,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004914265969426594,
|
|
"loss": 5.4514,
|
|
"mean_token_accuracy": 0.1729304686188698,
|
|
"num_tokens": 22059608.0,
|
|
"step": 10630
|
|
},
|
|
{
|
|
"entropy": 5.734684801101684,
|
|
"epoch": 0.9647133526850508,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004914177479536338,
|
|
"loss": 5.5893,
|
|
"mean_token_accuracy": 0.16089479848742486,
|
|
"num_tokens": 22070036.0,
|
|
"step": 10635
|
|
},
|
|
{
|
|
"entropy": 5.69744758605957,
|
|
"epoch": 0.965166908563135,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.000491408894489034,
|
|
"loss": 5.5981,
|
|
"mean_token_accuracy": 0.15690391808748244,
|
|
"num_tokens": 22080679.0,
|
|
"step": 10640
|
|
},
|
|
{
|
|
"entropy": 5.714641809463501,
|
|
"epoch": 0.9656204644412192,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004914000365490432,
|
|
"loss": 5.4326,
|
|
"mean_token_accuracy": 0.16730457097291945,
|
|
"num_tokens": 22092192.0,
|
|
"step": 10645
|
|
},
|
|
{
|
|
"entropy": 5.755234003067017,
|
|
"epoch": 0.9660740203193033,
|
|
"grad_norm": 3.09375,
|
|
"learning_rate": 0.0004913911741338445,
|
|
"loss": 5.6146,
|
|
"mean_token_accuracy": 0.15648854225873948,
|
|
"num_tokens": 22102722.0,
|
|
"step": 10650
|
|
},
|
|
{
|
|
"entropy": 5.649051523208618,
|
|
"epoch": 0.9665275761973875,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004913823072436211,
|
|
"loss": 5.5007,
|
|
"mean_token_accuracy": 0.16615082323551178,
|
|
"num_tokens": 22113521.0,
|
|
"step": 10655
|
|
},
|
|
{
|
|
"entropy": 5.74636926651001,
|
|
"epoch": 0.9669811320754716,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004913734358785565,
|
|
"loss": 5.6001,
|
|
"mean_token_accuracy": 0.16211069673299788,
|
|
"num_tokens": 22124891.0,
|
|
"step": 10660
|
|
},
|
|
{
|
|
"entropy": 5.719308185577392,
|
|
"epoch": 0.9674346879535559,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004913645600388341,
|
|
"loss": 5.5751,
|
|
"mean_token_accuracy": 0.15703691840171813,
|
|
"num_tokens": 22135972.0,
|
|
"step": 10665
|
|
},
|
|
{
|
|
"entropy": 5.794891214370727,
|
|
"epoch": 0.9678882438316401,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004913556797246374,
|
|
"loss": 5.6231,
|
|
"mean_token_accuracy": 0.15371696650981903,
|
|
"num_tokens": 22146623.0,
|
|
"step": 10670
|
|
},
|
|
{
|
|
"entropy": 5.788426351547241,
|
|
"epoch": 0.9683417997097242,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.0004913467949361503,
|
|
"loss": 5.5443,
|
|
"mean_token_accuracy": 0.16075709462165833,
|
|
"num_tokens": 22157619.0,
|
|
"step": 10675
|
|
},
|
|
{
|
|
"entropy": 5.692183113098144,
|
|
"epoch": 0.9687953555878084,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004913379056735561,
|
|
"loss": 5.5548,
|
|
"mean_token_accuracy": 0.15465807020664216,
|
|
"num_tokens": 22168655.0,
|
|
"step": 10680
|
|
},
|
|
{
|
|
"entropy": 5.688295364379883,
|
|
"epoch": 0.9692489114658926,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.000491329011937039,
|
|
"loss": 5.5868,
|
|
"mean_token_accuracy": 0.15701992586255073,
|
|
"num_tokens": 22178500.0,
|
|
"step": 10685
|
|
},
|
|
{
|
|
"entropy": 5.80420241355896,
|
|
"epoch": 0.9697024673439768,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004913201137267828,
|
|
"loss": 5.5725,
|
|
"mean_token_accuracy": 0.15838107019662856,
|
|
"num_tokens": 22188873.0,
|
|
"step": 10690
|
|
},
|
|
{
|
|
"entropy": 5.698489236831665,
|
|
"epoch": 0.970156023222061,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004913112110429715,
|
|
"loss": 5.5071,
|
|
"mean_token_accuracy": 0.15958190113306045,
|
|
"num_tokens": 22199743.0,
|
|
"step": 10695
|
|
},
|
|
{
|
|
"entropy": 5.650565147399902,
|
|
"epoch": 0.9706095791001451,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004913023038857892,
|
|
"loss": 5.4762,
|
|
"mean_token_accuracy": 0.16382057666778566,
|
|
"num_tokens": 22210301.0,
|
|
"step": 10700
|
|
},
|
|
{
|
|
"entropy": 5.681193113327026,
|
|
"epoch": 0.9710631349782293,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004912933922554203,
|
|
"loss": 5.4813,
|
|
"mean_token_accuracy": 0.16924688071012498,
|
|
"num_tokens": 22220771.0,
|
|
"step": 10705
|
|
},
|
|
{
|
|
"entropy": 5.7108416080474855,
|
|
"epoch": 0.9715166908563135,
|
|
"grad_norm": 3.359375,
|
|
"learning_rate": 0.0004912844761520487,
|
|
"loss": 5.5658,
|
|
"mean_token_accuracy": 0.15979118421673774,
|
|
"num_tokens": 22231100.0,
|
|
"step": 10710
|
|
},
|
|
{
|
|
"entropy": 5.739949893951416,
|
|
"epoch": 0.9719702467343977,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004912755555758592,
|
|
"loss": 5.5618,
|
|
"mean_token_accuracy": 0.1600915715098381,
|
|
"num_tokens": 22240997.0,
|
|
"step": 10715
|
|
},
|
|
{
|
|
"entropy": 5.680482530593872,
|
|
"epoch": 0.9724238026124818,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.000491266630527036,
|
|
"loss": 5.5696,
|
|
"mean_token_accuracy": 0.1592530682682991,
|
|
"num_tokens": 22251795.0,
|
|
"step": 10720
|
|
},
|
|
{
|
|
"entropy": 5.785782337188721,
|
|
"epoch": 0.972877358490566,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004912577010057638,
|
|
"loss": 5.6312,
|
|
"mean_token_accuracy": 0.15350310355424882,
|
|
"num_tokens": 22262465.0,
|
|
"step": 10725
|
|
},
|
|
{
|
|
"entropy": 5.860809850692749,
|
|
"epoch": 0.9733309143686503,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004912487670122273,
|
|
"loss": 5.7117,
|
|
"mean_token_accuracy": 0.15684562176465988,
|
|
"num_tokens": 22272399.0,
|
|
"step": 10730
|
|
},
|
|
{
|
|
"entropy": 5.769578075408935,
|
|
"epoch": 0.9737844702467344,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004912398285466111,
|
|
"loss": 5.6449,
|
|
"mean_token_accuracy": 0.15478661060333251,
|
|
"num_tokens": 22282545.0,
|
|
"step": 10735
|
|
},
|
|
{
|
|
"entropy": 5.745041799545288,
|
|
"epoch": 0.9742380261248186,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004912308856091002,
|
|
"loss": 5.5668,
|
|
"mean_token_accuracy": 0.16344818621873855,
|
|
"num_tokens": 22293154.0,
|
|
"step": 10740
|
|
},
|
|
{
|
|
"entropy": 5.732537937164307,
|
|
"epoch": 0.9746915820029027,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004912219381998795,
|
|
"loss": 5.5202,
|
|
"mean_token_accuracy": 0.1639418214559555,
|
|
"num_tokens": 22302309.0,
|
|
"step": 10745
|
|
},
|
|
{
|
|
"entropy": 5.719917678833008,
|
|
"epoch": 0.9751451378809869,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004912129863191339,
|
|
"loss": 5.6337,
|
|
"mean_token_accuracy": 0.1525130420923233,
|
|
"num_tokens": 22312316.0,
|
|
"step": 10750
|
|
},
|
|
{
|
|
"entropy": 5.771625661849976,
|
|
"epoch": 0.9755986937590712,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004912040299670487,
|
|
"loss": 5.5943,
|
|
"mean_token_accuracy": 0.1620956376194954,
|
|
"num_tokens": 22322387.0,
|
|
"step": 10755
|
|
},
|
|
{
|
|
"entropy": 5.817542362213135,
|
|
"epoch": 0.9760522496371553,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004911950691438091,
|
|
"loss": 5.5621,
|
|
"mean_token_accuracy": 0.16862929463386536,
|
|
"num_tokens": 22332759.0,
|
|
"step": 10760
|
|
},
|
|
{
|
|
"entropy": 5.7432643413543705,
|
|
"epoch": 0.9765058055152395,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004911861038496004,
|
|
"loss": 5.6178,
|
|
"mean_token_accuracy": 0.16080676764249802,
|
|
"num_tokens": 22344056.0,
|
|
"step": 10765
|
|
},
|
|
{
|
|
"entropy": 5.669678401947022,
|
|
"epoch": 0.9769593613933236,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004911771340846079,
|
|
"loss": 5.5711,
|
|
"mean_token_accuracy": 0.15599628835916518,
|
|
"num_tokens": 22353877.0,
|
|
"step": 10770
|
|
},
|
|
{
|
|
"entropy": 5.775995683670044,
|
|
"epoch": 0.9774129172714079,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004911681598490172,
|
|
"loss": 5.5988,
|
|
"mean_token_accuracy": 0.1615854263305664,
|
|
"num_tokens": 22363549.0,
|
|
"step": 10775
|
|
},
|
|
{
|
|
"entropy": 5.829509258270264,
|
|
"epoch": 0.977866473149492,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004911591811430139,
|
|
"loss": 5.6585,
|
|
"mean_token_accuracy": 0.16007038503885268,
|
|
"num_tokens": 22374040.0,
|
|
"step": 10780
|
|
},
|
|
{
|
|
"entropy": 5.829401731491089,
|
|
"epoch": 0.9783200290275762,
|
|
"grad_norm": 2.984375,
|
|
"learning_rate": 0.0004911501979667836,
|
|
"loss": 5.7099,
|
|
"mean_token_accuracy": 0.1552772752940655,
|
|
"num_tokens": 22384819.0,
|
|
"step": 10785
|
|
},
|
|
{
|
|
"entropy": 5.765942192077636,
|
|
"epoch": 0.9787735849056604,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004911412103205122,
|
|
"loss": 5.5331,
|
|
"mean_token_accuracy": 0.16170297265052797,
|
|
"num_tokens": 22395130.0,
|
|
"step": 10790
|
|
},
|
|
{
|
|
"entropy": 5.678496885299682,
|
|
"epoch": 0.9792271407837445,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004911322182043855,
|
|
"loss": 5.5641,
|
|
"mean_token_accuracy": 0.16248281747102739,
|
|
"num_tokens": 22405093.0,
|
|
"step": 10795
|
|
},
|
|
{
|
|
"entropy": 5.727722120285034,
|
|
"epoch": 0.9796806966618288,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004911232216185893,
|
|
"loss": 5.5797,
|
|
"mean_token_accuracy": 0.15475896149873733,
|
|
"num_tokens": 22415008.0,
|
|
"step": 10800
|
|
},
|
|
{
|
|
"entropy": 5.789134883880616,
|
|
"epoch": 0.9801342525399129,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004911142205633099,
|
|
"loss": 5.6457,
|
|
"mean_token_accuracy": 0.1566619172692299,
|
|
"num_tokens": 22426486.0,
|
|
"step": 10805
|
|
},
|
|
{
|
|
"entropy": 5.751878976821899,
|
|
"epoch": 0.9805878084179971,
|
|
"grad_norm": 4.6875,
|
|
"learning_rate": 0.0004911052150387334,
|
|
"loss": 5.5407,
|
|
"mean_token_accuracy": 0.15937202721834182,
|
|
"num_tokens": 22436844.0,
|
|
"step": 10810
|
|
},
|
|
{
|
|
"entropy": 5.799398756027221,
|
|
"epoch": 0.9810413642960812,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004910962050450458,
|
|
"loss": 5.6831,
|
|
"mean_token_accuracy": 0.15681086331605912,
|
|
"num_tokens": 22446630.0,
|
|
"step": 10815
|
|
},
|
|
{
|
|
"entropy": 5.735904836654663,
|
|
"epoch": 0.9814949201741655,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004910871905824338,
|
|
"loss": 5.5139,
|
|
"mean_token_accuracy": 0.16504132747650146,
|
|
"num_tokens": 22456406.0,
|
|
"step": 10820
|
|
},
|
|
{
|
|
"entropy": 5.66645450592041,
|
|
"epoch": 0.9819484760522497,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004910781716510837,
|
|
"loss": 5.5224,
|
|
"mean_token_accuracy": 0.16115539371967316,
|
|
"num_tokens": 22466210.0,
|
|
"step": 10825
|
|
},
|
|
{
|
|
"entropy": 5.687051486968994,
|
|
"epoch": 0.9824020319303338,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004910691482511817,
|
|
"loss": 5.597,
|
|
"mean_token_accuracy": 0.16166132241487502,
|
|
"num_tokens": 22476978.0,
|
|
"step": 10830
|
|
},
|
|
{
|
|
"entropy": 5.84561562538147,
|
|
"epoch": 0.982855587808418,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004910601203829148,
|
|
"loss": 5.5722,
|
|
"mean_token_accuracy": 0.16071754544973374,
|
|
"num_tokens": 22488613.0,
|
|
"step": 10835
|
|
},
|
|
{
|
|
"entropy": 5.699246978759765,
|
|
"epoch": 0.9833091436865021,
|
|
"grad_norm": 3.296875,
|
|
"learning_rate": 0.0004910510880464696,
|
|
"loss": 5.4698,
|
|
"mean_token_accuracy": 0.1734047457575798,
|
|
"num_tokens": 22498312.0,
|
|
"step": 10840
|
|
},
|
|
{
|
|
"entropy": 5.660033941268921,
|
|
"epoch": 0.9837626995645864,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004910420512420327,
|
|
"loss": 5.5972,
|
|
"mean_token_accuracy": 0.15813935846090316,
|
|
"num_tokens": 22508131.0,
|
|
"step": 10845
|
|
},
|
|
{
|
|
"entropy": 5.752862119674683,
|
|
"epoch": 0.9842162554426706,
|
|
"grad_norm": 3.15625,
|
|
"learning_rate": 0.0004910330099697913,
|
|
"loss": 5.5836,
|
|
"mean_token_accuracy": 0.16345801204442978,
|
|
"num_tokens": 22517842.0,
|
|
"step": 10850
|
|
},
|
|
{
|
|
"entropy": 5.726582098007202,
|
|
"epoch": 0.9846698113207547,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004910239642299321,
|
|
"loss": 5.5544,
|
|
"mean_token_accuracy": 0.15972914397716523,
|
|
"num_tokens": 22528239.0,
|
|
"step": 10855
|
|
},
|
|
{
|
|
"entropy": 5.733843421936035,
|
|
"epoch": 0.9851233671988389,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004910149140226422,
|
|
"loss": 5.5417,
|
|
"mean_token_accuracy": 0.16060816943645478,
|
|
"num_tokens": 22539734.0,
|
|
"step": 10860
|
|
},
|
|
{
|
|
"entropy": 5.739208984375,
|
|
"epoch": 0.9855769230769231,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004910058593481089,
|
|
"loss": 5.5491,
|
|
"mean_token_accuracy": 0.16439297050237656,
|
|
"num_tokens": 22549796.0,
|
|
"step": 10865
|
|
},
|
|
{
|
|
"entropy": 5.62042760848999,
|
|
"epoch": 0.9860304789550073,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004909968002065195,
|
|
"loss": 5.5194,
|
|
"mean_token_accuracy": 0.16418687254190445,
|
|
"num_tokens": 22559934.0,
|
|
"step": 10870
|
|
},
|
|
{
|
|
"entropy": 5.776461553573609,
|
|
"epoch": 0.9864840348330914,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.000490987736598061,
|
|
"loss": 5.6138,
|
|
"mean_token_accuracy": 0.15013618245720864,
|
|
"num_tokens": 22569864.0,
|
|
"step": 10875
|
|
},
|
|
{
|
|
"entropy": 5.736488580703735,
|
|
"epoch": 0.9869375907111756,
|
|
"grad_norm": 3.15625,
|
|
"learning_rate": 0.0004909786685229211,
|
|
"loss": 5.5578,
|
|
"mean_token_accuracy": 0.16165782660245895,
|
|
"num_tokens": 22580687.0,
|
|
"step": 10880
|
|
},
|
|
{
|
|
"entropy": 5.789476490020752,
|
|
"epoch": 0.9873911465892597,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004909695959812875,
|
|
"loss": 5.6041,
|
|
"mean_token_accuracy": 0.16118057519197465,
|
|
"num_tokens": 22590507.0,
|
|
"step": 10885
|
|
},
|
|
{
|
|
"entropy": 5.788194942474365,
|
|
"epoch": 0.987844702467344,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004909605189733474,
|
|
"loss": 5.6503,
|
|
"mean_token_accuracy": 0.1631125494837761,
|
|
"num_tokens": 22601901.0,
|
|
"step": 10890
|
|
},
|
|
{
|
|
"entropy": 5.705813884735107,
|
|
"epoch": 0.9882982583454282,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004909514374992889,
|
|
"loss": 5.5789,
|
|
"mean_token_accuracy": 0.16136145442724228,
|
|
"num_tokens": 22613003.0,
|
|
"step": 10895
|
|
},
|
|
{
|
|
"entropy": 5.765278148651123,
|
|
"epoch": 0.9887518142235123,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004909423515592996,
|
|
"loss": 5.4413,
|
|
"mean_token_accuracy": 0.16426870822906495,
|
|
"num_tokens": 22623401.0,
|
|
"step": 10900
|
|
},
|
|
{
|
|
"entropy": 5.72953429222107,
|
|
"epoch": 0.9892053701015965,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004909332611535675,
|
|
"loss": 5.586,
|
|
"mean_token_accuracy": 0.16077908277511596,
|
|
"num_tokens": 22633147.0,
|
|
"step": 10905
|
|
},
|
|
{
|
|
"entropy": 5.64373745918274,
|
|
"epoch": 0.9896589259796807,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004909241662822804,
|
|
"loss": 5.418,
|
|
"mean_token_accuracy": 0.17826375216245652,
|
|
"num_tokens": 22642990.0,
|
|
"step": 10910
|
|
},
|
|
{
|
|
"entropy": 5.674500799179077,
|
|
"epoch": 0.9901124818577649,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004909150669456265,
|
|
"loss": 5.6498,
|
|
"mean_token_accuracy": 0.15278446823358535,
|
|
"num_tokens": 22652734.0,
|
|
"step": 10915
|
|
},
|
|
{
|
|
"entropy": 5.754950618743896,
|
|
"epoch": 0.9905660377358491,
|
|
"grad_norm": 3.671875,
|
|
"learning_rate": 0.000490905963143794,
|
|
"loss": 5.6636,
|
|
"mean_token_accuracy": 0.1509729042649269,
|
|
"num_tokens": 22662968.0,
|
|
"step": 10920
|
|
},
|
|
{
|
|
"entropy": 5.717150115966797,
|
|
"epoch": 0.9910195936139332,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004908968548769713,
|
|
"loss": 5.4636,
|
|
"mean_token_accuracy": 0.171461820602417,
|
|
"num_tokens": 22673157.0,
|
|
"step": 10925
|
|
},
|
|
{
|
|
"entropy": 5.713420248031616,
|
|
"epoch": 0.9914731494920174,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004908877421453466,
|
|
"loss": 5.6151,
|
|
"mean_token_accuracy": 0.15981991440057755,
|
|
"num_tokens": 22683105.0,
|
|
"step": 10930
|
|
},
|
|
{
|
|
"entropy": 5.786050939559937,
|
|
"epoch": 0.9919267053701016,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004908786249491082,
|
|
"loss": 5.5749,
|
|
"mean_token_accuracy": 0.16708844006061555,
|
|
"num_tokens": 22693793.0,
|
|
"step": 10935
|
|
},
|
|
{
|
|
"entropy": 5.878396320343017,
|
|
"epoch": 0.9923802612481858,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.000490869503288445,
|
|
"loss": 5.6106,
|
|
"mean_token_accuracy": 0.15875798910856248,
|
|
"num_tokens": 22703884.0,
|
|
"step": 10940
|
|
},
|
|
{
|
|
"entropy": 5.763932800292968,
|
|
"epoch": 0.99283381712627,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004908603771635454,
|
|
"loss": 5.6379,
|
|
"mean_token_accuracy": 0.15752845704555513,
|
|
"num_tokens": 22713699.0,
|
|
"step": 10945
|
|
},
|
|
{
|
|
"entropy": 5.781189060211181,
|
|
"epoch": 0.9932873730043541,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004908512465745982,
|
|
"loss": 5.481,
|
|
"mean_token_accuracy": 0.16702580600976943,
|
|
"num_tokens": 22722871.0,
|
|
"step": 10950
|
|
},
|
|
{
|
|
"entropy": 5.658702611923218,
|
|
"epoch": 0.9937409288824384,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004908421115217922,
|
|
"loss": 5.5156,
|
|
"mean_token_accuracy": 0.15721324533224107,
|
|
"num_tokens": 22733314.0,
|
|
"step": 10955
|
|
},
|
|
{
|
|
"entropy": 5.6310563564300535,
|
|
"epoch": 0.9941944847605225,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004908329720053164,
|
|
"loss": 5.5013,
|
|
"mean_token_accuracy": 0.16958092600107194,
|
|
"num_tokens": 22743255.0,
|
|
"step": 10960
|
|
},
|
|
{
|
|
"entropy": 5.6909441471099855,
|
|
"epoch": 0.9946480406386067,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004908238280253597,
|
|
"loss": 5.4918,
|
|
"mean_token_accuracy": 0.16851367354393004,
|
|
"num_tokens": 22753857.0,
|
|
"step": 10965
|
|
},
|
|
{
|
|
"entropy": 5.7038675308227536,
|
|
"epoch": 0.9951015965166908,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004908146795821112,
|
|
"loss": 5.4859,
|
|
"mean_token_accuracy": 0.15742357522249223,
|
|
"num_tokens": 22764326.0,
|
|
"step": 10970
|
|
},
|
|
{
|
|
"entropy": 5.703307294845581,
|
|
"epoch": 0.995555152394775,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004908055266757602,
|
|
"loss": 5.5662,
|
|
"mean_token_accuracy": 0.161642362177372,
|
|
"num_tokens": 22774958.0,
|
|
"step": 10975
|
|
},
|
|
{
|
|
"entropy": 5.712768840789795,
|
|
"epoch": 0.9960087082728593,
|
|
"grad_norm": 2.890625,
|
|
"learning_rate": 0.0004907963693064958,
|
|
"loss": 5.486,
|
|
"mean_token_accuracy": 0.16258807778358458,
|
|
"num_tokens": 22785616.0,
|
|
"step": 10980
|
|
},
|
|
{
|
|
"entropy": 5.819687604904175,
|
|
"epoch": 0.9964622641509434,
|
|
"grad_norm": 2.875,
|
|
"learning_rate": 0.0004907872074745075,
|
|
"loss": 5.6575,
|
|
"mean_token_accuracy": 0.15479800775647162,
|
|
"num_tokens": 22795967.0,
|
|
"step": 10985
|
|
},
|
|
{
|
|
"entropy": 5.696770811080933,
|
|
"epoch": 0.9969158200290276,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004907780411799849,
|
|
"loss": 5.6609,
|
|
"mean_token_accuracy": 0.1599399119615555,
|
|
"num_tokens": 22806335.0,
|
|
"step": 10990
|
|
},
|
|
{
|
|
"entropy": 5.751335668563843,
|
|
"epoch": 0.9973693759071117,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004907688704231173,
|
|
"loss": 5.56,
|
|
"mean_token_accuracy": 0.16738625019788742,
|
|
"num_tokens": 22816390.0,
|
|
"step": 10995
|
|
},
|
|
{
|
|
"entropy": 5.830067443847656,
|
|
"epoch": 0.997822931785196,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004907596952040945,
|
|
"loss": 5.644,
|
|
"mean_token_accuracy": 0.1559669032692909,
|
|
"num_tokens": 22826395.0,
|
|
"step": 11000
|
|
},
|
|
{
|
|
"entropy": 5.786629343032837,
|
|
"epoch": 0.9982764876632801,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004907505155231063,
|
|
"loss": 5.6213,
|
|
"mean_token_accuracy": 0.16246810108423232,
|
|
"num_tokens": 22836790.0,
|
|
"step": 11005
|
|
},
|
|
{
|
|
"entropy": 5.725517416000367,
|
|
"epoch": 0.9987300435413643,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.0004907413313803424,
|
|
"loss": 5.5155,
|
|
"mean_token_accuracy": 0.16071072071790696,
|
|
"num_tokens": 22846687.0,
|
|
"step": 11010
|
|
},
|
|
{
|
|
"entropy": 5.766845846176148,
|
|
"epoch": 0.9991835994194485,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004907321427759928,
|
|
"loss": 5.5257,
|
|
"mean_token_accuracy": 0.16574752032756807,
|
|
"num_tokens": 22857208.0,
|
|
"step": 11015
|
|
},
|
|
{
|
|
"entropy": 5.770552062988282,
|
|
"epoch": 0.9996371552975326,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004907229497102475,
|
|
"loss": 5.6656,
|
|
"mean_token_accuracy": 0.15088542252779008,
|
|
"num_tokens": 22868556.0,
|
|
"step": 11020
|
|
},
|
|
{
|
|
"entropy": 5.776932954788208,
|
|
"epoch": 1.0000907111756168,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004907137521832966,
|
|
"loss": 5.623,
|
|
"mean_token_accuracy": 0.16129784733057023,
|
|
"num_tokens": 22880081.0,
|
|
"step": 11025
|
|
},
|
|
{
|
|
"entropy": 5.745475149154663,
|
|
"epoch": 1.000544267053701,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004907045501953304,
|
|
"loss": 5.4612,
|
|
"mean_token_accuracy": 0.16633213609457015,
|
|
"num_tokens": 22892141.0,
|
|
"step": 11030
|
|
},
|
|
{
|
|
"entropy": 5.713094472885132,
|
|
"epoch": 1.0009978229317853,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.000490695343746539,
|
|
"loss": 5.5143,
|
|
"mean_token_accuracy": 0.1668661803007126,
|
|
"num_tokens": 22902688.0,
|
|
"step": 11035
|
|
},
|
|
{
|
|
"entropy": 5.581777143478393,
|
|
"epoch": 1.0014513788098693,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004906861328371131,
|
|
"loss": 5.4272,
|
|
"mean_token_accuracy": 0.16959985345602036,
|
|
"num_tokens": 22912453.0,
|
|
"step": 11040
|
|
},
|
|
{
|
|
"entropy": 5.726792812347412,
|
|
"epoch": 1.0019049346879536,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004906769174672429,
|
|
"loss": 5.5818,
|
|
"mean_token_accuracy": 0.15689807087183,
|
|
"num_tokens": 22923167.0,
|
|
"step": 11045
|
|
},
|
|
{
|
|
"entropy": 5.858908843994141,
|
|
"epoch": 1.0023584905660377,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.000490667697637119,
|
|
"loss": 5.5633,
|
|
"mean_token_accuracy": 0.15579785108566285,
|
|
"num_tokens": 22934753.0,
|
|
"step": 11050
|
|
},
|
|
{
|
|
"entropy": 5.709219932556152,
|
|
"epoch": 1.002812046444122,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004906584733469324,
|
|
"loss": 5.4789,
|
|
"mean_token_accuracy": 0.1702205315232277,
|
|
"num_tokens": 22945277.0,
|
|
"step": 11055
|
|
},
|
|
{
|
|
"entropy": 5.7002856731414795,
|
|
"epoch": 1.0032656023222062,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004906492445968735,
|
|
"loss": 5.5636,
|
|
"mean_token_accuracy": 0.1544661305844784,
|
|
"num_tokens": 22955797.0,
|
|
"step": 11060
|
|
},
|
|
{
|
|
"entropy": 5.747836065292359,
|
|
"epoch": 1.0037191582002902,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004906400113871332,
|
|
"loss": 5.5297,
|
|
"mean_token_accuracy": 0.16249612867832183,
|
|
"num_tokens": 22965969.0,
|
|
"step": 11065
|
|
},
|
|
{
|
|
"entropy": 5.671520948410034,
|
|
"epoch": 1.0041727140783745,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004906307737179026,
|
|
"loss": 5.4754,
|
|
"mean_token_accuracy": 0.17179337590932847,
|
|
"num_tokens": 22975323.0,
|
|
"step": 11070
|
|
},
|
|
{
|
|
"entropy": 5.649836444854737,
|
|
"epoch": 1.0046262699564585,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004906215315893726,
|
|
"loss": 5.4993,
|
|
"mean_token_accuracy": 0.1667332634329796,
|
|
"num_tokens": 22985063.0,
|
|
"step": 11075
|
|
},
|
|
{
|
|
"entropy": 5.739915657043457,
|
|
"epoch": 1.0050798258345428,
|
|
"grad_norm": 3.234375,
|
|
"learning_rate": 0.0004906122850017344,
|
|
"loss": 5.6441,
|
|
"mean_token_accuracy": 0.15481821447610855,
|
|
"num_tokens": 22996001.0,
|
|
"step": 11080
|
|
},
|
|
{
|
|
"entropy": 5.78344316482544,
|
|
"epoch": 1.005533381712627,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004906030339551792,
|
|
"loss": 5.5485,
|
|
"mean_token_accuracy": 0.15982701778411865,
|
|
"num_tokens": 23006896.0,
|
|
"step": 11085
|
|
},
|
|
{
|
|
"entropy": 5.775651979446411,
|
|
"epoch": 1.0059869375907111,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004905937784498983,
|
|
"loss": 5.5207,
|
|
"mean_token_accuracy": 0.16342724859714508,
|
|
"num_tokens": 23017080.0,
|
|
"step": 11090
|
|
},
|
|
{
|
|
"entropy": 5.750964403152466,
|
|
"epoch": 1.0064404934687954,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004905845184860831,
|
|
"loss": 5.4843,
|
|
"mean_token_accuracy": 0.16523307263851167,
|
|
"num_tokens": 23027168.0,
|
|
"step": 11095
|
|
},
|
|
{
|
|
"entropy": 5.675059747695923,
|
|
"epoch": 1.0068940493468794,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004905752540639252,
|
|
"loss": 5.5186,
|
|
"mean_token_accuracy": 0.15660738050937653,
|
|
"num_tokens": 23037364.0,
|
|
"step": 11100
|
|
},
|
|
{
|
|
"entropy": 5.6551567077636715,
|
|
"epoch": 1.0073476052249637,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004905659851836161,
|
|
"loss": 5.4238,
|
|
"mean_token_accuracy": 0.16720033884048463,
|
|
"num_tokens": 23047609.0,
|
|
"step": 11105
|
|
},
|
|
{
|
|
"entropy": 5.752944469451904,
|
|
"epoch": 1.007801161103048,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004905567118453475,
|
|
"loss": 5.5539,
|
|
"mean_token_accuracy": 0.15717345476150513,
|
|
"num_tokens": 23057942.0,
|
|
"step": 11110
|
|
},
|
|
{
|
|
"entropy": 5.696563768386841,
|
|
"epoch": 1.008254716981132,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004905474340493111,
|
|
"loss": 5.4736,
|
|
"mean_token_accuracy": 0.15992814153432847,
|
|
"num_tokens": 23069119.0,
|
|
"step": 11115
|
|
},
|
|
{
|
|
"entropy": 5.642239999771118,
|
|
"epoch": 1.0087082728592163,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004905381517956988,
|
|
"loss": 5.4661,
|
|
"mean_token_accuracy": 0.164231638610363,
|
|
"num_tokens": 23080060.0,
|
|
"step": 11120
|
|
},
|
|
{
|
|
"entropy": 5.677470064163208,
|
|
"epoch": 1.0091618287373005,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004905288650847027,
|
|
"loss": 5.467,
|
|
"mean_token_accuracy": 0.16300048679113388,
|
|
"num_tokens": 23090645.0,
|
|
"step": 11125
|
|
},
|
|
{
|
|
"entropy": 5.7578113079071045,
|
|
"epoch": 1.0096153846153846,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004905195739165146,
|
|
"loss": 5.5145,
|
|
"mean_token_accuracy": 0.16242439150810242,
|
|
"num_tokens": 23100449.0,
|
|
"step": 11130
|
|
},
|
|
{
|
|
"entropy": 5.721842336654663,
|
|
"epoch": 1.0100689404934688,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.000490510278291327,
|
|
"loss": 5.4816,
|
|
"mean_token_accuracy": 0.15985626131296157,
|
|
"num_tokens": 23110415.0,
|
|
"step": 11135
|
|
},
|
|
{
|
|
"entropy": 5.662206602096558,
|
|
"epoch": 1.010522496371553,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004905009782093318,
|
|
"loss": 5.4652,
|
|
"mean_token_accuracy": 0.1620655581355095,
|
|
"num_tokens": 23120336.0,
|
|
"step": 11140
|
|
},
|
|
{
|
|
"entropy": 5.617066764831543,
|
|
"epoch": 1.0109760522496372,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004904916736707214,
|
|
"loss": 5.5436,
|
|
"mean_token_accuracy": 0.15817906707525253,
|
|
"num_tokens": 23130568.0,
|
|
"step": 11145
|
|
},
|
|
{
|
|
"entropy": 5.769860363006591,
|
|
"epoch": 1.0114296081277214,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004904823646756885,
|
|
"loss": 5.5134,
|
|
"mean_token_accuracy": 0.16534475982189178,
|
|
"num_tokens": 23140080.0,
|
|
"step": 11150
|
|
},
|
|
{
|
|
"entropy": 5.737817716598511,
|
|
"epoch": 1.0118831640058055,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004904730512244252,
|
|
"loss": 5.4651,
|
|
"mean_token_accuracy": 0.16075796633958817,
|
|
"num_tokens": 23150360.0,
|
|
"step": 11155
|
|
},
|
|
{
|
|
"entropy": 5.648607540130615,
|
|
"epoch": 1.0123367198838897,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004904637333171243,
|
|
"loss": 5.449,
|
|
"mean_token_accuracy": 0.15600711107254028,
|
|
"num_tokens": 23160620.0,
|
|
"step": 11160
|
|
},
|
|
{
|
|
"entropy": 5.797400951385498,
|
|
"epoch": 1.0127902757619738,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004904544109539785,
|
|
"loss": 5.5604,
|
|
"mean_token_accuracy": 0.1614887036383152,
|
|
"num_tokens": 23171920.0,
|
|
"step": 11165
|
|
},
|
|
{
|
|
"entropy": 5.7219016551971436,
|
|
"epoch": 1.013243831640058,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004904450841351805,
|
|
"loss": 5.4973,
|
|
"mean_token_accuracy": 0.1665508985519409,
|
|
"num_tokens": 23182929.0,
|
|
"step": 11170
|
|
},
|
|
{
|
|
"entropy": 5.738533163070679,
|
|
"epoch": 1.0136973875181423,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004904357528609236,
|
|
"loss": 5.4549,
|
|
"mean_token_accuracy": 0.15924956649541855,
|
|
"num_tokens": 23193020.0,
|
|
"step": 11175
|
|
},
|
|
{
|
|
"entropy": 5.646423721313477,
|
|
"epoch": 1.0141509433962264,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004904264171314,
|
|
"loss": 5.4965,
|
|
"mean_token_accuracy": 0.16382967233657836,
|
|
"num_tokens": 23204073.0,
|
|
"step": 11180
|
|
},
|
|
{
|
|
"entropy": 5.652504205703735,
|
|
"epoch": 1.0146044992743106,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004904170769468035,
|
|
"loss": 5.3946,
|
|
"mean_token_accuracy": 0.16075338125228883,
|
|
"num_tokens": 23214376.0,
|
|
"step": 11185
|
|
},
|
|
{
|
|
"entropy": 5.748986434936524,
|
|
"epoch": 1.0150580551523947,
|
|
"grad_norm": 3.96875,
|
|
"learning_rate": 0.0004904077323073268,
|
|
"loss": 5.5478,
|
|
"mean_token_accuracy": 0.16466937959194183,
|
|
"num_tokens": 23224304.0,
|
|
"step": 11190
|
|
},
|
|
{
|
|
"entropy": 5.739000749588013,
|
|
"epoch": 1.015511611030479,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004903983832131633,
|
|
"loss": 5.5588,
|
|
"mean_token_accuracy": 0.15770039707422256,
|
|
"num_tokens": 23235324.0,
|
|
"step": 11195
|
|
},
|
|
{
|
|
"entropy": 5.756187772750854,
|
|
"epoch": 1.0159651669085632,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004903890296645063,
|
|
"loss": 5.5331,
|
|
"mean_token_accuracy": 0.16240763217210769,
|
|
"num_tokens": 23245774.0,
|
|
"step": 11200
|
|
},
|
|
{
|
|
"entropy": 5.690393877029419,
|
|
"epoch": 1.0164187227866472,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004903796716615495,
|
|
"loss": 5.4731,
|
|
"mean_token_accuracy": 0.16231398433446884,
|
|
"num_tokens": 23256274.0,
|
|
"step": 11205
|
|
},
|
|
{
|
|
"entropy": 5.630316686630249,
|
|
"epoch": 1.0168722786647315,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004903703092044861,
|
|
"loss": 5.4945,
|
|
"mean_token_accuracy": 0.1659520074725151,
|
|
"num_tokens": 23266304.0,
|
|
"step": 11210
|
|
},
|
|
{
|
|
"entropy": 5.605863046646118,
|
|
"epoch": 1.0173258345428158,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004903609422935097,
|
|
"loss": 5.3886,
|
|
"mean_token_accuracy": 0.16759308874607087,
|
|
"num_tokens": 23276552.0,
|
|
"step": 11215
|
|
},
|
|
{
|
|
"entropy": 5.693448114395141,
|
|
"epoch": 1.0177793904208998,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004903515709288143,
|
|
"loss": 5.5168,
|
|
"mean_token_accuracy": 0.15542106926441193,
|
|
"num_tokens": 23287799.0,
|
|
"step": 11220
|
|
},
|
|
{
|
|
"entropy": 5.639061498641968,
|
|
"epoch": 1.018232946298984,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004903421951105933,
|
|
"loss": 5.3692,
|
|
"mean_token_accuracy": 0.17155689299106597,
|
|
"num_tokens": 23297958.0,
|
|
"step": 11225
|
|
},
|
|
{
|
|
"entropy": 5.658200454711914,
|
|
"epoch": 1.0186865021770681,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004903328148390411,
|
|
"loss": 5.5534,
|
|
"mean_token_accuracy": 0.15948002487421037,
|
|
"num_tokens": 23307523.0,
|
|
"step": 11230
|
|
},
|
|
{
|
|
"entropy": 5.710340356826782,
|
|
"epoch": 1.0191400580551524,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004903234301143513,
|
|
"loss": 5.5387,
|
|
"mean_token_accuracy": 0.15993663370609285,
|
|
"num_tokens": 23317970.0,
|
|
"step": 11235
|
|
},
|
|
{
|
|
"entropy": 5.718249082565308,
|
|
"epoch": 1.0195936139332367,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004903140409367181,
|
|
"loss": 5.5008,
|
|
"mean_token_accuracy": 0.16363682448863984,
|
|
"num_tokens": 23328612.0,
|
|
"step": 11240
|
|
},
|
|
{
|
|
"entropy": 5.675393724441529,
|
|
"epoch": 1.0200471698113207,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004903046473063357,
|
|
"loss": 5.4547,
|
|
"mean_token_accuracy": 0.16415297389030456,
|
|
"num_tokens": 23338104.0,
|
|
"step": 11245
|
|
},
|
|
{
|
|
"entropy": 5.621548366546631,
|
|
"epoch": 1.020500725689405,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004902952492233983,
|
|
"loss": 5.3833,
|
|
"mean_token_accuracy": 0.17474015355110167,
|
|
"num_tokens": 23348105.0,
|
|
"step": 11250
|
|
},
|
|
{
|
|
"entropy": 5.599571704864502,
|
|
"epoch": 1.020954281567489,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004902858466881002,
|
|
"loss": 5.3594,
|
|
"mean_token_accuracy": 0.16733870059251785,
|
|
"num_tokens": 23357150.0,
|
|
"step": 11255
|
|
},
|
|
{
|
|
"entropy": 5.678447008132935,
|
|
"epoch": 1.0214078374455733,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.000490276439700636,
|
|
"loss": 5.5363,
|
|
"mean_token_accuracy": 0.16148153096437454,
|
|
"num_tokens": 23367223.0,
|
|
"step": 11260
|
|
},
|
|
{
|
|
"entropy": 5.734092712402344,
|
|
"epoch": 1.0218613933236576,
|
|
"grad_norm": 3.09375,
|
|
"learning_rate": 0.0004902670282612002,
|
|
"loss": 5.4893,
|
|
"mean_token_accuracy": 0.16005946919322014,
|
|
"num_tokens": 23377664.0,
|
|
"step": 11265
|
|
},
|
|
{
|
|
"entropy": 5.609952211380005,
|
|
"epoch": 1.0223149492017416,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004902576123699873,
|
|
"loss": 5.3815,
|
|
"mean_token_accuracy": 0.1697452947497368,
|
|
"num_tokens": 23388057.0,
|
|
"step": 11270
|
|
},
|
|
{
|
|
"entropy": 5.574613952636719,
|
|
"epoch": 1.0227685050798259,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004902481920271922,
|
|
"loss": 5.3425,
|
|
"mean_token_accuracy": 0.1659125156700611,
|
|
"num_tokens": 23397808.0,
|
|
"step": 11275
|
|
},
|
|
{
|
|
"entropy": 5.636931276321411,
|
|
"epoch": 1.02322206095791,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004902387672330097,
|
|
"loss": 5.4173,
|
|
"mean_token_accuracy": 0.16670368611812592,
|
|
"num_tokens": 23406979.0,
|
|
"step": 11280
|
|
},
|
|
{
|
|
"entropy": 5.646340990066529,
|
|
"epoch": 1.0236756168359942,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004902293379876345,
|
|
"loss": 5.4416,
|
|
"mean_token_accuracy": 0.16889553517103195,
|
|
"num_tokens": 23416545.0,
|
|
"step": 11285
|
|
},
|
|
{
|
|
"entropy": 5.664075613021851,
|
|
"epoch": 1.0241291727140784,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004902199042912618,
|
|
"loss": 5.5248,
|
|
"mean_token_accuracy": 0.1551606424152851,
|
|
"num_tokens": 23427464.0,
|
|
"step": 11290
|
|
},
|
|
{
|
|
"entropy": 5.738067674636841,
|
|
"epoch": 1.0245827285921625,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004902104661440868,
|
|
"loss": 5.5121,
|
|
"mean_token_accuracy": 0.16560570597648622,
|
|
"num_tokens": 23436690.0,
|
|
"step": 11295
|
|
},
|
|
{
|
|
"entropy": 5.717732667922974,
|
|
"epoch": 1.0250362844702468,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004902010235463042,
|
|
"loss": 5.4569,
|
|
"mean_token_accuracy": 0.1640504091978073,
|
|
"num_tokens": 23446701.0,
|
|
"step": 11300
|
|
},
|
|
{
|
|
"entropy": 5.671495628356934,
|
|
"epoch": 1.025489840348331,
|
|
"grad_norm": 3.4375,
|
|
"learning_rate": 0.0004901915764981098,
|
|
"loss": 5.5402,
|
|
"mean_token_accuracy": 0.15890878587961196,
|
|
"num_tokens": 23456966.0,
|
|
"step": 11305
|
|
},
|
|
{
|
|
"entropy": 5.688267946243286,
|
|
"epoch": 1.025943396226415,
|
|
"grad_norm": 3.328125,
|
|
"learning_rate": 0.0004901821249996988,
|
|
"loss": 5.521,
|
|
"mean_token_accuracy": 0.16089604198932647,
|
|
"num_tokens": 23467300.0,
|
|
"step": 11310
|
|
},
|
|
{
|
|
"entropy": 5.7953697681427006,
|
|
"epoch": 1.0263969521044993,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004901726690512665,
|
|
"loss": 5.533,
|
|
"mean_token_accuracy": 0.15731682926416396,
|
|
"num_tokens": 23478457.0,
|
|
"step": 11315
|
|
},
|
|
{
|
|
"entropy": 5.688040161132813,
|
|
"epoch": 1.0268505079825834,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004901632086530087,
|
|
"loss": 5.4457,
|
|
"mean_token_accuracy": 0.16622142642736434,
|
|
"num_tokens": 23488066.0,
|
|
"step": 11320
|
|
},
|
|
{
|
|
"entropy": 5.674229335784912,
|
|
"epoch": 1.0273040638606676,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004901537438051207,
|
|
"loss": 5.5206,
|
|
"mean_token_accuracy": 0.15642925202846528,
|
|
"num_tokens": 23498856.0,
|
|
"step": 11325
|
|
},
|
|
{
|
|
"entropy": 5.725272989273071,
|
|
"epoch": 1.027757619738752,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004901442745077986,
|
|
"loss": 5.4856,
|
|
"mean_token_accuracy": 0.16164782792329788,
|
|
"num_tokens": 23509845.0,
|
|
"step": 11330
|
|
},
|
|
{
|
|
"entropy": 5.7919717788696286,
|
|
"epoch": 1.028211175616836,
|
|
"grad_norm": 4.1875,
|
|
"learning_rate": 0.0004901348007612381,
|
|
"loss": 5.6079,
|
|
"mean_token_accuracy": 0.15739612206816672,
|
|
"num_tokens": 23520322.0,
|
|
"step": 11335
|
|
},
|
|
{
|
|
"entropy": 5.7488353729248045,
|
|
"epoch": 1.0286647314949202,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004901253225656351,
|
|
"loss": 5.5193,
|
|
"mean_token_accuracy": 0.16183076649904252,
|
|
"num_tokens": 23530030.0,
|
|
"step": 11340
|
|
},
|
|
{
|
|
"entropy": 5.7212597846984865,
|
|
"epoch": 1.0291182873730043,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004901158399211855,
|
|
"loss": 5.5601,
|
|
"mean_token_accuracy": 0.16002503633499146,
|
|
"num_tokens": 23541063.0,
|
|
"step": 11345
|
|
},
|
|
{
|
|
"entropy": 5.651064491271972,
|
|
"epoch": 1.0295718432510885,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004901063528280856,
|
|
"loss": 5.4834,
|
|
"mean_token_accuracy": 0.15865931063890457,
|
|
"num_tokens": 23551693.0,
|
|
"step": 11350
|
|
},
|
|
{
|
|
"entropy": 5.745538377761841,
|
|
"epoch": 1.0300253991291728,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004900968612865314,
|
|
"loss": 5.5072,
|
|
"mean_token_accuracy": 0.17061571925878524,
|
|
"num_tokens": 23561758.0,
|
|
"step": 11355
|
|
},
|
|
{
|
|
"entropy": 5.6544593334197994,
|
|
"epoch": 1.0304789550072568,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004900873652967195,
|
|
"loss": 5.4678,
|
|
"mean_token_accuracy": 0.16072627454996108,
|
|
"num_tokens": 23571912.0,
|
|
"step": 11360
|
|
},
|
|
{
|
|
"entropy": 5.6927159309387205,
|
|
"epoch": 1.030932510885341,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004900778648588459,
|
|
"loss": 5.4423,
|
|
"mean_token_accuracy": 0.1640793040394783,
|
|
"num_tokens": 23582600.0,
|
|
"step": 11365
|
|
},
|
|
{
|
|
"entropy": 5.628821563720703,
|
|
"epoch": 1.0313860667634251,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004900683599731073,
|
|
"loss": 5.3635,
|
|
"mean_token_accuracy": 0.16977159976959227,
|
|
"num_tokens": 23592761.0,
|
|
"step": 11370
|
|
},
|
|
{
|
|
"entropy": 5.727665281295776,
|
|
"epoch": 1.0318396226415094,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004900588506397002,
|
|
"loss": 5.5509,
|
|
"mean_token_accuracy": 0.16307468563318253,
|
|
"num_tokens": 23603119.0,
|
|
"step": 11375
|
|
},
|
|
{
|
|
"entropy": 5.646284484863282,
|
|
"epoch": 1.0322931785195937,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004900493368588213,
|
|
"loss": 5.4615,
|
|
"mean_token_accuracy": 0.16338064521551132,
|
|
"num_tokens": 23613916.0,
|
|
"step": 11380
|
|
},
|
|
{
|
|
"entropy": 5.7100780487060545,
|
|
"epoch": 1.0327467343976777,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.0004900398186306672,
|
|
"loss": 5.5972,
|
|
"mean_token_accuracy": 0.1593170702457428,
|
|
"num_tokens": 23623956.0,
|
|
"step": 11385
|
|
},
|
|
{
|
|
"entropy": 5.724980401992798,
|
|
"epoch": 1.033200290275762,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.000490030295955435,
|
|
"loss": 5.5015,
|
|
"mean_token_accuracy": 0.16104393154382707,
|
|
"num_tokens": 23634666.0,
|
|
"step": 11390
|
|
},
|
|
{
|
|
"entropy": 5.641574096679688,
|
|
"epoch": 1.0336538461538463,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004900207688333215,
|
|
"loss": 5.453,
|
|
"mean_token_accuracy": 0.1598928764462471,
|
|
"num_tokens": 23645601.0,
|
|
"step": 11395
|
|
},
|
|
{
|
|
"entropy": 5.7129758358001705,
|
|
"epoch": 1.0341074020319303,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004900112372645236,
|
|
"loss": 5.5217,
|
|
"mean_token_accuracy": 0.1632014572620392,
|
|
"num_tokens": 23656339.0,
|
|
"step": 11400
|
|
},
|
|
{
|
|
"entropy": 5.741979885101318,
|
|
"epoch": 1.0345609579100146,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004900017012492386,
|
|
"loss": 5.4908,
|
|
"mean_token_accuracy": 0.16513044536113738,
|
|
"num_tokens": 23667433.0,
|
|
"step": 11405
|
|
},
|
|
{
|
|
"entropy": 5.731367588043213,
|
|
"epoch": 1.0350145137880986,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004899921607876634,
|
|
"loss": 5.5214,
|
|
"mean_token_accuracy": 0.16046342849731446,
|
|
"num_tokens": 23678186.0,
|
|
"step": 11410
|
|
},
|
|
{
|
|
"entropy": 5.716891431808472,
|
|
"epoch": 1.0354680696661829,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004899826158799958,
|
|
"loss": 5.4756,
|
|
"mean_token_accuracy": 0.15944126844406128,
|
|
"num_tokens": 23688317.0,
|
|
"step": 11415
|
|
},
|
|
{
|
|
"entropy": 5.667319297790527,
|
|
"epoch": 1.0359216255442671,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004899730665264328,
|
|
"loss": 5.4081,
|
|
"mean_token_accuracy": 0.1637391299009323,
|
|
"num_tokens": 23697752.0,
|
|
"step": 11420
|
|
},
|
|
{
|
|
"entropy": 5.594397449493409,
|
|
"epoch": 1.0363751814223512,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004899635127271721,
|
|
"loss": 5.3942,
|
|
"mean_token_accuracy": 0.1683803990483284,
|
|
"num_tokens": 23707803.0,
|
|
"step": 11425
|
|
},
|
|
{
|
|
"entropy": 5.5841114044189455,
|
|
"epoch": 1.0368287373004355,
|
|
"grad_norm": 3.125,
|
|
"learning_rate": 0.0004899539544824111,
|
|
"loss": 5.4223,
|
|
"mean_token_accuracy": 0.16886471211910248,
|
|
"num_tokens": 23717630.0,
|
|
"step": 11430
|
|
},
|
|
{
|
|
"entropy": 5.689569139480591,
|
|
"epoch": 1.0372822931785195,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004899443917923476,
|
|
"loss": 5.5322,
|
|
"mean_token_accuracy": 0.1593359060585499,
|
|
"num_tokens": 23728836.0,
|
|
"step": 11435
|
|
},
|
|
{
|
|
"entropy": 5.691890668869019,
|
|
"epoch": 1.0377358490566038,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004899348246571792,
|
|
"loss": 5.508,
|
|
"mean_token_accuracy": 0.16283636242151261,
|
|
"num_tokens": 23740145.0,
|
|
"step": 11440
|
|
},
|
|
{
|
|
"entropy": 5.706368684768677,
|
|
"epoch": 1.038189404934688,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.000489925253077104,
|
|
"loss": 5.4694,
|
|
"mean_token_accuracy": 0.16566665917634965,
|
|
"num_tokens": 23751162.0,
|
|
"step": 11445
|
|
},
|
|
{
|
|
"entropy": 5.670011043548584,
|
|
"epoch": 1.038642960812772,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.0004899156770523196,
|
|
"loss": 5.4893,
|
|
"mean_token_accuracy": 0.1650935158133507,
|
|
"num_tokens": 23761634.0,
|
|
"step": 11450
|
|
},
|
|
{
|
|
"entropy": 5.695934915542603,
|
|
"epoch": 1.0390965166908563,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004899060965830244,
|
|
"loss": 5.4661,
|
|
"mean_token_accuracy": 0.16658298373222352,
|
|
"num_tokens": 23772483.0,
|
|
"step": 11455
|
|
},
|
|
{
|
|
"entropy": 5.6645409107208256,
|
|
"epoch": 1.0395500725689404,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004898965116694162,
|
|
"loss": 5.4106,
|
|
"mean_token_accuracy": 0.16603813022375108,
|
|
"num_tokens": 23782298.0,
|
|
"step": 11460
|
|
},
|
|
{
|
|
"entropy": 5.631785678863525,
|
|
"epoch": 1.0400036284470247,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004898869223116935,
|
|
"loss": 5.4915,
|
|
"mean_token_accuracy": 0.15760239362716674,
|
|
"num_tokens": 23792492.0,
|
|
"step": 11465
|
|
},
|
|
{
|
|
"entropy": 5.784116125106811,
|
|
"epoch": 1.040457184325109,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004898773285100546,
|
|
"loss": 5.6367,
|
|
"mean_token_accuracy": 0.15588644444942473,
|
|
"num_tokens": 23802999.0,
|
|
"step": 11470
|
|
},
|
|
{
|
|
"entropy": 5.664670991897583,
|
|
"epoch": 1.040910740203193,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004898677302646975,
|
|
"loss": 5.4491,
|
|
"mean_token_accuracy": 0.16652671247720718,
|
|
"num_tokens": 23812541.0,
|
|
"step": 11475
|
|
},
|
|
{
|
|
"entropy": 5.698764944076538,
|
|
"epoch": 1.0413642960812772,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004898581275758211,
|
|
"loss": 5.5541,
|
|
"mean_token_accuracy": 0.15557721704244615,
|
|
"num_tokens": 23823244.0,
|
|
"step": 11480
|
|
},
|
|
{
|
|
"entropy": 5.684282112121582,
|
|
"epoch": 1.0418178519593615,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004898485204436239,
|
|
"loss": 5.4017,
|
|
"mean_token_accuracy": 0.16914846003055573,
|
|
"num_tokens": 23832346.0,
|
|
"step": 11485
|
|
},
|
|
{
|
|
"entropy": 5.7313415050506595,
|
|
"epoch": 1.0422714078374455,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004898389088683047,
|
|
"loss": 5.5509,
|
|
"mean_token_accuracy": 0.1662890285253525,
|
|
"num_tokens": 23842554.0,
|
|
"step": 11490
|
|
},
|
|
{
|
|
"entropy": 5.670367813110351,
|
|
"epoch": 1.0427249637155298,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004898292928500619,
|
|
"loss": 5.3903,
|
|
"mean_token_accuracy": 0.1707548752427101,
|
|
"num_tokens": 23852938.0,
|
|
"step": 11495
|
|
},
|
|
{
|
|
"entropy": 5.653375148773193,
|
|
"epoch": 1.0431785195936139,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004898196723890947,
|
|
"loss": 5.415,
|
|
"mean_token_accuracy": 0.16743821352720262,
|
|
"num_tokens": 23862367.0,
|
|
"step": 11500
|
|
},
|
|
{
|
|
"entropy": 5.661140298843383,
|
|
"epoch": 1.0436320754716981,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004898100474856019,
|
|
"loss": 5.5272,
|
|
"mean_token_accuracy": 0.16270209848880768,
|
|
"num_tokens": 23873249.0,
|
|
"step": 11505
|
|
},
|
|
{
|
|
"entropy": 5.687123250961304,
|
|
"epoch": 1.0440856313497824,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004898004181397824,
|
|
"loss": 5.5106,
|
|
"mean_token_accuracy": 0.15756412595510483,
|
|
"num_tokens": 23883830.0,
|
|
"step": 11510
|
|
},
|
|
{
|
|
"entropy": 5.730164003372193,
|
|
"epoch": 1.0445391872278664,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004897907843518358,
|
|
"loss": 5.4584,
|
|
"mean_token_accuracy": 0.16315511912107467,
|
|
"num_tokens": 23894359.0,
|
|
"step": 11515
|
|
},
|
|
{
|
|
"entropy": 5.668785762786865,
|
|
"epoch": 1.0449927431059507,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004897811461219609,
|
|
"loss": 5.4449,
|
|
"mean_token_accuracy": 0.16634607017040254,
|
|
"num_tokens": 23903779.0,
|
|
"step": 11520
|
|
},
|
|
{
|
|
"entropy": 5.638818788528442,
|
|
"epoch": 1.0454462989840347,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004897715034503571,
|
|
"loss": 5.5072,
|
|
"mean_token_accuracy": 0.15962491035461426,
|
|
"num_tokens": 23914523.0,
|
|
"step": 11525
|
|
},
|
|
{
|
|
"entropy": 5.656733798980713,
|
|
"epoch": 1.045899854862119,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.000489761856337224,
|
|
"loss": 5.4891,
|
|
"mean_token_accuracy": 0.16741018891334533,
|
|
"num_tokens": 23924996.0,
|
|
"step": 11530
|
|
},
|
|
{
|
|
"entropy": 5.708329582214356,
|
|
"epoch": 1.0463534107402033,
|
|
"grad_norm": 2.984375,
|
|
"learning_rate": 0.0004897522047827609,
|
|
"loss": 5.4536,
|
|
"mean_token_accuracy": 0.16641439944505693,
|
|
"num_tokens": 23935843.0,
|
|
"step": 11535
|
|
},
|
|
{
|
|
"entropy": 5.670756483078003,
|
|
"epoch": 1.0468069666182873,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004897425487871676,
|
|
"loss": 5.4135,
|
|
"mean_token_accuracy": 0.1644849494099617,
|
|
"num_tokens": 23945044.0,
|
|
"step": 11540
|
|
},
|
|
{
|
|
"entropy": 5.6055107593536375,
|
|
"epoch": 1.0472605224963716,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004897328883506436,
|
|
"loss": 5.4679,
|
|
"mean_token_accuracy": 0.16350773721933365,
|
|
"num_tokens": 23955933.0,
|
|
"step": 11545
|
|
},
|
|
{
|
|
"entropy": 5.664115381240845,
|
|
"epoch": 1.0477140783744556,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004897232234733887,
|
|
"loss": 5.5336,
|
|
"mean_token_accuracy": 0.15979939103126525,
|
|
"num_tokens": 23966320.0,
|
|
"step": 11550
|
|
},
|
|
{
|
|
"entropy": 5.6529889583587645,
|
|
"epoch": 1.04816763425254,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004897135541556028,
|
|
"loss": 5.4334,
|
|
"mean_token_accuracy": 0.1675807476043701,
|
|
"num_tokens": 23976233.0,
|
|
"step": 11555
|
|
},
|
|
{
|
|
"entropy": 5.678344440460205,
|
|
"epoch": 1.0486211901306242,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.000489703880397486,
|
|
"loss": 5.5067,
|
|
"mean_token_accuracy": 0.15979358106851577,
|
|
"num_tokens": 23987854.0,
|
|
"step": 11560
|
|
},
|
|
{
|
|
"entropy": 5.668689107894897,
|
|
"epoch": 1.0490747460087082,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004896942021992382,
|
|
"loss": 5.4915,
|
|
"mean_token_accuracy": 0.16086126863956451,
|
|
"num_tokens": 23997973.0,
|
|
"step": 11565
|
|
},
|
|
{
|
|
"entropy": 5.665507125854492,
|
|
"epoch": 1.0495283018867925,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004896845195610595,
|
|
"loss": 5.4855,
|
|
"mean_token_accuracy": 0.16499314606189727,
|
|
"num_tokens": 24007313.0,
|
|
"step": 11570
|
|
},
|
|
{
|
|
"entropy": 5.657023763656616,
|
|
"epoch": 1.0499818577648767,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004896748324831504,
|
|
"loss": 5.5184,
|
|
"mean_token_accuracy": 0.15559491664171218,
|
|
"num_tokens": 24018254.0,
|
|
"step": 11575
|
|
},
|
|
{
|
|
"entropy": 5.724479293823242,
|
|
"epoch": 1.0504354136429608,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004896651409657109,
|
|
"loss": 5.5174,
|
|
"mean_token_accuracy": 0.16293338686227798,
|
|
"num_tokens": 24029799.0,
|
|
"step": 11580
|
|
},
|
|
{
|
|
"entropy": 5.6325288772583,
|
|
"epoch": 1.050888969521045,
|
|
"grad_norm": 3.1875,
|
|
"learning_rate": 0.0004896554450089417,
|
|
"loss": 5.4274,
|
|
"mean_token_accuracy": 0.17104499340057372,
|
|
"num_tokens": 24040972.0,
|
|
"step": 11585
|
|
},
|
|
{
|
|
"entropy": 5.650476551055908,
|
|
"epoch": 1.051342525399129,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.0004896457446130431,
|
|
"loss": 5.3591,
|
|
"mean_token_accuracy": 0.16625747382640838,
|
|
"num_tokens": 24050781.0,
|
|
"step": 11590
|
|
},
|
|
{
|
|
"entropy": 5.657065582275391,
|
|
"epoch": 1.0517960812772134,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.0004896360397782159,
|
|
"loss": 5.4629,
|
|
"mean_token_accuracy": 0.15812716335058213,
|
|
"num_tokens": 24060184.0,
|
|
"step": 11595
|
|
},
|
|
{
|
|
"entropy": 5.751388502120972,
|
|
"epoch": 1.0522496371552976,
|
|
"grad_norm": 3.34375,
|
|
"learning_rate": 0.0004896263305046607,
|
|
"loss": 5.5284,
|
|
"mean_token_accuracy": 0.1678271234035492,
|
|
"num_tokens": 24070777.0,
|
|
"step": 11600
|
|
},
|
|
{
|
|
"entropy": 5.691410112380981,
|
|
"epoch": 1.0527031930333817,
|
|
"grad_norm": 2.890625,
|
|
"learning_rate": 0.0004896166167925782,
|
|
"loss": 5.5594,
|
|
"mean_token_accuracy": 0.16018476486206054,
|
|
"num_tokens": 24080878.0,
|
|
"step": 11605
|
|
},
|
|
{
|
|
"entropy": 5.738567972183228,
|
|
"epoch": 1.053156748911466,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004896068986421693,
|
|
"loss": 5.5387,
|
|
"mean_token_accuracy": 0.16707061529159545,
|
|
"num_tokens": 24090038.0,
|
|
"step": 11610
|
|
},
|
|
{
|
|
"entropy": 5.7405332088470455,
|
|
"epoch": 1.05361030478955,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004895971760536351,
|
|
"loss": 5.5227,
|
|
"mean_token_accuracy": 0.16330166906118393,
|
|
"num_tokens": 24100425.0,
|
|
"step": 11615
|
|
},
|
|
{
|
|
"entropy": 5.717467832565307,
|
|
"epoch": 1.0540638606676342,
|
|
"grad_norm": 3.03125,
|
|
"learning_rate": 0.0004895874490271768,
|
|
"loss": 5.614,
|
|
"mean_token_accuracy": 0.16039578020572662,
|
|
"num_tokens": 24112182.0,
|
|
"step": 11620
|
|
},
|
|
{
|
|
"entropy": 5.751130056381226,
|
|
"epoch": 1.0545174165457185,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004895777175629952,
|
|
"loss": 5.4723,
|
|
"mean_token_accuracy": 0.16274027526378632,
|
|
"num_tokens": 24122182.0,
|
|
"step": 11625
|
|
},
|
|
{
|
|
"entropy": 5.729969835281372,
|
|
"epoch": 1.0549709724238026,
|
|
"grad_norm": 2.921875,
|
|
"learning_rate": 0.0004895679816612917,
|
|
"loss": 5.4683,
|
|
"mean_token_accuracy": 0.16087260991334915,
|
|
"num_tokens": 24131930.0,
|
|
"step": 11630
|
|
},
|
|
{
|
|
"entropy": 5.763346099853516,
|
|
"epoch": 1.0554245283018868,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004895582413222678,
|
|
"loss": 5.4631,
|
|
"mean_token_accuracy": 0.16693939864635468,
|
|
"num_tokens": 24141575.0,
|
|
"step": 11635
|
|
},
|
|
{
|
|
"entropy": 5.735921049118042,
|
|
"epoch": 1.0558780841799709,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004895484965461247,
|
|
"loss": 5.5954,
|
|
"mean_token_accuracy": 0.1555388368666172,
|
|
"num_tokens": 24151720.0,
|
|
"step": 11640
|
|
},
|
|
{
|
|
"entropy": 5.648131036758423,
|
|
"epoch": 1.0563316400580551,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.000489538747333064,
|
|
"loss": 5.5117,
|
|
"mean_token_accuracy": 0.16520230025053023,
|
|
"num_tokens": 24161881.0,
|
|
"step": 11645
|
|
},
|
|
{
|
|
"entropy": 5.662093210220337,
|
|
"epoch": 1.0567851959361394,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004895289936832874,
|
|
"loss": 5.4369,
|
|
"mean_token_accuracy": 0.16942374557256698,
|
|
"num_tokens": 24171474.0,
|
|
"step": 11650
|
|
},
|
|
{
|
|
"entropy": 5.748489904403686,
|
|
"epoch": 1.0572387518142234,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004895192355969966,
|
|
"loss": 5.5614,
|
|
"mean_token_accuracy": 0.15769891440868378,
|
|
"num_tokens": 24182186.0,
|
|
"step": 11655
|
|
},
|
|
{
|
|
"entropy": 5.703788089752197,
|
|
"epoch": 1.0576923076923077,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004895094730743932,
|
|
"loss": 5.4812,
|
|
"mean_token_accuracy": 0.16618662774562837,
|
|
"num_tokens": 24192318.0,
|
|
"step": 11660
|
|
},
|
|
{
|
|
"entropy": 5.762940311431885,
|
|
"epoch": 1.058145863570392,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004894997061156793,
|
|
"loss": 5.5472,
|
|
"mean_token_accuracy": 0.16404073536396027,
|
|
"num_tokens": 24202918.0,
|
|
"step": 11665
|
|
},
|
|
{
|
|
"entropy": 5.747736024856567,
|
|
"epoch": 1.058599419448476,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004894899347210567,
|
|
"loss": 5.4335,
|
|
"mean_token_accuracy": 0.1657499462366104,
|
|
"num_tokens": 24213218.0,
|
|
"step": 11670
|
|
},
|
|
{
|
|
"entropy": 5.698459959030151,
|
|
"epoch": 1.0590529753265603,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004894801588907278,
|
|
"loss": 5.4434,
|
|
"mean_token_accuracy": 0.16459385752677919,
|
|
"num_tokens": 24223229.0,
|
|
"step": 11675
|
|
},
|
|
{
|
|
"entropy": 5.691482496261597,
|
|
"epoch": 1.0595065312046443,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004894703786248944,
|
|
"loss": 5.4891,
|
|
"mean_token_accuracy": 0.1545097529888153,
|
|
"num_tokens": 24233637.0,
|
|
"step": 11680
|
|
},
|
|
{
|
|
"entropy": 5.707527017593383,
|
|
"epoch": 1.0599600870827286,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.000489460593923759,
|
|
"loss": 5.5302,
|
|
"mean_token_accuracy": 0.16494784951210023,
|
|
"num_tokens": 24244251.0,
|
|
"step": 11685
|
|
},
|
|
{
|
|
"entropy": 5.678729057312012,
|
|
"epoch": 1.0604136429608129,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004894508047875237,
|
|
"loss": 5.4393,
|
|
"mean_token_accuracy": 0.16561634540557862,
|
|
"num_tokens": 24254380.0,
|
|
"step": 11690
|
|
},
|
|
{
|
|
"entropy": 5.555606508255005,
|
|
"epoch": 1.060867198838897,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004894410112163913,
|
|
"loss": 5.3777,
|
|
"mean_token_accuracy": 0.1666809767484665,
|
|
"num_tokens": 24264841.0,
|
|
"step": 11695
|
|
},
|
|
{
|
|
"entropy": 5.6319968700408936,
|
|
"epoch": 1.0613207547169812,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004894312132105641,
|
|
"loss": 5.4333,
|
|
"mean_token_accuracy": 0.1644104465842247,
|
|
"num_tokens": 24274383.0,
|
|
"step": 11700
|
|
},
|
|
{
|
|
"entropy": 5.77095308303833,
|
|
"epoch": 1.0617743105950652,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004894214107702447,
|
|
"loss": 5.4955,
|
|
"mean_token_accuracy": 0.15817901492118835,
|
|
"num_tokens": 24284140.0,
|
|
"step": 11705
|
|
},
|
|
{
|
|
"entropy": 5.77086820602417,
|
|
"epoch": 1.0622278664731495,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.000489411603895636,
|
|
"loss": 5.5858,
|
|
"mean_token_accuracy": 0.1616477981209755,
|
|
"num_tokens": 24295044.0,
|
|
"step": 11710
|
|
},
|
|
{
|
|
"entropy": 5.714500379562378,
|
|
"epoch": 1.0626814223512338,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004894017925869406,
|
|
"loss": 5.4777,
|
|
"mean_token_accuracy": 0.16508449912071227,
|
|
"num_tokens": 24305080.0,
|
|
"step": 11715
|
|
},
|
|
{
|
|
"entropy": 5.670073461532593,
|
|
"epoch": 1.0631349782293178,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004893919768443615,
|
|
"loss": 5.5075,
|
|
"mean_token_accuracy": 0.16324373930692673,
|
|
"num_tokens": 24316306.0,
|
|
"step": 11720
|
|
},
|
|
{
|
|
"entropy": 5.628389167785644,
|
|
"epoch": 1.063588534107402,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004893821566681017,
|
|
"loss": 5.4964,
|
|
"mean_token_accuracy": 0.16520899683237075,
|
|
"num_tokens": 24326740.0,
|
|
"step": 11725
|
|
},
|
|
{
|
|
"entropy": 5.758682012557983,
|
|
"epoch": 1.0640420899854863,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004893723320583644,
|
|
"loss": 5.5239,
|
|
"mean_token_accuracy": 0.1560986489057541,
|
|
"num_tokens": 24337621.0,
|
|
"step": 11730
|
|
},
|
|
{
|
|
"entropy": 5.6249427318573,
|
|
"epoch": 1.0644956458635704,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.0004893625030153525,
|
|
"loss": 5.3794,
|
|
"mean_token_accuracy": 0.17017927914857864,
|
|
"num_tokens": 24347732.0,
|
|
"step": 11735
|
|
},
|
|
{
|
|
"entropy": 5.618579435348511,
|
|
"epoch": 1.0649492017416546,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004893526695392694,
|
|
"loss": 5.4249,
|
|
"mean_token_accuracy": 0.1729237586259842,
|
|
"num_tokens": 24359173.0,
|
|
"step": 11740
|
|
},
|
|
{
|
|
"entropy": 5.675628185272217,
|
|
"epoch": 1.0654027576197387,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004893428316303185,
|
|
"loss": 5.4098,
|
|
"mean_token_accuracy": 0.16480653285980223,
|
|
"num_tokens": 24369465.0,
|
|
"step": 11745
|
|
},
|
|
{
|
|
"entropy": 5.630265855789185,
|
|
"epoch": 1.065856313497823,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004893329892887031,
|
|
"loss": 5.4469,
|
|
"mean_token_accuracy": 0.1663668632507324,
|
|
"num_tokens": 24378899.0,
|
|
"step": 11750
|
|
},
|
|
{
|
|
"entropy": 5.67476077079773,
|
|
"epoch": 1.0663098693759072,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004893231425146271,
|
|
"loss": 5.5629,
|
|
"mean_token_accuracy": 0.1607450008392334,
|
|
"num_tokens": 24388919.0,
|
|
"step": 11755
|
|
},
|
|
{
|
|
"entropy": 5.701404047012329,
|
|
"epoch": 1.0667634252539913,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004893132913082937,
|
|
"loss": 5.4384,
|
|
"mean_token_accuracy": 0.16536288857460021,
|
|
"num_tokens": 24399632.0,
|
|
"step": 11760
|
|
},
|
|
{
|
|
"entropy": 5.74302043914795,
|
|
"epoch": 1.0672169811320755,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004893034356699069,
|
|
"loss": 5.4753,
|
|
"mean_token_accuracy": 0.17018363177776336,
|
|
"num_tokens": 24410817.0,
|
|
"step": 11765
|
|
},
|
|
{
|
|
"entropy": 5.684437227249146,
|
|
"epoch": 1.0676705370101596,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004892935755996705,
|
|
"loss": 5.4785,
|
|
"mean_token_accuracy": 0.16521605104207993,
|
|
"num_tokens": 24421058.0,
|
|
"step": 11770
|
|
},
|
|
{
|
|
"entropy": 5.635939073562622,
|
|
"epoch": 1.0681240928882438,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004892837110977883,
|
|
"loss": 5.3836,
|
|
"mean_token_accuracy": 0.16255545616149902,
|
|
"num_tokens": 24431522.0,
|
|
"step": 11775
|
|
},
|
|
{
|
|
"entropy": 5.6678132057189945,
|
|
"epoch": 1.068577648766328,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004892738421644644,
|
|
"loss": 5.4367,
|
|
"mean_token_accuracy": 0.16589227616786956,
|
|
"num_tokens": 24441746.0,
|
|
"step": 11780
|
|
},
|
|
{
|
|
"entropy": 5.642408323287964,
|
|
"epoch": 1.0690312046444121,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004892639687999027,
|
|
"loss": 5.3366,
|
|
"mean_token_accuracy": 0.17012789845466614,
|
|
"num_tokens": 24451916.0,
|
|
"step": 11785
|
|
},
|
|
{
|
|
"entropy": 5.600446510314941,
|
|
"epoch": 1.0694847605224964,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004892540910043076,
|
|
"loss": 5.4636,
|
|
"mean_token_accuracy": 0.1702978640794754,
|
|
"num_tokens": 24461935.0,
|
|
"step": 11790
|
|
},
|
|
{
|
|
"entropy": 5.652465438842773,
|
|
"epoch": 1.0699383164005805,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004892442087778833,
|
|
"loss": 5.3873,
|
|
"mean_token_accuracy": 0.16691230684518815,
|
|
"num_tokens": 24472437.0,
|
|
"step": 11795
|
|
},
|
|
{
|
|
"entropy": 5.676327228546143,
|
|
"epoch": 1.0703918722786647,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004892343221208342,
|
|
"loss": 5.4556,
|
|
"mean_token_accuracy": 0.1689540833234787,
|
|
"num_tokens": 24481726.0,
|
|
"step": 11800
|
|
},
|
|
{
|
|
"entropy": 5.703737497329712,
|
|
"epoch": 1.070845428156749,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.0004892244310333646,
|
|
"loss": 5.5716,
|
|
"mean_token_accuracy": 0.16031845808029174,
|
|
"num_tokens": 24492340.0,
|
|
"step": 11805
|
|
},
|
|
{
|
|
"entropy": 5.65077576637268,
|
|
"epoch": 1.071298984034833,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004892145355156793,
|
|
"loss": 5.4329,
|
|
"mean_token_accuracy": 0.16874348223209382,
|
|
"num_tokens": 24502138.0,
|
|
"step": 11810
|
|
},
|
|
{
|
|
"entropy": 5.6699635028839115,
|
|
"epoch": 1.0717525399129173,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004892046355679829,
|
|
"loss": 5.4882,
|
|
"mean_token_accuracy": 0.16253758668899537,
|
|
"num_tokens": 24512723.0,
|
|
"step": 11815
|
|
},
|
|
{
|
|
"entropy": 5.76206111907959,
|
|
"epoch": 1.0722060957910013,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004891947311904799,
|
|
"loss": 5.5273,
|
|
"mean_token_accuracy": 0.1545532837510109,
|
|
"num_tokens": 24523766.0,
|
|
"step": 11820
|
|
},
|
|
{
|
|
"entropy": 5.722152757644653,
|
|
"epoch": 1.0726596516690856,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004891848223833753,
|
|
"loss": 5.4867,
|
|
"mean_token_accuracy": 0.16395717561244966,
|
|
"num_tokens": 24534571.0,
|
|
"step": 11825
|
|
},
|
|
{
|
|
"entropy": 5.676762294769287,
|
|
"epoch": 1.0731132075471699,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.000489174909146874,
|
|
"loss": 5.4836,
|
|
"mean_token_accuracy": 0.1708870127797127,
|
|
"num_tokens": 24545265.0,
|
|
"step": 11830
|
|
},
|
|
{
|
|
"entropy": 5.716233587265014,
|
|
"epoch": 1.073566763425254,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004891649914811811,
|
|
"loss": 5.5463,
|
|
"mean_token_accuracy": 0.16311245858669282,
|
|
"num_tokens": 24555524.0,
|
|
"step": 11835
|
|
},
|
|
{
|
|
"entropy": 5.654330205917359,
|
|
"epoch": 1.0740203193033382,
|
|
"grad_norm": 3.40625,
|
|
"learning_rate": 0.0004891550693865014,
|
|
"loss": 5.4091,
|
|
"mean_token_accuracy": 0.17148073762655258,
|
|
"num_tokens": 24565420.0,
|
|
"step": 11840
|
|
},
|
|
{
|
|
"entropy": 5.720872783660889,
|
|
"epoch": 1.0744738751814222,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004891451428630405,
|
|
"loss": 5.4748,
|
|
"mean_token_accuracy": 0.16167662292718887,
|
|
"num_tokens": 24576794.0,
|
|
"step": 11845
|
|
},
|
|
{
|
|
"entropy": 5.667735147476196,
|
|
"epoch": 1.0749274310595065,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004891352119110033,
|
|
"loss": 5.4645,
|
|
"mean_token_accuracy": 0.1657649412751198,
|
|
"num_tokens": 24586320.0,
|
|
"step": 11850
|
|
},
|
|
{
|
|
"entropy": 5.613676357269287,
|
|
"epoch": 1.0753809869375908,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004891252765305954,
|
|
"loss": 5.4661,
|
|
"mean_token_accuracy": 0.16950256377458572,
|
|
"num_tokens": 24596524.0,
|
|
"step": 11855
|
|
},
|
|
{
|
|
"entropy": 5.6887397289276125,
|
|
"epoch": 1.0758345428156748,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004891153367220222,
|
|
"loss": 5.3971,
|
|
"mean_token_accuracy": 0.17449808716773987,
|
|
"num_tokens": 24605877.0,
|
|
"step": 11860
|
|
},
|
|
{
|
|
"entropy": 5.75593147277832,
|
|
"epoch": 1.076288098693759,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.0004891053924854894,
|
|
"loss": 5.6121,
|
|
"mean_token_accuracy": 0.15270848274230958,
|
|
"num_tokens": 24616719.0,
|
|
"step": 11865
|
|
},
|
|
{
|
|
"entropy": 5.6395628452301025,
|
|
"epoch": 1.0767416545718433,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004890954438212024,
|
|
"loss": 5.3641,
|
|
"mean_token_accuracy": 0.17522723376750945,
|
|
"num_tokens": 24626882.0,
|
|
"step": 11870
|
|
},
|
|
{
|
|
"entropy": 5.685314607620239,
|
|
"epoch": 1.0771952104499274,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004890854907293671,
|
|
"loss": 5.4656,
|
|
"mean_token_accuracy": 0.16192277669906616,
|
|
"num_tokens": 24637884.0,
|
|
"step": 11875
|
|
},
|
|
{
|
|
"entropy": 5.606918239593506,
|
|
"epoch": 1.0776487663280117,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.0004890755332101893,
|
|
"loss": 5.4259,
|
|
"mean_token_accuracy": 0.16859775483608247,
|
|
"num_tokens": 24647389.0,
|
|
"step": 11880
|
|
},
|
|
{
|
|
"entropy": 5.65148286819458,
|
|
"epoch": 1.0781023222060957,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004890655712638749,
|
|
"loss": 5.4943,
|
|
"mean_token_accuracy": 0.15603562593460082,
|
|
"num_tokens": 24657595.0,
|
|
"step": 11885
|
|
},
|
|
{
|
|
"entropy": 5.646364498138428,
|
|
"epoch": 1.07855587808418,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.00048905560489063,
|
|
"loss": 5.3962,
|
|
"mean_token_accuracy": 0.1689474180340767,
|
|
"num_tokens": 24667683.0,
|
|
"step": 11890
|
|
},
|
|
{
|
|
"entropy": 5.754399967193604,
|
|
"epoch": 1.0790094339622642,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.0004890456340906605,
|
|
"loss": 5.5284,
|
|
"mean_token_accuracy": 0.1611856073141098,
|
|
"num_tokens": 24678041.0,
|
|
"step": 11895
|
|
},
|
|
{
|
|
"entropy": 5.69939603805542,
|
|
"epoch": 1.0794629898403483,
|
|
"grad_norm": 3.703125,
|
|
"learning_rate": 0.0004890356588641729,
|
|
"loss": 5.527,
|
|
"mean_token_accuracy": 0.16652222573757172,
|
|
"num_tokens": 24688569.0,
|
|
"step": 11900
|
|
},
|
|
{
|
|
"entropy": 5.696583557128906,
|
|
"epoch": 1.0799165457184325,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004890256792113733,
|
|
"loss": 5.5013,
|
|
"mean_token_accuracy": 0.16928274929523468,
|
|
"num_tokens": 24699913.0,
|
|
"step": 11905
|
|
},
|
|
{
|
|
"entropy": 5.756126785278321,
|
|
"epoch": 1.0803701015965168,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004890156951324681,
|
|
"loss": 5.5162,
|
|
"mean_token_accuracy": 0.16144007071852684,
|
|
"num_tokens": 24710682.0,
|
|
"step": 11910
|
|
},
|
|
{
|
|
"entropy": 5.77729983329773,
|
|
"epoch": 1.0808236574746009,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.0004890057066276636,
|
|
"loss": 5.5868,
|
|
"mean_token_accuracy": 0.15677228569984436,
|
|
"num_tokens": 24721087.0,
|
|
"step": 11915
|
|
},
|
|
{
|
|
"entropy": 5.619917345046997,
|
|
"epoch": 1.0812772133526851,
|
|
"grad_norm": 3.265625,
|
|
"learning_rate": 0.0004889957136971668,
|
|
"loss": 5.4291,
|
|
"mean_token_accuracy": 0.17020707130432128,
|
|
"num_tokens": 24731323.0,
|
|
"step": 11920
|
|
},
|
|
{
|
|
"entropy": 5.632232761383056,
|
|
"epoch": 1.0817307692307692,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.000488985716341184,
|
|
"loss": 5.477,
|
|
"mean_token_accuracy": 0.1615115150809288,
|
|
"num_tokens": 24742559.0,
|
|
"step": 11925
|
|
},
|
|
{
|
|
"entropy": 5.741951131820679,
|
|
"epoch": 1.0821843251088534,
|
|
"grad_norm": 3.453125,
|
|
"learning_rate": 0.0004889757145599222,
|
|
"loss": 5.457,
|
|
"mean_token_accuracy": 0.1640556514263153,
|
|
"num_tokens": 24752307.0,
|
|
"step": 11930
|
|
},
|
|
{
|
|
"entropy": 5.596507740020752,
|
|
"epoch": 1.0826378809869377,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.000488965708353588,
|
|
"loss": 5.4033,
|
|
"mean_token_accuracy": 0.1625491425395012,
|
|
"num_tokens": 24762792.0,
|
|
"step": 11935
|
|
},
|
|
{
|
|
"entropy": 5.6874185562133786,
|
|
"epoch": 1.0830914368650217,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004889556977223883,
|
|
"loss": 5.5312,
|
|
"mean_token_accuracy": 0.1622696116566658,
|
|
"num_tokens": 24774377.0,
|
|
"step": 11940
|
|
},
|
|
{
|
|
"entropy": 5.685650110244751,
|
|
"epoch": 1.083544992743106,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004889456826665304,
|
|
"loss": 5.459,
|
|
"mean_token_accuracy": 0.16030688136816024,
|
|
"num_tokens": 24785919.0,
|
|
"step": 11945
|
|
},
|
|
{
|
|
"entropy": 5.725156927108765,
|
|
"epoch": 1.08399854862119,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004889356631862211,
|
|
"loss": 5.4989,
|
|
"mean_token_accuracy": 0.16235191971063614,
|
|
"num_tokens": 24796594.0,
|
|
"step": 11950
|
|
},
|
|
{
|
|
"entropy": 5.669553279876709,
|
|
"epoch": 1.0844521044992743,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.000488925639281668,
|
|
"loss": 5.4865,
|
|
"mean_token_accuracy": 0.16784421354532242,
|
|
"num_tokens": 24807322.0,
|
|
"step": 11955
|
|
},
|
|
{
|
|
"entropy": 5.650086355209351,
|
|
"epoch": 1.0849056603773586,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004889156109530781,
|
|
"loss": 5.3857,
|
|
"mean_token_accuracy": 0.17202035188674927,
|
|
"num_tokens": 24817593.0,
|
|
"step": 11960
|
|
},
|
|
{
|
|
"entropy": 5.653538036346435,
|
|
"epoch": 1.0853592162554426,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.0004889055782006588,
|
|
"loss": 5.4103,
|
|
"mean_token_accuracy": 0.16473422348499298,
|
|
"num_tokens": 24827577.0,
|
|
"step": 11965
|
|
},
|
|
{
|
|
"entropy": 5.645232152938843,
|
|
"epoch": 1.085812772133527,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004888955410246176,
|
|
"loss": 5.4467,
|
|
"mean_token_accuracy": 0.1693625271320343,
|
|
"num_tokens": 24838148.0,
|
|
"step": 11970
|
|
},
|
|
{
|
|
"entropy": 5.637764406204224,
|
|
"epoch": 1.086266328011611,
|
|
"grad_norm": 3.1875,
|
|
"learning_rate": 0.0004888854994251621,
|
|
"loss": 5.4001,
|
|
"mean_token_accuracy": 0.17168040871620177,
|
|
"num_tokens": 24848451.0,
|
|
"step": 11975
|
|
},
|
|
{
|
|
"entropy": 5.6610595703125,
|
|
"epoch": 1.0867198838896952,
|
|
"grad_norm": 3.0,
|
|
"learning_rate": 0.0004888754534025,
|
|
"loss": 5.512,
|
|
"mean_token_accuracy": 0.15536458790302277,
|
|
"num_tokens": 24859619.0,
|
|
"step": 11980
|
|
},
|
|
{
|
|
"entropy": 5.712717580795288,
|
|
"epoch": 1.0871734397677795,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004888654029568391,
|
|
"loss": 5.5426,
|
|
"mean_token_accuracy": 0.15636597573757172,
|
|
"num_tokens": 24869863.0,
|
|
"step": 11985
|
|
},
|
|
{
|
|
"entropy": 5.702992534637451,
|
|
"epoch": 1.0876269956458635,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004888553480883871,
|
|
"loss": 5.4738,
|
|
"mean_token_accuracy": 0.16064688116312026,
|
|
"num_tokens": 24880524.0,
|
|
"step": 11990
|
|
},
|
|
{
|
|
"entropy": 5.625993013381958,
|
|
"epoch": 1.0880805515239478,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.000488845288797352,
|
|
"loss": 5.4488,
|
|
"mean_token_accuracy": 0.16684104204177858,
|
|
"num_tokens": 24891514.0,
|
|
"step": 11995
|
|
},
|
|
{
|
|
"entropy": 5.666551733016968,
|
|
"epoch": 1.0885341074020318,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004888352250839418,
|
|
"loss": 5.4291,
|
|
"mean_token_accuracy": 0.16988996863365174,
|
|
"num_tokens": 24900842.0,
|
|
"step": 12000
|
|
},
|
|
{
|
|
"epoch": 1.0885341074020318,
|
|
"eval_entropy": 5.4917067224623395,
|
|
"eval_loss": 5.547037601470947,
|
|
"eval_mean_token_accuracy": 0.1696599738352102,
|
|
"eval_num_tokens": 24900842.0,
|
|
"eval_runtime": 26.5653,
|
|
"eval_samples_per_second": 1331.059,
|
|
"eval_steps_per_second": 166.382,
|
|
"step": 12000
|
|
},
|
|
{
|
|
"entropy": 5.670194816589356,
|
|
"epoch": 1.088987663280116,
|
|
"grad_norm": 2.984375,
|
|
"learning_rate": 0.0004888251569483647,
|
|
"loss": 5.3917,
|
|
"mean_token_accuracy": 0.16915951818227767,
|
|
"num_tokens": 24911845.0,
|
|
"step": 12005
|
|
},
|
|
{
|
|
"entropy": 5.6056849479675295,
|
|
"epoch": 1.0894412191582004,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004888150843908288,
|
|
"loss": 5.4339,
|
|
"mean_token_accuracy": 0.1710403323173523,
|
|
"num_tokens": 24922211.0,
|
|
"step": 12010
|
|
},
|
|
{
|
|
"entropy": 5.695519495010376,
|
|
"epoch": 1.0898947750362844,
|
|
"grad_norm": 6.4375,
|
|
"learning_rate": 0.0004888050074115426,
|
|
"loss": 5.518,
|
|
"mean_token_accuracy": 0.164350263774395,
|
|
"num_tokens": 24932129.0,
|
|
"step": 12015
|
|
},
|
|
{
|
|
"entropy": 5.7670728206634525,
|
|
"epoch": 1.0903483309143687,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004887949260107143,
|
|
"loss": 5.5225,
|
|
"mean_token_accuracy": 0.165336212515831,
|
|
"num_tokens": 24942869.0,
|
|
"step": 12020
|
|
},
|
|
{
|
|
"entropy": 5.679707002639771,
|
|
"epoch": 1.0908018867924527,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004887848401885524,
|
|
"loss": 5.4765,
|
|
"mean_token_accuracy": 0.16629921942949294,
|
|
"num_tokens": 24952621.0,
|
|
"step": 12025
|
|
},
|
|
{
|
|
"entropy": 5.78301157951355,
|
|
"epoch": 1.091255442670537,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004887747499452656,
|
|
"loss": 5.5758,
|
|
"mean_token_accuracy": 0.15608390420675278,
|
|
"num_tokens": 24963587.0,
|
|
"step": 12030
|
|
},
|
|
{
|
|
"entropy": 5.706737279891968,
|
|
"epoch": 1.0917089985486212,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004887646552810624,
|
|
"loss": 5.431,
|
|
"mean_token_accuracy": 0.16578478068113328,
|
|
"num_tokens": 24974122.0,
|
|
"step": 12035
|
|
},
|
|
{
|
|
"entropy": 5.664782428741455,
|
|
"epoch": 1.0921625544267053,
|
|
"grad_norm": 2.921875,
|
|
"learning_rate": 0.0004887545561961517,
|
|
"loss": 5.5073,
|
|
"mean_token_accuracy": 0.16499629467725754,
|
|
"num_tokens": 24985145.0,
|
|
"step": 12040
|
|
},
|
|
{
|
|
"entropy": 5.619267225265503,
|
|
"epoch": 1.0926161103047896,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004887444526907424,
|
|
"loss": 5.4411,
|
|
"mean_token_accuracy": 0.16479480862617493,
|
|
"num_tokens": 24995511.0,
|
|
"step": 12045
|
|
},
|
|
{
|
|
"entropy": 5.738991785049438,
|
|
"epoch": 1.0930696661828738,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004887343447650432,
|
|
"loss": 5.4683,
|
|
"mean_token_accuracy": 0.15823200345039368,
|
|
"num_tokens": 25006193.0,
|
|
"step": 12050
|
|
},
|
|
{
|
|
"entropy": 5.754913568496704,
|
|
"epoch": 1.0935232220609579,
|
|
"grad_norm": 6.28125,
|
|
"learning_rate": 0.0004887242324192634,
|
|
"loss": 5.5013,
|
|
"mean_token_accuracy": 0.164893439412117,
|
|
"num_tokens": 25016444.0,
|
|
"step": 12055
|
|
},
|
|
{
|
|
"entropy": 5.7211450099945065,
|
|
"epoch": 1.0939767779390421,
|
|
"grad_norm": 3.421875,
|
|
"learning_rate": 0.0004887141156536119,
|
|
"loss": 5.5151,
|
|
"mean_token_accuracy": 0.1593260571360588,
|
|
"num_tokens": 25027898.0,
|
|
"step": 12060
|
|
},
|
|
{
|
|
"entropy": 5.651731491088867,
|
|
"epoch": 1.0944303338171262,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004887039944682981,
|
|
"loss": 5.3837,
|
|
"mean_token_accuracy": 0.1656123623251915,
|
|
"num_tokens": 25038201.0,
|
|
"step": 12065
|
|
},
|
|
{
|
|
"entropy": 5.789763069152832,
|
|
"epoch": 1.0948838896952104,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004886938688635313,
|
|
"loss": 5.6098,
|
|
"mean_token_accuracy": 0.15215777307748796,
|
|
"num_tokens": 25048466.0,
|
|
"step": 12070
|
|
},
|
|
{
|
|
"entropy": 5.781514883041382,
|
|
"epoch": 1.0953374455732947,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004886837388395207,
|
|
"loss": 5.5238,
|
|
"mean_token_accuracy": 0.16359960585832595,
|
|
"num_tokens": 25059064.0,
|
|
"step": 12075
|
|
},
|
|
{
|
|
"entropy": 5.702906131744385,
|
|
"epoch": 1.0957910014513788,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.000488673604396476,
|
|
"loss": 5.5813,
|
|
"mean_token_accuracy": 0.15476004183292388,
|
|
"num_tokens": 25068834.0,
|
|
"step": 12080
|
|
},
|
|
{
|
|
"entropy": 5.729817342758179,
|
|
"epoch": 1.096244557329463,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004886634655346067,
|
|
"loss": 5.5567,
|
|
"mean_token_accuracy": 0.15498937666416168,
|
|
"num_tokens": 25080058.0,
|
|
"step": 12085
|
|
},
|
|
{
|
|
"entropy": 5.68301911354065,
|
|
"epoch": 1.0966981132075473,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004886533222541225,
|
|
"loss": 5.431,
|
|
"mean_token_accuracy": 0.1705911174416542,
|
|
"num_tokens": 25089751.0,
|
|
"step": 12090
|
|
},
|
|
{
|
|
"entropy": 5.676012802124023,
|
|
"epoch": 1.0971516690856313,
|
|
"grad_norm": 3.21875,
|
|
"learning_rate": 0.0004886431745552331,
|
|
"loss": 5.4654,
|
|
"mean_token_accuracy": 0.16738311648368837,
|
|
"num_tokens": 25099055.0,
|
|
"step": 12095
|
|
},
|
|
{
|
|
"entropy": 5.7157176494598385,
|
|
"epoch": 1.0976052249637156,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004886330224381485,
|
|
"loss": 5.5677,
|
|
"mean_token_accuracy": 0.15419784635305406,
|
|
"num_tokens": 25109793.0,
|
|
"step": 12100
|
|
},
|
|
{
|
|
"entropy": 5.689939498901367,
|
|
"epoch": 1.0980587808417996,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004886228659030785,
|
|
"loss": 5.5062,
|
|
"mean_token_accuracy": 0.16634927392005922,
|
|
"num_tokens": 25119814.0,
|
|
"step": 12105
|
|
},
|
|
{
|
|
"entropy": 5.73965048789978,
|
|
"epoch": 1.098512336719884,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004886127049502331,
|
|
"loss": 5.5382,
|
|
"mean_token_accuracy": 0.16082532703876495,
|
|
"num_tokens": 25130747.0,
|
|
"step": 12110
|
|
},
|
|
{
|
|
"entropy": 5.741819572448731,
|
|
"epoch": 1.0989658925979682,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004886025395798228,
|
|
"loss": 5.4496,
|
|
"mean_token_accuracy": 0.16673803478479385,
|
|
"num_tokens": 25142235.0,
|
|
"step": 12115
|
|
},
|
|
{
|
|
"entropy": 5.58083553314209,
|
|
"epoch": 1.0994194484760522,
|
|
"grad_norm": 2.875,
|
|
"learning_rate": 0.0004885923697920573,
|
|
"loss": 5.3755,
|
|
"mean_token_accuracy": 0.17349785566329956,
|
|
"num_tokens": 25152047.0,
|
|
"step": 12120
|
|
},
|
|
{
|
|
"entropy": 5.5714937210083,
|
|
"epoch": 1.0998730043541365,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004885821955871472,
|
|
"loss": 5.4461,
|
|
"mean_token_accuracy": 0.17241339534521102,
|
|
"num_tokens": 25162678.0,
|
|
"step": 12125
|
|
},
|
|
{
|
|
"entropy": 5.707140588760376,
|
|
"epoch": 1.1003265602322205,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.0004885720169653028,
|
|
"loss": 5.4377,
|
|
"mean_token_accuracy": 0.1642293870449066,
|
|
"num_tokens": 25172973.0,
|
|
"step": 12130
|
|
},
|
|
{
|
|
"entropy": 5.712309169769287,
|
|
"epoch": 1.1007801161103048,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004885618339267348,
|
|
"loss": 5.5357,
|
|
"mean_token_accuracy": 0.16533599197864532,
|
|
"num_tokens": 25183458.0,
|
|
"step": 12135
|
|
},
|
|
{
|
|
"entropy": 5.664244842529297,
|
|
"epoch": 1.101233671988389,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004885516464716537,
|
|
"loss": 5.4818,
|
|
"mean_token_accuracy": 0.16317940056324004,
|
|
"num_tokens": 25193827.0,
|
|
"step": 12140
|
|
},
|
|
{
|
|
"entropy": 5.716042947769165,
|
|
"epoch": 1.101687227866473,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.00048854145460027,
|
|
"loss": 5.484,
|
|
"mean_token_accuracy": 0.15731145590543746,
|
|
"num_tokens": 25204448.0,
|
|
"step": 12145
|
|
},
|
|
{
|
|
"entropy": 5.72451810836792,
|
|
"epoch": 1.1021407837445574,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004885312583127946,
|
|
"loss": 5.4299,
|
|
"mean_token_accuracy": 0.1701052352786064,
|
|
"num_tokens": 25215041.0,
|
|
"step": 12150
|
|
},
|
|
{
|
|
"entropy": 5.674443006515503,
|
|
"epoch": 1.1025943396226414,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004885210576094385,
|
|
"loss": 5.4861,
|
|
"mean_token_accuracy": 0.161158986389637,
|
|
"num_tokens": 25225937.0,
|
|
"step": 12155
|
|
},
|
|
{
|
|
"entropy": 5.636095237731934,
|
|
"epoch": 1.1030478955007257,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004885108524904124,
|
|
"loss": 5.3798,
|
|
"mean_token_accuracy": 0.16490069031715393,
|
|
"num_tokens": 25235270.0,
|
|
"step": 12160
|
|
},
|
|
{
|
|
"entropy": 5.689498090744019,
|
|
"epoch": 1.10350145137881,
|
|
"grad_norm": 3.09375,
|
|
"learning_rate": 0.0004885006429559275,
|
|
"loss": 5.5069,
|
|
"mean_token_accuracy": 0.15696319937705994,
|
|
"num_tokens": 25247080.0,
|
|
"step": 12165
|
|
},
|
|
{
|
|
"entropy": 5.767489337921143,
|
|
"epoch": 1.103955007256894,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004884904290061949,
|
|
"loss": 5.4497,
|
|
"mean_token_accuracy": 0.15679980516433717,
|
|
"num_tokens": 25256718.0,
|
|
"step": 12170
|
|
},
|
|
{
|
|
"entropy": 5.710507726669311,
|
|
"epoch": 1.1044085631349783,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004884802106414258,
|
|
"loss": 5.5718,
|
|
"mean_token_accuracy": 0.1566874548792839,
|
|
"num_tokens": 25266632.0,
|
|
"step": 12175
|
|
},
|
|
{
|
|
"entropy": 5.707070446014404,
|
|
"epoch": 1.1048621190130623,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004884699878618316,
|
|
"loss": 5.4336,
|
|
"mean_token_accuracy": 0.16789204627275467,
|
|
"num_tokens": 25275598.0,
|
|
"step": 12180
|
|
},
|
|
{
|
|
"entropy": 5.791386318206787,
|
|
"epoch": 1.1053156748911466,
|
|
"grad_norm": 3.03125,
|
|
"learning_rate": 0.0004884597606676236,
|
|
"loss": 5.5652,
|
|
"mean_token_accuracy": 0.16393594592809677,
|
|
"num_tokens": 25286598.0,
|
|
"step": 12185
|
|
},
|
|
{
|
|
"entropy": 5.6667577743530275,
|
|
"epoch": 1.1057692307692308,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004884495290590134,
|
|
"loss": 5.4658,
|
|
"mean_token_accuracy": 0.1686956986784935,
|
|
"num_tokens": 25296730.0,
|
|
"step": 12190
|
|
},
|
|
{
|
|
"entropy": 5.638488101959228,
|
|
"epoch": 1.1062227866473149,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004884392930362124,
|
|
"loss": 5.3838,
|
|
"mean_token_accuracy": 0.1706097424030304,
|
|
"num_tokens": 25306326.0,
|
|
"step": 12195
|
|
},
|
|
{
|
|
"entropy": 5.715025901794434,
|
|
"epoch": 1.1066763425253991,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.0004884290525994326,
|
|
"loss": 5.4982,
|
|
"mean_token_accuracy": 0.16701997965574264,
|
|
"num_tokens": 25316342.0,
|
|
"step": 12200
|
|
},
|
|
{
|
|
"entropy": 5.76042594909668,
|
|
"epoch": 1.1071298984034832,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004884188077488855,
|
|
"loss": 5.5259,
|
|
"mean_token_accuracy": 0.15774716883897782,
|
|
"num_tokens": 25326129.0,
|
|
"step": 12205
|
|
},
|
|
{
|
|
"entropy": 5.7002403259277346,
|
|
"epoch": 1.1075834542815675,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004884085584847831,
|
|
"loss": 5.4984,
|
|
"mean_token_accuracy": 0.16067406684160232,
|
|
"num_tokens": 25337156.0,
|
|
"step": 12210
|
|
},
|
|
{
|
|
"entropy": 5.761056232452392,
|
|
"epoch": 1.1080370101596517,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004883983048073375,
|
|
"loss": 5.5939,
|
|
"mean_token_accuracy": 0.15557485222816467,
|
|
"num_tokens": 25347632.0,
|
|
"step": 12215
|
|
},
|
|
{
|
|
"entropy": 5.715365171432495,
|
|
"epoch": 1.1084905660377358,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004883880467167603,
|
|
"loss": 5.3908,
|
|
"mean_token_accuracy": 0.16727125346660615,
|
|
"num_tokens": 25359186.0,
|
|
"step": 12220
|
|
},
|
|
{
|
|
"entropy": 5.682850027084351,
|
|
"epoch": 1.10894412191582,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.000488377784213264,
|
|
"loss": 5.4901,
|
|
"mean_token_accuracy": 0.1654043361544609,
|
|
"num_tokens": 25368993.0,
|
|
"step": 12225
|
|
},
|
|
{
|
|
"entropy": 5.617303848266602,
|
|
"epoch": 1.1093976777939043,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004883675172970608,
|
|
"loss": 5.4654,
|
|
"mean_token_accuracy": 0.16332084089517593,
|
|
"num_tokens": 25379880.0,
|
|
"step": 12230
|
|
},
|
|
{
|
|
"entropy": 5.705286884307862,
|
|
"epoch": 1.1098512336719883,
|
|
"grad_norm": 3.53125,
|
|
"learning_rate": 0.000488357245968363,
|
|
"loss": 5.6378,
|
|
"mean_token_accuracy": 0.15578718483448029,
|
|
"num_tokens": 25389942.0,
|
|
"step": 12235
|
|
},
|
|
{
|
|
"entropy": 5.74719467163086,
|
|
"epoch": 1.1103047895500726,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004883469702273829,
|
|
"loss": 5.4135,
|
|
"mean_token_accuracy": 0.17045416682958603,
|
|
"num_tokens": 25400836.0,
|
|
"step": 12240
|
|
},
|
|
{
|
|
"entropy": 5.686006259918213,
|
|
"epoch": 1.1107583454281567,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004883366900743331,
|
|
"loss": 5.4501,
|
|
"mean_token_accuracy": 0.17041821479797364,
|
|
"num_tokens": 25410502.0,
|
|
"step": 12245
|
|
},
|
|
{
|
|
"entropy": 5.632413101196289,
|
|
"epoch": 1.111211901306241,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004883264055094262,
|
|
"loss": 5.3807,
|
|
"mean_token_accuracy": 0.17125042974948884,
|
|
"num_tokens": 25420301.0,
|
|
"step": 12250
|
|
},
|
|
{
|
|
"entropy": 5.663805437088013,
|
|
"epoch": 1.1116654571843252,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004883161165328749,
|
|
"loss": 5.4664,
|
|
"mean_token_accuracy": 0.1629238620400429,
|
|
"num_tokens": 25431107.0,
|
|
"step": 12255
|
|
},
|
|
{
|
|
"entropy": 5.684454679489136,
|
|
"epoch": 1.1121190130624092,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.000488305823144892,
|
|
"loss": 5.4915,
|
|
"mean_token_accuracy": 0.16330774426460265,
|
|
"num_tokens": 25441256.0,
|
|
"step": 12260
|
|
},
|
|
{
|
|
"entropy": 5.7120894432067875,
|
|
"epoch": 1.1125725689404935,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004882955253456902,
|
|
"loss": 5.4362,
|
|
"mean_token_accuracy": 0.17027565985918044,
|
|
"num_tokens": 25451627.0,
|
|
"step": 12265
|
|
},
|
|
{
|
|
"entropy": 5.6989459037780765,
|
|
"epoch": 1.1130261248185778,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004882852231354826,
|
|
"loss": 5.5469,
|
|
"mean_token_accuracy": 0.1544725142419338,
|
|
"num_tokens": 25461273.0,
|
|
"step": 12270
|
|
},
|
|
{
|
|
"entropy": 5.671705436706543,
|
|
"epoch": 1.1134796806966618,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004882749165144822,
|
|
"loss": 5.4206,
|
|
"mean_token_accuracy": 0.16808366477489473,
|
|
"num_tokens": 25471949.0,
|
|
"step": 12275
|
|
},
|
|
{
|
|
"entropy": 5.672485589981079,
|
|
"epoch": 1.113933236574746,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004882646054829023,
|
|
"loss": 5.4533,
|
|
"mean_token_accuracy": 0.1631114512681961,
|
|
"num_tokens": 25482175.0,
|
|
"step": 12280
|
|
},
|
|
{
|
|
"entropy": 5.680838298797608,
|
|
"epoch": 1.1143867924528301,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.00048825429004095597,
|
|
"loss": 5.5169,
|
|
"mean_token_accuracy": 0.1640658587217331,
|
|
"num_tokens": 25491786.0,
|
|
"step": 12285
|
|
},
|
|
{
|
|
"entropy": 5.6861183643341064,
|
|
"epoch": 1.1148403483309144,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004882439701888566,
|
|
"loss": 5.448,
|
|
"mean_token_accuracy": 0.17438565641641618,
|
|
"num_tokens": 25502103.0,
|
|
"step": 12290
|
|
},
|
|
{
|
|
"entropy": 5.655974388122559,
|
|
"epoch": 1.1152939042089987,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.00048823364592681754,
|
|
"loss": 5.4152,
|
|
"mean_token_accuracy": 0.16853358298540116,
|
|
"num_tokens": 25512530.0,
|
|
"step": 12295
|
|
},
|
|
{
|
|
"entropy": 5.631742858886719,
|
|
"epoch": 1.1157474600870827,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.00048822331725505234,
|
|
"loss": 5.4217,
|
|
"mean_token_accuracy": 0.16453604251146317,
|
|
"num_tokens": 25522905.0,
|
|
"step": 12300
|
|
},
|
|
{
|
|
"entropy": 5.64605302810669,
|
|
"epoch": 1.116201015965167,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.00048821298417377456,
|
|
"loss": 5.3975,
|
|
"mean_token_accuracy": 0.17024944424629213,
|
|
"num_tokens": 25532963.0,
|
|
"step": 12305
|
|
},
|
|
{
|
|
"entropy": 5.574787712097168,
|
|
"epoch": 1.116654571843251,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.000488202646683198,
|
|
"loss": 5.4824,
|
|
"mean_token_accuracy": 0.16479005962610244,
|
|
"num_tokens": 25542583.0,
|
|
"step": 12310
|
|
},
|
|
{
|
|
"entropy": 5.676205587387085,
|
|
"epoch": 1.1171081277213353,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.0004881923047835364,
|
|
"loss": 5.4566,
|
|
"mean_token_accuracy": 0.16621775925159454,
|
|
"num_tokens": 25553367.0,
|
|
"step": 12315
|
|
},
|
|
{
|
|
"entropy": 5.813305044174195,
|
|
"epoch": 1.1175616835994195,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004881819584750036,
|
|
"loss": 5.5508,
|
|
"mean_token_accuracy": 0.15558717548847198,
|
|
"num_tokens": 25564823.0,
|
|
"step": 12320
|
|
},
|
|
{
|
|
"entropy": 5.702445077896118,
|
|
"epoch": 1.1180152394775036,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.00048817160775781356,
|
|
"loss": 5.5264,
|
|
"mean_token_accuracy": 0.16343066692352295,
|
|
"num_tokens": 25574946.0,
|
|
"step": 12325
|
|
},
|
|
{
|
|
"entropy": 5.727000427246094,
|
|
"epoch": 1.1184687953555879,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.00048816125263218023,
|
|
"loss": 5.5134,
|
|
"mean_token_accuracy": 0.16239065527915955,
|
|
"num_tokens": 25584779.0,
|
|
"step": 12330
|
|
},
|
|
{
|
|
"entropy": 5.728642177581787,
|
|
"epoch": 1.118922351233672,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.00048815089309831803,
|
|
"loss": 5.5505,
|
|
"mean_token_accuracy": 0.16122682094573976,
|
|
"num_tokens": 25594725.0,
|
|
"step": 12335
|
|
},
|
|
{
|
|
"entropy": 5.693500328063965,
|
|
"epoch": 1.1193759071117562,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.000488140529156441,
|
|
"loss": 5.5504,
|
|
"mean_token_accuracy": 0.15737500935792922,
|
|
"num_tokens": 25605499.0,
|
|
"step": 12340
|
|
},
|
|
{
|
|
"entropy": 5.70117154121399,
|
|
"epoch": 1.1198294629898404,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004881301608067635,
|
|
"loss": 5.4829,
|
|
"mean_token_accuracy": 0.16727777123451232,
|
|
"num_tokens": 25616443.0,
|
|
"step": 12345
|
|
},
|
|
{
|
|
"entropy": 5.677675819396972,
|
|
"epoch": 1.1202830188679245,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.00048811978804949997,
|
|
"loss": 5.4739,
|
|
"mean_token_accuracy": 0.1600932240486145,
|
|
"num_tokens": 25627762.0,
|
|
"step": 12350
|
|
},
|
|
{
|
|
"entropy": 5.727726984024048,
|
|
"epoch": 1.1207365747460087,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.000488109410884865,
|
|
"loss": 5.5216,
|
|
"mean_token_accuracy": 0.16268306225538254,
|
|
"num_tokens": 25637904.0,
|
|
"step": 12355
|
|
},
|
|
{
|
|
"entropy": 5.729953241348267,
|
|
"epoch": 1.1211901306240928,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00048809902931307294,
|
|
"loss": 5.4079,
|
|
"mean_token_accuracy": 0.16491089165210723,
|
|
"num_tokens": 25649058.0,
|
|
"step": 12360
|
|
},
|
|
{
|
|
"entropy": 5.710848140716553,
|
|
"epoch": 1.121643686502177,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004880886433343388,
|
|
"loss": 5.4888,
|
|
"mean_token_accuracy": 0.168439182639122,
|
|
"num_tokens": 25659161.0,
|
|
"step": 12365
|
|
},
|
|
{
|
|
"entropy": 5.645144748687744,
|
|
"epoch": 1.1220972423802613,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004880782529488771,
|
|
"loss": 5.392,
|
|
"mean_token_accuracy": 0.1683065488934517,
|
|
"num_tokens": 25669336.0,
|
|
"step": 12370
|
|
},
|
|
{
|
|
"entropy": 5.6779046058654785,
|
|
"epoch": 1.1225507982583454,
|
|
"grad_norm": 2.875,
|
|
"learning_rate": 0.0004880678581569029,
|
|
"loss": 5.5275,
|
|
"mean_token_accuracy": 0.167069973051548,
|
|
"num_tokens": 25680443.0,
|
|
"step": 12375
|
|
},
|
|
{
|
|
"entropy": 5.649819374084473,
|
|
"epoch": 1.1230043541364296,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.00048805745895863105,
|
|
"loss": 5.4264,
|
|
"mean_token_accuracy": 0.16533208042383193,
|
|
"num_tokens": 25690202.0,
|
|
"step": 12380
|
|
},
|
|
{
|
|
"entropy": 5.639210271835327,
|
|
"epoch": 1.1234579100145137,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004880470553542767,
|
|
"loss": 5.4786,
|
|
"mean_token_accuracy": 0.16973664313554765,
|
|
"num_tokens": 25699255.0,
|
|
"step": 12385
|
|
},
|
|
{
|
|
"entropy": 5.6339024066925045,
|
|
"epoch": 1.123911465892598,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.00048803664734405495,
|
|
"loss": 5.4704,
|
|
"mean_token_accuracy": 0.16109772622585297,
|
|
"num_tokens": 25710714.0,
|
|
"step": 12390
|
|
},
|
|
{
|
|
"entropy": 5.7163794994354244,
|
|
"epoch": 1.1243650217706822,
|
|
"grad_norm": 2.984375,
|
|
"learning_rate": 0.000488026234928181,
|
|
"loss": 5.4618,
|
|
"mean_token_accuracy": 0.16500280201435089,
|
|
"num_tokens": 25721722.0,
|
|
"step": 12395
|
|
},
|
|
{
|
|
"entropy": 5.679118204116821,
|
|
"epoch": 1.1248185776487662,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004880158181068703,
|
|
"loss": 5.4345,
|
|
"mean_token_accuracy": 0.17283545881509782,
|
|
"num_tokens": 25732096.0,
|
|
"step": 12400
|
|
},
|
|
{
|
|
"entropy": 5.688442707061768,
|
|
"epoch": 1.1252721335268505,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.00048800539688033807,
|
|
"loss": 5.4866,
|
|
"mean_token_accuracy": 0.16553248167037965,
|
|
"num_tokens": 25741499.0,
|
|
"step": 12405
|
|
},
|
|
{
|
|
"entropy": 5.73737850189209,
|
|
"epoch": 1.1257256894049348,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004879949712488001,
|
|
"loss": 5.5901,
|
|
"mean_token_accuracy": 0.16267940849065782,
|
|
"num_tokens": 25751913.0,
|
|
"step": 12410
|
|
},
|
|
{
|
|
"entropy": 5.7223235130310055,
|
|
"epoch": 1.1261792452830188,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.00048798454121247177,
|
|
"loss": 5.5062,
|
|
"mean_token_accuracy": 0.16354126930236818,
|
|
"num_tokens": 25762602.0,
|
|
"step": 12415
|
|
},
|
|
{
|
|
"entropy": 5.682435655593872,
|
|
"epoch": 1.126632801161103,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004879741067715688,
|
|
"loss": 5.4598,
|
|
"mean_token_accuracy": 0.16635682433843613,
|
|
"num_tokens": 25773872.0,
|
|
"step": 12420
|
|
},
|
|
{
|
|
"entropy": 5.760980224609375,
|
|
"epoch": 1.1270863570391871,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.00048796366792630715,
|
|
"loss": 5.4928,
|
|
"mean_token_accuracy": 0.16088351458311081,
|
|
"num_tokens": 25784723.0,
|
|
"step": 12425
|
|
},
|
|
{
|
|
"entropy": 5.6614080429077145,
|
|
"epoch": 1.1275399129172714,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004879532246769025,
|
|
"loss": 5.4908,
|
|
"mean_token_accuracy": 0.16577196568250657,
|
|
"num_tokens": 25794897.0,
|
|
"step": 12430
|
|
},
|
|
{
|
|
"entropy": 5.655796670913697,
|
|
"epoch": 1.1279934687953557,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004879427770235709,
|
|
"loss": 5.3731,
|
|
"mean_token_accuracy": 0.17425438910722732,
|
|
"num_tokens": 25804445.0,
|
|
"step": 12435
|
|
},
|
|
{
|
|
"entropy": 5.715863275527954,
|
|
"epoch": 1.1284470246734397,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.00048793232496652846,
|
|
"loss": 5.5384,
|
|
"mean_token_accuracy": 0.16060084253549575,
|
|
"num_tokens": 25815495.0,
|
|
"step": 12440
|
|
},
|
|
{
|
|
"entropy": 5.731628894805908,
|
|
"epoch": 1.128900580551524,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.00048792186850599124,
|
|
"loss": 5.4796,
|
|
"mean_token_accuracy": 0.16989186704158782,
|
|
"num_tokens": 25826120.0,
|
|
"step": 12445
|
|
},
|
|
{
|
|
"entropy": 5.637911796569824,
|
|
"epoch": 1.1293541364296082,
|
|
"grad_norm": 11.4375,
|
|
"learning_rate": 0.0004879114076421755,
|
|
"loss": 5.474,
|
|
"mean_token_accuracy": 0.16747748851776123,
|
|
"num_tokens": 25835926.0,
|
|
"step": 12450
|
|
},
|
|
{
|
|
"entropy": 5.656536197662353,
|
|
"epoch": 1.1298076923076923,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.00048790094237529763,
|
|
"loss": 5.5172,
|
|
"mean_token_accuracy": 0.1612439125776291,
|
|
"num_tokens": 25846095.0,
|
|
"step": 12455
|
|
},
|
|
{
|
|
"entropy": 5.734703397750854,
|
|
"epoch": 1.1302612481857766,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.000487890472705574,
|
|
"loss": 5.5097,
|
|
"mean_token_accuracy": 0.15791749209165573,
|
|
"num_tokens": 25858541.0,
|
|
"step": 12460
|
|
},
|
|
{
|
|
"entropy": 5.735379600524903,
|
|
"epoch": 1.1307148040638606,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00048787999863322113,
|
|
"loss": 5.3943,
|
|
"mean_token_accuracy": 0.17095805555582047,
|
|
"num_tokens": 25867664.0,
|
|
"step": 12465
|
|
},
|
|
{
|
|
"entropy": 5.66964545249939,
|
|
"epoch": 1.1311683599419449,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004878695201584557,
|
|
"loss": 5.4643,
|
|
"mean_token_accuracy": 0.16811592876911163,
|
|
"num_tokens": 25877300.0,
|
|
"step": 12470
|
|
},
|
|
{
|
|
"entropy": 5.64678258895874,
|
|
"epoch": 1.1316219158200291,
|
|
"grad_norm": 4.09375,
|
|
"learning_rate": 0.0004878590372814943,
|
|
"loss": 5.4624,
|
|
"mean_token_accuracy": 0.1708560436964035,
|
|
"num_tokens": 25888009.0,
|
|
"step": 12475
|
|
},
|
|
{
|
|
"entropy": 5.720460653305054,
|
|
"epoch": 1.1320754716981132,
|
|
"grad_norm": 4.21875,
|
|
"learning_rate": 0.00048784855000255374,
|
|
"loss": 5.5176,
|
|
"mean_token_accuracy": 0.15952577590942382,
|
|
"num_tokens": 25897285.0,
|
|
"step": 12480
|
|
},
|
|
{
|
|
"entropy": 5.65304479598999,
|
|
"epoch": 1.1325290275761974,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.00048783805832185097,
|
|
"loss": 5.393,
|
|
"mean_token_accuracy": 0.17271489948034285,
|
|
"num_tokens": 25907355.0,
|
|
"step": 12485
|
|
},
|
|
{
|
|
"entropy": 5.64521369934082,
|
|
"epoch": 1.1329825834542815,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004878275622396029,
|
|
"loss": 5.4913,
|
|
"mean_token_accuracy": 0.16741527020931243,
|
|
"num_tokens": 25918566.0,
|
|
"step": 12490
|
|
},
|
|
{
|
|
"entropy": 5.696262645721435,
|
|
"epoch": 1.1334361393323658,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.00048781706175602665,
|
|
"loss": 5.5373,
|
|
"mean_token_accuracy": 0.16235175132751464,
|
|
"num_tokens": 25929145.0,
|
|
"step": 12495
|
|
},
|
|
{
|
|
"entropy": 5.644708967208862,
|
|
"epoch": 1.13388969521045,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.00048780655687133927,
|
|
"loss": 5.3719,
|
|
"mean_token_accuracy": 0.1706993505358696,
|
|
"num_tokens": 25938163.0,
|
|
"step": 12500
|
|
},
|
|
{
|
|
"entropy": 5.655734014511109,
|
|
"epoch": 1.134343251088534,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.00048779604758575806,
|
|
"loss": 5.4278,
|
|
"mean_token_accuracy": 0.16455347687005997,
|
|
"num_tokens": 25948962.0,
|
|
"step": 12505
|
|
},
|
|
{
|
|
"entropy": 5.641784429550171,
|
|
"epoch": 1.1347968069666183,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004877855338995004,
|
|
"loss": 5.4169,
|
|
"mean_token_accuracy": 0.1596992239356041,
|
|
"num_tokens": 25959653.0,
|
|
"step": 12510
|
|
},
|
|
{
|
|
"entropy": 5.715621280670166,
|
|
"epoch": 1.1352503628447024,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.00048777501581278367,
|
|
"loss": 5.491,
|
|
"mean_token_accuracy": 0.16352986246347428,
|
|
"num_tokens": 25970268.0,
|
|
"step": 12515
|
|
},
|
|
{
|
|
"entropy": 5.664155435562134,
|
|
"epoch": 1.1357039187227866,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004877644933258254,
|
|
"loss": 5.4377,
|
|
"mean_token_accuracy": 0.16603747457265855,
|
|
"num_tokens": 25980321.0,
|
|
"step": 12520
|
|
},
|
|
{
|
|
"entropy": 5.613667106628418,
|
|
"epoch": 1.136157474600871,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004877539664388432,
|
|
"loss": 5.4499,
|
|
"mean_token_accuracy": 0.15894390940666198,
|
|
"num_tokens": 25992466.0,
|
|
"step": 12525
|
|
},
|
|
{
|
|
"entropy": 5.637245559692383,
|
|
"epoch": 1.136611030478955,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.00048774343515205464,
|
|
"loss": 5.4502,
|
|
"mean_token_accuracy": 0.16515804678201676,
|
|
"num_tokens": 26003553.0,
|
|
"step": 12530
|
|
},
|
|
{
|
|
"entropy": 5.729487705230713,
|
|
"epoch": 1.1370645863570392,
|
|
"grad_norm": 3.15625,
|
|
"learning_rate": 0.0004877328994656778,
|
|
"loss": 5.4548,
|
|
"mean_token_accuracy": 0.1668217360973358,
|
|
"num_tokens": 26013299.0,
|
|
"step": 12535
|
|
},
|
|
{
|
|
"entropy": 5.670506477355957,
|
|
"epoch": 1.1375181422351233,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004877223593799303,
|
|
"loss": 5.4545,
|
|
"mean_token_accuracy": 0.17032000422477722,
|
|
"num_tokens": 26022913.0,
|
|
"step": 12540
|
|
},
|
|
{
|
|
"entropy": 5.632179546356201,
|
|
"epoch": 1.1379716981132075,
|
|
"grad_norm": 5.59375,
|
|
"learning_rate": 0.0004877118148950302,
|
|
"loss": 5.4527,
|
|
"mean_token_accuracy": 0.1688927471637726,
|
|
"num_tokens": 26033191.0,
|
|
"step": 12545
|
|
},
|
|
{
|
|
"entropy": 5.817878866195679,
|
|
"epoch": 1.1384252539912918,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.00048770126601119555,
|
|
"loss": 5.5913,
|
|
"mean_token_accuracy": 0.1574409358203411,
|
|
"num_tokens": 26043517.0,
|
|
"step": 12550
|
|
},
|
|
{
|
|
"entropy": 5.759597492218018,
|
|
"epoch": 1.1388788098693758,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.00048769071272864454,
|
|
"loss": 5.5454,
|
|
"mean_token_accuracy": 0.15523600578308105,
|
|
"num_tokens": 26054173.0,
|
|
"step": 12555
|
|
},
|
|
{
|
|
"entropy": 5.72742338180542,
|
|
"epoch": 1.13933236574746,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.00048768015504759536,
|
|
"loss": 5.5349,
|
|
"mean_token_accuracy": 0.15635675191879272,
|
|
"num_tokens": 26064929.0,
|
|
"step": 12560
|
|
},
|
|
{
|
|
"entropy": 5.640500593185425,
|
|
"epoch": 1.1397859216255442,
|
|
"grad_norm": 3.9375,
|
|
"learning_rate": 0.0004876695929682665,
|
|
"loss": 5.422,
|
|
"mean_token_accuracy": 0.17017849087715148,
|
|
"num_tokens": 26074872.0,
|
|
"step": 12565
|
|
},
|
|
{
|
|
"entropy": 5.684097814559936,
|
|
"epoch": 1.1402394775036284,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.00048765902649087605,
|
|
"loss": 5.3704,
|
|
"mean_token_accuracy": 0.16702675968408584,
|
|
"num_tokens": 26086328.0,
|
|
"step": 12570
|
|
},
|
|
{
|
|
"entropy": 5.716231346130371,
|
|
"epoch": 1.1406930333817127,
|
|
"grad_norm": 3.109375,
|
|
"learning_rate": 0.00048764845561564285,
|
|
"loss": 5.4638,
|
|
"mean_token_accuracy": 0.1646862208843231,
|
|
"num_tokens": 26096477.0,
|
|
"step": 12575
|
|
},
|
|
{
|
|
"entropy": 5.693419027328491,
|
|
"epoch": 1.1411465892597967,
|
|
"grad_norm": 2.9375,
|
|
"learning_rate": 0.00048763788034278545,
|
|
"loss": 5.437,
|
|
"mean_token_accuracy": 0.1698093980550766,
|
|
"num_tokens": 26106183.0,
|
|
"step": 12580
|
|
},
|
|
{
|
|
"entropy": 5.688015460968018,
|
|
"epoch": 1.141600145137881,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004876273006725225,
|
|
"loss": 5.4869,
|
|
"mean_token_accuracy": 0.16437682062387465,
|
|
"num_tokens": 26117932.0,
|
|
"step": 12585
|
|
},
|
|
{
|
|
"entropy": 5.638660287857055,
|
|
"epoch": 1.1420537010159653,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.00048761671660507266,
|
|
"loss": 5.458,
|
|
"mean_token_accuracy": 0.16882532685995102,
|
|
"num_tokens": 26128616.0,
|
|
"step": 12590
|
|
},
|
|
{
|
|
"entropy": 5.685114908218384,
|
|
"epoch": 1.1425072568940493,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.000487606128140655,
|
|
"loss": 5.4355,
|
|
"mean_token_accuracy": 0.1643654316663742,
|
|
"num_tokens": 26138758.0,
|
|
"step": 12595
|
|
},
|
|
{
|
|
"entropy": 5.643755102157593,
|
|
"epoch": 1.1429608127721336,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004875955352794885,
|
|
"loss": 5.4362,
|
|
"mean_token_accuracy": 0.16572753041982652,
|
|
"num_tokens": 26149199.0,
|
|
"step": 12600
|
|
},
|
|
{
|
|
"entropy": 5.667513704299926,
|
|
"epoch": 1.1434143686502176,
|
|
"grad_norm": 2.875,
|
|
"learning_rate": 0.0004875849380217921,
|
|
"loss": 5.5444,
|
|
"mean_token_accuracy": 0.16516696214675902,
|
|
"num_tokens": 26160276.0,
|
|
"step": 12605
|
|
},
|
|
{
|
|
"entropy": 5.720070314407349,
|
|
"epoch": 1.1438679245283019,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.000487574336367785,
|
|
"loss": 5.4267,
|
|
"mean_token_accuracy": 0.1680523633956909,
|
|
"num_tokens": 26169564.0,
|
|
"step": 12610
|
|
},
|
|
{
|
|
"entropy": 5.593117618560791,
|
|
"epoch": 1.1443214804063861,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004875637303176865,
|
|
"loss": 5.3867,
|
|
"mean_token_accuracy": 0.1710687458515167,
|
|
"num_tokens": 26179135.0,
|
|
"step": 12615
|
|
},
|
|
{
|
|
"entropy": 5.724180269241333,
|
|
"epoch": 1.1447750362844702,
|
|
"grad_norm": 7.28125,
|
|
"learning_rate": 0.00048755311987171585,
|
|
"loss": 5.5515,
|
|
"mean_token_accuracy": 0.16266196072101594,
|
|
"num_tokens": 26190116.0,
|
|
"step": 12620
|
|
},
|
|
{
|
|
"entropy": 5.719642448425293,
|
|
"epoch": 1.1452285921625545,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.00048754250503009244,
|
|
"loss": 5.6032,
|
|
"mean_token_accuracy": 0.15758416056632996,
|
|
"num_tokens": 26200847.0,
|
|
"step": 12625
|
|
},
|
|
{
|
|
"entropy": 5.782734537124634,
|
|
"epoch": 1.1456821480406387,
|
|
"grad_norm": 3.265625,
|
|
"learning_rate": 0.00048753188579303596,
|
|
"loss": 5.5558,
|
|
"mean_token_accuracy": 0.15852403193712233,
|
|
"num_tokens": 26211151.0,
|
|
"step": 12630
|
|
},
|
|
{
|
|
"entropy": 5.745510673522949,
|
|
"epoch": 1.1461357039187228,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004875212621607659,
|
|
"loss": 5.4529,
|
|
"mean_token_accuracy": 0.17111167013645173,
|
|
"num_tokens": 26221273.0,
|
|
"step": 12635
|
|
},
|
|
{
|
|
"entropy": 5.725997638702393,
|
|
"epoch": 1.146589259796807,
|
|
"grad_norm": 2.984375,
|
|
"learning_rate": 0.00048751063413350203,
|
|
"loss": 5.5663,
|
|
"mean_token_accuracy": 0.16114696413278579,
|
|
"num_tokens": 26231770.0,
|
|
"step": 12640
|
|
},
|
|
{
|
|
"entropy": 5.685273218154907,
|
|
"epoch": 1.147042815674891,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.000487500001711464,
|
|
"loss": 5.521,
|
|
"mean_token_accuracy": 0.15823211371898652,
|
|
"num_tokens": 26241386.0,
|
|
"step": 12645
|
|
},
|
|
{
|
|
"entropy": 5.771583080291748,
|
|
"epoch": 1.1474963715529753,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004874893648948719,
|
|
"loss": 5.594,
|
|
"mean_token_accuracy": 0.1569131463766098,
|
|
"num_tokens": 26251991.0,
|
|
"step": 12650
|
|
},
|
|
{
|
|
"entropy": 5.873394870758057,
|
|
"epoch": 1.1479499274310596,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.00048747872368394546,
|
|
"loss": 5.6321,
|
|
"mean_token_accuracy": 0.16126348823308945,
|
|
"num_tokens": 26262331.0,
|
|
"step": 12655
|
|
},
|
|
{
|
|
"entropy": 5.802481746673584,
|
|
"epoch": 1.1484034833091437,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.00048746807807890496,
|
|
"loss": 5.536,
|
|
"mean_token_accuracy": 0.1619427666068077,
|
|
"num_tokens": 26272939.0,
|
|
"step": 12660
|
|
},
|
|
{
|
|
"entropy": 5.6912065029144285,
|
|
"epoch": 1.148857039187228,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.00048745742807997046,
|
|
"loss": 5.4793,
|
|
"mean_token_accuracy": 0.1716838300228119,
|
|
"num_tokens": 26282849.0,
|
|
"step": 12665
|
|
},
|
|
{
|
|
"entropy": 5.695969581604004,
|
|
"epoch": 1.149310595065312,
|
|
"grad_norm": 3.0625,
|
|
"learning_rate": 0.00048744677368736216,
|
|
"loss": 5.492,
|
|
"mean_token_accuracy": 0.17240264564752578,
|
|
"num_tokens": 26292449.0,
|
|
"step": 12670
|
|
},
|
|
{
|
|
"entropy": 5.608897972106933,
|
|
"epoch": 1.1497641509433962,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00048743611490130044,
|
|
"loss": 5.4427,
|
|
"mean_token_accuracy": 0.16311823576688766,
|
|
"num_tokens": 26302506.0,
|
|
"step": 12675
|
|
},
|
|
{
|
|
"entropy": 5.674193859100342,
|
|
"epoch": 1.1502177068214805,
|
|
"grad_norm": 3.859375,
|
|
"learning_rate": 0.00048742545172200576,
|
|
"loss": 5.49,
|
|
"mean_token_accuracy": 0.1684115409851074,
|
|
"num_tokens": 26312346.0,
|
|
"step": 12680
|
|
},
|
|
{
|
|
"entropy": 5.794550657272339,
|
|
"epoch": 1.1506712626995645,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004874147841496986,
|
|
"loss": 5.5127,
|
|
"mean_token_accuracy": 0.16813080310821532,
|
|
"num_tokens": 26323173.0,
|
|
"step": 12685
|
|
},
|
|
{
|
|
"entropy": 5.787297344207763,
|
|
"epoch": 1.1511248185776488,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004874041121845996,
|
|
"loss": 5.5494,
|
|
"mean_token_accuracy": 0.15646430850028992,
|
|
"num_tokens": 26334371.0,
|
|
"step": 12690
|
|
},
|
|
{
|
|
"entropy": 5.676742315292358,
|
|
"epoch": 1.1515783744557329,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004873934358269294,
|
|
"loss": 5.4917,
|
|
"mean_token_accuracy": 0.16978609263896943,
|
|
"num_tokens": 26344506.0,
|
|
"step": 12695
|
|
},
|
|
{
|
|
"entropy": 5.739569473266601,
|
|
"epoch": 1.1520319303338171,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004873827550769088,
|
|
"loss": 5.4909,
|
|
"mean_token_accuracy": 0.1606821045279503,
|
|
"num_tokens": 26354534.0,
|
|
"step": 12700
|
|
},
|
|
{
|
|
"entropy": 5.717080450057983,
|
|
"epoch": 1.1524854862119014,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004873720699347587,
|
|
"loss": 5.4788,
|
|
"mean_token_accuracy": 0.1608733579516411,
|
|
"num_tokens": 26365682.0,
|
|
"step": 12705
|
|
},
|
|
{
|
|
"entropy": 5.737882661819458,
|
|
"epoch": 1.1529390420899854,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004873613804007001,
|
|
"loss": 5.5687,
|
|
"mean_token_accuracy": 0.16541330218315126,
|
|
"num_tokens": 26376702.0,
|
|
"step": 12710
|
|
},
|
|
{
|
|
"entropy": 5.6979655742645265,
|
|
"epoch": 1.1533925979680697,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004873506864749541,
|
|
"loss": 5.3895,
|
|
"mean_token_accuracy": 0.16552336364984513,
|
|
"num_tokens": 26387154.0,
|
|
"step": 12715
|
|
},
|
|
{
|
|
"entropy": 5.773201513290405,
|
|
"epoch": 1.1538461538461537,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004873399881577417,
|
|
"loss": 5.5641,
|
|
"mean_token_accuracy": 0.1565118119120598,
|
|
"num_tokens": 26397883.0,
|
|
"step": 12720
|
|
},
|
|
{
|
|
"entropy": 5.624920177459717,
|
|
"epoch": 1.154299709724238,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004873292854492842,
|
|
"loss": 5.3926,
|
|
"mean_token_accuracy": 0.17122539281845092,
|
|
"num_tokens": 26407613.0,
|
|
"step": 12725
|
|
},
|
|
{
|
|
"entropy": 5.578226327896118,
|
|
"epoch": 1.1547532656023223,
|
|
"grad_norm": 3.0625,
|
|
"learning_rate": 0.0004873185783498031,
|
|
"loss": 5.39,
|
|
"mean_token_accuracy": 0.17040119469165801,
|
|
"num_tokens": 26417221.0,
|
|
"step": 12730
|
|
},
|
|
{
|
|
"entropy": 5.671765661239624,
|
|
"epoch": 1.1552068214804063,
|
|
"grad_norm": 3.015625,
|
|
"learning_rate": 0.0004873078668595197,
|
|
"loss": 5.4874,
|
|
"mean_token_accuracy": 0.16436854004859924,
|
|
"num_tokens": 26427976.0,
|
|
"step": 12735
|
|
},
|
|
{
|
|
"entropy": 5.740582656860352,
|
|
"epoch": 1.1556603773584906,
|
|
"grad_norm": 3.8125,
|
|
"learning_rate": 0.00048729715097865534,
|
|
"loss": 5.5331,
|
|
"mean_token_accuracy": 0.16175803393125535,
|
|
"num_tokens": 26439213.0,
|
|
"step": 12740
|
|
},
|
|
{
|
|
"entropy": 5.687251281738281,
|
|
"epoch": 1.1561139332365746,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004872864307074319,
|
|
"loss": 5.4601,
|
|
"mean_token_accuracy": 0.1701526626944542,
|
|
"num_tokens": 26449763.0,
|
|
"step": 12745
|
|
},
|
|
{
|
|
"entropy": 5.728672504425049,
|
|
"epoch": 1.156567489114659,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.00048727570604607096,
|
|
"loss": 5.5248,
|
|
"mean_token_accuracy": 0.1643197387456894,
|
|
"num_tokens": 26460133.0,
|
|
"step": 12750
|
|
},
|
|
{
|
|
"entropy": 5.705990123748779,
|
|
"epoch": 1.1570210449927432,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.00048726497699479437,
|
|
"loss": 5.4461,
|
|
"mean_token_accuracy": 0.16539129763841628,
|
|
"num_tokens": 26470164.0,
|
|
"step": 12755
|
|
},
|
|
{
|
|
"entropy": 5.72627625465393,
|
|
"epoch": 1.1574746008708272,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.000487254243553824,
|
|
"loss": 5.485,
|
|
"mean_token_accuracy": 0.1625959813594818,
|
|
"num_tokens": 26480314.0,
|
|
"step": 12760
|
|
},
|
|
{
|
|
"entropy": 5.671308469772339,
|
|
"epoch": 1.1579281567489115,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.0004872435057233817,
|
|
"loss": 5.4557,
|
|
"mean_token_accuracy": 0.1708862990140915,
|
|
"num_tokens": 26491184.0,
|
|
"step": 12765
|
|
},
|
|
{
|
|
"entropy": 5.638969039916992,
|
|
"epoch": 1.1583817126269957,
|
|
"grad_norm": 3.1875,
|
|
"learning_rate": 0.00048723276350368957,
|
|
"loss": 5.3636,
|
|
"mean_token_accuracy": 0.17109058648347855,
|
|
"num_tokens": 26501432.0,
|
|
"step": 12770
|
|
},
|
|
{
|
|
"entropy": 5.71687536239624,
|
|
"epoch": 1.1588352685050798,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.00048722201689496984,
|
|
"loss": 5.4613,
|
|
"mean_token_accuracy": 0.16260756850242614,
|
|
"num_tokens": 26510379.0,
|
|
"step": 12775
|
|
},
|
|
{
|
|
"entropy": 5.669999790191651,
|
|
"epoch": 1.159288824383164,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004872112658974447,
|
|
"loss": 5.4396,
|
|
"mean_token_accuracy": 0.16915746331214904,
|
|
"num_tokens": 26519454.0,
|
|
"step": 12780
|
|
},
|
|
{
|
|
"entropy": 5.645273876190186,
|
|
"epoch": 1.159742380261248,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.00048720051051133657,
|
|
"loss": 5.3739,
|
|
"mean_token_accuracy": 0.1694876566529274,
|
|
"num_tokens": 26531325.0,
|
|
"step": 12785
|
|
},
|
|
{
|
|
"entropy": 5.668484020233154,
|
|
"epoch": 1.1601959361393324,
|
|
"grad_norm": 3.875,
|
|
"learning_rate": 0.0004871897507368678,
|
|
"loss": 5.5059,
|
|
"mean_token_accuracy": 0.16702394783496857,
|
|
"num_tokens": 26541510.0,
|
|
"step": 12790
|
|
},
|
|
{
|
|
"entropy": 5.7515599727630615,
|
|
"epoch": 1.1606494920174166,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.00048717898657426093,
|
|
"loss": 5.6318,
|
|
"mean_token_accuracy": 0.1585722751915455,
|
|
"num_tokens": 26553400.0,
|
|
"step": 12795
|
|
},
|
|
{
|
|
"entropy": 5.722867393493653,
|
|
"epoch": 1.1611030478955007,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.00048716821802373856,
|
|
"loss": 5.4859,
|
|
"mean_token_accuracy": 0.16533118188381196,
|
|
"num_tokens": 26564340.0,
|
|
"step": 12800
|
|
},
|
|
{
|
|
"entropy": 5.714131498336792,
|
|
"epoch": 1.161556603773585,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.00048715744508552334,
|
|
"loss": 5.4526,
|
|
"mean_token_accuracy": 0.16750866025686265,
|
|
"num_tokens": 26573615.0,
|
|
"step": 12805
|
|
},
|
|
{
|
|
"entropy": 5.725940895080567,
|
|
"epoch": 1.1620101596516692,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004871466677598381,
|
|
"loss": 5.6172,
|
|
"mean_token_accuracy": 0.15981352627277373,
|
|
"num_tokens": 26584149.0,
|
|
"step": 12810
|
|
},
|
|
{
|
|
"entropy": 5.6734460353851315,
|
|
"epoch": 1.1624637155297532,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.0004871358860469057,
|
|
"loss": 5.4922,
|
|
"mean_token_accuracy": 0.15879530608654022,
|
|
"num_tokens": 26595064.0,
|
|
"step": 12815
|
|
},
|
|
{
|
|
"entropy": 5.684795475006103,
|
|
"epoch": 1.1629172714078375,
|
|
"grad_norm": 12.1875,
|
|
"learning_rate": 0.00048712509994694903,
|
|
"loss": 5.5002,
|
|
"mean_token_accuracy": 0.16152793169021606,
|
|
"num_tokens": 26605636.0,
|
|
"step": 12820
|
|
},
|
|
{
|
|
"entropy": 5.735297393798828,
|
|
"epoch": 1.1633708272859216,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004871143094601914,
|
|
"loss": 5.5835,
|
|
"mean_token_accuracy": 0.15922466069459915,
|
|
"num_tokens": 26616065.0,
|
|
"step": 12825
|
|
},
|
|
{
|
|
"entropy": 5.800519371032715,
|
|
"epoch": 1.1638243831640058,
|
|
"grad_norm": 2.875,
|
|
"learning_rate": 0.0004871035145868557,
|
|
"loss": 5.5359,
|
|
"mean_token_accuracy": 0.15710667371749878,
|
|
"num_tokens": 26627246.0,
|
|
"step": 12830
|
|
},
|
|
{
|
|
"entropy": 5.700431299209595,
|
|
"epoch": 1.16427793904209,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.00048709271532716524,
|
|
"loss": 5.5,
|
|
"mean_token_accuracy": 0.16222633868455888,
|
|
"num_tokens": 26637630.0,
|
|
"step": 12835
|
|
},
|
|
{
|
|
"entropy": 5.700282382965088,
|
|
"epoch": 1.1647314949201741,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004870819116813434,
|
|
"loss": 5.586,
|
|
"mean_token_accuracy": 0.16132223457098008,
|
|
"num_tokens": 26648683.0,
|
|
"step": 12840
|
|
},
|
|
{
|
|
"entropy": 5.767683458328247,
|
|
"epoch": 1.1651850507982584,
|
|
"grad_norm": 3.140625,
|
|
"learning_rate": 0.00048707110364961363,
|
|
"loss": 5.5114,
|
|
"mean_token_accuracy": 0.156746444106102,
|
|
"num_tokens": 26659573.0,
|
|
"step": 12845
|
|
},
|
|
{
|
|
"entropy": 5.6991064071655275,
|
|
"epoch": 1.1656386066763424,
|
|
"grad_norm": 4.28125,
|
|
"learning_rate": 0.00048706029123219937,
|
|
"loss": 5.4134,
|
|
"mean_token_accuracy": 0.1704317197203636,
|
|
"num_tokens": 26669384.0,
|
|
"step": 12850
|
|
},
|
|
{
|
|
"entropy": 5.738013887405396,
|
|
"epoch": 1.1660921625544267,
|
|
"grad_norm": 3.84375,
|
|
"learning_rate": 0.00048704947442932426,
|
|
"loss": 5.5677,
|
|
"mean_token_accuracy": 0.1565699651837349,
|
|
"num_tokens": 26679721.0,
|
|
"step": 12855
|
|
},
|
|
{
|
|
"entropy": 5.768910217285156,
|
|
"epoch": 1.166545718432511,
|
|
"grad_norm": 13.0,
|
|
"learning_rate": 0.00048703865324121196,
|
|
"loss": 5.4461,
|
|
"mean_token_accuracy": 0.1679557368159294,
|
|
"num_tokens": 26689923.0,
|
|
"step": 12860
|
|
},
|
|
{
|
|
"entropy": 5.706762504577637,
|
|
"epoch": 1.166999274310595,
|
|
"grad_norm": 10.6875,
|
|
"learning_rate": 0.00048702782766808637,
|
|
"loss": 5.4371,
|
|
"mean_token_accuracy": 0.16808807998895645,
|
|
"num_tokens": 26699953.0,
|
|
"step": 12865
|
|
},
|
|
{
|
|
"entropy": 5.734587526321411,
|
|
"epoch": 1.1674528301886793,
|
|
"grad_norm": 3.234375,
|
|
"learning_rate": 0.0004870169977101711,
|
|
"loss": 5.6517,
|
|
"mean_token_accuracy": 0.15469444543123245,
|
|
"num_tokens": 26712099.0,
|
|
"step": 12870
|
|
},
|
|
{
|
|
"entropy": 5.7446013450622555,
|
|
"epoch": 1.1679063860667633,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.00048700616336769037,
|
|
"loss": 5.5146,
|
|
"mean_token_accuracy": 0.1691799506545067,
|
|
"num_tokens": 26722334.0,
|
|
"step": 12875
|
|
},
|
|
{
|
|
"entropy": 5.749744701385498,
|
|
"epoch": 1.1683599419448476,
|
|
"grad_norm": 6.6875,
|
|
"learning_rate": 0.00048699532464086817,
|
|
"loss": 5.457,
|
|
"mean_token_accuracy": 0.16672621816396713,
|
|
"num_tokens": 26732470.0,
|
|
"step": 12880
|
|
},
|
|
{
|
|
"entropy": 5.715337324142456,
|
|
"epoch": 1.1688134978229319,
|
|
"grad_norm": 3.015625,
|
|
"learning_rate": 0.00048698448152992865,
|
|
"loss": 5.4701,
|
|
"mean_token_accuracy": 0.16592652648687362,
|
|
"num_tokens": 26742015.0,
|
|
"step": 12885
|
|
},
|
|
{
|
|
"entropy": 5.670409774780273,
|
|
"epoch": 1.169267053701016,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.00048697363403509605,
|
|
"loss": 5.4829,
|
|
"mean_token_accuracy": 0.1605442337691784,
|
|
"num_tokens": 26753231.0,
|
|
"step": 12890
|
|
},
|
|
{
|
|
"entropy": 5.72727780342102,
|
|
"epoch": 1.1697206095791002,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004869627821565946,
|
|
"loss": 5.4782,
|
|
"mean_token_accuracy": 0.1639266714453697,
|
|
"num_tokens": 26763895.0,
|
|
"step": 12895
|
|
},
|
|
{
|
|
"entropy": 5.77225399017334,
|
|
"epoch": 1.1701741654571842,
|
|
"grad_norm": 3.640625,
|
|
"learning_rate": 0.0004869519258946489,
|
|
"loss": 5.549,
|
|
"mean_token_accuracy": 0.16188820898532869,
|
|
"num_tokens": 26774208.0,
|
|
"step": 12900
|
|
},
|
|
{
|
|
"entropy": 5.711518478393555,
|
|
"epoch": 1.1706277213352685,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.00048694106524948324,
|
|
"loss": 5.4917,
|
|
"mean_token_accuracy": 0.16647729873657227,
|
|
"num_tokens": 26785554.0,
|
|
"step": 12905
|
|
},
|
|
{
|
|
"entropy": 5.717995691299438,
|
|
"epoch": 1.1710812772133528,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.00048693020022132243,
|
|
"loss": 5.4107,
|
|
"mean_token_accuracy": 0.16847751438617706,
|
|
"num_tokens": 26795488.0,
|
|
"step": 12910
|
|
},
|
|
{
|
|
"entropy": 5.6882671356201175,
|
|
"epoch": 1.1715348330914368,
|
|
"grad_norm": 4.25,
|
|
"learning_rate": 0.000486919330810391,
|
|
"loss": 5.5398,
|
|
"mean_token_accuracy": 0.1561539202928543,
|
|
"num_tokens": 26806801.0,
|
|
"step": 12915
|
|
},
|
|
{
|
|
"entropy": 5.7337775230407715,
|
|
"epoch": 1.171988388969521,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004869084570169139,
|
|
"loss": 5.469,
|
|
"mean_token_accuracy": 0.16835110634565353,
|
|
"num_tokens": 26816869.0,
|
|
"step": 12920
|
|
},
|
|
{
|
|
"entropy": 5.666212749481201,
|
|
"epoch": 1.172441944847605,
|
|
"grad_norm": 3.390625,
|
|
"learning_rate": 0.00048689757884111585,
|
|
"loss": 5.4485,
|
|
"mean_token_accuracy": 0.16816746741533278,
|
|
"num_tokens": 26827003.0,
|
|
"step": 12925
|
|
},
|
|
{
|
|
"entropy": 5.662833213806152,
|
|
"epoch": 1.1728955007256894,
|
|
"grad_norm": 3.78125,
|
|
"learning_rate": 0.00048688669628322185,
|
|
"loss": 5.4441,
|
|
"mean_token_accuracy": 0.16363555788993836,
|
|
"num_tokens": 26837065.0,
|
|
"step": 12930
|
|
},
|
|
{
|
|
"entropy": 5.637846422195435,
|
|
"epoch": 1.1733490566037736,
|
|
"grad_norm": 3.734375,
|
|
"learning_rate": 0.000486875809343457,
|
|
"loss": 5.3754,
|
|
"mean_token_accuracy": 0.17018994092941284,
|
|
"num_tokens": 26847487.0,
|
|
"step": 12935
|
|
},
|
|
{
|
|
"entropy": 5.709881830215454,
|
|
"epoch": 1.1738026124818577,
|
|
"grad_norm": 3.15625,
|
|
"learning_rate": 0.00048686491802204645,
|
|
"loss": 5.4552,
|
|
"mean_token_accuracy": 0.1754214808344841,
|
|
"num_tokens": 26858407.0,
|
|
"step": 12940
|
|
},
|
|
{
|
|
"entropy": 5.7500287055969235,
|
|
"epoch": 1.174256168359942,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004868540223192154,
|
|
"loss": 5.4974,
|
|
"mean_token_accuracy": 0.16165805459022523,
|
|
"num_tokens": 26868469.0,
|
|
"step": 12945
|
|
},
|
|
{
|
|
"entropy": 5.729928922653198,
|
|
"epoch": 1.1747097242380262,
|
|
"grad_norm": 3.03125,
|
|
"learning_rate": 0.0004868431222351892,
|
|
"loss": 5.5219,
|
|
"mean_token_accuracy": 0.16922100633382797,
|
|
"num_tokens": 26879580.0,
|
|
"step": 12950
|
|
},
|
|
{
|
|
"entropy": 5.6656300067901615,
|
|
"epoch": 1.1751632801161103,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.00048683221777019313,
|
|
"loss": 5.4956,
|
|
"mean_token_accuracy": 0.1699163645505905,
|
|
"num_tokens": 26889513.0,
|
|
"step": 12955
|
|
},
|
|
{
|
|
"entropy": 5.729463052749634,
|
|
"epoch": 1.1756168359941945,
|
|
"grad_norm": 3.234375,
|
|
"learning_rate": 0.00048682130892445293,
|
|
"loss": 5.5785,
|
|
"mean_token_accuracy": 0.16356457024812698,
|
|
"num_tokens": 26900792.0,
|
|
"step": 12960
|
|
},
|
|
{
|
|
"entropy": 5.732970094680786,
|
|
"epoch": 1.1760703918722786,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.000486810395698194,
|
|
"loss": 5.4553,
|
|
"mean_token_accuracy": 0.168211230635643,
|
|
"num_tokens": 26911298.0,
|
|
"step": 12965
|
|
},
|
|
{
|
|
"entropy": 5.727179956436157,
|
|
"epoch": 1.1765239477503628,
|
|
"grad_norm": 2.84375,
|
|
"learning_rate": 0.00048679947809164223,
|
|
"loss": 5.5226,
|
|
"mean_token_accuracy": 0.15627816170454026,
|
|
"num_tokens": 26921545.0,
|
|
"step": 12970
|
|
},
|
|
{
|
|
"entropy": 5.756848764419556,
|
|
"epoch": 1.176977503628447,
|
|
"grad_norm": 6.21875,
|
|
"learning_rate": 0.0004867885561050232,
|
|
"loss": 5.4763,
|
|
"mean_token_accuracy": 0.17487795352935792,
|
|
"num_tokens": 26932140.0,
|
|
"step": 12975
|
|
},
|
|
{
|
|
"entropy": 5.752702522277832,
|
|
"epoch": 1.1774310595065312,
|
|
"grad_norm": 3.5,
|
|
"learning_rate": 0.0004867776297385629,
|
|
"loss": 5.5112,
|
|
"mean_token_accuracy": 0.15944356173276902,
|
|
"num_tokens": 26942634.0,
|
|
"step": 12980
|
|
},
|
|
{
|
|
"entropy": 5.683873796463013,
|
|
"epoch": 1.1778846153846154,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.00048676669899248723,
|
|
"loss": 5.4928,
|
|
"mean_token_accuracy": 0.1656934916973114,
|
|
"num_tokens": 26952758.0,
|
|
"step": 12985
|
|
},
|
|
{
|
|
"entropy": 5.664761877059936,
|
|
"epoch": 1.1783381712626997,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004867557638670222,
|
|
"loss": 5.4172,
|
|
"mean_token_accuracy": 0.1719130828976631,
|
|
"num_tokens": 26963439.0,
|
|
"step": 12990
|
|
},
|
|
{
|
|
"entropy": 5.715179967880249,
|
|
"epoch": 1.1787917271407837,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.0004867448243623941,
|
|
"loss": 5.4684,
|
|
"mean_token_accuracy": 0.16016929298639299,
|
|
"num_tokens": 26974331.0,
|
|
"step": 12995
|
|
},
|
|
{
|
|
"entropy": 5.6329480648040775,
|
|
"epoch": 1.179245283018868,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.000486733880478829,
|
|
"loss": 5.3461,
|
|
"mean_token_accuracy": 0.1673539474606514,
|
|
"num_tokens": 26983416.0,
|
|
"step": 13000
|
|
},
|
|
{
|
|
"entropy": 5.631265497207641,
|
|
"epoch": 1.179698838896952,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.00048672293221655333,
|
|
"loss": 5.4659,
|
|
"mean_token_accuracy": 0.16780232191085814,
|
|
"num_tokens": 26994176.0,
|
|
"step": 13005
|
|
},
|
|
{
|
|
"entropy": 5.68020486831665,
|
|
"epoch": 1.1801523947750363,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004867119795757935,
|
|
"loss": 5.466,
|
|
"mean_token_accuracy": 0.163288214802742,
|
|
"num_tokens": 27003295.0,
|
|
"step": 13010
|
|
},
|
|
{
|
|
"entropy": 5.685923862457275,
|
|
"epoch": 1.1806059506531206,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.000486701022556776,
|
|
"loss": 5.438,
|
|
"mean_token_accuracy": 0.164357490837574,
|
|
"num_tokens": 27014018.0,
|
|
"step": 13015
|
|
},
|
|
{
|
|
"entropy": 5.708155536651612,
|
|
"epoch": 1.1810595065312046,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004866900611597273,
|
|
"loss": 5.4541,
|
|
"mean_token_accuracy": 0.16907531172037124,
|
|
"num_tokens": 27024706.0,
|
|
"step": 13020
|
|
},
|
|
{
|
|
"entropy": 5.722987413406372,
|
|
"epoch": 1.1815130624092889,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.00048667909538487427,
|
|
"loss": 5.4631,
|
|
"mean_token_accuracy": 0.16984497308731078,
|
|
"num_tokens": 27035801.0,
|
|
"step": 13025
|
|
},
|
|
{
|
|
"entropy": 5.586116218566895,
|
|
"epoch": 1.181966618287373,
|
|
"grad_norm": 3.09375,
|
|
"learning_rate": 0.0004866681252324436,
|
|
"loss": 5.3448,
|
|
"mean_token_accuracy": 0.17099255174398423,
|
|
"num_tokens": 27046596.0,
|
|
"step": 13030
|
|
},
|
|
{
|
|
"entropy": 5.656288957595825,
|
|
"epoch": 1.1824201741654572,
|
|
"grad_norm": 3.703125,
|
|
"learning_rate": 0.00048665715070266214,
|
|
"loss": 5.4519,
|
|
"mean_token_accuracy": 0.16451231092214585,
|
|
"num_tokens": 27057057.0,
|
|
"step": 13035
|
|
},
|
|
{
|
|
"entropy": 5.616890001296997,
|
|
"epoch": 1.1828737300435415,
|
|
"grad_norm": 3.796875,
|
|
"learning_rate": 0.00048664617179575685,
|
|
"loss": 5.4178,
|
|
"mean_token_accuracy": 0.17188993394374846,
|
|
"num_tokens": 27067947.0,
|
|
"step": 13040
|
|
},
|
|
{
|
|
"entropy": 5.6808055400848385,
|
|
"epoch": 1.1833272859216255,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004866351885119548,
|
|
"loss": 5.4605,
|
|
"mean_token_accuracy": 0.16962431073188783,
|
|
"num_tokens": 27077503.0,
|
|
"step": 13045
|
|
},
|
|
{
|
|
"entropy": 5.799249505996704,
|
|
"epoch": 1.1837808417997098,
|
|
"grad_norm": 3.6875,
|
|
"learning_rate": 0.0004866242008514832,
|
|
"loss": 5.5821,
|
|
"mean_token_accuracy": 0.1642658978700638,
|
|
"num_tokens": 27088298.0,
|
|
"step": 13050
|
|
},
|
|
{
|
|
"entropy": 5.719179391860962,
|
|
"epoch": 1.1842343976777938,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.00048661320881456904,
|
|
"loss": 5.4262,
|
|
"mean_token_accuracy": 0.16438489109277726,
|
|
"num_tokens": 27097841.0,
|
|
"step": 13055
|
|
},
|
|
{
|
|
"entropy": 5.613000774383545,
|
|
"epoch": 1.184687953555878,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004866022124014399,
|
|
"loss": 5.3734,
|
|
"mean_token_accuracy": 0.1711506724357605,
|
|
"num_tokens": 27108263.0,
|
|
"step": 13060
|
|
},
|
|
{
|
|
"entropy": 5.635557460784912,
|
|
"epoch": 1.1851415094339623,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.00048659121161232313,
|
|
"loss": 5.4596,
|
|
"mean_token_accuracy": 0.16825067847967148,
|
|
"num_tokens": 27119339.0,
|
|
"step": 13065
|
|
},
|
|
{
|
|
"entropy": 5.71527853012085,
|
|
"epoch": 1.1855950653120464,
|
|
"grad_norm": 3.625,
|
|
"learning_rate": 0.0004865802064474461,
|
|
"loss": 5.503,
|
|
"mean_token_accuracy": 0.16429284811019898,
|
|
"num_tokens": 27130393.0,
|
|
"step": 13070
|
|
},
|
|
{
|
|
"entropy": 5.736957979202271,
|
|
"epoch": 1.1860486211901307,
|
|
"grad_norm": 3.21875,
|
|
"learning_rate": 0.00048656919690703653,
|
|
"loss": 5.4857,
|
|
"mean_token_accuracy": 0.1615216076374054,
|
|
"num_tokens": 27141156.0,
|
|
"step": 13075
|
|
},
|
|
{
|
|
"entropy": 5.728420877456665,
|
|
"epoch": 1.1865021770682147,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.000486558182991322,
|
|
"loss": 5.5404,
|
|
"mean_token_accuracy": 0.16249743849039078,
|
|
"num_tokens": 27151630.0,
|
|
"step": 13080
|
|
},
|
|
{
|
|
"entropy": 5.6820111751556395,
|
|
"epoch": 1.186955732946299,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004865471647005304,
|
|
"loss": 5.3836,
|
|
"mean_token_accuracy": 0.1714625298976898,
|
|
"num_tokens": 27160734.0,
|
|
"step": 13085
|
|
},
|
|
{
|
|
"entropy": 5.69131441116333,
|
|
"epoch": 1.1874092888243832,
|
|
"grad_norm": 3.125,
|
|
"learning_rate": 0.00048653614203488947,
|
|
"loss": 5.4676,
|
|
"mean_token_accuracy": 0.1670915111899376,
|
|
"num_tokens": 27171584.0,
|
|
"step": 13090
|
|
},
|
|
{
|
|
"entropy": 5.67682785987854,
|
|
"epoch": 1.1878628447024673,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.0004865251149946273,
|
|
"loss": 5.3837,
|
|
"mean_token_accuracy": 0.17403001338243484,
|
|
"num_tokens": 27180817.0,
|
|
"step": 13095
|
|
},
|
|
{
|
|
"entropy": 5.710021448135376,
|
|
"epoch": 1.1883164005805515,
|
|
"grad_norm": 5.03125,
|
|
"learning_rate": 0.00048651408357997173,
|
|
"loss": 5.464,
|
|
"mean_token_accuracy": 0.16094271391630172,
|
|
"num_tokens": 27190363.0,
|
|
"step": 13100
|
|
},
|
|
{
|
|
"entropy": 5.705183649063111,
|
|
"epoch": 1.1887699564586356,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.00048650304779115114,
|
|
"loss": 5.4421,
|
|
"mean_token_accuracy": 0.16800282150506973,
|
|
"num_tokens": 27202181.0,
|
|
"step": 13105
|
|
},
|
|
{
|
|
"entropy": 5.674891376495362,
|
|
"epoch": 1.1892235123367199,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004864920076283935,
|
|
"loss": 5.4766,
|
|
"mean_token_accuracy": 0.16456827223300935,
|
|
"num_tokens": 27212514.0,
|
|
"step": 13110
|
|
},
|
|
{
|
|
"entropy": 5.7431059837341305,
|
|
"epoch": 1.1896770682148041,
|
|
"grad_norm": 3.65625,
|
|
"learning_rate": 0.0004864809630919273,
|
|
"loss": 5.4595,
|
|
"mean_token_accuracy": 0.17190263867378236,
|
|
"num_tokens": 27223352.0,
|
|
"step": 13115
|
|
},
|
|
{
|
|
"entropy": 5.67922077178955,
|
|
"epoch": 1.1901306240928882,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004864699141819809,
|
|
"loss": 5.3893,
|
|
"mean_token_accuracy": 0.1744512438774109,
|
|
"num_tokens": 27232643.0,
|
|
"step": 13120
|
|
},
|
|
{
|
|
"entropy": 5.639497709274292,
|
|
"epoch": 1.1905841799709724,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.00048645886089878276,
|
|
"loss": 5.4553,
|
|
"mean_token_accuracy": 0.1679536834359169,
|
|
"num_tokens": 27243793.0,
|
|
"step": 13125
|
|
},
|
|
{
|
|
"entropy": 5.708324193954468,
|
|
"epoch": 1.1910377358490567,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.00048644780324256153,
|
|
"loss": 5.468,
|
|
"mean_token_accuracy": 0.16620355248451232,
|
|
"num_tokens": 27254554.0,
|
|
"step": 13130
|
|
},
|
|
{
|
|
"entropy": 5.768608570098877,
|
|
"epoch": 1.1914912917271407,
|
|
"grad_norm": 3.609375,
|
|
"learning_rate": 0.0004864367412135458,
|
|
"loss": 5.5326,
|
|
"mean_token_accuracy": 0.1597672089934349,
|
|
"num_tokens": 27265842.0,
|
|
"step": 13135
|
|
},
|
|
{
|
|
"entropy": 5.698971605300903,
|
|
"epoch": 1.191944847605225,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.00048642567481196446,
|
|
"loss": 5.5273,
|
|
"mean_token_accuracy": 0.16369922161102296,
|
|
"num_tokens": 27277617.0,
|
|
"step": 13140
|
|
},
|
|
{
|
|
"entropy": 5.659363222122193,
|
|
"epoch": 1.192398403483309,
|
|
"grad_norm": 3.125,
|
|
"learning_rate": 0.0004864146040380462,
|
|
"loss": 5.4361,
|
|
"mean_token_accuracy": 0.16867364943027496,
|
|
"num_tokens": 27287450.0,
|
|
"step": 13145
|
|
},
|
|
{
|
|
"entropy": 5.700063848495484,
|
|
"epoch": 1.1928519593613933,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004864035288920202,
|
|
"loss": 5.4493,
|
|
"mean_token_accuracy": 0.16554722785949708,
|
|
"num_tokens": 27297010.0,
|
|
"step": 13150
|
|
},
|
|
{
|
|
"entropy": 5.690625190734863,
|
|
"epoch": 1.1933055152394776,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00048639244937411516,
|
|
"loss": 5.5027,
|
|
"mean_token_accuracy": 0.16306924372911452,
|
|
"num_tokens": 27306874.0,
|
|
"step": 13155
|
|
},
|
|
{
|
|
"entropy": 5.723809242248535,
|
|
"epoch": 1.1937590711175616,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.00048638136548456045,
|
|
"loss": 5.5196,
|
|
"mean_token_accuracy": 0.16260000914335251,
|
|
"num_tokens": 27318762.0,
|
|
"step": 13160
|
|
},
|
|
{
|
|
"entropy": 5.68551197052002,
|
|
"epoch": 1.194212626995646,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.00048637027722358536,
|
|
"loss": 5.3591,
|
|
"mean_token_accuracy": 0.18111200928688048,
|
|
"num_tokens": 27327231.0,
|
|
"step": 13165
|
|
},
|
|
{
|
|
"entropy": 5.634676361083985,
|
|
"epoch": 1.1946661828737302,
|
|
"grad_norm": 3.0,
|
|
"learning_rate": 0.00048635918459141893,
|
|
"loss": 5.3991,
|
|
"mean_token_accuracy": 0.1688601478934288,
|
|
"num_tokens": 27338517.0,
|
|
"step": 13170
|
|
},
|
|
{
|
|
"entropy": 5.69713978767395,
|
|
"epoch": 1.1951197387518142,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.00048634808758829073,
|
|
"loss": 5.4889,
|
|
"mean_token_accuracy": 0.16143457740545272,
|
|
"num_tokens": 27348861.0,
|
|
"step": 13175
|
|
},
|
|
{
|
|
"entropy": 5.684321022033691,
|
|
"epoch": 1.1955732946298985,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.00048633698621443024,
|
|
"loss": 5.421,
|
|
"mean_token_accuracy": 0.1740343376994133,
|
|
"num_tokens": 27358610.0,
|
|
"step": 13180
|
|
},
|
|
{
|
|
"entropy": 5.698762035369873,
|
|
"epoch": 1.1960268505079825,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.000486325880470067,
|
|
"loss": 5.5367,
|
|
"mean_token_accuracy": 0.16109849959611894,
|
|
"num_tokens": 27369707.0,
|
|
"step": 13185
|
|
},
|
|
{
|
|
"entropy": 5.7220031261444095,
|
|
"epoch": 1.1964804063860668,
|
|
"grad_norm": 3.453125,
|
|
"learning_rate": 0.0004863147703554307,
|
|
"loss": 5.4746,
|
|
"mean_token_accuracy": 0.16537181586027144,
|
|
"num_tokens": 27381030.0,
|
|
"step": 13190
|
|
},
|
|
{
|
|
"entropy": 5.724670696258545,
|
|
"epoch": 1.196933962264151,
|
|
"grad_norm": 4.78125,
|
|
"learning_rate": 0.00048630365587075115,
|
|
"loss": 5.4817,
|
|
"mean_token_accuracy": 0.1625423923134804,
|
|
"num_tokens": 27390866.0,
|
|
"step": 13195
|
|
},
|
|
{
|
|
"entropy": 5.673598766326904,
|
|
"epoch": 1.197387518142235,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.00048629253701625816,
|
|
"loss": 5.4211,
|
|
"mean_token_accuracy": 0.17088403552770615,
|
|
"num_tokens": 27400724.0,
|
|
"step": 13200
|
|
},
|
|
{
|
|
"entropy": 5.69467978477478,
|
|
"epoch": 1.1978410740203194,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004862814137921816,
|
|
"loss": 5.4574,
|
|
"mean_token_accuracy": 0.16633116453886032,
|
|
"num_tokens": 27411212.0,
|
|
"step": 13205
|
|
},
|
|
{
|
|
"entropy": 5.7285857677459715,
|
|
"epoch": 1.1982946298984034,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.00048627028619875157,
|
|
"loss": 5.4869,
|
|
"mean_token_accuracy": 0.16490317285060882,
|
|
"num_tokens": 27421279.0,
|
|
"step": 13210
|
|
},
|
|
{
|
|
"entropy": 5.6902681350708,
|
|
"epoch": 1.1987481857764877,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.0004862591542361982,
|
|
"loss": 5.4552,
|
|
"mean_token_accuracy": 0.16912527978420258,
|
|
"num_tokens": 27432520.0,
|
|
"step": 13215
|
|
},
|
|
{
|
|
"entropy": 5.642423343658447,
|
|
"epoch": 1.199201741654572,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.0004862480179047516,
|
|
"loss": 5.3832,
|
|
"mean_token_accuracy": 0.171939218044281,
|
|
"num_tokens": 27442246.0,
|
|
"step": 13220
|
|
},
|
|
{
|
|
"entropy": 5.696604204177857,
|
|
"epoch": 1.199655297532656,
|
|
"grad_norm": 3.421875,
|
|
"learning_rate": 0.0004862368772046423,
|
|
"loss": 5.425,
|
|
"mean_token_accuracy": 0.1671583205461502,
|
|
"num_tokens": 27452134.0,
|
|
"step": 13225
|
|
},
|
|
{
|
|
"entropy": 5.6761455059051515,
|
|
"epoch": 1.2001088534107403,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.00048622573213610057,
|
|
"loss": 5.4895,
|
|
"mean_token_accuracy": 0.16351793110370635,
|
|
"num_tokens": 27462253.0,
|
|
"step": 13230
|
|
},
|
|
{
|
|
"entropy": 5.672337436676026,
|
|
"epoch": 1.2005624092888243,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00048621458269935676,
|
|
"loss": 5.4378,
|
|
"mean_token_accuracy": 0.1669228807091713,
|
|
"num_tokens": 27473131.0,
|
|
"step": 13235
|
|
},
|
|
{
|
|
"entropy": 5.711008882522583,
|
|
"epoch": 1.2010159651669086,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.00048620342889464153,
|
|
"loss": 5.4355,
|
|
"mean_token_accuracy": 0.17158128321170807,
|
|
"num_tokens": 27483683.0,
|
|
"step": 13240
|
|
},
|
|
{
|
|
"entropy": 5.626327180862427,
|
|
"epoch": 1.2014695210449928,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.00048619227072218565,
|
|
"loss": 5.428,
|
|
"mean_token_accuracy": 0.16544183790683747,
|
|
"num_tokens": 27493679.0,
|
|
"step": 13245
|
|
},
|
|
{
|
|
"entropy": 5.658449983596801,
|
|
"epoch": 1.2019230769230769,
|
|
"grad_norm": 3.5625,
|
|
"learning_rate": 0.0004861811081822198,
|
|
"loss": 5.4375,
|
|
"mean_token_accuracy": 0.1670785963535309,
|
|
"num_tokens": 27503897.0,
|
|
"step": 13250
|
|
},
|
|
{
|
|
"entropy": 5.730658340454101,
|
|
"epoch": 1.2023766328011611,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004861699412749748,
|
|
"loss": 5.513,
|
|
"mean_token_accuracy": 0.16086259633302688,
|
|
"num_tokens": 27514560.0,
|
|
"step": 13255
|
|
},
|
|
{
|
|
"entropy": 5.648807621002197,
|
|
"epoch": 1.2028301886792452,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004861587700006816,
|
|
"loss": 5.4192,
|
|
"mean_token_accuracy": 0.16771598160266876,
|
|
"num_tokens": 27525594.0,
|
|
"step": 13260
|
|
},
|
|
{
|
|
"entropy": 5.63125319480896,
|
|
"epoch": 1.2032837445573294,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.00048614759435957114,
|
|
"loss": 5.3835,
|
|
"mean_token_accuracy": 0.17013244181871415,
|
|
"num_tokens": 27535676.0,
|
|
"step": 13265
|
|
},
|
|
{
|
|
"entropy": 5.646376132965088,
|
|
"epoch": 1.2037373004354137,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004861364143518747,
|
|
"loss": 5.3826,
|
|
"mean_token_accuracy": 0.16219785511493684,
|
|
"num_tokens": 27545520.0,
|
|
"step": 13270
|
|
},
|
|
{
|
|
"entropy": 5.7230266571044925,
|
|
"epoch": 1.2041908563134978,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004861252299778234,
|
|
"loss": 5.4918,
|
|
"mean_token_accuracy": 0.15810096859931946,
|
|
"num_tokens": 27556866.0,
|
|
"step": 13275
|
|
},
|
|
{
|
|
"entropy": 5.6460377216339115,
|
|
"epoch": 1.204644412191582,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.00048611404123764855,
|
|
"loss": 5.4319,
|
|
"mean_token_accuracy": 0.1693384662270546,
|
|
"num_tokens": 27566951.0,
|
|
"step": 13280
|
|
},
|
|
{
|
|
"entropy": 5.697328329086304,
|
|
"epoch": 1.205097968069666,
|
|
"grad_norm": 3.125,
|
|
"learning_rate": 0.00048610284813158154,
|
|
"loss": 5.5221,
|
|
"mean_token_accuracy": 0.17121272832155227,
|
|
"num_tokens": 27576796.0,
|
|
"step": 13285
|
|
},
|
|
{
|
|
"entropy": 5.580730676651001,
|
|
"epoch": 1.2055515239477503,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004860916506598538,
|
|
"loss": 5.3915,
|
|
"mean_token_accuracy": 0.16058777421712875,
|
|
"num_tokens": 27586902.0,
|
|
"step": 13290
|
|
},
|
|
{
|
|
"entropy": 5.7661216259002686,
|
|
"epoch": 1.2060050798258346,
|
|
"grad_norm": 4.03125,
|
|
"learning_rate": 0.00048608044882269695,
|
|
"loss": 5.6071,
|
|
"mean_token_accuracy": 0.15429281443357468,
|
|
"num_tokens": 27599232.0,
|
|
"step": 13295
|
|
},
|
|
{
|
|
"entropy": 5.6870119094848635,
|
|
"epoch": 1.2064586357039186,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004860692426203427,
|
|
"loss": 5.3651,
|
|
"mean_token_accuracy": 0.1673690751194954,
|
|
"num_tokens": 27609022.0,
|
|
"step": 13300
|
|
},
|
|
{
|
|
"entropy": 5.702845239639283,
|
|
"epoch": 1.206912191582003,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.0004860580320530226,
|
|
"loss": 5.536,
|
|
"mean_token_accuracy": 0.16660940945148467,
|
|
"num_tokens": 27619829.0,
|
|
"step": 13305
|
|
},
|
|
{
|
|
"entropy": 5.704975271224976,
|
|
"epoch": 1.2073657474600872,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004860468171209687,
|
|
"loss": 5.5301,
|
|
"mean_token_accuracy": 0.17217028141021729,
|
|
"num_tokens": 27629337.0,
|
|
"step": 13310
|
|
},
|
|
{
|
|
"entropy": 5.729160213470459,
|
|
"epoch": 1.2078193033381712,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004860355978244128,
|
|
"loss": 5.5404,
|
|
"mean_token_accuracy": 0.16833944320678712,
|
|
"num_tokens": 27639377.0,
|
|
"step": 13315
|
|
},
|
|
{
|
|
"entropy": 5.69356255531311,
|
|
"epoch": 1.2082728592162555,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.000486024374163587,
|
|
"loss": 5.4282,
|
|
"mean_token_accuracy": 0.1654542326927185,
|
|
"num_tokens": 27649989.0,
|
|
"step": 13320
|
|
},
|
|
{
|
|
"entropy": 5.652547454833984,
|
|
"epoch": 1.2087264150943395,
|
|
"grad_norm": 3.078125,
|
|
"learning_rate": 0.00048601314613872334,
|
|
"loss": 5.5002,
|
|
"mean_token_accuracy": 0.16046180799603463,
|
|
"num_tokens": 27659967.0,
|
|
"step": 13325
|
|
},
|
|
{
|
|
"entropy": 5.705963134765625,
|
|
"epoch": 1.2091799709724238,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.000486001913750054,
|
|
"loss": 5.4529,
|
|
"mean_token_accuracy": 0.1703234940767288,
|
|
"num_tokens": 27670099.0,
|
|
"step": 13330
|
|
},
|
|
{
|
|
"entropy": 5.677967929840088,
|
|
"epoch": 1.209633526850508,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004859906769978113,
|
|
"loss": 5.4955,
|
|
"mean_token_accuracy": 0.15858108252286912,
|
|
"num_tokens": 27681497.0,
|
|
"step": 13335
|
|
},
|
|
{
|
|
"entropy": 5.713388204574585,
|
|
"epoch": 1.2100870827285921,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.00048597943588222776,
|
|
"loss": 5.6098,
|
|
"mean_token_accuracy": 0.1591266244649887,
|
|
"num_tokens": 27691828.0,
|
|
"step": 13340
|
|
},
|
|
{
|
|
"entropy": 5.713830471038818,
|
|
"epoch": 1.2105406386066764,
|
|
"grad_norm": 4.0,
|
|
"learning_rate": 0.00048596819040353564,
|
|
"loss": 5.4097,
|
|
"mean_token_accuracy": 0.17334879487752913,
|
|
"num_tokens": 27701426.0,
|
|
"step": 13345
|
|
},
|
|
{
|
|
"entropy": 5.694164991378784,
|
|
"epoch": 1.2109941944847606,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004859569405619676,
|
|
"loss": 5.4073,
|
|
"mean_token_accuracy": 0.17024950236082076,
|
|
"num_tokens": 27711112.0,
|
|
"step": 13350
|
|
},
|
|
{
|
|
"entropy": 5.680766153335571,
|
|
"epoch": 1.2114477503628447,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004859456863577562,
|
|
"loss": 5.5166,
|
|
"mean_token_accuracy": 0.16613214761018752,
|
|
"num_tokens": 27723160.0,
|
|
"step": 13355
|
|
},
|
|
{
|
|
"entropy": 5.692246294021606,
|
|
"epoch": 1.211901306240929,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.00048593442779113437,
|
|
"loss": 5.4882,
|
|
"mean_token_accuracy": 0.1640458285808563,
|
|
"num_tokens": 27733143.0,
|
|
"step": 13360
|
|
},
|
|
{
|
|
"entropy": 5.628830528259277,
|
|
"epoch": 1.212354862119013,
|
|
"grad_norm": 3.421875,
|
|
"learning_rate": 0.0004859231648623348,
|
|
"loss": 5.5029,
|
|
"mean_token_accuracy": 0.1653238669037819,
|
|
"num_tokens": 27743956.0,
|
|
"step": 13365
|
|
},
|
|
{
|
|
"entropy": 5.6937291622161865,
|
|
"epoch": 1.2128084179970973,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.00048591189757159035,
|
|
"loss": 5.4546,
|
|
"mean_token_accuracy": 0.17339136451482773,
|
|
"num_tokens": 27754192.0,
|
|
"step": 13370
|
|
},
|
|
{
|
|
"entropy": 5.688690137863159,
|
|
"epoch": 1.2132619738751815,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004859006259191342,
|
|
"loss": 5.5045,
|
|
"mean_token_accuracy": 0.1576140820980072,
|
|
"num_tokens": 27763939.0,
|
|
"step": 13375
|
|
},
|
|
{
|
|
"entropy": 5.64592866897583,
|
|
"epoch": 1.2137155297532656,
|
|
"grad_norm": 3.75,
|
|
"learning_rate": 0.0004858893499051993,
|
|
"loss": 5.4806,
|
|
"mean_token_accuracy": 0.17126801908016204,
|
|
"num_tokens": 27774743.0,
|
|
"step": 13380
|
|
},
|
|
{
|
|
"entropy": 5.660031938552857,
|
|
"epoch": 1.2141690856313498,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004858780695300189,
|
|
"loss": 5.4467,
|
|
"mean_token_accuracy": 0.16889214515686035,
|
|
"num_tokens": 27785344.0,
|
|
"step": 13385
|
|
},
|
|
{
|
|
"entropy": 5.756564664840698,
|
|
"epoch": 1.2146226415094339,
|
|
"grad_norm": 2.875,
|
|
"learning_rate": 0.0004858667847938263,
|
|
"loss": 5.5468,
|
|
"mean_token_accuracy": 0.16128505617380143,
|
|
"num_tokens": 27797101.0,
|
|
"step": 13390
|
|
},
|
|
{
|
|
"entropy": 5.684372854232788,
|
|
"epoch": 1.2150761973875182,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.00048585549569685486,
|
|
"loss": 5.3972,
|
|
"mean_token_accuracy": 0.17084303945302964,
|
|
"num_tokens": 27807581.0,
|
|
"step": 13395
|
|
},
|
|
{
|
|
"entropy": 5.625679922103882,
|
|
"epoch": 1.2155297532656024,
|
|
"grad_norm": 2.921875,
|
|
"learning_rate": 0.00048584420223933805,
|
|
"loss": 5.3978,
|
|
"mean_token_accuracy": 0.16682219207286836,
|
|
"num_tokens": 27818170.0,
|
|
"step": 13400
|
|
},
|
|
{
|
|
"entropy": 5.612948036193847,
|
|
"epoch": 1.2159833091436865,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004858329044215094,
|
|
"loss": 5.4376,
|
|
"mean_token_accuracy": 0.16606553345918657,
|
|
"num_tokens": 27828153.0,
|
|
"step": 13405
|
|
},
|
|
{
|
|
"entropy": 5.721183824539184,
|
|
"epoch": 1.2164368650217707,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.00048582160224360253,
|
|
"loss": 5.3566,
|
|
"mean_token_accuracy": 0.1773148372769356,
|
|
"num_tokens": 27837681.0,
|
|
"step": 13410
|
|
},
|
|
{
|
|
"entropy": 5.665108489990234,
|
|
"epoch": 1.2168904208998548,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004858102957058513,
|
|
"loss": 5.4804,
|
|
"mean_token_accuracy": 0.16784761995077133,
|
|
"num_tokens": 27847447.0,
|
|
"step": 13415
|
|
},
|
|
{
|
|
"entropy": 5.598166227340698,
|
|
"epoch": 1.217343976777939,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.00048579898480848933,
|
|
"loss": 5.3596,
|
|
"mean_token_accuracy": 0.16875684708356858,
|
|
"num_tokens": 27858586.0,
|
|
"step": 13420
|
|
},
|
|
{
|
|
"entropy": 5.642669057846069,
|
|
"epoch": 1.2177975326560233,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004857876695517507,
|
|
"loss": 5.4527,
|
|
"mean_token_accuracy": 0.16710106879472733,
|
|
"num_tokens": 27868832.0,
|
|
"step": 13425
|
|
},
|
|
{
|
|
"entropy": 5.694575214385987,
|
|
"epoch": 1.2182510885341074,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.00048577634993586923,
|
|
"loss": 5.4623,
|
|
"mean_token_accuracy": 0.16507479250431062,
|
|
"num_tokens": 27879339.0,
|
|
"step": 13430
|
|
},
|
|
{
|
|
"entropy": 5.737501859664917,
|
|
"epoch": 1.2187046444121916,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.00048576502596107924,
|
|
"loss": 5.4816,
|
|
"mean_token_accuracy": 0.16954989433288575,
|
|
"num_tokens": 27889964.0,
|
|
"step": 13435
|
|
},
|
|
{
|
|
"entropy": 5.726656723022461,
|
|
"epoch": 1.2191582002902757,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004857536976276148,
|
|
"loss": 5.523,
|
|
"mean_token_accuracy": 0.15809039026498795,
|
|
"num_tokens": 27901004.0,
|
|
"step": 13440
|
|
},
|
|
{
|
|
"entropy": 5.627189350128174,
|
|
"epoch": 1.21961175616836,
|
|
"grad_norm": 3.3125,
|
|
"learning_rate": 0.0004857423649357102,
|
|
"loss": 5.4371,
|
|
"mean_token_accuracy": 0.16341549754142762,
|
|
"num_tokens": 27910788.0,
|
|
"step": 13445
|
|
},
|
|
{
|
|
"entropy": 5.720109224319458,
|
|
"epoch": 1.2200653120464442,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.00048573102788559974,
|
|
"loss": 5.4706,
|
|
"mean_token_accuracy": 0.1677633300423622,
|
|
"num_tokens": 27921360.0,
|
|
"step": 13450
|
|
},
|
|
{
|
|
"entropy": 5.6626873970031735,
|
|
"epoch": 1.2205188679245282,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004857196864775179,
|
|
"loss": 5.4375,
|
|
"mean_token_accuracy": 0.17158131003379823,
|
|
"num_tokens": 27931889.0,
|
|
"step": 13455
|
|
},
|
|
{
|
|
"entropy": 5.648244857788086,
|
|
"epoch": 1.2209724238026125,
|
|
"grad_norm": 3.15625,
|
|
"learning_rate": 0.00048570834071169926,
|
|
"loss": 5.4182,
|
|
"mean_token_accuracy": 0.17155199199914933,
|
|
"num_tokens": 27942049.0,
|
|
"step": 13460
|
|
},
|
|
{
|
|
"entropy": 5.731772327423096,
|
|
"epoch": 1.2214259796806965,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.00048569699058837856,
|
|
"loss": 5.558,
|
|
"mean_token_accuracy": 0.16700346022844315,
|
|
"num_tokens": 27952416.0,
|
|
"step": 13465
|
|
},
|
|
{
|
|
"entropy": 5.637008237838745,
|
|
"epoch": 1.2218795355587808,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004856856361077903,
|
|
"loss": 5.4105,
|
|
"mean_token_accuracy": 0.1732843965291977,
|
|
"num_tokens": 27962009.0,
|
|
"step": 13470
|
|
},
|
|
{
|
|
"entropy": 5.706995868682862,
|
|
"epoch": 1.222333091436865,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004856742772701694,
|
|
"loss": 5.4751,
|
|
"mean_token_accuracy": 0.1659412771463394,
|
|
"num_tokens": 27972175.0,
|
|
"step": 13475
|
|
},
|
|
{
|
|
"entropy": 5.710698080062866,
|
|
"epoch": 1.2227866473149491,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.00048566291407575073,
|
|
"loss": 5.4882,
|
|
"mean_token_accuracy": 0.16880583316087722,
|
|
"num_tokens": 27982899.0,
|
|
"step": 13480
|
|
},
|
|
{
|
|
"entropy": 5.692344999313354,
|
|
"epoch": 1.2232402031930334,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.00048565154652476937,
|
|
"loss": 5.4262,
|
|
"mean_token_accuracy": 0.16932539641857147,
|
|
"num_tokens": 27993231.0,
|
|
"step": 13485
|
|
},
|
|
{
|
|
"entropy": 5.6381865501403805,
|
|
"epoch": 1.2236937590711174,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004856401746174603,
|
|
"loss": 5.3984,
|
|
"mean_token_accuracy": 0.16890249103307725,
|
|
"num_tokens": 28003623.0,
|
|
"step": 13490
|
|
},
|
|
{
|
|
"entropy": 5.651740169525146,
|
|
"epoch": 1.2241473149492017,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.00048562879835405874,
|
|
"loss": 5.3952,
|
|
"mean_token_accuracy": 0.16568892151117326,
|
|
"num_tokens": 28013878.0,
|
|
"step": 13495
|
|
},
|
|
{
|
|
"entropy": 5.609378528594971,
|
|
"epoch": 1.224600870827286,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004856174177348,
|
|
"loss": 5.4869,
|
|
"mean_token_accuracy": 0.16728068739175797,
|
|
"num_tokens": 28024224.0,
|
|
"step": 13500
|
|
},
|
|
{
|
|
"entropy": 5.66985673904419,
|
|
"epoch": 1.22505442670537,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004856060327599194,
|
|
"loss": 5.3941,
|
|
"mean_token_accuracy": 0.16848818510770797,
|
|
"num_tokens": 28034819.0,
|
|
"step": 13505
|
|
},
|
|
{
|
|
"entropy": 5.657116174697876,
|
|
"epoch": 1.2255079825834543,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.00048559464342965233,
|
|
"loss": 5.4562,
|
|
"mean_token_accuracy": 0.1675002470612526,
|
|
"num_tokens": 28044240.0,
|
|
"step": 13510
|
|
},
|
|
{
|
|
"entropy": 5.736130142211914,
|
|
"epoch": 1.2259615384615385,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004855832497442344,
|
|
"loss": 5.6,
|
|
"mean_token_accuracy": 0.16132477968931197,
|
|
"num_tokens": 28055046.0,
|
|
"step": 13515
|
|
},
|
|
{
|
|
"entropy": 5.672455358505249,
|
|
"epoch": 1.2264150943396226,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004855718517039012,
|
|
"loss": 5.4009,
|
|
"mean_token_accuracy": 0.16896926015615463,
|
|
"num_tokens": 28065272.0,
|
|
"step": 13520
|
|
},
|
|
{
|
|
"entropy": 5.718912792205811,
|
|
"epoch": 1.2268686502177069,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.00048556044930888844,
|
|
"loss": 5.4062,
|
|
"mean_token_accuracy": 0.17534483522176741,
|
|
"num_tokens": 28076255.0,
|
|
"step": 13525
|
|
},
|
|
{
|
|
"entropy": 5.64792652130127,
|
|
"epoch": 1.2273222060957911,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004855490425594319,
|
|
"loss": 5.5043,
|
|
"mean_token_accuracy": 0.16752651184797288,
|
|
"num_tokens": 28086258.0,
|
|
"step": 13530
|
|
},
|
|
{
|
|
"entropy": 5.660040187835693,
|
|
"epoch": 1.2277757619738752,
|
|
"grad_norm": 4.34375,
|
|
"learning_rate": 0.0004855376314557675,
|
|
"loss": 5.4328,
|
|
"mean_token_accuracy": 0.1726176083087921,
|
|
"num_tokens": 28096497.0,
|
|
"step": 13535
|
|
},
|
|
{
|
|
"entropy": 5.716834354400635,
|
|
"epoch": 1.2282293178519594,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004855262159981313,
|
|
"loss": 5.45,
|
|
"mean_token_accuracy": 0.17329759895801544,
|
|
"num_tokens": 28106282.0,
|
|
"step": 13540
|
|
},
|
|
{
|
|
"entropy": 5.622872447967529,
|
|
"epoch": 1.2286828737300435,
|
|
"grad_norm": 3.0,
|
|
"learning_rate": 0.00048551479618675925,
|
|
"loss": 5.4941,
|
|
"mean_token_accuracy": 0.16633868962526321,
|
|
"num_tokens": 28115771.0,
|
|
"step": 13545
|
|
},
|
|
{
|
|
"entropy": 5.715664005279541,
|
|
"epoch": 1.2291364296081277,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.00048550337202188756,
|
|
"loss": 5.4348,
|
|
"mean_token_accuracy": 0.1748673602938652,
|
|
"num_tokens": 28125477.0,
|
|
"step": 13550
|
|
},
|
|
{
|
|
"entropy": 5.750489902496338,
|
|
"epoch": 1.229589985486212,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004854919435037525,
|
|
"loss": 5.4514,
|
|
"mean_token_accuracy": 0.16456642895936965,
|
|
"num_tokens": 28135800.0,
|
|
"step": 13555
|
|
},
|
|
{
|
|
"entropy": 5.612999439239502,
|
|
"epoch": 1.230043541364296,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004854805106325904,
|
|
"loss": 5.351,
|
|
"mean_token_accuracy": 0.16951490491628646,
|
|
"num_tokens": 28146779.0,
|
|
"step": 13560
|
|
},
|
|
{
|
|
"entropy": 5.6327980041503904,
|
|
"epoch": 1.2304970972423803,
|
|
"grad_norm": 3.390625,
|
|
"learning_rate": 0.0004854690734086378,
|
|
"loss": 5.495,
|
|
"mean_token_accuracy": 0.16267938464879989,
|
|
"num_tokens": 28156819.0,
|
|
"step": 13565
|
|
},
|
|
{
|
|
"entropy": 5.671770763397217,
|
|
"epoch": 1.2309506531204644,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004854576318321311,
|
|
"loss": 5.4676,
|
|
"mean_token_accuracy": 0.16391557157039643,
|
|
"num_tokens": 28168553.0,
|
|
"step": 13570
|
|
},
|
|
{
|
|
"entropy": 5.705468845367432,
|
|
"epoch": 1.2314042089985486,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.00048544618590330685,
|
|
"loss": 5.4426,
|
|
"mean_token_accuracy": 0.16718784719705582,
|
|
"num_tokens": 28178064.0,
|
|
"step": 13575
|
|
},
|
|
{
|
|
"entropy": 5.738477897644043,
|
|
"epoch": 1.231857764876633,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.00048543473562240194,
|
|
"loss": 5.5894,
|
|
"mean_token_accuracy": 0.16764417737722398,
|
|
"num_tokens": 28188580.0,
|
|
"step": 13580
|
|
},
|
|
{
|
|
"entropy": 5.714741516113281,
|
|
"epoch": 1.232311320754717,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.000485423280989653,
|
|
"loss": 5.5402,
|
|
"mean_token_accuracy": 0.16061850041151046,
|
|
"num_tokens": 28199955.0,
|
|
"step": 13585
|
|
},
|
|
{
|
|
"entropy": 5.751879644393921,
|
|
"epoch": 1.2327648766328012,
|
|
"grad_norm": 6.0,
|
|
"learning_rate": 0.000485411822005297,
|
|
"loss": 5.5108,
|
|
"mean_token_accuracy": 0.16442260295152664,
|
|
"num_tokens": 28210506.0,
|
|
"step": 13590
|
|
},
|
|
{
|
|
"entropy": 5.667520761489868,
|
|
"epoch": 1.2332184325108853,
|
|
"grad_norm": 3.078125,
|
|
"learning_rate": 0.00048540035866957097,
|
|
"loss": 5.4368,
|
|
"mean_token_accuracy": 0.17275745570659637,
|
|
"num_tokens": 28220486.0,
|
|
"step": 13595
|
|
},
|
|
{
|
|
"entropy": 5.7030706882476805,
|
|
"epoch": 1.2336719883889695,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.0004853888909827118,
|
|
"loss": 5.5534,
|
|
"mean_token_accuracy": 0.15965298116207122,
|
|
"num_tokens": 28232668.0,
|
|
"step": 13600
|
|
},
|
|
{
|
|
"entropy": 5.6738749027252195,
|
|
"epoch": 1.2341255442670538,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004853774189449568,
|
|
"loss": 5.488,
|
|
"mean_token_accuracy": 0.1644887551665306,
|
|
"num_tokens": 28243733.0,
|
|
"step": 13605
|
|
},
|
|
{
|
|
"entropy": 5.77504301071167,
|
|
"epoch": 1.2345791001451378,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.00048536594255654315,
|
|
"loss": 5.5425,
|
|
"mean_token_accuracy": 0.16191980093717576,
|
|
"num_tokens": 28254953.0,
|
|
"step": 13610
|
|
},
|
|
{
|
|
"entropy": 5.70064754486084,
|
|
"epoch": 1.235032656023222,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004853544618177083,
|
|
"loss": 5.452,
|
|
"mean_token_accuracy": 0.1697838768362999,
|
|
"num_tokens": 28264959.0,
|
|
"step": 13615
|
|
},
|
|
{
|
|
"entropy": 5.739923715591431,
|
|
"epoch": 1.2354862119013061,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.00048534297672868945,
|
|
"loss": 5.457,
|
|
"mean_token_accuracy": 0.17003882080316543,
|
|
"num_tokens": 28275509.0,
|
|
"step": 13620
|
|
},
|
|
{
|
|
"entropy": 5.705825567245483,
|
|
"epoch": 1.2359397677793904,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.00048533148728972434,
|
|
"loss": 5.4076,
|
|
"mean_token_accuracy": 0.17201863676309587,
|
|
"num_tokens": 28285983.0,
|
|
"step": 13625
|
|
},
|
|
{
|
|
"entropy": 5.763514566421509,
|
|
"epoch": 1.2363933236574747,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.00048531999350105037,
|
|
"loss": 5.5094,
|
|
"mean_token_accuracy": 0.16036102026700974,
|
|
"num_tokens": 28296178.0,
|
|
"step": 13630
|
|
},
|
|
{
|
|
"entropy": 5.699604558944702,
|
|
"epoch": 1.2368468795355587,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.00048530849536290537,
|
|
"loss": 5.4943,
|
|
"mean_token_accuracy": 0.1571711540222168,
|
|
"num_tokens": 28305741.0,
|
|
"step": 13635
|
|
},
|
|
{
|
|
"entropy": 5.646511363983154,
|
|
"epoch": 1.237300435413643,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004852969928755271,
|
|
"loss": 5.4131,
|
|
"mean_token_accuracy": 0.1711614802479744,
|
|
"num_tokens": 28315607.0,
|
|
"step": 13640
|
|
},
|
|
{
|
|
"entropy": 5.645528411865234,
|
|
"epoch": 1.237753991291727,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.00048528548603915344,
|
|
"loss": 5.4422,
|
|
"mean_token_accuracy": 0.1682300165295601,
|
|
"num_tokens": 28327349.0,
|
|
"step": 13645
|
|
},
|
|
{
|
|
"entropy": 5.696292734146118,
|
|
"epoch": 1.2382075471698113,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.00048527397485402236,
|
|
"loss": 5.4425,
|
|
"mean_token_accuracy": 0.16492995172739028,
|
|
"num_tokens": 28339949.0,
|
|
"step": 13650
|
|
},
|
|
{
|
|
"entropy": 5.71319899559021,
|
|
"epoch": 1.2386611030478956,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.00048526245932037186,
|
|
"loss": 5.475,
|
|
"mean_token_accuracy": 0.16872302144765855,
|
|
"num_tokens": 28351340.0,
|
|
"step": 13655
|
|
},
|
|
{
|
|
"entropy": 5.584167909622193,
|
|
"epoch": 1.2391146589259796,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.00048525093943844013,
|
|
"loss": 5.3199,
|
|
"mean_token_accuracy": 0.17474932968616486,
|
|
"num_tokens": 28360929.0,
|
|
"step": 13660
|
|
},
|
|
{
|
|
"entropy": 5.632277774810791,
|
|
"epoch": 1.2395682148040639,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004852394152084654,
|
|
"loss": 5.4286,
|
|
"mean_token_accuracy": 0.16977956295013427,
|
|
"num_tokens": 28370477.0,
|
|
"step": 13665
|
|
},
|
|
{
|
|
"entropy": 5.640987396240234,
|
|
"epoch": 1.240021770682148,
|
|
"grad_norm": 4.5,
|
|
"learning_rate": 0.000485227886630686,
|
|
"loss": 5.3673,
|
|
"mean_token_accuracy": 0.17773811966180803,
|
|
"num_tokens": 28380876.0,
|
|
"step": 13670
|
|
},
|
|
{
|
|
"entropy": 5.59354567527771,
|
|
"epoch": 1.2404753265602322,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004852163537053403,
|
|
"loss": 5.3453,
|
|
"mean_token_accuracy": 0.16759152561426163,
|
|
"num_tokens": 28390685.0,
|
|
"step": 13675
|
|
},
|
|
{
|
|
"entropy": 5.6510436058044435,
|
|
"epoch": 1.2409288824383164,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004852048164326669,
|
|
"loss": 5.4229,
|
|
"mean_token_accuracy": 0.16464937776327132,
|
|
"num_tokens": 28400236.0,
|
|
"step": 13680
|
|
},
|
|
{
|
|
"entropy": 5.691786527633667,
|
|
"epoch": 1.2413824383164005,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004851932748129043,
|
|
"loss": 5.4734,
|
|
"mean_token_accuracy": 0.16798210591077806,
|
|
"num_tokens": 28410353.0,
|
|
"step": 13685
|
|
},
|
|
{
|
|
"entropy": 5.6685749053955075,
|
|
"epoch": 1.2418359941944848,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004851817288462912,
|
|
"loss": 5.4055,
|
|
"mean_token_accuracy": 0.16603224873542785,
|
|
"num_tokens": 28420241.0,
|
|
"step": 13690
|
|
},
|
|
{
|
|
"entropy": 5.6494224071502686,
|
|
"epoch": 1.242289550072569,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004851701785330663,
|
|
"loss": 5.4645,
|
|
"mean_token_accuracy": 0.1651461213827133,
|
|
"num_tokens": 28430610.0,
|
|
"step": 13695
|
|
},
|
|
{
|
|
"entropy": 5.638227272033691,
|
|
"epoch": 1.242743105950653,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004851586238734687,
|
|
"loss": 5.3878,
|
|
"mean_token_accuracy": 0.17127603739500047,
|
|
"num_tokens": 28440026.0,
|
|
"step": 13700
|
|
},
|
|
{
|
|
"entropy": 5.647902154922486,
|
|
"epoch": 1.2431966618287373,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004851470648677371,
|
|
"loss": 5.491,
|
|
"mean_token_accuracy": 0.1600342720746994,
|
|
"num_tokens": 28450707.0,
|
|
"step": 13705
|
|
},
|
|
{
|
|
"entropy": 5.666454792022705,
|
|
"epoch": 1.2436502177068216,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.0004851355015161107,
|
|
"loss": 5.4384,
|
|
"mean_token_accuracy": 0.16631873100996017,
|
|
"num_tokens": 28462378.0,
|
|
"step": 13710
|
|
},
|
|
{
|
|
"entropy": 5.771892929077149,
|
|
"epoch": 1.2441037735849056,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004851239338188286,
|
|
"loss": 5.5065,
|
|
"mean_token_accuracy": 0.1620028495788574,
|
|
"num_tokens": 28473084.0,
|
|
"step": 13715
|
|
},
|
|
{
|
|
"entropy": 5.696097803115845,
|
|
"epoch": 1.24455732946299,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.00048511236177612994,
|
|
"loss": 5.433,
|
|
"mean_token_accuracy": 0.1704879328608513,
|
|
"num_tokens": 28482767.0,
|
|
"step": 13720
|
|
},
|
|
{
|
|
"entropy": 5.689369153976441,
|
|
"epoch": 1.245010885341074,
|
|
"grad_norm": 3.015625,
|
|
"learning_rate": 0.00048510078538825413,
|
|
"loss": 5.4342,
|
|
"mean_token_accuracy": 0.165481898188591,
|
|
"num_tokens": 28493274.0,
|
|
"step": 13725
|
|
},
|
|
{
|
|
"entropy": 5.743248128890992,
|
|
"epoch": 1.2454644412191582,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.00048508920465544056,
|
|
"loss": 5.422,
|
|
"mean_token_accuracy": 0.1693935289978981,
|
|
"num_tokens": 28503823.0,
|
|
"step": 13730
|
|
},
|
|
{
|
|
"entropy": 5.627215433120727,
|
|
"epoch": 1.2459179970972425,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.0004850776195779286,
|
|
"loss": 5.4935,
|
|
"mean_token_accuracy": 0.16939234882593154,
|
|
"num_tokens": 28514209.0,
|
|
"step": 13735
|
|
},
|
|
{
|
|
"entropy": 5.715521001815796,
|
|
"epoch": 1.2463715529753265,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.000485066030155958,
|
|
"loss": 5.481,
|
|
"mean_token_accuracy": 0.16151022762060166,
|
|
"num_tokens": 28524665.0,
|
|
"step": 13740
|
|
},
|
|
{
|
|
"entropy": 5.683956289291382,
|
|
"epoch": 1.2468251088534108,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004850544363897684,
|
|
"loss": 5.3803,
|
|
"mean_token_accuracy": 0.17140159606933594,
|
|
"num_tokens": 28533639.0,
|
|
"step": 13745
|
|
},
|
|
{
|
|
"entropy": 5.575437307357788,
|
|
"epoch": 1.2472786647314948,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.00048504283827959947,
|
|
"loss": 5.418,
|
|
"mean_token_accuracy": 0.16962771564722062,
|
|
"num_tokens": 28544469.0,
|
|
"step": 13750
|
|
},
|
|
{
|
|
"entropy": 5.667253684997559,
|
|
"epoch": 1.2477322206095791,
|
|
"grad_norm": 3.0,
|
|
"learning_rate": 0.0004850312358256912,
|
|
"loss": 5.4069,
|
|
"mean_token_accuracy": 0.17162897884845735,
|
|
"num_tokens": 28554637.0,
|
|
"step": 13755
|
|
},
|
|
{
|
|
"entropy": 5.649656963348389,
|
|
"epoch": 1.2481857764876634,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004850196290282834,
|
|
"loss": 5.4303,
|
|
"mean_token_accuracy": 0.16922784894704818,
|
|
"num_tokens": 28564752.0,
|
|
"step": 13760
|
|
},
|
|
{
|
|
"entropy": 5.724267816543579,
|
|
"epoch": 1.2486393323657474,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.00048500801788761613,
|
|
"loss": 5.555,
|
|
"mean_token_accuracy": 0.17009359896183013,
|
|
"num_tokens": 28575007.0,
|
|
"step": 13765
|
|
},
|
|
{
|
|
"entropy": 5.7254486083984375,
|
|
"epoch": 1.2490928882438317,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004849964024039296,
|
|
"loss": 5.4448,
|
|
"mean_token_accuracy": 0.16415586471557617,
|
|
"num_tokens": 28584907.0,
|
|
"step": 13770
|
|
},
|
|
{
|
|
"entropy": 5.738451671600342,
|
|
"epoch": 1.2495464441219157,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.00048498478257746387,
|
|
"loss": 5.5117,
|
|
"mean_token_accuracy": 0.17165456414222718,
|
|
"num_tokens": 28594244.0,
|
|
"step": 13775
|
|
},
|
|
{
|
|
"entropy": 5.7049955368042,
|
|
"epoch": 1.25,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.00048497315840845934,
|
|
"loss": 5.4725,
|
|
"mean_token_accuracy": 0.16984983831644057,
|
|
"num_tokens": 28603816.0,
|
|
"step": 13780
|
|
},
|
|
{
|
|
"entropy": 5.745558977127075,
|
|
"epoch": 1.2504535558780843,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004849615298971565,
|
|
"loss": 5.5249,
|
|
"mean_token_accuracy": 0.16440579742193223,
|
|
"num_tokens": 28613067.0,
|
|
"step": 13785
|
|
},
|
|
{
|
|
"entropy": 5.70158805847168,
|
|
"epoch": 1.2509071117561683,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.00048494989704379556,
|
|
"loss": 5.4463,
|
|
"mean_token_accuracy": 0.17193411588668822,
|
|
"num_tokens": 28623752.0,
|
|
"step": 13790
|
|
},
|
|
{
|
|
"entropy": 5.646337556838989,
|
|
"epoch": 1.2513606676342526,
|
|
"grad_norm": 5.8125,
|
|
"learning_rate": 0.0004849382598486173,
|
|
"loss": 5.3974,
|
|
"mean_token_accuracy": 0.1736889585852623,
|
|
"num_tokens": 28633190.0,
|
|
"step": 13795
|
|
},
|
|
{
|
|
"entropy": 5.805173730850219,
|
|
"epoch": 1.2518142235123366,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.00048492661831186243,
|
|
"loss": 5.5229,
|
|
"mean_token_accuracy": 0.16259529292583466,
|
|
"num_tokens": 28644567.0,
|
|
"step": 13800
|
|
},
|
|
{
|
|
"entropy": 5.707221984863281,
|
|
"epoch": 1.2522677793904209,
|
|
"grad_norm": 2.984375,
|
|
"learning_rate": 0.0004849149724337715,
|
|
"loss": 5.4958,
|
|
"mean_token_accuracy": 0.16383040249347686,
|
|
"num_tokens": 28654785.0,
|
|
"step": 13805
|
|
},
|
|
{
|
|
"entropy": 5.649905395507813,
|
|
"epoch": 1.2527213352685052,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.00048490332221458543,
|
|
"loss": 5.376,
|
|
"mean_token_accuracy": 0.16477833092212676,
|
|
"num_tokens": 28665286.0,
|
|
"step": 13810
|
|
},
|
|
{
|
|
"entropy": 5.774849319458008,
|
|
"epoch": 1.2531748911465892,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004848916676545452,
|
|
"loss": 5.5079,
|
|
"mean_token_accuracy": 0.16705044806003572,
|
|
"num_tokens": 28675830.0,
|
|
"step": 13815
|
|
},
|
|
{
|
|
"entropy": 5.7492077350616455,
|
|
"epoch": 1.2536284470246735,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.00048488000875389174,
|
|
"loss": 5.5489,
|
|
"mean_token_accuracy": 0.16196076869964598,
|
|
"num_tokens": 28686640.0,
|
|
"step": 13820
|
|
},
|
|
{
|
|
"entropy": 5.691709804534912,
|
|
"epoch": 1.2540820029027575,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004848683455128663,
|
|
"loss": 5.4452,
|
|
"mean_token_accuracy": 0.17170837074518203,
|
|
"num_tokens": 28697677.0,
|
|
"step": 13825
|
|
},
|
|
{
|
|
"entropy": 5.6644867897033695,
|
|
"epoch": 1.2545355587808418,
|
|
"grad_norm": 3.78125,
|
|
"learning_rate": 0.00048485667793170994,
|
|
"loss": 5.4518,
|
|
"mean_token_accuracy": 0.16473356783390045,
|
|
"num_tokens": 28708831.0,
|
|
"step": 13830
|
|
},
|
|
{
|
|
"entropy": 5.70420732498169,
|
|
"epoch": 1.254989114658926,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.000484845006010664,
|
|
"loss": 5.4642,
|
|
"mean_token_accuracy": 0.1631591275334358,
|
|
"num_tokens": 28718959.0,
|
|
"step": 13835
|
|
},
|
|
{
|
|
"entropy": 5.717105579376221,
|
|
"epoch": 1.25544267053701,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004848333297499699,
|
|
"loss": 5.438,
|
|
"mean_token_accuracy": 0.170646832883358,
|
|
"num_tokens": 28728719.0,
|
|
"step": 13840
|
|
},
|
|
{
|
|
"entropy": 5.777034902572632,
|
|
"epoch": 1.2558962264150944,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.00048482164914986903,
|
|
"loss": 5.5707,
|
|
"mean_token_accuracy": 0.15989163964986802,
|
|
"num_tokens": 28740032.0,
|
|
"step": 13845
|
|
},
|
|
{
|
|
"entropy": 5.627986574172974,
|
|
"epoch": 1.2563497822931784,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.00048480996421060307,
|
|
"loss": 5.4239,
|
|
"mean_token_accuracy": 0.17002172470092775,
|
|
"num_tokens": 28749374.0,
|
|
"step": 13850
|
|
},
|
|
{
|
|
"entropy": 5.600414800643921,
|
|
"epoch": 1.2568033381712627,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.00048479827493241347,
|
|
"loss": 5.4318,
|
|
"mean_token_accuracy": 0.1711934044957161,
|
|
"num_tokens": 28760038.0,
|
|
"step": 13855
|
|
},
|
|
{
|
|
"entropy": 5.729163742065429,
|
|
"epoch": 1.257256894049347,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.00048478658131554216,
|
|
"loss": 5.4593,
|
|
"mean_token_accuracy": 0.16701972633600234,
|
|
"num_tokens": 28770247.0,
|
|
"step": 13860
|
|
},
|
|
{
|
|
"entropy": 5.6806481838226315,
|
|
"epoch": 1.2577104499274312,
|
|
"grad_norm": 3.828125,
|
|
"learning_rate": 0.0004847748833602308,
|
|
"loss": 5.4329,
|
|
"mean_token_accuracy": 0.1663332000374794,
|
|
"num_tokens": 28780251.0,
|
|
"step": 13865
|
|
},
|
|
{
|
|
"entropy": 5.62819128036499,
|
|
"epoch": 1.2581640058055152,
|
|
"grad_norm": 2.84375,
|
|
"learning_rate": 0.0004847631810667215,
|
|
"loss": 5.3982,
|
|
"mean_token_accuracy": 0.17300962656736374,
|
|
"num_tokens": 28790829.0,
|
|
"step": 13870
|
|
},
|
|
{
|
|
"entropy": 5.6472255229949955,
|
|
"epoch": 1.2586175616835993,
|
|
"grad_norm": 2.96875,
|
|
"learning_rate": 0.0004847514744352561,
|
|
"loss": 5.3577,
|
|
"mean_token_accuracy": 0.17472456246614457,
|
|
"num_tokens": 28801036.0,
|
|
"step": 13875
|
|
},
|
|
{
|
|
"entropy": 5.60392484664917,
|
|
"epoch": 1.2590711175616836,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004847397634660768,
|
|
"loss": 5.3905,
|
|
"mean_token_accuracy": 0.177178230881691,
|
|
"num_tokens": 28811013.0,
|
|
"step": 13880
|
|
},
|
|
{
|
|
"entropy": 5.645857810974121,
|
|
"epoch": 1.2595246734397678,
|
|
"grad_norm": 12.0,
|
|
"learning_rate": 0.00048472804815942575,
|
|
"loss": 5.389,
|
|
"mean_token_accuracy": 0.16914450824260713,
|
|
"num_tokens": 28821367.0,
|
|
"step": 13885
|
|
},
|
|
{
|
|
"entropy": 5.655232524871826,
|
|
"epoch": 1.259978229317852,
|
|
"grad_norm": 3.140625,
|
|
"learning_rate": 0.00048471632851554517,
|
|
"loss": 5.422,
|
|
"mean_token_accuracy": 0.1748315215110779,
|
|
"num_tokens": 28831077.0,
|
|
"step": 13890
|
|
},
|
|
{
|
|
"entropy": 5.681191396713257,
|
|
"epoch": 1.2604317851959361,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004847046045346775,
|
|
"loss": 5.4509,
|
|
"mean_token_accuracy": 0.1631412386894226,
|
|
"num_tokens": 28841490.0,
|
|
"step": 13895
|
|
},
|
|
{
|
|
"entropy": 5.6786730766296385,
|
|
"epoch": 1.2608853410740204,
|
|
"grad_norm": 3.703125,
|
|
"learning_rate": 0.00048469287621706516,
|
|
"loss": 5.4507,
|
|
"mean_token_accuracy": 0.1661476358771324,
|
|
"num_tokens": 28852510.0,
|
|
"step": 13900
|
|
},
|
|
{
|
|
"entropy": 5.66128249168396,
|
|
"epoch": 1.2613388969521044,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004846811435629507,
|
|
"loss": 5.435,
|
|
"mean_token_accuracy": 0.1728310152888298,
|
|
"num_tokens": 28863388.0,
|
|
"step": 13905
|
|
},
|
|
{
|
|
"entropy": 5.595666933059692,
|
|
"epoch": 1.2617924528301887,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004846694065725768,
|
|
"loss": 5.4121,
|
|
"mean_token_accuracy": 0.170094396173954,
|
|
"num_tokens": 28873798.0,
|
|
"step": 13910
|
|
},
|
|
{
|
|
"entropy": 5.709187126159668,
|
|
"epoch": 1.262246008708273,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.0004846576652461861,
|
|
"loss": 5.411,
|
|
"mean_token_accuracy": 0.16752930134534835,
|
|
"num_tokens": 28883482.0,
|
|
"step": 13915
|
|
},
|
|
{
|
|
"entropy": 5.646584939956665,
|
|
"epoch": 1.262699564586357,
|
|
"grad_norm": 3.75,
|
|
"learning_rate": 0.00048464591958402147,
|
|
"loss": 5.3907,
|
|
"mean_token_accuracy": 0.17253719717264177,
|
|
"num_tokens": 28893573.0,
|
|
"step": 13920
|
|
},
|
|
{
|
|
"entropy": 5.721584415435791,
|
|
"epoch": 1.2631531204644413,
|
|
"grad_norm": 3.0625,
|
|
"learning_rate": 0.00048463416958632573,
|
|
"loss": 5.538,
|
|
"mean_token_accuracy": 0.16560013741254806,
|
|
"num_tokens": 28904064.0,
|
|
"step": 13925
|
|
},
|
|
{
|
|
"entropy": 5.732397651672363,
|
|
"epoch": 1.2636066763425253,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.00048462241525334206,
|
|
"loss": 5.4879,
|
|
"mean_token_accuracy": 0.16327666789293288,
|
|
"num_tokens": 28915329.0,
|
|
"step": 13930
|
|
},
|
|
{
|
|
"entropy": 5.698703956604004,
|
|
"epoch": 1.2640602322206096,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004846106565853133,
|
|
"loss": 5.5412,
|
|
"mean_token_accuracy": 0.1598303884267807,
|
|
"num_tokens": 28925228.0,
|
|
"step": 13935
|
|
},
|
|
{
|
|
"entropy": 5.694935655593872,
|
|
"epoch": 1.2645137880986939,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.00048459889358248284,
|
|
"loss": 5.408,
|
|
"mean_token_accuracy": 0.16858856081962587,
|
|
"num_tokens": 28935891.0,
|
|
"step": 13940
|
|
},
|
|
{
|
|
"entropy": 5.638549947738648,
|
|
"epoch": 1.264967343976778,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.00048458712624509383,
|
|
"loss": 5.3809,
|
|
"mean_token_accuracy": 0.1695699065923691,
|
|
"num_tokens": 28946372.0,
|
|
"step": 13945
|
|
},
|
|
{
|
|
"entropy": 5.670534324645996,
|
|
"epoch": 1.2654208998548622,
|
|
"grad_norm": 3.484375,
|
|
"learning_rate": 0.00048457535457338964,
|
|
"loss": 5.4521,
|
|
"mean_token_accuracy": 0.16337735205888748,
|
|
"num_tokens": 28957874.0,
|
|
"step": 13950
|
|
},
|
|
{
|
|
"entropy": 5.690100860595703,
|
|
"epoch": 1.2658744557329462,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.0004845635785676137,
|
|
"loss": 5.4528,
|
|
"mean_token_accuracy": 0.1634893000125885,
|
|
"num_tokens": 28968023.0,
|
|
"step": 13955
|
|
},
|
|
{
|
|
"entropy": 5.670593023300171,
|
|
"epoch": 1.2663280116110305,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.00048455179822800957,
|
|
"loss": 5.3431,
|
|
"mean_token_accuracy": 0.171196049451828,
|
|
"num_tokens": 28977744.0,
|
|
"step": 13960
|
|
},
|
|
{
|
|
"entropy": 5.719510746002197,
|
|
"epoch": 1.2667815674891147,
|
|
"grad_norm": 4.3125,
|
|
"learning_rate": 0.0004845400135548208,
|
|
"loss": 5.6236,
|
|
"mean_token_accuracy": 0.160818712413311,
|
|
"num_tokens": 28988875.0,
|
|
"step": 13965
|
|
},
|
|
{
|
|
"entropy": 5.659023571014404,
|
|
"epoch": 1.2672351233671988,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004845282245482912,
|
|
"loss": 5.4007,
|
|
"mean_token_accuracy": 0.17226431965827943,
|
|
"num_tokens": 28998562.0,
|
|
"step": 13970
|
|
},
|
|
{
|
|
"entropy": 5.707257604598999,
|
|
"epoch": 1.267688679245283,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004845164312086646,
|
|
"loss": 5.4232,
|
|
"mean_token_accuracy": 0.17367802560329437,
|
|
"num_tokens": 29008783.0,
|
|
"step": 13975
|
|
},
|
|
{
|
|
"entropy": 5.577992534637451,
|
|
"epoch": 1.268142235123367,
|
|
"grad_norm": 3.453125,
|
|
"learning_rate": 0.0004845046335361847,
|
|
"loss": 5.3545,
|
|
"mean_token_accuracy": 0.17083748877048494,
|
|
"num_tokens": 29019303.0,
|
|
"step": 13980
|
|
},
|
|
{
|
|
"entropy": 5.633865594863892,
|
|
"epoch": 1.2685957910014514,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.00048449283153109566,
|
|
"loss": 5.5689,
|
|
"mean_token_accuracy": 0.16304050385951996,
|
|
"num_tokens": 29029843.0,
|
|
"step": 13985
|
|
},
|
|
{
|
|
"entropy": 5.7184789180755615,
|
|
"epoch": 1.2690493468795356,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004844810251936413,
|
|
"loss": 5.5167,
|
|
"mean_token_accuracy": 0.158305761218071,
|
|
"num_tokens": 29040603.0,
|
|
"step": 13990
|
|
},
|
|
{
|
|
"entropy": 5.675988483428955,
|
|
"epoch": 1.2695029027576197,
|
|
"grad_norm": 4.5625,
|
|
"learning_rate": 0.0004844692145240661,
|
|
"loss": 5.422,
|
|
"mean_token_accuracy": 0.170756097137928,
|
|
"num_tokens": 29050599.0,
|
|
"step": 13995
|
|
},
|
|
{
|
|
"entropy": 5.681896781921386,
|
|
"epoch": 1.269956458635704,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.0004844573995226142,
|
|
"loss": 5.4727,
|
|
"mean_token_accuracy": 0.16802088618278505,
|
|
"num_tokens": 29061292.0,
|
|
"step": 14000
|
|
},
|
|
{
|
|
"entropy": 5.637258291244507,
|
|
"epoch": 1.270410014513788,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.00048444558018952984,
|
|
"loss": 5.39,
|
|
"mean_token_accuracy": 0.17351942062377929,
|
|
"num_tokens": 29071779.0,
|
|
"step": 14005
|
|
},
|
|
{
|
|
"entropy": 5.645436143875122,
|
|
"epoch": 1.2708635703918723,
|
|
"grad_norm": 4.78125,
|
|
"learning_rate": 0.00048443375652505754,
|
|
"loss": 5.3731,
|
|
"mean_token_accuracy": 0.1697446435689926,
|
|
"num_tokens": 29082073.0,
|
|
"step": 14010
|
|
},
|
|
{
|
|
"entropy": 5.660416221618652,
|
|
"epoch": 1.2713171262699565,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004844219285294418,
|
|
"loss": 5.3663,
|
|
"mean_token_accuracy": 0.17080736607313157,
|
|
"num_tokens": 29092032.0,
|
|
"step": 14015
|
|
},
|
|
{
|
|
"entropy": 5.64392728805542,
|
|
"epoch": 1.2717706821480406,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.00048441009620292714,
|
|
"loss": 5.3993,
|
|
"mean_token_accuracy": 0.17586700171232222,
|
|
"num_tokens": 29102936.0,
|
|
"step": 14020
|
|
},
|
|
{
|
|
"entropy": 5.661731863021851,
|
|
"epoch": 1.2722242380261248,
|
|
"grad_norm": 4.59375,
|
|
"learning_rate": 0.0004843982595457584,
|
|
"loss": 5.4206,
|
|
"mean_token_accuracy": 0.17215556204319,
|
|
"num_tokens": 29113385.0,
|
|
"step": 14025
|
|
},
|
|
{
|
|
"entropy": 5.620763111114502,
|
|
"epoch": 1.2726777939042089,
|
|
"grad_norm": 2.890625,
|
|
"learning_rate": 0.00048438641855818026,
|
|
"loss": 5.4757,
|
|
"mean_token_accuracy": 0.1610592320561409,
|
|
"num_tokens": 29125075.0,
|
|
"step": 14030
|
|
},
|
|
{
|
|
"entropy": 5.7270745754241945,
|
|
"epoch": 1.2731313497822931,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004843745732404376,
|
|
"loss": 5.3931,
|
|
"mean_token_accuracy": 0.1666548952460289,
|
|
"num_tokens": 29135098.0,
|
|
"step": 14035
|
|
},
|
|
{
|
|
"entropy": 5.73830361366272,
|
|
"epoch": 1.2735849056603774,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004843627235927755,
|
|
"loss": 5.4879,
|
|
"mean_token_accuracy": 0.16855627447366714,
|
|
"num_tokens": 29145577.0,
|
|
"step": 14040
|
|
},
|
|
{
|
|
"entropy": 5.659957408905029,
|
|
"epoch": 1.2740384615384617,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.0004843508696154388,
|
|
"loss": 5.4455,
|
|
"mean_token_accuracy": 0.16806548684835435,
|
|
"num_tokens": 29155905.0,
|
|
"step": 14045
|
|
},
|
|
{
|
|
"entropy": 5.619107866287232,
|
|
"epoch": 1.2744920174165457,
|
|
"grad_norm": 3.515625,
|
|
"learning_rate": 0.00048433901130867283,
|
|
"loss": 5.3572,
|
|
"mean_token_accuracy": 0.1729203999042511,
|
|
"num_tokens": 29164926.0,
|
|
"step": 14050
|
|
},
|
|
{
|
|
"entropy": 5.632939386367798,
|
|
"epoch": 1.2749455732946298,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004843271486727228,
|
|
"loss": 5.4027,
|
|
"mean_token_accuracy": 0.16958474814891816,
|
|
"num_tokens": 29175050.0,
|
|
"step": 14055
|
|
},
|
|
{
|
|
"entropy": 5.630424976348877,
|
|
"epoch": 1.275399129172714,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.00048431528170783395,
|
|
"loss": 5.466,
|
|
"mean_token_accuracy": 0.16685863584280014,
|
|
"num_tokens": 29186255.0,
|
|
"step": 14060
|
|
},
|
|
{
|
|
"entropy": 5.691948461532593,
|
|
"epoch": 1.2758526850507983,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004843034104142517,
|
|
"loss": 5.4341,
|
|
"mean_token_accuracy": 0.17712722718715668,
|
|
"num_tokens": 29195639.0,
|
|
"step": 14065
|
|
},
|
|
{
|
|
"entropy": 5.757039737701416,
|
|
"epoch": 1.2763062409288826,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004842915347922216,
|
|
"loss": 5.4675,
|
|
"mean_token_accuracy": 0.16244897097349167,
|
|
"num_tokens": 29206482.0,
|
|
"step": 14070
|
|
},
|
|
{
|
|
"entropy": 5.695897197723388,
|
|
"epoch": 1.2767597968069666,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004842796548419893,
|
|
"loss": 5.4462,
|
|
"mean_token_accuracy": 0.16596107482910155,
|
|
"num_tokens": 29217433.0,
|
|
"step": 14075
|
|
},
|
|
{
|
|
"entropy": 5.691596031188965,
|
|
"epoch": 1.2772133526850509,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.00048426777056380035,
|
|
"loss": 5.4887,
|
|
"mean_token_accuracy": 0.16159137189388276,
|
|
"num_tokens": 29226193.0,
|
|
"step": 14080
|
|
},
|
|
{
|
|
"entropy": 5.616465997695923,
|
|
"epoch": 1.277666908563135,
|
|
"grad_norm": 3.265625,
|
|
"learning_rate": 0.0004842558819579006,
|
|
"loss": 5.4502,
|
|
"mean_token_accuracy": 0.16858242601156234,
|
|
"num_tokens": 29237061.0,
|
|
"step": 14085
|
|
},
|
|
{
|
|
"entropy": 5.631988286972046,
|
|
"epoch": 1.2781204644412192,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.0004842439890245358,
|
|
"loss": 5.4095,
|
|
"mean_token_accuracy": 0.1701940432190895,
|
|
"num_tokens": 29247689.0,
|
|
"step": 14090
|
|
},
|
|
{
|
|
"entropy": 5.666023206710816,
|
|
"epoch": 1.2785740203193035,
|
|
"grad_norm": 3.3125,
|
|
"learning_rate": 0.00048423209176395204,
|
|
"loss": 5.3787,
|
|
"mean_token_accuracy": 0.1690239429473877,
|
|
"num_tokens": 29258235.0,
|
|
"step": 14095
|
|
},
|
|
{
|
|
"entropy": 5.660300016403198,
|
|
"epoch": 1.2790275761973875,
|
|
"grad_norm": 2.921875,
|
|
"learning_rate": 0.0004842201901763954,
|
|
"loss": 5.3911,
|
|
"mean_token_accuracy": 0.16932945996522902,
|
|
"num_tokens": 29268884.0,
|
|
"step": 14100
|
|
},
|
|
{
|
|
"entropy": 5.6654359817504885,
|
|
"epoch": 1.2794811320754718,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004842082842621118,
|
|
"loss": 5.5271,
|
|
"mean_token_accuracy": 0.16088276356458664,
|
|
"num_tokens": 29280484.0,
|
|
"step": 14105
|
|
},
|
|
{
|
|
"entropy": 5.687781238555909,
|
|
"epoch": 1.2799346879535558,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004841963740213476,
|
|
"loss": 5.4882,
|
|
"mean_token_accuracy": 0.1668796196579933,
|
|
"num_tokens": 29291199.0,
|
|
"step": 14110
|
|
},
|
|
{
|
|
"entropy": 5.75243034362793,
|
|
"epoch": 1.28038824383164,
|
|
"grad_norm": 3.578125,
|
|
"learning_rate": 0.0004841844594543491,
|
|
"loss": 5.4404,
|
|
"mean_token_accuracy": 0.168342025578022,
|
|
"num_tokens": 29302007.0,
|
|
"step": 14115
|
|
},
|
|
{
|
|
"entropy": 5.688542079925537,
|
|
"epoch": 1.2808417997097243,
|
|
"grad_norm": 3.34375,
|
|
"learning_rate": 0.0004841725405613626,
|
|
"loss": 5.4266,
|
|
"mean_token_accuracy": 0.17462775558233262,
|
|
"num_tokens": 29312127.0,
|
|
"step": 14120
|
|
},
|
|
{
|
|
"entropy": 5.697545385360717,
|
|
"epoch": 1.2812953555878084,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004841606173426347,
|
|
"loss": 5.5401,
|
|
"mean_token_accuracy": 0.1659781739115715,
|
|
"num_tokens": 29323691.0,
|
|
"step": 14125
|
|
},
|
|
{
|
|
"entropy": 5.653088617324829,
|
|
"epoch": 1.2817489114658926,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.00048414868979841197,
|
|
"loss": 5.4525,
|
|
"mean_token_accuracy": 0.1659421518445015,
|
|
"num_tokens": 29335203.0,
|
|
"step": 14130
|
|
},
|
|
{
|
|
"entropy": 5.773173046112061,
|
|
"epoch": 1.2822024673439767,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.00048413675792894105,
|
|
"loss": 5.4924,
|
|
"mean_token_accuracy": 0.1678732842206955,
|
|
"num_tokens": 29346422.0,
|
|
"step": 14135
|
|
},
|
|
{
|
|
"entropy": 5.686990690231323,
|
|
"epoch": 1.282656023222061,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004841248217344686,
|
|
"loss": 5.4051,
|
|
"mean_token_accuracy": 0.16861994415521622,
|
|
"num_tokens": 29356084.0,
|
|
"step": 14140
|
|
},
|
|
{
|
|
"entropy": 5.615359210968018,
|
|
"epoch": 1.2831095791001452,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004841128812152415,
|
|
"loss": 5.4104,
|
|
"mean_token_accuracy": 0.16842042058706283,
|
|
"num_tokens": 29366093.0,
|
|
"step": 14145
|
|
},
|
|
{
|
|
"entropy": 5.690057277679443,
|
|
"epoch": 1.2835631349782293,
|
|
"grad_norm": 4.46875,
|
|
"learning_rate": 0.0004841009363715068,
|
|
"loss": 5.4787,
|
|
"mean_token_accuracy": 0.15991912186145782,
|
|
"num_tokens": 29376621.0,
|
|
"step": 14150
|
|
},
|
|
{
|
|
"entropy": 5.717804431915283,
|
|
"epoch": 1.2840166908563135,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004840889872035115,
|
|
"loss": 5.5191,
|
|
"mean_token_accuracy": 0.16535184979438783,
|
|
"num_tokens": 29387119.0,
|
|
"step": 14155
|
|
},
|
|
{
|
|
"entropy": 5.680791425704956,
|
|
"epoch": 1.2844702467343976,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004840770337115026,
|
|
"loss": 5.4316,
|
|
"mean_token_accuracy": 0.17243173867464065,
|
|
"num_tokens": 29396981.0,
|
|
"step": 14160
|
|
},
|
|
{
|
|
"entropy": 5.68158712387085,
|
|
"epoch": 1.2849238026124818,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.00048406507589572747,
|
|
"loss": 5.4118,
|
|
"mean_token_accuracy": 0.1733437567949295,
|
|
"num_tokens": 29406737.0,
|
|
"step": 14165
|
|
},
|
|
{
|
|
"entropy": 5.659775114059448,
|
|
"epoch": 1.2853773584905661,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004840531137564331,
|
|
"loss": 5.4439,
|
|
"mean_token_accuracy": 0.16904757171869278,
|
|
"num_tokens": 29417300.0,
|
|
"step": 14170
|
|
},
|
|
{
|
|
"entropy": 5.69018521308899,
|
|
"epoch": 1.2858309143686502,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004840411472938672,
|
|
"loss": 5.3396,
|
|
"mean_token_accuracy": 0.1760461613535881,
|
|
"num_tokens": 29426749.0,
|
|
"step": 14175
|
|
},
|
|
{
|
|
"entropy": 5.598387336730957,
|
|
"epoch": 1.2862844702467344,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004840291765082771,
|
|
"loss": 5.3745,
|
|
"mean_token_accuracy": 0.16847390234470366,
|
|
"num_tokens": 29437264.0,
|
|
"step": 14180
|
|
},
|
|
{
|
|
"entropy": 5.59941349029541,
|
|
"epoch": 1.2867380261248185,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.00048401720139991036,
|
|
"loss": 5.3956,
|
|
"mean_token_accuracy": 0.16394897997379304,
|
|
"num_tokens": 29448192.0,
|
|
"step": 14185
|
|
},
|
|
{
|
|
"entropy": 5.663647651672363,
|
|
"epoch": 1.2871915820029027,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004840052219690146,
|
|
"loss": 5.3011,
|
|
"mean_token_accuracy": 0.1785078763961792,
|
|
"num_tokens": 29457923.0,
|
|
"step": 14190
|
|
},
|
|
{
|
|
"entropy": 5.578242063522339,
|
|
"epoch": 1.287645137880987,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004839932382158376,
|
|
"loss": 5.3657,
|
|
"mean_token_accuracy": 0.17978979051113128,
|
|
"num_tokens": 29466914.0,
|
|
"step": 14195
|
|
},
|
|
{
|
|
"entropy": 5.597816419601441,
|
|
"epoch": 1.288098693759071,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004839812501406272,
|
|
"loss": 5.4715,
|
|
"mean_token_accuracy": 0.1600590318441391,
|
|
"num_tokens": 29477648.0,
|
|
"step": 14200
|
|
},
|
|
{
|
|
"entropy": 5.714437675476074,
|
|
"epoch": 1.2885522496371553,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004839692577436313,
|
|
"loss": 5.4413,
|
|
"mean_token_accuracy": 0.172724886238575,
|
|
"num_tokens": 29487947.0,
|
|
"step": 14205
|
|
},
|
|
{
|
|
"entropy": 5.784171295166016,
|
|
"epoch": 1.2890058055152394,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004839572610250978,
|
|
"loss": 5.534,
|
|
"mean_token_accuracy": 0.16086170673370362,
|
|
"num_tokens": 29497667.0,
|
|
"step": 14210
|
|
},
|
|
{
|
|
"entropy": 5.640085506439209,
|
|
"epoch": 1.2894593613933236,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.00048394525998527496,
|
|
"loss": 5.4087,
|
|
"mean_token_accuracy": 0.16141595393419267,
|
|
"num_tokens": 29507065.0,
|
|
"step": 14215
|
|
},
|
|
{
|
|
"entropy": 5.693887519836426,
|
|
"epoch": 1.2899129172714079,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004839332546244109,
|
|
"loss": 5.5354,
|
|
"mean_token_accuracy": 0.16008612215518953,
|
|
"num_tokens": 29517752.0,
|
|
"step": 14220
|
|
},
|
|
{
|
|
"entropy": 5.728807544708252,
|
|
"epoch": 1.2903664731494922,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.00048392124494275385,
|
|
"loss": 5.4256,
|
|
"mean_token_accuracy": 0.16439801156520845,
|
|
"num_tokens": 29527894.0,
|
|
"step": 14225
|
|
},
|
|
{
|
|
"entropy": 5.670609378814698,
|
|
"epoch": 1.2908200290275762,
|
|
"grad_norm": 3.609375,
|
|
"learning_rate": 0.0004839092309405523,
|
|
"loss": 5.4702,
|
|
"mean_token_accuracy": 0.16752054244279863,
|
|
"num_tokens": 29538136.0,
|
|
"step": 14230
|
|
},
|
|
{
|
|
"entropy": 5.669034099578857,
|
|
"epoch": 1.2912735849056602,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.00048389721261805457,
|
|
"loss": 5.429,
|
|
"mean_token_accuracy": 0.1679697647690773,
|
|
"num_tokens": 29549193.0,
|
|
"step": 14235
|
|
},
|
|
{
|
|
"entropy": 5.607318353652954,
|
|
"epoch": 1.2917271407837445,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.00048388518997550926,
|
|
"loss": 5.3272,
|
|
"mean_token_accuracy": 0.17729277014732361,
|
|
"num_tokens": 29558889.0,
|
|
"step": 14240
|
|
},
|
|
{
|
|
"entropy": 5.657179737091065,
|
|
"epoch": 1.2921806966618288,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.00048387316301316493,
|
|
"loss": 5.452,
|
|
"mean_token_accuracy": 0.16469668745994567,
|
|
"num_tokens": 29569691.0,
|
|
"step": 14245
|
|
},
|
|
{
|
|
"entropy": 5.701911354064942,
|
|
"epoch": 1.292634252539913,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004838611317312705,
|
|
"loss": 5.4999,
|
|
"mean_token_accuracy": 0.16484348326921464,
|
|
"num_tokens": 29580459.0,
|
|
"step": 14250
|
|
},
|
|
{
|
|
"entropy": 5.699386692047119,
|
|
"epoch": 1.293087808417997,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004838490961300745,
|
|
"loss": 5.4522,
|
|
"mean_token_accuracy": 0.16723748594522475,
|
|
"num_tokens": 29590652.0,
|
|
"step": 14255
|
|
},
|
|
{
|
|
"entropy": 5.667637777328491,
|
|
"epoch": 1.2935413642960814,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.00048383705620982606,
|
|
"loss": 5.4442,
|
|
"mean_token_accuracy": 0.17683394402265548,
|
|
"num_tokens": 29600353.0,
|
|
"step": 14260
|
|
},
|
|
{
|
|
"entropy": 5.675521039962769,
|
|
"epoch": 1.2939949201741654,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.00048382501197077405,
|
|
"loss": 5.4188,
|
|
"mean_token_accuracy": 0.17441921234130858,
|
|
"num_tokens": 29610561.0,
|
|
"step": 14265
|
|
},
|
|
{
|
|
"entropy": 5.611335754394531,
|
|
"epoch": 1.2944484760522497,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004838129634131675,
|
|
"loss": 5.4309,
|
|
"mean_token_accuracy": 0.1699035048484802,
|
|
"num_tokens": 29621741.0,
|
|
"step": 14270
|
|
},
|
|
{
|
|
"entropy": 5.639781475067139,
|
|
"epoch": 1.294902031930334,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004838009105372558,
|
|
"loss": 5.367,
|
|
"mean_token_accuracy": 0.16665788292884826,
|
|
"num_tokens": 29633097.0,
|
|
"step": 14275
|
|
},
|
|
{
|
|
"entropy": 5.6843993186950685,
|
|
"epoch": 1.295355587808418,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.00048378885334328793,
|
|
"loss": 5.4698,
|
|
"mean_token_accuracy": 0.1561775416135788,
|
|
"num_tokens": 29644290.0,
|
|
"step": 14280
|
|
},
|
|
{
|
|
"entropy": 5.789220809936523,
|
|
"epoch": 1.2958091436865022,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.0004837767918315135,
|
|
"loss": 5.517,
|
|
"mean_token_accuracy": 0.16151989251375198,
|
|
"num_tokens": 29654977.0,
|
|
"step": 14285
|
|
},
|
|
{
|
|
"entropy": 5.728539657592774,
|
|
"epoch": 1.2962626995645863,
|
|
"grad_norm": 3.40625,
|
|
"learning_rate": 0.00048376472600218174,
|
|
"loss": 5.4901,
|
|
"mean_token_accuracy": 0.16670093983411788,
|
|
"num_tokens": 29665020.0,
|
|
"step": 14290
|
|
},
|
|
{
|
|
"entropy": 5.633534049987793,
|
|
"epoch": 1.2967162554426706,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004837526558555422,
|
|
"loss": 5.4682,
|
|
"mean_token_accuracy": 0.16938306093215943,
|
|
"num_tokens": 29675098.0,
|
|
"step": 14295
|
|
},
|
|
{
|
|
"entropy": 5.6732477188110355,
|
|
"epoch": 1.2971698113207548,
|
|
"grad_norm": 2.953125,
|
|
"learning_rate": 0.0004837405813918446,
|
|
"loss": 5.3978,
|
|
"mean_token_accuracy": 0.173392952978611,
|
|
"num_tokens": 29685450.0,
|
|
"step": 14300
|
|
},
|
|
{
|
|
"entropy": 5.694787979125977,
|
|
"epoch": 1.2976233671988389,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.00048372850261133856,
|
|
"loss": 5.3976,
|
|
"mean_token_accuracy": 0.16944468766450882,
|
|
"num_tokens": 29694818.0,
|
|
"step": 14305
|
|
},
|
|
{
|
|
"entropy": 5.700145149230957,
|
|
"epoch": 1.2980769230769231,
|
|
"grad_norm": 4.71875,
|
|
"learning_rate": 0.00048371641951427393,
|
|
"loss": 5.4855,
|
|
"mean_token_accuracy": 0.16497548520565034,
|
|
"num_tokens": 29705573.0,
|
|
"step": 14310
|
|
},
|
|
{
|
|
"entropy": 5.644560670852661,
|
|
"epoch": 1.2985304789550072,
|
|
"grad_norm": 3.15625,
|
|
"learning_rate": 0.00048370433210090055,
|
|
"loss": 5.4139,
|
|
"mean_token_accuracy": 0.16326866894960404,
|
|
"num_tokens": 29716366.0,
|
|
"step": 14315
|
|
},
|
|
{
|
|
"entropy": 5.6263148307800295,
|
|
"epoch": 1.2989840348330914,
|
|
"grad_norm": 4.84375,
|
|
"learning_rate": 0.0004836922403714683,
|
|
"loss": 5.4274,
|
|
"mean_token_accuracy": 0.16740379929542543,
|
|
"num_tokens": 29727181.0,
|
|
"step": 14320
|
|
},
|
|
{
|
|
"entropy": 5.673771762847901,
|
|
"epoch": 1.2994375907111757,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00048368014432622746,
|
|
"loss": 5.4176,
|
|
"mean_token_accuracy": 0.17463201731443406,
|
|
"num_tokens": 29736960.0,
|
|
"step": 14325
|
|
},
|
|
{
|
|
"entropy": 5.643455505371094,
|
|
"epoch": 1.2998911465892597,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.000483668043965428,
|
|
"loss": 5.3373,
|
|
"mean_token_accuracy": 0.1795383021235466,
|
|
"num_tokens": 29746354.0,
|
|
"step": 14330
|
|
},
|
|
{
|
|
"entropy": 5.607268238067627,
|
|
"epoch": 1.300344702467344,
|
|
"grad_norm": 6.28125,
|
|
"learning_rate": 0.0004836559392893203,
|
|
"loss": 5.4435,
|
|
"mean_token_accuracy": 0.16780341267585755,
|
|
"num_tokens": 29756627.0,
|
|
"step": 14335
|
|
},
|
|
{
|
|
"entropy": 5.673342084884643,
|
|
"epoch": 1.300798258345428,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004836438302981545,
|
|
"loss": 5.4227,
|
|
"mean_token_accuracy": 0.17357626110315322,
|
|
"num_tokens": 29766684.0,
|
|
"step": 14340
|
|
},
|
|
{
|
|
"entropy": 5.6772393703460695,
|
|
"epoch": 1.3012518142235123,
|
|
"grad_norm": 3.21875,
|
|
"learning_rate": 0.0004836317169921811,
|
|
"loss": 5.4584,
|
|
"mean_token_accuracy": 0.1684758260846138,
|
|
"num_tokens": 29776556.0,
|
|
"step": 14345
|
|
},
|
|
{
|
|
"entropy": 5.759073877334595,
|
|
"epoch": 1.3017053701015966,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.00048361959937165075,
|
|
"loss": 5.5544,
|
|
"mean_token_accuracy": 0.16648434102535248,
|
|
"num_tokens": 29786896.0,
|
|
"step": 14350
|
|
},
|
|
{
|
|
"entropy": 5.671124219894409,
|
|
"epoch": 1.3021589259796806,
|
|
"grad_norm": 4.6875,
|
|
"learning_rate": 0.0004836074774368138,
|
|
"loss": 5.374,
|
|
"mean_token_accuracy": 0.17254958748817445,
|
|
"num_tokens": 29797332.0,
|
|
"step": 14355
|
|
},
|
|
{
|
|
"entropy": 5.666433954238892,
|
|
"epoch": 1.302612481857765,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.00048359535118792116,
|
|
"loss": 5.4635,
|
|
"mean_token_accuracy": 0.16886902153491973,
|
|
"num_tokens": 29806428.0,
|
|
"step": 14360
|
|
},
|
|
{
|
|
"entropy": 5.6294313907623295,
|
|
"epoch": 1.303066037735849,
|
|
"grad_norm": 3.359375,
|
|
"learning_rate": 0.0004835832206252235,
|
|
"loss": 5.4311,
|
|
"mean_token_accuracy": 0.16715630143880844,
|
|
"num_tokens": 29816794.0,
|
|
"step": 14365
|
|
},
|
|
{
|
|
"entropy": 5.720850610733033,
|
|
"epoch": 1.3035195936139332,
|
|
"grad_norm": 2.921875,
|
|
"learning_rate": 0.0004835710857489716,
|
|
"loss": 5.4739,
|
|
"mean_token_accuracy": 0.1732134461402893,
|
|
"num_tokens": 29827077.0,
|
|
"step": 14370
|
|
},
|
|
{
|
|
"entropy": 5.6719818115234375,
|
|
"epoch": 1.3039731494920175,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004835589465594165,
|
|
"loss": 5.4288,
|
|
"mean_token_accuracy": 0.17095793187618255,
|
|
"num_tokens": 29837868.0,
|
|
"step": 14375
|
|
},
|
|
{
|
|
"entropy": 5.707431840896606,
|
|
"epoch": 1.3044267053701015,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.00048354680305680926,
|
|
"loss": 5.4718,
|
|
"mean_token_accuracy": 0.1704709455370903,
|
|
"num_tokens": 29846929.0,
|
|
"step": 14380
|
|
},
|
|
{
|
|
"entropy": 5.627755880355835,
|
|
"epoch": 1.3048802612481858,
|
|
"grad_norm": 3.15625,
|
|
"learning_rate": 0.00048353465524140105,
|
|
"loss": 5.3963,
|
|
"mean_token_accuracy": 0.16750642359256745,
|
|
"num_tokens": 29857905.0,
|
|
"step": 14385
|
|
},
|
|
{
|
|
"entropy": 5.684084701538086,
|
|
"epoch": 1.3053338171262698,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.000483522503113443,
|
|
"loss": 5.4595,
|
|
"mean_token_accuracy": 0.16680840402841568,
|
|
"num_tokens": 29868230.0,
|
|
"step": 14390
|
|
},
|
|
{
|
|
"entropy": 5.689841461181641,
|
|
"epoch": 1.305787373004354,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.00048351034667318634,
|
|
"loss": 5.4039,
|
|
"mean_token_accuracy": 0.16890274435281755,
|
|
"num_tokens": 29879224.0,
|
|
"step": 14395
|
|
},
|
|
{
|
|
"entropy": 5.704214286804199,
|
|
"epoch": 1.3062409288824384,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004834981859208827,
|
|
"loss": 5.5481,
|
|
"mean_token_accuracy": 0.16577224880456926,
|
|
"num_tokens": 29890416.0,
|
|
"step": 14400
|
|
},
|
|
{
|
|
"entropy": 5.681263542175293,
|
|
"epoch": 1.3066944847605226,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.00048348602085678346,
|
|
"loss": 5.4895,
|
|
"mean_token_accuracy": 0.16298967599868774,
|
|
"num_tokens": 29901064.0,
|
|
"step": 14405
|
|
},
|
|
{
|
|
"entropy": 5.764485692977905,
|
|
"epoch": 1.3071480406386067,
|
|
"grad_norm": 3.34375,
|
|
"learning_rate": 0.00048347385148114004,
|
|
"loss": 5.5191,
|
|
"mean_token_accuracy": 0.17046493887901307,
|
|
"num_tokens": 29911084.0,
|
|
"step": 14410
|
|
},
|
|
{
|
|
"entropy": 5.59453444480896,
|
|
"epoch": 1.3076015965166907,
|
|
"grad_norm": 3.28125,
|
|
"learning_rate": 0.00048346167779420436,
|
|
"loss": 5.3641,
|
|
"mean_token_accuracy": 0.17378372251987456,
|
|
"num_tokens": 29921104.0,
|
|
"step": 14415
|
|
},
|
|
{
|
|
"entropy": 5.6693824291229244,
|
|
"epoch": 1.308055152394775,
|
|
"grad_norm": 3.25,
|
|
"learning_rate": 0.00048344949979622806,
|
|
"loss": 5.4291,
|
|
"mean_token_accuracy": 0.17077409476041794,
|
|
"num_tokens": 29932014.0,
|
|
"step": 14420
|
|
},
|
|
{
|
|
"entropy": 5.638308668136597,
|
|
"epoch": 1.3085087082728593,
|
|
"grad_norm": 5.03125,
|
|
"learning_rate": 0.00048343731748746294,
|
|
"loss": 5.4269,
|
|
"mean_token_accuracy": 0.17219559997320175,
|
|
"num_tokens": 29941707.0,
|
|
"step": 14425
|
|
},
|
|
{
|
|
"entropy": 5.630267810821533,
|
|
"epoch": 1.3089622641509435,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.000483425130868161,
|
|
"loss": 5.4211,
|
|
"mean_token_accuracy": 0.16948040425777436,
|
|
"num_tokens": 29952082.0,
|
|
"step": 14430
|
|
},
|
|
{
|
|
"entropy": 5.617520713806153,
|
|
"epoch": 1.3094158200290276,
|
|
"grad_norm": 2.875,
|
|
"learning_rate": 0.0004834129399385742,
|
|
"loss": 5.281,
|
|
"mean_token_accuracy": 0.18956174254417418,
|
|
"num_tokens": 29961744.0,
|
|
"step": 14435
|
|
},
|
|
{
|
|
"entropy": 5.677798843383789,
|
|
"epoch": 1.3098693759071118,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004834007446989548,
|
|
"loss": 5.4249,
|
|
"mean_token_accuracy": 0.17415703535079957,
|
|
"num_tokens": 29972611.0,
|
|
"step": 14440
|
|
},
|
|
{
|
|
"entropy": 5.627491283416748,
|
|
"epoch": 1.3103229317851959,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.00048338854514955474,
|
|
"loss": 5.3507,
|
|
"mean_token_accuracy": 0.17409025728702546,
|
|
"num_tokens": 29982660.0,
|
|
"step": 14445
|
|
},
|
|
{
|
|
"entropy": 5.649427461624145,
|
|
"epoch": 1.3107764876632801,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.00048337634129062655,
|
|
"loss": 5.4365,
|
|
"mean_token_accuracy": 0.1583799049258232,
|
|
"num_tokens": 29993349.0,
|
|
"step": 14450
|
|
},
|
|
{
|
|
"entropy": 5.7475364208221436,
|
|
"epoch": 1.3112300435413644,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00048336413312242255,
|
|
"loss": 5.5379,
|
|
"mean_token_accuracy": 0.1634845957159996,
|
|
"num_tokens": 30004474.0,
|
|
"step": 14455
|
|
},
|
|
{
|
|
"entropy": 5.75244107246399,
|
|
"epoch": 1.3116835994194485,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.00048335192064519514,
|
|
"loss": 5.5137,
|
|
"mean_token_accuracy": 0.1663166403770447,
|
|
"num_tokens": 30015189.0,
|
|
"step": 14460
|
|
},
|
|
{
|
|
"entropy": 5.694970703125,
|
|
"epoch": 1.3121371552975327,
|
|
"grad_norm": 3.6875,
|
|
"learning_rate": 0.00048333970385919695,
|
|
"loss": 5.4123,
|
|
"mean_token_accuracy": 0.16820802241563798,
|
|
"num_tokens": 30025491.0,
|
|
"step": 14465
|
|
},
|
|
{
|
|
"entropy": 5.650426244735717,
|
|
"epoch": 1.3125907111756168,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.00048332748276468053,
|
|
"loss": 5.4227,
|
|
"mean_token_accuracy": 0.17188505381345748,
|
|
"num_tokens": 30034683.0,
|
|
"step": 14470
|
|
},
|
|
{
|
|
"entropy": 5.653153038024902,
|
|
"epoch": 1.313044267053701,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004833152573618987,
|
|
"loss": 5.4132,
|
|
"mean_token_accuracy": 0.1698354497551918,
|
|
"num_tokens": 30044135.0,
|
|
"step": 14475
|
|
},
|
|
{
|
|
"entropy": 5.7156288623809814,
|
|
"epoch": 1.3134978229317853,
|
|
"grad_norm": 3.15625,
|
|
"learning_rate": 0.00048330302765110436,
|
|
"loss": 5.5048,
|
|
"mean_token_accuracy": 0.17033421993255615,
|
|
"num_tokens": 30054520.0,
|
|
"step": 14480
|
|
},
|
|
{
|
|
"entropy": 5.677278804779053,
|
|
"epoch": 1.3139513788098693,
|
|
"grad_norm": 3.5,
|
|
"learning_rate": 0.00048329079363255024,
|
|
"loss": 5.5102,
|
|
"mean_token_accuracy": 0.1647307887673378,
|
|
"num_tokens": 30065439.0,
|
|
"step": 14485
|
|
},
|
|
{
|
|
"entropy": 5.693774747848511,
|
|
"epoch": 1.3144049346879536,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.00048327855530648934,
|
|
"loss": 5.4563,
|
|
"mean_token_accuracy": 0.17114406526088716,
|
|
"num_tokens": 30075362.0,
|
|
"step": 14490
|
|
},
|
|
{
|
|
"entropy": 5.680651664733887,
|
|
"epoch": 1.3148584905660377,
|
|
"grad_norm": 3.328125,
|
|
"learning_rate": 0.000483266312673175,
|
|
"loss": 5.4495,
|
|
"mean_token_accuracy": 0.16592298895120622,
|
|
"num_tokens": 30084913.0,
|
|
"step": 14495
|
|
},
|
|
{
|
|
"entropy": 5.684485149383545,
|
|
"epoch": 1.315312046444122,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004832540657328602,
|
|
"loss": 5.4548,
|
|
"mean_token_accuracy": 0.16851414889097213,
|
|
"num_tokens": 30095704.0,
|
|
"step": 14500
|
|
},
|
|
{
|
|
"entropy": 5.63128809928894,
|
|
"epoch": 1.3157656023222062,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004832418144857982,
|
|
"loss": 5.4216,
|
|
"mean_token_accuracy": 0.16449407190084459,
|
|
"num_tokens": 30105981.0,
|
|
"step": 14505
|
|
},
|
|
{
|
|
"entropy": 5.623980283737183,
|
|
"epoch": 1.3162191582002902,
|
|
"grad_norm": 3.4375,
|
|
"learning_rate": 0.00048322955893224245,
|
|
"loss": 5.4486,
|
|
"mean_token_accuracy": 0.1641072452068329,
|
|
"num_tokens": 30115772.0,
|
|
"step": 14510
|
|
},
|
|
{
|
|
"entropy": 5.667907619476319,
|
|
"epoch": 1.3166727140783745,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.00048321729907244626,
|
|
"loss": 5.4221,
|
|
"mean_token_accuracy": 0.16959927827119828,
|
|
"num_tokens": 30127050.0,
|
|
"step": 14515
|
|
},
|
|
{
|
|
"entropy": 5.699899387359619,
|
|
"epoch": 1.3171262699564585,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004832050349066634,
|
|
"loss": 5.4578,
|
|
"mean_token_accuracy": 0.1643613561987877,
|
|
"num_tokens": 30138221.0,
|
|
"step": 14520
|
|
},
|
|
{
|
|
"entropy": 5.758052062988281,
|
|
"epoch": 1.3175798258345428,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004831927664351473,
|
|
"loss": 5.5215,
|
|
"mean_token_accuracy": 0.16590933203697206,
|
|
"num_tokens": 30150181.0,
|
|
"step": 14525
|
|
},
|
|
{
|
|
"entropy": 5.6789978504180905,
|
|
"epoch": 1.318033381712627,
|
|
"grad_norm": 3.828125,
|
|
"learning_rate": 0.0004831804936581518,
|
|
"loss": 5.4901,
|
|
"mean_token_accuracy": 0.16738905012607574,
|
|
"num_tokens": 30160521.0,
|
|
"step": 14530
|
|
},
|
|
{
|
|
"entropy": 5.661901330947876,
|
|
"epoch": 1.3184869375907111,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004831682165759305,
|
|
"loss": 5.4661,
|
|
"mean_token_accuracy": 0.16416670829057695,
|
|
"num_tokens": 30170611.0,
|
|
"step": 14535
|
|
},
|
|
{
|
|
"entropy": 5.697042036056518,
|
|
"epoch": 1.3189404934687954,
|
|
"grad_norm": 3.015625,
|
|
"learning_rate": 0.00048315593518873757,
|
|
"loss": 5.4327,
|
|
"mean_token_accuracy": 0.17526847273111343,
|
|
"num_tokens": 30179914.0,
|
|
"step": 14540
|
|
},
|
|
{
|
|
"entropy": 5.654429531097412,
|
|
"epoch": 1.3193940493468794,
|
|
"grad_norm": 3.78125,
|
|
"learning_rate": 0.0004831436494968268,
|
|
"loss": 5.4505,
|
|
"mean_token_accuracy": 0.1679841846227646,
|
|
"num_tokens": 30191426.0,
|
|
"step": 14545
|
|
},
|
|
{
|
|
"entropy": 5.642498254776001,
|
|
"epoch": 1.3198476052249637,
|
|
"grad_norm": 2.984375,
|
|
"learning_rate": 0.00048313135950045234,
|
|
"loss": 5.3799,
|
|
"mean_token_accuracy": 0.16499294340610504,
|
|
"num_tokens": 30202813.0,
|
|
"step": 14550
|
|
},
|
|
{
|
|
"entropy": 5.6492969512939455,
|
|
"epoch": 1.320301161103048,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.00048311906519986824,
|
|
"loss": 5.3485,
|
|
"mean_token_accuracy": 0.17431945353746414,
|
|
"num_tokens": 30213044.0,
|
|
"step": 14555
|
|
},
|
|
{
|
|
"entropy": 5.708267879486084,
|
|
"epoch": 1.320754716981132,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.000483106766595329,
|
|
"loss": 5.4233,
|
|
"mean_token_accuracy": 0.1654726967215538,
|
|
"num_tokens": 30223419.0,
|
|
"step": 14560
|
|
},
|
|
{
|
|
"entropy": 5.657113552093506,
|
|
"epoch": 1.3212082728592163,
|
|
"grad_norm": 3.15625,
|
|
"learning_rate": 0.0004830944636870887,
|
|
"loss": 5.4544,
|
|
"mean_token_accuracy": 0.16578158885240554,
|
|
"num_tokens": 30233203.0,
|
|
"step": 14565
|
|
},
|
|
{
|
|
"entropy": 5.670950317382813,
|
|
"epoch": 1.3216618287373003,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.00048308215647540183,
|
|
"loss": 5.48,
|
|
"mean_token_accuracy": 0.164300599694252,
|
|
"num_tokens": 30244604.0,
|
|
"step": 14570
|
|
},
|
|
{
|
|
"entropy": 5.790321254730225,
|
|
"epoch": 1.3221153846153846,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.00048306984496052297,
|
|
"loss": 5.5186,
|
|
"mean_token_accuracy": 0.17074266523122789,
|
|
"num_tokens": 30255355.0,
|
|
"step": 14575
|
|
},
|
|
{
|
|
"entropy": 5.751319551467896,
|
|
"epoch": 1.3225689404934688,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.00048305752914270665,
|
|
"loss": 5.5507,
|
|
"mean_token_accuracy": 0.15976754873991011,
|
|
"num_tokens": 30265665.0,
|
|
"step": 14580
|
|
},
|
|
{
|
|
"entropy": 5.692703056335449,
|
|
"epoch": 1.3230224963715531,
|
|
"grad_norm": 2.953125,
|
|
"learning_rate": 0.00048304520902220767,
|
|
"loss": 5.5017,
|
|
"mean_token_accuracy": 0.16947568207979202,
|
|
"num_tokens": 30274347.0,
|
|
"step": 14585
|
|
},
|
|
{
|
|
"entropy": 5.698094511032105,
|
|
"epoch": 1.3234760522496372,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.0004830328845992808,
|
|
"loss": 5.3225,
|
|
"mean_token_accuracy": 0.1740431472659111,
|
|
"num_tokens": 30284243.0,
|
|
"step": 14590
|
|
},
|
|
{
|
|
"entropy": 5.60071029663086,
|
|
"epoch": 1.3239296081277212,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.00048302055587418074,
|
|
"loss": 5.3517,
|
|
"mean_token_accuracy": 0.17382536977529525,
|
|
"num_tokens": 30294327.0,
|
|
"step": 14595
|
|
},
|
|
{
|
|
"entropy": 5.584099674224854,
|
|
"epoch": 1.3243831640058055,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004830082228471626,
|
|
"loss": 5.4432,
|
|
"mean_token_accuracy": 0.16964444667100906,
|
|
"num_tokens": 30304188.0,
|
|
"step": 14600
|
|
},
|
|
{
|
|
"entropy": 5.608399343490601,
|
|
"epoch": 1.3248367198838897,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.00048299588551848146,
|
|
"loss": 5.3774,
|
|
"mean_token_accuracy": 0.1724721983075142,
|
|
"num_tokens": 30314917.0,
|
|
"step": 14605
|
|
},
|
|
{
|
|
"entropy": 5.620994901657104,
|
|
"epoch": 1.325290275761974,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.00048298354388839237,
|
|
"loss": 5.3984,
|
|
"mean_token_accuracy": 0.1697178825736046,
|
|
"num_tokens": 30325221.0,
|
|
"step": 14610
|
|
},
|
|
{
|
|
"entropy": 5.700454425811768,
|
|
"epoch": 1.325743831640058,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.0004829711979571506,
|
|
"loss": 5.4938,
|
|
"mean_token_accuracy": 0.16430918872356415,
|
|
"num_tokens": 30336196.0,
|
|
"step": 14615
|
|
},
|
|
{
|
|
"entropy": 5.611325454711914,
|
|
"epoch": 1.3261973875181423,
|
|
"grad_norm": 3.625,
|
|
"learning_rate": 0.0004829588477250115,
|
|
"loss": 5.2926,
|
|
"mean_token_accuracy": 0.1796329975128174,
|
|
"num_tokens": 30345546.0,
|
|
"step": 14620
|
|
},
|
|
{
|
|
"entropy": 5.617626190185547,
|
|
"epoch": 1.3266509433962264,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004829464931922304,
|
|
"loss": 5.4515,
|
|
"mean_token_accuracy": 0.1692885160446167,
|
|
"num_tokens": 30355672.0,
|
|
"step": 14625
|
|
},
|
|
{
|
|
"entropy": 5.6184608936309814,
|
|
"epoch": 1.3271044992743106,
|
|
"grad_norm": 3.015625,
|
|
"learning_rate": 0.00048293413435906285,
|
|
"loss": 5.4367,
|
|
"mean_token_accuracy": 0.16728255450725554,
|
|
"num_tokens": 30366233.0,
|
|
"step": 14630
|
|
},
|
|
{
|
|
"entropy": 5.705129146575928,
|
|
"epoch": 1.327558055152395,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004829217712257644,
|
|
"loss": 5.4357,
|
|
"mean_token_accuracy": 0.16476741880178453,
|
|
"num_tokens": 30377366.0,
|
|
"step": 14635
|
|
},
|
|
{
|
|
"entropy": 5.709057569503784,
|
|
"epoch": 1.328011611030479,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.00048290940379259073,
|
|
"loss": 5.4905,
|
|
"mean_token_accuracy": 0.16770050972700118,
|
|
"num_tokens": 30388022.0,
|
|
"step": 14640
|
|
},
|
|
{
|
|
"entropy": 5.702963781356812,
|
|
"epoch": 1.3284651669085632,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.00048289703205979756,
|
|
"loss": 5.3759,
|
|
"mean_token_accuracy": 0.16565300077199935,
|
|
"num_tokens": 30399235.0,
|
|
"step": 14645
|
|
},
|
|
{
|
|
"entropy": 5.755176782608032,
|
|
"epoch": 1.3289187227866472,
|
|
"grad_norm": 3.921875,
|
|
"learning_rate": 0.00048288465602764084,
|
|
"loss": 5.5161,
|
|
"mean_token_accuracy": 0.16743238717317582,
|
|
"num_tokens": 30409112.0,
|
|
"step": 14650
|
|
},
|
|
{
|
|
"entropy": 5.6054911613464355,
|
|
"epoch": 1.3293722786647315,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.00048287227569637645,
|
|
"loss": 5.4298,
|
|
"mean_token_accuracy": 0.17225294113159179,
|
|
"num_tokens": 30420202.0,
|
|
"step": 14655
|
|
},
|
|
{
|
|
"entropy": 5.685276126861572,
|
|
"epoch": 1.3298258345428158,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.00048285989106626036,
|
|
"loss": 5.4543,
|
|
"mean_token_accuracy": 0.1686527892947197,
|
|
"num_tokens": 30431210.0,
|
|
"step": 14660
|
|
},
|
|
{
|
|
"entropy": 5.658618831634522,
|
|
"epoch": 1.3302793904208998,
|
|
"grad_norm": 3.9375,
|
|
"learning_rate": 0.0004828475021375489,
|
|
"loss": 5.3828,
|
|
"mean_token_accuracy": 0.17452999353408813,
|
|
"num_tokens": 30441291.0,
|
|
"step": 14665
|
|
},
|
|
{
|
|
"entropy": 5.630302238464355,
|
|
"epoch": 1.330732946298984,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004828351089104981,
|
|
"loss": 5.319,
|
|
"mean_token_accuracy": 0.17881160080432892,
|
|
"num_tokens": 30450285.0,
|
|
"step": 14670
|
|
},
|
|
{
|
|
"entropy": 5.618921279907227,
|
|
"epoch": 1.3311865021770681,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.00048282271138536424,
|
|
"loss": 5.4263,
|
|
"mean_token_accuracy": 0.1682681232690811,
|
|
"num_tokens": 30460311.0,
|
|
"step": 14675
|
|
},
|
|
{
|
|
"entropy": 5.7256622314453125,
|
|
"epoch": 1.3316400580551524,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004828103095624037,
|
|
"loss": 5.4752,
|
|
"mean_token_accuracy": 0.1661389723420143,
|
|
"num_tokens": 30470188.0,
|
|
"step": 14680
|
|
},
|
|
{
|
|
"entropy": 5.670418310165405,
|
|
"epoch": 1.3320936139332367,
|
|
"grad_norm": 4.0,
|
|
"learning_rate": 0.000482797903441873,
|
|
"loss": 5.4014,
|
|
"mean_token_accuracy": 0.16848141700029373,
|
|
"num_tokens": 30481406.0,
|
|
"step": 14685
|
|
},
|
|
{
|
|
"entropy": 5.588410949707031,
|
|
"epoch": 1.3325471698113207,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004827854930240288,
|
|
"loss": 5.4184,
|
|
"mean_token_accuracy": 0.16885267347097396,
|
|
"num_tokens": 30492314.0,
|
|
"step": 14690
|
|
},
|
|
{
|
|
"entropy": 5.718427038192749,
|
|
"epoch": 1.333000725689405,
|
|
"grad_norm": 3.0625,
|
|
"learning_rate": 0.0004827730783091276,
|
|
"loss": 5.5302,
|
|
"mean_token_accuracy": 0.15815719068050385,
|
|
"num_tokens": 30503273.0,
|
|
"step": 14695
|
|
},
|
|
{
|
|
"entropy": 5.761682939529419,
|
|
"epoch": 1.333454281567489,
|
|
"grad_norm": 3.359375,
|
|
"learning_rate": 0.00048276065929742616,
|
|
"loss": 5.4305,
|
|
"mean_token_accuracy": 0.16706839948892593,
|
|
"num_tokens": 30513582.0,
|
|
"step": 14700
|
|
},
|
|
{
|
|
"entropy": 5.6007555484771725,
|
|
"epoch": 1.3339078374455733,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004827482359891814,
|
|
"loss": 5.3471,
|
|
"mean_token_accuracy": 0.17730867713689805,
|
|
"num_tokens": 30523261.0,
|
|
"step": 14705
|
|
},
|
|
{
|
|
"entropy": 5.619212532043457,
|
|
"epoch": 1.3343613933236576,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.00048273580838465016,
|
|
"loss": 5.4598,
|
|
"mean_token_accuracy": 0.16707663089036942,
|
|
"num_tokens": 30533774.0,
|
|
"step": 14710
|
|
},
|
|
{
|
|
"entropy": 5.688348388671875,
|
|
"epoch": 1.3348149492017416,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004827233764840894,
|
|
"loss": 5.4942,
|
|
"mean_token_accuracy": 0.16616595387458802,
|
|
"num_tokens": 30544580.0,
|
|
"step": 14715
|
|
},
|
|
{
|
|
"entropy": 5.731724786758423,
|
|
"epoch": 1.3352685050798259,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.0004827109402877564,
|
|
"loss": 5.3689,
|
|
"mean_token_accuracy": 0.17311762273311615,
|
|
"num_tokens": 30555105.0,
|
|
"step": 14720
|
|
},
|
|
{
|
|
"entropy": 5.673054313659668,
|
|
"epoch": 1.33572206095791,
|
|
"grad_norm": 3.078125,
|
|
"learning_rate": 0.0004826984997959082,
|
|
"loss": 5.4787,
|
|
"mean_token_accuracy": 0.16191026270389558,
|
|
"num_tokens": 30564912.0,
|
|
"step": 14725
|
|
},
|
|
{
|
|
"entropy": 5.667166757583618,
|
|
"epoch": 1.3361756168359942,
|
|
"grad_norm": 5.0625,
|
|
"learning_rate": 0.000482686055008802,
|
|
"loss": 5.4313,
|
|
"mean_token_accuracy": 0.16767922341823577,
|
|
"num_tokens": 30575862.0,
|
|
"step": 14730
|
|
},
|
|
{
|
|
"entropy": 5.6772270679473875,
|
|
"epoch": 1.3366291727140784,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.00048267360592669535,
|
|
"loss": 5.5428,
|
|
"mean_token_accuracy": 0.16349230706691742,
|
|
"num_tokens": 30586951.0,
|
|
"step": 14735
|
|
},
|
|
{
|
|
"entropy": 5.663767004013062,
|
|
"epoch": 1.3370827285921625,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004826611525498456,
|
|
"loss": 5.4611,
|
|
"mean_token_accuracy": 0.16858391165733339,
|
|
"num_tokens": 30597604.0,
|
|
"step": 14740
|
|
},
|
|
{
|
|
"entropy": 5.7306732654571535,
|
|
"epoch": 1.3375362844702468,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004826486948785103,
|
|
"loss": 5.4916,
|
|
"mean_token_accuracy": 0.16721050590276718,
|
|
"num_tokens": 30608157.0,
|
|
"step": 14745
|
|
},
|
|
{
|
|
"entropy": 5.713084554672241,
|
|
"epoch": 1.3379898403483308,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00048263623291294706,
|
|
"loss": 5.4409,
|
|
"mean_token_accuracy": 0.16467640846967696,
|
|
"num_tokens": 30618527.0,
|
|
"step": 14750
|
|
},
|
|
{
|
|
"entropy": 5.680625152587891,
|
|
"epoch": 1.338443396226415,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.00048262376665341355,
|
|
"loss": 5.5245,
|
|
"mean_token_accuracy": 0.16314170882105827,
|
|
"num_tokens": 30629253.0,
|
|
"step": 14755
|
|
},
|
|
{
|
|
"entropy": 5.690137815475464,
|
|
"epoch": 1.3388969521044993,
|
|
"grad_norm": 3.171875,
|
|
"learning_rate": 0.0004826112961001677,
|
|
"loss": 5.4878,
|
|
"mean_token_accuracy": 0.15508340746164323,
|
|
"num_tokens": 30639015.0,
|
|
"step": 14760
|
|
},
|
|
{
|
|
"entropy": 5.744121408462524,
|
|
"epoch": 1.3393505079825834,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00048259882125346735,
|
|
"loss": 5.5699,
|
|
"mean_token_accuracy": 0.1580655336380005,
|
|
"num_tokens": 30650035.0,
|
|
"step": 14765
|
|
},
|
|
{
|
|
"entropy": 5.704358959197998,
|
|
"epoch": 1.3398040638606676,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.00048258634211357045,
|
|
"loss": 5.4678,
|
|
"mean_token_accuracy": 0.16911328583955765,
|
|
"num_tokens": 30659813.0,
|
|
"step": 14770
|
|
},
|
|
{
|
|
"entropy": 5.66546630859375,
|
|
"epoch": 1.3402576197387517,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004825738586807351,
|
|
"loss": 5.4288,
|
|
"mean_token_accuracy": 0.16552227437496186,
|
|
"num_tokens": 30670243.0,
|
|
"step": 14775
|
|
},
|
|
{
|
|
"entropy": 5.601436567306519,
|
|
"epoch": 1.340711175616836,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00048256137095521945,
|
|
"loss": 5.381,
|
|
"mean_token_accuracy": 0.17233275771141052,
|
|
"num_tokens": 30680056.0,
|
|
"step": 14780
|
|
},
|
|
{
|
|
"entropy": 5.689186382293701,
|
|
"epoch": 1.3411647314949202,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.00048254887893728175,
|
|
"loss": 5.35,
|
|
"mean_token_accuracy": 0.1781058728694916,
|
|
"num_tokens": 30690536.0,
|
|
"step": 14785
|
|
},
|
|
{
|
|
"entropy": 5.619725036621094,
|
|
"epoch": 1.3416182873730045,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004825363826271804,
|
|
"loss": 5.4253,
|
|
"mean_token_accuracy": 0.16493427157402038,
|
|
"num_tokens": 30700200.0,
|
|
"step": 14790
|
|
},
|
|
{
|
|
"entropy": 5.597233772277832,
|
|
"epoch": 1.3420718432510885,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004825238820251737,
|
|
"loss": 5.3337,
|
|
"mean_token_accuracy": 0.16788668185472488,
|
|
"num_tokens": 30710576.0,
|
|
"step": 14795
|
|
},
|
|
{
|
|
"entropy": 5.67504358291626,
|
|
"epoch": 1.3425253991291728,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.00048251137713152027,
|
|
"loss": 5.4606,
|
|
"mean_token_accuracy": 0.1644124910235405,
|
|
"num_tokens": 30721495.0,
|
|
"step": 14800
|
|
},
|
|
{
|
|
"entropy": 5.706405925750732,
|
|
"epoch": 1.3429789550072568,
|
|
"grad_norm": 4.03125,
|
|
"learning_rate": 0.0004824988679464787,
|
|
"loss": 5.4803,
|
|
"mean_token_accuracy": 0.1640086926519871,
|
|
"num_tokens": 30731700.0,
|
|
"step": 14805
|
|
},
|
|
{
|
|
"entropy": 5.728052377700806,
|
|
"epoch": 1.343432510885341,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.00048248635447030767,
|
|
"loss": 5.4658,
|
|
"mean_token_accuracy": 0.16700598746538162,
|
|
"num_tokens": 30743421.0,
|
|
"step": 14810
|
|
},
|
|
{
|
|
"entropy": 5.581864738464356,
|
|
"epoch": 1.3438860667634254,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004824738367032659,
|
|
"loss": 5.3571,
|
|
"mean_token_accuracy": 0.17403800487518312,
|
|
"num_tokens": 30754238.0,
|
|
"step": 14815
|
|
},
|
|
{
|
|
"entropy": 5.597588682174683,
|
|
"epoch": 1.3443396226415094,
|
|
"grad_norm": 2.84375,
|
|
"learning_rate": 0.0004824613146456123,
|
|
"loss": 5.4659,
|
|
"mean_token_accuracy": 0.16692458242177963,
|
|
"num_tokens": 30763938.0,
|
|
"step": 14820
|
|
},
|
|
{
|
|
"entropy": 5.732440519332886,
|
|
"epoch": 1.3447931785195937,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004824487882976059,
|
|
"loss": 5.5181,
|
|
"mean_token_accuracy": 0.1637802541255951,
|
|
"num_tokens": 30773654.0,
|
|
"step": 14825
|
|
},
|
|
{
|
|
"entropy": 5.738879251480102,
|
|
"epoch": 1.3452467343976777,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.00048243625765950564,
|
|
"loss": 5.4861,
|
|
"mean_token_accuracy": 0.16771991848945617,
|
|
"num_tokens": 30784659.0,
|
|
"step": 14830
|
|
},
|
|
{
|
|
"entropy": 5.613475704193116,
|
|
"epoch": 1.345700290275762,
|
|
"grad_norm": 4.15625,
|
|
"learning_rate": 0.0004824237227315708,
|
|
"loss": 5.3522,
|
|
"mean_token_accuracy": 0.16558544039726258,
|
|
"num_tokens": 30795194.0,
|
|
"step": 14835
|
|
},
|
|
{
|
|
"entropy": 5.575544548034668,
|
|
"epoch": 1.3461538461538463,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004824111835140604,
|
|
"loss": 5.2944,
|
|
"mean_token_accuracy": 0.17966565787792205,
|
|
"num_tokens": 30805623.0,
|
|
"step": 14840
|
|
},
|
|
{
|
|
"entropy": 5.616778802871704,
|
|
"epoch": 1.3466074020319303,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.000482398640007234,
|
|
"loss": 5.3424,
|
|
"mean_token_accuracy": 0.1759002186357975,
|
|
"num_tokens": 30814899.0,
|
|
"step": 14845
|
|
},
|
|
{
|
|
"entropy": 5.639277124404908,
|
|
"epoch": 1.3470609579100146,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.00048238609221135076,
|
|
"loss": 5.4857,
|
|
"mean_token_accuracy": 0.16421593129634857,
|
|
"num_tokens": 30825546.0,
|
|
"step": 14850
|
|
},
|
|
{
|
|
"entropy": 5.632196617126465,
|
|
"epoch": 1.3475145137880986,
|
|
"grad_norm": 2.84375,
|
|
"learning_rate": 0.0004823735401266704,
|
|
"loss": 5.3752,
|
|
"mean_token_accuracy": 0.17042914479970933,
|
|
"num_tokens": 30836406.0,
|
|
"step": 14855
|
|
},
|
|
{
|
|
"entropy": 5.678290128707886,
|
|
"epoch": 1.3479680696661829,
|
|
"grad_norm": 5.34375,
|
|
"learning_rate": 0.00048236098375345227,
|
|
"loss": 5.4668,
|
|
"mean_token_accuracy": 0.16611820459365845,
|
|
"num_tokens": 30847966.0,
|
|
"step": 14860
|
|
},
|
|
{
|
|
"entropy": 5.7364074230194095,
|
|
"epoch": 1.3484216255442671,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004823484230919563,
|
|
"loss": 5.4738,
|
|
"mean_token_accuracy": 0.16581880301237106,
|
|
"num_tokens": 30856831.0,
|
|
"step": 14865
|
|
},
|
|
{
|
|
"entropy": 5.57171664237976,
|
|
"epoch": 1.3488751814223512,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.00048233585814244195,
|
|
"loss": 5.2858,
|
|
"mean_token_accuracy": 0.1769997775554657,
|
|
"num_tokens": 30866076.0,
|
|
"step": 14870
|
|
},
|
|
{
|
|
"entropy": 5.614659452438355,
|
|
"epoch": 1.3493287373004355,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004823232889051693,
|
|
"loss": 5.3808,
|
|
"mean_token_accuracy": 0.17341279685497285,
|
|
"num_tokens": 30876845.0,
|
|
"step": 14875
|
|
},
|
|
{
|
|
"entropy": 5.5787904262542725,
|
|
"epoch": 1.3497822931785195,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.00048231071538039816,
|
|
"loss": 5.4376,
|
|
"mean_token_accuracy": 0.16730086654424667,
|
|
"num_tokens": 30887448.0,
|
|
"step": 14880
|
|
},
|
|
{
|
|
"entropy": 5.692947483062744,
|
|
"epoch": 1.3502358490566038,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.00048229813756838863,
|
|
"loss": 5.4271,
|
|
"mean_token_accuracy": 0.16784110069274902,
|
|
"num_tokens": 30898414.0,
|
|
"step": 14885
|
|
},
|
|
{
|
|
"entropy": 5.699644899368286,
|
|
"epoch": 1.350689404934688,
|
|
"grad_norm": 3.640625,
|
|
"learning_rate": 0.0004822855554694007,
|
|
"loss": 5.4358,
|
|
"mean_token_accuracy": 0.1690657377243042,
|
|
"num_tokens": 30908559.0,
|
|
"step": 14890
|
|
},
|
|
{
|
|
"entropy": 5.686734390258789,
|
|
"epoch": 1.351142960812772,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.00048227296908369475,
|
|
"loss": 5.4177,
|
|
"mean_token_accuracy": 0.1688425436615944,
|
|
"num_tokens": 30918655.0,
|
|
"step": 14895
|
|
},
|
|
{
|
|
"entropy": 5.657523727416992,
|
|
"epoch": 1.3515965166908563,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.00048226037841153104,
|
|
"loss": 5.4367,
|
|
"mean_token_accuracy": 0.16655483990907669,
|
|
"num_tokens": 30929188.0,
|
|
"step": 14900
|
|
},
|
|
{
|
|
"entropy": 5.717204284667969,
|
|
"epoch": 1.3520500725689404,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004822477834531698,
|
|
"loss": 5.4971,
|
|
"mean_token_accuracy": 0.17080031037330629,
|
|
"num_tokens": 30939902.0,
|
|
"step": 14905
|
|
},
|
|
{
|
|
"entropy": 5.666650676727295,
|
|
"epoch": 1.3525036284470247,
|
|
"grad_norm": 2.984375,
|
|
"learning_rate": 0.0004822351842088716,
|
|
"loss": 5.4437,
|
|
"mean_token_accuracy": 0.1659674823284149,
|
|
"num_tokens": 30951289.0,
|
|
"step": 14910
|
|
},
|
|
{
|
|
"entropy": 5.727969932556152,
|
|
"epoch": 1.352957184325109,
|
|
"grad_norm": 3.578125,
|
|
"learning_rate": 0.0004822225806788969,
|
|
"loss": 5.5593,
|
|
"mean_token_accuracy": 0.1619352400302887,
|
|
"num_tokens": 30961233.0,
|
|
"step": 14915
|
|
},
|
|
{
|
|
"entropy": 5.690713262557983,
|
|
"epoch": 1.353410740203193,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.00048220997286350654,
|
|
"loss": 5.3936,
|
|
"mean_token_accuracy": 0.1755960389971733,
|
|
"num_tokens": 30971922.0,
|
|
"step": 14920
|
|
},
|
|
{
|
|
"entropy": 5.660112094879151,
|
|
"epoch": 1.3538642960812772,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.00048219736076296114,
|
|
"loss": 5.4168,
|
|
"mean_token_accuracy": 0.17356983423233033,
|
|
"num_tokens": 30981358.0,
|
|
"step": 14925
|
|
},
|
|
{
|
|
"entropy": 5.701062202453613,
|
|
"epoch": 1.3543178519593613,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004821847443775214,
|
|
"loss": 5.5318,
|
|
"mean_token_accuracy": 0.16448161602020264,
|
|
"num_tokens": 30991984.0,
|
|
"step": 14930
|
|
},
|
|
{
|
|
"entropy": 5.711239242553711,
|
|
"epoch": 1.3547714078374455,
|
|
"grad_norm": 3.03125,
|
|
"learning_rate": 0.00048217212370744853,
|
|
"loss": 5.4161,
|
|
"mean_token_accuracy": 0.16704692244529723,
|
|
"num_tokens": 31002790.0,
|
|
"step": 14935
|
|
},
|
|
{
|
|
"entropy": 5.596688938140869,
|
|
"epoch": 1.3552249637155298,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.00048215949875300327,
|
|
"loss": 5.2751,
|
|
"mean_token_accuracy": 0.175712713599205,
|
|
"num_tokens": 31012827.0,
|
|
"step": 14940
|
|
},
|
|
{
|
|
"entropy": 5.606149053573608,
|
|
"epoch": 1.3556785195936139,
|
|
"grad_norm": 2.890625,
|
|
"learning_rate": 0.0004821468695144467,
|
|
"loss": 5.3921,
|
|
"mean_token_accuracy": 0.1683544784784317,
|
|
"num_tokens": 31023075.0,
|
|
"step": 14945
|
|
},
|
|
{
|
|
"entropy": 5.682428359985352,
|
|
"epoch": 1.3561320754716981,
|
|
"grad_norm": 3.96875,
|
|
"learning_rate": 0.00048213423599204015,
|
|
"loss": 5.4429,
|
|
"mean_token_accuracy": 0.17283754497766496,
|
|
"num_tokens": 31032454.0,
|
|
"step": 14950
|
|
},
|
|
{
|
|
"entropy": 5.75163516998291,
|
|
"epoch": 1.3565856313497822,
|
|
"grad_norm": 3.6875,
|
|
"learning_rate": 0.00048212159818604477,
|
|
"loss": 5.5428,
|
|
"mean_token_accuracy": 0.16015919297933578,
|
|
"num_tokens": 31042498.0,
|
|
"step": 14955
|
|
},
|
|
{
|
|
"entropy": 5.63552451133728,
|
|
"epoch": 1.3570391872278664,
|
|
"grad_norm": 4.53125,
|
|
"learning_rate": 0.000482108956096722,
|
|
"loss": 5.4209,
|
|
"mean_token_accuracy": 0.1648286208510399,
|
|
"num_tokens": 31053188.0,
|
|
"step": 14960
|
|
},
|
|
{
|
|
"entropy": 5.673468112945557,
|
|
"epoch": 1.3574927431059507,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.00048209630972433326,
|
|
"loss": 5.4021,
|
|
"mean_token_accuracy": 0.1744193211197853,
|
|
"num_tokens": 31062840.0,
|
|
"step": 14965
|
|
},
|
|
{
|
|
"entropy": 5.752945756912231,
|
|
"epoch": 1.357946298984035,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00048208365906914,
|
|
"loss": 5.5258,
|
|
"mean_token_accuracy": 0.16590188443660736,
|
|
"num_tokens": 31072646.0,
|
|
"step": 14970
|
|
},
|
|
{
|
|
"entropy": 5.587217140197754,
|
|
"epoch": 1.358399854862119,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.00048207100413140397,
|
|
"loss": 5.3493,
|
|
"mean_token_accuracy": 0.1665466234087944,
|
|
"num_tokens": 31082700.0,
|
|
"step": 14975
|
|
},
|
|
{
|
|
"entropy": 5.693356609344482,
|
|
"epoch": 1.3588534107402033,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004820583449113868,
|
|
"loss": 5.4673,
|
|
"mean_token_accuracy": 0.16692737713456154,
|
|
"num_tokens": 31093743.0,
|
|
"step": 14980
|
|
},
|
|
{
|
|
"entropy": 5.676620531082153,
|
|
"epoch": 1.3593069666182873,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.00048204568140935023,
|
|
"loss": 5.3991,
|
|
"mean_token_accuracy": 0.1669541910290718,
|
|
"num_tokens": 31104293.0,
|
|
"step": 14985
|
|
},
|
|
{
|
|
"entropy": 5.606513452529907,
|
|
"epoch": 1.3597605224963716,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.0004820330136255563,
|
|
"loss": 5.4125,
|
|
"mean_token_accuracy": 0.17368533909320832,
|
|
"num_tokens": 31114244.0,
|
|
"step": 14990
|
|
},
|
|
{
|
|
"entropy": 5.595551633834839,
|
|
"epoch": 1.3602140783744558,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.00048202034156026683,
|
|
"loss": 5.3947,
|
|
"mean_token_accuracy": 0.16981044709682463,
|
|
"num_tokens": 31123596.0,
|
|
"step": 14995
|
|
},
|
|
{
|
|
"entropy": 5.67397518157959,
|
|
"epoch": 1.36066763425254,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.00048200766521374396,
|
|
"loss": 5.4742,
|
|
"mean_token_accuracy": 0.16335548609495162,
|
|
"num_tokens": 31134258.0,
|
|
"step": 15000
|
|
},
|
|
{
|
|
"epoch": 1.36066763425254,
|
|
"eval_entropy": 5.501548231996562,
|
|
"eval_loss": 5.495517730712891,
|
|
"eval_mean_token_accuracy": 0.17400081258317734,
|
|
"eval_num_tokens": 31134258.0,
|
|
"eval_runtime": 26.6826,
|
|
"eval_samples_per_second": 1325.21,
|
|
"eval_steps_per_second": 165.651,
|
|
"step": 15000
|
|
},
|
|
{
|
|
"entropy": 5.6682600498199465,
|
|
"epoch": 1.3611211901306242,
|
|
"grad_norm": 3.015625,
|
|
"learning_rate": 0.0004819949845862498,
|
|
"loss": 5.4494,
|
|
"mean_token_accuracy": 0.16872814297676086,
|
|
"num_tokens": 31144806.0,
|
|
"step": 15005
|
|
},
|
|
{
|
|
"entropy": 5.719277954101562,
|
|
"epoch": 1.3615747460087082,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004819822996780466,
|
|
"loss": 5.5455,
|
|
"mean_token_accuracy": 0.16234517395496367,
|
|
"num_tokens": 31155642.0,
|
|
"step": 15010
|
|
},
|
|
{
|
|
"entropy": 5.685551691055298,
|
|
"epoch": 1.3620283018867925,
|
|
"grad_norm": 3.5625,
|
|
"learning_rate": 0.0004819696104893967,
|
|
"loss": 5.3633,
|
|
"mean_token_accuracy": 0.17262628078460693,
|
|
"num_tokens": 31165034.0,
|
|
"step": 15015
|
|
},
|
|
{
|
|
"entropy": 5.662414836883545,
|
|
"epoch": 1.3624818577648767,
|
|
"grad_norm": 3.84375,
|
|
"learning_rate": 0.0004819569170205625,
|
|
"loss": 5.4588,
|
|
"mean_token_accuracy": 0.16599993258714676,
|
|
"num_tokens": 31176491.0,
|
|
"step": 15020
|
|
},
|
|
{
|
|
"entropy": 5.681619453430176,
|
|
"epoch": 1.3629354136429608,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.00048194421927180654,
|
|
"loss": 5.4815,
|
|
"mean_token_accuracy": 0.16446527391672133,
|
|
"num_tokens": 31186198.0,
|
|
"step": 15025
|
|
},
|
|
{
|
|
"entropy": 5.72065372467041,
|
|
"epoch": 1.363388969521045,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004819315172433914,
|
|
"loss": 5.4296,
|
|
"mean_token_accuracy": 0.16811263859272002,
|
|
"num_tokens": 31197094.0,
|
|
"step": 15030
|
|
},
|
|
{
|
|
"entropy": 5.66937222480774,
|
|
"epoch": 1.363842525399129,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.00048191881093557977,
|
|
"loss": 5.4583,
|
|
"mean_token_accuracy": 0.16221732944250106,
|
|
"num_tokens": 31207505.0,
|
|
"step": 15035
|
|
},
|
|
{
|
|
"entropy": 5.755509662628174,
|
|
"epoch": 1.3642960812772134,
|
|
"grad_norm": 3.171875,
|
|
"learning_rate": 0.00048190610034863434,
|
|
"loss": 5.5647,
|
|
"mean_token_accuracy": 0.1550256922841072,
|
|
"num_tokens": 31218809.0,
|
|
"step": 15040
|
|
},
|
|
{
|
|
"entropy": 5.742776393890381,
|
|
"epoch": 1.3647496371552976,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004818933854828181,
|
|
"loss": 5.4869,
|
|
"mean_token_accuracy": 0.16092536747455596,
|
|
"num_tokens": 31230281.0,
|
|
"step": 15045
|
|
},
|
|
{
|
|
"entropy": 5.634827280044556,
|
|
"epoch": 1.3652031930333817,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004818806663383939,
|
|
"loss": 5.3766,
|
|
"mean_token_accuracy": 0.17061213552951812,
|
|
"num_tokens": 31239573.0,
|
|
"step": 15050
|
|
},
|
|
{
|
|
"entropy": 5.660884189605713,
|
|
"epoch": 1.365656748911466,
|
|
"grad_norm": 2.875,
|
|
"learning_rate": 0.0004818679429156248,
|
|
"loss": 5.4031,
|
|
"mean_token_accuracy": 0.17135041654109956,
|
|
"num_tokens": 31249671.0,
|
|
"step": 15055
|
|
},
|
|
{
|
|
"entropy": 5.619475841522217,
|
|
"epoch": 1.36611030478955,
|
|
"grad_norm": 3.0625,
|
|
"learning_rate": 0.00048185521521477385,
|
|
"loss": 5.4332,
|
|
"mean_token_accuracy": 0.1623852387070656,
|
|
"num_tokens": 31259601.0,
|
|
"step": 15060
|
|
},
|
|
{
|
|
"entropy": 5.64643030166626,
|
|
"epoch": 1.3665638606676342,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004818424832361044,
|
|
"loss": 5.3889,
|
|
"mean_token_accuracy": 0.17392275035381316,
|
|
"num_tokens": 31269085.0,
|
|
"step": 15065
|
|
},
|
|
{
|
|
"entropy": 5.662960958480835,
|
|
"epoch": 1.3670174165457185,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004818297469798797,
|
|
"loss": 5.431,
|
|
"mean_token_accuracy": 0.1654981106519699,
|
|
"num_tokens": 31280177.0,
|
|
"step": 15070
|
|
},
|
|
{
|
|
"entropy": 5.690148162841797,
|
|
"epoch": 1.3674709724238026,
|
|
"grad_norm": 3.984375,
|
|
"learning_rate": 0.00048181700644636314,
|
|
"loss": 5.3476,
|
|
"mean_token_accuracy": 0.17191191613674164,
|
|
"num_tokens": 31290545.0,
|
|
"step": 15075
|
|
},
|
|
{
|
|
"entropy": 5.610493278503418,
|
|
"epoch": 1.3679245283018868,
|
|
"grad_norm": 9.625,
|
|
"learning_rate": 0.00048180426163581816,
|
|
"loss": 5.3158,
|
|
"mean_token_accuracy": 0.1706655964255333,
|
|
"num_tokens": 31301143.0,
|
|
"step": 15080
|
|
},
|
|
{
|
|
"entropy": 5.604468727111817,
|
|
"epoch": 1.3683780841799709,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004817915125485083,
|
|
"loss": 5.3913,
|
|
"mean_token_accuracy": 0.17074546664953233,
|
|
"num_tokens": 31311071.0,
|
|
"step": 15085
|
|
},
|
|
{
|
|
"entropy": 5.696516036987305,
|
|
"epoch": 1.3688316400580551,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.00048177875918469735,
|
|
"loss": 5.5061,
|
|
"mean_token_accuracy": 0.16404856592416764,
|
|
"num_tokens": 31322263.0,
|
|
"step": 15090
|
|
},
|
|
{
|
|
"entropy": 5.713999605178833,
|
|
"epoch": 1.3692851959361394,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.00048176600154464897,
|
|
"loss": 5.404,
|
|
"mean_token_accuracy": 0.1703720435500145,
|
|
"num_tokens": 31332975.0,
|
|
"step": 15095
|
|
},
|
|
{
|
|
"entropy": 5.767354297637939,
|
|
"epoch": 1.3697387518142234,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004817532396286269,
|
|
"loss": 5.529,
|
|
"mean_token_accuracy": 0.16274141818284987,
|
|
"num_tokens": 31345252.0,
|
|
"step": 15100
|
|
},
|
|
{
|
|
"entropy": 5.65991907119751,
|
|
"epoch": 1.3701923076923077,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004817404734368952,
|
|
"loss": 5.3781,
|
|
"mean_token_accuracy": 0.17311747670173644,
|
|
"num_tokens": 31355479.0,
|
|
"step": 15105
|
|
},
|
|
{
|
|
"entropy": 5.712386512756348,
|
|
"epoch": 1.3706458635703918,
|
|
"grad_norm": 3.75,
|
|
"learning_rate": 0.00048172770296971785,
|
|
"loss": 5.5063,
|
|
"mean_token_accuracy": 0.16422264724969865,
|
|
"num_tokens": 31366020.0,
|
|
"step": 15110
|
|
},
|
|
{
|
|
"entropy": 5.658100175857544,
|
|
"epoch": 1.371099419448476,
|
|
"grad_norm": 3.046875,
|
|
"learning_rate": 0.0004817149282273589,
|
|
"loss": 5.4322,
|
|
"mean_token_accuracy": 0.16983609795570373,
|
|
"num_tokens": 31376055.0,
|
|
"step": 15115
|
|
},
|
|
{
|
|
"entropy": 5.695992183685303,
|
|
"epoch": 1.3715529753265603,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004817021492100825,
|
|
"loss": 5.5556,
|
|
"mean_token_accuracy": 0.1613660916686058,
|
|
"num_tokens": 31386179.0,
|
|
"step": 15120
|
|
},
|
|
{
|
|
"entropy": 5.5961933612823485,
|
|
"epoch": 1.3720065312046443,
|
|
"grad_norm": 4.0625,
|
|
"learning_rate": 0.000481689365918153,
|
|
"loss": 5.3568,
|
|
"mean_token_accuracy": 0.17269919514656068,
|
|
"num_tokens": 31395850.0,
|
|
"step": 15125
|
|
},
|
|
{
|
|
"entropy": 5.6600488185882565,
|
|
"epoch": 1.3724600870827286,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004816765783518348,
|
|
"loss": 5.3174,
|
|
"mean_token_accuracy": 0.17576884478330612,
|
|
"num_tokens": 31405053.0,
|
|
"step": 15130
|
|
},
|
|
{
|
|
"entropy": 5.669331741333008,
|
|
"epoch": 1.3729136429608126,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004816637865113923,
|
|
"loss": 5.3455,
|
|
"mean_token_accuracy": 0.17577203065156938,
|
|
"num_tokens": 31415153.0,
|
|
"step": 15135
|
|
},
|
|
{
|
|
"entropy": 5.6466367721557615,
|
|
"epoch": 1.373367198838897,
|
|
"grad_norm": 3.03125,
|
|
"learning_rate": 0.00048165099039708994,
|
|
"loss": 5.4338,
|
|
"mean_token_accuracy": 0.1653134271502495,
|
|
"num_tokens": 31425451.0,
|
|
"step": 15140
|
|
},
|
|
{
|
|
"entropy": 5.627091312408448,
|
|
"epoch": 1.3738207547169812,
|
|
"grad_norm": 2.953125,
|
|
"learning_rate": 0.0004816381900091925,
|
|
"loss": 5.4228,
|
|
"mean_token_accuracy": 0.16785698831081391,
|
|
"num_tokens": 31436298.0,
|
|
"step": 15145
|
|
},
|
|
{
|
|
"entropy": 5.6469869136810305,
|
|
"epoch": 1.3742743105950654,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.00048162538534796465,
|
|
"loss": 5.4026,
|
|
"mean_token_accuracy": 0.1762536272406578,
|
|
"num_tokens": 31446932.0,
|
|
"step": 15150
|
|
},
|
|
{
|
|
"entropy": 5.695488405227661,
|
|
"epoch": 1.3747278664731495,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004816125764136711,
|
|
"loss": 5.4774,
|
|
"mean_token_accuracy": 0.15518141388893128,
|
|
"num_tokens": 31457582.0,
|
|
"step": 15155
|
|
},
|
|
{
|
|
"entropy": 5.72378306388855,
|
|
"epoch": 1.3751814223512338,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004815997632065769,
|
|
"loss": 5.4577,
|
|
"mean_token_accuracy": 0.16241936087608339,
|
|
"num_tokens": 31468168.0,
|
|
"step": 15160
|
|
},
|
|
{
|
|
"entropy": 5.676669359207153,
|
|
"epoch": 1.3756349782293178,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.00048158694572694694,
|
|
"loss": 5.4286,
|
|
"mean_token_accuracy": 0.16876673698425293,
|
|
"num_tokens": 31478524.0,
|
|
"step": 15165
|
|
},
|
|
{
|
|
"entropy": 5.658973455429077,
|
|
"epoch": 1.376088534107402,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.00048157412397504623,
|
|
"loss": 5.3953,
|
|
"mean_token_accuracy": 0.17391918003559112,
|
|
"num_tokens": 31488608.0,
|
|
"step": 15170
|
|
},
|
|
{
|
|
"entropy": 5.612822198867798,
|
|
"epoch": 1.3765420899854863,
|
|
"grad_norm": 3.484375,
|
|
"learning_rate": 0.0004815612979511401,
|
|
"loss": 5.4234,
|
|
"mean_token_accuracy": 0.1725473254919052,
|
|
"num_tokens": 31498984.0,
|
|
"step": 15175
|
|
},
|
|
{
|
|
"entropy": 5.698418378829956,
|
|
"epoch": 1.3769956458635704,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.00048154846765549353,
|
|
"loss": 5.4458,
|
|
"mean_token_accuracy": 0.1710878372192383,
|
|
"num_tokens": 31509110.0,
|
|
"step": 15180
|
|
},
|
|
{
|
|
"entropy": 5.634779214859009,
|
|
"epoch": 1.3774492017416546,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.00048153563308837215,
|
|
"loss": 5.4099,
|
|
"mean_token_accuracy": 0.17363847494125367,
|
|
"num_tokens": 31519266.0,
|
|
"step": 15185
|
|
},
|
|
{
|
|
"entropy": 5.60769567489624,
|
|
"epoch": 1.3779027576197387,
|
|
"grad_norm": 2.984375,
|
|
"learning_rate": 0.00048152279425004124,
|
|
"loss": 5.425,
|
|
"mean_token_accuracy": 0.16909566819667815,
|
|
"num_tokens": 31529043.0,
|
|
"step": 15190
|
|
},
|
|
{
|
|
"entropy": 5.750562000274658,
|
|
"epoch": 1.378356313497823,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004815099511407663,
|
|
"loss": 5.4221,
|
|
"mean_token_accuracy": 0.17295784801244735,
|
|
"num_tokens": 31538650.0,
|
|
"step": 15195
|
|
},
|
|
{
|
|
"entropy": 5.6088419437408445,
|
|
"epoch": 1.3788098693759072,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.000481497103760813,
|
|
"loss": 5.3512,
|
|
"mean_token_accuracy": 0.1766062244772911,
|
|
"num_tokens": 31549392.0,
|
|
"step": 15200
|
|
},
|
|
{
|
|
"entropy": 5.618231964111328,
|
|
"epoch": 1.3792634252539913,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.00048148425211044684,
|
|
"loss": 5.5474,
|
|
"mean_token_accuracy": 0.15680575370788574,
|
|
"num_tokens": 31559999.0,
|
|
"step": 15205
|
|
},
|
|
{
|
|
"entropy": 5.7145874977111815,
|
|
"epoch": 1.3797169811320755,
|
|
"grad_norm": 3.140625,
|
|
"learning_rate": 0.0004814713961899338,
|
|
"loss": 5.4442,
|
|
"mean_token_accuracy": 0.1666990891098976,
|
|
"num_tokens": 31570108.0,
|
|
"step": 15210
|
|
},
|
|
{
|
|
"entropy": 5.711512088775635,
|
|
"epoch": 1.3801705370101596,
|
|
"grad_norm": 2.984375,
|
|
"learning_rate": 0.00048145853599953966,
|
|
"loss": 5.3802,
|
|
"mean_token_accuracy": 0.16898790150880813,
|
|
"num_tokens": 31579698.0,
|
|
"step": 15215
|
|
},
|
|
{
|
|
"entropy": 5.622971487045288,
|
|
"epoch": 1.3806240928882438,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.00048144567153953036,
|
|
"loss": 5.4408,
|
|
"mean_token_accuracy": 0.16487733274698257,
|
|
"num_tokens": 31589292.0,
|
|
"step": 15220
|
|
},
|
|
{
|
|
"entropy": 5.705999565124512,
|
|
"epoch": 1.381077648766328,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.00048143280281017197,
|
|
"loss": 5.4997,
|
|
"mean_token_accuracy": 0.16975594758987428,
|
|
"num_tokens": 31599848.0,
|
|
"step": 15225
|
|
},
|
|
{
|
|
"entropy": 5.713175964355469,
|
|
"epoch": 1.3815312046444121,
|
|
"grad_norm": 5.03125,
|
|
"learning_rate": 0.0004814199298117307,
|
|
"loss": 5.4641,
|
|
"mean_token_accuracy": 0.1655859738588333,
|
|
"num_tokens": 31611109.0,
|
|
"step": 15230
|
|
},
|
|
{
|
|
"entropy": 5.666203737258911,
|
|
"epoch": 1.3819847605224964,
|
|
"grad_norm": 3.921875,
|
|
"learning_rate": 0.00048140705254447256,
|
|
"loss": 5.373,
|
|
"mean_token_accuracy": 0.17308667302131653,
|
|
"num_tokens": 31621140.0,
|
|
"step": 15235
|
|
},
|
|
{
|
|
"entropy": 5.716932582855224,
|
|
"epoch": 1.3824383164005805,
|
|
"grad_norm": 7.09375,
|
|
"learning_rate": 0.00048139417100866405,
|
|
"loss": 5.4856,
|
|
"mean_token_accuracy": 0.1679752677679062,
|
|
"num_tokens": 31631268.0,
|
|
"step": 15240
|
|
},
|
|
{
|
|
"entropy": 5.678811740875244,
|
|
"epoch": 1.3828918722786647,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.00048138128520457146,
|
|
"loss": 5.4045,
|
|
"mean_token_accuracy": 0.166739059984684,
|
|
"num_tokens": 31640758.0,
|
|
"step": 15245
|
|
},
|
|
{
|
|
"entropy": 5.598401308059692,
|
|
"epoch": 1.383345428156749,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004813683951324613,
|
|
"loss": 5.4117,
|
|
"mean_token_accuracy": 0.16683411747217178,
|
|
"num_tokens": 31651060.0,
|
|
"step": 15250
|
|
},
|
|
{
|
|
"entropy": 5.687079000473022,
|
|
"epoch": 1.383798984034833,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.00048135550079260014,
|
|
"loss": 5.5211,
|
|
"mean_token_accuracy": 0.16653005182743072,
|
|
"num_tokens": 31662282.0,
|
|
"step": 15255
|
|
},
|
|
{
|
|
"entropy": 5.680498266220093,
|
|
"epoch": 1.3842525399129173,
|
|
"grad_norm": 3.078125,
|
|
"learning_rate": 0.0004813426021852547,
|
|
"loss": 5.3922,
|
|
"mean_token_accuracy": 0.16504303365945816,
|
|
"num_tokens": 31672364.0,
|
|
"step": 15260
|
|
},
|
|
{
|
|
"entropy": 5.689055109024048,
|
|
"epoch": 1.3847060957910013,
|
|
"grad_norm": 4.78125,
|
|
"learning_rate": 0.00048132969931069156,
|
|
"loss": 5.4528,
|
|
"mean_token_accuracy": 0.1649829238653183,
|
|
"num_tokens": 31683094.0,
|
|
"step": 15265
|
|
},
|
|
{
|
|
"entropy": 5.651013469696045,
|
|
"epoch": 1.3851596516690856,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004813167921691777,
|
|
"loss": 5.4138,
|
|
"mean_token_accuracy": 0.1687225118279457,
|
|
"num_tokens": 31693087.0,
|
|
"step": 15270
|
|
},
|
|
{
|
|
"entropy": 5.6905182838439945,
|
|
"epoch": 1.3856132075471699,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.00048130388076098003,
|
|
"loss": 5.4114,
|
|
"mean_token_accuracy": 0.16467617005109786,
|
|
"num_tokens": 31703708.0,
|
|
"step": 15275
|
|
},
|
|
{
|
|
"entropy": 5.647258567810058,
|
|
"epoch": 1.386066763425254,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.00048129096508636547,
|
|
"loss": 5.3529,
|
|
"mean_token_accuracy": 0.1736495926976204,
|
|
"num_tokens": 31713640.0,
|
|
"step": 15280
|
|
},
|
|
{
|
|
"entropy": 5.624648666381836,
|
|
"epoch": 1.3865203193033382,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00048127804514560126,
|
|
"loss": 5.422,
|
|
"mean_token_accuracy": 0.17019286155700683,
|
|
"num_tokens": 31723526.0,
|
|
"step": 15285
|
|
},
|
|
{
|
|
"entropy": 5.616580963134766,
|
|
"epoch": 1.3869738751814222,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.00048126512093895447,
|
|
"loss": 5.3758,
|
|
"mean_token_accuracy": 0.17120354175567626,
|
|
"num_tokens": 31733265.0,
|
|
"step": 15290
|
|
},
|
|
{
|
|
"entropy": 5.735524320602417,
|
|
"epoch": 1.3874274310595065,
|
|
"grad_norm": 2.84375,
|
|
"learning_rate": 0.0004812521924666925,
|
|
"loss": 5.381,
|
|
"mean_token_accuracy": 0.17192656099796294,
|
|
"num_tokens": 31743832.0,
|
|
"step": 15295
|
|
},
|
|
{
|
|
"entropy": 5.6787032127380375,
|
|
"epoch": 1.3878809869375908,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004812392597290825,
|
|
"loss": 5.454,
|
|
"mean_token_accuracy": 0.17683753222227097,
|
|
"num_tokens": 31754443.0,
|
|
"step": 15300
|
|
},
|
|
{
|
|
"entropy": 5.644234085083008,
|
|
"epoch": 1.3883345428156748,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004812263227263921,
|
|
"loss": 5.4039,
|
|
"mean_token_accuracy": 0.16839405745267869,
|
|
"num_tokens": 31765304.0,
|
|
"step": 15305
|
|
},
|
|
{
|
|
"entropy": 5.635614824295044,
|
|
"epoch": 1.388788098693759,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004812133814588888,
|
|
"loss": 5.4111,
|
|
"mean_token_accuracy": 0.16823060512542726,
|
|
"num_tokens": 31775809.0,
|
|
"step": 15310
|
|
},
|
|
{
|
|
"entropy": 5.653427600860596,
|
|
"epoch": 1.3892416545718431,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004812004359268402,
|
|
"loss": 5.4052,
|
|
"mean_token_accuracy": 0.17473479956388474,
|
|
"num_tokens": 31786271.0,
|
|
"step": 15315
|
|
},
|
|
{
|
|
"entropy": 5.695763969421387,
|
|
"epoch": 1.3896952104499274,
|
|
"grad_norm": 4.25,
|
|
"learning_rate": 0.0004811874861305141,
|
|
"loss": 5.4662,
|
|
"mean_token_accuracy": 0.17090054005384445,
|
|
"num_tokens": 31797358.0,
|
|
"step": 15320
|
|
},
|
|
{
|
|
"entropy": 5.6816675662994385,
|
|
"epoch": 1.3901487663280117,
|
|
"grad_norm": 2.875,
|
|
"learning_rate": 0.0004811745320701782,
|
|
"loss": 5.3961,
|
|
"mean_token_accuracy": 0.17551984637975693,
|
|
"num_tokens": 31808303.0,
|
|
"step": 15325
|
|
},
|
|
{
|
|
"entropy": 5.594783020019531,
|
|
"epoch": 1.390602322206096,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004811615737461004,
|
|
"loss": 5.3928,
|
|
"mean_token_accuracy": 0.16915278881788254,
|
|
"num_tokens": 31818837.0,
|
|
"step": 15330
|
|
},
|
|
{
|
|
"entropy": 5.685364246368408,
|
|
"epoch": 1.39105587808418,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.00048114861115854877,
|
|
"loss": 5.4153,
|
|
"mean_token_accuracy": 0.17045014798641206,
|
|
"num_tokens": 31829729.0,
|
|
"step": 15335
|
|
},
|
|
{
|
|
"entropy": 5.6593116283416744,
|
|
"epoch": 1.3915094339622642,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.00048113564430779136,
|
|
"loss": 5.3475,
|
|
"mean_token_accuracy": 0.16975994110107423,
|
|
"num_tokens": 31839996.0,
|
|
"step": 15340
|
|
},
|
|
{
|
|
"entropy": 5.580916404724121,
|
|
"epoch": 1.3919629898403483,
|
|
"grad_norm": 3.609375,
|
|
"learning_rate": 0.0004811226731940962,
|
|
"loss": 5.335,
|
|
"mean_token_accuracy": 0.17470775693655013,
|
|
"num_tokens": 31850298.0,
|
|
"step": 15345
|
|
},
|
|
{
|
|
"entropy": 5.638900375366211,
|
|
"epoch": 1.3924165457184325,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.00048110969781773173,
|
|
"loss": 5.4417,
|
|
"mean_token_accuracy": 0.17755676656961442,
|
|
"num_tokens": 31862170.0,
|
|
"step": 15350
|
|
},
|
|
{
|
|
"entropy": 5.7088765621185305,
|
|
"epoch": 1.3928701015965168,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.00048109671817896614,
|
|
"loss": 5.4849,
|
|
"mean_token_accuracy": 0.16611828953027724,
|
|
"num_tokens": 31872081.0,
|
|
"step": 15355
|
|
},
|
|
{
|
|
"entropy": 5.656893301010132,
|
|
"epoch": 1.3933236574746009,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.00048108373427806797,
|
|
"loss": 5.4414,
|
|
"mean_token_accuracy": 0.16902300715446472,
|
|
"num_tokens": 31882715.0,
|
|
"step": 15360
|
|
},
|
|
{
|
|
"entropy": 5.690029668807983,
|
|
"epoch": 1.3937772133526851,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.00048107074611530555,
|
|
"loss": 5.393,
|
|
"mean_token_accuracy": 0.1771523281931877,
|
|
"num_tokens": 31891925.0,
|
|
"step": 15365
|
|
},
|
|
{
|
|
"entropy": 5.681637382507324,
|
|
"epoch": 1.3942307692307692,
|
|
"grad_norm": 4.65625,
|
|
"learning_rate": 0.00048105775369094756,
|
|
"loss": 5.4388,
|
|
"mean_token_accuracy": 0.16404650658369063,
|
|
"num_tokens": 31902320.0,
|
|
"step": 15370
|
|
},
|
|
{
|
|
"entropy": 5.621541118621826,
|
|
"epoch": 1.3946843251088534,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004810447570052628,
|
|
"loss": 5.3377,
|
|
"mean_token_accuracy": 0.17234056442975998,
|
|
"num_tokens": 31912726.0,
|
|
"step": 15375
|
|
},
|
|
{
|
|
"entropy": 5.633533573150634,
|
|
"epoch": 1.3951378809869377,
|
|
"grad_norm": 3.03125,
|
|
"learning_rate": 0.00048103175605851997,
|
|
"loss": 5.4466,
|
|
"mean_token_accuracy": 0.1711600735783577,
|
|
"num_tokens": 31924039.0,
|
|
"step": 15380
|
|
},
|
|
{
|
|
"entropy": 5.550946474075317,
|
|
"epoch": 1.3955914368650217,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004810187508509879,
|
|
"loss": 5.2995,
|
|
"mean_token_accuracy": 0.18083962351083754,
|
|
"num_tokens": 31933280.0,
|
|
"step": 15385
|
|
},
|
|
{
|
|
"entropy": 5.649135637283325,
|
|
"epoch": 1.396044992743106,
|
|
"grad_norm": 5.71875,
|
|
"learning_rate": 0.0004810057413829355,
|
|
"loss": 5.5236,
|
|
"mean_token_accuracy": 0.16582777947187424,
|
|
"num_tokens": 31943182.0,
|
|
"step": 15390
|
|
},
|
|
{
|
|
"entropy": 5.749302625656128,
|
|
"epoch": 1.39649854862119,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.00048099272765463193,
|
|
"loss": 5.4614,
|
|
"mean_token_accuracy": 0.16771859526634217,
|
|
"num_tokens": 31953256.0,
|
|
"step": 15395
|
|
},
|
|
{
|
|
"entropy": 5.744611835479736,
|
|
"epoch": 1.3969521044992743,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.0004809797096663463,
|
|
"loss": 5.5565,
|
|
"mean_token_accuracy": 0.16261217445135118,
|
|
"num_tokens": 31964231.0,
|
|
"step": 15400
|
|
},
|
|
{
|
|
"entropy": 5.652368688583374,
|
|
"epoch": 1.3974056603773586,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004809666874183477,
|
|
"loss": 5.3785,
|
|
"mean_token_accuracy": 0.17156968414783477,
|
|
"num_tokens": 31974322.0,
|
|
"step": 15405
|
|
},
|
|
{
|
|
"entropy": 5.6468902111053465,
|
|
"epoch": 1.3978592162554426,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004809536609109056,
|
|
"loss": 5.4608,
|
|
"mean_token_accuracy": 0.17404037415981294,
|
|
"num_tokens": 31984239.0,
|
|
"step": 15410
|
|
},
|
|
{
|
|
"entropy": 5.577282571792603,
|
|
"epoch": 1.398312772133527,
|
|
"grad_norm": 3.1875,
|
|
"learning_rate": 0.00048094063014428925,
|
|
"loss": 5.4299,
|
|
"mean_token_accuracy": 0.16560655385255812,
|
|
"num_tokens": 31994366.0,
|
|
"step": 15415
|
|
},
|
|
{
|
|
"entropy": 5.730257177352906,
|
|
"epoch": 1.398766328011611,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004809275951187682,
|
|
"loss": 5.5201,
|
|
"mean_token_accuracy": 0.16394859403371811,
|
|
"num_tokens": 32004921.0,
|
|
"step": 15420
|
|
},
|
|
{
|
|
"entropy": 5.669726324081421,
|
|
"epoch": 1.3992198838896952,
|
|
"grad_norm": 3.40625,
|
|
"learning_rate": 0.00048091455583461204,
|
|
"loss": 5.452,
|
|
"mean_token_accuracy": 0.16952450573444366,
|
|
"num_tokens": 32016385.0,
|
|
"step": 15425
|
|
},
|
|
{
|
|
"entropy": 5.7163256168365475,
|
|
"epoch": 1.3996734397677795,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.00048090151229209036,
|
|
"loss": 5.448,
|
|
"mean_token_accuracy": 0.16484728902578355,
|
|
"num_tokens": 32027398.0,
|
|
"step": 15430
|
|
},
|
|
{
|
|
"entropy": 5.704950618743896,
|
|
"epoch": 1.4001269956458635,
|
|
"grad_norm": 3.328125,
|
|
"learning_rate": 0.0004808884644914729,
|
|
"loss": 5.428,
|
|
"mean_token_accuracy": 0.17022111862897873,
|
|
"num_tokens": 32038326.0,
|
|
"step": 15435
|
|
},
|
|
{
|
|
"entropy": 5.669045448303223,
|
|
"epoch": 1.4005805515239478,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004808754124330296,
|
|
"loss": 5.4854,
|
|
"mean_token_accuracy": 0.16933807283639907,
|
|
"num_tokens": 32048744.0,
|
|
"step": 15440
|
|
},
|
|
{
|
|
"entropy": 5.659678173065186,
|
|
"epoch": 1.4010341074020318,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.0004808623561170302,
|
|
"loss": 5.3785,
|
|
"mean_token_accuracy": 0.17687961906194688,
|
|
"num_tokens": 32059133.0,
|
|
"step": 15445
|
|
},
|
|
{
|
|
"entropy": 5.6465356826782225,
|
|
"epoch": 1.401487663280116,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004808492955437449,
|
|
"loss": 5.4108,
|
|
"mean_token_accuracy": 0.16790107935667037,
|
|
"num_tokens": 32069277.0,
|
|
"step": 15450
|
|
},
|
|
{
|
|
"entropy": 5.67818922996521,
|
|
"epoch": 1.4019412191582004,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.00048083623071344374,
|
|
"loss": 5.3735,
|
|
"mean_token_accuracy": 0.17342840433120726,
|
|
"num_tokens": 32079802.0,
|
|
"step": 15455
|
|
},
|
|
{
|
|
"entropy": 5.663562679290772,
|
|
"epoch": 1.4023947750362844,
|
|
"grad_norm": 3.296875,
|
|
"learning_rate": 0.00048082316162639685,
|
|
"loss": 5.4977,
|
|
"mean_token_accuracy": 0.16621191650629044,
|
|
"num_tokens": 32090962.0,
|
|
"step": 15460
|
|
},
|
|
{
|
|
"entropy": 5.614001321792602,
|
|
"epoch": 1.4028483309143687,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.00048081008828287447,
|
|
"loss": 5.4403,
|
|
"mean_token_accuracy": 0.16960980892181396,
|
|
"num_tokens": 32101058.0,
|
|
"step": 15465
|
|
},
|
|
{
|
|
"entropy": 5.731743240356446,
|
|
"epoch": 1.4033018867924527,
|
|
"grad_norm": 3.28125,
|
|
"learning_rate": 0.00048079701068314706,
|
|
"loss": 5.4456,
|
|
"mean_token_accuracy": 0.1729030802845955,
|
|
"num_tokens": 32111763.0,
|
|
"step": 15470
|
|
},
|
|
{
|
|
"entropy": 5.760666084289551,
|
|
"epoch": 1.403755442670537,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.00048078392882748507,
|
|
"loss": 5.5177,
|
|
"mean_token_accuracy": 0.1696193978190422,
|
|
"num_tokens": 32123556.0,
|
|
"step": 15475
|
|
},
|
|
{
|
|
"entropy": 5.687629175186157,
|
|
"epoch": 1.4042089985486212,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.00048077084271615895,
|
|
"loss": 5.4049,
|
|
"mean_token_accuracy": 0.17171141505241394,
|
|
"num_tokens": 32134012.0,
|
|
"step": 15480
|
|
},
|
|
{
|
|
"entropy": 5.604795312881469,
|
|
"epoch": 1.4046625544267053,
|
|
"grad_norm": 7.46875,
|
|
"learning_rate": 0.0004807577523494394,
|
|
"loss": 5.3619,
|
|
"mean_token_accuracy": 0.18062683194875717,
|
|
"num_tokens": 32144540.0,
|
|
"step": 15485
|
|
},
|
|
{
|
|
"entropy": 5.651252269744873,
|
|
"epoch": 1.4051161103047896,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.00048074465772759707,
|
|
"loss": 5.4838,
|
|
"mean_token_accuracy": 0.16747957617044448,
|
|
"num_tokens": 32154655.0,
|
|
"step": 15490
|
|
},
|
|
{
|
|
"entropy": 5.649133729934692,
|
|
"epoch": 1.4055696661828736,
|
|
"grad_norm": 3.125,
|
|
"learning_rate": 0.00048073155885090276,
|
|
"loss": 5.3906,
|
|
"mean_token_accuracy": 0.170157353579998,
|
|
"num_tokens": 32165191.0,
|
|
"step": 15495
|
|
},
|
|
{
|
|
"entropy": 5.681288146972657,
|
|
"epoch": 1.4060232220609579,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00048071845571962733,
|
|
"loss": 5.4537,
|
|
"mean_token_accuracy": 0.16495953649282455,
|
|
"num_tokens": 32175961.0,
|
|
"step": 15500
|
|
},
|
|
{
|
|
"entropy": 5.706629276275635,
|
|
"epoch": 1.4064767779390421,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004807053483340419,
|
|
"loss": 5.4479,
|
|
"mean_token_accuracy": 0.16543769091367722,
|
|
"num_tokens": 32187073.0,
|
|
"step": 15505
|
|
},
|
|
{
|
|
"entropy": 5.662785053253174,
|
|
"epoch": 1.4069303338171264,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.0004806922366944175,
|
|
"loss": 5.4259,
|
|
"mean_token_accuracy": 0.1727198138833046,
|
|
"num_tokens": 32197426.0,
|
|
"step": 15510
|
|
},
|
|
{
|
|
"entropy": 5.735806322097778,
|
|
"epoch": 1.4073838896952104,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.00048067912080102513,
|
|
"loss": 5.4113,
|
|
"mean_token_accuracy": 0.18016623705625534,
|
|
"num_tokens": 32206847.0,
|
|
"step": 15515
|
|
},
|
|
{
|
|
"entropy": 5.654276752471924,
|
|
"epoch": 1.4078374455732947,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004806660006541362,
|
|
"loss": 5.4497,
|
|
"mean_token_accuracy": 0.16919416785240174,
|
|
"num_tokens": 32217647.0,
|
|
"step": 15520
|
|
},
|
|
{
|
|
"entropy": 5.548145294189453,
|
|
"epoch": 1.4082910014513788,
|
|
"grad_norm": 3.96875,
|
|
"learning_rate": 0.0004806528762540219,
|
|
"loss": 5.3107,
|
|
"mean_token_accuracy": 0.17773349583148956,
|
|
"num_tokens": 32227133.0,
|
|
"step": 15525
|
|
},
|
|
{
|
|
"entropy": 5.680746603012085,
|
|
"epoch": 1.408744557329463,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.00048063974760095374,
|
|
"loss": 5.5133,
|
|
"mean_token_accuracy": 0.16216963678598403,
|
|
"num_tokens": 32237378.0,
|
|
"step": 15530
|
|
},
|
|
{
|
|
"entropy": 5.579992437362671,
|
|
"epoch": 1.4091981132075473,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.00048062661469520327,
|
|
"loss": 5.3879,
|
|
"mean_token_accuracy": 0.17251131534576417,
|
|
"num_tokens": 32247213.0,
|
|
"step": 15535
|
|
},
|
|
{
|
|
"entropy": 5.693244886398316,
|
|
"epoch": 1.4096516690856313,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.00048061347753704193,
|
|
"loss": 5.4273,
|
|
"mean_token_accuracy": 0.17255329638719558,
|
|
"num_tokens": 32257100.0,
|
|
"step": 15540
|
|
},
|
|
{
|
|
"entropy": 5.700950956344604,
|
|
"epoch": 1.4101052249637156,
|
|
"grad_norm": 3.28125,
|
|
"learning_rate": 0.0004806003361267415,
|
|
"loss": 5.3953,
|
|
"mean_token_accuracy": 0.16766183078289032,
|
|
"num_tokens": 32267456.0,
|
|
"step": 15545
|
|
},
|
|
{
|
|
"entropy": 5.581422281265259,
|
|
"epoch": 1.4105587808417996,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004805871904645737,
|
|
"loss": 5.3798,
|
|
"mean_token_accuracy": 0.175940203666687,
|
|
"num_tokens": 32278220.0,
|
|
"step": 15550
|
|
},
|
|
{
|
|
"entropy": 5.612519979476929,
|
|
"epoch": 1.411012336719884,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004805740405508103,
|
|
"loss": 5.4375,
|
|
"mean_token_accuracy": 0.17269578874111174,
|
|
"num_tokens": 32289036.0,
|
|
"step": 15555
|
|
},
|
|
{
|
|
"entropy": 5.660814046859741,
|
|
"epoch": 1.4114658925979682,
|
|
"grad_norm": 3.1875,
|
|
"learning_rate": 0.0004805608863857236,
|
|
"loss": 5.3373,
|
|
"mean_token_accuracy": 0.17372834980487822,
|
|
"num_tokens": 32298909.0,
|
|
"step": 15560
|
|
},
|
|
{
|
|
"entropy": 5.674689722061157,
|
|
"epoch": 1.4119194484760522,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.00048054772796958517,
|
|
"loss": 5.4027,
|
|
"mean_token_accuracy": 0.16938709020614623,
|
|
"num_tokens": 32309851.0,
|
|
"step": 15565
|
|
},
|
|
{
|
|
"entropy": 5.581267023086548,
|
|
"epoch": 1.4123730043541365,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004805345653026675,
|
|
"loss": 5.3564,
|
|
"mean_token_accuracy": 0.17718882113695145,
|
|
"num_tokens": 32319336.0,
|
|
"step": 15570
|
|
},
|
|
{
|
|
"entropy": 5.675482892990113,
|
|
"epoch": 1.4128265602322205,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00048052139838524263,
|
|
"loss": 5.4011,
|
|
"mean_token_accuracy": 0.1720806822180748,
|
|
"num_tokens": 32329898.0,
|
|
"step": 15575
|
|
},
|
|
{
|
|
"entropy": 5.637049579620362,
|
|
"epoch": 1.4132801161103048,
|
|
"grad_norm": 3.8125,
|
|
"learning_rate": 0.00048050822721758274,
|
|
"loss": 5.2898,
|
|
"mean_token_accuracy": 0.17177536636590957,
|
|
"num_tokens": 32340100.0,
|
|
"step": 15580
|
|
},
|
|
{
|
|
"entropy": 5.625023651123047,
|
|
"epoch": 1.413733671988389,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.0004804950517999604,
|
|
"loss": 5.4102,
|
|
"mean_token_accuracy": 0.17198781669139862,
|
|
"num_tokens": 32349663.0,
|
|
"step": 15585
|
|
},
|
|
{
|
|
"entropy": 5.669428491592408,
|
|
"epoch": 1.414187227866473,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004804818721326481,
|
|
"loss": 5.4789,
|
|
"mean_token_accuracy": 0.1697591796517372,
|
|
"num_tokens": 32360461.0,
|
|
"step": 15590
|
|
},
|
|
{
|
|
"entropy": 5.642770051956177,
|
|
"epoch": 1.4146407837445574,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004804686882159183,
|
|
"loss": 5.4379,
|
|
"mean_token_accuracy": 0.17173535227775574,
|
|
"num_tokens": 32370910.0,
|
|
"step": 15595
|
|
},
|
|
{
|
|
"entropy": 5.807270574569702,
|
|
"epoch": 1.4150943396226414,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.00048045550005004355,
|
|
"loss": 5.4712,
|
|
"mean_token_accuracy": 0.17406957894563674,
|
|
"num_tokens": 32381669.0,
|
|
"step": 15600
|
|
},
|
|
{
|
|
"entropy": 5.660248327255249,
|
|
"epoch": 1.4155478955007257,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004804423076352968,
|
|
"loss": 5.385,
|
|
"mean_token_accuracy": 0.1698262184858322,
|
|
"num_tokens": 32392024.0,
|
|
"step": 15605
|
|
},
|
|
{
|
|
"entropy": 5.535472869873047,
|
|
"epoch": 1.41600145137881,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.00048042911097195075,
|
|
"loss": 5.3749,
|
|
"mean_token_accuracy": 0.17553981393575668,
|
|
"num_tokens": 32401872.0,
|
|
"step": 15610
|
|
},
|
|
{
|
|
"entropy": 5.598290300369262,
|
|
"epoch": 1.416455007256894,
|
|
"grad_norm": 4.40625,
|
|
"learning_rate": 0.0004804159100602784,
|
|
"loss": 5.3541,
|
|
"mean_token_accuracy": 0.17918634563684463,
|
|
"num_tokens": 32411749.0,
|
|
"step": 15615
|
|
},
|
|
{
|
|
"entropy": 5.776797151565551,
|
|
"epoch": 1.4169085631349783,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.00048040270490055264,
|
|
"loss": 5.5139,
|
|
"mean_token_accuracy": 0.1646192580461502,
|
|
"num_tokens": 32421358.0,
|
|
"step": 15620
|
|
},
|
|
{
|
|
"entropy": 5.749031496047974,
|
|
"epoch": 1.4173621190130623,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004803894954930465,
|
|
"loss": 5.4515,
|
|
"mean_token_accuracy": 0.16799685060977937,
|
|
"num_tokens": 32432322.0,
|
|
"step": 15625
|
|
},
|
|
{
|
|
"entropy": 5.604976320266724,
|
|
"epoch": 1.4178156748911466,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004803762818380334,
|
|
"loss": 5.4316,
|
|
"mean_token_accuracy": 0.16826535165309905,
|
|
"num_tokens": 32440930.0,
|
|
"step": 15630
|
|
},
|
|
{
|
|
"entropy": 5.684864902496338,
|
|
"epoch": 1.4182692307692308,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.00048036306393578644,
|
|
"loss": 5.4547,
|
|
"mean_token_accuracy": 0.16712224781513213,
|
|
"num_tokens": 32451124.0,
|
|
"step": 15635
|
|
},
|
|
{
|
|
"entropy": 5.706327295303344,
|
|
"epoch": 1.4187227866473149,
|
|
"grad_norm": 3.609375,
|
|
"learning_rate": 0.0004803498417865789,
|
|
"loss": 5.4016,
|
|
"mean_token_accuracy": 0.16872473955154418,
|
|
"num_tokens": 32460636.0,
|
|
"step": 15640
|
|
},
|
|
{
|
|
"entropy": 5.696467685699463,
|
|
"epoch": 1.4191763425253991,
|
|
"grad_norm": 3.734375,
|
|
"learning_rate": 0.0004803366153906844,
|
|
"loss": 5.4629,
|
|
"mean_token_accuracy": 0.1678663820028305,
|
|
"num_tokens": 32470501.0,
|
|
"step": 15645
|
|
},
|
|
{
|
|
"entropy": 5.739888286590576,
|
|
"epoch": 1.4196298984034832,
|
|
"grad_norm": 2.984375,
|
|
"learning_rate": 0.0004803233847483763,
|
|
"loss": 5.569,
|
|
"mean_token_accuracy": 0.1635578006505966,
|
|
"num_tokens": 32481559.0,
|
|
"step": 15650
|
|
},
|
|
{
|
|
"entropy": 5.792959833145142,
|
|
"epoch": 1.4200834542815675,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.00048031014985992825,
|
|
"loss": 5.5882,
|
|
"mean_token_accuracy": 0.1597353957593441,
|
|
"num_tokens": 32493000.0,
|
|
"step": 15655
|
|
},
|
|
{
|
|
"entropy": 5.650546073913574,
|
|
"epoch": 1.4205370101596517,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.000480296910725614,
|
|
"loss": 5.4002,
|
|
"mean_token_accuracy": 0.17490327805280687,
|
|
"num_tokens": 32502773.0,
|
|
"step": 15660
|
|
},
|
|
{
|
|
"entropy": 5.645022296905518,
|
|
"epoch": 1.4209905660377358,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004802836673457074,
|
|
"loss": 5.477,
|
|
"mean_token_accuracy": 0.16599569469690323,
|
|
"num_tokens": 32513430.0,
|
|
"step": 15665
|
|
},
|
|
{
|
|
"entropy": 5.687364816665649,
|
|
"epoch": 1.42144412191582,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.00048027041972048225,
|
|
"loss": 5.4038,
|
|
"mean_token_accuracy": 0.17007039338350297,
|
|
"num_tokens": 32524409.0,
|
|
"step": 15670
|
|
},
|
|
{
|
|
"entropy": 5.747781991958618,
|
|
"epoch": 1.421897677793904,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004802571678502124,
|
|
"loss": 5.4553,
|
|
"mean_token_accuracy": 0.16455676704645156,
|
|
"num_tokens": 32534696.0,
|
|
"step": 15675
|
|
},
|
|
{
|
|
"entropy": 5.753636264801026,
|
|
"epoch": 1.4223512336719883,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.000480243911735172,
|
|
"loss": 5.4353,
|
|
"mean_token_accuracy": 0.16956795752048492,
|
|
"num_tokens": 32544782.0,
|
|
"step": 15680
|
|
},
|
|
{
|
|
"entropy": 5.678309345245362,
|
|
"epoch": 1.4228047895500726,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.00048023065137563534,
|
|
"loss": 5.4334,
|
|
"mean_token_accuracy": 0.16707800924777985,
|
|
"num_tokens": 32554818.0,
|
|
"step": 15685
|
|
},
|
|
{
|
|
"entropy": 5.684877347946167,
|
|
"epoch": 1.4232583454281569,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004802173867718764,
|
|
"loss": 5.4606,
|
|
"mean_token_accuracy": 0.17083225697278975,
|
|
"num_tokens": 32565007.0,
|
|
"step": 15690
|
|
},
|
|
{
|
|
"entropy": 5.6730822086334225,
|
|
"epoch": 1.423711901306241,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004802041179241697,
|
|
"loss": 5.4322,
|
|
"mean_token_accuracy": 0.16779104471206666,
|
|
"num_tokens": 32575657.0,
|
|
"step": 15695
|
|
},
|
|
{
|
|
"entropy": 5.667398452758789,
|
|
"epoch": 1.4241654571843252,
|
|
"grad_norm": 3.203125,
|
|
"learning_rate": 0.0004801908448327895,
|
|
"loss": 5.4549,
|
|
"mean_token_accuracy": 0.1669660747051239,
|
|
"num_tokens": 32586676.0,
|
|
"step": 15700
|
|
},
|
|
{
|
|
"entropy": 5.699419355392456,
|
|
"epoch": 1.4246190130624092,
|
|
"grad_norm": 3.09375,
|
|
"learning_rate": 0.0004801775674980103,
|
|
"loss": 5.3972,
|
|
"mean_token_accuracy": 0.1673714965581894,
|
|
"num_tokens": 32596191.0,
|
|
"step": 15705
|
|
},
|
|
{
|
|
"entropy": 5.716184425354004,
|
|
"epoch": 1.4250725689404935,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00048016428592010676,
|
|
"loss": 5.4704,
|
|
"mean_token_accuracy": 0.1621180698275566,
|
|
"num_tokens": 32607178.0,
|
|
"step": 15710
|
|
},
|
|
{
|
|
"entropy": 5.733434820175171,
|
|
"epoch": 1.4255261248185778,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.00048015100009935347,
|
|
"loss": 5.3796,
|
|
"mean_token_accuracy": 0.17195765674114227,
|
|
"num_tokens": 32617301.0,
|
|
"step": 15715
|
|
},
|
|
{
|
|
"entropy": 5.573254585266113,
|
|
"epoch": 1.4259796806966618,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004801377100360253,
|
|
"loss": 5.3948,
|
|
"mean_token_accuracy": 0.17385706752538682,
|
|
"num_tokens": 32627395.0,
|
|
"step": 15720
|
|
},
|
|
{
|
|
"entropy": 5.610266876220703,
|
|
"epoch": 1.426433236574746,
|
|
"grad_norm": 3.265625,
|
|
"learning_rate": 0.000480124415730397,
|
|
"loss": 5.424,
|
|
"mean_token_accuracy": 0.16927729174494743,
|
|
"num_tokens": 32638460.0,
|
|
"step": 15725
|
|
},
|
|
{
|
|
"entropy": 5.729848718643188,
|
|
"epoch": 1.4268867924528301,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004801111171827434,
|
|
"loss": 5.4863,
|
|
"mean_token_accuracy": 0.1682023748755455,
|
|
"num_tokens": 32649319.0,
|
|
"step": 15730
|
|
},
|
|
{
|
|
"entropy": 5.706736898422241,
|
|
"epoch": 1.4273403483309144,
|
|
"grad_norm": 3.15625,
|
|
"learning_rate": 0.0004800978143933398,
|
|
"loss": 5.4406,
|
|
"mean_token_accuracy": 0.1704932004213333,
|
|
"num_tokens": 32659976.0,
|
|
"step": 15735
|
|
},
|
|
{
|
|
"entropy": 5.6266333103179935,
|
|
"epoch": 1.4277939042089987,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.00048008450736246094,
|
|
"loss": 5.3491,
|
|
"mean_token_accuracy": 0.16656942814588546,
|
|
"num_tokens": 32670772.0,
|
|
"step": 15740
|
|
},
|
|
{
|
|
"entropy": 5.710064029693603,
|
|
"epoch": 1.4282474600870827,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.00048007119609038237,
|
|
"loss": 5.5008,
|
|
"mean_token_accuracy": 0.15849669873714448,
|
|
"num_tokens": 32682368.0,
|
|
"step": 15745
|
|
},
|
|
{
|
|
"entropy": 5.605566453933716,
|
|
"epoch": 1.428701015965167,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.00048005788057737907,
|
|
"loss": 5.3207,
|
|
"mean_token_accuracy": 0.1772705301642418,
|
|
"num_tokens": 32692649.0,
|
|
"step": 15750
|
|
},
|
|
{
|
|
"entropy": 5.669286775588989,
|
|
"epoch": 1.429154571843251,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004800445608237266,
|
|
"loss": 5.5522,
|
|
"mean_token_accuracy": 0.16629677563905715,
|
|
"num_tokens": 32704075.0,
|
|
"step": 15755
|
|
},
|
|
{
|
|
"entropy": 5.698248052597046,
|
|
"epoch": 1.4296081277213353,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.00048003123682970045,
|
|
"loss": 5.5497,
|
|
"mean_token_accuracy": 0.1590011015534401,
|
|
"num_tokens": 32714670.0,
|
|
"step": 15760
|
|
},
|
|
{
|
|
"entropy": 5.692164754867553,
|
|
"epoch": 1.4300616835994195,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.00048001790859557596,
|
|
"loss": 5.3776,
|
|
"mean_token_accuracy": 0.17560035288333892,
|
|
"num_tokens": 32724601.0,
|
|
"step": 15765
|
|
},
|
|
{
|
|
"entropy": 5.632785129547119,
|
|
"epoch": 1.4305152394775036,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004800045761216289,
|
|
"loss": 5.3575,
|
|
"mean_token_accuracy": 0.17378036677837372,
|
|
"num_tokens": 32735015.0,
|
|
"step": 15770
|
|
},
|
|
{
|
|
"entropy": 5.670291805267334,
|
|
"epoch": 1.4309687953555879,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.000479991239408135,
|
|
"loss": 5.4509,
|
|
"mean_token_accuracy": 0.17154160887002945,
|
|
"num_tokens": 32745899.0,
|
|
"step": 15775
|
|
},
|
|
{
|
|
"entropy": 5.662806034088135,
|
|
"epoch": 1.431422351233672,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.00047997789845537003,
|
|
"loss": 5.3988,
|
|
"mean_token_accuracy": 0.17458115071058272,
|
|
"num_tokens": 32756052.0,
|
|
"step": 15780
|
|
},
|
|
{
|
|
"entropy": 5.600939321517944,
|
|
"epoch": 1.4318759071117562,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004799645532636098,
|
|
"loss": 5.4096,
|
|
"mean_token_accuracy": 0.17252406477928162,
|
|
"num_tokens": 32767118.0,
|
|
"step": 15785
|
|
},
|
|
{
|
|
"entropy": 5.600234317779541,
|
|
"epoch": 1.4323294629898404,
|
|
"grad_norm": 3.203125,
|
|
"learning_rate": 0.00047995120383313044,
|
|
"loss": 5.2778,
|
|
"mean_token_accuracy": 0.18220913112163545,
|
|
"num_tokens": 32777069.0,
|
|
"step": 15790
|
|
},
|
|
{
|
|
"entropy": 5.705127811431884,
|
|
"epoch": 1.4327830188679245,
|
|
"grad_norm": 7.5625,
|
|
"learning_rate": 0.00047993785016420796,
|
|
"loss": 5.505,
|
|
"mean_token_accuracy": 0.16060466170310975,
|
|
"num_tokens": 32786967.0,
|
|
"step": 15795
|
|
},
|
|
{
|
|
"entropy": 5.666577339172363,
|
|
"epoch": 1.4332365747460087,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.00047992449225711854,
|
|
"loss": 5.3669,
|
|
"mean_token_accuracy": 0.1724660649895668,
|
|
"num_tokens": 32797563.0,
|
|
"step": 15800
|
|
},
|
|
{
|
|
"entropy": 5.622033596038818,
|
|
"epoch": 1.4336901306240928,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.00047991113011213837,
|
|
"loss": 5.3555,
|
|
"mean_token_accuracy": 0.1752047598361969,
|
|
"num_tokens": 32808730.0,
|
|
"step": 15805
|
|
},
|
|
{
|
|
"entropy": 5.606434726715088,
|
|
"epoch": 1.434143686502177,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004798977637295438,
|
|
"loss": 5.3382,
|
|
"mean_token_accuracy": 0.1796541377902031,
|
|
"num_tokens": 32818050.0,
|
|
"step": 15810
|
|
},
|
|
{
|
|
"entropy": 5.643495559692383,
|
|
"epoch": 1.4345972423802613,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004798843931096113,
|
|
"loss": 5.4089,
|
|
"mean_token_accuracy": 0.16689786016941072,
|
|
"num_tokens": 32828993.0,
|
|
"step": 15815
|
|
},
|
|
{
|
|
"entropy": 5.679268836975098,
|
|
"epoch": 1.4350507982583454,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.0004798710182526173,
|
|
"loss": 5.4013,
|
|
"mean_token_accuracy": 0.17752082645893097,
|
|
"num_tokens": 32839331.0,
|
|
"step": 15820
|
|
},
|
|
{
|
|
"entropy": 5.6197838306427,
|
|
"epoch": 1.4355043541364296,
|
|
"grad_norm": 3.671875,
|
|
"learning_rate": 0.00047985763915883847,
|
|
"loss": 5.41,
|
|
"mean_token_accuracy": 0.1645444944500923,
|
|
"num_tokens": 32849946.0,
|
|
"step": 15825
|
|
},
|
|
{
|
|
"entropy": 5.545694780349732,
|
|
"epoch": 1.4359579100145137,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004798442558285514,
|
|
"loss": 5.3553,
|
|
"mean_token_accuracy": 0.17636923044919967,
|
|
"num_tokens": 32859960.0,
|
|
"step": 15830
|
|
},
|
|
{
|
|
"entropy": 5.635845708847046,
|
|
"epoch": 1.436411465892598,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004798308682620329,
|
|
"loss": 5.375,
|
|
"mean_token_accuracy": 0.17063209563493728,
|
|
"num_tokens": 32870317.0,
|
|
"step": 15835
|
|
},
|
|
{
|
|
"entropy": 5.757098913192749,
|
|
"epoch": 1.4368650217706822,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.00047981747645955996,
|
|
"loss": 5.5142,
|
|
"mean_token_accuracy": 0.16291905269026757,
|
|
"num_tokens": 32880906.0,
|
|
"step": 15840
|
|
},
|
|
{
|
|
"entropy": 5.737436723709107,
|
|
"epoch": 1.4373185776487662,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004798040804214094,
|
|
"loss": 5.5617,
|
|
"mean_token_accuracy": 0.16629908233880997,
|
|
"num_tokens": 32891038.0,
|
|
"step": 15845
|
|
},
|
|
{
|
|
"entropy": 5.742472219467163,
|
|
"epoch": 1.4377721335268505,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004797906801478582,
|
|
"loss": 5.5139,
|
|
"mean_token_accuracy": 0.1728471964597702,
|
|
"num_tokens": 32901013.0,
|
|
"step": 15850
|
|
},
|
|
{
|
|
"entropy": 5.71471848487854,
|
|
"epoch": 1.4382256894049346,
|
|
"grad_norm": 4.3125,
|
|
"learning_rate": 0.0004797772756391836,
|
|
"loss": 5.4171,
|
|
"mean_token_accuracy": 0.17284273058176042,
|
|
"num_tokens": 32911592.0,
|
|
"step": 15855
|
|
},
|
|
{
|
|
"entropy": 5.60514349937439,
|
|
"epoch": 1.4386792452830188,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004797638668956627,
|
|
"loss": 5.351,
|
|
"mean_token_accuracy": 0.17432959079742433,
|
|
"num_tokens": 32922087.0,
|
|
"step": 15860
|
|
},
|
|
{
|
|
"entropy": 5.631624412536621,
|
|
"epoch": 1.439132801161103,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004797504539175729,
|
|
"loss": 5.4237,
|
|
"mean_token_accuracy": 0.1716810643672943,
|
|
"num_tokens": 32932039.0,
|
|
"step": 15865
|
|
},
|
|
{
|
|
"entropy": 5.62772126197815,
|
|
"epoch": 1.4395863570391874,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004797370367051915,
|
|
"loss": 5.4047,
|
|
"mean_token_accuracy": 0.17124366760253906,
|
|
"num_tokens": 32941896.0,
|
|
"step": 15870
|
|
},
|
|
{
|
|
"entropy": 5.642360782623291,
|
|
"epoch": 1.4400399129172714,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.000479723615258796,
|
|
"loss": 5.3984,
|
|
"mean_token_accuracy": 0.1626461088657379,
|
|
"num_tokens": 32951675.0,
|
|
"step": 15875
|
|
},
|
|
{
|
|
"entropy": 5.7276215076446535,
|
|
"epoch": 1.4404934687953557,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.00047971018957866396,
|
|
"loss": 5.4802,
|
|
"mean_token_accuracy": 0.17649320811033248,
|
|
"num_tokens": 32961378.0,
|
|
"step": 15880
|
|
},
|
|
{
|
|
"entropy": 5.7153294563293455,
|
|
"epoch": 1.4409470246734397,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.00047969675966507314,
|
|
"loss": 5.3772,
|
|
"mean_token_accuracy": 0.17163359820842744,
|
|
"num_tokens": 32971770.0,
|
|
"step": 15885
|
|
},
|
|
{
|
|
"entropy": 5.661875200271607,
|
|
"epoch": 1.441400580551524,
|
|
"grad_norm": 3.234375,
|
|
"learning_rate": 0.000479683325518301,
|
|
"loss": 5.4053,
|
|
"mean_token_accuracy": 0.1684826910495758,
|
|
"num_tokens": 32982934.0,
|
|
"step": 15890
|
|
},
|
|
{
|
|
"entropy": 5.607405042648315,
|
|
"epoch": 1.4418541364296082,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004796698871386257,
|
|
"loss": 5.4166,
|
|
"mean_token_accuracy": 0.16766930520534515,
|
|
"num_tokens": 32993252.0,
|
|
"step": 15895
|
|
},
|
|
{
|
|
"entropy": 5.651888513565064,
|
|
"epoch": 1.4423076923076923,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004796564445263249,
|
|
"loss": 5.4344,
|
|
"mean_token_accuracy": 0.1657497838139534,
|
|
"num_tokens": 33003610.0,
|
|
"step": 15900
|
|
},
|
|
{
|
|
"entropy": 5.722106456756592,
|
|
"epoch": 1.4427612481857766,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.00047964299768167665,
|
|
"loss": 5.3935,
|
|
"mean_token_accuracy": 0.17508534491062164,
|
|
"num_tokens": 33014037.0,
|
|
"step": 15905
|
|
},
|
|
{
|
|
"entropy": 5.666836977005005,
|
|
"epoch": 1.4432148040638606,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004796295466049591,
|
|
"loss": 5.4056,
|
|
"mean_token_accuracy": 0.16833537220954894,
|
|
"num_tokens": 33023299.0,
|
|
"step": 15910
|
|
},
|
|
{
|
|
"entropy": 5.724859094619751,
|
|
"epoch": 1.4436683599419449,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.00047961609129645036,
|
|
"loss": 5.4525,
|
|
"mean_token_accuracy": 0.16838695704936982,
|
|
"num_tokens": 33034194.0,
|
|
"step": 15915
|
|
},
|
|
{
|
|
"entropy": 5.671311235427856,
|
|
"epoch": 1.4441219158200291,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.00047960263175642867,
|
|
"loss": 5.3318,
|
|
"mean_token_accuracy": 0.17579748928546907,
|
|
"num_tokens": 33044715.0,
|
|
"step": 15920
|
|
},
|
|
{
|
|
"entropy": 5.59004054069519,
|
|
"epoch": 1.4445754716981132,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004795891679851724,
|
|
"loss": 5.3761,
|
|
"mean_token_accuracy": 0.1769031971693039,
|
|
"num_tokens": 33055214.0,
|
|
"step": 15925
|
|
},
|
|
{
|
|
"entropy": 5.647002029418945,
|
|
"epoch": 1.4450290275761974,
|
|
"grad_norm": 6.25,
|
|
"learning_rate": 0.0004795756999829601,
|
|
"loss": 5.3861,
|
|
"mean_token_accuracy": 0.17465085983276368,
|
|
"num_tokens": 33065026.0,
|
|
"step": 15930
|
|
},
|
|
{
|
|
"entropy": 5.7132641792297365,
|
|
"epoch": 1.4454825834542815,
|
|
"grad_norm": 3.296875,
|
|
"learning_rate": 0.00047956222775007016,
|
|
"loss": 5.4513,
|
|
"mean_token_accuracy": 0.16689809709787368,
|
|
"num_tokens": 33075138.0,
|
|
"step": 15935
|
|
},
|
|
{
|
|
"entropy": 5.712882375717163,
|
|
"epoch": 1.4459361393323658,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004795487512867812,
|
|
"loss": 5.4477,
|
|
"mean_token_accuracy": 0.17068978399038315,
|
|
"num_tokens": 33086625.0,
|
|
"step": 15940
|
|
},
|
|
{
|
|
"entropy": 5.696731758117676,
|
|
"epoch": 1.44638969521045,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.00047953527059337194,
|
|
"loss": 5.4833,
|
|
"mean_token_accuracy": 0.1649426817893982,
|
|
"num_tokens": 33097076.0,
|
|
"step": 15945
|
|
},
|
|
{
|
|
"entropy": 5.642807388305664,
|
|
"epoch": 1.446843251088534,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.0004795217856701212,
|
|
"loss": 5.408,
|
|
"mean_token_accuracy": 0.1698189616203308,
|
|
"num_tokens": 33107168.0,
|
|
"step": 15950
|
|
},
|
|
{
|
|
"entropy": 5.740230321884155,
|
|
"epoch": 1.4472968069666183,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.00047950829651730774,
|
|
"loss": 5.4627,
|
|
"mean_token_accuracy": 0.1677447095513344,
|
|
"num_tokens": 33117862.0,
|
|
"step": 15955
|
|
},
|
|
{
|
|
"entropy": 5.6486626148223875,
|
|
"epoch": 1.4477503628447024,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004794948031352107,
|
|
"loss": 5.3727,
|
|
"mean_token_accuracy": 0.1727929949760437,
|
|
"num_tokens": 33127144.0,
|
|
"step": 15960
|
|
},
|
|
{
|
|
"entropy": 5.703910827636719,
|
|
"epoch": 1.4482039187227866,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.00047948130552410897,
|
|
"loss": 5.5487,
|
|
"mean_token_accuracy": 0.1609547182917595,
|
|
"num_tokens": 33139180.0,
|
|
"step": 15965
|
|
},
|
|
{
|
|
"entropy": 5.750797843933105,
|
|
"epoch": 1.448657474600871,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.00047946780368428175,
|
|
"loss": 5.4323,
|
|
"mean_token_accuracy": 0.1670147269964218,
|
|
"num_tokens": 33149467.0,
|
|
"step": 15970
|
|
},
|
|
{
|
|
"entropy": 5.648169326782226,
|
|
"epoch": 1.449111030478955,
|
|
"grad_norm": 3.90625,
|
|
"learning_rate": 0.0004794542976160081,
|
|
"loss": 5.2832,
|
|
"mean_token_accuracy": 0.18440093845129013,
|
|
"num_tokens": 33158752.0,
|
|
"step": 15975
|
|
},
|
|
{
|
|
"entropy": 5.612135934829712,
|
|
"epoch": 1.4495645863570392,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.00047944078731956765,
|
|
"loss": 5.3529,
|
|
"mean_token_accuracy": 0.17740466743707656,
|
|
"num_tokens": 33168242.0,
|
|
"step": 15980
|
|
},
|
|
{
|
|
"entropy": 5.592283296585083,
|
|
"epoch": 1.4500181422351233,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.00047942727279523957,
|
|
"loss": 5.3718,
|
|
"mean_token_accuracy": 0.17053792774677276,
|
|
"num_tokens": 33179134.0,
|
|
"step": 15985
|
|
},
|
|
{
|
|
"entropy": 5.6713423252105715,
|
|
"epoch": 1.4504716981132075,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004794137540433034,
|
|
"loss": 5.466,
|
|
"mean_token_accuracy": 0.16407588124275208,
|
|
"num_tokens": 33188388.0,
|
|
"step": 15990
|
|
},
|
|
{
|
|
"entropy": 5.711167669296264,
|
|
"epoch": 1.4509252539912918,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004794002310640386,
|
|
"loss": 5.3912,
|
|
"mean_token_accuracy": 0.17118203341960908,
|
|
"num_tokens": 33198750.0,
|
|
"step": 15995
|
|
},
|
|
{
|
|
"entropy": 5.803665256500244,
|
|
"epoch": 1.4513788098693758,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.00047938670385772503,
|
|
"loss": 5.5056,
|
|
"mean_token_accuracy": 0.1595338314771652,
|
|
"num_tokens": 33209532.0,
|
|
"step": 16000
|
|
},
|
|
{
|
|
"entropy": 5.66889328956604,
|
|
"epoch": 1.45183236574746,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.00047937317242464244,
|
|
"loss": 5.3904,
|
|
"mean_token_accuracy": 0.17303771823644637,
|
|
"num_tokens": 33219675.0,
|
|
"step": 16005
|
|
},
|
|
{
|
|
"entropy": 5.688104963302612,
|
|
"epoch": 1.4522859216255442,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.0004793596367650704,
|
|
"loss": 5.4897,
|
|
"mean_token_accuracy": 0.1644310623407364,
|
|
"num_tokens": 33230919.0,
|
|
"step": 16010
|
|
},
|
|
{
|
|
"entropy": 5.68540325164795,
|
|
"epoch": 1.4527394775036284,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004793460968792891,
|
|
"loss": 5.3774,
|
|
"mean_token_accuracy": 0.1797064334154129,
|
|
"num_tokens": 33241146.0,
|
|
"step": 16015
|
|
},
|
|
{
|
|
"entropy": 5.694696855545044,
|
|
"epoch": 1.4531930333817127,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.00047933255276757836,
|
|
"loss": 5.4309,
|
|
"mean_token_accuracy": 0.16857415139675141,
|
|
"num_tokens": 33251434.0,
|
|
"step": 16020
|
|
},
|
|
{
|
|
"entropy": 5.709229516983032,
|
|
"epoch": 1.4536465892597967,
|
|
"grad_norm": 6.75,
|
|
"learning_rate": 0.0004793190044302184,
|
|
"loss": 5.5285,
|
|
"mean_token_accuracy": 0.15956925302743913,
|
|
"num_tokens": 33261868.0,
|
|
"step": 16025
|
|
},
|
|
{
|
|
"entropy": 5.690166568756103,
|
|
"epoch": 1.454100145137881,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.00047930545186748936,
|
|
"loss": 5.3405,
|
|
"mean_token_accuracy": 0.17178133726119996,
|
|
"num_tokens": 33271798.0,
|
|
"step": 16030
|
|
},
|
|
{
|
|
"entropy": 5.653804445266724,
|
|
"epoch": 1.454553701015965,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.00047929189507967153,
|
|
"loss": 5.4537,
|
|
"mean_token_accuracy": 0.16889558136463165,
|
|
"num_tokens": 33282614.0,
|
|
"step": 16035
|
|
},
|
|
{
|
|
"entropy": 5.593717098236084,
|
|
"epoch": 1.4550072568940493,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.00047927833406704516,
|
|
"loss": 5.3719,
|
|
"mean_token_accuracy": 0.167829267680645,
|
|
"num_tokens": 33292906.0,
|
|
"step": 16040
|
|
},
|
|
{
|
|
"entropy": 5.641296148300171,
|
|
"epoch": 1.4554608127721336,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004792647688298909,
|
|
"loss": 5.372,
|
|
"mean_token_accuracy": 0.1716025799512863,
|
|
"num_tokens": 33302720.0,
|
|
"step": 16045
|
|
},
|
|
{
|
|
"entropy": 5.62772855758667,
|
|
"epoch": 1.4559143686502178,
|
|
"grad_norm": 3.40625,
|
|
"learning_rate": 0.0004792511993684891,
|
|
"loss": 5.3573,
|
|
"mean_token_accuracy": 0.17477886974811555,
|
|
"num_tokens": 33312959.0,
|
|
"step": 16050
|
|
},
|
|
{
|
|
"entropy": 5.627491664886475,
|
|
"epoch": 1.4563679245283019,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.00047923762568312053,
|
|
"loss": 5.3177,
|
|
"mean_token_accuracy": 0.17603887915611266,
|
|
"num_tokens": 33322737.0,
|
|
"step": 16055
|
|
},
|
|
{
|
|
"entropy": 5.610012054443359,
|
|
"epoch": 1.4568214804063861,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004792240477740657,
|
|
"loss": 5.3263,
|
|
"mean_token_accuracy": 0.18020515739917756,
|
|
"num_tokens": 33333185.0,
|
|
"step": 16060
|
|
},
|
|
{
|
|
"entropy": 5.686456727981567,
|
|
"epoch": 1.4572750362844702,
|
|
"grad_norm": 3.390625,
|
|
"learning_rate": 0.0004792104656416056,
|
|
"loss": 5.4481,
|
|
"mean_token_accuracy": 0.16517818868160247,
|
|
"num_tokens": 33343414.0,
|
|
"step": 16065
|
|
},
|
|
{
|
|
"entropy": 5.674755430221557,
|
|
"epoch": 1.4577285921625545,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.00047919687928602104,
|
|
"loss": 5.3838,
|
|
"mean_token_accuracy": 0.1714176908135414,
|
|
"num_tokens": 33352527.0,
|
|
"step": 16070
|
|
},
|
|
{
|
|
"entropy": 5.700991678237915,
|
|
"epoch": 1.4581821480406387,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.00047918328870759293,
|
|
"loss": 5.4497,
|
|
"mean_token_accuracy": 0.16451606005430222,
|
|
"num_tokens": 33363526.0,
|
|
"step": 16075
|
|
},
|
|
{
|
|
"entropy": 5.659315347671509,
|
|
"epoch": 1.4586357039187228,
|
|
"grad_norm": 3.234375,
|
|
"learning_rate": 0.0004791696939066024,
|
|
"loss": 5.4673,
|
|
"mean_token_accuracy": 0.17120738476514816,
|
|
"num_tokens": 33374302.0,
|
|
"step": 16080
|
|
},
|
|
{
|
|
"entropy": 5.665696525573731,
|
|
"epoch": 1.459089259796807,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.0004791560948833306,
|
|
"loss": 5.4256,
|
|
"mean_token_accuracy": 0.17265185713768005,
|
|
"num_tokens": 33384786.0,
|
|
"step": 16085
|
|
},
|
|
{
|
|
"entropy": 5.690181636810303,
|
|
"epoch": 1.459542815674891,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004791424916380586,
|
|
"loss": 5.4166,
|
|
"mean_token_accuracy": 0.17830681055784225,
|
|
"num_tokens": 33394464.0,
|
|
"step": 16090
|
|
},
|
|
{
|
|
"entropy": 5.607785654067993,
|
|
"epoch": 1.4599963715529753,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.000479128884171068,
|
|
"loss": 5.4332,
|
|
"mean_token_accuracy": 0.16649201810359954,
|
|
"num_tokens": 33405476.0,
|
|
"step": 16095
|
|
},
|
|
{
|
|
"entropy": 5.634016609191894,
|
|
"epoch": 1.4604499274310596,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.00047911527248264003,
|
|
"loss": 5.4579,
|
|
"mean_token_accuracy": 0.16773583889007568,
|
|
"num_tokens": 33415758.0,
|
|
"step": 16100
|
|
},
|
|
{
|
|
"entropy": 5.648102903366089,
|
|
"epoch": 1.4609034833091437,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.00047910165657305613,
|
|
"loss": 5.4161,
|
|
"mean_token_accuracy": 0.17153127044439315,
|
|
"num_tokens": 33424845.0,
|
|
"step": 16105
|
|
},
|
|
{
|
|
"entropy": 5.715788888931274,
|
|
"epoch": 1.461357039187228,
|
|
"grad_norm": 3.96875,
|
|
"learning_rate": 0.00047908803644259804,
|
|
"loss": 5.454,
|
|
"mean_token_accuracy": 0.16871043890714646,
|
|
"num_tokens": 33435928.0,
|
|
"step": 16110
|
|
},
|
|
{
|
|
"entropy": 5.682786130905152,
|
|
"epoch": 1.461810595065312,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.00047907441209154726,
|
|
"loss": 5.3617,
|
|
"mean_token_accuracy": 0.16772275418043137,
|
|
"num_tokens": 33447307.0,
|
|
"step": 16115
|
|
},
|
|
{
|
|
"entropy": 5.658818531036377,
|
|
"epoch": 1.4622641509433962,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.00047906078352018575,
|
|
"loss": 5.4275,
|
|
"mean_token_accuracy": 0.16872664988040925,
|
|
"num_tokens": 33458116.0,
|
|
"step": 16120
|
|
},
|
|
{
|
|
"entropy": 5.551340246200562,
|
|
"epoch": 1.4627177068214805,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004790471507287952,
|
|
"loss": 5.2914,
|
|
"mean_token_accuracy": 0.1764333263039589,
|
|
"num_tokens": 33469065.0,
|
|
"step": 16125
|
|
},
|
|
{
|
|
"entropy": 5.677801847457886,
|
|
"epoch": 1.4631712626995645,
|
|
"grad_norm": 3.359375,
|
|
"learning_rate": 0.00047903351371765757,
|
|
"loss": 5.4043,
|
|
"mean_token_accuracy": 0.17442615926265717,
|
|
"num_tokens": 33479118.0,
|
|
"step": 16130
|
|
},
|
|
{
|
|
"entropy": 5.733373498916626,
|
|
"epoch": 1.4636248185776488,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.00047901987248705484,
|
|
"loss": 5.4412,
|
|
"mean_token_accuracy": 0.1721336930990219,
|
|
"num_tokens": 33489642.0,
|
|
"step": 16135
|
|
},
|
|
{
|
|
"entropy": 5.6405439376831055,
|
|
"epoch": 1.4640783744557329,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004790062270372693,
|
|
"loss": 5.441,
|
|
"mean_token_accuracy": 0.1666528284549713,
|
|
"num_tokens": 33499771.0,
|
|
"step": 16140
|
|
},
|
|
{
|
|
"entropy": 5.589552211761474,
|
|
"epoch": 1.4645319303338171,
|
|
"grad_norm": 3.875,
|
|
"learning_rate": 0.0004789925773685828,
|
|
"loss": 5.3993,
|
|
"mean_token_accuracy": 0.1702257886528969,
|
|
"num_tokens": 33509975.0,
|
|
"step": 16145
|
|
},
|
|
{
|
|
"entropy": 5.677236413955688,
|
|
"epoch": 1.4649854862119014,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004789789234812779,
|
|
"loss": 5.4552,
|
|
"mean_token_accuracy": 0.16531885415315628,
|
|
"num_tokens": 33520017.0,
|
|
"step": 16150
|
|
},
|
|
{
|
|
"entropy": 5.69922022819519,
|
|
"epoch": 1.4654390420899854,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.00047896526537563686,
|
|
"loss": 5.5061,
|
|
"mean_token_accuracy": 0.16388868167996407,
|
|
"num_tokens": 33531977.0,
|
|
"step": 16155
|
|
},
|
|
{
|
|
"entropy": 5.6679198265075685,
|
|
"epoch": 1.4658925979680697,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.00047895160305194223,
|
|
"loss": 5.4401,
|
|
"mean_token_accuracy": 0.17290413826704026,
|
|
"num_tokens": 33543660.0,
|
|
"step": 16160
|
|
},
|
|
{
|
|
"entropy": 5.656180715560913,
|
|
"epoch": 1.4663461538461537,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004789379365104764,
|
|
"loss": 5.3903,
|
|
"mean_token_accuracy": 0.1741354301571846,
|
|
"num_tokens": 33553814.0,
|
|
"step": 16165
|
|
},
|
|
{
|
|
"entropy": 5.7217058658599855,
|
|
"epoch": 1.466799709724238,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004789242657515221,
|
|
"loss": 5.4111,
|
|
"mean_token_accuracy": 0.17557623684406282,
|
|
"num_tokens": 33564250.0,
|
|
"step": 16170
|
|
},
|
|
{
|
|
"entropy": 5.635580921173096,
|
|
"epoch": 1.4672532656023223,
|
|
"grad_norm": 2.875,
|
|
"learning_rate": 0.0004789105907753621,
|
|
"loss": 5.4111,
|
|
"mean_token_accuracy": 0.169688118994236,
|
|
"num_tokens": 33574755.0,
|
|
"step": 16175
|
|
},
|
|
{
|
|
"entropy": 5.623884010314941,
|
|
"epoch": 1.4677068214804063,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.000478896911582279,
|
|
"loss": 5.338,
|
|
"mean_token_accuracy": 0.17514874190092086,
|
|
"num_tokens": 33585268.0,
|
|
"step": 16180
|
|
},
|
|
{
|
|
"entropy": 5.673941802978516,
|
|
"epoch": 1.4681603773584906,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004788832281725558,
|
|
"loss": 5.4672,
|
|
"mean_token_accuracy": 0.1732576996088028,
|
|
"num_tokens": 33595753.0,
|
|
"step": 16185
|
|
},
|
|
{
|
|
"entropy": 5.637123727798462,
|
|
"epoch": 1.4686139332365746,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004788695405464755,
|
|
"loss": 5.3252,
|
|
"mean_token_accuracy": 0.1780784994363785,
|
|
"num_tokens": 33605270.0,
|
|
"step": 16190
|
|
},
|
|
{
|
|
"entropy": 5.637136173248291,
|
|
"epoch": 1.469067489114659,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.00047885584870432127,
|
|
"loss": 5.4401,
|
|
"mean_token_accuracy": 0.17039285749197006,
|
|
"num_tokens": 33615096.0,
|
|
"step": 16195
|
|
},
|
|
{
|
|
"entropy": 5.62698712348938,
|
|
"epoch": 1.4695210449927432,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.00047884215264637606,
|
|
"loss": 5.3346,
|
|
"mean_token_accuracy": 0.17280481606721879,
|
|
"num_tokens": 33624770.0,
|
|
"step": 16200
|
|
},
|
|
{
|
|
"entropy": 5.697276782989502,
|
|
"epoch": 1.4699746008708272,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004788284523729232,
|
|
"loss": 5.4648,
|
|
"mean_token_accuracy": 0.1670017123222351,
|
|
"num_tokens": 33634545.0,
|
|
"step": 16205
|
|
},
|
|
{
|
|
"entropy": 5.7432389736175535,
|
|
"epoch": 1.4704281567489115,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.00047881474788424595,
|
|
"loss": 5.4375,
|
|
"mean_token_accuracy": 0.17102768123149872,
|
|
"num_tokens": 33644950.0,
|
|
"step": 16210
|
|
},
|
|
{
|
|
"entropy": 5.69329948425293,
|
|
"epoch": 1.4708817126269955,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.00047880103918062776,
|
|
"loss": 5.3747,
|
|
"mean_token_accuracy": 0.17394309490919113,
|
|
"num_tokens": 33654369.0,
|
|
"step": 16215
|
|
},
|
|
{
|
|
"entropy": 5.568559551239014,
|
|
"epoch": 1.4713352685050798,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.00047878732626235225,
|
|
"loss": 5.4182,
|
|
"mean_token_accuracy": 0.16677456349134445,
|
|
"num_tokens": 33664687.0,
|
|
"step": 16220
|
|
},
|
|
{
|
|
"entropy": 5.6562131404876705,
|
|
"epoch": 1.471788824383164,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004787736091297028,
|
|
"loss": 5.3898,
|
|
"mean_token_accuracy": 0.17816735804080963,
|
|
"num_tokens": 33675832.0,
|
|
"step": 16225
|
|
},
|
|
{
|
|
"entropy": 5.7310200214385985,
|
|
"epoch": 1.4722423802612483,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004787598877829633,
|
|
"loss": 5.46,
|
|
"mean_token_accuracy": 0.17091700285673142,
|
|
"num_tokens": 33686788.0,
|
|
"step": 16230
|
|
},
|
|
{
|
|
"entropy": 5.645125770568848,
|
|
"epoch": 1.4726959361393324,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004787461622224173,
|
|
"loss": 5.3747,
|
|
"mean_token_accuracy": 0.17359818369150162,
|
|
"num_tokens": 33696384.0,
|
|
"step": 16235
|
|
},
|
|
{
|
|
"entropy": 5.628522968292236,
|
|
"epoch": 1.4731494920174166,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004787324324483488,
|
|
"loss": 5.392,
|
|
"mean_token_accuracy": 0.17510557174682617,
|
|
"num_tokens": 33707758.0,
|
|
"step": 16240
|
|
},
|
|
{
|
|
"entropy": 5.658224391937256,
|
|
"epoch": 1.4736030478955007,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004787186984610416,
|
|
"loss": 5.3521,
|
|
"mean_token_accuracy": 0.1747954860329628,
|
|
"num_tokens": 33717747.0,
|
|
"step": 16245
|
|
},
|
|
{
|
|
"entropy": 5.613659000396728,
|
|
"epoch": 1.474056603773585,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.00047870496026077984,
|
|
"loss": 5.3659,
|
|
"mean_token_accuracy": 0.16818437725305557,
|
|
"num_tokens": 33727960.0,
|
|
"step": 16250
|
|
},
|
|
{
|
|
"entropy": 5.593056583404541,
|
|
"epoch": 1.4745101596516692,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.0004786912178478476,
|
|
"loss": 5.3354,
|
|
"mean_token_accuracy": 0.17685847282409667,
|
|
"num_tokens": 33738874.0,
|
|
"step": 16255
|
|
},
|
|
{
|
|
"entropy": 5.606376218795776,
|
|
"epoch": 1.4749637155297532,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004786774712225291,
|
|
"loss": 5.3647,
|
|
"mean_token_accuracy": 0.1758086249232292,
|
|
"num_tokens": 33749071.0,
|
|
"step": 16260
|
|
},
|
|
{
|
|
"entropy": 5.616236877441406,
|
|
"epoch": 1.4754172714078375,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004786637203851086,
|
|
"loss": 5.3818,
|
|
"mean_token_accuracy": 0.16859227120876313,
|
|
"num_tokens": 33759509.0,
|
|
"step": 16265
|
|
},
|
|
{
|
|
"entropy": 5.729612684249878,
|
|
"epoch": 1.4758708272859216,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004786499653358705,
|
|
"loss": 5.4458,
|
|
"mean_token_accuracy": 0.16829277575016022,
|
|
"num_tokens": 33769974.0,
|
|
"step": 16270
|
|
},
|
|
{
|
|
"entropy": 5.7238648414611815,
|
|
"epoch": 1.4763243831640058,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004786362060750991,
|
|
"loss": 5.438,
|
|
"mean_token_accuracy": 0.1710064761340618,
|
|
"num_tokens": 33780403.0,
|
|
"step": 16275
|
|
},
|
|
{
|
|
"entropy": 5.665211629867554,
|
|
"epoch": 1.47677793904209,
|
|
"grad_norm": 3.15625,
|
|
"learning_rate": 0.00047862244260307913,
|
|
"loss": 5.4945,
|
|
"mean_token_accuracy": 0.16881189346313477,
|
|
"num_tokens": 33791364.0,
|
|
"step": 16280
|
|
},
|
|
{
|
|
"entropy": 5.6299046039581295,
|
|
"epoch": 1.4772314949201741,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004786086749200951,
|
|
"loss": 5.3931,
|
|
"mean_token_accuracy": 0.17134786695241927,
|
|
"num_tokens": 33801964.0,
|
|
"step": 16285
|
|
},
|
|
{
|
|
"entropy": 5.715665006637574,
|
|
"epoch": 1.4776850507982584,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004785949030264319,
|
|
"loss": 5.4215,
|
|
"mean_token_accuracy": 0.1752404049038887,
|
|
"num_tokens": 33813132.0,
|
|
"step": 16290
|
|
},
|
|
{
|
|
"entropy": 5.680302524566651,
|
|
"epoch": 1.4781386066763424,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004785811269223741,
|
|
"loss": 5.3804,
|
|
"mean_token_accuracy": 0.1807881161570549,
|
|
"num_tokens": 33823069.0,
|
|
"step": 16295
|
|
},
|
|
{
|
|
"entropy": 5.6748566150665285,
|
|
"epoch": 1.4785921625544267,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004785673466082068,
|
|
"loss": 5.3783,
|
|
"mean_token_accuracy": 0.17184956073760987,
|
|
"num_tokens": 33832626.0,
|
|
"step": 16300
|
|
},
|
|
{
|
|
"entropy": 5.59094271659851,
|
|
"epoch": 1.479045718432511,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.00047855356208421484,
|
|
"loss": 5.3524,
|
|
"mean_token_accuracy": 0.17500858753919601,
|
|
"num_tokens": 33843384.0,
|
|
"step": 16305
|
|
},
|
|
{
|
|
"entropy": 5.622916889190674,
|
|
"epoch": 1.479499274310595,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004785397733506834,
|
|
"loss": 5.3776,
|
|
"mean_token_accuracy": 0.17020393311977386,
|
|
"num_tokens": 33854286.0,
|
|
"step": 16310
|
|
},
|
|
{
|
|
"entropy": 5.638805866241455,
|
|
"epoch": 1.4799528301886793,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004785259804078976,
|
|
"loss": 5.3417,
|
|
"mean_token_accuracy": 0.17736321836709976,
|
|
"num_tokens": 33863379.0,
|
|
"step": 16315
|
|
},
|
|
{
|
|
"entropy": 5.728190565109253,
|
|
"epoch": 1.4804063860667633,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004785121832561426,
|
|
"loss": 5.5822,
|
|
"mean_token_accuracy": 0.15954595133662225,
|
|
"num_tokens": 33875641.0,
|
|
"step": 16320
|
|
},
|
|
{
|
|
"entropy": 5.639981698989868,
|
|
"epoch": 1.4808599419448476,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.00047849838189570375,
|
|
"loss": 5.3458,
|
|
"mean_token_accuracy": 0.17915641367435456,
|
|
"num_tokens": 33885023.0,
|
|
"step": 16325
|
|
},
|
|
{
|
|
"entropy": 5.704492378234863,
|
|
"epoch": 1.4813134978229319,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004784845763268666,
|
|
"loss": 5.4857,
|
|
"mean_token_accuracy": 0.15945612043142318,
|
|
"num_tokens": 33895562.0,
|
|
"step": 16330
|
|
},
|
|
{
|
|
"entropy": 5.6507896900177,
|
|
"epoch": 1.481767053701016,
|
|
"grad_norm": 3.46875,
|
|
"learning_rate": 0.0004784707665499165,
|
|
"loss": 5.438,
|
|
"mean_token_accuracy": 0.17200744301080703,
|
|
"num_tokens": 33907095.0,
|
|
"step": 16335
|
|
},
|
|
{
|
|
"entropy": 5.592977046966553,
|
|
"epoch": 1.4822206095791002,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004784569525651391,
|
|
"loss": 5.2444,
|
|
"mean_token_accuracy": 0.1795291408896446,
|
|
"num_tokens": 33917475.0,
|
|
"step": 16340
|
|
},
|
|
{
|
|
"entropy": 5.635351991653442,
|
|
"epoch": 1.4826741654571842,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.00047844313437282005,
|
|
"loss": 5.401,
|
|
"mean_token_accuracy": 0.17188327014446259,
|
|
"num_tokens": 33927740.0,
|
|
"step": 16345
|
|
},
|
|
{
|
|
"entropy": 5.629772567749024,
|
|
"epoch": 1.4831277213352685,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.00047842931197324525,
|
|
"loss": 5.3413,
|
|
"mean_token_accuracy": 0.17079071700572968,
|
|
"num_tokens": 33937416.0,
|
|
"step": 16350
|
|
},
|
|
{
|
|
"entropy": 5.560959434509277,
|
|
"epoch": 1.4835812772133528,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.00047841548536670033,
|
|
"loss": 5.3037,
|
|
"mean_token_accuracy": 0.17871298193931578,
|
|
"num_tokens": 33946968.0,
|
|
"step": 16355
|
|
},
|
|
{
|
|
"entropy": 5.665979719161987,
|
|
"epoch": 1.4840348330914368,
|
|
"grad_norm": 3.5,
|
|
"learning_rate": 0.00047840165455347136,
|
|
"loss": 5.4587,
|
|
"mean_token_accuracy": 0.16613715887069702,
|
|
"num_tokens": 33957877.0,
|
|
"step": 16360
|
|
},
|
|
{
|
|
"entropy": 5.670029926300049,
|
|
"epoch": 1.484488388969521,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.00047838781953384436,
|
|
"loss": 5.4438,
|
|
"mean_token_accuracy": 0.17064746618270873,
|
|
"num_tokens": 33967890.0,
|
|
"step": 16365
|
|
},
|
|
{
|
|
"entropy": 5.596904182434082,
|
|
"epoch": 1.484941944847605,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004783739803081054,
|
|
"loss": 5.3835,
|
|
"mean_token_accuracy": 0.17397388964891433,
|
|
"num_tokens": 33977117.0,
|
|
"step": 16370
|
|
},
|
|
{
|
|
"entropy": 5.700948905944824,
|
|
"epoch": 1.4853955007256894,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.00047836013687654075,
|
|
"loss": 5.4803,
|
|
"mean_token_accuracy": 0.16971482187509537,
|
|
"num_tokens": 33986943.0,
|
|
"step": 16375
|
|
},
|
|
{
|
|
"entropy": 5.653525972366333,
|
|
"epoch": 1.4858490566037736,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.00047834628923943654,
|
|
"loss": 5.3822,
|
|
"mean_token_accuracy": 0.1744118630886078,
|
|
"num_tokens": 33996499.0,
|
|
"step": 16380
|
|
},
|
|
{
|
|
"entropy": 5.7164051055908205,
|
|
"epoch": 1.4863026124818577,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004783324373970793,
|
|
"loss": 5.4841,
|
|
"mean_token_accuracy": 0.1707533061504364,
|
|
"num_tokens": 34006749.0,
|
|
"step": 16385
|
|
},
|
|
{
|
|
"entropy": 5.7368104457855225,
|
|
"epoch": 1.486756168359942,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004783185813497555,
|
|
"loss": 5.5028,
|
|
"mean_token_accuracy": 0.1603444531559944,
|
|
"num_tokens": 34017194.0,
|
|
"step": 16390
|
|
},
|
|
{
|
|
"entropy": 5.721175670623779,
|
|
"epoch": 1.487209724238026,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004783047210977516,
|
|
"loss": 5.4083,
|
|
"mean_token_accuracy": 0.17377747297286988,
|
|
"num_tokens": 34027386.0,
|
|
"step": 16395
|
|
},
|
|
{
|
|
"entropy": 5.742207145690918,
|
|
"epoch": 1.4876632801161103,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.00047829085664135424,
|
|
"loss": 5.465,
|
|
"mean_token_accuracy": 0.16687700003385544,
|
|
"num_tokens": 34037540.0,
|
|
"step": 16400
|
|
},
|
|
{
|
|
"entropy": 5.6692585945129395,
|
|
"epoch": 1.4881168359941945,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.00047827698798085015,
|
|
"loss": 5.4162,
|
|
"mean_token_accuracy": 0.17182037979364395,
|
|
"num_tokens": 34048008.0,
|
|
"step": 16405
|
|
},
|
|
{
|
|
"entropy": 5.686663818359375,
|
|
"epoch": 1.4885703918722788,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004782631151165262,
|
|
"loss": 5.435,
|
|
"mean_token_accuracy": 0.16636475026607514,
|
|
"num_tokens": 34058009.0,
|
|
"step": 16410
|
|
},
|
|
{
|
|
"entropy": 5.708872890472412,
|
|
"epoch": 1.4890239477503628,
|
|
"grad_norm": 3.96875,
|
|
"learning_rate": 0.00047824923804866914,
|
|
"loss": 5.3892,
|
|
"mean_token_accuracy": 0.16933866888284682,
|
|
"num_tokens": 34067625.0,
|
|
"step": 16415
|
|
},
|
|
{
|
|
"entropy": 5.579290914535522,
|
|
"epoch": 1.4894775036284469,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.00047823535677756607,
|
|
"loss": 5.3789,
|
|
"mean_token_accuracy": 0.165143920481205,
|
|
"num_tokens": 34077349.0,
|
|
"step": 16420
|
|
},
|
|
{
|
|
"entropy": 5.685181331634522,
|
|
"epoch": 1.4899310595065312,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004782214713035041,
|
|
"loss": 5.5118,
|
|
"mean_token_accuracy": 0.16662946492433547,
|
|
"num_tokens": 34088636.0,
|
|
"step": 16425
|
|
},
|
|
{
|
|
"entropy": 5.758614730834961,
|
|
"epoch": 1.4903846153846154,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.00047820758162677026,
|
|
"loss": 5.4117,
|
|
"mean_token_accuracy": 0.1764942839741707,
|
|
"num_tokens": 34098806.0,
|
|
"step": 16430
|
|
},
|
|
{
|
|
"entropy": 5.688050603866577,
|
|
"epoch": 1.4908381712626997,
|
|
"grad_norm": 4.15625,
|
|
"learning_rate": 0.00047819368774765187,
|
|
"loss": 5.4418,
|
|
"mean_token_accuracy": 0.17239126265048982,
|
|
"num_tokens": 34109713.0,
|
|
"step": 16435
|
|
},
|
|
{
|
|
"entropy": 5.584250116348267,
|
|
"epoch": 1.4912917271407837,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.00047817978966643626,
|
|
"loss": 5.3965,
|
|
"mean_token_accuracy": 0.1738654762506485,
|
|
"num_tokens": 34119585.0,
|
|
"step": 16440
|
|
},
|
|
{
|
|
"entropy": 5.714080286026001,
|
|
"epoch": 1.491745283018868,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004781658873834108,
|
|
"loss": 5.4212,
|
|
"mean_token_accuracy": 0.16614149808883666,
|
|
"num_tokens": 34131245.0,
|
|
"step": 16445
|
|
},
|
|
{
|
|
"entropy": 5.693969964981079,
|
|
"epoch": 1.492198838896952,
|
|
"grad_norm": 3.21875,
|
|
"learning_rate": 0.00047815198089886296,
|
|
"loss": 5.4057,
|
|
"mean_token_accuracy": 0.17329985797405242,
|
|
"num_tokens": 34141229.0,
|
|
"step": 16450
|
|
},
|
|
{
|
|
"entropy": 5.648536157608032,
|
|
"epoch": 1.4926523947750363,
|
|
"grad_norm": 3.140625,
|
|
"learning_rate": 0.0004781380702130805,
|
|
"loss": 5.4494,
|
|
"mean_token_accuracy": 0.16873722523450851,
|
|
"num_tokens": 34151781.0,
|
|
"step": 16455
|
|
},
|
|
{
|
|
"entropy": 5.67364993095398,
|
|
"epoch": 1.4931059506531206,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.00047812415532635087,
|
|
"loss": 5.3863,
|
|
"mean_token_accuracy": 0.17272000163793563,
|
|
"num_tokens": 34162305.0,
|
|
"step": 16460
|
|
},
|
|
{
|
|
"entropy": 5.7063133239746096,
|
|
"epoch": 1.4935595065312046,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.000478110236238962,
|
|
"loss": 5.4721,
|
|
"mean_token_accuracy": 0.1721112012863159,
|
|
"num_tokens": 34173613.0,
|
|
"step": 16465
|
|
},
|
|
{
|
|
"entropy": 5.635888671875,
|
|
"epoch": 1.4940130624092889,
|
|
"grad_norm": 2.984375,
|
|
"learning_rate": 0.00047809631295120164,
|
|
"loss": 5.3851,
|
|
"mean_token_accuracy": 0.17233798950910567,
|
|
"num_tokens": 34183540.0,
|
|
"step": 16470
|
|
},
|
|
{
|
|
"entropy": 5.590045833587647,
|
|
"epoch": 1.494466618287373,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00047808238546335786,
|
|
"loss": 5.4019,
|
|
"mean_token_accuracy": 0.1688580647110939,
|
|
"num_tokens": 34193292.0,
|
|
"step": 16475
|
|
},
|
|
{
|
|
"entropy": 5.721243906021118,
|
|
"epoch": 1.4949201741654572,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.00047806845377571856,
|
|
"loss": 5.4483,
|
|
"mean_token_accuracy": 0.17377619743347167,
|
|
"num_tokens": 34202697.0,
|
|
"step": 16480
|
|
},
|
|
{
|
|
"entropy": 5.662637853622437,
|
|
"epoch": 1.4953737300435415,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.00047805451788857187,
|
|
"loss": 5.3566,
|
|
"mean_token_accuracy": 0.1747078314423561,
|
|
"num_tokens": 34213396.0,
|
|
"step": 16485
|
|
},
|
|
{
|
|
"entropy": 5.667623472213745,
|
|
"epoch": 1.4958272859216255,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.000478040577802206,
|
|
"loss": 5.3685,
|
|
"mean_token_accuracy": 0.17463064789772034,
|
|
"num_tokens": 34223020.0,
|
|
"step": 16490
|
|
},
|
|
{
|
|
"entropy": 5.605656623840332,
|
|
"epoch": 1.4962808417997098,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004780266335169093,
|
|
"loss": 5.4125,
|
|
"mean_token_accuracy": 0.17131119668483735,
|
|
"num_tokens": 34233249.0,
|
|
"step": 16495
|
|
},
|
|
{
|
|
"entropy": 5.712879705429077,
|
|
"epoch": 1.4967343976777938,
|
|
"grad_norm": 3.46875,
|
|
"learning_rate": 0.00047801268503297,
|
|
"loss": 5.4648,
|
|
"mean_token_accuracy": 0.16647974401712418,
|
|
"num_tokens": 34244091.0,
|
|
"step": 16500
|
|
},
|
|
{
|
|
"entropy": 5.688513708114624,
|
|
"epoch": 1.497187953555878,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.00047799873235067667,
|
|
"loss": 5.445,
|
|
"mean_token_accuracy": 0.17347988486289978,
|
|
"num_tokens": 34255060.0,
|
|
"step": 16505
|
|
},
|
|
{
|
|
"entropy": 5.649759769439697,
|
|
"epoch": 1.4976415094339623,
|
|
"grad_norm": 2.875,
|
|
"learning_rate": 0.0004779847754703178,
|
|
"loss": 5.3209,
|
|
"mean_token_accuracy": 0.17872562259435654,
|
|
"num_tokens": 34264361.0,
|
|
"step": 16510
|
|
},
|
|
{
|
|
"entropy": 5.628484535217285,
|
|
"epoch": 1.4980950653120464,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004779708143921821,
|
|
"loss": 5.3983,
|
|
"mean_token_accuracy": 0.17308261394500732,
|
|
"num_tokens": 34274480.0,
|
|
"step": 16515
|
|
},
|
|
{
|
|
"entropy": 5.588571691513062,
|
|
"epoch": 1.4985486211901307,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.00047795684911655824,
|
|
"loss": 5.4173,
|
|
"mean_token_accuracy": 0.17368457168340684,
|
|
"num_tokens": 34285951.0,
|
|
"step": 16520
|
|
},
|
|
{
|
|
"entropy": 5.681325912475586,
|
|
"epoch": 1.4990021770682147,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.000477942879643735,
|
|
"loss": 5.4485,
|
|
"mean_token_accuracy": 0.1654208481311798,
|
|
"num_tokens": 34296384.0,
|
|
"step": 16525
|
|
},
|
|
{
|
|
"entropy": 5.665684604644776,
|
|
"epoch": 1.499455732946299,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00047792890597400125,
|
|
"loss": 5.3812,
|
|
"mean_token_accuracy": 0.17565633952617646,
|
|
"num_tokens": 34306776.0,
|
|
"step": 16530
|
|
},
|
|
{
|
|
"entropy": 5.681633758544922,
|
|
"epoch": 1.4999092888243832,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.00047791492810764604,
|
|
"loss": 5.3872,
|
|
"mean_token_accuracy": 0.17081659883260727,
|
|
"num_tokens": 34317047.0,
|
|
"step": 16535
|
|
},
|
|
{
|
|
"entropy": 5.624424028396606,
|
|
"epoch": 1.5003628447024675,
|
|
"grad_norm": 3.734375,
|
|
"learning_rate": 0.0004779009460449584,
|
|
"loss": 5.3391,
|
|
"mean_token_accuracy": 0.17481434792280198,
|
|
"num_tokens": 34326392.0,
|
|
"step": 16540
|
|
},
|
|
{
|
|
"entropy": 5.657869482040406,
|
|
"epoch": 1.5008164005805515,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.00047788695978622756,
|
|
"loss": 5.3971,
|
|
"mean_token_accuracy": 0.17772299200296401,
|
|
"num_tokens": 34336580.0,
|
|
"step": 16545
|
|
},
|
|
{
|
|
"entropy": 5.600024652481079,
|
|
"epoch": 1.5012699564586356,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.00047787296933174265,
|
|
"loss": 5.4154,
|
|
"mean_token_accuracy": 0.17094704061746596,
|
|
"num_tokens": 34346792.0,
|
|
"step": 16550
|
|
},
|
|
{
|
|
"entropy": 5.663271760940551,
|
|
"epoch": 1.5017235123367199,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.000477858974681793,
|
|
"loss": 5.4103,
|
|
"mean_token_accuracy": 0.17566470354795455,
|
|
"num_tokens": 34356675.0,
|
|
"step": 16555
|
|
},
|
|
{
|
|
"entropy": 5.671497011184693,
|
|
"epoch": 1.5021770682148041,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004778449758366681,
|
|
"loss": 5.4001,
|
|
"mean_token_accuracy": 0.1753545492887497,
|
|
"num_tokens": 34366357.0,
|
|
"step": 16560
|
|
},
|
|
{
|
|
"entropy": 5.626584148406982,
|
|
"epoch": 1.5026306240928884,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004778309727966574,
|
|
"loss": 5.407,
|
|
"mean_token_accuracy": 0.17490795254707336,
|
|
"num_tokens": 34377229.0,
|
|
"step": 16565
|
|
},
|
|
{
|
|
"entropy": 5.5568070888519285,
|
|
"epoch": 1.5030841799709724,
|
|
"grad_norm": 3.796875,
|
|
"learning_rate": 0.00047781696556205045,
|
|
"loss": 5.3201,
|
|
"mean_token_accuracy": 0.17836829125881196,
|
|
"num_tokens": 34387873.0,
|
|
"step": 16570
|
|
},
|
|
{
|
|
"entropy": 5.651993274688721,
|
|
"epoch": 1.5035377358490565,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.00047780295413313696,
|
|
"loss": 5.3688,
|
|
"mean_token_accuracy": 0.17528494596481323,
|
|
"num_tokens": 34398889.0,
|
|
"step": 16575
|
|
},
|
|
{
|
|
"entropy": 5.6404272556304935,
|
|
"epoch": 1.5039912917271407,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.00047778893851020676,
|
|
"loss": 5.3155,
|
|
"mean_token_accuracy": 0.17178105860948562,
|
|
"num_tokens": 34408508.0,
|
|
"step": 16580
|
|
},
|
|
{
|
|
"entropy": 5.618759346008301,
|
|
"epoch": 1.504444847605225,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004777749186935496,
|
|
"loss": 5.4809,
|
|
"mean_token_accuracy": 0.17052135914564132,
|
|
"num_tokens": 34418928.0,
|
|
"step": 16585
|
|
},
|
|
{
|
|
"entropy": 5.650527048110962,
|
|
"epoch": 1.5048984034833093,
|
|
"grad_norm": 3.6875,
|
|
"learning_rate": 0.0004777608946834555,
|
|
"loss": 5.4517,
|
|
"mean_token_accuracy": 0.17076525539159776,
|
|
"num_tokens": 34429789.0,
|
|
"step": 16590
|
|
},
|
|
{
|
|
"entropy": 5.696921539306641,
|
|
"epoch": 1.5053519593613933,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004777468664802144,
|
|
"loss": 5.5247,
|
|
"mean_token_accuracy": 0.16477661281824113,
|
|
"num_tokens": 34440795.0,
|
|
"step": 16595
|
|
},
|
|
{
|
|
"entropy": 5.723385524749756,
|
|
"epoch": 1.5058055152394774,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00047773283408411636,
|
|
"loss": 5.4305,
|
|
"mean_token_accuracy": 0.1642413169145584,
|
|
"num_tokens": 34450772.0,
|
|
"step": 16600
|
|
},
|
|
{
|
|
"entropy": 5.642021799087525,
|
|
"epoch": 1.5062590711175616,
|
|
"grad_norm": 3.21875,
|
|
"learning_rate": 0.00047771879749545175,
|
|
"loss": 5.3607,
|
|
"mean_token_accuracy": 0.16948054283857344,
|
|
"num_tokens": 34461273.0,
|
|
"step": 16605
|
|
},
|
|
{
|
|
"entropy": 5.655682945251465,
|
|
"epoch": 1.506712626995646,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.00047770475671451073,
|
|
"loss": 5.4342,
|
|
"mean_token_accuracy": 0.16622820645570754,
|
|
"num_tokens": 34470942.0,
|
|
"step": 16610
|
|
},
|
|
{
|
|
"entropy": 5.719380044937134,
|
|
"epoch": 1.5071661828737302,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.0004776907117415837,
|
|
"loss": 5.3642,
|
|
"mean_token_accuracy": 0.17244614362716676,
|
|
"num_tokens": 34481117.0,
|
|
"step": 16615
|
|
},
|
|
{
|
|
"entropy": 5.58799033164978,
|
|
"epoch": 1.5076197387518142,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00047767666257696103,
|
|
"loss": 5.3424,
|
|
"mean_token_accuracy": 0.1762220337986946,
|
|
"num_tokens": 34490953.0,
|
|
"step": 16620
|
|
},
|
|
{
|
|
"entropy": 5.605688381195068,
|
|
"epoch": 1.5080732946298983,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.00047766260922093337,
|
|
"loss": 5.3055,
|
|
"mean_token_accuracy": 0.1788915976881981,
|
|
"num_tokens": 34502765.0,
|
|
"step": 16625
|
|
},
|
|
{
|
|
"entropy": 5.738406181335449,
|
|
"epoch": 1.5085268505079825,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004776485516737913,
|
|
"loss": 5.517,
|
|
"mean_token_accuracy": 0.16625301241874696,
|
|
"num_tokens": 34514473.0,
|
|
"step": 16630
|
|
},
|
|
{
|
|
"entropy": 5.740399026870728,
|
|
"epoch": 1.5089804063860668,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004776344899358256,
|
|
"loss": 5.5005,
|
|
"mean_token_accuracy": 0.16496001482009887,
|
|
"num_tokens": 34524218.0,
|
|
"step": 16635
|
|
},
|
|
{
|
|
"entropy": 5.702562284469605,
|
|
"epoch": 1.509433962264151,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004776204240073269,
|
|
"loss": 5.3937,
|
|
"mean_token_accuracy": 0.17263842970132828,
|
|
"num_tokens": 34535697.0,
|
|
"step": 16640
|
|
},
|
|
{
|
|
"entropy": 5.66512975692749,
|
|
"epoch": 1.509887518142235,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.00047760635388858624,
|
|
"loss": 5.4295,
|
|
"mean_token_accuracy": 0.17574798613786696,
|
|
"num_tokens": 34545130.0,
|
|
"step": 16645
|
|
},
|
|
{
|
|
"entropy": 5.590177440643311,
|
|
"epoch": 1.5103410740203191,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00047759227957989465,
|
|
"loss": 5.3715,
|
|
"mean_token_accuracy": 0.17056550085544586,
|
|
"num_tokens": 34554974.0,
|
|
"step": 16650
|
|
},
|
|
{
|
|
"entropy": 5.660144805908203,
|
|
"epoch": 1.5107946298984034,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.000477578201081543,
|
|
"loss": 5.3984,
|
|
"mean_token_accuracy": 0.17017912864685059,
|
|
"num_tokens": 34565660.0,
|
|
"step": 16655
|
|
},
|
|
{
|
|
"entropy": 5.692255449295044,
|
|
"epoch": 1.5112481857764877,
|
|
"grad_norm": 3.5,
|
|
"learning_rate": 0.0004775641183938225,
|
|
"loss": 5.4198,
|
|
"mean_token_accuracy": 0.1706186279654503,
|
|
"num_tokens": 34576447.0,
|
|
"step": 16660
|
|
},
|
|
{
|
|
"entropy": 5.729809713363648,
|
|
"epoch": 1.511701741654572,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.00047755003151702443,
|
|
"loss": 5.5547,
|
|
"mean_token_accuracy": 0.16927665024995803,
|
|
"num_tokens": 34588333.0,
|
|
"step": 16665
|
|
},
|
|
{
|
|
"entropy": 5.647052240371704,
|
|
"epoch": 1.512155297532656,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.00047753594045144015,
|
|
"loss": 5.2926,
|
|
"mean_token_accuracy": 0.17350688874721526,
|
|
"num_tokens": 34598166.0,
|
|
"step": 16670
|
|
},
|
|
{
|
|
"entropy": 5.592651128768921,
|
|
"epoch": 1.5126088534107403,
|
|
"grad_norm": 3.90625,
|
|
"learning_rate": 0.0004775218451973609,
|
|
"loss": 5.3395,
|
|
"mean_token_accuracy": 0.17370067685842513,
|
|
"num_tokens": 34608615.0,
|
|
"step": 16675
|
|
},
|
|
{
|
|
"entropy": 5.5916108131408695,
|
|
"epoch": 1.5130624092888243,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004775077457550784,
|
|
"loss": 5.393,
|
|
"mean_token_accuracy": 0.17484464943408967,
|
|
"num_tokens": 34618618.0,
|
|
"step": 16680
|
|
},
|
|
{
|
|
"entropy": 5.6926459789276125,
|
|
"epoch": 1.5135159651669086,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.00047749364212488403,
|
|
"loss": 5.4248,
|
|
"mean_token_accuracy": 0.1676697999238968,
|
|
"num_tokens": 34629412.0,
|
|
"step": 16685
|
|
},
|
|
{
|
|
"entropy": 5.751585578918457,
|
|
"epoch": 1.5139695210449928,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.0004774795343070696,
|
|
"loss": 5.4983,
|
|
"mean_token_accuracy": 0.17461639791727065,
|
|
"num_tokens": 34640487.0,
|
|
"step": 16690
|
|
},
|
|
{
|
|
"entropy": 5.645683431625367,
|
|
"epoch": 1.5144230769230769,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004774654223019268,
|
|
"loss": 5.3961,
|
|
"mean_token_accuracy": 0.17697820514440538,
|
|
"num_tokens": 34650126.0,
|
|
"step": 16695
|
|
},
|
|
{
|
|
"entropy": 5.577963781356812,
|
|
"epoch": 1.5148766328011611,
|
|
"grad_norm": 4.28125,
|
|
"learning_rate": 0.0004774513061097474,
|
|
"loss": 5.2675,
|
|
"mean_token_accuracy": 0.18066167533397676,
|
|
"num_tokens": 34659721.0,
|
|
"step": 16700
|
|
},
|
|
{
|
|
"entropy": 5.618318653106689,
|
|
"epoch": 1.5153301886792452,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004774371857308235,
|
|
"loss": 5.3839,
|
|
"mean_token_accuracy": 0.17571649849414825,
|
|
"num_tokens": 34670611.0,
|
|
"step": 16705
|
|
},
|
|
{
|
|
"entropy": 5.659499454498291,
|
|
"epoch": 1.5157837445573294,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.00047742306116544693,
|
|
"loss": 5.3657,
|
|
"mean_token_accuracy": 0.18024436086416246,
|
|
"num_tokens": 34680173.0,
|
|
"step": 16710
|
|
},
|
|
{
|
|
"entropy": 5.647472858428955,
|
|
"epoch": 1.5162373004354137,
|
|
"grad_norm": 2.984375,
|
|
"learning_rate": 0.00047740893241390994,
|
|
"loss": 5.433,
|
|
"mean_token_accuracy": 0.17252063304185866,
|
|
"num_tokens": 34690176.0,
|
|
"step": 16715
|
|
},
|
|
{
|
|
"entropy": 5.690574836730957,
|
|
"epoch": 1.516690856313498,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004773947994765046,
|
|
"loss": 5.3661,
|
|
"mean_token_accuracy": 0.17495691627264023,
|
|
"num_tokens": 34700481.0,
|
|
"step": 16720
|
|
},
|
|
{
|
|
"entropy": 5.651398944854736,
|
|
"epoch": 1.517144412191582,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004773806623535232,
|
|
"loss": 5.5368,
|
|
"mean_token_accuracy": 0.16878045946359635,
|
|
"num_tokens": 34710643.0,
|
|
"step": 16725
|
|
},
|
|
{
|
|
"entropy": 5.696643114089966,
|
|
"epoch": 1.517597968069666,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.00047736652104525816,
|
|
"loss": 5.3986,
|
|
"mean_token_accuracy": 0.16928562819957732,
|
|
"num_tokens": 34720998.0,
|
|
"step": 16730
|
|
},
|
|
{
|
|
"entropy": 5.711614894866943,
|
|
"epoch": 1.5180515239477503,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004773523755520019,
|
|
"loss": 5.4532,
|
|
"mean_token_accuracy": 0.1697494000196457,
|
|
"num_tokens": 34731071.0,
|
|
"step": 16735
|
|
},
|
|
{
|
|
"entropy": 5.624730348587036,
|
|
"epoch": 1.5185050798258346,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.000477338225874047,
|
|
"loss": 5.3462,
|
|
"mean_token_accuracy": 0.16994858533143997,
|
|
"num_tokens": 34741346.0,
|
|
"step": 16740
|
|
},
|
|
{
|
|
"entropy": 5.722128295898438,
|
|
"epoch": 1.5189586357039189,
|
|
"grad_norm": 3.5625,
|
|
"learning_rate": 0.00047732407201168595,
|
|
"loss": 5.3506,
|
|
"mean_token_accuracy": 0.17380651235580444,
|
|
"num_tokens": 34751092.0,
|
|
"step": 16745
|
|
},
|
|
{
|
|
"entropy": 5.717962694168091,
|
|
"epoch": 1.519412191582003,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004773099139652116,
|
|
"loss": 5.4775,
|
|
"mean_token_accuracy": 0.1686473846435547,
|
|
"num_tokens": 34761477.0,
|
|
"step": 16750
|
|
},
|
|
{
|
|
"entropy": 5.609793329238892,
|
|
"epoch": 1.519865747460087,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.0004772957517349167,
|
|
"loss": 5.3927,
|
|
"mean_token_accuracy": 0.1696197733283043,
|
|
"num_tokens": 34772491.0,
|
|
"step": 16755
|
|
},
|
|
{
|
|
"entropy": 5.621784305572509,
|
|
"epoch": 1.5203193033381712,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004772815853210939,
|
|
"loss": 5.4362,
|
|
"mean_token_accuracy": 0.16394334733486177,
|
|
"num_tokens": 34783192.0,
|
|
"step": 16760
|
|
},
|
|
{
|
|
"entropy": 5.644205474853516,
|
|
"epoch": 1.5207728592162555,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.00047726741472403655,
|
|
"loss": 5.4083,
|
|
"mean_token_accuracy": 0.17407684475183488,
|
|
"num_tokens": 34794164.0,
|
|
"step": 16765
|
|
},
|
|
{
|
|
"entropy": 5.6784453868865965,
|
|
"epoch": 1.5212264150943398,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.00047725323994403753,
|
|
"loss": 5.431,
|
|
"mean_token_accuracy": 0.16949652433395385,
|
|
"num_tokens": 34804390.0,
|
|
"step": 16770
|
|
},
|
|
{
|
|
"entropy": 5.78183422088623,
|
|
"epoch": 1.5216799709724238,
|
|
"grad_norm": 4.15625,
|
|
"learning_rate": 0.00047723906098138993,
|
|
"loss": 5.5338,
|
|
"mean_token_accuracy": 0.16549902707338332,
|
|
"num_tokens": 34814751.0,
|
|
"step": 16775
|
|
},
|
|
{
|
|
"entropy": 5.674895429611206,
|
|
"epoch": 1.5221335268505078,
|
|
"grad_norm": 2.875,
|
|
"learning_rate": 0.00047722487783638697,
|
|
"loss": 5.3589,
|
|
"mean_token_accuracy": 0.17601838558912278,
|
|
"num_tokens": 34824977.0,
|
|
"step": 16780
|
|
},
|
|
{
|
|
"entropy": 5.633380031585693,
|
|
"epoch": 1.5225870827285921,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.000477210690509322,
|
|
"loss": 5.4429,
|
|
"mean_token_accuracy": 0.1707715332508087,
|
|
"num_tokens": 34835540.0,
|
|
"step": 16785
|
|
},
|
|
{
|
|
"entropy": 5.681983900070191,
|
|
"epoch": 1.5230406386066764,
|
|
"grad_norm": 4.9375,
|
|
"learning_rate": 0.00047719649900048843,
|
|
"loss": 5.4047,
|
|
"mean_token_accuracy": 0.17071651071310043,
|
|
"num_tokens": 34845233.0,
|
|
"step": 16790
|
|
},
|
|
{
|
|
"entropy": 5.751985502243042,
|
|
"epoch": 1.5234941944847606,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.00047718230331017975,
|
|
"loss": 5.5007,
|
|
"mean_token_accuracy": 0.16404855027794837,
|
|
"num_tokens": 34855756.0,
|
|
"step": 16795
|
|
},
|
|
{
|
|
"entropy": 5.652025938034058,
|
|
"epoch": 1.5239477503628447,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.00047716810343868956,
|
|
"loss": 5.4161,
|
|
"mean_token_accuracy": 0.16214538365602493,
|
|
"num_tokens": 34867869.0,
|
|
"step": 16800
|
|
},
|
|
{
|
|
"entropy": 5.734392166137695,
|
|
"epoch": 1.5244013062409287,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00047715389938631143,
|
|
"loss": 5.4826,
|
|
"mean_token_accuracy": 0.17144400179386138,
|
|
"num_tokens": 34878625.0,
|
|
"step": 16805
|
|
},
|
|
{
|
|
"entropy": 5.750245666503906,
|
|
"epoch": 1.524854862119013,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.00047713969115333916,
|
|
"loss": 5.4404,
|
|
"mean_token_accuracy": 0.16525504142045974,
|
|
"num_tokens": 34889408.0,
|
|
"step": 16810
|
|
},
|
|
{
|
|
"entropy": 5.6276116371154785,
|
|
"epoch": 1.5253084179970973,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.0004771254787400666,
|
|
"loss": 5.481,
|
|
"mean_token_accuracy": 0.16606520265340804,
|
|
"num_tokens": 34899602.0,
|
|
"step": 16815
|
|
},
|
|
{
|
|
"entropy": 5.629642915725708,
|
|
"epoch": 1.5257619738751815,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004771112621467876,
|
|
"loss": 5.3163,
|
|
"mean_token_accuracy": 0.17435577660799026,
|
|
"num_tokens": 34910215.0,
|
|
"step": 16820
|
|
},
|
|
{
|
|
"entropy": 5.622303915023804,
|
|
"epoch": 1.5262155297532656,
|
|
"grad_norm": 3.015625,
|
|
"learning_rate": 0.0004770970413737961,
|
|
"loss": 5.4051,
|
|
"mean_token_accuracy": 0.17695687413215638,
|
|
"num_tokens": 34919641.0,
|
|
"step": 16825
|
|
},
|
|
{
|
|
"entropy": 5.670840930938721,
|
|
"epoch": 1.5266690856313496,
|
|
"grad_norm": 3.53125,
|
|
"learning_rate": 0.0004770828164213865,
|
|
"loss": 5.3102,
|
|
"mean_token_accuracy": 0.1793120965361595,
|
|
"num_tokens": 34930243.0,
|
|
"step": 16830
|
|
},
|
|
{
|
|
"entropy": 5.710893535614014,
|
|
"epoch": 1.5271226415094339,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004770685872898525,
|
|
"loss": 5.4669,
|
|
"mean_token_accuracy": 0.16873344779014587,
|
|
"num_tokens": 34941057.0,
|
|
"step": 16835
|
|
},
|
|
{
|
|
"entropy": 5.662563514709473,
|
|
"epoch": 1.5275761973875182,
|
|
"grad_norm": 4.46875,
|
|
"learning_rate": 0.00047705435397948876,
|
|
"loss": 5.3292,
|
|
"mean_token_accuracy": 0.1774134263396263,
|
|
"num_tokens": 34951150.0,
|
|
"step": 16840
|
|
},
|
|
{
|
|
"entropy": 5.650436067581177,
|
|
"epoch": 1.5280297532656024,
|
|
"grad_norm": 3.421875,
|
|
"learning_rate": 0.0004770401164905895,
|
|
"loss": 5.4245,
|
|
"mean_token_accuracy": 0.17145764380693435,
|
|
"num_tokens": 34961648.0,
|
|
"step": 16845
|
|
},
|
|
{
|
|
"entropy": 5.6528076171875,
|
|
"epoch": 1.5284833091436865,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.00047702587482344915,
|
|
"loss": 5.4397,
|
|
"mean_token_accuracy": 0.16921953856945038,
|
|
"num_tokens": 34971573.0,
|
|
"step": 16850
|
|
},
|
|
{
|
|
"entropy": 5.68293194770813,
|
|
"epoch": 1.5289368650217707,
|
|
"grad_norm": 4.1875,
|
|
"learning_rate": 0.0004770116289783622,
|
|
"loss": 5.4038,
|
|
"mean_token_accuracy": 0.16956733018159867,
|
|
"num_tokens": 34981984.0,
|
|
"step": 16855
|
|
},
|
|
{
|
|
"entropy": 5.626167058944702,
|
|
"epoch": 1.5293904208998548,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004769973789556233,
|
|
"loss": 5.4245,
|
|
"mean_token_accuracy": 0.16706011295318604,
|
|
"num_tokens": 34990861.0,
|
|
"step": 16860
|
|
},
|
|
{
|
|
"entropy": 5.695982551574707,
|
|
"epoch": 1.529843976777939,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.00047698312475552714,
|
|
"loss": 5.4264,
|
|
"mean_token_accuracy": 0.16927399784326552,
|
|
"num_tokens": 35001504.0,
|
|
"step": 16865
|
|
},
|
|
{
|
|
"entropy": 5.702606058120727,
|
|
"epoch": 1.5302975326560233,
|
|
"grad_norm": 3.515625,
|
|
"learning_rate": 0.0004769688663783684,
|
|
"loss": 5.3593,
|
|
"mean_token_accuracy": 0.17745755463838578,
|
|
"num_tokens": 35012425.0,
|
|
"step": 16870
|
|
},
|
|
{
|
|
"entropy": 5.604656171798706,
|
|
"epoch": 1.5307510885341074,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004769546038244421,
|
|
"loss": 5.3535,
|
|
"mean_token_accuracy": 0.17786695957183837,
|
|
"num_tokens": 35022854.0,
|
|
"step": 16875
|
|
},
|
|
{
|
|
"entropy": 5.651180219650269,
|
|
"epoch": 1.5312046444121916,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.00047694033709404313,
|
|
"loss": 5.4697,
|
|
"mean_token_accuracy": 0.1693316236138344,
|
|
"num_tokens": 35032694.0,
|
|
"step": 16880
|
|
},
|
|
{
|
|
"entropy": 5.60539231300354,
|
|
"epoch": 1.5316582002902757,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.00047692606618746655,
|
|
"loss": 5.3661,
|
|
"mean_token_accuracy": 0.1783360868692398,
|
|
"num_tokens": 35042217.0,
|
|
"step": 16885
|
|
},
|
|
{
|
|
"entropy": 5.667411375045776,
|
|
"epoch": 1.53211175616836,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.00047691179110500735,
|
|
"loss": 5.4485,
|
|
"mean_token_accuracy": 0.16157716363668442,
|
|
"num_tokens": 35052831.0,
|
|
"step": 16890
|
|
},
|
|
{
|
|
"entropy": 5.7473798274993895,
|
|
"epoch": 1.5325653120464442,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.00047689751184696097,
|
|
"loss": 5.4642,
|
|
"mean_token_accuracy": 0.16560643911361694,
|
|
"num_tokens": 35061955.0,
|
|
"step": 16895
|
|
},
|
|
{
|
|
"entropy": 5.679140329360962,
|
|
"epoch": 1.5330188679245285,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004768832284136226,
|
|
"loss": 5.3797,
|
|
"mean_token_accuracy": 0.16960711479187013,
|
|
"num_tokens": 35072526.0,
|
|
"step": 16900
|
|
},
|
|
{
|
|
"entropy": 5.612961530685425,
|
|
"epoch": 1.5334724238026125,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004768689408052876,
|
|
"loss": 5.3359,
|
|
"mean_token_accuracy": 0.17970145642757415,
|
|
"num_tokens": 35082415.0,
|
|
"step": 16905
|
|
},
|
|
{
|
|
"entropy": 5.599942922592163,
|
|
"epoch": 1.5339259796806965,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.00047685464902225144,
|
|
"loss": 5.3642,
|
|
"mean_token_accuracy": 0.17599014192819595,
|
|
"num_tokens": 35092805.0,
|
|
"step": 16910
|
|
},
|
|
{
|
|
"entropy": 5.698967218399048,
|
|
"epoch": 1.5343795355587808,
|
|
"grad_norm": 4.0625,
|
|
"learning_rate": 0.0004768403530648097,
|
|
"loss": 5.4062,
|
|
"mean_token_accuracy": 0.17842955887317657,
|
|
"num_tokens": 35102963.0,
|
|
"step": 16915
|
|
},
|
|
{
|
|
"entropy": 5.742544174194336,
|
|
"epoch": 1.534833091436865,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.00047682605293325806,
|
|
"loss": 5.421,
|
|
"mean_token_accuracy": 0.17184364944696426,
|
|
"num_tokens": 35114140.0,
|
|
"step": 16920
|
|
},
|
|
{
|
|
"entropy": 5.716738510131836,
|
|
"epoch": 1.5352866473149493,
|
|
"grad_norm": 2.921875,
|
|
"learning_rate": 0.00047681174862789215,
|
|
"loss": 5.4903,
|
|
"mean_token_accuracy": 0.1684983715415001,
|
|
"num_tokens": 35125314.0,
|
|
"step": 16925
|
|
},
|
|
{
|
|
"entropy": 5.646747207641601,
|
|
"epoch": 1.5357402031930334,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.00047679744014900795,
|
|
"loss": 5.3868,
|
|
"mean_token_accuracy": 0.1705384522676468,
|
|
"num_tokens": 35134934.0,
|
|
"step": 16930
|
|
},
|
|
{
|
|
"entropy": 5.633379316329956,
|
|
"epoch": 1.5361937590711174,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004767831274969011,
|
|
"loss": 5.3593,
|
|
"mean_token_accuracy": 0.17271686792373658,
|
|
"num_tokens": 35145341.0,
|
|
"step": 16935
|
|
},
|
|
{
|
|
"entropy": 5.617522096633911,
|
|
"epoch": 1.5366473149492017,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00047676881067186793,
|
|
"loss": 5.333,
|
|
"mean_token_accuracy": 0.17121649533510208,
|
|
"num_tokens": 35156046.0,
|
|
"step": 16940
|
|
},
|
|
{
|
|
"entropy": 5.691127872467041,
|
|
"epoch": 1.537100870827286,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.00047675448967420426,
|
|
"loss": 5.4904,
|
|
"mean_token_accuracy": 0.1646376982331276,
|
|
"num_tokens": 35168232.0,
|
|
"step": 16945
|
|
},
|
|
{
|
|
"entropy": 5.779607105255127,
|
|
"epoch": 1.5375544267053702,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004767401645042064,
|
|
"loss": 5.4336,
|
|
"mean_token_accuracy": 0.17115551084280015,
|
|
"num_tokens": 35178585.0,
|
|
"step": 16950
|
|
},
|
|
{
|
|
"entropy": 5.645753669738769,
|
|
"epoch": 1.5380079825834543,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.00047672583516217043,
|
|
"loss": 5.3174,
|
|
"mean_token_accuracy": 0.1758516922593117,
|
|
"num_tokens": 35189417.0,
|
|
"step": 16955
|
|
},
|
|
{
|
|
"entropy": 5.596486234664917,
|
|
"epoch": 1.5384615384615383,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004767115016483928,
|
|
"loss": 5.3667,
|
|
"mean_token_accuracy": 0.17198648303747177,
|
|
"num_tokens": 35200167.0,
|
|
"step": 16960
|
|
},
|
|
{
|
|
"entropy": 5.648817491531372,
|
|
"epoch": 1.5389150943396226,
|
|
"grad_norm": 7.71875,
|
|
"learning_rate": 0.0004766971639631699,
|
|
"loss": 5.3912,
|
|
"mean_token_accuracy": 0.17599288672208785,
|
|
"num_tokens": 35210711.0,
|
|
"step": 16965
|
|
},
|
|
{
|
|
"entropy": 5.653993749618531,
|
|
"epoch": 1.5393686502177069,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00047668282210679825,
|
|
"loss": 5.4058,
|
|
"mean_token_accuracy": 0.17106241434812547,
|
|
"num_tokens": 35220866.0,
|
|
"step": 16970
|
|
},
|
|
{
|
|
"entropy": 5.61572756767273,
|
|
"epoch": 1.5398222060957911,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004766684760795745,
|
|
"loss": 5.3615,
|
|
"mean_token_accuracy": 0.1750795677304268,
|
|
"num_tokens": 35231478.0,
|
|
"step": 16975
|
|
},
|
|
{
|
|
"entropy": 5.563072299957275,
|
|
"epoch": 1.5402757619738752,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.00047665412588179524,
|
|
"loss": 5.326,
|
|
"mean_token_accuracy": 0.17991118282079696,
|
|
"num_tokens": 35242233.0,
|
|
"step": 16980
|
|
},
|
|
{
|
|
"entropy": 5.58691029548645,
|
|
"epoch": 1.5407293178519592,
|
|
"grad_norm": 3.453125,
|
|
"learning_rate": 0.0004766397715137573,
|
|
"loss": 5.3711,
|
|
"mean_token_accuracy": 0.1699317514896393,
|
|
"num_tokens": 35253097.0,
|
|
"step": 16985
|
|
},
|
|
{
|
|
"entropy": 5.736815786361694,
|
|
"epoch": 1.5411828737300435,
|
|
"grad_norm": 3.046875,
|
|
"learning_rate": 0.00047662541297575743,
|
|
"loss": 5.5176,
|
|
"mean_token_accuracy": 0.17129866778850555,
|
|
"num_tokens": 35264258.0,
|
|
"step": 16990
|
|
},
|
|
{
|
|
"entropy": 5.797584676742554,
|
|
"epoch": 1.5416364296081277,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.00047661105026809274,
|
|
"loss": 5.5135,
|
|
"mean_token_accuracy": 0.16247532814741134,
|
|
"num_tokens": 35273501.0,
|
|
"step": 16995
|
|
},
|
|
{
|
|
"entropy": 5.664180135726928,
|
|
"epoch": 1.542089985486212,
|
|
"grad_norm": 3.421875,
|
|
"learning_rate": 0.0004765966833910601,
|
|
"loss": 5.4461,
|
|
"mean_token_accuracy": 0.16710411608219147,
|
|
"num_tokens": 35284125.0,
|
|
"step": 17000
|
|
},
|
|
{
|
|
"entropy": 5.721617078781128,
|
|
"epoch": 1.542543541364296,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004765823123449567,
|
|
"loss": 5.4466,
|
|
"mean_token_accuracy": 0.16854842603206635,
|
|
"num_tokens": 35296039.0,
|
|
"step": 17005
|
|
},
|
|
{
|
|
"entropy": 5.719720983505249,
|
|
"epoch": 1.54299709724238,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.00047656793713007965,
|
|
"loss": 5.3949,
|
|
"mean_token_accuracy": 0.17008774280548095,
|
|
"num_tokens": 35306178.0,
|
|
"step": 17010
|
|
},
|
|
{
|
|
"entropy": 5.624810361862183,
|
|
"epoch": 1.5434506531204644,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.00047655355774672636,
|
|
"loss": 5.4203,
|
|
"mean_token_accuracy": 0.17162414640188217,
|
|
"num_tokens": 35316445.0,
|
|
"step": 17015
|
|
},
|
|
{
|
|
"entropy": 5.659040689468384,
|
|
"epoch": 1.5439042089985486,
|
|
"grad_norm": 2.984375,
|
|
"learning_rate": 0.00047653917419519413,
|
|
"loss": 5.391,
|
|
"mean_token_accuracy": 0.16948893219232558,
|
|
"num_tokens": 35327274.0,
|
|
"step": 17020
|
|
},
|
|
{
|
|
"entropy": 5.700904512405396,
|
|
"epoch": 1.544357764876633,
|
|
"grad_norm": 2.96875,
|
|
"learning_rate": 0.0004765247864757804,
|
|
"loss": 5.3933,
|
|
"mean_token_accuracy": 0.17256319969892503,
|
|
"num_tokens": 35339007.0,
|
|
"step": 17025
|
|
},
|
|
{
|
|
"entropy": 5.696538400650025,
|
|
"epoch": 1.544811320754717,
|
|
"grad_norm": 3.09375,
|
|
"learning_rate": 0.0004765103945887827,
|
|
"loss": 5.5014,
|
|
"mean_token_accuracy": 0.1586498111486435,
|
|
"num_tokens": 35349303.0,
|
|
"step": 17030
|
|
},
|
|
{
|
|
"entropy": 5.700264978408813,
|
|
"epoch": 1.5452648766328012,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004764959985344987,
|
|
"loss": 5.322,
|
|
"mean_token_accuracy": 0.17687153667211533,
|
|
"num_tokens": 35359556.0,
|
|
"step": 17035
|
|
},
|
|
{
|
|
"entropy": 5.622378015518189,
|
|
"epoch": 1.5457184325108853,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004764815983132261,
|
|
"loss": 5.3423,
|
|
"mean_token_accuracy": 0.18195056170225143,
|
|
"num_tokens": 35370043.0,
|
|
"step": 17040
|
|
},
|
|
{
|
|
"entropy": 5.628189516067505,
|
|
"epoch": 1.5461719883889695,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004764671939252628,
|
|
"loss": 5.3504,
|
|
"mean_token_accuracy": 0.17485000491142272,
|
|
"num_tokens": 35380031.0,
|
|
"step": 17045
|
|
},
|
|
{
|
|
"entropy": 5.620057249069214,
|
|
"epoch": 1.5466255442670538,
|
|
"grad_norm": 2.921875,
|
|
"learning_rate": 0.0004764527853709064,
|
|
"loss": 5.4468,
|
|
"mean_token_accuracy": 0.1704546794295311,
|
|
"num_tokens": 35390481.0,
|
|
"step": 17050
|
|
},
|
|
{
|
|
"entropy": 5.636156272888184,
|
|
"epoch": 1.5470791001451378,
|
|
"grad_norm": 2.84375,
|
|
"learning_rate": 0.0004764383726504552,
|
|
"loss": 5.409,
|
|
"mean_token_accuracy": 0.17394430190324783,
|
|
"num_tokens": 35401756.0,
|
|
"step": 17055
|
|
},
|
|
{
|
|
"entropy": 5.682874584197998,
|
|
"epoch": 1.547532656023222,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004764239557642071,
|
|
"loss": 5.343,
|
|
"mean_token_accuracy": 0.17790085822343826,
|
|
"num_tokens": 35411045.0,
|
|
"step": 17060
|
|
},
|
|
{
|
|
"entropy": 5.645724964141846,
|
|
"epoch": 1.5479862119013061,
|
|
"grad_norm": 3.5,
|
|
"learning_rate": 0.0004764095347124603,
|
|
"loss": 5.3865,
|
|
"mean_token_accuracy": 0.17036917358636855,
|
|
"num_tokens": 35421256.0,
|
|
"step": 17065
|
|
},
|
|
{
|
|
"entropy": 5.642555522918701,
|
|
"epoch": 1.5484397677793904,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004763951094955129,
|
|
"loss": 5.3984,
|
|
"mean_token_accuracy": 0.17603887766599655,
|
|
"num_tokens": 35430798.0,
|
|
"step": 17070
|
|
},
|
|
{
|
|
"entropy": 5.626025104522705,
|
|
"epoch": 1.5488933236574747,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004763806801136634,
|
|
"loss": 5.347,
|
|
"mean_token_accuracy": 0.18143416047096253,
|
|
"num_tokens": 35440459.0,
|
|
"step": 17075
|
|
},
|
|
{
|
|
"entropy": 5.664116525650025,
|
|
"epoch": 1.549346879535559,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004763662465672101,
|
|
"loss": 5.3936,
|
|
"mean_token_accuracy": 0.17345059514045716,
|
|
"num_tokens": 35451586.0,
|
|
"step": 17080
|
|
},
|
|
{
|
|
"entropy": 5.657958269119263,
|
|
"epoch": 1.549800435413643,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.00047635180885645146,
|
|
"loss": 5.4421,
|
|
"mean_token_accuracy": 0.17020758390426635,
|
|
"num_tokens": 35462197.0,
|
|
"step": 17085
|
|
},
|
|
{
|
|
"entropy": 5.7076562404632565,
|
|
"epoch": 1.550253991291727,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004763373669816862,
|
|
"loss": 5.3397,
|
|
"mean_token_accuracy": 0.1760431110858917,
|
|
"num_tokens": 35471737.0,
|
|
"step": 17090
|
|
},
|
|
{
|
|
"entropy": 5.683960103988648,
|
|
"epoch": 1.5507075471698113,
|
|
"grad_norm": 3.0625,
|
|
"learning_rate": 0.0004763229209432128,
|
|
"loss": 5.4223,
|
|
"mean_token_accuracy": 0.1668218806385994,
|
|
"num_tokens": 35482016.0,
|
|
"step": 17095
|
|
},
|
|
{
|
|
"entropy": 5.6712922096252445,
|
|
"epoch": 1.5511611030478956,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004763084707413301,
|
|
"loss": 5.5186,
|
|
"mean_token_accuracy": 0.15694814920425415,
|
|
"num_tokens": 35492622.0,
|
|
"step": 17100
|
|
},
|
|
{
|
|
"entropy": 5.747307395935058,
|
|
"epoch": 1.5516146589259798,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00047629401637633696,
|
|
"loss": 5.5688,
|
|
"mean_token_accuracy": 0.1649051383137703,
|
|
"num_tokens": 35504468.0,
|
|
"step": 17105
|
|
},
|
|
{
|
|
"entropy": 5.674877691268921,
|
|
"epoch": 1.5520682148040639,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.00047627955784853226,
|
|
"loss": 5.3646,
|
|
"mean_token_accuracy": 0.17190408408641816,
|
|
"num_tokens": 35514272.0,
|
|
"step": 17110
|
|
},
|
|
{
|
|
"entropy": 5.6460713863372805,
|
|
"epoch": 1.552521770682148,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.000476265095158215,
|
|
"loss": 5.355,
|
|
"mean_token_accuracy": 0.1690351814031601,
|
|
"num_tokens": 35524110.0,
|
|
"step": 17115
|
|
},
|
|
{
|
|
"entropy": 5.610192060470581,
|
|
"epoch": 1.5529753265602322,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004762506283056843,
|
|
"loss": 5.3308,
|
|
"mean_token_accuracy": 0.17832489758729936,
|
|
"num_tokens": 35535504.0,
|
|
"step": 17120
|
|
},
|
|
{
|
|
"entropy": 5.74502911567688,
|
|
"epoch": 1.5534288824383164,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004762361572912393,
|
|
"loss": 5.4761,
|
|
"mean_token_accuracy": 0.17100796848535538,
|
|
"num_tokens": 35544885.0,
|
|
"step": 17125
|
|
},
|
|
{
|
|
"entropy": 5.6985321044921875,
|
|
"epoch": 1.5538824383164007,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.00047622168211517926,
|
|
"loss": 5.4976,
|
|
"mean_token_accuracy": 0.17145250290632247,
|
|
"num_tokens": 35555485.0,
|
|
"step": 17130
|
|
},
|
|
{
|
|
"entropy": 5.60291748046875,
|
|
"epoch": 1.5543359941944848,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.00047620720277780353,
|
|
"loss": 5.3371,
|
|
"mean_token_accuracy": 0.17470266819000244,
|
|
"num_tokens": 35567197.0,
|
|
"step": 17135
|
|
},
|
|
{
|
|
"entropy": 5.6995948314666744,
|
|
"epoch": 1.5547895500725688,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.00047619271927941165,
|
|
"loss": 5.3639,
|
|
"mean_token_accuracy": 0.17752195447683333,
|
|
"num_tokens": 35577576.0,
|
|
"step": 17140
|
|
},
|
|
{
|
|
"entropy": 5.639021015167236,
|
|
"epoch": 1.555243105950653,
|
|
"grad_norm": 3.078125,
|
|
"learning_rate": 0.000476178231620303,
|
|
"loss": 5.4158,
|
|
"mean_token_accuracy": 0.17060236483812333,
|
|
"num_tokens": 35588012.0,
|
|
"step": 17145
|
|
},
|
|
{
|
|
"entropy": 5.606847667694092,
|
|
"epoch": 1.5556966618287373,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004761637398007774,
|
|
"loss": 5.4049,
|
|
"mean_token_accuracy": 0.16612281799316406,
|
|
"num_tokens": 35598076.0,
|
|
"step": 17150
|
|
},
|
|
{
|
|
"entropy": 5.563495779037476,
|
|
"epoch": 1.5561502177068216,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004761492438211342,
|
|
"loss": 5.2063,
|
|
"mean_token_accuracy": 0.1833631783723831,
|
|
"num_tokens": 35607170.0,
|
|
"step": 17155
|
|
},
|
|
{
|
|
"entropy": 5.6494566917419435,
|
|
"epoch": 1.5566037735849056,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.00047613474368167355,
|
|
"loss": 5.3571,
|
|
"mean_token_accuracy": 0.16956139206886292,
|
|
"num_tokens": 35617865.0,
|
|
"step": 17160
|
|
},
|
|
{
|
|
"entropy": 5.6541759967803955,
|
|
"epoch": 1.5570573294629897,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.000476120239382695,
|
|
"loss": 5.4463,
|
|
"mean_token_accuracy": 0.17057694345712662,
|
|
"num_tokens": 35629329.0,
|
|
"step": 17165
|
|
},
|
|
{
|
|
"entropy": 5.6103123188018795,
|
|
"epoch": 1.557510885341074,
|
|
"grad_norm": 2.9375,
|
|
"learning_rate": 0.00047610573092449877,
|
|
"loss": 5.4171,
|
|
"mean_token_accuracy": 0.1667105570435524,
|
|
"num_tokens": 35640044.0,
|
|
"step": 17170
|
|
},
|
|
{
|
|
"entropy": 5.669890975952148,
|
|
"epoch": 1.5579644412191582,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004760912183073847,
|
|
"loss": 5.4462,
|
|
"mean_token_accuracy": 0.17360056787729264,
|
|
"num_tokens": 35650435.0,
|
|
"step": 17175
|
|
},
|
|
{
|
|
"entropy": 5.660927248001099,
|
|
"epoch": 1.5584179970972425,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.000476076701531653,
|
|
"loss": 5.3465,
|
|
"mean_token_accuracy": 0.1702407881617546,
|
|
"num_tokens": 35659613.0,
|
|
"step": 17180
|
|
},
|
|
{
|
|
"entropy": 5.6343292713165285,
|
|
"epoch": 1.5588715529753265,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004760621805976039,
|
|
"loss": 5.4052,
|
|
"mean_token_accuracy": 0.1732204020023346,
|
|
"num_tokens": 35670987.0,
|
|
"step": 17185
|
|
},
|
|
{
|
|
"entropy": 5.6290536403656,
|
|
"epoch": 1.5593251088534106,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.00047604765550553766,
|
|
"loss": 5.39,
|
|
"mean_token_accuracy": 0.17468850016593934,
|
|
"num_tokens": 35682505.0,
|
|
"step": 17190
|
|
},
|
|
{
|
|
"entropy": 5.652574300765991,
|
|
"epoch": 1.5597786647314948,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.00047603312625575466,
|
|
"loss": 5.3574,
|
|
"mean_token_accuracy": 0.17486406117677689,
|
|
"num_tokens": 35693056.0,
|
|
"step": 17195
|
|
},
|
|
{
|
|
"entropy": 5.636611747741699,
|
|
"epoch": 1.5602322206095791,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.00047601859284855544,
|
|
"loss": 5.3298,
|
|
"mean_token_accuracy": 0.1776195615530014,
|
|
"num_tokens": 35703659.0,
|
|
"step": 17200
|
|
},
|
|
{
|
|
"entropy": 5.646828985214233,
|
|
"epoch": 1.5606857764876634,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004760040552842403,
|
|
"loss": 5.4045,
|
|
"mean_token_accuracy": 0.16908743381500244,
|
|
"num_tokens": 35714367.0,
|
|
"step": 17205
|
|
},
|
|
{
|
|
"entropy": 5.611659002304077,
|
|
"epoch": 1.5611393323657474,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.00047598951356311035,
|
|
"loss": 5.3476,
|
|
"mean_token_accuracy": 0.17328743934631347,
|
|
"num_tokens": 35724773.0,
|
|
"step": 17210
|
|
},
|
|
{
|
|
"entropy": 5.695950841903686,
|
|
"epoch": 1.5615928882438317,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004759749676854658,
|
|
"loss": 5.5052,
|
|
"mean_token_accuracy": 0.1704159438610077,
|
|
"num_tokens": 35735622.0,
|
|
"step": 17215
|
|
},
|
|
{
|
|
"entropy": 5.692738103866577,
|
|
"epoch": 1.5620464441219157,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004759604176516079,
|
|
"loss": 5.3571,
|
|
"mean_token_accuracy": 0.17691242694854736,
|
|
"num_tokens": 35744967.0,
|
|
"step": 17220
|
|
},
|
|
{
|
|
"entropy": 5.695892858505249,
|
|
"epoch": 1.5625,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004759458634618372,
|
|
"loss": 5.4155,
|
|
"mean_token_accuracy": 0.1701454147696495,
|
|
"num_tokens": 35755647.0,
|
|
"step": 17225
|
|
},
|
|
{
|
|
"entropy": 5.670782899856567,
|
|
"epoch": 1.5629535558780843,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004759313051164549,
|
|
"loss": 5.4262,
|
|
"mean_token_accuracy": 0.16771045625209807,
|
|
"num_tokens": 35765595.0,
|
|
"step": 17230
|
|
},
|
|
{
|
|
"entropy": 5.689231443405151,
|
|
"epoch": 1.5634071117561683,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.000475916742615762,
|
|
"loss": 5.3894,
|
|
"mean_token_accuracy": 0.1745188057422638,
|
|
"num_tokens": 35775804.0,
|
|
"step": 17235
|
|
},
|
|
{
|
|
"entropy": 5.605354595184326,
|
|
"epoch": 1.5638606676342526,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.0004759021759600597,
|
|
"loss": 5.3434,
|
|
"mean_token_accuracy": 0.17657775431871414,
|
|
"num_tokens": 35786227.0,
|
|
"step": 17240
|
|
},
|
|
{
|
|
"entropy": 5.706438779830933,
|
|
"epoch": 1.5643142235123366,
|
|
"grad_norm": 3.15625,
|
|
"learning_rate": 0.0004758876051496492,
|
|
"loss": 5.4573,
|
|
"mean_token_accuracy": 0.1723747193813324,
|
|
"num_tokens": 35797511.0,
|
|
"step": 17245
|
|
},
|
|
{
|
|
"entropy": 5.707958698272705,
|
|
"epoch": 1.5647677793904209,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.00047587303018483177,
|
|
"loss": 5.4057,
|
|
"mean_token_accuracy": 0.16878646463155747,
|
|
"num_tokens": 35807248.0,
|
|
"step": 17250
|
|
},
|
|
{
|
|
"entropy": 5.660100889205933,
|
|
"epoch": 1.5652213352685052,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00047585845106590897,
|
|
"loss": 5.4128,
|
|
"mean_token_accuracy": 0.16771808713674546,
|
|
"num_tokens": 35818164.0,
|
|
"step": 17255
|
|
},
|
|
{
|
|
"entropy": 5.6253211975097654,
|
|
"epoch": 1.5656748911465894,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.00047584386779318214,
|
|
"loss": 5.3773,
|
|
"mean_token_accuracy": 0.18237612247467042,
|
|
"num_tokens": 35828746.0,
|
|
"step": 17260
|
|
},
|
|
{
|
|
"entropy": 5.665443325042725,
|
|
"epoch": 1.5661284470246735,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.000475829280366953,
|
|
"loss": 5.4284,
|
|
"mean_token_accuracy": 0.1683792382478714,
|
|
"num_tokens": 35839325.0,
|
|
"step": 17265
|
|
},
|
|
{
|
|
"entropy": 5.712682485580444,
|
|
"epoch": 1.5665820029027575,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.00047581468878752313,
|
|
"loss": 5.376,
|
|
"mean_token_accuracy": 0.17710108011960984,
|
|
"num_tokens": 35849406.0,
|
|
"step": 17270
|
|
},
|
|
{
|
|
"entropy": 5.605699729919434,
|
|
"epoch": 1.5670355587808418,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00047580009305519427,
|
|
"loss": 5.2997,
|
|
"mean_token_accuracy": 0.17497554123401643,
|
|
"num_tokens": 35858715.0,
|
|
"step": 17275
|
|
},
|
|
{
|
|
"entropy": 5.590784645080566,
|
|
"epoch": 1.567489114658926,
|
|
"grad_norm": 3.34375,
|
|
"learning_rate": 0.0004757854931702684,
|
|
"loss": 5.3977,
|
|
"mean_token_accuracy": 0.1702730044722557,
|
|
"num_tokens": 35869063.0,
|
|
"step": 17280
|
|
},
|
|
{
|
|
"entropy": 5.619686794281006,
|
|
"epoch": 1.5679426705370103,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.00047577088913304733,
|
|
"loss": 5.2768,
|
|
"mean_token_accuracy": 0.1755272477865219,
|
|
"num_tokens": 35878428.0,
|
|
"step": 17285
|
|
},
|
|
{
|
|
"entropy": 5.653322362899781,
|
|
"epoch": 1.5683962264150944,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.00047575628094383317,
|
|
"loss": 5.4215,
|
|
"mean_token_accuracy": 0.1735541880130768,
|
|
"num_tokens": 35888801.0,
|
|
"step": 17290
|
|
},
|
|
{
|
|
"entropy": 5.601457929611206,
|
|
"epoch": 1.5688497822931784,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004757416686029279,
|
|
"loss": 5.4129,
|
|
"mean_token_accuracy": 0.16844217330217362,
|
|
"num_tokens": 35899381.0,
|
|
"step": 17295
|
|
},
|
|
{
|
|
"entropy": 5.699126386642456,
|
|
"epoch": 1.5693033381712627,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004757270521106338,
|
|
"loss": 5.4474,
|
|
"mean_token_accuracy": 0.17238806039094925,
|
|
"num_tokens": 35909546.0,
|
|
"step": 17300
|
|
},
|
|
{
|
|
"entropy": 5.671964168548584,
|
|
"epoch": 1.569756894049347,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004757124314672531,
|
|
"loss": 5.4102,
|
|
"mean_token_accuracy": 0.17266113460063934,
|
|
"num_tokens": 35919301.0,
|
|
"step": 17305
|
|
},
|
|
{
|
|
"entropy": 5.737994766235351,
|
|
"epoch": 1.5702104499274312,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.00047569780667308816,
|
|
"loss": 5.4826,
|
|
"mean_token_accuracy": 0.16358221769332887,
|
|
"num_tokens": 35928603.0,
|
|
"step": 17310
|
|
},
|
|
{
|
|
"entropy": 5.670061016082764,
|
|
"epoch": 1.5706640058055152,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.00047568317772844147,
|
|
"loss": 5.4035,
|
|
"mean_token_accuracy": 0.17784096747636796,
|
|
"num_tokens": 35939005.0,
|
|
"step": 17315
|
|
},
|
|
{
|
|
"entropy": 5.68056435585022,
|
|
"epoch": 1.5711175616835993,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.00047566854463361544,
|
|
"loss": 5.3892,
|
|
"mean_token_accuracy": 0.18400239944458008,
|
|
"num_tokens": 35948471.0,
|
|
"step": 17320
|
|
},
|
|
{
|
|
"entropy": 5.65282940864563,
|
|
"epoch": 1.5715711175616836,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004756539073889128,
|
|
"loss": 5.4315,
|
|
"mean_token_accuracy": 0.17117742598056793,
|
|
"num_tokens": 35958488.0,
|
|
"step": 17325
|
|
},
|
|
{
|
|
"entropy": 5.633076238632202,
|
|
"epoch": 1.5720246734397678,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.00047563926599463623,
|
|
"loss": 5.4658,
|
|
"mean_token_accuracy": 0.168238827586174,
|
|
"num_tokens": 35968291.0,
|
|
"step": 17330
|
|
},
|
|
{
|
|
"entropy": 5.717834424972534,
|
|
"epoch": 1.572478229317852,
|
|
"grad_norm": 3.46875,
|
|
"learning_rate": 0.0004756246204510886,
|
|
"loss": 5.4209,
|
|
"mean_token_accuracy": 0.1701866164803505,
|
|
"num_tokens": 35978565.0,
|
|
"step": 17335
|
|
},
|
|
{
|
|
"entropy": 5.681910514831543,
|
|
"epoch": 1.5729317851959361,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.00047560997075857253,
|
|
"loss": 5.3516,
|
|
"mean_token_accuracy": 0.17865179628133773,
|
|
"num_tokens": 35987483.0,
|
|
"step": 17340
|
|
},
|
|
{
|
|
"entropy": 5.604638195037841,
|
|
"epoch": 1.5733853410740202,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004755953169173913,
|
|
"loss": 5.4235,
|
|
"mean_token_accuracy": 0.16991666704416275,
|
|
"num_tokens": 35998355.0,
|
|
"step": 17345
|
|
},
|
|
{
|
|
"entropy": 5.597176933288575,
|
|
"epoch": 1.5738388969521044,
|
|
"grad_norm": 3.40625,
|
|
"learning_rate": 0.0004755806589278477,
|
|
"loss": 5.3753,
|
|
"mean_token_accuracy": 0.1786399155855179,
|
|
"num_tokens": 36008365.0,
|
|
"step": 17350
|
|
},
|
|
{
|
|
"entropy": 5.701880598068238,
|
|
"epoch": 1.5742924528301887,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.00047556599679024497,
|
|
"loss": 5.4501,
|
|
"mean_token_accuracy": 0.1673444390296936,
|
|
"num_tokens": 36018880.0,
|
|
"step": 17355
|
|
},
|
|
{
|
|
"entropy": 5.7095667839050295,
|
|
"epoch": 1.574746008708273,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.00047555133050488637,
|
|
"loss": 5.4683,
|
|
"mean_token_accuracy": 0.16584511399269103,
|
|
"num_tokens": 36029335.0,
|
|
"step": 17360
|
|
},
|
|
{
|
|
"entropy": 5.650959920883179,
|
|
"epoch": 1.575199564586357,
|
|
"grad_norm": 3.6875,
|
|
"learning_rate": 0.00047553666007207516,
|
|
"loss": 5.3755,
|
|
"mean_token_accuracy": 0.178165103495121,
|
|
"num_tokens": 36039774.0,
|
|
"step": 17365
|
|
},
|
|
{
|
|
"entropy": 5.72376012802124,
|
|
"epoch": 1.575653120464441,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.00047552198549211463,
|
|
"loss": 5.4987,
|
|
"mean_token_accuracy": 0.17618722468614578,
|
|
"num_tokens": 36049864.0,
|
|
"step": 17370
|
|
},
|
|
{
|
|
"entropy": 5.7121187210083,
|
|
"epoch": 1.5761066763425253,
|
|
"grad_norm": 3.984375,
|
|
"learning_rate": 0.0004755073067653084,
|
|
"loss": 5.403,
|
|
"mean_token_accuracy": 0.16964422166347504,
|
|
"num_tokens": 36059224.0,
|
|
"step": 17375
|
|
},
|
|
{
|
|
"entropy": 5.540336036682129,
|
|
"epoch": 1.5765602322206096,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004754926238919599,
|
|
"loss": 5.3505,
|
|
"mean_token_accuracy": 0.17871894538402558,
|
|
"num_tokens": 36069243.0,
|
|
"step": 17380
|
|
},
|
|
{
|
|
"entropy": 5.610846757888794,
|
|
"epoch": 1.5770137880986939,
|
|
"grad_norm": 3.578125,
|
|
"learning_rate": 0.0004754779368723729,
|
|
"loss": 5.3798,
|
|
"mean_token_accuracy": 0.17132749557495117,
|
|
"num_tokens": 36079833.0,
|
|
"step": 17385
|
|
},
|
|
{
|
|
"entropy": 5.705043935775757,
|
|
"epoch": 1.577467343976778,
|
|
"grad_norm": 5.4375,
|
|
"learning_rate": 0.0004754632457068511,
|
|
"loss": 5.3894,
|
|
"mean_token_accuracy": 0.17683931142091752,
|
|
"num_tokens": 36090673.0,
|
|
"step": 17390
|
|
},
|
|
{
|
|
"entropy": 5.685024738311768,
|
|
"epoch": 1.5779208998548622,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004754485503956982,
|
|
"loss": 5.4324,
|
|
"mean_token_accuracy": 0.17435317486524582,
|
|
"num_tokens": 36101719.0,
|
|
"step": 17395
|
|
},
|
|
{
|
|
"entropy": 5.6559507846832275,
|
|
"epoch": 1.5783744557329462,
|
|
"grad_norm": 3.375,
|
|
"learning_rate": 0.0004754338509392183,
|
|
"loss": 5.3819,
|
|
"mean_token_accuracy": 0.16655096858739854,
|
|
"num_tokens": 36112352.0,
|
|
"step": 17400
|
|
},
|
|
{
|
|
"entropy": 5.580322790145874,
|
|
"epoch": 1.5788280116110305,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004754191473377153,
|
|
"loss": 5.2549,
|
|
"mean_token_accuracy": 0.17936209589242935,
|
|
"num_tokens": 36121797.0,
|
|
"step": 17405
|
|
},
|
|
{
|
|
"entropy": 5.642678689956665,
|
|
"epoch": 1.5792815674891147,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.00047540443959149316,
|
|
"loss": 5.4126,
|
|
"mean_token_accuracy": 0.1732194483280182,
|
|
"num_tokens": 36132094.0,
|
|
"step": 17410
|
|
},
|
|
{
|
|
"entropy": 5.643293714523315,
|
|
"epoch": 1.5797351233671988,
|
|
"grad_norm": 3.125,
|
|
"learning_rate": 0.0004753897277008562,
|
|
"loss": 5.3889,
|
|
"mean_token_accuracy": 0.1739877849817276,
|
|
"num_tokens": 36142860.0,
|
|
"step": 17415
|
|
},
|
|
{
|
|
"entropy": 5.718941688537598,
|
|
"epoch": 1.580188679245283,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004753750116661086,
|
|
"loss": 5.3969,
|
|
"mean_token_accuracy": 0.16496087610721588,
|
|
"num_tokens": 36154555.0,
|
|
"step": 17420
|
|
},
|
|
{
|
|
"entropy": 5.745329666137695,
|
|
"epoch": 1.580642235123367,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.00047536029148755477,
|
|
"loss": 5.4982,
|
|
"mean_token_accuracy": 0.16311438530683517,
|
|
"num_tokens": 36165479.0,
|
|
"step": 17425
|
|
},
|
|
{
|
|
"entropy": 5.67413444519043,
|
|
"epoch": 1.5810957910014514,
|
|
"grad_norm": 3.40625,
|
|
"learning_rate": 0.00047534556716549893,
|
|
"loss": 5.4087,
|
|
"mean_token_accuracy": 0.171665221452713,
|
|
"num_tokens": 36175873.0,
|
|
"step": 17430
|
|
},
|
|
{
|
|
"entropy": 5.64816198348999,
|
|
"epoch": 1.5815493468795356,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.00047533083870024575,
|
|
"loss": 5.3763,
|
|
"mean_token_accuracy": 0.17893075197935104,
|
|
"num_tokens": 36186792.0,
|
|
"step": 17435
|
|
},
|
|
{
|
|
"entropy": 5.78192172050476,
|
|
"epoch": 1.58200290275762,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004753161060920998,
|
|
"loss": 5.5123,
|
|
"mean_token_accuracy": 0.16583681404590606,
|
|
"num_tokens": 36196691.0,
|
|
"step": 17440
|
|
},
|
|
{
|
|
"entropy": 5.7443279266357425,
|
|
"epoch": 1.582456458635704,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004753013693413657,
|
|
"loss": 5.4021,
|
|
"mean_token_accuracy": 0.1751517966389656,
|
|
"num_tokens": 36207173.0,
|
|
"step": 17445
|
|
},
|
|
{
|
|
"entropy": 5.577095794677734,
|
|
"epoch": 1.582910014513788,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.00047528662844834827,
|
|
"loss": 5.3964,
|
|
"mean_token_accuracy": 0.1724944606423378,
|
|
"num_tokens": 36217912.0,
|
|
"step": 17450
|
|
},
|
|
{
|
|
"entropy": 5.5774664878845215,
|
|
"epoch": 1.5833635703918723,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.00047527188341335233,
|
|
"loss": 5.3199,
|
|
"mean_token_accuracy": 0.17873115390539168,
|
|
"num_tokens": 36227714.0,
|
|
"step": 17455
|
|
},
|
|
{
|
|
"entropy": 5.7274171829223635,
|
|
"epoch": 1.5838171262699565,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004752571342366828,
|
|
"loss": 5.4006,
|
|
"mean_token_accuracy": 0.1704569548368454,
|
|
"num_tokens": 36239114.0,
|
|
"step": 17460
|
|
},
|
|
{
|
|
"entropy": 5.659423828125,
|
|
"epoch": 1.5842706821480408,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004752423809186446,
|
|
"loss": 5.3966,
|
|
"mean_token_accuracy": 0.16819894313812256,
|
|
"num_tokens": 36249436.0,
|
|
"step": 17465
|
|
},
|
|
{
|
|
"entropy": 5.642833805084228,
|
|
"epoch": 1.5847242380261248,
|
|
"grad_norm": 2.875,
|
|
"learning_rate": 0.00047522762345954305,
|
|
"loss": 5.3442,
|
|
"mean_token_accuracy": 0.17347895503044128,
|
|
"num_tokens": 36259541.0,
|
|
"step": 17470
|
|
},
|
|
{
|
|
"entropy": 5.665331697463989,
|
|
"epoch": 1.5851777939042089,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004752128618596832,
|
|
"loss": 5.4094,
|
|
"mean_token_accuracy": 0.16681926995515822,
|
|
"num_tokens": 36270689.0,
|
|
"step": 17475
|
|
},
|
|
{
|
|
"entropy": 5.759731769561768,
|
|
"epoch": 1.5856313497822931,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.00047519809611937036,
|
|
"loss": 5.482,
|
|
"mean_token_accuracy": 0.16794963777065278,
|
|
"num_tokens": 36281191.0,
|
|
"step": 17480
|
|
},
|
|
{
|
|
"entropy": 5.563282155990601,
|
|
"epoch": 1.5860849056603774,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004751833262389098,
|
|
"loss": 5.3675,
|
|
"mean_token_accuracy": 0.17524173855781555,
|
|
"num_tokens": 36291022.0,
|
|
"step": 17485
|
|
},
|
|
{
|
|
"entropy": 5.673428106307983,
|
|
"epoch": 1.5865384615384617,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.00047516855221860715,
|
|
"loss": 5.4204,
|
|
"mean_token_accuracy": 0.17473491579294204,
|
|
"num_tokens": 36301237.0,
|
|
"step": 17490
|
|
},
|
|
{
|
|
"entropy": 5.711238098144531,
|
|
"epoch": 1.5869920174165457,
|
|
"grad_norm": 3.953125,
|
|
"learning_rate": 0.00047515377405876774,
|
|
"loss": 5.3977,
|
|
"mean_token_accuracy": 0.1660773128271103,
|
|
"num_tokens": 36311792.0,
|
|
"step": 17495
|
|
},
|
|
{
|
|
"entropy": 5.567358875274659,
|
|
"epoch": 1.5874455732946298,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004751389917596973,
|
|
"loss": 5.3676,
|
|
"mean_token_accuracy": 0.177433580160141,
|
|
"num_tokens": 36321847.0,
|
|
"step": 17500
|
|
},
|
|
{
|
|
"entropy": 5.641406106948852,
|
|
"epoch": 1.587899129172714,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.00047512420532170154,
|
|
"loss": 5.4704,
|
|
"mean_token_accuracy": 0.16595210433006286,
|
|
"num_tokens": 36332735.0,
|
|
"step": 17505
|
|
},
|
|
{
|
|
"entropy": 5.727991533279419,
|
|
"epoch": 1.5883526850507983,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004751094147450862,
|
|
"loss": 5.4636,
|
|
"mean_token_accuracy": 0.17142474949359893,
|
|
"num_tokens": 36343149.0,
|
|
"step": 17510
|
|
},
|
|
{
|
|
"entropy": 5.663159513473511,
|
|
"epoch": 1.5888062409288826,
|
|
"grad_norm": 3.46875,
|
|
"learning_rate": 0.0004750946200301571,
|
|
"loss": 5.3636,
|
|
"mean_token_accuracy": 0.17695342302322387,
|
|
"num_tokens": 36353081.0,
|
|
"step": 17515
|
|
},
|
|
{
|
|
"entropy": 5.6339208602905275,
|
|
"epoch": 1.5892597968069666,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.00047507982117722035,
|
|
"loss": 5.4252,
|
|
"mean_token_accuracy": 0.16885654479265214,
|
|
"num_tokens": 36363624.0,
|
|
"step": 17520
|
|
},
|
|
{
|
|
"entropy": 5.70914511680603,
|
|
"epoch": 1.5897133526850507,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.000475065018186582,
|
|
"loss": 5.4485,
|
|
"mean_token_accuracy": 0.17073243111371994,
|
|
"num_tokens": 36374081.0,
|
|
"step": 17525
|
|
},
|
|
{
|
|
"entropy": 5.6653858661651615,
|
|
"epoch": 1.590166908563135,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.00047505021105854794,
|
|
"loss": 5.5217,
|
|
"mean_token_accuracy": 0.1654040440917015,
|
|
"num_tokens": 36384360.0,
|
|
"step": 17530
|
|
},
|
|
{
|
|
"entropy": 5.691194009780884,
|
|
"epoch": 1.5906204644412192,
|
|
"grad_norm": 3.265625,
|
|
"learning_rate": 0.00047503539979342456,
|
|
"loss": 5.458,
|
|
"mean_token_accuracy": 0.1707295447587967,
|
|
"num_tokens": 36395924.0,
|
|
"step": 17535
|
|
},
|
|
{
|
|
"entropy": 5.591055488586425,
|
|
"epoch": 1.5910740203193035,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004750205843915182,
|
|
"loss": 5.3061,
|
|
"mean_token_accuracy": 0.17841509282588958,
|
|
"num_tokens": 36405246.0,
|
|
"step": 17540
|
|
},
|
|
{
|
|
"entropy": 5.653607368469238,
|
|
"epoch": 1.5915275761973875,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004750057648531351,
|
|
"loss": 5.3673,
|
|
"mean_token_accuracy": 0.17659929841756822,
|
|
"num_tokens": 36414964.0,
|
|
"step": 17545
|
|
},
|
|
{
|
|
"entropy": 5.582899951934815,
|
|
"epoch": 1.5919811320754715,
|
|
"grad_norm": 3.984375,
|
|
"learning_rate": 0.0004749909411785819,
|
|
"loss": 5.4343,
|
|
"mean_token_accuracy": 0.1683146595954895,
|
|
"num_tokens": 36425011.0,
|
|
"step": 17550
|
|
},
|
|
{
|
|
"entropy": 5.575544261932373,
|
|
"epoch": 1.5924346879535558,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.000474976113368165,
|
|
"loss": 5.3318,
|
|
"mean_token_accuracy": 0.18348198533058166,
|
|
"num_tokens": 36434734.0,
|
|
"step": 17555
|
|
},
|
|
{
|
|
"entropy": 5.679828691482544,
|
|
"epoch": 1.59288824383164,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004749612814221912,
|
|
"loss": 5.4142,
|
|
"mean_token_accuracy": 0.17027070969343186,
|
|
"num_tokens": 36444748.0,
|
|
"step": 17560
|
|
},
|
|
{
|
|
"entropy": 5.746703100204468,
|
|
"epoch": 1.5933417997097243,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.00047494644534096703,
|
|
"loss": 5.426,
|
|
"mean_token_accuracy": 0.16810113787651063,
|
|
"num_tokens": 36455076.0,
|
|
"step": 17565
|
|
},
|
|
{
|
|
"entropy": 5.611432981491089,
|
|
"epoch": 1.5937953555878084,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004749316051247995,
|
|
"loss": 5.3542,
|
|
"mean_token_accuracy": 0.1751040369272232,
|
|
"num_tokens": 36465302.0,
|
|
"step": 17570
|
|
},
|
|
{
|
|
"entropy": 5.62572169303894,
|
|
"epoch": 1.5942489114658926,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.00047491676077399543,
|
|
"loss": 5.4778,
|
|
"mean_token_accuracy": 0.16590761989355088,
|
|
"num_tokens": 36476666.0,
|
|
"step": 17575
|
|
},
|
|
{
|
|
"entropy": 5.624130344390869,
|
|
"epoch": 1.5947024673439767,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004749019122888618,
|
|
"loss": 5.3073,
|
|
"mean_token_accuracy": 0.17947846353054048,
|
|
"num_tokens": 36487379.0,
|
|
"step": 17580
|
|
},
|
|
{
|
|
"entropy": 5.6327001571655275,
|
|
"epoch": 1.595156023222061,
|
|
"grad_norm": 2.9375,
|
|
"learning_rate": 0.00047488705966970565,
|
|
"loss": 5.3347,
|
|
"mean_token_accuracy": 0.17959275841712952,
|
|
"num_tokens": 36497897.0,
|
|
"step": 17585
|
|
},
|
|
{
|
|
"entropy": 5.624341106414795,
|
|
"epoch": 1.5956095791001452,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004748722029168342,
|
|
"loss": 5.45,
|
|
"mean_token_accuracy": 0.17603489756584167,
|
|
"num_tokens": 36508528.0,
|
|
"step": 17590
|
|
},
|
|
{
|
|
"entropy": 5.703414726257324,
|
|
"epoch": 1.5960631349782293,
|
|
"grad_norm": 4.03125,
|
|
"learning_rate": 0.0004748573420305546,
|
|
"loss": 5.4357,
|
|
"mean_token_accuracy": 0.1686316430568695,
|
|
"num_tokens": 36519196.0,
|
|
"step": 17595
|
|
},
|
|
{
|
|
"entropy": 5.661535215377808,
|
|
"epoch": 1.5965166908563135,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.00047484247701117427,
|
|
"loss": 5.4343,
|
|
"mean_token_accuracy": 0.16735027730464935,
|
|
"num_tokens": 36529871.0,
|
|
"step": 17600
|
|
},
|
|
{
|
|
"entropy": 5.682347059249878,
|
|
"epoch": 1.5969702467343976,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004748276078590006,
|
|
"loss": 5.4638,
|
|
"mean_token_accuracy": 0.16416953802108764,
|
|
"num_tokens": 36541188.0,
|
|
"step": 17605
|
|
},
|
|
{
|
|
"entropy": 5.732767391204834,
|
|
"epoch": 1.5974238026124818,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004748127345743411,
|
|
"loss": 5.462,
|
|
"mean_token_accuracy": 0.17132306545972825,
|
|
"num_tokens": 36551968.0,
|
|
"step": 17610
|
|
},
|
|
{
|
|
"entropy": 5.653164196014404,
|
|
"epoch": 1.5978773584905661,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004747978571575033,
|
|
"loss": 5.4126,
|
|
"mean_token_accuracy": 0.16931667923927307,
|
|
"num_tokens": 36562870.0,
|
|
"step": 17615
|
|
},
|
|
{
|
|
"entropy": 5.586216402053833,
|
|
"epoch": 1.5983309143686504,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004747829756087949,
|
|
"loss": 5.3438,
|
|
"mean_token_accuracy": 0.17604034692049025,
|
|
"num_tokens": 36573295.0,
|
|
"step": 17620
|
|
},
|
|
{
|
|
"entropy": 5.614579105377198,
|
|
"epoch": 1.5987844702467344,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.00047476808992852364,
|
|
"loss": 5.3389,
|
|
"mean_token_accuracy": 0.17735567390918733,
|
|
"num_tokens": 36583830.0,
|
|
"step": 17625
|
|
},
|
|
{
|
|
"entropy": 5.680988693237305,
|
|
"epoch": 1.5992380261248185,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004747532001169974,
|
|
"loss": 5.3954,
|
|
"mean_token_accuracy": 0.17751946151256562,
|
|
"num_tokens": 36594052.0,
|
|
"step": 17630
|
|
},
|
|
{
|
|
"entropy": 5.674018335342407,
|
|
"epoch": 1.5996915820029027,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.00047473830617452415,
|
|
"loss": 5.4263,
|
|
"mean_token_accuracy": 0.1704084038734436,
|
|
"num_tokens": 36604378.0,
|
|
"step": 17635
|
|
},
|
|
{
|
|
"entropy": 5.674513626098633,
|
|
"epoch": 1.600145137880987,
|
|
"grad_norm": 6.28125,
|
|
"learning_rate": 0.00047472340810141163,
|
|
"loss": 5.5126,
|
|
"mean_token_accuracy": 0.16009544134140014,
|
|
"num_tokens": 36615588.0,
|
|
"step": 17640
|
|
},
|
|
{
|
|
"entropy": 5.752115869522095,
|
|
"epoch": 1.6005986937590713,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00047470850589796833,
|
|
"loss": 5.4293,
|
|
"mean_token_accuracy": 0.16888996362686157,
|
|
"num_tokens": 36626369.0,
|
|
"step": 17645
|
|
},
|
|
{
|
|
"entropy": 5.702257204055786,
|
|
"epoch": 1.6010522496371553,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.00047469359956450215,
|
|
"loss": 5.4521,
|
|
"mean_token_accuracy": 0.16592315286397935,
|
|
"num_tokens": 36636565.0,
|
|
"step": 17650
|
|
},
|
|
{
|
|
"entropy": 5.718983793258667,
|
|
"epoch": 1.6015058055152394,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.00047467868910132144,
|
|
"loss": 5.5111,
|
|
"mean_token_accuracy": 0.16422746032476426,
|
|
"num_tokens": 36647721.0,
|
|
"step": 17655
|
|
},
|
|
{
|
|
"entropy": 5.638012313842774,
|
|
"epoch": 1.6019593613933236,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004746637745087346,
|
|
"loss": 5.3018,
|
|
"mean_token_accuracy": 0.18042997270822525,
|
|
"num_tokens": 36657887.0,
|
|
"step": 17660
|
|
},
|
|
{
|
|
"entropy": 5.713828420639038,
|
|
"epoch": 1.6024129172714079,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.00047464885578705,
|
|
"loss": 5.4038,
|
|
"mean_token_accuracy": 0.16940520256757735,
|
|
"num_tokens": 36667918.0,
|
|
"step": 17665
|
|
},
|
|
{
|
|
"entropy": 5.576410484313965,
|
|
"epoch": 1.6028664731494922,
|
|
"grad_norm": 2.96875,
|
|
"learning_rate": 0.00047463393293657616,
|
|
"loss": 5.3416,
|
|
"mean_token_accuracy": 0.17885959446430205,
|
|
"num_tokens": 36678491.0,
|
|
"step": 17670
|
|
},
|
|
{
|
|
"entropy": 5.63793535232544,
|
|
"epoch": 1.6033200290275762,
|
|
"grad_norm": 3.328125,
|
|
"learning_rate": 0.0004746190059576217,
|
|
"loss": 5.4344,
|
|
"mean_token_accuracy": 0.1704348787665367,
|
|
"num_tokens": 36688638.0,
|
|
"step": 17675
|
|
},
|
|
{
|
|
"entropy": 5.681444120407105,
|
|
"epoch": 1.6037735849056602,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004746040748504954,
|
|
"loss": 5.4369,
|
|
"mean_token_accuracy": 0.17416483610868455,
|
|
"num_tokens": 36699344.0,
|
|
"step": 17680
|
|
},
|
|
{
|
|
"entropy": 5.636284732818604,
|
|
"epoch": 1.6042271407837445,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.00047458913961550593,
|
|
"loss": 5.3639,
|
|
"mean_token_accuracy": 0.17728210538625716,
|
|
"num_tokens": 36709606.0,
|
|
"step": 17685
|
|
},
|
|
{
|
|
"entropy": 5.580390357971192,
|
|
"epoch": 1.6046806966618288,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004745742002529622,
|
|
"loss": 5.3345,
|
|
"mean_token_accuracy": 0.1729191780090332,
|
|
"num_tokens": 36718740.0,
|
|
"step": 17690
|
|
},
|
|
{
|
|
"entropy": 5.687528610229492,
|
|
"epoch": 1.605134252539913,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004745592567631731,
|
|
"loss": 5.409,
|
|
"mean_token_accuracy": 0.16813482940196992,
|
|
"num_tokens": 36729960.0,
|
|
"step": 17695
|
|
},
|
|
{
|
|
"entropy": 5.588144254684448,
|
|
"epoch": 1.605587808417997,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.00047454430914644773,
|
|
"loss": 5.3259,
|
|
"mean_token_accuracy": 0.1748509645462036,
|
|
"num_tokens": 36740221.0,
|
|
"step": 17700
|
|
},
|
|
{
|
|
"entropy": 5.531030750274658,
|
|
"epoch": 1.6060413642960811,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004745293574030952,
|
|
"loss": 5.3492,
|
|
"mean_token_accuracy": 0.17761264741420746,
|
|
"num_tokens": 36750841.0,
|
|
"step": 17705
|
|
},
|
|
{
|
|
"entropy": 5.5816473960876465,
|
|
"epoch": 1.6064949201741654,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.00047451440153342477,
|
|
"loss": 5.369,
|
|
"mean_token_accuracy": 0.16956630498170852,
|
|
"num_tokens": 36760944.0,
|
|
"step": 17710
|
|
},
|
|
{
|
|
"entropy": 5.681816577911377,
|
|
"epoch": 1.6069484760522497,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.0004744994415377457,
|
|
"loss": 5.3781,
|
|
"mean_token_accuracy": 0.1742231696844101,
|
|
"num_tokens": 36770922.0,
|
|
"step": 17715
|
|
},
|
|
{
|
|
"entropy": 5.66191987991333,
|
|
"epoch": 1.607402031930334,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.00047448447741636724,
|
|
"loss": 5.4004,
|
|
"mean_token_accuracy": 0.1697769433259964,
|
|
"num_tokens": 36780702.0,
|
|
"step": 17720
|
|
},
|
|
{
|
|
"entropy": 5.652406692504883,
|
|
"epoch": 1.607855587808418,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.00047446950916959905,
|
|
"loss": 5.4282,
|
|
"mean_token_accuracy": 0.16965330094099046,
|
|
"num_tokens": 36791868.0,
|
|
"step": 17725
|
|
},
|
|
{
|
|
"entropy": 5.729321050643921,
|
|
"epoch": 1.608309143686502,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004744545367977505,
|
|
"loss": 5.4414,
|
|
"mean_token_accuracy": 0.171072119474411,
|
|
"num_tokens": 36802330.0,
|
|
"step": 17730
|
|
},
|
|
{
|
|
"entropy": 5.693122291564942,
|
|
"epoch": 1.6087626995645863,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.00047443956030113134,
|
|
"loss": 5.4449,
|
|
"mean_token_accuracy": 0.16435248404741287,
|
|
"num_tokens": 36812936.0,
|
|
"step": 17735
|
|
},
|
|
{
|
|
"entropy": 5.647220945358276,
|
|
"epoch": 1.6092162554426706,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.00047442457968005123,
|
|
"loss": 5.4119,
|
|
"mean_token_accuracy": 0.1731739491224289,
|
|
"num_tokens": 36823123.0,
|
|
"step": 17740
|
|
},
|
|
{
|
|
"entropy": 5.603677463531494,
|
|
"epoch": 1.6096698113207548,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.00047440959493481996,
|
|
"loss": 5.3069,
|
|
"mean_token_accuracy": 0.17567766308784485,
|
|
"num_tokens": 36833050.0,
|
|
"step": 17745
|
|
},
|
|
{
|
|
"entropy": 5.6944983959197994,
|
|
"epoch": 1.6101233671988389,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.00047439460606574745,
|
|
"loss": 5.4369,
|
|
"mean_token_accuracy": 0.1724836841225624,
|
|
"num_tokens": 36842520.0,
|
|
"step": 17750
|
|
},
|
|
{
|
|
"entropy": 5.627097129821777,
|
|
"epoch": 1.6105769230769231,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004743796130731437,
|
|
"loss": 5.3757,
|
|
"mean_token_accuracy": 0.17105068415403366,
|
|
"num_tokens": 36853024.0,
|
|
"step": 17755
|
|
},
|
|
{
|
|
"entropy": 5.6285669803619385,
|
|
"epoch": 1.6110304789550072,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004743646159573188,
|
|
"loss": 5.3426,
|
|
"mean_token_accuracy": 0.17796698957681656,
|
|
"num_tokens": 36862534.0,
|
|
"step": 17760
|
|
},
|
|
{
|
|
"entropy": 5.629456615447998,
|
|
"epoch": 1.6114840348330914,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004743496147185828,
|
|
"loss": 5.3386,
|
|
"mean_token_accuracy": 0.17737095206975936,
|
|
"num_tokens": 36872356.0,
|
|
"step": 17765
|
|
},
|
|
{
|
|
"entropy": 5.587741374969482,
|
|
"epoch": 1.6119375907111757,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.00047433460935724595,
|
|
"loss": 5.3993,
|
|
"mean_token_accuracy": 0.16610107868909835,
|
|
"num_tokens": 36882643.0,
|
|
"step": 17770
|
|
},
|
|
{
|
|
"entropy": 5.69529390335083,
|
|
"epoch": 1.6123911465892597,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004743195998736186,
|
|
"loss": 5.3909,
|
|
"mean_token_accuracy": 0.17147992700338363,
|
|
"num_tokens": 36893349.0,
|
|
"step": 17775
|
|
},
|
|
{
|
|
"entropy": 5.780875301361084,
|
|
"epoch": 1.612844702467344,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.00047430458626801107,
|
|
"loss": 5.4057,
|
|
"mean_token_accuracy": 0.17658130079507828,
|
|
"num_tokens": 36903713.0,
|
|
"step": 17780
|
|
},
|
|
{
|
|
"entropy": 5.594718170166016,
|
|
"epoch": 1.613298258345428,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.000474289568540734,
|
|
"loss": 5.3099,
|
|
"mean_token_accuracy": 0.17800772786140442,
|
|
"num_tokens": 36912999.0,
|
|
"step": 17785
|
|
},
|
|
{
|
|
"entropy": 5.687292242050171,
|
|
"epoch": 1.6137518142235123,
|
|
"grad_norm": 3.046875,
|
|
"learning_rate": 0.00047427454669209785,
|
|
"loss": 5.4367,
|
|
"mean_token_accuracy": 0.17026375830173493,
|
|
"num_tokens": 36923598.0,
|
|
"step": 17790
|
|
},
|
|
{
|
|
"entropy": 5.628356218338013,
|
|
"epoch": 1.6142053701015966,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.00047425952072241326,
|
|
"loss": 5.3388,
|
|
"mean_token_accuracy": 0.16974585205316545,
|
|
"num_tokens": 36933036.0,
|
|
"step": 17795
|
|
},
|
|
{
|
|
"entropy": 5.612567377090454,
|
|
"epoch": 1.6146589259796809,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.000474244490631991,
|
|
"loss": 5.4389,
|
|
"mean_token_accuracy": 0.1670399472117424,
|
|
"num_tokens": 36943137.0,
|
|
"step": 17800
|
|
},
|
|
{
|
|
"entropy": 5.777279901504516,
|
|
"epoch": 1.615112481857765,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004742294564211419,
|
|
"loss": 5.5852,
|
|
"mean_token_accuracy": 0.15988447815179824,
|
|
"num_tokens": 36955619.0,
|
|
"step": 17805
|
|
},
|
|
{
|
|
"entropy": 5.690830993652344,
|
|
"epoch": 1.615566037735849,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004742144180901769,
|
|
"loss": 5.3588,
|
|
"mean_token_accuracy": 0.18071587085723878,
|
|
"num_tokens": 36966377.0,
|
|
"step": 17810
|
|
},
|
|
{
|
|
"entropy": 5.655510759353637,
|
|
"epoch": 1.6160195936139332,
|
|
"grad_norm": 3.375,
|
|
"learning_rate": 0.00047419937563940697,
|
|
"loss": 5.3908,
|
|
"mean_token_accuracy": 0.1764805868268013,
|
|
"num_tokens": 36977100.0,
|
|
"step": 17815
|
|
},
|
|
{
|
|
"entropy": 5.632277727127075,
|
|
"epoch": 1.6164731494920175,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.00047418432906914314,
|
|
"loss": 5.4694,
|
|
"mean_token_accuracy": 0.17377229034900665,
|
|
"num_tokens": 36987120.0,
|
|
"step": 17820
|
|
},
|
|
{
|
|
"entropy": 5.671475458145141,
|
|
"epoch": 1.6169267053701017,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004741692783796967,
|
|
"loss": 5.4069,
|
|
"mean_token_accuracy": 0.17421459704637526,
|
|
"num_tokens": 36996885.0,
|
|
"step": 17825
|
|
},
|
|
{
|
|
"entropy": 5.678603410720825,
|
|
"epoch": 1.6173802612481858,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.00047415422357137876,
|
|
"loss": 5.3541,
|
|
"mean_token_accuracy": 0.1789191335439682,
|
|
"num_tokens": 37006570.0,
|
|
"step": 17830
|
|
},
|
|
{
|
|
"entropy": 5.690235900878906,
|
|
"epoch": 1.6178338171262698,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.0004741391646445008,
|
|
"loss": 5.4441,
|
|
"mean_token_accuracy": 0.1696111351251602,
|
|
"num_tokens": 37017185.0,
|
|
"step": 17835
|
|
},
|
|
{
|
|
"entropy": 5.6540594577789305,
|
|
"epoch": 1.618287373004354,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004741241015993741,
|
|
"loss": 5.4299,
|
|
"mean_token_accuracy": 0.17558567970991135,
|
|
"num_tokens": 37028386.0,
|
|
"step": 17840
|
|
},
|
|
{
|
|
"entropy": 5.607161569595337,
|
|
"epoch": 1.6187409288824384,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.00047410903443631026,
|
|
"loss": 5.3148,
|
|
"mean_token_accuracy": 0.1740579292178154,
|
|
"num_tokens": 37038326.0,
|
|
"step": 17845
|
|
},
|
|
{
|
|
"entropy": 5.738449621200561,
|
|
"epoch": 1.6191944847605226,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004740939631556209,
|
|
"loss": 5.4163,
|
|
"mean_token_accuracy": 0.17534601390361787,
|
|
"num_tokens": 37048570.0,
|
|
"step": 17850
|
|
},
|
|
{
|
|
"entropy": 5.589099359512329,
|
|
"epoch": 1.6196480406386067,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004740788877576176,
|
|
"loss": 5.3112,
|
|
"mean_token_accuracy": 0.17910967767238617,
|
|
"num_tokens": 37058909.0,
|
|
"step": 17855
|
|
},
|
|
{
|
|
"entropy": 5.614863157272339,
|
|
"epoch": 1.6201015965166907,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004740638082426121,
|
|
"loss": 5.3734,
|
|
"mean_token_accuracy": 0.18206009566783904,
|
|
"num_tokens": 37068957.0,
|
|
"step": 17860
|
|
},
|
|
{
|
|
"entropy": 5.712525367736816,
|
|
"epoch": 1.620555152394775,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.00047404872461091643,
|
|
"loss": 5.3532,
|
|
"mean_token_accuracy": 0.1704546883702278,
|
|
"num_tokens": 37080187.0,
|
|
"step": 17865
|
|
},
|
|
{
|
|
"entropy": 5.666663646697998,
|
|
"epoch": 1.6210087082728593,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.00047403363686284236,
|
|
"loss": 5.4226,
|
|
"mean_token_accuracy": 0.17072656452655793,
|
|
"num_tokens": 37090314.0,
|
|
"step": 17870
|
|
},
|
|
{
|
|
"entropy": 5.695016860961914,
|
|
"epoch": 1.6214622641509435,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.00047401854499870197,
|
|
"loss": 5.4387,
|
|
"mean_token_accuracy": 0.17307930141687394,
|
|
"num_tokens": 37099907.0,
|
|
"step": 17875
|
|
},
|
|
{
|
|
"entropy": 5.666306972503662,
|
|
"epoch": 1.6219158200290276,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.00047400344901880735,
|
|
"loss": 5.455,
|
|
"mean_token_accuracy": 0.16570448279380798,
|
|
"num_tokens": 37110495.0,
|
|
"step": 17880
|
|
},
|
|
{
|
|
"entropy": 5.738508033752441,
|
|
"epoch": 1.6223693759071116,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004739883489234707,
|
|
"loss": 5.4518,
|
|
"mean_token_accuracy": 0.17158548384904862,
|
|
"num_tokens": 37121957.0,
|
|
"step": 17885
|
|
},
|
|
{
|
|
"entropy": 5.6558459281921385,
|
|
"epoch": 1.6228229317851959,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.00047397324471300424,
|
|
"loss": 5.3465,
|
|
"mean_token_accuracy": 0.1763668790459633,
|
|
"num_tokens": 37132743.0,
|
|
"step": 17890
|
|
},
|
|
{
|
|
"entropy": 5.654357671737671,
|
|
"epoch": 1.6232764876632801,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.00047395813638772047,
|
|
"loss": 5.441,
|
|
"mean_token_accuracy": 0.1658615693449974,
|
|
"num_tokens": 37143947.0,
|
|
"step": 17895
|
|
},
|
|
{
|
|
"entropy": 5.7994874000549315,
|
|
"epoch": 1.6237300435413644,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.00047394302394793164,
|
|
"loss": 5.5215,
|
|
"mean_token_accuracy": 0.16456594169139863,
|
|
"num_tokens": 37154316.0,
|
|
"step": 17900
|
|
},
|
|
{
|
|
"entropy": 5.650878429412842,
|
|
"epoch": 1.6241835994194485,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004739279073939504,
|
|
"loss": 5.4098,
|
|
"mean_token_accuracy": 0.17563293427228927,
|
|
"num_tokens": 37164999.0,
|
|
"step": 17905
|
|
},
|
|
{
|
|
"entropy": 5.703804445266724,
|
|
"epoch": 1.6246371552975325,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004739127867260894,
|
|
"loss": 5.4367,
|
|
"mean_token_accuracy": 0.17274462133646012,
|
|
"num_tokens": 37174392.0,
|
|
"step": 17910
|
|
},
|
|
{
|
|
"entropy": 5.618399810791016,
|
|
"epoch": 1.6250907111756168,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004738976619446613,
|
|
"loss": 5.4384,
|
|
"mean_token_accuracy": 0.16613603830337526,
|
|
"num_tokens": 37185341.0,
|
|
"step": 17915
|
|
},
|
|
{
|
|
"entropy": 5.7512147426605225,
|
|
"epoch": 1.625544267053701,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.00047388253304997874,
|
|
"loss": 5.4333,
|
|
"mean_token_accuracy": 0.16576243191957474,
|
|
"num_tokens": 37196725.0,
|
|
"step": 17920
|
|
},
|
|
{
|
|
"entropy": 5.641399669647217,
|
|
"epoch": 1.6259978229317853,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004738674000423548,
|
|
"loss": 5.3255,
|
|
"mean_token_accuracy": 0.17872455567121506,
|
|
"num_tokens": 37206877.0,
|
|
"step": 17925
|
|
},
|
|
{
|
|
"entropy": 5.538093423843383,
|
|
"epoch": 1.6264513788098693,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004738522629221023,
|
|
"loss": 5.3093,
|
|
"mean_token_accuracy": 0.17440678030252457,
|
|
"num_tokens": 37217277.0,
|
|
"step": 17930
|
|
},
|
|
{
|
|
"entropy": 5.625094366073609,
|
|
"epoch": 1.6269049346879536,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004738371216895344,
|
|
"loss": 5.304,
|
|
"mean_token_accuracy": 0.1748187869787216,
|
|
"num_tokens": 37227716.0,
|
|
"step": 17935
|
|
},
|
|
{
|
|
"entropy": 5.578723907470703,
|
|
"epoch": 1.6273584905660377,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004738219763449641,
|
|
"loss": 5.4048,
|
|
"mean_token_accuracy": 0.16494585275650026,
|
|
"num_tokens": 37238178.0,
|
|
"step": 17940
|
|
},
|
|
{
|
|
"entropy": 5.625629472732544,
|
|
"epoch": 1.627812046444122,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004738068268887047,
|
|
"loss": 5.4179,
|
|
"mean_token_accuracy": 0.1752077430486679,
|
|
"num_tokens": 37248408.0,
|
|
"step": 17945
|
|
},
|
|
{
|
|
"entropy": 5.695736026763916,
|
|
"epoch": 1.6282656023222062,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004737916733210694,
|
|
"loss": 5.5199,
|
|
"mean_token_accuracy": 0.168146713078022,
|
|
"num_tokens": 37259176.0,
|
|
"step": 17950
|
|
},
|
|
{
|
|
"entropy": 5.677813243865967,
|
|
"epoch": 1.6287191582002902,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.00047377651564237165,
|
|
"loss": 5.3037,
|
|
"mean_token_accuracy": 0.17941929548978805,
|
|
"num_tokens": 37269205.0,
|
|
"step": 17955
|
|
},
|
|
{
|
|
"entropy": 5.694856739044189,
|
|
"epoch": 1.6291727140783745,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.00047376135385292494,
|
|
"loss": 5.4229,
|
|
"mean_token_accuracy": 0.18203565925359727,
|
|
"num_tokens": 37278841.0,
|
|
"step": 17960
|
|
},
|
|
{
|
|
"entropy": 5.639402294158936,
|
|
"epoch": 1.6296262699564585,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004737461879530428,
|
|
"loss": 5.4468,
|
|
"mean_token_accuracy": 0.17196953147649766,
|
|
"num_tokens": 37288487.0,
|
|
"step": 17965
|
|
},
|
|
{
|
|
"entropy": 5.700185298919678,
|
|
"epoch": 1.6300798258345428,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.00047373101794303884,
|
|
"loss": 5.4403,
|
|
"mean_token_accuracy": 0.16728301495313644,
|
|
"num_tokens": 37300086.0,
|
|
"step": 17970
|
|
},
|
|
{
|
|
"entropy": 5.715151357650757,
|
|
"epoch": 1.630533381712627,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004737158438232267,
|
|
"loss": 5.4511,
|
|
"mean_token_accuracy": 0.16204124540090561,
|
|
"num_tokens": 37310072.0,
|
|
"step": 17975
|
|
},
|
|
{
|
|
"entropy": 5.7027839660644535,
|
|
"epoch": 1.6309869375907113,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00047370066559392033,
|
|
"loss": 5.4221,
|
|
"mean_token_accuracy": 0.17666150629520416,
|
|
"num_tokens": 37320278.0,
|
|
"step": 17980
|
|
},
|
|
{
|
|
"entropy": 5.654754686355591,
|
|
"epoch": 1.6314404934687954,
|
|
"grad_norm": 3.046875,
|
|
"learning_rate": 0.00047368548325543366,
|
|
"loss": 5.3328,
|
|
"mean_token_accuracy": 0.1722416564822197,
|
|
"num_tokens": 37330741.0,
|
|
"step": 17985
|
|
},
|
|
{
|
|
"entropy": 5.6650426387786865,
|
|
"epoch": 1.6318940493468794,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004736702968080804,
|
|
"loss": 5.4261,
|
|
"mean_token_accuracy": 0.17141182869672775,
|
|
"num_tokens": 37341213.0,
|
|
"step": 17990
|
|
},
|
|
{
|
|
"entropy": 5.650553560256958,
|
|
"epoch": 1.6323476052249637,
|
|
"grad_norm": 3.03125,
|
|
"learning_rate": 0.00047365510625217483,
|
|
"loss": 5.2994,
|
|
"mean_token_accuracy": 0.17408107072114945,
|
|
"num_tokens": 37350528.0,
|
|
"step": 17995
|
|
},
|
|
{
|
|
"entropy": 5.646546745300293,
|
|
"epoch": 1.632801161103048,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.00047363991158803117,
|
|
"loss": 5.3946,
|
|
"mean_token_accuracy": 0.16936032772064208,
|
|
"num_tokens": 37359938.0,
|
|
"step": 18000
|
|
},
|
|
{
|
|
"epoch": 1.632801161103048,
|
|
"eval_entropy": 5.416080831941976,
|
|
"eval_loss": 5.452061176300049,
|
|
"eval_mean_token_accuracy": 0.1779371223045825,
|
|
"eval_num_tokens": 37359938.0,
|
|
"eval_runtime": 26.7698,
|
|
"eval_samples_per_second": 1320.894,
|
|
"eval_steps_per_second": 165.112,
|
|
"step": 18000
|
|
},
|
|
{
|
|
"entropy": 5.643016910552978,
|
|
"epoch": 1.6332547169811322,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00047362471281596334,
|
|
"loss": 5.3928,
|
|
"mean_token_accuracy": 0.1719544693827629,
|
|
"num_tokens": 37369744.0,
|
|
"step": 18005
|
|
},
|
|
{
|
|
"entropy": 5.7466846942901615,
|
|
"epoch": 1.6337082728592163,
|
|
"grad_norm": 3.125,
|
|
"learning_rate": 0.00047360950993628585,
|
|
"loss": 5.4969,
|
|
"mean_token_accuracy": 0.17240673750638963,
|
|
"num_tokens": 37380578.0,
|
|
"step": 18010
|
|
},
|
|
{
|
|
"entropy": 5.667456197738647,
|
|
"epoch": 1.6341618287373003,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004735943029493132,
|
|
"loss": 5.3818,
|
|
"mean_token_accuracy": 0.17203010022640228,
|
|
"num_tokens": 37390237.0,
|
|
"step": 18015
|
|
},
|
|
{
|
|
"entropy": 5.652147483825684,
|
|
"epoch": 1.6346153846153846,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.00047357909185535965,
|
|
"loss": 5.4336,
|
|
"mean_token_accuracy": 0.1707598701119423,
|
|
"num_tokens": 37400261.0,
|
|
"step": 18020
|
|
},
|
|
{
|
|
"entropy": 5.66914701461792,
|
|
"epoch": 1.6350689404934688,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004735638766547399,
|
|
"loss": 5.4114,
|
|
"mean_token_accuracy": 0.1755010724067688,
|
|
"num_tokens": 37410012.0,
|
|
"step": 18025
|
|
},
|
|
{
|
|
"entropy": 5.7171515941619875,
|
|
"epoch": 1.6355224963715531,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.00047354865734776857,
|
|
"loss": 5.517,
|
|
"mean_token_accuracy": 0.16210531890392305,
|
|
"num_tokens": 37420530.0,
|
|
"step": 18030
|
|
},
|
|
{
|
|
"entropy": 5.683720874786377,
|
|
"epoch": 1.6359760522496372,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004735334339347605,
|
|
"loss": 5.3811,
|
|
"mean_token_accuracy": 0.17746386528015137,
|
|
"num_tokens": 37431146.0,
|
|
"step": 18035
|
|
},
|
|
{
|
|
"entropy": 5.658093547821045,
|
|
"epoch": 1.6364296081277212,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.00047351820641603035,
|
|
"loss": 5.3269,
|
|
"mean_token_accuracy": 0.17577678710222244,
|
|
"num_tokens": 37441253.0,
|
|
"step": 18040
|
|
},
|
|
{
|
|
"entropy": 5.565347003936767,
|
|
"epoch": 1.6368831640058055,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004735029747918931,
|
|
"loss": 5.3747,
|
|
"mean_token_accuracy": 0.17229868173599244,
|
|
"num_tokens": 37451326.0,
|
|
"step": 18045
|
|
},
|
|
{
|
|
"entropy": 5.614554357528687,
|
|
"epoch": 1.6373367198838897,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.00047348773906266374,
|
|
"loss": 5.3554,
|
|
"mean_token_accuracy": 0.1771339848637581,
|
|
"num_tokens": 37462462.0,
|
|
"step": 18050
|
|
},
|
|
{
|
|
"entropy": 5.599406290054321,
|
|
"epoch": 1.637790275761974,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004734724992286574,
|
|
"loss": 5.3355,
|
|
"mean_token_accuracy": 0.1755107417702675,
|
|
"num_tokens": 37473016.0,
|
|
"step": 18055
|
|
},
|
|
{
|
|
"entropy": 5.657382965087891,
|
|
"epoch": 1.638243831640058,
|
|
"grad_norm": 4.90625,
|
|
"learning_rate": 0.0004734572552901892,
|
|
"loss": 5.4643,
|
|
"mean_token_accuracy": 0.17492182403802872,
|
|
"num_tokens": 37483737.0,
|
|
"step": 18060
|
|
},
|
|
{
|
|
"entropy": 5.6546868801116945,
|
|
"epoch": 1.638697387518142,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004734420072475743,
|
|
"loss": 5.3526,
|
|
"mean_token_accuracy": 0.17013950943946837,
|
|
"num_tokens": 37493070.0,
|
|
"step": 18065
|
|
},
|
|
{
|
|
"entropy": 5.666880893707275,
|
|
"epoch": 1.6391509433962264,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004734267551011282,
|
|
"loss": 5.3727,
|
|
"mean_token_accuracy": 0.17240895032882692,
|
|
"num_tokens": 37503696.0,
|
|
"step": 18070
|
|
},
|
|
{
|
|
"entropy": 5.5956450462341305,
|
|
"epoch": 1.6396044992743106,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004734114988511662,
|
|
"loss": 5.3904,
|
|
"mean_token_accuracy": 0.17092562168836595,
|
|
"num_tokens": 37513468.0,
|
|
"step": 18075
|
|
},
|
|
{
|
|
"entropy": 5.591035509109497,
|
|
"epoch": 1.640058055152395,
|
|
"grad_norm": 2.84375,
|
|
"learning_rate": 0.0004733962384980039,
|
|
"loss": 5.2538,
|
|
"mean_token_accuracy": 0.18059017062187194,
|
|
"num_tokens": 37523631.0,
|
|
"step": 18080
|
|
},
|
|
{
|
|
"entropy": 5.695684194564819,
|
|
"epoch": 1.640511611030479,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004733809740419568,
|
|
"loss": 5.4463,
|
|
"mean_token_accuracy": 0.17196233123540877,
|
|
"num_tokens": 37534602.0,
|
|
"step": 18085
|
|
},
|
|
{
|
|
"entropy": 5.60761661529541,
|
|
"epoch": 1.640965166908563,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.00047336570548334053,
|
|
"loss": 5.3609,
|
|
"mean_token_accuracy": 0.1761796236038208,
|
|
"num_tokens": 37544547.0,
|
|
"step": 18090
|
|
},
|
|
{
|
|
"entropy": 5.667062568664551,
|
|
"epoch": 1.6414187227866472,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.00047335043282247105,
|
|
"loss": 5.3652,
|
|
"mean_token_accuracy": 0.17026483565568923,
|
|
"num_tokens": 37554903.0,
|
|
"step": 18095
|
|
},
|
|
{
|
|
"entropy": 5.6601931095123295,
|
|
"epoch": 1.6418722786647315,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.00047333515605966396,
|
|
"loss": 5.3009,
|
|
"mean_token_accuracy": 0.17445314377546312,
|
|
"num_tokens": 37565586.0,
|
|
"step": 18100
|
|
},
|
|
{
|
|
"entropy": 5.67895359992981,
|
|
"epoch": 1.6423258345428158,
|
|
"grad_norm": 3.421875,
|
|
"learning_rate": 0.00047331987519523533,
|
|
"loss": 5.3982,
|
|
"mean_token_accuracy": 0.1797369971871376,
|
|
"num_tokens": 37575996.0,
|
|
"step": 18105
|
|
},
|
|
{
|
|
"entropy": 5.584648942947387,
|
|
"epoch": 1.6427793904208998,
|
|
"grad_norm": 2.890625,
|
|
"learning_rate": 0.0004733045902295012,
|
|
"loss": 5.2902,
|
|
"mean_token_accuracy": 0.16891822814941407,
|
|
"num_tokens": 37586441.0,
|
|
"step": 18110
|
|
},
|
|
{
|
|
"entropy": 5.654280042648315,
|
|
"epoch": 1.643232946298984,
|
|
"grad_norm": 3.640625,
|
|
"learning_rate": 0.00047328930116277755,
|
|
"loss": 5.4314,
|
|
"mean_token_accuracy": 0.1742355763912201,
|
|
"num_tokens": 37598226.0,
|
|
"step": 18115
|
|
},
|
|
{
|
|
"entropy": 5.6726690292358395,
|
|
"epoch": 1.6436865021770681,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004732740079953806,
|
|
"loss": 5.3867,
|
|
"mean_token_accuracy": 0.17353078722953796,
|
|
"num_tokens": 37609102.0,
|
|
"step": 18120
|
|
},
|
|
{
|
|
"entropy": 5.661259365081787,
|
|
"epoch": 1.6441400580551524,
|
|
"grad_norm": 2.875,
|
|
"learning_rate": 0.0004732587107276267,
|
|
"loss": 5.3953,
|
|
"mean_token_accuracy": 0.17297383546829223,
|
|
"num_tokens": 37619349.0,
|
|
"step": 18125
|
|
},
|
|
{
|
|
"entropy": 5.6543418884277346,
|
|
"epoch": 1.6445936139332367,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.00047324340935983225,
|
|
"loss": 5.3864,
|
|
"mean_token_accuracy": 0.18282674849033356,
|
|
"num_tokens": 37629844.0,
|
|
"step": 18130
|
|
},
|
|
{
|
|
"entropy": 5.590123176574707,
|
|
"epoch": 1.6450471698113207,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.00047322810389231333,
|
|
"loss": 5.3133,
|
|
"mean_token_accuracy": 0.17169909328222274,
|
|
"num_tokens": 37639339.0,
|
|
"step": 18135
|
|
},
|
|
{
|
|
"entropy": 5.5904889583587645,
|
|
"epoch": 1.645500725689405,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004732127943253868,
|
|
"loss": 5.3067,
|
|
"mean_token_accuracy": 0.1766883611679077,
|
|
"num_tokens": 37648836.0,
|
|
"step": 18140
|
|
},
|
|
{
|
|
"entropy": 5.658511447906494,
|
|
"epoch": 1.645954281567489,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004731974806593693,
|
|
"loss": 5.349,
|
|
"mean_token_accuracy": 0.1792044907808304,
|
|
"num_tokens": 37658424.0,
|
|
"step": 18145
|
|
},
|
|
{
|
|
"entropy": 5.6705022811889645,
|
|
"epoch": 1.6464078374455733,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.00047318216289457727,
|
|
"loss": 5.374,
|
|
"mean_token_accuracy": 0.1767248883843422,
|
|
"num_tokens": 37669849.0,
|
|
"step": 18150
|
|
},
|
|
{
|
|
"entropy": 5.597399377822876,
|
|
"epoch": 1.6468613933236576,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.00047316684103132766,
|
|
"loss": 5.3355,
|
|
"mean_token_accuracy": 0.17555111050605773,
|
|
"num_tokens": 37678987.0,
|
|
"step": 18155
|
|
},
|
|
{
|
|
"entropy": 5.684874868392944,
|
|
"epoch": 1.6473149492017418,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.0004731515150699372,
|
|
"loss": 5.3867,
|
|
"mean_token_accuracy": 0.17189523801207543,
|
|
"num_tokens": 37689692.0,
|
|
"step": 18160
|
|
},
|
|
{
|
|
"entropy": 5.703072834014892,
|
|
"epoch": 1.6477685050798259,
|
|
"grad_norm": 4.125,
|
|
"learning_rate": 0.00047313618501072303,
|
|
"loss": 5.5296,
|
|
"mean_token_accuracy": 0.16913227885961532,
|
|
"num_tokens": 37700092.0,
|
|
"step": 18165
|
|
},
|
|
{
|
|
"entropy": 5.629307746887207,
|
|
"epoch": 1.64822206095791,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.00047312085085400194,
|
|
"loss": 5.4312,
|
|
"mean_token_accuracy": 0.1718517243862152,
|
|
"num_tokens": 37710305.0,
|
|
"step": 18170
|
|
},
|
|
{
|
|
"entropy": 5.736398792266845,
|
|
"epoch": 1.6486756168359942,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.00047310551260009126,
|
|
"loss": 5.4936,
|
|
"mean_token_accuracy": 0.1635923907160759,
|
|
"num_tokens": 37720451.0,
|
|
"step": 18175
|
|
},
|
|
{
|
|
"entropy": 5.680885171890258,
|
|
"epoch": 1.6491291727140784,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.000473090170249308,
|
|
"loss": 5.4105,
|
|
"mean_token_accuracy": 0.17822588682174684,
|
|
"num_tokens": 37731952.0,
|
|
"step": 18180
|
|
},
|
|
{
|
|
"entropy": 5.594832515716552,
|
|
"epoch": 1.6495827285921627,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004730748238019696,
|
|
"loss": 5.3146,
|
|
"mean_token_accuracy": 0.17393461614847183,
|
|
"num_tokens": 37742201.0,
|
|
"step": 18185
|
|
},
|
|
{
|
|
"entropy": 5.5848473072052,
|
|
"epoch": 1.6500362844702468,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.00047305947325839337,
|
|
"loss": 5.3634,
|
|
"mean_token_accuracy": 0.1762213945388794,
|
|
"num_tokens": 37753317.0,
|
|
"step": 18190
|
|
},
|
|
{
|
|
"entropy": 5.682903051376343,
|
|
"epoch": 1.6504898403483308,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004730441186188968,
|
|
"loss": 5.3847,
|
|
"mean_token_accuracy": 0.17651373594999314,
|
|
"num_tokens": 37763452.0,
|
|
"step": 18195
|
|
},
|
|
{
|
|
"entropy": 5.642944383621216,
|
|
"epoch": 1.650943396226415,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00047302875988379734,
|
|
"loss": 5.2999,
|
|
"mean_token_accuracy": 0.17861631959676744,
|
|
"num_tokens": 37772804.0,
|
|
"step": 18200
|
|
},
|
|
{
|
|
"entropy": 5.596706819534302,
|
|
"epoch": 1.6513969521044993,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.00047301339705341266,
|
|
"loss": 5.409,
|
|
"mean_token_accuracy": 0.16562383025884628,
|
|
"num_tokens": 37784441.0,
|
|
"step": 18205
|
|
},
|
|
{
|
|
"entropy": 5.6764942646026615,
|
|
"epoch": 1.6518505079825836,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.00047299803012806056,
|
|
"loss": 5.4195,
|
|
"mean_token_accuracy": 0.1758231222629547,
|
|
"num_tokens": 37795103.0,
|
|
"step": 18210
|
|
},
|
|
{
|
|
"entropy": 5.6812488555908205,
|
|
"epoch": 1.6523040638606676,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004729826591080586,
|
|
"loss": 5.3922,
|
|
"mean_token_accuracy": 0.1719244584441185,
|
|
"num_tokens": 37806654.0,
|
|
"step": 18215
|
|
},
|
|
{
|
|
"entropy": 5.638551330566406,
|
|
"epoch": 1.6527576197387517,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.00047296728399372483,
|
|
"loss": 5.412,
|
|
"mean_token_accuracy": 0.17587378472089768,
|
|
"num_tokens": 37816673.0,
|
|
"step": 18220
|
|
},
|
|
{
|
|
"entropy": 5.632792901992798,
|
|
"epoch": 1.653211175616836,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.00047295190478537725,
|
|
"loss": 5.3991,
|
|
"mean_token_accuracy": 0.16898447573184966,
|
|
"num_tokens": 37827389.0,
|
|
"step": 18225
|
|
},
|
|
{
|
|
"entropy": 5.747861242294311,
|
|
"epoch": 1.6536647314949202,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.00047293652148333376,
|
|
"loss": 5.4284,
|
|
"mean_token_accuracy": 0.17220207303762436,
|
|
"num_tokens": 37838087.0,
|
|
"step": 18230
|
|
},
|
|
{
|
|
"entropy": 5.582599925994873,
|
|
"epoch": 1.6541182873730045,
|
|
"grad_norm": 3.703125,
|
|
"learning_rate": 0.00047292113408791266,
|
|
"loss": 5.2889,
|
|
"mean_token_accuracy": 0.17738645523786545,
|
|
"num_tokens": 37848630.0,
|
|
"step": 18235
|
|
},
|
|
{
|
|
"entropy": 5.555059242248535,
|
|
"epoch": 1.6545718432510885,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00047290574259943195,
|
|
"loss": 5.275,
|
|
"mean_token_accuracy": 0.18653450459241866,
|
|
"num_tokens": 37858689.0,
|
|
"step": 18240
|
|
},
|
|
{
|
|
"entropy": 5.670050048828125,
|
|
"epoch": 1.6550253991291726,
|
|
"grad_norm": 3.265625,
|
|
"learning_rate": 0.00047289034701821013,
|
|
"loss": 5.442,
|
|
"mean_token_accuracy": 0.17385028153657914,
|
|
"num_tokens": 37869049.0,
|
|
"step": 18245
|
|
},
|
|
{
|
|
"entropy": 5.599637746810913,
|
|
"epoch": 1.6554789550072568,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00047287494734456545,
|
|
"loss": 5.3542,
|
|
"mean_token_accuracy": 0.17090777009725572,
|
|
"num_tokens": 37879495.0,
|
|
"step": 18250
|
|
},
|
|
{
|
|
"entropy": 5.661890506744385,
|
|
"epoch": 1.655932510885341,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.00047285954357881646,
|
|
"loss": 5.4081,
|
|
"mean_token_accuracy": 0.17140484750270843,
|
|
"num_tokens": 37889442.0,
|
|
"step": 18255
|
|
},
|
|
{
|
|
"entropy": 5.727365589141845,
|
|
"epoch": 1.6563860667634254,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004728441357212817,
|
|
"loss": 5.5192,
|
|
"mean_token_accuracy": 0.16357721984386445,
|
|
"num_tokens": 37900147.0,
|
|
"step": 18260
|
|
},
|
|
{
|
|
"entropy": 5.685968065261841,
|
|
"epoch": 1.6568396226415094,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004728287237722798,
|
|
"loss": 5.351,
|
|
"mean_token_accuracy": 0.17148176431655884,
|
|
"num_tokens": 37910307.0,
|
|
"step": 18265
|
|
},
|
|
{
|
|
"entropy": 5.57409553527832,
|
|
"epoch": 1.6572931785195935,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.0004728133077321295,
|
|
"loss": 5.3311,
|
|
"mean_token_accuracy": 0.16771164238452912,
|
|
"num_tokens": 37920838.0,
|
|
"step": 18270
|
|
},
|
|
{
|
|
"entropy": 5.667352151870728,
|
|
"epoch": 1.6577467343976777,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.00047279788760114954,
|
|
"loss": 5.4046,
|
|
"mean_token_accuracy": 0.17411608397960662,
|
|
"num_tokens": 37930717.0,
|
|
"step": 18275
|
|
},
|
|
{
|
|
"entropy": 5.746258735656738,
|
|
"epoch": 1.658200290275762,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004727824633796589,
|
|
"loss": 5.4158,
|
|
"mean_token_accuracy": 0.16951513439416885,
|
|
"num_tokens": 37941254.0,
|
|
"step": 18280
|
|
},
|
|
{
|
|
"entropy": 5.618251323699951,
|
|
"epoch": 1.6586538461538463,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004727670350679765,
|
|
"loss": 5.4003,
|
|
"mean_token_accuracy": 0.18202670514583588,
|
|
"num_tokens": 37952132.0,
|
|
"step": 18285
|
|
},
|
|
{
|
|
"entropy": 5.641467714309693,
|
|
"epoch": 1.6591074020319303,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004727516026664214,
|
|
"loss": 5.3881,
|
|
"mean_token_accuracy": 0.17911292016506195,
|
|
"num_tokens": 37962026.0,
|
|
"step": 18290
|
|
},
|
|
{
|
|
"entropy": 5.655465698242187,
|
|
"epoch": 1.6595609579100146,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004727361661753128,
|
|
"loss": 5.3162,
|
|
"mean_token_accuracy": 0.17448180317878723,
|
|
"num_tokens": 37972911.0,
|
|
"step": 18295
|
|
},
|
|
{
|
|
"entropy": 5.663960313796997,
|
|
"epoch": 1.6600145137880986,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004727207255949699,
|
|
"loss": 5.3534,
|
|
"mean_token_accuracy": 0.17574661374092101,
|
|
"num_tokens": 37983577.0,
|
|
"step": 18300
|
|
},
|
|
{
|
|
"entropy": 5.702342367172241,
|
|
"epoch": 1.6604680696661829,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.00047270528092571197,
|
|
"loss": 5.4607,
|
|
"mean_token_accuracy": 0.1680197983980179,
|
|
"num_tokens": 37994294.0,
|
|
"step": 18305
|
|
},
|
|
{
|
|
"entropy": 5.640758037567139,
|
|
"epoch": 1.6609216255442671,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004726898321678584,
|
|
"loss": 5.3987,
|
|
"mean_token_accuracy": 0.1784611612558365,
|
|
"num_tokens": 38005144.0,
|
|
"step": 18310
|
|
},
|
|
{
|
|
"entropy": 5.623813629150391,
|
|
"epoch": 1.6613751814223512,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004726743793217288,
|
|
"loss": 5.4287,
|
|
"mean_token_accuracy": 0.17360378950834274,
|
|
"num_tokens": 38015277.0,
|
|
"step": 18315
|
|
},
|
|
{
|
|
"entropy": 5.718982744216919,
|
|
"epoch": 1.6618287373004355,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.00047265892238764265,
|
|
"loss": 5.3675,
|
|
"mean_token_accuracy": 0.17518638223409652,
|
|
"num_tokens": 38027530.0,
|
|
"step": 18320
|
|
},
|
|
{
|
|
"entropy": 5.684377241134643,
|
|
"epoch": 1.6622822931785195,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.0004726434613659196,
|
|
"loss": 5.4509,
|
|
"mean_token_accuracy": 0.17049351334571838,
|
|
"num_tokens": 38036895.0,
|
|
"step": 18325
|
|
},
|
|
{
|
|
"entropy": 5.692365980148315,
|
|
"epoch": 1.6627358490566038,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004726279962568794,
|
|
"loss": 5.465,
|
|
"mean_token_accuracy": 0.17064944058656692,
|
|
"num_tokens": 38047001.0,
|
|
"step": 18330
|
|
},
|
|
{
|
|
"entropy": 5.632791900634766,
|
|
"epoch": 1.663189404934688,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004726125270608419,
|
|
"loss": 5.3617,
|
|
"mean_token_accuracy": 0.1808722123503685,
|
|
"num_tokens": 38056815.0,
|
|
"step": 18335
|
|
},
|
|
{
|
|
"entropy": 5.68270206451416,
|
|
"epoch": 1.6636429608127723,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.00047259705377812703,
|
|
"loss": 5.4223,
|
|
"mean_token_accuracy": 0.17136966735124587,
|
|
"num_tokens": 38067139.0,
|
|
"step": 18340
|
|
},
|
|
{
|
|
"entropy": 5.682863759994507,
|
|
"epoch": 1.6640965166908563,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004725815764090546,
|
|
"loss": 5.3555,
|
|
"mean_token_accuracy": 0.1786683604121208,
|
|
"num_tokens": 38076824.0,
|
|
"step": 18345
|
|
},
|
|
{
|
|
"entropy": 5.62578763961792,
|
|
"epoch": 1.6645500725689404,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.00047256609495394494,
|
|
"loss": 5.4053,
|
|
"mean_token_accuracy": 0.17157495021820068,
|
|
"num_tokens": 38087517.0,
|
|
"step": 18350
|
|
},
|
|
{
|
|
"entropy": 5.6803083419799805,
|
|
"epoch": 1.6650036284470247,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000472550609413118,
|
|
"loss": 5.4017,
|
|
"mean_token_accuracy": 0.16848212480545044,
|
|
"num_tokens": 38098499.0,
|
|
"step": 18355
|
|
},
|
|
{
|
|
"entropy": 5.622167778015137,
|
|
"epoch": 1.665457184325109,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004725351197868942,
|
|
"loss": 5.3736,
|
|
"mean_token_accuracy": 0.1753442481160164,
|
|
"num_tokens": 38108327.0,
|
|
"step": 18360
|
|
},
|
|
{
|
|
"entropy": 5.699132251739502,
|
|
"epoch": 1.6659107402031932,
|
|
"grad_norm": 3.390625,
|
|
"learning_rate": 0.00047251962607559373,
|
|
"loss": 5.4076,
|
|
"mean_token_accuracy": 0.16830229759216309,
|
|
"num_tokens": 38118667.0,
|
|
"step": 18365
|
|
},
|
|
{
|
|
"entropy": 5.6302886486053465,
|
|
"epoch": 1.6663642960812772,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.00047250412827953717,
|
|
"loss": 5.3572,
|
|
"mean_token_accuracy": 0.17750990241765977,
|
|
"num_tokens": 38128571.0,
|
|
"step": 18370
|
|
},
|
|
{
|
|
"entropy": 5.658462762832642,
|
|
"epoch": 1.6668178519593613,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004724886263990448,
|
|
"loss": 5.4823,
|
|
"mean_token_accuracy": 0.16648177951574325,
|
|
"num_tokens": 38138921.0,
|
|
"step": 18375
|
|
},
|
|
{
|
|
"entropy": 5.682944297790527,
|
|
"epoch": 1.6672714078374455,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004724731204344372,
|
|
"loss": 5.4212,
|
|
"mean_token_accuracy": 0.16866416931152345,
|
|
"num_tokens": 38148858.0,
|
|
"step": 18380
|
|
},
|
|
{
|
|
"entropy": 5.5965070724487305,
|
|
"epoch": 1.6677249637155298,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.00047245761038603536,
|
|
"loss": 5.33,
|
|
"mean_token_accuracy": 0.174160698056221,
|
|
"num_tokens": 38159107.0,
|
|
"step": 18385
|
|
},
|
|
{
|
|
"entropy": 5.747486400604248,
|
|
"epoch": 1.668178519593614,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.00047244209625415975,
|
|
"loss": 5.4657,
|
|
"mean_token_accuracy": 0.16497890204191207,
|
|
"num_tokens": 38169228.0,
|
|
"step": 18390
|
|
},
|
|
{
|
|
"entropy": 5.7210297107696535,
|
|
"epoch": 1.6686320754716981,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004724265780391312,
|
|
"loss": 5.4112,
|
|
"mean_token_accuracy": 0.17308203279972076,
|
|
"num_tokens": 38179175.0,
|
|
"step": 18395
|
|
},
|
|
{
|
|
"entropy": 5.631084680557251,
|
|
"epoch": 1.6690856313497822,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004724110557412708,
|
|
"loss": 5.4144,
|
|
"mean_token_accuracy": 0.17391143143177032,
|
|
"num_tokens": 38188537.0,
|
|
"step": 18400
|
|
},
|
|
{
|
|
"entropy": 5.651392793655395,
|
|
"epoch": 1.6695391872278664,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.00047239552936089943,
|
|
"loss": 5.3947,
|
|
"mean_token_accuracy": 0.17216247469186782,
|
|
"num_tokens": 38198972.0,
|
|
"step": 18405
|
|
},
|
|
{
|
|
"entropy": 5.6211648941040036,
|
|
"epoch": 1.6699927431059507,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00047237999889833816,
|
|
"loss": 5.291,
|
|
"mean_token_accuracy": 0.17303640246391297,
|
|
"num_tokens": 38209472.0,
|
|
"step": 18410
|
|
},
|
|
{
|
|
"entropy": 5.522346353530883,
|
|
"epoch": 1.670446298984035,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00047236446435390826,
|
|
"loss": 5.3031,
|
|
"mean_token_accuracy": 0.1733207106590271,
|
|
"num_tokens": 38219977.0,
|
|
"step": 18415
|
|
},
|
|
{
|
|
"entropy": 5.654332685470581,
|
|
"epoch": 1.670899854862119,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00047234892572793093,
|
|
"loss": 5.3903,
|
|
"mean_token_accuracy": 0.1742865487933159,
|
|
"num_tokens": 38230492.0,
|
|
"step": 18420
|
|
},
|
|
{
|
|
"entropy": 5.641199445724487,
|
|
"epoch": 1.671353410740203,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004723333830207275,
|
|
"loss": 5.3599,
|
|
"mean_token_accuracy": 0.16987651586532593,
|
|
"num_tokens": 38240799.0,
|
|
"step": 18425
|
|
},
|
|
{
|
|
"entropy": 5.623621559143066,
|
|
"epoch": 1.6718069666182873,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00047231783623261954,
|
|
"loss": 5.3478,
|
|
"mean_token_accuracy": 0.16964757591485977,
|
|
"num_tokens": 38251439.0,
|
|
"step": 18430
|
|
},
|
|
{
|
|
"entropy": 5.6987738609313965,
|
|
"epoch": 1.6722605224963716,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.0004723022853639283,
|
|
"loss": 5.5004,
|
|
"mean_token_accuracy": 0.17003905326128005,
|
|
"num_tokens": 38261795.0,
|
|
"step": 18435
|
|
},
|
|
{
|
|
"entropy": 5.615638542175293,
|
|
"epoch": 1.6727140783744558,
|
|
"grad_norm": 3.21875,
|
|
"learning_rate": 0.0004722867304149756,
|
|
"loss": 5.337,
|
|
"mean_token_accuracy": 0.17484993785619735,
|
|
"num_tokens": 38272172.0,
|
|
"step": 18440
|
|
},
|
|
{
|
|
"entropy": 5.655874252319336,
|
|
"epoch": 1.67316763425254,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004722711713860831,
|
|
"loss": 5.4482,
|
|
"mean_token_accuracy": 0.1641718178987503,
|
|
"num_tokens": 38282829.0,
|
|
"step": 18445
|
|
},
|
|
{
|
|
"entropy": 5.728269863128662,
|
|
"epoch": 1.673621190130624,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004722556082775724,
|
|
"loss": 5.462,
|
|
"mean_token_accuracy": 0.17394049614667892,
|
|
"num_tokens": 38293793.0,
|
|
"step": 18450
|
|
},
|
|
{
|
|
"entropy": 5.719940328598023,
|
|
"epoch": 1.6740747460087082,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004722400410897655,
|
|
"loss": 5.414,
|
|
"mean_token_accuracy": 0.17267084419727324,
|
|
"num_tokens": 38302577.0,
|
|
"step": 18455
|
|
},
|
|
{
|
|
"entropy": 5.666782283782959,
|
|
"epoch": 1.6745283018867925,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004722244698229842,
|
|
"loss": 5.3792,
|
|
"mean_token_accuracy": 0.168960802257061,
|
|
"num_tokens": 38312571.0,
|
|
"step": 18460
|
|
},
|
|
{
|
|
"entropy": 5.662950325012207,
|
|
"epoch": 1.6749818577648767,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.00047220889447755073,
|
|
"loss": 5.3317,
|
|
"mean_token_accuracy": 0.1760710746049881,
|
|
"num_tokens": 38323544.0,
|
|
"step": 18465
|
|
},
|
|
{
|
|
"entropy": 5.723745489120484,
|
|
"epoch": 1.6754354136429608,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004721933150537869,
|
|
"loss": 5.4161,
|
|
"mean_token_accuracy": 0.17267605513334275,
|
|
"num_tokens": 38334509.0,
|
|
"step": 18470
|
|
},
|
|
{
|
|
"entropy": 5.558260250091553,
|
|
"epoch": 1.675888969521045,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00047217773155201526,
|
|
"loss": 5.3171,
|
|
"mean_token_accuracy": 0.17648527026176453,
|
|
"num_tokens": 38344747.0,
|
|
"step": 18475
|
|
},
|
|
{
|
|
"entropy": 5.664712238311767,
|
|
"epoch": 1.676342525399129,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00047216214397255776,
|
|
"loss": 5.4203,
|
|
"mean_token_accuracy": 0.16821975409984588,
|
|
"num_tokens": 38355671.0,
|
|
"step": 18480
|
|
},
|
|
{
|
|
"entropy": 5.687516164779663,
|
|
"epoch": 1.6767960812772134,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.00047214655231573693,
|
|
"loss": 5.4159,
|
|
"mean_token_accuracy": 0.17539804577827453,
|
|
"num_tokens": 38366368.0,
|
|
"step": 18485
|
|
},
|
|
{
|
|
"entropy": 5.677178239822387,
|
|
"epoch": 1.6772496371552976,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004721309565818752,
|
|
"loss": 5.4818,
|
|
"mean_token_accuracy": 0.16989386826753616,
|
|
"num_tokens": 38377322.0,
|
|
"step": 18490
|
|
},
|
|
{
|
|
"entropy": 5.706867313385009,
|
|
"epoch": 1.6777031930333817,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00047211535677129496,
|
|
"loss": 5.4473,
|
|
"mean_token_accuracy": 0.17131308913230897,
|
|
"num_tokens": 38389204.0,
|
|
"step": 18495
|
|
},
|
|
{
|
|
"entropy": 5.667079734802246,
|
|
"epoch": 1.678156748911466,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.00047209975288431893,
|
|
"loss": 5.4122,
|
|
"mean_token_accuracy": 0.16819470524787902,
|
|
"num_tokens": 38399117.0,
|
|
"step": 18500
|
|
},
|
|
{
|
|
"entropy": 5.668642663955689,
|
|
"epoch": 1.67861030478955,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.00047208414492126986,
|
|
"loss": 5.3814,
|
|
"mean_token_accuracy": 0.16863546818494796,
|
|
"num_tokens": 38410341.0,
|
|
"step": 18505
|
|
},
|
|
{
|
|
"entropy": 5.667917680740357,
|
|
"epoch": 1.6790638606676342,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.00047206853288247043,
|
|
"loss": 5.4398,
|
|
"mean_token_accuracy": 0.1675254672765732,
|
|
"num_tokens": 38422742.0,
|
|
"step": 18510
|
|
},
|
|
{
|
|
"entropy": 5.661226511001587,
|
|
"epoch": 1.6795174165457185,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.00047205291676824345,
|
|
"loss": 5.4531,
|
|
"mean_token_accuracy": 0.16555930972099303,
|
|
"num_tokens": 38433022.0,
|
|
"step": 18515
|
|
},
|
|
{
|
|
"entropy": 5.706762886047363,
|
|
"epoch": 1.6799709724238028,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.000472037296578912,
|
|
"loss": 5.416,
|
|
"mean_token_accuracy": 0.1675378978252411,
|
|
"num_tokens": 38444325.0,
|
|
"step": 18520
|
|
},
|
|
{
|
|
"entropy": 5.613591527938842,
|
|
"epoch": 1.6804245283018868,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.000472021672314799,
|
|
"loss": 5.329,
|
|
"mean_token_accuracy": 0.176575468480587,
|
|
"num_tokens": 38454576.0,
|
|
"step": 18525
|
|
},
|
|
{
|
|
"entropy": 5.675047302246094,
|
|
"epoch": 1.6808780841799709,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00047200604397622763,
|
|
"loss": 5.3369,
|
|
"mean_token_accuracy": 0.17943419218063356,
|
|
"num_tokens": 38465090.0,
|
|
"step": 18530
|
|
},
|
|
{
|
|
"entropy": 5.721300935745239,
|
|
"epoch": 1.6813316400580551,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004719904115635211,
|
|
"loss": 5.5694,
|
|
"mean_token_accuracy": 0.16057168394327165,
|
|
"num_tokens": 38477253.0,
|
|
"step": 18535
|
|
},
|
|
{
|
|
"entropy": 5.703014755249024,
|
|
"epoch": 1.6817851959361394,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004719747750770026,
|
|
"loss": 5.4974,
|
|
"mean_token_accuracy": 0.16343106627464293,
|
|
"num_tokens": 38488040.0,
|
|
"step": 18540
|
|
},
|
|
{
|
|
"entropy": 5.600345325469971,
|
|
"epoch": 1.6822387518142237,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004719591345169956,
|
|
"loss": 5.3612,
|
|
"mean_token_accuracy": 0.17844004184007645,
|
|
"num_tokens": 38498016.0,
|
|
"step": 18545
|
|
},
|
|
{
|
|
"entropy": 5.705804443359375,
|
|
"epoch": 1.6826923076923077,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.00047194348988382345,
|
|
"loss": 5.4757,
|
|
"mean_token_accuracy": 0.1663868948817253,
|
|
"num_tokens": 38508996.0,
|
|
"step": 18550
|
|
},
|
|
{
|
|
"entropy": 5.674479341506958,
|
|
"epoch": 1.6831458635703918,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004719278411778097,
|
|
"loss": 5.4275,
|
|
"mean_token_accuracy": 0.17415012717247008,
|
|
"num_tokens": 38519608.0,
|
|
"step": 18555
|
|
},
|
|
{
|
|
"entropy": 5.637381172180175,
|
|
"epoch": 1.683599419448476,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00047191218839927817,
|
|
"loss": 5.3848,
|
|
"mean_token_accuracy": 0.170048551261425,
|
|
"num_tokens": 38530737.0,
|
|
"step": 18560
|
|
},
|
|
{
|
|
"entropy": 5.6512611389160154,
|
|
"epoch": 1.6840529753265603,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004718965315485523,
|
|
"loss": 5.3161,
|
|
"mean_token_accuracy": 0.1756977304816246,
|
|
"num_tokens": 38540925.0,
|
|
"step": 18565
|
|
},
|
|
{
|
|
"entropy": 5.629465246200562,
|
|
"epoch": 1.6845065312046446,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004718808706259561,
|
|
"loss": 5.4134,
|
|
"mean_token_accuracy": 0.16729561388492584,
|
|
"num_tokens": 38553176.0,
|
|
"step": 18570
|
|
},
|
|
{
|
|
"entropy": 5.674219417572021,
|
|
"epoch": 1.6849600870827286,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.00047186520563181325,
|
|
"loss": 5.4332,
|
|
"mean_token_accuracy": 0.1690286099910736,
|
|
"num_tokens": 38563394.0,
|
|
"step": 18575
|
|
},
|
|
{
|
|
"entropy": 5.704145050048828,
|
|
"epoch": 1.6854136429608126,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004718495365664477,
|
|
"loss": 5.4078,
|
|
"mean_token_accuracy": 0.17212702631950377,
|
|
"num_tokens": 38573243.0,
|
|
"step": 18580
|
|
},
|
|
{
|
|
"entropy": 5.67421555519104,
|
|
"epoch": 1.685867198838897,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.00047183386343018364,
|
|
"loss": 5.4096,
|
|
"mean_token_accuracy": 0.16571134179830552,
|
|
"num_tokens": 38584014.0,
|
|
"step": 18585
|
|
},
|
|
{
|
|
"entropy": 5.619153213500977,
|
|
"epoch": 1.6863207547169812,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004718181862233451,
|
|
"loss": 5.3561,
|
|
"mean_token_accuracy": 0.17566684484481812,
|
|
"num_tokens": 38594467.0,
|
|
"step": 18590
|
|
},
|
|
{
|
|
"entropy": 5.712275743484497,
|
|
"epoch": 1.6867743105950654,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004718025049462563,
|
|
"loss": 5.4234,
|
|
"mean_token_accuracy": 0.17392756640911103,
|
|
"num_tokens": 38604407.0,
|
|
"step": 18595
|
|
},
|
|
{
|
|
"entropy": 5.665349102020263,
|
|
"epoch": 1.6872278664731495,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004717868195992416,
|
|
"loss": 5.42,
|
|
"mean_token_accuracy": 0.17348481267690657,
|
|
"num_tokens": 38614508.0,
|
|
"step": 18600
|
|
},
|
|
{
|
|
"entropy": 5.686980772018432,
|
|
"epoch": 1.6876814223512335,
|
|
"grad_norm": 3.140625,
|
|
"learning_rate": 0.0004717711301826253,
|
|
"loss": 5.4347,
|
|
"mean_token_accuracy": 0.17064355462789535,
|
|
"num_tokens": 38626244.0,
|
|
"step": 18605
|
|
},
|
|
{
|
|
"entropy": 5.617934656143189,
|
|
"epoch": 1.6881349782293178,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00047175543669673186,
|
|
"loss": 5.374,
|
|
"mean_token_accuracy": 0.16954473704099654,
|
|
"num_tokens": 38636694.0,
|
|
"step": 18610
|
|
},
|
|
{
|
|
"entropy": 5.724964189529419,
|
|
"epoch": 1.688588534107402,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.00047173973914188587,
|
|
"loss": 5.4739,
|
|
"mean_token_accuracy": 0.1696009799838066,
|
|
"num_tokens": 38647414.0,
|
|
"step": 18615
|
|
},
|
|
{
|
|
"entropy": 5.665409183502197,
|
|
"epoch": 1.6890420899854863,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00047172403751841196,
|
|
"loss": 5.3867,
|
|
"mean_token_accuracy": 0.1723177656531334,
|
|
"num_tokens": 38657425.0,
|
|
"step": 18620
|
|
},
|
|
{
|
|
"entropy": 5.682467699050903,
|
|
"epoch": 1.6894956458635704,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.00047170833182663485,
|
|
"loss": 5.4011,
|
|
"mean_token_accuracy": 0.17273204028606415,
|
|
"num_tokens": 38667751.0,
|
|
"step": 18625
|
|
},
|
|
{
|
|
"entropy": 5.538998126983643,
|
|
"epoch": 1.6899492017416544,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004716926220668793,
|
|
"loss": 5.2948,
|
|
"mean_token_accuracy": 0.18344302773475646,
|
|
"num_tokens": 38676918.0,
|
|
"step": 18630
|
|
},
|
|
{
|
|
"entropy": 5.6284832000732425,
|
|
"epoch": 1.6904027576197387,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.00047167690823947015,
|
|
"loss": 5.3813,
|
|
"mean_token_accuracy": 0.17748730927705764,
|
|
"num_tokens": 38685887.0,
|
|
"step": 18635
|
|
},
|
|
{
|
|
"entropy": 5.6294450759887695,
|
|
"epoch": 1.690856313497823,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004716611903447325,
|
|
"loss": 5.3866,
|
|
"mean_token_accuracy": 0.1748419925570488,
|
|
"num_tokens": 38696179.0,
|
|
"step": 18640
|
|
},
|
|
{
|
|
"entropy": 5.643867063522339,
|
|
"epoch": 1.6913098693759072,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004716454683829912,
|
|
"loss": 5.3716,
|
|
"mean_token_accuracy": 0.17171803563833238,
|
|
"num_tokens": 38705777.0,
|
|
"step": 18645
|
|
},
|
|
{
|
|
"entropy": 5.618920946121216,
|
|
"epoch": 1.6917634252539913,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.00047162974235457163,
|
|
"loss": 5.4106,
|
|
"mean_token_accuracy": 0.1726861983537674,
|
|
"num_tokens": 38717709.0,
|
|
"step": 18650
|
|
},
|
|
{
|
|
"entropy": 5.659681940078736,
|
|
"epoch": 1.6922169811320755,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004716140122597988,
|
|
"loss": 5.368,
|
|
"mean_token_accuracy": 0.17809147983789445,
|
|
"num_tokens": 38729517.0,
|
|
"step": 18655
|
|
},
|
|
{
|
|
"entropy": 5.673700904846191,
|
|
"epoch": 1.6926705370101596,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004715982780989981,
|
|
"loss": 5.4157,
|
|
"mean_token_accuracy": 0.17625726461410524,
|
|
"num_tokens": 38740878.0,
|
|
"step": 18660
|
|
},
|
|
{
|
|
"entropy": 5.610745239257812,
|
|
"epoch": 1.6931240928882438,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.00047158253987249487,
|
|
"loss": 5.3365,
|
|
"mean_token_accuracy": 0.1747508391737938,
|
|
"num_tokens": 38751291.0,
|
|
"step": 18665
|
|
},
|
|
{
|
|
"entropy": 5.567899417877197,
|
|
"epoch": 1.693577648766328,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00047156679758061465,
|
|
"loss": 5.3118,
|
|
"mean_token_accuracy": 0.17990041822195052,
|
|
"num_tokens": 38760940.0,
|
|
"step": 18670
|
|
},
|
|
{
|
|
"entropy": 5.661107301712036,
|
|
"epoch": 1.6940312046444121,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.00047155105122368297,
|
|
"loss": 5.3192,
|
|
"mean_token_accuracy": 0.17731436043977739,
|
|
"num_tokens": 38770240.0,
|
|
"step": 18675
|
|
},
|
|
{
|
|
"entropy": 5.57831597328186,
|
|
"epoch": 1.6944847605224964,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004715353008020255,
|
|
"loss": 5.3593,
|
|
"mean_token_accuracy": 0.1780167818069458,
|
|
"num_tokens": 38780452.0,
|
|
"step": 18680
|
|
},
|
|
{
|
|
"entropy": 5.689421796798706,
|
|
"epoch": 1.6949383164005805,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00047151954631596794,
|
|
"loss": 5.4268,
|
|
"mean_token_accuracy": 0.17343385368585587,
|
|
"num_tokens": 38790763.0,
|
|
"step": 18685
|
|
},
|
|
{
|
|
"entropy": 5.6311273097991945,
|
|
"epoch": 1.6953918722786647,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.00047150378776583603,
|
|
"loss": 5.3189,
|
|
"mean_token_accuracy": 0.18228260576725006,
|
|
"num_tokens": 38802164.0,
|
|
"step": 18690
|
|
},
|
|
{
|
|
"entropy": 5.630303239822387,
|
|
"epoch": 1.695845428156749,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004714880251519557,
|
|
"loss": 5.3613,
|
|
"mean_token_accuracy": 0.16691019833087922,
|
|
"num_tokens": 38812901.0,
|
|
"step": 18695
|
|
},
|
|
{
|
|
"entropy": 5.663488578796387,
|
|
"epoch": 1.6962989840348333,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.000471472258474653,
|
|
"loss": 5.3555,
|
|
"mean_token_accuracy": 0.17075988203287124,
|
|
"num_tokens": 38823305.0,
|
|
"step": 18700
|
|
},
|
|
{
|
|
"entropy": 5.656470775604248,
|
|
"epoch": 1.6967525399129173,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.00047145648773425384,
|
|
"loss": 5.3438,
|
|
"mean_token_accuracy": 0.1667855814099312,
|
|
"num_tokens": 38833602.0,
|
|
"step": 18705
|
|
},
|
|
{
|
|
"entropy": 5.633403491973877,
|
|
"epoch": 1.6972060957910013,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.00047144071293108456,
|
|
"loss": 5.4383,
|
|
"mean_token_accuracy": 0.17118894159793854,
|
|
"num_tokens": 38843950.0,
|
|
"step": 18710
|
|
},
|
|
{
|
|
"entropy": 5.608430290222168,
|
|
"epoch": 1.6976596516690856,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004714249340654712,
|
|
"loss": 5.3328,
|
|
"mean_token_accuracy": 0.17331786900758744,
|
|
"num_tokens": 38853753.0,
|
|
"step": 18715
|
|
},
|
|
{
|
|
"entropy": 5.578097248077393,
|
|
"epoch": 1.6981132075471699,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004714091511377402,
|
|
"loss": 5.2924,
|
|
"mean_token_accuracy": 0.17190752774477006,
|
|
"num_tokens": 38863394.0,
|
|
"step": 18720
|
|
},
|
|
{
|
|
"entropy": 5.624987602233887,
|
|
"epoch": 1.6985667634252541,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00047139336414821784,
|
|
"loss": 5.3632,
|
|
"mean_token_accuracy": 0.17347008734941483,
|
|
"num_tokens": 38872972.0,
|
|
"step": 18725
|
|
},
|
|
{
|
|
"entropy": 5.605926656723023,
|
|
"epoch": 1.6990203193033382,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00047137757309723073,
|
|
"loss": 5.3541,
|
|
"mean_token_accuracy": 0.18138625025749205,
|
|
"num_tokens": 38883251.0,
|
|
"step": 18730
|
|
},
|
|
{
|
|
"entropy": 5.550278759002685,
|
|
"epoch": 1.6994738751814222,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004713617779851053,
|
|
"loss": 5.3759,
|
|
"mean_token_accuracy": 0.1751328393816948,
|
|
"num_tokens": 38893274.0,
|
|
"step": 18735
|
|
},
|
|
{
|
|
"entropy": 5.6975658416748045,
|
|
"epoch": 1.6999274310595065,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004713459788121683,
|
|
"loss": 5.4718,
|
|
"mean_token_accuracy": 0.1692628264427185,
|
|
"num_tokens": 38903870.0,
|
|
"step": 18740
|
|
},
|
|
{
|
|
"entropy": 5.688255405426025,
|
|
"epoch": 1.7003809869375908,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004713301755787464,
|
|
"loss": 5.4237,
|
|
"mean_token_accuracy": 0.16898000091314316,
|
|
"num_tokens": 38914921.0,
|
|
"step": 18745
|
|
},
|
|
{
|
|
"entropy": 5.654485988616943,
|
|
"epoch": 1.700834542815675,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004713143682851665,
|
|
"loss": 5.367,
|
|
"mean_token_accuracy": 0.17632925659418106,
|
|
"num_tokens": 38924630.0,
|
|
"step": 18750
|
|
},
|
|
{
|
|
"entropy": 5.598672008514404,
|
|
"epoch": 1.701288098693759,
|
|
"grad_norm": 4.0,
|
|
"learning_rate": 0.0004712985569317553,
|
|
"loss": 5.3521,
|
|
"mean_token_accuracy": 0.1766107574105263,
|
|
"num_tokens": 38934926.0,
|
|
"step": 18755
|
|
},
|
|
{
|
|
"entropy": 5.709752702713013,
|
|
"epoch": 1.7017416545718431,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004712827415188401,
|
|
"loss": 5.4993,
|
|
"mean_token_accuracy": 0.16466707289218901,
|
|
"num_tokens": 38944513.0,
|
|
"step": 18760
|
|
},
|
|
{
|
|
"entropy": 5.643617916107178,
|
|
"epoch": 1.7021952104499274,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004712669220467476,
|
|
"loss": 5.3792,
|
|
"mean_token_accuracy": 0.1710243672132492,
|
|
"num_tokens": 38955918.0,
|
|
"step": 18765
|
|
},
|
|
{
|
|
"entropy": 5.643879413604736,
|
|
"epoch": 1.7026487663280117,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.00047125109851580533,
|
|
"loss": 5.3877,
|
|
"mean_token_accuracy": 0.17239867895841599,
|
|
"num_tokens": 38966221.0,
|
|
"step": 18770
|
|
},
|
|
{
|
|
"entropy": 5.612437772750854,
|
|
"epoch": 1.703102322206096,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00047123527092634025,
|
|
"loss": 5.3356,
|
|
"mean_token_accuracy": 0.17269362956285478,
|
|
"num_tokens": 38976463.0,
|
|
"step": 18775
|
|
},
|
|
{
|
|
"entropy": 5.567640256881714,
|
|
"epoch": 1.70355587808418,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004712194392786797,
|
|
"loss": 5.2591,
|
|
"mean_token_accuracy": 0.17480912506580354,
|
|
"num_tokens": 38986375.0,
|
|
"step": 18780
|
|
},
|
|
{
|
|
"entropy": 5.650631237030029,
|
|
"epoch": 1.704009433962264,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.00047120360357315127,
|
|
"loss": 5.4367,
|
|
"mean_token_accuracy": 0.16977938413619995,
|
|
"num_tokens": 38996116.0,
|
|
"step": 18785
|
|
},
|
|
{
|
|
"entropy": 5.611443662643433,
|
|
"epoch": 1.7044629898403483,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00047118776381008216,
|
|
"loss": 5.3536,
|
|
"mean_token_accuracy": 0.17452395409345628,
|
|
"num_tokens": 39005846.0,
|
|
"step": 18790
|
|
},
|
|
{
|
|
"entropy": 5.652708959579468,
|
|
"epoch": 1.7049165457184325,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.00047117191998980026,
|
|
"loss": 5.3863,
|
|
"mean_token_accuracy": 0.1693885251879692,
|
|
"num_tokens": 39016744.0,
|
|
"step": 18795
|
|
},
|
|
{
|
|
"entropy": 5.671818351745605,
|
|
"epoch": 1.7053701015965168,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.00047115607211263295,
|
|
"loss": 5.4283,
|
|
"mean_token_accuracy": 0.16544880121946334,
|
|
"num_tokens": 39026725.0,
|
|
"step": 18800
|
|
},
|
|
{
|
|
"entropy": 5.680934286117553,
|
|
"epoch": 1.7058236574746009,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.00047114022017890814,
|
|
"loss": 5.3949,
|
|
"mean_token_accuracy": 0.17234705686569213,
|
|
"num_tokens": 39036851.0,
|
|
"step": 18805
|
|
},
|
|
{
|
|
"entropy": 5.564892721176148,
|
|
"epoch": 1.706277213352685,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004711243641889536,
|
|
"loss": 5.3052,
|
|
"mean_token_accuracy": 0.17486591041088104,
|
|
"num_tokens": 39047179.0,
|
|
"step": 18810
|
|
},
|
|
{
|
|
"entropy": 5.574800062179565,
|
|
"epoch": 1.7067307692307692,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.00047110850414309714,
|
|
"loss": 5.2379,
|
|
"mean_token_accuracy": 0.1831071764230728,
|
|
"num_tokens": 39057758.0,
|
|
"step": 18815
|
|
},
|
|
{
|
|
"entropy": 5.60599718093872,
|
|
"epoch": 1.7071843251088534,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.00047109264004166696,
|
|
"loss": 5.443,
|
|
"mean_token_accuracy": 0.1696527674794197,
|
|
"num_tokens": 39068142.0,
|
|
"step": 18820
|
|
},
|
|
{
|
|
"entropy": 5.634007215499878,
|
|
"epoch": 1.7076378809869377,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004710767718849909,
|
|
"loss": 5.3268,
|
|
"mean_token_accuracy": 0.16925108730792998,
|
|
"num_tokens": 39078157.0,
|
|
"step": 18825
|
|
},
|
|
{
|
|
"entropy": 5.634946346282959,
|
|
"epoch": 1.7080914368650217,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004710608996733973,
|
|
"loss": 5.3766,
|
|
"mean_token_accuracy": 0.1783433213829994,
|
|
"num_tokens": 39089090.0,
|
|
"step": 18830
|
|
},
|
|
{
|
|
"entropy": 5.645534086227417,
|
|
"epoch": 1.708544992743106,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.00047104502340721433,
|
|
"loss": 5.4194,
|
|
"mean_token_accuracy": 0.1664641723036766,
|
|
"num_tokens": 39099079.0,
|
|
"step": 18835
|
|
},
|
|
{
|
|
"entropy": 5.624309015274048,
|
|
"epoch": 1.70899854862119,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.00047102914308677033,
|
|
"loss": 5.3688,
|
|
"mean_token_accuracy": 0.17123167663812638,
|
|
"num_tokens": 39109927.0,
|
|
"step": 18840
|
|
},
|
|
{
|
|
"entropy": 5.6402698993682865,
|
|
"epoch": 1.7094521044992743,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.00047101325871239363,
|
|
"loss": 5.3586,
|
|
"mean_token_accuracy": 0.17462224811315535,
|
|
"num_tokens": 39119806.0,
|
|
"step": 18845
|
|
},
|
|
{
|
|
"entropy": 5.714513492584229,
|
|
"epoch": 1.7099056603773586,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004709973702844128,
|
|
"loss": 5.4513,
|
|
"mean_token_accuracy": 0.17004262953996657,
|
|
"num_tokens": 39130147.0,
|
|
"step": 18850
|
|
},
|
|
{
|
|
"entropy": 5.562098693847656,
|
|
"epoch": 1.7103592162554426,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.00047098147780315645,
|
|
"loss": 5.2896,
|
|
"mean_token_accuracy": 0.18149088323116302,
|
|
"num_tokens": 39139937.0,
|
|
"step": 18855
|
|
},
|
|
{
|
|
"entropy": 5.631501817703247,
|
|
"epoch": 1.710812772133527,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004709655812689532,
|
|
"loss": 5.3903,
|
|
"mean_token_accuracy": 0.1710236430168152,
|
|
"num_tokens": 39149977.0,
|
|
"step": 18860
|
|
},
|
|
{
|
|
"entropy": 5.670045709609985,
|
|
"epoch": 1.711266328011611,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004709496806821318,
|
|
"loss": 5.3845,
|
|
"mean_token_accuracy": 0.17494307905435563,
|
|
"num_tokens": 39161076.0,
|
|
"step": 18865
|
|
},
|
|
{
|
|
"entropy": 5.691786003112793,
|
|
"epoch": 1.7117198838896952,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00047093377604302106,
|
|
"loss": 5.4275,
|
|
"mean_token_accuracy": 0.16837404519319535,
|
|
"num_tokens": 39170776.0,
|
|
"step": 18870
|
|
},
|
|
{
|
|
"entropy": 5.6190728664398195,
|
|
"epoch": 1.7121734397677795,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.0004709178673519499,
|
|
"loss": 5.3702,
|
|
"mean_token_accuracy": 0.17359258681535722,
|
|
"num_tokens": 39181134.0,
|
|
"step": 18875
|
|
},
|
|
{
|
|
"entropy": 5.670098400115966,
|
|
"epoch": 1.7126269956458637,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004709019546092473,
|
|
"loss": 5.5092,
|
|
"mean_token_accuracy": 0.1646428257226944,
|
|
"num_tokens": 39193331.0,
|
|
"step": 18880
|
|
},
|
|
{
|
|
"entropy": 5.7846921443939205,
|
|
"epoch": 1.7130805515239478,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.00047088603781524237,
|
|
"loss": 5.4635,
|
|
"mean_token_accuracy": 0.16676535308361054,
|
|
"num_tokens": 39204372.0,
|
|
"step": 18885
|
|
},
|
|
{
|
|
"entropy": 5.652272748947143,
|
|
"epoch": 1.7135341074020318,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004708701169702642,
|
|
"loss": 5.3756,
|
|
"mean_token_accuracy": 0.17675669342279435,
|
|
"num_tokens": 39214725.0,
|
|
"step": 18890
|
|
},
|
|
{
|
|
"entropy": 5.516621875762939,
|
|
"epoch": 1.713987663280116,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004708541920746422,
|
|
"loss": 5.3138,
|
|
"mean_token_accuracy": 0.17645542621612548,
|
|
"num_tokens": 39225119.0,
|
|
"step": 18895
|
|
},
|
|
{
|
|
"entropy": 5.605922269821167,
|
|
"epoch": 1.7144412191582004,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004708382631287055,
|
|
"loss": 5.328,
|
|
"mean_token_accuracy": 0.17461291402578355,
|
|
"num_tokens": 39235021.0,
|
|
"step": 18900
|
|
},
|
|
{
|
|
"entropy": 5.6856584548950195,
|
|
"epoch": 1.7148947750362846,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004708223301327837,
|
|
"loss": 5.4927,
|
|
"mean_token_accuracy": 0.16371752321720123,
|
|
"num_tokens": 39245830.0,
|
|
"step": 18905
|
|
},
|
|
{
|
|
"entropy": 5.717454051971435,
|
|
"epoch": 1.7153483309143687,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.00047080639308720617,
|
|
"loss": 5.4491,
|
|
"mean_token_accuracy": 0.17564899176359178,
|
|
"num_tokens": 39255264.0,
|
|
"step": 18910
|
|
},
|
|
{
|
|
"entropy": 5.644083404541016,
|
|
"epoch": 1.7158018867924527,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.00047079045199230254,
|
|
"loss": 5.3534,
|
|
"mean_token_accuracy": 0.17511814087629318,
|
|
"num_tokens": 39264966.0,
|
|
"step": 18915
|
|
},
|
|
{
|
|
"entropy": 5.649512147903442,
|
|
"epoch": 1.716255442670537,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00047077450684840247,
|
|
"loss": 5.4329,
|
|
"mean_token_accuracy": 0.17194833159446715,
|
|
"num_tokens": 39275082.0,
|
|
"step": 18920
|
|
},
|
|
{
|
|
"entropy": 5.704360675811768,
|
|
"epoch": 1.7167089985486212,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004707585576558357,
|
|
"loss": 5.5139,
|
|
"mean_token_accuracy": 0.1681419312953949,
|
|
"num_tokens": 39285426.0,
|
|
"step": 18925
|
|
},
|
|
{
|
|
"entropy": 5.762727546691894,
|
|
"epoch": 1.7171625544267055,
|
|
"grad_norm": 2.84375,
|
|
"learning_rate": 0.0004707426044149321,
|
|
"loss": 5.4686,
|
|
"mean_token_accuracy": 0.1703044593334198,
|
|
"num_tokens": 39296633.0,
|
|
"step": 18930
|
|
},
|
|
{
|
|
"entropy": 5.61013240814209,
|
|
"epoch": 1.7176161103047896,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00047072664712602153,
|
|
"loss": 5.2578,
|
|
"mean_token_accuracy": 0.18421832621097564,
|
|
"num_tokens": 39306775.0,
|
|
"step": 18935
|
|
},
|
|
{
|
|
"entropy": 5.6474159240722654,
|
|
"epoch": 1.7180696661828736,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.000470710685789434,
|
|
"loss": 5.4005,
|
|
"mean_token_accuracy": 0.1649927794933319,
|
|
"num_tokens": 39317917.0,
|
|
"step": 18940
|
|
},
|
|
{
|
|
"entropy": 5.642625713348389,
|
|
"epoch": 1.7185232220609579,
|
|
"grad_norm": 4.28125,
|
|
"learning_rate": 0.00047069472040549965,
|
|
"loss": 5.4002,
|
|
"mean_token_accuracy": 0.167388978600502,
|
|
"num_tokens": 39328387.0,
|
|
"step": 18945
|
|
},
|
|
{
|
|
"entropy": 5.5607682228088375,
|
|
"epoch": 1.7189767779390421,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004706787509745486,
|
|
"loss": 5.2561,
|
|
"mean_token_accuracy": 0.18363773077726364,
|
|
"num_tokens": 39337639.0,
|
|
"step": 18950
|
|
},
|
|
{
|
|
"entropy": 5.6095290184021,
|
|
"epoch": 1.7194303338171264,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.00047066277749691115,
|
|
"loss": 5.3854,
|
|
"mean_token_accuracy": 0.17599396109580995,
|
|
"num_tokens": 39347971.0,
|
|
"step": 18955
|
|
},
|
|
{
|
|
"entropy": 5.6669854640960695,
|
|
"epoch": 1.7198838896952104,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004706467999729175,
|
|
"loss": 5.385,
|
|
"mean_token_accuracy": 0.17056430727243424,
|
|
"num_tokens": 39358038.0,
|
|
"step": 18960
|
|
},
|
|
{
|
|
"entropy": 5.708543920516968,
|
|
"epoch": 1.7203374455732945,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004706308184028983,
|
|
"loss": 5.409,
|
|
"mean_token_accuracy": 0.17191378623247147,
|
|
"num_tokens": 39367834.0,
|
|
"step": 18965
|
|
},
|
|
{
|
|
"entropy": 5.686937856674194,
|
|
"epoch": 1.7207910014513788,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004706148327871839,
|
|
"loss": 5.4143,
|
|
"mean_token_accuracy": 0.17525920271873474,
|
|
"num_tokens": 39378924.0,
|
|
"step": 18970
|
|
},
|
|
{
|
|
"entropy": 5.740410470962525,
|
|
"epoch": 1.721244557329463,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00047059884312610487,
|
|
"loss": 5.5138,
|
|
"mean_token_accuracy": 0.16248524338006973,
|
|
"num_tokens": 39390082.0,
|
|
"step": 18975
|
|
},
|
|
{
|
|
"entropy": 5.648524475097656,
|
|
"epoch": 1.7216981132075473,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.00047058284941999185,
|
|
"loss": 5.4108,
|
|
"mean_token_accuracy": 0.17066845744848252,
|
|
"num_tokens": 39400485.0,
|
|
"step": 18980
|
|
},
|
|
{
|
|
"entropy": 5.67932014465332,
|
|
"epoch": 1.7221516690856313,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004705668516691758,
|
|
"loss": 5.422,
|
|
"mean_token_accuracy": 0.1767018511891365,
|
|
"num_tokens": 39411601.0,
|
|
"step": 18985
|
|
},
|
|
{
|
|
"entropy": 5.621626091003418,
|
|
"epoch": 1.7226052249637154,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00047055084987398735,
|
|
"loss": 5.3066,
|
|
"mean_token_accuracy": 0.18038994520902635,
|
|
"num_tokens": 39421625.0,
|
|
"step": 18990
|
|
},
|
|
{
|
|
"entropy": 5.599380922317505,
|
|
"epoch": 1.7230587808417996,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004705348440347575,
|
|
"loss": 5.3753,
|
|
"mean_token_accuracy": 0.17103705555200577,
|
|
"num_tokens": 39432033.0,
|
|
"step": 18995
|
|
},
|
|
{
|
|
"entropy": 5.598644828796386,
|
|
"epoch": 1.723512336719884,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.00047051883415181724,
|
|
"loss": 5.342,
|
|
"mean_token_accuracy": 0.17536700367927552,
|
|
"num_tokens": 39442514.0,
|
|
"step": 19000
|
|
},
|
|
{
|
|
"entropy": 5.620339107513428,
|
|
"epoch": 1.7239658925979682,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004705028202254977,
|
|
"loss": 5.2704,
|
|
"mean_token_accuracy": 0.18265477269887925,
|
|
"num_tokens": 39452497.0,
|
|
"step": 19005
|
|
},
|
|
{
|
|
"entropy": 5.572072982788086,
|
|
"epoch": 1.7244194484760522,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00047048680225612996,
|
|
"loss": 5.3765,
|
|
"mean_token_accuracy": 0.1753297284245491,
|
|
"num_tokens": 39462173.0,
|
|
"step": 19010
|
|
},
|
|
{
|
|
"entropy": 5.6737298488616945,
|
|
"epoch": 1.7248730043541363,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004704707802440454,
|
|
"loss": 5.4514,
|
|
"mean_token_accuracy": 0.17579246014356614,
|
|
"num_tokens": 39473123.0,
|
|
"step": 19015
|
|
},
|
|
{
|
|
"entropy": 5.658503866195678,
|
|
"epoch": 1.7253265602322205,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.00047045475418957524,
|
|
"loss": 5.4082,
|
|
"mean_token_accuracy": 0.16486870050430297,
|
|
"num_tokens": 39484142.0,
|
|
"step": 19020
|
|
},
|
|
{
|
|
"entropy": 5.643023586273193,
|
|
"epoch": 1.7257801161103048,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.0004704387240930509,
|
|
"loss": 5.3992,
|
|
"mean_token_accuracy": 0.16818183958530425,
|
|
"num_tokens": 39494926.0,
|
|
"step": 19025
|
|
},
|
|
{
|
|
"entropy": 5.647661924362183,
|
|
"epoch": 1.726233671988389,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004704226899548041,
|
|
"loss": 5.3703,
|
|
"mean_token_accuracy": 0.17307351231575013,
|
|
"num_tokens": 39505153.0,
|
|
"step": 19030
|
|
},
|
|
{
|
|
"entropy": 5.61102614402771,
|
|
"epoch": 1.726687227866473,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.00047040665177516616,
|
|
"loss": 5.3391,
|
|
"mean_token_accuracy": 0.1762945294380188,
|
|
"num_tokens": 39515905.0,
|
|
"step": 19035
|
|
},
|
|
{
|
|
"entropy": 5.594401550292969,
|
|
"epoch": 1.7271407837445574,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.00047039060955446886,
|
|
"loss": 5.3577,
|
|
"mean_token_accuracy": 0.17357611954212188,
|
|
"num_tokens": 39526762.0,
|
|
"step": 19040
|
|
},
|
|
{
|
|
"entropy": 5.607455110549926,
|
|
"epoch": 1.7275943396226414,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.000470374563293044,
|
|
"loss": 5.3455,
|
|
"mean_token_accuracy": 0.17173245251178743,
|
|
"num_tokens": 39537340.0,
|
|
"step": 19045
|
|
},
|
|
{
|
|
"entropy": 5.680099964141846,
|
|
"epoch": 1.7280478955007257,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004703585129912234,
|
|
"loss": 5.3544,
|
|
"mean_token_accuracy": 0.17708337008953096,
|
|
"num_tokens": 39547144.0,
|
|
"step": 19050
|
|
},
|
|
{
|
|
"entropy": 5.774206686019897,
|
|
"epoch": 1.72850145137881,
|
|
"grad_norm": 3.203125,
|
|
"learning_rate": 0.00047034245864933894,
|
|
"loss": 5.4922,
|
|
"mean_token_accuracy": 0.1648596003651619,
|
|
"num_tokens": 39557707.0,
|
|
"step": 19055
|
|
},
|
|
{
|
|
"entropy": 5.707273817062378,
|
|
"epoch": 1.728955007256894,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.00047032640026772274,
|
|
"loss": 5.4468,
|
|
"mean_token_accuracy": 0.17281936407089232,
|
|
"num_tokens": 39567629.0,
|
|
"step": 19060
|
|
},
|
|
{
|
|
"entropy": 5.656304931640625,
|
|
"epoch": 1.7294085631349783,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004703103378467067,
|
|
"loss": 5.3466,
|
|
"mean_token_accuracy": 0.17502628564834594,
|
|
"num_tokens": 39577918.0,
|
|
"step": 19065
|
|
},
|
|
{
|
|
"entropy": 5.630748176574707,
|
|
"epoch": 1.7298621190130623,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.00047029427138662314,
|
|
"loss": 5.4301,
|
|
"mean_token_accuracy": 0.17522955685853958,
|
|
"num_tokens": 39587838.0,
|
|
"step": 19070
|
|
},
|
|
{
|
|
"entropy": 5.610006952285767,
|
|
"epoch": 1.7303156748911466,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004702782008878042,
|
|
"loss": 5.2731,
|
|
"mean_token_accuracy": 0.18283845633268356,
|
|
"num_tokens": 39597353.0,
|
|
"step": 19075
|
|
},
|
|
{
|
|
"entropy": 5.616329526901245,
|
|
"epoch": 1.7307692307692308,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004702621263505824,
|
|
"loss": 5.3467,
|
|
"mean_token_accuracy": 0.1736709088087082,
|
|
"num_tokens": 39607349.0,
|
|
"step": 19080
|
|
},
|
|
{
|
|
"entropy": 5.667447710037232,
|
|
"epoch": 1.731222786647315,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004702460477752901,
|
|
"loss": 5.4043,
|
|
"mean_token_accuracy": 0.17067914456129074,
|
|
"num_tokens": 39617810.0,
|
|
"step": 19085
|
|
},
|
|
{
|
|
"entropy": 5.603252315521241,
|
|
"epoch": 1.7316763425253991,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004702299651622597,
|
|
"loss": 5.2845,
|
|
"mean_token_accuracy": 0.18291763216257095,
|
|
"num_tokens": 39626805.0,
|
|
"step": 19090
|
|
},
|
|
{
|
|
"entropy": 5.558157253265381,
|
|
"epoch": 1.7321298984034832,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004702138785118239,
|
|
"loss": 5.3374,
|
|
"mean_token_accuracy": 0.1751893311738968,
|
|
"num_tokens": 39637839.0,
|
|
"step": 19095
|
|
},
|
|
{
|
|
"entropy": 5.601668834686279,
|
|
"epoch": 1.7325834542815675,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004701977878243153,
|
|
"loss": 5.3227,
|
|
"mean_token_accuracy": 0.1742377147078514,
|
|
"num_tokens": 39648697.0,
|
|
"step": 19100
|
|
},
|
|
{
|
|
"entropy": 5.576577806472779,
|
|
"epoch": 1.7330370101596517,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004701816931000668,
|
|
"loss": 5.3231,
|
|
"mean_token_accuracy": 0.17688826322555543,
|
|
"num_tokens": 39658154.0,
|
|
"step": 19105
|
|
},
|
|
{
|
|
"entropy": 5.614622640609741,
|
|
"epoch": 1.733490566037736,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00047016559433941106,
|
|
"loss": 5.3815,
|
|
"mean_token_accuracy": 0.17345051765441893,
|
|
"num_tokens": 39667939.0,
|
|
"step": 19110
|
|
},
|
|
{
|
|
"entropy": 5.58646297454834,
|
|
"epoch": 1.73394412191582,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004701494915426812,
|
|
"loss": 5.288,
|
|
"mean_token_accuracy": 0.17590879499912263,
|
|
"num_tokens": 39678289.0,
|
|
"step": 19115
|
|
},
|
|
{
|
|
"entropy": 5.6326367378234865,
|
|
"epoch": 1.734397677793904,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.00047013338471021,
|
|
"loss": 5.3612,
|
|
"mean_token_accuracy": 0.17490290254354476,
|
|
"num_tokens": 39689901.0,
|
|
"step": 19120
|
|
},
|
|
{
|
|
"entropy": 5.66708402633667,
|
|
"epoch": 1.7348512336719883,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.00047011727384233074,
|
|
"loss": 5.3793,
|
|
"mean_token_accuracy": 0.1740761712193489,
|
|
"num_tokens": 39700831.0,
|
|
"step": 19125
|
|
},
|
|
{
|
|
"entropy": 5.668937492370605,
|
|
"epoch": 1.7353047895500726,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004701011589393765,
|
|
"loss": 5.4118,
|
|
"mean_token_accuracy": 0.1687848076224327,
|
|
"num_tokens": 39711794.0,
|
|
"step": 19130
|
|
},
|
|
{
|
|
"entropy": 5.571121788024902,
|
|
"epoch": 1.7357583454281569,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.00047008504000168054,
|
|
"loss": 5.3463,
|
|
"mean_token_accuracy": 0.17577434927225113,
|
|
"num_tokens": 39721889.0,
|
|
"step": 19135
|
|
},
|
|
{
|
|
"entropy": 5.551446485519409,
|
|
"epoch": 1.736211901306241,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004700689170295763,
|
|
"loss": 5.4249,
|
|
"mean_token_accuracy": 0.1743490919470787,
|
|
"num_tokens": 39732562.0,
|
|
"step": 19140
|
|
},
|
|
{
|
|
"entropy": 5.744309568405152,
|
|
"epoch": 1.736665457184325,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.00047005279002339717,
|
|
"loss": 5.3755,
|
|
"mean_token_accuracy": 0.1711914986371994,
|
|
"num_tokens": 39742286.0,
|
|
"step": 19145
|
|
},
|
|
{
|
|
"entropy": 5.675173950195313,
|
|
"epoch": 1.7371190130624092,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.00047003665898347663,
|
|
"loss": 5.4018,
|
|
"mean_token_accuracy": 0.1711731344461441,
|
|
"num_tokens": 39754336.0,
|
|
"step": 19150
|
|
},
|
|
{
|
|
"entropy": 5.575232219696045,
|
|
"epoch": 1.7375725689404935,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004700205239101483,
|
|
"loss": 5.2903,
|
|
"mean_token_accuracy": 0.18277034163475037,
|
|
"num_tokens": 39763545.0,
|
|
"step": 19155
|
|
},
|
|
{
|
|
"entropy": 5.636547422409057,
|
|
"epoch": 1.7380261248185778,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004700043848037458,
|
|
"loss": 5.4439,
|
|
"mean_token_accuracy": 0.16540831178426743,
|
|
"num_tokens": 39774536.0,
|
|
"step": 19160
|
|
},
|
|
{
|
|
"entropy": 5.6986030578613285,
|
|
"epoch": 1.7384796806966618,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004699882416646029,
|
|
"loss": 5.3657,
|
|
"mean_token_accuracy": 0.17401862144470215,
|
|
"num_tokens": 39785377.0,
|
|
"step": 19165
|
|
},
|
|
{
|
|
"entropy": 5.682500410079956,
|
|
"epoch": 1.7389332365747459,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004699720944930535,
|
|
"loss": 5.4577,
|
|
"mean_token_accuracy": 0.1599442854523659,
|
|
"num_tokens": 39796692.0,
|
|
"step": 19170
|
|
},
|
|
{
|
|
"entropy": 5.577452087402344,
|
|
"epoch": 1.7393867924528301,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.00046995594328943147,
|
|
"loss": 5.3613,
|
|
"mean_token_accuracy": 0.17553267925977706,
|
|
"num_tokens": 39807927.0,
|
|
"step": 19175
|
|
},
|
|
{
|
|
"entropy": 5.7666534900665285,
|
|
"epoch": 1.7398403483309144,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004699397880540709,
|
|
"loss": 5.558,
|
|
"mean_token_accuracy": 0.16735330000519752,
|
|
"num_tokens": 39817617.0,
|
|
"step": 19180
|
|
},
|
|
{
|
|
"entropy": 5.669684171676636,
|
|
"epoch": 1.7402939042089987,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004699236287873058,
|
|
"loss": 5.2479,
|
|
"mean_token_accuracy": 0.18251994103193284,
|
|
"num_tokens": 39827092.0,
|
|
"step": 19185
|
|
},
|
|
{
|
|
"entropy": 5.587097883224487,
|
|
"epoch": 1.7407474600870827,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004699074654894705,
|
|
"loss": 5.3282,
|
|
"mean_token_accuracy": 0.17538771033287048,
|
|
"num_tokens": 39837378.0,
|
|
"step": 19190
|
|
},
|
|
{
|
|
"entropy": 5.61565055847168,
|
|
"epoch": 1.7412010159651667,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.000469891298160899,
|
|
"loss": 5.3373,
|
|
"mean_token_accuracy": 0.16629883050918579,
|
|
"num_tokens": 39848191.0,
|
|
"step": 19195
|
|
},
|
|
{
|
|
"entropy": 5.614153814315796,
|
|
"epoch": 1.741654571843251,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.00046987512680192586,
|
|
"loss": 5.3346,
|
|
"mean_token_accuracy": 0.17837357819080352,
|
|
"num_tokens": 39857886.0,
|
|
"step": 19200
|
|
},
|
|
{
|
|
"entropy": 5.709580564498902,
|
|
"epoch": 1.7421081277213353,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00046985895141288546,
|
|
"loss": 5.4267,
|
|
"mean_token_accuracy": 0.1687893360853195,
|
|
"num_tokens": 39868348.0,
|
|
"step": 19205
|
|
},
|
|
{
|
|
"entropy": 5.663555860519409,
|
|
"epoch": 1.7425616835994195,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00046984277199411224,
|
|
"loss": 5.432,
|
|
"mean_token_accuracy": 0.17092141062021254,
|
|
"num_tokens": 39879129.0,
|
|
"step": 19210
|
|
},
|
|
{
|
|
"entropy": 5.59379472732544,
|
|
"epoch": 1.7430152394775036,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.00046982658854594083,
|
|
"loss": 5.3295,
|
|
"mean_token_accuracy": 0.17386892884969712,
|
|
"num_tokens": 39890239.0,
|
|
"step": 19215
|
|
},
|
|
{
|
|
"entropy": 5.596347665786743,
|
|
"epoch": 1.7434687953555879,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00046981040106870595,
|
|
"loss": 5.2306,
|
|
"mean_token_accuracy": 0.1791740834712982,
|
|
"num_tokens": 39900907.0,
|
|
"step": 19220
|
|
},
|
|
{
|
|
"entropy": 5.645833158493042,
|
|
"epoch": 1.743922351233672,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004697942095627423,
|
|
"loss": 5.3747,
|
|
"mean_token_accuracy": 0.17560596019029617,
|
|
"num_tokens": 39911564.0,
|
|
"step": 19225
|
|
},
|
|
{
|
|
"entropy": 5.600389766693115,
|
|
"epoch": 1.7443759071117562,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004697780140283848,
|
|
"loss": 5.3012,
|
|
"mean_token_accuracy": 0.17497724592685698,
|
|
"num_tokens": 39922168.0,
|
|
"step": 19230
|
|
},
|
|
{
|
|
"entropy": 5.617383575439453,
|
|
"epoch": 1.7448294629898404,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004697618144659683,
|
|
"loss": 5.3471,
|
|
"mean_token_accuracy": 0.1770832806825638,
|
|
"num_tokens": 39932690.0,
|
|
"step": 19235
|
|
},
|
|
{
|
|
"entropy": 5.746314954757691,
|
|
"epoch": 1.7452830188679245,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004697456108758278,
|
|
"loss": 5.5145,
|
|
"mean_token_accuracy": 0.16842736452817916,
|
|
"num_tokens": 39942970.0,
|
|
"step": 19240
|
|
},
|
|
{
|
|
"entropy": 5.618770694732666,
|
|
"epoch": 1.7457365747460087,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004697294032582986,
|
|
"loss": 5.3476,
|
|
"mean_token_accuracy": 0.17076418399810792,
|
|
"num_tokens": 39953255.0,
|
|
"step": 19245
|
|
},
|
|
{
|
|
"entropy": 5.57149829864502,
|
|
"epoch": 1.7461901306240928,
|
|
"grad_norm": 3.453125,
|
|
"learning_rate": 0.00046971319161371564,
|
|
"loss": 5.2713,
|
|
"mean_token_accuracy": 0.1803775131702423,
|
|
"num_tokens": 39963521.0,
|
|
"step": 19250
|
|
},
|
|
{
|
|
"entropy": 5.65076699256897,
|
|
"epoch": 1.746643686502177,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.00046969697594241426,
|
|
"loss": 5.3594,
|
|
"mean_token_accuracy": 0.17208747267723085,
|
|
"num_tokens": 39973494.0,
|
|
"step": 19255
|
|
},
|
|
{
|
|
"entropy": 5.64431324005127,
|
|
"epoch": 1.7470972423802613,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004696807562447298,
|
|
"loss": 5.4873,
|
|
"mean_token_accuracy": 0.163669390976429,
|
|
"num_tokens": 39984652.0,
|
|
"step": 19260
|
|
},
|
|
{
|
|
"entropy": 5.685377597808838,
|
|
"epoch": 1.7475507982583456,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00046966453252099763,
|
|
"loss": 5.4315,
|
|
"mean_token_accuracy": 0.17161906212568284,
|
|
"num_tokens": 39995490.0,
|
|
"step": 19265
|
|
},
|
|
{
|
|
"entropy": 5.61215443611145,
|
|
"epoch": 1.7480043541364296,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.00046964830477155335,
|
|
"loss": 5.2288,
|
|
"mean_token_accuracy": 0.18911190778017045,
|
|
"num_tokens": 40006447.0,
|
|
"step": 19270
|
|
},
|
|
{
|
|
"entropy": 5.723793983459473,
|
|
"epoch": 1.7484579100145137,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.00046963207299673257,
|
|
"loss": 5.442,
|
|
"mean_token_accuracy": 0.17048927992582322,
|
|
"num_tokens": 40015733.0,
|
|
"step": 19275
|
|
},
|
|
{
|
|
"entropy": 5.69354658126831,
|
|
"epoch": 1.748911465892598,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.00046961583719687085,
|
|
"loss": 5.3136,
|
|
"mean_token_accuracy": 0.1748669847846031,
|
|
"num_tokens": 40025844.0,
|
|
"step": 19280
|
|
},
|
|
{
|
|
"entropy": 5.629614782333374,
|
|
"epoch": 1.7493650217706822,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.00046959959737230414,
|
|
"loss": 5.3617,
|
|
"mean_token_accuracy": 0.18143562078475953,
|
|
"num_tokens": 40035942.0,
|
|
"step": 19285
|
|
},
|
|
{
|
|
"entropy": 5.583377122879028,
|
|
"epoch": 1.7498185776487665,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00046958335352336806,
|
|
"loss": 5.2476,
|
|
"mean_token_accuracy": 0.1826334834098816,
|
|
"num_tokens": 40045551.0,
|
|
"step": 19290
|
|
},
|
|
{
|
|
"entropy": 5.6562048435211185,
|
|
"epoch": 1.7502721335268505,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004695671056503987,
|
|
"loss": 5.3584,
|
|
"mean_token_accuracy": 0.18128399699926376,
|
|
"num_tokens": 40055803.0,
|
|
"step": 19295
|
|
},
|
|
{
|
|
"entropy": 5.574113893508911,
|
|
"epoch": 1.7507256894049346,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.000469550853753732,
|
|
"loss": 5.3709,
|
|
"mean_token_accuracy": 0.17281553596258165,
|
|
"num_tokens": 40066004.0,
|
|
"step": 19300
|
|
},
|
|
{
|
|
"entropy": 5.646218347549438,
|
|
"epoch": 1.7511792452830188,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.000469534597833704,
|
|
"loss": 5.3669,
|
|
"mean_token_accuracy": 0.17948138117790222,
|
|
"num_tokens": 40075522.0,
|
|
"step": 19305
|
|
},
|
|
{
|
|
"entropy": 5.689025020599365,
|
|
"epoch": 1.751632801161103,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.000469518337890651,
|
|
"loss": 5.3552,
|
|
"mean_token_accuracy": 0.18483193963766098,
|
|
"num_tokens": 40084839.0,
|
|
"step": 19310
|
|
},
|
|
{
|
|
"entropy": 5.654287433624267,
|
|
"epoch": 1.7520863570391874,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.00046950207392490917,
|
|
"loss": 5.376,
|
|
"mean_token_accuracy": 0.17209792286157607,
|
|
"num_tokens": 40094392.0,
|
|
"step": 19315
|
|
},
|
|
{
|
|
"entropy": 5.5473888397216795,
|
|
"epoch": 1.7525399129172714,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.00046948580593681496,
|
|
"loss": 5.3241,
|
|
"mean_token_accuracy": 0.17652449756860733,
|
|
"num_tokens": 40105990.0,
|
|
"step": 19320
|
|
},
|
|
{
|
|
"entropy": 5.5448164463043215,
|
|
"epoch": 1.7529934687953554,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004694695339267047,
|
|
"loss": 5.2652,
|
|
"mean_token_accuracy": 0.18078768849372864,
|
|
"num_tokens": 40116143.0,
|
|
"step": 19325
|
|
},
|
|
{
|
|
"entropy": 5.760106325149536,
|
|
"epoch": 1.7534470246734397,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00046945325789491483,
|
|
"loss": 5.4348,
|
|
"mean_token_accuracy": 0.1718847393989563,
|
|
"num_tokens": 40126849.0,
|
|
"step": 19330
|
|
},
|
|
{
|
|
"entropy": 5.662941741943359,
|
|
"epoch": 1.753900580551524,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004694369778417822,
|
|
"loss": 5.4041,
|
|
"mean_token_accuracy": 0.17341629713773726,
|
|
"num_tokens": 40137259.0,
|
|
"step": 19335
|
|
},
|
|
{
|
|
"entropy": 5.5429158210754395,
|
|
"epoch": 1.7543541364296082,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004694206937676431,
|
|
"loss": 5.2647,
|
|
"mean_token_accuracy": 0.1789962261915207,
|
|
"num_tokens": 40148578.0,
|
|
"step": 19340
|
|
},
|
|
{
|
|
"entropy": 5.653353357315064,
|
|
"epoch": 1.7548076923076923,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004694044056728347,
|
|
"loss": 5.4069,
|
|
"mean_token_accuracy": 0.1690630331635475,
|
|
"num_tokens": 40159754.0,
|
|
"step": 19345
|
|
},
|
|
{
|
|
"entropy": 5.659046792984009,
|
|
"epoch": 1.7552612481857763,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00046938811355769363,
|
|
"loss": 5.3806,
|
|
"mean_token_accuracy": 0.17346472591161727,
|
|
"num_tokens": 40169388.0,
|
|
"step": 19350
|
|
},
|
|
{
|
|
"entropy": 5.589139556884765,
|
|
"epoch": 1.7557148040638606,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.00046937181742255673,
|
|
"loss": 5.3581,
|
|
"mean_token_accuracy": 0.17579484283924102,
|
|
"num_tokens": 40179271.0,
|
|
"step": 19355
|
|
},
|
|
{
|
|
"entropy": 5.582015323638916,
|
|
"epoch": 1.7561683599419449,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004693555172677612,
|
|
"loss": 5.4004,
|
|
"mean_token_accuracy": 0.17221444994211196,
|
|
"num_tokens": 40189292.0,
|
|
"step": 19360
|
|
},
|
|
{
|
|
"entropy": 5.6200989246368405,
|
|
"epoch": 1.7566219158200291,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.000469339213093644,
|
|
"loss": 5.3596,
|
|
"mean_token_accuracy": 0.17219399958848952,
|
|
"num_tokens": 40199271.0,
|
|
"step": 19365
|
|
},
|
|
{
|
|
"entropy": 5.594471120834351,
|
|
"epoch": 1.7570754716981132,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00046932290490054235,
|
|
"loss": 5.3852,
|
|
"mean_token_accuracy": 0.1731199324131012,
|
|
"num_tokens": 40210386.0,
|
|
"step": 19370
|
|
},
|
|
{
|
|
"entropy": 5.650211906433105,
|
|
"epoch": 1.7575290275761972,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004693065926887936,
|
|
"loss": 5.3514,
|
|
"mean_token_accuracy": 0.1746983453631401,
|
|
"num_tokens": 40220892.0,
|
|
"step": 19375
|
|
},
|
|
{
|
|
"entropy": 5.681675243377685,
|
|
"epoch": 1.7579825834542815,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.00046929027645873484,
|
|
"loss": 5.3615,
|
|
"mean_token_accuracy": 0.17474503070116043,
|
|
"num_tokens": 40231737.0,
|
|
"step": 19380
|
|
},
|
|
{
|
|
"entropy": 5.621780300140381,
|
|
"epoch": 1.7584361393323658,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004692739562107038,
|
|
"loss": 5.4015,
|
|
"mean_token_accuracy": 0.17259714752435684,
|
|
"num_tokens": 40242218.0,
|
|
"step": 19385
|
|
},
|
|
{
|
|
"entropy": 5.626964426040649,
|
|
"epoch": 1.75888969521045,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.00046925763194503775,
|
|
"loss": 5.3672,
|
|
"mean_token_accuracy": 0.17726352959871292,
|
|
"num_tokens": 40253659.0,
|
|
"step": 19390
|
|
},
|
|
{
|
|
"entropy": 5.587478160858154,
|
|
"epoch": 1.759343251088534,
|
|
"grad_norm": 3.40625,
|
|
"learning_rate": 0.0004692413036620744,
|
|
"loss": 5.2376,
|
|
"mean_token_accuracy": 0.1812431901693344,
|
|
"num_tokens": 40264328.0,
|
|
"step": 19395
|
|
},
|
|
{
|
|
"entropy": 5.61889238357544,
|
|
"epoch": 1.7597968069666183,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004692249713621514,
|
|
"loss": 5.3196,
|
|
"mean_token_accuracy": 0.1762406811118126,
|
|
"num_tokens": 40275188.0,
|
|
"step": 19400
|
|
},
|
|
{
|
|
"entropy": 5.633780241012573,
|
|
"epoch": 1.7602503628447024,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.00046920863504560647,
|
|
"loss": 5.4896,
|
|
"mean_token_accuracy": 0.16785765141248704,
|
|
"num_tokens": 40287094.0,
|
|
"step": 19405
|
|
},
|
|
{
|
|
"entropy": 5.624924850463867,
|
|
"epoch": 1.7607039187227866,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004691922947127775,
|
|
"loss": 5.3196,
|
|
"mean_token_accuracy": 0.17450563311576844,
|
|
"num_tokens": 40296551.0,
|
|
"step": 19410
|
|
},
|
|
{
|
|
"entropy": 5.585101556777954,
|
|
"epoch": 1.761157474600871,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004691759503640024,
|
|
"loss": 5.3335,
|
|
"mean_token_accuracy": 0.16877332627773284,
|
|
"num_tokens": 40306920.0,
|
|
"step": 19415
|
|
},
|
|
{
|
|
"entropy": 5.563895416259766,
|
|
"epoch": 1.761611030478955,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004691596019996191,
|
|
"loss": 5.2453,
|
|
"mean_token_accuracy": 0.18344950824975967,
|
|
"num_tokens": 40316797.0,
|
|
"step": 19420
|
|
},
|
|
{
|
|
"entropy": 5.532508754730225,
|
|
"epoch": 1.7620645863570392,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004691432496199658,
|
|
"loss": 5.289,
|
|
"mean_token_accuracy": 0.17305812686681749,
|
|
"num_tokens": 40327002.0,
|
|
"step": 19425
|
|
},
|
|
{
|
|
"entropy": 5.716414213180542,
|
|
"epoch": 1.7625181422351233,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.00046912689322538064,
|
|
"loss": 5.4687,
|
|
"mean_token_accuracy": 0.17434363216161727,
|
|
"num_tokens": 40337247.0,
|
|
"step": 19430
|
|
},
|
|
{
|
|
"entropy": 5.690283918380738,
|
|
"epoch": 1.7629716981132075,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.00046911053281620187,
|
|
"loss": 5.4004,
|
|
"mean_token_accuracy": 0.1752691760659218,
|
|
"num_tokens": 40346960.0,
|
|
"step": 19435
|
|
},
|
|
{
|
|
"entropy": 5.6690993309021,
|
|
"epoch": 1.7634252539912918,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.00046909416839276775,
|
|
"loss": 5.4145,
|
|
"mean_token_accuracy": 0.1694744884967804,
|
|
"num_tokens": 40357169.0,
|
|
"step": 19440
|
|
},
|
|
{
|
|
"entropy": 5.554582977294922,
|
|
"epoch": 1.763878809869376,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004690777999554168,
|
|
"loss": 5.2588,
|
|
"mean_token_accuracy": 0.18240912556648253,
|
|
"num_tokens": 40367660.0,
|
|
"step": 19445
|
|
},
|
|
{
|
|
"entropy": 5.619625902175903,
|
|
"epoch": 1.76433236574746,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004690614275044875,
|
|
"loss": 5.2599,
|
|
"mean_token_accuracy": 0.17677654922008515,
|
|
"num_tokens": 40378217.0,
|
|
"step": 19450
|
|
},
|
|
{
|
|
"entropy": 5.59921669960022,
|
|
"epoch": 1.7647859216255442,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004690450510403184,
|
|
"loss": 5.3561,
|
|
"mean_token_accuracy": 0.17798468321561814,
|
|
"num_tokens": 40388249.0,
|
|
"step": 19455
|
|
},
|
|
{
|
|
"entropy": 5.671416902542115,
|
|
"epoch": 1.7652394775036284,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004690286705632483,
|
|
"loss": 5.4486,
|
|
"mean_token_accuracy": 0.1709713876247406,
|
|
"num_tokens": 40398239.0,
|
|
"step": 19460
|
|
},
|
|
{
|
|
"entropy": 5.638196659088135,
|
|
"epoch": 1.7656930333817127,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004690122860736157,
|
|
"loss": 5.4026,
|
|
"mean_token_accuracy": 0.1683029130101204,
|
|
"num_tokens": 40408473.0,
|
|
"step": 19465
|
|
},
|
|
{
|
|
"entropy": 5.724247884750366,
|
|
"epoch": 1.766146589259797,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.00046899589757175964,
|
|
"loss": 5.4726,
|
|
"mean_token_accuracy": 0.17186292111873627,
|
|
"num_tokens": 40418674.0,
|
|
"step": 19470
|
|
},
|
|
{
|
|
"entropy": 5.576864528656006,
|
|
"epoch": 1.766600145137881,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.000468979505058019,
|
|
"loss": 5.3175,
|
|
"mean_token_accuracy": 0.17606194466352462,
|
|
"num_tokens": 40429815.0,
|
|
"step": 19475
|
|
},
|
|
{
|
|
"entropy": 5.699040651321411,
|
|
"epoch": 1.767053701015965,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00046896310853273274,
|
|
"loss": 5.4485,
|
|
"mean_token_accuracy": 0.17742576748132705,
|
|
"num_tokens": 40439809.0,
|
|
"step": 19480
|
|
},
|
|
{
|
|
"entropy": 5.736165761947632,
|
|
"epoch": 1.7675072568940493,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00046894670799624,
|
|
"loss": 5.426,
|
|
"mean_token_accuracy": 0.1707823842763901,
|
|
"num_tokens": 40449503.0,
|
|
"step": 19485
|
|
},
|
|
{
|
|
"entropy": 5.565196704864502,
|
|
"epoch": 1.7679608127721336,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00046893030344887995,
|
|
"loss": 5.4309,
|
|
"mean_token_accuracy": 0.1625237300992012,
|
|
"num_tokens": 40459794.0,
|
|
"step": 19490
|
|
},
|
|
{
|
|
"entropy": 5.601535654067993,
|
|
"epoch": 1.7684143686502178,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00046891389489099166,
|
|
"loss": 5.3204,
|
|
"mean_token_accuracy": 0.18280165046453475,
|
|
"num_tokens": 40470044.0,
|
|
"step": 19495
|
|
},
|
|
{
|
|
"entropy": 5.654168224334716,
|
|
"epoch": 1.7688679245283019,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.00046889748232291476,
|
|
"loss": 5.353,
|
|
"mean_token_accuracy": 0.17374522238969803,
|
|
"num_tokens": 40480709.0,
|
|
"step": 19500
|
|
},
|
|
{
|
|
"entropy": 5.563494539260864,
|
|
"epoch": 1.769321480406386,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.00046888106574498843,
|
|
"loss": 5.1822,
|
|
"mean_token_accuracy": 0.18480696231126786,
|
|
"num_tokens": 40490906.0,
|
|
"step": 19505
|
|
},
|
|
{
|
|
"entropy": 5.532447576522827,
|
|
"epoch": 1.7697750362844702,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004688646451575522,
|
|
"loss": 5.3008,
|
|
"mean_token_accuracy": 0.18016231209039688,
|
|
"num_tokens": 40501971.0,
|
|
"step": 19510
|
|
},
|
|
{
|
|
"entropy": 5.586827945709229,
|
|
"epoch": 1.7702285921625545,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.00046884822056094587,
|
|
"loss": 5.4055,
|
|
"mean_token_accuracy": 0.17003688365221023,
|
|
"num_tokens": 40512685.0,
|
|
"step": 19515
|
|
},
|
|
{
|
|
"entropy": 5.59279499053955,
|
|
"epoch": 1.7706821480406387,
|
|
"grad_norm": 4.125,
|
|
"learning_rate": 0.00046883179195550883,
|
|
"loss": 5.3294,
|
|
"mean_token_accuracy": 0.17971712797880174,
|
|
"num_tokens": 40523460.0,
|
|
"step": 19520
|
|
},
|
|
{
|
|
"entropy": 5.604184293746949,
|
|
"epoch": 1.7711357039187228,
|
|
"grad_norm": 5.71875,
|
|
"learning_rate": 0.00046881535934158094,
|
|
"loss": 5.3299,
|
|
"mean_token_accuracy": 0.1768566519021988,
|
|
"num_tokens": 40533594.0,
|
|
"step": 19525
|
|
},
|
|
{
|
|
"entropy": 5.611560344696045,
|
|
"epoch": 1.7715892597968068,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004687989227195021,
|
|
"loss": 5.3659,
|
|
"mean_token_accuracy": 0.17740196287631987,
|
|
"num_tokens": 40543504.0,
|
|
"step": 19530
|
|
},
|
|
{
|
|
"entropy": 5.665998697280884,
|
|
"epoch": 1.772042815674891,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00046878248208961204,
|
|
"loss": 5.3014,
|
|
"mean_token_accuracy": 0.17771965265274048,
|
|
"num_tokens": 40553711.0,
|
|
"step": 19535
|
|
},
|
|
{
|
|
"entropy": 5.566425037384033,
|
|
"epoch": 1.7724963715529753,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.000468766037452251,
|
|
"loss": 5.3633,
|
|
"mean_token_accuracy": 0.17329737693071365,
|
|
"num_tokens": 40563731.0,
|
|
"step": 19540
|
|
},
|
|
{
|
|
"entropy": 5.603219366073608,
|
|
"epoch": 1.7729499274310596,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00046874958880775886,
|
|
"loss": 5.395,
|
|
"mean_token_accuracy": 0.1741158291697502,
|
|
"num_tokens": 40574235.0,
|
|
"step": 19545
|
|
},
|
|
{
|
|
"entropy": 5.659231328964234,
|
|
"epoch": 1.7734034833091437,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004687331361564758,
|
|
"loss": 5.3071,
|
|
"mean_token_accuracy": 0.17857076674699784,
|
|
"num_tokens": 40584459.0,
|
|
"step": 19550
|
|
},
|
|
{
|
|
"entropy": 5.603427314758301,
|
|
"epoch": 1.7738570391872277,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004687166794987422,
|
|
"loss": 5.3171,
|
|
"mean_token_accuracy": 0.17530257850885392,
|
|
"num_tokens": 40594268.0,
|
|
"step": 19555
|
|
},
|
|
{
|
|
"entropy": 5.586503314971924,
|
|
"epoch": 1.774310595065312,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004687002188348983,
|
|
"loss": 5.3215,
|
|
"mean_token_accuracy": 0.1814294531941414,
|
|
"num_tokens": 40604673.0,
|
|
"step": 19560
|
|
},
|
|
{
|
|
"entropy": 5.543392705917358,
|
|
"epoch": 1.7747641509433962,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00046868375416528443,
|
|
"loss": 5.2889,
|
|
"mean_token_accuracy": 0.17835271805524827,
|
|
"num_tokens": 40614998.0,
|
|
"step": 19565
|
|
},
|
|
{
|
|
"entropy": 5.600796127319336,
|
|
"epoch": 1.7752177068214805,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.00046866728549024123,
|
|
"loss": 5.3717,
|
|
"mean_token_accuracy": 0.1752070292830467,
|
|
"num_tokens": 40624729.0,
|
|
"step": 19570
|
|
},
|
|
{
|
|
"entropy": 5.627136278152466,
|
|
"epoch": 1.7756712626995645,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004686508128101092,
|
|
"loss": 5.4458,
|
|
"mean_token_accuracy": 0.1720251366496086,
|
|
"num_tokens": 40635673.0,
|
|
"step": 19575
|
|
},
|
|
{
|
|
"entropy": 5.672923469543457,
|
|
"epoch": 1.7761248185776488,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.000468634336125229,
|
|
"loss": 5.4009,
|
|
"mean_token_accuracy": 0.16949871182441711,
|
|
"num_tokens": 40645990.0,
|
|
"step": 19580
|
|
},
|
|
{
|
|
"entropy": 5.668621253967285,
|
|
"epoch": 1.7765783744557329,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.00046861785543594143,
|
|
"loss": 5.3777,
|
|
"mean_token_accuracy": 0.17749251276254654,
|
|
"num_tokens": 40656339.0,
|
|
"step": 19585
|
|
},
|
|
{
|
|
"entropy": 5.630721759796143,
|
|
"epoch": 1.7770319303338171,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.0004686013707425873,
|
|
"loss": 5.2606,
|
|
"mean_token_accuracy": 0.18306045830249787,
|
|
"num_tokens": 40666371.0,
|
|
"step": 19590
|
|
},
|
|
{
|
|
"entropy": 5.607341766357422,
|
|
"epoch": 1.7774854862119014,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.00046858488204550735,
|
|
"loss": 5.3164,
|
|
"mean_token_accuracy": 0.1738098680973053,
|
|
"num_tokens": 40676423.0,
|
|
"step": 19595
|
|
},
|
|
{
|
|
"entropy": 5.570472717285156,
|
|
"epoch": 1.7779390420899854,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004685683893450428,
|
|
"loss": 5.2855,
|
|
"mean_token_accuracy": 0.1856871724128723,
|
|
"num_tokens": 40686331.0,
|
|
"step": 19600
|
|
},
|
|
{
|
|
"entropy": 5.5181825160980225,
|
|
"epoch": 1.7783925979680697,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004685518926415346,
|
|
"loss": 5.3249,
|
|
"mean_token_accuracy": 0.18334242850542068,
|
|
"num_tokens": 40697408.0,
|
|
"step": 19605
|
|
},
|
|
{
|
|
"entropy": 5.489157724380493,
|
|
"epoch": 1.7788461538461537,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.000468535391935324,
|
|
"loss": 5.2084,
|
|
"mean_token_accuracy": 0.18436521291732788,
|
|
"num_tokens": 40707078.0,
|
|
"step": 19610
|
|
},
|
|
{
|
|
"entropy": 5.622270679473877,
|
|
"epoch": 1.779299709724238,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004685188872267521,
|
|
"loss": 5.3487,
|
|
"mean_token_accuracy": 0.17885661423206328,
|
|
"num_tokens": 40718116.0,
|
|
"step": 19615
|
|
},
|
|
{
|
|
"entropy": 5.6123566150665285,
|
|
"epoch": 1.7797532656023223,
|
|
"grad_norm": 4.34375,
|
|
"learning_rate": 0.0004685023785161603,
|
|
"loss": 5.3575,
|
|
"mean_token_accuracy": 0.17374705374240876,
|
|
"num_tokens": 40727737.0,
|
|
"step": 19620
|
|
},
|
|
{
|
|
"entropy": 5.608822631835937,
|
|
"epoch": 1.7802068214804065,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004684858658038901,
|
|
"loss": 5.3367,
|
|
"mean_token_accuracy": 0.17094670236110687,
|
|
"num_tokens": 40737455.0,
|
|
"step": 19625
|
|
},
|
|
{
|
|
"entropy": 5.686861944198609,
|
|
"epoch": 1.7806603773584906,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004684693490902828,
|
|
"loss": 5.3551,
|
|
"mean_token_accuracy": 0.17705453783273697,
|
|
"num_tokens": 40746715.0,
|
|
"step": 19630
|
|
},
|
|
{
|
|
"entropy": 5.51792049407959,
|
|
"epoch": 1.7811139332365746,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.00046845282837568,
|
|
"loss": 5.2225,
|
|
"mean_token_accuracy": 0.179936046898365,
|
|
"num_tokens": 40756432.0,
|
|
"step": 19635
|
|
},
|
|
{
|
|
"entropy": 5.472628164291382,
|
|
"epoch": 1.781567489114659,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.00046843630366042355,
|
|
"loss": 5.3065,
|
|
"mean_token_accuracy": 0.17616971731185913,
|
|
"num_tokens": 40766629.0,
|
|
"step": 19640
|
|
},
|
|
{
|
|
"entropy": 5.693086004257202,
|
|
"epoch": 1.7820210449927432,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00046841977494485506,
|
|
"loss": 5.4176,
|
|
"mean_token_accuracy": 0.17106624990701674,
|
|
"num_tokens": 40776650.0,
|
|
"step": 19645
|
|
},
|
|
{
|
|
"entropy": 5.682708835601806,
|
|
"epoch": 1.7824746008708274,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004684032422293162,
|
|
"loss": 5.345,
|
|
"mean_token_accuracy": 0.1819027453660965,
|
|
"num_tokens": 40786722.0,
|
|
"step": 19650
|
|
},
|
|
{
|
|
"entropy": 5.507744073867798,
|
|
"epoch": 1.7829281567489115,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.000468386705514149,
|
|
"loss": 5.2045,
|
|
"mean_token_accuracy": 0.18634451925754547,
|
|
"num_tokens": 40797058.0,
|
|
"step": 19655
|
|
},
|
|
{
|
|
"entropy": 5.577466821670532,
|
|
"epoch": 1.7833817126269955,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004683701647996956,
|
|
"loss": 5.3927,
|
|
"mean_token_accuracy": 0.1774196907877922,
|
|
"num_tokens": 40808207.0,
|
|
"step": 19660
|
|
},
|
|
{
|
|
"entropy": 5.67679648399353,
|
|
"epoch": 1.7838352685050798,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004683536200862978,
|
|
"loss": 5.4368,
|
|
"mean_token_accuracy": 0.172083580493927,
|
|
"num_tokens": 40819655.0,
|
|
"step": 19665
|
|
},
|
|
{
|
|
"entropy": 5.641156578063965,
|
|
"epoch": 1.784288824383164,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.0004683370713742979,
|
|
"loss": 5.4459,
|
|
"mean_token_accuracy": 0.1721500813961029,
|
|
"num_tokens": 40831015.0,
|
|
"step": 19670
|
|
},
|
|
{
|
|
"entropy": 5.584281778335571,
|
|
"epoch": 1.7847423802612483,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.00046832051866403814,
|
|
"loss": 5.304,
|
|
"mean_token_accuracy": 0.1812559112906456,
|
|
"num_tokens": 40841763.0,
|
|
"step": 19675
|
|
},
|
|
{
|
|
"entropy": 5.59940824508667,
|
|
"epoch": 1.7851959361393324,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004683039619558607,
|
|
"loss": 5.3122,
|
|
"mean_token_accuracy": 0.17499426305294036,
|
|
"num_tokens": 40852479.0,
|
|
"step": 19680
|
|
},
|
|
{
|
|
"entropy": 5.661858701705933,
|
|
"epoch": 1.7856494920174164,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00046828740125010813,
|
|
"loss": 5.3481,
|
|
"mean_token_accuracy": 0.17899500131607055,
|
|
"num_tokens": 40862486.0,
|
|
"step": 19685
|
|
},
|
|
{
|
|
"entropy": 5.6543860912323,
|
|
"epoch": 1.7861030478955007,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004682708365471228,
|
|
"loss": 5.4242,
|
|
"mean_token_accuracy": 0.1727115660905838,
|
|
"num_tokens": 40872182.0,
|
|
"step": 19690
|
|
},
|
|
{
|
|
"entropy": 5.6501482963562015,
|
|
"epoch": 1.786556603773585,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00046825426784724734,
|
|
"loss": 5.4084,
|
|
"mean_token_accuracy": 0.17491225451231002,
|
|
"num_tokens": 40883036.0,
|
|
"step": 19695
|
|
},
|
|
{
|
|
"entropy": 5.6441576957702635,
|
|
"epoch": 1.7870101596516692,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.0004682376951508244,
|
|
"loss": 5.4321,
|
|
"mean_token_accuracy": 0.1642234057188034,
|
|
"num_tokens": 40893684.0,
|
|
"step": 19700
|
|
},
|
|
{
|
|
"entropy": 5.639164161682129,
|
|
"epoch": 1.7874637155297532,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.00046822111845819665,
|
|
"loss": 5.4164,
|
|
"mean_token_accuracy": 0.17425484359264373,
|
|
"num_tokens": 40904540.0,
|
|
"step": 19705
|
|
},
|
|
{
|
|
"entropy": 5.6711570739746096,
|
|
"epoch": 1.7879172714078373,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.00046820453776970697,
|
|
"loss": 5.4144,
|
|
"mean_token_accuracy": 0.17422958463430405,
|
|
"num_tokens": 40915269.0,
|
|
"step": 19710
|
|
},
|
|
{
|
|
"entropy": 5.668402481079101,
|
|
"epoch": 1.7883708272859216,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.00046818795308569815,
|
|
"loss": 5.3969,
|
|
"mean_token_accuracy": 0.17223942875862122,
|
|
"num_tokens": 40925987.0,
|
|
"step": 19715
|
|
},
|
|
{
|
|
"entropy": 5.595521783828735,
|
|
"epoch": 1.7888243831640058,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004681713644065133,
|
|
"loss": 5.3044,
|
|
"mean_token_accuracy": 0.18692538738250733,
|
|
"num_tokens": 40936130.0,
|
|
"step": 19720
|
|
},
|
|
{
|
|
"entropy": 5.538811588287354,
|
|
"epoch": 1.78927793904209,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004681547717324954,
|
|
"loss": 5.224,
|
|
"mean_token_accuracy": 0.18530235737562178,
|
|
"num_tokens": 40945476.0,
|
|
"step": 19725
|
|
},
|
|
{
|
|
"entropy": 5.471759605407715,
|
|
"epoch": 1.7897314949201741,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.00046813817506398755,
|
|
"loss": 5.2342,
|
|
"mean_token_accuracy": 0.18331867456436157,
|
|
"num_tokens": 40956492.0,
|
|
"step": 19730
|
|
},
|
|
{
|
|
"entropy": 5.619176197052002,
|
|
"epoch": 1.7901850507982582,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.00046812157440133303,
|
|
"loss": 5.4302,
|
|
"mean_token_accuracy": 0.17047760486602784,
|
|
"num_tokens": 40966990.0,
|
|
"step": 19735
|
|
},
|
|
{
|
|
"entropy": 5.659490776062012,
|
|
"epoch": 1.7906386066763424,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004681049697448752,
|
|
"loss": 5.3138,
|
|
"mean_token_accuracy": 0.17451289892196656,
|
|
"num_tokens": 40977065.0,
|
|
"step": 19740
|
|
},
|
|
{
|
|
"entropy": 5.603129100799561,
|
|
"epoch": 1.7910921625544267,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.00046808836109495734,
|
|
"loss": 5.3646,
|
|
"mean_token_accuracy": 0.17330581843852996,
|
|
"num_tokens": 40987207.0,
|
|
"step": 19745
|
|
},
|
|
{
|
|
"entropy": 5.575490951538086,
|
|
"epoch": 1.791545718432511,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004680717484519229,
|
|
"loss": 5.3102,
|
|
"mean_token_accuracy": 0.18159120976924897,
|
|
"num_tokens": 40997541.0,
|
|
"step": 19750
|
|
},
|
|
{
|
|
"entropy": 5.605378723144531,
|
|
"epoch": 1.791999274310595,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004680551318161156,
|
|
"loss": 5.3407,
|
|
"mean_token_accuracy": 0.18300080299377441,
|
|
"num_tokens": 41009044.0,
|
|
"step": 19755
|
|
},
|
|
{
|
|
"entropy": 5.631345415115357,
|
|
"epoch": 1.7924528301886793,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.00046803851118787897,
|
|
"loss": 5.3373,
|
|
"mean_token_accuracy": 0.17582239359617233,
|
|
"num_tokens": 41018165.0,
|
|
"step": 19760
|
|
},
|
|
{
|
|
"entropy": 5.550268459320068,
|
|
"epoch": 1.7929063860667633,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004680218865675567,
|
|
"loss": 5.3063,
|
|
"mean_token_accuracy": 0.17780545055866243,
|
|
"num_tokens": 41028972.0,
|
|
"step": 19765
|
|
},
|
|
{
|
|
"entropy": 5.595979261398315,
|
|
"epoch": 1.7933599419448476,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004680052579554926,
|
|
"loss": 5.3198,
|
|
"mean_token_accuracy": 0.18248026967048644,
|
|
"num_tokens": 41039552.0,
|
|
"step": 19770
|
|
},
|
|
{
|
|
"entropy": 5.642802572250366,
|
|
"epoch": 1.7938134978229319,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004679886253520307,
|
|
"loss": 5.4001,
|
|
"mean_token_accuracy": 0.16658999174833297,
|
|
"num_tokens": 41049808.0,
|
|
"step": 19775
|
|
},
|
|
{
|
|
"entropy": 5.6162810802459715,
|
|
"epoch": 1.794267053701016,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.00046797198875751474,
|
|
"loss": 5.2845,
|
|
"mean_token_accuracy": 0.173672154545784,
|
|
"num_tokens": 41060574.0,
|
|
"step": 19780
|
|
},
|
|
{
|
|
"entropy": 5.674869871139526,
|
|
"epoch": 1.7947206095791002,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004679553481722889,
|
|
"loss": 5.473,
|
|
"mean_token_accuracy": 0.17000739574432372,
|
|
"num_tokens": 41071239.0,
|
|
"step": 19785
|
|
},
|
|
{
|
|
"entropy": 5.704235553741455,
|
|
"epoch": 1.7951741654571842,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00046793870359669733,
|
|
"loss": 5.4637,
|
|
"mean_token_accuracy": 0.1706404209136963,
|
|
"num_tokens": 41080819.0,
|
|
"step": 19790
|
|
},
|
|
{
|
|
"entropy": 5.653326225280762,
|
|
"epoch": 1.7956277213352685,
|
|
"grad_norm": 3.265625,
|
|
"learning_rate": 0.0004679220550310842,
|
|
"loss": 5.2953,
|
|
"mean_token_accuracy": 0.1841547295451164,
|
|
"num_tokens": 41090457.0,
|
|
"step": 19795
|
|
},
|
|
{
|
|
"entropy": 5.60247311592102,
|
|
"epoch": 1.7960812772133528,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004679054024757937,
|
|
"loss": 5.336,
|
|
"mean_token_accuracy": 0.17884690910577775,
|
|
"num_tokens": 41101210.0,
|
|
"step": 19800
|
|
},
|
|
{
|
|
"entropy": 5.616740322113037,
|
|
"epoch": 1.796534833091437,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004678887459311704,
|
|
"loss": 5.3533,
|
|
"mean_token_accuracy": 0.17643235474824906,
|
|
"num_tokens": 41110566.0,
|
|
"step": 19805
|
|
},
|
|
{
|
|
"entropy": 5.5478087902069095,
|
|
"epoch": 1.796988388969521,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004678720853975587,
|
|
"loss": 5.2625,
|
|
"mean_token_accuracy": 0.18281441032886506,
|
|
"num_tokens": 41120000.0,
|
|
"step": 19810
|
|
},
|
|
{
|
|
"entropy": 5.507268953323364,
|
|
"epoch": 1.797441944847605,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.00046785542087530307,
|
|
"loss": 5.2357,
|
|
"mean_token_accuracy": 0.18511320799589157,
|
|
"num_tokens": 41129944.0,
|
|
"step": 19815
|
|
},
|
|
{
|
|
"entropy": 5.520359992980957,
|
|
"epoch": 1.7978955007256894,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004678387523647483,
|
|
"loss": 5.3314,
|
|
"mean_token_accuracy": 0.17720931321382521,
|
|
"num_tokens": 41138803.0,
|
|
"step": 19820
|
|
},
|
|
{
|
|
"entropy": 5.654990482330322,
|
|
"epoch": 1.7983490566037736,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.00046782207986623885,
|
|
"loss": 5.421,
|
|
"mean_token_accuracy": 0.1659836545586586,
|
|
"num_tokens": 41150365.0,
|
|
"step": 19825
|
|
},
|
|
{
|
|
"entropy": 5.705380439758301,
|
|
"epoch": 1.798802612481858,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.00046780540338011974,
|
|
"loss": 5.3748,
|
|
"mean_token_accuracy": 0.17414844632148743,
|
|
"num_tokens": 41160310.0,
|
|
"step": 19830
|
|
},
|
|
{
|
|
"entropy": 5.540922451019287,
|
|
"epoch": 1.799256168359942,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004677887229067358,
|
|
"loss": 5.2491,
|
|
"mean_token_accuracy": 0.17833552807569503,
|
|
"num_tokens": 41170506.0,
|
|
"step": 19835
|
|
},
|
|
{
|
|
"entropy": 5.62306547164917,
|
|
"epoch": 1.799709724238026,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.00046777203844643184,
|
|
"loss": 5.3847,
|
|
"mean_token_accuracy": 0.17115574181079865,
|
|
"num_tokens": 41181293.0,
|
|
"step": 19840
|
|
},
|
|
{
|
|
"entropy": 5.602049398422241,
|
|
"epoch": 1.8001632801161103,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.00046775534999955303,
|
|
"loss": 5.3155,
|
|
"mean_token_accuracy": 0.1731480911374092,
|
|
"num_tokens": 41191637.0,
|
|
"step": 19845
|
|
},
|
|
{
|
|
"entropy": 5.545235109329224,
|
|
"epoch": 1.8006168359941945,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004677386575664445,
|
|
"loss": 5.2979,
|
|
"mean_token_accuracy": 0.1854297086596489,
|
|
"num_tokens": 41201833.0,
|
|
"step": 19850
|
|
},
|
|
{
|
|
"entropy": 5.72061595916748,
|
|
"epoch": 1.8010703918722788,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00046772196114745133,
|
|
"loss": 5.3872,
|
|
"mean_token_accuracy": 0.17720824480056763,
|
|
"num_tokens": 41211243.0,
|
|
"step": 19855
|
|
},
|
|
{
|
|
"entropy": 5.656714582443238,
|
|
"epoch": 1.8015239477503628,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004677052607429189,
|
|
"loss": 5.3389,
|
|
"mean_token_accuracy": 0.1809652641415596,
|
|
"num_tokens": 41221111.0,
|
|
"step": 19860
|
|
},
|
|
{
|
|
"entropy": 5.512231683731079,
|
|
"epoch": 1.8019775036284469,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004676885563531927,
|
|
"loss": 5.3384,
|
|
"mean_token_accuracy": 0.17413154244422913,
|
|
"num_tokens": 41231578.0,
|
|
"step": 19865
|
|
},
|
|
{
|
|
"entropy": 5.588280487060547,
|
|
"epoch": 1.8024310595065312,
|
|
"grad_norm": 3.140625,
|
|
"learning_rate": 0.00046767184797861795,
|
|
"loss": 5.3868,
|
|
"mean_token_accuracy": 0.18158360570669174,
|
|
"num_tokens": 41242130.0,
|
|
"step": 19870
|
|
},
|
|
{
|
|
"entropy": 5.684222173690796,
|
|
"epoch": 1.8028846153846154,
|
|
"grad_norm": 5.0625,
|
|
"learning_rate": 0.00046765513561954026,
|
|
"loss": 5.3657,
|
|
"mean_token_accuracy": 0.17205049097537994,
|
|
"num_tokens": 41252885.0,
|
|
"step": 19875
|
|
},
|
|
{
|
|
"entropy": 5.690085124969483,
|
|
"epoch": 1.8033381712626997,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.00046763841927630534,
|
|
"loss": 5.3882,
|
|
"mean_token_accuracy": 0.17447094172239302,
|
|
"num_tokens": 41263532.0,
|
|
"step": 19880
|
|
},
|
|
{
|
|
"entropy": 5.631875801086426,
|
|
"epoch": 1.8037917271407837,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00046762169894925876,
|
|
"loss": 5.3498,
|
|
"mean_token_accuracy": 0.17695174217224122,
|
|
"num_tokens": 41273469.0,
|
|
"step": 19885
|
|
},
|
|
{
|
|
"entropy": 5.618402767181396,
|
|
"epoch": 1.8042452830188678,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004676049746387464,
|
|
"loss": 5.3557,
|
|
"mean_token_accuracy": 0.17450938671827315,
|
|
"num_tokens": 41283663.0,
|
|
"step": 19890
|
|
},
|
|
{
|
|
"entropy": 5.554345703125,
|
|
"epoch": 1.804698838896952,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004675882463451141,
|
|
"loss": 5.2826,
|
|
"mean_token_accuracy": 0.17934316992759705,
|
|
"num_tokens": 41294657.0,
|
|
"step": 19895
|
|
},
|
|
{
|
|
"entropy": 5.6345805644989015,
|
|
"epoch": 1.8051523947750363,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004675715140687078,
|
|
"loss": 5.3759,
|
|
"mean_token_accuracy": 0.17511067688465118,
|
|
"num_tokens": 41305124.0,
|
|
"step": 19900
|
|
},
|
|
{
|
|
"entropy": 5.608033275604248,
|
|
"epoch": 1.8056059506531206,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.00046755477780987344,
|
|
"loss": 5.3055,
|
|
"mean_token_accuracy": 0.1842399314045906,
|
|
"num_tokens": 41315839.0,
|
|
"step": 19905
|
|
},
|
|
{
|
|
"entropy": 5.664808750152588,
|
|
"epoch": 1.8060595065312046,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.00046753803756895726,
|
|
"loss": 5.3671,
|
|
"mean_token_accuracy": 0.17416536659002305,
|
|
"num_tokens": 41326388.0,
|
|
"step": 19910
|
|
},
|
|
{
|
|
"entropy": 5.594422292709351,
|
|
"epoch": 1.8065130624092887,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004675212933463054,
|
|
"loss": 5.3907,
|
|
"mean_token_accuracy": 0.1707173004746437,
|
|
"num_tokens": 41337333.0,
|
|
"step": 19915
|
|
},
|
|
{
|
|
"entropy": 5.65008864402771,
|
|
"epoch": 1.806966618287373,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004675045451422641,
|
|
"loss": 5.4108,
|
|
"mean_token_accuracy": 0.16649702936410904,
|
|
"num_tokens": 41348353.0,
|
|
"step": 19920
|
|
},
|
|
{
|
|
"entropy": 5.649384260177612,
|
|
"epoch": 1.8074201741654572,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.00046748779295717973,
|
|
"loss": 5.4156,
|
|
"mean_token_accuracy": 0.17900662273168563,
|
|
"num_tokens": 41358797.0,
|
|
"step": 19925
|
|
},
|
|
{
|
|
"entropy": 5.621867752075195,
|
|
"epoch": 1.8078737300435415,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004674710367913989,
|
|
"loss": 5.3831,
|
|
"mean_token_accuracy": 0.17351793944835664,
|
|
"num_tokens": 41368818.0,
|
|
"step": 19930
|
|
},
|
|
{
|
|
"entropy": 5.611099624633789,
|
|
"epoch": 1.8083272859216255,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004674542766452678,
|
|
"loss": 5.3503,
|
|
"mean_token_accuracy": 0.1799370139837265,
|
|
"num_tokens": 41378949.0,
|
|
"step": 19935
|
|
},
|
|
{
|
|
"entropy": 5.600044250488281,
|
|
"epoch": 1.8087808417997098,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.00046743751251913327,
|
|
"loss": 5.332,
|
|
"mean_token_accuracy": 0.17422647923231124,
|
|
"num_tokens": 41388892.0,
|
|
"step": 19940
|
|
},
|
|
{
|
|
"entropy": 5.639744710922241,
|
|
"epoch": 1.8092343976777938,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00046742074441334197,
|
|
"loss": 5.346,
|
|
"mean_token_accuracy": 0.17806581705808638,
|
|
"num_tokens": 41399197.0,
|
|
"step": 19945
|
|
},
|
|
{
|
|
"entropy": 5.6118812084198,
|
|
"epoch": 1.809687953555878,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004674039723282406,
|
|
"loss": 5.3605,
|
|
"mean_token_accuracy": 0.17362990975379944,
|
|
"num_tokens": 41409551.0,
|
|
"step": 19950
|
|
},
|
|
{
|
|
"entropy": 5.579838466644287,
|
|
"epoch": 1.8101415094339623,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00046738719626417607,
|
|
"loss": 5.2743,
|
|
"mean_token_accuracy": 0.17530772536993028,
|
|
"num_tokens": 41418900.0,
|
|
"step": 19955
|
|
},
|
|
{
|
|
"entropy": 5.563149547576904,
|
|
"epoch": 1.8105950653120464,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.00046737041622149536,
|
|
"loss": 5.2974,
|
|
"mean_token_accuracy": 0.17335549294948577,
|
|
"num_tokens": 41428204.0,
|
|
"step": 19960
|
|
},
|
|
{
|
|
"entropy": 5.6016950607299805,
|
|
"epoch": 1.8110486211901307,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004673536322005454,
|
|
"loss": 5.3303,
|
|
"mean_token_accuracy": 0.1719498112797737,
|
|
"num_tokens": 41437922.0,
|
|
"step": 19965
|
|
},
|
|
{
|
|
"entropy": 5.642927742004394,
|
|
"epoch": 1.8115021770682147,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004673368442016732,
|
|
"loss": 5.3336,
|
|
"mean_token_accuracy": 0.17381825745105745,
|
|
"num_tokens": 41447411.0,
|
|
"step": 19970
|
|
},
|
|
{
|
|
"entropy": 5.697069358825684,
|
|
"epoch": 1.811955732946299,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004673200522252261,
|
|
"loss": 5.4531,
|
|
"mean_token_accuracy": 0.174184912443161,
|
|
"num_tokens": 41458756.0,
|
|
"step": 19975
|
|
},
|
|
{
|
|
"entropy": 5.6131586074829105,
|
|
"epoch": 1.8124092888243832,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004673032562715514,
|
|
"loss": 5.3332,
|
|
"mean_token_accuracy": 0.17937437891960145,
|
|
"num_tokens": 41468610.0,
|
|
"step": 19980
|
|
},
|
|
{
|
|
"entropy": 5.6222865104675295,
|
|
"epoch": 1.8128628447024675,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.00046728645634099627,
|
|
"loss": 5.4543,
|
|
"mean_token_accuracy": 0.16775120943784713,
|
|
"num_tokens": 41479849.0,
|
|
"step": 19985
|
|
},
|
|
{
|
|
"entropy": 5.671052885055542,
|
|
"epoch": 1.8133164005805515,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.00046726965243390825,
|
|
"loss": 5.3696,
|
|
"mean_token_accuracy": 0.17068469524383545,
|
|
"num_tokens": 41490945.0,
|
|
"step": 19990
|
|
},
|
|
{
|
|
"entropy": 5.587462329864502,
|
|
"epoch": 1.8137699564586356,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004672528445506348,
|
|
"loss": 5.2874,
|
|
"mean_token_accuracy": 0.1736278772354126,
|
|
"num_tokens": 41501479.0,
|
|
"step": 19995
|
|
},
|
|
{
|
|
"entropy": 5.617448520660401,
|
|
"epoch": 1.8142235123367199,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004672360326915236,
|
|
"loss": 5.2934,
|
|
"mean_token_accuracy": 0.18212878108024597,
|
|
"num_tokens": 41512447.0,
|
|
"step": 20000
|
|
},
|
|
{
|
|
"entropy": 5.556536054611206,
|
|
"epoch": 1.8146770682148041,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004672192168569222,
|
|
"loss": 5.2531,
|
|
"mean_token_accuracy": 0.18824298232793807,
|
|
"num_tokens": 41521905.0,
|
|
"step": 20005
|
|
},
|
|
{
|
|
"entropy": 5.604899740219116,
|
|
"epoch": 1.8151306240928884,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.00046720239704717845,
|
|
"loss": 5.3859,
|
|
"mean_token_accuracy": 0.17762788087129594,
|
|
"num_tokens": 41533143.0,
|
|
"step": 20010
|
|
},
|
|
{
|
|
"entropy": 5.607953929901123,
|
|
"epoch": 1.8155841799709724,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.00046718557326264,
|
|
"loss": 5.2868,
|
|
"mean_token_accuracy": 0.17668697088956833,
|
|
"num_tokens": 41542234.0,
|
|
"step": 20015
|
|
},
|
|
{
|
|
"entropy": 5.6473315238952635,
|
|
"epoch": 1.8160377358490565,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.0004671687455036551,
|
|
"loss": 5.4129,
|
|
"mean_token_accuracy": 0.17008544951677323,
|
|
"num_tokens": 41552632.0,
|
|
"step": 20020
|
|
},
|
|
{
|
|
"entropy": 5.613354730606079,
|
|
"epoch": 1.8164912917271407,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004671519137705715,
|
|
"loss": 5.3613,
|
|
"mean_token_accuracy": 0.18266426473855973,
|
|
"num_tokens": 41563723.0,
|
|
"step": 20025
|
|
},
|
|
{
|
|
"entropy": 5.631220102310181,
|
|
"epoch": 1.816944847605225,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00046713507806373736,
|
|
"loss": 5.3012,
|
|
"mean_token_accuracy": 0.17664394229650499,
|
|
"num_tokens": 41573680.0,
|
|
"step": 20030
|
|
},
|
|
{
|
|
"entropy": 5.614723777770996,
|
|
"epoch": 1.8173984034833093,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00046711823838350086,
|
|
"loss": 5.3797,
|
|
"mean_token_accuracy": 0.1761721834540367,
|
|
"num_tokens": 41584722.0,
|
|
"step": 20035
|
|
},
|
|
{
|
|
"entropy": 5.626146984100342,
|
|
"epoch": 1.8178519593613933,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.00046710139473021025,
|
|
"loss": 5.4157,
|
|
"mean_token_accuracy": 0.1732687994837761,
|
|
"num_tokens": 41595785.0,
|
|
"step": 20040
|
|
},
|
|
{
|
|
"entropy": 5.631767082214355,
|
|
"epoch": 1.8183055152394774,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.00046708454710421376,
|
|
"loss": 5.4214,
|
|
"mean_token_accuracy": 0.17052825838327407,
|
|
"num_tokens": 41606023.0,
|
|
"step": 20045
|
|
},
|
|
{
|
|
"entropy": 5.634230422973633,
|
|
"epoch": 1.8187590711175616,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00046706769550586,
|
|
"loss": 5.3364,
|
|
"mean_token_accuracy": 0.1778011977672577,
|
|
"num_tokens": 41616010.0,
|
|
"step": 20050
|
|
},
|
|
{
|
|
"entropy": 5.648975563049317,
|
|
"epoch": 1.819212626995646,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00046705083993549723,
|
|
"loss": 5.3025,
|
|
"mean_token_accuracy": 0.17905359864234924,
|
|
"num_tokens": 41625105.0,
|
|
"step": 20055
|
|
},
|
|
{
|
|
"entropy": 5.605409955978393,
|
|
"epoch": 1.8196661828737302,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004670339803934743,
|
|
"loss": 5.3536,
|
|
"mean_token_accuracy": 0.17418388575315474,
|
|
"num_tokens": 41634989.0,
|
|
"step": 20060
|
|
},
|
|
{
|
|
"entropy": 5.5826162815094,
|
|
"epoch": 1.8201197387518142,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004670171168801396,
|
|
"loss": 5.3414,
|
|
"mean_token_accuracy": 0.1753065213561058,
|
|
"num_tokens": 41645736.0,
|
|
"step": 20065
|
|
},
|
|
{
|
|
"entropy": 5.728058242797852,
|
|
"epoch": 1.8205732946298983,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.000467000249395842,
|
|
"loss": 5.3594,
|
|
"mean_token_accuracy": 0.17920278310775756,
|
|
"num_tokens": 41655505.0,
|
|
"step": 20070
|
|
},
|
|
{
|
|
"entropy": 5.5785785675048825,
|
|
"epoch": 1.8210268505079825,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004669833779409303,
|
|
"loss": 5.3229,
|
|
"mean_token_accuracy": 0.1806856095790863,
|
|
"num_tokens": 41665732.0,
|
|
"step": 20075
|
|
},
|
|
{
|
|
"entropy": 5.530978584289551,
|
|
"epoch": 1.8214804063860668,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004669665025157535,
|
|
"loss": 5.3016,
|
|
"mean_token_accuracy": 0.17425428330898285,
|
|
"num_tokens": 41676050.0,
|
|
"step": 20080
|
|
},
|
|
{
|
|
"entropy": 5.687395906448364,
|
|
"epoch": 1.821933962264151,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00046694962312066046,
|
|
"loss": 5.4747,
|
|
"mean_token_accuracy": 0.17320988923311234,
|
|
"num_tokens": 41686787.0,
|
|
"step": 20085
|
|
},
|
|
{
|
|
"entropy": 5.614485025405884,
|
|
"epoch": 1.822387518142235,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.00046693273975600036,
|
|
"loss": 5.2737,
|
|
"mean_token_accuracy": 0.1782482758164406,
|
|
"num_tokens": 41697168.0,
|
|
"step": 20090
|
|
},
|
|
{
|
|
"entropy": 5.574175643920898,
|
|
"epoch": 1.8228410740203191,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004669158524221222,
|
|
"loss": 5.357,
|
|
"mean_token_accuracy": 0.1797088772058487,
|
|
"num_tokens": 41707524.0,
|
|
"step": 20095
|
|
},
|
|
{
|
|
"entropy": 5.625791263580322,
|
|
"epoch": 1.8232946298984034,
|
|
"grad_norm": 3.28125,
|
|
"learning_rate": 0.00046689896111937537,
|
|
"loss": 5.4033,
|
|
"mean_token_accuracy": 0.1816592827439308,
|
|
"num_tokens": 41718109.0,
|
|
"step": 20100
|
|
},
|
|
{
|
|
"entropy": 5.672273778915406,
|
|
"epoch": 1.8237481857764877,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004668820658481091,
|
|
"loss": 5.3722,
|
|
"mean_token_accuracy": 0.1740395247936249,
|
|
"num_tokens": 41728862.0,
|
|
"step": 20105
|
|
},
|
|
{
|
|
"entropy": 5.684803867340088,
|
|
"epoch": 1.824201741654572,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00046686516660867283,
|
|
"loss": 5.4264,
|
|
"mean_token_accuracy": 0.17284301817417144,
|
|
"num_tokens": 41739024.0,
|
|
"step": 20110
|
|
},
|
|
{
|
|
"entropy": 5.623004150390625,
|
|
"epoch": 1.824655297532656,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004668482634014159,
|
|
"loss": 5.3591,
|
|
"mean_token_accuracy": 0.17618923783302307,
|
|
"num_tokens": 41748979.0,
|
|
"step": 20115
|
|
},
|
|
{
|
|
"entropy": 5.6008225440979,
|
|
"epoch": 1.8251088534107403,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004668313562266882,
|
|
"loss": 5.39,
|
|
"mean_token_accuracy": 0.1737375944852829,
|
|
"num_tokens": 41759972.0,
|
|
"step": 20120
|
|
},
|
|
{
|
|
"entropy": 5.623783779144287,
|
|
"epoch": 1.8255624092888243,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.000466814445084839,
|
|
"loss": 5.2465,
|
|
"mean_token_accuracy": 0.1842593476176262,
|
|
"num_tokens": 41770150.0,
|
|
"step": 20125
|
|
},
|
|
{
|
|
"entropy": 5.591795539855957,
|
|
"epoch": 1.8260159651669086,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004667975299762183,
|
|
"loss": 5.3006,
|
|
"mean_token_accuracy": 0.18156401216983795,
|
|
"num_tokens": 41780405.0,
|
|
"step": 20130
|
|
},
|
|
{
|
|
"entropy": 5.550405597686767,
|
|
"epoch": 1.8264695210449928,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00046678061090117576,
|
|
"loss": 5.242,
|
|
"mean_token_accuracy": 0.1840645283460617,
|
|
"num_tokens": 41791269.0,
|
|
"step": 20135
|
|
},
|
|
{
|
|
"entropy": 5.533142137527466,
|
|
"epoch": 1.8269230769230769,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.0004667636878600613,
|
|
"loss": 5.2404,
|
|
"mean_token_accuracy": 0.18553030490875244,
|
|
"num_tokens": 41802513.0,
|
|
"step": 20140
|
|
},
|
|
{
|
|
"entropy": 5.649284219741821,
|
|
"epoch": 1.8273766328011611,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.0004667467608532249,
|
|
"loss": 5.4113,
|
|
"mean_token_accuracy": 0.1646406263113022,
|
|
"num_tokens": 41814149.0,
|
|
"step": 20145
|
|
},
|
|
{
|
|
"entropy": 5.649250650405884,
|
|
"epoch": 1.8278301886792452,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004667298298810167,
|
|
"loss": 5.3678,
|
|
"mean_token_accuracy": 0.17089359313249589,
|
|
"num_tokens": 41825763.0,
|
|
"step": 20150
|
|
},
|
|
{
|
|
"entropy": 5.582114934921265,
|
|
"epoch": 1.8282837445573294,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004667128949437867,
|
|
"loss": 5.3152,
|
|
"mean_token_accuracy": 0.1824391633272171,
|
|
"num_tokens": 41834543.0,
|
|
"step": 20155
|
|
},
|
|
{
|
|
"entropy": 5.556038331985474,
|
|
"epoch": 1.8287373004354137,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004666959560418852,
|
|
"loss": 5.259,
|
|
"mean_token_accuracy": 0.185418201982975,
|
|
"num_tokens": 41844940.0,
|
|
"step": 20160
|
|
},
|
|
{
|
|
"entropy": 5.521585845947266,
|
|
"epoch": 1.829190856313498,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.00046667901317566245,
|
|
"loss": 5.2515,
|
|
"mean_token_accuracy": 0.18432953655719758,
|
|
"num_tokens": 41855532.0,
|
|
"step": 20165
|
|
},
|
|
{
|
|
"entropy": 5.603979825973511,
|
|
"epoch": 1.829644412191582,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004666620663454689,
|
|
"loss": 5.3424,
|
|
"mean_token_accuracy": 0.17588334381580353,
|
|
"num_tokens": 41865661.0,
|
|
"step": 20170
|
|
},
|
|
{
|
|
"entropy": 5.62714695930481,
|
|
"epoch": 1.830097968069666,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.00046664511555165496,
|
|
"loss": 5.3543,
|
|
"mean_token_accuracy": 0.17444636076688766,
|
|
"num_tokens": 41875662.0,
|
|
"step": 20175
|
|
},
|
|
{
|
|
"entropy": 5.58561863899231,
|
|
"epoch": 1.8305515239477503,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.00046662816079457114,
|
|
"loss": 5.3167,
|
|
"mean_token_accuracy": 0.1847178116440773,
|
|
"num_tokens": 41886211.0,
|
|
"step": 20180
|
|
},
|
|
{
|
|
"entropy": 5.671750831604004,
|
|
"epoch": 1.8310050798258346,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004666112020745682,
|
|
"loss": 5.4254,
|
|
"mean_token_accuracy": 0.1701081231236458,
|
|
"num_tokens": 41896737.0,
|
|
"step": 20185
|
|
},
|
|
{
|
|
"entropy": 5.6402030944824215,
|
|
"epoch": 1.8314586357039189,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004665942393919967,
|
|
"loss": 5.3239,
|
|
"mean_token_accuracy": 0.1777401939034462,
|
|
"num_tokens": 41907768.0,
|
|
"step": 20190
|
|
},
|
|
{
|
|
"entropy": 5.581164216995239,
|
|
"epoch": 1.831912191582003,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.00046657727274720755,
|
|
"loss": 5.2784,
|
|
"mean_token_accuracy": 0.17186637818813325,
|
|
"num_tokens": 41917587.0,
|
|
"step": 20195
|
|
},
|
|
{
|
|
"entropy": 5.559817361831665,
|
|
"epoch": 1.832365747460087,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004665603021405516,
|
|
"loss": 5.2575,
|
|
"mean_token_accuracy": 0.18595339804887773,
|
|
"num_tokens": 41927842.0,
|
|
"step": 20200
|
|
},
|
|
{
|
|
"entropy": 5.570213460922242,
|
|
"epoch": 1.8328193033381712,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004665433275723798,
|
|
"loss": 5.328,
|
|
"mean_token_accuracy": 0.18083423972129822,
|
|
"num_tokens": 41939899.0,
|
|
"step": 20205
|
|
},
|
|
{
|
|
"entropy": 5.552170753479004,
|
|
"epoch": 1.8332728592162555,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004665263490430431,
|
|
"loss": 5.321,
|
|
"mean_token_accuracy": 0.17033784687519074,
|
|
"num_tokens": 41950932.0,
|
|
"step": 20210
|
|
},
|
|
{
|
|
"entropy": 5.666450691223145,
|
|
"epoch": 1.8337264150943398,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004665093665528928,
|
|
"loss": 5.3876,
|
|
"mean_token_accuracy": 0.18021780550479888,
|
|
"num_tokens": 41963512.0,
|
|
"step": 20215
|
|
},
|
|
{
|
|
"entropy": 5.682989931106567,
|
|
"epoch": 1.8341799709724238,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.00046649238010227983,
|
|
"loss": 5.3735,
|
|
"mean_token_accuracy": 0.18292613029479982,
|
|
"num_tokens": 41974677.0,
|
|
"step": 20220
|
|
},
|
|
{
|
|
"entropy": 5.539256381988525,
|
|
"epoch": 1.8346335268505078,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004664753896915558,
|
|
"loss": 5.272,
|
|
"mean_token_accuracy": 0.18018632978200913,
|
|
"num_tokens": 41984582.0,
|
|
"step": 20225
|
|
},
|
|
{
|
|
"entropy": 5.591216421127319,
|
|
"epoch": 1.8350870827285921,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004664583953210719,
|
|
"loss": 5.2618,
|
|
"mean_token_accuracy": 0.17830848395824433,
|
|
"num_tokens": 41994624.0,
|
|
"step": 20230
|
|
},
|
|
{
|
|
"entropy": 5.581273794174194,
|
|
"epoch": 1.8355406386066764,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004664413969911795,
|
|
"loss": 5.2628,
|
|
"mean_token_accuracy": 0.18329974859952927,
|
|
"num_tokens": 42004835.0,
|
|
"step": 20235
|
|
},
|
|
{
|
|
"entropy": 5.492052745819092,
|
|
"epoch": 1.8359941944847606,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004664243947022303,
|
|
"loss": 5.2872,
|
|
"mean_token_accuracy": 0.18002185374498367,
|
|
"num_tokens": 42014727.0,
|
|
"step": 20240
|
|
},
|
|
{
|
|
"entropy": 5.598493385314941,
|
|
"epoch": 1.8364477503628447,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.00046640738845457586,
|
|
"loss": 5.3489,
|
|
"mean_token_accuracy": 0.18274054825305938,
|
|
"num_tokens": 42023628.0,
|
|
"step": 20245
|
|
},
|
|
{
|
|
"entropy": 5.701423168182373,
|
|
"epoch": 1.8369013062409287,
|
|
"grad_norm": 3.28125,
|
|
"learning_rate": 0.0004663903782485678,
|
|
"loss": 5.3931,
|
|
"mean_token_accuracy": 0.16785927712917328,
|
|
"num_tokens": 42033587.0,
|
|
"step": 20250
|
|
},
|
|
{
|
|
"entropy": 5.674915981292725,
|
|
"epoch": 1.837354862119013,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.00046637336408455793,
|
|
"loss": 5.3823,
|
|
"mean_token_accuracy": 0.1756364196538925,
|
|
"num_tokens": 42043765.0,
|
|
"step": 20255
|
|
},
|
|
{
|
|
"entropy": 5.674901723861694,
|
|
"epoch": 1.8378084179970973,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00046635634596289816,
|
|
"loss": 5.4417,
|
|
"mean_token_accuracy": 0.17061454057693481,
|
|
"num_tokens": 42054205.0,
|
|
"step": 20260
|
|
},
|
|
{
|
|
"entropy": 5.541941499710083,
|
|
"epoch": 1.8382619738751815,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004663393238839404,
|
|
"loss": 5.2468,
|
|
"mean_token_accuracy": 0.1775173917412758,
|
|
"num_tokens": 42064512.0,
|
|
"step": 20265
|
|
},
|
|
{
|
|
"entropy": 5.627379274368286,
|
|
"epoch": 1.8387155297532656,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004663222978480366,
|
|
"loss": 5.3335,
|
|
"mean_token_accuracy": 0.17358211874961854,
|
|
"num_tokens": 42074954.0,
|
|
"step": 20270
|
|
},
|
|
{
|
|
"entropy": 5.61252384185791,
|
|
"epoch": 1.8391690856313496,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000466305267855539,
|
|
"loss": 5.3553,
|
|
"mean_token_accuracy": 0.17447749376296998,
|
|
"num_tokens": 42084914.0,
|
|
"step": 20275
|
|
},
|
|
{
|
|
"entropy": 5.611517524719238,
|
|
"epoch": 1.8396226415094339,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004662882339067996,
|
|
"loss": 5.382,
|
|
"mean_token_accuracy": 0.1819140538573265,
|
|
"num_tokens": 42095454.0,
|
|
"step": 20280
|
|
},
|
|
{
|
|
"entropy": 5.6298657894134525,
|
|
"epoch": 1.8400761973875182,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004662711960021709,
|
|
"loss": 5.4129,
|
|
"mean_token_accuracy": 0.1735288083553314,
|
|
"num_tokens": 42106960.0,
|
|
"step": 20285
|
|
},
|
|
{
|
|
"entropy": 5.621958208084107,
|
|
"epoch": 1.8405297532656024,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00046625415414200513,
|
|
"loss": 5.3231,
|
|
"mean_token_accuracy": 0.17864820808172227,
|
|
"num_tokens": 42117009.0,
|
|
"step": 20290
|
|
},
|
|
{
|
|
"entropy": 5.624494504928589,
|
|
"epoch": 1.8409833091436865,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004662371083266546,
|
|
"loss": 5.3247,
|
|
"mean_token_accuracy": 0.1826027363538742,
|
|
"num_tokens": 42126371.0,
|
|
"step": 20295
|
|
},
|
|
{
|
|
"entropy": 5.622463512420654,
|
|
"epoch": 1.8414368650217707,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.000466220058556472,
|
|
"loss": 5.353,
|
|
"mean_token_accuracy": 0.17544743418693542,
|
|
"num_tokens": 42135890.0,
|
|
"step": 20300
|
|
},
|
|
{
|
|
"entropy": 5.685268688201904,
|
|
"epoch": 1.8418904208998548,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00046620300483180986,
|
|
"loss": 5.4649,
|
|
"mean_token_accuracy": 0.16984558552503587,
|
|
"num_tokens": 42145696.0,
|
|
"step": 20305
|
|
},
|
|
{
|
|
"entropy": 5.658343839645386,
|
|
"epoch": 1.842343976777939,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004661859471530209,
|
|
"loss": 5.3903,
|
|
"mean_token_accuracy": 0.178889399766922,
|
|
"num_tokens": 42156236.0,
|
|
"step": 20310
|
|
},
|
|
{
|
|
"entropy": 5.661155796051025,
|
|
"epoch": 1.8427975326560233,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004661688855204578,
|
|
"loss": 5.397,
|
|
"mean_token_accuracy": 0.1761537730693817,
|
|
"num_tokens": 42166179.0,
|
|
"step": 20315
|
|
},
|
|
{
|
|
"entropy": 5.5670881271362305,
|
|
"epoch": 1.8432510885341074,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.00046615181993447344,
|
|
"loss": 5.2584,
|
|
"mean_token_accuracy": 0.18012099862098693,
|
|
"num_tokens": 42176643.0,
|
|
"step": 20320
|
|
},
|
|
{
|
|
"entropy": 5.654352903366089,
|
|
"epoch": 1.8437046444121916,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004661347503954207,
|
|
"loss": 5.5222,
|
|
"mean_token_accuracy": 0.16660608053207399,
|
|
"num_tokens": 42188328.0,
|
|
"step": 20325
|
|
},
|
|
{
|
|
"entropy": 5.702789449691773,
|
|
"epoch": 1.8441582002902757,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.00046611767690365265,
|
|
"loss": 5.3771,
|
|
"mean_token_accuracy": 0.17802393883466722,
|
|
"num_tokens": 42198110.0,
|
|
"step": 20330
|
|
},
|
|
{
|
|
"entropy": 5.5508620262146,
|
|
"epoch": 1.84461175616836,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004661005994595223,
|
|
"loss": 5.3065,
|
|
"mean_token_accuracy": 0.1750512793660164,
|
|
"num_tokens": 42208438.0,
|
|
"step": 20335
|
|
},
|
|
{
|
|
"entropy": 5.582424640655518,
|
|
"epoch": 1.8450653120464442,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004660835180633829,
|
|
"loss": 5.3184,
|
|
"mean_token_accuracy": 0.17899395972490312,
|
|
"num_tokens": 42220052.0,
|
|
"step": 20340
|
|
},
|
|
{
|
|
"entropy": 5.58581509590149,
|
|
"epoch": 1.8455188679245285,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004660664327155876,
|
|
"loss": 5.3126,
|
|
"mean_token_accuracy": 0.1791388601064682,
|
|
"num_tokens": 42229497.0,
|
|
"step": 20345
|
|
},
|
|
{
|
|
"entropy": 5.645520401000977,
|
|
"epoch": 1.8459724238026125,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004660493434164898,
|
|
"loss": 5.3673,
|
|
"mean_token_accuracy": 0.1652689278125763,
|
|
"num_tokens": 42240725.0,
|
|
"step": 20350
|
|
},
|
|
{
|
|
"entropy": 5.660212230682373,
|
|
"epoch": 1.8464259796806965,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004660322501664429,
|
|
"loss": 5.3664,
|
|
"mean_token_accuracy": 0.17083102464675903,
|
|
"num_tokens": 42251114.0,
|
|
"step": 20355
|
|
},
|
|
{
|
|
"entropy": 5.627463436126709,
|
|
"epoch": 1.8468795355587808,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004660151529658004,
|
|
"loss": 5.5339,
|
|
"mean_token_accuracy": 0.16776434928178788,
|
|
"num_tokens": 42262825.0,
|
|
"step": 20360
|
|
},
|
|
{
|
|
"entropy": 5.673953485488892,
|
|
"epoch": 1.847333091436865,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004659980518149158,
|
|
"loss": 5.3731,
|
|
"mean_token_accuracy": 0.1870659828186035,
|
|
"num_tokens": 42272176.0,
|
|
"step": 20365
|
|
},
|
|
{
|
|
"entropy": 5.697510862350464,
|
|
"epoch": 1.8477866473149493,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00046598094671414285,
|
|
"loss": 5.4101,
|
|
"mean_token_accuracy": 0.17941180616617203,
|
|
"num_tokens": 42281934.0,
|
|
"step": 20370
|
|
},
|
|
{
|
|
"entropy": 5.612187623977661,
|
|
"epoch": 1.8482402031930334,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.00046596383766383533,
|
|
"loss": 5.2729,
|
|
"mean_token_accuracy": 0.18222297430038453,
|
|
"num_tokens": 42291927.0,
|
|
"step": 20375
|
|
},
|
|
{
|
|
"entropy": 5.5269444465637205,
|
|
"epoch": 1.8486937590711174,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004659467246643469,
|
|
"loss": 5.2798,
|
|
"mean_token_accuracy": 0.17771393358707427,
|
|
"num_tokens": 42301407.0,
|
|
"step": 20380
|
|
},
|
|
{
|
|
"entropy": 5.549838924407959,
|
|
"epoch": 1.8491473149492017,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00046592960771603154,
|
|
"loss": 5.2209,
|
|
"mean_token_accuracy": 0.18676933646202087,
|
|
"num_tokens": 42311199.0,
|
|
"step": 20385
|
|
},
|
|
{
|
|
"entropy": 5.605197238922119,
|
|
"epoch": 1.849600870827286,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004659124868192433,
|
|
"loss": 5.2908,
|
|
"mean_token_accuracy": 0.18158123046159744,
|
|
"num_tokens": 42320725.0,
|
|
"step": 20390
|
|
},
|
|
{
|
|
"entropy": 5.68499722480774,
|
|
"epoch": 1.8500544267053702,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004658953619743361,
|
|
"loss": 5.4138,
|
|
"mean_token_accuracy": 0.18145075738430022,
|
|
"num_tokens": 42330857.0,
|
|
"step": 20395
|
|
},
|
|
{
|
|
"entropy": 5.5652374744415285,
|
|
"epoch": 1.8505079825834543,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.00046587823318166427,
|
|
"loss": 5.2394,
|
|
"mean_token_accuracy": 0.17721331119537354,
|
|
"num_tokens": 42340241.0,
|
|
"step": 20400
|
|
},
|
|
{
|
|
"entropy": 5.637735891342163,
|
|
"epoch": 1.8509615384615383,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00046586110044158184,
|
|
"loss": 5.4651,
|
|
"mean_token_accuracy": 0.16881994903087616,
|
|
"num_tokens": 42351756.0,
|
|
"step": 20405
|
|
},
|
|
{
|
|
"entropy": 5.572450923919678,
|
|
"epoch": 1.8514150943396226,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00046584396375444335,
|
|
"loss": 5.2824,
|
|
"mean_token_accuracy": 0.18508216589689255,
|
|
"num_tokens": 42361649.0,
|
|
"step": 20410
|
|
},
|
|
{
|
|
"entropy": 5.5724200248718265,
|
|
"epoch": 1.8518686502177069,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00046582682312060295,
|
|
"loss": 5.3256,
|
|
"mean_token_accuracy": 0.17992573082447053,
|
|
"num_tokens": 42371273.0,
|
|
"step": 20415
|
|
},
|
|
{
|
|
"entropy": 5.567512798309326,
|
|
"epoch": 1.8523222060957911,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004658096785404152,
|
|
"loss": 5.3198,
|
|
"mean_token_accuracy": 0.1752101555466652,
|
|
"num_tokens": 42382275.0,
|
|
"step": 20420
|
|
},
|
|
{
|
|
"entropy": 5.647589302062988,
|
|
"epoch": 1.8527757619738752,
|
|
"grad_norm": 3.1875,
|
|
"learning_rate": 0.00046579253001423473,
|
|
"loss": 5.3431,
|
|
"mean_token_accuracy": 0.1732073649764061,
|
|
"num_tokens": 42392360.0,
|
|
"step": 20425
|
|
},
|
|
{
|
|
"entropy": 5.5687182426452635,
|
|
"epoch": 1.8532293178519592,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.00046577537754241604,
|
|
"loss": 5.3626,
|
|
"mean_token_accuracy": 0.17189036309719086,
|
|
"num_tokens": 42403695.0,
|
|
"step": 20430
|
|
},
|
|
{
|
|
"entropy": 5.590752410888672,
|
|
"epoch": 1.8536828737300435,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.000465758221125314,
|
|
"loss": 5.2713,
|
|
"mean_token_accuracy": 0.18004548996686937,
|
|
"num_tokens": 42414199.0,
|
|
"step": 20435
|
|
},
|
|
{
|
|
"entropy": 5.632169389724732,
|
|
"epoch": 1.8541364296081277,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00046574106076328333,
|
|
"loss": 5.3939,
|
|
"mean_token_accuracy": 0.17645664662122726,
|
|
"num_tokens": 42423655.0,
|
|
"step": 20440
|
|
},
|
|
{
|
|
"entropy": 5.615240955352784,
|
|
"epoch": 1.854589985486212,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004657238964566789,
|
|
"loss": 5.3001,
|
|
"mean_token_accuracy": 0.1796916276216507,
|
|
"num_tokens": 42434235.0,
|
|
"step": 20445
|
|
},
|
|
{
|
|
"entropy": 5.530942678451538,
|
|
"epoch": 1.855043541364296,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004657067282058557,
|
|
"loss": 5.3314,
|
|
"mean_token_accuracy": 0.17877513617277146,
|
|
"num_tokens": 42444701.0,
|
|
"step": 20450
|
|
},
|
|
{
|
|
"entropy": 5.569309091567993,
|
|
"epoch": 1.85549709724238,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004656895560111687,
|
|
"loss": 5.2904,
|
|
"mean_token_accuracy": 0.17917528599500657,
|
|
"num_tokens": 42454499.0,
|
|
"step": 20455
|
|
},
|
|
{
|
|
"entropy": 5.701203536987305,
|
|
"epoch": 1.8559506531204644,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00046567237987297323,
|
|
"loss": 5.2946,
|
|
"mean_token_accuracy": 0.16980371698737146,
|
|
"num_tokens": 42465391.0,
|
|
"step": 20460
|
|
},
|
|
{
|
|
"entropy": 5.651789426803589,
|
|
"epoch": 1.8564042089985486,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004656551997916243,
|
|
"loss": 5.2989,
|
|
"mean_token_accuracy": 0.17136711925268172,
|
|
"num_tokens": 42476126.0,
|
|
"step": 20465
|
|
},
|
|
{
|
|
"entropy": 5.646161890029907,
|
|
"epoch": 1.856857764876633,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.00046563801576747716,
|
|
"loss": 5.3882,
|
|
"mean_token_accuracy": 0.17604161202907562,
|
|
"num_tokens": 42486833.0,
|
|
"step": 20470
|
|
},
|
|
{
|
|
"entropy": 5.702832269668579,
|
|
"epoch": 1.857311320754717,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.00046562082780088733,
|
|
"loss": 5.4117,
|
|
"mean_token_accuracy": 0.1702314518392086,
|
|
"num_tokens": 42496986.0,
|
|
"step": 20475
|
|
},
|
|
{
|
|
"entropy": 5.612835550308228,
|
|
"epoch": 1.8577648766328012,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004656036358922103,
|
|
"loss": 5.3182,
|
|
"mean_token_accuracy": 0.17395937144756318,
|
|
"num_tokens": 42507352.0,
|
|
"step": 20480
|
|
},
|
|
{
|
|
"entropy": 5.618195343017578,
|
|
"epoch": 1.8582184325108853,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004655864400418014,
|
|
"loss": 5.3449,
|
|
"mean_token_accuracy": 0.18069646805524825,
|
|
"num_tokens": 42517655.0,
|
|
"step": 20485
|
|
},
|
|
{
|
|
"entropy": 5.556723022460938,
|
|
"epoch": 1.8586719883889695,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004655692402500163,
|
|
"loss": 5.2488,
|
|
"mean_token_accuracy": 0.18646966218948363,
|
|
"num_tokens": 42527502.0,
|
|
"step": 20490
|
|
},
|
|
{
|
|
"entropy": 5.58910551071167,
|
|
"epoch": 1.8591255442670538,
|
|
"grad_norm": 3.421875,
|
|
"learning_rate": 0.00046555203651721085,
|
|
"loss": 5.3041,
|
|
"mean_token_accuracy": 0.18079341053962708,
|
|
"num_tokens": 42538893.0,
|
|
"step": 20495
|
|
},
|
|
{
|
|
"entropy": 5.441390562057495,
|
|
"epoch": 1.8595791001451378,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004655348288437407,
|
|
"loss": 5.201,
|
|
"mean_token_accuracy": 0.1881030946969986,
|
|
"num_tokens": 42550372.0,
|
|
"step": 20500
|
|
},
|
|
{
|
|
"entropy": 5.613985919952393,
|
|
"epoch": 1.860032656023222,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004655176172299618,
|
|
"loss": 5.409,
|
|
"mean_token_accuracy": 0.17917974442243575,
|
|
"num_tokens": 42560814.0,
|
|
"step": 20505
|
|
},
|
|
{
|
|
"entropy": 5.737222957611084,
|
|
"epoch": 1.8604862119013061,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.00046550040167622986,
|
|
"loss": 5.414,
|
|
"mean_token_accuracy": 0.1705317124724388,
|
|
"num_tokens": 42570993.0,
|
|
"step": 20510
|
|
},
|
|
{
|
|
"entropy": 5.657390785217285,
|
|
"epoch": 1.8609397677793904,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.00046548318218290124,
|
|
"loss": 5.2738,
|
|
"mean_token_accuracy": 0.17954902052879335,
|
|
"num_tokens": 42581357.0,
|
|
"step": 20515
|
|
},
|
|
{
|
|
"entropy": 5.573286533355713,
|
|
"epoch": 1.8613933236574747,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004654659587503318,
|
|
"loss": 5.3818,
|
|
"mean_token_accuracy": 0.1689586341381073,
|
|
"num_tokens": 42591653.0,
|
|
"step": 20520
|
|
},
|
|
{
|
|
"entropy": 5.66587200164795,
|
|
"epoch": 1.861846879535559,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004654487313788778,
|
|
"loss": 5.4407,
|
|
"mean_token_accuracy": 0.1715084880590439,
|
|
"num_tokens": 42602232.0,
|
|
"step": 20525
|
|
},
|
|
{
|
|
"entropy": 5.660058927536011,
|
|
"epoch": 1.862300435413643,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.00046543150006889546,
|
|
"loss": 5.3699,
|
|
"mean_token_accuracy": 0.18198084235191345,
|
|
"num_tokens": 42613283.0,
|
|
"step": 20530
|
|
},
|
|
{
|
|
"entropy": 5.616076850891114,
|
|
"epoch": 1.862753991291727,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004654142648207412,
|
|
"loss": 5.2782,
|
|
"mean_token_accuracy": 0.1811835512518883,
|
|
"num_tokens": 42623594.0,
|
|
"step": 20535
|
|
},
|
|
{
|
|
"entropy": 5.616824007034301,
|
|
"epoch": 1.8632075471698113,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004653970256347715,
|
|
"loss": 5.3395,
|
|
"mean_token_accuracy": 0.176822666823864,
|
|
"num_tokens": 42633587.0,
|
|
"step": 20540
|
|
},
|
|
{
|
|
"entropy": 5.645715951919556,
|
|
"epoch": 1.8636611030478956,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.00046537978251134265,
|
|
"loss": 5.3238,
|
|
"mean_token_accuracy": 0.1751443088054657,
|
|
"num_tokens": 42643426.0,
|
|
"step": 20545
|
|
},
|
|
{
|
|
"entropy": 5.550547647476196,
|
|
"epoch": 1.8641146589259798,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004653625354508115,
|
|
"loss": 5.3237,
|
|
"mean_token_accuracy": 0.18057238757610322,
|
|
"num_tokens": 42653521.0,
|
|
"step": 20550
|
|
},
|
|
{
|
|
"entropy": 5.643773126602173,
|
|
"epoch": 1.8645682148040639,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004653452844535346,
|
|
"loss": 5.3526,
|
|
"mean_token_accuracy": 0.17800124138593673,
|
|
"num_tokens": 42664818.0,
|
|
"step": 20555
|
|
},
|
|
{
|
|
"entropy": 5.676923418045044,
|
|
"epoch": 1.865021770682148,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00046532802951986863,
|
|
"loss": 5.3747,
|
|
"mean_token_accuracy": 0.18144397139549256,
|
|
"num_tokens": 42674738.0,
|
|
"step": 20560
|
|
},
|
|
{
|
|
"entropy": 5.554422187805176,
|
|
"epoch": 1.8654753265602322,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004653107706501705,
|
|
"loss": 5.2839,
|
|
"mean_token_accuracy": 0.19220789074897765,
|
|
"num_tokens": 42685003.0,
|
|
"step": 20565
|
|
},
|
|
{
|
|
"entropy": 5.576437616348267,
|
|
"epoch": 1.8659288824383164,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004652935078447973,
|
|
"loss": 5.3437,
|
|
"mean_token_accuracy": 0.1833068087697029,
|
|
"num_tokens": 42695428.0,
|
|
"step": 20570
|
|
},
|
|
{
|
|
"entropy": 5.6458300113677975,
|
|
"epoch": 1.8663824383164007,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00046527624110410574,
|
|
"loss": 5.3002,
|
|
"mean_token_accuracy": 0.17992193549871444,
|
|
"num_tokens": 42704901.0,
|
|
"step": 20575
|
|
},
|
|
{
|
|
"entropy": 5.6179321765899655,
|
|
"epoch": 1.8668359941944848,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.000465258970428453,
|
|
"loss": 5.3865,
|
|
"mean_token_accuracy": 0.1714644491672516,
|
|
"num_tokens": 42714379.0,
|
|
"step": 20580
|
|
},
|
|
{
|
|
"entropy": 5.694949436187744,
|
|
"epoch": 1.8672895500725688,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.00046524169581819633,
|
|
"loss": 5.4984,
|
|
"mean_token_accuracy": 0.17281682640314103,
|
|
"num_tokens": 42724813.0,
|
|
"step": 20585
|
|
},
|
|
{
|
|
"entropy": 5.604990530014038,
|
|
"epoch": 1.867743105950653,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004652244172736929,
|
|
"loss": 5.332,
|
|
"mean_token_accuracy": 0.17379411607980727,
|
|
"num_tokens": 42736590.0,
|
|
"step": 20590
|
|
},
|
|
{
|
|
"entropy": 5.671986865997314,
|
|
"epoch": 1.8681966618287373,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004652071347953,
|
|
"loss": 5.4122,
|
|
"mean_token_accuracy": 0.1704006239771843,
|
|
"num_tokens": 42746718.0,
|
|
"step": 20595
|
|
},
|
|
{
|
|
"entropy": 5.632694053649902,
|
|
"epoch": 1.8686502177068216,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.00046518984838337513,
|
|
"loss": 5.3097,
|
|
"mean_token_accuracy": 0.170805025100708,
|
|
"num_tokens": 42756484.0,
|
|
"step": 20600
|
|
},
|
|
{
|
|
"entropy": 5.647777032852173,
|
|
"epoch": 1.8691037735849056,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004651725580382757,
|
|
"loss": 5.414,
|
|
"mean_token_accuracy": 0.17438575327396394,
|
|
"num_tokens": 42768512.0,
|
|
"step": 20605
|
|
},
|
|
{
|
|
"entropy": 5.5940991878509525,
|
|
"epoch": 1.8695573294629897,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.00046515526376035934,
|
|
"loss": 5.2697,
|
|
"mean_token_accuracy": 0.18001617044210433,
|
|
"num_tokens": 42779812.0,
|
|
"step": 20610
|
|
},
|
|
{
|
|
"entropy": 5.500312948226929,
|
|
"epoch": 1.870010885341074,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004651379655499837,
|
|
"loss": 5.2707,
|
|
"mean_token_accuracy": 0.1779527708888054,
|
|
"num_tokens": 42791163.0,
|
|
"step": 20615
|
|
},
|
|
{
|
|
"entropy": 5.574215698242187,
|
|
"epoch": 1.8704644412191582,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.00046512066340750636,
|
|
"loss": 5.333,
|
|
"mean_token_accuracy": 0.17868062257766723,
|
|
"num_tokens": 42801810.0,
|
|
"step": 20620
|
|
},
|
|
{
|
|
"entropy": 5.678797769546509,
|
|
"epoch": 1.8709179970972425,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004651033573332853,
|
|
"loss": 5.3651,
|
|
"mean_token_accuracy": 0.17606739401817323,
|
|
"num_tokens": 42813358.0,
|
|
"step": 20625
|
|
},
|
|
{
|
|
"entropy": 5.506175899505616,
|
|
"epoch": 1.8713715529753265,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004650860473276784,
|
|
"loss": 5.1795,
|
|
"mean_token_accuracy": 0.18999922275543213,
|
|
"num_tokens": 42823519.0,
|
|
"step": 20630
|
|
},
|
|
{
|
|
"entropy": 5.5974531173706055,
|
|
"epoch": 1.8718251088534106,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004650687333910436,
|
|
"loss": 5.3344,
|
|
"mean_token_accuracy": 0.1828067734837532,
|
|
"num_tokens": 42833257.0,
|
|
"step": 20635
|
|
},
|
|
{
|
|
"entropy": 5.673833131790161,
|
|
"epoch": 1.8722786647314948,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.00046505141552373897,
|
|
"loss": 5.3957,
|
|
"mean_token_accuracy": 0.17281923890113832,
|
|
"num_tokens": 42843536.0,
|
|
"step": 20640
|
|
},
|
|
{
|
|
"entropy": 5.576288223266602,
|
|
"epoch": 1.8727322206095791,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004650340937261226,
|
|
"loss": 5.3132,
|
|
"mean_token_accuracy": 0.17522123008966445,
|
|
"num_tokens": 42853911.0,
|
|
"step": 20645
|
|
},
|
|
{
|
|
"entropy": 5.6582784175872805,
|
|
"epoch": 1.8731857764876634,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004650167679985528,
|
|
"loss": 5.4288,
|
|
"mean_token_accuracy": 0.16875021159648895,
|
|
"num_tokens": 42864173.0,
|
|
"step": 20650
|
|
},
|
|
{
|
|
"entropy": 5.599008417129516,
|
|
"epoch": 1.8736393323657474,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.0004649994383413877,
|
|
"loss": 5.2834,
|
|
"mean_token_accuracy": 0.17973707020282745,
|
|
"num_tokens": 42873470.0,
|
|
"step": 20655
|
|
},
|
|
{
|
|
"entropy": 5.549261808395386,
|
|
"epoch": 1.8740928882438317,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.00046498210475498595,
|
|
"loss": 5.2616,
|
|
"mean_token_accuracy": 0.18513393104076387,
|
|
"num_tokens": 42882496.0,
|
|
"step": 20660
|
|
},
|
|
{
|
|
"entropy": 5.568225479125976,
|
|
"epoch": 1.8745464441219157,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.00046496476723970574,
|
|
"loss": 5.2701,
|
|
"mean_token_accuracy": 0.1788099706172943,
|
|
"num_tokens": 42893163.0,
|
|
"step": 20665
|
|
},
|
|
{
|
|
"entropy": 5.608275318145752,
|
|
"epoch": 1.875,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004649474257959058,
|
|
"loss": 5.3147,
|
|
"mean_token_accuracy": 0.17859405428171157,
|
|
"num_tokens": 42903406.0,
|
|
"step": 20670
|
|
},
|
|
{
|
|
"entropy": 5.643258953094483,
|
|
"epoch": 1.8754535558780843,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004649300804239447,
|
|
"loss": 5.2964,
|
|
"mean_token_accuracy": 0.1793823078274727,
|
|
"num_tokens": 42913702.0,
|
|
"step": 20675
|
|
},
|
|
{
|
|
"entropy": 5.511851692199707,
|
|
"epoch": 1.8759071117561683,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.00046491273112418105,
|
|
"loss": 5.2648,
|
|
"mean_token_accuracy": 0.18129619508981704,
|
|
"num_tokens": 42923877.0,
|
|
"step": 20680
|
|
},
|
|
{
|
|
"entropy": 5.512067890167236,
|
|
"epoch": 1.8763606676342526,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.00046489537789697386,
|
|
"loss": 5.2969,
|
|
"mean_token_accuracy": 0.18108658492565155,
|
|
"num_tokens": 42934393.0,
|
|
"step": 20685
|
|
},
|
|
{
|
|
"entropy": 5.6547352313995365,
|
|
"epoch": 1.8768142235123366,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.00046487802074268177,
|
|
"loss": 5.3821,
|
|
"mean_token_accuracy": 0.1757466897368431,
|
|
"num_tokens": 42945803.0,
|
|
"step": 20690
|
|
},
|
|
{
|
|
"entropy": 5.603908395767212,
|
|
"epoch": 1.8772677793904209,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.00046486065966166377,
|
|
"loss": 5.295,
|
|
"mean_token_accuracy": 0.18259052336215972,
|
|
"num_tokens": 42955829.0,
|
|
"step": 20695
|
|
},
|
|
{
|
|
"entropy": 5.602593946456909,
|
|
"epoch": 1.8777213352685052,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004648432946542791,
|
|
"loss": 5.3533,
|
|
"mean_token_accuracy": 0.1753669947385788,
|
|
"num_tokens": 42967080.0,
|
|
"step": 20700
|
|
},
|
|
{
|
|
"entropy": 5.576368999481201,
|
|
"epoch": 1.8781748911465894,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.00046482592572088654,
|
|
"loss": 5.3129,
|
|
"mean_token_accuracy": 0.17287670373916625,
|
|
"num_tokens": 42978082.0,
|
|
"step": 20705
|
|
},
|
|
{
|
|
"entropy": 5.617576837539673,
|
|
"epoch": 1.8786284470246735,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00046480855286184565,
|
|
"loss": 5.3757,
|
|
"mean_token_accuracy": 0.17589739263057708,
|
|
"num_tokens": 42988982.0,
|
|
"step": 20710
|
|
},
|
|
{
|
|
"entropy": 5.582280874252319,
|
|
"epoch": 1.8790820029027575,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.00046479117607751535,
|
|
"loss": 5.3266,
|
|
"mean_token_accuracy": 0.16875794529914856,
|
|
"num_tokens": 42998982.0,
|
|
"step": 20715
|
|
},
|
|
{
|
|
"entropy": 5.586578512191773,
|
|
"epoch": 1.8795355587808418,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.00046477379536825534,
|
|
"loss": 5.2728,
|
|
"mean_token_accuracy": 0.1798436388373375,
|
|
"num_tokens": 43009574.0,
|
|
"step": 20720
|
|
},
|
|
{
|
|
"entropy": 5.591803693771363,
|
|
"epoch": 1.879989114658926,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004647564107344247,
|
|
"loss": 5.2816,
|
|
"mean_token_accuracy": 0.17499952912330627,
|
|
"num_tokens": 43019335.0,
|
|
"step": 20725
|
|
},
|
|
{
|
|
"entropy": 5.5097216129302975,
|
|
"epoch": 1.8804426705370103,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.00046473902217638327,
|
|
"loss": 5.3423,
|
|
"mean_token_accuracy": 0.18070039749145508,
|
|
"num_tokens": 43029264.0,
|
|
"step": 20730
|
|
},
|
|
{
|
|
"entropy": 5.580739116668701,
|
|
"epoch": 1.8808962264150944,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.00046472162969449037,
|
|
"loss": 5.3184,
|
|
"mean_token_accuracy": 0.17644916623830795,
|
|
"num_tokens": 43040519.0,
|
|
"step": 20735
|
|
},
|
|
{
|
|
"entropy": 5.640692234039307,
|
|
"epoch": 1.8813497822931784,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.00046470423328910594,
|
|
"loss": 5.3328,
|
|
"mean_token_accuracy": 0.18375409990549088,
|
|
"num_tokens": 43051146.0,
|
|
"step": 20740
|
|
},
|
|
{
|
|
"entropy": 5.644921875,
|
|
"epoch": 1.8818033381712627,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.00046468683296058957,
|
|
"loss": 5.4232,
|
|
"mean_token_accuracy": 0.17581836730241776,
|
|
"num_tokens": 43061339.0,
|
|
"step": 20745
|
|
},
|
|
{
|
|
"entropy": 5.603753852844238,
|
|
"epoch": 1.882256894049347,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00046466942870930126,
|
|
"loss": 5.3514,
|
|
"mean_token_accuracy": 0.18153993934392929,
|
|
"num_tokens": 43072624.0,
|
|
"step": 20750
|
|
},
|
|
{
|
|
"entropy": 5.5939271450042725,
|
|
"epoch": 1.8827104499274312,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004646520205356007,
|
|
"loss": 5.2742,
|
|
"mean_token_accuracy": 0.18300144970417023,
|
|
"num_tokens": 43082120.0,
|
|
"step": 20755
|
|
},
|
|
{
|
|
"entropy": 5.654293584823608,
|
|
"epoch": 1.8831640058055152,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00046463460843984805,
|
|
"loss": 5.4269,
|
|
"mean_token_accuracy": 0.17298397719860076,
|
|
"num_tokens": 43093202.0,
|
|
"step": 20760
|
|
},
|
|
{
|
|
"entropy": 5.754545402526856,
|
|
"epoch": 1.8836175616835993,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004646171924224034,
|
|
"loss": 5.509,
|
|
"mean_token_accuracy": 0.17467231154441834,
|
|
"num_tokens": 43104801.0,
|
|
"step": 20765
|
|
},
|
|
{
|
|
"entropy": 5.650036478042603,
|
|
"epoch": 1.8840711175616836,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00046459977248362687,
|
|
"loss": 5.3191,
|
|
"mean_token_accuracy": 0.18114111870527266,
|
|
"num_tokens": 43114855.0,
|
|
"step": 20770
|
|
},
|
|
{
|
|
"entropy": 5.5707591533660885,
|
|
"epoch": 1.8845246734397678,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004645823486238788,
|
|
"loss": 5.2991,
|
|
"mean_token_accuracy": 0.17109865993261336,
|
|
"num_tokens": 43124759.0,
|
|
"step": 20775
|
|
},
|
|
{
|
|
"entropy": 5.6159440040588375,
|
|
"epoch": 1.884978229317852,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004645649208435193,
|
|
"loss": 5.3145,
|
|
"mean_token_accuracy": 0.18269165456295014,
|
|
"num_tokens": 43135526.0,
|
|
"step": 20780
|
|
},
|
|
{
|
|
"entropy": 5.611689138412475,
|
|
"epoch": 1.8854317851959361,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00046454748914290906,
|
|
"loss": 5.3992,
|
|
"mean_token_accuracy": 0.17349134236574174,
|
|
"num_tokens": 43145605.0,
|
|
"step": 20785
|
|
},
|
|
{
|
|
"entropy": 5.6439375400543215,
|
|
"epoch": 1.8858853410740202,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.00046453005352240835,
|
|
"loss": 5.4576,
|
|
"mean_token_accuracy": 0.16929818391799928,
|
|
"num_tokens": 43156578.0,
|
|
"step": 20790
|
|
},
|
|
{
|
|
"entropy": 5.701980876922607,
|
|
"epoch": 1.8863388969521044,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.000464512613982378,
|
|
"loss": 5.3463,
|
|
"mean_token_accuracy": 0.1824999913573265,
|
|
"num_tokens": 43166870.0,
|
|
"step": 20795
|
|
},
|
|
{
|
|
"entropy": 5.516854095458984,
|
|
"epoch": 1.8867924528301887,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004644951705231783,
|
|
"loss": 5.2757,
|
|
"mean_token_accuracy": 0.1866844490170479,
|
|
"num_tokens": 43176406.0,
|
|
"step": 20800
|
|
},
|
|
{
|
|
"entropy": 5.660739231109619,
|
|
"epoch": 1.887246008708273,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00046447772314517024,
|
|
"loss": 5.4892,
|
|
"mean_token_accuracy": 0.1739048182964325,
|
|
"num_tokens": 43187502.0,
|
|
"step": 20805
|
|
},
|
|
{
|
|
"entropy": 5.594518232345581,
|
|
"epoch": 1.887699564586357,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.00046446027184871464,
|
|
"loss": 5.2478,
|
|
"mean_token_accuracy": 0.17893144488334656,
|
|
"num_tokens": 43197928.0,
|
|
"step": 20810
|
|
},
|
|
{
|
|
"entropy": 5.55735411643982,
|
|
"epoch": 1.888153120464441,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.00046444281663417236,
|
|
"loss": 5.3228,
|
|
"mean_token_accuracy": 0.18455597311258315,
|
|
"num_tokens": 43209083.0,
|
|
"step": 20815
|
|
},
|
|
{
|
|
"entropy": 5.596759510040283,
|
|
"epoch": 1.8886066763425253,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004644253575019043,
|
|
"loss": 5.2974,
|
|
"mean_token_accuracy": 0.17374453991651534,
|
|
"num_tokens": 43219089.0,
|
|
"step": 20820
|
|
},
|
|
{
|
|
"entropy": 5.649628925323486,
|
|
"epoch": 1.8890602322206096,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004644078944522716,
|
|
"loss": 5.3555,
|
|
"mean_token_accuracy": 0.17738717347383498,
|
|
"num_tokens": 43229440.0,
|
|
"step": 20825
|
|
},
|
|
{
|
|
"entropy": 5.625776100158691,
|
|
"epoch": 1.8895137880986939,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004643904274856353,
|
|
"loss": 5.3097,
|
|
"mean_token_accuracy": 0.17851014882326127,
|
|
"num_tokens": 43239995.0,
|
|
"step": 20830
|
|
},
|
|
{
|
|
"entropy": 5.5659499168396,
|
|
"epoch": 1.889967343976778,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.00046437295660235674,
|
|
"loss": 5.2981,
|
|
"mean_token_accuracy": 0.18747041672468184,
|
|
"num_tokens": 43249722.0,
|
|
"step": 20835
|
|
},
|
|
{
|
|
"entropy": 5.528922891616821,
|
|
"epoch": 1.8904208998548622,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004643554818027972,
|
|
"loss": 5.3442,
|
|
"mean_token_accuracy": 0.18040507584810256,
|
|
"num_tokens": 43260029.0,
|
|
"step": 20840
|
|
},
|
|
{
|
|
"entropy": 5.606607961654663,
|
|
"epoch": 1.8908744557329462,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004643380030873181,
|
|
"loss": 5.3083,
|
|
"mean_token_accuracy": 0.17728309333324432,
|
|
"num_tokens": 43270571.0,
|
|
"step": 20845
|
|
},
|
|
{
|
|
"entropy": 5.594561243057251,
|
|
"epoch": 1.8913280116110305,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004643205204562808,
|
|
"loss": 5.2982,
|
|
"mean_token_accuracy": 0.1809353768825531,
|
|
"num_tokens": 43281310.0,
|
|
"step": 20850
|
|
},
|
|
{
|
|
"entropy": 5.608454465866089,
|
|
"epoch": 1.8917815674891147,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00046430303391004687,
|
|
"loss": 5.3234,
|
|
"mean_token_accuracy": 0.1786809206008911,
|
|
"num_tokens": 43292904.0,
|
|
"step": 20855
|
|
},
|
|
{
|
|
"entropy": 5.6189062118530275,
|
|
"epoch": 1.8922351233671988,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004642855434489779,
|
|
"loss": 5.3047,
|
|
"mean_token_accuracy": 0.1750437617301941,
|
|
"num_tokens": 43303745.0,
|
|
"step": 20860
|
|
},
|
|
{
|
|
"entropy": 5.580311107635498,
|
|
"epoch": 1.892688679245283,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.00046426804907343574,
|
|
"loss": 5.3323,
|
|
"mean_token_accuracy": 0.17613555639982223,
|
|
"num_tokens": 43314652.0,
|
|
"step": 20865
|
|
},
|
|
{
|
|
"entropy": 5.5656225204467775,
|
|
"epoch": 1.893142235123367,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.00046425055078378206,
|
|
"loss": 5.203,
|
|
"mean_token_accuracy": 0.18994248062372207,
|
|
"num_tokens": 43324242.0,
|
|
"step": 20870
|
|
},
|
|
{
|
|
"entropy": 5.57157187461853,
|
|
"epoch": 1.8935957910014514,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00046423304858037885,
|
|
"loss": 5.2956,
|
|
"mean_token_accuracy": 0.18590951710939407,
|
|
"num_tokens": 43334054.0,
|
|
"step": 20875
|
|
},
|
|
{
|
|
"entropy": 5.53522481918335,
|
|
"epoch": 1.8940493468795356,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004642155424635878,
|
|
"loss": 5.2115,
|
|
"mean_token_accuracy": 0.19229754954576492,
|
|
"num_tokens": 43343389.0,
|
|
"step": 20880
|
|
},
|
|
{
|
|
"entropy": 5.520655727386474,
|
|
"epoch": 1.89450290275762,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.00046419803243377125,
|
|
"loss": 5.2815,
|
|
"mean_token_accuracy": 0.1867304190993309,
|
|
"num_tokens": 43353892.0,
|
|
"step": 20885
|
|
},
|
|
{
|
|
"entropy": 5.534739255905151,
|
|
"epoch": 1.894956458635704,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00046418051849129115,
|
|
"loss": 5.2903,
|
|
"mean_token_accuracy": 0.1830419510602951,
|
|
"num_tokens": 43363912.0,
|
|
"step": 20890
|
|
},
|
|
{
|
|
"entropy": 5.610625123977661,
|
|
"epoch": 1.895410014513788,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004641630006365097,
|
|
"loss": 5.3761,
|
|
"mean_token_accuracy": 0.17380095422267913,
|
|
"num_tokens": 43374719.0,
|
|
"step": 20895
|
|
},
|
|
{
|
|
"entropy": 5.647830295562744,
|
|
"epoch": 1.8958635703918723,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00046414547886978926,
|
|
"loss": 5.3467,
|
|
"mean_token_accuracy": 0.17791692912578583,
|
|
"num_tokens": 43385549.0,
|
|
"step": 20900
|
|
},
|
|
{
|
|
"entropy": 5.630586624145508,
|
|
"epoch": 1.8963171262699565,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00046412795319149204,
|
|
"loss": 5.3539,
|
|
"mean_token_accuracy": 0.18276966065168382,
|
|
"num_tokens": 43395503.0,
|
|
"step": 20905
|
|
},
|
|
{
|
|
"entropy": 5.5715405464172365,
|
|
"epoch": 1.8967706821480408,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00046411042360198053,
|
|
"loss": 5.3714,
|
|
"mean_token_accuracy": 0.1706641599535942,
|
|
"num_tokens": 43406913.0,
|
|
"step": 20910
|
|
},
|
|
{
|
|
"entropy": 5.606768989562989,
|
|
"epoch": 1.8972242380261248,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004640928901016173,
|
|
"loss": 5.2422,
|
|
"mean_token_accuracy": 0.18101359903812408,
|
|
"num_tokens": 43416459.0,
|
|
"step": 20915
|
|
},
|
|
{
|
|
"entropy": 5.571891975402832,
|
|
"epoch": 1.8976777939042089,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.00046407535269076493,
|
|
"loss": 5.3305,
|
|
"mean_token_accuracy": 0.17816429883241652,
|
|
"num_tokens": 43426280.0,
|
|
"step": 20920
|
|
},
|
|
{
|
|
"entropy": 5.6534583568573,
|
|
"epoch": 1.8981313497822931,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00046405781136978606,
|
|
"loss": 5.3662,
|
|
"mean_token_accuracy": 0.1801248550415039,
|
|
"num_tokens": 43436676.0,
|
|
"step": 20925
|
|
},
|
|
{
|
|
"entropy": 5.695371675491333,
|
|
"epoch": 1.8985849056603774,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.00046404026613904357,
|
|
"loss": 5.3704,
|
|
"mean_token_accuracy": 0.1709836706519127,
|
|
"num_tokens": 43447019.0,
|
|
"step": 20930
|
|
},
|
|
{
|
|
"entropy": 5.62223334312439,
|
|
"epoch": 1.8990384615384617,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004640227169989001,
|
|
"loss": 5.3071,
|
|
"mean_token_accuracy": 0.175585512816906,
|
|
"num_tokens": 43456609.0,
|
|
"step": 20935
|
|
},
|
|
{
|
|
"entropy": 5.5712072372436525,
|
|
"epoch": 1.8994920174165457,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004640051639497187,
|
|
"loss": 5.3783,
|
|
"mean_token_accuracy": 0.17614445686340333,
|
|
"num_tokens": 43467616.0,
|
|
"step": 20940
|
|
},
|
|
{
|
|
"entropy": 5.532619142532349,
|
|
"epoch": 1.8999455732946298,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004639876069918624,
|
|
"loss": 5.3485,
|
|
"mean_token_accuracy": 0.17412057518959045,
|
|
"num_tokens": 43478209.0,
|
|
"step": 20945
|
|
},
|
|
{
|
|
"entropy": 5.592949390411377,
|
|
"epoch": 1.900399129172714,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.00046397004612569416,
|
|
"loss": 5.2223,
|
|
"mean_token_accuracy": 0.17981274127960206,
|
|
"num_tokens": 43487278.0,
|
|
"step": 20950
|
|
},
|
|
{
|
|
"entropy": 5.542866802215576,
|
|
"epoch": 1.9008526850507983,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.00046395248135157715,
|
|
"loss": 5.2738,
|
|
"mean_token_accuracy": 0.18340047001838683,
|
|
"num_tokens": 43497457.0,
|
|
"step": 20955
|
|
},
|
|
{
|
|
"entropy": 5.59867844581604,
|
|
"epoch": 1.9013062409288826,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.00046393491266987484,
|
|
"loss": 5.3742,
|
|
"mean_token_accuracy": 0.17737839072942735,
|
|
"num_tokens": 43507761.0,
|
|
"step": 20960
|
|
},
|
|
{
|
|
"entropy": 5.537381410598755,
|
|
"epoch": 1.9017597968069666,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004639173400809502,
|
|
"loss": 5.2873,
|
|
"mean_token_accuracy": 0.17688101530075073,
|
|
"num_tokens": 43517198.0,
|
|
"step": 20965
|
|
},
|
|
{
|
|
"entropy": 5.637010860443115,
|
|
"epoch": 1.9022133526850507,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004638997635851669,
|
|
"loss": 5.3848,
|
|
"mean_token_accuracy": 0.17337929606437683,
|
|
"num_tokens": 43527429.0,
|
|
"step": 20970
|
|
},
|
|
{
|
|
"entropy": 5.688073682785034,
|
|
"epoch": 1.902666908563135,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00046388218318288844,
|
|
"loss": 5.381,
|
|
"mean_token_accuracy": 0.1783633455634117,
|
|
"num_tokens": 43537867.0,
|
|
"step": 20975
|
|
},
|
|
{
|
|
"entropy": 5.607548522949219,
|
|
"epoch": 1.9031204644412192,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004638645988744782,
|
|
"loss": 5.2997,
|
|
"mean_token_accuracy": 0.17947393357753755,
|
|
"num_tokens": 43547284.0,
|
|
"step": 20980
|
|
},
|
|
{
|
|
"entropy": 5.59152569770813,
|
|
"epoch": 1.9035740203193035,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004638470106603,
|
|
"loss": 5.3561,
|
|
"mean_token_accuracy": 0.17779273837804793,
|
|
"num_tokens": 43557693.0,
|
|
"step": 20985
|
|
},
|
|
{
|
|
"entropy": 5.6111414432525635,
|
|
"epoch": 1.9040275761973875,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004638294185407174,
|
|
"loss": 5.3218,
|
|
"mean_token_accuracy": 0.18465977907180786,
|
|
"num_tokens": 43566909.0,
|
|
"step": 20990
|
|
},
|
|
{
|
|
"entropy": 5.567410039901733,
|
|
"epoch": 1.9044811320754715,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004638118225160944,
|
|
"loss": 5.3807,
|
|
"mean_token_accuracy": 0.18191552460193633,
|
|
"num_tokens": 43576963.0,
|
|
"step": 20995
|
|
},
|
|
{
|
|
"entropy": 5.576124286651611,
|
|
"epoch": 1.9049346879535558,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00046379422258679477,
|
|
"loss": 5.2794,
|
|
"mean_token_accuracy": 0.18046508431434632,
|
|
"num_tokens": 43586649.0,
|
|
"step": 21000
|
|
},
|
|
{
|
|
"epoch": 1.9049346879535558,
|
|
"eval_entropy": 5.44728610925545,
|
|
"eval_loss": 5.387212753295898,
|
|
"eval_mean_token_accuracy": 0.18351733332238584,
|
|
"eval_num_tokens": 43586649.0,
|
|
"eval_runtime": 26.7249,
|
|
"eval_samples_per_second": 1323.108,
|
|
"eval_steps_per_second": 165.389,
|
|
"step": 21000
|
|
},
|
|
{
|
|
"entropy": 5.623881864547729,
|
|
"epoch": 1.90538824383164,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004637766187531825,
|
|
"loss": 5.2838,
|
|
"mean_token_accuracy": 0.18054773807525634,
|
|
"num_tokens": 43596506.0,
|
|
"step": 21005
|
|
},
|
|
{
|
|
"entropy": 5.572930240631104,
|
|
"epoch": 1.9058417997097243,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.00046375901101562163,
|
|
"loss": 5.3488,
|
|
"mean_token_accuracy": 0.1786554589867592,
|
|
"num_tokens": 43607188.0,
|
|
"step": 21010
|
|
},
|
|
{
|
|
"entropy": 5.5709117412567135,
|
|
"epoch": 1.9062953555878084,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004637413993744763,
|
|
"loss": 5.2717,
|
|
"mean_token_accuracy": 0.18902230262756348,
|
|
"num_tokens": 43617465.0,
|
|
"step": 21015
|
|
},
|
|
{
|
|
"entropy": 5.577703809738159,
|
|
"epoch": 1.9067489114658926,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.00046372378383011077,
|
|
"loss": 5.2715,
|
|
"mean_token_accuracy": 0.18411399126052858,
|
|
"num_tokens": 43627692.0,
|
|
"step": 21020
|
|
},
|
|
{
|
|
"entropy": 5.615819787979126,
|
|
"epoch": 1.9072024673439767,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00046370616438288933,
|
|
"loss": 5.3874,
|
|
"mean_token_accuracy": 0.17368493378162383,
|
|
"num_tokens": 43637350.0,
|
|
"step": 21025
|
|
},
|
|
{
|
|
"entropy": 5.584165620803833,
|
|
"epoch": 1.907656023222061,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00046368854103317624,
|
|
"loss": 5.3429,
|
|
"mean_token_accuracy": 0.1774825558066368,
|
|
"num_tokens": 43647092.0,
|
|
"step": 21030
|
|
},
|
|
{
|
|
"entropy": 5.607875394821167,
|
|
"epoch": 1.9081095791001452,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00046367091378133615,
|
|
"loss": 5.3162,
|
|
"mean_token_accuracy": 0.18319867551326752,
|
|
"num_tokens": 43657237.0,
|
|
"step": 21035
|
|
},
|
|
{
|
|
"entropy": 5.575351142883301,
|
|
"epoch": 1.9085631349782293,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004636532826277333,
|
|
"loss": 5.3291,
|
|
"mean_token_accuracy": 0.1801980897784233,
|
|
"num_tokens": 43667966.0,
|
|
"step": 21040
|
|
},
|
|
{
|
|
"entropy": 5.545058965682983,
|
|
"epoch": 1.9090166908563135,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00046363564757273264,
|
|
"loss": 5.3204,
|
|
"mean_token_accuracy": 0.17826954424381256,
|
|
"num_tokens": 43678059.0,
|
|
"step": 21045
|
|
},
|
|
{
|
|
"entropy": 5.602904558181763,
|
|
"epoch": 1.9094702467343976,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.00046361800861669867,
|
|
"loss": 5.3179,
|
|
"mean_token_accuracy": 0.18371757715940476,
|
|
"num_tokens": 43687556.0,
|
|
"step": 21050
|
|
},
|
|
{
|
|
"entropy": 5.620968961715699,
|
|
"epoch": 1.9099238026124818,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00046360036575999623,
|
|
"loss": 5.341,
|
|
"mean_token_accuracy": 0.17613849937915801,
|
|
"num_tokens": 43697791.0,
|
|
"step": 21055
|
|
},
|
|
{
|
|
"entropy": 5.569432735443115,
|
|
"epoch": 1.9103773584905661,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004635827190029902,
|
|
"loss": 5.2414,
|
|
"mean_token_accuracy": 0.17820777595043183,
|
|
"num_tokens": 43707390.0,
|
|
"step": 21060
|
|
},
|
|
{
|
|
"entropy": 5.7060750961303714,
|
|
"epoch": 1.9108309143686504,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004635650683460454,
|
|
"loss": 5.3854,
|
|
"mean_token_accuracy": 0.17718380689620972,
|
|
"num_tokens": 43716842.0,
|
|
"step": 21065
|
|
},
|
|
{
|
|
"entropy": 5.585051345825195,
|
|
"epoch": 1.9112844702467344,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.000463547413789527,
|
|
"loss": 5.3177,
|
|
"mean_token_accuracy": 0.17926882952451706,
|
|
"num_tokens": 43726967.0,
|
|
"step": 21070
|
|
},
|
|
{
|
|
"entropy": 5.605566883087159,
|
|
"epoch": 1.9117380261248185,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00046352975533379997,
|
|
"loss": 5.3197,
|
|
"mean_token_accuracy": 0.18421442359685897,
|
|
"num_tokens": 43737425.0,
|
|
"step": 21075
|
|
},
|
|
{
|
|
"entropy": 5.538187694549561,
|
|
"epoch": 1.9121915820029027,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00046351209297922964,
|
|
"loss": 5.2701,
|
|
"mean_token_accuracy": 0.18415768891572953,
|
|
"num_tokens": 43747395.0,
|
|
"step": 21080
|
|
},
|
|
{
|
|
"entropy": 5.652841854095459,
|
|
"epoch": 1.912645137880987,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.00046349442672618114,
|
|
"loss": 5.3568,
|
|
"mean_token_accuracy": 0.1791637733578682,
|
|
"num_tokens": 43756348.0,
|
|
"step": 21085
|
|
},
|
|
{
|
|
"entropy": 5.5833290100097654,
|
|
"epoch": 1.9130986937590713,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.00046347675657501986,
|
|
"loss": 5.317,
|
|
"mean_token_accuracy": 0.17932792156934738,
|
|
"num_tokens": 43767629.0,
|
|
"step": 21090
|
|
},
|
|
{
|
|
"entropy": 5.5381570816040036,
|
|
"epoch": 1.9135522496371553,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004634590825261113,
|
|
"loss": 5.2263,
|
|
"mean_token_accuracy": 0.18422976434230803,
|
|
"num_tokens": 43777398.0,
|
|
"step": 21095
|
|
},
|
|
{
|
|
"entropy": 5.5936198234558105,
|
|
"epoch": 1.9140058055152394,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.00046344140457982075,
|
|
"loss": 5.3468,
|
|
"mean_token_accuracy": 0.1782150000333786,
|
|
"num_tokens": 43787605.0,
|
|
"step": 21100
|
|
},
|
|
{
|
|
"entropy": 5.5727485656738285,
|
|
"epoch": 1.9144593613933236,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.000463423722736514,
|
|
"loss": 5.3179,
|
|
"mean_token_accuracy": 0.17834594547748567,
|
|
"num_tokens": 43796989.0,
|
|
"step": 21105
|
|
},
|
|
{
|
|
"entropy": 5.570778465270996,
|
|
"epoch": 1.9149129172714079,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004634060369965567,
|
|
"loss": 5.3269,
|
|
"mean_token_accuracy": 0.180311419069767,
|
|
"num_tokens": 43806653.0,
|
|
"step": 21110
|
|
},
|
|
{
|
|
"entropy": 5.582885456085205,
|
|
"epoch": 1.9153664731494922,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00046338834736031446,
|
|
"loss": 5.2433,
|
|
"mean_token_accuracy": 0.18077142387628556,
|
|
"num_tokens": 43817152.0,
|
|
"step": 21115
|
|
},
|
|
{
|
|
"entropy": 5.611099672317505,
|
|
"epoch": 1.9158200290275762,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.00046337065382815324,
|
|
"loss": 5.2722,
|
|
"mean_token_accuracy": 0.17811735719442368,
|
|
"num_tokens": 43827341.0,
|
|
"step": 21120
|
|
},
|
|
{
|
|
"entropy": 5.510884618759155,
|
|
"epoch": 1.9162735849056602,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00046335295640043887,
|
|
"loss": 5.2748,
|
|
"mean_token_accuracy": 0.1880389630794525,
|
|
"num_tokens": 43837195.0,
|
|
"step": 21125
|
|
},
|
|
{
|
|
"entropy": 5.543963670730591,
|
|
"epoch": 1.9167271407837445,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00046333525507753743,
|
|
"loss": 5.2443,
|
|
"mean_token_accuracy": 0.18670160174369813,
|
|
"num_tokens": 43847473.0,
|
|
"step": 21130
|
|
},
|
|
{
|
|
"entropy": 5.530115413665771,
|
|
"epoch": 1.9171806966618288,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004633175498598148,
|
|
"loss": 5.2792,
|
|
"mean_token_accuracy": 0.18352845758199693,
|
|
"num_tokens": 43857590.0,
|
|
"step": 21135
|
|
},
|
|
{
|
|
"entropy": 5.598562908172608,
|
|
"epoch": 1.917634252539913,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00046329984074763733,
|
|
"loss": 5.427,
|
|
"mean_token_accuracy": 0.17722698152065278,
|
|
"num_tokens": 43867085.0,
|
|
"step": 21140
|
|
},
|
|
{
|
|
"entropy": 5.625794982910156,
|
|
"epoch": 1.918087808417997,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004632821277413711,
|
|
"loss": 5.2599,
|
|
"mean_token_accuracy": 0.17892192006111146,
|
|
"num_tokens": 43877153.0,
|
|
"step": 21145
|
|
},
|
|
{
|
|
"entropy": 5.620444917678833,
|
|
"epoch": 1.9185413642960811,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004632644108413825,
|
|
"loss": 5.4037,
|
|
"mean_token_accuracy": 0.1670834541320801,
|
|
"num_tokens": 43887977.0,
|
|
"step": 21150
|
|
},
|
|
{
|
|
"entropy": 5.506011533737182,
|
|
"epoch": 1.9189949201741654,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00046324669004803803,
|
|
"loss": 5.3162,
|
|
"mean_token_accuracy": 0.178001469373703,
|
|
"num_tokens": 43898649.0,
|
|
"step": 21155
|
|
},
|
|
{
|
|
"entropy": 5.714464950561523,
|
|
"epoch": 1.9194484760522497,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000463228965361704,
|
|
"loss": 5.4011,
|
|
"mean_token_accuracy": 0.17516182661056517,
|
|
"num_tokens": 43909369.0,
|
|
"step": 21160
|
|
},
|
|
{
|
|
"entropy": 5.629020738601684,
|
|
"epoch": 1.919902031930334,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004632112367827469,
|
|
"loss": 5.3089,
|
|
"mean_token_accuracy": 0.17783424109220505,
|
|
"num_tokens": 43919941.0,
|
|
"step": 21165
|
|
},
|
|
{
|
|
"entropy": 5.552997732162476,
|
|
"epoch": 1.920355587808418,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004631935043115335,
|
|
"loss": 5.3586,
|
|
"mean_token_accuracy": 0.17745957374572754,
|
|
"num_tokens": 43929710.0,
|
|
"step": 21170
|
|
},
|
|
{
|
|
"entropy": 5.535930395126343,
|
|
"epoch": 1.920809143686502,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00046317576794843056,
|
|
"loss": 5.2897,
|
|
"mean_token_accuracy": 0.17723879665136338,
|
|
"num_tokens": 43939850.0,
|
|
"step": 21175
|
|
},
|
|
{
|
|
"entropy": 5.573296689987183,
|
|
"epoch": 1.9212626995645863,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046315802769380474,
|
|
"loss": 5.2399,
|
|
"mean_token_accuracy": 0.18444838523864746,
|
|
"num_tokens": 43950067.0,
|
|
"step": 21180
|
|
},
|
|
{
|
|
"entropy": 5.5802253723144535,
|
|
"epoch": 1.9217162554426706,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004631402835480229,
|
|
"loss": 5.3135,
|
|
"mean_token_accuracy": 0.18268365710973739,
|
|
"num_tokens": 43960029.0,
|
|
"step": 21185
|
|
},
|
|
{
|
|
"entropy": 5.574585199356079,
|
|
"epoch": 1.9221698113207548,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.00046312253551145213,
|
|
"loss": 5.3189,
|
|
"mean_token_accuracy": 0.17937521636486053,
|
|
"num_tokens": 43971221.0,
|
|
"step": 21190
|
|
},
|
|
{
|
|
"entropy": 5.576491212844848,
|
|
"epoch": 1.9226233671988389,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.00046310478358445935,
|
|
"loss": 5.3423,
|
|
"mean_token_accuracy": 0.17691329419612883,
|
|
"num_tokens": 43981579.0,
|
|
"step": 21195
|
|
},
|
|
{
|
|
"entropy": 5.6511846542358395,
|
|
"epoch": 1.9230769230769231,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004630870277674117,
|
|
"loss": 5.436,
|
|
"mean_token_accuracy": 0.16667191684246063,
|
|
"num_tokens": 43991132.0,
|
|
"step": 21200
|
|
},
|
|
{
|
|
"entropy": 5.5643393993377686,
|
|
"epoch": 1.9235304789550072,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004630692680606764,
|
|
"loss": 5.2417,
|
|
"mean_token_accuracy": 0.18385390788316727,
|
|
"num_tokens": 44001255.0,
|
|
"step": 21205
|
|
},
|
|
{
|
|
"entropy": 5.485634660720825,
|
|
"epoch": 1.9239840348330914,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004630515044646207,
|
|
"loss": 5.1703,
|
|
"mean_token_accuracy": 0.18722822070121764,
|
|
"num_tokens": 44011275.0,
|
|
"step": 21210
|
|
},
|
|
{
|
|
"entropy": 5.542092275619507,
|
|
"epoch": 1.9244375907111757,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.000463033736979612,
|
|
"loss": 5.33,
|
|
"mean_token_accuracy": 0.17806195616722106,
|
|
"num_tokens": 44022524.0,
|
|
"step": 21215
|
|
},
|
|
{
|
|
"entropy": 5.527626276016235,
|
|
"epoch": 1.9248911465892597,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00046301596560601767,
|
|
"loss": 5.2405,
|
|
"mean_token_accuracy": 0.1797426760196686,
|
|
"num_tokens": 44033955.0,
|
|
"step": 21220
|
|
},
|
|
{
|
|
"entropy": 5.583935689926148,
|
|
"epoch": 1.925344702467344,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004629981903442052,
|
|
"loss": 5.3617,
|
|
"mean_token_accuracy": 0.17566695362329482,
|
|
"num_tokens": 44045149.0,
|
|
"step": 21225
|
|
},
|
|
{
|
|
"entropy": 5.633055305480957,
|
|
"epoch": 1.925798258345428,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004629804111945424,
|
|
"loss": 5.333,
|
|
"mean_token_accuracy": 0.1746840000152588,
|
|
"num_tokens": 44055280.0,
|
|
"step": 21230
|
|
},
|
|
{
|
|
"entropy": 5.561671209335327,
|
|
"epoch": 1.9262518142235123,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004629626281573966,
|
|
"loss": 5.2972,
|
|
"mean_token_accuracy": 0.18013984858989715,
|
|
"num_tokens": 44065578.0,
|
|
"step": 21235
|
|
},
|
|
{
|
|
"entropy": 5.51923565864563,
|
|
"epoch": 1.9267053701015966,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004629448412331359,
|
|
"loss": 5.243,
|
|
"mean_token_accuracy": 0.18409126847982407,
|
|
"num_tokens": 44075454.0,
|
|
"step": 21240
|
|
},
|
|
{
|
|
"entropy": 5.554708957672119,
|
|
"epoch": 1.9271589259796809,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004629270504221279,
|
|
"loss": 5.3383,
|
|
"mean_token_accuracy": 0.1778293251991272,
|
|
"num_tokens": 44085680.0,
|
|
"step": 21245
|
|
},
|
|
{
|
|
"entropy": 5.48723783493042,
|
|
"epoch": 1.927612481857765,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004629092557247407,
|
|
"loss": 5.2516,
|
|
"mean_token_accuracy": 0.1857435807585716,
|
|
"num_tokens": 44097177.0,
|
|
"step": 21250
|
|
},
|
|
{
|
|
"entropy": 5.607778167724609,
|
|
"epoch": 1.928066037735849,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004628914571413422,
|
|
"loss": 5.3738,
|
|
"mean_token_accuracy": 0.1770976886153221,
|
|
"num_tokens": 44107251.0,
|
|
"step": 21255
|
|
},
|
|
{
|
|
"entropy": 5.647589063644409,
|
|
"epoch": 1.9285195936139332,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00046287365467230035,
|
|
"loss": 5.3578,
|
|
"mean_token_accuracy": 0.17430492639541625,
|
|
"num_tokens": 44117943.0,
|
|
"step": 21260
|
|
},
|
|
{
|
|
"entropy": 5.64258975982666,
|
|
"epoch": 1.9289731494920175,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00046285584831798354,
|
|
"loss": 5.381,
|
|
"mean_token_accuracy": 0.1804455503821373,
|
|
"num_tokens": 44128608.0,
|
|
"step": 21265
|
|
},
|
|
{
|
|
"entropy": 5.581456327438355,
|
|
"epoch": 1.9294267053701017,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00046283803807875996,
|
|
"loss": 5.3173,
|
|
"mean_token_accuracy": 0.18316273987293244,
|
|
"num_tokens": 44138809.0,
|
|
"step": 21270
|
|
},
|
|
{
|
|
"entropy": 5.584235095977784,
|
|
"epoch": 1.9298802612481858,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00046282022395499785,
|
|
"loss": 5.3144,
|
|
"mean_token_accuracy": 0.18126629143953324,
|
|
"num_tokens": 44148532.0,
|
|
"step": 21275
|
|
},
|
|
{
|
|
"entropy": 5.608316421508789,
|
|
"epoch": 1.9303338171262698,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004628024059470656,
|
|
"loss": 5.3369,
|
|
"mean_token_accuracy": 0.17683209329843522,
|
|
"num_tokens": 44158628.0,
|
|
"step": 21280
|
|
},
|
|
{
|
|
"entropy": 5.554081535339355,
|
|
"epoch": 1.930787373004354,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004627845840553318,
|
|
"loss": 5.2102,
|
|
"mean_token_accuracy": 0.18880697786808015,
|
|
"num_tokens": 44168574.0,
|
|
"step": 21285
|
|
},
|
|
{
|
|
"entropy": 5.630626773834228,
|
|
"epoch": 1.9312409288824384,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00046276675828016493,
|
|
"loss": 5.3969,
|
|
"mean_token_accuracy": 0.17696617543697357,
|
|
"num_tokens": 44180207.0,
|
|
"step": 21290
|
|
},
|
|
{
|
|
"entropy": 5.622194147109985,
|
|
"epoch": 1.9316944847605226,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004627489286219336,
|
|
"loss": 5.4173,
|
|
"mean_token_accuracy": 0.17504074275493622,
|
|
"num_tokens": 44190473.0,
|
|
"step": 21295
|
|
},
|
|
{
|
|
"entropy": 5.669592618942261,
|
|
"epoch": 1.9321480406386067,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004627310950810066,
|
|
"loss": 5.374,
|
|
"mean_token_accuracy": 0.18231589198112488,
|
|
"num_tokens": 44201150.0,
|
|
"step": 21300
|
|
},
|
|
{
|
|
"entropy": 5.580922985076905,
|
|
"epoch": 1.9326015965166907,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004627132576577528,
|
|
"loss": 5.3146,
|
|
"mean_token_accuracy": 0.17355852127075194,
|
|
"num_tokens": 44211272.0,
|
|
"step": 21305
|
|
},
|
|
{
|
|
"entropy": 5.590257978439331,
|
|
"epoch": 1.933055152394775,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.000462695416352541,
|
|
"loss": 5.3953,
|
|
"mean_token_accuracy": 0.17513257265090942,
|
|
"num_tokens": 44223556.0,
|
|
"step": 21310
|
|
},
|
|
{
|
|
"entropy": 5.66590051651001,
|
|
"epoch": 1.9335087082728593,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.00046267757116574,
|
|
"loss": 5.3037,
|
|
"mean_token_accuracy": 0.1834760159254074,
|
|
"num_tokens": 44233911.0,
|
|
"step": 21315
|
|
},
|
|
{
|
|
"entropy": 5.688560438156128,
|
|
"epoch": 1.9339622641509435,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004626597220977191,
|
|
"loss": 5.3729,
|
|
"mean_token_accuracy": 0.18070325553417205,
|
|
"num_tokens": 44244108.0,
|
|
"step": 21320
|
|
},
|
|
{
|
|
"entropy": 5.48749794960022,
|
|
"epoch": 1.9344158200290276,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00046264186914884737,
|
|
"loss": 5.2577,
|
|
"mean_token_accuracy": 0.18209335207939148,
|
|
"num_tokens": 44253604.0,
|
|
"step": 21325
|
|
},
|
|
{
|
|
"entropy": 5.537864828109742,
|
|
"epoch": 1.9348693759071116,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00046262401231949386,
|
|
"loss": 5.3632,
|
|
"mean_token_accuracy": 0.1740374505519867,
|
|
"num_tokens": 44263573.0,
|
|
"step": 21330
|
|
},
|
|
{
|
|
"entropy": 5.64324369430542,
|
|
"epoch": 1.9353229317851959,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.00046260615161002803,
|
|
"loss": 5.3084,
|
|
"mean_token_accuracy": 0.1787741854786873,
|
|
"num_tokens": 44274071.0,
|
|
"step": 21335
|
|
},
|
|
{
|
|
"entropy": 5.672721815109253,
|
|
"epoch": 1.9357764876632801,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004625882870208192,
|
|
"loss": 5.3378,
|
|
"mean_token_accuracy": 0.17635011672973633,
|
|
"num_tokens": 44283997.0,
|
|
"step": 21340
|
|
},
|
|
{
|
|
"entropy": 5.569957113265991,
|
|
"epoch": 1.9362300435413644,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00046257041855223674,
|
|
"loss": 5.3124,
|
|
"mean_token_accuracy": 0.17735303193330765,
|
|
"num_tokens": 44295024.0,
|
|
"step": 21345
|
|
},
|
|
{
|
|
"entropy": 5.550043392181396,
|
|
"epoch": 1.9366835994194485,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00046255254620465033,
|
|
"loss": 5.2529,
|
|
"mean_token_accuracy": 0.18249621540307998,
|
|
"num_tokens": 44305476.0,
|
|
"step": 21350
|
|
},
|
|
{
|
|
"entropy": 5.527661514282227,
|
|
"epoch": 1.9371371552975325,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00046253466997842936,
|
|
"loss": 5.2508,
|
|
"mean_token_accuracy": 0.18053626865148545,
|
|
"num_tokens": 44316101.0,
|
|
"step": 21355
|
|
},
|
|
{
|
|
"entropy": 5.488785696029663,
|
|
"epoch": 1.9375907111756168,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004625167898739436,
|
|
"loss": 5.1793,
|
|
"mean_token_accuracy": 0.18670917302370071,
|
|
"num_tokens": 44325058.0,
|
|
"step": 21360
|
|
},
|
|
{
|
|
"entropy": 5.72654767036438,
|
|
"epoch": 1.938044267053701,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.000462498905891563,
|
|
"loss": 5.5162,
|
|
"mean_token_accuracy": 0.16438383460044861,
|
|
"num_tokens": 44336585.0,
|
|
"step": 21365
|
|
},
|
|
{
|
|
"entropy": 5.6125775337219235,
|
|
"epoch": 1.9384978229317853,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004624810180316571,
|
|
"loss": 5.3012,
|
|
"mean_token_accuracy": 0.183238223195076,
|
|
"num_tokens": 44346911.0,
|
|
"step": 21370
|
|
},
|
|
{
|
|
"entropy": 5.536642551422119,
|
|
"epoch": 1.9389513788098693,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00046246312629459596,
|
|
"loss": 5.2861,
|
|
"mean_token_accuracy": 0.17887787222862245,
|
|
"num_tokens": 44358040.0,
|
|
"step": 21375
|
|
},
|
|
{
|
|
"entropy": 5.597347784042358,
|
|
"epoch": 1.9394049346879536,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004624452306807497,
|
|
"loss": 5.3133,
|
|
"mean_token_accuracy": 0.181216099858284,
|
|
"num_tokens": 44368781.0,
|
|
"step": 21380
|
|
},
|
|
{
|
|
"entropy": 5.493802547454834,
|
|
"epoch": 1.9398584905660377,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004624273311904882,
|
|
"loss": 5.2493,
|
|
"mean_token_accuracy": 0.1806768298149109,
|
|
"num_tokens": 44378809.0,
|
|
"step": 21385
|
|
},
|
|
{
|
|
"entropy": 5.611697435379028,
|
|
"epoch": 1.940312046444122,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00046240942782418184,
|
|
"loss": 5.406,
|
|
"mean_token_accuracy": 0.17294420450925826,
|
|
"num_tokens": 44388517.0,
|
|
"step": 21390
|
|
},
|
|
{
|
|
"entropy": 5.67592601776123,
|
|
"epoch": 1.9407656023222062,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004623915205822007,
|
|
"loss": 5.3571,
|
|
"mean_token_accuracy": 0.17639275640249252,
|
|
"num_tokens": 44399364.0,
|
|
"step": 21395
|
|
},
|
|
{
|
|
"entropy": 5.5691169738769535,
|
|
"epoch": 1.9412191582002902,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.00046237360946491514,
|
|
"loss": 5.2566,
|
|
"mean_token_accuracy": 0.1748315140604973,
|
|
"num_tokens": 44409506.0,
|
|
"step": 21400
|
|
},
|
|
{
|
|
"entropy": 5.593041849136353,
|
|
"epoch": 1.9416727140783745,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004623556944726956,
|
|
"loss": 5.3149,
|
|
"mean_token_accuracy": 0.17703113406896592,
|
|
"num_tokens": 44419446.0,
|
|
"step": 21405
|
|
},
|
|
{
|
|
"entropy": 5.540841436386108,
|
|
"epoch": 1.9421262699564585,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.00046233777560591256,
|
|
"loss": 5.3043,
|
|
"mean_token_accuracy": 0.18094540983438492,
|
|
"num_tokens": 44429560.0,
|
|
"step": 21410
|
|
},
|
|
{
|
|
"entropy": 5.565748453140259,
|
|
"epoch": 1.9425798258345428,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00046231985286493654,
|
|
"loss": 5.2897,
|
|
"mean_token_accuracy": 0.17795810848474503,
|
|
"num_tokens": 44439640.0,
|
|
"step": 21415
|
|
},
|
|
{
|
|
"entropy": 5.637230348587036,
|
|
"epoch": 1.943033381712627,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.00046230192625013836,
|
|
"loss": 5.3228,
|
|
"mean_token_accuracy": 0.17501559406518935,
|
|
"num_tokens": 44450480.0,
|
|
"step": 21420
|
|
},
|
|
{
|
|
"entropy": 5.4903092861175535,
|
|
"epoch": 1.9434869375907113,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.00046228399576188844,
|
|
"loss": 5.1834,
|
|
"mean_token_accuracy": 0.18323935121297835,
|
|
"num_tokens": 44460633.0,
|
|
"step": 21425
|
|
},
|
|
{
|
|
"entropy": 5.53410325050354,
|
|
"epoch": 1.9439404934687954,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00046226606140055784,
|
|
"loss": 5.2814,
|
|
"mean_token_accuracy": 0.1819428324699402,
|
|
"num_tokens": 44470917.0,
|
|
"step": 21430
|
|
},
|
|
{
|
|
"entropy": 5.582603788375854,
|
|
"epoch": 1.9443940493468794,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00046224812316651736,
|
|
"loss": 5.3339,
|
|
"mean_token_accuracy": 0.1758107900619507,
|
|
"num_tokens": 44482538.0,
|
|
"step": 21435
|
|
},
|
|
{
|
|
"entropy": 5.645057153701782,
|
|
"epoch": 1.9448476052249637,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.000462230181060138,
|
|
"loss": 5.3361,
|
|
"mean_token_accuracy": 0.17961706817150117,
|
|
"num_tokens": 44493518.0,
|
|
"step": 21440
|
|
},
|
|
{
|
|
"entropy": 5.542262268066406,
|
|
"epoch": 1.945301161103048,
|
|
"grad_norm": 2.84375,
|
|
"learning_rate": 0.00046221223508179077,
|
|
"loss": 5.335,
|
|
"mean_token_accuracy": 0.1843020960688591,
|
|
"num_tokens": 44503685.0,
|
|
"step": 21445
|
|
},
|
|
{
|
|
"entropy": 5.50782961845398,
|
|
"epoch": 1.9457547169811322,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00046219428523184685,
|
|
"loss": 5.2699,
|
|
"mean_token_accuracy": 0.18328675478696824,
|
|
"num_tokens": 44514015.0,
|
|
"step": 21450
|
|
},
|
|
{
|
|
"entropy": 5.561082124710083,
|
|
"epoch": 1.9462082728592163,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004621763315106774,
|
|
"loss": 5.3252,
|
|
"mean_token_accuracy": 0.17855403423309327,
|
|
"num_tokens": 44525187.0,
|
|
"step": 21455
|
|
},
|
|
{
|
|
"entropy": 5.530112934112549,
|
|
"epoch": 1.9466618287373003,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00046215837391865364,
|
|
"loss": 5.2772,
|
|
"mean_token_accuracy": 0.182682828605175,
|
|
"num_tokens": 44535964.0,
|
|
"step": 21460
|
|
},
|
|
{
|
|
"entropy": 5.537807369232178,
|
|
"epoch": 1.9471153846153846,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00046214041245614713,
|
|
"loss": 5.2648,
|
|
"mean_token_accuracy": 0.1769727885723114,
|
|
"num_tokens": 44546985.0,
|
|
"step": 21465
|
|
},
|
|
{
|
|
"entropy": 5.58845624923706,
|
|
"epoch": 1.9475689404934688,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004621224471235291,
|
|
"loss": 5.323,
|
|
"mean_token_accuracy": 0.1790289580821991,
|
|
"num_tokens": 44556888.0,
|
|
"step": 21470
|
|
},
|
|
{
|
|
"entropy": 5.530765676498413,
|
|
"epoch": 1.9480224963715531,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.00046210447792117114,
|
|
"loss": 5.2733,
|
|
"mean_token_accuracy": 0.17880664616823197,
|
|
"num_tokens": 44566857.0,
|
|
"step": 21475
|
|
},
|
|
{
|
|
"entropy": 5.616748809814453,
|
|
"epoch": 1.9484760522496372,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000462086504849445,
|
|
"loss": 5.3471,
|
|
"mean_token_accuracy": 0.1750559166073799,
|
|
"num_tokens": 44578152.0,
|
|
"step": 21480
|
|
},
|
|
{
|
|
"entropy": 5.618349027633667,
|
|
"epoch": 1.9489296081277212,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004620685279087222,
|
|
"loss": 5.2984,
|
|
"mean_token_accuracy": 0.18475719094276427,
|
|
"num_tokens": 44588814.0,
|
|
"step": 21485
|
|
},
|
|
{
|
|
"entropy": 5.5475365161895756,
|
|
"epoch": 1.9493831640058055,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00046205054709937474,
|
|
"loss": 5.2597,
|
|
"mean_token_accuracy": 0.17906009703874587,
|
|
"num_tokens": 44599366.0,
|
|
"step": 21490
|
|
},
|
|
{
|
|
"entropy": 5.613944959640503,
|
|
"epoch": 1.9498367198838897,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004620325624217741,
|
|
"loss": 5.3889,
|
|
"mean_token_accuracy": 0.17378757745027543,
|
|
"num_tokens": 44609962.0,
|
|
"step": 21495
|
|
},
|
|
{
|
|
"entropy": 5.651360368728637,
|
|
"epoch": 1.950290275761974,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004620145738762925,
|
|
"loss": 5.3452,
|
|
"mean_token_accuracy": 0.18051276355981827,
|
|
"num_tokens": 44619917.0,
|
|
"step": 21500
|
|
},
|
|
{
|
|
"entropy": 5.544938611984253,
|
|
"epoch": 1.950743831640058,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004619965814633019,
|
|
"loss": 5.299,
|
|
"mean_token_accuracy": 0.18267780989408494,
|
|
"num_tokens": 44629723.0,
|
|
"step": 21505
|
|
},
|
|
{
|
|
"entropy": 5.537790203094483,
|
|
"epoch": 1.951197387518142,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004619785851831742,
|
|
"loss": 5.3454,
|
|
"mean_token_accuracy": 0.1776015043258667,
|
|
"num_tokens": 44641011.0,
|
|
"step": 21510
|
|
},
|
|
{
|
|
"entropy": 5.630759048461914,
|
|
"epoch": 1.9516509433962264,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046196058503628176,
|
|
"loss": 5.2604,
|
|
"mean_token_accuracy": 0.18178843706846237,
|
|
"num_tokens": 44651154.0,
|
|
"step": 21515
|
|
},
|
|
{
|
|
"entropy": 5.614014101028443,
|
|
"epoch": 1.9521044992743106,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004619425810229968,
|
|
"loss": 5.3725,
|
|
"mean_token_accuracy": 0.1765950858592987,
|
|
"num_tokens": 44661672.0,
|
|
"step": 21520
|
|
},
|
|
{
|
|
"entropy": 5.520532274246216,
|
|
"epoch": 1.952558055152395,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004619245731436917,
|
|
"loss": 5.2452,
|
|
"mean_token_accuracy": 0.18721432834863663,
|
|
"num_tokens": 44671449.0,
|
|
"step": 21525
|
|
},
|
|
{
|
|
"entropy": 5.557680273056031,
|
|
"epoch": 1.953011611030479,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00046190656139873863,
|
|
"loss": 5.2613,
|
|
"mean_token_accuracy": 0.18542284071445464,
|
|
"num_tokens": 44681977.0,
|
|
"step": 21530
|
|
},
|
|
{
|
|
"entropy": 5.507194566726684,
|
|
"epoch": 1.953465166908563,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004618885457885103,
|
|
"loss": 5.2692,
|
|
"mean_token_accuracy": 0.18048060387372972,
|
|
"num_tokens": 44691946.0,
|
|
"step": 21535
|
|
},
|
|
{
|
|
"entropy": 5.586454153060913,
|
|
"epoch": 1.9539187227866472,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004618705263133793,
|
|
"loss": 5.3278,
|
|
"mean_token_accuracy": 0.17601757496595383,
|
|
"num_tokens": 44702012.0,
|
|
"step": 21540
|
|
},
|
|
{
|
|
"entropy": 5.571926879882812,
|
|
"epoch": 1.9543722786647315,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004618525029737182,
|
|
"loss": 5.2365,
|
|
"mean_token_accuracy": 0.18310380280017852,
|
|
"num_tokens": 44711605.0,
|
|
"step": 21545
|
|
},
|
|
{
|
|
"entropy": 5.649220132827759,
|
|
"epoch": 1.9548258345428158,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.00046183447576989966,
|
|
"loss": 5.3754,
|
|
"mean_token_accuracy": 0.18211107105016708,
|
|
"num_tokens": 44722765.0,
|
|
"step": 21550
|
|
},
|
|
{
|
|
"entropy": 5.633371067047119,
|
|
"epoch": 1.9552793904208998,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.00046181644470229656,
|
|
"loss": 5.296,
|
|
"mean_token_accuracy": 0.18027015328407286,
|
|
"num_tokens": 44732082.0,
|
|
"step": 21555
|
|
},
|
|
{
|
|
"entropy": 5.486901521682739,
|
|
"epoch": 1.955732946298984,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004617984097712817,
|
|
"loss": 5.2195,
|
|
"mean_token_accuracy": 0.18883929699659346,
|
|
"num_tokens": 44742054.0,
|
|
"step": 21560
|
|
},
|
|
{
|
|
"entropy": 5.531009292602539,
|
|
"epoch": 1.9561865021770681,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004617803709772282,
|
|
"loss": 5.3376,
|
|
"mean_token_accuracy": 0.18170125186443328,
|
|
"num_tokens": 44752954.0,
|
|
"step": 21565
|
|
},
|
|
{
|
|
"entropy": 5.6339640617370605,
|
|
"epoch": 1.9566400580551524,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004617623283205091,
|
|
"loss": 5.3828,
|
|
"mean_token_accuracy": 0.17390358448028564,
|
|
"num_tokens": 44764277.0,
|
|
"step": 21570
|
|
},
|
|
{
|
|
"entropy": 5.625865411758423,
|
|
"epoch": 1.9570936139332367,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00046174428180149733,
|
|
"loss": 5.3614,
|
|
"mean_token_accuracy": 0.17908811271190644,
|
|
"num_tokens": 44775429.0,
|
|
"step": 21575
|
|
},
|
|
{
|
|
"entropy": 5.611550998687744,
|
|
"epoch": 1.9575471698113207,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004617262314205663,
|
|
"loss": 5.3562,
|
|
"mean_token_accuracy": 0.17302486151456833,
|
|
"num_tokens": 44786390.0,
|
|
"step": 21580
|
|
},
|
|
{
|
|
"entropy": 5.607249784469604,
|
|
"epoch": 1.958000725689405,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004617081771780893,
|
|
"loss": 5.2914,
|
|
"mean_token_accuracy": 0.18453651219606398,
|
|
"num_tokens": 44796473.0,
|
|
"step": 21585
|
|
},
|
|
{
|
|
"entropy": 5.524594402313232,
|
|
"epoch": 1.958454281567489,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00046169011907443944,
|
|
"loss": 5.2622,
|
|
"mean_token_accuracy": 0.18296688199043273,
|
|
"num_tokens": 44806379.0,
|
|
"step": 21590
|
|
},
|
|
{
|
|
"entropy": 5.549508285522461,
|
|
"epoch": 1.9589078374455733,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004616720571099904,
|
|
"loss": 5.3421,
|
|
"mean_token_accuracy": 0.17736609131097794,
|
|
"num_tokens": 44817659.0,
|
|
"step": 21595
|
|
},
|
|
{
|
|
"entropy": 5.614672565460205,
|
|
"epoch": 1.9593613933236576,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004616539912851157,
|
|
"loss": 5.2487,
|
|
"mean_token_accuracy": 0.17944755107164384,
|
|
"num_tokens": 44827073.0,
|
|
"step": 21600
|
|
},
|
|
{
|
|
"entropy": 5.558100700378418,
|
|
"epoch": 1.9598149492017418,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00046163592160018886,
|
|
"loss": 5.2605,
|
|
"mean_token_accuracy": 0.18146224617958068,
|
|
"num_tokens": 44837019.0,
|
|
"step": 21605
|
|
},
|
|
{
|
|
"entropy": 5.500057220458984,
|
|
"epoch": 1.9602685050798259,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004616178480555836,
|
|
"loss": 5.2716,
|
|
"mean_token_accuracy": 0.18179352730512618,
|
|
"num_tokens": 44846670.0,
|
|
"step": 21610
|
|
},
|
|
{
|
|
"entropy": 5.471788835525513,
|
|
"epoch": 1.96072206095791,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004615997706516737,
|
|
"loss": 5.2205,
|
|
"mean_token_accuracy": 0.1821857586503029,
|
|
"num_tokens": 44857016.0,
|
|
"step": 21615
|
|
},
|
|
{
|
|
"entropy": 5.65317440032959,
|
|
"epoch": 1.9611756168359942,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.000461581689388833,
|
|
"loss": 5.395,
|
|
"mean_token_accuracy": 0.16817007809877396,
|
|
"num_tokens": 44868180.0,
|
|
"step": 21620
|
|
},
|
|
{
|
|
"entropy": 5.570417404174805,
|
|
"epoch": 1.9616291727140784,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00046156360426743536,
|
|
"loss": 5.2241,
|
|
"mean_token_accuracy": 0.18666786700487137,
|
|
"num_tokens": 44877864.0,
|
|
"step": 21625
|
|
},
|
|
{
|
|
"entropy": 5.502156400680542,
|
|
"epoch": 1.9620827285921627,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004615455152878549,
|
|
"loss": 5.2966,
|
|
"mean_token_accuracy": 0.1886972427368164,
|
|
"num_tokens": 44887737.0,
|
|
"step": 21630
|
|
},
|
|
{
|
|
"entropy": 5.468607425689697,
|
|
"epoch": 1.9625362844702468,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004615274224504657,
|
|
"loss": 5.2929,
|
|
"mean_token_accuracy": 0.175810706615448,
|
|
"num_tokens": 44898669.0,
|
|
"step": 21635
|
|
},
|
|
{
|
|
"entropy": 5.615883207321167,
|
|
"epoch": 1.9629898403483308,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00046150932575564173,
|
|
"loss": 5.3841,
|
|
"mean_token_accuracy": 0.1780763104557991,
|
|
"num_tokens": 44909074.0,
|
|
"step": 21640
|
|
},
|
|
{
|
|
"entropy": 5.60457329750061,
|
|
"epoch": 1.963443396226415,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00046149122520375746,
|
|
"loss": 5.2499,
|
|
"mean_token_accuracy": 0.18124958723783494,
|
|
"num_tokens": 44919468.0,
|
|
"step": 21645
|
|
},
|
|
{
|
|
"entropy": 5.618048477172851,
|
|
"epoch": 1.9638969521044993,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004614731207951871,
|
|
"loss": 5.365,
|
|
"mean_token_accuracy": 0.17308651506900788,
|
|
"num_tokens": 44930470.0,
|
|
"step": 21650
|
|
},
|
|
{
|
|
"entropy": 5.58341498374939,
|
|
"epoch": 1.9643505079825836,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004614550125303051,
|
|
"loss": 5.3446,
|
|
"mean_token_accuracy": 0.18149602115154267,
|
|
"num_tokens": 44940611.0,
|
|
"step": 21655
|
|
},
|
|
{
|
|
"entropy": 5.593374586105346,
|
|
"epoch": 1.9648040638606676,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004614369004094859,
|
|
"loss": 5.3411,
|
|
"mean_token_accuracy": 0.18154329657554627,
|
|
"num_tokens": 44950985.0,
|
|
"step": 21660
|
|
},
|
|
{
|
|
"entropy": 5.579255056381226,
|
|
"epoch": 1.9652576197387517,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.00046141878443310415,
|
|
"loss": 5.3504,
|
|
"mean_token_accuracy": 0.17677582949399948,
|
|
"num_tokens": 44961858.0,
|
|
"step": 21665
|
|
},
|
|
{
|
|
"entropy": 5.625710439682007,
|
|
"epoch": 1.965711175616836,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.00046140066460153444,
|
|
"loss": 5.3102,
|
|
"mean_token_accuracy": 0.18018480986356736,
|
|
"num_tokens": 44972048.0,
|
|
"step": 21670
|
|
},
|
|
{
|
|
"entropy": 5.5971826076507565,
|
|
"epoch": 1.9661647314949202,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00046138254091515136,
|
|
"loss": 5.2493,
|
|
"mean_token_accuracy": 0.18468988239765166,
|
|
"num_tokens": 44981835.0,
|
|
"step": 21675
|
|
},
|
|
{
|
|
"entropy": 5.5312541961669925,
|
|
"epoch": 1.9666182873730045,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.00046136441337432996,
|
|
"loss": 5.2102,
|
|
"mean_token_accuracy": 0.19076460152864455,
|
|
"num_tokens": 44992108.0,
|
|
"step": 21680
|
|
},
|
|
{
|
|
"entropy": 5.659492874145508,
|
|
"epoch": 1.9670718432510885,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00046134628197944496,
|
|
"loss": 5.3727,
|
|
"mean_token_accuracy": 0.173721943795681,
|
|
"num_tokens": 45002105.0,
|
|
"step": 21685
|
|
},
|
|
{
|
|
"entropy": 5.5487264633178714,
|
|
"epoch": 1.9675253991291726,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00046132814673087143,
|
|
"loss": 5.3312,
|
|
"mean_token_accuracy": 0.17222759127616882,
|
|
"num_tokens": 45013934.0,
|
|
"step": 21690
|
|
},
|
|
{
|
|
"entropy": 5.535455322265625,
|
|
"epoch": 1.9679789550072568,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004613100076289842,
|
|
"loss": 5.291,
|
|
"mean_token_accuracy": 0.1785733237862587,
|
|
"num_tokens": 45023851.0,
|
|
"step": 21695
|
|
},
|
|
{
|
|
"entropy": 5.51913800239563,
|
|
"epoch": 1.968432510885341,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004612918646741586,
|
|
"loss": 5.2205,
|
|
"mean_token_accuracy": 0.18113995641469954,
|
|
"num_tokens": 45034140.0,
|
|
"step": 21700
|
|
},
|
|
{
|
|
"entropy": 5.52028079032898,
|
|
"epoch": 1.9688860667634254,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004612737178667698,
|
|
"loss": 5.2714,
|
|
"mean_token_accuracy": 0.1770318940281868,
|
|
"num_tokens": 45044452.0,
|
|
"step": 21705
|
|
},
|
|
{
|
|
"entropy": 5.557014656066895,
|
|
"epoch": 1.9693396226415094,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00046125556720719304,
|
|
"loss": 5.2993,
|
|
"mean_token_accuracy": 0.17751598358154297,
|
|
"num_tokens": 45053845.0,
|
|
"step": 21710
|
|
},
|
|
{
|
|
"entropy": 5.625747919082642,
|
|
"epoch": 1.9697931785195935,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004612374126958037,
|
|
"loss": 5.2393,
|
|
"mean_token_accuracy": 0.18654453307390212,
|
|
"num_tokens": 45063973.0,
|
|
"step": 21715
|
|
},
|
|
{
|
|
"entropy": 5.670189285278321,
|
|
"epoch": 1.9702467343976777,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004612192543329771,
|
|
"loss": 5.4137,
|
|
"mean_token_accuracy": 0.1771538093686104,
|
|
"num_tokens": 45074879.0,
|
|
"step": 21720
|
|
},
|
|
{
|
|
"entropy": 5.5301131248474125,
|
|
"epoch": 1.970700290275762,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.000461201092119089,
|
|
"loss": 5.2059,
|
|
"mean_token_accuracy": 0.18522760570049285,
|
|
"num_tokens": 45085161.0,
|
|
"step": 21725
|
|
},
|
|
{
|
|
"entropy": 5.580789852142334,
|
|
"epoch": 1.9711538461538463,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004611829260545148,
|
|
"loss": 5.37,
|
|
"mean_token_accuracy": 0.1761306568980217,
|
|
"num_tokens": 45095862.0,
|
|
"step": 21730
|
|
},
|
|
{
|
|
"entropy": 5.6204548358917235,
|
|
"epoch": 1.9716074020319303,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.00046116475613963026,
|
|
"loss": 5.2944,
|
|
"mean_token_accuracy": 0.17831196188926696,
|
|
"num_tokens": 45106396.0,
|
|
"step": 21735
|
|
},
|
|
{
|
|
"entropy": 5.613033771514893,
|
|
"epoch": 1.9720609579100146,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.00046114658237481114,
|
|
"loss": 5.2244,
|
|
"mean_token_accuracy": 0.1873910829424858,
|
|
"num_tokens": 45117178.0,
|
|
"step": 21740
|
|
},
|
|
{
|
|
"entropy": 5.460865831375122,
|
|
"epoch": 1.9725145137880986,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004611284047604332,
|
|
"loss": 5.2087,
|
|
"mean_token_accuracy": 0.1887686222791672,
|
|
"num_tokens": 45126571.0,
|
|
"step": 21745
|
|
},
|
|
{
|
|
"entropy": 5.602301931381225,
|
|
"epoch": 1.9729680696661829,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.00046111022329687246,
|
|
"loss": 5.3564,
|
|
"mean_token_accuracy": 0.18028296530246735,
|
|
"num_tokens": 45137247.0,
|
|
"step": 21750
|
|
},
|
|
{
|
|
"entropy": 5.652207851409912,
|
|
"epoch": 1.9734216255442671,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00046109203798450483,
|
|
"loss": 5.3105,
|
|
"mean_token_accuracy": 0.1766239583492279,
|
|
"num_tokens": 45147531.0,
|
|
"step": 21755
|
|
},
|
|
{
|
|
"entropy": 5.535717487335205,
|
|
"epoch": 1.9738751814223512,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004610738488237065,
|
|
"loss": 5.2799,
|
|
"mean_token_accuracy": 0.1858828216791153,
|
|
"num_tokens": 45158312.0,
|
|
"step": 21760
|
|
},
|
|
{
|
|
"entropy": 5.555647182464599,
|
|
"epoch": 1.9743287373004355,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004610556558148535,
|
|
"loss": 5.3451,
|
|
"mean_token_accuracy": 0.1813496842980385,
|
|
"num_tokens": 45169754.0,
|
|
"step": 21765
|
|
},
|
|
{
|
|
"entropy": 5.636524486541748,
|
|
"epoch": 1.9747822931785195,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004610374589583222,
|
|
"loss": 5.3569,
|
|
"mean_token_accuracy": 0.17629070430994034,
|
|
"num_tokens": 45180428.0,
|
|
"step": 21770
|
|
},
|
|
{
|
|
"entropy": 5.622860860824585,
|
|
"epoch": 1.9752358490566038,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004610192582544888,
|
|
"loss": 5.263,
|
|
"mean_token_accuracy": 0.18079162985086442,
|
|
"num_tokens": 45191558.0,
|
|
"step": 21775
|
|
},
|
|
{
|
|
"entropy": 5.510887002944946,
|
|
"epoch": 1.975689404934688,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004610010537037297,
|
|
"loss": 5.2252,
|
|
"mean_token_accuracy": 0.18412295877933502,
|
|
"num_tokens": 45201567.0,
|
|
"step": 21780
|
|
},
|
|
{
|
|
"entropy": 5.5899604797363285,
|
|
"epoch": 1.9761429608127723,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004609828453064214,
|
|
"loss": 5.3865,
|
|
"mean_token_accuracy": 0.17417013496160508,
|
|
"num_tokens": 45211359.0,
|
|
"step": 21785
|
|
},
|
|
{
|
|
"entropy": 5.658561754226684,
|
|
"epoch": 1.9765965166908563,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00046096463306294057,
|
|
"loss": 5.2922,
|
|
"mean_token_accuracy": 0.1777358517050743,
|
|
"num_tokens": 45222106.0,
|
|
"step": 21790
|
|
},
|
|
{
|
|
"entropy": 5.5397905826568605,
|
|
"epoch": 1.9770500725689404,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.00046094641697366366,
|
|
"loss": 5.3296,
|
|
"mean_token_accuracy": 0.17780682146549226,
|
|
"num_tokens": 45233169.0,
|
|
"step": 21795
|
|
},
|
|
{
|
|
"entropy": 5.6275317668914795,
|
|
"epoch": 1.9775036284470247,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004609281970389675,
|
|
"loss": 5.3648,
|
|
"mean_token_accuracy": 0.1755299061536789,
|
|
"num_tokens": 45243627.0,
|
|
"step": 21800
|
|
},
|
|
{
|
|
"entropy": 5.60023865699768,
|
|
"epoch": 1.977957184325109,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00046090997325922887,
|
|
"loss": 5.2386,
|
|
"mean_token_accuracy": 0.18640235513448716,
|
|
"num_tokens": 45253730.0,
|
|
"step": 21805
|
|
},
|
|
{
|
|
"entropy": 5.530814552307129,
|
|
"epoch": 1.9784107402031932,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00046089174563482456,
|
|
"loss": 5.3555,
|
|
"mean_token_accuracy": 0.180723837018013,
|
|
"num_tokens": 45263443.0,
|
|
"step": 21810
|
|
},
|
|
{
|
|
"entropy": 5.568198490142822,
|
|
"epoch": 1.9788642960812772,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004608735141661316,
|
|
"loss": 5.279,
|
|
"mean_token_accuracy": 0.18429996222257614,
|
|
"num_tokens": 45275298.0,
|
|
"step": 21815
|
|
},
|
|
{
|
|
"entropy": 5.593659496307373,
|
|
"epoch": 1.9793178519593613,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.00046085527885352694,
|
|
"loss": 5.3375,
|
|
"mean_token_accuracy": 0.18081700950860977,
|
|
"num_tokens": 45285628.0,
|
|
"step": 21820
|
|
},
|
|
{
|
|
"entropy": 5.53930401802063,
|
|
"epoch": 1.9797714078374455,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004608370396973878,
|
|
"loss": 5.2211,
|
|
"mean_token_accuracy": 0.18943082988262178,
|
|
"num_tokens": 45295559.0,
|
|
"step": 21825
|
|
},
|
|
{
|
|
"entropy": 5.532186651229859,
|
|
"epoch": 1.9802249637155298,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00046081879669809133,
|
|
"loss": 5.2402,
|
|
"mean_token_accuracy": 0.18276432007551194,
|
|
"num_tokens": 45305395.0,
|
|
"step": 21830
|
|
},
|
|
{
|
|
"entropy": 5.520247316360473,
|
|
"epoch": 1.980678519593614,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004608005498560148,
|
|
"loss": 5.2886,
|
|
"mean_token_accuracy": 0.1812789782881737,
|
|
"num_tokens": 45316763.0,
|
|
"step": 21835
|
|
},
|
|
{
|
|
"entropy": 5.59122486114502,
|
|
"epoch": 1.9811320754716981,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004607822991715356,
|
|
"loss": 5.3938,
|
|
"mean_token_accuracy": 0.17995795458555222,
|
|
"num_tokens": 45326484.0,
|
|
"step": 21840
|
|
},
|
|
{
|
|
"entropy": 5.638384246826172,
|
|
"epoch": 1.9815856313497822,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.000460764044645031,
|
|
"loss": 5.333,
|
|
"mean_token_accuracy": 0.1764498010277748,
|
|
"num_tokens": 45335792.0,
|
|
"step": 21845
|
|
},
|
|
{
|
|
"entropy": 5.612069463729858,
|
|
"epoch": 1.9820391872278664,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004607457862768787,
|
|
"loss": 5.2504,
|
|
"mean_token_accuracy": 0.1747642770409584,
|
|
"num_tokens": 45347247.0,
|
|
"step": 21850
|
|
},
|
|
{
|
|
"entropy": 5.597916507720948,
|
|
"epoch": 1.9824927431059507,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004607275240674562,
|
|
"loss": 5.3717,
|
|
"mean_token_accuracy": 0.17591406553983688,
|
|
"num_tokens": 45357994.0,
|
|
"step": 21855
|
|
},
|
|
{
|
|
"entropy": 5.526047897338867,
|
|
"epoch": 1.982946298984035,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004607092580171411,
|
|
"loss": 5.2961,
|
|
"mean_token_accuracy": 0.18549751490354538,
|
|
"num_tokens": 45368170.0,
|
|
"step": 21860
|
|
},
|
|
{
|
|
"entropy": 5.6480175971984865,
|
|
"epoch": 1.983399854862119,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004606909881263113,
|
|
"loss": 5.347,
|
|
"mean_token_accuracy": 0.1798924282193184,
|
|
"num_tokens": 45378696.0,
|
|
"step": 21865
|
|
},
|
|
{
|
|
"entropy": 5.569428539276123,
|
|
"epoch": 1.983853410740203,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.00046067271439534445,
|
|
"loss": 5.3572,
|
|
"mean_token_accuracy": 0.18211608082056047,
|
|
"num_tokens": 45388578.0,
|
|
"step": 21870
|
|
},
|
|
{
|
|
"entropy": 5.535323190689087,
|
|
"epoch": 1.9843069666182873,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00046065443682461864,
|
|
"loss": 5.3413,
|
|
"mean_token_accuracy": 0.1853299021720886,
|
|
"num_tokens": 45398835.0,
|
|
"step": 21875
|
|
},
|
|
{
|
|
"entropy": 5.619301271438599,
|
|
"epoch": 1.9847605224963716,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.00046063615541451177,
|
|
"loss": 5.3241,
|
|
"mean_token_accuracy": 0.18542393296957016,
|
|
"num_tokens": 45409032.0,
|
|
"step": 21880
|
|
},
|
|
{
|
|
"entropy": 5.727363157272339,
|
|
"epoch": 1.9852140783744558,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00046061787016540184,
|
|
"loss": 5.459,
|
|
"mean_token_accuracy": 0.17095108330249786,
|
|
"num_tokens": 45420661.0,
|
|
"step": 21885
|
|
},
|
|
{
|
|
"entropy": 5.547087240219116,
|
|
"epoch": 1.98566763425254,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00046059958107766706,
|
|
"loss": 5.1667,
|
|
"mean_token_accuracy": 0.1898372694849968,
|
|
"num_tokens": 45429751.0,
|
|
"step": 21890
|
|
},
|
|
{
|
|
"entropy": 5.556672811508179,
|
|
"epoch": 1.986121190130624,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004605812881516857,
|
|
"loss": 5.3177,
|
|
"mean_token_accuracy": 0.1812572494149208,
|
|
"num_tokens": 45439551.0,
|
|
"step": 21895
|
|
},
|
|
{
|
|
"entropy": 5.491260719299317,
|
|
"epoch": 1.9865747460087082,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.00046056299138783595,
|
|
"loss": 5.2007,
|
|
"mean_token_accuracy": 0.19646471440792085,
|
|
"num_tokens": 45449543.0,
|
|
"step": 21900
|
|
},
|
|
{
|
|
"entropy": 5.619277143478394,
|
|
"epoch": 1.9870283018867925,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004605446907864963,
|
|
"loss": 5.2912,
|
|
"mean_token_accuracy": 0.18639226704835893,
|
|
"num_tokens": 45459069.0,
|
|
"step": 21905
|
|
},
|
|
{
|
|
"entropy": 5.558329916000366,
|
|
"epoch": 1.9874818577648767,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004605263863480452,
|
|
"loss": 5.3811,
|
|
"mean_token_accuracy": 0.17197523415088653,
|
|
"num_tokens": 45468987.0,
|
|
"step": 21910
|
|
},
|
|
{
|
|
"entropy": 5.578445243835449,
|
|
"epoch": 1.9879354136429608,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.00046050807807286105,
|
|
"loss": 5.3214,
|
|
"mean_token_accuracy": 0.18158025443553924,
|
|
"num_tokens": 45479781.0,
|
|
"step": 21915
|
|
},
|
|
{
|
|
"entropy": 5.620148420333862,
|
|
"epoch": 1.988388969521045,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00046048976596132265,
|
|
"loss": 5.4387,
|
|
"mean_token_accuracy": 0.1673465594649315,
|
|
"num_tokens": 45490318.0,
|
|
"step": 21920
|
|
},
|
|
{
|
|
"entropy": 5.6376145362854,
|
|
"epoch": 1.988842525399129,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.00046047145001380856,
|
|
"loss": 5.2905,
|
|
"mean_token_accuracy": 0.17976690232753753,
|
|
"num_tokens": 45501514.0,
|
|
"step": 21925
|
|
},
|
|
{
|
|
"entropy": 5.617892742156982,
|
|
"epoch": 1.9892960812772134,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.00046045313023069764,
|
|
"loss": 5.2987,
|
|
"mean_token_accuracy": 0.18053478449583055,
|
|
"num_tokens": 45511727.0,
|
|
"step": 21930
|
|
},
|
|
{
|
|
"entropy": 5.608760166168213,
|
|
"epoch": 1.9897496371552976,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004604348066123688,
|
|
"loss": 5.3762,
|
|
"mean_token_accuracy": 0.17653663605451583,
|
|
"num_tokens": 45521807.0,
|
|
"step": 21935
|
|
},
|
|
{
|
|
"entropy": 5.6047900199890135,
|
|
"epoch": 1.9902031930333817,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004604164791592008,
|
|
"loss": 5.4061,
|
|
"mean_token_accuracy": 0.17540066987276076,
|
|
"num_tokens": 45532033.0,
|
|
"step": 21940
|
|
},
|
|
{
|
|
"entropy": 5.576085472106934,
|
|
"epoch": 1.990656748911466,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.00046039814787157283,
|
|
"loss": 5.3158,
|
|
"mean_token_accuracy": 0.17934771925210952,
|
|
"num_tokens": 45542806.0,
|
|
"step": 21945
|
|
},
|
|
{
|
|
"entropy": 5.609518909454346,
|
|
"epoch": 1.99111030478955,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004603798127498639,
|
|
"loss": 5.2172,
|
|
"mean_token_accuracy": 0.19429333209991456,
|
|
"num_tokens": 45551982.0,
|
|
"step": 21950
|
|
},
|
|
{
|
|
"entropy": 5.559415864944458,
|
|
"epoch": 1.9915638606676342,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004603614737944532,
|
|
"loss": 5.3009,
|
|
"mean_token_accuracy": 0.17657733261585234,
|
|
"num_tokens": 45561998.0,
|
|
"step": 21955
|
|
},
|
|
{
|
|
"entropy": 5.509364032745362,
|
|
"epoch": 1.9920174165457185,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.00046034313100571994,
|
|
"loss": 5.3224,
|
|
"mean_token_accuracy": 0.18323838114738464,
|
|
"num_tokens": 45572246.0,
|
|
"step": 21960
|
|
},
|
|
{
|
|
"entropy": 5.619767951965332,
|
|
"epoch": 1.9924709724238028,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004603247843840436,
|
|
"loss": 5.3138,
|
|
"mean_token_accuracy": 0.18217200934886932,
|
|
"num_tokens": 45582251.0,
|
|
"step": 21965
|
|
},
|
|
{
|
|
"entropy": 5.5912439823150635,
|
|
"epoch": 1.9929245283018868,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004603064339298034,
|
|
"loss": 5.2065,
|
|
"mean_token_accuracy": 0.18167163729667662,
|
|
"num_tokens": 45592749.0,
|
|
"step": 21970
|
|
},
|
|
{
|
|
"entropy": 5.527221441268921,
|
|
"epoch": 1.9933780841799709,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004602880796433789,
|
|
"loss": 5.2594,
|
|
"mean_token_accuracy": 0.18709229081869125,
|
|
"num_tokens": 45602412.0,
|
|
"step": 21975
|
|
},
|
|
{
|
|
"entropy": 5.558908605575562,
|
|
"epoch": 1.9938316400580551,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00046026972152514976,
|
|
"loss": 5.3118,
|
|
"mean_token_accuracy": 0.18222615569829942,
|
|
"num_tokens": 45612736.0,
|
|
"step": 21980
|
|
},
|
|
{
|
|
"entropy": 5.564388704299927,
|
|
"epoch": 1.9942851959361394,
|
|
"grad_norm": 4.375,
|
|
"learning_rate": 0.0004602513595754956,
|
|
"loss": 5.3078,
|
|
"mean_token_accuracy": 0.18002102971076966,
|
|
"num_tokens": 45622952.0,
|
|
"step": 21985
|
|
},
|
|
{
|
|
"entropy": 5.653039598464966,
|
|
"epoch": 1.9947387518142237,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.00046023299379479606,
|
|
"loss": 5.3102,
|
|
"mean_token_accuracy": 0.18130840361118317,
|
|
"num_tokens": 45633569.0,
|
|
"step": 21990
|
|
},
|
|
{
|
|
"entropy": 5.5706329345703125,
|
|
"epoch": 1.9951923076923077,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00046021462418343104,
|
|
"loss": 5.2793,
|
|
"mean_token_accuracy": 0.18419425934553146,
|
|
"num_tokens": 45644347.0,
|
|
"step": 21995
|
|
},
|
|
{
|
|
"entropy": 5.6028087615966795,
|
|
"epoch": 1.9956458635703918,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004601962507417804,
|
|
"loss": 5.3501,
|
|
"mean_token_accuracy": 0.18111425042152404,
|
|
"num_tokens": 45655268.0,
|
|
"step": 22000
|
|
},
|
|
{
|
|
"entropy": 5.545610094070435,
|
|
"epoch": 1.996099419448476,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00046017787347022403,
|
|
"loss": 5.2607,
|
|
"mean_token_accuracy": 0.18070369809865952,
|
|
"num_tokens": 45664900.0,
|
|
"step": 22005
|
|
},
|
|
{
|
|
"entropy": 5.576204061508179,
|
|
"epoch": 1.9965529753265603,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00046015949236914217,
|
|
"loss": 5.3457,
|
|
"mean_token_accuracy": 0.18392767608165742,
|
|
"num_tokens": 45675252.0,
|
|
"step": 22010
|
|
},
|
|
{
|
|
"entropy": 5.68876576423645,
|
|
"epoch": 1.9970065312046446,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004601411074389147,
|
|
"loss": 5.2699,
|
|
"mean_token_accuracy": 0.1898592934012413,
|
|
"num_tokens": 45686027.0,
|
|
"step": 22015
|
|
},
|
|
{
|
|
"entropy": 5.579426336288452,
|
|
"epoch": 1.9974600870827286,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.000460122718679922,
|
|
"loss": 5.2935,
|
|
"mean_token_accuracy": 0.18306645303964614,
|
|
"num_tokens": 45696436.0,
|
|
"step": 22020
|
|
},
|
|
{
|
|
"entropy": 5.601642179489136,
|
|
"epoch": 1.9979136429608126,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004601043260925443,
|
|
"loss": 5.3665,
|
|
"mean_token_accuracy": 0.1849289655685425,
|
|
"num_tokens": 45706509.0,
|
|
"step": 22025
|
|
},
|
|
{
|
|
"entropy": 5.660798692703247,
|
|
"epoch": 1.998367198838897,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00046008592967716197,
|
|
"loss": 5.4243,
|
|
"mean_token_accuracy": 0.17634244114160538,
|
|
"num_tokens": 45717933.0,
|
|
"step": 22030
|
|
},
|
|
{
|
|
"entropy": 5.551484537124634,
|
|
"epoch": 1.9988207547169812,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004600675294341554,
|
|
"loss": 5.3401,
|
|
"mean_token_accuracy": 0.1721138045191765,
|
|
"num_tokens": 45727966.0,
|
|
"step": 22035
|
|
},
|
|
{
|
|
"entropy": 5.5878290176391605,
|
|
"epoch": 1.9992743105950654,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00046004912536390526,
|
|
"loss": 5.2915,
|
|
"mean_token_accuracy": 0.17779464423656463,
|
|
"num_tokens": 45737649.0,
|
|
"step": 22040
|
|
},
|
|
{
|
|
"entropy": 5.572466802597046,
|
|
"epoch": 1.9997278664731495,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.000460030717466792,
|
|
"loss": 5.2643,
|
|
"mean_token_accuracy": 0.1817932590842247,
|
|
"num_tokens": 45747561.0,
|
|
"step": 22045
|
|
},
|
|
{
|
|
"entropy": 5.517218399047851,
|
|
"epoch": 2.0001814223512335,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004600123057431963,
|
|
"loss": 5.243,
|
|
"mean_token_accuracy": 0.18627494126558303,
|
|
"num_tokens": 45758183.0,
|
|
"step": 22050
|
|
},
|
|
{
|
|
"entropy": 5.543736124038697,
|
|
"epoch": 2.000634978229318,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000459993890193499,
|
|
"loss": 5.185,
|
|
"mean_token_accuracy": 0.19367986023426056,
|
|
"num_tokens": 45768006.0,
|
|
"step": 22055
|
|
},
|
|
{
|
|
"entropy": 5.656395530700683,
|
|
"epoch": 2.001088534107402,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004599754708180809,
|
|
"loss": 5.3365,
|
|
"mean_token_accuracy": 0.17612339109182357,
|
|
"num_tokens": 45777981.0,
|
|
"step": 22060
|
|
},
|
|
{
|
|
"entropy": 5.602379322052002,
|
|
"epoch": 2.0015420899854863,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.000459957047617323,
|
|
"loss": 5.2748,
|
|
"mean_token_accuracy": 0.17245786488056183,
|
|
"num_tokens": 45789083.0,
|
|
"step": 22065
|
|
},
|
|
{
|
|
"entropy": 5.577207136154175,
|
|
"epoch": 2.0019956458635706,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00045993862059160617,
|
|
"loss": 5.226,
|
|
"mean_token_accuracy": 0.18475177139043808,
|
|
"num_tokens": 45799750.0,
|
|
"step": 22070
|
|
},
|
|
{
|
|
"entropy": 5.54208607673645,
|
|
"epoch": 2.0024492017416544,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004599201897413116,
|
|
"loss": 5.2094,
|
|
"mean_token_accuracy": 0.18328294157981873,
|
|
"num_tokens": 45810321.0,
|
|
"step": 22075
|
|
},
|
|
{
|
|
"entropy": 5.512918281555176,
|
|
"epoch": 2.0029027576197387,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00045990175506682024,
|
|
"loss": 5.2061,
|
|
"mean_token_accuracy": 0.19508396089076996,
|
|
"num_tokens": 45820581.0,
|
|
"step": 22080
|
|
},
|
|
{
|
|
"entropy": 5.53116397857666,
|
|
"epoch": 2.003356313497823,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00045988331656851355,
|
|
"loss": 5.2804,
|
|
"mean_token_accuracy": 0.18593716919422149,
|
|
"num_tokens": 45831504.0,
|
|
"step": 22085
|
|
},
|
|
{
|
|
"entropy": 5.6681318283081055,
|
|
"epoch": 2.003809869375907,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00045986487424677284,
|
|
"loss": 5.3046,
|
|
"mean_token_accuracy": 0.1736682802438736,
|
|
"num_tokens": 45841100.0,
|
|
"step": 22090
|
|
},
|
|
{
|
|
"entropy": 5.598131799697876,
|
|
"epoch": 2.0042634252539915,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004598464281019793,
|
|
"loss": 5.2744,
|
|
"mean_token_accuracy": 0.18418213725090027,
|
|
"num_tokens": 45851647.0,
|
|
"step": 22095
|
|
},
|
|
{
|
|
"entropy": 5.540210580825805,
|
|
"epoch": 2.0047169811320753,
|
|
"grad_norm": 5.34375,
|
|
"learning_rate": 0.00045982797813451463,
|
|
"loss": 5.2178,
|
|
"mean_token_accuracy": 0.1872380182147026,
|
|
"num_tokens": 45862995.0,
|
|
"step": 22100
|
|
},
|
|
{
|
|
"entropy": 5.54449143409729,
|
|
"epoch": 2.0051705370101596,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00045980952434476014,
|
|
"loss": 5.1919,
|
|
"mean_token_accuracy": 0.18440558314323424,
|
|
"num_tokens": 45872360.0,
|
|
"step": 22105
|
|
},
|
|
{
|
|
"entropy": 5.5372288703918455,
|
|
"epoch": 2.005624092888244,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00045979106673309765,
|
|
"loss": 5.2909,
|
|
"mean_token_accuracy": 0.17900955379009248,
|
|
"num_tokens": 45883440.0,
|
|
"step": 22110
|
|
},
|
|
{
|
|
"entropy": 5.533351993560791,
|
|
"epoch": 2.006077648766328,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00045977260529990883,
|
|
"loss": 5.2429,
|
|
"mean_token_accuracy": 0.17758926153182983,
|
|
"num_tokens": 45894323.0,
|
|
"step": 22115
|
|
},
|
|
{
|
|
"entropy": 5.612805986404419,
|
|
"epoch": 2.0065312046444124,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004597541400455755,
|
|
"loss": 5.2984,
|
|
"mean_token_accuracy": 0.17962462902069093,
|
|
"num_tokens": 45904544.0,
|
|
"step": 22120
|
|
},
|
|
{
|
|
"entropy": 5.605461502075196,
|
|
"epoch": 2.006984760522496,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00045973567097047933,
|
|
"loss": 5.1548,
|
|
"mean_token_accuracy": 0.19899992793798446,
|
|
"num_tokens": 45913225.0,
|
|
"step": 22125
|
|
},
|
|
{
|
|
"entropy": 5.546856498718261,
|
|
"epoch": 2.0074383164005805,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00045971719807500253,
|
|
"loss": 5.2864,
|
|
"mean_token_accuracy": 0.18350888639688492,
|
|
"num_tokens": 45923306.0,
|
|
"step": 22130
|
|
},
|
|
{
|
|
"entropy": 5.557965040206909,
|
|
"epoch": 2.0078918722786647,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.000459698721359527,
|
|
"loss": 5.2505,
|
|
"mean_token_accuracy": 0.18236721605062484,
|
|
"num_tokens": 45933243.0,
|
|
"step": 22135
|
|
},
|
|
{
|
|
"entropy": 5.538159990310669,
|
|
"epoch": 2.008345428156749,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004596802408244348,
|
|
"loss": 5.2988,
|
|
"mean_token_accuracy": 0.18269335180521012,
|
|
"num_tokens": 45944498.0,
|
|
"step": 22140
|
|
},
|
|
{
|
|
"entropy": 5.510904979705811,
|
|
"epoch": 2.0087989840348333,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004596617564701081,
|
|
"loss": 5.1381,
|
|
"mean_token_accuracy": 0.1855629026889801,
|
|
"num_tokens": 45954550.0,
|
|
"step": 22145
|
|
},
|
|
{
|
|
"entropy": 5.6369232654571535,
|
|
"epoch": 2.009252539912917,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.00045964326829692925,
|
|
"loss": 5.29,
|
|
"mean_token_accuracy": 0.183208891749382,
|
|
"num_tokens": 45965425.0,
|
|
"step": 22150
|
|
},
|
|
{
|
|
"entropy": 5.593247270584106,
|
|
"epoch": 2.0097060957910013,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.00045962477630528064,
|
|
"loss": 5.1813,
|
|
"mean_token_accuracy": 0.18812217563390732,
|
|
"num_tokens": 45975637.0,
|
|
"step": 22155
|
|
},
|
|
{
|
|
"entropy": 5.458828639984131,
|
|
"epoch": 2.0101596516690856,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.00045960628049554453,
|
|
"loss": 5.2868,
|
|
"mean_token_accuracy": 0.17874969840049743,
|
|
"num_tokens": 45985268.0,
|
|
"step": 22160
|
|
},
|
|
{
|
|
"entropy": 5.548216533660889,
|
|
"epoch": 2.01061320754717,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.00045958778086810354,
|
|
"loss": 5.1785,
|
|
"mean_token_accuracy": 0.18602558225393295,
|
|
"num_tokens": 45995335.0,
|
|
"step": 22165
|
|
},
|
|
{
|
|
"entropy": 5.611292505264283,
|
|
"epoch": 2.011066763425254,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004595692774233402,
|
|
"loss": 5.2893,
|
|
"mean_token_accuracy": 0.17343450337648392,
|
|
"num_tokens": 46006037.0,
|
|
"step": 22170
|
|
},
|
|
{
|
|
"entropy": 5.578270101547242,
|
|
"epoch": 2.011520319303338,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00045955077016163713,
|
|
"loss": 5.2025,
|
|
"mean_token_accuracy": 0.1844080537557602,
|
|
"num_tokens": 46017016.0,
|
|
"step": 22175
|
|
},
|
|
{
|
|
"entropy": 5.608216142654419,
|
|
"epoch": 2.0119738751814222,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045953225908337717,
|
|
"loss": 5.324,
|
|
"mean_token_accuracy": 0.17642613649368286,
|
|
"num_tokens": 46026797.0,
|
|
"step": 22180
|
|
},
|
|
{
|
|
"entropy": 5.508034181594849,
|
|
"epoch": 2.0124274310595065,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.00045951374418894304,
|
|
"loss": 5.1789,
|
|
"mean_token_accuracy": 0.18664344698190688,
|
|
"num_tokens": 46037799.0,
|
|
"step": 22185
|
|
},
|
|
{
|
|
"entropy": 5.566151762008667,
|
|
"epoch": 2.0128809869375908,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.00045949522547871765,
|
|
"loss": 5.184,
|
|
"mean_token_accuracy": 0.1824946880340576,
|
|
"num_tokens": 46048617.0,
|
|
"step": 22190
|
|
},
|
|
{
|
|
"entropy": 5.582837009429932,
|
|
"epoch": 2.013334542815675,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000459476702953084,
|
|
"loss": 5.3067,
|
|
"mean_token_accuracy": 0.17904813438653946,
|
|
"num_tokens": 46060122.0,
|
|
"step": 22195
|
|
},
|
|
{
|
|
"entropy": 5.5567139148712155,
|
|
"epoch": 2.013788098693759,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.000459458176612425,
|
|
"loss": 5.2665,
|
|
"mean_token_accuracy": 0.18596346080303192,
|
|
"num_tokens": 46071488.0,
|
|
"step": 22200
|
|
},
|
|
{
|
|
"entropy": 5.597385692596435,
|
|
"epoch": 2.014241654571843,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.00045943964645712407,
|
|
"loss": 5.3079,
|
|
"mean_token_accuracy": 0.17813366353511811,
|
|
"num_tokens": 46081954.0,
|
|
"step": 22205
|
|
},
|
|
{
|
|
"entropy": 5.584795188903809,
|
|
"epoch": 2.0146952104499274,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004594211124875642,
|
|
"loss": 5.2383,
|
|
"mean_token_accuracy": 0.18410923331975937,
|
|
"num_tokens": 46092488.0,
|
|
"step": 22210
|
|
},
|
|
{
|
|
"entropy": 5.511542844772339,
|
|
"epoch": 2.0151487663280117,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004594025747041287,
|
|
"loss": 5.213,
|
|
"mean_token_accuracy": 0.188099767267704,
|
|
"num_tokens": 46102451.0,
|
|
"step": 22215
|
|
},
|
|
{
|
|
"entropy": 5.5436341762542725,
|
|
"epoch": 2.015602322206096,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.000459384033107201,
|
|
"loss": 5.2665,
|
|
"mean_token_accuracy": 0.18776106238365173,
|
|
"num_tokens": 46113862.0,
|
|
"step": 22220
|
|
},
|
|
{
|
|
"entropy": 5.648655223846435,
|
|
"epoch": 2.01605587808418,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004593654876971645,
|
|
"loss": 5.3293,
|
|
"mean_token_accuracy": 0.17838037610054017,
|
|
"num_tokens": 46124517.0,
|
|
"step": 22225
|
|
},
|
|
{
|
|
"entropy": 5.537239933013916,
|
|
"epoch": 2.016509433962264,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004593469384744027,
|
|
"loss": 5.2462,
|
|
"mean_token_accuracy": 0.1860145077109337,
|
|
"num_tokens": 46134221.0,
|
|
"step": 22230
|
|
},
|
|
{
|
|
"entropy": 5.583055734634399,
|
|
"epoch": 2.0169629898403483,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00045932838543929924,
|
|
"loss": 5.3138,
|
|
"mean_token_accuracy": 0.17881361097097398,
|
|
"num_tokens": 46144512.0,
|
|
"step": 22235
|
|
},
|
|
{
|
|
"entropy": 5.556908226013183,
|
|
"epoch": 2.0174165457184325,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004593098285922378,
|
|
"loss": 5.223,
|
|
"mean_token_accuracy": 0.18170927166938783,
|
|
"num_tokens": 46154373.0,
|
|
"step": 22240
|
|
},
|
|
{
|
|
"entropy": 5.587155723571778,
|
|
"epoch": 2.017870101596517,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004592912679336021,
|
|
"loss": 5.3554,
|
|
"mean_token_accuracy": 0.18244194239377975,
|
|
"num_tokens": 46164834.0,
|
|
"step": 22245
|
|
},
|
|
{
|
|
"entropy": 5.603373003005982,
|
|
"epoch": 2.018323657474601,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004592727034637761,
|
|
"loss": 5.1712,
|
|
"mean_token_accuracy": 0.18579149693250657,
|
|
"num_tokens": 46174815.0,
|
|
"step": 22250
|
|
},
|
|
{
|
|
"entropy": 5.555668687820434,
|
|
"epoch": 2.018777213352685,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00045925413518314363,
|
|
"loss": 5.2485,
|
|
"mean_token_accuracy": 0.18030916154384613,
|
|
"num_tokens": 46185155.0,
|
|
"step": 22255
|
|
},
|
|
{
|
|
"entropy": 5.5531786441802975,
|
|
"epoch": 2.019230769230769,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004592355630920886,
|
|
"loss": 5.2717,
|
|
"mean_token_accuracy": 0.18342005908489228,
|
|
"num_tokens": 46194537.0,
|
|
"step": 22260
|
|
},
|
|
{
|
|
"entropy": 5.621317672729492,
|
|
"epoch": 2.0196843251088534,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.00045921698719099527,
|
|
"loss": 5.315,
|
|
"mean_token_accuracy": 0.17778042405843736,
|
|
"num_tokens": 46205494.0,
|
|
"step": 22265
|
|
},
|
|
{
|
|
"entropy": 5.523827266693115,
|
|
"epoch": 2.0201378809869377,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.00045919840748024764,
|
|
"loss": 5.2146,
|
|
"mean_token_accuracy": 0.18887046724557877,
|
|
"num_tokens": 46216399.0,
|
|
"step": 22270
|
|
},
|
|
{
|
|
"entropy": 5.499228429794312,
|
|
"epoch": 2.020591436865022,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.00045917982396023,
|
|
"loss": 5.1941,
|
|
"mean_token_accuracy": 0.18737938404083251,
|
|
"num_tokens": 46226515.0,
|
|
"step": 22275
|
|
},
|
|
{
|
|
"entropy": 5.585562467575073,
|
|
"epoch": 2.021044992743106,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00045916123663132676,
|
|
"loss": 5.2956,
|
|
"mean_token_accuracy": 0.17914576083421707,
|
|
"num_tokens": 46236688.0,
|
|
"step": 22280
|
|
},
|
|
{
|
|
"entropy": 5.574934720993042,
|
|
"epoch": 2.02149854862119,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00045914264549392215,
|
|
"loss": 5.2309,
|
|
"mean_token_accuracy": 0.18677876889705658,
|
|
"num_tokens": 46247166.0,
|
|
"step": 22285
|
|
},
|
|
{
|
|
"entropy": 5.580445861816406,
|
|
"epoch": 2.0219521044992743,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004591240505484007,
|
|
"loss": 5.2221,
|
|
"mean_token_accuracy": 0.18615317344665527,
|
|
"num_tokens": 46258902.0,
|
|
"step": 22290
|
|
},
|
|
{
|
|
"entropy": 5.561169958114624,
|
|
"epoch": 2.0224056603773586,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00045910545179514694,
|
|
"loss": 5.3508,
|
|
"mean_token_accuracy": 0.18281570374965667,
|
|
"num_tokens": 46269819.0,
|
|
"step": 22295
|
|
},
|
|
{
|
|
"entropy": 5.643772029876709,
|
|
"epoch": 2.022859216255443,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004590868492345455,
|
|
"loss": 5.3036,
|
|
"mean_token_accuracy": 0.18942114114761352,
|
|
"num_tokens": 46280715.0,
|
|
"step": 22300
|
|
},
|
|
{
|
|
"entropy": 5.569918298721314,
|
|
"epoch": 2.0233127721335267,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004590682428669813,
|
|
"loss": 5.3067,
|
|
"mean_token_accuracy": 0.17759570479393005,
|
|
"num_tokens": 46291079.0,
|
|
"step": 22305
|
|
},
|
|
{
|
|
"entropy": 5.558801078796387,
|
|
"epoch": 2.023766328011611,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004590496326928387,
|
|
"loss": 5.237,
|
|
"mean_token_accuracy": 0.18530105352401732,
|
|
"num_tokens": 46301362.0,
|
|
"step": 22310
|
|
},
|
|
{
|
|
"entropy": 5.5890665531158445,
|
|
"epoch": 2.024219883889695,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00045903101871250295,
|
|
"loss": 5.2378,
|
|
"mean_token_accuracy": 0.18844351023435593,
|
|
"num_tokens": 46311820.0,
|
|
"step": 22315
|
|
},
|
|
{
|
|
"entropy": 5.594406032562256,
|
|
"epoch": 2.0246734397677795,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004590124009263587,
|
|
"loss": 5.3226,
|
|
"mean_token_accuracy": 0.1816896066069603,
|
|
"num_tokens": 46321992.0,
|
|
"step": 22320
|
|
},
|
|
{
|
|
"entropy": 5.576642608642578,
|
|
"epoch": 2.0251269956458637,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004589937793347912,
|
|
"loss": 5.2616,
|
|
"mean_token_accuracy": 0.1818601071834564,
|
|
"num_tokens": 46331537.0,
|
|
"step": 22325
|
|
},
|
|
{
|
|
"entropy": 5.597654247283936,
|
|
"epoch": 2.0255805515239476,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00045897515393818547,
|
|
"loss": 5.2653,
|
|
"mean_token_accuracy": 0.18324426263570787,
|
|
"num_tokens": 46342214.0,
|
|
"step": 22330
|
|
},
|
|
{
|
|
"entropy": 5.557746410369873,
|
|
"epoch": 2.026034107402032,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004589565247369266,
|
|
"loss": 5.2363,
|
|
"mean_token_accuracy": 0.18328023254871367,
|
|
"num_tokens": 46352471.0,
|
|
"step": 22335
|
|
},
|
|
{
|
|
"entropy": 5.546024656295776,
|
|
"epoch": 2.026487663280116,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004589378917314,
|
|
"loss": 5.2817,
|
|
"mean_token_accuracy": 0.18391880691051482,
|
|
"num_tokens": 46363221.0,
|
|
"step": 22340
|
|
},
|
|
{
|
|
"entropy": 5.506575965881348,
|
|
"epoch": 2.0269412191582004,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.00045891925492199087,
|
|
"loss": 5.1331,
|
|
"mean_token_accuracy": 0.19392141550779343,
|
|
"num_tokens": 46373454.0,
|
|
"step": 22345
|
|
},
|
|
{
|
|
"entropy": 5.646241283416748,
|
|
"epoch": 2.0273947750362846,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004589006143090847,
|
|
"loss": 5.4223,
|
|
"mean_token_accuracy": 0.17742058634757996,
|
|
"num_tokens": 46384403.0,
|
|
"step": 22350
|
|
},
|
|
{
|
|
"entropy": 5.543138742446899,
|
|
"epoch": 2.0278483309143684,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.00045888196989306697,
|
|
"loss": 5.1212,
|
|
"mean_token_accuracy": 0.19595131725072862,
|
|
"num_tokens": 46393362.0,
|
|
"step": 22355
|
|
},
|
|
{
|
|
"entropy": 5.607797622680664,
|
|
"epoch": 2.0283018867924527,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004588633216743232,
|
|
"loss": 5.376,
|
|
"mean_token_accuracy": 0.17772231996059418,
|
|
"num_tokens": 46405100.0,
|
|
"step": 22360
|
|
},
|
|
{
|
|
"entropy": 5.499736595153808,
|
|
"epoch": 2.028755442670537,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00045884466965323914,
|
|
"loss": 5.1704,
|
|
"mean_token_accuracy": 0.1847025364637375,
|
|
"num_tokens": 46415058.0,
|
|
"step": 22365
|
|
},
|
|
{
|
|
"entropy": 5.531554222106934,
|
|
"epoch": 2.0292089985486212,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00045882601383020045,
|
|
"loss": 5.2253,
|
|
"mean_token_accuracy": 0.18793194144964218,
|
|
"num_tokens": 46425863.0,
|
|
"step": 22370
|
|
},
|
|
{
|
|
"entropy": 5.585980319976807,
|
|
"epoch": 2.0296625544267055,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004588073542055929,
|
|
"loss": 5.2528,
|
|
"mean_token_accuracy": 0.18112456500530244,
|
|
"num_tokens": 46436172.0,
|
|
"step": 22375
|
|
},
|
|
{
|
|
"entropy": 5.5844025135040285,
|
|
"epoch": 2.0301161103047893,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.00045878869077980246,
|
|
"loss": 5.2659,
|
|
"mean_token_accuracy": 0.18312447071075438,
|
|
"num_tokens": 46446717.0,
|
|
"step": 22380
|
|
},
|
|
{
|
|
"entropy": 5.539090156555176,
|
|
"epoch": 2.0305696661828736,
|
|
"grad_norm": 3.078125,
|
|
"learning_rate": 0.00045877002355321504,
|
|
"loss": 5.2903,
|
|
"mean_token_accuracy": 0.1787529394030571,
|
|
"num_tokens": 46456944.0,
|
|
"step": 22385
|
|
},
|
|
{
|
|
"entropy": 5.616184425354004,
|
|
"epoch": 2.031023222060958,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004587513525262168,
|
|
"loss": 5.3487,
|
|
"mean_token_accuracy": 0.17832941114902495,
|
|
"num_tokens": 46467231.0,
|
|
"step": 22390
|
|
},
|
|
{
|
|
"entropy": 5.612815999984742,
|
|
"epoch": 2.031476777939042,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00045873267769919364,
|
|
"loss": 5.2073,
|
|
"mean_token_accuracy": 0.18122973740100862,
|
|
"num_tokens": 46477107.0,
|
|
"step": 22395
|
|
},
|
|
{
|
|
"entropy": 5.517215204238892,
|
|
"epoch": 2.0319303338171264,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004587139990725319,
|
|
"loss": 5.2452,
|
|
"mean_token_accuracy": 0.18325329571962357,
|
|
"num_tokens": 46487351.0,
|
|
"step": 22400
|
|
},
|
|
{
|
|
"entropy": 5.5741489887237545,
|
|
"epoch": 2.0323838896952107,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004586953166466179,
|
|
"loss": 5.2551,
|
|
"mean_token_accuracy": 0.1834300547838211,
|
|
"num_tokens": 46497685.0,
|
|
"step": 22405
|
|
},
|
|
{
|
|
"entropy": 5.553748035430909,
|
|
"epoch": 2.0328374455732945,
|
|
"grad_norm": 4.1875,
|
|
"learning_rate": 0.0004586766304218379,
|
|
"loss": 5.2613,
|
|
"mean_token_accuracy": 0.17877312898635864,
|
|
"num_tokens": 46507866.0,
|
|
"step": 22410
|
|
},
|
|
{
|
|
"entropy": 5.4715980052947994,
|
|
"epoch": 2.0332910014513788,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00045865794039857846,
|
|
"loss": 5.1374,
|
|
"mean_token_accuracy": 0.18936495780944823,
|
|
"num_tokens": 46518797.0,
|
|
"step": 22415
|
|
},
|
|
{
|
|
"entropy": 5.541735315322876,
|
|
"epoch": 2.033744557329463,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004586392465772259,
|
|
"loss": 5.2226,
|
|
"mean_token_accuracy": 0.18874711394309998,
|
|
"num_tokens": 46528759.0,
|
|
"step": 22420
|
|
},
|
|
{
|
|
"entropy": 5.621553754806518,
|
|
"epoch": 2.0341981132075473,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00045862054895816703,
|
|
"loss": 5.3792,
|
|
"mean_token_accuracy": 0.1738415241241455,
|
|
"num_tokens": 46539014.0,
|
|
"step": 22425
|
|
},
|
|
{
|
|
"entropy": 5.539882326126099,
|
|
"epoch": 2.0346516690856316,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004586018475417884,
|
|
"loss": 5.2188,
|
|
"mean_token_accuracy": 0.18710640966892242,
|
|
"num_tokens": 46548856.0,
|
|
"step": 22430
|
|
},
|
|
{
|
|
"entropy": 5.543344879150391,
|
|
"epoch": 2.0351052249637154,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004585831423284766,
|
|
"loss": 5.1646,
|
|
"mean_token_accuracy": 0.18906009048223496,
|
|
"num_tokens": 46559164.0,
|
|
"step": 22435
|
|
},
|
|
{
|
|
"entropy": 5.581176853179931,
|
|
"epoch": 2.0355587808417996,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004585644333186188,
|
|
"loss": 5.2962,
|
|
"mean_token_accuracy": 0.1818004682660103,
|
|
"num_tokens": 46569793.0,
|
|
"step": 22440
|
|
},
|
|
{
|
|
"entropy": 5.4963539123535154,
|
|
"epoch": 2.036012336719884,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00045854572051260166,
|
|
"loss": 5.2602,
|
|
"mean_token_accuracy": 0.1805044174194336,
|
|
"num_tokens": 46580257.0,
|
|
"step": 22445
|
|
},
|
|
{
|
|
"entropy": 5.550759172439575,
|
|
"epoch": 2.036465892597968,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00045852700391081234,
|
|
"loss": 5.2569,
|
|
"mean_token_accuracy": 0.17985691726207734,
|
|
"num_tokens": 46590297.0,
|
|
"step": 22450
|
|
},
|
|
{
|
|
"entropy": 5.6076905727386475,
|
|
"epoch": 2.0369194484760524,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004585082835136378,
|
|
"loss": 5.2006,
|
|
"mean_token_accuracy": 0.18670224994421006,
|
|
"num_tokens": 46600647.0,
|
|
"step": 22455
|
|
},
|
|
{
|
|
"entropy": 5.544330883026123,
|
|
"epoch": 2.0373730043541363,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004584895593214652,
|
|
"loss": 5.2107,
|
|
"mean_token_accuracy": 0.1794478103518486,
|
|
"num_tokens": 46610478.0,
|
|
"step": 22460
|
|
},
|
|
{
|
|
"entropy": 5.551231861114502,
|
|
"epoch": 2.0378265602322205,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.00045847083133468164,
|
|
"loss": 5.307,
|
|
"mean_token_accuracy": 0.17770083844661713,
|
|
"num_tokens": 46620159.0,
|
|
"step": 22465
|
|
},
|
|
{
|
|
"entropy": 5.606198835372925,
|
|
"epoch": 2.038280116110305,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.00045845209955367464,
|
|
"loss": 5.2573,
|
|
"mean_token_accuracy": 0.19012654274702073,
|
|
"num_tokens": 46630555.0,
|
|
"step": 22470
|
|
},
|
|
{
|
|
"entropy": 5.60363278388977,
|
|
"epoch": 2.038733671988389,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00045843336397883146,
|
|
"loss": 5.2967,
|
|
"mean_token_accuracy": 0.18084371089935303,
|
|
"num_tokens": 46640188.0,
|
|
"step": 22475
|
|
},
|
|
{
|
|
"entropy": 5.554281187057495,
|
|
"epoch": 2.0391872278664733,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004584146246105396,
|
|
"loss": 5.2271,
|
|
"mean_token_accuracy": 0.1813964769244194,
|
|
"num_tokens": 46650284.0,
|
|
"step": 22480
|
|
},
|
|
{
|
|
"entropy": 5.608973646163941,
|
|
"epoch": 2.039640783744557,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00045839588144918643,
|
|
"loss": 5.2537,
|
|
"mean_token_accuracy": 0.18517248779535295,
|
|
"num_tokens": 46661466.0,
|
|
"step": 22485
|
|
},
|
|
{
|
|
"entropy": 5.593744325637817,
|
|
"epoch": 2.0400943396226414,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004583771344951598,
|
|
"loss": 5.2379,
|
|
"mean_token_accuracy": 0.18128122836351396,
|
|
"num_tokens": 46671683.0,
|
|
"step": 22490
|
|
},
|
|
{
|
|
"entropy": 5.585569858551025,
|
|
"epoch": 2.0405478955007257,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00045835838374884733,
|
|
"loss": 5.2675,
|
|
"mean_token_accuracy": 0.1802387624979019,
|
|
"num_tokens": 46681787.0,
|
|
"step": 22495
|
|
},
|
|
{
|
|
"entropy": 5.570886945724487,
|
|
"epoch": 2.04100145137881,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00045833962921063665,
|
|
"loss": 5.2546,
|
|
"mean_token_accuracy": 0.1862754613161087,
|
|
"num_tokens": 46692752.0,
|
|
"step": 22500
|
|
},
|
|
{
|
|
"entropy": 5.5832967281341555,
|
|
"epoch": 2.041455007256894,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00045832087088091574,
|
|
"loss": 5.2624,
|
|
"mean_token_accuracy": 0.18069402277469634,
|
|
"num_tokens": 46702980.0,
|
|
"step": 22505
|
|
},
|
|
{
|
|
"entropy": 5.553123331069946,
|
|
"epoch": 2.041908563134978,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00045830210876007257,
|
|
"loss": 5.1804,
|
|
"mean_token_accuracy": 0.18543682843446732,
|
|
"num_tokens": 46712281.0,
|
|
"step": 22510
|
|
},
|
|
{
|
|
"entropy": 5.559214401245117,
|
|
"epoch": 2.0423621190130623,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.000458283342848495,
|
|
"loss": 5.2255,
|
|
"mean_token_accuracy": 0.18368201702833176,
|
|
"num_tokens": 46722097.0,
|
|
"step": 22515
|
|
},
|
|
{
|
|
"entropy": 5.562899923324585,
|
|
"epoch": 2.0428156748911466,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004582645731465713,
|
|
"loss": 5.1674,
|
|
"mean_token_accuracy": 0.18806900978088378,
|
|
"num_tokens": 46733056.0,
|
|
"step": 22520
|
|
},
|
|
{
|
|
"entropy": 5.472023344039917,
|
|
"epoch": 2.043269230769231,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00045824579965468944,
|
|
"loss": 5.2069,
|
|
"mean_token_accuracy": 0.18518491536378862,
|
|
"num_tokens": 46742608.0,
|
|
"step": 22525
|
|
},
|
|
{
|
|
"entropy": 5.476154041290283,
|
|
"epoch": 2.043722786647315,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.00045822702237323777,
|
|
"loss": 5.1854,
|
|
"mean_token_accuracy": 0.18788106441497804,
|
|
"num_tokens": 46751762.0,
|
|
"step": 22530
|
|
},
|
|
{
|
|
"entropy": 5.552197694778442,
|
|
"epoch": 2.044176342525399,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00045820824130260457,
|
|
"loss": 5.1623,
|
|
"mean_token_accuracy": 0.19049201607704164,
|
|
"num_tokens": 46762252.0,
|
|
"step": 22535
|
|
},
|
|
{
|
|
"entropy": 5.501244831085205,
|
|
"epoch": 2.044629898403483,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004581894564431783,
|
|
"loss": 5.2336,
|
|
"mean_token_accuracy": 0.18134398013353348,
|
|
"num_tokens": 46772172.0,
|
|
"step": 22540
|
|
},
|
|
{
|
|
"entropy": 5.523800325393677,
|
|
"epoch": 2.0450834542815675,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004581706677953473,
|
|
"loss": 5.263,
|
|
"mean_token_accuracy": 0.18642648011446,
|
|
"num_tokens": 46782894.0,
|
|
"step": 22545
|
|
},
|
|
{
|
|
"entropy": 5.600769853591919,
|
|
"epoch": 2.0455370101596517,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.00045815187535950034,
|
|
"loss": 5.2477,
|
|
"mean_token_accuracy": 0.1886550799012184,
|
|
"num_tokens": 46793097.0,
|
|
"step": 22550
|
|
},
|
|
{
|
|
"entropy": 5.611119365692138,
|
|
"epoch": 2.045990566037736,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00045813307913602586,
|
|
"loss": 5.3502,
|
|
"mean_token_accuracy": 0.1757679581642151,
|
|
"num_tokens": 46804196.0,
|
|
"step": 22555
|
|
},
|
|
{
|
|
"entropy": 5.566511154174805,
|
|
"epoch": 2.04644412191582,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004581142791253126,
|
|
"loss": 5.224,
|
|
"mean_token_accuracy": 0.18303194344043733,
|
|
"num_tokens": 46813985.0,
|
|
"step": 22560
|
|
},
|
|
{
|
|
"entropy": 5.510678100585937,
|
|
"epoch": 2.046897677793904,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00045809547532774943,
|
|
"loss": 5.1334,
|
|
"mean_token_accuracy": 0.18302185982465743,
|
|
"num_tokens": 46824125.0,
|
|
"step": 22565
|
|
},
|
|
{
|
|
"entropy": 5.520827436447144,
|
|
"epoch": 2.0473512336719883,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00045807666774372514,
|
|
"loss": 5.1978,
|
|
"mean_token_accuracy": 0.18725704103708268,
|
|
"num_tokens": 46834982.0,
|
|
"step": 22570
|
|
},
|
|
{
|
|
"entropy": 5.528695774078369,
|
|
"epoch": 2.0478047895500726,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00045805785637362874,
|
|
"loss": 5.1577,
|
|
"mean_token_accuracy": 0.19719699174165725,
|
|
"num_tokens": 46844669.0,
|
|
"step": 22575
|
|
},
|
|
{
|
|
"entropy": 5.5569398403167725,
|
|
"epoch": 2.048258345428157,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004580390412178492,
|
|
"loss": 5.2649,
|
|
"mean_token_accuracy": 0.18722840547561645,
|
|
"num_tokens": 46855108.0,
|
|
"step": 22580
|
|
},
|
|
{
|
|
"entropy": 5.57944884300232,
|
|
"epoch": 2.048711901306241,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00045802022227677566,
|
|
"loss": 5.1967,
|
|
"mean_token_accuracy": 0.18706497251987458,
|
|
"num_tokens": 46864878.0,
|
|
"step": 22585
|
|
},
|
|
{
|
|
"entropy": 5.5038293361663815,
|
|
"epoch": 2.049165457184325,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00045800139955079727,
|
|
"loss": 5.2671,
|
|
"mean_token_accuracy": 0.1807018041610718,
|
|
"num_tokens": 46874916.0,
|
|
"step": 22590
|
|
},
|
|
{
|
|
"entropy": 5.638081836700439,
|
|
"epoch": 2.0496190130624092,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004579825730403033,
|
|
"loss": 5.3079,
|
|
"mean_token_accuracy": 0.18072825968265532,
|
|
"num_tokens": 46885167.0,
|
|
"step": 22595
|
|
},
|
|
{
|
|
"entropy": 5.613559150695801,
|
|
"epoch": 2.0500725689404935,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004579637427456831,
|
|
"loss": 5.2458,
|
|
"mean_token_accuracy": 0.17957068830728531,
|
|
"num_tokens": 46895526.0,
|
|
"step": 22600
|
|
},
|
|
{
|
|
"entropy": 5.502073526382446,
|
|
"epoch": 2.0505261248185778,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00045794490866732607,
|
|
"loss": 5.2248,
|
|
"mean_token_accuracy": 0.1866829961538315,
|
|
"num_tokens": 46905426.0,
|
|
"step": 22605
|
|
},
|
|
{
|
|
"entropy": 5.524333524703979,
|
|
"epoch": 2.050979680696662,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004579260708056217,
|
|
"loss": 5.2599,
|
|
"mean_token_accuracy": 0.18404529243707657,
|
|
"num_tokens": 46915728.0,
|
|
"step": 22610
|
|
},
|
|
{
|
|
"entropy": 5.526735734939575,
|
|
"epoch": 2.051433236574746,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004579072291609596,
|
|
"loss": 5.1911,
|
|
"mean_token_accuracy": 0.1857095405459404,
|
|
"num_tokens": 46925972.0,
|
|
"step": 22615
|
|
},
|
|
{
|
|
"entropy": 5.553948068618775,
|
|
"epoch": 2.05188679245283,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00045788838373372935,
|
|
"loss": 5.2394,
|
|
"mean_token_accuracy": 0.18838306814432143,
|
|
"num_tokens": 46937108.0,
|
|
"step": 22620
|
|
},
|
|
{
|
|
"entropy": 5.479068279266357,
|
|
"epoch": 2.0523403483309144,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00045786953452432076,
|
|
"loss": 5.2058,
|
|
"mean_token_accuracy": 0.18425551801919937,
|
|
"num_tokens": 46947684.0,
|
|
"step": 22625
|
|
},
|
|
{
|
|
"entropy": 5.604144191741943,
|
|
"epoch": 2.0527939042089987,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004578506815331236,
|
|
"loss": 5.2917,
|
|
"mean_token_accuracy": 0.1778078109025955,
|
|
"num_tokens": 46958089.0,
|
|
"step": 22630
|
|
},
|
|
{
|
|
"entropy": 5.590747356414795,
|
|
"epoch": 2.053247460087083,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004578318247605277,
|
|
"loss": 5.2065,
|
|
"mean_token_accuracy": 0.18725903630256652,
|
|
"num_tokens": 46968618.0,
|
|
"step": 22635
|
|
},
|
|
{
|
|
"entropy": 5.589133310317993,
|
|
"epoch": 2.0537010159651667,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004578129642069231,
|
|
"loss": 5.244,
|
|
"mean_token_accuracy": 0.1850969284772873,
|
|
"num_tokens": 46978791.0,
|
|
"step": 22640
|
|
},
|
|
{
|
|
"entropy": 5.5199071884155275,
|
|
"epoch": 2.054154571843251,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004577940998726998,
|
|
"loss": 5.1528,
|
|
"mean_token_accuracy": 0.1928577184677124,
|
|
"num_tokens": 46988706.0,
|
|
"step": 22645
|
|
},
|
|
{
|
|
"entropy": 5.630297613143921,
|
|
"epoch": 2.0546081277213353,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00045777523175824796,
|
|
"loss": 5.3816,
|
|
"mean_token_accuracy": 0.16492514163255692,
|
|
"num_tokens": 47000140.0,
|
|
"step": 22650
|
|
},
|
|
{
|
|
"entropy": 5.563996934890747,
|
|
"epoch": 2.0550616835994195,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004577563598639577,
|
|
"loss": 5.2085,
|
|
"mean_token_accuracy": 0.18276981264352798,
|
|
"num_tokens": 47009773.0,
|
|
"step": 22655
|
|
},
|
|
{
|
|
"entropy": 5.600859022140503,
|
|
"epoch": 2.055515239477504,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045773748419021944,
|
|
"loss": 5.2739,
|
|
"mean_token_accuracy": 0.17971778362989427,
|
|
"num_tokens": 47020326.0,
|
|
"step": 22660
|
|
},
|
|
{
|
|
"entropy": 5.514641809463501,
|
|
"epoch": 2.0559687953555876,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00045771860473742347,
|
|
"loss": 5.2031,
|
|
"mean_token_accuracy": 0.1790774792432785,
|
|
"num_tokens": 47030410.0,
|
|
"step": 22665
|
|
},
|
|
{
|
|
"entropy": 5.561816024780273,
|
|
"epoch": 2.056422351233672,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00045769972150596006,
|
|
"loss": 5.2549,
|
|
"mean_token_accuracy": 0.1846028283238411,
|
|
"num_tokens": 47040546.0,
|
|
"step": 22670
|
|
},
|
|
{
|
|
"entropy": 5.556395387649536,
|
|
"epoch": 2.056875907111756,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00045768083449621987,
|
|
"loss": 5.208,
|
|
"mean_token_accuracy": 0.19297388941049576,
|
|
"num_tokens": 47050210.0,
|
|
"step": 22675
|
|
},
|
|
{
|
|
"entropy": 5.621342945098877,
|
|
"epoch": 2.0573294629898404,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00045766194370859347,
|
|
"loss": 5.3524,
|
|
"mean_token_accuracy": 0.17087695598602295,
|
|
"num_tokens": 47060641.0,
|
|
"step": 22680
|
|
},
|
|
{
|
|
"entropy": 5.5494180679321286,
|
|
"epoch": 2.0577830188679247,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004576430491434716,
|
|
"loss": 5.3068,
|
|
"mean_token_accuracy": 0.17801005840301515,
|
|
"num_tokens": 47070737.0,
|
|
"step": 22685
|
|
},
|
|
{
|
|
"entropy": 5.647875070571899,
|
|
"epoch": 2.0582365747460085,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00045762415080124487,
|
|
"loss": 5.2577,
|
|
"mean_token_accuracy": 0.18341841101646422,
|
|
"num_tokens": 47080884.0,
|
|
"step": 22690
|
|
},
|
|
{
|
|
"entropy": 5.530067348480225,
|
|
"epoch": 2.058690130624093,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00045760524868230417,
|
|
"loss": 5.275,
|
|
"mean_token_accuracy": 0.18093051314353942,
|
|
"num_tokens": 47090865.0,
|
|
"step": 22695
|
|
},
|
|
{
|
|
"entropy": 5.560960960388184,
|
|
"epoch": 2.059143686502177,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004575863427870404,
|
|
"loss": 5.2483,
|
|
"mean_token_accuracy": 0.1885710299015045,
|
|
"num_tokens": 47100570.0,
|
|
"step": 22700
|
|
},
|
|
{
|
|
"entropy": 5.548301935195923,
|
|
"epoch": 2.0595972423802613,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004575674331158446,
|
|
"loss": 5.2428,
|
|
"mean_token_accuracy": 0.18918072283267975,
|
|
"num_tokens": 47111199.0,
|
|
"step": 22705
|
|
},
|
|
{
|
|
"entropy": 5.510970592498779,
|
|
"epoch": 2.0600507982583456,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004575485196691076,
|
|
"loss": 5.2354,
|
|
"mean_token_accuracy": 0.1906953051686287,
|
|
"num_tokens": 47121191.0,
|
|
"step": 22710
|
|
},
|
|
{
|
|
"entropy": 5.588504695892334,
|
|
"epoch": 2.0605043541364294,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004575296024472209,
|
|
"loss": 5.3209,
|
|
"mean_token_accuracy": 0.18385429233312606,
|
|
"num_tokens": 47131608.0,
|
|
"step": 22715
|
|
},
|
|
{
|
|
"entropy": 5.61322603225708,
|
|
"epoch": 2.0609579100145137,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004575106814505753,
|
|
"loss": 5.2663,
|
|
"mean_token_accuracy": 0.17905865907669066,
|
|
"num_tokens": 47141492.0,
|
|
"step": 22720
|
|
},
|
|
{
|
|
"entropy": 5.5094013690948485,
|
|
"epoch": 2.061411465892598,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004574917566795624,
|
|
"loss": 5.1496,
|
|
"mean_token_accuracy": 0.19303366541862488,
|
|
"num_tokens": 47152576.0,
|
|
"step": 22725
|
|
},
|
|
{
|
|
"entropy": 5.5755633354187015,
|
|
"epoch": 2.061865021770682,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00045747282813457345,
|
|
"loss": 5.2667,
|
|
"mean_token_accuracy": 0.1839375913143158,
|
|
"num_tokens": 47163863.0,
|
|
"step": 22730
|
|
},
|
|
{
|
|
"entropy": 5.562052059173584,
|
|
"epoch": 2.0623185776487665,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.000457453895816,
|
|
"loss": 5.2095,
|
|
"mean_token_accuracy": 0.1835006445646286,
|
|
"num_tokens": 47174140.0,
|
|
"step": 22735
|
|
},
|
|
{
|
|
"entropy": 5.5928675651550295,
|
|
"epoch": 2.0627721335268503,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00045743495972423346,
|
|
"loss": 5.2721,
|
|
"mean_token_accuracy": 0.18226301670074463,
|
|
"num_tokens": 47184708.0,
|
|
"step": 22740
|
|
},
|
|
{
|
|
"entropy": 5.520556688308716,
|
|
"epoch": 2.0632256894049346,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004574160198596653,
|
|
"loss": 5.2592,
|
|
"mean_token_accuracy": 0.18227149546146393,
|
|
"num_tokens": 47196286.0,
|
|
"step": 22745
|
|
},
|
|
{
|
|
"entropy": 5.493962001800537,
|
|
"epoch": 2.063679245283019,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00045739707622268757,
|
|
"loss": 5.2107,
|
|
"mean_token_accuracy": 0.1878925770521164,
|
|
"num_tokens": 47206774.0,
|
|
"step": 22750
|
|
},
|
|
{
|
|
"entropy": 5.4928460121154785,
|
|
"epoch": 2.064132801161103,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004573781288136917,
|
|
"loss": 5.1153,
|
|
"mean_token_accuracy": 0.19034356474876404,
|
|
"num_tokens": 47217009.0,
|
|
"step": 22755
|
|
},
|
|
{
|
|
"entropy": 5.519750642776489,
|
|
"epoch": 2.0645863570391874,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00045735917763306967,
|
|
"loss": 5.2541,
|
|
"mean_token_accuracy": 0.1821233555674553,
|
|
"num_tokens": 47226718.0,
|
|
"step": 22760
|
|
},
|
|
{
|
|
"entropy": 5.4953711986541744,
|
|
"epoch": 2.065039912917271,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004573402226812134,
|
|
"loss": 5.1367,
|
|
"mean_token_accuracy": 0.18909185528755187,
|
|
"num_tokens": 47237666.0,
|
|
"step": 22765
|
|
},
|
|
{
|
|
"entropy": 5.528785133361817,
|
|
"epoch": 2.0654934687953554,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00045732126395851483,
|
|
"loss": 5.2869,
|
|
"mean_token_accuracy": 0.17933062911033631,
|
|
"num_tokens": 47249230.0,
|
|
"step": 22770
|
|
},
|
|
{
|
|
"entropy": 5.539918375015259,
|
|
"epoch": 2.0659470246734397,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004573023014653661,
|
|
"loss": 5.2011,
|
|
"mean_token_accuracy": 0.1888681173324585,
|
|
"num_tokens": 47259232.0,
|
|
"step": 22775
|
|
},
|
|
{
|
|
"entropy": 5.5421136856079105,
|
|
"epoch": 2.066400580551524,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00045728333520215933,
|
|
"loss": 5.2287,
|
|
"mean_token_accuracy": 0.1854269415140152,
|
|
"num_tokens": 47269006.0,
|
|
"step": 22780
|
|
},
|
|
{
|
|
"entropy": 5.619526052474976,
|
|
"epoch": 2.0668541364296082,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004572643651692867,
|
|
"loss": 5.3568,
|
|
"mean_token_accuracy": 0.17479745745658876,
|
|
"num_tokens": 47280048.0,
|
|
"step": 22785
|
|
},
|
|
{
|
|
"entropy": 5.550009632110596,
|
|
"epoch": 2.0673076923076925,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00045724539136714063,
|
|
"loss": 5.1869,
|
|
"mean_token_accuracy": 0.18713129162788392,
|
|
"num_tokens": 47290019.0,
|
|
"step": 22790
|
|
},
|
|
{
|
|
"entropy": 5.526314210891724,
|
|
"epoch": 2.0677612481857763,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004572264137961133,
|
|
"loss": 5.197,
|
|
"mean_token_accuracy": 0.19014092832803725,
|
|
"num_tokens": 47300573.0,
|
|
"step": 22795
|
|
},
|
|
{
|
|
"entropy": 5.5123954772949215,
|
|
"epoch": 2.0682148040638606,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00045720743245659734,
|
|
"loss": 5.2342,
|
|
"mean_token_accuracy": 0.17934393733739853,
|
|
"num_tokens": 47311795.0,
|
|
"step": 22800
|
|
},
|
|
{
|
|
"entropy": 5.477789688110351,
|
|
"epoch": 2.068668359941945,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004571884473489853,
|
|
"loss": 5.1043,
|
|
"mean_token_accuracy": 0.1941846042871475,
|
|
"num_tokens": 47321768.0,
|
|
"step": 22805
|
|
},
|
|
{
|
|
"entropy": 5.567196035385132,
|
|
"epoch": 2.069121915820029,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004571694584736696,
|
|
"loss": 5.3217,
|
|
"mean_token_accuracy": 0.1826891615986824,
|
|
"num_tokens": 47332662.0,
|
|
"step": 22810
|
|
},
|
|
{
|
|
"entropy": 5.552196502685547,
|
|
"epoch": 2.0695754716981134,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004571504658310432,
|
|
"loss": 5.2314,
|
|
"mean_token_accuracy": 0.18449398130178452,
|
|
"num_tokens": 47344355.0,
|
|
"step": 22815
|
|
},
|
|
{
|
|
"entropy": 5.547899436950684,
|
|
"epoch": 2.0700290275761972,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004571314694214987,
|
|
"loss": 5.1645,
|
|
"mean_token_accuracy": 0.18716369718313217,
|
|
"num_tokens": 47354228.0,
|
|
"step": 22820
|
|
},
|
|
{
|
|
"entropy": 5.563525247573852,
|
|
"epoch": 2.0704825834542815,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004571124692454291,
|
|
"loss": 5.253,
|
|
"mean_token_accuracy": 0.188925601541996,
|
|
"num_tokens": 47364477.0,
|
|
"step": 22825
|
|
},
|
|
{
|
|
"entropy": 5.633573389053344,
|
|
"epoch": 2.0709361393323658,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00045709346530322715,
|
|
"loss": 5.3014,
|
|
"mean_token_accuracy": 0.18268002271652223,
|
|
"num_tokens": 47375745.0,
|
|
"step": 22830
|
|
},
|
|
{
|
|
"entropy": 5.566318511962891,
|
|
"epoch": 2.07138969521045,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004570744575952859,
|
|
"loss": 5.3187,
|
|
"mean_token_accuracy": 0.18831775933504105,
|
|
"num_tokens": 47385341.0,
|
|
"step": 22835
|
|
},
|
|
{
|
|
"entropy": 5.551354837417603,
|
|
"epoch": 2.0718432510885343,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004570554461219985,
|
|
"loss": 5.251,
|
|
"mean_token_accuracy": 0.185641872882843,
|
|
"num_tokens": 47396266.0,
|
|
"step": 22840
|
|
},
|
|
{
|
|
"entropy": 5.562741756439209,
|
|
"epoch": 2.072296806966618,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00045703643088375806,
|
|
"loss": 5.2438,
|
|
"mean_token_accuracy": 0.18217995911836624,
|
|
"num_tokens": 47406772.0,
|
|
"step": 22845
|
|
},
|
|
{
|
|
"entropy": 5.587442874908447,
|
|
"epoch": 2.0727503628447024,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00045701741188095793,
|
|
"loss": 5.332,
|
|
"mean_token_accuracy": 0.1831201896071434,
|
|
"num_tokens": 47416833.0,
|
|
"step": 22850
|
|
},
|
|
{
|
|
"entropy": 5.587214136123658,
|
|
"epoch": 2.0732039187227866,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004569983891139912,
|
|
"loss": 5.2378,
|
|
"mean_token_accuracy": 0.18645152151584626,
|
|
"num_tokens": 47426954.0,
|
|
"step": 22855
|
|
},
|
|
{
|
|
"entropy": 5.459418773651123,
|
|
"epoch": 2.073657474600871,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00045697936258325155,
|
|
"loss": 5.1713,
|
|
"mean_token_accuracy": 0.19373421669006347,
|
|
"num_tokens": 47437520.0,
|
|
"step": 22860
|
|
},
|
|
{
|
|
"entropy": 5.526633453369141,
|
|
"epoch": 2.074111030478955,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.00045696033228913226,
|
|
"loss": 5.2111,
|
|
"mean_token_accuracy": 0.18460774570703506,
|
|
"num_tokens": 47447977.0,
|
|
"step": 22865
|
|
},
|
|
{
|
|
"entropy": 5.607237005233765,
|
|
"epoch": 2.074564586357039,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00045694129823202684,
|
|
"loss": 5.2722,
|
|
"mean_token_accuracy": 0.18083774894475937,
|
|
"num_tokens": 47458458.0,
|
|
"step": 22870
|
|
},
|
|
{
|
|
"entropy": 5.57957878112793,
|
|
"epoch": 2.0750181422351233,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004569222604123291,
|
|
"loss": 5.2691,
|
|
"mean_token_accuracy": 0.18077927976846694,
|
|
"num_tokens": 47469048.0,
|
|
"step": 22875
|
|
},
|
|
{
|
|
"entropy": 5.590211296081543,
|
|
"epoch": 2.0754716981132075,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004569032188304326,
|
|
"loss": 5.3091,
|
|
"mean_token_accuracy": 0.1756760686635971,
|
|
"num_tokens": 47480353.0,
|
|
"step": 22880
|
|
},
|
|
{
|
|
"entropy": 5.493614721298218,
|
|
"epoch": 2.075925253991292,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004568841734867313,
|
|
"loss": 5.1138,
|
|
"mean_token_accuracy": 0.18970161825418472,
|
|
"num_tokens": 47489951.0,
|
|
"step": 22885
|
|
},
|
|
{
|
|
"entropy": 5.464808988571167,
|
|
"epoch": 2.076378809869376,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004568651243816188,
|
|
"loss": 5.1781,
|
|
"mean_token_accuracy": 0.18353427797555924,
|
|
"num_tokens": 47499015.0,
|
|
"step": 22890
|
|
},
|
|
{
|
|
"entropy": 5.5940288543701175,
|
|
"epoch": 2.07683236574746,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00045684607151548923,
|
|
"loss": 5.2385,
|
|
"mean_token_accuracy": 0.1819751515984535,
|
|
"num_tokens": 47508694.0,
|
|
"step": 22895
|
|
},
|
|
{
|
|
"entropy": 5.755943155288696,
|
|
"epoch": 2.077285921625544,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00045682701488873655,
|
|
"loss": 5.4166,
|
|
"mean_token_accuracy": 0.17069879174232483,
|
|
"num_tokens": 47521336.0,
|
|
"step": 22900
|
|
},
|
|
{
|
|
"entropy": 5.610723352432251,
|
|
"epoch": 2.0777394775036284,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004568079545017549,
|
|
"loss": 5.3751,
|
|
"mean_token_accuracy": 0.17433918714523317,
|
|
"num_tokens": 47531857.0,
|
|
"step": 22905
|
|
},
|
|
{
|
|
"entropy": 5.577100849151611,
|
|
"epoch": 2.0781930333817127,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004567888903549385,
|
|
"loss": 5.2528,
|
|
"mean_token_accuracy": 0.18148279637098313,
|
|
"num_tokens": 47542224.0,
|
|
"step": 22910
|
|
},
|
|
{
|
|
"entropy": 5.540488243103027,
|
|
"epoch": 2.078646589259797,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004567698224486813,
|
|
"loss": 5.2994,
|
|
"mean_token_accuracy": 0.18394510298967362,
|
|
"num_tokens": 47552370.0,
|
|
"step": 22915
|
|
},
|
|
{
|
|
"entropy": 5.6529645919799805,
|
|
"epoch": 2.0791001451378808,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00045675075078337803,
|
|
"loss": 5.239,
|
|
"mean_token_accuracy": 0.18739912360906602,
|
|
"num_tokens": 47561997.0,
|
|
"step": 22920
|
|
},
|
|
{
|
|
"entropy": 5.585226249694824,
|
|
"epoch": 2.079553701015965,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004567316753594229,
|
|
"loss": 5.2492,
|
|
"mean_token_accuracy": 0.18579200953245162,
|
|
"num_tokens": 47571968.0,
|
|
"step": 22925
|
|
},
|
|
{
|
|
"entropy": 5.54933533668518,
|
|
"epoch": 2.0800072568940493,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00045671259617721037,
|
|
"loss": 5.2866,
|
|
"mean_token_accuracy": 0.18114285916090012,
|
|
"num_tokens": 47583459.0,
|
|
"step": 22930
|
|
},
|
|
{
|
|
"entropy": 5.500029516220093,
|
|
"epoch": 2.0804608127721336,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.000456693513237135,
|
|
"loss": 5.1934,
|
|
"mean_token_accuracy": 0.18878258913755416,
|
|
"num_tokens": 47594026.0,
|
|
"step": 22935
|
|
},
|
|
{
|
|
"entropy": 5.593518781661987,
|
|
"epoch": 2.080914368650218,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004566744265395916,
|
|
"loss": 5.2752,
|
|
"mean_token_accuracy": 0.18107996881008148,
|
|
"num_tokens": 47605246.0,
|
|
"step": 22940
|
|
},
|
|
{
|
|
"entropy": 5.618311071395874,
|
|
"epoch": 2.081367924528302,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00045665533608497467,
|
|
"loss": 5.3183,
|
|
"mean_token_accuracy": 0.17675235271453857,
|
|
"num_tokens": 47616702.0,
|
|
"step": 22945
|
|
},
|
|
{
|
|
"entropy": 5.614699125289917,
|
|
"epoch": 2.081821480406386,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00045663624187367914,
|
|
"loss": 5.3175,
|
|
"mean_token_accuracy": 0.17705948501825333,
|
|
"num_tokens": 47627616.0,
|
|
"step": 22950
|
|
},
|
|
{
|
|
"entropy": 5.563124179840088,
|
|
"epoch": 2.08227503628447,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004566171439060998,
|
|
"loss": 5.1978,
|
|
"mean_token_accuracy": 0.18692784756422043,
|
|
"num_tokens": 47637287.0,
|
|
"step": 22955
|
|
},
|
|
{
|
|
"entropy": 5.479030799865723,
|
|
"epoch": 2.0827285921625545,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004565980421826317,
|
|
"loss": 5.2092,
|
|
"mean_token_accuracy": 0.18833253979682923,
|
|
"num_tokens": 47647474.0,
|
|
"step": 22960
|
|
},
|
|
{
|
|
"entropy": 5.5970179557800295,
|
|
"epoch": 2.0831821480406387,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004565789367036697,
|
|
"loss": 5.29,
|
|
"mean_token_accuracy": 0.18573150038719177,
|
|
"num_tokens": 47657036.0,
|
|
"step": 22965
|
|
},
|
|
{
|
|
"entropy": 5.5521303653717045,
|
|
"epoch": 2.083635703918723,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004565598274696091,
|
|
"loss": 5.1819,
|
|
"mean_token_accuracy": 0.1827223300933838,
|
|
"num_tokens": 47668026.0,
|
|
"step": 22970
|
|
},
|
|
{
|
|
"entropy": 5.654318475723267,
|
|
"epoch": 2.084089259796807,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00045654071448084506,
|
|
"loss": 5.3409,
|
|
"mean_token_accuracy": 0.17729299813508986,
|
|
"num_tokens": 47679508.0,
|
|
"step": 22975
|
|
},
|
|
{
|
|
"entropy": 5.552447748184204,
|
|
"epoch": 2.084542815674891,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00045652159773777273,
|
|
"loss": 5.2491,
|
|
"mean_token_accuracy": 0.18305727541446687,
|
|
"num_tokens": 47688474.0,
|
|
"step": 22980
|
|
},
|
|
{
|
|
"entropy": 5.6845542907714846,
|
|
"epoch": 2.0849963715529753,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004565024772407875,
|
|
"loss": 5.4415,
|
|
"mean_token_accuracy": 0.16990629732608795,
|
|
"num_tokens": 47698675.0,
|
|
"step": 22985
|
|
},
|
|
{
|
|
"entropy": 5.526213550567627,
|
|
"epoch": 2.0854499274310596,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004564833529902848,
|
|
"loss": 5.216,
|
|
"mean_token_accuracy": 0.19322959035634996,
|
|
"num_tokens": 47709214.0,
|
|
"step": 22990
|
|
},
|
|
{
|
|
"entropy": 5.602399492263794,
|
|
"epoch": 2.085903483309144,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00045646422498666,
|
|
"loss": 5.3454,
|
|
"mean_token_accuracy": 0.17914690375328063,
|
|
"num_tokens": 47721000.0,
|
|
"step": 22995
|
|
},
|
|
{
|
|
"entropy": 5.531584978103638,
|
|
"epoch": 2.0863570391872277,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00045644509323030893,
|
|
"loss": 5.2312,
|
|
"mean_token_accuracy": 0.1844460368156433,
|
|
"num_tokens": 47731218.0,
|
|
"step": 23000
|
|
},
|
|
{
|
|
"entropy": 5.549739789962769,
|
|
"epoch": 2.086810595065312,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00045642595772162704,
|
|
"loss": 5.2312,
|
|
"mean_token_accuracy": 0.18288175761699677,
|
|
"num_tokens": 47742339.0,
|
|
"step": 23005
|
|
},
|
|
{
|
|
"entropy": 5.5863316535949705,
|
|
"epoch": 2.0872641509433962,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00045640681846101014,
|
|
"loss": 5.3232,
|
|
"mean_token_accuracy": 0.18214187026023865,
|
|
"num_tokens": 47752858.0,
|
|
"step": 23010
|
|
},
|
|
{
|
|
"entropy": 5.496779727935791,
|
|
"epoch": 2.0877177068214805,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004563876754488539,
|
|
"loss": 5.1647,
|
|
"mean_token_accuracy": 0.1939734175801277,
|
|
"num_tokens": 47763303.0,
|
|
"step": 23015
|
|
},
|
|
{
|
|
"entropy": 5.5193158149719235,
|
|
"epoch": 2.0881712626995648,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004563685286855544,
|
|
"loss": 5.2208,
|
|
"mean_token_accuracy": 0.18555020540952682,
|
|
"num_tokens": 47773212.0,
|
|
"step": 23020
|
|
},
|
|
{
|
|
"entropy": 5.611819744110107,
|
|
"epoch": 2.0886248185776486,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004563493781715075,
|
|
"loss": 5.3636,
|
|
"mean_token_accuracy": 0.17754304856061937,
|
|
"num_tokens": 47783376.0,
|
|
"step": 23025
|
|
},
|
|
{
|
|
"entropy": 5.560051584243775,
|
|
"epoch": 2.089078374455733,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004563302239071093,
|
|
"loss": 5.2592,
|
|
"mean_token_accuracy": 0.18456920683383943,
|
|
"num_tokens": 47794859.0,
|
|
"step": 23030
|
|
},
|
|
{
|
|
"entropy": 5.610524034500122,
|
|
"epoch": 2.089531930333817,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045631106589275576,
|
|
"loss": 5.2646,
|
|
"mean_token_accuracy": 0.1866685837507248,
|
|
"num_tokens": 47804721.0,
|
|
"step": 23035
|
|
},
|
|
{
|
|
"entropy": 5.5184088230133055,
|
|
"epoch": 2.0899854862119014,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00045629190412884324,
|
|
"loss": 5.1418,
|
|
"mean_token_accuracy": 0.18846865445375444,
|
|
"num_tokens": 47814701.0,
|
|
"step": 23040
|
|
},
|
|
{
|
|
"entropy": 5.4788963317871096,
|
|
"epoch": 2.0904390420899857,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00045627273861576786,
|
|
"loss": 5.1777,
|
|
"mean_token_accuracy": 0.19065566807985307,
|
|
"num_tokens": 47823941.0,
|
|
"step": 23045
|
|
},
|
|
{
|
|
"entropy": 5.550774097442627,
|
|
"epoch": 2.0908925979680695,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00045625356935392614,
|
|
"loss": 5.2814,
|
|
"mean_token_accuracy": 0.17882297784090043,
|
|
"num_tokens": 47835793.0,
|
|
"step": 23050
|
|
},
|
|
{
|
|
"entropy": 5.62972846031189,
|
|
"epoch": 2.0913461538461537,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004562343963437144,
|
|
"loss": 5.3116,
|
|
"mean_token_accuracy": 0.17980162650346757,
|
|
"num_tokens": 47845677.0,
|
|
"step": 23055
|
|
},
|
|
{
|
|
"entropy": 5.575396251678467,
|
|
"epoch": 2.091799709724238,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004562152195855291,
|
|
"loss": 5.2351,
|
|
"mean_token_accuracy": 0.18680448830127716,
|
|
"num_tokens": 47855611.0,
|
|
"step": 23060
|
|
},
|
|
{
|
|
"entropy": 5.503036594390869,
|
|
"epoch": 2.0922532656023223,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004561960390797669,
|
|
"loss": 5.2488,
|
|
"mean_token_accuracy": 0.183307047188282,
|
|
"num_tokens": 47865115.0,
|
|
"step": 23065
|
|
},
|
|
{
|
|
"entropy": 5.681470346450806,
|
|
"epoch": 2.0927068214804065,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.00045617685482682454,
|
|
"loss": 5.3354,
|
|
"mean_token_accuracy": 0.17674277424812318,
|
|
"num_tokens": 47876690.0,
|
|
"step": 23070
|
|
},
|
|
{
|
|
"entropy": 5.522285270690918,
|
|
"epoch": 2.0931603773584904,
|
|
"grad_norm": 4.25,
|
|
"learning_rate": 0.0004561576668270986,
|
|
"loss": 5.267,
|
|
"mean_token_accuracy": 0.18302233815193175,
|
|
"num_tokens": 47887709.0,
|
|
"step": 23075
|
|
},
|
|
{
|
|
"entropy": 5.5460100173950195,
|
|
"epoch": 2.0936139332365746,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045613847508098587,
|
|
"loss": 5.2635,
|
|
"mean_token_accuracy": 0.18220479786396027,
|
|
"num_tokens": 47898209.0,
|
|
"step": 23080
|
|
},
|
|
{
|
|
"entropy": 5.518504571914673,
|
|
"epoch": 2.094067489114659,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045611927958888335,
|
|
"loss": 5.1139,
|
|
"mean_token_accuracy": 0.19105662554502487,
|
|
"num_tokens": 47907494.0,
|
|
"step": 23085
|
|
},
|
|
{
|
|
"entropy": 5.5047680854797365,
|
|
"epoch": 2.094521044992743,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00045610008035118797,
|
|
"loss": 5.2507,
|
|
"mean_token_accuracy": 0.18476071655750276,
|
|
"num_tokens": 47916923.0,
|
|
"step": 23090
|
|
},
|
|
{
|
|
"entropy": 5.479627275466919,
|
|
"epoch": 2.0949746008708274,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00045608087736829687,
|
|
"loss": 5.1926,
|
|
"mean_token_accuracy": 0.1833968296647072,
|
|
"num_tokens": 47927043.0,
|
|
"step": 23095
|
|
},
|
|
{
|
|
"entropy": 5.63160662651062,
|
|
"epoch": 2.0954281567489113,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000456061670640607,
|
|
"loss": 5.2382,
|
|
"mean_token_accuracy": 0.18200140148401261,
|
|
"num_tokens": 47937296.0,
|
|
"step": 23100
|
|
},
|
|
{
|
|
"entropy": 5.569198322296143,
|
|
"epoch": 2.0958817126269955,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004560424601685157,
|
|
"loss": 5.2882,
|
|
"mean_token_accuracy": 0.18726493120193483,
|
|
"num_tokens": 47948268.0,
|
|
"step": 23105
|
|
},
|
|
{
|
|
"entropy": 5.5012613296508786,
|
|
"epoch": 2.09633526850508,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004560232459524201,
|
|
"loss": 5.207,
|
|
"mean_token_accuracy": 0.17921757698059082,
|
|
"num_tokens": 47958375.0,
|
|
"step": 23110
|
|
},
|
|
{
|
|
"entropy": 5.575702381134033,
|
|
"epoch": 2.096788824383164,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00045600402799271766,
|
|
"loss": 5.2866,
|
|
"mean_token_accuracy": 0.18766777366399764,
|
|
"num_tokens": 47968469.0,
|
|
"step": 23115
|
|
},
|
|
{
|
|
"entropy": 5.541971111297608,
|
|
"epoch": 2.0972423802612483,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004559848062898058,
|
|
"loss": 5.186,
|
|
"mean_token_accuracy": 0.19299905747175217,
|
|
"num_tokens": 47979630.0,
|
|
"step": 23120
|
|
},
|
|
{
|
|
"entropy": 5.537010669708252,
|
|
"epoch": 2.097695936139332,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004559655808440821,
|
|
"loss": 5.2378,
|
|
"mean_token_accuracy": 0.18564467132091522,
|
|
"num_tokens": 47989828.0,
|
|
"step": 23125
|
|
},
|
|
{
|
|
"entropy": 5.560104179382324,
|
|
"epoch": 2.0981494920174164,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.00045594635165594404,
|
|
"loss": 5.3517,
|
|
"mean_token_accuracy": 0.17640459686517715,
|
|
"num_tokens": 47999219.0,
|
|
"step": 23130
|
|
},
|
|
{
|
|
"entropy": 5.576062917709351,
|
|
"epoch": 2.0986030478955007,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045592711872578925,
|
|
"loss": 5.2374,
|
|
"mean_token_accuracy": 0.19000064730644226,
|
|
"num_tokens": 48009244.0,
|
|
"step": 23135
|
|
},
|
|
{
|
|
"entropy": 5.552267932891846,
|
|
"epoch": 2.099056603773585,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045590788205401557,
|
|
"loss": 5.1932,
|
|
"mean_token_accuracy": 0.1846208319067955,
|
|
"num_tokens": 48019066.0,
|
|
"step": 23140
|
|
},
|
|
{
|
|
"entropy": 5.4497843265533445,
|
|
"epoch": 2.099510159651669,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00045588864164102086,
|
|
"loss": 5.2031,
|
|
"mean_token_accuracy": 0.18780387938022614,
|
|
"num_tokens": 48028704.0,
|
|
"step": 23145
|
|
},
|
|
{
|
|
"entropy": 5.526807355880737,
|
|
"epoch": 2.0999637155297535,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00045586939748720284,
|
|
"loss": 5.2246,
|
|
"mean_token_accuracy": 0.18773807138204573,
|
|
"num_tokens": 48039210.0,
|
|
"step": 23150
|
|
},
|
|
{
|
|
"entropy": 5.59726037979126,
|
|
"epoch": 2.1004172714078373,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.00045585014959295965,
|
|
"loss": 5.3336,
|
|
"mean_token_accuracy": 0.17790410965681075,
|
|
"num_tokens": 48048446.0,
|
|
"step": 23155
|
|
},
|
|
{
|
|
"entropy": 5.580673599243164,
|
|
"epoch": 2.1008708272859216,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045583089795868934,
|
|
"loss": 5.2571,
|
|
"mean_token_accuracy": 0.18648320734500884,
|
|
"num_tokens": 48058880.0,
|
|
"step": 23160
|
|
},
|
|
{
|
|
"entropy": 5.576579952239991,
|
|
"epoch": 2.101324383164006,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004558116425847899,
|
|
"loss": 5.2869,
|
|
"mean_token_accuracy": 0.19217455089092256,
|
|
"num_tokens": 48070224.0,
|
|
"step": 23165
|
|
},
|
|
{
|
|
"entropy": 5.57338285446167,
|
|
"epoch": 2.10177793904209,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004557923834716596,
|
|
"loss": 5.2875,
|
|
"mean_token_accuracy": 0.17995548844337464,
|
|
"num_tokens": 48080914.0,
|
|
"step": 23170
|
|
},
|
|
{
|
|
"entropy": 5.509504270553589,
|
|
"epoch": 2.1022314949201744,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045577312061969677,
|
|
"loss": 5.2501,
|
|
"mean_token_accuracy": 0.17952490150928496,
|
|
"num_tokens": 48090873.0,
|
|
"step": 23175
|
|
},
|
|
{
|
|
"entropy": 5.6494756698608395,
|
|
"epoch": 2.102685050798258,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004557538540292997,
|
|
"loss": 5.3166,
|
|
"mean_token_accuracy": 0.18105077147483825,
|
|
"num_tokens": 48101885.0,
|
|
"step": 23180
|
|
},
|
|
{
|
|
"entropy": 5.62645149230957,
|
|
"epoch": 2.1031386066763424,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004557345837008669,
|
|
"loss": 5.3157,
|
|
"mean_token_accuracy": 0.1827493578195572,
|
|
"num_tokens": 48111472.0,
|
|
"step": 23185
|
|
},
|
|
{
|
|
"entropy": 5.4409160137176515,
|
|
"epoch": 2.1035921625544267,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00045571530963479684,
|
|
"loss": 5.1665,
|
|
"mean_token_accuracy": 0.1909235253930092,
|
|
"num_tokens": 48121351.0,
|
|
"step": 23190
|
|
},
|
|
{
|
|
"entropy": 5.588344669342041,
|
|
"epoch": 2.104045718432511,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00045569603183148814,
|
|
"loss": 5.2386,
|
|
"mean_token_accuracy": 0.19047794938087464,
|
|
"num_tokens": 48131104.0,
|
|
"step": 23195
|
|
},
|
|
{
|
|
"entropy": 5.588274574279785,
|
|
"epoch": 2.1044992743105952,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004556767502913395,
|
|
"loss": 5.3535,
|
|
"mean_token_accuracy": 0.17587995082139968,
|
|
"num_tokens": 48142895.0,
|
|
"step": 23200
|
|
},
|
|
{
|
|
"entropy": 5.492545652389526,
|
|
"epoch": 2.104952830188679,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00045565746501474946,
|
|
"loss": 5.1169,
|
|
"mean_token_accuracy": 0.18924620151519775,
|
|
"num_tokens": 48153294.0,
|
|
"step": 23205
|
|
},
|
|
{
|
|
"entropy": 5.598348999023438,
|
|
"epoch": 2.1054063860667633,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00045563817600211714,
|
|
"loss": 5.3086,
|
|
"mean_token_accuracy": 0.1792502671480179,
|
|
"num_tokens": 48164319.0,
|
|
"step": 23210
|
|
},
|
|
{
|
|
"entropy": 5.558218669891358,
|
|
"epoch": 2.1058599419448476,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00045561888325384124,
|
|
"loss": 5.2552,
|
|
"mean_token_accuracy": 0.18732925951480867,
|
|
"num_tokens": 48173918.0,
|
|
"step": 23215
|
|
},
|
|
{
|
|
"entropy": 5.6496278762817385,
|
|
"epoch": 2.106313497822932,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004555995867703209,
|
|
"loss": 5.2607,
|
|
"mean_token_accuracy": 0.18190909326076507,
|
|
"num_tokens": 48184127.0,
|
|
"step": 23220
|
|
},
|
|
{
|
|
"entropy": 5.486669969558716,
|
|
"epoch": 2.106767053701016,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.00045558028655195504,
|
|
"loss": 5.2132,
|
|
"mean_token_accuracy": 0.1821914330124855,
|
|
"num_tokens": 48194198.0,
|
|
"step": 23225
|
|
},
|
|
{
|
|
"entropy": 5.480316638946533,
|
|
"epoch": 2.1072206095791,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00045556098259914293,
|
|
"loss": 5.1983,
|
|
"mean_token_accuracy": 0.18586371690034867,
|
|
"num_tokens": 48204654.0,
|
|
"step": 23230
|
|
},
|
|
{
|
|
"entropy": 5.6114418506622314,
|
|
"epoch": 2.1076741654571842,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00045554167491228357,
|
|
"loss": 5.3497,
|
|
"mean_token_accuracy": 0.17171355336904526,
|
|
"num_tokens": 48215322.0,
|
|
"step": 23235
|
|
},
|
|
{
|
|
"entropy": 5.536103248596191,
|
|
"epoch": 2.1081277213352685,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00045552236349177637,
|
|
"loss": 5.1399,
|
|
"mean_token_accuracy": 0.19050137400627137,
|
|
"num_tokens": 48226142.0,
|
|
"step": 23240
|
|
},
|
|
{
|
|
"entropy": 5.455999326705933,
|
|
"epoch": 2.1085812772133528,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00045550304833802066,
|
|
"loss": 5.179,
|
|
"mean_token_accuracy": 0.18835047781467437,
|
|
"num_tokens": 48236896.0,
|
|
"step": 23245
|
|
},
|
|
{
|
|
"entropy": 5.439623022079468,
|
|
"epoch": 2.109034833091437,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.000455483729451416,
|
|
"loss": 5.1887,
|
|
"mean_token_accuracy": 0.1862416535615921,
|
|
"num_tokens": 48247425.0,
|
|
"step": 23250
|
|
},
|
|
{
|
|
"entropy": 5.6239160060882565,
|
|
"epoch": 2.109488388969521,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00045546440683236173,
|
|
"loss": 5.2906,
|
|
"mean_token_accuracy": 0.18124392926692962,
|
|
"num_tokens": 48258560.0,
|
|
"step": 23255
|
|
},
|
|
{
|
|
"entropy": 5.614392805099487,
|
|
"epoch": 2.109941944847605,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00045544508048125763,
|
|
"loss": 5.3258,
|
|
"mean_token_accuracy": 0.17836454063653945,
|
|
"num_tokens": 48269469.0,
|
|
"step": 23260
|
|
},
|
|
{
|
|
"entropy": 5.485283422470093,
|
|
"epoch": 2.1103955007256894,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004554257503985032,
|
|
"loss": 5.2139,
|
|
"mean_token_accuracy": 0.1873537316918373,
|
|
"num_tokens": 48278847.0,
|
|
"step": 23265
|
|
},
|
|
{
|
|
"entropy": 5.516034650802612,
|
|
"epoch": 2.1108490566037736,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.00045540641658449834,
|
|
"loss": 5.1613,
|
|
"mean_token_accuracy": 0.18364228308200836,
|
|
"num_tokens": 48288091.0,
|
|
"step": 23270
|
|
},
|
|
{
|
|
"entropy": 5.504547595977783,
|
|
"epoch": 2.111302612481858,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045538707903964275,
|
|
"loss": 5.162,
|
|
"mean_token_accuracy": 0.18624603897333145,
|
|
"num_tokens": 48297946.0,
|
|
"step": 23275
|
|
},
|
|
{
|
|
"entropy": 5.534684801101685,
|
|
"epoch": 2.1117561683599417,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00045536773776433647,
|
|
"loss": 5.2301,
|
|
"mean_token_accuracy": 0.18833478093147277,
|
|
"num_tokens": 48307650.0,
|
|
"step": 23280
|
|
},
|
|
{
|
|
"entropy": 5.56654806137085,
|
|
"epoch": 2.112209724238026,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00045534839275897937,
|
|
"loss": 5.3493,
|
|
"mean_token_accuracy": 0.17021159082651138,
|
|
"num_tokens": 48318824.0,
|
|
"step": 23285
|
|
},
|
|
{
|
|
"entropy": 5.530518388748169,
|
|
"epoch": 2.1126632801161103,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00045532904402397157,
|
|
"loss": 5.1896,
|
|
"mean_token_accuracy": 0.18862651735544206,
|
|
"num_tokens": 48329909.0,
|
|
"step": 23290
|
|
},
|
|
{
|
|
"entropy": 5.5567584991455075,
|
|
"epoch": 2.1131168359941945,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004553096915597132,
|
|
"loss": 5.3648,
|
|
"mean_token_accuracy": 0.17867941409349442,
|
|
"num_tokens": 48340142.0,
|
|
"step": 23295
|
|
},
|
|
{
|
|
"entropy": 5.563858222961426,
|
|
"epoch": 2.113570391872279,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004552903353666044,
|
|
"loss": 5.1933,
|
|
"mean_token_accuracy": 0.19307237416505812,
|
|
"num_tokens": 48350540.0,
|
|
"step": 23300
|
|
},
|
|
{
|
|
"entropy": 5.473031091690063,
|
|
"epoch": 2.114023947750363,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045527097544504556,
|
|
"loss": 5.1576,
|
|
"mean_token_accuracy": 0.19414756149053575,
|
|
"num_tokens": 48360153.0,
|
|
"step": 23305
|
|
},
|
|
{
|
|
"entropy": 5.456988191604614,
|
|
"epoch": 2.114477503628447,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.000455251611795437,
|
|
"loss": 5.2271,
|
|
"mean_token_accuracy": 0.19019637554883956,
|
|
"num_tokens": 48370088.0,
|
|
"step": 23310
|
|
},
|
|
{
|
|
"entropy": 5.608984422683716,
|
|
"epoch": 2.114931059506531,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004552322444181792,
|
|
"loss": 5.2577,
|
|
"mean_token_accuracy": 0.1820507675409317,
|
|
"num_tokens": 48381325.0,
|
|
"step": 23315
|
|
},
|
|
{
|
|
"entropy": 5.582639694213867,
|
|
"epoch": 2.1153846153846154,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004552128733136726,
|
|
"loss": 5.236,
|
|
"mean_token_accuracy": 0.18084612339735032,
|
|
"num_tokens": 48393077.0,
|
|
"step": 23320
|
|
},
|
|
{
|
|
"entropy": 5.493713140487671,
|
|
"epoch": 2.1158381712626997,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004551934984823179,
|
|
"loss": 5.234,
|
|
"mean_token_accuracy": 0.18685855567455292,
|
|
"num_tokens": 48403260.0,
|
|
"step": 23325
|
|
},
|
|
{
|
|
"entropy": 5.50230770111084,
|
|
"epoch": 2.116291727140784,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004551741199245157,
|
|
"loss": 5.2134,
|
|
"mean_token_accuracy": 0.18800910264253617,
|
|
"num_tokens": 48413616.0,
|
|
"step": 23330
|
|
},
|
|
{
|
|
"entropy": 5.568106746673584,
|
|
"epoch": 2.1167452830188678,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00045515473764066685,
|
|
"loss": 5.2221,
|
|
"mean_token_accuracy": 0.18675131350755692,
|
|
"num_tokens": 48424189.0,
|
|
"step": 23335
|
|
},
|
|
{
|
|
"entropy": 5.494173240661621,
|
|
"epoch": 2.117198838896952,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045513535163117205,
|
|
"loss": 5.2946,
|
|
"mean_token_accuracy": 0.18396503031253814,
|
|
"num_tokens": 48433603.0,
|
|
"step": 23340
|
|
},
|
|
{
|
|
"entropy": 5.579180669784546,
|
|
"epoch": 2.1176523947750363,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004551159618964323,
|
|
"loss": 5.2568,
|
|
"mean_token_accuracy": 0.18151301741600037,
|
|
"num_tokens": 48443043.0,
|
|
"step": 23345
|
|
},
|
|
{
|
|
"entropy": 5.514496755599976,
|
|
"epoch": 2.1181059506531206,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004550965684368486,
|
|
"loss": 5.1417,
|
|
"mean_token_accuracy": 0.19857997745275496,
|
|
"num_tokens": 48452765.0,
|
|
"step": 23350
|
|
},
|
|
{
|
|
"entropy": 5.509217929840088,
|
|
"epoch": 2.118559506531205,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004550771712528219,
|
|
"loss": 5.2005,
|
|
"mean_token_accuracy": 0.18599249571561813,
|
|
"num_tokens": 48463191.0,
|
|
"step": 23355
|
|
},
|
|
{
|
|
"entropy": 5.506817150115967,
|
|
"epoch": 2.1190130624092887,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004550577703447534,
|
|
"loss": 5.1906,
|
|
"mean_token_accuracy": 0.192564395070076,
|
|
"num_tokens": 48473280.0,
|
|
"step": 23360
|
|
},
|
|
{
|
|
"entropy": 5.506261348724365,
|
|
"epoch": 2.119466618287373,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00045503836571304443,
|
|
"loss": 5.1448,
|
|
"mean_token_accuracy": 0.19023039788007737,
|
|
"num_tokens": 48483465.0,
|
|
"step": 23365
|
|
},
|
|
{
|
|
"entropy": 5.525187969207764,
|
|
"epoch": 2.119920174165457,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004550189573580961,
|
|
"loss": 5.1537,
|
|
"mean_token_accuracy": 0.1900908187031746,
|
|
"num_tokens": 48494497.0,
|
|
"step": 23370
|
|
},
|
|
{
|
|
"entropy": 5.499065351486206,
|
|
"epoch": 2.1203737300435415,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004549995452803098,
|
|
"loss": 5.2431,
|
|
"mean_token_accuracy": 0.19374665766954421,
|
|
"num_tokens": 48504106.0,
|
|
"step": 23375
|
|
},
|
|
{
|
|
"entropy": 5.592017650604248,
|
|
"epoch": 2.1208272859216257,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004549801294800872,
|
|
"loss": 5.2902,
|
|
"mean_token_accuracy": 0.18086389005184172,
|
|
"num_tokens": 48515729.0,
|
|
"step": 23380
|
|
},
|
|
{
|
|
"entropy": 5.574238204956055,
|
|
"epoch": 2.1212808417997095,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004549607099578295,
|
|
"loss": 5.3018,
|
|
"mean_token_accuracy": 0.17742065191268921,
|
|
"num_tokens": 48526611.0,
|
|
"step": 23385
|
|
},
|
|
{
|
|
"entropy": 5.500802278518677,
|
|
"epoch": 2.121734397677794,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004549412867139386,
|
|
"loss": 5.1774,
|
|
"mean_token_accuracy": 0.19075438231229783,
|
|
"num_tokens": 48537016.0,
|
|
"step": 23390
|
|
},
|
|
{
|
|
"entropy": 5.531674098968506,
|
|
"epoch": 2.122187953555878,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00045492185974881587,
|
|
"loss": 5.2579,
|
|
"mean_token_accuracy": 0.1869484707713127,
|
|
"num_tokens": 48546786.0,
|
|
"step": 23395
|
|
},
|
|
{
|
|
"entropy": 5.533998680114746,
|
|
"epoch": 2.1226415094339623,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004549024290628634,
|
|
"loss": 5.2455,
|
|
"mean_token_accuracy": 0.18363831341266632,
|
|
"num_tokens": 48556306.0,
|
|
"step": 23400
|
|
},
|
|
{
|
|
"entropy": 5.595207166671753,
|
|
"epoch": 2.1230950653120466,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004548829946564827,
|
|
"loss": 5.2796,
|
|
"mean_token_accuracy": 0.184670127928257,
|
|
"num_tokens": 48566303.0,
|
|
"step": 23405
|
|
},
|
|
{
|
|
"entropy": 5.596986770629883,
|
|
"epoch": 2.1235486211901304,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004548635565300759,
|
|
"loss": 5.2566,
|
|
"mean_token_accuracy": 0.18599195629358292,
|
|
"num_tokens": 48576313.0,
|
|
"step": 23410
|
|
},
|
|
{
|
|
"entropy": 5.536003303527832,
|
|
"epoch": 2.1240021770682147,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004548441146840449,
|
|
"loss": 5.2248,
|
|
"mean_token_accuracy": 0.18671382665634156,
|
|
"num_tokens": 48587133.0,
|
|
"step": 23415
|
|
},
|
|
{
|
|
"entropy": 5.593124008178711,
|
|
"epoch": 2.124455732946299,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00045482466911879184,
|
|
"loss": 5.3599,
|
|
"mean_token_accuracy": 0.18328820466995238,
|
|
"num_tokens": 48598524.0,
|
|
"step": 23420
|
|
},
|
|
{
|
|
"entropy": 5.460141658782959,
|
|
"epoch": 2.1249092888243832,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045480521983471875,
|
|
"loss": 5.2084,
|
|
"mean_token_accuracy": 0.18777912706136704,
|
|
"num_tokens": 48609870.0,
|
|
"step": 23425
|
|
},
|
|
{
|
|
"entropy": 5.5559361457824705,
|
|
"epoch": 2.1253628447024675,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004547857668322279,
|
|
"loss": 5.2419,
|
|
"mean_token_accuracy": 0.18906091749668122,
|
|
"num_tokens": 48619828.0,
|
|
"step": 23430
|
|
},
|
|
{
|
|
"entropy": 5.505760669708252,
|
|
"epoch": 2.1258164005805513,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004547663101117215,
|
|
"loss": 5.185,
|
|
"mean_token_accuracy": 0.19073476046323776,
|
|
"num_tokens": 48630361.0,
|
|
"step": 23435
|
|
},
|
|
{
|
|
"entropy": 5.530551433563232,
|
|
"epoch": 2.1262699564586356,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00045474684967360216,
|
|
"loss": 5.2146,
|
|
"mean_token_accuracy": 0.17668013274669647,
|
|
"num_tokens": 48641113.0,
|
|
"step": 23440
|
|
},
|
|
{
|
|
"entropy": 5.6428464412689205,
|
|
"epoch": 2.12672351233672,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.000454727385518272,
|
|
"loss": 5.306,
|
|
"mean_token_accuracy": 0.17429667264223098,
|
|
"num_tokens": 48651777.0,
|
|
"step": 23445
|
|
},
|
|
{
|
|
"entropy": 5.620138692855835,
|
|
"epoch": 2.127177068214804,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004547079176461338,
|
|
"loss": 5.3566,
|
|
"mean_token_accuracy": 0.17666784673929214,
|
|
"num_tokens": 48663237.0,
|
|
"step": 23450
|
|
},
|
|
{
|
|
"entropy": 5.4850727081298825,
|
|
"epoch": 2.1276306240928884,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004546884460575901,
|
|
"loss": 5.2269,
|
|
"mean_token_accuracy": 0.1928386464715004,
|
|
"num_tokens": 48673932.0,
|
|
"step": 23455
|
|
},
|
|
{
|
|
"entropy": 5.515140390396118,
|
|
"epoch": 2.1280841799709727,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004546689707530434,
|
|
"loss": 5.1553,
|
|
"mean_token_accuracy": 0.19041721820831298,
|
|
"num_tokens": 48684304.0,
|
|
"step": 23460
|
|
},
|
|
{
|
|
"entropy": 5.514015054702758,
|
|
"epoch": 2.1285377358490565,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00045464949173289676,
|
|
"loss": 5.1324,
|
|
"mean_token_accuracy": 0.1894081339240074,
|
|
"num_tokens": 48695569.0,
|
|
"step": 23465
|
|
},
|
|
{
|
|
"entropy": 5.479301452636719,
|
|
"epoch": 2.1289912917271407,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004546300089975528,
|
|
"loss": 5.2148,
|
|
"mean_token_accuracy": 0.18794697076082229,
|
|
"num_tokens": 48706550.0,
|
|
"step": 23470
|
|
},
|
|
{
|
|
"entropy": 5.564679288864136,
|
|
"epoch": 2.129444847605225,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045461052254741445,
|
|
"loss": 5.2783,
|
|
"mean_token_accuracy": 0.1785402163863182,
|
|
"num_tokens": 48716852.0,
|
|
"step": 23475
|
|
},
|
|
{
|
|
"entropy": 5.488575458526611,
|
|
"epoch": 2.1298984034833093,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.00045459103238288474,
|
|
"loss": 5.168,
|
|
"mean_token_accuracy": 0.18758633136749267,
|
|
"num_tokens": 48726607.0,
|
|
"step": 23480
|
|
},
|
|
{
|
|
"entropy": 5.572689628601074,
|
|
"epoch": 2.130351959361393,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004545715385043667,
|
|
"loss": 5.3746,
|
|
"mean_token_accuracy": 0.17686063647270203,
|
|
"num_tokens": 48738011.0,
|
|
"step": 23485
|
|
},
|
|
{
|
|
"entropy": 5.602808332443237,
|
|
"epoch": 2.1308055152394774,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004545520409122635,
|
|
"loss": 5.2627,
|
|
"mean_token_accuracy": 0.17963460683822632,
|
|
"num_tokens": 48747899.0,
|
|
"step": 23490
|
|
},
|
|
{
|
|
"entropy": 5.569302654266357,
|
|
"epoch": 2.1312590711175616,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004545325396069783,
|
|
"loss": 5.2745,
|
|
"mean_token_accuracy": 0.1831532746553421,
|
|
"num_tokens": 48758719.0,
|
|
"step": 23495
|
|
},
|
|
{
|
|
"entropy": 5.606571435928345,
|
|
"epoch": 2.131712626995646,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004545130345889145,
|
|
"loss": 5.3033,
|
|
"mean_token_accuracy": 0.18162241876125335,
|
|
"num_tokens": 48769677.0,
|
|
"step": 23500
|
|
},
|
|
{
|
|
"entropy": 5.5069633483886715,
|
|
"epoch": 2.13216618287373,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004544935258584754,
|
|
"loss": 5.251,
|
|
"mean_token_accuracy": 0.17889445126056672,
|
|
"num_tokens": 48778440.0,
|
|
"step": 23505
|
|
},
|
|
{
|
|
"entropy": 5.6102362155914305,
|
|
"epoch": 2.1326197387518144,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004544740134160644,
|
|
"loss": 5.3281,
|
|
"mean_token_accuracy": 0.17688387781381607,
|
|
"num_tokens": 48788328.0,
|
|
"step": 23510
|
|
},
|
|
{
|
|
"entropy": 5.583460283279419,
|
|
"epoch": 2.1330732946298983,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004544544972620851,
|
|
"loss": 5.2836,
|
|
"mean_token_accuracy": 0.17650232911109925,
|
|
"num_tokens": 48799218.0,
|
|
"step": 23515
|
|
},
|
|
{
|
|
"entropy": 5.575055742263794,
|
|
"epoch": 2.1335268505079825,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004544349773969411,
|
|
"loss": 5.2235,
|
|
"mean_token_accuracy": 0.17890469133853912,
|
|
"num_tokens": 48809648.0,
|
|
"step": 23520
|
|
},
|
|
{
|
|
"entropy": 5.573635625839233,
|
|
"epoch": 2.133980406386067,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004544154538210359,
|
|
"loss": 5.2429,
|
|
"mean_token_accuracy": 0.18026207536458969,
|
|
"num_tokens": 48819965.0,
|
|
"step": 23525
|
|
},
|
|
{
|
|
"entropy": 5.616595602035522,
|
|
"epoch": 2.134433962264151,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004543959265347735,
|
|
"loss": 5.3127,
|
|
"mean_token_accuracy": 0.18344487994909286,
|
|
"num_tokens": 48829862.0,
|
|
"step": 23530
|
|
},
|
|
{
|
|
"entropy": 5.561789274215698,
|
|
"epoch": 2.1348875181422353,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00045437639553855757,
|
|
"loss": 5.2305,
|
|
"mean_token_accuracy": 0.184020534157753,
|
|
"num_tokens": 48840551.0,
|
|
"step": 23535
|
|
},
|
|
{
|
|
"entropy": 5.477449989318847,
|
|
"epoch": 2.135341074020319,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004543568608327921,
|
|
"loss": 5.2448,
|
|
"mean_token_accuracy": 0.19140903502702714,
|
|
"num_tokens": 48851032.0,
|
|
"step": 23540
|
|
},
|
|
{
|
|
"entropy": 5.484786891937256,
|
|
"epoch": 2.1357946298984034,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00045433732241788105,
|
|
"loss": 5.3019,
|
|
"mean_token_accuracy": 0.17777798175811768,
|
|
"num_tokens": 48861773.0,
|
|
"step": 23545
|
|
},
|
|
{
|
|
"entropy": 5.57232894897461,
|
|
"epoch": 2.1362481857764877,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.00045431778029422846,
|
|
"loss": 5.3318,
|
|
"mean_token_accuracy": 0.1819698616862297,
|
|
"num_tokens": 48872430.0,
|
|
"step": 23550
|
|
},
|
|
{
|
|
"entropy": 5.558100414276123,
|
|
"epoch": 2.136701741654572,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004542982344622385,
|
|
"loss": 5.1259,
|
|
"mean_token_accuracy": 0.18951501697301865,
|
|
"num_tokens": 48882575.0,
|
|
"step": 23555
|
|
},
|
|
{
|
|
"entropy": 5.492110633850098,
|
|
"epoch": 2.137155297532656,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045427868492231533,
|
|
"loss": 5.2206,
|
|
"mean_token_accuracy": 0.18477199971675873,
|
|
"num_tokens": 48893337.0,
|
|
"step": 23560
|
|
},
|
|
{
|
|
"entropy": 5.6229753494262695,
|
|
"epoch": 2.13760885341074,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00045425913167486333,
|
|
"loss": 5.3911,
|
|
"mean_token_accuracy": 0.1793430492281914,
|
|
"num_tokens": 48904675.0,
|
|
"step": 23565
|
|
},
|
|
{
|
|
"entropy": 5.534790086746216,
|
|
"epoch": 2.1380624092888243,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00045423957472028677,
|
|
"loss": 5.1756,
|
|
"mean_token_accuracy": 0.19572654366493225,
|
|
"num_tokens": 48914831.0,
|
|
"step": 23570
|
|
},
|
|
{
|
|
"entropy": 5.45021686553955,
|
|
"epoch": 2.1385159651669086,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004542200140589901,
|
|
"loss": 5.1495,
|
|
"mean_token_accuracy": 0.18653791695833205,
|
|
"num_tokens": 48924574.0,
|
|
"step": 23575
|
|
},
|
|
{
|
|
"entropy": 5.527271175384522,
|
|
"epoch": 2.138969521044993,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00045420044969137787,
|
|
"loss": 5.27,
|
|
"mean_token_accuracy": 0.19084595143795013,
|
|
"num_tokens": 48933921.0,
|
|
"step": 23580
|
|
},
|
|
{
|
|
"entropy": 5.544913911819458,
|
|
"epoch": 2.139423076923077,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004541808816178547,
|
|
"loss": 5.236,
|
|
"mean_token_accuracy": 0.1856432482600212,
|
|
"num_tokens": 48944571.0,
|
|
"step": 23585
|
|
},
|
|
{
|
|
"entropy": 5.553588962554931,
|
|
"epoch": 2.139876632801161,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00045416130983882524,
|
|
"loss": 5.2707,
|
|
"mean_token_accuracy": 0.1828185185790062,
|
|
"num_tokens": 48954569.0,
|
|
"step": 23590
|
|
},
|
|
{
|
|
"entropy": 5.535702896118164,
|
|
"epoch": 2.140330188679245,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00045414173435469427,
|
|
"loss": 5.2245,
|
|
"mean_token_accuracy": 0.1847543463110924,
|
|
"num_tokens": 48965886.0,
|
|
"step": 23595
|
|
},
|
|
{
|
|
"entropy": 5.542579460144043,
|
|
"epoch": 2.1407837445573294,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00045412215516586654,
|
|
"loss": 5.2373,
|
|
"mean_token_accuracy": 0.18331113010644912,
|
|
"num_tokens": 48976219.0,
|
|
"step": 23600
|
|
},
|
|
{
|
|
"entropy": 5.486555576324463,
|
|
"epoch": 2.1412373004354137,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.000454102572272747,
|
|
"loss": 5.2248,
|
|
"mean_token_accuracy": 0.1810384511947632,
|
|
"num_tokens": 48986322.0,
|
|
"step": 23605
|
|
},
|
|
{
|
|
"entropy": 5.527420091629028,
|
|
"epoch": 2.141690856313498,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004540829856757406,
|
|
"loss": 5.1578,
|
|
"mean_token_accuracy": 0.19207797795534134,
|
|
"num_tokens": 48996297.0,
|
|
"step": 23610
|
|
},
|
|
{
|
|
"entropy": 5.528951930999756,
|
|
"epoch": 2.142144412191582,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004540633953752525,
|
|
"loss": 5.2433,
|
|
"mean_token_accuracy": 0.18835059702396392,
|
|
"num_tokens": 49006165.0,
|
|
"step": 23615
|
|
},
|
|
{
|
|
"entropy": 5.520523118972778,
|
|
"epoch": 2.142597968069666,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004540438013716876,
|
|
"loss": 5.1898,
|
|
"mean_token_accuracy": 0.17799636274576186,
|
|
"num_tokens": 49017278.0,
|
|
"step": 23620
|
|
},
|
|
{
|
|
"entropy": 5.457895421981812,
|
|
"epoch": 2.1430515239477503,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004540242036654514,
|
|
"loss": 5.2127,
|
|
"mean_token_accuracy": 0.17904087901115417,
|
|
"num_tokens": 49027088.0,
|
|
"step": 23625
|
|
},
|
|
{
|
|
"entropy": 5.529484844207763,
|
|
"epoch": 2.1435050798258346,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000454004602256949,
|
|
"loss": 5.1433,
|
|
"mean_token_accuracy": 0.18626231849193572,
|
|
"num_tokens": 49038156.0,
|
|
"step": 23630
|
|
},
|
|
{
|
|
"entropy": 5.527454137802124,
|
|
"epoch": 2.143958635703919,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004539849971465858,
|
|
"loss": 5.2457,
|
|
"mean_token_accuracy": 0.18078603744506835,
|
|
"num_tokens": 49047480.0,
|
|
"step": 23635
|
|
},
|
|
{
|
|
"entropy": 5.537511777877808,
|
|
"epoch": 2.1444121915820027,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00045396538833476725,
|
|
"loss": 5.2782,
|
|
"mean_token_accuracy": 0.18552188575267792,
|
|
"num_tokens": 49057373.0,
|
|
"step": 23640
|
|
},
|
|
{
|
|
"entropy": 5.558531618118286,
|
|
"epoch": 2.144865747460087,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004539457758218989,
|
|
"loss": 5.2533,
|
|
"mean_token_accuracy": 0.18661893606185914,
|
|
"num_tokens": 49068380.0,
|
|
"step": 23645
|
|
},
|
|
{
|
|
"entropy": 5.523972034454346,
|
|
"epoch": 2.1453193033381712,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004539261596083863,
|
|
"loss": 5.2496,
|
|
"mean_token_accuracy": 0.18654801845550537,
|
|
"num_tokens": 49078646.0,
|
|
"step": 23650
|
|
},
|
|
{
|
|
"entropy": 5.514596939086914,
|
|
"epoch": 2.1457728592162555,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004539065396946351,
|
|
"loss": 5.1831,
|
|
"mean_token_accuracy": 0.19482836425304412,
|
|
"num_tokens": 49089281.0,
|
|
"step": 23655
|
|
},
|
|
{
|
|
"entropy": 5.5675867080688475,
|
|
"epoch": 2.1462264150943398,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004538869160810511,
|
|
"loss": 5.2478,
|
|
"mean_token_accuracy": 0.1848730206489563,
|
|
"num_tokens": 49099514.0,
|
|
"step": 23660
|
|
},
|
|
{
|
|
"entropy": 5.5800450325012205,
|
|
"epoch": 2.146679970972424,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045386728876804,
|
|
"loss": 5.2953,
|
|
"mean_token_accuracy": 0.18286470472812652,
|
|
"num_tokens": 49110247.0,
|
|
"step": 23665
|
|
},
|
|
{
|
|
"entropy": 5.605365991592407,
|
|
"epoch": 2.147133526850508,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00045384765775600787,
|
|
"loss": 5.3329,
|
|
"mean_token_accuracy": 0.1784706234931946,
|
|
"num_tokens": 49122492.0,
|
|
"step": 23670
|
|
},
|
|
{
|
|
"entropy": 5.528875255584717,
|
|
"epoch": 2.147587082728592,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004538280230453606,
|
|
"loss": 5.2154,
|
|
"mean_token_accuracy": 0.1879258632659912,
|
|
"num_tokens": 49132395.0,
|
|
"step": 23675
|
|
},
|
|
{
|
|
"entropy": 5.598564481735229,
|
|
"epoch": 2.1480406386066764,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004538083846365042,
|
|
"loss": 5.2645,
|
|
"mean_token_accuracy": 0.18835472017526628,
|
|
"num_tokens": 49142909.0,
|
|
"step": 23680
|
|
},
|
|
{
|
|
"entropy": 5.54509162902832,
|
|
"epoch": 2.1484941944847606,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004537887425298448,
|
|
"loss": 5.2213,
|
|
"mean_token_accuracy": 0.18041691780090333,
|
|
"num_tokens": 49152933.0,
|
|
"step": 23685
|
|
},
|
|
{
|
|
"entropy": 5.496678304672241,
|
|
"epoch": 2.1489477503628445,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00045376909672578875,
|
|
"loss": 5.1913,
|
|
"mean_token_accuracy": 0.19037156105041503,
|
|
"num_tokens": 49163595.0,
|
|
"step": 23690
|
|
},
|
|
{
|
|
"entropy": 5.513009309768677,
|
|
"epoch": 2.1494013062409287,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004537494472247422,
|
|
"loss": 5.2067,
|
|
"mean_token_accuracy": 0.18977898955345154,
|
|
"num_tokens": 49174664.0,
|
|
"step": 23695
|
|
},
|
|
{
|
|
"entropy": 5.569059991836548,
|
|
"epoch": 2.149854862119013,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004537297940271115,
|
|
"loss": 5.2709,
|
|
"mean_token_accuracy": 0.18595193028450013,
|
|
"num_tokens": 49185105.0,
|
|
"step": 23700
|
|
},
|
|
{
|
|
"entropy": 5.446787691116333,
|
|
"epoch": 2.1503084179970973,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004537101371333031,
|
|
"loss": 5.1732,
|
|
"mean_token_accuracy": 0.1884971171617508,
|
|
"num_tokens": 49194679.0,
|
|
"step": 23705
|
|
},
|
|
{
|
|
"entropy": 5.485320281982422,
|
|
"epoch": 2.1507619738751815,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045369047654372356,
|
|
"loss": 5.1386,
|
|
"mean_token_accuracy": 0.18643070459365846,
|
|
"num_tokens": 49204563.0,
|
|
"step": 23710
|
|
},
|
|
{
|
|
"entropy": 5.5924159526824955,
|
|
"epoch": 2.151215529753266,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004536708122587795,
|
|
"loss": 5.215,
|
|
"mean_token_accuracy": 0.18975315243005753,
|
|
"num_tokens": 49213759.0,
|
|
"step": 23715
|
|
},
|
|
{
|
|
"entropy": 5.458385562896728,
|
|
"epoch": 2.1516690856313496,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004536511442788774,
|
|
"loss": 5.1077,
|
|
"mean_token_accuracy": 0.19501331001520156,
|
|
"num_tokens": 49223604.0,
|
|
"step": 23720
|
|
},
|
|
{
|
|
"entropy": 5.485271358489991,
|
|
"epoch": 2.152122641509434,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004536314726044241,
|
|
"loss": 5.2582,
|
|
"mean_token_accuracy": 0.18416979163885117,
|
|
"num_tokens": 49234000.0,
|
|
"step": 23725
|
|
},
|
|
{
|
|
"entropy": 5.570834064483643,
|
|
"epoch": 2.152576197387518,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00045361179723582654,
|
|
"loss": 5.212,
|
|
"mean_token_accuracy": 0.18378099352121352,
|
|
"num_tokens": 49244874.0,
|
|
"step": 23730
|
|
},
|
|
{
|
|
"entropy": 5.627907848358154,
|
|
"epoch": 2.1530297532656024,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004535921181734914,
|
|
"loss": 5.4201,
|
|
"mean_token_accuracy": 0.17902245372533798,
|
|
"num_tokens": 49255495.0,
|
|
"step": 23735
|
|
},
|
|
{
|
|
"entropy": 5.579271745681763,
|
|
"epoch": 2.1534833091436867,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004535724354178257,
|
|
"loss": 5.1792,
|
|
"mean_token_accuracy": 0.18805274963378907,
|
|
"num_tokens": 49265357.0,
|
|
"step": 23740
|
|
},
|
|
{
|
|
"entropy": 5.548789548873901,
|
|
"epoch": 2.1539368650217705,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.00045355274896923664,
|
|
"loss": 5.3175,
|
|
"mean_token_accuracy": 0.17559544146060943,
|
|
"num_tokens": 49276396.0,
|
|
"step": 23745
|
|
},
|
|
{
|
|
"entropy": 5.513066291809082,
|
|
"epoch": 2.1543904208998548,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004535330588281312,
|
|
"loss": 5.1409,
|
|
"mean_token_accuracy": 0.1905217707157135,
|
|
"num_tokens": 49285925.0,
|
|
"step": 23750
|
|
},
|
|
{
|
|
"entropy": 5.471875429153442,
|
|
"epoch": 2.154843976777939,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004535133649949166,
|
|
"loss": 5.2346,
|
|
"mean_token_accuracy": 0.18743821680545808,
|
|
"num_tokens": 49296493.0,
|
|
"step": 23755
|
|
},
|
|
{
|
|
"entropy": 5.503355979919434,
|
|
"epoch": 2.1552975326560233,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004534936674700001,
|
|
"loss": 5.1618,
|
|
"mean_token_accuracy": 0.19320950508117676,
|
|
"num_tokens": 49307273.0,
|
|
"step": 23760
|
|
},
|
|
{
|
|
"entropy": 5.5043933391571045,
|
|
"epoch": 2.1557510885341076,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00045347396625378914,
|
|
"loss": 5.1587,
|
|
"mean_token_accuracy": 0.19420345574617387,
|
|
"num_tokens": 49317055.0,
|
|
"step": 23765
|
|
},
|
|
{
|
|
"entropy": 5.532133293151856,
|
|
"epoch": 2.1562046444121914,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00045345426134669103,
|
|
"loss": 5.2431,
|
|
"mean_token_accuracy": 0.18028467893600464,
|
|
"num_tokens": 49327420.0,
|
|
"step": 23770
|
|
},
|
|
{
|
|
"entropy": 5.488499784469605,
|
|
"epoch": 2.1566582002902757,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00045343455274911325,
|
|
"loss": 5.3045,
|
|
"mean_token_accuracy": 0.18351339548826218,
|
|
"num_tokens": 49338323.0,
|
|
"step": 23775
|
|
},
|
|
{
|
|
"entropy": 5.590408086776733,
|
|
"epoch": 2.15711175616836,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004534148404614635,
|
|
"loss": 5.2681,
|
|
"mean_token_accuracy": 0.18426342755556108,
|
|
"num_tokens": 49348364.0,
|
|
"step": 23780
|
|
},
|
|
{
|
|
"entropy": 5.607063961029053,
|
|
"epoch": 2.157565312046444,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00045339512448414943,
|
|
"loss": 5.275,
|
|
"mean_token_accuracy": 0.18968066126108168,
|
|
"num_tokens": 49358274.0,
|
|
"step": 23785
|
|
},
|
|
{
|
|
"entropy": 5.498753070831299,
|
|
"epoch": 2.1580188679245285,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004533754048175787,
|
|
"loss": 5.1541,
|
|
"mean_token_accuracy": 0.18107390850782396,
|
|
"num_tokens": 49368651.0,
|
|
"step": 23790
|
|
},
|
|
{
|
|
"entropy": 5.488153457641602,
|
|
"epoch": 2.1584724238026123,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004533556814621591,
|
|
"loss": 5.1734,
|
|
"mean_token_accuracy": 0.1834540531039238,
|
|
"num_tokens": 49378363.0,
|
|
"step": 23795
|
|
},
|
|
{
|
|
"entropy": 5.516530990600586,
|
|
"epoch": 2.1589259796806965,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.00045333595441829865,
|
|
"loss": 5.1978,
|
|
"mean_token_accuracy": 0.18973224610090256,
|
|
"num_tokens": 49388241.0,
|
|
"step": 23800
|
|
},
|
|
{
|
|
"entropy": 5.506728267669677,
|
|
"epoch": 2.159379535558781,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004533162236864051,
|
|
"loss": 5.1892,
|
|
"mean_token_accuracy": 0.1860138088464737,
|
|
"num_tokens": 49397678.0,
|
|
"step": 23805
|
|
},
|
|
{
|
|
"entropy": 5.543123483657837,
|
|
"epoch": 2.159833091436865,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004532964892668867,
|
|
"loss": 5.3011,
|
|
"mean_token_accuracy": 0.18222862780094146,
|
|
"num_tokens": 49407368.0,
|
|
"step": 23810
|
|
},
|
|
{
|
|
"entropy": 5.5107865810394285,
|
|
"epoch": 2.1602866473149493,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00045327675116015146,
|
|
"loss": 5.1993,
|
|
"mean_token_accuracy": 0.18793988227844238,
|
|
"num_tokens": 49417926.0,
|
|
"step": 23815
|
|
},
|
|
{
|
|
"entropy": 5.5844484806060795,
|
|
"epoch": 2.1607402031930336,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004532570093666075,
|
|
"loss": 5.3287,
|
|
"mean_token_accuracy": 0.17421953678131102,
|
|
"num_tokens": 49427899.0,
|
|
"step": 23820
|
|
},
|
|
{
|
|
"entropy": 5.5534200191497805,
|
|
"epoch": 2.1611937590711174,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004532372638866633,
|
|
"loss": 5.1858,
|
|
"mean_token_accuracy": 0.19405387938022614,
|
|
"num_tokens": 49439102.0,
|
|
"step": 23825
|
|
},
|
|
{
|
|
"entropy": 5.469966697692871,
|
|
"epoch": 2.1616473149492017,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045321751472072693,
|
|
"loss": 5.1291,
|
|
"mean_token_accuracy": 0.19439317137002946,
|
|
"num_tokens": 49448013.0,
|
|
"step": 23830
|
|
},
|
|
{
|
|
"entropy": 5.397324800491333,
|
|
"epoch": 2.162100870827286,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045319776186920695,
|
|
"loss": 5.191,
|
|
"mean_token_accuracy": 0.19246648252010345,
|
|
"num_tokens": 49457620.0,
|
|
"step": 23835
|
|
},
|
|
{
|
|
"entropy": 5.489075183868408,
|
|
"epoch": 2.1625544267053702,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045317800533251193,
|
|
"loss": 5.2116,
|
|
"mean_token_accuracy": 0.18259596228599548,
|
|
"num_tokens": 49468038.0,
|
|
"step": 23840
|
|
},
|
|
{
|
|
"entropy": 5.5078418254852295,
|
|
"epoch": 2.163007982583454,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045315824511105027,
|
|
"loss": 5.1463,
|
|
"mean_token_accuracy": 0.18916950672864913,
|
|
"num_tokens": 49477714.0,
|
|
"step": 23845
|
|
},
|
|
{
|
|
"entropy": 5.560369968414307,
|
|
"epoch": 2.1634615384615383,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045313848120523073,
|
|
"loss": 5.1594,
|
|
"mean_token_accuracy": 0.18786828815937043,
|
|
"num_tokens": 49488214.0,
|
|
"step": 23850
|
|
},
|
|
{
|
|
"entropy": 5.487946462631226,
|
|
"epoch": 2.1639150943396226,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045311871361546205,
|
|
"loss": 5.2833,
|
|
"mean_token_accuracy": 0.18800524175167083,
|
|
"num_tokens": 49498444.0,
|
|
"step": 23855
|
|
},
|
|
{
|
|
"entropy": 5.468801593780517,
|
|
"epoch": 2.164368650217707,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004530989423421529,
|
|
"loss": 5.1339,
|
|
"mean_token_accuracy": 0.1893084689974785,
|
|
"num_tokens": 49508759.0,
|
|
"step": 23860
|
|
},
|
|
{
|
|
"entropy": 5.431907987594604,
|
|
"epoch": 2.164822206095791,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045307916738571223,
|
|
"loss": 5.0784,
|
|
"mean_token_accuracy": 0.19418512731790544,
|
|
"num_tokens": 49518787.0,
|
|
"step": 23865
|
|
},
|
|
{
|
|
"entropy": 5.4640082836151125,
|
|
"epoch": 2.1652757619738754,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004530593887465491,
|
|
"loss": 5.1857,
|
|
"mean_token_accuracy": 0.19431376159191133,
|
|
"num_tokens": 49528130.0,
|
|
"step": 23870
|
|
},
|
|
{
|
|
"entropy": 5.587690925598144,
|
|
"epoch": 2.165729317851959,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00045303960642507235,
|
|
"loss": 5.3763,
|
|
"mean_token_accuracy": 0.18270596265792846,
|
|
"num_tokens": 49539128.0,
|
|
"step": 23875
|
|
},
|
|
{
|
|
"entropy": 5.47186393737793,
|
|
"epoch": 2.1661828737300435,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045301982042169123,
|
|
"loss": 5.2468,
|
|
"mean_token_accuracy": 0.18942346274852753,
|
|
"num_tokens": 49550571.0,
|
|
"step": 23880
|
|
},
|
|
{
|
|
"entropy": 5.540140438079834,
|
|
"epoch": 2.1666364296081277,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00045300003073681485,
|
|
"loss": 5.2439,
|
|
"mean_token_accuracy": 0.18797926008701324,
|
|
"num_tokens": 49561106.0,
|
|
"step": 23885
|
|
},
|
|
{
|
|
"entropy": 5.472275161743164,
|
|
"epoch": 2.167089985486212,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045298023737085243,
|
|
"loss": 5.1218,
|
|
"mean_token_accuracy": 0.1873560979962349,
|
|
"num_tokens": 49571389.0,
|
|
"step": 23890
|
|
},
|
|
{
|
|
"entropy": 5.462834405899048,
|
|
"epoch": 2.1675435413642963,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004529604403242134,
|
|
"loss": 5.2199,
|
|
"mean_token_accuracy": 0.18892295509576798,
|
|
"num_tokens": 49582224.0,
|
|
"step": 23895
|
|
},
|
|
{
|
|
"entropy": 5.502124834060669,
|
|
"epoch": 2.16799709724238,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045294063959730707,
|
|
"loss": 5.2401,
|
|
"mean_token_accuracy": 0.18107422292232514,
|
|
"num_tokens": 49592413.0,
|
|
"step": 23900
|
|
},
|
|
{
|
|
"entropy": 5.567758369445801,
|
|
"epoch": 2.1684506531204644,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045292083519054297,
|
|
"loss": 5.3142,
|
|
"mean_token_accuracy": 0.17169708460569383,
|
|
"num_tokens": 49602796.0,
|
|
"step": 23905
|
|
},
|
|
{
|
|
"entropy": 5.515660095214844,
|
|
"epoch": 2.1689042089985486,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004529010271043307,
|
|
"loss": 5.1736,
|
|
"mean_token_accuracy": 0.1908756226301193,
|
|
"num_tokens": 49613625.0,
|
|
"step": 23910
|
|
},
|
|
{
|
|
"entropy": 5.625437784194946,
|
|
"epoch": 2.169357764876633,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045288121533907977,
|
|
"loss": 5.321,
|
|
"mean_token_accuracy": 0.1820809856057167,
|
|
"num_tokens": 49624719.0,
|
|
"step": 23915
|
|
},
|
|
{
|
|
"entropy": 5.544964838027954,
|
|
"epoch": 2.169811320754717,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045286139989520006,
|
|
"loss": 5.2688,
|
|
"mean_token_accuracy": 0.18213230669498442,
|
|
"num_tokens": 49634916.0,
|
|
"step": 23920
|
|
},
|
|
{
|
|
"entropy": 5.510926055908203,
|
|
"epoch": 2.170264876632801,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004528415807731012,
|
|
"loss": 5.1688,
|
|
"mean_token_accuracy": 0.1872358351945877,
|
|
"num_tokens": 49645215.0,
|
|
"step": 23925
|
|
},
|
|
{
|
|
"entropy": 5.508106374740601,
|
|
"epoch": 2.1707184325108853,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00045282175797319317,
|
|
"loss": 5.2362,
|
|
"mean_token_accuracy": 0.19037553071975707,
|
|
"num_tokens": 49655805.0,
|
|
"step": 23930
|
|
},
|
|
{
|
|
"entropy": 5.584711599349975,
|
|
"epoch": 2.1711719883889695,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004528019314958859,
|
|
"loss": 5.2384,
|
|
"mean_token_accuracy": 0.1876452460885048,
|
|
"num_tokens": 49665264.0,
|
|
"step": 23935
|
|
},
|
|
{
|
|
"entropy": 5.571161079406738,
|
|
"epoch": 2.171625544267054,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00045278210134158935,
|
|
"loss": 5.2822,
|
|
"mean_token_accuracy": 0.1823883518576622,
|
|
"num_tokens": 49676152.0,
|
|
"step": 23940
|
|
},
|
|
{
|
|
"entropy": 5.557181787490845,
|
|
"epoch": 2.172079100145138,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004527622675107137,
|
|
"loss": 5.2261,
|
|
"mean_token_accuracy": 0.18117580860853194,
|
|
"num_tokens": 49686762.0,
|
|
"step": 23945
|
|
},
|
|
{
|
|
"entropy": 5.525688648223877,
|
|
"epoch": 2.172532656023222,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00045274243000366897,
|
|
"loss": 5.2606,
|
|
"mean_token_accuracy": 0.1876365378499031,
|
|
"num_tokens": 49697504.0,
|
|
"step": 23950
|
|
},
|
|
{
|
|
"entropy": 5.514986276626587,
|
|
"epoch": 2.172986211901306,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004527225888208655,
|
|
"loss": 5.3057,
|
|
"mean_token_accuracy": 0.1764551430940628,
|
|
"num_tokens": 49709197.0,
|
|
"step": 23955
|
|
},
|
|
{
|
|
"entropy": 5.539081239700318,
|
|
"epoch": 2.1734397677793904,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004527027439627137,
|
|
"loss": 5.2599,
|
|
"mean_token_accuracy": 0.18191298693418503,
|
|
"num_tokens": 49719764.0,
|
|
"step": 23960
|
|
},
|
|
{
|
|
"entropy": 5.552999210357666,
|
|
"epoch": 2.1738933236574747,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045268289542962377,
|
|
"loss": 5.2081,
|
|
"mean_token_accuracy": 0.1810215562582016,
|
|
"num_tokens": 49730363.0,
|
|
"step": 23965
|
|
},
|
|
{
|
|
"entropy": 5.525349569320679,
|
|
"epoch": 2.174346879535559,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004526630432220063,
|
|
"loss": 5.2449,
|
|
"mean_token_accuracy": 0.1780279040336609,
|
|
"num_tokens": 49741037.0,
|
|
"step": 23970
|
|
},
|
|
{
|
|
"entropy": 5.476911211013794,
|
|
"epoch": 2.1748004354136428,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004526431873402719,
|
|
"loss": 5.135,
|
|
"mean_token_accuracy": 0.19056045413017272,
|
|
"num_tokens": 49750127.0,
|
|
"step": 23975
|
|
},
|
|
{
|
|
"entropy": 5.587504291534424,
|
|
"epoch": 2.175253991291727,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.000452623327784831,
|
|
"loss": 5.3541,
|
|
"mean_token_accuracy": 0.17918340861797333,
|
|
"num_tokens": 49760298.0,
|
|
"step": 23980
|
|
},
|
|
{
|
|
"entropy": 5.574003505706787,
|
|
"epoch": 2.1757075471698113,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004526034645560945,
|
|
"loss": 5.2241,
|
|
"mean_token_accuracy": 0.184489506483078,
|
|
"num_tokens": 49770841.0,
|
|
"step": 23985
|
|
},
|
|
{
|
|
"entropy": 5.477240705490113,
|
|
"epoch": 2.1761611030478956,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00045258359765447306,
|
|
"loss": 5.2084,
|
|
"mean_token_accuracy": 0.18433146327733993,
|
|
"num_tokens": 49781000.0,
|
|
"step": 23990
|
|
},
|
|
{
|
|
"entropy": 5.53297700881958,
|
|
"epoch": 2.17661465892598,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004525637270803776,
|
|
"loss": 5.2269,
|
|
"mean_token_accuracy": 0.18725013732910156,
|
|
"num_tokens": 49790886.0,
|
|
"step": 23995
|
|
},
|
|
{
|
|
"entropy": 5.512389183044434,
|
|
"epoch": 2.1770682148040637,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00045254385283421896,
|
|
"loss": 5.222,
|
|
"mean_token_accuracy": 0.19252946227788925,
|
|
"num_tokens": 49801477.0,
|
|
"step": 24000
|
|
},
|
|
{
|
|
"epoch": 2.1770682148040637,
|
|
"eval_entropy": 5.314434872925012,
|
|
"eval_loss": 5.31955099105835,
|
|
"eval_mean_token_accuracy": 0.1898961775830833,
|
|
"eval_num_tokens": 49801477.0,
|
|
"eval_runtime": 26.7104,
|
|
"eval_samples_per_second": 1323.827,
|
|
"eval_steps_per_second": 165.478,
|
|
"step": 24000
|
|
},
|
|
{
|
|
"entropy": 5.541253137588501,
|
|
"epoch": 2.177521770682148,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004525239749164082,
|
|
"loss": 5.2706,
|
|
"mean_token_accuracy": 0.18745269924402236,
|
|
"num_tokens": 49812044.0,
|
|
"step": 24005
|
|
},
|
|
{
|
|
"entropy": 5.455629968643189,
|
|
"epoch": 2.177975326560232,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004525040933273564,
|
|
"loss": 5.1282,
|
|
"mean_token_accuracy": 0.19051404297351837,
|
|
"num_tokens": 49821559.0,
|
|
"step": 24010
|
|
},
|
|
{
|
|
"entropy": 5.5425135612487795,
|
|
"epoch": 2.1784288824383164,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00045248420806747483,
|
|
"loss": 5.3082,
|
|
"mean_token_accuracy": 0.17816372364759445,
|
|
"num_tokens": 49832937.0,
|
|
"step": 24015
|
|
},
|
|
{
|
|
"entropy": 5.575357151031494,
|
|
"epoch": 2.1788824383164007,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004524643191371745,
|
|
"loss": 5.2284,
|
|
"mean_token_accuracy": 0.18884204626083373,
|
|
"num_tokens": 49843176.0,
|
|
"step": 24020
|
|
},
|
|
{
|
|
"entropy": 5.51520185470581,
|
|
"epoch": 2.179335994194485,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045244442653686684,
|
|
"loss": 5.144,
|
|
"mean_token_accuracy": 0.19736648499965667,
|
|
"num_tokens": 49852522.0,
|
|
"step": 24025
|
|
},
|
|
{
|
|
"entropy": 5.437822103500366,
|
|
"epoch": 2.179789550072569,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00045242453026696325,
|
|
"loss": 5.149,
|
|
"mean_token_accuracy": 0.19155023097991944,
|
|
"num_tokens": 49863143.0,
|
|
"step": 24030
|
|
},
|
|
{
|
|
"entropy": 5.549478149414062,
|
|
"epoch": 2.180243105950653,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004524046303278752,
|
|
"loss": 5.2863,
|
|
"mean_token_accuracy": 0.18259314447641373,
|
|
"num_tokens": 49873465.0,
|
|
"step": 24035
|
|
},
|
|
{
|
|
"entropy": 5.61569356918335,
|
|
"epoch": 2.1806966618287373,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004523847267200141,
|
|
"loss": 5.327,
|
|
"mean_token_accuracy": 0.17811169028282164,
|
|
"num_tokens": 49883690.0,
|
|
"step": 24040
|
|
},
|
|
{
|
|
"entropy": 5.554614305496216,
|
|
"epoch": 2.1811502177068216,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00045236481944379165,
|
|
"loss": 5.2882,
|
|
"mean_token_accuracy": 0.18247264623641968,
|
|
"num_tokens": 49894418.0,
|
|
"step": 24045
|
|
},
|
|
{
|
|
"entropy": 5.476203775405883,
|
|
"epoch": 2.1816037735849054,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004523449084996196,
|
|
"loss": 5.151,
|
|
"mean_token_accuracy": 0.19018777459859848,
|
|
"num_tokens": 49903927.0,
|
|
"step": 24050
|
|
},
|
|
{
|
|
"entropy": 5.494016456604004,
|
|
"epoch": 2.1820573294629897,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004523249938879096,
|
|
"loss": 5.2267,
|
|
"mean_token_accuracy": 0.18583659678697587,
|
|
"num_tokens": 49914203.0,
|
|
"step": 24055
|
|
},
|
|
{
|
|
"entropy": 5.520952987670898,
|
|
"epoch": 2.182510885341074,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00045230507560907354,
|
|
"loss": 5.2256,
|
|
"mean_token_accuracy": 0.1864370360970497,
|
|
"num_tokens": 49924320.0,
|
|
"step": 24060
|
|
},
|
|
{
|
|
"entropy": 5.459879159927368,
|
|
"epoch": 2.1829644412191582,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045228515366352334,
|
|
"loss": 5.1666,
|
|
"mean_token_accuracy": 0.189295694231987,
|
|
"num_tokens": 49934634.0,
|
|
"step": 24065
|
|
},
|
|
{
|
|
"entropy": 5.584216547012329,
|
|
"epoch": 2.1834179970972425,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00045226522805167095,
|
|
"loss": 5.2501,
|
|
"mean_token_accuracy": 0.18597296327352525,
|
|
"num_tokens": 49944586.0,
|
|
"step": 24070
|
|
},
|
|
{
|
|
"entropy": 5.51998381614685,
|
|
"epoch": 2.1838715529753268,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004522452987739286,
|
|
"loss": 5.2252,
|
|
"mean_token_accuracy": 0.18600001335144042,
|
|
"num_tokens": 49955441.0,
|
|
"step": 24075
|
|
},
|
|
{
|
|
"entropy": 5.596885824203492,
|
|
"epoch": 2.1843251088534106,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00045222536583070823,
|
|
"loss": 5.3545,
|
|
"mean_token_accuracy": 0.18532377928495408,
|
|
"num_tokens": 49966718.0,
|
|
"step": 24080
|
|
},
|
|
{
|
|
"entropy": 5.57854437828064,
|
|
"epoch": 2.184778664731495,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00045220542922242205,
|
|
"loss": 5.3324,
|
|
"mean_token_accuracy": 0.1777525708079338,
|
|
"num_tokens": 49979483.0,
|
|
"step": 24085
|
|
},
|
|
{
|
|
"entropy": 5.4970146179199215,
|
|
"epoch": 2.185232220609579,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045218548894948254,
|
|
"loss": 5.232,
|
|
"mean_token_accuracy": 0.1874102994799614,
|
|
"num_tokens": 49989976.0,
|
|
"step": 24090
|
|
},
|
|
{
|
|
"entropy": 5.471968317031861,
|
|
"epoch": 2.1856857764876634,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00045216554501230187,
|
|
"loss": 5.1362,
|
|
"mean_token_accuracy": 0.18813505321741103,
|
|
"num_tokens": 50000069.0,
|
|
"step": 24095
|
|
},
|
|
{
|
|
"entropy": 5.523547601699829,
|
|
"epoch": 2.1861393323657476,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004521455974112927,
|
|
"loss": 5.2168,
|
|
"mean_token_accuracy": 0.18920828998088837,
|
|
"num_tokens": 50009970.0,
|
|
"step": 24100
|
|
},
|
|
{
|
|
"entropy": 5.525372123718261,
|
|
"epoch": 2.1865928882438315,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00045212564614686735,
|
|
"loss": 5.2285,
|
|
"mean_token_accuracy": 0.1874394178390503,
|
|
"num_tokens": 50019590.0,
|
|
"step": 24105
|
|
},
|
|
{
|
|
"entropy": 5.487250757217407,
|
|
"epoch": 2.1870464441219157,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004521056912194386,
|
|
"loss": 5.2444,
|
|
"mean_token_accuracy": 0.17620793581008912,
|
|
"num_tokens": 50030092.0,
|
|
"step": 24110
|
|
},
|
|
{
|
|
"entropy": 5.501592206954956,
|
|
"epoch": 2.1875,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004520857326294189,
|
|
"loss": 5.2397,
|
|
"mean_token_accuracy": 0.18218229115009307,
|
|
"num_tokens": 50040318.0,
|
|
"step": 24115
|
|
},
|
|
{
|
|
"entropy": 5.5564045906066895,
|
|
"epoch": 2.1879535558780843,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00045206577037722114,
|
|
"loss": 5.3325,
|
|
"mean_token_accuracy": 0.17281712889671325,
|
|
"num_tokens": 50050507.0,
|
|
"step": 24120
|
|
},
|
|
{
|
|
"entropy": 5.67215929031372,
|
|
"epoch": 2.1884071117561685,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004520458044632582,
|
|
"loss": 5.287,
|
|
"mean_token_accuracy": 0.1852780684828758,
|
|
"num_tokens": 50059727.0,
|
|
"step": 24125
|
|
},
|
|
{
|
|
"entropy": 5.5502830982208256,
|
|
"epoch": 2.1888606676342524,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045202583488794285,
|
|
"loss": 5.2336,
|
|
"mean_token_accuracy": 0.18476210236549379,
|
|
"num_tokens": 50070812.0,
|
|
"step": 24130
|
|
},
|
|
{
|
|
"entropy": 5.525482273101806,
|
|
"epoch": 2.1893142235123366,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004520058616516881,
|
|
"loss": 5.3475,
|
|
"mean_token_accuracy": 0.17417027354240416,
|
|
"num_tokens": 50081175.0,
|
|
"step": 24135
|
|
},
|
|
{
|
|
"entropy": 5.552982568740845,
|
|
"epoch": 2.189767779390421,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00045198588475490716,
|
|
"loss": 5.2078,
|
|
"mean_token_accuracy": 0.1849895089864731,
|
|
"num_tokens": 50092246.0,
|
|
"step": 24140
|
|
},
|
|
{
|
|
"entropy": 5.554775905609131,
|
|
"epoch": 2.190221335268505,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004519659041980129,
|
|
"loss": 5.2746,
|
|
"mean_token_accuracy": 0.18905856609344482,
|
|
"num_tokens": 50101934.0,
|
|
"step": 24145
|
|
},
|
|
{
|
|
"entropy": 5.505129623413086,
|
|
"epoch": 2.1906748911465894,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004519459199814187,
|
|
"loss": 5.2831,
|
|
"mean_token_accuracy": 0.1805013597011566,
|
|
"num_tokens": 50112159.0,
|
|
"step": 24150
|
|
},
|
|
{
|
|
"entropy": 5.522120523452759,
|
|
"epoch": 2.1911284470246732,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004519259321055377,
|
|
"loss": 5.2793,
|
|
"mean_token_accuracy": 0.1831263318657875,
|
|
"num_tokens": 50123079.0,
|
|
"step": 24155
|
|
},
|
|
{
|
|
"entropy": 5.589271354675293,
|
|
"epoch": 2.1915820029027575,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004519059405707834,
|
|
"loss": 5.2233,
|
|
"mean_token_accuracy": 0.18760035037994385,
|
|
"num_tokens": 50133097.0,
|
|
"step": 24160
|
|
},
|
|
{
|
|
"entropy": 5.617005825042725,
|
|
"epoch": 2.1920355587808418,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00045188594537756916,
|
|
"loss": 5.3108,
|
|
"mean_token_accuracy": 0.18454811125993728,
|
|
"num_tokens": 50143062.0,
|
|
"step": 24165
|
|
},
|
|
{
|
|
"entropy": 5.577868127822876,
|
|
"epoch": 2.192489114658926,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045186594652630853,
|
|
"loss": 5.239,
|
|
"mean_token_accuracy": 0.18194850534200668,
|
|
"num_tokens": 50154482.0,
|
|
"step": 24170
|
|
},
|
|
{
|
|
"entropy": 5.541304063796997,
|
|
"epoch": 2.1929426705370103,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.000451845944017415,
|
|
"loss": 5.2193,
|
|
"mean_token_accuracy": 0.18745504021644593,
|
|
"num_tokens": 50164880.0,
|
|
"step": 24175
|
|
},
|
|
{
|
|
"entropy": 5.493355226516724,
|
|
"epoch": 2.1933962264150946,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045182593785130225,
|
|
"loss": 5.1603,
|
|
"mean_token_accuracy": 0.1914045974612236,
|
|
"num_tokens": 50173896.0,
|
|
"step": 24180
|
|
},
|
|
{
|
|
"entropy": 5.548250722885132,
|
|
"epoch": 2.1938497822931784,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004518059280283842,
|
|
"loss": 5.2943,
|
|
"mean_token_accuracy": 0.1798468843102455,
|
|
"num_tokens": 50185078.0,
|
|
"step": 24185
|
|
},
|
|
{
|
|
"entropy": 5.548509359359741,
|
|
"epoch": 2.1943033381712627,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00045178591454907434,
|
|
"loss": 5.2736,
|
|
"mean_token_accuracy": 0.1837758883833885,
|
|
"num_tokens": 50195500.0,
|
|
"step": 24190
|
|
},
|
|
{
|
|
"entropy": 5.492220163345337,
|
|
"epoch": 2.194756894049347,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00045176589741378675,
|
|
"loss": 5.1849,
|
|
"mean_token_accuracy": 0.18536744862794877,
|
|
"num_tokens": 50206103.0,
|
|
"step": 24195
|
|
},
|
|
{
|
|
"entropy": 5.490248775482177,
|
|
"epoch": 2.195210449927431,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004517458766229354,
|
|
"loss": 5.1502,
|
|
"mean_token_accuracy": 0.1876194253563881,
|
|
"num_tokens": 50216522.0,
|
|
"step": 24200
|
|
},
|
|
{
|
|
"entropy": 5.545748329162597,
|
|
"epoch": 2.195664005805515,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00045172585217693426,
|
|
"loss": 5.243,
|
|
"mean_token_accuracy": 0.19047030657529831,
|
|
"num_tokens": 50226721.0,
|
|
"step": 24205
|
|
},
|
|
{
|
|
"entropy": 5.544781494140625,
|
|
"epoch": 2.1961175616835993,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045170582407619747,
|
|
"loss": 5.2938,
|
|
"mean_token_accuracy": 0.18063254058361053,
|
|
"num_tokens": 50236327.0,
|
|
"step": 24210
|
|
},
|
|
{
|
|
"entropy": 5.49363489151001,
|
|
"epoch": 2.1965711175616836,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004516857923211392,
|
|
"loss": 5.1664,
|
|
"mean_token_accuracy": 0.1969466522336006,
|
|
"num_tokens": 50245729.0,
|
|
"step": 24215
|
|
},
|
|
{
|
|
"entropy": 5.6063587188720705,
|
|
"epoch": 2.197024673439768,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00045166575691217375,
|
|
"loss": 5.3553,
|
|
"mean_token_accuracy": 0.17688291370868683,
|
|
"num_tokens": 50257024.0,
|
|
"step": 24220
|
|
},
|
|
{
|
|
"entropy": 5.560926675796509,
|
|
"epoch": 2.197478229317852,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00045164571784971536,
|
|
"loss": 5.1759,
|
|
"mean_token_accuracy": 0.18599977642297744,
|
|
"num_tokens": 50266910.0,
|
|
"step": 24225
|
|
},
|
|
{
|
|
"entropy": 5.524508857727051,
|
|
"epoch": 2.1979317851959363,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00045162567513417864,
|
|
"loss": 5.238,
|
|
"mean_token_accuracy": 0.18662774115800856,
|
|
"num_tokens": 50278233.0,
|
|
"step": 24230
|
|
},
|
|
{
|
|
"entropy": 5.486080694198608,
|
|
"epoch": 2.19838534107402,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00045160562876597776,
|
|
"loss": 5.2003,
|
|
"mean_token_accuracy": 0.1832010567188263,
|
|
"num_tokens": 50289276.0,
|
|
"step": 24235
|
|
},
|
|
{
|
|
"entropy": 5.5235004901885985,
|
|
"epoch": 2.1988388969521044,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004515855787455276,
|
|
"loss": 5.2086,
|
|
"mean_token_accuracy": 0.18494585007429123,
|
|
"num_tokens": 50299336.0,
|
|
"step": 24240
|
|
},
|
|
{
|
|
"entropy": 5.535049200057983,
|
|
"epoch": 2.1992924528301887,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004515655250732426,
|
|
"loss": 5.1828,
|
|
"mean_token_accuracy": 0.1902652144432068,
|
|
"num_tokens": 50308308.0,
|
|
"step": 24245
|
|
},
|
|
{
|
|
"entropy": 5.4933555126190186,
|
|
"epoch": 2.199746008708273,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.00045154546774953764,
|
|
"loss": 5.2162,
|
|
"mean_token_accuracy": 0.187896528840065,
|
|
"num_tokens": 50318295.0,
|
|
"step": 24250
|
|
},
|
|
{
|
|
"entropy": 5.480124759674072,
|
|
"epoch": 2.2001995645863572,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004515254067748274,
|
|
"loss": 5.2253,
|
|
"mean_token_accuracy": 0.19016793072223664,
|
|
"num_tokens": 50329296.0,
|
|
"step": 24255
|
|
},
|
|
{
|
|
"entropy": 5.5384279727935795,
|
|
"epoch": 2.200653120464441,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004515053421495267,
|
|
"loss": 5.2828,
|
|
"mean_token_accuracy": 0.18130358755588533,
|
|
"num_tokens": 50339389.0,
|
|
"step": 24260
|
|
},
|
|
{
|
|
"entropy": 5.58393120765686,
|
|
"epoch": 2.2011066763425253,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00045148527387405056,
|
|
"loss": 5.3001,
|
|
"mean_token_accuracy": 0.17953888773918153,
|
|
"num_tokens": 50349647.0,
|
|
"step": 24265
|
|
},
|
|
{
|
|
"entropy": 5.60192084312439,
|
|
"epoch": 2.2015602322206096,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004514652019488141,
|
|
"loss": 5.3003,
|
|
"mean_token_accuracy": 0.17888210117816924,
|
|
"num_tokens": 50361292.0,
|
|
"step": 24270
|
|
},
|
|
{
|
|
"entropy": 5.501269721984864,
|
|
"epoch": 2.202013788098694,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004514451263742321,
|
|
"loss": 5.1977,
|
|
"mean_token_accuracy": 0.18494318127632142,
|
|
"num_tokens": 50372293.0,
|
|
"step": 24275
|
|
},
|
|
{
|
|
"entropy": 5.489620637893677,
|
|
"epoch": 2.202467343976778,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004514250471507201,
|
|
"loss": 5.175,
|
|
"mean_token_accuracy": 0.19515495598316193,
|
|
"num_tokens": 50382462.0,
|
|
"step": 24280
|
|
},
|
|
{
|
|
"entropy": 5.555467367172241,
|
|
"epoch": 2.202920899854862,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00045140496427869306,
|
|
"loss": 5.2646,
|
|
"mean_token_accuracy": 0.1924166798591614,
|
|
"num_tokens": 50393157.0,
|
|
"step": 24285
|
|
},
|
|
{
|
|
"entropy": 5.447172355651856,
|
|
"epoch": 2.203374455732946,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004513848777585664,
|
|
"loss": 5.1457,
|
|
"mean_token_accuracy": 0.19300558865070344,
|
|
"num_tokens": 50403474.0,
|
|
"step": 24290
|
|
},
|
|
{
|
|
"entropy": 5.540361833572388,
|
|
"epoch": 2.2038280116110305,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004513647875907556,
|
|
"loss": 5.2345,
|
|
"mean_token_accuracy": 0.18396909683942794,
|
|
"num_tokens": 50414337.0,
|
|
"step": 24295
|
|
},
|
|
{
|
|
"entropy": 5.6253026008605955,
|
|
"epoch": 2.2042815674891147,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00045134469377567597,
|
|
"loss": 5.3371,
|
|
"mean_token_accuracy": 0.17733388096094133,
|
|
"num_tokens": 50424863.0,
|
|
"step": 24300
|
|
},
|
|
{
|
|
"entropy": 5.555252552032471,
|
|
"epoch": 2.204735123367199,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004513245963137432,
|
|
"loss": 5.2601,
|
|
"mean_token_accuracy": 0.186156564950943,
|
|
"num_tokens": 50435982.0,
|
|
"step": 24305
|
|
},
|
|
{
|
|
"entropy": 5.47930417060852,
|
|
"epoch": 2.205188679245283,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004513044952053728,
|
|
"loss": 5.1637,
|
|
"mean_token_accuracy": 0.18856670409440995,
|
|
"num_tokens": 50445112.0,
|
|
"step": 24310
|
|
},
|
|
{
|
|
"entropy": 5.4845599174499515,
|
|
"epoch": 2.205642235123367,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00045128439045098045,
|
|
"loss": 5.1526,
|
|
"mean_token_accuracy": 0.19773039370775222,
|
|
"num_tokens": 50455266.0,
|
|
"step": 24315
|
|
},
|
|
{
|
|
"entropy": 5.542871618270874,
|
|
"epoch": 2.2060957910014514,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00045126428205098207,
|
|
"loss": 5.3042,
|
|
"mean_token_accuracy": 0.1725046679377556,
|
|
"num_tokens": 50466930.0,
|
|
"step": 24320
|
|
},
|
|
{
|
|
"entropy": 5.515679025650025,
|
|
"epoch": 2.2065493468795356,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004512441700057934,
|
|
"loss": 5.2361,
|
|
"mean_token_accuracy": 0.18801286220550537,
|
|
"num_tokens": 50477534.0,
|
|
"step": 24325
|
|
},
|
|
{
|
|
"entropy": 5.535473918914795,
|
|
"epoch": 2.20700290275762,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004512240543158305,
|
|
"loss": 5.2141,
|
|
"mean_token_accuracy": 0.1852893963456154,
|
|
"num_tokens": 50487352.0,
|
|
"step": 24330
|
|
},
|
|
{
|
|
"entropy": 5.506581497192383,
|
|
"epoch": 2.2074564586357037,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00045120393498150905,
|
|
"loss": 5.1255,
|
|
"mean_token_accuracy": 0.1947678118944168,
|
|
"num_tokens": 50496227.0,
|
|
"step": 24335
|
|
},
|
|
{
|
|
"entropy": 5.5088152408599855,
|
|
"epoch": 2.207910014513788,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045118381200324537,
|
|
"loss": 5.2559,
|
|
"mean_token_accuracy": 0.18085824996232985,
|
|
"num_tokens": 50507536.0,
|
|
"step": 24340
|
|
},
|
|
{
|
|
"entropy": 5.53237829208374,
|
|
"epoch": 2.2083635703918723,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004511636853814556,
|
|
"loss": 5.227,
|
|
"mean_token_accuracy": 0.19232204854488372,
|
|
"num_tokens": 50517659.0,
|
|
"step": 24345
|
|
},
|
|
{
|
|
"entropy": 5.52504072189331,
|
|
"epoch": 2.2088171262699565,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00045114355511655595,
|
|
"loss": 5.2165,
|
|
"mean_token_accuracy": 0.18096200078725816,
|
|
"num_tokens": 50528717.0,
|
|
"step": 24350
|
|
},
|
|
{
|
|
"entropy": 5.5235038757324215,
|
|
"epoch": 2.209270682148041,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00045112342120896267,
|
|
"loss": 5.1237,
|
|
"mean_token_accuracy": 0.18933966159820556,
|
|
"num_tokens": 50538449.0,
|
|
"step": 24355
|
|
},
|
|
{
|
|
"entropy": 5.520903635025024,
|
|
"epoch": 2.2097242380261246,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00045110328365909215,
|
|
"loss": 5.2876,
|
|
"mean_token_accuracy": 0.18385672122240065,
|
|
"num_tokens": 50549098.0,
|
|
"step": 24360
|
|
},
|
|
{
|
|
"entropy": 5.564284563064575,
|
|
"epoch": 2.210177793904209,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004510831424673609,
|
|
"loss": 5.2763,
|
|
"mean_token_accuracy": 0.18258044272661209,
|
|
"num_tokens": 50560047.0,
|
|
"step": 24365
|
|
},
|
|
{
|
|
"entropy": 5.576068496704101,
|
|
"epoch": 2.210631349782293,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004510629976341853,
|
|
"loss": 5.2009,
|
|
"mean_token_accuracy": 0.18213998824357985,
|
|
"num_tokens": 50569704.0,
|
|
"step": 24370
|
|
},
|
|
{
|
|
"entropy": 5.499861145019532,
|
|
"epoch": 2.2110849056603774,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045104284915998215,
|
|
"loss": 5.2303,
|
|
"mean_token_accuracy": 0.18464716523885727,
|
|
"num_tokens": 50580006.0,
|
|
"step": 24375
|
|
},
|
|
{
|
|
"entropy": 5.441331243515014,
|
|
"epoch": 2.2115384615384617,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00045102269704516793,
|
|
"loss": 5.1907,
|
|
"mean_token_accuracy": 0.19384168833494186,
|
|
"num_tokens": 50589593.0,
|
|
"step": 24380
|
|
},
|
|
{
|
|
"entropy": 5.508224391937256,
|
|
"epoch": 2.211992017416546,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004510025412901595,
|
|
"loss": 5.1637,
|
|
"mean_token_accuracy": 0.1895603433251381,
|
|
"num_tokens": 50598774.0,
|
|
"step": 24385
|
|
},
|
|
{
|
|
"entropy": 5.422340631484985,
|
|
"epoch": 2.2124455732946298,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00045098238189537367,
|
|
"loss": 5.1443,
|
|
"mean_token_accuracy": 0.1966112107038498,
|
|
"num_tokens": 50608815.0,
|
|
"step": 24390
|
|
},
|
|
{
|
|
"entropy": 5.429356813430786,
|
|
"epoch": 2.212899129172714,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045096221886122733,
|
|
"loss": 5.3088,
|
|
"mean_token_accuracy": 0.1919084832072258,
|
|
"num_tokens": 50619255.0,
|
|
"step": 24395
|
|
},
|
|
{
|
|
"entropy": 5.578326940536499,
|
|
"epoch": 2.2133526850507983,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004509420521881375,
|
|
"loss": 5.2271,
|
|
"mean_token_accuracy": 0.18914820551872252,
|
|
"num_tokens": 50629483.0,
|
|
"step": 24400
|
|
},
|
|
{
|
|
"entropy": 5.507671213150024,
|
|
"epoch": 2.2138062409288826,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004509218818765211,
|
|
"loss": 5.1364,
|
|
"mean_token_accuracy": 0.18830680549144746,
|
|
"num_tokens": 50638552.0,
|
|
"step": 24405
|
|
},
|
|
{
|
|
"entropy": 5.506286668777466,
|
|
"epoch": 2.2142597968069664,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00045090170792679544,
|
|
"loss": 5.1547,
|
|
"mean_token_accuracy": 0.18813738375902175,
|
|
"num_tokens": 50648752.0,
|
|
"step": 24410
|
|
},
|
|
{
|
|
"entropy": 5.5299379348754885,
|
|
"epoch": 2.2147133526850507,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00045088153033937765,
|
|
"loss": 5.2136,
|
|
"mean_token_accuracy": 0.18776571303606032,
|
|
"num_tokens": 50658373.0,
|
|
"step": 24415
|
|
},
|
|
{
|
|
"entropy": 5.485628414154053,
|
|
"epoch": 2.215166908563135,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00045086134911468496,
|
|
"loss": 5.2572,
|
|
"mean_token_accuracy": 0.18963996767997743,
|
|
"num_tokens": 50668529.0,
|
|
"step": 24420
|
|
},
|
|
{
|
|
"entropy": 5.529165410995484,
|
|
"epoch": 2.215620464441219,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004508411642531347,
|
|
"loss": 5.1816,
|
|
"mean_token_accuracy": 0.18995936810970307,
|
|
"num_tokens": 50678038.0,
|
|
"step": 24425
|
|
},
|
|
{
|
|
"entropy": 5.5511609554290775,
|
|
"epoch": 2.2160740203193035,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004508209757551445,
|
|
"loss": 5.2319,
|
|
"mean_token_accuracy": 0.19369424134492874,
|
|
"num_tokens": 50687788.0,
|
|
"step": 24430
|
|
},
|
|
{
|
|
"entropy": 5.552525520324707,
|
|
"epoch": 2.2165275761973877,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045080078362113153,
|
|
"loss": 5.2208,
|
|
"mean_token_accuracy": 0.1799136757850647,
|
|
"num_tokens": 50697748.0,
|
|
"step": 24435
|
|
},
|
|
{
|
|
"entropy": 5.462859964370727,
|
|
"epoch": 2.2169811320754715,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00045078058785151363,
|
|
"loss": 5.1473,
|
|
"mean_token_accuracy": 0.19096100479364395,
|
|
"num_tokens": 50707776.0,
|
|
"step": 24440
|
|
},
|
|
{
|
|
"entropy": 5.5224329948425295,
|
|
"epoch": 2.217434687953556,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004507603884467085,
|
|
"loss": 5.2805,
|
|
"mean_token_accuracy": 0.1812685251235962,
|
|
"num_tokens": 50717547.0,
|
|
"step": 24445
|
|
},
|
|
{
|
|
"entropy": 5.5132369041442875,
|
|
"epoch": 2.21788824383164,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004507401854071336,
|
|
"loss": 5.1802,
|
|
"mean_token_accuracy": 0.19472675025463104,
|
|
"num_tokens": 50728446.0,
|
|
"step": 24450
|
|
},
|
|
{
|
|
"entropy": 5.458808374404907,
|
|
"epoch": 2.2183417997097243,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045071997873320687,
|
|
"loss": 5.1289,
|
|
"mean_token_accuracy": 0.18792459666728972,
|
|
"num_tokens": 50737909.0,
|
|
"step": 24455
|
|
},
|
|
{
|
|
"entropy": 5.457469797134399,
|
|
"epoch": 2.2187953555878086,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045069976842534635,
|
|
"loss": 5.233,
|
|
"mean_token_accuracy": 0.18836229741573335,
|
|
"num_tokens": 50749745.0,
|
|
"step": 24460
|
|
},
|
|
{
|
|
"entropy": 5.5625111103057865,
|
|
"epoch": 2.2192489114658924,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004506795544839697,
|
|
"loss": 5.1835,
|
|
"mean_token_accuracy": 0.1890425741672516,
|
|
"num_tokens": 50760073.0,
|
|
"step": 24465
|
|
},
|
|
{
|
|
"entropy": 5.549318790435791,
|
|
"epoch": 2.2197024673439767,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004506593369094951,
|
|
"loss": 5.1576,
|
|
"mean_token_accuracy": 0.1906005084514618,
|
|
"num_tokens": 50769261.0,
|
|
"step": 24470
|
|
},
|
|
{
|
|
"entropy": 5.548531103134155,
|
|
"epoch": 2.220156023222061,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00045063911570234074,
|
|
"loss": 5.3089,
|
|
"mean_token_accuracy": 0.17784660011529924,
|
|
"num_tokens": 50779572.0,
|
|
"step": 24475
|
|
},
|
|
{
|
|
"entropy": 5.514779090881348,
|
|
"epoch": 2.2206095791001452,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004506188908629247,
|
|
"loss": 5.1667,
|
|
"mean_token_accuracy": 0.18985204994678498,
|
|
"num_tokens": 50789893.0,
|
|
"step": 24480
|
|
},
|
|
{
|
|
"entropy": 5.480316591262818,
|
|
"epoch": 2.2210631349782295,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004505986623916652,
|
|
"loss": 5.098,
|
|
"mean_token_accuracy": 0.19024841636419296,
|
|
"num_tokens": 50799177.0,
|
|
"step": 24485
|
|
},
|
|
{
|
|
"entropy": 5.480689477920532,
|
|
"epoch": 2.2215166908563133,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004505784302889806,
|
|
"loss": 5.2077,
|
|
"mean_token_accuracy": 0.19385787695646287,
|
|
"num_tokens": 50810093.0,
|
|
"step": 24490
|
|
},
|
|
{
|
|
"entropy": 5.578008365631104,
|
|
"epoch": 2.2219702467343976,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00045055819455528935,
|
|
"loss": 5.3583,
|
|
"mean_token_accuracy": 0.18033462315797805,
|
|
"num_tokens": 50820272.0,
|
|
"step": 24495
|
|
},
|
|
{
|
|
"entropy": 5.5643187999725345,
|
|
"epoch": 2.222423802612482,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004505379551910099,
|
|
"loss": 5.2816,
|
|
"mean_token_accuracy": 0.1878863602876663,
|
|
"num_tokens": 50830301.0,
|
|
"step": 24500
|
|
},
|
|
{
|
|
"entropy": 5.602193450927734,
|
|
"epoch": 2.222877358490566,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004505177121965608,
|
|
"loss": 5.2576,
|
|
"mean_token_accuracy": 0.18859702795743943,
|
|
"num_tokens": 50839937.0,
|
|
"step": 24505
|
|
},
|
|
{
|
|
"entropy": 5.4500203132629395,
|
|
"epoch": 2.2233309143686504,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00045049746557236067,
|
|
"loss": 5.1983,
|
|
"mean_token_accuracy": 0.18992771357297897,
|
|
"num_tokens": 50850295.0,
|
|
"step": 24510
|
|
},
|
|
{
|
|
"entropy": 5.541101312637329,
|
|
"epoch": 2.223784470246734,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045047721531882827,
|
|
"loss": 5.2479,
|
|
"mean_token_accuracy": 0.18347131162881852,
|
|
"num_tokens": 50861889.0,
|
|
"step": 24515
|
|
},
|
|
{
|
|
"entropy": 5.567200326919556,
|
|
"epoch": 2.2242380261248185,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004504569614363823,
|
|
"loss": 5.206,
|
|
"mean_token_accuracy": 0.1871414765715599,
|
|
"num_tokens": 50872011.0,
|
|
"step": 24520
|
|
},
|
|
{
|
|
"entropy": 5.618700218200684,
|
|
"epoch": 2.2246915820029027,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004504367039254416,
|
|
"loss": 5.2695,
|
|
"mean_token_accuracy": 0.18100117295980453,
|
|
"num_tokens": 50882559.0,
|
|
"step": 24525
|
|
},
|
|
{
|
|
"entropy": 5.504925346374511,
|
|
"epoch": 2.225145137880987,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00045041644278642523,
|
|
"loss": 5.3038,
|
|
"mean_token_accuracy": 0.17665010690689087,
|
|
"num_tokens": 50894132.0,
|
|
"step": 24530
|
|
},
|
|
{
|
|
"entropy": 5.569277906417847,
|
|
"epoch": 2.2255986937590713,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045039617801975214,
|
|
"loss": 5.2372,
|
|
"mean_token_accuracy": 0.1847958579659462,
|
|
"num_tokens": 50904337.0,
|
|
"step": 24535
|
|
},
|
|
{
|
|
"entropy": 5.5760904312133786,
|
|
"epoch": 2.2260522496371555,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045037590962584143,
|
|
"loss": 5.2754,
|
|
"mean_token_accuracy": 0.17991961240768434,
|
|
"num_tokens": 50914961.0,
|
|
"step": 24540
|
|
},
|
|
{
|
|
"entropy": 5.527539539337158,
|
|
"epoch": 2.2265058055152394,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004503556376051121,
|
|
"loss": 5.2111,
|
|
"mean_token_accuracy": 0.18723059594631195,
|
|
"num_tokens": 50925682.0,
|
|
"step": 24545
|
|
},
|
|
{
|
|
"entropy": 5.51977572441101,
|
|
"epoch": 2.2269593613933236,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00045033536195798355,
|
|
"loss": 5.1261,
|
|
"mean_token_accuracy": 0.19815251529216765,
|
|
"num_tokens": 50935809.0,
|
|
"step": 24550
|
|
},
|
|
{
|
|
"entropy": 5.60448579788208,
|
|
"epoch": 2.227412917271408,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000450315082684875,
|
|
"loss": 5.3427,
|
|
"mean_token_accuracy": 0.17679157257080078,
|
|
"num_tokens": 50946098.0,
|
|
"step": 24555
|
|
},
|
|
{
|
|
"entropy": 5.576545000076294,
|
|
"epoch": 2.227866473149492,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004502947997862059,
|
|
"loss": 5.2808,
|
|
"mean_token_accuracy": 0.18118986785411834,
|
|
"num_tokens": 50956240.0,
|
|
"step": 24560
|
|
},
|
|
{
|
|
"entropy": 5.517518806457519,
|
|
"epoch": 2.228320029027576,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004502745132623957,
|
|
"loss": 5.179,
|
|
"mean_token_accuracy": 0.19403042644262314,
|
|
"num_tokens": 50966870.0,
|
|
"step": 24565
|
|
},
|
|
{
|
|
"entropy": 5.532647132873535,
|
|
"epoch": 2.2287735849056602,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004502542231138639,
|
|
"loss": 5.2021,
|
|
"mean_token_accuracy": 0.18417965471744538,
|
|
"num_tokens": 50977528.0,
|
|
"step": 24570
|
|
},
|
|
{
|
|
"entropy": 5.526747989654541,
|
|
"epoch": 2.2292271407837445,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00045023392934103005,
|
|
"loss": 5.22,
|
|
"mean_token_accuracy": 0.18578640818595887,
|
|
"num_tokens": 50988565.0,
|
|
"step": 24575
|
|
},
|
|
{
|
|
"entropy": 5.507862758636475,
|
|
"epoch": 2.2296806966618288,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045021363194431397,
|
|
"loss": 5.2602,
|
|
"mean_token_accuracy": 0.18820759356021882,
|
|
"num_tokens": 50998410.0,
|
|
"step": 24580
|
|
},
|
|
{
|
|
"entropy": 5.592985200881958,
|
|
"epoch": 2.230134252539913,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004501933309241352,
|
|
"loss": 5.2418,
|
|
"mean_token_accuracy": 0.1849873349070549,
|
|
"num_tokens": 51008890.0,
|
|
"step": 24585
|
|
},
|
|
{
|
|
"entropy": 5.494642305374145,
|
|
"epoch": 2.2305878084179973,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004501730262809138,
|
|
"loss": 5.2226,
|
|
"mean_token_accuracy": 0.18251721262931825,
|
|
"num_tokens": 51020264.0,
|
|
"step": 24590
|
|
},
|
|
{
|
|
"entropy": 5.457375240325928,
|
|
"epoch": 2.231041364296081,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004501527180150696,
|
|
"loss": 5.1173,
|
|
"mean_token_accuracy": 0.19574576914310454,
|
|
"num_tokens": 51029892.0,
|
|
"step": 24595
|
|
},
|
|
{
|
|
"entropy": 5.575293254852295,
|
|
"epoch": 2.2314949201741654,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004501324061270224,
|
|
"loss": 5.3411,
|
|
"mean_token_accuracy": 0.18005668073892594,
|
|
"num_tokens": 51040499.0,
|
|
"step": 24600
|
|
},
|
|
{
|
|
"entropy": 5.456138944625854,
|
|
"epoch": 2.2319484760522497,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004501120906171926,
|
|
"loss": 5.1274,
|
|
"mean_token_accuracy": 0.19259736239910125,
|
|
"num_tokens": 51050395.0,
|
|
"step": 24605
|
|
},
|
|
{
|
|
"entropy": 5.528149890899658,
|
|
"epoch": 2.232402031930334,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00045009177148600004,
|
|
"loss": 5.145,
|
|
"mean_token_accuracy": 0.19123973846435546,
|
|
"num_tokens": 51060316.0,
|
|
"step": 24610
|
|
},
|
|
{
|
|
"entropy": 5.428176736831665,
|
|
"epoch": 2.232855587808418,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045007144873386514,
|
|
"loss": 5.1915,
|
|
"mean_token_accuracy": 0.18797125071287155,
|
|
"num_tokens": 51070032.0,
|
|
"step": 24615
|
|
},
|
|
{
|
|
"entropy": 5.6515556335449215,
|
|
"epoch": 2.233309143686502,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045005112236120795,
|
|
"loss": 5.3444,
|
|
"mean_token_accuracy": 0.1790979653596878,
|
|
"num_tokens": 51080738.0,
|
|
"step": 24620
|
|
},
|
|
{
|
|
"entropy": 5.511699056625366,
|
|
"epoch": 2.2337626995645863,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000450030792368449,
|
|
"loss": 5.1675,
|
|
"mean_token_accuracy": 0.19185739308595656,
|
|
"num_tokens": 51090287.0,
|
|
"step": 24625
|
|
},
|
|
{
|
|
"entropy": 5.4584253311157225,
|
|
"epoch": 2.2342162554426706,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004500104587560086,
|
|
"loss": 5.2369,
|
|
"mean_token_accuracy": 0.18365846276283265,
|
|
"num_tokens": 51101188.0,
|
|
"step": 24630
|
|
},
|
|
{
|
|
"entropy": 5.47718620300293,
|
|
"epoch": 2.234669811320755,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004499901215243074,
|
|
"loss": 5.1264,
|
|
"mean_token_accuracy": 0.18906819373369216,
|
|
"num_tokens": 51112310.0,
|
|
"step": 24635
|
|
},
|
|
{
|
|
"entropy": 5.547688102722168,
|
|
"epoch": 2.235123367198839,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00044996978067376575,
|
|
"loss": 5.2741,
|
|
"mean_token_accuracy": 0.18241726607084274,
|
|
"num_tokens": 51122481.0,
|
|
"step": 24640
|
|
},
|
|
{
|
|
"entropy": 5.468135786056519,
|
|
"epoch": 2.235576923076923,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00044994943620480453,
|
|
"loss": 5.1733,
|
|
"mean_token_accuracy": 0.18605529516935349,
|
|
"num_tokens": 51131918.0,
|
|
"step": 24645
|
|
},
|
|
{
|
|
"entropy": 5.507819604873657,
|
|
"epoch": 2.236030478955007,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00044992908811784446,
|
|
"loss": 5.2661,
|
|
"mean_token_accuracy": 0.17710863649845124,
|
|
"num_tokens": 51142861.0,
|
|
"step": 24650
|
|
},
|
|
{
|
|
"entropy": 5.565795278549194,
|
|
"epoch": 2.2364840348330914,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00044990873641330615,
|
|
"loss": 5.2633,
|
|
"mean_token_accuracy": 0.18860044628381728,
|
|
"num_tokens": 51153956.0,
|
|
"step": 24655
|
|
},
|
|
{
|
|
"entropy": 5.542715692520142,
|
|
"epoch": 2.2369375907111757,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004498883810916107,
|
|
"loss": 5.1446,
|
|
"mean_token_accuracy": 0.19179385602474214,
|
|
"num_tokens": 51164499.0,
|
|
"step": 24660
|
|
},
|
|
{
|
|
"entropy": 5.524789667129516,
|
|
"epoch": 2.23739114658926,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004498680221531789,
|
|
"loss": 5.3027,
|
|
"mean_token_accuracy": 0.18132394254207612,
|
|
"num_tokens": 51175722.0,
|
|
"step": 24665
|
|
},
|
|
{
|
|
"entropy": 5.512550592422485,
|
|
"epoch": 2.237844702467344,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004498476595984319,
|
|
"loss": 5.1872,
|
|
"mean_token_accuracy": 0.18991294354200364,
|
|
"num_tokens": 51184597.0,
|
|
"step": 24670
|
|
},
|
|
{
|
|
"entropy": 5.494153928756714,
|
|
"epoch": 2.238298258345428,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004498272934277906,
|
|
"loss": 5.2482,
|
|
"mean_token_accuracy": 0.18873439580202103,
|
|
"num_tokens": 51194751.0,
|
|
"step": 24675
|
|
},
|
|
{
|
|
"entropy": 5.523139381408692,
|
|
"epoch": 2.2387518142235123,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044980692364167646,
|
|
"loss": 5.1659,
|
|
"mean_token_accuracy": 0.1975642830133438,
|
|
"num_tokens": 51204184.0,
|
|
"step": 24680
|
|
},
|
|
{
|
|
"entropy": 5.471007871627807,
|
|
"epoch": 2.2392053701015966,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004497865502405105,
|
|
"loss": 5.2849,
|
|
"mean_token_accuracy": 0.18946120887994766,
|
|
"num_tokens": 51213761.0,
|
|
"step": 24685
|
|
},
|
|
{
|
|
"entropy": 5.4999064922332765,
|
|
"epoch": 2.239658925979681,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00044976617322471424,
|
|
"loss": 5.1843,
|
|
"mean_token_accuracy": 0.19168171286582947,
|
|
"num_tokens": 51224150.0,
|
|
"step": 24690
|
|
},
|
|
{
|
|
"entropy": 5.595245981216431,
|
|
"epoch": 2.2401124818577647,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000449745792594709,
|
|
"loss": 5.3212,
|
|
"mean_token_accuracy": 0.1831376627087593,
|
|
"num_tokens": 51235133.0,
|
|
"step": 24695
|
|
},
|
|
{
|
|
"entropy": 5.598513650894165,
|
|
"epoch": 2.240566037735849,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00044972540835091617,
|
|
"loss": 5.2292,
|
|
"mean_token_accuracy": 0.18625451028347015,
|
|
"num_tokens": 51245632.0,
|
|
"step": 24700
|
|
},
|
|
{
|
|
"entropy": 5.488026285171509,
|
|
"epoch": 2.241019593613933,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00044970502049375736,
|
|
"loss": 5.2499,
|
|
"mean_token_accuracy": 0.18875888586044312,
|
|
"num_tokens": 51255747.0,
|
|
"step": 24705
|
|
},
|
|
{
|
|
"entropy": 5.500178956985474,
|
|
"epoch": 2.2414731494920175,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004496846290236542,
|
|
"loss": 5.2069,
|
|
"mean_token_accuracy": 0.18989852219820022,
|
|
"num_tokens": 51265531.0,
|
|
"step": 24710
|
|
},
|
|
{
|
|
"entropy": 5.517583560943604,
|
|
"epoch": 2.2419267053701017,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00044966423394102845,
|
|
"loss": 5.2478,
|
|
"mean_token_accuracy": 0.18695535361766816,
|
|
"num_tokens": 51275319.0,
|
|
"step": 24715
|
|
},
|
|
{
|
|
"entropy": 5.537263631820679,
|
|
"epoch": 2.2423802612481856,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00044964383524630176,
|
|
"loss": 5.2364,
|
|
"mean_token_accuracy": 0.19023171216249465,
|
|
"num_tokens": 51285655.0,
|
|
"step": 24720
|
|
},
|
|
{
|
|
"entropy": 5.465473985671997,
|
|
"epoch": 2.24283381712627,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004496234329398961,
|
|
"loss": 5.1454,
|
|
"mean_token_accuracy": 0.18646425306797026,
|
|
"num_tokens": 51295938.0,
|
|
"step": 24725
|
|
},
|
|
{
|
|
"entropy": 5.55394172668457,
|
|
"epoch": 2.243287373004354,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004496030270222333,
|
|
"loss": 5.1847,
|
|
"mean_token_accuracy": 0.1894288182258606,
|
|
"num_tokens": 51306483.0,
|
|
"step": 24730
|
|
},
|
|
{
|
|
"entropy": 5.537232255935669,
|
|
"epoch": 2.2437409288824384,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00044958261749373547,
|
|
"loss": 5.2166,
|
|
"mean_token_accuracy": 0.18847108334302903,
|
|
"num_tokens": 51316446.0,
|
|
"step": 24735
|
|
},
|
|
{
|
|
"entropy": 5.4771665096282955,
|
|
"epoch": 2.2441944847605226,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00044956220435482465,
|
|
"loss": 5.2191,
|
|
"mean_token_accuracy": 0.18854653537273408,
|
|
"num_tokens": 51326840.0,
|
|
"step": 24740
|
|
},
|
|
{
|
|
"entropy": 5.486555910110473,
|
|
"epoch": 2.244648040638607,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044954178760592283,
|
|
"loss": 5.2882,
|
|
"mean_token_accuracy": 0.1784976989030838,
|
|
"num_tokens": 51337573.0,
|
|
"step": 24745
|
|
},
|
|
{
|
|
"entropy": 5.636218929290772,
|
|
"epoch": 2.2451015965166907,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00044952136724745254,
|
|
"loss": 5.2522,
|
|
"mean_token_accuracy": 0.18477672785520555,
|
|
"num_tokens": 51347827.0,
|
|
"step": 24750
|
|
},
|
|
{
|
|
"entropy": 5.526098251342773,
|
|
"epoch": 2.245555152394775,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004495009432798358,
|
|
"loss": 5.2014,
|
|
"mean_token_accuracy": 0.19117653369903564,
|
|
"num_tokens": 51358396.0,
|
|
"step": 24755
|
|
},
|
|
{
|
|
"entropy": 5.505629301071167,
|
|
"epoch": 2.2460087082728593,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00044948051570349503,
|
|
"loss": 5.2232,
|
|
"mean_token_accuracy": 0.1812226489186287,
|
|
"num_tokens": 51368882.0,
|
|
"step": 24760
|
|
},
|
|
{
|
|
"entropy": 5.496224594116211,
|
|
"epoch": 2.2464622641509435,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004494600845188528,
|
|
"loss": 5.2527,
|
|
"mean_token_accuracy": 0.19160245209932328,
|
|
"num_tokens": 51378717.0,
|
|
"step": 24765
|
|
},
|
|
{
|
|
"entropy": 5.562796926498413,
|
|
"epoch": 2.2469158200290273,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00044943964972633154,
|
|
"loss": 5.213,
|
|
"mean_token_accuracy": 0.18345645815134048,
|
|
"num_tokens": 51389270.0,
|
|
"step": 24770
|
|
},
|
|
{
|
|
"entropy": 5.535325288772583,
|
|
"epoch": 2.2473693759071116,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004494192113263539,
|
|
"loss": 5.224,
|
|
"mean_token_accuracy": 0.18637387454509735,
|
|
"num_tokens": 51400025.0,
|
|
"step": 24775
|
|
},
|
|
{
|
|
"entropy": 5.510826206207275,
|
|
"epoch": 2.247822931785196,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00044939876931934255,
|
|
"loss": 5.2292,
|
|
"mean_token_accuracy": 0.1919806644320488,
|
|
"num_tokens": 51410903.0,
|
|
"step": 24780
|
|
},
|
|
{
|
|
"entropy": 5.434448528289795,
|
|
"epoch": 2.24827648766328,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004493783237057201,
|
|
"loss": 5.1823,
|
|
"mean_token_accuracy": 0.18758255243301392,
|
|
"num_tokens": 51420246.0,
|
|
"step": 24785
|
|
},
|
|
{
|
|
"entropy": 5.577030658721924,
|
|
"epoch": 2.2487300435413644,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004493578744859095,
|
|
"loss": 5.3369,
|
|
"mean_token_accuracy": 0.19047934114933013,
|
|
"num_tokens": 51431309.0,
|
|
"step": 24790
|
|
},
|
|
{
|
|
"entropy": 5.611192798614502,
|
|
"epoch": 2.2491835994194487,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004493374216603338,
|
|
"loss": 5.3018,
|
|
"mean_token_accuracy": 0.18156531006097792,
|
|
"num_tokens": 51443142.0,
|
|
"step": 24795
|
|
},
|
|
{
|
|
"entropy": 5.637078666687012,
|
|
"epoch": 2.2496371552975325,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004493169652294156,
|
|
"loss": 5.4588,
|
|
"mean_token_accuracy": 0.17319048345088958,
|
|
"num_tokens": 51454499.0,
|
|
"step": 24800
|
|
},
|
|
{
|
|
"entropy": 5.5747137546539305,
|
|
"epoch": 2.2500907111756168,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00044929650519357823,
|
|
"loss": 5.2318,
|
|
"mean_token_accuracy": 0.18456303477287292,
|
|
"num_tokens": 51464667.0,
|
|
"step": 24805
|
|
},
|
|
{
|
|
"entropy": 5.552005195617676,
|
|
"epoch": 2.250544267053701,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004492760415532447,
|
|
"loss": 5.2229,
|
|
"mean_token_accuracy": 0.1903552308678627,
|
|
"num_tokens": 51473627.0,
|
|
"step": 24810
|
|
},
|
|
{
|
|
"entropy": 5.43942289352417,
|
|
"epoch": 2.2509978229317853,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004492555743088382,
|
|
"loss": 5.0856,
|
|
"mean_token_accuracy": 0.18687689453363418,
|
|
"num_tokens": 51483052.0,
|
|
"step": 24815
|
|
},
|
|
{
|
|
"entropy": 5.487134075164795,
|
|
"epoch": 2.2514513788098696,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.000449235103460782,
|
|
"loss": 5.2259,
|
|
"mean_token_accuracy": 0.18376254737377168,
|
|
"num_tokens": 51492422.0,
|
|
"step": 24820
|
|
},
|
|
{
|
|
"entropy": 5.468579530715942,
|
|
"epoch": 2.2519049346879534,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004492146290094995,
|
|
"loss": 5.176,
|
|
"mean_token_accuracy": 0.18922526389360428,
|
|
"num_tokens": 51503566.0,
|
|
"step": 24825
|
|
},
|
|
{
|
|
"entropy": 5.515962266921997,
|
|
"epoch": 2.2523584905660377,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00044919415095541406,
|
|
"loss": 5.2027,
|
|
"mean_token_accuracy": 0.19143216609954833,
|
|
"num_tokens": 51513699.0,
|
|
"step": 24830
|
|
},
|
|
{
|
|
"entropy": 5.5623450756073,
|
|
"epoch": 2.252812046444122,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00044917366929894914,
|
|
"loss": 5.2246,
|
|
"mean_token_accuracy": 0.1827203020453453,
|
|
"num_tokens": 51524745.0,
|
|
"step": 24835
|
|
},
|
|
{
|
|
"entropy": 5.4841086864471436,
|
|
"epoch": 2.253265602322206,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00044915318404052846,
|
|
"loss": 5.1479,
|
|
"mean_token_accuracy": 0.1893371120095253,
|
|
"num_tokens": 51536516.0,
|
|
"step": 24840
|
|
},
|
|
{
|
|
"entropy": 5.519898366928101,
|
|
"epoch": 2.2537191582002905,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00044913269518057547,
|
|
"loss": 5.2572,
|
|
"mean_token_accuracy": 0.18024464696645737,
|
|
"num_tokens": 51547063.0,
|
|
"step": 24845
|
|
},
|
|
{
|
|
"entropy": 5.5055811405181885,
|
|
"epoch": 2.2541727140783743,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000449112202719514,
|
|
"loss": 5.2026,
|
|
"mean_token_accuracy": 0.18606879264116288,
|
|
"num_tokens": 51557244.0,
|
|
"step": 24850
|
|
},
|
|
{
|
|
"entropy": 5.558277320861817,
|
|
"epoch": 2.2546262699564585,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004490917066577678,
|
|
"loss": 5.2533,
|
|
"mean_token_accuracy": 0.18759612441062928,
|
|
"num_tokens": 51567630.0,
|
|
"step": 24855
|
|
},
|
|
{
|
|
"entropy": 5.459316873550415,
|
|
"epoch": 2.255079825834543,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044907120699576075,
|
|
"loss": 5.2453,
|
|
"mean_token_accuracy": 0.18991733938455582,
|
|
"num_tokens": 51577951.0,
|
|
"step": 24860
|
|
},
|
|
{
|
|
"entropy": 5.538358736038208,
|
|
"epoch": 2.255533381712627,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00044905070373391684,
|
|
"loss": 5.1923,
|
|
"mean_token_accuracy": 0.18625101894140245,
|
|
"num_tokens": 51587533.0,
|
|
"step": 24865
|
|
},
|
|
{
|
|
"entropy": 5.567177629470825,
|
|
"epoch": 2.2559869375907113,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004490301968726599,
|
|
"loss": 5.1984,
|
|
"mean_token_accuracy": 0.19577679485082627,
|
|
"num_tokens": 51597212.0,
|
|
"step": 24870
|
|
},
|
|
{
|
|
"entropy": 5.4891674518585205,
|
|
"epoch": 2.256440493468795,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.00044900968641241426,
|
|
"loss": 5.2558,
|
|
"mean_token_accuracy": 0.18986984342336655,
|
|
"num_tokens": 51608520.0,
|
|
"step": 24875
|
|
},
|
|
{
|
|
"entropy": 5.544170999526978,
|
|
"epoch": 2.2568940493468794,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004489891723536039,
|
|
"loss": 5.3122,
|
|
"mean_token_accuracy": 0.18017210364341735,
|
|
"num_tokens": 51619651.0,
|
|
"step": 24880
|
|
},
|
|
{
|
|
"entropy": 5.481785631179809,
|
|
"epoch": 2.2573476052249637,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004489686546966531,
|
|
"loss": 5.1229,
|
|
"mean_token_accuracy": 0.19037391245365143,
|
|
"num_tokens": 51630184.0,
|
|
"step": 24885
|
|
},
|
|
{
|
|
"entropy": 5.431570959091187,
|
|
"epoch": 2.257801161103048,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00044894813344198626,
|
|
"loss": 5.1413,
|
|
"mean_token_accuracy": 0.19470726996660231,
|
|
"num_tokens": 51641293.0,
|
|
"step": 24890
|
|
},
|
|
{
|
|
"entropy": 5.531812858581543,
|
|
"epoch": 2.2582547169811322,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004489276085900276,
|
|
"loss": 5.1955,
|
|
"mean_token_accuracy": 0.1912273645401001,
|
|
"num_tokens": 51652002.0,
|
|
"step": 24895
|
|
},
|
|
{
|
|
"entropy": 5.412841749191284,
|
|
"epoch": 2.2587082728592165,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00044890708014120174,
|
|
"loss": 5.0737,
|
|
"mean_token_accuracy": 0.19880862087011336,
|
|
"num_tokens": 51661668.0,
|
|
"step": 24900
|
|
},
|
|
{
|
|
"entropy": 5.603960752487183,
|
|
"epoch": 2.2591618287373003,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004488865480959331,
|
|
"loss": 5.2745,
|
|
"mean_token_accuracy": 0.1820397913455963,
|
|
"num_tokens": 51672879.0,
|
|
"step": 24905
|
|
},
|
|
{
|
|
"entropy": 5.5529228210449215,
|
|
"epoch": 2.2596153846153846,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004488660124546464,
|
|
"loss": 5.2104,
|
|
"mean_token_accuracy": 0.18445618450641632,
|
|
"num_tokens": 51683878.0,
|
|
"step": 24910
|
|
},
|
|
{
|
|
"entropy": 5.437809801101684,
|
|
"epoch": 2.260068940493469,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004488454732177662,
|
|
"loss": 5.2232,
|
|
"mean_token_accuracy": 0.18606841415166855,
|
|
"num_tokens": 51693971.0,
|
|
"step": 24915
|
|
},
|
|
{
|
|
"entropy": 5.5181248664855955,
|
|
"epoch": 2.260522496371553,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00044882493038571737,
|
|
"loss": 5.1233,
|
|
"mean_token_accuracy": 0.19614336490631104,
|
|
"num_tokens": 51703685.0,
|
|
"step": 24920
|
|
},
|
|
{
|
|
"entropy": 5.509007549285888,
|
|
"epoch": 2.260976052249637,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00044880438395892457,
|
|
"loss": 5.256,
|
|
"mean_token_accuracy": 0.1871053919196129,
|
|
"num_tokens": 51714469.0,
|
|
"step": 24925
|
|
},
|
|
{
|
|
"entropy": 5.528822422027588,
|
|
"epoch": 2.261429608127721,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004487838339378129,
|
|
"loss": 5.2619,
|
|
"mean_token_accuracy": 0.17717180103063584,
|
|
"num_tokens": 51725283.0,
|
|
"step": 24930
|
|
},
|
|
{
|
|
"entropy": 5.542246007919312,
|
|
"epoch": 2.2618831640058055,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004487632803228072,
|
|
"loss": 5.2091,
|
|
"mean_token_accuracy": 0.18882830291986466,
|
|
"num_tokens": 51735628.0,
|
|
"step": 24935
|
|
},
|
|
{
|
|
"entropy": 5.420746564865112,
|
|
"epoch": 2.2623367198838897,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00044874272311433265,
|
|
"loss": 5.0756,
|
|
"mean_token_accuracy": 0.1926303192973137,
|
|
"num_tokens": 51745991.0,
|
|
"step": 24940
|
|
},
|
|
{
|
|
"entropy": 5.408369779586792,
|
|
"epoch": 2.262790275761974,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004487221623128143,
|
|
"loss": 5.1435,
|
|
"mean_token_accuracy": 0.19441402554512024,
|
|
"num_tokens": 51756306.0,
|
|
"step": 24945
|
|
},
|
|
{
|
|
"entropy": 5.454325914382935,
|
|
"epoch": 2.2632438316400583,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00044870159791867743,
|
|
"loss": 5.222,
|
|
"mean_token_accuracy": 0.19527778178453445,
|
|
"num_tokens": 51765466.0,
|
|
"step": 24950
|
|
},
|
|
{
|
|
"entropy": 5.5393609523773195,
|
|
"epoch": 2.263697387518142,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00044868102993234716,
|
|
"loss": 5.2315,
|
|
"mean_token_accuracy": 0.18349151462316513,
|
|
"num_tokens": 51775526.0,
|
|
"step": 24955
|
|
},
|
|
{
|
|
"entropy": 5.542573308944702,
|
|
"epoch": 2.2641509433962264,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044866045835424896,
|
|
"loss": 5.2071,
|
|
"mean_token_accuracy": 0.18322362154722213,
|
|
"num_tokens": 51785434.0,
|
|
"step": 24960
|
|
},
|
|
{
|
|
"entropy": 5.558357810974121,
|
|
"epoch": 2.2646044992743106,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004486398831848082,
|
|
"loss": 5.2627,
|
|
"mean_token_accuracy": 0.18183176666498185,
|
|
"num_tokens": 51796047.0,
|
|
"step": 24965
|
|
},
|
|
{
|
|
"entropy": 5.531978368759155,
|
|
"epoch": 2.265058055152395,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00044861930442445037,
|
|
"loss": 5.2381,
|
|
"mean_token_accuracy": 0.18033275455236436,
|
|
"num_tokens": 51806173.0,
|
|
"step": 24970
|
|
},
|
|
{
|
|
"entropy": 5.622264242172241,
|
|
"epoch": 2.2655116110304787,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004485987220736012,
|
|
"loss": 5.3946,
|
|
"mean_token_accuracy": 0.17634397596120835,
|
|
"num_tokens": 51817644.0,
|
|
"step": 24975
|
|
},
|
|
{
|
|
"entropy": 5.579347324371338,
|
|
"epoch": 2.265965166908563,
|
|
"grad_norm": 3.203125,
|
|
"learning_rate": 0.0004485781361326861,
|
|
"loss": 5.3345,
|
|
"mean_token_accuracy": 0.18289747834205627,
|
|
"num_tokens": 51829746.0,
|
|
"step": 24980
|
|
},
|
|
{
|
|
"entropy": 5.51652455329895,
|
|
"epoch": 2.2664187227866472,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000448557546602131,
|
|
"loss": 5.2678,
|
|
"mean_token_accuracy": 0.18096466064453126,
|
|
"num_tokens": 51840868.0,
|
|
"step": 24985
|
|
},
|
|
{
|
|
"entropy": 5.514470052719116,
|
|
"epoch": 2.2668722786647315,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00044853695348236156,
|
|
"loss": 5.1227,
|
|
"mean_token_accuracy": 0.19331321716308594,
|
|
"num_tokens": 51851385.0,
|
|
"step": 24990
|
|
},
|
|
{
|
|
"entropy": 5.4886620998382565,
|
|
"epoch": 2.2673258345428158,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044851635677380374,
|
|
"loss": 5.1678,
|
|
"mean_token_accuracy": 0.1815304711461067,
|
|
"num_tokens": 51861021.0,
|
|
"step": 24995
|
|
},
|
|
{
|
|
"entropy": 5.538556385040283,
|
|
"epoch": 2.2677793904209,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004484957564768834,
|
|
"loss": 5.2698,
|
|
"mean_token_accuracy": 0.1832360878586769,
|
|
"num_tokens": 51870688.0,
|
|
"step": 25000
|
|
},
|
|
{
|
|
"entropy": 5.485268211364746,
|
|
"epoch": 2.268232946298984,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00044847515259202657,
|
|
"loss": 5.2109,
|
|
"mean_token_accuracy": 0.1877143830060959,
|
|
"num_tokens": 51880439.0,
|
|
"step": 25005
|
|
},
|
|
{
|
|
"entropy": 5.488817930221558,
|
|
"epoch": 2.268686502177068,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00044845454511965947,
|
|
"loss": 5.1752,
|
|
"mean_token_accuracy": 0.1921513333916664,
|
|
"num_tokens": 51890861.0,
|
|
"step": 25010
|
|
},
|
|
{
|
|
"entropy": 5.5495203018188475,
|
|
"epoch": 2.2691400580551524,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00044843393406020823,
|
|
"loss": 5.1746,
|
|
"mean_token_accuracy": 0.19130060374736785,
|
|
"num_tokens": 51900687.0,
|
|
"step": 25015
|
|
},
|
|
{
|
|
"entropy": 5.526278305053711,
|
|
"epoch": 2.2695936139332367,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00044841331941409884,
|
|
"loss": 5.3572,
|
|
"mean_token_accuracy": 0.1766958013176918,
|
|
"num_tokens": 51911805.0,
|
|
"step": 25020
|
|
},
|
|
{
|
|
"entropy": 5.511693096160888,
|
|
"epoch": 2.270047169811321,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00044839270118175793,
|
|
"loss": 5.1547,
|
|
"mean_token_accuracy": 0.19866640120744705,
|
|
"num_tokens": 51922520.0,
|
|
"step": 25025
|
|
},
|
|
{
|
|
"entropy": 5.561278343200684,
|
|
"epoch": 2.2705007256894048,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004483720793636118,
|
|
"loss": 5.3011,
|
|
"mean_token_accuracy": 0.18117391914129258,
|
|
"num_tokens": 51934056.0,
|
|
"step": 25030
|
|
},
|
|
{
|
|
"entropy": 5.543147277832031,
|
|
"epoch": 2.270954281567489,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.00044835145396008685,
|
|
"loss": 5.2711,
|
|
"mean_token_accuracy": 0.18891075849533082,
|
|
"num_tokens": 51944696.0,
|
|
"step": 25035
|
|
},
|
|
{
|
|
"entropy": 5.555205821990967,
|
|
"epoch": 2.2714078374455733,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004483308249716097,
|
|
"loss": 5.2479,
|
|
"mean_token_accuracy": 0.18476490080356597,
|
|
"num_tokens": 51955111.0,
|
|
"step": 25040
|
|
},
|
|
{
|
|
"entropy": 5.4594801902771,
|
|
"epoch": 2.2718613933236576,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004483101923986068,
|
|
"loss": 5.2069,
|
|
"mean_token_accuracy": 0.1920732542872429,
|
|
"num_tokens": 51966036.0,
|
|
"step": 25045
|
|
},
|
|
{
|
|
"entropy": 5.466973400115966,
|
|
"epoch": 2.272314949201742,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00044828955624150505,
|
|
"loss": 5.212,
|
|
"mean_token_accuracy": 0.19036890864372252,
|
|
"num_tokens": 51976060.0,
|
|
"step": 25050
|
|
},
|
|
{
|
|
"entropy": 5.527909755706787,
|
|
"epoch": 2.2727685050798256,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004482689165007311,
|
|
"loss": 5.1954,
|
|
"mean_token_accuracy": 0.18528743237257003,
|
|
"num_tokens": 51986016.0,
|
|
"step": 25055
|
|
},
|
|
{
|
|
"entropy": 5.473757791519165,
|
|
"epoch": 2.27322206095791,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00044824827317671177,
|
|
"loss": 5.1622,
|
|
"mean_token_accuracy": 0.19820739775896073,
|
|
"num_tokens": 51994794.0,
|
|
"step": 25060
|
|
},
|
|
{
|
|
"entropy": 5.422681188583374,
|
|
"epoch": 2.273675616835994,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000448227626269874,
|
|
"loss": 5.1279,
|
|
"mean_token_accuracy": 0.1956025630235672,
|
|
"num_tokens": 52004976.0,
|
|
"step": 25065
|
|
},
|
|
{
|
|
"entropy": 5.493689012527466,
|
|
"epoch": 2.2741291727140784,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00044820697578064485,
|
|
"loss": 5.2347,
|
|
"mean_token_accuracy": 0.1793815329670906,
|
|
"num_tokens": 52016380.0,
|
|
"step": 25070
|
|
},
|
|
{
|
|
"entropy": 5.553690671920776,
|
|
"epoch": 2.2745827285921627,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004481863217094513,
|
|
"loss": 5.1853,
|
|
"mean_token_accuracy": 0.1897353932261467,
|
|
"num_tokens": 52026439.0,
|
|
"step": 25075
|
|
},
|
|
{
|
|
"entropy": 5.474989795684815,
|
|
"epoch": 2.2750362844702465,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004481656640567204,
|
|
"loss": 5.1622,
|
|
"mean_token_accuracy": 0.191728413105011,
|
|
"num_tokens": 52037111.0,
|
|
"step": 25080
|
|
},
|
|
{
|
|
"entropy": 5.472513437271118,
|
|
"epoch": 2.275489840348331,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004481450028228795,
|
|
"loss": 5.2046,
|
|
"mean_token_accuracy": 0.18711133748292924,
|
|
"num_tokens": 52047463.0,
|
|
"step": 25085
|
|
},
|
|
{
|
|
"entropy": 5.541540098190308,
|
|
"epoch": 2.275943396226415,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004481243380083558,
|
|
"loss": 5.2343,
|
|
"mean_token_accuracy": 0.19059928208589555,
|
|
"num_tokens": 52058081.0,
|
|
"step": 25090
|
|
},
|
|
{
|
|
"entropy": 5.493239116668701,
|
|
"epoch": 2.2763969521044993,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004481036696135767,
|
|
"loss": 5.2425,
|
|
"mean_token_accuracy": 0.18881710022687911,
|
|
"num_tokens": 52069367.0,
|
|
"step": 25095
|
|
},
|
|
{
|
|
"entropy": 5.533731460571289,
|
|
"epoch": 2.2768505079825836,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004480829976389695,
|
|
"loss": 5.1655,
|
|
"mean_token_accuracy": 0.19106044471263886,
|
|
"num_tokens": 52080023.0,
|
|
"step": 25100
|
|
},
|
|
{
|
|
"entropy": 5.414236545562744,
|
|
"epoch": 2.277304063860668,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00044806232208496194,
|
|
"loss": 5.1995,
|
|
"mean_token_accuracy": 0.19319998621940612,
|
|
"num_tokens": 52089184.0,
|
|
"step": 25105
|
|
},
|
|
{
|
|
"entropy": 5.558595848083496,
|
|
"epoch": 2.2777576197387517,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004480416429519814,
|
|
"loss": 5.2865,
|
|
"mean_token_accuracy": 0.18393801152706146,
|
|
"num_tokens": 52098711.0,
|
|
"step": 25110
|
|
},
|
|
{
|
|
"entropy": 5.5816535472869875,
|
|
"epoch": 2.278211175616836,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004480209602404556,
|
|
"loss": 5.1819,
|
|
"mean_token_accuracy": 0.1902400001883507,
|
|
"num_tokens": 52108826.0,
|
|
"step": 25115
|
|
},
|
|
{
|
|
"entropy": 5.449687242507935,
|
|
"epoch": 2.27866473149492,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004480002739508122,
|
|
"loss": 5.1513,
|
|
"mean_token_accuracy": 0.19204332828521728,
|
|
"num_tokens": 52118934.0,
|
|
"step": 25120
|
|
},
|
|
{
|
|
"entropy": 5.450011730194092,
|
|
"epoch": 2.2791182873730045,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004479795840834791,
|
|
"loss": 5.1637,
|
|
"mean_token_accuracy": 0.19538755416870118,
|
|
"num_tokens": 52129803.0,
|
|
"step": 25125
|
|
},
|
|
{
|
|
"entropy": 5.43389368057251,
|
|
"epoch": 2.2795718432510883,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00044795889063888413,
|
|
"loss": 5.0745,
|
|
"mean_token_accuracy": 0.19470565021038055,
|
|
"num_tokens": 52140070.0,
|
|
"step": 25130
|
|
},
|
|
{
|
|
"entropy": 5.665645265579224,
|
|
"epoch": 2.2800253991291726,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004479381936174552,
|
|
"loss": 5.3921,
|
|
"mean_token_accuracy": 0.17939860373735428,
|
|
"num_tokens": 52150462.0,
|
|
"step": 25135
|
|
},
|
|
{
|
|
"entropy": 5.556212615966797,
|
|
"epoch": 2.280478955007257,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004479174930196204,
|
|
"loss": 5.2289,
|
|
"mean_token_accuracy": 0.18989668488502504,
|
|
"num_tokens": 52160552.0,
|
|
"step": 25140
|
|
},
|
|
{
|
|
"entropy": 5.37483959197998,
|
|
"epoch": 2.280932510885341,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00044789678884580767,
|
|
"loss": 5.1185,
|
|
"mean_token_accuracy": 0.19328116923570632,
|
|
"num_tokens": 52169780.0,
|
|
"step": 25145
|
|
},
|
|
{
|
|
"entropy": 5.525588798522949,
|
|
"epoch": 2.2813860667634254,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00044787608109644536,
|
|
"loss": 5.2574,
|
|
"mean_token_accuracy": 0.18805521577596665,
|
|
"num_tokens": 52180055.0,
|
|
"step": 25150
|
|
},
|
|
{
|
|
"entropy": 5.501560926437378,
|
|
"epoch": 2.2818396226415096,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004478553697719616,
|
|
"loss": 5.1651,
|
|
"mean_token_accuracy": 0.1964058443903923,
|
|
"num_tokens": 52189772.0,
|
|
"step": 25155
|
|
},
|
|
{
|
|
"entropy": 5.492020940780639,
|
|
"epoch": 2.2822931785195935,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004478346548727848,
|
|
"loss": 5.1706,
|
|
"mean_token_accuracy": 0.19698209911584855,
|
|
"num_tokens": 52199608.0,
|
|
"step": 25160
|
|
},
|
|
{
|
|
"entropy": 5.468634510040284,
|
|
"epoch": 2.2827467343976777,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004478139363993433,
|
|
"loss": 5.2048,
|
|
"mean_token_accuracy": 0.1869959756731987,
|
|
"num_tokens": 52208236.0,
|
|
"step": 25165
|
|
},
|
|
{
|
|
"entropy": 5.527006340026856,
|
|
"epoch": 2.283200290275762,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004477932143520655,
|
|
"loss": 5.2343,
|
|
"mean_token_accuracy": 0.1912461683154106,
|
|
"num_tokens": 52218403.0,
|
|
"step": 25170
|
|
},
|
|
{
|
|
"entropy": 5.502253293991089,
|
|
"epoch": 2.2836538461538463,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00044777248873138005,
|
|
"loss": 5.203,
|
|
"mean_token_accuracy": 0.1899342194199562,
|
|
"num_tokens": 52228255.0,
|
|
"step": 25175
|
|
},
|
|
{
|
|
"entropy": 5.557885456085205,
|
|
"epoch": 2.2841074020319305,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00044775175953771547,
|
|
"loss": 5.2339,
|
|
"mean_token_accuracy": 0.1850964456796646,
|
|
"num_tokens": 52237732.0,
|
|
"step": 25180
|
|
},
|
|
{
|
|
"entropy": 5.611035966873169,
|
|
"epoch": 2.2845609579100143,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004477310267715005,
|
|
"loss": 5.393,
|
|
"mean_token_accuracy": 0.17389880269765853,
|
|
"num_tokens": 52249226.0,
|
|
"step": 25185
|
|
},
|
|
{
|
|
"entropy": 5.5551410675048825,
|
|
"epoch": 2.2850145137880986,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004477102904331639,
|
|
"loss": 5.2034,
|
|
"mean_token_accuracy": 0.19158486574888228,
|
|
"num_tokens": 52259550.0,
|
|
"step": 25190
|
|
},
|
|
{
|
|
"entropy": 5.571929216384888,
|
|
"epoch": 2.285468069666183,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00044768955052313443,
|
|
"loss": 5.2297,
|
|
"mean_token_accuracy": 0.18799718767404555,
|
|
"num_tokens": 52269670.0,
|
|
"step": 25195
|
|
},
|
|
{
|
|
"entropy": 5.549346160888672,
|
|
"epoch": 2.285921625544267,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00044766880704184104,
|
|
"loss": 5.2126,
|
|
"mean_token_accuracy": 0.18811457902193068,
|
|
"num_tokens": 52280135.0,
|
|
"step": 25200
|
|
},
|
|
{
|
|
"entropy": 5.437598419189453,
|
|
"epoch": 2.2863751814223514,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004476480599897128,
|
|
"loss": 5.1461,
|
|
"mean_token_accuracy": 0.19242414385080336,
|
|
"num_tokens": 52291806.0,
|
|
"step": 25205
|
|
},
|
|
{
|
|
"entropy": 5.410020112991333,
|
|
"epoch": 2.2868287373004352,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004476273093671786,
|
|
"loss": 5.1716,
|
|
"mean_token_accuracy": 0.19210486710071564,
|
|
"num_tokens": 52302118.0,
|
|
"step": 25210
|
|
},
|
|
{
|
|
"entropy": 5.594678497314453,
|
|
"epoch": 2.2872822931785195,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00044760655517466766,
|
|
"loss": 5.2755,
|
|
"mean_token_accuracy": 0.18378280252218246,
|
|
"num_tokens": 52312762.0,
|
|
"step": 25215
|
|
},
|
|
{
|
|
"entropy": 5.551855230331421,
|
|
"epoch": 2.2877358490566038,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00044758579741260916,
|
|
"loss": 5.2334,
|
|
"mean_token_accuracy": 0.17931348085403442,
|
|
"num_tokens": 52323367.0,
|
|
"step": 25220
|
|
},
|
|
{
|
|
"entropy": 5.571346378326416,
|
|
"epoch": 2.288189404934688,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00044756503608143247,
|
|
"loss": 5.2934,
|
|
"mean_token_accuracy": 0.1789943754673004,
|
|
"num_tokens": 52335231.0,
|
|
"step": 25225
|
|
},
|
|
{
|
|
"entropy": 5.541528987884521,
|
|
"epoch": 2.2886429608127723,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00044754427118156675,
|
|
"loss": 5.1695,
|
|
"mean_token_accuracy": 0.18907103389501573,
|
|
"num_tokens": 52345066.0,
|
|
"step": 25230
|
|
},
|
|
{
|
|
"entropy": 5.512851762771606,
|
|
"epoch": 2.289096516690856,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004475235027134416,
|
|
"loss": 5.206,
|
|
"mean_token_accuracy": 0.19125315099954604,
|
|
"num_tokens": 52356383.0,
|
|
"step": 25235
|
|
},
|
|
{
|
|
"entropy": 5.507763433456421,
|
|
"epoch": 2.2895500725689404,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004475027306774865,
|
|
"loss": 5.3123,
|
|
"mean_token_accuracy": 0.19167663305997848,
|
|
"num_tokens": 52366013.0,
|
|
"step": 25240
|
|
},
|
|
{
|
|
"entropy": 5.540942573547364,
|
|
"epoch": 2.2900036284470247,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00044748195507413095,
|
|
"loss": 5.271,
|
|
"mean_token_accuracy": 0.1837622344493866,
|
|
"num_tokens": 52376298.0,
|
|
"step": 25245
|
|
},
|
|
{
|
|
"entropy": 5.459442090988159,
|
|
"epoch": 2.290457184325109,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00044746117590380456,
|
|
"loss": 5.1295,
|
|
"mean_token_accuracy": 0.1885437473654747,
|
|
"num_tokens": 52387134.0,
|
|
"step": 25250
|
|
},
|
|
{
|
|
"entropy": 5.476705551147461,
|
|
"epoch": 2.290910740203193,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004474403931669371,
|
|
"loss": 5.1115,
|
|
"mean_token_accuracy": 0.19036143720149995,
|
|
"num_tokens": 52397389.0,
|
|
"step": 25255
|
|
},
|
|
{
|
|
"entropy": 5.502002191543579,
|
|
"epoch": 2.2913642960812775,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004474196068639584,
|
|
"loss": 5.1559,
|
|
"mean_token_accuracy": 0.19305479079484938,
|
|
"num_tokens": 52407456.0,
|
|
"step": 25260
|
|
},
|
|
{
|
|
"entropy": 5.477440690994262,
|
|
"epoch": 2.2918178519593613,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004473988169952983,
|
|
"loss": 5.2044,
|
|
"mean_token_accuracy": 0.19129723608493804,
|
|
"num_tokens": 52417967.0,
|
|
"step": 25265
|
|
},
|
|
{
|
|
"entropy": 5.54453854560852,
|
|
"epoch": 2.2922714078374455,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00044737802356138674,
|
|
"loss": 5.316,
|
|
"mean_token_accuracy": 0.18943058252334594,
|
|
"num_tokens": 52428757.0,
|
|
"step": 25270
|
|
},
|
|
{
|
|
"entropy": 5.525933265686035,
|
|
"epoch": 2.29272496371553,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004473572265626537,
|
|
"loss": 5.2138,
|
|
"mean_token_accuracy": 0.19023091942071915,
|
|
"num_tokens": 52438973.0,
|
|
"step": 25275
|
|
},
|
|
{
|
|
"entropy": 5.457763719558716,
|
|
"epoch": 2.293178519593614,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004473364259995293,
|
|
"loss": 5.151,
|
|
"mean_token_accuracy": 0.18930006474256517,
|
|
"num_tokens": 52449323.0,
|
|
"step": 25280
|
|
},
|
|
{
|
|
"entropy": 5.525722455978394,
|
|
"epoch": 2.293632075471698,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004473156218724436,
|
|
"loss": 5.2048,
|
|
"mean_token_accuracy": 0.19143303483724594,
|
|
"num_tokens": 52459299.0,
|
|
"step": 25285
|
|
},
|
|
{
|
|
"entropy": 5.463899612426758,
|
|
"epoch": 2.294085631349782,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00044729481418182704,
|
|
"loss": 5.1533,
|
|
"mean_token_accuracy": 0.18486829102039337,
|
|
"num_tokens": 52470026.0,
|
|
"step": 25290
|
|
},
|
|
{
|
|
"entropy": 5.517204856872558,
|
|
"epoch": 2.2945391872278664,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00044727400292810985,
|
|
"loss": 5.1548,
|
|
"mean_token_accuracy": 0.1912297338247299,
|
|
"num_tokens": 52479975.0,
|
|
"step": 25295
|
|
},
|
|
{
|
|
"entropy": 5.514515018463134,
|
|
"epoch": 2.2949927431059507,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00044725318811172227,
|
|
"loss": 5.3166,
|
|
"mean_token_accuracy": 0.18205595165491104,
|
|
"num_tokens": 52491067.0,
|
|
"step": 25300
|
|
},
|
|
{
|
|
"entropy": 5.455070352554321,
|
|
"epoch": 2.295446298984035,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000447232369733095,
|
|
"loss": 5.1695,
|
|
"mean_token_accuracy": 0.1929253101348877,
|
|
"num_tokens": 52500671.0,
|
|
"step": 25305
|
|
},
|
|
{
|
|
"entropy": 5.511729288101196,
|
|
"epoch": 2.2958998548621192,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004472115477926583,
|
|
"loss": 5.1333,
|
|
"mean_token_accuracy": 0.19024352878332138,
|
|
"num_tokens": 52509910.0,
|
|
"step": 25310
|
|
},
|
|
{
|
|
"entropy": 5.480220031738281,
|
|
"epoch": 2.296353410740203,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00044719072229084295,
|
|
"loss": 5.1644,
|
|
"mean_token_accuracy": 0.1926088184118271,
|
|
"num_tokens": 52520517.0,
|
|
"step": 25315
|
|
},
|
|
{
|
|
"entropy": 5.517775583267212,
|
|
"epoch": 2.2968069666182873,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004471698932280796,
|
|
"loss": 5.2545,
|
|
"mean_token_accuracy": 0.1931234136223793,
|
|
"num_tokens": 52530760.0,
|
|
"step": 25320
|
|
},
|
|
{
|
|
"entropy": 5.558865880966186,
|
|
"epoch": 2.2972605224963716,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000447149060604799,
|
|
"loss": 5.2978,
|
|
"mean_token_accuracy": 0.18081767857074738,
|
|
"num_tokens": 52541791.0,
|
|
"step": 25325
|
|
},
|
|
{
|
|
"entropy": 5.578357744216919,
|
|
"epoch": 2.297714078374456,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00044712822442143194,
|
|
"loss": 5.2929,
|
|
"mean_token_accuracy": 0.18807110488414763,
|
|
"num_tokens": 52551885.0,
|
|
"step": 25330
|
|
},
|
|
{
|
|
"entropy": 5.4606201171875,
|
|
"epoch": 2.2981676342525397,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00044710738467840927,
|
|
"loss": 5.1721,
|
|
"mean_token_accuracy": 0.19183236956596375,
|
|
"num_tokens": 52563080.0,
|
|
"step": 25335
|
|
},
|
|
{
|
|
"entropy": 5.49315915107727,
|
|
"epoch": 2.298621190130624,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004470865413761621,
|
|
"loss": 5.1364,
|
|
"mean_token_accuracy": 0.19646793901920317,
|
|
"num_tokens": 52573564.0,
|
|
"step": 25340
|
|
},
|
|
{
|
|
"entropy": 5.497422742843628,
|
|
"epoch": 2.299074746008708,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00044706569451512143,
|
|
"loss": 5.1834,
|
|
"mean_token_accuracy": 0.18996860533952714,
|
|
"num_tokens": 52583801.0,
|
|
"step": 25345
|
|
},
|
|
{
|
|
"entropy": 5.498368835449218,
|
|
"epoch": 2.2995283018867925,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00044704484409571825,
|
|
"loss": 5.2411,
|
|
"mean_token_accuracy": 0.18525651693344117,
|
|
"num_tokens": 52594908.0,
|
|
"step": 25350
|
|
},
|
|
{
|
|
"entropy": 5.4423003673553465,
|
|
"epoch": 2.2999818577648767,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00044702399011838393,
|
|
"loss": 5.1199,
|
|
"mean_token_accuracy": 0.1873708114027977,
|
|
"num_tokens": 52604861.0,
|
|
"step": 25355
|
|
},
|
|
{
|
|
"entropy": 5.5083128929138185,
|
|
"epoch": 2.300435413642961,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004470031325835497,
|
|
"loss": 5.1944,
|
|
"mean_token_accuracy": 0.19191232323646545,
|
|
"num_tokens": 52616203.0,
|
|
"step": 25360
|
|
},
|
|
{
|
|
"entropy": 5.4927441596984865,
|
|
"epoch": 2.300888969521045,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004469822714916468,
|
|
"loss": 5.1281,
|
|
"mean_token_accuracy": 0.19551850110292435,
|
|
"num_tokens": 52625838.0,
|
|
"step": 25365
|
|
},
|
|
{
|
|
"entropy": 5.425113821029663,
|
|
"epoch": 2.301342525399129,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004469614068431067,
|
|
"loss": 5.1525,
|
|
"mean_token_accuracy": 0.19615086615085603,
|
|
"num_tokens": 52635741.0,
|
|
"step": 25370
|
|
},
|
|
{
|
|
"entropy": 5.44022946357727,
|
|
"epoch": 2.3017960812772134,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004469405386383608,
|
|
"loss": 5.128,
|
|
"mean_token_accuracy": 0.19411210715770721,
|
|
"num_tokens": 52645948.0,
|
|
"step": 25375
|
|
},
|
|
{
|
|
"entropy": 5.474126243591309,
|
|
"epoch": 2.3022496371552976,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00044691966687784087,
|
|
"loss": 5.1901,
|
|
"mean_token_accuracy": 0.19243766814470292,
|
|
"num_tokens": 52655073.0,
|
|
"step": 25380
|
|
},
|
|
{
|
|
"entropy": 5.466939973831177,
|
|
"epoch": 2.302703193033382,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00044689879156197833,
|
|
"loss": 5.1856,
|
|
"mean_token_accuracy": 0.19250601679086685,
|
|
"num_tokens": 52664429.0,
|
|
"step": 25385
|
|
},
|
|
{
|
|
"entropy": 5.622706890106201,
|
|
"epoch": 2.3031567489114657,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00044687791269120504,
|
|
"loss": 5.277,
|
|
"mean_token_accuracy": 0.1892236664891243,
|
|
"num_tokens": 52674890.0,
|
|
"step": 25390
|
|
},
|
|
{
|
|
"entropy": 5.561400890350342,
|
|
"epoch": 2.30361030478955,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00044685703026595266,
|
|
"loss": 5.284,
|
|
"mean_token_accuracy": 0.18784015625715256,
|
|
"num_tokens": 52685673.0,
|
|
"step": 25395
|
|
},
|
|
{
|
|
"entropy": 5.555271339416504,
|
|
"epoch": 2.3040638606676342,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00044683614428665314,
|
|
"loss": 5.298,
|
|
"mean_token_accuracy": 0.1851145178079605,
|
|
"num_tokens": 52696696.0,
|
|
"step": 25400
|
|
},
|
|
{
|
|
"entropy": 5.526582717895508,
|
|
"epoch": 2.3045174165457185,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00044681525475373843,
|
|
"loss": 5.2475,
|
|
"mean_token_accuracy": 0.18182406723499298,
|
|
"num_tokens": 52707662.0,
|
|
"step": 25405
|
|
},
|
|
{
|
|
"entropy": 5.491095304489136,
|
|
"epoch": 2.3049709724238028,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004467943616676403,
|
|
"loss": 5.1876,
|
|
"mean_token_accuracy": 0.19208026826381683,
|
|
"num_tokens": 52718438.0,
|
|
"step": 25410
|
|
},
|
|
{
|
|
"entropy": 5.486144018173218,
|
|
"epoch": 2.3054245283018866,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004467734650287911,
|
|
"loss": 5.1683,
|
|
"mean_token_accuracy": 0.1901540994644165,
|
|
"num_tokens": 52729267.0,
|
|
"step": 25415
|
|
},
|
|
{
|
|
"entropy": 5.403106737136841,
|
|
"epoch": 2.305878084179971,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004467525648376229,
|
|
"loss": 5.1161,
|
|
"mean_token_accuracy": 0.20204663574695586,
|
|
"num_tokens": 52738754.0,
|
|
"step": 25420
|
|
},
|
|
{
|
|
"entropy": 5.469247722625733,
|
|
"epoch": 2.306331640058055,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004467316610945679,
|
|
"loss": 5.1953,
|
|
"mean_token_accuracy": 0.19402356147766114,
|
|
"num_tokens": 52749086.0,
|
|
"step": 25425
|
|
},
|
|
{
|
|
"entropy": 5.5766987800598145,
|
|
"epoch": 2.3067851959361394,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00044671075380005825,
|
|
"loss": 5.2891,
|
|
"mean_token_accuracy": 0.18568981140851976,
|
|
"num_tokens": 52758961.0,
|
|
"step": 25430
|
|
},
|
|
{
|
|
"entropy": 5.523191690444946,
|
|
"epoch": 2.3072387518142237,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004466898429545266,
|
|
"loss": 5.2256,
|
|
"mean_token_accuracy": 0.18896642178297043,
|
|
"num_tokens": 52769447.0,
|
|
"step": 25435
|
|
},
|
|
{
|
|
"entropy": 5.573553895950317,
|
|
"epoch": 2.3076923076923075,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00044666892855840513,
|
|
"loss": 5.304,
|
|
"mean_token_accuracy": 0.18132491558790206,
|
|
"num_tokens": 52780306.0,
|
|
"step": 25440
|
|
},
|
|
{
|
|
"entropy": 5.519498348236084,
|
|
"epoch": 2.3081458635703918,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004466480106121266,
|
|
"loss": 5.1768,
|
|
"mean_token_accuracy": 0.18614603877067565,
|
|
"num_tokens": 52791263.0,
|
|
"step": 25445
|
|
},
|
|
{
|
|
"entropy": 5.541317701339722,
|
|
"epoch": 2.308599419448476,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004466270891161234,
|
|
"loss": 5.2049,
|
|
"mean_token_accuracy": 0.1819124326109886,
|
|
"num_tokens": 52802194.0,
|
|
"step": 25450
|
|
},
|
|
{
|
|
"entropy": 5.494677352905273,
|
|
"epoch": 2.3090529753265603,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00044660616407082827,
|
|
"loss": 5.1885,
|
|
"mean_token_accuracy": 0.19485800415277482,
|
|
"num_tokens": 52812391.0,
|
|
"step": 25455
|
|
},
|
|
{
|
|
"entropy": 5.519350862503051,
|
|
"epoch": 2.3095065312046446,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00044658523547667385,
|
|
"loss": 5.1785,
|
|
"mean_token_accuracy": 0.18902233242988586,
|
|
"num_tokens": 52823540.0,
|
|
"step": 25460
|
|
},
|
|
{
|
|
"entropy": 5.42989444732666,
|
|
"epoch": 2.309960087082729,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004465643033340931,
|
|
"loss": 5.1006,
|
|
"mean_token_accuracy": 0.20167146921157836,
|
|
"num_tokens": 52833238.0,
|
|
"step": 25465
|
|
},
|
|
{
|
|
"entropy": 5.563292121887207,
|
|
"epoch": 2.3104136429608126,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00044654336764351886,
|
|
"loss": 5.2863,
|
|
"mean_token_accuracy": 0.18161465376615524,
|
|
"num_tokens": 52844510.0,
|
|
"step": 25470
|
|
},
|
|
{
|
|
"entropy": 5.5683166027069095,
|
|
"epoch": 2.310867198838897,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00044652242840538406,
|
|
"loss": 5.2524,
|
|
"mean_token_accuracy": 0.19076793193817138,
|
|
"num_tokens": 52856311.0,
|
|
"step": 25475
|
|
},
|
|
{
|
|
"entropy": 5.431954669952392,
|
|
"epoch": 2.311320754716981,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004465014856201218,
|
|
"loss": 5.1407,
|
|
"mean_token_accuracy": 0.19299663007259368,
|
|
"num_tokens": 52866295.0,
|
|
"step": 25480
|
|
},
|
|
{
|
|
"entropy": 5.529575538635254,
|
|
"epoch": 2.3117743105950654,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.000446480539288165,
|
|
"loss": 5.2208,
|
|
"mean_token_accuracy": 0.18795954287052155,
|
|
"num_tokens": 52876818.0,
|
|
"step": 25485
|
|
},
|
|
{
|
|
"entropy": 5.521617746353149,
|
|
"epoch": 2.3122278664731493,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004464595894099469,
|
|
"loss": 5.1675,
|
|
"mean_token_accuracy": 0.1894690528512001,
|
|
"num_tokens": 52886173.0,
|
|
"step": 25490
|
|
},
|
|
{
|
|
"entropy": 5.44191346168518,
|
|
"epoch": 2.3126814223512335,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00044643863598590094,
|
|
"loss": 5.1425,
|
|
"mean_token_accuracy": 0.18821143209934235,
|
|
"num_tokens": 52895875.0,
|
|
"step": 25495
|
|
},
|
|
{
|
|
"entropy": 5.496223449707031,
|
|
"epoch": 2.313134978229318,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00044641767901646025,
|
|
"loss": 5.281,
|
|
"mean_token_accuracy": 0.1847118020057678,
|
|
"num_tokens": 52906465.0,
|
|
"step": 25500
|
|
},
|
|
{
|
|
"entropy": 5.585584306716919,
|
|
"epoch": 2.313588534107402,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004463967185020583,
|
|
"loss": 5.1874,
|
|
"mean_token_accuracy": 0.1931558683514595,
|
|
"num_tokens": 52916378.0,
|
|
"step": 25505
|
|
},
|
|
{
|
|
"entropy": 5.519186115264892,
|
|
"epoch": 2.3140420899854863,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004463757544431285,
|
|
"loss": 5.2582,
|
|
"mean_token_accuracy": 0.1918842762708664,
|
|
"num_tokens": 52926698.0,
|
|
"step": 25510
|
|
},
|
|
{
|
|
"entropy": 5.541992425918579,
|
|
"epoch": 2.3144956458635706,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004463547868401044,
|
|
"loss": 5.1974,
|
|
"mean_token_accuracy": 0.18753234595060347,
|
|
"num_tokens": 52936469.0,
|
|
"step": 25515
|
|
},
|
|
{
|
|
"entropy": 5.493165636062622,
|
|
"epoch": 2.3149492017416544,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00044633381569341964,
|
|
"loss": 5.2245,
|
|
"mean_token_accuracy": 0.18733305633068084,
|
|
"num_tokens": 52947006.0,
|
|
"step": 25520
|
|
},
|
|
{
|
|
"entropy": 5.418885803222656,
|
|
"epoch": 2.3154027576197387,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004463128410035079,
|
|
"loss": 5.0798,
|
|
"mean_token_accuracy": 0.19684522300958635,
|
|
"num_tokens": 52956663.0,
|
|
"step": 25525
|
|
},
|
|
{
|
|
"entropy": 5.47121787071228,
|
|
"epoch": 2.315856313497823,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00044629186277080307,
|
|
"loss": 5.121,
|
|
"mean_token_accuracy": 0.19093904942274093,
|
|
"num_tokens": 52967383.0,
|
|
"step": 25530
|
|
},
|
|
{
|
|
"entropy": 5.4486976146698,
|
|
"epoch": 2.316309869375907,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00044627088099573884,
|
|
"loss": 5.1011,
|
|
"mean_token_accuracy": 0.20028786659240722,
|
|
"num_tokens": 52976567.0,
|
|
"step": 25535
|
|
},
|
|
{
|
|
"entropy": 5.436496639251709,
|
|
"epoch": 2.3167634252539915,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00044624989567874907,
|
|
"loss": 5.2147,
|
|
"mean_token_accuracy": 0.19069817811250686,
|
|
"num_tokens": 52986159.0,
|
|
"step": 25540
|
|
},
|
|
{
|
|
"entropy": 5.536816692352295,
|
|
"epoch": 2.3172169811320753,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00044622890682026787,
|
|
"loss": 5.2191,
|
|
"mean_token_accuracy": 0.1823960140347481,
|
|
"num_tokens": 52996028.0,
|
|
"step": 25545
|
|
},
|
|
{
|
|
"entropy": 5.58886456489563,
|
|
"epoch": 2.3176705370101596,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004462079144207292,
|
|
"loss": 5.232,
|
|
"mean_token_accuracy": 0.18502465337514878,
|
|
"num_tokens": 53006446.0,
|
|
"step": 25550
|
|
},
|
|
{
|
|
"entropy": 5.545679378509521,
|
|
"epoch": 2.318124092888244,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00044618691848056726,
|
|
"loss": 5.1805,
|
|
"mean_token_accuracy": 0.1809551477432251,
|
|
"num_tokens": 53016497.0,
|
|
"step": 25555
|
|
},
|
|
{
|
|
"entropy": 5.490944910049438,
|
|
"epoch": 2.318577648766328,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004461659190002162,
|
|
"loss": 5.2737,
|
|
"mean_token_accuracy": 0.19166708439588548,
|
|
"num_tokens": 53027811.0,
|
|
"step": 25560
|
|
},
|
|
{
|
|
"entropy": 5.479932546615601,
|
|
"epoch": 2.3190312046444124,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00044614491598011027,
|
|
"loss": 5.1853,
|
|
"mean_token_accuracy": 0.18056707084178925,
|
|
"num_tokens": 53038206.0,
|
|
"step": 25565
|
|
},
|
|
{
|
|
"entropy": 5.513529253005982,
|
|
"epoch": 2.319484760522496,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004461239094206839,
|
|
"loss": 5.2293,
|
|
"mean_token_accuracy": 0.18893577456474303,
|
|
"num_tokens": 53047974.0,
|
|
"step": 25570
|
|
},
|
|
{
|
|
"entropy": 5.5978058815002445,
|
|
"epoch": 2.3199383164005805,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00044610289932237154,
|
|
"loss": 5.256,
|
|
"mean_token_accuracy": 0.19001227170228957,
|
|
"num_tokens": 53057904.0,
|
|
"step": 25575
|
|
},
|
|
{
|
|
"entropy": 5.487049150466919,
|
|
"epoch": 2.3203918722786647,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00044608188568560756,
|
|
"loss": 5.1898,
|
|
"mean_token_accuracy": 0.1894395112991333,
|
|
"num_tokens": 53068447.0,
|
|
"step": 25580
|
|
},
|
|
{
|
|
"entropy": 5.483026742935181,
|
|
"epoch": 2.320845428156749,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004460608685108266,
|
|
"loss": 5.2149,
|
|
"mean_token_accuracy": 0.18620056211948394,
|
|
"num_tokens": 53079369.0,
|
|
"step": 25585
|
|
},
|
|
{
|
|
"entropy": 5.611340713500977,
|
|
"epoch": 2.3212989840348333,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00044603984779846334,
|
|
"loss": 5.2896,
|
|
"mean_token_accuracy": 0.18259021639823914,
|
|
"num_tokens": 53090794.0,
|
|
"step": 25590
|
|
},
|
|
{
|
|
"entropy": 5.501590824127197,
|
|
"epoch": 2.321752539912917,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004460188235489524,
|
|
"loss": 5.1065,
|
|
"mean_token_accuracy": 0.19021077901124955,
|
|
"num_tokens": 53100802.0,
|
|
"step": 25595
|
|
},
|
|
{
|
|
"entropy": 5.39031343460083,
|
|
"epoch": 2.3222060957910013,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004459977957627285,
|
|
"loss": 5.2389,
|
|
"mean_token_accuracy": 0.18540845662355424,
|
|
"num_tokens": 53111950.0,
|
|
"step": 25600
|
|
},
|
|
{
|
|
"entropy": 5.411601448059082,
|
|
"epoch": 2.3226596516690856,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00044597676444022683,
|
|
"loss": 5.046,
|
|
"mean_token_accuracy": 0.19747465401887893,
|
|
"num_tokens": 53121908.0,
|
|
"step": 25605
|
|
},
|
|
{
|
|
"entropy": 5.541889190673828,
|
|
"epoch": 2.32311320754717,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00044595572958188194,
|
|
"loss": 5.199,
|
|
"mean_token_accuracy": 0.18805230557918548,
|
|
"num_tokens": 53133065.0,
|
|
"step": 25610
|
|
},
|
|
{
|
|
"entropy": 5.429856061935425,
|
|
"epoch": 2.323566763425254,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004459346911881291,
|
|
"loss": 5.1432,
|
|
"mean_token_accuracy": 0.18831832706928253,
|
|
"num_tokens": 53144135.0,
|
|
"step": 25615
|
|
},
|
|
{
|
|
"entropy": 5.4859668731689455,
|
|
"epoch": 2.3240203193033384,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004459136492594032,
|
|
"loss": 5.1244,
|
|
"mean_token_accuracy": 0.20140901803970337,
|
|
"num_tokens": 53153916.0,
|
|
"step": 25620
|
|
},
|
|
{
|
|
"entropy": 5.423862504959106,
|
|
"epoch": 2.3244738751814222,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004458926037961394,
|
|
"loss": 5.0972,
|
|
"mean_token_accuracy": 0.20087340027093886,
|
|
"num_tokens": 53163937.0,
|
|
"step": 25625
|
|
},
|
|
{
|
|
"entropy": 5.553349351882934,
|
|
"epoch": 2.3249274310595065,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004458715547987732,
|
|
"loss": 5.276,
|
|
"mean_token_accuracy": 0.1798061490058899,
|
|
"num_tokens": 53174327.0,
|
|
"step": 25630
|
|
},
|
|
{
|
|
"entropy": 5.573512554168701,
|
|
"epoch": 2.3253809869375908,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004458505022677396,
|
|
"loss": 5.2105,
|
|
"mean_token_accuracy": 0.1858027309179306,
|
|
"num_tokens": 53185946.0,
|
|
"step": 25635
|
|
},
|
|
{
|
|
"entropy": 5.480445480346679,
|
|
"epoch": 2.325834542815675,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004458294462034741,
|
|
"loss": 5.1503,
|
|
"mean_token_accuracy": 0.1929897755384445,
|
|
"num_tokens": 53195944.0,
|
|
"step": 25640
|
|
},
|
|
{
|
|
"entropy": 5.4226282119750975,
|
|
"epoch": 2.326288098693759,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004458083866064121,
|
|
"loss": 5.1991,
|
|
"mean_token_accuracy": 0.19813326895236968,
|
|
"num_tokens": 53206054.0,
|
|
"step": 25645
|
|
},
|
|
{
|
|
"entropy": 5.523681783676148,
|
|
"epoch": 2.326741654571843,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004457873234769891,
|
|
"loss": 5.1972,
|
|
"mean_token_accuracy": 0.18883479684591292,
|
|
"num_tokens": 53216923.0,
|
|
"step": 25650
|
|
},
|
|
{
|
|
"entropy": 5.484314060211181,
|
|
"epoch": 2.3271952104499274,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00044576625681564086,
|
|
"loss": 5.1904,
|
|
"mean_token_accuracy": 0.18846548944711686,
|
|
"num_tokens": 53226788.0,
|
|
"step": 25655
|
|
},
|
|
{
|
|
"entropy": 5.502345275878906,
|
|
"epoch": 2.3276487663280117,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00044574518662280276,
|
|
"loss": 5.2172,
|
|
"mean_token_accuracy": 0.18728783130645751,
|
|
"num_tokens": 53237573.0,
|
|
"step": 25660
|
|
},
|
|
{
|
|
"entropy": 5.545324611663818,
|
|
"epoch": 2.328102322206096,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004457241128989108,
|
|
"loss": 5.2369,
|
|
"mean_token_accuracy": 0.18594879806041717,
|
|
"num_tokens": 53247724.0,
|
|
"step": 25665
|
|
},
|
|
{
|
|
"entropy": 5.568013715744018,
|
|
"epoch": 2.32855587808418,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004457030356444006,
|
|
"loss": 5.2072,
|
|
"mean_token_accuracy": 0.18623981773853301,
|
|
"num_tokens": 53258774.0,
|
|
"step": 25670
|
|
},
|
|
{
|
|
"entropy": 5.514351654052734,
|
|
"epoch": 2.329009433962264,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004456819548597082,
|
|
"loss": 5.1701,
|
|
"mean_token_accuracy": 0.19452315121889113,
|
|
"num_tokens": 53268550.0,
|
|
"step": 25675
|
|
},
|
|
{
|
|
"entropy": 5.326637172698975,
|
|
"epoch": 2.3294629898403483,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00044566087054526946,
|
|
"loss": 5.1197,
|
|
"mean_token_accuracy": 0.19845902770757676,
|
|
"num_tokens": 53277975.0,
|
|
"step": 25680
|
|
},
|
|
{
|
|
"entropy": 5.539934062957764,
|
|
"epoch": 2.3299165457184325,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004456397827015204,
|
|
"loss": 5.281,
|
|
"mean_token_accuracy": 0.1873871862888336,
|
|
"num_tokens": 53287939.0,
|
|
"step": 25685
|
|
},
|
|
{
|
|
"entropy": 5.548870277404785,
|
|
"epoch": 2.330370101596517,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004456186913288971,
|
|
"loss": 5.2363,
|
|
"mean_token_accuracy": 0.18967908769845962,
|
|
"num_tokens": 53298355.0,
|
|
"step": 25690
|
|
},
|
|
{
|
|
"entropy": 5.543321895599365,
|
|
"epoch": 2.3308236574746006,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004455975964278359,
|
|
"loss": 5.2893,
|
|
"mean_token_accuracy": 0.18608454912900924,
|
|
"num_tokens": 53308513.0,
|
|
"step": 25695
|
|
},
|
|
{
|
|
"entropy": 5.583715152740479,
|
|
"epoch": 2.331277213352685,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044557649799877285,
|
|
"loss": 5.2196,
|
|
"mean_token_accuracy": 0.19090366065502168,
|
|
"num_tokens": 53318249.0,
|
|
"step": 25700
|
|
},
|
|
{
|
|
"entropy": 5.411293935775757,
|
|
"epoch": 2.331730769230769,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004455553960421443,
|
|
"loss": 5.1635,
|
|
"mean_token_accuracy": 0.18852543085813522,
|
|
"num_tokens": 53328460.0,
|
|
"step": 25705
|
|
},
|
|
{
|
|
"entropy": 5.442607402801514,
|
|
"epoch": 2.3321843251088534,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00044553429055838685,
|
|
"loss": 5.1859,
|
|
"mean_token_accuracy": 0.19299584925174712,
|
|
"num_tokens": 53338984.0,
|
|
"step": 25710
|
|
},
|
|
{
|
|
"entropy": 5.538253307342529,
|
|
"epoch": 2.3326378809869377,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00044551318154793676,
|
|
"loss": 5.2366,
|
|
"mean_token_accuracy": 0.18716114461421968,
|
|
"num_tokens": 53348092.0,
|
|
"step": 25715
|
|
},
|
|
{
|
|
"entropy": 5.451183414459228,
|
|
"epoch": 2.333091436865022,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00044549206901123056,
|
|
"loss": 5.1355,
|
|
"mean_token_accuracy": 0.19499774277210236,
|
|
"num_tokens": 53357343.0,
|
|
"step": 25720
|
|
},
|
|
{
|
|
"entropy": 5.428317880630493,
|
|
"epoch": 2.333544992743106,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000445470952948705,
|
|
"loss": 5.0954,
|
|
"mean_token_accuracy": 0.1960338220000267,
|
|
"num_tokens": 53367343.0,
|
|
"step": 25725
|
|
},
|
|
{
|
|
"entropy": 5.593164110183716,
|
|
"epoch": 2.33399854862119,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00044544983336079665,
|
|
"loss": 5.3098,
|
|
"mean_token_accuracy": 0.18519120365381242,
|
|
"num_tokens": 53379093.0,
|
|
"step": 25730
|
|
},
|
|
{
|
|
"entropy": 5.4923137664794925,
|
|
"epoch": 2.3344521044992743,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004454287102479423,
|
|
"loss": 5.1602,
|
|
"mean_token_accuracy": 0.18955432176589965,
|
|
"num_tokens": 53388883.0,
|
|
"step": 25735
|
|
},
|
|
{
|
|
"entropy": 5.493251180648803,
|
|
"epoch": 2.3349056603773586,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004454075836105788,
|
|
"loss": 5.1836,
|
|
"mean_token_accuracy": 0.19276126921176912,
|
|
"num_tokens": 53399393.0,
|
|
"step": 25740
|
|
},
|
|
{
|
|
"entropy": 5.451741409301758,
|
|
"epoch": 2.335359216255443,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00044538645344914307,
|
|
"loss": 5.1125,
|
|
"mean_token_accuracy": 0.19679182320833205,
|
|
"num_tokens": 53408545.0,
|
|
"step": 25745
|
|
},
|
|
{
|
|
"entropy": 5.464933586120606,
|
|
"epoch": 2.3358127721335267,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004453653197640721,
|
|
"loss": 5.2024,
|
|
"mean_token_accuracy": 0.19249732941389083,
|
|
"num_tokens": 53418325.0,
|
|
"step": 25750
|
|
},
|
|
{
|
|
"entropy": 5.546941804885864,
|
|
"epoch": 2.336266328011611,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044534418255580286,
|
|
"loss": 5.2047,
|
|
"mean_token_accuracy": 0.17904344648122789,
|
|
"num_tokens": 53427984.0,
|
|
"step": 25755
|
|
},
|
|
{
|
|
"entropy": 5.594863843917847,
|
|
"epoch": 2.336719883889695,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00044532304182477245,
|
|
"loss": 5.2864,
|
|
"mean_token_accuracy": 0.18222948163747787,
|
|
"num_tokens": 53438765.0,
|
|
"step": 25760
|
|
},
|
|
{
|
|
"entropy": 5.538774633407593,
|
|
"epoch": 2.3371734397677795,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004453018975714182,
|
|
"loss": 5.1999,
|
|
"mean_token_accuracy": 0.19131192266941072,
|
|
"num_tokens": 53448792.0,
|
|
"step": 25765
|
|
},
|
|
{
|
|
"entropy": 5.514457893371582,
|
|
"epoch": 2.3376269956458637,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004452807497961773,
|
|
"loss": 5.2613,
|
|
"mean_token_accuracy": 0.18242344856262208,
|
|
"num_tokens": 53459334.0,
|
|
"step": 25770
|
|
},
|
|
{
|
|
"entropy": 5.504983282089233,
|
|
"epoch": 2.3380805515239476,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00044525959849948704,
|
|
"loss": 5.2799,
|
|
"mean_token_accuracy": 0.1872578352689743,
|
|
"num_tokens": 53469841.0,
|
|
"step": 25775
|
|
},
|
|
{
|
|
"entropy": 5.537545108795166,
|
|
"epoch": 2.338534107402032,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00044523844368178503,
|
|
"loss": 5.2328,
|
|
"mean_token_accuracy": 0.18252523690462114,
|
|
"num_tokens": 53480660.0,
|
|
"step": 25780
|
|
},
|
|
{
|
|
"entropy": 5.523983001708984,
|
|
"epoch": 2.338987663280116,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004452172853435085,
|
|
"loss": 5.1218,
|
|
"mean_token_accuracy": 0.1907709941267967,
|
|
"num_tokens": 53490276.0,
|
|
"step": 25785
|
|
},
|
|
{
|
|
"entropy": 5.322309255599976,
|
|
"epoch": 2.3394412191582004,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004451961234850953,
|
|
"loss": 5.1014,
|
|
"mean_token_accuracy": 0.2053075760602951,
|
|
"num_tokens": 53501100.0,
|
|
"step": 25790
|
|
},
|
|
{
|
|
"entropy": 5.426096963882446,
|
|
"epoch": 2.3398947750362846,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004451749581069827,
|
|
"loss": 5.1723,
|
|
"mean_token_accuracy": 0.19530562162399293,
|
|
"num_tokens": 53511680.0,
|
|
"step": 25795
|
|
},
|
|
{
|
|
"entropy": 5.574353456497192,
|
|
"epoch": 2.3403483309143684,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004451537892096087,
|
|
"loss": 5.242,
|
|
"mean_token_accuracy": 0.19105677604675292,
|
|
"num_tokens": 53521298.0,
|
|
"step": 25800
|
|
},
|
|
{
|
|
"entropy": 5.4895929336547855,
|
|
"epoch": 2.3408018867924527,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044513261679341094,
|
|
"loss": 5.1001,
|
|
"mean_token_accuracy": 0.19617393463850022,
|
|
"num_tokens": 53530413.0,
|
|
"step": 25805
|
|
},
|
|
{
|
|
"entropy": 5.426892518997192,
|
|
"epoch": 2.341255442670537,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004451114408588273,
|
|
"loss": 5.1821,
|
|
"mean_token_accuracy": 0.19226768612861633,
|
|
"num_tokens": 53540959.0,
|
|
"step": 25810
|
|
},
|
|
{
|
|
"entropy": 5.503199338912964,
|
|
"epoch": 2.3417089985486212,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00044509026140629584,
|
|
"loss": 5.1893,
|
|
"mean_token_accuracy": 0.19129462242126466,
|
|
"num_tokens": 53551265.0,
|
|
"step": 25815
|
|
},
|
|
{
|
|
"entropy": 5.56953649520874,
|
|
"epoch": 2.3421625544267055,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00044506907843625427,
|
|
"loss": 5.2153,
|
|
"mean_token_accuracy": 0.18622094988822938,
|
|
"num_tokens": 53562666.0,
|
|
"step": 25820
|
|
},
|
|
{
|
|
"entropy": 5.489358377456665,
|
|
"epoch": 2.34261611030479,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00044504789194914086,
|
|
"loss": 5.2881,
|
|
"mean_token_accuracy": 0.18379205763339995,
|
|
"num_tokens": 53573688.0,
|
|
"step": 25825
|
|
},
|
|
{
|
|
"entropy": 5.547303104400635,
|
|
"epoch": 2.3430696661828736,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00044502670194539374,
|
|
"loss": 5.1611,
|
|
"mean_token_accuracy": 0.19132557064294814,
|
|
"num_tokens": 53584055.0,
|
|
"step": 25830
|
|
},
|
|
{
|
|
"entropy": 5.385729646682739,
|
|
"epoch": 2.343523222060958,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00044500550842545104,
|
|
"loss": 5.0586,
|
|
"mean_token_accuracy": 0.1983447402715683,
|
|
"num_tokens": 53593765.0,
|
|
"step": 25835
|
|
},
|
|
{
|
|
"entropy": 5.432418251037598,
|
|
"epoch": 2.343976777939042,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004449843113897512,
|
|
"loss": 5.1237,
|
|
"mean_token_accuracy": 0.197091943025589,
|
|
"num_tokens": 53603480.0,
|
|
"step": 25840
|
|
},
|
|
{
|
|
"entropy": 5.498619508743286,
|
|
"epoch": 2.3444303338171264,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004449631108387325,
|
|
"loss": 5.1806,
|
|
"mean_token_accuracy": 0.19322241544723512,
|
|
"num_tokens": 53613797.0,
|
|
"step": 25845
|
|
},
|
|
{
|
|
"entropy": 5.46619291305542,
|
|
"epoch": 2.34488388969521,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004449419067728333,
|
|
"loss": 5.1325,
|
|
"mean_token_accuracy": 0.1925736978650093,
|
|
"num_tokens": 53623646.0,
|
|
"step": 25850
|
|
},
|
|
{
|
|
"entropy": 5.437866306304931,
|
|
"epoch": 2.3453374455732945,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.00044492069919249206,
|
|
"loss": 5.1502,
|
|
"mean_token_accuracy": 0.1879100114107132,
|
|
"num_tokens": 53634118.0,
|
|
"step": 25855
|
|
},
|
|
{
|
|
"entropy": 5.489466524124145,
|
|
"epoch": 2.3457910014513788,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004448994880981476,
|
|
"loss": 5.1673,
|
|
"mean_token_accuracy": 0.1905420497059822,
|
|
"num_tokens": 53644370.0,
|
|
"step": 25860
|
|
},
|
|
{
|
|
"entropy": 5.556042718887329,
|
|
"epoch": 2.346244557329463,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044487827349023833,
|
|
"loss": 5.2263,
|
|
"mean_token_accuracy": 0.1820527732372284,
|
|
"num_tokens": 53655560.0,
|
|
"step": 25865
|
|
},
|
|
{
|
|
"entropy": 5.509190559387207,
|
|
"epoch": 2.3466981132075473,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.00044485705536920315,
|
|
"loss": 5.2658,
|
|
"mean_token_accuracy": 0.1853916108608246,
|
|
"num_tokens": 53666401.0,
|
|
"step": 25870
|
|
},
|
|
{
|
|
"entropy": 5.583950328826904,
|
|
"epoch": 2.3471516690856316,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00044483583373548075,
|
|
"loss": 5.269,
|
|
"mean_token_accuracy": 0.1982741504907608,
|
|
"num_tokens": 53676133.0,
|
|
"step": 25875
|
|
},
|
|
{
|
|
"entropy": 5.476702070236206,
|
|
"epoch": 2.3476052249637154,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004448146085895101,
|
|
"loss": 5.1915,
|
|
"mean_token_accuracy": 0.1853589281439781,
|
|
"num_tokens": 53687683.0,
|
|
"step": 25880
|
|
},
|
|
{
|
|
"entropy": 5.484755945205689,
|
|
"epoch": 2.3480587808417996,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004447933799317299,
|
|
"loss": 5.2579,
|
|
"mean_token_accuracy": 0.18485674113035203,
|
|
"num_tokens": 53698343.0,
|
|
"step": 25885
|
|
},
|
|
{
|
|
"entropy": 5.54767918586731,
|
|
"epoch": 2.348512336719884,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004447721477625795,
|
|
"loss": 5.1843,
|
|
"mean_token_accuracy": 0.1879412665963173,
|
|
"num_tokens": 53709014.0,
|
|
"step": 25890
|
|
},
|
|
{
|
|
"entropy": 5.424594593048096,
|
|
"epoch": 2.348965892597968,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00044475091208249774,
|
|
"loss": 5.1944,
|
|
"mean_token_accuracy": 0.19179718494415282,
|
|
"num_tokens": 53718838.0,
|
|
"step": 25895
|
|
},
|
|
{
|
|
"entropy": 5.453534412384033,
|
|
"epoch": 2.3494194484760524,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004447296728919239,
|
|
"loss": 5.1425,
|
|
"mean_token_accuracy": 0.19470445662736893,
|
|
"num_tokens": 53728526.0,
|
|
"step": 25900
|
|
},
|
|
{
|
|
"entropy": 5.546575975418091,
|
|
"epoch": 2.3498730043541363,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004447084301912972,
|
|
"loss": 5.2513,
|
|
"mean_token_accuracy": 0.18933185189962387,
|
|
"num_tokens": 53739261.0,
|
|
"step": 25905
|
|
},
|
|
{
|
|
"entropy": 5.534142303466797,
|
|
"epoch": 2.3503265602322205,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004446871839810568,
|
|
"loss": 5.2344,
|
|
"mean_token_accuracy": 0.1908136084675789,
|
|
"num_tokens": 53749599.0,
|
|
"step": 25910
|
|
},
|
|
{
|
|
"entropy": 5.485835933685303,
|
|
"epoch": 2.350780116110305,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00044466593426164224,
|
|
"loss": 5.222,
|
|
"mean_token_accuracy": 0.19021402895450593,
|
|
"num_tokens": 53759898.0,
|
|
"step": 25915
|
|
},
|
|
{
|
|
"entropy": 5.526998233795166,
|
|
"epoch": 2.351233671988389,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000444644681033493,
|
|
"loss": 5.1682,
|
|
"mean_token_accuracy": 0.18615276217460633,
|
|
"num_tokens": 53770561.0,
|
|
"step": 25920
|
|
},
|
|
{
|
|
"entropy": 5.502005863189697,
|
|
"epoch": 2.3516872278664733,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00044462342429704845,
|
|
"loss": 5.1741,
|
|
"mean_token_accuracy": 0.18618976324796677,
|
|
"num_tokens": 53780408.0,
|
|
"step": 25925
|
|
},
|
|
{
|
|
"entropy": 5.3955319881439205,
|
|
"epoch": 2.352140783744557,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00044460216405274827,
|
|
"loss": 5.0978,
|
|
"mean_token_accuracy": 0.20469291806221007,
|
|
"num_tokens": 53789125.0,
|
|
"step": 25930
|
|
},
|
|
{
|
|
"entropy": 5.4760839462280275,
|
|
"epoch": 2.3525943396226414,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00044458090030103216,
|
|
"loss": 5.132,
|
|
"mean_token_accuracy": 0.19928941279649734,
|
|
"num_tokens": 53799164.0,
|
|
"step": 25935
|
|
},
|
|
{
|
|
"entropy": 5.511787462234497,
|
|
"epoch": 2.3530478955007257,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00044455963304233976,
|
|
"loss": 5.1322,
|
|
"mean_token_accuracy": 0.19397305846214294,
|
|
"num_tokens": 53810710.0,
|
|
"step": 25940
|
|
},
|
|
{
|
|
"entropy": 5.438886260986328,
|
|
"epoch": 2.35350145137881,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.000444538362277111,
|
|
"loss": 5.162,
|
|
"mean_token_accuracy": 0.18794308304786683,
|
|
"num_tokens": 53820692.0,
|
|
"step": 25945
|
|
},
|
|
{
|
|
"entropy": 5.524816226959229,
|
|
"epoch": 2.353955007256894,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004445170880057857,
|
|
"loss": 5.2146,
|
|
"mean_token_accuracy": 0.18913199454545976,
|
|
"num_tokens": 53831082.0,
|
|
"step": 25950
|
|
},
|
|
{
|
|
"entropy": 5.575177240371704,
|
|
"epoch": 2.354408563134978,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044449581022880375,
|
|
"loss": 5.2623,
|
|
"mean_token_accuracy": 0.18017906099557876,
|
|
"num_tokens": 53842602.0,
|
|
"step": 25955
|
|
},
|
|
{
|
|
"entropy": 5.506014442443847,
|
|
"epoch": 2.3548621190130623,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004444745289466053,
|
|
"loss": 5.1823,
|
|
"mean_token_accuracy": 0.1912481665611267,
|
|
"num_tokens": 53853784.0,
|
|
"step": 25960
|
|
},
|
|
{
|
|
"entropy": 5.443855333328247,
|
|
"epoch": 2.3553156748911466,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00044445324415963043,
|
|
"loss": 5.0618,
|
|
"mean_token_accuracy": 0.20090377181768418,
|
|
"num_tokens": 53863526.0,
|
|
"step": 25965
|
|
},
|
|
{
|
|
"entropy": 5.399431991577148,
|
|
"epoch": 2.355769230769231,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004444319558683192,
|
|
"loss": 5.1918,
|
|
"mean_token_accuracy": 0.19003627598285674,
|
|
"num_tokens": 53874594.0,
|
|
"step": 25970
|
|
},
|
|
{
|
|
"entropy": 5.526120042800903,
|
|
"epoch": 2.356222786647315,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00044441066407311205,
|
|
"loss": 5.2052,
|
|
"mean_token_accuracy": 0.18473076820373535,
|
|
"num_tokens": 53884771.0,
|
|
"step": 25975
|
|
},
|
|
{
|
|
"entropy": 5.537659406661987,
|
|
"epoch": 2.3566763425253994,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004443893687744492,
|
|
"loss": 5.1576,
|
|
"mean_token_accuracy": 0.19355572909116744,
|
|
"num_tokens": 53895181.0,
|
|
"step": 25980
|
|
},
|
|
{
|
|
"entropy": 5.390619707107544,
|
|
"epoch": 2.357129898403483,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00044436806997277096,
|
|
"loss": 5.0742,
|
|
"mean_token_accuracy": 0.2001146450638771,
|
|
"num_tokens": 53904153.0,
|
|
"step": 25985
|
|
},
|
|
{
|
|
"entropy": 5.440086460113525,
|
|
"epoch": 2.3575834542815675,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00044434676766851787,
|
|
"loss": 5.1606,
|
|
"mean_token_accuracy": 0.18983470797538757,
|
|
"num_tokens": 53914064.0,
|
|
"step": 25990
|
|
},
|
|
{
|
|
"entropy": 5.531126022338867,
|
|
"epoch": 2.3580370101596517,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044432546186213054,
|
|
"loss": 5.1836,
|
|
"mean_token_accuracy": 0.1862040400505066,
|
|
"num_tokens": 53924240.0,
|
|
"step": 25995
|
|
},
|
|
{
|
|
"entropy": 5.517126274108887,
|
|
"epoch": 2.358490566037736,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00044430415255404944,
|
|
"loss": 5.2611,
|
|
"mean_token_accuracy": 0.19215566664934158,
|
|
"num_tokens": 53935395.0,
|
|
"step": 26000
|
|
},
|
|
{
|
|
"entropy": 5.449412298202515,
|
|
"epoch": 2.35894412191582,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00044428283974471533,
|
|
"loss": 5.1679,
|
|
"mean_token_accuracy": 0.19037346988916398,
|
|
"num_tokens": 53945768.0,
|
|
"step": 26005
|
|
},
|
|
{
|
|
"entropy": 5.430865716934204,
|
|
"epoch": 2.359397677793904,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.000444261523434569,
|
|
"loss": 5.1587,
|
|
"mean_token_accuracy": 0.19527660310268402,
|
|
"num_tokens": 53956467.0,
|
|
"step": 26010
|
|
},
|
|
{
|
|
"entropy": 5.4443402767181395,
|
|
"epoch": 2.3598512336719883,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00044424020362405126,
|
|
"loss": 5.1067,
|
|
"mean_token_accuracy": 0.19516755938529967,
|
|
"num_tokens": 53967587.0,
|
|
"step": 26015
|
|
},
|
|
{
|
|
"entropy": 5.431970024108887,
|
|
"epoch": 2.3603047895500726,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004442188803136029,
|
|
"loss": 5.1437,
|
|
"mean_token_accuracy": 0.19296565651893616,
|
|
"num_tokens": 53977691.0,
|
|
"step": 26020
|
|
},
|
|
{
|
|
"entropy": 5.414587020874023,
|
|
"epoch": 2.360758345428157,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000444197553503665,
|
|
"loss": 5.2539,
|
|
"mean_token_accuracy": 0.18249812424182893,
|
|
"num_tokens": 53987608.0,
|
|
"step": 26025
|
|
},
|
|
{
|
|
"entropy": 5.577799510955811,
|
|
"epoch": 2.361211901306241,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00044417622319467857,
|
|
"loss": 5.2954,
|
|
"mean_token_accuracy": 0.18445613533258437,
|
|
"num_tokens": 53998010.0,
|
|
"step": 26030
|
|
},
|
|
{
|
|
"entropy": 5.519234704971313,
|
|
"epoch": 2.361665457184325,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00044415488938708475,
|
|
"loss": 5.2121,
|
|
"mean_token_accuracy": 0.1925637036561966,
|
|
"num_tokens": 54009852.0,
|
|
"step": 26035
|
|
},
|
|
{
|
|
"entropy": 5.502933168411255,
|
|
"epoch": 2.3621190130624092,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004441335520813247,
|
|
"loss": 5.126,
|
|
"mean_token_accuracy": 0.1941057413816452,
|
|
"num_tokens": 54019635.0,
|
|
"step": 26040
|
|
},
|
|
{
|
|
"entropy": 5.491660118103027,
|
|
"epoch": 2.3625725689404935,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00044411221127783966,
|
|
"loss": 5.1739,
|
|
"mean_token_accuracy": 0.19172800928354264,
|
|
"num_tokens": 54030046.0,
|
|
"step": 26045
|
|
},
|
|
{
|
|
"entropy": 5.505272388458252,
|
|
"epoch": 2.3630261248185778,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004440908669770711,
|
|
"loss": 5.1707,
|
|
"mean_token_accuracy": 0.1877626359462738,
|
|
"num_tokens": 54041197.0,
|
|
"step": 26050
|
|
},
|
|
{
|
|
"entropy": 5.5106299877166744,
|
|
"epoch": 2.3634796806966616,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004440695191794602,
|
|
"loss": 5.159,
|
|
"mean_token_accuracy": 0.1953093782067299,
|
|
"num_tokens": 54051592.0,
|
|
"step": 26055
|
|
},
|
|
{
|
|
"entropy": 5.502125072479248,
|
|
"epoch": 2.363933236574746,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004440481678854487,
|
|
"loss": 5.2384,
|
|
"mean_token_accuracy": 0.17919106930494308,
|
|
"num_tokens": 54062893.0,
|
|
"step": 26060
|
|
},
|
|
{
|
|
"entropy": 5.519675827026367,
|
|
"epoch": 2.36438679245283,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00044402681309547786,
|
|
"loss": 5.2502,
|
|
"mean_token_accuracy": 0.18472384363412858,
|
|
"num_tokens": 54073651.0,
|
|
"step": 26065
|
|
},
|
|
{
|
|
"entropy": 5.4599912643432615,
|
|
"epoch": 2.3648403483309144,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00044400545480998956,
|
|
"loss": 5.1688,
|
|
"mean_token_accuracy": 0.1982242926955223,
|
|
"num_tokens": 54084889.0,
|
|
"step": 26070
|
|
},
|
|
{
|
|
"entropy": 5.431340599060059,
|
|
"epoch": 2.3652939042089987,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00044398409302942533,
|
|
"loss": 5.1876,
|
|
"mean_token_accuracy": 0.1896272376179695,
|
|
"num_tokens": 54095724.0,
|
|
"step": 26075
|
|
},
|
|
{
|
|
"entropy": 5.477410936355591,
|
|
"epoch": 2.365747460087083,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000443962727754227,
|
|
"loss": 5.1538,
|
|
"mean_token_accuracy": 0.18897663205862045,
|
|
"num_tokens": 54106581.0,
|
|
"step": 26080
|
|
},
|
|
{
|
|
"entropy": 5.552161359786988,
|
|
"epoch": 2.3662010159651667,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004439413589848364,
|
|
"loss": 5.188,
|
|
"mean_token_accuracy": 0.1896439254283905,
|
|
"num_tokens": 54116074.0,
|
|
"step": 26085
|
|
},
|
|
{
|
|
"entropy": 5.451416063308716,
|
|
"epoch": 2.366654571843251,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004439199867216955,
|
|
"loss": 5.2034,
|
|
"mean_token_accuracy": 0.19002893269062043,
|
|
"num_tokens": 54126902.0,
|
|
"step": 26090
|
|
},
|
|
{
|
|
"entropy": 5.432494735717773,
|
|
"epoch": 2.3671081277213353,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004438986109652462,
|
|
"loss": 5.1497,
|
|
"mean_token_accuracy": 0.19214021414518356,
|
|
"num_tokens": 54137554.0,
|
|
"step": 26095
|
|
},
|
|
{
|
|
"entropy": 5.5106971740722654,
|
|
"epoch": 2.3675616835994195,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004438772317159306,
|
|
"loss": 5.1522,
|
|
"mean_token_accuracy": 0.1880502849817276,
|
|
"num_tokens": 54148035.0,
|
|
"step": 26100
|
|
},
|
|
{
|
|
"entropy": 5.504541635513306,
|
|
"epoch": 2.368015239477504,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00044385584897419075,
|
|
"loss": 5.1404,
|
|
"mean_token_accuracy": 0.19908200353384017,
|
|
"num_tokens": 54157417.0,
|
|
"step": 26105
|
|
},
|
|
{
|
|
"entropy": 5.451739931106568,
|
|
"epoch": 2.3684687953555876,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000443834462740469,
|
|
"loss": 5.1989,
|
|
"mean_token_accuracy": 0.18985515534877778,
|
|
"num_tokens": 54168353.0,
|
|
"step": 26110
|
|
},
|
|
{
|
|
"entropy": 5.434903335571289,
|
|
"epoch": 2.368922351233672,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004438130730152074,
|
|
"loss": 5.2427,
|
|
"mean_token_accuracy": 0.1855220690369606,
|
|
"num_tokens": 54180182.0,
|
|
"step": 26115
|
|
},
|
|
{
|
|
"entropy": 5.54587607383728,
|
|
"epoch": 2.369375907111756,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044379167979884847,
|
|
"loss": 5.2064,
|
|
"mean_token_accuracy": 0.1883375123143196,
|
|
"num_tokens": 54190973.0,
|
|
"step": 26120
|
|
},
|
|
{
|
|
"entropy": 5.565592432022095,
|
|
"epoch": 2.3698294629898404,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004437702830918347,
|
|
"loss": 5.2679,
|
|
"mean_token_accuracy": 0.186723954975605,
|
|
"num_tokens": 54202077.0,
|
|
"step": 26125
|
|
},
|
|
{
|
|
"entropy": 5.470746850967407,
|
|
"epoch": 2.3702830188679247,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004437488828946084,
|
|
"loss": 5.1623,
|
|
"mean_token_accuracy": 0.19240250587463378,
|
|
"num_tokens": 54211778.0,
|
|
"step": 26130
|
|
},
|
|
{
|
|
"entropy": 5.450083303451538,
|
|
"epoch": 2.3707365747460085,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004437274792076122,
|
|
"loss": 5.065,
|
|
"mean_token_accuracy": 0.20132106691598892,
|
|
"num_tokens": 54220941.0,
|
|
"step": 26135
|
|
},
|
|
{
|
|
"entropy": 5.489142847061157,
|
|
"epoch": 2.371190130624093,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044370607203128874,
|
|
"loss": 5.2579,
|
|
"mean_token_accuracy": 0.1870471492409706,
|
|
"num_tokens": 54231602.0,
|
|
"step": 26140
|
|
},
|
|
{
|
|
"entropy": 5.5124797344207765,
|
|
"epoch": 2.371643686502177,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004436846613660807,
|
|
"loss": 5.1904,
|
|
"mean_token_accuracy": 0.18974509686231614,
|
|
"num_tokens": 54241797.0,
|
|
"step": 26145
|
|
},
|
|
{
|
|
"entropy": 5.547727966308594,
|
|
"epoch": 2.3720972423802613,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004436632472124308,
|
|
"loss": 5.2603,
|
|
"mean_token_accuracy": 0.1849563330411911,
|
|
"num_tokens": 54253085.0,
|
|
"step": 26150
|
|
},
|
|
{
|
|
"entropy": 5.603859901428223,
|
|
"epoch": 2.3725507982583456,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004436418295707821,
|
|
"loss": 5.2063,
|
|
"mean_token_accuracy": 0.1899482026696205,
|
|
"num_tokens": 54262164.0,
|
|
"step": 26155
|
|
},
|
|
{
|
|
"entropy": 5.4451171398162845,
|
|
"epoch": 2.3730043541364294,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004436204084415774,
|
|
"loss": 5.1916,
|
|
"mean_token_accuracy": 0.1877191558480263,
|
|
"num_tokens": 54271922.0,
|
|
"step": 26160
|
|
},
|
|
{
|
|
"entropy": 5.48450722694397,
|
|
"epoch": 2.3734579100145137,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004435989838252596,
|
|
"loss": 5.1488,
|
|
"mean_token_accuracy": 0.19362039715051652,
|
|
"num_tokens": 54281738.0,
|
|
"step": 26165
|
|
},
|
|
{
|
|
"entropy": 5.463846445083618,
|
|
"epoch": 2.373911465892598,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004435775557222719,
|
|
"loss": 5.1784,
|
|
"mean_token_accuracy": 0.19034328758716584,
|
|
"num_tokens": 54292252.0,
|
|
"step": 26170
|
|
},
|
|
{
|
|
"entropy": 5.476745891571045,
|
|
"epoch": 2.374365021770682,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00044355612413305736,
|
|
"loss": 5.233,
|
|
"mean_token_accuracy": 0.18672363460063934,
|
|
"num_tokens": 54302518.0,
|
|
"step": 26175
|
|
},
|
|
{
|
|
"entropy": 5.514387893676758,
|
|
"epoch": 2.3748185776487665,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004435346890580593,
|
|
"loss": 5.1946,
|
|
"mean_token_accuracy": 0.19195342510938646,
|
|
"num_tokens": 54312917.0,
|
|
"step": 26180
|
|
},
|
|
{
|
|
"entropy": 5.48413405418396,
|
|
"epoch": 2.3752721335268507,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00044351325049772085,
|
|
"loss": 5.1391,
|
|
"mean_token_accuracy": 0.19377283602952958,
|
|
"num_tokens": 54322552.0,
|
|
"step": 26185
|
|
},
|
|
{
|
|
"entropy": 5.463000059127808,
|
|
"epoch": 2.3757256894049346,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00044349180845248536,
|
|
"loss": 5.1906,
|
|
"mean_token_accuracy": 0.19223040640354155,
|
|
"num_tokens": 54332917.0,
|
|
"step": 26190
|
|
},
|
|
{
|
|
"entropy": 5.425872468948365,
|
|
"epoch": 2.376179245283019,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004434703629227964,
|
|
"loss": 5.1444,
|
|
"mean_token_accuracy": 0.19416536688804625,
|
|
"num_tokens": 54342791.0,
|
|
"step": 26195
|
|
},
|
|
{
|
|
"entropy": 5.432805299758911,
|
|
"epoch": 2.376632801161103,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004434489139090975,
|
|
"loss": 5.0492,
|
|
"mean_token_accuracy": 0.20332444459199905,
|
|
"num_tokens": 54352821.0,
|
|
"step": 26200
|
|
},
|
|
{
|
|
"entropy": 5.524904680252075,
|
|
"epoch": 2.3770863570391874,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00044342746141183206,
|
|
"loss": 5.2563,
|
|
"mean_token_accuracy": 0.18560180962085723,
|
|
"num_tokens": 54363095.0,
|
|
"step": 26205
|
|
},
|
|
{
|
|
"entropy": 5.414607954025269,
|
|
"epoch": 2.377539912917271,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004434060054314438,
|
|
"loss": 5.1461,
|
|
"mean_token_accuracy": 0.19071876406669616,
|
|
"num_tokens": 54373841.0,
|
|
"step": 26210
|
|
},
|
|
{
|
|
"entropy": 5.430546665191651,
|
|
"epoch": 2.3779934687953554,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044338454596837637,
|
|
"loss": 5.1128,
|
|
"mean_token_accuracy": 0.19370895028114318,
|
|
"num_tokens": 54385012.0,
|
|
"step": 26215
|
|
},
|
|
{
|
|
"entropy": 5.4907958984375,
|
|
"epoch": 2.3784470246734397,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004433630830230737,
|
|
"loss": 5.1743,
|
|
"mean_token_accuracy": 0.19250587671995162,
|
|
"num_tokens": 54395298.0,
|
|
"step": 26220
|
|
},
|
|
{
|
|
"entropy": 5.461127185821534,
|
|
"epoch": 2.378900580551524,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004433416165959795,
|
|
"loss": 5.1799,
|
|
"mean_token_accuracy": 0.1892583727836609,
|
|
"num_tokens": 54405752.0,
|
|
"step": 26225
|
|
},
|
|
{
|
|
"entropy": 5.539376831054687,
|
|
"epoch": 2.3793541364296082,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004433201466875378,
|
|
"loss": 5.2023,
|
|
"mean_token_accuracy": 0.18872940987348558,
|
|
"num_tokens": 54416607.0,
|
|
"step": 26230
|
|
},
|
|
{
|
|
"entropy": 5.5053599834442135,
|
|
"epoch": 2.3798076923076925,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004432986732981926,
|
|
"loss": 5.1606,
|
|
"mean_token_accuracy": 0.1934921845793724,
|
|
"num_tokens": 54426873.0,
|
|
"step": 26235
|
|
},
|
|
{
|
|
"entropy": 5.410028982162475,
|
|
"epoch": 2.3802612481857763,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000443277196428388,
|
|
"loss": 5.0932,
|
|
"mean_token_accuracy": 0.20053356289863586,
|
|
"num_tokens": 54437611.0,
|
|
"step": 26240
|
|
},
|
|
{
|
|
"entropy": 5.536921215057373,
|
|
"epoch": 2.3807148040638606,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000443255716078568,
|
|
"loss": 5.1984,
|
|
"mean_token_accuracy": 0.19148409962654114,
|
|
"num_tokens": 54448992.0,
|
|
"step": 26245
|
|
},
|
|
{
|
|
"entropy": 5.470829725265503,
|
|
"epoch": 2.381168359941945,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004432342322491769,
|
|
"loss": 5.1466,
|
|
"mean_token_accuracy": 0.19786928445100785,
|
|
"num_tokens": 54459172.0,
|
|
"step": 26250
|
|
},
|
|
{
|
|
"entropy": 5.414367914199829,
|
|
"epoch": 2.381621915820029,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00044321274494065903,
|
|
"loss": 5.1317,
|
|
"mean_token_accuracy": 0.1947687655687332,
|
|
"num_tokens": 54469660.0,
|
|
"step": 26255
|
|
},
|
|
{
|
|
"entropy": 5.484135675430298,
|
|
"epoch": 2.3820754716981134,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00044319125415345886,
|
|
"loss": 5.2337,
|
|
"mean_token_accuracy": 0.1898196369409561,
|
|
"num_tokens": 54479567.0,
|
|
"step": 26260
|
|
},
|
|
{
|
|
"entropy": 5.453938341140747,
|
|
"epoch": 2.3825290275761972,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004431697598880205,
|
|
"loss": 5.2213,
|
|
"mean_token_accuracy": 0.19236694127321244,
|
|
"num_tokens": 54489690.0,
|
|
"step": 26265
|
|
},
|
|
{
|
|
"entropy": 5.504976511001587,
|
|
"epoch": 2.3829825834542815,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00044314826214478877,
|
|
"loss": 5.2043,
|
|
"mean_token_accuracy": 0.18891242295503616,
|
|
"num_tokens": 54500876.0,
|
|
"step": 26270
|
|
},
|
|
{
|
|
"entropy": 5.518356370925903,
|
|
"epoch": 2.3834361393323658,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00044312676092420804,
|
|
"loss": 5.2126,
|
|
"mean_token_accuracy": 0.18424091190099717,
|
|
"num_tokens": 54510988.0,
|
|
"step": 26275
|
|
},
|
|
{
|
|
"entropy": 5.507981634140014,
|
|
"epoch": 2.38388969521045,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004431052562267231,
|
|
"loss": 5.1434,
|
|
"mean_token_accuracy": 0.19814385771751403,
|
|
"num_tokens": 54522149.0,
|
|
"step": 26280
|
|
},
|
|
{
|
|
"entropy": 5.508959627151489,
|
|
"epoch": 2.3843432510885343,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00044308374805277867,
|
|
"loss": 5.2941,
|
|
"mean_token_accuracy": 0.18036867678165436,
|
|
"num_tokens": 54533482.0,
|
|
"step": 26285
|
|
},
|
|
{
|
|
"entropy": 5.483785390853882,
|
|
"epoch": 2.384796806966618,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004430622364028194,
|
|
"loss": 5.2048,
|
|
"mean_token_accuracy": 0.18884738981723787,
|
|
"num_tokens": 54543058.0,
|
|
"step": 26290
|
|
},
|
|
{
|
|
"entropy": 5.5157825469970705,
|
|
"epoch": 2.3852503628447024,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00044304072127729035,
|
|
"loss": 5.1733,
|
|
"mean_token_accuracy": 0.19027304649353027,
|
|
"num_tokens": 54552655.0,
|
|
"step": 26295
|
|
},
|
|
{
|
|
"entropy": 5.465918445587159,
|
|
"epoch": 2.3857039187227866,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00044301920267663633,
|
|
"loss": 5.0978,
|
|
"mean_token_accuracy": 0.18902018815279006,
|
|
"num_tokens": 54562696.0,
|
|
"step": 26300
|
|
},
|
|
{
|
|
"entropy": 5.480964422225952,
|
|
"epoch": 2.386157474600871,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004429976806013024,
|
|
"loss": 5.1572,
|
|
"mean_token_accuracy": 0.19773696660995482,
|
|
"num_tokens": 54572803.0,
|
|
"step": 26305
|
|
},
|
|
{
|
|
"entropy": 5.414204740524292,
|
|
"epoch": 2.386611030478955,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004429761550517336,
|
|
"loss": 5.2015,
|
|
"mean_token_accuracy": 0.18870255649089812,
|
|
"num_tokens": 54582450.0,
|
|
"step": 26310
|
|
},
|
|
{
|
|
"entropy": 5.378747034072876,
|
|
"epoch": 2.387064586357039,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00044295462602837504,
|
|
"loss": 5.1338,
|
|
"mean_token_accuracy": 0.19235174357891083,
|
|
"num_tokens": 54591868.0,
|
|
"step": 26315
|
|
},
|
|
{
|
|
"entropy": 5.525502920150757,
|
|
"epoch": 2.3875181422351233,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004429330935316721,
|
|
"loss": 5.1515,
|
|
"mean_token_accuracy": 0.186648990213871,
|
|
"num_tokens": 54601858.0,
|
|
"step": 26320
|
|
},
|
|
{
|
|
"entropy": 5.5094681739807125,
|
|
"epoch": 2.3879716981132075,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044291155756206996,
|
|
"loss": 5.2129,
|
|
"mean_token_accuracy": 0.1912524566054344,
|
|
"num_tokens": 54612243.0,
|
|
"step": 26325
|
|
},
|
|
{
|
|
"entropy": 5.446991682052612,
|
|
"epoch": 2.388425253991292,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00044289001812001404,
|
|
"loss": 5.0848,
|
|
"mean_token_accuracy": 0.199724280834198,
|
|
"num_tokens": 54622365.0,
|
|
"step": 26330
|
|
},
|
|
{
|
|
"entropy": 5.455876588821411,
|
|
"epoch": 2.388878809869376,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004428684752059497,
|
|
"loss": 5.1025,
|
|
"mean_token_accuracy": 0.19842044860124589,
|
|
"num_tokens": 54632356.0,
|
|
"step": 26335
|
|
},
|
|
{
|
|
"entropy": 5.513736915588379,
|
|
"epoch": 2.3893323657474603,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004428469288203226,
|
|
"loss": 5.1901,
|
|
"mean_token_accuracy": 0.18965649157762526,
|
|
"num_tokens": 54642976.0,
|
|
"step": 26340
|
|
},
|
|
{
|
|
"entropy": 5.549398469924927,
|
|
"epoch": 2.389785921625544,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004428253789635783,
|
|
"loss": 5.1944,
|
|
"mean_token_accuracy": 0.19311258047819138,
|
|
"num_tokens": 54652597.0,
|
|
"step": 26345
|
|
},
|
|
{
|
|
"entropy": 5.447600030899048,
|
|
"epoch": 2.3902394775036284,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004428038256361622,
|
|
"loss": 5.3017,
|
|
"mean_token_accuracy": 0.18540326207876207,
|
|
"num_tokens": 54662930.0,
|
|
"step": 26350
|
|
},
|
|
{
|
|
"entropy": 5.648104429244995,
|
|
"epoch": 2.3906930333817127,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004427822688385203,
|
|
"loss": 5.4062,
|
|
"mean_token_accuracy": 0.1865266516804695,
|
|
"num_tokens": 54674562.0,
|
|
"step": 26355
|
|
},
|
|
{
|
|
"entropy": 5.531478500366211,
|
|
"epoch": 2.391146589259797,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004427607085710984,
|
|
"loss": 5.1906,
|
|
"mean_token_accuracy": 0.1876704290509224,
|
|
"num_tokens": 54684432.0,
|
|
"step": 26360
|
|
},
|
|
{
|
|
"entropy": 5.4847814559936525,
|
|
"epoch": 2.3916001451378808,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00044273914483434226,
|
|
"loss": 5.199,
|
|
"mean_token_accuracy": 0.19111575186252594,
|
|
"num_tokens": 54694060.0,
|
|
"step": 26365
|
|
},
|
|
{
|
|
"entropy": 5.432723569869995,
|
|
"epoch": 2.392053701015965,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00044271757762869777,
|
|
"loss": 5.2145,
|
|
"mean_token_accuracy": 0.1874765932559967,
|
|
"num_tokens": 54704411.0,
|
|
"step": 26370
|
|
},
|
|
{
|
|
"entropy": 5.489800882339478,
|
|
"epoch": 2.3925072568940493,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004426960069546112,
|
|
"loss": 5.1903,
|
|
"mean_token_accuracy": 0.19239063411951066,
|
|
"num_tokens": 54715185.0,
|
|
"step": 26375
|
|
},
|
|
{
|
|
"entropy": 5.50071702003479,
|
|
"epoch": 2.3929608127721336,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004426744328125284,
|
|
"loss": 5.0761,
|
|
"mean_token_accuracy": 0.20016064792871474,
|
|
"num_tokens": 54725529.0,
|
|
"step": 26380
|
|
},
|
|
{
|
|
"entropy": 5.530541181564331,
|
|
"epoch": 2.393414368650218,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004426528552028955,
|
|
"loss": 5.2639,
|
|
"mean_token_accuracy": 0.19363997876644135,
|
|
"num_tokens": 54736992.0,
|
|
"step": 26385
|
|
},
|
|
{
|
|
"entropy": 5.444268989562988,
|
|
"epoch": 2.393867924528302,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00044263127412615897,
|
|
"loss": 5.1479,
|
|
"mean_token_accuracy": 0.1875066876411438,
|
|
"num_tokens": 54746951.0,
|
|
"step": 26390
|
|
},
|
|
{
|
|
"entropy": 5.468863821029663,
|
|
"epoch": 2.394321480406386,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004426096895827649,
|
|
"loss": 5.1179,
|
|
"mean_token_accuracy": 0.19618390500545502,
|
|
"num_tokens": 54757272.0,
|
|
"step": 26395
|
|
},
|
|
{
|
|
"entropy": 5.52228422164917,
|
|
"epoch": 2.39477503628447,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00044258810157315977,
|
|
"loss": 5.231,
|
|
"mean_token_accuracy": 0.18838101476430893,
|
|
"num_tokens": 54767835.0,
|
|
"step": 26400
|
|
},
|
|
{
|
|
"entropy": 5.4872955799102785,
|
|
"epoch": 2.3952285921625545,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00044256651009779,
|
|
"loss": 5.1824,
|
|
"mean_token_accuracy": 0.19678659737110138,
|
|
"num_tokens": 54778432.0,
|
|
"step": 26405
|
|
},
|
|
{
|
|
"entropy": 5.524017095565796,
|
|
"epoch": 2.3956821480406387,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00044254491515710213,
|
|
"loss": 5.2421,
|
|
"mean_token_accuracy": 0.18545918613672258,
|
|
"num_tokens": 54788582.0,
|
|
"step": 26410
|
|
},
|
|
{
|
|
"entropy": 5.5137725353240965,
|
|
"epoch": 2.3961357039187225,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004425233167515426,
|
|
"loss": 5.2129,
|
|
"mean_token_accuracy": 0.19380639046430587,
|
|
"num_tokens": 54798848.0,
|
|
"step": 26415
|
|
},
|
|
{
|
|
"entropy": 5.465574598312378,
|
|
"epoch": 2.396589259796807,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004425017148815583,
|
|
"loss": 5.1127,
|
|
"mean_token_accuracy": 0.19185822010040282,
|
|
"num_tokens": 54809867.0,
|
|
"step": 26420
|
|
},
|
|
{
|
|
"entropy": 5.478222322463989,
|
|
"epoch": 2.397042815674891,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.00044248010954759575,
|
|
"loss": 5.1613,
|
|
"mean_token_accuracy": 0.1883823275566101,
|
|
"num_tokens": 54819905.0,
|
|
"step": 26425
|
|
},
|
|
{
|
|
"entropy": 5.450499439239502,
|
|
"epoch": 2.3974963715529753,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00044245850075010193,
|
|
"loss": 5.183,
|
|
"mean_token_accuracy": 0.194965922832489,
|
|
"num_tokens": 54829723.0,
|
|
"step": 26430
|
|
},
|
|
{
|
|
"entropy": 5.437198781967163,
|
|
"epoch": 2.3979499274310596,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.00044243688848952364,
|
|
"loss": 5.1169,
|
|
"mean_token_accuracy": 0.19342725723981857,
|
|
"num_tokens": 54840008.0,
|
|
"step": 26435
|
|
},
|
|
{
|
|
"entropy": 5.501434278488159,
|
|
"epoch": 2.398403483309144,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004424152727663078,
|
|
"loss": 5.1718,
|
|
"mean_token_accuracy": 0.18947475254535676,
|
|
"num_tokens": 54851693.0,
|
|
"step": 26440
|
|
},
|
|
{
|
|
"entropy": 5.5563475608825685,
|
|
"epoch": 2.3988570391872277,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004423936535809015,
|
|
"loss": 5.1571,
|
|
"mean_token_accuracy": 0.18665498346090317,
|
|
"num_tokens": 54862086.0,
|
|
"step": 26445
|
|
},
|
|
{
|
|
"entropy": 5.567739963531494,
|
|
"epoch": 2.399310595065312,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004423720309337517,
|
|
"loss": 5.2798,
|
|
"mean_token_accuracy": 0.18893419355154037,
|
|
"num_tokens": 54872883.0,
|
|
"step": 26450
|
|
},
|
|
{
|
|
"entropy": 5.484560108184814,
|
|
"epoch": 2.3997641509433962,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00044235040482530576,
|
|
"loss": 5.1896,
|
|
"mean_token_accuracy": 0.18765744268894197,
|
|
"num_tokens": 54882815.0,
|
|
"step": 26455
|
|
},
|
|
{
|
|
"entropy": 5.28981204032898,
|
|
"epoch": 2.4002177068214805,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004423287752560108,
|
|
"loss": 5.0127,
|
|
"mean_token_accuracy": 0.20500417351722716,
|
|
"num_tokens": 54892480.0,
|
|
"step": 26460
|
|
},
|
|
{
|
|
"entropy": 5.383967113494873,
|
|
"epoch": 2.4006712626995648,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00044230714222631397,
|
|
"loss": 5.0487,
|
|
"mean_token_accuracy": 0.20512762814760208,
|
|
"num_tokens": 54901607.0,
|
|
"step": 26465
|
|
},
|
|
{
|
|
"entropy": 5.5950798988342285,
|
|
"epoch": 2.4011248185776486,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00044228550573666294,
|
|
"loss": 5.318,
|
|
"mean_token_accuracy": 0.18752305060625077,
|
|
"num_tokens": 54913545.0,
|
|
"step": 26470
|
|
},
|
|
{
|
|
"entropy": 5.579449987411499,
|
|
"epoch": 2.401578374455733,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000442263865787505,
|
|
"loss": 5.2195,
|
|
"mean_token_accuracy": 0.18877409547567367,
|
|
"num_tokens": 54924392.0,
|
|
"step": 26475
|
|
},
|
|
{
|
|
"entropy": 5.463951301574707,
|
|
"epoch": 2.402031930333817,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004422422223792877,
|
|
"loss": 5.1805,
|
|
"mean_token_accuracy": 0.19318219274282455,
|
|
"num_tokens": 54934114.0,
|
|
"step": 26480
|
|
},
|
|
{
|
|
"entropy": 5.510929965972901,
|
|
"epoch": 2.4024854862119014,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004422205755124586,
|
|
"loss": 5.1944,
|
|
"mean_token_accuracy": 0.18810656517744065,
|
|
"num_tokens": 54944268.0,
|
|
"step": 26485
|
|
},
|
|
{
|
|
"entropy": 5.510135507583618,
|
|
"epoch": 2.4029390420899857,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00044219892518746536,
|
|
"loss": 5.1968,
|
|
"mean_token_accuracy": 0.18537435084581375,
|
|
"num_tokens": 54954877.0,
|
|
"step": 26490
|
|
},
|
|
{
|
|
"entropy": 5.4478291988372805,
|
|
"epoch": 2.4033925979680695,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044217727140475585,
|
|
"loss": 5.1335,
|
|
"mean_token_accuracy": 0.19740778654813768,
|
|
"num_tokens": 54964745.0,
|
|
"step": 26495
|
|
},
|
|
{
|
|
"entropy": 5.4581403732299805,
|
|
"epoch": 2.4038461538461537,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044215561416477764,
|
|
"loss": 5.0562,
|
|
"mean_token_accuracy": 0.19499919563531876,
|
|
"num_tokens": 54975256.0,
|
|
"step": 26500
|
|
},
|
|
{
|
|
"entropy": 5.5184284210205075,
|
|
"epoch": 2.404299709724238,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004421339534679788,
|
|
"loss": 5.2075,
|
|
"mean_token_accuracy": 0.18477817475795746,
|
|
"num_tokens": 54986226.0,
|
|
"step": 26505
|
|
},
|
|
{
|
|
"entropy": 5.513497638702392,
|
|
"epoch": 2.4047532656023223,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004421122893148072,
|
|
"loss": 5.2082,
|
|
"mean_token_accuracy": 0.18181806057691574,
|
|
"num_tokens": 54997350.0,
|
|
"step": 26510
|
|
},
|
|
{
|
|
"entropy": 5.492211198806762,
|
|
"epoch": 2.4052068214804065,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00044209062170571086,
|
|
"loss": 5.1531,
|
|
"mean_token_accuracy": 0.1939580485224724,
|
|
"num_tokens": 55007947.0,
|
|
"step": 26515
|
|
},
|
|
{
|
|
"entropy": 5.456211996078491,
|
|
"epoch": 2.4056603773584904,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004420689506411379,
|
|
"loss": 5.1938,
|
|
"mean_token_accuracy": 0.19209712892770767,
|
|
"num_tokens": 55018789.0,
|
|
"step": 26520
|
|
},
|
|
{
|
|
"entropy": 5.46499490737915,
|
|
"epoch": 2.4061139332365746,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044204727612153643,
|
|
"loss": 5.1169,
|
|
"mean_token_accuracy": 0.19282877445220947,
|
|
"num_tokens": 55028934.0,
|
|
"step": 26525
|
|
},
|
|
{
|
|
"entropy": 5.469417142868042,
|
|
"epoch": 2.406567489114659,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00044202559814735475,
|
|
"loss": 5.1421,
|
|
"mean_token_accuracy": 0.19694661796092988,
|
|
"num_tokens": 55039395.0,
|
|
"step": 26530
|
|
},
|
|
{
|
|
"entropy": 5.434657764434815,
|
|
"epoch": 2.407021044992743,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004420039167190411,
|
|
"loss": 5.0885,
|
|
"mean_token_accuracy": 0.193474879860878,
|
|
"num_tokens": 55049932.0,
|
|
"step": 26535
|
|
},
|
|
{
|
|
"entropy": 5.508932876586914,
|
|
"epoch": 2.4074746008708274,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000441982231837044,
|
|
"loss": 5.2111,
|
|
"mean_token_accuracy": 0.1835590958595276,
|
|
"num_tokens": 55061532.0,
|
|
"step": 26540
|
|
},
|
|
{
|
|
"entropy": 5.53223180770874,
|
|
"epoch": 2.4079281567489117,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004419605435018117,
|
|
"loss": 5.2445,
|
|
"mean_token_accuracy": 0.18833991140127182,
|
|
"num_tokens": 55072368.0,
|
|
"step": 26545
|
|
},
|
|
{
|
|
"entropy": 5.506918239593506,
|
|
"epoch": 2.4083817126269955,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004419388517137928,
|
|
"loss": 5.192,
|
|
"mean_token_accuracy": 0.18777872174978255,
|
|
"num_tokens": 55083128.0,
|
|
"step": 26550
|
|
},
|
|
{
|
|
"entropy": 5.467003297805786,
|
|
"epoch": 2.40883526850508,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00044191715647343594,
|
|
"loss": 5.175,
|
|
"mean_token_accuracy": 0.19282962679862975,
|
|
"num_tokens": 55094071.0,
|
|
"step": 26555
|
|
},
|
|
{
|
|
"entropy": 5.5005392074584964,
|
|
"epoch": 2.409288824383164,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044189545778118973,
|
|
"loss": 5.1245,
|
|
"mean_token_accuracy": 0.1895374611020088,
|
|
"num_tokens": 55104504.0,
|
|
"step": 26560
|
|
},
|
|
{
|
|
"entropy": 5.486297988891602,
|
|
"epoch": 2.4097423802612483,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.000441873755637503,
|
|
"loss": 5.1958,
|
|
"mean_token_accuracy": 0.1897708296775818,
|
|
"num_tokens": 55115722.0,
|
|
"step": 26565
|
|
},
|
|
{
|
|
"entropy": 5.458194875717163,
|
|
"epoch": 2.410195936139332,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004418520500428244,
|
|
"loss": 5.1384,
|
|
"mean_token_accuracy": 0.19266563504934311,
|
|
"num_tokens": 55126628.0,
|
|
"step": 26570
|
|
},
|
|
{
|
|
"entropy": 5.442138767242431,
|
|
"epoch": 2.4106494920174164,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00044183034099760287,
|
|
"loss": 5.1656,
|
|
"mean_token_accuracy": 0.19024500697851182,
|
|
"num_tokens": 55137352.0,
|
|
"step": 26575
|
|
},
|
|
{
|
|
"entropy": 5.5461756706237795,
|
|
"epoch": 2.4111030478955007,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004418086285022874,
|
|
"loss": 5.1686,
|
|
"mean_token_accuracy": 0.19193991124629975,
|
|
"num_tokens": 55147145.0,
|
|
"step": 26580
|
|
},
|
|
{
|
|
"entropy": 5.506606912612915,
|
|
"epoch": 2.411556603773585,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00044178691255732707,
|
|
"loss": 5.1727,
|
|
"mean_token_accuracy": 0.19273429214954377,
|
|
"num_tokens": 55157386.0,
|
|
"step": 26585
|
|
},
|
|
{
|
|
"entropy": 5.514048528671265,
|
|
"epoch": 2.412010159651669,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004417651931631708,
|
|
"loss": 5.2544,
|
|
"mean_token_accuracy": 0.18872957676649094,
|
|
"num_tokens": 55168969.0,
|
|
"step": 26590
|
|
},
|
|
{
|
|
"entropy": 5.480277013778687,
|
|
"epoch": 2.4124637155297535,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004417434703202678,
|
|
"loss": 5.1706,
|
|
"mean_token_accuracy": 0.1822812795639038,
|
|
"num_tokens": 55180123.0,
|
|
"step": 26595
|
|
},
|
|
{
|
|
"entropy": 5.472670412063598,
|
|
"epoch": 2.4129172714078373,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004417217440290673,
|
|
"loss": 5.1393,
|
|
"mean_token_accuracy": 0.19516260027885438,
|
|
"num_tokens": 55190668.0,
|
|
"step": 26600
|
|
},
|
|
{
|
|
"entropy": 5.442038583755493,
|
|
"epoch": 2.4133708272859216,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004417000142900188,
|
|
"loss": 5.117,
|
|
"mean_token_accuracy": 0.19752880781888962,
|
|
"num_tokens": 55200852.0,
|
|
"step": 26605
|
|
},
|
|
{
|
|
"entropy": 5.5277503490447994,
|
|
"epoch": 2.413824383164006,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004416782811035715,
|
|
"loss": 5.3111,
|
|
"mean_token_accuracy": 0.1814615547657013,
|
|
"num_tokens": 55211174.0,
|
|
"step": 26610
|
|
},
|
|
{
|
|
"entropy": 5.412288045883178,
|
|
"epoch": 2.41427793904209,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00044165654447017485,
|
|
"loss": 5.0604,
|
|
"mean_token_accuracy": 0.1984475165605545,
|
|
"num_tokens": 55222042.0,
|
|
"step": 26615
|
|
},
|
|
{
|
|
"entropy": 5.49451756477356,
|
|
"epoch": 2.4147314949201744,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044163480439027845,
|
|
"loss": 5.2199,
|
|
"mean_token_accuracy": 0.18804965019226075,
|
|
"num_tokens": 55231688.0,
|
|
"step": 26620
|
|
},
|
|
{
|
|
"entropy": 5.530316305160523,
|
|
"epoch": 2.415185050798258,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004416130608643317,
|
|
"loss": 5.1883,
|
|
"mean_token_accuracy": 0.19272987097501754,
|
|
"num_tokens": 55241089.0,
|
|
"step": 26625
|
|
},
|
|
{
|
|
"entropy": 5.492316007614136,
|
|
"epoch": 2.4156386066763424,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004415913138927844,
|
|
"loss": 5.16,
|
|
"mean_token_accuracy": 0.1966664895415306,
|
|
"num_tokens": 55251511.0,
|
|
"step": 26630
|
|
},
|
|
{
|
|
"entropy": 5.4085160255432125,
|
|
"epoch": 2.4160921625544267,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004415695634760864,
|
|
"loss": 5.1548,
|
|
"mean_token_accuracy": 0.18956756293773652,
|
|
"num_tokens": 55262855.0,
|
|
"step": 26635
|
|
},
|
|
{
|
|
"entropy": 5.406140089035034,
|
|
"epoch": 2.416545718432511,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004415478096146873,
|
|
"loss": 5.045,
|
|
"mean_token_accuracy": 0.20041245520114898,
|
|
"num_tokens": 55273035.0,
|
|
"step": 26640
|
|
},
|
|
{
|
|
"entropy": 5.441612720489502,
|
|
"epoch": 2.4169992743105952,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000441526052309037,
|
|
"loss": 5.1496,
|
|
"mean_token_accuracy": 0.19772055596113206,
|
|
"num_tokens": 55284033.0,
|
|
"step": 26645
|
|
},
|
|
{
|
|
"entropy": 5.460815954208374,
|
|
"epoch": 2.417452830188679,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004415042915595856,
|
|
"loss": 5.1511,
|
|
"mean_token_accuracy": 0.19415093064308167,
|
|
"num_tokens": 55294290.0,
|
|
"step": 26650
|
|
},
|
|
{
|
|
"entropy": 5.495938682556153,
|
|
"epoch": 2.4179063860667633,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.000441482527366783,
|
|
"loss": 5.1787,
|
|
"mean_token_accuracy": 0.19007434248924254,
|
|
"num_tokens": 55305681.0,
|
|
"step": 26655
|
|
},
|
|
{
|
|
"entropy": 5.386196327209473,
|
|
"epoch": 2.4183599419448476,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004414607597310793,
|
|
"loss": 5.1555,
|
|
"mean_token_accuracy": 0.19187290221452713,
|
|
"num_tokens": 55316647.0,
|
|
"step": 26660
|
|
},
|
|
{
|
|
"entropy": 5.542524433135986,
|
|
"epoch": 2.418813497822932,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004414389886529247,
|
|
"loss": 5.2977,
|
|
"mean_token_accuracy": 0.18319075256586076,
|
|
"num_tokens": 55328318.0,
|
|
"step": 26665
|
|
},
|
|
{
|
|
"entropy": 5.572151517868042,
|
|
"epoch": 2.419267053701016,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004414172141327693,
|
|
"loss": 5.1906,
|
|
"mean_token_accuracy": 0.1858651578426361,
|
|
"num_tokens": 55338483.0,
|
|
"step": 26670
|
|
},
|
|
{
|
|
"entropy": 5.485858297348022,
|
|
"epoch": 2.4197206095791,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004413954361710636,
|
|
"loss": 5.2382,
|
|
"mean_token_accuracy": 0.19226597547531127,
|
|
"num_tokens": 55348648.0,
|
|
"step": 26675
|
|
},
|
|
{
|
|
"entropy": 5.465226125717163,
|
|
"epoch": 2.4201741654571842,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00044137365476825785,
|
|
"loss": 5.1184,
|
|
"mean_token_accuracy": 0.19400652199983598,
|
|
"num_tokens": 55358599.0,
|
|
"step": 26680
|
|
},
|
|
{
|
|
"entropy": 5.539732837677002,
|
|
"epoch": 2.4206277213352685,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044135186992480253,
|
|
"loss": 5.2007,
|
|
"mean_token_accuracy": 0.1895705506205559,
|
|
"num_tokens": 55369847.0,
|
|
"step": 26685
|
|
},
|
|
{
|
|
"entropy": 5.456209182739258,
|
|
"epoch": 2.4210812772133528,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044133008164114814,
|
|
"loss": 5.1808,
|
|
"mean_token_accuracy": 0.19217421114444733,
|
|
"num_tokens": 55381235.0,
|
|
"step": 26690
|
|
},
|
|
{
|
|
"entropy": 5.45429539680481,
|
|
"epoch": 2.421534833091437,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00044130828991774526,
|
|
"loss": 5.1929,
|
|
"mean_token_accuracy": 0.18920920342206954,
|
|
"num_tokens": 55391527.0,
|
|
"step": 26695
|
|
},
|
|
{
|
|
"entropy": 5.540144348144532,
|
|
"epoch": 2.4219883889695213,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00044128649475504454,
|
|
"loss": 5.2417,
|
|
"mean_token_accuracy": 0.19046828746795655,
|
|
"num_tokens": 55401528.0,
|
|
"step": 26700
|
|
},
|
|
{
|
|
"entropy": 5.565656328201294,
|
|
"epoch": 2.422441944847605,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004412646961534968,
|
|
"loss": 5.2311,
|
|
"mean_token_accuracy": 0.18398878276348113,
|
|
"num_tokens": 55411411.0,
|
|
"step": 26705
|
|
},
|
|
{
|
|
"entropy": 5.434611225128174,
|
|
"epoch": 2.4228955007256894,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004412428941135528,
|
|
"loss": 5.0458,
|
|
"mean_token_accuracy": 0.1990864098072052,
|
|
"num_tokens": 55423164.0,
|
|
"step": 26710
|
|
},
|
|
{
|
|
"entropy": 5.474182891845703,
|
|
"epoch": 2.4233490566037736,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004412210886356633,
|
|
"loss": 5.1157,
|
|
"mean_token_accuracy": 0.1968049317598343,
|
|
"num_tokens": 55433397.0,
|
|
"step": 26715
|
|
},
|
|
{
|
|
"entropy": 5.442093086242676,
|
|
"epoch": 2.423802612481858,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00044119927972027936,
|
|
"loss": 5.1534,
|
|
"mean_token_accuracy": 0.18703151494264603,
|
|
"num_tokens": 55442898.0,
|
|
"step": 26720
|
|
},
|
|
{
|
|
"entropy": 5.466669273376465,
|
|
"epoch": 2.4242561683599417,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00044117746736785195,
|
|
"loss": 5.1538,
|
|
"mean_token_accuracy": 0.19709618538618087,
|
|
"num_tokens": 55452226.0,
|
|
"step": 26725
|
|
},
|
|
{
|
|
"entropy": 5.462764692306519,
|
|
"epoch": 2.424709724238026,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004411556515788322,
|
|
"loss": 5.1562,
|
|
"mean_token_accuracy": 0.18875204771757126,
|
|
"num_tokens": 55462503.0,
|
|
"step": 26730
|
|
},
|
|
{
|
|
"entropy": 5.537374687194824,
|
|
"epoch": 2.4251632801161103,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004411338323536712,
|
|
"loss": 5.3154,
|
|
"mean_token_accuracy": 0.1863126903772354,
|
|
"num_tokens": 55472789.0,
|
|
"step": 26735
|
|
},
|
|
{
|
|
"entropy": 5.493677139282227,
|
|
"epoch": 2.4256168359941945,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004411120096928203,
|
|
"loss": 5.1117,
|
|
"mean_token_accuracy": 0.1913519099354744,
|
|
"num_tokens": 55482572.0,
|
|
"step": 26740
|
|
},
|
|
{
|
|
"entropy": 5.4902650833129885,
|
|
"epoch": 2.426070391872279,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004410901835967306,
|
|
"loss": 5.1625,
|
|
"mean_token_accuracy": 0.19771286845207214,
|
|
"num_tokens": 55493033.0,
|
|
"step": 26745
|
|
},
|
|
{
|
|
"entropy": 5.437348508834839,
|
|
"epoch": 2.426523947750363,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00044106835406585354,
|
|
"loss": 5.1215,
|
|
"mean_token_accuracy": 0.19276510030031205,
|
|
"num_tokens": 55503574.0,
|
|
"step": 26750
|
|
},
|
|
{
|
|
"entropy": 5.53547887802124,
|
|
"epoch": 2.426977503628447,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00044104652110064067,
|
|
"loss": 5.2034,
|
|
"mean_token_accuracy": 0.18402977287769318,
|
|
"num_tokens": 55514119.0,
|
|
"step": 26755
|
|
},
|
|
{
|
|
"entropy": 5.442062473297119,
|
|
"epoch": 2.427431059506531,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004410246847015435,
|
|
"loss": 5.123,
|
|
"mean_token_accuracy": 0.19014650583267212,
|
|
"num_tokens": 55524973.0,
|
|
"step": 26760
|
|
},
|
|
{
|
|
"entropy": 5.464318943023682,
|
|
"epoch": 2.4278846153846154,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004410028448690134,
|
|
"loss": 5.2202,
|
|
"mean_token_accuracy": 0.19147544652223586,
|
|
"num_tokens": 55534847.0,
|
|
"step": 26765
|
|
},
|
|
{
|
|
"entropy": 5.539493274688721,
|
|
"epoch": 2.4283381712626997,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004409810016035023,
|
|
"loss": 5.1818,
|
|
"mean_token_accuracy": 0.18547868579626084,
|
|
"num_tokens": 55544886.0,
|
|
"step": 26770
|
|
},
|
|
{
|
|
"entropy": 5.501645231246949,
|
|
"epoch": 2.4287917271407835,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004409591549054617,
|
|
"loss": 5.2384,
|
|
"mean_token_accuracy": 0.18720608204603195,
|
|
"num_tokens": 55554534.0,
|
|
"step": 26775
|
|
},
|
|
{
|
|
"entropy": 5.47567343711853,
|
|
"epoch": 2.4292452830188678,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00044093730477534355,
|
|
"loss": 5.2068,
|
|
"mean_token_accuracy": 0.1828114628791809,
|
|
"num_tokens": 55564302.0,
|
|
"step": 26780
|
|
},
|
|
{
|
|
"entropy": 5.42730073928833,
|
|
"epoch": 2.429698838896952,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004409154512135996,
|
|
"loss": 5.1199,
|
|
"mean_token_accuracy": 0.19596581012010575,
|
|
"num_tokens": 55574543.0,
|
|
"step": 26785
|
|
},
|
|
{
|
|
"entropy": 5.419318103790284,
|
|
"epoch": 2.4301523947750363,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004408935942206818,
|
|
"loss": 5.1232,
|
|
"mean_token_accuracy": 0.19859084784984588,
|
|
"num_tokens": 55583849.0,
|
|
"step": 26790
|
|
},
|
|
{
|
|
"entropy": 5.482312726974487,
|
|
"epoch": 2.4306059506531206,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004408717337970423,
|
|
"loss": 5.1912,
|
|
"mean_token_accuracy": 0.19149016886949538,
|
|
"num_tokens": 55594294.0,
|
|
"step": 26795
|
|
},
|
|
{
|
|
"entropy": 5.520352363586426,
|
|
"epoch": 2.431059506531205,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00044084986994313304,
|
|
"loss": 5.1868,
|
|
"mean_token_accuracy": 0.19246220141649245,
|
|
"num_tokens": 55604185.0,
|
|
"step": 26800
|
|
},
|
|
{
|
|
"entropy": 5.449983167648315,
|
|
"epoch": 2.4315130624092887,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004408280026594062,
|
|
"loss": 5.1271,
|
|
"mean_token_accuracy": 0.19350560307502745,
|
|
"num_tokens": 55615203.0,
|
|
"step": 26805
|
|
},
|
|
{
|
|
"entropy": 5.429185485839843,
|
|
"epoch": 2.431966618287373,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.000440806131946314,
|
|
"loss": 5.2551,
|
|
"mean_token_accuracy": 0.18904095888137817,
|
|
"num_tokens": 55626157.0,
|
|
"step": 26810
|
|
},
|
|
{
|
|
"entropy": 5.587380981445312,
|
|
"epoch": 2.432420174165457,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00044078425780430877,
|
|
"loss": 5.1853,
|
|
"mean_token_accuracy": 0.18360470235347748,
|
|
"num_tokens": 55636862.0,
|
|
"step": 26815
|
|
},
|
|
{
|
|
"entropy": 5.461618041992187,
|
|
"epoch": 2.4328737300435415,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004407623802338428,
|
|
"loss": 5.1041,
|
|
"mean_token_accuracy": 0.1938580632209778,
|
|
"num_tokens": 55647646.0,
|
|
"step": 26820
|
|
},
|
|
{
|
|
"entropy": 5.4593719959259035,
|
|
"epoch": 2.4333272859216257,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00044074049923536855,
|
|
"loss": 5.1739,
|
|
"mean_token_accuracy": 0.19680033773183822,
|
|
"num_tokens": 55659847.0,
|
|
"step": 26825
|
|
},
|
|
{
|
|
"entropy": 5.440123987197876,
|
|
"epoch": 2.4337808417997095,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004407186148093386,
|
|
"loss": 5.1917,
|
|
"mean_token_accuracy": 0.19102033078670502,
|
|
"num_tokens": 55670626.0,
|
|
"step": 26830
|
|
},
|
|
{
|
|
"entropy": 5.517249345779419,
|
|
"epoch": 2.434234397677794,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00044069672695620543,
|
|
"loss": 5.2398,
|
|
"mean_token_accuracy": 0.19013434797525405,
|
|
"num_tokens": 55681368.0,
|
|
"step": 26835
|
|
},
|
|
{
|
|
"entropy": 5.424569463729858,
|
|
"epoch": 2.434687953555878,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004406748356764217,
|
|
"loss": 5.0775,
|
|
"mean_token_accuracy": 0.19140954464673995,
|
|
"num_tokens": 55691606.0,
|
|
"step": 26840
|
|
},
|
|
{
|
|
"entropy": 5.51986141204834,
|
|
"epoch": 2.4351415094339623,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044065294097044017,
|
|
"loss": 5.2732,
|
|
"mean_token_accuracy": 0.1867581993341446,
|
|
"num_tokens": 55702223.0,
|
|
"step": 26845
|
|
},
|
|
{
|
|
"entropy": 5.472577238082886,
|
|
"epoch": 2.4355950653120466,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004406310428387136,
|
|
"loss": 5.0753,
|
|
"mean_token_accuracy": 0.19445646852254866,
|
|
"num_tokens": 55712729.0,
|
|
"step": 26850
|
|
},
|
|
{
|
|
"entropy": 5.436416149139404,
|
|
"epoch": 2.4360486211901304,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004406091412816949,
|
|
"loss": 5.1756,
|
|
"mean_token_accuracy": 0.19905580431222916,
|
|
"num_tokens": 55722863.0,
|
|
"step": 26855
|
|
},
|
|
{
|
|
"entropy": 5.488876008987427,
|
|
"epoch": 2.4365021770682147,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00044058723629983694,
|
|
"loss": 5.2473,
|
|
"mean_token_accuracy": 0.19607122391462325,
|
|
"num_tokens": 55733124.0,
|
|
"step": 26860
|
|
},
|
|
{
|
|
"entropy": 5.593814992904663,
|
|
"epoch": 2.436955732946299,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004405653278935927,
|
|
"loss": 5.1893,
|
|
"mean_token_accuracy": 0.1971494510769844,
|
|
"num_tokens": 55743438.0,
|
|
"step": 26865
|
|
},
|
|
{
|
|
"entropy": 5.426559829711914,
|
|
"epoch": 2.4374092888243832,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00044054341606341533,
|
|
"loss": 5.0417,
|
|
"mean_token_accuracy": 0.19239933043718338,
|
|
"num_tokens": 55753602.0,
|
|
"step": 26870
|
|
},
|
|
{
|
|
"entropy": 5.390385007858276,
|
|
"epoch": 2.4378628447024675,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004405215008097579,
|
|
"loss": 5.1089,
|
|
"mean_token_accuracy": 0.20121799111366273,
|
|
"num_tokens": 55763473.0,
|
|
"step": 26875
|
|
},
|
|
{
|
|
"entropy": 5.445552206039428,
|
|
"epoch": 2.4383164005805513,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00044049958213307364,
|
|
"loss": 5.1174,
|
|
"mean_token_accuracy": 0.19292762577533723,
|
|
"num_tokens": 55772848.0,
|
|
"step": 26880
|
|
},
|
|
{
|
|
"entropy": 5.4057868957519535,
|
|
"epoch": 2.4387699564586356,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00044047766003381584,
|
|
"loss": 5.1031,
|
|
"mean_token_accuracy": 0.19620450139045714,
|
|
"num_tokens": 55783468.0,
|
|
"step": 26885
|
|
},
|
|
{
|
|
"entropy": 5.483026552200317,
|
|
"epoch": 2.43922351233672,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00044045573451243793,
|
|
"loss": 5.1964,
|
|
"mean_token_accuracy": 0.19419519901275634,
|
|
"num_tokens": 55793619.0,
|
|
"step": 26890
|
|
},
|
|
{
|
|
"entropy": 5.512571048736572,
|
|
"epoch": 2.439677068214804,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00044043380556939326,
|
|
"loss": 5.1483,
|
|
"mean_token_accuracy": 0.19364974200725554,
|
|
"num_tokens": 55803869.0,
|
|
"step": 26895
|
|
},
|
|
{
|
|
"entropy": 5.546723985671997,
|
|
"epoch": 2.4401306240928884,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004404118732051353,
|
|
"loss": 5.1811,
|
|
"mean_token_accuracy": 0.19016877710819244,
|
|
"num_tokens": 55814754.0,
|
|
"step": 26900
|
|
},
|
|
{
|
|
"entropy": 5.462547397613525,
|
|
"epoch": 2.4405841799709727,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004403899374201176,
|
|
"loss": 5.1264,
|
|
"mean_token_accuracy": 0.19030200690031052,
|
|
"num_tokens": 55824862.0,
|
|
"step": 26905
|
|
},
|
|
{
|
|
"entropy": 5.368801736831665,
|
|
"epoch": 2.4410377358490565,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00044036799821479397,
|
|
"loss": 5.1155,
|
|
"mean_token_accuracy": 0.19226290732622148,
|
|
"num_tokens": 55835506.0,
|
|
"step": 26910
|
|
},
|
|
{
|
|
"entropy": 5.518970394134522,
|
|
"epoch": 2.4414912917271407,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00044034605558961786,
|
|
"loss": 5.2341,
|
|
"mean_token_accuracy": 0.1914172038435936,
|
|
"num_tokens": 55846244.0,
|
|
"step": 26915
|
|
},
|
|
{
|
|
"entropy": 5.447471666336059,
|
|
"epoch": 2.441944847605225,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044032410954504325,
|
|
"loss": 5.1108,
|
|
"mean_token_accuracy": 0.1975011259317398,
|
|
"num_tokens": 55856192.0,
|
|
"step": 26920
|
|
},
|
|
{
|
|
"entropy": 5.438844013214111,
|
|
"epoch": 2.4423984034833093,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00044030216008152394,
|
|
"loss": 5.1618,
|
|
"mean_token_accuracy": 0.1894742488861084,
|
|
"num_tokens": 55866509.0,
|
|
"step": 26925
|
|
},
|
|
{
|
|
"entropy": 5.475953674316406,
|
|
"epoch": 2.442851959361393,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00044028020719951376,
|
|
"loss": 5.18,
|
|
"mean_token_accuracy": 0.1921185851097107,
|
|
"num_tokens": 55877321.0,
|
|
"step": 26930
|
|
},
|
|
{
|
|
"entropy": 5.486038398742676,
|
|
"epoch": 2.4433055152394774,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004402582508994669,
|
|
"loss": 5.1691,
|
|
"mean_token_accuracy": 0.19011268466711045,
|
|
"num_tokens": 55887933.0,
|
|
"step": 26935
|
|
},
|
|
{
|
|
"entropy": 5.434567213058472,
|
|
"epoch": 2.4437590711175616,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044023629118183726,
|
|
"loss": 5.1082,
|
|
"mean_token_accuracy": 0.1935700461268425,
|
|
"num_tokens": 55897274.0,
|
|
"step": 26940
|
|
},
|
|
{
|
|
"entropy": 5.516665363311768,
|
|
"epoch": 2.444212626995646,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00044021432804707895,
|
|
"loss": 5.2518,
|
|
"mean_token_accuracy": 0.18589022755622864,
|
|
"num_tokens": 55907393.0,
|
|
"step": 26945
|
|
},
|
|
{
|
|
"entropy": 5.457393312454224,
|
|
"epoch": 2.44466618287373,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004401923614956463,
|
|
"loss": 5.1529,
|
|
"mean_token_accuracy": 0.19154416471719743,
|
|
"num_tokens": 55918429.0,
|
|
"step": 26950
|
|
},
|
|
{
|
|
"entropy": 5.5087274551391605,
|
|
"epoch": 2.4451197387518144,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004401703915279935,
|
|
"loss": 5.132,
|
|
"mean_token_accuracy": 0.193335685133934,
|
|
"num_tokens": 55928733.0,
|
|
"step": 26955
|
|
},
|
|
{
|
|
"entropy": 5.464372014999389,
|
|
"epoch": 2.4455732946298983,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00044014841814457486,
|
|
"loss": 5.1088,
|
|
"mean_token_accuracy": 0.19345467537641525,
|
|
"num_tokens": 55939128.0,
|
|
"step": 26960
|
|
},
|
|
{
|
|
"entropy": 5.470645570755005,
|
|
"epoch": 2.4460268505079825,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004401264413458449,
|
|
"loss": 5.2617,
|
|
"mean_token_accuracy": 0.18822572231292725,
|
|
"num_tokens": 55950237.0,
|
|
"step": 26965
|
|
},
|
|
{
|
|
"entropy": 5.47876672744751,
|
|
"epoch": 2.446480406386067,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004401044611322581,
|
|
"loss": 5.0784,
|
|
"mean_token_accuracy": 0.1949218139052391,
|
|
"num_tokens": 55960436.0,
|
|
"step": 26970
|
|
},
|
|
{
|
|
"entropy": 5.445422983169555,
|
|
"epoch": 2.446933962264151,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004400824775042689,
|
|
"loss": 5.0527,
|
|
"mean_token_accuracy": 0.19980934709310533,
|
|
"num_tokens": 55970446.0,
|
|
"step": 26975
|
|
},
|
|
{
|
|
"entropy": 5.4439233303070065,
|
|
"epoch": 2.447387518142235,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000440060490462332,
|
|
"loss": 5.1849,
|
|
"mean_token_accuracy": 0.19319839924573898,
|
|
"num_tokens": 55980706.0,
|
|
"step": 26980
|
|
},
|
|
{
|
|
"entropy": 5.481804990768433,
|
|
"epoch": 2.447841074020319,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004400385000069021,
|
|
"loss": 5.2265,
|
|
"mean_token_accuracy": 0.1852267012000084,
|
|
"num_tokens": 55990669.0,
|
|
"step": 26985
|
|
},
|
|
{
|
|
"entropy": 5.558605146408081,
|
|
"epoch": 2.4482946298984034,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00044001650613843395,
|
|
"loss": 5.2662,
|
|
"mean_token_accuracy": 0.1851024553179741,
|
|
"num_tokens": 56000709.0,
|
|
"step": 26990
|
|
},
|
|
{
|
|
"entropy": 5.460955667495727,
|
|
"epoch": 2.4487481857764877,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004399945088573824,
|
|
"loss": 5.1348,
|
|
"mean_token_accuracy": 0.19717805534601213,
|
|
"num_tokens": 56011435.0,
|
|
"step": 26995
|
|
},
|
|
{
|
|
"entropy": 5.4811478614807125,
|
|
"epoch": 2.449201741654572,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.00043997250816420246,
|
|
"loss": 5.1687,
|
|
"mean_token_accuracy": 0.19690214544534684,
|
|
"num_tokens": 56021264.0,
|
|
"step": 27000
|
|
},
|
|
{
|
|
"epoch": 2.449201741654572,
|
|
"eval_entropy": 5.268413006126611,
|
|
"eval_loss": 5.246584892272949,
|
|
"eval_mean_token_accuracy": 0.19647663870480805,
|
|
"eval_num_tokens": 56021264.0,
|
|
"eval_runtime": 26.5161,
|
|
"eval_samples_per_second": 1333.529,
|
|
"eval_steps_per_second": 166.691,
|
|
"step": 27000
|
|
},
|
|
{
|
|
"entropy": 5.448145151138306,
|
|
"epoch": 2.449655297532656,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004399505040593489,
|
|
"loss": 5.1864,
|
|
"mean_token_accuracy": 0.188833087682724,
|
|
"num_tokens": 56031463.0,
|
|
"step": 27005
|
|
},
|
|
{
|
|
"entropy": 5.399741744995117,
|
|
"epoch": 2.45010885341074,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00043992849654327695,
|
|
"loss": 5.0413,
|
|
"mean_token_accuracy": 0.2000730261206627,
|
|
"num_tokens": 56041195.0,
|
|
"step": 27010
|
|
},
|
|
{
|
|
"entropy": 5.473090076446534,
|
|
"epoch": 2.4505624092888243,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004399064856164416,
|
|
"loss": 5.1898,
|
|
"mean_token_accuracy": 0.18953490406274795,
|
|
"num_tokens": 56051840.0,
|
|
"step": 27015
|
|
},
|
|
{
|
|
"entropy": 5.4872383117675785,
|
|
"epoch": 2.4510159651669086,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00043988447127929817,
|
|
"loss": 5.2083,
|
|
"mean_token_accuracy": 0.19188733845949174,
|
|
"num_tokens": 56062535.0,
|
|
"step": 27020
|
|
},
|
|
{
|
|
"entropy": 5.465021276473999,
|
|
"epoch": 2.451469521044993,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00043986245353230173,
|
|
"loss": 5.1111,
|
|
"mean_token_accuracy": 0.20290941298007964,
|
|
"num_tokens": 56072177.0,
|
|
"step": 27025
|
|
},
|
|
{
|
|
"entropy": 5.427853631973266,
|
|
"epoch": 2.451923076923077,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00043984043237590785,
|
|
"loss": 5.1779,
|
|
"mean_token_accuracy": 0.1959080070257187,
|
|
"num_tokens": 56081607.0,
|
|
"step": 27030
|
|
},
|
|
{
|
|
"entropy": 5.498212146759033,
|
|
"epoch": 2.452376632801161,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00043981840781057185,
|
|
"loss": 5.1581,
|
|
"mean_token_accuracy": 0.1899774983525276,
|
|
"num_tokens": 56093371.0,
|
|
"step": 27035
|
|
},
|
|
{
|
|
"entropy": 5.497996139526367,
|
|
"epoch": 2.452830188679245,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00043979637983674913,
|
|
"loss": 5.1598,
|
|
"mean_token_accuracy": 0.19446336328983307,
|
|
"num_tokens": 56103973.0,
|
|
"step": 27040
|
|
},
|
|
{
|
|
"entropy": 5.4510650634765625,
|
|
"epoch": 2.4532837445573294,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004397743484548953,
|
|
"loss": 5.1633,
|
|
"mean_token_accuracy": 0.19224979728460312,
|
|
"num_tokens": 56113906.0,
|
|
"step": 27045
|
|
},
|
|
{
|
|
"entropy": 5.432815361022949,
|
|
"epoch": 2.4537373004354137,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004397523136654659,
|
|
"loss": 5.1486,
|
|
"mean_token_accuracy": 0.1899968683719635,
|
|
"num_tokens": 56124172.0,
|
|
"step": 27050
|
|
},
|
|
{
|
|
"entropy": 5.442570972442627,
|
|
"epoch": 2.454190856313498,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00043973027546891677,
|
|
"loss": 5.0102,
|
|
"mean_token_accuracy": 0.20063939094543456,
|
|
"num_tokens": 56133088.0,
|
|
"step": 27055
|
|
},
|
|
{
|
|
"entropy": 5.393769216537476,
|
|
"epoch": 2.4546444121915822,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004397082338657034,
|
|
"loss": 5.1143,
|
|
"mean_token_accuracy": 0.19996993243694305,
|
|
"num_tokens": 56143098.0,
|
|
"step": 27060
|
|
},
|
|
{
|
|
"entropy": 5.443475580215454,
|
|
"epoch": 2.455097968069666,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00043968618885628185,
|
|
"loss": 5.1293,
|
|
"mean_token_accuracy": 0.20092600733041763,
|
|
"num_tokens": 56153889.0,
|
|
"step": 27065
|
|
},
|
|
{
|
|
"entropy": 5.4067576885223385,
|
|
"epoch": 2.4555515239477503,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00043966414044110805,
|
|
"loss": 5.1025,
|
|
"mean_token_accuracy": 0.19481375217437744,
|
|
"num_tokens": 56164164.0,
|
|
"step": 27070
|
|
},
|
|
{
|
|
"entropy": 5.492004680633545,
|
|
"epoch": 2.4560050798258346,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00043964208862063775,
|
|
"loss": 5.1916,
|
|
"mean_token_accuracy": 0.19288532733917235,
|
|
"num_tokens": 56173172.0,
|
|
"step": 27075
|
|
},
|
|
{
|
|
"entropy": 5.497450876235962,
|
|
"epoch": 2.456458635703919,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00043962003339532714,
|
|
"loss": 5.149,
|
|
"mean_token_accuracy": 0.19758872538805008,
|
|
"num_tokens": 56183127.0,
|
|
"step": 27080
|
|
},
|
|
{
|
|
"entropy": 5.449055147171021,
|
|
"epoch": 2.4569121915820027,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00043959797476563226,
|
|
"loss": 5.1784,
|
|
"mean_token_accuracy": 0.19480707198381425,
|
|
"num_tokens": 56192528.0,
|
|
"step": 27085
|
|
},
|
|
{
|
|
"entropy": 5.422716236114502,
|
|
"epoch": 2.457365747460087,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00043957591273200943,
|
|
"loss": 5.13,
|
|
"mean_token_accuracy": 0.19299134314060212,
|
|
"num_tokens": 56203239.0,
|
|
"step": 27090
|
|
},
|
|
{
|
|
"entropy": 5.526778888702393,
|
|
"epoch": 2.4578193033381712,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004395538472949146,
|
|
"loss": 5.1992,
|
|
"mean_token_accuracy": 0.18980610072612764,
|
|
"num_tokens": 56214068.0,
|
|
"step": 27095
|
|
},
|
|
{
|
|
"entropy": 5.514319944381714,
|
|
"epoch": 2.4582728592162555,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004395317784548045,
|
|
"loss": 5.1877,
|
|
"mean_token_accuracy": 0.18344323784112931,
|
|
"num_tokens": 56224829.0,
|
|
"step": 27100
|
|
},
|
|
{
|
|
"entropy": 5.478230381011963,
|
|
"epoch": 2.4587264150943398,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004395097062121351,
|
|
"loss": 5.1952,
|
|
"mean_token_accuracy": 0.19008611440658568,
|
|
"num_tokens": 56235412.0,
|
|
"step": 27105
|
|
},
|
|
{
|
|
"entropy": 5.515901231765747,
|
|
"epoch": 2.459179970972424,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00043948763056736315,
|
|
"loss": 5.2321,
|
|
"mean_token_accuracy": 0.19119343310594558,
|
|
"num_tokens": 56246785.0,
|
|
"step": 27110
|
|
},
|
|
{
|
|
"entropy": 5.51850380897522,
|
|
"epoch": 2.459633526850508,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000439465551520945,
|
|
"loss": 5.2017,
|
|
"mean_token_accuracy": 0.18832609355449675,
|
|
"num_tokens": 56256701.0,
|
|
"step": 27115
|
|
},
|
|
{
|
|
"entropy": 5.477804470062256,
|
|
"epoch": 2.460087082728592,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00043944346907333744,
|
|
"loss": 5.1598,
|
|
"mean_token_accuracy": 0.19609074145555497,
|
|
"num_tokens": 56267418.0,
|
|
"step": 27120
|
|
},
|
|
{
|
|
"entropy": 5.425305700302124,
|
|
"epoch": 2.4605406386066764,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000439421383224997,
|
|
"loss": 5.0786,
|
|
"mean_token_accuracy": 0.19687206894159318,
|
|
"num_tokens": 56278232.0,
|
|
"step": 27125
|
|
},
|
|
{
|
|
"entropy": 5.512353515625,
|
|
"epoch": 2.4609941944847606,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004393992939763804,
|
|
"loss": 5.1746,
|
|
"mean_token_accuracy": 0.1979220137000084,
|
|
"num_tokens": 56289866.0,
|
|
"step": 27130
|
|
},
|
|
{
|
|
"entropy": 5.449100637435913,
|
|
"epoch": 2.4614477503628445,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00043937720132794457,
|
|
"loss": 5.1209,
|
|
"mean_token_accuracy": 0.194915471971035,
|
|
"num_tokens": 56299595.0,
|
|
"step": 27135
|
|
},
|
|
{
|
|
"entropy": 5.505272293090821,
|
|
"epoch": 2.4619013062409287,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00043935510528014625,
|
|
"loss": 5.2434,
|
|
"mean_token_accuracy": 0.19015640020370483,
|
|
"num_tokens": 56310152.0,
|
|
"step": 27140
|
|
},
|
|
{
|
|
"entropy": 5.495244836807251,
|
|
"epoch": 2.462354862119013,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004393330058334426,
|
|
"loss": 5.2632,
|
|
"mean_token_accuracy": 0.18302183002233505,
|
|
"num_tokens": 56320288.0,
|
|
"step": 27145
|
|
},
|
|
{
|
|
"entropy": 5.530053424835205,
|
|
"epoch": 2.4628084179970973,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00043931090298829047,
|
|
"loss": 5.1817,
|
|
"mean_token_accuracy": 0.18495816886425018,
|
|
"num_tokens": 56330345.0,
|
|
"step": 27150
|
|
},
|
|
{
|
|
"entropy": 5.57894606590271,
|
|
"epoch": 2.4632619738751815,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00043928879674514694,
|
|
"loss": 5.3076,
|
|
"mean_token_accuracy": 0.192377308011055,
|
|
"num_tokens": 56340996.0,
|
|
"step": 27155
|
|
},
|
|
{
|
|
"entropy": 5.356012201309204,
|
|
"epoch": 2.463715529753266,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004392666871044692,
|
|
"loss": 5.0207,
|
|
"mean_token_accuracy": 0.20606105923652648,
|
|
"num_tokens": 56350326.0,
|
|
"step": 27160
|
|
},
|
|
{
|
|
"entropy": 5.444810819625855,
|
|
"epoch": 2.4641690856313496,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00043924457406671456,
|
|
"loss": 5.1604,
|
|
"mean_token_accuracy": 0.19813981503248215,
|
|
"num_tokens": 56360556.0,
|
|
"step": 27165
|
|
},
|
|
{
|
|
"entropy": 5.481877708435059,
|
|
"epoch": 2.464622641509434,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004392224576323403,
|
|
"loss": 5.1111,
|
|
"mean_token_accuracy": 0.19301420003175734,
|
|
"num_tokens": 56369980.0,
|
|
"step": 27170
|
|
},
|
|
{
|
|
"entropy": 5.46888222694397,
|
|
"epoch": 2.465076197387518,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00043920033780180367,
|
|
"loss": 5.1766,
|
|
"mean_token_accuracy": 0.1895393341779709,
|
|
"num_tokens": 56379974.0,
|
|
"step": 27175
|
|
},
|
|
{
|
|
"entropy": 5.442137908935547,
|
|
"epoch": 2.4655297532656024,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004391782145755623,
|
|
"loss": 5.0966,
|
|
"mean_token_accuracy": 0.19753481894731523,
|
|
"num_tokens": 56390542.0,
|
|
"step": 27180
|
|
},
|
|
{
|
|
"entropy": 5.533555746078491,
|
|
"epoch": 2.4659833091436867,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004391560879540736,
|
|
"loss": 5.2818,
|
|
"mean_token_accuracy": 0.18208527117967604,
|
|
"num_tokens": 56401755.0,
|
|
"step": 27185
|
|
},
|
|
{
|
|
"entropy": 5.483276653289795,
|
|
"epoch": 2.4664368650217705,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004391339579377952,
|
|
"loss": 5.163,
|
|
"mean_token_accuracy": 0.19031016081571578,
|
|
"num_tokens": 56412223.0,
|
|
"step": 27190
|
|
},
|
|
{
|
|
"entropy": 5.484303140640259,
|
|
"epoch": 2.4668904208998548,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00043911182452718476,
|
|
"loss": 5.2042,
|
|
"mean_token_accuracy": 0.18937601149082184,
|
|
"num_tokens": 56422947.0,
|
|
"step": 27195
|
|
},
|
|
{
|
|
"entropy": 5.433365297317505,
|
|
"epoch": 2.467343976777939,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00043908968772269984,
|
|
"loss": 5.1858,
|
|
"mean_token_accuracy": 0.1942855104804039,
|
|
"num_tokens": 56433189.0,
|
|
"step": 27200
|
|
},
|
|
{
|
|
"entropy": 5.501993036270141,
|
|
"epoch": 2.4677975326560233,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00043906754752479836,
|
|
"loss": 5.1838,
|
|
"mean_token_accuracy": 0.19418145418167115,
|
|
"num_tokens": 56444460.0,
|
|
"step": 27205
|
|
},
|
|
{
|
|
"entropy": 5.567674732208252,
|
|
"epoch": 2.4682510885341076,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004390454039339383,
|
|
"loss": 5.2017,
|
|
"mean_token_accuracy": 0.18919933438301087,
|
|
"num_tokens": 56454368.0,
|
|
"step": 27210
|
|
},
|
|
{
|
|
"entropy": 5.381188821792603,
|
|
"epoch": 2.4687046444121914,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00043902325695057743,
|
|
"loss": 5.1046,
|
|
"mean_token_accuracy": 0.19667531847953795,
|
|
"num_tokens": 56464153.0,
|
|
"step": 27215
|
|
},
|
|
{
|
|
"entropy": 5.411316967010498,
|
|
"epoch": 2.4691582002902757,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00043900110657517377,
|
|
"loss": 5.1208,
|
|
"mean_token_accuracy": 0.19932612627744675,
|
|
"num_tokens": 56473627.0,
|
|
"step": 27220
|
|
},
|
|
{
|
|
"entropy": 5.437023258209228,
|
|
"epoch": 2.46961175616836,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004389789528081855,
|
|
"loss": 5.1218,
|
|
"mean_token_accuracy": 0.19690182954072952,
|
|
"num_tokens": 56483660.0,
|
|
"step": 27225
|
|
},
|
|
{
|
|
"entropy": 5.488110637664795,
|
|
"epoch": 2.470065312046444,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004389567956500707,
|
|
"loss": 5.1059,
|
|
"mean_token_accuracy": 0.19689717292785644,
|
|
"num_tokens": 56492653.0,
|
|
"step": 27230
|
|
},
|
|
{
|
|
"entropy": 5.535518407821655,
|
|
"epoch": 2.4705188679245285,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004389346351012876,
|
|
"loss": 5.292,
|
|
"mean_token_accuracy": 0.1863325759768486,
|
|
"num_tokens": 56503289.0,
|
|
"step": 27235
|
|
},
|
|
{
|
|
"entropy": 5.472991895675659,
|
|
"epoch": 2.4709724238026123,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00043891247116229436,
|
|
"loss": 5.222,
|
|
"mean_token_accuracy": 0.1821546271443367,
|
|
"num_tokens": 56513843.0,
|
|
"step": 27240
|
|
},
|
|
{
|
|
"entropy": 5.513165664672852,
|
|
"epoch": 2.4714259796806965,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00043889030383354957,
|
|
"loss": 5.1848,
|
|
"mean_token_accuracy": 0.19124116450548173,
|
|
"num_tokens": 56524175.0,
|
|
"step": 27245
|
|
},
|
|
{
|
|
"entropy": 5.446495771408081,
|
|
"epoch": 2.471879535558781,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004388681331155114,
|
|
"loss": 5.0895,
|
|
"mean_token_accuracy": 0.20319874435663224,
|
|
"num_tokens": 56534976.0,
|
|
"step": 27250
|
|
},
|
|
{
|
|
"entropy": 5.507737112045288,
|
|
"epoch": 2.472333091436865,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004388459590086386,
|
|
"loss": 5.2141,
|
|
"mean_token_accuracy": 0.189651919901371,
|
|
"num_tokens": 56545967.0,
|
|
"step": 27255
|
|
},
|
|
{
|
|
"entropy": 5.491087532043457,
|
|
"epoch": 2.4727866473149493,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00043882378151338956,
|
|
"loss": 5.1782,
|
|
"mean_token_accuracy": 0.19126976728439332,
|
|
"num_tokens": 56555527.0,
|
|
"step": 27260
|
|
},
|
|
{
|
|
"entropy": 5.50524320602417,
|
|
"epoch": 2.4732402031930336,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000438801600630223,
|
|
"loss": 5.1919,
|
|
"mean_token_accuracy": 0.1821846216917038,
|
|
"num_tokens": 56565874.0,
|
|
"step": 27265
|
|
},
|
|
{
|
|
"entropy": 5.4256328582763675,
|
|
"epoch": 2.4736937590711174,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00043877941635959755,
|
|
"loss": 5.0901,
|
|
"mean_token_accuracy": 0.1952810764312744,
|
|
"num_tokens": 56575452.0,
|
|
"step": 27270
|
|
},
|
|
{
|
|
"entropy": 5.418340730667114,
|
|
"epoch": 2.4741473149492017,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00043875722870197214,
|
|
"loss": 5.0992,
|
|
"mean_token_accuracy": 0.2014816462993622,
|
|
"num_tokens": 56586176.0,
|
|
"step": 27275
|
|
},
|
|
{
|
|
"entropy": 5.484587240219116,
|
|
"epoch": 2.474600870827286,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004387350376578054,
|
|
"loss": 5.1413,
|
|
"mean_token_accuracy": 0.19403706043958663,
|
|
"num_tokens": 56595473.0,
|
|
"step": 27280
|
|
},
|
|
{
|
|
"entropy": 5.461724519729614,
|
|
"epoch": 2.4750544267053702,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004387128432275563,
|
|
"loss": 5.2028,
|
|
"mean_token_accuracy": 0.18999613374471663,
|
|
"num_tokens": 56606016.0,
|
|
"step": 27285
|
|
},
|
|
{
|
|
"entropy": 5.502641677856445,
|
|
"epoch": 2.475507982583454,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000438690645411684,
|
|
"loss": 5.1886,
|
|
"mean_token_accuracy": 0.19050587713718414,
|
|
"num_tokens": 56617674.0,
|
|
"step": 27290
|
|
},
|
|
{
|
|
"entropy": 5.4800434589385985,
|
|
"epoch": 2.4759615384615383,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00043866844421064745,
|
|
"loss": 5.1529,
|
|
"mean_token_accuracy": 0.19337929636240006,
|
|
"num_tokens": 56628077.0,
|
|
"step": 27295
|
|
},
|
|
{
|
|
"entropy": 5.463146162033081,
|
|
"epoch": 2.4764150943396226,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00043864623962490575,
|
|
"loss": 5.0954,
|
|
"mean_token_accuracy": 0.19515756517648697,
|
|
"num_tokens": 56638691.0,
|
|
"step": 27300
|
|
},
|
|
{
|
|
"entropy": 5.423010683059692,
|
|
"epoch": 2.476868650217707,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004386240316549181,
|
|
"loss": 5.1572,
|
|
"mean_token_accuracy": 0.18914340138435365,
|
|
"num_tokens": 56650338.0,
|
|
"step": 27305
|
|
},
|
|
{
|
|
"entropy": 5.466610431671143,
|
|
"epoch": 2.477322206095791,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00043860182030114374,
|
|
"loss": 5.0944,
|
|
"mean_token_accuracy": 0.1964074671268463,
|
|
"num_tokens": 56660328.0,
|
|
"step": 27310
|
|
},
|
|
{
|
|
"entropy": 5.530678939819336,
|
|
"epoch": 2.4777757619738754,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00043857960556404214,
|
|
"loss": 5.2295,
|
|
"mean_token_accuracy": 0.19294241070747375,
|
|
"num_tokens": 56670674.0,
|
|
"step": 27315
|
|
},
|
|
{
|
|
"entropy": 5.457210969924927,
|
|
"epoch": 2.478229317851959,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004385573874440725,
|
|
"loss": 5.1301,
|
|
"mean_token_accuracy": 0.2000304415822029,
|
|
"num_tokens": 56680656.0,
|
|
"step": 27320
|
|
},
|
|
{
|
|
"entropy": 5.416438293457031,
|
|
"epoch": 2.4786828737300435,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00043853516594169446,
|
|
"loss": 5.0857,
|
|
"mean_token_accuracy": 0.19581278413534164,
|
|
"num_tokens": 56691039.0,
|
|
"step": 27325
|
|
},
|
|
{
|
|
"entropy": 5.463028764724731,
|
|
"epoch": 2.4791364296081277,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004385129410573675,
|
|
"loss": 5.1604,
|
|
"mean_token_accuracy": 0.18894172608852386,
|
|
"num_tokens": 56703101.0,
|
|
"step": 27330
|
|
},
|
|
{
|
|
"entropy": 5.511876726150513,
|
|
"epoch": 2.479589985486212,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00043849071279155124,
|
|
"loss": 5.2081,
|
|
"mean_token_accuracy": 0.19392369985580443,
|
|
"num_tokens": 56712351.0,
|
|
"step": 27335
|
|
},
|
|
{
|
|
"entropy": 5.460506200790405,
|
|
"epoch": 2.480043541364296,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00043846848114470537,
|
|
"loss": 5.1884,
|
|
"mean_token_accuracy": 0.19892620742321016,
|
|
"num_tokens": 56722836.0,
|
|
"step": 27340
|
|
},
|
|
{
|
|
"entropy": 5.487525272369385,
|
|
"epoch": 2.48049709724238,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00043844624611728974,
|
|
"loss": 5.1508,
|
|
"mean_token_accuracy": 0.19064265936613084,
|
|
"num_tokens": 56734032.0,
|
|
"step": 27345
|
|
},
|
|
{
|
|
"entropy": 5.463614892959595,
|
|
"epoch": 2.4809506531204644,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00043842400770976406,
|
|
"loss": 5.1262,
|
|
"mean_token_accuracy": 0.1907668799161911,
|
|
"num_tokens": 56743536.0,
|
|
"step": 27350
|
|
},
|
|
{
|
|
"entropy": 5.472437763214112,
|
|
"epoch": 2.4814042089985486,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004384017659225882,
|
|
"loss": 5.1402,
|
|
"mean_token_accuracy": 0.19335696399211882,
|
|
"num_tokens": 56753475.0,
|
|
"step": 27355
|
|
},
|
|
{
|
|
"entropy": 5.406447410583496,
|
|
"epoch": 2.481857764876633,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00043837952075622224,
|
|
"loss": 5.0768,
|
|
"mean_token_accuracy": 0.19809019565582275,
|
|
"num_tokens": 56763602.0,
|
|
"step": 27360
|
|
},
|
|
{
|
|
"entropy": 5.491286134719848,
|
|
"epoch": 2.482311320754717,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004383572722111261,
|
|
"loss": 5.0991,
|
|
"mean_token_accuracy": 0.2034037783741951,
|
|
"num_tokens": 56773859.0,
|
|
"step": 27365
|
|
},
|
|
{
|
|
"entropy": 5.457459831237793,
|
|
"epoch": 2.482764876632801,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00043833502028775995,
|
|
"loss": 5.1576,
|
|
"mean_token_accuracy": 0.198157899081707,
|
|
"num_tokens": 56783810.0,
|
|
"step": 27370
|
|
},
|
|
{
|
|
"entropy": 5.524997234344482,
|
|
"epoch": 2.4832184325108853,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00043831276498658395,
|
|
"loss": 5.2322,
|
|
"mean_token_accuracy": 0.18957628905773163,
|
|
"num_tokens": 56794088.0,
|
|
"step": 27375
|
|
},
|
|
{
|
|
"entropy": 5.405243682861328,
|
|
"epoch": 2.4836719883889695,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004382905063080584,
|
|
"loss": 5.0988,
|
|
"mean_token_accuracy": 0.19415124356746674,
|
|
"num_tokens": 56804623.0,
|
|
"step": 27380
|
|
},
|
|
{
|
|
"entropy": 5.399438142776489,
|
|
"epoch": 2.484125544267054,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00043826824425264357,
|
|
"loss": 5.1701,
|
|
"mean_token_accuracy": 0.19034765064716339,
|
|
"num_tokens": 56813842.0,
|
|
"step": 27385
|
|
},
|
|
{
|
|
"entropy": 5.533923625946045,
|
|
"epoch": 2.484579100145138,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004382459788207997,
|
|
"loss": 5.1529,
|
|
"mean_token_accuracy": 0.19177406579256057,
|
|
"num_tokens": 56823501.0,
|
|
"step": 27390
|
|
},
|
|
{
|
|
"entropy": 5.4938311100006105,
|
|
"epoch": 2.485032656023222,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00043822371001298754,
|
|
"loss": 5.1835,
|
|
"mean_token_accuracy": 0.19214850962162017,
|
|
"num_tokens": 56834601.0,
|
|
"step": 27395
|
|
},
|
|
{
|
|
"entropy": 5.379020404815674,
|
|
"epoch": 2.485486211901306,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004382014378296674,
|
|
"loss": 5.1607,
|
|
"mean_token_accuracy": 0.18952295929193497,
|
|
"num_tokens": 56844701.0,
|
|
"step": 27400
|
|
},
|
|
{
|
|
"entropy": 5.415239000320435,
|
|
"epoch": 2.4859397677793904,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004381791622713,
|
|
"loss": 5.134,
|
|
"mean_token_accuracy": 0.1972360849380493,
|
|
"num_tokens": 56854867.0,
|
|
"step": 27405
|
|
},
|
|
{
|
|
"entropy": 5.583620500564575,
|
|
"epoch": 2.4863933236574747,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000438156883338346,
|
|
"loss": 5.1926,
|
|
"mean_token_accuracy": 0.19229190647602082,
|
|
"num_tokens": 56865688.0,
|
|
"step": 27410
|
|
},
|
|
{
|
|
"entropy": 5.529424715042114,
|
|
"epoch": 2.486846879535559,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00043813460103126595,
|
|
"loss": 5.1996,
|
|
"mean_token_accuracy": 0.19487567543983458,
|
|
"num_tokens": 56876504.0,
|
|
"step": 27415
|
|
},
|
|
{
|
|
"entropy": 5.422201442718506,
|
|
"epoch": 2.487300435413643,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00043811231535052076,
|
|
"loss": 5.121,
|
|
"mean_token_accuracy": 0.19544498175382613,
|
|
"num_tokens": 56886083.0,
|
|
"step": 27420
|
|
},
|
|
{
|
|
"entropy": 5.479322671890259,
|
|
"epoch": 2.487753991291727,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004380900262965714,
|
|
"loss": 5.217,
|
|
"mean_token_accuracy": 0.19539043307304382,
|
|
"num_tokens": 56897079.0,
|
|
"step": 27425
|
|
},
|
|
{
|
|
"entropy": 5.529209136962891,
|
|
"epoch": 2.4882075471698113,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004380677338698787,
|
|
"loss": 5.1057,
|
|
"mean_token_accuracy": 0.19709296375513077,
|
|
"num_tokens": 56906962.0,
|
|
"step": 27430
|
|
},
|
|
{
|
|
"entropy": 5.516290378570557,
|
|
"epoch": 2.4886611030478956,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00043804543807090374,
|
|
"loss": 5.2466,
|
|
"mean_token_accuracy": 0.1883732870221138,
|
|
"num_tokens": 56918156.0,
|
|
"step": 27435
|
|
},
|
|
{
|
|
"entropy": 5.43582067489624,
|
|
"epoch": 2.48911465892598,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00043802313890010757,
|
|
"loss": 5.161,
|
|
"mean_token_accuracy": 0.18976226896047593,
|
|
"num_tokens": 56928888.0,
|
|
"step": 27440
|
|
},
|
|
{
|
|
"entropy": 5.489259862899781,
|
|
"epoch": 2.4895682148040637,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004380008363579513,
|
|
"loss": 5.1522,
|
|
"mean_token_accuracy": 0.1929439514875412,
|
|
"num_tokens": 56939929.0,
|
|
"step": 27445
|
|
},
|
|
{
|
|
"entropy": 5.481848335266113,
|
|
"epoch": 2.490021770682148,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00043797853044489623,
|
|
"loss": 5.0824,
|
|
"mean_token_accuracy": 0.1989647701382637,
|
|
"num_tokens": 56950992.0,
|
|
"step": 27450
|
|
},
|
|
{
|
|
"entropy": 5.528964567184448,
|
|
"epoch": 2.490475326560232,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004379562211614036,
|
|
"loss": 5.2629,
|
|
"mean_token_accuracy": 0.1922592267394066,
|
|
"num_tokens": 56962118.0,
|
|
"step": 27455
|
|
},
|
|
{
|
|
"entropy": 5.5043412208557125,
|
|
"epoch": 2.4909288824383164,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004379339085079348,
|
|
"loss": 5.1628,
|
|
"mean_token_accuracy": 0.1914939448237419,
|
|
"num_tokens": 56972837.0,
|
|
"step": 27460
|
|
},
|
|
{
|
|
"entropy": 5.4816389083862305,
|
|
"epoch": 2.4913824383164007,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004379115924849512,
|
|
"loss": 5.1491,
|
|
"mean_token_accuracy": 0.1967402547597885,
|
|
"num_tokens": 56982794.0,
|
|
"step": 27465
|
|
},
|
|
{
|
|
"entropy": 5.593693351745605,
|
|
"epoch": 2.491835994194485,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004378892730929145,
|
|
"loss": 5.3184,
|
|
"mean_token_accuracy": 0.18507957011461257,
|
|
"num_tokens": 56993979.0,
|
|
"step": 27470
|
|
},
|
|
{
|
|
"entropy": 5.487763929367065,
|
|
"epoch": 2.492289550072569,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00043786695033228604,
|
|
"loss": 5.1368,
|
|
"mean_token_accuracy": 0.19242842644453048,
|
|
"num_tokens": 57004505.0,
|
|
"step": 27475
|
|
},
|
|
{
|
|
"entropy": 5.5084367275238035,
|
|
"epoch": 2.492743105950653,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00043784462420352747,
|
|
"loss": 5.1875,
|
|
"mean_token_accuracy": 0.18984789699316024,
|
|
"num_tokens": 57014121.0,
|
|
"step": 27480
|
|
},
|
|
{
|
|
"entropy": 5.516815900802612,
|
|
"epoch": 2.4931966618287373,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00043782229470710067,
|
|
"loss": 5.157,
|
|
"mean_token_accuracy": 0.19564312547445298,
|
|
"num_tokens": 57023748.0,
|
|
"step": 27485
|
|
},
|
|
{
|
|
"entropy": 5.444222736358642,
|
|
"epoch": 2.4936502177068216,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004377999618434673,
|
|
"loss": 5.1445,
|
|
"mean_token_accuracy": 0.19226664900779725,
|
|
"num_tokens": 57034782.0,
|
|
"step": 27490
|
|
},
|
|
{
|
|
"entropy": 5.431159257888794,
|
|
"epoch": 2.4941037735849054,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004377776256130892,
|
|
"loss": 5.0725,
|
|
"mean_token_accuracy": 0.1974221333861351,
|
|
"num_tokens": 57045136.0,
|
|
"step": 27495
|
|
},
|
|
{
|
|
"entropy": 5.468269491195679,
|
|
"epoch": 2.4945573294629897,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00043775528601642833,
|
|
"loss": 5.2951,
|
|
"mean_token_accuracy": 0.18470180481672288,
|
|
"num_tokens": 57055893.0,
|
|
"step": 27500
|
|
},
|
|
{
|
|
"entropy": 5.491204357147216,
|
|
"epoch": 2.495010885341074,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00043773294305394665,
|
|
"loss": 5.1885,
|
|
"mean_token_accuracy": 0.18674533814191818,
|
|
"num_tokens": 57067189.0,
|
|
"step": 27505
|
|
},
|
|
{
|
|
"entropy": 5.529479360580444,
|
|
"epoch": 2.4954644412191582,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00043771059672610636,
|
|
"loss": 5.175,
|
|
"mean_token_accuracy": 0.19538995623588562,
|
|
"num_tokens": 57077374.0,
|
|
"step": 27510
|
|
},
|
|
{
|
|
"entropy": 5.479859066009522,
|
|
"epoch": 2.4959179970972425,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00043768824703336933,
|
|
"loss": 5.1414,
|
|
"mean_token_accuracy": 0.1885259047150612,
|
|
"num_tokens": 57088168.0,
|
|
"step": 27515
|
|
},
|
|
{
|
|
"entropy": 5.439310741424561,
|
|
"epoch": 2.4963715529753268,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004376658939761979,
|
|
"loss": 5.0907,
|
|
"mean_token_accuracy": 0.19508860558271407,
|
|
"num_tokens": 57098743.0,
|
|
"step": 27520
|
|
},
|
|
{
|
|
"entropy": 5.453170728683472,
|
|
"epoch": 2.4968251088534106,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004376435375550544,
|
|
"loss": 5.269,
|
|
"mean_token_accuracy": 0.18481728285551072,
|
|
"num_tokens": 57109854.0,
|
|
"step": 27525
|
|
},
|
|
{
|
|
"entropy": 5.448837375640869,
|
|
"epoch": 2.497278664731495,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00043762117777040106,
|
|
"loss": 5.0765,
|
|
"mean_token_accuracy": 0.20304430574178695,
|
|
"num_tokens": 57120296.0,
|
|
"step": 27530
|
|
},
|
|
{
|
|
"entropy": 5.438287448883057,
|
|
"epoch": 2.497732220609579,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004375988146227003,
|
|
"loss": 5.1201,
|
|
"mean_token_accuracy": 0.19021186828613282,
|
|
"num_tokens": 57131295.0,
|
|
"step": 27535
|
|
},
|
|
{
|
|
"entropy": 5.495009231567383,
|
|
"epoch": 2.4981857764876634,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004375764481124147,
|
|
"loss": 5.182,
|
|
"mean_token_accuracy": 0.18859187364578248,
|
|
"num_tokens": 57141936.0,
|
|
"step": 27540
|
|
},
|
|
{
|
|
"entropy": 5.41836576461792,
|
|
"epoch": 2.4986393323657476,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00043755407824000664,
|
|
"loss": 5.1098,
|
|
"mean_token_accuracy": 0.20071842074394225,
|
|
"num_tokens": 57152510.0,
|
|
"step": 27545
|
|
},
|
|
{
|
|
"entropy": 5.463023328781128,
|
|
"epoch": 2.4990928882438315,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00043753170500593884,
|
|
"loss": 5.1437,
|
|
"mean_token_accuracy": 0.19434604197740554,
|
|
"num_tokens": 57162546.0,
|
|
"step": 27550
|
|
},
|
|
{
|
|
"entropy": 5.386328506469726,
|
|
"epoch": 2.4995464441219157,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00043750932841067397,
|
|
"loss": 5.0795,
|
|
"mean_token_accuracy": 0.20058237314224242,
|
|
"num_tokens": 57174658.0,
|
|
"step": 27555
|
|
},
|
|
{
|
|
"entropy": 5.5214673519134525,
|
|
"epoch": 2.5,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00043748694845467483,
|
|
"loss": 5.2849,
|
|
"mean_token_accuracy": 0.18236890137195588,
|
|
"num_tokens": 57185157.0,
|
|
"step": 27560
|
|
},
|
|
{
|
|
"entropy": 5.492548847198487,
|
|
"epoch": 2.5004535558780843,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00043746456513840405,
|
|
"loss": 5.0594,
|
|
"mean_token_accuracy": 0.19416719824075698,
|
|
"num_tokens": 57195277.0,
|
|
"step": 27565
|
|
},
|
|
{
|
|
"entropy": 5.486960124969483,
|
|
"epoch": 2.5009071117561685,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004374421784623248,
|
|
"loss": 5.1799,
|
|
"mean_token_accuracy": 0.1921134665608406,
|
|
"num_tokens": 57205374.0,
|
|
"step": 27570
|
|
},
|
|
{
|
|
"entropy": 5.436812448501587,
|
|
"epoch": 2.501360667634253,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.00043741978842689987,
|
|
"loss": 5.1436,
|
|
"mean_token_accuracy": 0.19174654334783553,
|
|
"num_tokens": 57215700.0,
|
|
"step": 27575
|
|
},
|
|
{
|
|
"entropy": 5.472171688079834,
|
|
"epoch": 2.5018142235123366,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004373973950325923,
|
|
"loss": 5.1999,
|
|
"mean_token_accuracy": 0.19585930556058884,
|
|
"num_tokens": 57225765.0,
|
|
"step": 27580
|
|
},
|
|
{
|
|
"entropy": 5.480496740341186,
|
|
"epoch": 2.502267779390421,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00043737499827986527,
|
|
"loss": 5.1677,
|
|
"mean_token_accuracy": 0.19576041251420975,
|
|
"num_tokens": 57235913.0,
|
|
"step": 27585
|
|
},
|
|
{
|
|
"entropy": 5.44107575416565,
|
|
"epoch": 2.502721335268505,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00043735259816918184,
|
|
"loss": 5.08,
|
|
"mean_token_accuracy": 0.19656820297241212,
|
|
"num_tokens": 57246204.0,
|
|
"step": 27590
|
|
},
|
|
{
|
|
"entropy": 5.467139959335327,
|
|
"epoch": 2.5031748911465894,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004373301947010053,
|
|
"loss": 5.1699,
|
|
"mean_token_accuracy": 0.18935434222221376,
|
|
"num_tokens": 57256167.0,
|
|
"step": 27595
|
|
},
|
|
{
|
|
"entropy": 5.41440052986145,
|
|
"epoch": 2.5036284470246732,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00043730778787579895,
|
|
"loss": 5.1271,
|
|
"mean_token_accuracy": 0.1946038633584976,
|
|
"num_tokens": 57266621.0,
|
|
"step": 27600
|
|
},
|
|
{
|
|
"entropy": 5.510943508148193,
|
|
"epoch": 2.5040820029027575,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00043728537769402627,
|
|
"loss": 5.1699,
|
|
"mean_token_accuracy": 0.18702106028795243,
|
|
"num_tokens": 57277282.0,
|
|
"step": 27605
|
|
},
|
|
{
|
|
"entropy": 5.516334772109985,
|
|
"epoch": 2.5045355587808418,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004372629641561506,
|
|
"loss": 5.2336,
|
|
"mean_token_accuracy": 0.18862368017435074,
|
|
"num_tokens": 57287541.0,
|
|
"step": 27610
|
|
},
|
|
{
|
|
"entropy": 5.464295291900635,
|
|
"epoch": 2.504989114658926,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00043724054726263547,
|
|
"loss": 5.1574,
|
|
"mean_token_accuracy": 0.19007603377103804,
|
|
"num_tokens": 57298158.0,
|
|
"step": 27615
|
|
},
|
|
{
|
|
"entropy": 5.495907545089722,
|
|
"epoch": 2.5054426705370103,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004372181270139444,
|
|
"loss": 5.1736,
|
|
"mean_token_accuracy": 0.18934156596660615,
|
|
"num_tokens": 57308356.0,
|
|
"step": 27620
|
|
},
|
|
{
|
|
"entropy": 5.435403966903687,
|
|
"epoch": 2.5058962264150946,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00043719570341054127,
|
|
"loss": 5.0676,
|
|
"mean_token_accuracy": 0.19424182176589966,
|
|
"num_tokens": 57317905.0,
|
|
"step": 27625
|
|
},
|
|
{
|
|
"entropy": 5.473773050308227,
|
|
"epoch": 2.5063497822931784,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00043717327645288956,
|
|
"loss": 5.2192,
|
|
"mean_token_accuracy": 0.19758496582508087,
|
|
"num_tokens": 57328277.0,
|
|
"step": 27630
|
|
},
|
|
{
|
|
"entropy": 5.560351610183716,
|
|
"epoch": 2.5068033381712627,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00043715084614145316,
|
|
"loss": 5.2175,
|
|
"mean_token_accuracy": 0.18873682618141174,
|
|
"num_tokens": 57338975.0,
|
|
"step": 27635
|
|
},
|
|
{
|
|
"entropy": 5.451284408569336,
|
|
"epoch": 2.507256894049347,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000437128412476696,
|
|
"loss": 5.132,
|
|
"mean_token_accuracy": 0.19536236077547073,
|
|
"num_tokens": 57349439.0,
|
|
"step": 27640
|
|
},
|
|
{
|
|
"entropy": 5.4628270149230955,
|
|
"epoch": 2.507710449927431,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004371059754590819,
|
|
"loss": 5.1985,
|
|
"mean_token_accuracy": 0.19389130920171738,
|
|
"num_tokens": 57359414.0,
|
|
"step": 27645
|
|
},
|
|
{
|
|
"entropy": 5.566140270233154,
|
|
"epoch": 2.508164005805515,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00043708353508907494,
|
|
"loss": 5.228,
|
|
"mean_token_accuracy": 0.19496976286172868,
|
|
"num_tokens": 57369711.0,
|
|
"step": 27650
|
|
},
|
|
{
|
|
"entropy": 5.4269716262817385,
|
|
"epoch": 2.5086175616835993,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004370610913671392,
|
|
"loss": 5.0746,
|
|
"mean_token_accuracy": 0.20143769085407257,
|
|
"num_tokens": 57380001.0,
|
|
"step": 27655
|
|
},
|
|
{
|
|
"entropy": 5.486323404312134,
|
|
"epoch": 2.5090711175616836,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00043703864429373875,
|
|
"loss": 5.2785,
|
|
"mean_token_accuracy": 0.1801478311419487,
|
|
"num_tokens": 57390794.0,
|
|
"step": 27660
|
|
},
|
|
{
|
|
"entropy": 5.53278284072876,
|
|
"epoch": 2.509524673439768,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00043701619386933793,
|
|
"loss": 5.2151,
|
|
"mean_token_accuracy": 0.18487172871828078,
|
|
"num_tokens": 57401975.0,
|
|
"step": 27665
|
|
},
|
|
{
|
|
"entropy": 5.408484172821045,
|
|
"epoch": 2.509978229317852,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00043699374009440085,
|
|
"loss": 5.0426,
|
|
"mean_token_accuracy": 0.20530659705400467,
|
|
"num_tokens": 57411249.0,
|
|
"step": 27670
|
|
},
|
|
{
|
|
"entropy": 5.440446090698242,
|
|
"epoch": 2.5104317851959363,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004369712829693919,
|
|
"loss": 5.1047,
|
|
"mean_token_accuracy": 0.20041485726833344,
|
|
"num_tokens": 57422679.0,
|
|
"step": 27675
|
|
},
|
|
{
|
|
"entropy": 5.483030652999878,
|
|
"epoch": 2.51088534107402,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004369488224947757,
|
|
"loss": 5.1485,
|
|
"mean_token_accuracy": 0.1966699942946434,
|
|
"num_tokens": 57433265.0,
|
|
"step": 27680
|
|
},
|
|
{
|
|
"entropy": 5.487168264389038,
|
|
"epoch": 2.5113388969521044,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004369263586710164,
|
|
"loss": 5.1668,
|
|
"mean_token_accuracy": 0.19467692971229553,
|
|
"num_tokens": 57444095.0,
|
|
"step": 27685
|
|
},
|
|
{
|
|
"entropy": 5.4541301250457765,
|
|
"epoch": 2.5117924528301887,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004369038914985789,
|
|
"loss": 5.1176,
|
|
"mean_token_accuracy": 0.19534635692834854,
|
|
"num_tokens": 57454059.0,
|
|
"step": 27690
|
|
},
|
|
{
|
|
"entropy": 5.438295984268189,
|
|
"epoch": 2.512246008708273,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004368814209779276,
|
|
"loss": 5.1003,
|
|
"mean_token_accuracy": 0.1971222996711731,
|
|
"num_tokens": 57463940.0,
|
|
"step": 27695
|
|
},
|
|
{
|
|
"entropy": 5.377117776870728,
|
|
"epoch": 2.512699564586357,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00043685894710952724,
|
|
"loss": 5.1312,
|
|
"mean_token_accuracy": 0.1927450940012932,
|
|
"num_tokens": 57474731.0,
|
|
"step": 27700
|
|
},
|
|
{
|
|
"entropy": 5.4258355617523195,
|
|
"epoch": 2.513153120464441,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004368364698938426,
|
|
"loss": 5.0727,
|
|
"mean_token_accuracy": 0.19964365065097808,
|
|
"num_tokens": 57485096.0,
|
|
"step": 27705
|
|
},
|
|
{
|
|
"entropy": 5.452251958847046,
|
|
"epoch": 2.5136066763425253,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004368139893313385,
|
|
"loss": 5.1477,
|
|
"mean_token_accuracy": 0.19517046511173247,
|
|
"num_tokens": 57496371.0,
|
|
"step": 27710
|
|
},
|
|
{
|
|
"entropy": 5.525375938415527,
|
|
"epoch": 2.5140602322206096,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00043679150542248,
|
|
"loss": 5.154,
|
|
"mean_token_accuracy": 0.19117128998041152,
|
|
"num_tokens": 57506012.0,
|
|
"step": 27715
|
|
},
|
|
{
|
|
"entropy": 5.4614417552948,
|
|
"epoch": 2.514513788098694,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00043676901816773174,
|
|
"loss": 5.1884,
|
|
"mean_token_accuracy": 0.18899285197257995,
|
|
"num_tokens": 57516536.0,
|
|
"step": 27720
|
|
},
|
|
{
|
|
"entropy": 5.45789794921875,
|
|
"epoch": 2.514967343976778,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004367465275675591,
|
|
"loss": 5.0785,
|
|
"mean_token_accuracy": 0.19615563303232192,
|
|
"num_tokens": 57527450.0,
|
|
"step": 27725
|
|
},
|
|
{
|
|
"entropy": 5.510025358200073,
|
|
"epoch": 2.5154208998548624,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00043672403362242704,
|
|
"loss": 5.2098,
|
|
"mean_token_accuracy": 0.1937198594212532,
|
|
"num_tokens": 57538234.0,
|
|
"step": 27730
|
|
},
|
|
{
|
|
"entropy": 5.425774574279785,
|
|
"epoch": 2.515874455732946,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00043670153633280066,
|
|
"loss": 5.1166,
|
|
"mean_token_accuracy": 0.19797841608524322,
|
|
"num_tokens": 57547938.0,
|
|
"step": 27735
|
|
},
|
|
{
|
|
"entropy": 5.499861145019532,
|
|
"epoch": 2.5163280116110305,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004366790356991454,
|
|
"loss": 5.1711,
|
|
"mean_token_accuracy": 0.1941956952214241,
|
|
"num_tokens": 57560553.0,
|
|
"step": 27740
|
|
},
|
|
{
|
|
"entropy": 5.419819068908692,
|
|
"epoch": 2.5167815674891147,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004366565317219265,
|
|
"loss": 5.1186,
|
|
"mean_token_accuracy": 0.1978362888097763,
|
|
"num_tokens": 57570670.0,
|
|
"step": 27745
|
|
},
|
|
{
|
|
"entropy": 5.581870985031128,
|
|
"epoch": 2.5172351233671986,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00043663402440160924,
|
|
"loss": 5.346,
|
|
"mean_token_accuracy": 0.18061141669750214,
|
|
"num_tokens": 57582377.0,
|
|
"step": 27750
|
|
},
|
|
{
|
|
"entropy": 5.474020385742188,
|
|
"epoch": 2.517688679245283,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004366115137386592,
|
|
"loss": 5.0284,
|
|
"mean_token_accuracy": 0.20093393474817275,
|
|
"num_tokens": 57592764.0,
|
|
"step": 27755
|
|
},
|
|
{
|
|
"entropy": 5.442656707763672,
|
|
"epoch": 2.518142235123367,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004365889997335419,
|
|
"loss": 5.1293,
|
|
"mean_token_accuracy": 0.19369311332702638,
|
|
"num_tokens": 57603768.0,
|
|
"step": 27760
|
|
},
|
|
{
|
|
"entropy": 5.389196157455444,
|
|
"epoch": 2.5185957910014514,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00043656648238672285,
|
|
"loss": 5.1126,
|
|
"mean_token_accuracy": 0.19763253927230834,
|
|
"num_tokens": 57614346.0,
|
|
"step": 27765
|
|
},
|
|
{
|
|
"entropy": 5.534186458587646,
|
|
"epoch": 2.5190493468795356,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004365439616986678,
|
|
"loss": 5.2646,
|
|
"mean_token_accuracy": 0.1931869849562645,
|
|
"num_tokens": 57625015.0,
|
|
"step": 27770
|
|
},
|
|
{
|
|
"entropy": 5.560124778747559,
|
|
"epoch": 2.51950290275762,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00043652143766984247,
|
|
"loss": 5.2281,
|
|
"mean_token_accuracy": 0.1872229501605034,
|
|
"num_tokens": 57635476.0,
|
|
"step": 27775
|
|
},
|
|
{
|
|
"entropy": 5.4468365669250485,
|
|
"epoch": 2.519956458635704,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00043649891030071264,
|
|
"loss": 5.1073,
|
|
"mean_token_accuracy": 0.19547179937362671,
|
|
"num_tokens": 57645512.0,
|
|
"step": 27780
|
|
},
|
|
{
|
|
"entropy": 5.440681886672974,
|
|
"epoch": 2.520410014513788,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00043647637959174425,
|
|
"loss": 5.1058,
|
|
"mean_token_accuracy": 0.19356202334165573,
|
|
"num_tokens": 57655766.0,
|
|
"step": 27785
|
|
},
|
|
{
|
|
"entropy": 5.481655502319336,
|
|
"epoch": 2.5208635703918723,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00043645384554340315,
|
|
"loss": 5.1619,
|
|
"mean_token_accuracy": 0.1947731539607048,
|
|
"num_tokens": 57667325.0,
|
|
"step": 27790
|
|
},
|
|
{
|
|
"entropy": 5.448427534103393,
|
|
"epoch": 2.5213171262699565,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00043643130815615536,
|
|
"loss": 5.1362,
|
|
"mean_token_accuracy": 0.1892292782664299,
|
|
"num_tokens": 57677884.0,
|
|
"step": 27795
|
|
},
|
|
{
|
|
"entropy": 5.53461856842041,
|
|
"epoch": 2.521770682148041,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00043640876743046694,
|
|
"loss": 5.1687,
|
|
"mean_token_accuracy": 0.19449444860219955,
|
|
"num_tokens": 57687765.0,
|
|
"step": 27800
|
|
},
|
|
{
|
|
"entropy": 5.433779525756836,
|
|
"epoch": 2.5222242380261246,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004363862233668041,
|
|
"loss": 5.121,
|
|
"mean_token_accuracy": 0.1899241417646408,
|
|
"num_tokens": 57697777.0,
|
|
"step": 27805
|
|
},
|
|
{
|
|
"entropy": 5.448614549636841,
|
|
"epoch": 2.522677793904209,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000436363675965633,
|
|
"loss": 5.1311,
|
|
"mean_token_accuracy": 0.19415992349386216,
|
|
"num_tokens": 57708765.0,
|
|
"step": 27810
|
|
},
|
|
{
|
|
"entropy": 5.513792371749878,
|
|
"epoch": 2.523131349782293,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004363411252274201,
|
|
"loss": 5.1503,
|
|
"mean_token_accuracy": 0.1965918719768524,
|
|
"num_tokens": 57719658.0,
|
|
"step": 27815
|
|
},
|
|
{
|
|
"entropy": 5.477378845214844,
|
|
"epoch": 2.5235849056603774,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00043631857115263153,
|
|
"loss": 5.1351,
|
|
"mean_token_accuracy": 0.19912769347429277,
|
|
"num_tokens": 57730018.0,
|
|
"step": 27820
|
|
},
|
|
{
|
|
"entropy": 5.39125018119812,
|
|
"epoch": 2.5240384615384617,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004362960137417338,
|
|
"loss": 5.081,
|
|
"mean_token_accuracy": 0.19689868986606598,
|
|
"num_tokens": 57741251.0,
|
|
"step": 27825
|
|
},
|
|
{
|
|
"entropy": 5.441256666183472,
|
|
"epoch": 2.524492017416546,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004362734529951933,
|
|
"loss": 5.1694,
|
|
"mean_token_accuracy": 0.19452113509178162,
|
|
"num_tokens": 57751020.0,
|
|
"step": 27830
|
|
},
|
|
{
|
|
"entropy": 5.4000771045684814,
|
|
"epoch": 2.5249455732946298,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00043625088891347685,
|
|
"loss": 5.1196,
|
|
"mean_token_accuracy": 0.19787223190069197,
|
|
"num_tokens": 57760989.0,
|
|
"step": 27835
|
|
},
|
|
{
|
|
"entropy": 5.5363058090209964,
|
|
"epoch": 2.525399129172714,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00043622832149705086,
|
|
"loss": 5.2037,
|
|
"mean_token_accuracy": 0.1941297322511673,
|
|
"num_tokens": 57770882.0,
|
|
"step": 27840
|
|
},
|
|
{
|
|
"entropy": 5.561728858947754,
|
|
"epoch": 2.5258526850507983,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00043620575074638206,
|
|
"loss": 5.213,
|
|
"mean_token_accuracy": 0.19184637814760208,
|
|
"num_tokens": 57781812.0,
|
|
"step": 27845
|
|
},
|
|
{
|
|
"entropy": 5.4698432922363285,
|
|
"epoch": 2.5263062409288826,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00043618317666193734,
|
|
"loss": 5.1269,
|
|
"mean_token_accuracy": 0.19990103989839553,
|
|
"num_tokens": 57792009.0,
|
|
"step": 27850
|
|
},
|
|
{
|
|
"entropy": 5.395656299591065,
|
|
"epoch": 2.5267597968069664,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00043616059924418346,
|
|
"loss": 5.1013,
|
|
"mean_token_accuracy": 0.20418144762516022,
|
|
"num_tokens": 57802109.0,
|
|
"step": 27855
|
|
},
|
|
{
|
|
"entropy": 5.473630380630493,
|
|
"epoch": 2.5272133526850507,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004361380184935872,
|
|
"loss": 5.1531,
|
|
"mean_token_accuracy": 0.19732701480388642,
|
|
"num_tokens": 57812374.0,
|
|
"step": 27860
|
|
},
|
|
{
|
|
"entropy": 5.462021160125732,
|
|
"epoch": 2.527666908563135,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004361154344106158,
|
|
"loss": 5.0558,
|
|
"mean_token_accuracy": 0.20009137839078903,
|
|
"num_tokens": 57822936.0,
|
|
"step": 27865
|
|
},
|
|
{
|
|
"entropy": 5.589845275878906,
|
|
"epoch": 2.528120464441219,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00043609284699573604,
|
|
"loss": 5.3061,
|
|
"mean_token_accuracy": 0.19105252921581267,
|
|
"num_tokens": 57832693.0,
|
|
"step": 27870
|
|
},
|
|
{
|
|
"entropy": 5.513688278198242,
|
|
"epoch": 2.5285740203193035,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00043607025624941523,
|
|
"loss": 5.1688,
|
|
"mean_token_accuracy": 0.19165294915437697,
|
|
"num_tokens": 57843161.0,
|
|
"step": 27875
|
|
},
|
|
{
|
|
"entropy": 5.46702241897583,
|
|
"epoch": 2.5290275761973877,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004360476621721204,
|
|
"loss": 5.1265,
|
|
"mean_token_accuracy": 0.2010165810585022,
|
|
"num_tokens": 57853027.0,
|
|
"step": 27880
|
|
},
|
|
{
|
|
"entropy": 5.483937931060791,
|
|
"epoch": 2.5294811320754715,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004360250647643189,
|
|
"loss": 5.1413,
|
|
"mean_token_accuracy": 0.19840545058250428,
|
|
"num_tokens": 57862821.0,
|
|
"step": 27885
|
|
},
|
|
{
|
|
"entropy": 5.429378890991211,
|
|
"epoch": 2.529934687953556,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00043600246402647805,
|
|
"loss": 5.0991,
|
|
"mean_token_accuracy": 0.1977141097187996,
|
|
"num_tokens": 57874065.0,
|
|
"step": 27890
|
|
},
|
|
{
|
|
"entropy": 5.457605028152466,
|
|
"epoch": 2.53038824383164,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004359798599590652,
|
|
"loss": 5.1646,
|
|
"mean_token_accuracy": 0.19130789786577224,
|
|
"num_tokens": 57885190.0,
|
|
"step": 27895
|
|
},
|
|
{
|
|
"entropy": 5.451262378692627,
|
|
"epoch": 2.5308417997097243,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00043595725256254786,
|
|
"loss": 5.0951,
|
|
"mean_token_accuracy": 0.19412341862916946,
|
|
"num_tokens": 57894234.0,
|
|
"step": 27900
|
|
},
|
|
{
|
|
"entropy": 5.49261326789856,
|
|
"epoch": 2.531295355587808,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004359346418373935,
|
|
"loss": 5.2583,
|
|
"mean_token_accuracy": 0.18851349502801895,
|
|
"num_tokens": 57905401.0,
|
|
"step": 27905
|
|
},
|
|
{
|
|
"entropy": 5.433671712875366,
|
|
"epoch": 2.5317489114658924,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00043591202778406975,
|
|
"loss": 5.1198,
|
|
"mean_token_accuracy": 0.1957638904452324,
|
|
"num_tokens": 57916097.0,
|
|
"step": 27910
|
|
},
|
|
{
|
|
"entropy": 5.39014310836792,
|
|
"epoch": 2.5322024673439767,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004358894104030442,
|
|
"loss": 5.0141,
|
|
"mean_token_accuracy": 0.20297979116439818,
|
|
"num_tokens": 57926871.0,
|
|
"step": 27915
|
|
},
|
|
{
|
|
"entropy": 5.4334156036376955,
|
|
"epoch": 2.532656023222061,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00043586678969478464,
|
|
"loss": 5.1039,
|
|
"mean_token_accuracy": 0.20281903445720673,
|
|
"num_tokens": 57937344.0,
|
|
"step": 27920
|
|
},
|
|
{
|
|
"entropy": 5.548401689529419,
|
|
"epoch": 2.5331095791001452,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000435844165659759,
|
|
"loss": 5.2082,
|
|
"mean_token_accuracy": 0.1905469611287117,
|
|
"num_tokens": 57947633.0,
|
|
"step": 27925
|
|
},
|
|
{
|
|
"entropy": 5.452645683288575,
|
|
"epoch": 2.5335631349782295,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00043582153829843493,
|
|
"loss": 5.0806,
|
|
"mean_token_accuracy": 0.19504162222146987,
|
|
"num_tokens": 57957948.0,
|
|
"step": 27930
|
|
},
|
|
{
|
|
"entropy": 5.4584153175354,
|
|
"epoch": 2.5340166908563138,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004357989076112805,
|
|
"loss": 5.1254,
|
|
"mean_token_accuracy": 0.19332910925149918,
|
|
"num_tokens": 57967719.0,
|
|
"step": 27935
|
|
},
|
|
{
|
|
"entropy": 5.527117776870727,
|
|
"epoch": 2.5344702467343976,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004357762735987637,
|
|
"loss": 5.2034,
|
|
"mean_token_accuracy": 0.19371762871742249,
|
|
"num_tokens": 57978218.0,
|
|
"step": 27940
|
|
},
|
|
{
|
|
"entropy": 5.466984510421753,
|
|
"epoch": 2.534923802612482,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004357536362613525,
|
|
"loss": 5.0622,
|
|
"mean_token_accuracy": 0.20284992158412934,
|
|
"num_tokens": 57987860.0,
|
|
"step": 27945
|
|
},
|
|
{
|
|
"entropy": 5.443209600448609,
|
|
"epoch": 2.535377358490566,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00043573099559951516,
|
|
"loss": 5.1466,
|
|
"mean_token_accuracy": 0.20064428299665452,
|
|
"num_tokens": 57997872.0,
|
|
"step": 27950
|
|
},
|
|
{
|
|
"entropy": 5.501068210601806,
|
|
"epoch": 2.5358309143686504,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004357083516137199,
|
|
"loss": 5.2039,
|
|
"mean_token_accuracy": 0.19258169680833817,
|
|
"num_tokens": 58007771.0,
|
|
"step": 27955
|
|
},
|
|
{
|
|
"entropy": 5.536766433715821,
|
|
"epoch": 2.536284470246734,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000435685704304435,
|
|
"loss": 5.1553,
|
|
"mean_token_accuracy": 0.18980990052223207,
|
|
"num_tokens": 58018972.0,
|
|
"step": 27960
|
|
},
|
|
{
|
|
"entropy": 5.43449215888977,
|
|
"epoch": 2.5367380261248185,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00043566305367212884,
|
|
"loss": 5.0272,
|
|
"mean_token_accuracy": 0.1990218937397003,
|
|
"num_tokens": 58028581.0,
|
|
"step": 27965
|
|
},
|
|
{
|
|
"entropy": 5.397999238967896,
|
|
"epoch": 2.5371915820029027,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00043564039971726964,
|
|
"loss": 5.1591,
|
|
"mean_token_accuracy": 0.19728743880987168,
|
|
"num_tokens": 58038877.0,
|
|
"step": 27970
|
|
},
|
|
{
|
|
"entropy": 5.466147136688233,
|
|
"epoch": 2.537645137880987,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00043561774244032614,
|
|
"loss": 5.1295,
|
|
"mean_token_accuracy": 0.1981060743331909,
|
|
"num_tokens": 58048777.0,
|
|
"step": 27975
|
|
},
|
|
{
|
|
"entropy": 5.558273410797119,
|
|
"epoch": 2.5380986937590713,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00043559508184176675,
|
|
"loss": 5.2129,
|
|
"mean_token_accuracy": 0.19491234719753264,
|
|
"num_tokens": 58060270.0,
|
|
"step": 27980
|
|
},
|
|
{
|
|
"entropy": 5.462563419342041,
|
|
"epoch": 2.5385522496371555,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00043557241792206014,
|
|
"loss": 5.1612,
|
|
"mean_token_accuracy": 0.1966187760233879,
|
|
"num_tokens": 58070838.0,
|
|
"step": 27985
|
|
},
|
|
{
|
|
"entropy": 5.508216285705567,
|
|
"epoch": 2.5390058055152394,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00043554975068167505,
|
|
"loss": 5.2068,
|
|
"mean_token_accuracy": 0.19576613903045653,
|
|
"num_tokens": 58079933.0,
|
|
"step": 27990
|
|
},
|
|
{
|
|
"entropy": 5.440029716491699,
|
|
"epoch": 2.5394593613933236,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004355270801210802,
|
|
"loss": 5.159,
|
|
"mean_token_accuracy": 0.1985938921570778,
|
|
"num_tokens": 58090673.0,
|
|
"step": 27995
|
|
},
|
|
{
|
|
"entropy": 5.410306215286255,
|
|
"epoch": 2.539912917271408,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004355044062407444,
|
|
"loss": 4.981,
|
|
"mean_token_accuracy": 0.21032235622406006,
|
|
"num_tokens": 58100172.0,
|
|
"step": 28000
|
|
},
|
|
{
|
|
"entropy": 5.406428289413452,
|
|
"epoch": 2.540366473149492,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004354817290411366,
|
|
"loss": 5.1427,
|
|
"mean_token_accuracy": 0.19736346900463103,
|
|
"num_tokens": 58108965.0,
|
|
"step": 28005
|
|
},
|
|
{
|
|
"entropy": 5.484673976898193,
|
|
"epoch": 2.540820029027576,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00043545904852272573,
|
|
"loss": 5.1187,
|
|
"mean_token_accuracy": 0.1905390128493309,
|
|
"num_tokens": 58120094.0,
|
|
"step": 28010
|
|
},
|
|
{
|
|
"entropy": 5.5446977615356445,
|
|
"epoch": 2.5412735849056602,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00043543636468598083,
|
|
"loss": 5.2096,
|
|
"mean_token_accuracy": 0.18648625016212464,
|
|
"num_tokens": 58131525.0,
|
|
"step": 28015
|
|
},
|
|
{
|
|
"entropy": 5.45141224861145,
|
|
"epoch": 2.5417271407837445,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00043541367753137107,
|
|
"loss": 5.1038,
|
|
"mean_token_accuracy": 0.19663870185613633,
|
|
"num_tokens": 58141986.0,
|
|
"step": 28020
|
|
},
|
|
{
|
|
"entropy": 5.452038812637329,
|
|
"epoch": 2.5421806966618288,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004353909870593656,
|
|
"loss": 5.1693,
|
|
"mean_token_accuracy": 0.19190458655357362,
|
|
"num_tokens": 58154122.0,
|
|
"step": 28025
|
|
},
|
|
{
|
|
"entropy": 5.484263515472412,
|
|
"epoch": 2.542634252539913,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004353682932704336,
|
|
"loss": 5.0793,
|
|
"mean_token_accuracy": 0.20607253760099412,
|
|
"num_tokens": 58164148.0,
|
|
"step": 28030
|
|
},
|
|
{
|
|
"entropy": 5.384628438949585,
|
|
"epoch": 2.5430878084179973,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004353455961650444,
|
|
"loss": 5.0561,
|
|
"mean_token_accuracy": 0.19570014625787735,
|
|
"num_tokens": 58173836.0,
|
|
"step": 28035
|
|
},
|
|
{
|
|
"entropy": 5.416028070449829,
|
|
"epoch": 2.543541364296081,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004353228957436675,
|
|
"loss": 5.1299,
|
|
"mean_token_accuracy": 0.1971164122223854,
|
|
"num_tokens": 58184598.0,
|
|
"step": 28040
|
|
},
|
|
{
|
|
"entropy": 5.430428218841553,
|
|
"epoch": 2.5439949201741654,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00043530019200677215,
|
|
"loss": 5.0757,
|
|
"mean_token_accuracy": 0.1969187155365944,
|
|
"num_tokens": 58194820.0,
|
|
"step": 28045
|
|
},
|
|
{
|
|
"entropy": 5.491367197036743,
|
|
"epoch": 2.5444484760522497,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00043527748495482806,
|
|
"loss": 5.2255,
|
|
"mean_token_accuracy": 0.18882363736629487,
|
|
"num_tokens": 58206589.0,
|
|
"step": 28050
|
|
},
|
|
{
|
|
"entropy": 5.501545667648315,
|
|
"epoch": 2.544902031930334,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00043525477458830473,
|
|
"loss": 5.161,
|
|
"mean_token_accuracy": 0.19570170789957048,
|
|
"num_tokens": 58216750.0,
|
|
"step": 28055
|
|
},
|
|
{
|
|
"entropy": 5.413025522232056,
|
|
"epoch": 2.5453555878084178,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004352320609076718,
|
|
"loss": 5.1367,
|
|
"mean_token_accuracy": 0.19641029387712478,
|
|
"num_tokens": 58228496.0,
|
|
"step": 28060
|
|
},
|
|
{
|
|
"entropy": 5.43959150314331,
|
|
"epoch": 2.545809143686502,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00043520934391339894,
|
|
"loss": 5.0875,
|
|
"mean_token_accuracy": 0.19608789682388306,
|
|
"num_tokens": 58237844.0,
|
|
"step": 28065
|
|
},
|
|
{
|
|
"entropy": 5.399880504608154,
|
|
"epoch": 2.5462626995645863,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004351866236059561,
|
|
"loss": 5.0693,
|
|
"mean_token_accuracy": 0.19833358079195024,
|
|
"num_tokens": 58248522.0,
|
|
"step": 28070
|
|
},
|
|
{
|
|
"entropy": 5.394072771072388,
|
|
"epoch": 2.5467162554426706,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00043516389998581305,
|
|
"loss": 5.0737,
|
|
"mean_token_accuracy": 0.20122049152851104,
|
|
"num_tokens": 58258492.0,
|
|
"step": 28075
|
|
},
|
|
{
|
|
"entropy": 5.368023920059204,
|
|
"epoch": 2.547169811320755,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004351411730534398,
|
|
"loss": 5.0995,
|
|
"mean_token_accuracy": 0.19375693947076797,
|
|
"num_tokens": 58268683.0,
|
|
"step": 28080
|
|
},
|
|
{
|
|
"entropy": 5.455535888671875,
|
|
"epoch": 2.547623367198839,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004351184428093062,
|
|
"loss": 5.1777,
|
|
"mean_token_accuracy": 0.19224916249513627,
|
|
"num_tokens": 58279479.0,
|
|
"step": 28085
|
|
},
|
|
{
|
|
"entropy": 5.568472576141358,
|
|
"epoch": 2.5480769230769234,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004350957092538825,
|
|
"loss": 5.2182,
|
|
"mean_token_accuracy": 0.1896723911166191,
|
|
"num_tokens": 58290751.0,
|
|
"step": 28090
|
|
},
|
|
{
|
|
"entropy": 5.531956148147583,
|
|
"epoch": 2.548530478955007,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004350729723876386,
|
|
"loss": 5.2168,
|
|
"mean_token_accuracy": 0.18909630924463272,
|
|
"num_tokens": 58302163.0,
|
|
"step": 28095
|
|
},
|
|
{
|
|
"entropy": 5.4237048625946045,
|
|
"epoch": 2.5489840348330914,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00043505023221104497,
|
|
"loss": 5.1499,
|
|
"mean_token_accuracy": 0.18994668871164322,
|
|
"num_tokens": 58311488.0,
|
|
"step": 28100
|
|
},
|
|
{
|
|
"entropy": 5.462003087997436,
|
|
"epoch": 2.5494375907111757,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00043502748872457166,
|
|
"loss": 5.1206,
|
|
"mean_token_accuracy": 0.1943930983543396,
|
|
"num_tokens": 58321599.0,
|
|
"step": 28105
|
|
},
|
|
{
|
|
"entropy": 5.45291314125061,
|
|
"epoch": 2.5498911465892595,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004350047419286892,
|
|
"loss": 5.0939,
|
|
"mean_token_accuracy": 0.19603629261255265,
|
|
"num_tokens": 58330696.0,
|
|
"step": 28110
|
|
},
|
|
{
|
|
"entropy": 5.392053079605103,
|
|
"epoch": 2.550344702467344,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00043498199182386775,
|
|
"loss": 5.1498,
|
|
"mean_token_accuracy": 0.19813734143972397,
|
|
"num_tokens": 58341793.0,
|
|
"step": 28115
|
|
},
|
|
{
|
|
"entropy": 5.498857116699218,
|
|
"epoch": 2.550798258345428,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00043495923841057807,
|
|
"loss": 5.2283,
|
|
"mean_token_accuracy": 0.18695678561925888,
|
|
"num_tokens": 58352260.0,
|
|
"step": 28120
|
|
},
|
|
{
|
|
"entropy": 5.624668312072754,
|
|
"epoch": 2.5512518142235123,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00043493648168929053,
|
|
"loss": 5.272,
|
|
"mean_token_accuracy": 0.18491027802228927,
|
|
"num_tokens": 58363052.0,
|
|
"step": 28125
|
|
},
|
|
{
|
|
"entropy": 5.537218999862671,
|
|
"epoch": 2.5517053701015966,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004349137216604758,
|
|
"loss": 5.1658,
|
|
"mean_token_accuracy": 0.1913690447807312,
|
|
"num_tokens": 58374039.0,
|
|
"step": 28130
|
|
},
|
|
{
|
|
"entropy": 5.357602310180664,
|
|
"epoch": 2.552158925979681,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004348909583246045,
|
|
"loss": 4.9804,
|
|
"mean_token_accuracy": 0.20973735749721528,
|
|
"num_tokens": 58383441.0,
|
|
"step": 28135
|
|
},
|
|
{
|
|
"entropy": 5.41722526550293,
|
|
"epoch": 2.552612481857765,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004348681916821475,
|
|
"loss": 5.104,
|
|
"mean_token_accuracy": 0.19413017481565475,
|
|
"num_tokens": 58394164.0,
|
|
"step": 28140
|
|
},
|
|
{
|
|
"entropy": 5.416472387313843,
|
|
"epoch": 2.553066037735849,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004348454217335755,
|
|
"loss": 5.1306,
|
|
"mean_token_accuracy": 0.19727632999420167,
|
|
"num_tokens": 58404610.0,
|
|
"step": 28145
|
|
},
|
|
{
|
|
"entropy": 5.404795694351196,
|
|
"epoch": 2.553519593613933,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00043482264847935953,
|
|
"loss": 5.0546,
|
|
"mean_token_accuracy": 0.19759696573019028,
|
|
"num_tokens": 58414512.0,
|
|
"step": 28150
|
|
},
|
|
{
|
|
"entropy": 5.504234743118286,
|
|
"epoch": 2.5539731494920175,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00043479987191997045,
|
|
"loss": 5.2243,
|
|
"mean_token_accuracy": 0.191572867333889,
|
|
"num_tokens": 58424669.0,
|
|
"step": 28155
|
|
},
|
|
{
|
|
"entropy": 5.390405750274658,
|
|
"epoch": 2.5544267053701017,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004347770920558792,
|
|
"loss": 5.0443,
|
|
"mean_token_accuracy": 0.2006317988038063,
|
|
"num_tokens": 58435348.0,
|
|
"step": 28160
|
|
},
|
|
{
|
|
"entropy": 5.465986061096191,
|
|
"epoch": 2.5548802612481856,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00043475430888755706,
|
|
"loss": 5.1229,
|
|
"mean_token_accuracy": 0.19476572573184966,
|
|
"num_tokens": 58445534.0,
|
|
"step": 28165
|
|
},
|
|
{
|
|
"entropy": 5.464107990264893,
|
|
"epoch": 2.55533381712627,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004347315224154751,
|
|
"loss": 5.1608,
|
|
"mean_token_accuracy": 0.19368952959775926,
|
|
"num_tokens": 58456718.0,
|
|
"step": 28170
|
|
},
|
|
{
|
|
"entropy": 5.5570409297943115,
|
|
"epoch": 2.555787373004354,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004347087326401045,
|
|
"loss": 5.1992,
|
|
"mean_token_accuracy": 0.18851266354322432,
|
|
"num_tokens": 58467176.0,
|
|
"step": 28175
|
|
},
|
|
{
|
|
"entropy": 5.443571901321411,
|
|
"epoch": 2.5562409288824384,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00043468593956191663,
|
|
"loss": 5.0719,
|
|
"mean_token_accuracy": 0.201207035779953,
|
|
"num_tokens": 58477642.0,
|
|
"step": 28180
|
|
},
|
|
{
|
|
"entropy": 5.428380393981934,
|
|
"epoch": 2.5566944847605226,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004346631431813829,
|
|
"loss": 5.1165,
|
|
"mean_token_accuracy": 0.18737881183624266,
|
|
"num_tokens": 58489055.0,
|
|
"step": 28185
|
|
},
|
|
{
|
|
"entropy": 5.481821823120117,
|
|
"epoch": 2.557148040638607,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004346403434989746,
|
|
"loss": 5.1412,
|
|
"mean_token_accuracy": 0.18792611062526704,
|
|
"num_tokens": 58499062.0,
|
|
"step": 28190
|
|
},
|
|
{
|
|
"entropy": 5.45368185043335,
|
|
"epoch": 2.5576015965166907,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004346175405151633,
|
|
"loss": 5.1424,
|
|
"mean_token_accuracy": 0.1912708893418312,
|
|
"num_tokens": 58509154.0,
|
|
"step": 28195
|
|
},
|
|
{
|
|
"entropy": 5.447254419326782,
|
|
"epoch": 2.558055152394775,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004345947342304207,
|
|
"loss": 5.043,
|
|
"mean_token_accuracy": 0.1997836336493492,
|
|
"num_tokens": 58520056.0,
|
|
"step": 28200
|
|
},
|
|
{
|
|
"entropy": 5.4443258285522464,
|
|
"epoch": 2.5585087082728593,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00043457192464521827,
|
|
"loss": 5.1162,
|
|
"mean_token_accuracy": 0.1973338842391968,
|
|
"num_tokens": 58529934.0,
|
|
"step": 28205
|
|
},
|
|
{
|
|
"entropy": 5.354188013076782,
|
|
"epoch": 2.5589622641509435,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004345491117600278,
|
|
"loss": 5.0371,
|
|
"mean_token_accuracy": 0.1990734338760376,
|
|
"num_tokens": 58540013.0,
|
|
"step": 28210
|
|
},
|
|
{
|
|
"entropy": 5.519778680801392,
|
|
"epoch": 2.5594158200290273,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00043452629557532097,
|
|
"loss": 5.1405,
|
|
"mean_token_accuracy": 0.19281181544065476,
|
|
"num_tokens": 58550282.0,
|
|
"step": 28215
|
|
},
|
|
{
|
|
"entropy": 5.493044042587281,
|
|
"epoch": 2.5598693759071116,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00043450347609156974,
|
|
"loss": 5.1687,
|
|
"mean_token_accuracy": 0.18859091252088547,
|
|
"num_tokens": 58560490.0,
|
|
"step": 28220
|
|
},
|
|
{
|
|
"entropy": 5.401831865310669,
|
|
"epoch": 2.560322931785196,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00043448065330924595,
|
|
"loss": 5.178,
|
|
"mean_token_accuracy": 0.19059792757034302,
|
|
"num_tokens": 58570371.0,
|
|
"step": 28225
|
|
},
|
|
{
|
|
"entropy": 5.505850601196289,
|
|
"epoch": 2.56077648766328,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004344578272288216,
|
|
"loss": 5.0904,
|
|
"mean_token_accuracy": 0.19916279315948487,
|
|
"num_tokens": 58580701.0,
|
|
"step": 28230
|
|
},
|
|
{
|
|
"entropy": 5.494679260253906,
|
|
"epoch": 2.5612300435413644,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00043443499785076885,
|
|
"loss": 5.1718,
|
|
"mean_token_accuracy": 0.1925850048661232,
|
|
"num_tokens": 58590903.0,
|
|
"step": 28235
|
|
},
|
|
{
|
|
"entropy": 5.440380477905274,
|
|
"epoch": 2.5616835994194487,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004344121651755596,
|
|
"loss": 5.1279,
|
|
"mean_token_accuracy": 0.19333727806806564,
|
|
"num_tokens": 58600924.0,
|
|
"step": 28240
|
|
},
|
|
{
|
|
"entropy": 5.469644021987915,
|
|
"epoch": 2.5621371552975325,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00043438932920366615,
|
|
"loss": 5.2147,
|
|
"mean_token_accuracy": 0.19504625499248504,
|
|
"num_tokens": 58611369.0,
|
|
"step": 28245
|
|
},
|
|
{
|
|
"entropy": 5.545947313308716,
|
|
"epoch": 2.5625907111756168,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004343664899355608,
|
|
"loss": 5.1932,
|
|
"mean_token_accuracy": 0.19647764265537263,
|
|
"num_tokens": 58622725.0,
|
|
"step": 28250
|
|
},
|
|
{
|
|
"entropy": 5.46453857421875,
|
|
"epoch": 2.563044267053701,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00043434364737171587,
|
|
"loss": 5.1445,
|
|
"mean_token_accuracy": 0.19757252633571626,
|
|
"num_tokens": 58634157.0,
|
|
"step": 28255
|
|
},
|
|
{
|
|
"entropy": 5.445435428619385,
|
|
"epoch": 2.5634978229317853,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00043432080151260366,
|
|
"loss": 5.0283,
|
|
"mean_token_accuracy": 0.19664961397647857,
|
|
"num_tokens": 58643384.0,
|
|
"step": 28260
|
|
},
|
|
{
|
|
"entropy": 5.447703313827515,
|
|
"epoch": 2.563951378809869,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00043429795235869667,
|
|
"loss": 5.0947,
|
|
"mean_token_accuracy": 0.19713700860738753,
|
|
"num_tokens": 58653748.0,
|
|
"step": 28265
|
|
},
|
|
{
|
|
"entropy": 5.456646871566773,
|
|
"epoch": 2.5644049346879534,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00043427509991046746,
|
|
"loss": 5.1366,
|
|
"mean_token_accuracy": 0.19032903462648393,
|
|
"num_tokens": 58664619.0,
|
|
"step": 28270
|
|
},
|
|
{
|
|
"entropy": 5.41891450881958,
|
|
"epoch": 2.5648584905660377,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00043425224416838857,
|
|
"loss": 5.0273,
|
|
"mean_token_accuracy": 0.2054901346564293,
|
|
"num_tokens": 58674506.0,
|
|
"step": 28275
|
|
},
|
|
{
|
|
"entropy": 5.505383539199829,
|
|
"epoch": 2.565312046444122,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004342293851329327,
|
|
"loss": 5.2228,
|
|
"mean_token_accuracy": 0.18860923796892165,
|
|
"num_tokens": 58686252.0,
|
|
"step": 28280
|
|
},
|
|
{
|
|
"entropy": 5.451576566696167,
|
|
"epoch": 2.565765602322206,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00043420652280457255,
|
|
"loss": 5.1225,
|
|
"mean_token_accuracy": 0.1906526654958725,
|
|
"num_tokens": 58696477.0,
|
|
"step": 28285
|
|
},
|
|
{
|
|
"entropy": 5.373048973083496,
|
|
"epoch": 2.5662191582002905,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00043418365718378096,
|
|
"loss": 4.9914,
|
|
"mean_token_accuracy": 0.2068661019206047,
|
|
"num_tokens": 58706664.0,
|
|
"step": 28290
|
|
},
|
|
{
|
|
"entropy": 5.397172260284424,
|
|
"epoch": 2.5666727140783747,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004341607882710307,
|
|
"loss": 5.0834,
|
|
"mean_token_accuracy": 0.19882954210042952,
|
|
"num_tokens": 58716950.0,
|
|
"step": 28295
|
|
},
|
|
{
|
|
"entropy": 5.432723522186279,
|
|
"epoch": 2.5671262699564585,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004341379160667949,
|
|
"loss": 5.1115,
|
|
"mean_token_accuracy": 0.200768119096756,
|
|
"num_tokens": 58727723.0,
|
|
"step": 28300
|
|
},
|
|
{
|
|
"entropy": 5.42686653137207,
|
|
"epoch": 2.567579825834543,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004341150405715464,
|
|
"loss": 5.187,
|
|
"mean_token_accuracy": 0.19098964631557463,
|
|
"num_tokens": 58737956.0,
|
|
"step": 28305
|
|
},
|
|
{
|
|
"entropy": 5.443574857711792,
|
|
"epoch": 2.568033381712627,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00043409216178575826,
|
|
"loss": 5.0629,
|
|
"mean_token_accuracy": 0.20394996255636216,
|
|
"num_tokens": 58748476.0,
|
|
"step": 28310
|
|
},
|
|
{
|
|
"entropy": 5.482954311370849,
|
|
"epoch": 2.5684869375907113,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004340692797099037,
|
|
"loss": 5.1578,
|
|
"mean_token_accuracy": 0.1995851755142212,
|
|
"num_tokens": 58759604.0,
|
|
"step": 28315
|
|
},
|
|
{
|
|
"entropy": 5.472654676437378,
|
|
"epoch": 2.568940493468795,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004340463943444559,
|
|
"loss": 5.1066,
|
|
"mean_token_accuracy": 0.19930654913187026,
|
|
"num_tokens": 58769781.0,
|
|
"step": 28320
|
|
},
|
|
{
|
|
"entropy": 5.486348295211792,
|
|
"epoch": 2.5693940493468794,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004340235056898882,
|
|
"loss": 5.1562,
|
|
"mean_token_accuracy": 0.19756087362766267,
|
|
"num_tokens": 58779384.0,
|
|
"step": 28325
|
|
},
|
|
{
|
|
"entropy": 5.542926359176636,
|
|
"epoch": 2.5698476052249637,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00043400061374667374,
|
|
"loss": 5.228,
|
|
"mean_token_accuracy": 0.19291359484195708,
|
|
"num_tokens": 58791953.0,
|
|
"step": 28330
|
|
},
|
|
{
|
|
"entropy": 5.382512378692627,
|
|
"epoch": 2.570301161103048,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004339777185152862,
|
|
"loss": 5.1115,
|
|
"mean_token_accuracy": 0.1966812565922737,
|
|
"num_tokens": 58802415.0,
|
|
"step": 28335
|
|
},
|
|
{
|
|
"entropy": 5.564323472976684,
|
|
"epoch": 2.5707547169811322,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004339548199961989,
|
|
"loss": 5.1311,
|
|
"mean_token_accuracy": 0.2006854459643364,
|
|
"num_tokens": 58812582.0,
|
|
"step": 28340
|
|
},
|
|
{
|
|
"entropy": 5.449481678009033,
|
|
"epoch": 2.5712082728592165,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00043393191818988543,
|
|
"loss": 5.1795,
|
|
"mean_token_accuracy": 0.19047804325819015,
|
|
"num_tokens": 58822987.0,
|
|
"step": 28345
|
|
},
|
|
{
|
|
"entropy": 5.380622148513794,
|
|
"epoch": 2.5716618287373003,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004339090130968193,
|
|
"loss": 5.0819,
|
|
"mean_token_accuracy": 0.19899807423353194,
|
|
"num_tokens": 58832651.0,
|
|
"step": 28350
|
|
},
|
|
{
|
|
"entropy": 5.478375816345215,
|
|
"epoch": 2.5721153846153846,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004338861047174743,
|
|
"loss": 5.165,
|
|
"mean_token_accuracy": 0.19286981970071793,
|
|
"num_tokens": 58842493.0,
|
|
"step": 28355
|
|
},
|
|
{
|
|
"entropy": 5.452835369110107,
|
|
"epoch": 2.572568940493469,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004338631930523242,
|
|
"loss": 5.0332,
|
|
"mean_token_accuracy": 0.2052317276597023,
|
|
"num_tokens": 58852428.0,
|
|
"step": 28360
|
|
},
|
|
{
|
|
"entropy": 5.381743335723877,
|
|
"epoch": 2.573022496371553,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004338402781018429,
|
|
"loss": 5.0632,
|
|
"mean_token_accuracy": 0.20562693625688552,
|
|
"num_tokens": 58863234.0,
|
|
"step": 28365
|
|
},
|
|
{
|
|
"entropy": 5.41164231300354,
|
|
"epoch": 2.573476052249637,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000433817359866504,
|
|
"loss": 5.0974,
|
|
"mean_token_accuracy": 0.20417440086603164,
|
|
"num_tokens": 58872632.0,
|
|
"step": 28370
|
|
},
|
|
{
|
|
"entropy": 5.534259891510009,
|
|
"epoch": 2.573929608127721,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004337944383467817,
|
|
"loss": 5.2996,
|
|
"mean_token_accuracy": 0.1817069746553898,
|
|
"num_tokens": 58882774.0,
|
|
"step": 28375
|
|
},
|
|
{
|
|
"entropy": 5.395226860046387,
|
|
"epoch": 2.5743831640058055,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00043377151354314996,
|
|
"loss": 5.0585,
|
|
"mean_token_accuracy": 0.20583649426698686,
|
|
"num_tokens": 58892380.0,
|
|
"step": 28380
|
|
},
|
|
{
|
|
"entropy": 5.491864490509033,
|
|
"epoch": 2.5748367198838897,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004337485854560829,
|
|
"loss": 5.1329,
|
|
"mean_token_accuracy": 0.1903280258178711,
|
|
"num_tokens": 58902659.0,
|
|
"step": 28385
|
|
},
|
|
{
|
|
"entropy": 5.4210638999938965,
|
|
"epoch": 2.575290275761974,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004337256540860545,
|
|
"loss": 5.0975,
|
|
"mean_token_accuracy": 0.19838036298751832,
|
|
"num_tokens": 58913979.0,
|
|
"step": 28390
|
|
},
|
|
{
|
|
"entropy": 5.469257593154907,
|
|
"epoch": 2.5757438316400583,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004337027194335393,
|
|
"loss": 5.1842,
|
|
"mean_token_accuracy": 0.19745553135871888,
|
|
"num_tokens": 58924481.0,
|
|
"step": 28395
|
|
},
|
|
{
|
|
"entropy": 5.466364145278931,
|
|
"epoch": 2.576197387518142,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00043367978149901125,
|
|
"loss": 5.1663,
|
|
"mean_token_accuracy": 0.19140664786100386,
|
|
"num_tokens": 58936287.0,
|
|
"step": 28400
|
|
},
|
|
{
|
|
"entropy": 5.493136024475097,
|
|
"epoch": 2.5766509433962264,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00043365684028294493,
|
|
"loss": 5.1377,
|
|
"mean_token_accuracy": 0.19935017079114914,
|
|
"num_tokens": 58946070.0,
|
|
"step": 28405
|
|
},
|
|
{
|
|
"entropy": 5.4810357093811035,
|
|
"epoch": 2.5771044992743106,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00043363389578581483,
|
|
"loss": 5.2063,
|
|
"mean_token_accuracy": 0.1869784414768219,
|
|
"num_tokens": 58956083.0,
|
|
"step": 28410
|
|
},
|
|
{
|
|
"entropy": 5.496880149841308,
|
|
"epoch": 2.577558055152395,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004336109480080953,
|
|
"loss": 5.1456,
|
|
"mean_token_accuracy": 0.18932646811008452,
|
|
"num_tokens": 58967557.0,
|
|
"step": 28415
|
|
},
|
|
{
|
|
"entropy": 5.435784006118775,
|
|
"epoch": 2.5780116110304787,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004335879969502608,
|
|
"loss": 5.0924,
|
|
"mean_token_accuracy": 0.1970480501651764,
|
|
"num_tokens": 58977509.0,
|
|
"step": 28420
|
|
},
|
|
{
|
|
"entropy": 5.3605506896972654,
|
|
"epoch": 2.578465166908563,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00043356504261278625,
|
|
"loss": 4.9858,
|
|
"mean_token_accuracy": 0.2087059199810028,
|
|
"num_tokens": 58987498.0,
|
|
"step": 28425
|
|
},
|
|
{
|
|
"entropy": 5.523089647293091,
|
|
"epoch": 2.5789187227866472,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004335420849961462,
|
|
"loss": 5.2645,
|
|
"mean_token_accuracy": 0.18169484436511993,
|
|
"num_tokens": 58998503.0,
|
|
"step": 28430
|
|
},
|
|
{
|
|
"entropy": 5.43694429397583,
|
|
"epoch": 2.5793722786647315,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004335191241008154,
|
|
"loss": 5.1022,
|
|
"mean_token_accuracy": 0.19273339509963988,
|
|
"num_tokens": 59007384.0,
|
|
"step": 28435
|
|
},
|
|
{
|
|
"entropy": 5.52167592048645,
|
|
"epoch": 2.5798258345428158,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004334961599272687,
|
|
"loss": 5.2477,
|
|
"mean_token_accuracy": 0.19267988502979277,
|
|
"num_tokens": 59017739.0,
|
|
"step": 28440
|
|
},
|
|
{
|
|
"entropy": 5.500754261016846,
|
|
"epoch": 2.5802793904209,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004334731924759811,
|
|
"loss": 5.159,
|
|
"mean_token_accuracy": 0.19559521973133087,
|
|
"num_tokens": 59028439.0,
|
|
"step": 28445
|
|
},
|
|
{
|
|
"entropy": 5.473103332519531,
|
|
"epoch": 2.5807329462989843,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004334502217474274,
|
|
"loss": 5.0963,
|
|
"mean_token_accuracy": 0.19392124861478804,
|
|
"num_tokens": 59039250.0,
|
|
"step": 28450
|
|
},
|
|
{
|
|
"entropy": 5.496140336990356,
|
|
"epoch": 2.581186502177068,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00043342724774208277,
|
|
"loss": 5.2221,
|
|
"mean_token_accuracy": 0.1957597091794014,
|
|
"num_tokens": 59049375.0,
|
|
"step": 28455
|
|
},
|
|
{
|
|
"entropy": 5.4958874702453615,
|
|
"epoch": 2.5816400580551524,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00043340427046042237,
|
|
"loss": 5.2311,
|
|
"mean_token_accuracy": 0.19012197256088256,
|
|
"num_tokens": 59059873.0,
|
|
"step": 28460
|
|
},
|
|
{
|
|
"entropy": 5.431320333480835,
|
|
"epoch": 2.5820936139332367,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004333812899029212,
|
|
"loss": 5.0957,
|
|
"mean_token_accuracy": 0.20299678295850754,
|
|
"num_tokens": 59069288.0,
|
|
"step": 28465
|
|
},
|
|
{
|
|
"entropy": 5.4481102466583256,
|
|
"epoch": 2.5825471698113205,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00043335830607005456,
|
|
"loss": 5.1347,
|
|
"mean_token_accuracy": 0.19256216436624526,
|
|
"num_tokens": 59079339.0,
|
|
"step": 28470
|
|
},
|
|
{
|
|
"entropy": 5.506537675857544,
|
|
"epoch": 2.5830007256894048,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004333353189622979,
|
|
"loss": 5.1513,
|
|
"mean_token_accuracy": 0.190752811729908,
|
|
"num_tokens": 59089883.0,
|
|
"step": 28475
|
|
},
|
|
{
|
|
"entropy": 5.474219560623169,
|
|
"epoch": 2.583454281567489,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004333123285801264,
|
|
"loss": 5.2387,
|
|
"mean_token_accuracy": 0.1978512868285179,
|
|
"num_tokens": 59100532.0,
|
|
"step": 28480
|
|
},
|
|
{
|
|
"entropy": 5.462402439117431,
|
|
"epoch": 2.5839078374455733,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004332893349240156,
|
|
"loss": 5.1208,
|
|
"mean_token_accuracy": 0.19653973430395127,
|
|
"num_tokens": 59111295.0,
|
|
"step": 28485
|
|
},
|
|
{
|
|
"entropy": 5.498360013961792,
|
|
"epoch": 2.5843613933236576,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004332663379944411,
|
|
"loss": 5.1493,
|
|
"mean_token_accuracy": 0.19291332215070725,
|
|
"num_tokens": 59120808.0,
|
|
"step": 28490
|
|
},
|
|
{
|
|
"entropy": 5.47884521484375,
|
|
"epoch": 2.584814949201742,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00043324333779187844,
|
|
"loss": 5.1863,
|
|
"mean_token_accuracy": 0.20024335086345674,
|
|
"num_tokens": 59131438.0,
|
|
"step": 28495
|
|
},
|
|
{
|
|
"entropy": 5.398147630691528,
|
|
"epoch": 2.585268505079826,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00043322033431680314,
|
|
"loss": 5.1432,
|
|
"mean_token_accuracy": 0.1990566521883011,
|
|
"num_tokens": 59141701.0,
|
|
"step": 28500
|
|
},
|
|
{
|
|
"entropy": 5.416412258148194,
|
|
"epoch": 2.58572206095791,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000433197327569691,
|
|
"loss": 5.0964,
|
|
"mean_token_accuracy": 0.20096934884786605,
|
|
"num_tokens": 59152184.0,
|
|
"step": 28505
|
|
},
|
|
{
|
|
"entropy": 5.46069974899292,
|
|
"epoch": 2.586175616835994,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00043317431755101785,
|
|
"loss": 5.0708,
|
|
"mean_token_accuracy": 0.204009610414505,
|
|
"num_tokens": 59162177.0,
|
|
"step": 28510
|
|
},
|
|
{
|
|
"entropy": 5.515927410125732,
|
|
"epoch": 2.5866291727140784,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004331513042612594,
|
|
"loss": 5.229,
|
|
"mean_token_accuracy": 0.1962345138192177,
|
|
"num_tokens": 59171964.0,
|
|
"step": 28515
|
|
},
|
|
{
|
|
"entropy": 5.428318691253662,
|
|
"epoch": 2.5870827285921627,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004331282877008918,
|
|
"loss": 5.1111,
|
|
"mean_token_accuracy": 0.1970956027507782,
|
|
"num_tokens": 59182224.0,
|
|
"step": 28520
|
|
},
|
|
{
|
|
"entropy": 5.468687105178833,
|
|
"epoch": 2.5875362844702465,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004331052678703909,
|
|
"loss": 5.1014,
|
|
"mean_token_accuracy": 0.19651497304439544,
|
|
"num_tokens": 59191912.0,
|
|
"step": 28525
|
|
},
|
|
{
|
|
"entropy": 5.47572431564331,
|
|
"epoch": 2.587989840348331,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004330822447702327,
|
|
"loss": 5.0813,
|
|
"mean_token_accuracy": 0.1964610517024994,
|
|
"num_tokens": 59200984.0,
|
|
"step": 28530
|
|
},
|
|
{
|
|
"entropy": 5.477437162399292,
|
|
"epoch": 2.588443396226415,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00043305921840089347,
|
|
"loss": 5.1616,
|
|
"mean_token_accuracy": 0.19952479898929595,
|
|
"num_tokens": 59210672.0,
|
|
"step": 28535
|
|
},
|
|
{
|
|
"entropy": 5.42399640083313,
|
|
"epoch": 2.5888969521044993,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00043303618876284935,
|
|
"loss": 5.1505,
|
|
"mean_token_accuracy": 0.20214855223894118,
|
|
"num_tokens": 59220230.0,
|
|
"step": 28540
|
|
},
|
|
{
|
|
"entropy": 5.365796232223511,
|
|
"epoch": 2.5893505079825836,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00043301315585657645,
|
|
"loss": 5.0503,
|
|
"mean_token_accuracy": 0.19966747760772705,
|
|
"num_tokens": 59230615.0,
|
|
"step": 28545
|
|
},
|
|
{
|
|
"entropy": 5.5062096118927,
|
|
"epoch": 2.589804063860668,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004329901196825513,
|
|
"loss": 5.1945,
|
|
"mean_token_accuracy": 0.19572148621082305,
|
|
"num_tokens": 59241717.0,
|
|
"step": 28550
|
|
},
|
|
{
|
|
"entropy": 5.488765096664428,
|
|
"epoch": 2.5902576197387517,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00043296708024125025,
|
|
"loss": 5.1645,
|
|
"mean_token_accuracy": 0.19188499599695205,
|
|
"num_tokens": 59251791.0,
|
|
"step": 28555
|
|
},
|
|
{
|
|
"entropy": 5.379494619369507,
|
|
"epoch": 2.590711175616836,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00043294403753314965,
|
|
"loss": 5.0144,
|
|
"mean_token_accuracy": 0.20587010979652404,
|
|
"num_tokens": 59262434.0,
|
|
"step": 28560
|
|
},
|
|
{
|
|
"entropy": 5.420469665527344,
|
|
"epoch": 2.59116473149492,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004329209915587261,
|
|
"loss": 5.194,
|
|
"mean_token_accuracy": 0.19454638957977294,
|
|
"num_tokens": 59272138.0,
|
|
"step": 28565
|
|
},
|
|
{
|
|
"entropy": 5.494358968734741,
|
|
"epoch": 2.5916182873730045,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00043289794231845624,
|
|
"loss": 5.1623,
|
|
"mean_token_accuracy": 0.1969299405813217,
|
|
"num_tokens": 59283470.0,
|
|
"step": 28570
|
|
},
|
|
{
|
|
"entropy": 5.397904634475708,
|
|
"epoch": 2.5920718432510883,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004328748898128168,
|
|
"loss": 5.1227,
|
|
"mean_token_accuracy": 0.19528110474348068,
|
|
"num_tokens": 59293670.0,
|
|
"step": 28575
|
|
},
|
|
{
|
|
"entropy": 5.438844203948975,
|
|
"epoch": 2.5925253991291726,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004328518340422842,
|
|
"loss": 5.1204,
|
|
"mean_token_accuracy": 0.19745898693799974,
|
|
"num_tokens": 59303728.0,
|
|
"step": 28580
|
|
},
|
|
{
|
|
"entropy": 5.441618919372559,
|
|
"epoch": 2.592978955007257,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00043282877500733555,
|
|
"loss": 5.0901,
|
|
"mean_token_accuracy": 0.19994381964206695,
|
|
"num_tokens": 59314271.0,
|
|
"step": 28585
|
|
},
|
|
{
|
|
"entropy": 5.456299114227295,
|
|
"epoch": 2.593432510885341,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004328057127084476,
|
|
"loss": 5.1326,
|
|
"mean_token_accuracy": 0.1979525476694107,
|
|
"num_tokens": 59324581.0,
|
|
"step": 28590
|
|
},
|
|
{
|
|
"entropy": 5.430464458465576,
|
|
"epoch": 2.5938860667634254,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00043278264714609733,
|
|
"loss": 5.0853,
|
|
"mean_token_accuracy": 0.2018032804131508,
|
|
"num_tokens": 59333912.0,
|
|
"step": 28595
|
|
},
|
|
{
|
|
"entropy": 5.43172516822815,
|
|
"epoch": 2.5943396226415096,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00043275957832076173,
|
|
"loss": 5.0626,
|
|
"mean_token_accuracy": 0.19754872769117354,
|
|
"num_tokens": 59344245.0,
|
|
"step": 28600
|
|
},
|
|
{
|
|
"entropy": 5.478683805465698,
|
|
"epoch": 2.5947931785195935,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00043273650623291775,
|
|
"loss": 5.2007,
|
|
"mean_token_accuracy": 0.19545897096395493,
|
|
"num_tokens": 59353825.0,
|
|
"step": 28605
|
|
},
|
|
{
|
|
"entropy": 5.456785058975219,
|
|
"epoch": 2.5952467343976777,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004327134308830427,
|
|
"loss": 5.1528,
|
|
"mean_token_accuracy": 0.1943235769867897,
|
|
"num_tokens": 59364901.0,
|
|
"step": 28610
|
|
},
|
|
{
|
|
"entropy": 5.428807306289673,
|
|
"epoch": 2.595700290275762,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004326903522716137,
|
|
"loss": 5.0915,
|
|
"mean_token_accuracy": 0.19803925454616547,
|
|
"num_tokens": 59374772.0,
|
|
"step": 28615
|
|
},
|
|
{
|
|
"entropy": 5.360065841674805,
|
|
"epoch": 2.5961538461538463,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000432667270399108,
|
|
"loss": 4.9986,
|
|
"mean_token_accuracy": 0.21405043751001357,
|
|
"num_tokens": 59383640.0,
|
|
"step": 28620
|
|
},
|
|
{
|
|
"entropy": 5.468089246749878,
|
|
"epoch": 2.59660740203193,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00043264418526600305,
|
|
"loss": 5.0837,
|
|
"mean_token_accuracy": 0.19658653289079667,
|
|
"num_tokens": 59392928.0,
|
|
"step": 28625
|
|
},
|
|
{
|
|
"entropy": 5.527629423141479,
|
|
"epoch": 2.5970609579100143,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004326210968727761,
|
|
"loss": 5.1859,
|
|
"mean_token_accuracy": 0.1923971638083458,
|
|
"num_tokens": 59402969.0,
|
|
"step": 28630
|
|
},
|
|
{
|
|
"entropy": 5.467450952529907,
|
|
"epoch": 2.5975145137880986,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004325980052199047,
|
|
"loss": 5.1924,
|
|
"mean_token_accuracy": 0.18481415510177612,
|
|
"num_tokens": 59413439.0,
|
|
"step": 28635
|
|
},
|
|
{
|
|
"entropy": 5.466186952590943,
|
|
"epoch": 2.597968069666183,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00043257491030786644,
|
|
"loss": 5.1621,
|
|
"mean_token_accuracy": 0.19094212502241134,
|
|
"num_tokens": 59423403.0,
|
|
"step": 28640
|
|
},
|
|
{
|
|
"entropy": 5.509402942657471,
|
|
"epoch": 2.598421625544267,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00043255181213713883,
|
|
"loss": 5.2125,
|
|
"mean_token_accuracy": 0.1896583318710327,
|
|
"num_tokens": 59434519.0,
|
|
"step": 28645
|
|
},
|
|
{
|
|
"entropy": 5.479797792434693,
|
|
"epoch": 2.5988751814223514,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004325287107081996,
|
|
"loss": 5.14,
|
|
"mean_token_accuracy": 0.19123670160770417,
|
|
"num_tokens": 59445056.0,
|
|
"step": 28650
|
|
},
|
|
{
|
|
"entropy": 5.432455205917359,
|
|
"epoch": 2.5993287373004357,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004325056060215265,
|
|
"loss": 5.1024,
|
|
"mean_token_accuracy": 0.1938372239470482,
|
|
"num_tokens": 59455037.0,
|
|
"step": 28655
|
|
},
|
|
{
|
|
"entropy": 5.428658771514892,
|
|
"epoch": 2.5997822931785195,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004324824980775973,
|
|
"loss": 5.1555,
|
|
"mean_token_accuracy": 0.1947989821434021,
|
|
"num_tokens": 59465093.0,
|
|
"step": 28660
|
|
},
|
|
{
|
|
"entropy": 5.426808023452759,
|
|
"epoch": 2.6002358490566038,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00043245938687688995,
|
|
"loss": 5.2117,
|
|
"mean_token_accuracy": 0.19841732680797577,
|
|
"num_tokens": 59475449.0,
|
|
"step": 28665
|
|
},
|
|
{
|
|
"entropy": 5.5073466300964355,
|
|
"epoch": 2.600689404934688,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00043243627241988235,
|
|
"loss": 5.1444,
|
|
"mean_token_accuracy": 0.19366762638092042,
|
|
"num_tokens": 59484990.0,
|
|
"step": 28670
|
|
},
|
|
{
|
|
"entropy": 5.539692211151123,
|
|
"epoch": 2.6011429608127723,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00043241315470705254,
|
|
"loss": 5.1376,
|
|
"mean_token_accuracy": 0.19128239154815674,
|
|
"num_tokens": 59495739.0,
|
|
"step": 28675
|
|
},
|
|
{
|
|
"entropy": 5.4420253276824955,
|
|
"epoch": 2.601596516690856,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00043239003373887855,
|
|
"loss": 5.1467,
|
|
"mean_token_accuracy": 0.194882170855999,
|
|
"num_tokens": 59506432.0,
|
|
"step": 28680
|
|
},
|
|
{
|
|
"entropy": 5.440292835235596,
|
|
"epoch": 2.6020500725689404,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004323669095158385,
|
|
"loss": 5.1198,
|
|
"mean_token_accuracy": 0.19650436639785768,
|
|
"num_tokens": 59516585.0,
|
|
"step": 28685
|
|
},
|
|
{
|
|
"entropy": 5.453428840637207,
|
|
"epoch": 2.6025036284470247,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004323437820384107,
|
|
"loss": 5.1264,
|
|
"mean_token_accuracy": 0.1939498230814934,
|
|
"num_tokens": 59526824.0,
|
|
"step": 28690
|
|
},
|
|
{
|
|
"entropy": 5.553655385971069,
|
|
"epoch": 2.602957184325109,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004323206513070734,
|
|
"loss": 5.1974,
|
|
"mean_token_accuracy": 0.1913823038339615,
|
|
"num_tokens": 59537749.0,
|
|
"step": 28695
|
|
},
|
|
{
|
|
"entropy": 5.457994699478149,
|
|
"epoch": 2.603410740203193,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000432297517322305,
|
|
"loss": 5.1205,
|
|
"mean_token_accuracy": 0.18633127808570862,
|
|
"num_tokens": 59548310.0,
|
|
"step": 28700
|
|
},
|
|
{
|
|
"entropy": 5.4459856986999515,
|
|
"epoch": 2.6038642960812775,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004322743800845838,
|
|
"loss": 5.2069,
|
|
"mean_token_accuracy": 0.19442571103572845,
|
|
"num_tokens": 59558191.0,
|
|
"step": 28705
|
|
},
|
|
{
|
|
"entropy": 5.5116198539733885,
|
|
"epoch": 2.6043178519593613,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00043225123959438836,
|
|
"loss": 5.1831,
|
|
"mean_token_accuracy": 0.18727602064609528,
|
|
"num_tokens": 59568961.0,
|
|
"step": 28710
|
|
},
|
|
{
|
|
"entropy": 5.450961542129517,
|
|
"epoch": 2.6047714078374455,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00043222809585219716,
|
|
"loss": 5.1128,
|
|
"mean_token_accuracy": 0.19201462119817733,
|
|
"num_tokens": 59579137.0,
|
|
"step": 28715
|
|
},
|
|
{
|
|
"entropy": 5.2921178340911865,
|
|
"epoch": 2.60522496371553,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00043220494885848896,
|
|
"loss": 4.9449,
|
|
"mean_token_accuracy": 0.20530825704336167,
|
|
"num_tokens": 59589612.0,
|
|
"step": 28720
|
|
},
|
|
{
|
|
"entropy": 5.510920000076294,
|
|
"epoch": 2.605678519593614,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004321817986137423,
|
|
"loss": 5.1734,
|
|
"mean_token_accuracy": 0.1916310891509056,
|
|
"num_tokens": 59600332.0,
|
|
"step": 28725
|
|
},
|
|
{
|
|
"entropy": 5.402308511734009,
|
|
"epoch": 2.606132075471698,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000432158645118436,
|
|
"loss": 5.0561,
|
|
"mean_token_accuracy": 0.20507203936576843,
|
|
"num_tokens": 59610491.0,
|
|
"step": 28730
|
|
},
|
|
{
|
|
"entropy": 5.571159219741821,
|
|
"epoch": 2.606585631349782,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004321354883730488,
|
|
"loss": 5.2917,
|
|
"mean_token_accuracy": 0.18139125406742096,
|
|
"num_tokens": 59620729.0,
|
|
"step": 28735
|
|
},
|
|
{
|
|
"entropy": 5.416206884384155,
|
|
"epoch": 2.6070391872278664,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00043211232837805973,
|
|
"loss": 5.0758,
|
|
"mean_token_accuracy": 0.20193370282649994,
|
|
"num_tokens": 59631243.0,
|
|
"step": 28740
|
|
},
|
|
{
|
|
"entropy": 5.4254029273986815,
|
|
"epoch": 2.6074927431059507,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00043208916513394767,
|
|
"loss": 5.1263,
|
|
"mean_token_accuracy": 0.19873527586460113,
|
|
"num_tokens": 59642055.0,
|
|
"step": 28745
|
|
},
|
|
{
|
|
"entropy": 5.521464872360229,
|
|
"epoch": 2.607946298984035,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00043206599864119164,
|
|
"loss": 5.2044,
|
|
"mean_token_accuracy": 0.19187806248664857,
|
|
"num_tokens": 59652144.0,
|
|
"step": 28750
|
|
},
|
|
{
|
|
"entropy": 5.484245634078979,
|
|
"epoch": 2.6083998548621192,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00043204282890027074,
|
|
"loss": 5.0789,
|
|
"mean_token_accuracy": 0.20655472725629806,
|
|
"num_tokens": 59662367.0,
|
|
"step": 28755
|
|
},
|
|
{
|
|
"entropy": 5.474783992767334,
|
|
"epoch": 2.608853410740203,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00043201965591166413,
|
|
"loss": 5.1472,
|
|
"mean_token_accuracy": 0.19710581451654435,
|
|
"num_tokens": 59672729.0,
|
|
"step": 28760
|
|
},
|
|
{
|
|
"entropy": 5.511939430236817,
|
|
"epoch": 2.6093069666182873,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000431996479675851,
|
|
"loss": 5.1696,
|
|
"mean_token_accuracy": 0.2008424386382103,
|
|
"num_tokens": 59683282.0,
|
|
"step": 28765
|
|
},
|
|
{
|
|
"entropy": 5.507523536682129,
|
|
"epoch": 2.6097605224963716,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00043197330019331074,
|
|
"loss": 5.2295,
|
|
"mean_token_accuracy": 0.19028718322515487,
|
|
"num_tokens": 59694297.0,
|
|
"step": 28770
|
|
},
|
|
{
|
|
"entropy": 5.404334449768067,
|
|
"epoch": 2.610214078374456,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00043195011746452244,
|
|
"loss": 5.0584,
|
|
"mean_token_accuracy": 0.2013949066400528,
|
|
"num_tokens": 59704149.0,
|
|
"step": 28775
|
|
},
|
|
{
|
|
"entropy": 5.466426706314087,
|
|
"epoch": 2.6106676342525397,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00043192693148996585,
|
|
"loss": 5.177,
|
|
"mean_token_accuracy": 0.19796580970287322,
|
|
"num_tokens": 59714811.0,
|
|
"step": 28780
|
|
},
|
|
{
|
|
"entropy": 5.45164532661438,
|
|
"epoch": 2.611121190130624,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004319037422701203,
|
|
"loss": 5.0748,
|
|
"mean_token_accuracy": 0.20408218652009963,
|
|
"num_tokens": 59724950.0,
|
|
"step": 28785
|
|
},
|
|
{
|
|
"entropy": 5.452914142608643,
|
|
"epoch": 2.611574746008708,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004318805498054654,
|
|
"loss": 5.2328,
|
|
"mean_token_accuracy": 0.18169571012258529,
|
|
"num_tokens": 59735905.0,
|
|
"step": 28790
|
|
},
|
|
{
|
|
"entropy": 5.526255178451538,
|
|
"epoch": 2.6120283018867925,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00043185735409648077,
|
|
"loss": 5.1892,
|
|
"mean_token_accuracy": 0.19288735538721086,
|
|
"num_tokens": 59746743.0,
|
|
"step": 28795
|
|
},
|
|
{
|
|
"entropy": 5.483309984207153,
|
|
"epoch": 2.6124818577648767,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00043183415514364606,
|
|
"loss": 5.1228,
|
|
"mean_token_accuracy": 0.19303398281335832,
|
|
"num_tokens": 59757205.0,
|
|
"step": 28800
|
|
},
|
|
{
|
|
"entropy": 5.358642101287842,
|
|
"epoch": 2.612935413642961,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004318109529474411,
|
|
"loss": 5.1113,
|
|
"mean_token_accuracy": 0.20014714747667312,
|
|
"num_tokens": 59767691.0,
|
|
"step": 28805
|
|
},
|
|
{
|
|
"entropy": 5.448139953613281,
|
|
"epoch": 2.6133889695210453,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004317877475083456,
|
|
"loss": 5.1452,
|
|
"mean_token_accuracy": 0.19204398542642592,
|
|
"num_tokens": 59778618.0,
|
|
"step": 28810
|
|
},
|
|
{
|
|
"entropy": 5.517183589935303,
|
|
"epoch": 2.613842525399129,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00043176453882683955,
|
|
"loss": 5.1741,
|
|
"mean_token_accuracy": 0.18565222322940828,
|
|
"num_tokens": 59789423.0,
|
|
"step": 28815
|
|
},
|
|
{
|
|
"entropy": 5.533334970474243,
|
|
"epoch": 2.6142960812772134,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00043174132690340287,
|
|
"loss": 5.2207,
|
|
"mean_token_accuracy": 0.1823578879237175,
|
|
"num_tokens": 59800021.0,
|
|
"step": 28820
|
|
},
|
|
{
|
|
"entropy": 5.3918756484985355,
|
|
"epoch": 2.6147496371552976,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004317181117385156,
|
|
"loss": 5.0902,
|
|
"mean_token_accuracy": 0.19223477095365524,
|
|
"num_tokens": 59810006.0,
|
|
"step": 28825
|
|
},
|
|
{
|
|
"entropy": 5.459610509872436,
|
|
"epoch": 2.6152031930333814,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00043169489333265795,
|
|
"loss": 5.1485,
|
|
"mean_token_accuracy": 0.19336678385734557,
|
|
"num_tokens": 59819505.0,
|
|
"step": 28830
|
|
},
|
|
{
|
|
"entropy": 5.516499376296997,
|
|
"epoch": 2.6156567489114657,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00043167167168630977,
|
|
"loss": 5.2113,
|
|
"mean_token_accuracy": 0.19204161018133165,
|
|
"num_tokens": 59830439.0,
|
|
"step": 28835
|
|
},
|
|
{
|
|
"entropy": 5.48603515625,
|
|
"epoch": 2.61611030478955,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004316484467999516,
|
|
"loss": 5.1293,
|
|
"mean_token_accuracy": 0.19645541906356812,
|
|
"num_tokens": 59841281.0,
|
|
"step": 28840
|
|
},
|
|
{
|
|
"entropy": 5.47170581817627,
|
|
"epoch": 2.6165638606676342,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00043162521867406376,
|
|
"loss": 5.1977,
|
|
"mean_token_accuracy": 0.18256135880947114,
|
|
"num_tokens": 59853581.0,
|
|
"step": 28845
|
|
},
|
|
{
|
|
"entropy": 5.5568379878997805,
|
|
"epoch": 2.6170174165457185,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004316019873091263,
|
|
"loss": 5.205,
|
|
"mean_token_accuracy": 0.19184259623289107,
|
|
"num_tokens": 59864787.0,
|
|
"step": 28850
|
|
},
|
|
{
|
|
"entropy": 5.466487455368042,
|
|
"epoch": 2.6174709724238028,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004315787527056199,
|
|
"loss": 5.1531,
|
|
"mean_token_accuracy": 0.1979665219783783,
|
|
"num_tokens": 59875244.0,
|
|
"step": 28855
|
|
},
|
|
{
|
|
"entropy": 5.410990142822266,
|
|
"epoch": 2.617924528301887,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004315555148640251,
|
|
"loss": 5.1252,
|
|
"mean_token_accuracy": 0.192264586687088,
|
|
"num_tokens": 59886535.0,
|
|
"step": 28860
|
|
},
|
|
{
|
|
"entropy": 5.493392753601074,
|
|
"epoch": 2.618378084179971,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004315322737848222,
|
|
"loss": 5.1156,
|
|
"mean_token_accuracy": 0.19693153649568557,
|
|
"num_tokens": 59896298.0,
|
|
"step": 28865
|
|
},
|
|
{
|
|
"entropy": 5.396373653411866,
|
|
"epoch": 2.618831640058055,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000431509029468492,
|
|
"loss": 5.0905,
|
|
"mean_token_accuracy": 0.196759133040905,
|
|
"num_tokens": 59907010.0,
|
|
"step": 28870
|
|
},
|
|
{
|
|
"entropy": 5.507491254806519,
|
|
"epoch": 2.6192851959361394,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004314857819155153,
|
|
"loss": 5.0967,
|
|
"mean_token_accuracy": 0.2016877695918083,
|
|
"num_tokens": 59916247.0,
|
|
"step": 28875
|
|
},
|
|
{
|
|
"entropy": 5.390821409225464,
|
|
"epoch": 2.6197387518142237,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00043146253112637267,
|
|
"loss": 5.0161,
|
|
"mean_token_accuracy": 0.20619006752967833,
|
|
"num_tokens": 59926680.0,
|
|
"step": 28880
|
|
},
|
|
{
|
|
"entropy": 5.392478799819946,
|
|
"epoch": 2.6201923076923075,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00043143927710154504,
|
|
"loss": 5.048,
|
|
"mean_token_accuracy": 0.20607219636440277,
|
|
"num_tokens": 59936346.0,
|
|
"step": 28885
|
|
},
|
|
{
|
|
"entropy": 5.427476978302002,
|
|
"epoch": 2.6206458635703918,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004314160198415133,
|
|
"loss": 5.1576,
|
|
"mean_token_accuracy": 0.19842206686735153,
|
|
"num_tokens": 59947007.0,
|
|
"step": 28890
|
|
},
|
|
{
|
|
"entropy": 5.48990159034729,
|
|
"epoch": 2.621099419448476,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00043139275934675844,
|
|
"loss": 5.1818,
|
|
"mean_token_accuracy": 0.19234142899513246,
|
|
"num_tokens": 59957123.0,
|
|
"step": 28895
|
|
},
|
|
{
|
|
"entropy": 5.444052839279175,
|
|
"epoch": 2.6215529753265603,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004313694956177613,
|
|
"loss": 5.1385,
|
|
"mean_token_accuracy": 0.19923786371946334,
|
|
"num_tokens": 59966566.0,
|
|
"step": 28900
|
|
},
|
|
{
|
|
"entropy": 5.424648666381836,
|
|
"epoch": 2.6220065312046446,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00043134622865500334,
|
|
"loss": 5.0958,
|
|
"mean_token_accuracy": 0.19484418481588364,
|
|
"num_tokens": 59976065.0,
|
|
"step": 28905
|
|
},
|
|
{
|
|
"entropy": 5.493240070343018,
|
|
"epoch": 2.622460087082729,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004313229584589655,
|
|
"loss": 5.1228,
|
|
"mean_token_accuracy": 0.1996952176094055,
|
|
"num_tokens": 59986201.0,
|
|
"step": 28910
|
|
},
|
|
{
|
|
"entropy": 5.393883562088012,
|
|
"epoch": 2.6229136429608126,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000431299685030129,
|
|
"loss": 5.1468,
|
|
"mean_token_accuracy": 0.19320023506879808,
|
|
"num_tokens": 59996574.0,
|
|
"step": 28915
|
|
},
|
|
{
|
|
"entropy": 5.458710098266602,
|
|
"epoch": 2.623367198838897,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00043127640836897516,
|
|
"loss": 5.1655,
|
|
"mean_token_accuracy": 0.19762139916419982,
|
|
"num_tokens": 60006082.0,
|
|
"step": 28920
|
|
},
|
|
{
|
|
"entropy": 5.470600128173828,
|
|
"epoch": 2.623820754716981,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004312531284759854,
|
|
"loss": 5.1268,
|
|
"mean_token_accuracy": 0.1925727754831314,
|
|
"num_tokens": 60015483.0,
|
|
"step": 28925
|
|
},
|
|
{
|
|
"entropy": 5.497373819351196,
|
|
"epoch": 2.6242743105950654,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00043122984535164116,
|
|
"loss": 5.0631,
|
|
"mean_token_accuracy": 0.20681374669075012,
|
|
"num_tokens": 60025984.0,
|
|
"step": 28930
|
|
},
|
|
{
|
|
"entropy": 5.494083738327026,
|
|
"epoch": 2.6247278664731493,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00043120655899642386,
|
|
"loss": 5.1229,
|
|
"mean_token_accuracy": 0.19177793860435485,
|
|
"num_tokens": 60036109.0,
|
|
"step": 28935
|
|
},
|
|
{
|
|
"entropy": 5.553118896484375,
|
|
"epoch": 2.6251814223512335,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00043118326941081513,
|
|
"loss": 5.193,
|
|
"mean_token_accuracy": 0.18823944330215453,
|
|
"num_tokens": 60046546.0,
|
|
"step": 28940
|
|
},
|
|
{
|
|
"entropy": 5.48793134689331,
|
|
"epoch": 2.625634978229318,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004311599765952966,
|
|
"loss": 5.2081,
|
|
"mean_token_accuracy": 0.19987789690494537,
|
|
"num_tokens": 60056768.0,
|
|
"step": 28945
|
|
},
|
|
{
|
|
"entropy": 5.486684989929199,
|
|
"epoch": 2.626088534107402,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00043113668055034995,
|
|
"loss": 5.2525,
|
|
"mean_token_accuracy": 0.18914880603551865,
|
|
"num_tokens": 60066962.0,
|
|
"step": 28950
|
|
},
|
|
{
|
|
"entropy": 5.482069826126098,
|
|
"epoch": 2.6265420899854863,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004311133812764569,
|
|
"loss": 5.1306,
|
|
"mean_token_accuracy": 0.19418049454689026,
|
|
"num_tokens": 60076477.0,
|
|
"step": 28955
|
|
},
|
|
{
|
|
"entropy": 5.409635972976685,
|
|
"epoch": 2.6269956458635706,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00043109007877409946,
|
|
"loss": 5.0213,
|
|
"mean_token_accuracy": 0.20124822854995728,
|
|
"num_tokens": 60088060.0,
|
|
"step": 28960
|
|
},
|
|
{
|
|
"entropy": 5.4533556461334225,
|
|
"epoch": 2.6274492017416544,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00043106677304375935,
|
|
"loss": 5.1575,
|
|
"mean_token_accuracy": 0.19732300341129302,
|
|
"num_tokens": 60098677.0,
|
|
"step": 28965
|
|
},
|
|
{
|
|
"entropy": 5.508442544937134,
|
|
"epoch": 2.6279027576197387,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004310434640859186,
|
|
"loss": 5.1979,
|
|
"mean_token_accuracy": 0.19381850212812424,
|
|
"num_tokens": 60109054.0,
|
|
"step": 28970
|
|
},
|
|
{
|
|
"entropy": 5.43244252204895,
|
|
"epoch": 2.628356313497823,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004310201519010592,
|
|
"loss": 5.0626,
|
|
"mean_token_accuracy": 0.20294984579086303,
|
|
"num_tokens": 60119951.0,
|
|
"step": 28975
|
|
},
|
|
{
|
|
"entropy": 5.326442718505859,
|
|
"epoch": 2.628809869375907,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00043099683648966335,
|
|
"loss": 5.0088,
|
|
"mean_token_accuracy": 0.20029909610748292,
|
|
"num_tokens": 60130026.0,
|
|
"step": 28980
|
|
},
|
|
{
|
|
"entropy": 5.3603355884552,
|
|
"epoch": 2.629263425253991,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004309735178522132,
|
|
"loss": 5.0437,
|
|
"mean_token_accuracy": 0.20576637089252472,
|
|
"num_tokens": 60140748.0,
|
|
"step": 28985
|
|
},
|
|
{
|
|
"entropy": 5.437090635299683,
|
|
"epoch": 2.6297169811320753,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004309501959891909,
|
|
"loss": 5.1086,
|
|
"mean_token_accuracy": 0.19918859899044036,
|
|
"num_tokens": 60151042.0,
|
|
"step": 28990
|
|
},
|
|
{
|
|
"entropy": 5.5001976013183596,
|
|
"epoch": 2.6301705370101596,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00043092687090107883,
|
|
"loss": 5.0997,
|
|
"mean_token_accuracy": 0.19202472120523453,
|
|
"num_tokens": 60160758.0,
|
|
"step": 28995
|
|
},
|
|
{
|
|
"entropy": 5.399976062774658,
|
|
"epoch": 2.630624092888244,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00043090354258835934,
|
|
"loss": 5.1402,
|
|
"mean_token_accuracy": 0.19159202724695207,
|
|
"num_tokens": 60170249.0,
|
|
"step": 29000
|
|
},
|
|
{
|
|
"entropy": 5.4228448390960695,
|
|
"epoch": 2.631077648766328,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00043088021105151483,
|
|
"loss": 5.1403,
|
|
"mean_token_accuracy": 0.197448992729187,
|
|
"num_tokens": 60181216.0,
|
|
"step": 29005
|
|
},
|
|
{
|
|
"entropy": 5.425262022018432,
|
|
"epoch": 2.6315312046444124,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004308568762910279,
|
|
"loss": 5.091,
|
|
"mean_token_accuracy": 0.20086933076381683,
|
|
"num_tokens": 60190559.0,
|
|
"step": 29010
|
|
},
|
|
{
|
|
"entropy": 5.580953979492188,
|
|
"epoch": 2.6319847605224966,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00043083353830738097,
|
|
"loss": 5.2226,
|
|
"mean_token_accuracy": 0.18484575748443605,
|
|
"num_tokens": 60201268.0,
|
|
"step": 29015
|
|
},
|
|
{
|
|
"entropy": 5.4058754444122314,
|
|
"epoch": 2.6324383164005805,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00043081019710105683,
|
|
"loss": 4.9708,
|
|
"mean_token_accuracy": 0.19910791665315627,
|
|
"num_tokens": 60210907.0,
|
|
"step": 29020
|
|
},
|
|
{
|
|
"entropy": 5.3628521919250485,
|
|
"epoch": 2.6328918722786647,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004307868526725381,
|
|
"loss": 5.0444,
|
|
"mean_token_accuracy": 0.19977784007787705,
|
|
"num_tokens": 60220298.0,
|
|
"step": 29025
|
|
},
|
|
{
|
|
"entropy": 5.362751293182373,
|
|
"epoch": 2.633345428156749,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004307635050223075,
|
|
"loss": 5.071,
|
|
"mean_token_accuracy": 0.2060060366988182,
|
|
"num_tokens": 60230811.0,
|
|
"step": 29030
|
|
},
|
|
{
|
|
"entropy": 5.473233890533447,
|
|
"epoch": 2.6337989840348333,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000430740154150848,
|
|
"loss": 5.0307,
|
|
"mean_token_accuracy": 0.20202568769454957,
|
|
"num_tokens": 60241211.0,
|
|
"step": 29035
|
|
},
|
|
{
|
|
"entropy": 5.405398035049439,
|
|
"epoch": 2.634252539912917,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004307168000586423,
|
|
"loss": 5.0787,
|
|
"mean_token_accuracy": 0.2043818101286888,
|
|
"num_tokens": 60251506.0,
|
|
"step": 29040
|
|
},
|
|
{
|
|
"entropy": 5.397137069702149,
|
|
"epoch": 2.6347060957910013,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004306934427461736,
|
|
"loss": 5.0662,
|
|
"mean_token_accuracy": 0.2089862197637558,
|
|
"num_tokens": 60261416.0,
|
|
"step": 29045
|
|
},
|
|
{
|
|
"entropy": 5.4813906192779545,
|
|
"epoch": 2.6351596516690856,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004306700822139248,
|
|
"loss": 5.1244,
|
|
"mean_token_accuracy": 0.197095787525177,
|
|
"num_tokens": 60272315.0,
|
|
"step": 29050
|
|
},
|
|
{
|
|
"entropy": 5.477901649475098,
|
|
"epoch": 2.63561320754717,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000430646718462379,
|
|
"loss": 5.1891,
|
|
"mean_token_accuracy": 0.19563914090394974,
|
|
"num_tokens": 60282722.0,
|
|
"step": 29055
|
|
},
|
|
{
|
|
"entropy": 5.423585081100464,
|
|
"epoch": 2.636066763425254,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004306233514920194,
|
|
"loss": 5.117,
|
|
"mean_token_accuracy": 0.1935572236776352,
|
|
"num_tokens": 60292636.0,
|
|
"step": 29060
|
|
},
|
|
{
|
|
"entropy": 5.4510420799255375,
|
|
"epoch": 2.6365203193033384,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00043059998130332933,
|
|
"loss": 5.0987,
|
|
"mean_token_accuracy": 0.20251962095499038,
|
|
"num_tokens": 60302979.0,
|
|
"step": 29065
|
|
},
|
|
{
|
|
"entropy": 5.452149820327759,
|
|
"epoch": 2.6369738751814222,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00043057660789679194,
|
|
"loss": 5.1279,
|
|
"mean_token_accuracy": 0.19787863045930862,
|
|
"num_tokens": 60313181.0,
|
|
"step": 29070
|
|
},
|
|
{
|
|
"entropy": 5.458758974075318,
|
|
"epoch": 2.6374274310595065,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004305532312728906,
|
|
"loss": 5.0841,
|
|
"mean_token_accuracy": 0.1955509677529335,
|
|
"num_tokens": 60323401.0,
|
|
"step": 29075
|
|
},
|
|
{
|
|
"entropy": 5.465690469741821,
|
|
"epoch": 2.6378809869375908,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004305298514321088,
|
|
"loss": 5.1846,
|
|
"mean_token_accuracy": 0.19056945592164992,
|
|
"num_tokens": 60333478.0,
|
|
"step": 29080
|
|
},
|
|
{
|
|
"entropy": 5.474025869369507,
|
|
"epoch": 2.638334542815675,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00043050646837493014,
|
|
"loss": 5.0777,
|
|
"mean_token_accuracy": 0.2010500341653824,
|
|
"num_tokens": 60343980.0,
|
|
"step": 29085
|
|
},
|
|
{
|
|
"entropy": 5.457110786437989,
|
|
"epoch": 2.638788098693759,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004304830821018381,
|
|
"loss": 5.0991,
|
|
"mean_token_accuracy": 0.19840539544820784,
|
|
"num_tokens": 60354262.0,
|
|
"step": 29090
|
|
},
|
|
{
|
|
"entropy": 5.472892475128174,
|
|
"epoch": 2.639241654571843,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004304596926133162,
|
|
"loss": 5.1646,
|
|
"mean_token_accuracy": 0.19989408999681474,
|
|
"num_tokens": 60364137.0,
|
|
"step": 29095
|
|
},
|
|
{
|
|
"entropy": 5.41890058517456,
|
|
"epoch": 2.6396952104499274,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00043043629990984823,
|
|
"loss": 5.1702,
|
|
"mean_token_accuracy": 0.191661474108696,
|
|
"num_tokens": 60374528.0,
|
|
"step": 29100
|
|
},
|
|
{
|
|
"entropy": 5.448637533187866,
|
|
"epoch": 2.6401487663280117,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00043041290399191797,
|
|
"loss": 5.14,
|
|
"mean_token_accuracy": 0.19798330515623092,
|
|
"num_tokens": 60384880.0,
|
|
"step": 29105
|
|
},
|
|
{
|
|
"entropy": 5.4928178787231445,
|
|
"epoch": 2.640602322206096,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004303895048600093,
|
|
"loss": 5.0683,
|
|
"mean_token_accuracy": 0.19662932604551314,
|
|
"num_tokens": 60395543.0,
|
|
"step": 29110
|
|
},
|
|
{
|
|
"entropy": 5.491670799255371,
|
|
"epoch": 2.64105587808418,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004303661025146061,
|
|
"loss": 5.1043,
|
|
"mean_token_accuracy": 0.19778985381126404,
|
|
"num_tokens": 60405432.0,
|
|
"step": 29115
|
|
},
|
|
{
|
|
"entropy": 5.499238395690918,
|
|
"epoch": 2.641509433962264,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004303426969561922,
|
|
"loss": 5.1965,
|
|
"mean_token_accuracy": 0.18782521784305573,
|
|
"num_tokens": 60416360.0,
|
|
"step": 29120
|
|
},
|
|
{
|
|
"entropy": 5.4677268981933596,
|
|
"epoch": 2.6419629898403483,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004303192881852518,
|
|
"loss": 5.1412,
|
|
"mean_token_accuracy": 0.19429480135440827,
|
|
"num_tokens": 60426371.0,
|
|
"step": 29125
|
|
},
|
|
{
|
|
"entropy": 5.490205430984497,
|
|
"epoch": 2.6424165457184325,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00043029587620226897,
|
|
"loss": 5.1274,
|
|
"mean_token_accuracy": 0.1926904320716858,
|
|
"num_tokens": 60437505.0,
|
|
"step": 29130
|
|
},
|
|
{
|
|
"entropy": 5.487719488143921,
|
|
"epoch": 2.642870101596517,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004302724610077278,
|
|
"loss": 5.1212,
|
|
"mean_token_accuracy": 0.1945409208536148,
|
|
"num_tokens": 60448170.0,
|
|
"step": 29135
|
|
},
|
|
{
|
|
"entropy": 5.480887317657471,
|
|
"epoch": 2.6433236574746006,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004302490426021126,
|
|
"loss": 5.2163,
|
|
"mean_token_accuracy": 0.18564389944076537,
|
|
"num_tokens": 60458776.0,
|
|
"step": 29140
|
|
},
|
|
{
|
|
"entropy": 5.434029006958008,
|
|
"epoch": 2.643777213352685,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004302256209859076,
|
|
"loss": 5.1001,
|
|
"mean_token_accuracy": 0.20651496201753616,
|
|
"num_tokens": 60468279.0,
|
|
"step": 29145
|
|
},
|
|
{
|
|
"entropy": 5.486887121200562,
|
|
"epoch": 2.644230769230769,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00043020219615959727,
|
|
"loss": 5.1776,
|
|
"mean_token_accuracy": 0.18980637788772584,
|
|
"num_tokens": 60478507.0,
|
|
"step": 29150
|
|
},
|
|
{
|
|
"entropy": 5.547963047027588,
|
|
"epoch": 2.6446843251088534,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004301787681236659,
|
|
"loss": 5.2255,
|
|
"mean_token_accuracy": 0.1865597516298294,
|
|
"num_tokens": 60489016.0,
|
|
"step": 29155
|
|
},
|
|
{
|
|
"entropy": 5.5279529094696045,
|
|
"epoch": 2.6451378809869377,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004301553368785981,
|
|
"loss": 5.179,
|
|
"mean_token_accuracy": 0.1900160565972328,
|
|
"num_tokens": 60500169.0,
|
|
"step": 29160
|
|
},
|
|
{
|
|
"entropy": 5.378922367095948,
|
|
"epoch": 2.645591436865022,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004301319024248784,
|
|
"loss": 5.0704,
|
|
"mean_token_accuracy": 0.19661298990249634,
|
|
"num_tokens": 60511109.0,
|
|
"step": 29165
|
|
},
|
|
{
|
|
"entropy": 5.379435682296753,
|
|
"epoch": 2.6460449927431062,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00043010846476299145,
|
|
"loss": 5.0891,
|
|
"mean_token_accuracy": 0.20474544912576675,
|
|
"num_tokens": 60521735.0,
|
|
"step": 29170
|
|
},
|
|
{
|
|
"entropy": 5.533560371398925,
|
|
"epoch": 2.64649854862119,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004300850238934219,
|
|
"loss": 5.1642,
|
|
"mean_token_accuracy": 0.1899804174900055,
|
|
"num_tokens": 60532071.0,
|
|
"step": 29175
|
|
},
|
|
{
|
|
"entropy": 5.508131456375122,
|
|
"epoch": 2.6469521044992743,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00043006157981665446,
|
|
"loss": 5.1055,
|
|
"mean_token_accuracy": 0.19868643283843995,
|
|
"num_tokens": 60541909.0,
|
|
"step": 29180
|
|
},
|
|
{
|
|
"entropy": 5.394447183609008,
|
|
"epoch": 2.6474056603773586,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00043003813253317415,
|
|
"loss": 5.0776,
|
|
"mean_token_accuracy": 0.19971198588609695,
|
|
"num_tokens": 60551361.0,
|
|
"step": 29185
|
|
},
|
|
{
|
|
"entropy": 5.3695954322814945,
|
|
"epoch": 2.6478592162554424,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00043001468204346564,
|
|
"loss": 5.1618,
|
|
"mean_token_accuracy": 0.19637354612350463,
|
|
"num_tokens": 60562112.0,
|
|
"step": 29190
|
|
},
|
|
{
|
|
"entropy": 5.487666177749634,
|
|
"epoch": 2.6483127721335267,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00042999122834801406,
|
|
"loss": 5.1664,
|
|
"mean_token_accuracy": 0.18817604035139085,
|
|
"num_tokens": 60572827.0,
|
|
"step": 29195
|
|
},
|
|
{
|
|
"entropy": 5.414308691024781,
|
|
"epoch": 2.648766328011611,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004299677714473044,
|
|
"loss": 5.0609,
|
|
"mean_token_accuracy": 0.2005642682313919,
|
|
"num_tokens": 60582222.0,
|
|
"step": 29200
|
|
},
|
|
{
|
|
"entropy": 5.479833602905273,
|
|
"epoch": 2.649219883889695,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004299443113418217,
|
|
"loss": 5.1649,
|
|
"mean_token_accuracy": 0.19728855937719345,
|
|
"num_tokens": 60592943.0,
|
|
"step": 29205
|
|
},
|
|
{
|
|
"entropy": 5.455406332015992,
|
|
"epoch": 2.6496734397677795,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00042992084803205124,
|
|
"loss": 5.135,
|
|
"mean_token_accuracy": 0.19524182975292206,
|
|
"num_tokens": 60603206.0,
|
|
"step": 29210
|
|
},
|
|
{
|
|
"entropy": 5.403353261947632,
|
|
"epoch": 2.6501269956458637,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000429897381518478,
|
|
"loss": 5.0747,
|
|
"mean_token_accuracy": 0.20084209740161896,
|
|
"num_tokens": 60614776.0,
|
|
"step": 29215
|
|
},
|
|
{
|
|
"entropy": 5.436590337753296,
|
|
"epoch": 2.650580551523948,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00042987391180158757,
|
|
"loss": 5.0807,
|
|
"mean_token_accuracy": 0.19743491113185882,
|
|
"num_tokens": 60625914.0,
|
|
"step": 29220
|
|
},
|
|
{
|
|
"entropy": 5.431179428100586,
|
|
"epoch": 2.651034107402032,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00042985043888186516,
|
|
"loss": 5.1071,
|
|
"mean_token_accuracy": 0.20042033791542052,
|
|
"num_tokens": 60636934.0,
|
|
"step": 29225
|
|
},
|
|
{
|
|
"entropy": 5.435689640045166,
|
|
"epoch": 2.651487663280116,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004298269627597962,
|
|
"loss": 5.1343,
|
|
"mean_token_accuracy": 0.19107767045497895,
|
|
"num_tokens": 60647707.0,
|
|
"step": 29230
|
|
},
|
|
{
|
|
"entropy": 5.392133522033691,
|
|
"epoch": 2.6519412191582004,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00042980348343586624,
|
|
"loss": 5.0643,
|
|
"mean_token_accuracy": 0.19855798184871673,
|
|
"num_tokens": 60658691.0,
|
|
"step": 29235
|
|
},
|
|
{
|
|
"entropy": 5.441264533996582,
|
|
"epoch": 2.6523947750362846,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00042978000091056074,
|
|
"loss": 5.1606,
|
|
"mean_token_accuracy": 0.19569013714790345,
|
|
"num_tokens": 60668479.0,
|
|
"step": 29240
|
|
},
|
|
{
|
|
"entropy": 5.44349217414856,
|
|
"epoch": 2.6528483309143684,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004297565151843653,
|
|
"loss": 5.0281,
|
|
"mean_token_accuracy": 0.20135795176029206,
|
|
"num_tokens": 60679158.0,
|
|
"step": 29245
|
|
},
|
|
{
|
|
"entropy": 5.499759244918823,
|
|
"epoch": 2.6533018867924527,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004297330262577659,
|
|
"loss": 5.243,
|
|
"mean_token_accuracy": 0.18976051211357117,
|
|
"num_tokens": 60689363.0,
|
|
"step": 29250
|
|
},
|
|
{
|
|
"entropy": 5.411139917373657,
|
|
"epoch": 2.653755442670537,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004297095341312479,
|
|
"loss": 5.0016,
|
|
"mean_token_accuracy": 0.20142282247543336,
|
|
"num_tokens": 60699650.0,
|
|
"step": 29255
|
|
},
|
|
{
|
|
"entropy": 5.411409091949463,
|
|
"epoch": 2.6542089985486212,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004296860388052974,
|
|
"loss": 5.0908,
|
|
"mean_token_accuracy": 0.1967955932021141,
|
|
"num_tokens": 60709921.0,
|
|
"step": 29260
|
|
},
|
|
{
|
|
"entropy": 5.458208751678467,
|
|
"epoch": 2.6546625544267055,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00042966254028040015,
|
|
"loss": 5.0826,
|
|
"mean_token_accuracy": 0.1990387976169586,
|
|
"num_tokens": 60720112.0,
|
|
"step": 29265
|
|
},
|
|
{
|
|
"entropy": 5.413223743438721,
|
|
"epoch": 2.65511611030479,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00042963903855704216,
|
|
"loss": 5.0311,
|
|
"mean_token_accuracy": 0.19280820190906525,
|
|
"num_tokens": 60730604.0,
|
|
"step": 29270
|
|
},
|
|
{
|
|
"entropy": 5.372323226928711,
|
|
"epoch": 2.6555696661828736,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00042961553363570946,
|
|
"loss": 5.0828,
|
|
"mean_token_accuracy": 0.20043278783559798,
|
|
"num_tokens": 60740896.0,
|
|
"step": 29275
|
|
},
|
|
{
|
|
"entropy": 5.483045959472657,
|
|
"epoch": 2.656023222060958,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004295920255168881,
|
|
"loss": 5.0874,
|
|
"mean_token_accuracy": 0.1999877229332924,
|
|
"num_tokens": 60751771.0,
|
|
"step": 29280
|
|
},
|
|
{
|
|
"entropy": 5.497738361358643,
|
|
"epoch": 2.656476777939042,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00042956851420106423,
|
|
"loss": 5.1466,
|
|
"mean_token_accuracy": 0.19612168669700622,
|
|
"num_tokens": 60762802.0,
|
|
"step": 29285
|
|
},
|
|
{
|
|
"entropy": 5.416465091705322,
|
|
"epoch": 2.6569303338171264,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004295449996887242,
|
|
"loss": 5.065,
|
|
"mean_token_accuracy": 0.20077981650829316,
|
|
"num_tokens": 60774102.0,
|
|
"step": 29290
|
|
},
|
|
{
|
|
"entropy": 5.405487060546875,
|
|
"epoch": 2.65738388969521,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004295214819803541,
|
|
"loss": 5.1314,
|
|
"mean_token_accuracy": 0.19476838856935502,
|
|
"num_tokens": 60785383.0,
|
|
"step": 29295
|
|
},
|
|
{
|
|
"entropy": 5.448839998245239,
|
|
"epoch": 2.6578374455732945,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00042949796107644053,
|
|
"loss": 5.1147,
|
|
"mean_token_accuracy": 0.20209996849298478,
|
|
"num_tokens": 60795173.0,
|
|
"step": 29300
|
|
},
|
|
{
|
|
"entropy": 5.484297609329223,
|
|
"epoch": 2.6582910014513788,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00042947443697746956,
|
|
"loss": 5.1078,
|
|
"mean_token_accuracy": 0.20254946798086165,
|
|
"num_tokens": 60805621.0,
|
|
"step": 29305
|
|
},
|
|
{
|
|
"entropy": 5.485119342803955,
|
|
"epoch": 2.658744557329463,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004294509096839279,
|
|
"loss": 5.2345,
|
|
"mean_token_accuracy": 0.18484722822904587,
|
|
"num_tokens": 60816799.0,
|
|
"step": 29310
|
|
},
|
|
{
|
|
"entropy": 5.344655752182007,
|
|
"epoch": 2.6591981132075473,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00042942737919630215,
|
|
"loss": 5.0377,
|
|
"mean_token_accuracy": 0.19815288186073304,
|
|
"num_tokens": 60826827.0,
|
|
"step": 29315
|
|
},
|
|
{
|
|
"entropy": 5.428536891937256,
|
|
"epoch": 2.6596516690856316,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00042940384551507876,
|
|
"loss": 5.1196,
|
|
"mean_token_accuracy": 0.19957258701324462,
|
|
"num_tokens": 60836567.0,
|
|
"step": 29320
|
|
},
|
|
{
|
|
"entropy": 5.4341628074646,
|
|
"epoch": 2.6601052249637154,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004293803086407447,
|
|
"loss": 5.1105,
|
|
"mean_token_accuracy": 0.19295050501823424,
|
|
"num_tokens": 60846723.0,
|
|
"step": 29325
|
|
},
|
|
{
|
|
"entropy": 5.469846534729004,
|
|
"epoch": 2.6605587808417996,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004293567685737863,
|
|
"loss": 5.2185,
|
|
"mean_token_accuracy": 0.19187780767679213,
|
|
"num_tokens": 60857434.0,
|
|
"step": 29330
|
|
},
|
|
{
|
|
"entropy": 5.503839826583862,
|
|
"epoch": 2.661012336719884,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00042933322531469074,
|
|
"loss": 5.1777,
|
|
"mean_token_accuracy": 0.19434020221233367,
|
|
"num_tokens": 60868780.0,
|
|
"step": 29335
|
|
},
|
|
{
|
|
"entropy": 5.532587623596191,
|
|
"epoch": 2.661465892597968,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00042930967886394456,
|
|
"loss": 5.172,
|
|
"mean_token_accuracy": 0.19705101400613784,
|
|
"num_tokens": 60879037.0,
|
|
"step": 29340
|
|
},
|
|
{
|
|
"entropy": 5.37778754234314,
|
|
"epoch": 2.661919448476052,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000429286129222035,
|
|
"loss": 5.0991,
|
|
"mean_token_accuracy": 0.19751688987016677,
|
|
"num_tokens": 60889543.0,
|
|
"step": 29345
|
|
},
|
|
{
|
|
"entropy": 5.373901748657227,
|
|
"epoch": 2.6623730043541363,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000429262576389449,
|
|
"loss": 5.0912,
|
|
"mean_token_accuracy": 0.1962379053235054,
|
|
"num_tokens": 60900141.0,
|
|
"step": 29350
|
|
},
|
|
{
|
|
"entropy": 5.471867513656616,
|
|
"epoch": 2.6628265602322205,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004292390203666736,
|
|
"loss": 5.1287,
|
|
"mean_token_accuracy": 0.20202799290418624,
|
|
"num_tokens": 60910244.0,
|
|
"step": 29355
|
|
},
|
|
{
|
|
"entropy": 5.430280303955078,
|
|
"epoch": 2.663280116110305,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000429215461154196,
|
|
"loss": 5.0676,
|
|
"mean_token_accuracy": 0.2065708667039871,
|
|
"num_tokens": 60919908.0,
|
|
"step": 29360
|
|
},
|
|
{
|
|
"entropy": 5.4005711555480955,
|
|
"epoch": 2.663733671988389,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00042919189875250324,
|
|
"loss": 5.1219,
|
|
"mean_token_accuracy": 0.19241765588521959,
|
|
"num_tokens": 60929096.0,
|
|
"step": 29365
|
|
},
|
|
{
|
|
"entropy": 5.423188638687134,
|
|
"epoch": 2.6641872278664733,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00042916833316208284,
|
|
"loss": 5.092,
|
|
"mean_token_accuracy": 0.19420232325792314,
|
|
"num_tokens": 60939346.0,
|
|
"step": 29370
|
|
},
|
|
{
|
|
"entropy": 5.505782508850098,
|
|
"epoch": 2.6646407837445576,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004291447643834219,
|
|
"loss": 5.121,
|
|
"mean_token_accuracy": 0.19410959929227828,
|
|
"num_tokens": 60950364.0,
|
|
"step": 29375
|
|
},
|
|
{
|
|
"entropy": 5.452425861358643,
|
|
"epoch": 2.6650943396226414,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000429121192417008,
|
|
"loss": 5.0658,
|
|
"mean_token_accuracy": 0.20124853402376175,
|
|
"num_tokens": 60960905.0,
|
|
"step": 29380
|
|
},
|
|
{
|
|
"entropy": 5.470377445220947,
|
|
"epoch": 2.6655478955007257,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00042909761726332864,
|
|
"loss": 5.1331,
|
|
"mean_token_accuracy": 0.2032613679766655,
|
|
"num_tokens": 60971281.0,
|
|
"step": 29385
|
|
},
|
|
{
|
|
"entropy": 5.41895227432251,
|
|
"epoch": 2.66600145137881,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004290740389228712,
|
|
"loss": 5.1363,
|
|
"mean_token_accuracy": 0.1970226988196373,
|
|
"num_tokens": 60982522.0,
|
|
"step": 29390
|
|
},
|
|
{
|
|
"entropy": 5.411933469772339,
|
|
"epoch": 2.6664550072568938,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00042905045739612347,
|
|
"loss": 5.1315,
|
|
"mean_token_accuracy": 0.19336792826652527,
|
|
"num_tokens": 60992738.0,
|
|
"step": 29395
|
|
},
|
|
{
|
|
"entropy": 5.52802472114563,
|
|
"epoch": 2.666908563134978,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00042902687268357297,
|
|
"loss": 5.2271,
|
|
"mean_token_accuracy": 0.19553557485342027,
|
|
"num_tokens": 61003665.0,
|
|
"step": 29400
|
|
},
|
|
{
|
|
"entropy": 5.618065309524536,
|
|
"epoch": 2.6673621190130623,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00042900328478570745,
|
|
"loss": 5.2535,
|
|
"mean_token_accuracy": 0.19044299572706222,
|
|
"num_tokens": 61014663.0,
|
|
"step": 29405
|
|
},
|
|
{
|
|
"entropy": 5.437908935546875,
|
|
"epoch": 2.6678156748911466,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004289796937030148,
|
|
"loss": 5.0352,
|
|
"mean_token_accuracy": 0.2021021857857704,
|
|
"num_tokens": 61024916.0,
|
|
"step": 29410
|
|
},
|
|
{
|
|
"entropy": 5.351429653167725,
|
|
"epoch": 2.668269230769231,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00042895609943598286,
|
|
"loss": 5.0519,
|
|
"mean_token_accuracy": 0.19803449809551238,
|
|
"num_tokens": 61035043.0,
|
|
"step": 29415
|
|
},
|
|
{
|
|
"entropy": 5.439659166336059,
|
|
"epoch": 2.668722786647315,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004289325019850995,
|
|
"loss": 5.1839,
|
|
"mean_token_accuracy": 0.1896361529827118,
|
|
"num_tokens": 61046153.0,
|
|
"step": 29420
|
|
},
|
|
{
|
|
"entropy": 5.5127815246582035,
|
|
"epoch": 2.6691763425253994,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004289089013508528,
|
|
"loss": 5.088,
|
|
"mean_token_accuracy": 0.19840790927410126,
|
|
"num_tokens": 61057009.0,
|
|
"step": 29425
|
|
},
|
|
{
|
|
"entropy": 5.53412880897522,
|
|
"epoch": 2.669629898403483,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004288852975337308,
|
|
"loss": 5.2405,
|
|
"mean_token_accuracy": 0.18482281416654586,
|
|
"num_tokens": 61068514.0,
|
|
"step": 29430
|
|
},
|
|
{
|
|
"entropy": 5.45208158493042,
|
|
"epoch": 2.6700834542815675,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00042886169053422165,
|
|
"loss": 5.1296,
|
|
"mean_token_accuracy": 0.19873087704181672,
|
|
"num_tokens": 61078902.0,
|
|
"step": 29435
|
|
},
|
|
{
|
|
"entropy": 5.4396298885345455,
|
|
"epoch": 2.6705370101596517,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004288380803528135,
|
|
"loss": 5.1369,
|
|
"mean_token_accuracy": 0.20436131656169892,
|
|
"num_tokens": 61089216.0,
|
|
"step": 29440
|
|
},
|
|
{
|
|
"entropy": 5.410428667068482,
|
|
"epoch": 2.670990566037736,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00042881446698999465,
|
|
"loss": 5.0495,
|
|
"mean_token_accuracy": 0.2043750211596489,
|
|
"num_tokens": 61098470.0,
|
|
"step": 29445
|
|
},
|
|
{
|
|
"entropy": 5.561413335800171,
|
|
"epoch": 2.67144412191582,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004287908504462534,
|
|
"loss": 5.2589,
|
|
"mean_token_accuracy": 0.1977041780948639,
|
|
"num_tokens": 61108694.0,
|
|
"step": 29450
|
|
},
|
|
{
|
|
"entropy": 5.421489477157593,
|
|
"epoch": 2.671897677793904,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00042876723072207825,
|
|
"loss": 5.0922,
|
|
"mean_token_accuracy": 0.1999683126807213,
|
|
"num_tokens": 61119389.0,
|
|
"step": 29455
|
|
},
|
|
{
|
|
"entropy": 5.524545049667358,
|
|
"epoch": 2.6723512336719883,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00042874360781795757,
|
|
"loss": 5.1873,
|
|
"mean_token_accuracy": 0.18957899510860443,
|
|
"num_tokens": 61130491.0,
|
|
"step": 29460
|
|
},
|
|
{
|
|
"entropy": 5.4531055927276615,
|
|
"epoch": 2.6728047895500726,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00042871998173437987,
|
|
"loss": 5.1472,
|
|
"mean_token_accuracy": 0.20026929378509523,
|
|
"num_tokens": 61140404.0,
|
|
"step": 29465
|
|
},
|
|
{
|
|
"entropy": 5.491747951507568,
|
|
"epoch": 2.673258345428157,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00042869635247183373,
|
|
"loss": 5.2035,
|
|
"mean_token_accuracy": 0.19228211790323257,
|
|
"num_tokens": 61150777.0,
|
|
"step": 29470
|
|
},
|
|
{
|
|
"entropy": 5.426292896270752,
|
|
"epoch": 2.673711901306241,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00042867272003080793,
|
|
"loss": 5.1261,
|
|
"mean_token_accuracy": 0.19826802015304565,
|
|
"num_tokens": 61160685.0,
|
|
"step": 29475
|
|
},
|
|
{
|
|
"entropy": 5.4717916488647464,
|
|
"epoch": 2.674165457184325,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004286490844117911,
|
|
"loss": 5.1011,
|
|
"mean_token_accuracy": 0.19731123447418214,
|
|
"num_tokens": 61170553.0,
|
|
"step": 29480
|
|
},
|
|
{
|
|
"entropy": 5.513185787200928,
|
|
"epoch": 2.6746190130624092,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00042862544561527203,
|
|
"loss": 5.1468,
|
|
"mean_token_accuracy": 0.19720278531312943,
|
|
"num_tokens": 61181396.0,
|
|
"step": 29485
|
|
},
|
|
{
|
|
"entropy": 5.472494506835938,
|
|
"epoch": 2.6750725689404935,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004286018036417396,
|
|
"loss": 5.1338,
|
|
"mean_token_accuracy": 0.19679125249385834,
|
|
"num_tokens": 61192315.0,
|
|
"step": 29490
|
|
},
|
|
{
|
|
"entropy": 5.42399640083313,
|
|
"epoch": 2.6755261248185778,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00042857815849168277,
|
|
"loss": 5.0959,
|
|
"mean_token_accuracy": 0.2036660760641098,
|
|
"num_tokens": 61202719.0,
|
|
"step": 29495
|
|
},
|
|
{
|
|
"entropy": 5.3372564792633055,
|
|
"epoch": 2.6759796806966616,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004285545101655904,
|
|
"loss": 4.9893,
|
|
"mean_token_accuracy": 0.2064372941851616,
|
|
"num_tokens": 61212703.0,
|
|
"step": 29500
|
|
},
|
|
{
|
|
"entropy": 5.352444076538086,
|
|
"epoch": 2.676433236574746,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004285308586639517,
|
|
"loss": 4.9636,
|
|
"mean_token_accuracy": 0.21041134148836135,
|
|
"num_tokens": 61222406.0,
|
|
"step": 29505
|
|
},
|
|
{
|
|
"entropy": 5.423331785202026,
|
|
"epoch": 2.67688679245283,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00042850720398725575,
|
|
"loss": 5.2048,
|
|
"mean_token_accuracy": 0.1880118116736412,
|
|
"num_tokens": 61232758.0,
|
|
"step": 29510
|
|
},
|
|
{
|
|
"entropy": 5.434298181533814,
|
|
"epoch": 2.6773403483309144,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00042848354613599164,
|
|
"loss": 5.0767,
|
|
"mean_token_accuracy": 0.20453009456396104,
|
|
"num_tokens": 61243715.0,
|
|
"step": 29515
|
|
},
|
|
{
|
|
"entropy": 5.491742706298828,
|
|
"epoch": 2.6777939042089987,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00042845988511064863,
|
|
"loss": 5.1191,
|
|
"mean_token_accuracy": 0.19940157383680343,
|
|
"num_tokens": 61254669.0,
|
|
"step": 29520
|
|
},
|
|
{
|
|
"entropy": 5.422694110870362,
|
|
"epoch": 2.678247460087083,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00042843622091171625,
|
|
"loss": 5.1111,
|
|
"mean_token_accuracy": 0.19999384135007858,
|
|
"num_tokens": 61264377.0,
|
|
"step": 29525
|
|
},
|
|
{
|
|
"entropy": 5.421661996841431,
|
|
"epoch": 2.6787010159651667,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004284125535396836,
|
|
"loss": 5.1031,
|
|
"mean_token_accuracy": 0.19747277349233627,
|
|
"num_tokens": 61275348.0,
|
|
"step": 29530
|
|
},
|
|
{
|
|
"entropy": 5.371469879150391,
|
|
"epoch": 2.679154571843251,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00042838888299504024,
|
|
"loss": 4.9649,
|
|
"mean_token_accuracy": 0.21100204437971115,
|
|
"num_tokens": 61285579.0,
|
|
"step": 29535
|
|
},
|
|
{
|
|
"entropy": 5.420116519927978,
|
|
"epoch": 2.6796081277213353,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00042836520927827575,
|
|
"loss": 5.0587,
|
|
"mean_token_accuracy": 0.19959112256765366,
|
|
"num_tokens": 61296037.0,
|
|
"step": 29540
|
|
},
|
|
{
|
|
"entropy": 5.433517789840698,
|
|
"epoch": 2.6800616835994195,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004283415323898797,
|
|
"loss": 5.0468,
|
|
"mean_token_accuracy": 0.2106414720416069,
|
|
"num_tokens": 61305882.0,
|
|
"step": 29545
|
|
},
|
|
{
|
|
"entropy": 5.394411945343018,
|
|
"epoch": 2.6805152394775034,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00042831785233034156,
|
|
"loss": 5.0446,
|
|
"mean_token_accuracy": 0.20515130460262299,
|
|
"num_tokens": 61317117.0,
|
|
"step": 29550
|
|
},
|
|
{
|
|
"entropy": 5.428763437271118,
|
|
"epoch": 2.6809687953555876,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00042829416910015116,
|
|
"loss": 5.1505,
|
|
"mean_token_accuracy": 0.19401995241641998,
|
|
"num_tokens": 61328190.0,
|
|
"step": 29555
|
|
},
|
|
{
|
|
"entropy": 5.429900217056274,
|
|
"epoch": 2.681422351233672,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00042827048269979834,
|
|
"loss": 5.126,
|
|
"mean_token_accuracy": 0.19661581367254258,
|
|
"num_tokens": 61337978.0,
|
|
"step": 29560
|
|
},
|
|
{
|
|
"entropy": 5.506636381149292,
|
|
"epoch": 2.681875907111756,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004282467931297729,
|
|
"loss": 5.1754,
|
|
"mean_token_accuracy": 0.19216285794973373,
|
|
"num_tokens": 61348523.0,
|
|
"step": 29565
|
|
},
|
|
{
|
|
"entropy": 5.415856122970581,
|
|
"epoch": 2.6823294629898404,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004282231003905647,
|
|
"loss": 5.0349,
|
|
"mean_token_accuracy": 0.2028779223561287,
|
|
"num_tokens": 61359250.0,
|
|
"step": 29570
|
|
},
|
|
{
|
|
"entropy": 5.393287897109985,
|
|
"epoch": 2.6827830188679247,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00042819940448266376,
|
|
"loss": 5.0196,
|
|
"mean_token_accuracy": 0.20428380668163298,
|
|
"num_tokens": 61369999.0,
|
|
"step": 29575
|
|
},
|
|
{
|
|
"entropy": 5.474727439880371,
|
|
"epoch": 2.683236574746009,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00042817570540656003,
|
|
"loss": 5.1568,
|
|
"mean_token_accuracy": 0.1901353895664215,
|
|
"num_tokens": 61380279.0,
|
|
"step": 29580
|
|
},
|
|
{
|
|
"entropy": 5.394483757019043,
|
|
"epoch": 2.683690130624093,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004281520031627438,
|
|
"loss": 5.0984,
|
|
"mean_token_accuracy": 0.2060855507850647,
|
|
"num_tokens": 61389794.0,
|
|
"step": 29585
|
|
},
|
|
{
|
|
"entropy": 5.479899597167969,
|
|
"epoch": 2.684143686502177,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00042812829775170497,
|
|
"loss": 5.226,
|
|
"mean_token_accuracy": 0.1891067609190941,
|
|
"num_tokens": 61401136.0,
|
|
"step": 29590
|
|
},
|
|
{
|
|
"entropy": 5.46061143875122,
|
|
"epoch": 2.6845972423802613,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00042810458917393404,
|
|
"loss": 5.1691,
|
|
"mean_token_accuracy": 0.1951831951737404,
|
|
"num_tokens": 61412830.0,
|
|
"step": 29595
|
|
},
|
|
{
|
|
"entropy": 5.442211294174195,
|
|
"epoch": 2.6850507982583456,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004280808774299211,
|
|
"loss": 5.0508,
|
|
"mean_token_accuracy": 0.20600090622901918,
|
|
"num_tokens": 61422168.0,
|
|
"step": 29600
|
|
},
|
|
{
|
|
"entropy": 5.426320648193359,
|
|
"epoch": 2.6855043541364294,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00042805716252015665,
|
|
"loss": 5.0686,
|
|
"mean_token_accuracy": 0.2005813956260681,
|
|
"num_tokens": 61432471.0,
|
|
"step": 29605
|
|
},
|
|
{
|
|
"entropy": 5.449317884445191,
|
|
"epoch": 2.6859579100145137,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00042803344444513106,
|
|
"loss": 5.1001,
|
|
"mean_token_accuracy": 0.20341489762067794,
|
|
"num_tokens": 61443402.0,
|
|
"step": 29610
|
|
},
|
|
{
|
|
"entropy": 5.480668735504151,
|
|
"epoch": 2.686411465892598,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004280097232053349,
|
|
"loss": 5.0957,
|
|
"mean_token_accuracy": 0.19515273571014405,
|
|
"num_tokens": 61454465.0,
|
|
"step": 29615
|
|
},
|
|
{
|
|
"entropy": 5.408124208450317,
|
|
"epoch": 2.686865021770682,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004279859988012586,
|
|
"loss": 5.109,
|
|
"mean_token_accuracy": 0.1975116327404976,
|
|
"num_tokens": 61464671.0,
|
|
"step": 29620
|
|
},
|
|
{
|
|
"entropy": 5.403388738632202,
|
|
"epoch": 2.6873185776487665,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004279622712333929,
|
|
"loss": 5.0777,
|
|
"mean_token_accuracy": 0.20575159043073654,
|
|
"num_tokens": 61474940.0,
|
|
"step": 29625
|
|
},
|
|
{
|
|
"entropy": 5.464933300018311,
|
|
"epoch": 2.6877721335268507,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004279385405022284,
|
|
"loss": 5.1312,
|
|
"mean_token_accuracy": 0.19602077901363374,
|
|
"num_tokens": 61485240.0,
|
|
"step": 29630
|
|
},
|
|
{
|
|
"entropy": 5.429579639434815,
|
|
"epoch": 2.6882256894049346,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000427914806608256,
|
|
"loss": 5.0732,
|
|
"mean_token_accuracy": 0.19976018518209457,
|
|
"num_tokens": 61495382.0,
|
|
"step": 29635
|
|
},
|
|
{
|
|
"entropy": 5.368665075302124,
|
|
"epoch": 2.688679245283019,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004278910695519663,
|
|
"loss": 5.0136,
|
|
"mean_token_accuracy": 0.20676134079694747,
|
|
"num_tokens": 61505372.0,
|
|
"step": 29640
|
|
},
|
|
{
|
|
"entropy": 5.465173625946045,
|
|
"epoch": 2.689132801161103,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00042786732933385046,
|
|
"loss": 5.1214,
|
|
"mean_token_accuracy": 0.19888957291841508,
|
|
"num_tokens": 61516039.0,
|
|
"step": 29645
|
|
},
|
|
{
|
|
"entropy": 5.442552137374878,
|
|
"epoch": 2.6895863570391874,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004278435859543992,
|
|
"loss": 5.1475,
|
|
"mean_token_accuracy": 0.19675657600164415,
|
|
"num_tokens": 61525435.0,
|
|
"step": 29650
|
|
},
|
|
{
|
|
"entropy": 5.453938579559326,
|
|
"epoch": 2.690039912917271,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004278198394141037,
|
|
"loss": 5.1113,
|
|
"mean_token_accuracy": 0.19307331144809722,
|
|
"num_tokens": 61534714.0,
|
|
"step": 29655
|
|
},
|
|
{
|
|
"entropy": 5.486738395690918,
|
|
"epoch": 2.6904934687953554,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00042779608971345496,
|
|
"loss": 5.2526,
|
|
"mean_token_accuracy": 0.18731694519519806,
|
|
"num_tokens": 61545841.0,
|
|
"step": 29660
|
|
},
|
|
{
|
|
"entropy": 5.3851464748382565,
|
|
"epoch": 2.6909470246734397,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00042777233685294407,
|
|
"loss": 5.0188,
|
|
"mean_token_accuracy": 0.20898500382900237,
|
|
"num_tokens": 61555355.0,
|
|
"step": 29665
|
|
},
|
|
{
|
|
"entropy": 5.459988737106324,
|
|
"epoch": 2.691400580551524,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00042774858083306246,
|
|
"loss": 5.1329,
|
|
"mean_token_accuracy": 0.1962617576122284,
|
|
"num_tokens": 61565474.0,
|
|
"step": 29670
|
|
},
|
|
{
|
|
"entropy": 5.441480207443237,
|
|
"epoch": 2.6918541364296082,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00042772482165430117,
|
|
"loss": 5.033,
|
|
"mean_token_accuracy": 0.20853874683380128,
|
|
"num_tokens": 61575631.0,
|
|
"step": 29675
|
|
},
|
|
{
|
|
"entropy": 5.390586948394775,
|
|
"epoch": 2.6923076923076925,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00042770105931715167,
|
|
"loss": 5.0908,
|
|
"mean_token_accuracy": 0.20003880560398102,
|
|
"num_tokens": 61586398.0,
|
|
"step": 29680
|
|
},
|
|
{
|
|
"entropy": 5.389509582519532,
|
|
"epoch": 2.6927612481857763,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004276772938221054,
|
|
"loss": 5.0044,
|
|
"mean_token_accuracy": 0.2063089579343796,
|
|
"num_tokens": 61596630.0,
|
|
"step": 29685
|
|
},
|
|
{
|
|
"entropy": 5.4452183723449705,
|
|
"epoch": 2.6932148040638606,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004276535251696537,
|
|
"loss": 5.121,
|
|
"mean_token_accuracy": 0.2050401121377945,
|
|
"num_tokens": 61605965.0,
|
|
"step": 29690
|
|
},
|
|
{
|
|
"entropy": 5.472912216186524,
|
|
"epoch": 2.693668359941945,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004276297533602883,
|
|
"loss": 5.1882,
|
|
"mean_token_accuracy": 0.19321861863136292,
|
|
"num_tokens": 61616973.0,
|
|
"step": 29695
|
|
},
|
|
{
|
|
"entropy": 5.5055530071258545,
|
|
"epoch": 2.694121915820029,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00042760597839450057,
|
|
"loss": 5.1487,
|
|
"mean_token_accuracy": 0.19401031881570815,
|
|
"num_tokens": 61627420.0,
|
|
"step": 29700
|
|
},
|
|
{
|
|
"entropy": 5.420056295394898,
|
|
"epoch": 2.694575471698113,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004275822002727824,
|
|
"loss": 5.11,
|
|
"mean_token_accuracy": 0.19846609532833098,
|
|
"num_tokens": 61638315.0,
|
|
"step": 29705
|
|
},
|
|
{
|
|
"entropy": 5.384257841110229,
|
|
"epoch": 2.6950290275761972,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00042755841899562544,
|
|
"loss": 5.1053,
|
|
"mean_token_accuracy": 0.20378195643424987,
|
|
"num_tokens": 61649294.0,
|
|
"step": 29710
|
|
},
|
|
{
|
|
"entropy": 5.501961898803711,
|
|
"epoch": 2.6954825834542815,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00042753463456352155,
|
|
"loss": 5.1426,
|
|
"mean_token_accuracy": 0.193469800055027,
|
|
"num_tokens": 61660312.0,
|
|
"step": 29715
|
|
},
|
|
{
|
|
"entropy": 5.457520580291748,
|
|
"epoch": 2.6959361393323658,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004275108469769625,
|
|
"loss": 5.1088,
|
|
"mean_token_accuracy": 0.20225777626037597,
|
|
"num_tokens": 61670539.0,
|
|
"step": 29720
|
|
},
|
|
{
|
|
"entropy": 5.437741041183472,
|
|
"epoch": 2.69638969521045,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00042748705623644025,
|
|
"loss": 5.0288,
|
|
"mean_token_accuracy": 0.20634331405162812,
|
|
"num_tokens": 61679613.0,
|
|
"step": 29725
|
|
},
|
|
{
|
|
"entropy": 5.466332006454468,
|
|
"epoch": 2.6968432510885343,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004274632623424468,
|
|
"loss": 5.1261,
|
|
"mean_token_accuracy": 0.1943456217646599,
|
|
"num_tokens": 61689714.0,
|
|
"step": 29730
|
|
},
|
|
{
|
|
"entropy": 5.460966539382935,
|
|
"epoch": 2.6972968069666186,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00042743946529547435,
|
|
"loss": 5.1773,
|
|
"mean_token_accuracy": 0.1927887335419655,
|
|
"num_tokens": 61700701.0,
|
|
"step": 29735
|
|
},
|
|
{
|
|
"entropy": 5.465850019454956,
|
|
"epoch": 2.6977503628447024,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004274156650960148,
|
|
"loss": 5.1549,
|
|
"mean_token_accuracy": 0.19566457122564315,
|
|
"num_tokens": 61711403.0,
|
|
"step": 29740
|
|
},
|
|
{
|
|
"entropy": 5.365576601028442,
|
|
"epoch": 2.6982039187227866,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004273918617445605,
|
|
"loss": 4.9562,
|
|
"mean_token_accuracy": 0.20682112127542496,
|
|
"num_tokens": 61721787.0,
|
|
"step": 29745
|
|
},
|
|
{
|
|
"entropy": 5.476622438430786,
|
|
"epoch": 2.698657474600871,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00042736805524160363,
|
|
"loss": 5.2163,
|
|
"mean_token_accuracy": 0.19301782101392745,
|
|
"num_tokens": 61732702.0,
|
|
"step": 29750
|
|
},
|
|
{
|
|
"entropy": 5.419493198394775,
|
|
"epoch": 2.6991110304789547,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00042734424558763656,
|
|
"loss": 5.1136,
|
|
"mean_token_accuracy": 0.2004708006978035,
|
|
"num_tokens": 61743477.0,
|
|
"step": 29755
|
|
},
|
|
{
|
|
"entropy": 5.504614782333374,
|
|
"epoch": 2.699564586357039,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004273204327831516,
|
|
"loss": 5.1779,
|
|
"mean_token_accuracy": 0.1907023161649704,
|
|
"num_tokens": 61753620.0,
|
|
"step": 29760
|
|
},
|
|
{
|
|
"entropy": 5.470947551727295,
|
|
"epoch": 2.7000181422351233,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004272966168286414,
|
|
"loss": 5.0709,
|
|
"mean_token_accuracy": 0.2031553253531456,
|
|
"num_tokens": 61763678.0,
|
|
"step": 29765
|
|
},
|
|
{
|
|
"entropy": 5.45763463973999,
|
|
"epoch": 2.7004716981132075,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00042727279772459837,
|
|
"loss": 5.1659,
|
|
"mean_token_accuracy": 0.1975630357861519,
|
|
"num_tokens": 61774419.0,
|
|
"step": 29770
|
|
},
|
|
{
|
|
"entropy": 5.536614894866943,
|
|
"epoch": 2.700925253991292,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000427248975471515,
|
|
"loss": 5.1665,
|
|
"mean_token_accuracy": 0.19502773731946946,
|
|
"num_tokens": 61785546.0,
|
|
"step": 29775
|
|
},
|
|
{
|
|
"entropy": 5.518295669555664,
|
|
"epoch": 2.701378809869376,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00042722515006988397,
|
|
"loss": 5.0715,
|
|
"mean_token_accuracy": 0.20008080899715425,
|
|
"num_tokens": 61795846.0,
|
|
"step": 29780
|
|
},
|
|
{
|
|
"entropy": 5.388440132141113,
|
|
"epoch": 2.7018323657474603,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004272013215201982,
|
|
"loss": 5.1418,
|
|
"mean_token_accuracy": 0.19375985562801362,
|
|
"num_tokens": 61806440.0,
|
|
"step": 29785
|
|
},
|
|
{
|
|
"entropy": 5.3748719692230225,
|
|
"epoch": 2.702285921625544,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00042717748982295015,
|
|
"loss": 5.0767,
|
|
"mean_token_accuracy": 0.20224415361881257,
|
|
"num_tokens": 61815371.0,
|
|
"step": 29790
|
|
},
|
|
{
|
|
"entropy": 5.466035461425781,
|
|
"epoch": 2.7027394775036284,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004271536549786329,
|
|
"loss": 5.0527,
|
|
"mean_token_accuracy": 0.20649864822626113,
|
|
"num_tokens": 61825225.0,
|
|
"step": 29795
|
|
},
|
|
{
|
|
"entropy": 5.431989669799805,
|
|
"epoch": 2.7031930333817127,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004271298169877393,
|
|
"loss": 5.132,
|
|
"mean_token_accuracy": 0.19877117574214936,
|
|
"num_tokens": 61836705.0,
|
|
"step": 29800
|
|
},
|
|
{
|
|
"entropy": 5.404431247711182,
|
|
"epoch": 2.703646589259797,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004271059758507624,
|
|
"loss": 5.0931,
|
|
"mean_token_accuracy": 0.201427660882473,
|
|
"num_tokens": 61847082.0,
|
|
"step": 29805
|
|
},
|
|
{
|
|
"entropy": 5.436115312576294,
|
|
"epoch": 2.7041001451378808,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00042708213156819505,
|
|
"loss": 5.1141,
|
|
"mean_token_accuracy": 0.19561623334884642,
|
|
"num_tokens": 61857130.0,
|
|
"step": 29810
|
|
},
|
|
{
|
|
"entropy": 5.535294151306152,
|
|
"epoch": 2.704553701015965,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004270582841405305,
|
|
"loss": 5.1907,
|
|
"mean_token_accuracy": 0.18731946647167205,
|
|
"num_tokens": 61866796.0,
|
|
"step": 29815
|
|
},
|
|
{
|
|
"entropy": 5.508513164520264,
|
|
"epoch": 2.7050072568940493,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004270344335682618,
|
|
"loss": 5.1211,
|
|
"mean_token_accuracy": 0.19442027807235718,
|
|
"num_tokens": 61876356.0,
|
|
"step": 29820
|
|
},
|
|
{
|
|
"entropy": 5.412174701690674,
|
|
"epoch": 2.7054608127721336,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00042701057985188235,
|
|
"loss": 5.1428,
|
|
"mean_token_accuracy": 0.19170159846544266,
|
|
"num_tokens": 61887374.0,
|
|
"step": 29825
|
|
},
|
|
{
|
|
"entropy": 5.486065340042114,
|
|
"epoch": 2.705914368650218,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004269867229918854,
|
|
"loss": 5.1842,
|
|
"mean_token_accuracy": 0.19617659747600555,
|
|
"num_tokens": 61897376.0,
|
|
"step": 29830
|
|
},
|
|
{
|
|
"entropy": 5.541559314727783,
|
|
"epoch": 2.706367924528302,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00042696286298876424,
|
|
"loss": 5.2094,
|
|
"mean_token_accuracy": 0.18819091767072677,
|
|
"num_tokens": 61908212.0,
|
|
"step": 29835
|
|
},
|
|
{
|
|
"entropy": 5.495310068130493,
|
|
"epoch": 2.706821480406386,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004269389998430124,
|
|
"loss": 5.2115,
|
|
"mean_token_accuracy": 0.18687502443790435,
|
|
"num_tokens": 61920699.0,
|
|
"step": 29840
|
|
},
|
|
{
|
|
"entropy": 5.463731145858764,
|
|
"epoch": 2.70727503628447,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004269151335551233,
|
|
"loss": 5.1268,
|
|
"mean_token_accuracy": 0.1919954761862755,
|
|
"num_tokens": 61931556.0,
|
|
"step": 29845
|
|
},
|
|
{
|
|
"entropy": 5.538934707641602,
|
|
"epoch": 2.7077285921625545,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004268912641255905,
|
|
"loss": 5.2454,
|
|
"mean_token_accuracy": 0.1962532803416252,
|
|
"num_tokens": 61941483.0,
|
|
"step": 29850
|
|
},
|
|
{
|
|
"entropy": 5.459211778640747,
|
|
"epoch": 2.7081821480406387,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00042686739155490763,
|
|
"loss": 5.073,
|
|
"mean_token_accuracy": 0.20349819213151932,
|
|
"num_tokens": 61951262.0,
|
|
"step": 29855
|
|
},
|
|
{
|
|
"entropy": 5.516035079956055,
|
|
"epoch": 2.7086357039187225,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004268435158435684,
|
|
"loss": 5.1769,
|
|
"mean_token_accuracy": 0.19452525824308395,
|
|
"num_tokens": 61962423.0,
|
|
"step": 29860
|
|
},
|
|
{
|
|
"entropy": 5.553733062744141,
|
|
"epoch": 2.709089259796807,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00042681963699206667,
|
|
"loss": 5.2412,
|
|
"mean_token_accuracy": 0.1881875663995743,
|
|
"num_tokens": 61973276.0,
|
|
"step": 29865
|
|
},
|
|
{
|
|
"entropy": 5.432758903503418,
|
|
"epoch": 2.709542815674891,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00042679575500089605,
|
|
"loss": 5.0686,
|
|
"mean_token_accuracy": 0.1998469963669777,
|
|
"num_tokens": 61984369.0,
|
|
"step": 29870
|
|
},
|
|
{
|
|
"entropy": 5.388268899917603,
|
|
"epoch": 2.7099963715529753,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004267718698705506,
|
|
"loss": 5.0404,
|
|
"mean_token_accuracy": 0.1954925388097763,
|
|
"num_tokens": 61994224.0,
|
|
"step": 29875
|
|
},
|
|
{
|
|
"entropy": 5.427571725845337,
|
|
"epoch": 2.7104499274310596,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004267479816015242,
|
|
"loss": 5.1253,
|
|
"mean_token_accuracy": 0.20167887955904007,
|
|
"num_tokens": 62004546.0,
|
|
"step": 29880
|
|
},
|
|
{
|
|
"entropy": 5.505898475646973,
|
|
"epoch": 2.710903483309144,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004267240901943109,
|
|
"loss": 5.1126,
|
|
"mean_token_accuracy": 0.20522039979696274,
|
|
"num_tokens": 62013924.0,
|
|
"step": 29885
|
|
},
|
|
{
|
|
"entropy": 5.446325159072876,
|
|
"epoch": 2.7113570391872277,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00042670019564940474,
|
|
"loss": 5.1022,
|
|
"mean_token_accuracy": 0.19731968492269517,
|
|
"num_tokens": 62026150.0,
|
|
"step": 29890
|
|
},
|
|
{
|
|
"entropy": 5.443903875350952,
|
|
"epoch": 2.711810595065312,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004266762979672998,
|
|
"loss": 5.1179,
|
|
"mean_token_accuracy": 0.19880579710006713,
|
|
"num_tokens": 62036203.0,
|
|
"step": 29895
|
|
},
|
|
{
|
|
"entropy": 5.455031681060791,
|
|
"epoch": 2.7122641509433962,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00042665239714849044,
|
|
"loss": 5.1099,
|
|
"mean_token_accuracy": 0.19513218253850936,
|
|
"num_tokens": 62046961.0,
|
|
"step": 29900
|
|
},
|
|
{
|
|
"entropy": 5.394465684890747,
|
|
"epoch": 2.7127177068214805,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00042662849319347073,
|
|
"loss": 5.076,
|
|
"mean_token_accuracy": 0.198934842646122,
|
|
"num_tokens": 62057365.0,
|
|
"step": 29905
|
|
},
|
|
{
|
|
"entropy": 5.4549719333648685,
|
|
"epoch": 2.7131712626995643,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00042660458610273527,
|
|
"loss": 5.0578,
|
|
"mean_token_accuracy": 0.19760850369930266,
|
|
"num_tokens": 62067934.0,
|
|
"step": 29910
|
|
},
|
|
{
|
|
"entropy": 5.508092260360717,
|
|
"epoch": 2.7136248185776486,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004265806758767783,
|
|
"loss": 5.1749,
|
|
"mean_token_accuracy": 0.1933584615588188,
|
|
"num_tokens": 62077203.0,
|
|
"step": 29915
|
|
},
|
|
{
|
|
"entropy": 5.500318765640259,
|
|
"epoch": 2.714078374455733,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00042655676251609435,
|
|
"loss": 5.098,
|
|
"mean_token_accuracy": 0.19901293963193895,
|
|
"num_tokens": 62087262.0,
|
|
"step": 29920
|
|
},
|
|
{
|
|
"entropy": 5.425823783874511,
|
|
"epoch": 2.714531930333817,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00042653284602117795,
|
|
"loss": 5.1169,
|
|
"mean_token_accuracy": 0.19736236035823823,
|
|
"num_tokens": 62097931.0,
|
|
"step": 29925
|
|
},
|
|
{
|
|
"entropy": 5.439107751846313,
|
|
"epoch": 2.7149854862119014,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004265089263925236,
|
|
"loss": 5.1983,
|
|
"mean_token_accuracy": 0.1937421292066574,
|
|
"num_tokens": 62109478.0,
|
|
"step": 29930
|
|
},
|
|
{
|
|
"entropy": 5.543734931945801,
|
|
"epoch": 2.7154390420899857,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000426485003630626,
|
|
"loss": 5.1935,
|
|
"mean_token_accuracy": 0.19167068600654602,
|
|
"num_tokens": 62120735.0,
|
|
"step": 29935
|
|
},
|
|
{
|
|
"entropy": 5.475822305679321,
|
|
"epoch": 2.71589259796807,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004264610777359801,
|
|
"loss": 5.1002,
|
|
"mean_token_accuracy": 0.1968720719218254,
|
|
"num_tokens": 62130950.0,
|
|
"step": 29940
|
|
},
|
|
{
|
|
"entropy": 5.429284334182739,
|
|
"epoch": 2.7163461538461537,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004264371487090804,
|
|
"loss": 5.1132,
|
|
"mean_token_accuracy": 0.19628608226776123,
|
|
"num_tokens": 62141351.0,
|
|
"step": 29945
|
|
},
|
|
{
|
|
"entropy": 5.350387191772461,
|
|
"epoch": 2.716799709724238,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00042641321655042185,
|
|
"loss": 5.045,
|
|
"mean_token_accuracy": 0.20157115459442138,
|
|
"num_tokens": 62151388.0,
|
|
"step": 29950
|
|
},
|
|
{
|
|
"entropy": 5.502964019775391,
|
|
"epoch": 2.7172532656023223,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004263892812604995,
|
|
"loss": 5.2551,
|
|
"mean_token_accuracy": 0.18981505185365677,
|
|
"num_tokens": 62162809.0,
|
|
"step": 29955
|
|
},
|
|
{
|
|
"entropy": 5.476113224029541,
|
|
"epoch": 2.7177068214804065,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00042636534283980814,
|
|
"loss": 5.0991,
|
|
"mean_token_accuracy": 0.20077234357595444,
|
|
"num_tokens": 62172738.0,
|
|
"step": 29960
|
|
},
|
|
{
|
|
"entropy": 5.507036972045898,
|
|
"epoch": 2.7181603773584904,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000426341401288843,
|
|
"loss": 5.2489,
|
|
"mean_token_accuracy": 0.190889111161232,
|
|
"num_tokens": 62182508.0,
|
|
"step": 29965
|
|
},
|
|
{
|
|
"entropy": 5.457352638244629,
|
|
"epoch": 2.7186139332365746,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00042631745660809905,
|
|
"loss": 5.2019,
|
|
"mean_token_accuracy": 0.18645721971988677,
|
|
"num_tokens": 62192873.0,
|
|
"step": 29970
|
|
},
|
|
{
|
|
"entropy": 5.553123664855957,
|
|
"epoch": 2.719067489114659,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00042629350879807155,
|
|
"loss": 5.2393,
|
|
"mean_token_accuracy": 0.18771189898252488,
|
|
"num_tokens": 62204727.0,
|
|
"step": 29975
|
|
},
|
|
{
|
|
"entropy": 5.511037445068359,
|
|
"epoch": 2.719521044992743,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00042626955785925576,
|
|
"loss": 5.1019,
|
|
"mean_token_accuracy": 0.19439011961221694,
|
|
"num_tokens": 62214268.0,
|
|
"step": 29980
|
|
},
|
|
{
|
|
"entropy": 5.492970943450928,
|
|
"epoch": 2.7199746008708274,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00042624560379214693,
|
|
"loss": 5.1588,
|
|
"mean_token_accuracy": 0.19690617322921752,
|
|
"num_tokens": 62224756.0,
|
|
"step": 29985
|
|
},
|
|
{
|
|
"entropy": 5.470497703552246,
|
|
"epoch": 2.7204281567489117,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004262216465972405,
|
|
"loss": 5.1083,
|
|
"mean_token_accuracy": 0.19380614459514617,
|
|
"num_tokens": 62234065.0,
|
|
"step": 29990
|
|
},
|
|
{
|
|
"entropy": 5.513600540161133,
|
|
"epoch": 2.7208817126269955,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004261976862750318,
|
|
"loss": 5.132,
|
|
"mean_token_accuracy": 0.19974490702152253,
|
|
"num_tokens": 62243732.0,
|
|
"step": 29995
|
|
},
|
|
{
|
|
"entropy": 5.509850215911865,
|
|
"epoch": 2.72133526850508,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004261737228260165,
|
|
"loss": 5.1417,
|
|
"mean_token_accuracy": 0.19822950214147567,
|
|
"num_tokens": 62253461.0,
|
|
"step": 30000
|
|
},
|
|
{
|
|
"epoch": 2.72133526850508,
|
|
"eval_entropy": 5.2264057917832245,
|
|
"eval_loss": 5.179539203643799,
|
|
"eval_mean_token_accuracy": 0.20245886086001655,
|
|
"eval_num_tokens": 62253461.0,
|
|
"eval_runtime": 26.5611,
|
|
"eval_samples_per_second": 1331.271,
|
|
"eval_steps_per_second": 166.409,
|
|
"step": 30000
|
|
},
|
|
{
|
|
"entropy": 5.483057880401612,
|
|
"epoch": 2.721788824383164,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004261497562506901,
|
|
"loss": 5.1671,
|
|
"mean_token_accuracy": 0.19555775076150894,
|
|
"num_tokens": 62263830.0,
|
|
"step": 30005
|
|
},
|
|
{
|
|
"entropy": 5.419095993041992,
|
|
"epoch": 2.7222423802612483,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004261257865495483,
|
|
"loss": 5.0661,
|
|
"mean_token_accuracy": 0.20372154116630553,
|
|
"num_tokens": 62274383.0,
|
|
"step": 30010
|
|
},
|
|
{
|
|
"entropy": 5.539979648590088,
|
|
"epoch": 2.722695936139332,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004261018137230865,
|
|
"loss": 5.2636,
|
|
"mean_token_accuracy": 0.1800091326236725,
|
|
"num_tokens": 62286476.0,
|
|
"step": 30015
|
|
},
|
|
{
|
|
"entropy": 5.568504714965821,
|
|
"epoch": 2.7231494920174164,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00042607783777180085,
|
|
"loss": 5.1473,
|
|
"mean_token_accuracy": 0.1972183719277382,
|
|
"num_tokens": 62296192.0,
|
|
"step": 30020
|
|
},
|
|
{
|
|
"entropy": 5.426519966125488,
|
|
"epoch": 2.7236030478955007,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00042605385869618693,
|
|
"loss": 5.0612,
|
|
"mean_token_accuracy": 0.20651172250509262,
|
|
"num_tokens": 62305300.0,
|
|
"step": 30025
|
|
},
|
|
{
|
|
"entropy": 5.4594536304473875,
|
|
"epoch": 2.724056603773585,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004260298764967408,
|
|
"loss": 5.1206,
|
|
"mean_token_accuracy": 0.1968049705028534,
|
|
"num_tokens": 62316802.0,
|
|
"step": 30030
|
|
},
|
|
{
|
|
"entropy": 5.397939586639405,
|
|
"epoch": 2.724510159651669,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004260058911739583,
|
|
"loss": 5.0982,
|
|
"mean_token_accuracy": 0.197990320622921,
|
|
"num_tokens": 62326444.0,
|
|
"step": 30035
|
|
},
|
|
{
|
|
"entropy": 5.472284412384033,
|
|
"epoch": 2.7249637155297535,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00042598190272833547,
|
|
"loss": 5.0419,
|
|
"mean_token_accuracy": 0.20364526361227037,
|
|
"num_tokens": 62336872.0,
|
|
"step": 30040
|
|
},
|
|
{
|
|
"entropy": 5.352237892150879,
|
|
"epoch": 2.7254172714078373,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004259579111603685,
|
|
"loss": 4.9855,
|
|
"mean_token_accuracy": 0.20215152204036713,
|
|
"num_tokens": 62346771.0,
|
|
"step": 30045
|
|
},
|
|
{
|
|
"entropy": 5.442007637023925,
|
|
"epoch": 2.7258708272859216,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00042593391647055334,
|
|
"loss": 5.1295,
|
|
"mean_token_accuracy": 0.1981871619820595,
|
|
"num_tokens": 62357503.0,
|
|
"step": 30050
|
|
},
|
|
{
|
|
"entropy": 5.409018468856812,
|
|
"epoch": 2.726324383164006,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004259099186593864,
|
|
"loss": 5.0042,
|
|
"mean_token_accuracy": 0.20614733248949052,
|
|
"num_tokens": 62367664.0,
|
|
"step": 30055
|
|
},
|
|
{
|
|
"entropy": 5.445386600494385,
|
|
"epoch": 2.72677793904209,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004258859177273639,
|
|
"loss": 5.069,
|
|
"mean_token_accuracy": 0.19768042862415314,
|
|
"num_tokens": 62376924.0,
|
|
"step": 30060
|
|
},
|
|
{
|
|
"entropy": 5.32843246459961,
|
|
"epoch": 2.727231494920174,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004258619136749821,
|
|
"loss": 4.995,
|
|
"mean_token_accuracy": 0.20146752148866653,
|
|
"num_tokens": 62387529.0,
|
|
"step": 30065
|
|
},
|
|
{
|
|
"entropy": 5.409206104278565,
|
|
"epoch": 2.727685050798258,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004258379065027375,
|
|
"loss": 5.0846,
|
|
"mean_token_accuracy": 0.19625200629234313,
|
|
"num_tokens": 62397833.0,
|
|
"step": 30070
|
|
},
|
|
{
|
|
"entropy": 5.552338552474976,
|
|
"epoch": 2.7281386066763424,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004258138962111266,
|
|
"loss": 5.1606,
|
|
"mean_token_accuracy": 0.19295165836811065,
|
|
"num_tokens": 62409022.0,
|
|
"step": 30075
|
|
},
|
|
{
|
|
"entropy": 5.420463895797729,
|
|
"epoch": 2.7285921625544267,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004257898828006459,
|
|
"loss": 5.1257,
|
|
"mean_token_accuracy": 0.18937184512615204,
|
|
"num_tokens": 62419105.0,
|
|
"step": 30080
|
|
},
|
|
{
|
|
"entropy": 5.4217345237731935,
|
|
"epoch": 2.729045718432511,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004257658662717919,
|
|
"loss": 5.1199,
|
|
"mean_token_accuracy": 0.20195865929126738,
|
|
"num_tokens": 62428371.0,
|
|
"step": 30085
|
|
},
|
|
{
|
|
"entropy": 5.493077516555786,
|
|
"epoch": 2.7294992743105952,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004257418466250615,
|
|
"loss": 5.0777,
|
|
"mean_token_accuracy": 0.2003744900226593,
|
|
"num_tokens": 62439301.0,
|
|
"step": 30090
|
|
},
|
|
{
|
|
"entropy": 5.465613269805909,
|
|
"epoch": 2.7299528301886795,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00042571782386095124,
|
|
"loss": 5.0646,
|
|
"mean_token_accuracy": 0.19722287952899933,
|
|
"num_tokens": 62449450.0,
|
|
"step": 30095
|
|
},
|
|
{
|
|
"entropy": 5.452042579650879,
|
|
"epoch": 2.7304063860667633,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.00042569379797995793,
|
|
"loss": 5.0958,
|
|
"mean_token_accuracy": 0.19497155249118805,
|
|
"num_tokens": 62461051.0,
|
|
"step": 30100
|
|
},
|
|
{
|
|
"entropy": 5.435441207885742,
|
|
"epoch": 2.7308599419448476,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004256697689825785,
|
|
"loss": 5.0368,
|
|
"mean_token_accuracy": 0.20348265022039413,
|
|
"num_tokens": 62471755.0,
|
|
"step": 30105
|
|
},
|
|
{
|
|
"entropy": 5.36994252204895,
|
|
"epoch": 2.731313497822932,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00042564573686930987,
|
|
"loss": 5.0812,
|
|
"mean_token_accuracy": 0.19870873987674714,
|
|
"num_tokens": 62482060.0,
|
|
"step": 30110
|
|
},
|
|
{
|
|
"entropy": 5.378240728378296,
|
|
"epoch": 2.7317670537010157,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000425621701640649,
|
|
"loss": 5.1113,
|
|
"mean_token_accuracy": 0.19728308022022248,
|
|
"num_tokens": 62493735.0,
|
|
"step": 30115
|
|
},
|
|
{
|
|
"entropy": 5.486940860748291,
|
|
"epoch": 2.7322206095791,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000425597663297093,
|
|
"loss": 5.1427,
|
|
"mean_token_accuracy": 0.1935557931661606,
|
|
"num_tokens": 62504582.0,
|
|
"step": 30120
|
|
},
|
|
{
|
|
"entropy": 5.4579860210418705,
|
|
"epoch": 2.7326741654571842,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004255736218391389,
|
|
"loss": 5.0809,
|
|
"mean_token_accuracy": 0.1913334310054779,
|
|
"num_tokens": 62516665.0,
|
|
"step": 30125
|
|
},
|
|
{
|
|
"entropy": 5.440260601043701,
|
|
"epoch": 2.7331277213352685,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00042554957726728394,
|
|
"loss": 5.1203,
|
|
"mean_token_accuracy": 0.19841173887252808,
|
|
"num_tokens": 62527745.0,
|
|
"step": 30130
|
|
},
|
|
{
|
|
"entropy": 5.425635766983032,
|
|
"epoch": 2.7335812772133528,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004255255295820253,
|
|
"loss": 5.0835,
|
|
"mean_token_accuracy": 0.20229580551385878,
|
|
"num_tokens": 62538622.0,
|
|
"step": 30135
|
|
},
|
|
{
|
|
"entropy": 5.443960332870484,
|
|
"epoch": 2.734034833091437,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00042550147878386044,
|
|
"loss": 5.0976,
|
|
"mean_token_accuracy": 0.20214707851409913,
|
|
"num_tokens": 62548302.0,
|
|
"step": 30140
|
|
},
|
|
{
|
|
"entropy": 5.39757776260376,
|
|
"epoch": 2.7344883889695213,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004254774248732867,
|
|
"loss": 5.0031,
|
|
"mean_token_accuracy": 0.20783760845661164,
|
|
"num_tokens": 62557150.0,
|
|
"step": 30145
|
|
},
|
|
{
|
|
"entropy": 5.557438611984253,
|
|
"epoch": 2.734941944847605,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00042545336785080126,
|
|
"loss": 5.3048,
|
|
"mean_token_accuracy": 0.18536362498998643,
|
|
"num_tokens": 62568291.0,
|
|
"step": 30150
|
|
},
|
|
{
|
|
"entropy": 5.460798263549805,
|
|
"epoch": 2.7353955007256894,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000425429307716902,
|
|
"loss": 5.1038,
|
|
"mean_token_accuracy": 0.19929360300302507,
|
|
"num_tokens": 62579351.0,
|
|
"step": 30155
|
|
},
|
|
{
|
|
"entropy": 5.368372058868408,
|
|
"epoch": 2.7358490566037736,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00042540524447208625,
|
|
"loss": 4.9667,
|
|
"mean_token_accuracy": 0.20723361372947693,
|
|
"num_tokens": 62588614.0,
|
|
"step": 30160
|
|
},
|
|
{
|
|
"entropy": 5.446892166137696,
|
|
"epoch": 2.736302612481858,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00042538117811685174,
|
|
"loss": 5.1161,
|
|
"mean_token_accuracy": 0.19642314612865447,
|
|
"num_tokens": 62598844.0,
|
|
"step": 30165
|
|
},
|
|
{
|
|
"entropy": 5.469114589691162,
|
|
"epoch": 2.7367561683599417,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00042535710865169616,
|
|
"loss": 5.1405,
|
|
"mean_token_accuracy": 0.19257161319255828,
|
|
"num_tokens": 62608722.0,
|
|
"step": 30170
|
|
},
|
|
{
|
|
"entropy": 5.442769002914429,
|
|
"epoch": 2.737209724238026,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004253330360771173,
|
|
"loss": 5.0322,
|
|
"mean_token_accuracy": 0.19901881515979766,
|
|
"num_tokens": 62618712.0,
|
|
"step": 30175
|
|
},
|
|
{
|
|
"entropy": 5.492716455459595,
|
|
"epoch": 2.7376632801161103,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00042530896039361284,
|
|
"loss": 5.1928,
|
|
"mean_token_accuracy": 0.18629237711429597,
|
|
"num_tokens": 62629329.0,
|
|
"step": 30180
|
|
},
|
|
{
|
|
"entropy": 5.513123083114624,
|
|
"epoch": 2.7381168359941945,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00042528488160168077,
|
|
"loss": 5.1469,
|
|
"mean_token_accuracy": 0.19257192462682723,
|
|
"num_tokens": 62639644.0,
|
|
"step": 30185
|
|
},
|
|
{
|
|
"entropy": 5.51532096862793,
|
|
"epoch": 2.738570391872279,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00042526079970181915,
|
|
"loss": 5.1805,
|
|
"mean_token_accuracy": 0.18717548251152039,
|
|
"num_tokens": 62650979.0,
|
|
"step": 30190
|
|
},
|
|
{
|
|
"entropy": 5.544275522232056,
|
|
"epoch": 2.739023947750363,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004252367146945259,
|
|
"loss": 5.1968,
|
|
"mean_token_accuracy": 0.19159470349550248,
|
|
"num_tokens": 62661163.0,
|
|
"step": 30195
|
|
},
|
|
{
|
|
"entropy": 5.452200412750244,
|
|
"epoch": 2.739477503628447,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00042521262658029905,
|
|
"loss": 5.1937,
|
|
"mean_token_accuracy": 0.19185044765472412,
|
|
"num_tokens": 62672371.0,
|
|
"step": 30200
|
|
},
|
|
{
|
|
"entropy": 5.452580881118775,
|
|
"epoch": 2.739931059506531,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.00042518853535963673,
|
|
"loss": 5.05,
|
|
"mean_token_accuracy": 0.2039768800139427,
|
|
"num_tokens": 62682521.0,
|
|
"step": 30205
|
|
},
|
|
{
|
|
"entropy": 5.415886926651001,
|
|
"epoch": 2.7403846153846154,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00042516444103303736,
|
|
"loss": 4.9762,
|
|
"mean_token_accuracy": 0.208219213783741,
|
|
"num_tokens": 62692420.0,
|
|
"step": 30210
|
|
},
|
|
{
|
|
"entropy": 5.38433952331543,
|
|
"epoch": 2.7408381712626997,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00042514034360099907,
|
|
"loss": 5.077,
|
|
"mean_token_accuracy": 0.19949229955673217,
|
|
"num_tokens": 62702686.0,
|
|
"step": 30215
|
|
},
|
|
{
|
|
"entropy": 5.4584592342376705,
|
|
"epoch": 2.7412917271407835,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00042511624306402015,
|
|
"loss": 5.1018,
|
|
"mean_token_accuracy": 0.1983841836452484,
|
|
"num_tokens": 62713262.0,
|
|
"step": 30220
|
|
},
|
|
{
|
|
"entropy": 5.489618253707886,
|
|
"epoch": 2.7417452830188678,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004250921394225992,
|
|
"loss": 5.0553,
|
|
"mean_token_accuracy": 0.20525307059288025,
|
|
"num_tokens": 62724460.0,
|
|
"step": 30225
|
|
},
|
|
{
|
|
"entropy": 5.394492197036743,
|
|
"epoch": 2.742198838896952,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004250680326772343,
|
|
"loss": 5.1433,
|
|
"mean_token_accuracy": 0.19559476673603057,
|
|
"num_tokens": 62734190.0,
|
|
"step": 30230
|
|
},
|
|
{
|
|
"entropy": 5.447148561477661,
|
|
"epoch": 2.7426523947750363,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004250439228284244,
|
|
"loss": 5.0712,
|
|
"mean_token_accuracy": 0.19723022133111953,
|
|
"num_tokens": 62744323.0,
|
|
"step": 30235
|
|
},
|
|
{
|
|
"entropy": 5.461796808242798,
|
|
"epoch": 2.7431059506531206,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00042501980987666807,
|
|
"loss": 5.0869,
|
|
"mean_token_accuracy": 0.1971021592617035,
|
|
"num_tokens": 62753868.0,
|
|
"step": 30240
|
|
},
|
|
{
|
|
"entropy": 5.475715446472168,
|
|
"epoch": 2.743559506531205,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004249956938224636,
|
|
"loss": 5.1804,
|
|
"mean_token_accuracy": 0.1965029865503311,
|
|
"num_tokens": 62763954.0,
|
|
"step": 30245
|
|
},
|
|
{
|
|
"entropy": 5.458673620223999,
|
|
"epoch": 2.7440130624092887,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00042497157466631015,
|
|
"loss": 5.1059,
|
|
"mean_token_accuracy": 0.2059745416045189,
|
|
"num_tokens": 62774116.0,
|
|
"step": 30250
|
|
},
|
|
{
|
|
"entropy": 5.568659448623658,
|
|
"epoch": 2.744466618287373,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00042494745240870626,
|
|
"loss": 5.1631,
|
|
"mean_token_accuracy": 0.19104692339897156,
|
|
"num_tokens": 62784939.0,
|
|
"step": 30255
|
|
},
|
|
{
|
|
"entropy": 5.446510696411133,
|
|
"epoch": 2.744920174165457,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00042492332705015075,
|
|
"loss": 5.1115,
|
|
"mean_token_accuracy": 0.19612197428941727,
|
|
"num_tokens": 62794988.0,
|
|
"step": 30260
|
|
},
|
|
{
|
|
"entropy": 5.426673364639282,
|
|
"epoch": 2.7453737300435415,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00042489919859114273,
|
|
"loss": 5.1129,
|
|
"mean_token_accuracy": 0.20369841158390045,
|
|
"num_tokens": 62804984.0,
|
|
"step": 30265
|
|
},
|
|
{
|
|
"entropy": 5.480232286453247,
|
|
"epoch": 2.7458272859216253,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00042487506703218104,
|
|
"loss": 5.0966,
|
|
"mean_token_accuracy": 0.18896463066339492,
|
|
"num_tokens": 62816401.0,
|
|
"step": 30270
|
|
},
|
|
{
|
|
"entropy": 5.407698774337769,
|
|
"epoch": 2.7462808417997095,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004248509323737648,
|
|
"loss": 5.0463,
|
|
"mean_token_accuracy": 0.19926249831914902,
|
|
"num_tokens": 62826411.0,
|
|
"step": 30275
|
|
},
|
|
{
|
|
"entropy": 5.469961738586425,
|
|
"epoch": 2.746734397677794,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004248267946163931,
|
|
"loss": 5.1568,
|
|
"mean_token_accuracy": 0.19404255449771882,
|
|
"num_tokens": 62837228.0,
|
|
"step": 30280
|
|
},
|
|
{
|
|
"entropy": 5.410887575149536,
|
|
"epoch": 2.747187953555878,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00042480265376056506,
|
|
"loss": 5.019,
|
|
"mean_token_accuracy": 0.20497162342071534,
|
|
"num_tokens": 62847852.0,
|
|
"step": 30285
|
|
},
|
|
{
|
|
"entropy": 5.40019474029541,
|
|
"epoch": 2.7476415094339623,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00042477850980678,
|
|
"loss": 5.1472,
|
|
"mean_token_accuracy": 0.19310158640146255,
|
|
"num_tokens": 62859516.0,
|
|
"step": 30290
|
|
},
|
|
{
|
|
"entropy": 5.45748929977417,
|
|
"epoch": 2.7480950653120466,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004247543627555372,
|
|
"loss": 5.1056,
|
|
"mean_token_accuracy": 0.19668046236038209,
|
|
"num_tokens": 62869757.0,
|
|
"step": 30295
|
|
},
|
|
{
|
|
"entropy": 5.426281070709228,
|
|
"epoch": 2.748548621190131,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000424730212607336,
|
|
"loss": 5.1722,
|
|
"mean_token_accuracy": 0.19720150977373124,
|
|
"num_tokens": 62879618.0,
|
|
"step": 30300
|
|
},
|
|
{
|
|
"entropy": 5.4517827987670895,
|
|
"epoch": 2.7490021770682147,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004247060593626758,
|
|
"loss": 5.1285,
|
|
"mean_token_accuracy": 0.1909634590148926,
|
|
"num_tokens": 62890491.0,
|
|
"step": 30305
|
|
},
|
|
{
|
|
"entropy": 5.507602977752685,
|
|
"epoch": 2.749455732946299,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004246819030220562,
|
|
"loss": 5.1385,
|
|
"mean_token_accuracy": 0.201398803293705,
|
|
"num_tokens": 62899954.0,
|
|
"step": 30310
|
|
},
|
|
{
|
|
"entropy": 5.44568452835083,
|
|
"epoch": 2.7499092888243832,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004246577435859767,
|
|
"loss": 5.1815,
|
|
"mean_token_accuracy": 0.19903719872236253,
|
|
"num_tokens": 62911857.0,
|
|
"step": 30315
|
|
},
|
|
{
|
|
"entropy": 5.460589075088501,
|
|
"epoch": 2.7503628447024675,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004246335810549369,
|
|
"loss": 5.0849,
|
|
"mean_token_accuracy": 0.20401278883218765,
|
|
"num_tokens": 62922023.0,
|
|
"step": 30320
|
|
},
|
|
{
|
|
"entropy": 5.52382001876831,
|
|
"epoch": 2.7508164005805513,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00042460941542943656,
|
|
"loss": 5.1618,
|
|
"mean_token_accuracy": 0.20405737012624742,
|
|
"num_tokens": 62932845.0,
|
|
"step": 30325
|
|
},
|
|
{
|
|
"entropy": 5.450982093811035,
|
|
"epoch": 2.7512699564586356,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004245852467099753,
|
|
"loss": 5.0803,
|
|
"mean_token_accuracy": 0.19679995626211166,
|
|
"num_tokens": 62942881.0,
|
|
"step": 30330
|
|
},
|
|
{
|
|
"entropy": 5.401119804382324,
|
|
"epoch": 2.75172351233672,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004245610748970531,
|
|
"loss": 5.0649,
|
|
"mean_token_accuracy": 0.2024009719491005,
|
|
"num_tokens": 62953957.0,
|
|
"step": 30335
|
|
},
|
|
{
|
|
"entropy": 5.413307619094849,
|
|
"epoch": 2.752177068214804,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00042453689999116974,
|
|
"loss": 5.0792,
|
|
"mean_token_accuracy": 0.20579976290464402,
|
|
"num_tokens": 62964803.0,
|
|
"step": 30340
|
|
},
|
|
{
|
|
"entropy": 5.42594165802002,
|
|
"epoch": 2.7526306240928884,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004245127219928252,
|
|
"loss": 5.0489,
|
|
"mean_token_accuracy": 0.20018686205148697,
|
|
"num_tokens": 62975477.0,
|
|
"step": 30345
|
|
},
|
|
{
|
|
"entropy": 5.424289321899414,
|
|
"epoch": 2.7530841799709727,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00042448854090251944,
|
|
"loss": 5.1092,
|
|
"mean_token_accuracy": 0.19904824197292328,
|
|
"num_tokens": 62985430.0,
|
|
"step": 30350
|
|
},
|
|
{
|
|
"entropy": 5.434984111785889,
|
|
"epoch": 2.7535377358490565,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00042446435672075254,
|
|
"loss": 5.0991,
|
|
"mean_token_accuracy": 0.19750851392745972,
|
|
"num_tokens": 62997493.0,
|
|
"step": 30355
|
|
},
|
|
{
|
|
"entropy": 5.510907363891602,
|
|
"epoch": 2.7539912917271407,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00042444016944802467,
|
|
"loss": 5.2072,
|
|
"mean_token_accuracy": 0.19467689394950866,
|
|
"num_tokens": 63007573.0,
|
|
"step": 30360
|
|
},
|
|
{
|
|
"entropy": 5.480451822280884,
|
|
"epoch": 2.754444847605225,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00042441597908483603,
|
|
"loss": 5.1594,
|
|
"mean_token_accuracy": 0.20052365213632584,
|
|
"num_tokens": 63018372.0,
|
|
"step": 30365
|
|
},
|
|
{
|
|
"entropy": 5.437300348281861,
|
|
"epoch": 2.7548984034833093,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004243917856316869,
|
|
"loss": 5.0727,
|
|
"mean_token_accuracy": 0.20676460564136506,
|
|
"num_tokens": 63028632.0,
|
|
"step": 30370
|
|
},
|
|
{
|
|
"entropy": 5.464409255981446,
|
|
"epoch": 2.755351959361393,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00042436758908907747,
|
|
"loss": 5.0867,
|
|
"mean_token_accuracy": 0.19428150802850724,
|
|
"num_tokens": 63038510.0,
|
|
"step": 30375
|
|
},
|
|
{
|
|
"entropy": 5.568482494354248,
|
|
"epoch": 2.7558055152394774,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00042434338945750833,
|
|
"loss": 5.275,
|
|
"mean_token_accuracy": 0.17917096316814424,
|
|
"num_tokens": 63049375.0,
|
|
"step": 30380
|
|
},
|
|
{
|
|
"entropy": 5.458902597427368,
|
|
"epoch": 2.7562590711175616,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00042431918673747974,
|
|
"loss": 5.0974,
|
|
"mean_token_accuracy": 0.19501018077135085,
|
|
"num_tokens": 63059422.0,
|
|
"step": 30385
|
|
},
|
|
{
|
|
"entropy": 5.507776737213135,
|
|
"epoch": 2.756712626995646,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00042429498092949245,
|
|
"loss": 5.1943,
|
|
"mean_token_accuracy": 0.1867898404598236,
|
|
"num_tokens": 63071101.0,
|
|
"step": 30390
|
|
},
|
|
{
|
|
"entropy": 5.393851232528687,
|
|
"epoch": 2.75716618287373,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004242707720340468,
|
|
"loss": 5.0422,
|
|
"mean_token_accuracy": 0.20566240698099136,
|
|
"num_tokens": 63081104.0,
|
|
"step": 30395
|
|
},
|
|
{
|
|
"entropy": 5.4616481304168705,
|
|
"epoch": 2.7576197387518144,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004242465600516436,
|
|
"loss": 5.1215,
|
|
"mean_token_accuracy": 0.19702198803424836,
|
|
"num_tokens": 63091123.0,
|
|
"step": 30400
|
|
},
|
|
{
|
|
"entropy": 5.450449895858765,
|
|
"epoch": 2.7580732946298983,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00042422234498278353,
|
|
"loss": 5.1064,
|
|
"mean_token_accuracy": 0.19628460258245467,
|
|
"num_tokens": 63101541.0,
|
|
"step": 30405
|
|
},
|
|
{
|
|
"entropy": 5.483859634399414,
|
|
"epoch": 2.7585268505079825,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00042419812682796727,
|
|
"loss": 5.1741,
|
|
"mean_token_accuracy": 0.18788404017686844,
|
|
"num_tokens": 63112012.0,
|
|
"step": 30410
|
|
},
|
|
{
|
|
"entropy": 5.47482008934021,
|
|
"epoch": 2.758980406386067,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004241739055876957,
|
|
"loss": 5.0997,
|
|
"mean_token_accuracy": 0.19975534528493882,
|
|
"num_tokens": 63122021.0,
|
|
"step": 30415
|
|
},
|
|
{
|
|
"entropy": 5.544798374176025,
|
|
"epoch": 2.759433962264151,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00042414968126246985,
|
|
"loss": 5.2015,
|
|
"mean_token_accuracy": 0.19446804970502854,
|
|
"num_tokens": 63132286.0,
|
|
"step": 30420
|
|
},
|
|
{
|
|
"entropy": 5.443775653839111,
|
|
"epoch": 2.759887518142235,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00042412545385279055,
|
|
"loss": 5.0787,
|
|
"mean_token_accuracy": 0.20546094626188277,
|
|
"num_tokens": 63142159.0,
|
|
"step": 30425
|
|
},
|
|
{
|
|
"entropy": 5.407216358184814,
|
|
"epoch": 2.760341074020319,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00042410122335915883,
|
|
"loss": 5.0552,
|
|
"mean_token_accuracy": 0.1976408377289772,
|
|
"num_tokens": 63152225.0,
|
|
"step": 30430
|
|
},
|
|
{
|
|
"entropy": 5.391296482086181,
|
|
"epoch": 2.7607946298984034,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004240769897820758,
|
|
"loss": 5.0874,
|
|
"mean_token_accuracy": 0.1953212335705757,
|
|
"num_tokens": 63162522.0,
|
|
"step": 30435
|
|
},
|
|
{
|
|
"entropy": 5.472185182571411,
|
|
"epoch": 2.7612481857764877,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00042405275312204266,
|
|
"loss": 5.0409,
|
|
"mean_token_accuracy": 0.2021949678659439,
|
|
"num_tokens": 63172094.0,
|
|
"step": 30440
|
|
},
|
|
{
|
|
"entropy": 5.4891321659088135,
|
|
"epoch": 2.761701741654572,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00042402851337956066,
|
|
"loss": 5.1207,
|
|
"mean_token_accuracy": 0.1955082044005394,
|
|
"num_tokens": 63182122.0,
|
|
"step": 30445
|
|
},
|
|
{
|
|
"entropy": 5.405099678039551,
|
|
"epoch": 2.762155297532656,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00042400427055513094,
|
|
"loss": 5.0874,
|
|
"mean_token_accuracy": 0.19648720622062682,
|
|
"num_tokens": 63193174.0,
|
|
"step": 30450
|
|
},
|
|
{
|
|
"entropy": 5.459750509262085,
|
|
"epoch": 2.7626088534107405,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000423980024649255,
|
|
"loss": 5.0301,
|
|
"mean_token_accuracy": 0.20567665100097657,
|
|
"num_tokens": 63203698.0,
|
|
"step": 30455
|
|
},
|
|
{
|
|
"entropy": 5.347402572631836,
|
|
"epoch": 2.7630624092888243,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004239557756624342,
|
|
"loss": 4.9783,
|
|
"mean_token_accuracy": 0.20131055861711503,
|
|
"num_tokens": 63213343.0,
|
|
"step": 30460
|
|
},
|
|
{
|
|
"entropy": 5.466785955429077,
|
|
"epoch": 2.7635159651669086,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00042393152359516994,
|
|
"loss": 5.1931,
|
|
"mean_token_accuracy": 0.1927690476179123,
|
|
"num_tokens": 63223962.0,
|
|
"step": 30465
|
|
},
|
|
{
|
|
"entropy": 5.441215324401855,
|
|
"epoch": 2.763969521044993,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00042390726844796384,
|
|
"loss": 5.0591,
|
|
"mean_token_accuracy": 0.19732695519924165,
|
|
"num_tokens": 63234279.0,
|
|
"step": 30470
|
|
},
|
|
{
|
|
"entropy": 5.513955211639404,
|
|
"epoch": 2.7644230769230766,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004238830102213174,
|
|
"loss": 5.156,
|
|
"mean_token_accuracy": 0.19888577461242676,
|
|
"num_tokens": 63245567.0,
|
|
"step": 30475
|
|
},
|
|
{
|
|
"entropy": 5.445709085464477,
|
|
"epoch": 2.764876632801161,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004238587489157325,
|
|
"loss": 5.0662,
|
|
"mean_token_accuracy": 0.2039734974503517,
|
|
"num_tokens": 63256227.0,
|
|
"step": 30480
|
|
},
|
|
{
|
|
"entropy": 5.380319452285766,
|
|
"epoch": 2.765330188679245,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004238344845317107,
|
|
"loss": 5.0084,
|
|
"mean_token_accuracy": 0.20255834907293319,
|
|
"num_tokens": 63266618.0,
|
|
"step": 30485
|
|
},
|
|
{
|
|
"entropy": 5.4000115394592285,
|
|
"epoch": 2.7657837445573294,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004238102170697539,
|
|
"loss": 5.0394,
|
|
"mean_token_accuracy": 0.2055308684706688,
|
|
"num_tokens": 63277130.0,
|
|
"step": 30490
|
|
},
|
|
{
|
|
"entropy": 5.363031196594238,
|
|
"epoch": 2.7662373004354137,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004237859465303637,
|
|
"loss": 4.9603,
|
|
"mean_token_accuracy": 0.20936691015958786,
|
|
"num_tokens": 63287351.0,
|
|
"step": 30495
|
|
},
|
|
{
|
|
"entropy": 5.359759426116943,
|
|
"epoch": 2.766690856313498,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00042376167291404234,
|
|
"loss": 5.0404,
|
|
"mean_token_accuracy": 0.20127637982368468,
|
|
"num_tokens": 63298573.0,
|
|
"step": 30500
|
|
},
|
|
{
|
|
"entropy": 5.457450342178345,
|
|
"epoch": 2.7671444121915822,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00042373739622129166,
|
|
"loss": 5.1195,
|
|
"mean_token_accuracy": 0.19206231981515884,
|
|
"num_tokens": 63310740.0,
|
|
"step": 30505
|
|
},
|
|
{
|
|
"entropy": 5.440865182876587,
|
|
"epoch": 2.767597968069666,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00042371311645261376,
|
|
"loss": 5.0897,
|
|
"mean_token_accuracy": 0.1992865487933159,
|
|
"num_tokens": 63321323.0,
|
|
"step": 30510
|
|
},
|
|
{
|
|
"entropy": 5.452223634719848,
|
|
"epoch": 2.7680515239477503,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004236888336085107,
|
|
"loss": 5.0965,
|
|
"mean_token_accuracy": 0.20479266047477723,
|
|
"num_tokens": 63332322.0,
|
|
"step": 30515
|
|
},
|
|
{
|
|
"entropy": 5.379767227172851,
|
|
"epoch": 2.7685050798258346,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004236645476894846,
|
|
"loss": 4.9902,
|
|
"mean_token_accuracy": 0.20565419942140578,
|
|
"num_tokens": 63342204.0,
|
|
"step": 30520
|
|
},
|
|
{
|
|
"entropy": 5.3151750564575195,
|
|
"epoch": 2.768958635703919,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004236402586960378,
|
|
"loss": 5.0574,
|
|
"mean_token_accuracy": 0.20382263362407685,
|
|
"num_tokens": 63352460.0,
|
|
"step": 30525
|
|
},
|
|
{
|
|
"entropy": 5.366339540481567,
|
|
"epoch": 2.7694121915820027,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004236159666286726,
|
|
"loss": 5.0334,
|
|
"mean_token_accuracy": 0.20237740725278855,
|
|
"num_tokens": 63362474.0,
|
|
"step": 30530
|
|
},
|
|
{
|
|
"entropy": 5.481100988388062,
|
|
"epoch": 2.769865747460087,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00042359167148789135,
|
|
"loss": 5.0694,
|
|
"mean_token_accuracy": 0.20606732815504075,
|
|
"num_tokens": 63372537.0,
|
|
"step": 30535
|
|
},
|
|
{
|
|
"entropy": 5.395490217208862,
|
|
"epoch": 2.7703193033381712,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004235673732741964,
|
|
"loss": 4.9796,
|
|
"mean_token_accuracy": 0.211866994202137,
|
|
"num_tokens": 63382985.0,
|
|
"step": 30540
|
|
},
|
|
{
|
|
"entropy": 5.407249689102173,
|
|
"epoch": 2.7707728592162555,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00042354307198809037,
|
|
"loss": 5.0618,
|
|
"mean_token_accuracy": 0.20237739384174347,
|
|
"num_tokens": 63393424.0,
|
|
"step": 30545
|
|
},
|
|
{
|
|
"entropy": 5.325113296508789,
|
|
"epoch": 2.7712264150943398,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004235187676300757,
|
|
"loss": 4.9626,
|
|
"mean_token_accuracy": 0.2098858803510666,
|
|
"num_tokens": 63403160.0,
|
|
"step": 30550
|
|
},
|
|
{
|
|
"entropy": 5.496388006210327,
|
|
"epoch": 2.771679970972424,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004234944602006552,
|
|
"loss": 5.1235,
|
|
"mean_token_accuracy": 0.1988478884100914,
|
|
"num_tokens": 63413001.0,
|
|
"step": 30555
|
|
},
|
|
{
|
|
"entropy": 5.46978645324707,
|
|
"epoch": 2.772133526850508,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00042347014970033124,
|
|
"loss": 5.0572,
|
|
"mean_token_accuracy": 0.20675707310438157,
|
|
"num_tokens": 63422735.0,
|
|
"step": 30560
|
|
},
|
|
{
|
|
"entropy": 5.317018747329712,
|
|
"epoch": 2.772587082728592,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004234458361296069,
|
|
"loss": 5.0505,
|
|
"mean_token_accuracy": 0.19980158507823945,
|
|
"num_tokens": 63432566.0,
|
|
"step": 30565
|
|
},
|
|
{
|
|
"entropy": 5.468571424484253,
|
|
"epoch": 2.7730406386066764,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00042342151948898476,
|
|
"loss": 5.0617,
|
|
"mean_token_accuracy": 0.20038823038339615,
|
|
"num_tokens": 63442412.0,
|
|
"step": 30570
|
|
},
|
|
{
|
|
"entropy": 5.4606475830078125,
|
|
"epoch": 2.7734941944847606,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00042339719977896784,
|
|
"loss": 5.0819,
|
|
"mean_token_accuracy": 0.20560524016618728,
|
|
"num_tokens": 63453018.0,
|
|
"step": 30575
|
|
},
|
|
{
|
|
"entropy": 5.469740629196167,
|
|
"epoch": 2.7739477503628445,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000423372877000059,
|
|
"loss": 5.1111,
|
|
"mean_token_accuracy": 0.19795765727758408,
|
|
"num_tokens": 63464286.0,
|
|
"step": 30580
|
|
},
|
|
{
|
|
"entropy": 5.366232204437256,
|
|
"epoch": 2.7744013062409287,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00042334855115276117,
|
|
"loss": 5.109,
|
|
"mean_token_accuracy": 0.19996265321969986,
|
|
"num_tokens": 63475138.0,
|
|
"step": 30585
|
|
},
|
|
{
|
|
"entropy": 5.529539108276367,
|
|
"epoch": 2.774854862119013,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00042332422223757756,
|
|
"loss": 5.148,
|
|
"mean_token_accuracy": 0.20031228959560393,
|
|
"num_tokens": 63486104.0,
|
|
"step": 30590
|
|
},
|
|
{
|
|
"entropy": 5.407452917098999,
|
|
"epoch": 2.7753084179970973,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00042329989025501123,
|
|
"loss": 5.0562,
|
|
"mean_token_accuracy": 0.20201291292905807,
|
|
"num_tokens": 63496490.0,
|
|
"step": 30595
|
|
},
|
|
{
|
|
"entropy": 5.389845466613769,
|
|
"epoch": 2.7757619738751815,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00042327555520556536,
|
|
"loss": 5.0459,
|
|
"mean_token_accuracy": 0.19839254915714263,
|
|
"num_tokens": 63506562.0,
|
|
"step": 30600
|
|
},
|
|
{
|
|
"entropy": 5.428741025924682,
|
|
"epoch": 2.776215529753266,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00042325121708974324,
|
|
"loss": 5.0739,
|
|
"mean_token_accuracy": 0.20799240916967393,
|
|
"num_tokens": 63516641.0,
|
|
"step": 30605
|
|
},
|
|
{
|
|
"entropy": 5.424184513092041,
|
|
"epoch": 2.7766690856313496,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004232268759080482,
|
|
"loss": 5.0729,
|
|
"mean_token_accuracy": 0.2020537093281746,
|
|
"num_tokens": 63526864.0,
|
|
"step": 30610
|
|
},
|
|
{
|
|
"entropy": 5.471606826782226,
|
|
"epoch": 2.777122641509434,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00042320253166098354,
|
|
"loss": 5.1625,
|
|
"mean_token_accuracy": 0.19517819881439208,
|
|
"num_tokens": 63537160.0,
|
|
"step": 30615
|
|
},
|
|
{
|
|
"entropy": 5.462520933151245,
|
|
"epoch": 2.777576197387518,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00042317818434905275,
|
|
"loss": 5.057,
|
|
"mean_token_accuracy": 0.19949071556329728,
|
|
"num_tokens": 63547485.0,
|
|
"step": 30620
|
|
},
|
|
{
|
|
"entropy": 5.4205735206604,
|
|
"epoch": 2.7780297532656024,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004231538339727594,
|
|
"loss": 5.0417,
|
|
"mean_token_accuracy": 0.1996966317296028,
|
|
"num_tokens": 63559369.0,
|
|
"step": 30625
|
|
},
|
|
{
|
|
"entropy": 5.53844313621521,
|
|
"epoch": 2.7784833091436862,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00042312948053260704,
|
|
"loss": 5.2363,
|
|
"mean_token_accuracy": 0.18452441096305847,
|
|
"num_tokens": 63570033.0,
|
|
"step": 30630
|
|
},
|
|
{
|
|
"entropy": 5.44473671913147,
|
|
"epoch": 2.7789368650217705,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004231051240290992,
|
|
"loss": 5.047,
|
|
"mean_token_accuracy": 0.20029836893081665,
|
|
"num_tokens": 63581274.0,
|
|
"step": 30635
|
|
},
|
|
{
|
|
"entropy": 5.4185929775238035,
|
|
"epoch": 2.7793904208998548,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00042308076446273963,
|
|
"loss": 5.0831,
|
|
"mean_token_accuracy": 0.2004862293601036,
|
|
"num_tokens": 63590903.0,
|
|
"step": 30640
|
|
},
|
|
{
|
|
"entropy": 5.3736742496490475,
|
|
"epoch": 2.779843976777939,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00042305640183403214,
|
|
"loss": 5.0794,
|
|
"mean_token_accuracy": 0.1965278148651123,
|
|
"num_tokens": 63600982.0,
|
|
"step": 30645
|
|
},
|
|
{
|
|
"entropy": 5.3667045593261715,
|
|
"epoch": 2.7802975326560233,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00042303203614348057,
|
|
"loss": 4.9804,
|
|
"mean_token_accuracy": 0.20629388093948364,
|
|
"num_tokens": 63612411.0,
|
|
"step": 30650
|
|
},
|
|
{
|
|
"entropy": 5.409779644012451,
|
|
"epoch": 2.7807510885341076,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004230076673915888,
|
|
"loss": 5.0494,
|
|
"mean_token_accuracy": 0.20446045249700545,
|
|
"num_tokens": 63622128.0,
|
|
"step": 30655
|
|
},
|
|
{
|
|
"entropy": 5.427618074417114,
|
|
"epoch": 2.781204644412192,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00042298329557886074,
|
|
"loss": 5.1164,
|
|
"mean_token_accuracy": 0.20271588563919068,
|
|
"num_tokens": 63632047.0,
|
|
"step": 30660
|
|
},
|
|
{
|
|
"entropy": 5.528031349182129,
|
|
"epoch": 2.7816582002902757,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004229589207058003,
|
|
"loss": 5.1374,
|
|
"mean_token_accuracy": 0.19918162971735,
|
|
"num_tokens": 63642490.0,
|
|
"step": 30665
|
|
},
|
|
{
|
|
"entropy": 5.387956714630127,
|
|
"epoch": 2.78211175616836,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00042293454277291177,
|
|
"loss": 5.0545,
|
|
"mean_token_accuracy": 0.20075123608112336,
|
|
"num_tokens": 63653206.0,
|
|
"step": 30670
|
|
},
|
|
{
|
|
"entropy": 5.367197036743164,
|
|
"epoch": 2.782565312046444,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00042291016178069916,
|
|
"loss": 5.0578,
|
|
"mean_token_accuracy": 0.20317523330450057,
|
|
"num_tokens": 63663427.0,
|
|
"step": 30675
|
|
},
|
|
{
|
|
"entropy": 5.361718034744262,
|
|
"epoch": 2.7830188679245285,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004228857777296668,
|
|
"loss": 5.0525,
|
|
"mean_token_accuracy": 0.20298995077610016,
|
|
"num_tokens": 63674269.0,
|
|
"step": 30680
|
|
},
|
|
{
|
|
"entropy": 5.411952781677246,
|
|
"epoch": 2.7834724238026123,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004228613906203188,
|
|
"loss": 5.0376,
|
|
"mean_token_accuracy": 0.20142799317836763,
|
|
"num_tokens": 63683989.0,
|
|
"step": 30685
|
|
},
|
|
{
|
|
"entropy": 5.449591541290284,
|
|
"epoch": 2.7839259796806965,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00042283700045315955,
|
|
"loss": 5.0653,
|
|
"mean_token_accuracy": 0.19948091953992844,
|
|
"num_tokens": 63694540.0,
|
|
"step": 30690
|
|
},
|
|
{
|
|
"entropy": 5.408837556838989,
|
|
"epoch": 2.784379535558781,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00042281260722869355,
|
|
"loss": 5.043,
|
|
"mean_token_accuracy": 0.2000819981098175,
|
|
"num_tokens": 63705149.0,
|
|
"step": 30695
|
|
},
|
|
{
|
|
"entropy": 5.363717031478882,
|
|
"epoch": 2.784833091436865,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00042278821094742495,
|
|
"loss": 5.0563,
|
|
"mean_token_accuracy": 0.20044126212596894,
|
|
"num_tokens": 63714061.0,
|
|
"step": 30700
|
|
},
|
|
{
|
|
"entropy": 5.475161218643189,
|
|
"epoch": 2.7852866473149493,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00042276381160985874,
|
|
"loss": 5.1247,
|
|
"mean_token_accuracy": 0.19785477519035338,
|
|
"num_tokens": 63724732.0,
|
|
"step": 30705
|
|
},
|
|
{
|
|
"entropy": 5.454126834869385,
|
|
"epoch": 2.7857402031930336,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004227394092164991,
|
|
"loss": 5.1057,
|
|
"mean_token_accuracy": 0.19833313375711442,
|
|
"num_tokens": 63734942.0,
|
|
"step": 30710
|
|
},
|
|
{
|
|
"entropy": 5.495724105834961,
|
|
"epoch": 2.7861937590711174,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004227150037678509,
|
|
"loss": 5.2002,
|
|
"mean_token_accuracy": 0.2051568791270256,
|
|
"num_tokens": 63745326.0,
|
|
"step": 30715
|
|
},
|
|
{
|
|
"entropy": 5.475992155075073,
|
|
"epoch": 2.7866473149492017,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004226905952644188,
|
|
"loss": 5.0795,
|
|
"mean_token_accuracy": 0.19791887998580932,
|
|
"num_tokens": 63755355.0,
|
|
"step": 30720
|
|
},
|
|
{
|
|
"entropy": 5.450553941726684,
|
|
"epoch": 2.787100870827286,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00042266618370670743,
|
|
"loss": 5.0649,
|
|
"mean_token_accuracy": 0.20136197805404663,
|
|
"num_tokens": 63765112.0,
|
|
"step": 30725
|
|
},
|
|
{
|
|
"entropy": 5.373752450942993,
|
|
"epoch": 2.7875544267053702,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00042264176909522183,
|
|
"loss": 5.0139,
|
|
"mean_token_accuracy": 0.20659071952104568,
|
|
"num_tokens": 63774680.0,
|
|
"step": 30730
|
|
},
|
|
{
|
|
"entropy": 5.48524580001831,
|
|
"epoch": 2.788007982583454,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004226173514304669,
|
|
"loss": 5.1614,
|
|
"mean_token_accuracy": 0.2029497429728508,
|
|
"num_tokens": 63784939.0,
|
|
"step": 30735
|
|
},
|
|
{
|
|
"entropy": 5.485718679428101,
|
|
"epoch": 2.7884615384615383,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004225929307129474,
|
|
"loss": 5.1503,
|
|
"mean_token_accuracy": 0.18724573999643326,
|
|
"num_tokens": 63795836.0,
|
|
"step": 30740
|
|
},
|
|
{
|
|
"entropy": 5.408643960952759,
|
|
"epoch": 2.7889150943396226,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00042256850694316844,
|
|
"loss": 5.0228,
|
|
"mean_token_accuracy": 0.19762269109487535,
|
|
"num_tokens": 63805607.0,
|
|
"step": 30745
|
|
},
|
|
{
|
|
"entropy": 5.357620906829834,
|
|
"epoch": 2.789368650217707,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004225440801216353,
|
|
"loss": 5.0256,
|
|
"mean_token_accuracy": 0.20234490633010865,
|
|
"num_tokens": 63815081.0,
|
|
"step": 30750
|
|
},
|
|
{
|
|
"entropy": 5.352141332626343,
|
|
"epoch": 2.789822206095791,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004225196502488529,
|
|
"loss": 5.0436,
|
|
"mean_token_accuracy": 0.2051697179675102,
|
|
"num_tokens": 63825932.0,
|
|
"step": 30755
|
|
},
|
|
{
|
|
"entropy": 5.403826093673706,
|
|
"epoch": 2.7902757619738754,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00042249521732532657,
|
|
"loss": 5.0078,
|
|
"mean_token_accuracy": 0.20390547513961793,
|
|
"num_tokens": 63835653.0,
|
|
"step": 30760
|
|
},
|
|
{
|
|
"entropy": 5.503281831741333,
|
|
"epoch": 2.790729317851959,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004224707813515615,
|
|
"loss": 5.211,
|
|
"mean_token_accuracy": 0.1940175026655197,
|
|
"num_tokens": 63847657.0,
|
|
"step": 30765
|
|
},
|
|
{
|
|
"entropy": 5.5128639221191404,
|
|
"epoch": 2.7911828737300435,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00042244634232806324,
|
|
"loss": 5.1234,
|
|
"mean_token_accuracy": 0.1945151224732399,
|
|
"num_tokens": 63858476.0,
|
|
"step": 30770
|
|
},
|
|
{
|
|
"entropy": 5.393078136444092,
|
|
"epoch": 2.7916364296081277,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00042242190025533694,
|
|
"loss": 4.9691,
|
|
"mean_token_accuracy": 0.20336677730083466,
|
|
"num_tokens": 63867970.0,
|
|
"step": 30775
|
|
},
|
|
{
|
|
"entropy": 5.424435377120972,
|
|
"epoch": 2.792089985486212,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004223974551338881,
|
|
"loss": 5.0589,
|
|
"mean_token_accuracy": 0.20939590632915497,
|
|
"num_tokens": 63878294.0,
|
|
"step": 30780
|
|
},
|
|
{
|
|
"entropy": 5.361523246765136,
|
|
"epoch": 2.792543541364296,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004223730069642224,
|
|
"loss": 5.0612,
|
|
"mean_token_accuracy": 0.19951161891222,
|
|
"num_tokens": 63889315.0,
|
|
"step": 30785
|
|
},
|
|
{
|
|
"entropy": 5.372024917602539,
|
|
"epoch": 2.79299709724238,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004223485557468454,
|
|
"loss": 5.0362,
|
|
"mean_token_accuracy": 0.19983876049518584,
|
|
"num_tokens": 63899923.0,
|
|
"step": 30790
|
|
},
|
|
{
|
|
"entropy": 5.374402618408203,
|
|
"epoch": 2.7934506531204644,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00042232410148226277,
|
|
"loss": 5.0312,
|
|
"mean_token_accuracy": 0.20755939036607743,
|
|
"num_tokens": 63909813.0,
|
|
"step": 30795
|
|
},
|
|
{
|
|
"entropy": 5.438010120391846,
|
|
"epoch": 2.7939042089985486,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00042229964417098007,
|
|
"loss": 5.0658,
|
|
"mean_token_accuracy": 0.19565244466066362,
|
|
"num_tokens": 63920931.0,
|
|
"step": 30800
|
|
},
|
|
{
|
|
"entropy": 5.377100419998169,
|
|
"epoch": 2.794357764876633,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00042227518381350316,
|
|
"loss": 5.0059,
|
|
"mean_token_accuracy": 0.20704604387283326,
|
|
"num_tokens": 63930799.0,
|
|
"step": 30805
|
|
},
|
|
{
|
|
"entropy": 5.532281732559204,
|
|
"epoch": 2.794811320754717,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00042225072041033804,
|
|
"loss": 5.1841,
|
|
"mean_token_accuracy": 0.19225446432828902,
|
|
"num_tokens": 63941763.0,
|
|
"step": 30810
|
|
},
|
|
{
|
|
"entropy": 5.494026565551758,
|
|
"epoch": 2.7952648766328014,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00042222625396199043,
|
|
"loss": 5.1658,
|
|
"mean_token_accuracy": 0.18985291868448256,
|
|
"num_tokens": 63952775.0,
|
|
"step": 30815
|
|
},
|
|
{
|
|
"entropy": 5.440386056900024,
|
|
"epoch": 2.7957184325108853,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004222017844689663,
|
|
"loss": 5.1217,
|
|
"mean_token_accuracy": 0.2046050935983658,
|
|
"num_tokens": 63964223.0,
|
|
"step": 30820
|
|
},
|
|
{
|
|
"entropy": 5.451787996292114,
|
|
"epoch": 2.7961719883889695,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004221773119317719,
|
|
"loss": 5.1721,
|
|
"mean_token_accuracy": 0.19606389701366425,
|
|
"num_tokens": 63976413.0,
|
|
"step": 30825
|
|
},
|
|
{
|
|
"entropy": 5.544559335708618,
|
|
"epoch": 2.796625544267054,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00042215283635091313,
|
|
"loss": 5.1393,
|
|
"mean_token_accuracy": 0.20341821908950805,
|
|
"num_tokens": 63986578.0,
|
|
"step": 30830
|
|
},
|
|
{
|
|
"entropy": 5.446145820617676,
|
|
"epoch": 2.7970791001451376,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004221283577268962,
|
|
"loss": 5.0939,
|
|
"mean_token_accuracy": 0.20146804451942443,
|
|
"num_tokens": 63996856.0,
|
|
"step": 30835
|
|
},
|
|
{
|
|
"entropy": 5.360592651367187,
|
|
"epoch": 2.797532656023222,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00042210387606022724,
|
|
"loss": 5.0449,
|
|
"mean_token_accuracy": 0.20774262696504592,
|
|
"num_tokens": 64007700.0,
|
|
"step": 30840
|
|
},
|
|
{
|
|
"entropy": 5.501379776000976,
|
|
"epoch": 2.797986211901306,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004220793913514128,
|
|
"loss": 5.219,
|
|
"mean_token_accuracy": 0.18947813659906387,
|
|
"num_tokens": 64018771.0,
|
|
"step": 30845
|
|
},
|
|
{
|
|
"entropy": 5.462937355041504,
|
|
"epoch": 2.7984397677793904,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004220549036009589,
|
|
"loss": 5.0818,
|
|
"mean_token_accuracy": 0.19818098694086075,
|
|
"num_tokens": 64029381.0,
|
|
"step": 30850
|
|
},
|
|
{
|
|
"entropy": 5.337518835067749,
|
|
"epoch": 2.7988933236574747,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00042203041280937224,
|
|
"loss": 5.0104,
|
|
"mean_token_accuracy": 0.20618090480566026,
|
|
"num_tokens": 64039596.0,
|
|
"step": 30855
|
|
},
|
|
{
|
|
"entropy": 5.469533252716064,
|
|
"epoch": 2.799346879535559,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004220059189771592,
|
|
"loss": 5.0867,
|
|
"mean_token_accuracy": 0.20928966850042344,
|
|
"num_tokens": 64049123.0,
|
|
"step": 30860
|
|
},
|
|
{
|
|
"entropy": 5.478454446792602,
|
|
"epoch": 2.799800435413643,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00042198142210482623,
|
|
"loss": 5.1453,
|
|
"mean_token_accuracy": 0.19954018592834472,
|
|
"num_tokens": 64059426.0,
|
|
"step": 30865
|
|
},
|
|
{
|
|
"entropy": 5.398906087875366,
|
|
"epoch": 2.800253991291727,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00042195692219287997,
|
|
"loss": 4.9931,
|
|
"mean_token_accuracy": 0.20798448324203492,
|
|
"num_tokens": 64069227.0,
|
|
"step": 30870
|
|
},
|
|
{
|
|
"entropy": 5.44100432395935,
|
|
"epoch": 2.8007075471698113,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004219324192418272,
|
|
"loss": 5.0861,
|
|
"mean_token_accuracy": 0.20426160246133804,
|
|
"num_tokens": 64078482.0,
|
|
"step": 30875
|
|
},
|
|
{
|
|
"entropy": 5.41948618888855,
|
|
"epoch": 2.8011611030478956,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00042190791325217447,
|
|
"loss": 5.0587,
|
|
"mean_token_accuracy": 0.20126447826623917,
|
|
"num_tokens": 64088664.0,
|
|
"step": 30880
|
|
},
|
|
{
|
|
"entropy": 5.431994771957397,
|
|
"epoch": 2.80161465892598,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004218834042244287,
|
|
"loss": 5.004,
|
|
"mean_token_accuracy": 0.20645587742328644,
|
|
"num_tokens": 64099316.0,
|
|
"step": 30885
|
|
},
|
|
{
|
|
"entropy": 5.36523323059082,
|
|
"epoch": 2.8020682148040637,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00042185889215909665,
|
|
"loss": 5.052,
|
|
"mean_token_accuracy": 0.20200250297784805,
|
|
"num_tokens": 64109786.0,
|
|
"step": 30890
|
|
},
|
|
{
|
|
"entropy": 5.446825551986694,
|
|
"epoch": 2.802521770682148,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00042183437705668535,
|
|
"loss": 5.0468,
|
|
"mean_token_accuracy": 0.20227925777435302,
|
|
"num_tokens": 64120771.0,
|
|
"step": 30895
|
|
},
|
|
{
|
|
"entropy": 5.431718111038208,
|
|
"epoch": 2.802975326560232,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00042180985891770176,
|
|
"loss": 5.1129,
|
|
"mean_token_accuracy": 0.1984316498041153,
|
|
"num_tokens": 64130833.0,
|
|
"step": 30900
|
|
},
|
|
{
|
|
"entropy": 5.312987613677978,
|
|
"epoch": 2.8034288824383164,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004217853377426528,
|
|
"loss": 5.0113,
|
|
"mean_token_accuracy": 0.20586902797222137,
|
|
"num_tokens": 64139672.0,
|
|
"step": 30905
|
|
},
|
|
{
|
|
"entropy": 5.50145697593689,
|
|
"epoch": 2.8038824383164007,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004217608135320456,
|
|
"loss": 5.2188,
|
|
"mean_token_accuracy": 0.19498223215341567,
|
|
"num_tokens": 64150383.0,
|
|
"step": 30910
|
|
},
|
|
{
|
|
"entropy": 5.4479286670684814,
|
|
"epoch": 2.804335994194485,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004217362862863875,
|
|
"loss": 5.0307,
|
|
"mean_token_accuracy": 0.20441506803035736,
|
|
"num_tokens": 64160786.0,
|
|
"step": 30915
|
|
},
|
|
{
|
|
"entropy": 5.491817474365234,
|
|
"epoch": 2.804789550072569,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00042171175600618546,
|
|
"loss": 5.1344,
|
|
"mean_token_accuracy": 0.193738155066967,
|
|
"num_tokens": 64172057.0,
|
|
"step": 30920
|
|
},
|
|
{
|
|
"entropy": 5.420497941970825,
|
|
"epoch": 2.805243105950653,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00042168722269194704,
|
|
"loss": 5.0986,
|
|
"mean_token_accuracy": 0.20313433110713958,
|
|
"num_tokens": 64182599.0,
|
|
"step": 30925
|
|
},
|
|
{
|
|
"entropy": 5.4349781513214115,
|
|
"epoch": 2.8056966618287373,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004216626863441794,
|
|
"loss": 5.1314,
|
|
"mean_token_accuracy": 0.19368946999311448,
|
|
"num_tokens": 64193356.0,
|
|
"step": 30930
|
|
},
|
|
{
|
|
"entropy": 5.492118263244629,
|
|
"epoch": 2.8061502177068216,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00042163814696339014,
|
|
"loss": 5.1973,
|
|
"mean_token_accuracy": 0.19415435045957566,
|
|
"num_tokens": 64203625.0,
|
|
"step": 30935
|
|
},
|
|
{
|
|
"entropy": 5.450488948822022,
|
|
"epoch": 2.8066037735849054,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004216136045500866,
|
|
"loss": 5.2018,
|
|
"mean_token_accuracy": 0.19811427891254424,
|
|
"num_tokens": 64214742.0,
|
|
"step": 30940
|
|
},
|
|
{
|
|
"entropy": 5.497168922424317,
|
|
"epoch": 2.8070573294629897,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004215890591047763,
|
|
"loss": 5.1056,
|
|
"mean_token_accuracy": 0.20020431876182557,
|
|
"num_tokens": 64223811.0,
|
|
"step": 30945
|
|
},
|
|
{
|
|
"entropy": 5.4323813915252686,
|
|
"epoch": 2.807510885341074,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00042156451062796686,
|
|
"loss": 4.985,
|
|
"mean_token_accuracy": 0.20995582193136214,
|
|
"num_tokens": 64234854.0,
|
|
"step": 30950
|
|
},
|
|
{
|
|
"entropy": 5.408839511871338,
|
|
"epoch": 2.8079644412191582,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00042153995912016606,
|
|
"loss": 5.1234,
|
|
"mean_token_accuracy": 0.19832305908203124,
|
|
"num_tokens": 64245914.0,
|
|
"step": 30955
|
|
},
|
|
{
|
|
"entropy": 5.4090574264526365,
|
|
"epoch": 2.8084179970972425,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004215154045818816,
|
|
"loss": 5.1523,
|
|
"mean_token_accuracy": 0.1938547283411026,
|
|
"num_tokens": 64256217.0,
|
|
"step": 30960
|
|
},
|
|
{
|
|
"entropy": 5.476193141937256,
|
|
"epoch": 2.8088715529753268,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004214908470136212,
|
|
"loss": 5.1605,
|
|
"mean_token_accuracy": 0.18867257386445999,
|
|
"num_tokens": 64267211.0,
|
|
"step": 30965
|
|
},
|
|
{
|
|
"entropy": 5.527535629272461,
|
|
"epoch": 2.8093251088534106,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004214662864158927,
|
|
"loss": 5.1371,
|
|
"mean_token_accuracy": 0.2011988192796707,
|
|
"num_tokens": 64277770.0,
|
|
"step": 30970
|
|
},
|
|
{
|
|
"entropy": 5.374342727661133,
|
|
"epoch": 2.809778664731495,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00042144172278920413,
|
|
"loss": 5.0201,
|
|
"mean_token_accuracy": 0.2062619760632515,
|
|
"num_tokens": 64287973.0,
|
|
"step": 30975
|
|
},
|
|
{
|
|
"entropy": 5.371738290786743,
|
|
"epoch": 2.810232220609579,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004214171561340634,
|
|
"loss": 5.0968,
|
|
"mean_token_accuracy": 0.19711117148399354,
|
|
"num_tokens": 64297898.0,
|
|
"step": 30980
|
|
},
|
|
{
|
|
"entropy": 5.422922658920288,
|
|
"epoch": 2.8106857764876634,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00042139258645097863,
|
|
"loss": 4.9878,
|
|
"mean_token_accuracy": 0.21104531288146972,
|
|
"num_tokens": 64308114.0,
|
|
"step": 30985
|
|
},
|
|
{
|
|
"entropy": 5.394778871536255,
|
|
"epoch": 2.811139332365747,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00042136801374045775,
|
|
"loss": 5.0593,
|
|
"mean_token_accuracy": 0.19936760365962983,
|
|
"num_tokens": 64319586.0,
|
|
"step": 30990
|
|
},
|
|
{
|
|
"entropy": 5.4347984313964846,
|
|
"epoch": 2.8115928882438315,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004213434380030091,
|
|
"loss": 5.1368,
|
|
"mean_token_accuracy": 0.20049012899398805,
|
|
"num_tokens": 64330612.0,
|
|
"step": 30995
|
|
},
|
|
{
|
|
"entropy": 5.507143354415893,
|
|
"epoch": 2.8120464441219157,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004213188592391409,
|
|
"loss": 5.1735,
|
|
"mean_token_accuracy": 0.19412329643964768,
|
|
"num_tokens": 64341934.0,
|
|
"step": 31000
|
|
},
|
|
{
|
|
"entropy": 5.451130390167236,
|
|
"epoch": 2.8125,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004212942774493614,
|
|
"loss": 5.0492,
|
|
"mean_token_accuracy": 0.20119091868400574,
|
|
"num_tokens": 64352166.0,
|
|
"step": 31005
|
|
},
|
|
{
|
|
"entropy": 5.412240123748779,
|
|
"epoch": 2.8129535558780843,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00042126969263417885,
|
|
"loss": 5.1031,
|
|
"mean_token_accuracy": 0.19532829374074936,
|
|
"num_tokens": 64361995.0,
|
|
"step": 31010
|
|
},
|
|
{
|
|
"entropy": 5.377422332763672,
|
|
"epoch": 2.8134071117561685,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00042124510479410183,
|
|
"loss": 5.0531,
|
|
"mean_token_accuracy": 0.19625771939754486,
|
|
"num_tokens": 64372336.0,
|
|
"step": 31015
|
|
},
|
|
{
|
|
"entropy": 5.452481937408447,
|
|
"epoch": 2.813860667634253,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00042122051392963885,
|
|
"loss": 5.0918,
|
|
"mean_token_accuracy": 0.2115592822432518,
|
|
"num_tokens": 64382309.0,
|
|
"step": 31020
|
|
},
|
|
{
|
|
"entropy": 5.463210201263427,
|
|
"epoch": 2.8143142235123366,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004211959200412984,
|
|
"loss": 5.1458,
|
|
"mean_token_accuracy": 0.19819066375494004,
|
|
"num_tokens": 64393205.0,
|
|
"step": 31025
|
|
},
|
|
{
|
|
"entropy": 5.399936580657959,
|
|
"epoch": 2.814767779390421,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004211713231295889,
|
|
"loss": 5.0793,
|
|
"mean_token_accuracy": 0.20134287923574448,
|
|
"num_tokens": 64403068.0,
|
|
"step": 31030
|
|
},
|
|
{
|
|
"entropy": 5.447476243972778,
|
|
"epoch": 2.815221335268505,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004211467231950194,
|
|
"loss": 5.0875,
|
|
"mean_token_accuracy": 0.20236201733350753,
|
|
"num_tokens": 64414296.0,
|
|
"step": 31035
|
|
},
|
|
{
|
|
"entropy": 5.42960524559021,
|
|
"epoch": 2.8156748911465894,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00042112212023809824,
|
|
"loss": 5.0891,
|
|
"mean_token_accuracy": 0.1973024606704712,
|
|
"num_tokens": 64424748.0,
|
|
"step": 31040
|
|
},
|
|
{
|
|
"entropy": 5.451018285751343,
|
|
"epoch": 2.8161284470246732,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004210975142593345,
|
|
"loss": 5.0256,
|
|
"mean_token_accuracy": 0.19944209605455399,
|
|
"num_tokens": 64434723.0,
|
|
"step": 31045
|
|
},
|
|
{
|
|
"entropy": 5.493959903717041,
|
|
"epoch": 2.8165820029027575,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004210729052592369,
|
|
"loss": 5.1793,
|
|
"mean_token_accuracy": 0.19235269278287886,
|
|
"num_tokens": 64445864.0,
|
|
"step": 31050
|
|
},
|
|
{
|
|
"entropy": 5.3770993709564205,
|
|
"epoch": 2.8170355587808418,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004210482932383144,
|
|
"loss": 5.0229,
|
|
"mean_token_accuracy": 0.20120305866003035,
|
|
"num_tokens": 64456704.0,
|
|
"step": 31055
|
|
},
|
|
{
|
|
"entropy": 5.359657669067383,
|
|
"epoch": 2.817489114658926,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000421023678197076,
|
|
"loss": 5.0796,
|
|
"mean_token_accuracy": 0.20384103059768677,
|
|
"num_tokens": 64466870.0,
|
|
"step": 31060
|
|
},
|
|
{
|
|
"entropy": 5.457637119293213,
|
|
"epoch": 2.8179426705370103,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004209990601360307,
|
|
"loss": 5.0905,
|
|
"mean_token_accuracy": 0.1973940595984459,
|
|
"num_tokens": 64477069.0,
|
|
"step": 31065
|
|
},
|
|
{
|
|
"entropy": 5.453010225296021,
|
|
"epoch": 2.8183962264150946,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00042097443905568765,
|
|
"loss": 5.0829,
|
|
"mean_token_accuracy": 0.19410039335489274,
|
|
"num_tokens": 64487165.0,
|
|
"step": 31070
|
|
},
|
|
{
|
|
"entropy": 5.369174957275391,
|
|
"epoch": 2.8188497822931784,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00042094981495655596,
|
|
"loss": 4.9538,
|
|
"mean_token_accuracy": 0.2066846713423729,
|
|
"num_tokens": 64497977.0,
|
|
"step": 31075
|
|
},
|
|
{
|
|
"entropy": 5.442254734039307,
|
|
"epoch": 2.8193033381712627,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000420925187839145,
|
|
"loss": 5.1029,
|
|
"mean_token_accuracy": 0.19969508796930313,
|
|
"num_tokens": 64508767.0,
|
|
"step": 31080
|
|
},
|
|
{
|
|
"entropy": 5.401233768463134,
|
|
"epoch": 2.819756894049347,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00042090055770396383,
|
|
"loss": 5.0011,
|
|
"mean_token_accuracy": 0.20463042855262756,
|
|
"num_tokens": 64519040.0,
|
|
"step": 31085
|
|
},
|
|
{
|
|
"entropy": 5.394052219390869,
|
|
"epoch": 2.820210449927431,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00042087592455152206,
|
|
"loss": 5.0367,
|
|
"mean_token_accuracy": 0.2089098185300827,
|
|
"num_tokens": 64529721.0,
|
|
"step": 31090
|
|
},
|
|
{
|
|
"entropy": 5.436457967758178,
|
|
"epoch": 2.820664005805515,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000420851288382329,
|
|
"loss": 5.1841,
|
|
"mean_token_accuracy": 0.1863437443971634,
|
|
"num_tokens": 64541299.0,
|
|
"step": 31095
|
|
},
|
|
{
|
|
"entropy": 5.472109699249268,
|
|
"epoch": 2.8211175616835993,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00042082664919689406,
|
|
"loss": 5.0385,
|
|
"mean_token_accuracy": 0.1985249400138855,
|
|
"num_tokens": 64550831.0,
|
|
"step": 31100
|
|
},
|
|
{
|
|
"entropy": 5.423081970214843,
|
|
"epoch": 2.8215711175616836,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004208020069957269,
|
|
"loss": 5.0651,
|
|
"mean_token_accuracy": 0.19693537205457687,
|
|
"num_tokens": 64562076.0,
|
|
"step": 31105
|
|
},
|
|
{
|
|
"entropy": 5.356098556518555,
|
|
"epoch": 2.822024673439768,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000420777361779337,
|
|
"loss": 5.0608,
|
|
"mean_token_accuracy": 0.20103810727596283,
|
|
"num_tokens": 64572955.0,
|
|
"step": 31110
|
|
},
|
|
{
|
|
"entropy": 5.502241420745849,
|
|
"epoch": 2.822478229317852,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00042075271354823427,
|
|
"loss": 5.1072,
|
|
"mean_token_accuracy": 0.20130279958248137,
|
|
"num_tokens": 64584376.0,
|
|
"step": 31115
|
|
},
|
|
{
|
|
"entropy": 5.509278392791748,
|
|
"epoch": 2.8229317851959363,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004207280623029281,
|
|
"loss": 5.0949,
|
|
"mean_token_accuracy": 0.19536512941122056,
|
|
"num_tokens": 64594522.0,
|
|
"step": 31120
|
|
},
|
|
{
|
|
"entropy": 5.447764205932617,
|
|
"epoch": 2.82338534107402,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00042070340804392853,
|
|
"loss": 5.1252,
|
|
"mean_token_accuracy": 0.2007225424051285,
|
|
"num_tokens": 64604625.0,
|
|
"step": 31125
|
|
},
|
|
{
|
|
"entropy": 5.42065396308899,
|
|
"epoch": 2.8238388969521044,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004206787507717454,
|
|
"loss": 5.0974,
|
|
"mean_token_accuracy": 0.2008758082985878,
|
|
"num_tokens": 64614184.0,
|
|
"step": 31130
|
|
},
|
|
{
|
|
"entropy": 5.497580337524414,
|
|
"epoch": 2.8242924528301887,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00042065409048688856,
|
|
"loss": 5.1354,
|
|
"mean_token_accuracy": 0.19363967776298524,
|
|
"num_tokens": 64623019.0,
|
|
"step": 31135
|
|
},
|
|
{
|
|
"entropy": 5.437322092056275,
|
|
"epoch": 2.824746008708273,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000420629427189868,
|
|
"loss": 5.0733,
|
|
"mean_token_accuracy": 0.19676849991083145,
|
|
"num_tokens": 64634017.0,
|
|
"step": 31140
|
|
},
|
|
{
|
|
"entropy": 5.397054767608642,
|
|
"epoch": 2.825199564586357,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00042060476088119376,
|
|
"loss": 5.0684,
|
|
"mean_token_accuracy": 0.20426547825336455,
|
|
"num_tokens": 64645007.0,
|
|
"step": 31145
|
|
},
|
|
{
|
|
"entropy": 5.4766401767730715,
|
|
"epoch": 2.825653120464441,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000420580091561376,
|
|
"loss": 5.1182,
|
|
"mean_token_accuracy": 0.1965460240840912,
|
|
"num_tokens": 64655705.0,
|
|
"step": 31150
|
|
},
|
|
{
|
|
"entropy": 5.540651845932007,
|
|
"epoch": 2.8261066763425253,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00042055541923092485,
|
|
"loss": 5.1628,
|
|
"mean_token_accuracy": 0.1990489661693573,
|
|
"num_tokens": 64666094.0,
|
|
"step": 31155
|
|
},
|
|
{
|
|
"entropy": 5.4921262741088865,
|
|
"epoch": 2.8265602322206096,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004205307438903505,
|
|
"loss": 5.1556,
|
|
"mean_token_accuracy": 0.1924944579601288,
|
|
"num_tokens": 64676107.0,
|
|
"step": 31160
|
|
},
|
|
{
|
|
"entropy": 5.40272068977356,
|
|
"epoch": 2.827013788098694,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004205060655401633,
|
|
"loss": 5.0543,
|
|
"mean_token_accuracy": 0.20003008991479873,
|
|
"num_tokens": 64685846.0,
|
|
"step": 31165
|
|
},
|
|
{
|
|
"entropy": 5.4078145027160645,
|
|
"epoch": 2.827467343976778,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004204813841808736,
|
|
"loss": 5.0211,
|
|
"mean_token_accuracy": 0.2039273589849472,
|
|
"num_tokens": 64695959.0,
|
|
"step": 31170
|
|
},
|
|
{
|
|
"entropy": 5.431266784667969,
|
|
"epoch": 2.8279208998548624,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004204566998129917,
|
|
"loss": 5.0451,
|
|
"mean_token_accuracy": 0.20689373463392258,
|
|
"num_tokens": 64705594.0,
|
|
"step": 31175
|
|
},
|
|
{
|
|
"entropy": 5.460352182388306,
|
|
"epoch": 2.828374455732946,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00042043201243702834,
|
|
"loss": 5.098,
|
|
"mean_token_accuracy": 0.19416000843048095,
|
|
"num_tokens": 64715974.0,
|
|
"step": 31180
|
|
},
|
|
{
|
|
"entropy": 5.367126560211181,
|
|
"epoch": 2.8288280116110305,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004204073220534938,
|
|
"loss": 5.0267,
|
|
"mean_token_accuracy": 0.20514230728149413,
|
|
"num_tokens": 64725846.0,
|
|
"step": 31185
|
|
},
|
|
{
|
|
"entropy": 5.3862580299377445,
|
|
"epoch": 2.8292815674891147,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004203826286628988,
|
|
"loss": 5.0063,
|
|
"mean_token_accuracy": 0.20465577989816666,
|
|
"num_tokens": 64735789.0,
|
|
"step": 31190
|
|
},
|
|
{
|
|
"entropy": 5.387496757507324,
|
|
"epoch": 2.8297351233671986,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000420357932265754,
|
|
"loss": 4.989,
|
|
"mean_token_accuracy": 0.21733041405677794,
|
|
"num_tokens": 64745738.0,
|
|
"step": 31195
|
|
},
|
|
{
|
|
"entropy": 5.43909912109375,
|
|
"epoch": 2.830188679245283,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004203332328625701,
|
|
"loss": 5.0763,
|
|
"mean_token_accuracy": 0.194720458984375,
|
|
"num_tokens": 64756523.0,
|
|
"step": 31200
|
|
},
|
|
{
|
|
"entropy": 5.492659950256348,
|
|
"epoch": 2.830642235123367,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00042030853045385796,
|
|
"loss": 5.1605,
|
|
"mean_token_accuracy": 0.19749205857515334,
|
|
"num_tokens": 64767367.0,
|
|
"step": 31205
|
|
},
|
|
{
|
|
"entropy": 5.4598925590515135,
|
|
"epoch": 2.8310957910014514,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00042028382504012837,
|
|
"loss": 5.1029,
|
|
"mean_token_accuracy": 0.2001082867383957,
|
|
"num_tokens": 64777729.0,
|
|
"step": 31210
|
|
},
|
|
{
|
|
"entropy": 5.479545259475708,
|
|
"epoch": 2.8315493468795356,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00042025911662189224,
|
|
"loss": 5.1209,
|
|
"mean_token_accuracy": 0.20155202150344848,
|
|
"num_tokens": 64788223.0,
|
|
"step": 31215
|
|
},
|
|
{
|
|
"entropy": 5.392916297912597,
|
|
"epoch": 2.83200290275762,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00042023440519966057,
|
|
"loss": 5.0698,
|
|
"mean_token_accuracy": 0.20044146925210954,
|
|
"num_tokens": 64797367.0,
|
|
"step": 31220
|
|
},
|
|
{
|
|
"entropy": 5.449520063400269,
|
|
"epoch": 2.832456458635704,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00042020969077394434,
|
|
"loss": 5.09,
|
|
"mean_token_accuracy": 0.20296941250562667,
|
|
"num_tokens": 64807179.0,
|
|
"step": 31225
|
|
},
|
|
{
|
|
"entropy": 5.474658727645874,
|
|
"epoch": 2.832910014513788,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00042018497334525475,
|
|
"loss": 4.9881,
|
|
"mean_token_accuracy": 0.19910144060850143,
|
|
"num_tokens": 64817276.0,
|
|
"step": 31230
|
|
},
|
|
{
|
|
"entropy": 5.409675264358521,
|
|
"epoch": 2.8333635703918723,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004201602529141029,
|
|
"loss": 5.0902,
|
|
"mean_token_accuracy": 0.2032744288444519,
|
|
"num_tokens": 64827509.0,
|
|
"step": 31235
|
|
},
|
|
{
|
|
"entropy": 5.433466148376465,
|
|
"epoch": 2.8338171262699565,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00042013552948100003,
|
|
"loss": 5.0794,
|
|
"mean_token_accuracy": 0.1981348216533661,
|
|
"num_tokens": 64836578.0,
|
|
"step": 31240
|
|
},
|
|
{
|
|
"entropy": 5.435758876800537,
|
|
"epoch": 2.834270682148041,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004201108030464574,
|
|
"loss": 5.0109,
|
|
"mean_token_accuracy": 0.21283946931362152,
|
|
"num_tokens": 64846518.0,
|
|
"step": 31245
|
|
},
|
|
{
|
|
"entropy": 5.470474815368652,
|
|
"epoch": 2.8347242380261246,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00042008607361098646,
|
|
"loss": 5.0762,
|
|
"mean_token_accuracy": 0.20203745365142822,
|
|
"num_tokens": 64856304.0,
|
|
"step": 31250
|
|
},
|
|
{
|
|
"entropy": 5.3923204898834225,
|
|
"epoch": 2.835177793904209,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004200613411750985,
|
|
"loss": 4.9965,
|
|
"mean_token_accuracy": 0.21087777763605117,
|
|
"num_tokens": 64867381.0,
|
|
"step": 31255
|
|
},
|
|
{
|
|
"entropy": 5.4330281734466555,
|
|
"epoch": 2.835631349782293,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000420036605739305,
|
|
"loss": 5.1073,
|
|
"mean_token_accuracy": 0.19812535494565964,
|
|
"num_tokens": 64877306.0,
|
|
"step": 31260
|
|
},
|
|
{
|
|
"entropy": 5.330726146697998,
|
|
"epoch": 2.8360849056603774,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004200118673041176,
|
|
"loss": 5.027,
|
|
"mean_token_accuracy": 0.20286148488521577,
|
|
"num_tokens": 64886932.0,
|
|
"step": 31265
|
|
},
|
|
{
|
|
"entropy": 5.479885530471802,
|
|
"epoch": 2.8365384615384617,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00041998712587004776,
|
|
"loss": 5.1004,
|
|
"mean_token_accuracy": 0.19896485209465026,
|
|
"num_tokens": 64897387.0,
|
|
"step": 31270
|
|
},
|
|
{
|
|
"entropy": 5.472931623458862,
|
|
"epoch": 2.836992017416546,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00041996238143760726,
|
|
"loss": 5.1156,
|
|
"mean_token_accuracy": 0.20374761372804642,
|
|
"num_tokens": 64907251.0,
|
|
"step": 31275
|
|
},
|
|
{
|
|
"entropy": 5.367519998550415,
|
|
"epoch": 2.8374455732946298,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00041993763400730776,
|
|
"loss": 5.0632,
|
|
"mean_token_accuracy": 0.20022127032279968,
|
|
"num_tokens": 64917300.0,
|
|
"step": 31280
|
|
},
|
|
{
|
|
"entropy": 5.39328236579895,
|
|
"epoch": 2.837899129172714,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004199128835796611,
|
|
"loss": 5.0127,
|
|
"mean_token_accuracy": 0.20954301059246064,
|
|
"num_tokens": 64927133.0,
|
|
"step": 31285
|
|
},
|
|
{
|
|
"entropy": 5.454548168182373,
|
|
"epoch": 2.8383526850507983,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000419888130155179,
|
|
"loss": 5.0665,
|
|
"mean_token_accuracy": 0.20421828776597978,
|
|
"num_tokens": 64937789.0,
|
|
"step": 31290
|
|
},
|
|
{
|
|
"entropy": 5.463897085189819,
|
|
"epoch": 2.8388062409288826,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004198633737343735,
|
|
"loss": 5.1077,
|
|
"mean_token_accuracy": 0.20141364485025406,
|
|
"num_tokens": 64948127.0,
|
|
"step": 31295
|
|
},
|
|
{
|
|
"entropy": 5.46923599243164,
|
|
"epoch": 2.8392597968069664,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004198386143177565,
|
|
"loss": 5.1539,
|
|
"mean_token_accuracy": 0.1979905277490616,
|
|
"num_tokens": 64959632.0,
|
|
"step": 31300
|
|
},
|
|
{
|
|
"entropy": 5.313565349578857,
|
|
"epoch": 2.8397133526850507,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00041981385190584003,
|
|
"loss": 4.907,
|
|
"mean_token_accuracy": 0.21088111847639085,
|
|
"num_tokens": 64970411.0,
|
|
"step": 31305
|
|
},
|
|
{
|
|
"entropy": 5.374856853485108,
|
|
"epoch": 2.840166908563135,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004197890864991362,
|
|
"loss": 5.0438,
|
|
"mean_token_accuracy": 0.20163641273975372,
|
|
"num_tokens": 64980748.0,
|
|
"step": 31310
|
|
},
|
|
{
|
|
"entropy": 5.389368486404419,
|
|
"epoch": 2.840620464441219,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004197643180981572,
|
|
"loss": 4.996,
|
|
"mean_token_accuracy": 0.2044817328453064,
|
|
"num_tokens": 64990818.0,
|
|
"step": 31315
|
|
},
|
|
{
|
|
"entropy": 5.424988842010498,
|
|
"epoch": 2.8410740203193035,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004197395467034152,
|
|
"loss": 5.064,
|
|
"mean_token_accuracy": 0.203326515853405,
|
|
"num_tokens": 65001993.0,
|
|
"step": 31320
|
|
},
|
|
{
|
|
"entropy": 5.3413153171539305,
|
|
"epoch": 2.8415275761973877,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004197147723154225,
|
|
"loss": 5.0338,
|
|
"mean_token_accuracy": 0.210561540722847,
|
|
"num_tokens": 65013007.0,
|
|
"step": 31325
|
|
},
|
|
{
|
|
"entropy": 5.452834367752075,
|
|
"epoch": 2.8419811320754715,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004196899949346914,
|
|
"loss": 5.0482,
|
|
"mean_token_accuracy": 0.20244922190904618,
|
|
"num_tokens": 65023595.0,
|
|
"step": 31330
|
|
},
|
|
{
|
|
"entropy": 5.419467258453369,
|
|
"epoch": 2.842434687953556,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004196652145617343,
|
|
"loss": 5.0538,
|
|
"mean_token_accuracy": 0.20489303022623062,
|
|
"num_tokens": 65033631.0,
|
|
"step": 31335
|
|
},
|
|
{
|
|
"entropy": 5.488633680343628,
|
|
"epoch": 2.84288824383164,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004196404311970638,
|
|
"loss": 5.076,
|
|
"mean_token_accuracy": 0.20048194527626037,
|
|
"num_tokens": 65044059.0,
|
|
"step": 31340
|
|
},
|
|
{
|
|
"entropy": 5.400067663192749,
|
|
"epoch": 2.8433417997097243,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004196156448411922,
|
|
"loss": 5.0751,
|
|
"mean_token_accuracy": 0.20431259870529175,
|
|
"num_tokens": 65053931.0,
|
|
"step": 31345
|
|
},
|
|
{
|
|
"entropy": 5.425926303863525,
|
|
"epoch": 2.843795355587808,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00041959085549463234,
|
|
"loss": 5.064,
|
|
"mean_token_accuracy": 0.20615503638982774,
|
|
"num_tokens": 65064011.0,
|
|
"step": 31350
|
|
},
|
|
{
|
|
"entropy": 5.504314804077149,
|
|
"epoch": 2.8442489114658924,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004195660631578966,
|
|
"loss": 5.1463,
|
|
"mean_token_accuracy": 0.19826109558343888,
|
|
"num_tokens": 65074417.0,
|
|
"step": 31355
|
|
},
|
|
{
|
|
"entropy": 5.358891439437866,
|
|
"epoch": 2.8447024673439767,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000419541267831498,
|
|
"loss": 5.0445,
|
|
"mean_token_accuracy": 0.20642485618591308,
|
|
"num_tokens": 65084593.0,
|
|
"step": 31360
|
|
},
|
|
{
|
|
"entropy": 5.41818790435791,
|
|
"epoch": 2.845156023222061,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000419516469515949,
|
|
"loss": 5.0688,
|
|
"mean_token_accuracy": 0.2084965631365776,
|
|
"num_tokens": 65095047.0,
|
|
"step": 31365
|
|
},
|
|
{
|
|
"entropy": 5.469940042495727,
|
|
"epoch": 2.8456095791001452,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00041949166821176264,
|
|
"loss": 5.1586,
|
|
"mean_token_accuracy": 0.20636339187622071,
|
|
"num_tokens": 65104434.0,
|
|
"step": 31370
|
|
},
|
|
{
|
|
"entropy": 5.442753410339355,
|
|
"epoch": 2.8460631349782295,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00041946686391945183,
|
|
"loss": 5.1406,
|
|
"mean_token_accuracy": 0.20479176789522172,
|
|
"num_tokens": 65114039.0,
|
|
"step": 31375
|
|
},
|
|
{
|
|
"entropy": 5.527789306640625,
|
|
"epoch": 2.8465166908563138,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004194420566395294,
|
|
"loss": 5.2003,
|
|
"mean_token_accuracy": 0.18808066844940186,
|
|
"num_tokens": 65125387.0,
|
|
"step": 31380
|
|
},
|
|
{
|
|
"entropy": 5.464668273925781,
|
|
"epoch": 2.8469702467343976,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004194172463725084,
|
|
"loss": 5.1142,
|
|
"mean_token_accuracy": 0.20628439486026764,
|
|
"num_tokens": 65136351.0,
|
|
"step": 31385
|
|
},
|
|
{
|
|
"entropy": 5.414179515838623,
|
|
"epoch": 2.847423802612482,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00041939243311890195,
|
|
"loss": 5.0806,
|
|
"mean_token_accuracy": 0.19693423807621002,
|
|
"num_tokens": 65147343.0,
|
|
"step": 31390
|
|
},
|
|
{
|
|
"entropy": 5.385195970535278,
|
|
"epoch": 2.847877358490566,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00041936761687922324,
|
|
"loss": 5.0248,
|
|
"mean_token_accuracy": 0.20848031789064408,
|
|
"num_tokens": 65157097.0,
|
|
"step": 31395
|
|
},
|
|
{
|
|
"entropy": 5.44538631439209,
|
|
"epoch": 2.8483309143686504,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00041934279765398535,
|
|
"loss": 5.082,
|
|
"mean_token_accuracy": 0.20151045322418212,
|
|
"num_tokens": 65167546.0,
|
|
"step": 31400
|
|
},
|
|
{
|
|
"entropy": 5.4525634288787845,
|
|
"epoch": 2.848784470246734,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004193179754437017,
|
|
"loss": 5.0931,
|
|
"mean_token_accuracy": 0.1957506477832794,
|
|
"num_tokens": 65178497.0,
|
|
"step": 31405
|
|
},
|
|
{
|
|
"entropy": 5.3464549541473385,
|
|
"epoch": 2.8492380261248185,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004192931502488855,
|
|
"loss": 5.014,
|
|
"mean_token_accuracy": 0.2064516067504883,
|
|
"num_tokens": 65189530.0,
|
|
"step": 31410
|
|
},
|
|
{
|
|
"entropy": 5.405603742599487,
|
|
"epoch": 2.8496915820029027,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00041926832207005025,
|
|
"loss": 5.0541,
|
|
"mean_token_accuracy": 0.19943397045135497,
|
|
"num_tokens": 65199836.0,
|
|
"step": 31415
|
|
},
|
|
{
|
|
"entropy": 5.338866758346557,
|
|
"epoch": 2.850145137880987,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004192434909077092,
|
|
"loss": 4.9095,
|
|
"mean_token_accuracy": 0.21302028745412827,
|
|
"num_tokens": 65210208.0,
|
|
"step": 31420
|
|
},
|
|
{
|
|
"entropy": 5.413356971740723,
|
|
"epoch": 2.8505986937590713,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00041921865676237605,
|
|
"loss": 5.0744,
|
|
"mean_token_accuracy": 0.20014867037534714,
|
|
"num_tokens": 65220954.0,
|
|
"step": 31425
|
|
},
|
|
{
|
|
"entropy": 5.46695876121521,
|
|
"epoch": 2.8510522496371555,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00041919381963456437,
|
|
"loss": 5.0513,
|
|
"mean_token_accuracy": 0.2039593741297722,
|
|
"num_tokens": 65230870.0,
|
|
"step": 31430
|
|
},
|
|
{
|
|
"entropy": 5.452144527435303,
|
|
"epoch": 2.8515058055152394,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004191689795247877,
|
|
"loss": 5.1011,
|
|
"mean_token_accuracy": 0.20686156153678895,
|
|
"num_tokens": 65241913.0,
|
|
"step": 31435
|
|
},
|
|
{
|
|
"entropy": 5.446830081939697,
|
|
"epoch": 2.8519593613933236,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004191441364335598,
|
|
"loss": 5.053,
|
|
"mean_token_accuracy": 0.20537354052066803,
|
|
"num_tokens": 65252513.0,
|
|
"step": 31440
|
|
},
|
|
{
|
|
"entropy": 5.370380830764771,
|
|
"epoch": 2.852412917271408,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00041911929036139457,
|
|
"loss": 5.086,
|
|
"mean_token_accuracy": 0.20023019462823868,
|
|
"num_tokens": 65262695.0,
|
|
"step": 31445
|
|
},
|
|
{
|
|
"entropy": 5.471360063552856,
|
|
"epoch": 2.852866473149492,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00041909444130880553,
|
|
"loss": 5.1504,
|
|
"mean_token_accuracy": 0.19864822477102279,
|
|
"num_tokens": 65274131.0,
|
|
"step": 31450
|
|
},
|
|
{
|
|
"entropy": 5.410283470153809,
|
|
"epoch": 2.853320029027576,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00041906958927630673,
|
|
"loss": 5.0773,
|
|
"mean_token_accuracy": 0.20402240753173828,
|
|
"num_tokens": 65285080.0,
|
|
"step": 31455
|
|
},
|
|
{
|
|
"entropy": 5.545388460159302,
|
|
"epoch": 2.8537735849056602,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004190447342644122,
|
|
"loss": 5.2753,
|
|
"mean_token_accuracy": 0.19547655284404755,
|
|
"num_tokens": 65296512.0,
|
|
"step": 31460
|
|
},
|
|
{
|
|
"entropy": 5.423305225372315,
|
|
"epoch": 2.8542271407837445,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004190198762736358,
|
|
"loss": 5.0021,
|
|
"mean_token_accuracy": 0.21280923038721083,
|
|
"num_tokens": 65306054.0,
|
|
"step": 31465
|
|
},
|
|
{
|
|
"entropy": 5.327408123016357,
|
|
"epoch": 2.8546806966618288,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004189950153044917,
|
|
"loss": 5.0518,
|
|
"mean_token_accuracy": 0.2034689500927925,
|
|
"num_tokens": 65315046.0,
|
|
"step": 31470
|
|
},
|
|
{
|
|
"entropy": 5.4276323318481445,
|
|
"epoch": 2.855134252539913,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004189701513574939,
|
|
"loss": 5.0185,
|
|
"mean_token_accuracy": 0.2008647844195366,
|
|
"num_tokens": 65325482.0,
|
|
"step": 31475
|
|
},
|
|
{
|
|
"entropy": 5.398829984664917,
|
|
"epoch": 2.8555878084179973,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004189452844331567,
|
|
"loss": 4.9804,
|
|
"mean_token_accuracy": 0.20303141325712204,
|
|
"num_tokens": 65335518.0,
|
|
"step": 31480
|
|
},
|
|
{
|
|
"entropy": 5.441408729553222,
|
|
"epoch": 2.856041364296081,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00041892041453199443,
|
|
"loss": 5.1363,
|
|
"mean_token_accuracy": 0.19862606823444368,
|
|
"num_tokens": 65346079.0,
|
|
"step": 31485
|
|
},
|
|
{
|
|
"entropy": 5.407349014282227,
|
|
"epoch": 2.8564949201741654,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004188955416545212,
|
|
"loss": 5.0469,
|
|
"mean_token_accuracy": 0.20119009912014008,
|
|
"num_tokens": 65356719.0,
|
|
"step": 31490
|
|
},
|
|
{
|
|
"entropy": 5.432226848602295,
|
|
"epoch": 2.8569484760522497,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004188706658012516,
|
|
"loss": 5.0934,
|
|
"mean_token_accuracy": 0.1989014595746994,
|
|
"num_tokens": 65367877.0,
|
|
"step": 31495
|
|
},
|
|
{
|
|
"entropy": 5.478250789642334,
|
|
"epoch": 2.857402031930334,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00041884578697269994,
|
|
"loss": 5.1408,
|
|
"mean_token_accuracy": 0.1941220358014107,
|
|
"num_tokens": 65379624.0,
|
|
"step": 31500
|
|
},
|
|
{
|
|
"entropy": 5.465831995010376,
|
|
"epoch": 2.8578555878084178,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004188209051693807,
|
|
"loss": 5.1267,
|
|
"mean_token_accuracy": 0.20182569324970245,
|
|
"num_tokens": 65390417.0,
|
|
"step": 31505
|
|
},
|
|
{
|
|
"entropy": 5.291795825958252,
|
|
"epoch": 2.858309143686502,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00041879602039180856,
|
|
"loss": 4.9142,
|
|
"mean_token_accuracy": 0.21135148257017136,
|
|
"num_tokens": 65401681.0,
|
|
"step": 31510
|
|
},
|
|
{
|
|
"entropy": 5.395376300811767,
|
|
"epoch": 2.8587626995645863,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00041877113264049805,
|
|
"loss": 5.0384,
|
|
"mean_token_accuracy": 0.20547031462192536,
|
|
"num_tokens": 65412520.0,
|
|
"step": 31515
|
|
},
|
|
{
|
|
"entropy": 5.3982359886169435,
|
|
"epoch": 2.8592162554426706,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00041874624191596383,
|
|
"loss": 5.0667,
|
|
"mean_token_accuracy": 0.20560586899518968,
|
|
"num_tokens": 65423201.0,
|
|
"step": 31520
|
|
},
|
|
{
|
|
"entropy": 5.376867055892944,
|
|
"epoch": 2.859669811320755,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004187213482187207,
|
|
"loss": 5.0794,
|
|
"mean_token_accuracy": 0.19964115023612977,
|
|
"num_tokens": 65432778.0,
|
|
"step": 31525
|
|
},
|
|
{
|
|
"entropy": 5.509898996353149,
|
|
"epoch": 2.860123367198839,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004186964515492835,
|
|
"loss": 5.1,
|
|
"mean_token_accuracy": 0.20295303463935851,
|
|
"num_tokens": 65442323.0,
|
|
"step": 31530
|
|
},
|
|
{
|
|
"entropy": 5.427868986129761,
|
|
"epoch": 2.8605769230769234,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004186715519081671,
|
|
"loss": 5.0684,
|
|
"mean_token_accuracy": 0.20548560619354247,
|
|
"num_tokens": 65451980.0,
|
|
"step": 31535
|
|
},
|
|
{
|
|
"entropy": 5.321336269378662,
|
|
"epoch": 2.861030478955007,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004186466492958864,
|
|
"loss": 5.0005,
|
|
"mean_token_accuracy": 0.20419093817472458,
|
|
"num_tokens": 65463359.0,
|
|
"step": 31540
|
|
},
|
|
{
|
|
"entropy": 5.4222643852233885,
|
|
"epoch": 2.8614840348330914,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004186217437129562,
|
|
"loss": 5.097,
|
|
"mean_token_accuracy": 0.20022185295820236,
|
|
"num_tokens": 65474155.0,
|
|
"step": 31545
|
|
},
|
|
{
|
|
"entropy": 5.435354804992675,
|
|
"epoch": 2.8619375907111757,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00041859683515989196,
|
|
"loss": 5.0222,
|
|
"mean_token_accuracy": 0.2091570019721985,
|
|
"num_tokens": 65484884.0,
|
|
"step": 31550
|
|
},
|
|
{
|
|
"entropy": 5.42715163230896,
|
|
"epoch": 2.8623911465892595,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00041857192363720845,
|
|
"loss": 5.0826,
|
|
"mean_token_accuracy": 0.20704313218593598,
|
|
"num_tokens": 65494380.0,
|
|
"step": 31555
|
|
},
|
|
{
|
|
"entropy": 5.418828916549683,
|
|
"epoch": 2.862844702467344,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004185470091454211,
|
|
"loss": 5.0715,
|
|
"mean_token_accuracy": 0.20242948085069656,
|
|
"num_tokens": 65505735.0,
|
|
"step": 31560
|
|
},
|
|
{
|
|
"entropy": 5.480842351913452,
|
|
"epoch": 2.863298258345428,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004185220916850449,
|
|
"loss": 5.0221,
|
|
"mean_token_accuracy": 0.2001458689570427,
|
|
"num_tokens": 65515956.0,
|
|
"step": 31565
|
|
},
|
|
{
|
|
"entropy": 5.371691656112671,
|
|
"epoch": 2.8637518142235123,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00041849717125659537,
|
|
"loss": 4.9846,
|
|
"mean_token_accuracy": 0.2029000401496887,
|
|
"num_tokens": 65526369.0,
|
|
"step": 31570
|
|
},
|
|
{
|
|
"entropy": 5.361418533325195,
|
|
"epoch": 2.8642053701015966,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004184722478605877,
|
|
"loss": 5.0322,
|
|
"mean_token_accuracy": 0.2048902466893196,
|
|
"num_tokens": 65536032.0,
|
|
"step": 31575
|
|
},
|
|
{
|
|
"entropy": 5.3768463134765625,
|
|
"epoch": 2.864658925979681,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004184473214975374,
|
|
"loss": 5.0774,
|
|
"mean_token_accuracy": 0.197220116853714,
|
|
"num_tokens": 65546121.0,
|
|
"step": 31580
|
|
},
|
|
{
|
|
"entropy": 5.432025289535522,
|
|
"epoch": 2.865112481857765,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00041842239216795994,
|
|
"loss": 5.0326,
|
|
"mean_token_accuracy": 0.203322134912014,
|
|
"num_tokens": 65555915.0,
|
|
"step": 31585
|
|
},
|
|
{
|
|
"entropy": 5.452295637130737,
|
|
"epoch": 2.865566037735849,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00041839745987237086,
|
|
"loss": 5.0829,
|
|
"mean_token_accuracy": 0.19709926396608352,
|
|
"num_tokens": 65566267.0,
|
|
"step": 31590
|
|
},
|
|
{
|
|
"entropy": 5.4483277797698975,
|
|
"epoch": 2.866019593613933,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004183725246112857,
|
|
"loss": 5.056,
|
|
"mean_token_accuracy": 0.20674380362033845,
|
|
"num_tokens": 65577126.0,
|
|
"step": 31595
|
|
},
|
|
{
|
|
"entropy": 5.472174596786499,
|
|
"epoch": 2.8664731494920175,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00041834758638522034,
|
|
"loss": 5.1649,
|
|
"mean_token_accuracy": 0.19020292311906814,
|
|
"num_tokens": 65587158.0,
|
|
"step": 31600
|
|
},
|
|
{
|
|
"entropy": 5.427806758880616,
|
|
"epoch": 2.8669267053701017,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00041832264519469026,
|
|
"loss": 5.0671,
|
|
"mean_token_accuracy": 0.19991413205862046,
|
|
"num_tokens": 65597720.0,
|
|
"step": 31605
|
|
},
|
|
{
|
|
"entropy": 5.488526248931885,
|
|
"epoch": 2.8673802612481856,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00041829770104021143,
|
|
"loss": 5.1014,
|
|
"mean_token_accuracy": 0.20070147514343262,
|
|
"num_tokens": 65607409.0,
|
|
"step": 31610
|
|
},
|
|
{
|
|
"entropy": 5.4044232845306395,
|
|
"epoch": 2.86783381712627,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00041827275392229956,
|
|
"loss": 5.0098,
|
|
"mean_token_accuracy": 0.21103212535381316,
|
|
"num_tokens": 65616785.0,
|
|
"step": 31615
|
|
},
|
|
{
|
|
"entropy": 5.4074146270751955,
|
|
"epoch": 2.868287373004354,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004182478038414706,
|
|
"loss": 5.1234,
|
|
"mean_token_accuracy": 0.19729211628437043,
|
|
"num_tokens": 65625794.0,
|
|
"step": 31620
|
|
},
|
|
{
|
|
"entropy": 5.3480761528015135,
|
|
"epoch": 2.8687409288824384,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00041822285079824056,
|
|
"loss": 4.9424,
|
|
"mean_token_accuracy": 0.21056529581546785,
|
|
"num_tokens": 65635789.0,
|
|
"step": 31625
|
|
},
|
|
{
|
|
"entropy": 5.490546131134034,
|
|
"epoch": 2.8691944847605226,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004181978947931256,
|
|
"loss": 5.1806,
|
|
"mean_token_accuracy": 0.19727547019720076,
|
|
"num_tokens": 65646266.0,
|
|
"step": 31630
|
|
},
|
|
{
|
|
"entropy": 5.431754779815674,
|
|
"epoch": 2.869648040638607,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004181729358266415,
|
|
"loss": 5.0524,
|
|
"mean_token_accuracy": 0.20150660574436188,
|
|
"num_tokens": 65656538.0,
|
|
"step": 31635
|
|
},
|
|
{
|
|
"entropy": 5.485798454284668,
|
|
"epoch": 2.8701015965166907,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00041814797389930474,
|
|
"loss": 5.0848,
|
|
"mean_token_accuracy": 0.2072420284152031,
|
|
"num_tokens": 65666926.0,
|
|
"step": 31640
|
|
},
|
|
{
|
|
"entropy": 5.429387855529785,
|
|
"epoch": 2.870555152394775,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004181230090116313,
|
|
"loss": 5.0524,
|
|
"mean_token_accuracy": 0.19737420827150345,
|
|
"num_tokens": 65677219.0,
|
|
"step": 31645
|
|
},
|
|
{
|
|
"entropy": 5.437917757034302,
|
|
"epoch": 2.8710087082728593,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00041809804116413763,
|
|
"loss": 5.1169,
|
|
"mean_token_accuracy": 0.19299848079681398,
|
|
"num_tokens": 65688281.0,
|
|
"step": 31650
|
|
},
|
|
{
|
|
"entropy": 5.541569423675537,
|
|
"epoch": 2.8714622641509435,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00041807307035734,
|
|
"loss": 5.1674,
|
|
"mean_token_accuracy": 0.19891929030418395,
|
|
"num_tokens": 65698815.0,
|
|
"step": 31655
|
|
},
|
|
{
|
|
"entropy": 5.444745492935181,
|
|
"epoch": 2.8719158200290273,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004180480965917548,
|
|
"loss": 5.1053,
|
|
"mean_token_accuracy": 0.19675618261098862,
|
|
"num_tokens": 65709481.0,
|
|
"step": 31660
|
|
},
|
|
{
|
|
"entropy": 5.479586839675903,
|
|
"epoch": 2.8723693759071116,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00041802311986789854,
|
|
"loss": 5.0604,
|
|
"mean_token_accuracy": 0.19360993951559066,
|
|
"num_tokens": 65720561.0,
|
|
"step": 31665
|
|
},
|
|
{
|
|
"entropy": 5.452166128158569,
|
|
"epoch": 2.872822931785196,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00041799814018628765,
|
|
"loss": 5.1062,
|
|
"mean_token_accuracy": 0.19473909437656403,
|
|
"num_tokens": 65730384.0,
|
|
"step": 31670
|
|
},
|
|
{
|
|
"entropy": 5.442211723327636,
|
|
"epoch": 2.87327648766328,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00041797315754743883,
|
|
"loss": 5.066,
|
|
"mean_token_accuracy": 0.20454145818948746,
|
|
"num_tokens": 65740711.0,
|
|
"step": 31675
|
|
},
|
|
{
|
|
"entropy": 5.554357051849365,
|
|
"epoch": 2.8737300435413644,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00041794817195186867,
|
|
"loss": 5.1839,
|
|
"mean_token_accuracy": 0.19674251228570938,
|
|
"num_tokens": 65751033.0,
|
|
"step": 31680
|
|
},
|
|
{
|
|
"entropy": 5.467114543914795,
|
|
"epoch": 2.8741835994194487,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004179231834000939,
|
|
"loss": 5.1518,
|
|
"mean_token_accuracy": 0.19392010867595671,
|
|
"num_tokens": 65761500.0,
|
|
"step": 31685
|
|
},
|
|
{
|
|
"entropy": 5.3722740650177006,
|
|
"epoch": 2.8746371552975325,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00041789819189263117,
|
|
"loss": 4.9774,
|
|
"mean_token_accuracy": 0.21077350080013274,
|
|
"num_tokens": 65771095.0,
|
|
"step": 31690
|
|
},
|
|
{
|
|
"entropy": 5.390261125564575,
|
|
"epoch": 2.8750907111756168,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00041787319742999756,
|
|
"loss": 5.0469,
|
|
"mean_token_accuracy": 0.2051885098218918,
|
|
"num_tokens": 65782058.0,
|
|
"step": 31695
|
|
},
|
|
{
|
|
"entropy": 5.416783237457276,
|
|
"epoch": 2.875544267053701,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004178482000127098,
|
|
"loss": 5.086,
|
|
"mean_token_accuracy": 0.20798977464437485,
|
|
"num_tokens": 65791710.0,
|
|
"step": 31700
|
|
},
|
|
{
|
|
"entropy": 5.479998159408569,
|
|
"epoch": 2.8759978229317853,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004178231996412848,
|
|
"loss": 5.1322,
|
|
"mean_token_accuracy": 0.19244628846645356,
|
|
"num_tokens": 65802180.0,
|
|
"step": 31705
|
|
},
|
|
{
|
|
"entropy": 5.393694067001343,
|
|
"epoch": 2.876451378809869,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004177981963162396,
|
|
"loss": 5.0091,
|
|
"mean_token_accuracy": 0.2094086602330208,
|
|
"num_tokens": 65812998.0,
|
|
"step": 31710
|
|
},
|
|
{
|
|
"entropy": 5.4486016750335695,
|
|
"epoch": 2.8769049346879534,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004177731900380914,
|
|
"loss": 5.094,
|
|
"mean_token_accuracy": 0.1978503108024597,
|
|
"num_tokens": 65824210.0,
|
|
"step": 31715
|
|
},
|
|
{
|
|
"entropy": 5.398553371429443,
|
|
"epoch": 2.8773584905660377,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004177481808073572,
|
|
"loss": 5.0216,
|
|
"mean_token_accuracy": 0.20683513432741166,
|
|
"num_tokens": 65834322.0,
|
|
"step": 31720
|
|
},
|
|
{
|
|
"entropy": 5.428415393829345,
|
|
"epoch": 2.877812046444122,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00041772316862455426,
|
|
"loss": 4.9943,
|
|
"mean_token_accuracy": 0.20867783278226854,
|
|
"num_tokens": 65845347.0,
|
|
"step": 31725
|
|
},
|
|
{
|
|
"entropy": 5.433452987670899,
|
|
"epoch": 2.878265602322206,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00041769815349019986,
|
|
"loss": 5.0975,
|
|
"mean_token_accuracy": 0.20005858540534974,
|
|
"num_tokens": 65855616.0,
|
|
"step": 31730
|
|
},
|
|
{
|
|
"entropy": 5.419916200637817,
|
|
"epoch": 2.8787191582002905,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00041767313540481125,
|
|
"loss": 5.0539,
|
|
"mean_token_accuracy": 0.20045070201158524,
|
|
"num_tokens": 65865542.0,
|
|
"step": 31735
|
|
},
|
|
{
|
|
"entropy": 5.381126785278321,
|
|
"epoch": 2.8791727140783747,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004176481143689058,
|
|
"loss": 5.0358,
|
|
"mean_token_accuracy": 0.20027120113372804,
|
|
"num_tokens": 65874478.0,
|
|
"step": 31740
|
|
},
|
|
{
|
|
"entropy": 5.473600625991821,
|
|
"epoch": 2.8796262699564585,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004176230903830011,
|
|
"loss": 5.0967,
|
|
"mean_token_accuracy": 0.2018531307578087,
|
|
"num_tokens": 65884609.0,
|
|
"step": 31745
|
|
},
|
|
{
|
|
"entropy": 5.420750761032105,
|
|
"epoch": 2.880079825834543,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004175980634476145,
|
|
"loss": 5.0561,
|
|
"mean_token_accuracy": 0.20726320296525955,
|
|
"num_tokens": 65894486.0,
|
|
"step": 31750
|
|
},
|
|
{
|
|
"entropy": 5.35667576789856,
|
|
"epoch": 2.880533381712627,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004175730335632635,
|
|
"loss": 4.9961,
|
|
"mean_token_accuracy": 0.20610481351614,
|
|
"num_tokens": 65904643.0,
|
|
"step": 31755
|
|
},
|
|
{
|
|
"entropy": 5.319256067276001,
|
|
"epoch": 2.8809869375907113,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00041754800073046593,
|
|
"loss": 5.0158,
|
|
"mean_token_accuracy": 0.2114411324262619,
|
|
"num_tokens": 65914107.0,
|
|
"step": 31760
|
|
},
|
|
{
|
|
"entropy": 5.374335765838623,
|
|
"epoch": 2.881440493468795,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004175229649497394,
|
|
"loss": 5.0061,
|
|
"mean_token_accuracy": 0.20349210053682326,
|
|
"num_tokens": 65925112.0,
|
|
"step": 31765
|
|
},
|
|
{
|
|
"entropy": 5.441638565063476,
|
|
"epoch": 2.8818940493468794,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004174979262216016,
|
|
"loss": 5.0746,
|
|
"mean_token_accuracy": 0.20233961194753647,
|
|
"num_tokens": 65934624.0,
|
|
"step": 31770
|
|
},
|
|
{
|
|
"entropy": 5.443161249160767,
|
|
"epoch": 2.8823476052249637,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004174728845465704,
|
|
"loss": 5.076,
|
|
"mean_token_accuracy": 0.19949449449777604,
|
|
"num_tokens": 65945951.0,
|
|
"step": 31775
|
|
},
|
|
{
|
|
"entropy": 5.365787410736084,
|
|
"epoch": 2.882801161103048,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004174478399251636,
|
|
"loss": 4.9767,
|
|
"mean_token_accuracy": 0.2107846572995186,
|
|
"num_tokens": 65956871.0,
|
|
"step": 31780
|
|
},
|
|
{
|
|
"entropy": 5.493707323074341,
|
|
"epoch": 2.8832547169811322,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004174227923578992,
|
|
"loss": 5.2076,
|
|
"mean_token_accuracy": 0.19496545791625977,
|
|
"num_tokens": 65967814.0,
|
|
"step": 31785
|
|
},
|
|
{
|
|
"entropy": 5.45697865486145,
|
|
"epoch": 2.8837082728592165,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004173977418452952,
|
|
"loss": 5.089,
|
|
"mean_token_accuracy": 0.19353815764188767,
|
|
"num_tokens": 65978118.0,
|
|
"step": 31790
|
|
},
|
|
{
|
|
"entropy": 5.42093448638916,
|
|
"epoch": 2.8841618287373003,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00041737268838786955,
|
|
"loss": 5.0386,
|
|
"mean_token_accuracy": 0.20277292281389236,
|
|
"num_tokens": 65988240.0,
|
|
"step": 31795
|
|
},
|
|
{
|
|
"entropy": 5.418774080276489,
|
|
"epoch": 2.8846153846153846,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004173476319861404,
|
|
"loss": 5.0039,
|
|
"mean_token_accuracy": 0.20215294808149337,
|
|
"num_tokens": 65998126.0,
|
|
"step": 31800
|
|
},
|
|
{
|
|
"entropy": 5.417162322998047,
|
|
"epoch": 2.885068940493469,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004173225726406261,
|
|
"loss": 5.0754,
|
|
"mean_token_accuracy": 0.2047414407134056,
|
|
"num_tokens": 66009118.0,
|
|
"step": 31805
|
|
},
|
|
{
|
|
"entropy": 5.421855354309082,
|
|
"epoch": 2.885522496371553,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00041729751035184457,
|
|
"loss": 5.1275,
|
|
"mean_token_accuracy": 0.19839080572128295,
|
|
"num_tokens": 66019340.0,
|
|
"step": 31810
|
|
},
|
|
{
|
|
"entropy": 5.398412704467773,
|
|
"epoch": 2.885976052249637,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00041727244512031425,
|
|
"loss": 5.0199,
|
|
"mean_token_accuracy": 0.20589553117752074,
|
|
"num_tokens": 66029784.0,
|
|
"step": 31815
|
|
},
|
|
{
|
|
"entropy": 5.484686613082886,
|
|
"epoch": 2.886429608127721,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004172473769465536,
|
|
"loss": 5.1751,
|
|
"mean_token_accuracy": 0.1919332593679428,
|
|
"num_tokens": 66039987.0,
|
|
"step": 31820
|
|
},
|
|
{
|
|
"entropy": 5.442124319076538,
|
|
"epoch": 2.8868831640058055,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00041722230583108097,
|
|
"loss": 5.1059,
|
|
"mean_token_accuracy": 0.20559971928596496,
|
|
"num_tokens": 66049150.0,
|
|
"step": 31825
|
|
},
|
|
{
|
|
"entropy": 5.446267747879029,
|
|
"epoch": 2.8873367198838897,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00041719723177441467,
|
|
"loss": 5.1131,
|
|
"mean_token_accuracy": 0.20442284047603607,
|
|
"num_tokens": 66060719.0,
|
|
"step": 31830
|
|
},
|
|
{
|
|
"entropy": 5.468173551559448,
|
|
"epoch": 2.887790275761974,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004171721547770735,
|
|
"loss": 5.1019,
|
|
"mean_token_accuracy": 0.19944203794002532,
|
|
"num_tokens": 66071126.0,
|
|
"step": 31835
|
|
},
|
|
{
|
|
"entropy": 5.422418212890625,
|
|
"epoch": 2.8882438316400583,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004171470748395759,
|
|
"loss": 5.0051,
|
|
"mean_token_accuracy": 0.20647664815187455,
|
|
"num_tokens": 66080928.0,
|
|
"step": 31840
|
|
},
|
|
{
|
|
"entropy": 5.434895610809326,
|
|
"epoch": 2.888697387518142,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004171219919624406,
|
|
"loss": 5.0732,
|
|
"mean_token_accuracy": 0.19993187487125397,
|
|
"num_tokens": 66090900.0,
|
|
"step": 31845
|
|
},
|
|
{
|
|
"entropy": 5.405395126342773,
|
|
"epoch": 2.8891509433962264,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00041709690614618624,
|
|
"loss": 5.0856,
|
|
"mean_token_accuracy": 0.19690482765436174,
|
|
"num_tokens": 66100720.0,
|
|
"step": 31850
|
|
},
|
|
{
|
|
"entropy": 5.398652458190918,
|
|
"epoch": 2.8896044992743106,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00041707181739133163,
|
|
"loss": 5.0802,
|
|
"mean_token_accuracy": 0.19854838997125626,
|
|
"num_tokens": 66110780.0,
|
|
"step": 31855
|
|
},
|
|
{
|
|
"entropy": 5.421828365325927,
|
|
"epoch": 2.890058055152395,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004170467256983957,
|
|
"loss": 5.0388,
|
|
"mean_token_accuracy": 0.2114819824695587,
|
|
"num_tokens": 66120976.0,
|
|
"step": 31860
|
|
},
|
|
{
|
|
"entropy": 5.426223278045654,
|
|
"epoch": 2.8905116110304787,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004170216310678973,
|
|
"loss": 5.065,
|
|
"mean_token_accuracy": 0.2054508998990059,
|
|
"num_tokens": 66130221.0,
|
|
"step": 31865
|
|
},
|
|
{
|
|
"entropy": 5.3638246059417725,
|
|
"epoch": 2.890965166908563,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00041699653350035527,
|
|
"loss": 4.9901,
|
|
"mean_token_accuracy": 0.211863711476326,
|
|
"num_tokens": 66140060.0,
|
|
"step": 31870
|
|
},
|
|
{
|
|
"entropy": 5.405194854736328,
|
|
"epoch": 2.8914187227866472,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00041697143299628886,
|
|
"loss": 5.0808,
|
|
"mean_token_accuracy": 0.20767352730035782,
|
|
"num_tokens": 66151640.0,
|
|
"step": 31875
|
|
},
|
|
{
|
|
"entropy": 5.425278568267823,
|
|
"epoch": 2.8918722786647315,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00041694632955621697,
|
|
"loss": 5.0472,
|
|
"mean_token_accuracy": 0.20720952600240708,
|
|
"num_tokens": 66162923.0,
|
|
"step": 31880
|
|
},
|
|
{
|
|
"entropy": 5.462364292144775,
|
|
"epoch": 2.8923258345428158,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00041692122318065885,
|
|
"loss": 5.094,
|
|
"mean_token_accuracy": 0.20296721309423446,
|
|
"num_tokens": 66173108.0,
|
|
"step": 31885
|
|
},
|
|
{
|
|
"entropy": 5.411975145339966,
|
|
"epoch": 2.8927793904209,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00041689611387013363,
|
|
"loss": 5.0128,
|
|
"mean_token_accuracy": 0.21007219702005386,
|
|
"num_tokens": 66185280.0,
|
|
"step": 31890
|
|
},
|
|
{
|
|
"entropy": 5.3814231872558596,
|
|
"epoch": 2.8932329462989843,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004168710016251606,
|
|
"loss": 5.0406,
|
|
"mean_token_accuracy": 0.1984519764780998,
|
|
"num_tokens": 66196020.0,
|
|
"step": 31895
|
|
},
|
|
{
|
|
"entropy": 5.359273195266724,
|
|
"epoch": 2.893686502177068,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004168458864462592,
|
|
"loss": 4.9725,
|
|
"mean_token_accuracy": 0.20406593829393388,
|
|
"num_tokens": 66205753.0,
|
|
"step": 31900
|
|
},
|
|
{
|
|
"entropy": 5.426529216766357,
|
|
"epoch": 2.8941400580551524,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00041682076833394864,
|
|
"loss": 5.1636,
|
|
"mean_token_accuracy": 0.19650042057037354,
|
|
"num_tokens": 66218415.0,
|
|
"step": 31905
|
|
},
|
|
{
|
|
"entropy": 5.440398550033569,
|
|
"epoch": 2.8945936139332367,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00041679564728874845,
|
|
"loss": 5.1412,
|
|
"mean_token_accuracy": 0.1973641648888588,
|
|
"num_tokens": 66228090.0,
|
|
"step": 31910
|
|
},
|
|
{
|
|
"entropy": 5.385549116134643,
|
|
"epoch": 2.8950471698113205,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004167705233111782,
|
|
"loss": 4.9969,
|
|
"mean_token_accuracy": 0.20975734889507294,
|
|
"num_tokens": 66237587.0,
|
|
"step": 31915
|
|
},
|
|
{
|
|
"entropy": 5.400952625274658,
|
|
"epoch": 2.8955007256894048,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00041674539640175733,
|
|
"loss": 5.0365,
|
|
"mean_token_accuracy": 0.20284364223480225,
|
|
"num_tokens": 66248162.0,
|
|
"step": 31920
|
|
},
|
|
{
|
|
"entropy": 5.341111850738526,
|
|
"epoch": 2.895954281567489,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004167202665610055,
|
|
"loss": 4.9952,
|
|
"mean_token_accuracy": 0.2113674223423004,
|
|
"num_tokens": 66258370.0,
|
|
"step": 31925
|
|
},
|
|
{
|
|
"entropy": 5.424095821380615,
|
|
"epoch": 2.8964078374455733,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00041669513378944254,
|
|
"loss": 5.0724,
|
|
"mean_token_accuracy": 0.2011097863316536,
|
|
"num_tokens": 66269267.0,
|
|
"step": 31930
|
|
},
|
|
{
|
|
"entropy": 5.513514184951783,
|
|
"epoch": 2.8968613933236576,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00041666999808758815,
|
|
"loss": 5.0831,
|
|
"mean_token_accuracy": 0.2008492171764374,
|
|
"num_tokens": 66280077.0,
|
|
"step": 31935
|
|
},
|
|
{
|
|
"entropy": 5.398401832580566,
|
|
"epoch": 2.897314949201742,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000416644859455962,
|
|
"loss": 5.0333,
|
|
"mean_token_accuracy": 0.20506357103586198,
|
|
"num_tokens": 66291678.0,
|
|
"step": 31940
|
|
},
|
|
{
|
|
"entropy": 5.397225189208984,
|
|
"epoch": 2.897768505079826,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004166197178950841,
|
|
"loss": 5.0491,
|
|
"mean_token_accuracy": 0.20006881803274154,
|
|
"num_tokens": 66302046.0,
|
|
"step": 31945
|
|
},
|
|
{
|
|
"entropy": 5.381431818008423,
|
|
"epoch": 2.89822206095791,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00041659457340547436,
|
|
"loss": 5.0565,
|
|
"mean_token_accuracy": 0.20004966259002685,
|
|
"num_tokens": 66311888.0,
|
|
"step": 31950
|
|
},
|
|
{
|
|
"entropy": 5.379310941696167,
|
|
"epoch": 2.898675616835994,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00041656942598765275,
|
|
"loss": 5.0173,
|
|
"mean_token_accuracy": 0.2044637218117714,
|
|
"num_tokens": 66321507.0,
|
|
"step": 31955
|
|
},
|
|
{
|
|
"entropy": 5.336543273925781,
|
|
"epoch": 2.8991291727140784,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00041654427564213924,
|
|
"loss": 5.0007,
|
|
"mean_token_accuracy": 0.20785539746284484,
|
|
"num_tokens": 66331458.0,
|
|
"step": 31960
|
|
},
|
|
{
|
|
"entropy": 5.406649732589722,
|
|
"epoch": 2.8995827285921627,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00041651912236945416,
|
|
"loss": 5.0421,
|
|
"mean_token_accuracy": 0.20679719150066375,
|
|
"num_tokens": 66340875.0,
|
|
"step": 31965
|
|
},
|
|
{
|
|
"entropy": 5.407155752182007,
|
|
"epoch": 2.9000362844702465,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00041649396617011753,
|
|
"loss": 5.1248,
|
|
"mean_token_accuracy": 0.19466441720724106,
|
|
"num_tokens": 66350784.0,
|
|
"step": 31970
|
|
},
|
|
{
|
|
"entropy": 5.399053382873535,
|
|
"epoch": 2.900489840348331,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004164688070446496,
|
|
"loss": 5.1251,
|
|
"mean_token_accuracy": 0.1942175880074501,
|
|
"num_tokens": 66361591.0,
|
|
"step": 31975
|
|
},
|
|
{
|
|
"entropy": 5.452833938598633,
|
|
"epoch": 2.900943396226415,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004164436449935707,
|
|
"loss": 5.0022,
|
|
"mean_token_accuracy": 0.20774240493774415,
|
|
"num_tokens": 66371540.0,
|
|
"step": 31980
|
|
},
|
|
{
|
|
"entropy": 5.434154415130616,
|
|
"epoch": 2.9013969521044993,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00041641848001740126,
|
|
"loss": 5.0673,
|
|
"mean_token_accuracy": 0.20503420233726502,
|
|
"num_tokens": 66382053.0,
|
|
"step": 31985
|
|
},
|
|
{
|
|
"entropy": 5.383768033981323,
|
|
"epoch": 2.9018505079825836,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004163933121166615,
|
|
"loss": 5.0325,
|
|
"mean_token_accuracy": 0.20653424561023712,
|
|
"num_tokens": 66392563.0,
|
|
"step": 31990
|
|
},
|
|
{
|
|
"entropy": 5.402456331253052,
|
|
"epoch": 2.902304063860668,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000416368141291872,
|
|
"loss": 4.9888,
|
|
"mean_token_accuracy": 0.2061233028769493,
|
|
"num_tokens": 66403582.0,
|
|
"step": 31995
|
|
},
|
|
{
|
|
"entropy": 5.309687376022339,
|
|
"epoch": 2.9027576197387517,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00041634296754355346,
|
|
"loss": 4.9581,
|
|
"mean_token_accuracy": 0.20505453646183014,
|
|
"num_tokens": 66413713.0,
|
|
"step": 32000
|
|
},
|
|
{
|
|
"entropy": 5.358116292953492,
|
|
"epoch": 2.903211175616836,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004163177908722262,
|
|
"loss": 5.0415,
|
|
"mean_token_accuracy": 0.2004800796508789,
|
|
"num_tokens": 66424802.0,
|
|
"step": 32005
|
|
},
|
|
{
|
|
"entropy": 5.369229459762574,
|
|
"epoch": 2.90366473149492,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00041629261127841105,
|
|
"loss": 4.994,
|
|
"mean_token_accuracy": 0.20663417279720306,
|
|
"num_tokens": 66434716.0,
|
|
"step": 32010
|
|
},
|
|
{
|
|
"entropy": 5.408300447463989,
|
|
"epoch": 2.9041182873730045,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00041626742876262876,
|
|
"loss": 5.0537,
|
|
"mean_token_accuracy": 0.20098212659358977,
|
|
"num_tokens": 66445725.0,
|
|
"step": 32015
|
|
},
|
|
{
|
|
"entropy": 5.48498010635376,
|
|
"epoch": 2.9045718432510883,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00041624224332539997,
|
|
"loss": 5.1174,
|
|
"mean_token_accuracy": 0.19503306746482849,
|
|
"num_tokens": 66457492.0,
|
|
"step": 32020
|
|
},
|
|
{
|
|
"entropy": 5.46607551574707,
|
|
"epoch": 2.9050253991291726,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004162170549672455,
|
|
"loss": 5.025,
|
|
"mean_token_accuracy": 0.20545709431171416,
|
|
"num_tokens": 66467490.0,
|
|
"step": 32025
|
|
},
|
|
{
|
|
"entropy": 5.4697089195251465,
|
|
"epoch": 2.905478955007257,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004161918636886865,
|
|
"loss": 5.1463,
|
|
"mean_token_accuracy": 0.19862099289894103,
|
|
"num_tokens": 66478160.0,
|
|
"step": 32030
|
|
},
|
|
{
|
|
"entropy": 5.48202338218689,
|
|
"epoch": 2.905932510885341,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004161666694902437,
|
|
"loss": 5.049,
|
|
"mean_token_accuracy": 0.2001396283507347,
|
|
"num_tokens": 66488181.0,
|
|
"step": 32035
|
|
},
|
|
{
|
|
"entropy": 5.439352369308471,
|
|
"epoch": 2.9063860667634254,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004161414723724383,
|
|
"loss": 5.114,
|
|
"mean_token_accuracy": 0.2053363025188446,
|
|
"num_tokens": 66498507.0,
|
|
"step": 32040
|
|
},
|
|
{
|
|
"entropy": 5.318047142028808,
|
|
"epoch": 2.9068396226415096,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004161162723357912,
|
|
"loss": 4.9962,
|
|
"mean_token_accuracy": 0.20452762097120286,
|
|
"num_tokens": 66507752.0,
|
|
"step": 32045
|
|
},
|
|
{
|
|
"entropy": 5.384854459762574,
|
|
"epoch": 2.9072931785195935,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004160910693808236,
|
|
"loss": 5.0535,
|
|
"mean_token_accuracy": 0.1974830761551857,
|
|
"num_tokens": 66519360.0,
|
|
"step": 32050
|
|
},
|
|
{
|
|
"entropy": 5.503075885772705,
|
|
"epoch": 2.9077467343976777,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00041606586350805686,
|
|
"loss": 5.1315,
|
|
"mean_token_accuracy": 0.2007386401295662,
|
|
"num_tokens": 66529790.0,
|
|
"step": 32055
|
|
},
|
|
{
|
|
"entropy": 5.3849364757537845,
|
|
"epoch": 2.908200290275762,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000416040654718012,
|
|
"loss": 5.0004,
|
|
"mean_token_accuracy": 0.21189829111099243,
|
|
"num_tokens": 66539617.0,
|
|
"step": 32060
|
|
},
|
|
{
|
|
"entropy": 5.367508411407471,
|
|
"epoch": 2.9086538461538463,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00041601544301121045,
|
|
"loss": 5.0064,
|
|
"mean_token_accuracy": 0.20622930079698562,
|
|
"num_tokens": 66549861.0,
|
|
"step": 32065
|
|
},
|
|
{
|
|
"entropy": 5.487117195129395,
|
|
"epoch": 2.90910740203193,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004159902283881737,
|
|
"loss": 5.1662,
|
|
"mean_token_accuracy": 0.20390439182519912,
|
|
"num_tokens": 66560388.0,
|
|
"step": 32070
|
|
},
|
|
{
|
|
"entropy": 5.495299816131592,
|
|
"epoch": 2.9095609579100143,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000415965010849423,
|
|
"loss": 5.1376,
|
|
"mean_token_accuracy": 0.19583988040685654,
|
|
"num_tokens": 66570795.0,
|
|
"step": 32075
|
|
},
|
|
{
|
|
"entropy": 5.444519710540772,
|
|
"epoch": 2.9100145137880986,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00041593979039548,
|
|
"loss": 5.0675,
|
|
"mean_token_accuracy": 0.19887125492095947,
|
|
"num_tokens": 66580268.0,
|
|
"step": 32080
|
|
},
|
|
{
|
|
"entropy": 5.422425699234009,
|
|
"epoch": 2.910468069666183,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004159145670268662,
|
|
"loss": 5.1277,
|
|
"mean_token_accuracy": 0.20038248151540755,
|
|
"num_tokens": 66591192.0,
|
|
"step": 32085
|
|
},
|
|
{
|
|
"entropy": 5.450817728042603,
|
|
"epoch": 2.910921625544267,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004158893407441033,
|
|
"loss": 5.1224,
|
|
"mean_token_accuracy": 0.20433106869459153,
|
|
"num_tokens": 66600768.0,
|
|
"step": 32090
|
|
},
|
|
{
|
|
"entropy": 5.541464376449585,
|
|
"epoch": 2.9113751814223514,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00041586411154771285,
|
|
"loss": 5.1212,
|
|
"mean_token_accuracy": 0.19703042954206468,
|
|
"num_tokens": 66612207.0,
|
|
"step": 32095
|
|
},
|
|
{
|
|
"entropy": 5.339552927017212,
|
|
"epoch": 2.9118287373004357,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00041583887943821667,
|
|
"loss": 4.992,
|
|
"mean_token_accuracy": 0.20798822343349457,
|
|
"num_tokens": 66622175.0,
|
|
"step": 32100
|
|
},
|
|
{
|
|
"entropy": 5.395655250549316,
|
|
"epoch": 2.9122822931785195,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004158136444161367,
|
|
"loss": 5.0412,
|
|
"mean_token_accuracy": 0.19987685680389405,
|
|
"num_tokens": 66633936.0,
|
|
"step": 32105
|
|
},
|
|
{
|
|
"entropy": 5.473412084579468,
|
|
"epoch": 2.9127358490566038,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00041578840648199455,
|
|
"loss": 5.1116,
|
|
"mean_token_accuracy": 0.19331673234701158,
|
|
"num_tokens": 66643502.0,
|
|
"step": 32110
|
|
},
|
|
{
|
|
"entropy": 5.430240535736084,
|
|
"epoch": 2.913189404934688,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004157631656363124,
|
|
"loss": 5.0646,
|
|
"mean_token_accuracy": 0.2045750230550766,
|
|
"num_tokens": 66654890.0,
|
|
"step": 32115
|
|
},
|
|
{
|
|
"entropy": 5.465670585632324,
|
|
"epoch": 2.9136429608127723,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000415737921879612,
|
|
"loss": 5.1565,
|
|
"mean_token_accuracy": 0.18771313428878783,
|
|
"num_tokens": 66667037.0,
|
|
"step": 32120
|
|
},
|
|
{
|
|
"entropy": 5.421905994415283,
|
|
"epoch": 2.914096516690856,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00041571267521241554,
|
|
"loss": 5.0404,
|
|
"mean_token_accuracy": 0.20043586045503617,
|
|
"num_tokens": 66677291.0,
|
|
"step": 32125
|
|
},
|
|
{
|
|
"entropy": 5.370097303390503,
|
|
"epoch": 2.9145500725689404,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004156874256352451,
|
|
"loss": 4.9946,
|
|
"mean_token_accuracy": 0.2023351401090622,
|
|
"num_tokens": 66687421.0,
|
|
"step": 32130
|
|
},
|
|
{
|
|
"entropy": 5.525965785980224,
|
|
"epoch": 2.9150036284470247,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004156621731486228,
|
|
"loss": 5.1291,
|
|
"mean_token_accuracy": 0.19508872628211976,
|
|
"num_tokens": 66697190.0,
|
|
"step": 32135
|
|
},
|
|
{
|
|
"entropy": 5.4451584815979,
|
|
"epoch": 2.915457184325109,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000415636917753071,
|
|
"loss": 5.1315,
|
|
"mean_token_accuracy": 0.20065375417470932,
|
|
"num_tokens": 66707255.0,
|
|
"step": 32140
|
|
},
|
|
{
|
|
"entropy": 5.347908401489258,
|
|
"epoch": 2.915910740203193,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004156116594491119,
|
|
"loss": 4.9632,
|
|
"mean_token_accuracy": 0.20605600625276566,
|
|
"num_tokens": 66716451.0,
|
|
"step": 32145
|
|
},
|
|
{
|
|
"entropy": 5.401303958892822,
|
|
"epoch": 2.9163642960812775,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004155863982372678,
|
|
"loss": 5.0742,
|
|
"mean_token_accuracy": 0.20495266169309617,
|
|
"num_tokens": 66727157.0,
|
|
"step": 32150
|
|
},
|
|
{
|
|
"entropy": 5.4650962352752686,
|
|
"epoch": 2.9168178519593613,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00041556113411806117,
|
|
"loss": 5.0613,
|
|
"mean_token_accuracy": 0.20490677058696746,
|
|
"num_tokens": 66737523.0,
|
|
"step": 32155
|
|
},
|
|
{
|
|
"entropy": 5.42980637550354,
|
|
"epoch": 2.9172714078374455,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00041553586709201453,
|
|
"loss": 5.0708,
|
|
"mean_token_accuracy": 0.20509493798017503,
|
|
"num_tokens": 66748183.0,
|
|
"step": 32160
|
|
},
|
|
{
|
|
"entropy": 5.44272747039795,
|
|
"epoch": 2.91772496371553,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004155105971596503,
|
|
"loss": 5.0392,
|
|
"mean_token_accuracy": 0.2072732999920845,
|
|
"num_tokens": 66758794.0,
|
|
"step": 32165
|
|
},
|
|
{
|
|
"entropy": 5.493326950073242,
|
|
"epoch": 2.918178519593614,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00041548532432149105,
|
|
"loss": 5.1732,
|
|
"mean_token_accuracy": 0.2004552662372589,
|
|
"num_tokens": 66769916.0,
|
|
"step": 32170
|
|
},
|
|
{
|
|
"entropy": 5.408281373977661,
|
|
"epoch": 2.918632075471698,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004154600485780595,
|
|
"loss": 5.0624,
|
|
"mean_token_accuracy": 0.21089243292808532,
|
|
"num_tokens": 66779658.0,
|
|
"step": 32175
|
|
},
|
|
{
|
|
"entropy": 5.391109609603882,
|
|
"epoch": 2.919085631349782,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00041543476992987843,
|
|
"loss": 4.9942,
|
|
"mean_token_accuracy": 0.20724807679653168,
|
|
"num_tokens": 66788909.0,
|
|
"step": 32180
|
|
},
|
|
{
|
|
"entropy": 5.504585027694702,
|
|
"epoch": 2.9195391872278664,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00041540948837747056,
|
|
"loss": 5.111,
|
|
"mean_token_accuracy": 0.20148321092128754,
|
|
"num_tokens": 66799519.0,
|
|
"step": 32185
|
|
},
|
|
{
|
|
"entropy": 5.363579225540161,
|
|
"epoch": 2.9199927431059507,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004153842039213586,
|
|
"loss": 4.988,
|
|
"mean_token_accuracy": 0.20643852055072784,
|
|
"num_tokens": 66808915.0,
|
|
"step": 32190
|
|
},
|
|
{
|
|
"entropy": 5.408230829238891,
|
|
"epoch": 2.920446298984035,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004153589165620656,
|
|
"loss": 5.1174,
|
|
"mean_token_accuracy": 0.19771337658166885,
|
|
"num_tokens": 66818819.0,
|
|
"step": 32195
|
|
},
|
|
{
|
|
"entropy": 5.307103252410888,
|
|
"epoch": 2.9208998548621192,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00041533362630011435,
|
|
"loss": 4.9292,
|
|
"mean_token_accuracy": 0.21490803062915803,
|
|
"num_tokens": 66829274.0,
|
|
"step": 32200
|
|
},
|
|
{
|
|
"entropy": 5.480767726898193,
|
|
"epoch": 2.921353410740203,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000415308333136028,
|
|
"loss": 5.1052,
|
|
"mean_token_accuracy": 0.205857115983963,
|
|
"num_tokens": 66839659.0,
|
|
"step": 32205
|
|
},
|
|
{
|
|
"entropy": 5.453414583206177,
|
|
"epoch": 2.9218069666182873,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00041528303707032957,
|
|
"loss": 5.1239,
|
|
"mean_token_accuracy": 0.20307401716709136,
|
|
"num_tokens": 66850415.0,
|
|
"step": 32210
|
|
},
|
|
{
|
|
"entropy": 5.412446117401123,
|
|
"epoch": 2.9222605224963716,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004152577381035422,
|
|
"loss": 5.012,
|
|
"mean_token_accuracy": 0.2126409962773323,
|
|
"num_tokens": 66860663.0,
|
|
"step": 32215
|
|
},
|
|
{
|
|
"entropy": 5.481760454177857,
|
|
"epoch": 2.922714078374456,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00041523243623618907,
|
|
"loss": 5.051,
|
|
"mean_token_accuracy": 0.20303923040628433,
|
|
"num_tokens": 66871473.0,
|
|
"step": 32220
|
|
},
|
|
{
|
|
"entropy": 5.362732172012329,
|
|
"epoch": 2.9231676342525397,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00041520713146879333,
|
|
"loss": 5.0039,
|
|
"mean_token_accuracy": 0.20691501647233962,
|
|
"num_tokens": 66881609.0,
|
|
"step": 32225
|
|
},
|
|
{
|
|
"entropy": 5.415475940704345,
|
|
"epoch": 2.923621190130624,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00041518182380187853,
|
|
"loss": 5.063,
|
|
"mean_token_accuracy": 0.20319955796003342,
|
|
"num_tokens": 66891780.0,
|
|
"step": 32230
|
|
},
|
|
{
|
|
"entropy": 5.446313571929932,
|
|
"epoch": 2.924074746008708,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00041515651323596774,
|
|
"loss": 5.1476,
|
|
"mean_token_accuracy": 0.199581141769886,
|
|
"num_tokens": 66902251.0,
|
|
"step": 32235
|
|
},
|
|
{
|
|
"entropy": 5.444370985031128,
|
|
"epoch": 2.9245283018867925,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00041513119977158464,
|
|
"loss": 5.1171,
|
|
"mean_token_accuracy": 0.2006971314549446,
|
|
"num_tokens": 66912538.0,
|
|
"step": 32240
|
|
},
|
|
{
|
|
"entropy": 5.463493347167969,
|
|
"epoch": 2.9249818577648767,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004151058834092526,
|
|
"loss": 5.0229,
|
|
"mean_token_accuracy": 0.20611802637577056,
|
|
"num_tokens": 66922648.0,
|
|
"step": 32245
|
|
},
|
|
{
|
|
"entropy": 5.386238527297974,
|
|
"epoch": 2.925435413642961,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00041508056414949515,
|
|
"loss": 4.9853,
|
|
"mean_token_accuracy": 0.20601886957883836,
|
|
"num_tokens": 66933115.0,
|
|
"step": 32250
|
|
},
|
|
{
|
|
"entropy": 5.459532690048218,
|
|
"epoch": 2.9258889695210453,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000415055241992836,
|
|
"loss": 5.2042,
|
|
"mean_token_accuracy": 0.19023966491222383,
|
|
"num_tokens": 66943727.0,
|
|
"step": 32255
|
|
},
|
|
{
|
|
"entropy": 5.42129602432251,
|
|
"epoch": 2.926342525399129,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004150299169397987,
|
|
"loss": 5.0172,
|
|
"mean_token_accuracy": 0.20650955140590668,
|
|
"num_tokens": 66953488.0,
|
|
"step": 32260
|
|
},
|
|
{
|
|
"entropy": 5.4687470436096195,
|
|
"epoch": 2.9267960812772134,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004150045889909071,
|
|
"loss": 5.1654,
|
|
"mean_token_accuracy": 0.18760771602392196,
|
|
"num_tokens": 66964586.0,
|
|
"step": 32265
|
|
},
|
|
{
|
|
"entropy": 5.461675500869751,
|
|
"epoch": 2.9272496371552976,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004149792581466848,
|
|
"loss": 5.0827,
|
|
"mean_token_accuracy": 0.20101723670959473,
|
|
"num_tokens": 66975032.0,
|
|
"step": 32270
|
|
},
|
|
{
|
|
"entropy": 5.433660697937012,
|
|
"epoch": 2.9277031930333814,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00041495392440765586,
|
|
"loss": 5.0295,
|
|
"mean_token_accuracy": 0.2087118774652481,
|
|
"num_tokens": 66984910.0,
|
|
"step": 32275
|
|
},
|
|
{
|
|
"entropy": 5.363365221023559,
|
|
"epoch": 2.9281567489114657,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00041492858777434407,
|
|
"loss": 4.8739,
|
|
"mean_token_accuracy": 0.21809761226177216,
|
|
"num_tokens": 66995238.0,
|
|
"step": 32280
|
|
},
|
|
{
|
|
"entropy": 5.378975963592529,
|
|
"epoch": 2.92861030478955,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004149032482472734,
|
|
"loss": 5.0149,
|
|
"mean_token_accuracy": 0.2118966743350029,
|
|
"num_tokens": 67005596.0,
|
|
"step": 32285
|
|
},
|
|
{
|
|
"entropy": 5.472035312652588,
|
|
"epoch": 2.9290638606676342,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00041487790582696803,
|
|
"loss": 5.2226,
|
|
"mean_token_accuracy": 0.190968419611454,
|
|
"num_tokens": 67017312.0,
|
|
"step": 32290
|
|
},
|
|
{
|
|
"entropy": 5.422653293609619,
|
|
"epoch": 2.9295174165457185,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004148525605139518,
|
|
"loss": 5.0175,
|
|
"mean_token_accuracy": 0.20747601836919785,
|
|
"num_tokens": 67026692.0,
|
|
"step": 32295
|
|
},
|
|
{
|
|
"entropy": 5.372057580947876,
|
|
"epoch": 2.9299709724238028,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00041482721230874897,
|
|
"loss": 5.0472,
|
|
"mean_token_accuracy": 0.2064458906650543,
|
|
"num_tokens": 67036801.0,
|
|
"step": 32300
|
|
},
|
|
{
|
|
"entropy": 5.378249645233154,
|
|
"epoch": 2.930424528301887,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00041480186121188383,
|
|
"loss": 4.9931,
|
|
"mean_token_accuracy": 0.20803266614675522,
|
|
"num_tokens": 67047262.0,
|
|
"step": 32305
|
|
},
|
|
{
|
|
"entropy": 5.470685958862305,
|
|
"epoch": 2.930878084179971,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004147765072238806,
|
|
"loss": 5.102,
|
|
"mean_token_accuracy": 0.19875151216983794,
|
|
"num_tokens": 67058019.0,
|
|
"step": 32310
|
|
},
|
|
{
|
|
"entropy": 5.48073787689209,
|
|
"epoch": 2.931331640058055,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004147511503452635,
|
|
"loss": 5.1303,
|
|
"mean_token_accuracy": 0.1982719212770462,
|
|
"num_tokens": 67068844.0,
|
|
"step": 32315
|
|
},
|
|
{
|
|
"entropy": 5.44241681098938,
|
|
"epoch": 2.9317851959361394,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00041472579057655703,
|
|
"loss": 4.9941,
|
|
"mean_token_accuracy": 0.21166519224643707,
|
|
"num_tokens": 67077400.0,
|
|
"step": 32320
|
|
},
|
|
{
|
|
"entropy": 5.440207481384277,
|
|
"epoch": 2.9322387518142237,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004147004279182856,
|
|
"loss": 5.1916,
|
|
"mean_token_accuracy": 0.19254966229200363,
|
|
"num_tokens": 67088352.0,
|
|
"step": 32325
|
|
},
|
|
{
|
|
"entropy": 5.485732984542847,
|
|
"epoch": 2.9326923076923075,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004146750623709737,
|
|
"loss": 5.1053,
|
|
"mean_token_accuracy": 0.201947583258152,
|
|
"num_tokens": 67097879.0,
|
|
"step": 32330
|
|
},
|
|
{
|
|
"entropy": 5.417378520965576,
|
|
"epoch": 2.9331458635703918,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00041464969393514595,
|
|
"loss": 5.0172,
|
|
"mean_token_accuracy": 0.20638987571001052,
|
|
"num_tokens": 67108355.0,
|
|
"step": 32335
|
|
},
|
|
{
|
|
"entropy": 5.410375261306763,
|
|
"epoch": 2.933599419448476,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004146243226113269,
|
|
"loss": 5.1038,
|
|
"mean_token_accuracy": 0.19801610559225083,
|
|
"num_tokens": 67118348.0,
|
|
"step": 32340
|
|
},
|
|
{
|
|
"entropy": 5.3832676887512205,
|
|
"epoch": 2.9340529753265603,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00041459894840004135,
|
|
"loss": 4.9755,
|
|
"mean_token_accuracy": 0.2076404422521591,
|
|
"num_tokens": 67128944.0,
|
|
"step": 32345
|
|
},
|
|
{
|
|
"entropy": 5.468999290466309,
|
|
"epoch": 2.9345065312046446,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00041457357130181396,
|
|
"loss": 5.1029,
|
|
"mean_token_accuracy": 0.19850339144468307,
|
|
"num_tokens": 67139365.0,
|
|
"step": 32350
|
|
},
|
|
{
|
|
"entropy": 5.418531036376953,
|
|
"epoch": 2.934960087082729,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00041454819131716945,
|
|
"loss": 5.0436,
|
|
"mean_token_accuracy": 0.19965721070766448,
|
|
"num_tokens": 67150406.0,
|
|
"step": 32355
|
|
},
|
|
{
|
|
"entropy": 5.510232162475586,
|
|
"epoch": 2.9354136429608126,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00041452280844663295,
|
|
"loss": 5.2229,
|
|
"mean_token_accuracy": 0.1936228483915329,
|
|
"num_tokens": 67161631.0,
|
|
"step": 32360
|
|
},
|
|
{
|
|
"entropy": 5.3819983959197994,
|
|
"epoch": 2.935867198838897,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004144974226907291,
|
|
"loss": 5.0586,
|
|
"mean_token_accuracy": 0.20719848126173018,
|
|
"num_tokens": 67171735.0,
|
|
"step": 32365
|
|
},
|
|
{
|
|
"entropy": 5.410039663314819,
|
|
"epoch": 2.936320754716981,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000414472034049983,
|
|
"loss": 5.0799,
|
|
"mean_token_accuracy": 0.19900058656930925,
|
|
"num_tokens": 67181616.0,
|
|
"step": 32370
|
|
},
|
|
{
|
|
"entropy": 5.42422251701355,
|
|
"epoch": 2.9367743105950654,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004144466425249197,
|
|
"loss": 5.0303,
|
|
"mean_token_accuracy": 0.20618122667074204,
|
|
"num_tokens": 67192519.0,
|
|
"step": 32375
|
|
},
|
|
{
|
|
"entropy": 5.426108169555664,
|
|
"epoch": 2.9372278664731493,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004144212481160643,
|
|
"loss": 5.0461,
|
|
"mean_token_accuracy": 0.2051159143447876,
|
|
"num_tokens": 67202805.0,
|
|
"step": 32380
|
|
},
|
|
{
|
|
"entropy": 5.447917032241821,
|
|
"epoch": 2.9376814223512335,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004143958508239419,
|
|
"loss": 5.0404,
|
|
"mean_token_accuracy": 0.20612580925226212,
|
|
"num_tokens": 67212778.0,
|
|
"step": 32385
|
|
},
|
|
{
|
|
"entropy": 5.373782682418823,
|
|
"epoch": 2.938134978229318,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004143704506490779,
|
|
"loss": 5.0995,
|
|
"mean_token_accuracy": 0.2020643249154091,
|
|
"num_tokens": 67222588.0,
|
|
"step": 32390
|
|
},
|
|
{
|
|
"entropy": 5.4723193645477295,
|
|
"epoch": 2.938588534107402,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004143450475919975,
|
|
"loss": 5.0863,
|
|
"mean_token_accuracy": 0.19946806579828263,
|
|
"num_tokens": 67233022.0,
|
|
"step": 32395
|
|
},
|
|
{
|
|
"entropy": 5.434817552566528,
|
|
"epoch": 2.9390420899854863,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004143196416532259,
|
|
"loss": 5.0475,
|
|
"mean_token_accuracy": 0.20774469077587127,
|
|
"num_tokens": 67242631.0,
|
|
"step": 32400
|
|
},
|
|
{
|
|
"entropy": 5.35536470413208,
|
|
"epoch": 2.9394956458635706,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004142942328332887,
|
|
"loss": 4.9877,
|
|
"mean_token_accuracy": 0.21339151859283448,
|
|
"num_tokens": 67252376.0,
|
|
"step": 32405
|
|
},
|
|
{
|
|
"entropy": 5.400999402999878,
|
|
"epoch": 2.9399492017416544,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004142688211327111,
|
|
"loss": 5.0082,
|
|
"mean_token_accuracy": 0.2036372020840645,
|
|
"num_tokens": 67262209.0,
|
|
"step": 32410
|
|
},
|
|
{
|
|
"entropy": 5.454795980453492,
|
|
"epoch": 2.9404027576197387,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004142434065520189,
|
|
"loss": 5.0774,
|
|
"mean_token_accuracy": 0.19892836958169938,
|
|
"num_tokens": 67272893.0,
|
|
"step": 32415
|
|
},
|
|
{
|
|
"entropy": 5.38972840309143,
|
|
"epoch": 2.940856313497823,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004142179890917376,
|
|
"loss": 5.0435,
|
|
"mean_token_accuracy": 0.2015369266271591,
|
|
"num_tokens": 67284017.0,
|
|
"step": 32420
|
|
},
|
|
{
|
|
"entropy": 5.383106374740601,
|
|
"epoch": 2.941309869375907,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00041419256875239275,
|
|
"loss": 5.0318,
|
|
"mean_token_accuracy": 0.21388382315635682,
|
|
"num_tokens": 67293674.0,
|
|
"step": 32425
|
|
},
|
|
{
|
|
"entropy": 5.402885150909424,
|
|
"epoch": 2.941763425253991,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004141671455345101,
|
|
"loss": 5.0831,
|
|
"mean_token_accuracy": 0.201033154129982,
|
|
"num_tokens": 67303759.0,
|
|
"step": 32430
|
|
},
|
|
{
|
|
"entropy": 5.485676956176758,
|
|
"epoch": 2.9422169811320753,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00041414171943861543,
|
|
"loss": 5.0916,
|
|
"mean_token_accuracy": 0.2013459637761116,
|
|
"num_tokens": 67314962.0,
|
|
"step": 32435
|
|
},
|
|
{
|
|
"entropy": 5.4716747283935545,
|
|
"epoch": 2.9426705370101596,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004141162904652346,
|
|
"loss": 5.162,
|
|
"mean_token_accuracy": 0.19511002898216248,
|
|
"num_tokens": 67325210.0,
|
|
"step": 32440
|
|
},
|
|
{
|
|
"entropy": 5.437849283218384,
|
|
"epoch": 2.943124092888244,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004140908586148934,
|
|
"loss": 5.0894,
|
|
"mean_token_accuracy": 0.1998877465724945,
|
|
"num_tokens": 67335110.0,
|
|
"step": 32445
|
|
},
|
|
{
|
|
"entropy": 5.4097991466522215,
|
|
"epoch": 2.943577648766328,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004140654238881178,
|
|
"loss": 5.1817,
|
|
"mean_token_accuracy": 0.1954920008778572,
|
|
"num_tokens": 67345872.0,
|
|
"step": 32450
|
|
},
|
|
{
|
|
"entropy": 5.402998447418213,
|
|
"epoch": 2.9440312046444124,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00041403998628543375,
|
|
"loss": 5.0402,
|
|
"mean_token_accuracy": 0.2043477401137352,
|
|
"num_tokens": 67356532.0,
|
|
"step": 32455
|
|
},
|
|
{
|
|
"entropy": 5.432572507858277,
|
|
"epoch": 2.9444847605224966,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00041401454580736744,
|
|
"loss": 5.0508,
|
|
"mean_token_accuracy": 0.20933209955692292,
|
|
"num_tokens": 67366603.0,
|
|
"step": 32460
|
|
},
|
|
{
|
|
"entropy": 5.510068368911743,
|
|
"epoch": 2.9449383164005805,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004139891024544448,
|
|
"loss": 5.1934,
|
|
"mean_token_accuracy": 0.19644128084182738,
|
|
"num_tokens": 67377487.0,
|
|
"step": 32465
|
|
},
|
|
{
|
|
"entropy": 5.470737075805664,
|
|
"epoch": 2.9453918722786647,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004139636562271921,
|
|
"loss": 5.1357,
|
|
"mean_token_accuracy": 0.20020587593317032,
|
|
"num_tokens": 67387704.0,
|
|
"step": 32470
|
|
},
|
|
{
|
|
"entropy": 5.452878475189209,
|
|
"epoch": 2.945845428156749,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00041393820712613567,
|
|
"loss": 5.103,
|
|
"mean_token_accuracy": 0.19799476563930513,
|
|
"num_tokens": 67398409.0,
|
|
"step": 32475
|
|
},
|
|
{
|
|
"entropy": 5.457312440872192,
|
|
"epoch": 2.9462989840348333,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00041391275515180166,
|
|
"loss": 5.004,
|
|
"mean_token_accuracy": 0.2010439544916153,
|
|
"num_tokens": 67408905.0,
|
|
"step": 32480
|
|
},
|
|
{
|
|
"entropy": 5.38221492767334,
|
|
"epoch": 2.946752539912917,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004138873003047165,
|
|
"loss": 5.001,
|
|
"mean_token_accuracy": 0.2122493341565132,
|
|
"num_tokens": 67418466.0,
|
|
"step": 32485
|
|
},
|
|
{
|
|
"entropy": 5.3452106475830075,
|
|
"epoch": 2.9472060957910013,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004138618425854066,
|
|
"loss": 5.0293,
|
|
"mean_token_accuracy": 0.20658196210861207,
|
|
"num_tokens": 67428597.0,
|
|
"step": 32490
|
|
},
|
|
{
|
|
"entropy": 5.447670745849609,
|
|
"epoch": 2.9476596516690856,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00041383638199439824,
|
|
"loss": 5.0479,
|
|
"mean_token_accuracy": 0.2025267004966736,
|
|
"num_tokens": 67439158.0,
|
|
"step": 32495
|
|
},
|
|
{
|
|
"entropy": 5.4971840381622314,
|
|
"epoch": 2.94811320754717,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00041381091853221835,
|
|
"loss": 5.0724,
|
|
"mean_token_accuracy": 0.2006855472922325,
|
|
"num_tokens": 67449540.0,
|
|
"step": 32500
|
|
},
|
|
{
|
|
"entropy": 5.392175006866455,
|
|
"epoch": 2.948566763425254,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004137854521993932,
|
|
"loss": 5.0091,
|
|
"mean_token_accuracy": 0.20707719624042512,
|
|
"num_tokens": 67459385.0,
|
|
"step": 32505
|
|
},
|
|
{
|
|
"entropy": 5.416623115539551,
|
|
"epoch": 2.9490203193033384,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00041375998299644946,
|
|
"loss": 5.1053,
|
|
"mean_token_accuracy": 0.20226395279169082,
|
|
"num_tokens": 67469597.0,
|
|
"step": 32510
|
|
},
|
|
{
|
|
"entropy": 5.370545148849487,
|
|
"epoch": 2.9494738751814222,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000413734510923914,
|
|
"loss": 4.976,
|
|
"mean_token_accuracy": 0.20007159560918808,
|
|
"num_tokens": 67479271.0,
|
|
"step": 32515
|
|
},
|
|
{
|
|
"entropy": 5.347590827941895,
|
|
"epoch": 2.9499274310595065,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004137090359823135,
|
|
"loss": 4.9843,
|
|
"mean_token_accuracy": 0.2085232377052307,
|
|
"num_tokens": 67488997.0,
|
|
"step": 32520
|
|
},
|
|
{
|
|
"entropy": 5.439016199111938,
|
|
"epoch": 2.9503809869375908,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00041368355817217474,
|
|
"loss": 5.0253,
|
|
"mean_token_accuracy": 0.20626693069934846,
|
|
"num_tokens": 67499507.0,
|
|
"step": 32525
|
|
},
|
|
{
|
|
"entropy": 5.404528665542602,
|
|
"epoch": 2.950834542815675,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00041365807749402467,
|
|
"loss": 4.9926,
|
|
"mean_token_accuracy": 0.20798412412405015,
|
|
"num_tokens": 67509916.0,
|
|
"step": 32530
|
|
},
|
|
{
|
|
"entropy": 5.36402997970581,
|
|
"epoch": 2.951288098693759,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004136325939483902,
|
|
"loss": 5.009,
|
|
"mean_token_accuracy": 0.19769441932439805,
|
|
"num_tokens": 67519759.0,
|
|
"step": 32535
|
|
},
|
|
{
|
|
"entropy": 5.3799519538879395,
|
|
"epoch": 2.951741654571843,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004136071075357984,
|
|
"loss": 5.0537,
|
|
"mean_token_accuracy": 0.20884837806224824,
|
|
"num_tokens": 67529261.0,
|
|
"step": 32540
|
|
},
|
|
{
|
|
"entropy": 5.41085000038147,
|
|
"epoch": 2.9521952104499274,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004135816182567763,
|
|
"loss": 5.0244,
|
|
"mean_token_accuracy": 0.20190137922763823,
|
|
"num_tokens": 67539084.0,
|
|
"step": 32545
|
|
},
|
|
{
|
|
"entropy": 5.414923000335693,
|
|
"epoch": 2.9526487663280117,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000413556126111851,
|
|
"loss": 5.0934,
|
|
"mean_token_accuracy": 0.20501596182584764,
|
|
"num_tokens": 67548551.0,
|
|
"step": 32550
|
|
},
|
|
{
|
|
"entropy": 5.462216997146607,
|
|
"epoch": 2.953102322206096,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004135306311015497,
|
|
"loss": 5.0445,
|
|
"mean_token_accuracy": 0.20049311518669127,
|
|
"num_tokens": 67558364.0,
|
|
"step": 32555
|
|
},
|
|
{
|
|
"entropy": 5.466135787963867,
|
|
"epoch": 2.95355587808418,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004135051332263996,
|
|
"loss": 5.0573,
|
|
"mean_token_accuracy": 0.20778274685144424,
|
|
"num_tokens": 67569257.0,
|
|
"step": 32560
|
|
},
|
|
{
|
|
"entropy": 5.390544414520264,
|
|
"epoch": 2.954009433962264,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00041347963248692814,
|
|
"loss": 5.126,
|
|
"mean_token_accuracy": 0.19913280308246611,
|
|
"num_tokens": 67580135.0,
|
|
"step": 32565
|
|
},
|
|
{
|
|
"entropy": 5.437038946151733,
|
|
"epoch": 2.9544629898403483,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004134541288836626,
|
|
"loss": 5.0496,
|
|
"mean_token_accuracy": 0.20363733023405076,
|
|
"num_tokens": 67589705.0,
|
|
"step": 32570
|
|
},
|
|
{
|
|
"entropy": 5.436109495162964,
|
|
"epoch": 2.9549165457184325,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00041342862241713034,
|
|
"loss": 5.0024,
|
|
"mean_token_accuracy": 0.20490633100271224,
|
|
"num_tokens": 67599648.0,
|
|
"step": 32575
|
|
},
|
|
{
|
|
"entropy": 5.41980619430542,
|
|
"epoch": 2.955370101596517,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00041340311308785886,
|
|
"loss": 5.0173,
|
|
"mean_token_accuracy": 0.20396335870027543,
|
|
"num_tokens": 67609624.0,
|
|
"step": 32580
|
|
},
|
|
{
|
|
"entropy": 5.3406788349151615,
|
|
"epoch": 2.9558236574746006,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00041337760089637577,
|
|
"loss": 5.0395,
|
|
"mean_token_accuracy": 0.2029004380106926,
|
|
"num_tokens": 67619596.0,
|
|
"step": 32585
|
|
},
|
|
{
|
|
"entropy": 5.433111715316772,
|
|
"epoch": 2.956277213352685,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00041335208584320865,
|
|
"loss": 5.0729,
|
|
"mean_token_accuracy": 0.19814513623714447,
|
|
"num_tokens": 67629667.0,
|
|
"step": 32590
|
|
},
|
|
{
|
|
"entropy": 5.468498659133911,
|
|
"epoch": 2.956730769230769,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004133265679288851,
|
|
"loss": 5.0589,
|
|
"mean_token_accuracy": 0.20020340085029603,
|
|
"num_tokens": 67640048.0,
|
|
"step": 32595
|
|
},
|
|
{
|
|
"entropy": 5.4495923042297365,
|
|
"epoch": 2.9571843251088534,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004133010471539329,
|
|
"loss": 5.1196,
|
|
"mean_token_accuracy": 0.1970471605658531,
|
|
"num_tokens": 67650731.0,
|
|
"step": 32600
|
|
},
|
|
{
|
|
"entropy": 5.395864725112915,
|
|
"epoch": 2.9576378809869377,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00041327552351887983,
|
|
"loss": 5.0543,
|
|
"mean_token_accuracy": 0.20356555730104448,
|
|
"num_tokens": 67661696.0,
|
|
"step": 32605
|
|
},
|
|
{
|
|
"entropy": 5.434980297088623,
|
|
"epoch": 2.958091436865022,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00041324999702425366,
|
|
"loss": 5.0612,
|
|
"mean_token_accuracy": 0.20339757800102234,
|
|
"num_tokens": 67671758.0,
|
|
"step": 32610
|
|
},
|
|
{
|
|
"entropy": 5.386895751953125,
|
|
"epoch": 2.9585449927431062,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004132244676705823,
|
|
"loss": 5.0369,
|
|
"mean_token_accuracy": 0.20457230508327484,
|
|
"num_tokens": 67682488.0,
|
|
"step": 32615
|
|
},
|
|
{
|
|
"entropy": 5.453609657287598,
|
|
"epoch": 2.95899854862119,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004131989354583938,
|
|
"loss": 5.0565,
|
|
"mean_token_accuracy": 0.20860493332147598,
|
|
"num_tokens": 67692945.0,
|
|
"step": 32620
|
|
},
|
|
{
|
|
"entropy": 5.400771188735962,
|
|
"epoch": 2.9594521044992743,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000413173400388216,
|
|
"loss": 4.9792,
|
|
"mean_token_accuracy": 0.2047429323196411,
|
|
"num_tokens": 67702924.0,
|
|
"step": 32625
|
|
},
|
|
{
|
|
"entropy": 5.399952125549317,
|
|
"epoch": 2.9599056603773586,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004131478624605771,
|
|
"loss": 5.0743,
|
|
"mean_token_accuracy": 0.20142187774181367,
|
|
"num_tokens": 67714284.0,
|
|
"step": 32630
|
|
},
|
|
{
|
|
"entropy": 5.444569206237793,
|
|
"epoch": 2.9603592162554424,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004131223216760052,
|
|
"loss": 5.134,
|
|
"mean_token_accuracy": 0.19343200027942659,
|
|
"num_tokens": 67725902.0,
|
|
"step": 32635
|
|
},
|
|
{
|
|
"entropy": 5.433411073684693,
|
|
"epoch": 2.9608127721335267,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004130967780350286,
|
|
"loss": 5.0452,
|
|
"mean_token_accuracy": 0.19844017177820206,
|
|
"num_tokens": 67736268.0,
|
|
"step": 32640
|
|
},
|
|
{
|
|
"entropy": 5.502456378936768,
|
|
"epoch": 2.961266328011611,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004130712315381753,
|
|
"loss": 5.0978,
|
|
"mean_token_accuracy": 0.20939357727766036,
|
|
"num_tokens": 67745709.0,
|
|
"step": 32645
|
|
},
|
|
{
|
|
"entropy": 5.439459037780762,
|
|
"epoch": 2.961719883889695,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00041304568218597385,
|
|
"loss": 5.0459,
|
|
"mean_token_accuracy": 0.2020131304860115,
|
|
"num_tokens": 67756092.0,
|
|
"step": 32650
|
|
},
|
|
{
|
|
"entropy": 5.426393651962281,
|
|
"epoch": 2.9621734397677795,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00041302012997895246,
|
|
"loss": 5.0633,
|
|
"mean_token_accuracy": 0.19881993681192398,
|
|
"num_tokens": 67766224.0,
|
|
"step": 32655
|
|
},
|
|
{
|
|
"entropy": 5.516324424743653,
|
|
"epoch": 2.9626269956458637,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004129945749176395,
|
|
"loss": 5.1935,
|
|
"mean_token_accuracy": 0.20004573762416838,
|
|
"num_tokens": 67776787.0,
|
|
"step": 32660
|
|
},
|
|
{
|
|
"entropy": 5.388972187042237,
|
|
"epoch": 2.963080551523948,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00041296901700256375,
|
|
"loss": 5.0458,
|
|
"mean_token_accuracy": 0.20073368400335312,
|
|
"num_tokens": 67787924.0,
|
|
"step": 32665
|
|
},
|
|
{
|
|
"entropy": 5.40651502609253,
|
|
"epoch": 2.963534107402032,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004129434562342535,
|
|
"loss": 5.0463,
|
|
"mean_token_accuracy": 0.19485465288162232,
|
|
"num_tokens": 67798544.0,
|
|
"step": 32670
|
|
},
|
|
{
|
|
"entropy": 5.3967945098876955,
|
|
"epoch": 2.963987663280116,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00041291789261323734,
|
|
"loss": 5.0502,
|
|
"mean_token_accuracy": 0.2031262144446373,
|
|
"num_tokens": 67809528.0,
|
|
"step": 32675
|
|
},
|
|
{
|
|
"entropy": 5.317273807525635,
|
|
"epoch": 2.9644412191582004,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00041289232614004416,
|
|
"loss": 4.9366,
|
|
"mean_token_accuracy": 0.2166508838534355,
|
|
"num_tokens": 67820263.0,
|
|
"step": 32680
|
|
},
|
|
{
|
|
"entropy": 5.4895635604858395,
|
|
"epoch": 2.9648947750362846,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004128667568152024,
|
|
"loss": 5.1257,
|
|
"mean_token_accuracy": 0.19765955060720444,
|
|
"num_tokens": 67830687.0,
|
|
"step": 32685
|
|
},
|
|
{
|
|
"entropy": 5.509335565567016,
|
|
"epoch": 2.9653483309143684,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00041284118463924107,
|
|
"loss": 5.1343,
|
|
"mean_token_accuracy": 0.19623125046491624,
|
|
"num_tokens": 67841714.0,
|
|
"step": 32690
|
|
},
|
|
{
|
|
"entropy": 5.382079076766968,
|
|
"epoch": 2.9658018867924527,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004128156096126889,
|
|
"loss": 5.0319,
|
|
"mean_token_accuracy": 0.2029604732990265,
|
|
"num_tokens": 67851952.0,
|
|
"step": 32695
|
|
},
|
|
{
|
|
"entropy": 5.332967710494995,
|
|
"epoch": 2.966255442670537,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00041279003173607477,
|
|
"loss": 4.9326,
|
|
"mean_token_accuracy": 0.20718971490859986,
|
|
"num_tokens": 67861958.0,
|
|
"step": 32700
|
|
},
|
|
{
|
|
"entropy": 5.351459264755249,
|
|
"epoch": 2.9667089985486212,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004127644510099278,
|
|
"loss": 4.9361,
|
|
"mean_token_accuracy": 0.20980960130691528,
|
|
"num_tokens": 67871654.0,
|
|
"step": 32705
|
|
},
|
|
{
|
|
"entropy": 5.334363126754761,
|
|
"epoch": 2.9671625544267055,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004127388674347767,
|
|
"loss": 5.0251,
|
|
"mean_token_accuracy": 0.21096129417419435,
|
|
"num_tokens": 67881678.0,
|
|
"step": 32710
|
|
},
|
|
{
|
|
"entropy": 5.393507766723633,
|
|
"epoch": 2.96761611030479,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00041271328101115075,
|
|
"loss": 5.0729,
|
|
"mean_token_accuracy": 0.2019503965973854,
|
|
"num_tokens": 67892663.0,
|
|
"step": 32715
|
|
},
|
|
{
|
|
"entropy": 5.561925649642944,
|
|
"epoch": 2.9680696661828736,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00041268769173957915,
|
|
"loss": 5.2341,
|
|
"mean_token_accuracy": 0.19370659291744233,
|
|
"num_tokens": 67903308.0,
|
|
"step": 32720
|
|
},
|
|
{
|
|
"entropy": 5.47245421409607,
|
|
"epoch": 2.968523222060958,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00041266209962059097,
|
|
"loss": 5.0339,
|
|
"mean_token_accuracy": 0.20860547125339507,
|
|
"num_tokens": 67913092.0,
|
|
"step": 32725
|
|
},
|
|
{
|
|
"entropy": 5.416002035140991,
|
|
"epoch": 2.968976777939042,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004126365046547154,
|
|
"loss": 5.0354,
|
|
"mean_token_accuracy": 0.21257272064685823,
|
|
"num_tokens": 67923708.0,
|
|
"step": 32730
|
|
},
|
|
{
|
|
"entropy": 5.372655534744263,
|
|
"epoch": 2.9694303338171264,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004126109068424819,
|
|
"loss": 5.0301,
|
|
"mean_token_accuracy": 0.20436687767505646,
|
|
"num_tokens": 67934164.0,
|
|
"step": 32735
|
|
},
|
|
{
|
|
"entropy": 5.459881544113159,
|
|
"epoch": 2.96988388969521,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004125853061844198,
|
|
"loss": 5.1339,
|
|
"mean_token_accuracy": 0.19685615599155426,
|
|
"num_tokens": 67943162.0,
|
|
"step": 32740
|
|
},
|
|
{
|
|
"entropy": 5.482471609115601,
|
|
"epoch": 2.9703374455732945,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004125597026810585,
|
|
"loss": 5.1186,
|
|
"mean_token_accuracy": 0.2016544446349144,
|
|
"num_tokens": 67953943.0,
|
|
"step": 32745
|
|
},
|
|
{
|
|
"entropy": 5.359710216522217,
|
|
"epoch": 2.9707910014513788,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00041253409633292747,
|
|
"loss": 5.0216,
|
|
"mean_token_accuracy": 0.20564395040273667,
|
|
"num_tokens": 67964603.0,
|
|
"step": 32750
|
|
},
|
|
{
|
|
"entropy": 5.473698711395263,
|
|
"epoch": 2.971244557329463,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00041250848714055626,
|
|
"loss": 5.0948,
|
|
"mean_token_accuracy": 0.205639311671257,
|
|
"num_tokens": 67974541.0,
|
|
"step": 32755
|
|
},
|
|
{
|
|
"entropy": 5.4692802906036375,
|
|
"epoch": 2.9716981132075473,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004124828751044746,
|
|
"loss": 5.0548,
|
|
"mean_token_accuracy": 0.2007441282272339,
|
|
"num_tokens": 67984968.0,
|
|
"step": 32760
|
|
},
|
|
{
|
|
"entropy": 5.367335796356201,
|
|
"epoch": 2.9721516690856316,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004124572602252119,
|
|
"loss": 5.0205,
|
|
"mean_token_accuracy": 0.20245739370584487,
|
|
"num_tokens": 67995567.0,
|
|
"step": 32765
|
|
},
|
|
{
|
|
"entropy": 5.469276189804077,
|
|
"epoch": 2.9726052249637154,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004124316425032981,
|
|
"loss": 5.2023,
|
|
"mean_token_accuracy": 0.1900266543030739,
|
|
"num_tokens": 68008530.0,
|
|
"step": 32770
|
|
},
|
|
{
|
|
"entropy": 5.488479042053223,
|
|
"epoch": 2.9730587808417996,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00041240602193926294,
|
|
"loss": 5.1196,
|
|
"mean_token_accuracy": 0.19937289208173753,
|
|
"num_tokens": 68018393.0,
|
|
"step": 32775
|
|
},
|
|
{
|
|
"entropy": 5.484728670120239,
|
|
"epoch": 2.973512336719884,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004123803985336362,
|
|
"loss": 5.0631,
|
|
"mean_token_accuracy": 0.1984148308634758,
|
|
"num_tokens": 68027677.0,
|
|
"step": 32780
|
|
},
|
|
{
|
|
"entropy": 5.33840389251709,
|
|
"epoch": 2.973965892597968,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00041235477228694786,
|
|
"loss": 4.9575,
|
|
"mean_token_accuracy": 0.21336801797151567,
|
|
"num_tokens": 68037157.0,
|
|
"step": 32785
|
|
},
|
|
{
|
|
"entropy": 5.37793755531311,
|
|
"epoch": 2.974419448476052,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00041232914319972775,
|
|
"loss": 5.0293,
|
|
"mean_token_accuracy": 0.2116871014237404,
|
|
"num_tokens": 68047793.0,
|
|
"step": 32790
|
|
},
|
|
{
|
|
"entropy": 5.432454061508179,
|
|
"epoch": 2.9748730043541363,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00041230351127250603,
|
|
"loss": 5.0924,
|
|
"mean_token_accuracy": 0.20476160794496537,
|
|
"num_tokens": 68058155.0,
|
|
"step": 32795
|
|
},
|
|
{
|
|
"entropy": 5.485487174987793,
|
|
"epoch": 2.9753265602322205,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00041227787650581266,
|
|
"loss": 4.99,
|
|
"mean_token_accuracy": 0.2096954107284546,
|
|
"num_tokens": 68067440.0,
|
|
"step": 32800
|
|
},
|
|
{
|
|
"entropy": 5.3983094692230225,
|
|
"epoch": 2.975780116110305,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00041225223890017785,
|
|
"loss": 5.0643,
|
|
"mean_token_accuracy": 0.20259551107883453,
|
|
"num_tokens": 68077815.0,
|
|
"step": 32805
|
|
},
|
|
{
|
|
"entropy": 5.408013534545899,
|
|
"epoch": 2.976233671988389,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00041222659845613173,
|
|
"loss": 5.0149,
|
|
"mean_token_accuracy": 0.20635936856269838,
|
|
"num_tokens": 68087692.0,
|
|
"step": 32810
|
|
},
|
|
{
|
|
"entropy": 5.387275266647339,
|
|
"epoch": 2.9766872278664733,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00041220095517420464,
|
|
"loss": 4.9987,
|
|
"mean_token_accuracy": 0.20591391921043395,
|
|
"num_tokens": 68097774.0,
|
|
"step": 32815
|
|
},
|
|
{
|
|
"entropy": 5.417366790771484,
|
|
"epoch": 2.9771407837445576,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004121753090549268,
|
|
"loss": 5.0729,
|
|
"mean_token_accuracy": 0.20071449428796767,
|
|
"num_tokens": 68107992.0,
|
|
"step": 32820
|
|
},
|
|
{
|
|
"entropy": 5.343447017669678,
|
|
"epoch": 2.9775943396226414,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00041214966009882857,
|
|
"loss": 4.9847,
|
|
"mean_token_accuracy": 0.2116597354412079,
|
|
"num_tokens": 68117103.0,
|
|
"step": 32825
|
|
},
|
|
{
|
|
"entropy": 5.464438199996948,
|
|
"epoch": 2.9780478955007257,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004121240083064405,
|
|
"loss": 5.1091,
|
|
"mean_token_accuracy": 0.20602559000253678,
|
|
"num_tokens": 68127951.0,
|
|
"step": 32830
|
|
},
|
|
{
|
|
"entropy": 5.487927484512329,
|
|
"epoch": 2.97850145137881,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00041209835367829293,
|
|
"loss": 5.1232,
|
|
"mean_token_accuracy": 0.20482053160667418,
|
|
"num_tokens": 68138229.0,
|
|
"step": 32835
|
|
},
|
|
{
|
|
"entropy": 5.326704263687134,
|
|
"epoch": 2.9789550072568938,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00041207269621491654,
|
|
"loss": 5.0134,
|
|
"mean_token_accuracy": 0.20840660780668258,
|
|
"num_tokens": 68148019.0,
|
|
"step": 32840
|
|
},
|
|
{
|
|
"entropy": 5.359653902053833,
|
|
"epoch": 2.979408563134978,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004120470359168418,
|
|
"loss": 5.0466,
|
|
"mean_token_accuracy": 0.20058955997228622,
|
|
"num_tokens": 68158704.0,
|
|
"step": 32845
|
|
},
|
|
{
|
|
"entropy": 5.4847893714904785,
|
|
"epoch": 2.9798621190130623,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00041202137278459946,
|
|
"loss": 5.0568,
|
|
"mean_token_accuracy": 0.20660750418901444,
|
|
"num_tokens": 68169105.0,
|
|
"step": 32850
|
|
},
|
|
{
|
|
"entropy": 5.399052429199219,
|
|
"epoch": 2.9803156748911466,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004119957068187202,
|
|
"loss": 4.9884,
|
|
"mean_token_accuracy": 0.20691830515861512,
|
|
"num_tokens": 68179778.0,
|
|
"step": 32855
|
|
},
|
|
{
|
|
"entropy": 5.347516202926636,
|
|
"epoch": 2.980769230769231,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004119700380197348,
|
|
"loss": 5.0147,
|
|
"mean_token_accuracy": 0.20417394787073134,
|
|
"num_tokens": 68189405.0,
|
|
"step": 32860
|
|
},
|
|
{
|
|
"entropy": 5.32415509223938,
|
|
"epoch": 2.981222786647315,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00041194436638817417,
|
|
"loss": 4.9639,
|
|
"mean_token_accuracy": 0.21721175462007522,
|
|
"num_tokens": 68199351.0,
|
|
"step": 32865
|
|
},
|
|
{
|
|
"entropy": 5.475106334686279,
|
|
"epoch": 2.9816763425253994,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00041191869192456907,
|
|
"loss": 5.1424,
|
|
"mean_token_accuracy": 0.19889063537120819,
|
|
"num_tokens": 68209904.0,
|
|
"step": 32870
|
|
},
|
|
{
|
|
"entropy": 5.468987989425659,
|
|
"epoch": 2.982129898403483,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004118930146294506,
|
|
"loss": 5.1308,
|
|
"mean_token_accuracy": 0.19896190464496613,
|
|
"num_tokens": 68221754.0,
|
|
"step": 32875
|
|
},
|
|
{
|
|
"entropy": 5.451415872573852,
|
|
"epoch": 2.9825834542815675,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004118673345033496,
|
|
"loss": 5.0485,
|
|
"mean_token_accuracy": 0.20052987188100815,
|
|
"num_tokens": 68232328.0,
|
|
"step": 32880
|
|
},
|
|
{
|
|
"entropy": 5.365130090713501,
|
|
"epoch": 2.9830370101596517,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004118416515467974,
|
|
"loss": 4.9902,
|
|
"mean_token_accuracy": 0.1993743896484375,
|
|
"num_tokens": 68242812.0,
|
|
"step": 32885
|
|
},
|
|
{
|
|
"entropy": 5.462041568756104,
|
|
"epoch": 2.983490566037736,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004118159657603248,
|
|
"loss": 5.1321,
|
|
"mean_token_accuracy": 0.1981256514787674,
|
|
"num_tokens": 68253888.0,
|
|
"step": 32890
|
|
},
|
|
{
|
|
"entropy": 5.44194712638855,
|
|
"epoch": 2.98394412191582,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004117902771444633,
|
|
"loss": 5.0585,
|
|
"mean_token_accuracy": 0.20262978076934815,
|
|
"num_tokens": 68264877.0,
|
|
"step": 32895
|
|
},
|
|
{
|
|
"entropy": 5.5233203887939455,
|
|
"epoch": 2.984397677793904,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000411764585699744,
|
|
"loss": 5.1421,
|
|
"mean_token_accuracy": 0.19479060769081116,
|
|
"num_tokens": 68275863.0,
|
|
"step": 32900
|
|
},
|
|
{
|
|
"entropy": 5.465900325775147,
|
|
"epoch": 2.9848512336719883,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00041173889142669806,
|
|
"loss": 5.0758,
|
|
"mean_token_accuracy": 0.20030643045902252,
|
|
"num_tokens": 68286768.0,
|
|
"step": 32905
|
|
},
|
|
{
|
|
"entropy": 5.380517768859863,
|
|
"epoch": 2.9853047895500726,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004117131943258572,
|
|
"loss": 4.9941,
|
|
"mean_token_accuracy": 0.2078376069664955,
|
|
"num_tokens": 68296990.0,
|
|
"step": 32910
|
|
},
|
|
{
|
|
"entropy": 5.314198541641235,
|
|
"epoch": 2.985758345428157,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00041168749439775255,
|
|
"loss": 4.971,
|
|
"mean_token_accuracy": 0.20619772374629974,
|
|
"num_tokens": 68307646.0,
|
|
"step": 32915
|
|
},
|
|
{
|
|
"entropy": 5.468535137176514,
|
|
"epoch": 2.986211901306241,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004116617916429156,
|
|
"loss": 5.1557,
|
|
"mean_token_accuracy": 0.1905728980898857,
|
|
"num_tokens": 68319586.0,
|
|
"step": 32920
|
|
},
|
|
{
|
|
"entropy": 5.516706085205078,
|
|
"epoch": 2.986665457184325,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004116360860618781,
|
|
"loss": 5.1093,
|
|
"mean_token_accuracy": 0.19858939945697784,
|
|
"num_tokens": 68329692.0,
|
|
"step": 32925
|
|
},
|
|
{
|
|
"entropy": 5.483304166793824,
|
|
"epoch": 2.9871190130624092,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004116103776551715,
|
|
"loss": 5.0594,
|
|
"mean_token_accuracy": 0.20199441760778428,
|
|
"num_tokens": 68339589.0,
|
|
"step": 32930
|
|
},
|
|
{
|
|
"entropy": 5.433497142791748,
|
|
"epoch": 2.9875725689404935,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00041158466642332743,
|
|
"loss": 5.1054,
|
|
"mean_token_accuracy": 0.19269715696573259,
|
|
"num_tokens": 68349485.0,
|
|
"step": 32935
|
|
},
|
|
{
|
|
"entropy": 5.441445922851562,
|
|
"epoch": 2.9880261248185778,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004115589523668777,
|
|
"loss": 5.0314,
|
|
"mean_token_accuracy": 0.20994330048561097,
|
|
"num_tokens": 68359695.0,
|
|
"step": 32940
|
|
},
|
|
{
|
|
"entropy": 5.3427060604095455,
|
|
"epoch": 2.9884796806966616,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000411533235486354,
|
|
"loss": 4.9265,
|
|
"mean_token_accuracy": 0.21385785788297654,
|
|
"num_tokens": 68369591.0,
|
|
"step": 32945
|
|
},
|
|
{
|
|
"entropy": 5.418456315994263,
|
|
"epoch": 2.988933236574746,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004115075157822883,
|
|
"loss": 5.0862,
|
|
"mean_token_accuracy": 0.2051855206489563,
|
|
"num_tokens": 68380382.0,
|
|
"step": 32950
|
|
},
|
|
{
|
|
"entropy": 5.305290079116821,
|
|
"epoch": 2.98938679245283,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004114817932552122,
|
|
"loss": 4.9365,
|
|
"mean_token_accuracy": 0.2065068781375885,
|
|
"num_tokens": 68389865.0,
|
|
"step": 32955
|
|
},
|
|
{
|
|
"entropy": 5.3690910816192625,
|
|
"epoch": 2.9898403483309144,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00041145606790565797,
|
|
"loss": 4.9701,
|
|
"mean_token_accuracy": 0.21782325506210326,
|
|
"num_tokens": 68399267.0,
|
|
"step": 32960
|
|
},
|
|
{
|
|
"entropy": 5.425803327560425,
|
|
"epoch": 2.9902939042089987,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004114303397341575,
|
|
"loss": 5.0818,
|
|
"mean_token_accuracy": 0.21225244104862212,
|
|
"num_tokens": 68409480.0,
|
|
"step": 32965
|
|
},
|
|
{
|
|
"entropy": 5.518222236633301,
|
|
"epoch": 2.990747460087083,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004114046087412427,
|
|
"loss": 5.1658,
|
|
"mean_token_accuracy": 0.19810915887355804,
|
|
"num_tokens": 68420019.0,
|
|
"step": 32970
|
|
},
|
|
{
|
|
"entropy": 5.327055788040161,
|
|
"epoch": 2.9912010159651667,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000411378874927446,
|
|
"loss": 5.0153,
|
|
"mean_token_accuracy": 0.20757474899291992,
|
|
"num_tokens": 68429967.0,
|
|
"step": 32975
|
|
},
|
|
{
|
|
"entropy": 5.372650623321533,
|
|
"epoch": 2.991654571843251,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004113531382932993,
|
|
"loss": 5.0156,
|
|
"mean_token_accuracy": 0.19970046281814574,
|
|
"num_tokens": 68441639.0,
|
|
"step": 32980
|
|
},
|
|
{
|
|
"entropy": 5.48040280342102,
|
|
"epoch": 2.9921081277213353,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000411327398839335,
|
|
"loss": 5.0589,
|
|
"mean_token_accuracy": 0.19749085754156112,
|
|
"num_tokens": 68452781.0,
|
|
"step": 32985
|
|
},
|
|
{
|
|
"entropy": 5.412837266921997,
|
|
"epoch": 2.9925616835994195,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004113016565660854,
|
|
"loss": 5.0156,
|
|
"mean_token_accuracy": 0.207204906642437,
|
|
"num_tokens": 68463353.0,
|
|
"step": 32990
|
|
},
|
|
{
|
|
"entropy": 5.343805456161499,
|
|
"epoch": 2.9930152394775034,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00041127591147408274,
|
|
"loss": 5.0097,
|
|
"mean_token_accuracy": 0.19936254471540452,
|
|
"num_tokens": 68473507.0,
|
|
"step": 32995
|
|
},
|
|
{
|
|
"entropy": 5.419275569915771,
|
|
"epoch": 2.9934687953555876,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00041125016356385945,
|
|
"loss": 5.026,
|
|
"mean_token_accuracy": 0.20898279845714568,
|
|
"num_tokens": 68483737.0,
|
|
"step": 33000
|
|
},
|
|
{
|
|
"epoch": 2.9934687953555876,
|
|
"eval_entropy": 5.196332440117366,
|
|
"eval_loss": 5.10872220993042,
|
|
"eval_mean_token_accuracy": 0.2095028891864473,
|
|
"eval_num_tokens": 68483737.0,
|
|
"eval_runtime": 26.5736,
|
|
"eval_samples_per_second": 1330.645,
|
|
"eval_steps_per_second": 166.331,
|
|
"step": 33000
|
|
},
|
|
{
|
|
"entropy": 5.413018703460693,
|
|
"epoch": 2.993922351233672,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00041122441283594817,
|
|
"loss": 5.0577,
|
|
"mean_token_accuracy": 0.20816163271665572,
|
|
"num_tokens": 68494013.0,
|
|
"step": 33005
|
|
},
|
|
{
|
|
"entropy": 5.336371326446534,
|
|
"epoch": 2.994375907111756,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004111986592908813,
|
|
"loss": 5.0084,
|
|
"mean_token_accuracy": 0.2110838532447815,
|
|
"num_tokens": 68504361.0,
|
|
"step": 33010
|
|
},
|
|
{
|
|
"entropy": 5.387077140808105,
|
|
"epoch": 2.9948294629898404,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00041117290292919134,
|
|
"loss": 4.9903,
|
|
"mean_token_accuracy": 0.20517551749944687,
|
|
"num_tokens": 68514825.0,
|
|
"step": 33015
|
|
},
|
|
{
|
|
"entropy": 5.440815401077271,
|
|
"epoch": 2.9952830188679247,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004111471437514111,
|
|
"loss": 4.9955,
|
|
"mean_token_accuracy": 0.20155260860919952,
|
|
"num_tokens": 68524858.0,
|
|
"step": 33020
|
|
},
|
|
{
|
|
"entropy": 5.36371259689331,
|
|
"epoch": 2.995736574746009,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004111213817580733,
|
|
"loss": 4.9445,
|
|
"mean_token_accuracy": 0.21869589537382125,
|
|
"num_tokens": 68534481.0,
|
|
"step": 33025
|
|
},
|
|
{
|
|
"entropy": 5.322112369537353,
|
|
"epoch": 2.996190130624093,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004110956169497106,
|
|
"loss": 5.0398,
|
|
"mean_token_accuracy": 0.2047148495912552,
|
|
"num_tokens": 68545436.0,
|
|
"step": 33030
|
|
},
|
|
{
|
|
"entropy": 5.39660530090332,
|
|
"epoch": 2.996643686502177,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004110698493268558,
|
|
"loss": 5.0252,
|
|
"mean_token_accuracy": 0.20899762511253356,
|
|
"num_tokens": 68555434.0,
|
|
"step": 33035
|
|
},
|
|
{
|
|
"entropy": 5.443991088867188,
|
|
"epoch": 2.9970972423802613,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004110440788900419,
|
|
"loss": 5.1515,
|
|
"mean_token_accuracy": 0.20130567401647567,
|
|
"num_tokens": 68566295.0,
|
|
"step": 33040
|
|
},
|
|
{
|
|
"entropy": 5.368240928649902,
|
|
"epoch": 2.9975507982583456,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00041101830563980174,
|
|
"loss": 4.964,
|
|
"mean_token_accuracy": 0.21837229579687117,
|
|
"num_tokens": 68575927.0,
|
|
"step": 33045
|
|
},
|
|
{
|
|
"entropy": 5.476277208328247,
|
|
"epoch": 2.9980043541364294,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00041099252957666843,
|
|
"loss": 5.0615,
|
|
"mean_token_accuracy": 0.20632801651954652,
|
|
"num_tokens": 68586254.0,
|
|
"step": 33050
|
|
},
|
|
{
|
|
"entropy": 5.385083246231079,
|
|
"epoch": 2.9984579100145137,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00041096675070117496,
|
|
"loss": 5.0505,
|
|
"mean_token_accuracy": 0.2046806424856186,
|
|
"num_tokens": 68596881.0,
|
|
"step": 33055
|
|
},
|
|
{
|
|
"entropy": 5.342594146728516,
|
|
"epoch": 2.998911465892598,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00041094096901385434,
|
|
"loss": 4.9458,
|
|
"mean_token_accuracy": 0.21209774613380433,
|
|
"num_tokens": 68606875.0,
|
|
"step": 33060
|
|
},
|
|
{
|
|
"entropy": 5.454997444152832,
|
|
"epoch": 2.999365021770682,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004109151845152399,
|
|
"loss": 5.0634,
|
|
"mean_token_accuracy": 0.2054750457406044,
|
|
"num_tokens": 68617011.0,
|
|
"step": 33065
|
|
},
|
|
{
|
|
"entropy": 5.461607360839844,
|
|
"epoch": 2.9998185776487665,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004108893972058649,
|
|
"loss": 5.0948,
|
|
"mean_token_accuracy": 0.19985458850860596,
|
|
"num_tokens": 68627764.0,
|
|
"step": 33070
|
|
},
|
|
{
|
|
"entropy": 5.464165687561035,
|
|
"epoch": 3.0002721335268503,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00041086360708626236,
|
|
"loss": 5.0125,
|
|
"mean_token_accuracy": 0.20900590270757674,
|
|
"num_tokens": 68637272.0,
|
|
"step": 33075
|
|
},
|
|
{
|
|
"entropy": 5.360660409927368,
|
|
"epoch": 3.0007256894049346,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00041083781415696585,
|
|
"loss": 4.9741,
|
|
"mean_token_accuracy": 0.20505621135234833,
|
|
"num_tokens": 68648058.0,
|
|
"step": 33080
|
|
},
|
|
{
|
|
"entropy": 5.332688522338867,
|
|
"epoch": 3.001179245283019,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004108120184185088,
|
|
"loss": 4.8945,
|
|
"mean_token_accuracy": 0.21415623277425766,
|
|
"num_tokens": 68658174.0,
|
|
"step": 33085
|
|
},
|
|
{
|
|
"entropy": 5.390836524963379,
|
|
"epoch": 3.001632801161103,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00041078621987142457,
|
|
"loss": 4.9616,
|
|
"mean_token_accuracy": 0.2162644922733307,
|
|
"num_tokens": 68669281.0,
|
|
"step": 33090
|
|
},
|
|
{
|
|
"entropy": 5.357333326339722,
|
|
"epoch": 3.0020863570391874,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004107604185162467,
|
|
"loss": 4.9754,
|
|
"mean_token_accuracy": 0.21004239469766617,
|
|
"num_tokens": 68679879.0,
|
|
"step": 33095
|
|
},
|
|
{
|
|
"entropy": 5.353488779067993,
|
|
"epoch": 3.0025399129172716,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00041073461435350877,
|
|
"loss": 4.8723,
|
|
"mean_token_accuracy": 0.21212994307279587,
|
|
"num_tokens": 68689852.0,
|
|
"step": 33100
|
|
},
|
|
{
|
|
"entropy": 5.358632612228393,
|
|
"epoch": 3.0029934687953554,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00041070880738374447,
|
|
"loss": 4.9699,
|
|
"mean_token_accuracy": 0.20714278370141984,
|
|
"num_tokens": 68700149.0,
|
|
"step": 33105
|
|
},
|
|
{
|
|
"entropy": 5.401361703872681,
|
|
"epoch": 3.0034470246734397,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00041068299760748734,
|
|
"loss": 4.964,
|
|
"mean_token_accuracy": 0.20922545939683915,
|
|
"num_tokens": 68710837.0,
|
|
"step": 33110
|
|
},
|
|
{
|
|
"entropy": 5.3996048927307125,
|
|
"epoch": 3.003900580551524,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00041065718502527134,
|
|
"loss": 5.0157,
|
|
"mean_token_accuracy": 0.2089641734957695,
|
|
"num_tokens": 68721451.0,
|
|
"step": 33115
|
|
},
|
|
{
|
|
"entropy": 5.363801956176758,
|
|
"epoch": 3.0043541364296082,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00041063136963763013,
|
|
"loss": 4.9567,
|
|
"mean_token_accuracy": 0.2118072897195816,
|
|
"num_tokens": 68732911.0,
|
|
"step": 33120
|
|
},
|
|
{
|
|
"entropy": 5.345286464691162,
|
|
"epoch": 3.0048076923076925,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004106055514450977,
|
|
"loss": 4.9174,
|
|
"mean_token_accuracy": 0.21509664505720139,
|
|
"num_tokens": 68742650.0,
|
|
"step": 33125
|
|
},
|
|
{
|
|
"entropy": 5.345604372024536,
|
|
"epoch": 3.0052612481857763,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004105797304482079,
|
|
"loss": 4.935,
|
|
"mean_token_accuracy": 0.21093812882900237,
|
|
"num_tokens": 68753660.0,
|
|
"step": 33130
|
|
},
|
|
{
|
|
"entropy": 5.321128892898559,
|
|
"epoch": 3.0057148040638606,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004105539066474947,
|
|
"loss": 4.8502,
|
|
"mean_token_accuracy": 0.2126137286424637,
|
|
"num_tokens": 68763868.0,
|
|
"step": 33135
|
|
},
|
|
{
|
|
"entropy": 5.371802520751953,
|
|
"epoch": 3.006168359941945,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00041052808004349214,
|
|
"loss": 4.9555,
|
|
"mean_token_accuracy": 0.20645214021205902,
|
|
"num_tokens": 68773911.0,
|
|
"step": 33140
|
|
},
|
|
{
|
|
"entropy": 5.459891223907471,
|
|
"epoch": 3.006621915820029,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004105022506367344,
|
|
"loss": 5.0671,
|
|
"mean_token_accuracy": 0.20512431710958481,
|
|
"num_tokens": 68786423.0,
|
|
"step": 33145
|
|
},
|
|
{
|
|
"entropy": 5.385189151763916,
|
|
"epoch": 3.0070754716981134,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004104764184277555,
|
|
"loss": 5.0435,
|
|
"mean_token_accuracy": 0.1992296427488327,
|
|
"num_tokens": 68797329.0,
|
|
"step": 33150
|
|
},
|
|
{
|
|
"entropy": 5.4746846675872805,
|
|
"epoch": 3.0075290275761972,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004104505834170898,
|
|
"loss": 5.0554,
|
|
"mean_token_accuracy": 0.2068174421787262,
|
|
"num_tokens": 68808447.0,
|
|
"step": 33155
|
|
},
|
|
{
|
|
"entropy": 5.4634926319122314,
|
|
"epoch": 3.0079825834542815,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00041042474560527153,
|
|
"loss": 4.9955,
|
|
"mean_token_accuracy": 0.20471063554286956,
|
|
"num_tokens": 68819381.0,
|
|
"step": 33160
|
|
},
|
|
{
|
|
"entropy": 5.289469623565674,
|
|
"epoch": 3.0084361393323658,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000410398904992835,
|
|
"loss": 4.9115,
|
|
"mean_token_accuracy": 0.21886170357465745,
|
|
"num_tokens": 68829319.0,
|
|
"step": 33165
|
|
},
|
|
{
|
|
"entropy": 5.341322946548462,
|
|
"epoch": 3.00888969521045,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00041037306158031464,
|
|
"loss": 5.0258,
|
|
"mean_token_accuracy": 0.20831956267356871,
|
|
"num_tokens": 68838640.0,
|
|
"step": 33170
|
|
},
|
|
{
|
|
"entropy": 5.4534751892089846,
|
|
"epoch": 3.0093432510885343,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004103472153682448,
|
|
"loss": 4.956,
|
|
"mean_token_accuracy": 0.20546354949474335,
|
|
"num_tokens": 68847960.0,
|
|
"step": 33175
|
|
},
|
|
{
|
|
"entropy": 5.394598054885864,
|
|
"epoch": 3.009796806966618,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00041032136635716016,
|
|
"loss": 4.9754,
|
|
"mean_token_accuracy": 0.20483439564704894,
|
|
"num_tokens": 68858851.0,
|
|
"step": 33180
|
|
},
|
|
{
|
|
"entropy": 5.29312481880188,
|
|
"epoch": 3.0102503628447024,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004102955145475951,
|
|
"loss": 4.9391,
|
|
"mean_token_accuracy": 0.20440325438976287,
|
|
"num_tokens": 68869006.0,
|
|
"step": 33185
|
|
},
|
|
{
|
|
"entropy": 5.492068672180176,
|
|
"epoch": 3.0107039187227866,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00041026965994008435,
|
|
"loss": 5.0482,
|
|
"mean_token_accuracy": 0.20347707569599152,
|
|
"num_tokens": 68879606.0,
|
|
"step": 33190
|
|
},
|
|
{
|
|
"entropy": 5.3722639083862305,
|
|
"epoch": 3.011157474600871,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00041024380253516253,
|
|
"loss": 4.928,
|
|
"mean_token_accuracy": 0.2203933745622635,
|
|
"num_tokens": 68889862.0,
|
|
"step": 33195
|
|
},
|
|
{
|
|
"entropy": 5.484805536270142,
|
|
"epoch": 3.011611030478955,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00041021794233336444,
|
|
"loss": 5.0412,
|
|
"mean_token_accuracy": 0.2072233572602272,
|
|
"num_tokens": 68900512.0,
|
|
"step": 33200
|
|
},
|
|
{
|
|
"entropy": 5.393145751953125,
|
|
"epoch": 3.012064586357039,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004101920793352249,
|
|
"loss": 4.9823,
|
|
"mean_token_accuracy": 0.20563024282455444,
|
|
"num_tokens": 68910475.0,
|
|
"step": 33205
|
|
},
|
|
{
|
|
"entropy": 5.432478523254394,
|
|
"epoch": 3.0125181422351233,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004101662135412786,
|
|
"loss": 5.0174,
|
|
"mean_token_accuracy": 0.2095721185207367,
|
|
"num_tokens": 68920583.0,
|
|
"step": 33210
|
|
},
|
|
{
|
|
"entropy": 5.333495140075684,
|
|
"epoch": 3.0129716981132075,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004101403449520606,
|
|
"loss": 4.9119,
|
|
"mean_token_accuracy": 0.20838203728199006,
|
|
"num_tokens": 68931016.0,
|
|
"step": 33215
|
|
},
|
|
{
|
|
"entropy": 5.368942546844482,
|
|
"epoch": 3.013425253991292,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00041011447356810584,
|
|
"loss": 4.9568,
|
|
"mean_token_accuracy": 0.20688424110412598,
|
|
"num_tokens": 68941489.0,
|
|
"step": 33220
|
|
},
|
|
{
|
|
"entropy": 5.41350212097168,
|
|
"epoch": 3.013878809869376,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004100885993899493,
|
|
"loss": 5.0388,
|
|
"mean_token_accuracy": 0.2022132769227028,
|
|
"num_tokens": 68952322.0,
|
|
"step": 33225
|
|
},
|
|
{
|
|
"entropy": 5.396971273422241,
|
|
"epoch": 3.01433236574746,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004100627224181261,
|
|
"loss": 5.0227,
|
|
"mean_token_accuracy": 0.20692562013864518,
|
|
"num_tokens": 68962570.0,
|
|
"step": 33230
|
|
},
|
|
{
|
|
"entropy": 5.425085210800171,
|
|
"epoch": 3.014785921625544,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00041003684265317143,
|
|
"loss": 4.9484,
|
|
"mean_token_accuracy": 0.2111646130681038,
|
|
"num_tokens": 68973733.0,
|
|
"step": 33235
|
|
},
|
|
{
|
|
"entropy": 5.3716956615448,
|
|
"epoch": 3.0152394775036284,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00041001096009562045,
|
|
"loss": 4.9702,
|
|
"mean_token_accuracy": 0.2147448554635048,
|
|
"num_tokens": 68983526.0,
|
|
"step": 33240
|
|
},
|
|
{
|
|
"entropy": 5.430476188659668,
|
|
"epoch": 3.0156930333817127,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004099850747460084,
|
|
"loss": 5.066,
|
|
"mean_token_accuracy": 0.20779648274183274,
|
|
"num_tokens": 68993968.0,
|
|
"step": 33245
|
|
},
|
|
{
|
|
"entropy": 5.464944505691529,
|
|
"epoch": 3.016146589259797,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00040995918660487055,
|
|
"loss": 4.9345,
|
|
"mean_token_accuracy": 0.21965857446193696,
|
|
"num_tokens": 69003599.0,
|
|
"step": 33250
|
|
},
|
|
{
|
|
"entropy": 5.41151008605957,
|
|
"epoch": 3.0166001451378808,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004099332956727424,
|
|
"loss": 4.9544,
|
|
"mean_token_accuracy": 0.20683460980653762,
|
|
"num_tokens": 69013686.0,
|
|
"step": 33255
|
|
},
|
|
{
|
|
"entropy": 5.362606477737427,
|
|
"epoch": 3.017053701015965,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004099074019501593,
|
|
"loss": 4.9634,
|
|
"mean_token_accuracy": 0.20583849102258683,
|
|
"num_tokens": 69023803.0,
|
|
"step": 33260
|
|
},
|
|
{
|
|
"entropy": 5.30820746421814,
|
|
"epoch": 3.0175072568940493,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004098815054376567,
|
|
"loss": 4.8678,
|
|
"mean_token_accuracy": 0.21526146531105042,
|
|
"num_tokens": 69033885.0,
|
|
"step": 33265
|
|
},
|
|
{
|
|
"entropy": 5.386491060256958,
|
|
"epoch": 3.0179608127721336,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004098556061357702,
|
|
"loss": 4.9356,
|
|
"mean_token_accuracy": 0.2097113162279129,
|
|
"num_tokens": 69044471.0,
|
|
"step": 33270
|
|
},
|
|
{
|
|
"entropy": 5.361119508743286,
|
|
"epoch": 3.018414368650218,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00040982970404503544,
|
|
"loss": 4.8443,
|
|
"mean_token_accuracy": 0.21775802224874496,
|
|
"num_tokens": 69055109.0,
|
|
"step": 33275
|
|
},
|
|
{
|
|
"entropy": 5.344230365753174,
|
|
"epoch": 3.018867924528302,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00040980379916598803,
|
|
"loss": 4.9566,
|
|
"mean_token_accuracy": 0.20991152822971343,
|
|
"num_tokens": 69064692.0,
|
|
"step": 33280
|
|
},
|
|
{
|
|
"entropy": 5.410597705841065,
|
|
"epoch": 3.019321480406386,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004097778914991637,
|
|
"loss": 4.9776,
|
|
"mean_token_accuracy": 0.2077532336115837,
|
|
"num_tokens": 69075331.0,
|
|
"step": 33285
|
|
},
|
|
{
|
|
"entropy": 5.3692302227020265,
|
|
"epoch": 3.01977503628447,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00040975198104509827,
|
|
"loss": 4.9523,
|
|
"mean_token_accuracy": 0.212227064371109,
|
|
"num_tokens": 69085017.0,
|
|
"step": 33290
|
|
},
|
|
{
|
|
"entropy": 5.329959106445313,
|
|
"epoch": 3.0202285921625545,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004097260678043275,
|
|
"loss": 4.9538,
|
|
"mean_token_accuracy": 0.20449776351451873,
|
|
"num_tokens": 69096128.0,
|
|
"step": 33295
|
|
},
|
|
{
|
|
"entropy": 5.439202880859375,
|
|
"epoch": 3.0206821480406387,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00040970015177738725,
|
|
"loss": 5.0489,
|
|
"mean_token_accuracy": 0.20628515034914016,
|
|
"num_tokens": 69106479.0,
|
|
"step": 33300
|
|
},
|
|
{
|
|
"entropy": 5.496522569656372,
|
|
"epoch": 3.021135703918723,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004096742329648136,
|
|
"loss": 4.9946,
|
|
"mean_token_accuracy": 0.2026435449719429,
|
|
"num_tokens": 69116346.0,
|
|
"step": 33305
|
|
},
|
|
{
|
|
"entropy": 5.36800332069397,
|
|
"epoch": 3.021589259796807,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004096483113671425,
|
|
"loss": 5.0173,
|
|
"mean_token_accuracy": 0.2053676202893257,
|
|
"num_tokens": 69126489.0,
|
|
"step": 33310
|
|
},
|
|
{
|
|
"entropy": 5.4105932235717775,
|
|
"epoch": 3.022042815674891,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00040962238698490994,
|
|
"loss": 4.9442,
|
|
"mean_token_accuracy": 0.21348126530647277,
|
|
"num_tokens": 69136618.0,
|
|
"step": 33315
|
|
},
|
|
{
|
|
"entropy": 5.452576494216919,
|
|
"epoch": 3.0224963715529753,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004095964598186522,
|
|
"loss": 5.0205,
|
|
"mean_token_accuracy": 0.20183546841144562,
|
|
"num_tokens": 69146242.0,
|
|
"step": 33320
|
|
},
|
|
{
|
|
"entropy": 5.413334941864013,
|
|
"epoch": 3.0229499274310596,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004095705298689053,
|
|
"loss": 4.9511,
|
|
"mean_token_accuracy": 0.21099747270345687,
|
|
"num_tokens": 69157269.0,
|
|
"step": 33325
|
|
},
|
|
{
|
|
"entropy": 5.481033611297607,
|
|
"epoch": 3.023403483309144,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00040954459713620563,
|
|
"loss": 5.0392,
|
|
"mean_token_accuracy": 0.20459752678871154,
|
|
"num_tokens": 69169260.0,
|
|
"step": 33330
|
|
},
|
|
{
|
|
"entropy": 5.48305926322937,
|
|
"epoch": 3.0238570391872277,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004095186616210893,
|
|
"loss": 5.0842,
|
|
"mean_token_accuracy": 0.19440108686685562,
|
|
"num_tokens": 69179815.0,
|
|
"step": 33335
|
|
},
|
|
{
|
|
"entropy": 5.431493806838989,
|
|
"epoch": 3.024310595065312,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004094927233240928,
|
|
"loss": 5.0615,
|
|
"mean_token_accuracy": 0.20560021549463273,
|
|
"num_tokens": 69189959.0,
|
|
"step": 33340
|
|
},
|
|
{
|
|
"entropy": 5.417695045471191,
|
|
"epoch": 3.0247641509433962,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00040946678224575264,
|
|
"loss": 4.9566,
|
|
"mean_token_accuracy": 0.2105316236615181,
|
|
"num_tokens": 69199485.0,
|
|
"step": 33345
|
|
},
|
|
{
|
|
"entropy": 5.368299436569214,
|
|
"epoch": 3.0252177068214805,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000409440838386605,
|
|
"loss": 4.9639,
|
|
"mean_token_accuracy": 0.21055269688367845,
|
|
"num_tokens": 69209180.0,
|
|
"step": 33350
|
|
},
|
|
{
|
|
"entropy": 5.412179565429687,
|
|
"epoch": 3.0256712626995648,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004094148917471866,
|
|
"loss": 5.019,
|
|
"mean_token_accuracy": 0.20606115013360976,
|
|
"num_tokens": 69220648.0,
|
|
"step": 33355
|
|
},
|
|
{
|
|
"entropy": 5.336133575439453,
|
|
"epoch": 3.0261248185776486,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000409388942328034,
|
|
"loss": 4.8457,
|
|
"mean_token_accuracy": 0.21851281076669693,
|
|
"num_tokens": 69230685.0,
|
|
"step": 33360
|
|
},
|
|
{
|
|
"entropy": 5.319089078903199,
|
|
"epoch": 3.026578374455733,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004093629901296838,
|
|
"loss": 5.0081,
|
|
"mean_token_accuracy": 0.20164573043584824,
|
|
"num_tokens": 69240407.0,
|
|
"step": 33365
|
|
},
|
|
{
|
|
"entropy": 5.519814205169678,
|
|
"epoch": 3.027031930333817,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004093370351526727,
|
|
"loss": 5.0418,
|
|
"mean_token_accuracy": 0.2033224657177925,
|
|
"num_tokens": 69250624.0,
|
|
"step": 33370
|
|
},
|
|
{
|
|
"entropy": 5.460324287414551,
|
|
"epoch": 3.0274854862119014,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004093110773975376,
|
|
"loss": 5.0447,
|
|
"mean_token_accuracy": 0.19693015217781068,
|
|
"num_tokens": 69261131.0,
|
|
"step": 33375
|
|
},
|
|
{
|
|
"entropy": 5.340627765655517,
|
|
"epoch": 3.0279390420899857,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004092851168648152,
|
|
"loss": 5.0015,
|
|
"mean_token_accuracy": 0.19961002618074417,
|
|
"num_tokens": 69270668.0,
|
|
"step": 33380
|
|
},
|
|
{
|
|
"entropy": 5.366391849517822,
|
|
"epoch": 3.0283925979680695,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004092591535550422,
|
|
"loss": 4.9226,
|
|
"mean_token_accuracy": 0.21862062811851501,
|
|
"num_tokens": 69280528.0,
|
|
"step": 33385
|
|
},
|
|
{
|
|
"entropy": 5.36923565864563,
|
|
"epoch": 3.0288461538461537,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004092331874687558,
|
|
"loss": 4.9622,
|
|
"mean_token_accuracy": 0.20919521450996398,
|
|
"num_tokens": 69290376.0,
|
|
"step": 33390
|
|
},
|
|
{
|
|
"entropy": 5.405319547653198,
|
|
"epoch": 3.029299709724238,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.00040920721860649285,
|
|
"loss": 4.9782,
|
|
"mean_token_accuracy": 0.21422320753335952,
|
|
"num_tokens": 69301766.0,
|
|
"step": 33395
|
|
},
|
|
{
|
|
"entropy": 5.429558420181275,
|
|
"epoch": 3.0297532656023223,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004091812469687904,
|
|
"loss": 4.9598,
|
|
"mean_token_accuracy": 0.20571360141038894,
|
|
"num_tokens": 69312668.0,
|
|
"step": 33400
|
|
},
|
|
{
|
|
"entropy": 5.411078596115113,
|
|
"epoch": 3.0302068214804065,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004091552725561856,
|
|
"loss": 5.015,
|
|
"mean_token_accuracy": 0.19993540048599243,
|
|
"num_tokens": 69323195.0,
|
|
"step": 33405
|
|
},
|
|
{
|
|
"entropy": 5.341571092605591,
|
|
"epoch": 3.0306603773584904,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004091292953692156,
|
|
"loss": 4.9542,
|
|
"mean_token_accuracy": 0.21174536347389222,
|
|
"num_tokens": 69333812.0,
|
|
"step": 33410
|
|
},
|
|
{
|
|
"entropy": 5.408873558044434,
|
|
"epoch": 3.0311139332365746,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00040910331540841755,
|
|
"loss": 4.9738,
|
|
"mean_token_accuracy": 0.21504355669021608,
|
|
"num_tokens": 69344378.0,
|
|
"step": 33415
|
|
},
|
|
{
|
|
"entropy": 5.3597776889801025,
|
|
"epoch": 3.031567489114659,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00040907733267432877,
|
|
"loss": 4.985,
|
|
"mean_token_accuracy": 0.20827000290155412,
|
|
"num_tokens": 69354592.0,
|
|
"step": 33420
|
|
},
|
|
{
|
|
"entropy": 5.3999309062957765,
|
|
"epoch": 3.032021044992743,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00040905134716748656,
|
|
"loss": 4.9732,
|
|
"mean_token_accuracy": 0.20895325094461442,
|
|
"num_tokens": 69365011.0,
|
|
"step": 33425
|
|
},
|
|
{
|
|
"entropy": 5.3561375617980955,
|
|
"epoch": 3.0324746008708274,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004090253588884284,
|
|
"loss": 4.9782,
|
|
"mean_token_accuracy": 0.2011265739798546,
|
|
"num_tokens": 69377010.0,
|
|
"step": 33430
|
|
},
|
|
{
|
|
"entropy": 5.404412746429443,
|
|
"epoch": 3.0329281567489113,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00040899936783769157,
|
|
"loss": 4.9912,
|
|
"mean_token_accuracy": 0.20858065783977509,
|
|
"num_tokens": 69387263.0,
|
|
"step": 33435
|
|
},
|
|
{
|
|
"entropy": 5.408755922317505,
|
|
"epoch": 3.0333817126269955,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00040897337401581374,
|
|
"loss": 5.0091,
|
|
"mean_token_accuracy": 0.20764359682798386,
|
|
"num_tokens": 69399188.0,
|
|
"step": 33440
|
|
},
|
|
{
|
|
"entropy": 5.388518381118774,
|
|
"epoch": 3.03383526850508,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00040894737742333244,
|
|
"loss": 4.983,
|
|
"mean_token_accuracy": 0.20427111834287642,
|
|
"num_tokens": 69408271.0,
|
|
"step": 33445
|
|
},
|
|
{
|
|
"entropy": 5.472212314605713,
|
|
"epoch": 3.034288824383164,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004089213780607851,
|
|
"loss": 5.0823,
|
|
"mean_token_accuracy": 0.19882635474205018,
|
|
"num_tokens": 69418424.0,
|
|
"step": 33450
|
|
},
|
|
{
|
|
"entropy": 5.424959135055542,
|
|
"epoch": 3.0347423802612483,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004088953759287096,
|
|
"loss": 4.9681,
|
|
"mean_token_accuracy": 0.212503819167614,
|
|
"num_tokens": 69427802.0,
|
|
"step": 33455
|
|
},
|
|
{
|
|
"entropy": 5.36511926651001,
|
|
"epoch": 3.0351959361393326,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004088693710276436,
|
|
"loss": 5.0069,
|
|
"mean_token_accuracy": 0.21071501225233077,
|
|
"num_tokens": 69437581.0,
|
|
"step": 33460
|
|
},
|
|
{
|
|
"entropy": 5.415577173233032,
|
|
"epoch": 3.0356494920174164,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00040884336335812494,
|
|
"loss": 4.9323,
|
|
"mean_token_accuracy": 0.21033487617969512,
|
|
"num_tokens": 69447711.0,
|
|
"step": 33465
|
|
},
|
|
{
|
|
"entropy": 5.46212682723999,
|
|
"epoch": 3.0361030478955007,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004088173529206914,
|
|
"loss": 4.9215,
|
|
"mean_token_accuracy": 0.2122591808438301,
|
|
"num_tokens": 69457692.0,
|
|
"step": 33470
|
|
},
|
|
{
|
|
"entropy": 5.341244888305664,
|
|
"epoch": 3.036556603773585,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004087913397158809,
|
|
"loss": 4.9223,
|
|
"mean_token_accuracy": 0.20891974121332169,
|
|
"num_tokens": 69468034.0,
|
|
"step": 33475
|
|
},
|
|
{
|
|
"entropy": 5.320609092712402,
|
|
"epoch": 3.037010159651669,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00040876532374423135,
|
|
"loss": 4.957,
|
|
"mean_token_accuracy": 0.2119564086198807,
|
|
"num_tokens": 69477719.0,
|
|
"step": 33480
|
|
},
|
|
{
|
|
"entropy": 5.417308664321899,
|
|
"epoch": 3.0374637155297535,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004087393050062809,
|
|
"loss": 4.9712,
|
|
"mean_token_accuracy": 0.20104044079780578,
|
|
"num_tokens": 69487261.0,
|
|
"step": 33485
|
|
},
|
|
{
|
|
"entropy": 5.4207621097564695,
|
|
"epoch": 3.0379172714078373,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00040871328350256745,
|
|
"loss": 4.9491,
|
|
"mean_token_accuracy": 0.20987641662359238,
|
|
"num_tokens": 69496658.0,
|
|
"step": 33490
|
|
},
|
|
{
|
|
"entropy": 5.45028247833252,
|
|
"epoch": 3.0383708272859216,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00040868725923362927,
|
|
"loss": 5.1135,
|
|
"mean_token_accuracy": 0.19764907509088517,
|
|
"num_tokens": 69507197.0,
|
|
"step": 33495
|
|
},
|
|
{
|
|
"entropy": 5.388896894454956,
|
|
"epoch": 3.038824383164006,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00040866123220000455,
|
|
"loss": 5.0074,
|
|
"mean_token_accuracy": 0.21039742231369019,
|
|
"num_tokens": 69516905.0,
|
|
"step": 33500
|
|
},
|
|
{
|
|
"entropy": 5.457586574554443,
|
|
"epoch": 3.03927793904209,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00040863520240223144,
|
|
"loss": 4.9344,
|
|
"mean_token_accuracy": 0.21189486235380173,
|
|
"num_tokens": 69526869.0,
|
|
"step": 33505
|
|
},
|
|
{
|
|
"entropy": 5.440717983245849,
|
|
"epoch": 3.0397314949201744,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004086091698408483,
|
|
"loss": 4.9926,
|
|
"mean_token_accuracy": 0.20492009967565536,
|
|
"num_tokens": 69537058.0,
|
|
"step": 33510
|
|
},
|
|
{
|
|
"entropy": 5.4362043857574465,
|
|
"epoch": 3.040185050798258,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00040858313451639343,
|
|
"loss": 5.0633,
|
|
"mean_token_accuracy": 0.19675164222717284,
|
|
"num_tokens": 69547617.0,
|
|
"step": 33515
|
|
},
|
|
{
|
|
"entropy": 5.434525203704834,
|
|
"epoch": 3.0406386066763424,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004085570964294053,
|
|
"loss": 5.0242,
|
|
"mean_token_accuracy": 0.19647775292396547,
|
|
"num_tokens": 69558733.0,
|
|
"step": 33520
|
|
},
|
|
{
|
|
"entropy": 5.524934434890747,
|
|
"epoch": 3.0410921625544267,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004085310555804225,
|
|
"loss": 5.0851,
|
|
"mean_token_accuracy": 0.1992304652929306,
|
|
"num_tokens": 69570011.0,
|
|
"step": 33525
|
|
},
|
|
{
|
|
"entropy": 5.473267650604248,
|
|
"epoch": 3.041545718432511,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00040850501196998336,
|
|
"loss": 5.1008,
|
|
"mean_token_accuracy": 0.19791147708892823,
|
|
"num_tokens": 69580894.0,
|
|
"step": 33530
|
|
},
|
|
{
|
|
"entropy": 5.401235961914063,
|
|
"epoch": 3.0419992743105952,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00040847896559862654,
|
|
"loss": 5.0041,
|
|
"mean_token_accuracy": 0.2068530797958374,
|
|
"num_tokens": 69591438.0,
|
|
"step": 33535
|
|
},
|
|
{
|
|
"entropy": 5.392526149749756,
|
|
"epoch": 3.042452830188679,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004084529164668907,
|
|
"loss": 5.0024,
|
|
"mean_token_accuracy": 0.20654854029417039,
|
|
"num_tokens": 69601745.0,
|
|
"step": 33540
|
|
},
|
|
{
|
|
"entropy": 5.399510145187378,
|
|
"epoch": 3.0429063860667633,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00040842686457531453,
|
|
"loss": 4.9746,
|
|
"mean_token_accuracy": 0.21126957684755326,
|
|
"num_tokens": 69611872.0,
|
|
"step": 33545
|
|
},
|
|
{
|
|
"entropy": 5.4029285430908205,
|
|
"epoch": 3.0433599419448476,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004084008099244368,
|
|
"loss": 4.9476,
|
|
"mean_token_accuracy": 0.20681148916482925,
|
|
"num_tokens": 69621673.0,
|
|
"step": 33550
|
|
},
|
|
{
|
|
"entropy": 5.353816556930542,
|
|
"epoch": 3.043813497822932,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00040837475251479633,
|
|
"loss": 4.9047,
|
|
"mean_token_accuracy": 0.21161580234766006,
|
|
"num_tokens": 69632090.0,
|
|
"step": 33555
|
|
},
|
|
{
|
|
"entropy": 5.35086989402771,
|
|
"epoch": 3.044267053701016,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000408348692346932,
|
|
"loss": 4.9403,
|
|
"mean_token_accuracy": 0.2123799055814743,
|
|
"num_tokens": 69642920.0,
|
|
"step": 33560
|
|
},
|
|
{
|
|
"entropy": 5.4451720237731935,
|
|
"epoch": 3.0447206095791,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00040832262942138277,
|
|
"loss": 5.0686,
|
|
"mean_token_accuracy": 0.20352713614702225,
|
|
"num_tokens": 69653936.0,
|
|
"step": 33565
|
|
},
|
|
{
|
|
"entropy": 5.380244874954224,
|
|
"epoch": 3.0451741654571842,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004082965637386875,
|
|
"loss": 4.904,
|
|
"mean_token_accuracy": 0.20972564965486526,
|
|
"num_tokens": 69663362.0,
|
|
"step": 33570
|
|
},
|
|
{
|
|
"entropy": 5.353717851638794,
|
|
"epoch": 3.0456277213352685,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004082704952993854,
|
|
"loss": 4.935,
|
|
"mean_token_accuracy": 0.21129612773656845,
|
|
"num_tokens": 69673178.0,
|
|
"step": 33575
|
|
},
|
|
{
|
|
"entropy": 5.450744342803955,
|
|
"epoch": 3.0460812772133528,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004082444241040155,
|
|
"loss": 5.0187,
|
|
"mean_token_accuracy": 0.20730959475040436,
|
|
"num_tokens": 69683627.0,
|
|
"step": 33580
|
|
},
|
|
{
|
|
"entropy": 5.402276802062988,
|
|
"epoch": 3.046534833091437,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004082183501531169,
|
|
"loss": 4.9943,
|
|
"mean_token_accuracy": 0.2093367099761963,
|
|
"num_tokens": 69694010.0,
|
|
"step": 33585
|
|
},
|
|
{
|
|
"entropy": 5.401848268508911,
|
|
"epoch": 3.046988388969521,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00040819227344722893,
|
|
"loss": 5.0078,
|
|
"mean_token_accuracy": 0.20072248280048371,
|
|
"num_tokens": 69704888.0,
|
|
"step": 33590
|
|
},
|
|
{
|
|
"entropy": 5.3750526905059814,
|
|
"epoch": 3.047441944847605,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00040816619398689074,
|
|
"loss": 4.9659,
|
|
"mean_token_accuracy": 0.21443431079387665,
|
|
"num_tokens": 69714718.0,
|
|
"step": 33595
|
|
},
|
|
{
|
|
"entropy": 5.3663575649261475,
|
|
"epoch": 3.0478955007256894,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00040814011177264174,
|
|
"loss": 4.9585,
|
|
"mean_token_accuracy": 0.20567569881677628,
|
|
"num_tokens": 69726076.0,
|
|
"step": 33600
|
|
},
|
|
{
|
|
"entropy": 5.3559335231781,
|
|
"epoch": 3.0483490566037736,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00040811402680502137,
|
|
"loss": 4.9344,
|
|
"mean_token_accuracy": 0.21242115497589112,
|
|
"num_tokens": 69736507.0,
|
|
"step": 33605
|
|
},
|
|
{
|
|
"entropy": 5.333018589019775,
|
|
"epoch": 3.048802612481858,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00040808793908456885,
|
|
"loss": 4.934,
|
|
"mean_token_accuracy": 0.21006479114294052,
|
|
"num_tokens": 69746061.0,
|
|
"step": 33610
|
|
},
|
|
{
|
|
"entropy": 5.374688053131104,
|
|
"epoch": 3.0492561683599417,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004080618486118241,
|
|
"loss": 5.008,
|
|
"mean_token_accuracy": 0.20616169422864913,
|
|
"num_tokens": 69756493.0,
|
|
"step": 33615
|
|
},
|
|
{
|
|
"entropy": 5.393036556243897,
|
|
"epoch": 3.049709724238026,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004080357553873261,
|
|
"loss": 4.9285,
|
|
"mean_token_accuracy": 0.2120664581656456,
|
|
"num_tokens": 69766937.0,
|
|
"step": 33620
|
|
},
|
|
{
|
|
"entropy": 5.338047742843628,
|
|
"epoch": 3.0501632801161103,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000408009659411615,
|
|
"loss": 4.9518,
|
|
"mean_token_accuracy": 0.20979992896318436,
|
|
"num_tokens": 69776872.0,
|
|
"step": 33625
|
|
},
|
|
{
|
|
"entropy": 5.373754930496216,
|
|
"epoch": 3.0506168359941945,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004079835606852301,
|
|
"loss": 4.9636,
|
|
"mean_token_accuracy": 0.2083745762705803,
|
|
"num_tokens": 69788145.0,
|
|
"step": 33630
|
|
},
|
|
{
|
|
"entropy": 5.4049866676330565,
|
|
"epoch": 3.051070391872279,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004079574592087114,
|
|
"loss": 4.965,
|
|
"mean_token_accuracy": 0.20547184348106384,
|
|
"num_tokens": 69797353.0,
|
|
"step": 33635
|
|
},
|
|
{
|
|
"entropy": 5.344005393981933,
|
|
"epoch": 3.051523947750363,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00040793135498259854,
|
|
"loss": 4.9525,
|
|
"mean_token_accuracy": 0.21444593369960785,
|
|
"num_tokens": 69806915.0,
|
|
"step": 33640
|
|
},
|
|
{
|
|
"entropy": 5.35697021484375,
|
|
"epoch": 3.051977503628447,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00040790524800743134,
|
|
"loss": 4.963,
|
|
"mean_token_accuracy": 0.20975673645734788,
|
|
"num_tokens": 69817695.0,
|
|
"step": 33645
|
|
},
|
|
{
|
|
"entropy": 5.3162620067596436,
|
|
"epoch": 3.052431059506531,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004078791382837498,
|
|
"loss": 4.8866,
|
|
"mean_token_accuracy": 0.22530017644166947,
|
|
"num_tokens": 69827451.0,
|
|
"step": 33650
|
|
},
|
|
{
|
|
"entropy": 5.439416790008545,
|
|
"epoch": 3.0528846153846154,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00040785302581209374,
|
|
"loss": 4.9965,
|
|
"mean_token_accuracy": 0.20987783521413803,
|
|
"num_tokens": 69837897.0,
|
|
"step": 33655
|
|
},
|
|
{
|
|
"entropy": 5.374963092803955,
|
|
"epoch": 3.0533381712626997,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00040782691059300326,
|
|
"loss": 4.9417,
|
|
"mean_token_accuracy": 0.20961795151233673,
|
|
"num_tokens": 69847378.0,
|
|
"step": 33660
|
|
},
|
|
{
|
|
"entropy": 5.36504807472229,
|
|
"epoch": 3.053791727140784,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004078007926270185,
|
|
"loss": 5.0361,
|
|
"mean_token_accuracy": 0.20640498846769334,
|
|
"num_tokens": 69857522.0,
|
|
"step": 33665
|
|
},
|
|
{
|
|
"entropy": 5.4503249168396,
|
|
"epoch": 3.0542452830188678,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00040777467191467946,
|
|
"loss": 4.9589,
|
|
"mean_token_accuracy": 0.2096404626965523,
|
|
"num_tokens": 69868384.0,
|
|
"step": 33670
|
|
},
|
|
{
|
|
"entropy": 5.424129056930542,
|
|
"epoch": 3.054698838896952,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004077485484565264,
|
|
"loss": 4.9633,
|
|
"mean_token_accuracy": 0.210124209523201,
|
|
"num_tokens": 69878761.0,
|
|
"step": 33675
|
|
},
|
|
{
|
|
"entropy": 5.379916715621948,
|
|
"epoch": 3.0551523947750363,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004077224222530994,
|
|
"loss": 4.9387,
|
|
"mean_token_accuracy": 0.20277036279439925,
|
|
"num_tokens": 69888366.0,
|
|
"step": 33680
|
|
},
|
|
{
|
|
"entropy": 5.373523950576782,
|
|
"epoch": 3.0556059506531206,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000407696293304939,
|
|
"loss": 4.972,
|
|
"mean_token_accuracy": 0.20280903875827788,
|
|
"num_tokens": 69898489.0,
|
|
"step": 33685
|
|
},
|
|
{
|
|
"entropy": 5.387333536148072,
|
|
"epoch": 3.056059506531205,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004076701616125854,
|
|
"loss": 4.9266,
|
|
"mean_token_accuracy": 0.20672191977500914,
|
|
"num_tokens": 69908425.0,
|
|
"step": 33690
|
|
},
|
|
{
|
|
"entropy": 5.414623737335205,
|
|
"epoch": 3.0565130624092887,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004076440271765791,
|
|
"loss": 5.0057,
|
|
"mean_token_accuracy": 0.20709355771541596,
|
|
"num_tokens": 69918488.0,
|
|
"step": 33695
|
|
},
|
|
{
|
|
"entropy": 5.337385797500611,
|
|
"epoch": 3.056966618287373,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004076178899974605,
|
|
"loss": 4.8824,
|
|
"mean_token_accuracy": 0.2170867383480072,
|
|
"num_tokens": 69928831.0,
|
|
"step": 33700
|
|
},
|
|
{
|
|
"entropy": 5.439281606674195,
|
|
"epoch": 3.057420174165457,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00040759175007577017,
|
|
"loss": 4.9964,
|
|
"mean_token_accuracy": 0.20118823498487473,
|
|
"num_tokens": 69938974.0,
|
|
"step": 33705
|
|
},
|
|
{
|
|
"entropy": 5.3697755336761475,
|
|
"epoch": 3.0578737300435415,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004075656074120486,
|
|
"loss": 4.8775,
|
|
"mean_token_accuracy": 0.21034224182367325,
|
|
"num_tokens": 69948804.0,
|
|
"step": 33710
|
|
},
|
|
{
|
|
"entropy": 5.360610389709473,
|
|
"epoch": 3.0583272859216257,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004075394620068365,
|
|
"loss": 4.9651,
|
|
"mean_token_accuracy": 0.20928685069084169,
|
|
"num_tokens": 69958945.0,
|
|
"step": 33715
|
|
},
|
|
{
|
|
"entropy": 5.365410041809082,
|
|
"epoch": 3.0587808417997095,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00040751331386067456,
|
|
"loss": 4.9159,
|
|
"mean_token_accuracy": 0.21187992990016938,
|
|
"num_tokens": 69968826.0,
|
|
"step": 33720
|
|
},
|
|
{
|
|
"entropy": 5.4671307563781735,
|
|
"epoch": 3.059234397677794,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004074871629741035,
|
|
"loss": 5.0341,
|
|
"mean_token_accuracy": 0.20812514126300813,
|
|
"num_tokens": 69978961.0,
|
|
"step": 33725
|
|
},
|
|
{
|
|
"entropy": 5.328664302825928,
|
|
"epoch": 3.059687953555878,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004074610093476641,
|
|
"loss": 5.0062,
|
|
"mean_token_accuracy": 0.20813081711530684,
|
|
"num_tokens": 69989848.0,
|
|
"step": 33730
|
|
},
|
|
{
|
|
"entropy": 5.386085557937622,
|
|
"epoch": 3.0601415094339623,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00040743485298189744,
|
|
"loss": 4.9466,
|
|
"mean_token_accuracy": 0.20960619151592255,
|
|
"num_tokens": 69999607.0,
|
|
"step": 33735
|
|
},
|
|
{
|
|
"entropy": 5.420104503631592,
|
|
"epoch": 3.0605950653120466,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00040740869387734415,
|
|
"loss": 4.9832,
|
|
"mean_token_accuracy": 0.2103833243250847,
|
|
"num_tokens": 70010446.0,
|
|
"step": 33740
|
|
},
|
|
{
|
|
"entropy": 5.364973640441894,
|
|
"epoch": 3.0610486211901304,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004073825320345453,
|
|
"loss": 4.8892,
|
|
"mean_token_accuracy": 0.21309886425733565,
|
|
"num_tokens": 70021148.0,
|
|
"step": 33745
|
|
},
|
|
{
|
|
"entropy": 5.414050769805908,
|
|
"epoch": 3.0615021770682147,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00040735636745404196,
|
|
"loss": 5.0506,
|
|
"mean_token_accuracy": 0.20042066872119904,
|
|
"num_tokens": 70030765.0,
|
|
"step": 33750
|
|
},
|
|
{
|
|
"entropy": 5.462839126586914,
|
|
"epoch": 3.061955732946299,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00040733020013637526,
|
|
"loss": 4.9924,
|
|
"mean_token_accuracy": 0.20853463411331177,
|
|
"num_tokens": 70041717.0,
|
|
"step": 33755
|
|
},
|
|
{
|
|
"entropy": 5.457137250900269,
|
|
"epoch": 3.0624092888243832,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00040730403008208633,
|
|
"loss": 5.0327,
|
|
"mean_token_accuracy": 0.2035130649805069,
|
|
"num_tokens": 70052178.0,
|
|
"step": 33760
|
|
},
|
|
{
|
|
"entropy": 5.394750547409058,
|
|
"epoch": 3.0628628447024675,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004072778572917163,
|
|
"loss": 4.9922,
|
|
"mean_token_accuracy": 0.20393073558807373,
|
|
"num_tokens": 70062819.0,
|
|
"step": 33765
|
|
},
|
|
{
|
|
"entropy": 5.327018594741821,
|
|
"epoch": 3.0633164005805513,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004072516817658065,
|
|
"loss": 4.9885,
|
|
"mean_token_accuracy": 0.21043820828199386,
|
|
"num_tokens": 70073966.0,
|
|
"step": 33770
|
|
},
|
|
{
|
|
"entropy": 5.43222713470459,
|
|
"epoch": 3.0637699564586356,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00040722550350489825,
|
|
"loss": 4.9737,
|
|
"mean_token_accuracy": 0.20990875214338303,
|
|
"num_tokens": 70083884.0,
|
|
"step": 33775
|
|
},
|
|
{
|
|
"entropy": 5.4832535743713375,
|
|
"epoch": 3.06422351233672,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004071993225095327,
|
|
"loss": 4.9663,
|
|
"mean_token_accuracy": 0.21161504089832306,
|
|
"num_tokens": 70094910.0,
|
|
"step": 33780
|
|
},
|
|
{
|
|
"entropy": 5.3268656730651855,
|
|
"epoch": 3.064677068214804,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004071731387802517,
|
|
"loss": 4.8044,
|
|
"mean_token_accuracy": 0.2213035836815834,
|
|
"num_tokens": 70104480.0,
|
|
"step": 33785
|
|
},
|
|
{
|
|
"entropy": 5.308366298675537,
|
|
"epoch": 3.0651306240928884,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004071469523175964,
|
|
"loss": 4.9395,
|
|
"mean_token_accuracy": 0.21444627046585082,
|
|
"num_tokens": 70114003.0,
|
|
"step": 33790
|
|
},
|
|
{
|
|
"entropy": 5.386834526062012,
|
|
"epoch": 3.065584179970972,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00040712076312210844,
|
|
"loss": 5.0051,
|
|
"mean_token_accuracy": 0.20610248446464538,
|
|
"num_tokens": 70123604.0,
|
|
"step": 33795
|
|
},
|
|
{
|
|
"entropy": 5.42407865524292,
|
|
"epoch": 3.0660377358490565,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00040709457119432945,
|
|
"loss": 5.0078,
|
|
"mean_token_accuracy": 0.20599641352891923,
|
|
"num_tokens": 70133895.0,
|
|
"step": 33800
|
|
},
|
|
{
|
|
"entropy": 5.439183950424194,
|
|
"epoch": 3.0664912917271407,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00040706837653480113,
|
|
"loss": 4.9529,
|
|
"mean_token_accuracy": 0.21360517144203187,
|
|
"num_tokens": 70145063.0,
|
|
"step": 33805
|
|
},
|
|
{
|
|
"entropy": 5.379903411865234,
|
|
"epoch": 3.066944847605225,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000407042179144065,
|
|
"loss": 5.047,
|
|
"mean_token_accuracy": 0.2046153202652931,
|
|
"num_tokens": 70155456.0,
|
|
"step": 33810
|
|
},
|
|
{
|
|
"entropy": 5.297136449813843,
|
|
"epoch": 3.0673984034833093,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00040701597902266306,
|
|
"loss": 4.8979,
|
|
"mean_token_accuracy": 0.21493635326623917,
|
|
"num_tokens": 70165427.0,
|
|
"step": 33815
|
|
},
|
|
{
|
|
"entropy": 5.468492889404297,
|
|
"epoch": 3.067851959361393,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000406989776171137,
|
|
"loss": 5.0251,
|
|
"mean_token_accuracy": 0.20780297070741655,
|
|
"num_tokens": 70175161.0,
|
|
"step": 33820
|
|
},
|
|
{
|
|
"entropy": 5.386501979827881,
|
|
"epoch": 3.0683055152394774,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00040696357059002877,
|
|
"loss": 4.9674,
|
|
"mean_token_accuracy": 0.2159438908100128,
|
|
"num_tokens": 70185026.0,
|
|
"step": 33825
|
|
},
|
|
{
|
|
"entropy": 5.40493221282959,
|
|
"epoch": 3.0687590711175616,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004069373622798802,
|
|
"loss": 4.9714,
|
|
"mean_token_accuracy": 0.21510398536920547,
|
|
"num_tokens": 70195645.0,
|
|
"step": 33830
|
|
},
|
|
{
|
|
"entropy": 5.454832649230957,
|
|
"epoch": 3.069212626995646,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004069111512412334,
|
|
"loss": 5.0508,
|
|
"mean_token_accuracy": 0.2069808453321457,
|
|
"num_tokens": 70206591.0,
|
|
"step": 33835
|
|
},
|
|
{
|
|
"entropy": 5.450249052047729,
|
|
"epoch": 3.06966618287373,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00040688493747463036,
|
|
"loss": 4.9872,
|
|
"mean_token_accuracy": 0.2114460676908493,
|
|
"num_tokens": 70216945.0,
|
|
"step": 33840
|
|
},
|
|
{
|
|
"entropy": 5.327123308181763,
|
|
"epoch": 3.0701197387518144,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004068587209806132,
|
|
"loss": 4.8582,
|
|
"mean_token_accuracy": 0.22277194112539292,
|
|
"num_tokens": 70226983.0,
|
|
"step": 33845
|
|
},
|
|
{
|
|
"entropy": 5.346568918228149,
|
|
"epoch": 3.0705732946298983,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00040683250175972414,
|
|
"loss": 4.9363,
|
|
"mean_token_accuracy": 0.21315456926822662,
|
|
"num_tokens": 70237730.0,
|
|
"step": 33850
|
|
},
|
|
{
|
|
"entropy": 5.4232179641723635,
|
|
"epoch": 3.0710268505079825,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004068062798125053,
|
|
"loss": 5.0303,
|
|
"mean_token_accuracy": 0.20234647989273072,
|
|
"num_tokens": 70248499.0,
|
|
"step": 33855
|
|
},
|
|
{
|
|
"entropy": 5.376066875457764,
|
|
"epoch": 3.071480406386067,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000406780055139499,
|
|
"loss": 4.9439,
|
|
"mean_token_accuracy": 0.2135530084371567,
|
|
"num_tokens": 70259294.0,
|
|
"step": 33860
|
|
},
|
|
{
|
|
"entropy": 5.42730450630188,
|
|
"epoch": 3.071933962264151,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004067538277412476,
|
|
"loss": 5.0264,
|
|
"mean_token_accuracy": 0.20384614467620848,
|
|
"num_tokens": 70269400.0,
|
|
"step": 33865
|
|
},
|
|
{
|
|
"entropy": 5.4761217594146725,
|
|
"epoch": 3.0723875181422353,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004067275976182935,
|
|
"loss": 5.0643,
|
|
"mean_token_accuracy": 0.20960506796836853,
|
|
"num_tokens": 70279380.0,
|
|
"step": 33870
|
|
},
|
|
{
|
|
"entropy": 5.400189733505249,
|
|
"epoch": 3.072841074020319,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00040670136477117906,
|
|
"loss": 4.9667,
|
|
"mean_token_accuracy": 0.21236572414636612,
|
|
"num_tokens": 70289919.0,
|
|
"step": 33875
|
|
},
|
|
{
|
|
"entropy": 5.477989625930786,
|
|
"epoch": 3.0732946298984034,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00040667512920044684,
|
|
"loss": 5.0741,
|
|
"mean_token_accuracy": 0.20753045082092286,
|
|
"num_tokens": 70300136.0,
|
|
"step": 33880
|
|
},
|
|
{
|
|
"entropy": 5.322221851348877,
|
|
"epoch": 3.0737481857764877,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00040664889090663944,
|
|
"loss": 4.8671,
|
|
"mean_token_accuracy": 0.22013276368379592,
|
|
"num_tokens": 70310072.0,
|
|
"step": 33885
|
|
},
|
|
{
|
|
"entropy": 5.397931432723999,
|
|
"epoch": 3.074201741654572,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00040662264989029933,
|
|
"loss": 4.9565,
|
|
"mean_token_accuracy": 0.21083286106586457,
|
|
"num_tokens": 70320185.0,
|
|
"step": 33890
|
|
},
|
|
{
|
|
"entropy": 5.382282876968384,
|
|
"epoch": 3.074655297532656,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004065964061519694,
|
|
"loss": 4.9563,
|
|
"mean_token_accuracy": 0.2082895889878273,
|
|
"num_tokens": 70330211.0,
|
|
"step": 33895
|
|
},
|
|
{
|
|
"entropy": 5.40395975112915,
|
|
"epoch": 3.07510885341074,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004065701596921922,
|
|
"loss": 5.0295,
|
|
"mean_token_accuracy": 0.2016332358121872,
|
|
"num_tokens": 70341044.0,
|
|
"step": 33900
|
|
},
|
|
{
|
|
"entropy": 5.432175207138061,
|
|
"epoch": 3.0755624092888243,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004065439105115106,
|
|
"loss": 5.0222,
|
|
"mean_token_accuracy": 0.20953429490327835,
|
|
"num_tokens": 70351320.0,
|
|
"step": 33905
|
|
},
|
|
{
|
|
"entropy": 5.3616479396820065,
|
|
"epoch": 3.0760159651669086,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00040651765861046734,
|
|
"loss": 4.9017,
|
|
"mean_token_accuracy": 0.22008792012929917,
|
|
"num_tokens": 70361214.0,
|
|
"step": 33910
|
|
},
|
|
{
|
|
"entropy": 5.421438455581665,
|
|
"epoch": 3.076469521044993,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00040649140398960537,
|
|
"loss": 5.0063,
|
|
"mean_token_accuracy": 0.21083803325891495,
|
|
"num_tokens": 70371083.0,
|
|
"step": 33915
|
|
},
|
|
{
|
|
"entropy": 5.447430801391602,
|
|
"epoch": 3.076923076923077,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00040646514664946775,
|
|
"loss": 5.1055,
|
|
"mean_token_accuracy": 0.2071588084101677,
|
|
"num_tokens": 70381987.0,
|
|
"step": 33920
|
|
},
|
|
{
|
|
"entropy": 5.37062783241272,
|
|
"epoch": 3.077376632801161,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004064388865905974,
|
|
"loss": 4.9312,
|
|
"mean_token_accuracy": 0.21333444565534593,
|
|
"num_tokens": 70393462.0,
|
|
"step": 33925
|
|
},
|
|
{
|
|
"entropy": 5.321013593673706,
|
|
"epoch": 3.077830188679245,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004064126238135373,
|
|
"loss": 4.8233,
|
|
"mean_token_accuracy": 0.22526043206453322,
|
|
"num_tokens": 70403664.0,
|
|
"step": 33930
|
|
},
|
|
{
|
|
"entropy": 5.320590925216675,
|
|
"epoch": 3.0782837445573294,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004063863583188308,
|
|
"loss": 4.9866,
|
|
"mean_token_accuracy": 0.20872800946235656,
|
|
"num_tokens": 70414588.0,
|
|
"step": 33935
|
|
},
|
|
{
|
|
"entropy": 5.374155807495117,
|
|
"epoch": 3.0787373004354137,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004063600901070207,
|
|
"loss": 5.0288,
|
|
"mean_token_accuracy": 0.20499978363513946,
|
|
"num_tokens": 70425572.0,
|
|
"step": 33940
|
|
},
|
|
{
|
|
"entropy": 5.414248085021972,
|
|
"epoch": 3.079190856313498,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00040633381917865057,
|
|
"loss": 4.9405,
|
|
"mean_token_accuracy": 0.20446614176034927,
|
|
"num_tokens": 70436140.0,
|
|
"step": 33945
|
|
},
|
|
{
|
|
"entropy": 5.379499101638794,
|
|
"epoch": 3.079644412191582,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004063075455342636,
|
|
"loss": 4.9681,
|
|
"mean_token_accuracy": 0.21319712996482848,
|
|
"num_tokens": 70447117.0,
|
|
"step": 33950
|
|
},
|
|
{
|
|
"entropy": 5.405711603164673,
|
|
"epoch": 3.080097968069666,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004062812691744032,
|
|
"loss": 4.9575,
|
|
"mean_token_accuracy": 0.20904008150100709,
|
|
"num_tokens": 70457756.0,
|
|
"step": 33955
|
|
},
|
|
{
|
|
"entropy": 5.372046089172363,
|
|
"epoch": 3.0805515239477503,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004062549900996126,
|
|
"loss": 5.0164,
|
|
"mean_token_accuracy": 0.20676693618297576,
|
|
"num_tokens": 70468671.0,
|
|
"step": 33960
|
|
},
|
|
{
|
|
"entropy": 5.392218828201294,
|
|
"epoch": 3.0810050798258346,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004062287083104354,
|
|
"loss": 4.9203,
|
|
"mean_token_accuracy": 0.21403491497039795,
|
|
"num_tokens": 70478212.0,
|
|
"step": 33965
|
|
},
|
|
{
|
|
"entropy": 5.3382423400878904,
|
|
"epoch": 3.081458635703919,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00040620242380741504,
|
|
"loss": 4.9547,
|
|
"mean_token_accuracy": 0.21052537411451339,
|
|
"num_tokens": 70489062.0,
|
|
"step": 33970
|
|
},
|
|
{
|
|
"entropy": 5.408094310760498,
|
|
"epoch": 3.0819121915820027,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004061761365910951,
|
|
"loss": 5.034,
|
|
"mean_token_accuracy": 0.20929313600063323,
|
|
"num_tokens": 70499732.0,
|
|
"step": 33975
|
|
},
|
|
{
|
|
"entropy": 5.466299533843994,
|
|
"epoch": 3.082365747460087,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00040614984666201927,
|
|
"loss": 4.9713,
|
|
"mean_token_accuracy": 0.20446203052997589,
|
|
"num_tokens": 70509777.0,
|
|
"step": 33980
|
|
},
|
|
{
|
|
"entropy": 5.42483344078064,
|
|
"epoch": 3.0828193033381712,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004061235540207312,
|
|
"loss": 5.0057,
|
|
"mean_token_accuracy": 0.20639838874340058,
|
|
"num_tokens": 70520674.0,
|
|
"step": 33985
|
|
},
|
|
{
|
|
"entropy": 5.368442535400391,
|
|
"epoch": 3.0832728592162555,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004060972586677746,
|
|
"loss": 4.9755,
|
|
"mean_token_accuracy": 0.20859332233667374,
|
|
"num_tokens": 70531115.0,
|
|
"step": 33990
|
|
},
|
|
{
|
|
"entropy": 5.341448020935059,
|
|
"epoch": 3.0837264150943398,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004060709606036933,
|
|
"loss": 4.9514,
|
|
"mean_token_accuracy": 0.21578848659992217,
|
|
"num_tokens": 70540726.0,
|
|
"step": 33995
|
|
},
|
|
{
|
|
"entropy": 5.389986610412597,
|
|
"epoch": 3.084179970972424,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004060446598290311,
|
|
"loss": 4.9345,
|
|
"mean_token_accuracy": 0.2161898523569107,
|
|
"num_tokens": 70551227.0,
|
|
"step": 34000
|
|
},
|
|
{
|
|
"entropy": 5.330567932128906,
|
|
"epoch": 3.084633526850508,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000406018356344332,
|
|
"loss": 4.9585,
|
|
"mean_token_accuracy": 0.20620685517787934,
|
|
"num_tokens": 70560815.0,
|
|
"step": 34005
|
|
},
|
|
{
|
|
"entropy": 5.440746879577636,
|
|
"epoch": 3.085087082728592,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004059920501501398,
|
|
"loss": 5.038,
|
|
"mean_token_accuracy": 0.20138205587863922,
|
|
"num_tokens": 70570247.0,
|
|
"step": 34010
|
|
},
|
|
{
|
|
"entropy": 5.430915975570679,
|
|
"epoch": 3.0855406386066764,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004059657412469987,
|
|
"loss": 4.9997,
|
|
"mean_token_accuracy": 0.21156656593084336,
|
|
"num_tokens": 70581497.0,
|
|
"step": 34015
|
|
},
|
|
{
|
|
"entropy": 5.391872215270996,
|
|
"epoch": 3.0859941944847606,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004059394296354527,
|
|
"loss": 4.983,
|
|
"mean_token_accuracy": 0.20851872414350509,
|
|
"num_tokens": 70593133.0,
|
|
"step": 34020
|
|
},
|
|
{
|
|
"entropy": 5.391919755935669,
|
|
"epoch": 3.086447750362845,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004059131153160459,
|
|
"loss": 4.9776,
|
|
"mean_token_accuracy": 0.21240515261888504,
|
|
"num_tokens": 70603953.0,
|
|
"step": 34025
|
|
},
|
|
{
|
|
"entropy": 5.36649260520935,
|
|
"epoch": 3.0869013062409287,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004058867982893225,
|
|
"loss": 4.9273,
|
|
"mean_token_accuracy": 0.21510619819164276,
|
|
"num_tokens": 70615292.0,
|
|
"step": 34030
|
|
},
|
|
{
|
|
"entropy": 5.448488426208496,
|
|
"epoch": 3.087354862119013,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004058604785558268,
|
|
"loss": 5.1042,
|
|
"mean_token_accuracy": 0.1977824792265892,
|
|
"num_tokens": 70626681.0,
|
|
"step": 34035
|
|
},
|
|
{
|
|
"entropy": 5.4561927318573,
|
|
"epoch": 3.0878084179970973,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00040583415611610305,
|
|
"loss": 5.0087,
|
|
"mean_token_accuracy": 0.2024817332625389,
|
|
"num_tokens": 70637339.0,
|
|
"step": 34040
|
|
},
|
|
{
|
|
"entropy": 5.446174430847168,
|
|
"epoch": 3.0882619738751815,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004058078309706956,
|
|
"loss": 4.9666,
|
|
"mean_token_accuracy": 0.21367208212614058,
|
|
"num_tokens": 70647980.0,
|
|
"step": 34045
|
|
},
|
|
{
|
|
"entropy": 5.326940727233887,
|
|
"epoch": 3.088715529753266,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004057815031201488,
|
|
"loss": 4.803,
|
|
"mean_token_accuracy": 0.2254161551594734,
|
|
"num_tokens": 70657042.0,
|
|
"step": 34050
|
|
},
|
|
{
|
|
"entropy": 5.391008281707764,
|
|
"epoch": 3.0891690856313496,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004057551725650073,
|
|
"loss": 5.0212,
|
|
"mean_token_accuracy": 0.19898638874292374,
|
|
"num_tokens": 70668542.0,
|
|
"step": 34055
|
|
},
|
|
{
|
|
"entropy": 5.42230224609375,
|
|
"epoch": 3.089622641509434,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00040572883930581544,
|
|
"loss": 5.0294,
|
|
"mean_token_accuracy": 0.20920245945453644,
|
|
"num_tokens": 70679332.0,
|
|
"step": 34060
|
|
},
|
|
{
|
|
"entropy": 5.521007919311524,
|
|
"epoch": 3.090076197387518,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004057025033431179,
|
|
"loss": 5.1047,
|
|
"mean_token_accuracy": 0.20355639308691026,
|
|
"num_tokens": 70689897.0,
|
|
"step": 34065
|
|
},
|
|
{
|
|
"entropy": 5.364918947219849,
|
|
"epoch": 3.0905297532656024,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00040567616467745933,
|
|
"loss": 4.914,
|
|
"mean_token_accuracy": 0.21574291586875916,
|
|
"num_tokens": 70699965.0,
|
|
"step": 34070
|
|
},
|
|
{
|
|
"entropy": 5.385646677017212,
|
|
"epoch": 3.0909833091436867,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004056498233093843,
|
|
"loss": 5.0444,
|
|
"mean_token_accuracy": 0.20981895923614502,
|
|
"num_tokens": 70710583.0,
|
|
"step": 34075
|
|
},
|
|
{
|
|
"entropy": 5.376272439956665,
|
|
"epoch": 3.0914368650217705,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00040562347923943766,
|
|
"loss": 4.9246,
|
|
"mean_token_accuracy": 0.21714130342006682,
|
|
"num_tokens": 70721800.0,
|
|
"step": 34080
|
|
},
|
|
{
|
|
"entropy": 5.3592935562133786,
|
|
"epoch": 3.0918904208998548,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004055971324681642,
|
|
"loss": 4.9744,
|
|
"mean_token_accuracy": 0.20826804637908936,
|
|
"num_tokens": 70731527.0,
|
|
"step": 34085
|
|
},
|
|
{
|
|
"entropy": 5.403912925720215,
|
|
"epoch": 3.092343976777939,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004055707829961087,
|
|
"loss": 4.9923,
|
|
"mean_token_accuracy": 0.20958248674869537,
|
|
"num_tokens": 70740821.0,
|
|
"step": 34090
|
|
},
|
|
{
|
|
"entropy": 5.345268392562867,
|
|
"epoch": 3.0927975326560233,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00040554443082381627,
|
|
"loss": 4.9351,
|
|
"mean_token_accuracy": 0.21259150207042693,
|
|
"num_tokens": 70750506.0,
|
|
"step": 34095
|
|
},
|
|
{
|
|
"entropy": 5.33419361114502,
|
|
"epoch": 3.0932510885341076,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004055180759518315,
|
|
"loss": 4.97,
|
|
"mean_token_accuracy": 0.2150561273097992,
|
|
"num_tokens": 70762009.0,
|
|
"step": 34100
|
|
},
|
|
{
|
|
"entropy": 5.367439270019531,
|
|
"epoch": 3.0937046444121914,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004054917183806999,
|
|
"loss": 4.9485,
|
|
"mean_token_accuracy": 0.20770492255687714,
|
|
"num_tokens": 70772030.0,
|
|
"step": 34105
|
|
},
|
|
{
|
|
"entropy": 5.427121829986572,
|
|
"epoch": 3.0941582002902757,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00040546535811096626,
|
|
"loss": 5.004,
|
|
"mean_token_accuracy": 0.20483729839324952,
|
|
"num_tokens": 70782539.0,
|
|
"step": 34110
|
|
},
|
|
{
|
|
"entropy": 5.511289310455322,
|
|
"epoch": 3.09461175616836,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00040543899514317564,
|
|
"loss": 5.1259,
|
|
"mean_token_accuracy": 0.1933589071035385,
|
|
"num_tokens": 70793433.0,
|
|
"step": 34115
|
|
},
|
|
{
|
|
"entropy": 5.429194498062134,
|
|
"epoch": 3.095065312046444,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004054126294778735,
|
|
"loss": 5.0092,
|
|
"mean_token_accuracy": 0.20400434285402297,
|
|
"num_tokens": 70802919.0,
|
|
"step": 34120
|
|
},
|
|
{
|
|
"entropy": 5.386557245254517,
|
|
"epoch": 3.0955188679245285,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00040538626111560487,
|
|
"loss": 4.9282,
|
|
"mean_token_accuracy": 0.21258202344179153,
|
|
"num_tokens": 70813827.0,
|
|
"step": 34125
|
|
},
|
|
{
|
|
"entropy": 5.444431495666504,
|
|
"epoch": 3.0959724238026123,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00040535989005691515,
|
|
"loss": 5.047,
|
|
"mean_token_accuracy": 0.20873341113328933,
|
|
"num_tokens": 70824117.0,
|
|
"step": 34130
|
|
},
|
|
{
|
|
"entropy": 5.345888948440551,
|
|
"epoch": 3.0964259796806965,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00040533351630234985,
|
|
"loss": 4.8988,
|
|
"mean_token_accuracy": 0.21471309363842012,
|
|
"num_tokens": 70833387.0,
|
|
"step": 34135
|
|
},
|
|
{
|
|
"entropy": 5.384161710739136,
|
|
"epoch": 3.096879535558781,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000405307139852454,
|
|
"loss": 4.9484,
|
|
"mean_token_accuracy": 0.21142172515392305,
|
|
"num_tokens": 70844363.0,
|
|
"step": 34140
|
|
},
|
|
{
|
|
"entropy": 5.393801736831665,
|
|
"epoch": 3.097333091436865,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00040528076070777335,
|
|
"loss": 5.0199,
|
|
"mean_token_accuracy": 0.20669183731079102,
|
|
"num_tokens": 70854759.0,
|
|
"step": 34145
|
|
},
|
|
{
|
|
"entropy": 5.323620748519898,
|
|
"epoch": 3.0977866473149493,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004052543788688534,
|
|
"loss": 4.9882,
|
|
"mean_token_accuracy": 0.21146004945039748,
|
|
"num_tokens": 70865682.0,
|
|
"step": 34150
|
|
},
|
|
{
|
|
"entropy": 5.485985231399536,
|
|
"epoch": 3.098240203193033,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004052279943362396,
|
|
"loss": 5.0191,
|
|
"mean_token_accuracy": 0.20857788175344466,
|
|
"num_tokens": 70875449.0,
|
|
"step": 34155
|
|
},
|
|
{
|
|
"entropy": 5.423348379135132,
|
|
"epoch": 3.0986937590711174,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004052016071104779,
|
|
"loss": 4.9462,
|
|
"mean_token_accuracy": 0.2067654550075531,
|
|
"num_tokens": 70885885.0,
|
|
"step": 34160
|
|
},
|
|
{
|
|
"entropy": 5.366792392730713,
|
|
"epoch": 3.0991473149492017,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004051752171921136,
|
|
"loss": 4.9521,
|
|
"mean_token_accuracy": 0.20977181196212769,
|
|
"num_tokens": 70896320.0,
|
|
"step": 34165
|
|
},
|
|
{
|
|
"entropy": 5.344477701187134,
|
|
"epoch": 3.099600870827286,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00040514882458169267,
|
|
"loss": 4.9082,
|
|
"mean_token_accuracy": 0.2089126303792,
|
|
"num_tokens": 70907074.0,
|
|
"step": 34170
|
|
},
|
|
{
|
|
"entropy": 5.371123266220093,
|
|
"epoch": 3.1000544267053702,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004051224292797609,
|
|
"loss": 4.9764,
|
|
"mean_token_accuracy": 0.20413909405469893,
|
|
"num_tokens": 70916567.0,
|
|
"step": 34175
|
|
},
|
|
{
|
|
"entropy": 5.358697700500488,
|
|
"epoch": 3.100507982583454,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00040509603128686413,
|
|
"loss": 4.9722,
|
|
"mean_token_accuracy": 0.21231076568365098,
|
|
"num_tokens": 70926163.0,
|
|
"step": 34180
|
|
},
|
|
{
|
|
"entropy": 5.413224792480468,
|
|
"epoch": 3.1009615384615383,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004050696306035483,
|
|
"loss": 4.9739,
|
|
"mean_token_accuracy": 0.20706432014703752,
|
|
"num_tokens": 70937358.0,
|
|
"step": 34185
|
|
},
|
|
{
|
|
"entropy": 5.359447193145752,
|
|
"epoch": 3.1014150943396226,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00040504322723035937,
|
|
"loss": 4.9638,
|
|
"mean_token_accuracy": 0.2096409723162651,
|
|
"num_tokens": 70949305.0,
|
|
"step": 34190
|
|
},
|
|
{
|
|
"entropy": 5.299627685546875,
|
|
"epoch": 3.101868650217707,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00040501682116784326,
|
|
"loss": 4.92,
|
|
"mean_token_accuracy": 0.21429477483034134,
|
|
"num_tokens": 70959146.0,
|
|
"step": 34195
|
|
},
|
|
{
|
|
"entropy": 5.345715713500977,
|
|
"epoch": 3.102322206095791,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00040499041241654626,
|
|
"loss": 4.9852,
|
|
"mean_token_accuracy": 0.21171454191207886,
|
|
"num_tokens": 70968828.0,
|
|
"step": 34200
|
|
},
|
|
{
|
|
"entropy": 5.39027886390686,
|
|
"epoch": 3.1027757619738754,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004049640009770144,
|
|
"loss": 4.9698,
|
|
"mean_token_accuracy": 0.21204471290111543,
|
|
"num_tokens": 70979733.0,
|
|
"step": 34205
|
|
},
|
|
{
|
|
"entropy": 5.410312175750732,
|
|
"epoch": 3.103229317851959,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004049375868497939,
|
|
"loss": 5.0226,
|
|
"mean_token_accuracy": 0.21166270971298218,
|
|
"num_tokens": 70989726.0,
|
|
"step": 34210
|
|
},
|
|
{
|
|
"entropy": 5.409689855575562,
|
|
"epoch": 3.1036828737300435,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00040491117003543087,
|
|
"loss": 5.0292,
|
|
"mean_token_accuracy": 0.2058967486023903,
|
|
"num_tokens": 71000715.0,
|
|
"step": 34215
|
|
},
|
|
{
|
|
"entropy": 5.30754017829895,
|
|
"epoch": 3.1041364296081277,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00040488475053447186,
|
|
"loss": 4.8088,
|
|
"mean_token_accuracy": 0.22146107852458954,
|
|
"num_tokens": 71011453.0,
|
|
"step": 34220
|
|
},
|
|
{
|
|
"entropy": 5.37459979057312,
|
|
"epoch": 3.104589985486212,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00040485832834746306,
|
|
"loss": 4.9864,
|
|
"mean_token_accuracy": 0.20893027931451796,
|
|
"num_tokens": 71021477.0,
|
|
"step": 34225
|
|
},
|
|
{
|
|
"entropy": 5.367611217498779,
|
|
"epoch": 3.1050435413642963,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00040483190347495097,
|
|
"loss": 4.9179,
|
|
"mean_token_accuracy": 0.21271353214979172,
|
|
"num_tokens": 71031706.0,
|
|
"step": 34230
|
|
},
|
|
{
|
|
"entropy": 5.41801495552063,
|
|
"epoch": 3.10549709724238,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000404805475917482,
|
|
"loss": 4.9628,
|
|
"mean_token_accuracy": 0.21213012039661408,
|
|
"num_tokens": 71042882.0,
|
|
"step": 34235
|
|
},
|
|
{
|
|
"entropy": 5.341535139083862,
|
|
"epoch": 3.1059506531204644,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00040477904567560275,
|
|
"loss": 4.9435,
|
|
"mean_token_accuracy": 0.2136406973004341,
|
|
"num_tokens": 71052804.0,
|
|
"step": 34240
|
|
},
|
|
{
|
|
"entropy": 5.39377875328064,
|
|
"epoch": 3.1064042089985486,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004047526127498597,
|
|
"loss": 5.0575,
|
|
"mean_token_accuracy": 0.20351703763008117,
|
|
"num_tokens": 71064349.0,
|
|
"step": 34245
|
|
},
|
|
{
|
|
"entropy": 5.38600640296936,
|
|
"epoch": 3.106857764876633,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00040472617714079964,
|
|
"loss": 4.9926,
|
|
"mean_token_accuracy": 0.20882279127836229,
|
|
"num_tokens": 71075754.0,
|
|
"step": 34250
|
|
},
|
|
{
|
|
"entropy": 5.413196420669555,
|
|
"epoch": 3.107311320754717,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004046997388489691,
|
|
"loss": 4.9076,
|
|
"mean_token_accuracy": 0.21182560324668884,
|
|
"num_tokens": 71085338.0,
|
|
"step": 34255
|
|
},
|
|
{
|
|
"entropy": 5.316802930831909,
|
|
"epoch": 3.107764876632801,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004046732978749149,
|
|
"loss": 4.9163,
|
|
"mean_token_accuracy": 0.21405382603406906,
|
|
"num_tokens": 71097089.0,
|
|
"step": 34260
|
|
},
|
|
{
|
|
"entropy": 5.318968152999878,
|
|
"epoch": 3.1082184325108853,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000404646854219184,
|
|
"loss": 4.8844,
|
|
"mean_token_accuracy": 0.2189664825797081,
|
|
"num_tokens": 71106990.0,
|
|
"step": 34265
|
|
},
|
|
{
|
|
"entropy": 5.347984552383423,
|
|
"epoch": 3.1086719883889695,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000404620407882323,
|
|
"loss": 4.9323,
|
|
"mean_token_accuracy": 0.21169679909944533,
|
|
"num_tokens": 71117634.0,
|
|
"step": 34270
|
|
},
|
|
{
|
|
"entropy": 5.33830304145813,
|
|
"epoch": 3.109125544267054,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00040459395886487885,
|
|
"loss": 4.8846,
|
|
"mean_token_accuracy": 0.21105389595031737,
|
|
"num_tokens": 71127717.0,
|
|
"step": 34275
|
|
},
|
|
{
|
|
"entropy": 5.3393237590789795,
|
|
"epoch": 3.109579100145138,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004045675071673988,
|
|
"loss": 4.8885,
|
|
"mean_token_accuracy": 0.22166024893522263,
|
|
"num_tokens": 71137172.0,
|
|
"step": 34280
|
|
},
|
|
{
|
|
"entropy": 5.409679651260376,
|
|
"epoch": 3.110032656023222,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004045410527904296,
|
|
"loss": 4.9927,
|
|
"mean_token_accuracy": 0.20362756550312042,
|
|
"num_tokens": 71146843.0,
|
|
"step": 34285
|
|
},
|
|
{
|
|
"entropy": 5.315624666213989,
|
|
"epoch": 3.110486211901306,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004045145957345184,
|
|
"loss": 4.8796,
|
|
"mean_token_accuracy": 0.21614221185445787,
|
|
"num_tokens": 71156619.0,
|
|
"step": 34290
|
|
},
|
|
{
|
|
"entropy": 5.365515899658203,
|
|
"epoch": 3.1109397677793904,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004044881360002123,
|
|
"loss": 4.9558,
|
|
"mean_token_accuracy": 0.21097393929958344,
|
|
"num_tokens": 71167234.0,
|
|
"step": 34295
|
|
},
|
|
{
|
|
"entropy": 5.366363477706909,
|
|
"epoch": 3.1113933236574747,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004044616735880586,
|
|
"loss": 4.9465,
|
|
"mean_token_accuracy": 0.21720622926950456,
|
|
"num_tokens": 71178049.0,
|
|
"step": 34300
|
|
},
|
|
{
|
|
"entropy": 5.355534505844116,
|
|
"epoch": 3.111846879535559,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00040443520849860453,
|
|
"loss": 4.8974,
|
|
"mean_token_accuracy": 0.20825353115797043,
|
|
"num_tokens": 71188568.0,
|
|
"step": 34305
|
|
},
|
|
{
|
|
"entropy": 5.424851560592652,
|
|
"epoch": 3.1123004354136428,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00040440874073239733,
|
|
"loss": 4.9744,
|
|
"mean_token_accuracy": 0.205704465508461,
|
|
"num_tokens": 71199004.0,
|
|
"step": 34310
|
|
},
|
|
{
|
|
"entropy": 5.333631086349487,
|
|
"epoch": 3.112753991291727,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00040438227028998436,
|
|
"loss": 4.9591,
|
|
"mean_token_accuracy": 0.21005713194608688,
|
|
"num_tokens": 71209239.0,
|
|
"step": 34315
|
|
},
|
|
{
|
|
"entropy": 5.358435869216919,
|
|
"epoch": 3.1132075471698113,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00040435579717191313,
|
|
"loss": 4.9926,
|
|
"mean_token_accuracy": 0.2101889505982399,
|
|
"num_tokens": 71219469.0,
|
|
"step": 34320
|
|
},
|
|
{
|
|
"entropy": 5.41197361946106,
|
|
"epoch": 3.1136611030478956,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00040432932137873107,
|
|
"loss": 5.0154,
|
|
"mean_token_accuracy": 0.20387060642242433,
|
|
"num_tokens": 71230670.0,
|
|
"step": 34325
|
|
},
|
|
{
|
|
"entropy": 5.456201267242432,
|
|
"epoch": 3.11411465892598,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004043028429109857,
|
|
"loss": 5.0846,
|
|
"mean_token_accuracy": 0.20550154149532318,
|
|
"num_tokens": 71241512.0,
|
|
"step": 34330
|
|
},
|
|
{
|
|
"entropy": 5.388176679611206,
|
|
"epoch": 3.1145682148040637,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004042763617692245,
|
|
"loss": 4.9163,
|
|
"mean_token_accuracy": 0.21181716322898864,
|
|
"num_tokens": 71250869.0,
|
|
"step": 34335
|
|
},
|
|
{
|
|
"entropy": 5.292936182022094,
|
|
"epoch": 3.115021770682148,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00040424987795399523,
|
|
"loss": 4.8965,
|
|
"mean_token_accuracy": 0.21311134099960327,
|
|
"num_tokens": 71260577.0,
|
|
"step": 34340
|
|
},
|
|
{
|
|
"entropy": 5.334729242324829,
|
|
"epoch": 3.115475326560232,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004042233914658455,
|
|
"loss": 4.9943,
|
|
"mean_token_accuracy": 0.21045412570238115,
|
|
"num_tokens": 71270185.0,
|
|
"step": 34345
|
|
},
|
|
{
|
|
"entropy": 5.362140226364136,
|
|
"epoch": 3.1159288824383164,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00040419690230532324,
|
|
"loss": 4.9326,
|
|
"mean_token_accuracy": 0.21579869985580444,
|
|
"num_tokens": 71279427.0,
|
|
"step": 34350
|
|
},
|
|
{
|
|
"entropy": 5.377448081970215,
|
|
"epoch": 3.1163824383164007,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00040417041047297606,
|
|
"loss": 4.8941,
|
|
"mean_token_accuracy": 0.21202695667743682,
|
|
"num_tokens": 71290857.0,
|
|
"step": 34355
|
|
},
|
|
{
|
|
"entropy": 5.37336368560791,
|
|
"epoch": 3.116835994194485,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004041439159693518,
|
|
"loss": 5.0092,
|
|
"mean_token_accuracy": 0.2094824030995369,
|
|
"num_tokens": 71300971.0,
|
|
"step": 34360
|
|
},
|
|
{
|
|
"entropy": 5.406455373764038,
|
|
"epoch": 3.117289550072569,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004041174187949985,
|
|
"loss": 5.0901,
|
|
"mean_token_accuracy": 0.20098105370998381,
|
|
"num_tokens": 71311017.0,
|
|
"step": 34365
|
|
},
|
|
{
|
|
"entropy": 5.413253450393677,
|
|
"epoch": 3.117743105950653,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00040409091895046413,
|
|
"loss": 5.0639,
|
|
"mean_token_accuracy": 0.20372433960437775,
|
|
"num_tokens": 71321546.0,
|
|
"step": 34370
|
|
},
|
|
{
|
|
"entropy": 5.377795457839966,
|
|
"epoch": 3.1181966618287373,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00040406441643629656,
|
|
"loss": 4.9784,
|
|
"mean_token_accuracy": 0.2036840558052063,
|
|
"num_tokens": 71332345.0,
|
|
"step": 34375
|
|
},
|
|
{
|
|
"entropy": 5.4588032245635985,
|
|
"epoch": 3.1186502177068216,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00040403791125304405,
|
|
"loss": 5.0729,
|
|
"mean_token_accuracy": 0.20491876304149628,
|
|
"num_tokens": 71342670.0,
|
|
"step": 34380
|
|
},
|
|
{
|
|
"entropy": 5.398355913162232,
|
|
"epoch": 3.119103773584906,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004040114034012546,
|
|
"loss": 4.9069,
|
|
"mean_token_accuracy": 0.20841556638479233,
|
|
"num_tokens": 71353440.0,
|
|
"step": 34385
|
|
},
|
|
{
|
|
"entropy": 5.378566026687622,
|
|
"epoch": 3.1195573294629897,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00040398489288147646,
|
|
"loss": 5.0344,
|
|
"mean_token_accuracy": 0.20847833305597305,
|
|
"num_tokens": 71363199.0,
|
|
"step": 34390
|
|
},
|
|
{
|
|
"entropy": 5.4123228073120115,
|
|
"epoch": 3.120010885341074,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00040395837969425786,
|
|
"loss": 4.9473,
|
|
"mean_token_accuracy": 0.20726829320192336,
|
|
"num_tokens": 71372925.0,
|
|
"step": 34395
|
|
},
|
|
{
|
|
"entropy": 5.4084855079650875,
|
|
"epoch": 3.1204644412191582,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004039318638401471,
|
|
"loss": 4.9776,
|
|
"mean_token_accuracy": 0.21064271479845048,
|
|
"num_tokens": 71383350.0,
|
|
"step": 34400
|
|
},
|
|
{
|
|
"entropy": 5.327110958099365,
|
|
"epoch": 3.1209179970972425,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004039053453196926,
|
|
"loss": 4.9132,
|
|
"mean_token_accuracy": 0.21904214322566987,
|
|
"num_tokens": 71394006.0,
|
|
"step": 34405
|
|
},
|
|
{
|
|
"entropy": 5.330052137374878,
|
|
"epoch": 3.1213715529753268,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004038788241334427,
|
|
"loss": 4.9563,
|
|
"mean_token_accuracy": 0.20923216491937638,
|
|
"num_tokens": 71403945.0,
|
|
"step": 34410
|
|
},
|
|
{
|
|
"entropy": 5.416377878189087,
|
|
"epoch": 3.1218251088534106,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004038523002819458,
|
|
"loss": 4.9966,
|
|
"mean_token_accuracy": 0.20063163936138154,
|
|
"num_tokens": 71414238.0,
|
|
"step": 34415
|
|
},
|
|
{
|
|
"entropy": 5.375718498229981,
|
|
"epoch": 3.122278664731495,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00040382577376575055,
|
|
"loss": 4.9939,
|
|
"mean_token_accuracy": 0.20265325009822846,
|
|
"num_tokens": 71423586.0,
|
|
"step": 34420
|
|
},
|
|
{
|
|
"entropy": 5.394520044326782,
|
|
"epoch": 3.122732220609579,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004037992445854054,
|
|
"loss": 4.9166,
|
|
"mean_token_accuracy": 0.21904806047677994,
|
|
"num_tokens": 71434261.0,
|
|
"step": 34425
|
|
},
|
|
{
|
|
"entropy": 5.379656505584717,
|
|
"epoch": 3.1231857764876634,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00040377271274145916,
|
|
"loss": 4.945,
|
|
"mean_token_accuracy": 0.21178686618804932,
|
|
"num_tokens": 71443952.0,
|
|
"step": 34430
|
|
},
|
|
{
|
|
"entropy": 5.397014617919922,
|
|
"epoch": 3.1236393323657476,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004037461782344603,
|
|
"loss": 4.9464,
|
|
"mean_token_accuracy": 0.21374981701374055,
|
|
"num_tokens": 71454051.0,
|
|
"step": 34435
|
|
},
|
|
{
|
|
"entropy": 5.342506456375122,
|
|
"epoch": 3.1240928882438315,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00040371964106495777,
|
|
"loss": 4.9504,
|
|
"mean_token_accuracy": 0.21411318331956863,
|
|
"num_tokens": 71464579.0,
|
|
"step": 34440
|
|
},
|
|
{
|
|
"entropy": 5.3669415473937985,
|
|
"epoch": 3.1245464441219157,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00040369310123350015,
|
|
"loss": 4.9525,
|
|
"mean_token_accuracy": 0.21506297141313552,
|
|
"num_tokens": 71474631.0,
|
|
"step": 34445
|
|
},
|
|
{
|
|
"entropy": 5.477498865127563,
|
|
"epoch": 3.125,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00040366655874063645,
|
|
"loss": 5.005,
|
|
"mean_token_accuracy": 0.20993651449680328,
|
|
"num_tokens": 71485266.0,
|
|
"step": 34450
|
|
},
|
|
{
|
|
"entropy": 5.318931579589844,
|
|
"epoch": 3.1254535558780843,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004036400135869156,
|
|
"loss": 4.8256,
|
|
"mean_token_accuracy": 0.22117182314395906,
|
|
"num_tokens": 71495248.0,
|
|
"step": 34455
|
|
},
|
|
{
|
|
"entropy": 5.3108323097229,
|
|
"epoch": 3.1259071117561685,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00040361346577288645,
|
|
"loss": 4.9388,
|
|
"mean_token_accuracy": 0.2173376902937889,
|
|
"num_tokens": 71505600.0,
|
|
"step": 34460
|
|
},
|
|
{
|
|
"entropy": 5.388060092926025,
|
|
"epoch": 3.1263606676342524,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00040358691529909796,
|
|
"loss": 4.9897,
|
|
"mean_token_accuracy": 0.2066195383667946,
|
|
"num_tokens": 71516634.0,
|
|
"step": 34465
|
|
},
|
|
{
|
|
"entropy": 5.427005290985107,
|
|
"epoch": 3.1268142235123366,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00040356036216609943,
|
|
"loss": 4.9594,
|
|
"mean_token_accuracy": 0.2083444520831108,
|
|
"num_tokens": 71526745.0,
|
|
"step": 34470
|
|
},
|
|
{
|
|
"entropy": 5.3914618492126465,
|
|
"epoch": 3.127267779390421,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00040353380637443974,
|
|
"loss": 5.0833,
|
|
"mean_token_accuracy": 0.19982859045267104,
|
|
"num_tokens": 71537015.0,
|
|
"step": 34475
|
|
},
|
|
{
|
|
"entropy": 5.353847074508667,
|
|
"epoch": 3.127721335268505,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00040350724792466826,
|
|
"loss": 4.841,
|
|
"mean_token_accuracy": 0.2175277590751648,
|
|
"num_tokens": 71546660.0,
|
|
"step": 34480
|
|
},
|
|
{
|
|
"entropy": 5.3798277378082275,
|
|
"epoch": 3.1281748911465894,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004034806868173341,
|
|
"loss": 4.9786,
|
|
"mean_token_accuracy": 0.21116065084934235,
|
|
"num_tokens": 71557309.0,
|
|
"step": 34485
|
|
},
|
|
{
|
|
"entropy": 5.3431665897369385,
|
|
"epoch": 3.1286284470246732,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004034541230529866,
|
|
"loss": 4.8615,
|
|
"mean_token_accuracy": 0.2122953549027443,
|
|
"num_tokens": 71567651.0,
|
|
"step": 34490
|
|
},
|
|
{
|
|
"entropy": 5.322652339935303,
|
|
"epoch": 3.1290820029027575,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00040342755663217507,
|
|
"loss": 4.8966,
|
|
"mean_token_accuracy": 0.2156175509095192,
|
|
"num_tokens": 71577538.0,
|
|
"step": 34495
|
|
},
|
|
{
|
|
"entropy": 5.30092453956604,
|
|
"epoch": 3.1295355587808418,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000403400987555449,
|
|
"loss": 4.9179,
|
|
"mean_token_accuracy": 0.218988236784935,
|
|
"num_tokens": 71588299.0,
|
|
"step": 34500
|
|
},
|
|
{
|
|
"entropy": 5.357177495956421,
|
|
"epoch": 3.129989114658926,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004033744158233577,
|
|
"loss": 5.03,
|
|
"mean_token_accuracy": 0.2093717560172081,
|
|
"num_tokens": 71598989.0,
|
|
"step": 34505
|
|
},
|
|
{
|
|
"entropy": 5.402267646789551,
|
|
"epoch": 3.1304426705370103,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00040334784143645087,
|
|
"loss": 4.9577,
|
|
"mean_token_accuracy": 0.20841888785362245,
|
|
"num_tokens": 71608596.0,
|
|
"step": 34510
|
|
},
|
|
{
|
|
"entropy": 5.331049394607544,
|
|
"epoch": 3.1308962264150946,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004033212643952779,
|
|
"loss": 4.9048,
|
|
"mean_token_accuracy": 0.21395685225725175,
|
|
"num_tokens": 71619182.0,
|
|
"step": 34515
|
|
},
|
|
{
|
|
"entropy": 5.368327188491821,
|
|
"epoch": 3.1313497822931784,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00040329468470038857,
|
|
"loss": 4.9867,
|
|
"mean_token_accuracy": 0.20585400611162186,
|
|
"num_tokens": 71629526.0,
|
|
"step": 34520
|
|
},
|
|
{
|
|
"entropy": 5.423572254180908,
|
|
"epoch": 3.1318033381712627,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004032681023523324,
|
|
"loss": 5.0386,
|
|
"mean_token_accuracy": 0.20880638360977172,
|
|
"num_tokens": 71640146.0,
|
|
"step": 34525
|
|
},
|
|
{
|
|
"entropy": 5.336004686355591,
|
|
"epoch": 3.132256894049347,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004032415173516592,
|
|
"loss": 4.864,
|
|
"mean_token_accuracy": 0.2146475985646248,
|
|
"num_tokens": 71649652.0,
|
|
"step": 34530
|
|
},
|
|
{
|
|
"entropy": 5.345359420776367,
|
|
"epoch": 3.132710449927431,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004032149296989187,
|
|
"loss": 4.9359,
|
|
"mean_token_accuracy": 0.21555101871490479,
|
|
"num_tokens": 71659264.0,
|
|
"step": 34535
|
|
},
|
|
{
|
|
"entropy": 5.392646169662475,
|
|
"epoch": 3.133164005805515,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00040318833939466083,
|
|
"loss": 4.9707,
|
|
"mean_token_accuracy": 0.2071085900068283,
|
|
"num_tokens": 71669175.0,
|
|
"step": 34540
|
|
},
|
|
{
|
|
"entropy": 5.357173585891724,
|
|
"epoch": 3.1336175616835993,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004031617464394354,
|
|
"loss": 4.9553,
|
|
"mean_token_accuracy": 0.20644948184490203,
|
|
"num_tokens": 71679537.0,
|
|
"step": 34545
|
|
},
|
|
{
|
|
"entropy": 5.403783559799194,
|
|
"epoch": 3.1340711175616836,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004031351508337925,
|
|
"loss": 5.0226,
|
|
"mean_token_accuracy": 0.20997911542654038,
|
|
"num_tokens": 71690024.0,
|
|
"step": 34550
|
|
},
|
|
{
|
|
"entropy": 5.434506750106811,
|
|
"epoch": 3.134524673439768,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004031085525782819,
|
|
"loss": 4.9644,
|
|
"mean_token_accuracy": 0.21139238327741622,
|
|
"num_tokens": 71700019.0,
|
|
"step": 34555
|
|
},
|
|
{
|
|
"entropy": 5.379543828964233,
|
|
"epoch": 3.134978229317852,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004030819516734539,
|
|
"loss": 5.0011,
|
|
"mean_token_accuracy": 0.19721015244722367,
|
|
"num_tokens": 71710570.0,
|
|
"step": 34560
|
|
},
|
|
{
|
|
"entropy": 5.394551038742065,
|
|
"epoch": 3.1354317851959363,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00040305534811985844,
|
|
"loss": 5.0199,
|
|
"mean_token_accuracy": 0.21622054725885392,
|
|
"num_tokens": 71720619.0,
|
|
"step": 34565
|
|
},
|
|
{
|
|
"entropy": 5.382475757598877,
|
|
"epoch": 3.13588534107402,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004030287419180457,
|
|
"loss": 4.9442,
|
|
"mean_token_accuracy": 0.21367517709732056,
|
|
"num_tokens": 71730201.0,
|
|
"step": 34570
|
|
},
|
|
{
|
|
"entropy": 5.403360652923584,
|
|
"epoch": 3.1363388969521044,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00040300213306856606,
|
|
"loss": 4.9772,
|
|
"mean_token_accuracy": 0.21266766637563705,
|
|
"num_tokens": 71741368.0,
|
|
"step": 34575
|
|
},
|
|
{
|
|
"entropy": 5.306556320190429,
|
|
"epoch": 3.1367924528301887,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004029755215719696,
|
|
"loss": 4.9044,
|
|
"mean_token_accuracy": 0.22033482789993286,
|
|
"num_tokens": 71751361.0,
|
|
"step": 34580
|
|
},
|
|
{
|
|
"entropy": 5.388446712493897,
|
|
"epoch": 3.137246008708273,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00040294890742880677,
|
|
"loss": 4.9516,
|
|
"mean_token_accuracy": 0.21206740885972977,
|
|
"num_tokens": 71761164.0,
|
|
"step": 34585
|
|
},
|
|
{
|
|
"entropy": 5.345343971252442,
|
|
"epoch": 3.1376995645863572,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00040292229063962787,
|
|
"loss": 4.9357,
|
|
"mean_token_accuracy": 0.21841154843568802,
|
|
"num_tokens": 71770726.0,
|
|
"step": 34590
|
|
},
|
|
{
|
|
"entropy": 5.430886363983154,
|
|
"epoch": 3.138153120464441,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004028956712049834,
|
|
"loss": 5.0071,
|
|
"mean_token_accuracy": 0.21028072386980057,
|
|
"num_tokens": 71781124.0,
|
|
"step": 34595
|
|
},
|
|
{
|
|
"entropy": 5.340396595001221,
|
|
"epoch": 3.1386066763425253,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000402869049125424,
|
|
"loss": 4.9223,
|
|
"mean_token_accuracy": 0.20577138364315034,
|
|
"num_tokens": 71791218.0,
|
|
"step": 34600
|
|
},
|
|
{
|
|
"entropy": 5.383511018753052,
|
|
"epoch": 3.1390602322206096,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004028424244015,
|
|
"loss": 4.9565,
|
|
"mean_token_accuracy": 0.2107613205909729,
|
|
"num_tokens": 71801013.0,
|
|
"step": 34605
|
|
},
|
|
{
|
|
"entropy": 5.43832836151123,
|
|
"epoch": 3.139513788098694,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000402815797033762,
|
|
"loss": 5.0494,
|
|
"mean_token_accuracy": 0.1993896871805191,
|
|
"num_tokens": 71811742.0,
|
|
"step": 34610
|
|
},
|
|
{
|
|
"entropy": 5.323000240325928,
|
|
"epoch": 3.139967343976778,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004027891670227609,
|
|
"loss": 4.9364,
|
|
"mean_token_accuracy": 0.2053819477558136,
|
|
"num_tokens": 71822265.0,
|
|
"step": 34615
|
|
},
|
|
{
|
|
"entropy": 5.372462415695191,
|
|
"epoch": 3.140420899854862,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004027625343690472,
|
|
"loss": 4.9233,
|
|
"mean_token_accuracy": 0.21033763140439987,
|
|
"num_tokens": 71832090.0,
|
|
"step": 34620
|
|
},
|
|
{
|
|
"entropy": 5.3542462348937985,
|
|
"epoch": 3.140874455732946,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004027358990731717,
|
|
"loss": 4.9358,
|
|
"mean_token_accuracy": 0.21037745773792266,
|
|
"num_tokens": 71841381.0,
|
|
"step": 34625
|
|
},
|
|
{
|
|
"entropy": 5.385398912429809,
|
|
"epoch": 3.1413280116110305,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00040270926113568524,
|
|
"loss": 4.9606,
|
|
"mean_token_accuracy": 0.20852302014827728,
|
|
"num_tokens": 71851383.0,
|
|
"step": 34630
|
|
},
|
|
{
|
|
"entropy": 5.357740688323974,
|
|
"epoch": 3.1417815674891147,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00040268262055713873,
|
|
"loss": 4.951,
|
|
"mean_token_accuracy": 0.21095759570598602,
|
|
"num_tokens": 71862588.0,
|
|
"step": 34635
|
|
},
|
|
{
|
|
"entropy": 5.331533765792846,
|
|
"epoch": 3.142235123367199,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004026559773380831,
|
|
"loss": 4.9367,
|
|
"mean_token_accuracy": 0.20706787705421448,
|
|
"num_tokens": 71873975.0,
|
|
"step": 34640
|
|
},
|
|
{
|
|
"entropy": 5.40365080833435,
|
|
"epoch": 3.142688679245283,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004026293314790694,
|
|
"loss": 5.0135,
|
|
"mean_token_accuracy": 0.20245340317487717,
|
|
"num_tokens": 71884084.0,
|
|
"step": 34645
|
|
},
|
|
{
|
|
"entropy": 5.3743195056915285,
|
|
"epoch": 3.143142235123367,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004026026829806485,
|
|
"loss": 4.9518,
|
|
"mean_token_accuracy": 0.209006467461586,
|
|
"num_tokens": 71894643.0,
|
|
"step": 34650
|
|
},
|
|
{
|
|
"entropy": 5.317592620849609,
|
|
"epoch": 3.1435957910014514,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00040257603184337167,
|
|
"loss": 4.8972,
|
|
"mean_token_accuracy": 0.21569420248270035,
|
|
"num_tokens": 71905245.0,
|
|
"step": 34655
|
|
},
|
|
{
|
|
"entropy": 5.435889768600464,
|
|
"epoch": 3.1440493468795356,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00040254937806778995,
|
|
"loss": 5.0109,
|
|
"mean_token_accuracy": 0.19850692003965378,
|
|
"num_tokens": 71916473.0,
|
|
"step": 34660
|
|
},
|
|
{
|
|
"entropy": 5.370273208618164,
|
|
"epoch": 3.14450290275762,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00040252272165445456,
|
|
"loss": 4.9575,
|
|
"mean_token_accuracy": 0.2111424207687378,
|
|
"num_tokens": 71927465.0,
|
|
"step": 34665
|
|
},
|
|
{
|
|
"entropy": 5.405249214172363,
|
|
"epoch": 3.1449564586357037,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004024960626039168,
|
|
"loss": 4.9568,
|
|
"mean_token_accuracy": 0.21361453980207443,
|
|
"num_tokens": 71937380.0,
|
|
"step": 34670
|
|
},
|
|
{
|
|
"entropy": 5.374631071090699,
|
|
"epoch": 3.145410014513788,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00040246940091672806,
|
|
"loss": 5.0041,
|
|
"mean_token_accuracy": 0.21456093192100525,
|
|
"num_tokens": 71948088.0,
|
|
"step": 34675
|
|
},
|
|
{
|
|
"entropy": 5.361200523376465,
|
|
"epoch": 3.1458635703918723,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004024427365934395,
|
|
"loss": 4.9076,
|
|
"mean_token_accuracy": 0.2201966166496277,
|
|
"num_tokens": 71958284.0,
|
|
"step": 34680
|
|
},
|
|
{
|
|
"entropy": 5.33362078666687,
|
|
"epoch": 3.1463171262699565,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00040241606963460283,
|
|
"loss": 5.0235,
|
|
"mean_token_accuracy": 0.20211744159460068,
|
|
"num_tokens": 71968138.0,
|
|
"step": 34685
|
|
},
|
|
{
|
|
"entropy": 5.432987260818481,
|
|
"epoch": 3.146770682148041,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00040238940004076924,
|
|
"loss": 5.0228,
|
|
"mean_token_accuracy": 0.20766627341508864,
|
|
"num_tokens": 71978275.0,
|
|
"step": 34690
|
|
},
|
|
{
|
|
"entropy": 5.366911315917969,
|
|
"epoch": 3.1472242380261246,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00040236272781249047,
|
|
"loss": 4.9859,
|
|
"mean_token_accuracy": 0.21002472192049026,
|
|
"num_tokens": 71988875.0,
|
|
"step": 34695
|
|
},
|
|
{
|
|
"entropy": 5.363919401168824,
|
|
"epoch": 3.147677793904209,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00040233605295031795,
|
|
"loss": 4.9424,
|
|
"mean_token_accuracy": 0.21187273412942886,
|
|
"num_tokens": 71999560.0,
|
|
"step": 34700
|
|
},
|
|
{
|
|
"entropy": 5.3705206394195555,
|
|
"epoch": 3.148131349782293,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004023093754548034,
|
|
"loss": 4.9588,
|
|
"mean_token_accuracy": 0.21431076824665068,
|
|
"num_tokens": 72009970.0,
|
|
"step": 34705
|
|
},
|
|
{
|
|
"entropy": 5.388108253479004,
|
|
"epoch": 3.1485849056603774,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004022826953264986,
|
|
"loss": 4.9865,
|
|
"mean_token_accuracy": 0.21909504383802414,
|
|
"num_tokens": 72020196.0,
|
|
"step": 34710
|
|
},
|
|
{
|
|
"entropy": 5.385088157653809,
|
|
"epoch": 3.1490384615384617,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00040225601256595525,
|
|
"loss": 4.9219,
|
|
"mean_token_accuracy": 0.21171695291996,
|
|
"num_tokens": 72031456.0,
|
|
"step": 34715
|
|
},
|
|
{
|
|
"entropy": 5.3814976692199705,
|
|
"epoch": 3.149492017416546,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000402229327173725,
|
|
"loss": 5.0305,
|
|
"mean_token_accuracy": 0.20822802782058716,
|
|
"num_tokens": 72042260.0,
|
|
"step": 34720
|
|
},
|
|
{
|
|
"entropy": 5.46431827545166,
|
|
"epoch": 3.1499455732946298,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00040220263915035997,
|
|
"loss": 5.1092,
|
|
"mean_token_accuracy": 0.1889035940170288,
|
|
"num_tokens": 72053463.0,
|
|
"step": 34725
|
|
},
|
|
{
|
|
"entropy": 5.504976272583008,
|
|
"epoch": 3.150399129172714,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00040217594849641195,
|
|
"loss": 5.0854,
|
|
"mean_token_accuracy": 0.20068628042936326,
|
|
"num_tokens": 72064508.0,
|
|
"step": 34730
|
|
},
|
|
{
|
|
"entropy": 5.343131065368652,
|
|
"epoch": 3.1508526850507983,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00040214925521243287,
|
|
"loss": 4.9647,
|
|
"mean_token_accuracy": 0.20980717092752457,
|
|
"num_tokens": 72074758.0,
|
|
"step": 34735
|
|
},
|
|
{
|
|
"entropy": 5.375572729110718,
|
|
"epoch": 3.1513062409288826,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00040212255929897474,
|
|
"loss": 4.9207,
|
|
"mean_token_accuracy": 0.21455363631248475,
|
|
"num_tokens": 72085548.0,
|
|
"step": 34740
|
|
},
|
|
{
|
|
"entropy": 5.387920999526978,
|
|
"epoch": 3.1517597968069664,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004020958607565897,
|
|
"loss": 5.0421,
|
|
"mean_token_accuracy": 0.20320530384778976,
|
|
"num_tokens": 72096773.0,
|
|
"step": 34745
|
|
},
|
|
{
|
|
"entropy": 5.376247262954712,
|
|
"epoch": 3.1522133526850507,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004020691595858299,
|
|
"loss": 5.0213,
|
|
"mean_token_accuracy": 0.20796359181404114,
|
|
"num_tokens": 72106832.0,
|
|
"step": 34750
|
|
},
|
|
{
|
|
"entropy": 5.393571901321411,
|
|
"epoch": 3.152666908563135,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00040204245578724754,
|
|
"loss": 5.0069,
|
|
"mean_token_accuracy": 0.2131665512919426,
|
|
"num_tokens": 72117758.0,
|
|
"step": 34755
|
|
},
|
|
{
|
|
"entropy": 5.412879943847656,
|
|
"epoch": 3.153120464441219,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00040201574936139475,
|
|
"loss": 4.9229,
|
|
"mean_token_accuracy": 0.20792412459850312,
|
|
"num_tokens": 72127522.0,
|
|
"step": 34760
|
|
},
|
|
{
|
|
"entropy": 5.321492910385132,
|
|
"epoch": 3.1535740203193035,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004019890403088239,
|
|
"loss": 4.9682,
|
|
"mean_token_accuracy": 0.21429017186164856,
|
|
"num_tokens": 72138310.0,
|
|
"step": 34765
|
|
},
|
|
{
|
|
"entropy": 5.3383684158325195,
|
|
"epoch": 3.1540275761973877,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00040196232863008735,
|
|
"loss": 5.0037,
|
|
"mean_token_accuracy": 0.21630358695983887,
|
|
"num_tokens": 72148958.0,
|
|
"step": 34770
|
|
},
|
|
{
|
|
"entropy": 5.45716290473938,
|
|
"epoch": 3.1544811320754715,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00040193561432573754,
|
|
"loss": 4.9564,
|
|
"mean_token_accuracy": 0.21751149147748947,
|
|
"num_tokens": 72158594.0,
|
|
"step": 34775
|
|
},
|
|
{
|
|
"entropy": 5.454514074325561,
|
|
"epoch": 3.154934687953556,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004019088973963268,
|
|
"loss": 5.0592,
|
|
"mean_token_accuracy": 0.20609721690416336,
|
|
"num_tokens": 72168552.0,
|
|
"step": 34780
|
|
},
|
|
{
|
|
"entropy": 5.39018497467041,
|
|
"epoch": 3.15538824383164,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00040188217784240785,
|
|
"loss": 4.9148,
|
|
"mean_token_accuracy": 0.2129778653383255,
|
|
"num_tokens": 72178584.0,
|
|
"step": 34785
|
|
},
|
|
{
|
|
"entropy": 5.327080106735229,
|
|
"epoch": 3.1558417997097243,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000401855455664533,
|
|
"loss": 4.9378,
|
|
"mean_token_accuracy": 0.21323640793561935,
|
|
"num_tokens": 72189144.0,
|
|
"step": 34790
|
|
},
|
|
{
|
|
"entropy": 5.396936082839966,
|
|
"epoch": 3.1562953555878086,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004018287308632551,
|
|
"loss": 4.9627,
|
|
"mean_token_accuracy": 0.21348147094249725,
|
|
"num_tokens": 72198326.0,
|
|
"step": 34795
|
|
},
|
|
{
|
|
"entropy": 5.397228193283081,
|
|
"epoch": 3.1567489114658924,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004018020034391266,
|
|
"loss": 4.9494,
|
|
"mean_token_accuracy": 0.21146649569272996,
|
|
"num_tokens": 72207916.0,
|
|
"step": 34800
|
|
},
|
|
{
|
|
"entropy": 5.445782232284546,
|
|
"epoch": 3.1572024673439767,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004017752733927004,
|
|
"loss": 4.9859,
|
|
"mean_token_accuracy": 0.2167130783200264,
|
|
"num_tokens": 72219111.0,
|
|
"step": 34805
|
|
},
|
|
{
|
|
"entropy": 5.334923601150512,
|
|
"epoch": 3.157656023222061,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004017485407245293,
|
|
"loss": 4.9793,
|
|
"mean_token_accuracy": 0.21403907239437103,
|
|
"num_tokens": 72230081.0,
|
|
"step": 34810
|
|
},
|
|
{
|
|
"entropy": 5.334024906158447,
|
|
"epoch": 3.1581095791001452,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000401721805435166,
|
|
"loss": 4.9146,
|
|
"mean_token_accuracy": 0.2150342658162117,
|
|
"num_tokens": 72240693.0,
|
|
"step": 34815
|
|
},
|
|
{
|
|
"entropy": 5.350507974624634,
|
|
"epoch": 3.1585631349782295,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00040169506752516356,
|
|
"loss": 4.889,
|
|
"mean_token_accuracy": 0.22217790484428407,
|
|
"num_tokens": 72250925.0,
|
|
"step": 34820
|
|
},
|
|
{
|
|
"entropy": 5.3101543426513675,
|
|
"epoch": 3.1590166908563133,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004016683269950748,
|
|
"loss": 4.9002,
|
|
"mean_token_accuracy": 0.22428060472011566,
|
|
"num_tokens": 72261027.0,
|
|
"step": 34825
|
|
},
|
|
{
|
|
"entropy": 5.345968389511109,
|
|
"epoch": 3.1594702467343976,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00040164158384545267,
|
|
"loss": 4.8439,
|
|
"mean_token_accuracy": 0.22963706403970718,
|
|
"num_tokens": 72269430.0,
|
|
"step": 34830
|
|
},
|
|
{
|
|
"entropy": 5.282098579406738,
|
|
"epoch": 3.159923802612482,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004016148380768504,
|
|
"loss": 4.8996,
|
|
"mean_token_accuracy": 0.21711872816085814,
|
|
"num_tokens": 72280207.0,
|
|
"step": 34835
|
|
},
|
|
{
|
|
"entropy": 5.395097351074218,
|
|
"epoch": 3.160377358490566,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00040158808968982103,
|
|
"loss": 5.0883,
|
|
"mean_token_accuracy": 0.20572586208581925,
|
|
"num_tokens": 72290093.0,
|
|
"step": 34840
|
|
},
|
|
{
|
|
"entropy": 5.3705864429473875,
|
|
"epoch": 3.1608309143686504,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00040156133868491766,
|
|
"loss": 4.8871,
|
|
"mean_token_accuracy": 0.21355647146701812,
|
|
"num_tokens": 72300203.0,
|
|
"step": 34845
|
|
},
|
|
{
|
|
"entropy": 5.373437023162841,
|
|
"epoch": 3.161284470246734,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00040153458506269365,
|
|
"loss": 4.9688,
|
|
"mean_token_accuracy": 0.20671821832656861,
|
|
"num_tokens": 72311778.0,
|
|
"step": 34850
|
|
},
|
|
{
|
|
"entropy": 5.381914377212524,
|
|
"epoch": 3.1617380261248185,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000401507828823702,
|
|
"loss": 4.9319,
|
|
"mean_token_accuracy": 0.20842544883489608,
|
|
"num_tokens": 72322142.0,
|
|
"step": 34855
|
|
},
|
|
{
|
|
"entropy": 5.4014264106750485,
|
|
"epoch": 3.1621915820029027,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00040148106996849636,
|
|
"loss": 5.0438,
|
|
"mean_token_accuracy": 0.209368035197258,
|
|
"num_tokens": 72332312.0,
|
|
"step": 34860
|
|
},
|
|
{
|
|
"entropy": 5.303100204467773,
|
|
"epoch": 3.162645137880987,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00040145430849762993,
|
|
"loss": 4.8873,
|
|
"mean_token_accuracy": 0.21550435572862625,
|
|
"num_tokens": 72342157.0,
|
|
"step": 34865
|
|
},
|
|
{
|
|
"entropy": 5.427502298355103,
|
|
"epoch": 3.1630986937590713,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00040142754441165615,
|
|
"loss": 4.9685,
|
|
"mean_token_accuracy": 0.20948588997125625,
|
|
"num_tokens": 72353417.0,
|
|
"step": 34870
|
|
},
|
|
{
|
|
"entropy": 5.430898714065552,
|
|
"epoch": 3.1635522496371555,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004014007777111285,
|
|
"loss": 4.9255,
|
|
"mean_token_accuracy": 0.21667166501283647,
|
|
"num_tokens": 72363744.0,
|
|
"step": 34875
|
|
},
|
|
{
|
|
"entropy": 5.348420476913452,
|
|
"epoch": 3.1640058055152394,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00040137400839660066,
|
|
"loss": 5.0053,
|
|
"mean_token_accuracy": 0.20947813391685485,
|
|
"num_tokens": 72375241.0,
|
|
"step": 34880
|
|
},
|
|
{
|
|
"entropy": 5.392428255081176,
|
|
"epoch": 3.1644593613933236,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00040134723646862607,
|
|
"loss": 4.9839,
|
|
"mean_token_accuracy": 0.2093729630112648,
|
|
"num_tokens": 72385475.0,
|
|
"step": 34885
|
|
},
|
|
{
|
|
"entropy": 5.371641826629639,
|
|
"epoch": 3.164912917271408,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00040132046192775835,
|
|
"loss": 5.0429,
|
|
"mean_token_accuracy": 0.2072496384382248,
|
|
"num_tokens": 72396417.0,
|
|
"step": 34890
|
|
},
|
|
{
|
|
"entropy": 5.428116703033448,
|
|
"epoch": 3.165366473149492,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004012936847745514,
|
|
"loss": 4.9971,
|
|
"mean_token_accuracy": 0.21130856722593308,
|
|
"num_tokens": 72406169.0,
|
|
"step": 34895
|
|
},
|
|
{
|
|
"entropy": 5.4249461650848385,
|
|
"epoch": 3.165820029027576,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004012669050095589,
|
|
"loss": 5.0006,
|
|
"mean_token_accuracy": 0.20529956817626954,
|
|
"num_tokens": 72416522.0,
|
|
"step": 34900
|
|
},
|
|
{
|
|
"entropy": 5.406265163421631,
|
|
"epoch": 3.1662735849056602,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004012401226333345,
|
|
"loss": 5.01,
|
|
"mean_token_accuracy": 0.20654958635568618,
|
|
"num_tokens": 72426000.0,
|
|
"step": 34905
|
|
},
|
|
{
|
|
"entropy": 5.41317777633667,
|
|
"epoch": 3.1667271407837445,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004012133376464322,
|
|
"loss": 5.0421,
|
|
"mean_token_accuracy": 0.20693349242210388,
|
|
"num_tokens": 72435952.0,
|
|
"step": 34910
|
|
},
|
|
{
|
|
"entropy": 5.440124416351319,
|
|
"epoch": 3.1671806966618288,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00040118655004940597,
|
|
"loss": 5.0172,
|
|
"mean_token_accuracy": 0.20897049605846404,
|
|
"num_tokens": 72449957.0,
|
|
"step": 34915
|
|
},
|
|
{
|
|
"entropy": 5.421927881240845,
|
|
"epoch": 3.167634252539913,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004011597598428097,
|
|
"loss": 4.9936,
|
|
"mean_token_accuracy": 0.21043002158403395,
|
|
"num_tokens": 72459956.0,
|
|
"step": 34920
|
|
},
|
|
{
|
|
"entropy": 5.36583685874939,
|
|
"epoch": 3.1680878084179973,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004011329670271975,
|
|
"loss": 4.9017,
|
|
"mean_token_accuracy": 0.21610476970672607,
|
|
"num_tokens": 72471107.0,
|
|
"step": 34925
|
|
},
|
|
{
|
|
"entropy": 5.281576776504517,
|
|
"epoch": 3.168541364296081,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00040110617160312334,
|
|
"loss": 4.9136,
|
|
"mean_token_accuracy": 0.2185553714632988,
|
|
"num_tokens": 72481428.0,
|
|
"step": 34930
|
|
},
|
|
{
|
|
"entropy": 5.379683542251587,
|
|
"epoch": 3.1689949201741654,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004010793735711415,
|
|
"loss": 5.0163,
|
|
"mean_token_accuracy": 0.20173770934343338,
|
|
"num_tokens": 72491133.0,
|
|
"step": 34935
|
|
},
|
|
{
|
|
"entropy": 5.332044506072998,
|
|
"epoch": 3.1694484760522497,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00040105257293180605,
|
|
"loss": 4.9036,
|
|
"mean_token_accuracy": 0.2164423555135727,
|
|
"num_tokens": 72502047.0,
|
|
"step": 34940
|
|
},
|
|
{
|
|
"entropy": 5.410404825210572,
|
|
"epoch": 3.169902031930334,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004010257696856712,
|
|
"loss": 4.9708,
|
|
"mean_token_accuracy": 0.20477061420679094,
|
|
"num_tokens": 72513120.0,
|
|
"step": 34945
|
|
},
|
|
{
|
|
"entropy": 5.43150954246521,
|
|
"epoch": 3.170355587808418,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00040099896383329135,
|
|
"loss": 5.0809,
|
|
"mean_token_accuracy": 0.21262899339199065,
|
|
"num_tokens": 72523118.0,
|
|
"step": 34950
|
|
},
|
|
{
|
|
"entropy": 5.436398553848266,
|
|
"epoch": 3.170809143686502,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00040097215537522086,
|
|
"loss": 5.0885,
|
|
"mean_token_accuracy": 0.20874471962451935,
|
|
"num_tokens": 72533697.0,
|
|
"step": 34955
|
|
},
|
|
{
|
|
"entropy": 5.343241739273071,
|
|
"epoch": 3.1712626995645863,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00040094534431201406,
|
|
"loss": 4.9163,
|
|
"mean_token_accuracy": 0.22065825164318084,
|
|
"num_tokens": 72543661.0,
|
|
"step": 34960
|
|
},
|
|
{
|
|
"entropy": 5.402493715286255,
|
|
"epoch": 3.1717162554426706,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004009185306442255,
|
|
"loss": 5.0449,
|
|
"mean_token_accuracy": 0.2071995198726654,
|
|
"num_tokens": 72554551.0,
|
|
"step": 34965
|
|
},
|
|
{
|
|
"entropy": 5.406247663497925,
|
|
"epoch": 3.172169811320755,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00040089171437240954,
|
|
"loss": 5.0704,
|
|
"mean_token_accuracy": 0.2005411669611931,
|
|
"num_tokens": 72565134.0,
|
|
"step": 34970
|
|
},
|
|
{
|
|
"entropy": 5.359982013702393,
|
|
"epoch": 3.172623367198839,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00040086489549712097,
|
|
"loss": 4.9669,
|
|
"mean_token_accuracy": 0.2147507905960083,
|
|
"num_tokens": 72574981.0,
|
|
"step": 34975
|
|
},
|
|
{
|
|
"entropy": 5.367000102996826,
|
|
"epoch": 3.173076923076923,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004008380740189142,
|
|
"loss": 4.9719,
|
|
"mean_token_accuracy": 0.20965934693813323,
|
|
"num_tokens": 72585073.0,
|
|
"step": 34980
|
|
},
|
|
{
|
|
"entropy": 5.435624456405639,
|
|
"epoch": 3.173530478955007,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000400811249938344,
|
|
"loss": 4.9877,
|
|
"mean_token_accuracy": 0.21388707906007767,
|
|
"num_tokens": 72595719.0,
|
|
"step": 34985
|
|
},
|
|
{
|
|
"entropy": 5.429925775527954,
|
|
"epoch": 3.1739840348330914,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004007844232559652,
|
|
"loss": 4.962,
|
|
"mean_token_accuracy": 0.20853069871664048,
|
|
"num_tokens": 72605276.0,
|
|
"step": 34990
|
|
},
|
|
{
|
|
"entropy": 5.415445137023926,
|
|
"epoch": 3.1744375907111757,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004007575939723324,
|
|
"loss": 5.0089,
|
|
"mean_token_accuracy": 0.20749756097793579,
|
|
"num_tokens": 72614964.0,
|
|
"step": 34995
|
|
},
|
|
{
|
|
"entropy": 5.433081340789795,
|
|
"epoch": 3.17489114658926,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004007307620880004,
|
|
"loss": 4.9926,
|
|
"mean_token_accuracy": 0.2106993317604065,
|
|
"num_tokens": 72625461.0,
|
|
"step": 35000
|
|
},
|
|
{
|
|
"entropy": 5.400582122802734,
|
|
"epoch": 3.175344702467344,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00040070392760352424,
|
|
"loss": 5.0095,
|
|
"mean_token_accuracy": 0.21057715713977815,
|
|
"num_tokens": 72636192.0,
|
|
"step": 35005
|
|
},
|
|
{
|
|
"entropy": 5.40768780708313,
|
|
"epoch": 3.175798258345428,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00040067709051945895,
|
|
"loss": 5.0172,
|
|
"mean_token_accuracy": 0.20821761935949326,
|
|
"num_tokens": 72648432.0,
|
|
"step": 35010
|
|
},
|
|
{
|
|
"entropy": 5.393998146057129,
|
|
"epoch": 3.1762518142235123,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004006502508363593,
|
|
"loss": 4.934,
|
|
"mean_token_accuracy": 0.21059673130512238,
|
|
"num_tokens": 72658678.0,
|
|
"step": 35015
|
|
},
|
|
{
|
|
"entropy": 5.494761991500854,
|
|
"epoch": 3.1767053701015966,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00040062340855478046,
|
|
"loss": 5.1531,
|
|
"mean_token_accuracy": 0.20212775468826294,
|
|
"num_tokens": 72669191.0,
|
|
"step": 35020
|
|
},
|
|
{
|
|
"entropy": 5.423246622085571,
|
|
"epoch": 3.177158925979681,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00040059656367527754,
|
|
"loss": 4.9358,
|
|
"mean_token_accuracy": 0.20837749987840654,
|
|
"num_tokens": 72679327.0,
|
|
"step": 35025
|
|
},
|
|
{
|
|
"entropy": 5.390931701660156,
|
|
"epoch": 3.1776124818577647,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004005697161984056,
|
|
"loss": 5.0408,
|
|
"mean_token_accuracy": 0.20667457431554795,
|
|
"num_tokens": 72689673.0,
|
|
"step": 35030
|
|
},
|
|
{
|
|
"entropy": 5.3503138542175295,
|
|
"epoch": 3.178066037735849,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00040054286612472006,
|
|
"loss": 5.0301,
|
|
"mean_token_accuracy": 0.1992456927895546,
|
|
"num_tokens": 72700606.0,
|
|
"step": 35035
|
|
},
|
|
{
|
|
"entropy": 5.45453519821167,
|
|
"epoch": 3.178519593613933,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00040051601345477593,
|
|
"loss": 4.9626,
|
|
"mean_token_accuracy": 0.21093820184469222,
|
|
"num_tokens": 72711195.0,
|
|
"step": 35040
|
|
},
|
|
{
|
|
"entropy": 5.382533168792724,
|
|
"epoch": 3.1789731494920175,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00040048915818912875,
|
|
"loss": 4.9816,
|
|
"mean_token_accuracy": 0.21162929832935334,
|
|
"num_tokens": 72721160.0,
|
|
"step": 35045
|
|
},
|
|
{
|
|
"entropy": 5.327274656295776,
|
|
"epoch": 3.1794267053701017,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00040046230032833374,
|
|
"loss": 4.9848,
|
|
"mean_token_accuracy": 0.2071424812078476,
|
|
"num_tokens": 72730867.0,
|
|
"step": 35050
|
|
},
|
|
{
|
|
"entropy": 5.373201608657837,
|
|
"epoch": 3.1798802612481856,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004004354398729464,
|
|
"loss": 5.0026,
|
|
"mean_token_accuracy": 0.20965151637792587,
|
|
"num_tokens": 72740453.0,
|
|
"step": 35055
|
|
},
|
|
{
|
|
"entropy": 5.466176605224609,
|
|
"epoch": 3.18033381712627,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004004085768235222,
|
|
"loss": 5.0338,
|
|
"mean_token_accuracy": 0.19995568841695785,
|
|
"num_tokens": 72751395.0,
|
|
"step": 35060
|
|
},
|
|
{
|
|
"entropy": 5.399306058883667,
|
|
"epoch": 3.180787373004354,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00040038171118061673,
|
|
"loss": 4.9565,
|
|
"mean_token_accuracy": 0.21097032725811005,
|
|
"num_tokens": 72761300.0,
|
|
"step": 35065
|
|
},
|
|
{
|
|
"entropy": 5.307538080215454,
|
|
"epoch": 3.1812409288824384,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004003548429447855,
|
|
"loss": 4.9316,
|
|
"mean_token_accuracy": 0.22054625302553177,
|
|
"num_tokens": 72772011.0,
|
|
"step": 35070
|
|
},
|
|
{
|
|
"entropy": 5.381379556655884,
|
|
"epoch": 3.1816944847605226,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004003279721165841,
|
|
"loss": 4.9804,
|
|
"mean_token_accuracy": 0.2055664613842964,
|
|
"num_tokens": 72782521.0,
|
|
"step": 35075
|
|
},
|
|
{
|
|
"entropy": 5.328105831146241,
|
|
"epoch": 3.182148040638607,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004003010986965683,
|
|
"loss": 4.8833,
|
|
"mean_token_accuracy": 0.2122318282723427,
|
|
"num_tokens": 72793125.0,
|
|
"step": 35080
|
|
},
|
|
{
|
|
"entropy": 5.449015045166016,
|
|
"epoch": 3.1826015965166907,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000400274222685294,
|
|
"loss": 5.0122,
|
|
"mean_token_accuracy": 0.20642999708652496,
|
|
"num_tokens": 72804541.0,
|
|
"step": 35085
|
|
},
|
|
{
|
|
"entropy": 5.541956043243408,
|
|
"epoch": 3.183055152394775,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00040024734408331664,
|
|
"loss": 5.0777,
|
|
"mean_token_accuracy": 0.21144443154335021,
|
|
"num_tokens": 72814447.0,
|
|
"step": 35090
|
|
},
|
|
{
|
|
"entropy": 5.415646123886108,
|
|
"epoch": 3.1835087082728593,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00040022046289119246,
|
|
"loss": 4.9976,
|
|
"mean_token_accuracy": 0.21780386120080947,
|
|
"num_tokens": 72823545.0,
|
|
"step": 35095
|
|
},
|
|
{
|
|
"entropy": 5.34375958442688,
|
|
"epoch": 3.1839622641509435,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00040019357910947714,
|
|
"loss": 4.8551,
|
|
"mean_token_accuracy": 0.21355679184198378,
|
|
"num_tokens": 72833803.0,
|
|
"step": 35100
|
|
},
|
|
{
|
|
"entropy": 5.425967216491699,
|
|
"epoch": 3.1844158200290273,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00040016669273872666,
|
|
"loss": 4.9871,
|
|
"mean_token_accuracy": 0.20973266661167145,
|
|
"num_tokens": 72843383.0,
|
|
"step": 35105
|
|
},
|
|
{
|
|
"entropy": 5.427226972579956,
|
|
"epoch": 3.1848693759071116,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00040013980377949716,
|
|
"loss": 5.0448,
|
|
"mean_token_accuracy": 0.20614749193191528,
|
|
"num_tokens": 72853285.0,
|
|
"step": 35110
|
|
},
|
|
{
|
|
"entropy": 5.412894153594971,
|
|
"epoch": 3.185322931785196,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00040011291223234456,
|
|
"loss": 5.0258,
|
|
"mean_token_accuracy": 0.20640143156051635,
|
|
"num_tokens": 72863556.0,
|
|
"step": 35115
|
|
},
|
|
{
|
|
"entropy": 5.425095558166504,
|
|
"epoch": 3.18577648766328,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00040008601809782507,
|
|
"loss": 4.9093,
|
|
"mean_token_accuracy": 0.21102923154830933,
|
|
"num_tokens": 72873296.0,
|
|
"step": 35120
|
|
},
|
|
{
|
|
"entropy": 5.405566263198852,
|
|
"epoch": 3.1862300435413644,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004000591213764948,
|
|
"loss": 5.0643,
|
|
"mean_token_accuracy": 0.19814064651727675,
|
|
"num_tokens": 72884738.0,
|
|
"step": 35125
|
|
},
|
|
{
|
|
"entropy": 5.44295973777771,
|
|
"epoch": 3.1866835994194487,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00040003222206891017,
|
|
"loss": 5.0169,
|
|
"mean_token_accuracy": 0.2034027874469757,
|
|
"num_tokens": 72894573.0,
|
|
"step": 35130
|
|
},
|
|
{
|
|
"entropy": 5.352384757995606,
|
|
"epoch": 3.1871371552975325,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004000053201756272,
|
|
"loss": 4.9245,
|
|
"mean_token_accuracy": 0.21167003810405732,
|
|
"num_tokens": 72904976.0,
|
|
"step": 35135
|
|
},
|
|
{
|
|
"entropy": 5.394094467163086,
|
|
"epoch": 3.1875907111756168,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003999784156972024,
|
|
"loss": 4.9708,
|
|
"mean_token_accuracy": 0.207271908223629,
|
|
"num_tokens": 72915152.0,
|
|
"step": 35140
|
|
},
|
|
{
|
|
"entropy": 5.441866111755371,
|
|
"epoch": 3.188044267053701,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0003999515086341921,
|
|
"loss": 5.0626,
|
|
"mean_token_accuracy": 0.20511133670806886,
|
|
"num_tokens": 72925450.0,
|
|
"step": 35145
|
|
},
|
|
{
|
|
"entropy": 5.3905909061431885,
|
|
"epoch": 3.1884978229317853,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0003999245989871527,
|
|
"loss": 4.9128,
|
|
"mean_token_accuracy": 0.2066663235425949,
|
|
"num_tokens": 72935990.0,
|
|
"step": 35150
|
|
},
|
|
{
|
|
"entropy": 5.35360107421875,
|
|
"epoch": 3.1889513788098696,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00039989768675664084,
|
|
"loss": 4.8324,
|
|
"mean_token_accuracy": 0.2126160517334938,
|
|
"num_tokens": 72945662.0,
|
|
"step": 35155
|
|
},
|
|
{
|
|
"entropy": 5.280396366119385,
|
|
"epoch": 3.1894049346879534,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00039987077194321305,
|
|
"loss": 4.7999,
|
|
"mean_token_accuracy": 0.21994009464979172,
|
|
"num_tokens": 72955313.0,
|
|
"step": 35160
|
|
},
|
|
{
|
|
"entropy": 5.417825698852539,
|
|
"epoch": 3.1898584905660377,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00039984385454742576,
|
|
"loss": 5.0896,
|
|
"mean_token_accuracy": 0.20180364698171616,
|
|
"num_tokens": 72965347.0,
|
|
"step": 35165
|
|
},
|
|
{
|
|
"entropy": 5.380123519897461,
|
|
"epoch": 3.190312046444122,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00039981693456983574,
|
|
"loss": 4.9109,
|
|
"mean_token_accuracy": 0.20913738310337066,
|
|
"num_tokens": 72976794.0,
|
|
"step": 35170
|
|
},
|
|
{
|
|
"entropy": 5.335891485214233,
|
|
"epoch": 3.190765602322206,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003997900120109998,
|
|
"loss": 4.9893,
|
|
"mean_token_accuracy": 0.2121645286679268,
|
|
"num_tokens": 72986837.0,
|
|
"step": 35175
|
|
},
|
|
{
|
|
"entropy": 5.385090732574463,
|
|
"epoch": 3.1912191582002905,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0003997630868714745,
|
|
"loss": 4.9553,
|
|
"mean_token_accuracy": 0.209311144053936,
|
|
"num_tokens": 72996819.0,
|
|
"step": 35180
|
|
},
|
|
{
|
|
"entropy": 5.323226690292358,
|
|
"epoch": 3.1916727140783743,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00039973615915181687,
|
|
"loss": 4.8427,
|
|
"mean_token_accuracy": 0.21907134652137755,
|
|
"num_tokens": 73005963.0,
|
|
"step": 35185
|
|
},
|
|
{
|
|
"entropy": 5.327568674087525,
|
|
"epoch": 3.1921262699564585,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00039970922885258363,
|
|
"loss": 5.0133,
|
|
"mean_token_accuracy": 0.2031439647078514,
|
|
"num_tokens": 73015912.0,
|
|
"step": 35190
|
|
},
|
|
{
|
|
"entropy": 5.318052768707275,
|
|
"epoch": 3.192579825834543,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0003996822959743318,
|
|
"loss": 4.8688,
|
|
"mean_token_accuracy": 0.2234595388174057,
|
|
"num_tokens": 73026528.0,
|
|
"step": 35195
|
|
},
|
|
{
|
|
"entropy": 5.382684421539307,
|
|
"epoch": 3.193033381712627,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003996553605176183,
|
|
"loss": 5.0074,
|
|
"mean_token_accuracy": 0.20513821691274642,
|
|
"num_tokens": 73036255.0,
|
|
"step": 35200
|
|
},
|
|
{
|
|
"entropy": 5.426249217987061,
|
|
"epoch": 3.1934869375907113,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0003996284224830002,
|
|
"loss": 5.0775,
|
|
"mean_token_accuracy": 0.205106420814991,
|
|
"num_tokens": 73046686.0,
|
|
"step": 35205
|
|
},
|
|
{
|
|
"entropy": 5.395255184173584,
|
|
"epoch": 3.193940493468795,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00039960148187103453,
|
|
"loss": 4.8808,
|
|
"mean_token_accuracy": 0.2170860782265663,
|
|
"num_tokens": 73056070.0,
|
|
"step": 35210
|
|
},
|
|
{
|
|
"entropy": 5.442257881164551,
|
|
"epoch": 3.1943940493468794,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00039957453868227845,
|
|
"loss": 5.0051,
|
|
"mean_token_accuracy": 0.21265001446008683,
|
|
"num_tokens": 73066288.0,
|
|
"step": 35215
|
|
},
|
|
{
|
|
"entropy": 5.376668119430542,
|
|
"epoch": 3.1948476052249637,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00039954759291728915,
|
|
"loss": 4.9634,
|
|
"mean_token_accuracy": 0.21290157735347748,
|
|
"num_tokens": 73076297.0,
|
|
"step": 35220
|
|
},
|
|
{
|
|
"entropy": 5.406425333023071,
|
|
"epoch": 3.195301161103048,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00039952064457662395,
|
|
"loss": 5.0325,
|
|
"mean_token_accuracy": 0.20899555087089539,
|
|
"num_tokens": 73086249.0,
|
|
"step": 35225
|
|
},
|
|
{
|
|
"entropy": 5.350601673126221,
|
|
"epoch": 3.1957547169811322,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00039949369366084,
|
|
"loss": 4.9182,
|
|
"mean_token_accuracy": 0.21585121154785156,
|
|
"num_tokens": 73096358.0,
|
|
"step": 35230
|
|
},
|
|
{
|
|
"entropy": 5.342401504516602,
|
|
"epoch": 3.196208272859216,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00039946674017049484,
|
|
"loss": 4.9005,
|
|
"mean_token_accuracy": 0.20905726701021193,
|
|
"num_tokens": 73106891.0,
|
|
"step": 35235
|
|
},
|
|
{
|
|
"entropy": 5.322328901290893,
|
|
"epoch": 3.1966618287373003,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00039943978410614565,
|
|
"loss": 4.9063,
|
|
"mean_token_accuracy": 0.21472661048173905,
|
|
"num_tokens": 73117106.0,
|
|
"step": 35240
|
|
},
|
|
{
|
|
"entropy": 5.39273681640625,
|
|
"epoch": 3.1971153846153846,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00039941282546835017,
|
|
"loss": 4.977,
|
|
"mean_token_accuracy": 0.2123194456100464,
|
|
"num_tokens": 73127112.0,
|
|
"step": 35245
|
|
},
|
|
{
|
|
"entropy": 5.38098373413086,
|
|
"epoch": 3.197568940493469,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00039938586425766564,
|
|
"loss": 4.9787,
|
|
"mean_token_accuracy": 0.20952617824077607,
|
|
"num_tokens": 73137751.0,
|
|
"step": 35250
|
|
},
|
|
{
|
|
"entropy": 5.4103710651397705,
|
|
"epoch": 3.198022496371553,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0003993589004746498,
|
|
"loss": 4.9703,
|
|
"mean_token_accuracy": 0.21299329847097398,
|
|
"num_tokens": 73149303.0,
|
|
"step": 35255
|
|
},
|
|
{
|
|
"entropy": 5.356432819366455,
|
|
"epoch": 3.198476052249637,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00039933193411986024,
|
|
"loss": 4.9426,
|
|
"mean_token_accuracy": 0.21107823699712752,
|
|
"num_tokens": 73160025.0,
|
|
"step": 35260
|
|
},
|
|
{
|
|
"entropy": 5.360507392883301,
|
|
"epoch": 3.198929608127721,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00039930496519385454,
|
|
"loss": 4.9525,
|
|
"mean_token_accuracy": 0.21778085082769394,
|
|
"num_tokens": 73170721.0,
|
|
"step": 35265
|
|
},
|
|
{
|
|
"entropy": 5.387619113922119,
|
|
"epoch": 3.1993831640058055,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00039927799369719047,
|
|
"loss": 4.9878,
|
|
"mean_token_accuracy": 0.20736612379550934,
|
|
"num_tokens": 73180902.0,
|
|
"step": 35270
|
|
},
|
|
{
|
|
"entropy": 5.263919067382813,
|
|
"epoch": 3.1998367198838897,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0003992510196304258,
|
|
"loss": 4.8158,
|
|
"mean_token_accuracy": 0.2206836462020874,
|
|
"num_tokens": 73191259.0,
|
|
"step": 35275
|
|
},
|
|
{
|
|
"entropy": 5.384864425659179,
|
|
"epoch": 3.200290275761974,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00039922404299411846,
|
|
"loss": 4.9475,
|
|
"mean_token_accuracy": 0.22013089954853057,
|
|
"num_tokens": 73201654.0,
|
|
"step": 35280
|
|
},
|
|
{
|
|
"entropy": 5.422863912582398,
|
|
"epoch": 3.2007438316400583,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003991970637888262,
|
|
"loss": 4.9951,
|
|
"mean_token_accuracy": 0.1999611645936966,
|
|
"num_tokens": 73212658.0,
|
|
"step": 35285
|
|
},
|
|
{
|
|
"entropy": 5.403540706634521,
|
|
"epoch": 3.201197387518142,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000399170082015107,
|
|
"loss": 4.9755,
|
|
"mean_token_accuracy": 0.2093115881085396,
|
|
"num_tokens": 73222883.0,
|
|
"step": 35290
|
|
},
|
|
{
|
|
"entropy": 5.377951002120971,
|
|
"epoch": 3.2016509433962264,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000399143097673519,
|
|
"loss": 4.9212,
|
|
"mean_token_accuracy": 0.21092883199453355,
|
|
"num_tokens": 73233731.0,
|
|
"step": 35295
|
|
},
|
|
{
|
|
"entropy": 5.35588059425354,
|
|
"epoch": 3.2021044992743106,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00039911611076461995,
|
|
"loss": 4.875,
|
|
"mean_token_accuracy": 0.2232860341668129,
|
|
"num_tokens": 73243794.0,
|
|
"step": 35300
|
|
},
|
|
{
|
|
"entropy": 5.364216375350952,
|
|
"epoch": 3.202558055152395,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00039908912128896817,
|
|
"loss": 4.9363,
|
|
"mean_token_accuracy": 0.203682105243206,
|
|
"num_tokens": 73254708.0,
|
|
"step": 35305
|
|
},
|
|
{
|
|
"entropy": 5.352473449707031,
|
|
"epoch": 3.203011611030479,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0003990621292471217,
|
|
"loss": 4.9256,
|
|
"mean_token_accuracy": 0.21025055795907974,
|
|
"num_tokens": 73265311.0,
|
|
"step": 35310
|
|
},
|
|
{
|
|
"entropy": 5.492097663879394,
|
|
"epoch": 3.203465166908563,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00039903513463963874,
|
|
"loss": 5.124,
|
|
"mean_token_accuracy": 0.20295002162456513,
|
|
"num_tokens": 73275886.0,
|
|
"step": 35315
|
|
},
|
|
{
|
|
"entropy": 5.442448234558105,
|
|
"epoch": 3.2039187227866472,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003990081374670777,
|
|
"loss": 4.9836,
|
|
"mean_token_accuracy": 0.21511095464229585,
|
|
"num_tokens": 73285903.0,
|
|
"step": 35320
|
|
},
|
|
{
|
|
"entropy": 5.330180835723877,
|
|
"epoch": 3.2043722786647315,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00039898113772999665,
|
|
"loss": 4.9486,
|
|
"mean_token_accuracy": 0.21536389738321304,
|
|
"num_tokens": 73296571.0,
|
|
"step": 35325
|
|
},
|
|
{
|
|
"entropy": 5.394683456420898,
|
|
"epoch": 3.2048258345428158,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00039895413542895427,
|
|
"loss": 5.0017,
|
|
"mean_token_accuracy": 0.20456946939229964,
|
|
"num_tokens": 73307105.0,
|
|
"step": 35330
|
|
},
|
|
{
|
|
"entropy": 5.334899377822876,
|
|
"epoch": 3.2052793904209,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003989271305645086,
|
|
"loss": 4.9066,
|
|
"mean_token_accuracy": 0.2164454534649849,
|
|
"num_tokens": 73316664.0,
|
|
"step": 35335
|
|
},
|
|
{
|
|
"entropy": 5.372825193405151,
|
|
"epoch": 3.205732946298984,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00039890012313721835,
|
|
"loss": 4.9855,
|
|
"mean_token_accuracy": 0.21919727176427842,
|
|
"num_tokens": 73327438.0,
|
|
"step": 35340
|
|
},
|
|
{
|
|
"entropy": 5.347080326080322,
|
|
"epoch": 3.206186502177068,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000398873113147642,
|
|
"loss": 4.9696,
|
|
"mean_token_accuracy": 0.21493005156517028,
|
|
"num_tokens": 73337635.0,
|
|
"step": 35345
|
|
},
|
|
{
|
|
"entropy": 5.349483489990234,
|
|
"epoch": 3.2066400580551524,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00039884610059633807,
|
|
"loss": 4.9473,
|
|
"mean_token_accuracy": 0.21678098738193513,
|
|
"num_tokens": 73347032.0,
|
|
"step": 35350
|
|
},
|
|
{
|
|
"entropy": 5.465374088287353,
|
|
"epoch": 3.2070936139332367,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0003988190854838652,
|
|
"loss": 5.0336,
|
|
"mean_token_accuracy": 0.2078541025519371,
|
|
"num_tokens": 73357780.0,
|
|
"step": 35355
|
|
},
|
|
{
|
|
"entropy": 5.428545665740967,
|
|
"epoch": 3.207547169811321,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00039879206781078214,
|
|
"loss": 5.0199,
|
|
"mean_token_accuracy": 0.21036245077848434,
|
|
"num_tokens": 73367831.0,
|
|
"step": 35360
|
|
},
|
|
{
|
|
"entropy": 5.395096158981323,
|
|
"epoch": 3.2080007256894048,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0003987650475776476,
|
|
"loss": 4.9685,
|
|
"mean_token_accuracy": 0.21222956031560897,
|
|
"num_tokens": 73378588.0,
|
|
"step": 35365
|
|
},
|
|
{
|
|
"entropy": 5.334544658660889,
|
|
"epoch": 3.208454281567489,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00039873802478502027,
|
|
"loss": 4.9558,
|
|
"mean_token_accuracy": 0.21439647078514099,
|
|
"num_tokens": 73388414.0,
|
|
"step": 35370
|
|
},
|
|
{
|
|
"entropy": 5.380976009368896,
|
|
"epoch": 3.2089078374455733,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0003987109994334591,
|
|
"loss": 4.9608,
|
|
"mean_token_accuracy": 0.21215300858020783,
|
|
"num_tokens": 73398891.0,
|
|
"step": 35375
|
|
},
|
|
{
|
|
"entropy": 5.373863649368286,
|
|
"epoch": 3.2093613933236576,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0003986839715235229,
|
|
"loss": 5.0047,
|
|
"mean_token_accuracy": 0.2113189607858658,
|
|
"num_tokens": 73409605.0,
|
|
"step": 35380
|
|
},
|
|
{
|
|
"entropy": 5.446058130264282,
|
|
"epoch": 3.209814949201742,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00039865694105577063,
|
|
"loss": 5.0252,
|
|
"mean_token_accuracy": 0.20706187337636947,
|
|
"num_tokens": 73419103.0,
|
|
"step": 35385
|
|
},
|
|
{
|
|
"entropy": 5.3291136741638185,
|
|
"epoch": 3.2102685050798256,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003986299080307614,
|
|
"loss": 4.9505,
|
|
"mean_token_accuracy": 0.21419034600257875,
|
|
"num_tokens": 73429134.0,
|
|
"step": 35390
|
|
},
|
|
{
|
|
"entropy": 5.4023853778839115,
|
|
"epoch": 3.21072206095791,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0003986028724490541,
|
|
"loss": 5.0382,
|
|
"mean_token_accuracy": 0.20544440746307374,
|
|
"num_tokens": 73440382.0,
|
|
"step": 35395
|
|
},
|
|
{
|
|
"entropy": 5.449522638320923,
|
|
"epoch": 3.211175616835994,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0003985758343112079,
|
|
"loss": 4.9615,
|
|
"mean_token_accuracy": 0.21153661161661147,
|
|
"num_tokens": 73451300.0,
|
|
"step": 35400
|
|
},
|
|
{
|
|
"entropy": 5.384654951095581,
|
|
"epoch": 3.2116291727140784,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00039854879361778193,
|
|
"loss": 4.8608,
|
|
"mean_token_accuracy": 0.2129544273018837,
|
|
"num_tokens": 73461339.0,
|
|
"step": 35405
|
|
},
|
|
{
|
|
"entropy": 5.346892404556274,
|
|
"epoch": 3.2120827285921627,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00039852175036933545,
|
|
"loss": 4.969,
|
|
"mean_token_accuracy": 0.2171823114156723,
|
|
"num_tokens": 73470961.0,
|
|
"step": 35410
|
|
},
|
|
{
|
|
"entropy": 5.423472213745117,
|
|
"epoch": 3.2125362844702465,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00039849470456642777,
|
|
"loss": 5.0468,
|
|
"mean_token_accuracy": 0.20472047626972198,
|
|
"num_tokens": 73481492.0,
|
|
"step": 35415
|
|
},
|
|
{
|
|
"entropy": 5.359263229370117,
|
|
"epoch": 3.212989840348331,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00039846765620961806,
|
|
"loss": 4.9238,
|
|
"mean_token_accuracy": 0.21137960851192475,
|
|
"num_tokens": 73492351.0,
|
|
"step": 35420
|
|
},
|
|
{
|
|
"entropy": 5.399704790115356,
|
|
"epoch": 3.213443396226415,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003984406052994658,
|
|
"loss": 5.024,
|
|
"mean_token_accuracy": 0.20508077442646028,
|
|
"num_tokens": 73503265.0,
|
|
"step": 35425
|
|
},
|
|
{
|
|
"entropy": 5.410698556900025,
|
|
"epoch": 3.2138969521044993,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0003984135518365303,
|
|
"loss": 4.9861,
|
|
"mean_token_accuracy": 0.20548361986875535,
|
|
"num_tokens": 73513804.0,
|
|
"step": 35430
|
|
},
|
|
{
|
|
"entropy": 5.420540189743042,
|
|
"epoch": 3.2143505079825836,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00039838649582137113,
|
|
"loss": 4.9942,
|
|
"mean_token_accuracy": 0.2124916911125183,
|
|
"num_tokens": 73523453.0,
|
|
"step": 35435
|
|
},
|
|
{
|
|
"entropy": 5.4449155807495115,
|
|
"epoch": 3.214804063860668,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00039835943725454777,
|
|
"loss": 5.0969,
|
|
"mean_token_accuracy": 0.2012621656060219,
|
|
"num_tokens": 73533931.0,
|
|
"step": 35440
|
|
},
|
|
{
|
|
"entropy": 5.474432563781738,
|
|
"epoch": 3.2152576197387517,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00039833237613661984,
|
|
"loss": 5.026,
|
|
"mean_token_accuracy": 0.2077494367957115,
|
|
"num_tokens": 73544562.0,
|
|
"step": 35445
|
|
},
|
|
{
|
|
"entropy": 5.439730024337768,
|
|
"epoch": 3.215711175616836,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003983053124681469,
|
|
"loss": 4.9649,
|
|
"mean_token_accuracy": 0.21245760172605516,
|
|
"num_tokens": 73555149.0,
|
|
"step": 35450
|
|
},
|
|
{
|
|
"entropy": 5.358032274246216,
|
|
"epoch": 3.21616473149492,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00039827824624968873,
|
|
"loss": 4.8954,
|
|
"mean_token_accuracy": 0.2081266701221466,
|
|
"num_tokens": 73565131.0,
|
|
"step": 35455
|
|
},
|
|
{
|
|
"entropy": 5.318211460113526,
|
|
"epoch": 3.2166182873730045,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00039825117748180493,
|
|
"loss": 4.9197,
|
|
"mean_token_accuracy": 0.21609107106924058,
|
|
"num_tokens": 73574185.0,
|
|
"step": 35460
|
|
},
|
|
{
|
|
"entropy": 5.401047849655152,
|
|
"epoch": 3.2170718432510883,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00039822410616505545,
|
|
"loss": 5.0486,
|
|
"mean_token_accuracy": 0.2013027250766754,
|
|
"num_tokens": 73585733.0,
|
|
"step": 35465
|
|
},
|
|
{
|
|
"entropy": 5.47329683303833,
|
|
"epoch": 3.2175253991291726,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00039819703230000006,
|
|
"loss": 5.0624,
|
|
"mean_token_accuracy": 0.20533248484134675,
|
|
"num_tokens": 73597077.0,
|
|
"step": 35470
|
|
},
|
|
{
|
|
"entropy": 5.341036462783814,
|
|
"epoch": 3.217978955007257,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0003981699558871986,
|
|
"loss": 5.0198,
|
|
"mean_token_accuracy": 0.2103291481733322,
|
|
"num_tokens": 73607885.0,
|
|
"step": 35475
|
|
},
|
|
{
|
|
"entropy": 5.398135709762573,
|
|
"epoch": 3.218432510885341,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000398142876927211,
|
|
"loss": 4.9678,
|
|
"mean_token_accuracy": 0.21020368486642838,
|
|
"num_tokens": 73618769.0,
|
|
"step": 35480
|
|
},
|
|
{
|
|
"entropy": 5.453195285797119,
|
|
"epoch": 3.2188860667634254,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00039811579542059744,
|
|
"loss": 5.0824,
|
|
"mean_token_accuracy": 0.20098513513803482,
|
|
"num_tokens": 73629345.0,
|
|
"step": 35485
|
|
},
|
|
{
|
|
"entropy": 5.367208957672119,
|
|
"epoch": 3.2193396226415096,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00039808871136791786,
|
|
"loss": 4.95,
|
|
"mean_token_accuracy": 0.20887200832366942,
|
|
"num_tokens": 73639698.0,
|
|
"step": 35490
|
|
},
|
|
{
|
|
"entropy": 5.325884532928467,
|
|
"epoch": 3.2197931785195935,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00039806162476973227,
|
|
"loss": 4.952,
|
|
"mean_token_accuracy": 0.21090780347585678,
|
|
"num_tokens": 73650954.0,
|
|
"step": 35495
|
|
},
|
|
{
|
|
"entropy": 5.432744693756104,
|
|
"epoch": 3.2202467343976777,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000398034535626601,
|
|
"loss": 5.0559,
|
|
"mean_token_accuracy": 0.20662647038698195,
|
|
"num_tokens": 73661195.0,
|
|
"step": 35500
|
|
},
|
|
{
|
|
"entropy": 5.510959243774414,
|
|
"epoch": 3.220700290275762,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00039800744393908414,
|
|
"loss": 5.0848,
|
|
"mean_token_accuracy": 0.20444774031639099,
|
|
"num_tokens": 73670512.0,
|
|
"step": 35505
|
|
},
|
|
{
|
|
"entropy": 5.447427892684937,
|
|
"epoch": 3.2211538461538463,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000397980349707742,
|
|
"loss": 5.0199,
|
|
"mean_token_accuracy": 0.20608623772859574,
|
|
"num_tokens": 73681927.0,
|
|
"step": 35510
|
|
},
|
|
{
|
|
"entropy": 5.41335916519165,
|
|
"epoch": 3.2216074020319305,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00039795325293313493,
|
|
"loss": 5.0263,
|
|
"mean_token_accuracy": 0.20232611298561096,
|
|
"num_tokens": 73692025.0,
|
|
"step": 35515
|
|
},
|
|
{
|
|
"entropy": 5.338897705078125,
|
|
"epoch": 3.2220609579100143,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00039792615361582324,
|
|
"loss": 4.9609,
|
|
"mean_token_accuracy": 0.2104138419032097,
|
|
"num_tokens": 73702278.0,
|
|
"step": 35520
|
|
},
|
|
{
|
|
"entropy": 5.485140657424926,
|
|
"epoch": 3.2225145137880986,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00039789905175636726,
|
|
"loss": 5.0761,
|
|
"mean_token_accuracy": 0.20070533007383345,
|
|
"num_tokens": 73713511.0,
|
|
"step": 35525
|
|
},
|
|
{
|
|
"entropy": 5.326216840744019,
|
|
"epoch": 3.222968069666183,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00039787194735532765,
|
|
"loss": 4.8544,
|
|
"mean_token_accuracy": 0.21757350862026215,
|
|
"num_tokens": 73723683.0,
|
|
"step": 35530
|
|
},
|
|
{
|
|
"entropy": 5.385692024230957,
|
|
"epoch": 3.223421625544267,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003978448404132649,
|
|
"loss": 4.9444,
|
|
"mean_token_accuracy": 0.21226968765258789,
|
|
"num_tokens": 73734191.0,
|
|
"step": 35535
|
|
},
|
|
{
|
|
"entropy": 5.3947145462036135,
|
|
"epoch": 3.2238751814223514,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00039781773093073956,
|
|
"loss": 4.9769,
|
|
"mean_token_accuracy": 0.21133617907762528,
|
|
"num_tokens": 73743747.0,
|
|
"step": 35540
|
|
},
|
|
{
|
|
"entropy": 5.342904376983642,
|
|
"epoch": 3.2243287373004352,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0003977906189083122,
|
|
"loss": 4.9284,
|
|
"mean_token_accuracy": 0.21338338404893875,
|
|
"num_tokens": 73754466.0,
|
|
"step": 35545
|
|
},
|
|
{
|
|
"entropy": 5.375818586349487,
|
|
"epoch": 3.2247822931785195,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003977635043465435,
|
|
"loss": 4.9407,
|
|
"mean_token_accuracy": 0.2124062955379486,
|
|
"num_tokens": 73765948.0,
|
|
"step": 35550
|
|
},
|
|
{
|
|
"entropy": 5.288950490951538,
|
|
"epoch": 3.2252358490566038,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0003977363872459943,
|
|
"loss": 4.9015,
|
|
"mean_token_accuracy": 0.21281630098819732,
|
|
"num_tokens": 73776003.0,
|
|
"step": 35555
|
|
},
|
|
{
|
|
"entropy": 5.474228572845459,
|
|
"epoch": 3.225689404934688,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003977092676072254,
|
|
"loss": 5.1267,
|
|
"mean_token_accuracy": 0.20433258265256882,
|
|
"num_tokens": 73787821.0,
|
|
"step": 35560
|
|
},
|
|
{
|
|
"entropy": 5.4115057468414305,
|
|
"epoch": 3.2261429608127723,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00039768214543079746,
|
|
"loss": 4.9829,
|
|
"mean_token_accuracy": 0.206539985537529,
|
|
"num_tokens": 73799207.0,
|
|
"step": 35565
|
|
},
|
|
{
|
|
"entropy": 5.374158430099487,
|
|
"epoch": 3.226596516690856,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0003976550207172716,
|
|
"loss": 4.9224,
|
|
"mean_token_accuracy": 0.21607128232717515,
|
|
"num_tokens": 73809987.0,
|
|
"step": 35570
|
|
},
|
|
{
|
|
"entropy": 5.321122121810913,
|
|
"epoch": 3.2270500725689404,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00039762789346720854,
|
|
"loss": 4.9306,
|
|
"mean_token_accuracy": 0.20246421694755554,
|
|
"num_tokens": 73819075.0,
|
|
"step": 35575
|
|
},
|
|
{
|
|
"entropy": 5.400986814498902,
|
|
"epoch": 3.2275036284470247,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0003976007636811694,
|
|
"loss": 5.0026,
|
|
"mean_token_accuracy": 0.2116263598203659,
|
|
"num_tokens": 73829831.0,
|
|
"step": 35580
|
|
},
|
|
{
|
|
"entropy": 5.416312265396118,
|
|
"epoch": 3.227957184325109,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0003975736313597153,
|
|
"loss": 4.9964,
|
|
"mean_token_accuracy": 0.21300914287567138,
|
|
"num_tokens": 73839826.0,
|
|
"step": 35585
|
|
},
|
|
{
|
|
"entropy": 5.369287300109863,
|
|
"epoch": 3.228410740203193,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0003975464965034072,
|
|
"loss": 4.9193,
|
|
"mean_token_accuracy": 0.2119651883840561,
|
|
"num_tokens": 73850006.0,
|
|
"step": 35590
|
|
},
|
|
{
|
|
"entropy": 5.389595794677734,
|
|
"epoch": 3.228864296081277,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003975193591128064,
|
|
"loss": 4.9603,
|
|
"mean_token_accuracy": 0.20964526534080505,
|
|
"num_tokens": 73860309.0,
|
|
"step": 35595
|
|
},
|
|
{
|
|
"entropy": 5.422483682632446,
|
|
"epoch": 3.2293178519593613,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00039749221918847406,
|
|
"loss": 5.0649,
|
|
"mean_token_accuracy": 0.19895834475755692,
|
|
"num_tokens": 73871613.0,
|
|
"step": 35600
|
|
},
|
|
{
|
|
"entropy": 5.278899145126343,
|
|
"epoch": 3.2297714078374455,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0003974650767309713,
|
|
"loss": 4.902,
|
|
"mean_token_accuracy": 0.21160268038511276,
|
|
"num_tokens": 73882303.0,
|
|
"step": 35605
|
|
},
|
|
{
|
|
"entropy": 5.418464088439942,
|
|
"epoch": 3.23022496371553,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00039743793174085965,
|
|
"loss": 5.0077,
|
|
"mean_token_accuracy": 0.19817761778831483,
|
|
"num_tokens": 73893548.0,
|
|
"step": 35610
|
|
},
|
|
{
|
|
"entropy": 5.4505760192871096,
|
|
"epoch": 3.230678519593614,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00039741078421870024,
|
|
"loss": 4.9458,
|
|
"mean_token_accuracy": 0.20673478692770003,
|
|
"num_tokens": 73903934.0,
|
|
"step": 35615
|
|
},
|
|
{
|
|
"entropy": 5.448424005508423,
|
|
"epoch": 3.231132075471698,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00039738363416505474,
|
|
"loss": 5.0676,
|
|
"mean_token_accuracy": 0.20604825764894485,
|
|
"num_tokens": 73913813.0,
|
|
"step": 35620
|
|
},
|
|
{
|
|
"entropy": 5.406937026977539,
|
|
"epoch": 3.231585631349782,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00039735648158048444,
|
|
"loss": 5.0049,
|
|
"mean_token_accuracy": 0.20701453685760499,
|
|
"num_tokens": 73924339.0,
|
|
"step": 35625
|
|
},
|
|
{
|
|
"entropy": 5.386964797973633,
|
|
"epoch": 3.2320391872278664,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003973293264655509,
|
|
"loss": 4.9611,
|
|
"mean_token_accuracy": 0.2031710132956505,
|
|
"num_tokens": 73935318.0,
|
|
"step": 35630
|
|
},
|
|
{
|
|
"entropy": 5.39028263092041,
|
|
"epoch": 3.2324927431059507,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0003973021688208158,
|
|
"loss": 4.9346,
|
|
"mean_token_accuracy": 0.21446627229452134,
|
|
"num_tokens": 73945547.0,
|
|
"step": 35635
|
|
},
|
|
{
|
|
"entropy": 5.404459476470947,
|
|
"epoch": 3.232946298984035,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003972750086468406,
|
|
"loss": 4.9767,
|
|
"mean_token_accuracy": 0.20522586554288863,
|
|
"num_tokens": 73956195.0,
|
|
"step": 35640
|
|
},
|
|
{
|
|
"entropy": 5.395975971221924,
|
|
"epoch": 3.2333998548621192,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00039724784594418714,
|
|
"loss": 4.9056,
|
|
"mean_token_accuracy": 0.22050540447235106,
|
|
"num_tokens": 73966843.0,
|
|
"step": 35645
|
|
},
|
|
{
|
|
"entropy": 5.4122288703918455,
|
|
"epoch": 3.233853410740203,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.000397220680713417,
|
|
"loss": 4.957,
|
|
"mean_token_accuracy": 0.21212082654237746,
|
|
"num_tokens": 73978516.0,
|
|
"step": 35650
|
|
},
|
|
{
|
|
"entropy": 5.332116174697876,
|
|
"epoch": 3.2343069666182873,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00039719351295509203,
|
|
"loss": 4.9095,
|
|
"mean_token_accuracy": 0.21551603376865386,
|
|
"num_tokens": 73988376.0,
|
|
"step": 35655
|
|
},
|
|
{
|
|
"entropy": 5.37200961112976,
|
|
"epoch": 3.2347605224963716,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00039716634266977413,
|
|
"loss": 4.9317,
|
|
"mean_token_accuracy": 0.22016535550355912,
|
|
"num_tokens": 73998232.0,
|
|
"step": 35660
|
|
},
|
|
{
|
|
"entropy": 5.382065868377685,
|
|
"epoch": 3.235214078374456,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0003971391698580252,
|
|
"loss": 4.9495,
|
|
"mean_token_accuracy": 0.20946948528289794,
|
|
"num_tokens": 74008726.0,
|
|
"step": 35665
|
|
},
|
|
{
|
|
"entropy": 5.355972480773926,
|
|
"epoch": 3.23566763425254,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00039711199452040696,
|
|
"loss": 4.964,
|
|
"mean_token_accuracy": 0.21215932071208954,
|
|
"num_tokens": 74018746.0,
|
|
"step": 35670
|
|
},
|
|
{
|
|
"entropy": 5.352242517471313,
|
|
"epoch": 3.236121190130624,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00039708481665748157,
|
|
"loss": 4.9294,
|
|
"mean_token_accuracy": 0.21172347217798232,
|
|
"num_tokens": 74028615.0,
|
|
"step": 35675
|
|
},
|
|
{
|
|
"entropy": 5.3991978645324705,
|
|
"epoch": 3.236574746008708,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0003970576362698111,
|
|
"loss": 5.0013,
|
|
"mean_token_accuracy": 0.2026448905467987,
|
|
"num_tokens": 74039219.0,
|
|
"step": 35680
|
|
},
|
|
{
|
|
"entropy": 5.383815813064575,
|
|
"epoch": 3.2370283018867925,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00039703045335795766,
|
|
"loss": 4.9385,
|
|
"mean_token_accuracy": 0.21366861909627916,
|
|
"num_tokens": 74049385.0,
|
|
"step": 35685
|
|
},
|
|
{
|
|
"entropy": 5.4326435089111325,
|
|
"epoch": 3.2374818577648767,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003970032679224833,
|
|
"loss": 5.1123,
|
|
"mean_token_accuracy": 0.19677113592624665,
|
|
"num_tokens": 74059437.0,
|
|
"step": 35690
|
|
},
|
|
{
|
|
"entropy": 5.4400719165802,
|
|
"epoch": 3.237935413642961,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00039697607996395023,
|
|
"loss": 5.0238,
|
|
"mean_token_accuracy": 0.2019175946712494,
|
|
"num_tokens": 74068834.0,
|
|
"step": 35695
|
|
},
|
|
{
|
|
"entropy": 5.4640881538391115,
|
|
"epoch": 3.238388969521045,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0003969488894829208,
|
|
"loss": 5.0114,
|
|
"mean_token_accuracy": 0.19980765581130983,
|
|
"num_tokens": 74079757.0,
|
|
"step": 35700
|
|
},
|
|
{
|
|
"entropy": 5.386493778228759,
|
|
"epoch": 3.238842525399129,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0003969216964799573,
|
|
"loss": 4.9481,
|
|
"mean_token_accuracy": 0.2110060453414917,
|
|
"num_tokens": 74091092.0,
|
|
"step": 35705
|
|
},
|
|
{
|
|
"entropy": 5.339123916625977,
|
|
"epoch": 3.2392960812772134,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003968945009556219,
|
|
"loss": 4.947,
|
|
"mean_token_accuracy": 0.21284967362880708,
|
|
"num_tokens": 74102272.0,
|
|
"step": 35710
|
|
},
|
|
{
|
|
"entropy": 5.360544919967651,
|
|
"epoch": 3.2397496371552976,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0003968673029104773,
|
|
"loss": 4.9282,
|
|
"mean_token_accuracy": 0.21543143391609193,
|
|
"num_tokens": 74113101.0,
|
|
"step": 35715
|
|
},
|
|
{
|
|
"entropy": 5.450589895248413,
|
|
"epoch": 3.240203193033382,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003968401023450858,
|
|
"loss": 4.9574,
|
|
"mean_token_accuracy": 0.21700484454631805,
|
|
"num_tokens": 74123180.0,
|
|
"step": 35720
|
|
},
|
|
{
|
|
"entropy": 5.35306453704834,
|
|
"epoch": 3.2406567489114657,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00039681289926000985,
|
|
"loss": 4.9436,
|
|
"mean_token_accuracy": 0.21485716998577117,
|
|
"num_tokens": 74133675.0,
|
|
"step": 35725
|
|
},
|
|
{
|
|
"entropy": 5.296636772155762,
|
|
"epoch": 3.24111030478955,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003967856936558122,
|
|
"loss": 4.8893,
|
|
"mean_token_accuracy": 0.2138315796852112,
|
|
"num_tokens": 74143472.0,
|
|
"step": 35730
|
|
},
|
|
{
|
|
"entropy": 5.414577198028565,
|
|
"epoch": 3.2415638606676342,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00039675848553305526,
|
|
"loss": 4.9492,
|
|
"mean_token_accuracy": 0.20777079313993455,
|
|
"num_tokens": 74154682.0,
|
|
"step": 35735
|
|
},
|
|
{
|
|
"entropy": 5.392607593536377,
|
|
"epoch": 3.2420174165457185,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003967312748923019,
|
|
"loss": 4.9642,
|
|
"mean_token_accuracy": 0.20974746942520142,
|
|
"num_tokens": 74164745.0,
|
|
"step": 35740
|
|
},
|
|
{
|
|
"entropy": 5.283349943161011,
|
|
"epoch": 3.2424709724238028,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00039670406173411473,
|
|
"loss": 4.8916,
|
|
"mean_token_accuracy": 0.21865113377571105,
|
|
"num_tokens": 74175388.0,
|
|
"step": 35745
|
|
},
|
|
{
|
|
"entropy": 5.334941816329956,
|
|
"epoch": 3.2429245283018866,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003966768460590566,
|
|
"loss": 4.9134,
|
|
"mean_token_accuracy": 0.21326206475496293,
|
|
"num_tokens": 74185929.0,
|
|
"step": 35750
|
|
},
|
|
{
|
|
"entropy": 5.407745695114135,
|
|
"epoch": 3.243378084179971,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00039664962786769013,
|
|
"loss": 4.9254,
|
|
"mean_token_accuracy": 0.2140391066670418,
|
|
"num_tokens": 74196165.0,
|
|
"step": 35755
|
|
},
|
|
{
|
|
"entropy": 5.37808780670166,
|
|
"epoch": 3.243831640058055,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00039662240716057854,
|
|
"loss": 4.9421,
|
|
"mean_token_accuracy": 0.21266786009073257,
|
|
"num_tokens": 74206843.0,
|
|
"step": 35760
|
|
},
|
|
{
|
|
"entropy": 5.335856580734253,
|
|
"epoch": 3.2442851959361394,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003965951839382845,
|
|
"loss": 4.9285,
|
|
"mean_token_accuracy": 0.21269794404506684,
|
|
"num_tokens": 74216854.0,
|
|
"step": 35765
|
|
},
|
|
{
|
|
"entropy": 5.31274380683899,
|
|
"epoch": 3.2447387518142237,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000396567958201371,
|
|
"loss": 4.9037,
|
|
"mean_token_accuracy": 0.21331822574138642,
|
|
"num_tokens": 74226158.0,
|
|
"step": 35770
|
|
},
|
|
{
|
|
"entropy": 5.374884939193725,
|
|
"epoch": 3.2451923076923075,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0003965407299504013,
|
|
"loss": 4.9885,
|
|
"mean_token_accuracy": 0.21605556607246398,
|
|
"num_tokens": 74236860.0,
|
|
"step": 35775
|
|
},
|
|
{
|
|
"entropy": 5.411153984069824,
|
|
"epoch": 3.2456458635703918,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003965134991859382,
|
|
"loss": 4.9483,
|
|
"mean_token_accuracy": 0.21342063546180726,
|
|
"num_tokens": 74247706.0,
|
|
"step": 35780
|
|
},
|
|
{
|
|
"entropy": 5.44333930015564,
|
|
"epoch": 3.246099419448476,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000396486265908545,
|
|
"loss": 4.9927,
|
|
"mean_token_accuracy": 0.21085022985935212,
|
|
"num_tokens": 74259479.0,
|
|
"step": 35785
|
|
},
|
|
{
|
|
"entropy": 5.358527994155883,
|
|
"epoch": 3.2465529753265603,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0003964590301187849,
|
|
"loss": 4.9984,
|
|
"mean_token_accuracy": 0.2138197124004364,
|
|
"num_tokens": 74270371.0,
|
|
"step": 35790
|
|
},
|
|
{
|
|
"entropy": 5.373487234115601,
|
|
"epoch": 3.2470065312046446,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003964317918172211,
|
|
"loss": 4.92,
|
|
"mean_token_accuracy": 0.22208261936903,
|
|
"num_tokens": 74279637.0,
|
|
"step": 35795
|
|
},
|
|
{
|
|
"entropy": 5.407387828826904,
|
|
"epoch": 3.247460087082729,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00039640455100441684,
|
|
"loss": 5.053,
|
|
"mean_token_accuracy": 0.20412746965885162,
|
|
"num_tokens": 74289889.0,
|
|
"step": 35800
|
|
},
|
|
{
|
|
"entropy": 5.390875720977784,
|
|
"epoch": 3.2479136429608126,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00039637730768093564,
|
|
"loss": 4.9864,
|
|
"mean_token_accuracy": 0.21560679227113724,
|
|
"num_tokens": 74300949.0,
|
|
"step": 35805
|
|
},
|
|
{
|
|
"entropy": 5.390940093994141,
|
|
"epoch": 3.248367198838897,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003963500618473407,
|
|
"loss": 4.9222,
|
|
"mean_token_accuracy": 0.21626006066799164,
|
|
"num_tokens": 74312077.0,
|
|
"step": 35810
|
|
},
|
|
{
|
|
"entropy": 5.357425832748413,
|
|
"epoch": 3.248820754716981,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0003963228135041956,
|
|
"loss": 5.0077,
|
|
"mean_token_accuracy": 0.20865391194820404,
|
|
"num_tokens": 74322610.0,
|
|
"step": 35815
|
|
},
|
|
{
|
|
"entropy": 5.324527740478516,
|
|
"epoch": 3.2492743105950654,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00039629556265206373,
|
|
"loss": 4.8543,
|
|
"mean_token_accuracy": 0.21321856826543809,
|
|
"num_tokens": 74331970.0,
|
|
"step": 35820
|
|
},
|
|
{
|
|
"entropy": 5.356959819793701,
|
|
"epoch": 3.2497278664731493,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0003962683092915088,
|
|
"loss": 4.9091,
|
|
"mean_token_accuracy": 0.21497557312250137,
|
|
"num_tokens": 74342812.0,
|
|
"step": 35825
|
|
},
|
|
{
|
|
"entropy": 5.356831312179565,
|
|
"epoch": 3.2501814223512335,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0003962410534230943,
|
|
"loss": 4.8831,
|
|
"mean_token_accuracy": 0.21481046229600906,
|
|
"num_tokens": 74353786.0,
|
|
"step": 35830
|
|
},
|
|
{
|
|
"entropy": 5.398156547546387,
|
|
"epoch": 3.250634978229318,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00039621379504738385,
|
|
"loss": 5.0083,
|
|
"mean_token_accuracy": 0.21052553355693818,
|
|
"num_tokens": 74363732.0,
|
|
"step": 35835
|
|
},
|
|
{
|
|
"entropy": 5.384274625778199,
|
|
"epoch": 3.251088534107402,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00039618653416494137,
|
|
"loss": 5.0027,
|
|
"mean_token_accuracy": 0.21270507872104644,
|
|
"num_tokens": 74374077.0,
|
|
"step": 35840
|
|
},
|
|
{
|
|
"entropy": 5.385674285888672,
|
|
"epoch": 3.2515420899854863,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00039615927077633043,
|
|
"loss": 5.0096,
|
|
"mean_token_accuracy": 0.2074568048119545,
|
|
"num_tokens": 74384758.0,
|
|
"step": 35845
|
|
},
|
|
{
|
|
"entropy": 5.478406572341919,
|
|
"epoch": 3.2519956458635706,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00039613200488211483,
|
|
"loss": 5.0286,
|
|
"mean_token_accuracy": 0.2091982528567314,
|
|
"num_tokens": 74395811.0,
|
|
"step": 35850
|
|
},
|
|
{
|
|
"entropy": 5.431172513961792,
|
|
"epoch": 3.2524492017416544,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00039610473648285857,
|
|
"loss": 5.0136,
|
|
"mean_token_accuracy": 0.20342869013547898,
|
|
"num_tokens": 74407830.0,
|
|
"step": 35855
|
|
},
|
|
{
|
|
"entropy": 5.308012008666992,
|
|
"epoch": 3.2529027576197387,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0003960774655791255,
|
|
"loss": 4.9012,
|
|
"mean_token_accuracy": 0.21398843079805374,
|
|
"num_tokens": 74417565.0,
|
|
"step": 35860
|
|
},
|
|
{
|
|
"entropy": 5.404665899276734,
|
|
"epoch": 3.253356313497823,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00039605019217147947,
|
|
"loss": 4.9864,
|
|
"mean_token_accuracy": 0.2062416836619377,
|
|
"num_tokens": 74428015.0,
|
|
"step": 35865
|
|
},
|
|
{
|
|
"entropy": 5.372069263458252,
|
|
"epoch": 3.253809869375907,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00039602291626048475,
|
|
"loss": 4.9612,
|
|
"mean_token_accuracy": 0.2152887061238289,
|
|
"num_tokens": 74439523.0,
|
|
"step": 35870
|
|
},
|
|
{
|
|
"entropy": 5.450466871261597,
|
|
"epoch": 3.2542634252539915,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00039599563784670526,
|
|
"loss": 5.0481,
|
|
"mean_token_accuracy": 0.19911497086286545,
|
|
"num_tokens": 74449897.0,
|
|
"step": 35875
|
|
},
|
|
{
|
|
"entropy": 5.364455938339233,
|
|
"epoch": 3.2547169811320753,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0003959683569307051,
|
|
"loss": 4.8915,
|
|
"mean_token_accuracy": 0.21729716658592224,
|
|
"num_tokens": 74459888.0,
|
|
"step": 35880
|
|
},
|
|
{
|
|
"entropy": 5.341001367568969,
|
|
"epoch": 3.2551705370101596,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003959410735130485,
|
|
"loss": 4.8435,
|
|
"mean_token_accuracy": 0.2116606742143631,
|
|
"num_tokens": 74470894.0,
|
|
"step": 35885
|
|
},
|
|
{
|
|
"entropy": 5.334443616867065,
|
|
"epoch": 3.255624092888244,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00039591378759429974,
|
|
"loss": 4.8802,
|
|
"mean_token_accuracy": 0.22038175761699677,
|
|
"num_tokens": 74481306.0,
|
|
"step": 35890
|
|
},
|
|
{
|
|
"entropy": 5.370121049880981,
|
|
"epoch": 3.256077648766328,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000395886499175023,
|
|
"loss": 4.9487,
|
|
"mean_token_accuracy": 0.20991116613149643,
|
|
"num_tokens": 74491048.0,
|
|
"step": 35895
|
|
},
|
|
{
|
|
"entropy": 5.317673444747925,
|
|
"epoch": 3.2565312046444124,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00039585920825578266,
|
|
"loss": 4.8859,
|
|
"mean_token_accuracy": 0.21955070048570632,
|
|
"num_tokens": 74501656.0,
|
|
"step": 35900
|
|
},
|
|
{
|
|
"entropy": 5.426463270187378,
|
|
"epoch": 3.256984760522496,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0003958319148371431,
|
|
"loss": 5.0114,
|
|
"mean_token_accuracy": 0.20927781462669373,
|
|
"num_tokens": 74513280.0,
|
|
"step": 35905
|
|
},
|
|
{
|
|
"entropy": 5.357208967208862,
|
|
"epoch": 3.2574383164005805,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0003958046189196687,
|
|
"loss": 4.974,
|
|
"mean_token_accuracy": 0.21052121073007585,
|
|
"num_tokens": 74522898.0,
|
|
"step": 35910
|
|
},
|
|
{
|
|
"entropy": 5.495421075820923,
|
|
"epoch": 3.2578918722786647,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00039577732050392395,
|
|
"loss": 5.0263,
|
|
"mean_token_accuracy": 0.20686648190021514,
|
|
"num_tokens": 74532551.0,
|
|
"step": 35915
|
|
},
|
|
{
|
|
"entropy": 5.410580110549927,
|
|
"epoch": 3.258345428156749,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003957500195904735,
|
|
"loss": 4.9727,
|
|
"mean_token_accuracy": 0.2157336711883545,
|
|
"num_tokens": 74542285.0,
|
|
"step": 35920
|
|
},
|
|
{
|
|
"entropy": 5.380132627487183,
|
|
"epoch": 3.2587989840348333,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000395722716179882,
|
|
"loss": 5.0032,
|
|
"mean_token_accuracy": 0.2106045514345169,
|
|
"num_tokens": 74551982.0,
|
|
"step": 35925
|
|
},
|
|
{
|
|
"entropy": 5.390248012542725,
|
|
"epoch": 3.259252539912917,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0003956954102727138,
|
|
"loss": 4.9671,
|
|
"mean_token_accuracy": 0.2105133205652237,
|
|
"num_tokens": 74562190.0,
|
|
"step": 35930
|
|
},
|
|
{
|
|
"entropy": 5.350546979904175,
|
|
"epoch": 3.2597060957910013,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00039566810186953376,
|
|
"loss": 4.8934,
|
|
"mean_token_accuracy": 0.214102078974247,
|
|
"num_tokens": 74572673.0,
|
|
"step": 35935
|
|
},
|
|
{
|
|
"entropy": 5.334931898117065,
|
|
"epoch": 3.2601596516690856,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0003956407909709068,
|
|
"loss": 4.9027,
|
|
"mean_token_accuracy": 0.2227718025445938,
|
|
"num_tokens": 74582686.0,
|
|
"step": 35940
|
|
},
|
|
{
|
|
"entropy": 5.416879892349243,
|
|
"epoch": 3.26061320754717,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00039561347757739734,
|
|
"loss": 5.0426,
|
|
"mean_token_accuracy": 0.20687223672866822,
|
|
"num_tokens": 74593658.0,
|
|
"step": 35945
|
|
},
|
|
{
|
|
"entropy": 5.45359992980957,
|
|
"epoch": 3.261066763425254,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00039558616168957044,
|
|
"loss": 5.0393,
|
|
"mean_token_accuracy": 0.21080212742090226,
|
|
"num_tokens": 74603585.0,
|
|
"step": 35950
|
|
},
|
|
{
|
|
"entropy": 5.378395462036133,
|
|
"epoch": 3.2615203193033384,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003955588433079911,
|
|
"loss": 4.9198,
|
|
"mean_token_accuracy": 0.21462933272123336,
|
|
"num_tokens": 74612806.0,
|
|
"step": 35955
|
|
},
|
|
{
|
|
"entropy": 5.413948059082031,
|
|
"epoch": 3.2619738751814222,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00039553152243322414,
|
|
"loss": 4.9708,
|
|
"mean_token_accuracy": 0.2204448476433754,
|
|
"num_tokens": 74623252.0,
|
|
"step": 35960
|
|
},
|
|
{
|
|
"entropy": 5.370652723312378,
|
|
"epoch": 3.2624274310595065,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003955041990658346,
|
|
"loss": 4.941,
|
|
"mean_token_accuracy": 0.21544478535652162,
|
|
"num_tokens": 74633555.0,
|
|
"step": 35965
|
|
},
|
|
{
|
|
"entropy": 5.398770141601562,
|
|
"epoch": 3.2628809869375908,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0003954768732063874,
|
|
"loss": 4.9485,
|
|
"mean_token_accuracy": 0.21359411180019378,
|
|
"num_tokens": 74643322.0,
|
|
"step": 35970
|
|
},
|
|
{
|
|
"entropy": 5.358492612838745,
|
|
"epoch": 3.263334542815675,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0003954495448554478,
|
|
"loss": 4.9355,
|
|
"mean_token_accuracy": 0.22155113220214845,
|
|
"num_tokens": 74653461.0,
|
|
"step": 35975
|
|
},
|
|
{
|
|
"entropy": 5.3368387699127195,
|
|
"epoch": 3.263788098693759,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00039542221401358104,
|
|
"loss": 4.9864,
|
|
"mean_token_accuracy": 0.208555006980896,
|
|
"num_tokens": 74663470.0,
|
|
"step": 35980
|
|
},
|
|
{
|
|
"entropy": 5.342227792739868,
|
|
"epoch": 3.264241654571843,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000395394880681352,
|
|
"loss": 4.8913,
|
|
"mean_token_accuracy": 0.22123870998620987,
|
|
"num_tokens": 74674074.0,
|
|
"step": 35985
|
|
},
|
|
{
|
|
"entropy": 5.486236667633056,
|
|
"epoch": 3.2646952104499274,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00039536754485932626,
|
|
"loss": 5.0619,
|
|
"mean_token_accuracy": 0.2031155928969383,
|
|
"num_tokens": 74684968.0,
|
|
"step": 35990
|
|
},
|
|
{
|
|
"entropy": 5.3435461044311525,
|
|
"epoch": 3.2651487663280117,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00039534020654806906,
|
|
"loss": 4.8765,
|
|
"mean_token_accuracy": 0.22972255647182466,
|
|
"num_tokens": 74694776.0,
|
|
"step": 35995
|
|
},
|
|
{
|
|
"entropy": 5.353729581832885,
|
|
"epoch": 3.265602322206096,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00039531286574814563,
|
|
"loss": 4.8881,
|
|
"mean_token_accuracy": 0.21359238773584366,
|
|
"num_tokens": 74705506.0,
|
|
"step": 36000
|
|
},
|
|
{
|
|
"epoch": 3.265602322206096,
|
|
"eval_entropy": 5.118330060626587,
|
|
"eval_loss": 5.062209129333496,
|
|
"eval_mean_token_accuracy": 0.21401237869019962,
|
|
"eval_num_tokens": 74705506.0,
|
|
"eval_runtime": 26.5957,
|
|
"eval_samples_per_second": 1329.538,
|
|
"eval_steps_per_second": 166.192,
|
|
"step": 36000
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 110230,
|
|
"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": 1.09311181193088e+17,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|