4628d1d8eb
Model: fpadovani/nld-latn-100mb-after-ppt-Dp-100mb-ckpt500_seed3407 Source: Original Platform
6046 lines
164 KiB
JSON
6046 lines
164 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.27213352685050796,
|
|
"eval_steps": 3000,
|
|
"global_step": 3000,
|
|
"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
|
|
}
|
|
],
|
|
"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": 9028611385344000.0,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|