12057 lines
330 KiB
JSON
12057 lines
330 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 1.1705199492732417,
|
|
"eval_steps": 3000,
|
|
"global_step": 6000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 10.692006397247315,
|
|
"epoch": 0.0009755145839430299,
|
|
"grad_norm": 12.9375,
|
|
"learning_rate": 2e-06,
|
|
"loss": 10.892,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 17120.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 10.691958236694337,
|
|
"epoch": 0.0019510291678860598,
|
|
"grad_norm": 12.8125,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 10.8306,
|
|
"mean_token_accuracy": 0.00028931311098858716,
|
|
"num_tokens": 34182.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 10.688035488128662,
|
|
"epoch": 0.0029265437518290896,
|
|
"grad_norm": 9.5625,
|
|
"learning_rate": 7e-06,
|
|
"loss": 10.545,
|
|
"mean_token_accuracy": 0.0563898827880621,
|
|
"num_tokens": 51205.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 10.501210594177246,
|
|
"epoch": 0.0039020583357721197,
|
|
"grad_norm": 4.90625,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 10.2388,
|
|
"mean_token_accuracy": 0.0683012217283249,
|
|
"num_tokens": 67722.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 10.27708158493042,
|
|
"epoch": 0.00487757291971515,
|
|
"grad_norm": 4.125,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 10.0655,
|
|
"mean_token_accuracy": 0.06708129495382309,
|
|
"num_tokens": 84230.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 10.517713356018067,
|
|
"epoch": 0.005853087503658179,
|
|
"grad_norm": 2.890625,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 9.9573,
|
|
"mean_token_accuracy": 0.06805420815944671,
|
|
"num_tokens": 100967.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 10.29547052383423,
|
|
"epoch": 0.00682860208760121,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 9.8479,
|
|
"mean_token_accuracy": 0.0726205624639988,
|
|
"num_tokens": 117450.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 10.387489223480225,
|
|
"epoch": 0.007804116671544239,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 9.8467,
|
|
"mean_token_accuracy": 0.06873829215765,
|
|
"num_tokens": 135328.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 10.264148712158203,
|
|
"epoch": 0.00877963125548727,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 9.8057,
|
|
"mean_token_accuracy": 0.07149567306041718,
|
|
"num_tokens": 152571.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 10.268710899353028,
|
|
"epoch": 0.0097551458394303,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 9.7553,
|
|
"mean_token_accuracy": 0.07231884635984898,
|
|
"num_tokens": 170216.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 10.260807514190674,
|
|
"epoch": 0.010730660423373329,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 9.702,
|
|
"mean_token_accuracy": 0.07669694796204567,
|
|
"num_tokens": 186513.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 10.229700088500977,
|
|
"epoch": 0.011706175007316359,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 9.6889,
|
|
"mean_token_accuracy": 0.07528627961874008,
|
|
"num_tokens": 202600.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 10.081421279907227,
|
|
"epoch": 0.01268168959125939,
|
|
"grad_norm": 3.3125,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 9.5969,
|
|
"mean_token_accuracy": 0.08673674017190933,
|
|
"num_tokens": 220270.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 10.137750053405762,
|
|
"epoch": 0.01365720417520242,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 9.5338,
|
|
"mean_token_accuracy": 0.08762008398771286,
|
|
"num_tokens": 236810.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 10.082253742218018,
|
|
"epoch": 0.014632718759145449,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 9.5259,
|
|
"mean_token_accuracy": 0.08117572665214538,
|
|
"num_tokens": 252559.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 10.097311305999757,
|
|
"epoch": 0.015608233343088479,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 9.4073,
|
|
"mean_token_accuracy": 0.09147667810320854,
|
|
"num_tokens": 268507.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 10.028666019439697,
|
|
"epoch": 0.01658374792703151,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 9.406,
|
|
"mean_token_accuracy": 0.0866853080689907,
|
|
"num_tokens": 284776.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 10.004025745391846,
|
|
"epoch": 0.01755926251097454,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 9.3519,
|
|
"mean_token_accuracy": 0.08328424319624901,
|
|
"num_tokens": 300937.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 10.073490333557128,
|
|
"epoch": 0.01853477709491757,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 9.2741,
|
|
"mean_token_accuracy": 0.08352594524621963,
|
|
"num_tokens": 317464.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 9.939503002166749,
|
|
"epoch": 0.0195102916788606,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 9.1496,
|
|
"mean_token_accuracy": 0.08892395347356796,
|
|
"num_tokens": 334022.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 9.905517959594727,
|
|
"epoch": 0.02048580626280363,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 9.1039,
|
|
"mean_token_accuracy": 0.087137870490551,
|
|
"num_tokens": 350545.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 9.737315464019776,
|
|
"epoch": 0.021461320846746658,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 9.0136,
|
|
"mean_token_accuracy": 0.09296058937907219,
|
|
"num_tokens": 368878.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 9.848572158813477,
|
|
"epoch": 0.022436835430689687,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 9.0059,
|
|
"mean_token_accuracy": 0.08585245460271836,
|
|
"num_tokens": 388381.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 9.741306686401368,
|
|
"epoch": 0.023412350014632717,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 8.9316,
|
|
"mean_token_accuracy": 0.08110709637403488,
|
|
"num_tokens": 403727.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 9.699060344696045,
|
|
"epoch": 0.02438786459857575,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 8.882,
|
|
"mean_token_accuracy": 0.08276206851005555,
|
|
"num_tokens": 419046.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 9.528530883789063,
|
|
"epoch": 0.02536337918251878,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 8.7349,
|
|
"mean_token_accuracy": 0.09832416251301765,
|
|
"num_tokens": 435186.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 9.434342861175537,
|
|
"epoch": 0.02633889376646181,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 8.7342,
|
|
"mean_token_accuracy": 0.08667377829551696,
|
|
"num_tokens": 451552.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 9.417459678649902,
|
|
"epoch": 0.02731440835040484,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 8.7047,
|
|
"mean_token_accuracy": 0.08775919750332832,
|
|
"num_tokens": 468006.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 9.20961685180664,
|
|
"epoch": 0.02828992293434787,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 8.6358,
|
|
"mean_token_accuracy": 0.08715632259845733,
|
|
"num_tokens": 484381.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 9.286615180969239,
|
|
"epoch": 0.029265437518290898,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 8.6472,
|
|
"mean_token_accuracy": 0.08763191923499107,
|
|
"num_tokens": 501309.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 9.081134414672851,
|
|
"epoch": 0.030240952102233928,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 8.5847,
|
|
"mean_token_accuracy": 0.08041713163256645,
|
|
"num_tokens": 518290.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 9.070791053771973,
|
|
"epoch": 0.031216466686176957,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 8.5477,
|
|
"mean_token_accuracy": 0.0860756978392601,
|
|
"num_tokens": 533700.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 8.901391220092773,
|
|
"epoch": 0.03219198127011999,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 8.4125,
|
|
"mean_token_accuracy": 0.09618512019515038,
|
|
"num_tokens": 548935.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 8.865772151947022,
|
|
"epoch": 0.03316749585406302,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 8.4734,
|
|
"mean_token_accuracy": 0.08627908602356911,
|
|
"num_tokens": 565869.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 8.87720022201538,
|
|
"epoch": 0.03414301043800605,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 8.4862,
|
|
"mean_token_accuracy": 0.08944675847887992,
|
|
"num_tokens": 583065.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 8.795064163208007,
|
|
"epoch": 0.03511852502194908,
|
|
"grad_norm": 2.921875,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 8.4763,
|
|
"mean_token_accuracy": 0.09086722284555435,
|
|
"num_tokens": 599875.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 8.737292766571045,
|
|
"epoch": 0.03609403960589211,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 8.4493,
|
|
"mean_token_accuracy": 0.0904251515865326,
|
|
"num_tokens": 616296.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 8.838920211791992,
|
|
"epoch": 0.03706955418983514,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 8.4171,
|
|
"mean_token_accuracy": 0.08522484824061394,
|
|
"num_tokens": 632548.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 8.708141040802001,
|
|
"epoch": 0.03804506877377817,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 8.4184,
|
|
"mean_token_accuracy": 0.09042482525110244,
|
|
"num_tokens": 650395.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 8.621811580657958,
|
|
"epoch": 0.0390205833577212,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 8.4313,
|
|
"mean_token_accuracy": 0.0962656319141388,
|
|
"num_tokens": 668453.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 8.641033744812011,
|
|
"epoch": 0.03999609794166423,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000102,
|
|
"loss": 8.3245,
|
|
"mean_token_accuracy": 0.09897583797574043,
|
|
"num_tokens": 683914.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 8.632667446136475,
|
|
"epoch": 0.04097161252560726,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 8.4474,
|
|
"mean_token_accuracy": 0.0904572695493698,
|
|
"num_tokens": 700480.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 8.652472400665284,
|
|
"epoch": 0.041947127109550286,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.000107,
|
|
"loss": 8.4236,
|
|
"mean_token_accuracy": 0.08843122720718384,
|
|
"num_tokens": 716604.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 8.608741188049317,
|
|
"epoch": 0.042922641693493316,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 8.4127,
|
|
"mean_token_accuracy": 0.0901436910033226,
|
|
"num_tokens": 732697.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 8.667686557769775,
|
|
"epoch": 0.043898156277436345,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000112,
|
|
"loss": 8.4916,
|
|
"mean_token_accuracy": 0.08182057477533818,
|
|
"num_tokens": 749072.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 8.605211448669433,
|
|
"epoch": 0.044873670861379375,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 8.4343,
|
|
"mean_token_accuracy": 0.08532521277666091,
|
|
"num_tokens": 767826.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 8.613678073883056,
|
|
"epoch": 0.045849185445322405,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 8.3376,
|
|
"mean_token_accuracy": 0.09638948515057563,
|
|
"num_tokens": 786863.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 8.50732488632202,
|
|
"epoch": 0.046824700029265434,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 8.3269,
|
|
"mean_token_accuracy": 0.10453230515122414,
|
|
"num_tokens": 803925.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 8.582274150848388,
|
|
"epoch": 0.04780021461320847,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000122,
|
|
"loss": 8.4043,
|
|
"mean_token_accuracy": 0.09170760661363601,
|
|
"num_tokens": 822088.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 8.597280120849609,
|
|
"epoch": 0.0487757291971515,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 8.4091,
|
|
"mean_token_accuracy": 0.08865795284509659,
|
|
"num_tokens": 837991.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 8.430963706970214,
|
|
"epoch": 0.04975124378109453,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.000127,
|
|
"loss": 8.3073,
|
|
"mean_token_accuracy": 0.10073584988713265,
|
|
"num_tokens": 855593.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 8.710581207275391,
|
|
"epoch": 0.05072675836503756,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 8.3215,
|
|
"mean_token_accuracy": 0.09267524480819703,
|
|
"num_tokens": 873696.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 8.442234230041503,
|
|
"epoch": 0.05170227294898059,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000132,
|
|
"loss": 8.2974,
|
|
"mean_token_accuracy": 0.098615263402462,
|
|
"num_tokens": 890023.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 8.602227687835693,
|
|
"epoch": 0.05267778753292362,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 8.4573,
|
|
"mean_token_accuracy": 0.08713396042585372,
|
|
"num_tokens": 906492.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 8.557075691223144,
|
|
"epoch": 0.05365330211686665,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 8.3801,
|
|
"mean_token_accuracy": 0.08883005455136299,
|
|
"num_tokens": 921837.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 8.565664386749267,
|
|
"epoch": 0.05462881670080968,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 8.3169,
|
|
"mean_token_accuracy": 0.0994895301759243,
|
|
"num_tokens": 938771.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 8.539812088012695,
|
|
"epoch": 0.05560433128475271,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 8.3361,
|
|
"mean_token_accuracy": 0.09000369980931282,
|
|
"num_tokens": 954562.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 8.536813306808472,
|
|
"epoch": 0.05657984586869574,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 8.2737,
|
|
"mean_token_accuracy": 0.09747345894575118,
|
|
"num_tokens": 973700.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 8.417824840545654,
|
|
"epoch": 0.05755536045263877,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.000147,
|
|
"loss": 8.3354,
|
|
"mean_token_accuracy": 0.09296533018350601,
|
|
"num_tokens": 990688.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 8.517854309082031,
|
|
"epoch": 0.058530875036581796,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 8.4108,
|
|
"mean_token_accuracy": 0.08671896606683731,
|
|
"num_tokens": 1008144.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 8.50785789489746,
|
|
"epoch": 0.059506389620524826,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.000152,
|
|
"loss": 8.3529,
|
|
"mean_token_accuracy": 0.08922475874423981,
|
|
"num_tokens": 1027379.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 8.543958187103271,
|
|
"epoch": 0.060481904204467855,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 8.3276,
|
|
"mean_token_accuracy": 0.09632412865757942,
|
|
"num_tokens": 1043999.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 8.512003898620605,
|
|
"epoch": 0.061457418788410885,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000157,
|
|
"loss": 8.3399,
|
|
"mean_token_accuracy": 0.08813720867037773,
|
|
"num_tokens": 1062237.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 8.499386405944824,
|
|
"epoch": 0.062432933372353915,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 8.2911,
|
|
"mean_token_accuracy": 0.09350473955273628,
|
|
"num_tokens": 1078092.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 8.514391231536866,
|
|
"epoch": 0.06340844795629695,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000162,
|
|
"loss": 8.3255,
|
|
"mean_token_accuracy": 0.09594152867794037,
|
|
"num_tokens": 1095124.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 8.501588439941406,
|
|
"epoch": 0.06438396254023998,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 8.3112,
|
|
"mean_token_accuracy": 0.0899473249912262,
|
|
"num_tokens": 1112775.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 8.435393333435059,
|
|
"epoch": 0.06535947712418301,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 8.2395,
|
|
"mean_token_accuracy": 0.09844813719391823,
|
|
"num_tokens": 1129726.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 8.475375080108643,
|
|
"epoch": 0.06633499170812604,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 8.2963,
|
|
"mean_token_accuracy": 0.09962385520339012,
|
|
"num_tokens": 1144034.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 8.432106876373291,
|
|
"epoch": 0.06731050629206907,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 8.243,
|
|
"mean_token_accuracy": 0.0963106982409954,
|
|
"num_tokens": 1159633.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 8.410737228393554,
|
|
"epoch": 0.0682860208760121,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 8.2048,
|
|
"mean_token_accuracy": 0.09049743562936782,
|
|
"num_tokens": 1175350.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 8.411827564239502,
|
|
"epoch": 0.06926153545995513,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.000177,
|
|
"loss": 8.1279,
|
|
"mean_token_accuracy": 0.09687257036566735,
|
|
"num_tokens": 1193121.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 8.431901168823241,
|
|
"epoch": 0.07023705004389816,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 8.2869,
|
|
"mean_token_accuracy": 0.090427827835083,
|
|
"num_tokens": 1209896.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 8.414903736114502,
|
|
"epoch": 0.07121256462784119,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000182,
|
|
"loss": 8.2795,
|
|
"mean_token_accuracy": 0.09120966792106629,
|
|
"num_tokens": 1227011.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 8.36677007675171,
|
|
"epoch": 0.07218807921178422,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 8.2051,
|
|
"mean_token_accuracy": 0.09367732107639312,
|
|
"num_tokens": 1241595.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 8.433219146728515,
|
|
"epoch": 0.07316359379572725,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000187,
|
|
"loss": 8.2106,
|
|
"mean_token_accuracy": 0.09003259316086769,
|
|
"num_tokens": 1256919.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 8.26855993270874,
|
|
"epoch": 0.07413910837967028,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 8.2039,
|
|
"mean_token_accuracy": 0.1087122842669487,
|
|
"num_tokens": 1274344.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 8.406241989135742,
|
|
"epoch": 0.0751146229636133,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000192,
|
|
"loss": 8.1847,
|
|
"mean_token_accuracy": 0.09858927503228188,
|
|
"num_tokens": 1290252.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 8.430280685424805,
|
|
"epoch": 0.07609013754755634,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 8.241,
|
|
"mean_token_accuracy": 0.09144357889890671,
|
|
"num_tokens": 1306987.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 8.38391466140747,
|
|
"epoch": 0.07706565213149937,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 8.2544,
|
|
"mean_token_accuracy": 0.0886089101433754,
|
|
"num_tokens": 1323031.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 8.422025775909423,
|
|
"epoch": 0.0780411667154424,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 8.1942,
|
|
"mean_token_accuracy": 0.09101833701133728,
|
|
"num_tokens": 1339592.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 8.359192848205566,
|
|
"epoch": 0.07901668129938542,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000202,
|
|
"loss": 8.1758,
|
|
"mean_token_accuracy": 0.10071646049618721,
|
|
"num_tokens": 1358131.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 8.330156660079956,
|
|
"epoch": 0.07999219588332845,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 8.0996,
|
|
"mean_token_accuracy": 0.10162749364972115,
|
|
"num_tokens": 1375705.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 8.238559198379516,
|
|
"epoch": 0.08096771046727148,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000207,
|
|
"loss": 8.1287,
|
|
"mean_token_accuracy": 0.10049679651856422,
|
|
"num_tokens": 1392736.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 8.364288711547852,
|
|
"epoch": 0.08194322505121451,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 8.1716,
|
|
"mean_token_accuracy": 0.09369641467928887,
|
|
"num_tokens": 1408536.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 8.287070560455323,
|
|
"epoch": 0.08291873963515754,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.000212,
|
|
"loss": 8.1448,
|
|
"mean_token_accuracy": 0.09421766176819801,
|
|
"num_tokens": 1425423.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 8.344510269165038,
|
|
"epoch": 0.08389425421910057,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 8.1528,
|
|
"mean_token_accuracy": 0.09409154579043388,
|
|
"num_tokens": 1442420.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 8.356864070892334,
|
|
"epoch": 0.0848697688030436,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 8.1051,
|
|
"mean_token_accuracy": 0.09946276843547822,
|
|
"num_tokens": 1458835.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 8.345529747009277,
|
|
"epoch": 0.08584528338698663,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 8.2056,
|
|
"mean_token_accuracy": 0.09219177067279816,
|
|
"num_tokens": 1475563.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 8.245398807525635,
|
|
"epoch": 0.08682079797092966,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000222,
|
|
"loss": 8.1443,
|
|
"mean_token_accuracy": 0.10394385680556298,
|
|
"num_tokens": 1492687.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 8.398572254180909,
|
|
"epoch": 0.08779631255487269,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 8.1549,
|
|
"mean_token_accuracy": 0.09206878691911698,
|
|
"num_tokens": 1508394.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 8.238665962219239,
|
|
"epoch": 0.08877182713881572,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 8.1345,
|
|
"mean_token_accuracy": 0.1022073931992054,
|
|
"num_tokens": 1527112.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 8.340081214904785,
|
|
"epoch": 0.08974734172275875,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 8.172,
|
|
"mean_token_accuracy": 0.1001360334455967,
|
|
"num_tokens": 1545401.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 8.266607761383057,
|
|
"epoch": 0.09072285630670178,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 8.0632,
|
|
"mean_token_accuracy": 0.09910417199134827,
|
|
"num_tokens": 1561621.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 8.288278388977051,
|
|
"epoch": 0.09169837089064481,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 8.1701,
|
|
"mean_token_accuracy": 0.09583483785390853,
|
|
"num_tokens": 1579225.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 8.34649305343628,
|
|
"epoch": 0.09267388547458784,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000237,
|
|
"loss": 8.0698,
|
|
"mean_token_accuracy": 0.09566665440797806,
|
|
"num_tokens": 1596125.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 8.171308040618896,
|
|
"epoch": 0.09364940005853087,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 8.1873,
|
|
"mean_token_accuracy": 0.0900168351829052,
|
|
"num_tokens": 1613451.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 8.294004344940186,
|
|
"epoch": 0.09462491464247391,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.000242,
|
|
"loss": 8.1328,
|
|
"mean_token_accuracy": 0.09555885493755341,
|
|
"num_tokens": 1630929.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 8.21247615814209,
|
|
"epoch": 0.09560042922641694,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 8.1292,
|
|
"mean_token_accuracy": 0.09596397504210472,
|
|
"num_tokens": 1647379.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 8.275317049026489,
|
|
"epoch": 0.09657594381035997,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000247,
|
|
"loss": 7.9022,
|
|
"mean_token_accuracy": 0.10550546199083329,
|
|
"num_tokens": 1664415.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 8.096874141693116,
|
|
"epoch": 0.097551458394303,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 7.98,
|
|
"mean_token_accuracy": 0.10389248356223106,
|
|
"num_tokens": 1679556.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 8.084659719467163,
|
|
"epoch": 0.09852697297824603,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000252,
|
|
"loss": 7.929,
|
|
"mean_token_accuracy": 0.11411564722657204,
|
|
"num_tokens": 1696727.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 8.191386079788208,
|
|
"epoch": 0.09950248756218906,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 7.9651,
|
|
"mean_token_accuracy": 0.10536571145057679,
|
|
"num_tokens": 1713918.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 8.281560707092286,
|
|
"epoch": 0.10047800214613209,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000257,
|
|
"loss": 8.1123,
|
|
"mean_token_accuracy": 0.08992677107453347,
|
|
"num_tokens": 1729581.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 8.201297378540039,
|
|
"epoch": 0.10145351673007512,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 7.9692,
|
|
"mean_token_accuracy": 0.09487369433045387,
|
|
"num_tokens": 1746367.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 8.232381868362427,
|
|
"epoch": 0.10242903131401815,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000262,
|
|
"loss": 8.0664,
|
|
"mean_token_accuracy": 0.09260008409619332,
|
|
"num_tokens": 1765009.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 8.1582435131073,
|
|
"epoch": 0.10340454589796118,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 8.0738,
|
|
"mean_token_accuracy": 0.09549360871315002,
|
|
"num_tokens": 1782113.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 8.155733203887939,
|
|
"epoch": 0.10438006048190421,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 7.9716,
|
|
"mean_token_accuracy": 0.0997552827000618,
|
|
"num_tokens": 1798301.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 8.204453039169312,
|
|
"epoch": 0.10535557506584724,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 8.0163,
|
|
"mean_token_accuracy": 0.09422366693615913,
|
|
"num_tokens": 1815059.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 8.108425045013428,
|
|
"epoch": 0.10633108964979027,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 7.9208,
|
|
"mean_token_accuracy": 0.10392606258392334,
|
|
"num_tokens": 1831699.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 8.054630374908447,
|
|
"epoch": 0.1073066042337333,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 7.987,
|
|
"mean_token_accuracy": 0.09787993282079696,
|
|
"num_tokens": 1847993.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 8.20120029449463,
|
|
"epoch": 0.10828211881767633,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000277,
|
|
"loss": 7.8415,
|
|
"mean_token_accuracy": 0.10329653769731521,
|
|
"num_tokens": 1864753.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 8.112896871566772,
|
|
"epoch": 0.10925763340161936,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 7.998,
|
|
"mean_token_accuracy": 0.10229669883847237,
|
|
"num_tokens": 1882154.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 8.059369564056396,
|
|
"epoch": 0.11023314798556239,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 7.8607,
|
|
"mean_token_accuracy": 0.10597956404089928,
|
|
"num_tokens": 1899683.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 8.033463430404662,
|
|
"epoch": 0.11120866256950541,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 7.8691,
|
|
"mean_token_accuracy": 0.10046507343649864,
|
|
"num_tokens": 1918489.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 8.10311417579651,
|
|
"epoch": 0.11218417715344844,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000287,
|
|
"loss": 7.9332,
|
|
"mean_token_accuracy": 0.0978827528655529,
|
|
"num_tokens": 1935609.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 8.027519035339356,
|
|
"epoch": 0.11315969173739147,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 7.9663,
|
|
"mean_token_accuracy": 0.09261189103126526,
|
|
"num_tokens": 1951311.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 8.112423610687255,
|
|
"epoch": 0.1141352063213345,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000292,
|
|
"loss": 8.0193,
|
|
"mean_token_accuracy": 0.09270902574062348,
|
|
"num_tokens": 1968908.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 8.119378280639648,
|
|
"epoch": 0.11511072090527753,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 7.9161,
|
|
"mean_token_accuracy": 0.09896000772714615,
|
|
"num_tokens": 1983807.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 8.102399921417236,
|
|
"epoch": 0.11608623548922056,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000297,
|
|
"loss": 7.9479,
|
|
"mean_token_accuracy": 0.09910893440246582,
|
|
"num_tokens": 2000219.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 8.085544061660766,
|
|
"epoch": 0.11706175007316359,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 7.8969,
|
|
"mean_token_accuracy": 0.10566937029361725,
|
|
"num_tokens": 2017360.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 7.984587049484253,
|
|
"epoch": 0.11803726465710662,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000302,
|
|
"loss": 7.8842,
|
|
"mean_token_accuracy": 0.10565442368388175,
|
|
"num_tokens": 2034953.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 8.064342927932739,
|
|
"epoch": 0.11901277924104965,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 7.8435,
|
|
"mean_token_accuracy": 0.09929553419351578,
|
|
"num_tokens": 2051551.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 8.023351669311523,
|
|
"epoch": 0.11998829382499268,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000307,
|
|
"loss": 7.8137,
|
|
"mean_token_accuracy": 0.10783486068248749,
|
|
"num_tokens": 2067188.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 7.9922370433807375,
|
|
"epoch": 0.12096380840893571,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 7.8723,
|
|
"mean_token_accuracy": 0.10359162315726281,
|
|
"num_tokens": 2082569.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 8.063414001464844,
|
|
"epoch": 0.12193932299287874,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.000312,
|
|
"loss": 7.9427,
|
|
"mean_token_accuracy": 0.09755868315696717,
|
|
"num_tokens": 2099446.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 8.01604437828064,
|
|
"epoch": 0.12291483757682177,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 7.8774,
|
|
"mean_token_accuracy": 0.1052703656256199,
|
|
"num_tokens": 2116526.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 8.07321276664734,
|
|
"epoch": 0.1238903521607648,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000317,
|
|
"loss": 7.9364,
|
|
"mean_token_accuracy": 0.09000732526183128,
|
|
"num_tokens": 2134624.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 7.8934488773345945,
|
|
"epoch": 0.12486586674470783,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 7.7724,
|
|
"mean_token_accuracy": 0.10647233128547669,
|
|
"num_tokens": 2152872.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 8.017675352096557,
|
|
"epoch": 0.12584138132865086,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000322,
|
|
"loss": 7.9026,
|
|
"mean_token_accuracy": 0.09761283919215202,
|
|
"num_tokens": 2169480.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 7.964239072799683,
|
|
"epoch": 0.1268168959125939,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 7.7652,
|
|
"mean_token_accuracy": 0.11001085266470909,
|
|
"num_tokens": 2186054.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 8.021305990219116,
|
|
"epoch": 0.12779241049653692,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 7.9007,
|
|
"mean_token_accuracy": 0.09257680848240853,
|
|
"num_tokens": 2202320.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 7.897371673583985,
|
|
"epoch": 0.12876792508047996,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 7.7826,
|
|
"mean_token_accuracy": 0.10420317128300667,
|
|
"num_tokens": 2218817.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 8.001240921020507,
|
|
"epoch": 0.12974343966442298,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 7.9361,
|
|
"mean_token_accuracy": 0.09622591212391854,
|
|
"num_tokens": 2234845.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 8.018117094039917,
|
|
"epoch": 0.13071895424836602,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 7.87,
|
|
"mean_token_accuracy": 0.09835803210735321,
|
|
"num_tokens": 2251904.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 7.918103551864624,
|
|
"epoch": 0.13169446883230904,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000337,
|
|
"loss": 7.872,
|
|
"mean_token_accuracy": 0.10161498412489892,
|
|
"num_tokens": 2268343.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 8.039315509796143,
|
|
"epoch": 0.13266998341625208,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 7.8635,
|
|
"mean_token_accuracy": 0.10121119394898415,
|
|
"num_tokens": 2284524.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 7.767062854766846,
|
|
"epoch": 0.1336454980001951,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000342,
|
|
"loss": 7.7948,
|
|
"mean_token_accuracy": 0.10690312683582306,
|
|
"num_tokens": 2302350.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 8.020025968551636,
|
|
"epoch": 0.13462101258413814,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 7.8576,
|
|
"mean_token_accuracy": 0.09347154945135117,
|
|
"num_tokens": 2319953.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 7.949396181106567,
|
|
"epoch": 0.13559652716808115,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000347,
|
|
"loss": 7.7541,
|
|
"mean_token_accuracy": 0.10058033019304276,
|
|
"num_tokens": 2336698.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 7.795568990707397,
|
|
"epoch": 0.1365720417520242,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 7.7172,
|
|
"mean_token_accuracy": 0.10608202442526818,
|
|
"num_tokens": 2353986.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 7.892446756362915,
|
|
"epoch": 0.1375475563359672,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000352,
|
|
"loss": 7.7931,
|
|
"mean_token_accuracy": 0.10464861243963242,
|
|
"num_tokens": 2370320.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 7.920102310180664,
|
|
"epoch": 0.13852307091991026,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 7.8371,
|
|
"mean_token_accuracy": 0.09619187116622925,
|
|
"num_tokens": 2385453.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 7.961038494110108,
|
|
"epoch": 0.13949858550385327,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000357,
|
|
"loss": 7.8199,
|
|
"mean_token_accuracy": 0.09596224501729012,
|
|
"num_tokens": 2401545.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 7.852643156051636,
|
|
"epoch": 0.14047410008779632,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 7.8045,
|
|
"mean_token_accuracy": 0.10015163868665695,
|
|
"num_tokens": 2418414.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 7.859485912322998,
|
|
"epoch": 0.14144961467173933,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000362,
|
|
"loss": 7.8569,
|
|
"mean_token_accuracy": 0.09870302975177765,
|
|
"num_tokens": 2434973.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 7.955648517608642,
|
|
"epoch": 0.14242512925568238,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 7.8625,
|
|
"mean_token_accuracy": 0.09559171572327614,
|
|
"num_tokens": 2451053.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 7.91767840385437,
|
|
"epoch": 0.1434006438396254,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000367,
|
|
"loss": 7.8198,
|
|
"mean_token_accuracy": 0.09590378031134605,
|
|
"num_tokens": 2467280.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 7.8793638229370115,
|
|
"epoch": 0.14437615842356843,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 7.7417,
|
|
"mean_token_accuracy": 0.10683688595890999,
|
|
"num_tokens": 2484588.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 7.828915596008301,
|
|
"epoch": 0.14535167300751145,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000372,
|
|
"loss": 7.7492,
|
|
"mean_token_accuracy": 0.10286132618784904,
|
|
"num_tokens": 2501200.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 7.78443865776062,
|
|
"epoch": 0.1463271875914545,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 7.7085,
|
|
"mean_token_accuracy": 0.11014421433210372,
|
|
"num_tokens": 2517199.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 7.8230297565460205,
|
|
"epoch": 0.1473027021753975,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000377,
|
|
"loss": 7.772,
|
|
"mean_token_accuracy": 0.0969228208065033,
|
|
"num_tokens": 2534824.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 7.725612926483154,
|
|
"epoch": 0.14827821675934055,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 7.6539,
|
|
"mean_token_accuracy": 0.10735608860850335,
|
|
"num_tokens": 2550842.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 7.8303399085998535,
|
|
"epoch": 0.14925373134328357,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000382,
|
|
"loss": 7.5965,
|
|
"mean_token_accuracy": 0.10855040177702904,
|
|
"num_tokens": 2567878.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 7.791242980957032,
|
|
"epoch": 0.1502292459272266,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 7.7018,
|
|
"mean_token_accuracy": 0.1028899759054184,
|
|
"num_tokens": 2584148.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 7.784344911575317,
|
|
"epoch": 0.15120476051116966,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 7.7143,
|
|
"mean_token_accuracy": 0.10468425303697586,
|
|
"num_tokens": 2600067.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 7.857481384277344,
|
|
"epoch": 0.15218027509511267,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 7.6988,
|
|
"mean_token_accuracy": 0.10016048923134804,
|
|
"num_tokens": 2615746.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 7.801036739349366,
|
|
"epoch": 0.15315578967905571,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 7.7356,
|
|
"mean_token_accuracy": 0.09950978606939316,
|
|
"num_tokens": 2631641.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 7.770744705200196,
|
|
"epoch": 0.15413130426299873,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 7.723,
|
|
"mean_token_accuracy": 0.10329516828060151,
|
|
"num_tokens": 2647015.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 7.763613557815551,
|
|
"epoch": 0.15510681884694177,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 7.6529,
|
|
"mean_token_accuracy": 0.09973687306046486,
|
|
"num_tokens": 2664045.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 7.779078197479248,
|
|
"epoch": 0.1560823334308848,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 7.6204,
|
|
"mean_token_accuracy": 0.10611663311719895,
|
|
"num_tokens": 2680774.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 7.753378868103027,
|
|
"epoch": 0.15705784801482783,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000402,
|
|
"loss": 7.7434,
|
|
"mean_token_accuracy": 0.10084796100854873,
|
|
"num_tokens": 2697719.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 7.735131311416626,
|
|
"epoch": 0.15803336259877085,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 7.6936,
|
|
"mean_token_accuracy": 0.09436290189623833,
|
|
"num_tokens": 2714518.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 7.7410211086273195,
|
|
"epoch": 0.1590088771827139,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 7.7422,
|
|
"mean_token_accuracy": 0.1037781998515129,
|
|
"num_tokens": 2729288.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 7.805609893798828,
|
|
"epoch": 0.1599843917666569,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 7.7328,
|
|
"mean_token_accuracy": 0.10105982348322869,
|
|
"num_tokens": 2746782.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 7.723773622512818,
|
|
"epoch": 0.16095990635059995,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000412,
|
|
"loss": 7.7618,
|
|
"mean_token_accuracy": 0.09355797246098518,
|
|
"num_tokens": 2763159.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 7.758946180343628,
|
|
"epoch": 0.16193542093454297,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 7.7035,
|
|
"mean_token_accuracy": 0.10159995257854462,
|
|
"num_tokens": 2780338.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 7.690690183639527,
|
|
"epoch": 0.162910935518486,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000417,
|
|
"loss": 7.6255,
|
|
"mean_token_accuracy": 0.1065425306558609,
|
|
"num_tokens": 2796214.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 7.810243940353393,
|
|
"epoch": 0.16388645010242903,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 7.7369,
|
|
"mean_token_accuracy": 0.09597960785031319,
|
|
"num_tokens": 2812745.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 7.653784370422363,
|
|
"epoch": 0.16486196468637207,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000422,
|
|
"loss": 7.6108,
|
|
"mean_token_accuracy": 0.10254015624523163,
|
|
"num_tokens": 2828288.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 7.766561985015869,
|
|
"epoch": 0.16583747927031509,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 7.7323,
|
|
"mean_token_accuracy": 0.0973560057580471,
|
|
"num_tokens": 2843618.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 7.639662551879883,
|
|
"epoch": 0.16681299385425813,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000427,
|
|
"loss": 7.5204,
|
|
"mean_token_accuracy": 0.11329260393977165,
|
|
"num_tokens": 2860659.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 7.678345632553101,
|
|
"epoch": 0.16778850843820114,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 7.6314,
|
|
"mean_token_accuracy": 0.09550370648503304,
|
|
"num_tokens": 2877482.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 7.740656137466431,
|
|
"epoch": 0.1687640230221442,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.000432,
|
|
"loss": 7.7182,
|
|
"mean_token_accuracy": 0.0953593485057354,
|
|
"num_tokens": 2895868.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 7.680325174331665,
|
|
"epoch": 0.1697395376060872,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 7.7127,
|
|
"mean_token_accuracy": 0.09883771538734436,
|
|
"num_tokens": 2913103.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 7.702930736541748,
|
|
"epoch": 0.17071505219003025,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000437,
|
|
"loss": 7.6396,
|
|
"mean_token_accuracy": 0.1021553747355938,
|
|
"num_tokens": 2928291.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 7.616526365280151,
|
|
"epoch": 0.17169056677397326,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 7.6904,
|
|
"mean_token_accuracy": 0.10376504734158516,
|
|
"num_tokens": 2945115.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 7.760608196258545,
|
|
"epoch": 0.1726660813579163,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000442,
|
|
"loss": 7.5907,
|
|
"mean_token_accuracy": 0.0988293744623661,
|
|
"num_tokens": 2962869.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 7.663983917236328,
|
|
"epoch": 0.17364159594185932,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 7.7038,
|
|
"mean_token_accuracy": 0.09704967588186264,
|
|
"num_tokens": 2979298.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 7.685730457305908,
|
|
"epoch": 0.17461711052580237,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000447,
|
|
"loss": 7.5975,
|
|
"mean_token_accuracy": 0.10688030645251274,
|
|
"num_tokens": 2996146.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 7.635448312759399,
|
|
"epoch": 0.17559262510974538,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 7.679,
|
|
"mean_token_accuracy": 0.10033529624342918,
|
|
"num_tokens": 3013075.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 7.693193626403809,
|
|
"epoch": 0.17656813969368843,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 7.632,
|
|
"mean_token_accuracy": 0.09835075661540031,
|
|
"num_tokens": 3029494.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 7.6192834854125975,
|
|
"epoch": 0.17754365427763144,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 7.6371,
|
|
"mean_token_accuracy": 0.10126575529575348,
|
|
"num_tokens": 3046333.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 7.632585287094116,
|
|
"epoch": 0.17851916886157448,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 7.6164,
|
|
"mean_token_accuracy": 0.10273443460464478,
|
|
"num_tokens": 3062714.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 7.714128875732422,
|
|
"epoch": 0.1794946834455175,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 7.6159,
|
|
"mean_token_accuracy": 0.10113414600491524,
|
|
"num_tokens": 3080711.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 7.591054010391235,
|
|
"epoch": 0.18047019802946054,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000462,
|
|
"loss": 7.6972,
|
|
"mean_token_accuracy": 0.09632447808980941,
|
|
"num_tokens": 3096885.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 7.6689952373504635,
|
|
"epoch": 0.18144571261340356,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 7.5938,
|
|
"mean_token_accuracy": 0.10410150662064552,
|
|
"num_tokens": 3114536.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 7.593691968917847,
|
|
"epoch": 0.1824212271973466,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.000467,
|
|
"loss": 7.5417,
|
|
"mean_token_accuracy": 0.10690793171525001,
|
|
"num_tokens": 3131921.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 7.663251686096191,
|
|
"epoch": 0.18339674178128962,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 7.6836,
|
|
"mean_token_accuracy": 0.09887410327792168,
|
|
"num_tokens": 3148064.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 7.519239473342895,
|
|
"epoch": 0.18437225636523266,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.000472,
|
|
"loss": 7.4983,
|
|
"mean_token_accuracy": 0.11145109161734582,
|
|
"num_tokens": 3165822.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 7.600449705123902,
|
|
"epoch": 0.18534777094917568,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 7.5992,
|
|
"mean_token_accuracy": 0.10686507672071457,
|
|
"num_tokens": 3183286.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 7.692311573028564,
|
|
"epoch": 0.18632328553311872,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000477,
|
|
"loss": 7.6311,
|
|
"mean_token_accuracy": 0.0974265143275261,
|
|
"num_tokens": 3198522.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 7.514405059814453,
|
|
"epoch": 0.18729880011706174,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 7.6467,
|
|
"mean_token_accuracy": 0.10179897472262382,
|
|
"num_tokens": 3218422.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 7.675178670883179,
|
|
"epoch": 0.18827431470100478,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000482,
|
|
"loss": 7.6831,
|
|
"mean_token_accuracy": 0.09527623429894447,
|
|
"num_tokens": 3236407.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 7.584980392456055,
|
|
"epoch": 0.18924982928494782,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 7.5995,
|
|
"mean_token_accuracy": 0.10131113454699517,
|
|
"num_tokens": 3252740.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 7.610750722885132,
|
|
"epoch": 0.19022534386889084,
|
|
"grad_norm": 0.74609375,
|
|
"learning_rate": 0.000487,
|
|
"loss": 7.5638,
|
|
"mean_token_accuracy": 0.09960713386535644,
|
|
"num_tokens": 3269874.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 7.584094142913818,
|
|
"epoch": 0.19120085845283388,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 7.6135,
|
|
"mean_token_accuracy": 0.10098579525947571,
|
|
"num_tokens": 3286515.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 7.482845687866211,
|
|
"epoch": 0.1921763730367769,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.000492,
|
|
"loss": 7.3981,
|
|
"mean_token_accuracy": 0.12201494947075844,
|
|
"num_tokens": 3303700.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 7.54534764289856,
|
|
"epoch": 0.19315188762071994,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 7.5804,
|
|
"mean_token_accuracy": 0.10665170550346374,
|
|
"num_tokens": 3319768.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 7.5603784084320065,
|
|
"epoch": 0.19412740220466296,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000497,
|
|
"loss": 7.4928,
|
|
"mean_token_accuracy": 0.1061321146786213,
|
|
"num_tokens": 3336555.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 7.4874776840209964,
|
|
"epoch": 0.195102916788606,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 7.4912,
|
|
"mean_token_accuracy": 0.10724320039153099,
|
|
"num_tokens": 3353273.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 7.5069818019866945,
|
|
"epoch": 0.19607843137254902,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004999999929644166,
|
|
"loss": 7.3894,
|
|
"mean_token_accuracy": 0.11500273495912552,
|
|
"num_tokens": 3369408.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 7.454842758178711,
|
|
"epoch": 0.19705394595649206,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004999999643823598,
|
|
"loss": 7.458,
|
|
"mean_token_accuracy": 0.10803161263465881,
|
|
"num_tokens": 3385834.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 7.504195785522461,
|
|
"epoch": 0.19802946054043508,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004999999138141084,
|
|
"loss": 7.5588,
|
|
"mean_token_accuracy": 0.10538785606622696,
|
|
"num_tokens": 3401407.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 7.613107299804687,
|
|
"epoch": 0.19900497512437812,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004999998412596673,
|
|
"loss": 7.5628,
|
|
"mean_token_accuracy": 0.09914690926671028,
|
|
"num_tokens": 3418256.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 7.500989294052124,
|
|
"epoch": 0.19998048970832114,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999997467190435,
|
|
"loss": 7.5344,
|
|
"mean_token_accuracy": 0.1071588896214962,
|
|
"num_tokens": 3433932.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 7.476874446868896,
|
|
"epoch": 0.20095600429226418,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999996301922465,
|
|
"loss": 7.5814,
|
|
"mean_token_accuracy": 0.09997389689087868,
|
|
"num_tokens": 3451723.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 7.533150291442871,
|
|
"epoch": 0.2019315188762072,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999994916792876,
|
|
"loss": 7.5493,
|
|
"mean_token_accuracy": 0.10057334378361701,
|
|
"num_tokens": 3469170.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 7.584330272674561,
|
|
"epoch": 0.20290703346015024,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004999993311801802,
|
|
"loss": 7.5659,
|
|
"mean_token_accuracy": 0.09998832419514656,
|
|
"num_tokens": 3485282.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 7.521093273162842,
|
|
"epoch": 0.20388254804409325,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00049999914869494,
|
|
"loss": 7.571,
|
|
"mean_token_accuracy": 0.09400331526994705,
|
|
"num_tokens": 3502206.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 7.571083688735962,
|
|
"epoch": 0.2048580626280363,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.000499998944223585,
|
|
"loss": 7.4951,
|
|
"mean_token_accuracy": 0.10485005304217339,
|
|
"num_tokens": 3520384.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 7.377060794830323,
|
|
"epoch": 0.2058335772119793,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004999987177661351,
|
|
"loss": 7.4949,
|
|
"mean_token_accuracy": 0.10567046105861663,
|
|
"num_tokens": 3536314.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 7.494265747070313,
|
|
"epoch": 0.20680909179592236,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004999984693226124,
|
|
"loss": 7.4656,
|
|
"mean_token_accuracy": 0.11277214139699936,
|
|
"num_tokens": 3551510.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 7.456046295166016,
|
|
"epoch": 0.20778460637986537,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999981988930411,
|
|
"loss": 7.4626,
|
|
"mean_token_accuracy": 0.10642851740121842,
|
|
"num_tokens": 3568515.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 7.450523471832275,
|
|
"epoch": 0.20876012096380842,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004999979064774478,
|
|
"loss": 7.4992,
|
|
"mean_token_accuracy": 0.10894627124071121,
|
|
"num_tokens": 3585183.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 7.419216012954712,
|
|
"epoch": 0.20973563554775143,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000499997592075861,
|
|
"loss": 7.4519,
|
|
"mean_token_accuracy": 0.10805186256766319,
|
|
"num_tokens": 3601898.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 7.5282000541687015,
|
|
"epoch": 0.21071115013169447,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999972556883113,
|
|
"loss": 7.5039,
|
|
"mean_token_accuracy": 0.103752601146698,
|
|
"num_tokens": 3616699.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 7.493114757537842,
|
|
"epoch": 0.2116866647156375,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004999968973148318,
|
|
"loss": 7.5122,
|
|
"mean_token_accuracy": 0.10303746312856674,
|
|
"num_tokens": 3634030.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 7.544573545455933,
|
|
"epoch": 0.21266217929958053,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004999965169554573,
|
|
"loss": 7.5177,
|
|
"mean_token_accuracy": 0.1014569953083992,
|
|
"num_tokens": 3650495.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 7.461155843734741,
|
|
"epoch": 0.21363769388352355,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999961146102251,
|
|
"loss": 7.4642,
|
|
"mean_token_accuracy": 0.10736886784434319,
|
|
"num_tokens": 3666926.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 7.4098371982574465,
|
|
"epoch": 0.2146132084674666,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004999956902791746,
|
|
"loss": 7.4399,
|
|
"mean_token_accuracy": 0.11416979283094406,
|
|
"num_tokens": 3683061.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 7.425881814956665,
|
|
"epoch": 0.2155887230514096,
|
|
"grad_norm": 0.7421875,
|
|
"learning_rate": 0.0004999952439623469,
|
|
"loss": 7.5083,
|
|
"mean_token_accuracy": 0.10643071681261063,
|
|
"num_tokens": 3703013.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 7.470410490036011,
|
|
"epoch": 0.21656423763535265,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.000499994775659786,
|
|
"loss": 7.3552,
|
|
"mean_token_accuracy": 0.11576942354440689,
|
|
"num_tokens": 3719885.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 7.442147254943848,
|
|
"epoch": 0.21753975221929567,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999942853715375,
|
|
"loss": 7.5,
|
|
"mean_token_accuracy": 0.10365172252058982,
|
|
"num_tokens": 3735122.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 7.475345134735107,
|
|
"epoch": 0.2185152668032387,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0004999937730976494,
|
|
"loss": 7.4711,
|
|
"mean_token_accuracy": 0.10123512893915176,
|
|
"num_tokens": 3751627.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 7.391668796539307,
|
|
"epoch": 0.21949078138718173,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999932388381716,
|
|
"loss": 7.4941,
|
|
"mean_token_accuracy": 0.10175474062561989,
|
|
"num_tokens": 3768165.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 7.565304565429687,
|
|
"epoch": 0.22046629597112477,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004999926825931564,
|
|
"loss": 7.5158,
|
|
"mean_token_accuracy": 0.1036800429224968,
|
|
"num_tokens": 3784245.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 7.275793266296387,
|
|
"epoch": 0.2214418105550678,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004999921043626582,
|
|
"loss": 7.2665,
|
|
"mean_token_accuracy": 0.11247111111879349,
|
|
"num_tokens": 3802057.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 7.457341098785401,
|
|
"epoch": 0.22241732513901083,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004999915041467333,
|
|
"loss": 7.4519,
|
|
"mean_token_accuracy": 0.10512350872159004,
|
|
"num_tokens": 3817104.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 7.422237396240234,
|
|
"epoch": 0.22339283972295385,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004999908819454407,
|
|
"loss": 7.446,
|
|
"mean_token_accuracy": 0.10683505311608314,
|
|
"num_tokens": 3833037.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 7.36663784980774,
|
|
"epoch": 0.2243683543068969,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004999902377588408,
|
|
"loss": 7.3331,
|
|
"mean_token_accuracy": 0.10857838094234466,
|
|
"num_tokens": 3849634.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 7.420496654510498,
|
|
"epoch": 0.2253438688908399,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.000499989571586997,
|
|
"loss": 7.4986,
|
|
"mean_token_accuracy": 0.10436328127980232,
|
|
"num_tokens": 3865949.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 7.3169677734375,
|
|
"epoch": 0.22631938347478295,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004999888834299739,
|
|
"loss": 7.3869,
|
|
"mean_token_accuracy": 0.11616735979914665,
|
|
"num_tokens": 3884646.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 7.491457986831665,
|
|
"epoch": 0.227294898058726,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004999881732878391,
|
|
"loss": 7.466,
|
|
"mean_token_accuracy": 0.10703919902443886,
|
|
"num_tokens": 3900740.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 7.363152885437012,
|
|
"epoch": 0.228270412642669,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004999874411606618,
|
|
"loss": 7.4314,
|
|
"mean_token_accuracy": 0.11084038242697716,
|
|
"num_tokens": 3918619.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 7.45768780708313,
|
|
"epoch": 0.22924592722661205,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004999866870485137,
|
|
"loss": 7.3911,
|
|
"mean_token_accuracy": 0.10921363979578018,
|
|
"num_tokens": 3938161.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 7.441078805923462,
|
|
"epoch": 0.23022144181055507,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999859109514684,
|
|
"loss": 7.4416,
|
|
"mean_token_accuracy": 0.1069450207054615,
|
|
"num_tokens": 3953582.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 7.39387698173523,
|
|
"epoch": 0.2311969563944981,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004999851128696017,
|
|
"loss": 7.409,
|
|
"mean_token_accuracy": 0.1000187411904335,
|
|
"num_tokens": 3969747.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 7.476375389099121,
|
|
"epoch": 0.23217247097844113,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004999842928029917,
|
|
"loss": 7.4518,
|
|
"mean_token_accuracy": 0.10572833418846131,
|
|
"num_tokens": 3984646.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 7.347596120834351,
|
|
"epoch": 0.23314798556238417,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004999834507517184,
|
|
"loss": 7.4403,
|
|
"mean_token_accuracy": 0.10399013683199883,
|
|
"num_tokens": 4003108.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 7.443073081970215,
|
|
"epoch": 0.23412350014632718,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004999825867158642,
|
|
"loss": 7.5053,
|
|
"mean_token_accuracy": 0.10046004429459572,
|
|
"num_tokens": 4019944.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 7.434243679046631,
|
|
"epoch": 0.23509901473027023,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004999817006955134,
|
|
"loss": 7.3817,
|
|
"mean_token_accuracy": 0.11024417504668235,
|
|
"num_tokens": 4037617.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 7.375543785095215,
|
|
"epoch": 0.23607452931421324,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004999807926907527,
|
|
"loss": 7.3821,
|
|
"mean_token_accuracy": 0.10390213131904602,
|
|
"num_tokens": 4053483.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 7.442840242385865,
|
|
"epoch": 0.2370500438981563,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004999798627016707,
|
|
"loss": 7.4542,
|
|
"mean_token_accuracy": 0.10955530405044556,
|
|
"num_tokens": 4070165.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 7.404299592971801,
|
|
"epoch": 0.2380255584820993,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999789107283586,
|
|
"loss": 7.4285,
|
|
"mean_token_accuracy": 0.1026936151087284,
|
|
"num_tokens": 4086208.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 7.361278438568116,
|
|
"epoch": 0.23900107306604235,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.000499977936770909,
|
|
"loss": 7.3886,
|
|
"mean_token_accuracy": 0.10849282145500183,
|
|
"num_tokens": 4101790.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 7.39232292175293,
|
|
"epoch": 0.23997658764998536,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004999769408294173,
|
|
"loss": 7.3226,
|
|
"mean_token_accuracy": 0.11622612252831459,
|
|
"num_tokens": 4117633.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 7.36030535697937,
|
|
"epoch": 0.2409521022339284,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004999759229039807,
|
|
"loss": 7.3937,
|
|
"mean_token_accuracy": 0.10975055694580078,
|
|
"num_tokens": 4132634.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 7.391692495346069,
|
|
"epoch": 0.24192761681787142,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004999748829946988,
|
|
"loss": 7.4326,
|
|
"mean_token_accuracy": 0.10449747890233993,
|
|
"num_tokens": 4150702.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 7.378620338439942,
|
|
"epoch": 0.24290313140181446,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004999738211016732,
|
|
"loss": 7.3054,
|
|
"mean_token_accuracy": 0.12116105854511261,
|
|
"num_tokens": 4168483.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 7.168521881103516,
|
|
"epoch": 0.24387864598575748,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999727372250076,
|
|
"loss": 7.269,
|
|
"mean_token_accuracy": 0.11330273225903512,
|
|
"num_tokens": 4186199.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 7.455726528167725,
|
|
"epoch": 0.24485416056970052,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004999716313648079,
|
|
"loss": 7.4094,
|
|
"mean_token_accuracy": 0.10582706704735756,
|
|
"num_tokens": 4202303.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 7.416627550125122,
|
|
"epoch": 0.24582967515364354,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004999705035211822,
|
|
"loss": 7.4334,
|
|
"mean_token_accuracy": 0.1056906208395958,
|
|
"num_tokens": 4218541.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 7.40962781906128,
|
|
"epoch": 0.24680518973758658,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999693536942406,
|
|
"loss": 7.4016,
|
|
"mean_token_accuracy": 0.10808240473270417,
|
|
"num_tokens": 4234025.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 7.359267616271973,
|
|
"epoch": 0.2477807043215296,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999681818840957,
|
|
"loss": 7.4212,
|
|
"mean_token_accuracy": 0.10803825408220291,
|
|
"num_tokens": 4250798.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 7.362655210494995,
|
|
"epoch": 0.24875621890547264,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000499966988090862,
|
|
"loss": 7.4198,
|
|
"mean_token_accuracy": 0.10368345007300377,
|
|
"num_tokens": 4266453.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 7.493310832977295,
|
|
"epoch": 0.24973173348941566,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999657723146558,
|
|
"loss": 7.3599,
|
|
"mean_token_accuracy": 0.11028055846691132,
|
|
"num_tokens": 4281825.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 7.1498860836029055,
|
|
"epoch": 0.2507072480733587,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004999645345555962,
|
|
"loss": 7.2152,
|
|
"mean_token_accuracy": 0.12320265024900437,
|
|
"num_tokens": 4298821.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 7.333085250854492,
|
|
"epoch": 0.2516827626573017,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004999632748138041,
|
|
"loss": 7.2362,
|
|
"mean_token_accuracy": 0.11482708379626275,
|
|
"num_tokens": 4314076.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 7.318206071853638,
|
|
"epoch": 0.25265827724124473,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004999619930894025,
|
|
"loss": 7.2854,
|
|
"mean_token_accuracy": 0.11372094079852105,
|
|
"num_tokens": 4330909.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 7.337229156494141,
|
|
"epoch": 0.2536337918251878,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004999606893825168,
|
|
"loss": 7.3535,
|
|
"mean_token_accuracy": 0.11244488433003426,
|
|
"num_tokens": 4346927.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 7.334287166595459,
|
|
"epoch": 0.2546093064091308,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004999593636932742,
|
|
"loss": 7.4025,
|
|
"mean_token_accuracy": 0.106304831802845,
|
|
"num_tokens": 4364956.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 7.3552874565124515,
|
|
"epoch": 0.25558482099307384,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004999580160218044,
|
|
"loss": 7.3232,
|
|
"mean_token_accuracy": 0.11021103486418724,
|
|
"num_tokens": 4383014.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 7.275822448730469,
|
|
"epoch": 0.25656033557701685,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004999566463682391,
|
|
"loss": 7.4183,
|
|
"mean_token_accuracy": 0.10739389285445214,
|
|
"num_tokens": 4401050.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 7.3236278057098385,
|
|
"epoch": 0.2575358501609599,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004999552547327119,
|
|
"loss": 7.2918,
|
|
"mean_token_accuracy": 0.1109052024781704,
|
|
"num_tokens": 4415453.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 7.293913793563843,
|
|
"epoch": 0.25851136474490294,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004999538411153591,
|
|
"loss": 7.2756,
|
|
"mean_token_accuracy": 0.1161400705575943,
|
|
"num_tokens": 4433107.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 7.332246017456055,
|
|
"epoch": 0.25948687932884595,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004999524055163187,
|
|
"loss": 7.3661,
|
|
"mean_token_accuracy": 0.10503623932600022,
|
|
"num_tokens": 4449440.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 7.3815333366394045,
|
|
"epoch": 0.26046239391278897,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.000499950947935731,
|
|
"loss": 7.3488,
|
|
"mean_token_accuracy": 0.10719693452119827,
|
|
"num_tokens": 4465327.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 7.370807838439942,
|
|
"epoch": 0.26143790849673204,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004999494683737384,
|
|
"loss": 7.3741,
|
|
"mean_token_accuracy": 0.1034908264875412,
|
|
"num_tokens": 4481518.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 7.375785827636719,
|
|
"epoch": 0.26241342308067506,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004999479668304854,
|
|
"loss": 7.3928,
|
|
"mean_token_accuracy": 0.10684486851096153,
|
|
"num_tokens": 4497632.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 7.132483434677124,
|
|
"epoch": 0.2633889376646181,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004999464433061188,
|
|
"loss": 7.1541,
|
|
"mean_token_accuracy": 0.12024063989520073,
|
|
"num_tokens": 4513790.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 7.308583927154541,
|
|
"epoch": 0.26436445224856114,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004999448978007876,
|
|
"loss": 7.278,
|
|
"mean_token_accuracy": 0.112956852465868,
|
|
"num_tokens": 4530802.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 7.34735803604126,
|
|
"epoch": 0.26533996683250416,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999433303146426,
|
|
"loss": 7.3344,
|
|
"mean_token_accuracy": 0.10671353563666344,
|
|
"num_tokens": 4546208.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 7.294841766357422,
|
|
"epoch": 0.2663154814164472,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0004999417408478371,
|
|
"loss": 7.3908,
|
|
"mean_token_accuracy": 0.10694388523697854,
|
|
"num_tokens": 4563753.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 7.300462913513184,
|
|
"epoch": 0.2672909960003902,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999401294005264,
|
|
"loss": 7.275,
|
|
"mean_token_accuracy": 0.11355202496051789,
|
|
"num_tokens": 4580274.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 7.285962104797363,
|
|
"epoch": 0.26826651058433326,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000499938495972868,
|
|
"loss": 7.3565,
|
|
"mean_token_accuracy": 0.10627115666866302,
|
|
"num_tokens": 4596085.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 7.340288925170898,
|
|
"epoch": 0.2692420251682763,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004999368405650214,
|
|
"loss": 7.3823,
|
|
"mean_token_accuracy": 0.10515163168311119,
|
|
"num_tokens": 4613258.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 7.229737424850464,
|
|
"epoch": 0.2702175397522193,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004999351631771485,
|
|
"loss": 7.2144,
|
|
"mean_token_accuracy": 0.11676347106695176,
|
|
"num_tokens": 4630128.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 7.2856508731842045,
|
|
"epoch": 0.2711930543361623,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004999334638094131,
|
|
"loss": 7.2457,
|
|
"mean_token_accuracy": 0.11199160739779472,
|
|
"num_tokens": 4646181.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 7.3243039608001705,
|
|
"epoch": 0.2721685689201054,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004999317424619812,
|
|
"loss": 7.2958,
|
|
"mean_token_accuracy": 0.10610211119055749,
|
|
"num_tokens": 4661804.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 7.253617286682129,
|
|
"epoch": 0.2731440835040484,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004999299991350212,
|
|
"loss": 7.2073,
|
|
"mean_token_accuracy": 0.11567432507872581,
|
|
"num_tokens": 4678163.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 7.251808834075928,
|
|
"epoch": 0.2741195980879914,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004999282338287034,
|
|
"loss": 7.2031,
|
|
"mean_token_accuracy": 0.11231900975108147,
|
|
"num_tokens": 4695469.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 7.328244829177857,
|
|
"epoch": 0.2750951126719344,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004999264465432001,
|
|
"loss": 7.3404,
|
|
"mean_token_accuracy": 0.11071868836879731,
|
|
"num_tokens": 4711599.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 7.275565099716187,
|
|
"epoch": 0.2760706272558775,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004999246372786862,
|
|
"loss": 7.3392,
|
|
"mean_token_accuracy": 0.10794105604290963,
|
|
"num_tokens": 4728381.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 7.267817783355713,
|
|
"epoch": 0.2770461418398205,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004999228060353385,
|
|
"loss": 7.3392,
|
|
"mean_token_accuracy": 0.10768465995788574,
|
|
"num_tokens": 4745348.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 7.346744680404663,
|
|
"epoch": 0.27802165642376353,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999209528133357,
|
|
"loss": 7.341,
|
|
"mean_token_accuracy": 0.10165520682930947,
|
|
"num_tokens": 4763011.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 7.288636779785156,
|
|
"epoch": 0.27899717100770655,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000499919077612859,
|
|
"loss": 7.288,
|
|
"mean_token_accuracy": 0.10964113101363182,
|
|
"num_tokens": 4779462.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 7.215214252471924,
|
|
"epoch": 0.2799726855916496,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004999171804340917,
|
|
"loss": 7.2462,
|
|
"mean_token_accuracy": 0.11817943677306175,
|
|
"num_tokens": 4796844.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 7.266482639312744,
|
|
"epoch": 0.28094820017559263,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004999152612772191,
|
|
"loss": 7.2566,
|
|
"mean_token_accuracy": 0.1129236064851284,
|
|
"num_tokens": 4812851.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 7.202636861801148,
|
|
"epoch": 0.28192371475953565,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999133201424288,
|
|
"loss": 7.2044,
|
|
"mean_token_accuracy": 0.11233072057366371,
|
|
"num_tokens": 4830144.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 7.329087591171264,
|
|
"epoch": 0.28289922934347866,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999113570299105,
|
|
"loss": 7.2945,
|
|
"mean_token_accuracy": 0.10283592864871025,
|
|
"num_tokens": 4846981.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 7.3973691940307615,
|
|
"epoch": 0.28387474392742174,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004999093719398561,
|
|
"loss": 7.4583,
|
|
"mean_token_accuracy": 0.09933406785130501,
|
|
"num_tokens": 4864404.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 7.256984806060791,
|
|
"epoch": 0.28485025851136475,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999073648724592,
|
|
"loss": 7.3441,
|
|
"mean_token_accuracy": 0.10281749814748764,
|
|
"num_tokens": 4882004.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 7.35606198310852,
|
|
"epoch": 0.28582577309530777,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004999053358279164,
|
|
"loss": 7.2788,
|
|
"mean_token_accuracy": 0.10536540821194648,
|
|
"num_tokens": 4899444.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 7.294085502624512,
|
|
"epoch": 0.2868012876792508,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004999032848064256,
|
|
"loss": 7.2738,
|
|
"mean_token_accuracy": 0.10585445612668991,
|
|
"num_tokens": 4917214.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 7.19778618812561,
|
|
"epoch": 0.28777680226319385,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999012118081875,
|
|
"loss": 7.3654,
|
|
"mean_token_accuracy": 0.10196950063109397,
|
|
"num_tokens": 4934534.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 7.33796648979187,
|
|
"epoch": 0.28875231684713687,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004998991168334045,
|
|
"loss": 7.2736,
|
|
"mean_token_accuracy": 0.10711966082453728,
|
|
"num_tokens": 4950740.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 7.282023906707764,
|
|
"epoch": 0.2897278314310799,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998969998822814,
|
|
"loss": 7.357,
|
|
"mean_token_accuracy": 0.10374500527977944,
|
|
"num_tokens": 4966720.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 7.320036554336548,
|
|
"epoch": 0.2907033460150229,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004998948609550249,
|
|
"loss": 7.2468,
|
|
"mean_token_accuracy": 0.10450642704963684,
|
|
"num_tokens": 4982195.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 7.250419092178345,
|
|
"epoch": 0.29167886059896597,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998927000518442,
|
|
"loss": 7.3605,
|
|
"mean_token_accuracy": 0.10471020191907883,
|
|
"num_tokens": 4997487.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 7.259267807006836,
|
|
"epoch": 0.292654375182909,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004998905171729505,
|
|
"loss": 7.2455,
|
|
"mean_token_accuracy": 0.10793293043971061,
|
|
"num_tokens": 5012913.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 7.207444763183593,
|
|
"epoch": 0.293629889766852,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004998883123185568,
|
|
"loss": 7.2118,
|
|
"mean_token_accuracy": 0.1189083606004715,
|
|
"num_tokens": 5031462.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 7.273334741592407,
|
|
"epoch": 0.294605404350795,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004998860854888788,
|
|
"loss": 7.2006,
|
|
"mean_token_accuracy": 0.11655357554554939,
|
|
"num_tokens": 5047354.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 7.1826136112213135,
|
|
"epoch": 0.2955809189347381,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.0004998838366841341,
|
|
"loss": 7.2666,
|
|
"mean_token_accuracy": 0.11233135238289833,
|
|
"num_tokens": 5065268.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 7.27263765335083,
|
|
"epoch": 0.2965564335186811,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004998815659045423,
|
|
"loss": 7.2622,
|
|
"mean_token_accuracy": 0.10862576067447663,
|
|
"num_tokens": 5081066.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 7.27400689125061,
|
|
"epoch": 0.2975319481026241,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004998792731503254,
|
|
"loss": 7.2909,
|
|
"mean_token_accuracy": 0.11164338439702988,
|
|
"num_tokens": 5099440.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 7.246980094909668,
|
|
"epoch": 0.29850746268656714,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004998769584217074,
|
|
"loss": 7.2408,
|
|
"mean_token_accuracy": 0.11869253292679786,
|
|
"num_tokens": 5116573.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 7.087693595886231,
|
|
"epoch": 0.2994829772705102,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004998746217189145,
|
|
"loss": 7.0129,
|
|
"mean_token_accuracy": 0.12668982818722724,
|
|
"num_tokens": 5132920.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 7.322620582580567,
|
|
"epoch": 0.3004584918544532,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.000499872263042175,
|
|
"loss": 7.2676,
|
|
"mean_token_accuracy": 0.10794816985726356,
|
|
"num_tokens": 5150681.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 7.098180484771729,
|
|
"epoch": 0.30143400643839624,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004998698823917196,
|
|
"loss": 7.0585,
|
|
"mean_token_accuracy": 0.1271660767495632,
|
|
"num_tokens": 5167473.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 7.247739934921265,
|
|
"epoch": 0.3024095210223393,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004998674797677805,
|
|
"loss": 7.3303,
|
|
"mean_token_accuracy": 0.10471464842557907,
|
|
"num_tokens": 5183847.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 7.218716812133789,
|
|
"epoch": 0.3033850356062823,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004998650551705929,
|
|
"loss": 7.2864,
|
|
"mean_token_accuracy": 0.1065748505294323,
|
|
"num_tokens": 5200019.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 7.149478721618652,
|
|
"epoch": 0.30436055019022534,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004998626086003934,
|
|
"loss": 7.1586,
|
|
"mean_token_accuracy": 0.11314807906746864,
|
|
"num_tokens": 5217245.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 7.24084324836731,
|
|
"epoch": 0.30533606477416836,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004998601400574213,
|
|
"loss": 7.0673,
|
|
"mean_token_accuracy": 0.11648911908268929,
|
|
"num_tokens": 5234822.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 7.2059166431427,
|
|
"epoch": 0.30631157935811143,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998576495419177,
|
|
"loss": 7.1987,
|
|
"mean_token_accuracy": 0.110284673422575,
|
|
"num_tokens": 5251282.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 7.137545871734619,
|
|
"epoch": 0.30728709394205445,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.000499855137054126,
|
|
"loss": 7.1793,
|
|
"mean_token_accuracy": 0.10772244781255721,
|
|
"num_tokens": 5269630.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 7.247171068191529,
|
|
"epoch": 0.30826260852599746,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004998526025942917,
|
|
"loss": 7.2419,
|
|
"mean_token_accuracy": 0.10699235051870346,
|
|
"num_tokens": 5287106.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 7.254577684402466,
|
|
"epoch": 0.3092381231099405,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004998500461626625,
|
|
"loss": 7.2723,
|
|
"mean_token_accuracy": 0.10746567994356156,
|
|
"num_tokens": 5303387.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 7.319872236251831,
|
|
"epoch": 0.31021363769388355,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.000499847467759488,
|
|
"loss": 7.2542,
|
|
"mean_token_accuracy": 0.10725675225257873,
|
|
"num_tokens": 5320482.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 7.208133268356323,
|
|
"epoch": 0.31118915227782656,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004998448673850205,
|
|
"loss": 7.223,
|
|
"mean_token_accuracy": 0.11193624213337898,
|
|
"num_tokens": 5336420.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 7.094880104064941,
|
|
"epoch": 0.3121646668617696,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998422450395139,
|
|
"loss": 7.1597,
|
|
"mean_token_accuracy": 0.11134122982621193,
|
|
"num_tokens": 5353464.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 7.231945180892945,
|
|
"epoch": 0.3131401814457126,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004998396007232244,
|
|
"loss": 7.2267,
|
|
"mean_token_accuracy": 0.11414750963449478,
|
|
"num_tokens": 5372607.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 7.20907883644104,
|
|
"epoch": 0.31411569602965567,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004998369344364105,
|
|
"loss": 7.2419,
|
|
"mean_token_accuracy": 0.11458229944109917,
|
|
"num_tokens": 5390134.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 7.192635631561279,
|
|
"epoch": 0.3150912106135987,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004998342461793328,
|
|
"loss": 7.1426,
|
|
"mean_token_accuracy": 0.11570450440049171,
|
|
"num_tokens": 5407083.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 7.023532438278198,
|
|
"epoch": 0.3160667251975417,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004998315359522538,
|
|
"loss": 7.0462,
|
|
"mean_token_accuracy": 0.12723288238048552,
|
|
"num_tokens": 5424617.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 7.210883092880249,
|
|
"epoch": 0.3170422397814847,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004998288037554383,
|
|
"loss": 7.1847,
|
|
"mean_token_accuracy": 0.12012180760502815,
|
|
"num_tokens": 5440913.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 7.20393934249878,
|
|
"epoch": 0.3180177543654278,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004998260495891535,
|
|
"loss": 7.2107,
|
|
"mean_token_accuracy": 0.11585899069905281,
|
|
"num_tokens": 5457157.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 7.133607053756714,
|
|
"epoch": 0.3189932689493708,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.0004998232734536685,
|
|
"loss": 7.1437,
|
|
"mean_token_accuracy": 0.11597841158509255,
|
|
"num_tokens": 5474520.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 7.240679121017456,
|
|
"epoch": 0.3199687835333138,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998204753492544,
|
|
"loss": 7.2093,
|
|
"mean_token_accuracy": 0.11443925127387047,
|
|
"num_tokens": 5490599.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 7.190227603912353,
|
|
"epoch": 0.32094429811725683,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004998176552761848,
|
|
"loss": 7.2699,
|
|
"mean_token_accuracy": 0.10237837061285973,
|
|
"num_tokens": 5506714.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 7.265681362152099,
|
|
"epoch": 0.3219198127011999,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004998148132347352,
|
|
"loss": 7.2306,
|
|
"mean_token_accuracy": 0.10756946429610252,
|
|
"num_tokens": 5522894.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 7.134102153778076,
|
|
"epoch": 0.3228953272851429,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004998119492251832,
|
|
"loss": 7.0984,
|
|
"mean_token_accuracy": 0.11984493806958199,
|
|
"num_tokens": 5540054.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 7.262777042388916,
|
|
"epoch": 0.32387084186908593,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004998090632478088,
|
|
"loss": 7.2625,
|
|
"mean_token_accuracy": 0.10252039134502411,
|
|
"num_tokens": 5556189.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 7.238120269775391,
|
|
"epoch": 0.32484635645302895,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.000499806155302894,
|
|
"loss": 7.2793,
|
|
"mean_token_accuracy": 0.1049114279448986,
|
|
"num_tokens": 5572562.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 7.277428388595581,
|
|
"epoch": 0.325821871036972,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.000499803225390723,
|
|
"loss": 7.2699,
|
|
"mean_token_accuracy": 0.1055513508617878,
|
|
"num_tokens": 5588992.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 7.255199003219604,
|
|
"epoch": 0.32679738562091504,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004998002735115819,
|
|
"loss": 7.1826,
|
|
"mean_token_accuracy": 0.10926883295178413,
|
|
"num_tokens": 5604143.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 7.182808113098145,
|
|
"epoch": 0.32777290020485805,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004997972996657593,
|
|
"loss": 7.295,
|
|
"mean_token_accuracy": 0.10058706179261208,
|
|
"num_tokens": 5620887.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 7.215796041488647,
|
|
"epoch": 0.32874841478880107,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004997943038535459,
|
|
"loss": 7.2408,
|
|
"mean_token_accuracy": 0.10989224687218666,
|
|
"num_tokens": 5637156.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 7.2290528297424315,
|
|
"epoch": 0.32972392937274414,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.0004997912860752341,
|
|
"loss": 7.1963,
|
|
"mean_token_accuracy": 0.10859450697898865,
|
|
"num_tokens": 5654024.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 7.167445707321167,
|
|
"epoch": 0.33069944395668716,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004997882463311192,
|
|
"loss": 7.1421,
|
|
"mean_token_accuracy": 0.10873658806085587,
|
|
"num_tokens": 5671538.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 7.191862487792969,
|
|
"epoch": 0.33167495854063017,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004997851846214979,
|
|
"loss": 7.1813,
|
|
"mean_token_accuracy": 0.11439736038446427,
|
|
"num_tokens": 5688788.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 7.1439920425415036,
|
|
"epoch": 0.3326504731245732,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004997821009466695,
|
|
"loss": 7.1274,
|
|
"mean_token_accuracy": 0.11521929055452347,
|
|
"num_tokens": 5706066.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 7.128738975524902,
|
|
"epoch": 0.33362598770851626,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004997789953069354,
|
|
"loss": 7.1059,
|
|
"mean_token_accuracy": 0.11363393142819404,
|
|
"num_tokens": 5722100.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 7.202400350570679,
|
|
"epoch": 0.3346015022924593,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004997758677025989,
|
|
"loss": 7.2373,
|
|
"mean_token_accuracy": 0.10656889006495476,
|
|
"num_tokens": 5739068.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 7.182660055160523,
|
|
"epoch": 0.3355770168764023,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004997727181339658,
|
|
"loss": 7.2038,
|
|
"mean_token_accuracy": 0.10887709036469459,
|
|
"num_tokens": 5756147.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 7.202863168716431,
|
|
"epoch": 0.3365525314603453,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004997695466013438,
|
|
"loss": 7.1747,
|
|
"mean_token_accuracy": 0.10922196507453918,
|
|
"num_tokens": 5772157.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 7.202521228790284,
|
|
"epoch": 0.3375280460442884,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004997663531050427,
|
|
"loss": 7.1983,
|
|
"mean_token_accuracy": 0.11102297827601433,
|
|
"num_tokens": 5788128.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 7.124049186706543,
|
|
"epoch": 0.3385035606282314,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004997631376453749,
|
|
"loss": 7.1898,
|
|
"mean_token_accuracy": 0.11080607250332833,
|
|
"num_tokens": 5804793.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 7.14783296585083,
|
|
"epoch": 0.3394790752121744,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004997599002226541,
|
|
"loss": 7.1129,
|
|
"mean_token_accuracy": 0.11176546439528465,
|
|
"num_tokens": 5822409.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 7.101404285430908,
|
|
"epoch": 0.3404545897961175,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499756640837197,
|
|
"loss": 7.1547,
|
|
"mean_token_accuracy": 0.10845724120736122,
|
|
"num_tokens": 5839023.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 7.241454839706421,
|
|
"epoch": 0.3414301043800605,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000499753359489322,
|
|
"loss": 7.169,
|
|
"mean_token_accuracy": 0.10654053464531898,
|
|
"num_tokens": 5855804.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 7.1083615779876705,
|
|
"epoch": 0.3424056189640035,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004997500561793498,
|
|
"loss": 7.1759,
|
|
"mean_token_accuracy": 0.11318699792027473,
|
|
"num_tokens": 5872372.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 7.232053995132446,
|
|
"epoch": 0.3433811335479465,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004997467309076031,
|
|
"loss": 7.2216,
|
|
"mean_token_accuracy": 0.10516873672604561,
|
|
"num_tokens": 5888666.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 7.054588890075683,
|
|
"epoch": 0.3443566481318896,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004997433836744069,
|
|
"loss": 7.1628,
|
|
"mean_token_accuracy": 0.11004716753959656,
|
|
"num_tokens": 5905577.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 7.211126518249512,
|
|
"epoch": 0.3453321627158326,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004997400144800882,
|
|
"loss": 7.1273,
|
|
"mean_token_accuracy": 0.11347045078873634,
|
|
"num_tokens": 5922570.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 7.046509408950806,
|
|
"epoch": 0.34630767729977563,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004997366233249762,
|
|
"loss": 7.0896,
|
|
"mean_token_accuracy": 0.12237504422664643,
|
|
"num_tokens": 5938995.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 7.139289665222168,
|
|
"epoch": 0.34728319188371864,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004997332102094024,
|
|
"loss": 7.1051,
|
|
"mean_token_accuracy": 0.11859508603811264,
|
|
"num_tokens": 5954869.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 7.272542238235474,
|
|
"epoch": 0.3482587064676617,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004997297751337004,
|
|
"loss": 7.2014,
|
|
"mean_token_accuracy": 0.11317256689071656,
|
|
"num_tokens": 5972750.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 7.0967755794525145,
|
|
"epoch": 0.34923422105160473,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004997263180982055,
|
|
"loss": 7.1296,
|
|
"mean_token_accuracy": 0.1137120395898819,
|
|
"num_tokens": 5989004.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 7.098430013656616,
|
|
"epoch": 0.35020973563554775,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004997228391032559,
|
|
"loss": 7.1462,
|
|
"mean_token_accuracy": 0.11115683764219284,
|
|
"num_tokens": 6004749.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 7.090719604492188,
|
|
"epoch": 0.35118525021949076,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004997193381491913,
|
|
"loss": 7.019,
|
|
"mean_token_accuracy": 0.11676162034273148,
|
|
"num_tokens": 6022235.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 7.0829535007476805,
|
|
"epoch": 0.35216076480343383,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000499715815236354,
|
|
"loss": 7.1947,
|
|
"mean_token_accuracy": 0.10693453401327133,
|
|
"num_tokens": 6039194.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 7.189563322067261,
|
|
"epoch": 0.35313627938737685,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.000499712270365088,
|
|
"loss": 7.0593,
|
|
"mean_token_accuracy": 0.10776279419660569,
|
|
"num_tokens": 6055376.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 7.125262308120727,
|
|
"epoch": 0.35411179397131987,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004997087035357398,
|
|
"loss": 7.1277,
|
|
"mean_token_accuracy": 0.11357001885771752,
|
|
"num_tokens": 6071105.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 7.074201965332032,
|
|
"epoch": 0.3550873085552629,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997051147486582,
|
|
"loss": 7.0519,
|
|
"mean_token_accuracy": 0.11605791896581649,
|
|
"num_tokens": 6087964.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 7.086669158935547,
|
|
"epoch": 0.35606282313920595,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004997015040041935,
|
|
"loss": 7.1199,
|
|
"mean_token_accuracy": 0.10704236179590225,
|
|
"num_tokens": 6105245.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 7.13190975189209,
|
|
"epoch": 0.35703833772314897,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004996978713026986,
|
|
"loss": 7.0724,
|
|
"mean_token_accuracy": 0.12007546350359917,
|
|
"num_tokens": 6121736.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 7.104649305343628,
|
|
"epoch": 0.358013852307092,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004996942166445287,
|
|
"loss": 7.1355,
|
|
"mean_token_accuracy": 0.11229356825351715,
|
|
"num_tokens": 6137751.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 7.145856428146362,
|
|
"epoch": 0.358989366891035,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004996905400300407,
|
|
"loss": 7.1839,
|
|
"mean_token_accuracy": 0.1106605127453804,
|
|
"num_tokens": 6154655.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 7.193540096282959,
|
|
"epoch": 0.35996488147497807,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000499686841459594,
|
|
"loss": 7.1746,
|
|
"mean_token_accuracy": 0.10867514237761497,
|
|
"num_tokens": 6172230.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 7.10019702911377,
|
|
"epoch": 0.3609403960589211,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004996831209335497,
|
|
"loss": 7.1168,
|
|
"mean_token_accuracy": 0.10731762573122978,
|
|
"num_tokens": 6188520.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 7.129278135299683,
|
|
"epoch": 0.3619159106428641,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004996793784522719,
|
|
"loss": 7.1545,
|
|
"mean_token_accuracy": 0.10917501226067543,
|
|
"num_tokens": 6205555.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 7.180557060241699,
|
|
"epoch": 0.3628914252268071,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004996756140161259,
|
|
"loss": 7.1412,
|
|
"mean_token_accuracy": 0.11165231317281724,
|
|
"num_tokens": 6223548.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 7.114638328552246,
|
|
"epoch": 0.3638669398107502,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004996718276254797,
|
|
"loss": 7.151,
|
|
"mean_token_accuracy": 0.10733274817466736,
|
|
"num_tokens": 6239266.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 7.132656908035278,
|
|
"epoch": 0.3648424543946932,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004996680192807032,
|
|
"loss": 7.115,
|
|
"mean_token_accuracy": 0.11217067912220954,
|
|
"num_tokens": 6255020.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 7.115752077102661,
|
|
"epoch": 0.3658179689786362,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004996641889821686,
|
|
"loss": 7.0536,
|
|
"mean_token_accuracy": 0.10760100483894348,
|
|
"num_tokens": 6272774.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 7.088830280303955,
|
|
"epoch": 0.36679348356257924,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004996603367302502,
|
|
"loss": 7.0727,
|
|
"mean_token_accuracy": 0.11251697391271591,
|
|
"num_tokens": 6290478.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 7.100843334197998,
|
|
"epoch": 0.3677689981465223,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004996564625253244,
|
|
"loss": 7.1506,
|
|
"mean_token_accuracy": 0.11167759746313095,
|
|
"num_tokens": 6308003.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 7.098121881484985,
|
|
"epoch": 0.3687445127304653,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004996525663677697,
|
|
"loss": 7.1054,
|
|
"mean_token_accuracy": 0.10613081008195877,
|
|
"num_tokens": 6325748.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 7.079687166213989,
|
|
"epoch": 0.36972002731440834,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000499648648257967,
|
|
"loss": 7.0579,
|
|
"mean_token_accuracy": 0.12034444063901902,
|
|
"num_tokens": 6344031.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 7.065695476531983,
|
|
"epoch": 0.37069554189835136,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.000499644708196299,
|
|
"loss": 7.1106,
|
|
"mean_token_accuracy": 0.11427498012781143,
|
|
"num_tokens": 6359821.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 7.036489105224609,
|
|
"epoch": 0.3716710564822944,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004996407461831507,
|
|
"loss": 6.9544,
|
|
"mean_token_accuracy": 0.12395858988165856,
|
|
"num_tokens": 6376464.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 7.124951982498169,
|
|
"epoch": 0.37264657106623744,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004996367622189094,
|
|
"loss": 7.1286,
|
|
"mean_token_accuracy": 0.109093027561903,
|
|
"num_tokens": 6392415.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 7.078305053710937,
|
|
"epoch": 0.37362208565018046,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004996327563039643,
|
|
"loss": 7.1238,
|
|
"mean_token_accuracy": 0.1082805871963501,
|
|
"num_tokens": 6409151.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 7.166975975036621,
|
|
"epoch": 0.3745976002341235,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004996287284387068,
|
|
"loss": 7.0814,
|
|
"mean_token_accuracy": 0.11464927569031716,
|
|
"num_tokens": 6426997.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 7.088303327560425,
|
|
"epoch": 0.37557311481806654,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004996246786235306,
|
|
"loss": 7.0782,
|
|
"mean_token_accuracy": 0.11261907815933228,
|
|
"num_tokens": 6442871.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 7.04116382598877,
|
|
"epoch": 0.37654862940200956,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004996206068588314,
|
|
"loss": 7.0759,
|
|
"mean_token_accuracy": 0.11092812642455101,
|
|
"num_tokens": 6459677.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 7.167269468307495,
|
|
"epoch": 0.3775241439859526,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004996165131450071,
|
|
"loss": 7.2127,
|
|
"mean_token_accuracy": 0.10652901008725166,
|
|
"num_tokens": 6477239.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 7.098695421218872,
|
|
"epoch": 0.37849965856989565,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004996123974824576,
|
|
"loss": 7.0695,
|
|
"mean_token_accuracy": 0.11821612566709519,
|
|
"num_tokens": 6493277.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 7.047782516479492,
|
|
"epoch": 0.37947517315383866,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004996082598715852,
|
|
"loss": 7.0966,
|
|
"mean_token_accuracy": 0.11363401412963867,
|
|
"num_tokens": 6509204.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 7.014270877838134,
|
|
"epoch": 0.3804506877377817,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000499604100312794,
|
|
"loss": 6.9519,
|
|
"mean_token_accuracy": 0.12616565227508544,
|
|
"num_tokens": 6525486.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 7.046218776702881,
|
|
"epoch": 0.3814262023217247,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004995999188064908,
|
|
"loss": 7.158,
|
|
"mean_token_accuracy": 0.10741189196705818,
|
|
"num_tokens": 6542227.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 7.1583123207092285,
|
|
"epoch": 0.38240171690566777,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000499595715353084,
|
|
"loss": 7.2279,
|
|
"mean_token_accuracy": 0.10246274694800377,
|
|
"num_tokens": 6558951.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 7.150441884994507,
|
|
"epoch": 0.3833772314896108,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004995914899529844,
|
|
"loss": 7.1286,
|
|
"mean_token_accuracy": 0.11037195920944214,
|
|
"num_tokens": 6574696.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 7.180084657669068,
|
|
"epoch": 0.3843527460735538,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004995872426066048,
|
|
"loss": 7.1448,
|
|
"mean_token_accuracy": 0.11020474806427956,
|
|
"num_tokens": 6591628.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 7.103500747680664,
|
|
"epoch": 0.3853282606574968,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004995829733143602,
|
|
"loss": 7.0431,
|
|
"mean_token_accuracy": 0.11289738193154335,
|
|
"num_tokens": 6608107.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 7.082343816757202,
|
|
"epoch": 0.3863037752414399,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000499578682076668,
|
|
"loss": 7.1855,
|
|
"mean_token_accuracy": 0.11477380469441414,
|
|
"num_tokens": 6626699.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 7.221960496902466,
|
|
"epoch": 0.3872792898253829,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004995743688939474,
|
|
"loss": 7.1891,
|
|
"mean_token_accuracy": 0.1018472857773304,
|
|
"num_tokens": 6644540.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 7.113204669952393,
|
|
"epoch": 0.3882548044093259,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004995700337666199,
|
|
"loss": 7.1306,
|
|
"mean_token_accuracy": 0.10720818117260933,
|
|
"num_tokens": 6660653.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 7.155580043792725,
|
|
"epoch": 0.38923031899326893,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.000499565676695109,
|
|
"loss": 7.1317,
|
|
"mean_token_accuracy": 0.10808075144886971,
|
|
"num_tokens": 6677553.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 7.119460582733154,
|
|
"epoch": 0.390205833577212,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004995612976798406,
|
|
"loss": 7.1175,
|
|
"mean_token_accuracy": 0.1091853991150856,
|
|
"num_tokens": 6695274.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 7.064525413513183,
|
|
"epoch": 0.391181348161155,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004995568967212425,
|
|
"loss": 7.0522,
|
|
"mean_token_accuracy": 0.11336143016815185,
|
|
"num_tokens": 6711166.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 7.021340322494507,
|
|
"epoch": 0.39215686274509803,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004995524738197448,
|
|
"loss": 7.028,
|
|
"mean_token_accuracy": 0.11226390227675438,
|
|
"num_tokens": 6728827.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 6.996756649017334,
|
|
"epoch": 0.39313237732904105,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004995480289757796,
|
|
"loss": 7.0064,
|
|
"mean_token_accuracy": 0.12143127471208573,
|
|
"num_tokens": 6745901.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 7.007443380355835,
|
|
"epoch": 0.3941078919129841,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004995435621897815,
|
|
"loss": 6.985,
|
|
"mean_token_accuracy": 0.11859407424926757,
|
|
"num_tokens": 6762176.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 7.087689161300659,
|
|
"epoch": 0.39508340649692714,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004995390734621867,
|
|
"loss": 7.139,
|
|
"mean_token_accuracy": 0.10878413170576096,
|
|
"num_tokens": 6779322.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 7.182950258255005,
|
|
"epoch": 0.39605892108087015,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004995345627934338,
|
|
"loss": 7.0747,
|
|
"mean_token_accuracy": 0.1140649899840355,
|
|
"num_tokens": 6794293.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 6.839075326919556,
|
|
"epoch": 0.39703443566481317,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004995300301839637,
|
|
"loss": 6.9084,
|
|
"mean_token_accuracy": 0.1312996357679367,
|
|
"num_tokens": 6812880.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 7.124480581283569,
|
|
"epoch": 0.39800995024875624,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004995254756342194,
|
|
"loss": 7.1075,
|
|
"mean_token_accuracy": 0.10809694975614548,
|
|
"num_tokens": 6829230.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 7.089977121353149,
|
|
"epoch": 0.39898546483269925,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004995208991446458,
|
|
"loss": 7.102,
|
|
"mean_token_accuracy": 0.11135954707860947,
|
|
"num_tokens": 6846787.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 7.006796836853027,
|
|
"epoch": 0.39996097941664227,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004995163007156902,
|
|
"loss": 6.9749,
|
|
"mean_token_accuracy": 0.11075088903307914,
|
|
"num_tokens": 6862990.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 7.126283025741577,
|
|
"epoch": 0.4009364940005853,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004995116803478018,
|
|
"loss": 7.1272,
|
|
"mean_token_accuracy": 0.1081840455532074,
|
|
"num_tokens": 6879170.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 7.005995607376098,
|
|
"epoch": 0.40191200858452836,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004995070380414321,
|
|
"loss": 7.1092,
|
|
"mean_token_accuracy": 0.10969639047980309,
|
|
"num_tokens": 6895635.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 7.09612774848938,
|
|
"epoch": 0.4028875231684714,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000499502373797035,
|
|
"loss": 7.0205,
|
|
"mean_token_accuracy": 0.11540707424283028,
|
|
"num_tokens": 6912836.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 7.0344482421875,
|
|
"epoch": 0.4038630377524144,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000499497687615066,
|
|
"loss": 7.0476,
|
|
"mean_token_accuracy": 0.11897711828351021,
|
|
"num_tokens": 6929507.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 7.0960619926452635,
|
|
"epoch": 0.4048385523363574,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.000499492979495983,
|
|
"loss": 7.0645,
|
|
"mean_token_accuracy": 0.10878148227930069,
|
|
"num_tokens": 6946527.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 7.08494553565979,
|
|
"epoch": 0.4058140669203005,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004994882494402462,
|
|
"loss": 7.0716,
|
|
"mean_token_accuracy": 0.11425348073244095,
|
|
"num_tokens": 6962582.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 7.053049182891845,
|
|
"epoch": 0.4067895815042435,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004994834974483178,
|
|
"loss": 7.0636,
|
|
"mean_token_accuracy": 0.11429096385836601,
|
|
"num_tokens": 6979389.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 6.987600946426392,
|
|
"epoch": 0.4077650960881865,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004994787235206621,
|
|
"loss": 7.0396,
|
|
"mean_token_accuracy": 0.11151788830757141,
|
|
"num_tokens": 6996637.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 7.187871599197388,
|
|
"epoch": 0.4087406106721295,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004994739276577456,
|
|
"loss": 7.1287,
|
|
"mean_token_accuracy": 0.10643508210778237,
|
|
"num_tokens": 7013013.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 6.9453386783599855,
|
|
"epoch": 0.4097161252560726,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004994691098600369,
|
|
"loss": 7.0909,
|
|
"mean_token_accuracy": 0.11552847772836686,
|
|
"num_tokens": 7031476.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 7.183104228973389,
|
|
"epoch": 0.4106916398400156,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004994642701280068,
|
|
"loss": 7.0001,
|
|
"mean_token_accuracy": 0.11294645816087723,
|
|
"num_tokens": 7047424.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 6.992200660705566,
|
|
"epoch": 0.4116671544239586,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004994594084621282,
|
|
"loss": 7.0871,
|
|
"mean_token_accuracy": 0.10682062655687333,
|
|
"num_tokens": 7063793.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 7.219247531890869,
|
|
"epoch": 0.41264266900790164,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004994545248628762,
|
|
"loss": 7.1364,
|
|
"mean_token_accuracy": 0.10866177827119827,
|
|
"num_tokens": 7079026.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 7.020672225952149,
|
|
"epoch": 0.4136181835918447,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.000499449619330728,
|
|
"loss": 7.0572,
|
|
"mean_token_accuracy": 0.1168307289481163,
|
|
"num_tokens": 7097524.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 7.141960477828979,
|
|
"epoch": 0.41459369817578773,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.000499444691866163,
|
|
"loss": 7.1313,
|
|
"mean_token_accuracy": 0.10980155616998673,
|
|
"num_tokens": 7115514.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 7.095918035507202,
|
|
"epoch": 0.41556921275973074,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004994397424696625,
|
|
"loss": 7.0673,
|
|
"mean_token_accuracy": 0.11292248368263244,
|
|
"num_tokens": 7132589.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 7.082249641418457,
|
|
"epoch": 0.4165447273436738,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004994347711417105,
|
|
"loss": 7.082,
|
|
"mean_token_accuracy": 0.10995210707187653,
|
|
"num_tokens": 7149416.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 6.970026350021362,
|
|
"epoch": 0.41752024192761683,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004994297778827924,
|
|
"loss": 7.018,
|
|
"mean_token_accuracy": 0.11910998299717904,
|
|
"num_tokens": 7165763.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 7.037493944168091,
|
|
"epoch": 0.41849575651155985,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004994247626933964,
|
|
"loss": 7.0108,
|
|
"mean_token_accuracy": 0.12116987556219101,
|
|
"num_tokens": 7183131.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 6.9932863235473635,
|
|
"epoch": 0.41947127109550286,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004994197255740124,
|
|
"loss": 7.0341,
|
|
"mean_token_accuracy": 0.11638646721839904,
|
|
"num_tokens": 7200467.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 7.079003763198853,
|
|
"epoch": 0.42044678567944593,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004994146665251327,
|
|
"loss": 7.0269,
|
|
"mean_token_accuracy": 0.11671786457300186,
|
|
"num_tokens": 7217311.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 6.985736274719239,
|
|
"epoch": 0.42142230026338895,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004994095855472516,
|
|
"loss": 7.0325,
|
|
"mean_token_accuracy": 0.11662963330745697,
|
|
"num_tokens": 7235244.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 7.125861310958863,
|
|
"epoch": 0.42239781484733196,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004994044826408656,
|
|
"loss": 7.0606,
|
|
"mean_token_accuracy": 0.10941600650548935,
|
|
"num_tokens": 7252235.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 7.026695823669433,
|
|
"epoch": 0.423373329431275,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004993993578064733,
|
|
"loss": 7.0796,
|
|
"mean_token_accuracy": 0.10855171978473663,
|
|
"num_tokens": 7269367.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 7.164697599411011,
|
|
"epoch": 0.42434884401521805,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004993942110445756,
|
|
"loss": 7.0575,
|
|
"mean_token_accuracy": 0.10973318442702293,
|
|
"num_tokens": 7287198.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 7.023011207580566,
|
|
"epoch": 0.42532435859916107,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004993890423556753,
|
|
"loss": 6.9969,
|
|
"mean_token_accuracy": 0.11209728047251702,
|
|
"num_tokens": 7302356.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 7.013686943054199,
|
|
"epoch": 0.4262998731831041,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004993838517402775,
|
|
"loss": 6.992,
|
|
"mean_token_accuracy": 0.11840955764055253,
|
|
"num_tokens": 7318530.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 7.065437269210816,
|
|
"epoch": 0.4272753877670471,
|
|
"grad_norm": 0.7421875,
|
|
"learning_rate": 0.0004993786391988894,
|
|
"loss": 6.9724,
|
|
"mean_token_accuracy": 0.11313622668385506,
|
|
"num_tokens": 7335195.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 6.926114702224732,
|
|
"epoch": 0.42825090235099017,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004993734047320206,
|
|
"loss": 6.9729,
|
|
"mean_token_accuracy": 0.11200029700994492,
|
|
"num_tokens": 7352233.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 7.071037006378174,
|
|
"epoch": 0.4292264169349332,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004993681483401821,
|
|
"loss": 7.027,
|
|
"mean_token_accuracy": 0.11576457694172859,
|
|
"num_tokens": 7368569.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 7.000790357589722,
|
|
"epoch": 0.4302019315188762,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004993628700238879,
|
|
"loss": 7.0716,
|
|
"mean_token_accuracy": 0.11266482919454575,
|
|
"num_tokens": 7384669.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 7.18484787940979,
|
|
"epoch": 0.4311774461028192,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004993575697836537,
|
|
"loss": 7.0834,
|
|
"mean_token_accuracy": 0.10938332602381706,
|
|
"num_tokens": 7401833.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 6.963419961929321,
|
|
"epoch": 0.4321529606867623,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004993522476199975,
|
|
"loss": 6.978,
|
|
"mean_token_accuracy": 0.1122715525329113,
|
|
"num_tokens": 7418663.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 7.067373323440552,
|
|
"epoch": 0.4331284752707053,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004993469035334392,
|
|
"loss": 6.9573,
|
|
"mean_token_accuracy": 0.12277843132615089,
|
|
"num_tokens": 7434701.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 6.984041833877564,
|
|
"epoch": 0.4341039898546483,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.000499341537524501,
|
|
"loss": 7.0441,
|
|
"mean_token_accuracy": 0.10746957212686539,
|
|
"num_tokens": 7450154.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 6.906111478805542,
|
|
"epoch": 0.43507950443859134,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004993361495937074,
|
|
"loss": 6.8559,
|
|
"mean_token_accuracy": 0.13145155981183052,
|
|
"num_tokens": 7468110.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 7.01196985244751,
|
|
"epoch": 0.4360550190225344,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004993307397415848,
|
|
"loss": 6.9797,
|
|
"mean_token_accuracy": 0.11334640309214591,
|
|
"num_tokens": 7482962.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 7.0998986721038815,
|
|
"epoch": 0.4370305336064774,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0004993253079686619,
|
|
"loss": 7.1178,
|
|
"mean_token_accuracy": 0.10759365484118462,
|
|
"num_tokens": 7499116.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 7.059480142593384,
|
|
"epoch": 0.43800604819042044,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004993198542754692,
|
|
"loss": 7.0707,
|
|
"mean_token_accuracy": 0.11301630288362503,
|
|
"num_tokens": 7515765.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 7.048842477798462,
|
|
"epoch": 0.43898156277436345,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004993143786625401,
|
|
"loss": 7.0522,
|
|
"mean_token_accuracy": 0.11276320442557335,
|
|
"num_tokens": 7532074.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 6.91264853477478,
|
|
"epoch": 0.4399570773583065,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004993088811304092,
|
|
"loss": 6.8962,
|
|
"mean_token_accuracy": 0.12252458482980728,
|
|
"num_tokens": 7547704.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 7.015114450454712,
|
|
"epoch": 0.44093259194224954,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004993033616796139,
|
|
"loss": 7.0158,
|
|
"mean_token_accuracy": 0.11404076218605042,
|
|
"num_tokens": 7563317.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 6.961794090270996,
|
|
"epoch": 0.44190810652619256,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004992978203106936,
|
|
"loss": 7.0042,
|
|
"mean_token_accuracy": 0.11175615265965462,
|
|
"num_tokens": 7580770.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 7.016242122650146,
|
|
"epoch": 0.4428836211101356,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004992922570241896,
|
|
"loss": 6.9809,
|
|
"mean_token_accuracy": 0.11705166772007942,
|
|
"num_tokens": 7598181.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 7.028905820846558,
|
|
"epoch": 0.44385913569407864,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004992866718206457,
|
|
"loss": 6.9722,
|
|
"mean_token_accuracy": 0.11778600364923478,
|
|
"num_tokens": 7613739.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 7.025203371047974,
|
|
"epoch": 0.44483465027802166,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004992810647006077,
|
|
"loss": 7.0563,
|
|
"mean_token_accuracy": 0.11031661182641983,
|
|
"num_tokens": 7629297.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 7.087608432769775,
|
|
"epoch": 0.4458101648619647,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004992754356646234,
|
|
"loss": 7.049,
|
|
"mean_token_accuracy": 0.110834738612175,
|
|
"num_tokens": 7645273.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 7.067881631851196,
|
|
"epoch": 0.4467856794459077,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004992697847132427,
|
|
"loss": 7.0014,
|
|
"mean_token_accuracy": 0.10971406400203705,
|
|
"num_tokens": 7661296.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 6.86855297088623,
|
|
"epoch": 0.44776119402985076,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.000499264111847018,
|
|
"loss": 7.0023,
|
|
"mean_token_accuracy": 0.11386808529496192,
|
|
"num_tokens": 7678658.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 7.125934982299805,
|
|
"epoch": 0.4487367086137938,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004992584170665037,
|
|
"loss": 7.0306,
|
|
"mean_token_accuracy": 0.1094054788351059,
|
|
"num_tokens": 7693678.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 6.985922002792359,
|
|
"epoch": 0.4497122231977368,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.000499252700372256,
|
|
"loss": 7.0232,
|
|
"mean_token_accuracy": 0.11486716344952583,
|
|
"num_tokens": 7709526.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 7.020515871047974,
|
|
"epoch": 0.4506877377816798,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004992469617648337,
|
|
"loss": 6.9265,
|
|
"mean_token_accuracy": 0.11158730164170265,
|
|
"num_tokens": 7725055.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 6.868546867370606,
|
|
"epoch": 0.4516632523656229,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004992412012447976,
|
|
"loss": 6.8277,
|
|
"mean_token_accuracy": 0.13100250884890557,
|
|
"num_tokens": 7742047.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 7.032267808914185,
|
|
"epoch": 0.4526387669495659,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004992354188127105,
|
|
"loss": 7.0045,
|
|
"mean_token_accuracy": 0.11193139106035233,
|
|
"num_tokens": 7758283.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 6.975220394134522,
|
|
"epoch": 0.4536142815335089,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004992296144691375,
|
|
"loss": 6.9442,
|
|
"mean_token_accuracy": 0.1183014951646328,
|
|
"num_tokens": 7774660.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 6.93505334854126,
|
|
"epoch": 0.454589796117452,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004992237882146456,
|
|
"loss": 6.9561,
|
|
"mean_token_accuracy": 0.11839842200279235,
|
|
"num_tokens": 7792147.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 6.9103350162506105,
|
|
"epoch": 0.455565310701395,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004992179400498044,
|
|
"loss": 6.8987,
|
|
"mean_token_accuracy": 0.1161189466714859,
|
|
"num_tokens": 7809021.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 7.007769536972046,
|
|
"epoch": 0.456540825285338,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004992120699751852,
|
|
"loss": 6.9624,
|
|
"mean_token_accuracy": 0.11379743441939354,
|
|
"num_tokens": 7825074.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 6.837625646591187,
|
|
"epoch": 0.45751633986928103,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004992061779913616,
|
|
"loss": 6.8918,
|
|
"mean_token_accuracy": 0.12118960246443748,
|
|
"num_tokens": 7843413.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 7.060509872436524,
|
|
"epoch": 0.4584918544532241,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004992002640989094,
|
|
"loss": 6.9842,
|
|
"mean_token_accuracy": 0.10777736902236938,
|
|
"num_tokens": 7859874.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 6.888943815231324,
|
|
"epoch": 0.4594673690371671,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004991943282984065,
|
|
"loss": 6.9176,
|
|
"mean_token_accuracy": 0.11951580569148064,
|
|
"num_tokens": 7877302.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 7.015088510513306,
|
|
"epoch": 0.46044288362111013,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004991883705904328,
|
|
"loss": 7.0317,
|
|
"mean_token_accuracy": 0.10920384526252747,
|
|
"num_tokens": 7893207.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 6.905005931854248,
|
|
"epoch": 0.46141839820505315,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004991823909755705,
|
|
"loss": 6.8904,
|
|
"mean_token_accuracy": 0.12214830294251441,
|
|
"num_tokens": 7910239.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 7.027743482589722,
|
|
"epoch": 0.4623939127889962,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004991763894544041,
|
|
"loss": 7.0056,
|
|
"mean_token_accuracy": 0.11172575429081917,
|
|
"num_tokens": 7928030.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 6.973042011260986,
|
|
"epoch": 0.46336942737293924,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004991703660275199,
|
|
"loss": 6.9695,
|
|
"mean_token_accuracy": 0.11384573951363564,
|
|
"num_tokens": 7943653.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 7.05312213897705,
|
|
"epoch": 0.46434494195688225,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004991643206955064,
|
|
"loss": 7.0329,
|
|
"mean_token_accuracy": 0.11237467974424362,
|
|
"num_tokens": 7960564.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 7.014554071426391,
|
|
"epoch": 0.46532045654082527,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004991582534589544,
|
|
"loss": 6.9782,
|
|
"mean_token_accuracy": 0.11644384115934373,
|
|
"num_tokens": 7978045.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 7.0076799392700195,
|
|
"epoch": 0.46629597112476834,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004991521643184567,
|
|
"loss": 7.0233,
|
|
"mean_token_accuracy": 0.11004308089613915,
|
|
"num_tokens": 7995074.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 7.057988786697388,
|
|
"epoch": 0.46727148570871135,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004991460532746087,
|
|
"loss": 7.0417,
|
|
"mean_token_accuracy": 0.10691535025835038,
|
|
"num_tokens": 8011800.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 7.042518377304077,
|
|
"epoch": 0.46824700029265437,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.000499139920328007,
|
|
"loss": 7.0164,
|
|
"mean_token_accuracy": 0.11115067452192307,
|
|
"num_tokens": 8028090.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 6.991872024536133,
|
|
"epoch": 0.4692225148765974,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004991337654792512,
|
|
"loss": 6.9636,
|
|
"mean_token_accuracy": 0.1162964753806591,
|
|
"num_tokens": 8044140.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 6.921262788772583,
|
|
"epoch": 0.47019802946054046,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004991275887289427,
|
|
"loss": 6.9011,
|
|
"mean_token_accuracy": 0.11688902750611305,
|
|
"num_tokens": 8060030.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 6.954582357406617,
|
|
"epoch": 0.47117354404448347,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004991213900776849,
|
|
"loss": 6.9477,
|
|
"mean_token_accuracy": 0.11353798434138299,
|
|
"num_tokens": 8075445.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 7.039027690887451,
|
|
"epoch": 0.4721490586284265,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004991151695260838,
|
|
"loss": 6.9547,
|
|
"mean_token_accuracy": 0.11307838335633277,
|
|
"num_tokens": 8093250.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 6.871022033691406,
|
|
"epoch": 0.4731245732123695,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000499108927074747,
|
|
"loss": 6.8995,
|
|
"mean_token_accuracy": 0.1290725477039814,
|
|
"num_tokens": 8109615.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 6.977431726455689,
|
|
"epoch": 0.4741000877963126,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004991026627242846,
|
|
"loss": 7.007,
|
|
"mean_token_accuracy": 0.1094487626105547,
|
|
"num_tokens": 8126591.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 6.984453248977661,
|
|
"epoch": 0.4750756023802556,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004990963764753088,
|
|
"loss": 6.9201,
|
|
"mean_token_accuracy": 0.11406318247318267,
|
|
"num_tokens": 8141360.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 6.96773853302002,
|
|
"epoch": 0.4760511169641986,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004990900683284337,
|
|
"loss": 7.0228,
|
|
"mean_token_accuracy": 0.11445973664522172,
|
|
"num_tokens": 8159688.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 6.959125900268555,
|
|
"epoch": 0.4770266315481416,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004990837382842758,
|
|
"loss": 6.9831,
|
|
"mean_token_accuracy": 0.11357531175017357,
|
|
"num_tokens": 8176887.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 6.870701313018799,
|
|
"epoch": 0.4780021461320847,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.0004990773863434537,
|
|
"loss": 6.8034,
|
|
"mean_token_accuracy": 0.12336878180503845,
|
|
"num_tokens": 8193372.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 6.963567733764648,
|
|
"epoch": 0.4789776607160277,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004990710125065879,
|
|
"loss": 7.0044,
|
|
"mean_token_accuracy": 0.1109432339668274,
|
|
"num_tokens": 8209713.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 7.021219301223755,
|
|
"epoch": 0.4799531752999707,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004990646167743015,
|
|
"loss": 7.0058,
|
|
"mean_token_accuracy": 0.11337054893374443,
|
|
"num_tokens": 8226359.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 6.926394844055176,
|
|
"epoch": 0.48092868988391374,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004990581991472193,
|
|
"loss": 6.9675,
|
|
"mean_token_accuracy": 0.11650057286024093,
|
|
"num_tokens": 8243182.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 6.998376560211182,
|
|
"epoch": 0.4819042044678568,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004990517596259684,
|
|
"loss": 6.9843,
|
|
"mean_token_accuracy": 0.11314982771873475,
|
|
"num_tokens": 8259185.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 7.04877028465271,
|
|
"epoch": 0.4828797190517998,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004990452982111781,
|
|
"loss": 7.0446,
|
|
"mean_token_accuracy": 0.10870871022343635,
|
|
"num_tokens": 8275941.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 6.96405930519104,
|
|
"epoch": 0.48385523363574284,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004990388149034797,
|
|
"loss": 6.9846,
|
|
"mean_token_accuracy": 0.11402082219719886,
|
|
"num_tokens": 8292535.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 6.987648439407349,
|
|
"epoch": 0.48483074821968586,
|
|
"grad_norm": 0.75390625,
|
|
"learning_rate": 0.0004990323097035069,
|
|
"loss": 6.9301,
|
|
"mean_token_accuracy": 0.11991023421287536,
|
|
"num_tokens": 8310562.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 6.940241813659668,
|
|
"epoch": 0.48580626280362893,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004990257826118952,
|
|
"loss": 6.9636,
|
|
"mean_token_accuracy": 0.10830035284161568,
|
|
"num_tokens": 8327241.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 6.913412094116211,
|
|
"epoch": 0.48678177738757195,
|
|
"grad_norm": 0.75390625,
|
|
"learning_rate": 0.0004990192336292824,
|
|
"loss": 6.9088,
|
|
"mean_token_accuracy": 0.11822234392166138,
|
|
"num_tokens": 8343516.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 6.8137157440185545,
|
|
"epoch": 0.48775729197151496,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004990126627563087,
|
|
"loss": 6.7738,
|
|
"mean_token_accuracy": 0.12430693060159684,
|
|
"num_tokens": 8361809.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 6.875748491287231,
|
|
"epoch": 0.488732806555458,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004990060699936159,
|
|
"loss": 6.8307,
|
|
"mean_token_accuracy": 0.12605192884802818,
|
|
"num_tokens": 8378632.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 6.968320083618164,
|
|
"epoch": 0.48970832113940105,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004989994553418483,
|
|
"loss": 6.9914,
|
|
"mean_token_accuracy": 0.10726674050092697,
|
|
"num_tokens": 8396201.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 6.940235614776611,
|
|
"epoch": 0.49068383572334406,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004989928188016522,
|
|
"loss": 6.8782,
|
|
"mean_token_accuracy": 0.11905882507562637,
|
|
"num_tokens": 8412851.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 6.7344177722930905,
|
|
"epoch": 0.4916593503072871,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004989861603736762,
|
|
"loss": 6.7232,
|
|
"mean_token_accuracy": 0.12667507529258729,
|
|
"num_tokens": 8430026.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 6.928332138061523,
|
|
"epoch": 0.49263486489123015,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004989794800585711,
|
|
"loss": 6.9486,
|
|
"mean_token_accuracy": 0.11339501067996025,
|
|
"num_tokens": 8446696.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 7.059392595291138,
|
|
"epoch": 0.49361037947517317,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004989727778569893,
|
|
"loss": 7.0275,
|
|
"mean_token_accuracy": 0.11218074709177017,
|
|
"num_tokens": 8464827.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 6.951289224624634,
|
|
"epoch": 0.4945858940591162,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004989660537695859,
|
|
"loss": 6.9867,
|
|
"mean_token_accuracy": 0.1131703607738018,
|
|
"num_tokens": 8480185.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 6.900561904907226,
|
|
"epoch": 0.4955614086430592,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.000498959307797018,
|
|
"loss": 6.8754,
|
|
"mean_token_accuracy": 0.12406175062060357,
|
|
"num_tokens": 8497511.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 6.917745304107666,
|
|
"epoch": 0.49653692322700227,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004989525399399447,
|
|
"loss": 6.9347,
|
|
"mean_token_accuracy": 0.11667040959000588,
|
|
"num_tokens": 8514394.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 6.989028596878052,
|
|
"epoch": 0.4975124378109453,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004989457501990275,
|
|
"loss": 6.9368,
|
|
"mean_token_accuracy": 0.11208094283938408,
|
|
"num_tokens": 8531659.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 6.9539367198944095,
|
|
"epoch": 0.4984879523948883,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004989389385749297,
|
|
"loss": 6.9859,
|
|
"mean_token_accuracy": 0.11457662954926491,
|
|
"num_tokens": 8547986.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 7.001014041900635,
|
|
"epoch": 0.4994634669788313,
|
|
"grad_norm": 0.75,
|
|
"learning_rate": 0.0004989321050683169,
|
|
"loss": 6.9339,
|
|
"mean_token_accuracy": 0.11468060165643693,
|
|
"num_tokens": 8565021.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 6.915047597885132,
|
|
"epoch": 0.5004389815627743,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000498925249679857,
|
|
"loss": 6.9396,
|
|
"mean_token_accuracy": 0.11381619796156883,
|
|
"num_tokens": 8582135.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 6.90760645866394,
|
|
"epoch": 0.5014144961467174,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004989183724102196,
|
|
"loss": 6.9589,
|
|
"mean_token_accuracy": 0.11705165952444077,
|
|
"num_tokens": 8599946.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 7.0192211151123045,
|
|
"epoch": 0.5023900107306605,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004989114732600771,
|
|
"loss": 6.983,
|
|
"mean_token_accuracy": 0.110711020976305,
|
|
"num_tokens": 8615831.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 6.89142541885376,
|
|
"epoch": 0.5033655253146034,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004989045522301033,
|
|
"loss": 6.8671,
|
|
"mean_token_accuracy": 0.11825199350714684,
|
|
"num_tokens": 8631886.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 6.981450748443604,
|
|
"epoch": 0.5043410398985465,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004988976093209747,
|
|
"loss": 6.9144,
|
|
"mean_token_accuracy": 0.11438037380576134,
|
|
"num_tokens": 8647520.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 6.870293664932251,
|
|
"epoch": 0.5053165544824895,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004988906445333698,
|
|
"loss": 6.8368,
|
|
"mean_token_accuracy": 0.12467891722917557,
|
|
"num_tokens": 8663995.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 6.890131139755249,
|
|
"epoch": 0.5062920690664325,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004988836578679691,
|
|
"loss": 6.9143,
|
|
"mean_token_accuracy": 0.11203564777970314,
|
|
"num_tokens": 8680201.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 6.963378143310547,
|
|
"epoch": 0.5072675836503756,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004988766493254552,
|
|
"loss": 6.9014,
|
|
"mean_token_accuracy": 0.12187715098261834,
|
|
"num_tokens": 8696978.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 6.8637247562408445,
|
|
"epoch": 0.5082430982343186,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.000498869618906513,
|
|
"loss": 6.9428,
|
|
"mean_token_accuracy": 0.11771589368581772,
|
|
"num_tokens": 8713335.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 6.99650011062622,
|
|
"epoch": 0.5092186128182616,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004988625666118296,
|
|
"loss": 6.9406,
|
|
"mean_token_accuracy": 0.11646446585655212,
|
|
"num_tokens": 8730722.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 6.877693843841553,
|
|
"epoch": 0.5101941274022047,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.000498855492442094,
|
|
"loss": 6.8641,
|
|
"mean_token_accuracy": 0.11773835569620132,
|
|
"num_tokens": 8747430.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 6.937593746185303,
|
|
"epoch": 0.5111696419861477,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004988483963979975,
|
|
"loss": 6.9526,
|
|
"mean_token_accuracy": 0.11680929362773895,
|
|
"num_tokens": 8764817.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 7.029442834854126,
|
|
"epoch": 0.5121451565700907,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004988412784802336,
|
|
"loss": 6.9674,
|
|
"mean_token_accuracy": 0.11305484101176262,
|
|
"num_tokens": 8780412.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 6.956655883789063,
|
|
"epoch": 0.5131206711540337,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004988341386894977,
|
|
"loss": 7.0367,
|
|
"mean_token_accuracy": 0.11347447261214257,
|
|
"num_tokens": 8795526.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 6.934908723831176,
|
|
"epoch": 0.5140961857379768,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004988269770264876,
|
|
"loss": 6.8335,
|
|
"mean_token_accuracy": 0.12252563685178756,
|
|
"num_tokens": 8813568.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 6.978274250030518,
|
|
"epoch": 0.5150717003219198,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004988197934919029,
|
|
"loss": 6.984,
|
|
"mean_token_accuracy": 0.11146572455763817,
|
|
"num_tokens": 8831807.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 7.024217653274536,
|
|
"epoch": 0.5160472149058628,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004988125880864458,
|
|
"loss": 6.9811,
|
|
"mean_token_accuracy": 0.11375662460923194,
|
|
"num_tokens": 8848875.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 6.793162870407104,
|
|
"epoch": 0.5170227294898059,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004988053608108203,
|
|
"loss": 6.6888,
|
|
"mean_token_accuracy": 0.12523928061127662,
|
|
"num_tokens": 8866317.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 6.868563032150268,
|
|
"epoch": 0.517998244073749,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004987981116657325,
|
|
"loss": 6.8371,
|
|
"mean_token_accuracy": 0.11552531272172928,
|
|
"num_tokens": 8882543.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 6.922529649734497,
|
|
"epoch": 0.5189737586576919,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004987908406518909,
|
|
"loss": 6.8399,
|
|
"mean_token_accuracy": 0.11445399224758149,
|
|
"num_tokens": 8898640.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 6.936803960800171,
|
|
"epoch": 0.519949273241635,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.000498783547770006,
|
|
"loss": 6.9548,
|
|
"mean_token_accuracy": 0.11621619910001754,
|
|
"num_tokens": 8914649.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 6.978597927093506,
|
|
"epoch": 0.5209247878255779,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004987762330207903,
|
|
"loss": 6.9706,
|
|
"mean_token_accuracy": 0.11318715661764145,
|
|
"num_tokens": 8931585.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 6.846628665924072,
|
|
"epoch": 0.521900302409521,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004987688964049587,
|
|
"loss": 6.8613,
|
|
"mean_token_accuracy": 0.12094739824533463,
|
|
"num_tokens": 8948827.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 6.8830482959747314,
|
|
"epoch": 0.5228758169934641,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.000498761537923228,
|
|
"loss": 6.8239,
|
|
"mean_token_accuracy": 0.12365922555327416,
|
|
"num_tokens": 8965680.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 6.981524515151977,
|
|
"epoch": 0.523851331577407,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004987541575763175,
|
|
"loss": 6.9672,
|
|
"mean_token_accuracy": 0.1103598140180111,
|
|
"num_tokens": 8982813.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 6.949263191223144,
|
|
"epoch": 0.5248268461613501,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.000498746755364948,
|
|
"loss": 6.9504,
|
|
"mean_token_accuracy": 0.11520707830786706,
|
|
"num_tokens": 9000497.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 6.882326602935791,
|
|
"epoch": 0.5258023607452932,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004987393312898431,
|
|
"loss": 6.8758,
|
|
"mean_token_accuracy": 0.11944987401366233,
|
|
"num_tokens": 9016195.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 6.863258600234985,
|
|
"epoch": 0.5267778753292361,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004987318853517282,
|
|
"loss": 6.8335,
|
|
"mean_token_accuracy": 0.125432301312685,
|
|
"num_tokens": 9033295.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 6.933648490905762,
|
|
"epoch": 0.5277533899131792,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004987244175513308,
|
|
"loss": 6.9282,
|
|
"mean_token_accuracy": 0.11364365071058273,
|
|
"num_tokens": 9050725.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 6.941001844406128,
|
|
"epoch": 0.5287289044971223,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004987169278893807,
|
|
"loss": 6.8772,
|
|
"mean_token_accuracy": 0.11788134574890137,
|
|
"num_tokens": 9067842.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 6.962023401260376,
|
|
"epoch": 0.5297044190810652,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004987094163666098,
|
|
"loss": 6.9033,
|
|
"mean_token_accuracy": 0.10963810235261917,
|
|
"num_tokens": 9084602.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 6.882829856872559,
|
|
"epoch": 0.5306799336650083,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.000498701882983752,
|
|
"loss": 6.8256,
|
|
"mean_token_accuracy": 0.12473871782422066,
|
|
"num_tokens": 9100530.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 6.901415729522705,
|
|
"epoch": 0.5316554482489513,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004986943277415435,
|
|
"loss": 6.9164,
|
|
"mean_token_accuracy": 0.1212962508201599,
|
|
"num_tokens": 9117304.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 6.846544599533081,
|
|
"epoch": 0.5326309628328944,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004986867506407225,
|
|
"loss": 6.8622,
|
|
"mean_token_accuracy": 0.13095585703849794,
|
|
"num_tokens": 9133974.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 6.914484453201294,
|
|
"epoch": 0.5336064774168374,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004986791516820295,
|
|
"loss": 6.8267,
|
|
"mean_token_accuracy": 0.12075289562344552,
|
|
"num_tokens": 9150600.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 6.834219551086425,
|
|
"epoch": 0.5345819920007804,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.000498671530866207,
|
|
"loss": 6.8344,
|
|
"mean_token_accuracy": 0.11510834842920303,
|
|
"num_tokens": 9167449.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 6.90480670928955,
|
|
"epoch": 0.5355575065847235,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004986638881939997,
|
|
"loss": 6.7687,
|
|
"mean_token_accuracy": 0.12122940719127655,
|
|
"num_tokens": 9184570.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 6.853910255432129,
|
|
"epoch": 0.5365330211686665,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004986562236661544,
|
|
"loss": 6.961,
|
|
"mean_token_accuracy": 0.10868783816695213,
|
|
"num_tokens": 9200537.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 7.009225177764892,
|
|
"epoch": 0.5375085357526095,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.00049864853728342,
|
|
"loss": 6.866,
|
|
"mean_token_accuracy": 0.12115592211484909,
|
|
"num_tokens": 9217252.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 6.878779077529908,
|
|
"epoch": 0.5384840503365526,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004986408290465476,
|
|
"loss": 6.9131,
|
|
"mean_token_accuracy": 0.11528742164373398,
|
|
"num_tokens": 9234108.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 6.938559627532959,
|
|
"epoch": 0.5394595649204955,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004986330989562906,
|
|
"loss": 6.8108,
|
|
"mean_token_accuracy": 0.12083505392074585,
|
|
"num_tokens": 9251017.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 6.805785608291626,
|
|
"epoch": 0.5404350795044386,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004986253470134042,
|
|
"loss": 6.7762,
|
|
"mean_token_accuracy": 0.1270703725516796,
|
|
"num_tokens": 9267922.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 6.761190700531006,
|
|
"epoch": 0.5414105940883817,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.0004986175732186459,
|
|
"loss": 6.7694,
|
|
"mean_token_accuracy": 0.1298803262412548,
|
|
"num_tokens": 9284954.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 6.956725168228149,
|
|
"epoch": 0.5423861086723246,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004986097775727752,
|
|
"loss": 6.8884,
|
|
"mean_token_accuracy": 0.11942665055394172,
|
|
"num_tokens": 9303306.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 6.79859299659729,
|
|
"epoch": 0.5433616232562677,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0004986019600765541,
|
|
"loss": 6.7824,
|
|
"mean_token_accuracy": 0.1234261803328991,
|
|
"num_tokens": 9319754.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 6.857258653640747,
|
|
"epoch": 0.5443371378402108,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004985941207307462,
|
|
"loss": 6.8724,
|
|
"mean_token_accuracy": 0.120131453871727,
|
|
"num_tokens": 9335736.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 6.854156827926635,
|
|
"epoch": 0.5453126524241537,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004985862595361179,
|
|
"loss": 6.8434,
|
|
"mean_token_accuracy": 0.12304849475622177,
|
|
"num_tokens": 9350435.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 6.9249341011047365,
|
|
"epoch": 0.5462881670080968,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004985783764934372,
|
|
"loss": 6.9191,
|
|
"mean_token_accuracy": 0.11444221660494805,
|
|
"num_tokens": 9367613.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 6.848372459411621,
|
|
"epoch": 0.5472636815920398,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004985704716034744,
|
|
"loss": 6.7859,
|
|
"mean_token_accuracy": 0.12150981798768043,
|
|
"num_tokens": 9385590.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 6.905705404281616,
|
|
"epoch": 0.5482391961759828,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004985625448670019,
|
|
"loss": 6.9263,
|
|
"mean_token_accuracy": 0.10945390835404396,
|
|
"num_tokens": 9403286.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 6.994100189208984,
|
|
"epoch": 0.5492147107599259,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004985545962847943,
|
|
"loss": 6.9189,
|
|
"mean_token_accuracy": 0.11298392787575721,
|
|
"num_tokens": 9419880.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 6.9102226257324215,
|
|
"epoch": 0.5501902253438689,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004985466258576283,
|
|
"loss": 6.8775,
|
|
"mean_token_accuracy": 0.11068576276302337,
|
|
"num_tokens": 9436579.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 6.943197536468506,
|
|
"epoch": 0.5511657399278119,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004985386335862829,
|
|
"loss": 6.9511,
|
|
"mean_token_accuracy": 0.11212421581149101,
|
|
"num_tokens": 9452802.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 6.9377796173095705,
|
|
"epoch": 0.552141254511755,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004985306194715387,
|
|
"loss": 6.9462,
|
|
"mean_token_accuracy": 0.11190766394138336,
|
|
"num_tokens": 9468297.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 6.920965957641601,
|
|
"epoch": 0.553116769095698,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004985225835141792,
|
|
"loss": 6.9673,
|
|
"mean_token_accuracy": 0.10958375483751297,
|
|
"num_tokens": 9484954.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 7.036347913742065,
|
|
"epoch": 0.554092283679641,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004985145257149895,
|
|
"loss": 7.0055,
|
|
"mean_token_accuracy": 0.10926211625337601,
|
|
"num_tokens": 9502211.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 6.92486252784729,
|
|
"epoch": 0.555067798263584,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004985064460747569,
|
|
"loss": 6.9012,
|
|
"mean_token_accuracy": 0.11126281246542931,
|
|
"num_tokens": 9518103.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 6.856705045700073,
|
|
"epoch": 0.5560433128475271,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000498498344594271,
|
|
"loss": 6.8237,
|
|
"mean_token_accuracy": 0.11587432101368904,
|
|
"num_tokens": 9534155.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 6.8256289005279545,
|
|
"epoch": 0.5570188274314701,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004984902212743234,
|
|
"loss": 6.8099,
|
|
"mean_token_accuracy": 0.12739480584859847,
|
|
"num_tokens": 9549972.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 6.8014082431793215,
|
|
"epoch": 0.5579943420154131,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004984820761157079,
|
|
"loss": 6.736,
|
|
"mean_token_accuracy": 0.13063260465860366,
|
|
"num_tokens": 9567306.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 6.940472412109375,
|
|
"epoch": 0.5589698565993562,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004984739091192205,
|
|
"loss": 6.9327,
|
|
"mean_token_accuracy": 0.1139756128191948,
|
|
"num_tokens": 9583488.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 6.727579021453858,
|
|
"epoch": 0.5599453711832992,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004984657202856592,
|
|
"loss": 6.7233,
|
|
"mean_token_accuracy": 0.12913710996508598,
|
|
"num_tokens": 9600030.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 6.848877954483032,
|
|
"epoch": 0.5609208857672422,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000498457509615824,
|
|
"loss": 6.842,
|
|
"mean_token_accuracy": 0.12119656652212143,
|
|
"num_tokens": 9615791.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 6.978024339675903,
|
|
"epoch": 0.5618964003511853,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004984492771105175,
|
|
"loss": 6.9141,
|
|
"mean_token_accuracy": 0.11272858902812004,
|
|
"num_tokens": 9630955.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 6.791843271255493,
|
|
"epoch": 0.5628719149351282,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004984410227705439,
|
|
"loss": 6.8307,
|
|
"mean_token_accuracy": 0.12661578208208085,
|
|
"num_tokens": 9647743.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 6.833824110031128,
|
|
"epoch": 0.5638474295190713,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004984327465967101,
|
|
"loss": 6.7632,
|
|
"mean_token_accuracy": 0.12368033602833747,
|
|
"num_tokens": 9665495.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 6.867427635192871,
|
|
"epoch": 0.5648229441030144,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004984244485898246,
|
|
"loss": 6.7957,
|
|
"mean_token_accuracy": 0.12146139666438102,
|
|
"num_tokens": 9683489.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 6.681371450424194,
|
|
"epoch": 0.5657984586869573,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004984161287506982,
|
|
"loss": 6.7306,
|
|
"mean_token_accuracy": 0.13925604596734048,
|
|
"num_tokens": 9700491.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 6.976580095291138,
|
|
"epoch": 0.5667739732709004,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.000498407787080144,
|
|
"loss": 6.8928,
|
|
"mean_token_accuracy": 0.11349690333008766,
|
|
"num_tokens": 9715694.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 6.8997095108032225,
|
|
"epoch": 0.5677494878548435,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.000498399423578977,
|
|
"loss": 6.9487,
|
|
"mean_token_accuracy": 0.11223901212215423,
|
|
"num_tokens": 9731317.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 7.015579509735107,
|
|
"epoch": 0.5687250024387864,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004983910382480146,
|
|
"loss": 6.919,
|
|
"mean_token_accuracy": 0.11128888130187989,
|
|
"num_tokens": 9747928.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 6.893016815185547,
|
|
"epoch": 0.5697005170227295,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004983826310880762,
|
|
"loss": 6.8544,
|
|
"mean_token_accuracy": 0.11194843426346779,
|
|
"num_tokens": 9765454.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 6.965768766403198,
|
|
"epoch": 0.5706760316066726,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004983742020999832,
|
|
"loss": 6.9344,
|
|
"mean_token_accuracy": 0.10903514623641967,
|
|
"num_tokens": 9782255.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 6.727192163467407,
|
|
"epoch": 0.5716515461906155,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004983657512845593,
|
|
"loss": 6.7417,
|
|
"mean_token_accuracy": 0.1272973582148552,
|
|
"num_tokens": 9798680.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 6.887448167800903,
|
|
"epoch": 0.5726270607745586,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004983572786426302,
|
|
"loss": 6.882,
|
|
"mean_token_accuracy": 0.115676748752594,
|
|
"num_tokens": 9813955.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 6.7411586284637455,
|
|
"epoch": 0.5736025753585016,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004983487841750239,
|
|
"loss": 6.7617,
|
|
"mean_token_accuracy": 0.1255027547478676,
|
|
"num_tokens": 9830692.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 6.937388372421265,
|
|
"epoch": 0.5745780899424446,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004983402678825705,
|
|
"loss": 6.885,
|
|
"mean_token_accuracy": 0.11392842903733254,
|
|
"num_tokens": 9848825.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 6.873228216171265,
|
|
"epoch": 0.5755536045263877,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004983317297661021,
|
|
"loss": 6.8859,
|
|
"mean_token_accuracy": 0.11650989279150963,
|
|
"num_tokens": 9865802.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 6.91488995552063,
|
|
"epoch": 0.5765291191103307,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004983231698264531,
|
|
"loss": 6.9293,
|
|
"mean_token_accuracy": 0.11482540965080261,
|
|
"num_tokens": 9883540.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 6.936852312088012,
|
|
"epoch": 0.5775046336942737,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004983145880644597,
|
|
"loss": 6.8625,
|
|
"mean_token_accuracy": 0.11717101335525512,
|
|
"num_tokens": 9897724.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 6.896431303024292,
|
|
"epoch": 0.5784801482782168,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004983059844809608,
|
|
"loss": 6.8137,
|
|
"mean_token_accuracy": 0.12274272590875626,
|
|
"num_tokens": 9914710.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 6.854437398910522,
|
|
"epoch": 0.5794556628621598,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004982973590767969,
|
|
"loss": 6.9261,
|
|
"mean_token_accuracy": 0.11889142394065857,
|
|
"num_tokens": 9932362.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 6.84909086227417,
|
|
"epoch": 0.5804311774461028,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.000498288711852811,
|
|
"loss": 6.7269,
|
|
"mean_token_accuracy": 0.12317892163991928,
|
|
"num_tokens": 9949409.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 6.850289630889892,
|
|
"epoch": 0.5814066920300458,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.000498280042809848,
|
|
"loss": 6.8803,
|
|
"mean_token_accuracy": 0.11638240292668342,
|
|
"num_tokens": 9967467.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 6.904487228393554,
|
|
"epoch": 0.5823822066139889,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004982713519487549,
|
|
"loss": 6.8065,
|
|
"mean_token_accuracy": 0.1210539199411869,
|
|
"num_tokens": 9983082.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 6.827433156967163,
|
|
"epoch": 0.5833577211979319,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004982626392703812,
|
|
"loss": 6.8852,
|
|
"mean_token_accuracy": 0.11658342108130455,
|
|
"num_tokens": 10000046.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 6.890923309326172,
|
|
"epoch": 0.5843332357818749,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000498253904775578,
|
|
"loss": 6.8249,
|
|
"mean_token_accuracy": 0.11711288690567016,
|
|
"num_tokens": 10014674.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 6.777483081817627,
|
|
"epoch": 0.585308750365818,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004982451484651988,
|
|
"loss": 6.7075,
|
|
"mean_token_accuracy": 0.12117704004049301,
|
|
"num_tokens": 10030647.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.585308750365818,
|
|
"eval_entropy": 6.687477521946967,
|
|
"eval_loss": 6.875298976898193,
|
|
"eval_mean_token_accuracy": 0.1196487419652266,
|
|
"eval_num_tokens": 10030647.0,
|
|
"eval_runtime": 15.4221,
|
|
"eval_samples_per_second": 1074.886,
|
|
"eval_steps_per_second": 134.417,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"entropy": 6.8513280868530275,
|
|
"epoch": 0.586284264949761,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004982363703400995,
|
|
"loss": 6.7869,
|
|
"mean_token_accuracy": 0.1201705053448677,
|
|
"num_tokens": 10046468.0,
|
|
"step": 3005
|
|
},
|
|
{
|
|
"entropy": 6.865765953063965,
|
|
"epoch": 0.587259779533704,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004982275704011377,
|
|
"loss": 6.9013,
|
|
"mean_token_accuracy": 0.11224028393626213,
|
|
"num_tokens": 10063062.0,
|
|
"step": 3010
|
|
},
|
|
{
|
|
"entropy": 6.8745828628540036,
|
|
"epoch": 0.5882352941176471,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004982187486491734,
|
|
"loss": 6.854,
|
|
"mean_token_accuracy": 0.11705698743462563,
|
|
"num_tokens": 10079616.0,
|
|
"step": 3015
|
|
},
|
|
{
|
|
"entropy": 6.804439449310303,
|
|
"epoch": 0.58921080870159,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004982099050850685,
|
|
"loss": 6.8084,
|
|
"mean_token_accuracy": 0.11702773049473762,
|
|
"num_tokens": 10096830.0,
|
|
"step": 3020
|
|
},
|
|
{
|
|
"entropy": 6.83272910118103,
|
|
"epoch": 0.5901863232855331,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004982010397096871,
|
|
"loss": 6.8404,
|
|
"mean_token_accuracy": 0.12048523053526879,
|
|
"num_tokens": 10114041.0,
|
|
"step": 3025
|
|
},
|
|
{
|
|
"entropy": 6.825710821151733,
|
|
"epoch": 0.5911618378694762,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004981921525238957,
|
|
"loss": 6.7654,
|
|
"mean_token_accuracy": 0.12277414426207542,
|
|
"num_tokens": 10130075.0,
|
|
"step": 3030
|
|
},
|
|
{
|
|
"entropy": 6.862203550338745,
|
|
"epoch": 0.5921373524534191,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004981832435285626,
|
|
"loss": 6.9224,
|
|
"mean_token_accuracy": 0.1168674349784851,
|
|
"num_tokens": 10146716.0,
|
|
"step": 3035
|
|
},
|
|
{
|
|
"entropy": 6.939451122283936,
|
|
"epoch": 0.5931128670373622,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004981743127245584,
|
|
"loss": 6.8381,
|
|
"mean_token_accuracy": 0.11847971603274346,
|
|
"num_tokens": 10162116.0,
|
|
"step": 3040
|
|
},
|
|
{
|
|
"entropy": 6.92747654914856,
|
|
"epoch": 0.5940883816213053,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004981653601127557,
|
|
"loss": 6.9259,
|
|
"mean_token_accuracy": 0.11367085874080658,
|
|
"num_tokens": 10179326.0,
|
|
"step": 3045
|
|
},
|
|
{
|
|
"entropy": 6.87494010925293,
|
|
"epoch": 0.5950638962052482,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004981563856940295,
|
|
"loss": 6.8561,
|
|
"mean_token_accuracy": 0.11840385645627975,
|
|
"num_tokens": 10195278.0,
|
|
"step": 3050
|
|
},
|
|
{
|
|
"entropy": 6.825404977798462,
|
|
"epoch": 0.5960394107891913,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004981473894692565,
|
|
"loss": 6.7803,
|
|
"mean_token_accuracy": 0.12475141808390618,
|
|
"num_tokens": 10210175.0,
|
|
"step": 3055
|
|
},
|
|
{
|
|
"entropy": 6.86231541633606,
|
|
"epoch": 0.5970149253731343,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.000498138371439316,
|
|
"loss": 6.8905,
|
|
"mean_token_accuracy": 0.11413062140345573,
|
|
"num_tokens": 10225600.0,
|
|
"step": 3060
|
|
},
|
|
{
|
|
"entropy": 6.701946353912353,
|
|
"epoch": 0.5979904399570773,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004981293316050891,
|
|
"loss": 6.5854,
|
|
"mean_token_accuracy": 0.14134220480918885,
|
|
"num_tokens": 10243451.0,
|
|
"step": 3065
|
|
},
|
|
{
|
|
"entropy": 6.881609916687012,
|
|
"epoch": 0.5989659545410204,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004981202699674592,
|
|
"loss": 6.8611,
|
|
"mean_token_accuracy": 0.11565692573785782,
|
|
"num_tokens": 10260392.0,
|
|
"step": 3070
|
|
},
|
|
{
|
|
"entropy": 6.908903980255127,
|
|
"epoch": 0.5999414691249634,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004981111865273117,
|
|
"loss": 6.8959,
|
|
"mean_token_accuracy": 0.11276777759194374,
|
|
"num_tokens": 10277016.0,
|
|
"step": 3075
|
|
},
|
|
{
|
|
"entropy": 6.734448194503784,
|
|
"epoch": 0.6009169837089064,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004981020812855342,
|
|
"loss": 6.7726,
|
|
"mean_token_accuracy": 0.12777200788259507,
|
|
"num_tokens": 10295927.0,
|
|
"step": 3080
|
|
},
|
|
{
|
|
"entropy": 6.909026622772217,
|
|
"epoch": 0.6018924982928495,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004980929542430165,
|
|
"loss": 6.8405,
|
|
"mean_token_accuracy": 0.11428990885615349,
|
|
"num_tokens": 10311140.0,
|
|
"step": 3085
|
|
},
|
|
{
|
|
"entropy": 6.867432880401611,
|
|
"epoch": 0.6028680128767925,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004980838054006504,
|
|
"loss": 6.8842,
|
|
"mean_token_accuracy": 0.12005732953548431,
|
|
"num_tokens": 10328496.0,
|
|
"step": 3090
|
|
},
|
|
{
|
|
"entropy": 6.882465982437134,
|
|
"epoch": 0.6038435274607356,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.00049807463475933,
|
|
"loss": 6.834,
|
|
"mean_token_accuracy": 0.11526197642087936,
|
|
"num_tokens": 10345232.0,
|
|
"step": 3095
|
|
},
|
|
{
|
|
"entropy": 6.938439607620239,
|
|
"epoch": 0.6048190420446786,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004980654423199513,
|
|
"loss": 6.9647,
|
|
"mean_token_accuracy": 0.1157417967915535,
|
|
"num_tokens": 10361777.0,
|
|
"step": 3100
|
|
},
|
|
{
|
|
"entropy": 6.889785575866699,
|
|
"epoch": 0.6057945566286216,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004980562280834126,
|
|
"loss": 6.8752,
|
|
"mean_token_accuracy": 0.11926004961133004,
|
|
"num_tokens": 10377117.0,
|
|
"step": 3105
|
|
},
|
|
{
|
|
"entropy": 6.660214853286743,
|
|
"epoch": 0.6067700712125647,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004980469920506142,
|
|
"loss": 6.5254,
|
|
"mean_token_accuracy": 0.1441980741918087,
|
|
"num_tokens": 10394506.0,
|
|
"step": 3110
|
|
},
|
|
{
|
|
"entropy": 6.730488109588623,
|
|
"epoch": 0.6077455857965076,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004980377342224588,
|
|
"loss": 6.6581,
|
|
"mean_token_accuracy": 0.1327843114733696,
|
|
"num_tokens": 10410281.0,
|
|
"step": 3115
|
|
},
|
|
{
|
|
"entropy": 6.839040660858155,
|
|
"epoch": 0.6087211003804507,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004980284545998509,
|
|
"loss": 6.8726,
|
|
"mean_token_accuracy": 0.11320614889264106,
|
|
"num_tokens": 10425165.0,
|
|
"step": 3120
|
|
},
|
|
{
|
|
"entropy": 6.93717360496521,
|
|
"epoch": 0.6096966149643938,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004980191531836973,
|
|
"loss": 6.8349,
|
|
"mean_token_accuracy": 0.11161382794380188,
|
|
"num_tokens": 10441643.0,
|
|
"step": 3125
|
|
},
|
|
{
|
|
"entropy": 6.826653146743775,
|
|
"epoch": 0.6106721295483367,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004980098299749068,
|
|
"loss": 6.8711,
|
|
"mean_token_accuracy": 0.11073935478925705,
|
|
"num_tokens": 10457436.0,
|
|
"step": 3130
|
|
},
|
|
{
|
|
"entropy": 6.925049781799316,
|
|
"epoch": 0.6116476441322798,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004980004849743908,
|
|
"loss": 6.8777,
|
|
"mean_token_accuracy": 0.11430571228265762,
|
|
"num_tokens": 10475020.0,
|
|
"step": 3135
|
|
},
|
|
{
|
|
"entropy": 6.622587394714356,
|
|
"epoch": 0.6126231587162229,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000497991118183062,
|
|
"loss": 6.6524,
|
|
"mean_token_accuracy": 0.12878014519810677,
|
|
"num_tokens": 10492029.0,
|
|
"step": 3140
|
|
},
|
|
{
|
|
"entropy": 6.769395542144776,
|
|
"epoch": 0.6135986733001658,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004979817296018359,
|
|
"loss": 6.6708,
|
|
"mean_token_accuracy": 0.1282647155225277,
|
|
"num_tokens": 10510145.0,
|
|
"step": 3145
|
|
},
|
|
{
|
|
"entropy": 6.8891397476196286,
|
|
"epoch": 0.6145741878841089,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004979723192316299,
|
|
"loss": 6.9298,
|
|
"mean_token_accuracy": 0.11716325283050537,
|
|
"num_tokens": 10527192.0,
|
|
"step": 3150
|
|
},
|
|
{
|
|
"entropy": 6.900948619842529,
|
|
"epoch": 0.6155497024680519,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004979628870733637,
|
|
"loss": 6.8692,
|
|
"mean_token_accuracy": 0.11685981303453445,
|
|
"num_tokens": 10542269.0,
|
|
"step": 3155
|
|
},
|
|
{
|
|
"entropy": 6.838070392608643,
|
|
"epoch": 0.6165252170519949,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004979534331279586,
|
|
"loss": 6.8522,
|
|
"mean_token_accuracy": 0.11938246861100196,
|
|
"num_tokens": 10559425.0,
|
|
"step": 3160
|
|
},
|
|
{
|
|
"entropy": 6.875582695007324,
|
|
"epoch": 0.617500731635938,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004979439573963388,
|
|
"loss": 6.8547,
|
|
"mean_token_accuracy": 0.11787030398845673,
|
|
"num_tokens": 10576818.0,
|
|
"step": 3165
|
|
},
|
|
{
|
|
"entropy": 6.758587884902954,
|
|
"epoch": 0.618476246219881,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004979344598794299,
|
|
"loss": 6.7572,
|
|
"mean_token_accuracy": 0.12366017401218414,
|
|
"num_tokens": 10593456.0,
|
|
"step": 3170
|
|
},
|
|
{
|
|
"entropy": 6.911983013153076,
|
|
"epoch": 0.619451760803824,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004979249405781602,
|
|
"loss": 6.9468,
|
|
"mean_token_accuracy": 0.1103769950568676,
|
|
"num_tokens": 10609049.0,
|
|
"step": 3175
|
|
},
|
|
{
|
|
"entropy": 6.810990285873413,
|
|
"epoch": 0.6204272753877671,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004979153994934599,
|
|
"loss": 6.763,
|
|
"mean_token_accuracy": 0.12128573358058929,
|
|
"num_tokens": 10626921.0,
|
|
"step": 3180
|
|
},
|
|
{
|
|
"entropy": 6.8773603439331055,
|
|
"epoch": 0.6214027899717101,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004979058366262613,
|
|
"loss": 6.8234,
|
|
"mean_token_accuracy": 0.11325632035732269,
|
|
"num_tokens": 10643447.0,
|
|
"step": 3185
|
|
},
|
|
{
|
|
"entropy": 6.9067542552948,
|
|
"epoch": 0.6223783045556531,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004978962519774987,
|
|
"loss": 6.891,
|
|
"mean_token_accuracy": 0.11275544539093971,
|
|
"num_tokens": 10659896.0,
|
|
"step": 3190
|
|
},
|
|
{
|
|
"entropy": 6.820027017593384,
|
|
"epoch": 0.6233538191395961,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004978866455481087,
|
|
"loss": 6.7462,
|
|
"mean_token_accuracy": 0.12121571525931359,
|
|
"num_tokens": 10675331.0,
|
|
"step": 3195
|
|
},
|
|
{
|
|
"entropy": 6.875732040405273,
|
|
"epoch": 0.6243293337235392,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004978770173390301,
|
|
"loss": 6.9141,
|
|
"mean_token_accuracy": 0.11388504430651665,
|
|
"num_tokens": 10692678.0,
|
|
"step": 3200
|
|
},
|
|
{
|
|
"entropy": 6.919794797897339,
|
|
"epoch": 0.6253048483074822,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004978673673512039,
|
|
"loss": 6.835,
|
|
"mean_token_accuracy": 0.11259569525718689,
|
|
"num_tokens": 10708500.0,
|
|
"step": 3205
|
|
},
|
|
{
|
|
"entropy": 6.811052465438843,
|
|
"epoch": 0.6262803628914252,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004978576955855727,
|
|
"loss": 6.7608,
|
|
"mean_token_accuracy": 0.12187205329537391,
|
|
"num_tokens": 10725424.0,
|
|
"step": 3210
|
|
},
|
|
{
|
|
"entropy": 6.854435682296753,
|
|
"epoch": 0.6272558774753683,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004978480020430818,
|
|
"loss": 6.787,
|
|
"mean_token_accuracy": 0.12234523594379425,
|
|
"num_tokens": 10740960.0,
|
|
"step": 3215
|
|
},
|
|
{
|
|
"entropy": 6.860615539550781,
|
|
"epoch": 0.6282313920593113,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004978382867246784,
|
|
"loss": 6.814,
|
|
"mean_token_accuracy": 0.11499368697404862,
|
|
"num_tokens": 10756426.0,
|
|
"step": 3220
|
|
},
|
|
{
|
|
"entropy": 6.772602510452271,
|
|
"epoch": 0.6292069066432543,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004978285496313119,
|
|
"loss": 6.6981,
|
|
"mean_token_accuracy": 0.12667033076286316,
|
|
"num_tokens": 10772748.0,
|
|
"step": 3225
|
|
},
|
|
{
|
|
"entropy": 6.779733800888062,
|
|
"epoch": 0.6301824212271974,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004978187907639336,
|
|
"loss": 6.7383,
|
|
"mean_token_accuracy": 0.12489306554198265,
|
|
"num_tokens": 10790024.0,
|
|
"step": 3230
|
|
},
|
|
{
|
|
"entropy": 6.877752780914307,
|
|
"epoch": 0.6311579358111403,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004978090101234972,
|
|
"loss": 6.8543,
|
|
"mean_token_accuracy": 0.11172328889369965,
|
|
"num_tokens": 10806280.0,
|
|
"step": 3235
|
|
},
|
|
{
|
|
"entropy": 6.7855456352233885,
|
|
"epoch": 0.6321334503950834,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004977992077109585,
|
|
"loss": 6.7268,
|
|
"mean_token_accuracy": 0.12426211014389991,
|
|
"num_tokens": 10822166.0,
|
|
"step": 3240
|
|
},
|
|
{
|
|
"entropy": 6.851929378509522,
|
|
"epoch": 0.6331089649790265,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004977893835272754,
|
|
"loss": 6.8871,
|
|
"mean_token_accuracy": 0.11298680528998375,
|
|
"num_tokens": 10839833.0,
|
|
"step": 3245
|
|
},
|
|
{
|
|
"entropy": 6.885575437545777,
|
|
"epoch": 0.6340844795629694,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004977795375734075,
|
|
"loss": 6.8477,
|
|
"mean_token_accuracy": 0.1159172646701336,
|
|
"num_tokens": 10856803.0,
|
|
"step": 3250
|
|
},
|
|
{
|
|
"entropy": 6.793505048751831,
|
|
"epoch": 0.6350599941469125,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004977696698503174,
|
|
"loss": 6.7191,
|
|
"mean_token_accuracy": 0.1280121773481369,
|
|
"num_tokens": 10874245.0,
|
|
"step": 3255
|
|
},
|
|
{
|
|
"entropy": 6.794358921051026,
|
|
"epoch": 0.6360355087308556,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.000497759780358969,
|
|
"loss": 6.7251,
|
|
"mean_token_accuracy": 0.12450512126088142,
|
|
"num_tokens": 10890380.0,
|
|
"step": 3260
|
|
},
|
|
{
|
|
"entropy": 6.836582469940185,
|
|
"epoch": 0.6370110233147985,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004977498691003288,
|
|
"loss": 6.7974,
|
|
"mean_token_accuracy": 0.1160903625190258,
|
|
"num_tokens": 10906927.0,
|
|
"step": 3265
|
|
},
|
|
{
|
|
"entropy": 6.883288717269897,
|
|
"epoch": 0.6379865378987416,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004977399360753654,
|
|
"loss": 6.8525,
|
|
"mean_token_accuracy": 0.11490120962262154,
|
|
"num_tokens": 10922922.0,
|
|
"step": 3270
|
|
},
|
|
{
|
|
"entropy": 6.842705535888672,
|
|
"epoch": 0.6389620524826846,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004977299812850492,
|
|
"loss": 6.8685,
|
|
"mean_token_accuracy": 0.11662356927990913,
|
|
"num_tokens": 10939607.0,
|
|
"step": 3275
|
|
},
|
|
{
|
|
"entropy": 6.745472097396851,
|
|
"epoch": 0.6399375670666276,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004977200047303532,
|
|
"loss": 6.7767,
|
|
"mean_token_accuracy": 0.12351038977503777,
|
|
"num_tokens": 10956830.0,
|
|
"step": 3280
|
|
},
|
|
{
|
|
"entropy": 6.8052795886993405,
|
|
"epoch": 0.6409130816505707,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.000497710006412252,
|
|
"loss": 6.721,
|
|
"mean_token_accuracy": 0.12086443901062012,
|
|
"num_tokens": 10974364.0,
|
|
"step": 3285
|
|
},
|
|
{
|
|
"entropy": 6.8465166091918945,
|
|
"epoch": 0.6418885962345137,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004976999863317228,
|
|
"loss": 6.7918,
|
|
"mean_token_accuracy": 0.12175193578004836,
|
|
"num_tokens": 10990645.0,
|
|
"step": 3290
|
|
},
|
|
{
|
|
"entropy": 6.824837923049927,
|
|
"epoch": 0.6428641108184567,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004976899444897446,
|
|
"loss": 6.7911,
|
|
"mean_token_accuracy": 0.12471163049340248,
|
|
"num_tokens": 11007952.0,
|
|
"step": 3295
|
|
},
|
|
{
|
|
"entropy": 6.674902296066284,
|
|
"epoch": 0.6438396254023998,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004976798808872987,
|
|
"loss": 6.6974,
|
|
"mean_token_accuracy": 0.12610986977815627,
|
|
"num_tokens": 11024708.0,
|
|
"step": 3300
|
|
},
|
|
{
|
|
"entropy": 6.844508504867553,
|
|
"epoch": 0.6448151399863428,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004976697955253685,
|
|
"loss": 6.8105,
|
|
"mean_token_accuracy": 0.11966940686106682,
|
|
"num_tokens": 11040447.0,
|
|
"step": 3305
|
|
},
|
|
{
|
|
"entropy": 6.855398273468017,
|
|
"epoch": 0.6457906545702858,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004976596884049395,
|
|
"loss": 6.846,
|
|
"mean_token_accuracy": 0.11857131198048591,
|
|
"num_tokens": 11057359.0,
|
|
"step": 3310
|
|
},
|
|
{
|
|
"entropy": 6.787343740463257,
|
|
"epoch": 0.6467661691542289,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004976495595269994,
|
|
"loss": 6.6875,
|
|
"mean_token_accuracy": 0.12616341635584832,
|
|
"num_tokens": 11072997.0,
|
|
"step": 3315
|
|
},
|
|
{
|
|
"entropy": 6.854625463485718,
|
|
"epoch": 0.6477416837381719,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004976394088925377,
|
|
"loss": 6.9191,
|
|
"mean_token_accuracy": 0.10992388501763344,
|
|
"num_tokens": 11089951.0,
|
|
"step": 3320
|
|
},
|
|
{
|
|
"entropy": 6.75814414024353,
|
|
"epoch": 0.6487171983221149,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004976292365025465,
|
|
"loss": 6.6237,
|
|
"mean_token_accuracy": 0.12900391817092896,
|
|
"num_tokens": 11107929.0,
|
|
"step": 3325
|
|
},
|
|
{
|
|
"entropy": 6.630945301055908,
|
|
"epoch": 0.6496927129060579,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004976190423580199,
|
|
"loss": 6.589,
|
|
"mean_token_accuracy": 0.13649226799607278,
|
|
"num_tokens": 11125479.0,
|
|
"step": 3330
|
|
},
|
|
{
|
|
"entropy": 6.801066732406616,
|
|
"epoch": 0.650668227490001,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004976088264599538,
|
|
"loss": 6.8374,
|
|
"mean_token_accuracy": 0.11279109418392182,
|
|
"num_tokens": 11142316.0,
|
|
"step": 3335
|
|
},
|
|
{
|
|
"entropy": 6.895862197875976,
|
|
"epoch": 0.651643742073944,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004975985888093467,
|
|
"loss": 6.8977,
|
|
"mean_token_accuracy": 0.1115566574037075,
|
|
"num_tokens": 11158664.0,
|
|
"step": 3340
|
|
},
|
|
{
|
|
"entropy": 6.842674636840821,
|
|
"epoch": 0.652619256657887,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004975883294071987,
|
|
"loss": 6.8087,
|
|
"mean_token_accuracy": 0.11642391607165337,
|
|
"num_tokens": 11175732.0,
|
|
"step": 3345
|
|
},
|
|
{
|
|
"entropy": 6.9053382396698,
|
|
"epoch": 0.6535947712418301,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004975780482545125,
|
|
"loss": 6.8721,
|
|
"mean_token_accuracy": 0.1097185492515564,
|
|
"num_tokens": 11191921.0,
|
|
"step": 3350
|
|
},
|
|
{
|
|
"entropy": 6.720562934875488,
|
|
"epoch": 0.6545702858257731,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004975677453522928,
|
|
"loss": 6.6518,
|
|
"mean_token_accuracy": 0.12887165546417237,
|
|
"num_tokens": 11208119.0,
|
|
"step": 3355
|
|
},
|
|
{
|
|
"entropy": 6.906631994247436,
|
|
"epoch": 0.6555458004097161,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004975574207015462,
|
|
"loss": 6.8195,
|
|
"mean_token_accuracy": 0.12121018841862678,
|
|
"num_tokens": 11224501.0,
|
|
"step": 3360
|
|
},
|
|
{
|
|
"entropy": 6.864675712585449,
|
|
"epoch": 0.6565213149936592,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004975470743032817,
|
|
"loss": 6.8526,
|
|
"mean_token_accuracy": 0.11966774761676788,
|
|
"num_tokens": 11240211.0,
|
|
"step": 3365
|
|
},
|
|
{
|
|
"entropy": 6.7802001476287845,
|
|
"epoch": 0.6574968295776021,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004975367061585102,
|
|
"loss": 6.7773,
|
|
"mean_token_accuracy": 0.11676874458789825,
|
|
"num_tokens": 11257921.0,
|
|
"step": 3370
|
|
},
|
|
{
|
|
"entropy": 6.800877904891967,
|
|
"epoch": 0.6584723441615452,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004975263162682449,
|
|
"loss": 6.7531,
|
|
"mean_token_accuracy": 0.12485904321074486,
|
|
"num_tokens": 11274526.0,
|
|
"step": 3375
|
|
},
|
|
{
|
|
"entropy": 6.848165798187256,
|
|
"epoch": 0.6594478587454883,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000497515904633501,
|
|
"loss": 6.7461,
|
|
"mean_token_accuracy": 0.11670261323451996,
|
|
"num_tokens": 11290883.0,
|
|
"step": 3380
|
|
},
|
|
{
|
|
"entropy": 6.824203252792358,
|
|
"epoch": 0.6604233733294312,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004975054712552963,
|
|
"loss": 6.7997,
|
|
"mean_token_accuracy": 0.11825350970029831,
|
|
"num_tokens": 11307406.0,
|
|
"step": 3385
|
|
},
|
|
{
|
|
"entropy": 6.7294018268585205,
|
|
"epoch": 0.6613988879133743,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004974950161346496,
|
|
"loss": 6.6392,
|
|
"mean_token_accuracy": 0.12867554873228074,
|
|
"num_tokens": 11322728.0,
|
|
"step": 3390
|
|
},
|
|
{
|
|
"entropy": 6.626737594604492,
|
|
"epoch": 0.6623744024973174,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000497484539272583,
|
|
"loss": 6.6303,
|
|
"mean_token_accuracy": 0.12962965667247772,
|
|
"num_tokens": 11338995.0,
|
|
"step": 3395
|
|
},
|
|
{
|
|
"entropy": 6.701203060150147,
|
|
"epoch": 0.6633499170812603,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004974740406701203,
|
|
"loss": 6.627,
|
|
"mean_token_accuracy": 0.13213070183992387,
|
|
"num_tokens": 11356154.0,
|
|
"step": 3400
|
|
},
|
|
{
|
|
"entropy": 6.736870336532593,
|
|
"epoch": 0.6643254316652034,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004974635203282873,
|
|
"loss": 6.7773,
|
|
"mean_token_accuracy": 0.12062362283468246,
|
|
"num_tokens": 11372755.0,
|
|
"step": 3405
|
|
},
|
|
{
|
|
"entropy": 6.729350614547729,
|
|
"epoch": 0.6653009462491464,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004974529782481119,
|
|
"loss": 6.7195,
|
|
"mean_token_accuracy": 0.1277965262532234,
|
|
"num_tokens": 11389424.0,
|
|
"step": 3410
|
|
},
|
|
{
|
|
"entropy": 6.835336303710937,
|
|
"epoch": 0.6662764608330894,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004974424144306241,
|
|
"loss": 6.7921,
|
|
"mean_token_accuracy": 0.11730759367346763,
|
|
"num_tokens": 11406515.0,
|
|
"step": 3415
|
|
},
|
|
{
|
|
"entropy": 6.788410711288452,
|
|
"epoch": 0.6672519754170325,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0004974318288768566,
|
|
"loss": 6.701,
|
|
"mean_token_accuracy": 0.12985792085528375,
|
|
"num_tokens": 11423195.0,
|
|
"step": 3420
|
|
},
|
|
{
|
|
"entropy": 6.803180170059204,
|
|
"epoch": 0.6682274900009755,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004974212215878435,
|
|
"loss": 6.8159,
|
|
"mean_token_accuracy": 0.1159481205046177,
|
|
"num_tokens": 11440011.0,
|
|
"step": 3425
|
|
},
|
|
{
|
|
"entropy": 6.8443480968475345,
|
|
"epoch": 0.6692030045849185,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004974105925646213,
|
|
"loss": 6.804,
|
|
"mean_token_accuracy": 0.11974711194634438,
|
|
"num_tokens": 11456131.0,
|
|
"step": 3430
|
|
},
|
|
{
|
|
"entropy": 6.740056133270263,
|
|
"epoch": 0.6701785191688616,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004973999418082287,
|
|
"loss": 6.7388,
|
|
"mean_token_accuracy": 0.11901577860116959,
|
|
"num_tokens": 11471420.0,
|
|
"step": 3435
|
|
},
|
|
{
|
|
"entropy": 6.792703628540039,
|
|
"epoch": 0.6711540337528046,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004973892693197064,
|
|
"loss": 6.6694,
|
|
"mean_token_accuracy": 0.12913597151637077,
|
|
"num_tokens": 11488453.0,
|
|
"step": 3440
|
|
},
|
|
{
|
|
"entropy": 6.832985591888428,
|
|
"epoch": 0.6721295483367477,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004973785751000974,
|
|
"loss": 6.8394,
|
|
"mean_token_accuracy": 0.11533381640911103,
|
|
"num_tokens": 11505144.0,
|
|
"step": 3445
|
|
},
|
|
{
|
|
"entropy": 6.809585237503052,
|
|
"epoch": 0.6731050629206906,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004973678591504464,
|
|
"loss": 6.789,
|
|
"mean_token_accuracy": 0.11653169542551041,
|
|
"num_tokens": 11521249.0,
|
|
"step": 3450
|
|
},
|
|
{
|
|
"entropy": 6.708143949508667,
|
|
"epoch": 0.6740805775046337,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000497357121471801,
|
|
"loss": 6.717,
|
|
"mean_token_accuracy": 0.12129049971699715,
|
|
"num_tokens": 11537977.0,
|
|
"step": 3455
|
|
},
|
|
{
|
|
"entropy": 6.79323377609253,
|
|
"epoch": 0.6750560920885768,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.00049734636206521,
|
|
"loss": 6.7687,
|
|
"mean_token_accuracy": 0.11533507481217384,
|
|
"num_tokens": 11556642.0,
|
|
"step": 3460
|
|
},
|
|
{
|
|
"entropy": 6.8568257808685305,
|
|
"epoch": 0.6760316066725197,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.000497335580931725,
|
|
"loss": 6.9302,
|
|
"mean_token_accuracy": 0.11058564111590385,
|
|
"num_tokens": 11574727.0,
|
|
"step": 3465
|
|
},
|
|
{
|
|
"entropy": 6.768952512741089,
|
|
"epoch": 0.6770071212564628,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004973247780723995,
|
|
"loss": 6.6373,
|
|
"mean_token_accuracy": 0.12921419739723206,
|
|
"num_tokens": 11592982.0,
|
|
"step": 3470
|
|
},
|
|
{
|
|
"entropy": 6.677181434631348,
|
|
"epoch": 0.6779826358404059,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004973139534882891,
|
|
"loss": 6.7103,
|
|
"mean_token_accuracy": 0.13103846237063407,
|
|
"num_tokens": 11609250.0,
|
|
"step": 3475
|
|
},
|
|
{
|
|
"entropy": 6.858221530914307,
|
|
"epoch": 0.6789581504243488,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004973031071804515,
|
|
"loss": 6.7437,
|
|
"mean_token_accuracy": 0.11711718887090683,
|
|
"num_tokens": 11626269.0,
|
|
"step": 3480
|
|
},
|
|
{
|
|
"entropy": 6.7978660583496096,
|
|
"epoch": 0.6799336650082919,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004972922391499465,
|
|
"loss": 6.7533,
|
|
"mean_token_accuracy": 0.1171741932630539,
|
|
"num_tokens": 11642721.0,
|
|
"step": 3485
|
|
},
|
|
{
|
|
"entropy": 6.655276918411255,
|
|
"epoch": 0.680909179592235,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004972813493978361,
|
|
"loss": 6.6812,
|
|
"mean_token_accuracy": 0.12508639469742774,
|
|
"num_tokens": 11659729.0,
|
|
"step": 3490
|
|
},
|
|
{
|
|
"entropy": 6.819024229049683,
|
|
"epoch": 0.6818846941761779,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004972704379251845,
|
|
"loss": 6.6994,
|
|
"mean_token_accuracy": 0.11821742653846741,
|
|
"num_tokens": 11675568.0,
|
|
"step": 3495
|
|
},
|
|
{
|
|
"entropy": 6.786591529846191,
|
|
"epoch": 0.682860208760121,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.000497259504733058,
|
|
"loss": 6.8149,
|
|
"mean_token_accuracy": 0.12347409054636956,
|
|
"num_tokens": 11692827.0,
|
|
"step": 3500
|
|
},
|
|
{
|
|
"entropy": 6.836846399307251,
|
|
"epoch": 0.683835723344064,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004972485498225247,
|
|
"loss": 6.7889,
|
|
"mean_token_accuracy": 0.11375942602753639,
|
|
"num_tokens": 11708730.0,
|
|
"step": 3505
|
|
},
|
|
{
|
|
"entropy": 6.791144609451294,
|
|
"epoch": 0.684811237928007,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004972375731946554,
|
|
"loss": 6.765,
|
|
"mean_token_accuracy": 0.11388128846883774,
|
|
"num_tokens": 11725031.0,
|
|
"step": 3510
|
|
},
|
|
{
|
|
"entropy": 6.8500282764434814,
|
|
"epoch": 0.6857867525119501,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004972265748505224,
|
|
"loss": 6.8459,
|
|
"mean_token_accuracy": 0.11484316736459732,
|
|
"num_tokens": 11742419.0,
|
|
"step": 3515
|
|
},
|
|
{
|
|
"entropy": 6.78658618927002,
|
|
"epoch": 0.686762267095893,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004972155547912005,
|
|
"loss": 6.722,
|
|
"mean_token_accuracy": 0.1189639039337635,
|
|
"num_tokens": 11757474.0,
|
|
"step": 3520
|
|
},
|
|
{
|
|
"entropy": 6.910969591140747,
|
|
"epoch": 0.6877377816798361,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004972045130177666,
|
|
"loss": 6.8099,
|
|
"mean_token_accuracy": 0.11256312653422355,
|
|
"num_tokens": 11774467.0,
|
|
"step": 3525
|
|
},
|
|
{
|
|
"entropy": 6.744571208953857,
|
|
"epoch": 0.6887132962637792,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004971934495312996,
|
|
"loss": 6.7036,
|
|
"mean_token_accuracy": 0.12474005371332168,
|
|
"num_tokens": 11790597.0,
|
|
"step": 3530
|
|
},
|
|
{
|
|
"entropy": 6.799027061462402,
|
|
"epoch": 0.6896888108477222,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004971823643328807,
|
|
"loss": 6.698,
|
|
"mean_token_accuracy": 0.1301779679954052,
|
|
"num_tokens": 11806459.0,
|
|
"step": 3535
|
|
},
|
|
{
|
|
"entropy": 6.70832052230835,
|
|
"epoch": 0.6906643254316652,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000497171257423593,
|
|
"loss": 6.7723,
|
|
"mean_token_accuracy": 0.11867458820343017,
|
|
"num_tokens": 11823410.0,
|
|
"step": 3540
|
|
},
|
|
{
|
|
"entropy": 6.855541467666626,
|
|
"epoch": 0.6916398400156082,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004971601288045219,
|
|
"loss": 6.7572,
|
|
"mean_token_accuracy": 0.11353341564536094,
|
|
"num_tokens": 11838684.0,
|
|
"step": 3545
|
|
},
|
|
{
|
|
"entropy": 6.770979261398315,
|
|
"epoch": 0.6926153545995513,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004971489784767547,
|
|
"loss": 6.7535,
|
|
"mean_token_accuracy": 0.12208975777029991,
|
|
"num_tokens": 11854324.0,
|
|
"step": 3550
|
|
},
|
|
{
|
|
"entropy": 6.759768009185791,
|
|
"epoch": 0.6935908691834943,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004971378064413813,
|
|
"loss": 6.7501,
|
|
"mean_token_accuracy": 0.11917683184146881,
|
|
"num_tokens": 11871992.0,
|
|
"step": 3555
|
|
},
|
|
{
|
|
"entropy": 6.8846478939056395,
|
|
"epoch": 0.6945663837674373,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004971266126994929,
|
|
"loss": 6.8525,
|
|
"mean_token_accuracy": 0.11340126171708106,
|
|
"num_tokens": 11889195.0,
|
|
"step": 3560
|
|
},
|
|
{
|
|
"entropy": 6.808067083358765,
|
|
"epoch": 0.6955418983513804,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004971153972521837,
|
|
"loss": 6.8449,
|
|
"mean_token_accuracy": 0.11085446551442146,
|
|
"num_tokens": 11906316.0,
|
|
"step": 3565
|
|
},
|
|
{
|
|
"entropy": 6.814440298080444,
|
|
"epoch": 0.6965174129353234,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004971041601005495,
|
|
"loss": 6.844,
|
|
"mean_token_accuracy": 0.11176281869411468,
|
|
"num_tokens": 11924097.0,
|
|
"step": 3570
|
|
},
|
|
{
|
|
"entropy": 6.911610507965088,
|
|
"epoch": 0.6974929275192664,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004970929012456884,
|
|
"loss": 6.8477,
|
|
"mean_token_accuracy": 0.11460289284586907,
|
|
"num_tokens": 11942344.0,
|
|
"step": 3575
|
|
},
|
|
{
|
|
"entropy": 6.758803224563598,
|
|
"epoch": 0.6984684421032095,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004970816206887005,
|
|
"loss": 6.6734,
|
|
"mean_token_accuracy": 0.12892143800854683,
|
|
"num_tokens": 11959045.0,
|
|
"step": 3580
|
|
},
|
|
{
|
|
"entropy": 6.746231603622436,
|
|
"epoch": 0.6994439566871524,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004970703184306881,
|
|
"loss": 6.7159,
|
|
"mean_token_accuracy": 0.11938348487019539,
|
|
"num_tokens": 11976244.0,
|
|
"step": 3585
|
|
},
|
|
{
|
|
"entropy": 6.839864778518677,
|
|
"epoch": 0.7004194712710955,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004970589944727558,
|
|
"loss": 6.7576,
|
|
"mean_token_accuracy": 0.11265199854969979,
|
|
"num_tokens": 11993644.0,
|
|
"step": 3590
|
|
},
|
|
{
|
|
"entropy": 6.7174201011657715,
|
|
"epoch": 0.7013949858550386,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004970476488160098,
|
|
"loss": 6.6646,
|
|
"mean_token_accuracy": 0.12267008423805237,
|
|
"num_tokens": 12010419.0,
|
|
"step": 3595
|
|
},
|
|
{
|
|
"entropy": 6.732359600067139,
|
|
"epoch": 0.7023705004389815,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004970362814615592,
|
|
"loss": 6.6888,
|
|
"mean_token_accuracy": 0.12445817664265632,
|
|
"num_tokens": 12027199.0,
|
|
"step": 3600
|
|
},
|
|
{
|
|
"entropy": 6.635884618759155,
|
|
"epoch": 0.7033460150229246,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004970248924105144,
|
|
"loss": 6.6855,
|
|
"mean_token_accuracy": 0.1271976575255394,
|
|
"num_tokens": 12044267.0,
|
|
"step": 3605
|
|
},
|
|
{
|
|
"entropy": 6.864033126831055,
|
|
"epoch": 0.7043215296068677,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004970134816639884,
|
|
"loss": 6.7513,
|
|
"mean_token_accuracy": 0.11400457099080086,
|
|
"num_tokens": 12062838.0,
|
|
"step": 3610
|
|
},
|
|
{
|
|
"entropy": 6.800624942779541,
|
|
"epoch": 0.7052970441908106,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004970020492230963,
|
|
"loss": 6.8262,
|
|
"mean_token_accuracy": 0.11326520815491677,
|
|
"num_tokens": 12079144.0,
|
|
"step": 3615
|
|
},
|
|
{
|
|
"entropy": 6.75108699798584,
|
|
"epoch": 0.7062725587747537,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.000496990595088955,
|
|
"loss": 6.6825,
|
|
"mean_token_accuracy": 0.1265578031539917,
|
|
"num_tokens": 12096477.0,
|
|
"step": 3620
|
|
},
|
|
{
|
|
"entropy": 6.806216096878051,
|
|
"epoch": 0.7072480733586967,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004969791192626841,
|
|
"loss": 6.7273,
|
|
"mean_token_accuracy": 0.12237825244665146,
|
|
"num_tokens": 12113307.0,
|
|
"step": 3625
|
|
},
|
|
{
|
|
"entropy": 6.787025499343872,
|
|
"epoch": 0.7082235879426397,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004969676217454048,
|
|
"loss": 6.8651,
|
|
"mean_token_accuracy": 0.11767023876309395,
|
|
"num_tokens": 12131814.0,
|
|
"step": 3630
|
|
},
|
|
{
|
|
"entropy": 6.869916296005249,
|
|
"epoch": 0.7091991025265828,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004969561025382405,
|
|
"loss": 6.6789,
|
|
"mean_token_accuracy": 0.11936165541410446,
|
|
"num_tokens": 12147110.0,
|
|
"step": 3635
|
|
},
|
|
{
|
|
"entropy": 6.638847494125367,
|
|
"epoch": 0.7101746171105258,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004969445616423171,
|
|
"loss": 6.6544,
|
|
"mean_token_accuracy": 0.12048555612564087,
|
|
"num_tokens": 12162954.0,
|
|
"step": 3640
|
|
},
|
|
{
|
|
"entropy": 6.667431879043579,
|
|
"epoch": 0.7111501316944688,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000496932999058762,
|
|
"loss": 6.5692,
|
|
"mean_token_accuracy": 0.12412386685609818,
|
|
"num_tokens": 12181169.0,
|
|
"step": 3645
|
|
},
|
|
{
|
|
"entropy": 6.880050086975098,
|
|
"epoch": 0.7121256462784119,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004969214147887053,
|
|
"loss": 6.899,
|
|
"mean_token_accuracy": 0.11512195393443107,
|
|
"num_tokens": 12198367.0,
|
|
"step": 3650
|
|
},
|
|
{
|
|
"entropy": 6.732449722290039,
|
|
"epoch": 0.7131011608623549,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004969098088332789,
|
|
"loss": 6.6998,
|
|
"mean_token_accuracy": 0.12247187048196792,
|
|
"num_tokens": 12215614.0,
|
|
"step": 3655
|
|
},
|
|
{
|
|
"entropy": 6.7817481517791744,
|
|
"epoch": 0.7140766754462979,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004968981811936169,
|
|
"loss": 6.6811,
|
|
"mean_token_accuracy": 0.12360340207815171,
|
|
"num_tokens": 12232123.0,
|
|
"step": 3660
|
|
},
|
|
{
|
|
"entropy": 6.733463907241822,
|
|
"epoch": 0.7150521900302409,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004968865318708555,
|
|
"loss": 6.7833,
|
|
"mean_token_accuracy": 0.11817984133958817,
|
|
"num_tokens": 12248417.0,
|
|
"step": 3665
|
|
},
|
|
{
|
|
"entropy": 6.836424541473389,
|
|
"epoch": 0.716027704614184,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004968748608661328,
|
|
"loss": 6.7228,
|
|
"mean_token_accuracy": 0.11769269406795502,
|
|
"num_tokens": 12264388.0,
|
|
"step": 3670
|
|
},
|
|
{
|
|
"entropy": 6.777669239044189,
|
|
"epoch": 0.717003219198127,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004968631681805897,
|
|
"loss": 6.7809,
|
|
"mean_token_accuracy": 0.11273467019200326,
|
|
"num_tokens": 12282157.0,
|
|
"step": 3675
|
|
},
|
|
{
|
|
"entropy": 6.825763845443726,
|
|
"epoch": 0.71797873378207,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004968514538153685,
|
|
"loss": 6.776,
|
|
"mean_token_accuracy": 0.11356953755021096,
|
|
"num_tokens": 12298368.0,
|
|
"step": 3680
|
|
},
|
|
{
|
|
"entropy": 6.691401529312134,
|
|
"epoch": 0.7189542483660131,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000496839717771614,
|
|
"loss": 6.7202,
|
|
"mean_token_accuracy": 0.12515802308917046,
|
|
"num_tokens": 12314860.0,
|
|
"step": 3685
|
|
},
|
|
{
|
|
"entropy": 6.8083117485046385,
|
|
"epoch": 0.7199297629499561,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004968279600504729,
|
|
"loss": 6.7077,
|
|
"mean_token_accuracy": 0.11886250749230384,
|
|
"num_tokens": 12331424.0,
|
|
"step": 3690
|
|
},
|
|
{
|
|
"entropy": 6.780414819717407,
|
|
"epoch": 0.7209052775338991,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000496816180653094,
|
|
"loss": 6.8256,
|
|
"mean_token_accuracy": 0.1168772540986538,
|
|
"num_tokens": 12348358.0,
|
|
"step": 3695
|
|
},
|
|
{
|
|
"entropy": 6.821427059173584,
|
|
"epoch": 0.7218807921178422,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004968043795806285,
|
|
"loss": 6.7389,
|
|
"mean_token_accuracy": 0.12133604064583778,
|
|
"num_tokens": 12364932.0,
|
|
"step": 3700
|
|
},
|
|
{
|
|
"entropy": 6.7891761302948,
|
|
"epoch": 0.7228563067017852,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004967925568342297,
|
|
"loss": 6.7955,
|
|
"mean_token_accuracy": 0.11829720437526703,
|
|
"num_tokens": 12381852.0,
|
|
"step": 3705
|
|
},
|
|
{
|
|
"entropy": 6.782630777359008,
|
|
"epoch": 0.7238318212857282,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004967807124150527,
|
|
"loss": 6.7906,
|
|
"mean_token_accuracy": 0.11280990019440651,
|
|
"num_tokens": 12397164.0,
|
|
"step": 3710
|
|
},
|
|
{
|
|
"entropy": 6.764940166473389,
|
|
"epoch": 0.7248073358696713,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004967688463242549,
|
|
"loss": 6.7471,
|
|
"mean_token_accuracy": 0.12165748104453086,
|
|
"num_tokens": 12412520.0,
|
|
"step": 3715
|
|
},
|
|
{
|
|
"entropy": 6.788241720199585,
|
|
"epoch": 0.7257828504536142,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004967569585629958,
|
|
"loss": 6.7549,
|
|
"mean_token_accuracy": 0.1214120127260685,
|
|
"num_tokens": 12427039.0,
|
|
"step": 3720
|
|
},
|
|
{
|
|
"entropy": 6.805818223953247,
|
|
"epoch": 0.7267583650375573,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004967450491324371,
|
|
"loss": 6.7347,
|
|
"mean_token_accuracy": 0.11801778674125671,
|
|
"num_tokens": 12441903.0,
|
|
"step": 3725
|
|
},
|
|
{
|
|
"entropy": 6.697656297683716,
|
|
"epoch": 0.7277338796215004,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004967331180337425,
|
|
"loss": 6.6266,
|
|
"mean_token_accuracy": 0.12944651171565055,
|
|
"num_tokens": 12458883.0,
|
|
"step": 3730
|
|
},
|
|
{
|
|
"entropy": 6.761776256561279,
|
|
"epoch": 0.7287093942054433,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004967211652680779,
|
|
"loss": 6.794,
|
|
"mean_token_accuracy": 0.11859319433569908,
|
|
"num_tokens": 12475347.0,
|
|
"step": 3735
|
|
},
|
|
{
|
|
"entropy": 6.806973648071289,
|
|
"epoch": 0.7296849087893864,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004967091908366113,
|
|
"loss": 6.8078,
|
|
"mean_token_accuracy": 0.10862454399466515,
|
|
"num_tokens": 12490393.0,
|
|
"step": 3740
|
|
},
|
|
{
|
|
"entropy": 6.813240242004395,
|
|
"epoch": 0.7306604233733295,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004966971947405127,
|
|
"loss": 6.7694,
|
|
"mean_token_accuracy": 0.12506349757313728,
|
|
"num_tokens": 12505679.0,
|
|
"step": 3745
|
|
},
|
|
{
|
|
"entropy": 6.734861612319946,
|
|
"epoch": 0.7316359379572724,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004966851769809543,
|
|
"loss": 6.7332,
|
|
"mean_token_accuracy": 0.1219899483025074,
|
|
"num_tokens": 12522316.0,
|
|
"step": 3750
|
|
},
|
|
{
|
|
"entropy": 6.841101360321045,
|
|
"epoch": 0.7326114525412155,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004966731375591106,
|
|
"loss": 6.8163,
|
|
"mean_token_accuracy": 0.11920790374279022,
|
|
"num_tokens": 12539638.0,
|
|
"step": 3755
|
|
},
|
|
{
|
|
"entropy": 6.724351072311402,
|
|
"epoch": 0.7335869671251585,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004966610764761579,
|
|
"loss": 6.6783,
|
|
"mean_token_accuracy": 0.12096166461706162,
|
|
"num_tokens": 12556296.0,
|
|
"step": 3760
|
|
},
|
|
{
|
|
"entropy": 6.8287938117980955,
|
|
"epoch": 0.7345624817091015,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004966489937332748,
|
|
"loss": 6.77,
|
|
"mean_token_accuracy": 0.11994385421276092,
|
|
"num_tokens": 12573248.0,
|
|
"step": 3765
|
|
},
|
|
{
|
|
"entropy": 6.681254959106445,
|
|
"epoch": 0.7355379962930446,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004966368893316421,
|
|
"loss": 6.5765,
|
|
"mean_token_accuracy": 0.1358570449054241,
|
|
"num_tokens": 12590918.0,
|
|
"step": 3770
|
|
},
|
|
{
|
|
"entropy": 6.664647769927979,
|
|
"epoch": 0.7365135108769876,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004966247632724425,
|
|
"loss": 6.7027,
|
|
"mean_token_accuracy": 0.12417802438139916,
|
|
"num_tokens": 12607037.0,
|
|
"step": 3775
|
|
},
|
|
{
|
|
"entropy": 6.652344560623169,
|
|
"epoch": 0.7374890254609306,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004966126155568609,
|
|
"loss": 6.6685,
|
|
"mean_token_accuracy": 0.12528103291988374,
|
|
"num_tokens": 12623934.0,
|
|
"step": 3780
|
|
},
|
|
{
|
|
"entropy": 6.739942312240601,
|
|
"epoch": 0.7384645400448737,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004966004461860843,
|
|
"loss": 6.6484,
|
|
"mean_token_accuracy": 0.13267690390348436,
|
|
"num_tokens": 12640607.0,
|
|
"step": 3785
|
|
},
|
|
{
|
|
"entropy": 6.791224431991577,
|
|
"epoch": 0.7394400546288167,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004965882551613019,
|
|
"loss": 6.6993,
|
|
"mean_token_accuracy": 0.11643879413604737,
|
|
"num_tokens": 12656671.0,
|
|
"step": 3790
|
|
},
|
|
{
|
|
"entropy": 6.7684379577636715,
|
|
"epoch": 0.7404155692127597,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000496576042483705,
|
|
"loss": 6.7871,
|
|
"mean_token_accuracy": 0.10826998054981232,
|
|
"num_tokens": 12673271.0,
|
|
"step": 3795
|
|
},
|
|
{
|
|
"entropy": 6.636662578582763,
|
|
"epoch": 0.7413910837967027,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004965638081544869,
|
|
"loss": 6.6274,
|
|
"mean_token_accuracy": 0.13479933515191078,
|
|
"num_tokens": 12691005.0,
|
|
"step": 3800
|
|
},
|
|
{
|
|
"entropy": 6.805237865447998,
|
|
"epoch": 0.7423665983806458,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004965515521748432,
|
|
"loss": 6.7553,
|
|
"mean_token_accuracy": 0.1200227439403534,
|
|
"num_tokens": 12706170.0,
|
|
"step": 3805
|
|
},
|
|
{
|
|
"entropy": 6.67332091331482,
|
|
"epoch": 0.7433421129645889,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004965392745459714,
|
|
"loss": 6.6502,
|
|
"mean_token_accuracy": 0.1258610777556896,
|
|
"num_tokens": 12722794.0,
|
|
"step": 3810
|
|
},
|
|
{
|
|
"entropy": 6.828030967712403,
|
|
"epoch": 0.7443176275485318,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004965269752690713,
|
|
"loss": 6.7709,
|
|
"mean_token_accuracy": 0.11361561119556426,
|
|
"num_tokens": 12739676.0,
|
|
"step": 3815
|
|
},
|
|
{
|
|
"entropy": 6.777934741973877,
|
|
"epoch": 0.7452931421324749,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004965146543453446,
|
|
"loss": 6.7815,
|
|
"mean_token_accuracy": 0.1157730832695961,
|
|
"num_tokens": 12756231.0,
|
|
"step": 3820
|
|
},
|
|
{
|
|
"entropy": 6.5929851055145265,
|
|
"epoch": 0.746268656716418,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004965023117759954,
|
|
"loss": 6.6042,
|
|
"mean_token_accuracy": 0.13663500174880028,
|
|
"num_tokens": 12771877.0,
|
|
"step": 3825
|
|
},
|
|
{
|
|
"entropy": 6.808469629287719,
|
|
"epoch": 0.7472441713003609,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004964899475622299,
|
|
"loss": 6.7332,
|
|
"mean_token_accuracy": 0.11765263751149177,
|
|
"num_tokens": 12790698.0,
|
|
"step": 3830
|
|
},
|
|
{
|
|
"entropy": 6.7798467636108395,
|
|
"epoch": 0.748219685884304,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000496477561705256,
|
|
"loss": 6.7476,
|
|
"mean_token_accuracy": 0.11698138862848281,
|
|
"num_tokens": 12806160.0,
|
|
"step": 3835
|
|
},
|
|
{
|
|
"entropy": 6.797970008850098,
|
|
"epoch": 0.749195200468247,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004964651542062841,
|
|
"loss": 6.7946,
|
|
"mean_token_accuracy": 0.11112525835633277,
|
|
"num_tokens": 12822382.0,
|
|
"step": 3840
|
|
},
|
|
{
|
|
"entropy": 6.821391296386719,
|
|
"epoch": 0.75017071505219,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004964527250665268,
|
|
"loss": 6.7189,
|
|
"mean_token_accuracy": 0.12206549495458603,
|
|
"num_tokens": 12839421.0,
|
|
"step": 3845
|
|
},
|
|
{
|
|
"entropy": 6.679543161392212,
|
|
"epoch": 0.7511462296361331,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004964402742871983,
|
|
"loss": 6.5475,
|
|
"mean_token_accuracy": 0.13399601727724075,
|
|
"num_tokens": 12856609.0,
|
|
"step": 3850
|
|
},
|
|
{
|
|
"entropy": 6.760881471633911,
|
|
"epoch": 0.752121744220076,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004964278018695156,
|
|
"loss": 6.7486,
|
|
"mean_token_accuracy": 0.11472928673028945,
|
|
"num_tokens": 12871659.0,
|
|
"step": 3855
|
|
},
|
|
{
|
|
"entropy": 6.769639348983764,
|
|
"epoch": 0.7530972588040191,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004964153078146971,
|
|
"loss": 6.7369,
|
|
"mean_token_accuracy": 0.11840879917144775,
|
|
"num_tokens": 12889029.0,
|
|
"step": 3860
|
|
},
|
|
{
|
|
"entropy": 6.736374759674073,
|
|
"epoch": 0.7540727733879622,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004964027921239639,
|
|
"loss": 6.7045,
|
|
"mean_token_accuracy": 0.12693476006388665,
|
|
"num_tokens": 12905735.0,
|
|
"step": 3865
|
|
},
|
|
{
|
|
"entropy": 6.758614540100098,
|
|
"epoch": 0.7550482879719052,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000496390254798539,
|
|
"loss": 6.6904,
|
|
"mean_token_accuracy": 0.1233099102973938,
|
|
"num_tokens": 12921886.0,
|
|
"step": 3870
|
|
},
|
|
{
|
|
"entropy": 6.657391500473023,
|
|
"epoch": 0.7560238025558482,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004963776958396475,
|
|
"loss": 6.6293,
|
|
"mean_token_accuracy": 0.12961574792861938,
|
|
"num_tokens": 12938658.0,
|
|
"step": 3875
|
|
},
|
|
{
|
|
"entropy": 6.776090812683106,
|
|
"epoch": 0.7569993171397913,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004963651152485165,
|
|
"loss": 6.7836,
|
|
"mean_token_accuracy": 0.117157681286335,
|
|
"num_tokens": 12955788.0,
|
|
"step": 3880
|
|
},
|
|
{
|
|
"entropy": 6.6640403270721436,
|
|
"epoch": 0.7579748317237343,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004963525130263753,
|
|
"loss": 6.6125,
|
|
"mean_token_accuracy": 0.12636376842856406,
|
|
"num_tokens": 12972590.0,
|
|
"step": 3885
|
|
},
|
|
{
|
|
"entropy": 6.837289428710937,
|
|
"epoch": 0.7589503463076773,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004963398891744557,
|
|
"loss": 6.7364,
|
|
"mean_token_accuracy": 0.11580163910984993,
|
|
"num_tokens": 12989560.0,
|
|
"step": 3890
|
|
},
|
|
{
|
|
"entropy": 6.763892412185669,
|
|
"epoch": 0.7599258608916203,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004963272436939908,
|
|
"loss": 6.6966,
|
|
"mean_token_accuracy": 0.12822128161787988,
|
|
"num_tokens": 13005584.0,
|
|
"step": 3895
|
|
},
|
|
{
|
|
"entropy": 6.744999647140503,
|
|
"epoch": 0.7609013754755634,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004963145765862166,
|
|
"loss": 6.7632,
|
|
"mean_token_accuracy": 0.11568630561232567,
|
|
"num_tokens": 13021635.0,
|
|
"step": 3900
|
|
},
|
|
{
|
|
"entropy": 6.74825086593628,
|
|
"epoch": 0.7618768900595064,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004963018878523706,
|
|
"loss": 6.6711,
|
|
"mean_token_accuracy": 0.12459334060549736,
|
|
"num_tokens": 13037838.0,
|
|
"step": 3905
|
|
},
|
|
{
|
|
"entropy": 6.6404791355133055,
|
|
"epoch": 0.7628524046434494,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004962891774936929,
|
|
"loss": 6.6295,
|
|
"mean_token_accuracy": 0.1281932219862938,
|
|
"num_tokens": 13054596.0,
|
|
"step": 3910
|
|
},
|
|
{
|
|
"entropy": 6.7271068572998045,
|
|
"epoch": 0.7638279192273925,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004962764455114255,
|
|
"loss": 6.6721,
|
|
"mean_token_accuracy": 0.12489277943968773,
|
|
"num_tokens": 13070462.0,
|
|
"step": 3915
|
|
},
|
|
{
|
|
"entropy": 6.688215589523315,
|
|
"epoch": 0.7648034338113355,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004962636919068125,
|
|
"loss": 6.6323,
|
|
"mean_token_accuracy": 0.12610245123505592,
|
|
"num_tokens": 13086686.0,
|
|
"step": 3920
|
|
},
|
|
{
|
|
"entropy": 6.797585153579712,
|
|
"epoch": 0.7657789483952785,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004962509166811001,
|
|
"loss": 6.7729,
|
|
"mean_token_accuracy": 0.11477677449584008,
|
|
"num_tokens": 13102430.0,
|
|
"step": 3925
|
|
},
|
|
{
|
|
"entropy": 6.697382831573487,
|
|
"epoch": 0.7667544629792216,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004962381198355367,
|
|
"loss": 6.6661,
|
|
"mean_token_accuracy": 0.12673756256699562,
|
|
"num_tokens": 13118944.0,
|
|
"step": 3930
|
|
},
|
|
{
|
|
"entropy": 6.766244792938233,
|
|
"epoch": 0.7677299775631645,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004962253013713726,
|
|
"loss": 6.7012,
|
|
"mean_token_accuracy": 0.1196364089846611,
|
|
"num_tokens": 13136393.0,
|
|
"step": 3935
|
|
},
|
|
{
|
|
"entropy": 6.759472370147705,
|
|
"epoch": 0.7687054921471076,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004962124612898607,
|
|
"loss": 6.766,
|
|
"mean_token_accuracy": 0.11796955838799476,
|
|
"num_tokens": 13153834.0,
|
|
"step": 3940
|
|
},
|
|
{
|
|
"entropy": 6.718040132522583,
|
|
"epoch": 0.7696810067310507,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004961995995922553,
|
|
"loss": 6.6143,
|
|
"mean_token_accuracy": 0.12660875543951988,
|
|
"num_tokens": 13170904.0,
|
|
"step": 3945
|
|
},
|
|
{
|
|
"entropy": 6.80735673904419,
|
|
"epoch": 0.7706565213149936,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004961867162798136,
|
|
"loss": 6.7234,
|
|
"mean_token_accuracy": 0.11786188408732415,
|
|
"num_tokens": 13187274.0,
|
|
"step": 3950
|
|
},
|
|
{
|
|
"entropy": 6.634725093841553,
|
|
"epoch": 0.7716320358989367,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004961738113537943,
|
|
"loss": 6.6851,
|
|
"mean_token_accuracy": 0.12893542572855948,
|
|
"num_tokens": 13203448.0,
|
|
"step": 3955
|
|
},
|
|
{
|
|
"entropy": 6.790357828140259,
|
|
"epoch": 0.7726075504828798,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004961608848154583,
|
|
"loss": 6.7075,
|
|
"mean_token_accuracy": 0.11817660257220268,
|
|
"num_tokens": 13220460.0,
|
|
"step": 3960
|
|
},
|
|
{
|
|
"entropy": 6.718967390060425,
|
|
"epoch": 0.7735830650668227,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.000496147936666069,
|
|
"loss": 6.6598,
|
|
"mean_token_accuracy": 0.12472839578986168,
|
|
"num_tokens": 13237502.0,
|
|
"step": 3965
|
|
},
|
|
{
|
|
"entropy": 6.729021263122559,
|
|
"epoch": 0.7745585796507658,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004961349669068913,
|
|
"loss": 6.7015,
|
|
"mean_token_accuracy": 0.11904591247439385,
|
|
"num_tokens": 13254314.0,
|
|
"step": 3970
|
|
},
|
|
{
|
|
"entropy": 6.775465393066407,
|
|
"epoch": 0.7755340942347088,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000496121975539193,
|
|
"loss": 6.7943,
|
|
"mean_token_accuracy": 0.11937612965703011,
|
|
"num_tokens": 13271737.0,
|
|
"step": 3975
|
|
},
|
|
{
|
|
"entropy": 6.7876416683197025,
|
|
"epoch": 0.7765096088186518,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004961089625642433,
|
|
"loss": 6.716,
|
|
"mean_token_accuracy": 0.12027950659394264,
|
|
"num_tokens": 13288546.0,
|
|
"step": 3980
|
|
},
|
|
{
|
|
"entropy": 6.728000688552856,
|
|
"epoch": 0.7774851234025949,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004960959279833137,
|
|
"loss": 6.6282,
|
|
"mean_token_accuracy": 0.1268797516822815,
|
|
"num_tokens": 13304309.0,
|
|
"step": 3985
|
|
},
|
|
{
|
|
"entropy": 6.715612697601318,
|
|
"epoch": 0.7784606379865379,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004960828717976781,
|
|
"loss": 6.6915,
|
|
"mean_token_accuracy": 0.12041431367397308,
|
|
"num_tokens": 13319797.0,
|
|
"step": 3990
|
|
},
|
|
{
|
|
"entropy": 6.604159641265869,
|
|
"epoch": 0.7794361525704809,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004960697940086121,
|
|
"loss": 6.5165,
|
|
"mean_token_accuracy": 0.13471487611532212,
|
|
"num_tokens": 13336040.0,
|
|
"step": 3995
|
|
},
|
|
{
|
|
"entropy": 6.788204956054687,
|
|
"epoch": 0.780411667154424,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004960566946173939,
|
|
"loss": 6.6926,
|
|
"mean_token_accuracy": 0.1225688099861145,
|
|
"num_tokens": 13352762.0,
|
|
"step": 4000
|
|
},
|
|
{
|
|
"entropy": 6.7109339237213135,
|
|
"epoch": 0.781387181738367,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004960435736253034,
|
|
"loss": 6.6622,
|
|
"mean_token_accuracy": 0.12224569097161293,
|
|
"num_tokens": 13368577.0,
|
|
"step": 4005
|
|
},
|
|
{
|
|
"entropy": 6.794810390472412,
|
|
"epoch": 0.78236269632231,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004960304310336226,
|
|
"loss": 6.7857,
|
|
"mean_token_accuracy": 0.11249362006783485,
|
|
"num_tokens": 13384170.0,
|
|
"step": 4010
|
|
},
|
|
{
|
|
"entropy": 6.672754859924316,
|
|
"epoch": 0.783338210906253,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004960172668436359,
|
|
"loss": 6.5892,
|
|
"mean_token_accuracy": 0.13162605240941047,
|
|
"num_tokens": 13400143.0,
|
|
"step": 4015
|
|
},
|
|
{
|
|
"entropy": 6.741737031936646,
|
|
"epoch": 0.7843137254901961,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004960040810566295,
|
|
"loss": 6.6906,
|
|
"mean_token_accuracy": 0.11996093839406967,
|
|
"num_tokens": 13416553.0,
|
|
"step": 4020
|
|
},
|
|
{
|
|
"entropy": 6.670932960510254,
|
|
"epoch": 0.7852892400741391,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004959908736738921,
|
|
"loss": 6.7033,
|
|
"mean_token_accuracy": 0.11937930807471275,
|
|
"num_tokens": 13432694.0,
|
|
"step": 4025
|
|
},
|
|
{
|
|
"entropy": 6.798852443695068,
|
|
"epoch": 0.7862647546580821,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004959776446967141,
|
|
"loss": 6.717,
|
|
"mean_token_accuracy": 0.11765834838151931,
|
|
"num_tokens": 13450333.0,
|
|
"step": 4030
|
|
},
|
|
{
|
|
"entropy": 6.558846807479858,
|
|
"epoch": 0.7872402692420252,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004959643941263882,
|
|
"loss": 6.5239,
|
|
"mean_token_accuracy": 0.13116379976272582,
|
|
"num_tokens": 13467150.0,
|
|
"step": 4035
|
|
},
|
|
{
|
|
"entropy": 6.726905393600464,
|
|
"epoch": 0.7882157838259682,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004959511219642092,
|
|
"loss": 6.6858,
|
|
"mean_token_accuracy": 0.12244507521390915,
|
|
"num_tokens": 13484796.0,
|
|
"step": 4040
|
|
},
|
|
{
|
|
"entropy": 6.744570350646972,
|
|
"epoch": 0.7891912984099112,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004959378282114741,
|
|
"loss": 6.616,
|
|
"mean_token_accuracy": 0.12753701359033584,
|
|
"num_tokens": 13501533.0,
|
|
"step": 4045
|
|
},
|
|
{
|
|
"entropy": 6.745242929458618,
|
|
"epoch": 0.7901668129938543,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004959245128694819,
|
|
"loss": 6.79,
|
|
"mean_token_accuracy": 0.11227769255638123,
|
|
"num_tokens": 13518270.0,
|
|
"step": 4050
|
|
},
|
|
{
|
|
"entropy": 6.639493465423584,
|
|
"epoch": 0.7911423275777972,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004959111759395337,
|
|
"loss": 6.5576,
|
|
"mean_token_accuracy": 0.1302938900887966,
|
|
"num_tokens": 13535356.0,
|
|
"step": 4055
|
|
},
|
|
{
|
|
"entropy": 6.709262371063232,
|
|
"epoch": 0.7921178421617403,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004958978174229326,
|
|
"loss": 6.6109,
|
|
"mean_token_accuracy": 0.12324444577097893,
|
|
"num_tokens": 13550530.0,
|
|
"step": 4060
|
|
},
|
|
{
|
|
"entropy": 6.625330972671509,
|
|
"epoch": 0.7930933567456834,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004958844373209843,
|
|
"loss": 6.5848,
|
|
"mean_token_accuracy": 0.13065190538764,
|
|
"num_tokens": 13569492.0,
|
|
"step": 4065
|
|
},
|
|
{
|
|
"entropy": 6.803159570693969,
|
|
"epoch": 0.7940688713296263,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004958710356349958,
|
|
"loss": 6.7924,
|
|
"mean_token_accuracy": 0.1154083989560604,
|
|
"num_tokens": 13585096.0,
|
|
"step": 4070
|
|
},
|
|
{
|
|
"entropy": 6.779484510421753,
|
|
"epoch": 0.7950443859135694,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000495857612366277,
|
|
"loss": 6.7529,
|
|
"mean_token_accuracy": 0.11882292926311493,
|
|
"num_tokens": 13600667.0,
|
|
"step": 4075
|
|
},
|
|
{
|
|
"entropy": 6.809414291381836,
|
|
"epoch": 0.7960199004975125,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004958441675161395,
|
|
"loss": 6.7873,
|
|
"mean_token_accuracy": 0.11253518834710122,
|
|
"num_tokens": 13618212.0,
|
|
"step": 4080
|
|
},
|
|
{
|
|
"entropy": 6.755683946609497,
|
|
"epoch": 0.7969954150814554,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000495830701085897,
|
|
"loss": 6.6983,
|
|
"mean_token_accuracy": 0.12447260543704033,
|
|
"num_tokens": 13634067.0,
|
|
"step": 4085
|
|
},
|
|
{
|
|
"entropy": 6.654263257980347,
|
|
"epoch": 0.7979709296653985,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004958172130768655,
|
|
"loss": 6.6462,
|
|
"mean_token_accuracy": 0.12971843555569648,
|
|
"num_tokens": 13651306.0,
|
|
"step": 4090
|
|
},
|
|
{
|
|
"entropy": 6.714829635620117,
|
|
"epoch": 0.7989464442493416,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004958037034903628,
|
|
"loss": 6.6772,
|
|
"mean_token_accuracy": 0.11633258238434792,
|
|
"num_tokens": 13667563.0,
|
|
"step": 4095
|
|
},
|
|
{
|
|
"entropy": 6.626688718795776,
|
|
"epoch": 0.7999219588332845,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004957901723277093,
|
|
"loss": 6.5717,
|
|
"mean_token_accuracy": 0.128354312479496,
|
|
"num_tokens": 13684857.0,
|
|
"step": 4100
|
|
},
|
|
{
|
|
"entropy": 6.795753049850464,
|
|
"epoch": 0.8008974734172276,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004957766195902271,
|
|
"loss": 6.7787,
|
|
"mean_token_accuracy": 0.11245289444923401,
|
|
"num_tokens": 13700356.0,
|
|
"step": 4105
|
|
},
|
|
{
|
|
"entropy": 6.700359964370728,
|
|
"epoch": 0.8018729880011706,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004957630452792404,
|
|
"loss": 6.6204,
|
|
"mean_token_accuracy": 0.12925208508968353,
|
|
"num_tokens": 13717146.0,
|
|
"step": 4110
|
|
},
|
|
{
|
|
"entropy": 6.697245359420776,
|
|
"epoch": 0.8028485025851136,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004957494493960757,
|
|
"loss": 6.7026,
|
|
"mean_token_accuracy": 0.11700485944747925,
|
|
"num_tokens": 13732520.0,
|
|
"step": 4115
|
|
},
|
|
{
|
|
"entropy": 6.828039741516113,
|
|
"epoch": 0.8038240171690567,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004957358319420617,
|
|
"loss": 6.8057,
|
|
"mean_token_accuracy": 0.11363594830036164,
|
|
"num_tokens": 13749135.0,
|
|
"step": 4120
|
|
},
|
|
{
|
|
"entropy": 6.724052381515503,
|
|
"epoch": 0.8047995317529997,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004957221929185288,
|
|
"loss": 6.5375,
|
|
"mean_token_accuracy": 0.1360141485929489,
|
|
"num_tokens": 13766218.0,
|
|
"step": 4125
|
|
},
|
|
{
|
|
"entropy": 6.709185028076172,
|
|
"epoch": 0.8057750463369427,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004957085323268099,
|
|
"loss": 6.738,
|
|
"mean_token_accuracy": 0.1204710379242897,
|
|
"num_tokens": 13784421.0,
|
|
"step": 4130
|
|
},
|
|
{
|
|
"entropy": 6.715061235427856,
|
|
"epoch": 0.8067505609208858,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004956948501682399,
|
|
"loss": 6.6257,
|
|
"mean_token_accuracy": 0.12764252349734306,
|
|
"num_tokens": 13800054.0,
|
|
"step": 4135
|
|
},
|
|
{
|
|
"entropy": 6.701275396347046,
|
|
"epoch": 0.8077260755048288,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004956811464441556,
|
|
"loss": 6.6347,
|
|
"mean_token_accuracy": 0.12368953004479408,
|
|
"num_tokens": 13816433.0,
|
|
"step": 4140
|
|
},
|
|
{
|
|
"entropy": 6.7797950267791744,
|
|
"epoch": 0.8087015900887718,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004956674211558963,
|
|
"loss": 6.7581,
|
|
"mean_token_accuracy": 0.11446516662836075,
|
|
"num_tokens": 13832441.0,
|
|
"step": 4145
|
|
},
|
|
{
|
|
"entropy": 6.741479969024658,
|
|
"epoch": 0.8096771046727148,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.000495653674304803,
|
|
"loss": 6.7062,
|
|
"mean_token_accuracy": 0.12266986891627311,
|
|
"num_tokens": 13849012.0,
|
|
"step": 4150
|
|
},
|
|
{
|
|
"entropy": 6.761842107772827,
|
|
"epoch": 0.8106526192566579,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004956399058922192,
|
|
"loss": 6.7517,
|
|
"mean_token_accuracy": 0.11419290229678154,
|
|
"num_tokens": 13866486.0,
|
|
"step": 4155
|
|
},
|
|
{
|
|
"entropy": 6.757631158828735,
|
|
"epoch": 0.811628133840601,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00049562611591949,
|
|
"loss": 6.6137,
|
|
"mean_token_accuracy": 0.12622506320476531,
|
|
"num_tokens": 13882453.0,
|
|
"step": 4160
|
|
},
|
|
{
|
|
"entropy": 6.674859952926636,
|
|
"epoch": 0.8126036484245439,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004956123043879632,
|
|
"loss": 6.6903,
|
|
"mean_token_accuracy": 0.12404049932956696,
|
|
"num_tokens": 13898090.0,
|
|
"step": 4165
|
|
},
|
|
{
|
|
"entropy": 6.721875333786011,
|
|
"epoch": 0.813579163008487,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004955984712989882,
|
|
"loss": 6.6387,
|
|
"mean_token_accuracy": 0.12283464446663857,
|
|
"num_tokens": 13914818.0,
|
|
"step": 4170
|
|
},
|
|
{
|
|
"entropy": 6.76822419166565,
|
|
"epoch": 0.81455467759243,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004955846166539169,
|
|
"loss": 6.7468,
|
|
"mean_token_accuracy": 0.11454955786466599,
|
|
"num_tokens": 13930690.0,
|
|
"step": 4175
|
|
},
|
|
{
|
|
"entropy": 6.776472806930542,
|
|
"epoch": 0.815530192176373,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000495570740454103,
|
|
"loss": 6.7492,
|
|
"mean_token_accuracy": 0.12043305486440659,
|
|
"num_tokens": 13946128.0,
|
|
"step": 4180
|
|
},
|
|
{
|
|
"entropy": 6.701993083953857,
|
|
"epoch": 0.8165057067603161,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004955568427009024,
|
|
"loss": 6.6667,
|
|
"mean_token_accuracy": 0.1222498893737793,
|
|
"num_tokens": 13961766.0,
|
|
"step": 4185
|
|
},
|
|
{
|
|
"entropy": 6.621545314788818,
|
|
"epoch": 0.817481221344259,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004955429233956733,
|
|
"loss": 6.6356,
|
|
"mean_token_accuracy": 0.1275513857603073,
|
|
"num_tokens": 13978632.0,
|
|
"step": 4190
|
|
},
|
|
{
|
|
"entropy": 6.778307628631592,
|
|
"epoch": 0.8184567359282021,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004955289825397757,
|
|
"loss": 6.7142,
|
|
"mean_token_accuracy": 0.1170975185930729,
|
|
"num_tokens": 13995297.0,
|
|
"step": 4195
|
|
},
|
|
{
|
|
"entropy": 6.757305335998535,
|
|
"epoch": 0.8194322505121452,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000495515020134572,
|
|
"loss": 6.7177,
|
|
"mean_token_accuracy": 0.12182304188609124,
|
|
"num_tokens": 14010439.0,
|
|
"step": 4200
|
|
},
|
|
{
|
|
"entropy": 6.759061670303344,
|
|
"epoch": 0.8204077650960881,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004955010361814264,
|
|
"loss": 6.7243,
|
|
"mean_token_accuracy": 0.12254129126667976,
|
|
"num_tokens": 14028538.0,
|
|
"step": 4205
|
|
},
|
|
{
|
|
"entropy": 6.758128118515015,
|
|
"epoch": 0.8213832796800312,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004954870306817054,
|
|
"loss": 6.7438,
|
|
"mean_token_accuracy": 0.1150165468454361,
|
|
"num_tokens": 14045290.0,
|
|
"step": 4210
|
|
},
|
|
{
|
|
"entropy": 6.653536939620972,
|
|
"epoch": 0.8223587942639743,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004954730036367776,
|
|
"loss": 6.6531,
|
|
"mean_token_accuracy": 0.1254504479467869,
|
|
"num_tokens": 14062247.0,
|
|
"step": 4215
|
|
},
|
|
{
|
|
"entropy": 6.715406084060669,
|
|
"epoch": 0.8233343088479173,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004954589550480137,
|
|
"loss": 6.6747,
|
|
"mean_token_accuracy": 0.12312890812754632,
|
|
"num_tokens": 14078599.0,
|
|
"step": 4220
|
|
},
|
|
{
|
|
"entropy": 6.686068964004517,
|
|
"epoch": 0.8243098234318603,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004954448849167864,
|
|
"loss": 6.6838,
|
|
"mean_token_accuracy": 0.12093207761645317,
|
|
"num_tokens": 14094686.0,
|
|
"step": 4225
|
|
},
|
|
{
|
|
"entropy": 6.712847375869751,
|
|
"epoch": 0.8252853380158033,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004954307932444707,
|
|
"loss": 6.699,
|
|
"mean_token_accuracy": 0.12001883164048195,
|
|
"num_tokens": 14110255.0,
|
|
"step": 4230
|
|
},
|
|
{
|
|
"entropy": 6.732178688049316,
|
|
"epoch": 0.8262608525997464,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004954166800324434,
|
|
"loss": 6.6993,
|
|
"mean_token_accuracy": 0.12034580633044242,
|
|
"num_tokens": 14127160.0,
|
|
"step": 4235
|
|
},
|
|
{
|
|
"entropy": 6.655609035491944,
|
|
"epoch": 0.8272363671836894,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004954025452820837,
|
|
"loss": 6.6029,
|
|
"mean_token_accuracy": 0.12616494596004485,
|
|
"num_tokens": 14144704.0,
|
|
"step": 4240
|
|
},
|
|
{
|
|
"entropy": 6.727292442321778,
|
|
"epoch": 0.8282118817676324,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000495388388994773,
|
|
"loss": 6.6944,
|
|
"mean_token_accuracy": 0.11928221806883813,
|
|
"num_tokens": 14162125.0,
|
|
"step": 4245
|
|
},
|
|
{
|
|
"entropy": 6.680639982223511,
|
|
"epoch": 0.8291873963515755,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004953742111718942,
|
|
"loss": 6.5959,
|
|
"mean_token_accuracy": 0.1251651883125305,
|
|
"num_tokens": 14179735.0,
|
|
"step": 4250
|
|
},
|
|
{
|
|
"entropy": 6.71265058517456,
|
|
"epoch": 0.8301629109355185,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.000495360011814833,
|
|
"loss": 6.782,
|
|
"mean_token_accuracy": 0.11723508760333061,
|
|
"num_tokens": 14196964.0,
|
|
"step": 4255
|
|
},
|
|
{
|
|
"entropy": 6.70638337135315,
|
|
"epoch": 0.8311384255194615,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004953457909249768,
|
|
"loss": 6.622,
|
|
"mean_token_accuracy": 0.12491095066070557,
|
|
"num_tokens": 14212802.0,
|
|
"step": 4260
|
|
},
|
|
{
|
|
"entropy": 6.677652311325073,
|
|
"epoch": 0.8321139401034046,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004953315485037152,
|
|
"loss": 6.6308,
|
|
"mean_token_accuracy": 0.12438410967588424,
|
|
"num_tokens": 14229183.0,
|
|
"step": 4265
|
|
},
|
|
{
|
|
"entropy": 6.777984380722046,
|
|
"epoch": 0.8330894546873476,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004953172845524401,
|
|
"loss": 6.6541,
|
|
"mean_token_accuracy": 0.11971034854650497,
|
|
"num_tokens": 14245859.0,
|
|
"step": 4270
|
|
},
|
|
{
|
|
"entropy": 6.7283673763275145,
|
|
"epoch": 0.8340649692712906,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004953029990725452,
|
|
"loss": 6.7177,
|
|
"mean_token_accuracy": 0.12735827192664145,
|
|
"num_tokens": 14261689.0,
|
|
"step": 4275
|
|
},
|
|
{
|
|
"entropy": 6.618604230880737,
|
|
"epoch": 0.8350404838552337,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004952886920654262,
|
|
"loss": 6.5665,
|
|
"mean_token_accuracy": 0.12919991165399553,
|
|
"num_tokens": 14280638.0,
|
|
"step": 4280
|
|
},
|
|
{
|
|
"entropy": 6.686739873886109,
|
|
"epoch": 0.8360159984391766,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004952743635324813,
|
|
"loss": 6.5769,
|
|
"mean_token_accuracy": 0.13148723170161247,
|
|
"num_tokens": 14296595.0,
|
|
"step": 4285
|
|
},
|
|
{
|
|
"entropy": 6.684880876541138,
|
|
"epoch": 0.8369915130231197,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004952600134751109,
|
|
"loss": 6.7492,
|
|
"mean_token_accuracy": 0.11857855841517448,
|
|
"num_tokens": 14312384.0,
|
|
"step": 4290
|
|
},
|
|
{
|
|
"entropy": 6.7694282054901125,
|
|
"epoch": 0.8379670276070628,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004952456418947168,
|
|
"loss": 6.6588,
|
|
"mean_token_accuracy": 0.12094428539276122,
|
|
"num_tokens": 14327852.0,
|
|
"step": 4295
|
|
},
|
|
{
|
|
"entropy": 6.678110218048095,
|
|
"epoch": 0.8389425421910057,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004952312487927037,
|
|
"loss": 6.6688,
|
|
"mean_token_accuracy": 0.11853241845965386,
|
|
"num_tokens": 14343666.0,
|
|
"step": 4300
|
|
},
|
|
{
|
|
"entropy": 6.667179918289184,
|
|
"epoch": 0.8399180567749488,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004952168341704778,
|
|
"loss": 6.6316,
|
|
"mean_token_accuracy": 0.12984849214553834,
|
|
"num_tokens": 14359819.0,
|
|
"step": 4305
|
|
},
|
|
{
|
|
"entropy": 6.827196645736694,
|
|
"epoch": 0.8408935713588919,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004952023980294478,
|
|
"loss": 6.7642,
|
|
"mean_token_accuracy": 0.11426869928836822,
|
|
"num_tokens": 14377762.0,
|
|
"step": 4310
|
|
},
|
|
{
|
|
"entropy": 6.657854652404785,
|
|
"epoch": 0.8418690859428348,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004951879403710242,
|
|
"loss": 6.6098,
|
|
"mean_token_accuracy": 0.12350710481405258,
|
|
"num_tokens": 14393995.0,
|
|
"step": 4315
|
|
},
|
|
{
|
|
"entropy": 6.785690212249756,
|
|
"epoch": 0.8428446005267779,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004951734611966199,
|
|
"loss": 6.6605,
|
|
"mean_token_accuracy": 0.12853777334094046,
|
|
"num_tokens": 14411959.0,
|
|
"step": 4320
|
|
},
|
|
{
|
|
"entropy": 6.663223648071289,
|
|
"epoch": 0.8438201151107209,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004951589605076495,
|
|
"loss": 6.7404,
|
|
"mean_token_accuracy": 0.11804835647344589,
|
|
"num_tokens": 14427659.0,
|
|
"step": 4325
|
|
},
|
|
{
|
|
"entropy": 6.5604030132293705,
|
|
"epoch": 0.8447956296946639,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004951444383055304,
|
|
"loss": 6.4655,
|
|
"mean_token_accuracy": 0.14055540934205055,
|
|
"num_tokens": 14443887.0,
|
|
"step": 4330
|
|
},
|
|
{
|
|
"entropy": 6.727321624755859,
|
|
"epoch": 0.845771144278607,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004951298945916812,
|
|
"loss": 6.6779,
|
|
"mean_token_accuracy": 0.12308569550514221,
|
|
"num_tokens": 14461907.0,
|
|
"step": 4335
|
|
},
|
|
{
|
|
"entropy": 6.610097646713257,
|
|
"epoch": 0.84674665886255,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004951153293675235,
|
|
"loss": 6.637,
|
|
"mean_token_accuracy": 0.1213378705084324,
|
|
"num_tokens": 14476912.0,
|
|
"step": 4340
|
|
},
|
|
{
|
|
"entropy": 6.68468861579895,
|
|
"epoch": 0.847722173446493,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004951007426344801,
|
|
"loss": 6.5323,
|
|
"mean_token_accuracy": 0.128171668946743,
|
|
"num_tokens": 14493499.0,
|
|
"step": 4345
|
|
},
|
|
{
|
|
"entropy": 6.766698122024536,
|
|
"epoch": 0.8486976880304361,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004950861343939767,
|
|
"loss": 6.6832,
|
|
"mean_token_accuracy": 0.12308905869722367,
|
|
"num_tokens": 14511266.0,
|
|
"step": 4350
|
|
},
|
|
{
|
|
"entropy": 6.703920888900757,
|
|
"epoch": 0.8496732026143791,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004950715046474405,
|
|
"loss": 6.6986,
|
|
"mean_token_accuracy": 0.12056632414460182,
|
|
"num_tokens": 14528930.0,
|
|
"step": 4355
|
|
},
|
|
{
|
|
"entropy": 6.753537034988403,
|
|
"epoch": 0.8506487171983221,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004950568533963013,
|
|
"loss": 6.651,
|
|
"mean_token_accuracy": 0.13303152322769166,
|
|
"num_tokens": 14546637.0,
|
|
"step": 4360
|
|
},
|
|
{
|
|
"entropy": 6.577473402023315,
|
|
"epoch": 0.8516242317822651,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004950421806419907,
|
|
"loss": 6.6718,
|
|
"mean_token_accuracy": 0.12299416586756706,
|
|
"num_tokens": 14563332.0,
|
|
"step": 4365
|
|
},
|
|
{
|
|
"entropy": 6.622354555130005,
|
|
"epoch": 0.8525997463662082,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004950274863859425,
|
|
"loss": 6.5246,
|
|
"mean_token_accuracy": 0.13299155309796334,
|
|
"num_tokens": 14579806.0,
|
|
"step": 4370
|
|
},
|
|
{
|
|
"entropy": 6.759409093856812,
|
|
"epoch": 0.8535752609501512,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004950127706295923,
|
|
"loss": 6.7296,
|
|
"mean_token_accuracy": 0.11770405918359757,
|
|
"num_tokens": 14597129.0,
|
|
"step": 4375
|
|
},
|
|
{
|
|
"entropy": 6.582925271987915,
|
|
"epoch": 0.8545507755340942,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004949980333743786,
|
|
"loss": 6.4736,
|
|
"mean_token_accuracy": 0.13698861226439477,
|
|
"num_tokens": 14615000.0,
|
|
"step": 4380
|
|
},
|
|
{
|
|
"entropy": 6.697421503067017,
|
|
"epoch": 0.8555262901180373,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000494983274621741,
|
|
"loss": 6.6604,
|
|
"mean_token_accuracy": 0.1320178158581257,
|
|
"num_tokens": 14631338.0,
|
|
"step": 4385
|
|
},
|
|
{
|
|
"entropy": 6.659046077728272,
|
|
"epoch": 0.8565018047019803,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004949684943731219,
|
|
"loss": 6.6303,
|
|
"mean_token_accuracy": 0.12667946740984917,
|
|
"num_tokens": 14647886.0,
|
|
"step": 4390
|
|
},
|
|
{
|
|
"entropy": 6.717004680633545,
|
|
"epoch": 0.8574773192859233,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004949536926299654,
|
|
"loss": 6.6164,
|
|
"mean_token_accuracy": 0.12475013434886932,
|
|
"num_tokens": 14665054.0,
|
|
"step": 4395
|
|
},
|
|
{
|
|
"entropy": 6.63008484840393,
|
|
"epoch": 0.8584528338698664,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000494938869393718,
|
|
"loss": 6.6404,
|
|
"mean_token_accuracy": 0.12373051568865776,
|
|
"num_tokens": 14679413.0,
|
|
"step": 4400
|
|
},
|
|
{
|
|
"entropy": 6.655140399932861,
|
|
"epoch": 0.8594283484538093,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004949240246658283,
|
|
"loss": 6.5943,
|
|
"mean_token_accuracy": 0.1296962633728981,
|
|
"num_tokens": 14696562.0,
|
|
"step": 4405
|
|
},
|
|
{
|
|
"entropy": 6.661473751068115,
|
|
"epoch": 0.8604038630377524,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004949091584477465,
|
|
"loss": 6.5144,
|
|
"mean_token_accuracy": 0.13233201950788498,
|
|
"num_tokens": 14713782.0,
|
|
"step": 4410
|
|
},
|
|
{
|
|
"entropy": 6.717836523056031,
|
|
"epoch": 0.8613793776216955,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004948942707409257,
|
|
"loss": 6.7541,
|
|
"mean_token_accuracy": 0.11957289427518844,
|
|
"num_tokens": 14730139.0,
|
|
"step": 4415
|
|
},
|
|
{
|
|
"entropy": 6.7486186027526855,
|
|
"epoch": 0.8623548922056384,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004948793615468205,
|
|
"loss": 6.6904,
|
|
"mean_token_accuracy": 0.11351295858621598,
|
|
"num_tokens": 14746830.0,
|
|
"step": 4420
|
|
},
|
|
{
|
|
"entropy": 6.763196659088135,
|
|
"epoch": 0.8633304067895815,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004948644308668877,
|
|
"loss": 6.7074,
|
|
"mean_token_accuracy": 0.12098187506198883,
|
|
"num_tokens": 14762410.0,
|
|
"step": 4425
|
|
},
|
|
{
|
|
"entropy": 6.69735426902771,
|
|
"epoch": 0.8643059213735246,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004948494787025863,
|
|
"loss": 6.618,
|
|
"mean_token_accuracy": 0.11744904592633247,
|
|
"num_tokens": 14778283.0,
|
|
"step": 4430
|
|
},
|
|
{
|
|
"entropy": 6.586069536209107,
|
|
"epoch": 0.8652814359574675,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004948345050553774,
|
|
"loss": 6.5865,
|
|
"mean_token_accuracy": 0.12278729230165482,
|
|
"num_tokens": 14797005.0,
|
|
"step": 4435
|
|
},
|
|
{
|
|
"entropy": 6.707292747497559,
|
|
"epoch": 0.8662569505414106,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004948195099267242,
|
|
"loss": 6.7045,
|
|
"mean_token_accuracy": 0.11417438983917236,
|
|
"num_tokens": 14814548.0,
|
|
"step": 4440
|
|
},
|
|
{
|
|
"entropy": 6.723720407485962,
|
|
"epoch": 0.8672324651253536,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004948044933180919,
|
|
"loss": 6.6428,
|
|
"mean_token_accuracy": 0.12684162706136703,
|
|
"num_tokens": 14830630.0,
|
|
"step": 4445
|
|
},
|
|
{
|
|
"entropy": 6.677996444702148,
|
|
"epoch": 0.8682079797092966,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000494789455230948,
|
|
"loss": 6.6598,
|
|
"mean_token_accuracy": 0.11942166835069656,
|
|
"num_tokens": 14846247.0,
|
|
"step": 4450
|
|
},
|
|
{
|
|
"entropy": 6.774417924880981,
|
|
"epoch": 0.8691834942932397,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004947743956667617,
|
|
"loss": 6.6875,
|
|
"mean_token_accuracy": 0.12094950750470161,
|
|
"num_tokens": 14864480.0,
|
|
"step": 4455
|
|
},
|
|
{
|
|
"entropy": 6.753264331817627,
|
|
"epoch": 0.8701590088771827,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004947593146270049,
|
|
"loss": 6.7316,
|
|
"mean_token_accuracy": 0.12086831554770469,
|
|
"num_tokens": 14881382.0,
|
|
"step": 4460
|
|
},
|
|
{
|
|
"entropy": 6.698492479324341,
|
|
"epoch": 0.8711345234611257,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000494744212113151,
|
|
"loss": 6.6635,
|
|
"mean_token_accuracy": 0.11897140815854072,
|
|
"num_tokens": 14897546.0,
|
|
"step": 4465
|
|
},
|
|
{
|
|
"entropy": 6.712836122512817,
|
|
"epoch": 0.8721100380450688,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004947290881266759,
|
|
"loss": 6.6429,
|
|
"mean_token_accuracy": 0.12065940648317337,
|
|
"num_tokens": 14913995.0,
|
|
"step": 4470
|
|
},
|
|
{
|
|
"entropy": 6.693822050094605,
|
|
"epoch": 0.8730855526290118,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004947139426690576,
|
|
"loss": 6.6972,
|
|
"mean_token_accuracy": 0.11218658685684205,
|
|
"num_tokens": 14931097.0,
|
|
"step": 4475
|
|
},
|
|
{
|
|
"entropy": 6.643001985549927,
|
|
"epoch": 0.8740610672129548,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004946987757417757,
|
|
"loss": 6.5735,
|
|
"mean_token_accuracy": 0.12658286988735198,
|
|
"num_tokens": 14948010.0,
|
|
"step": 4480
|
|
},
|
|
{
|
|
"entropy": 6.5114312171936035,
|
|
"epoch": 0.8750365817968979,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004946835873463126,
|
|
"loss": 6.5412,
|
|
"mean_token_accuracy": 0.13816641941666602,
|
|
"num_tokens": 14966940.0,
|
|
"step": 4485
|
|
},
|
|
{
|
|
"entropy": 6.825555610656738,
|
|
"epoch": 0.8760120963808409,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004946683774841522,
|
|
"loss": 6.7327,
|
|
"mean_token_accuracy": 0.11743103116750717,
|
|
"num_tokens": 14983482.0,
|
|
"step": 4490
|
|
},
|
|
{
|
|
"entropy": 6.590304565429688,
|
|
"epoch": 0.876987610964784,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.000494653146156781,
|
|
"loss": 6.5815,
|
|
"mean_token_accuracy": 0.12662649601697923,
|
|
"num_tokens": 15000709.0,
|
|
"step": 4495
|
|
},
|
|
{
|
|
"entropy": 6.630526399612426,
|
|
"epoch": 0.8779631255487269,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004946378933656871,
|
|
"loss": 6.5529,
|
|
"mean_token_accuracy": 0.12919438406825065,
|
|
"num_tokens": 15016584.0,
|
|
"step": 4500
|
|
},
|
|
{
|
|
"entropy": 6.661861753463745,
|
|
"epoch": 0.87893864013267,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.000494622619112361,
|
|
"loss": 6.731,
|
|
"mean_token_accuracy": 0.12312712743878365,
|
|
"num_tokens": 15033598.0,
|
|
"step": 4505
|
|
},
|
|
{
|
|
"entropy": 6.763346576690674,
|
|
"epoch": 0.879914154716613,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004946073233982954,
|
|
"loss": 6.6967,
|
|
"mean_token_accuracy": 0.11884970888495446,
|
|
"num_tokens": 15049842.0,
|
|
"step": 4510
|
|
},
|
|
{
|
|
"entropy": 6.562280750274658,
|
|
"epoch": 0.880889669300556,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004945920062249849,
|
|
"loss": 6.4494,
|
|
"mean_token_accuracy": 0.13671814277768135,
|
|
"num_tokens": 15066278.0,
|
|
"step": 4515
|
|
},
|
|
{
|
|
"entropy": 6.709124946594239,
|
|
"epoch": 0.8818651838844991,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004945766675939261,
|
|
"loss": 6.6624,
|
|
"mean_token_accuracy": 0.12936284244060517,
|
|
"num_tokens": 15083316.0,
|
|
"step": 4520
|
|
},
|
|
{
|
|
"entropy": 6.658744144439697,
|
|
"epoch": 0.8828406984684422,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004945613075066181,
|
|
"loss": 6.7004,
|
|
"mean_token_accuracy": 0.12172035872936249,
|
|
"num_tokens": 15103135.0,
|
|
"step": 4525
|
|
},
|
|
{
|
|
"entropy": 6.652385950088501,
|
|
"epoch": 0.8838162130523851,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004945459259645614,
|
|
"loss": 6.5441,
|
|
"mean_token_accuracy": 0.13916929215192794,
|
|
"num_tokens": 15122441.0,
|
|
"step": 4530
|
|
},
|
|
{
|
|
"entropy": 6.757006406784058,
|
|
"epoch": 0.8847917276363282,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004945305229692594,
|
|
"loss": 6.6525,
|
|
"mean_token_accuracy": 0.12212066426873207,
|
|
"num_tokens": 15139526.0,
|
|
"step": 4535
|
|
},
|
|
{
|
|
"entropy": 6.6799506664276125,
|
|
"epoch": 0.8857672422202711,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004945150985222171,
|
|
"loss": 6.6316,
|
|
"mean_token_accuracy": 0.12037071436643601,
|
|
"num_tokens": 15156139.0,
|
|
"step": 4540
|
|
},
|
|
{
|
|
"entropy": 6.606849956512451,
|
|
"epoch": 0.8867427568042142,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004944996526249419,
|
|
"loss": 6.5548,
|
|
"mean_token_accuracy": 0.13367788642644882,
|
|
"num_tokens": 15172894.0,
|
|
"step": 4545
|
|
},
|
|
{
|
|
"entropy": 6.66869044303894,
|
|
"epoch": 0.8877182713881573,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004944841852789427,
|
|
"loss": 6.667,
|
|
"mean_token_accuracy": 0.12238618284463883,
|
|
"num_tokens": 15190900.0,
|
|
"step": 4550
|
|
},
|
|
{
|
|
"entropy": 6.713797855377197,
|
|
"epoch": 0.8886937859721002,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004944686964857314,
|
|
"loss": 6.6375,
|
|
"mean_token_accuracy": 0.11876249313354492,
|
|
"num_tokens": 15208018.0,
|
|
"step": 4555
|
|
},
|
|
{
|
|
"entropy": 6.7016003131866455,
|
|
"epoch": 0.8896693005560433,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004944531862468211,
|
|
"loss": 6.6531,
|
|
"mean_token_accuracy": 0.12680244743824004,
|
|
"num_tokens": 15222781.0,
|
|
"step": 4560
|
|
},
|
|
{
|
|
"entropy": 6.655779457092285,
|
|
"epoch": 0.8906448151399864,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004944376545637277,
|
|
"loss": 6.6865,
|
|
"mean_token_accuracy": 0.12332582548260689,
|
|
"num_tokens": 15241405.0,
|
|
"step": 4565
|
|
},
|
|
{
|
|
"entropy": 6.772011137008667,
|
|
"epoch": 0.8916203297239294,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004944221014379688,
|
|
"loss": 6.6835,
|
|
"mean_token_accuracy": 0.12466043531894684,
|
|
"num_tokens": 15258340.0,
|
|
"step": 4570
|
|
},
|
|
{
|
|
"entropy": 6.655908012390137,
|
|
"epoch": 0.8925958443078724,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004944065268710641,
|
|
"loss": 6.6346,
|
|
"mean_token_accuracy": 0.12317401990294456,
|
|
"num_tokens": 15274655.0,
|
|
"step": 4575
|
|
},
|
|
{
|
|
"entropy": 6.765136957168579,
|
|
"epoch": 0.8935713588918154,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004943909308645356,
|
|
"loss": 6.6932,
|
|
"mean_token_accuracy": 0.11527744755148887,
|
|
"num_tokens": 15291197.0,
|
|
"step": 4580
|
|
},
|
|
{
|
|
"entropy": 6.71063346862793,
|
|
"epoch": 0.8945468734757585,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004943753134199072,
|
|
"loss": 6.6709,
|
|
"mean_token_accuracy": 0.11931663602590561,
|
|
"num_tokens": 15306879.0,
|
|
"step": 4585
|
|
},
|
|
{
|
|
"entropy": 6.718756675720215,
|
|
"epoch": 0.8955223880597015,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004943596745387052,
|
|
"loss": 6.6907,
|
|
"mean_token_accuracy": 0.11892857179045677,
|
|
"num_tokens": 15322880.0,
|
|
"step": 4590
|
|
},
|
|
{
|
|
"entropy": 6.6826776504516605,
|
|
"epoch": 0.8964979026436445,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004943440142224575,
|
|
"loss": 6.6093,
|
|
"mean_token_accuracy": 0.12427129596471786,
|
|
"num_tokens": 15338282.0,
|
|
"step": 4595
|
|
},
|
|
{
|
|
"entropy": 6.6650200366973875,
|
|
"epoch": 0.8974734172275876,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004943283324726944,
|
|
"loss": 6.6232,
|
|
"mean_token_accuracy": 0.12531112059950827,
|
|
"num_tokens": 15354507.0,
|
|
"step": 4600
|
|
},
|
|
{
|
|
"entropy": 6.739825582504272,
|
|
"epoch": 0.8984489318115306,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004943126292909485,
|
|
"loss": 6.6478,
|
|
"mean_token_accuracy": 0.11825016587972641,
|
|
"num_tokens": 15373204.0,
|
|
"step": 4605
|
|
},
|
|
{
|
|
"entropy": 6.614193677902222,
|
|
"epoch": 0.8994244463954736,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004942969046787541,
|
|
"loss": 6.5005,
|
|
"mean_token_accuracy": 0.1372572049498558,
|
|
"num_tokens": 15390743.0,
|
|
"step": 4610
|
|
},
|
|
{
|
|
"entropy": 6.668061208724976,
|
|
"epoch": 0.9003999609794167,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004942811586376476,
|
|
"loss": 6.6212,
|
|
"mean_token_accuracy": 0.11788920611143112,
|
|
"num_tokens": 15408565.0,
|
|
"step": 4615
|
|
},
|
|
{
|
|
"entropy": 6.616222238540649,
|
|
"epoch": 0.9013754755633596,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004942653911691679,
|
|
"loss": 6.5754,
|
|
"mean_token_accuracy": 0.12987908348441124,
|
|
"num_tokens": 15425747.0,
|
|
"step": 4620
|
|
},
|
|
{
|
|
"entropy": 6.59138560295105,
|
|
"epoch": 0.9023509901473027,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004942496022748557,
|
|
"loss": 6.5923,
|
|
"mean_token_accuracy": 0.1267254300415516,
|
|
"num_tokens": 15441882.0,
|
|
"step": 4625
|
|
},
|
|
{
|
|
"entropy": 6.683704900741577,
|
|
"epoch": 0.9033265047312458,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004942337919562539,
|
|
"loss": 6.5582,
|
|
"mean_token_accuracy": 0.12106533646583557,
|
|
"num_tokens": 15458003.0,
|
|
"step": 4630
|
|
},
|
|
{
|
|
"entropy": 6.471642923355103,
|
|
"epoch": 0.9043020193151887,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004942179602149071,
|
|
"loss": 6.4814,
|
|
"mean_token_accuracy": 0.13770075365900994,
|
|
"num_tokens": 15473798.0,
|
|
"step": 4635
|
|
},
|
|
{
|
|
"entropy": 6.610068988800049,
|
|
"epoch": 0.9052775338991318,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004942021070523626,
|
|
"loss": 6.4933,
|
|
"mean_token_accuracy": 0.1362534999847412,
|
|
"num_tokens": 15490620.0,
|
|
"step": 4640
|
|
},
|
|
{
|
|
"entropy": 6.6062335014343265,
|
|
"epoch": 0.9062530484830749,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004941862324701695,
|
|
"loss": 6.5126,
|
|
"mean_token_accuracy": 0.13429864272475242,
|
|
"num_tokens": 15506777.0,
|
|
"step": 4645
|
|
},
|
|
{
|
|
"entropy": 6.669408464431763,
|
|
"epoch": 0.9072285630670178,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004941703364698789,
|
|
"loss": 6.7304,
|
|
"mean_token_accuracy": 0.11547983065247536,
|
|
"num_tokens": 15523416.0,
|
|
"step": 4650
|
|
},
|
|
{
|
|
"entropy": 6.714564371109009,
|
|
"epoch": 0.9082040776509609,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004941544190530442,
|
|
"loss": 6.4847,
|
|
"mean_token_accuracy": 0.1340474598109722,
|
|
"num_tokens": 15541064.0,
|
|
"step": 4655
|
|
},
|
|
{
|
|
"entropy": 6.697964000701904,
|
|
"epoch": 0.909179592234904,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004941384802212207,
|
|
"loss": 6.7557,
|
|
"mean_token_accuracy": 0.11731927022337914,
|
|
"num_tokens": 15559391.0,
|
|
"step": 4660
|
|
},
|
|
{
|
|
"entropy": 6.672799587249756,
|
|
"epoch": 0.9101551068188469,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000494122519975966,
|
|
"loss": 6.5787,
|
|
"mean_token_accuracy": 0.122499381005764,
|
|
"num_tokens": 15576842.0,
|
|
"step": 4665
|
|
},
|
|
{
|
|
"entropy": 6.579967832565307,
|
|
"epoch": 0.91113062140279,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004941065383188396,
|
|
"loss": 6.5482,
|
|
"mean_token_accuracy": 0.13241146877408028,
|
|
"num_tokens": 15592442.0,
|
|
"step": 4670
|
|
},
|
|
{
|
|
"entropy": 6.660164785385132,
|
|
"epoch": 0.912106135986733,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004940905352514032,
|
|
"loss": 6.633,
|
|
"mean_token_accuracy": 0.12085811123251915,
|
|
"num_tokens": 15608402.0,
|
|
"step": 4675
|
|
},
|
|
{
|
|
"entropy": 6.706618070602417,
|
|
"epoch": 0.913081650570676,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004940745107752205,
|
|
"loss": 6.5886,
|
|
"mean_token_accuracy": 0.12359507083892822,
|
|
"num_tokens": 15624349.0,
|
|
"step": 4680
|
|
},
|
|
{
|
|
"entropy": 6.595095109939575,
|
|
"epoch": 0.9140571651546191,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004940584648918573,
|
|
"loss": 6.6704,
|
|
"mean_token_accuracy": 0.12645146995782852,
|
|
"num_tokens": 15640901.0,
|
|
"step": 4685
|
|
},
|
|
{
|
|
"entropy": 6.778916740417481,
|
|
"epoch": 0.9150326797385621,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004940423976028819,
|
|
"loss": 6.7129,
|
|
"mean_token_accuracy": 0.1202821284532547,
|
|
"num_tokens": 15658947.0,
|
|
"step": 4690
|
|
},
|
|
{
|
|
"entropy": 6.796932315826416,
|
|
"epoch": 0.9160081943225051,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004940263089098639,
|
|
"loss": 6.7345,
|
|
"mean_token_accuracy": 0.12005108818411828,
|
|
"num_tokens": 15674459.0,
|
|
"step": 4695
|
|
},
|
|
{
|
|
"entropy": 6.653960514068603,
|
|
"epoch": 0.9169837089064482,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004940101988143757,
|
|
"loss": 6.6299,
|
|
"mean_token_accuracy": 0.12654874175786973,
|
|
"num_tokens": 15691951.0,
|
|
"step": 4700
|
|
},
|
|
{
|
|
"entropy": 6.670955848693848,
|
|
"epoch": 0.9179592234903912,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004939940673179914,
|
|
"loss": 6.6652,
|
|
"mean_token_accuracy": 0.11814407333731651,
|
|
"num_tokens": 15708539.0,
|
|
"step": 4705
|
|
},
|
|
{
|
|
"entropy": 6.688578033447266,
|
|
"epoch": 0.9189347380743342,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004939779144222873,
|
|
"loss": 6.6528,
|
|
"mean_token_accuracy": 0.12420998886227608,
|
|
"num_tokens": 15727108.0,
|
|
"step": 4710
|
|
},
|
|
{
|
|
"entropy": 6.752237367630005,
|
|
"epoch": 0.9199102526582772,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004939617401288419,
|
|
"loss": 6.6132,
|
|
"mean_token_accuracy": 0.12033751457929612,
|
|
"num_tokens": 15743436.0,
|
|
"step": 4715
|
|
},
|
|
{
|
|
"entropy": 6.685384035110474,
|
|
"epoch": 0.9208857672422203,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004939455444392357,
|
|
"loss": 6.7128,
|
|
"mean_token_accuracy": 0.11941062510013581,
|
|
"num_tokens": 15761438.0,
|
|
"step": 4720
|
|
},
|
|
{
|
|
"entropy": 6.659618711471557,
|
|
"epoch": 0.9218612818261633,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004939293273550512,
|
|
"loss": 6.5786,
|
|
"mean_token_accuracy": 0.12445952966809273,
|
|
"num_tokens": 15777064.0,
|
|
"step": 4725
|
|
},
|
|
{
|
|
"entropy": 6.698070812225342,
|
|
"epoch": 0.9228367964101063,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004939130888778731,
|
|
"loss": 6.5903,
|
|
"mean_token_accuracy": 0.12435366734862327,
|
|
"num_tokens": 15793346.0,
|
|
"step": 4730
|
|
},
|
|
{
|
|
"entropy": 6.632796144485473,
|
|
"epoch": 0.9238123109940494,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004938968290092883,
|
|
"loss": 6.6117,
|
|
"mean_token_accuracy": 0.12173701003193856,
|
|
"num_tokens": 15809557.0,
|
|
"step": 4735
|
|
},
|
|
{
|
|
"entropy": 6.7369804859161375,
|
|
"epoch": 0.9247878255779924,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004938805477508853,
|
|
"loss": 6.6537,
|
|
"mean_token_accuracy": 0.1170791320502758,
|
|
"num_tokens": 15826717.0,
|
|
"step": 4740
|
|
},
|
|
{
|
|
"entropy": 6.69337797164917,
|
|
"epoch": 0.9257633401619354,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004938642451042554,
|
|
"loss": 6.6309,
|
|
"mean_token_accuracy": 0.12194430679082871,
|
|
"num_tokens": 15842472.0,
|
|
"step": 4745
|
|
},
|
|
{
|
|
"entropy": 6.542177820205689,
|
|
"epoch": 0.9267388547458785,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004938479210709915,
|
|
"loss": 6.5379,
|
|
"mean_token_accuracy": 0.1319144681096077,
|
|
"num_tokens": 15860136.0,
|
|
"step": 4750
|
|
},
|
|
{
|
|
"entropy": 6.712498664855957,
|
|
"epoch": 0.9277143693298214,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004938315756526886,
|
|
"loss": 6.5805,
|
|
"mean_token_accuracy": 0.13106356039643288,
|
|
"num_tokens": 15878538.0,
|
|
"step": 4755
|
|
},
|
|
{
|
|
"entropy": 6.658322286605835,
|
|
"epoch": 0.9286898839137645,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004938152088509442,
|
|
"loss": 6.6286,
|
|
"mean_token_accuracy": 0.12106969356536865,
|
|
"num_tokens": 15892875.0,
|
|
"step": 4760
|
|
},
|
|
{
|
|
"entropy": 6.6288975238800045,
|
|
"epoch": 0.9296653984977076,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004937988206673576,
|
|
"loss": 6.4853,
|
|
"mean_token_accuracy": 0.13124295622110366,
|
|
"num_tokens": 15909366.0,
|
|
"step": 4765
|
|
},
|
|
{
|
|
"entropy": 6.573721599578858,
|
|
"epoch": 0.9306409130816505,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004937824111035298,
|
|
"loss": 6.5675,
|
|
"mean_token_accuracy": 0.127024757117033,
|
|
"num_tokens": 15927712.0,
|
|
"step": 4770
|
|
},
|
|
{
|
|
"entropy": 6.743673801422119,
|
|
"epoch": 0.9316164276655936,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004937659801610647,
|
|
"loss": 6.6818,
|
|
"mean_token_accuracy": 0.11650491803884507,
|
|
"num_tokens": 15943474.0,
|
|
"step": 4775
|
|
},
|
|
{
|
|
"entropy": 6.6824544906616214,
|
|
"epoch": 0.9325919422495367,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004937495278415677,
|
|
"loss": 6.642,
|
|
"mean_token_accuracy": 0.11333007216453553,
|
|
"num_tokens": 15959546.0,
|
|
"step": 4780
|
|
},
|
|
{
|
|
"entropy": 6.696650695800781,
|
|
"epoch": 0.9335674568334796,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004937330541466465,
|
|
"loss": 6.5643,
|
|
"mean_token_accuracy": 0.12147774696350097,
|
|
"num_tokens": 15975669.0,
|
|
"step": 4785
|
|
},
|
|
{
|
|
"entropy": 6.579188585281372,
|
|
"epoch": 0.9345429714174227,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004937165590779108,
|
|
"loss": 6.5561,
|
|
"mean_token_accuracy": 0.13940777480602265,
|
|
"num_tokens": 15992898.0,
|
|
"step": 4790
|
|
},
|
|
{
|
|
"entropy": 6.648973178863526,
|
|
"epoch": 0.9355184860013657,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004937000426369724,
|
|
"loss": 6.5696,
|
|
"mean_token_accuracy": 0.12058120220899582,
|
|
"num_tokens": 16010102.0,
|
|
"step": 4795
|
|
},
|
|
{
|
|
"entropy": 6.737446594238281,
|
|
"epoch": 0.9364940005853087,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004936835048254453,
|
|
"loss": 6.6501,
|
|
"mean_token_accuracy": 0.1192353531718254,
|
|
"num_tokens": 16027167.0,
|
|
"step": 4800
|
|
},
|
|
{
|
|
"entropy": 6.625647020339966,
|
|
"epoch": 0.9374695151692518,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004936669456449455,
|
|
"loss": 6.6172,
|
|
"mean_token_accuracy": 0.12086767256259918,
|
|
"num_tokens": 16042873.0,
|
|
"step": 4805
|
|
},
|
|
{
|
|
"entropy": 6.676335382461548,
|
|
"epoch": 0.9384450297531948,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004936503650970912,
|
|
"loss": 6.66,
|
|
"mean_token_accuracy": 0.123435228317976,
|
|
"num_tokens": 16060814.0,
|
|
"step": 4810
|
|
},
|
|
{
|
|
"entropy": 6.678223657608032,
|
|
"epoch": 0.9394205443371378,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004936337631835024,
|
|
"loss": 6.6154,
|
|
"mean_token_accuracy": 0.11649640649557114,
|
|
"num_tokens": 16078378.0,
|
|
"step": 4815
|
|
},
|
|
{
|
|
"entropy": 6.518010520935059,
|
|
"epoch": 0.9403960589210809,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004936171399058017,
|
|
"loss": 6.4107,
|
|
"mean_token_accuracy": 0.1329922579228878,
|
|
"num_tokens": 16094601.0,
|
|
"step": 4820
|
|
},
|
|
{
|
|
"entropy": 6.520982170104981,
|
|
"epoch": 0.9413715735050239,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004936004952656131,
|
|
"loss": 6.4947,
|
|
"mean_token_accuracy": 0.13207095712423325,
|
|
"num_tokens": 16113189.0,
|
|
"step": 4825
|
|
},
|
|
{
|
|
"entropy": 6.730196952819824,
|
|
"epoch": 0.9423470880889669,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004935838292645632,
|
|
"loss": 6.7288,
|
|
"mean_token_accuracy": 0.11580159068107605,
|
|
"num_tokens": 16131225.0,
|
|
"step": 4830
|
|
},
|
|
{
|
|
"entropy": 6.615125370025635,
|
|
"epoch": 0.9433226026729099,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004935671419042805,
|
|
"loss": 6.5735,
|
|
"mean_token_accuracy": 0.11887683346867561,
|
|
"num_tokens": 16149733.0,
|
|
"step": 4835
|
|
},
|
|
{
|
|
"entropy": 6.668589496612549,
|
|
"epoch": 0.944298117256853,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004935504331863958,
|
|
"loss": 6.5309,
|
|
"mean_token_accuracy": 0.12559316381812097,
|
|
"num_tokens": 16167499.0,
|
|
"step": 4840
|
|
},
|
|
{
|
|
"entropy": 6.488853073120117,
|
|
"epoch": 0.945273631840796,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004935337031125416,
|
|
"loss": 6.4575,
|
|
"mean_token_accuracy": 0.13981773778796197,
|
|
"num_tokens": 16184858.0,
|
|
"step": 4845
|
|
},
|
|
{
|
|
"entropy": 6.650036144256592,
|
|
"epoch": 0.946249146424739,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004935169516843528,
|
|
"loss": 6.6496,
|
|
"mean_token_accuracy": 0.12991729602217675,
|
|
"num_tokens": 16201824.0,
|
|
"step": 4850
|
|
},
|
|
{
|
|
"entropy": 6.58286566734314,
|
|
"epoch": 0.9472246610086821,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004935001789034664,
|
|
"loss": 6.45,
|
|
"mean_token_accuracy": 0.13316916972398757,
|
|
"num_tokens": 16219551.0,
|
|
"step": 4855
|
|
},
|
|
{
|
|
"entropy": 6.615507555007935,
|
|
"epoch": 0.9482001755926251,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004934833847715212,
|
|
"loss": 6.5614,
|
|
"mean_token_accuracy": 0.13198114782571793,
|
|
"num_tokens": 16237447.0,
|
|
"step": 4860
|
|
},
|
|
{
|
|
"entropy": 6.719435358047486,
|
|
"epoch": 0.9491756901765681,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004934665692901583,
|
|
"loss": 6.7313,
|
|
"mean_token_accuracy": 0.11948551908135414,
|
|
"num_tokens": 16254377.0,
|
|
"step": 4865
|
|
},
|
|
{
|
|
"entropy": 6.620981216430664,
|
|
"epoch": 0.9501512047605112,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000493449732461021,
|
|
"loss": 6.53,
|
|
"mean_token_accuracy": 0.13025119826197623,
|
|
"num_tokens": 16271669.0,
|
|
"step": 4870
|
|
},
|
|
{
|
|
"entropy": 6.566729879379272,
|
|
"epoch": 0.9511267193444543,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004934328742857543,
|
|
"loss": 6.5185,
|
|
"mean_token_accuracy": 0.12990475296974183,
|
|
"num_tokens": 16287088.0,
|
|
"step": 4875
|
|
},
|
|
{
|
|
"entropy": 6.489052724838257,
|
|
"epoch": 0.9521022339283972,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004934159947660057,
|
|
"loss": 6.4672,
|
|
"mean_token_accuracy": 0.1319138616323471,
|
|
"num_tokens": 16303646.0,
|
|
"step": 4880
|
|
},
|
|
{
|
|
"entropy": 6.632110834121704,
|
|
"epoch": 0.9530777485123403,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004933990939034244,
|
|
"loss": 6.5392,
|
|
"mean_token_accuracy": 0.12867142334580423,
|
|
"num_tokens": 16320610.0,
|
|
"step": 4885
|
|
},
|
|
{
|
|
"entropy": 6.606713533401489,
|
|
"epoch": 0.9540532630962832,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004933821716996621,
|
|
"loss": 6.4925,
|
|
"mean_token_accuracy": 0.13168270513415337,
|
|
"num_tokens": 16337983.0,
|
|
"step": 4890
|
|
},
|
|
{
|
|
"entropy": 6.58355393409729,
|
|
"epoch": 0.9550287776802263,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004933652281563723,
|
|
"loss": 6.5456,
|
|
"mean_token_accuracy": 0.12196272388100624,
|
|
"num_tokens": 16356645.0,
|
|
"step": 4895
|
|
},
|
|
{
|
|
"entropy": 6.634447431564331,
|
|
"epoch": 0.9560042922641694,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004933482632752107,
|
|
"loss": 6.5681,
|
|
"mean_token_accuracy": 0.1199418343603611,
|
|
"num_tokens": 16371619.0,
|
|
"step": 4900
|
|
},
|
|
{
|
|
"entropy": 6.608288097381592,
|
|
"epoch": 0.9569798068481123,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004933312770578351,
|
|
"loss": 6.5657,
|
|
"mean_token_accuracy": 0.13260002583265304,
|
|
"num_tokens": 16389831.0,
|
|
"step": 4905
|
|
},
|
|
{
|
|
"entropy": 6.70386381149292,
|
|
"epoch": 0.9579553214320554,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004933142695059052,
|
|
"loss": 6.6094,
|
|
"mean_token_accuracy": 0.12035082131624222,
|
|
"num_tokens": 16406132.0,
|
|
"step": 4910
|
|
},
|
|
{
|
|
"entropy": 6.635140991210937,
|
|
"epoch": 0.9589308360159985,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004932972406210829,
|
|
"loss": 6.5998,
|
|
"mean_token_accuracy": 0.12434241697192192,
|
|
"num_tokens": 16422442.0,
|
|
"step": 4915
|
|
},
|
|
{
|
|
"entropy": 6.623861598968506,
|
|
"epoch": 0.9599063505999414,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004932801904050323,
|
|
"loss": 6.5311,
|
|
"mean_token_accuracy": 0.12398128062486649,
|
|
"num_tokens": 16440290.0,
|
|
"step": 4920
|
|
},
|
|
{
|
|
"entropy": 6.668986082077026,
|
|
"epoch": 0.9608818651838845,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004932631188594195,
|
|
"loss": 6.643,
|
|
"mean_token_accuracy": 0.13026585206389427,
|
|
"num_tokens": 16456904.0,
|
|
"step": 4925
|
|
},
|
|
{
|
|
"entropy": 6.6683837413787845,
|
|
"epoch": 0.9618573797678275,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004932460259859127,
|
|
"loss": 6.5621,
|
|
"mean_token_accuracy": 0.12911980003118514,
|
|
"num_tokens": 16473777.0,
|
|
"step": 4930
|
|
},
|
|
{
|
|
"entropy": 6.552981281280518,
|
|
"epoch": 0.9628328943517706,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004932289117861819,
|
|
"loss": 6.507,
|
|
"mean_token_accuracy": 0.12757593393325806,
|
|
"num_tokens": 16490401.0,
|
|
"step": 4935
|
|
},
|
|
{
|
|
"entropy": 6.630919027328491,
|
|
"epoch": 0.9638084089357136,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004932117762618997,
|
|
"loss": 6.5618,
|
|
"mean_token_accuracy": 0.12119901701807975,
|
|
"num_tokens": 16508582.0,
|
|
"step": 4940
|
|
},
|
|
{
|
|
"entropy": 6.672357892990112,
|
|
"epoch": 0.9647839235196566,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004931946194147404,
|
|
"loss": 6.6125,
|
|
"mean_token_accuracy": 0.12198699861764908,
|
|
"num_tokens": 16523939.0,
|
|
"step": 4945
|
|
},
|
|
{
|
|
"entropy": 6.557337045669556,
|
|
"epoch": 0.9657594381035997,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004931774412463806,
|
|
"loss": 6.5806,
|
|
"mean_token_accuracy": 0.12593406885862352,
|
|
"num_tokens": 16541139.0,
|
|
"step": 4950
|
|
},
|
|
{
|
|
"entropy": 6.721051263809204,
|
|
"epoch": 0.9667349526875427,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004931602417584989,
|
|
"loss": 6.6121,
|
|
"mean_token_accuracy": 0.11947675794363022,
|
|
"num_tokens": 16558351.0,
|
|
"step": 4955
|
|
},
|
|
{
|
|
"entropy": 6.6499754905700685,
|
|
"epoch": 0.9677104672714857,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004931430209527759,
|
|
"loss": 6.6603,
|
|
"mean_token_accuracy": 0.11794270351529121,
|
|
"num_tokens": 16575777.0,
|
|
"step": 4960
|
|
},
|
|
{
|
|
"entropy": 6.695547437667846,
|
|
"epoch": 0.9686859818554288,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004931257788308943,
|
|
"loss": 6.6188,
|
|
"mean_token_accuracy": 0.12605267986655236,
|
|
"num_tokens": 16592490.0,
|
|
"step": 4965
|
|
},
|
|
{
|
|
"entropy": 6.621754693984985,
|
|
"epoch": 0.9696614964393717,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000493108515394539,
|
|
"loss": 6.6084,
|
|
"mean_token_accuracy": 0.1257001869380474,
|
|
"num_tokens": 16610378.0,
|
|
"step": 4970
|
|
},
|
|
{
|
|
"entropy": 6.65980863571167,
|
|
"epoch": 0.9706370110233148,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004930912306453971,
|
|
"loss": 6.6547,
|
|
"mean_token_accuracy": 0.11664781272411347,
|
|
"num_tokens": 16625445.0,
|
|
"step": 4975
|
|
},
|
|
{
|
|
"entropy": 6.7707250118255615,
|
|
"epoch": 0.9716125256072579,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004930739245851571,
|
|
"loss": 6.6634,
|
|
"mean_token_accuracy": 0.11818922311067581,
|
|
"num_tokens": 16641821.0,
|
|
"step": 4980
|
|
},
|
|
{
|
|
"entropy": 6.687586498260498,
|
|
"epoch": 0.9725880401912008,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004930565972155106,
|
|
"loss": 6.6077,
|
|
"mean_token_accuracy": 0.11795932576060295,
|
|
"num_tokens": 16658418.0,
|
|
"step": 4985
|
|
},
|
|
{
|
|
"entropy": 6.633223676681519,
|
|
"epoch": 0.9735635547751439,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004930392485381506,
|
|
"loss": 6.6411,
|
|
"mean_token_accuracy": 0.12292293533682823,
|
|
"num_tokens": 16674218.0,
|
|
"step": 4990
|
|
},
|
|
{
|
|
"entropy": 6.626083421707153,
|
|
"epoch": 0.974539069359087,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004930218785547724,
|
|
"loss": 6.6344,
|
|
"mean_token_accuracy": 0.12941502556204795,
|
|
"num_tokens": 16692171.0,
|
|
"step": 4995
|
|
},
|
|
{
|
|
"entropy": 6.812588739395141,
|
|
"epoch": 0.9755145839430299,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004930044872670733,
|
|
"loss": 6.6919,
|
|
"mean_token_accuracy": 0.11611484512686729,
|
|
"num_tokens": 16709231.0,
|
|
"step": 5000
|
|
},
|
|
{
|
|
"entropy": 6.631097793579102,
|
|
"epoch": 0.976490098526973,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004929870746767525,
|
|
"loss": 6.6003,
|
|
"mean_token_accuracy": 0.12302238866686821,
|
|
"num_tokens": 16726281.0,
|
|
"step": 5005
|
|
},
|
|
{
|
|
"entropy": 6.678535747528076,
|
|
"epoch": 0.977465613110916,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004929696407855118,
|
|
"loss": 6.6629,
|
|
"mean_token_accuracy": 0.11728469282388687,
|
|
"num_tokens": 16744821.0,
|
|
"step": 5010
|
|
},
|
|
{
|
|
"entropy": 6.62296690940857,
|
|
"epoch": 0.978441127694859,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004929521855950546,
|
|
"loss": 6.4761,
|
|
"mean_token_accuracy": 0.12532831653952597,
|
|
"num_tokens": 16762564.0,
|
|
"step": 5015
|
|
},
|
|
{
|
|
"entropy": 6.537908267974854,
|
|
"epoch": 0.9794166422788021,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004929347091070866,
|
|
"loss": 6.4418,
|
|
"mean_token_accuracy": 0.13645802289247513,
|
|
"num_tokens": 16777681.0,
|
|
"step": 5020
|
|
},
|
|
{
|
|
"entropy": 6.642671203613281,
|
|
"epoch": 0.9803921568627451,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004929172113233157,
|
|
"loss": 6.6679,
|
|
"mean_token_accuracy": 0.1217079408466816,
|
|
"num_tokens": 16793820.0,
|
|
"step": 5025
|
|
},
|
|
{
|
|
"entropy": 6.697930383682251,
|
|
"epoch": 0.9813676714466881,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004928996922454515,
|
|
"loss": 6.661,
|
|
"mean_token_accuracy": 0.12151671722531318,
|
|
"num_tokens": 16811445.0,
|
|
"step": 5030
|
|
},
|
|
{
|
|
"entropy": 6.669512224197388,
|
|
"epoch": 0.9823431860306312,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004928821518752059,
|
|
"loss": 6.6281,
|
|
"mean_token_accuracy": 0.12296324074268342,
|
|
"num_tokens": 16827961.0,
|
|
"step": 5035
|
|
},
|
|
{
|
|
"entropy": 6.685556697845459,
|
|
"epoch": 0.9833187006145742,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004928645902142931,
|
|
"loss": 6.5085,
|
|
"mean_token_accuracy": 0.12533797919750214,
|
|
"num_tokens": 16844074.0,
|
|
"step": 5040
|
|
},
|
|
{
|
|
"entropy": 6.594580554962159,
|
|
"epoch": 0.9842942151985172,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000492847007264429,
|
|
"loss": 6.5567,
|
|
"mean_token_accuracy": 0.12318136021494866,
|
|
"num_tokens": 16862004.0,
|
|
"step": 5045
|
|
},
|
|
{
|
|
"entropy": 6.651034498214722,
|
|
"epoch": 0.9852697297824603,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004928294030273317,
|
|
"loss": 6.5728,
|
|
"mean_token_accuracy": 0.12023101672530175,
|
|
"num_tokens": 16879738.0,
|
|
"step": 5050
|
|
},
|
|
{
|
|
"entropy": 6.571604299545288,
|
|
"epoch": 0.9862452443664033,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004928117775047215,
|
|
"loss": 6.5189,
|
|
"mean_token_accuracy": 0.1304342307150364,
|
|
"num_tokens": 16896565.0,
|
|
"step": 5055
|
|
},
|
|
{
|
|
"entropy": 6.6606298923492435,
|
|
"epoch": 0.9872207589503463,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004927941306983207,
|
|
"loss": 6.5986,
|
|
"mean_token_accuracy": 0.12416143789887428,
|
|
"num_tokens": 16912443.0,
|
|
"step": 5060
|
|
},
|
|
{
|
|
"entropy": 6.7300214767456055,
|
|
"epoch": 0.9881962735342893,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004927764626098537,
|
|
"loss": 6.6451,
|
|
"mean_token_accuracy": 0.12084420844912529,
|
|
"num_tokens": 16928292.0,
|
|
"step": 5065
|
|
},
|
|
{
|
|
"entropy": 6.581207752227783,
|
|
"epoch": 0.9891717881182324,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000492758773241047,
|
|
"loss": 6.6149,
|
|
"mean_token_accuracy": 0.12660691365599633,
|
|
"num_tokens": 16945432.0,
|
|
"step": 5070
|
|
},
|
|
{
|
|
"entropy": 6.592297506332398,
|
|
"epoch": 0.9901473027021754,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000492741062593629,
|
|
"loss": 6.4377,
|
|
"mean_token_accuracy": 0.13518854454159737,
|
|
"num_tokens": 16962440.0,
|
|
"step": 5075
|
|
},
|
|
{
|
|
"entropy": 6.625493860244751,
|
|
"epoch": 0.9911228172861184,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004927233306693305,
|
|
"loss": 6.5453,
|
|
"mean_token_accuracy": 0.132390309125185,
|
|
"num_tokens": 16979227.0,
|
|
"step": 5080
|
|
},
|
|
{
|
|
"entropy": 6.639019393920899,
|
|
"epoch": 0.9920983318700615,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004927055774698839,
|
|
"loss": 6.6155,
|
|
"mean_token_accuracy": 0.11907379180192948,
|
|
"num_tokens": 16994873.0,
|
|
"step": 5085
|
|
},
|
|
{
|
|
"entropy": 6.709123754501343,
|
|
"epoch": 0.9930738464540045,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004926878029970245,
|
|
"loss": 6.6625,
|
|
"mean_token_accuracy": 0.12043715417385101,
|
|
"num_tokens": 17011516.0,
|
|
"step": 5090
|
|
},
|
|
{
|
|
"entropy": 6.6828512191772464,
|
|
"epoch": 0.9940493610379475,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004926700072524887,
|
|
"loss": 6.5558,
|
|
"mean_token_accuracy": 0.12185238450765609,
|
|
"num_tokens": 17029407.0,
|
|
"step": 5095
|
|
},
|
|
{
|
|
"entropy": 6.569974803924561,
|
|
"epoch": 0.9950248756218906,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004926521902380154,
|
|
"loss": 6.6213,
|
|
"mean_token_accuracy": 0.11747233867645264,
|
|
"num_tokens": 17044451.0,
|
|
"step": 5100
|
|
},
|
|
{
|
|
"entropy": 6.560687065124512,
|
|
"epoch": 0.9960003902058335,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004926343519553461,
|
|
"loss": 6.4607,
|
|
"mean_token_accuracy": 0.13538789376616478,
|
|
"num_tokens": 17060420.0,
|
|
"step": 5105
|
|
},
|
|
{
|
|
"entropy": 6.659314250946045,
|
|
"epoch": 0.9969759047897766,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004926164924062234,
|
|
"loss": 6.5825,
|
|
"mean_token_accuracy": 0.1263728991150856,
|
|
"num_tokens": 17076562.0,
|
|
"step": 5110
|
|
},
|
|
{
|
|
"entropy": 6.5243745803833,
|
|
"epoch": 0.9979514193737197,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004925986115923927,
|
|
"loss": 6.6253,
|
|
"mean_token_accuracy": 0.1355351284146309,
|
|
"num_tokens": 17092441.0,
|
|
"step": 5115
|
|
},
|
|
{
|
|
"entropy": 6.698624849319458,
|
|
"epoch": 0.9989269339576626,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004925807095156013,
|
|
"loss": 6.6156,
|
|
"mean_token_accuracy": 0.122457255423069,
|
|
"num_tokens": 17109447.0,
|
|
"step": 5120
|
|
},
|
|
{
|
|
"entropy": 6.58987455368042,
|
|
"epoch": 0.9999024485416057,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004925627861775983,
|
|
"loss": 6.5027,
|
|
"mean_token_accuracy": 0.12990742921829224,
|
|
"num_tokens": 17125795.0,
|
|
"step": 5125
|
|
},
|
|
{
|
|
"entropy": 6.596915245056152,
|
|
"epoch": 1.0007804116671544,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004925448415801353,
|
|
"loss": 6.5085,
|
|
"mean_token_accuracy": 0.1282887558142344,
|
|
"num_tokens": 17139062.0,
|
|
"step": 5130
|
|
},
|
|
{
|
|
"entropy": 6.662649250030517,
|
|
"epoch": 1.0017559262510976,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004925268757249657,
|
|
"loss": 6.5491,
|
|
"mean_token_accuracy": 0.11685445830225945,
|
|
"num_tokens": 17155465.0,
|
|
"step": 5135
|
|
},
|
|
{
|
|
"entropy": 6.652193307876587,
|
|
"epoch": 1.0027314408350405,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004925088886138451,
|
|
"loss": 6.4378,
|
|
"mean_token_accuracy": 0.12471524178981781,
|
|
"num_tokens": 17171284.0,
|
|
"step": 5140
|
|
},
|
|
{
|
|
"entropy": 6.490083503723144,
|
|
"epoch": 1.0037069554189835,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004924908802485311,
|
|
"loss": 6.3742,
|
|
"mean_token_accuracy": 0.13570912629365922,
|
|
"num_tokens": 17190823.0,
|
|
"step": 5145
|
|
},
|
|
{
|
|
"entropy": 6.649887275695801,
|
|
"epoch": 1.0046824700029267,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004924728506307835,
|
|
"loss": 6.4943,
|
|
"mean_token_accuracy": 0.12312807664275169,
|
|
"num_tokens": 17208866.0,
|
|
"step": 5150
|
|
},
|
|
{
|
|
"entropy": 6.63740644454956,
|
|
"epoch": 1.0056579845868696,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000492454799762364,
|
|
"loss": 6.5907,
|
|
"mean_token_accuracy": 0.11987160593271255,
|
|
"num_tokens": 17225609.0,
|
|
"step": 5155
|
|
},
|
|
{
|
|
"entropy": 6.712731170654297,
|
|
"epoch": 1.0066334991708126,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004924367276450364,
|
|
"loss": 6.5681,
|
|
"mean_token_accuracy": 0.12204663529992103,
|
|
"num_tokens": 17242198.0,
|
|
"step": 5160
|
|
},
|
|
{
|
|
"entropy": 6.602420902252197,
|
|
"epoch": 1.0076090137547555,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004924186342805669,
|
|
"loss": 6.5292,
|
|
"mean_token_accuracy": 0.12135994359850884,
|
|
"num_tokens": 17258712.0,
|
|
"step": 5165
|
|
},
|
|
{
|
|
"entropy": 6.625925064086914,
|
|
"epoch": 1.0085845283386987,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004924005196707233,
|
|
"loss": 6.5122,
|
|
"mean_token_accuracy": 0.1274842731654644,
|
|
"num_tokens": 17274790.0,
|
|
"step": 5170
|
|
},
|
|
{
|
|
"entropy": 6.671714973449707,
|
|
"epoch": 1.0095600429226417,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004923823838172756,
|
|
"loss": 6.4673,
|
|
"mean_token_accuracy": 0.12393850460648537,
|
|
"num_tokens": 17290526.0,
|
|
"step": 5175
|
|
},
|
|
{
|
|
"entropy": 6.591447734832764,
|
|
"epoch": 1.0105355575065846,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004923642267219962,
|
|
"loss": 6.5513,
|
|
"mean_token_accuracy": 0.1229638509452343,
|
|
"num_tokens": 17306022.0,
|
|
"step": 5180
|
|
},
|
|
{
|
|
"entropy": 6.650031518936157,
|
|
"epoch": 1.0115110720905278,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004923460483866593,
|
|
"loss": 6.5344,
|
|
"mean_token_accuracy": 0.12451162859797478,
|
|
"num_tokens": 17321601.0,
|
|
"step": 5185
|
|
},
|
|
{
|
|
"entropy": 6.438239049911499,
|
|
"epoch": 1.0124865866744708,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004923278488130412,
|
|
"loss": 6.3974,
|
|
"mean_token_accuracy": 0.1328222155570984,
|
|
"num_tokens": 17337997.0,
|
|
"step": 5190
|
|
},
|
|
{
|
|
"entropy": 6.646114301681519,
|
|
"epoch": 1.0134621012584137,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004923096280029202,
|
|
"loss": 6.4878,
|
|
"mean_token_accuracy": 0.12334999218583106,
|
|
"num_tokens": 17354809.0,
|
|
"step": 5195
|
|
},
|
|
{
|
|
"entropy": 6.572849988937378,
|
|
"epoch": 1.014437615842357,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000492291385958077,
|
|
"loss": 6.3549,
|
|
"mean_token_accuracy": 0.13586337342858315,
|
|
"num_tokens": 17371548.0,
|
|
"step": 5200
|
|
},
|
|
{
|
|
"entropy": 6.53950982093811,
|
|
"epoch": 1.0154131304262999,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004922731226802939,
|
|
"loss": 6.4701,
|
|
"mean_token_accuracy": 0.12709207460284233,
|
|
"num_tokens": 17388891.0,
|
|
"step": 5205
|
|
},
|
|
{
|
|
"entropy": 6.518743848800659,
|
|
"epoch": 1.0163886450102428,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004922548381713556,
|
|
"loss": 6.449,
|
|
"mean_token_accuracy": 0.13167748525738715,
|
|
"num_tokens": 17407501.0,
|
|
"step": 5210
|
|
},
|
|
{
|
|
"entropy": 6.56757345199585,
|
|
"epoch": 1.017364159594186,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004922365324330489,
|
|
"loss": 6.5082,
|
|
"mean_token_accuracy": 0.1273205004632473,
|
|
"num_tokens": 17425541.0,
|
|
"step": 5215
|
|
},
|
|
{
|
|
"entropy": 6.604098844528198,
|
|
"epoch": 1.018339674178129,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004922182054671625,
|
|
"loss": 6.4286,
|
|
"mean_token_accuracy": 0.12133291736245155,
|
|
"num_tokens": 17441588.0,
|
|
"step": 5220
|
|
},
|
|
{
|
|
"entropy": 6.5796490669250485,
|
|
"epoch": 1.019315188762072,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004921998572754872,
|
|
"loss": 6.432,
|
|
"mean_token_accuracy": 0.12967671304941178,
|
|
"num_tokens": 17458874.0,
|
|
"step": 5225
|
|
},
|
|
{
|
|
"entropy": 6.499201822280884,
|
|
"epoch": 1.0202907033460151,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004921814878598159,
|
|
"loss": 6.3816,
|
|
"mean_token_accuracy": 0.13181468173861505,
|
|
"num_tokens": 17475815.0,
|
|
"step": 5230
|
|
},
|
|
{
|
|
"entropy": 6.591932201385498,
|
|
"epoch": 1.021266217929958,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004921630972219437,
|
|
"loss": 6.4318,
|
|
"mean_token_accuracy": 0.12273628488183022,
|
|
"num_tokens": 17492068.0,
|
|
"step": 5235
|
|
},
|
|
{
|
|
"entropy": 6.494872617721557,
|
|
"epoch": 1.022241732513901,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004921446853636676,
|
|
"loss": 6.4259,
|
|
"mean_token_accuracy": 0.12693707570433616,
|
|
"num_tokens": 17508156.0,
|
|
"step": 5240
|
|
},
|
|
{
|
|
"entropy": 6.632508420944214,
|
|
"epoch": 1.023217247097844,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004921262522867869,
|
|
"loss": 6.5194,
|
|
"mean_token_accuracy": 0.12190214693546295,
|
|
"num_tokens": 17525374.0,
|
|
"step": 5245
|
|
},
|
|
{
|
|
"entropy": 6.607191038131714,
|
|
"epoch": 1.0241927616817872,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004921077979931026,
|
|
"loss": 6.4051,
|
|
"mean_token_accuracy": 0.1285308673977852,
|
|
"num_tokens": 17541453.0,
|
|
"step": 5250
|
|
},
|
|
{
|
|
"entropy": 6.586507844924927,
|
|
"epoch": 1.0251682762657301,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000492089322484418,
|
|
"loss": 6.4708,
|
|
"mean_token_accuracy": 0.1251534566283226,
|
|
"num_tokens": 17557981.0,
|
|
"step": 5255
|
|
},
|
|
{
|
|
"entropy": 6.556712818145752,
|
|
"epoch": 1.026143790849673,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004920708257625386,
|
|
"loss": 6.3651,
|
|
"mean_token_accuracy": 0.13043977618217467,
|
|
"num_tokens": 17573094.0,
|
|
"step": 5260
|
|
},
|
|
{
|
|
"entropy": 6.6070150375366214,
|
|
"epoch": 1.0271193054336163,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004920523078292718,
|
|
"loss": 6.5895,
|
|
"mean_token_accuracy": 0.12108369395136834,
|
|
"num_tokens": 17589933.0,
|
|
"step": 5265
|
|
},
|
|
{
|
|
"entropy": 6.6827788829803465,
|
|
"epoch": 1.0280948200175593,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004920337686864269,
|
|
"loss": 6.5161,
|
|
"mean_token_accuracy": 0.12310748770833016,
|
|
"num_tokens": 17607008.0,
|
|
"step": 5270
|
|
},
|
|
{
|
|
"entropy": 6.618128728866577,
|
|
"epoch": 1.0290703346015022,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004920152083358158,
|
|
"loss": 6.493,
|
|
"mean_token_accuracy": 0.13205681145191192,
|
|
"num_tokens": 17624160.0,
|
|
"step": 5275
|
|
},
|
|
{
|
|
"entropy": 6.582401514053345,
|
|
"epoch": 1.0300458491854454,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.000491996626779252,
|
|
"loss": 6.4393,
|
|
"mean_token_accuracy": 0.13004341647028922,
|
|
"num_tokens": 17640067.0,
|
|
"step": 5280
|
|
},
|
|
{
|
|
"entropy": 6.624403047561645,
|
|
"epoch": 1.0310213637693884,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004919780240185512,
|
|
"loss": 6.5151,
|
|
"mean_token_accuracy": 0.12554793059825897,
|
|
"num_tokens": 17658278.0,
|
|
"step": 5285
|
|
},
|
|
{
|
|
"entropy": 6.571302175521851,
|
|
"epoch": 1.0319968783533313,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004919594000555311,
|
|
"loss": 6.5057,
|
|
"mean_token_accuracy": 0.11933596730232239,
|
|
"num_tokens": 17673878.0,
|
|
"step": 5290
|
|
},
|
|
{
|
|
"entropy": 6.547737884521484,
|
|
"epoch": 1.0329723929372745,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004919407548920118,
|
|
"loss": 6.4443,
|
|
"mean_token_accuracy": 0.1272198125720024,
|
|
"num_tokens": 17688872.0,
|
|
"step": 5295
|
|
},
|
|
{
|
|
"entropy": 6.632787466049194,
|
|
"epoch": 1.0339479075212175,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000491922088529815,
|
|
"loss": 6.4685,
|
|
"mean_token_accuracy": 0.12183011472225189,
|
|
"num_tokens": 17704284.0,
|
|
"step": 5300
|
|
},
|
|
{
|
|
"entropy": 6.490485095977784,
|
|
"epoch": 1.0349234221051604,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004919034009707651,
|
|
"loss": 6.3441,
|
|
"mean_token_accuracy": 0.13623440861701966,
|
|
"num_tokens": 17721296.0,
|
|
"step": 5305
|
|
},
|
|
{
|
|
"entropy": 6.645764493942261,
|
|
"epoch": 1.0358989366891036,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004918846922166877,
|
|
"loss": 6.5354,
|
|
"mean_token_accuracy": 0.12314954772591591,
|
|
"num_tokens": 17738549.0,
|
|
"step": 5310
|
|
},
|
|
{
|
|
"entropy": 6.5780901432037355,
|
|
"epoch": 1.0368744512730466,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004918659622694111,
|
|
"loss": 6.4162,
|
|
"mean_token_accuracy": 0.1375381752848625,
|
|
"num_tokens": 17755297.0,
|
|
"step": 5315
|
|
},
|
|
{
|
|
"entropy": 6.555587387084961,
|
|
"epoch": 1.0378499658569895,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004918472111307658,
|
|
"loss": 6.4561,
|
|
"mean_token_accuracy": 0.12622232735157013,
|
|
"num_tokens": 17771459.0,
|
|
"step": 5320
|
|
},
|
|
{
|
|
"entropy": 6.538183307647705,
|
|
"epoch": 1.0388254804409325,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004918284388025837,
|
|
"loss": 6.4699,
|
|
"mean_token_accuracy": 0.12990106120705605,
|
|
"num_tokens": 17787009.0,
|
|
"step": 5325
|
|
},
|
|
{
|
|
"entropy": 6.584714746475219,
|
|
"epoch": 1.0398009950248757,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004918096452866995,
|
|
"loss": 6.4825,
|
|
"mean_token_accuracy": 0.12380722537636757,
|
|
"num_tokens": 17804643.0,
|
|
"step": 5330
|
|
},
|
|
{
|
|
"entropy": 6.647181034088135,
|
|
"epoch": 1.0407765096088186,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004917908305849493,
|
|
"loss": 6.5413,
|
|
"mean_token_accuracy": 0.12234015837311744,
|
|
"num_tokens": 17821104.0,
|
|
"step": 5335
|
|
},
|
|
{
|
|
"entropy": 6.647149229049683,
|
|
"epoch": 1.0417520241927616,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000491771994699172,
|
|
"loss": 6.5435,
|
|
"mean_token_accuracy": 0.1256248153746128,
|
|
"num_tokens": 17838094.0,
|
|
"step": 5340
|
|
},
|
|
{
|
|
"entropy": 6.447141313552857,
|
|
"epoch": 1.0427275387767048,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004917531376312079,
|
|
"loss": 6.3884,
|
|
"mean_token_accuracy": 0.13285162746906282,
|
|
"num_tokens": 17853856.0,
|
|
"step": 5345
|
|
},
|
|
{
|
|
"entropy": 6.611274147033692,
|
|
"epoch": 1.0437030533606477,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004917342593828997,
|
|
"loss": 6.5112,
|
|
"mean_token_accuracy": 0.11438147872686386,
|
|
"num_tokens": 17870032.0,
|
|
"step": 5350
|
|
},
|
|
{
|
|
"entropy": 6.506755828857422,
|
|
"epoch": 1.0446785679445907,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000491715359956092,
|
|
"loss": 6.3786,
|
|
"mean_token_accuracy": 0.13739703297615052,
|
|
"num_tokens": 17886384.0,
|
|
"step": 5355
|
|
},
|
|
{
|
|
"entropy": 6.7496544361114506,
|
|
"epoch": 1.0456540825285339,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004916964393526319,
|
|
"loss": 6.599,
|
|
"mean_token_accuracy": 0.1245718851685524,
|
|
"num_tokens": 17903444.0,
|
|
"step": 5360
|
|
},
|
|
{
|
|
"entropy": 6.604519414901733,
|
|
"epoch": 1.0466295971124768,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004916774975743679,
|
|
"loss": 6.4537,
|
|
"mean_token_accuracy": 0.1255309671163559,
|
|
"num_tokens": 17920042.0,
|
|
"step": 5365
|
|
},
|
|
{
|
|
"entropy": 6.484612989425659,
|
|
"epoch": 1.0476051116964198,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004916585346231513,
|
|
"loss": 6.4339,
|
|
"mean_token_accuracy": 0.14163719937205316,
|
|
"num_tokens": 17937115.0,
|
|
"step": 5370
|
|
},
|
|
{
|
|
"entropy": 6.62762417793274,
|
|
"epoch": 1.048580626280363,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004916395505008347,
|
|
"loss": 6.4792,
|
|
"mean_token_accuracy": 0.1252438932657242,
|
|
"num_tokens": 17953582.0,
|
|
"step": 5375
|
|
},
|
|
{
|
|
"entropy": 6.549891996383667,
|
|
"epoch": 1.049556140864306,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004916205452092735,
|
|
"loss": 6.489,
|
|
"mean_token_accuracy": 0.12088946253061295,
|
|
"num_tokens": 17970457.0,
|
|
"step": 5380
|
|
},
|
|
{
|
|
"entropy": 6.644790124893189,
|
|
"epoch": 1.050531655448249,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004916015187503245,
|
|
"loss": 6.4573,
|
|
"mean_token_accuracy": 0.13033200427889824,
|
|
"num_tokens": 17987168.0,
|
|
"step": 5385
|
|
},
|
|
{
|
|
"entropy": 6.431623411178589,
|
|
"epoch": 1.051507170032192,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004915824711258472,
|
|
"loss": 6.39,
|
|
"mean_token_accuracy": 0.1380588836967945,
|
|
"num_tokens": 18004964.0,
|
|
"step": 5390
|
|
},
|
|
{
|
|
"entropy": 6.593130970001221,
|
|
"epoch": 1.052482684616135,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004915634023377026,
|
|
"loss": 6.4792,
|
|
"mean_token_accuracy": 0.12763603702187537,
|
|
"num_tokens": 18021778.0,
|
|
"step": 5395
|
|
},
|
|
{
|
|
"entropy": 6.450467252731324,
|
|
"epoch": 1.053458199200078,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004915443123877543,
|
|
"loss": 6.3135,
|
|
"mean_token_accuracy": 0.13204340562224387,
|
|
"num_tokens": 18037620.0,
|
|
"step": 5400
|
|
},
|
|
{
|
|
"entropy": 6.587109661102295,
|
|
"epoch": 1.0544337137840212,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004915252012778676,
|
|
"loss": 6.4298,
|
|
"mean_token_accuracy": 0.12864309176802635,
|
|
"num_tokens": 18054623.0,
|
|
"step": 5405
|
|
},
|
|
{
|
|
"entropy": 6.508930730819702,
|
|
"epoch": 1.0554092283679641,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004915060690099098,
|
|
"loss": 6.4503,
|
|
"mean_token_accuracy": 0.1248053140938282,
|
|
"num_tokens": 18071271.0,
|
|
"step": 5410
|
|
},
|
|
{
|
|
"entropy": 6.640260648727417,
|
|
"epoch": 1.056384742951907,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004914869155857506,
|
|
"loss": 6.5114,
|
|
"mean_token_accuracy": 0.12000223621726036,
|
|
"num_tokens": 18087661.0,
|
|
"step": 5415
|
|
},
|
|
{
|
|
"entropy": 6.534674119949341,
|
|
"epoch": 1.05736025753585,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004914677410072616,
|
|
"loss": 6.4185,
|
|
"mean_token_accuracy": 0.1311955474317074,
|
|
"num_tokens": 18106116.0,
|
|
"step": 5420
|
|
},
|
|
{
|
|
"entropy": 6.629261684417725,
|
|
"epoch": 1.0583357721197932,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004914485452763165,
|
|
"loss": 6.5167,
|
|
"mean_token_accuracy": 0.12160368859767914,
|
|
"num_tokens": 18122420.0,
|
|
"step": 5425
|
|
},
|
|
{
|
|
"entropy": 6.619902229309082,
|
|
"epoch": 1.0593112867037362,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000491429328394791,
|
|
"loss": 6.535,
|
|
"mean_token_accuracy": 0.12085146531462669,
|
|
"num_tokens": 18137974.0,
|
|
"step": 5430
|
|
},
|
|
{
|
|
"entropy": 6.4901636123657225,
|
|
"epoch": 1.0602868012876792,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004914100903645629,
|
|
"loss": 6.3607,
|
|
"mean_token_accuracy": 0.13631421253085135,
|
|
"num_tokens": 18154711.0,
|
|
"step": 5435
|
|
},
|
|
{
|
|
"entropy": 6.599040079116821,
|
|
"epoch": 1.0612623158716223,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000491390831187512,
|
|
"loss": 6.5359,
|
|
"mean_token_accuracy": 0.12500369027256966,
|
|
"num_tokens": 18172422.0,
|
|
"step": 5440
|
|
},
|
|
{
|
|
"entropy": 6.499564504623413,
|
|
"epoch": 1.0622378304555653,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004913715508655203,
|
|
"loss": 6.4072,
|
|
"mean_token_accuracy": 0.13683367073535918,
|
|
"num_tokens": 18189517.0,
|
|
"step": 5445
|
|
},
|
|
{
|
|
"entropy": 6.563850593566895,
|
|
"epoch": 1.0632133450395083,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004913522494004719,
|
|
"loss": 6.4633,
|
|
"mean_token_accuracy": 0.11954438388347625,
|
|
"num_tokens": 18206339.0,
|
|
"step": 5450
|
|
},
|
|
{
|
|
"entropy": 6.511515474319458,
|
|
"epoch": 1.0641888596234514,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004913329267942527,
|
|
"loss": 6.3322,
|
|
"mean_token_accuracy": 0.13666890412569047,
|
|
"num_tokens": 18223953.0,
|
|
"step": 5455
|
|
},
|
|
{
|
|
"entropy": 6.656779623031616,
|
|
"epoch": 1.0651643742073944,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000491313583048751,
|
|
"loss": 6.4499,
|
|
"mean_token_accuracy": 0.1283232867717743,
|
|
"num_tokens": 18241361.0,
|
|
"step": 5460
|
|
},
|
|
{
|
|
"entropy": 6.47305645942688,
|
|
"epoch": 1.0661398887913374,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004912942181658569,
|
|
"loss": 6.4726,
|
|
"mean_token_accuracy": 0.1302261881530285,
|
|
"num_tokens": 18257897.0,
|
|
"step": 5465
|
|
},
|
|
{
|
|
"entropy": 6.615524625778198,
|
|
"epoch": 1.0671154033752805,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004912748321474627,
|
|
"loss": 6.479,
|
|
"mean_token_accuracy": 0.12725064158439636,
|
|
"num_tokens": 18274935.0,
|
|
"step": 5470
|
|
},
|
|
{
|
|
"entropy": 6.532500886917115,
|
|
"epoch": 1.0680909179592235,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004912554249954626,
|
|
"loss": 6.5346,
|
|
"mean_token_accuracy": 0.12413807064294816,
|
|
"num_tokens": 18292529.0,
|
|
"step": 5475
|
|
},
|
|
{
|
|
"entropy": 6.630389213562012,
|
|
"epoch": 1.0690664325431665,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004912359967117532,
|
|
"loss": 6.4784,
|
|
"mean_token_accuracy": 0.1240428201854229,
|
|
"num_tokens": 18310278.0,
|
|
"step": 5480
|
|
},
|
|
{
|
|
"entropy": 6.594868898391724,
|
|
"epoch": 1.0700419471271096,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004912165472982329,
|
|
"loss": 6.4819,
|
|
"mean_token_accuracy": 0.13026003912091255,
|
|
"num_tokens": 18326972.0,
|
|
"step": 5485
|
|
},
|
|
{
|
|
"entropy": 6.567061138153076,
|
|
"epoch": 1.0710174617110526,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004911970767568022,
|
|
"loss": 6.5815,
|
|
"mean_token_accuracy": 0.1251130685210228,
|
|
"num_tokens": 18345065.0,
|
|
"step": 5490
|
|
},
|
|
{
|
|
"entropy": 6.609437704086304,
|
|
"epoch": 1.0719929762949956,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004911775850893637,
|
|
"loss": 6.5124,
|
|
"mean_token_accuracy": 0.125931616127491,
|
|
"num_tokens": 18363251.0,
|
|
"step": 5495
|
|
},
|
|
{
|
|
"entropy": 6.5563764572143555,
|
|
"epoch": 1.0729684908789388,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000491158072297822,
|
|
"loss": 6.3532,
|
|
"mean_token_accuracy": 0.13417559415102004,
|
|
"num_tokens": 18378650.0,
|
|
"step": 5500
|
|
},
|
|
{
|
|
"entropy": 6.555327129364014,
|
|
"epoch": 1.0739440054628817,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004911385383840839,
|
|
"loss": 6.5025,
|
|
"mean_token_accuracy": 0.12478141784667969,
|
|
"num_tokens": 18394533.0,
|
|
"step": 5505
|
|
},
|
|
{
|
|
"entropy": 6.637202644348145,
|
|
"epoch": 1.0749195200468247,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004911189833500582,
|
|
"loss": 6.5374,
|
|
"mean_token_accuracy": 0.12420445084571838,
|
|
"num_tokens": 18410752.0,
|
|
"step": 5510
|
|
},
|
|
{
|
|
"entropy": 6.428289270401001,
|
|
"epoch": 1.0758950346307676,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004910994071976556,
|
|
"loss": 6.3321,
|
|
"mean_token_accuracy": 0.13563249707221986,
|
|
"num_tokens": 18428027.0,
|
|
"step": 5515
|
|
},
|
|
{
|
|
"entropy": 6.530197095870972,
|
|
"epoch": 1.0768705492147108,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004910798099287894,
|
|
"loss": 6.4039,
|
|
"mean_token_accuracy": 0.13054279163479804,
|
|
"num_tokens": 18446380.0,
|
|
"step": 5520
|
|
},
|
|
{
|
|
"entropy": 6.486781263351441,
|
|
"epoch": 1.0778460637986538,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000491060191545374,
|
|
"loss": 6.3542,
|
|
"mean_token_accuracy": 0.14291133135557174,
|
|
"num_tokens": 18464628.0,
|
|
"step": 5525
|
|
},
|
|
{
|
|
"entropy": 6.507884740829468,
|
|
"epoch": 1.0788215783825967,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004910405520493268,
|
|
"loss": 6.4474,
|
|
"mean_token_accuracy": 0.1286935307085514,
|
|
"num_tokens": 18479995.0,
|
|
"step": 5530
|
|
},
|
|
{
|
|
"entropy": 6.588743066787719,
|
|
"epoch": 1.07979709296654,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004910208914425669,
|
|
"loss": 6.5018,
|
|
"mean_token_accuracy": 0.12521815448999404,
|
|
"num_tokens": 18497143.0,
|
|
"step": 5535
|
|
},
|
|
{
|
|
"entropy": 6.614776659011841,
|
|
"epoch": 1.0807726075504829,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004910012097270153,
|
|
"loss": 6.4785,
|
|
"mean_token_accuracy": 0.12295236065983772,
|
|
"num_tokens": 18513428.0,
|
|
"step": 5540
|
|
},
|
|
{
|
|
"entropy": 6.6159947395324705,
|
|
"epoch": 1.0817481221344258,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004909815069045955,
|
|
"loss": 6.5705,
|
|
"mean_token_accuracy": 0.12293544039130211,
|
|
"num_tokens": 18529475.0,
|
|
"step": 5545
|
|
},
|
|
{
|
|
"entropy": 6.6814250469207765,
|
|
"epoch": 1.082723636718369,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004909617829772325,
|
|
"loss": 6.5023,
|
|
"mean_token_accuracy": 0.12687653601169585,
|
|
"num_tokens": 18546156.0,
|
|
"step": 5550
|
|
},
|
|
{
|
|
"entropy": 6.430613374710083,
|
|
"epoch": 1.083699151302312,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004909420379468537,
|
|
"loss": 6.2898,
|
|
"mean_token_accuracy": 0.15224805250763893,
|
|
"num_tokens": 18562719.0,
|
|
"step": 5555
|
|
},
|
|
{
|
|
"entropy": 6.5273730754852295,
|
|
"epoch": 1.084674665886255,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004909222718153887,
|
|
"loss": 6.4652,
|
|
"mean_token_accuracy": 0.13347663059830667,
|
|
"num_tokens": 18580123.0,
|
|
"step": 5560
|
|
},
|
|
{
|
|
"entropy": 6.531805229187012,
|
|
"epoch": 1.0856501804701981,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004909024845847689,
|
|
"loss": 6.3738,
|
|
"mean_token_accuracy": 0.1292390413582325,
|
|
"num_tokens": 18597003.0,
|
|
"step": 5565
|
|
},
|
|
{
|
|
"entropy": 6.566313886642456,
|
|
"epoch": 1.086625695054141,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004908826762569276,
|
|
"loss": 6.4631,
|
|
"mean_token_accuracy": 0.12568305507302285,
|
|
"num_tokens": 18613812.0,
|
|
"step": 5570
|
|
},
|
|
{
|
|
"entropy": 6.441074657440185,
|
|
"epoch": 1.087601209638084,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004908628468338008,
|
|
"loss": 6.4006,
|
|
"mean_token_accuracy": 0.13834046721458435,
|
|
"num_tokens": 18630333.0,
|
|
"step": 5575
|
|
},
|
|
{
|
|
"entropy": 6.5953254222869875,
|
|
"epoch": 1.088576724222027,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000490842996317326,
|
|
"loss": 6.4879,
|
|
"mean_token_accuracy": 0.122976104170084,
|
|
"num_tokens": 18646784.0,
|
|
"step": 5580
|
|
},
|
|
{
|
|
"entropy": 6.554603576660156,
|
|
"epoch": 1.0895522388059702,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004908231247094427,
|
|
"loss": 6.4557,
|
|
"mean_token_accuracy": 0.13023305535316468,
|
|
"num_tokens": 18664358.0,
|
|
"step": 5585
|
|
},
|
|
{
|
|
"entropy": 6.545828914642334,
|
|
"epoch": 1.0905277533899131,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004908032320120929,
|
|
"loss": 6.376,
|
|
"mean_token_accuracy": 0.1292611226439476,
|
|
"num_tokens": 18681849.0,
|
|
"step": 5590
|
|
},
|
|
{
|
|
"entropy": 6.59822416305542,
|
|
"epoch": 1.091503267973856,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004907833182272204,
|
|
"loss": 6.4888,
|
|
"mean_token_accuracy": 0.12697385102510453,
|
|
"num_tokens": 18697127.0,
|
|
"step": 5595
|
|
},
|
|
{
|
|
"entropy": 6.419705057144165,
|
|
"epoch": 1.0924787825577993,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004907633833567711,
|
|
"loss": 6.4277,
|
|
"mean_token_accuracy": 0.13404160514473915,
|
|
"num_tokens": 18714859.0,
|
|
"step": 5600
|
|
},
|
|
{
|
|
"entropy": 6.604875898361206,
|
|
"epoch": 1.0934542971417422,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000490743427402693,
|
|
"loss": 6.4472,
|
|
"mean_token_accuracy": 0.12782273665070534,
|
|
"num_tokens": 18730083.0,
|
|
"step": 5605
|
|
},
|
|
{
|
|
"entropy": 6.511402750015259,
|
|
"epoch": 1.0944298117256852,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004907234503669361,
|
|
"loss": 6.3933,
|
|
"mean_token_accuracy": 0.1279137946665287,
|
|
"num_tokens": 18746694.0,
|
|
"step": 5610
|
|
},
|
|
{
|
|
"entropy": 6.620362091064453,
|
|
"epoch": 1.0954053263096284,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004907034522514524,
|
|
"loss": 6.4669,
|
|
"mean_token_accuracy": 0.12902965620160103,
|
|
"num_tokens": 18764333.0,
|
|
"step": 5615
|
|
},
|
|
{
|
|
"entropy": 6.53497838973999,
|
|
"epoch": 1.0963808408935714,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004906834330581963,
|
|
"loss": 6.4664,
|
|
"mean_token_accuracy": 0.12389565780758857,
|
|
"num_tokens": 18780309.0,
|
|
"step": 5620
|
|
},
|
|
{
|
|
"entropy": 6.547825765609741,
|
|
"epoch": 1.0973563554775143,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004906633927891237,
|
|
"loss": 6.478,
|
|
"mean_token_accuracy": 0.12841159999370574,
|
|
"num_tokens": 18797322.0,
|
|
"step": 5625
|
|
},
|
|
{
|
|
"entropy": 6.588565540313721,
|
|
"epoch": 1.0983318700614575,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000490643331446193,
|
|
"loss": 6.5036,
|
|
"mean_token_accuracy": 0.1253478355705738,
|
|
"num_tokens": 18813185.0,
|
|
"step": 5630
|
|
},
|
|
{
|
|
"entropy": 6.490045690536499,
|
|
"epoch": 1.0993073846454005,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004906232490313646,
|
|
"loss": 6.407,
|
|
"mean_token_accuracy": 0.13243664652109147,
|
|
"num_tokens": 18829445.0,
|
|
"step": 5635
|
|
},
|
|
{
|
|
"entropy": 6.560099935531616,
|
|
"epoch": 1.1002828992293434,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004906031455466008,
|
|
"loss": 6.5497,
|
|
"mean_token_accuracy": 0.12305900380015374,
|
|
"num_tokens": 18846229.0,
|
|
"step": 5640
|
|
},
|
|
{
|
|
"entropy": 6.574111080169677,
|
|
"epoch": 1.1012584138132866,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004905830209938659,
|
|
"loss": 6.5157,
|
|
"mean_token_accuracy": 0.12333257123827934,
|
|
"num_tokens": 18861904.0,
|
|
"step": 5645
|
|
},
|
|
{
|
|
"entropy": 6.605819416046143,
|
|
"epoch": 1.1022339283972296,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004905628753751267,
|
|
"loss": 6.5473,
|
|
"mean_token_accuracy": 0.12370965853333474,
|
|
"num_tokens": 18879160.0,
|
|
"step": 5650
|
|
},
|
|
{
|
|
"entropy": 6.63520450592041,
|
|
"epoch": 1.1032094429811725,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004905427086923515,
|
|
"loss": 6.5071,
|
|
"mean_token_accuracy": 0.11914285346865654,
|
|
"num_tokens": 18895388.0,
|
|
"step": 5655
|
|
},
|
|
{
|
|
"entropy": 6.556660747528076,
|
|
"epoch": 1.1041849575651157,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000490522520947511,
|
|
"loss": 6.4541,
|
|
"mean_token_accuracy": 0.12643730267882347,
|
|
"num_tokens": 18912392.0,
|
|
"step": 5660
|
|
},
|
|
{
|
|
"entropy": 6.560411977767944,
|
|
"epoch": 1.1051604721490587,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004905023121425779,
|
|
"loss": 6.4524,
|
|
"mean_token_accuracy": 0.12493916451931,
|
|
"num_tokens": 18928721.0,
|
|
"step": 5665
|
|
},
|
|
{
|
|
"entropy": 6.638048696517944,
|
|
"epoch": 1.1061359867330016,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000490482082279527,
|
|
"loss": 6.517,
|
|
"mean_token_accuracy": 0.12104974538087845,
|
|
"num_tokens": 18947144.0,
|
|
"step": 5670
|
|
},
|
|
{
|
|
"entropy": 6.535524892807007,
|
|
"epoch": 1.1071115013169446,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000490461831360335,
|
|
"loss": 6.4502,
|
|
"mean_token_accuracy": 0.1259155109524727,
|
|
"num_tokens": 18963682.0,
|
|
"step": 5675
|
|
},
|
|
{
|
|
"entropy": 6.570698833465576,
|
|
"epoch": 1.1080870159008878,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004904415593869806,
|
|
"loss": 6.4738,
|
|
"mean_token_accuracy": 0.12692107632756233,
|
|
"num_tokens": 18980812.0,
|
|
"step": 5680
|
|
},
|
|
{
|
|
"entropy": 6.600488519668579,
|
|
"epoch": 1.1090625304848307,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004904212663614452,
|
|
"loss": 6.4607,
|
|
"mean_token_accuracy": 0.12653002366423607,
|
|
"num_tokens": 18996816.0,
|
|
"step": 5685
|
|
},
|
|
{
|
|
"entropy": 6.514034080505371,
|
|
"epoch": 1.1100380450687737,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004904009522857111,
|
|
"loss": 6.4643,
|
|
"mean_token_accuracy": 0.12371735200285912,
|
|
"num_tokens": 19012324.0,
|
|
"step": 5690
|
|
},
|
|
{
|
|
"entropy": 6.493304824829101,
|
|
"epoch": 1.1110135596527169,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004903806171617638,
|
|
"loss": 6.3067,
|
|
"mean_token_accuracy": 0.1370067186653614,
|
|
"num_tokens": 19030195.0,
|
|
"step": 5695
|
|
},
|
|
{
|
|
"entropy": 6.4784034252166744,
|
|
"epoch": 1.1119890742366598,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004903602609915901,
|
|
"loss": 6.3233,
|
|
"mean_token_accuracy": 0.13605086356401444,
|
|
"num_tokens": 19048467.0,
|
|
"step": 5700
|
|
},
|
|
{
|
|
"entropy": 6.4795104503631595,
|
|
"epoch": 1.1129645888206028,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004903398837771794,
|
|
"loss": 6.4237,
|
|
"mean_token_accuracy": 0.13188365772366523,
|
|
"num_tokens": 19066290.0,
|
|
"step": 5705
|
|
},
|
|
{
|
|
"entropy": 6.430404090881348,
|
|
"epoch": 1.113940103404546,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004903194855205227,
|
|
"loss": 6.351,
|
|
"mean_token_accuracy": 0.13573224246501922,
|
|
"num_tokens": 19083455.0,
|
|
"step": 5710
|
|
},
|
|
{
|
|
"entropy": 6.546180343627929,
|
|
"epoch": 1.114915617988489,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004902990662236132,
|
|
"loss": 6.4189,
|
|
"mean_token_accuracy": 0.12527831569314002,
|
|
"num_tokens": 19100347.0,
|
|
"step": 5715
|
|
},
|
|
{
|
|
"entropy": 6.507894659042359,
|
|
"epoch": 1.1158911325724319,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004902786258884463,
|
|
"loss": 6.4563,
|
|
"mean_token_accuracy": 0.1286146141588688,
|
|
"num_tokens": 19117379.0,
|
|
"step": 5720
|
|
},
|
|
{
|
|
"entropy": 6.573186254501342,
|
|
"epoch": 1.116866647156375,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004902581645170194,
|
|
"loss": 6.4056,
|
|
"mean_token_accuracy": 0.1359679475426674,
|
|
"num_tokens": 19134751.0,
|
|
"step": 5725
|
|
},
|
|
{
|
|
"entropy": 6.536538696289062,
|
|
"epoch": 1.117842161740318,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004902376821113319,
|
|
"loss": 6.4635,
|
|
"mean_token_accuracy": 0.12697202786803247,
|
|
"num_tokens": 19150647.0,
|
|
"step": 5730
|
|
},
|
|
{
|
|
"entropy": 6.4569262027740475,
|
|
"epoch": 1.118817676324261,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004902171786733852,
|
|
"loss": 6.4297,
|
|
"mean_token_accuracy": 0.12503438964486122,
|
|
"num_tokens": 19166654.0,
|
|
"step": 5735
|
|
},
|
|
{
|
|
"entropy": 6.578834152221679,
|
|
"epoch": 1.1197931909082042,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004901966542051828,
|
|
"loss": 6.441,
|
|
"mean_token_accuracy": 0.12763153091073037,
|
|
"num_tokens": 19182787.0,
|
|
"step": 5740
|
|
},
|
|
{
|
|
"entropy": 6.5263933658599855,
|
|
"epoch": 1.1207687054921471,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004901761087087303,
|
|
"loss": 6.4258,
|
|
"mean_token_accuracy": 0.12796253338456154,
|
|
"num_tokens": 19200218.0,
|
|
"step": 5745
|
|
},
|
|
{
|
|
"entropy": 6.5948272228240965,
|
|
"epoch": 1.12174422007609,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004901555421860354,
|
|
"loss": 6.5197,
|
|
"mean_token_accuracy": 0.12886387407779692,
|
|
"num_tokens": 19217310.0,
|
|
"step": 5750
|
|
},
|
|
{
|
|
"entropy": 6.6174171447753904,
|
|
"epoch": 1.1227197346600333,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004901349546391078,
|
|
"loss": 6.4659,
|
|
"mean_token_accuracy": 0.12403839826583862,
|
|
"num_tokens": 19233293.0,
|
|
"step": 5755
|
|
},
|
|
{
|
|
"entropy": 6.48001012802124,
|
|
"epoch": 1.1236952492439762,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004901143460699592,
|
|
"loss": 6.3735,
|
|
"mean_token_accuracy": 0.13677070215344428,
|
|
"num_tokens": 19250606.0,
|
|
"step": 5760
|
|
},
|
|
{
|
|
"entropy": 6.460719966888428,
|
|
"epoch": 1.1246707638279192,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004900937164806033,
|
|
"loss": 6.3443,
|
|
"mean_token_accuracy": 0.13824956640601158,
|
|
"num_tokens": 19267848.0,
|
|
"step": 5765
|
|
},
|
|
{
|
|
"entropy": 6.567539358139038,
|
|
"epoch": 1.1256462784118622,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004900730658730561,
|
|
"loss": 6.4437,
|
|
"mean_token_accuracy": 0.13009870797395706,
|
|
"num_tokens": 19284317.0,
|
|
"step": 5770
|
|
},
|
|
{
|
|
"entropy": 6.508305788040161,
|
|
"epoch": 1.1266217929958053,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004900523942493353,
|
|
"loss": 6.3976,
|
|
"mean_token_accuracy": 0.1312617041170597,
|
|
"num_tokens": 19300766.0,
|
|
"step": 5775
|
|
},
|
|
{
|
|
"entropy": 6.523960161209106,
|
|
"epoch": 1.1275973075797483,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004900317016114611,
|
|
"loss": 6.3849,
|
|
"mean_token_accuracy": 0.13123794496059418,
|
|
"num_tokens": 19316966.0,
|
|
"step": 5780
|
|
},
|
|
{
|
|
"entropy": 6.493864965438843,
|
|
"epoch": 1.1285728221636913,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004900109879614554,
|
|
"loss": 6.468,
|
|
"mean_token_accuracy": 0.12624579891562462,
|
|
"num_tokens": 19334389.0,
|
|
"step": 5785
|
|
},
|
|
{
|
|
"entropy": 6.654735565185547,
|
|
"epoch": 1.1295483367476344,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004899902533013423,
|
|
"loss": 6.4922,
|
|
"mean_token_accuracy": 0.12549679204821587,
|
|
"num_tokens": 19350238.0,
|
|
"step": 5790
|
|
},
|
|
{
|
|
"entropy": 6.577755975723266,
|
|
"epoch": 1.1305238513315774,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004899694976331478,
|
|
"loss": 6.4343,
|
|
"mean_token_accuracy": 0.12250350043177605,
|
|
"num_tokens": 19367244.0,
|
|
"step": 5795
|
|
},
|
|
{
|
|
"entropy": 6.526617193222046,
|
|
"epoch": 1.1314993659155204,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004899487209589001,
|
|
"loss": 6.4441,
|
|
"mean_token_accuracy": 0.12574658319354057,
|
|
"num_tokens": 19384949.0,
|
|
"step": 5800
|
|
},
|
|
{
|
|
"entropy": 6.610388278961182,
|
|
"epoch": 1.1324748804994635,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004899279232806297,
|
|
"loss": 6.5365,
|
|
"mean_token_accuracy": 0.12342826351523399,
|
|
"num_tokens": 19402149.0,
|
|
"step": 5805
|
|
},
|
|
{
|
|
"entropy": 6.506670379638672,
|
|
"epoch": 1.1334503950834065,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004899071046003686,
|
|
"loss": 6.415,
|
|
"mean_token_accuracy": 0.1276380516588688,
|
|
"num_tokens": 19419032.0,
|
|
"step": 5810
|
|
},
|
|
{
|
|
"entropy": 6.523136186599731,
|
|
"epoch": 1.1344259096673495,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004898862649201511,
|
|
"loss": 6.4389,
|
|
"mean_token_accuracy": 0.1293345682322979,
|
|
"num_tokens": 19435656.0,
|
|
"step": 5815
|
|
},
|
|
{
|
|
"entropy": 6.463804817199707,
|
|
"epoch": 1.1354014242512926,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004898654042420137,
|
|
"loss": 6.3675,
|
|
"mean_token_accuracy": 0.1348014935851097,
|
|
"num_tokens": 19451482.0,
|
|
"step": 5820
|
|
},
|
|
{
|
|
"entropy": 6.57603964805603,
|
|
"epoch": 1.1363769388352356,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004898445225679948,
|
|
"loss": 6.5038,
|
|
"mean_token_accuracy": 0.12616358026862146,
|
|
"num_tokens": 19467758.0,
|
|
"step": 5825
|
|
},
|
|
{
|
|
"entropy": 6.611044216156006,
|
|
"epoch": 1.1373524534191786,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004898236199001347,
|
|
"loss": 6.5057,
|
|
"mean_token_accuracy": 0.11911980733275414,
|
|
"num_tokens": 19483673.0,
|
|
"step": 5830
|
|
},
|
|
{
|
|
"entropy": 6.612524557113647,
|
|
"epoch": 1.1383279680031215,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004898026962404762,
|
|
"loss": 6.5588,
|
|
"mean_token_accuracy": 0.12010793536901473,
|
|
"num_tokens": 19500171.0,
|
|
"step": 5835
|
|
},
|
|
{
|
|
"entropy": 6.5147035121917725,
|
|
"epoch": 1.1393034825870647,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004897817515910639,
|
|
"loss": 6.3843,
|
|
"mean_token_accuracy": 0.13616218343377112,
|
|
"num_tokens": 19516531.0,
|
|
"step": 5840
|
|
},
|
|
{
|
|
"entropy": 6.557428073883057,
|
|
"epoch": 1.1402789971710077,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004897607859539443,
|
|
"loss": 6.495,
|
|
"mean_token_accuracy": 0.12165050432085991,
|
|
"num_tokens": 19534289.0,
|
|
"step": 5845
|
|
},
|
|
{
|
|
"entropy": 6.408714723587036,
|
|
"epoch": 1.1412545117549509,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000489739799331166,
|
|
"loss": 6.2956,
|
|
"mean_token_accuracy": 0.13851187378168106,
|
|
"num_tokens": 19550190.0,
|
|
"step": 5850
|
|
},
|
|
{
|
|
"entropy": 6.416967487335205,
|
|
"epoch": 1.1422300263388938,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00048971879172478,
|
|
"loss": 6.2373,
|
|
"mean_token_accuracy": 0.14037353694438934,
|
|
"num_tokens": 19567774.0,
|
|
"step": 5855
|
|
},
|
|
{
|
|
"entropy": 6.602610683441162,
|
|
"epoch": 1.1432055409228368,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004896977631368389,
|
|
"loss": 6.5161,
|
|
"mean_token_accuracy": 0.11956854313611984,
|
|
"num_tokens": 19583690.0,
|
|
"step": 5860
|
|
},
|
|
{
|
|
"entropy": 6.5007750511169435,
|
|
"epoch": 1.1441810555067797,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004896767135693976,
|
|
"loss": 6.3584,
|
|
"mean_token_accuracy": 0.137470730394125,
|
|
"num_tokens": 19600563.0,
|
|
"step": 5865
|
|
},
|
|
{
|
|
"entropy": 6.479723024368286,
|
|
"epoch": 1.145156570090723,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000489655643024513,
|
|
"loss": 6.4098,
|
|
"mean_token_accuracy": 0.1324410058557987,
|
|
"num_tokens": 19618043.0,
|
|
"step": 5870
|
|
},
|
|
{
|
|
"entropy": 6.534117031097412,
|
|
"epoch": 1.1461320846746659,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004896345515042439,
|
|
"loss": 6.4611,
|
|
"mean_token_accuracy": 0.13174949660897256,
|
|
"num_tokens": 19634807.0,
|
|
"step": 5875
|
|
},
|
|
{
|
|
"entropy": 6.460294485092163,
|
|
"epoch": 1.1471075992586088,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004896134390106515,
|
|
"loss": 6.3274,
|
|
"mean_token_accuracy": 0.13763210251927377,
|
|
"num_tokens": 19650814.0,
|
|
"step": 5880
|
|
},
|
|
{
|
|
"entropy": 6.363318681716919,
|
|
"epoch": 1.148083113842552,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004895923055457987,
|
|
"loss": 6.269,
|
|
"mean_token_accuracy": 0.14773210510611534,
|
|
"num_tokens": 19666293.0,
|
|
"step": 5885
|
|
},
|
|
{
|
|
"entropy": 6.441751766204834,
|
|
"epoch": 1.149058628426495,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004895711511117506,
|
|
"loss": 6.3512,
|
|
"mean_token_accuracy": 0.1351919375360012,
|
|
"num_tokens": 19682549.0,
|
|
"step": 5890
|
|
},
|
|
{
|
|
"entropy": 6.522295570373535,
|
|
"epoch": 1.150034143010438,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004895499757105743,
|
|
"loss": 6.4347,
|
|
"mean_token_accuracy": 0.12619928047060966,
|
|
"num_tokens": 19697776.0,
|
|
"step": 5895
|
|
},
|
|
{
|
|
"entropy": 6.486112785339356,
|
|
"epoch": 1.1510096575943811,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004895287793443391,
|
|
"loss": 6.3703,
|
|
"mean_token_accuracy": 0.1375209853053093,
|
|
"num_tokens": 19715219.0,
|
|
"step": 5900
|
|
},
|
|
{
|
|
"entropy": 6.462946367263794,
|
|
"epoch": 1.151985172178324,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004895075620151162,
|
|
"loss": 6.4108,
|
|
"mean_token_accuracy": 0.1331235684454441,
|
|
"num_tokens": 19731934.0,
|
|
"step": 5905
|
|
},
|
|
{
|
|
"entropy": 6.44971079826355,
|
|
"epoch": 1.152960686762267,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004894863237249789,
|
|
"loss": 6.4071,
|
|
"mean_token_accuracy": 0.13736931830644608,
|
|
"num_tokens": 19748933.0,
|
|
"step": 5910
|
|
},
|
|
{
|
|
"entropy": 6.568155002593994,
|
|
"epoch": 1.1539362013462102,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004894650644760024,
|
|
"loss": 6.4396,
|
|
"mean_token_accuracy": 0.12765090987086297,
|
|
"num_tokens": 19765430.0,
|
|
"step": 5915
|
|
},
|
|
{
|
|
"entropy": 6.588688039779663,
|
|
"epoch": 1.1549117159301532,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004894437842702642,
|
|
"loss": 6.4863,
|
|
"mean_token_accuracy": 0.1251302592456341,
|
|
"num_tokens": 19783626.0,
|
|
"step": 5920
|
|
},
|
|
{
|
|
"entropy": 6.534032964706421,
|
|
"epoch": 1.1558872305140961,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004894224831098437,
|
|
"loss": 6.4821,
|
|
"mean_token_accuracy": 0.12369620725512505,
|
|
"num_tokens": 19800269.0,
|
|
"step": 5925
|
|
},
|
|
{
|
|
"entropy": 6.58092565536499,
|
|
"epoch": 1.156862745098039,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004894011609968224,
|
|
"loss": 6.4117,
|
|
"mean_token_accuracy": 0.127414258569479,
|
|
"num_tokens": 19816837.0,
|
|
"step": 5930
|
|
},
|
|
{
|
|
"entropy": 6.5918220520019535,
|
|
"epoch": 1.1578382596819823,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004893798179332837,
|
|
"loss": 6.5784,
|
|
"mean_token_accuracy": 0.12134540975093841,
|
|
"num_tokens": 19833029.0,
|
|
"step": 5935
|
|
},
|
|
{
|
|
"entropy": 6.48732705116272,
|
|
"epoch": 1.1588137742659252,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004893584539213134,
|
|
"loss": 6.3282,
|
|
"mean_token_accuracy": 0.14143061637878418,
|
|
"num_tokens": 19851600.0,
|
|
"step": 5940
|
|
},
|
|
{
|
|
"entropy": 6.501591587066651,
|
|
"epoch": 1.1597892888498684,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004893370689629988,
|
|
"loss": 6.4395,
|
|
"mean_token_accuracy": 0.12635367289185523,
|
|
"num_tokens": 19867152.0,
|
|
"step": 5945
|
|
},
|
|
{
|
|
"entropy": 6.416906881332397,
|
|
"epoch": 1.1607648034338114,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004893156630604298,
|
|
"loss": 6.2833,
|
|
"mean_token_accuracy": 0.13901434391736983,
|
|
"num_tokens": 19884035.0,
|
|
"step": 5950
|
|
},
|
|
{
|
|
"entropy": 6.556456279754639,
|
|
"epoch": 1.1617403180177543,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000489294236215698,
|
|
"loss": 6.4099,
|
|
"mean_token_accuracy": 0.12774893045425414,
|
|
"num_tokens": 19899186.0,
|
|
"step": 5955
|
|
},
|
|
{
|
|
"entropy": 6.550547409057617,
|
|
"epoch": 1.1627158326016973,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004892727884308972,
|
|
"loss": 6.4608,
|
|
"mean_token_accuracy": 0.12457498013973237,
|
|
"num_tokens": 19914162.0,
|
|
"step": 5960
|
|
},
|
|
{
|
|
"entropy": 6.473769760131836,
|
|
"epoch": 1.1636913471856405,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004892513197081233,
|
|
"loss": 6.4079,
|
|
"mean_token_accuracy": 0.12491532042622566,
|
|
"num_tokens": 19931758.0,
|
|
"step": 5965
|
|
},
|
|
{
|
|
"entropy": 6.557174921035767,
|
|
"epoch": 1.1646668617695835,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000489229830049474,
|
|
"loss": 6.4664,
|
|
"mean_token_accuracy": 0.12935682833194734,
|
|
"num_tokens": 19949397.0,
|
|
"step": 5970
|
|
},
|
|
{
|
|
"entropy": 6.481569290161133,
|
|
"epoch": 1.1656423763535264,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004892083194570492,
|
|
"loss": 6.3857,
|
|
"mean_token_accuracy": 0.1293022096157074,
|
|
"num_tokens": 19967356.0,
|
|
"step": 5975
|
|
},
|
|
{
|
|
"entropy": 6.509683227539062,
|
|
"epoch": 1.1666178909374696,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004891867879329509,
|
|
"loss": 6.3266,
|
|
"mean_token_accuracy": 0.13855745568871497,
|
|
"num_tokens": 19984343.0,
|
|
"step": 5980
|
|
},
|
|
{
|
|
"entropy": 6.610266637802124,
|
|
"epoch": 1.1675934055214126,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004891652354792831,
|
|
"loss": 6.4916,
|
|
"mean_token_accuracy": 0.12480206862092018,
|
|
"num_tokens": 20001600.0,
|
|
"step": 5985
|
|
},
|
|
{
|
|
"entropy": 6.5437633991241455,
|
|
"epoch": 1.1685689201053555,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004891436620981517,
|
|
"loss": 6.4327,
|
|
"mean_token_accuracy": 0.12529526352882386,
|
|
"num_tokens": 20016816.0,
|
|
"step": 5990
|
|
},
|
|
{
|
|
"entropy": 6.588145208358765,
|
|
"epoch": 1.1695444346892987,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004891220677916649,
|
|
"loss": 6.4451,
|
|
"mean_token_accuracy": 0.12561682164669036,
|
|
"num_tokens": 20033754.0,
|
|
"step": 5995
|
|
},
|
|
{
|
|
"entropy": 6.391103363037109,
|
|
"epoch": 1.1705199492732417,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004891004525619327,
|
|
"loss": 6.3872,
|
|
"mean_token_accuracy": 0.13740353658795357,
|
|
"num_tokens": 20051899.0,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"epoch": 1.1705199492732417,
|
|
"eval_entropy": 6.355995783872554,
|
|
"eval_loss": 6.539937496185303,
|
|
"eval_mean_token_accuracy": 0.12913638515082523,
|
|
"eval_num_tokens": 20051899.0,
|
|
"eval_runtime": 15.3581,
|
|
"eval_samples_per_second": 1079.362,
|
|
"eval_steps_per_second": 134.977,
|
|
"step": 6000
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 51250,
|
|
"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": 2.7034114664448e+16,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|