42112 lines
1.1 MiB
42112 lines
1.1 MiB
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 2.0991652921477484,
|
|
"eval_steps": 3000,
|
|
"global_step": 21000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 10.742113018035889,
|
|
"epoch": 0.00049982506122857,
|
|
"grad_norm": 4.875,
|
|
"learning_rate": 2e-06,
|
|
"loss": 10.7354,
|
|
"mean_token_accuracy": 0.0002496711676940322,
|
|
"num_tokens": 8821.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 10.742119884490966,
|
|
"epoch": 0.00099965012245714,
|
|
"grad_norm": 5.125,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 10.7497,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 18288.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 10.742119789123535,
|
|
"epoch": 0.00149947518368571,
|
|
"grad_norm": 4.65625,
|
|
"learning_rate": 7e-06,
|
|
"loss": 10.7421,
|
|
"mean_token_accuracy": 0.0002510460326448083,
|
|
"num_tokens": 28664.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 10.742084407806397,
|
|
"epoch": 0.00199930024491428,
|
|
"grad_norm": 6.0,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 10.6882,
|
|
"mean_token_accuracy": 0.00013869625981897116,
|
|
"num_tokens": 37807.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 10.74200439453125,
|
|
"epoch": 0.00249912530614285,
|
|
"grad_norm": 4.375,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 10.6462,
|
|
"mean_token_accuracy": 0.004488382575800642,
|
|
"num_tokens": 48086.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 10.741621685028075,
|
|
"epoch": 0.00299895036737142,
|
|
"grad_norm": 4.03125,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 10.5223,
|
|
"mean_token_accuracy": 0.030498435720801353,
|
|
"num_tokens": 57427.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 10.740404415130616,
|
|
"epoch": 0.00349877542859999,
|
|
"grad_norm": 3.453125,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 10.4113,
|
|
"mean_token_accuracy": 0.04445975758135319,
|
|
"num_tokens": 66662.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 10.736149501800536,
|
|
"epoch": 0.00399860048982856,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 10.3341,
|
|
"mean_token_accuracy": 0.04500314220786095,
|
|
"num_tokens": 77388.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 10.725442790985108,
|
|
"epoch": 0.00449842555105713,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 10.1941,
|
|
"mean_token_accuracy": 0.04626995846629143,
|
|
"num_tokens": 86093.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 10.711077690124512,
|
|
"epoch": 0.0049982506122857,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 10.1926,
|
|
"mean_token_accuracy": 0.04310738146305084,
|
|
"num_tokens": 96097.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 10.69948215484619,
|
|
"epoch": 0.00549807567351427,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 10.1482,
|
|
"mean_token_accuracy": 0.042906814627349375,
|
|
"num_tokens": 106328.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 10.692364120483399,
|
|
"epoch": 0.00599790073474284,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 10.0247,
|
|
"mean_token_accuracy": 0.04474271964281797,
|
|
"num_tokens": 114822.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 10.684545135498047,
|
|
"epoch": 0.00649772579597141,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 10.0297,
|
|
"mean_token_accuracy": 0.04712004661560058,
|
|
"num_tokens": 124984.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 10.676221084594726,
|
|
"epoch": 0.00699755085719998,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 9.9346,
|
|
"mean_token_accuracy": 0.04551910758018494,
|
|
"num_tokens": 134054.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 10.668924236297608,
|
|
"epoch": 0.00749737591842855,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 9.9081,
|
|
"mean_token_accuracy": 0.04679625704884529,
|
|
"num_tokens": 144561.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 10.661227989196778,
|
|
"epoch": 0.00799720097965712,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 9.8997,
|
|
"mean_token_accuracy": 0.0436519380658865,
|
|
"num_tokens": 153701.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 10.653296184539794,
|
|
"epoch": 0.00849702604088569,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 9.7945,
|
|
"mean_token_accuracy": 0.05020407922565937,
|
|
"num_tokens": 164291.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 10.636521530151366,
|
|
"epoch": 0.00899685110211426,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 9.7719,
|
|
"mean_token_accuracy": 0.05209365636110306,
|
|
"num_tokens": 174136.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 10.617370223999023,
|
|
"epoch": 0.00949667616334283,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 9.708,
|
|
"mean_token_accuracy": 0.05729338489472866,
|
|
"num_tokens": 184368.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 10.591236019134522,
|
|
"epoch": 0.0099965012245714,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 9.6914,
|
|
"mean_token_accuracy": 0.056233976408839224,
|
|
"num_tokens": 194659.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 10.571689224243164,
|
|
"epoch": 0.01049632628579997,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 9.5729,
|
|
"mean_token_accuracy": 0.057006143406033515,
|
|
"num_tokens": 204875.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 10.52930965423584,
|
|
"epoch": 0.01099615134702854,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 9.577,
|
|
"mean_token_accuracy": 0.05334683395922184,
|
|
"num_tokens": 217033.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 10.460849475860595,
|
|
"epoch": 0.01149597640825711,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 9.4015,
|
|
"mean_token_accuracy": 0.062102947011590005,
|
|
"num_tokens": 225946.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 10.396935844421387,
|
|
"epoch": 0.01199580146948568,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 9.3632,
|
|
"mean_token_accuracy": 0.056867911294102666,
|
|
"num_tokens": 235413.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 10.36595640182495,
|
|
"epoch": 0.01249562653071425,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 9.3793,
|
|
"mean_token_accuracy": 0.048073610663414,
|
|
"num_tokens": 247913.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 10.35603609085083,
|
|
"epoch": 0.01299545159194282,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 9.2476,
|
|
"mean_token_accuracy": 0.06040509082376957,
|
|
"num_tokens": 258486.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 10.29154281616211,
|
|
"epoch": 0.01349527665317139,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 9.161,
|
|
"mean_token_accuracy": 0.05578649267554283,
|
|
"num_tokens": 268027.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 10.207606983184814,
|
|
"epoch": 0.01399510171439996,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 9.0596,
|
|
"mean_token_accuracy": 0.06114833988249302,
|
|
"num_tokens": 277470.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 10.14081039428711,
|
|
"epoch": 0.01449492677562853,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 8.9902,
|
|
"mean_token_accuracy": 0.05893770642578602,
|
|
"num_tokens": 286891.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 10.036300086975098,
|
|
"epoch": 0.0149947518368571,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 8.8746,
|
|
"mean_token_accuracy": 0.06821754761040211,
|
|
"num_tokens": 295636.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 9.924018096923827,
|
|
"epoch": 0.01549457689808567,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 8.8147,
|
|
"mean_token_accuracy": 0.06259672716259956,
|
|
"num_tokens": 306542.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 9.83233995437622,
|
|
"epoch": 0.01599440195931424,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 8.7427,
|
|
"mean_token_accuracy": 0.060157052055001256,
|
|
"num_tokens": 315956.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 9.716417980194091,
|
|
"epoch": 0.01649422702054281,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 8.7001,
|
|
"mean_token_accuracy": 0.05990239083766937,
|
|
"num_tokens": 325500.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 9.563173198699952,
|
|
"epoch": 0.01699405208177138,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 8.6683,
|
|
"mean_token_accuracy": 0.06383000239729882,
|
|
"num_tokens": 335194.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 9.43425817489624,
|
|
"epoch": 0.01749387714299995,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 8.6082,
|
|
"mean_token_accuracy": 0.061490171030163764,
|
|
"num_tokens": 344717.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 9.373362159729004,
|
|
"epoch": 0.01799370220422852,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 8.5056,
|
|
"mean_token_accuracy": 0.06233922764658928,
|
|
"num_tokens": 354476.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 9.256193733215332,
|
|
"epoch": 0.01849352726545709,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 8.5486,
|
|
"mean_token_accuracy": 0.06391786970198154,
|
|
"num_tokens": 363939.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 9.170073986053467,
|
|
"epoch": 0.01899335232668566,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 8.5757,
|
|
"mean_token_accuracy": 0.061041193455457686,
|
|
"num_tokens": 373187.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 9.10431718826294,
|
|
"epoch": 0.01949317738791423,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 8.4889,
|
|
"mean_token_accuracy": 0.06612157672643662,
|
|
"num_tokens": 382999.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 9.082199668884277,
|
|
"epoch": 0.0199930024491428,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 8.5374,
|
|
"mean_token_accuracy": 0.061392434686422345,
|
|
"num_tokens": 392639.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 9.000153255462646,
|
|
"epoch": 0.02049282751037137,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.000102,
|
|
"loss": 8.5164,
|
|
"mean_token_accuracy": 0.06042192354798317,
|
|
"num_tokens": 403089.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 8.976395606994629,
|
|
"epoch": 0.02099265257159994,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 8.4681,
|
|
"mean_token_accuracy": 0.06152507662773132,
|
|
"num_tokens": 412321.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 8.91478672027588,
|
|
"epoch": 0.02149247763282851,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000107,
|
|
"loss": 8.502,
|
|
"mean_token_accuracy": 0.06330714970827103,
|
|
"num_tokens": 421599.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 8.860779762268066,
|
|
"epoch": 0.02199230269405708,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 8.4778,
|
|
"mean_token_accuracy": 0.06263926923274994,
|
|
"num_tokens": 432012.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 8.922132301330567,
|
|
"epoch": 0.02249212775528565,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000112,
|
|
"loss": 8.453,
|
|
"mean_token_accuracy": 0.06589648500084877,
|
|
"num_tokens": 441989.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 8.896614170074463,
|
|
"epoch": 0.02299195281651422,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 8.4297,
|
|
"mean_token_accuracy": 0.06669879406690597,
|
|
"num_tokens": 451532.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 8.810688591003418,
|
|
"epoch": 0.02349177787774279,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 8.4408,
|
|
"mean_token_accuracy": 0.06297187581658363,
|
|
"num_tokens": 461815.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 8.825593757629395,
|
|
"epoch": 0.02399160293897136,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 8.5024,
|
|
"mean_token_accuracy": 0.06163628771901131,
|
|
"num_tokens": 470860.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 8.804152870178223,
|
|
"epoch": 0.02449142800019993,
|
|
"grad_norm": 0.7265625,
|
|
"learning_rate": 0.000122,
|
|
"loss": 8.4705,
|
|
"mean_token_accuracy": 0.06292311102151871,
|
|
"num_tokens": 480649.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 8.85675745010376,
|
|
"epoch": 0.0249912530614285,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 8.4032,
|
|
"mean_token_accuracy": 0.06878387741744518,
|
|
"num_tokens": 489969.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 8.763758945465089,
|
|
"epoch": 0.02549107812265707,
|
|
"grad_norm": 0.7421875,
|
|
"learning_rate": 0.000127,
|
|
"loss": 8.4088,
|
|
"mean_token_accuracy": 0.06565447077155113,
|
|
"num_tokens": 500000.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 8.834418106079102,
|
|
"epoch": 0.02599090318388564,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 8.3918,
|
|
"mean_token_accuracy": 0.06619769148528576,
|
|
"num_tokens": 510013.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 8.717261409759521,
|
|
"epoch": 0.026490728245114212,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000132,
|
|
"loss": 8.4183,
|
|
"mean_token_accuracy": 0.06544177196919918,
|
|
"num_tokens": 519698.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 8.820175933837891,
|
|
"epoch": 0.02699055330634278,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 8.4225,
|
|
"mean_token_accuracy": 0.06441575214266777,
|
|
"num_tokens": 531631.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 8.775634002685546,
|
|
"epoch": 0.02749037836757135,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 8.3921,
|
|
"mean_token_accuracy": 0.0714694295078516,
|
|
"num_tokens": 542204.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 8.750507164001466,
|
|
"epoch": 0.02799020342879992,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 8.313,
|
|
"mean_token_accuracy": 0.06778912842273713,
|
|
"num_tokens": 552269.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 8.71799602508545,
|
|
"epoch": 0.02849002849002849,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 8.3159,
|
|
"mean_token_accuracy": 0.0691824123263359,
|
|
"num_tokens": 561907.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 8.687597274780273,
|
|
"epoch": 0.02898985355125706,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 8.426,
|
|
"mean_token_accuracy": 0.06967848278582096,
|
|
"num_tokens": 571283.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 8.732817840576171,
|
|
"epoch": 0.02948967861248563,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.000147,
|
|
"loss": 8.2974,
|
|
"mean_token_accuracy": 0.07371204271912575,
|
|
"num_tokens": 579896.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 8.68296022415161,
|
|
"epoch": 0.0299895036737142,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 8.2576,
|
|
"mean_token_accuracy": 0.08281500861048699,
|
|
"num_tokens": 588856.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 8.575243282318116,
|
|
"epoch": 0.03048932873494277,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000152,
|
|
"loss": 8.3118,
|
|
"mean_token_accuracy": 0.07554283365607262,
|
|
"num_tokens": 598910.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 8.752356338500977,
|
|
"epoch": 0.03098915379617134,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 8.3723,
|
|
"mean_token_accuracy": 0.0699452206492424,
|
|
"num_tokens": 609248.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 8.696213340759277,
|
|
"epoch": 0.03148897885739991,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.000157,
|
|
"loss": 8.3617,
|
|
"mean_token_accuracy": 0.07190549783408642,
|
|
"num_tokens": 619352.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 8.718466758728027,
|
|
"epoch": 0.03198880391862848,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 8.3708,
|
|
"mean_token_accuracy": 0.07149303182959557,
|
|
"num_tokens": 628300.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 8.677219200134278,
|
|
"epoch": 0.03248862897985705,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000162,
|
|
"loss": 8.3068,
|
|
"mean_token_accuracy": 0.0743933729827404,
|
|
"num_tokens": 637969.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 8.681064319610595,
|
|
"epoch": 0.03298845404108562,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 8.2194,
|
|
"mean_token_accuracy": 0.07997227124869824,
|
|
"num_tokens": 647518.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 8.710070419311524,
|
|
"epoch": 0.03348827910231419,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 8.401,
|
|
"mean_token_accuracy": 0.07310340739786625,
|
|
"num_tokens": 658292.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 8.64979133605957,
|
|
"epoch": 0.03398810416354276,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 8.282,
|
|
"mean_token_accuracy": 0.0751060452312231,
|
|
"num_tokens": 667872.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 8.58129940032959,
|
|
"epoch": 0.03448792922477133,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 8.195,
|
|
"mean_token_accuracy": 0.0765431810170412,
|
|
"num_tokens": 676976.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 8.645341205596925,
|
|
"epoch": 0.0349877542859999,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 8.2187,
|
|
"mean_token_accuracy": 0.08100063130259513,
|
|
"num_tokens": 686149.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 8.57761583328247,
|
|
"epoch": 0.03548757934722847,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.000177,
|
|
"loss": 8.1215,
|
|
"mean_token_accuracy": 0.08577202558517456,
|
|
"num_tokens": 696439.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 8.503854370117187,
|
|
"epoch": 0.03598740440845704,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 8.1526,
|
|
"mean_token_accuracy": 0.08154284283518791,
|
|
"num_tokens": 705902.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 8.575439071655273,
|
|
"epoch": 0.03648722946968561,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000182,
|
|
"loss": 8.304,
|
|
"mean_token_accuracy": 0.07753718234598636,
|
|
"num_tokens": 715973.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 8.580668735504151,
|
|
"epoch": 0.03698705453091418,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 8.2083,
|
|
"mean_token_accuracy": 0.07895785272121429,
|
|
"num_tokens": 725463.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 8.613331699371338,
|
|
"epoch": 0.03748687959214275,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000187,
|
|
"loss": 8.2239,
|
|
"mean_token_accuracy": 0.07793777883052826,
|
|
"num_tokens": 734941.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 8.614311981201173,
|
|
"epoch": 0.03798670465337132,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 8.2425,
|
|
"mean_token_accuracy": 0.07460713312029839,
|
|
"num_tokens": 744302.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 8.519310474395752,
|
|
"epoch": 0.03848652971459989,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000192,
|
|
"loss": 8.1684,
|
|
"mean_token_accuracy": 0.08556054756045342,
|
|
"num_tokens": 754341.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 8.755522155761719,
|
|
"epoch": 0.03898635477582846,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 8.2985,
|
|
"mean_token_accuracy": 0.07072081565856933,
|
|
"num_tokens": 764087.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 8.485608291625976,
|
|
"epoch": 0.03948617983705703,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 8.2273,
|
|
"mean_token_accuracy": 0.07447122037410736,
|
|
"num_tokens": 773728.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 8.685750102996826,
|
|
"epoch": 0.0399860048982856,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 8.2393,
|
|
"mean_token_accuracy": 0.07686416134238243,
|
|
"num_tokens": 784839.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 8.61361484527588,
|
|
"epoch": 0.04048582995951417,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000202,
|
|
"loss": 8.2227,
|
|
"mean_token_accuracy": 0.08219211772084237,
|
|
"num_tokens": 794514.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 8.532085800170899,
|
|
"epoch": 0.04098565502074274,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 8.2007,
|
|
"mean_token_accuracy": 0.08283689394593238,
|
|
"num_tokens": 805254.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 8.567570400238036,
|
|
"epoch": 0.04148548008197131,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000207,
|
|
"loss": 8.107,
|
|
"mean_token_accuracy": 0.08443296402692795,
|
|
"num_tokens": 814135.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 8.450470733642579,
|
|
"epoch": 0.04198530514319988,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 8.1524,
|
|
"mean_token_accuracy": 0.08148454427719116,
|
|
"num_tokens": 823531.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 8.421721839904786,
|
|
"epoch": 0.04248513020442845,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000212,
|
|
"loss": 8.0779,
|
|
"mean_token_accuracy": 0.08629797920584678,
|
|
"num_tokens": 832833.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 8.48620538711548,
|
|
"epoch": 0.04298495526565702,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 8.0685,
|
|
"mean_token_accuracy": 0.08419421762228012,
|
|
"num_tokens": 841541.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 8.445399856567382,
|
|
"epoch": 0.04348478032688559,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 8.0899,
|
|
"mean_token_accuracy": 0.08340806141495705,
|
|
"num_tokens": 850689.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 8.459619426727295,
|
|
"epoch": 0.04398460538811416,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 8.0362,
|
|
"mean_token_accuracy": 0.09014891162514686,
|
|
"num_tokens": 860573.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 8.543528842926026,
|
|
"epoch": 0.04448443044934273,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000222,
|
|
"loss": 8.1546,
|
|
"mean_token_accuracy": 0.07898386307060719,
|
|
"num_tokens": 869784.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 8.455932331085204,
|
|
"epoch": 0.0449842555105713,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 8.1017,
|
|
"mean_token_accuracy": 0.08015754446387291,
|
|
"num_tokens": 878716.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 8.446991348266602,
|
|
"epoch": 0.04548408057179987,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 8.175,
|
|
"mean_token_accuracy": 0.08237311467528344,
|
|
"num_tokens": 888334.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 8.467612648010254,
|
|
"epoch": 0.04598390563302844,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 8.1105,
|
|
"mean_token_accuracy": 0.07949303276836872,
|
|
"num_tokens": 897701.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 8.498649311065673,
|
|
"epoch": 0.04648373069425701,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 8.0756,
|
|
"mean_token_accuracy": 0.0814065046608448,
|
|
"num_tokens": 907278.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 8.423473739624024,
|
|
"epoch": 0.04698355575548558,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 8.0835,
|
|
"mean_token_accuracy": 0.07995141670107841,
|
|
"num_tokens": 916194.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 8.476182556152343,
|
|
"epoch": 0.04748338081671415,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000237,
|
|
"loss": 8.0997,
|
|
"mean_token_accuracy": 0.08503060936927795,
|
|
"num_tokens": 926743.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 8.453644371032714,
|
|
"epoch": 0.04798320587794272,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 8.1388,
|
|
"mean_token_accuracy": 0.07848219200968742,
|
|
"num_tokens": 936059.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 8.39522933959961,
|
|
"epoch": 0.04848303093917129,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000242,
|
|
"loss": 8.0484,
|
|
"mean_token_accuracy": 0.08674658462405205,
|
|
"num_tokens": 945990.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 8.503808116912841,
|
|
"epoch": 0.04898285600039986,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 8.1173,
|
|
"mean_token_accuracy": 0.08412509486079216,
|
|
"num_tokens": 956626.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 8.41580810546875,
|
|
"epoch": 0.04948268106162843,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000247,
|
|
"loss": 8.0777,
|
|
"mean_token_accuracy": 0.08279605060815812,
|
|
"num_tokens": 966200.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 8.39886407852173,
|
|
"epoch": 0.049982506122857,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 8.0361,
|
|
"mean_token_accuracy": 0.08273001238703728,
|
|
"num_tokens": 975651.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 8.383611392974853,
|
|
"epoch": 0.05048233118408557,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000252,
|
|
"loss": 8.0191,
|
|
"mean_token_accuracy": 0.08777477145195008,
|
|
"num_tokens": 985264.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 8.448287868499756,
|
|
"epoch": 0.05098215624531414,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 8.053,
|
|
"mean_token_accuracy": 0.08592012897133827,
|
|
"num_tokens": 996723.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 8.31779079437256,
|
|
"epoch": 0.05148198130654271,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000257,
|
|
"loss": 8.0489,
|
|
"mean_token_accuracy": 0.08642567917704583,
|
|
"num_tokens": 1006098.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 8.480357837677001,
|
|
"epoch": 0.05198180636777128,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 8.0707,
|
|
"mean_token_accuracy": 0.08443118557333947,
|
|
"num_tokens": 1016595.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 8.306590175628662,
|
|
"epoch": 0.05248163142899985,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000262,
|
|
"loss": 7.9342,
|
|
"mean_token_accuracy": 0.09165540859103202,
|
|
"num_tokens": 1026281.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 8.408623600006104,
|
|
"epoch": 0.052981456490228424,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 8.0266,
|
|
"mean_token_accuracy": 0.09572977796196938,
|
|
"num_tokens": 1036697.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 8.276596641540527,
|
|
"epoch": 0.05348128155145699,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 7.9901,
|
|
"mean_token_accuracy": 0.08793360516428947,
|
|
"num_tokens": 1047433.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 8.411270713806152,
|
|
"epoch": 0.05398110661268556,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 8.0427,
|
|
"mean_token_accuracy": 0.08355218432843685,
|
|
"num_tokens": 1056774.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 8.40280523300171,
|
|
"epoch": 0.05448093167391413,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 7.9525,
|
|
"mean_token_accuracy": 0.08867315500974655,
|
|
"num_tokens": 1068056.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 8.254864311218261,
|
|
"epoch": 0.0549807567351427,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 7.9596,
|
|
"mean_token_accuracy": 0.0920575998723507,
|
|
"num_tokens": 1077698.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 8.321324825286865,
|
|
"epoch": 0.05548058179637127,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000277,
|
|
"loss": 7.9305,
|
|
"mean_token_accuracy": 0.08997995480895042,
|
|
"num_tokens": 1086485.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 8.285623931884766,
|
|
"epoch": 0.05598040685759984,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 8.0035,
|
|
"mean_token_accuracy": 0.08188552521169186,
|
|
"num_tokens": 1097329.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 8.301086711883546,
|
|
"epoch": 0.05648023191882841,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 7.9439,
|
|
"mean_token_accuracy": 0.08813558220863342,
|
|
"num_tokens": 1107990.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 8.220473194122315,
|
|
"epoch": 0.05698005698005698,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 7.8945,
|
|
"mean_token_accuracy": 0.09917720332741738,
|
|
"num_tokens": 1117798.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 8.299683856964112,
|
|
"epoch": 0.05747988204128555,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000287,
|
|
"loss": 8.0225,
|
|
"mean_token_accuracy": 0.08569787368178368,
|
|
"num_tokens": 1126976.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 8.327748203277588,
|
|
"epoch": 0.05797970710251412,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 7.9334,
|
|
"mean_token_accuracy": 0.09346841722726822,
|
|
"num_tokens": 1136410.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 8.28176794052124,
|
|
"epoch": 0.05847953216374269,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000292,
|
|
"loss": 7.987,
|
|
"mean_token_accuracy": 0.090962153673172,
|
|
"num_tokens": 1147162.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 8.228501224517823,
|
|
"epoch": 0.05897935722497126,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 7.9276,
|
|
"mean_token_accuracy": 0.09324892237782478,
|
|
"num_tokens": 1157578.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 8.30532102584839,
|
|
"epoch": 0.05947918228619983,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000297,
|
|
"loss": 7.8498,
|
|
"mean_token_accuracy": 0.09714705944061279,
|
|
"num_tokens": 1166914.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 8.3526291847229,
|
|
"epoch": 0.0599790073474284,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 8.0223,
|
|
"mean_token_accuracy": 0.07643549218773842,
|
|
"num_tokens": 1176740.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 8.228054428100586,
|
|
"epoch": 0.06047883240865697,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000302,
|
|
"loss": 7.9041,
|
|
"mean_token_accuracy": 0.08873437419533729,
|
|
"num_tokens": 1185497.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 8.404792785644531,
|
|
"epoch": 0.06097865746988554,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 8.0288,
|
|
"mean_token_accuracy": 0.08556954115629196,
|
|
"num_tokens": 1197390.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 8.208370685577393,
|
|
"epoch": 0.06147848253111411,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.000307,
|
|
"loss": 7.8988,
|
|
"mean_token_accuracy": 0.09034750014543533,
|
|
"num_tokens": 1208293.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 8.260112953186034,
|
|
"epoch": 0.06197830759234268,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 7.8837,
|
|
"mean_token_accuracy": 0.09412865191698075,
|
|
"num_tokens": 1217860.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 8.192390155792236,
|
|
"epoch": 0.06247813265357125,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000312,
|
|
"loss": 7.8716,
|
|
"mean_token_accuracy": 0.09198905006051064,
|
|
"num_tokens": 1227259.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 8.16130018234253,
|
|
"epoch": 0.06297795771479982,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 7.7885,
|
|
"mean_token_accuracy": 0.10033405348658561,
|
|
"num_tokens": 1236775.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 8.210112524032592,
|
|
"epoch": 0.06347778277602839,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000317,
|
|
"loss": 7.9116,
|
|
"mean_token_accuracy": 0.09359579831361771,
|
|
"num_tokens": 1246307.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 8.269742012023926,
|
|
"epoch": 0.06397760783725696,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 7.8657,
|
|
"mean_token_accuracy": 0.09205928593873977,
|
|
"num_tokens": 1255197.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 8.189111995697022,
|
|
"epoch": 0.06447743289848552,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000322,
|
|
"loss": 7.8667,
|
|
"mean_token_accuracy": 0.09405043423175811,
|
|
"num_tokens": 1265056.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 8.203232288360596,
|
|
"epoch": 0.0649772579597141,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 7.8283,
|
|
"mean_token_accuracy": 0.09532282426953316,
|
|
"num_tokens": 1274718.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 8.204540061950684,
|
|
"epoch": 0.06547708302094267,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 7.9137,
|
|
"mean_token_accuracy": 0.09175522401928901,
|
|
"num_tokens": 1284364.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 8.217914533615112,
|
|
"epoch": 0.06597690808217124,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 7.8891,
|
|
"mean_token_accuracy": 0.09070554673671723,
|
|
"num_tokens": 1294186.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 8.16135516166687,
|
|
"epoch": 0.06647673314339982,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 7.8175,
|
|
"mean_token_accuracy": 0.09384845942258835,
|
|
"num_tokens": 1303393.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 8.106479072570801,
|
|
"epoch": 0.06697655820462838,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 7.817,
|
|
"mean_token_accuracy": 0.09376823343336582,
|
|
"num_tokens": 1312819.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 8.17269515991211,
|
|
"epoch": 0.06747638326585695,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000337,
|
|
"loss": 7.851,
|
|
"mean_token_accuracy": 0.08638178259134292,
|
|
"num_tokens": 1323001.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 8.182546710968017,
|
|
"epoch": 0.06797620832708552,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 7.8232,
|
|
"mean_token_accuracy": 0.09359516352415084,
|
|
"num_tokens": 1333260.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 8.1503267288208,
|
|
"epoch": 0.0684760333883141,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000342,
|
|
"loss": 7.8104,
|
|
"mean_token_accuracy": 0.09704278111457824,
|
|
"num_tokens": 1342696.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 8.134940958023071,
|
|
"epoch": 0.06897585844954265,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 7.7834,
|
|
"mean_token_accuracy": 0.09516805186867713,
|
|
"num_tokens": 1353104.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 8.105061912536621,
|
|
"epoch": 0.06947568351077123,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000347,
|
|
"loss": 7.8471,
|
|
"mean_token_accuracy": 0.08959203399717808,
|
|
"num_tokens": 1362871.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 8.226502609252929,
|
|
"epoch": 0.0699755085719998,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 7.8302,
|
|
"mean_token_accuracy": 0.09120392128825187,
|
|
"num_tokens": 1373622.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 7.967414331436157,
|
|
"epoch": 0.07047533363322837,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000352,
|
|
"loss": 7.7096,
|
|
"mean_token_accuracy": 0.09465244933962821,
|
|
"num_tokens": 1382707.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 8.168174076080323,
|
|
"epoch": 0.07097515869445695,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 7.794,
|
|
"mean_token_accuracy": 0.09188380241394042,
|
|
"num_tokens": 1392048.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 8.040040349960327,
|
|
"epoch": 0.0714749837556855,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000357,
|
|
"loss": 7.6498,
|
|
"mean_token_accuracy": 0.10075373873114586,
|
|
"num_tokens": 1401387.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 8.03524203300476,
|
|
"epoch": 0.07197480881691408,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 7.7718,
|
|
"mean_token_accuracy": 0.09415309280157089,
|
|
"num_tokens": 1411404.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 8.118272829055787,
|
|
"epoch": 0.07247463387814265,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000362,
|
|
"loss": 7.7716,
|
|
"mean_token_accuracy": 0.09523647800087928,
|
|
"num_tokens": 1420292.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 8.011260223388671,
|
|
"epoch": 0.07297445893937123,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 7.7221,
|
|
"mean_token_accuracy": 0.09846484884619713,
|
|
"num_tokens": 1429990.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 8.110036754608155,
|
|
"epoch": 0.07347428400059978,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000367,
|
|
"loss": 7.7661,
|
|
"mean_token_accuracy": 0.0931557647883892,
|
|
"num_tokens": 1440148.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 8.04368724822998,
|
|
"epoch": 0.07397410906182836,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 7.6823,
|
|
"mean_token_accuracy": 0.09766408279538155,
|
|
"num_tokens": 1450015.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 8.074540615081787,
|
|
"epoch": 0.07447393412305693,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000372,
|
|
"loss": 7.7128,
|
|
"mean_token_accuracy": 0.09001053497195244,
|
|
"num_tokens": 1459582.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 8.047771739959718,
|
|
"epoch": 0.0749737591842855,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 7.7654,
|
|
"mean_token_accuracy": 0.09219523742794991,
|
|
"num_tokens": 1468151.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 7.934108066558838,
|
|
"epoch": 0.07547358424551406,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000377,
|
|
"loss": 7.6629,
|
|
"mean_token_accuracy": 0.09758676961064339,
|
|
"num_tokens": 1479099.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 8.08583436012268,
|
|
"epoch": 0.07597340930674264,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 7.7606,
|
|
"mean_token_accuracy": 0.09898279458284379,
|
|
"num_tokens": 1488060.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 8.037435007095336,
|
|
"epoch": 0.07647323436797121,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000382,
|
|
"loss": 7.7476,
|
|
"mean_token_accuracy": 0.09002138823270797,
|
|
"num_tokens": 1498230.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 8.06327486038208,
|
|
"epoch": 0.07697305942919978,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 7.7279,
|
|
"mean_token_accuracy": 0.09608541578054428,
|
|
"num_tokens": 1507962.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 8.107155275344848,
|
|
"epoch": 0.07747288449042836,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 7.8234,
|
|
"mean_token_accuracy": 0.09302043840289116,
|
|
"num_tokens": 1518607.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 8.132760810852051,
|
|
"epoch": 0.07797270955165692,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 7.6654,
|
|
"mean_token_accuracy": 0.09478092044591904,
|
|
"num_tokens": 1527166.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 7.994145393371582,
|
|
"epoch": 0.07847253461288549,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 7.7769,
|
|
"mean_token_accuracy": 0.09216032102704048,
|
|
"num_tokens": 1536683.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 8.052890396118164,
|
|
"epoch": 0.07897235967411406,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 7.6444,
|
|
"mean_token_accuracy": 0.09586679339408874,
|
|
"num_tokens": 1546243.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 7.990080165863037,
|
|
"epoch": 0.07947218473534264,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 7.6838,
|
|
"mean_token_accuracy": 0.09463807120919228,
|
|
"num_tokens": 1555916.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 7.892803049087524,
|
|
"epoch": 0.0799720097965712,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 7.5913,
|
|
"mean_token_accuracy": 0.10165544375777244,
|
|
"num_tokens": 1566617.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 7.9309196949005125,
|
|
"epoch": 0.08047183485779977,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000402,
|
|
"loss": 7.6573,
|
|
"mean_token_accuracy": 0.09189758896827697,
|
|
"num_tokens": 1575413.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 7.9370897769927975,
|
|
"epoch": 0.08097165991902834,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 7.6576,
|
|
"mean_token_accuracy": 0.09608973935246468,
|
|
"num_tokens": 1586863.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 8.001241874694824,
|
|
"epoch": 0.08147148498025691,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 7.7234,
|
|
"mean_token_accuracy": 0.09731132909655571,
|
|
"num_tokens": 1597685.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 7.99445104598999,
|
|
"epoch": 0.08197131004148547,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 7.6245,
|
|
"mean_token_accuracy": 0.09776123687624931,
|
|
"num_tokens": 1607103.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 7.999743795394897,
|
|
"epoch": 0.08247113510271405,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000412,
|
|
"loss": 7.6631,
|
|
"mean_token_accuracy": 0.0952106162905693,
|
|
"num_tokens": 1617919.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 7.934334754943848,
|
|
"epoch": 0.08297096016394262,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 7.7062,
|
|
"mean_token_accuracy": 0.09701430797576904,
|
|
"num_tokens": 1627293.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 7.999687910079956,
|
|
"epoch": 0.08347078522517119,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000417,
|
|
"loss": 7.7125,
|
|
"mean_token_accuracy": 0.09134984835982322,
|
|
"num_tokens": 1638440.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 7.880404663085938,
|
|
"epoch": 0.08397061028639977,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 7.6324,
|
|
"mean_token_accuracy": 0.09711692780256272,
|
|
"num_tokens": 1648148.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 7.96956696510315,
|
|
"epoch": 0.08447043534762833,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000422,
|
|
"loss": 7.6519,
|
|
"mean_token_accuracy": 0.10145560279488564,
|
|
"num_tokens": 1658334.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 8.041061925888062,
|
|
"epoch": 0.0849702604088569,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 7.6965,
|
|
"mean_token_accuracy": 0.09095216616988182,
|
|
"num_tokens": 1667963.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 7.87789101600647,
|
|
"epoch": 0.08547008547008547,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000427,
|
|
"loss": 7.5978,
|
|
"mean_token_accuracy": 0.09792420715093612,
|
|
"num_tokens": 1677270.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 7.916245174407959,
|
|
"epoch": 0.08596991053131404,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 7.5792,
|
|
"mean_token_accuracy": 0.09994457513093949,
|
|
"num_tokens": 1686770.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 7.882506227493286,
|
|
"epoch": 0.0864697355925426,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000432,
|
|
"loss": 7.6509,
|
|
"mean_token_accuracy": 0.0953475922346115,
|
|
"num_tokens": 1697507.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 7.81713080406189,
|
|
"epoch": 0.08696956065377118,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 7.5814,
|
|
"mean_token_accuracy": 0.10015851929783821,
|
|
"num_tokens": 1708253.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 7.997309446334839,
|
|
"epoch": 0.08746938571499975,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000437,
|
|
"loss": 7.6658,
|
|
"mean_token_accuracy": 0.09474888741970063,
|
|
"num_tokens": 1717827.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 7.760024833679199,
|
|
"epoch": 0.08796921077622832,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 7.4538,
|
|
"mean_token_accuracy": 0.10792813673615456,
|
|
"num_tokens": 1726678.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 7.866535377502442,
|
|
"epoch": 0.0884690358374569,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.000442,
|
|
"loss": 7.5961,
|
|
"mean_token_accuracy": 0.09604379087686539,
|
|
"num_tokens": 1737518.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 7.879868602752685,
|
|
"epoch": 0.08896886089868546,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 7.4935,
|
|
"mean_token_accuracy": 0.10566615983843804,
|
|
"num_tokens": 1746338.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 7.823741006851196,
|
|
"epoch": 0.08946868595991403,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000447,
|
|
"loss": 7.5613,
|
|
"mean_token_accuracy": 0.10079468935728073,
|
|
"num_tokens": 1756538.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 7.876118326187134,
|
|
"epoch": 0.0899685110211426,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 7.5836,
|
|
"mean_token_accuracy": 0.09676425233483314,
|
|
"num_tokens": 1766722.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 7.753104639053345,
|
|
"epoch": 0.09046833608237118,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 7.4967,
|
|
"mean_token_accuracy": 0.10072999745607376,
|
|
"num_tokens": 1777039.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 7.91089015007019,
|
|
"epoch": 0.09096816114359974,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 7.6107,
|
|
"mean_token_accuracy": 0.0950322225689888,
|
|
"num_tokens": 1787621.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 7.87430214881897,
|
|
"epoch": 0.09146798620482831,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 7.6136,
|
|
"mean_token_accuracy": 0.09905622452497483,
|
|
"num_tokens": 1798345.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 7.831703472137451,
|
|
"epoch": 0.09196781126605688,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 7.56,
|
|
"mean_token_accuracy": 0.1018152303993702,
|
|
"num_tokens": 1807994.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 7.771154356002808,
|
|
"epoch": 0.09246763632728545,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000462,
|
|
"loss": 7.5007,
|
|
"mean_token_accuracy": 0.0945871725678444,
|
|
"num_tokens": 1817965.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 7.880890274047852,
|
|
"epoch": 0.09296746138851401,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 7.5537,
|
|
"mean_token_accuracy": 0.09793060868978501,
|
|
"num_tokens": 1827094.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 7.78585376739502,
|
|
"epoch": 0.09346728644974259,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000467,
|
|
"loss": 7.5184,
|
|
"mean_token_accuracy": 0.09652820006012916,
|
|
"num_tokens": 1837754.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 7.771854496002197,
|
|
"epoch": 0.09396711151097116,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 7.5075,
|
|
"mean_token_accuracy": 0.10058806762099266,
|
|
"num_tokens": 1847500.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 7.791559839248658,
|
|
"epoch": 0.09446693657219973,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000472,
|
|
"loss": 7.5732,
|
|
"mean_token_accuracy": 0.09383994415402412,
|
|
"num_tokens": 1857663.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 7.871378183364868,
|
|
"epoch": 0.0949667616334283,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 7.6231,
|
|
"mean_token_accuracy": 0.09650576040148735,
|
|
"num_tokens": 1867752.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 7.807382106781006,
|
|
"epoch": 0.09546658669465687,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000477,
|
|
"loss": 7.5452,
|
|
"mean_token_accuracy": 0.09623196721076965,
|
|
"num_tokens": 1877479.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 7.763889932632447,
|
|
"epoch": 0.09596641175588544,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 7.5723,
|
|
"mean_token_accuracy": 0.09741483479738236,
|
|
"num_tokens": 1887944.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 7.879271364212036,
|
|
"epoch": 0.09646623681711401,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000482,
|
|
"loss": 7.4957,
|
|
"mean_token_accuracy": 0.10076584815979003,
|
|
"num_tokens": 1896991.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 7.705447959899902,
|
|
"epoch": 0.09696606187834259,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 7.4952,
|
|
"mean_token_accuracy": 0.10603907033801079,
|
|
"num_tokens": 1907216.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 7.8304407596588135,
|
|
"epoch": 0.09746588693957114,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000487,
|
|
"loss": 7.5332,
|
|
"mean_token_accuracy": 0.09332873225212097,
|
|
"num_tokens": 1917206.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 7.699482154846192,
|
|
"epoch": 0.09796571200079972,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 7.5962,
|
|
"mean_token_accuracy": 0.09308115392923355,
|
|
"num_tokens": 1929669.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 7.849009084701538,
|
|
"epoch": 0.09846553706202829,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000492,
|
|
"loss": 7.4585,
|
|
"mean_token_accuracy": 0.10018454045057297,
|
|
"num_tokens": 1939881.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 7.612346506118774,
|
|
"epoch": 0.09896536212325686,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 7.4929,
|
|
"mean_token_accuracy": 0.09991356357932091,
|
|
"num_tokens": 1949423.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 7.8288792133331295,
|
|
"epoch": 0.09946518718448542,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000497,
|
|
"loss": 7.5251,
|
|
"mean_token_accuracy": 0.09757097363471985,
|
|
"num_tokens": 1959214.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 7.802850389480591,
|
|
"epoch": 0.099965012245714,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 7.4851,
|
|
"mean_token_accuracy": 0.0973809115588665,
|
|
"num_tokens": 1968963.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 7.674502229690551,
|
|
"epoch": 0.10046483730694257,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999999981884985,
|
|
"loss": 7.4751,
|
|
"mean_token_accuracy": 0.09699616283178329,
|
|
"num_tokens": 1979551.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 7.707011651992798,
|
|
"epoch": 0.10096466236817114,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004999999908292739,
|
|
"loss": 7.4402,
|
|
"mean_token_accuracy": 0.10390993803739548,
|
|
"num_tokens": 1988432.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 7.738900566101075,
|
|
"epoch": 0.10146448742939972,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999999778091072,
|
|
"loss": 7.4858,
|
|
"mean_token_accuracy": 0.1000777617096901,
|
|
"num_tokens": 1997509.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 7.792381763458252,
|
|
"epoch": 0.10196431249062828,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999999591279991,
|
|
"loss": 7.6484,
|
|
"mean_token_accuracy": 0.09373814240098,
|
|
"num_tokens": 2007406.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 7.805833625793457,
|
|
"epoch": 0.10246413755185685,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00049999993478595,
|
|
"loss": 7.4674,
|
|
"mean_token_accuracy": 0.09718732684850692,
|
|
"num_tokens": 2016760.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 7.635655355453491,
|
|
"epoch": 0.10296396261308542,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999999047829604,
|
|
"loss": 7.4949,
|
|
"mean_token_accuracy": 0.10022416040301323,
|
|
"num_tokens": 2027776.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 7.69910683631897,
|
|
"epoch": 0.103463787674314,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499999869119031,
|
|
"loss": 7.4395,
|
|
"mean_token_accuracy": 0.10272038653492928,
|
|
"num_tokens": 2036955.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 7.6816685676574705,
|
|
"epoch": 0.10396361273554255,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999998277941629,
|
|
"loss": 7.3558,
|
|
"mean_token_accuracy": 0.10612019002437592,
|
|
"num_tokens": 2046118.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 7.632660675048828,
|
|
"epoch": 0.10446343779677113,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999997808083569,
|
|
"loss": 7.4229,
|
|
"mean_token_accuracy": 0.09605257287621498,
|
|
"num_tokens": 2056266.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 7.6546745777130125,
|
|
"epoch": 0.1049632628579997,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004999997281616144,
|
|
"loss": 7.4632,
|
|
"mean_token_accuracy": 0.10460180416703224,
|
|
"num_tokens": 2067416.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 7.745044374465943,
|
|
"epoch": 0.10546308791922827,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999996698539366,
|
|
"loss": 7.4574,
|
|
"mean_token_accuracy": 0.09959002882242203,
|
|
"num_tokens": 2076926.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 7.669534826278687,
|
|
"epoch": 0.10596291298045685,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499999605885325,
|
|
"loss": 7.4478,
|
|
"mean_token_accuracy": 0.10303856655955315,
|
|
"num_tokens": 2088017.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 7.680190181732177,
|
|
"epoch": 0.1064627380416854,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999995362557813,
|
|
"loss": 7.4762,
|
|
"mean_token_accuracy": 0.10051115751266479,
|
|
"num_tokens": 2097249.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 7.5991401195526125,
|
|
"epoch": 0.10696256310291398,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000499999460965307,
|
|
"loss": 7.4297,
|
|
"mean_token_accuracy": 0.10126611217856407,
|
|
"num_tokens": 2105778.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 7.731232929229736,
|
|
"epoch": 0.10746238816414255,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999993800139043,
|
|
"loss": 7.4517,
|
|
"mean_token_accuracy": 0.10296982377767563,
|
|
"num_tokens": 2114710.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 7.639475536346436,
|
|
"epoch": 0.10796221322537113,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999992934015752,
|
|
"loss": 7.3907,
|
|
"mean_token_accuracy": 0.10413632541894913,
|
|
"num_tokens": 2124002.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 7.7447285652160645,
|
|
"epoch": 0.10846203828659969,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999992011283215,
|
|
"loss": 7.4876,
|
|
"mean_token_accuracy": 0.09875040203332901,
|
|
"num_tokens": 2134592.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 7.503586864471435,
|
|
"epoch": 0.10896186334782826,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999991031941459,
|
|
"loss": 7.3316,
|
|
"mean_token_accuracy": 0.1076856717467308,
|
|
"num_tokens": 2143641.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 7.718939399719238,
|
|
"epoch": 0.10946168840905683,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999989995990509,
|
|
"loss": 7.4484,
|
|
"mean_token_accuracy": 0.10091273114085197,
|
|
"num_tokens": 2154738.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 7.511824655532837,
|
|
"epoch": 0.1099615134702854,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999988903430389,
|
|
"loss": 7.3804,
|
|
"mean_token_accuracy": 0.11026987135410309,
|
|
"num_tokens": 2164365.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 7.610298585891724,
|
|
"epoch": 0.11046133853151396,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999987754261126,
|
|
"loss": 7.2694,
|
|
"mean_token_accuracy": 0.1102310411632061,
|
|
"num_tokens": 2173185.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 7.579056692123413,
|
|
"epoch": 0.11096116359274254,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999986548482751,
|
|
"loss": 7.382,
|
|
"mean_token_accuracy": 0.10696444734930992,
|
|
"num_tokens": 2184717.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 7.6235607147216795,
|
|
"epoch": 0.11146098865397111,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999985286095293,
|
|
"loss": 7.3611,
|
|
"mean_token_accuracy": 0.10928932800889016,
|
|
"num_tokens": 2193681.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 7.571579217910767,
|
|
"epoch": 0.11196081371519968,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004999983967098785,
|
|
"loss": 7.3752,
|
|
"mean_token_accuracy": 0.10050557106733322,
|
|
"num_tokens": 2203366.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 7.621008968353271,
|
|
"epoch": 0.11246063877642826,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999982591493258,
|
|
"loss": 7.3709,
|
|
"mean_token_accuracy": 0.10311305895447731,
|
|
"num_tokens": 2213982.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 7.596260356903076,
|
|
"epoch": 0.11296046383765682,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999981159278749,
|
|
"loss": 7.4162,
|
|
"mean_token_accuracy": 0.09981422498822212,
|
|
"num_tokens": 2222897.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 7.580492305755615,
|
|
"epoch": 0.11346028889888539,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999979670455292,
|
|
"loss": 7.3682,
|
|
"mean_token_accuracy": 0.10767317786812783,
|
|
"num_tokens": 2232472.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 7.618267774581909,
|
|
"epoch": 0.11396011396011396,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004999978125022926,
|
|
"loss": 7.408,
|
|
"mean_token_accuracy": 0.10514756217598915,
|
|
"num_tokens": 2242666.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 7.6292320728302006,
|
|
"epoch": 0.11445993902134254,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000499997652298169,
|
|
"loss": 7.4861,
|
|
"mean_token_accuracy": 0.09657154306769371,
|
|
"num_tokens": 2254586.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 7.628611993789673,
|
|
"epoch": 0.1149597640825711,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999974864331624,
|
|
"loss": 7.3073,
|
|
"mean_token_accuracy": 0.11019685044884682,
|
|
"num_tokens": 2264619.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 7.67947096824646,
|
|
"epoch": 0.11545958914379967,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999973149072768,
|
|
"loss": 7.3913,
|
|
"mean_token_accuracy": 0.09589539244771003,
|
|
"num_tokens": 2274114.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 7.469546747207642,
|
|
"epoch": 0.11595941420502824,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999971377205167,
|
|
"loss": 7.303,
|
|
"mean_token_accuracy": 0.10781149342656135,
|
|
"num_tokens": 2283887.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 7.548113679885864,
|
|
"epoch": 0.11645923926625681,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999969548728864,
|
|
"loss": 7.3248,
|
|
"mean_token_accuracy": 0.10801458954811097,
|
|
"num_tokens": 2293090.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 7.564089012145996,
|
|
"epoch": 0.11695906432748537,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999967663643908,
|
|
"loss": 7.4209,
|
|
"mean_token_accuracy": 0.10221518129110337,
|
|
"num_tokens": 2302828.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 7.659123516082763,
|
|
"epoch": 0.11745888938871395,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999965721950345,
|
|
"loss": 7.3104,
|
|
"mean_token_accuracy": 0.10870119705796241,
|
|
"num_tokens": 2311415.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 7.541514921188354,
|
|
"epoch": 0.11795871444994252,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999963723648222,
|
|
"loss": 7.3946,
|
|
"mean_token_accuracy": 0.10008503422141075,
|
|
"num_tokens": 2321512.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 7.579466390609741,
|
|
"epoch": 0.1184585395111711,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000499996166873759,
|
|
"loss": 7.2918,
|
|
"mean_token_accuracy": 0.1035538524389267,
|
|
"num_tokens": 2331398.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 7.571394538879394,
|
|
"epoch": 0.11895836457239967,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999959557218502,
|
|
"loss": 7.2865,
|
|
"mean_token_accuracy": 0.11054573953151703,
|
|
"num_tokens": 2341751.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 7.55456509590149,
|
|
"epoch": 0.11945818963362823,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999957389091012,
|
|
"loss": 7.3187,
|
|
"mean_token_accuracy": 0.10006105899810791,
|
|
"num_tokens": 2352538.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 7.590258026123047,
|
|
"epoch": 0.1199580146948568,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999955164355171,
|
|
"loss": 7.3704,
|
|
"mean_token_accuracy": 0.09887034147977829,
|
|
"num_tokens": 2362433.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 7.561069488525391,
|
|
"epoch": 0.12045783975608537,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999952883011038,
|
|
"loss": 7.3513,
|
|
"mean_token_accuracy": 0.10028525441884995,
|
|
"num_tokens": 2372431.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 7.55907883644104,
|
|
"epoch": 0.12095766481731395,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000499995054505867,
|
|
"loss": 7.361,
|
|
"mean_token_accuracy": 0.10952726975083352,
|
|
"num_tokens": 2382483.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 7.617351865768432,
|
|
"epoch": 0.1214574898785425,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999948150498124,
|
|
"loss": 7.33,
|
|
"mean_token_accuracy": 0.0975058175623417,
|
|
"num_tokens": 2392835.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 7.545529508590699,
|
|
"epoch": 0.12195731493977108,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999945699329462,
|
|
"loss": 7.3021,
|
|
"mean_token_accuracy": 0.1018272578716278,
|
|
"num_tokens": 2402305.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 7.388929176330566,
|
|
"epoch": 0.12245714000099965,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999943191552745,
|
|
"loss": 7.2427,
|
|
"mean_token_accuracy": 0.10890847146511078,
|
|
"num_tokens": 2412093.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 7.547239828109741,
|
|
"epoch": 0.12295696506222822,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999940627168037,
|
|
"loss": 7.2174,
|
|
"mean_token_accuracy": 0.11171707957983017,
|
|
"num_tokens": 2421349.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 7.439934778213501,
|
|
"epoch": 0.12345679012345678,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00049999380061754,
|
|
"loss": 7.2001,
|
|
"mean_token_accuracy": 0.12013261988759041,
|
|
"num_tokens": 2430672.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 7.468397808074951,
|
|
"epoch": 0.12395661518468536,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999935328574903,
|
|
"loss": 7.2823,
|
|
"mean_token_accuracy": 0.10177658125758171,
|
|
"num_tokens": 2439355.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 7.4700652122497555,
|
|
"epoch": 0.12445644024591393,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999932594366613,
|
|
"loss": 7.2817,
|
|
"mean_token_accuracy": 0.11226417720317841,
|
|
"num_tokens": 2448860.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 7.478579568862915,
|
|
"epoch": 0.1249562653071425,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999929803550597,
|
|
"loss": 7.3139,
|
|
"mean_token_accuracy": 0.10246847122907639,
|
|
"num_tokens": 2458276.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 7.4616804122924805,
|
|
"epoch": 0.12545609036837108,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999926956126927,
|
|
"loss": 7.2455,
|
|
"mean_token_accuracy": 0.10908352881669998,
|
|
"num_tokens": 2467791.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 7.4985151290893555,
|
|
"epoch": 0.12595591542959964,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999924052095672,
|
|
"loss": 7.3538,
|
|
"mean_token_accuracy": 0.10554418563842774,
|
|
"num_tokens": 2477549.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 7.4841855525970455,
|
|
"epoch": 0.12645574049082822,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999921091456907,
|
|
"loss": 7.267,
|
|
"mean_token_accuracy": 0.10368448942899704,
|
|
"num_tokens": 2487549.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 7.513351202011108,
|
|
"epoch": 0.12695556555205678,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999918074210707,
|
|
"loss": 7.2834,
|
|
"mean_token_accuracy": 0.10522937551140785,
|
|
"num_tokens": 2496799.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 7.574540710449218,
|
|
"epoch": 0.12745539061328534,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999915000357147,
|
|
"loss": 7.3662,
|
|
"mean_token_accuracy": 0.10323404893279076,
|
|
"num_tokens": 2505795.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 7.454508924484253,
|
|
"epoch": 0.12795521567451393,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999911869896305,
|
|
"loss": 7.1844,
|
|
"mean_token_accuracy": 0.10558920055627823,
|
|
"num_tokens": 2515289.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 7.503220081329346,
|
|
"epoch": 0.1284550407357425,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999908682828258,
|
|
"loss": 7.3608,
|
|
"mean_token_accuracy": 0.0966832160949707,
|
|
"num_tokens": 2524563.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 7.508555841445923,
|
|
"epoch": 0.12895486579697105,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999905439153089,
|
|
"loss": 7.2596,
|
|
"mean_token_accuracy": 0.10827950909733772,
|
|
"num_tokens": 2534057.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 7.381141519546508,
|
|
"epoch": 0.12945469085819963,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999902138870878,
|
|
"loss": 7.236,
|
|
"mean_token_accuracy": 0.11027004197239876,
|
|
"num_tokens": 2544646.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 7.5540282249450685,
|
|
"epoch": 0.1299545159194282,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999898781981707,
|
|
"loss": 7.3068,
|
|
"mean_token_accuracy": 0.10171382352709771,
|
|
"num_tokens": 2553843.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 7.427649259567261,
|
|
"epoch": 0.13045434098065678,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999895368485662,
|
|
"loss": 7.3316,
|
|
"mean_token_accuracy": 0.10106317475438117,
|
|
"num_tokens": 2564061.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 7.458715009689331,
|
|
"epoch": 0.13095416604188534,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000499989189838283,
|
|
"loss": 7.2052,
|
|
"mean_token_accuracy": 0.10916719138622284,
|
|
"num_tokens": 2574758.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 7.455377197265625,
|
|
"epoch": 0.1314539911031139,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999888371673295,
|
|
"loss": 7.2648,
|
|
"mean_token_accuracy": 0.10652579218149186,
|
|
"num_tokens": 2585213.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 7.495338344573975,
|
|
"epoch": 0.13195381616434249,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999884788357147,
|
|
"loss": 7.3251,
|
|
"mean_token_accuracy": 0.1046051949262619,
|
|
"num_tokens": 2595511.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 7.45457911491394,
|
|
"epoch": 0.13245364122557104,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999881148434478,
|
|
"loss": 7.2535,
|
|
"mean_token_accuracy": 0.1045147307217121,
|
|
"num_tokens": 2605930.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 7.457170677185059,
|
|
"epoch": 0.13295346628679963,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999877451905378,
|
|
"loss": 7.1207,
|
|
"mean_token_accuracy": 0.11842303052544594,
|
|
"num_tokens": 2614224.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 7.472532939910889,
|
|
"epoch": 0.1334532913480282,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999873698769941,
|
|
"loss": 7.3418,
|
|
"mean_token_accuracy": 0.09856024906039237,
|
|
"num_tokens": 2624879.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 7.5039904594421385,
|
|
"epoch": 0.13395311640925675,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000499986988902826,
|
|
"loss": 7.2125,
|
|
"mean_token_accuracy": 0.10768636465072631,
|
|
"num_tokens": 2633836.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 7.338539552688599,
|
|
"epoch": 0.13445294147048534,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999866022680431,
|
|
"loss": 7.2666,
|
|
"mean_token_accuracy": 0.1048534668982029,
|
|
"num_tokens": 2643754.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 7.622525882720947,
|
|
"epoch": 0.1349527665317139,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999862099726552,
|
|
"loss": 7.3281,
|
|
"mean_token_accuracy": 0.1025710292160511,
|
|
"num_tokens": 2652708.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 7.392505550384522,
|
|
"epoch": 0.13545259159294248,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004999858120166721,
|
|
"loss": 7.2885,
|
|
"mean_token_accuracy": 0.10265006273984909,
|
|
"num_tokens": 2662353.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 7.424199056625366,
|
|
"epoch": 0.13595241665417104,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999854084001039,
|
|
"loss": 7.19,
|
|
"mean_token_accuracy": 0.10960527732968331,
|
|
"num_tokens": 2672376.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 7.4624227523803714,
|
|
"epoch": 0.1364522417153996,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999849991229608,
|
|
"loss": 7.2762,
|
|
"mean_token_accuracy": 0.10267233923077583,
|
|
"num_tokens": 2682115.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 7.424701595306397,
|
|
"epoch": 0.1369520667766282,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000499984584185253,
|
|
"loss": 7.2615,
|
|
"mean_token_accuracy": 0.1053126648068428,
|
|
"num_tokens": 2692429.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 7.444271993637085,
|
|
"epoch": 0.13745189183785675,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999841635869909,
|
|
"loss": 7.2144,
|
|
"mean_token_accuracy": 0.10922285541892052,
|
|
"num_tokens": 2701373.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 7.525673151016235,
|
|
"epoch": 0.1379517168990853,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004999837373281852,
|
|
"loss": 7.3898,
|
|
"mean_token_accuracy": 0.10230721682310104,
|
|
"num_tokens": 2710717.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 7.4701214790344235,
|
|
"epoch": 0.1384515419603139,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999833054088465,
|
|
"loss": 7.2443,
|
|
"mean_token_accuracy": 0.10736606866121293,
|
|
"num_tokens": 2720936.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 7.437333965301514,
|
|
"epoch": 0.13895136702154245,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999828678289858,
|
|
"loss": 7.1823,
|
|
"mean_token_accuracy": 0.11095159128308296,
|
|
"num_tokens": 2730504.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 7.421475410461426,
|
|
"epoch": 0.13945119208277104,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499982424588614,
|
|
"loss": 7.2116,
|
|
"mean_token_accuracy": 0.10913697853684426,
|
|
"num_tokens": 2739069.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 7.433441162109375,
|
|
"epoch": 0.1399510171439996,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999819756877422,
|
|
"loss": 7.2829,
|
|
"mean_token_accuracy": 0.10340380370616913,
|
|
"num_tokens": 2748941.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 7.4657440185546875,
|
|
"epoch": 0.14045084220522816,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999815211263819,
|
|
"loss": 7.2414,
|
|
"mean_token_accuracy": 0.10870002508163452,
|
|
"num_tokens": 2758915.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 7.471285152435303,
|
|
"epoch": 0.14095066726645675,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999810609045444,
|
|
"loss": 7.2686,
|
|
"mean_token_accuracy": 0.10555689707398415,
|
|
"num_tokens": 2768972.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 7.414257478713989,
|
|
"epoch": 0.1414504923276853,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999805950222412,
|
|
"loss": 7.1266,
|
|
"mean_token_accuracy": 0.112129794806242,
|
|
"num_tokens": 2777989.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 7.3253881454467775,
|
|
"epoch": 0.1419503173889139,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999801234794843,
|
|
"loss": 7.2124,
|
|
"mean_token_accuracy": 0.10934107601642609,
|
|
"num_tokens": 2788227.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 7.480621862411499,
|
|
"epoch": 0.14245014245014245,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999796462762853,
|
|
"loss": 7.212,
|
|
"mean_token_accuracy": 0.1068321980535984,
|
|
"num_tokens": 2797729.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 7.441812515258789,
|
|
"epoch": 0.142949967511371,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999791634126562,
|
|
"loss": 7.1993,
|
|
"mean_token_accuracy": 0.10914001166820526,
|
|
"num_tokens": 2807215.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 7.380958318710327,
|
|
"epoch": 0.1434497925725996,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999786748886094,
|
|
"loss": 7.1273,
|
|
"mean_token_accuracy": 0.10741899609565735,
|
|
"num_tokens": 2816945.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 7.335004377365112,
|
|
"epoch": 0.14394961763382816,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999781807041569,
|
|
"loss": 7.2064,
|
|
"mean_token_accuracy": 0.10659912303090095,
|
|
"num_tokens": 2827072.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 7.436053657531739,
|
|
"epoch": 0.14444944269505672,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999776808593113,
|
|
"loss": 7.1381,
|
|
"mean_token_accuracy": 0.10905283689498901,
|
|
"num_tokens": 2837928.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 7.265142488479614,
|
|
"epoch": 0.1449492677562853,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999771753540852,
|
|
"loss": 7.179,
|
|
"mean_token_accuracy": 0.10916463062167167,
|
|
"num_tokens": 2847861.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 7.440875148773193,
|
|
"epoch": 0.14544909281751386,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999766641884912,
|
|
"loss": 7.1819,
|
|
"mean_token_accuracy": 0.1099862240254879,
|
|
"num_tokens": 2857885.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 7.47276120185852,
|
|
"epoch": 0.14594891787874245,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999761473625422,
|
|
"loss": 7.1931,
|
|
"mean_token_accuracy": 0.10840637236833572,
|
|
"num_tokens": 2867004.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 7.34009747505188,
|
|
"epoch": 0.146448742939971,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999756248762513,
|
|
"loss": 7.0759,
|
|
"mean_token_accuracy": 0.11003444865345954,
|
|
"num_tokens": 2876285.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 7.343789863586426,
|
|
"epoch": 0.14694856800119957,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004999750967296315,
|
|
"loss": 7.1943,
|
|
"mean_token_accuracy": 0.10783570408821105,
|
|
"num_tokens": 2886967.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 7.352244138717651,
|
|
"epoch": 0.14744839306242816,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999745629226962,
|
|
"loss": 7.1707,
|
|
"mean_token_accuracy": 0.10942457839846612,
|
|
"num_tokens": 2897137.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 7.343924140930175,
|
|
"epoch": 0.14794821812365672,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004999740234554589,
|
|
"loss": 7.1515,
|
|
"mean_token_accuracy": 0.11578499227762222,
|
|
"num_tokens": 2907658.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 7.364530467987061,
|
|
"epoch": 0.1484480431848853,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999734783279327,
|
|
"loss": 7.1334,
|
|
"mean_token_accuracy": 0.11196301355957985,
|
|
"num_tokens": 2917801.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 7.394926309585571,
|
|
"epoch": 0.14894786824611386,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499972927540132,
|
|
"loss": 7.237,
|
|
"mean_token_accuracy": 0.10743141695857047,
|
|
"num_tokens": 2927188.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 7.377376556396484,
|
|
"epoch": 0.14944769330734242,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999723710920703,
|
|
"loss": 7.1152,
|
|
"mean_token_accuracy": 0.10680729150772095,
|
|
"num_tokens": 2936781.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 7.2929119110107425,
|
|
"epoch": 0.149947518368571,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999718089837616,
|
|
"loss": 7.0999,
|
|
"mean_token_accuracy": 0.10934963151812553,
|
|
"num_tokens": 2946426.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 7.274065399169922,
|
|
"epoch": 0.15044734342979957,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00049997124121522,
|
|
"loss": 7.1414,
|
|
"mean_token_accuracy": 0.10659637004137039,
|
|
"num_tokens": 2956246.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 7.381241321563721,
|
|
"epoch": 0.15094716849102813,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999706677864599,
|
|
"loss": 7.1364,
|
|
"mean_token_accuracy": 0.10887710601091385,
|
|
"num_tokens": 2965930.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 7.290860176086426,
|
|
"epoch": 0.15144699355225671,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004999700886974958,
|
|
"loss": 7.0529,
|
|
"mean_token_accuracy": 0.11699229776859284,
|
|
"num_tokens": 2975975.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 7.316656589508057,
|
|
"epoch": 0.15194681861348527,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000499969503948342,
|
|
"loss": 7.082,
|
|
"mean_token_accuracy": 0.1087965801358223,
|
|
"num_tokens": 2985343.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 7.285784769058227,
|
|
"epoch": 0.15244664367471386,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999689135390134,
|
|
"loss": 7.1083,
|
|
"mean_token_accuracy": 0.11093569695949554,
|
|
"num_tokens": 2994420.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 7.318411874771118,
|
|
"epoch": 0.15294646873594242,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999683174695249,
|
|
"loss": 7.2103,
|
|
"mean_token_accuracy": 0.10868243128061295,
|
|
"num_tokens": 3004447.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 7.479772996902466,
|
|
"epoch": 0.15344629379717098,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004999677157398914,
|
|
"loss": 7.1,
|
|
"mean_token_accuracy": 0.11058899015188217,
|
|
"num_tokens": 3014596.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 7.251273250579834,
|
|
"epoch": 0.15394611885839957,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004999671083501281,
|
|
"loss": 7.0292,
|
|
"mean_token_accuracy": 0.11444317251443863,
|
|
"num_tokens": 3024528.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 7.28997917175293,
|
|
"epoch": 0.15444594391962813,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999664953002502,
|
|
"loss": 7.1557,
|
|
"mean_token_accuracy": 0.10664113461971284,
|
|
"num_tokens": 3035233.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 7.3472541809082035,
|
|
"epoch": 0.1549457689808567,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499965876590273,
|
|
"loss": 7.1567,
|
|
"mean_token_accuracy": 0.11339146867394448,
|
|
"num_tokens": 3045890.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 7.251162910461426,
|
|
"epoch": 0.15544559404208527,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999652522202125,
|
|
"loss": 7.0648,
|
|
"mean_token_accuracy": 0.11411697939038276,
|
|
"num_tokens": 3056640.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 7.315458631515503,
|
|
"epoch": 0.15594541910331383,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999646221900839,
|
|
"loss": 7.0761,
|
|
"mean_token_accuracy": 0.11611308604478836,
|
|
"num_tokens": 3066938.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 7.28765344619751,
|
|
"epoch": 0.15644524416454242,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004999639864999034,
|
|
"loss": 7.1933,
|
|
"mean_token_accuracy": 0.1076837420463562,
|
|
"num_tokens": 3076791.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 7.381633186340332,
|
|
"epoch": 0.15694506922577098,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000499963345149687,
|
|
"loss": 7.0536,
|
|
"mean_token_accuracy": 0.11385932415723801,
|
|
"num_tokens": 3087532.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 7.220392751693725,
|
|
"epoch": 0.15744489428699954,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004999626981394506,
|
|
"loss": 7.1733,
|
|
"mean_token_accuracy": 0.11016052812337876,
|
|
"num_tokens": 3097465.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 7.435248279571534,
|
|
"epoch": 0.15794471934822812,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999620454692106,
|
|
"loss": 7.0846,
|
|
"mean_token_accuracy": 0.1115849569439888,
|
|
"num_tokens": 3107162.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 7.236566162109375,
|
|
"epoch": 0.15844454440945668,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999613871389836,
|
|
"loss": 7.0768,
|
|
"mean_token_accuracy": 0.11040661185979843,
|
|
"num_tokens": 3117154.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 7.266448545455932,
|
|
"epoch": 0.15894436947068527,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999607231487858,
|
|
"loss": 7.0859,
|
|
"mean_token_accuracy": 0.11145442575216294,
|
|
"num_tokens": 3127635.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 7.3993692874908445,
|
|
"epoch": 0.15944419453191383,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000499960053498634,
|
|
"loss": 7.1231,
|
|
"mean_token_accuracy": 0.10866989269852638,
|
|
"num_tokens": 3137806.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 7.321648645401001,
|
|
"epoch": 0.1599440195931424,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999593781885454,
|
|
"loss": 7.1575,
|
|
"mean_token_accuracy": 0.10646053105592727,
|
|
"num_tokens": 3147704.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 7.28309473991394,
|
|
"epoch": 0.16044384465437098,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999586972185366,
|
|
"loss": 7.1107,
|
|
"mean_token_accuracy": 0.105899029225111,
|
|
"num_tokens": 3158486.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 7.324327421188355,
|
|
"epoch": 0.16094366971559954,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999580105886248,
|
|
"loss": 7.108,
|
|
"mean_token_accuracy": 0.10965174809098244,
|
|
"num_tokens": 3168518.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 7.243863439559936,
|
|
"epoch": 0.16144349477682812,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999573182988275,
|
|
"loss": 7.0088,
|
|
"mean_token_accuracy": 0.11485414430499077,
|
|
"num_tokens": 3177502.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 7.24871244430542,
|
|
"epoch": 0.16194331983805668,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999566203491619,
|
|
"loss": 7.0729,
|
|
"mean_token_accuracy": 0.11296822354197503,
|
|
"num_tokens": 3187408.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 7.314590549468994,
|
|
"epoch": 0.16244314489928524,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999559167396455,
|
|
"loss": 7.1227,
|
|
"mean_token_accuracy": 0.11361486688256264,
|
|
"num_tokens": 3196812.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 7.246614170074463,
|
|
"epoch": 0.16294296996051383,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999552074702963,
|
|
"loss": 6.9737,
|
|
"mean_token_accuracy": 0.11634291410446167,
|
|
"num_tokens": 3206159.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 7.23604302406311,
|
|
"epoch": 0.1634427950217424,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004999544925411318,
|
|
"loss": 6.9716,
|
|
"mean_token_accuracy": 0.11750346943736076,
|
|
"num_tokens": 3217329.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 7.23541374206543,
|
|
"epoch": 0.16394262008297095,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004999537719521703,
|
|
"loss": 7.0904,
|
|
"mean_token_accuracy": 0.11265335828065873,
|
|
"num_tokens": 3227558.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 7.3270646095275875,
|
|
"epoch": 0.16444244514419953,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999530457034297,
|
|
"loss": 7.1907,
|
|
"mean_token_accuracy": 0.10715283155441284,
|
|
"num_tokens": 3237719.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 7.3062530040740965,
|
|
"epoch": 0.1649422702054281,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999523137949283,
|
|
"loss": 7.0868,
|
|
"mean_token_accuracy": 0.11413407698273659,
|
|
"num_tokens": 3246483.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 7.198418855667114,
|
|
"epoch": 0.16544209526665668,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004999515762266846,
|
|
"loss": 6.9876,
|
|
"mean_token_accuracy": 0.11951323971152306,
|
|
"num_tokens": 3256955.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 7.281463003158569,
|
|
"epoch": 0.16594192032788524,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999508329987173,
|
|
"loss": 7.0615,
|
|
"mean_token_accuracy": 0.10993959754705429,
|
|
"num_tokens": 3266799.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 7.3243176460266115,
|
|
"epoch": 0.1664417453891138,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999500841110447,
|
|
"loss": 7.0627,
|
|
"mean_token_accuracy": 0.11115454137325287,
|
|
"num_tokens": 3276595.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 7.170014476776123,
|
|
"epoch": 0.16694157045034239,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000499949329563686,
|
|
"loss": 7.0036,
|
|
"mean_token_accuracy": 0.11233359575271606,
|
|
"num_tokens": 3286047.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 7.2867292881011965,
|
|
"epoch": 0.16744139551157095,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00049994856935666,
|
|
"loss": 7.0971,
|
|
"mean_token_accuracy": 0.10945143923163414,
|
|
"num_tokens": 3295364.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 7.282499170303344,
|
|
"epoch": 0.16794122057279953,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000499947803489986,
|
|
"loss": 6.9968,
|
|
"mean_token_accuracy": 0.11751805990934372,
|
|
"num_tokens": 3305319.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 7.17340202331543,
|
|
"epoch": 0.1684410456340281,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999470319636829,
|
|
"loss": 7.0171,
|
|
"mean_token_accuracy": 0.11624193787574769,
|
|
"num_tokens": 3315349.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 7.2853912830352785,
|
|
"epoch": 0.16894087069525665,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999462547777705,
|
|
"loss": 7.0887,
|
|
"mean_token_accuracy": 0.10680258646607399,
|
|
"num_tokens": 3325603.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 7.203047037124634,
|
|
"epoch": 0.16944069575648524,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999454719322682,
|
|
"loss": 6.9998,
|
|
"mean_token_accuracy": 0.11204721629619599,
|
|
"num_tokens": 3334693.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 7.272320556640625,
|
|
"epoch": 0.1699405208177138,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999446834271958,
|
|
"loss": 7.0064,
|
|
"mean_token_accuracy": 0.10611082762479782,
|
|
"num_tokens": 3345259.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 7.210876941680908,
|
|
"epoch": 0.17044034587894236,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999438892625728,
|
|
"loss": 7.0013,
|
|
"mean_token_accuracy": 0.11196986362338066,
|
|
"num_tokens": 3354072.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 7.286466646194458,
|
|
"epoch": 0.17094017094017094,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999430894384198,
|
|
"loss": 7.0142,
|
|
"mean_token_accuracy": 0.1119252622127533,
|
|
"num_tokens": 3364881.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 7.226142120361328,
|
|
"epoch": 0.1714399960013995,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999422839547564,
|
|
"loss": 6.9904,
|
|
"mean_token_accuracy": 0.11430766358971596,
|
|
"num_tokens": 3374030.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 7.220478677749634,
|
|
"epoch": 0.1719398210626281,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999414728116029,
|
|
"loss": 6.9778,
|
|
"mean_token_accuracy": 0.11128946840763092,
|
|
"num_tokens": 3384009.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 7.301162242889404,
|
|
"epoch": 0.17243964612385665,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999406560089798,
|
|
"loss": 7.1074,
|
|
"mean_token_accuracy": 0.11010550707578659,
|
|
"num_tokens": 3393660.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 7.27868685722351,
|
|
"epoch": 0.1729394711850852,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999398335469078,
|
|
"loss": 7.1187,
|
|
"mean_token_accuracy": 0.10912684947252274,
|
|
"num_tokens": 3404364.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 7.307126235961914,
|
|
"epoch": 0.1734392962463138,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999390054254074,
|
|
"loss": 7.0129,
|
|
"mean_token_accuracy": 0.10965274721384048,
|
|
"num_tokens": 3412990.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 7.103516006469727,
|
|
"epoch": 0.17393912130754235,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999381716444996,
|
|
"loss": 6.984,
|
|
"mean_token_accuracy": 0.11489634066820145,
|
|
"num_tokens": 3422339.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 7.192869377136231,
|
|
"epoch": 0.17443894636877094,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004999373322042052,
|
|
"loss": 6.9704,
|
|
"mean_token_accuracy": 0.1187138944864273,
|
|
"num_tokens": 3433093.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 7.266874742507935,
|
|
"epoch": 0.1749387714299995,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999364871045455,
|
|
"loss": 7.0579,
|
|
"mean_token_accuracy": 0.1107969380915165,
|
|
"num_tokens": 3443464.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 7.208977365493775,
|
|
"epoch": 0.17543859649122806,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004999356363455415,
|
|
"loss": 6.9891,
|
|
"mean_token_accuracy": 0.11229778155684471,
|
|
"num_tokens": 3453380.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 7.2512282371521,
|
|
"epoch": 0.17593842155245665,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000499934779927215,
|
|
"loss": 7.0487,
|
|
"mean_token_accuracy": 0.11276780366897583,
|
|
"num_tokens": 3463583.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 7.108209085464478,
|
|
"epoch": 0.1764382466136852,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999339178495872,
|
|
"loss": 6.9567,
|
|
"mean_token_accuracy": 0.1195647343993187,
|
|
"num_tokens": 3473640.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 7.258290004730225,
|
|
"epoch": 0.1769380716749138,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999330501126798,
|
|
"loss": 7.0087,
|
|
"mean_token_accuracy": 0.11589695587754249,
|
|
"num_tokens": 3483827.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 7.162285470962525,
|
|
"epoch": 0.17743789673614235,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999321767165148,
|
|
"loss": 6.9711,
|
|
"mean_token_accuracy": 0.12137874588370323,
|
|
"num_tokens": 3493763.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 7.261633634567261,
|
|
"epoch": 0.1779377217973709,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999312976611142,
|
|
"loss": 7.0714,
|
|
"mean_token_accuracy": 0.11497013196349144,
|
|
"num_tokens": 3503119.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 7.239193248748779,
|
|
"epoch": 0.1784375468585995,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999304129465,
|
|
"loss": 7.0063,
|
|
"mean_token_accuracy": 0.11441105306148529,
|
|
"num_tokens": 3513235.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 7.172239589691162,
|
|
"epoch": 0.17893737191982806,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999295225726945,
|
|
"loss": 7.109,
|
|
"mean_token_accuracy": 0.11077995523810387,
|
|
"num_tokens": 3523633.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 7.217508792877197,
|
|
"epoch": 0.17943719698105662,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00049992862653972,
|
|
"loss": 6.9661,
|
|
"mean_token_accuracy": 0.11305666714906693,
|
|
"num_tokens": 3532888.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 7.171756887435913,
|
|
"epoch": 0.1799370220422852,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999277248475992,
|
|
"loss": 6.9914,
|
|
"mean_token_accuracy": 0.11619005724787712,
|
|
"num_tokens": 3541942.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 7.162946081161499,
|
|
"epoch": 0.18043684710351376,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999268174963547,
|
|
"loss": 6.9532,
|
|
"mean_token_accuracy": 0.11453788876533508,
|
|
"num_tokens": 3551544.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 7.187183475494384,
|
|
"epoch": 0.18093667216474235,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999259044860093,
|
|
"loss": 6.9411,
|
|
"mean_token_accuracy": 0.11845703423023224,
|
|
"num_tokens": 3561024.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 7.203239154815674,
|
|
"epoch": 0.1814364972259709,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999249858165861,
|
|
"loss": 6.9324,
|
|
"mean_token_accuracy": 0.12066594958305359,
|
|
"num_tokens": 3570962.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 7.026967144012451,
|
|
"epoch": 0.18193632228719947,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999240614881082,
|
|
"loss": 6.9255,
|
|
"mean_token_accuracy": 0.12051551789045334,
|
|
"num_tokens": 3580669.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 7.2166660785675045,
|
|
"epoch": 0.18243614734842806,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999231315005987,
|
|
"loss": 6.9524,
|
|
"mean_token_accuracy": 0.11456257104873657,
|
|
"num_tokens": 3590627.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 7.190853023529053,
|
|
"epoch": 0.18293597240965662,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999221958540811,
|
|
"loss": 7.015,
|
|
"mean_token_accuracy": 0.10618584454059601,
|
|
"num_tokens": 3599872.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 7.208268022537231,
|
|
"epoch": 0.1834357974708852,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999212545485789,
|
|
"loss": 7.0008,
|
|
"mean_token_accuracy": 0.11748863831162452,
|
|
"num_tokens": 3609809.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 7.2950187683105465,
|
|
"epoch": 0.18393562253211376,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999203075841159,
|
|
"loss": 7.0256,
|
|
"mean_token_accuracy": 0.11501933261752129,
|
|
"num_tokens": 3619385.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 7.049505376815796,
|
|
"epoch": 0.18443544759334232,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004999193549607157,
|
|
"loss": 6.8527,
|
|
"mean_token_accuracy": 0.12542221918702126,
|
|
"num_tokens": 3628867.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 7.11543025970459,
|
|
"epoch": 0.1849352726545709,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999183966784026,
|
|
"loss": 6.8588,
|
|
"mean_token_accuracy": 0.12358809560537339,
|
|
"num_tokens": 3637528.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 7.202391195297241,
|
|
"epoch": 0.18543509771579947,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004999174327372004,
|
|
"loss": 7.0118,
|
|
"mean_token_accuracy": 0.11167162656784058,
|
|
"num_tokens": 3648011.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 7.162098455429077,
|
|
"epoch": 0.18593492277702803,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999164631371335,
|
|
"loss": 6.9861,
|
|
"mean_token_accuracy": 0.11887979209423065,
|
|
"num_tokens": 3657648.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 7.202825736999512,
|
|
"epoch": 0.18643474783825661,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999154878782262,
|
|
"loss": 6.9828,
|
|
"mean_token_accuracy": 0.11495407447218894,
|
|
"num_tokens": 3666965.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 7.200334119796753,
|
|
"epoch": 0.18693457289948517,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499914506960503,
|
|
"loss": 6.9956,
|
|
"mean_token_accuracy": 0.11006476879119872,
|
|
"num_tokens": 3676609.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 7.093168592453003,
|
|
"epoch": 0.18743439796071376,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999135203839889,
|
|
"loss": 6.8839,
|
|
"mean_token_accuracy": 0.11935680136084556,
|
|
"num_tokens": 3685884.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 7.126411867141724,
|
|
"epoch": 0.18793422302194232,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999125281487084,
|
|
"loss": 7.0068,
|
|
"mean_token_accuracy": 0.1182105928659439,
|
|
"num_tokens": 3695436.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 7.144247961044312,
|
|
"epoch": 0.18843404808317088,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999115302546866,
|
|
"loss": 6.8441,
|
|
"mean_token_accuracy": 0.12458746284246444,
|
|
"num_tokens": 3704806.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 7.070190811157227,
|
|
"epoch": 0.18893387314439947,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004999105267019486,
|
|
"loss": 6.927,
|
|
"mean_token_accuracy": 0.11586586683988571,
|
|
"num_tokens": 3713927.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 7.240120220184326,
|
|
"epoch": 0.18943369820562803,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999095174905195,
|
|
"loss": 6.9918,
|
|
"mean_token_accuracy": 0.11079314202070237,
|
|
"num_tokens": 3723685.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 7.096197319030762,
|
|
"epoch": 0.1899335232668566,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999085026204249,
|
|
"loss": 6.949,
|
|
"mean_token_accuracy": 0.11694203093647956,
|
|
"num_tokens": 3733918.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 7.182708120346069,
|
|
"epoch": 0.19043334832808517,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004999074820916903,
|
|
"loss": 6.9316,
|
|
"mean_token_accuracy": 0.11336019709706306,
|
|
"num_tokens": 3744466.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 7.1592817306518555,
|
|
"epoch": 0.19093317338931373,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999064559043412,
|
|
"loss": 6.8797,
|
|
"mean_token_accuracy": 0.11740054339170455,
|
|
"num_tokens": 3754082.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 7.081003665924072,
|
|
"epoch": 0.19143299845054232,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999054240584037,
|
|
"loss": 6.9088,
|
|
"mean_token_accuracy": 0.1203138992190361,
|
|
"num_tokens": 3763111.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 7.212647819519043,
|
|
"epoch": 0.19193282351177088,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999043865539035,
|
|
"loss": 6.9635,
|
|
"mean_token_accuracy": 0.10895317792892456,
|
|
"num_tokens": 3772555.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 7.189334392547607,
|
|
"epoch": 0.19243264857299944,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999033433908667,
|
|
"loss": 6.998,
|
|
"mean_token_accuracy": 0.11409115567803382,
|
|
"num_tokens": 3783073.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 7.0710899353027346,
|
|
"epoch": 0.19293247363422802,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999022945693198,
|
|
"loss": 6.9411,
|
|
"mean_token_accuracy": 0.11544915810227394,
|
|
"num_tokens": 3792277.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 7.1727738857269285,
|
|
"epoch": 0.19343229869545658,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000499901240089289,
|
|
"loss": 6.8969,
|
|
"mean_token_accuracy": 0.11691495999693871,
|
|
"num_tokens": 3801098.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 7.160139465332032,
|
|
"epoch": 0.19393212375668517,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999001799508009,
|
|
"loss": 6.9196,
|
|
"mean_token_accuracy": 0.11668399348855019,
|
|
"num_tokens": 3810614.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 7.043404626846313,
|
|
"epoch": 0.19443194881791373,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998991141538821,
|
|
"loss": 6.9305,
|
|
"mean_token_accuracy": 0.11645101308822632,
|
|
"num_tokens": 3818989.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 7.1233776092529295,
|
|
"epoch": 0.1949317738791423,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998980426985596,
|
|
"loss": 6.9665,
|
|
"mean_token_accuracy": 0.11670495495200157,
|
|
"num_tokens": 3829319.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 7.134263134002685,
|
|
"epoch": 0.19543159894037088,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00049989696558486,
|
|
"loss": 6.9779,
|
|
"mean_token_accuracy": 0.11338206753134727,
|
|
"num_tokens": 3839545.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 7.1283763408660885,
|
|
"epoch": 0.19593142400159944,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998958828128108,
|
|
"loss": 6.9192,
|
|
"mean_token_accuracy": 0.11778575927019119,
|
|
"num_tokens": 3849029.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 7.100479316711426,
|
|
"epoch": 0.19643124906282802,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998947943824389,
|
|
"loss": 6.9572,
|
|
"mean_token_accuracy": 0.11571668013930321,
|
|
"num_tokens": 3859463.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 7.251784420013427,
|
|
"epoch": 0.19693107412405658,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998937002937719,
|
|
"loss": 6.9985,
|
|
"mean_token_accuracy": 0.11572480946779251,
|
|
"num_tokens": 3869695.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 7.1218890190124515,
|
|
"epoch": 0.19743089918528514,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004998926005468373,
|
|
"loss": 6.9564,
|
|
"mean_token_accuracy": 0.11750205978751183,
|
|
"num_tokens": 3879608.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 7.101331901550293,
|
|
"epoch": 0.19793072424651373,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998914951416627,
|
|
"loss": 6.8697,
|
|
"mean_token_accuracy": 0.11973301321268082,
|
|
"num_tokens": 3888709.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 7.0645873069763185,
|
|
"epoch": 0.1984305493077423,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000499890384078276,
|
|
"loss": 6.8144,
|
|
"mean_token_accuracy": 0.11889860406517982,
|
|
"num_tokens": 3898392.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 7.083717393875122,
|
|
"epoch": 0.19893037436897085,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004998892673567051,
|
|
"loss": 7.0328,
|
|
"mean_token_accuracy": 0.10867243111133576,
|
|
"num_tokens": 3909508.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 7.095362138748169,
|
|
"epoch": 0.19943019943019943,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004998881449769781,
|
|
"loss": 6.8772,
|
|
"mean_token_accuracy": 0.11684270799160004,
|
|
"num_tokens": 3918155.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 7.156151819229126,
|
|
"epoch": 0.199930024491428,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004998870169391232,
|
|
"loss": 6.91,
|
|
"mean_token_accuracy": 0.11658932641148567,
|
|
"num_tokens": 3928478.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 7.094034481048584,
|
|
"epoch": 0.20042984955265658,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000499885883243169,
|
|
"loss": 6.9807,
|
|
"mean_token_accuracy": 0.12299856469035149,
|
|
"num_tokens": 3938126.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 7.0389543056488035,
|
|
"epoch": 0.20092967461388514,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998847438891437,
|
|
"loss": 6.7931,
|
|
"mean_token_accuracy": 0.12135762944817544,
|
|
"num_tokens": 3948176.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 7.130215978622436,
|
|
"epoch": 0.2014294996751137,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004998835988770761,
|
|
"loss": 6.9243,
|
|
"mean_token_accuracy": 0.11784106865525246,
|
|
"num_tokens": 3958983.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 7.148845577239991,
|
|
"epoch": 0.20192932473634229,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000499882448206995,
|
|
"loss": 6.8748,
|
|
"mean_token_accuracy": 0.12108960896730422,
|
|
"num_tokens": 3968766.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 7.093853235244751,
|
|
"epoch": 0.20242914979757085,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998812918789293,
|
|
"loss": 6.8862,
|
|
"mean_token_accuracy": 0.12036861553788185,
|
|
"num_tokens": 3979487.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 7.037854337692261,
|
|
"epoch": 0.20292897485879943,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004998801298929084,
|
|
"loss": 6.8591,
|
|
"mean_token_accuracy": 0.11948419883847236,
|
|
"num_tokens": 3988450.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 7.083759737014771,
|
|
"epoch": 0.203428799920028,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998789622489611,
|
|
"loss": 6.8639,
|
|
"mean_token_accuracy": 0.1209349848330021,
|
|
"num_tokens": 3997492.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 7.120600318908691,
|
|
"epoch": 0.20392862498125655,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998777889471171,
|
|
"loss": 6.8659,
|
|
"mean_token_accuracy": 0.12269705757498742,
|
|
"num_tokens": 4007298.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 7.064807891845703,
|
|
"epoch": 0.20442845004248514,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998766099874056,
|
|
"loss": 6.8977,
|
|
"mean_token_accuracy": 0.11901947408914566,
|
|
"num_tokens": 4017727.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 7.092329645156861,
|
|
"epoch": 0.2049282751037137,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998754253698566,
|
|
"loss": 6.9052,
|
|
"mean_token_accuracy": 0.1160533107817173,
|
|
"num_tokens": 4027618.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 7.058936882019043,
|
|
"epoch": 0.20542810016494226,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004998742350944998,
|
|
"loss": 6.9305,
|
|
"mean_token_accuracy": 0.11532141789793968,
|
|
"num_tokens": 4038831.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 7.055427837371826,
|
|
"epoch": 0.20592792522617084,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004998730391613651,
|
|
"loss": 6.8681,
|
|
"mean_token_accuracy": 0.12060280740261078,
|
|
"num_tokens": 4048736.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 7.093530511856079,
|
|
"epoch": 0.2064277502873994,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998718375704825,
|
|
"loss": 6.805,
|
|
"mean_token_accuracy": 0.12220611199736595,
|
|
"num_tokens": 4057633.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 7.054113101959229,
|
|
"epoch": 0.206927575348628,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998706303218825,
|
|
"loss": 6.9191,
|
|
"mean_token_accuracy": 0.12357110977172851,
|
|
"num_tokens": 4067883.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 7.159766292572021,
|
|
"epoch": 0.20742740040985655,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998694174155952,
|
|
"loss": 6.7905,
|
|
"mean_token_accuracy": 0.1274022191762924,
|
|
"num_tokens": 4078147.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 7.028505516052246,
|
|
"epoch": 0.2079272254710851,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998681988516512,
|
|
"loss": 6.7782,
|
|
"mean_token_accuracy": 0.12301289215683937,
|
|
"num_tokens": 4087130.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 6.935732984542847,
|
|
"epoch": 0.2084270505323137,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998669746300811,
|
|
"loss": 6.903,
|
|
"mean_token_accuracy": 0.124887103587389,
|
|
"num_tokens": 4096840.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 7.1919714450836185,
|
|
"epoch": 0.20892687559354226,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998657447509159,
|
|
"loss": 6.8965,
|
|
"mean_token_accuracy": 0.11713318973779678,
|
|
"num_tokens": 4105842.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 6.997682905197143,
|
|
"epoch": 0.20942670065477084,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004998645092141864,
|
|
"loss": 6.8033,
|
|
"mean_token_accuracy": 0.12010766267776489,
|
|
"num_tokens": 4114865.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 7.080593633651733,
|
|
"epoch": 0.2099265257159994,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998632680199238,
|
|
"loss": 6.9373,
|
|
"mean_token_accuracy": 0.11356281042098999,
|
|
"num_tokens": 4124954.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 7.025081729888916,
|
|
"epoch": 0.21042635077722796,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004998620211681591,
|
|
"loss": 6.8203,
|
|
"mean_token_accuracy": 0.12838008180260657,
|
|
"num_tokens": 4134091.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 7.1411622047424315,
|
|
"epoch": 0.21092617583845655,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998607686589239,
|
|
"loss": 6.8802,
|
|
"mean_token_accuracy": 0.11798109486699104,
|
|
"num_tokens": 4143566.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 7.026936674118042,
|
|
"epoch": 0.2114260008996851,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004998595104922496,
|
|
"loss": 6.8579,
|
|
"mean_token_accuracy": 0.11757076904177666,
|
|
"num_tokens": 4153053.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 7.064190101623535,
|
|
"epoch": 0.2119258259609137,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004998582466681678,
|
|
"loss": 6.8287,
|
|
"mean_token_accuracy": 0.12464014589786529,
|
|
"num_tokens": 4162925.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 6.9577514171600345,
|
|
"epoch": 0.21242565102214225,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998569771867105,
|
|
"loss": 6.759,
|
|
"mean_token_accuracy": 0.1262947879731655,
|
|
"num_tokens": 4172077.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 6.999064683914185,
|
|
"epoch": 0.2129254760833708,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998557020479095,
|
|
"loss": 6.8494,
|
|
"mean_token_accuracy": 0.12305980324745178,
|
|
"num_tokens": 4182134.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 7.176851749420166,
|
|
"epoch": 0.2134253011445994,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004998544212517968,
|
|
"loss": 6.8664,
|
|
"mean_token_accuracy": 0.11641905829310417,
|
|
"num_tokens": 4191963.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 6.967975282669068,
|
|
"epoch": 0.21392512620582796,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998531347984047,
|
|
"loss": 6.8121,
|
|
"mean_token_accuracy": 0.12236538529396057,
|
|
"num_tokens": 4202180.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 7.056608772277832,
|
|
"epoch": 0.21442495126705652,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998518426877656,
|
|
"loss": 6.8498,
|
|
"mean_token_accuracy": 0.12232566028833389,
|
|
"num_tokens": 4211874.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 7.057928800582886,
|
|
"epoch": 0.2149247763282851,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998505449199122,
|
|
"loss": 6.7936,
|
|
"mean_token_accuracy": 0.1208051361143589,
|
|
"num_tokens": 4221610.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 6.943663740158081,
|
|
"epoch": 0.21542460138951366,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004998492414948768,
|
|
"loss": 6.748,
|
|
"mean_token_accuracy": 0.133094572275877,
|
|
"num_tokens": 4230610.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 6.993412733078003,
|
|
"epoch": 0.21592442645074225,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004998479324126924,
|
|
"loss": 6.8782,
|
|
"mean_token_accuracy": 0.11309932991862297,
|
|
"num_tokens": 4241389.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 7.034138774871826,
|
|
"epoch": 0.2164242515119708,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998466176733918,
|
|
"loss": 6.8262,
|
|
"mean_token_accuracy": 0.12450739443302154,
|
|
"num_tokens": 4250617.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 6.97466025352478,
|
|
"epoch": 0.21692407657319937,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998452972770082,
|
|
"loss": 6.7973,
|
|
"mean_token_accuracy": 0.12435769960284233,
|
|
"num_tokens": 4260000.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 6.991814851760864,
|
|
"epoch": 0.21742390163442796,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998439712235747,
|
|
"loss": 6.7444,
|
|
"mean_token_accuracy": 0.12331395819783211,
|
|
"num_tokens": 4269751.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 7.0533545970916744,
|
|
"epoch": 0.21792372669565652,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998426395131248,
|
|
"loss": 6.7905,
|
|
"mean_token_accuracy": 0.12443327084183693,
|
|
"num_tokens": 4279210.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 6.989436435699463,
|
|
"epoch": 0.2184235517568851,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998413021456919,
|
|
"loss": 6.7657,
|
|
"mean_token_accuracy": 0.12329083904623986,
|
|
"num_tokens": 4288573.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 7.008385276794433,
|
|
"epoch": 0.21892337681811366,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998399591213098,
|
|
"loss": 6.7964,
|
|
"mean_token_accuracy": 0.12139227017760276,
|
|
"num_tokens": 4298438.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 6.953334188461303,
|
|
"epoch": 0.21942320187934222,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998386104400122,
|
|
"loss": 6.7268,
|
|
"mean_token_accuracy": 0.13097667396068574,
|
|
"num_tokens": 4307174.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 7.032305383682251,
|
|
"epoch": 0.2199230269405708,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004998372561018329,
|
|
"loss": 6.8946,
|
|
"mean_token_accuracy": 0.11677326709032058,
|
|
"num_tokens": 4317220.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 7.0936168193817135,
|
|
"epoch": 0.22042285200179937,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998358961068062,
|
|
"loss": 6.7989,
|
|
"mean_token_accuracy": 0.12612595781683922,
|
|
"num_tokens": 4326496.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 7.025656223297119,
|
|
"epoch": 0.22092267706302793,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998345304549661,
|
|
"loss": 6.8081,
|
|
"mean_token_accuracy": 0.12592438012361526,
|
|
"num_tokens": 4335705.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 7.022608041763306,
|
|
"epoch": 0.22142250212425652,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998331591463471,
|
|
"loss": 6.8211,
|
|
"mean_token_accuracy": 0.12835633084177972,
|
|
"num_tokens": 4344711.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 7.006923866271973,
|
|
"epoch": 0.22192232718548507,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998317821809837,
|
|
"loss": 6.8391,
|
|
"mean_token_accuracy": 0.1216700553894043,
|
|
"num_tokens": 4355448.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 6.954414653778076,
|
|
"epoch": 0.22242215224671366,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998303995589104,
|
|
"loss": 6.7257,
|
|
"mean_token_accuracy": 0.12261889353394509,
|
|
"num_tokens": 4365104.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 6.914372348785401,
|
|
"epoch": 0.22292197730794222,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004998290112801623,
|
|
"loss": 6.6823,
|
|
"mean_token_accuracy": 0.1286713495850563,
|
|
"num_tokens": 4375219.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 7.024904727935791,
|
|
"epoch": 0.22342180236917078,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499827617344774,
|
|
"loss": 6.8458,
|
|
"mean_token_accuracy": 0.11705941632390023,
|
|
"num_tokens": 4385294.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 7.090032148361206,
|
|
"epoch": 0.22392162743039937,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004998262177527807,
|
|
"loss": 6.7875,
|
|
"mean_token_accuracy": 0.11647440493106842,
|
|
"num_tokens": 4394305.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 6.9880218505859375,
|
|
"epoch": 0.22442145249162793,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998248125042177,
|
|
"loss": 6.6909,
|
|
"mean_token_accuracy": 0.12566715776920317,
|
|
"num_tokens": 4403732.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 6.976096105575562,
|
|
"epoch": 0.2249212775528565,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004998234015991202,
|
|
"loss": 6.8776,
|
|
"mean_token_accuracy": 0.11910765767097473,
|
|
"num_tokens": 4413730.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 7.104625558853149,
|
|
"epoch": 0.22542110261408507,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998219850375238,
|
|
"loss": 6.8875,
|
|
"mean_token_accuracy": 0.11642134636640548,
|
|
"num_tokens": 4423051.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 7.09229040145874,
|
|
"epoch": 0.22592092767531363,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004998205628194641,
|
|
"loss": 6.8914,
|
|
"mean_token_accuracy": 0.12018313780426979,
|
|
"num_tokens": 4433363.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 7.084233140945434,
|
|
"epoch": 0.22642075273654222,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004998191349449768,
|
|
"loss": 6.8453,
|
|
"mean_token_accuracy": 0.11719286441802979,
|
|
"num_tokens": 4442984.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 6.962313604354859,
|
|
"epoch": 0.22692057779777078,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998177014140981,
|
|
"loss": 6.7755,
|
|
"mean_token_accuracy": 0.11933308243751525,
|
|
"num_tokens": 4452364.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 7.018482780456543,
|
|
"epoch": 0.22742040285899934,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998162622268637,
|
|
"loss": 6.8136,
|
|
"mean_token_accuracy": 0.11589978188276291,
|
|
"num_tokens": 4461904.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 7.027294683456421,
|
|
"epoch": 0.22792022792022792,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998148173833101,
|
|
"loss": 6.7632,
|
|
"mean_token_accuracy": 0.12299803197383881,
|
|
"num_tokens": 4470633.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 6.9562835693359375,
|
|
"epoch": 0.22842005298145648,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998133668834735,
|
|
"loss": 6.7806,
|
|
"mean_token_accuracy": 0.12278707697987556,
|
|
"num_tokens": 4480673.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 7.003961133956909,
|
|
"epoch": 0.22891987804268507,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004998119107273905,
|
|
"loss": 6.7636,
|
|
"mean_token_accuracy": 0.11756833791732788,
|
|
"num_tokens": 4489923.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 6.959622764587403,
|
|
"epoch": 0.22941970310391363,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004998104489150975,
|
|
"loss": 6.7422,
|
|
"mean_token_accuracy": 0.12293882742524147,
|
|
"num_tokens": 4501007.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 6.924298858642578,
|
|
"epoch": 0.2299195281651422,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998089814466318,
|
|
"loss": 6.757,
|
|
"mean_token_accuracy": 0.12394008114933967,
|
|
"num_tokens": 4510460.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 7.008149099349976,
|
|
"epoch": 0.23041935322637078,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004998075083220295,
|
|
"loss": 6.8235,
|
|
"mean_token_accuracy": 0.12430360317230224,
|
|
"num_tokens": 4521026.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 6.980177974700927,
|
|
"epoch": 0.23091917828759934,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998060295413286,
|
|
"loss": 6.7636,
|
|
"mean_token_accuracy": 0.12551465407013893,
|
|
"num_tokens": 4530818.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 6.8737717628479,
|
|
"epoch": 0.23141900334882792,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998045451045656,
|
|
"loss": 6.6986,
|
|
"mean_token_accuracy": 0.12920840978622436,
|
|
"num_tokens": 4539512.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 7.047420930862427,
|
|
"epoch": 0.23191882841005648,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998030550117782,
|
|
"loss": 6.8763,
|
|
"mean_token_accuracy": 0.1164549469947815,
|
|
"num_tokens": 4549030.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 6.9811506271362305,
|
|
"epoch": 0.23241865347128504,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004998015592630037,
|
|
"loss": 6.7185,
|
|
"mean_token_accuracy": 0.12747346982359886,
|
|
"num_tokens": 4559347.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 6.960136795043946,
|
|
"epoch": 0.23291847853251363,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004998000578582798,
|
|
"loss": 6.7664,
|
|
"mean_token_accuracy": 0.11763800606131554,
|
|
"num_tokens": 4568721.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 7.016366481781006,
|
|
"epoch": 0.2334183035937422,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997985507976443,
|
|
"loss": 6.7841,
|
|
"mean_token_accuracy": 0.12403129637241364,
|
|
"num_tokens": 4578265.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 6.948030614852906,
|
|
"epoch": 0.23391812865497075,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997970380811351,
|
|
"loss": 6.7471,
|
|
"mean_token_accuracy": 0.1287473239004612,
|
|
"num_tokens": 4588694.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 6.98386058807373,
|
|
"epoch": 0.23441795371619933,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997955197087904,
|
|
"loss": 6.7427,
|
|
"mean_token_accuracy": 0.12793392390012742,
|
|
"num_tokens": 4597754.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 6.998698759078979,
|
|
"epoch": 0.2349177787774279,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997939956806481,
|
|
"loss": 6.7509,
|
|
"mean_token_accuracy": 0.12661289870738984,
|
|
"num_tokens": 4606874.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 6.916998815536499,
|
|
"epoch": 0.23541760383865648,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997924659967467,
|
|
"loss": 6.6337,
|
|
"mean_token_accuracy": 0.1290208764374256,
|
|
"num_tokens": 4615588.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 6.882282018661499,
|
|
"epoch": 0.23591742889988504,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004997909306571248,
|
|
"loss": 6.8043,
|
|
"mean_token_accuracy": 0.12569234296679496,
|
|
"num_tokens": 4625919.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 6.9637391567230225,
|
|
"epoch": 0.2364172539611136,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004997893896618209,
|
|
"loss": 6.7433,
|
|
"mean_token_accuracy": 0.12109558060765266,
|
|
"num_tokens": 4635539.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 6.9393453121185305,
|
|
"epoch": 0.2369170790223422,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004997878430108738,
|
|
"loss": 6.7328,
|
|
"mean_token_accuracy": 0.1250187486410141,
|
|
"num_tokens": 4645833.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 6.908280897140503,
|
|
"epoch": 0.23741690408357075,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004997862907043224,
|
|
"loss": 6.8564,
|
|
"mean_token_accuracy": 0.12477396801114082,
|
|
"num_tokens": 4655166.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 7.021889305114746,
|
|
"epoch": 0.23791672914479933,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004997847327422059,
|
|
"loss": 6.7268,
|
|
"mean_token_accuracy": 0.12371973022818565,
|
|
"num_tokens": 4664884.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 6.913659334182739,
|
|
"epoch": 0.2384165542060279,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997831691245632,
|
|
"loss": 6.821,
|
|
"mean_token_accuracy": 0.12349852249026298,
|
|
"num_tokens": 4675172.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 7.036015272140503,
|
|
"epoch": 0.23891637926725645,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997815998514337,
|
|
"loss": 6.7131,
|
|
"mean_token_accuracy": 0.12983411476016044,
|
|
"num_tokens": 4684588.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 6.936409759521484,
|
|
"epoch": 0.23941620432848504,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004997800249228572,
|
|
"loss": 6.8333,
|
|
"mean_token_accuracy": 0.12305981665849686,
|
|
"num_tokens": 4694434.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 6.906350755691529,
|
|
"epoch": 0.2399160293897136,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004997784443388732,
|
|
"loss": 6.77,
|
|
"mean_token_accuracy": 0.12484433725476266,
|
|
"num_tokens": 4705080.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 7.01893367767334,
|
|
"epoch": 0.24041585445094216,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004997768580995212,
|
|
"loss": 6.8441,
|
|
"mean_token_accuracy": 0.11970154121518135,
|
|
"num_tokens": 4714466.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 6.934593868255615,
|
|
"epoch": 0.24091567951217074,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004997752662048413,
|
|
"loss": 6.7455,
|
|
"mean_token_accuracy": 0.12879132330417634,
|
|
"num_tokens": 4724047.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 6.970644330978393,
|
|
"epoch": 0.2414155045733993,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997736686548736,
|
|
"loss": 6.7948,
|
|
"mean_token_accuracy": 0.12079165503382683,
|
|
"num_tokens": 4733153.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 6.966701793670654,
|
|
"epoch": 0.2419153296346279,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004997720654496582,
|
|
"loss": 6.6605,
|
|
"mean_token_accuracy": 0.12834780439734458,
|
|
"num_tokens": 4743239.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 6.895601415634156,
|
|
"epoch": 0.24241515469585645,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004997704565892355,
|
|
"loss": 6.7198,
|
|
"mean_token_accuracy": 0.12349500507116318,
|
|
"num_tokens": 4753128.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 7.051494407653808,
|
|
"epoch": 0.242914979757085,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004997688420736459,
|
|
"loss": 6.9319,
|
|
"mean_token_accuracy": 0.11143164709210396,
|
|
"num_tokens": 4764056.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 6.981206607818604,
|
|
"epoch": 0.2434148048183136,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997672219029301,
|
|
"loss": 6.7644,
|
|
"mean_token_accuracy": 0.12327315658330917,
|
|
"num_tokens": 4773354.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 6.906646108627319,
|
|
"epoch": 0.24391462987954216,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004997655960771288,
|
|
"loss": 6.7012,
|
|
"mean_token_accuracy": 0.12343468591570854,
|
|
"num_tokens": 4783367.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 6.925524520874023,
|
|
"epoch": 0.24441445494077074,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.000499763964596283,
|
|
"loss": 6.5979,
|
|
"mean_token_accuracy": 0.13321683332324027,
|
|
"num_tokens": 4793028.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 6.9859123706817625,
|
|
"epoch": 0.2449142800019993,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004997623274604336,
|
|
"loss": 6.7693,
|
|
"mean_token_accuracy": 0.12341286316514015,
|
|
"num_tokens": 4804032.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 6.952797555923462,
|
|
"epoch": 0.24541410506322786,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000499760684669622,
|
|
"loss": 6.8046,
|
|
"mean_token_accuracy": 0.12445300966501235,
|
|
"num_tokens": 4813294.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 6.929312753677368,
|
|
"epoch": 0.24591393012445645,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004997590362238894,
|
|
"loss": 6.72,
|
|
"mean_token_accuracy": 0.12648141980171204,
|
|
"num_tokens": 4823461.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 6.869597625732422,
|
|
"epoch": 0.246413755185685,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004997573821232772,
|
|
"loss": 6.7532,
|
|
"mean_token_accuracy": 0.12967433482408525,
|
|
"num_tokens": 4832464.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 6.955246114730835,
|
|
"epoch": 0.24691358024691357,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004997557223678272,
|
|
"loss": 6.7354,
|
|
"mean_token_accuracy": 0.12091749757528306,
|
|
"num_tokens": 4842697.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 6.9567407131195065,
|
|
"epoch": 0.24741340530814215,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004997540569575809,
|
|
"loss": 6.7918,
|
|
"mean_token_accuracy": 0.1257416233420372,
|
|
"num_tokens": 4853129.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 6.962767553329468,
|
|
"epoch": 0.2479132303693707,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004997523858925805,
|
|
"loss": 6.8053,
|
|
"mean_token_accuracy": 0.11744737774133682,
|
|
"num_tokens": 4864048.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 6.851801061630249,
|
|
"epoch": 0.2484130554305993,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004997507091728678,
|
|
"loss": 6.7685,
|
|
"mean_token_accuracy": 0.12485729232430458,
|
|
"num_tokens": 4874368.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 7.036509084701538,
|
|
"epoch": 0.24891288049182786,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004997490267984853,
|
|
"loss": 6.7286,
|
|
"mean_token_accuracy": 0.12454072982072831,
|
|
"num_tokens": 4884813.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 6.88193793296814,
|
|
"epoch": 0.24941270555305642,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004997473387694749,
|
|
"loss": 6.8044,
|
|
"mean_token_accuracy": 0.1220268465578556,
|
|
"num_tokens": 4895594.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 6.93081693649292,
|
|
"epoch": 0.249912530614285,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004997456450858793,
|
|
"loss": 6.7087,
|
|
"mean_token_accuracy": 0.12661490142345427,
|
|
"num_tokens": 4904922.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 6.91534686088562,
|
|
"epoch": 0.25041235567551356,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004997439457477412,
|
|
"loss": 6.6958,
|
|
"mean_token_accuracy": 0.12675042897462846,
|
|
"num_tokens": 4915009.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 6.967141246795654,
|
|
"epoch": 0.25091218073674215,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997422407551032,
|
|
"loss": 6.8361,
|
|
"mean_token_accuracy": 0.11825927272439003,
|
|
"num_tokens": 4924916.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 6.931365871429444,
|
|
"epoch": 0.2514120057979707,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004997405301080082,
|
|
"loss": 6.7417,
|
|
"mean_token_accuracy": 0.12296365350484847,
|
|
"num_tokens": 4935127.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 6.934671115875244,
|
|
"epoch": 0.25191183085919927,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997388138064994,
|
|
"loss": 6.7531,
|
|
"mean_token_accuracy": 0.12879148945212365,
|
|
"num_tokens": 4944749.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 6.895633125305176,
|
|
"epoch": 0.25241165592042786,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997370918506198,
|
|
"loss": 6.5853,
|
|
"mean_token_accuracy": 0.13921203166246415,
|
|
"num_tokens": 4953868.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 6.875580501556397,
|
|
"epoch": 0.25291148098165644,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004997353642404129,
|
|
"loss": 6.7073,
|
|
"mean_token_accuracy": 0.12661241069436074,
|
|
"num_tokens": 4963282.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 6.783172845840454,
|
|
"epoch": 0.253411306042885,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004997336309759219,
|
|
"loss": 6.546,
|
|
"mean_token_accuracy": 0.13192983344197273,
|
|
"num_tokens": 4973099.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 6.893124055862427,
|
|
"epoch": 0.25391113110411356,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997318920571907,
|
|
"loss": 6.729,
|
|
"mean_token_accuracy": 0.12053842768073082,
|
|
"num_tokens": 4983771.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 6.787672758102417,
|
|
"epoch": 0.25441095616534215,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499730147484263,
|
|
"loss": 6.634,
|
|
"mean_token_accuracy": 0.1280955545604229,
|
|
"num_tokens": 4993648.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 6.879558324813843,
|
|
"epoch": 0.2549107812265707,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004997283972571824,
|
|
"loss": 6.7273,
|
|
"mean_token_accuracy": 0.12890966087579728,
|
|
"num_tokens": 5002821.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 6.9560950756072994,
|
|
"epoch": 0.25541060628779927,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004997266413759934,
|
|
"loss": 6.7505,
|
|
"mean_token_accuracy": 0.12259442135691642,
|
|
"num_tokens": 5012655.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 6.8323667526245115,
|
|
"epoch": 0.25591043134902786,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004997248798407397,
|
|
"loss": 6.7075,
|
|
"mean_token_accuracy": 0.1233678974211216,
|
|
"num_tokens": 5023649.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 6.922650480270386,
|
|
"epoch": 0.2564102564102564,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997231126514659,
|
|
"loss": 6.6567,
|
|
"mean_token_accuracy": 0.12875650003552436,
|
|
"num_tokens": 5031945.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 6.931125116348267,
|
|
"epoch": 0.256910081471485,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004997213398082165,
|
|
"loss": 6.7269,
|
|
"mean_token_accuracy": 0.12369013354182243,
|
|
"num_tokens": 5042036.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 6.919758987426758,
|
|
"epoch": 0.25740990653271356,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000499719561311036,
|
|
"loss": 6.7212,
|
|
"mean_token_accuracy": 0.1250573143362999,
|
|
"num_tokens": 5050986.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 6.9465330123901365,
|
|
"epoch": 0.2579097315939421,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004997177771599691,
|
|
"loss": 6.7021,
|
|
"mean_token_accuracy": 0.1267305240035057,
|
|
"num_tokens": 5061408.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 6.826210260391235,
|
|
"epoch": 0.2584095566551707,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004997159873550607,
|
|
"loss": 6.6251,
|
|
"mean_token_accuracy": 0.12948956787586213,
|
|
"num_tokens": 5071646.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 6.825673580169678,
|
|
"epoch": 0.25890938171639927,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004997141918963561,
|
|
"loss": 6.7227,
|
|
"mean_token_accuracy": 0.12857370674610138,
|
|
"num_tokens": 5083185.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 6.901279354095459,
|
|
"epoch": 0.25940920677762785,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997123907839001,
|
|
"loss": 6.6898,
|
|
"mean_token_accuracy": 0.12528114542365074,
|
|
"num_tokens": 5092993.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 6.949271011352539,
|
|
"epoch": 0.2599090318388564,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997105840177381,
|
|
"loss": 6.7435,
|
|
"mean_token_accuracy": 0.12175171375274658,
|
|
"num_tokens": 5102709.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 6.911493444442749,
|
|
"epoch": 0.260408856900085,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997087715979157,
|
|
"loss": 6.6904,
|
|
"mean_token_accuracy": 0.12231686487793922,
|
|
"num_tokens": 5112858.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 6.915732145309448,
|
|
"epoch": 0.26090868196131356,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997069535244785,
|
|
"loss": 6.6057,
|
|
"mean_token_accuracy": 0.13236649036407472,
|
|
"num_tokens": 5123573.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 6.77972183227539,
|
|
"epoch": 0.2614085070225421,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004997051297974722,
|
|
"loss": 6.7799,
|
|
"mean_token_accuracy": 0.11823756992816925,
|
|
"num_tokens": 5132908.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 6.903223943710327,
|
|
"epoch": 0.2619083320837707,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004997033004169425,
|
|
"loss": 6.6634,
|
|
"mean_token_accuracy": 0.13124899789690972,
|
|
"num_tokens": 5142331.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 6.986439514160156,
|
|
"epoch": 0.26240815714499927,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004997014653829357,
|
|
"loss": 6.7434,
|
|
"mean_token_accuracy": 0.1203452467918396,
|
|
"num_tokens": 5152517.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 6.8694833278656,
|
|
"epoch": 0.2629079822062278,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004996996246954977,
|
|
"loss": 6.6749,
|
|
"mean_token_accuracy": 0.129129771143198,
|
|
"num_tokens": 5162418.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 6.847884941101074,
|
|
"epoch": 0.2634078072674564,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996977783546752,
|
|
"loss": 6.7101,
|
|
"mean_token_accuracy": 0.12350467145442963,
|
|
"num_tokens": 5171948.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 6.947595262527466,
|
|
"epoch": 0.26390763232868497,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996959263605143,
|
|
"loss": 6.626,
|
|
"mean_token_accuracy": 0.1277811646461487,
|
|
"num_tokens": 5180963.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 6.835096788406372,
|
|
"epoch": 0.2644074573899135,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004996940687130617,
|
|
"loss": 6.743,
|
|
"mean_token_accuracy": 0.12740767300128936,
|
|
"num_tokens": 5192305.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 6.8839599132537845,
|
|
"epoch": 0.2649072824511421,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004996922054123641,
|
|
"loss": 6.6193,
|
|
"mean_token_accuracy": 0.12462258934974671,
|
|
"num_tokens": 5201503.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 6.921473693847656,
|
|
"epoch": 0.2654071075123707,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004996903364584685,
|
|
"loss": 6.6076,
|
|
"mean_token_accuracy": 0.12627073228359223,
|
|
"num_tokens": 5210206.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 6.762358474731445,
|
|
"epoch": 0.26590693257359926,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004996884618514219,
|
|
"loss": 6.6135,
|
|
"mean_token_accuracy": 0.1311767116189003,
|
|
"num_tokens": 5220256.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 6.803161573410034,
|
|
"epoch": 0.2664067576348278,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996865815912713,
|
|
"loss": 6.637,
|
|
"mean_token_accuracy": 0.1329315148293972,
|
|
"num_tokens": 5229128.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 6.895367097854614,
|
|
"epoch": 0.2669065826960564,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004996846956780642,
|
|
"loss": 6.5866,
|
|
"mean_token_accuracy": 0.12857141569256783,
|
|
"num_tokens": 5239468.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 6.834448194503784,
|
|
"epoch": 0.26740640775728497,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000499682804111848,
|
|
"loss": 6.6913,
|
|
"mean_token_accuracy": 0.12485808730125428,
|
|
"num_tokens": 5247957.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 6.868956804275513,
|
|
"epoch": 0.2679062328185135,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004996809068926702,
|
|
"loss": 6.6983,
|
|
"mean_token_accuracy": 0.1235993355512619,
|
|
"num_tokens": 5257960.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 6.826748180389404,
|
|
"epoch": 0.2684060578797421,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004996790040205786,
|
|
"loss": 6.5729,
|
|
"mean_token_accuracy": 0.1311322994530201,
|
|
"num_tokens": 5266696.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 6.84700608253479,
|
|
"epoch": 0.2689058829409707,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996770954956211,
|
|
"loss": 6.542,
|
|
"mean_token_accuracy": 0.1364964410662651,
|
|
"num_tokens": 5275619.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 6.814588451385498,
|
|
"epoch": 0.2694057080021992,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004996751813178456,
|
|
"loss": 6.6823,
|
|
"mean_token_accuracy": 0.12757562324404717,
|
|
"num_tokens": 5284884.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 6.885785722732544,
|
|
"epoch": 0.2699055330634278,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004996732614873005,
|
|
"loss": 6.5761,
|
|
"mean_token_accuracy": 0.13537995815277098,
|
|
"num_tokens": 5293909.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 6.8018866062164305,
|
|
"epoch": 0.2704053581246564,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004996713360040339,
|
|
"loss": 6.6667,
|
|
"mean_token_accuracy": 0.12470442354679108,
|
|
"num_tokens": 5303142.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 6.832062864303589,
|
|
"epoch": 0.27090518318588497,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996694048680942,
|
|
"loss": 6.6007,
|
|
"mean_token_accuracy": 0.1250078909099102,
|
|
"num_tokens": 5313055.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 6.856688165664673,
|
|
"epoch": 0.2714050082471135,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004996674680795302,
|
|
"loss": 6.7171,
|
|
"mean_token_accuracy": 0.11953588724136352,
|
|
"num_tokens": 5323773.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 6.701740312576294,
|
|
"epoch": 0.2719048333083421,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004996655256383905,
|
|
"loss": 6.5089,
|
|
"mean_token_accuracy": 0.1433877095580101,
|
|
"num_tokens": 5334613.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 6.785739469528198,
|
|
"epoch": 0.2724046583695707,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000499663577544724,
|
|
"loss": 6.5988,
|
|
"mean_token_accuracy": 0.1337459959089756,
|
|
"num_tokens": 5344151.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 6.790981101989746,
|
|
"epoch": 0.2729044834307992,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996616237985796,
|
|
"loss": 6.5667,
|
|
"mean_token_accuracy": 0.1349438451230526,
|
|
"num_tokens": 5352425.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 6.783331489562988,
|
|
"epoch": 0.2734043084920278,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004996596644000066,
|
|
"loss": 6.7637,
|
|
"mean_token_accuracy": 0.12367659956216812,
|
|
"num_tokens": 5361811.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 6.8914836883544925,
|
|
"epoch": 0.2739041335532564,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004996576993490543,
|
|
"loss": 6.6965,
|
|
"mean_token_accuracy": 0.12055673524737358,
|
|
"num_tokens": 5371463.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 6.8567499160766605,
|
|
"epoch": 0.2744039586144849,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004996557286457721,
|
|
"loss": 6.5675,
|
|
"mean_token_accuracy": 0.13478375598788261,
|
|
"num_tokens": 5381464.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 6.737442064285278,
|
|
"epoch": 0.2749037836757135,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996537522902096,
|
|
"loss": 6.643,
|
|
"mean_token_accuracy": 0.12358913272619247,
|
|
"num_tokens": 5391012.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 6.900225830078125,
|
|
"epoch": 0.2754036087369421,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004996517702824163,
|
|
"loss": 6.7441,
|
|
"mean_token_accuracy": 0.1277411937713623,
|
|
"num_tokens": 5401198.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 6.965499496459961,
|
|
"epoch": 0.2759034337981706,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004996497826224425,
|
|
"loss": 6.6872,
|
|
"mean_token_accuracy": 0.1266508638858795,
|
|
"num_tokens": 5410592.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 6.733990907669067,
|
|
"epoch": 0.2764032588593992,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004996477893103379,
|
|
"loss": 6.6455,
|
|
"mean_token_accuracy": 0.13018811568617822,
|
|
"num_tokens": 5420878.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 6.837689924240112,
|
|
"epoch": 0.2769030839206278,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004996457903461527,
|
|
"loss": 6.6557,
|
|
"mean_token_accuracy": 0.12990267798304558,
|
|
"num_tokens": 5431199.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 6.825644302368164,
|
|
"epoch": 0.2774029089818564,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004996437857299373,
|
|
"loss": 6.5869,
|
|
"mean_token_accuracy": 0.13335442095994948,
|
|
"num_tokens": 5441661.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 6.765251636505127,
|
|
"epoch": 0.2779027340430849,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000499641775461742,
|
|
"loss": 6.5892,
|
|
"mean_token_accuracy": 0.13393662124872208,
|
|
"num_tokens": 5451863.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 6.830867719650269,
|
|
"epoch": 0.2784025591043135,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004996397595416173,
|
|
"loss": 6.6382,
|
|
"mean_token_accuracy": 0.13025332391262054,
|
|
"num_tokens": 5461600.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 6.891679525375366,
|
|
"epoch": 0.2789023841655421,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004996377379696143,
|
|
"loss": 6.6689,
|
|
"mean_token_accuracy": 0.1225666806101799,
|
|
"num_tokens": 5470097.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 6.880445766448974,
|
|
"epoch": 0.2794022092267706,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004996357107457834,
|
|
"loss": 6.7974,
|
|
"mean_token_accuracy": 0.1164699487388134,
|
|
"num_tokens": 5480906.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 6.941256761550903,
|
|
"epoch": 0.2799020342879992,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499633677870176,
|
|
"loss": 6.677,
|
|
"mean_token_accuracy": 0.12477467060089112,
|
|
"num_tokens": 5489732.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 6.70820631980896,
|
|
"epoch": 0.2804018593492278,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004996316393428429,
|
|
"loss": 6.5058,
|
|
"mean_token_accuracy": 0.13490227609872818,
|
|
"num_tokens": 5498422.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 6.741797018051147,
|
|
"epoch": 0.2809016844104563,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004996295951638357,
|
|
"loss": 6.6417,
|
|
"mean_token_accuracy": 0.12436849176883698,
|
|
"num_tokens": 5507958.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 6.871691799163818,
|
|
"epoch": 0.2814015094716849,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004996275453332057,
|
|
"loss": 6.6753,
|
|
"mean_token_accuracy": 0.12770553976297377,
|
|
"num_tokens": 5516752.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 6.804839038848877,
|
|
"epoch": 0.2819013345329135,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004996254898510043,
|
|
"loss": 6.68,
|
|
"mean_token_accuracy": 0.12850109338760377,
|
|
"num_tokens": 5527211.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 6.820689105987549,
|
|
"epoch": 0.282401159594142,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004996234287172835,
|
|
"loss": 6.5746,
|
|
"mean_token_accuracy": 0.12999471724033357,
|
|
"num_tokens": 5536925.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 6.883645534515381,
|
|
"epoch": 0.2829009846553706,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000499621361932095,
|
|
"loss": 6.7608,
|
|
"mean_token_accuracy": 0.12017307057976723,
|
|
"num_tokens": 5546800.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 6.764953994750977,
|
|
"epoch": 0.2834008097165992,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004996192894954909,
|
|
"loss": 6.6006,
|
|
"mean_token_accuracy": 0.12868443727493287,
|
|
"num_tokens": 5557266.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 6.817695951461792,
|
|
"epoch": 0.2839006347778278,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004996172114075232,
|
|
"loss": 6.5858,
|
|
"mean_token_accuracy": 0.13033762723207473,
|
|
"num_tokens": 5566169.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 6.8027301788330075,
|
|
"epoch": 0.2844004598390563,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004996151276682443,
|
|
"loss": 6.6751,
|
|
"mean_token_accuracy": 0.1305215150117874,
|
|
"num_tokens": 5575566.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 6.791625738143921,
|
|
"epoch": 0.2849002849002849,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004996130382777065,
|
|
"loss": 6.5596,
|
|
"mean_token_accuracy": 0.1286344051361084,
|
|
"num_tokens": 5584804.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 6.78387484550476,
|
|
"epoch": 0.2854001099615135,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004996109432359625,
|
|
"loss": 6.6093,
|
|
"mean_token_accuracy": 0.12663276568055154,
|
|
"num_tokens": 5594361.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 6.868547153472901,
|
|
"epoch": 0.285899935022742,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004996088425430651,
|
|
"loss": 6.619,
|
|
"mean_token_accuracy": 0.12699493318796157,
|
|
"num_tokens": 5605682.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 6.808011245727539,
|
|
"epoch": 0.2863997600839706,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004996067361990669,
|
|
"loss": 6.6979,
|
|
"mean_token_accuracy": 0.12324106916785241,
|
|
"num_tokens": 5617251.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 6.7848552703857425,
|
|
"epoch": 0.2868995851451992,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004996046242040209,
|
|
"loss": 6.5719,
|
|
"mean_token_accuracy": 0.13272615447640418,
|
|
"num_tokens": 5627140.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 6.77541823387146,
|
|
"epoch": 0.28739941020642773,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004996025065579805,
|
|
"loss": 6.5212,
|
|
"mean_token_accuracy": 0.13640954494476318,
|
|
"num_tokens": 5635486.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 6.838054370880127,
|
|
"epoch": 0.2878992352676563,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004996003832609988,
|
|
"loss": 6.6731,
|
|
"mean_token_accuracy": 0.1194192998111248,
|
|
"num_tokens": 5645621.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 6.928879976272583,
|
|
"epoch": 0.2883990603288849,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004995982543131292,
|
|
"loss": 6.7457,
|
|
"mean_token_accuracy": 0.12103333249688149,
|
|
"num_tokens": 5655626.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 6.829890489578247,
|
|
"epoch": 0.28889888539011344,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004995961197144254,
|
|
"loss": 6.6795,
|
|
"mean_token_accuracy": 0.12712434753775598,
|
|
"num_tokens": 5664547.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 6.834103298187256,
|
|
"epoch": 0.289398710451342,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000499593979464941,
|
|
"loss": 6.6403,
|
|
"mean_token_accuracy": 0.12402470111846924,
|
|
"num_tokens": 5674861.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 6.787194728851318,
|
|
"epoch": 0.2898985355125706,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004995918335647298,
|
|
"loss": 6.5982,
|
|
"mean_token_accuracy": 0.12460636496543884,
|
|
"num_tokens": 5684143.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 6.791854190826416,
|
|
"epoch": 0.2903983605737992,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004995896820138459,
|
|
"loss": 6.558,
|
|
"mean_token_accuracy": 0.12753776907920839,
|
|
"num_tokens": 5693837.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 6.880584764480591,
|
|
"epoch": 0.29089818563502773,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004995875248123434,
|
|
"loss": 6.655,
|
|
"mean_token_accuracy": 0.12204006910324097,
|
|
"num_tokens": 5704827.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 6.8240148544311525,
|
|
"epoch": 0.2913980106962563,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004995853619602766,
|
|
"loss": 6.694,
|
|
"mean_token_accuracy": 0.1257927805185318,
|
|
"num_tokens": 5714419.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 6.83175892829895,
|
|
"epoch": 0.2918978357574849,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004995831934576998,
|
|
"loss": 6.6069,
|
|
"mean_token_accuracy": 0.1266295939683914,
|
|
"num_tokens": 5724983.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 6.7419945240020756,
|
|
"epoch": 0.29239766081871343,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004995810193046677,
|
|
"loss": 6.5335,
|
|
"mean_token_accuracy": 0.1366861306130886,
|
|
"num_tokens": 5734471.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 6.81366982460022,
|
|
"epoch": 0.292897485879942,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000499578839501235,
|
|
"loss": 6.6862,
|
|
"mean_token_accuracy": 0.12929900363087654,
|
|
"num_tokens": 5744801.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 6.82947154045105,
|
|
"epoch": 0.2933973109411706,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004995766540474564,
|
|
"loss": 6.6191,
|
|
"mean_token_accuracy": 0.1266006588935852,
|
|
"num_tokens": 5754267.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 6.7092602252960205,
|
|
"epoch": 0.29389713600239914,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.000499574462943387,
|
|
"loss": 6.5378,
|
|
"mean_token_accuracy": 0.13515163734555244,
|
|
"num_tokens": 5764466.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 6.785275030136108,
|
|
"epoch": 0.2943969610636277,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000499572266189082,
|
|
"loss": 6.6676,
|
|
"mean_token_accuracy": 0.12391036003828049,
|
|
"num_tokens": 5775158.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 6.8545256614685055,
|
|
"epoch": 0.2948967861248563,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004995700637845964,
|
|
"loss": 6.4676,
|
|
"mean_token_accuracy": 0.13657867833971976,
|
|
"num_tokens": 5783320.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 6.7285840034484865,
|
|
"epoch": 0.29539661118608485,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004995678557299859,
|
|
"loss": 6.6247,
|
|
"mean_token_accuracy": 0.13014830350875856,
|
|
"num_tokens": 5792980.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 6.84141960144043,
|
|
"epoch": 0.29589643624731343,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004995656420253058,
|
|
"loss": 6.6712,
|
|
"mean_token_accuracy": 0.1261442005634308,
|
|
"num_tokens": 5802338.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 6.790224504470825,
|
|
"epoch": 0.296396261308542,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499563422670612,
|
|
"loss": 6.5638,
|
|
"mean_token_accuracy": 0.13231244459748268,
|
|
"num_tokens": 5811388.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 6.8048484325408936,
|
|
"epoch": 0.2968960863697706,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004995611976659604,
|
|
"loss": 6.6027,
|
|
"mean_token_accuracy": 0.12747790962457656,
|
|
"num_tokens": 5821108.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 6.801449108123779,
|
|
"epoch": 0.29739591143099914,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004995589670114067,
|
|
"loss": 6.6456,
|
|
"mean_token_accuracy": 0.1197404257953167,
|
|
"num_tokens": 5831389.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 6.763365077972412,
|
|
"epoch": 0.2978957364922277,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004995567307070072,
|
|
"loss": 6.5087,
|
|
"mean_token_accuracy": 0.13231854736804963,
|
|
"num_tokens": 5840392.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 6.758113431930542,
|
|
"epoch": 0.2983955615534563,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004995544887528182,
|
|
"loss": 6.5226,
|
|
"mean_token_accuracy": 0.13557453379034995,
|
|
"num_tokens": 5850032.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 6.788800477981567,
|
|
"epoch": 0.29889538661468484,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004995522411488959,
|
|
"loss": 6.5933,
|
|
"mean_token_accuracy": 0.13116523027420043,
|
|
"num_tokens": 5859204.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 6.742308712005615,
|
|
"epoch": 0.29939521167591343,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004995499878952971,
|
|
"loss": 6.5951,
|
|
"mean_token_accuracy": 0.13226681798696518,
|
|
"num_tokens": 5868582.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 6.788286781311035,
|
|
"epoch": 0.299895036737142,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004995477289920784,
|
|
"loss": 6.5333,
|
|
"mean_token_accuracy": 0.13418369889259338,
|
|
"num_tokens": 5879601.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.299895036737142,
|
|
"eval_entropy": 6.630776028631889,
|
|
"eval_loss": 6.627320289611816,
|
|
"eval_mean_token_accuracy": 0.1339761095548169,
|
|
"eval_num_tokens": 5879601.0,
|
|
"eval_runtime": 18.4371,
|
|
"eval_samples_per_second": 1683.83,
|
|
"eval_steps_per_second": 210.499,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"entropy": 6.783554172515869,
|
|
"epoch": 0.30039486179837055,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004995454644392967,
|
|
"loss": 6.606,
|
|
"mean_token_accuracy": 0.12053637430071831,
|
|
"num_tokens": 5890255.0,
|
|
"step": 3005
|
|
},
|
|
{
|
|
"entropy": 6.720775699615478,
|
|
"epoch": 0.30089468685959914,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004995431942370087,
|
|
"loss": 6.6203,
|
|
"mean_token_accuracy": 0.13547174111008645,
|
|
"num_tokens": 5899965.0,
|
|
"step": 3010
|
|
},
|
|
{
|
|
"entropy": 6.76155366897583,
|
|
"epoch": 0.3013945119208277,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004995409183852718,
|
|
"loss": 6.5231,
|
|
"mean_token_accuracy": 0.13390932902693747,
|
|
"num_tokens": 5910082.0,
|
|
"step": 3015
|
|
},
|
|
{
|
|
"entropy": 6.7451270580291744,
|
|
"epoch": 0.30189433698205626,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004995386368841432,
|
|
"loss": 6.6386,
|
|
"mean_token_accuracy": 0.12414429485797882,
|
|
"num_tokens": 5920267.0,
|
|
"step": 3020
|
|
},
|
|
{
|
|
"entropy": 6.810834884643555,
|
|
"epoch": 0.30239416204328484,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004995363497336802,
|
|
"loss": 6.6254,
|
|
"mean_token_accuracy": 0.12998512089252473,
|
|
"num_tokens": 5929275.0,
|
|
"step": 3025
|
|
},
|
|
{
|
|
"entropy": 6.804172372817993,
|
|
"epoch": 0.30289398710451343,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004995340569339405,
|
|
"loss": 6.6433,
|
|
"mean_token_accuracy": 0.1219985917210579,
|
|
"num_tokens": 5939305.0,
|
|
"step": 3030
|
|
},
|
|
{
|
|
"entropy": 6.841426134109497,
|
|
"epoch": 0.303393812165742,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004995317584849817,
|
|
"loss": 6.6928,
|
|
"mean_token_accuracy": 0.12304298430681229,
|
|
"num_tokens": 5950816.0,
|
|
"step": 3035
|
|
},
|
|
{
|
|
"entropy": 6.70551700592041,
|
|
"epoch": 0.30389363722697055,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004995294543868615,
|
|
"loss": 6.4907,
|
|
"mean_token_accuracy": 0.1406556949019432,
|
|
"num_tokens": 5959824.0,
|
|
"step": 3040
|
|
},
|
|
{
|
|
"entropy": 6.794424343109131,
|
|
"epoch": 0.30439346228819913,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004995271446396382,
|
|
"loss": 6.5975,
|
|
"mean_token_accuracy": 0.1330313928425312,
|
|
"num_tokens": 5968752.0,
|
|
"step": 3045
|
|
},
|
|
{
|
|
"entropy": 6.750303077697754,
|
|
"epoch": 0.3048932873494277,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004995248292433697,
|
|
"loss": 6.5396,
|
|
"mean_token_accuracy": 0.12796283811330794,
|
|
"num_tokens": 5979085.0,
|
|
"step": 3050
|
|
},
|
|
{
|
|
"entropy": 6.761692380905151,
|
|
"epoch": 0.30539311241065625,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004995225081981142,
|
|
"loss": 6.5971,
|
|
"mean_token_accuracy": 0.12856600284576417,
|
|
"num_tokens": 5990378.0,
|
|
"step": 3055
|
|
},
|
|
{
|
|
"entropy": 6.748683977127075,
|
|
"epoch": 0.30589293747188484,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004995201815039301,
|
|
"loss": 6.4713,
|
|
"mean_token_accuracy": 0.14121382609009742,
|
|
"num_tokens": 5999524.0,
|
|
"step": 3060
|
|
},
|
|
{
|
|
"entropy": 6.7300026416778564,
|
|
"epoch": 0.3063927625331134,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004995178491608762,
|
|
"loss": 6.5851,
|
|
"mean_token_accuracy": 0.1298016183078289,
|
|
"num_tokens": 6009928.0,
|
|
"step": 3065
|
|
},
|
|
{
|
|
"entropy": 6.667418193817139,
|
|
"epoch": 0.30689258759434196,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004995155111690107,
|
|
"loss": 6.4623,
|
|
"mean_token_accuracy": 0.13725680708885193,
|
|
"num_tokens": 6019683.0,
|
|
"step": 3070
|
|
},
|
|
{
|
|
"entropy": 6.802922630310059,
|
|
"epoch": 0.30739241265557055,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000499513167528393,
|
|
"loss": 6.6029,
|
|
"mean_token_accuracy": 0.12657553628087043,
|
|
"num_tokens": 6030506.0,
|
|
"step": 3075
|
|
},
|
|
{
|
|
"entropy": 6.765255117416382,
|
|
"epoch": 0.30789223771679913,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004995108182390815,
|
|
"loss": 6.5603,
|
|
"mean_token_accuracy": 0.130464369058609,
|
|
"num_tokens": 6039720.0,
|
|
"step": 3080
|
|
},
|
|
{
|
|
"entropy": 6.649257755279541,
|
|
"epoch": 0.30839206277802766,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004995084633011359,
|
|
"loss": 6.4125,
|
|
"mean_token_accuracy": 0.1420907124876976,
|
|
"num_tokens": 6049336.0,
|
|
"step": 3085
|
|
},
|
|
{
|
|
"entropy": 6.6750640869140625,
|
|
"epoch": 0.30889188783925625,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000499506102714615,
|
|
"loss": 6.4497,
|
|
"mean_token_accuracy": 0.13145486935973166,
|
|
"num_tokens": 6059420.0,
|
|
"step": 3090
|
|
},
|
|
{
|
|
"entropy": 6.771726655960083,
|
|
"epoch": 0.30939171290048484,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004995037364795782,
|
|
"loss": 6.5325,
|
|
"mean_token_accuracy": 0.1350548505783081,
|
|
"num_tokens": 6069035.0,
|
|
"step": 3095
|
|
},
|
|
{
|
|
"entropy": 6.751552534103394,
|
|
"epoch": 0.3098915379617134,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004995013645960853,
|
|
"loss": 6.5333,
|
|
"mean_token_accuracy": 0.13230074495077132,
|
|
"num_tokens": 6077863.0,
|
|
"step": 3100
|
|
},
|
|
{
|
|
"entropy": 6.707284641265869,
|
|
"epoch": 0.31039136302294196,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004994989870641958,
|
|
"loss": 6.5719,
|
|
"mean_token_accuracy": 0.12928358912467958,
|
|
"num_tokens": 6088929.0,
|
|
"step": 3105
|
|
},
|
|
{
|
|
"entropy": 6.739338779449463,
|
|
"epoch": 0.31089118808417054,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004994966038839695,
|
|
"loss": 6.5183,
|
|
"mean_token_accuracy": 0.13488781303167344,
|
|
"num_tokens": 6098673.0,
|
|
"step": 3110
|
|
},
|
|
{
|
|
"entropy": 6.739440679550171,
|
|
"epoch": 0.31139101314539913,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004994942150554666,
|
|
"loss": 6.3982,
|
|
"mean_token_accuracy": 0.13903475776314736,
|
|
"num_tokens": 6107289.0,
|
|
"step": 3115
|
|
},
|
|
{
|
|
"entropy": 6.680595541000367,
|
|
"epoch": 0.31189083820662766,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004994918205787468,
|
|
"loss": 6.4573,
|
|
"mean_token_accuracy": 0.1357430823147297,
|
|
"num_tokens": 6117811.0,
|
|
"step": 3120
|
|
},
|
|
{
|
|
"entropy": 6.713736963272095,
|
|
"epoch": 0.31239066326785625,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004994894204538706,
|
|
"loss": 6.5585,
|
|
"mean_token_accuracy": 0.12887152135372162,
|
|
"num_tokens": 6127740.0,
|
|
"step": 3125
|
|
},
|
|
{
|
|
"entropy": 6.769714260101319,
|
|
"epoch": 0.31289048832908484,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004994870146808984,
|
|
"loss": 6.5349,
|
|
"mean_token_accuracy": 0.13567256852984427,
|
|
"num_tokens": 6137253.0,
|
|
"step": 3130
|
|
},
|
|
{
|
|
"entropy": 6.71686201095581,
|
|
"epoch": 0.31339031339031337,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004994846032598906,
|
|
"loss": 6.5743,
|
|
"mean_token_accuracy": 0.13248624205589293,
|
|
"num_tokens": 6147420.0,
|
|
"step": 3135
|
|
},
|
|
{
|
|
"entropy": 6.699933815002441,
|
|
"epoch": 0.31389013845154196,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004994821861909082,
|
|
"loss": 6.5169,
|
|
"mean_token_accuracy": 0.13643142953515053,
|
|
"num_tokens": 6156436.0,
|
|
"step": 3140
|
|
},
|
|
{
|
|
"entropy": 6.659816646575928,
|
|
"epoch": 0.31438996351277054,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004994797634740114,
|
|
"loss": 6.4767,
|
|
"mean_token_accuracy": 0.12807029634714126,
|
|
"num_tokens": 6165526.0,
|
|
"step": 3145
|
|
},
|
|
{
|
|
"entropy": 6.840546131134033,
|
|
"epoch": 0.3148897885739991,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004994773351092618,
|
|
"loss": 6.6801,
|
|
"mean_token_accuracy": 0.12378201708197593,
|
|
"num_tokens": 6176093.0,
|
|
"step": 3150
|
|
},
|
|
{
|
|
"entropy": 6.737400197982788,
|
|
"epoch": 0.31538961363522766,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00049947490109672,
|
|
"loss": 6.4903,
|
|
"mean_token_accuracy": 0.1427481345832348,
|
|
"num_tokens": 6185373.0,
|
|
"step": 3155
|
|
},
|
|
{
|
|
"entropy": 6.738193511962891,
|
|
"epoch": 0.31588943869645625,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004994724614364476,
|
|
"loss": 6.614,
|
|
"mean_token_accuracy": 0.12659135907888414,
|
|
"num_tokens": 6196252.0,
|
|
"step": 3160
|
|
},
|
|
{
|
|
"entropy": 6.806258583068848,
|
|
"epoch": 0.31638926375768484,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004994700161285058,
|
|
"loss": 6.5388,
|
|
"mean_token_accuracy": 0.13199907094240187,
|
|
"num_tokens": 6206463.0,
|
|
"step": 3165
|
|
},
|
|
{
|
|
"entropy": 6.748357820510864,
|
|
"epoch": 0.31688908881891337,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000499467565172956,
|
|
"loss": 6.5052,
|
|
"mean_token_accuracy": 0.13882621228694916,
|
|
"num_tokens": 6216676.0,
|
|
"step": 3170
|
|
},
|
|
{
|
|
"entropy": 6.709172964096069,
|
|
"epoch": 0.31738891388014195,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004994651085698602,
|
|
"loss": 6.5471,
|
|
"mean_token_accuracy": 0.13136286586523055,
|
|
"num_tokens": 6227261.0,
|
|
"step": 3175
|
|
},
|
|
{
|
|
"entropy": 6.738838720321655,
|
|
"epoch": 0.31788873894137054,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00049946264631928,
|
|
"loss": 6.4719,
|
|
"mean_token_accuracy": 0.13089419528841972,
|
|
"num_tokens": 6237468.0,
|
|
"step": 3180
|
|
},
|
|
{
|
|
"entropy": 6.661934852600098,
|
|
"epoch": 0.3183885640025991,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004994601784212774,
|
|
"loss": 6.4472,
|
|
"mean_token_accuracy": 0.1331954061985016,
|
|
"num_tokens": 6247164.0,
|
|
"step": 3185
|
|
},
|
|
{
|
|
"entropy": 6.6419719696044925,
|
|
"epoch": 0.31888838906382766,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004994577048759144,
|
|
"loss": 6.5523,
|
|
"mean_token_accuracy": 0.132597766071558,
|
|
"num_tokens": 6257635.0,
|
|
"step": 3190
|
|
},
|
|
{
|
|
"entropy": 6.771932888031006,
|
|
"epoch": 0.31938821412505625,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004994552256832533,
|
|
"loss": 6.6061,
|
|
"mean_token_accuracy": 0.1313496634364128,
|
|
"num_tokens": 6266823.0,
|
|
"step": 3195
|
|
},
|
|
{
|
|
"entropy": 6.75528392791748,
|
|
"epoch": 0.3198880391862848,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004994527408433566,
|
|
"loss": 6.531,
|
|
"mean_token_accuracy": 0.13688323944807052,
|
|
"num_tokens": 6276527.0,
|
|
"step": 3200
|
|
},
|
|
{
|
|
"entropy": 6.73806791305542,
|
|
"epoch": 0.32038786424751337,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004994502503562865,
|
|
"loss": 6.5808,
|
|
"mean_token_accuracy": 0.12626547291874884,
|
|
"num_tokens": 6286499.0,
|
|
"step": 3205
|
|
},
|
|
{
|
|
"entropy": 6.7163379192352295,
|
|
"epoch": 0.32088768930874195,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.000499447754222106,
|
|
"loss": 6.512,
|
|
"mean_token_accuracy": 0.1329052247107029,
|
|
"num_tokens": 6296550.0,
|
|
"step": 3210
|
|
},
|
|
{
|
|
"entropy": 6.700007677078247,
|
|
"epoch": 0.3213875143699705,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004994452524408777,
|
|
"loss": 6.553,
|
|
"mean_token_accuracy": 0.12814397141337394,
|
|
"num_tokens": 6306951.0,
|
|
"step": 3215
|
|
},
|
|
{
|
|
"entropy": 6.822968578338623,
|
|
"epoch": 0.32188733943119907,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004994427450126646,
|
|
"loss": 6.5738,
|
|
"mean_token_accuracy": 0.1254580870270729,
|
|
"num_tokens": 6316026.0,
|
|
"step": 3220
|
|
},
|
|
{
|
|
"entropy": 6.688732433319092,
|
|
"epoch": 0.32238716449242766,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004994402319375298,
|
|
"loss": 6.5166,
|
|
"mean_token_accuracy": 0.13167576789855956,
|
|
"num_tokens": 6325064.0,
|
|
"step": 3225
|
|
},
|
|
{
|
|
"entropy": 6.757549905776978,
|
|
"epoch": 0.32288698955365625,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004994377132155366,
|
|
"loss": 6.5588,
|
|
"mean_token_accuracy": 0.1331995628774166,
|
|
"num_tokens": 6334443.0,
|
|
"step": 3230
|
|
},
|
|
{
|
|
"entropy": 6.740247392654419,
|
|
"epoch": 0.3233868146148848,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004994351888467482,
|
|
"loss": 6.5674,
|
|
"mean_token_accuracy": 0.13573309332132338,
|
|
"num_tokens": 6346103.0,
|
|
"step": 3235
|
|
},
|
|
{
|
|
"entropy": 6.6513190269470215,
|
|
"epoch": 0.32388663967611336,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004994326588312282,
|
|
"loss": 6.532,
|
|
"mean_token_accuracy": 0.1347044326364994,
|
|
"num_tokens": 6356576.0,
|
|
"step": 3240
|
|
},
|
|
{
|
|
"entropy": 6.810565853118897,
|
|
"epoch": 0.32438646473734195,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004994301231690403,
|
|
"loss": 6.53,
|
|
"mean_token_accuracy": 0.13375264555215835,
|
|
"num_tokens": 6364796.0,
|
|
"step": 3245
|
|
},
|
|
{
|
|
"entropy": 6.718886804580689,
|
|
"epoch": 0.3248862897985705,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004994275818602482,
|
|
"loss": 6.611,
|
|
"mean_token_accuracy": 0.12929279431700708,
|
|
"num_tokens": 6374951.0,
|
|
"step": 3250
|
|
},
|
|
{
|
|
"entropy": 6.654961729049683,
|
|
"epoch": 0.32538611485979907,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004994250349049159,
|
|
"loss": 6.4877,
|
|
"mean_token_accuracy": 0.1318598873913288,
|
|
"num_tokens": 6384230.0,
|
|
"step": 3255
|
|
},
|
|
{
|
|
"entropy": 6.6994367122650145,
|
|
"epoch": 0.32588593992102766,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004994224823031075,
|
|
"loss": 6.5009,
|
|
"mean_token_accuracy": 0.13323622792959214,
|
|
"num_tokens": 6394070.0,
|
|
"step": 3260
|
|
},
|
|
{
|
|
"entropy": 6.685267400741577,
|
|
"epoch": 0.3263857649822562,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004994199240548873,
|
|
"loss": 6.5074,
|
|
"mean_token_accuracy": 0.13391340300440788,
|
|
"num_tokens": 6403968.0,
|
|
"step": 3265
|
|
},
|
|
{
|
|
"entropy": 6.800641918182373,
|
|
"epoch": 0.3268855900434848,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004994173601603194,
|
|
"loss": 6.6056,
|
|
"mean_token_accuracy": 0.1315523624420166,
|
|
"num_tokens": 6413254.0,
|
|
"step": 3270
|
|
},
|
|
{
|
|
"entropy": 6.716506385803223,
|
|
"epoch": 0.32738541510471336,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004994147906194684,
|
|
"loss": 6.4388,
|
|
"mean_token_accuracy": 0.13731389120221138,
|
|
"num_tokens": 6421266.0,
|
|
"step": 3275
|
|
},
|
|
{
|
|
"entropy": 6.752088499069214,
|
|
"epoch": 0.3278852401659419,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004994122154323992,
|
|
"loss": 6.5521,
|
|
"mean_token_accuracy": 0.13202136158943176,
|
|
"num_tokens": 6429596.0,
|
|
"step": 3280
|
|
},
|
|
{
|
|
"entropy": 6.7733715057373045,
|
|
"epoch": 0.3283850652271705,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004994096345991763,
|
|
"loss": 6.5447,
|
|
"mean_token_accuracy": 0.12929541245102882,
|
|
"num_tokens": 6440825.0,
|
|
"step": 3285
|
|
},
|
|
{
|
|
"entropy": 6.628010320663452,
|
|
"epoch": 0.32888489028839907,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004994070481198649,
|
|
"loss": 6.5088,
|
|
"mean_token_accuracy": 0.13302811831235886,
|
|
"num_tokens": 6450576.0,
|
|
"step": 3290
|
|
},
|
|
{
|
|
"entropy": 6.725134086608887,
|
|
"epoch": 0.32938471534962765,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004994044559945296,
|
|
"loss": 6.5108,
|
|
"mean_token_accuracy": 0.1391789697110653,
|
|
"num_tokens": 6459673.0,
|
|
"step": 3295
|
|
},
|
|
{
|
|
"entropy": 6.701463890075684,
|
|
"epoch": 0.3298845404108562,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004994018582232361,
|
|
"loss": 6.4957,
|
|
"mean_token_accuracy": 0.13158030807971954,
|
|
"num_tokens": 6469353.0,
|
|
"step": 3300
|
|
},
|
|
{
|
|
"entropy": 6.686995601654052,
|
|
"epoch": 0.3303843654720848,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004993992548060497,
|
|
"loss": 6.5204,
|
|
"mean_token_accuracy": 0.1333637237548828,
|
|
"num_tokens": 6479610.0,
|
|
"step": 3305
|
|
},
|
|
{
|
|
"entropy": 6.653195333480835,
|
|
"epoch": 0.33088419053331336,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004993966457430357,
|
|
"loss": 6.54,
|
|
"mean_token_accuracy": 0.13573898300528525,
|
|
"num_tokens": 6488866.0,
|
|
"step": 3310
|
|
},
|
|
{
|
|
"entropy": 6.707664632797242,
|
|
"epoch": 0.3313840155945419,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004993940310342598,
|
|
"loss": 6.4089,
|
|
"mean_token_accuracy": 0.14174082949757577,
|
|
"num_tokens": 6498396.0,
|
|
"step": 3315
|
|
},
|
|
{
|
|
"entropy": 6.6880530834198,
|
|
"epoch": 0.3318838406557705,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004993914106797879,
|
|
"loss": 6.462,
|
|
"mean_token_accuracy": 0.13719740733504296,
|
|
"num_tokens": 6508347.0,
|
|
"step": 3320
|
|
},
|
|
{
|
|
"entropy": 6.746197128295899,
|
|
"epoch": 0.33238366571699907,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004993887846796858,
|
|
"loss": 6.55,
|
|
"mean_token_accuracy": 0.13088712841272354,
|
|
"num_tokens": 6518369.0,
|
|
"step": 3325
|
|
},
|
|
{
|
|
"entropy": 6.689602565765381,
|
|
"epoch": 0.3328834907782276,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004993861530340196,
|
|
"loss": 6.5129,
|
|
"mean_token_accuracy": 0.13891283497214318,
|
|
"num_tokens": 6527477.0,
|
|
"step": 3330
|
|
},
|
|
{
|
|
"entropy": 6.6981299877166744,
|
|
"epoch": 0.3333833158394562,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004993835157428555,
|
|
"loss": 6.427,
|
|
"mean_token_accuracy": 0.13673900961875915,
|
|
"num_tokens": 6536271.0,
|
|
"step": 3335
|
|
},
|
|
{
|
|
"entropy": 6.709859848022461,
|
|
"epoch": 0.33388314090068477,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004993808728062599,
|
|
"loss": 6.5468,
|
|
"mean_token_accuracy": 0.1339237831532955,
|
|
"num_tokens": 6546295.0,
|
|
"step": 3340
|
|
},
|
|
{
|
|
"entropy": 6.751101922988892,
|
|
"epoch": 0.3343829659619133,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004993782242242994,
|
|
"loss": 6.4807,
|
|
"mean_token_accuracy": 0.1411467172205448,
|
|
"num_tokens": 6557338.0,
|
|
"step": 3345
|
|
},
|
|
{
|
|
"entropy": 6.62189621925354,
|
|
"epoch": 0.3348827910231419,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004993755699970404,
|
|
"loss": 6.4857,
|
|
"mean_token_accuracy": 0.13300028294324875,
|
|
"num_tokens": 6567916.0,
|
|
"step": 3350
|
|
},
|
|
{
|
|
"entropy": 6.669709730148315,
|
|
"epoch": 0.3353826160843705,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004993729101245498,
|
|
"loss": 6.5897,
|
|
"mean_token_accuracy": 0.13144382759928702,
|
|
"num_tokens": 6577821.0,
|
|
"step": 3355
|
|
},
|
|
{
|
|
"entropy": 6.73370041847229,
|
|
"epoch": 0.33588244114559906,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004993702446068945,
|
|
"loss": 6.4813,
|
|
"mean_token_accuracy": 0.13519612178206444,
|
|
"num_tokens": 6587674.0,
|
|
"step": 3360
|
|
},
|
|
{
|
|
"entropy": 6.7071089267730715,
|
|
"epoch": 0.3363822662068276,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004993675734441416,
|
|
"loss": 6.5485,
|
|
"mean_token_accuracy": 0.1344440333545208,
|
|
"num_tokens": 6597292.0,
|
|
"step": 3365
|
|
},
|
|
{
|
|
"entropy": 6.598604822158814,
|
|
"epoch": 0.3368820912680562,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004993648966363583,
|
|
"loss": 6.4849,
|
|
"mean_token_accuracy": 0.13681957721710206,
|
|
"num_tokens": 6608698.0,
|
|
"step": 3370
|
|
},
|
|
{
|
|
"entropy": 6.67167592048645,
|
|
"epoch": 0.33738191632928477,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000499362214183612,
|
|
"loss": 6.4849,
|
|
"mean_token_accuracy": 0.1337135910987854,
|
|
"num_tokens": 6617914.0,
|
|
"step": 3375
|
|
},
|
|
{
|
|
"entropy": 6.646800756454468,
|
|
"epoch": 0.3378817413905133,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00049935952608597,
|
|
"loss": 6.4374,
|
|
"mean_token_accuracy": 0.13931273743510247,
|
|
"num_tokens": 6627457.0,
|
|
"step": 3380
|
|
},
|
|
{
|
|
"entropy": 6.691873693466187,
|
|
"epoch": 0.3383815664517419,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004993568323435002,
|
|
"loss": 6.4614,
|
|
"mean_token_accuracy": 0.13891924247145654,
|
|
"num_tokens": 6636511.0,
|
|
"step": 3385
|
|
},
|
|
{
|
|
"entropy": 6.6973389148712155,
|
|
"epoch": 0.3388813915129705,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004993541329562702,
|
|
"loss": 6.4567,
|
|
"mean_token_accuracy": 0.13489941284060478,
|
|
"num_tokens": 6647028.0,
|
|
"step": 3390
|
|
},
|
|
{
|
|
"entropy": 6.704586410522461,
|
|
"epoch": 0.339381216574199,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004993514279243477,
|
|
"loss": 6.5207,
|
|
"mean_token_accuracy": 0.13709425255656243,
|
|
"num_tokens": 6656407.0,
|
|
"step": 3395
|
|
},
|
|
{
|
|
"entropy": 6.684051561355591,
|
|
"epoch": 0.3398810416354276,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004993487172478012,
|
|
"loss": 6.4482,
|
|
"mean_token_accuracy": 0.1370632082223892,
|
|
"num_tokens": 6665554.0,
|
|
"step": 3400
|
|
},
|
|
{
|
|
"entropy": 6.693660068511963,
|
|
"epoch": 0.3403808666966562,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004993460009266988,
|
|
"loss": 6.5328,
|
|
"mean_token_accuracy": 0.13296378701925277,
|
|
"num_tokens": 6675730.0,
|
|
"step": 3405
|
|
},
|
|
{
|
|
"entropy": 6.618661642074585,
|
|
"epoch": 0.3408806917578847,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004993432789611086,
|
|
"loss": 6.4407,
|
|
"mean_token_accuracy": 0.1402636870741844,
|
|
"num_tokens": 6685871.0,
|
|
"step": 3410
|
|
},
|
|
{
|
|
"entropy": 6.68305401802063,
|
|
"epoch": 0.3413805168191133,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004993405513510992,
|
|
"loss": 6.6555,
|
|
"mean_token_accuracy": 0.12181652784347534,
|
|
"num_tokens": 6697503.0,
|
|
"step": 3415
|
|
},
|
|
{
|
|
"entropy": 6.764069128036499,
|
|
"epoch": 0.3418803418803419,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004993378180967394,
|
|
"loss": 6.4533,
|
|
"mean_token_accuracy": 0.13776906058192254,
|
|
"num_tokens": 6708022.0,
|
|
"step": 3420
|
|
},
|
|
{
|
|
"entropy": 6.661357784271241,
|
|
"epoch": 0.3423801669415705,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004993350791980978,
|
|
"loss": 6.5332,
|
|
"mean_token_accuracy": 0.13591760620474816,
|
|
"num_tokens": 6717510.0,
|
|
"step": 3425
|
|
},
|
|
{
|
|
"entropy": 6.690187072753906,
|
|
"epoch": 0.342879992002799,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004993323346552433,
|
|
"loss": 6.5449,
|
|
"mean_token_accuracy": 0.1342686742544174,
|
|
"num_tokens": 6726538.0,
|
|
"step": 3430
|
|
},
|
|
{
|
|
"entropy": 6.745046710968017,
|
|
"epoch": 0.3433798170640276,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004993295844682449,
|
|
"loss": 6.4522,
|
|
"mean_token_accuracy": 0.13962674587965013,
|
|
"num_tokens": 6736750.0,
|
|
"step": 3435
|
|
},
|
|
{
|
|
"entropy": 6.694317245483399,
|
|
"epoch": 0.3438796421252562,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.000499326828637172,
|
|
"loss": 6.4945,
|
|
"mean_token_accuracy": 0.1315005213022232,
|
|
"num_tokens": 6746366.0,
|
|
"step": 3440
|
|
},
|
|
{
|
|
"entropy": 6.620949411392212,
|
|
"epoch": 0.3443794671864847,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004993240671620938,
|
|
"loss": 6.506,
|
|
"mean_token_accuracy": 0.13108294382691382,
|
|
"num_tokens": 6755887.0,
|
|
"step": 3445
|
|
},
|
|
{
|
|
"entropy": 6.657417678833008,
|
|
"epoch": 0.3448792922477133,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004993213000430797,
|
|
"loss": 6.5253,
|
|
"mean_token_accuracy": 0.1426558807492256,
|
|
"num_tokens": 6764434.0,
|
|
"step": 3450
|
|
},
|
|
{
|
|
"entropy": 6.746588850021363,
|
|
"epoch": 0.3453791173089419,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004993185272801995,
|
|
"loss": 6.5931,
|
|
"mean_token_accuracy": 0.12617274150252342,
|
|
"num_tokens": 6774237.0,
|
|
"step": 3455
|
|
},
|
|
{
|
|
"entropy": 6.757678699493408,
|
|
"epoch": 0.3458789423701704,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004993157488735228,
|
|
"loss": 6.4517,
|
|
"mean_token_accuracy": 0.13550997152924538,
|
|
"num_tokens": 6784537.0,
|
|
"step": 3460
|
|
},
|
|
{
|
|
"entropy": 6.620314359664917,
|
|
"epoch": 0.346378767431399,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004993129648231197,
|
|
"loss": 6.4528,
|
|
"mean_token_accuracy": 0.13878890573978425,
|
|
"num_tokens": 6794223.0,
|
|
"step": 3465
|
|
},
|
|
{
|
|
"entropy": 6.578345108032226,
|
|
"epoch": 0.3468785924926276,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00049931017512906,
|
|
"loss": 6.4867,
|
|
"mean_token_accuracy": 0.13346309959888458,
|
|
"num_tokens": 6803680.0,
|
|
"step": 3470
|
|
},
|
|
{
|
|
"entropy": 6.795741987228394,
|
|
"epoch": 0.3473784175538562,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004993073797914141,
|
|
"loss": 6.4955,
|
|
"mean_token_accuracy": 0.12922861874103547,
|
|
"num_tokens": 6812853.0,
|
|
"step": 3475
|
|
},
|
|
{
|
|
"entropy": 6.641557931900024,
|
|
"epoch": 0.3478782426150847,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004993045788102522,
|
|
"loss": 6.5486,
|
|
"mean_token_accuracy": 0.1343071274459362,
|
|
"num_tokens": 6822104.0,
|
|
"step": 3480
|
|
},
|
|
{
|
|
"entropy": 6.695757436752319,
|
|
"epoch": 0.3483780676763133,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004993017721856449,
|
|
"loss": 6.525,
|
|
"mean_token_accuracy": 0.1304760381579399,
|
|
"num_tokens": 6832683.0,
|
|
"step": 3485
|
|
},
|
|
{
|
|
"entropy": 6.766643762588501,
|
|
"epoch": 0.3488778927375419,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004992989599176626,
|
|
"loss": 6.4937,
|
|
"mean_token_accuracy": 0.13055627271533013,
|
|
"num_tokens": 6843191.0,
|
|
"step": 3490
|
|
},
|
|
{
|
|
"entropy": 6.646753549575806,
|
|
"epoch": 0.3493777177987704,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004992961420063763,
|
|
"loss": 6.488,
|
|
"mean_token_accuracy": 0.1350575193762779,
|
|
"num_tokens": 6852205.0,
|
|
"step": 3495
|
|
},
|
|
{
|
|
"entropy": 6.518329524993897,
|
|
"epoch": 0.349877542859999,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004992933184518567,
|
|
"loss": 6.4188,
|
|
"mean_token_accuracy": 0.13439195230603218,
|
|
"num_tokens": 6863052.0,
|
|
"step": 3500
|
|
},
|
|
{
|
|
"entropy": 6.669634056091309,
|
|
"epoch": 0.3503773679212276,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004992904892541749,
|
|
"loss": 6.4826,
|
|
"mean_token_accuracy": 0.13792546093463898,
|
|
"num_tokens": 6872717.0,
|
|
"step": 3505
|
|
},
|
|
{
|
|
"entropy": 6.661230278015137,
|
|
"epoch": 0.3508771929824561,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004992876544134022,
|
|
"loss": 6.4042,
|
|
"mean_token_accuracy": 0.14081311523914336,
|
|
"num_tokens": 6881351.0,
|
|
"step": 3510
|
|
},
|
|
{
|
|
"entropy": 6.657224369049072,
|
|
"epoch": 0.3513770180436847,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004992848139296098,
|
|
"loss": 6.4693,
|
|
"mean_token_accuracy": 0.1372024357318878,
|
|
"num_tokens": 6891353.0,
|
|
"step": 3515
|
|
},
|
|
{
|
|
"entropy": 6.670392465591431,
|
|
"epoch": 0.3518768431049133,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004992819678028692,
|
|
"loss": 6.5511,
|
|
"mean_token_accuracy": 0.12800328955054283,
|
|
"num_tokens": 6902352.0,
|
|
"step": 3520
|
|
},
|
|
{
|
|
"entropy": 6.704895782470703,
|
|
"epoch": 0.3523766681661418,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000499279116033252,
|
|
"loss": 6.5333,
|
|
"mean_token_accuracy": 0.12561603039503097,
|
|
"num_tokens": 6911950.0,
|
|
"step": 3525
|
|
},
|
|
{
|
|
"entropy": 6.643403100967407,
|
|
"epoch": 0.3528764932273704,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004992762586208299,
|
|
"loss": 6.3963,
|
|
"mean_token_accuracy": 0.14974639415740967,
|
|
"num_tokens": 6921949.0,
|
|
"step": 3530
|
|
},
|
|
{
|
|
"entropy": 6.679204940795898,
|
|
"epoch": 0.353376318288599,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004992733955656749,
|
|
"loss": 6.4509,
|
|
"mean_token_accuracy": 0.1364126905798912,
|
|
"num_tokens": 6932561.0,
|
|
"step": 3535
|
|
},
|
|
{
|
|
"entropy": 6.588069105148316,
|
|
"epoch": 0.3538761433498276,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004992705268678589,
|
|
"loss": 6.4587,
|
|
"mean_token_accuracy": 0.14087284058332444,
|
|
"num_tokens": 6941663.0,
|
|
"step": 3540
|
|
},
|
|
{
|
|
"entropy": 6.66983814239502,
|
|
"epoch": 0.3543759684110561,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004992676525274542,
|
|
"loss": 6.4736,
|
|
"mean_token_accuracy": 0.13467896357178688,
|
|
"num_tokens": 6952373.0,
|
|
"step": 3545
|
|
},
|
|
{
|
|
"entropy": 6.582099103927613,
|
|
"epoch": 0.3548757934722847,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004992647725445331,
|
|
"loss": 6.4782,
|
|
"mean_token_accuracy": 0.1386075034737587,
|
|
"num_tokens": 6961337.0,
|
|
"step": 3550
|
|
},
|
|
{
|
|
"entropy": 6.63136854171753,
|
|
"epoch": 0.3553756185335133,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000499261886919168,
|
|
"loss": 6.4389,
|
|
"mean_token_accuracy": 0.14342176765203477,
|
|
"num_tokens": 6971649.0,
|
|
"step": 3555
|
|
},
|
|
{
|
|
"entropy": 6.664999771118164,
|
|
"epoch": 0.3558754435947418,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004992589956514316,
|
|
"loss": 6.4629,
|
|
"mean_token_accuracy": 0.14281074404716493,
|
|
"num_tokens": 6982261.0,
|
|
"step": 3560
|
|
},
|
|
{
|
|
"entropy": 6.6441254138946535,
|
|
"epoch": 0.3563752686559704,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004992560987413965,
|
|
"loss": 6.4532,
|
|
"mean_token_accuracy": 0.1330704264342785,
|
|
"num_tokens": 6991324.0,
|
|
"step": 3565
|
|
},
|
|
{
|
|
"entropy": 6.598061990737915,
|
|
"epoch": 0.356875093717199,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004992531961891356,
|
|
"loss": 6.4082,
|
|
"mean_token_accuracy": 0.13796095177531242,
|
|
"num_tokens": 7001396.0,
|
|
"step": 3570
|
|
},
|
|
{
|
|
"entropy": 6.738022136688232,
|
|
"epoch": 0.35737491877842753,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004992502879947222,
|
|
"loss": 6.418,
|
|
"mean_token_accuracy": 0.13556585609912872,
|
|
"num_tokens": 7010354.0,
|
|
"step": 3575
|
|
},
|
|
{
|
|
"entropy": 6.683406686782837,
|
|
"epoch": 0.3578747438396561,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004992473741582291,
|
|
"loss": 6.5325,
|
|
"mean_token_accuracy": 0.13325171321630477,
|
|
"num_tokens": 7019835.0,
|
|
"step": 3580
|
|
},
|
|
{
|
|
"entropy": 6.611473226547242,
|
|
"epoch": 0.3583745689008847,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004992444546797298,
|
|
"loss": 6.3968,
|
|
"mean_token_accuracy": 0.14161786958575248,
|
|
"num_tokens": 7030515.0,
|
|
"step": 3585
|
|
},
|
|
{
|
|
"entropy": 6.557840633392334,
|
|
"epoch": 0.35887439396211324,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004992415295592977,
|
|
"loss": 6.4576,
|
|
"mean_token_accuracy": 0.1419329449534416,
|
|
"num_tokens": 7041248.0,
|
|
"step": 3590
|
|
},
|
|
{
|
|
"entropy": 6.674872970581054,
|
|
"epoch": 0.3593742190233418,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004992385987970064,
|
|
"loss": 6.4892,
|
|
"mean_token_accuracy": 0.1341181978583336,
|
|
"num_tokens": 7050578.0,
|
|
"step": 3595
|
|
},
|
|
{
|
|
"entropy": 6.7030867576599125,
|
|
"epoch": 0.3598740440845704,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004992356623929297,
|
|
"loss": 6.5005,
|
|
"mean_token_accuracy": 0.13172903209924697,
|
|
"num_tokens": 7060270.0,
|
|
"step": 3600
|
|
},
|
|
{
|
|
"entropy": 6.659629535675049,
|
|
"epoch": 0.360373869145799,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004992327203471414,
|
|
"loss": 6.5262,
|
|
"mean_token_accuracy": 0.13164970204234122,
|
|
"num_tokens": 7070259.0,
|
|
"step": 3605
|
|
},
|
|
{
|
|
"entropy": 6.609259414672851,
|
|
"epoch": 0.36087369420702753,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004992297726597156,
|
|
"loss": 6.4417,
|
|
"mean_token_accuracy": 0.1405242405831814,
|
|
"num_tokens": 7078784.0,
|
|
"step": 3610
|
|
},
|
|
{
|
|
"entropy": 6.668364095687866,
|
|
"epoch": 0.3613735192682561,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004992268193307264,
|
|
"loss": 6.4893,
|
|
"mean_token_accuracy": 0.13246863335371017,
|
|
"num_tokens": 7088632.0,
|
|
"step": 3615
|
|
},
|
|
{
|
|
"entropy": 6.66567554473877,
|
|
"epoch": 0.3618733443294847,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004992238603602481,
|
|
"loss": 6.4853,
|
|
"mean_token_accuracy": 0.1330085888504982,
|
|
"num_tokens": 7097703.0,
|
|
"step": 3620
|
|
},
|
|
{
|
|
"entropy": 6.603204727172852,
|
|
"epoch": 0.36237316939071323,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004992208957483552,
|
|
"loss": 6.4036,
|
|
"mean_token_accuracy": 0.14176397770643234,
|
|
"num_tokens": 7107183.0,
|
|
"step": 3625
|
|
},
|
|
{
|
|
"entropy": 6.723782539367676,
|
|
"epoch": 0.3628729944519418,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004992179254951223,
|
|
"loss": 6.5149,
|
|
"mean_token_accuracy": 0.13444778174161912,
|
|
"num_tokens": 7118220.0,
|
|
"step": 3630
|
|
},
|
|
{
|
|
"entropy": 6.647170352935791,
|
|
"epoch": 0.3633728195131704,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000499214949600624,
|
|
"loss": 6.4518,
|
|
"mean_token_accuracy": 0.13443228974938393,
|
|
"num_tokens": 7128322.0,
|
|
"step": 3635
|
|
},
|
|
{
|
|
"entropy": 6.547049283981323,
|
|
"epoch": 0.36387264457439894,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004992119680649355,
|
|
"loss": 6.4497,
|
|
"mean_token_accuracy": 0.13709384575486183,
|
|
"num_tokens": 7137284.0,
|
|
"step": 3640
|
|
},
|
|
{
|
|
"entropy": 6.602659273147583,
|
|
"epoch": 0.3643724696356275,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004992089808881313,
|
|
"loss": 6.3848,
|
|
"mean_token_accuracy": 0.14133235216140747,
|
|
"num_tokens": 7146598.0,
|
|
"step": 3645
|
|
},
|
|
{
|
|
"entropy": 6.784192419052124,
|
|
"epoch": 0.3648722946968561,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004992059880702869,
|
|
"loss": 6.5476,
|
|
"mean_token_accuracy": 0.13983522057533265,
|
|
"num_tokens": 7156816.0,
|
|
"step": 3650
|
|
},
|
|
{
|
|
"entropy": 6.682523441314697,
|
|
"epoch": 0.36537211975808465,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004992029896114775,
|
|
"loss": 6.4747,
|
|
"mean_token_accuracy": 0.13191716745495796,
|
|
"num_tokens": 7166855.0,
|
|
"step": 3655
|
|
},
|
|
{
|
|
"entropy": 6.522796726226806,
|
|
"epoch": 0.36587194481931323,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004991999855117787,
|
|
"loss": 6.3611,
|
|
"mean_token_accuracy": 0.14709938764572145,
|
|
"num_tokens": 7176477.0,
|
|
"step": 3660
|
|
},
|
|
{
|
|
"entropy": 6.633411931991577,
|
|
"epoch": 0.3663717698805418,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004991969757712659,
|
|
"loss": 6.4072,
|
|
"mean_token_accuracy": 0.13829985335469247,
|
|
"num_tokens": 7186173.0,
|
|
"step": 3665
|
|
},
|
|
{
|
|
"entropy": 6.5861372470855715,
|
|
"epoch": 0.3668715949417704,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004991939603900149,
|
|
"loss": 6.3603,
|
|
"mean_token_accuracy": 0.14236575812101365,
|
|
"num_tokens": 7195403.0,
|
|
"step": 3670
|
|
},
|
|
{
|
|
"entropy": 6.645879220962525,
|
|
"epoch": 0.36737142000299894,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004991909393681015,
|
|
"loss": 6.4559,
|
|
"mean_token_accuracy": 0.1353384457528591,
|
|
"num_tokens": 7204179.0,
|
|
"step": 3675
|
|
},
|
|
{
|
|
"entropy": 6.585832214355468,
|
|
"epoch": 0.3678712450642275,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004991879127056017,
|
|
"loss": 6.4186,
|
|
"mean_token_accuracy": 0.13716975525021552,
|
|
"num_tokens": 7214159.0,
|
|
"step": 3680
|
|
},
|
|
{
|
|
"entropy": 6.606347703933716,
|
|
"epoch": 0.3683710701254561,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004991848804025918,
|
|
"loss": 6.3778,
|
|
"mean_token_accuracy": 0.1415353387594223,
|
|
"num_tokens": 7224410.0,
|
|
"step": 3685
|
|
},
|
|
{
|
|
"entropy": 6.625489568710327,
|
|
"epoch": 0.36887089518668464,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.000499181842459148,
|
|
"loss": 6.4366,
|
|
"mean_token_accuracy": 0.1429909348487854,
|
|
"num_tokens": 7233740.0,
|
|
"step": 3690
|
|
},
|
|
{
|
|
"entropy": 6.654446172714233,
|
|
"epoch": 0.36937072024791323,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004991787988753467,
|
|
"loss": 6.4132,
|
|
"mean_token_accuracy": 0.13803667649626733,
|
|
"num_tokens": 7242834.0,
|
|
"step": 3695
|
|
},
|
|
{
|
|
"entropy": 6.568963098526001,
|
|
"epoch": 0.3698705453091418,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004991757496512645,
|
|
"loss": 6.369,
|
|
"mean_token_accuracy": 0.14709216505289077,
|
|
"num_tokens": 7252098.0,
|
|
"step": 3700
|
|
},
|
|
{
|
|
"entropy": 6.699278259277344,
|
|
"epoch": 0.37037037037037035,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004991726947869782,
|
|
"loss": 6.5498,
|
|
"mean_token_accuracy": 0.12648288458585738,
|
|
"num_tokens": 7261396.0,
|
|
"step": 3705
|
|
},
|
|
{
|
|
"entropy": 6.666980504989624,
|
|
"epoch": 0.37087019543159894,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004991696342825645,
|
|
"loss": 6.476,
|
|
"mean_token_accuracy": 0.13404362574219703,
|
|
"num_tokens": 7271138.0,
|
|
"step": 3710
|
|
},
|
|
{
|
|
"entropy": 6.602921342849731,
|
|
"epoch": 0.3713700204928275,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004991665681381005,
|
|
"loss": 6.3853,
|
|
"mean_token_accuracy": 0.1445363648235798,
|
|
"num_tokens": 7280164.0,
|
|
"step": 3715
|
|
},
|
|
{
|
|
"entropy": 6.648625707626342,
|
|
"epoch": 0.37186984555405606,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004991634963536633,
|
|
"loss": 6.4619,
|
|
"mean_token_accuracy": 0.13741569444537163,
|
|
"num_tokens": 7288830.0,
|
|
"step": 3720
|
|
},
|
|
{
|
|
"entropy": 6.619314241409302,
|
|
"epoch": 0.37236967061528464,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004991604189293303,
|
|
"loss": 6.4828,
|
|
"mean_token_accuracy": 0.1355450950562954,
|
|
"num_tokens": 7298955.0,
|
|
"step": 3725
|
|
},
|
|
{
|
|
"entropy": 6.656387805938721,
|
|
"epoch": 0.37286949567651323,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004991573358651787,
|
|
"loss": 6.3975,
|
|
"mean_token_accuracy": 0.13694959357380868,
|
|
"num_tokens": 7309829.0,
|
|
"step": 3730
|
|
},
|
|
{
|
|
"entropy": 6.646700286865235,
|
|
"epoch": 0.3733693207377418,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004991542471612864,
|
|
"loss": 6.4689,
|
|
"mean_token_accuracy": 0.1364390507340431,
|
|
"num_tokens": 7319654.0,
|
|
"step": 3735
|
|
},
|
|
{
|
|
"entropy": 6.689327192306519,
|
|
"epoch": 0.37386914579897035,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004991511528177307,
|
|
"loss": 6.4565,
|
|
"mean_token_accuracy": 0.13406700342893602,
|
|
"num_tokens": 7330415.0,
|
|
"step": 3740
|
|
},
|
|
{
|
|
"entropy": 6.686400318145752,
|
|
"epoch": 0.37436897086019894,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004991480528345898,
|
|
"loss": 6.487,
|
|
"mean_token_accuracy": 0.131680615991354,
|
|
"num_tokens": 7339511.0,
|
|
"step": 3745
|
|
},
|
|
{
|
|
"entropy": 6.741026449203491,
|
|
"epoch": 0.3748687959214275,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004991449472119416,
|
|
"loss": 6.4707,
|
|
"mean_token_accuracy": 0.12732115983963013,
|
|
"num_tokens": 7348488.0,
|
|
"step": 3750
|
|
},
|
|
{
|
|
"entropy": 6.6078413963317875,
|
|
"epoch": 0.37536862098265605,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004991418359498642,
|
|
"loss": 6.4016,
|
|
"mean_token_accuracy": 0.13857970386743546,
|
|
"num_tokens": 7357804.0,
|
|
"step": 3755
|
|
},
|
|
{
|
|
"entropy": 6.611809253692627,
|
|
"epoch": 0.37586844604388464,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004991387190484358,
|
|
"loss": 6.4852,
|
|
"mean_token_accuracy": 0.13374910578131677,
|
|
"num_tokens": 7367644.0,
|
|
"step": 3760
|
|
},
|
|
{
|
|
"entropy": 6.676985216140747,
|
|
"epoch": 0.37636827110511323,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000499135596507735,
|
|
"loss": 6.334,
|
|
"mean_token_accuracy": 0.13773026019334794,
|
|
"num_tokens": 7377357.0,
|
|
"step": 3765
|
|
},
|
|
{
|
|
"entropy": 6.600540542602539,
|
|
"epoch": 0.37686809616634176,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004991324683278402,
|
|
"loss": 6.5151,
|
|
"mean_token_accuracy": 0.1318119928240776,
|
|
"num_tokens": 7387306.0,
|
|
"step": 3770
|
|
},
|
|
{
|
|
"entropy": 6.620249891281128,
|
|
"epoch": 0.37736792122757035,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004991293345088301,
|
|
"loss": 6.4405,
|
|
"mean_token_accuracy": 0.13481418415904045,
|
|
"num_tokens": 7397472.0,
|
|
"step": 3775
|
|
},
|
|
{
|
|
"entropy": 6.617590999603271,
|
|
"epoch": 0.37786774628879893,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004991261950507837,
|
|
"loss": 6.493,
|
|
"mean_token_accuracy": 0.13492076247930526,
|
|
"num_tokens": 7408786.0,
|
|
"step": 3780
|
|
},
|
|
{
|
|
"entropy": 6.633843469619751,
|
|
"epoch": 0.37836757135002747,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00049912304995378,
|
|
"loss": 6.4569,
|
|
"mean_token_accuracy": 0.13087058067321777,
|
|
"num_tokens": 7417857.0,
|
|
"step": 3785
|
|
},
|
|
{
|
|
"entropy": 6.580232810974121,
|
|
"epoch": 0.37886739641125605,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004991198992178979,
|
|
"loss": 6.4244,
|
|
"mean_token_accuracy": 0.13517454341053964,
|
|
"num_tokens": 7427007.0,
|
|
"step": 3790
|
|
},
|
|
{
|
|
"entropy": 6.663159704208374,
|
|
"epoch": 0.37936722147248464,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004991167428432168,
|
|
"loss": 6.3556,
|
|
"mean_token_accuracy": 0.1432080551981926,
|
|
"num_tokens": 7437090.0,
|
|
"step": 3795
|
|
},
|
|
{
|
|
"entropy": 6.653858995437622,
|
|
"epoch": 0.3798670465337132,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004991135808298162,
|
|
"loss": 6.3963,
|
|
"mean_token_accuracy": 0.14008912220597267,
|
|
"num_tokens": 7446249.0,
|
|
"step": 3800
|
|
},
|
|
{
|
|
"entropy": 6.626196384429932,
|
|
"epoch": 0.38036687159494176,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004991104131777755,
|
|
"loss": 6.4173,
|
|
"mean_token_accuracy": 0.13473987355828285,
|
|
"num_tokens": 7455838.0,
|
|
"step": 3805
|
|
},
|
|
{
|
|
"entropy": 6.583133172988892,
|
|
"epoch": 0.38086669665617034,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004991072398871746,
|
|
"loss": 6.4987,
|
|
"mean_token_accuracy": 0.1326663985848427,
|
|
"num_tokens": 7466057.0,
|
|
"step": 3810
|
|
},
|
|
{
|
|
"entropy": 6.670406246185303,
|
|
"epoch": 0.38136652171739893,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004991040609580932,
|
|
"loss": 6.4548,
|
|
"mean_token_accuracy": 0.13467531204223632,
|
|
"num_tokens": 7475174.0,
|
|
"step": 3815
|
|
},
|
|
{
|
|
"entropy": 6.622626399993896,
|
|
"epoch": 0.38186634677862746,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004991008763906112,
|
|
"loss": 6.3807,
|
|
"mean_token_accuracy": 0.14110917896032332,
|
|
"num_tokens": 7484635.0,
|
|
"step": 3820
|
|
},
|
|
{
|
|
"entropy": 6.591571807861328,
|
|
"epoch": 0.38236617183985605,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004990976861848087,
|
|
"loss": 6.4522,
|
|
"mean_token_accuracy": 0.13135599717497826,
|
|
"num_tokens": 7496428.0,
|
|
"step": 3825
|
|
},
|
|
{
|
|
"entropy": 6.641083669662476,
|
|
"epoch": 0.38286599690108464,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004990944903407663,
|
|
"loss": 6.4786,
|
|
"mean_token_accuracy": 0.13468215465545655,
|
|
"num_tokens": 7506581.0,
|
|
"step": 3830
|
|
},
|
|
{
|
|
"entropy": 6.631896591186523,
|
|
"epoch": 0.38336582196231317,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004990912888585641,
|
|
"loss": 6.35,
|
|
"mean_token_accuracy": 0.14103600159287452,
|
|
"num_tokens": 7515809.0,
|
|
"step": 3835
|
|
},
|
|
{
|
|
"entropy": 6.509975290298462,
|
|
"epoch": 0.38386564702354176,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004990880817382828,
|
|
"loss": 6.3881,
|
|
"mean_token_accuracy": 0.13978929817676544,
|
|
"num_tokens": 7525800.0,
|
|
"step": 3840
|
|
},
|
|
{
|
|
"entropy": 6.590206432342529,
|
|
"epoch": 0.38436547208477034,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.000499084868980003,
|
|
"loss": 6.4761,
|
|
"mean_token_accuracy": 0.13252102136611937,
|
|
"num_tokens": 7536903.0,
|
|
"step": 3845
|
|
},
|
|
{
|
|
"entropy": 6.62482647895813,
|
|
"epoch": 0.3848652971459989,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004990816505838054,
|
|
"loss": 6.4483,
|
|
"mean_token_accuracy": 0.13781202882528304,
|
|
"num_tokens": 7546004.0,
|
|
"step": 3850
|
|
},
|
|
{
|
|
"entropy": 6.642586517333984,
|
|
"epoch": 0.38536512220722746,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004990784265497713,
|
|
"loss": 6.5578,
|
|
"mean_token_accuracy": 0.13435211181640624,
|
|
"num_tokens": 7555971.0,
|
|
"step": 3855
|
|
},
|
|
{
|
|
"entropy": 6.7109456062316895,
|
|
"epoch": 0.38586494726845605,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004990751968779817,
|
|
"loss": 6.4538,
|
|
"mean_token_accuracy": 0.13786686584353447,
|
|
"num_tokens": 7564569.0,
|
|
"step": 3860
|
|
},
|
|
{
|
|
"entropy": 6.602899742126465,
|
|
"epoch": 0.38636477232968464,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004990719615685176,
|
|
"loss": 6.4608,
|
|
"mean_token_accuracy": 0.13531645983457566,
|
|
"num_tokens": 7574134.0,
|
|
"step": 3865
|
|
},
|
|
{
|
|
"entropy": 6.598666667938232,
|
|
"epoch": 0.38686459739091317,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004990687206214608,
|
|
"loss": 6.3216,
|
|
"mean_token_accuracy": 0.14182653799653053,
|
|
"num_tokens": 7583631.0,
|
|
"step": 3870
|
|
},
|
|
{
|
|
"entropy": 6.506135177612305,
|
|
"epoch": 0.38736442245214175,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004990654740368925,
|
|
"loss": 6.294,
|
|
"mean_token_accuracy": 0.1420180991292,
|
|
"num_tokens": 7593281.0,
|
|
"step": 3875
|
|
},
|
|
{
|
|
"entropy": 6.484540557861328,
|
|
"epoch": 0.38786424751337034,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004990622218148947,
|
|
"loss": 6.4371,
|
|
"mean_token_accuracy": 0.1398145854473114,
|
|
"num_tokens": 7603735.0,
|
|
"step": 3880
|
|
},
|
|
{
|
|
"entropy": 6.647881507873535,
|
|
"epoch": 0.3883640725745989,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004990589639555489,
|
|
"loss": 6.399,
|
|
"mean_token_accuracy": 0.13606541529297828,
|
|
"num_tokens": 7613126.0,
|
|
"step": 3885
|
|
},
|
|
{
|
|
"entropy": 6.662182903289795,
|
|
"epoch": 0.38886389763582746,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004990557004589373,
|
|
"loss": 6.4325,
|
|
"mean_token_accuracy": 0.13136639297008515,
|
|
"num_tokens": 7623191.0,
|
|
"step": 3890
|
|
},
|
|
{
|
|
"entropy": 6.603696489334107,
|
|
"epoch": 0.38936372269705605,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004990524313251419,
|
|
"loss": 6.4133,
|
|
"mean_token_accuracy": 0.14168039411306382,
|
|
"num_tokens": 7634118.0,
|
|
"step": 3895
|
|
},
|
|
{
|
|
"entropy": 6.528379964828491,
|
|
"epoch": 0.3898635477582846,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004990491565542449,
|
|
"loss": 6.288,
|
|
"mean_token_accuracy": 0.15081499218940736,
|
|
"num_tokens": 7643228.0,
|
|
"step": 3900
|
|
},
|
|
{
|
|
"entropy": 6.561570167541504,
|
|
"epoch": 0.39036337281951317,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004990458761463289,
|
|
"loss": 6.4042,
|
|
"mean_token_accuracy": 0.13431327641010285,
|
|
"num_tokens": 7652578.0,
|
|
"step": 3905
|
|
},
|
|
{
|
|
"entropy": 6.5966715812683105,
|
|
"epoch": 0.39086319788074175,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004990425901014763,
|
|
"loss": 6.3664,
|
|
"mean_token_accuracy": 0.13791628554463387,
|
|
"num_tokens": 7661617.0,
|
|
"step": 3910
|
|
},
|
|
{
|
|
"entropy": 6.582742547988891,
|
|
"epoch": 0.3913630229419703,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004990392984197697,
|
|
"loss": 6.3775,
|
|
"mean_token_accuracy": 0.14419438168406487,
|
|
"num_tokens": 7670864.0,
|
|
"step": 3915
|
|
},
|
|
{
|
|
"entropy": 6.57593560218811,
|
|
"epoch": 0.39186284800319887,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004990360011012921,
|
|
"loss": 6.4378,
|
|
"mean_token_accuracy": 0.1298800878226757,
|
|
"num_tokens": 7681528.0,
|
|
"step": 3920
|
|
},
|
|
{
|
|
"entropy": 6.612252187728882,
|
|
"epoch": 0.39236267306442746,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004990326981461264,
|
|
"loss": 6.346,
|
|
"mean_token_accuracy": 0.14040571600198745,
|
|
"num_tokens": 7690398.0,
|
|
"step": 3925
|
|
},
|
|
{
|
|
"entropy": 6.536719942092896,
|
|
"epoch": 0.39286249812565605,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004990293895543555,
|
|
"loss": 6.3832,
|
|
"mean_token_accuracy": 0.1446215718984604,
|
|
"num_tokens": 7699843.0,
|
|
"step": 3930
|
|
},
|
|
{
|
|
"entropy": 6.584111309051513,
|
|
"epoch": 0.3933623231868846,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000499026075326063,
|
|
"loss": 6.4227,
|
|
"mean_token_accuracy": 0.1415751188993454,
|
|
"num_tokens": 7710181.0,
|
|
"step": 3935
|
|
},
|
|
{
|
|
"entropy": 6.592550754547119,
|
|
"epoch": 0.39386214824811316,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000499022755461332,
|
|
"loss": 6.3677,
|
|
"mean_token_accuracy": 0.1341855473816395,
|
|
"num_tokens": 7719148.0,
|
|
"step": 3940
|
|
},
|
|
{
|
|
"entropy": 6.473948907852173,
|
|
"epoch": 0.39436197330934175,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000499019429960246,
|
|
"loss": 6.2491,
|
|
"mean_token_accuracy": 0.14969748854637147,
|
|
"num_tokens": 7728551.0,
|
|
"step": 3945
|
|
},
|
|
{
|
|
"entropy": 6.605637121200561,
|
|
"epoch": 0.3948617983705703,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004990160988228888,
|
|
"loss": 6.451,
|
|
"mean_token_accuracy": 0.1340394489467144,
|
|
"num_tokens": 7739083.0,
|
|
"step": 3950
|
|
},
|
|
{
|
|
"entropy": 6.63070068359375,
|
|
"epoch": 0.39536162343179887,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004990127620493444,
|
|
"loss": 6.434,
|
|
"mean_token_accuracy": 0.13626187443733215,
|
|
"num_tokens": 7749684.0,
|
|
"step": 3955
|
|
},
|
|
{
|
|
"entropy": 6.54850549697876,
|
|
"epoch": 0.39586144849302746,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004990094196396964,
|
|
"loss": 6.3054,
|
|
"mean_token_accuracy": 0.1447399452328682,
|
|
"num_tokens": 7759281.0,
|
|
"step": 3960
|
|
},
|
|
{
|
|
"entropy": 6.550680875778198,
|
|
"epoch": 0.396361273554256,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000499006071594029,
|
|
"loss": 6.3874,
|
|
"mean_token_accuracy": 0.1380893476307392,
|
|
"num_tokens": 7768612.0,
|
|
"step": 3965
|
|
},
|
|
{
|
|
"entropy": 6.532160091400146,
|
|
"epoch": 0.3968610986154846,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004990027179124266,
|
|
"loss": 6.3271,
|
|
"mean_token_accuracy": 0.14160313084721565,
|
|
"num_tokens": 7778333.0,
|
|
"step": 3970
|
|
},
|
|
{
|
|
"entropy": 6.684771490097046,
|
|
"epoch": 0.39736092367671316,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004989993585949733,
|
|
"loss": 6.4557,
|
|
"mean_token_accuracy": 0.13541282787919046,
|
|
"num_tokens": 7787547.0,
|
|
"step": 3975
|
|
},
|
|
{
|
|
"entropy": 6.553624486923217,
|
|
"epoch": 0.3978607487379417,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004989959936417541,
|
|
"loss": 6.3988,
|
|
"mean_token_accuracy": 0.13911321386694908,
|
|
"num_tokens": 7798407.0,
|
|
"step": 3980
|
|
},
|
|
{
|
|
"entropy": 6.549784469604492,
|
|
"epoch": 0.3983605737991703,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.000498992623052853,
|
|
"loss": 6.3266,
|
|
"mean_token_accuracy": 0.14800373762845992,
|
|
"num_tokens": 7807879.0,
|
|
"step": 3985
|
|
},
|
|
{
|
|
"entropy": 6.575151538848877,
|
|
"epoch": 0.39886039886039887,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004989892468283553,
|
|
"loss": 6.3033,
|
|
"mean_token_accuracy": 0.14408419281244278,
|
|
"num_tokens": 7817210.0,
|
|
"step": 3990
|
|
},
|
|
{
|
|
"entropy": 6.662887382507324,
|
|
"epoch": 0.39936022392162746,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004989858649683457,
|
|
"loss": 6.5548,
|
|
"mean_token_accuracy": 0.12639033570885658,
|
|
"num_tokens": 7827845.0,
|
|
"step": 3995
|
|
},
|
|
{
|
|
"entropy": 6.706279182434082,
|
|
"epoch": 0.399860048982856,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004989824774729094,
|
|
"loss": 6.4104,
|
|
"mean_token_accuracy": 0.14265441671013832,
|
|
"num_tokens": 7836994.0,
|
|
"step": 4000
|
|
},
|
|
{
|
|
"entropy": 6.557466077804565,
|
|
"epoch": 0.4003598740440846,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004989790843421317,
|
|
"loss": 6.4394,
|
|
"mean_token_accuracy": 0.13453166633844377,
|
|
"num_tokens": 7846733.0,
|
|
"step": 4005
|
|
},
|
|
{
|
|
"entropy": 6.472391653060913,
|
|
"epoch": 0.40085969910531316,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004989756855760979,
|
|
"loss": 6.3679,
|
|
"mean_token_accuracy": 0.13990991711616516,
|
|
"num_tokens": 7856393.0,
|
|
"step": 4010
|
|
},
|
|
{
|
|
"entropy": 6.608847188949585,
|
|
"epoch": 0.4013595241665417,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004989722811748934,
|
|
"loss": 6.4517,
|
|
"mean_token_accuracy": 0.13580357208847998,
|
|
"num_tokens": 7866394.0,
|
|
"step": 4015
|
|
},
|
|
{
|
|
"entropy": 6.6143959045410154,
|
|
"epoch": 0.4018593492277703,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004989688711386039,
|
|
"loss": 6.4439,
|
|
"mean_token_accuracy": 0.134534602612257,
|
|
"num_tokens": 7877084.0,
|
|
"step": 4020
|
|
},
|
|
{
|
|
"entropy": 6.606017923355102,
|
|
"epoch": 0.40235917428899887,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004989654554673152,
|
|
"loss": 6.4577,
|
|
"mean_token_accuracy": 0.134698349237442,
|
|
"num_tokens": 7887289.0,
|
|
"step": 4025
|
|
},
|
|
{
|
|
"entropy": 6.532919216156006,
|
|
"epoch": 0.4028589993502274,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004989620341611133,
|
|
"loss": 6.4101,
|
|
"mean_token_accuracy": 0.13764130547642708,
|
|
"num_tokens": 7897315.0,
|
|
"step": 4030
|
|
},
|
|
{
|
|
"entropy": 6.674659585952758,
|
|
"epoch": 0.403358824411456,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004989586072200843,
|
|
"loss": 6.5104,
|
|
"mean_token_accuracy": 0.13267643377184868,
|
|
"num_tokens": 7905913.0,
|
|
"step": 4035
|
|
},
|
|
{
|
|
"entropy": 6.574588871002197,
|
|
"epoch": 0.40385864947268457,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004989551746443143,
|
|
"loss": 6.308,
|
|
"mean_token_accuracy": 0.14384820610284804,
|
|
"num_tokens": 7914879.0,
|
|
"step": 4040
|
|
},
|
|
{
|
|
"entropy": 6.553117942810059,
|
|
"epoch": 0.4043584745339131,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004989517364338899,
|
|
"loss": 6.4574,
|
|
"mean_token_accuracy": 0.13905400186777114,
|
|
"num_tokens": 7925163.0,
|
|
"step": 4045
|
|
},
|
|
{
|
|
"entropy": 6.620127153396607,
|
|
"epoch": 0.4048582995951417,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004989482925888974,
|
|
"loss": 6.3524,
|
|
"mean_token_accuracy": 0.14474843591451644,
|
|
"num_tokens": 7934380.0,
|
|
"step": 4050
|
|
},
|
|
{
|
|
"entropy": 6.6293004035949705,
|
|
"epoch": 0.4053581246563703,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004989448431094233,
|
|
"loss": 6.4243,
|
|
"mean_token_accuracy": 0.14015459418296813,
|
|
"num_tokens": 7944600.0,
|
|
"step": 4055
|
|
},
|
|
{
|
|
"entropy": 6.489453935623169,
|
|
"epoch": 0.40585794971759886,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004989413879955548,
|
|
"loss": 6.3354,
|
|
"mean_token_accuracy": 0.14372531324625015,
|
|
"num_tokens": 7953545.0,
|
|
"step": 4060
|
|
},
|
|
{
|
|
"entropy": 6.560867500305176,
|
|
"epoch": 0.4063577747788274,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004989379272473785,
|
|
"loss": 6.4095,
|
|
"mean_token_accuracy": 0.13583200797438622,
|
|
"num_tokens": 7962931.0,
|
|
"step": 4065
|
|
},
|
|
{
|
|
"entropy": 6.608096885681152,
|
|
"epoch": 0.406857599840056,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004989344608649815,
|
|
"loss": 6.3699,
|
|
"mean_token_accuracy": 0.1427628867328167,
|
|
"num_tokens": 7973090.0,
|
|
"step": 4070
|
|
},
|
|
{
|
|
"entropy": 6.61473650932312,
|
|
"epoch": 0.40735742490128457,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004989309888484511,
|
|
"loss": 6.4935,
|
|
"mean_token_accuracy": 0.13091094121336938,
|
|
"num_tokens": 7982208.0,
|
|
"step": 4075
|
|
},
|
|
{
|
|
"entropy": 6.5768373012542725,
|
|
"epoch": 0.4078572499625131,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004989275111978748,
|
|
"loss": 6.4575,
|
|
"mean_token_accuracy": 0.13970190584659575,
|
|
"num_tokens": 7993389.0,
|
|
"step": 4080
|
|
},
|
|
{
|
|
"entropy": 6.586777591705323,
|
|
"epoch": 0.4083570750237417,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004989240279133398,
|
|
"loss": 6.3408,
|
|
"mean_token_accuracy": 0.1417361781001091,
|
|
"num_tokens": 8002749.0,
|
|
"step": 4085
|
|
},
|
|
{
|
|
"entropy": 6.559087896347046,
|
|
"epoch": 0.4088569000849703,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004989205389949339,
|
|
"loss": 6.3169,
|
|
"mean_token_accuracy": 0.14500403106212617,
|
|
"num_tokens": 8011552.0,
|
|
"step": 4090
|
|
},
|
|
{
|
|
"entropy": 6.474533319473267,
|
|
"epoch": 0.4093567251461988,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004989170444427448,
|
|
"loss": 6.3374,
|
|
"mean_token_accuracy": 0.14319820553064347,
|
|
"num_tokens": 8020622.0,
|
|
"step": 4095
|
|
},
|
|
{
|
|
"entropy": 6.530226612091065,
|
|
"epoch": 0.4098565502074274,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004989135442568606,
|
|
"loss": 6.2953,
|
|
"mean_token_accuracy": 0.14594606310129166,
|
|
"num_tokens": 8030356.0,
|
|
"step": 4100
|
|
},
|
|
{
|
|
"entropy": 6.526857328414917,
|
|
"epoch": 0.410356375268656,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004989100384373693,
|
|
"loss": 6.4168,
|
|
"mean_token_accuracy": 0.13288672342896463,
|
|
"num_tokens": 8039903.0,
|
|
"step": 4105
|
|
},
|
|
{
|
|
"entropy": 6.5449991703033445,
|
|
"epoch": 0.4108562003298845,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004989065269843588,
|
|
"loss": 6.3355,
|
|
"mean_token_accuracy": 0.1405773088335991,
|
|
"num_tokens": 8050488.0,
|
|
"step": 4110
|
|
},
|
|
{
|
|
"entropy": 6.554579830169677,
|
|
"epoch": 0.4113560253911131,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000498903009897918,
|
|
"loss": 6.368,
|
|
"mean_token_accuracy": 0.13881764709949493,
|
|
"num_tokens": 8060179.0,
|
|
"step": 4115
|
|
},
|
|
{
|
|
"entropy": 6.54913649559021,
|
|
"epoch": 0.4118558504523417,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004988994871781349,
|
|
"loss": 6.4159,
|
|
"mean_token_accuracy": 0.13827834725379945,
|
|
"num_tokens": 8070915.0,
|
|
"step": 4120
|
|
},
|
|
{
|
|
"entropy": 6.544614601135254,
|
|
"epoch": 0.4123556755135703,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004988959588250983,
|
|
"loss": 6.3528,
|
|
"mean_token_accuracy": 0.14057195484638213,
|
|
"num_tokens": 8080203.0,
|
|
"step": 4125
|
|
},
|
|
{
|
|
"entropy": 6.590111541748047,
|
|
"epoch": 0.4128555005747988,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000498892424838897,
|
|
"loss": 6.3763,
|
|
"mean_token_accuracy": 0.1408051535487175,
|
|
"num_tokens": 8090552.0,
|
|
"step": 4130
|
|
},
|
|
{
|
|
"entropy": 6.577900981903076,
|
|
"epoch": 0.4133553256360274,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004988888852196199,
|
|
"loss": 6.3411,
|
|
"mean_token_accuracy": 0.14606880396604538,
|
|
"num_tokens": 8099947.0,
|
|
"step": 4135
|
|
},
|
|
{
|
|
"entropy": 6.520494270324707,
|
|
"epoch": 0.413855150697256,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004988853399673562,
|
|
"loss": 6.4335,
|
|
"mean_token_accuracy": 0.13198177739977837,
|
|
"num_tokens": 8110502.0,
|
|
"step": 4140
|
|
},
|
|
{
|
|
"entropy": 6.601160717010498,
|
|
"epoch": 0.4143549757584845,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004988817890821948,
|
|
"loss": 6.4419,
|
|
"mean_token_accuracy": 0.13627717047929763,
|
|
"num_tokens": 8118762.0,
|
|
"step": 4145
|
|
},
|
|
{
|
|
"entropy": 6.629729175567627,
|
|
"epoch": 0.4148548008197131,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004988782325642252,
|
|
"loss": 6.359,
|
|
"mean_token_accuracy": 0.13726264461874962,
|
|
"num_tokens": 8129072.0,
|
|
"step": 4150
|
|
},
|
|
{
|
|
"entropy": 6.5286548137664795,
|
|
"epoch": 0.4153546258809417,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000498874670413537,
|
|
"loss": 6.3832,
|
|
"mean_token_accuracy": 0.1353824555873871,
|
|
"num_tokens": 8138504.0,
|
|
"step": 4155
|
|
},
|
|
{
|
|
"entropy": 6.600216102600098,
|
|
"epoch": 0.4158544509421702,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004988711026302197,
|
|
"loss": 6.4528,
|
|
"mean_token_accuracy": 0.13507835268974305,
|
|
"num_tokens": 8148534.0,
|
|
"step": 4160
|
|
},
|
|
{
|
|
"entropy": 6.6404993534088135,
|
|
"epoch": 0.4163542760033988,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004988675292143629,
|
|
"loss": 6.5159,
|
|
"mean_token_accuracy": 0.13052211925387383,
|
|
"num_tokens": 8160272.0,
|
|
"step": 4165
|
|
},
|
|
{
|
|
"entropy": 6.600973844528198,
|
|
"epoch": 0.4168541010646274,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004988639501660568,
|
|
"loss": 6.3619,
|
|
"mean_token_accuracy": 0.1418714180588722,
|
|
"num_tokens": 8170053.0,
|
|
"step": 4170
|
|
},
|
|
{
|
|
"entropy": 6.596292352676391,
|
|
"epoch": 0.4173539261258559,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004988603654853913,
|
|
"loss": 6.393,
|
|
"mean_token_accuracy": 0.13247931376099586,
|
|
"num_tokens": 8179425.0,
|
|
"step": 4175
|
|
},
|
|
{
|
|
"entropy": 6.527098798751831,
|
|
"epoch": 0.4178537511870845,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004988567751724565,
|
|
"loss": 6.4046,
|
|
"mean_token_accuracy": 0.13386574983596802,
|
|
"num_tokens": 8189846.0,
|
|
"step": 4180
|
|
},
|
|
{
|
|
"entropy": 6.578232669830323,
|
|
"epoch": 0.4183535762483131,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000498853179227343,
|
|
"loss": 6.4186,
|
|
"mean_token_accuracy": 0.13852027505636216,
|
|
"num_tokens": 8198596.0,
|
|
"step": 4185
|
|
},
|
|
{
|
|
"entropy": 6.62082052230835,
|
|
"epoch": 0.4188534013095417,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000498849577650141,
|
|
"loss": 6.3176,
|
|
"mean_token_accuracy": 0.1402053378522396,
|
|
"num_tokens": 8206849.0,
|
|
"step": 4190
|
|
},
|
|
{
|
|
"entropy": 6.564785194396973,
|
|
"epoch": 0.4193532263707702,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004988459704409413,
|
|
"loss": 6.3569,
|
|
"mean_token_accuracy": 0.1440422423183918,
|
|
"num_tokens": 8216260.0,
|
|
"step": 4195
|
|
},
|
|
{
|
|
"entropy": 6.584865760803223,
|
|
"epoch": 0.4198530514319988,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004988423575998345,
|
|
"loss": 6.3703,
|
|
"mean_token_accuracy": 0.14182392060756682,
|
|
"num_tokens": 8224650.0,
|
|
"step": 4200
|
|
},
|
|
{
|
|
"entropy": 6.464220762252808,
|
|
"epoch": 0.4203528764932274,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004988387391269117,
|
|
"loss": 6.2355,
|
|
"mean_token_accuracy": 0.14646336287260056,
|
|
"num_tokens": 8235276.0,
|
|
"step": 4205
|
|
},
|
|
{
|
|
"entropy": 6.60213942527771,
|
|
"epoch": 0.4208527015544559,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004988351150222638,
|
|
"loss": 6.3147,
|
|
"mean_token_accuracy": 0.14053323045372962,
|
|
"num_tokens": 8244687.0,
|
|
"step": 4210
|
|
},
|
|
{
|
|
"entropy": 6.560609292984009,
|
|
"epoch": 0.4213525266156845,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004988314852859819,
|
|
"loss": 6.441,
|
|
"mean_token_accuracy": 0.13898905217647553,
|
|
"num_tokens": 8255091.0,
|
|
"step": 4215
|
|
},
|
|
{
|
|
"entropy": 6.518747138977051,
|
|
"epoch": 0.4218523516769131,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004988278499181575,
|
|
"loss": 6.2472,
|
|
"mean_token_accuracy": 0.15841120705008507,
|
|
"num_tokens": 8265172.0,
|
|
"step": 4220
|
|
},
|
|
{
|
|
"entropy": 6.577982473373413,
|
|
"epoch": 0.4223521767381416,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000498824208918882,
|
|
"loss": 6.3486,
|
|
"mean_token_accuracy": 0.13996930196881294,
|
|
"num_tokens": 8275625.0,
|
|
"step": 4225
|
|
},
|
|
{
|
|
"entropy": 6.514586544036865,
|
|
"epoch": 0.4228520017993702,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000498820562288247,
|
|
"loss": 6.3355,
|
|
"mean_token_accuracy": 0.13544740602374078,
|
|
"num_tokens": 8284343.0,
|
|
"step": 4230
|
|
},
|
|
{
|
|
"entropy": 6.574178791046142,
|
|
"epoch": 0.4233518268605988,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004988169100263442,
|
|
"loss": 6.4196,
|
|
"mean_token_accuracy": 0.13436390906572343,
|
|
"num_tokens": 8293430.0,
|
|
"step": 4235
|
|
},
|
|
{
|
|
"entropy": 6.509334516525269,
|
|
"epoch": 0.4238516519218274,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004988132521332656,
|
|
"loss": 6.3945,
|
|
"mean_token_accuracy": 0.13619714975357056,
|
|
"num_tokens": 8302925.0,
|
|
"step": 4240
|
|
},
|
|
{
|
|
"entropy": 6.548348474502563,
|
|
"epoch": 0.4243514769830559,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004988095886091031,
|
|
"loss": 6.3395,
|
|
"mean_token_accuracy": 0.1377752937376499,
|
|
"num_tokens": 8312134.0,
|
|
"step": 4245
|
|
},
|
|
{
|
|
"entropy": 6.588669157028198,
|
|
"epoch": 0.4248513020442845,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004988059194539489,
|
|
"loss": 6.3445,
|
|
"mean_token_accuracy": 0.13960151746869087,
|
|
"num_tokens": 8320942.0,
|
|
"step": 4250
|
|
},
|
|
{
|
|
"entropy": 6.555509424209594,
|
|
"epoch": 0.4253511271055131,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004988022446678954,
|
|
"loss": 6.3726,
|
|
"mean_token_accuracy": 0.13994579166173934,
|
|
"num_tokens": 8331898.0,
|
|
"step": 4255
|
|
},
|
|
{
|
|
"entropy": 6.532318449020385,
|
|
"epoch": 0.4258509521667416,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004987985642510352,
|
|
"loss": 6.3511,
|
|
"mean_token_accuracy": 0.1447647415101528,
|
|
"num_tokens": 8341728.0,
|
|
"step": 4260
|
|
},
|
|
{
|
|
"entropy": 6.56305890083313,
|
|
"epoch": 0.4263507772279702,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004987948782034605,
|
|
"loss": 6.3038,
|
|
"mean_token_accuracy": 0.14301208257675171,
|
|
"num_tokens": 8351611.0,
|
|
"step": 4265
|
|
},
|
|
{
|
|
"entropy": 6.5076521873474125,
|
|
"epoch": 0.4268506022891988,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004987911865252644,
|
|
"loss": 6.3281,
|
|
"mean_token_accuracy": 0.14357817620038987,
|
|
"num_tokens": 8360528.0,
|
|
"step": 4270
|
|
},
|
|
{
|
|
"entropy": 6.506665182113648,
|
|
"epoch": 0.42735042735042733,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004987874892165395,
|
|
"loss": 6.3834,
|
|
"mean_token_accuracy": 0.14152655079960824,
|
|
"num_tokens": 8369898.0,
|
|
"step": 4275
|
|
},
|
|
{
|
|
"entropy": 6.586957693099976,
|
|
"epoch": 0.4278502524116559,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000498783786277379,
|
|
"loss": 6.3355,
|
|
"mean_token_accuracy": 0.14503186643123628,
|
|
"num_tokens": 8379928.0,
|
|
"step": 4280
|
|
},
|
|
{
|
|
"entropy": 6.557859277725219,
|
|
"epoch": 0.4283500774728845,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004987800777078759,
|
|
"loss": 6.3643,
|
|
"mean_token_accuracy": 0.1393843911588192,
|
|
"num_tokens": 8389208.0,
|
|
"step": 4285
|
|
},
|
|
{
|
|
"entropy": 6.531264352798462,
|
|
"epoch": 0.42884990253411304,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004987763635081238,
|
|
"loss": 6.3598,
|
|
"mean_token_accuracy": 0.14071909934282303,
|
|
"num_tokens": 8398364.0,
|
|
"step": 4290
|
|
},
|
|
{
|
|
"entropy": 6.5567357540130615,
|
|
"epoch": 0.4293497275953416,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000498772643678216,
|
|
"loss": 6.366,
|
|
"mean_token_accuracy": 0.13652568832039833,
|
|
"num_tokens": 8408756.0,
|
|
"step": 4295
|
|
},
|
|
{
|
|
"entropy": 6.554677152633667,
|
|
"epoch": 0.4298495526565702,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004987689182182459,
|
|
"loss": 6.3251,
|
|
"mean_token_accuracy": 0.14305730685591697,
|
|
"num_tokens": 8418318.0,
|
|
"step": 4300
|
|
},
|
|
{
|
|
"entropy": 6.496006107330322,
|
|
"epoch": 0.4303493777177988,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004987651871283075,
|
|
"loss": 6.358,
|
|
"mean_token_accuracy": 0.13657767921686173,
|
|
"num_tokens": 8427709.0,
|
|
"step": 4305
|
|
},
|
|
{
|
|
"entropy": 6.571256923675537,
|
|
"epoch": 0.43084920277902733,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004987614504084946,
|
|
"loss": 6.374,
|
|
"mean_token_accuracy": 0.1362711362540722,
|
|
"num_tokens": 8437848.0,
|
|
"step": 4310
|
|
},
|
|
{
|
|
"entropy": 6.557821655273438,
|
|
"epoch": 0.4313490278402559,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004987577080589012,
|
|
"loss": 6.3204,
|
|
"mean_token_accuracy": 0.13983287513256074,
|
|
"num_tokens": 8447466.0,
|
|
"step": 4315
|
|
},
|
|
{
|
|
"entropy": 6.476554441452026,
|
|
"epoch": 0.4318488529014845,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004987539600796213,
|
|
"loss": 6.3137,
|
|
"mean_token_accuracy": 0.14809551909565927,
|
|
"num_tokens": 8456651.0,
|
|
"step": 4320
|
|
},
|
|
{
|
|
"entropy": 6.576989698410034,
|
|
"epoch": 0.43234867796271303,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004987502064707494,
|
|
"loss": 6.3649,
|
|
"mean_token_accuracy": 0.1401773512363434,
|
|
"num_tokens": 8466421.0,
|
|
"step": 4325
|
|
},
|
|
{
|
|
"entropy": 6.549679517745972,
|
|
"epoch": 0.4328485030239416,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004987464472323799,
|
|
"loss": 6.3053,
|
|
"mean_token_accuracy": 0.1403607189655304,
|
|
"num_tokens": 8476419.0,
|
|
"step": 4330
|
|
},
|
|
{
|
|
"entropy": 6.514598703384399,
|
|
"epoch": 0.4333483280851702,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004987426823646074,
|
|
"loss": 6.3337,
|
|
"mean_token_accuracy": 0.13671851754188538,
|
|
"num_tokens": 8486652.0,
|
|
"step": 4335
|
|
},
|
|
{
|
|
"entropy": 6.48084568977356,
|
|
"epoch": 0.43384815314639874,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004987389118675266,
|
|
"loss": 6.2866,
|
|
"mean_token_accuracy": 0.14497914016246796,
|
|
"num_tokens": 8495965.0,
|
|
"step": 4340
|
|
},
|
|
{
|
|
"entropy": 6.615687036514283,
|
|
"epoch": 0.4343479782076273,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004987351357412322,
|
|
"loss": 6.3703,
|
|
"mean_token_accuracy": 0.1346478521823883,
|
|
"num_tokens": 8506018.0,
|
|
"step": 4345
|
|
},
|
|
{
|
|
"entropy": 6.516758775711059,
|
|
"epoch": 0.4348478032688559,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004987313539858196,
|
|
"loss": 6.3686,
|
|
"mean_token_accuracy": 0.14214786589145662,
|
|
"num_tokens": 8516178.0,
|
|
"step": 4350
|
|
},
|
|
{
|
|
"entropy": 6.59868311882019,
|
|
"epoch": 0.43534762833008445,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004987275666013836,
|
|
"loss": 6.3895,
|
|
"mean_token_accuracy": 0.13959346786141397,
|
|
"num_tokens": 8525548.0,
|
|
"step": 4355
|
|
},
|
|
{
|
|
"entropy": 6.62802791595459,
|
|
"epoch": 0.43584745339131303,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004987237735880195,
|
|
"loss": 6.457,
|
|
"mean_token_accuracy": 0.13786746114492415,
|
|
"num_tokens": 8535941.0,
|
|
"step": 4360
|
|
},
|
|
{
|
|
"entropy": 6.453845882415772,
|
|
"epoch": 0.4363472784525416,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004987199749458229,
|
|
"loss": 6.253,
|
|
"mean_token_accuracy": 0.14585483819246292,
|
|
"num_tokens": 8545381.0,
|
|
"step": 4365
|
|
},
|
|
{
|
|
"entropy": 6.556795263290406,
|
|
"epoch": 0.4368471035137702,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004987161706748893,
|
|
"loss": 6.3584,
|
|
"mean_token_accuracy": 0.14306560084223746,
|
|
"num_tokens": 8555827.0,
|
|
"step": 4370
|
|
},
|
|
{
|
|
"entropy": 6.542530155181884,
|
|
"epoch": 0.43734692857499874,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004987123607753144,
|
|
"loss": 6.2519,
|
|
"mean_token_accuracy": 0.15178705900907516,
|
|
"num_tokens": 8565508.0,
|
|
"step": 4375
|
|
},
|
|
{
|
|
"entropy": 6.58016881942749,
|
|
"epoch": 0.4378467536362273,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000498708545247194,
|
|
"loss": 6.4514,
|
|
"mean_token_accuracy": 0.13461157009005548,
|
|
"num_tokens": 8576273.0,
|
|
"step": 4380
|
|
},
|
|
{
|
|
"entropy": 6.53968505859375,
|
|
"epoch": 0.4383465786974559,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004987047240906243,
|
|
"loss": 6.4078,
|
|
"mean_token_accuracy": 0.13572848811745644,
|
|
"num_tokens": 8585488.0,
|
|
"step": 4385
|
|
},
|
|
{
|
|
"entropy": 6.536394500732422,
|
|
"epoch": 0.43884640375868444,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004987008973057012,
|
|
"loss": 6.4451,
|
|
"mean_token_accuracy": 0.13745556324720382,
|
|
"num_tokens": 8595299.0,
|
|
"step": 4390
|
|
},
|
|
{
|
|
"entropy": 6.534514331817627,
|
|
"epoch": 0.43934622881991303,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004986970648925211,
|
|
"loss": 6.3101,
|
|
"mean_token_accuracy": 0.13881314992904664,
|
|
"num_tokens": 8604910.0,
|
|
"step": 4395
|
|
},
|
|
{
|
|
"entropy": 6.559590148925781,
|
|
"epoch": 0.4398460538811416,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004986932268511804,
|
|
"loss": 6.3358,
|
|
"mean_token_accuracy": 0.1425906352698803,
|
|
"num_tokens": 8614966.0,
|
|
"step": 4400
|
|
},
|
|
{
|
|
"entropy": 6.479949283599853,
|
|
"epoch": 0.44034587894237015,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004986893831817758,
|
|
"loss": 6.3389,
|
|
"mean_token_accuracy": 0.13987187445163726,
|
|
"num_tokens": 8624539.0,
|
|
"step": 4405
|
|
},
|
|
{
|
|
"entropy": 6.448312044143677,
|
|
"epoch": 0.44084570400359874,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004986855338844038,
|
|
"loss": 6.2097,
|
|
"mean_token_accuracy": 0.15294349938631058,
|
|
"num_tokens": 8633775.0,
|
|
"step": 4410
|
|
},
|
|
{
|
|
"entropy": 6.5140574932098385,
|
|
"epoch": 0.4413455290648273,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004986816789591613,
|
|
"loss": 6.3497,
|
|
"mean_token_accuracy": 0.13973081037402152,
|
|
"num_tokens": 8643798.0,
|
|
"step": 4415
|
|
},
|
|
{
|
|
"entropy": 6.4340917587280275,
|
|
"epoch": 0.44184535412605586,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004986778184061453,
|
|
"loss": 6.2814,
|
|
"mean_token_accuracy": 0.14660026282072067,
|
|
"num_tokens": 8653695.0,
|
|
"step": 4420
|
|
},
|
|
{
|
|
"entropy": 6.5121674060821535,
|
|
"epoch": 0.44234517918728444,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004986739522254529,
|
|
"loss": 6.2931,
|
|
"mean_token_accuracy": 0.14262207597494125,
|
|
"num_tokens": 8663521.0,
|
|
"step": 4425
|
|
},
|
|
{
|
|
"entropy": 6.610686874389648,
|
|
"epoch": 0.44284500424851303,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004986700804171816,
|
|
"loss": 6.4275,
|
|
"mean_token_accuracy": 0.13674290776252745,
|
|
"num_tokens": 8673108.0,
|
|
"step": 4430
|
|
},
|
|
{
|
|
"entropy": 6.578842210769653,
|
|
"epoch": 0.4433448293097416,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004986662029814285,
|
|
"loss": 6.3075,
|
|
"mean_token_accuracy": 0.14130824506282808,
|
|
"num_tokens": 8682917.0,
|
|
"step": 4435
|
|
},
|
|
{
|
|
"entropy": 6.528602027893067,
|
|
"epoch": 0.44384465437097015,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004986623199182913,
|
|
"loss": 6.4007,
|
|
"mean_token_accuracy": 0.13404660820960998,
|
|
"num_tokens": 8692436.0,
|
|
"step": 4440
|
|
},
|
|
{
|
|
"entropy": 6.5239604949951175,
|
|
"epoch": 0.44434447943219874,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004986584312278678,
|
|
"loss": 6.3106,
|
|
"mean_token_accuracy": 0.14313255548477172,
|
|
"num_tokens": 8702627.0,
|
|
"step": 4445
|
|
},
|
|
{
|
|
"entropy": 6.543689584732055,
|
|
"epoch": 0.4448443044934273,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004986545369102556,
|
|
"loss": 6.3211,
|
|
"mean_token_accuracy": 0.1331249937415123,
|
|
"num_tokens": 8711697.0,
|
|
"step": 4450
|
|
},
|
|
{
|
|
"entropy": 6.585853910446167,
|
|
"epoch": 0.44534412955465585,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004986506369655528,
|
|
"loss": 6.3508,
|
|
"mean_token_accuracy": 0.14003459364175797,
|
|
"num_tokens": 8721449.0,
|
|
"step": 4455
|
|
},
|
|
{
|
|
"entropy": 6.521495056152344,
|
|
"epoch": 0.44584395461588444,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004986467313938575,
|
|
"loss": 6.3286,
|
|
"mean_token_accuracy": 0.13868139386177064,
|
|
"num_tokens": 8731829.0,
|
|
"step": 4460
|
|
},
|
|
{
|
|
"entropy": 6.488602638244629,
|
|
"epoch": 0.44634377967711303,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.000498642820195268,
|
|
"loss": 6.1499,
|
|
"mean_token_accuracy": 0.15414085388183593,
|
|
"num_tokens": 8741768.0,
|
|
"step": 4465
|
|
},
|
|
{
|
|
"entropy": 6.543363189697265,
|
|
"epoch": 0.44684360473834156,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004986389033698827,
|
|
"loss": 6.4436,
|
|
"mean_token_accuracy": 0.1356188327074051,
|
|
"num_tokens": 8751473.0,
|
|
"step": 4470
|
|
},
|
|
{
|
|
"entropy": 6.566509199142456,
|
|
"epoch": 0.44734342979957015,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004986349809178002,
|
|
"loss": 6.3693,
|
|
"mean_token_accuracy": 0.13763006404042244,
|
|
"num_tokens": 8761229.0,
|
|
"step": 4475
|
|
},
|
|
{
|
|
"entropy": 6.47111701965332,
|
|
"epoch": 0.44784325486079873,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004986310528391192,
|
|
"loss": 6.3158,
|
|
"mean_token_accuracy": 0.14091528058052064,
|
|
"num_tokens": 8770670.0,
|
|
"step": 4480
|
|
},
|
|
{
|
|
"entropy": 6.554780721664429,
|
|
"epoch": 0.44834307992202727,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004986271191339383,
|
|
"loss": 6.3321,
|
|
"mean_token_accuracy": 0.14046338498592376,
|
|
"num_tokens": 8780816.0,
|
|
"step": 4485
|
|
},
|
|
{
|
|
"entropy": 6.643815612792968,
|
|
"epoch": 0.44884290498325585,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004986231798023566,
|
|
"loss": 6.4008,
|
|
"mean_token_accuracy": 0.13553248718380928,
|
|
"num_tokens": 8790304.0,
|
|
"step": 4490
|
|
},
|
|
{
|
|
"entropy": 6.523479557037353,
|
|
"epoch": 0.44934273004448444,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004986192348444734,
|
|
"loss": 6.3399,
|
|
"mean_token_accuracy": 0.14030980542302132,
|
|
"num_tokens": 8799188.0,
|
|
"step": 4495
|
|
},
|
|
{
|
|
"entropy": 6.53016505241394,
|
|
"epoch": 0.449842555105713,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004986152842603877,
|
|
"loss": 6.395,
|
|
"mean_token_accuracy": 0.14093470871448516,
|
|
"num_tokens": 8810194.0,
|
|
"step": 4500
|
|
},
|
|
{
|
|
"entropy": 6.619841718673706,
|
|
"epoch": 0.45034238016694156,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004986113280501989,
|
|
"loss": 6.4002,
|
|
"mean_token_accuracy": 0.13877397179603576,
|
|
"num_tokens": 8820394.0,
|
|
"step": 4505
|
|
},
|
|
{
|
|
"entropy": 6.525702428817749,
|
|
"epoch": 0.45084220522817015,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004986073662140068,
|
|
"loss": 6.3535,
|
|
"mean_token_accuracy": 0.14507648348808289,
|
|
"num_tokens": 8831308.0,
|
|
"step": 4510
|
|
},
|
|
{
|
|
"entropy": 6.482215404510498,
|
|
"epoch": 0.45134203028939873,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004986033987519109,
|
|
"loss": 6.2753,
|
|
"mean_token_accuracy": 0.14635651409626008,
|
|
"num_tokens": 8841461.0,
|
|
"step": 4515
|
|
},
|
|
{
|
|
"entropy": 6.533067750930786,
|
|
"epoch": 0.45184185535062726,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004985994256640108,
|
|
"loss": 6.2928,
|
|
"mean_token_accuracy": 0.14116144999861718,
|
|
"num_tokens": 8850356.0,
|
|
"step": 4520
|
|
},
|
|
{
|
|
"entropy": 6.559308958053589,
|
|
"epoch": 0.45234168041185585,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004985954469504069,
|
|
"loss": 6.392,
|
|
"mean_token_accuracy": 0.13512633517384529,
|
|
"num_tokens": 8859863.0,
|
|
"step": 4525
|
|
},
|
|
{
|
|
"entropy": 6.538211917877197,
|
|
"epoch": 0.45284150547308444,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004985914626111991,
|
|
"loss": 6.2717,
|
|
"mean_token_accuracy": 0.1402684345841408,
|
|
"num_tokens": 8869887.0,
|
|
"step": 4530
|
|
},
|
|
{
|
|
"entropy": 6.546883058547974,
|
|
"epoch": 0.45334133053431297,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004985874726464875,
|
|
"loss": 6.4243,
|
|
"mean_token_accuracy": 0.1382495306432247,
|
|
"num_tokens": 8879950.0,
|
|
"step": 4535
|
|
},
|
|
{
|
|
"entropy": 6.52933406829834,
|
|
"epoch": 0.45384115559554156,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004985834770563727,
|
|
"loss": 6.1893,
|
|
"mean_token_accuracy": 0.1510006695985794,
|
|
"num_tokens": 8888304.0,
|
|
"step": 4540
|
|
},
|
|
{
|
|
"entropy": 6.478248548507691,
|
|
"epoch": 0.45434098065677014,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004985794758409552,
|
|
"loss": 6.2096,
|
|
"mean_token_accuracy": 0.15427092462778091,
|
|
"num_tokens": 8898642.0,
|
|
"step": 4545
|
|
},
|
|
{
|
|
"entropy": 6.4841570377349855,
|
|
"epoch": 0.4548408057179987,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004985754690003354,
|
|
"loss": 6.4212,
|
|
"mean_token_accuracy": 0.13655322417616844,
|
|
"num_tokens": 8909202.0,
|
|
"step": 4550
|
|
},
|
|
{
|
|
"entropy": 6.4617311477661135,
|
|
"epoch": 0.45534063077922726,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004985714565346145,
|
|
"loss": 6.25,
|
|
"mean_token_accuracy": 0.15060166120529175,
|
|
"num_tokens": 8918844.0,
|
|
"step": 4555
|
|
},
|
|
{
|
|
"entropy": 6.5481210231781,
|
|
"epoch": 0.45584045584045585,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004985674384438933,
|
|
"loss": 6.3483,
|
|
"mean_token_accuracy": 0.13722689300775529,
|
|
"num_tokens": 8928706.0,
|
|
"step": 4560
|
|
},
|
|
{
|
|
"entropy": 6.530044269561768,
|
|
"epoch": 0.45634028090168444,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004985634147282729,
|
|
"loss": 6.2919,
|
|
"mean_token_accuracy": 0.14466736614704132,
|
|
"num_tokens": 8939293.0,
|
|
"step": 4565
|
|
},
|
|
{
|
|
"entropy": 6.468539047241211,
|
|
"epoch": 0.45684010596291297,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004985593853878544,
|
|
"loss": 6.2609,
|
|
"mean_token_accuracy": 0.1399562895298004,
|
|
"num_tokens": 8947922.0,
|
|
"step": 4570
|
|
},
|
|
{
|
|
"entropy": 6.459963941574097,
|
|
"epoch": 0.45733993102414155,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004985553504227394,
|
|
"loss": 6.2852,
|
|
"mean_token_accuracy": 0.14619463086128234,
|
|
"num_tokens": 8957745.0,
|
|
"step": 4575
|
|
},
|
|
{
|
|
"entropy": 6.572744941711425,
|
|
"epoch": 0.45783975608537014,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004985513098330293,
|
|
"loss": 6.4252,
|
|
"mean_token_accuracy": 0.134528299421072,
|
|
"num_tokens": 8968331.0,
|
|
"step": 4580
|
|
},
|
|
{
|
|
"entropy": 6.494533395767212,
|
|
"epoch": 0.4583395811465987,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004985472636188257,
|
|
"loss": 6.258,
|
|
"mean_token_accuracy": 0.14801517724990845,
|
|
"num_tokens": 8977752.0,
|
|
"step": 4585
|
|
},
|
|
{
|
|
"entropy": 6.491020774841308,
|
|
"epoch": 0.45883940620782726,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004985432117802305,
|
|
"loss": 6.3066,
|
|
"mean_token_accuracy": 0.13831876888871192,
|
|
"num_tokens": 8986701.0,
|
|
"step": 4590
|
|
},
|
|
{
|
|
"entropy": 6.481177520751953,
|
|
"epoch": 0.45933923126905585,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004985391543173456,
|
|
"loss": 6.3461,
|
|
"mean_token_accuracy": 0.13883562609553338,
|
|
"num_tokens": 8996192.0,
|
|
"step": 4595
|
|
},
|
|
{
|
|
"entropy": 6.54420051574707,
|
|
"epoch": 0.4598390563302844,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.000498535091230273,
|
|
"loss": 6.3086,
|
|
"mean_token_accuracy": 0.14105446189641951,
|
|
"num_tokens": 9007059.0,
|
|
"step": 4600
|
|
},
|
|
{
|
|
"entropy": 6.458060646057129,
|
|
"epoch": 0.46033888139151297,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004985310225191152,
|
|
"loss": 6.2587,
|
|
"mean_token_accuracy": 0.14425296783447267,
|
|
"num_tokens": 9016923.0,
|
|
"step": 4605
|
|
},
|
|
{
|
|
"entropy": 6.469832992553711,
|
|
"epoch": 0.46083870645274155,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004985269481839744,
|
|
"loss": 6.3767,
|
|
"mean_token_accuracy": 0.13866270035505296,
|
|
"num_tokens": 9026034.0,
|
|
"step": 4610
|
|
},
|
|
{
|
|
"entropy": 6.590351867675781,
|
|
"epoch": 0.4613385315139701,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004985228682249529,
|
|
"loss": 6.3882,
|
|
"mean_token_accuracy": 0.1375481203198433,
|
|
"num_tokens": 9036773.0,
|
|
"step": 4615
|
|
},
|
|
{
|
|
"entropy": 6.531398010253906,
|
|
"epoch": 0.46183835657519867,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004985187826421538,
|
|
"loss": 6.3289,
|
|
"mean_token_accuracy": 0.13996466919779776,
|
|
"num_tokens": 9047825.0,
|
|
"step": 4620
|
|
},
|
|
{
|
|
"entropy": 6.561636114120484,
|
|
"epoch": 0.46233818163642726,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004985146914356795,
|
|
"loss": 6.4206,
|
|
"mean_token_accuracy": 0.13960269317030907,
|
|
"num_tokens": 9056295.0,
|
|
"step": 4625
|
|
},
|
|
{
|
|
"entropy": 6.5317614555358885,
|
|
"epoch": 0.46283800669765585,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000498510594605633,
|
|
"loss": 6.3632,
|
|
"mean_token_accuracy": 0.1384408563375473,
|
|
"num_tokens": 9067245.0,
|
|
"step": 4630
|
|
},
|
|
{
|
|
"entropy": 6.4532373428344725,
|
|
"epoch": 0.4633378317588844,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004985064921521177,
|
|
"loss": 6.3319,
|
|
"mean_token_accuracy": 0.13723526373505593,
|
|
"num_tokens": 9077528.0,
|
|
"step": 4635
|
|
},
|
|
{
|
|
"entropy": 6.5533863544464115,
|
|
"epoch": 0.46383765682011296,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004985023840752364,
|
|
"loss": 6.2419,
|
|
"mean_token_accuracy": 0.1463705249130726,
|
|
"num_tokens": 9086015.0,
|
|
"step": 4640
|
|
},
|
|
{
|
|
"entropy": 6.536900424957276,
|
|
"epoch": 0.46433748188134155,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004984982703750926,
|
|
"loss": 6.3194,
|
|
"mean_token_accuracy": 0.13669760674238204,
|
|
"num_tokens": 9095963.0,
|
|
"step": 4645
|
|
},
|
|
{
|
|
"entropy": 6.3751177310943605,
|
|
"epoch": 0.4648373069425701,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004984941510517899,
|
|
"loss": 6.1413,
|
|
"mean_token_accuracy": 0.15125792622566223,
|
|
"num_tokens": 9105819.0,
|
|
"step": 4650
|
|
},
|
|
{
|
|
"entropy": 6.464892911911011,
|
|
"epoch": 0.46533713200379867,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004984900261054319,
|
|
"loss": 6.1824,
|
|
"mean_token_accuracy": 0.14837499260902404,
|
|
"num_tokens": 9114574.0,
|
|
"step": 4655
|
|
},
|
|
{
|
|
"entropy": 6.515645122528076,
|
|
"epoch": 0.46583695706502726,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004984858955361224,
|
|
"loss": 6.3693,
|
|
"mean_token_accuracy": 0.1343770481646061,
|
|
"num_tokens": 9125490.0,
|
|
"step": 4660
|
|
},
|
|
{
|
|
"entropy": 6.599453639984131,
|
|
"epoch": 0.4663367821262558,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004984817593439651,
|
|
"loss": 6.3226,
|
|
"mean_token_accuracy": 0.13833653926849365,
|
|
"num_tokens": 9134886.0,
|
|
"step": 4665
|
|
},
|
|
{
|
|
"entropy": 6.482732820510864,
|
|
"epoch": 0.4668366071874844,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004984776175290643,
|
|
"loss": 6.274,
|
|
"mean_token_accuracy": 0.1443267822265625,
|
|
"num_tokens": 9143598.0,
|
|
"step": 4670
|
|
},
|
|
{
|
|
"entropy": 6.461186647415161,
|
|
"epoch": 0.46733643224871296,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004984734700915242,
|
|
"loss": 6.3832,
|
|
"mean_token_accuracy": 0.13372259736061096,
|
|
"num_tokens": 9153051.0,
|
|
"step": 4675
|
|
},
|
|
{
|
|
"entropy": 6.584674549102783,
|
|
"epoch": 0.4678362573099415,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000498469317031449,
|
|
"loss": 6.2878,
|
|
"mean_token_accuracy": 0.14061242938041688,
|
|
"num_tokens": 9162472.0,
|
|
"step": 4680
|
|
},
|
|
{
|
|
"entropy": 6.486149549484253,
|
|
"epoch": 0.4683360823711701,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004984651583489434,
|
|
"loss": 6.3395,
|
|
"mean_token_accuracy": 0.14511577412486076,
|
|
"num_tokens": 9171453.0,
|
|
"step": 4685
|
|
},
|
|
{
|
|
"entropy": 6.4301036357879635,
|
|
"epoch": 0.46883590743239867,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004984609940441119,
|
|
"loss": 6.2823,
|
|
"mean_token_accuracy": 0.14500125348567963,
|
|
"num_tokens": 9181104.0,
|
|
"step": 4690
|
|
},
|
|
{
|
|
"entropy": 6.508776473999023,
|
|
"epoch": 0.46933573249362726,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004984568241170593,
|
|
"loss": 6.3576,
|
|
"mean_token_accuracy": 0.14792504906654358,
|
|
"num_tokens": 9190403.0,
|
|
"step": 4695
|
|
},
|
|
{
|
|
"entropy": 6.45200548171997,
|
|
"epoch": 0.4698355575548558,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004984526485678905,
|
|
"loss": 6.2202,
|
|
"mean_token_accuracy": 0.14412133619189263,
|
|
"num_tokens": 9199132.0,
|
|
"step": 4700
|
|
},
|
|
{
|
|
"entropy": 6.5063223361969,
|
|
"epoch": 0.4703353826160844,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004984484673967105,
|
|
"loss": 6.394,
|
|
"mean_token_accuracy": 0.13039350882172585,
|
|
"num_tokens": 9208274.0,
|
|
"step": 4705
|
|
},
|
|
{
|
|
"entropy": 6.47504997253418,
|
|
"epoch": 0.47083520767731296,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004984442806036246,
|
|
"loss": 6.3539,
|
|
"mean_token_accuracy": 0.14769015461206436,
|
|
"num_tokens": 9218513.0,
|
|
"step": 4710
|
|
},
|
|
{
|
|
"entropy": 6.551234483718872,
|
|
"epoch": 0.4713350327385415,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004984400881887381,
|
|
"loss": 6.3541,
|
|
"mean_token_accuracy": 0.13651967868208886,
|
|
"num_tokens": 9229197.0,
|
|
"step": 4715
|
|
},
|
|
{
|
|
"entropy": 6.499589490890503,
|
|
"epoch": 0.4718348577997701,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004984358901521565,
|
|
"loss": 6.2107,
|
|
"mean_token_accuracy": 0.14268688559532167,
|
|
"num_tokens": 9239465.0,
|
|
"step": 4720
|
|
},
|
|
{
|
|
"entropy": 6.4695335865020756,
|
|
"epoch": 0.47233468286099867,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004984316864939853,
|
|
"loss": 6.348,
|
|
"mean_token_accuracy": 0.1469755545258522,
|
|
"num_tokens": 9250112.0,
|
|
"step": 4725
|
|
},
|
|
{
|
|
"entropy": 6.508824443817138,
|
|
"epoch": 0.4728345079222272,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004984274772143304,
|
|
"loss": 6.3276,
|
|
"mean_token_accuracy": 0.1430274710059166,
|
|
"num_tokens": 9259406.0,
|
|
"step": 4730
|
|
},
|
|
{
|
|
"entropy": 6.583673524856567,
|
|
"epoch": 0.4733343329834558,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004984232623132977,
|
|
"loss": 6.266,
|
|
"mean_token_accuracy": 0.14246689677238464,
|
|
"num_tokens": 9269462.0,
|
|
"step": 4735
|
|
},
|
|
{
|
|
"entropy": 6.483604621887207,
|
|
"epoch": 0.4738341580446844,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004984190417909932,
|
|
"loss": 6.323,
|
|
"mean_token_accuracy": 0.13639454841613768,
|
|
"num_tokens": 9280291.0,
|
|
"step": 4740
|
|
},
|
|
{
|
|
"entropy": 6.5070860385894775,
|
|
"epoch": 0.4743339831059129,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004984148156475231,
|
|
"loss": 6.2965,
|
|
"mean_token_accuracy": 0.13384532183408737,
|
|
"num_tokens": 9289680.0,
|
|
"step": 4745
|
|
},
|
|
{
|
|
"entropy": 6.543754577636719,
|
|
"epoch": 0.4748338081671415,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004984105838829937,
|
|
"loss": 6.3061,
|
|
"mean_token_accuracy": 0.13828267604112626,
|
|
"num_tokens": 9301043.0,
|
|
"step": 4750
|
|
},
|
|
{
|
|
"entropy": 6.415587282180786,
|
|
"epoch": 0.4753336332283701,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004984063464975116,
|
|
"loss": 6.3145,
|
|
"mean_token_accuracy": 0.14800099208950995,
|
|
"num_tokens": 9311851.0,
|
|
"step": 4755
|
|
},
|
|
{
|
|
"entropy": 6.579112482070923,
|
|
"epoch": 0.47583345828959867,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004984021034911833,
|
|
"loss": 6.2891,
|
|
"mean_token_accuracy": 0.14502299576997757,
|
|
"num_tokens": 9320886.0,
|
|
"step": 4760
|
|
},
|
|
{
|
|
"entropy": 6.488643503189087,
|
|
"epoch": 0.4763332833508272,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004983978548641154,
|
|
"loss": 6.3394,
|
|
"mean_token_accuracy": 0.13805975541472434,
|
|
"num_tokens": 9330518.0,
|
|
"step": 4765
|
|
},
|
|
{
|
|
"entropy": 6.442863607406617,
|
|
"epoch": 0.4768331084120558,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004983936006164151,
|
|
"loss": 6.204,
|
|
"mean_token_accuracy": 0.14599989354610443,
|
|
"num_tokens": 9339703.0,
|
|
"step": 4770
|
|
},
|
|
{
|
|
"entropy": 6.587995529174805,
|
|
"epoch": 0.47733293347328437,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004983893407481892,
|
|
"loss": 6.4342,
|
|
"mean_token_accuracy": 0.1312703713774681,
|
|
"num_tokens": 9349931.0,
|
|
"step": 4775
|
|
},
|
|
{
|
|
"entropy": 6.507864952087402,
|
|
"epoch": 0.4778327585345129,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004983850752595451,
|
|
"loss": 6.3116,
|
|
"mean_token_accuracy": 0.14585210010409355,
|
|
"num_tokens": 9358984.0,
|
|
"step": 4780
|
|
},
|
|
{
|
|
"entropy": 6.5157966136932375,
|
|
"epoch": 0.4783325835957415,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004983808041505898,
|
|
"loss": 6.2416,
|
|
"mean_token_accuracy": 0.14548552930355071,
|
|
"num_tokens": 9368081.0,
|
|
"step": 4785
|
|
},
|
|
{
|
|
"entropy": 6.501175260543823,
|
|
"epoch": 0.4788324086569701,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004983765274214311,
|
|
"loss": 6.3742,
|
|
"mean_token_accuracy": 0.136806371062994,
|
|
"num_tokens": 9377346.0,
|
|
"step": 4790
|
|
},
|
|
{
|
|
"entropy": 6.436359977722168,
|
|
"epoch": 0.4793322337181986,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004983722450721764,
|
|
"loss": 6.3337,
|
|
"mean_token_accuracy": 0.14385157749056815,
|
|
"num_tokens": 9387493.0,
|
|
"step": 4795
|
|
},
|
|
{
|
|
"entropy": 6.520362520217896,
|
|
"epoch": 0.4798320587794272,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004983679571029336,
|
|
"loss": 6.2952,
|
|
"mean_token_accuracy": 0.1397965058684349,
|
|
"num_tokens": 9397154.0,
|
|
"step": 4800
|
|
},
|
|
{
|
|
"entropy": 6.57193775177002,
|
|
"epoch": 0.4803318838406558,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004983636635138103,
|
|
"loss": 6.4053,
|
|
"mean_token_accuracy": 0.13497058004140855,
|
|
"num_tokens": 9406705.0,
|
|
"step": 4805
|
|
},
|
|
{
|
|
"entropy": 6.510138034820557,
|
|
"epoch": 0.4808317089018843,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004983593643049148,
|
|
"loss": 6.2791,
|
|
"mean_token_accuracy": 0.148053440451622,
|
|
"num_tokens": 9416850.0,
|
|
"step": 4810
|
|
},
|
|
{
|
|
"entropy": 6.421587371826172,
|
|
"epoch": 0.4813315339631129,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004983550594763552,
|
|
"loss": 6.2334,
|
|
"mean_token_accuracy": 0.14565369784832,
|
|
"num_tokens": 9425841.0,
|
|
"step": 4815
|
|
},
|
|
{
|
|
"entropy": 6.430533838272095,
|
|
"epoch": 0.4818313590243415,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004983507490282397,
|
|
"loss": 6.1829,
|
|
"mean_token_accuracy": 0.14602613002061843,
|
|
"num_tokens": 9436748.0,
|
|
"step": 4820
|
|
},
|
|
{
|
|
"entropy": 6.473450517654419,
|
|
"epoch": 0.4823311840855701,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004983464329606768,
|
|
"loss": 6.3341,
|
|
"mean_token_accuracy": 0.14309628009796144,
|
|
"num_tokens": 9446043.0,
|
|
"step": 4825
|
|
},
|
|
{
|
|
"entropy": 6.497003698348999,
|
|
"epoch": 0.4828310091467986,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004983421112737752,
|
|
"loss": 6.3426,
|
|
"mean_token_accuracy": 0.14059921652078627,
|
|
"num_tokens": 9455480.0,
|
|
"step": 4830
|
|
},
|
|
{
|
|
"entropy": 6.52227029800415,
|
|
"epoch": 0.4833308342080272,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004983377839676435,
|
|
"loss": 6.3415,
|
|
"mean_token_accuracy": 0.1429636374115944,
|
|
"num_tokens": 9464412.0,
|
|
"step": 4835
|
|
},
|
|
{
|
|
"entropy": 6.487901496887207,
|
|
"epoch": 0.4838306592692558,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004983334510423906,
|
|
"loss": 6.2687,
|
|
"mean_token_accuracy": 0.14371415302157403,
|
|
"num_tokens": 9475639.0,
|
|
"step": 4840
|
|
},
|
|
{
|
|
"entropy": 6.496836519241333,
|
|
"epoch": 0.4843304843304843,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004983291124981257,
|
|
"loss": 6.2324,
|
|
"mean_token_accuracy": 0.1428309366106987,
|
|
"num_tokens": 9484721.0,
|
|
"step": 4845
|
|
},
|
|
{
|
|
"entropy": 6.392262268066406,
|
|
"epoch": 0.4848303093917129,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004983247683349576,
|
|
"loss": 6.1839,
|
|
"mean_token_accuracy": 0.15078072547912597,
|
|
"num_tokens": 9494594.0,
|
|
"step": 4850
|
|
},
|
|
{
|
|
"entropy": 6.379246187210083,
|
|
"epoch": 0.4853301344529415,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004983204185529959,
|
|
"loss": 6.2297,
|
|
"mean_token_accuracy": 0.15043352991342546,
|
|
"num_tokens": 9503707.0,
|
|
"step": 4855
|
|
},
|
|
{
|
|
"entropy": 6.49135274887085,
|
|
"epoch": 0.48582995951417,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004983160631523499,
|
|
"loss": 6.1902,
|
|
"mean_token_accuracy": 0.14579902365803718,
|
|
"num_tokens": 9512473.0,
|
|
"step": 4860
|
|
},
|
|
{
|
|
"entropy": 6.504326486587525,
|
|
"epoch": 0.4863297845753986,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004983117021331293,
|
|
"loss": 6.328,
|
|
"mean_token_accuracy": 0.14437096416950226,
|
|
"num_tokens": 9523253.0,
|
|
"step": 4865
|
|
},
|
|
{
|
|
"entropy": 6.5039753913879395,
|
|
"epoch": 0.4868296096366272,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004983073354954436,
|
|
"loss": 6.2876,
|
|
"mean_token_accuracy": 0.14891613274812698,
|
|
"num_tokens": 9531938.0,
|
|
"step": 4870
|
|
},
|
|
{
|
|
"entropy": 6.523850584030152,
|
|
"epoch": 0.4873294346978557,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004983029632394029,
|
|
"loss": 6.2931,
|
|
"mean_token_accuracy": 0.14198393672704696,
|
|
"num_tokens": 9541542.0,
|
|
"step": 4875
|
|
},
|
|
{
|
|
"entropy": 6.428567218780517,
|
|
"epoch": 0.4878292597590843,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000498298585365117,
|
|
"loss": 6.2193,
|
|
"mean_token_accuracy": 0.14667681604623795,
|
|
"num_tokens": 9551521.0,
|
|
"step": 4880
|
|
},
|
|
{
|
|
"entropy": 6.466378831863404,
|
|
"epoch": 0.4883290848203129,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004982942018726963,
|
|
"loss": 6.3514,
|
|
"mean_token_accuracy": 0.14658211767673493,
|
|
"num_tokens": 9561605.0,
|
|
"step": 4885
|
|
},
|
|
{
|
|
"entropy": 6.514699125289917,
|
|
"epoch": 0.4888289098815415,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004982898127622508,
|
|
"loss": 6.2553,
|
|
"mean_token_accuracy": 0.14559754058718682,
|
|
"num_tokens": 9571591.0,
|
|
"step": 4890
|
|
},
|
|
{
|
|
"entropy": 6.407695722579956,
|
|
"epoch": 0.48932873494277,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004982854180338911,
|
|
"loss": 6.2647,
|
|
"mean_token_accuracy": 0.1466855026781559,
|
|
"num_tokens": 9580994.0,
|
|
"step": 4895
|
|
},
|
|
{
|
|
"entropy": 6.5345968246459964,
|
|
"epoch": 0.4898285600039986,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004982810176877279,
|
|
"loss": 6.268,
|
|
"mean_token_accuracy": 0.14102225825190545,
|
|
"num_tokens": 9589268.0,
|
|
"step": 4900
|
|
},
|
|
{
|
|
"entropy": 6.470806026458741,
|
|
"epoch": 0.4903283850652272,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004982766117238716,
|
|
"loss": 6.3216,
|
|
"mean_token_accuracy": 0.1400758869946003,
|
|
"num_tokens": 9599461.0,
|
|
"step": 4905
|
|
},
|
|
{
|
|
"entropy": 6.453066110610962,
|
|
"epoch": 0.4908282101264557,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004982722001424331,
|
|
"loss": 6.2917,
|
|
"mean_token_accuracy": 0.14182407408952713,
|
|
"num_tokens": 9609629.0,
|
|
"step": 4910
|
|
},
|
|
{
|
|
"entropy": 6.418763780593872,
|
|
"epoch": 0.4913280351876843,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004982677829435236,
|
|
"loss": 6.2079,
|
|
"mean_token_accuracy": 0.15076979696750642,
|
|
"num_tokens": 9619618.0,
|
|
"step": 4915
|
|
},
|
|
{
|
|
"entropy": 6.472671461105347,
|
|
"epoch": 0.4918278602489129,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004982633601272543,
|
|
"loss": 6.2695,
|
|
"mean_token_accuracy": 0.14576450288295745,
|
|
"num_tokens": 9629042.0,
|
|
"step": 4920
|
|
},
|
|
{
|
|
"entropy": 6.462853670120239,
|
|
"epoch": 0.4923276853101414,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004982589316937361,
|
|
"loss": 6.243,
|
|
"mean_token_accuracy": 0.14421821683645247,
|
|
"num_tokens": 9638596.0,
|
|
"step": 4925
|
|
},
|
|
{
|
|
"entropy": 6.503546905517578,
|
|
"epoch": 0.49282751037137,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004982544976430808,
|
|
"loss": 6.333,
|
|
"mean_token_accuracy": 0.14002783223986626,
|
|
"num_tokens": 9648505.0,
|
|
"step": 4930
|
|
},
|
|
{
|
|
"entropy": 6.422399234771729,
|
|
"epoch": 0.4933273354325986,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004982500579753995,
|
|
"loss": 6.3015,
|
|
"mean_token_accuracy": 0.14369556680321693,
|
|
"num_tokens": 9658113.0,
|
|
"step": 4935
|
|
},
|
|
{
|
|
"entropy": 6.4771932601928714,
|
|
"epoch": 0.49382716049382713,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004982456126908044,
|
|
"loss": 6.328,
|
|
"mean_token_accuracy": 0.14563848972320556,
|
|
"num_tokens": 9668075.0,
|
|
"step": 4940
|
|
},
|
|
{
|
|
"entropy": 6.582532358169556,
|
|
"epoch": 0.4943269855550557,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004982411617894071,
|
|
"loss": 6.2838,
|
|
"mean_token_accuracy": 0.1421746701002121,
|
|
"num_tokens": 9678139.0,
|
|
"step": 4945
|
|
},
|
|
{
|
|
"entropy": 6.458785152435302,
|
|
"epoch": 0.4948268106162843,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004982367052713196,
|
|
"loss": 6.3209,
|
|
"mean_token_accuracy": 0.1364033341407776,
|
|
"num_tokens": 9687328.0,
|
|
"step": 4950
|
|
},
|
|
{
|
|
"entropy": 6.428125238418579,
|
|
"epoch": 0.4953266356775129,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004982322431366541,
|
|
"loss": 6.2963,
|
|
"mean_token_accuracy": 0.14726474955677987,
|
|
"num_tokens": 9697536.0,
|
|
"step": 4955
|
|
},
|
|
{
|
|
"entropy": 6.507616567611694,
|
|
"epoch": 0.4958264607387414,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004982277753855227,
|
|
"loss": 6.3239,
|
|
"mean_token_accuracy": 0.14271707609295844,
|
|
"num_tokens": 9706804.0,
|
|
"step": 4960
|
|
},
|
|
{
|
|
"entropy": 6.499647188186645,
|
|
"epoch": 0.49632628579997,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000498223302018038,
|
|
"loss": 6.2152,
|
|
"mean_token_accuracy": 0.15250640586018563,
|
|
"num_tokens": 9716868.0,
|
|
"step": 4965
|
|
},
|
|
{
|
|
"entropy": 6.424004459381104,
|
|
"epoch": 0.4968261108611986,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004982188230343124,
|
|
"loss": 6.2936,
|
|
"mean_token_accuracy": 0.14402196258306504,
|
|
"num_tokens": 9728790.0,
|
|
"step": 4970
|
|
},
|
|
{
|
|
"entropy": 6.521448183059692,
|
|
"epoch": 0.49732593592242713,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004982143384344587,
|
|
"loss": 6.3209,
|
|
"mean_token_accuracy": 0.14097120687365533,
|
|
"num_tokens": 9739118.0,
|
|
"step": 4975
|
|
},
|
|
{
|
|
"entropy": 6.506854438781739,
|
|
"epoch": 0.4978257609836557,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004982098482185897,
|
|
"loss": 6.3063,
|
|
"mean_token_accuracy": 0.14251478612422944,
|
|
"num_tokens": 9749347.0,
|
|
"step": 4980
|
|
},
|
|
{
|
|
"entropy": 6.511482858657837,
|
|
"epoch": 0.4983255860448843,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004982053523868182,
|
|
"loss": 6.3376,
|
|
"mean_token_accuracy": 0.14065980836749076,
|
|
"num_tokens": 9759432.0,
|
|
"step": 4985
|
|
},
|
|
{
|
|
"entropy": 6.447167539596558,
|
|
"epoch": 0.49882541110611284,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004982008509392576,
|
|
"loss": 6.2469,
|
|
"mean_token_accuracy": 0.14047390222549438,
|
|
"num_tokens": 9768666.0,
|
|
"step": 4990
|
|
},
|
|
{
|
|
"entropy": 6.373848533630371,
|
|
"epoch": 0.4993252361673414,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000498196343876021,
|
|
"loss": 6.2014,
|
|
"mean_token_accuracy": 0.1518920511007309,
|
|
"num_tokens": 9778699.0,
|
|
"step": 4995
|
|
},
|
|
{
|
|
"entropy": 6.458275175094604,
|
|
"epoch": 0.49982506122857,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004981918311972219,
|
|
"loss": 6.2379,
|
|
"mean_token_accuracy": 0.14668502882122994,
|
|
"num_tokens": 9788156.0,
|
|
"step": 5000
|
|
},
|
|
{
|
|
"entropy": 6.414515447616577,
|
|
"epoch": 0.5003248862897985,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004981873129029737,
|
|
"loss": 6.19,
|
|
"mean_token_accuracy": 0.15714230835437776,
|
|
"num_tokens": 9797293.0,
|
|
"step": 5005
|
|
},
|
|
{
|
|
"entropy": 6.414603519439697,
|
|
"epoch": 0.5008247113510271,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00049818278899339,
|
|
"loss": 6.208,
|
|
"mean_token_accuracy": 0.14584677964448928,
|
|
"num_tokens": 9806962.0,
|
|
"step": 5010
|
|
},
|
|
{
|
|
"entropy": 6.464185571670532,
|
|
"epoch": 0.5013245364122557,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000498178259468585,
|
|
"loss": 6.3421,
|
|
"mean_token_accuracy": 0.14279545992612838,
|
|
"num_tokens": 9816689.0,
|
|
"step": 5015
|
|
},
|
|
{
|
|
"entropy": 6.481401824951172,
|
|
"epoch": 0.5018243614734843,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004981737243286722,
|
|
"loss": 6.1872,
|
|
"mean_token_accuracy": 0.1465285986661911,
|
|
"num_tokens": 9826321.0,
|
|
"step": 5020
|
|
},
|
|
{
|
|
"entropy": 6.539868974685669,
|
|
"epoch": 0.5023241865347129,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004981691835737661,
|
|
"loss": 6.3484,
|
|
"mean_token_accuracy": 0.13538563400506973,
|
|
"num_tokens": 9836054.0,
|
|
"step": 5025
|
|
},
|
|
{
|
|
"entropy": 6.552703857421875,
|
|
"epoch": 0.5028240115959414,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004981646372039807,
|
|
"loss": 6.3359,
|
|
"mean_token_accuracy": 0.1394810661673546,
|
|
"num_tokens": 9846516.0,
|
|
"step": 5030
|
|
},
|
|
{
|
|
"entropy": 6.45863299369812,
|
|
"epoch": 0.50332383665717,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004981600852194305,
|
|
"loss": 6.1251,
|
|
"mean_token_accuracy": 0.15314733237028122,
|
|
"num_tokens": 9856599.0,
|
|
"step": 5035
|
|
},
|
|
{
|
|
"entropy": 6.457842016220093,
|
|
"epoch": 0.5038236617183985,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00049815552762023,
|
|
"loss": 6.2501,
|
|
"mean_token_accuracy": 0.14722048193216325,
|
|
"num_tokens": 9866922.0,
|
|
"step": 5040
|
|
},
|
|
{
|
|
"entropy": 6.429340839385986,
|
|
"epoch": 0.5043234867796271,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004981509644064937,
|
|
"loss": 6.2465,
|
|
"mean_token_accuracy": 0.14557284638285636,
|
|
"num_tokens": 9876174.0,
|
|
"step": 5045
|
|
},
|
|
{
|
|
"entropy": 6.437441682815551,
|
|
"epoch": 0.5048233118408557,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004981463955783367,
|
|
"loss": 6.197,
|
|
"mean_token_accuracy": 0.14810907393693923,
|
|
"num_tokens": 9886208.0,
|
|
"step": 5050
|
|
},
|
|
{
|
|
"entropy": 6.48028335571289,
|
|
"epoch": 0.5053231369020843,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004981418211358736,
|
|
"loss": 6.2502,
|
|
"mean_token_accuracy": 0.14508378654718398,
|
|
"num_tokens": 9896522.0,
|
|
"step": 5055
|
|
},
|
|
{
|
|
"entropy": 6.432210636138916,
|
|
"epoch": 0.5058229619633129,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004981372410792199,
|
|
"loss": 6.2389,
|
|
"mean_token_accuracy": 0.1507919669151306,
|
|
"num_tokens": 9905753.0,
|
|
"step": 5060
|
|
},
|
|
{
|
|
"entropy": 6.496094846725464,
|
|
"epoch": 0.5063227870245414,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004981326554084906,
|
|
"loss": 6.336,
|
|
"mean_token_accuracy": 0.14507129937410354,
|
|
"num_tokens": 9916566.0,
|
|
"step": 5065
|
|
},
|
|
{
|
|
"entropy": 6.500605773925781,
|
|
"epoch": 0.50682261208577,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004981280641238011,
|
|
"loss": 6.3197,
|
|
"mean_token_accuracy": 0.13981844410300254,
|
|
"num_tokens": 9926126.0,
|
|
"step": 5070
|
|
},
|
|
{
|
|
"entropy": 6.484925937652588,
|
|
"epoch": 0.5073224371469985,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004981234672252669,
|
|
"loss": 6.3035,
|
|
"mean_token_accuracy": 0.14005504474043845,
|
|
"num_tokens": 9937666.0,
|
|
"step": 5075
|
|
},
|
|
{
|
|
"entropy": 6.536907005310058,
|
|
"epoch": 0.5078222622082271,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004981188647130037,
|
|
"loss": 6.3467,
|
|
"mean_token_accuracy": 0.15003084391355515,
|
|
"num_tokens": 9947107.0,
|
|
"step": 5080
|
|
},
|
|
{
|
|
"entropy": 6.478869819641114,
|
|
"epoch": 0.5083220872694557,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004981142565871272,
|
|
"loss": 6.1996,
|
|
"mean_token_accuracy": 0.14651109427213668,
|
|
"num_tokens": 9956484.0,
|
|
"step": 5085
|
|
},
|
|
{
|
|
"entropy": 6.357135772705078,
|
|
"epoch": 0.5088219123306843,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004981096428477535,
|
|
"loss": 6.2558,
|
|
"mean_token_accuracy": 0.1442209430038929,
|
|
"num_tokens": 9966731.0,
|
|
"step": 5090
|
|
},
|
|
{
|
|
"entropy": 6.476908922195435,
|
|
"epoch": 0.5093217373919128,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004981050234949986,
|
|
"loss": 6.2411,
|
|
"mean_token_accuracy": 0.14739679247140886,
|
|
"num_tokens": 9976491.0,
|
|
"step": 5095
|
|
},
|
|
{
|
|
"entropy": 6.519944143295288,
|
|
"epoch": 0.5098215624531414,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004981003985289786,
|
|
"loss": 6.1776,
|
|
"mean_token_accuracy": 0.149426232278347,
|
|
"num_tokens": 9985248.0,
|
|
"step": 5100
|
|
},
|
|
{
|
|
"entropy": 6.409350252151489,
|
|
"epoch": 0.51032138751437,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004980957679498101,
|
|
"loss": 6.2726,
|
|
"mean_token_accuracy": 0.14669610783457757,
|
|
"num_tokens": 9995578.0,
|
|
"step": 5105
|
|
},
|
|
{
|
|
"entropy": 6.521508741378784,
|
|
"epoch": 0.5108212125755985,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004980911317576095,
|
|
"loss": 6.3613,
|
|
"mean_token_accuracy": 0.13964017778635024,
|
|
"num_tokens": 10006078.0,
|
|
"step": 5110
|
|
},
|
|
{
|
|
"entropy": 6.545692682266235,
|
|
"epoch": 0.5113210376368271,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004980864899524933,
|
|
"loss": 6.3158,
|
|
"mean_token_accuracy": 0.13703773245215417,
|
|
"num_tokens": 10015943.0,
|
|
"step": 5115
|
|
},
|
|
{
|
|
"entropy": 6.488755893707276,
|
|
"epoch": 0.5118208626980557,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004980818425345786,
|
|
"loss": 6.3259,
|
|
"mean_token_accuracy": 0.13959860056638718,
|
|
"num_tokens": 10025738.0,
|
|
"step": 5120
|
|
},
|
|
{
|
|
"entropy": 6.538602304458618,
|
|
"epoch": 0.5123206877592843,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000498077189503982,
|
|
"loss": 6.2814,
|
|
"mean_token_accuracy": 0.13867102414369584,
|
|
"num_tokens": 10035032.0,
|
|
"step": 5125
|
|
},
|
|
{
|
|
"entropy": 6.493793916702271,
|
|
"epoch": 0.5128205128205128,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004980725308608208,
|
|
"loss": 6.2353,
|
|
"mean_token_accuracy": 0.1468093454837799,
|
|
"num_tokens": 10044201.0,
|
|
"step": 5130
|
|
},
|
|
{
|
|
"entropy": 6.3738292217254635,
|
|
"epoch": 0.5133203378817414,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004980678666052121,
|
|
"loss": 6.2928,
|
|
"mean_token_accuracy": 0.14822009056806565,
|
|
"num_tokens": 10054163.0,
|
|
"step": 5135
|
|
},
|
|
{
|
|
"entropy": 6.444634294509887,
|
|
"epoch": 0.51382016294297,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004980631967372733,
|
|
"loss": 6.2834,
|
|
"mean_token_accuracy": 0.14270321428775787,
|
|
"num_tokens": 10065225.0,
|
|
"step": 5140
|
|
},
|
|
{
|
|
"entropy": 6.511883735656738,
|
|
"epoch": 0.5143199880041985,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004980585212571218,
|
|
"loss": 6.2556,
|
|
"mean_token_accuracy": 0.1469488687813282,
|
|
"num_tokens": 10074776.0,
|
|
"step": 5145
|
|
},
|
|
{
|
|
"entropy": 6.522441959381103,
|
|
"epoch": 0.5148198130654271,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004980538401648753,
|
|
"loss": 6.4009,
|
|
"mean_token_accuracy": 0.1429189771413803,
|
|
"num_tokens": 10085917.0,
|
|
"step": 5150
|
|
},
|
|
{
|
|
"entropy": 6.460656452178955,
|
|
"epoch": 0.5153196381266557,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004980491534606517,
|
|
"loss": 6.2226,
|
|
"mean_token_accuracy": 0.14594015330076218,
|
|
"num_tokens": 10094727.0,
|
|
"step": 5155
|
|
},
|
|
{
|
|
"entropy": 6.460877370834351,
|
|
"epoch": 0.5158194631878842,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004980444611445686,
|
|
"loss": 6.2006,
|
|
"mean_token_accuracy": 0.15095902010798454,
|
|
"num_tokens": 10104839.0,
|
|
"step": 5160
|
|
},
|
|
{
|
|
"entropy": 6.4641259670257565,
|
|
"epoch": 0.5163192882491128,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004980397632167444,
|
|
"loss": 6.1788,
|
|
"mean_token_accuracy": 0.14686077684164048,
|
|
"num_tokens": 10114501.0,
|
|
"step": 5165
|
|
},
|
|
{
|
|
"entropy": 6.442966508865356,
|
|
"epoch": 0.5168191133103414,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004980350596772971,
|
|
"loss": 6.2806,
|
|
"mean_token_accuracy": 0.14431710094213485,
|
|
"num_tokens": 10124597.0,
|
|
"step": 5170
|
|
},
|
|
{
|
|
"entropy": 6.368315505981445,
|
|
"epoch": 0.51731893837157,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004980303505263451,
|
|
"loss": 6.1467,
|
|
"mean_token_accuracy": 0.14768103063106536,
|
|
"num_tokens": 10135695.0,
|
|
"step": 5175
|
|
},
|
|
{
|
|
"entropy": 6.395515727996826,
|
|
"epoch": 0.5178187634327985,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004980256357640069,
|
|
"loss": 6.2358,
|
|
"mean_token_accuracy": 0.14446025490760803,
|
|
"num_tokens": 10146107.0,
|
|
"step": 5180
|
|
},
|
|
{
|
|
"entropy": 6.517473602294922,
|
|
"epoch": 0.5183185884940271,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004980209153904011,
|
|
"loss": 6.3026,
|
|
"mean_token_accuracy": 0.15090568512678146,
|
|
"num_tokens": 10155983.0,
|
|
"step": 5185
|
|
},
|
|
{
|
|
"entropy": 6.474668788909912,
|
|
"epoch": 0.5188184135552557,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004980161894056464,
|
|
"loss": 6.2742,
|
|
"mean_token_accuracy": 0.14347012788057328,
|
|
"num_tokens": 10166183.0,
|
|
"step": 5190
|
|
},
|
|
{
|
|
"entropy": 6.434601736068726,
|
|
"epoch": 0.5193182386164842,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004980114578098618,
|
|
"loss": 6.1767,
|
|
"mean_token_accuracy": 0.1427476190030575,
|
|
"num_tokens": 10175524.0,
|
|
"step": 5195
|
|
},
|
|
{
|
|
"entropy": 6.493268632888794,
|
|
"epoch": 0.5198180636777128,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004980067206031663,
|
|
"loss": 6.3107,
|
|
"mean_token_accuracy": 0.13323971778154373,
|
|
"num_tokens": 10186235.0,
|
|
"step": 5200
|
|
},
|
|
{
|
|
"entropy": 6.546220159530639,
|
|
"epoch": 0.5203178887389414,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004980019777856791,
|
|
"loss": 6.3085,
|
|
"mean_token_accuracy": 0.1422312580049038,
|
|
"num_tokens": 10196166.0,
|
|
"step": 5205
|
|
},
|
|
{
|
|
"entropy": 6.449694967269897,
|
|
"epoch": 0.52081771380017,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004979972293575195,
|
|
"loss": 6.2382,
|
|
"mean_token_accuracy": 0.14611050486564636,
|
|
"num_tokens": 10205691.0,
|
|
"step": 5210
|
|
},
|
|
{
|
|
"entropy": 6.425623273849487,
|
|
"epoch": 0.5213175388613985,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004979924753188069,
|
|
"loss": 6.2086,
|
|
"mean_token_accuracy": 0.14596198126673698,
|
|
"num_tokens": 10216224.0,
|
|
"step": 5215
|
|
},
|
|
{
|
|
"entropy": 6.424330139160157,
|
|
"epoch": 0.5218173639226271,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004979877156696612,
|
|
"loss": 6.2295,
|
|
"mean_token_accuracy": 0.1465998724102974,
|
|
"num_tokens": 10226468.0,
|
|
"step": 5220
|
|
},
|
|
{
|
|
"entropy": 6.575912141799927,
|
|
"epoch": 0.5223171889838556,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004979829504102018,
|
|
"loss": 6.2764,
|
|
"mean_token_accuracy": 0.14345307424664497,
|
|
"num_tokens": 10235932.0,
|
|
"step": 5225
|
|
},
|
|
{
|
|
"entropy": 6.516261863708496,
|
|
"epoch": 0.5228170140450842,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004979781795405488,
|
|
"loss": 6.3639,
|
|
"mean_token_accuracy": 0.1411351665854454,
|
|
"num_tokens": 10246052.0,
|
|
"step": 5230
|
|
},
|
|
{
|
|
"entropy": 6.561315822601318,
|
|
"epoch": 0.5233168391063128,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004979734030608222,
|
|
"loss": 6.2724,
|
|
"mean_token_accuracy": 0.1478128671646118,
|
|
"num_tokens": 10255056.0,
|
|
"step": 5235
|
|
},
|
|
{
|
|
"entropy": 6.44011173248291,
|
|
"epoch": 0.5238166641675414,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004979686209711422,
|
|
"loss": 6.2522,
|
|
"mean_token_accuracy": 0.14555570483207703,
|
|
"num_tokens": 10265403.0,
|
|
"step": 5240
|
|
},
|
|
{
|
|
"entropy": 6.352910900115967,
|
|
"epoch": 0.5243164892287699,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000497963833271629,
|
|
"loss": 6.2061,
|
|
"mean_token_accuracy": 0.15292444676160813,
|
|
"num_tokens": 10275148.0,
|
|
"step": 5245
|
|
},
|
|
{
|
|
"entropy": 6.492708539962768,
|
|
"epoch": 0.5248163142899985,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004979590399624031,
|
|
"loss": 6.2561,
|
|
"mean_token_accuracy": 0.14439393132925032,
|
|
"num_tokens": 10285083.0,
|
|
"step": 5250
|
|
},
|
|
{
|
|
"entropy": 6.423582601547241,
|
|
"epoch": 0.5253161393512271,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004979542410435852,
|
|
"loss": 6.216,
|
|
"mean_token_accuracy": 0.1387999877333641,
|
|
"num_tokens": 10294466.0,
|
|
"step": 5255
|
|
},
|
|
{
|
|
"entropy": 6.508393669128418,
|
|
"epoch": 0.5258159644124556,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004979494365152959,
|
|
"loss": 6.3139,
|
|
"mean_token_accuracy": 0.13836781978607177,
|
|
"num_tokens": 10304333.0,
|
|
"step": 5260
|
|
},
|
|
{
|
|
"entropy": 6.501136064529419,
|
|
"epoch": 0.5263157894736842,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004979446263776562,
|
|
"loss": 6.2463,
|
|
"mean_token_accuracy": 0.14248027056455612,
|
|
"num_tokens": 10314880.0,
|
|
"step": 5265
|
|
},
|
|
{
|
|
"entropy": 6.464469003677368,
|
|
"epoch": 0.5268156145349128,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000497939810630787,
|
|
"loss": 6.2065,
|
|
"mean_token_accuracy": 0.1451038010418415,
|
|
"num_tokens": 10324060.0,
|
|
"step": 5270
|
|
},
|
|
{
|
|
"entropy": 6.37868218421936,
|
|
"epoch": 0.5273154395961414,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004979349892748096,
|
|
"loss": 6.3192,
|
|
"mean_token_accuracy": 0.1428627409040928,
|
|
"num_tokens": 10335248.0,
|
|
"step": 5275
|
|
},
|
|
{
|
|
"entropy": 6.446943569183349,
|
|
"epoch": 0.5278152646573699,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004979301623098452,
|
|
"loss": 6.1332,
|
|
"mean_token_accuracy": 0.15440346747636796,
|
|
"num_tokens": 10343974.0,
|
|
"step": 5280
|
|
},
|
|
{
|
|
"entropy": 6.47099871635437,
|
|
"epoch": 0.5283150897185985,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004979253297360153,
|
|
"loss": 6.2439,
|
|
"mean_token_accuracy": 0.1459724336862564,
|
|
"num_tokens": 10354037.0,
|
|
"step": 5285
|
|
},
|
|
{
|
|
"entropy": 6.445359754562378,
|
|
"epoch": 0.528814914779827,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004979204915534415,
|
|
"loss": 6.2953,
|
|
"mean_token_accuracy": 0.14339115396142005,
|
|
"num_tokens": 10364714.0,
|
|
"step": 5290
|
|
},
|
|
{
|
|
"entropy": 6.44316873550415,
|
|
"epoch": 0.5293147398410556,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004979156477622454,
|
|
"loss": 6.2646,
|
|
"mean_token_accuracy": 0.1449811987578869,
|
|
"num_tokens": 10373972.0,
|
|
"step": 5295
|
|
},
|
|
{
|
|
"entropy": 6.415341997146607,
|
|
"epoch": 0.5298145649022842,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004979107983625491,
|
|
"loss": 6.1693,
|
|
"mean_token_accuracy": 0.1506952553987503,
|
|
"num_tokens": 10382882.0,
|
|
"step": 5300
|
|
},
|
|
{
|
|
"entropy": 6.407958555221557,
|
|
"epoch": 0.5303143899635128,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004979059433544744,
|
|
"loss": 6.2219,
|
|
"mean_token_accuracy": 0.14825646877288817,
|
|
"num_tokens": 10392257.0,
|
|
"step": 5305
|
|
},
|
|
{
|
|
"entropy": 6.448230981826782,
|
|
"epoch": 0.5308142150247414,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004979010827381435,
|
|
"loss": 6.2795,
|
|
"mean_token_accuracy": 0.14600449651479722,
|
|
"num_tokens": 10401055.0,
|
|
"step": 5310
|
|
},
|
|
{
|
|
"entropy": 6.492560720443725,
|
|
"epoch": 0.5313140400859699,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004978962165136787,
|
|
"loss": 6.3526,
|
|
"mean_token_accuracy": 0.13936564922332764,
|
|
"num_tokens": 10411443.0,
|
|
"step": 5315
|
|
},
|
|
{
|
|
"entropy": 6.534284257888794,
|
|
"epoch": 0.5318138651471985,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004978913446812025,
|
|
"loss": 6.3428,
|
|
"mean_token_accuracy": 0.14371119439601898,
|
|
"num_tokens": 10422142.0,
|
|
"step": 5320
|
|
},
|
|
{
|
|
"entropy": 6.515093898773193,
|
|
"epoch": 0.532313690208427,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004978864672408374,
|
|
"loss": 6.2592,
|
|
"mean_token_accuracy": 0.14365993440151215,
|
|
"num_tokens": 10432454.0,
|
|
"step": 5325
|
|
},
|
|
{
|
|
"entropy": 6.421989154815674,
|
|
"epoch": 0.5328135152696556,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004978815841927061,
|
|
"loss": 6.2525,
|
|
"mean_token_accuracy": 0.14374485164880751,
|
|
"num_tokens": 10443625.0,
|
|
"step": 5330
|
|
},
|
|
{
|
|
"entropy": 6.5193106174469,
|
|
"epoch": 0.5333133403308842,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004978766955369315,
|
|
"loss": 6.3038,
|
|
"mean_token_accuracy": 0.1444941483438015,
|
|
"num_tokens": 10454055.0,
|
|
"step": 5335
|
|
},
|
|
{
|
|
"entropy": 6.388335418701172,
|
|
"epoch": 0.5338131653921128,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004978718012736367,
|
|
"loss": 6.1437,
|
|
"mean_token_accuracy": 0.15102465599775314,
|
|
"num_tokens": 10462683.0,
|
|
"step": 5340
|
|
},
|
|
{
|
|
"entropy": 6.3790459632873535,
|
|
"epoch": 0.5343129904533414,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004978669014029446,
|
|
"loss": 6.1853,
|
|
"mean_token_accuracy": 0.15175978988409042,
|
|
"num_tokens": 10471699.0,
|
|
"step": 5345
|
|
},
|
|
{
|
|
"entropy": 6.343296670913697,
|
|
"epoch": 0.5348128155145699,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004978619959249787,
|
|
"loss": 6.1187,
|
|
"mean_token_accuracy": 0.15506782457232476,
|
|
"num_tokens": 10480790.0,
|
|
"step": 5350
|
|
},
|
|
{
|
|
"entropy": 6.406260776519775,
|
|
"epoch": 0.5353126405757984,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004978570848398623,
|
|
"loss": 6.2206,
|
|
"mean_token_accuracy": 0.142399550229311,
|
|
"num_tokens": 10490202.0,
|
|
"step": 5355
|
|
},
|
|
{
|
|
"entropy": 6.423729515075683,
|
|
"epoch": 0.535812465637027,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000497852168147719,
|
|
"loss": 6.2603,
|
|
"mean_token_accuracy": 0.1435429960489273,
|
|
"num_tokens": 10499690.0,
|
|
"step": 5360
|
|
},
|
|
{
|
|
"entropy": 6.444197463989258,
|
|
"epoch": 0.5363122906982556,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004978472458486724,
|
|
"loss": 6.2321,
|
|
"mean_token_accuracy": 0.14401177167892457,
|
|
"num_tokens": 10510120.0,
|
|
"step": 5365
|
|
},
|
|
{
|
|
"entropy": 6.504869747161865,
|
|
"epoch": 0.5368121157594842,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004978423179428466,
|
|
"loss": 6.3725,
|
|
"mean_token_accuracy": 0.1378040425479412,
|
|
"num_tokens": 10520521.0,
|
|
"step": 5370
|
|
},
|
|
{
|
|
"entropy": 6.377797651290893,
|
|
"epoch": 0.5373119408207128,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004978373844303653,
|
|
"loss": 6.0614,
|
|
"mean_token_accuracy": 0.15365611091256143,
|
|
"num_tokens": 10530233.0,
|
|
"step": 5375
|
|
},
|
|
{
|
|
"entropy": 6.388729000091553,
|
|
"epoch": 0.5378117658819414,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004978324453113528,
|
|
"loss": 6.2021,
|
|
"mean_token_accuracy": 0.14688197374343873,
|
|
"num_tokens": 10539683.0,
|
|
"step": 5380
|
|
},
|
|
{
|
|
"entropy": 6.384079170227051,
|
|
"epoch": 0.5383115909431699,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004978275005859333,
|
|
"loss": 6.2265,
|
|
"mean_token_accuracy": 0.14789662063121795,
|
|
"num_tokens": 10549483.0,
|
|
"step": 5385
|
|
},
|
|
{
|
|
"entropy": 6.47556619644165,
|
|
"epoch": 0.5388114160043984,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004978225502542313,
|
|
"loss": 6.34,
|
|
"mean_token_accuracy": 0.13866292610764502,
|
|
"num_tokens": 10560464.0,
|
|
"step": 5390
|
|
},
|
|
{
|
|
"entropy": 6.476946926116943,
|
|
"epoch": 0.539311241065627,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004978175943163712,
|
|
"loss": 6.2428,
|
|
"mean_token_accuracy": 0.1488696701824665,
|
|
"num_tokens": 10568660.0,
|
|
"step": 5395
|
|
},
|
|
{
|
|
"entropy": 6.466958045959473,
|
|
"epoch": 0.5398110661268556,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004978126327724777,
|
|
"loss": 6.289,
|
|
"mean_token_accuracy": 0.14666010886430741,
|
|
"num_tokens": 10577304.0,
|
|
"step": 5400
|
|
},
|
|
{
|
|
"entropy": 6.428526496887207,
|
|
"epoch": 0.5403108911880842,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004978076656226758,
|
|
"loss": 6.1838,
|
|
"mean_token_accuracy": 0.15669340565800666,
|
|
"num_tokens": 10587591.0,
|
|
"step": 5405
|
|
},
|
|
{
|
|
"entropy": 6.43843789100647,
|
|
"epoch": 0.5408107162493128,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004978026928670902,
|
|
"loss": 6.1286,
|
|
"mean_token_accuracy": 0.14771923720836638,
|
|
"num_tokens": 10598591.0,
|
|
"step": 5410
|
|
},
|
|
{
|
|
"entropy": 6.400979900360108,
|
|
"epoch": 0.5413105413105413,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004977977145058463,
|
|
"loss": 6.1542,
|
|
"mean_token_accuracy": 0.14819953516125678,
|
|
"num_tokens": 10608842.0,
|
|
"step": 5415
|
|
},
|
|
{
|
|
"entropy": 6.435693693161011,
|
|
"epoch": 0.5418103663717699,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004977927305390693,
|
|
"loss": 6.2422,
|
|
"mean_token_accuracy": 0.15102696046233177,
|
|
"num_tokens": 10618812.0,
|
|
"step": 5420
|
|
},
|
|
{
|
|
"entropy": 6.4845438480377195,
|
|
"epoch": 0.5423101914329984,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004977877409668845,
|
|
"loss": 6.3625,
|
|
"mean_token_accuracy": 0.14045077338814735,
|
|
"num_tokens": 10629244.0,
|
|
"step": 5425
|
|
},
|
|
{
|
|
"entropy": 6.497104930877685,
|
|
"epoch": 0.542810016494227,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004977827457894174,
|
|
"loss": 6.3105,
|
|
"mean_token_accuracy": 0.13931018710136414,
|
|
"num_tokens": 10638931.0,
|
|
"step": 5430
|
|
},
|
|
{
|
|
"entropy": 6.44123330116272,
|
|
"epoch": 0.5433098415554556,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004977777450067937,
|
|
"loss": 6.1622,
|
|
"mean_token_accuracy": 0.1503096863627434,
|
|
"num_tokens": 10648754.0,
|
|
"step": 5435
|
|
},
|
|
{
|
|
"entropy": 6.368002653121948,
|
|
"epoch": 0.5438096666166842,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004977727386191393,
|
|
"loss": 6.1405,
|
|
"mean_token_accuracy": 0.15083228647708893,
|
|
"num_tokens": 10657716.0,
|
|
"step": 5440
|
|
},
|
|
{
|
|
"entropy": 6.392760848999023,
|
|
"epoch": 0.5443094916779128,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004977677266265802,
|
|
"loss": 6.1741,
|
|
"mean_token_accuracy": 0.14957669675350188,
|
|
"num_tokens": 10667621.0,
|
|
"step": 5445
|
|
},
|
|
{
|
|
"entropy": 6.423801469802856,
|
|
"epoch": 0.5448093167391413,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004977627090292424,
|
|
"loss": 6.1616,
|
|
"mean_token_accuracy": 0.1466075710952282,
|
|
"num_tokens": 10676640.0,
|
|
"step": 5450
|
|
},
|
|
{
|
|
"entropy": 6.386547374725342,
|
|
"epoch": 0.5453091418003698,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004977576858272521,
|
|
"loss": 6.2624,
|
|
"mean_token_accuracy": 0.14105069115757943,
|
|
"num_tokens": 10687034.0,
|
|
"step": 5455
|
|
},
|
|
{
|
|
"entropy": 6.424188661575317,
|
|
"epoch": 0.5458089668615984,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004977526570207358,
|
|
"loss": 6.1505,
|
|
"mean_token_accuracy": 0.1486357644200325,
|
|
"num_tokens": 10696234.0,
|
|
"step": 5460
|
|
},
|
|
{
|
|
"entropy": 6.357306289672851,
|
|
"epoch": 0.546308791922827,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004977476226098199,
|
|
"loss": 6.174,
|
|
"mean_token_accuracy": 0.15825203508138658,
|
|
"num_tokens": 10705733.0,
|
|
"step": 5465
|
|
},
|
|
{
|
|
"entropy": 6.452626752853393,
|
|
"epoch": 0.5468086169840556,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004977425825946312,
|
|
"loss": 6.2025,
|
|
"mean_token_accuracy": 0.1456859290599823,
|
|
"num_tokens": 10714628.0,
|
|
"step": 5470
|
|
},
|
|
{
|
|
"entropy": 6.504712104797363,
|
|
"epoch": 0.5473084420452842,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004977375369752964,
|
|
"loss": 6.3574,
|
|
"mean_token_accuracy": 0.1356508083641529,
|
|
"num_tokens": 10726120.0,
|
|
"step": 5475
|
|
},
|
|
{
|
|
"entropy": 6.428026485443115,
|
|
"epoch": 0.5478082671065128,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004977324857519425,
|
|
"loss": 6.2019,
|
|
"mean_token_accuracy": 0.1466704823076725,
|
|
"num_tokens": 10735976.0,
|
|
"step": 5480
|
|
},
|
|
{
|
|
"entropy": 6.4640013694763185,
|
|
"epoch": 0.5483080921677413,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004977274289246967,
|
|
"loss": 6.2781,
|
|
"mean_token_accuracy": 0.1415743499994278,
|
|
"num_tokens": 10745730.0,
|
|
"step": 5485
|
|
},
|
|
{
|
|
"entropy": 6.442827749252319,
|
|
"epoch": 0.5488079172289698,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004977223664936859,
|
|
"loss": 6.2149,
|
|
"mean_token_accuracy": 0.1492815963923931,
|
|
"num_tokens": 10755435.0,
|
|
"step": 5490
|
|
},
|
|
{
|
|
"entropy": 6.371844530105591,
|
|
"epoch": 0.5493077422901984,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004977172984590378,
|
|
"loss": 6.1079,
|
|
"mean_token_accuracy": 0.1523657664656639,
|
|
"num_tokens": 10765483.0,
|
|
"step": 5495
|
|
},
|
|
{
|
|
"entropy": 6.380004167556763,
|
|
"epoch": 0.549807567351427,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004977122248208798,
|
|
"loss": 6.1937,
|
|
"mean_token_accuracy": 0.15215383172035218,
|
|
"num_tokens": 10775034.0,
|
|
"step": 5500
|
|
},
|
|
{
|
|
"entropy": 6.3309595584869385,
|
|
"epoch": 0.5503073924126556,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004977071455793394,
|
|
"loss": 6.1585,
|
|
"mean_token_accuracy": 0.15155598968267442,
|
|
"num_tokens": 10784799.0,
|
|
"step": 5505
|
|
},
|
|
{
|
|
"entropy": 6.428274869918823,
|
|
"epoch": 0.5508072174738842,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004977020607345445,
|
|
"loss": 6.2542,
|
|
"mean_token_accuracy": 0.13817675560712814,
|
|
"num_tokens": 10794907.0,
|
|
"step": 5510
|
|
},
|
|
{
|
|
"entropy": 6.428401327133178,
|
|
"epoch": 0.5513070425351128,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004976969702866231,
|
|
"loss": 6.1521,
|
|
"mean_token_accuracy": 0.15460718870162965,
|
|
"num_tokens": 10804374.0,
|
|
"step": 5515
|
|
},
|
|
{
|
|
"entropy": 6.422916030883789,
|
|
"epoch": 0.5518068675963412,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004976918742357033,
|
|
"loss": 6.1853,
|
|
"mean_token_accuracy": 0.14841345995664595,
|
|
"num_tokens": 10814245.0,
|
|
"step": 5520
|
|
},
|
|
{
|
|
"entropy": 6.369015789031982,
|
|
"epoch": 0.5523066926575698,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004976867725819133,
|
|
"loss": 6.1965,
|
|
"mean_token_accuracy": 0.15178618505597113,
|
|
"num_tokens": 10824667.0,
|
|
"step": 5525
|
|
},
|
|
{
|
|
"entropy": 6.395843553543091,
|
|
"epoch": 0.5528065177187984,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004976816653253813,
|
|
"loss": 6.172,
|
|
"mean_token_accuracy": 0.14885421246290206,
|
|
"num_tokens": 10834890.0,
|
|
"step": 5530
|
|
},
|
|
{
|
|
"entropy": 6.408791017532349,
|
|
"epoch": 0.553306342780027,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004976765524662359,
|
|
"loss": 6.1477,
|
|
"mean_token_accuracy": 0.15529358461499215,
|
|
"num_tokens": 10844751.0,
|
|
"step": 5535
|
|
},
|
|
{
|
|
"entropy": 6.479263210296631,
|
|
"epoch": 0.5538061678412556,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004976714340046058,
|
|
"loss": 6.2688,
|
|
"mean_token_accuracy": 0.1512459084391594,
|
|
"num_tokens": 10854113.0,
|
|
"step": 5540
|
|
},
|
|
{
|
|
"entropy": 6.38036961555481,
|
|
"epoch": 0.5543059929024842,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004976663099406196,
|
|
"loss": 6.1083,
|
|
"mean_token_accuracy": 0.1507673144340515,
|
|
"num_tokens": 10863468.0,
|
|
"step": 5545
|
|
},
|
|
{
|
|
"entropy": 6.417061519622803,
|
|
"epoch": 0.5548058179637128,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004976611802744066,
|
|
"loss": 6.2324,
|
|
"mean_token_accuracy": 0.1521667256951332,
|
|
"num_tokens": 10873381.0,
|
|
"step": 5550
|
|
},
|
|
{
|
|
"entropy": 6.4708188533782955,
|
|
"epoch": 0.5553056430249412,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004976560450060954,
|
|
"loss": 6.1443,
|
|
"mean_token_accuracy": 0.15245285779237747,
|
|
"num_tokens": 10883457.0,
|
|
"step": 5555
|
|
},
|
|
{
|
|
"entropy": 6.2844969749450685,
|
|
"epoch": 0.5558054680861698,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004976509041358154,
|
|
"loss": 6.1316,
|
|
"mean_token_accuracy": 0.15327222198247908,
|
|
"num_tokens": 10892822.0,
|
|
"step": 5560
|
|
},
|
|
{
|
|
"entropy": 6.376227521896363,
|
|
"epoch": 0.5563052931473984,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000497645757663696,
|
|
"loss": 6.0839,
|
|
"mean_token_accuracy": 0.16154446303844452,
|
|
"num_tokens": 10901935.0,
|
|
"step": 5565
|
|
},
|
|
{
|
|
"entropy": 6.347236442565918,
|
|
"epoch": 0.556805118208627,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004976406055898665,
|
|
"loss": 6.1838,
|
|
"mean_token_accuracy": 0.14250542744994163,
|
|
"num_tokens": 10911863.0,
|
|
"step": 5570
|
|
},
|
|
{
|
|
"entropy": 6.374010705947876,
|
|
"epoch": 0.5573049432698556,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004976354479144568,
|
|
"loss": 6.1622,
|
|
"mean_token_accuracy": 0.14557452499866486,
|
|
"num_tokens": 10921196.0,
|
|
"step": 5575
|
|
},
|
|
{
|
|
"entropy": 6.435430908203125,
|
|
"epoch": 0.5578047683310842,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004976302846375965,
|
|
"loss": 6.132,
|
|
"mean_token_accuracy": 0.14937174171209336,
|
|
"num_tokens": 10931374.0,
|
|
"step": 5580
|
|
},
|
|
{
|
|
"entropy": 6.522235774993897,
|
|
"epoch": 0.5583045933923126,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004976251157594155,
|
|
"loss": 6.2753,
|
|
"mean_token_accuracy": 0.14256571829319,
|
|
"num_tokens": 10941002.0,
|
|
"step": 5585
|
|
},
|
|
{
|
|
"entropy": 6.445342969894409,
|
|
"epoch": 0.5588044184535412,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004976199412800437,
|
|
"loss": 6.2148,
|
|
"mean_token_accuracy": 0.1462072491645813,
|
|
"num_tokens": 10950602.0,
|
|
"step": 5590
|
|
},
|
|
{
|
|
"entropy": 6.382048845291138,
|
|
"epoch": 0.5593042435147698,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004976147611996118,
|
|
"loss": 6.1817,
|
|
"mean_token_accuracy": 0.14778511226177216,
|
|
"num_tokens": 10960363.0,
|
|
"step": 5595
|
|
},
|
|
{
|
|
"entropy": 6.43527193069458,
|
|
"epoch": 0.5598040685759984,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004976095755182496,
|
|
"loss": 6.2752,
|
|
"mean_token_accuracy": 0.14148695692420005,
|
|
"num_tokens": 10970179.0,
|
|
"step": 5600
|
|
},
|
|
{
|
|
"entropy": 6.3876708984375,
|
|
"epoch": 0.560303893637227,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004976043842360877,
|
|
"loss": 6.1898,
|
|
"mean_token_accuracy": 0.14226483702659606,
|
|
"num_tokens": 10980446.0,
|
|
"step": 5605
|
|
},
|
|
{
|
|
"entropy": 6.412945365905761,
|
|
"epoch": 0.5608037186984556,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000497599187353257,
|
|
"loss": 6.2172,
|
|
"mean_token_accuracy": 0.143201994150877,
|
|
"num_tokens": 10990883.0,
|
|
"step": 5610
|
|
},
|
|
{
|
|
"entropy": 6.466598033905029,
|
|
"epoch": 0.5613035437596842,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004975939848698879,
|
|
"loss": 6.1145,
|
|
"mean_token_accuracy": 0.15407094955444336,
|
|
"num_tokens": 11000956.0,
|
|
"step": 5615
|
|
},
|
|
{
|
|
"entropy": 6.383142566680908,
|
|
"epoch": 0.5618033688209126,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004975887767861113,
|
|
"loss": 6.1915,
|
|
"mean_token_accuracy": 0.1499265745282173,
|
|
"num_tokens": 11010873.0,
|
|
"step": 5620
|
|
},
|
|
{
|
|
"entropy": 6.400553226470947,
|
|
"epoch": 0.5623031938821412,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004975835631020585,
|
|
"loss": 6.1561,
|
|
"mean_token_accuracy": 0.1501181647181511,
|
|
"num_tokens": 11020192.0,
|
|
"step": 5625
|
|
},
|
|
{
|
|
"entropy": 6.396825790405273,
|
|
"epoch": 0.5628030189433698,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004975783438178605,
|
|
"loss": 6.1791,
|
|
"mean_token_accuracy": 0.14332359358668328,
|
|
"num_tokens": 11030466.0,
|
|
"step": 5630
|
|
},
|
|
{
|
|
"entropy": 6.38042106628418,
|
|
"epoch": 0.5633028440045984,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004975731189336487,
|
|
"loss": 6.1524,
|
|
"mean_token_accuracy": 0.15266245305538179,
|
|
"num_tokens": 11040309.0,
|
|
"step": 5635
|
|
},
|
|
{
|
|
"entropy": 6.402611923217774,
|
|
"epoch": 0.563802669065827,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004975678884495544,
|
|
"loss": 6.2249,
|
|
"mean_token_accuracy": 0.14522777497768402,
|
|
"num_tokens": 11049560.0,
|
|
"step": 5640
|
|
},
|
|
{
|
|
"entropy": 6.489155292510986,
|
|
"epoch": 0.5643024941270556,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004975626523657093,
|
|
"loss": 6.3017,
|
|
"mean_token_accuracy": 0.13924765810370446,
|
|
"num_tokens": 11059352.0,
|
|
"step": 5645
|
|
},
|
|
{
|
|
"entropy": 6.469867610931397,
|
|
"epoch": 0.564802319188284,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004975574106822451,
|
|
"loss": 6.2131,
|
|
"mean_token_accuracy": 0.15009221136569978,
|
|
"num_tokens": 11069159.0,
|
|
"step": 5650
|
|
},
|
|
{
|
|
"entropy": 6.420383310317993,
|
|
"epoch": 0.5653021442495126,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004975521633992938,
|
|
"loss": 6.2864,
|
|
"mean_token_accuracy": 0.14288507103919984,
|
|
"num_tokens": 11078960.0,
|
|
"step": 5655
|
|
},
|
|
{
|
|
"entropy": 6.345410537719727,
|
|
"epoch": 0.5658019693107412,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004975469105169873,
|
|
"loss": 6.1235,
|
|
"mean_token_accuracy": 0.15768041908740998,
|
|
"num_tokens": 11089408.0,
|
|
"step": 5660
|
|
},
|
|
{
|
|
"entropy": 6.484627294540405,
|
|
"epoch": 0.5663017943719698,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004975416520354579,
|
|
"loss": 6.2816,
|
|
"mean_token_accuracy": 0.14217357113957405,
|
|
"num_tokens": 11099485.0,
|
|
"step": 5665
|
|
},
|
|
{
|
|
"entropy": 6.472567987442017,
|
|
"epoch": 0.5668016194331984,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004975363879548377,
|
|
"loss": 6.2813,
|
|
"mean_token_accuracy": 0.15160842835903168,
|
|
"num_tokens": 11109568.0,
|
|
"step": 5670
|
|
},
|
|
{
|
|
"entropy": 6.539796590805054,
|
|
"epoch": 0.567301444494427,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004975311182752592,
|
|
"loss": 6.3548,
|
|
"mean_token_accuracy": 0.13486458957195283,
|
|
"num_tokens": 11119433.0,
|
|
"step": 5675
|
|
},
|
|
{
|
|
"entropy": 6.45374436378479,
|
|
"epoch": 0.5678012695556556,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004975258429968551,
|
|
"loss": 6.2547,
|
|
"mean_token_accuracy": 0.1414391130208969,
|
|
"num_tokens": 11130060.0,
|
|
"step": 5680
|
|
},
|
|
{
|
|
"entropy": 6.499431180953979,
|
|
"epoch": 0.568301094616884,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004975205621197581,
|
|
"loss": 6.322,
|
|
"mean_token_accuracy": 0.14436408877372742,
|
|
"num_tokens": 11140417.0,
|
|
"step": 5685
|
|
},
|
|
{
|
|
"entropy": 6.483169174194336,
|
|
"epoch": 0.5688009196781126,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004975152756441009,
|
|
"loss": 6.264,
|
|
"mean_token_accuracy": 0.1493012122809887,
|
|
"num_tokens": 11150830.0,
|
|
"step": 5690
|
|
},
|
|
{
|
|
"entropy": 6.367444610595703,
|
|
"epoch": 0.5693007447393412,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004975099835700166,
|
|
"loss": 6.0914,
|
|
"mean_token_accuracy": 0.15718345940113068,
|
|
"num_tokens": 11161057.0,
|
|
"step": 5695
|
|
},
|
|
{
|
|
"entropy": 6.362324380874634,
|
|
"epoch": 0.5698005698005698,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004975046858976386,
|
|
"loss": 6.1687,
|
|
"mean_token_accuracy": 0.14591417461633682,
|
|
"num_tokens": 11170182.0,
|
|
"step": 5700
|
|
},
|
|
{
|
|
"entropy": 6.3738373756408695,
|
|
"epoch": 0.5703003948617984,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004974993826270997,
|
|
"loss": 6.1104,
|
|
"mean_token_accuracy": 0.147789067029953,
|
|
"num_tokens": 11179962.0,
|
|
"step": 5705
|
|
},
|
|
{
|
|
"entropy": 6.406001186370849,
|
|
"epoch": 0.570800219923027,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004974940737585337,
|
|
"loss": 6.0505,
|
|
"mean_token_accuracy": 0.16331670731306075,
|
|
"num_tokens": 11189341.0,
|
|
"step": 5710
|
|
},
|
|
{
|
|
"entropy": 6.34999189376831,
|
|
"epoch": 0.5713000449842555,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000497488759292074,
|
|
"loss": 6.1981,
|
|
"mean_token_accuracy": 0.1564978390932083,
|
|
"num_tokens": 11199264.0,
|
|
"step": 5715
|
|
},
|
|
{
|
|
"entropy": 6.320228910446167,
|
|
"epoch": 0.571799870045484,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004974834392278545,
|
|
"loss": 6.199,
|
|
"mean_token_accuracy": 0.15573666393756866,
|
|
"num_tokens": 11209257.0,
|
|
"step": 5720
|
|
},
|
|
{
|
|
"entropy": 6.453316259384155,
|
|
"epoch": 0.5722996951067126,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004974781135660088,
|
|
"loss": 6.255,
|
|
"mean_token_accuracy": 0.14868643283843994,
|
|
"num_tokens": 11218294.0,
|
|
"step": 5725
|
|
},
|
|
{
|
|
"entropy": 6.35547194480896,
|
|
"epoch": 0.5727995201679412,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004974727823066709,
|
|
"loss": 6.0812,
|
|
"mean_token_accuracy": 0.1533886343240738,
|
|
"num_tokens": 11227684.0,
|
|
"step": 5730
|
|
},
|
|
{
|
|
"entropy": 6.45539698600769,
|
|
"epoch": 0.5732993452291698,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004974674454499753,
|
|
"loss": 6.2986,
|
|
"mean_token_accuracy": 0.13858716040849686,
|
|
"num_tokens": 11237195.0,
|
|
"step": 5735
|
|
},
|
|
{
|
|
"entropy": 6.5260608196258545,
|
|
"epoch": 0.5737991702903984,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004974621029960559,
|
|
"loss": 6.2493,
|
|
"mean_token_accuracy": 0.14635457396507262,
|
|
"num_tokens": 11246871.0,
|
|
"step": 5740
|
|
},
|
|
{
|
|
"entropy": 6.434552001953125,
|
|
"epoch": 0.574298995351627,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004974567549450472,
|
|
"loss": 6.1166,
|
|
"mean_token_accuracy": 0.15176171213388442,
|
|
"num_tokens": 11256298.0,
|
|
"step": 5745
|
|
},
|
|
{
|
|
"entropy": 6.430844736099243,
|
|
"epoch": 0.5747988204128555,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004974514012970839,
|
|
"loss": 6.2957,
|
|
"mean_token_accuracy": 0.14615521505475043,
|
|
"num_tokens": 11265857.0,
|
|
"step": 5750
|
|
},
|
|
{
|
|
"entropy": 6.362429904937744,
|
|
"epoch": 0.575298645474084,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004974460420523005,
|
|
"loss": 6.0778,
|
|
"mean_token_accuracy": 0.15784539580345153,
|
|
"num_tokens": 11275406.0,
|
|
"step": 5755
|
|
},
|
|
{
|
|
"entropy": 6.41445484161377,
|
|
"epoch": 0.5757984705353126,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004974406772108319,
|
|
"loss": 6.0761,
|
|
"mean_token_accuracy": 0.15416193678975104,
|
|
"num_tokens": 11283910.0,
|
|
"step": 5760
|
|
},
|
|
{
|
|
"entropy": 6.401713132858276,
|
|
"epoch": 0.5762982955965412,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004974353067728132,
|
|
"loss": 6.1497,
|
|
"mean_token_accuracy": 0.14307589083909988,
|
|
"num_tokens": 11293808.0,
|
|
"step": 5765
|
|
},
|
|
{
|
|
"entropy": 6.411474323272705,
|
|
"epoch": 0.5767981206577698,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004974299307383794,
|
|
"loss": 6.1918,
|
|
"mean_token_accuracy": 0.1455647498369217,
|
|
"num_tokens": 11302519.0,
|
|
"step": 5770
|
|
},
|
|
{
|
|
"entropy": 6.461847305297852,
|
|
"epoch": 0.5772979457189984,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004974245491076656,
|
|
"loss": 6.2883,
|
|
"mean_token_accuracy": 0.14553347378969192,
|
|
"num_tokens": 11312609.0,
|
|
"step": 5775
|
|
},
|
|
{
|
|
"entropy": 6.460581731796265,
|
|
"epoch": 0.5777977707802269,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004974191618808075,
|
|
"loss": 6.2231,
|
|
"mean_token_accuracy": 0.14999218359589578,
|
|
"num_tokens": 11322471.0,
|
|
"step": 5780
|
|
},
|
|
{
|
|
"entropy": 6.489849090576172,
|
|
"epoch": 0.5782975958414555,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004974137690579405,
|
|
"loss": 6.2189,
|
|
"mean_token_accuracy": 0.14874884039163588,
|
|
"num_tokens": 11333332.0,
|
|
"step": 5785
|
|
},
|
|
{
|
|
"entropy": 6.405481672286987,
|
|
"epoch": 0.578797420902684,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004974083706392004,
|
|
"loss": 6.2115,
|
|
"mean_token_accuracy": 0.14520230516791344,
|
|
"num_tokens": 11342952.0,
|
|
"step": 5790
|
|
},
|
|
{
|
|
"entropy": 6.403951978683471,
|
|
"epoch": 0.5792972459639126,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004974029666247228,
|
|
"loss": 6.292,
|
|
"mean_token_accuracy": 0.14103597924113273,
|
|
"num_tokens": 11353509.0,
|
|
"step": 5795
|
|
},
|
|
{
|
|
"entropy": 6.534165239334106,
|
|
"epoch": 0.5797970710251412,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004973975570146438,
|
|
"loss": 6.2846,
|
|
"mean_token_accuracy": 0.14150195941329002,
|
|
"num_tokens": 11363065.0,
|
|
"step": 5800
|
|
},
|
|
{
|
|
"entropy": 6.369716548919678,
|
|
"epoch": 0.5802968960863698,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004973921418090997,
|
|
"loss": 6.1528,
|
|
"mean_token_accuracy": 0.1501327022910118,
|
|
"num_tokens": 11373720.0,
|
|
"step": 5805
|
|
},
|
|
{
|
|
"entropy": 6.3334290981292725,
|
|
"epoch": 0.5807967211475984,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004973867210082263,
|
|
"loss": 6.1558,
|
|
"mean_token_accuracy": 0.15207915008068085,
|
|
"num_tokens": 11384432.0,
|
|
"step": 5810
|
|
},
|
|
{
|
|
"entropy": 6.435679340362549,
|
|
"epoch": 0.5812965462088269,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004973812946121603,
|
|
"loss": 6.3084,
|
|
"mean_token_accuracy": 0.14357167333364487,
|
|
"num_tokens": 11394100.0,
|
|
"step": 5815
|
|
},
|
|
{
|
|
"entropy": 6.392176246643066,
|
|
"epoch": 0.5817963712700555,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004973758626210382,
|
|
"loss": 6.1979,
|
|
"mean_token_accuracy": 0.14371618926525115,
|
|
"num_tokens": 11403359.0,
|
|
"step": 5820
|
|
},
|
|
{
|
|
"entropy": 6.464417791366577,
|
|
"epoch": 0.582296196331284,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004973704250349965,
|
|
"loss": 6.2106,
|
|
"mean_token_accuracy": 0.1430139996111393,
|
|
"num_tokens": 11412921.0,
|
|
"step": 5825
|
|
},
|
|
{
|
|
"entropy": 6.407368803024292,
|
|
"epoch": 0.5827960213925126,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004973649818541722,
|
|
"loss": 6.1908,
|
|
"mean_token_accuracy": 0.14863360822200775,
|
|
"num_tokens": 11422459.0,
|
|
"step": 5830
|
|
},
|
|
{
|
|
"entropy": 6.36591362953186,
|
|
"epoch": 0.5832958464537412,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004973595330787022,
|
|
"loss": 6.136,
|
|
"mean_token_accuracy": 0.14982437193393708,
|
|
"num_tokens": 11431517.0,
|
|
"step": 5835
|
|
},
|
|
{
|
|
"entropy": 6.445391035079956,
|
|
"epoch": 0.5837956715149698,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004973540787087235,
|
|
"loss": 6.1754,
|
|
"mean_token_accuracy": 0.14735695570707322,
|
|
"num_tokens": 11440662.0,
|
|
"step": 5840
|
|
},
|
|
{
|
|
"entropy": 6.367056179046631,
|
|
"epoch": 0.5842954965761983,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004973486187443734,
|
|
"loss": 6.0289,
|
|
"mean_token_accuracy": 0.16187193095684052,
|
|
"num_tokens": 11449762.0,
|
|
"step": 5845
|
|
},
|
|
{
|
|
"entropy": 6.292886066436767,
|
|
"epoch": 0.5847953216374269,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004973431531857893,
|
|
"loss": 6.0315,
|
|
"mean_token_accuracy": 0.15769076347351074,
|
|
"num_tokens": 11459963.0,
|
|
"step": 5850
|
|
},
|
|
{
|
|
"entropy": 6.4106189727783205,
|
|
"epoch": 0.5852951466986555,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004973376820331087,
|
|
"loss": 6.2113,
|
|
"mean_token_accuracy": 0.14407769367098808,
|
|
"num_tokens": 11469063.0,
|
|
"step": 5855
|
|
},
|
|
{
|
|
"entropy": 6.413491582870483,
|
|
"epoch": 0.585794971759884,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004973322052864692,
|
|
"loss": 6.1149,
|
|
"mean_token_accuracy": 0.15207016319036484,
|
|
"num_tokens": 11477651.0,
|
|
"step": 5860
|
|
},
|
|
{
|
|
"entropy": 6.439757919311523,
|
|
"epoch": 0.5862947968211126,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004973267229460087,
|
|
"loss": 6.3233,
|
|
"mean_token_accuracy": 0.13958670869469642,
|
|
"num_tokens": 11487248.0,
|
|
"step": 5865
|
|
},
|
|
{
|
|
"entropy": 6.4254437446594235,
|
|
"epoch": 0.5867946218823412,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000497321235011865,
|
|
"loss": 6.2761,
|
|
"mean_token_accuracy": 0.1482052683830261,
|
|
"num_tokens": 11497066.0,
|
|
"step": 5870
|
|
},
|
|
{
|
|
"entropy": 6.509588432312012,
|
|
"epoch": 0.5872944469435698,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004973157414841763,
|
|
"loss": 6.2506,
|
|
"mean_token_accuracy": 0.14056255891919137,
|
|
"num_tokens": 11508490.0,
|
|
"step": 5875
|
|
},
|
|
{
|
|
"entropy": 6.468327188491822,
|
|
"epoch": 0.5877942720047983,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004973102423630806,
|
|
"loss": 6.2349,
|
|
"mean_token_accuracy": 0.14740702211856843,
|
|
"num_tokens": 11518851.0,
|
|
"step": 5880
|
|
},
|
|
{
|
|
"entropy": 6.401625251770019,
|
|
"epoch": 0.5882940970660269,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004973047376487166,
|
|
"loss": 6.1816,
|
|
"mean_token_accuracy": 0.150423264503479,
|
|
"num_tokens": 11529102.0,
|
|
"step": 5885
|
|
},
|
|
{
|
|
"entropy": 6.372255086898804,
|
|
"epoch": 0.5887939221272555,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004972992273412224,
|
|
"loss": 6.2182,
|
|
"mean_token_accuracy": 0.14426240026950837,
|
|
"num_tokens": 11540563.0,
|
|
"step": 5890
|
|
},
|
|
{
|
|
"entropy": 6.3703391551971436,
|
|
"epoch": 0.589293747188484,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004972937114407369,
|
|
"loss": 6.1403,
|
|
"mean_token_accuracy": 0.1549333855509758,
|
|
"num_tokens": 11549955.0,
|
|
"step": 5895
|
|
},
|
|
{
|
|
"entropy": 6.40195665359497,
|
|
"epoch": 0.5897935722497126,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000497288189947399,
|
|
"loss": 6.1181,
|
|
"mean_token_accuracy": 0.1515316516160965,
|
|
"num_tokens": 11558932.0,
|
|
"step": 5900
|
|
},
|
|
{
|
|
"entropy": 6.308910465240478,
|
|
"epoch": 0.5902933973109412,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004972826628613472,
|
|
"loss": 6.1271,
|
|
"mean_token_accuracy": 0.15501016229391099,
|
|
"num_tokens": 11568901.0,
|
|
"step": 5905
|
|
},
|
|
{
|
|
"entropy": 6.437039089202881,
|
|
"epoch": 0.5907932223721697,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004972771301827209,
|
|
"loss": 6.1912,
|
|
"mean_token_accuracy": 0.14727447926998138,
|
|
"num_tokens": 11579738.0,
|
|
"step": 5910
|
|
},
|
|
{
|
|
"entropy": 6.4059497833251955,
|
|
"epoch": 0.5912930474333983,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004972715919116592,
|
|
"loss": 6.1518,
|
|
"mean_token_accuracy": 0.1520642265677452,
|
|
"num_tokens": 11590293.0,
|
|
"step": 5915
|
|
},
|
|
{
|
|
"entropy": 6.389673900604248,
|
|
"epoch": 0.5917928724946269,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004972660480483015,
|
|
"loss": 6.2351,
|
|
"mean_token_accuracy": 0.1434284321963787,
|
|
"num_tokens": 11599745.0,
|
|
"step": 5920
|
|
},
|
|
{
|
|
"entropy": 6.437257289886475,
|
|
"epoch": 0.5922926975558555,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004972604985927871,
|
|
"loss": 6.2199,
|
|
"mean_token_accuracy": 0.14112672805786133,
|
|
"num_tokens": 11609958.0,
|
|
"step": 5925
|
|
},
|
|
{
|
|
"entropy": 6.457437992095947,
|
|
"epoch": 0.592792522617084,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004972549435452558,
|
|
"loss": 6.2125,
|
|
"mean_token_accuracy": 0.14297294169664382,
|
|
"num_tokens": 11619941.0,
|
|
"step": 5930
|
|
},
|
|
{
|
|
"entropy": 6.411074447631836,
|
|
"epoch": 0.5932923476783126,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004972493829058474,
|
|
"loss": 6.0894,
|
|
"mean_token_accuracy": 0.15717873275279998,
|
|
"num_tokens": 11630287.0,
|
|
"step": 5935
|
|
},
|
|
{
|
|
"entropy": 6.387608861923217,
|
|
"epoch": 0.5937921727395412,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004972438166747016,
|
|
"loss": 6.1421,
|
|
"mean_token_accuracy": 0.14942783191800119,
|
|
"num_tokens": 11639806.0,
|
|
"step": 5940
|
|
},
|
|
{
|
|
"entropy": 6.374695730209351,
|
|
"epoch": 0.5942919978007697,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004972382448519586,
|
|
"loss": 6.2379,
|
|
"mean_token_accuracy": 0.14599600732326506,
|
|
"num_tokens": 11650132.0,
|
|
"step": 5945
|
|
},
|
|
{
|
|
"entropy": 6.424087762832642,
|
|
"epoch": 0.5947918228619983,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004972326674377586,
|
|
"loss": 6.161,
|
|
"mean_token_accuracy": 0.14550729915499688,
|
|
"num_tokens": 11659670.0,
|
|
"step": 5950
|
|
},
|
|
{
|
|
"entropy": 6.427029752731324,
|
|
"epoch": 0.5952916479232269,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004972270844322418,
|
|
"loss": 6.1978,
|
|
"mean_token_accuracy": 0.1531231015920639,
|
|
"num_tokens": 11669998.0,
|
|
"step": 5955
|
|
},
|
|
{
|
|
"entropy": 6.402192211151123,
|
|
"epoch": 0.5957914729844555,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004972214958355488,
|
|
"loss": 6.2097,
|
|
"mean_token_accuracy": 0.14409659951925277,
|
|
"num_tokens": 11679052.0,
|
|
"step": 5960
|
|
},
|
|
{
|
|
"entropy": 6.398138427734375,
|
|
"epoch": 0.596291298045684,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004972159016478201,
|
|
"loss": 6.1735,
|
|
"mean_token_accuracy": 0.1523020088672638,
|
|
"num_tokens": 11687957.0,
|
|
"step": 5965
|
|
},
|
|
{
|
|
"entropy": 6.407905435562133,
|
|
"epoch": 0.5967911231069126,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004972103018691965,
|
|
"loss": 6.1189,
|
|
"mean_token_accuracy": 0.15084125101566315,
|
|
"num_tokens": 11696922.0,
|
|
"step": 5970
|
|
},
|
|
{
|
|
"entropy": 6.357454299926758,
|
|
"epoch": 0.5972909481681411,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004972046964998189,
|
|
"loss": 6.0937,
|
|
"mean_token_accuracy": 0.1565779283642769,
|
|
"num_tokens": 11706600.0,
|
|
"step": 5975
|
|
},
|
|
{
|
|
"entropy": 6.358139848709106,
|
|
"epoch": 0.5977907732293697,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004971990855398283,
|
|
"loss": 6.154,
|
|
"mean_token_accuracy": 0.1468999430537224,
|
|
"num_tokens": 11715933.0,
|
|
"step": 5980
|
|
},
|
|
{
|
|
"entropy": 6.39614429473877,
|
|
"epoch": 0.5982905982905983,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004971934689893658,
|
|
"loss": 6.0974,
|
|
"mean_token_accuracy": 0.1552150011062622,
|
|
"num_tokens": 11724807.0,
|
|
"step": 5985
|
|
},
|
|
{
|
|
"entropy": 6.429772758483887,
|
|
"epoch": 0.5987904233518269,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004971878468485729,
|
|
"loss": 6.1776,
|
|
"mean_token_accuracy": 0.14787413328886032,
|
|
"num_tokens": 11734985.0,
|
|
"step": 5990
|
|
},
|
|
{
|
|
"entropy": 6.373316287994385,
|
|
"epoch": 0.5992902484130554,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000497182219117591,
|
|
"loss": 6.1633,
|
|
"mean_token_accuracy": 0.1456233836710453,
|
|
"num_tokens": 11743418.0,
|
|
"step": 5995
|
|
},
|
|
{
|
|
"entropy": 6.3798729419708256,
|
|
"epoch": 0.599790073474284,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004971765857965615,
|
|
"loss": 6.102,
|
|
"mean_token_accuracy": 0.1504545032978058,
|
|
"num_tokens": 11752953.0,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"epoch": 0.599790073474284,
|
|
"eval_entropy": 6.190445968030317,
|
|
"eval_loss": 6.201533794403076,
|
|
"eval_mean_token_accuracy": 0.15422710121331626,
|
|
"eval_num_tokens": 11752953.0,
|
|
"eval_runtime": 18.1743,
|
|
"eval_samples_per_second": 1708.18,
|
|
"eval_steps_per_second": 213.543,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"entropy": 6.414371156692505,
|
|
"epoch": 0.6002898985355126,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004971709468856263,
|
|
"loss": 6.2484,
|
|
"mean_token_accuracy": 0.1458593115210533,
|
|
"num_tokens": 11763260.0,
|
|
"step": 6005
|
|
},
|
|
{
|
|
"entropy": 6.304040479660034,
|
|
"epoch": 0.6007897235967411,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004971653023849274,
|
|
"loss": 6.0209,
|
|
"mean_token_accuracy": 0.16909098103642464,
|
|
"num_tokens": 11773255.0,
|
|
"step": 6010
|
|
},
|
|
{
|
|
"entropy": 6.384859848022461,
|
|
"epoch": 0.6012895486579697,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004971596522946065,
|
|
"loss": 6.1636,
|
|
"mean_token_accuracy": 0.14832017049193383,
|
|
"num_tokens": 11783443.0,
|
|
"step": 6015
|
|
},
|
|
{
|
|
"entropy": 6.317033958435059,
|
|
"epoch": 0.6017893737191983,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004971539966148059,
|
|
"loss": 6.1204,
|
|
"mean_token_accuracy": 0.15199731811881065,
|
|
"num_tokens": 11791932.0,
|
|
"step": 6020
|
|
},
|
|
{
|
|
"entropy": 6.357777881622314,
|
|
"epoch": 0.6022891987804269,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004971483353456681,
|
|
"loss": 6.0974,
|
|
"mean_token_accuracy": 0.15433032661676407,
|
|
"num_tokens": 11801420.0,
|
|
"step": 6025
|
|
},
|
|
{
|
|
"entropy": 6.431672286987305,
|
|
"epoch": 0.6027890238416554,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004971426684873352,
|
|
"loss": 6.2544,
|
|
"mean_token_accuracy": 0.14638083875179292,
|
|
"num_tokens": 11810977.0,
|
|
"step": 6030
|
|
},
|
|
{
|
|
"entropy": 6.361601877212524,
|
|
"epoch": 0.603288848902884,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004971369960399499,
|
|
"loss": 6.0536,
|
|
"mean_token_accuracy": 0.1578028455376625,
|
|
"num_tokens": 11821016.0,
|
|
"step": 6035
|
|
},
|
|
{
|
|
"entropy": 6.3685469150543215,
|
|
"epoch": 0.6037886739641125,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000497131318003655,
|
|
"loss": 6.2039,
|
|
"mean_token_accuracy": 0.14420628547668457,
|
|
"num_tokens": 11831157.0,
|
|
"step": 6040
|
|
},
|
|
{
|
|
"entropy": 6.346438884735107,
|
|
"epoch": 0.6042884990253411,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004971256343785932,
|
|
"loss": 6.1101,
|
|
"mean_token_accuracy": 0.15514256656169892,
|
|
"num_tokens": 11840319.0,
|
|
"step": 6045
|
|
},
|
|
{
|
|
"entropy": 6.4193297863006595,
|
|
"epoch": 0.6047883240865697,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004971199451649078,
|
|
"loss": 6.2462,
|
|
"mean_token_accuracy": 0.1454211428761482,
|
|
"num_tokens": 11850808.0,
|
|
"step": 6050
|
|
},
|
|
{
|
|
"entropy": 6.488301753997803,
|
|
"epoch": 0.6052881491477983,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004971142503627415,
|
|
"loss": 6.2771,
|
|
"mean_token_accuracy": 0.14777473211288453,
|
|
"num_tokens": 11861123.0,
|
|
"step": 6055
|
|
},
|
|
{
|
|
"entropy": 6.30822229385376,
|
|
"epoch": 0.6057879742090269,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.000497108549972238,
|
|
"loss": 6.0222,
|
|
"mean_token_accuracy": 0.16141136288642882,
|
|
"num_tokens": 11870308.0,
|
|
"step": 6060
|
|
},
|
|
{
|
|
"entropy": 6.443945360183716,
|
|
"epoch": 0.6062877992702554,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004971028439935404,
|
|
"loss": 6.1644,
|
|
"mean_token_accuracy": 0.1443210080265999,
|
|
"num_tokens": 11880254.0,
|
|
"step": 6065
|
|
},
|
|
{
|
|
"entropy": 6.410022115707397,
|
|
"epoch": 0.606787624331484,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004970971324267925,
|
|
"loss": 6.1608,
|
|
"mean_token_accuracy": 0.15488466769456863,
|
|
"num_tokens": 11891272.0,
|
|
"step": 6070
|
|
},
|
|
{
|
|
"entropy": 6.310713243484497,
|
|
"epoch": 0.6072874493927125,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004970914152721378,
|
|
"loss": 6.1808,
|
|
"mean_token_accuracy": 0.14843776524066926,
|
|
"num_tokens": 11901176.0,
|
|
"step": 6075
|
|
},
|
|
{
|
|
"entropy": 6.418321180343628,
|
|
"epoch": 0.6077872744539411,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004970856925297204,
|
|
"loss": 6.1982,
|
|
"mean_token_accuracy": 0.14708398804068565,
|
|
"num_tokens": 11910820.0,
|
|
"step": 6080
|
|
},
|
|
{
|
|
"entropy": 6.421906614303589,
|
|
"epoch": 0.6082870995151697,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000497079964199684,
|
|
"loss": 6.1611,
|
|
"mean_token_accuracy": 0.1443112276494503,
|
|
"num_tokens": 11920458.0,
|
|
"step": 6085
|
|
},
|
|
{
|
|
"entropy": 6.283801746368408,
|
|
"epoch": 0.6087869245763983,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004970742302821729,
|
|
"loss": 5.9987,
|
|
"mean_token_accuracy": 0.15824998021125794,
|
|
"num_tokens": 11931150.0,
|
|
"step": 6090
|
|
},
|
|
{
|
|
"entropy": 6.341992807388306,
|
|
"epoch": 0.6092867496376269,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004970684907773312,
|
|
"loss": 6.12,
|
|
"mean_token_accuracy": 0.15010675191879272,
|
|
"num_tokens": 11939960.0,
|
|
"step": 6095
|
|
},
|
|
{
|
|
"entropy": 6.450232076644897,
|
|
"epoch": 0.6097865746988554,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004970627456853036,
|
|
"loss": 6.2644,
|
|
"mean_token_accuracy": 0.14708733037114144,
|
|
"num_tokens": 11950781.0,
|
|
"step": 6100
|
|
},
|
|
{
|
|
"entropy": 6.437028884887695,
|
|
"epoch": 0.6102863997600839,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004970569950062343,
|
|
"loss": 6.1299,
|
|
"mean_token_accuracy": 0.152546326816082,
|
|
"num_tokens": 11960489.0,
|
|
"step": 6105
|
|
},
|
|
{
|
|
"entropy": 6.409123706817627,
|
|
"epoch": 0.6107862248213125,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004970512387402682,
|
|
"loss": 6.1653,
|
|
"mean_token_accuracy": 0.15546404644846917,
|
|
"num_tokens": 11970651.0,
|
|
"step": 6110
|
|
},
|
|
{
|
|
"entropy": 6.289830303192138,
|
|
"epoch": 0.6112860498825411,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004970454768875501,
|
|
"loss": 6.1354,
|
|
"mean_token_accuracy": 0.15251707658171654,
|
|
"num_tokens": 11980349.0,
|
|
"step": 6115
|
|
},
|
|
{
|
|
"entropy": 6.353547525405884,
|
|
"epoch": 0.6117858749437697,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004970397094482249,
|
|
"loss": 6.1631,
|
|
"mean_token_accuracy": 0.15197541415691376,
|
|
"num_tokens": 11990076.0,
|
|
"step": 6120
|
|
},
|
|
{
|
|
"entropy": 6.347495079040527,
|
|
"epoch": 0.6122857000049983,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004970339364224378,
|
|
"loss": 6.0802,
|
|
"mean_token_accuracy": 0.16009331941604615,
|
|
"num_tokens": 11999515.0,
|
|
"step": 6125
|
|
},
|
|
{
|
|
"entropy": 6.420997190475464,
|
|
"epoch": 0.6127855250662269,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004970281578103339,
|
|
"loss": 6.1992,
|
|
"mean_token_accuracy": 0.14599146842956542,
|
|
"num_tokens": 12009224.0,
|
|
"step": 6130
|
|
},
|
|
{
|
|
"entropy": 6.327088117599487,
|
|
"epoch": 0.6132853501274554,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004970223736120587,
|
|
"loss": 6.0934,
|
|
"mean_token_accuracy": 0.15674970299005508,
|
|
"num_tokens": 12019295.0,
|
|
"step": 6135
|
|
},
|
|
{
|
|
"entropy": 6.397483015060425,
|
|
"epoch": 0.6137851751886839,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004970165838277578,
|
|
"loss": 6.1744,
|
|
"mean_token_accuracy": 0.14948792681097983,
|
|
"num_tokens": 12029130.0,
|
|
"step": 6140
|
|
},
|
|
{
|
|
"entropy": 6.382640838623047,
|
|
"epoch": 0.6142850002499125,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004970107884575767,
|
|
"loss": 6.1415,
|
|
"mean_token_accuracy": 0.1544598527252674,
|
|
"num_tokens": 12038676.0,
|
|
"step": 6145
|
|
},
|
|
{
|
|
"entropy": 6.411570501327515,
|
|
"epoch": 0.6147848253111411,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004970049875016613,
|
|
"loss": 6.0955,
|
|
"mean_token_accuracy": 0.16193794459104538,
|
|
"num_tokens": 12048089.0,
|
|
"step": 6150
|
|
},
|
|
{
|
|
"entropy": 6.379500150680542,
|
|
"epoch": 0.6152846503723697,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004969991809601576,
|
|
"loss": 6.1842,
|
|
"mean_token_accuracy": 0.1491437926888466,
|
|
"num_tokens": 12059531.0,
|
|
"step": 6155
|
|
},
|
|
{
|
|
"entropy": 6.412176322937012,
|
|
"epoch": 0.6157844754335983,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004969933688332115,
|
|
"loss": 6.1891,
|
|
"mean_token_accuracy": 0.14602637887001038,
|
|
"num_tokens": 12070103.0,
|
|
"step": 6160
|
|
},
|
|
{
|
|
"entropy": 6.351621532440186,
|
|
"epoch": 0.6162843004948269,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004969875511209694,
|
|
"loss": 6.167,
|
|
"mean_token_accuracy": 0.14610393717885017,
|
|
"num_tokens": 12078481.0,
|
|
"step": 6165
|
|
},
|
|
{
|
|
"entropy": 6.401747369766236,
|
|
"epoch": 0.6167841255560553,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004969817278235777,
|
|
"loss": 6.2561,
|
|
"mean_token_accuracy": 0.1471801958978176,
|
|
"num_tokens": 12088875.0,
|
|
"step": 6170
|
|
},
|
|
{
|
|
"entropy": 6.435576868057251,
|
|
"epoch": 0.6172839506172839,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004969758989411829,
|
|
"loss": 6.1621,
|
|
"mean_token_accuracy": 0.14885308817029,
|
|
"num_tokens": 12099769.0,
|
|
"step": 6175
|
|
},
|
|
{
|
|
"entropy": 6.451336288452149,
|
|
"epoch": 0.6177837756785125,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004969700644739315,
|
|
"loss": 6.1266,
|
|
"mean_token_accuracy": 0.15046553462743759,
|
|
"num_tokens": 12109334.0,
|
|
"step": 6180
|
|
},
|
|
{
|
|
"entropy": 6.3981605052948,
|
|
"epoch": 0.6182836007397411,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004969642244219705,
|
|
"loss": 6.1376,
|
|
"mean_token_accuracy": 0.1497718021273613,
|
|
"num_tokens": 12119017.0,
|
|
"step": 6185
|
|
},
|
|
{
|
|
"entropy": 6.281883335113525,
|
|
"epoch": 0.6187834258009697,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004969583787854467,
|
|
"loss": 6.0423,
|
|
"mean_token_accuracy": 0.16523782461881636,
|
|
"num_tokens": 12128002.0,
|
|
"step": 6190
|
|
},
|
|
{
|
|
"entropy": 6.386834239959716,
|
|
"epoch": 0.6192832508621983,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004969525275645071,
|
|
"loss": 6.1505,
|
|
"mean_token_accuracy": 0.14462432786822318,
|
|
"num_tokens": 12137802.0,
|
|
"step": 6195
|
|
},
|
|
{
|
|
"entropy": 6.300003099441528,
|
|
"epoch": 0.6197830759234269,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004969466707592991,
|
|
"loss": 6.1093,
|
|
"mean_token_accuracy": 0.15344394445419313,
|
|
"num_tokens": 12147270.0,
|
|
"step": 6200
|
|
},
|
|
{
|
|
"entropy": 6.36989016532898,
|
|
"epoch": 0.6202829009846553,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00049694080836997,
|
|
"loss": 6.1736,
|
|
"mean_token_accuracy": 0.15202322900295256,
|
|
"num_tokens": 12157358.0,
|
|
"step": 6205
|
|
},
|
|
{
|
|
"entropy": 6.441101694107056,
|
|
"epoch": 0.6207827260458839,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004969349403966672,
|
|
"loss": 6.2169,
|
|
"mean_token_accuracy": 0.1466719038784504,
|
|
"num_tokens": 12166159.0,
|
|
"step": 6210
|
|
},
|
|
{
|
|
"entropy": 6.377940511703491,
|
|
"epoch": 0.6212825511071125,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004969290668395385,
|
|
"loss": 6.1817,
|
|
"mean_token_accuracy": 0.14901216626167296,
|
|
"num_tokens": 12176405.0,
|
|
"step": 6215
|
|
},
|
|
{
|
|
"entropy": 6.4397608757019045,
|
|
"epoch": 0.6217823761683411,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004969231876987315,
|
|
"loss": 6.2399,
|
|
"mean_token_accuracy": 0.14596698209643363,
|
|
"num_tokens": 12186021.0,
|
|
"step": 6220
|
|
},
|
|
{
|
|
"entropy": 6.343081760406494,
|
|
"epoch": 0.6222822012295697,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004969173029743942,
|
|
"loss": 6.1053,
|
|
"mean_token_accuracy": 0.15684943795204162,
|
|
"num_tokens": 12195222.0,
|
|
"step": 6225
|
|
},
|
|
{
|
|
"entropy": 6.349526119232178,
|
|
"epoch": 0.6227820262907983,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004969114126666746,
|
|
"loss": 6.0835,
|
|
"mean_token_accuracy": 0.15733208805322646,
|
|
"num_tokens": 12205443.0,
|
|
"step": 6230
|
|
},
|
|
{
|
|
"entropy": 6.434093904495239,
|
|
"epoch": 0.6232818513520267,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004969055167757211,
|
|
"loss": 6.2823,
|
|
"mean_token_accuracy": 0.1480371654033661,
|
|
"num_tokens": 12215181.0,
|
|
"step": 6235
|
|
},
|
|
{
|
|
"entropy": 6.390381383895874,
|
|
"epoch": 0.6237816764132553,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004968996153016819,
|
|
"loss": 6.1581,
|
|
"mean_token_accuracy": 0.150498066842556,
|
|
"num_tokens": 12224327.0,
|
|
"step": 6240
|
|
},
|
|
{
|
|
"entropy": 6.394075202941894,
|
|
"epoch": 0.6242815014744839,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004968937082447054,
|
|
"loss": 6.1761,
|
|
"mean_token_accuracy": 0.14878209233283995,
|
|
"num_tokens": 12234962.0,
|
|
"step": 6245
|
|
},
|
|
{
|
|
"entropy": 6.42145185470581,
|
|
"epoch": 0.6247813265357125,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004968877956049403,
|
|
"loss": 6.2465,
|
|
"mean_token_accuracy": 0.15092108845710756,
|
|
"num_tokens": 12245883.0,
|
|
"step": 6250
|
|
},
|
|
{
|
|
"entropy": 6.448516130447388,
|
|
"epoch": 0.6252811515969411,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004968818773825355,
|
|
"loss": 6.2182,
|
|
"mean_token_accuracy": 0.14223939478397368,
|
|
"num_tokens": 12254412.0,
|
|
"step": 6255
|
|
},
|
|
{
|
|
"entropy": 6.299964761734008,
|
|
"epoch": 0.6257809766581697,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004968759535776396,
|
|
"loss": 6.0931,
|
|
"mean_token_accuracy": 0.15128926932811737,
|
|
"num_tokens": 12264894.0,
|
|
"step": 6260
|
|
},
|
|
{
|
|
"entropy": 6.374241733551026,
|
|
"epoch": 0.6262808017193983,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004968700241904018,
|
|
"loss": 6.2001,
|
|
"mean_token_accuracy": 0.1505408175289631,
|
|
"num_tokens": 12274557.0,
|
|
"step": 6265
|
|
},
|
|
{
|
|
"entropy": 6.40683422088623,
|
|
"epoch": 0.6267806267806267,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004968640892209714,
|
|
"loss": 6.0088,
|
|
"mean_token_accuracy": 0.15743694752454757,
|
|
"num_tokens": 12283696.0,
|
|
"step": 6270
|
|
},
|
|
{
|
|
"entropy": 6.3402036190032955,
|
|
"epoch": 0.6272804518418553,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004968581486694975,
|
|
"loss": 6.1202,
|
|
"mean_token_accuracy": 0.15782214179635048,
|
|
"num_tokens": 12292981.0,
|
|
"step": 6275
|
|
},
|
|
{
|
|
"entropy": 6.3552894115448,
|
|
"epoch": 0.6277802769030839,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004968522025361297,
|
|
"loss": 5.9951,
|
|
"mean_token_accuracy": 0.15552034676074983,
|
|
"num_tokens": 12302865.0,
|
|
"step": 6280
|
|
},
|
|
{
|
|
"entropy": 6.336669015884399,
|
|
"epoch": 0.6282801019643125,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004968462508210176,
|
|
"loss": 6.1545,
|
|
"mean_token_accuracy": 0.15222094357013702,
|
|
"num_tokens": 12313099.0,
|
|
"step": 6285
|
|
},
|
|
{
|
|
"entropy": 6.381136894226074,
|
|
"epoch": 0.6287799270255411,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004968402935243109,
|
|
"loss": 6.1941,
|
|
"mean_token_accuracy": 0.15020949989557267,
|
|
"num_tokens": 12324155.0,
|
|
"step": 6290
|
|
},
|
|
{
|
|
"entropy": 6.343426322937011,
|
|
"epoch": 0.6292797520867697,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004968343306461595,
|
|
"loss": 6.0233,
|
|
"mean_token_accuracy": 0.1567442983388901,
|
|
"num_tokens": 12334082.0,
|
|
"step": 6295
|
|
},
|
|
{
|
|
"entropy": 6.3027894496917725,
|
|
"epoch": 0.6297795771479981,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004968283621867134,
|
|
"loss": 6.1438,
|
|
"mean_token_accuracy": 0.15131822675466539,
|
|
"num_tokens": 12344673.0,
|
|
"step": 6300
|
|
},
|
|
{
|
|
"entropy": 6.371920156478882,
|
|
"epoch": 0.6302794022092267,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004968223881461227,
|
|
"loss": 6.1368,
|
|
"mean_token_accuracy": 0.14937038272619246,
|
|
"num_tokens": 12355149.0,
|
|
"step": 6305
|
|
},
|
|
{
|
|
"entropy": 6.373556089401245,
|
|
"epoch": 0.6307792272704553,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000496816408524538,
|
|
"loss": 6.0463,
|
|
"mean_token_accuracy": 0.15889935195446014,
|
|
"num_tokens": 12364043.0,
|
|
"step": 6310
|
|
},
|
|
{
|
|
"entropy": 6.367973566055298,
|
|
"epoch": 0.6312790523316839,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004968104233221094,
|
|
"loss": 6.2408,
|
|
"mean_token_accuracy": 0.14706538245081902,
|
|
"num_tokens": 12373591.0,
|
|
"step": 6315
|
|
},
|
|
{
|
|
"entropy": 6.360639667510986,
|
|
"epoch": 0.6317788773929125,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004968044325389877,
|
|
"loss": 6.1734,
|
|
"mean_token_accuracy": 0.15179983973503114,
|
|
"num_tokens": 12383570.0,
|
|
"step": 6320
|
|
},
|
|
{
|
|
"entropy": 6.4673093318939205,
|
|
"epoch": 0.6322787024541411,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004967984361753235,
|
|
"loss": 6.1557,
|
|
"mean_token_accuracy": 0.15092750489711762,
|
|
"num_tokens": 12393682.0,
|
|
"step": 6325
|
|
},
|
|
{
|
|
"entropy": 6.418556165695191,
|
|
"epoch": 0.6327785275153697,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004967924342312677,
|
|
"loss": 6.0859,
|
|
"mean_token_accuracy": 0.15357855558395386,
|
|
"num_tokens": 12403478.0,
|
|
"step": 6330
|
|
},
|
|
{
|
|
"entropy": 6.325319099426269,
|
|
"epoch": 0.6332783525765981,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004967864267069713,
|
|
"loss": 6.185,
|
|
"mean_token_accuracy": 0.15216561108827592,
|
|
"num_tokens": 12412810.0,
|
|
"step": 6335
|
|
},
|
|
{
|
|
"entropy": 6.284311437606812,
|
|
"epoch": 0.6337781776378267,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004967804136025856,
|
|
"loss": 6.0813,
|
|
"mean_token_accuracy": 0.1570043072104454,
|
|
"num_tokens": 12422209.0,
|
|
"step": 6340
|
|
},
|
|
{
|
|
"entropy": 6.3864611148834225,
|
|
"epoch": 0.6342780026990553,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004967743949182617,
|
|
"loss": 6.1379,
|
|
"mean_token_accuracy": 0.15099855959415437,
|
|
"num_tokens": 12431569.0,
|
|
"step": 6345
|
|
},
|
|
{
|
|
"entropy": 6.308241939544677,
|
|
"epoch": 0.6347778277602839,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004967683706541511,
|
|
"loss": 5.9946,
|
|
"mean_token_accuracy": 0.17168646901845933,
|
|
"num_tokens": 12441607.0,
|
|
"step": 6350
|
|
},
|
|
{
|
|
"entropy": 6.295763063430786,
|
|
"epoch": 0.6352776528215125,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004967623408104054,
|
|
"loss": 6.1351,
|
|
"mean_token_accuracy": 0.14483131766319274,
|
|
"num_tokens": 12451072.0,
|
|
"step": 6355
|
|
},
|
|
{
|
|
"entropy": 6.38209114074707,
|
|
"epoch": 0.6357774778827411,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004967563053871762,
|
|
"loss": 6.1505,
|
|
"mean_token_accuracy": 0.14997408762574196,
|
|
"num_tokens": 12460798.0,
|
|
"step": 6360
|
|
},
|
|
{
|
|
"entropy": 6.31462550163269,
|
|
"epoch": 0.6362773029439696,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004967502643846155,
|
|
"loss": 6.0818,
|
|
"mean_token_accuracy": 0.15518784523010254,
|
|
"num_tokens": 12471891.0,
|
|
"step": 6365
|
|
},
|
|
{
|
|
"entropy": 6.3016307830810545,
|
|
"epoch": 0.6367771280051981,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000496744217802875,
|
|
"loss": 6.122,
|
|
"mean_token_accuracy": 0.15114265233278273,
|
|
"num_tokens": 12482212.0,
|
|
"step": 6370
|
|
},
|
|
{
|
|
"entropy": 6.3723132610321045,
|
|
"epoch": 0.6372769530664267,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004967381656421073,
|
|
"loss": 6.1353,
|
|
"mean_token_accuracy": 0.15127579718828202,
|
|
"num_tokens": 12492517.0,
|
|
"step": 6375
|
|
},
|
|
{
|
|
"entropy": 6.35697603225708,
|
|
"epoch": 0.6377767781276553,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004967321079024643,
|
|
"loss": 6.0612,
|
|
"mean_token_accuracy": 0.15172800570726394,
|
|
"num_tokens": 12502521.0,
|
|
"step": 6380
|
|
},
|
|
{
|
|
"entropy": 6.369220495223999,
|
|
"epoch": 0.6382766031888839,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004967260445840985,
|
|
"loss": 6.1996,
|
|
"mean_token_accuracy": 0.1520134449005127,
|
|
"num_tokens": 12513195.0,
|
|
"step": 6385
|
|
},
|
|
{
|
|
"entropy": 6.34788179397583,
|
|
"epoch": 0.6387764282501125,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004967199756871624,
|
|
"loss": 6.0109,
|
|
"mean_token_accuracy": 0.1613096699118614,
|
|
"num_tokens": 12521640.0,
|
|
"step": 6390
|
|
},
|
|
{
|
|
"entropy": 6.350938510894776,
|
|
"epoch": 0.6392762533113411,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004967139012118088,
|
|
"loss": 6.1505,
|
|
"mean_token_accuracy": 0.1580931320786476,
|
|
"num_tokens": 12530807.0,
|
|
"step": 6395
|
|
},
|
|
{
|
|
"entropy": 6.383451271057129,
|
|
"epoch": 0.6397760783725696,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004967078211581907,
|
|
"loss": 6.1942,
|
|
"mean_token_accuracy": 0.15094359517097472,
|
|
"num_tokens": 12542049.0,
|
|
"step": 6400
|
|
},
|
|
{
|
|
"entropy": 6.417659139633178,
|
|
"epoch": 0.6402759034337981,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004967017355264606,
|
|
"loss": 6.1472,
|
|
"mean_token_accuracy": 0.15765562951564788,
|
|
"num_tokens": 12551699.0,
|
|
"step": 6405
|
|
},
|
|
{
|
|
"entropy": 6.386373233795166,
|
|
"epoch": 0.6407757284950267,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000496695644316772,
|
|
"loss": 6.223,
|
|
"mean_token_accuracy": 0.14688841253519058,
|
|
"num_tokens": 12561414.0,
|
|
"step": 6410
|
|
},
|
|
{
|
|
"entropy": 6.383068656921386,
|
|
"epoch": 0.6412755535562553,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004966895475292781,
|
|
"loss": 6.2077,
|
|
"mean_token_accuracy": 0.15030010491609574,
|
|
"num_tokens": 12571950.0,
|
|
"step": 6415
|
|
},
|
|
{
|
|
"entropy": 6.473227834701538,
|
|
"epoch": 0.6417753786174839,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004966834451641322,
|
|
"loss": 6.2193,
|
|
"mean_token_accuracy": 0.1474399521946907,
|
|
"num_tokens": 12581264.0,
|
|
"step": 6420
|
|
},
|
|
{
|
|
"entropy": 6.440133810043335,
|
|
"epoch": 0.6422752036787125,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004966773372214878,
|
|
"loss": 6.1878,
|
|
"mean_token_accuracy": 0.15022074282169343,
|
|
"num_tokens": 12590950.0,
|
|
"step": 6425
|
|
},
|
|
{
|
|
"entropy": 6.3599693775177,
|
|
"epoch": 0.642775028739941,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004966712237014987,
|
|
"loss": 6.1044,
|
|
"mean_token_accuracy": 0.15040089339017867,
|
|
"num_tokens": 12599766.0,
|
|
"step": 6430
|
|
},
|
|
{
|
|
"entropy": 6.37359471321106,
|
|
"epoch": 0.6432748538011696,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004966651046043186,
|
|
"loss": 6.1352,
|
|
"mean_token_accuracy": 0.15839634090662003,
|
|
"num_tokens": 12610074.0,
|
|
"step": 6435
|
|
},
|
|
{
|
|
"entropy": 6.2677969455719,
|
|
"epoch": 0.6437746788623981,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004966589799301016,
|
|
"loss": 6.0262,
|
|
"mean_token_accuracy": 0.16640736907720566,
|
|
"num_tokens": 12619117.0,
|
|
"step": 6440
|
|
},
|
|
{
|
|
"entropy": 6.417395734786988,
|
|
"epoch": 0.6442745039236267,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004966528496790015,
|
|
"loss": 6.1514,
|
|
"mean_token_accuracy": 0.14867937788367272,
|
|
"num_tokens": 12627993.0,
|
|
"step": 6445
|
|
},
|
|
{
|
|
"entropy": 6.38639235496521,
|
|
"epoch": 0.6447743289848553,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004966467138511729,
|
|
"loss": 6.125,
|
|
"mean_token_accuracy": 0.14879951775074005,
|
|
"num_tokens": 12637787.0,
|
|
"step": 6450
|
|
},
|
|
{
|
|
"entropy": 6.417224407196045,
|
|
"epoch": 0.6452741540460839,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00049664057244677,
|
|
"loss": 6.2622,
|
|
"mean_token_accuracy": 0.14699337184429168,
|
|
"num_tokens": 12648409.0,
|
|
"step": 6455
|
|
},
|
|
{
|
|
"entropy": 6.358612155914306,
|
|
"epoch": 0.6457739791073125,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004966344254659473,
|
|
"loss": 6.0705,
|
|
"mean_token_accuracy": 0.15389290004968642,
|
|
"num_tokens": 12658391.0,
|
|
"step": 6460
|
|
},
|
|
{
|
|
"entropy": 6.329519510269165,
|
|
"epoch": 0.646273804168541,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004966282729088595,
|
|
"loss": 6.1155,
|
|
"mean_token_accuracy": 0.1458040416240692,
|
|
"num_tokens": 12669926.0,
|
|
"step": 6465
|
|
},
|
|
{
|
|
"entropy": 6.300841665267944,
|
|
"epoch": 0.6467736292297696,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004966221147756615,
|
|
"loss": 6.1863,
|
|
"mean_token_accuracy": 0.15250664204359055,
|
|
"num_tokens": 12679176.0,
|
|
"step": 6470
|
|
},
|
|
{
|
|
"entropy": 6.375632810592651,
|
|
"epoch": 0.6472734542909981,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004966159510665079,
|
|
"loss": 6.0779,
|
|
"mean_token_accuracy": 0.15300790071487427,
|
|
"num_tokens": 12688954.0,
|
|
"step": 6475
|
|
},
|
|
{
|
|
"entropy": 6.3250854969024655,
|
|
"epoch": 0.6477732793522267,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004966097817815542,
|
|
"loss": 6.0973,
|
|
"mean_token_accuracy": 0.1529160514473915,
|
|
"num_tokens": 12697577.0,
|
|
"step": 6480
|
|
},
|
|
{
|
|
"entropy": 6.3207316398620605,
|
|
"epoch": 0.6482731044134553,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004966036069209552,
|
|
"loss": 6.2109,
|
|
"mean_token_accuracy": 0.14236616268754004,
|
|
"num_tokens": 12708153.0,
|
|
"step": 6485
|
|
},
|
|
{
|
|
"entropy": 6.369741916656494,
|
|
"epoch": 0.6487729294746839,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004965974264848666,
|
|
"loss": 6.1726,
|
|
"mean_token_accuracy": 0.15143117308616638,
|
|
"num_tokens": 12717329.0,
|
|
"step": 6490
|
|
},
|
|
{
|
|
"entropy": 6.426022863388061,
|
|
"epoch": 0.6492727545359124,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004965912404734438,
|
|
"loss": 6.1534,
|
|
"mean_token_accuracy": 0.15484849885106086,
|
|
"num_tokens": 12726528.0,
|
|
"step": 6495
|
|
},
|
|
{
|
|
"entropy": 6.416892147064209,
|
|
"epoch": 0.649772579597141,
|
|
"grad_norm": 0.74609375,
|
|
"learning_rate": 0.0004965850488868424,
|
|
"loss": 6.1758,
|
|
"mean_token_accuracy": 0.14054541513323784,
|
|
"num_tokens": 12737341.0,
|
|
"step": 6500
|
|
},
|
|
{
|
|
"entropy": 6.32563099861145,
|
|
"epoch": 0.6502724046583696,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004965788517252181,
|
|
"loss": 6.0704,
|
|
"mean_token_accuracy": 0.15614385306835174,
|
|
"num_tokens": 12746973.0,
|
|
"step": 6505
|
|
},
|
|
{
|
|
"entropy": 6.400835609436035,
|
|
"epoch": 0.6507722297195981,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000496572648988727,
|
|
"loss": 6.107,
|
|
"mean_token_accuracy": 0.15600904524326326,
|
|
"num_tokens": 12756176.0,
|
|
"step": 6510
|
|
},
|
|
{
|
|
"entropy": 6.372300529479981,
|
|
"epoch": 0.6512720547808267,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000496566440677525,
|
|
"loss": 6.1068,
|
|
"mean_token_accuracy": 0.1507421314716339,
|
|
"num_tokens": 12766349.0,
|
|
"step": 6515
|
|
},
|
|
{
|
|
"entropy": 6.280128812789917,
|
|
"epoch": 0.6517718798420553,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004965602267917685,
|
|
"loss": 6.059,
|
|
"mean_token_accuracy": 0.15402039885520935,
|
|
"num_tokens": 12775857.0,
|
|
"step": 6520
|
|
},
|
|
{
|
|
"entropy": 6.325213050842285,
|
|
"epoch": 0.6522717049032839,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004965540073316136,
|
|
"loss": 6.1391,
|
|
"mean_token_accuracy": 0.1516575925052166,
|
|
"num_tokens": 12786376.0,
|
|
"step": 6525
|
|
},
|
|
{
|
|
"entropy": 6.344586610794067,
|
|
"epoch": 0.6527715299645124,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004965477822972169,
|
|
"loss": 6.1409,
|
|
"mean_token_accuracy": 0.14783751219511032,
|
|
"num_tokens": 12795719.0,
|
|
"step": 6530
|
|
},
|
|
{
|
|
"entropy": 6.3499805450439455,
|
|
"epoch": 0.653271355025741,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004965415516887349,
|
|
"loss": 6.1566,
|
|
"mean_token_accuracy": 0.14976436272263527,
|
|
"num_tokens": 12806742.0,
|
|
"step": 6535
|
|
},
|
|
{
|
|
"entropy": 6.293507242202759,
|
|
"epoch": 0.6537711800869695,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004965353155063246,
|
|
"loss": 5.9848,
|
|
"mean_token_accuracy": 0.15153535157442094,
|
|
"num_tokens": 12817362.0,
|
|
"step": 6540
|
|
},
|
|
{
|
|
"entropy": 6.23037805557251,
|
|
"epoch": 0.6542710051481981,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004965290737501427,
|
|
"loss": 5.9875,
|
|
"mean_token_accuracy": 0.16109038293361663,
|
|
"num_tokens": 12826516.0,
|
|
"step": 6545
|
|
},
|
|
{
|
|
"entropy": 6.3271490097045895,
|
|
"epoch": 0.6547708302094267,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004965228264203464,
|
|
"loss": 6.1655,
|
|
"mean_token_accuracy": 0.14252509251236917,
|
|
"num_tokens": 12836321.0,
|
|
"step": 6550
|
|
},
|
|
{
|
|
"entropy": 6.355516052246093,
|
|
"epoch": 0.6552706552706553,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004965165735170928,
|
|
"loss": 6.0351,
|
|
"mean_token_accuracy": 0.16001931726932525,
|
|
"num_tokens": 12845955.0,
|
|
"step": 6555
|
|
},
|
|
{
|
|
"entropy": 6.3337170600891115,
|
|
"epoch": 0.6557704803318838,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000496510315040539,
|
|
"loss": 6.2007,
|
|
"mean_token_accuracy": 0.14780328646302224,
|
|
"num_tokens": 12854749.0,
|
|
"step": 6560
|
|
},
|
|
{
|
|
"entropy": 6.328001642227173,
|
|
"epoch": 0.6562703053931124,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004965040509908429,
|
|
"loss": 6.1559,
|
|
"mean_token_accuracy": 0.15129912793636321,
|
|
"num_tokens": 12865145.0,
|
|
"step": 6565
|
|
},
|
|
{
|
|
"entropy": 6.372905540466308,
|
|
"epoch": 0.656770130454341,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004964977813681618,
|
|
"loss": 6.0883,
|
|
"mean_token_accuracy": 0.1573726311326027,
|
|
"num_tokens": 12876109.0,
|
|
"step": 6570
|
|
},
|
|
{
|
|
"entropy": 6.429256916046143,
|
|
"epoch": 0.6572699555155695,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004964915061726534,
|
|
"loss": 6.1508,
|
|
"mean_token_accuracy": 0.1481800615787506,
|
|
"num_tokens": 12886813.0,
|
|
"step": 6575
|
|
},
|
|
{
|
|
"entropy": 6.326648187637329,
|
|
"epoch": 0.6577697805767981,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004964852254044759,
|
|
"loss": 6.1247,
|
|
"mean_token_accuracy": 0.15234682857990264,
|
|
"num_tokens": 12897991.0,
|
|
"step": 6580
|
|
},
|
|
{
|
|
"entropy": 6.314520025253296,
|
|
"epoch": 0.6582696056380267,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004964789390637871,
|
|
"loss": 6.2017,
|
|
"mean_token_accuracy": 0.14077168628573417,
|
|
"num_tokens": 12907354.0,
|
|
"step": 6585
|
|
},
|
|
{
|
|
"entropy": 6.394770336151123,
|
|
"epoch": 0.6587694306992553,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004964726471507451,
|
|
"loss": 6.1104,
|
|
"mean_token_accuracy": 0.1573098734021187,
|
|
"num_tokens": 12917187.0,
|
|
"step": 6590
|
|
},
|
|
{
|
|
"entropy": 6.32343111038208,
|
|
"epoch": 0.6592692557604838,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004964663496655083,
|
|
"loss": 6.0656,
|
|
"mean_token_accuracy": 0.15588307976722718,
|
|
"num_tokens": 12926470.0,
|
|
"step": 6595
|
|
},
|
|
{
|
|
"entropy": 6.319895076751709,
|
|
"epoch": 0.6597690808217124,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004964600466082351,
|
|
"loss": 6.1129,
|
|
"mean_token_accuracy": 0.15508380830287932,
|
|
"num_tokens": 12936609.0,
|
|
"step": 6600
|
|
},
|
|
{
|
|
"entropy": 6.329181909561157,
|
|
"epoch": 0.660268905882941,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004964537379790842,
|
|
"loss": 6.0444,
|
|
"mean_token_accuracy": 0.15705326795578003,
|
|
"num_tokens": 12946286.0,
|
|
"step": 6605
|
|
},
|
|
{
|
|
"entropy": 6.352501058578492,
|
|
"epoch": 0.6607687309441695,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004964474237782141,
|
|
"loss": 6.0614,
|
|
"mean_token_accuracy": 0.15459955632686614,
|
|
"num_tokens": 12955881.0,
|
|
"step": 6610
|
|
},
|
|
{
|
|
"entropy": 6.383995819091797,
|
|
"epoch": 0.6612685560053981,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004964411040057839,
|
|
"loss": 6.197,
|
|
"mean_token_accuracy": 0.14883046746253967,
|
|
"num_tokens": 12966273.0,
|
|
"step": 6615
|
|
},
|
|
{
|
|
"entropy": 6.314850854873657,
|
|
"epoch": 0.6617683810666267,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004964347786619524,
|
|
"loss": 6.1615,
|
|
"mean_token_accuracy": 0.1448350228369236,
|
|
"num_tokens": 12975300.0,
|
|
"step": 6620
|
|
},
|
|
{
|
|
"entropy": 6.382529592514038,
|
|
"epoch": 0.6622682061278552,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004964284477468791,
|
|
"loss": 6.1152,
|
|
"mean_token_accuracy": 0.1607019305229187,
|
|
"num_tokens": 12985291.0,
|
|
"step": 6625
|
|
},
|
|
{
|
|
"entropy": 6.393477964401245,
|
|
"epoch": 0.6627680311890838,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004964221112607228,
|
|
"loss": 6.0805,
|
|
"mean_token_accuracy": 0.15713976621627807,
|
|
"num_tokens": 12995935.0,
|
|
"step": 6630
|
|
},
|
|
{
|
|
"entropy": 6.304874563217163,
|
|
"epoch": 0.6632678562503124,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004964157692036432,
|
|
"loss": 6.0623,
|
|
"mean_token_accuracy": 0.15830949395895005,
|
|
"num_tokens": 13006916.0,
|
|
"step": 6635
|
|
},
|
|
{
|
|
"entropy": 6.393911600112915,
|
|
"epoch": 0.663767681311541,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004964094215757998,
|
|
"loss": 6.328,
|
|
"mean_token_accuracy": 0.13789430782198905,
|
|
"num_tokens": 13017247.0,
|
|
"step": 6640
|
|
},
|
|
{
|
|
"entropy": 6.345292568206787,
|
|
"epoch": 0.6642675063727695,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004964030683773525,
|
|
"loss": 6.1419,
|
|
"mean_token_accuracy": 0.15398175567388533,
|
|
"num_tokens": 13026038.0,
|
|
"step": 6645
|
|
},
|
|
{
|
|
"entropy": 6.373729228973389,
|
|
"epoch": 0.6647673314339981,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004963967096084608,
|
|
"loss": 6.2139,
|
|
"mean_token_accuracy": 0.14222794100642205,
|
|
"num_tokens": 13036436.0,
|
|
"step": 6650
|
|
},
|
|
{
|
|
"entropy": 6.420047473907471,
|
|
"epoch": 0.6652671564952267,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004963903452692849,
|
|
"loss": 6.1556,
|
|
"mean_token_accuracy": 0.14814745411276817,
|
|
"num_tokens": 13045594.0,
|
|
"step": 6655
|
|
},
|
|
{
|
|
"entropy": 6.406752109527588,
|
|
"epoch": 0.6657669815564552,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004963839753599848,
|
|
"loss": 6.1465,
|
|
"mean_token_accuracy": 0.15128230899572373,
|
|
"num_tokens": 13056023.0,
|
|
"step": 6660
|
|
},
|
|
{
|
|
"entropy": 6.397957801818848,
|
|
"epoch": 0.6662668066176838,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000496377599880721,
|
|
"loss": 6.0909,
|
|
"mean_token_accuracy": 0.1555365115404129,
|
|
"num_tokens": 13064230.0,
|
|
"step": 6665
|
|
},
|
|
{
|
|
"entropy": 6.324149799346924,
|
|
"epoch": 0.6667666316789124,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004963712188316537,
|
|
"loss": 5.9924,
|
|
"mean_token_accuracy": 0.16710476577281952,
|
|
"num_tokens": 13073767.0,
|
|
"step": 6670
|
|
},
|
|
{
|
|
"entropy": 6.307120752334595,
|
|
"epoch": 0.667266456740141,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004963648322129435,
|
|
"loss": 6.046,
|
|
"mean_token_accuracy": 0.15849119648337365,
|
|
"num_tokens": 13083026.0,
|
|
"step": 6675
|
|
},
|
|
{
|
|
"entropy": 6.337471437454224,
|
|
"epoch": 0.6677662818013695,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000496358440024751,
|
|
"loss": 6.0679,
|
|
"mean_token_accuracy": 0.15523538291454314,
|
|
"num_tokens": 13092029.0,
|
|
"step": 6680
|
|
},
|
|
{
|
|
"entropy": 6.432424545288086,
|
|
"epoch": 0.6682661068625981,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004963520422672372,
|
|
"loss": 6.1974,
|
|
"mean_token_accuracy": 0.14917913526296617,
|
|
"num_tokens": 13101859.0,
|
|
"step": 6685
|
|
},
|
|
{
|
|
"entropy": 6.377618026733399,
|
|
"epoch": 0.6687659319238266,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.000496345638940563,
|
|
"loss": 6.0756,
|
|
"mean_token_accuracy": 0.15455148965120316,
|
|
"num_tokens": 13111007.0,
|
|
"step": 6690
|
|
},
|
|
{
|
|
"entropy": 6.268700122833252,
|
|
"epoch": 0.6692657569850552,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004963392300448894,
|
|
"loss": 6.0938,
|
|
"mean_token_accuracy": 0.15741010010242462,
|
|
"num_tokens": 13120662.0,
|
|
"step": 6695
|
|
},
|
|
{
|
|
"entropy": 6.315941667556762,
|
|
"epoch": 0.6697655820462838,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004963328155803778,
|
|
"loss": 6.0119,
|
|
"mean_token_accuracy": 0.1480046570301056,
|
|
"num_tokens": 13130263.0,
|
|
"step": 6700
|
|
},
|
|
{
|
|
"entropy": 6.391905784606934,
|
|
"epoch": 0.6702654071075124,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004963263955471895,
|
|
"loss": 6.0676,
|
|
"mean_token_accuracy": 0.157219298183918,
|
|
"num_tokens": 13139821.0,
|
|
"step": 6705
|
|
},
|
|
{
|
|
"entropy": 6.291745901107788,
|
|
"epoch": 0.670765232168741,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000496319969945486,
|
|
"loss": 6.0684,
|
|
"mean_token_accuracy": 0.1545048825442791,
|
|
"num_tokens": 13149731.0,
|
|
"step": 6710
|
|
},
|
|
{
|
|
"entropy": 6.310548782348633,
|
|
"epoch": 0.6712650572299695,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000496313538775429,
|
|
"loss": 6.1415,
|
|
"mean_token_accuracy": 0.15519914478063584,
|
|
"num_tokens": 13160689.0,
|
|
"step": 6715
|
|
},
|
|
{
|
|
"entropy": 6.372151947021484,
|
|
"epoch": 0.6717648822911981,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004963071020371803,
|
|
"loss": 6.2493,
|
|
"mean_token_accuracy": 0.15224682688713073,
|
|
"num_tokens": 13170694.0,
|
|
"step": 6720
|
|
},
|
|
{
|
|
"entropy": 6.416892147064209,
|
|
"epoch": 0.6722647073524266,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004963006597309019,
|
|
"loss": 6.2142,
|
|
"mean_token_accuracy": 0.15051673650741576,
|
|
"num_tokens": 13180514.0,
|
|
"step": 6725
|
|
},
|
|
{
|
|
"entropy": 6.3184366703033445,
|
|
"epoch": 0.6727645324136552,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004962942118567559,
|
|
"loss": 6.0267,
|
|
"mean_token_accuracy": 0.15538074523210527,
|
|
"num_tokens": 13190144.0,
|
|
"step": 6730
|
|
},
|
|
{
|
|
"entropy": 6.370538854598999,
|
|
"epoch": 0.6732643574748838,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004962877584149043,
|
|
"loss": 6.0767,
|
|
"mean_token_accuracy": 0.151009464263916,
|
|
"num_tokens": 13199640.0,
|
|
"step": 6735
|
|
},
|
|
{
|
|
"entropy": 6.365364742279053,
|
|
"epoch": 0.6737641825361124,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004962812994055098,
|
|
"loss": 6.0285,
|
|
"mean_token_accuracy": 0.16212347745895386,
|
|
"num_tokens": 13208824.0,
|
|
"step": 6740
|
|
},
|
|
{
|
|
"entropy": 6.27418098449707,
|
|
"epoch": 0.674264007597341,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004962748348287347,
|
|
"loss": 5.993,
|
|
"mean_token_accuracy": 0.17144986763596534,
|
|
"num_tokens": 13219305.0,
|
|
"step": 6745
|
|
},
|
|
{
|
|
"entropy": 6.328550195693969,
|
|
"epoch": 0.6747638326585695,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004962683646847416,
|
|
"loss": 6.0149,
|
|
"mean_token_accuracy": 0.16121758967638017,
|
|
"num_tokens": 13227727.0,
|
|
"step": 6750
|
|
},
|
|
{
|
|
"entropy": 6.331701040267944,
|
|
"epoch": 0.675263657719798,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004962618889736936,
|
|
"loss": 6.0705,
|
|
"mean_token_accuracy": 0.1556951217353344,
|
|
"num_tokens": 13237522.0,
|
|
"step": 6755
|
|
},
|
|
{
|
|
"entropy": 6.298553991317749,
|
|
"epoch": 0.6757634827810266,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004962554076957533,
|
|
"loss": 6.1272,
|
|
"mean_token_accuracy": 0.15072486400604249,
|
|
"num_tokens": 13247155.0,
|
|
"step": 6760
|
|
},
|
|
{
|
|
"entropy": 6.333307409286499,
|
|
"epoch": 0.6762633078422552,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004962489208510838,
|
|
"loss": 6.1542,
|
|
"mean_token_accuracy": 0.14725901037454606,
|
|
"num_tokens": 13257324.0,
|
|
"step": 6765
|
|
},
|
|
{
|
|
"entropy": 6.295897579193115,
|
|
"epoch": 0.6767631329034838,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004962424284398484,
|
|
"loss": 6.1339,
|
|
"mean_token_accuracy": 0.1507594883441925,
|
|
"num_tokens": 13267025.0,
|
|
"step": 6770
|
|
},
|
|
{
|
|
"entropy": 6.34990758895874,
|
|
"epoch": 0.6772629579647124,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004962359304622105,
|
|
"loss": 6.0501,
|
|
"mean_token_accuracy": 0.16186515390872955,
|
|
"num_tokens": 13276709.0,
|
|
"step": 6775
|
|
},
|
|
{
|
|
"entropy": 6.335904741287232,
|
|
"epoch": 0.677762783025941,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004962294269183335,
|
|
"loss": 6.0657,
|
|
"mean_token_accuracy": 0.14934478104114532,
|
|
"num_tokens": 13286029.0,
|
|
"step": 6780
|
|
},
|
|
{
|
|
"entropy": 6.357704019546508,
|
|
"epoch": 0.6782626080871695,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000496222917808381,
|
|
"loss": 6.2126,
|
|
"mean_token_accuracy": 0.14190776348114015,
|
|
"num_tokens": 13296367.0,
|
|
"step": 6785
|
|
},
|
|
{
|
|
"entropy": 6.422132253646851,
|
|
"epoch": 0.678762433148398,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004962164031325169,
|
|
"loss": 6.1451,
|
|
"mean_token_accuracy": 0.1498284511268139,
|
|
"num_tokens": 13305186.0,
|
|
"step": 6790
|
|
},
|
|
{
|
|
"entropy": 6.359393644332886,
|
|
"epoch": 0.6792622582096266,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000496209882890905,
|
|
"loss": 6.0906,
|
|
"mean_token_accuracy": 0.1526859447360039,
|
|
"num_tokens": 13314512.0,
|
|
"step": 6795
|
|
},
|
|
{
|
|
"entropy": 6.35632586479187,
|
|
"epoch": 0.6797620832708552,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004962033570837094,
|
|
"loss": 6.1499,
|
|
"mean_token_accuracy": 0.15353505611419677,
|
|
"num_tokens": 13324423.0,
|
|
"step": 6800
|
|
},
|
|
{
|
|
"entropy": 6.385927295684814,
|
|
"epoch": 0.6802619083320838,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004961968257110941,
|
|
"loss": 6.1834,
|
|
"mean_token_accuracy": 0.14684308022260667,
|
|
"num_tokens": 13334133.0,
|
|
"step": 6805
|
|
},
|
|
{
|
|
"entropy": 6.434768915176392,
|
|
"epoch": 0.6807617333933124,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004961902887732236,
|
|
"loss": 6.1664,
|
|
"mean_token_accuracy": 0.15219189077615738,
|
|
"num_tokens": 13344017.0,
|
|
"step": 6810
|
|
},
|
|
{
|
|
"entropy": 6.303944396972656,
|
|
"epoch": 0.681261558454541,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004961837462702626,
|
|
"loss": 5.9352,
|
|
"mean_token_accuracy": 0.16335101723670958,
|
|
"num_tokens": 13353922.0,
|
|
"step": 6815
|
|
},
|
|
{
|
|
"entropy": 6.333379888534546,
|
|
"epoch": 0.6817613835157694,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004961771982023752,
|
|
"loss": 6.1071,
|
|
"mean_token_accuracy": 0.1507889896631241,
|
|
"num_tokens": 13363890.0,
|
|
"step": 6820
|
|
},
|
|
{
|
|
"entropy": 6.3336488723754885,
|
|
"epoch": 0.682261208576998,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004961706445697265,
|
|
"loss": 6.0536,
|
|
"mean_token_accuracy": 0.1545298859477043,
|
|
"num_tokens": 13373726.0,
|
|
"step": 6825
|
|
},
|
|
{
|
|
"entropy": 6.295986080169678,
|
|
"epoch": 0.6827610336382266,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004961640853724813,
|
|
"loss": 5.9732,
|
|
"mean_token_accuracy": 0.16524138748645784,
|
|
"num_tokens": 13382049.0,
|
|
"step": 6830
|
|
},
|
|
{
|
|
"entropy": 6.233406591415405,
|
|
"epoch": 0.6832608586994552,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004961575206108046,
|
|
"loss": 5.9093,
|
|
"mean_token_accuracy": 0.16352120339870452,
|
|
"num_tokens": 13390977.0,
|
|
"step": 6835
|
|
},
|
|
{
|
|
"entropy": 6.394397211074829,
|
|
"epoch": 0.6837606837606838,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004961509502848616,
|
|
"loss": 6.1173,
|
|
"mean_token_accuracy": 0.15197082236409187,
|
|
"num_tokens": 13400165.0,
|
|
"step": 6840
|
|
},
|
|
{
|
|
"entropy": 6.38779845237732,
|
|
"epoch": 0.6842605088219124,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004961443743948177,
|
|
"loss": 6.1312,
|
|
"mean_token_accuracy": 0.14822078496217728,
|
|
"num_tokens": 13410201.0,
|
|
"step": 6845
|
|
},
|
|
{
|
|
"entropy": 6.359711456298828,
|
|
"epoch": 0.684760333883141,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000496137792940838,
|
|
"loss": 6.1173,
|
|
"mean_token_accuracy": 0.15910622775554656,
|
|
"num_tokens": 13421074.0,
|
|
"step": 6850
|
|
},
|
|
{
|
|
"entropy": 6.295166540145874,
|
|
"epoch": 0.6852601589443694,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004961312059230885,
|
|
"loss": 5.9639,
|
|
"mean_token_accuracy": 0.163887619972229,
|
|
"num_tokens": 13430387.0,
|
|
"step": 6855
|
|
},
|
|
{
|
|
"entropy": 6.290193653106689,
|
|
"epoch": 0.685759984005598,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004961246133417348,
|
|
"loss": 6.0307,
|
|
"mean_token_accuracy": 0.15789291858673096,
|
|
"num_tokens": 13439497.0,
|
|
"step": 6860
|
|
},
|
|
{
|
|
"entropy": 6.362320423126221,
|
|
"epoch": 0.6862598090668266,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004961180151969427,
|
|
"loss": 6.167,
|
|
"mean_token_accuracy": 0.1485782764852047,
|
|
"num_tokens": 13450543.0,
|
|
"step": 6865
|
|
},
|
|
{
|
|
"entropy": 6.317654848098755,
|
|
"epoch": 0.6867596341280552,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004961114114888782,
|
|
"loss": 6.0955,
|
|
"mean_token_accuracy": 0.15495266914367675,
|
|
"num_tokens": 13459996.0,
|
|
"step": 6870
|
|
},
|
|
{
|
|
"entropy": 6.314934349060058,
|
|
"epoch": 0.6872594591892838,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004961048022177074,
|
|
"loss": 6.0379,
|
|
"mean_token_accuracy": 0.15928415656089784,
|
|
"num_tokens": 13469141.0,
|
|
"step": 6875
|
|
},
|
|
{
|
|
"entropy": 6.280258464813232,
|
|
"epoch": 0.6877592842505124,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004960981873835968,
|
|
"loss": 6.0039,
|
|
"mean_token_accuracy": 0.16132644712924957,
|
|
"num_tokens": 13478349.0,
|
|
"step": 6880
|
|
},
|
|
{
|
|
"entropy": 6.2729377269744875,
|
|
"epoch": 0.6882591093117408,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004960915669867126,
|
|
"loss": 5.963,
|
|
"mean_token_accuracy": 0.15914051234722137,
|
|
"num_tokens": 13487417.0,
|
|
"step": 6885
|
|
},
|
|
{
|
|
"entropy": 6.439836692810059,
|
|
"epoch": 0.6887589343729694,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004960849410272216,
|
|
"loss": 6.2185,
|
|
"mean_token_accuracy": 0.15174390077590943,
|
|
"num_tokens": 13497607.0,
|
|
"step": 6890
|
|
},
|
|
{
|
|
"entropy": 6.363502311706543,
|
|
"epoch": 0.689258759434198,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004960783095052903,
|
|
"loss": 6.1838,
|
|
"mean_token_accuracy": 0.14652732163667678,
|
|
"num_tokens": 13508222.0,
|
|
"step": 6895
|
|
},
|
|
{
|
|
"entropy": 6.220916843414306,
|
|
"epoch": 0.6897585844954266,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004960716724210856,
|
|
"loss": 5.9654,
|
|
"mean_token_accuracy": 0.16771477311849595,
|
|
"num_tokens": 13519593.0,
|
|
"step": 6900
|
|
},
|
|
{
|
|
"entropy": 6.444327306747437,
|
|
"epoch": 0.6902584095566552,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004960650297747746,
|
|
"loss": 6.1769,
|
|
"mean_token_accuracy": 0.1447721801698208,
|
|
"num_tokens": 13531089.0,
|
|
"step": 6905
|
|
},
|
|
{
|
|
"entropy": 6.406421327590943,
|
|
"epoch": 0.6907582346178838,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004960583815665242,
|
|
"loss": 6.0815,
|
|
"mean_token_accuracy": 0.15794920697808265,
|
|
"num_tokens": 13539897.0,
|
|
"step": 6910
|
|
},
|
|
{
|
|
"entropy": 6.379333543777466,
|
|
"epoch": 0.6912580596791124,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004960517277965018,
|
|
"loss": 6.1673,
|
|
"mean_token_accuracy": 0.1449688643217087,
|
|
"num_tokens": 13549986.0,
|
|
"step": 6915
|
|
},
|
|
{
|
|
"entropy": 6.373147964477539,
|
|
"epoch": 0.6917578847403408,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004960450684648749,
|
|
"loss": 6.1677,
|
|
"mean_token_accuracy": 0.15427129566669465,
|
|
"num_tokens": 13559866.0,
|
|
"step": 6920
|
|
},
|
|
{
|
|
"entropy": 6.437018775939942,
|
|
"epoch": 0.6922577098015694,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000496038403571811,
|
|
"loss": 6.181,
|
|
"mean_token_accuracy": 0.14901704341173172,
|
|
"num_tokens": 13569789.0,
|
|
"step": 6925
|
|
},
|
|
{
|
|
"entropy": 6.391650104522705,
|
|
"epoch": 0.692757534862798,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004960317331174777,
|
|
"loss": 6.1717,
|
|
"mean_token_accuracy": 0.14617592915892602,
|
|
"num_tokens": 13579121.0,
|
|
"step": 6930
|
|
},
|
|
{
|
|
"entropy": 6.293175888061524,
|
|
"epoch": 0.6932573599240266,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004960250571020428,
|
|
"loss": 6.0553,
|
|
"mean_token_accuracy": 0.1584838956594467,
|
|
"num_tokens": 13589281.0,
|
|
"step": 6935
|
|
},
|
|
{
|
|
"entropy": 6.421004772186279,
|
|
"epoch": 0.6937571849852552,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004960183755256744,
|
|
"loss": 6.05,
|
|
"mean_token_accuracy": 0.1573459357023239,
|
|
"num_tokens": 13598312.0,
|
|
"step": 6940
|
|
},
|
|
{
|
|
"entropy": 6.325068998336792,
|
|
"epoch": 0.6942570100464838,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004960116883885406,
|
|
"loss": 6.1065,
|
|
"mean_token_accuracy": 0.15536510646343232,
|
|
"num_tokens": 13608164.0,
|
|
"step": 6945
|
|
},
|
|
{
|
|
"entropy": 6.3117225646972654,
|
|
"epoch": 0.6947568351077124,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004960049956908095,
|
|
"loss": 6.136,
|
|
"mean_token_accuracy": 0.1498507909476757,
|
|
"num_tokens": 13618314.0,
|
|
"step": 6950
|
|
},
|
|
{
|
|
"entropy": 6.355185413360596,
|
|
"epoch": 0.6952566601689408,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004959982974326496,
|
|
"loss": 6.1067,
|
|
"mean_token_accuracy": 0.15258670076727868,
|
|
"num_tokens": 13628846.0,
|
|
"step": 6955
|
|
},
|
|
{
|
|
"entropy": 6.299815368652344,
|
|
"epoch": 0.6957564852301694,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004959915936142294,
|
|
"loss": 6.004,
|
|
"mean_token_accuracy": 0.16522947400808335,
|
|
"num_tokens": 13637941.0,
|
|
"step": 6960
|
|
},
|
|
{
|
|
"entropy": 6.364964723587036,
|
|
"epoch": 0.696256310291398,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004959848842357175,
|
|
"loss": 6.0706,
|
|
"mean_token_accuracy": 0.1542408749461174,
|
|
"num_tokens": 13647734.0,
|
|
"step": 6965
|
|
},
|
|
{
|
|
"entropy": 6.2456310272216795,
|
|
"epoch": 0.6967561353526266,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004959781692972829,
|
|
"loss": 6.0409,
|
|
"mean_token_accuracy": 0.15711082890629768,
|
|
"num_tokens": 13657929.0,
|
|
"step": 6970
|
|
},
|
|
{
|
|
"entropy": 6.349732685089111,
|
|
"epoch": 0.6972559604138552,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004959714487990943,
|
|
"loss": 6.1373,
|
|
"mean_token_accuracy": 0.15083275437355043,
|
|
"num_tokens": 13668258.0,
|
|
"step": 6975
|
|
},
|
|
{
|
|
"entropy": 6.377843856811523,
|
|
"epoch": 0.6977557854750838,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000495964722741321,
|
|
"loss": 6.0763,
|
|
"mean_token_accuracy": 0.15968114882707596,
|
|
"num_tokens": 13677515.0,
|
|
"step": 6980
|
|
},
|
|
{
|
|
"entropy": 6.364668655395508,
|
|
"epoch": 0.6982556105363122,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004959579911241322,
|
|
"loss": 6.0952,
|
|
"mean_token_accuracy": 0.1535758212208748,
|
|
"num_tokens": 13686865.0,
|
|
"step": 6985
|
|
},
|
|
{
|
|
"entropy": 6.347046661376953,
|
|
"epoch": 0.6987554355975408,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004959512539476971,
|
|
"loss": 6.1689,
|
|
"mean_token_accuracy": 0.15347059890627862,
|
|
"num_tokens": 13696683.0,
|
|
"step": 6990
|
|
},
|
|
{
|
|
"entropy": 6.355521202087402,
|
|
"epoch": 0.6992552606587694,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004959445112121853,
|
|
"loss": 6.1423,
|
|
"mean_token_accuracy": 0.14905546456575394,
|
|
"num_tokens": 13706452.0,
|
|
"step": 6995
|
|
},
|
|
{
|
|
"entropy": 6.295386886596679,
|
|
"epoch": 0.699755085719998,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004959377629177665,
|
|
"loss": 6.0201,
|
|
"mean_token_accuracy": 0.15940037220716477,
|
|
"num_tokens": 13717474.0,
|
|
"step": 7000
|
|
},
|
|
{
|
|
"entropy": 6.295186948776245,
|
|
"epoch": 0.7002549107812266,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004959310090646104,
|
|
"loss": 6.0354,
|
|
"mean_token_accuracy": 0.1640301376581192,
|
|
"num_tokens": 13726723.0,
|
|
"step": 7005
|
|
},
|
|
{
|
|
"entropy": 6.403949785232544,
|
|
"epoch": 0.7007547358424552,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004959242496528869,
|
|
"loss": 6.2578,
|
|
"mean_token_accuracy": 0.14559866935014726,
|
|
"num_tokens": 13736432.0,
|
|
"step": 7010
|
|
},
|
|
{
|
|
"entropy": 6.313732671737671,
|
|
"epoch": 0.7012545609036838,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004959174846827663,
|
|
"loss": 6.0769,
|
|
"mean_token_accuracy": 0.15393958166241645,
|
|
"num_tokens": 13745767.0,
|
|
"step": 7015
|
|
},
|
|
{
|
|
"entropy": 6.395278596878052,
|
|
"epoch": 0.7017543859649122,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004959107141544186,
|
|
"loss": 6.1002,
|
|
"mean_token_accuracy": 0.1565880261361599,
|
|
"num_tokens": 13756035.0,
|
|
"step": 7020
|
|
},
|
|
{
|
|
"entropy": 6.28444013595581,
|
|
"epoch": 0.7022542110261408,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000495903938068014,
|
|
"loss": 5.9301,
|
|
"mean_token_accuracy": 0.1703647792339325,
|
|
"num_tokens": 13765715.0,
|
|
"step": 7025
|
|
},
|
|
{
|
|
"entropy": 6.30950961112976,
|
|
"epoch": 0.7027540360873694,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004958971564237233,
|
|
"loss": 6.1109,
|
|
"mean_token_accuracy": 0.15119080170989035,
|
|
"num_tokens": 13775987.0,
|
|
"step": 7030
|
|
},
|
|
{
|
|
"entropy": 6.309575510025025,
|
|
"epoch": 0.703253861148598,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000495890369221717,
|
|
"loss": 6.0342,
|
|
"mean_token_accuracy": 0.15727882981300353,
|
|
"num_tokens": 13785095.0,
|
|
"step": 7035
|
|
},
|
|
{
|
|
"entropy": 6.385285139083862,
|
|
"epoch": 0.7037536862098266,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004958835764621657,
|
|
"loss": 6.0876,
|
|
"mean_token_accuracy": 0.15080909579992294,
|
|
"num_tokens": 13794777.0,
|
|
"step": 7040
|
|
},
|
|
{
|
|
"entropy": 6.289635372161865,
|
|
"epoch": 0.7042535112710552,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004958767781452406,
|
|
"loss": 5.9865,
|
|
"mean_token_accuracy": 0.15363326221704482,
|
|
"num_tokens": 13803534.0,
|
|
"step": 7045
|
|
},
|
|
{
|
|
"entropy": 6.2926548480987545,
|
|
"epoch": 0.7047533363322837,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004958699742711126,
|
|
"loss": 6.0717,
|
|
"mean_token_accuracy": 0.15242997258901597,
|
|
"num_tokens": 13813941.0,
|
|
"step": 7050
|
|
},
|
|
{
|
|
"entropy": 6.318150615692138,
|
|
"epoch": 0.7052531613935122,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004958631648399528,
|
|
"loss": 6.0659,
|
|
"mean_token_accuracy": 0.15480947196483613,
|
|
"num_tokens": 13823611.0,
|
|
"step": 7055
|
|
},
|
|
{
|
|
"entropy": 6.4087670803070065,
|
|
"epoch": 0.7057529864547408,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004958563498519327,
|
|
"loss": 6.177,
|
|
"mean_token_accuracy": 0.14841430634260178,
|
|
"num_tokens": 13833047.0,
|
|
"step": 7060
|
|
},
|
|
{
|
|
"entropy": 6.3627767086029055,
|
|
"epoch": 0.7062528115159694,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004958495293072235,
|
|
"loss": 6.0846,
|
|
"mean_token_accuracy": 0.15810488313436508,
|
|
"num_tokens": 13843524.0,
|
|
"step": 7065
|
|
},
|
|
{
|
|
"entropy": 6.311433601379394,
|
|
"epoch": 0.706752636577198,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004958427032059971,
|
|
"loss": 6.0049,
|
|
"mean_token_accuracy": 0.16070111840963364,
|
|
"num_tokens": 13852188.0,
|
|
"step": 7070
|
|
},
|
|
{
|
|
"entropy": 6.289581298828125,
|
|
"epoch": 0.7072524616384266,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004958358715484251,
|
|
"loss": 6.113,
|
|
"mean_token_accuracy": 0.15342209935188295,
|
|
"num_tokens": 13863540.0,
|
|
"step": 7075
|
|
},
|
|
{
|
|
"entropy": 6.4064867973327635,
|
|
"epoch": 0.7077522866996552,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004958290343346795,
|
|
"loss": 6.1144,
|
|
"mean_token_accuracy": 0.15415723323822023,
|
|
"num_tokens": 13871828.0,
|
|
"step": 7080
|
|
},
|
|
{
|
|
"entropy": 6.364339208602905,
|
|
"epoch": 0.7082521117608837,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000495822191564932,
|
|
"loss": 6.1364,
|
|
"mean_token_accuracy": 0.15215339213609697,
|
|
"num_tokens": 13882222.0,
|
|
"step": 7085
|
|
},
|
|
{
|
|
"entropy": 6.308574485778808,
|
|
"epoch": 0.7087519368221122,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004958153432393553,
|
|
"loss": 6.1712,
|
|
"mean_token_accuracy": 0.14875813722610473,
|
|
"num_tokens": 13891689.0,
|
|
"step": 7090
|
|
},
|
|
{
|
|
"entropy": 6.291139602661133,
|
|
"epoch": 0.7092517618833408,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000495808489358121,
|
|
"loss": 6.0596,
|
|
"mean_token_accuracy": 0.1585016131401062,
|
|
"num_tokens": 13901310.0,
|
|
"step": 7095
|
|
},
|
|
{
|
|
"entropy": 6.336572980880737,
|
|
"epoch": 0.7097515869445694,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004958016299214022,
|
|
"loss": 6.0459,
|
|
"mean_token_accuracy": 0.1555250734090805,
|
|
"num_tokens": 13910350.0,
|
|
"step": 7100
|
|
},
|
|
{
|
|
"entropy": 6.3348150730133055,
|
|
"epoch": 0.710251412005798,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004957947649293712,
|
|
"loss": 6.1006,
|
|
"mean_token_accuracy": 0.15273423865437508,
|
|
"num_tokens": 13920481.0,
|
|
"step": 7105
|
|
},
|
|
{
|
|
"entropy": 6.364114236831665,
|
|
"epoch": 0.7107512370670266,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004957878943822006,
|
|
"loss": 6.1107,
|
|
"mean_token_accuracy": 0.15007705762982368,
|
|
"num_tokens": 13931232.0,
|
|
"step": 7110
|
|
},
|
|
{
|
|
"entropy": 6.381584882736206,
|
|
"epoch": 0.7112510621282551,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004957810182800634,
|
|
"loss": 6.1701,
|
|
"mean_token_accuracy": 0.14837423115968704,
|
|
"num_tokens": 13940717.0,
|
|
"step": 7115
|
|
},
|
|
{
|
|
"entropy": 6.352689504623413,
|
|
"epoch": 0.7117508871894836,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004957741366231327,
|
|
"loss": 6.0159,
|
|
"mean_token_accuracy": 0.159651917219162,
|
|
"num_tokens": 13949918.0,
|
|
"step": 7120
|
|
},
|
|
{
|
|
"entropy": 6.336006450653076,
|
|
"epoch": 0.7122507122507122,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004957672494115815,
|
|
"loss": 6.0373,
|
|
"mean_token_accuracy": 0.1582901269197464,
|
|
"num_tokens": 13959914.0,
|
|
"step": 7125
|
|
},
|
|
{
|
|
"entropy": 6.346986103057861,
|
|
"epoch": 0.7127505373119408,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000495760356645583,
|
|
"loss": 6.0555,
|
|
"mean_token_accuracy": 0.1581800937652588,
|
|
"num_tokens": 13970054.0,
|
|
"step": 7130
|
|
},
|
|
{
|
|
"entropy": 6.2381785869598385,
|
|
"epoch": 0.7132503623731694,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004957534583253108,
|
|
"loss": 5.9713,
|
|
"mean_token_accuracy": 0.1689275324344635,
|
|
"num_tokens": 13980339.0,
|
|
"step": 7135
|
|
},
|
|
{
|
|
"entropy": 6.282525110244751,
|
|
"epoch": 0.713750187434398,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004957465544509384,
|
|
"loss": 6.0771,
|
|
"mean_token_accuracy": 0.15145995244383811,
|
|
"num_tokens": 13990466.0,
|
|
"step": 7140
|
|
},
|
|
{
|
|
"entropy": 6.3833839893341064,
|
|
"epoch": 0.7142500124956266,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004957396450226395,
|
|
"loss": 6.1087,
|
|
"mean_token_accuracy": 0.15041610598564148,
|
|
"num_tokens": 13999822.0,
|
|
"step": 7145
|
|
},
|
|
{
|
|
"entropy": 6.423709201812744,
|
|
"epoch": 0.7147498375568551,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004957327300405879,
|
|
"loss": 6.1129,
|
|
"mean_token_accuracy": 0.15330879464745523,
|
|
"num_tokens": 14008939.0,
|
|
"step": 7150
|
|
},
|
|
{
|
|
"entropy": 6.3598388671875,
|
|
"epoch": 0.7152496626180836,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004957258095049577,
|
|
"loss": 6.0744,
|
|
"mean_token_accuracy": 0.1473304107785225,
|
|
"num_tokens": 14019005.0,
|
|
"step": 7155
|
|
},
|
|
{
|
|
"entropy": 6.315775966644287,
|
|
"epoch": 0.7157494876793122,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004957188834159229,
|
|
"loss": 5.9753,
|
|
"mean_token_accuracy": 0.16202560365200042,
|
|
"num_tokens": 14029390.0,
|
|
"step": 7160
|
|
},
|
|
{
|
|
"entropy": 6.313910865783692,
|
|
"epoch": 0.7162493127405408,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004957119517736577,
|
|
"loss": 6.0548,
|
|
"mean_token_accuracy": 0.1552247166633606,
|
|
"num_tokens": 14038613.0,
|
|
"step": 7165
|
|
},
|
|
{
|
|
"entropy": 6.277583837509155,
|
|
"epoch": 0.7167491378017694,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004957050145783366,
|
|
"loss": 6.0511,
|
|
"mean_token_accuracy": 0.15635842680931092,
|
|
"num_tokens": 14048144.0,
|
|
"step": 7170
|
|
},
|
|
{
|
|
"entropy": 6.245211029052735,
|
|
"epoch": 0.717248962862998,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004956980718301342,
|
|
"loss": 5.9671,
|
|
"mean_token_accuracy": 0.16858417689800262,
|
|
"num_tokens": 14056894.0,
|
|
"step": 7175
|
|
},
|
|
{
|
|
"entropy": 6.305768537521362,
|
|
"epoch": 0.7177487879242265,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004956911235292251,
|
|
"loss": 6.0449,
|
|
"mean_token_accuracy": 0.15435709953308105,
|
|
"num_tokens": 14066024.0,
|
|
"step": 7180
|
|
},
|
|
{
|
|
"entropy": 6.248495817184448,
|
|
"epoch": 0.7182486129854551,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004956841696757841,
|
|
"loss": 6.0587,
|
|
"mean_token_accuracy": 0.15853175073862075,
|
|
"num_tokens": 14075805.0,
|
|
"step": 7185
|
|
},
|
|
{
|
|
"entropy": 6.292652034759522,
|
|
"epoch": 0.7187484380466836,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004956772102699862,
|
|
"loss": 6.0769,
|
|
"mean_token_accuracy": 0.15876784026622773,
|
|
"num_tokens": 14085229.0,
|
|
"step": 7190
|
|
},
|
|
{
|
|
"entropy": 6.367125034332275,
|
|
"epoch": 0.7192482631079122,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004956702453120064,
|
|
"loss": 6.0491,
|
|
"mean_token_accuracy": 0.15297560393810272,
|
|
"num_tokens": 14094594.0,
|
|
"step": 7195
|
|
},
|
|
{
|
|
"entropy": 6.294458389282227,
|
|
"epoch": 0.7197480881691408,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004956632748020201,
|
|
"loss": 6.0845,
|
|
"mean_token_accuracy": 0.15934179052710534,
|
|
"num_tokens": 14104373.0,
|
|
"step": 7200
|
|
},
|
|
{
|
|
"entropy": 6.253583383560181,
|
|
"epoch": 0.7202479132303694,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004956562987402026,
|
|
"loss": 5.9804,
|
|
"mean_token_accuracy": 0.16113699227571487,
|
|
"num_tokens": 14113918.0,
|
|
"step": 7205
|
|
},
|
|
{
|
|
"entropy": 6.42399754524231,
|
|
"epoch": 0.720747738291598,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004956493171267293,
|
|
"loss": 6.201,
|
|
"mean_token_accuracy": 0.14336002692580224,
|
|
"num_tokens": 14123711.0,
|
|
"step": 7210
|
|
},
|
|
{
|
|
"entropy": 6.38614559173584,
|
|
"epoch": 0.7212475633528265,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000495642329961776,
|
|
"loss": 5.9908,
|
|
"mean_token_accuracy": 0.1615636467933655,
|
|
"num_tokens": 14132994.0,
|
|
"step": 7215
|
|
},
|
|
{
|
|
"entropy": 6.280452919006348,
|
|
"epoch": 0.7217473884140551,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004956353372455185,
|
|
"loss": 6.032,
|
|
"mean_token_accuracy": 0.15625657886266708,
|
|
"num_tokens": 14143398.0,
|
|
"step": 7220
|
|
},
|
|
{
|
|
"entropy": 6.278959321975708,
|
|
"epoch": 0.7222472134752836,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004956283389781327,
|
|
"loss": 6.0382,
|
|
"mean_token_accuracy": 0.1586635857820511,
|
|
"num_tokens": 14152374.0,
|
|
"step": 7225
|
|
},
|
|
{
|
|
"entropy": 6.346828269958496,
|
|
"epoch": 0.7227470385365122,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004956213351597946,
|
|
"loss": 5.9974,
|
|
"mean_token_accuracy": 0.15392591804265976,
|
|
"num_tokens": 14162123.0,
|
|
"step": 7230
|
|
},
|
|
{
|
|
"entropy": 6.390681219100952,
|
|
"epoch": 0.7232468635977408,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004956143257906805,
|
|
"loss": 6.176,
|
|
"mean_token_accuracy": 0.1489823803305626,
|
|
"num_tokens": 14172004.0,
|
|
"step": 7235
|
|
},
|
|
{
|
|
"entropy": 6.23836088180542,
|
|
"epoch": 0.7237466886589694,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004956073108709667,
|
|
"loss": 6.0475,
|
|
"mean_token_accuracy": 0.15373433083295823,
|
|
"num_tokens": 14181659.0,
|
|
"step": 7240
|
|
},
|
|
{
|
|
"entropy": 6.266837310791016,
|
|
"epoch": 0.7242465137201979,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004956002904008298,
|
|
"loss": 6.0348,
|
|
"mean_token_accuracy": 0.15708984881639482,
|
|
"num_tokens": 14191051.0,
|
|
"step": 7245
|
|
},
|
|
{
|
|
"entropy": 6.3565154552459715,
|
|
"epoch": 0.7247463387814265,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004955932643804463,
|
|
"loss": 6.1488,
|
|
"mean_token_accuracy": 0.15095992833375932,
|
|
"num_tokens": 14201232.0,
|
|
"step": 7250
|
|
},
|
|
{
|
|
"entropy": 6.352097702026367,
|
|
"epoch": 0.7252461638426551,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000495586232809993,
|
|
"loss": 6.0911,
|
|
"mean_token_accuracy": 0.15086081027984619,
|
|
"num_tokens": 14210426.0,
|
|
"step": 7255
|
|
},
|
|
{
|
|
"entropy": 6.256494808197021,
|
|
"epoch": 0.7257459889038836,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004955791956896469,
|
|
"loss": 5.9819,
|
|
"mean_token_accuracy": 0.16083145290613174,
|
|
"num_tokens": 14220013.0,
|
|
"step": 7260
|
|
},
|
|
{
|
|
"entropy": 6.325906705856323,
|
|
"epoch": 0.7262458139651122,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000495572153019585,
|
|
"loss": 6.1054,
|
|
"mean_token_accuracy": 0.15201605707406998,
|
|
"num_tokens": 14229249.0,
|
|
"step": 7265
|
|
},
|
|
{
|
|
"entropy": 6.350022649765014,
|
|
"epoch": 0.7267456390263408,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004955651047999844,
|
|
"loss": 5.9794,
|
|
"mean_token_accuracy": 0.16117955297231673,
|
|
"num_tokens": 14238370.0,
|
|
"step": 7270
|
|
},
|
|
{
|
|
"entropy": 6.236727142333985,
|
|
"epoch": 0.7272454640875694,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004955580510310226,
|
|
"loss": 6.0078,
|
|
"mean_token_accuracy": 0.1697586938738823,
|
|
"num_tokens": 14248037.0,
|
|
"step": 7275
|
|
},
|
|
{
|
|
"entropy": 6.23610553741455,
|
|
"epoch": 0.7277452891487979,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004955509917128771,
|
|
"loss": 6.097,
|
|
"mean_token_accuracy": 0.15329890176653863,
|
|
"num_tokens": 14257480.0,
|
|
"step": 7280
|
|
},
|
|
{
|
|
"entropy": 6.288200092315674,
|
|
"epoch": 0.7282451142100265,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004955439268457252,
|
|
"loss": 6.045,
|
|
"mean_token_accuracy": 0.15405199602246283,
|
|
"num_tokens": 14266114.0,
|
|
"step": 7285
|
|
},
|
|
{
|
|
"entropy": 6.28690390586853,
|
|
"epoch": 0.728744939271255,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004955368564297449,
|
|
"loss": 6.0692,
|
|
"mean_token_accuracy": 0.15843201130628587,
|
|
"num_tokens": 14276048.0,
|
|
"step": 7290
|
|
},
|
|
{
|
|
"entropy": 6.310165357589722,
|
|
"epoch": 0.7292447643324836,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004955297804651142,
|
|
"loss": 5.9545,
|
|
"mean_token_accuracy": 0.16382774114608764,
|
|
"num_tokens": 14285225.0,
|
|
"step": 7295
|
|
},
|
|
{
|
|
"entropy": 6.393028450012207,
|
|
"epoch": 0.7297445893937122,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004955226989520107,
|
|
"loss": 6.021,
|
|
"mean_token_accuracy": 0.15758152678608894,
|
|
"num_tokens": 14295566.0,
|
|
"step": 7300
|
|
},
|
|
{
|
|
"entropy": 6.297847747802734,
|
|
"epoch": 0.7302444144549408,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000495515611890613,
|
|
"loss": 6.0322,
|
|
"mean_token_accuracy": 0.15654397904872894,
|
|
"num_tokens": 14305072.0,
|
|
"step": 7305
|
|
},
|
|
{
|
|
"entropy": 6.228882741928101,
|
|
"epoch": 0.7307442395161693,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004955085192810993,
|
|
"loss": 5.8721,
|
|
"mean_token_accuracy": 0.16369707733392716,
|
|
"num_tokens": 14315273.0,
|
|
"step": 7310
|
|
},
|
|
{
|
|
"entropy": 6.357260704040527,
|
|
"epoch": 0.7312440645773979,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004955014211236479,
|
|
"loss": 6.0891,
|
|
"mean_token_accuracy": 0.1517564371228218,
|
|
"num_tokens": 14324818.0,
|
|
"step": 7315
|
|
},
|
|
{
|
|
"entropy": 6.319687032699585,
|
|
"epoch": 0.7317438896386265,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004954943174184375,
|
|
"loss": 6.1402,
|
|
"mean_token_accuracy": 0.15445371568202973,
|
|
"num_tokens": 14335129.0,
|
|
"step": 7320
|
|
},
|
|
{
|
|
"entropy": 6.346318769454956,
|
|
"epoch": 0.732243714699855,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004954872081656469,
|
|
"loss": 6.1243,
|
|
"mean_token_accuracy": 0.14883216470479965,
|
|
"num_tokens": 14344339.0,
|
|
"step": 7325
|
|
},
|
|
{
|
|
"entropy": 6.372745370864868,
|
|
"epoch": 0.7327435397610836,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004954800933654548,
|
|
"loss": 6.0556,
|
|
"mean_token_accuracy": 0.1492668554186821,
|
|
"num_tokens": 14353391.0,
|
|
"step": 7330
|
|
},
|
|
{
|
|
"entropy": 6.425935125350952,
|
|
"epoch": 0.7332433648223122,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004954729730180403,
|
|
"loss": 6.1897,
|
|
"mean_token_accuracy": 0.15134270042181014,
|
|
"num_tokens": 14363684.0,
|
|
"step": 7335
|
|
},
|
|
{
|
|
"entropy": 6.320706415176391,
|
|
"epoch": 0.7337431898835408,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004954658471235825,
|
|
"loss": 6.0673,
|
|
"mean_token_accuracy": 0.1559371069073677,
|
|
"num_tokens": 14372802.0,
|
|
"step": 7340
|
|
},
|
|
{
|
|
"entropy": 6.352352333068848,
|
|
"epoch": 0.7342430149447693,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004954587156822607,
|
|
"loss": 6.0945,
|
|
"mean_token_accuracy": 0.14530139714479445,
|
|
"num_tokens": 14382665.0,
|
|
"step": 7345
|
|
},
|
|
{
|
|
"entropy": 6.323452091217041,
|
|
"epoch": 0.7347428400059979,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004954515786942544,
|
|
"loss": 6.0524,
|
|
"mean_token_accuracy": 0.15289186835289,
|
|
"num_tokens": 14393631.0,
|
|
"step": 7350
|
|
},
|
|
{
|
|
"entropy": 6.35225191116333,
|
|
"epoch": 0.7352426650672265,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000495444436159743,
|
|
"loss": 6.0698,
|
|
"mean_token_accuracy": 0.15652450323104858,
|
|
"num_tokens": 14402713.0,
|
|
"step": 7355
|
|
},
|
|
{
|
|
"entropy": 6.407626104354859,
|
|
"epoch": 0.735742490128455,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004954372880789064,
|
|
"loss": 6.2033,
|
|
"mean_token_accuracy": 0.14676266089081763,
|
|
"num_tokens": 14412777.0,
|
|
"step": 7360
|
|
},
|
|
{
|
|
"entropy": 6.352416038513184,
|
|
"epoch": 0.7362423151896836,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004954301344519244,
|
|
"loss": 6.1302,
|
|
"mean_token_accuracy": 0.15103916823863983,
|
|
"num_tokens": 14422839.0,
|
|
"step": 7365
|
|
},
|
|
{
|
|
"entropy": 6.234886693954468,
|
|
"epoch": 0.7367421402509122,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004954229752789769,
|
|
"loss": 6.0122,
|
|
"mean_token_accuracy": 0.15759240835905075,
|
|
"num_tokens": 14433239.0,
|
|
"step": 7370
|
|
},
|
|
{
|
|
"entropy": 6.348111581802368,
|
|
"epoch": 0.7372419653121407,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004954158105602441,
|
|
"loss": 6.1149,
|
|
"mean_token_accuracy": 0.1497027561068535,
|
|
"num_tokens": 14442907.0,
|
|
"step": 7375
|
|
},
|
|
{
|
|
"entropy": 6.290708065032959,
|
|
"epoch": 0.7377417903733693,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004954086402959061,
|
|
"loss": 5.9551,
|
|
"mean_token_accuracy": 0.15731109082698821,
|
|
"num_tokens": 14452492.0,
|
|
"step": 7380
|
|
},
|
|
{
|
|
"entropy": 6.335931253433228,
|
|
"epoch": 0.7382416154345979,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004954014644861435,
|
|
"loss": 6.1077,
|
|
"mean_token_accuracy": 0.14976682364940644,
|
|
"num_tokens": 14461353.0,
|
|
"step": 7385
|
|
},
|
|
{
|
|
"entropy": 6.275920867919922,
|
|
"epoch": 0.7387414404958265,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004953942831311367,
|
|
"loss": 5.9842,
|
|
"mean_token_accuracy": 0.16973174065351487,
|
|
"num_tokens": 14470579.0,
|
|
"step": 7390
|
|
},
|
|
{
|
|
"entropy": 6.271680068969727,
|
|
"epoch": 0.739241265557055,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004953870962310666,
|
|
"loss": 5.9459,
|
|
"mean_token_accuracy": 0.16496060639619828,
|
|
"num_tokens": 14481608.0,
|
|
"step": 7395
|
|
},
|
|
{
|
|
"entropy": 6.312617778778076,
|
|
"epoch": 0.7397410906182836,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004953799037861138,
|
|
"loss": 6.1275,
|
|
"mean_token_accuracy": 0.15205059200525284,
|
|
"num_tokens": 14493074.0,
|
|
"step": 7400
|
|
},
|
|
{
|
|
"entropy": 6.312835025787353,
|
|
"epoch": 0.7402409156795122,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004953727057964594,
|
|
"loss": 5.9817,
|
|
"mean_token_accuracy": 0.16150762885808945,
|
|
"num_tokens": 14502469.0,
|
|
"step": 7405
|
|
},
|
|
{
|
|
"entropy": 6.3073982238769535,
|
|
"epoch": 0.7407407407407407,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004953655022622843,
|
|
"loss": 6.1209,
|
|
"mean_token_accuracy": 0.15200251787900926,
|
|
"num_tokens": 14512939.0,
|
|
"step": 7410
|
|
},
|
|
{
|
|
"entropy": 6.349795389175415,
|
|
"epoch": 0.7412405658019693,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004953582931837699,
|
|
"loss": 6.1168,
|
|
"mean_token_accuracy": 0.15250215232372283,
|
|
"num_tokens": 14522681.0,
|
|
"step": 7415
|
|
},
|
|
{
|
|
"entropy": 6.332542037963867,
|
|
"epoch": 0.7417403908631979,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004953510785610976,
|
|
"loss": 5.9724,
|
|
"mean_token_accuracy": 0.1658090427517891,
|
|
"num_tokens": 14532115.0,
|
|
"step": 7420
|
|
},
|
|
{
|
|
"entropy": 6.289231538772583,
|
|
"epoch": 0.7422402159244265,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004953438583944487,
|
|
"loss": 6.0547,
|
|
"mean_token_accuracy": 0.15433966666460036,
|
|
"num_tokens": 14541147.0,
|
|
"step": 7425
|
|
},
|
|
{
|
|
"entropy": 6.300818347930909,
|
|
"epoch": 0.742740040985655,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004953366326840052,
|
|
"loss": 6.1087,
|
|
"mean_token_accuracy": 0.15979793667793274,
|
|
"num_tokens": 14550373.0,
|
|
"step": 7430
|
|
},
|
|
{
|
|
"entropy": 6.402552652359009,
|
|
"epoch": 0.7432398660468836,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004953294014299486,
|
|
"loss": 6.1188,
|
|
"mean_token_accuracy": 0.16001539453864097,
|
|
"num_tokens": 14559396.0,
|
|
"step": 7435
|
|
},
|
|
{
|
|
"entropy": 6.38272271156311,
|
|
"epoch": 0.7437396911081121,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004953221646324611,
|
|
"loss": 6.1602,
|
|
"mean_token_accuracy": 0.14881806969642639,
|
|
"num_tokens": 14570292.0,
|
|
"step": 7440
|
|
},
|
|
{
|
|
"entropy": 6.283556222915649,
|
|
"epoch": 0.7442395161693407,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004953149222917245,
|
|
"loss": 6.026,
|
|
"mean_token_accuracy": 0.15976691395044326,
|
|
"num_tokens": 14579887.0,
|
|
"step": 7445
|
|
},
|
|
{
|
|
"entropy": 6.357969188690186,
|
|
"epoch": 0.7447393412305693,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004953076744079213,
|
|
"loss": 6.1131,
|
|
"mean_token_accuracy": 0.15271517336368562,
|
|
"num_tokens": 14590260.0,
|
|
"step": 7450
|
|
},
|
|
{
|
|
"entropy": 6.363396072387696,
|
|
"epoch": 0.7452391662917979,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004953004209812335,
|
|
"loss": 6.0402,
|
|
"mean_token_accuracy": 0.15461803376674652,
|
|
"num_tokens": 14599812.0,
|
|
"step": 7455
|
|
},
|
|
{
|
|
"entropy": 6.293329191207886,
|
|
"epoch": 0.7457389913530265,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004952931620118439,
|
|
"loss": 5.9757,
|
|
"mean_token_accuracy": 0.15982502102851867,
|
|
"num_tokens": 14609147.0,
|
|
"step": 7460
|
|
},
|
|
{
|
|
"entropy": 6.341886711120606,
|
|
"epoch": 0.746238816414255,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004952858974999351,
|
|
"loss": 6.0962,
|
|
"mean_token_accuracy": 0.14547627791762352,
|
|
"num_tokens": 14618834.0,
|
|
"step": 7465
|
|
},
|
|
{
|
|
"entropy": 6.281481456756592,
|
|
"epoch": 0.7467386414754836,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004952786274456896,
|
|
"loss": 5.9894,
|
|
"mean_token_accuracy": 0.16308936029672622,
|
|
"num_tokens": 14628556.0,
|
|
"step": 7470
|
|
},
|
|
{
|
|
"entropy": 6.282746362686157,
|
|
"epoch": 0.7472384665367121,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004952713518492907,
|
|
"loss": 6.0668,
|
|
"mean_token_accuracy": 0.15337453484535218,
|
|
"num_tokens": 14637486.0,
|
|
"step": 7475
|
|
},
|
|
{
|
|
"entropy": 6.285450553894043,
|
|
"epoch": 0.7477382915979407,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004952640707109213,
|
|
"loss": 6.0511,
|
|
"mean_token_accuracy": 0.1565631791949272,
|
|
"num_tokens": 14647599.0,
|
|
"step": 7480
|
|
},
|
|
{
|
|
"entropy": 6.3424841403961185,
|
|
"epoch": 0.7482381166591693,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004952567840307644,
|
|
"loss": 5.9472,
|
|
"mean_token_accuracy": 0.16097092032432556,
|
|
"num_tokens": 14656246.0,
|
|
"step": 7485
|
|
},
|
|
{
|
|
"entropy": 6.290265703201294,
|
|
"epoch": 0.7487379417203979,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004952494918090036,
|
|
"loss": 6.0838,
|
|
"mean_token_accuracy": 0.15815743207931518,
|
|
"num_tokens": 14665550.0,
|
|
"step": 7490
|
|
},
|
|
{
|
|
"entropy": 6.348566484451294,
|
|
"epoch": 0.7492377667816265,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004952421940458222,
|
|
"loss": 6.0857,
|
|
"mean_token_accuracy": 0.1551155313849449,
|
|
"num_tokens": 14676462.0,
|
|
"step": 7495
|
|
},
|
|
{
|
|
"entropy": 6.268645429611206,
|
|
"epoch": 0.749737591842855,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004952348907414039,
|
|
"loss": 5.9432,
|
|
"mean_token_accuracy": 0.16161280274391174,
|
|
"num_tokens": 14685963.0,
|
|
"step": 7500
|
|
},
|
|
{
|
|
"entropy": 6.269847679138183,
|
|
"epoch": 0.7502374169040835,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004952275818959325,
|
|
"loss": 6.0696,
|
|
"mean_token_accuracy": 0.15773803144693374,
|
|
"num_tokens": 14695764.0,
|
|
"step": 7505
|
|
},
|
|
{
|
|
"entropy": 6.284567880630493,
|
|
"epoch": 0.7507372419653121,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004952202675095916,
|
|
"loss": 6.0188,
|
|
"mean_token_accuracy": 0.16041758805513381,
|
|
"num_tokens": 14705839.0,
|
|
"step": 7510
|
|
},
|
|
{
|
|
"entropy": 6.308699750900269,
|
|
"epoch": 0.7512370670265407,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004952129475825657,
|
|
"loss": 5.999,
|
|
"mean_token_accuracy": 0.1592727228999138,
|
|
"num_tokens": 14714801.0,
|
|
"step": 7515
|
|
},
|
|
{
|
|
"entropy": 6.369070196151734,
|
|
"epoch": 0.7517368920877693,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004952056221150385,
|
|
"loss": 6.1093,
|
|
"mean_token_accuracy": 0.15584300011396407,
|
|
"num_tokens": 14723803.0,
|
|
"step": 7520
|
|
},
|
|
{
|
|
"entropy": 6.301577520370484,
|
|
"epoch": 0.7522367171489979,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004951982911071945,
|
|
"loss": 6.0071,
|
|
"mean_token_accuracy": 0.1624963477253914,
|
|
"num_tokens": 14732598.0,
|
|
"step": 7525
|
|
},
|
|
{
|
|
"entropy": 6.339388418197632,
|
|
"epoch": 0.7527365422102265,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004951909545592183,
|
|
"loss": 6.0743,
|
|
"mean_token_accuracy": 0.1598440870642662,
|
|
"num_tokens": 14742598.0,
|
|
"step": 7530
|
|
},
|
|
{
|
|
"entropy": 6.332610321044922,
|
|
"epoch": 0.753236367271455,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004951836124712942,
|
|
"loss": 6.0829,
|
|
"mean_token_accuracy": 0.160172039270401,
|
|
"num_tokens": 14751434.0,
|
|
"step": 7535
|
|
},
|
|
{
|
|
"entropy": 6.3407433986663815,
|
|
"epoch": 0.7537361923326835,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004951762648436073,
|
|
"loss": 6.0855,
|
|
"mean_token_accuracy": 0.15404346212744713,
|
|
"num_tokens": 14760661.0,
|
|
"step": 7540
|
|
},
|
|
{
|
|
"entropy": 6.353408908843994,
|
|
"epoch": 0.7542360173939121,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004951689116763419,
|
|
"loss": 6.0778,
|
|
"mean_token_accuracy": 0.1475398376584053,
|
|
"num_tokens": 14770431.0,
|
|
"step": 7545
|
|
},
|
|
{
|
|
"entropy": 6.3286073207855225,
|
|
"epoch": 0.7547358424551407,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004951615529696835,
|
|
"loss": 6.0835,
|
|
"mean_token_accuracy": 0.15042700469493867,
|
|
"num_tokens": 14780066.0,
|
|
"step": 7550
|
|
},
|
|
{
|
|
"entropy": 6.36154146194458,
|
|
"epoch": 0.7552356675163693,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004951541887238172,
|
|
"loss": 6.0905,
|
|
"mean_token_accuracy": 0.16041741371154786,
|
|
"num_tokens": 14789531.0,
|
|
"step": 7555
|
|
},
|
|
{
|
|
"entropy": 6.329356575012207,
|
|
"epoch": 0.7557354925775979,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004951468189389281,
|
|
"loss": 5.9914,
|
|
"mean_token_accuracy": 0.15692398101091384,
|
|
"num_tokens": 14799000.0,
|
|
"step": 7560
|
|
},
|
|
{
|
|
"entropy": 6.328855562210083,
|
|
"epoch": 0.7562353176388265,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004951394436152016,
|
|
"loss": 6.0338,
|
|
"mean_token_accuracy": 0.1653498664498329,
|
|
"num_tokens": 14808991.0,
|
|
"step": 7565
|
|
},
|
|
{
|
|
"entropy": 6.308737134933471,
|
|
"epoch": 0.7567351427000549,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004951320627528234,
|
|
"loss": 6.062,
|
|
"mean_token_accuracy": 0.1673951506614685,
|
|
"num_tokens": 14819351.0,
|
|
"step": 7570
|
|
},
|
|
{
|
|
"entropy": 6.293022918701172,
|
|
"epoch": 0.7572349677612835,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004951246763519791,
|
|
"loss": 6.0977,
|
|
"mean_token_accuracy": 0.15020481944084169,
|
|
"num_tokens": 14828924.0,
|
|
"step": 7575
|
|
},
|
|
{
|
|
"entropy": 6.486008167266846,
|
|
"epoch": 0.7577347928225121,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004951172844128546,
|
|
"loss": 6.2263,
|
|
"mean_token_accuracy": 0.13779762610793114,
|
|
"num_tokens": 14841077.0,
|
|
"step": 7580
|
|
},
|
|
{
|
|
"entropy": 6.404449224472046,
|
|
"epoch": 0.7582346178837407,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004951098869356358,
|
|
"loss": 6.1409,
|
|
"mean_token_accuracy": 0.14772530198097228,
|
|
"num_tokens": 14851223.0,
|
|
"step": 7585
|
|
},
|
|
{
|
|
"entropy": 6.319031763076782,
|
|
"epoch": 0.7587344429449693,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000495102483920509,
|
|
"loss": 6.0015,
|
|
"mean_token_accuracy": 0.15831595212221145,
|
|
"num_tokens": 14861003.0,
|
|
"step": 7590
|
|
},
|
|
{
|
|
"entropy": 6.362440824508667,
|
|
"epoch": 0.7592342680061979,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004950950753676603,
|
|
"loss": 6.1243,
|
|
"mean_token_accuracy": 0.15234379321336747,
|
|
"num_tokens": 14870207.0,
|
|
"step": 7595
|
|
},
|
|
{
|
|
"entropy": 6.239006471633911,
|
|
"epoch": 0.7597340930674265,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004950876612772763,
|
|
"loss": 6.0222,
|
|
"mean_token_accuracy": 0.1556150048971176,
|
|
"num_tokens": 14879886.0,
|
|
"step": 7600
|
|
},
|
|
{
|
|
"entropy": 6.249630975723266,
|
|
"epoch": 0.7602339181286549,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004950802416495431,
|
|
"loss": 5.998,
|
|
"mean_token_accuracy": 0.1585118979215622,
|
|
"num_tokens": 14889275.0,
|
|
"step": 7605
|
|
},
|
|
{
|
|
"entropy": 6.38168511390686,
|
|
"epoch": 0.7607337431898835,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004950728164846478,
|
|
"loss": 6.0967,
|
|
"mean_token_accuracy": 0.154704949259758,
|
|
"num_tokens": 14898317.0,
|
|
"step": 7610
|
|
},
|
|
{
|
|
"entropy": 6.2991108894348145,
|
|
"epoch": 0.7612335682511121,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004950653857827771,
|
|
"loss": 6.0152,
|
|
"mean_token_accuracy": 0.1585605561733246,
|
|
"num_tokens": 14907183.0,
|
|
"step": 7615
|
|
},
|
|
{
|
|
"entropy": 6.289191198348999,
|
|
"epoch": 0.7617333933123407,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004950579495441177,
|
|
"loss": 6.1565,
|
|
"mean_token_accuracy": 0.15245688557624817,
|
|
"num_tokens": 14917564.0,
|
|
"step": 7620
|
|
},
|
|
{
|
|
"entropy": 6.339101552963257,
|
|
"epoch": 0.7622332183735693,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004950505077688572,
|
|
"loss": 5.9979,
|
|
"mean_token_accuracy": 0.161814321577549,
|
|
"num_tokens": 14927102.0,
|
|
"step": 7625
|
|
},
|
|
{
|
|
"entropy": 6.236083555221557,
|
|
"epoch": 0.7627330434347979,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004950430604571824,
|
|
"loss": 5.891,
|
|
"mean_token_accuracy": 0.17401071041822433,
|
|
"num_tokens": 14937934.0,
|
|
"step": 7630
|
|
},
|
|
{
|
|
"entropy": 6.33174147605896,
|
|
"epoch": 0.7632328684960263,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004950356076092808,
|
|
"loss": 6.0419,
|
|
"mean_token_accuracy": 0.1568172812461853,
|
|
"num_tokens": 14948109.0,
|
|
"step": 7635
|
|
},
|
|
{
|
|
"entropy": 6.32998366355896,
|
|
"epoch": 0.7637326935572549,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00049502814922534,
|
|
"loss": 6.0861,
|
|
"mean_token_accuracy": 0.15185921490192414,
|
|
"num_tokens": 14956971.0,
|
|
"step": 7640
|
|
},
|
|
{
|
|
"entropy": 6.3382265090942385,
|
|
"epoch": 0.7642325186184835,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004950206853055475,
|
|
"loss": 6.0427,
|
|
"mean_token_accuracy": 0.16388896405696868,
|
|
"num_tokens": 14967046.0,
|
|
"step": 7645
|
|
},
|
|
{
|
|
"entropy": 6.33615403175354,
|
|
"epoch": 0.7647323436797121,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004950132158500913,
|
|
"loss": 6.03,
|
|
"mean_token_accuracy": 0.15015559047460555,
|
|
"num_tokens": 14976234.0,
|
|
"step": 7650
|
|
},
|
|
{
|
|
"entropy": 6.213335418701172,
|
|
"epoch": 0.7652321687409407,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004950057408591591,
|
|
"loss": 5.9746,
|
|
"mean_token_accuracy": 0.16839360147714616,
|
|
"num_tokens": 14985205.0,
|
|
"step": 7655
|
|
},
|
|
{
|
|
"entropy": 6.24402346611023,
|
|
"epoch": 0.7657319938021693,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004949982603329391,
|
|
"loss": 5.9755,
|
|
"mean_token_accuracy": 0.16419958919286728,
|
|
"num_tokens": 14994233.0,
|
|
"step": 7660
|
|
},
|
|
{
|
|
"entropy": 6.288731050491333,
|
|
"epoch": 0.7662318188633979,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004949907742716195,
|
|
"loss": 6.0018,
|
|
"mean_token_accuracy": 0.15989499390125275,
|
|
"num_tokens": 15004001.0,
|
|
"step": 7665
|
|
},
|
|
{
|
|
"entropy": 6.40303406715393,
|
|
"epoch": 0.7667316439246263,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004949832826753886,
|
|
"loss": 6.0547,
|
|
"mean_token_accuracy": 0.1487782247364521,
|
|
"num_tokens": 15015046.0,
|
|
"step": 7670
|
|
},
|
|
{
|
|
"entropy": 6.278237056732178,
|
|
"epoch": 0.7672314689858549,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000494975785544435,
|
|
"loss": 5.995,
|
|
"mean_token_accuracy": 0.15508314371109008,
|
|
"num_tokens": 15025404.0,
|
|
"step": 7675
|
|
},
|
|
{
|
|
"entropy": 6.331465864181519,
|
|
"epoch": 0.7677312940470835,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004949682828789472,
|
|
"loss": 6.0805,
|
|
"mean_token_accuracy": 0.14965164363384248,
|
|
"num_tokens": 15036160.0,
|
|
"step": 7680
|
|
},
|
|
{
|
|
"entropy": 6.277357912063598,
|
|
"epoch": 0.7682311191083121,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000494960774679114,
|
|
"loss": 6.0086,
|
|
"mean_token_accuracy": 0.16053372919559478,
|
|
"num_tokens": 15046356.0,
|
|
"step": 7685
|
|
},
|
|
{
|
|
"entropy": 6.292904233932495,
|
|
"epoch": 0.7687309441695407,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004949532609451242,
|
|
"loss": 5.9958,
|
|
"mean_token_accuracy": 0.1582586422562599,
|
|
"num_tokens": 15056101.0,
|
|
"step": 7690
|
|
},
|
|
{
|
|
"entropy": 6.307175350189209,
|
|
"epoch": 0.7692307692307693,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004949457416771671,
|
|
"loss": 6.0047,
|
|
"mean_token_accuracy": 0.1672866091132164,
|
|
"num_tokens": 15065726.0,
|
|
"step": 7695
|
|
},
|
|
{
|
|
"entropy": 6.265319299697876,
|
|
"epoch": 0.7697305942919977,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004949382168754316,
|
|
"loss": 6.0023,
|
|
"mean_token_accuracy": 0.16166395097970962,
|
|
"num_tokens": 15075211.0,
|
|
"step": 7700
|
|
},
|
|
{
|
|
"entropy": 6.253762483596802,
|
|
"epoch": 0.7702304193532263,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004949306865401073,
|
|
"loss": 5.9046,
|
|
"mean_token_accuracy": 0.16504451781511306,
|
|
"num_tokens": 15085525.0,
|
|
"step": 7705
|
|
},
|
|
{
|
|
"entropy": 6.340442562103272,
|
|
"epoch": 0.7707302444144549,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004949231506713833,
|
|
"loss": 6.0988,
|
|
"mean_token_accuracy": 0.14864008128643036,
|
|
"num_tokens": 15093851.0,
|
|
"step": 7710
|
|
},
|
|
{
|
|
"entropy": 6.417589330673218,
|
|
"epoch": 0.7712300694756835,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004949156092694496,
|
|
"loss": 6.1718,
|
|
"mean_token_accuracy": 0.15148043632507324,
|
|
"num_tokens": 15104066.0,
|
|
"step": 7715
|
|
},
|
|
{
|
|
"entropy": 6.343349885940552,
|
|
"epoch": 0.7717298945369121,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004949080623344958,
|
|
"loss": 6.0174,
|
|
"mean_token_accuracy": 0.16413416117429733,
|
|
"num_tokens": 15114047.0,
|
|
"step": 7720
|
|
},
|
|
{
|
|
"entropy": 6.291923236846924,
|
|
"epoch": 0.7722297195981407,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004949005098667117,
|
|
"loss": 6.0302,
|
|
"mean_token_accuracy": 0.1616566374897957,
|
|
"num_tokens": 15123719.0,
|
|
"step": 7725
|
|
},
|
|
{
|
|
"entropy": 6.273437070846557,
|
|
"epoch": 0.7727295446593693,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004948929518662873,
|
|
"loss": 6.0762,
|
|
"mean_token_accuracy": 0.15936142727732658,
|
|
"num_tokens": 15133978.0,
|
|
"step": 7730
|
|
},
|
|
{
|
|
"entropy": 6.3448058605194095,
|
|
"epoch": 0.7732293697205977,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004948853883334129,
|
|
"loss": 6.1028,
|
|
"mean_token_accuracy": 0.15688480734825133,
|
|
"num_tokens": 15145058.0,
|
|
"step": 7735
|
|
},
|
|
{
|
|
"entropy": 6.401759910583496,
|
|
"epoch": 0.7737291947818263,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004948778192682787,
|
|
"loss": 6.0856,
|
|
"mean_token_accuracy": 0.15542424619197845,
|
|
"num_tokens": 15155400.0,
|
|
"step": 7740
|
|
},
|
|
{
|
|
"entropy": 6.276227903366089,
|
|
"epoch": 0.7742290198430549,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000494870244671075,
|
|
"loss": 5.9725,
|
|
"mean_token_accuracy": 0.1656661108136177,
|
|
"num_tokens": 15164969.0,
|
|
"step": 7745
|
|
},
|
|
{
|
|
"entropy": 6.2992761611938475,
|
|
"epoch": 0.7747288449042835,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004948626645419926,
|
|
"loss": 5.9961,
|
|
"mean_token_accuracy": 0.16712433993816375,
|
|
"num_tokens": 15173840.0,
|
|
"step": 7750
|
|
},
|
|
{
|
|
"entropy": 6.325164842605591,
|
|
"epoch": 0.7752286699655121,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004948550788812222,
|
|
"loss": 6.1298,
|
|
"mean_token_accuracy": 0.14570028707385063,
|
|
"num_tokens": 15184541.0,
|
|
"step": 7755
|
|
},
|
|
{
|
|
"entropy": 6.319697713851928,
|
|
"epoch": 0.7757284950267407,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004948474876889545,
|
|
"loss": 6.0815,
|
|
"mean_token_accuracy": 0.156877700984478,
|
|
"num_tokens": 15195060.0,
|
|
"step": 7760
|
|
},
|
|
{
|
|
"entropy": 6.3745880126953125,
|
|
"epoch": 0.7762283200879692,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004948398909653806,
|
|
"loss": 6.0774,
|
|
"mean_token_accuracy": 0.15215039253234863,
|
|
"num_tokens": 15206093.0,
|
|
"step": 7765
|
|
},
|
|
{
|
|
"entropy": 6.339943838119507,
|
|
"epoch": 0.7767281451491977,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004948322887106917,
|
|
"loss": 6.0568,
|
|
"mean_token_accuracy": 0.15105302929878234,
|
|
"num_tokens": 15215359.0,
|
|
"step": 7770
|
|
},
|
|
{
|
|
"entropy": 6.287955093383789,
|
|
"epoch": 0.7772279702104263,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004948246809250788,
|
|
"loss": 6.0727,
|
|
"mean_token_accuracy": 0.15486107170581817,
|
|
"num_tokens": 15225283.0,
|
|
"step": 7775
|
|
},
|
|
{
|
|
"entropy": 6.2795709609985355,
|
|
"epoch": 0.7777277952716549,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004948170676087338,
|
|
"loss": 5.9447,
|
|
"mean_token_accuracy": 0.1627866581082344,
|
|
"num_tokens": 15234319.0,
|
|
"step": 7780
|
|
},
|
|
{
|
|
"entropy": 6.298702716827393,
|
|
"epoch": 0.7782276203328835,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004948094487618476,
|
|
"loss": 5.9503,
|
|
"mean_token_accuracy": 0.16435001492500306,
|
|
"num_tokens": 15244410.0,
|
|
"step": 7785
|
|
},
|
|
{
|
|
"entropy": 6.270851993560791,
|
|
"epoch": 0.7787274453941121,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004948018243846126,
|
|
"loss": 5.998,
|
|
"mean_token_accuracy": 0.15858768075704574,
|
|
"num_tokens": 15253431.0,
|
|
"step": 7790
|
|
},
|
|
{
|
|
"entropy": 6.276344871520996,
|
|
"epoch": 0.7792272704553407,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004947941944772199,
|
|
"loss": 6.0365,
|
|
"mean_token_accuracy": 0.15742659866809844,
|
|
"num_tokens": 15262566.0,
|
|
"step": 7795
|
|
},
|
|
{
|
|
"entropy": 6.425141429901123,
|
|
"epoch": 0.7797270955165692,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000494786559039862,
|
|
"loss": 6.1204,
|
|
"mean_token_accuracy": 0.15137385129928588,
|
|
"num_tokens": 15272122.0,
|
|
"step": 7800
|
|
},
|
|
{
|
|
"entropy": 6.359556198120117,
|
|
"epoch": 0.7802269205777977,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004947789180727308,
|
|
"loss": 6.0816,
|
|
"mean_token_accuracy": 0.15132945254445077,
|
|
"num_tokens": 15281165.0,
|
|
"step": 7805
|
|
},
|
|
{
|
|
"entropy": 6.255874872207642,
|
|
"epoch": 0.7807267456390263,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004947712715760186,
|
|
"loss": 6.0336,
|
|
"mean_token_accuracy": 0.15571321696043014,
|
|
"num_tokens": 15290992.0,
|
|
"step": 7810
|
|
},
|
|
{
|
|
"entropy": 6.416817474365234,
|
|
"epoch": 0.7812265707002549,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004947636195499177,
|
|
"loss": 6.0613,
|
|
"mean_token_accuracy": 0.15470456779003144,
|
|
"num_tokens": 15300454.0,
|
|
"step": 7815
|
|
},
|
|
{
|
|
"entropy": 6.330163240432739,
|
|
"epoch": 0.7817263957614835,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004947559619946207,
|
|
"loss": 6.009,
|
|
"mean_token_accuracy": 0.16466774940490722,
|
|
"num_tokens": 15310471.0,
|
|
"step": 7820
|
|
},
|
|
{
|
|
"entropy": 6.31559648513794,
|
|
"epoch": 0.7822262208227121,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004947482989103203,
|
|
"loss": 6.0913,
|
|
"mean_token_accuracy": 0.1510937914252281,
|
|
"num_tokens": 15320554.0,
|
|
"step": 7825
|
|
},
|
|
{
|
|
"entropy": 6.292080879211426,
|
|
"epoch": 0.7827260458839406,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004947406302972092,
|
|
"loss": 6.1229,
|
|
"mean_token_accuracy": 0.15209597572684289,
|
|
"num_tokens": 15331623.0,
|
|
"step": 7830
|
|
},
|
|
{
|
|
"entropy": 6.3830437660217285,
|
|
"epoch": 0.7832258709451692,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004947329561554804,
|
|
"loss": 5.9978,
|
|
"mean_token_accuracy": 0.15783745497465135,
|
|
"num_tokens": 15340954.0,
|
|
"step": 7835
|
|
},
|
|
{
|
|
"entropy": 6.3216980457305905,
|
|
"epoch": 0.7837256960063977,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004947252764853269,
|
|
"loss": 6.0846,
|
|
"mean_token_accuracy": 0.15559569448232652,
|
|
"num_tokens": 15350858.0,
|
|
"step": 7840
|
|
},
|
|
{
|
|
"entropy": 6.303387069702149,
|
|
"epoch": 0.7842255210676263,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004947175912869421,
|
|
"loss": 5.9876,
|
|
"mean_token_accuracy": 0.15498465597629546,
|
|
"num_tokens": 15360382.0,
|
|
"step": 7845
|
|
},
|
|
{
|
|
"entropy": 6.305787086486816,
|
|
"epoch": 0.7847253461288549,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004947099005605191,
|
|
"loss": 6.08,
|
|
"mean_token_accuracy": 0.15489040389657022,
|
|
"num_tokens": 15370626.0,
|
|
"step": 7850
|
|
},
|
|
{
|
|
"entropy": 6.339403247833252,
|
|
"epoch": 0.7852251711900835,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004947022043062517,
|
|
"loss": 6.0591,
|
|
"mean_token_accuracy": 0.1591949924826622,
|
|
"num_tokens": 15379582.0,
|
|
"step": 7855
|
|
},
|
|
{
|
|
"entropy": 6.305923986434936,
|
|
"epoch": 0.7857249962513121,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004946945025243333,
|
|
"loss": 5.9576,
|
|
"mean_token_accuracy": 0.16097877770662308,
|
|
"num_tokens": 15390168.0,
|
|
"step": 7860
|
|
},
|
|
{
|
|
"entropy": 6.185457229614258,
|
|
"epoch": 0.7862248213125406,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004946867952149577,
|
|
"loss": 5.9029,
|
|
"mean_token_accuracy": 0.17234977185726166,
|
|
"num_tokens": 15400979.0,
|
|
"step": 7865
|
|
},
|
|
{
|
|
"entropy": 6.325086879730224,
|
|
"epoch": 0.7867246463737692,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004946790823783189,
|
|
"loss": 6.0043,
|
|
"mean_token_accuracy": 0.1578134700655937,
|
|
"num_tokens": 15409954.0,
|
|
"step": 7870
|
|
},
|
|
{
|
|
"entropy": 6.296181631088257,
|
|
"epoch": 0.7872244714349977,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000494671364014611,
|
|
"loss": 6.0902,
|
|
"mean_token_accuracy": 0.1527877777814865,
|
|
"num_tokens": 15419539.0,
|
|
"step": 7875
|
|
},
|
|
{
|
|
"entropy": 6.252876901626587,
|
|
"epoch": 0.7877242964962263,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000494663640124028,
|
|
"loss": 6.0102,
|
|
"mean_token_accuracy": 0.15679827108979225,
|
|
"num_tokens": 15428751.0,
|
|
"step": 7880
|
|
},
|
|
{
|
|
"entropy": 6.2969481468200685,
|
|
"epoch": 0.7882241215574549,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004946559107067643,
|
|
"loss": 6.0493,
|
|
"mean_token_accuracy": 0.16218971014022826,
|
|
"num_tokens": 15438466.0,
|
|
"step": 7885
|
|
},
|
|
{
|
|
"entropy": 6.264706182479858,
|
|
"epoch": 0.7887239466186835,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004946481757630146,
|
|
"loss": 6.0204,
|
|
"mean_token_accuracy": 0.1577471151947975,
|
|
"num_tokens": 15448395.0,
|
|
"step": 7890
|
|
},
|
|
{
|
|
"entropy": 6.295848035812378,
|
|
"epoch": 0.789223771679912,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004946404352929732,
|
|
"loss": 6.054,
|
|
"mean_token_accuracy": 0.15462035834789276,
|
|
"num_tokens": 15457986.0,
|
|
"step": 7895
|
|
},
|
|
{
|
|
"entropy": 6.314553117752075,
|
|
"epoch": 0.7897235967411406,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.000494632689296835,
|
|
"loss": 6.0428,
|
|
"mean_token_accuracy": 0.15846251398324968,
|
|
"num_tokens": 15467989.0,
|
|
"step": 7900
|
|
},
|
|
{
|
|
"entropy": 6.316967582702636,
|
|
"epoch": 0.7902234218023692,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004946249377747947,
|
|
"loss": 5.9373,
|
|
"mean_token_accuracy": 0.1606815442442894,
|
|
"num_tokens": 15477537.0,
|
|
"step": 7905
|
|
},
|
|
{
|
|
"entropy": 6.322283792495727,
|
|
"epoch": 0.7907232468635977,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004946171807270476,
|
|
"loss": 6.0101,
|
|
"mean_token_accuracy": 0.15901870280504227,
|
|
"num_tokens": 15488007.0,
|
|
"step": 7910
|
|
},
|
|
{
|
|
"entropy": 6.294283628463745,
|
|
"epoch": 0.7912230719248263,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004946094181537887,
|
|
"loss": 6.0399,
|
|
"mean_token_accuracy": 0.15930212587118148,
|
|
"num_tokens": 15498122.0,
|
|
"step": 7915
|
|
},
|
|
{
|
|
"entropy": 6.312228488922119,
|
|
"epoch": 0.7917228969860549,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004946016500552134,
|
|
"loss": 6.0547,
|
|
"mean_token_accuracy": 0.15714965015649796,
|
|
"num_tokens": 15507585.0,
|
|
"step": 7920
|
|
},
|
|
{
|
|
"entropy": 6.3129908561706545,
|
|
"epoch": 0.7922227220472835,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004945938764315171,
|
|
"loss": 5.9702,
|
|
"mean_token_accuracy": 0.1596760258078575,
|
|
"num_tokens": 15516260.0,
|
|
"step": 7925
|
|
},
|
|
{
|
|
"entropy": 6.34543743133545,
|
|
"epoch": 0.792722547108512,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004945860972828954,
|
|
"loss": 6.0749,
|
|
"mean_token_accuracy": 0.1604975938796997,
|
|
"num_tokens": 15527372.0,
|
|
"step": 7930
|
|
},
|
|
{
|
|
"entropy": 6.284914207458496,
|
|
"epoch": 0.7932223721697406,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004945783126095439,
|
|
"loss": 6.0632,
|
|
"mean_token_accuracy": 0.15501769483089448,
|
|
"num_tokens": 15537244.0,
|
|
"step": 7935
|
|
},
|
|
{
|
|
"entropy": 6.399238157272339,
|
|
"epoch": 0.7937221972309692,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004945705224116586,
|
|
"loss": 6.0507,
|
|
"mean_token_accuracy": 0.15411500185728072,
|
|
"num_tokens": 15546512.0,
|
|
"step": 7940
|
|
},
|
|
{
|
|
"entropy": 6.268219089508056,
|
|
"epoch": 0.7942220222921977,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004945627266894354,
|
|
"loss": 6.0151,
|
|
"mean_token_accuracy": 0.16168650090694428,
|
|
"num_tokens": 15557381.0,
|
|
"step": 7945
|
|
},
|
|
{
|
|
"entropy": 6.286045408248901,
|
|
"epoch": 0.7947218473534263,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004945549254430707,
|
|
"loss": 6.1098,
|
|
"mean_token_accuracy": 0.15220927447080612,
|
|
"num_tokens": 15565806.0,
|
|
"step": 7950
|
|
},
|
|
{
|
|
"entropy": 6.289082765579224,
|
|
"epoch": 0.7952216724146549,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004945471186727603,
|
|
"loss": 6.0209,
|
|
"mean_token_accuracy": 0.1558805376291275,
|
|
"num_tokens": 15577059.0,
|
|
"step": 7955
|
|
},
|
|
{
|
|
"entropy": 6.390850400924682,
|
|
"epoch": 0.7957214974758834,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004945393063787011,
|
|
"loss": 6.1931,
|
|
"mean_token_accuracy": 0.14717739894986154,
|
|
"num_tokens": 15587827.0,
|
|
"step": 7960
|
|
},
|
|
{
|
|
"entropy": 6.419885969161987,
|
|
"epoch": 0.796221322537112,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004945314885610894,
|
|
"loss": 5.9992,
|
|
"mean_token_accuracy": 0.15139688029885293,
|
|
"num_tokens": 15598232.0,
|
|
"step": 7965
|
|
},
|
|
{
|
|
"entropy": 6.285418891906739,
|
|
"epoch": 0.7967211475983406,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004945236652201219,
|
|
"loss": 5.9543,
|
|
"mean_token_accuracy": 0.15880410224199296,
|
|
"num_tokens": 15606896.0,
|
|
"step": 7970
|
|
},
|
|
{
|
|
"entropy": 6.226030492782593,
|
|
"epoch": 0.7972209726595691,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004945158363559955,
|
|
"loss": 5.9495,
|
|
"mean_token_accuracy": 0.16316137760877608,
|
|
"num_tokens": 15616868.0,
|
|
"step": 7975
|
|
},
|
|
{
|
|
"entropy": 6.290950870513916,
|
|
"epoch": 0.7977207977207977,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004945080019689071,
|
|
"loss": 5.9824,
|
|
"mean_token_accuracy": 0.15485470741987228,
|
|
"num_tokens": 15626521.0,
|
|
"step": 7980
|
|
},
|
|
{
|
|
"entropy": 6.298295593261718,
|
|
"epoch": 0.7982206227820263,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004945001620590538,
|
|
"loss": 5.9729,
|
|
"mean_token_accuracy": 0.16681952327489852,
|
|
"num_tokens": 15635901.0,
|
|
"step": 7985
|
|
},
|
|
{
|
|
"entropy": 6.282628202438355,
|
|
"epoch": 0.7987204478432549,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000494492316626633,
|
|
"loss": 6.0232,
|
|
"mean_token_accuracy": 0.15542822778224946,
|
|
"num_tokens": 15645672.0,
|
|
"step": 7990
|
|
},
|
|
{
|
|
"entropy": 6.38148603439331,
|
|
"epoch": 0.7992202729044834,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004944844656718419,
|
|
"loss": 6.0653,
|
|
"mean_token_accuracy": 0.15439800694584846,
|
|
"num_tokens": 15656668.0,
|
|
"step": 7995
|
|
},
|
|
{
|
|
"entropy": 6.331287002563476,
|
|
"epoch": 0.799720097965712,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004944766091948783,
|
|
"loss": 6.0094,
|
|
"mean_token_accuracy": 0.16176359057426454,
|
|
"num_tokens": 15666176.0,
|
|
"step": 8000
|
|
},
|
|
{
|
|
"entropy": 6.295291185379028,
|
|
"epoch": 0.8002199230269406,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004944687471959395,
|
|
"loss": 6.0458,
|
|
"mean_token_accuracy": 0.1539482966065407,
|
|
"num_tokens": 15676162.0,
|
|
"step": 8005
|
|
},
|
|
{
|
|
"entropy": 6.330791330337524,
|
|
"epoch": 0.8007197480881691,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004944608796752237,
|
|
"loss": 6.04,
|
|
"mean_token_accuracy": 0.16030583530664444,
|
|
"num_tokens": 15685393.0,
|
|
"step": 8010
|
|
},
|
|
{
|
|
"entropy": 6.287073183059692,
|
|
"epoch": 0.8012195731493977,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004944530066329284,
|
|
"loss": 5.9583,
|
|
"mean_token_accuracy": 0.1641255423426628,
|
|
"num_tokens": 15694944.0,
|
|
"step": 8015
|
|
},
|
|
{
|
|
"entropy": 6.330994033813477,
|
|
"epoch": 0.8017193982106263,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004944451280692521,
|
|
"loss": 6.1077,
|
|
"mean_token_accuracy": 0.15276397317647933,
|
|
"num_tokens": 15704410.0,
|
|
"step": 8020
|
|
},
|
|
{
|
|
"entropy": 6.335663318634033,
|
|
"epoch": 0.8022192232718548,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004944372439843927,
|
|
"loss": 5.9902,
|
|
"mean_token_accuracy": 0.16062835603952408,
|
|
"num_tokens": 15713663.0,
|
|
"step": 8025
|
|
},
|
|
{
|
|
"entropy": 6.310619258880616,
|
|
"epoch": 0.8027190483330834,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004944293543785489,
|
|
"loss": 5.9494,
|
|
"mean_token_accuracy": 0.16796149760484697,
|
|
"num_tokens": 15722662.0,
|
|
"step": 8030
|
|
},
|
|
{
|
|
"entropy": 6.293089580535889,
|
|
"epoch": 0.803218873394312,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004944214592519188,
|
|
"loss": 6.136,
|
|
"mean_token_accuracy": 0.14677956327795982,
|
|
"num_tokens": 15732615.0,
|
|
"step": 8035
|
|
},
|
|
{
|
|
"entropy": 6.367898321151733,
|
|
"epoch": 0.8037186984555406,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004944135586047014,
|
|
"loss": 6.0613,
|
|
"mean_token_accuracy": 0.1663420766592026,
|
|
"num_tokens": 15741569.0,
|
|
"step": 8040
|
|
},
|
|
{
|
|
"entropy": 6.326604604721069,
|
|
"epoch": 0.8042185235167691,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004944056524370953,
|
|
"loss": 5.9257,
|
|
"mean_token_accuracy": 0.16761356443166733,
|
|
"num_tokens": 15750734.0,
|
|
"step": 8045
|
|
},
|
|
{
|
|
"entropy": 6.350539255142212,
|
|
"epoch": 0.8047183485779977,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004943977407492994,
|
|
"loss": 6.026,
|
|
"mean_token_accuracy": 0.1593258261680603,
|
|
"num_tokens": 15761664.0,
|
|
"step": 8050
|
|
},
|
|
{
|
|
"entropy": 6.268751049041748,
|
|
"epoch": 0.8052181736392263,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004943898235415128,
|
|
"loss": 5.9433,
|
|
"mean_token_accuracy": 0.1661013588309288,
|
|
"num_tokens": 15771159.0,
|
|
"step": 8055
|
|
},
|
|
{
|
|
"entropy": 6.329112386703491,
|
|
"epoch": 0.8057179987004548,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004943819008139347,
|
|
"loss": 6.0625,
|
|
"mean_token_accuracy": 0.15712908059358596,
|
|
"num_tokens": 15781429.0,
|
|
"step": 8060
|
|
},
|
|
{
|
|
"entropy": 6.317018222808838,
|
|
"epoch": 0.8062178237616834,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004943739725667644,
|
|
"loss": 5.9804,
|
|
"mean_token_accuracy": 0.1601518914103508,
|
|
"num_tokens": 15791361.0,
|
|
"step": 8065
|
|
},
|
|
{
|
|
"entropy": 6.332014799118042,
|
|
"epoch": 0.806717648822912,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004943660388002014,
|
|
"loss": 6.1,
|
|
"mean_token_accuracy": 0.1526860162615776,
|
|
"num_tokens": 15802020.0,
|
|
"step": 8070
|
|
},
|
|
{
|
|
"entropy": 6.251399850845337,
|
|
"epoch": 0.8072174738841406,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004943580995144454,
|
|
"loss": 5.9242,
|
|
"mean_token_accuracy": 0.16700202226638794,
|
|
"num_tokens": 15811319.0,
|
|
"step": 8075
|
|
},
|
|
{
|
|
"entropy": 6.355843782424927,
|
|
"epoch": 0.8077172989453691,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004943501547096961,
|
|
"loss": 6.0495,
|
|
"mean_token_accuracy": 0.15723416358232498,
|
|
"num_tokens": 15821337.0,
|
|
"step": 8080
|
|
},
|
|
{
|
|
"entropy": 6.3409507274627686,
|
|
"epoch": 0.8082171240065977,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004943422043861531,
|
|
"loss": 6.0507,
|
|
"mean_token_accuracy": 0.1606202594935894,
|
|
"num_tokens": 15832234.0,
|
|
"step": 8085
|
|
},
|
|
{
|
|
"entropy": 6.319289636611939,
|
|
"epoch": 0.8087169490678262,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004943342485440169,
|
|
"loss": 6.015,
|
|
"mean_token_accuracy": 0.15711220502853393,
|
|
"num_tokens": 15841797.0,
|
|
"step": 8090
|
|
},
|
|
{
|
|
"entropy": 6.286961030960083,
|
|
"epoch": 0.8092167741290548,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004943262871834874,
|
|
"loss": 6.0475,
|
|
"mean_token_accuracy": 0.1557351380586624,
|
|
"num_tokens": 15851031.0,
|
|
"step": 8095
|
|
},
|
|
{
|
|
"entropy": 6.319517278671265,
|
|
"epoch": 0.8097165991902834,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004943183203047649,
|
|
"loss": 6.0464,
|
|
"mean_token_accuracy": 0.15256616175174714,
|
|
"num_tokens": 15861297.0,
|
|
"step": 8100
|
|
},
|
|
{
|
|
"entropy": 6.345840072631836,
|
|
"epoch": 0.810216424251512,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004943103479080499,
|
|
"loss": 6.0605,
|
|
"mean_token_accuracy": 0.15655364692211152,
|
|
"num_tokens": 15871066.0,
|
|
"step": 8105
|
|
},
|
|
{
|
|
"entropy": 6.360694885253906,
|
|
"epoch": 0.8107162493127406,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000494302369993543,
|
|
"loss": 6.0542,
|
|
"mean_token_accuracy": 0.15328925251960754,
|
|
"num_tokens": 15880395.0,
|
|
"step": 8110
|
|
},
|
|
{
|
|
"entropy": 6.309396028518677,
|
|
"epoch": 0.8112160743739691,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004942943865614449,
|
|
"loss": 5.9993,
|
|
"mean_token_accuracy": 0.16092857122421264,
|
|
"num_tokens": 15889937.0,
|
|
"step": 8115
|
|
},
|
|
{
|
|
"entropy": 6.33162522315979,
|
|
"epoch": 0.8117158994351977,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004942863976119565,
|
|
"loss": 5.991,
|
|
"mean_token_accuracy": 0.15774793028831482,
|
|
"num_tokens": 15899894.0,
|
|
"step": 8120
|
|
},
|
|
{
|
|
"entropy": 6.20619764328003,
|
|
"epoch": 0.8122157244964262,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004942784031452788,
|
|
"loss": 5.8821,
|
|
"mean_token_accuracy": 0.17743793427944182,
|
|
"num_tokens": 15909038.0,
|
|
"step": 8125
|
|
},
|
|
{
|
|
"entropy": 6.272015857696533,
|
|
"epoch": 0.8127155495576548,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004942704031616127,
|
|
"loss": 6.0149,
|
|
"mean_token_accuracy": 0.1574663609266281,
|
|
"num_tokens": 15917891.0,
|
|
"step": 8130
|
|
},
|
|
{
|
|
"entropy": 6.3723695278167725,
|
|
"epoch": 0.8132153746188834,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004942623976611598,
|
|
"loss": 6.1394,
|
|
"mean_token_accuracy": 0.14506006017327308,
|
|
"num_tokens": 15928079.0,
|
|
"step": 8135
|
|
},
|
|
{
|
|
"entropy": 6.27050142288208,
|
|
"epoch": 0.813715199680112,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004942543866441215,
|
|
"loss": 5.9642,
|
|
"mean_token_accuracy": 0.1592273771762848,
|
|
"num_tokens": 15938065.0,
|
|
"step": 8140
|
|
},
|
|
{
|
|
"entropy": 6.258691740036011,
|
|
"epoch": 0.8142150247413406,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004942463701106992,
|
|
"loss": 5.9992,
|
|
"mean_token_accuracy": 0.1551909014582634,
|
|
"num_tokens": 15947650.0,
|
|
"step": 8145
|
|
},
|
|
{
|
|
"entropy": 6.285524368286133,
|
|
"epoch": 0.8147148498025691,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004942383480610946,
|
|
"loss": 5.9976,
|
|
"mean_token_accuracy": 0.159341561794281,
|
|
"num_tokens": 15957194.0,
|
|
"step": 8150
|
|
},
|
|
{
|
|
"entropy": 6.351723527908325,
|
|
"epoch": 0.8152146748637976,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004942303204955096,
|
|
"loss": 5.9696,
|
|
"mean_token_accuracy": 0.15660293102264405,
|
|
"num_tokens": 15966068.0,
|
|
"step": 8155
|
|
},
|
|
{
|
|
"entropy": 6.272865247726441,
|
|
"epoch": 0.8157144999250262,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004942222874141461,
|
|
"loss": 5.9908,
|
|
"mean_token_accuracy": 0.16238573789596558,
|
|
"num_tokens": 15975672.0,
|
|
"step": 8160
|
|
},
|
|
{
|
|
"entropy": 6.279624938964844,
|
|
"epoch": 0.8162143249862548,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004942142488172063,
|
|
"loss": 6.0054,
|
|
"mean_token_accuracy": 0.16126897037029267,
|
|
"num_tokens": 15986216.0,
|
|
"step": 8165
|
|
},
|
|
{
|
|
"entropy": 6.240652704238892,
|
|
"epoch": 0.8167141500474834,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004942062047048924,
|
|
"loss": 5.9457,
|
|
"mean_token_accuracy": 0.1646802917122841,
|
|
"num_tokens": 15994673.0,
|
|
"step": 8170
|
|
},
|
|
{
|
|
"entropy": 6.258727169036865,
|
|
"epoch": 0.817213975108712,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004941981550774068,
|
|
"loss": 5.9669,
|
|
"mean_token_accuracy": 0.1606065884232521,
|
|
"num_tokens": 16003576.0,
|
|
"step": 8175
|
|
},
|
|
{
|
|
"entropy": 6.213871335983276,
|
|
"epoch": 0.8177138001699406,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004941900999349521,
|
|
"loss": 5.9646,
|
|
"mean_token_accuracy": 0.16639024764299393,
|
|
"num_tokens": 16013334.0,
|
|
"step": 8180
|
|
},
|
|
{
|
|
"entropy": 6.334703540802002,
|
|
"epoch": 0.8182136252311691,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004941820392777307,
|
|
"loss": 5.9798,
|
|
"mean_token_accuracy": 0.16231327503919601,
|
|
"num_tokens": 16023101.0,
|
|
"step": 8185
|
|
},
|
|
{
|
|
"entropy": 6.282994222640991,
|
|
"epoch": 0.8187134502923976,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004941739731059457,
|
|
"loss": 6.0535,
|
|
"mean_token_accuracy": 0.15936345607042313,
|
|
"num_tokens": 16034189.0,
|
|
"step": 8190
|
|
},
|
|
{
|
|
"entropy": 6.307040691375732,
|
|
"epoch": 0.8192132753536262,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004941659014198,
|
|
"loss": 5.9579,
|
|
"mean_token_accuracy": 0.16265781372785568,
|
|
"num_tokens": 16044008.0,
|
|
"step": 8195
|
|
},
|
|
{
|
|
"entropy": 6.352166604995728,
|
|
"epoch": 0.8197131004148548,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004941578242194965,
|
|
"loss": 6.0538,
|
|
"mean_token_accuracy": 0.1634441077709198,
|
|
"num_tokens": 16053557.0,
|
|
"step": 8200
|
|
},
|
|
{
|
|
"entropy": 6.326949834823608,
|
|
"epoch": 0.8202129254760834,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004941497415052387,
|
|
"loss": 5.9862,
|
|
"mean_token_accuracy": 0.15928223729133606,
|
|
"num_tokens": 16063191.0,
|
|
"step": 8205
|
|
},
|
|
{
|
|
"entropy": 6.288394212722778,
|
|
"epoch": 0.820712750537312,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004941416532772296,
|
|
"loss": 5.9931,
|
|
"mean_token_accuracy": 0.15942111611366272,
|
|
"num_tokens": 16072482.0,
|
|
"step": 8210
|
|
},
|
|
{
|
|
"entropy": 6.222275876998902,
|
|
"epoch": 0.8212125755985406,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000494133559535673,
|
|
"loss": 5.9711,
|
|
"mean_token_accuracy": 0.16516152769327164,
|
|
"num_tokens": 16082848.0,
|
|
"step": 8215
|
|
},
|
|
{
|
|
"entropy": 6.365378522872925,
|
|
"epoch": 0.821712400659769,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004941254602807724,
|
|
"loss": 6.126,
|
|
"mean_token_accuracy": 0.1533277228474617,
|
|
"num_tokens": 16091604.0,
|
|
"step": 8220
|
|
},
|
|
{
|
|
"entropy": 6.386179447174072,
|
|
"epoch": 0.8222122257209976,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004941173555127315,
|
|
"loss": 5.9959,
|
|
"mean_token_accuracy": 0.15468641519546508,
|
|
"num_tokens": 16101427.0,
|
|
"step": 8225
|
|
},
|
|
{
|
|
"entropy": 6.266720581054687,
|
|
"epoch": 0.8227120507822262,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004941092452317546,
|
|
"loss": 5.9521,
|
|
"mean_token_accuracy": 0.1627202808856964,
|
|
"num_tokens": 16112206.0,
|
|
"step": 8230
|
|
},
|
|
{
|
|
"entropy": 6.348733854293823,
|
|
"epoch": 0.8232118758434548,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004941011294380452,
|
|
"loss": 6.081,
|
|
"mean_token_accuracy": 0.16018219143152237,
|
|
"num_tokens": 16122652.0,
|
|
"step": 8235
|
|
},
|
|
{
|
|
"entropy": 6.282577753067017,
|
|
"epoch": 0.8237117009046834,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004940930081318079,
|
|
"loss": 5.9703,
|
|
"mean_token_accuracy": 0.16304928660392762,
|
|
"num_tokens": 16132976.0,
|
|
"step": 8240
|
|
},
|
|
{
|
|
"entropy": 6.3599306583404545,
|
|
"epoch": 0.824211525965912,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004940848813132469,
|
|
"loss": 6.0602,
|
|
"mean_token_accuracy": 0.15872150510549546,
|
|
"num_tokens": 16143514.0,
|
|
"step": 8245
|
|
},
|
|
{
|
|
"entropy": 6.337618827819824,
|
|
"epoch": 0.8247113510271405,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004940767489825666,
|
|
"loss": 6.0347,
|
|
"mean_token_accuracy": 0.1554365411400795,
|
|
"num_tokens": 16154235.0,
|
|
"step": 8250
|
|
},
|
|
{
|
|
"entropy": 6.311557006835938,
|
|
"epoch": 0.825211176088369,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004940686111399716,
|
|
"loss": 5.9213,
|
|
"mean_token_accuracy": 0.16360237300395966,
|
|
"num_tokens": 16164251.0,
|
|
"step": 8255
|
|
},
|
|
{
|
|
"entropy": 6.223285436630249,
|
|
"epoch": 0.8257110011495976,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004940604677856669,
|
|
"loss": 5.9097,
|
|
"mean_token_accuracy": 0.17255427986383437,
|
|
"num_tokens": 16172780.0,
|
|
"step": 8260
|
|
},
|
|
{
|
|
"entropy": 6.176182651519776,
|
|
"epoch": 0.8262108262108262,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000494052318919857,
|
|
"loss": 5.8797,
|
|
"mean_token_accuracy": 0.1700695902109146,
|
|
"num_tokens": 16182443.0,
|
|
"step": 8265
|
|
},
|
|
{
|
|
"entropy": 6.302811527252198,
|
|
"epoch": 0.8267106512720548,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004940441645427473,
|
|
"loss": 5.9613,
|
|
"mean_token_accuracy": 0.1650758519768715,
|
|
"num_tokens": 16192515.0,
|
|
"step": 8270
|
|
},
|
|
{
|
|
"entropy": 6.309085083007813,
|
|
"epoch": 0.8272104763332834,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004940360046545427,
|
|
"loss": 5.9899,
|
|
"mean_token_accuracy": 0.1594035267829895,
|
|
"num_tokens": 16201615.0,
|
|
"step": 8275
|
|
},
|
|
{
|
|
"entropy": 6.289867162704468,
|
|
"epoch": 0.827710301394512,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004940278392554486,
|
|
"loss": 6.0208,
|
|
"mean_token_accuracy": 0.1563822664320469,
|
|
"num_tokens": 16210461.0,
|
|
"step": 8280
|
|
},
|
|
{
|
|
"entropy": 6.211748933792114,
|
|
"epoch": 0.8282101264557404,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004940196683456704,
|
|
"loss": 6.0048,
|
|
"mean_token_accuracy": 0.15217093974351883,
|
|
"num_tokens": 16220293.0,
|
|
"step": 8285
|
|
},
|
|
{
|
|
"entropy": 6.247614860534668,
|
|
"epoch": 0.828709951516969,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004940114919254137,
|
|
"loss": 5.9201,
|
|
"mean_token_accuracy": 0.16677623838186265,
|
|
"num_tokens": 16230020.0,
|
|
"step": 8290
|
|
},
|
|
{
|
|
"entropy": 6.289156246185303,
|
|
"epoch": 0.8292097765781976,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004940033099948843,
|
|
"loss": 5.9484,
|
|
"mean_token_accuracy": 0.15729523301124573,
|
|
"num_tokens": 16240187.0,
|
|
"step": 8295
|
|
},
|
|
{
|
|
"entropy": 6.290634059906006,
|
|
"epoch": 0.8297096016394262,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004939951225542879,
|
|
"loss": 5.9497,
|
|
"mean_token_accuracy": 0.15783804953098296,
|
|
"num_tokens": 16250200.0,
|
|
"step": 8300
|
|
},
|
|
{
|
|
"entropy": 6.322738456726074,
|
|
"epoch": 0.8302094267006548,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004939869296038306,
|
|
"loss": 6.0424,
|
|
"mean_token_accuracy": 0.1600612223148346,
|
|
"num_tokens": 16259396.0,
|
|
"step": 8305
|
|
},
|
|
{
|
|
"entropy": 6.34406042098999,
|
|
"epoch": 0.8307092517618834,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004939787311437185,
|
|
"loss": 6.0641,
|
|
"mean_token_accuracy": 0.14704681187868118,
|
|
"num_tokens": 16270033.0,
|
|
"step": 8310
|
|
},
|
|
{
|
|
"entropy": 6.356411790847778,
|
|
"epoch": 0.831209076823112,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004939705271741579,
|
|
"loss": 6.0194,
|
|
"mean_token_accuracy": 0.1587398409843445,
|
|
"num_tokens": 16281464.0,
|
|
"step": 8315
|
|
},
|
|
{
|
|
"entropy": 6.35593547821045,
|
|
"epoch": 0.8317089018843404,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004939623176953551,
|
|
"loss": 6.0765,
|
|
"mean_token_accuracy": 0.15352010428905488,
|
|
"num_tokens": 16292125.0,
|
|
"step": 8320
|
|
},
|
|
{
|
|
"entropy": 6.279843187332153,
|
|
"epoch": 0.832208726945569,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004939541027075168,
|
|
"loss": 6.0081,
|
|
"mean_token_accuracy": 0.15737985596060752,
|
|
"num_tokens": 16302993.0,
|
|
"step": 8325
|
|
},
|
|
{
|
|
"entropy": 6.296454381942749,
|
|
"epoch": 0.8327085520067976,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004939458822108496,
|
|
"loss": 5.9758,
|
|
"mean_token_accuracy": 0.1600040689110756,
|
|
"num_tokens": 16311287.0,
|
|
"step": 8330
|
|
},
|
|
{
|
|
"entropy": 6.2996152400970455,
|
|
"epoch": 0.8332083770680262,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004939376562055602,
|
|
"loss": 5.9734,
|
|
"mean_token_accuracy": 0.15882916301488875,
|
|
"num_tokens": 16320701.0,
|
|
"step": 8335
|
|
},
|
|
{
|
|
"entropy": 6.252297353744507,
|
|
"epoch": 0.8337082021292548,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004939294246918558,
|
|
"loss": 5.9976,
|
|
"mean_token_accuracy": 0.1609439618885517,
|
|
"num_tokens": 16329834.0,
|
|
"step": 8340
|
|
},
|
|
{
|
|
"entropy": 6.296989965438843,
|
|
"epoch": 0.8342080271904834,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004939211876699435,
|
|
"loss": 5.9992,
|
|
"mean_token_accuracy": 0.15677739232778548,
|
|
"num_tokens": 16339043.0,
|
|
"step": 8345
|
|
},
|
|
{
|
|
"entropy": 6.37321105003357,
|
|
"epoch": 0.8347078522517118,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004939129451400305,
|
|
"loss": 6.1096,
|
|
"mean_token_accuracy": 0.15234270095825195,
|
|
"num_tokens": 16348774.0,
|
|
"step": 8350
|
|
},
|
|
{
|
|
"entropy": 6.29345474243164,
|
|
"epoch": 0.8352076773129404,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000493904697102324,
|
|
"loss": 5.9733,
|
|
"mean_token_accuracy": 0.15583033114671707,
|
|
"num_tokens": 16357999.0,
|
|
"step": 8355
|
|
},
|
|
{
|
|
"entropy": 6.317603683471679,
|
|
"epoch": 0.835707502374169,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004938964435570317,
|
|
"loss": 5.9919,
|
|
"mean_token_accuracy": 0.16160280331969262,
|
|
"num_tokens": 16369308.0,
|
|
"step": 8360
|
|
},
|
|
{
|
|
"entropy": 6.244389152526855,
|
|
"epoch": 0.8362073274353976,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004938881845043612,
|
|
"loss": 5.9239,
|
|
"mean_token_accuracy": 0.16524045318365096,
|
|
"num_tokens": 16378001.0,
|
|
"step": 8365
|
|
},
|
|
{
|
|
"entropy": 6.399140071868897,
|
|
"epoch": 0.8367071524966262,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004938799199445202,
|
|
"loss": 6.1011,
|
|
"mean_token_accuracy": 0.15495192408561706,
|
|
"num_tokens": 16387925.0,
|
|
"step": 8370
|
|
},
|
|
{
|
|
"entropy": 6.361681127548218,
|
|
"epoch": 0.8372069775578548,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004938716498777169,
|
|
"loss": 6.0831,
|
|
"mean_token_accuracy": 0.1503365769982338,
|
|
"num_tokens": 16398200.0,
|
|
"step": 8375
|
|
},
|
|
{
|
|
"entropy": 6.203743410110474,
|
|
"epoch": 0.8377068026190834,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004938633743041592,
|
|
"loss": 5.8792,
|
|
"mean_token_accuracy": 0.1681562125682831,
|
|
"num_tokens": 16407874.0,
|
|
"step": 8380
|
|
},
|
|
{
|
|
"entropy": 6.315232372283935,
|
|
"epoch": 0.8382066276803118,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004938550932240552,
|
|
"loss": 5.9983,
|
|
"mean_token_accuracy": 0.16121616810560227,
|
|
"num_tokens": 16417825.0,
|
|
"step": 8385
|
|
},
|
|
{
|
|
"entropy": 6.285078287124634,
|
|
"epoch": 0.8387064527415404,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004938468066376134,
|
|
"loss": 5.9981,
|
|
"mean_token_accuracy": 0.1610456958413124,
|
|
"num_tokens": 16427265.0,
|
|
"step": 8390
|
|
},
|
|
{
|
|
"entropy": 6.177667474746704,
|
|
"epoch": 0.839206277802769,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004938385145450423,
|
|
"loss": 5.9246,
|
|
"mean_token_accuracy": 0.17087895572185516,
|
|
"num_tokens": 16436639.0,
|
|
"step": 8395
|
|
},
|
|
{
|
|
"entropy": 6.293653726577759,
|
|
"epoch": 0.8397061028639976,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004938302169465505,
|
|
"loss": 6.0044,
|
|
"mean_token_accuracy": 0.16215359568595886,
|
|
"num_tokens": 16446411.0,
|
|
"step": 8400
|
|
},
|
|
{
|
|
"entropy": 6.329254531860352,
|
|
"epoch": 0.8402059279252262,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004938219138423467,
|
|
"loss": 6.0529,
|
|
"mean_token_accuracy": 0.16097778379917144,
|
|
"num_tokens": 16455784.0,
|
|
"step": 8405
|
|
},
|
|
{
|
|
"entropy": 6.223066806793213,
|
|
"epoch": 0.8407057529864548,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004938136052326399,
|
|
"loss": 5.8976,
|
|
"mean_token_accuracy": 0.17020540684461594,
|
|
"num_tokens": 16464411.0,
|
|
"step": 8410
|
|
},
|
|
{
|
|
"entropy": 6.280291748046875,
|
|
"epoch": 0.8412055780476833,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004938052911176392,
|
|
"loss": 6.0331,
|
|
"mean_token_accuracy": 0.15589212775230407,
|
|
"num_tokens": 16473299.0,
|
|
"step": 8415
|
|
},
|
|
{
|
|
"entropy": 6.209199094772339,
|
|
"epoch": 0.8417054031089118,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004937969714975534,
|
|
"loss": 5.8685,
|
|
"mean_token_accuracy": 0.1721692994236946,
|
|
"num_tokens": 16483040.0,
|
|
"step": 8420
|
|
},
|
|
{
|
|
"entropy": 6.289967060089111,
|
|
"epoch": 0.8422052281701404,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004937886463725923,
|
|
"loss": 5.9743,
|
|
"mean_token_accuracy": 0.15987657457590104,
|
|
"num_tokens": 16492608.0,
|
|
"step": 8425
|
|
},
|
|
{
|
|
"entropy": 6.360797452926636,
|
|
"epoch": 0.842705053231369,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004937803157429651,
|
|
"loss": 6.0987,
|
|
"mean_token_accuracy": 0.15504923164844514,
|
|
"num_tokens": 16503139.0,
|
|
"step": 8430
|
|
},
|
|
{
|
|
"entropy": 6.248201894760132,
|
|
"epoch": 0.8432048782925976,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004937719796088815,
|
|
"loss": 5.9631,
|
|
"mean_token_accuracy": 0.1689337372779846,
|
|
"num_tokens": 16511584.0,
|
|
"step": 8435
|
|
},
|
|
{
|
|
"entropy": 6.235577869415283,
|
|
"epoch": 0.8437047033538262,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004937636379705511,
|
|
"loss": 5.9656,
|
|
"mean_token_accuracy": 0.1608283832669258,
|
|
"num_tokens": 16522407.0,
|
|
"step": 8440
|
|
},
|
|
{
|
|
"entropy": 6.2678779602050785,
|
|
"epoch": 0.8442045284150548,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004937552908281839,
|
|
"loss": 5.9888,
|
|
"mean_token_accuracy": 0.15717996060848236,
|
|
"num_tokens": 16532351.0,
|
|
"step": 8445
|
|
},
|
|
{
|
|
"entropy": 6.357618188858032,
|
|
"epoch": 0.8447043534762833,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004937469381819899,
|
|
"loss": 6.0509,
|
|
"mean_token_accuracy": 0.15357735753059387,
|
|
"num_tokens": 16541673.0,
|
|
"step": 8450
|
|
},
|
|
{
|
|
"entropy": 6.269177341461182,
|
|
"epoch": 0.8452041785375118,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004937385800321792,
|
|
"loss": 6.0097,
|
|
"mean_token_accuracy": 0.1666796922683716,
|
|
"num_tokens": 16551622.0,
|
|
"step": 8455
|
|
},
|
|
{
|
|
"entropy": 6.296357727050781,
|
|
"epoch": 0.8457040035987404,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004937302163789621,
|
|
"loss": 5.9649,
|
|
"mean_token_accuracy": 0.16314167827367781,
|
|
"num_tokens": 16559074.0,
|
|
"step": 8460
|
|
},
|
|
{
|
|
"entropy": 6.256822681427002,
|
|
"epoch": 0.846203828659969,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004937218472225491,
|
|
"loss": 5.9538,
|
|
"mean_token_accuracy": 0.172720205783844,
|
|
"num_tokens": 16568650.0,
|
|
"step": 8465
|
|
},
|
|
{
|
|
"entropy": 6.31704683303833,
|
|
"epoch": 0.8467036537211976,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004937134725631506,
|
|
"loss": 5.9869,
|
|
"mean_token_accuracy": 0.16269383132457732,
|
|
"num_tokens": 16578696.0,
|
|
"step": 8470
|
|
},
|
|
{
|
|
"entropy": 6.341166591644287,
|
|
"epoch": 0.8472034787824262,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004937050924009775,
|
|
"loss": 6.0467,
|
|
"mean_token_accuracy": 0.1565137267112732,
|
|
"num_tokens": 16589014.0,
|
|
"step": 8475
|
|
},
|
|
{
|
|
"entropy": 6.298156881332398,
|
|
"epoch": 0.8477033038436548,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004936967067362406,
|
|
"loss": 5.9196,
|
|
"mean_token_accuracy": 0.16253736913204192,
|
|
"num_tokens": 16598319.0,
|
|
"step": 8480
|
|
},
|
|
{
|
|
"entropy": 6.335547542572021,
|
|
"epoch": 0.8482031289048833,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004936883155691507,
|
|
"loss": 6.0654,
|
|
"mean_token_accuracy": 0.15766218304634094,
|
|
"num_tokens": 16607941.0,
|
|
"step": 8485
|
|
},
|
|
{
|
|
"entropy": 6.266610908508301,
|
|
"epoch": 0.8487029539661118,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004936799188999192,
|
|
"loss": 5.9928,
|
|
"mean_token_accuracy": 0.1601306438446045,
|
|
"num_tokens": 16618398.0,
|
|
"step": 8490
|
|
},
|
|
{
|
|
"entropy": 6.320463991165161,
|
|
"epoch": 0.8492027790273404,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004936715167287571,
|
|
"loss": 6.038,
|
|
"mean_token_accuracy": 0.150790324062109,
|
|
"num_tokens": 16628953.0,
|
|
"step": 8495
|
|
},
|
|
{
|
|
"entropy": 6.35287709236145,
|
|
"epoch": 0.849702604088569,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000493663109055876,
|
|
"loss": 5.9734,
|
|
"mean_token_accuracy": 0.15737926512956618,
|
|
"num_tokens": 16638783.0,
|
|
"step": 8500
|
|
},
|
|
{
|
|
"entropy": 6.309719896316528,
|
|
"epoch": 0.8502024291497976,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004936546958814873,
|
|
"loss": 6.0213,
|
|
"mean_token_accuracy": 0.15978955030441283,
|
|
"num_tokens": 16647432.0,
|
|
"step": 8505
|
|
},
|
|
{
|
|
"entropy": 6.330782794952393,
|
|
"epoch": 0.8507022542110262,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004936462772058026,
|
|
"loss": 5.9956,
|
|
"mean_token_accuracy": 0.15184449702501296,
|
|
"num_tokens": 16656839.0,
|
|
"step": 8510
|
|
},
|
|
{
|
|
"entropy": 6.3292662620544435,
|
|
"epoch": 0.8512020792722547,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004936378530290339,
|
|
"loss": 6.0523,
|
|
"mean_token_accuracy": 0.1559779539704323,
|
|
"num_tokens": 16667054.0,
|
|
"step": 8515
|
|
},
|
|
{
|
|
"entropy": 6.31857476234436,
|
|
"epoch": 0.8517019043334833,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004936294233513931,
|
|
"loss": 5.9948,
|
|
"mean_token_accuracy": 0.15994424596428872,
|
|
"num_tokens": 16676851.0,
|
|
"step": 8520
|
|
},
|
|
{
|
|
"entropy": 6.363214349746704,
|
|
"epoch": 0.8522017293947118,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004936209881730922,
|
|
"loss": 6.0069,
|
|
"mean_token_accuracy": 0.15777713060379028,
|
|
"num_tokens": 16686433.0,
|
|
"step": 8525
|
|
},
|
|
{
|
|
"entropy": 6.291280508041382,
|
|
"epoch": 0.8527015544559404,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004936125474943436,
|
|
"loss": 5.9583,
|
|
"mean_token_accuracy": 0.16686154305934905,
|
|
"num_tokens": 16695859.0,
|
|
"step": 8530
|
|
},
|
|
{
|
|
"entropy": 6.2647522449493405,
|
|
"epoch": 0.853201379517169,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004936041013153596,
|
|
"loss": 5.9846,
|
|
"mean_token_accuracy": 0.16125230491161346,
|
|
"num_tokens": 16704391.0,
|
|
"step": 8535
|
|
},
|
|
{
|
|
"entropy": 6.286400079727173,
|
|
"epoch": 0.8537012045783976,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004935956496363525,
|
|
"loss": 6.086,
|
|
"mean_token_accuracy": 0.15205976963043213,
|
|
"num_tokens": 16715316.0,
|
|
"step": 8540
|
|
},
|
|
{
|
|
"entropy": 6.441294002532959,
|
|
"epoch": 0.8542010296396262,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004935871924575352,
|
|
"loss": 6.1031,
|
|
"mean_token_accuracy": 0.14834528043866158,
|
|
"num_tokens": 16726215.0,
|
|
"step": 8545
|
|
},
|
|
{
|
|
"entropy": 6.331367921829224,
|
|
"epoch": 0.8547008547008547,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004935787297791204,
|
|
"loss": 5.9988,
|
|
"mean_token_accuracy": 0.1598176211118698,
|
|
"num_tokens": 16735768.0,
|
|
"step": 8550
|
|
},
|
|
{
|
|
"entropy": 6.236656999588012,
|
|
"epoch": 0.8552006797620832,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004935702616013209,
|
|
"loss": 5.8181,
|
|
"mean_token_accuracy": 0.17496980130672454,
|
|
"num_tokens": 16744265.0,
|
|
"step": 8555
|
|
},
|
|
{
|
|
"entropy": 6.229803228378296,
|
|
"epoch": 0.8557005048233118,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00049356178792435,
|
|
"loss": 6.0414,
|
|
"mean_token_accuracy": 0.16270768642425537,
|
|
"num_tokens": 16753713.0,
|
|
"step": 8560
|
|
},
|
|
{
|
|
"entropy": 6.32741756439209,
|
|
"epoch": 0.8562003298845404,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004935533087484207,
|
|
"loss": 5.9475,
|
|
"mean_token_accuracy": 0.1605185091495514,
|
|
"num_tokens": 16763670.0,
|
|
"step": 8565
|
|
},
|
|
{
|
|
"entropy": 6.283723974227906,
|
|
"epoch": 0.856700154945769,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004935448240737464,
|
|
"loss": 5.9774,
|
|
"mean_token_accuracy": 0.16209800243377687,
|
|
"num_tokens": 16773504.0,
|
|
"step": 8570
|
|
},
|
|
{
|
|
"entropy": 6.247960233688355,
|
|
"epoch": 0.8571999800069976,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004935363339005405,
|
|
"loss": 6.049,
|
|
"mean_token_accuracy": 0.15743016302585602,
|
|
"num_tokens": 16784181.0,
|
|
"step": 8575
|
|
},
|
|
{
|
|
"entropy": 6.345371389389038,
|
|
"epoch": 0.8576998050682261,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004935278382290168,
|
|
"loss": 6.026,
|
|
"mean_token_accuracy": 0.15428334921598436,
|
|
"num_tokens": 16793610.0,
|
|
"step": 8580
|
|
},
|
|
{
|
|
"entropy": 6.3127820014953615,
|
|
"epoch": 0.8581996301294547,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004935193370593887,
|
|
"loss": 6.0704,
|
|
"mean_token_accuracy": 0.14957648515701294,
|
|
"num_tokens": 16804068.0,
|
|
"step": 8585
|
|
},
|
|
{
|
|
"entropy": 6.263094568252564,
|
|
"epoch": 0.8586994551906832,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004935108303918705,
|
|
"loss": 6.0201,
|
|
"mean_token_accuracy": 0.1627806007862091,
|
|
"num_tokens": 16813769.0,
|
|
"step": 8590
|
|
},
|
|
{
|
|
"entropy": 6.258586692810058,
|
|
"epoch": 0.8591992802519118,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004935023182266761,
|
|
"loss": 5.952,
|
|
"mean_token_accuracy": 0.16163772642612456,
|
|
"num_tokens": 16822859.0,
|
|
"step": 8595
|
|
},
|
|
{
|
|
"entropy": 6.410567712783814,
|
|
"epoch": 0.8596991053131404,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004934938005640194,
|
|
"loss": 6.1838,
|
|
"mean_token_accuracy": 0.14456939920783043,
|
|
"num_tokens": 16834839.0,
|
|
"step": 8600
|
|
},
|
|
{
|
|
"entropy": 6.372849416732788,
|
|
"epoch": 0.860198930374369,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000493485277404115,
|
|
"loss": 6.0232,
|
|
"mean_token_accuracy": 0.15320356637239457,
|
|
"num_tokens": 16845205.0,
|
|
"step": 8605
|
|
},
|
|
{
|
|
"entropy": 6.325511312484741,
|
|
"epoch": 0.8606987554355976,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004934767487471772,
|
|
"loss": 6.0224,
|
|
"mean_token_accuracy": 0.15564613193273544,
|
|
"num_tokens": 16854874.0,
|
|
"step": 8610
|
|
},
|
|
{
|
|
"entropy": 6.2826642990112305,
|
|
"epoch": 0.8611985804968261,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004934682145934207,
|
|
"loss": 5.9157,
|
|
"mean_token_accuracy": 0.16233194023370742,
|
|
"num_tokens": 16864771.0,
|
|
"step": 8615
|
|
},
|
|
{
|
|
"entropy": 6.30085940361023,
|
|
"epoch": 0.8616984055580547,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00049345967494306,
|
|
"loss": 6.0091,
|
|
"mean_token_accuracy": 0.15559957921504974,
|
|
"num_tokens": 16874227.0,
|
|
"step": 8620
|
|
},
|
|
{
|
|
"entropy": 6.271422576904297,
|
|
"epoch": 0.8621982306192832,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004934511297963102,
|
|
"loss": 5.9177,
|
|
"mean_token_accuracy": 0.16722774505615234,
|
|
"num_tokens": 16883895.0,
|
|
"step": 8625
|
|
},
|
|
{
|
|
"entropy": 6.267648506164551,
|
|
"epoch": 0.8626980556805118,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004934425791533861,
|
|
"loss": 5.9322,
|
|
"mean_token_accuracy": 0.16592230498790742,
|
|
"num_tokens": 16893012.0,
|
|
"step": 8630
|
|
},
|
|
{
|
|
"entropy": 6.2932511329650875,
|
|
"epoch": 0.8631978807417404,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004934340230145031,
|
|
"loss": 6.0014,
|
|
"mean_token_accuracy": 0.16674718037247657,
|
|
"num_tokens": 16903831.0,
|
|
"step": 8635
|
|
},
|
|
{
|
|
"entropy": 6.3498108863830565,
|
|
"epoch": 0.863697705802969,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004934254613798761,
|
|
"loss": 6.0543,
|
|
"mean_token_accuracy": 0.14921953678131103,
|
|
"num_tokens": 16913649.0,
|
|
"step": 8640
|
|
},
|
|
{
|
|
"entropy": 6.277431535720825,
|
|
"epoch": 0.8641975308641975,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004934168942497207,
|
|
"loss": 5.9924,
|
|
"mean_token_accuracy": 0.16252291649580003,
|
|
"num_tokens": 16923063.0,
|
|
"step": 8645
|
|
},
|
|
{
|
|
"entropy": 6.35346474647522,
|
|
"epoch": 0.8646973559254261,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004934083216242526,
|
|
"loss": 5.9747,
|
|
"mean_token_accuracy": 0.15674864649772643,
|
|
"num_tokens": 16932901.0,
|
|
"step": 8650
|
|
},
|
|
{
|
|
"entropy": 6.3288496971130375,
|
|
"epoch": 0.8651971809866547,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004933997435036873,
|
|
"loss": 6.0915,
|
|
"mean_token_accuracy": 0.14949913769960405,
|
|
"num_tokens": 16942781.0,
|
|
"step": 8655
|
|
},
|
|
{
|
|
"entropy": 6.3220373630523685,
|
|
"epoch": 0.8656970060478832,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004933911598882405,
|
|
"loss": 5.9768,
|
|
"mean_token_accuracy": 0.1641226142644882,
|
|
"num_tokens": 16952064.0,
|
|
"step": 8660
|
|
},
|
|
{
|
|
"entropy": 6.229477071762085,
|
|
"epoch": 0.8661968311091118,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004933825707781284,
|
|
"loss": 5.9256,
|
|
"mean_token_accuracy": 0.16205176711082458,
|
|
"num_tokens": 16961528.0,
|
|
"step": 8665
|
|
},
|
|
{
|
|
"entropy": 6.289839601516723,
|
|
"epoch": 0.8666966561703404,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004933739761735671,
|
|
"loss": 6.0177,
|
|
"mean_token_accuracy": 0.159897018969059,
|
|
"num_tokens": 16971066.0,
|
|
"step": 8670
|
|
},
|
|
{
|
|
"entropy": 6.328601741790772,
|
|
"epoch": 0.867196481231569,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004933653760747726,
|
|
"loss": 6.0363,
|
|
"mean_token_accuracy": 0.15876379013061523,
|
|
"num_tokens": 16981438.0,
|
|
"step": 8675
|
|
},
|
|
{
|
|
"entropy": 6.296061944961548,
|
|
"epoch": 0.8676963062927975,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004933567704819615,
|
|
"loss": 5.9097,
|
|
"mean_token_accuracy": 0.17154327780008316,
|
|
"num_tokens": 16990836.0,
|
|
"step": 8680
|
|
},
|
|
{
|
|
"entropy": 6.251953268051148,
|
|
"epoch": 0.8681961313540261,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004933481593953502,
|
|
"loss": 5.9034,
|
|
"mean_token_accuracy": 0.16766417026519775,
|
|
"num_tokens": 17000254.0,
|
|
"step": 8685
|
|
},
|
|
{
|
|
"entropy": 6.293018245697022,
|
|
"epoch": 0.8686959564152547,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004933395428151554,
|
|
"loss": 5.9693,
|
|
"mean_token_accuracy": 0.167994187772274,
|
|
"num_tokens": 17010081.0,
|
|
"step": 8690
|
|
},
|
|
{
|
|
"entropy": 6.242474794387817,
|
|
"epoch": 0.8691957814764832,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000493330920741594,
|
|
"loss": 5.8377,
|
|
"mean_token_accuracy": 0.16764838248491287,
|
|
"num_tokens": 17018967.0,
|
|
"step": 8695
|
|
},
|
|
{
|
|
"entropy": 6.241475629806518,
|
|
"epoch": 0.8696956065377118,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004933222931748827,
|
|
"loss": 5.9817,
|
|
"mean_token_accuracy": 0.16205032765865326,
|
|
"num_tokens": 17027615.0,
|
|
"step": 8700
|
|
},
|
|
{
|
|
"entropy": 6.277568912506103,
|
|
"epoch": 0.8701954315989404,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004933136601152387,
|
|
"loss": 5.9657,
|
|
"mean_token_accuracy": 0.15991829335689545,
|
|
"num_tokens": 17038446.0,
|
|
"step": 8705
|
|
},
|
|
{
|
|
"entropy": 6.330829000473022,
|
|
"epoch": 0.8706952566601689,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004933050215628793,
|
|
"loss": 5.9964,
|
|
"mean_token_accuracy": 0.15547903925180434,
|
|
"num_tokens": 17047787.0,
|
|
"step": 8710
|
|
},
|
|
{
|
|
"entropy": 6.290249252319336,
|
|
"epoch": 0.8711950817213975,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004932963775180216,
|
|
"loss": 6.0243,
|
|
"mean_token_accuracy": 0.1581503041088581,
|
|
"num_tokens": 17056842.0,
|
|
"step": 8715
|
|
},
|
|
{
|
|
"entropy": 6.253875207901001,
|
|
"epoch": 0.8716949067826261,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004932877279808833,
|
|
"loss": 6.0439,
|
|
"mean_token_accuracy": 0.1574680671095848,
|
|
"num_tokens": 17066217.0,
|
|
"step": 8720
|
|
},
|
|
{
|
|
"entropy": 6.38287763595581,
|
|
"epoch": 0.8721947318438547,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004932790729516818,
|
|
"loss": 6.0859,
|
|
"mean_token_accuracy": 0.14897339791059494,
|
|
"num_tokens": 17077760.0,
|
|
"step": 8725
|
|
},
|
|
{
|
|
"entropy": 6.287076473236084,
|
|
"epoch": 0.8726945569050832,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004932704124306352,
|
|
"loss": 5.9441,
|
|
"mean_token_accuracy": 0.16397355273365974,
|
|
"num_tokens": 17088251.0,
|
|
"step": 8730
|
|
},
|
|
{
|
|
"entropy": 6.324968576431274,
|
|
"epoch": 0.8731943819663118,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000493261746417961,
|
|
"loss": 6.0009,
|
|
"mean_token_accuracy": 0.1548951581120491,
|
|
"num_tokens": 17098192.0,
|
|
"step": 8735
|
|
},
|
|
{
|
|
"entropy": 6.320489978790283,
|
|
"epoch": 0.8736942070275404,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004932530749138775,
|
|
"loss": 5.9802,
|
|
"mean_token_accuracy": 0.15758218765258789,
|
|
"num_tokens": 17107787.0,
|
|
"step": 8740
|
|
},
|
|
{
|
|
"entropy": 6.325667953491211,
|
|
"epoch": 0.8741940320887689,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004932443979186028,
|
|
"loss": 6.0697,
|
|
"mean_token_accuracy": 0.15468001887202262,
|
|
"num_tokens": 17118125.0,
|
|
"step": 8745
|
|
},
|
|
{
|
|
"entropy": 6.246259164810181,
|
|
"epoch": 0.8746938571499975,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004932357154323552,
|
|
"loss": 5.9382,
|
|
"mean_token_accuracy": 0.16619091480970383,
|
|
"num_tokens": 17127909.0,
|
|
"step": 8750
|
|
},
|
|
{
|
|
"entropy": 6.2894508838653564,
|
|
"epoch": 0.8751936822112261,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004932270274553531,
|
|
"loss": 5.9932,
|
|
"mean_token_accuracy": 0.1639045424759388,
|
|
"num_tokens": 17137672.0,
|
|
"step": 8755
|
|
},
|
|
{
|
|
"entropy": 6.253464698791504,
|
|
"epoch": 0.8756935072724547,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004932183339878153,
|
|
"loss": 5.9505,
|
|
"mean_token_accuracy": 0.16514331996440887,
|
|
"num_tokens": 17147151.0,
|
|
"step": 8760
|
|
},
|
|
{
|
|
"entropy": 6.269558668136597,
|
|
"epoch": 0.8761933323336832,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004932096350299602,
|
|
"loss": 5.8312,
|
|
"mean_token_accuracy": 0.16723036617040635,
|
|
"num_tokens": 17156615.0,
|
|
"step": 8765
|
|
},
|
|
{
|
|
"entropy": 6.27840633392334,
|
|
"epoch": 0.8766931573949118,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004932009305820069,
|
|
"loss": 5.9784,
|
|
"mean_token_accuracy": 0.16638180166482924,
|
|
"num_tokens": 17166089.0,
|
|
"step": 8770
|
|
},
|
|
{
|
|
"entropy": 6.316409873962402,
|
|
"epoch": 0.8771929824561403,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004931922206441743,
|
|
"loss": 6.0096,
|
|
"mean_token_accuracy": 0.1600225031375885,
|
|
"num_tokens": 17176565.0,
|
|
"step": 8775
|
|
},
|
|
{
|
|
"entropy": 6.241904830932617,
|
|
"epoch": 0.8776928075173689,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004931835052166817,
|
|
"loss": 5.9332,
|
|
"mean_token_accuracy": 0.1653585284948349,
|
|
"num_tokens": 17186987.0,
|
|
"step": 8780
|
|
},
|
|
{
|
|
"entropy": 6.268025064468384,
|
|
"epoch": 0.8781926325785975,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004931747842997481,
|
|
"loss": 5.9406,
|
|
"mean_token_accuracy": 0.16368341445922852,
|
|
"num_tokens": 17196325.0,
|
|
"step": 8785
|
|
},
|
|
{
|
|
"entropy": 6.347244501113892,
|
|
"epoch": 0.8786924576398261,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004931660578935931,
|
|
"loss": 5.992,
|
|
"mean_token_accuracy": 0.16090947836637498,
|
|
"num_tokens": 17206210.0,
|
|
"step": 8790
|
|
},
|
|
{
|
|
"entropy": 6.278488969802856,
|
|
"epoch": 0.8791922827010547,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004931573259984363,
|
|
"loss": 5.9323,
|
|
"mean_token_accuracy": 0.16109316945075988,
|
|
"num_tokens": 17216521.0,
|
|
"step": 8795
|
|
},
|
|
{
|
|
"entropy": 6.270577621459961,
|
|
"epoch": 0.8796921077622832,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004931485886144972,
|
|
"loss": 5.9463,
|
|
"mean_token_accuracy": 0.161488676071167,
|
|
"num_tokens": 17225125.0,
|
|
"step": 8800
|
|
},
|
|
{
|
|
"entropy": 6.2946327209472654,
|
|
"epoch": 0.8801919328235118,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004931398457419959,
|
|
"loss": 5.9592,
|
|
"mean_token_accuracy": 0.1619647979736328,
|
|
"num_tokens": 17234674.0,
|
|
"step": 8805
|
|
},
|
|
{
|
|
"entropy": 6.253011989593506,
|
|
"epoch": 0.8806917578847403,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004931310973811521,
|
|
"loss": 5.9129,
|
|
"mean_token_accuracy": 0.1603519558906555,
|
|
"num_tokens": 17244362.0,
|
|
"step": 8810
|
|
},
|
|
{
|
|
"entropy": 6.249275875091553,
|
|
"epoch": 0.8811915829459689,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000493122343532186,
|
|
"loss": 5.8972,
|
|
"mean_token_accuracy": 0.16217835247516632,
|
|
"num_tokens": 17253541.0,
|
|
"step": 8815
|
|
},
|
|
{
|
|
"entropy": 6.262957572937012,
|
|
"epoch": 0.8816914080071975,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000493113584195318,
|
|
"loss": 5.9096,
|
|
"mean_token_accuracy": 0.1663643643260002,
|
|
"num_tokens": 17263214.0,
|
|
"step": 8820
|
|
},
|
|
{
|
|
"entropy": 6.297371959686279,
|
|
"epoch": 0.8821912330684261,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004931048193707681,
|
|
"loss": 5.981,
|
|
"mean_token_accuracy": 0.1590479001402855,
|
|
"num_tokens": 17273991.0,
|
|
"step": 8825
|
|
},
|
|
{
|
|
"entropy": 6.257483386993409,
|
|
"epoch": 0.8826910581296546,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004930960490587573,
|
|
"loss": 5.8419,
|
|
"mean_token_accuracy": 0.1723306208848953,
|
|
"num_tokens": 17283221.0,
|
|
"step": 8830
|
|
},
|
|
{
|
|
"entropy": 6.220382976531982,
|
|
"epoch": 0.8831908831908832,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000493087273259506,
|
|
"loss": 5.9715,
|
|
"mean_token_accuracy": 0.16373782455921174,
|
|
"num_tokens": 17293520.0,
|
|
"step": 8835
|
|
},
|
|
{
|
|
"entropy": 6.228935861587525,
|
|
"epoch": 0.8836907082521117,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004930784919732349,
|
|
"loss": 5.9658,
|
|
"mean_token_accuracy": 0.1591949477791786,
|
|
"num_tokens": 17303881.0,
|
|
"step": 8840
|
|
},
|
|
{
|
|
"entropy": 6.232513046264648,
|
|
"epoch": 0.8841905333133403,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004930697052001651,
|
|
"loss": 5.879,
|
|
"mean_token_accuracy": 0.16962621510028839,
|
|
"num_tokens": 17314115.0,
|
|
"step": 8845
|
|
},
|
|
{
|
|
"entropy": 6.311823225021362,
|
|
"epoch": 0.8846903583745689,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004930609129405177,
|
|
"loss": 6.0372,
|
|
"mean_token_accuracy": 0.15722524076700212,
|
|
"num_tokens": 17324517.0,
|
|
"step": 8850
|
|
},
|
|
{
|
|
"entropy": 6.297610759735107,
|
|
"epoch": 0.8851901834357975,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004930521151945138,
|
|
"loss": 5.9879,
|
|
"mean_token_accuracy": 0.16122807413339615,
|
|
"num_tokens": 17334109.0,
|
|
"step": 8855
|
|
},
|
|
{
|
|
"entropy": 6.258606815338135,
|
|
"epoch": 0.8856900084970261,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004930433119623749,
|
|
"loss": 5.9415,
|
|
"mean_token_accuracy": 0.16207222491502762,
|
|
"num_tokens": 17344602.0,
|
|
"step": 8860
|
|
},
|
|
{
|
|
"entropy": 6.253335571289062,
|
|
"epoch": 0.8861898335582546,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004930345032443221,
|
|
"loss": 5.916,
|
|
"mean_token_accuracy": 0.1735669493675232,
|
|
"num_tokens": 17354476.0,
|
|
"step": 8865
|
|
},
|
|
{
|
|
"entropy": 6.285289144515991,
|
|
"epoch": 0.8866896586194832,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004930256890405777,
|
|
"loss": 5.9016,
|
|
"mean_token_accuracy": 0.16704263985157014,
|
|
"num_tokens": 17364748.0,
|
|
"step": 8870
|
|
},
|
|
{
|
|
"entropy": 6.265931892395019,
|
|
"epoch": 0.8871894836807117,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004930168693513627,
|
|
"loss": 5.9724,
|
|
"mean_token_accuracy": 0.16169362366199494,
|
|
"num_tokens": 17374162.0,
|
|
"step": 8875
|
|
},
|
|
{
|
|
"entropy": 6.270309209823608,
|
|
"epoch": 0.8876893087419403,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004930080441768995,
|
|
"loss": 6.0023,
|
|
"mean_token_accuracy": 0.1623801603913307,
|
|
"num_tokens": 17384042.0,
|
|
"step": 8880
|
|
},
|
|
{
|
|
"entropy": 6.265348434448242,
|
|
"epoch": 0.8881891338031689,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00049299921351741,
|
|
"loss": 5.9075,
|
|
"mean_token_accuracy": 0.1636982500553131,
|
|
"num_tokens": 17394181.0,
|
|
"step": 8885
|
|
},
|
|
{
|
|
"entropy": 6.309110927581787,
|
|
"epoch": 0.8886889588643975,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004929903773731164,
|
|
"loss": 6.0657,
|
|
"mean_token_accuracy": 0.15426195710897445,
|
|
"num_tokens": 17402983.0,
|
|
"step": 8890
|
|
},
|
|
{
|
|
"entropy": 6.370062732696534,
|
|
"epoch": 0.8891887839256261,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004929815357442409,
|
|
"loss": 6.1257,
|
|
"mean_token_accuracy": 0.15101911649107932,
|
|
"num_tokens": 17413442.0,
|
|
"step": 8895
|
|
},
|
|
{
|
|
"entropy": 6.289839220046997,
|
|
"epoch": 0.8896886089868546,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004929726886310062,
|
|
"loss": 5.9618,
|
|
"mean_token_accuracy": 0.15983574241399764,
|
|
"num_tokens": 17423644.0,
|
|
"step": 8900
|
|
},
|
|
{
|
|
"entropy": 6.32444953918457,
|
|
"epoch": 0.8901884340480831,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004929638360336348,
|
|
"loss": 6.001,
|
|
"mean_token_accuracy": 0.15785527378320693,
|
|
"num_tokens": 17433400.0,
|
|
"step": 8905
|
|
},
|
|
{
|
|
"entropy": 6.312784194946289,
|
|
"epoch": 0.8906882591093117,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004929549779523492,
|
|
"loss": 5.9725,
|
|
"mean_token_accuracy": 0.1608631819486618,
|
|
"num_tokens": 17443146.0,
|
|
"step": 8910
|
|
},
|
|
{
|
|
"entropy": 6.181512308120728,
|
|
"epoch": 0.8911880841705403,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004929461143873725,
|
|
"loss": 5.8509,
|
|
"mean_token_accuracy": 0.17120044827461242,
|
|
"num_tokens": 17452880.0,
|
|
"step": 8915
|
|
},
|
|
{
|
|
"entropy": 6.216238307952881,
|
|
"epoch": 0.8916879092317689,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004929372453389277,
|
|
"loss": 5.8919,
|
|
"mean_token_accuracy": 0.16418985575437545,
|
|
"num_tokens": 17461633.0,
|
|
"step": 8920
|
|
},
|
|
{
|
|
"entropy": 6.371498966217041,
|
|
"epoch": 0.8921877342929975,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004929283708072378,
|
|
"loss": 6.0573,
|
|
"mean_token_accuracy": 0.16026912182569503,
|
|
"num_tokens": 17470892.0,
|
|
"step": 8925
|
|
},
|
|
{
|
|
"entropy": 6.312393712997436,
|
|
"epoch": 0.8926875593542261,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004929194907925262,
|
|
"loss": 5.9447,
|
|
"mean_token_accuracy": 0.15884686559438704,
|
|
"num_tokens": 17481457.0,
|
|
"step": 8930
|
|
},
|
|
{
|
|
"entropy": 6.2684807777404785,
|
|
"epoch": 0.8931873844154546,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004929106052950163,
|
|
"loss": 5.9879,
|
|
"mean_token_accuracy": 0.15770442113280297,
|
|
"num_tokens": 17490387.0,
|
|
"step": 8935
|
|
},
|
|
{
|
|
"entropy": 6.284839916229248,
|
|
"epoch": 0.8936872094766831,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004929017143149317,
|
|
"loss": 5.9446,
|
|
"mean_token_accuracy": 0.1668263405561447,
|
|
"num_tokens": 17499478.0,
|
|
"step": 8940
|
|
},
|
|
{
|
|
"entropy": 6.33533034324646,
|
|
"epoch": 0.8941870345379117,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000492892817852496,
|
|
"loss": 6.0577,
|
|
"mean_token_accuracy": 0.15721446871757508,
|
|
"num_tokens": 17509396.0,
|
|
"step": 8945
|
|
},
|
|
{
|
|
"entropy": 6.289205551147461,
|
|
"epoch": 0.8946868595991403,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000492883915907933,
|
|
"loss": 6.0016,
|
|
"mean_token_accuracy": 0.16132455170154572,
|
|
"num_tokens": 17519773.0,
|
|
"step": 8950
|
|
},
|
|
{
|
|
"entropy": 6.268876218795777,
|
|
"epoch": 0.8951866846603689,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004928750084814668,
|
|
"loss": 5.9595,
|
|
"mean_token_accuracy": 0.16649766266345978,
|
|
"num_tokens": 17529873.0,
|
|
"step": 8955
|
|
},
|
|
{
|
|
"entropy": 6.207161092758179,
|
|
"epoch": 0.8956865097215975,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004928660955733214,
|
|
"loss": 5.9124,
|
|
"mean_token_accuracy": 0.1666805163025856,
|
|
"num_tokens": 17538642.0,
|
|
"step": 8960
|
|
},
|
|
{
|
|
"entropy": 6.30468258857727,
|
|
"epoch": 0.896186334782826,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004928571771837211,
|
|
"loss": 5.9432,
|
|
"mean_token_accuracy": 0.15742214620113373,
|
|
"num_tokens": 17546892.0,
|
|
"step": 8965
|
|
},
|
|
{
|
|
"entropy": 6.354885482788086,
|
|
"epoch": 0.8966861598440545,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004928482533128902,
|
|
"loss": 5.9948,
|
|
"mean_token_accuracy": 0.15852722972631456,
|
|
"num_tokens": 17556283.0,
|
|
"step": 8970
|
|
},
|
|
{
|
|
"entropy": 6.2500628471374515,
|
|
"epoch": 0.8971859849052831,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004928393239610535,
|
|
"loss": 5.9317,
|
|
"mean_token_accuracy": 0.15904702469706536,
|
|
"num_tokens": 17567021.0,
|
|
"step": 8975
|
|
},
|
|
{
|
|
"entropy": 6.286598110198975,
|
|
"epoch": 0.8976858099665117,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004928303891284354,
|
|
"loss": 5.9404,
|
|
"mean_token_accuracy": 0.16273575872182847,
|
|
"num_tokens": 17575927.0,
|
|
"step": 8980
|
|
},
|
|
{
|
|
"entropy": 6.2996362209320065,
|
|
"epoch": 0.8981856350277403,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004928214488152607,
|
|
"loss": 5.9861,
|
|
"mean_token_accuracy": 0.16216324120759965,
|
|
"num_tokens": 17585882.0,
|
|
"step": 8985
|
|
},
|
|
{
|
|
"entropy": 6.197223091125489,
|
|
"epoch": 0.8986854600889689,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004928125030217545,
|
|
"loss": 5.9243,
|
|
"mean_token_accuracy": 0.16700368672609328,
|
|
"num_tokens": 17595998.0,
|
|
"step": 8990
|
|
},
|
|
{
|
|
"entropy": 6.353938865661621,
|
|
"epoch": 0.8991852851501975,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004928035517481416,
|
|
"loss": 5.9475,
|
|
"mean_token_accuracy": 0.16484413295984268,
|
|
"num_tokens": 17605177.0,
|
|
"step": 8995
|
|
},
|
|
{
|
|
"entropy": 6.328395652770996,
|
|
"epoch": 0.899685110211426,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004927945949946476,
|
|
"loss": 6.0537,
|
|
"mean_token_accuracy": 0.15768050402402878,
|
|
"num_tokens": 17615089.0,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"epoch": 0.899685110211426,
|
|
"eval_entropy": 6.089246969313942,
|
|
"eval_loss": 5.979366302490234,
|
|
"eval_mean_token_accuracy": 0.16835626312266364,
|
|
"eval_num_tokens": 17615089.0,
|
|
"eval_runtime": 18.4396,
|
|
"eval_samples_per_second": 1683.607,
|
|
"eval_steps_per_second": 210.471,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"entropy": 6.292134714126587,
|
|
"epoch": 0.9001849352726545,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004927856327614975,
|
|
"loss": 5.9284,
|
|
"mean_token_accuracy": 0.16191588938236237,
|
|
"num_tokens": 17624708.0,
|
|
"step": 9005
|
|
},
|
|
{
|
|
"entropy": 6.278617477416992,
|
|
"epoch": 0.9006847603338831,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000492776665048917,
|
|
"loss": 5.9858,
|
|
"mean_token_accuracy": 0.16012932509183883,
|
|
"num_tokens": 17633639.0,
|
|
"step": 9010
|
|
},
|
|
{
|
|
"entropy": 6.231465530395508,
|
|
"epoch": 0.9011845853951117,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004927676918571316,
|
|
"loss": 5.9511,
|
|
"mean_token_accuracy": 0.162121245265007,
|
|
"num_tokens": 17643092.0,
|
|
"step": 9015
|
|
},
|
|
{
|
|
"entropy": 6.263545894622803,
|
|
"epoch": 0.9016844104563403,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004927587131863671,
|
|
"loss": 6.0164,
|
|
"mean_token_accuracy": 0.15603464394807814,
|
|
"num_tokens": 17652698.0,
|
|
"step": 9020
|
|
},
|
|
{
|
|
"entropy": 6.271323251724243,
|
|
"epoch": 0.9021842355175689,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004927497290368493,
|
|
"loss": 5.8888,
|
|
"mean_token_accuracy": 0.16828452795743942,
|
|
"num_tokens": 17662654.0,
|
|
"step": 9025
|
|
},
|
|
{
|
|
"entropy": 6.273025941848755,
|
|
"epoch": 0.9026840605787975,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004927407394088046,
|
|
"loss": 5.9429,
|
|
"mean_token_accuracy": 0.1610307961702347,
|
|
"num_tokens": 17672476.0,
|
|
"step": 9030
|
|
},
|
|
{
|
|
"entropy": 6.2586359024047855,
|
|
"epoch": 0.9031838856400259,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004927317443024587,
|
|
"loss": 5.9863,
|
|
"mean_token_accuracy": 0.15699801445007325,
|
|
"num_tokens": 17682612.0,
|
|
"step": 9035
|
|
},
|
|
{
|
|
"entropy": 6.320130825042725,
|
|
"epoch": 0.9036837107012545,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004927227437180382,
|
|
"loss": 5.994,
|
|
"mean_token_accuracy": 0.15611168295145034,
|
|
"num_tokens": 17692020.0,
|
|
"step": 9040
|
|
},
|
|
{
|
|
"entropy": 6.231010818481446,
|
|
"epoch": 0.9041835357624831,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004927137376557696,
|
|
"loss": 5.9379,
|
|
"mean_token_accuracy": 0.16400570720434188,
|
|
"num_tokens": 17702677.0,
|
|
"step": 9045
|
|
},
|
|
{
|
|
"entropy": 6.217643213272095,
|
|
"epoch": 0.9046833608237117,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004927047261158793,
|
|
"loss": 5.8297,
|
|
"mean_token_accuracy": 0.173498272895813,
|
|
"num_tokens": 17711753.0,
|
|
"step": 9050
|
|
},
|
|
{
|
|
"entropy": 6.31237382888794,
|
|
"epoch": 0.9051831858849403,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004926957090985942,
|
|
"loss": 5.9779,
|
|
"mean_token_accuracy": 0.15903800278902053,
|
|
"num_tokens": 17721293.0,
|
|
"step": 9055
|
|
},
|
|
{
|
|
"entropy": 6.312780284881592,
|
|
"epoch": 0.9056830109461689,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004926866866041409,
|
|
"loss": 5.9984,
|
|
"mean_token_accuracy": 0.16096413433551787,
|
|
"num_tokens": 17732311.0,
|
|
"step": 9060
|
|
},
|
|
{
|
|
"entropy": 6.253921222686768,
|
|
"epoch": 0.9061828360073975,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004926776586327467,
|
|
"loss": 5.9492,
|
|
"mean_token_accuracy": 0.16371444910764693,
|
|
"num_tokens": 17743040.0,
|
|
"step": 9065
|
|
},
|
|
{
|
|
"entropy": 6.241863203048706,
|
|
"epoch": 0.9066826610686259,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004926686251846386,
|
|
"loss": 5.88,
|
|
"mean_token_accuracy": 0.17258938103914262,
|
|
"num_tokens": 17752436.0,
|
|
"step": 9070
|
|
},
|
|
{
|
|
"entropy": 6.243113613128662,
|
|
"epoch": 0.9071824861298545,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004926595862600439,
|
|
"loss": 5.9307,
|
|
"mean_token_accuracy": 0.1576288029551506,
|
|
"num_tokens": 17762043.0,
|
|
"step": 9075
|
|
},
|
|
{
|
|
"entropy": 6.241170501708984,
|
|
"epoch": 0.9076823111910831,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004926505418591901,
|
|
"loss": 5.9659,
|
|
"mean_token_accuracy": 0.1605820342898369,
|
|
"num_tokens": 17772065.0,
|
|
"step": 9080
|
|
},
|
|
{
|
|
"entropy": 6.201979398727417,
|
|
"epoch": 0.9081821362523117,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004926414919823045,
|
|
"loss": 5.8558,
|
|
"mean_token_accuracy": 0.16861065924167634,
|
|
"num_tokens": 17781472.0,
|
|
"step": 9085
|
|
},
|
|
{
|
|
"entropy": 6.241433620452881,
|
|
"epoch": 0.9086819613135403,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004926324366296151,
|
|
"loss": 5.955,
|
|
"mean_token_accuracy": 0.16183115988969804,
|
|
"num_tokens": 17789435.0,
|
|
"step": 9090
|
|
},
|
|
{
|
|
"entropy": 6.2638514041900635,
|
|
"epoch": 0.9091817863747689,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004926233758013494,
|
|
"loss": 5.9374,
|
|
"mean_token_accuracy": 0.1634066179394722,
|
|
"num_tokens": 17798367.0,
|
|
"step": 9095
|
|
},
|
|
{
|
|
"entropy": 6.294947338104248,
|
|
"epoch": 0.9096816114359974,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004926143094977359,
|
|
"loss": 5.9351,
|
|
"mean_token_accuracy": 0.16648186147212982,
|
|
"num_tokens": 17807660.0,
|
|
"step": 9100
|
|
},
|
|
{
|
|
"entropy": 6.248531723022461,
|
|
"epoch": 0.9101814364972259,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004926052377190022,
|
|
"loss": 5.958,
|
|
"mean_token_accuracy": 0.1683475285768509,
|
|
"num_tokens": 17816993.0,
|
|
"step": 9105
|
|
},
|
|
{
|
|
"entropy": 6.3174378871917725,
|
|
"epoch": 0.9106812615584545,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004925961604653765,
|
|
"loss": 5.9222,
|
|
"mean_token_accuracy": 0.1601351022720337,
|
|
"num_tokens": 17826570.0,
|
|
"step": 9110
|
|
},
|
|
{
|
|
"entropy": 6.304720497131347,
|
|
"epoch": 0.9111810866196831,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004925870777370877,
|
|
"loss": 5.9501,
|
|
"mean_token_accuracy": 0.16615567058324815,
|
|
"num_tokens": 17835921.0,
|
|
"step": 9115
|
|
},
|
|
{
|
|
"entropy": 6.245967197418213,
|
|
"epoch": 0.9116809116809117,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004925779895343639,
|
|
"loss": 5.9598,
|
|
"mean_token_accuracy": 0.16665620654821395,
|
|
"num_tokens": 17845713.0,
|
|
"step": 9120
|
|
},
|
|
{
|
|
"entropy": 6.305330467224121,
|
|
"epoch": 0.9121807367421403,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004925688958574339,
|
|
"loss": 5.9642,
|
|
"mean_token_accuracy": 0.15834677070379258,
|
|
"num_tokens": 17855808.0,
|
|
"step": 9125
|
|
},
|
|
{
|
|
"entropy": 6.291973972320557,
|
|
"epoch": 0.9126805618033689,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004925597967065264,
|
|
"loss": 5.949,
|
|
"mean_token_accuracy": 0.16328009814023972,
|
|
"num_tokens": 17865427.0,
|
|
"step": 9130
|
|
},
|
|
{
|
|
"entropy": 6.271231603622437,
|
|
"epoch": 0.9131803868645973,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004925506920818705,
|
|
"loss": 6.0015,
|
|
"mean_token_accuracy": 0.1572902172803879,
|
|
"num_tokens": 17876371.0,
|
|
"step": 9135
|
|
},
|
|
{
|
|
"entropy": 6.2581878185272215,
|
|
"epoch": 0.9136802119258259,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004925415819836951,
|
|
"loss": 5.9355,
|
|
"mean_token_accuracy": 0.1624238073825836,
|
|
"num_tokens": 17886050.0,
|
|
"step": 9140
|
|
},
|
|
{
|
|
"entropy": 6.299579095840454,
|
|
"epoch": 0.9141800369870545,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004925324664122294,
|
|
"loss": 5.9438,
|
|
"mean_token_accuracy": 0.166976685076952,
|
|
"num_tokens": 17896509.0,
|
|
"step": 9145
|
|
},
|
|
{
|
|
"entropy": 6.364652252197265,
|
|
"epoch": 0.9146798620482831,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004925233453677029,
|
|
"loss": 5.9814,
|
|
"mean_token_accuracy": 0.1645218975841999,
|
|
"num_tokens": 17906242.0,
|
|
"step": 9150
|
|
},
|
|
{
|
|
"entropy": 6.244912767410279,
|
|
"epoch": 0.9151796871095117,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004925142188503451,
|
|
"loss": 5.9307,
|
|
"mean_token_accuracy": 0.1669577419757843,
|
|
"num_tokens": 17916261.0,
|
|
"step": 9155
|
|
},
|
|
{
|
|
"entropy": 6.257868528366089,
|
|
"epoch": 0.9156795121707403,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004925050868603854,
|
|
"loss": 5.9597,
|
|
"mean_token_accuracy": 0.1634727329015732,
|
|
"num_tokens": 17926486.0,
|
|
"step": 9160
|
|
},
|
|
{
|
|
"entropy": 6.272066068649292,
|
|
"epoch": 0.9161793372319688,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004924959493980537,
|
|
"loss": 5.9617,
|
|
"mean_token_accuracy": 0.1613192856311798,
|
|
"num_tokens": 17936374.0,
|
|
"step": 9165
|
|
},
|
|
{
|
|
"entropy": 6.388484382629395,
|
|
"epoch": 0.9166791622931973,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004924868064635798,
|
|
"loss": 6.215,
|
|
"mean_token_accuracy": 0.14638849198818207,
|
|
"num_tokens": 17946930.0,
|
|
"step": 9170
|
|
},
|
|
{
|
|
"entropy": 6.404567432403565,
|
|
"epoch": 0.9171789873544259,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000492477658057194,
|
|
"loss": 5.9626,
|
|
"mean_token_accuracy": 0.1665995702147484,
|
|
"num_tokens": 17955760.0,
|
|
"step": 9175
|
|
},
|
|
{
|
|
"entropy": 6.271450710296631,
|
|
"epoch": 0.9176788124156545,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004924685041791262,
|
|
"loss": 5.8991,
|
|
"mean_token_accuracy": 0.16514640748500825,
|
|
"num_tokens": 17965871.0,
|
|
"step": 9180
|
|
},
|
|
{
|
|
"entropy": 6.132813215255737,
|
|
"epoch": 0.9181786374768831,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004924593448296068,
|
|
"loss": 5.8745,
|
|
"mean_token_accuracy": 0.17241406589746475,
|
|
"num_tokens": 17974551.0,
|
|
"step": 9185
|
|
},
|
|
{
|
|
"entropy": 6.302043342590332,
|
|
"epoch": 0.9186784625381117,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004924501800088662,
|
|
"loss": 5.9878,
|
|
"mean_token_accuracy": 0.16283727288246155,
|
|
"num_tokens": 17983675.0,
|
|
"step": 9190
|
|
},
|
|
{
|
|
"entropy": 6.315224266052246,
|
|
"epoch": 0.9191782875993403,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004924410097171351,
|
|
"loss": 5.9522,
|
|
"mean_token_accuracy": 0.16294665336608888,
|
|
"num_tokens": 17993299.0,
|
|
"step": 9195
|
|
},
|
|
{
|
|
"entropy": 6.310178947448731,
|
|
"epoch": 0.9196781126605688,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000492431833954644,
|
|
"loss": 5.9236,
|
|
"mean_token_accuracy": 0.17401935905218124,
|
|
"num_tokens": 18004755.0,
|
|
"step": 9200
|
|
},
|
|
{
|
|
"entropy": 6.294361352920532,
|
|
"epoch": 0.9201779377217973,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004924226527216241,
|
|
"loss": 6.0573,
|
|
"mean_token_accuracy": 0.15418292582035065,
|
|
"num_tokens": 18014908.0,
|
|
"step": 9205
|
|
},
|
|
{
|
|
"entropy": 6.279791784286499,
|
|
"epoch": 0.9206777627830259,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004924134660183061,
|
|
"loss": 5.9196,
|
|
"mean_token_accuracy": 0.15847023725509643,
|
|
"num_tokens": 18023919.0,
|
|
"step": 9210
|
|
},
|
|
{
|
|
"entropy": 6.22650179862976,
|
|
"epoch": 0.9211775878442545,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004924042738449212,
|
|
"loss": 5.8757,
|
|
"mean_token_accuracy": 0.16466255635023117,
|
|
"num_tokens": 18033706.0,
|
|
"step": 9215
|
|
},
|
|
{
|
|
"entropy": 6.280341720581054,
|
|
"epoch": 0.9216774129054831,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004923950762017008,
|
|
"loss": 5.9824,
|
|
"mean_token_accuracy": 0.15151336118578912,
|
|
"num_tokens": 18043171.0,
|
|
"step": 9220
|
|
},
|
|
{
|
|
"entropy": 6.254725313186645,
|
|
"epoch": 0.9221772379667117,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004923858730888762,
|
|
"loss": 5.9054,
|
|
"mean_token_accuracy": 0.17280881702899933,
|
|
"num_tokens": 18052567.0,
|
|
"step": 9225
|
|
},
|
|
{
|
|
"entropy": 6.25433349609375,
|
|
"epoch": 0.9226770630279402,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000492376664506679,
|
|
"loss": 5.932,
|
|
"mean_token_accuracy": 0.1663724198937416,
|
|
"num_tokens": 18061648.0,
|
|
"step": 9230
|
|
},
|
|
{
|
|
"entropy": 6.243300437927246,
|
|
"epoch": 0.9231768880891688,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004923674504553408,
|
|
"loss": 5.9742,
|
|
"mean_token_accuracy": 0.1620986804366112,
|
|
"num_tokens": 18071079.0,
|
|
"step": 9235
|
|
},
|
|
{
|
|
"entropy": 6.306953430175781,
|
|
"epoch": 0.9236767131503973,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004923582309350935,
|
|
"loss": 6.0005,
|
|
"mean_token_accuracy": 0.15952717736363412,
|
|
"num_tokens": 18081162.0,
|
|
"step": 9240
|
|
},
|
|
{
|
|
"entropy": 6.345398807525635,
|
|
"epoch": 0.9241765382116259,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000492349005946169,
|
|
"loss": 5.9374,
|
|
"mean_token_accuracy": 0.16532410085201263,
|
|
"num_tokens": 18090072.0,
|
|
"step": 9245
|
|
},
|
|
{
|
|
"entropy": 6.303242635726929,
|
|
"epoch": 0.9246763632728545,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004923397754887994,
|
|
"loss": 5.9995,
|
|
"mean_token_accuracy": 0.15876416563987733,
|
|
"num_tokens": 18100565.0,
|
|
"step": 9250
|
|
},
|
|
{
|
|
"entropy": 6.240298080444336,
|
|
"epoch": 0.9251761883340831,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004923305395632172,
|
|
"loss": 5.9347,
|
|
"mean_token_accuracy": 0.16173174232244492,
|
|
"num_tokens": 18109795.0,
|
|
"step": 9255
|
|
},
|
|
{
|
|
"entropy": 6.315546941757202,
|
|
"epoch": 0.9256760133953117,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004923212981696543,
|
|
"loss": 5.9831,
|
|
"mean_token_accuracy": 0.1543680414557457,
|
|
"num_tokens": 18118821.0,
|
|
"step": 9260
|
|
},
|
|
{
|
|
"entropy": 6.290459442138672,
|
|
"epoch": 0.9261758384565402,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004923120513083436,
|
|
"loss": 5.9808,
|
|
"mean_token_accuracy": 0.16235587149858474,
|
|
"num_tokens": 18128709.0,
|
|
"step": 9265
|
|
},
|
|
{
|
|
"entropy": 6.252789449691773,
|
|
"epoch": 0.9266756635177688,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004923027989795175,
|
|
"loss": 6.0394,
|
|
"mean_token_accuracy": 0.15382776260375977,
|
|
"num_tokens": 18138134.0,
|
|
"step": 9270
|
|
},
|
|
{
|
|
"entropy": 6.252909088134766,
|
|
"epoch": 0.9271754885789973,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000492293541183409,
|
|
"loss": 5.8792,
|
|
"mean_token_accuracy": 0.1648166984319687,
|
|
"num_tokens": 18147455.0,
|
|
"step": 9275
|
|
},
|
|
{
|
|
"entropy": 6.248918867111206,
|
|
"epoch": 0.9276753136402259,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004922842779202509,
|
|
"loss": 5.9528,
|
|
"mean_token_accuracy": 0.16555965542793274,
|
|
"num_tokens": 18157787.0,
|
|
"step": 9280
|
|
},
|
|
{
|
|
"entropy": 6.201677131652832,
|
|
"epoch": 0.9281751387014545,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004922750091902763,
|
|
"loss": 5.9055,
|
|
"mean_token_accuracy": 0.16896117180585862,
|
|
"num_tokens": 18167607.0,
|
|
"step": 9285
|
|
},
|
|
{
|
|
"entropy": 6.239971256256103,
|
|
"epoch": 0.9286749637626831,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004922657349937183,
|
|
"loss": 5.9659,
|
|
"mean_token_accuracy": 0.15692343860864638,
|
|
"num_tokens": 18178927.0,
|
|
"step": 9290
|
|
},
|
|
{
|
|
"entropy": 6.226718902587891,
|
|
"epoch": 0.9291747888239116,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004922564553308103,
|
|
"loss": 5.8696,
|
|
"mean_token_accuracy": 0.16722559928894043,
|
|
"num_tokens": 18188907.0,
|
|
"step": 9295
|
|
},
|
|
{
|
|
"entropy": 6.30553789138794,
|
|
"epoch": 0.9296746138851402,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000492247170201786,
|
|
"loss": 5.8235,
|
|
"mean_token_accuracy": 0.16978015154600143,
|
|
"num_tokens": 18198937.0,
|
|
"step": 9300
|
|
},
|
|
{
|
|
"entropy": 6.3082949161529545,
|
|
"epoch": 0.9301744389463688,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004922378796068785,
|
|
"loss": 5.9083,
|
|
"mean_token_accuracy": 0.15979528725147246,
|
|
"num_tokens": 18209306.0,
|
|
"step": 9305
|
|
},
|
|
{
|
|
"entropy": 6.329949045181275,
|
|
"epoch": 0.9306742640075973,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000492228583546322,
|
|
"loss": 6.0446,
|
|
"mean_token_accuracy": 0.14997346997261046,
|
|
"num_tokens": 18219665.0,
|
|
"step": 9310
|
|
},
|
|
{
|
|
"entropy": 6.244217824935913,
|
|
"epoch": 0.9311740890688259,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004922192820203502,
|
|
"loss": 5.9165,
|
|
"mean_token_accuracy": 0.1625823497772217,
|
|
"num_tokens": 18229044.0,
|
|
"step": 9315
|
|
},
|
|
{
|
|
"entropy": 6.2535515308380125,
|
|
"epoch": 0.9316739141300545,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004922099750291972,
|
|
"loss": 5.883,
|
|
"mean_token_accuracy": 0.1696150168776512,
|
|
"num_tokens": 18239373.0,
|
|
"step": 9320
|
|
},
|
|
{
|
|
"entropy": 6.272071027755738,
|
|
"epoch": 0.9321737391912831,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004922006625730971,
|
|
"loss": 5.9231,
|
|
"mean_token_accuracy": 0.16318091452121736,
|
|
"num_tokens": 18249195.0,
|
|
"step": 9325
|
|
},
|
|
{
|
|
"entropy": 6.297378587722778,
|
|
"epoch": 0.9326735642525116,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004921913446522843,
|
|
"loss": 5.9079,
|
|
"mean_token_accuracy": 0.16697221100330353,
|
|
"num_tokens": 18258399.0,
|
|
"step": 9330
|
|
},
|
|
{
|
|
"entropy": 6.236215400695801,
|
|
"epoch": 0.9331733893137402,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.000492182021266993,
|
|
"loss": 5.9244,
|
|
"mean_token_accuracy": 0.17269572764635086,
|
|
"num_tokens": 18268952.0,
|
|
"step": 9335
|
|
},
|
|
{
|
|
"entropy": 6.251527929306031,
|
|
"epoch": 0.9336732143749688,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000492172692417458,
|
|
"loss": 5.8787,
|
|
"mean_token_accuracy": 0.1615613393485546,
|
|
"num_tokens": 18279482.0,
|
|
"step": 9340
|
|
},
|
|
{
|
|
"entropy": 6.219136714935303,
|
|
"epoch": 0.9341730394361973,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000492163358103914,
|
|
"loss": 5.9457,
|
|
"mean_token_accuracy": 0.16052954345941545,
|
|
"num_tokens": 18289069.0,
|
|
"step": 9345
|
|
},
|
|
{
|
|
"entropy": 6.226378631591797,
|
|
"epoch": 0.9346728644974259,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004921540183265957,
|
|
"loss": 5.9037,
|
|
"mean_token_accuracy": 0.16764697730541228,
|
|
"num_tokens": 18298333.0,
|
|
"step": 9350
|
|
},
|
|
{
|
|
"entropy": 6.261866760253906,
|
|
"epoch": 0.9351726895586545,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004921446730857383,
|
|
"loss": 5.9643,
|
|
"mean_token_accuracy": 0.162288798391819,
|
|
"num_tokens": 18307661.0,
|
|
"step": 9355
|
|
},
|
|
{
|
|
"entropy": 6.30472583770752,
|
|
"epoch": 0.935672514619883,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004921353223815767,
|
|
"loss": 6.0166,
|
|
"mean_token_accuracy": 0.15729953050613404,
|
|
"num_tokens": 18317786.0,
|
|
"step": 9360
|
|
},
|
|
{
|
|
"entropy": 6.332795429229736,
|
|
"epoch": 0.9361723396811116,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004921259662143463,
|
|
"loss": 6.009,
|
|
"mean_token_accuracy": 0.158196884393692,
|
|
"num_tokens": 18328430.0,
|
|
"step": 9365
|
|
},
|
|
{
|
|
"entropy": 6.300108432769775,
|
|
"epoch": 0.9366721647423402,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004921166045842825,
|
|
"loss": 6.0099,
|
|
"mean_token_accuracy": 0.16090964525938034,
|
|
"num_tokens": 18339800.0,
|
|
"step": 9370
|
|
},
|
|
{
|
|
"entropy": 6.3749799728393555,
|
|
"epoch": 0.9371719898035688,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004921072374916208,
|
|
"loss": 5.9799,
|
|
"mean_token_accuracy": 0.15587708204984665,
|
|
"num_tokens": 18348819.0,
|
|
"step": 9375
|
|
},
|
|
{
|
|
"entropy": 6.2640478134155275,
|
|
"epoch": 0.9376718148647973,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004920978649365968,
|
|
"loss": 5.8684,
|
|
"mean_token_accuracy": 0.1690756395459175,
|
|
"num_tokens": 18358189.0,
|
|
"step": 9380
|
|
},
|
|
{
|
|
"entropy": 6.243742990493774,
|
|
"epoch": 0.9381716399260259,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004920884869194463,
|
|
"loss": 5.8828,
|
|
"mean_token_accuracy": 0.1634888768196106,
|
|
"num_tokens": 18367571.0,
|
|
"step": 9385
|
|
},
|
|
{
|
|
"entropy": 6.2228577613830565,
|
|
"epoch": 0.9386714649872545,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004920791034404054,
|
|
"loss": 5.8837,
|
|
"mean_token_accuracy": 0.16610911041498183,
|
|
"num_tokens": 18376699.0,
|
|
"step": 9390
|
|
},
|
|
{
|
|
"entropy": 6.207282161712646,
|
|
"epoch": 0.939171290048483,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004920697144997102,
|
|
"loss": 5.7872,
|
|
"mean_token_accuracy": 0.16946833729743957,
|
|
"num_tokens": 18386036.0,
|
|
"step": 9395
|
|
},
|
|
{
|
|
"entropy": 6.231820106506348,
|
|
"epoch": 0.9396711151097116,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004920603200975968,
|
|
"loss": 5.9576,
|
|
"mean_token_accuracy": 0.17333413809537887,
|
|
"num_tokens": 18395363.0,
|
|
"step": 9400
|
|
},
|
|
{
|
|
"entropy": 6.2749590396881105,
|
|
"epoch": 0.9401709401709402,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004920509202343016,
|
|
"loss": 5.9288,
|
|
"mean_token_accuracy": 0.16022184640169143,
|
|
"num_tokens": 18404919.0,
|
|
"step": 9405
|
|
},
|
|
{
|
|
"entropy": 6.300900220870972,
|
|
"epoch": 0.9406707652321687,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000492041514910061,
|
|
"loss": 5.9841,
|
|
"mean_token_accuracy": 0.16264214664697646,
|
|
"num_tokens": 18413520.0,
|
|
"step": 9410
|
|
},
|
|
{
|
|
"entropy": 6.2958275318145756,
|
|
"epoch": 0.9411705902933973,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004920321041251118,
|
|
"loss": 5.9679,
|
|
"mean_token_accuracy": 0.16468316912651063,
|
|
"num_tokens": 18422942.0,
|
|
"step": 9415
|
|
},
|
|
{
|
|
"entropy": 6.321637487411499,
|
|
"epoch": 0.9416704153546259,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004920226878796908,
|
|
"loss": 5.9971,
|
|
"mean_token_accuracy": 0.15969598293304443,
|
|
"num_tokens": 18432782.0,
|
|
"step": 9420
|
|
},
|
|
{
|
|
"entropy": 6.28650164604187,
|
|
"epoch": 0.9421702404158544,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004920132661740348,
|
|
"loss": 5.9706,
|
|
"mean_token_accuracy": 0.16216376572847366,
|
|
"num_tokens": 18443058.0,
|
|
"step": 9425
|
|
},
|
|
{
|
|
"entropy": 6.2773552417755125,
|
|
"epoch": 0.942670065477083,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004920038390083808,
|
|
"loss": 5.8777,
|
|
"mean_token_accuracy": 0.16326519697904587,
|
|
"num_tokens": 18453138.0,
|
|
"step": 9430
|
|
},
|
|
{
|
|
"entropy": 6.275562477111817,
|
|
"epoch": 0.9431698905383116,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000491994406382966,
|
|
"loss": 5.9969,
|
|
"mean_token_accuracy": 0.16009863764047622,
|
|
"num_tokens": 18463763.0,
|
|
"step": 9435
|
|
},
|
|
{
|
|
"entropy": 6.2769359111785885,
|
|
"epoch": 0.9436697155995402,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004919849682980278,
|
|
"loss": 5.9007,
|
|
"mean_token_accuracy": 0.1656608447432518,
|
|
"num_tokens": 18473391.0,
|
|
"step": 9440
|
|
},
|
|
{
|
|
"entropy": 6.272989559173584,
|
|
"epoch": 0.9441695406607687,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004919755247538037,
|
|
"loss": 5.9317,
|
|
"mean_token_accuracy": 0.1613200545310974,
|
|
"num_tokens": 18483002.0,
|
|
"step": 9445
|
|
},
|
|
{
|
|
"entropy": 6.279959297180175,
|
|
"epoch": 0.9446693657219973,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004919660757505312,
|
|
"loss": 5.9063,
|
|
"mean_token_accuracy": 0.1690466932952404,
|
|
"num_tokens": 18493428.0,
|
|
"step": 9450
|
|
},
|
|
{
|
|
"entropy": 6.317495059967041,
|
|
"epoch": 0.9451691907832259,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004919566212884481,
|
|
"loss": 5.9257,
|
|
"mean_token_accuracy": 0.1611894354224205,
|
|
"num_tokens": 18502756.0,
|
|
"step": 9455
|
|
},
|
|
{
|
|
"entropy": 6.305592489242554,
|
|
"epoch": 0.9456690158444544,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004919471613677921,
|
|
"loss": 5.974,
|
|
"mean_token_accuracy": 0.15674229413270951,
|
|
"num_tokens": 18512576.0,
|
|
"step": 9460
|
|
},
|
|
{
|
|
"entropy": 6.26822247505188,
|
|
"epoch": 0.946168840905683,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004919376959888015,
|
|
"loss": 5.8719,
|
|
"mean_token_accuracy": 0.16143862009048462,
|
|
"num_tokens": 18522271.0,
|
|
"step": 9465
|
|
},
|
|
{
|
|
"entropy": 6.212142419815064,
|
|
"epoch": 0.9466686659669116,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004919282251517142,
|
|
"loss": 5.8461,
|
|
"mean_token_accuracy": 0.1665372982621193,
|
|
"num_tokens": 18532738.0,
|
|
"step": 9470
|
|
},
|
|
{
|
|
"entropy": 6.32465672492981,
|
|
"epoch": 0.9471684910281402,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004919187488567686,
|
|
"loss": 6.0566,
|
|
"mean_token_accuracy": 0.16513460576534272,
|
|
"num_tokens": 18543132.0,
|
|
"step": 9475
|
|
},
|
|
{
|
|
"entropy": 6.260820722579956,
|
|
"epoch": 0.9476683160893687,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004919092671042031,
|
|
"loss": 5.8519,
|
|
"mean_token_accuracy": 0.17434045523405076,
|
|
"num_tokens": 18551777.0,
|
|
"step": 9480
|
|
},
|
|
{
|
|
"entropy": 6.203169155120849,
|
|
"epoch": 0.9481681411505973,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004918997798942562,
|
|
"loss": 5.9106,
|
|
"mean_token_accuracy": 0.1641959860920906,
|
|
"num_tokens": 18561137.0,
|
|
"step": 9485
|
|
},
|
|
{
|
|
"entropy": 6.229916381835937,
|
|
"epoch": 0.9486679662118258,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004918902872271668,
|
|
"loss": 5.9682,
|
|
"mean_token_accuracy": 0.16389337182044983,
|
|
"num_tokens": 18571917.0,
|
|
"step": 9490
|
|
},
|
|
{
|
|
"entropy": 6.343405866622925,
|
|
"epoch": 0.9491677912730544,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004918807891031734,
|
|
"loss": 5.9482,
|
|
"mean_token_accuracy": 0.15927508920431138,
|
|
"num_tokens": 18581670.0,
|
|
"step": 9495
|
|
},
|
|
{
|
|
"entropy": 6.218849134445191,
|
|
"epoch": 0.949667616334283,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004918712855225154,
|
|
"loss": 5.8601,
|
|
"mean_token_accuracy": 0.1673530474305153,
|
|
"num_tokens": 18590140.0,
|
|
"step": 9500
|
|
},
|
|
{
|
|
"entropy": 6.119427585601807,
|
|
"epoch": 0.9501674413955116,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004918617764854314,
|
|
"loss": 5.8014,
|
|
"mean_token_accuracy": 0.17081253230571747,
|
|
"num_tokens": 18599496.0,
|
|
"step": 9505
|
|
},
|
|
{
|
|
"entropy": 6.249617624282837,
|
|
"epoch": 0.9506672664567402,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000491852261992161,
|
|
"loss": 5.9241,
|
|
"mean_token_accuracy": 0.1679234653711319,
|
|
"num_tokens": 18609415.0,
|
|
"step": 9510
|
|
},
|
|
{
|
|
"entropy": 6.283448076248169,
|
|
"epoch": 0.9511670915179687,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004918427420429435,
|
|
"loss": 5.9512,
|
|
"mean_token_accuracy": 0.16335123479366304,
|
|
"num_tokens": 18619215.0,
|
|
"step": 9515
|
|
},
|
|
{
|
|
"entropy": 6.332901191711426,
|
|
"epoch": 0.9516669165791973,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004918332166380185,
|
|
"loss": 6.0091,
|
|
"mean_token_accuracy": 0.1606967955827713,
|
|
"num_tokens": 18629381.0,
|
|
"step": 9520
|
|
},
|
|
{
|
|
"entropy": 6.238650560379028,
|
|
"epoch": 0.9521667416404258,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004918236857776254,
|
|
"loss": 5.9547,
|
|
"mean_token_accuracy": 0.16847832202911378,
|
|
"num_tokens": 18639049.0,
|
|
"step": 9525
|
|
},
|
|
{
|
|
"entropy": 6.28602786064148,
|
|
"epoch": 0.9526665667016544,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004918141494620042,
|
|
"loss": 5.9778,
|
|
"mean_token_accuracy": 0.16157467365264894,
|
|
"num_tokens": 18649096.0,
|
|
"step": 9530
|
|
},
|
|
{
|
|
"entropy": 6.310562324523926,
|
|
"epoch": 0.953166391762883,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004918046076913949,
|
|
"loss": 5.9326,
|
|
"mean_token_accuracy": 0.16652203798294068,
|
|
"num_tokens": 18658747.0,
|
|
"step": 9535
|
|
},
|
|
{
|
|
"entropy": 6.278875207901001,
|
|
"epoch": 0.9536662168241116,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004917950604660374,
|
|
"loss": 5.9994,
|
|
"mean_token_accuracy": 0.15605221539735795,
|
|
"num_tokens": 18668538.0,
|
|
"step": 9540
|
|
},
|
|
{
|
|
"entropy": 6.241620063781738,
|
|
"epoch": 0.9541660418853402,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000491785507786172,
|
|
"loss": 5.9232,
|
|
"mean_token_accuracy": 0.1616185799241066,
|
|
"num_tokens": 18679241.0,
|
|
"step": 9545
|
|
},
|
|
{
|
|
"entropy": 6.268738031387329,
|
|
"epoch": 0.9546658669465687,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004917759496520388,
|
|
"loss": 5.9461,
|
|
"mean_token_accuracy": 0.16174628883600234,
|
|
"num_tokens": 18689405.0,
|
|
"step": 9550
|
|
},
|
|
{
|
|
"entropy": 6.344794368743896,
|
|
"epoch": 0.9551656920077972,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004917663860638787,
|
|
"loss": 6.0081,
|
|
"mean_token_accuracy": 0.1577272281050682,
|
|
"num_tokens": 18697989.0,
|
|
"step": 9555
|
|
},
|
|
{
|
|
"entropy": 6.193477725982666,
|
|
"epoch": 0.9556655170690258,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004917568170219321,
|
|
"loss": 5.8794,
|
|
"mean_token_accuracy": 0.16585686057806015,
|
|
"num_tokens": 18706992.0,
|
|
"step": 9560
|
|
},
|
|
{
|
|
"entropy": 6.1859211921691895,
|
|
"epoch": 0.9561653421302544,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004917472425264397,
|
|
"loss": 5.9308,
|
|
"mean_token_accuracy": 0.16255859285593033,
|
|
"num_tokens": 18716742.0,
|
|
"step": 9565
|
|
},
|
|
{
|
|
"entropy": 6.308370923995971,
|
|
"epoch": 0.956665167191483,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004917376625776425,
|
|
"loss": 6.0649,
|
|
"mean_token_accuracy": 0.15201732367277146,
|
|
"num_tokens": 18725955.0,
|
|
"step": 9570
|
|
},
|
|
{
|
|
"entropy": 6.308044338226319,
|
|
"epoch": 0.9571649922527116,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004917280771757814,
|
|
"loss": 5.9624,
|
|
"mean_token_accuracy": 0.16200267970561982,
|
|
"num_tokens": 18735199.0,
|
|
"step": 9575
|
|
},
|
|
{
|
|
"entropy": 6.288038158416748,
|
|
"epoch": 0.9576648173139402,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004917184863210977,
|
|
"loss": 5.9869,
|
|
"mean_token_accuracy": 0.1553981587290764,
|
|
"num_tokens": 18745457.0,
|
|
"step": 9580
|
|
},
|
|
{
|
|
"entropy": 6.305157852172852,
|
|
"epoch": 0.9581646423751687,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004917088900138326,
|
|
"loss": 5.9591,
|
|
"mean_token_accuracy": 0.16513299345970153,
|
|
"num_tokens": 18753869.0,
|
|
"step": 9585
|
|
},
|
|
{
|
|
"entropy": 6.301988887786865,
|
|
"epoch": 0.9586644674363972,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004916992882542276,
|
|
"loss": 5.9321,
|
|
"mean_token_accuracy": 0.16602883189916612,
|
|
"num_tokens": 18763022.0,
|
|
"step": 9590
|
|
},
|
|
{
|
|
"entropy": 6.254857873916626,
|
|
"epoch": 0.9591642924976258,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004916896810425244,
|
|
"loss": 5.8475,
|
|
"mean_token_accuracy": 0.16943801194429398,
|
|
"num_tokens": 18772827.0,
|
|
"step": 9595
|
|
},
|
|
{
|
|
"entropy": 6.236195039749146,
|
|
"epoch": 0.9596641175588544,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004916800683789645,
|
|
"loss": 5.9105,
|
|
"mean_token_accuracy": 0.16517726480960845,
|
|
"num_tokens": 18782272.0,
|
|
"step": 9600
|
|
},
|
|
{
|
|
"entropy": 6.233999252319336,
|
|
"epoch": 0.960163942620083,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004916704502637897,
|
|
"loss": 5.9388,
|
|
"mean_token_accuracy": 0.1593950718641281,
|
|
"num_tokens": 18792125.0,
|
|
"step": 9605
|
|
},
|
|
{
|
|
"entropy": 6.260229444503784,
|
|
"epoch": 0.9606637676813116,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004916608266972422,
|
|
"loss": 5.8905,
|
|
"mean_token_accuracy": 0.17143204361200332,
|
|
"num_tokens": 18801498.0,
|
|
"step": 9610
|
|
},
|
|
{
|
|
"entropy": 6.356742000579834,
|
|
"epoch": 0.9611635927425402,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004916511976795642,
|
|
"loss": 6.0105,
|
|
"mean_token_accuracy": 0.1566941499710083,
|
|
"num_tokens": 18811904.0,
|
|
"step": 9615
|
|
},
|
|
{
|
|
"entropy": 6.296348905563354,
|
|
"epoch": 0.9616634178037686,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004916415632109977,
|
|
"loss": 5.9432,
|
|
"mean_token_accuracy": 0.16673944592475892,
|
|
"num_tokens": 18821388.0,
|
|
"step": 9620
|
|
},
|
|
{
|
|
"entropy": 6.28235878944397,
|
|
"epoch": 0.9621632428649972,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004916319232917852,
|
|
"loss": 5.9831,
|
|
"mean_token_accuracy": 0.16723036766052246,
|
|
"num_tokens": 18831392.0,
|
|
"step": 9625
|
|
},
|
|
{
|
|
"entropy": 6.282760906219482,
|
|
"epoch": 0.9626630679262258,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004916222779221694,
|
|
"loss": 5.9076,
|
|
"mean_token_accuracy": 0.1641290381550789,
|
|
"num_tokens": 18841211.0,
|
|
"step": 9630
|
|
},
|
|
{
|
|
"entropy": 6.340595817565918,
|
|
"epoch": 0.9631628929874544,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004916126271023926,
|
|
"loss": 5.9325,
|
|
"mean_token_accuracy": 0.1639515057206154,
|
|
"num_tokens": 18851033.0,
|
|
"step": 9635
|
|
},
|
|
{
|
|
"entropy": 6.267115688323974,
|
|
"epoch": 0.963662718048683,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000491602970832698,
|
|
"loss": 5.9693,
|
|
"mean_token_accuracy": 0.16806348264217377,
|
|
"num_tokens": 18861439.0,
|
|
"step": 9640
|
|
},
|
|
{
|
|
"entropy": 6.274883174896241,
|
|
"epoch": 0.9641625431099116,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004915933091133284,
|
|
"loss": 5.9613,
|
|
"mean_token_accuracy": 0.15946469604969024,
|
|
"num_tokens": 18872056.0,
|
|
"step": 9645
|
|
},
|
|
{
|
|
"entropy": 6.281517410278321,
|
|
"epoch": 0.9646623681711401,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004915836419445268,
|
|
"loss": 5.876,
|
|
"mean_token_accuracy": 0.17093551605939866,
|
|
"num_tokens": 18881540.0,
|
|
"step": 9650
|
|
},
|
|
{
|
|
"entropy": 6.2274576187133786,
|
|
"epoch": 0.9651621932323686,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004915739693265365,
|
|
"loss": 5.9187,
|
|
"mean_token_accuracy": 0.16384938061237336,
|
|
"num_tokens": 18890466.0,
|
|
"step": 9655
|
|
},
|
|
{
|
|
"entropy": 6.247204780578613,
|
|
"epoch": 0.9656620182935972,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004915642912596009,
|
|
"loss": 5.9412,
|
|
"mean_token_accuracy": 0.16255345046520234,
|
|
"num_tokens": 18901397.0,
|
|
"step": 9660
|
|
},
|
|
{
|
|
"entropy": 6.287102460861206,
|
|
"epoch": 0.9661618433548258,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004915546077439634,
|
|
"loss": 5.8676,
|
|
"mean_token_accuracy": 0.1708764523267746,
|
|
"num_tokens": 18911357.0,
|
|
"step": 9665
|
|
},
|
|
{
|
|
"entropy": 6.18993821144104,
|
|
"epoch": 0.9666616684160544,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004915449187798677,
|
|
"loss": 5.8284,
|
|
"mean_token_accuracy": 0.1767471671104431,
|
|
"num_tokens": 18920901.0,
|
|
"step": 9670
|
|
},
|
|
{
|
|
"entropy": 6.281289052963257,
|
|
"epoch": 0.967161493477283,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004915352243675576,
|
|
"loss": 5.9603,
|
|
"mean_token_accuracy": 0.1584109976887703,
|
|
"num_tokens": 18931012.0,
|
|
"step": 9675
|
|
},
|
|
{
|
|
"entropy": 6.277101993560791,
|
|
"epoch": 0.9676613185385116,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000491525524507277,
|
|
"loss": 6.0301,
|
|
"mean_token_accuracy": 0.1595999240875244,
|
|
"num_tokens": 18941222.0,
|
|
"step": 9680
|
|
},
|
|
{
|
|
"entropy": 6.301226234436035,
|
|
"epoch": 0.96816114359974,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004915158191992699,
|
|
"loss": 5.9979,
|
|
"mean_token_accuracy": 0.15881145000457764,
|
|
"num_tokens": 18951073.0,
|
|
"step": 9685
|
|
},
|
|
{
|
|
"entropy": 6.282379961013794,
|
|
"epoch": 0.9686609686609686,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004915061084437805,
|
|
"loss": 5.99,
|
|
"mean_token_accuracy": 0.1619382306933403,
|
|
"num_tokens": 18960996.0,
|
|
"step": 9690
|
|
},
|
|
{
|
|
"entropy": 6.326861619949341,
|
|
"epoch": 0.9691607937221972,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004914963922410531,
|
|
"loss": 6.0105,
|
|
"mean_token_accuracy": 0.1522103041410446,
|
|
"num_tokens": 18970451.0,
|
|
"step": 9695
|
|
},
|
|
{
|
|
"entropy": 6.203526878356934,
|
|
"epoch": 0.9696606187834258,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004914866705913322,
|
|
"loss": 5.8632,
|
|
"mean_token_accuracy": 0.16479158103466035,
|
|
"num_tokens": 18979781.0,
|
|
"step": 9700
|
|
},
|
|
{
|
|
"entropy": 6.26918363571167,
|
|
"epoch": 0.9701604438446544,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004914769434948623,
|
|
"loss": 5.9425,
|
|
"mean_token_accuracy": 0.16679849922657014,
|
|
"num_tokens": 18989663.0,
|
|
"step": 9705
|
|
},
|
|
{
|
|
"entropy": 6.300129747390747,
|
|
"epoch": 0.970660268905883,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004914672109518883,
|
|
"loss": 6.0521,
|
|
"mean_token_accuracy": 0.1623453050851822,
|
|
"num_tokens": 18999613.0,
|
|
"step": 9710
|
|
},
|
|
{
|
|
"entropy": 6.212369060516357,
|
|
"epoch": 0.9711600939671116,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000491457472962655,
|
|
"loss": 5.8742,
|
|
"mean_token_accuracy": 0.17220602184534073,
|
|
"num_tokens": 19008976.0,
|
|
"step": 9715
|
|
},
|
|
{
|
|
"entropy": 6.1931720733642575,
|
|
"epoch": 0.97165991902834,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004914477295274073,
|
|
"loss": 5.8776,
|
|
"mean_token_accuracy": 0.16770453602075577,
|
|
"num_tokens": 19019013.0,
|
|
"step": 9720
|
|
},
|
|
{
|
|
"entropy": 6.331746435165405,
|
|
"epoch": 0.9721597440895686,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004914379806463905,
|
|
"loss": 6.0027,
|
|
"mean_token_accuracy": 0.1598228394985199,
|
|
"num_tokens": 19029252.0,
|
|
"step": 9725
|
|
},
|
|
{
|
|
"entropy": 6.2833315372467045,
|
|
"epoch": 0.9726595691507972,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004914282263198498,
|
|
"loss": 5.9501,
|
|
"mean_token_accuracy": 0.16362771689891814,
|
|
"num_tokens": 19038563.0,
|
|
"step": 9730
|
|
},
|
|
{
|
|
"entropy": 6.249885320663452,
|
|
"epoch": 0.9731593942120258,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004914184665480305,
|
|
"loss": 5.951,
|
|
"mean_token_accuracy": 0.16210763305425643,
|
|
"num_tokens": 19048568.0,
|
|
"step": 9735
|
|
},
|
|
{
|
|
"entropy": 6.188617372512818,
|
|
"epoch": 0.9736592192732544,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004914087013311784,
|
|
"loss": 5.7279,
|
|
"mean_token_accuracy": 0.1786773681640625,
|
|
"num_tokens": 19057527.0,
|
|
"step": 9740
|
|
},
|
|
{
|
|
"entropy": 6.257363796234131,
|
|
"epoch": 0.974159044334483,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004913989306695389,
|
|
"loss": 5.8802,
|
|
"mean_token_accuracy": 0.16424163728952407,
|
|
"num_tokens": 19067372.0,
|
|
"step": 9745
|
|
},
|
|
{
|
|
"entropy": 6.164279937744141,
|
|
"epoch": 0.9746588693957114,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004913891545633582,
|
|
"loss": 5.863,
|
|
"mean_token_accuracy": 0.17022087275981904,
|
|
"num_tokens": 19077521.0,
|
|
"step": 9750
|
|
},
|
|
{
|
|
"entropy": 6.265728235244751,
|
|
"epoch": 0.97515869445694,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000491379373012882,
|
|
"loss": 5.8782,
|
|
"mean_token_accuracy": 0.16389999091625213,
|
|
"num_tokens": 19086674.0,
|
|
"step": 9755
|
|
},
|
|
{
|
|
"entropy": 6.313772773742675,
|
|
"epoch": 0.9756585195181686,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004913695860183563,
|
|
"loss": 6.0706,
|
|
"mean_token_accuracy": 0.1534619763493538,
|
|
"num_tokens": 19097586.0,
|
|
"step": 9760
|
|
},
|
|
{
|
|
"entropy": 6.288459205627442,
|
|
"epoch": 0.9761583445793972,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004913597935800276,
|
|
"loss": 6.0499,
|
|
"mean_token_accuracy": 0.1514739900827408,
|
|
"num_tokens": 19107763.0,
|
|
"step": 9765
|
|
},
|
|
{
|
|
"entropy": 6.281144618988037,
|
|
"epoch": 0.9766581696406258,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004913499956981422,
|
|
"loss": 5.8602,
|
|
"mean_token_accuracy": 0.1738614022731781,
|
|
"num_tokens": 19117931.0,
|
|
"step": 9770
|
|
},
|
|
{
|
|
"entropy": 6.265654373168945,
|
|
"epoch": 0.9771579947018544,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004913401923729465,
|
|
"loss": 5.9219,
|
|
"mean_token_accuracy": 0.16671146601438522,
|
|
"num_tokens": 19127707.0,
|
|
"step": 9775
|
|
},
|
|
{
|
|
"entropy": 6.204120731353759,
|
|
"epoch": 0.977657819763083,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004913303836046873,
|
|
"loss": 5.829,
|
|
"mean_token_accuracy": 0.16896477788686753,
|
|
"num_tokens": 19137633.0,
|
|
"step": 9780
|
|
},
|
|
{
|
|
"entropy": 6.303733253479004,
|
|
"epoch": 0.9781576448243114,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004913205693936112,
|
|
"loss": 5.9642,
|
|
"mean_token_accuracy": 0.1659124508500099,
|
|
"num_tokens": 19146247.0,
|
|
"step": 9785
|
|
},
|
|
{
|
|
"entropy": 6.158577919006348,
|
|
"epoch": 0.97865746988554,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004913107497399653,
|
|
"loss": 5.8805,
|
|
"mean_token_accuracy": 0.18305480033159255,
|
|
"num_tokens": 19156225.0,
|
|
"step": 9790
|
|
},
|
|
{
|
|
"entropy": 6.2418351650238035,
|
|
"epoch": 0.9791572949467686,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004913009246439966,
|
|
"loss": 5.8318,
|
|
"mean_token_accuracy": 0.17008442282676697,
|
|
"num_tokens": 19165763.0,
|
|
"step": 9795
|
|
},
|
|
{
|
|
"entropy": 6.261901044845581,
|
|
"epoch": 0.9796571200079972,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004912910941059525,
|
|
"loss": 5.8789,
|
|
"mean_token_accuracy": 0.16494118869304658,
|
|
"num_tokens": 19174116.0,
|
|
"step": 9800
|
|
},
|
|
{
|
|
"entropy": 6.315587854385376,
|
|
"epoch": 0.9801569450692258,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004912812581260799,
|
|
"loss": 6.0335,
|
|
"mean_token_accuracy": 0.15138949304819108,
|
|
"num_tokens": 19184416.0,
|
|
"step": 9805
|
|
},
|
|
{
|
|
"entropy": 6.291780757904053,
|
|
"epoch": 0.9806567701304544,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004912714167046265,
|
|
"loss": 6.002,
|
|
"mean_token_accuracy": 0.1574980691075325,
|
|
"num_tokens": 19193356.0,
|
|
"step": 9810
|
|
},
|
|
{
|
|
"entropy": 6.209781694412231,
|
|
"epoch": 0.9811565951916829,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004912615698418399,
|
|
"loss": 5.7983,
|
|
"mean_token_accuracy": 0.1800832062959671,
|
|
"num_tokens": 19204257.0,
|
|
"step": 9815
|
|
},
|
|
{
|
|
"entropy": 6.31696834564209,
|
|
"epoch": 0.9816564202529114,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004912517175379679,
|
|
"loss": 5.9311,
|
|
"mean_token_accuracy": 0.16595056354999543,
|
|
"num_tokens": 19213889.0,
|
|
"step": 9820
|
|
},
|
|
{
|
|
"entropy": 6.314828634262085,
|
|
"epoch": 0.98215624531414,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004912418597932584,
|
|
"loss": 6.0061,
|
|
"mean_token_accuracy": 0.15444094985723494,
|
|
"num_tokens": 19224008.0,
|
|
"step": 9825
|
|
},
|
|
{
|
|
"entropy": 6.319388151168823,
|
|
"epoch": 0.9826560703753686,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004912319966079592,
|
|
"loss": 5.9884,
|
|
"mean_token_accuracy": 0.16098888516426085,
|
|
"num_tokens": 19234247.0,
|
|
"step": 9830
|
|
},
|
|
{
|
|
"entropy": 6.37338433265686,
|
|
"epoch": 0.9831558954365972,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004912221279823187,
|
|
"loss": 5.9841,
|
|
"mean_token_accuracy": 0.15851364135742188,
|
|
"num_tokens": 19244838.0,
|
|
"step": 9835
|
|
},
|
|
{
|
|
"entropy": 6.271524047851562,
|
|
"epoch": 0.9836557204978258,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004912122539165851,
|
|
"loss": 5.9136,
|
|
"mean_token_accuracy": 0.16579616963863372,
|
|
"num_tokens": 19254989.0,
|
|
"step": 9840
|
|
},
|
|
{
|
|
"entropy": 6.237234210968017,
|
|
"epoch": 0.9841555455590544,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004912023744110068,
|
|
"loss": 5.9766,
|
|
"mean_token_accuracy": 0.16171518415212632,
|
|
"num_tokens": 19264519.0,
|
|
"step": 9845
|
|
},
|
|
{
|
|
"entropy": 6.264782667160034,
|
|
"epoch": 0.9846553706202829,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004911924894658324,
|
|
"loss": 5.9307,
|
|
"mean_token_accuracy": 0.16795245707035064,
|
|
"num_tokens": 19274153.0,
|
|
"step": 9850
|
|
},
|
|
{
|
|
"entropy": 6.212197351455688,
|
|
"epoch": 0.9851551956815114,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004911825990813107,
|
|
"loss": 5.8719,
|
|
"mean_token_accuracy": 0.1660114660859108,
|
|
"num_tokens": 19283383.0,
|
|
"step": 9855
|
|
},
|
|
{
|
|
"entropy": 6.211267948150635,
|
|
"epoch": 0.98565502074274,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004911727032576903,
|
|
"loss": 5.8657,
|
|
"mean_token_accuracy": 0.1675114303827286,
|
|
"num_tokens": 19292758.0,
|
|
"step": 9860
|
|
},
|
|
{
|
|
"entropy": 6.279982948303223,
|
|
"epoch": 0.9861548458039686,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004911628019952203,
|
|
"loss": 5.9603,
|
|
"mean_token_accuracy": 0.15791314616799354,
|
|
"num_tokens": 19302339.0,
|
|
"step": 9865
|
|
},
|
|
{
|
|
"entropy": 6.243218803405762,
|
|
"epoch": 0.9866546708651972,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004911528952941499,
|
|
"loss": 5.7645,
|
|
"mean_token_accuracy": 0.17031705528497695,
|
|
"num_tokens": 19312560.0,
|
|
"step": 9870
|
|
},
|
|
{
|
|
"entropy": 6.26758189201355,
|
|
"epoch": 0.9871544959264258,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004911429831547283,
|
|
"loss": 5.8536,
|
|
"mean_token_accuracy": 0.16890265196561813,
|
|
"num_tokens": 19322796.0,
|
|
"step": 9875
|
|
},
|
|
{
|
|
"entropy": 6.261846256256104,
|
|
"epoch": 0.9876543209876543,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004911330655772047,
|
|
"loss": 5.9732,
|
|
"mean_token_accuracy": 0.16209546178579332,
|
|
"num_tokens": 19332719.0,
|
|
"step": 9880
|
|
},
|
|
{
|
|
"entropy": 6.242090225219727,
|
|
"epoch": 0.9881541460488829,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000491123142561829,
|
|
"loss": 5.9376,
|
|
"mean_token_accuracy": 0.16399399042129517,
|
|
"num_tokens": 19342226.0,
|
|
"step": 9885
|
|
},
|
|
{
|
|
"entropy": 6.235197591781616,
|
|
"epoch": 0.9886539711101114,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004911132141088505,
|
|
"loss": 5.9425,
|
|
"mean_token_accuracy": 0.1587014377117157,
|
|
"num_tokens": 19351933.0,
|
|
"step": 9890
|
|
},
|
|
{
|
|
"entropy": 6.31852707862854,
|
|
"epoch": 0.98915379617134,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004911032802185192,
|
|
"loss": 5.8263,
|
|
"mean_token_accuracy": 0.16211523711681367,
|
|
"num_tokens": 19359900.0,
|
|
"step": 9895
|
|
},
|
|
{
|
|
"entropy": 6.2926102638244625,
|
|
"epoch": 0.9896536212325686,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000491093340891085,
|
|
"loss": 5.9303,
|
|
"mean_token_accuracy": 0.16268015801906585,
|
|
"num_tokens": 19369139.0,
|
|
"step": 9900
|
|
},
|
|
{
|
|
"entropy": 6.190810060501098,
|
|
"epoch": 0.9901534462937972,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004910833961267979,
|
|
"loss": 5.8611,
|
|
"mean_token_accuracy": 0.1693447545170784,
|
|
"num_tokens": 19378765.0,
|
|
"step": 9905
|
|
},
|
|
{
|
|
"entropy": 6.254684543609619,
|
|
"epoch": 0.9906532713550258,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004910734459259081,
|
|
"loss": 5.9357,
|
|
"mean_token_accuracy": 0.16080590784549714,
|
|
"num_tokens": 19389001.0,
|
|
"step": 9910
|
|
},
|
|
{
|
|
"entropy": 6.2591047286987305,
|
|
"epoch": 0.9911530964162543,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004910634902886662,
|
|
"loss": 5.8975,
|
|
"mean_token_accuracy": 0.16947824656963348,
|
|
"num_tokens": 19397990.0,
|
|
"step": 9915
|
|
},
|
|
{
|
|
"entropy": 6.1499528884887695,
|
|
"epoch": 0.9916529214774829,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004910535292153224,
|
|
"loss": 5.8413,
|
|
"mean_token_accuracy": 0.17278724610805513,
|
|
"num_tokens": 19408060.0,
|
|
"step": 9920
|
|
},
|
|
{
|
|
"entropy": 6.194256448745728,
|
|
"epoch": 0.9921527465387114,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004910435627061273,
|
|
"loss": 5.8483,
|
|
"mean_token_accuracy": 0.16953420490026475,
|
|
"num_tokens": 19417675.0,
|
|
"step": 9925
|
|
},
|
|
{
|
|
"entropy": 6.276304006576538,
|
|
"epoch": 0.99265257159994,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004910335907613318,
|
|
"loss": 5.8799,
|
|
"mean_token_accuracy": 0.164105623960495,
|
|
"num_tokens": 19426433.0,
|
|
"step": 9930
|
|
},
|
|
{
|
|
"entropy": 6.263840770721435,
|
|
"epoch": 0.9931523966611686,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004910236133811867,
|
|
"loss": 5.7834,
|
|
"mean_token_accuracy": 0.1739935979247093,
|
|
"num_tokens": 19435459.0,
|
|
"step": 9935
|
|
},
|
|
{
|
|
"entropy": 6.229986763000488,
|
|
"epoch": 0.9936522217223972,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004910136305659432,
|
|
"loss": 5.9192,
|
|
"mean_token_accuracy": 0.16355590671300888,
|
|
"num_tokens": 19445329.0,
|
|
"step": 9940
|
|
},
|
|
{
|
|
"entropy": 6.2493597030639645,
|
|
"epoch": 0.9941520467836257,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004910036423158523,
|
|
"loss": 5.8626,
|
|
"mean_token_accuracy": 0.16961516737937926,
|
|
"num_tokens": 19454417.0,
|
|
"step": 9945
|
|
},
|
|
{
|
|
"entropy": 6.266791486740113,
|
|
"epoch": 0.9946518718448543,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004909936486311653,
|
|
"loss": 5.9547,
|
|
"mean_token_accuracy": 0.15964613407850264,
|
|
"num_tokens": 19464274.0,
|
|
"step": 9950
|
|
},
|
|
{
|
|
"entropy": 6.277455520629883,
|
|
"epoch": 0.9951516969060828,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004909836495121336,
|
|
"loss": 5.9381,
|
|
"mean_token_accuracy": 0.16598208695650102,
|
|
"num_tokens": 19472455.0,
|
|
"step": 9955
|
|
},
|
|
{
|
|
"entropy": 6.283089637756348,
|
|
"epoch": 0.9956515219673114,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004909736449590091,
|
|
"loss": 6.0221,
|
|
"mean_token_accuracy": 0.15398839861154556,
|
|
"num_tokens": 19483320.0,
|
|
"step": 9960
|
|
},
|
|
{
|
|
"entropy": 6.276672267913819,
|
|
"epoch": 0.99615134702854,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000490963634972043,
|
|
"loss": 5.905,
|
|
"mean_token_accuracy": 0.1601263925433159,
|
|
"num_tokens": 19493644.0,
|
|
"step": 9965
|
|
},
|
|
{
|
|
"entropy": 6.238875770568848,
|
|
"epoch": 0.9966511720897686,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004909536195514875,
|
|
"loss": 5.8159,
|
|
"mean_token_accuracy": 0.17235923558473587,
|
|
"num_tokens": 19503035.0,
|
|
"step": 9970
|
|
},
|
|
{
|
|
"entropy": 6.245280456542969,
|
|
"epoch": 0.9971509971509972,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004909435986975946,
|
|
"loss": 5.943,
|
|
"mean_token_accuracy": 0.1685030549764633,
|
|
"num_tokens": 19512254.0,
|
|
"step": 9975
|
|
},
|
|
{
|
|
"entropy": 6.23340482711792,
|
|
"epoch": 0.9976508222122257,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004909335724106162,
|
|
"loss": 5.8602,
|
|
"mean_token_accuracy": 0.17098692804574966,
|
|
"num_tokens": 19523114.0,
|
|
"step": 9980
|
|
},
|
|
{
|
|
"entropy": 6.267901849746704,
|
|
"epoch": 0.9981506472734543,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004909235406908047,
|
|
"loss": 5.9306,
|
|
"mean_token_accuracy": 0.16138241291046143,
|
|
"num_tokens": 19532940.0,
|
|
"step": 9985
|
|
},
|
|
{
|
|
"entropy": 6.195018243789673,
|
|
"epoch": 0.9986504723346828,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004909135035384126,
|
|
"loss": 5.9021,
|
|
"mean_token_accuracy": 0.16862636804580688,
|
|
"num_tokens": 19542807.0,
|
|
"step": 9990
|
|
},
|
|
{
|
|
"entropy": 6.160175800323486,
|
|
"epoch": 0.9991502973959114,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004909034609536922,
|
|
"loss": 5.7907,
|
|
"mean_token_accuracy": 0.17045772969722747,
|
|
"num_tokens": 19552099.0,
|
|
"step": 9995
|
|
},
|
|
{
|
|
"entropy": 6.25959997177124,
|
|
"epoch": 0.99965012245714,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004908934129368963,
|
|
"loss": 5.8477,
|
|
"mean_token_accuracy": 0.17389266937971115,
|
|
"num_tokens": 19561709.0,
|
|
"step": 10000
|
|
},
|
|
{
|
|
"entropy": 6.283848550584581,
|
|
"epoch": 1.0000999650122457,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004908833594882777,
|
|
"loss": 5.9858,
|
|
"mean_token_accuracy": 0.16578309072388542,
|
|
"num_tokens": 19571739.0,
|
|
"step": 10005
|
|
},
|
|
{
|
|
"entropy": 6.314963531494141,
|
|
"epoch": 1.0005997900734742,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004908733006080893,
|
|
"loss": 5.8438,
|
|
"mean_token_accuracy": 0.17023817747831343,
|
|
"num_tokens": 19582084.0,
|
|
"step": 10010
|
|
},
|
|
{
|
|
"entropy": 6.172355461120605,
|
|
"epoch": 1.001099615134703,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004908632362965842,
|
|
"loss": 5.8033,
|
|
"mean_token_accuracy": 0.16811883747577666,
|
|
"num_tokens": 19591889.0,
|
|
"step": 10015
|
|
},
|
|
{
|
|
"entropy": 6.28244800567627,
|
|
"epoch": 1.0015994401959314,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004908531665540158,
|
|
"loss": 5.8976,
|
|
"mean_token_accuracy": 0.16543484777212142,
|
|
"num_tokens": 19601998.0,
|
|
"step": 10020
|
|
},
|
|
{
|
|
"entropy": 6.237816286087036,
|
|
"epoch": 1.00209926525716,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000490843091380637,
|
|
"loss": 5.7073,
|
|
"mean_token_accuracy": 0.1813892498612404,
|
|
"num_tokens": 19611347.0,
|
|
"step": 10025
|
|
},
|
|
{
|
|
"entropy": 6.305270481109619,
|
|
"epoch": 1.0025990903183886,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004908330107767018,
|
|
"loss": 5.8413,
|
|
"mean_token_accuracy": 0.1740329831838608,
|
|
"num_tokens": 19621522.0,
|
|
"step": 10030
|
|
},
|
|
{
|
|
"entropy": 6.204833602905273,
|
|
"epoch": 1.003098915379617,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004908229247424633,
|
|
"loss": 5.726,
|
|
"mean_token_accuracy": 0.17629946917295455,
|
|
"num_tokens": 19630815.0,
|
|
"step": 10035
|
|
},
|
|
{
|
|
"entropy": 6.245790576934814,
|
|
"epoch": 1.0035987404408457,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004908128332781758,
|
|
"loss": 5.8344,
|
|
"mean_token_accuracy": 0.17581446766853331,
|
|
"num_tokens": 19640811.0,
|
|
"step": 10040
|
|
},
|
|
{
|
|
"entropy": 6.214106130599975,
|
|
"epoch": 1.0040985655020742,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004908027363840928,
|
|
"loss": 5.8075,
|
|
"mean_token_accuracy": 0.17231352031230926,
|
|
"num_tokens": 19651335.0,
|
|
"step": 10045
|
|
},
|
|
{
|
|
"entropy": 6.23767352104187,
|
|
"epoch": 1.004598390563303,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004907926340604686,
|
|
"loss": 5.7669,
|
|
"mean_token_accuracy": 0.17468004375696183,
|
|
"num_tokens": 19660242.0,
|
|
"step": 10050
|
|
},
|
|
{
|
|
"entropy": 6.271671199798584,
|
|
"epoch": 1.0050982156245314,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004907825263075573,
|
|
"loss": 5.8294,
|
|
"mean_token_accuracy": 0.1668669417500496,
|
|
"num_tokens": 19670013.0,
|
|
"step": 10055
|
|
},
|
|
{
|
|
"entropy": 6.230937719345093,
|
|
"epoch": 1.00559804068576,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004907724131256129,
|
|
"loss": 5.7517,
|
|
"mean_token_accuracy": 0.17699647396802903,
|
|
"num_tokens": 19679479.0,
|
|
"step": 10060
|
|
},
|
|
{
|
|
"entropy": 6.1960677146911625,
|
|
"epoch": 1.0060978657469886,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004907622945148903,
|
|
"loss": 5.788,
|
|
"mean_token_accuracy": 0.17006356567144393,
|
|
"num_tokens": 19688603.0,
|
|
"step": 10065
|
|
},
|
|
{
|
|
"entropy": 6.197310447692871,
|
|
"epoch": 1.006597690808217,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004907521704756438,
|
|
"loss": 5.7742,
|
|
"mean_token_accuracy": 0.16711292862892152,
|
|
"num_tokens": 19698375.0,
|
|
"step": 10070
|
|
},
|
|
{
|
|
"entropy": 6.290510368347168,
|
|
"epoch": 1.0070975158694457,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004907420410081284,
|
|
"loss": 5.8204,
|
|
"mean_token_accuracy": 0.16991811394691467,
|
|
"num_tokens": 19708911.0,
|
|
"step": 10075
|
|
},
|
|
{
|
|
"entropy": 6.226446199417114,
|
|
"epoch": 1.0075973409306742,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004907319061125986,
|
|
"loss": 5.7895,
|
|
"mean_token_accuracy": 0.16729426085948945,
|
|
"num_tokens": 19717733.0,
|
|
"step": 10080
|
|
},
|
|
{
|
|
"entropy": 6.173346042633057,
|
|
"epoch": 1.008097165991903,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004907217657893096,
|
|
"loss": 5.8159,
|
|
"mean_token_accuracy": 0.17135279774665832,
|
|
"num_tokens": 19727192.0,
|
|
"step": 10085
|
|
},
|
|
{
|
|
"entropy": 6.201342535018921,
|
|
"epoch": 1.0085969910531314,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004907116200385165,
|
|
"loss": 5.7585,
|
|
"mean_token_accuracy": 0.1736773058772087,
|
|
"num_tokens": 19737937.0,
|
|
"step": 10090
|
|
},
|
|
{
|
|
"entropy": 6.229734134674072,
|
|
"epoch": 1.00909681611436,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004907014688604745,
|
|
"loss": 5.7633,
|
|
"mean_token_accuracy": 0.16932329833507537,
|
|
"num_tokens": 19748270.0,
|
|
"step": 10095
|
|
},
|
|
{
|
|
"entropy": 6.128997755050659,
|
|
"epoch": 1.0095966411755886,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004906913122554391,
|
|
"loss": 5.6379,
|
|
"mean_token_accuracy": 0.18163401931524276,
|
|
"num_tokens": 19758328.0,
|
|
"step": 10100
|
|
},
|
|
{
|
|
"entropy": 6.171188879013061,
|
|
"epoch": 1.010096466236817,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004906811502236657,
|
|
"loss": 5.722,
|
|
"mean_token_accuracy": 0.1772330105304718,
|
|
"num_tokens": 19767780.0,
|
|
"step": 10105
|
|
},
|
|
{
|
|
"entropy": 6.27977180480957,
|
|
"epoch": 1.0105962912980457,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004906709827654101,
|
|
"loss": 5.9025,
|
|
"mean_token_accuracy": 0.16755327582359314,
|
|
"num_tokens": 19777202.0,
|
|
"step": 10110
|
|
},
|
|
{
|
|
"entropy": 6.202955818176269,
|
|
"epoch": 1.0110961163592742,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004906608098809281,
|
|
"loss": 5.7683,
|
|
"mean_token_accuracy": 0.173154316842556,
|
|
"num_tokens": 19788341.0,
|
|
"step": 10115
|
|
},
|
|
{
|
|
"entropy": 6.289692306518555,
|
|
"epoch": 1.011595941420503,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004906506315704756,
|
|
"loss": 5.8869,
|
|
"mean_token_accuracy": 0.16591483503580093,
|
|
"num_tokens": 19797511.0,
|
|
"step": 10120
|
|
},
|
|
{
|
|
"entropy": 6.288926649093628,
|
|
"epoch": 1.0120957664817314,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004906404478343087,
|
|
"loss": 5.8305,
|
|
"mean_token_accuracy": 0.17129166126251222,
|
|
"num_tokens": 19807639.0,
|
|
"step": 10125
|
|
},
|
|
{
|
|
"entropy": 6.363392543792725,
|
|
"epoch": 1.0125955915429599,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004906302586726837,
|
|
"loss": 5.9417,
|
|
"mean_token_accuracy": 0.1635058641433716,
|
|
"num_tokens": 19818379.0,
|
|
"step": 10130
|
|
},
|
|
{
|
|
"entropy": 6.200148200988769,
|
|
"epoch": 1.0130954166041886,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004906200640858567,
|
|
"loss": 5.7634,
|
|
"mean_token_accuracy": 0.1789684697985649,
|
|
"num_tokens": 19828706.0,
|
|
"step": 10135
|
|
},
|
|
{
|
|
"entropy": 6.230577659606934,
|
|
"epoch": 1.013595241665417,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004906098640740846,
|
|
"loss": 5.816,
|
|
"mean_token_accuracy": 0.1816043347120285,
|
|
"num_tokens": 19838361.0,
|
|
"step": 10140
|
|
},
|
|
{
|
|
"entropy": 6.250348329544067,
|
|
"epoch": 1.0140950667266457,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004905996586376236,
|
|
"loss": 5.8555,
|
|
"mean_token_accuracy": 0.16723937392234803,
|
|
"num_tokens": 19848205.0,
|
|
"step": 10145
|
|
},
|
|
{
|
|
"entropy": 6.23565788269043,
|
|
"epoch": 1.0145948917878742,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004905894477767308,
|
|
"loss": 5.8688,
|
|
"mean_token_accuracy": 0.16988968551158906,
|
|
"num_tokens": 19858490.0,
|
|
"step": 10150
|
|
},
|
|
{
|
|
"entropy": 6.242792415618896,
|
|
"epoch": 1.015094716849103,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004905792314916629,
|
|
"loss": 5.8633,
|
|
"mean_token_accuracy": 0.16839646846055983,
|
|
"num_tokens": 19867551.0,
|
|
"step": 10155
|
|
},
|
|
{
|
|
"entropy": 6.2692241191864015,
|
|
"epoch": 1.0155945419103314,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004905690097826769,
|
|
"loss": 5.8702,
|
|
"mean_token_accuracy": 0.16994632333517073,
|
|
"num_tokens": 19877581.0,
|
|
"step": 10160
|
|
},
|
|
{
|
|
"entropy": 6.346371746063232,
|
|
"epoch": 1.0160943669715599,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004905587826500303,
|
|
"loss": 5.8943,
|
|
"mean_token_accuracy": 0.16771265268325805,
|
|
"num_tokens": 19887827.0,
|
|
"step": 10165
|
|
},
|
|
{
|
|
"entropy": 6.26185712814331,
|
|
"epoch": 1.0165941920327886,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004905485500939801,
|
|
"loss": 5.8157,
|
|
"mean_token_accuracy": 0.1695003479719162,
|
|
"num_tokens": 19897395.0,
|
|
"step": 10170
|
|
},
|
|
{
|
|
"entropy": 6.235832166671753,
|
|
"epoch": 1.017094017094017,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004905383121147838,
|
|
"loss": 5.8245,
|
|
"mean_token_accuracy": 0.16520053148269653,
|
|
"num_tokens": 19906601.0,
|
|
"step": 10175
|
|
},
|
|
{
|
|
"entropy": 6.260590505599976,
|
|
"epoch": 1.0175938421552457,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004905280687126991,
|
|
"loss": 5.7758,
|
|
"mean_token_accuracy": 0.1736768051981926,
|
|
"num_tokens": 19916422.0,
|
|
"step": 10180
|
|
},
|
|
{
|
|
"entropy": 6.291734743118286,
|
|
"epoch": 1.0180936672164742,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004905178198879837,
|
|
"loss": 5.8861,
|
|
"mean_token_accuracy": 0.16468494832515718,
|
|
"num_tokens": 19927182.0,
|
|
"step": 10185
|
|
},
|
|
{
|
|
"entropy": 6.254245805740356,
|
|
"epoch": 1.018593492277703,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004905075656408953,
|
|
"loss": 5.8857,
|
|
"mean_token_accuracy": 0.1595054402947426,
|
|
"num_tokens": 19936537.0,
|
|
"step": 10190
|
|
},
|
|
{
|
|
"entropy": 6.269895935058594,
|
|
"epoch": 1.0190933173389314,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000490497305971692,
|
|
"loss": 5.8223,
|
|
"mean_token_accuracy": 0.1778612971305847,
|
|
"num_tokens": 19946315.0,
|
|
"step": 10195
|
|
},
|
|
{
|
|
"entropy": 6.242901802062988,
|
|
"epoch": 1.0195931424001599,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000490487040880632,
|
|
"loss": 5.7457,
|
|
"mean_token_accuracy": 0.17350117564201356,
|
|
"num_tokens": 19956145.0,
|
|
"step": 10200
|
|
},
|
|
{
|
|
"entropy": 6.257519721984863,
|
|
"epoch": 1.0200929674613886,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004904767703679735,
|
|
"loss": 5.89,
|
|
"mean_token_accuracy": 0.165392504632473,
|
|
"num_tokens": 19966890.0,
|
|
"step": 10205
|
|
},
|
|
{
|
|
"entropy": 6.270732831954956,
|
|
"epoch": 1.020592792522617,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004904664944339748,
|
|
"loss": 5.8465,
|
|
"mean_token_accuracy": 0.16625440940260888,
|
|
"num_tokens": 19976156.0,
|
|
"step": 10210
|
|
},
|
|
{
|
|
"entropy": 6.229459238052368,
|
|
"epoch": 1.0210926175838457,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004904562130788947,
|
|
"loss": 5.7655,
|
|
"mean_token_accuracy": 0.17295474261045457,
|
|
"num_tokens": 19985851.0,
|
|
"step": 10215
|
|
},
|
|
{
|
|
"entropy": 6.188613176345825,
|
|
"epoch": 1.0215924426450742,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004904459263029916,
|
|
"loss": 5.8664,
|
|
"mean_token_accuracy": 0.1737103134393692,
|
|
"num_tokens": 19996531.0,
|
|
"step": 10220
|
|
},
|
|
{
|
|
"entropy": 6.270019245147705,
|
|
"epoch": 1.0220922677063027,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004904356341065245,
|
|
"loss": 5.7014,
|
|
"mean_token_accuracy": 0.1808296635746956,
|
|
"num_tokens": 20006050.0,
|
|
"step": 10225
|
|
},
|
|
{
|
|
"entropy": 6.303644371032715,
|
|
"epoch": 1.0225920927675314,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004904253364897521,
|
|
"loss": 5.8723,
|
|
"mean_token_accuracy": 0.1627875968813896,
|
|
"num_tokens": 20015997.0,
|
|
"step": 10230
|
|
},
|
|
{
|
|
"entropy": 6.30539345741272,
|
|
"epoch": 1.0230919178287599,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004904150334529339,
|
|
"loss": 5.9814,
|
|
"mean_token_accuracy": 0.16317925751209258,
|
|
"num_tokens": 20026682.0,
|
|
"step": 10235
|
|
},
|
|
{
|
|
"entropy": 6.285685110092163,
|
|
"epoch": 1.0235917428899886,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004904047249963289,
|
|
"loss": 5.8235,
|
|
"mean_token_accuracy": 0.1693215101957321,
|
|
"num_tokens": 20036166.0,
|
|
"step": 10240
|
|
},
|
|
{
|
|
"entropy": 6.2272144794464115,
|
|
"epoch": 1.024091567951217,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004903944111201964,
|
|
"loss": 5.7334,
|
|
"mean_token_accuracy": 0.18609341531991958,
|
|
"num_tokens": 20045545.0,
|
|
"step": 10245
|
|
},
|
|
{
|
|
"entropy": 6.251843643188477,
|
|
"epoch": 1.0245913930124457,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004903840918247958,
|
|
"loss": 5.7656,
|
|
"mean_token_accuracy": 0.1710270881652832,
|
|
"num_tokens": 20055072.0,
|
|
"step": 10250
|
|
},
|
|
{
|
|
"entropy": 6.2845922946929935,
|
|
"epoch": 1.0250912180736742,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000490373767110387,
|
|
"loss": 5.925,
|
|
"mean_token_accuracy": 0.16040323227643966,
|
|
"num_tokens": 20064227.0,
|
|
"step": 10255
|
|
},
|
|
{
|
|
"entropy": 6.267233085632324,
|
|
"epoch": 1.0255910431349027,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004903634369772296,
|
|
"loss": 5.8281,
|
|
"mean_token_accuracy": 0.16613586544990538,
|
|
"num_tokens": 20074833.0,
|
|
"step": 10260
|
|
},
|
|
{
|
|
"entropy": 6.261243438720703,
|
|
"epoch": 1.0260908681961314,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004903531014255835,
|
|
"loss": 5.81,
|
|
"mean_token_accuracy": 0.1663002386689186,
|
|
"num_tokens": 20084340.0,
|
|
"step": 10265
|
|
},
|
|
{
|
|
"entropy": 6.279541730880737,
|
|
"epoch": 1.0265906932573599,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004903427604557089,
|
|
"loss": 5.7796,
|
|
"mean_token_accuracy": 0.17315594106912613,
|
|
"num_tokens": 20094372.0,
|
|
"step": 10270
|
|
},
|
|
{
|
|
"entropy": 6.272610378265381,
|
|
"epoch": 1.0270905183185886,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004903324140678658,
|
|
"loss": 5.7565,
|
|
"mean_token_accuracy": 0.17285460829734803,
|
|
"num_tokens": 20104015.0,
|
|
"step": 10275
|
|
},
|
|
{
|
|
"entropy": 6.232513761520385,
|
|
"epoch": 1.027590343379817,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004903220622623146,
|
|
"loss": 5.8158,
|
|
"mean_token_accuracy": 0.16975024044513704,
|
|
"num_tokens": 20113570.0,
|
|
"step": 10280
|
|
},
|
|
{
|
|
"entropy": 6.279240274429322,
|
|
"epoch": 1.0280901684410457,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004903117050393157,
|
|
"loss": 5.8624,
|
|
"mean_token_accuracy": 0.1641963705420494,
|
|
"num_tokens": 20124147.0,
|
|
"step": 10285
|
|
},
|
|
{
|
|
"entropy": 6.240455102920532,
|
|
"epoch": 1.0285899935022742,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004903013423991296,
|
|
"loss": 5.8389,
|
|
"mean_token_accuracy": 0.16515177488327026,
|
|
"num_tokens": 20134310.0,
|
|
"step": 10290
|
|
},
|
|
{
|
|
"entropy": 6.2240275859832765,
|
|
"epoch": 1.0290898185635027,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004902909743420173,
|
|
"loss": 5.8086,
|
|
"mean_token_accuracy": 0.16902623623609542,
|
|
"num_tokens": 20143894.0,
|
|
"step": 10295
|
|
},
|
|
{
|
|
"entropy": 6.28502140045166,
|
|
"epoch": 1.0295896436247314,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004902806008682394,
|
|
"loss": 5.8534,
|
|
"mean_token_accuracy": 0.17261807769536971,
|
|
"num_tokens": 20154862.0,
|
|
"step": 10300
|
|
},
|
|
{
|
|
"entropy": 6.2506646633148195,
|
|
"epoch": 1.0300894686859599,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000490270221978057,
|
|
"loss": 5.7616,
|
|
"mean_token_accuracy": 0.175024177134037,
|
|
"num_tokens": 20164109.0,
|
|
"step": 10305
|
|
},
|
|
{
|
|
"entropy": 6.280239725112915,
|
|
"epoch": 1.0305892937471886,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004902598376717312,
|
|
"loss": 5.8173,
|
|
"mean_token_accuracy": 0.16779507249593734,
|
|
"num_tokens": 20173971.0,
|
|
"step": 10310
|
|
},
|
|
{
|
|
"entropy": 6.218884658813477,
|
|
"epoch": 1.031089118808417,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004902494479495233,
|
|
"loss": 5.8647,
|
|
"mean_token_accuracy": 0.1635557606816292,
|
|
"num_tokens": 20183683.0,
|
|
"step": 10315
|
|
},
|
|
{
|
|
"entropy": 6.244477272033691,
|
|
"epoch": 1.0315889438696457,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004902390528116946,
|
|
"loss": 5.782,
|
|
"mean_token_accuracy": 0.1706061691045761,
|
|
"num_tokens": 20192945.0,
|
|
"step": 10320
|
|
},
|
|
{
|
|
"entropy": 6.263478994369507,
|
|
"epoch": 1.0320887689308742,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004902286522585068,
|
|
"loss": 5.8258,
|
|
"mean_token_accuracy": 0.1707526698708534,
|
|
"num_tokens": 20202919.0,
|
|
"step": 10325
|
|
},
|
|
{
|
|
"entropy": 6.225732803344727,
|
|
"epoch": 1.0325885939921027,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004902182462902215,
|
|
"loss": 5.7449,
|
|
"mean_token_accuracy": 0.18247107416391373,
|
|
"num_tokens": 20212377.0,
|
|
"step": 10330
|
|
},
|
|
{
|
|
"entropy": 6.218394660949707,
|
|
"epoch": 1.0330884190533314,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004902078349071004,
|
|
"loss": 5.7522,
|
|
"mean_token_accuracy": 0.17558959126472473,
|
|
"num_tokens": 20221083.0,
|
|
"step": 10335
|
|
},
|
|
{
|
|
"entropy": 6.247791528701782,
|
|
"epoch": 1.0335882441145599,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004901974181094057,
|
|
"loss": 5.8823,
|
|
"mean_token_accuracy": 0.16718894690275193,
|
|
"num_tokens": 20229577.0,
|
|
"step": 10340
|
|
},
|
|
{
|
|
"entropy": 6.24241075515747,
|
|
"epoch": 1.0340880691757885,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004901869958973991,
|
|
"loss": 5.7338,
|
|
"mean_token_accuracy": 0.17685514837503433,
|
|
"num_tokens": 20238400.0,
|
|
"step": 10345
|
|
},
|
|
{
|
|
"entropy": 6.202972412109375,
|
|
"epoch": 1.034587894237017,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004901765682713432,
|
|
"loss": 5.8744,
|
|
"mean_token_accuracy": 0.16416851580142974,
|
|
"num_tokens": 20248479.0,
|
|
"step": 10350
|
|
},
|
|
{
|
|
"entropy": 6.223765325546265,
|
|
"epoch": 1.0350877192982457,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004901661352315003,
|
|
"loss": 5.8285,
|
|
"mean_token_accuracy": 0.17203006744384766,
|
|
"num_tokens": 20258268.0,
|
|
"step": 10355
|
|
},
|
|
{
|
|
"entropy": 6.251565599441529,
|
|
"epoch": 1.0355875443594742,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004901556967781327,
|
|
"loss": 5.7857,
|
|
"mean_token_accuracy": 0.17590277940034865,
|
|
"num_tokens": 20267924.0,
|
|
"step": 10360
|
|
},
|
|
{
|
|
"entropy": 6.283817863464355,
|
|
"epoch": 1.0360873694207027,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004901452529115031,
|
|
"loss": 5.8656,
|
|
"mean_token_accuracy": 0.16627820432186127,
|
|
"num_tokens": 20278173.0,
|
|
"step": 10365
|
|
},
|
|
{
|
|
"entropy": 6.178925180435181,
|
|
"epoch": 1.0365871944819314,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004901348036318743,
|
|
"loss": 5.7823,
|
|
"mean_token_accuracy": 0.17629594206809998,
|
|
"num_tokens": 20287557.0,
|
|
"step": 10370
|
|
},
|
|
{
|
|
"entropy": 6.285356044769287,
|
|
"epoch": 1.0370870195431598,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004901243489395093,
|
|
"loss": 5.9195,
|
|
"mean_token_accuracy": 0.1636206954717636,
|
|
"num_tokens": 20297517.0,
|
|
"step": 10375
|
|
},
|
|
{
|
|
"entropy": 6.268024873733521,
|
|
"epoch": 1.0375868446043885,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000490113888834671,
|
|
"loss": 5.7416,
|
|
"mean_token_accuracy": 0.17516834586858748,
|
|
"num_tokens": 20308029.0,
|
|
"step": 10380
|
|
},
|
|
{
|
|
"entropy": 6.125334072113037,
|
|
"epoch": 1.038086669665617,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004901034233176227,
|
|
"loss": 5.7059,
|
|
"mean_token_accuracy": 0.18342580795288085,
|
|
"num_tokens": 20318962.0,
|
|
"step": 10385
|
|
},
|
|
{
|
|
"entropy": 6.255030918121338,
|
|
"epoch": 1.0385864947268455,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004900929523886274,
|
|
"loss": 5.8391,
|
|
"mean_token_accuracy": 0.16445936411619186,
|
|
"num_tokens": 20328729.0,
|
|
"step": 10390
|
|
},
|
|
{
|
|
"entropy": 6.266230058670044,
|
|
"epoch": 1.0390863197880742,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000490082476047949,
|
|
"loss": 5.863,
|
|
"mean_token_accuracy": 0.16297389417886735,
|
|
"num_tokens": 20339002.0,
|
|
"step": 10395
|
|
},
|
|
{
|
|
"entropy": 6.244342517852783,
|
|
"epoch": 1.0395861448493027,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004900719942958506,
|
|
"loss": 5.7677,
|
|
"mean_token_accuracy": 0.17909812182188034,
|
|
"num_tokens": 20347869.0,
|
|
"step": 10400
|
|
},
|
|
{
|
|
"entropy": 6.158752393722534,
|
|
"epoch": 1.0400859699105314,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004900615071325963,
|
|
"loss": 5.6913,
|
|
"mean_token_accuracy": 0.1784303069114685,
|
|
"num_tokens": 20356609.0,
|
|
"step": 10405
|
|
},
|
|
{
|
|
"entropy": 6.175751733779907,
|
|
"epoch": 1.0405857949717598,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.00049005101455845,
|
|
"loss": 5.718,
|
|
"mean_token_accuracy": 0.1888083040714264,
|
|
"num_tokens": 20368793.0,
|
|
"step": 10410
|
|
},
|
|
{
|
|
"entropy": 6.212557029724121,
|
|
"epoch": 1.0410856200329885,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004900405165736753,
|
|
"loss": 5.7235,
|
|
"mean_token_accuracy": 0.1750956282019615,
|
|
"num_tokens": 20379525.0,
|
|
"step": 10415
|
|
},
|
|
{
|
|
"entropy": 6.262401866912842,
|
|
"epoch": 1.041585445094217,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004900300131785365,
|
|
"loss": 5.8294,
|
|
"mean_token_accuracy": 0.1726756677031517,
|
|
"num_tokens": 20388253.0,
|
|
"step": 10420
|
|
},
|
|
{
|
|
"entropy": 6.185280799865723,
|
|
"epoch": 1.0420852701554455,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000490019504373298,
|
|
"loss": 5.846,
|
|
"mean_token_accuracy": 0.16683781296014785,
|
|
"num_tokens": 20398086.0,
|
|
"step": 10425
|
|
},
|
|
{
|
|
"entropy": 6.255641984939575,
|
|
"epoch": 1.0425850952166742,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004900089901582241,
|
|
"loss": 5.9248,
|
|
"mean_token_accuracy": 0.16666711121797562,
|
|
"num_tokens": 20408113.0,
|
|
"step": 10430
|
|
},
|
|
{
|
|
"entropy": 6.3007896900177,
|
|
"epoch": 1.0430849202779027,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004899984705335792,
|
|
"loss": 5.8657,
|
|
"mean_token_accuracy": 0.16941911727190018,
|
|
"num_tokens": 20417717.0,
|
|
"step": 10435
|
|
},
|
|
{
|
|
"entropy": 6.168571805953979,
|
|
"epoch": 1.0435847453391314,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004899879454996282,
|
|
"loss": 5.7538,
|
|
"mean_token_accuracy": 0.17598707377910613,
|
|
"num_tokens": 20428307.0,
|
|
"step": 10440
|
|
},
|
|
{
|
|
"entropy": 6.181351137161255,
|
|
"epoch": 1.0440845704003598,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004899774150566358,
|
|
"loss": 5.7825,
|
|
"mean_token_accuracy": 0.17041172534227372,
|
|
"num_tokens": 20437493.0,
|
|
"step": 10445
|
|
},
|
|
{
|
|
"entropy": 6.216086053848267,
|
|
"epoch": 1.0445843954615885,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000489966879204867,
|
|
"loss": 5.8163,
|
|
"mean_token_accuracy": 0.16939641386270524,
|
|
"num_tokens": 20448218.0,
|
|
"step": 10450
|
|
},
|
|
{
|
|
"entropy": 6.299439239501953,
|
|
"epoch": 1.045084220522817,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004899563379445869,
|
|
"loss": 5.8424,
|
|
"mean_token_accuracy": 0.1753430038690567,
|
|
"num_tokens": 20457478.0,
|
|
"step": 10455
|
|
},
|
|
{
|
|
"entropy": 6.233699035644531,
|
|
"epoch": 1.0455840455840455,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004899457912760605,
|
|
"loss": 5.7334,
|
|
"mean_token_accuracy": 0.17275159657001496,
|
|
"num_tokens": 20466776.0,
|
|
"step": 10460
|
|
},
|
|
{
|
|
"entropy": 6.213349533081055,
|
|
"epoch": 1.0460838706452742,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004899352391995533,
|
|
"loss": 5.7688,
|
|
"mean_token_accuracy": 0.17292186319828035,
|
|
"num_tokens": 20476461.0,
|
|
"step": 10465
|
|
},
|
|
{
|
|
"entropy": 6.2046421527862545,
|
|
"epoch": 1.0465836957065027,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004899246817153309,
|
|
"loss": 5.8102,
|
|
"mean_token_accuracy": 0.17028536796569824,
|
|
"num_tokens": 20487022.0,
|
|
"step": 10470
|
|
},
|
|
{
|
|
"entropy": 6.191453123092652,
|
|
"epoch": 1.0470835207677314,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004899141188236587,
|
|
"loss": 5.7129,
|
|
"mean_token_accuracy": 0.17963015735149385,
|
|
"num_tokens": 20496326.0,
|
|
"step": 10475
|
|
},
|
|
{
|
|
"entropy": 6.23358941078186,
|
|
"epoch": 1.0475833458289598,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004899035505248027,
|
|
"loss": 5.7854,
|
|
"mean_token_accuracy": 0.17183300256729125,
|
|
"num_tokens": 20504933.0,
|
|
"step": 10480
|
|
},
|
|
{
|
|
"entropy": 6.2490253925323485,
|
|
"epoch": 1.0480831708901883,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004898929768190286,
|
|
"loss": 5.7769,
|
|
"mean_token_accuracy": 0.1729974180459976,
|
|
"num_tokens": 20513931.0,
|
|
"step": 10485
|
|
},
|
|
{
|
|
"entropy": 6.159022665023803,
|
|
"epoch": 1.048582995951417,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004898823977066024,
|
|
"loss": 5.738,
|
|
"mean_token_accuracy": 0.17705473452806472,
|
|
"num_tokens": 20523176.0,
|
|
"step": 10490
|
|
},
|
|
{
|
|
"entropy": 6.202305746078491,
|
|
"epoch": 1.0490828210126455,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004898718131877906,
|
|
"loss": 5.855,
|
|
"mean_token_accuracy": 0.16677090972661973,
|
|
"num_tokens": 20533049.0,
|
|
"step": 10495
|
|
},
|
|
{
|
|
"entropy": 6.225211095809937,
|
|
"epoch": 1.0495826460738742,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004898612232628591,
|
|
"loss": 5.7165,
|
|
"mean_token_accuracy": 0.17457233667373656,
|
|
"num_tokens": 20542132.0,
|
|
"step": 10500
|
|
},
|
|
{
|
|
"entropy": 6.202930641174317,
|
|
"epoch": 1.0500824711351027,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004898506279320745,
|
|
"loss": 5.8202,
|
|
"mean_token_accuracy": 0.16972397565841674,
|
|
"num_tokens": 20551779.0,
|
|
"step": 10505
|
|
},
|
|
{
|
|
"entropy": 6.226065015792846,
|
|
"epoch": 1.0505822961963314,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004898400271957034,
|
|
"loss": 5.8451,
|
|
"mean_token_accuracy": 0.1677120879292488,
|
|
"num_tokens": 20560548.0,
|
|
"step": 10510
|
|
},
|
|
{
|
|
"entropy": 6.263583564758301,
|
|
"epoch": 1.0510821212575598,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004898294210540126,
|
|
"loss": 5.9233,
|
|
"mean_token_accuracy": 0.16561291068792344,
|
|
"num_tokens": 20570909.0,
|
|
"step": 10515
|
|
},
|
|
{
|
|
"entropy": 6.358686208724976,
|
|
"epoch": 1.0515819463187883,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004898188095072688,
|
|
"loss": 5.8323,
|
|
"mean_token_accuracy": 0.16919361501932145,
|
|
"num_tokens": 20580367.0,
|
|
"step": 10520
|
|
},
|
|
{
|
|
"entropy": 6.252203416824341,
|
|
"epoch": 1.052081771380017,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000489808192555739,
|
|
"loss": 5.7416,
|
|
"mean_token_accuracy": 0.17091714441776276,
|
|
"num_tokens": 20589653.0,
|
|
"step": 10525
|
|
},
|
|
{
|
|
"entropy": 6.214619779586792,
|
|
"epoch": 1.0525815964412455,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004897975701996903,
|
|
"loss": 5.7525,
|
|
"mean_token_accuracy": 0.17405074685811997,
|
|
"num_tokens": 20599530.0,
|
|
"step": 10530
|
|
},
|
|
{
|
|
"entropy": 6.15150260925293,
|
|
"epoch": 1.0530814215024742,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004897869424393902,
|
|
"loss": 5.7707,
|
|
"mean_token_accuracy": 0.17092722207307814,
|
|
"num_tokens": 20607989.0,
|
|
"step": 10535
|
|
},
|
|
{
|
|
"entropy": 6.209667158126831,
|
|
"epoch": 1.0535812465637027,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004897763092751057,
|
|
"loss": 5.7635,
|
|
"mean_token_accuracy": 0.1693803608417511,
|
|
"num_tokens": 20618315.0,
|
|
"step": 10540
|
|
},
|
|
{
|
|
"entropy": 6.201652383804321,
|
|
"epoch": 1.0540810716249314,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004897656707071045,
|
|
"loss": 5.8412,
|
|
"mean_token_accuracy": 0.16767117381095886,
|
|
"num_tokens": 20627554.0,
|
|
"step": 10545
|
|
},
|
|
{
|
|
"entropy": 6.219838237762451,
|
|
"epoch": 1.0545808966861598,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004897550267356545,
|
|
"loss": 5.8227,
|
|
"mean_token_accuracy": 0.1705699861049652,
|
|
"num_tokens": 20636841.0,
|
|
"step": 10550
|
|
},
|
|
{
|
|
"entropy": 6.208605670928955,
|
|
"epoch": 1.0550807217473883,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004897443773610231,
|
|
"loss": 5.7374,
|
|
"mean_token_accuracy": 0.1732224330306053,
|
|
"num_tokens": 20647129.0,
|
|
"step": 10555
|
|
},
|
|
{
|
|
"entropy": 6.255770874023438,
|
|
"epoch": 1.055580546808617,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004897337225834785,
|
|
"loss": 5.8768,
|
|
"mean_token_accuracy": 0.16340237408876418,
|
|
"num_tokens": 20657971.0,
|
|
"step": 10560
|
|
},
|
|
{
|
|
"entropy": 6.2330952167510985,
|
|
"epoch": 1.0560803718698455,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004897230624032888,
|
|
"loss": 5.8094,
|
|
"mean_token_accuracy": 0.1710523098707199,
|
|
"num_tokens": 20666266.0,
|
|
"step": 10565
|
|
},
|
|
{
|
|
"entropy": 6.274275016784668,
|
|
"epoch": 1.0565801969310742,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004897123968207219,
|
|
"loss": 5.78,
|
|
"mean_token_accuracy": 0.17579889446496963,
|
|
"num_tokens": 20676454.0,
|
|
"step": 10570
|
|
},
|
|
{
|
|
"entropy": 6.219386911392212,
|
|
"epoch": 1.0570800219923027,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004897017258360465,
|
|
"loss": 5.876,
|
|
"mean_token_accuracy": 0.16664009541273117,
|
|
"num_tokens": 20687333.0,
|
|
"step": 10575
|
|
},
|
|
{
|
|
"entropy": 6.19634976387024,
|
|
"epoch": 1.0575798470535314,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004896910494495308,
|
|
"loss": 5.7097,
|
|
"mean_token_accuracy": 0.1722988158464432,
|
|
"num_tokens": 20696530.0,
|
|
"step": 10580
|
|
},
|
|
{
|
|
"entropy": 6.198044395446777,
|
|
"epoch": 1.0580796721147598,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004896803676614436,
|
|
"loss": 5.8468,
|
|
"mean_token_accuracy": 0.1684746265411377,
|
|
"num_tokens": 20706674.0,
|
|
"step": 10585
|
|
},
|
|
{
|
|
"entropy": 6.183947467803955,
|
|
"epoch": 1.0585794971759883,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004896696804720536,
|
|
"loss": 5.6588,
|
|
"mean_token_accuracy": 0.1962839975953102,
|
|
"num_tokens": 20715695.0,
|
|
"step": 10590
|
|
},
|
|
{
|
|
"entropy": 6.2287615776062015,
|
|
"epoch": 1.059079322237217,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004896589878816297,
|
|
"loss": 5.8708,
|
|
"mean_token_accuracy": 0.17158064991235733,
|
|
"num_tokens": 20725763.0,
|
|
"step": 10595
|
|
},
|
|
{
|
|
"entropy": 6.189944124221801,
|
|
"epoch": 1.0595791472984455,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004896482898904409,
|
|
"loss": 5.7725,
|
|
"mean_token_accuracy": 0.17073653042316436,
|
|
"num_tokens": 20734944.0,
|
|
"step": 10600
|
|
},
|
|
{
|
|
"entropy": 6.183209037780761,
|
|
"epoch": 1.0600789723596742,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004896375864987563,
|
|
"loss": 5.7598,
|
|
"mean_token_accuracy": 0.17914697378873826,
|
|
"num_tokens": 20744951.0,
|
|
"step": 10605
|
|
},
|
|
{
|
|
"entropy": 6.2028545379638675,
|
|
"epoch": 1.0605787974209027,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004896268777068453,
|
|
"loss": 5.732,
|
|
"mean_token_accuracy": 0.17752886712551116,
|
|
"num_tokens": 20754937.0,
|
|
"step": 10610
|
|
},
|
|
{
|
|
"entropy": 6.252514743804932,
|
|
"epoch": 1.0610786224821314,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004896161635149773,
|
|
"loss": 5.8143,
|
|
"mean_token_accuracy": 0.16960179656744004,
|
|
"num_tokens": 20767373.0,
|
|
"step": 10615
|
|
},
|
|
{
|
|
"entropy": 6.2377174377441404,
|
|
"epoch": 1.0615784475433598,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004896054439234217,
|
|
"loss": 5.7813,
|
|
"mean_token_accuracy": 0.1694555699825287,
|
|
"num_tokens": 20777647.0,
|
|
"step": 10620
|
|
},
|
|
{
|
|
"entropy": 6.241938352584839,
|
|
"epoch": 1.0620782726045883,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004895947189324486,
|
|
"loss": 5.8044,
|
|
"mean_token_accuracy": 0.17595423758029938,
|
|
"num_tokens": 20788598.0,
|
|
"step": 10625
|
|
},
|
|
{
|
|
"entropy": 6.218670892715454,
|
|
"epoch": 1.062578097665817,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004895839885423273,
|
|
"loss": 5.7513,
|
|
"mean_token_accuracy": 0.17201370149850845,
|
|
"num_tokens": 20798586.0,
|
|
"step": 10630
|
|
},
|
|
{
|
|
"entropy": 6.13684868812561,
|
|
"epoch": 1.0630779227270455,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004895732527533283,
|
|
"loss": 5.7373,
|
|
"mean_token_accuracy": 0.17971080243587495,
|
|
"num_tokens": 20807447.0,
|
|
"step": 10635
|
|
},
|
|
{
|
|
"entropy": 6.174538660049438,
|
|
"epoch": 1.0635777477882742,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004895625115657215,
|
|
"loss": 5.8024,
|
|
"mean_token_accuracy": 0.17490694522857667,
|
|
"num_tokens": 20817889.0,
|
|
"step": 10640
|
|
},
|
|
{
|
|
"entropy": 6.1932672500610355,
|
|
"epoch": 1.0640775728495027,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000489551764979777,
|
|
"loss": 5.7966,
|
|
"mean_token_accuracy": 0.16888925284147263,
|
|
"num_tokens": 20827858.0,
|
|
"step": 10645
|
|
},
|
|
{
|
|
"entropy": 6.214620923995971,
|
|
"epoch": 1.0645773979107314,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004895410129957653,
|
|
"loss": 5.7658,
|
|
"mean_token_accuracy": 0.1783762350678444,
|
|
"num_tokens": 20837114.0,
|
|
"step": 10650
|
|
},
|
|
{
|
|
"entropy": 6.2254410743713375,
|
|
"epoch": 1.0650772229719598,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004895302556139569,
|
|
"loss": 5.8397,
|
|
"mean_token_accuracy": 0.16404734253883363,
|
|
"num_tokens": 20846979.0,
|
|
"step": 10655
|
|
},
|
|
{
|
|
"entropy": 6.211126041412354,
|
|
"epoch": 1.0655770480331883,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004895194928346226,
|
|
"loss": 5.8175,
|
|
"mean_token_accuracy": 0.17312153279781342,
|
|
"num_tokens": 20856831.0,
|
|
"step": 10660
|
|
},
|
|
{
|
|
"entropy": 6.21453537940979,
|
|
"epoch": 1.066076873094417,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.000489508724658033,
|
|
"loss": 5.6824,
|
|
"mean_token_accuracy": 0.17439087480306625,
|
|
"num_tokens": 20866203.0,
|
|
"step": 10665
|
|
},
|
|
{
|
|
"entropy": 6.226136255264282,
|
|
"epoch": 1.0665766981556455,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000489497951084459,
|
|
"loss": 5.7495,
|
|
"mean_token_accuracy": 0.1708911545574665,
|
|
"num_tokens": 20875813.0,
|
|
"step": 10670
|
|
},
|
|
{
|
|
"entropy": 6.298255062103271,
|
|
"epoch": 1.0670765232168742,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004894871721141718,
|
|
"loss": 5.8206,
|
|
"mean_token_accuracy": 0.1713681325316429,
|
|
"num_tokens": 20884773.0,
|
|
"step": 10675
|
|
},
|
|
{
|
|
"entropy": 6.178518915176392,
|
|
"epoch": 1.0675763482781027,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004894763877474426,
|
|
"loss": 5.7582,
|
|
"mean_token_accuracy": 0.18290602713823317,
|
|
"num_tokens": 20894305.0,
|
|
"step": 10680
|
|
},
|
|
{
|
|
"entropy": 6.2204673290252686,
|
|
"epoch": 1.0680761733393311,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004894655979845427,
|
|
"loss": 5.8552,
|
|
"mean_token_accuracy": 0.16952344477176667,
|
|
"num_tokens": 20903849.0,
|
|
"step": 10685
|
|
},
|
|
{
|
|
"entropy": 6.234395122528076,
|
|
"epoch": 1.0685759984005598,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004894548028257434,
|
|
"loss": 5.7325,
|
|
"mean_token_accuracy": 0.17339884787797927,
|
|
"num_tokens": 20913380.0,
|
|
"step": 10690
|
|
},
|
|
{
|
|
"entropy": 6.202211141586304,
|
|
"epoch": 1.0690758234617883,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004894440022713165,
|
|
"loss": 5.8286,
|
|
"mean_token_accuracy": 0.17010540664196014,
|
|
"num_tokens": 20923921.0,
|
|
"step": 10695
|
|
},
|
|
{
|
|
"entropy": 6.205871343612671,
|
|
"epoch": 1.069575648523017,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004894331963215337,
|
|
"loss": 5.756,
|
|
"mean_token_accuracy": 0.17398875802755356,
|
|
"num_tokens": 20934613.0,
|
|
"step": 10700
|
|
},
|
|
{
|
|
"entropy": 6.226714563369751,
|
|
"epoch": 1.0700754735842455,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000489422384976667,
|
|
"loss": 5.7824,
|
|
"mean_token_accuracy": 0.174000982940197,
|
|
"num_tokens": 20944052.0,
|
|
"step": 10705
|
|
},
|
|
{
|
|
"entropy": 6.223764514923095,
|
|
"epoch": 1.0705752986454742,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004894115682369881,
|
|
"loss": 5.7919,
|
|
"mean_token_accuracy": 0.17544130086898804,
|
|
"num_tokens": 20953406.0,
|
|
"step": 10710
|
|
},
|
|
{
|
|
"entropy": 6.317852306365967,
|
|
"epoch": 1.0710751237067027,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004894007461027693,
|
|
"loss": 5.9391,
|
|
"mean_token_accuracy": 0.1626747652888298,
|
|
"num_tokens": 20963425.0,
|
|
"step": 10715
|
|
},
|
|
{
|
|
"entropy": 6.268984746932984,
|
|
"epoch": 1.0715749487679311,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004893899185742828,
|
|
"loss": 5.8778,
|
|
"mean_token_accuracy": 0.16015640646219254,
|
|
"num_tokens": 20973777.0,
|
|
"step": 10720
|
|
},
|
|
{
|
|
"entropy": 6.1665362358093265,
|
|
"epoch": 1.0720747738291598,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004893790856518014,
|
|
"loss": 5.7115,
|
|
"mean_token_accuracy": 0.17961511462926866,
|
|
"num_tokens": 20983418.0,
|
|
"step": 10725
|
|
},
|
|
{
|
|
"entropy": 6.177931833267212,
|
|
"epoch": 1.0725745988903883,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004893682473355972,
|
|
"loss": 5.7088,
|
|
"mean_token_accuracy": 0.17805280685424804,
|
|
"num_tokens": 20993051.0,
|
|
"step": 10730
|
|
},
|
|
{
|
|
"entropy": 6.156251049041748,
|
|
"epoch": 1.073074423951617,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004893574036259432,
|
|
"loss": 5.7089,
|
|
"mean_token_accuracy": 0.1864047572016716,
|
|
"num_tokens": 21003439.0,
|
|
"step": 10735
|
|
},
|
|
{
|
|
"entropy": 6.275533676147461,
|
|
"epoch": 1.0735742490128455,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004893465545231119,
|
|
"loss": 5.8021,
|
|
"mean_token_accuracy": 0.17340317219495774,
|
|
"num_tokens": 21013242.0,
|
|
"step": 10740
|
|
},
|
|
{
|
|
"entropy": 6.225524234771728,
|
|
"epoch": 1.074074074074074,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004893357000273765,
|
|
"loss": 5.7808,
|
|
"mean_token_accuracy": 0.1719970777630806,
|
|
"num_tokens": 21022268.0,
|
|
"step": 10745
|
|
},
|
|
{
|
|
"entropy": 6.215897464752198,
|
|
"epoch": 1.0745738991353027,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048932484013901,
|
|
"loss": 5.8544,
|
|
"mean_token_accuracy": 0.16874396800994873,
|
|
"num_tokens": 21032130.0,
|
|
"step": 10750
|
|
},
|
|
{
|
|
"entropy": 6.163355970382691,
|
|
"epoch": 1.0750737241965311,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004893139748582857,
|
|
"loss": 5.6937,
|
|
"mean_token_accuracy": 0.18166623413562774,
|
|
"num_tokens": 21041966.0,
|
|
"step": 10755
|
|
},
|
|
{
|
|
"entropy": 6.15837345123291,
|
|
"epoch": 1.0755735492577598,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000489303104185477,
|
|
"loss": 5.6712,
|
|
"mean_token_accuracy": 0.18380088061094285,
|
|
"num_tokens": 21051270.0,
|
|
"step": 10760
|
|
},
|
|
{
|
|
"entropy": 6.221372413635254,
|
|
"epoch": 1.0760733743189883,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004892922281208573,
|
|
"loss": 5.8686,
|
|
"mean_token_accuracy": 0.16481308937072753,
|
|
"num_tokens": 21060926.0,
|
|
"step": 10765
|
|
},
|
|
{
|
|
"entropy": 6.279391717910767,
|
|
"epoch": 1.076573199380217,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004892813466647002,
|
|
"loss": 5.9306,
|
|
"mean_token_accuracy": 0.16384380906820298,
|
|
"num_tokens": 21071367.0,
|
|
"step": 10770
|
|
},
|
|
{
|
|
"entropy": 6.21832389831543,
|
|
"epoch": 1.0770730244414455,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004892704598172797,
|
|
"loss": 5.787,
|
|
"mean_token_accuracy": 0.16521903574466706,
|
|
"num_tokens": 21082775.0,
|
|
"step": 10775
|
|
},
|
|
{
|
|
"entropy": 6.268756103515625,
|
|
"epoch": 1.077572849502674,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004892595675788696,
|
|
"loss": 5.8771,
|
|
"mean_token_accuracy": 0.16640841513872145,
|
|
"num_tokens": 21092018.0,
|
|
"step": 10780
|
|
},
|
|
{
|
|
"entropy": 6.217105579376221,
|
|
"epoch": 1.0780726745639027,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004892486699497439,
|
|
"loss": 5.765,
|
|
"mean_token_accuracy": 0.17629154175519943,
|
|
"num_tokens": 21101246.0,
|
|
"step": 10785
|
|
},
|
|
{
|
|
"entropy": 6.231991910934449,
|
|
"epoch": 1.0785724996251311,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004892377669301766,
|
|
"loss": 5.8013,
|
|
"mean_token_accuracy": 0.17352432906627654,
|
|
"num_tokens": 21110816.0,
|
|
"step": 10790
|
|
},
|
|
{
|
|
"entropy": 6.241929340362549,
|
|
"epoch": 1.0790723246863598,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004892268585204423,
|
|
"loss": 5.81,
|
|
"mean_token_accuracy": 0.17125056833028793,
|
|
"num_tokens": 21120228.0,
|
|
"step": 10795
|
|
},
|
|
{
|
|
"entropy": 6.156728887557984,
|
|
"epoch": 1.0795721497475883,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004892159447208154,
|
|
"loss": 5.7168,
|
|
"mean_token_accuracy": 0.18005625307559966,
|
|
"num_tokens": 21129921.0,
|
|
"step": 10800
|
|
},
|
|
{
|
|
"entropy": 6.1754354476928714,
|
|
"epoch": 1.080071974808817,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004892050255315705,
|
|
"loss": 5.8697,
|
|
"mean_token_accuracy": 0.1679516017436981,
|
|
"num_tokens": 21139605.0,
|
|
"step": 10805
|
|
},
|
|
{
|
|
"entropy": 6.1794617652893065,
|
|
"epoch": 1.0805717998700455,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004891941009529822,
|
|
"loss": 5.7474,
|
|
"mean_token_accuracy": 0.17792760729789733,
|
|
"num_tokens": 21149004.0,
|
|
"step": 10810
|
|
},
|
|
{
|
|
"entropy": 6.249739170074463,
|
|
"epoch": 1.081071624931274,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004891831709853255,
|
|
"loss": 5.8134,
|
|
"mean_token_accuracy": 0.16623160392045974,
|
|
"num_tokens": 21159013.0,
|
|
"step": 10815
|
|
},
|
|
{
|
|
"entropy": 6.166282081604004,
|
|
"epoch": 1.0815714499925027,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004891722356288752,
|
|
"loss": 5.7555,
|
|
"mean_token_accuracy": 0.16947653293609619,
|
|
"num_tokens": 21169432.0,
|
|
"step": 10820
|
|
},
|
|
{
|
|
"entropy": 6.156125450134278,
|
|
"epoch": 1.0820712750537311,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004891612948839068,
|
|
"loss": 5.7157,
|
|
"mean_token_accuracy": 0.17735745161771774,
|
|
"num_tokens": 21179672.0,
|
|
"step": 10825
|
|
},
|
|
{
|
|
"entropy": 6.203233766555786,
|
|
"epoch": 1.0825711001149598,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004891503487506951,
|
|
"loss": 5.7809,
|
|
"mean_token_accuracy": 0.17314334958791733,
|
|
"num_tokens": 21189562.0,
|
|
"step": 10830
|
|
},
|
|
{
|
|
"entropy": 6.306926202774048,
|
|
"epoch": 1.0830709251761883,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004891393972295159,
|
|
"loss": 5.8693,
|
|
"mean_token_accuracy": 0.16488782167434693,
|
|
"num_tokens": 21199538.0,
|
|
"step": 10835
|
|
},
|
|
{
|
|
"entropy": 6.252102041244507,
|
|
"epoch": 1.083570750237417,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004891284403206444,
|
|
"loss": 5.8241,
|
|
"mean_token_accuracy": 0.16683096289634705,
|
|
"num_tokens": 21209355.0,
|
|
"step": 10840
|
|
},
|
|
{
|
|
"entropy": 6.193649005889893,
|
|
"epoch": 1.0840705752986455,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004891174780243566,
|
|
"loss": 5.73,
|
|
"mean_token_accuracy": 0.17475489974021913,
|
|
"num_tokens": 21218268.0,
|
|
"step": 10845
|
|
},
|
|
{
|
|
"entropy": 6.233925533294678,
|
|
"epoch": 1.084570400359874,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000489106510340928,
|
|
"loss": 5.8537,
|
|
"mean_token_accuracy": 0.17145161405205728,
|
|
"num_tokens": 21228376.0,
|
|
"step": 10850
|
|
},
|
|
{
|
|
"entropy": 6.203484392166137,
|
|
"epoch": 1.0850702254211027,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004890955372706348,
|
|
"loss": 5.843,
|
|
"mean_token_accuracy": 0.17178430855274202,
|
|
"num_tokens": 21237781.0,
|
|
"step": 10855
|
|
},
|
|
{
|
|
"entropy": 6.1690703392028805,
|
|
"epoch": 1.0855700504823311,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004890845588137531,
|
|
"loss": 5.7138,
|
|
"mean_token_accuracy": 0.1764729291200638,
|
|
"num_tokens": 21247096.0,
|
|
"step": 10860
|
|
},
|
|
{
|
|
"entropy": 6.290404796600342,
|
|
"epoch": 1.0860698755435598,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004890735749705587,
|
|
"loss": 5.865,
|
|
"mean_token_accuracy": 0.17136863619089127,
|
|
"num_tokens": 21258645.0,
|
|
"step": 10865
|
|
},
|
|
{
|
|
"entropy": 6.2783324241638185,
|
|
"epoch": 1.0865697006047883,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004890625857413283,
|
|
"loss": 5.8099,
|
|
"mean_token_accuracy": 0.17180899232625962,
|
|
"num_tokens": 21268634.0,
|
|
"step": 10870
|
|
},
|
|
{
|
|
"entropy": 6.2138152599334715,
|
|
"epoch": 1.087069525666017,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004890515911263385,
|
|
"loss": 5.749,
|
|
"mean_token_accuracy": 0.17395084351301193,
|
|
"num_tokens": 21278996.0,
|
|
"step": 10875
|
|
},
|
|
{
|
|
"entropy": 6.120256042480468,
|
|
"epoch": 1.0875693507272455,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004890405911258656,
|
|
"loss": 5.5929,
|
|
"mean_token_accuracy": 0.18774231374263764,
|
|
"num_tokens": 21288689.0,
|
|
"step": 10880
|
|
},
|
|
{
|
|
"entropy": 6.2184830665588375,
|
|
"epoch": 1.088069175788474,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004890295857401866,
|
|
"loss": 5.8249,
|
|
"mean_token_accuracy": 0.16442839354276656,
|
|
"num_tokens": 21298542.0,
|
|
"step": 10885
|
|
},
|
|
{
|
|
"entropy": 6.201722812652588,
|
|
"epoch": 1.0885690008497027,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004890185749695783,
|
|
"loss": 5.7772,
|
|
"mean_token_accuracy": 0.16875378489494325,
|
|
"num_tokens": 21308035.0,
|
|
"step": 10890
|
|
},
|
|
{
|
|
"entropy": 6.299549865722656,
|
|
"epoch": 1.0890688259109311,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004890075588143176,
|
|
"loss": 5.8867,
|
|
"mean_token_accuracy": 0.16342998594045638,
|
|
"num_tokens": 21317898.0,
|
|
"step": 10895
|
|
},
|
|
{
|
|
"entropy": 6.193901491165161,
|
|
"epoch": 1.0895686509721598,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004889965372746819,
|
|
"loss": 5.7823,
|
|
"mean_token_accuracy": 0.17621756494045257,
|
|
"num_tokens": 21327347.0,
|
|
"step": 10900
|
|
},
|
|
{
|
|
"entropy": 6.252473020553589,
|
|
"epoch": 1.0900684760333883,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004889855103509484,
|
|
"loss": 5.8197,
|
|
"mean_token_accuracy": 0.16974932849407195,
|
|
"num_tokens": 21336592.0,
|
|
"step": 10905
|
|
},
|
|
{
|
|
"entropy": 6.242722129821777,
|
|
"epoch": 1.090568301094617,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004889744780433944,
|
|
"loss": 5.8612,
|
|
"mean_token_accuracy": 0.16345041394233703,
|
|
"num_tokens": 21345764.0,
|
|
"step": 10910
|
|
},
|
|
{
|
|
"entropy": 6.250154829025268,
|
|
"epoch": 1.0910681261558455,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004889634403522976,
|
|
"loss": 5.7884,
|
|
"mean_token_accuracy": 0.16654278635978698,
|
|
"num_tokens": 21354423.0,
|
|
"step": 10915
|
|
},
|
|
{
|
|
"entropy": 6.242933511734009,
|
|
"epoch": 1.091567951217074,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004889523972779359,
|
|
"loss": 5.8466,
|
|
"mean_token_accuracy": 0.18056381046772002,
|
|
"num_tokens": 21364407.0,
|
|
"step": 10920
|
|
},
|
|
{
|
|
"entropy": 6.293010139465332,
|
|
"epoch": 1.0920677762783026,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004889413488205868,
|
|
"loss": 5.8944,
|
|
"mean_token_accuracy": 0.1654813677072525,
|
|
"num_tokens": 21374642.0,
|
|
"step": 10925
|
|
},
|
|
{
|
|
"entropy": 6.171544361114502,
|
|
"epoch": 1.0925676013395311,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004889302949805283,
|
|
"loss": 5.7011,
|
|
"mean_token_accuracy": 0.1835593268275261,
|
|
"num_tokens": 21384437.0,
|
|
"step": 10930
|
|
},
|
|
{
|
|
"entropy": 6.22461256980896,
|
|
"epoch": 1.0930674264007598,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004889192357580388,
|
|
"loss": 5.7305,
|
|
"mean_token_accuracy": 0.17894354611635208,
|
|
"num_tokens": 21393924.0,
|
|
"step": 10935
|
|
},
|
|
{
|
|
"entropy": 6.173677396774292,
|
|
"epoch": 1.0935672514619883,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004889081711533964,
|
|
"loss": 5.747,
|
|
"mean_token_accuracy": 0.17737294733524323,
|
|
"num_tokens": 21402924.0,
|
|
"step": 10940
|
|
},
|
|
{
|
|
"entropy": 6.248400783538818,
|
|
"epoch": 1.0940670765232168,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004888971011668793,
|
|
"loss": 5.8602,
|
|
"mean_token_accuracy": 0.1645239621400833,
|
|
"num_tokens": 21412422.0,
|
|
"step": 10945
|
|
},
|
|
{
|
|
"entropy": 6.264774465560913,
|
|
"epoch": 1.0945669015844455,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004888860257987662,
|
|
"loss": 5.7996,
|
|
"mean_token_accuracy": 0.17798930257558823,
|
|
"num_tokens": 21421830.0,
|
|
"step": 10950
|
|
},
|
|
{
|
|
"entropy": 6.263902282714843,
|
|
"epoch": 1.095066726645674,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004888749450493358,
|
|
"loss": 5.7836,
|
|
"mean_token_accuracy": 0.17190886288881302,
|
|
"num_tokens": 21431602.0,
|
|
"step": 10955
|
|
},
|
|
{
|
|
"entropy": 6.248490524291992,
|
|
"epoch": 1.0955665517069026,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004888638589188669,
|
|
"loss": 5.8333,
|
|
"mean_token_accuracy": 0.1736230030655861,
|
|
"num_tokens": 21441110.0,
|
|
"step": 10960
|
|
},
|
|
{
|
|
"entropy": 6.290872716903687,
|
|
"epoch": 1.0960663767681311,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004888527674076382,
|
|
"loss": 5.8319,
|
|
"mean_token_accuracy": 0.16856259405612944,
|
|
"num_tokens": 21450626.0,
|
|
"step": 10965
|
|
},
|
|
{
|
|
"entropy": 6.155609607696533,
|
|
"epoch": 1.0965662018293598,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000488841670515929,
|
|
"loss": 5.7163,
|
|
"mean_token_accuracy": 0.17417923659086226,
|
|
"num_tokens": 21461174.0,
|
|
"step": 10970
|
|
},
|
|
{
|
|
"entropy": 6.18221378326416,
|
|
"epoch": 1.0970660268905883,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004888305682440183,
|
|
"loss": 5.765,
|
|
"mean_token_accuracy": 0.1813131883740425,
|
|
"num_tokens": 21470895.0,
|
|
"step": 10975
|
|
},
|
|
{
|
|
"entropy": 6.2094145774841305,
|
|
"epoch": 1.0975658519518168,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004888194605921855,
|
|
"loss": 5.7151,
|
|
"mean_token_accuracy": 0.1820187583565712,
|
|
"num_tokens": 21480192.0,
|
|
"step": 10980
|
|
},
|
|
{
|
|
"entropy": 6.31711254119873,
|
|
"epoch": 1.0980656770130455,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004888083475607102,
|
|
"loss": 5.827,
|
|
"mean_token_accuracy": 0.16963830292224885,
|
|
"num_tokens": 21489418.0,
|
|
"step": 10985
|
|
},
|
|
{
|
|
"entropy": 6.261421585083008,
|
|
"epoch": 1.098565502074274,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004887972291498718,
|
|
"loss": 5.8751,
|
|
"mean_token_accuracy": 0.16889005303382873,
|
|
"num_tokens": 21499228.0,
|
|
"step": 10990
|
|
},
|
|
{
|
|
"entropy": 6.205340909957886,
|
|
"epoch": 1.0990653271355026,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004887861053599503,
|
|
"loss": 5.7054,
|
|
"mean_token_accuracy": 0.1772100955247879,
|
|
"num_tokens": 21509051.0,
|
|
"step": 10995
|
|
},
|
|
{
|
|
"entropy": 6.227521800994873,
|
|
"epoch": 1.0995651521967311,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004887749761912252,
|
|
"loss": 5.8137,
|
|
"mean_token_accuracy": 0.16960758864879608,
|
|
"num_tokens": 21518853.0,
|
|
"step": 11000
|
|
},
|
|
{
|
|
"entropy": 6.290289878845215,
|
|
"epoch": 1.1000649772579596,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004887638416439768,
|
|
"loss": 5.8533,
|
|
"mean_token_accuracy": 0.16934311985969544,
|
|
"num_tokens": 21528547.0,
|
|
"step": 11005
|
|
},
|
|
{
|
|
"entropy": 6.303914260864258,
|
|
"epoch": 1.1005648023191883,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004887527017184851,
|
|
"loss": 5.8479,
|
|
"mean_token_accuracy": 0.1712890237569809,
|
|
"num_tokens": 21538166.0,
|
|
"step": 11010
|
|
},
|
|
{
|
|
"entropy": 6.265956211090088,
|
|
"epoch": 1.1010646273804168,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004887415564150305,
|
|
"loss": 5.7816,
|
|
"mean_token_accuracy": 0.17633587568998338,
|
|
"num_tokens": 21548212.0,
|
|
"step": 11015
|
|
},
|
|
{
|
|
"entropy": 6.277155637741089,
|
|
"epoch": 1.1015644524416455,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004887304057338934,
|
|
"loss": 5.7976,
|
|
"mean_token_accuracy": 0.1686053305864334,
|
|
"num_tokens": 21558809.0,
|
|
"step": 11020
|
|
},
|
|
{
|
|
"entropy": 6.165370130538941,
|
|
"epoch": 1.102064277502874,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000488719249675354,
|
|
"loss": 5.6828,
|
|
"mean_token_accuracy": 0.18382690250873565,
|
|
"num_tokens": 21567923.0,
|
|
"step": 11025
|
|
},
|
|
{
|
|
"entropy": 6.179647159576416,
|
|
"epoch": 1.1025641025641026,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004887080882396936,
|
|
"loss": 5.784,
|
|
"mean_token_accuracy": 0.17725792676210403,
|
|
"num_tokens": 21578051.0,
|
|
"step": 11030
|
|
},
|
|
{
|
|
"entropy": 6.203695011138916,
|
|
"epoch": 1.1030639276253311,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004886969214271925,
|
|
"loss": 5.8328,
|
|
"mean_token_accuracy": 0.17323004752397536,
|
|
"num_tokens": 21586950.0,
|
|
"step": 11035
|
|
},
|
|
{
|
|
"entropy": 6.266402339935302,
|
|
"epoch": 1.1035637526865596,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004886857492381319,
|
|
"loss": 5.8231,
|
|
"mean_token_accuracy": 0.17019603103399278,
|
|
"num_tokens": 21596577.0,
|
|
"step": 11040
|
|
},
|
|
{
|
|
"entropy": 6.241931676864624,
|
|
"epoch": 1.1040635777477883,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004886745716727928,
|
|
"loss": 5.8624,
|
|
"mean_token_accuracy": 0.1688755303621292,
|
|
"num_tokens": 21606474.0,
|
|
"step": 11045
|
|
},
|
|
{
|
|
"entropy": 6.175734138488769,
|
|
"epoch": 1.1045634028090168,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004886633887314565,
|
|
"loss": 5.6768,
|
|
"mean_token_accuracy": 0.18453330397605897,
|
|
"num_tokens": 21616277.0,
|
|
"step": 11050
|
|
},
|
|
{
|
|
"entropy": 6.312750625610351,
|
|
"epoch": 1.1050632278702455,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004886522004144044,
|
|
"loss": 5.8504,
|
|
"mean_token_accuracy": 0.16616131663322448,
|
|
"num_tokens": 21626096.0,
|
|
"step": 11055
|
|
},
|
|
{
|
|
"entropy": 6.308995151519776,
|
|
"epoch": 1.105563052931474,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004886410067219178,
|
|
"loss": 5.9065,
|
|
"mean_token_accuracy": 0.1638119600713253,
|
|
"num_tokens": 21635295.0,
|
|
"step": 11060
|
|
},
|
|
{
|
|
"entropy": 6.2731614112854,
|
|
"epoch": 1.1060628779927026,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004886298076542785,
|
|
"loss": 5.875,
|
|
"mean_token_accuracy": 0.1588502660393715,
|
|
"num_tokens": 21645900.0,
|
|
"step": 11065
|
|
},
|
|
{
|
|
"entropy": 6.220165157318116,
|
|
"epoch": 1.1065627030539311,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004886186032117682,
|
|
"loss": 5.7892,
|
|
"mean_token_accuracy": 0.1689761370420456,
|
|
"num_tokens": 21654757.0,
|
|
"step": 11070
|
|
},
|
|
{
|
|
"entropy": 6.1341719150543215,
|
|
"epoch": 1.1070625281151596,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004886073933946688,
|
|
"loss": 5.7165,
|
|
"mean_token_accuracy": 0.17799597829580308,
|
|
"num_tokens": 21665253.0,
|
|
"step": 11075
|
|
},
|
|
{
|
|
"entropy": 6.128421926498413,
|
|
"epoch": 1.1075623531763883,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004885961782032624,
|
|
"loss": 5.6558,
|
|
"mean_token_accuracy": 0.18141077160835267,
|
|
"num_tokens": 21674345.0,
|
|
"step": 11080
|
|
},
|
|
{
|
|
"entropy": 6.228607082366944,
|
|
"epoch": 1.1080621782376168,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000488584957637831,
|
|
"loss": 5.8447,
|
|
"mean_token_accuracy": 0.17070775479078293,
|
|
"num_tokens": 21683110.0,
|
|
"step": 11085
|
|
},
|
|
{
|
|
"entropy": 6.1816877841949465,
|
|
"epoch": 1.1085620032988455,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004885737316986571,
|
|
"loss": 5.7136,
|
|
"mean_token_accuracy": 0.17947593778371812,
|
|
"num_tokens": 21692141.0,
|
|
"step": 11090
|
|
},
|
|
{
|
|
"entropy": 6.261340141296387,
|
|
"epoch": 1.109061828360074,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000488562500386023,
|
|
"loss": 5.7781,
|
|
"mean_token_accuracy": 0.1798425167798996,
|
|
"num_tokens": 21700945.0,
|
|
"step": 11095
|
|
},
|
|
{
|
|
"entropy": 6.119849157333374,
|
|
"epoch": 1.1095616534213026,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004885512637002115,
|
|
"loss": 5.707,
|
|
"mean_token_accuracy": 0.1889697015285492,
|
|
"num_tokens": 21711630.0,
|
|
"step": 11100
|
|
},
|
|
{
|
|
"entropy": 6.286618947982788,
|
|
"epoch": 1.1100614784825311,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004885400216415051,
|
|
"loss": 5.9121,
|
|
"mean_token_accuracy": 0.16180640012025832,
|
|
"num_tokens": 21721673.0,
|
|
"step": 11105
|
|
},
|
|
{
|
|
"entropy": 6.286567878723145,
|
|
"epoch": 1.1105613035437596,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004885287742101865,
|
|
"loss": 5.8044,
|
|
"mean_token_accuracy": 0.17002964466810228,
|
|
"num_tokens": 21731655.0,
|
|
"step": 11110
|
|
},
|
|
{
|
|
"entropy": 6.191099309921265,
|
|
"epoch": 1.1110611286049883,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004885175214065392,
|
|
"loss": 5.8431,
|
|
"mean_token_accuracy": 0.17173275351524353,
|
|
"num_tokens": 21741465.0,
|
|
"step": 11115
|
|
},
|
|
{
|
|
"entropy": 6.184667158126831,
|
|
"epoch": 1.1115609536662168,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004885062632308457,
|
|
"loss": 5.7709,
|
|
"mean_token_accuracy": 0.174612657725811,
|
|
"num_tokens": 21750313.0,
|
|
"step": 11120
|
|
},
|
|
{
|
|
"entropy": 6.330377864837646,
|
|
"epoch": 1.1120607787274455,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004884949996833898,
|
|
"loss": 5.877,
|
|
"mean_token_accuracy": 0.1657683029770851,
|
|
"num_tokens": 21759842.0,
|
|
"step": 11125
|
|
},
|
|
{
|
|
"entropy": 6.2540651798248295,
|
|
"epoch": 1.112560603788674,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004884837307644545,
|
|
"loss": 5.7587,
|
|
"mean_token_accuracy": 0.1823249951004982,
|
|
"num_tokens": 21770126.0,
|
|
"step": 11130
|
|
},
|
|
{
|
|
"entropy": 6.1704099655151365,
|
|
"epoch": 1.1130604288499026,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004884724564743236,
|
|
"loss": 5.6904,
|
|
"mean_token_accuracy": 0.1786607950925827,
|
|
"num_tokens": 21779878.0,
|
|
"step": 11135
|
|
},
|
|
{
|
|
"entropy": 6.251582050323487,
|
|
"epoch": 1.1135602539111311,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004884611768132805,
|
|
"loss": 5.8823,
|
|
"mean_token_accuracy": 0.16604695469141006,
|
|
"num_tokens": 21790971.0,
|
|
"step": 11140
|
|
},
|
|
{
|
|
"entropy": 6.225974798202515,
|
|
"epoch": 1.1140600789723596,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004884498917816092,
|
|
"loss": 5.8528,
|
|
"mean_token_accuracy": 0.16633085161447525,
|
|
"num_tokens": 21800733.0,
|
|
"step": 11145
|
|
},
|
|
{
|
|
"entropy": 6.230315780639648,
|
|
"epoch": 1.1145599040335883,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004884386013795935,
|
|
"loss": 5.7706,
|
|
"mean_token_accuracy": 0.17795203924179076,
|
|
"num_tokens": 21809840.0,
|
|
"step": 11150
|
|
},
|
|
{
|
|
"entropy": 6.17916464805603,
|
|
"epoch": 1.1150597290948168,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004884273056075175,
|
|
"loss": 5.7589,
|
|
"mean_token_accuracy": 0.173184684664011,
|
|
"num_tokens": 21819539.0,
|
|
"step": 11155
|
|
},
|
|
{
|
|
"entropy": 6.232099151611328,
|
|
"epoch": 1.1155595541560455,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004884160044656654,
|
|
"loss": 5.7717,
|
|
"mean_token_accuracy": 0.1776152417063713,
|
|
"num_tokens": 21829488.0,
|
|
"step": 11160
|
|
},
|
|
{
|
|
"entropy": 6.324690485000611,
|
|
"epoch": 1.116059379217274,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004884046979543217,
|
|
"loss": 5.8516,
|
|
"mean_token_accuracy": 0.17098801583051682,
|
|
"num_tokens": 21839244.0,
|
|
"step": 11165
|
|
},
|
|
{
|
|
"entropy": 6.274945831298828,
|
|
"epoch": 1.1165592042785026,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004883933860737706,
|
|
"loss": 5.943,
|
|
"mean_token_accuracy": 0.16819828897714614,
|
|
"num_tokens": 21850102.0,
|
|
"step": 11170
|
|
},
|
|
{
|
|
"entropy": 6.305516624450684,
|
|
"epoch": 1.1170590293397311,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004883820688242968,
|
|
"loss": 5.8214,
|
|
"mean_token_accuracy": 0.17000374794006348,
|
|
"num_tokens": 21860409.0,
|
|
"step": 11175
|
|
},
|
|
{
|
|
"entropy": 6.205661010742188,
|
|
"epoch": 1.1175588544009596,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004883707462061851,
|
|
"loss": 5.706,
|
|
"mean_token_accuracy": 0.16940077394247055,
|
|
"num_tokens": 21870055.0,
|
|
"step": 11180
|
|
},
|
|
{
|
|
"entropy": 6.225744390487671,
|
|
"epoch": 1.1180586794621883,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004883594182197203,
|
|
"loss": 5.8215,
|
|
"mean_token_accuracy": 0.17390751838684082,
|
|
"num_tokens": 21879103.0,
|
|
"step": 11185
|
|
},
|
|
{
|
|
"entropy": 6.232093477249146,
|
|
"epoch": 1.1185585045234168,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004883480848651875,
|
|
"loss": 5.8553,
|
|
"mean_token_accuracy": 0.17245519906282425,
|
|
"num_tokens": 21890140.0,
|
|
"step": 11190
|
|
},
|
|
{
|
|
"entropy": 6.300969743728638,
|
|
"epoch": 1.1190583295846455,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004883367461428716,
|
|
"loss": 5.9711,
|
|
"mean_token_accuracy": 0.16240259855985642,
|
|
"num_tokens": 21900917.0,
|
|
"step": 11195
|
|
},
|
|
{
|
|
"entropy": 6.323266506195068,
|
|
"epoch": 1.119558154645874,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004883254020530582,
|
|
"loss": 5.8213,
|
|
"mean_token_accuracy": 0.16755623370409012,
|
|
"num_tokens": 21910476.0,
|
|
"step": 11200
|
|
},
|
|
{
|
|
"entropy": 6.2115668773651125,
|
|
"epoch": 1.1200579797071024,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004883140525960327,
|
|
"loss": 5.7953,
|
|
"mean_token_accuracy": 0.16874418705701827,
|
|
"num_tokens": 21920219.0,
|
|
"step": 11205
|
|
},
|
|
{
|
|
"entropy": 6.260230541229248,
|
|
"epoch": 1.1205578047683311,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004883026977720803,
|
|
"loss": 5.758,
|
|
"mean_token_accuracy": 0.1783435344696045,
|
|
"num_tokens": 21930592.0,
|
|
"step": 11210
|
|
},
|
|
{
|
|
"entropy": 6.349676465988159,
|
|
"epoch": 1.1210576298295596,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000488291337581487,
|
|
"loss": 5.9695,
|
|
"mean_token_accuracy": 0.16208571046590806,
|
|
"num_tokens": 21939785.0,
|
|
"step": 11215
|
|
},
|
|
{
|
|
"entropy": 6.18541579246521,
|
|
"epoch": 1.1215574548907883,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004882799720245385,
|
|
"loss": 5.802,
|
|
"mean_token_accuracy": 0.16937464624643325,
|
|
"num_tokens": 21948243.0,
|
|
"step": 11220
|
|
},
|
|
{
|
|
"entropy": 6.221899175643921,
|
|
"epoch": 1.1220572799520168,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004882686011015208,
|
|
"loss": 5.8347,
|
|
"mean_token_accuracy": 0.16447178572416304,
|
|
"num_tokens": 21958523.0,
|
|
"step": 11225
|
|
},
|
|
{
|
|
"entropy": 6.267468547821045,
|
|
"epoch": 1.1225571050132455,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00048825722481272006,
|
|
"loss": 5.841,
|
|
"mean_token_accuracy": 0.17036356627941132,
|
|
"num_tokens": 21968685.0,
|
|
"step": 11230
|
|
},
|
|
{
|
|
"entropy": 6.267496156692505,
|
|
"epoch": 1.123056930074474,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004882458431584223,
|
|
"loss": 5.8274,
|
|
"mean_token_accuracy": 0.16776166558265687,
|
|
"num_tokens": 21979896.0,
|
|
"step": 11235
|
|
},
|
|
{
|
|
"entropy": 6.286145353317261,
|
|
"epoch": 1.1235567551357024,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004882344561389141,
|
|
"loss": 5.8199,
|
|
"mean_token_accuracy": 0.17111533582210542,
|
|
"num_tokens": 21989513.0,
|
|
"step": 11240
|
|
},
|
|
{
|
|
"entropy": 6.213821792602539,
|
|
"epoch": 1.124056580196931,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048822306375448176,
|
|
"loss": 5.7527,
|
|
"mean_token_accuracy": 0.17665089964866637,
|
|
"num_tokens": 21999238.0,
|
|
"step": 11245
|
|
},
|
|
{
|
|
"entropy": 6.195715665817261,
|
|
"epoch": 1.1245564052581596,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004882116660054121,
|
|
"loss": 5.8076,
|
|
"mean_token_accuracy": 0.1697790428996086,
|
|
"num_tokens": 22008992.0,
|
|
"step": 11250
|
|
},
|
|
{
|
|
"entropy": 6.253434085845948,
|
|
"epoch": 1.1250562303193883,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004882002628919917,
|
|
"loss": 5.7946,
|
|
"mean_token_accuracy": 0.16568599343299867,
|
|
"num_tokens": 22018333.0,
|
|
"step": 11255
|
|
},
|
|
{
|
|
"entropy": 6.2230977535247805,
|
|
"epoch": 1.1255560553806168,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004881888544145076,
|
|
"loss": 5.8261,
|
|
"mean_token_accuracy": 0.17778431624174118,
|
|
"num_tokens": 22028003.0,
|
|
"step": 11260
|
|
},
|
|
{
|
|
"entropy": 6.26422610282898,
|
|
"epoch": 1.1260558804418452,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00048817744057324673,
|
|
"loss": 5.8517,
|
|
"mean_token_accuracy": 0.16741778701543808,
|
|
"num_tokens": 22038318.0,
|
|
"step": 11265
|
|
},
|
|
{
|
|
"entropy": 6.227572011947632,
|
|
"epoch": 1.126555705503074,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048816602136849644,
|
|
"loss": 5.7957,
|
|
"mean_token_accuracy": 0.17266601026058198,
|
|
"num_tokens": 22048180.0,
|
|
"step": 11270
|
|
},
|
|
{
|
|
"entropy": 6.210058403015137,
|
|
"epoch": 1.1270555305643024,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00048815459680054375,
|
|
"loss": 5.843,
|
|
"mean_token_accuracy": 0.16334192603826522,
|
|
"num_tokens": 22057831.0,
|
|
"step": 11275
|
|
},
|
|
{
|
|
"entropy": 6.1981902599334715,
|
|
"epoch": 1.127555355625531,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00048814316686967635,
|
|
"loss": 5.7388,
|
|
"mean_token_accuracy": 0.17760446071624755,
|
|
"num_tokens": 22068569.0,
|
|
"step": 11280
|
|
},
|
|
{
|
|
"entropy": 6.292048120498658,
|
|
"epoch": 1.1280551806867596,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004881317315761817,
|
|
"loss": 5.8645,
|
|
"mean_token_accuracy": 0.1663979634642601,
|
|
"num_tokens": 22079267.0,
|
|
"step": 11285
|
|
},
|
|
{
|
|
"entropy": 6.230951881408691,
|
|
"epoch": 1.1285550057479883,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00048812029092034747,
|
|
"loss": 5.7397,
|
|
"mean_token_accuracy": 0.17749470770359038,
|
|
"num_tokens": 22089469.0,
|
|
"step": 11290
|
|
},
|
|
{
|
|
"entropy": 6.209361028671265,
|
|
"epoch": 1.1290548308092168,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00048810884490246164,
|
|
"loss": 5.7856,
|
|
"mean_token_accuracy": 0.17891596555709838,
|
|
"num_tokens": 22099148.0,
|
|
"step": 11295
|
|
},
|
|
{
|
|
"entropy": 6.249563121795655,
|
|
"epoch": 1.1295546558704452,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000488097393522812,
|
|
"loss": 5.7799,
|
|
"mean_token_accuracy": 0.1714176669716835,
|
|
"num_tokens": 22107750.0,
|
|
"step": 11300
|
|
},
|
|
{
|
|
"entropy": 6.282929134368897,
|
|
"epoch": 1.130054480931674,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004880859367816868,
|
|
"loss": 5.9008,
|
|
"mean_token_accuracy": 0.16467449367046355,
|
|
"num_tokens": 22118336.0,
|
|
"step": 11305
|
|
},
|
|
{
|
|
"entropy": 6.257660627365112,
|
|
"epoch": 1.1305543059929024,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004880744746793744,
|
|
"loss": 5.7923,
|
|
"mean_token_accuracy": 0.169712895154953,
|
|
"num_tokens": 22128166.0,
|
|
"step": 11310
|
|
},
|
|
{
|
|
"entropy": 6.248444557189941,
|
|
"epoch": 1.131054131054131,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048806300721616295,
|
|
"loss": 5.7682,
|
|
"mean_token_accuracy": 0.17098281979560853,
|
|
"num_tokens": 22136810.0,
|
|
"step": 11315
|
|
},
|
|
{
|
|
"entropy": 6.215000200271606,
|
|
"epoch": 1.1315539561153596,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048805153439234107,
|
|
"loss": 5.7507,
|
|
"mean_token_accuracy": 0.17437787503004074,
|
|
"num_tokens": 22146398.0,
|
|
"step": 11320
|
|
},
|
|
{
|
|
"entropy": 6.279124450683594,
|
|
"epoch": 1.1320537811765883,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004880400562081974,
|
|
"loss": 5.7695,
|
|
"mean_token_accuracy": 0.17660158574581147,
|
|
"num_tokens": 22155161.0,
|
|
"step": 11325
|
|
},
|
|
{
|
|
"entropy": 6.160866975784302,
|
|
"epoch": 1.1325536062378168,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00048802857266402075,
|
|
"loss": 5.8248,
|
|
"mean_token_accuracy": 0.17553698271512985,
|
|
"num_tokens": 22166486.0,
|
|
"step": 11330
|
|
},
|
|
{
|
|
"entropy": 6.168705034255981,
|
|
"epoch": 1.1330534312990452,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004880170837601,
|
|
"loss": 5.7349,
|
|
"mean_token_accuracy": 0.17527956068515776,
|
|
"num_tokens": 22176487.0,
|
|
"step": 11335
|
|
},
|
|
{
|
|
"entropy": 6.249273681640625,
|
|
"epoch": 1.133553256360274,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004880055894967242,
|
|
"loss": 5.8186,
|
|
"mean_token_accuracy": 0.1695922538638115,
|
|
"num_tokens": 22186513.0,
|
|
"step": 11340
|
|
},
|
|
{
|
|
"entropy": 6.2300482273101805,
|
|
"epoch": 1.1340530814215024,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00048799408987418264,
|
|
"loss": 5.8191,
|
|
"mean_token_accuracy": 0.17059344947338104,
|
|
"num_tokens": 22197325.0,
|
|
"step": 11345
|
|
},
|
|
{
|
|
"entropy": 6.286693525314331,
|
|
"epoch": 1.134552906482731,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048798258489276457,
|
|
"loss": 5.8141,
|
|
"mean_token_accuracy": 0.17448866814374925,
|
|
"num_tokens": 22207160.0,
|
|
"step": 11350
|
|
},
|
|
{
|
|
"entropy": 6.297756338119507,
|
|
"epoch": 1.1350527315439596,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004879710745527595,
|
|
"loss": 5.8402,
|
|
"mean_token_accuracy": 0.16751058399677277,
|
|
"num_tokens": 22216533.0,
|
|
"step": 11355
|
|
},
|
|
{
|
|
"entropy": 6.2324244499206545,
|
|
"epoch": 1.1355525566051883,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00048795955885445696,
|
|
"loss": 5.8062,
|
|
"mean_token_accuracy": 0.16794915944337846,
|
|
"num_tokens": 22226186.0,
|
|
"step": 11360
|
|
},
|
|
{
|
|
"entropy": 6.2108564376831055,
|
|
"epoch": 1.1360523816664168,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004879480377981467,
|
|
"loss": 5.7797,
|
|
"mean_token_accuracy": 0.17575025260448457,
|
|
"num_tokens": 22236315.0,
|
|
"step": 11365
|
|
},
|
|
{
|
|
"entropy": 6.275953578948974,
|
|
"epoch": 1.1365522067276452,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048793651138411866,
|
|
"loss": 5.7686,
|
|
"mean_token_accuracy": 0.17561311274766922,
|
|
"num_tokens": 22245250.0,
|
|
"step": 11370
|
|
},
|
|
{
|
|
"entropy": 6.297906541824341,
|
|
"epoch": 1.137052031788874,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00048792497961266273,
|
|
"loss": 5.8888,
|
|
"mean_token_accuracy": 0.16260171234607695,
|
|
"num_tokens": 22255093.0,
|
|
"step": 11375
|
|
},
|
|
{
|
|
"entropy": 6.129483985900879,
|
|
"epoch": 1.1375518568501024,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00048791344248406916,
|
|
"loss": 5.6856,
|
|
"mean_token_accuracy": 0.17489950209856034,
|
|
"num_tokens": 22264680.0,
|
|
"step": 11380
|
|
},
|
|
{
|
|
"entropy": 6.22161831855774,
|
|
"epoch": 1.138051681911331,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048790189999862814,
|
|
"loss": 5.8564,
|
|
"mean_token_accuracy": 0.16608163714408875,
|
|
"num_tokens": 22273804.0,
|
|
"step": 11385
|
|
},
|
|
{
|
|
"entropy": 6.224338436126709,
|
|
"epoch": 1.1385515069725596,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00048789035215663013,
|
|
"loss": 5.8084,
|
|
"mean_token_accuracy": 0.17217524945735932,
|
|
"num_tokens": 22284302.0,
|
|
"step": 11390
|
|
},
|
|
{
|
|
"entropy": 6.2500324726104735,
|
|
"epoch": 1.1390513320337883,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00048787879895836563,
|
|
"loss": 5.7674,
|
|
"mean_token_accuracy": 0.17489862889051438,
|
|
"num_tokens": 22293439.0,
|
|
"step": 11395
|
|
},
|
|
{
|
|
"entropy": 6.249682903289795,
|
|
"epoch": 1.1395511570950168,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004878672404041253,
|
|
"loss": 5.7764,
|
|
"mean_token_accuracy": 0.17816191613674165,
|
|
"num_tokens": 22303005.0,
|
|
"step": 11400
|
|
},
|
|
{
|
|
"entropy": 6.2065142631530765,
|
|
"epoch": 1.1400509821562452,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00048785567649419994,
|
|
"loss": 5.7122,
|
|
"mean_token_accuracy": 0.17510510385036468,
|
|
"num_tokens": 22311962.0,
|
|
"step": 11405
|
|
},
|
|
{
|
|
"entropy": 6.193663597106934,
|
|
"epoch": 1.140550807217474,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004878441072288806,
|
|
"loss": 5.8106,
|
|
"mean_token_accuracy": 0.1643409550189972,
|
|
"num_tokens": 22320998.0,
|
|
"step": 11410
|
|
},
|
|
{
|
|
"entropy": 6.245450830459594,
|
|
"epoch": 1.1410506322787024,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048783253260845826,
|
|
"loss": 5.7595,
|
|
"mean_token_accuracy": 0.17526543959975244,
|
|
"num_tokens": 22330977.0,
|
|
"step": 11415
|
|
},
|
|
{
|
|
"entropy": 6.272841262817383,
|
|
"epoch": 1.141550457339931,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004878209526332242,
|
|
"loss": 5.7694,
|
|
"mean_token_accuracy": 0.17807236462831497,
|
|
"num_tokens": 22341287.0,
|
|
"step": 11420
|
|
},
|
|
{
|
|
"entropy": 6.19141731262207,
|
|
"epoch": 1.1420502824011596,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048780936730346967,
|
|
"loss": 5.7498,
|
|
"mean_token_accuracy": 0.18042602837085725,
|
|
"num_tokens": 22350507.0,
|
|
"step": 11425
|
|
},
|
|
{
|
|
"entropy": 6.278623819351196,
|
|
"epoch": 1.1425501074623883,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00048779777661948627,
|
|
"loss": 5.8713,
|
|
"mean_token_accuracy": 0.16439569294452666,
|
|
"num_tokens": 22361202.0,
|
|
"step": 11430
|
|
},
|
|
{
|
|
"entropy": 6.297684001922607,
|
|
"epoch": 1.1430499325236168,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004877861805815655,
|
|
"loss": 5.8532,
|
|
"mean_token_accuracy": 0.17978796362876892,
|
|
"num_tokens": 22370824.0,
|
|
"step": 11435
|
|
},
|
|
{
|
|
"entropy": 6.195598316192627,
|
|
"epoch": 1.1435497575848452,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004877745791899993,
|
|
"loss": 5.7459,
|
|
"mean_token_accuracy": 0.17266987264156342,
|
|
"num_tokens": 22380857.0,
|
|
"step": 11440
|
|
},
|
|
{
|
|
"entropy": 6.275242567062378,
|
|
"epoch": 1.144049582646074,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048776297244507936,
|
|
"loss": 5.7679,
|
|
"mean_token_accuracy": 0.17133274227380751,
|
|
"num_tokens": 22391354.0,
|
|
"step": 11445
|
|
},
|
|
{
|
|
"entropy": 6.250203657150268,
|
|
"epoch": 1.1445494077073024,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00048775136034709784,
|
|
"loss": 5.7173,
|
|
"mean_token_accuracy": 0.17875710278749465,
|
|
"num_tokens": 22400656.0,
|
|
"step": 11450
|
|
},
|
|
{
|
|
"entropy": 6.192895078659058,
|
|
"epoch": 1.145049232768531,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048773974289634676,
|
|
"loss": 5.8046,
|
|
"mean_token_accuracy": 0.16348920166492462,
|
|
"num_tokens": 22410887.0,
|
|
"step": 11455
|
|
},
|
|
{
|
|
"entropy": 6.267591142654419,
|
|
"epoch": 1.1455490578297596,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004877281200931185,
|
|
"loss": 5.7801,
|
|
"mean_token_accuracy": 0.1711859256029129,
|
|
"num_tokens": 22420370.0,
|
|
"step": 11460
|
|
},
|
|
{
|
|
"entropy": 6.192070341110229,
|
|
"epoch": 1.1460488828909883,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048771649193770554,
|
|
"loss": 5.6967,
|
|
"mean_token_accuracy": 0.17962920665740967,
|
|
"num_tokens": 22430746.0,
|
|
"step": 11465
|
|
},
|
|
{
|
|
"entropy": 6.228785419464112,
|
|
"epoch": 1.1465487079522168,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004877048584304004,
|
|
"loss": 5.7584,
|
|
"mean_token_accuracy": 0.17389902472496033,
|
|
"num_tokens": 22440812.0,
|
|
"step": 11470
|
|
},
|
|
{
|
|
"entropy": 6.2580712795257565,
|
|
"epoch": 1.1470485330134452,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048769321957149557,
|
|
"loss": 5.8776,
|
|
"mean_token_accuracy": 0.17196998447179795,
|
|
"num_tokens": 22450460.0,
|
|
"step": 11475
|
|
},
|
|
{
|
|
"entropy": 6.260286426544189,
|
|
"epoch": 1.147548358074674,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004876815753612843,
|
|
"loss": 5.788,
|
|
"mean_token_accuracy": 0.17571775019168853,
|
|
"num_tokens": 22460660.0,
|
|
"step": 11480
|
|
},
|
|
{
|
|
"entropy": 6.205839681625366,
|
|
"epoch": 1.1480481831359024,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004876699258000592,
|
|
"loss": 5.6851,
|
|
"mean_token_accuracy": 0.18637544214725493,
|
|
"num_tokens": 22469238.0,
|
|
"step": 11485
|
|
},
|
|
{
|
|
"entropy": 6.166919565200805,
|
|
"epoch": 1.148548008197131,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004876582708881135,
|
|
"loss": 5.7626,
|
|
"mean_token_accuracy": 0.1733090713620186,
|
|
"num_tokens": 22479685.0,
|
|
"step": 11490
|
|
},
|
|
{
|
|
"entropy": 6.19241156578064,
|
|
"epoch": 1.1490478332583596,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004876466106257404,
|
|
"loss": 5.6989,
|
|
"mean_token_accuracy": 0.17900993227958678,
|
|
"num_tokens": 22489770.0,
|
|
"step": 11495
|
|
},
|
|
{
|
|
"entropy": 6.312437343597412,
|
|
"epoch": 1.149547658319588,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00048763494501323333,
|
|
"loss": 5.8788,
|
|
"mean_token_accuracy": 0.17433477193117142,
|
|
"num_tokens": 22499957.0,
|
|
"step": 11500
|
|
},
|
|
{
|
|
"entropy": 6.231788635253906,
|
|
"epoch": 1.1500474833808167,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00048762327405088573,
|
|
"loss": 5.7216,
|
|
"mean_token_accuracy": 0.17455048859119415,
|
|
"num_tokens": 22508863.0,
|
|
"step": 11505
|
|
},
|
|
{
|
|
"entropy": 6.254695796966553,
|
|
"epoch": 1.1505473084420452,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004876115977389913,
|
|
"loss": 5.7758,
|
|
"mean_token_accuracy": 0.17207019478082658,
|
|
"num_tokens": 22517563.0,
|
|
"step": 11510
|
|
},
|
|
{
|
|
"entropy": 6.055664873123169,
|
|
"epoch": 1.151047133503274,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00048759991607784375,
|
|
"loss": 5.6541,
|
|
"mean_token_accuracy": 0.18784307241439818,
|
|
"num_tokens": 22527907.0,
|
|
"step": 11515
|
|
},
|
|
{
|
|
"entropy": 6.161161994934082,
|
|
"epoch": 1.1515469585645024,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048758822906773706,
|
|
"loss": 5.7347,
|
|
"mean_token_accuracy": 0.18115518987178802,
|
|
"num_tokens": 22537373.0,
|
|
"step": 11520
|
|
},
|
|
{
|
|
"entropy": 6.277247714996338,
|
|
"epoch": 1.1520467836257309,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048757653670896523,
|
|
"loss": 5.8664,
|
|
"mean_token_accuracy": 0.16633794605731964,
|
|
"num_tokens": 22547851.0,
|
|
"step": 11525
|
|
},
|
|
{
|
|
"entropy": 6.346578788757324,
|
|
"epoch": 1.1525466086869596,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004875648390018224,
|
|
"loss": 5.822,
|
|
"mean_token_accuracy": 0.17160701602697373,
|
|
"num_tokens": 22558127.0,
|
|
"step": 11530
|
|
},
|
|
{
|
|
"entropy": 6.206993436813354,
|
|
"epoch": 1.153046433748188,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000487553135946603,
|
|
"loss": 5.8544,
|
|
"mean_token_accuracy": 0.17372671961784364,
|
|
"num_tokens": 22568151.0,
|
|
"step": 11535
|
|
},
|
|
{
|
|
"entropy": 6.2295331954956055,
|
|
"epoch": 1.1535462588094167,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048754142754360135,
|
|
"loss": 5.8545,
|
|
"mean_token_accuracy": 0.16850703060626984,
|
|
"num_tokens": 22579772.0,
|
|
"step": 11540
|
|
},
|
|
{
|
|
"entropy": 6.225022554397583,
|
|
"epoch": 1.1540460838706452,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004875297137931121,
|
|
"loss": 5.8217,
|
|
"mean_token_accuracy": 0.17327682226896285,
|
|
"num_tokens": 22589551.0,
|
|
"step": 11545
|
|
},
|
|
{
|
|
"entropy": 6.2604066848754885,
|
|
"epoch": 1.154545908931874,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004875179946954298,
|
|
"loss": 5.8109,
|
|
"mean_token_accuracy": 0.17013591080904006,
|
|
"num_tokens": 22599139.0,
|
|
"step": 11550
|
|
},
|
|
{
|
|
"entropy": 6.324815654754639,
|
|
"epoch": 1.1550457339931024,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00048750627025084955,
|
|
"loss": 5.9307,
|
|
"mean_token_accuracy": 0.1601591795682907,
|
|
"num_tokens": 22609413.0,
|
|
"step": 11555
|
|
},
|
|
{
|
|
"entropy": 6.292019033432007,
|
|
"epoch": 1.1555455590543309,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004874945404596662,
|
|
"loss": 5.9057,
|
|
"mean_token_accuracy": 0.16681761145591736,
|
|
"num_tokens": 22619395.0,
|
|
"step": 11560
|
|
},
|
|
{
|
|
"entropy": 6.161822748184204,
|
|
"epoch": 1.1560453841155596,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048748280532217485,
|
|
"loss": 5.7211,
|
|
"mean_token_accuracy": 0.18740075826644897,
|
|
"num_tokens": 22629623.0,
|
|
"step": 11565
|
|
},
|
|
{
|
|
"entropy": 6.183514404296875,
|
|
"epoch": 1.156545209176788,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004874710648386709,
|
|
"loss": 5.7647,
|
|
"mean_token_accuracy": 0.17832190990448,
|
|
"num_tokens": 22639735.0,
|
|
"step": 11570
|
|
},
|
|
{
|
|
"entropy": 6.253946018218994,
|
|
"epoch": 1.1570450342380167,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004874593190094496,
|
|
"loss": 5.6881,
|
|
"mean_token_accuracy": 0.17365914732217788,
|
|
"num_tokens": 22648563.0,
|
|
"step": 11575
|
|
},
|
|
{
|
|
"entropy": 6.207092380523681,
|
|
"epoch": 1.1575448592992452,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004874475678348065,
|
|
"loss": 5.7538,
|
|
"mean_token_accuracy": 0.1761752799153328,
|
|
"num_tokens": 22657137.0,
|
|
"step": 11580
|
|
},
|
|
{
|
|
"entropy": 6.1642731666564945,
|
|
"epoch": 1.158044684360474,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048743581131503716,
|
|
"loss": 5.6986,
|
|
"mean_token_accuracy": 0.18019605427980423,
|
|
"num_tokens": 22667987.0,
|
|
"step": 11585
|
|
},
|
|
{
|
|
"entropy": 6.199779844284057,
|
|
"epoch": 1.1585445094217024,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004874240494504376,
|
|
"loss": 5.841,
|
|
"mean_token_accuracy": 0.1675383284687996,
|
|
"num_tokens": 22678830.0,
|
|
"step": 11590
|
|
},
|
|
{
|
|
"entropy": 6.309087181091309,
|
|
"epoch": 1.1590443344829309,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00048741228224130357,
|
|
"loss": 5.8364,
|
|
"mean_token_accuracy": 0.167610801756382,
|
|
"num_tokens": 22690568.0,
|
|
"step": 11595
|
|
},
|
|
{
|
|
"entropy": 6.303432846069336,
|
|
"epoch": 1.1595441595441596,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00048740050968793116,
|
|
"loss": 5.8337,
|
|
"mean_token_accuracy": 0.17321670949459075,
|
|
"num_tokens": 22700150.0,
|
|
"step": 11600
|
|
},
|
|
{
|
|
"entropy": 6.164283990859985,
|
|
"epoch": 1.160043984605388,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004873887317906166,
|
|
"loss": 5.7288,
|
|
"mean_token_accuracy": 0.17709567546844482,
|
|
"num_tokens": 22709365.0,
|
|
"step": 11605
|
|
},
|
|
{
|
|
"entropy": 6.330613279342652,
|
|
"epoch": 1.1605438096666167,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048737694854965617,
|
|
"loss": 5.9065,
|
|
"mean_token_accuracy": 0.16375362426042556,
|
|
"num_tokens": 22718636.0,
|
|
"step": 11610
|
|
},
|
|
{
|
|
"entropy": 6.296670722961426,
|
|
"epoch": 1.1610436347278452,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048736515996534644,
|
|
"loss": 5.8755,
|
|
"mean_token_accuracy": 0.16586533635854722,
|
|
"num_tokens": 22728713.0,
|
|
"step": 11615
|
|
},
|
|
{
|
|
"entropy": 6.178993082046508,
|
|
"epoch": 1.161543459789074,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004873533660379839,
|
|
"loss": 5.6151,
|
|
"mean_token_accuracy": 0.18736892193555832,
|
|
"num_tokens": 22739061.0,
|
|
"step": 11620
|
|
},
|
|
{
|
|
"entropy": 6.282159280776978,
|
|
"epoch": 1.1620432848503024,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048734156676786525,
|
|
"loss": 5.8195,
|
|
"mean_token_accuracy": 0.17118745446205139,
|
|
"num_tokens": 22748752.0,
|
|
"step": 11625
|
|
},
|
|
{
|
|
"entropy": 6.185739660263062,
|
|
"epoch": 1.1625431099115309,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004873297621552875,
|
|
"loss": 5.7217,
|
|
"mean_token_accuracy": 0.18202030807733535,
|
|
"num_tokens": 22758695.0,
|
|
"step": 11630
|
|
},
|
|
{
|
|
"entropy": 6.250395679473877,
|
|
"epoch": 1.1630429349727596,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00048731795220054755,
|
|
"loss": 5.8443,
|
|
"mean_token_accuracy": 0.17217816561460494,
|
|
"num_tokens": 22768948.0,
|
|
"step": 11635
|
|
},
|
|
{
|
|
"entropy": 6.280606412887574,
|
|
"epoch": 1.163542760033988,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004873061369039425,
|
|
"loss": 5.8239,
|
|
"mean_token_accuracy": 0.16938796639442444,
|
|
"num_tokens": 22779446.0,
|
|
"step": 11640
|
|
},
|
|
{
|
|
"entropy": 6.192312717437744,
|
|
"epoch": 1.1640425850952167,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004872943162657697,
|
|
"loss": 5.7523,
|
|
"mean_token_accuracy": 0.17236933410167693,
|
|
"num_tokens": 22789654.0,
|
|
"step": 11645
|
|
},
|
|
{
|
|
"entropy": 6.206375169754028,
|
|
"epoch": 1.1645424101564452,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004872824902863265,
|
|
"loss": 5.8384,
|
|
"mean_token_accuracy": 0.17297943085432052,
|
|
"num_tokens": 22798938.0,
|
|
"step": 11650
|
|
},
|
|
{
|
|
"entropy": 6.217448139190674,
|
|
"epoch": 1.165042235217674,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004872706589659106,
|
|
"loss": 5.8212,
|
|
"mean_token_accuracy": 0.1740794748067856,
|
|
"num_tokens": 22808279.0,
|
|
"step": 11655
|
|
},
|
|
{
|
|
"entropy": 6.227861833572388,
|
|
"epoch": 1.1655420602789024,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048725882230481947,
|
|
"loss": 5.7624,
|
|
"mean_token_accuracy": 0.17256905734539033,
|
|
"num_tokens": 22817378.0,
|
|
"step": 11660
|
|
},
|
|
{
|
|
"entropy": 6.320417165756226,
|
|
"epoch": 1.1660418853401309,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048724698030335096,
|
|
"loss": 5.8148,
|
|
"mean_token_accuracy": 0.17388846129179,
|
|
"num_tokens": 22828652.0,
|
|
"step": 11665
|
|
},
|
|
{
|
|
"entropy": 6.215070533752441,
|
|
"epoch": 1.1665417104013596,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004872351329618031,
|
|
"loss": 5.7966,
|
|
"mean_token_accuracy": 0.17438552528619766,
|
|
"num_tokens": 22839156.0,
|
|
"step": 11670
|
|
},
|
|
{
|
|
"entropy": 6.260087203979492,
|
|
"epoch": 1.167041535462588,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048722328028047386,
|
|
"loss": 5.878,
|
|
"mean_token_accuracy": 0.167583866417408,
|
|
"num_tokens": 22849004.0,
|
|
"step": 11675
|
|
},
|
|
{
|
|
"entropy": 6.224007558822632,
|
|
"epoch": 1.1675413605238167,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048721142225966146,
|
|
"loss": 5.8592,
|
|
"mean_token_accuracy": 0.16705726683139802,
|
|
"num_tokens": 22858984.0,
|
|
"step": 11680
|
|
},
|
|
{
|
|
"entropy": 6.2448930740356445,
|
|
"epoch": 1.1680411855850452,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004871995588996644,
|
|
"loss": 5.7685,
|
|
"mean_token_accuracy": 0.17646801918745042,
|
|
"num_tokens": 22869149.0,
|
|
"step": 11685
|
|
},
|
|
{
|
|
"entropy": 6.265959453582764,
|
|
"epoch": 1.168541010646274,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004871876902007809,
|
|
"loss": 5.9141,
|
|
"mean_token_accuracy": 0.16858813315629959,
|
|
"num_tokens": 22878522.0,
|
|
"step": 11690
|
|
},
|
|
{
|
|
"entropy": 6.234499216079712,
|
|
"epoch": 1.1690408357075024,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048717581616330985,
|
|
"loss": 5.8006,
|
|
"mean_token_accuracy": 0.17167114168405534,
|
|
"num_tokens": 22888356.0,
|
|
"step": 11695
|
|
},
|
|
{
|
|
"entropy": 6.242793989181519,
|
|
"epoch": 1.1695406607687309,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048716393678754975,
|
|
"loss": 5.7851,
|
|
"mean_token_accuracy": 0.17486385703086854,
|
|
"num_tokens": 22897551.0,
|
|
"step": 11700
|
|
},
|
|
{
|
|
"entropy": 6.250674295425415,
|
|
"epoch": 1.1700404858299596,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004871520520737996,
|
|
"loss": 5.7755,
|
|
"mean_token_accuracy": 0.17462820708751678,
|
|
"num_tokens": 22906480.0,
|
|
"step": 11705
|
|
},
|
|
{
|
|
"entropy": 6.165285301208496,
|
|
"epoch": 1.170540310891188,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004871401620223585,
|
|
"loss": 5.648,
|
|
"mean_token_accuracy": 0.1808565601706505,
|
|
"num_tokens": 22916544.0,
|
|
"step": 11710
|
|
},
|
|
{
|
|
"entropy": 6.170183324813843,
|
|
"epoch": 1.1710401359524167,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004871282666335255,
|
|
"loss": 5.6921,
|
|
"mean_token_accuracy": 0.18393508940935135,
|
|
"num_tokens": 22926083.0,
|
|
"step": 11715
|
|
},
|
|
{
|
|
"entropy": 6.306354188919068,
|
|
"epoch": 1.1715399610136452,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00048711636590759985,
|
|
"loss": 5.8208,
|
|
"mean_token_accuracy": 0.17299528419971466,
|
|
"num_tokens": 22936127.0,
|
|
"step": 11720
|
|
},
|
|
{
|
|
"entropy": 6.2306019306182865,
|
|
"epoch": 1.172039786074874,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00048710445984488106,
|
|
"loss": 5.7471,
|
|
"mean_token_accuracy": 0.17546326816082,
|
|
"num_tokens": 22946579.0,
|
|
"step": 11725
|
|
},
|
|
{
|
|
"entropy": 6.210904264450074,
|
|
"epoch": 1.1725396111361024,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004870925484456686,
|
|
"loss": 5.7837,
|
|
"mean_token_accuracy": 0.17980627566576005,
|
|
"num_tokens": 22956286.0,
|
|
"step": 11730
|
|
},
|
|
{
|
|
"entropy": 6.254963493347168,
|
|
"epoch": 1.1730394361973309,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004870806317102622,
|
|
"loss": 5.8336,
|
|
"mean_token_accuracy": 0.17119556218385695,
|
|
"num_tokens": 22965625.0,
|
|
"step": 11735
|
|
},
|
|
{
|
|
"entropy": 6.266835117340088,
|
|
"epoch": 1.1735392612585596,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004870687096389617,
|
|
"loss": 5.8427,
|
|
"mean_token_accuracy": 0.173385888338089,
|
|
"num_tokens": 22975853.0,
|
|
"step": 11740
|
|
},
|
|
{
|
|
"entropy": 6.2358283519744875,
|
|
"epoch": 1.174039086319788,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000487056782232067,
|
|
"loss": 5.8583,
|
|
"mean_token_accuracy": 0.16386536359786988,
|
|
"num_tokens": 22985928.0,
|
|
"step": 11745
|
|
},
|
|
{
|
|
"entropy": 6.253842878341675,
|
|
"epoch": 1.1745389113810167,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048704484948987824,
|
|
"loss": 5.8047,
|
|
"mean_token_accuracy": 0.17551685273647308,
|
|
"num_tokens": 22995222.0,
|
|
"step": 11750
|
|
},
|
|
{
|
|
"entropy": 6.27478928565979,
|
|
"epoch": 1.1750387364422452,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004870329114126956,
|
|
"loss": 5.7776,
|
|
"mean_token_accuracy": 0.1720517545938492,
|
|
"num_tokens": 23005735.0,
|
|
"step": 11755
|
|
},
|
|
{
|
|
"entropy": 6.228629732131958,
|
|
"epoch": 1.1755385615034737,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004870209680008196,
|
|
"loss": 5.7461,
|
|
"mean_token_accuracy": 0.17352901697158812,
|
|
"num_tokens": 23016198.0,
|
|
"step": 11760
|
|
},
|
|
{
|
|
"entropy": 6.2304408073425295,
|
|
"epoch": 1.1760383865647024,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004870090192545505,
|
|
"loss": 5.8207,
|
|
"mean_token_accuracy": 0.16388765424489976,
|
|
"num_tokens": 23025927.0,
|
|
"step": 11765
|
|
},
|
|
{
|
|
"entropy": 6.241334915161133,
|
|
"epoch": 1.1765382116259309,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000486997065174189,
|
|
"loss": 5.634,
|
|
"mean_token_accuracy": 0.18559691905975342,
|
|
"num_tokens": 23034626.0,
|
|
"step": 11770
|
|
},
|
|
{
|
|
"entropy": 6.215415716171265,
|
|
"epoch": 1.1770380366871596,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00048698510576003593,
|
|
"loss": 5.7383,
|
|
"mean_token_accuracy": 0.17484647333621978,
|
|
"num_tokens": 23045773.0,
|
|
"step": 11775
|
|
},
|
|
{
|
|
"entropy": 6.217964601516724,
|
|
"epoch": 1.177537861748388,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00048697314101239217,
|
|
"loss": 5.7167,
|
|
"mean_token_accuracy": 0.17458052337169647,
|
|
"num_tokens": 23056803.0,
|
|
"step": 11780
|
|
},
|
|
{
|
|
"entropy": 6.2117737293243405,
|
|
"epoch": 1.1780376868096165,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004869611709315587,
|
|
"loss": 5.812,
|
|
"mean_token_accuracy": 0.16732523441314698,
|
|
"num_tokens": 23066513.0,
|
|
"step": 11785
|
|
},
|
|
{
|
|
"entropy": 6.247967624664307,
|
|
"epoch": 1.1785375118708452,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00048694919551783665,
|
|
"loss": 5.805,
|
|
"mean_token_accuracy": 0.1688837394118309,
|
|
"num_tokens": 23077309.0,
|
|
"step": 11790
|
|
},
|
|
{
|
|
"entropy": 6.182036066055298,
|
|
"epoch": 1.1790373369320737,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00048693721477152755,
|
|
"loss": 5.7361,
|
|
"mean_token_accuracy": 0.1818900302052498,
|
|
"num_tokens": 23088292.0,
|
|
"step": 11795
|
|
},
|
|
{
|
|
"entropy": 6.256971216201782,
|
|
"epoch": 1.1795371619933024,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00048692522869293246,
|
|
"loss": 5.7431,
|
|
"mean_token_accuracy": 0.17318976074457168,
|
|
"num_tokens": 23098744.0,
|
|
"step": 11800
|
|
},
|
|
{
|
|
"entropy": 6.217524099349975,
|
|
"epoch": 1.1800369870545309,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004869132372823533,
|
|
"loss": 5.7213,
|
|
"mean_token_accuracy": 0.1842671513557434,
|
|
"num_tokens": 23108223.0,
|
|
"step": 11805
|
|
},
|
|
{
|
|
"entropy": 6.216798305511475,
|
|
"epoch": 1.1805368121157596,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048690124054009157,
|
|
"loss": 5.8225,
|
|
"mean_token_accuracy": 0.16841964274644852,
|
|
"num_tokens": 23118595.0,
|
|
"step": 11810
|
|
},
|
|
{
|
|
"entropy": 6.206343698501587,
|
|
"epoch": 1.181036637176988,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004868892384664491,
|
|
"loss": 5.6585,
|
|
"mean_token_accuracy": 0.18642991185188293,
|
|
"num_tokens": 23127640.0,
|
|
"step": 11815
|
|
},
|
|
{
|
|
"entropy": 6.258758974075318,
|
|
"epoch": 1.1815364622382165,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048687723106172805,
|
|
"loss": 5.8036,
|
|
"mean_token_accuracy": 0.16908579617738723,
|
|
"num_tokens": 23138409.0,
|
|
"step": 11820
|
|
},
|
|
{
|
|
"entropy": 6.194532346725464,
|
|
"epoch": 1.1820362872994452,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048686521832623026,
|
|
"loss": 5.7578,
|
|
"mean_token_accuracy": 0.1751507729291916,
|
|
"num_tokens": 23148427.0,
|
|
"step": 11825
|
|
},
|
|
{
|
|
"entropy": 6.202616119384766,
|
|
"epoch": 1.1825361123606737,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004868532002602581,
|
|
"loss": 5.772,
|
|
"mean_token_accuracy": 0.17785236835479737,
|
|
"num_tokens": 23157873.0,
|
|
"step": 11830
|
|
},
|
|
{
|
|
"entropy": 6.2059389591217045,
|
|
"epoch": 1.1830359374219024,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000486841176864114,
|
|
"loss": 5.7247,
|
|
"mean_token_accuracy": 0.17895689159631728,
|
|
"num_tokens": 23166488.0,
|
|
"step": 11835
|
|
},
|
|
{
|
|
"entropy": 6.154409503936767,
|
|
"epoch": 1.1835357624831309,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00048682914813810035,
|
|
"loss": 5.6937,
|
|
"mean_token_accuracy": 0.18015661537647248,
|
|
"num_tokens": 23176548.0,
|
|
"step": 11840
|
|
},
|
|
{
|
|
"entropy": 6.126815414428711,
|
|
"epoch": 1.1840355875443596,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048681711408251986,
|
|
"loss": 5.7561,
|
|
"mean_token_accuracy": 0.1695359542965889,
|
|
"num_tokens": 23186269.0,
|
|
"step": 11845
|
|
},
|
|
{
|
|
"entropy": 6.211962795257568,
|
|
"epoch": 1.184535412605588,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048680507469767533,
|
|
"loss": 5.6806,
|
|
"mean_token_accuracy": 0.18431740403175353,
|
|
"num_tokens": 23197181.0,
|
|
"step": 11850
|
|
},
|
|
{
|
|
"entropy": 6.22867865562439,
|
|
"epoch": 1.1850352376668165,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004867930299838696,
|
|
"loss": 5.7213,
|
|
"mean_token_accuracy": 0.1800643503665924,
|
|
"num_tokens": 23207391.0,
|
|
"step": 11855
|
|
},
|
|
{
|
|
"entropy": 6.343985748291016,
|
|
"epoch": 1.1855350627280452,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00048678097994140566,
|
|
"loss": 5.9111,
|
|
"mean_token_accuracy": 0.17081436216831208,
|
|
"num_tokens": 23217510.0,
|
|
"step": 11860
|
|
},
|
|
{
|
|
"entropy": 6.097823810577393,
|
|
"epoch": 1.1860348877892737,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048676892457058687,
|
|
"loss": 5.6679,
|
|
"mean_token_accuracy": 0.18267852216959,
|
|
"num_tokens": 23226746.0,
|
|
"step": 11865
|
|
},
|
|
{
|
|
"entropy": 6.1849600315094,
|
|
"epoch": 1.1865347128505024,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004867568638717164,
|
|
"loss": 5.8499,
|
|
"mean_token_accuracy": 0.16654213517904282,
|
|
"num_tokens": 23236333.0,
|
|
"step": 11870
|
|
},
|
|
{
|
|
"entropy": 6.228284740447998,
|
|
"epoch": 1.1870345379117309,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048674479784509766,
|
|
"loss": 5.6477,
|
|
"mean_token_accuracy": 0.18097325414419174,
|
|
"num_tokens": 23245071.0,
|
|
"step": 11875
|
|
},
|
|
{
|
|
"entropy": 6.184589481353759,
|
|
"epoch": 1.1875343629729596,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00048673272649103435,
|
|
"loss": 5.7298,
|
|
"mean_token_accuracy": 0.18016175627708436,
|
|
"num_tokens": 23254225.0,
|
|
"step": 11880
|
|
},
|
|
{
|
|
"entropy": 6.189892673492432,
|
|
"epoch": 1.188034188034188,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00048672064980983013,
|
|
"loss": 5.7334,
|
|
"mean_token_accuracy": 0.1795118883252144,
|
|
"num_tokens": 23264822.0,
|
|
"step": 11885
|
|
},
|
|
{
|
|
"entropy": 6.246009826660156,
|
|
"epoch": 1.1885340130954165,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00048670856780178874,
|
|
"loss": 5.8661,
|
|
"mean_token_accuracy": 0.16989630311727524,
|
|
"num_tokens": 23274559.0,
|
|
"step": 11890
|
|
},
|
|
{
|
|
"entropy": 6.2050745487213135,
|
|
"epoch": 1.1890338381566452,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048669648046721436,
|
|
"loss": 5.7978,
|
|
"mean_token_accuracy": 0.18016422539949417,
|
|
"num_tokens": 23284431.0,
|
|
"step": 11895
|
|
},
|
|
{
|
|
"entropy": 6.2322712421417235,
|
|
"epoch": 1.1895336632178737,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000486684387806411,
|
|
"loss": 5.8227,
|
|
"mean_token_accuracy": 0.16876443326473237,
|
|
"num_tokens": 23294814.0,
|
|
"step": 11900
|
|
},
|
|
{
|
|
"entropy": 6.2888512134552,
|
|
"epoch": 1.1900334882791024,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00048667228981968285,
|
|
"loss": 5.802,
|
|
"mean_token_accuracy": 0.16985612064599992,
|
|
"num_tokens": 23304701.0,
|
|
"step": 11905
|
|
},
|
|
{
|
|
"entropy": 6.340728712081909,
|
|
"epoch": 1.1905333133403309,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00048666018650733446,
|
|
"loss": 5.8472,
|
|
"mean_token_accuracy": 0.16559213250875474,
|
|
"num_tokens": 23314335.0,
|
|
"step": 11910
|
|
},
|
|
{
|
|
"entropy": 6.235889482498169,
|
|
"epoch": 1.1910331384015596,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004866480778696702,
|
|
"loss": 5.8362,
|
|
"mean_token_accuracy": 0.17277292162179947,
|
|
"num_tokens": 23324591.0,
|
|
"step": 11915
|
|
},
|
|
{
|
|
"entropy": 6.174012279510498,
|
|
"epoch": 1.191532963462788,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00048663596390699477,
|
|
"loss": 5.7728,
|
|
"mean_token_accuracy": 0.1783072382211685,
|
|
"num_tokens": 23334682.0,
|
|
"step": 11920
|
|
},
|
|
{
|
|
"entropy": 6.257135105133057,
|
|
"epoch": 1.1920327885240165,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004866238446196129,
|
|
"loss": 5.777,
|
|
"mean_token_accuracy": 0.17837144136428834,
|
|
"num_tokens": 23343943.0,
|
|
"step": 11925
|
|
},
|
|
{
|
|
"entropy": 6.206888628005982,
|
|
"epoch": 1.1925326135852452,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004866117200078296,
|
|
"loss": 5.7381,
|
|
"mean_token_accuracy": 0.17273104935884476,
|
|
"num_tokens": 23354031.0,
|
|
"step": 11930
|
|
},
|
|
{
|
|
"entropy": 6.249147891998291,
|
|
"epoch": 1.1930324386464737,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00048659959007194985,
|
|
"loss": 5.8442,
|
|
"mean_token_accuracy": 0.17439647167921066,
|
|
"num_tokens": 23363922.0,
|
|
"step": 11935
|
|
},
|
|
{
|
|
"entropy": 6.270565843582153,
|
|
"epoch": 1.1935322637077024,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048658745481227884,
|
|
"loss": 5.8393,
|
|
"mean_token_accuracy": 0.16836244612932205,
|
|
"num_tokens": 23372552.0,
|
|
"step": 11940
|
|
},
|
|
{
|
|
"entropy": 6.148928833007813,
|
|
"epoch": 1.1940320887689309,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000486575314229122,
|
|
"loss": 5.7533,
|
|
"mean_token_accuracy": 0.18450981378555298,
|
|
"num_tokens": 23383454.0,
|
|
"step": 11945
|
|
},
|
|
{
|
|
"entropy": 6.243237638473511,
|
|
"epoch": 1.1945319138301596,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004865631683227846,
|
|
"loss": 5.8062,
|
|
"mean_token_accuracy": 0.16754890382289886,
|
|
"num_tokens": 23393429.0,
|
|
"step": 11950
|
|
},
|
|
{
|
|
"entropy": 6.243479919433594,
|
|
"epoch": 1.195031738891388,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048655101709357243,
|
|
"loss": 5.7234,
|
|
"mean_token_accuracy": 0.17615862041711808,
|
|
"num_tokens": 23403742.0,
|
|
"step": 11955
|
|
},
|
|
{
|
|
"entropy": 6.192641878128052,
|
|
"epoch": 1.1955315639526165,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000486538860541791,
|
|
"loss": 5.7204,
|
|
"mean_token_accuracy": 0.1709155723452568,
|
|
"num_tokens": 23412875.0,
|
|
"step": 11960
|
|
},
|
|
{
|
|
"entropy": 6.2503632545471195,
|
|
"epoch": 1.1960313890138452,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048652669866774636,
|
|
"loss": 5.8048,
|
|
"mean_token_accuracy": 0.17032048851251602,
|
|
"num_tokens": 23422838.0,
|
|
"step": 11965
|
|
},
|
|
{
|
|
"entropy": 6.270262336730957,
|
|
"epoch": 1.1965312140750737,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004865145314717443,
|
|
"loss": 5.7832,
|
|
"mean_token_accuracy": 0.16736376658082008,
|
|
"num_tokens": 23431407.0,
|
|
"step": 11970
|
|
},
|
|
{
|
|
"entropy": 6.1491631984710695,
|
|
"epoch": 1.1970310391363024,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048650235895409115,
|
|
"loss": 5.7724,
|
|
"mean_token_accuracy": 0.18049606382846833,
|
|
"num_tokens": 23441580.0,
|
|
"step": 11975
|
|
},
|
|
{
|
|
"entropy": 6.219580602645874,
|
|
"epoch": 1.1975308641975309,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004864901811150931,
|
|
"loss": 5.8365,
|
|
"mean_token_accuracy": 0.16937092393636705,
|
|
"num_tokens": 23451508.0,
|
|
"step": 11980
|
|
},
|
|
{
|
|
"entropy": 6.2540247440338135,
|
|
"epoch": 1.1980306892587596,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004864779979550564,
|
|
"loss": 5.7996,
|
|
"mean_token_accuracy": 0.1720472827553749,
|
|
"num_tokens": 23461928.0,
|
|
"step": 11985
|
|
},
|
|
{
|
|
"entropy": 6.2472617626190186,
|
|
"epoch": 1.198530514319988,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004864658094742878,
|
|
"loss": 5.7626,
|
|
"mean_token_accuracy": 0.17643257826566697,
|
|
"num_tokens": 23471501.0,
|
|
"step": 11990
|
|
},
|
|
{
|
|
"entropy": 6.308350610733032,
|
|
"epoch": 1.1990303393812165,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048645361567309375,
|
|
"loss": 5.8741,
|
|
"mean_token_accuracy": 0.17936729043722152,
|
|
"num_tokens": 23481478.0,
|
|
"step": 11995
|
|
},
|
|
{
|
|
"entropy": 6.28343014717102,
|
|
"epoch": 1.1995301644424452,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004864414165517812,
|
|
"loss": 5.8533,
|
|
"mean_token_accuracy": 0.17057686299085617,
|
|
"num_tokens": 23491253.0,
|
|
"step": 12000
|
|
},
|
|
{
|
|
"epoch": 1.1995301644424452,
|
|
"eval_entropy": 5.975992608703126,
|
|
"eval_loss": 5.84630823135376,
|
|
"eval_mean_token_accuracy": 0.18042543807869196,
|
|
"eval_num_tokens": 23491253.0,
|
|
"eval_runtime": 18.4517,
|
|
"eval_samples_per_second": 1682.498,
|
|
"eval_steps_per_second": 210.333,
|
|
"step": 12000
|
|
},
|
|
{
|
|
"entropy": 6.252227067947388,
|
|
"epoch": 1.2000299895036737,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000486429212110657,
|
|
"loss": 5.8133,
|
|
"mean_token_accuracy": 0.17605598717927934,
|
|
"num_tokens": 23500753.0,
|
|
"step": 12005
|
|
},
|
|
{
|
|
"entropy": 6.282754278182983,
|
|
"epoch": 1.2005298145649024,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004864170023500282,
|
|
"loss": 5.869,
|
|
"mean_token_accuracy": 0.16279756277799606,
|
|
"num_tokens": 23509837.0,
|
|
"step": 12010
|
|
},
|
|
{
|
|
"entropy": 6.23346643447876,
|
|
"epoch": 1.2010296396261309,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004864047872702021,
|
|
"loss": 5.7736,
|
|
"mean_token_accuracy": 0.17406849563121796,
|
|
"num_tokens": 23519926.0,
|
|
"step": 12015
|
|
},
|
|
{
|
|
"entropy": 6.291954708099365,
|
|
"epoch": 1.2015294646873593,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004863925668714859,
|
|
"loss": 5.9258,
|
|
"mean_token_accuracy": 0.16397705078125,
|
|
"num_tokens": 23531165.0,
|
|
"step": 12020
|
|
},
|
|
{
|
|
"entropy": 6.266838693618775,
|
|
"epoch": 1.202029289748588,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004863803411541871,
|
|
"loss": 5.7523,
|
|
"mean_token_accuracy": 0.17627466171979905,
|
|
"num_tokens": 23541696.0,
|
|
"step": 12025
|
|
},
|
|
{
|
|
"entropy": 6.2620782375335695,
|
|
"epoch": 1.2025291148098165,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004863681101186134,
|
|
"loss": 5.7849,
|
|
"mean_token_accuracy": 0.17010432183742524,
|
|
"num_tokens": 23552382.0,
|
|
"step": 12030
|
|
},
|
|
{
|
|
"entropy": 6.240610122680664,
|
|
"epoch": 1.2030289398710452,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004863558737650723,
|
|
"loss": 5.8518,
|
|
"mean_token_accuracy": 0.17297555208206178,
|
|
"num_tokens": 23561444.0,
|
|
"step": 12035
|
|
},
|
|
{
|
|
"entropy": 6.216676330566406,
|
|
"epoch": 1.2035287649322737,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004863436320938719,
|
|
"loss": 5.7802,
|
|
"mean_token_accuracy": 0.17100454717874528,
|
|
"num_tokens": 23570985.0,
|
|
"step": 12040
|
|
},
|
|
{
|
|
"entropy": 6.1674339294433596,
|
|
"epoch": 1.2040285899935022,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00048633138510532003,
|
|
"loss": 5.7156,
|
|
"mean_token_accuracy": 0.1838998720049858,
|
|
"num_tokens": 23581291.0,
|
|
"step": 12045
|
|
},
|
|
{
|
|
"entropy": 6.275988435745239,
|
|
"epoch": 1.2045284150547308,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048631913279972497,
|
|
"loss": 5.8641,
|
|
"mean_token_accuracy": 0.1719813033938408,
|
|
"num_tokens": 23591087.0,
|
|
"step": 12050
|
|
},
|
|
{
|
|
"entropy": 6.2585938453674315,
|
|
"epoch": 1.2050282401159593,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00048630687517739484,
|
|
"loss": 5.842,
|
|
"mean_token_accuracy": 0.16810781583189965,
|
|
"num_tokens": 23601635.0,
|
|
"step": 12055
|
|
},
|
|
{
|
|
"entropy": 6.317281246185303,
|
|
"epoch": 1.205528065177188,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004862946122386381,
|
|
"loss": 5.8183,
|
|
"mean_token_accuracy": 0.1756850853562355,
|
|
"num_tokens": 23612523.0,
|
|
"step": 12060
|
|
},
|
|
{
|
|
"entropy": 6.252690601348877,
|
|
"epoch": 1.2060278902384165,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00048628234398376334,
|
|
"loss": 5.8122,
|
|
"mean_token_accuracy": 0.17701289802789688,
|
|
"num_tokens": 23622258.0,
|
|
"step": 12065
|
|
},
|
|
{
|
|
"entropy": 6.178759384155273,
|
|
"epoch": 1.2065277152996452,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00048627007041307914,
|
|
"loss": 5.6743,
|
|
"mean_token_accuracy": 0.1736823484301567,
|
|
"num_tokens": 23631198.0,
|
|
"step": 12070
|
|
},
|
|
{
|
|
"entropy": 6.230792570114136,
|
|
"epoch": 1.2070275403608737,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048625779152689435,
|
|
"loss": 5.806,
|
|
"mean_token_accuracy": 0.1718043640255928,
|
|
"num_tokens": 23641052.0,
|
|
"step": 12075
|
|
},
|
|
{
|
|
"entropy": 6.297239589691162,
|
|
"epoch": 1.2075273654221022,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004862455073255179,
|
|
"loss": 5.7775,
|
|
"mean_token_accuracy": 0.17754299491643905,
|
|
"num_tokens": 23650785.0,
|
|
"step": 12080
|
|
},
|
|
{
|
|
"entropy": 6.21585521697998,
|
|
"epoch": 1.2080271904833308,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048623321780925883,
|
|
"loss": 5.814,
|
|
"mean_token_accuracy": 0.17026566863059997,
|
|
"num_tokens": 23660548.0,
|
|
"step": 12085
|
|
},
|
|
{
|
|
"entropy": 6.127241754531861,
|
|
"epoch": 1.2085270155445593,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00048622092297842637,
|
|
"loss": 5.6798,
|
|
"mean_token_accuracy": 0.17964873015880584,
|
|
"num_tokens": 23669979.0,
|
|
"step": 12090
|
|
},
|
|
{
|
|
"entropy": 6.294066095352173,
|
|
"epoch": 1.209026840605788,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004862086228333298,
|
|
"loss": 5.8563,
|
|
"mean_token_accuracy": 0.16339568197727203,
|
|
"num_tokens": 23679740.0,
|
|
"step": 12095
|
|
},
|
|
{
|
|
"entropy": 6.292013502120971,
|
|
"epoch": 1.2095266656670165,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048619631737427865,
|
|
"loss": 5.8373,
|
|
"mean_token_accuracy": 0.1737920567393303,
|
|
"num_tokens": 23689688.0,
|
|
"step": 12100
|
|
},
|
|
{
|
|
"entropy": 6.225431680679321,
|
|
"epoch": 1.2100264907282452,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004861840066015825,
|
|
"loss": 5.7257,
|
|
"mean_token_accuracy": 0.1822040259838104,
|
|
"num_tokens": 23699550.0,
|
|
"step": 12105
|
|
},
|
|
{
|
|
"entropy": 6.243966007232666,
|
|
"epoch": 1.2105263157894737,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048617169051555113,
|
|
"loss": 5.8251,
|
|
"mean_token_accuracy": 0.1685713306069374,
|
|
"num_tokens": 23709114.0,
|
|
"step": 12110
|
|
},
|
|
{
|
|
"entropy": 6.254641580581665,
|
|
"epoch": 1.2110261408507021,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004861593691164942,
|
|
"loss": 5.8152,
|
|
"mean_token_accuracy": 0.16933439671993256,
|
|
"num_tokens": 23718758.0,
|
|
"step": 12115
|
|
},
|
|
{
|
|
"entropy": 6.268207120895386,
|
|
"epoch": 1.2115259659119308,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004861470424047221,
|
|
"loss": 5.7701,
|
|
"mean_token_accuracy": 0.17387983053922654,
|
|
"num_tokens": 23728175.0,
|
|
"step": 12120
|
|
},
|
|
{
|
|
"entropy": 6.050999307632447,
|
|
"epoch": 1.2120257909731593,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004861347103805446,
|
|
"loss": 5.6232,
|
|
"mean_token_accuracy": 0.18761055916547775,
|
|
"num_tokens": 23738308.0,
|
|
"step": 12125
|
|
},
|
|
{
|
|
"entropy": 6.259688758850098,
|
|
"epoch": 1.212525616034388,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004861223730442722,
|
|
"loss": 5.766,
|
|
"mean_token_accuracy": 0.17085681557655336,
|
|
"num_tokens": 23747867.0,
|
|
"step": 12130
|
|
},
|
|
{
|
|
"entropy": 6.195316362380981,
|
|
"epoch": 1.2130254410956165,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00048611003039621516,
|
|
"loss": 5.7247,
|
|
"mean_token_accuracy": 0.17571509033441543,
|
|
"num_tokens": 23758347.0,
|
|
"step": 12135
|
|
},
|
|
{
|
|
"entropy": 6.237366390228272,
|
|
"epoch": 1.2135252661568452,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004860976824366841,
|
|
"loss": 5.7812,
|
|
"mean_token_accuracy": 0.18126381933689117,
|
|
"num_tokens": 23767847.0,
|
|
"step": 12140
|
|
},
|
|
{
|
|
"entropy": 6.229058313369751,
|
|
"epoch": 1.2140250912180737,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048608532916598964,
|
|
"loss": 5.7897,
|
|
"mean_token_accuracy": 0.17472332417964936,
|
|
"num_tokens": 23777098.0,
|
|
"step": 12145
|
|
},
|
|
{
|
|
"entropy": 6.236595964431762,
|
|
"epoch": 1.2145249162793021,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048607297058444267,
|
|
"loss": 5.8215,
|
|
"mean_token_accuracy": 0.17561837881803513,
|
|
"num_tokens": 23787332.0,
|
|
"step": 12150
|
|
},
|
|
{
|
|
"entropy": 6.1729127883911135,
|
|
"epoch": 1.2150247413405308,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004860606066923541,
|
|
"loss": 5.7522,
|
|
"mean_token_accuracy": 0.17835317254066468,
|
|
"num_tokens": 23796263.0,
|
|
"step": 12155
|
|
},
|
|
{
|
|
"entropy": 6.228117847442627,
|
|
"epoch": 1.2155245664017593,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048604823749003485,
|
|
"loss": 5.788,
|
|
"mean_token_accuracy": 0.1665360301733017,
|
|
"num_tokens": 23806051.0,
|
|
"step": 12160
|
|
},
|
|
{
|
|
"entropy": 6.187891578674316,
|
|
"epoch": 1.216024391462988,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004860358629777963,
|
|
"loss": 5.7052,
|
|
"mean_token_accuracy": 0.18257190883159638,
|
|
"num_tokens": 23814925.0,
|
|
"step": 12165
|
|
},
|
|
{
|
|
"entropy": 6.1946220874786375,
|
|
"epoch": 1.2165242165242165,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004860234831559498,
|
|
"loss": 5.678,
|
|
"mean_token_accuracy": 0.1792776808142662,
|
|
"num_tokens": 23824785.0,
|
|
"step": 12170
|
|
},
|
|
{
|
|
"entropy": 6.197793245315552,
|
|
"epoch": 1.2170240415854452,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048601109802480676,
|
|
"loss": 5.8591,
|
|
"mean_token_accuracy": 0.1631132408976555,
|
|
"num_tokens": 23835102.0,
|
|
"step": 12175
|
|
},
|
|
{
|
|
"entropy": 6.217786169052124,
|
|
"epoch": 1.2175238666466737,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00048599870758467875,
|
|
"loss": 5.8119,
|
|
"mean_token_accuracy": 0.16933028846979142,
|
|
"num_tokens": 23845718.0,
|
|
"step": 12180
|
|
},
|
|
{
|
|
"entropy": 6.216218757629394,
|
|
"epoch": 1.2180236917079021,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048598631183587753,
|
|
"loss": 5.7512,
|
|
"mean_token_accuracy": 0.17435070276260375,
|
|
"num_tokens": 23855078.0,
|
|
"step": 12185
|
|
},
|
|
{
|
|
"entropy": 6.264580249786377,
|
|
"epoch": 1.2185235167691308,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00048597391077871504,
|
|
"loss": 5.824,
|
|
"mean_token_accuracy": 0.17251227796077728,
|
|
"num_tokens": 23864287.0,
|
|
"step": 12190
|
|
},
|
|
{
|
|
"entropy": 6.241967630386353,
|
|
"epoch": 1.2190233418303593,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00048596150441350324,
|
|
"loss": 5.9083,
|
|
"mean_token_accuracy": 0.1599275916814804,
|
|
"num_tokens": 23874477.0,
|
|
"step": 12195
|
|
},
|
|
{
|
|
"entropy": 6.226188230514526,
|
|
"epoch": 1.219523166891588,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004859490927405543,
|
|
"loss": 5.6764,
|
|
"mean_token_accuracy": 0.16883573830127716,
|
|
"num_tokens": 23884208.0,
|
|
"step": 12200
|
|
},
|
|
{
|
|
"entropy": 6.320587539672852,
|
|
"epoch": 1.2200229919528165,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004859366757601804,
|
|
"loss": 5.9027,
|
|
"mean_token_accuracy": 0.169129778444767,
|
|
"num_tokens": 23894226.0,
|
|
"step": 12205
|
|
},
|
|
{
|
|
"entropy": 6.166201162338257,
|
|
"epoch": 1.2205228170140452,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048592425347269405,
|
|
"loss": 5.7036,
|
|
"mean_token_accuracy": 0.18478777259588242,
|
|
"num_tokens": 23904238.0,
|
|
"step": 12210
|
|
},
|
|
{
|
|
"entropy": 6.167268896102906,
|
|
"epoch": 1.2210226420752737,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00048591182587840777,
|
|
"loss": 5.7393,
|
|
"mean_token_accuracy": 0.1731534868478775,
|
|
"num_tokens": 23914611.0,
|
|
"step": 12215
|
|
},
|
|
{
|
|
"entropy": 6.270431184768677,
|
|
"epoch": 1.2215224671365021,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004858993929776342,
|
|
"loss": 5.875,
|
|
"mean_token_accuracy": 0.16500010788440705,
|
|
"num_tokens": 23924270.0,
|
|
"step": 12220
|
|
},
|
|
{
|
|
"entropy": 6.226824522018433,
|
|
"epoch": 1.2220222921977308,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048588695477068617,
|
|
"loss": 5.7622,
|
|
"mean_token_accuracy": 0.1716660365462303,
|
|
"num_tokens": 23932677.0,
|
|
"step": 12225
|
|
},
|
|
{
|
|
"entropy": 6.278093338012695,
|
|
"epoch": 1.2225221172589593,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00048587451125787665,
|
|
"loss": 5.7648,
|
|
"mean_token_accuracy": 0.16963619738817215,
|
|
"num_tokens": 23943259.0,
|
|
"step": 12230
|
|
},
|
|
{
|
|
"entropy": 6.235840797424316,
|
|
"epoch": 1.223021942320188,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004858620624395187,
|
|
"loss": 5.7978,
|
|
"mean_token_accuracy": 0.17588536888360978,
|
|
"num_tokens": 23953162.0,
|
|
"step": 12235
|
|
},
|
|
{
|
|
"entropy": 6.261279964447022,
|
|
"epoch": 1.2235217673814165,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048584960831592547,
|
|
"loss": 5.8719,
|
|
"mean_token_accuracy": 0.16348388344049453,
|
|
"num_tokens": 23961577.0,
|
|
"step": 12240
|
|
},
|
|
{
|
|
"entropy": 6.1810081005096436,
|
|
"epoch": 1.2240215924426452,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00048583714888741035,
|
|
"loss": 5.6832,
|
|
"mean_token_accuracy": 0.1849902331829071,
|
|
"num_tokens": 23969691.0,
|
|
"step": 12245
|
|
},
|
|
{
|
|
"entropy": 6.167519998550415,
|
|
"epoch": 1.2245214175038737,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00048582468415428687,
|
|
"loss": 5.7703,
|
|
"mean_token_accuracy": 0.17323962450027466,
|
|
"num_tokens": 23980753.0,
|
|
"step": 12250
|
|
},
|
|
{
|
|
"entropy": 6.245575475692749,
|
|
"epoch": 1.2250212425651021,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048581221411686857,
|
|
"loss": 5.8299,
|
|
"mean_token_accuracy": 0.16962644904851915,
|
|
"num_tokens": 23991841.0,
|
|
"step": 12255
|
|
},
|
|
{
|
|
"entropy": 6.226211833953857,
|
|
"epoch": 1.2255210676263308,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00048579973877546916,
|
|
"loss": 5.7685,
|
|
"mean_token_accuracy": 0.17261390388011932,
|
|
"num_tokens": 24000749.0,
|
|
"step": 12260
|
|
},
|
|
{
|
|
"entropy": 6.306629180908203,
|
|
"epoch": 1.2260208926875593,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048578725813040263,
|
|
"loss": 5.9157,
|
|
"mean_token_accuracy": 0.1677663192152977,
|
|
"num_tokens": 24010055.0,
|
|
"step": 12265
|
|
},
|
|
{
|
|
"entropy": 6.235163927078247,
|
|
"epoch": 1.226520717748788,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004857747721819829,
|
|
"loss": 5.7803,
|
|
"mean_token_accuracy": 0.17879074066877365,
|
|
"num_tokens": 24019307.0,
|
|
"step": 12270
|
|
},
|
|
{
|
|
"entropy": 6.212776041030883,
|
|
"epoch": 1.2270205428100165,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004857622809305241,
|
|
"loss": 5.659,
|
|
"mean_token_accuracy": 0.18536266237497329,
|
|
"num_tokens": 24028913.0,
|
|
"step": 12275
|
|
},
|
|
{
|
|
"entropy": 6.233301496505737,
|
|
"epoch": 1.2275203678712452,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048574978437634057,
|
|
"loss": 5.67,
|
|
"mean_token_accuracy": 0.1782218486070633,
|
|
"num_tokens": 24038357.0,
|
|
"step": 12280
|
|
},
|
|
{
|
|
"entropy": 6.206346464157105,
|
|
"epoch": 1.2280201929324737,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004857372825197468,
|
|
"loss": 5.7469,
|
|
"mean_token_accuracy": 0.17971667051315307,
|
|
"num_tokens": 24048199.0,
|
|
"step": 12285
|
|
},
|
|
{
|
|
"entropy": 6.22651515007019,
|
|
"epoch": 1.2285200179937021,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004857247753610571,
|
|
"loss": 5.8123,
|
|
"mean_token_accuracy": 0.1738505095243454,
|
|
"num_tokens": 24058311.0,
|
|
"step": 12290
|
|
},
|
|
{
|
|
"entropy": 6.235115623474121,
|
|
"epoch": 1.2290198430549308,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048571226290058635,
|
|
"loss": 5.8028,
|
|
"mean_token_accuracy": 0.17441281229257583,
|
|
"num_tokens": 24068471.0,
|
|
"step": 12295
|
|
},
|
|
{
|
|
"entropy": 6.251537799835205,
|
|
"epoch": 1.2295196681161593,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004856997451386492,
|
|
"loss": 5.791,
|
|
"mean_token_accuracy": 0.1728360503911972,
|
|
"num_tokens": 24078118.0,
|
|
"step": 12300
|
|
},
|
|
{
|
|
"entropy": 6.277921533584594,
|
|
"epoch": 1.2300194931773878,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004856872220755607,
|
|
"loss": 5.7948,
|
|
"mean_token_accuracy": 0.17563612163066863,
|
|
"num_tokens": 24088517.0,
|
|
"step": 12305
|
|
},
|
|
{
|
|
"entropy": 6.296839666366577,
|
|
"epoch": 1.2305193182386165,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000485674693711636,
|
|
"loss": 5.8766,
|
|
"mean_token_accuracy": 0.17025070637464523,
|
|
"num_tokens": 24097421.0,
|
|
"step": 12310
|
|
},
|
|
{
|
|
"entropy": 6.171737909317017,
|
|
"epoch": 1.231019143299845,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004856621600471901,
|
|
"loss": 5.7208,
|
|
"mean_token_accuracy": 0.17783631533384323,
|
|
"num_tokens": 24106531.0,
|
|
"step": 12315
|
|
},
|
|
{
|
|
"entropy": 6.183775758743286,
|
|
"epoch": 1.2315189683610737,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048564962108253853,
|
|
"loss": 5.7538,
|
|
"mean_token_accuracy": 0.17404510378837584,
|
|
"num_tokens": 24115246.0,
|
|
"step": 12320
|
|
},
|
|
{
|
|
"entropy": 6.271859216690063,
|
|
"epoch": 1.2320187934223021,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004856370768179967,
|
|
"loss": 5.8489,
|
|
"mean_token_accuracy": 0.1693730264902115,
|
|
"num_tokens": 24126163.0,
|
|
"step": 12325
|
|
},
|
|
{
|
|
"entropy": 6.228876447677612,
|
|
"epoch": 1.2325186184835308,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048562452725388024,
|
|
"loss": 5.7976,
|
|
"mean_token_accuracy": 0.1704660788178444,
|
|
"num_tokens": 24135722.0,
|
|
"step": 12330
|
|
},
|
|
{
|
|
"entropy": 6.152893829345703,
|
|
"epoch": 1.2330184435447593,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004856119723905048,
|
|
"loss": 5.6239,
|
|
"mean_token_accuracy": 0.18743896037340163,
|
|
"num_tokens": 24145278.0,
|
|
"step": 12335
|
|
},
|
|
{
|
|
"entropy": 6.2094502449035645,
|
|
"epoch": 1.2335182686059878,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004855994122281864,
|
|
"loss": 5.7838,
|
|
"mean_token_accuracy": 0.1703975260257721,
|
|
"num_tokens": 24154710.0,
|
|
"step": 12340
|
|
},
|
|
{
|
|
"entropy": 6.264818954467773,
|
|
"epoch": 1.2340180936672165,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048558684676724083,
|
|
"loss": 5.8111,
|
|
"mean_token_accuracy": 0.16750631034374236,
|
|
"num_tokens": 24164373.0,
|
|
"step": 12345
|
|
},
|
|
{
|
|
"entropy": 6.204779005050659,
|
|
"epoch": 1.234517918728445,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048557427600798454,
|
|
"loss": 5.6711,
|
|
"mean_token_accuracy": 0.18137891590595245,
|
|
"num_tokens": 24173085.0,
|
|
"step": 12350
|
|
},
|
|
{
|
|
"entropy": 6.230932235717773,
|
|
"epoch": 1.2350177437896737,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004855616999507336,
|
|
"loss": 5.8007,
|
|
"mean_token_accuracy": 0.17388046979904176,
|
|
"num_tokens": 24182936.0,
|
|
"step": 12355
|
|
},
|
|
{
|
|
"entropy": 6.306598234176636,
|
|
"epoch": 1.2355175688509021,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00048554911859580445,
|
|
"loss": 5.7828,
|
|
"mean_token_accuracy": 0.17001889795064926,
|
|
"num_tokens": 24192407.0,
|
|
"step": 12360
|
|
},
|
|
{
|
|
"entropy": 6.303968334197998,
|
|
"epoch": 1.2360173939121308,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004855365319435137,
|
|
"loss": 5.7282,
|
|
"mean_token_accuracy": 0.18880087286233901,
|
|
"num_tokens": 24201770.0,
|
|
"step": 12365
|
|
},
|
|
{
|
|
"entropy": 6.1961585521698,
|
|
"epoch": 1.2365172189733593,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000485523939994178,
|
|
"loss": 5.7117,
|
|
"mean_token_accuracy": 0.1822067454457283,
|
|
"num_tokens": 24211287.0,
|
|
"step": 12370
|
|
},
|
|
{
|
|
"entropy": 6.143581485748291,
|
|
"epoch": 1.2370170440345878,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004855113427481141,
|
|
"loss": 5.7533,
|
|
"mean_token_accuracy": 0.1783610016107559,
|
|
"num_tokens": 24221277.0,
|
|
"step": 12375
|
|
},
|
|
{
|
|
"entropy": 6.242695331573486,
|
|
"epoch": 1.2375168690958165,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000485498740205639,
|
|
"loss": 5.6444,
|
|
"mean_token_accuracy": 0.18736617416143417,
|
|
"num_tokens": 24231272.0,
|
|
"step": 12380
|
|
},
|
|
{
|
|
"entropy": 6.254062128067017,
|
|
"epoch": 1.238016694157045,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048548613236706976,
|
|
"loss": 5.8102,
|
|
"mean_token_accuracy": 0.17784251570701598,
|
|
"num_tokens": 24242073.0,
|
|
"step": 12385
|
|
},
|
|
{
|
|
"entropy": 6.160064458847046,
|
|
"epoch": 1.2385165192182737,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004854735192327236,
|
|
"loss": 5.6303,
|
|
"mean_token_accuracy": 0.18967167139053345,
|
|
"num_tokens": 24251928.0,
|
|
"step": 12390
|
|
},
|
|
{
|
|
"entropy": 6.202083730697632,
|
|
"epoch": 1.2390163442795021,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00048546090080291783,
|
|
"loss": 5.7235,
|
|
"mean_token_accuracy": 0.18012016862630845,
|
|
"num_tokens": 24261146.0,
|
|
"step": 12395
|
|
},
|
|
{
|
|
"entropy": 6.248048257827759,
|
|
"epoch": 1.2395161693407308,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00048544827707797,
|
|
"loss": 5.8783,
|
|
"mean_token_accuracy": 0.16537221968173982,
|
|
"num_tokens": 24271675.0,
|
|
"step": 12400
|
|
},
|
|
{
|
|
"entropy": 6.21930775642395,
|
|
"epoch": 1.2400159944019593,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048543564805819764,
|
|
"loss": 5.7434,
|
|
"mean_token_accuracy": 0.17462845593690873,
|
|
"num_tokens": 24280795.0,
|
|
"step": 12405
|
|
},
|
|
{
|
|
"entropy": 6.201604175567627,
|
|
"epoch": 1.2405158194631878,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004854230137439185,
|
|
"loss": 5.7582,
|
|
"mean_token_accuracy": 0.1752499520778656,
|
|
"num_tokens": 24291204.0,
|
|
"step": 12410
|
|
},
|
|
{
|
|
"entropy": 6.236205148696899,
|
|
"epoch": 1.2410156445244165,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048541037413545046,
|
|
"loss": 5.7277,
|
|
"mean_token_accuracy": 0.1759438619017601,
|
|
"num_tokens": 24300926.0,
|
|
"step": 12415
|
|
},
|
|
{
|
|
"entropy": 6.173032569885254,
|
|
"epoch": 1.241515469585645,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004853977292331116,
|
|
"loss": 5.6569,
|
|
"mean_token_accuracy": 0.1785312831401825,
|
|
"num_tokens": 24310319.0,
|
|
"step": 12420
|
|
},
|
|
{
|
|
"entropy": 6.188090085983276,
|
|
"epoch": 1.2420152946468737,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004853850790372201,
|
|
"loss": 5.7782,
|
|
"mean_token_accuracy": 0.1748438760638237,
|
|
"num_tokens": 24321671.0,
|
|
"step": 12425
|
|
},
|
|
{
|
|
"entropy": 6.229245376586914,
|
|
"epoch": 1.2425151197081021,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048537242354809403,
|
|
"loss": 5.8415,
|
|
"mean_token_accuracy": 0.16499550193548201,
|
|
"num_tokens": 24330275.0,
|
|
"step": 12430
|
|
},
|
|
{
|
|
"entropy": 6.295279121398925,
|
|
"epoch": 1.2430149447693308,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048535976276605186,
|
|
"loss": 5.7952,
|
|
"mean_token_accuracy": 0.1720464274287224,
|
|
"num_tokens": 24339753.0,
|
|
"step": 12435
|
|
},
|
|
{
|
|
"entropy": 6.229263877868652,
|
|
"epoch": 1.2435147698305593,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004853470966914123,
|
|
"loss": 5.7674,
|
|
"mean_token_accuracy": 0.16822308003902436,
|
|
"num_tokens": 24349517.0,
|
|
"step": 12440
|
|
},
|
|
{
|
|
"entropy": 6.1482062339782715,
|
|
"epoch": 1.2440145948917878,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004853344253244939,
|
|
"loss": 5.6756,
|
|
"mean_token_accuracy": 0.18326727598905562,
|
|
"num_tokens": 24358036.0,
|
|
"step": 12445
|
|
},
|
|
{
|
|
"entropy": 6.148185539245605,
|
|
"epoch": 1.2445144199530165,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00048532174866561543,
|
|
"loss": 5.6285,
|
|
"mean_token_accuracy": 0.1877700611948967,
|
|
"num_tokens": 24367488.0,
|
|
"step": 12450
|
|
},
|
|
{
|
|
"entropy": 6.31269383430481,
|
|
"epoch": 1.245014245014245,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048530906671509597,
|
|
"loss": 5.9526,
|
|
"mean_token_accuracy": 0.15949220955371857,
|
|
"num_tokens": 24377053.0,
|
|
"step": 12455
|
|
},
|
|
{
|
|
"entropy": 6.243444728851318,
|
|
"epoch": 1.2455140700754737,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00048529637947325444,
|
|
"loss": 5.8156,
|
|
"mean_token_accuracy": 0.16543440520763397,
|
|
"num_tokens": 24387245.0,
|
|
"step": 12460
|
|
},
|
|
{
|
|
"entropy": 6.3041832447052,
|
|
"epoch": 1.2460138951367021,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004852836869404101,
|
|
"loss": 5.8816,
|
|
"mean_token_accuracy": 0.16927459239959716,
|
|
"num_tokens": 24395901.0,
|
|
"step": 12465
|
|
},
|
|
{
|
|
"entropy": 6.236918306350708,
|
|
"epoch": 1.2465137201979308,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004852709891168823,
|
|
"loss": 5.7075,
|
|
"mean_token_accuracy": 0.18079877644777298,
|
|
"num_tokens": 24405148.0,
|
|
"step": 12470
|
|
},
|
|
{
|
|
"entropy": 6.140580463409424,
|
|
"epoch": 1.2470135452591593,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004852582860029906,
|
|
"loss": 5.6576,
|
|
"mean_token_accuracy": 0.18379386514425278,
|
|
"num_tokens": 24415406.0,
|
|
"step": 12475
|
|
},
|
|
{
|
|
"entropy": 6.151240491867066,
|
|
"epoch": 1.2475133703203878,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048524557759905445,
|
|
"loss": 5.6836,
|
|
"mean_token_accuracy": 0.18338510096073152,
|
|
"num_tokens": 24425702.0,
|
|
"step": 12480
|
|
},
|
|
{
|
|
"entropy": 6.23250789642334,
|
|
"epoch": 1.2480131953816165,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004852328639053937,
|
|
"loss": 5.7539,
|
|
"mean_token_accuracy": 0.174046990275383,
|
|
"num_tokens": 24435702.0,
|
|
"step": 12485
|
|
},
|
|
{
|
|
"entropy": 6.265951681137085,
|
|
"epoch": 1.248513020442845,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004852201449223282,
|
|
"loss": 5.8412,
|
|
"mean_token_accuracy": 0.16099309027194977,
|
|
"num_tokens": 24445545.0,
|
|
"step": 12490
|
|
},
|
|
{
|
|
"entropy": 6.256677865982056,
|
|
"epoch": 1.2490128455040737,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000485207420650178,
|
|
"loss": 5.8558,
|
|
"mean_token_accuracy": 0.17179241329431533,
|
|
"num_tokens": 24455269.0,
|
|
"step": 12495
|
|
},
|
|
{
|
|
"entropy": 6.249303960800171,
|
|
"epoch": 1.2495126705653021,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004851946910892631,
|
|
"loss": 5.7694,
|
|
"mean_token_accuracy": 0.18585778176784515,
|
|
"num_tokens": 24465563.0,
|
|
"step": 12500
|
|
},
|
|
{
|
|
"entropy": 6.237961387634277,
|
|
"epoch": 1.2500124956265308,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004851819562399039,
|
|
"loss": 5.8414,
|
|
"mean_token_accuracy": 0.17462964206933976,
|
|
"num_tokens": 24475837.0,
|
|
"step": 12505
|
|
},
|
|
{
|
|
"entropy": 6.292201900482178,
|
|
"epoch": 1.2505123206877593,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004851692161024207,
|
|
"loss": 5.8674,
|
|
"mean_token_accuracy": 0.16775282472372055,
|
|
"num_tokens": 24486384.0,
|
|
"step": 12510
|
|
},
|
|
{
|
|
"entropy": 6.293866300582886,
|
|
"epoch": 1.2510121457489878,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048515647067713425,
|
|
"loss": 5.911,
|
|
"mean_token_accuracy": 0.16595742255449294,
|
|
"num_tokens": 24495840.0,
|
|
"step": 12515
|
|
},
|
|
{
|
|
"entropy": 6.233415269851685,
|
|
"epoch": 1.2515119708102165,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000485143719964365,
|
|
"loss": 5.7356,
|
|
"mean_token_accuracy": 0.17780937850475312,
|
|
"num_tokens": 24505849.0,
|
|
"step": 12520
|
|
},
|
|
{
|
|
"entropy": 6.235902547836304,
|
|
"epoch": 1.252011795871445,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004851309639644338,
|
|
"loss": 5.8287,
|
|
"mean_token_accuracy": 0.16437818557024003,
|
|
"num_tokens": 24517440.0,
|
|
"step": 12525
|
|
},
|
|
{
|
|
"entropy": 6.244646406173706,
|
|
"epoch": 1.2525116209326734,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004851182026776616,
|
|
"loss": 5.7291,
|
|
"mean_token_accuracy": 0.17561271637678147,
|
|
"num_tokens": 24527602.0,
|
|
"step": 12530
|
|
},
|
|
{
|
|
"entropy": 6.148610544204712,
|
|
"epoch": 1.2530114459939021,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004851054361043696,
|
|
"loss": 5.6727,
|
|
"mean_token_accuracy": 0.19009541124105453,
|
|
"num_tokens": 24536770.0,
|
|
"step": 12535
|
|
},
|
|
{
|
|
"entropy": 6.251919889450074,
|
|
"epoch": 1.2535112710551308,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048509266424487873,
|
|
"loss": 5.8033,
|
|
"mean_token_accuracy": 0.17327489331364632,
|
|
"num_tokens": 24546230.0,
|
|
"step": 12540
|
|
},
|
|
{
|
|
"entropy": 6.212267971038818,
|
|
"epoch": 1.2540110961163593,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004850798870995106,
|
|
"loss": 5.7623,
|
|
"mean_token_accuracy": 0.1696051150560379,
|
|
"num_tokens": 24555130.0,
|
|
"step": 12545
|
|
},
|
|
{
|
|
"entropy": 6.278397274017334,
|
|
"epoch": 1.2545109211775878,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00048506710466858657,
|
|
"loss": 5.8257,
|
|
"mean_token_accuracy": 0.17031870037317276,
|
|
"num_tokens": 24565167.0,
|
|
"step": 12550
|
|
},
|
|
{
|
|
"entropy": 6.203593778610229,
|
|
"epoch": 1.2550107462388165,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00048505431695242823,
|
|
"loss": 5.8309,
|
|
"mean_token_accuracy": 0.1764886349439621,
|
|
"num_tokens": 24574545.0,
|
|
"step": 12555
|
|
},
|
|
{
|
|
"entropy": 6.215765905380249,
|
|
"epoch": 1.255510571300045,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048504152395135726,
|
|
"loss": 5.8229,
|
|
"mean_token_accuracy": 0.17375658601522445,
|
|
"num_tokens": 24585050.0,
|
|
"step": 12560
|
|
},
|
|
{
|
|
"entropy": 6.31174488067627,
|
|
"epoch": 1.2560103963612734,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048502872566569564,
|
|
"loss": 5.8361,
|
|
"mean_token_accuracy": 0.177568319439888,
|
|
"num_tokens": 24596334.0,
|
|
"step": 12565
|
|
},
|
|
{
|
|
"entropy": 6.231105709075928,
|
|
"epoch": 1.2565102214225021,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00048501592209576535,
|
|
"loss": 5.7852,
|
|
"mean_token_accuracy": 0.17504560053348542,
|
|
"num_tokens": 24605947.0,
|
|
"step": 12570
|
|
},
|
|
{
|
|
"entropy": 6.202714443206787,
|
|
"epoch": 1.2570100464837308,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004850031132418885,
|
|
"loss": 5.6463,
|
|
"mean_token_accuracy": 0.19099502563476561,
|
|
"num_tokens": 24614336.0,
|
|
"step": 12575
|
|
},
|
|
{
|
|
"entropy": 6.225604057312012,
|
|
"epoch": 1.2575098715449593,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00048499029910438734,
|
|
"loss": 5.7478,
|
|
"mean_token_accuracy": 0.17353655993938447,
|
|
"num_tokens": 24624906.0,
|
|
"step": 12580
|
|
},
|
|
{
|
|
"entropy": 6.32500262260437,
|
|
"epoch": 1.2580096966061878,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048497747968358424,
|
|
"loss": 5.8114,
|
|
"mean_token_accuracy": 0.17104064524173737,
|
|
"num_tokens": 24634127.0,
|
|
"step": 12585
|
|
},
|
|
{
|
|
"entropy": 6.156301593780517,
|
|
"epoch": 1.2585095216674165,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004849646549798019,
|
|
"loss": 5.7052,
|
|
"mean_token_accuracy": 0.1812283515930176,
|
|
"num_tokens": 24642451.0,
|
|
"step": 12590
|
|
},
|
|
{
|
|
"entropy": 6.231295204162597,
|
|
"epoch": 1.259009346728645,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048495182499336275,
|
|
"loss": 5.7145,
|
|
"mean_token_accuracy": 0.17577390372753143,
|
|
"num_tokens": 24651229.0,
|
|
"step": 12595
|
|
},
|
|
{
|
|
"entropy": 6.269476747512817,
|
|
"epoch": 1.2595091717898734,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048493898972458985,
|
|
"loss": 5.8953,
|
|
"mean_token_accuracy": 0.1697018876671791,
|
|
"num_tokens": 24660435.0,
|
|
"step": 12600
|
|
},
|
|
{
|
|
"entropy": 6.251654481887817,
|
|
"epoch": 1.2600089968511021,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004849261491738059,
|
|
"loss": 5.8004,
|
|
"mean_token_accuracy": 0.1748076096177101,
|
|
"num_tokens": 24669254.0,
|
|
"step": 12605
|
|
},
|
|
{
|
|
"entropy": 6.229447364807129,
|
|
"epoch": 1.2605088219123306,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048491330334133405,
|
|
"loss": 5.6879,
|
|
"mean_token_accuracy": 0.18411677330732346,
|
|
"num_tokens": 24677943.0,
|
|
"step": 12610
|
|
},
|
|
{
|
|
"entropy": 6.261879968643188,
|
|
"epoch": 1.2610086469735593,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048490045222749744,
|
|
"loss": 5.8479,
|
|
"mean_token_accuracy": 0.16765474826097487,
|
|
"num_tokens": 24686678.0,
|
|
"step": 12615
|
|
},
|
|
{
|
|
"entropy": 6.251817512512207,
|
|
"epoch": 1.2615084720347878,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048488759583261955,
|
|
"loss": 5.7052,
|
|
"mean_token_accuracy": 0.18248615711927413,
|
|
"num_tokens": 24696417.0,
|
|
"step": 12620
|
|
},
|
|
{
|
|
"entropy": 6.231420087814331,
|
|
"epoch": 1.2620082970960165,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004848747341570238,
|
|
"loss": 5.8338,
|
|
"mean_token_accuracy": 0.17057206109166145,
|
|
"num_tokens": 24705624.0,
|
|
"step": 12625
|
|
},
|
|
{
|
|
"entropy": 6.237839412689209,
|
|
"epoch": 1.262508122157245,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048486186720103364,
|
|
"loss": 5.7575,
|
|
"mean_token_accuracy": 0.17428947240114212,
|
|
"num_tokens": 24715705.0,
|
|
"step": 12630
|
|
},
|
|
{
|
|
"entropy": 6.227580261230469,
|
|
"epoch": 1.2630079472184734,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000484848994964973,
|
|
"loss": 5.6907,
|
|
"mean_token_accuracy": 0.18478302508592606,
|
|
"num_tokens": 24725358.0,
|
|
"step": 12635
|
|
},
|
|
{
|
|
"entropy": 6.229623079299927,
|
|
"epoch": 1.2635077722797021,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00048483611744916556,
|
|
"loss": 5.813,
|
|
"mean_token_accuracy": 0.1740306705236435,
|
|
"num_tokens": 24735457.0,
|
|
"step": 12640
|
|
},
|
|
{
|
|
"entropy": 6.313747453689575,
|
|
"epoch": 1.2640075973409306,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048482323465393545,
|
|
"loss": 5.8213,
|
|
"mean_token_accuracy": 0.1688176393508911,
|
|
"num_tokens": 24745391.0,
|
|
"step": 12645
|
|
},
|
|
{
|
|
"entropy": 6.2491740703582765,
|
|
"epoch": 1.2645074224021593,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004848103465796067,
|
|
"loss": 5.7905,
|
|
"mean_token_accuracy": 0.17152443826198577,
|
|
"num_tokens": 24754578.0,
|
|
"step": 12650
|
|
},
|
|
{
|
|
"entropy": 6.1853508949279785,
|
|
"epoch": 1.2650072474633878,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004847974532265037,
|
|
"loss": 5.8046,
|
|
"mean_token_accuracy": 0.17224955707788467,
|
|
"num_tokens": 24764115.0,
|
|
"step": 12655
|
|
},
|
|
{
|
|
"entropy": 6.225566244125366,
|
|
"epoch": 1.2655070725246165,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004847845545949507,
|
|
"loss": 5.7483,
|
|
"mean_token_accuracy": 0.17926350831985474,
|
|
"num_tokens": 24773247.0,
|
|
"step": 12660
|
|
},
|
|
{
|
|
"entropy": 6.210208463668823,
|
|
"epoch": 1.266006897585845,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00048477165068527237,
|
|
"loss": 5.7165,
|
|
"mean_token_accuracy": 0.1788391128182411,
|
|
"num_tokens": 24783139.0,
|
|
"step": 12665
|
|
},
|
|
{
|
|
"entropy": 6.264866876602173,
|
|
"epoch": 1.2665067226470734,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048475874149779313,
|
|
"loss": 5.7797,
|
|
"mean_token_accuracy": 0.17601179480552673,
|
|
"num_tokens": 24793591.0,
|
|
"step": 12670
|
|
},
|
|
{
|
|
"entropy": 6.230595922470092,
|
|
"epoch": 1.2670065477083021,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000484745827032838,
|
|
"loss": 5.7055,
|
|
"mean_token_accuracy": 0.18230190724134446,
|
|
"num_tokens": 24803340.0,
|
|
"step": 12675
|
|
},
|
|
{
|
|
"entropy": 6.211068201065063,
|
|
"epoch": 1.2675063727695306,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048473290729073194,
|
|
"loss": 5.6601,
|
|
"mean_token_accuracy": 0.18029972165822983,
|
|
"num_tokens": 24812133.0,
|
|
"step": 12680
|
|
},
|
|
{
|
|
"entropy": 6.206431865692139,
|
|
"epoch": 1.2680061978307593,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004847199822717998,
|
|
"loss": 5.785,
|
|
"mean_token_accuracy": 0.17275950014591218,
|
|
"num_tokens": 24822443.0,
|
|
"step": 12685
|
|
},
|
|
{
|
|
"entropy": 6.138604640960693,
|
|
"epoch": 1.2685060228919878,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004847070519763668,
|
|
"loss": 5.7225,
|
|
"mean_token_accuracy": 0.18323297351598739,
|
|
"num_tokens": 24832390.0,
|
|
"step": 12690
|
|
},
|
|
{
|
|
"entropy": 6.2317603588104244,
|
|
"epoch": 1.2690058479532165,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004846941164047585,
|
|
"loss": 5.7031,
|
|
"mean_token_accuracy": 0.18496687859296798,
|
|
"num_tokens": 24841704.0,
|
|
"step": 12695
|
|
},
|
|
{
|
|
"entropy": 6.309862947463989,
|
|
"epoch": 1.269505673014445,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00048468117555730013,
|
|
"loss": 5.842,
|
|
"mean_token_accuracy": 0.17104243934154512,
|
|
"num_tokens": 24852459.0,
|
|
"step": 12700
|
|
},
|
|
{
|
|
"entropy": 6.242697286605835,
|
|
"epoch": 1.2700054980756734,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004846682294343173,
|
|
"loss": 5.825,
|
|
"mean_token_accuracy": 0.1757025882601738,
|
|
"num_tokens": 24861758.0,
|
|
"step": 12705
|
|
},
|
|
{
|
|
"entropy": 6.337801361083985,
|
|
"epoch": 1.2705053231369021,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004846552780361358,
|
|
"loss": 5.8519,
|
|
"mean_token_accuracy": 0.17196739464998245,
|
|
"num_tokens": 24871855.0,
|
|
"step": 12710
|
|
},
|
|
{
|
|
"entropy": 6.23482313156128,
|
|
"epoch": 1.2710051481981306,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00048464232136308146,
|
|
"loss": 5.7293,
|
|
"mean_token_accuracy": 0.17449234575033187,
|
|
"num_tokens": 24880602.0,
|
|
"step": 12715
|
|
},
|
|
{
|
|
"entropy": 6.225963306427002,
|
|
"epoch": 1.2715049732593593,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004846293594154802,
|
|
"loss": 5.7467,
|
|
"mean_token_accuracy": 0.18426534086465834,
|
|
"num_tokens": 24891032.0,
|
|
"step": 12720
|
|
},
|
|
{
|
|
"entropy": 6.211741161346436,
|
|
"epoch": 1.2720047983205878,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004846163921936583,
|
|
"loss": 5.7483,
|
|
"mean_token_accuracy": 0.17872345298528672,
|
|
"num_tokens": 24900892.0,
|
|
"step": 12725
|
|
},
|
|
{
|
|
"entropy": 6.289758586883545,
|
|
"epoch": 1.2725046233818165,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048460341969794183,
|
|
"loss": 5.8231,
|
|
"mean_token_accuracy": 0.1695672407746315,
|
|
"num_tokens": 24910576.0,
|
|
"step": 12730
|
|
},
|
|
{
|
|
"entropy": 6.192642641067505,
|
|
"epoch": 1.273004448443045,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048459044192865726,
|
|
"loss": 5.8149,
|
|
"mean_token_accuracy": 0.17469389289617537,
|
|
"num_tokens": 24920861.0,
|
|
"step": 12735
|
|
},
|
|
{
|
|
"entropy": 6.276024675369262,
|
|
"epoch": 1.2735042735042734,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004845774588861311,
|
|
"loss": 5.8117,
|
|
"mean_token_accuracy": 0.16997539550065993,
|
|
"num_tokens": 24930539.0,
|
|
"step": 12740
|
|
},
|
|
{
|
|
"entropy": 6.253031301498413,
|
|
"epoch": 1.2740040985655021,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048456447057069004,
|
|
"loss": 5.7967,
|
|
"mean_token_accuracy": 0.17416519820690154,
|
|
"num_tokens": 24939737.0,
|
|
"step": 12745
|
|
},
|
|
{
|
|
"entropy": 6.269772005081177,
|
|
"epoch": 1.2745039236267306,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048455147698266084,
|
|
"loss": 5.8695,
|
|
"mean_token_accuracy": 0.16874520033597945,
|
|
"num_tokens": 24949316.0,
|
|
"step": 12750
|
|
},
|
|
{
|
|
"entropy": 6.207537508010864,
|
|
"epoch": 1.2750037486879593,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004845384781223703,
|
|
"loss": 5.7071,
|
|
"mean_token_accuracy": 0.17887308895587922,
|
|
"num_tokens": 24959454.0,
|
|
"step": 12755
|
|
},
|
|
{
|
|
"entropy": 6.2144585132598875,
|
|
"epoch": 1.2755035737491878,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00048452547399014566,
|
|
"loss": 5.8101,
|
|
"mean_token_accuracy": 0.17206486463546752,
|
|
"num_tokens": 24969091.0,
|
|
"step": 12760
|
|
},
|
|
{
|
|
"entropy": 6.221261405944825,
|
|
"epoch": 1.2760033988104165,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000484512464586314,
|
|
"loss": 5.6551,
|
|
"mean_token_accuracy": 0.18769008666276932,
|
|
"num_tokens": 24979239.0,
|
|
"step": 12765
|
|
},
|
|
{
|
|
"entropy": 6.3152727603912355,
|
|
"epoch": 1.276503223871645,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048449944991120264,
|
|
"loss": 5.8411,
|
|
"mean_token_accuracy": 0.17128538638353347,
|
|
"num_tokens": 24989274.0,
|
|
"step": 12770
|
|
},
|
|
{
|
|
"entropy": 6.232810306549072,
|
|
"epoch": 1.2770030489328734,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004844864299651391,
|
|
"loss": 5.721,
|
|
"mean_token_accuracy": 0.182733915746212,
|
|
"num_tokens": 24997873.0,
|
|
"step": 12775
|
|
},
|
|
{
|
|
"entropy": 6.124591255187989,
|
|
"epoch": 1.2775028739941021,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048447340474845076,
|
|
"loss": 5.7308,
|
|
"mean_token_accuracy": 0.17520465552806855,
|
|
"num_tokens": 25007829.0,
|
|
"step": 12780
|
|
},
|
|
{
|
|
"entropy": 6.193792724609375,
|
|
"epoch": 1.2780026990553306,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048446037426146555,
|
|
"loss": 5.713,
|
|
"mean_token_accuracy": 0.17806896120309829,
|
|
"num_tokens": 25016795.0,
|
|
"step": 12785
|
|
},
|
|
{
|
|
"entropy": 6.25873761177063,
|
|
"epoch": 1.278502524116559,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004844473385045112,
|
|
"loss": 5.7696,
|
|
"mean_token_accuracy": 0.1726322278380394,
|
|
"num_tokens": 25026012.0,
|
|
"step": 12790
|
|
},
|
|
{
|
|
"entropy": 6.230656909942627,
|
|
"epoch": 1.2790023491777878,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004844342974779157,
|
|
"loss": 5.6871,
|
|
"mean_token_accuracy": 0.17814860492944717,
|
|
"num_tokens": 25035353.0,
|
|
"step": 12795
|
|
},
|
|
{
|
|
"entropy": 6.221228361129761,
|
|
"epoch": 1.2795021742390165,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00048442125118200707,
|
|
"loss": 5.7623,
|
|
"mean_token_accuracy": 0.17819851785898208,
|
|
"num_tokens": 25045301.0,
|
|
"step": 12800
|
|
},
|
|
{
|
|
"entropy": 6.259069728851318,
|
|
"epoch": 1.280001999300245,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004844081996171137,
|
|
"loss": 5.8216,
|
|
"mean_token_accuracy": 0.17064380645751953,
|
|
"num_tokens": 25055576.0,
|
|
"step": 12805
|
|
},
|
|
{
|
|
"entropy": 6.154357242584228,
|
|
"epoch": 1.2805018243614734,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000484395142783564,
|
|
"loss": 5.6757,
|
|
"mean_token_accuracy": 0.18060684949159622,
|
|
"num_tokens": 25064077.0,
|
|
"step": 12810
|
|
},
|
|
{
|
|
"entropy": 6.117851972579956,
|
|
"epoch": 1.2810016494227021,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004843820806816863,
|
|
"loss": 5.7038,
|
|
"mean_token_accuracy": 0.18161996454000473,
|
|
"num_tokens": 25072908.0,
|
|
"step": 12815
|
|
},
|
|
{
|
|
"entropy": 6.213370990753174,
|
|
"epoch": 1.2815014744839306,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004843690133118094,
|
|
"loss": 5.7776,
|
|
"mean_token_accuracy": 0.17534168660640717,
|
|
"num_tokens": 25082919.0,
|
|
"step": 12820
|
|
},
|
|
{
|
|
"entropy": 6.277567768096924,
|
|
"epoch": 1.282001299545159,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000484355940674262,
|
|
"loss": 5.8141,
|
|
"mean_token_accuracy": 0.17363958954811096,
|
|
"num_tokens": 25092520.0,
|
|
"step": 12825
|
|
},
|
|
{
|
|
"entropy": 6.287752294540406,
|
|
"epoch": 1.2825011246063878,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048434286276937294,
|
|
"loss": 5.8099,
|
|
"mean_token_accuracy": 0.1680579125881195,
|
|
"num_tokens": 25102638.0,
|
|
"step": 12830
|
|
},
|
|
{
|
|
"entropy": 6.227025747299194,
|
|
"epoch": 1.2830009496676165,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004843297795974713,
|
|
"loss": 5.7987,
|
|
"mean_token_accuracy": 0.17456592470407487,
|
|
"num_tokens": 25112011.0,
|
|
"step": 12835
|
|
},
|
|
{
|
|
"entropy": 6.28496675491333,
|
|
"epoch": 1.283500774728845,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004843166911588864,
|
|
"loss": 5.8415,
|
|
"mean_token_accuracy": 0.16926033198833465,
|
|
"num_tokens": 25122051.0,
|
|
"step": 12840
|
|
},
|
|
{
|
|
"entropy": 6.319478178024292,
|
|
"epoch": 1.2840005997900734,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004843035974539473,
|
|
"loss": 5.7911,
|
|
"mean_token_accuracy": 0.17550561875104903,
|
|
"num_tokens": 25131928.0,
|
|
"step": 12845
|
|
},
|
|
{
|
|
"entropy": 6.158261442184449,
|
|
"epoch": 1.2845004248513021,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048429049848298364,
|
|
"loss": 5.6215,
|
|
"mean_token_accuracy": 0.18737874627113343,
|
|
"num_tokens": 25140204.0,
|
|
"step": 12850
|
|
},
|
|
{
|
|
"entropy": 6.212171316146851,
|
|
"epoch": 1.2850002499125306,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048427739424632485,
|
|
"loss": 5.6889,
|
|
"mean_token_accuracy": 0.17787568867206574,
|
|
"num_tokens": 25149445.0,
|
|
"step": 12855
|
|
},
|
|
{
|
|
"entropy": 6.261015558242798,
|
|
"epoch": 1.285500074973759,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00048426428474430055,
|
|
"loss": 5.7503,
|
|
"mean_token_accuracy": 0.1748096838593483,
|
|
"num_tokens": 25159311.0,
|
|
"step": 12860
|
|
},
|
|
{
|
|
"entropy": 6.110807943344116,
|
|
"epoch": 1.2859999000349878,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048425116997724083,
|
|
"loss": 5.6626,
|
|
"mean_token_accuracy": 0.18549840301275253,
|
|
"num_tokens": 25168880.0,
|
|
"step": 12865
|
|
},
|
|
{
|
|
"entropy": 6.175733375549316,
|
|
"epoch": 1.2864997250962165,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00048423804994547555,
|
|
"loss": 5.7359,
|
|
"mean_token_accuracy": 0.17663412690162658,
|
|
"num_tokens": 25177812.0,
|
|
"step": 12870
|
|
},
|
|
{
|
|
"entropy": 6.1649822235107425,
|
|
"epoch": 1.286999550157445,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00048422492464933464,
|
|
"loss": 5.6551,
|
|
"mean_token_accuracy": 0.18246573507785796,
|
|
"num_tokens": 25187831.0,
|
|
"step": 12875
|
|
},
|
|
{
|
|
"entropy": 6.20123143196106,
|
|
"epoch": 1.2874993752186734,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048421179408914857,
|
|
"loss": 5.695,
|
|
"mean_token_accuracy": 0.17855336666107177,
|
|
"num_tokens": 25198164.0,
|
|
"step": 12880
|
|
},
|
|
{
|
|
"entropy": 6.299442720413208,
|
|
"epoch": 1.2879992002799021,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00048419865826524757,
|
|
"loss": 5.8105,
|
|
"mean_token_accuracy": 0.17440304011106492,
|
|
"num_tokens": 25208740.0,
|
|
"step": 12885
|
|
},
|
|
{
|
|
"entropy": 6.241351127624512,
|
|
"epoch": 1.2884990253411306,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048418551717796217,
|
|
"loss": 5.7243,
|
|
"mean_token_accuracy": 0.18224776089191436,
|
|
"num_tokens": 25218475.0,
|
|
"step": 12890
|
|
},
|
|
{
|
|
"entropy": 6.299259090423584,
|
|
"epoch": 1.288998850402359,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00048417237082762295,
|
|
"loss": 5.8248,
|
|
"mean_token_accuracy": 0.1745289921760559,
|
|
"num_tokens": 25227943.0,
|
|
"step": 12895
|
|
},
|
|
{
|
|
"entropy": 6.127731037139893,
|
|
"epoch": 1.2894986754635878,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048415921921456074,
|
|
"loss": 5.646,
|
|
"mean_token_accuracy": 0.1840042158961296,
|
|
"num_tokens": 25237131.0,
|
|
"step": 12900
|
|
},
|
|
{
|
|
"entropy": 6.2509315490722654,
|
|
"epoch": 1.2899985005248162,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048414606233910634,
|
|
"loss": 5.7207,
|
|
"mean_token_accuracy": 0.17842586636543273,
|
|
"num_tokens": 25245983.0,
|
|
"step": 12905
|
|
},
|
|
{
|
|
"entropy": 6.16154899597168,
|
|
"epoch": 1.290498325586045,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004841329002015909,
|
|
"loss": 5.7537,
|
|
"mean_token_accuracy": 0.17154667824506759,
|
|
"num_tokens": 25255155.0,
|
|
"step": 12910
|
|
},
|
|
{
|
|
"entropy": 6.207403755187988,
|
|
"epoch": 1.2909981506472734,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00048411973280234553,
|
|
"loss": 5.6725,
|
|
"mean_token_accuracy": 0.17895156741142274,
|
|
"num_tokens": 25265207.0,
|
|
"step": 12915
|
|
},
|
|
{
|
|
"entropy": 6.185838890075684,
|
|
"epoch": 1.291497975708502,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048410656014170135,
|
|
"loss": 5.6892,
|
|
"mean_token_accuracy": 0.1877056762576103,
|
|
"num_tokens": 25273995.0,
|
|
"step": 12920
|
|
},
|
|
{
|
|
"entropy": 6.179584598541259,
|
|
"epoch": 1.2919978007697306,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048409338221999,
|
|
"loss": 5.6797,
|
|
"mean_token_accuracy": 0.17760975658893585,
|
|
"num_tokens": 25284334.0,
|
|
"step": 12925
|
|
},
|
|
{
|
|
"entropy": 6.179208660125733,
|
|
"epoch": 1.292497625830959,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00048408019903754297,
|
|
"loss": 5.7314,
|
|
"mean_token_accuracy": 0.1824210524559021,
|
|
"num_tokens": 25294360.0,
|
|
"step": 12930
|
|
},
|
|
{
|
|
"entropy": 6.2364240169525145,
|
|
"epoch": 1.2929974508921878,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000484067010594692,
|
|
"loss": 5.7398,
|
|
"mean_token_accuracy": 0.1782961145043373,
|
|
"num_tokens": 25302869.0,
|
|
"step": 12935
|
|
},
|
|
{
|
|
"entropy": 6.1989439010620115,
|
|
"epoch": 1.2934972759534162,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.00048405381689176877,
|
|
"loss": 5.689,
|
|
"mean_token_accuracy": 0.18615340143442155,
|
|
"num_tokens": 25313825.0,
|
|
"step": 12940
|
|
},
|
|
{
|
|
"entropy": 6.2719227313995365,
|
|
"epoch": 1.293997101014645,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00048404061792910527,
|
|
"loss": 5.7486,
|
|
"mean_token_accuracy": 0.17829475849866866,
|
|
"num_tokens": 25323212.0,
|
|
"step": 12945
|
|
},
|
|
{
|
|
"entropy": 6.326823043823242,
|
|
"epoch": 1.2944969260758734,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00048402741370703363,
|
|
"loss": 5.8586,
|
|
"mean_token_accuracy": 0.17034607082605363,
|
|
"num_tokens": 25333037.0,
|
|
"step": 12950
|
|
},
|
|
{
|
|
"entropy": 6.238680219650268,
|
|
"epoch": 1.294996751137102,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004840142042258861,
|
|
"loss": 5.7632,
|
|
"mean_token_accuracy": 0.17785582989454268,
|
|
"num_tokens": 25342810.0,
|
|
"step": 12955
|
|
},
|
|
{
|
|
"entropy": 6.228901815414429,
|
|
"epoch": 1.2954965761983306,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000484000989485995,
|
|
"loss": 5.8577,
|
|
"mean_token_accuracy": 0.16967157274484634,
|
|
"num_tokens": 25353119.0,
|
|
"step": 12960
|
|
},
|
|
{
|
|
"entropy": 6.2599632263183596,
|
|
"epoch": 1.295996401259559,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048398776948769265,
|
|
"loss": 5.735,
|
|
"mean_token_accuracy": 0.18205017894506453,
|
|
"num_tokens": 25363450.0,
|
|
"step": 12965
|
|
},
|
|
{
|
|
"entropy": 6.217937898635864,
|
|
"epoch": 1.2964962263207878,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004839745442313119,
|
|
"loss": 5.6789,
|
|
"mean_token_accuracy": 0.17450142353773118,
|
|
"num_tokens": 25372830.0,
|
|
"step": 12970
|
|
},
|
|
{
|
|
"entropy": 6.250495767593383,
|
|
"epoch": 1.2969960513820162,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00048396131371718535,
|
|
"loss": 5.7421,
|
|
"mean_token_accuracy": 0.17225947678089143,
|
|
"num_tokens": 25382102.0,
|
|
"step": 12975
|
|
},
|
|
{
|
|
"entropy": 6.244801139831543,
|
|
"epoch": 1.297495876443245,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048394807794564586,
|
|
"loss": 5.8237,
|
|
"mean_token_accuracy": 0.17267883569002151,
|
|
"num_tokens": 25390817.0,
|
|
"step": 12980
|
|
},
|
|
{
|
|
"entropy": 6.213935375213623,
|
|
"epoch": 1.2979957015044734,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004839348369170266,
|
|
"loss": 5.7997,
|
|
"mean_token_accuracy": 0.1718600332736969,
|
|
"num_tokens": 25399958.0,
|
|
"step": 12985
|
|
},
|
|
{
|
|
"entropy": 6.286227893829346,
|
|
"epoch": 1.298495526565702,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048392159063166055,
|
|
"loss": 5.7633,
|
|
"mean_token_accuracy": 0.1750280126929283,
|
|
"num_tokens": 25410870.0,
|
|
"step": 12990
|
|
},
|
|
{
|
|
"entropy": 6.3040272235870365,
|
|
"epoch": 1.2989953516269306,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004839083390898811,
|
|
"loss": 5.8249,
|
|
"mean_token_accuracy": 0.16492467373609543,
|
|
"num_tokens": 25420906.0,
|
|
"step": 12995
|
|
},
|
|
{
|
|
"entropy": 6.265566873550415,
|
|
"epoch": 1.299495176688159,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004838950822920215,
|
|
"loss": 5.7649,
|
|
"mean_token_accuracy": 0.17018725574016572,
|
|
"num_tokens": 25430046.0,
|
|
"step": 13000
|
|
},
|
|
{
|
|
"entropy": 6.205768775939942,
|
|
"epoch": 1.2999950017493878,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004838818202384155,
|
|
"loss": 5.7068,
|
|
"mean_token_accuracy": 0.1850733771920204,
|
|
"num_tokens": 25438785.0,
|
|
"step": 13005
|
|
},
|
|
{
|
|
"entropy": 6.204996776580811,
|
|
"epoch": 1.3004948268106162,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048386855292939664,
|
|
"loss": 5.7862,
|
|
"mean_token_accuracy": 0.17885820865631102,
|
|
"num_tokens": 25448815.0,
|
|
"step": 13010
|
|
},
|
|
{
|
|
"entropy": 6.218413782119751,
|
|
"epoch": 1.300994651871845,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004838552803652986,
|
|
"loss": 5.7232,
|
|
"mean_token_accuracy": 0.17769965678453445,
|
|
"num_tokens": 25458528.0,
|
|
"step": 13015
|
|
},
|
|
{
|
|
"entropy": 6.204597854614258,
|
|
"epoch": 1.3014944769330734,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048384200254645557,
|
|
"loss": 5.6607,
|
|
"mean_token_accuracy": 0.1842055544257164,
|
|
"num_tokens": 25467678.0,
|
|
"step": 13020
|
|
},
|
|
{
|
|
"entropy": 6.096461057662964,
|
|
"epoch": 1.301994301994302,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048382871947320145,
|
|
"loss": 5.6472,
|
|
"mean_token_accuracy": 0.1928757280111313,
|
|
"num_tokens": 25478601.0,
|
|
"step": 13025
|
|
},
|
|
{
|
|
"entropy": 6.236186885833741,
|
|
"epoch": 1.3024941270555306,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004838154311458705,
|
|
"loss": 5.7187,
|
|
"mean_token_accuracy": 0.17450127750635147,
|
|
"num_tokens": 25489439.0,
|
|
"step": 13030
|
|
},
|
|
{
|
|
"entropy": 6.167818021774292,
|
|
"epoch": 1.302993952116759,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00048380213756479704,
|
|
"loss": 5.7357,
|
|
"mean_token_accuracy": 0.17700933367013932,
|
|
"num_tokens": 25499976.0,
|
|
"step": 13035
|
|
},
|
|
{
|
|
"entropy": 6.267694139480591,
|
|
"epoch": 1.3034937771779878,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00048378883873031553,
|
|
"loss": 5.8941,
|
|
"mean_token_accuracy": 0.17058451175689698,
|
|
"num_tokens": 25509737.0,
|
|
"step": 13040
|
|
},
|
|
{
|
|
"entropy": 6.322250461578369,
|
|
"epoch": 1.3039936022392162,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004837755346427605,
|
|
"loss": 5.7922,
|
|
"mean_token_accuracy": 0.176069013774395,
|
|
"num_tokens": 25519130.0,
|
|
"step": 13045
|
|
},
|
|
{
|
|
"entropy": 6.255865001678467,
|
|
"epoch": 1.3044934273004447,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00048376222530246684,
|
|
"loss": 5.7868,
|
|
"mean_token_accuracy": 0.17736284136772157,
|
|
"num_tokens": 25528625.0,
|
|
"step": 13050
|
|
},
|
|
{
|
|
"entropy": 6.267289495468139,
|
|
"epoch": 1.3049932523616734,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048374891070976925,
|
|
"loss": 5.8142,
|
|
"mean_token_accuracy": 0.16600591987371444,
|
|
"num_tokens": 25537912.0,
|
|
"step": 13055
|
|
},
|
|
{
|
|
"entropy": 6.274161338806152,
|
|
"epoch": 1.305493077422902,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004837355908650028,
|
|
"loss": 5.7876,
|
|
"mean_token_accuracy": 0.17701202183961867,
|
|
"num_tokens": 25548622.0,
|
|
"step": 13060
|
|
},
|
|
{
|
|
"entropy": 6.142975091934204,
|
|
"epoch": 1.3059929024841306,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004837222657685026,
|
|
"loss": 5.5704,
|
|
"mean_token_accuracy": 0.19098460525274277,
|
|
"num_tokens": 25558322.0,
|
|
"step": 13065
|
|
},
|
|
{
|
|
"entropy": 6.245699882507324,
|
|
"epoch": 1.306492727545359,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048370893542060383,
|
|
"loss": 5.7597,
|
|
"mean_token_accuracy": 0.17440939098596572,
|
|
"num_tokens": 25568586.0,
|
|
"step": 13070
|
|
},
|
|
{
|
|
"entropy": 6.253795576095581,
|
|
"epoch": 1.3069925526065878,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004836955998216421,
|
|
"loss": 5.7825,
|
|
"mean_token_accuracy": 0.1734976887702942,
|
|
"num_tokens": 25577405.0,
|
|
"step": 13075
|
|
},
|
|
{
|
|
"entropy": 6.145668363571167,
|
|
"epoch": 1.3074923776678162,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048368225897195264,
|
|
"loss": 5.5829,
|
|
"mean_token_accuracy": 0.19015832990407944,
|
|
"num_tokens": 25587719.0,
|
|
"step": 13080
|
|
},
|
|
{
|
|
"entropy": 6.21374363899231,
|
|
"epoch": 1.3079922027290447,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00048366891287187133,
|
|
"loss": 5.7724,
|
|
"mean_token_accuracy": 0.17455062866210938,
|
|
"num_tokens": 25597334.0,
|
|
"step": 13085
|
|
},
|
|
{
|
|
"entropy": 6.335827016830445,
|
|
"epoch": 1.3084920277902734,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004836555615217337,
|
|
"loss": 5.9215,
|
|
"mean_token_accuracy": 0.16298633813858032,
|
|
"num_tokens": 25606684.0,
|
|
"step": 13090
|
|
},
|
|
{
|
|
"entropy": 6.2142266750335695,
|
|
"epoch": 1.308991852851502,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004836422049218761,
|
|
"loss": 5.6677,
|
|
"mean_token_accuracy": 0.18307684361934662,
|
|
"num_tokens": 25615808.0,
|
|
"step": 13095
|
|
},
|
|
{
|
|
"entropy": 6.157536888122559,
|
|
"epoch": 1.3094916779127306,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048362884307263416,
|
|
"loss": 5.6808,
|
|
"mean_token_accuracy": 0.18365222960710526,
|
|
"num_tokens": 25626444.0,
|
|
"step": 13100
|
|
},
|
|
{
|
|
"entropy": 6.232510995864868,
|
|
"epoch": 1.309991502973959,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00048361547597434426,
|
|
"loss": 5.6833,
|
|
"mean_token_accuracy": 0.17635302245616913,
|
|
"num_tokens": 25635730.0,
|
|
"step": 13105
|
|
},
|
|
{
|
|
"entropy": 6.277277898788452,
|
|
"epoch": 1.3104913280351878,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00048360210362734257,
|
|
"loss": 5.766,
|
|
"mean_token_accuracy": 0.17441450357437133,
|
|
"num_tokens": 25645938.0,
|
|
"step": 13110
|
|
},
|
|
{
|
|
"entropy": 6.258178997039795,
|
|
"epoch": 1.3109911530964162,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004835887260319657,
|
|
"loss": 5.8554,
|
|
"mean_token_accuracy": 0.16857534497976304,
|
|
"num_tokens": 25656135.0,
|
|
"step": 13115
|
|
},
|
|
{
|
|
"entropy": 6.259627914428711,
|
|
"epoch": 1.3114909781576447,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004835753431885502,
|
|
"loss": 5.8344,
|
|
"mean_token_accuracy": 0.16925535053014756,
|
|
"num_tokens": 25666134.0,
|
|
"step": 13120
|
|
},
|
|
{
|
|
"entropy": 6.284022092819214,
|
|
"epoch": 1.3119908032188734,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00048356195509743265,
|
|
"loss": 5.8847,
|
|
"mean_token_accuracy": 0.16684625968337058,
|
|
"num_tokens": 25675716.0,
|
|
"step": 13125
|
|
},
|
|
{
|
|
"entropy": 6.2464978218078615,
|
|
"epoch": 1.312490628280102,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00048354856175895,
|
|
"loss": 5.7369,
|
|
"mean_token_accuracy": 0.1748029038310051,
|
|
"num_tokens": 25685814.0,
|
|
"step": 13130
|
|
},
|
|
{
|
|
"entropy": 6.235641860961914,
|
|
"epoch": 1.3129904533413306,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004835351631734392,
|
|
"loss": 5.7132,
|
|
"mean_token_accuracy": 0.17935896813869476,
|
|
"num_tokens": 25694995.0,
|
|
"step": 13135
|
|
},
|
|
{
|
|
"entropy": 6.259634733200073,
|
|
"epoch": 1.313490278402559,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004835217593412374,
|
|
"loss": 5.776,
|
|
"mean_token_accuracy": 0.1772772952914238,
|
|
"num_tokens": 25705041.0,
|
|
"step": 13140
|
|
},
|
|
{
|
|
"entropy": 6.2441822528839115,
|
|
"epoch": 1.3139901034637878,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004835083502626818,
|
|
"loss": 5.7554,
|
|
"mean_token_accuracy": 0.17774358689785003,
|
|
"num_tokens": 25715830.0,
|
|
"step": 13145
|
|
},
|
|
{
|
|
"entropy": 6.206713056564331,
|
|
"epoch": 1.3144899285250162,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00048349493593810973,
|
|
"loss": 5.7675,
|
|
"mean_token_accuracy": 0.1700425162911415,
|
|
"num_tokens": 25725357.0,
|
|
"step": 13150
|
|
},
|
|
{
|
|
"entropy": 6.23039608001709,
|
|
"epoch": 1.3149897535862447,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004834815163678587,
|
|
"loss": 5.797,
|
|
"mean_token_accuracy": 0.17578988373279572,
|
|
"num_tokens": 25735720.0,
|
|
"step": 13155
|
|
},
|
|
{
|
|
"entropy": 6.293112659454346,
|
|
"epoch": 1.3154895786474734,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004834680915522664,
|
|
"loss": 5.7903,
|
|
"mean_token_accuracy": 0.17059239149093627,
|
|
"num_tokens": 25745728.0,
|
|
"step": 13160
|
|
},
|
|
{
|
|
"entropy": 6.260885906219483,
|
|
"epoch": 1.3159894037087019,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004834546614916705,
|
|
"loss": 5.769,
|
|
"mean_token_accuracy": 0.1755282461643219,
|
|
"num_tokens": 25755917.0,
|
|
"step": 13165
|
|
},
|
|
{
|
|
"entropy": 6.2756482601165775,
|
|
"epoch": 1.3164892287699306,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00048344122618640905,
|
|
"loss": 5.8058,
|
|
"mean_token_accuracy": 0.18042713403701782,
|
|
"num_tokens": 25766195.0,
|
|
"step": 13170
|
|
},
|
|
{
|
|
"entropy": 6.237008476257325,
|
|
"epoch": 1.316989053831159,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004834277856368199,
|
|
"loss": 5.7103,
|
|
"mean_token_accuracy": 0.18123453706502915,
|
|
"num_tokens": 25774134.0,
|
|
"step": 13175
|
|
},
|
|
{
|
|
"entropy": 6.1179839134216305,
|
|
"epoch": 1.3174888788923877,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048341433984324127,
|
|
"loss": 5.7564,
|
|
"mean_token_accuracy": 0.18076372593641282,
|
|
"num_tokens": 25783377.0,
|
|
"step": 13180
|
|
},
|
|
{
|
|
"entropy": 6.106088542938233,
|
|
"epoch": 1.3179887039536162,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00048340088880601163,
|
|
"loss": 5.5554,
|
|
"mean_token_accuracy": 0.19430503398180007,
|
|
"num_tokens": 25793562.0,
|
|
"step": 13185
|
|
},
|
|
{
|
|
"entropy": 6.2316975593566895,
|
|
"epoch": 1.3184885290148447,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004833874325254691,
|
|
"loss": 5.7487,
|
|
"mean_token_accuracy": 0.18120116442441941,
|
|
"num_tokens": 25803299.0,
|
|
"step": 13190
|
|
},
|
|
{
|
|
"entropy": 6.27415132522583,
|
|
"epoch": 1.3189883540760734,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00048337397100195245,
|
|
"loss": 5.8215,
|
|
"mean_token_accuracy": 0.1677117183804512,
|
|
"num_tokens": 25813053.0,
|
|
"step": 13195
|
|
},
|
|
{
|
|
"entropy": 6.302714395523071,
|
|
"epoch": 1.3194881791373019,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004833605042358003,
|
|
"loss": 5.8188,
|
|
"mean_token_accuracy": 0.1724894881248474,
|
|
"num_tokens": 25822311.0,
|
|
"step": 13200
|
|
},
|
|
{
|
|
"entropy": 6.2269251346588135,
|
|
"epoch": 1.3199880041985306,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004833470322273515,
|
|
"loss": 5.8194,
|
|
"mean_token_accuracy": 0.16559606343507766,
|
|
"num_tokens": 25832473.0,
|
|
"step": 13205
|
|
},
|
|
{
|
|
"entropy": 6.267454195022583,
|
|
"epoch": 1.320487829259759,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048333355497694506,
|
|
"loss": 5.7309,
|
|
"mean_token_accuracy": 0.1778992921113968,
|
|
"num_tokens": 25840919.0,
|
|
"step": 13210
|
|
},
|
|
{
|
|
"entropy": 6.222518110275269,
|
|
"epoch": 1.3209876543209877,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004833200724849199,
|
|
"loss": 5.7237,
|
|
"mean_token_accuracy": 0.17681789994239808,
|
|
"num_tokens": 25850517.0,
|
|
"step": 13215
|
|
},
|
|
{
|
|
"entropy": 6.322263717651367,
|
|
"epoch": 1.3214874793822162,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048330658475161526,
|
|
"loss": 5.8862,
|
|
"mean_token_accuracy": 0.1654845029115677,
|
|
"num_tokens": 25861580.0,
|
|
"step": 13220
|
|
},
|
|
{
|
|
"entropy": 6.2865993022918705,
|
|
"epoch": 1.3219873044434447,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004832930917773706,
|
|
"loss": 5.7692,
|
|
"mean_token_accuracy": 0.17851028740406036,
|
|
"num_tokens": 25872383.0,
|
|
"step": 13225
|
|
},
|
|
{
|
|
"entropy": 6.230095291137696,
|
|
"epoch": 1.3224871295046734,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048327959356252544,
|
|
"loss": 5.8026,
|
|
"mean_token_accuracy": 0.17363771051168442,
|
|
"num_tokens": 25883016.0,
|
|
"step": 13230
|
|
},
|
|
{
|
|
"entropy": 6.212831687927246,
|
|
"epoch": 1.3229869545659019,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004832660901074192,
|
|
"loss": 5.777,
|
|
"mean_token_accuracy": 0.17354009598493575,
|
|
"num_tokens": 25892810.0,
|
|
"step": 13235
|
|
},
|
|
{
|
|
"entropy": 6.251553916931153,
|
|
"epoch": 1.3234867796271306,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00048325258141239174,
|
|
"loss": 5.7375,
|
|
"mean_token_accuracy": 0.1767112895846367,
|
|
"num_tokens": 25902548.0,
|
|
"step": 13240
|
|
},
|
|
{
|
|
"entropy": 6.19931993484497,
|
|
"epoch": 1.323986604688359,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004832390674777829,
|
|
"loss": 5.6744,
|
|
"mean_token_accuracy": 0.18609953075647354,
|
|
"num_tokens": 25911572.0,
|
|
"step": 13245
|
|
},
|
|
{
|
|
"entropy": 6.1704295635223385,
|
|
"epoch": 1.3244864297495877,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00048322554830393274,
|
|
"loss": 5.6803,
|
|
"mean_token_accuracy": 0.17577311247587205,
|
|
"num_tokens": 25921226.0,
|
|
"step": 13250
|
|
},
|
|
{
|
|
"entropy": 6.200627708435059,
|
|
"epoch": 1.3249862548108162,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004832120238911813,
|
|
"loss": 5.7692,
|
|
"mean_token_accuracy": 0.1699688270688057,
|
|
"num_tokens": 25930920.0,
|
|
"step": 13255
|
|
},
|
|
{
|
|
"entropy": 6.230641555786133,
|
|
"epoch": 1.3254860798720447,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000483198494239869,
|
|
"loss": 5.7122,
|
|
"mean_token_accuracy": 0.18619170635938645,
|
|
"num_tokens": 25941042.0,
|
|
"step": 13260
|
|
},
|
|
{
|
|
"entropy": 6.3052342414855955,
|
|
"epoch": 1.3259859049332734,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00048318495935033615,
|
|
"loss": 5.8737,
|
|
"mean_token_accuracy": 0.1619127109646797,
|
|
"num_tokens": 25950696.0,
|
|
"step": 13265
|
|
},
|
|
{
|
|
"entropy": 6.268920803070069,
|
|
"epoch": 1.3264857299945019,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048317141922292326,
|
|
"loss": 5.7221,
|
|
"mean_token_accuracy": 0.18108566105365753,
|
|
"num_tokens": 25960034.0,
|
|
"step": 13270
|
|
},
|
|
{
|
|
"entropy": 6.201660299301148,
|
|
"epoch": 1.3269855550557306,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004831578738579711,
|
|
"loss": 5.7439,
|
|
"mean_token_accuracy": 0.1816033110022545,
|
|
"num_tokens": 25969264.0,
|
|
"step": 13275
|
|
},
|
|
{
|
|
"entropy": 6.295983409881591,
|
|
"epoch": 1.327485380116959,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004831443232558203,
|
|
"loss": 5.8568,
|
|
"mean_token_accuracy": 0.1682647332549095,
|
|
"num_tokens": 25979046.0,
|
|
"step": 13280
|
|
},
|
|
{
|
|
"entropy": 6.247390556335449,
|
|
"epoch": 1.3279852051781877,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00048313076741681186,
|
|
"loss": 5.7707,
|
|
"mean_token_accuracy": 0.17020653784275055,
|
|
"num_tokens": 25988797.0,
|
|
"step": 13285
|
|
},
|
|
{
|
|
"entropy": 6.249956369400024,
|
|
"epoch": 1.3284850302394162,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00048311720634128697,
|
|
"loss": 5.663,
|
|
"mean_token_accuracy": 0.18328728377819062,
|
|
"num_tokens": 25997586.0,
|
|
"step": 13290
|
|
},
|
|
{
|
|
"entropy": 6.226766920089721,
|
|
"epoch": 1.3289848553006447,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004831036400295867,
|
|
"loss": 5.8226,
|
|
"mean_token_accuracy": 0.16795846521854402,
|
|
"num_tokens": 26007369.0,
|
|
"step": 13295
|
|
},
|
|
{
|
|
"entropy": 6.257897090911865,
|
|
"epoch": 1.3294846803618734,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048309006848205237,
|
|
"loss": 5.7718,
|
|
"mean_token_accuracy": 0.17309339195489884,
|
|
"num_tokens": 26017063.0,
|
|
"step": 13300
|
|
},
|
|
{
|
|
"entropy": 6.266967487335205,
|
|
"epoch": 1.3299845054231019,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004830764916990255,
|
|
"loss": 5.7175,
|
|
"mean_token_accuracy": 0.17861319482326507,
|
|
"num_tokens": 26026555.0,
|
|
"step": 13305
|
|
},
|
|
{
|
|
"entropy": 6.3272840023040775,
|
|
"epoch": 1.3304843304843303,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004830629096808476,
|
|
"loss": 5.7973,
|
|
"mean_token_accuracy": 0.17283224165439606,
|
|
"num_tokens": 26036698.0,
|
|
"step": 13310
|
|
},
|
|
{
|
|
"entropy": 6.23427791595459,
|
|
"epoch": 1.330984155545559,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004830493224278605,
|
|
"loss": 5.7559,
|
|
"mean_token_accuracy": 0.17911558449268342,
|
|
"num_tokens": 26046462.0,
|
|
"step": 13315
|
|
},
|
|
{
|
|
"entropy": 6.238739013671875,
|
|
"epoch": 1.3314839806067877,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004830357299404059,
|
|
"loss": 5.7522,
|
|
"mean_token_accuracy": 0.18504160940647124,
|
|
"num_tokens": 26056180.0,
|
|
"step": 13320
|
|
},
|
|
{
|
|
"entropy": 6.3000874519348145,
|
|
"epoch": 1.3319838056680162,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004830221322188259,
|
|
"loss": 5.7487,
|
|
"mean_token_accuracy": 0.17041344195604324,
|
|
"num_tokens": 26065621.0,
|
|
"step": 13325
|
|
},
|
|
{
|
|
"entropy": 6.295819711685181,
|
|
"epoch": 1.3324836307292447,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004830085292634626,
|
|
"loss": 5.7873,
|
|
"mean_token_accuracy": 0.1763737753033638,
|
|
"num_tokens": 26074640.0,
|
|
"step": 13330
|
|
},
|
|
{
|
|
"entropy": 6.232799911499024,
|
|
"epoch": 1.3329834557904734,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048299492107465816,
|
|
"loss": 5.7408,
|
|
"mean_token_accuracy": 0.17464609891176225,
|
|
"num_tokens": 26084221.0,
|
|
"step": 13335
|
|
},
|
|
{
|
|
"entropy": 6.242247867584228,
|
|
"epoch": 1.3334832808517019,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004829813076527551,
|
|
"loss": 5.7851,
|
|
"mean_token_accuracy": 0.1735181912779808,
|
|
"num_tokens": 26095065.0,
|
|
"step": 13340
|
|
},
|
|
{
|
|
"entropy": 6.238558673858643,
|
|
"epoch": 1.3339831059129303,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00048296768899809577,
|
|
"loss": 5.701,
|
|
"mean_token_accuracy": 0.18452496826648712,
|
|
"num_tokens": 26104978.0,
|
|
"step": 13345
|
|
},
|
|
{
|
|
"entropy": 6.163738632202149,
|
|
"epoch": 1.334482930974159,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00048295406511102303,
|
|
"loss": 5.6728,
|
|
"mean_token_accuracy": 0.18179230391979218,
|
|
"num_tokens": 26115023.0,
|
|
"step": 13350
|
|
},
|
|
{
|
|
"entropy": 6.276685047149658,
|
|
"epoch": 1.3349827560353877,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004829404359918795,
|
|
"loss": 5.8206,
|
|
"mean_token_accuracy": 0.17295039147138597,
|
|
"num_tokens": 26124533.0,
|
|
"step": 13355
|
|
},
|
|
{
|
|
"entropy": 6.26715497970581,
|
|
"epoch": 1.3354825810966162,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000482926801641008,
|
|
"loss": 5.7252,
|
|
"mean_token_accuracy": 0.1796407714486122,
|
|
"num_tokens": 26134466.0,
|
|
"step": 13360
|
|
},
|
|
{
|
|
"entropy": 6.230587291717529,
|
|
"epoch": 1.3359824061578447,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00048291316205875174,
|
|
"loss": 5.7889,
|
|
"mean_token_accuracy": 0.17489252090454102,
|
|
"num_tokens": 26145710.0,
|
|
"step": 13365
|
|
},
|
|
{
|
|
"entropy": 6.196503114700318,
|
|
"epoch": 1.3364822312190734,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048289951724545384,
|
|
"loss": 5.71,
|
|
"mean_token_accuracy": 0.18020857274532318,
|
|
"num_tokens": 26154393.0,
|
|
"step": 13370
|
|
},
|
|
{
|
|
"entropy": 6.141133737564087,
|
|
"epoch": 1.3369820562803019,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048288586720145757,
|
|
"loss": 5.6537,
|
|
"mean_token_accuracy": 0.18572520613670349,
|
|
"num_tokens": 26164230.0,
|
|
"step": 13375
|
|
},
|
|
{
|
|
"entropy": 6.272658061981201,
|
|
"epoch": 1.3374818813415303,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004828722119271064,
|
|
"loss": 5.7422,
|
|
"mean_token_accuracy": 0.18072646260261535,
|
|
"num_tokens": 26174224.0,
|
|
"step": 13380
|
|
},
|
|
{
|
|
"entropy": 6.219463586807251,
|
|
"epoch": 1.337981706402759,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048285855142274375,
|
|
"loss": 5.7254,
|
|
"mean_token_accuracy": 0.18258544951677322,
|
|
"num_tokens": 26183447.0,
|
|
"step": 13385
|
|
},
|
|
{
|
|
"entropy": 6.2940895557403564,
|
|
"epoch": 1.3384815314639877,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004828448856887135,
|
|
"loss": 5.8437,
|
|
"mean_token_accuracy": 0.17329373508691787,
|
|
"num_tokens": 26193479.0,
|
|
"step": 13390
|
|
},
|
|
{
|
|
"entropy": 6.277415323257446,
|
|
"epoch": 1.3389813565252162,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004828312147253595,
|
|
"loss": 5.8115,
|
|
"mean_token_accuracy": 0.168607097864151,
|
|
"num_tokens": 26202493.0,
|
|
"step": 13395
|
|
},
|
|
{
|
|
"entropy": 6.278912973403931,
|
|
"epoch": 1.3394811815864447,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004828175385330255,
|
|
"loss": 5.7794,
|
|
"mean_token_accuracy": 0.1733739823102951,
|
|
"num_tokens": 26212133.0,
|
|
"step": 13400
|
|
},
|
|
{
|
|
"entropy": 6.22666974067688,
|
|
"epoch": 1.3399810066476734,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004828038571120558,
|
|
"loss": 5.7648,
|
|
"mean_token_accuracy": 0.1856029748916626,
|
|
"num_tokens": 26222905.0,
|
|
"step": 13405
|
|
},
|
|
{
|
|
"entropy": 6.278553581237793,
|
|
"epoch": 1.3404808317089019,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048279017046279446,
|
|
"loss": 5.8023,
|
|
"mean_token_accuracy": 0.16860370486974716,
|
|
"num_tokens": 26234273.0,
|
|
"step": 13410
|
|
},
|
|
{
|
|
"entropy": 6.214068078994751,
|
|
"epoch": 1.3409806567701303,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00048277647858558596,
|
|
"loss": 5.6814,
|
|
"mean_token_accuracy": 0.1826475590467453,
|
|
"num_tokens": 26243965.0,
|
|
"step": 13415
|
|
},
|
|
{
|
|
"entropy": 6.239569425582886,
|
|
"epoch": 1.341480481831359,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048276278148077465,
|
|
"loss": 5.7489,
|
|
"mean_token_accuracy": 0.18083592057228087,
|
|
"num_tokens": 26253401.0,
|
|
"step": 13420
|
|
},
|
|
{
|
|
"entropy": 6.223789310455322,
|
|
"epoch": 1.3419803068925875,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00048274907914870526,
|
|
"loss": 5.7097,
|
|
"mean_token_accuracy": 0.17579205185174943,
|
|
"num_tokens": 26262481.0,
|
|
"step": 13425
|
|
},
|
|
{
|
|
"entropy": 6.3025829792022705,
|
|
"epoch": 1.3424801319538162,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048273537158972246,
|
|
"loss": 5.8758,
|
|
"mean_token_accuracy": 0.1697637543082237,
|
|
"num_tokens": 26271153.0,
|
|
"step": 13430
|
|
},
|
|
{
|
|
"entropy": 6.3132048606872555,
|
|
"epoch": 1.3429799570150447,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048272165880417124,
|
|
"loss": 5.9031,
|
|
"mean_token_accuracy": 0.1638144239783287,
|
|
"num_tokens": 26281047.0,
|
|
"step": 13435
|
|
},
|
|
{
|
|
"entropy": 6.326367950439453,
|
|
"epoch": 1.3434797820762734,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00048270794079239643,
|
|
"loss": 5.8159,
|
|
"mean_token_accuracy": 0.1682913139462471,
|
|
"num_tokens": 26291029.0,
|
|
"step": 13440
|
|
},
|
|
{
|
|
"entropy": 6.249785423278809,
|
|
"epoch": 1.3439796071375019,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048269421755474336,
|
|
"loss": 5.7651,
|
|
"mean_token_accuracy": 0.17182836681604385,
|
|
"num_tokens": 26300637.0,
|
|
"step": 13445
|
|
},
|
|
{
|
|
"entropy": 6.212202882766723,
|
|
"epoch": 1.3444794321987303,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004826804890915572,
|
|
"loss": 5.8206,
|
|
"mean_token_accuracy": 0.16933304518461229,
|
|
"num_tokens": 26309867.0,
|
|
"step": 13450
|
|
},
|
|
{
|
|
"entropy": 6.2981184959411625,
|
|
"epoch": 1.344979257259959,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004826667554031834,
|
|
"loss": 5.7127,
|
|
"mean_token_accuracy": 0.18237331360578538,
|
|
"num_tokens": 26318691.0,
|
|
"step": 13455
|
|
},
|
|
{
|
|
"entropy": 6.327997064590454,
|
|
"epoch": 1.3454790823211875,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004826530164899674,
|
|
"loss": 5.8077,
|
|
"mean_token_accuracy": 0.17460080832242966,
|
|
"num_tokens": 26327294.0,
|
|
"step": 13460
|
|
},
|
|
{
|
|
"entropy": 6.2126728057861325,
|
|
"epoch": 1.3459789073824162,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00048263927235225505,
|
|
"loss": 5.7781,
|
|
"mean_token_accuracy": 0.17812958508729934,
|
|
"num_tokens": 26339965.0,
|
|
"step": 13465
|
|
},
|
|
{
|
|
"entropy": 6.266047477722168,
|
|
"epoch": 1.3464787324436447,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004826255229903919,
|
|
"loss": 5.7218,
|
|
"mean_token_accuracy": 0.17947520464658737,
|
|
"num_tokens": 26350447.0,
|
|
"step": 13470
|
|
},
|
|
{
|
|
"entropy": 6.271970605850219,
|
|
"epoch": 1.3469785575048734,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048261176840472416,
|
|
"loss": 5.7764,
|
|
"mean_token_accuracy": 0.17459502518177034,
|
|
"num_tokens": 26359641.0,
|
|
"step": 13475
|
|
},
|
|
{
|
|
"entropy": 6.250219297409058,
|
|
"epoch": 1.3474783825661019,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00048259800859559764,
|
|
"loss": 5.9032,
|
|
"mean_token_accuracy": 0.16529819816350938,
|
|
"num_tokens": 26369161.0,
|
|
"step": 13480
|
|
},
|
|
{
|
|
"entropy": 6.22729525566101,
|
|
"epoch": 1.3479782076273303,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004825842435633587,
|
|
"loss": 5.7181,
|
|
"mean_token_accuracy": 0.1831057369709015,
|
|
"num_tokens": 26379592.0,
|
|
"step": 13485
|
|
},
|
|
{
|
|
"entropy": 6.2450323581695555,
|
|
"epoch": 1.348478032688559,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00048257047330835354,
|
|
"loss": 5.6991,
|
|
"mean_token_accuracy": 0.18238264173269272,
|
|
"num_tokens": 26389164.0,
|
|
"step": 13490
|
|
},
|
|
{
|
|
"entropy": 6.2462132453918455,
|
|
"epoch": 1.3489778577497875,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048255669783092876,
|
|
"loss": 5.8056,
|
|
"mean_token_accuracy": 0.17288618981838227,
|
|
"num_tokens": 26399574.0,
|
|
"step": 13495
|
|
},
|
|
{
|
|
"entropy": 6.1981123924255375,
|
|
"epoch": 1.3494776828110162,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00048254291713143083,
|
|
"loss": 5.7218,
|
|
"mean_token_accuracy": 0.1841903567314148,
|
|
"num_tokens": 26410240.0,
|
|
"step": 13500
|
|
},
|
|
{
|
|
"entropy": 6.2770367622375485,
|
|
"epoch": 1.3499775078722447,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004825291312102066,
|
|
"loss": 5.6955,
|
|
"mean_token_accuracy": 0.17366819977760314,
|
|
"num_tokens": 26419763.0,
|
|
"step": 13505
|
|
},
|
|
{
|
|
"entropy": 6.271602630615234,
|
|
"epoch": 1.3504773329334734,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004825153400676027,
|
|
"loss": 5.8082,
|
|
"mean_token_accuracy": 0.1684109777212143,
|
|
"num_tokens": 26429370.0,
|
|
"step": 13510
|
|
},
|
|
{
|
|
"entropy": 6.219728946685791,
|
|
"epoch": 1.3509771579947019,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004825015437039663,
|
|
"loss": 5.7326,
|
|
"mean_token_accuracy": 0.18093548715114594,
|
|
"num_tokens": 26438425.0,
|
|
"step": 13515
|
|
},
|
|
{
|
|
"entropy": 6.225958442687988,
|
|
"epoch": 1.3514769830559303,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004824877421196444,
|
|
"loss": 5.7894,
|
|
"mean_token_accuracy": 0.17434113323688508,
|
|
"num_tokens": 26448039.0,
|
|
"step": 13520
|
|
},
|
|
{
|
|
"entropy": 6.26229829788208,
|
|
"epoch": 1.351976808117159,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004824739353149844,
|
|
"loss": 5.7219,
|
|
"mean_token_accuracy": 0.18277289122343063,
|
|
"num_tokens": 26457682.0,
|
|
"step": 13525
|
|
},
|
|
{
|
|
"entropy": 6.127618026733399,
|
|
"epoch": 1.3524766331783875,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00048246012329033355,
|
|
"loss": 5.6639,
|
|
"mean_token_accuracy": 0.18296421319246292,
|
|
"num_tokens": 26466292.0,
|
|
"step": 13530
|
|
},
|
|
{
|
|
"entropy": 6.284750509262085,
|
|
"epoch": 1.3529764582396162,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048244630604603935,
|
|
"loss": 5.9085,
|
|
"mean_token_accuracy": 0.16855620294809343,
|
|
"num_tokens": 26476880.0,
|
|
"step": 13535
|
|
},
|
|
{
|
|
"entropy": 6.331115579605102,
|
|
"epoch": 1.3534762833008447,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00048243248358244945,
|
|
"loss": 5.809,
|
|
"mean_token_accuracy": 0.17039967179298401,
|
|
"num_tokens": 26486132.0,
|
|
"step": 13540
|
|
},
|
|
{
|
|
"entropy": 6.248620653152466,
|
|
"epoch": 1.3539761083620734,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004824186558999117,
|
|
"loss": 5.7111,
|
|
"mean_token_accuracy": 0.17023017406463622,
|
|
"num_tokens": 26495647.0,
|
|
"step": 13545
|
|
},
|
|
{
|
|
"entropy": 6.089357137680054,
|
|
"epoch": 1.3544759334233019,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048240482299877386,
|
|
"loss": 5.6825,
|
|
"mean_token_accuracy": 0.18619646430015563,
|
|
"num_tokens": 26506048.0,
|
|
"step": 13550
|
|
},
|
|
{
|
|
"entropy": 6.302104330062866,
|
|
"epoch": 1.3549757584845303,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004823909848793841,
|
|
"loss": 5.8187,
|
|
"mean_token_accuracy": 0.17745725959539413,
|
|
"num_tokens": 26515460.0,
|
|
"step": 13555
|
|
},
|
|
{
|
|
"entropy": 6.314521646499633,
|
|
"epoch": 1.355475583545759,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048237714154209053,
|
|
"loss": 5.7738,
|
|
"mean_token_accuracy": 0.17172162234783173,
|
|
"num_tokens": 26526106.0,
|
|
"step": 13560
|
|
},
|
|
{
|
|
"entropy": 6.175665998458863,
|
|
"epoch": 1.3559754086069875,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004823632929872415,
|
|
"loss": 5.6593,
|
|
"mean_token_accuracy": 0.18047255128622056,
|
|
"num_tokens": 26535582.0,
|
|
"step": 13565
|
|
},
|
|
{
|
|
"entropy": 6.219596481323242,
|
|
"epoch": 1.3564752336682162,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00048234943921518524,
|
|
"loss": 5.7081,
|
|
"mean_token_accuracy": 0.17930502444505692,
|
|
"num_tokens": 26544811.0,
|
|
"step": 13570
|
|
},
|
|
{
|
|
"entropy": 6.314125490188599,
|
|
"epoch": 1.3569750587294447,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004823355802262705,
|
|
"loss": 5.8396,
|
|
"mean_token_accuracy": 0.17258551567792893,
|
|
"num_tokens": 26555340.0,
|
|
"step": 13575
|
|
},
|
|
{
|
|
"entropy": 6.2894933223724365,
|
|
"epoch": 1.3574748837906734,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004823217160208459,
|
|
"loss": 5.7395,
|
|
"mean_token_accuracy": 0.17047121673822402,
|
|
"num_tokens": 26564876.0,
|
|
"step": 13580
|
|
},
|
|
{
|
|
"entropy": 6.166099691390992,
|
|
"epoch": 1.3579747088519019,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004823078465992604,
|
|
"loss": 5.7178,
|
|
"mean_token_accuracy": 0.1846370130777359,
|
|
"num_tokens": 26573967.0,
|
|
"step": 13585
|
|
},
|
|
{
|
|
"entropy": 6.235580158233643,
|
|
"epoch": 1.3584745339131303,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004822939719618627,
|
|
"loss": 5.7183,
|
|
"mean_token_accuracy": 0.18249887228012085,
|
|
"num_tokens": 26583753.0,
|
|
"step": 13590
|
|
},
|
|
{
|
|
"entropy": 6.245583343505859,
|
|
"epoch": 1.358974358974359,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000482280092109002,
|
|
"loss": 5.7706,
|
|
"mean_token_accuracy": 0.18000435531139375,
|
|
"num_tokens": 26593214.0,
|
|
"step": 13595
|
|
},
|
|
{
|
|
"entropy": 6.218242883682251,
|
|
"epoch": 1.3594741840355875,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048226620704102757,
|
|
"loss": 5.7835,
|
|
"mean_token_accuracy": 0.17493521720170974,
|
|
"num_tokens": 26603257.0,
|
|
"step": 13600
|
|
},
|
|
{
|
|
"entropy": 6.240775918960571,
|
|
"epoch": 1.359974009096816,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004822523167582886,
|
|
"loss": 5.6913,
|
|
"mean_token_accuracy": 0.18124682754278182,
|
|
"num_tokens": 26612483.0,
|
|
"step": 13605
|
|
},
|
|
{
|
|
"entropy": 6.308703947067261,
|
|
"epoch": 1.3604738341580447,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004822384212611348,
|
|
"loss": 5.8283,
|
|
"mean_token_accuracy": 0.1712574377655983,
|
|
"num_tokens": 26623116.0,
|
|
"step": 13610
|
|
},
|
|
{
|
|
"entropy": 6.286644506454468,
|
|
"epoch": 1.3609736592192734,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048222452054991563,
|
|
"loss": 5.6618,
|
|
"mean_token_accuracy": 0.1817282736301422,
|
|
"num_tokens": 26632648.0,
|
|
"step": 13615
|
|
},
|
|
{
|
|
"entropy": 6.221446800231933,
|
|
"epoch": 1.3614734842805019,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004822106146249808,
|
|
"loss": 5.7251,
|
|
"mean_token_accuracy": 0.17817514538764953,
|
|
"num_tokens": 26642208.0,
|
|
"step": 13620
|
|
},
|
|
{
|
|
"entropy": 6.264418697357177,
|
|
"epoch": 1.3619733093417303,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048219670348668026,
|
|
"loss": 5.7945,
|
|
"mean_token_accuracy": 0.16893005818128587,
|
|
"num_tokens": 26651967.0,
|
|
"step": 13625
|
|
},
|
|
{
|
|
"entropy": 6.193148756027222,
|
|
"epoch": 1.362473134402959,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00048218278713536394,
|
|
"loss": 5.6463,
|
|
"mean_token_accuracy": 0.1835130572319031,
|
|
"num_tokens": 26661138.0,
|
|
"step": 13630
|
|
},
|
|
{
|
|
"entropy": 6.172139596939087,
|
|
"epoch": 1.3629729594641875,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004821688655713821,
|
|
"loss": 5.7829,
|
|
"mean_token_accuracy": 0.17338551133871077,
|
|
"num_tokens": 26671779.0,
|
|
"step": 13635
|
|
},
|
|
{
|
|
"entropy": 6.046289396286011,
|
|
"epoch": 1.363472784525416,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00048215493879508474,
|
|
"loss": 5.4561,
|
|
"mean_token_accuracy": 0.20842170119285583,
|
|
"num_tokens": 26681030.0,
|
|
"step": 13640
|
|
},
|
|
{
|
|
"entropy": 6.263928651809692,
|
|
"epoch": 1.3639726095866447,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004821410068068226,
|
|
"loss": 5.8124,
|
|
"mean_token_accuracy": 0.17165465354919435,
|
|
"num_tokens": 26691609.0,
|
|
"step": 13645
|
|
},
|
|
{
|
|
"entropy": 6.335266828536987,
|
|
"epoch": 1.3644724346478734,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004821270696069459,
|
|
"loss": 5.8195,
|
|
"mean_token_accuracy": 0.17154824286699294,
|
|
"num_tokens": 26700874.0,
|
|
"step": 13650
|
|
},
|
|
{
|
|
"entropy": 6.210645866394043,
|
|
"epoch": 1.3649722597091019,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00048211312719580553,
|
|
"loss": 5.6618,
|
|
"mean_token_accuracy": 0.18701510429382323,
|
|
"num_tokens": 26711234.0,
|
|
"step": 13655
|
|
},
|
|
{
|
|
"entropy": 6.201102638244629,
|
|
"epoch": 1.3654720847703303,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004820991795737521,
|
|
"loss": 5.6201,
|
|
"mean_token_accuracy": 0.19191247820854188,
|
|
"num_tokens": 26720348.0,
|
|
"step": 13660
|
|
},
|
|
{
|
|
"entropy": 6.222518730163574,
|
|
"epoch": 1.365971909831559,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048208522674113665,
|
|
"loss": 5.7104,
|
|
"mean_token_accuracy": 0.17893719673156738,
|
|
"num_tokens": 26730868.0,
|
|
"step": 13665
|
|
},
|
|
{
|
|
"entropy": 6.304088735580445,
|
|
"epoch": 1.3664717348927875,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004820712686983101,
|
|
"loss": 5.786,
|
|
"mean_token_accuracy": 0.17884070724248885,
|
|
"num_tokens": 26740093.0,
|
|
"step": 13670
|
|
},
|
|
{
|
|
"entropy": 6.257049989700318,
|
|
"epoch": 1.366971559954016,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00048205730544562385,
|
|
"loss": 5.7778,
|
|
"mean_token_accuracy": 0.17366385459899902,
|
|
"num_tokens": 26749550.0,
|
|
"step": 13675
|
|
},
|
|
{
|
|
"entropy": 6.279650592803955,
|
|
"epoch": 1.3674713850152447,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000482043336983429,
|
|
"loss": 5.7621,
|
|
"mean_token_accuracy": 0.18426811844110488,
|
|
"num_tokens": 26759416.0,
|
|
"step": 13680
|
|
},
|
|
{
|
|
"entropy": 6.1938928127288815,
|
|
"epoch": 1.3679712100764732,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048202936331207707,
|
|
"loss": 5.7078,
|
|
"mean_token_accuracy": 0.1774096518754959,
|
|
"num_tokens": 26769782.0,
|
|
"step": 13685
|
|
},
|
|
{
|
|
"entropy": 6.3039778709411625,
|
|
"epoch": 1.3684710351377019,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004820153844319196,
|
|
"loss": 5.7438,
|
|
"mean_token_accuracy": 0.173559333384037,
|
|
"num_tokens": 26779007.0,
|
|
"step": 13690
|
|
},
|
|
{
|
|
"entropy": 6.1957732200622555,
|
|
"epoch": 1.3689708601989303,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048200140034330844,
|
|
"loss": 5.6963,
|
|
"mean_token_accuracy": 0.17968306094408035,
|
|
"num_tokens": 26787828.0,
|
|
"step": 13695
|
|
},
|
|
{
|
|
"entropy": 6.198487329483032,
|
|
"epoch": 1.369470685260159,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00048198741104659516,
|
|
"loss": 5.6636,
|
|
"mean_token_accuracy": 0.1803879529237747,
|
|
"num_tokens": 26798190.0,
|
|
"step": 13700
|
|
},
|
|
{
|
|
"entropy": 6.229644107818603,
|
|
"epoch": 1.3699705103213875,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000481973416542132,
|
|
"loss": 5.7498,
|
|
"mean_token_accuracy": 0.17116654217243193,
|
|
"num_tokens": 26807312.0,
|
|
"step": 13705
|
|
},
|
|
{
|
|
"entropy": 6.170847368240357,
|
|
"epoch": 1.370470335382616,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004819594168302709,
|
|
"loss": 5.7097,
|
|
"mean_token_accuracy": 0.1850699484348297,
|
|
"num_tokens": 26816477.0,
|
|
"step": 13710
|
|
},
|
|
{
|
|
"entropy": 6.155413579940796,
|
|
"epoch": 1.3709701604438447,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004819454119113641,
|
|
"loss": 5.6298,
|
|
"mean_token_accuracy": 0.18406075239181519,
|
|
"num_tokens": 26825826.0,
|
|
"step": 13715
|
|
},
|
|
{
|
|
"entropy": 6.239377212524414,
|
|
"epoch": 1.3714699855050732,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000481931401785764,
|
|
"loss": 5.7008,
|
|
"mean_token_accuracy": 0.1790718764066696,
|
|
"num_tokens": 26834809.0,
|
|
"step": 13720
|
|
},
|
|
{
|
|
"entropy": 6.186546707153321,
|
|
"epoch": 1.3719698105663019,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004819173864538231,
|
|
"loss": 5.6484,
|
|
"mean_token_accuracy": 0.18162696659564972,
|
|
"num_tokens": 26845322.0,
|
|
"step": 13725
|
|
},
|
|
{
|
|
"entropy": 6.257162618637085,
|
|
"epoch": 1.3724696356275303,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048190336591589394,
|
|
"loss": 5.8266,
|
|
"mean_token_accuracy": 0.16939685344696045,
|
|
"num_tokens": 26854328.0,
|
|
"step": 13730
|
|
},
|
|
{
|
|
"entropy": 6.250145530700683,
|
|
"epoch": 1.372969460688759,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004818893401723294,
|
|
"loss": 5.8262,
|
|
"mean_token_accuracy": 0.16525527983903884,
|
|
"num_tokens": 26863299.0,
|
|
"step": 13735
|
|
},
|
|
{
|
|
"entropy": 6.175264024734497,
|
|
"epoch": 1.3734692857499875,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048187530922348226,
|
|
"loss": 5.6957,
|
|
"mean_token_accuracy": 0.1877611130475998,
|
|
"num_tokens": 26873461.0,
|
|
"step": 13740
|
|
},
|
|
{
|
|
"entropy": 6.220022583007813,
|
|
"epoch": 1.373969110811216,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004818612730697056,
|
|
"loss": 5.7197,
|
|
"mean_token_accuracy": 0.18118956238031386,
|
|
"num_tokens": 26883310.0,
|
|
"step": 13745
|
|
},
|
|
{
|
|
"entropy": 6.2656933784484865,
|
|
"epoch": 1.3744689358724447,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00048184723171135256,
|
|
"loss": 5.7054,
|
|
"mean_token_accuracy": 0.184853757917881,
|
|
"num_tokens": 26892009.0,
|
|
"step": 13750
|
|
},
|
|
{
|
|
"entropy": 6.232237243652344,
|
|
"epoch": 1.3749687609336732,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00048183318514877634,
|
|
"loss": 5.7315,
|
|
"mean_token_accuracy": 0.1737321510910988,
|
|
"num_tokens": 26902246.0,
|
|
"step": 13755
|
|
},
|
|
{
|
|
"entropy": 6.293291234970093,
|
|
"epoch": 1.3754685859949018,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004818191333823305,
|
|
"loss": 5.7643,
|
|
"mean_token_accuracy": 0.1807708501815796,
|
|
"num_tokens": 26912912.0,
|
|
"step": 13760
|
|
},
|
|
{
|
|
"entropy": 6.2815563678741455,
|
|
"epoch": 1.3759684110561303,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004818050764123684,
|
|
"loss": 5.706,
|
|
"mean_token_accuracy": 0.17973458170890808,
|
|
"num_tokens": 26921431.0,
|
|
"step": 13765
|
|
},
|
|
{
|
|
"entropy": 6.223747777938843,
|
|
"epoch": 1.376468236117359,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004817910142392438,
|
|
"loss": 5.7506,
|
|
"mean_token_accuracy": 0.17710509449243544,
|
|
"num_tokens": 26931990.0,
|
|
"step": 13770
|
|
},
|
|
{
|
|
"entropy": 6.282187604904175,
|
|
"epoch": 1.3769680611785875,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048177694686331047,
|
|
"loss": 5.7952,
|
|
"mean_token_accuracy": 0.18039330393075942,
|
|
"num_tokens": 26942801.0,
|
|
"step": 13775
|
|
},
|
|
{
|
|
"entropy": 6.256533765792847,
|
|
"epoch": 1.377467886239816,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004817628742849224,
|
|
"loss": 5.7705,
|
|
"mean_token_accuracy": 0.18020402789115905,
|
|
"num_tokens": 26952896.0,
|
|
"step": 13780
|
|
},
|
|
{
|
|
"entropy": 6.217694854736328,
|
|
"epoch": 1.3779677113010447,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048174879650443364,
|
|
"loss": 5.8446,
|
|
"mean_token_accuracy": 0.17392366081476213,
|
|
"num_tokens": 26963170.0,
|
|
"step": 13785
|
|
},
|
|
{
|
|
"entropy": 6.27760157585144,
|
|
"epoch": 1.3784675363622731,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00048173471352219835,
|
|
"loss": 5.8074,
|
|
"mean_token_accuracy": 0.1771986350417137,
|
|
"num_tokens": 26972937.0,
|
|
"step": 13790
|
|
},
|
|
{
|
|
"entropy": 6.348644638061524,
|
|
"epoch": 1.3789673614235018,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004817206253385708,
|
|
"loss": 5.8666,
|
|
"mean_token_accuracy": 0.16888405233621598,
|
|
"num_tokens": 26985115.0,
|
|
"step": 13795
|
|
},
|
|
{
|
|
"entropy": 6.282139253616333,
|
|
"epoch": 1.3794671864847303,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048170653195390555,
|
|
"loss": 5.7655,
|
|
"mean_token_accuracy": 0.18240086436271669,
|
|
"num_tokens": 26993658.0,
|
|
"step": 13800
|
|
},
|
|
{
|
|
"entropy": 6.2495674133300785,
|
|
"epoch": 1.379967011545959,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004816924333685572,
|
|
"loss": 5.7647,
|
|
"mean_token_accuracy": 0.1735876113176346,
|
|
"num_tokens": 27003877.0,
|
|
"step": 13805
|
|
},
|
|
{
|
|
"entropy": 6.222351741790772,
|
|
"epoch": 1.3804668366071875,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004816783295828804,
|
|
"loss": 5.6648,
|
|
"mean_token_accuracy": 0.18170431405305862,
|
|
"num_tokens": 27012125.0,
|
|
"step": 13810
|
|
},
|
|
{
|
|
"entropy": 6.287107372283936,
|
|
"epoch": 1.380966661668416,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00048166422059722996,
|
|
"loss": 5.8063,
|
|
"mean_token_accuracy": 0.1716664046049118,
|
|
"num_tokens": 27022158.0,
|
|
"step": 13815
|
|
},
|
|
{
|
|
"entropy": 6.218655633926391,
|
|
"epoch": 1.3814664867296447,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004816501064119609,
|
|
"loss": 5.7837,
|
|
"mean_token_accuracy": 0.17598447650671006,
|
|
"num_tokens": 27031966.0,
|
|
"step": 13820
|
|
},
|
|
{
|
|
"entropy": 6.292202186584473,
|
|
"epoch": 1.3819663117908731,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004816359870274284,
|
|
"loss": 5.7176,
|
|
"mean_token_accuracy": 0.17752804309129716,
|
|
"num_tokens": 27040805.0,
|
|
"step": 13825
|
|
},
|
|
{
|
|
"entropy": 6.2769838809967045,
|
|
"epoch": 1.3824661368521018,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004816218624439876,
|
|
"loss": 5.8345,
|
|
"mean_token_accuracy": 0.1682060107588768,
|
|
"num_tokens": 27049210.0,
|
|
"step": 13830
|
|
},
|
|
{
|
|
"entropy": 6.161285734176635,
|
|
"epoch": 1.3829659619133303,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048160773266199384,
|
|
"loss": 5.6569,
|
|
"mean_token_accuracy": 0.18361397981643676,
|
|
"num_tokens": 27058980.0,
|
|
"step": 13835
|
|
},
|
|
{
|
|
"entropy": 6.235151386260986,
|
|
"epoch": 1.383465786974559,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004815935976818028,
|
|
"loss": 5.7702,
|
|
"mean_token_accuracy": 0.18029304593801498,
|
|
"num_tokens": 27068539.0,
|
|
"step": 13840
|
|
},
|
|
{
|
|
"entropy": 6.228704261779785,
|
|
"epoch": 1.3839656120357875,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00048157945750377005,
|
|
"loss": 5.705,
|
|
"mean_token_accuracy": 0.17899523973464965,
|
|
"num_tokens": 27077500.0,
|
|
"step": 13845
|
|
},
|
|
{
|
|
"entropy": 6.194318199157715,
|
|
"epoch": 1.384465437097016,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004815653121282512,
|
|
"loss": 5.6797,
|
|
"mean_token_accuracy": 0.18276926577091218,
|
|
"num_tokens": 27087039.0,
|
|
"step": 13850
|
|
},
|
|
{
|
|
"entropy": 6.2307562828063965,
|
|
"epoch": 1.3849652621582447,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048155116155560227,
|
|
"loss": 5.7306,
|
|
"mean_token_accuracy": 0.18289712220430374,
|
|
"num_tokens": 27096575.0,
|
|
"step": 13855
|
|
},
|
|
{
|
|
"entropy": 6.30819730758667,
|
|
"epoch": 1.3854650872194731,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00048153700578617924,
|
|
"loss": 5.8142,
|
|
"mean_token_accuracy": 0.17059277445077897,
|
|
"num_tokens": 27106246.0,
|
|
"step": 13860
|
|
},
|
|
{
|
|
"entropy": 6.239856576919555,
|
|
"epoch": 1.3859649122807016,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004815228448203384,
|
|
"loss": 5.7708,
|
|
"mean_token_accuracy": 0.17698092609643937,
|
|
"num_tokens": 27115529.0,
|
|
"step": 13865
|
|
},
|
|
{
|
|
"entropy": 6.217366170883179,
|
|
"epoch": 1.3864647373419303,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004815086786584358,
|
|
"loss": 5.669,
|
|
"mean_token_accuracy": 0.18127622455358505,
|
|
"num_tokens": 27125204.0,
|
|
"step": 13870
|
|
},
|
|
{
|
|
"entropy": 6.168311595916748,
|
|
"epoch": 1.386964562403159,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.000481494507300828,
|
|
"loss": 5.7148,
|
|
"mean_token_accuracy": 0.1765090450644493,
|
|
"num_tokens": 27135053.0,
|
|
"step": 13875
|
|
},
|
|
{
|
|
"entropy": 6.28028130531311,
|
|
"epoch": 1.3874643874643875,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004814803307478716,
|
|
"loss": 5.6606,
|
|
"mean_token_accuracy": 0.18859076797962188,
|
|
"num_tokens": 27144863.0,
|
|
"step": 13880
|
|
},
|
|
{
|
|
"entropy": 6.228376388549805,
|
|
"epoch": 1.387964212525616,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00048146614899992313,
|
|
"loss": 5.7254,
|
|
"mean_token_accuracy": 0.17925132662057877,
|
|
"num_tokens": 27154178.0,
|
|
"step": 13885
|
|
},
|
|
{
|
|
"entropy": 6.256547498703003,
|
|
"epoch": 1.3884640375868447,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00048145196205733954,
|
|
"loss": 5.6856,
|
|
"mean_token_accuracy": 0.18046016097068787,
|
|
"num_tokens": 27164218.0,
|
|
"step": 13890
|
|
},
|
|
{
|
|
"entropy": 6.274048566818237,
|
|
"epoch": 1.3889638626480731,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048143776992047767,
|
|
"loss": 5.7285,
|
|
"mean_token_accuracy": 0.17354659885168075,
|
|
"num_tokens": 27174255.0,
|
|
"step": 13895
|
|
},
|
|
{
|
|
"entropy": 6.225698471069336,
|
|
"epoch": 1.3894636877093016,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00048142357258969465,
|
|
"loss": 5.799,
|
|
"mean_token_accuracy": 0.16818102449178696,
|
|
"num_tokens": 27184989.0,
|
|
"step": 13900
|
|
},
|
|
{
|
|
"entropy": 6.2012402534484865,
|
|
"epoch": 1.3899635127705303,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004814093700653477,
|
|
"loss": 5.6697,
|
|
"mean_token_accuracy": 0.18565604835748672,
|
|
"num_tokens": 27196249.0,
|
|
"step": 13905
|
|
},
|
|
{
|
|
"entropy": 6.235785293579101,
|
|
"epoch": 1.390463337831759,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048139516234779403,
|
|
"loss": 5.6677,
|
|
"mean_token_accuracy": 0.18506960868835448,
|
|
"num_tokens": 27204997.0,
|
|
"step": 13910
|
|
},
|
|
{
|
|
"entropy": 6.247156715393066,
|
|
"epoch": 1.3909631628929875,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00048138094943739123,
|
|
"loss": 5.7252,
|
|
"mean_token_accuracy": 0.17788647562265397,
|
|
"num_tokens": 27214344.0,
|
|
"step": 13915
|
|
},
|
|
{
|
|
"entropy": 6.255765819549561,
|
|
"epoch": 1.391462987954216,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048136673133449687,
|
|
"loss": 5.7623,
|
|
"mean_token_accuracy": 0.17468605637550355,
|
|
"num_tokens": 27223950.0,
|
|
"step": 13920
|
|
},
|
|
{
|
|
"entropy": 6.194794988632202,
|
|
"epoch": 1.3919628130154447,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004813525080394686,
|
|
"loss": 5.5893,
|
|
"mean_token_accuracy": 0.18277718275785446,
|
|
"num_tokens": 27233371.0,
|
|
"step": 13925
|
|
},
|
|
{
|
|
"entropy": 6.219571352005005,
|
|
"epoch": 1.3924626380766731,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004813382795526644,
|
|
"loss": 5.813,
|
|
"mean_token_accuracy": 0.1783938318490982,
|
|
"num_tokens": 27243413.0,
|
|
"step": 13930
|
|
},
|
|
{
|
|
"entropy": 6.234514236450195,
|
|
"epoch": 1.3929624631379016,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004813240458744421,
|
|
"loss": 5.6911,
|
|
"mean_token_accuracy": 0.18215743601322174,
|
|
"num_tokens": 27254117.0,
|
|
"step": 13935
|
|
},
|
|
{
|
|
"entropy": 6.215664958953857,
|
|
"epoch": 1.3934622881991303,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00048130980700516,
|
|
"loss": 5.8206,
|
|
"mean_token_accuracy": 0.17270866185426711,
|
|
"num_tokens": 27263202.0,
|
|
"step": 13940
|
|
},
|
|
{
|
|
"entropy": 6.19507360458374,
|
|
"epoch": 1.3939621132603588,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004812955629451761,
|
|
"loss": 5.6906,
|
|
"mean_token_accuracy": 0.17731159627437593,
|
|
"num_tokens": 27272830.0,
|
|
"step": 13945
|
|
},
|
|
{
|
|
"entropy": 6.239712238311768,
|
|
"epoch": 1.3944619383215875,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004812813136948491,
|
|
"loss": 5.732,
|
|
"mean_token_accuracy": 0.1819087579846382,
|
|
"num_tokens": 27283567.0,
|
|
"step": 13950
|
|
},
|
|
{
|
|
"entropy": 6.268902349472046,
|
|
"epoch": 1.394961763382816,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00048126705925453716,
|
|
"loss": 5.6392,
|
|
"mean_token_accuracy": 0.1861199826002121,
|
|
"num_tokens": 27292113.0,
|
|
"step": 13955
|
|
},
|
|
{
|
|
"entropy": 6.1818568229675295,
|
|
"epoch": 1.3954615884440447,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004812527996245992,
|
|
"loss": 5.6363,
|
|
"mean_token_accuracy": 0.19188976138830185,
|
|
"num_tokens": 27301605.0,
|
|
"step": 13960
|
|
},
|
|
{
|
|
"entropy": 6.239265251159668,
|
|
"epoch": 1.3959614135052731,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004812385348053938,
|
|
"loss": 5.7661,
|
|
"mean_token_accuracy": 0.178920179605484,
|
|
"num_tokens": 27312453.0,
|
|
"step": 13965
|
|
},
|
|
{
|
|
"entropy": 6.216888809204102,
|
|
"epoch": 1.3964612385665016,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048122426479728,
|
|
"loss": 5.7752,
|
|
"mean_token_accuracy": 0.17099259793758392,
|
|
"num_tokens": 27322641.0,
|
|
"step": 13970
|
|
},
|
|
{
|
|
"entropy": 6.114824819564819,
|
|
"epoch": 1.3969610636277303,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004812099896006167,
|
|
"loss": 5.556,
|
|
"mean_token_accuracy": 0.19189831763505935,
|
|
"num_tokens": 27332283.0,
|
|
"step": 13975
|
|
},
|
|
{
|
|
"entropy": 6.198688268661499,
|
|
"epoch": 1.3974608886889588,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004811957092157631,
|
|
"loss": 5.7008,
|
|
"mean_token_accuracy": 0.18078365474939345,
|
|
"num_tokens": 27341203.0,
|
|
"step": 13980
|
|
},
|
|
{
|
|
"entropy": 6.217933416366577,
|
|
"epoch": 1.3979607137501875,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00048118142364307864,
|
|
"loss": 5.7682,
|
|
"mean_token_accuracy": 0.18085888624191285,
|
|
"num_tokens": 27351263.0,
|
|
"step": 13985
|
|
},
|
|
{
|
|
"entropy": 6.218268823623657,
|
|
"epoch": 1.398460538811416,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004811671328829225,
|
|
"loss": 5.7163,
|
|
"mean_token_accuracy": 0.17456373423337937,
|
|
"num_tokens": 27361001.0,
|
|
"step": 13990
|
|
},
|
|
{
|
|
"entropy": 6.241559314727783,
|
|
"epoch": 1.3989603638726447,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00048115283693565445,
|
|
"loss": 5.7082,
|
|
"mean_token_accuracy": 0.1796470269560814,
|
|
"num_tokens": 27370097.0,
|
|
"step": 13995
|
|
},
|
|
{
|
|
"entropy": 6.149133014678955,
|
|
"epoch": 1.3994601889338731,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000481138535801634,
|
|
"loss": 5.7493,
|
|
"mean_token_accuracy": 0.18215697705745698,
|
|
"num_tokens": 27379795.0,
|
|
"step": 14000
|
|
},
|
|
{
|
|
"entropy": 6.149370336532593,
|
|
"epoch": 1.3999600139951016,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000481124229481221,
|
|
"loss": 5.7245,
|
|
"mean_token_accuracy": 0.18643137365579604,
|
|
"num_tokens": 27389515.0,
|
|
"step": 14005
|
|
},
|
|
{
|
|
"entropy": 6.225639820098877,
|
|
"epoch": 1.4004598390563303,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004811099179747755,
|
|
"loss": 5.6038,
|
|
"mean_token_accuracy": 0.20365477204322815,
|
|
"num_tokens": 27400177.0,
|
|
"step": 14010
|
|
},
|
|
{
|
|
"entropy": 6.291042137145996,
|
|
"epoch": 1.4009596641175588,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048109560128265747,
|
|
"loss": 5.7265,
|
|
"mean_token_accuracy": 0.17576572448015212,
|
|
"num_tokens": 27409381.0,
|
|
"step": 14015
|
|
},
|
|
{
|
|
"entropy": 6.255701017379761,
|
|
"epoch": 1.4014594891787875,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004810812794052271,
|
|
"loss": 5.8335,
|
|
"mean_token_accuracy": 0.1701025679707527,
|
|
"num_tokens": 27419897.0,
|
|
"step": 14020
|
|
},
|
|
{
|
|
"entropy": 6.362720775604248,
|
|
"epoch": 1.401959314240016,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004810669523428449,
|
|
"loss": 5.9225,
|
|
"mean_token_accuracy": 0.169257290661335,
|
|
"num_tokens": 27430693.0,
|
|
"step": 14025
|
|
},
|
|
{
|
|
"entropy": 6.337117767333984,
|
|
"epoch": 1.4024591393012447,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000481052620095871,
|
|
"loss": 5.8639,
|
|
"mean_token_accuracy": 0.16824184805154802,
|
|
"num_tokens": 27440834.0,
|
|
"step": 14030
|
|
},
|
|
{
|
|
"entropy": 6.191962003707886,
|
|
"epoch": 1.4029589643624731,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004810382826646664,
|
|
"loss": 5.6428,
|
|
"mean_token_accuracy": 0.18614606261253358,
|
|
"num_tokens": 27450166.0,
|
|
"step": 14035
|
|
},
|
|
{
|
|
"entropy": 6.189534378051758,
|
|
"epoch": 1.4034587894237016,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004810239400495915,
|
|
"loss": 5.7356,
|
|
"mean_token_accuracy": 0.1745391756296158,
|
|
"num_tokens": 27459863.0,
|
|
"step": 14040
|
|
},
|
|
{
|
|
"entropy": 6.2063072681427,
|
|
"epoch": 1.4039586144849303,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004810095922510073,
|
|
"loss": 5.6829,
|
|
"mean_token_accuracy": 0.18003267645835877,
|
|
"num_tokens": 27469118.0,
|
|
"step": 14045
|
|
},
|
|
{
|
|
"entropy": 6.248623847961426,
|
|
"epoch": 1.4044584395461588,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00048099523926927487,
|
|
"loss": 5.7203,
|
|
"mean_token_accuracy": 0.18141238540410995,
|
|
"num_tokens": 27479550.0,
|
|
"step": 14050
|
|
},
|
|
{
|
|
"entropy": 6.258568286895752,
|
|
"epoch": 1.4049582646073875,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004809808811047552,
|
|
"loss": 5.7967,
|
|
"mean_token_accuracy": 0.17378372848033904,
|
|
"num_tokens": 27489625.0,
|
|
"step": 14055
|
|
},
|
|
{
|
|
"entropy": 6.287000131607056,
|
|
"epoch": 1.405458089668616,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048096651775780943,
|
|
"loss": 5.7954,
|
|
"mean_token_accuracy": 0.17735302597284316,
|
|
"num_tokens": 27501459.0,
|
|
"step": 14060
|
|
},
|
|
{
|
|
"entropy": 6.254177808761597,
|
|
"epoch": 1.4059579147298447,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004809521492287992,
|
|
"loss": 5.6465,
|
|
"mean_token_accuracy": 0.1842784583568573,
|
|
"num_tokens": 27511450.0,
|
|
"step": 14065
|
|
},
|
|
{
|
|
"entropy": 6.23374376296997,
|
|
"epoch": 1.4064577397910731,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004809377755180858,
|
|
"loss": 5.6483,
|
|
"mean_token_accuracy": 0.18289602994918824,
|
|
"num_tokens": 27520783.0,
|
|
"step": 14070
|
|
},
|
|
{
|
|
"entropy": 6.2741152286529545,
|
|
"epoch": 1.4069575648523016,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004809233966260311,
|
|
"loss": 5.6979,
|
|
"mean_token_accuracy": 0.1835711866617203,
|
|
"num_tokens": 27529433.0,
|
|
"step": 14075
|
|
},
|
|
{
|
|
"entropy": 6.177093553543091,
|
|
"epoch": 1.4074573899135303,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004809090125529966,
|
|
"loss": 5.7123,
|
|
"mean_token_accuracy": 0.1860586628317833,
|
|
"num_tokens": 27539278.0,
|
|
"step": 14080
|
|
},
|
|
{
|
|
"entropy": 6.252393293380737,
|
|
"epoch": 1.4079572149747588,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00048089462329934437,
|
|
"loss": 5.7946,
|
|
"mean_token_accuracy": 0.17225075960159303,
|
|
"num_tokens": 27548474.0,
|
|
"step": 14085
|
|
},
|
|
{
|
|
"entropy": 6.305006837844848,
|
|
"epoch": 1.4084570400359875,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00048088022886543636,
|
|
"loss": 5.7356,
|
|
"mean_token_accuracy": 0.18496729135513307,
|
|
"num_tokens": 27557757.0,
|
|
"step": 14090
|
|
},
|
|
{
|
|
"entropy": 6.288686895370484,
|
|
"epoch": 1.408956865097216,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004808658292516348,
|
|
"loss": 5.8251,
|
|
"mean_token_accuracy": 0.1710083618760109,
|
|
"num_tokens": 27567971.0,
|
|
"step": 14095
|
|
},
|
|
{
|
|
"entropy": 6.336109685897827,
|
|
"epoch": 1.4094566901584447,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048085142445830197,
|
|
"loss": 5.8467,
|
|
"mean_token_accuracy": 0.1621666356921196,
|
|
"num_tokens": 27578135.0,
|
|
"step": 14100
|
|
},
|
|
{
|
|
"entropy": 6.29666690826416,
|
|
"epoch": 1.4099565152196731,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00048083701448580027,
|
|
"loss": 5.725,
|
|
"mean_token_accuracy": 0.17977316677570343,
|
|
"num_tokens": 27587459.0,
|
|
"step": 14105
|
|
},
|
|
{
|
|
"entropy": 6.2890040397644045,
|
|
"epoch": 1.4104563402809016,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048082259933449224,
|
|
"loss": 5.801,
|
|
"mean_token_accuracy": 0.17532104402780532,
|
|
"num_tokens": 27596494.0,
|
|
"step": 14110
|
|
},
|
|
{
|
|
"entropy": 6.2068095207214355,
|
|
"epoch": 1.4109561653421303,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004808081790047406,
|
|
"loss": 5.6711,
|
|
"mean_token_accuracy": 0.18725600242614746,
|
|
"num_tokens": 27605482.0,
|
|
"step": 14115
|
|
},
|
|
{
|
|
"entropy": 6.2244960308074955,
|
|
"epoch": 1.4114559904033588,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048079375349690807,
|
|
"loss": 5.7173,
|
|
"mean_token_accuracy": 0.17902533411979676,
|
|
"num_tokens": 27615386.0,
|
|
"step": 14120
|
|
},
|
|
{
|
|
"entropy": 6.276747226715088,
|
|
"epoch": 1.4119558154645873,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00048077932281135775,
|
|
"loss": 5.7629,
|
|
"mean_token_accuracy": 0.17690217047929763,
|
|
"num_tokens": 27624834.0,
|
|
"step": 14125
|
|
},
|
|
{
|
|
"entropy": 6.248224925994873,
|
|
"epoch": 1.412455640525816,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048076488694845257,
|
|
"loss": 5.6798,
|
|
"mean_token_accuracy": 0.18383786380290984,
|
|
"num_tokens": 27634087.0,
|
|
"step": 14130
|
|
},
|
|
{
|
|
"entropy": 6.255794811248779,
|
|
"epoch": 1.4129554655870447,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00048075044590855574,
|
|
"loss": 5.6561,
|
|
"mean_token_accuracy": 0.18573059439659118,
|
|
"num_tokens": 27643739.0,
|
|
"step": 14135
|
|
},
|
|
{
|
|
"entropy": 6.25390477180481,
|
|
"epoch": 1.4134552906482731,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048073599969203064,
|
|
"loss": 5.7725,
|
|
"mean_token_accuracy": 0.17826998233795166,
|
|
"num_tokens": 27652594.0,
|
|
"step": 14140
|
|
},
|
|
{
|
|
"entropy": 6.219322967529297,
|
|
"epoch": 1.4139551157095016,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004807215482992408,
|
|
"loss": 5.7553,
|
|
"mean_token_accuracy": 0.18044300228357316,
|
|
"num_tokens": 27662766.0,
|
|
"step": 14145
|
|
},
|
|
{
|
|
"entropy": 6.294541835784912,
|
|
"epoch": 1.4144549407707303,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004807070917305497,
|
|
"loss": 5.8183,
|
|
"mean_token_accuracy": 0.1735577329993248,
|
|
"num_tokens": 27673547.0,
|
|
"step": 14150
|
|
},
|
|
{
|
|
"entropy": 6.3106804370880125,
|
|
"epoch": 1.4149547658319588,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00048069262998632115,
|
|
"loss": 5.7621,
|
|
"mean_token_accuracy": 0.17801573872566223,
|
|
"num_tokens": 27683056.0,
|
|
"step": 14155
|
|
},
|
|
{
|
|
"entropy": 6.290584516525269,
|
|
"epoch": 1.4154545908931873,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004806781630669189,
|
|
"loss": 5.7509,
|
|
"mean_token_accuracy": 0.17891205847263336,
|
|
"num_tokens": 27693049.0,
|
|
"step": 14160
|
|
},
|
|
{
|
|
"entropy": 6.270132541656494,
|
|
"epoch": 1.415954415954416,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00048066369097270694,
|
|
"loss": 5.6868,
|
|
"mean_token_accuracy": 0.18062028884887696,
|
|
"num_tokens": 27703712.0,
|
|
"step": 14165
|
|
},
|
|
{
|
|
"entropy": 6.188491725921631,
|
|
"epoch": 1.4164542410156447,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004806492137040495,
|
|
"loss": 5.7133,
|
|
"mean_token_accuracy": 0.1852886199951172,
|
|
"num_tokens": 27713460.0,
|
|
"step": 14170
|
|
},
|
|
{
|
|
"entropy": 6.287253046035767,
|
|
"epoch": 1.4169540660768731,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00048063473126131086,
|
|
"loss": 5.7784,
|
|
"mean_token_accuracy": 0.17596371173858644,
|
|
"num_tokens": 27722942.0,
|
|
"step": 14175
|
|
},
|
|
{
|
|
"entropy": 6.267826128005981,
|
|
"epoch": 1.4174538911381016,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004806202436448551,
|
|
"loss": 5.7363,
|
|
"mean_token_accuracy": 0.17499522119760513,
|
|
"num_tokens": 27732738.0,
|
|
"step": 14180
|
|
},
|
|
{
|
|
"entropy": 6.262534809112549,
|
|
"epoch": 1.4179537161993303,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004806057508550471,
|
|
"loss": 5.7942,
|
|
"mean_token_accuracy": 0.1741328217089176,
|
|
"num_tokens": 27742169.0,
|
|
"step": 14185
|
|
},
|
|
{
|
|
"entropy": 6.248822593688965,
|
|
"epoch": 1.4184535412605588,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004805912528922512,
|
|
"loss": 5.7512,
|
|
"mean_token_accuracy": 0.18285052329301835,
|
|
"num_tokens": 27752539.0,
|
|
"step": 14190
|
|
},
|
|
{
|
|
"entropy": 6.276381254196167,
|
|
"epoch": 1.4189533663217873,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004805767497568323,
|
|
"loss": 5.818,
|
|
"mean_token_accuracy": 0.1688002347946167,
|
|
"num_tokens": 27763494.0,
|
|
"step": 14195
|
|
},
|
|
{
|
|
"entropy": 6.2325366020202635,
|
|
"epoch": 1.419453191383016,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048056224144915534,
|
|
"loss": 5.6364,
|
|
"mean_token_accuracy": 0.1935661867260933,
|
|
"num_tokens": 27772884.0,
|
|
"step": 14200
|
|
},
|
|
{
|
|
"entropy": 6.182552480697632,
|
|
"epoch": 1.4199530164442444,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048054772796958517,
|
|
"loss": 5.6592,
|
|
"mean_token_accuracy": 0.18834893256425858,
|
|
"num_tokens": 27782447.0,
|
|
"step": 14205
|
|
},
|
|
{
|
|
"entropy": 6.21789059638977,
|
|
"epoch": 1.4204528415054731,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00048053320931848713,
|
|
"loss": 5.7345,
|
|
"mean_token_accuracy": 0.1818685844540596,
|
|
"num_tokens": 27790781.0,
|
|
"step": 14210
|
|
},
|
|
{
|
|
"entropy": 6.230807685852051,
|
|
"epoch": 1.4209526665667016,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048051868549622644,
|
|
"loss": 5.6538,
|
|
"mean_token_accuracy": 0.1879306897521019,
|
|
"num_tokens": 27799781.0,
|
|
"step": 14215
|
|
},
|
|
{
|
|
"entropy": 6.1659571647644045,
|
|
"epoch": 1.4214524916279303,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00048050415650316853,
|
|
"loss": 5.6811,
|
|
"mean_token_accuracy": 0.18200468719005586,
|
|
"num_tokens": 27809067.0,
|
|
"step": 14220
|
|
},
|
|
{
|
|
"entropy": 6.262529277801514,
|
|
"epoch": 1.4219523166891588,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004804896223396789,
|
|
"loss": 5.8023,
|
|
"mean_token_accuracy": 0.17195530682802201,
|
|
"num_tokens": 27819194.0,
|
|
"step": 14225
|
|
},
|
|
{
|
|
"entropy": 6.239363813400269,
|
|
"epoch": 1.4224521417503873,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004804750830061232,
|
|
"loss": 5.74,
|
|
"mean_token_accuracy": 0.1819899410009384,
|
|
"num_tokens": 27830179.0,
|
|
"step": 14230
|
|
},
|
|
{
|
|
"entropy": 6.257553672790527,
|
|
"epoch": 1.422951966811616,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004804605385028673,
|
|
"loss": 5.729,
|
|
"mean_token_accuracy": 0.180720953643322,
|
|
"num_tokens": 27840476.0,
|
|
"step": 14235
|
|
},
|
|
{
|
|
"entropy": 6.182767629623413,
|
|
"epoch": 1.4234517918728444,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004804459888302772,
|
|
"loss": 5.6372,
|
|
"mean_token_accuracy": 0.18414160907268523,
|
|
"num_tokens": 27850247.0,
|
|
"step": 14240
|
|
},
|
|
{
|
|
"entropy": 6.250250625610351,
|
|
"epoch": 1.4239516169340731,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00048043143398871874,
|
|
"loss": 5.8055,
|
|
"mean_token_accuracy": 0.17224833518266677,
|
|
"num_tokens": 27860290.0,
|
|
"step": 14245
|
|
},
|
|
{
|
|
"entropy": 6.258993625640869,
|
|
"epoch": 1.4244514419953016,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004804168739785583,
|
|
"loss": 5.7501,
|
|
"mean_token_accuracy": 0.17287932485342025,
|
|
"num_tokens": 27870506.0,
|
|
"step": 14250
|
|
},
|
|
{
|
|
"entropy": 6.274321985244751,
|
|
"epoch": 1.4249512670565303,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004804023088001623,
|
|
"loss": 5.7803,
|
|
"mean_token_accuracy": 0.18000191301107407,
|
|
"num_tokens": 27880679.0,
|
|
"step": 14255
|
|
},
|
|
{
|
|
"entropy": 6.222334003448486,
|
|
"epoch": 1.4254510921177588,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004803877384538969,
|
|
"loss": 5.7017,
|
|
"mean_token_accuracy": 0.18263466358184816,
|
|
"num_tokens": 27891532.0,
|
|
"step": 14260
|
|
},
|
|
{
|
|
"entropy": 6.023574256896973,
|
|
"epoch": 1.4259509171789873,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000480373162940129,
|
|
"loss": 5.5427,
|
|
"mean_token_accuracy": 0.2038571283221245,
|
|
"num_tokens": 27902659.0,
|
|
"step": 14265
|
|
},
|
|
{
|
|
"entropy": 6.197374725341797,
|
|
"epoch": 1.426450742240216,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048035858225922506,
|
|
"loss": 5.7213,
|
|
"mean_token_accuracy": 0.17853381782770156,
|
|
"num_tokens": 27912422.0,
|
|
"step": 14270
|
|
},
|
|
{
|
|
"entropy": 6.187658357620239,
|
|
"epoch": 1.4269505673014444,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00048034399641155206,
|
|
"loss": 5.7214,
|
|
"mean_token_accuracy": 0.17873954623937607,
|
|
"num_tokens": 27922898.0,
|
|
"step": 14275
|
|
},
|
|
{
|
|
"entropy": 6.2624509811401365,
|
|
"epoch": 1.4274503923626731,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048032940539747697,
|
|
"loss": 5.7118,
|
|
"mean_token_accuracy": 0.18238646537065506,
|
|
"num_tokens": 27932915.0,
|
|
"step": 14280
|
|
},
|
|
{
|
|
"entropy": 6.277338171005249,
|
|
"epoch": 1.4279502174239016,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00048031480921736686,
|
|
"loss": 5.7132,
|
|
"mean_token_accuracy": 0.17818601727485656,
|
|
"num_tokens": 27942760.0,
|
|
"step": 14285
|
|
},
|
|
{
|
|
"entropy": 6.22563328742981,
|
|
"epoch": 1.4284500424851303,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000480300207871589,
|
|
"loss": 5.7639,
|
|
"mean_token_accuracy": 0.17918461561203003,
|
|
"num_tokens": 27952898.0,
|
|
"step": 14290
|
|
},
|
|
{
|
|
"entropy": 6.194161701202392,
|
|
"epoch": 1.4289498675463588,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048028560136051076,
|
|
"loss": 5.7075,
|
|
"mean_token_accuracy": 0.1845705598592758,
|
|
"num_tokens": 27962292.0,
|
|
"step": 14295
|
|
},
|
|
{
|
|
"entropy": 6.270665550231934,
|
|
"epoch": 1.4294496926075873,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048027098968449954,
|
|
"loss": 5.721,
|
|
"mean_token_accuracy": 0.17931336611509324,
|
|
"num_tokens": 27972480.0,
|
|
"step": 14300
|
|
},
|
|
{
|
|
"entropy": 6.290039157867431,
|
|
"epoch": 1.429949517668816,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004802563728439231,
|
|
"loss": 5.8236,
|
|
"mean_token_accuracy": 0.17281898856163025,
|
|
"num_tokens": 27982224.0,
|
|
"step": 14305
|
|
},
|
|
{
|
|
"entropy": 6.273288583755493,
|
|
"epoch": 1.4304493427300444,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004802417508391491,
|
|
"loss": 5.8097,
|
|
"mean_token_accuracy": 0.18095888644456865,
|
|
"num_tokens": 27991512.0,
|
|
"step": 14310
|
|
},
|
|
{
|
|
"entropy": 6.218121957778931,
|
|
"epoch": 1.4309491677912731,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004802271236705455,
|
|
"loss": 5.5985,
|
|
"mean_token_accuracy": 0.1901114746928215,
|
|
"num_tokens": 28001392.0,
|
|
"step": 14315
|
|
},
|
|
{
|
|
"entropy": 6.1690162181854244,
|
|
"epoch": 1.4314489928525016,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00048021249133848025,
|
|
"loss": 5.5987,
|
|
"mean_token_accuracy": 0.1830947905778885,
|
|
"num_tokens": 28009934.0,
|
|
"step": 14320
|
|
},
|
|
{
|
|
"entropy": 6.221919202804566,
|
|
"epoch": 1.4319488179137303,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00048019785384332154,
|
|
"loss": 5.7266,
|
|
"mean_token_accuracy": 0.1795089527964592,
|
|
"num_tokens": 28019485.0,
|
|
"step": 14325
|
|
},
|
|
{
|
|
"entropy": 6.2428686141967775,
|
|
"epoch": 1.4324486429749588,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004801832111854376,
|
|
"loss": 5.7533,
|
|
"mean_token_accuracy": 0.17785028368234634,
|
|
"num_tokens": 28028666.0,
|
|
"step": 14330
|
|
},
|
|
{
|
|
"entropy": 6.254274892807007,
|
|
"epoch": 1.4329484680361873,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004801685633651969,
|
|
"loss": 5.737,
|
|
"mean_token_accuracy": 0.17736440300941467,
|
|
"num_tokens": 28038677.0,
|
|
"step": 14335
|
|
},
|
|
{
|
|
"entropy": 6.324802589416504,
|
|
"epoch": 1.433448293097416,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004801539103829679,
|
|
"loss": 5.8059,
|
|
"mean_token_accuracy": 0.1737270548939705,
|
|
"num_tokens": 28048580.0,
|
|
"step": 14340
|
|
},
|
|
{
|
|
"entropy": 6.267704582214355,
|
|
"epoch": 1.4339481181586444,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004801392522391193,
|
|
"loss": 5.7632,
|
|
"mean_token_accuracy": 0.1711771383881569,
|
|
"num_tokens": 28058958.0,
|
|
"step": 14345
|
|
},
|
|
{
|
|
"entropy": 6.256963443756104,
|
|
"epoch": 1.4344479432198731,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00048012458893401995,
|
|
"loss": 5.7124,
|
|
"mean_token_accuracy": 0.18066183030605315,
|
|
"num_tokens": 28068861.0,
|
|
"step": 14350
|
|
},
|
|
{
|
|
"entropy": 6.220772409439087,
|
|
"epoch": 1.4349477682811016,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004801099204680387,
|
|
"loss": 5.7623,
|
|
"mean_token_accuracy": 0.18608256578445434,
|
|
"num_tokens": 28078638.0,
|
|
"step": 14355
|
|
},
|
|
{
|
|
"entropy": 6.258652973175049,
|
|
"epoch": 1.4354475933423303,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048009524684154464,
|
|
"loss": 5.7395,
|
|
"mean_token_accuracy": 0.17701376527547835,
|
|
"num_tokens": 28088549.0,
|
|
"step": 14360
|
|
},
|
|
{
|
|
"entropy": 6.3693397521972654,
|
|
"epoch": 1.4359474184035588,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004800805680549069,
|
|
"loss": 5.8,
|
|
"mean_token_accuracy": 0.17124544829130173,
|
|
"num_tokens": 28097743.0,
|
|
"step": 14365
|
|
},
|
|
{
|
|
"entropy": 6.197420597076416,
|
|
"epoch": 1.4364472434647872,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048006588410849497,
|
|
"loss": 5.693,
|
|
"mean_token_accuracy": 0.18270379900932313,
|
|
"num_tokens": 28107187.0,
|
|
"step": 14370
|
|
},
|
|
{
|
|
"entropy": 6.204587411880493,
|
|
"epoch": 1.436947068526016,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000480051195002678,
|
|
"loss": 5.6671,
|
|
"mean_token_accuracy": 0.1848506212234497,
|
|
"num_tokens": 28117730.0,
|
|
"step": 14375
|
|
},
|
|
{
|
|
"entropy": 6.327721405029297,
|
|
"epoch": 1.4374468935872444,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00048003650073782586,
|
|
"loss": 5.7956,
|
|
"mean_token_accuracy": 0.1712308943271637,
|
|
"num_tokens": 28127803.0,
|
|
"step": 14380
|
|
},
|
|
{
|
|
"entropy": 6.242333602905274,
|
|
"epoch": 1.437946718648473,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000480021801314308,
|
|
"loss": 5.7121,
|
|
"mean_token_accuracy": 0.18539846688508987,
|
|
"num_tokens": 28137946.0,
|
|
"step": 14385
|
|
},
|
|
{
|
|
"entropy": 6.2396642684936525,
|
|
"epoch": 1.4384465437097016,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004800070967324944,
|
|
"loss": 5.8305,
|
|
"mean_token_accuracy": 0.17213737666606904,
|
|
"num_tokens": 28147895.0,
|
|
"step": 14390
|
|
},
|
|
{
|
|
"entropy": 6.203232192993164,
|
|
"epoch": 1.4389463687709303,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047999238699275506,
|
|
"loss": 5.7067,
|
|
"mean_token_accuracy": 0.18249442875385286,
|
|
"num_tokens": 28157641.0,
|
|
"step": 14395
|
|
},
|
|
{
|
|
"entropy": 6.25102219581604,
|
|
"epoch": 1.4394461938321588,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047997767209546,
|
|
"loss": 5.758,
|
|
"mean_token_accuracy": 0.17320270091295242,
|
|
"num_tokens": 28167320.0,
|
|
"step": 14400
|
|
},
|
|
{
|
|
"entropy": 6.214060354232788,
|
|
"epoch": 1.4399460188933872,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004799629520409795,
|
|
"loss": 5.7104,
|
|
"mean_token_accuracy": 0.18715313076972961,
|
|
"num_tokens": 28176697.0,
|
|
"step": 14405
|
|
},
|
|
{
|
|
"entropy": 6.267869472503662,
|
|
"epoch": 1.440445843954616,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047994822682968373,
|
|
"loss": 5.7914,
|
|
"mean_token_accuracy": 0.17940520495176315,
|
|
"num_tokens": 28186688.0,
|
|
"step": 14410
|
|
},
|
|
{
|
|
"entropy": 6.2640039920806885,
|
|
"epoch": 1.4409456690158444,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047993349646194343,
|
|
"loss": 5.8484,
|
|
"mean_token_accuracy": 0.1766495555639267,
|
|
"num_tokens": 28197293.0,
|
|
"step": 14415
|
|
},
|
|
{
|
|
"entropy": 6.328662014007568,
|
|
"epoch": 1.441445494077073,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00047991876093812904,
|
|
"loss": 5.8218,
|
|
"mean_token_accuracy": 0.17343741804361343,
|
|
"num_tokens": 28207413.0,
|
|
"step": 14420
|
|
},
|
|
{
|
|
"entropy": 6.295700550079346,
|
|
"epoch": 1.4419453191383016,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047990402025861143,
|
|
"loss": 5.7518,
|
|
"mean_token_accuracy": 0.17874359488487243,
|
|
"num_tokens": 28217575.0,
|
|
"step": 14425
|
|
},
|
|
{
|
|
"entropy": 6.108126211166382,
|
|
"epoch": 1.4424451441995303,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004798892744237613,
|
|
"loss": 5.6038,
|
|
"mean_token_accuracy": 0.18601782172918319,
|
|
"num_tokens": 28226460.0,
|
|
"step": 14430
|
|
},
|
|
{
|
|
"entropy": 6.174574327468872,
|
|
"epoch": 1.4429449692607588,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047987452343394976,
|
|
"loss": 5.7225,
|
|
"mean_token_accuracy": 0.1770335003733635,
|
|
"num_tokens": 28236689.0,
|
|
"step": 14435
|
|
},
|
|
{
|
|
"entropy": 6.2729416847229,
|
|
"epoch": 1.4434447943219872,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047985976728954794,
|
|
"loss": 5.7031,
|
|
"mean_token_accuracy": 0.18511833101511002,
|
|
"num_tokens": 28247057.0,
|
|
"step": 14440
|
|
},
|
|
{
|
|
"entropy": 6.333534240722656,
|
|
"epoch": 1.443944619383216,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004798450059909271,
|
|
"loss": 5.7648,
|
|
"mean_token_accuracy": 0.17951050251722336,
|
|
"num_tokens": 28256475.0,
|
|
"step": 14445
|
|
},
|
|
{
|
|
"entropy": 6.197693967819214,
|
|
"epoch": 1.4444444444444444,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004798302395384586,
|
|
"loss": 5.7019,
|
|
"mean_token_accuracy": 0.174527508020401,
|
|
"num_tokens": 28266120.0,
|
|
"step": 14450
|
|
},
|
|
{
|
|
"entropy": 6.231680011749267,
|
|
"epoch": 1.444944269505673,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047981546793251405,
|
|
"loss": 5.6836,
|
|
"mean_token_accuracy": 0.18160711824893952,
|
|
"num_tokens": 28276325.0,
|
|
"step": 14455
|
|
},
|
|
{
|
|
"entropy": 6.274576091766358,
|
|
"epoch": 1.4454440945669016,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000479800691173465,
|
|
"loss": 5.6878,
|
|
"mean_token_accuracy": 0.17919993847608567,
|
|
"num_tokens": 28286007.0,
|
|
"step": 14460
|
|
},
|
|
{
|
|
"entropy": 6.235414171218872,
|
|
"epoch": 1.4459439196281303,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004797859092616832,
|
|
"loss": 5.7278,
|
|
"mean_token_accuracy": 0.1761277958750725,
|
|
"num_tokens": 28296346.0,
|
|
"step": 14465
|
|
},
|
|
{
|
|
"entropy": 6.099767637252808,
|
|
"epoch": 1.4464437446893588,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047977112219754064,
|
|
"loss": 5.5927,
|
|
"mean_token_accuracy": 0.199086894094944,
|
|
"num_tokens": 28306137.0,
|
|
"step": 14470
|
|
},
|
|
{
|
|
"entropy": 6.287295532226563,
|
|
"epoch": 1.4469435697505872,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004797563299814094,
|
|
"loss": 5.8487,
|
|
"mean_token_accuracy": 0.1698226287961006,
|
|
"num_tokens": 28316369.0,
|
|
"step": 14475
|
|
},
|
|
{
|
|
"entropy": 6.331446170806885,
|
|
"epoch": 1.447443394811816,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047974153261366156,
|
|
"loss": 5.7163,
|
|
"mean_token_accuracy": 0.17795781195163726,
|
|
"num_tokens": 28325338.0,
|
|
"step": 14480
|
|
},
|
|
{
|
|
"entropy": 6.226688432693481,
|
|
"epoch": 1.4479432198730444,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004797267300946694,
|
|
"loss": 5.7021,
|
|
"mean_token_accuracy": 0.18082557171583175,
|
|
"num_tokens": 28334929.0,
|
|
"step": 14485
|
|
},
|
|
{
|
|
"entropy": 6.284310007095337,
|
|
"epoch": 1.448443044934273,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047971192242480544,
|
|
"loss": 5.757,
|
|
"mean_token_accuracy": 0.18275678306818008,
|
|
"num_tokens": 28345157.0,
|
|
"step": 14490
|
|
},
|
|
{
|
|
"entropy": 6.231031274795532,
|
|
"epoch": 1.4489428699955016,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004796971096044422,
|
|
"loss": 5.6728,
|
|
"mean_token_accuracy": 0.17863090485334396,
|
|
"num_tokens": 28354277.0,
|
|
"step": 14495
|
|
},
|
|
{
|
|
"entropy": 6.192262363433838,
|
|
"epoch": 1.44944269505673,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004796822916339523,
|
|
"loss": 5.6724,
|
|
"mean_token_accuracy": 0.1871244117617607,
|
|
"num_tokens": 28364154.0,
|
|
"step": 14500
|
|
},
|
|
{
|
|
"entropy": 6.257124137878418,
|
|
"epoch": 1.4499425201179588,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047966746851370865,
|
|
"loss": 5.7319,
|
|
"mean_token_accuracy": 0.17843688577413558,
|
|
"num_tokens": 28375260.0,
|
|
"step": 14505
|
|
},
|
|
{
|
|
"entropy": 6.208124828338623,
|
|
"epoch": 1.4504423451791872,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004796526402440841,
|
|
"loss": 5.7242,
|
|
"mean_token_accuracy": 0.17865039259195328,
|
|
"num_tokens": 28384359.0,
|
|
"step": 14510
|
|
},
|
|
{
|
|
"entropy": 6.247933626174927,
|
|
"epoch": 1.450942170240416,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004796378068254518,
|
|
"loss": 5.7184,
|
|
"mean_token_accuracy": 0.1818345382809639,
|
|
"num_tokens": 28394389.0,
|
|
"step": 14515
|
|
},
|
|
{
|
|
"entropy": 6.2347142696380615,
|
|
"epoch": 1.4514419953016444,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000479622968258185,
|
|
"loss": 5.7336,
|
|
"mean_token_accuracy": 0.17837004065513612,
|
|
"num_tokens": 28403495.0,
|
|
"step": 14520
|
|
},
|
|
{
|
|
"entropy": 6.264205694198608,
|
|
"epoch": 1.451941820362873,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004796081245426569,
|
|
"loss": 5.7895,
|
|
"mean_token_accuracy": 0.17259479761123658,
|
|
"num_tokens": 28413132.0,
|
|
"step": 14525
|
|
},
|
|
{
|
|
"entropy": 6.2543176174163815,
|
|
"epoch": 1.4524416454241016,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00047959327567924115,
|
|
"loss": 5.6871,
|
|
"mean_token_accuracy": 0.18983481228351592,
|
|
"num_tokens": 28423815.0,
|
|
"step": 14530
|
|
},
|
|
{
|
|
"entropy": 6.273637342453003,
|
|
"epoch": 1.45294147048533,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047957842166831103,
|
|
"loss": 5.6664,
|
|
"mean_token_accuracy": 0.18426739275455475,
|
|
"num_tokens": 28433682.0,
|
|
"step": 14535
|
|
},
|
|
{
|
|
"entropy": 6.230832433700561,
|
|
"epoch": 1.4534412955465588,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00047956356251024066,
|
|
"loss": 5.6862,
|
|
"mean_token_accuracy": 0.18629868775606157,
|
|
"num_tokens": 28442388.0,
|
|
"step": 14540
|
|
},
|
|
{
|
|
"entropy": 6.245588207244873,
|
|
"epoch": 1.4539411206077872,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004795486982054036,
|
|
"loss": 5.7198,
|
|
"mean_token_accuracy": 0.1811943307518959,
|
|
"num_tokens": 28452753.0,
|
|
"step": 14545
|
|
},
|
|
{
|
|
"entropy": 6.240262889862061,
|
|
"epoch": 1.454440945669016,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000479533828754174,
|
|
"loss": 5.8139,
|
|
"mean_token_accuracy": 0.17350170612335206,
|
|
"num_tokens": 28462818.0,
|
|
"step": 14550
|
|
},
|
|
{
|
|
"entropy": 6.22239580154419,
|
|
"epoch": 1.4549407707302444,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004795189541569258,
|
|
"loss": 5.7287,
|
|
"mean_token_accuracy": 0.1838924616575241,
|
|
"num_tokens": 28472208.0,
|
|
"step": 14555
|
|
},
|
|
{
|
|
"entropy": 6.2153726577758786,
|
|
"epoch": 1.455440595791473,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047950407441403343,
|
|
"loss": 5.6884,
|
|
"mean_token_accuracy": 0.18518940657377242,
|
|
"num_tokens": 28480887.0,
|
|
"step": 14560
|
|
},
|
|
{
|
|
"entropy": 6.269230318069458,
|
|
"epoch": 1.4559404208527016,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004794891895258711,
|
|
"loss": 5.8172,
|
|
"mean_token_accuracy": 0.1805801972746849,
|
|
"num_tokens": 28491805.0,
|
|
"step": 14565
|
|
},
|
|
{
|
|
"entropy": 6.28852071762085,
|
|
"epoch": 1.45644024591393,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004794742994928134,
|
|
"loss": 5.7526,
|
|
"mean_token_accuracy": 0.1828996941447258,
|
|
"num_tokens": 28502913.0,
|
|
"step": 14570
|
|
},
|
|
{
|
|
"entropy": 6.268663024902343,
|
|
"epoch": 1.4569400709751588,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000479459404315235,
|
|
"loss": 5.6663,
|
|
"mean_token_accuracy": 0.18062652051448821,
|
|
"num_tokens": 28513143.0,
|
|
"step": 14575
|
|
},
|
|
{
|
|
"entropy": 6.251817941665649,
|
|
"epoch": 1.4574398960363872,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047944450399351054,
|
|
"loss": 5.7714,
|
|
"mean_token_accuracy": 0.17653846889734268,
|
|
"num_tokens": 28522211.0,
|
|
"step": 14580
|
|
},
|
|
{
|
|
"entropy": 6.221505069732666,
|
|
"epoch": 1.457939721097616,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000479429598528015,
|
|
"loss": 5.7573,
|
|
"mean_token_accuracy": 0.17969507575035096,
|
|
"num_tokens": 28531672.0,
|
|
"step": 14585
|
|
},
|
|
{
|
|
"entropy": 6.188843441009522,
|
|
"epoch": 1.4584395461588444,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004794146879191233,
|
|
"loss": 5.6974,
|
|
"mean_token_accuracy": 0.1876656726002693,
|
|
"num_tokens": 28541614.0,
|
|
"step": 14590
|
|
},
|
|
{
|
|
"entropy": 6.268785429000855,
|
|
"epoch": 1.458939371220073,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004793997721672107,
|
|
"loss": 5.785,
|
|
"mean_token_accuracy": 0.17084388732910155,
|
|
"num_tokens": 28550353.0,
|
|
"step": 14595
|
|
},
|
|
{
|
|
"entropy": 6.248242282867432,
|
|
"epoch": 1.4594391962813016,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047938485127265243,
|
|
"loss": 5.735,
|
|
"mean_token_accuracy": 0.1758405774831772,
|
|
"num_tokens": 28559772.0,
|
|
"step": 14600
|
|
},
|
|
{
|
|
"entropy": 6.275469350814819,
|
|
"epoch": 1.45993902134253,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004793699252358239,
|
|
"loss": 5.7522,
|
|
"mean_token_accuracy": 0.17680173516273498,
|
|
"num_tokens": 28569564.0,
|
|
"step": 14605
|
|
},
|
|
{
|
|
"entropy": 6.272626495361328,
|
|
"epoch": 1.4604388464037588,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004793549940571006,
|
|
"loss": 5.7618,
|
|
"mean_token_accuracy": 0.1771249830722809,
|
|
"num_tokens": 28579473.0,
|
|
"step": 14610
|
|
},
|
|
{
|
|
"entropy": 6.291054010391235,
|
|
"epoch": 1.4609386714649872,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047934005773685824,
|
|
"loss": 5.7045,
|
|
"mean_token_accuracy": 0.18777770400047303,
|
|
"num_tokens": 28588407.0,
|
|
"step": 14615
|
|
},
|
|
{
|
|
"entropy": 6.265645217895508,
|
|
"epoch": 1.461438496526216,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047932511627547266,
|
|
"loss": 5.8238,
|
|
"mean_token_accuracy": 0.1723314568400383,
|
|
"num_tokens": 28599931.0,
|
|
"step": 14620
|
|
},
|
|
{
|
|
"entropy": 6.092682218551635,
|
|
"epoch": 1.4619383215874444,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004793101696733197,
|
|
"loss": 5.5125,
|
|
"mean_token_accuracy": 0.2017038345336914,
|
|
"num_tokens": 28609317.0,
|
|
"step": 14625
|
|
},
|
|
{
|
|
"entropy": 6.288852214813232,
|
|
"epoch": 1.4624381466486729,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047929521793077545,
|
|
"loss": 5.8269,
|
|
"mean_token_accuracy": 0.16894698441028594,
|
|
"num_tokens": 28618248.0,
|
|
"step": 14630
|
|
},
|
|
{
|
|
"entropy": 6.28073263168335,
|
|
"epoch": 1.4629379717099016,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004792802610482161,
|
|
"loss": 5.7657,
|
|
"mean_token_accuracy": 0.18213897496461867,
|
|
"num_tokens": 28629046.0,
|
|
"step": 14635
|
|
},
|
|
{
|
|
"entropy": 6.333286905288697,
|
|
"epoch": 1.46343779677113,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004792652990260179,
|
|
"loss": 5.8457,
|
|
"mean_token_accuracy": 0.16875241696834564,
|
|
"num_tokens": 28640829.0,
|
|
"step": 14640
|
|
},
|
|
{
|
|
"entropy": 6.275928783416748,
|
|
"epoch": 1.4639376218323585,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004792503318645574,
|
|
"loss": 5.7018,
|
|
"mean_token_accuracy": 0.1893280491232872,
|
|
"num_tokens": 28650812.0,
|
|
"step": 14645
|
|
},
|
|
{
|
|
"entropy": 6.290628480911255,
|
|
"epoch": 1.4644374468935872,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047923535956421104,
|
|
"loss": 5.7901,
|
|
"mean_token_accuracy": 0.17327506542205812,
|
|
"num_tokens": 28661795.0,
|
|
"step": 14650
|
|
},
|
|
{
|
|
"entropy": 6.257214450836182,
|
|
"epoch": 1.464937271954816,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047922038212535565,
|
|
"loss": 5.6335,
|
|
"mean_token_accuracy": 0.18375496715307235,
|
|
"num_tokens": 28670729.0,
|
|
"step": 14655
|
|
},
|
|
{
|
|
"entropy": 6.172500705718994,
|
|
"epoch": 1.4654370970160444,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00047920539954836793,
|
|
"loss": 5.6682,
|
|
"mean_token_accuracy": 0.187482550740242,
|
|
"num_tokens": 28680469.0,
|
|
"step": 14660
|
|
},
|
|
{
|
|
"entropy": 6.224727916717529,
|
|
"epoch": 1.4659369220772729,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000479190411833625,
|
|
"loss": 5.7402,
|
|
"mean_token_accuracy": 0.1769607737660408,
|
|
"num_tokens": 28689698.0,
|
|
"step": 14665
|
|
},
|
|
{
|
|
"entropy": 6.32418851852417,
|
|
"epoch": 1.4664367471385016,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00047917541898150377,
|
|
"loss": 5.6637,
|
|
"mean_token_accuracy": 0.18407945930957795,
|
|
"num_tokens": 28699861.0,
|
|
"step": 14670
|
|
},
|
|
{
|
|
"entropy": 6.250701856613159,
|
|
"epoch": 1.46693657219973,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047916042099238154,
|
|
"loss": 5.7094,
|
|
"mean_token_accuracy": 0.17601218223571777,
|
|
"num_tokens": 28709370.0,
|
|
"step": 14675
|
|
},
|
|
{
|
|
"entropy": 6.307362079620361,
|
|
"epoch": 1.4674363972609585,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047914541786663566,
|
|
"loss": 5.8298,
|
|
"mean_token_accuracy": 0.17585534900426864,
|
|
"num_tokens": 28718123.0,
|
|
"step": 14680
|
|
},
|
|
{
|
|
"entropy": 6.321792888641357,
|
|
"epoch": 1.4679362223221872,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047913040960464363,
|
|
"loss": 5.8276,
|
|
"mean_token_accuracy": 0.17360683530569077,
|
|
"num_tokens": 28727972.0,
|
|
"step": 14685
|
|
},
|
|
{
|
|
"entropy": 6.264152383804321,
|
|
"epoch": 1.468436047383416,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00047911539620678305,
|
|
"loss": 5.7366,
|
|
"mean_token_accuracy": 0.17280648946762084,
|
|
"num_tokens": 28737988.0,
|
|
"step": 14690
|
|
},
|
|
{
|
|
"entropy": 6.309325695037842,
|
|
"epoch": 1.4689358724446444,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004791003776734316,
|
|
"loss": 5.7926,
|
|
"mean_token_accuracy": 0.1738839790225029,
|
|
"num_tokens": 28747852.0,
|
|
"step": 14695
|
|
},
|
|
{
|
|
"entropy": 6.221268844604492,
|
|
"epoch": 1.4694356975058729,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047908535400496713,
|
|
"loss": 5.6579,
|
|
"mean_token_accuracy": 0.1863781675696373,
|
|
"num_tokens": 28758652.0,
|
|
"step": 14700
|
|
},
|
|
{
|
|
"entropy": 6.1771800994873045,
|
|
"epoch": 1.4699355225671016,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047907032520176765,
|
|
"loss": 5.6636,
|
|
"mean_token_accuracy": 0.18256059437990188,
|
|
"num_tokens": 28767603.0,
|
|
"step": 14705
|
|
},
|
|
{
|
|
"entropy": 6.209838914871216,
|
|
"epoch": 1.47043534762833,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004790552912642113,
|
|
"loss": 5.7185,
|
|
"mean_token_accuracy": 0.1834683448076248,
|
|
"num_tokens": 28777984.0,
|
|
"step": 14710
|
|
},
|
|
{
|
|
"entropy": 6.303139591217041,
|
|
"epoch": 1.4709351726895585,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047904025219267643,
|
|
"loss": 5.7719,
|
|
"mean_token_accuracy": 0.1812454417347908,
|
|
"num_tokens": 28789033.0,
|
|
"step": 14715
|
|
},
|
|
{
|
|
"entropy": 6.246758270263672,
|
|
"epoch": 1.4714349977507872,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00047902520798754125,
|
|
"loss": 5.6877,
|
|
"mean_token_accuracy": 0.1846887946128845,
|
|
"num_tokens": 28797728.0,
|
|
"step": 14720
|
|
},
|
|
{
|
|
"entropy": 6.167460489273071,
|
|
"epoch": 1.471934822812016,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004790101586491843,
|
|
"loss": 5.6966,
|
|
"mean_token_accuracy": 0.17763669639825821,
|
|
"num_tokens": 28807505.0,
|
|
"step": 14725
|
|
},
|
|
{
|
|
"entropy": 6.261149978637695,
|
|
"epoch": 1.4724346478732444,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004789951041779843,
|
|
"loss": 5.7515,
|
|
"mean_token_accuracy": 0.18463467061519623,
|
|
"num_tokens": 28817289.0,
|
|
"step": 14730
|
|
},
|
|
{
|
|
"entropy": 6.225901651382446,
|
|
"epoch": 1.4729344729344729,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047898004457432,
|
|
"loss": 5.7394,
|
|
"mean_token_accuracy": 0.18069594651460646,
|
|
"num_tokens": 28827697.0,
|
|
"step": 14735
|
|
},
|
|
{
|
|
"entropy": 6.322522115707398,
|
|
"epoch": 1.4734342979957016,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004789649798385702,
|
|
"loss": 5.796,
|
|
"mean_token_accuracy": 0.1741927146911621,
|
|
"num_tokens": 28837427.0,
|
|
"step": 14740
|
|
},
|
|
{
|
|
"entropy": 6.30994553565979,
|
|
"epoch": 1.47393412305693,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00047894990997111403,
|
|
"loss": 5.7579,
|
|
"mean_token_accuracy": 0.17023663073778153,
|
|
"num_tokens": 28845692.0,
|
|
"step": 14745
|
|
},
|
|
{
|
|
"entropy": 6.206459951400757,
|
|
"epoch": 1.4744339481181585,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047893483497233057,
|
|
"loss": 5.6505,
|
|
"mean_token_accuracy": 0.18078735023736953,
|
|
"num_tokens": 28854854.0,
|
|
"step": 14750
|
|
},
|
|
{
|
|
"entropy": 6.249371671676636,
|
|
"epoch": 1.4749337731793872,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004789197548425992,
|
|
"loss": 5.729,
|
|
"mean_token_accuracy": 0.17724224776029587,
|
|
"num_tokens": 28865711.0,
|
|
"step": 14755
|
|
},
|
|
{
|
|
"entropy": 6.191334676742554,
|
|
"epoch": 1.4754335982406157,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004789046695822992,
|
|
"loss": 5.6217,
|
|
"mean_token_accuracy": 0.19156913608312606,
|
|
"num_tokens": 28874193.0,
|
|
"step": 14760
|
|
},
|
|
{
|
|
"entropy": 6.1859450340271,
|
|
"epoch": 1.4759334233018444,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047888957919181026,
|
|
"loss": 5.7192,
|
|
"mean_token_accuracy": 0.1828435555100441,
|
|
"num_tokens": 28883652.0,
|
|
"step": 14765
|
|
},
|
|
{
|
|
"entropy": 6.256581974029541,
|
|
"epoch": 1.4764332483630729,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004788744836715119,
|
|
"loss": 5.7477,
|
|
"mean_token_accuracy": 0.17860166281461715,
|
|
"num_tokens": 28893040.0,
|
|
"step": 14770
|
|
},
|
|
{
|
|
"entropy": 6.2388592720031735,
|
|
"epoch": 1.4769330734243016,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004788593830217841,
|
|
"loss": 5.7052,
|
|
"mean_token_accuracy": 0.17961995601654052,
|
|
"num_tokens": 28903330.0,
|
|
"step": 14775
|
|
},
|
|
{
|
|
"entropy": 6.245730400085449,
|
|
"epoch": 1.47743289848553,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047884427724300657,
|
|
"loss": 5.7622,
|
|
"mean_token_accuracy": 0.18025969564914704,
|
|
"num_tokens": 28913032.0,
|
|
"step": 14780
|
|
},
|
|
{
|
|
"entropy": 6.238328075408935,
|
|
"epoch": 1.4779327235467585,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004788291663355595,
|
|
"loss": 5.6739,
|
|
"mean_token_accuracy": 0.1868657201528549,
|
|
"num_tokens": 28921298.0,
|
|
"step": 14785
|
|
},
|
|
{
|
|
"entropy": 6.181318950653076,
|
|
"epoch": 1.4784325486079872,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004788140502998231,
|
|
"loss": 5.6282,
|
|
"mean_token_accuracy": 0.19101465195417405,
|
|
"num_tokens": 28930724.0,
|
|
"step": 14790
|
|
},
|
|
{
|
|
"entropy": 6.293069076538086,
|
|
"epoch": 1.4789323736692157,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004787989291361776,
|
|
"loss": 5.8476,
|
|
"mean_token_accuracy": 0.16930603235960007,
|
|
"num_tokens": 28941670.0,
|
|
"step": 14795
|
|
},
|
|
{
|
|
"entropy": 6.230864000320435,
|
|
"epoch": 1.4794321987304444,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004787838028450035,
|
|
"loss": 5.6678,
|
|
"mean_token_accuracy": 0.1806313067674637,
|
|
"num_tokens": 28950175.0,
|
|
"step": 14800
|
|
},
|
|
{
|
|
"entropy": 6.23652663230896,
|
|
"epoch": 1.4799320237916729,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047876867142668136,
|
|
"loss": 5.6085,
|
|
"mean_token_accuracy": 0.18647850453853607,
|
|
"num_tokens": 28958410.0,
|
|
"step": 14805
|
|
},
|
|
{
|
|
"entropy": 6.18452000617981,
|
|
"epoch": 1.4804318488529016,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004787535348815918,
|
|
"loss": 5.5472,
|
|
"mean_token_accuracy": 0.190141199529171,
|
|
"num_tokens": 28967911.0,
|
|
"step": 14810
|
|
},
|
|
{
|
|
"entropy": 6.140769004821777,
|
|
"epoch": 1.48093167391413,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047873839321011587,
|
|
"loss": 5.6049,
|
|
"mean_token_accuracy": 0.1963050216436386,
|
|
"num_tokens": 28978112.0,
|
|
"step": 14815
|
|
},
|
|
{
|
|
"entropy": 6.2165360927581785,
|
|
"epoch": 1.4814314989753585,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004787232464126343,
|
|
"loss": 5.6844,
|
|
"mean_token_accuracy": 0.18107152581214905,
|
|
"num_tokens": 28987960.0,
|
|
"step": 14820
|
|
},
|
|
{
|
|
"entropy": 6.274215745925903,
|
|
"epoch": 1.4819313240365872,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004787080944895283,
|
|
"loss": 5.756,
|
|
"mean_token_accuracy": 0.17299099117517472,
|
|
"num_tokens": 28997000.0,
|
|
"step": 14825
|
|
},
|
|
{
|
|
"entropy": 6.323394536972046,
|
|
"epoch": 1.4824311490978157,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047869293744117906,
|
|
"loss": 5.7461,
|
|
"mean_token_accuracy": 0.18001665323972701,
|
|
"num_tokens": 29005725.0,
|
|
"step": 14830
|
|
},
|
|
{
|
|
"entropy": 6.13763313293457,
|
|
"epoch": 1.4829309741590444,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047867777526796793,
|
|
"loss": 5.6754,
|
|
"mean_token_accuracy": 0.1855710968375206,
|
|
"num_tokens": 29015168.0,
|
|
"step": 14835
|
|
},
|
|
{
|
|
"entropy": 6.258671140670776,
|
|
"epoch": 1.4834307992202729,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004786626079702764,
|
|
"loss": 5.8186,
|
|
"mean_token_accuracy": 0.17742711752653123,
|
|
"num_tokens": 29025170.0,
|
|
"step": 14840
|
|
},
|
|
{
|
|
"entropy": 6.30791654586792,
|
|
"epoch": 1.4839306242815016,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004786474355484861,
|
|
"loss": 5.6822,
|
|
"mean_token_accuracy": 0.18363353610038757,
|
|
"num_tokens": 29034262.0,
|
|
"step": 14845
|
|
},
|
|
{
|
|
"entropy": 6.266468620300293,
|
|
"epoch": 1.48443044934273,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004786322580029786,
|
|
"loss": 5.7421,
|
|
"mean_token_accuracy": 0.17769265323877334,
|
|
"num_tokens": 29043847.0,
|
|
"step": 14850
|
|
},
|
|
{
|
|
"entropy": 6.2174155712127686,
|
|
"epoch": 1.4849302744039585,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00047861707533413593,
|
|
"loss": 5.719,
|
|
"mean_token_accuracy": 0.1878831699490547,
|
|
"num_tokens": 29053378.0,
|
|
"step": 14855
|
|
},
|
|
{
|
|
"entropy": 6.283231496810913,
|
|
"epoch": 1.4854300994651872,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004786018875423401,
|
|
"loss": 5.7334,
|
|
"mean_token_accuracy": 0.18172533810138702,
|
|
"num_tokens": 29063335.0,
|
|
"step": 14860
|
|
},
|
|
{
|
|
"entropy": 6.218316173553466,
|
|
"epoch": 1.4859299245264157,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00047858669462797317,
|
|
"loss": 5.698,
|
|
"mean_token_accuracy": 0.18778129816055297,
|
|
"num_tokens": 29073322.0,
|
|
"step": 14865
|
|
},
|
|
{
|
|
"entropy": 6.213953256607056,
|
|
"epoch": 1.4864297495876444,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047857149659141736,
|
|
"loss": 5.7557,
|
|
"mean_token_accuracy": 0.1725238651037216,
|
|
"num_tokens": 29082618.0,
|
|
"step": 14870
|
|
},
|
|
{
|
|
"entropy": 6.238774585723877,
|
|
"epoch": 1.4869295746488729,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004785562934330551,
|
|
"loss": 5.6162,
|
|
"mean_token_accuracy": 0.1798434153199196,
|
|
"num_tokens": 29091854.0,
|
|
"step": 14875
|
|
},
|
|
{
|
|
"entropy": 6.188840055465699,
|
|
"epoch": 1.4874293997101016,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00047854108515326885,
|
|
"loss": 5.6481,
|
|
"mean_token_accuracy": 0.18778010904788972,
|
|
"num_tokens": 29100816.0,
|
|
"step": 14880
|
|
},
|
|
{
|
|
"entropy": 6.21351842880249,
|
|
"epoch": 1.48792922477133,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004785258717524412,
|
|
"loss": 5.6913,
|
|
"mean_token_accuracy": 0.1818792700767517,
|
|
"num_tokens": 29110216.0,
|
|
"step": 14885
|
|
},
|
|
{
|
|
"entropy": 6.281248760223389,
|
|
"epoch": 1.4884290498325585,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047851065323095514,
|
|
"loss": 5.7408,
|
|
"mean_token_accuracy": 0.17726927399635314,
|
|
"num_tokens": 29120910.0,
|
|
"step": 14890
|
|
},
|
|
{
|
|
"entropy": 6.249174404144287,
|
|
"epoch": 1.4889288748937872,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004784954295891933,
|
|
"loss": 5.766,
|
|
"mean_token_accuracy": 0.1774901956319809,
|
|
"num_tokens": 29131163.0,
|
|
"step": 14895
|
|
},
|
|
{
|
|
"entropy": 6.196197509765625,
|
|
"epoch": 1.4894286999550157,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047848020082753883,
|
|
"loss": 5.6721,
|
|
"mean_token_accuracy": 0.18522736430168152,
|
|
"num_tokens": 29140549.0,
|
|
"step": 14900
|
|
},
|
|
{
|
|
"entropy": 6.21249794960022,
|
|
"epoch": 1.4899285250162442,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004784649669463749,
|
|
"loss": 5.6456,
|
|
"mean_token_accuracy": 0.17905239909887313,
|
|
"num_tokens": 29149884.0,
|
|
"step": 14905
|
|
},
|
|
{
|
|
"entropy": 6.242288541793823,
|
|
"epoch": 1.4904283500774729,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047844972794608474,
|
|
"loss": 5.7878,
|
|
"mean_token_accuracy": 0.17596502006053924,
|
|
"num_tokens": 29158913.0,
|
|
"step": 14910
|
|
},
|
|
{
|
|
"entropy": 6.282042217254639,
|
|
"epoch": 1.4909281751387016,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047843448382705185,
|
|
"loss": 5.7563,
|
|
"mean_token_accuracy": 0.1726479262113571,
|
|
"num_tokens": 29167548.0,
|
|
"step": 14915
|
|
},
|
|
{
|
|
"entropy": 6.254443979263305,
|
|
"epoch": 1.49142800019993,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047841923458965966,
|
|
"loss": 5.7088,
|
|
"mean_token_accuracy": 0.18205585181713105,
|
|
"num_tokens": 29177155.0,
|
|
"step": 14920
|
|
},
|
|
{
|
|
"entropy": 6.285437536239624,
|
|
"epoch": 1.4919278252611585,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047840398023429176,
|
|
"loss": 5.7537,
|
|
"mean_token_accuracy": 0.18187938630580902,
|
|
"num_tokens": 29185920.0,
|
|
"step": 14925
|
|
},
|
|
{
|
|
"entropy": 6.3413660526275635,
|
|
"epoch": 1.4924276503223872,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00047838872076133213,
|
|
"loss": 5.725,
|
|
"mean_token_accuracy": 0.17912642061710357,
|
|
"num_tokens": 29195707.0,
|
|
"step": 14930
|
|
},
|
|
{
|
|
"entropy": 6.279572582244873,
|
|
"epoch": 1.4929274753836157,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004783734561711647,
|
|
"loss": 5.785,
|
|
"mean_token_accuracy": 0.17246552556753159,
|
|
"num_tokens": 29206395.0,
|
|
"step": 14935
|
|
},
|
|
{
|
|
"entropy": 6.250882720947265,
|
|
"epoch": 1.4934273004448442,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047835818646417333,
|
|
"loss": 5.7461,
|
|
"mean_token_accuracy": 0.18617818355560303,
|
|
"num_tokens": 29215903.0,
|
|
"step": 14940
|
|
},
|
|
{
|
|
"entropy": 6.29022364616394,
|
|
"epoch": 1.4939271255060729,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004783429116407423,
|
|
"loss": 5.7727,
|
|
"mean_token_accuracy": 0.18043697029352188,
|
|
"num_tokens": 29225768.0,
|
|
"step": 14945
|
|
},
|
|
{
|
|
"entropy": 6.2603050708770756,
|
|
"epoch": 1.4944269505673016,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047832763170125605,
|
|
"loss": 5.7707,
|
|
"mean_token_accuracy": 0.17429576069116592,
|
|
"num_tokens": 29235612.0,
|
|
"step": 14950
|
|
},
|
|
{
|
|
"entropy": 6.226527833938599,
|
|
"epoch": 1.49492677562853,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047831234664609887,
|
|
"loss": 5.661,
|
|
"mean_token_accuracy": 0.1860797181725502,
|
|
"num_tokens": 29244556.0,
|
|
"step": 14955
|
|
},
|
|
{
|
|
"entropy": 6.245067691802978,
|
|
"epoch": 1.4954266006897585,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047829705647565535,
|
|
"loss": 5.8128,
|
|
"mean_token_accuracy": 0.17385198473930358,
|
|
"num_tokens": 29254978.0,
|
|
"step": 14960
|
|
},
|
|
{
|
|
"entropy": 6.193341684341431,
|
|
"epoch": 1.4959264257509872,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004782817611903102,
|
|
"loss": 5.6238,
|
|
"mean_token_accuracy": 0.18424207717180252,
|
|
"num_tokens": 29263339.0,
|
|
"step": 14965
|
|
},
|
|
{
|
|
"entropy": 6.192237091064453,
|
|
"epoch": 1.4964262508122157,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00047826646079044826,
|
|
"loss": 5.564,
|
|
"mean_token_accuracy": 0.19148816615343095,
|
|
"num_tokens": 29272707.0,
|
|
"step": 14970
|
|
},
|
|
{
|
|
"entropy": 6.251887416839599,
|
|
"epoch": 1.4969260758734442,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047825115527645447,
|
|
"loss": 5.7427,
|
|
"mean_token_accuracy": 0.1754201978445053,
|
|
"num_tokens": 29282292.0,
|
|
"step": 14975
|
|
},
|
|
{
|
|
"entropy": 6.223221683502198,
|
|
"epoch": 1.4974259009346729,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004782358446487139,
|
|
"loss": 5.7825,
|
|
"mean_token_accuracy": 0.18608297854661943,
|
|
"num_tokens": 29291289.0,
|
|
"step": 14980
|
|
},
|
|
{
|
|
"entropy": 6.185023450851441,
|
|
"epoch": 1.4979257259959016,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00047822052890761173,
|
|
"loss": 5.6603,
|
|
"mean_token_accuracy": 0.18364254385232925,
|
|
"num_tokens": 29300166.0,
|
|
"step": 14985
|
|
},
|
|
{
|
|
"entropy": 6.192966556549072,
|
|
"epoch": 1.49842555105713,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004782052080535334,
|
|
"loss": 5.6764,
|
|
"mean_token_accuracy": 0.17342044562101364,
|
|
"num_tokens": 29308422.0,
|
|
"step": 14990
|
|
},
|
|
{
|
|
"entropy": 6.278373193740845,
|
|
"epoch": 1.4989253761183585,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004781898820868644,
|
|
"loss": 5.6918,
|
|
"mean_token_accuracy": 0.188363017141819,
|
|
"num_tokens": 29317699.0,
|
|
"step": 14995
|
|
},
|
|
{
|
|
"entropy": 6.292652702331543,
|
|
"epoch": 1.4994252011795872,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004781745510079901,
|
|
"loss": 5.7629,
|
|
"mean_token_accuracy": 0.17503958493471145,
|
|
"num_tokens": 29327711.0,
|
|
"step": 15000
|
|
},
|
|
{
|
|
"epoch": 1.4994252011795872,
|
|
"eval_entropy": 6.004267418946657,
|
|
"eval_loss": 5.76856803894043,
|
|
"eval_mean_token_accuracy": 0.18768596765891205,
|
|
"eval_num_tokens": 29327711.0,
|
|
"eval_runtime": 18.19,
|
|
"eval_samples_per_second": 1706.707,
|
|
"eval_steps_per_second": 213.359,
|
|
"step": 15000
|
|
},
|
|
{
|
|
"entropy": 6.2175031185150145,
|
|
"epoch": 1.4999250262408157,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047815921481729647,
|
|
"loss": 5.6609,
|
|
"mean_token_accuracy": 0.18214458376169204,
|
|
"num_tokens": 29336540.0,
|
|
"step": 15005
|
|
},
|
|
{
|
|
"entropy": 6.273611068725586,
|
|
"epoch": 1.5004248513020442,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004781438735151693,
|
|
"loss": 5.8716,
|
|
"mean_token_accuracy": 0.1653343290090561,
|
|
"num_tokens": 29345512.0,
|
|
"step": 15010
|
|
},
|
|
{
|
|
"entropy": 6.259011697769165,
|
|
"epoch": 1.5009246763632729,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047812852710199446,
|
|
"loss": 5.8285,
|
|
"mean_token_accuracy": 0.17300787717103958,
|
|
"num_tokens": 29355726.0,
|
|
"step": 15015
|
|
},
|
|
{
|
|
"entropy": 6.265674304962158,
|
|
"epoch": 1.5014245014245016,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004781131755781582,
|
|
"loss": 5.6595,
|
|
"mean_token_accuracy": 0.18554275631904601,
|
|
"num_tokens": 29366570.0,
|
|
"step": 15020
|
|
},
|
|
{
|
|
"entropy": 6.2745812892913815,
|
|
"epoch": 1.50192432648573,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004780978189440467,
|
|
"loss": 5.7663,
|
|
"mean_token_accuracy": 0.17833191454410552,
|
|
"num_tokens": 29376356.0,
|
|
"step": 15025
|
|
},
|
|
{
|
|
"entropy": 6.3148839473724365,
|
|
"epoch": 1.5024241515469585,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047808245720004633,
|
|
"loss": 5.8105,
|
|
"mean_token_accuracy": 0.17002350687980652,
|
|
"num_tokens": 29385246.0,
|
|
"step": 15030
|
|
},
|
|
{
|
|
"entropy": 6.215655517578125,
|
|
"epoch": 1.5029239766081872,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047806709034654355,
|
|
"loss": 5.6231,
|
|
"mean_token_accuracy": 0.18777413070201873,
|
|
"num_tokens": 29395352.0,
|
|
"step": 15035
|
|
},
|
|
{
|
|
"entropy": 6.250268745422363,
|
|
"epoch": 1.5034238016694157,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004780517183839251,
|
|
"loss": 5.7727,
|
|
"mean_token_accuracy": 0.1738983228802681,
|
|
"num_tokens": 29404771.0,
|
|
"step": 15040
|
|
},
|
|
{
|
|
"entropy": 6.2402012825012205,
|
|
"epoch": 1.5039236267306442,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004780363413125777,
|
|
"loss": 5.685,
|
|
"mean_token_accuracy": 0.1783513233065605,
|
|
"num_tokens": 29413378.0,
|
|
"step": 15045
|
|
},
|
|
{
|
|
"entropy": 6.264682102203369,
|
|
"epoch": 1.5044234517918729,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047802095913288814,
|
|
"loss": 5.7859,
|
|
"mean_token_accuracy": 0.17858470976352692,
|
|
"num_tokens": 29424125.0,
|
|
"step": 15050
|
|
},
|
|
{
|
|
"entropy": 6.205320024490357,
|
|
"epoch": 1.5049232768531016,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047800557184524345,
|
|
"loss": 5.7504,
|
|
"mean_token_accuracy": 0.17511598020792007,
|
|
"num_tokens": 29435411.0,
|
|
"step": 15055
|
|
},
|
|
{
|
|
"entropy": 6.244156122207642,
|
|
"epoch": 1.5054231019143298,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004779901794500308,
|
|
"loss": 5.7585,
|
|
"mean_token_accuracy": 0.17864918559789658,
|
|
"num_tokens": 29445515.0,
|
|
"step": 15060
|
|
},
|
|
{
|
|
"entropy": 6.316118335723877,
|
|
"epoch": 1.5059229269755585,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00047797478194763754,
|
|
"loss": 5.7705,
|
|
"mean_token_accuracy": 0.17464115619659423,
|
|
"num_tokens": 29454864.0,
|
|
"step": 15065
|
|
},
|
|
{
|
|
"entropy": 6.2774107456207275,
|
|
"epoch": 1.5064227520367872,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047795937933845103,
|
|
"loss": 5.8022,
|
|
"mean_token_accuracy": 0.1760898396372795,
|
|
"num_tokens": 29464443.0,
|
|
"step": 15070
|
|
},
|
|
{
|
|
"entropy": 6.282599639892578,
|
|
"epoch": 1.5069225770980157,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004779439716228587,
|
|
"loss": 5.7473,
|
|
"mean_token_accuracy": 0.1760036751627922,
|
|
"num_tokens": 29474954.0,
|
|
"step": 15075
|
|
},
|
|
{
|
|
"entropy": 6.297124671936035,
|
|
"epoch": 1.5074224021592442,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004779285588012482,
|
|
"loss": 5.7604,
|
|
"mean_token_accuracy": 0.17350617051124573,
|
|
"num_tokens": 29484647.0,
|
|
"step": 15080
|
|
},
|
|
{
|
|
"entropy": 6.259731912612915,
|
|
"epoch": 1.5079222272204729,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047791314087400745,
|
|
"loss": 5.7671,
|
|
"mean_token_accuracy": 0.1819387122988701,
|
|
"num_tokens": 29494782.0,
|
|
"step": 15085
|
|
},
|
|
{
|
|
"entropy": 6.180619955062866,
|
|
"epoch": 1.5084220522817016,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004778977178415243,
|
|
"loss": 5.6542,
|
|
"mean_token_accuracy": 0.1870558962225914,
|
|
"num_tokens": 29505311.0,
|
|
"step": 15090
|
|
},
|
|
{
|
|
"entropy": 6.261593341827393,
|
|
"epoch": 1.5089218773429298,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004778822897041868,
|
|
"loss": 5.6683,
|
|
"mean_token_accuracy": 0.17861256152391433,
|
|
"num_tokens": 29515192.0,
|
|
"step": 15095
|
|
},
|
|
{
|
|
"entropy": 6.2590233325958256,
|
|
"epoch": 1.5094217024041585,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000477866856462383,
|
|
"loss": 5.6765,
|
|
"mean_token_accuracy": 0.18553438484668733,
|
|
"num_tokens": 29524429.0,
|
|
"step": 15100
|
|
},
|
|
{
|
|
"entropy": 6.275223445892334,
|
|
"epoch": 1.5099215274653872,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004778514181165014,
|
|
"loss": 5.689,
|
|
"mean_token_accuracy": 0.17996586114168167,
|
|
"num_tokens": 29532926.0,
|
|
"step": 15105
|
|
},
|
|
{
|
|
"entropy": 6.283464479446411,
|
|
"epoch": 1.5104213525266157,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047783597466693025,
|
|
"loss": 5.7567,
|
|
"mean_token_accuracy": 0.1792757749557495,
|
|
"num_tokens": 29542588.0,
|
|
"step": 15110
|
|
},
|
|
{
|
|
"entropy": 6.251682138442993,
|
|
"epoch": 1.5109211775878442,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004778205261140582,
|
|
"loss": 5.7035,
|
|
"mean_token_accuracy": 0.18114275485277176,
|
|
"num_tokens": 29551710.0,
|
|
"step": 15115
|
|
},
|
|
{
|
|
"entropy": 6.2890753746032715,
|
|
"epoch": 1.5114210026490729,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004778050724582739,
|
|
"loss": 5.8084,
|
|
"mean_token_accuracy": 0.17799570560455322,
|
|
"num_tokens": 29561357.0,
|
|
"step": 15120
|
|
},
|
|
{
|
|
"entropy": 6.20161018371582,
|
|
"epoch": 1.5119208277103013,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047778961369996623,
|
|
"loss": 5.7067,
|
|
"mean_token_accuracy": 0.18194604963064193,
|
|
"num_tokens": 29570060.0,
|
|
"step": 15125
|
|
},
|
|
{
|
|
"entropy": 6.262983417510986,
|
|
"epoch": 1.5124206527715298,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000477774149839524,
|
|
"loss": 5.7349,
|
|
"mean_token_accuracy": 0.17810166478157044,
|
|
"num_tokens": 29580097.0,
|
|
"step": 15130
|
|
},
|
|
{
|
|
"entropy": 6.349424839019775,
|
|
"epoch": 1.5129204778327585,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047775868087733634,
|
|
"loss": 5.8969,
|
|
"mean_token_accuracy": 0.16771436035633086,
|
|
"num_tokens": 29590290.0,
|
|
"step": 15135
|
|
},
|
|
{
|
|
"entropy": 6.305739498138427,
|
|
"epoch": 1.5134203028939872,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047774320681379237,
|
|
"loss": 5.7376,
|
|
"mean_token_accuracy": 0.17773562520742417,
|
|
"num_tokens": 29598839.0,
|
|
"step": 15140
|
|
},
|
|
{
|
|
"entropy": 6.316554832458496,
|
|
"epoch": 1.5139201279552157,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004777277276492816,
|
|
"loss": 5.7465,
|
|
"mean_token_accuracy": 0.18222905397415162,
|
|
"num_tokens": 29609550.0,
|
|
"step": 15145
|
|
},
|
|
{
|
|
"entropy": 6.304064750671387,
|
|
"epoch": 1.5144199530164442,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047771224338419326,
|
|
"loss": 5.8892,
|
|
"mean_token_accuracy": 0.16323867589235305,
|
|
"num_tokens": 29619786.0,
|
|
"step": 15150
|
|
},
|
|
{
|
|
"entropy": 6.2424639701843265,
|
|
"epoch": 1.5149197780776729,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004776967540189171,
|
|
"loss": 5.6692,
|
|
"mean_token_accuracy": 0.18201952576637268,
|
|
"num_tokens": 29630492.0,
|
|
"step": 15155
|
|
},
|
|
{
|
|
"entropy": 6.338004922866821,
|
|
"epoch": 1.5154196031389013,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004776812595538428,
|
|
"loss": 5.7284,
|
|
"mean_token_accuracy": 0.18166555762290953,
|
|
"num_tokens": 29641965.0,
|
|
"step": 15160
|
|
},
|
|
{
|
|
"entropy": 6.278650617599487,
|
|
"epoch": 1.5159194282001298,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047766575998936013,
|
|
"loss": 5.7942,
|
|
"mean_token_accuracy": 0.17298658043146134,
|
|
"num_tokens": 29651692.0,
|
|
"step": 15165
|
|
},
|
|
{
|
|
"entropy": 6.248771095275879,
|
|
"epoch": 1.5164192532613585,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047765025532585907,
|
|
"loss": 5.7737,
|
|
"mean_token_accuracy": 0.17425073981285094,
|
|
"num_tokens": 29660541.0,
|
|
"step": 15170
|
|
},
|
|
{
|
|
"entropy": 6.220727777481079,
|
|
"epoch": 1.5169190783225872,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004776347455637298,
|
|
"loss": 5.7317,
|
|
"mean_token_accuracy": 0.17983776777982713,
|
|
"num_tokens": 29670498.0,
|
|
"step": 15175
|
|
},
|
|
{
|
|
"entropy": 6.223674678802491,
|
|
"epoch": 1.5174189033838157,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004776192307033624,
|
|
"loss": 5.6368,
|
|
"mean_token_accuracy": 0.19010072499513625,
|
|
"num_tokens": 29678898.0,
|
|
"step": 15180
|
|
},
|
|
{
|
|
"entropy": 6.303915166854859,
|
|
"epoch": 1.5179187284450442,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004776037107451473,
|
|
"loss": 5.6581,
|
|
"mean_token_accuracy": 0.19302872568368912,
|
|
"num_tokens": 29689723.0,
|
|
"step": 15185
|
|
},
|
|
{
|
|
"entropy": 6.2228742122650145,
|
|
"epoch": 1.5184185535062729,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000477588185689475,
|
|
"loss": 5.6812,
|
|
"mean_token_accuracy": 0.18620532900094985,
|
|
"num_tokens": 29699246.0,
|
|
"step": 15190
|
|
},
|
|
{
|
|
"entropy": 6.215426683425903,
|
|
"epoch": 1.5189183785675013,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047757265553673606,
|
|
"loss": 5.6542,
|
|
"mean_token_accuracy": 0.1835012450814247,
|
|
"num_tokens": 29709125.0,
|
|
"step": 15195
|
|
},
|
|
{
|
|
"entropy": 6.239310264587402,
|
|
"epoch": 1.5194182036287298,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047755712028732126,
|
|
"loss": 5.6911,
|
|
"mean_token_accuracy": 0.1792364627122879,
|
|
"num_tokens": 29718953.0,
|
|
"step": 15200
|
|
},
|
|
{
|
|
"entropy": 6.293081760406494,
|
|
"epoch": 1.5199180286899585,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004775415799416214,
|
|
"loss": 5.7334,
|
|
"mean_token_accuracy": 0.1754251942038536,
|
|
"num_tokens": 29728764.0,
|
|
"step": 15205
|
|
},
|
|
{
|
|
"entropy": 6.204664707183838,
|
|
"epoch": 1.5204178537511872,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004775260345000275,
|
|
"loss": 5.7254,
|
|
"mean_token_accuracy": 0.17859504669904708,
|
|
"num_tokens": 29738033.0,
|
|
"step": 15210
|
|
},
|
|
{
|
|
"entropy": 6.155918169021606,
|
|
"epoch": 1.5209176788124157,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00047751048396293077,
|
|
"loss": 5.6378,
|
|
"mean_token_accuracy": 0.20051828026771545,
|
|
"num_tokens": 29748450.0,
|
|
"step": 15215
|
|
},
|
|
{
|
|
"entropy": 6.3093719482421875,
|
|
"epoch": 1.5214175038736442,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00047749492833072226,
|
|
"loss": 5.7735,
|
|
"mean_token_accuracy": 0.17426538318395615,
|
|
"num_tokens": 29757984.0,
|
|
"step": 15220
|
|
},
|
|
{
|
|
"entropy": 6.231773710250854,
|
|
"epoch": 1.5219173289348729,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047747936760379354,
|
|
"loss": 5.7397,
|
|
"mean_token_accuracy": 0.1754847690463066,
|
|
"num_tokens": 29768200.0,
|
|
"step": 15225
|
|
},
|
|
{
|
|
"entropy": 6.198132944107056,
|
|
"epoch": 1.5224171539961013,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000477463801782536,
|
|
"loss": 5.7059,
|
|
"mean_token_accuracy": 0.17936768680810927,
|
|
"num_tokens": 29778242.0,
|
|
"step": 15230
|
|
},
|
|
{
|
|
"entropy": 6.3326558589935305,
|
|
"epoch": 1.5229169790573298,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00047744823086734136,
|
|
"loss": 5.8206,
|
|
"mean_token_accuracy": 0.16901098638772966,
|
|
"num_tokens": 29787636.0,
|
|
"step": 15235
|
|
},
|
|
{
|
|
"entropy": 6.314857244491577,
|
|
"epoch": 1.5234168041185585,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047743265485860123,
|
|
"loss": 5.6788,
|
|
"mean_token_accuracy": 0.1858382910490036,
|
|
"num_tokens": 29796537.0,
|
|
"step": 15240
|
|
},
|
|
{
|
|
"entropy": 6.241067600250244,
|
|
"epoch": 1.5239166291797872,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00047741707375670766,
|
|
"loss": 5.6724,
|
|
"mean_token_accuracy": 0.18799417465925217,
|
|
"num_tokens": 29805495.0,
|
|
"step": 15245
|
|
},
|
|
{
|
|
"entropy": 6.229263830184936,
|
|
"epoch": 1.5244164542410157,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004774014875620526,
|
|
"loss": 5.6462,
|
|
"mean_token_accuracy": 0.1823060020804405,
|
|
"num_tokens": 29815193.0,
|
|
"step": 15250
|
|
},
|
|
{
|
|
"entropy": 6.271628570556641,
|
|
"epoch": 1.5249162793022442,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047738589627502814,
|
|
"loss": 5.7357,
|
|
"mean_token_accuracy": 0.1803070455789566,
|
|
"num_tokens": 29825004.0,
|
|
"step": 15255
|
|
},
|
|
{
|
|
"entropy": 6.234771490097046,
|
|
"epoch": 1.5254161043634729,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047737029989602665,
|
|
"loss": 5.7476,
|
|
"mean_token_accuracy": 0.1851629674434662,
|
|
"num_tokens": 29834507.0,
|
|
"step": 15260
|
|
},
|
|
{
|
|
"entropy": 6.19706883430481,
|
|
"epoch": 1.5259159294247013,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004773546984254405,
|
|
"loss": 5.6143,
|
|
"mean_token_accuracy": 0.18455082029104233,
|
|
"num_tokens": 29844397.0,
|
|
"step": 15265
|
|
},
|
|
{
|
|
"entropy": 6.24389533996582,
|
|
"epoch": 1.5264157544859298,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004773390918636622,
|
|
"loss": 5.7069,
|
|
"mean_token_accuracy": 0.18568253219127656,
|
|
"num_tokens": 29855702.0,
|
|
"step": 15270
|
|
},
|
|
{
|
|
"entropy": 6.252154874801636,
|
|
"epoch": 1.5269155795471585,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004773234802110844,
|
|
"loss": 5.6425,
|
|
"mean_token_accuracy": 0.18629636019468307,
|
|
"num_tokens": 29865806.0,
|
|
"step": 15275
|
|
},
|
|
{
|
|
"entropy": 6.1700342178344725,
|
|
"epoch": 1.5274154046083872,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004773078634681,
|
|
"loss": 5.6244,
|
|
"mean_token_accuracy": 0.19658426195383072,
|
|
"num_tokens": 29874827.0,
|
|
"step": 15280
|
|
},
|
|
{
|
|
"entropy": 6.197042512893677,
|
|
"epoch": 1.5279152296696157,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047729224163510167,
|
|
"loss": 5.7243,
|
|
"mean_token_accuracy": 0.17685078084468842,
|
|
"num_tokens": 29883517.0,
|
|
"step": 15285
|
|
},
|
|
{
|
|
"entropy": 6.22168231010437,
|
|
"epoch": 1.5284150547308442,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047727661471248263,
|
|
"loss": 5.6402,
|
|
"mean_token_accuracy": 0.18396209925413132,
|
|
"num_tokens": 29893303.0,
|
|
"step": 15290
|
|
},
|
|
{
|
|
"entropy": 6.2823028564453125,
|
|
"epoch": 1.5289148797920729,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.000477260982700636,
|
|
"loss": 5.8335,
|
|
"mean_token_accuracy": 0.17231102883815766,
|
|
"num_tokens": 29904719.0,
|
|
"step": 15295
|
|
},
|
|
{
|
|
"entropy": 6.317986583709716,
|
|
"epoch": 1.5294147048533013,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004772453455999552,
|
|
"loss": 5.7299,
|
|
"mean_token_accuracy": 0.17988416105508803,
|
|
"num_tokens": 29914852.0,
|
|
"step": 15300
|
|
},
|
|
{
|
|
"entropy": 6.223712921142578,
|
|
"epoch": 1.5299145299145298,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004772297034108334,
|
|
"loss": 5.6933,
|
|
"mean_token_accuracy": 0.17957298159599305,
|
|
"num_tokens": 29924479.0,
|
|
"step": 15305
|
|
},
|
|
{
|
|
"entropy": 6.278890991210938,
|
|
"epoch": 1.5304143549757585,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047721405613366434,
|
|
"loss": 5.744,
|
|
"mean_token_accuracy": 0.1718659445643425,
|
|
"num_tokens": 29933162.0,
|
|
"step": 15310
|
|
},
|
|
{
|
|
"entropy": 6.210498809814453,
|
|
"epoch": 1.5309141800369872,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00047719840376884173,
|
|
"loss": 5.6463,
|
|
"mean_token_accuracy": 0.18544090688228607,
|
|
"num_tokens": 29942468.0,
|
|
"step": 15315
|
|
},
|
|
{
|
|
"entropy": 6.2440009117126465,
|
|
"epoch": 1.5314140050982155,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004771827463167593,
|
|
"loss": 5.7649,
|
|
"mean_token_accuracy": 0.1803063541650772,
|
|
"num_tokens": 29951716.0,
|
|
"step": 15320
|
|
},
|
|
{
|
|
"entropy": 6.238711214065551,
|
|
"epoch": 1.5319138301594442,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004771670837778109,
|
|
"loss": 5.7974,
|
|
"mean_token_accuracy": 0.17299650907516478,
|
|
"num_tokens": 29960233.0,
|
|
"step": 15325
|
|
},
|
|
{
|
|
"entropy": 6.240340757369995,
|
|
"epoch": 1.5324136552206729,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00047715141615239075,
|
|
"loss": 5.7389,
|
|
"mean_token_accuracy": 0.17513295412063598,
|
|
"num_tokens": 29968979.0,
|
|
"step": 15330
|
|
},
|
|
{
|
|
"entropy": 6.236359691619873,
|
|
"epoch": 1.5329134802819013,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047713574344089305,
|
|
"loss": 5.6816,
|
|
"mean_token_accuracy": 0.1775028884410858,
|
|
"num_tokens": 29978830.0,
|
|
"step": 15335
|
|
},
|
|
{
|
|
"entropy": 6.289929008483886,
|
|
"epoch": 1.5334133053431298,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000477120065643712,
|
|
"loss": 5.7117,
|
|
"mean_token_accuracy": 0.17756526917219162,
|
|
"num_tokens": 29987708.0,
|
|
"step": 15340
|
|
},
|
|
{
|
|
"entropy": 6.333661985397339,
|
|
"epoch": 1.5339131304043585,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004771043827612421,
|
|
"loss": 5.7444,
|
|
"mean_token_accuracy": 0.17541352808475494,
|
|
"num_tokens": 29997351.0,
|
|
"step": 15345
|
|
},
|
|
{
|
|
"entropy": 6.226978397369384,
|
|
"epoch": 1.5344129554655872,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00047708869479387795,
|
|
"loss": 5.7373,
|
|
"mean_token_accuracy": 0.18001431226730347,
|
|
"num_tokens": 30006412.0,
|
|
"step": 15350
|
|
},
|
|
{
|
|
"entropy": 6.25202202796936,
|
|
"epoch": 1.5349127805268155,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004770730017420143,
|
|
"loss": 5.689,
|
|
"mean_token_accuracy": 0.17341925203800201,
|
|
"num_tokens": 30016629.0,
|
|
"step": 15355
|
|
},
|
|
{
|
|
"entropy": 6.226939296722412,
|
|
"epoch": 1.5354126055880442,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004770573036060458,
|
|
"loss": 5.5997,
|
|
"mean_token_accuracy": 0.18654702752828597,
|
|
"num_tokens": 30026395.0,
|
|
"step": 15360
|
|
},
|
|
{
|
|
"entropy": 6.268282222747803,
|
|
"epoch": 1.5359124306492729,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004770416003863676,
|
|
"loss": 5.7763,
|
|
"mean_token_accuracy": 0.1705683246254921,
|
|
"num_tokens": 30037178.0,
|
|
"step": 15365
|
|
},
|
|
{
|
|
"entropy": 6.263752508163452,
|
|
"epoch": 1.5364122557105013,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004770258920833748,
|
|
"loss": 5.6492,
|
|
"mean_token_accuracy": 0.18249204605817795,
|
|
"num_tokens": 30046335.0,
|
|
"step": 15370
|
|
},
|
|
{
|
|
"entropy": 6.297060298919678,
|
|
"epoch": 1.5369120807717298,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00047701017869746236,
|
|
"loss": 5.7147,
|
|
"mean_token_accuracy": 0.17756885141134263,
|
|
"num_tokens": 30056574.0,
|
|
"step": 15375
|
|
},
|
|
{
|
|
"entropy": 6.184034967422486,
|
|
"epoch": 1.5374119058329585,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047699446022902596,
|
|
"loss": 5.6394,
|
|
"mean_token_accuracy": 0.18454264104366302,
|
|
"num_tokens": 30067048.0,
|
|
"step": 15380
|
|
},
|
|
{
|
|
"entropy": 6.186526346206665,
|
|
"epoch": 1.537911730894187,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047697873667846094,
|
|
"loss": 5.672,
|
|
"mean_token_accuracy": 0.1785300225019455,
|
|
"num_tokens": 30077177.0,
|
|
"step": 15385
|
|
},
|
|
{
|
|
"entropy": 6.320178747177124,
|
|
"epoch": 1.5384115559554155,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00047696300804616276,
|
|
"loss": 5.7833,
|
|
"mean_token_accuracy": 0.17442838549613954,
|
|
"num_tokens": 30086348.0,
|
|
"step": 15390
|
|
},
|
|
{
|
|
"entropy": 6.223853349685669,
|
|
"epoch": 1.5389113810166442,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004769472743325273,
|
|
"loss": 5.6188,
|
|
"mean_token_accuracy": 0.18745146840810775,
|
|
"num_tokens": 30096721.0,
|
|
"step": 15395
|
|
},
|
|
{
|
|
"entropy": 6.196120309829712,
|
|
"epoch": 1.5394112060778729,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047693153553795046,
|
|
"loss": 5.6426,
|
|
"mean_token_accuracy": 0.1842748388648033,
|
|
"num_tokens": 30106797.0,
|
|
"step": 15400
|
|
},
|
|
{
|
|
"entropy": 6.204634141921997,
|
|
"epoch": 1.5399110311391013,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004769157916628281,
|
|
"loss": 5.6758,
|
|
"mean_token_accuracy": 0.1802036553621292,
|
|
"num_tokens": 30116643.0,
|
|
"step": 15405
|
|
},
|
|
{
|
|
"entropy": 6.232893085479736,
|
|
"epoch": 1.5404108562003298,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047690004270755634,
|
|
"loss": 5.6486,
|
|
"mean_token_accuracy": 0.1883960783481598,
|
|
"num_tokens": 30125336.0,
|
|
"step": 15410
|
|
},
|
|
{
|
|
"entropy": 6.143060922622681,
|
|
"epoch": 1.5409106812615585,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004768842886725314,
|
|
"loss": 5.6763,
|
|
"mean_token_accuracy": 0.1851129487156868,
|
|
"num_tokens": 30135238.0,
|
|
"step": 15415
|
|
},
|
|
{
|
|
"entropy": 6.2773118019104,
|
|
"epoch": 1.541410506322787,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047686852955814986,
|
|
"loss": 5.7154,
|
|
"mean_token_accuracy": 0.17938656061887742,
|
|
"num_tokens": 30144469.0,
|
|
"step": 15420
|
|
},
|
|
{
|
|
"entropy": 6.254536294937134,
|
|
"epoch": 1.5419103313840155,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000476852765364808,
|
|
"loss": 5.718,
|
|
"mean_token_accuracy": 0.17852070331573486,
|
|
"num_tokens": 30154484.0,
|
|
"step": 15425
|
|
},
|
|
{
|
|
"entropy": 6.196579551696777,
|
|
"epoch": 1.5424101564452442,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004768369960929025,
|
|
"loss": 5.7057,
|
|
"mean_token_accuracy": 0.1822420910000801,
|
|
"num_tokens": 30163832.0,
|
|
"step": 15430
|
|
},
|
|
{
|
|
"entropy": 6.21150426864624,
|
|
"epoch": 1.5429099815064728,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004768212217428301,
|
|
"loss": 5.6401,
|
|
"mean_token_accuracy": 0.1809029459953308,
|
|
"num_tokens": 30173503.0,
|
|
"step": 15435
|
|
},
|
|
{
|
|
"entropy": 6.2821183681488035,
|
|
"epoch": 1.5434098065677013,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047680544231498766,
|
|
"loss": 5.7316,
|
|
"mean_token_accuracy": 0.18456377238035201,
|
|
"num_tokens": 30183476.0,
|
|
"step": 15440
|
|
},
|
|
{
|
|
"entropy": 6.247529602050781,
|
|
"epoch": 1.5439096316289298,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004767896578097723,
|
|
"loss": 5.7406,
|
|
"mean_token_accuracy": 0.18375616073608397,
|
|
"num_tokens": 30192552.0,
|
|
"step": 15445
|
|
},
|
|
{
|
|
"entropy": 6.277400398254395,
|
|
"epoch": 1.5444094566901585,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004767738682275811,
|
|
"loss": 5.784,
|
|
"mean_token_accuracy": 0.17536227256059647,
|
|
"num_tokens": 30202796.0,
|
|
"step": 15450
|
|
},
|
|
{
|
|
"entropy": 6.231901931762695,
|
|
"epoch": 1.544909281751387,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004767580735688112,
|
|
"loss": 5.6988,
|
|
"mean_token_accuracy": 0.18282005041837693,
|
|
"num_tokens": 30211878.0,
|
|
"step": 15455
|
|
},
|
|
{
|
|
"entropy": 6.256236886978149,
|
|
"epoch": 1.5454091068126155,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004767422738338601,
|
|
"loss": 5.7819,
|
|
"mean_token_accuracy": 0.16927876621484755,
|
|
"num_tokens": 30221572.0,
|
|
"step": 15460
|
|
},
|
|
{
|
|
"entropy": 6.27127857208252,
|
|
"epoch": 1.5459089318738441,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004767264690231253,
|
|
"loss": 5.688,
|
|
"mean_token_accuracy": 0.18030375838279725,
|
|
"num_tokens": 30230770.0,
|
|
"step": 15465
|
|
},
|
|
{
|
|
"entropy": 6.241928052902222,
|
|
"epoch": 1.5464087569350728,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004767106591370045,
|
|
"loss": 5.6372,
|
|
"mean_token_accuracy": 0.19048328697681427,
|
|
"num_tokens": 30241404.0,
|
|
"step": 15470
|
|
},
|
|
{
|
|
"entropy": 6.2550133228302,
|
|
"epoch": 1.5469085819963013,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047669484417589537,
|
|
"loss": 5.7565,
|
|
"mean_token_accuracy": 0.17867628186941148,
|
|
"num_tokens": 30251471.0,
|
|
"step": 15475
|
|
},
|
|
{
|
|
"entropy": 6.311341142654419,
|
|
"epoch": 1.5474084070575298,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00047667902414019585,
|
|
"loss": 5.7644,
|
|
"mean_token_accuracy": 0.17317678183317184,
|
|
"num_tokens": 30260962.0,
|
|
"step": 15480
|
|
},
|
|
{
|
|
"entropy": 6.321703910827637,
|
|
"epoch": 1.5479082321187585,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000476663199030304,
|
|
"loss": 5.7666,
|
|
"mean_token_accuracy": 0.1781412124633789,
|
|
"num_tokens": 30271959.0,
|
|
"step": 15485
|
|
},
|
|
{
|
|
"entropy": 6.209673881530762,
|
|
"epoch": 1.548408057179987,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047664736884661804,
|
|
"loss": 5.6516,
|
|
"mean_token_accuracy": 0.18466842621564866,
|
|
"num_tokens": 30281134.0,
|
|
"step": 15490
|
|
},
|
|
{
|
|
"entropy": 6.195499420166016,
|
|
"epoch": 1.5489078822412155,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047663153358953604,
|
|
"loss": 5.634,
|
|
"mean_token_accuracy": 0.18664761632680893,
|
|
"num_tokens": 30289989.0,
|
|
"step": 15495
|
|
},
|
|
{
|
|
"entropy": 6.2723838806152346,
|
|
"epoch": 1.5494077073024441,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004766156932594566,
|
|
"loss": 5.7359,
|
|
"mean_token_accuracy": 0.1753941774368286,
|
|
"num_tokens": 30300416.0,
|
|
"step": 15500
|
|
},
|
|
{
|
|
"entropy": 6.29197506904602,
|
|
"epoch": 1.5499075323636728,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00047659984785677824,
|
|
"loss": 5.6995,
|
|
"mean_token_accuracy": 0.182082836329937,
|
|
"num_tokens": 30310056.0,
|
|
"step": 15505
|
|
},
|
|
{
|
|
"entropy": 6.235292911529541,
|
|
"epoch": 1.5504073574249013,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047658399738189955,
|
|
"loss": 5.7335,
|
|
"mean_token_accuracy": 0.17585767656564713,
|
|
"num_tokens": 30319489.0,
|
|
"step": 15510
|
|
},
|
|
{
|
|
"entropy": 6.294917917251587,
|
|
"epoch": 1.5509071824861298,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047656814183521937,
|
|
"loss": 5.7897,
|
|
"mean_token_accuracy": 0.17822863161563873,
|
|
"num_tokens": 30328814.0,
|
|
"step": 15515
|
|
},
|
|
{
|
|
"entropy": 6.2495355129241945,
|
|
"epoch": 1.5514070075473585,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004765522812171366,
|
|
"loss": 5.6808,
|
|
"mean_token_accuracy": 0.18862601965665818,
|
|
"num_tokens": 30339219.0,
|
|
"step": 15520
|
|
},
|
|
{
|
|
"entropy": 6.155682516098023,
|
|
"epoch": 1.551906832608587,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00047653641552805023,
|
|
"loss": 5.6777,
|
|
"mean_token_accuracy": 0.18587038218975066,
|
|
"num_tokens": 30349553.0,
|
|
"step": 15525
|
|
},
|
|
{
|
|
"entropy": 6.246706104278564,
|
|
"epoch": 1.5524066576698154,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004765205447683595,
|
|
"loss": 5.7562,
|
|
"mean_token_accuracy": 0.16957818120718002,
|
|
"num_tokens": 30359782.0,
|
|
"step": 15530
|
|
},
|
|
{
|
|
"entropy": 6.275857162475586,
|
|
"epoch": 1.5529064827310441,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004765046689384638,
|
|
"loss": 5.693,
|
|
"mean_token_accuracy": 0.1833437815308571,
|
|
"num_tokens": 30369635.0,
|
|
"step": 15535
|
|
},
|
|
{
|
|
"entropy": 6.20795955657959,
|
|
"epoch": 1.5534063077922728,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004764887880387625,
|
|
"loss": 5.6359,
|
|
"mean_token_accuracy": 0.1871113508939743,
|
|
"num_tokens": 30379453.0,
|
|
"step": 15540
|
|
},
|
|
{
|
|
"entropy": 6.282252073287964,
|
|
"epoch": 1.5539061328535013,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00047647290206965506,
|
|
"loss": 5.6931,
|
|
"mean_token_accuracy": 0.18248275965452193,
|
|
"num_tokens": 30388989.0,
|
|
"step": 15545
|
|
},
|
|
{
|
|
"entropy": 6.288539981842041,
|
|
"epoch": 1.5544059579147298,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047645701103154125,
|
|
"loss": 5.7166,
|
|
"mean_token_accuracy": 0.18394965976476668,
|
|
"num_tokens": 30399401.0,
|
|
"step": 15550
|
|
},
|
|
{
|
|
"entropy": 6.311277580261231,
|
|
"epoch": 1.5549057829759585,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047644111492482094,
|
|
"loss": 5.7401,
|
|
"mean_token_accuracy": 0.17095987200737,
|
|
"num_tokens": 30409795.0,
|
|
"step": 15555
|
|
},
|
|
{
|
|
"entropy": 6.297830533981323,
|
|
"epoch": 1.555405608037187,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000476425213749894,
|
|
"loss": 5.7946,
|
|
"mean_token_accuracy": 0.17425591349601746,
|
|
"num_tokens": 30419243.0,
|
|
"step": 15560
|
|
},
|
|
{
|
|
"entropy": 6.296795988082886,
|
|
"epoch": 1.5559054330984154,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004764093075071605,
|
|
"loss": 5.7616,
|
|
"mean_token_accuracy": 0.17697412222623826,
|
|
"num_tokens": 30429278.0,
|
|
"step": 15565
|
|
},
|
|
{
|
|
"entropy": 6.228275775909424,
|
|
"epoch": 1.5564052581596441,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004763933961970206,
|
|
"loss": 5.7157,
|
|
"mean_token_accuracy": 0.18672619760036469,
|
|
"num_tokens": 30438442.0,
|
|
"step": 15570
|
|
},
|
|
{
|
|
"entropy": 6.240512943267822,
|
|
"epoch": 1.5569050832208728,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004763774798198748,
|
|
"loss": 5.6904,
|
|
"mean_token_accuracy": 0.17440212666988372,
|
|
"num_tokens": 30448779.0,
|
|
"step": 15575
|
|
},
|
|
{
|
|
"entropy": 6.2778112411499025,
|
|
"epoch": 1.5574049082821013,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004763615583761234,
|
|
"loss": 5.6754,
|
|
"mean_token_accuracy": 0.1815706104040146,
|
|
"num_tokens": 30458219.0,
|
|
"step": 15580
|
|
},
|
|
{
|
|
"entropy": 6.262195110321045,
|
|
"epoch": 1.5579047333433298,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004763456318661669,
|
|
"loss": 5.7283,
|
|
"mean_token_accuracy": 0.18053309321403505,
|
|
"num_tokens": 30467772.0,
|
|
"step": 15585
|
|
},
|
|
{
|
|
"entropy": 6.221865034103393,
|
|
"epoch": 1.5584045584045585,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004763297002904062,
|
|
"loss": 5.658,
|
|
"mean_token_accuracy": 0.18719948530197145,
|
|
"num_tokens": 30477025.0,
|
|
"step": 15590
|
|
},
|
|
{
|
|
"entropy": 6.308918285369873,
|
|
"epoch": 1.558904383465787,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047631376364924195,
|
|
"loss": 5.7552,
|
|
"mean_token_accuracy": 0.18313899785280227,
|
|
"num_tokens": 30486691.0,
|
|
"step": 15595
|
|
},
|
|
{
|
|
"entropy": 6.224018573760986,
|
|
"epoch": 1.5594042085270154,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004762978219430753,
|
|
"loss": 5.6653,
|
|
"mean_token_accuracy": 0.18383784592151642,
|
|
"num_tokens": 30497138.0,
|
|
"step": 15600
|
|
},
|
|
{
|
|
"entropy": 6.277801609039306,
|
|
"epoch": 1.5599040335882441,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004762818751723072,
|
|
"loss": 5.7965,
|
|
"mean_token_accuracy": 0.17256732881069184,
|
|
"num_tokens": 30507526.0,
|
|
"step": 15605
|
|
},
|
|
{
|
|
"entropy": 6.232067441940307,
|
|
"epoch": 1.5604038586494728,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047626592333733895,
|
|
"loss": 5.646,
|
|
"mean_token_accuracy": 0.18477025032043456,
|
|
"num_tokens": 30517823.0,
|
|
"step": 15610
|
|
},
|
|
{
|
|
"entropy": 6.218085384368896,
|
|
"epoch": 1.560903683710701,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004762499664385719,
|
|
"loss": 5.6801,
|
|
"mean_token_accuracy": 0.18616601526737214,
|
|
"num_tokens": 30527892.0,
|
|
"step": 15615
|
|
},
|
|
{
|
|
"entropy": 6.278189373016358,
|
|
"epoch": 1.5614035087719298,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047623400447640733,
|
|
"loss": 5.6951,
|
|
"mean_token_accuracy": 0.1903415083885193,
|
|
"num_tokens": 30537329.0,
|
|
"step": 15620
|
|
},
|
|
{
|
|
"entropy": 6.261933279037476,
|
|
"epoch": 1.5619033338331585,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047621803745124717,
|
|
"loss": 5.6918,
|
|
"mean_token_accuracy": 0.17873182892799377,
|
|
"num_tokens": 30546406.0,
|
|
"step": 15625
|
|
},
|
|
{
|
|
"entropy": 6.256925773620606,
|
|
"epoch": 1.562403158894387,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047620206536349294,
|
|
"loss": 5.7673,
|
|
"mean_token_accuracy": 0.1835520535707474,
|
|
"num_tokens": 30556646.0,
|
|
"step": 15630
|
|
},
|
|
{
|
|
"entropy": 6.197374582290649,
|
|
"epoch": 1.5629029839556154,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047618608821354636,
|
|
"loss": 5.6269,
|
|
"mean_token_accuracy": 0.1993168041110039,
|
|
"num_tokens": 30565984.0,
|
|
"step": 15635
|
|
},
|
|
{
|
|
"entropy": 6.254847717285156,
|
|
"epoch": 1.5634028090168441,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004761701060018097,
|
|
"loss": 5.7442,
|
|
"mean_token_accuracy": 0.17725103348493576,
|
|
"num_tokens": 30575257.0,
|
|
"step": 15640
|
|
},
|
|
{
|
|
"entropy": 6.24174132347107,
|
|
"epoch": 1.5639026340780728,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000476154118728685,
|
|
"loss": 5.698,
|
|
"mean_token_accuracy": 0.17722961604595183,
|
|
"num_tokens": 30584248.0,
|
|
"step": 15645
|
|
},
|
|
{
|
|
"entropy": 6.262402534484863,
|
|
"epoch": 1.564402459139301,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00047613812639457425,
|
|
"loss": 5.6568,
|
|
"mean_token_accuracy": 0.19191999435424806,
|
|
"num_tokens": 30593875.0,
|
|
"step": 15650
|
|
},
|
|
{
|
|
"entropy": 6.216759824752808,
|
|
"epoch": 1.5649022842005298,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004761221289998801,
|
|
"loss": 5.6091,
|
|
"mean_token_accuracy": 0.18796930611133575,
|
|
"num_tokens": 30603696.0,
|
|
"step": 15655
|
|
},
|
|
{
|
|
"entropy": 6.217262506484985,
|
|
"epoch": 1.5654021092617585,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004761061265450049,
|
|
"loss": 5.63,
|
|
"mean_token_accuracy": 0.18557002246379853,
|
|
"num_tokens": 30613451.0,
|
|
"step": 15660
|
|
},
|
|
{
|
|
"entropy": 6.256666421890259,
|
|
"epoch": 1.565901934322987,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047609011903035136,
|
|
"loss": 5.7491,
|
|
"mean_token_accuracy": 0.17490363419055938,
|
|
"num_tokens": 30623567.0,
|
|
"step": 15665
|
|
},
|
|
{
|
|
"entropy": 6.286512947082519,
|
|
"epoch": 1.5664017593842154,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00047607410645632216,
|
|
"loss": 5.6532,
|
|
"mean_token_accuracy": 0.1885724201798439,
|
|
"num_tokens": 30634828.0,
|
|
"step": 15670
|
|
},
|
|
{
|
|
"entropy": 6.352824926376343,
|
|
"epoch": 1.5669015844454441,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047605808882332013,
|
|
"loss": 5.8517,
|
|
"mean_token_accuracy": 0.17105073481798172,
|
|
"num_tokens": 30644552.0,
|
|
"step": 15675
|
|
},
|
|
{
|
|
"entropy": 6.316790962219239,
|
|
"epoch": 1.5674014095066726,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004760420661317484,
|
|
"loss": 5.8405,
|
|
"mean_token_accuracy": 0.17394140362739563,
|
|
"num_tokens": 30654874.0,
|
|
"step": 15680
|
|
},
|
|
{
|
|
"entropy": 6.301920652389526,
|
|
"epoch": 1.567901234567901,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004760260383820099,
|
|
"loss": 5.6952,
|
|
"mean_token_accuracy": 0.18169473111629486,
|
|
"num_tokens": 30665619.0,
|
|
"step": 15685
|
|
},
|
|
{
|
|
"entropy": 6.23515887260437,
|
|
"epoch": 1.5684010596291298,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047601000557450816,
|
|
"loss": 5.6858,
|
|
"mean_token_accuracy": 0.1818743273615837,
|
|
"num_tokens": 30675072.0,
|
|
"step": 15690
|
|
},
|
|
{
|
|
"entropy": 6.323769664764404,
|
|
"epoch": 1.5689008846903585,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004759939677096463,
|
|
"loss": 5.7965,
|
|
"mean_token_accuracy": 0.17124776691198348,
|
|
"num_tokens": 30684567.0,
|
|
"step": 15695
|
|
},
|
|
{
|
|
"entropy": 6.268719673156738,
|
|
"epoch": 1.569400709751587,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004759779247878279,
|
|
"loss": 5.6899,
|
|
"mean_token_accuracy": 0.18657400608062744,
|
|
"num_tokens": 30693808.0,
|
|
"step": 15700
|
|
},
|
|
{
|
|
"entropy": 6.148230504989624,
|
|
"epoch": 1.5699005348128154,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047596187680945675,
|
|
"loss": 5.6702,
|
|
"mean_token_accuracy": 0.18897647112607957,
|
|
"num_tokens": 30702895.0,
|
|
"step": 15705
|
|
},
|
|
{
|
|
"entropy": 6.286229038238526,
|
|
"epoch": 1.5704003598740441,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004759458237749364,
|
|
"loss": 5.799,
|
|
"mean_token_accuracy": 0.17594387680292128,
|
|
"num_tokens": 30714582.0,
|
|
"step": 15710
|
|
},
|
|
{
|
|
"entropy": 6.3413230895996096,
|
|
"epoch": 1.5709001849352726,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004759297656846708,
|
|
"loss": 5.7493,
|
|
"mean_token_accuracy": 0.1750856101512909,
|
|
"num_tokens": 30724415.0,
|
|
"step": 15715
|
|
},
|
|
{
|
|
"entropy": 6.251589345932007,
|
|
"epoch": 1.571400009996501,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047591370253906415,
|
|
"loss": 5.696,
|
|
"mean_token_accuracy": 0.18098368495702744,
|
|
"num_tokens": 30733040.0,
|
|
"step": 15720
|
|
},
|
|
{
|
|
"entropy": 6.178906440734863,
|
|
"epoch": 1.5718998350577298,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00047589763433852027,
|
|
"loss": 5.6734,
|
|
"mean_token_accuracy": 0.18315568715333938,
|
|
"num_tokens": 30743022.0,
|
|
"step": 15725
|
|
},
|
|
{
|
|
"entropy": 6.214314556121826,
|
|
"epoch": 1.5723996601189585,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004758815610834437,
|
|
"loss": 5.6709,
|
|
"mean_token_accuracy": 0.18373938500881196,
|
|
"num_tokens": 30753335.0,
|
|
"step": 15730
|
|
},
|
|
{
|
|
"entropy": 6.230402040481567,
|
|
"epoch": 1.572899485180187,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00047586548277423873,
|
|
"loss": 5.6959,
|
|
"mean_token_accuracy": 0.17993331104516982,
|
|
"num_tokens": 30762863.0,
|
|
"step": 15735
|
|
},
|
|
{
|
|
"entropy": 6.27605242729187,
|
|
"epoch": 1.5733993102414154,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047584939941130994,
|
|
"loss": 5.7524,
|
|
"mean_token_accuracy": 0.18213931173086167,
|
|
"num_tokens": 30773090.0,
|
|
"step": 15740
|
|
},
|
|
{
|
|
"entropy": 6.24851393699646,
|
|
"epoch": 1.5738991353026441,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004758333109950619,
|
|
"loss": 5.7571,
|
|
"mean_token_accuracy": 0.17888050079345702,
|
|
"num_tokens": 30782589.0,
|
|
"step": 15745
|
|
},
|
|
{
|
|
"entropy": 6.285316848754883,
|
|
"epoch": 1.5743989603638726,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047581721752589943,
|
|
"loss": 5.6547,
|
|
"mean_token_accuracy": 0.18296140134334565,
|
|
"num_tokens": 30791508.0,
|
|
"step": 15750
|
|
},
|
|
{
|
|
"entropy": 6.22731385231018,
|
|
"epoch": 1.574898785425101,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004758011190042274,
|
|
"loss": 5.6621,
|
|
"mean_token_accuracy": 0.1840491011738777,
|
|
"num_tokens": 30801133.0,
|
|
"step": 15755
|
|
},
|
|
{
|
|
"entropy": 6.226623296737671,
|
|
"epoch": 1.5753986104863298,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004757850154304509,
|
|
"loss": 5.5872,
|
|
"mean_token_accuracy": 0.18883244842290878,
|
|
"num_tokens": 30810100.0,
|
|
"step": 15760
|
|
},
|
|
{
|
|
"entropy": 6.192651891708374,
|
|
"epoch": 1.5758984355475585,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004757689068049752,
|
|
"loss": 5.6554,
|
|
"mean_token_accuracy": 0.19012159258127212,
|
|
"num_tokens": 30820118.0,
|
|
"step": 15765
|
|
},
|
|
{
|
|
"entropy": 6.258782052993775,
|
|
"epoch": 1.576398260608787,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047575279312820533,
|
|
"loss": 5.7134,
|
|
"mean_token_accuracy": 0.17487822324037552,
|
|
"num_tokens": 30830480.0,
|
|
"step": 15770
|
|
},
|
|
{
|
|
"entropy": 6.303906440734863,
|
|
"epoch": 1.5768980856700154,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004757366744005469,
|
|
"loss": 5.8436,
|
|
"mean_token_accuracy": 0.16671658605337142,
|
|
"num_tokens": 30840421.0,
|
|
"step": 15775
|
|
},
|
|
{
|
|
"entropy": 6.293060398101806,
|
|
"epoch": 1.5773979107312441,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00047572055062240537,
|
|
"loss": 5.7074,
|
|
"mean_token_accuracy": 0.1770254448056221,
|
|
"num_tokens": 30849247.0,
|
|
"step": 15780
|
|
},
|
|
{
|
|
"entropy": 6.267670917510986,
|
|
"epoch": 1.5778977357924726,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004757044217941865,
|
|
"loss": 5.7003,
|
|
"mean_token_accuracy": 0.18276656568050384,
|
|
"num_tokens": 30858804.0,
|
|
"step": 15785
|
|
},
|
|
{
|
|
"entropy": 6.2746659278869625,
|
|
"epoch": 1.578397560853701,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047568828791629605,
|
|
"loss": 5.6649,
|
|
"mean_token_accuracy": 0.18250425010919571,
|
|
"num_tokens": 30869150.0,
|
|
"step": 15790
|
|
},
|
|
{
|
|
"entropy": 6.164527225494385,
|
|
"epoch": 1.5788973859149298,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004756721489891398,
|
|
"loss": 5.6183,
|
|
"mean_token_accuracy": 0.19084577709436418,
|
|
"num_tokens": 30878671.0,
|
|
"step": 15795
|
|
},
|
|
{
|
|
"entropy": 6.298320865631103,
|
|
"epoch": 1.5793972109761585,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004756560050131239,
|
|
"loss": 5.7292,
|
|
"mean_token_accuracy": 0.18521663248538972,
|
|
"num_tokens": 30888064.0,
|
|
"step": 15800
|
|
},
|
|
{
|
|
"entropy": 6.300903463363648,
|
|
"epoch": 1.579897036037387,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047563985598865466,
|
|
"loss": 5.7736,
|
|
"mean_token_accuracy": 0.17741357088088988,
|
|
"num_tokens": 30898205.0,
|
|
"step": 15805
|
|
},
|
|
{
|
|
"entropy": 6.259327983856201,
|
|
"epoch": 1.5803968610986154,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047562370191613816,
|
|
"loss": 5.7445,
|
|
"mean_token_accuracy": 0.18190243244171142,
|
|
"num_tokens": 30907371.0,
|
|
"step": 15810
|
|
},
|
|
{
|
|
"entropy": 6.355114316940307,
|
|
"epoch": 1.5808966861598441,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004756075427959811,
|
|
"loss": 5.808,
|
|
"mean_token_accuracy": 0.1741660714149475,
|
|
"num_tokens": 30917481.0,
|
|
"step": 15815
|
|
},
|
|
{
|
|
"entropy": 6.2867701053619385,
|
|
"epoch": 1.5813965112210726,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004755913786285898,
|
|
"loss": 5.7667,
|
|
"mean_token_accuracy": 0.17645237892866134,
|
|
"num_tokens": 30927375.0,
|
|
"step": 15820
|
|
},
|
|
{
|
|
"entropy": 6.248933172225952,
|
|
"epoch": 1.581896336282301,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00047557520941437093,
|
|
"loss": 5.6827,
|
|
"mean_token_accuracy": 0.1812817081809044,
|
|
"num_tokens": 30935888.0,
|
|
"step": 15825
|
|
},
|
|
{
|
|
"entropy": 6.25911054611206,
|
|
"epoch": 1.5823961613435298,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047555903515373156,
|
|
"loss": 5.7138,
|
|
"mean_token_accuracy": 0.1905747503042221,
|
|
"num_tokens": 30946433.0,
|
|
"step": 15830
|
|
},
|
|
{
|
|
"entropy": 6.275790786743164,
|
|
"epoch": 1.5828959864047585,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00047554285584707834,
|
|
"loss": 5.7407,
|
|
"mean_token_accuracy": 0.17967026084661483,
|
|
"num_tokens": 30956951.0,
|
|
"step": 15835
|
|
},
|
|
{
|
|
"entropy": 6.179942464828491,
|
|
"epoch": 1.583395811465987,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004755266714948186,
|
|
"loss": 5.5956,
|
|
"mean_token_accuracy": 0.19184805005788802,
|
|
"num_tokens": 30967332.0,
|
|
"step": 15840
|
|
},
|
|
{
|
|
"entropy": 6.279737663269043,
|
|
"epoch": 1.5838956365272154,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004755104820973593,
|
|
"loss": 5.7788,
|
|
"mean_token_accuracy": 0.17669544219970704,
|
|
"num_tokens": 30977704.0,
|
|
"step": 15845
|
|
},
|
|
{
|
|
"entropy": 6.370969533920288,
|
|
"epoch": 1.5843954615884441,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00047549428765510793,
|
|
"loss": 5.8695,
|
|
"mean_token_accuracy": 0.16841506063938141,
|
|
"num_tokens": 30987916.0,
|
|
"step": 15850
|
|
},
|
|
{
|
|
"entropy": 6.235167074203491,
|
|
"epoch": 1.5848952866496726,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00047547808816847186,
|
|
"loss": 5.6401,
|
|
"mean_token_accuracy": 0.19121474176645278,
|
|
"num_tokens": 30997357.0,
|
|
"step": 15855
|
|
},
|
|
{
|
|
"entropy": 6.347006988525391,
|
|
"epoch": 1.585395111710901,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004754618836378587,
|
|
"loss": 5.7847,
|
|
"mean_token_accuracy": 0.17439056187868118,
|
|
"num_tokens": 31006113.0,
|
|
"step": 15860
|
|
},
|
|
{
|
|
"entropy": 6.269981765747071,
|
|
"epoch": 1.5858949367721298,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004754456740636761,
|
|
"loss": 5.6628,
|
|
"mean_token_accuracy": 0.18350521177053453,
|
|
"num_tokens": 31014952.0,
|
|
"step": 15865
|
|
},
|
|
{
|
|
"entropy": 6.3692199230194095,
|
|
"epoch": 1.5863947618333585,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00047542945944633187,
|
|
"loss": 5.7941,
|
|
"mean_token_accuracy": 0.16930631548166275,
|
|
"num_tokens": 31024934.0,
|
|
"step": 15870
|
|
},
|
|
{
|
|
"entropy": 6.255455017089844,
|
|
"epoch": 1.5868945868945867,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047541323978623405,
|
|
"loss": 5.6181,
|
|
"mean_token_accuracy": 0.18934710919857026,
|
|
"num_tokens": 31033934.0,
|
|
"step": 15875
|
|
},
|
|
{
|
|
"entropy": 6.263585186004638,
|
|
"epoch": 1.5873944119558154,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047539701508379073,
|
|
"loss": 5.7813,
|
|
"mean_token_accuracy": 0.18167778551578523,
|
|
"num_tokens": 31043896.0,
|
|
"step": 15880
|
|
},
|
|
{
|
|
"entropy": 6.222036504745484,
|
|
"epoch": 1.5878942370170441,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004753807853394101,
|
|
"loss": 5.7177,
|
|
"mean_token_accuracy": 0.18685174882411956,
|
|
"num_tokens": 31055103.0,
|
|
"step": 15885
|
|
},
|
|
{
|
|
"entropy": 6.320404481887818,
|
|
"epoch": 1.5883940620782726,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00047536455055350034,
|
|
"loss": 5.8001,
|
|
"mean_token_accuracy": 0.17541458159685136,
|
|
"num_tokens": 31065478.0,
|
|
"step": 15890
|
|
},
|
|
{
|
|
"entropy": 6.314428472518921,
|
|
"epoch": 1.588893887139501,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047534831072647016,
|
|
"loss": 5.7227,
|
|
"mean_token_accuracy": 0.1773834317922592,
|
|
"num_tokens": 31074408.0,
|
|
"step": 15895
|
|
},
|
|
{
|
|
"entropy": 6.283174800872803,
|
|
"epoch": 1.5893937122007298,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047533206585872805,
|
|
"loss": 5.7351,
|
|
"mean_token_accuracy": 0.17809061855077743,
|
|
"num_tokens": 31084223.0,
|
|
"step": 15900
|
|
},
|
|
{
|
|
"entropy": 6.175059366226196,
|
|
"epoch": 1.5898935372619585,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004753158159506827,
|
|
"loss": 5.6235,
|
|
"mean_token_accuracy": 0.19051660150289534,
|
|
"num_tokens": 31094133.0,
|
|
"step": 15905
|
|
},
|
|
{
|
|
"entropy": 6.257870721817016,
|
|
"epoch": 1.5903933623231867,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004752995610027429,
|
|
"loss": 5.7234,
|
|
"mean_token_accuracy": 0.18728581815958023,
|
|
"num_tokens": 31104283.0,
|
|
"step": 15910
|
|
},
|
|
{
|
|
"entropy": 6.277141761779785,
|
|
"epoch": 1.5908931873844154,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047528330101531777,
|
|
"loss": 5.7216,
|
|
"mean_token_accuracy": 0.1727937713265419,
|
|
"num_tokens": 31114274.0,
|
|
"step": 15915
|
|
},
|
|
{
|
|
"entropy": 6.287484645843506,
|
|
"epoch": 1.5913930124456441,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047526703598881623,
|
|
"loss": 5.7308,
|
|
"mean_token_accuracy": 0.17890642136335372,
|
|
"num_tokens": 31123680.0,
|
|
"step": 15920
|
|
},
|
|
{
|
|
"entropy": 6.220418214797974,
|
|
"epoch": 1.5918928375068726,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004752507659236476,
|
|
"loss": 5.6718,
|
|
"mean_token_accuracy": 0.18747132420539855,
|
|
"num_tokens": 31133520.0,
|
|
"step": 15925
|
|
},
|
|
{
|
|
"entropy": 6.191977405548096,
|
|
"epoch": 1.592392662568101,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004752344908202213,
|
|
"loss": 5.5948,
|
|
"mean_token_accuracy": 0.19603318870067596,
|
|
"num_tokens": 31142915.0,
|
|
"step": 15930
|
|
},
|
|
{
|
|
"entropy": 6.213077974319458,
|
|
"epoch": 1.5928924876293298,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004752182106789467,
|
|
"loss": 5.6469,
|
|
"mean_token_accuracy": 0.18407997488975525,
|
|
"num_tokens": 31152133.0,
|
|
"step": 15935
|
|
},
|
|
{
|
|
"entropy": 6.174561214447022,
|
|
"epoch": 1.5933923126905583,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047520192550023344,
|
|
"loss": 5.661,
|
|
"mean_token_accuracy": 0.18843680918216704,
|
|
"num_tokens": 31161666.0,
|
|
"step": 15940
|
|
},
|
|
{
|
|
"entropy": 6.189583206176758,
|
|
"epoch": 1.5938921377517867,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004751856352844913,
|
|
"loss": 5.6505,
|
|
"mean_token_accuracy": 0.1860222488641739,
|
|
"num_tokens": 31171591.0,
|
|
"step": 15945
|
|
},
|
|
{
|
|
"entropy": 6.332528018951416,
|
|
"epoch": 1.5943919628130154,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047516934003213,
|
|
"loss": 5.7897,
|
|
"mean_token_accuracy": 0.17788569778203964,
|
|
"num_tokens": 31181396.0,
|
|
"step": 15950
|
|
},
|
|
{
|
|
"entropy": 6.324274682998658,
|
|
"epoch": 1.5948917878742441,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047515303974355965,
|
|
"loss": 5.7411,
|
|
"mean_token_accuracy": 0.1799906611442566,
|
|
"num_tokens": 31191926.0,
|
|
"step": 15955
|
|
},
|
|
{
|
|
"entropy": 6.256118249893189,
|
|
"epoch": 1.5953916129354726,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047513673441919036,
|
|
"loss": 5.6716,
|
|
"mean_token_accuracy": 0.1829965278506279,
|
|
"num_tokens": 31202809.0,
|
|
"step": 15960
|
|
},
|
|
{
|
|
"entropy": 6.3104043960571286,
|
|
"epoch": 1.595891437996701,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004751204240594323,
|
|
"loss": 5.7003,
|
|
"mean_token_accuracy": 0.17571109533309937,
|
|
"num_tokens": 31211763.0,
|
|
"step": 15965
|
|
},
|
|
{
|
|
"entropy": 6.26321587562561,
|
|
"epoch": 1.5963912630579298,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004751041086646959,
|
|
"loss": 5.731,
|
|
"mean_token_accuracy": 0.17460990846157073,
|
|
"num_tokens": 31220881.0,
|
|
"step": 15970
|
|
},
|
|
{
|
|
"entropy": 6.224517107009888,
|
|
"epoch": 1.5968910881191583,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004750877882353915,
|
|
"loss": 5.6735,
|
|
"mean_token_accuracy": 0.18148336708545684,
|
|
"num_tokens": 31230740.0,
|
|
"step": 15975
|
|
},
|
|
{
|
|
"entropy": 6.217324924468994,
|
|
"epoch": 1.5973909131803867,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047507146277192997,
|
|
"loss": 5.5505,
|
|
"mean_token_accuracy": 0.19241280108690262,
|
|
"num_tokens": 31239777.0,
|
|
"step": 15980
|
|
},
|
|
{
|
|
"entropy": 6.2491021156311035,
|
|
"epoch": 1.5978907382416154,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004750551322747219,
|
|
"loss": 5.7139,
|
|
"mean_token_accuracy": 0.17616070806980133,
|
|
"num_tokens": 31248574.0,
|
|
"step": 15985
|
|
},
|
|
{
|
|
"entropy": 6.274359035491943,
|
|
"epoch": 1.5983905633028441,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004750387967441781,
|
|
"loss": 5.7495,
|
|
"mean_token_accuracy": 0.18263656347990037,
|
|
"num_tokens": 31258888.0,
|
|
"step": 15990
|
|
},
|
|
{
|
|
"entropy": 6.215943241119385,
|
|
"epoch": 1.5988903883640726,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047502245618070976,
|
|
"loss": 5.6529,
|
|
"mean_token_accuracy": 0.1872795432806015,
|
|
"num_tokens": 31269966.0,
|
|
"step": 15995
|
|
},
|
|
{
|
|
"entropy": 6.263910388946533,
|
|
"epoch": 1.599390213425301,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00047500611058472783,
|
|
"loss": 5.6976,
|
|
"mean_token_accuracy": 0.18193258941173554,
|
|
"num_tokens": 31279746.0,
|
|
"step": 16000
|
|
},
|
|
{
|
|
"entropy": 6.243450021743774,
|
|
"epoch": 1.5998900384865298,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047498975995664356,
|
|
"loss": 5.7375,
|
|
"mean_token_accuracy": 0.1778871089220047,
|
|
"num_tokens": 31289677.0,
|
|
"step": 16005
|
|
},
|
|
{
|
|
"entropy": 6.220459890365601,
|
|
"epoch": 1.6003898635477583,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004749734042968685,
|
|
"loss": 5.6673,
|
|
"mean_token_accuracy": 0.18671673834323882,
|
|
"num_tokens": 31299752.0,
|
|
"step": 16010
|
|
},
|
|
{
|
|
"entropy": 6.198047924041748,
|
|
"epoch": 1.6008896886089867,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000474957043605814,
|
|
"loss": 5.6497,
|
|
"mean_token_accuracy": 0.1888210281729698,
|
|
"num_tokens": 31308986.0,
|
|
"step": 16015
|
|
},
|
|
{
|
|
"entropy": 6.1774664402008055,
|
|
"epoch": 1.6013895136702154,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047494067788389174,
|
|
"loss": 5.6272,
|
|
"mean_token_accuracy": 0.19199795126914979,
|
|
"num_tokens": 31318848.0,
|
|
"step": 16020
|
|
},
|
|
{
|
|
"entropy": 6.272104501724243,
|
|
"epoch": 1.6018893387314441,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047492430713151347,
|
|
"loss": 5.771,
|
|
"mean_token_accuracy": 0.17472707629203796,
|
|
"num_tokens": 31329397.0,
|
|
"step": 16025
|
|
},
|
|
{
|
|
"entropy": 6.343345499038696,
|
|
"epoch": 1.6023891637926726,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004749079313490911,
|
|
"loss": 5.7873,
|
|
"mean_token_accuracy": 0.17500609606504441,
|
|
"num_tokens": 31340440.0,
|
|
"step": 16030
|
|
},
|
|
{
|
|
"entropy": 6.3016424655914305,
|
|
"epoch": 1.602888988853901,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00047489155053703655,
|
|
"loss": 5.7382,
|
|
"mean_token_accuracy": 0.18590079247951508,
|
|
"num_tokens": 31350418.0,
|
|
"step": 16035
|
|
},
|
|
{
|
|
"entropy": 6.266588401794434,
|
|
"epoch": 1.6033888139151298,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004748751646957621,
|
|
"loss": 5.7008,
|
|
"mean_token_accuracy": 0.18021347671747207,
|
|
"num_tokens": 31360714.0,
|
|
"step": 16040
|
|
},
|
|
{
|
|
"entropy": 6.299381303787231,
|
|
"epoch": 1.6038886389763582,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004748587738256799,
|
|
"loss": 5.72,
|
|
"mean_token_accuracy": 0.18213405460119247,
|
|
"num_tokens": 31369693.0,
|
|
"step": 16045
|
|
},
|
|
{
|
|
"entropy": 6.227974987030029,
|
|
"epoch": 1.6043884640375867,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004748423779272024,
|
|
"loss": 5.6686,
|
|
"mean_token_accuracy": 0.1801181346178055,
|
|
"num_tokens": 31380068.0,
|
|
"step": 16050
|
|
},
|
|
{
|
|
"entropy": 6.277038145065307,
|
|
"epoch": 1.6048882890988154,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047482597700074204,
|
|
"loss": 5.7533,
|
|
"mean_token_accuracy": 0.1811613231897354,
|
|
"num_tokens": 31389151.0,
|
|
"step": 16055
|
|
},
|
|
{
|
|
"entropy": 6.362710666656494,
|
|
"epoch": 1.6053881141600441,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047480957104671157,
|
|
"loss": 5.8693,
|
|
"mean_token_accuracy": 0.16936947107315065,
|
|
"num_tokens": 31400260.0,
|
|
"step": 16060
|
|
},
|
|
{
|
|
"entropy": 6.345929527282715,
|
|
"epoch": 1.6058879392212726,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004747931600655237,
|
|
"loss": 5.7351,
|
|
"mean_token_accuracy": 0.17922717779874803,
|
|
"num_tokens": 31410747.0,
|
|
"step": 16065
|
|
},
|
|
{
|
|
"entropy": 6.249888896942139,
|
|
"epoch": 1.606387764282501,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047477674405759136,
|
|
"loss": 5.7019,
|
|
"mean_token_accuracy": 0.1847398966550827,
|
|
"num_tokens": 31419230.0,
|
|
"step": 16070
|
|
},
|
|
{
|
|
"entropy": 6.241050767898559,
|
|
"epoch": 1.6068875893437298,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004747603230233275,
|
|
"loss": 5.7012,
|
|
"mean_token_accuracy": 0.18039611279964446,
|
|
"num_tokens": 31428314.0,
|
|
"step": 16075
|
|
},
|
|
{
|
|
"entropy": 6.172709989547729,
|
|
"epoch": 1.6073874144049582,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004747438969631453,
|
|
"loss": 5.6409,
|
|
"mean_token_accuracy": 0.18369593769311904,
|
|
"num_tokens": 31438141.0,
|
|
"step": 16080
|
|
},
|
|
{
|
|
"entropy": 6.237808895111084,
|
|
"epoch": 1.6078872394661867,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004747274658774581,
|
|
"loss": 5.6919,
|
|
"mean_token_accuracy": 0.1850784331560135,
|
|
"num_tokens": 31448609.0,
|
|
"step": 16085
|
|
},
|
|
{
|
|
"entropy": 6.285237073898315,
|
|
"epoch": 1.6083870645274154,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004747110297666793,
|
|
"loss": 5.7259,
|
|
"mean_token_accuracy": 0.18168442100286483,
|
|
"num_tokens": 31458603.0,
|
|
"step": 16090
|
|
},
|
|
{
|
|
"entropy": 6.23139500617981,
|
|
"epoch": 1.6088868895886441,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004746945886312223,
|
|
"loss": 5.5876,
|
|
"mean_token_accuracy": 0.1929546296596527,
|
|
"num_tokens": 31468917.0,
|
|
"step": 16095
|
|
},
|
|
{
|
|
"entropy": 6.236914443969726,
|
|
"epoch": 1.6093867146498726,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004746781424715009,
|
|
"loss": 5.7272,
|
|
"mean_token_accuracy": 0.1819476991891861,
|
|
"num_tokens": 31479061.0,
|
|
"step": 16100
|
|
},
|
|
{
|
|
"entropy": 6.301484775543213,
|
|
"epoch": 1.609886539711101,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047466169128792873,
|
|
"loss": 5.7912,
|
|
"mean_token_accuracy": 0.17149759083986282,
|
|
"num_tokens": 31488723.0,
|
|
"step": 16105
|
|
},
|
|
{
|
|
"entropy": 6.252268362045288,
|
|
"epoch": 1.6103863647723298,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004746452350809198,
|
|
"loss": 5.7411,
|
|
"mean_token_accuracy": 0.1779377654194832,
|
|
"num_tokens": 31497715.0,
|
|
"step": 16110
|
|
},
|
|
{
|
|
"entropy": 6.238306856155395,
|
|
"epoch": 1.6108861898335582,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047462877385088815,
|
|
"loss": 5.6882,
|
|
"mean_token_accuracy": 0.18096634447574617,
|
|
"num_tokens": 31507571.0,
|
|
"step": 16115
|
|
},
|
|
{
|
|
"entropy": 6.233126640319824,
|
|
"epoch": 1.6113860148947867,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00047461230759824794,
|
|
"loss": 5.7197,
|
|
"mean_token_accuracy": 0.18095490634441375,
|
|
"num_tokens": 31517582.0,
|
|
"step": 16120
|
|
},
|
|
{
|
|
"entropy": 6.325787925720215,
|
|
"epoch": 1.6118858399560154,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047459583632341343,
|
|
"loss": 5.7478,
|
|
"mean_token_accuracy": 0.18191785514354705,
|
|
"num_tokens": 31528225.0,
|
|
"step": 16125
|
|
},
|
|
{
|
|
"entropy": 6.2371725082397464,
|
|
"epoch": 1.6123856650172441,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047457936002679905,
|
|
"loss": 5.594,
|
|
"mean_token_accuracy": 0.19104175567626952,
|
|
"num_tokens": 31537778.0,
|
|
"step": 16130
|
|
},
|
|
{
|
|
"entropy": 6.204107570648193,
|
|
"epoch": 1.6128854900784724,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00047456287870881924,
|
|
"loss": 5.6531,
|
|
"mean_token_accuracy": 0.18928277045488356,
|
|
"num_tokens": 31548431.0,
|
|
"step": 16135
|
|
},
|
|
{
|
|
"entropy": 6.232661294937134,
|
|
"epoch": 1.613385315139701,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004745463923698888,
|
|
"loss": 5.6478,
|
|
"mean_token_accuracy": 0.1870620995759964,
|
|
"num_tokens": 31557333.0,
|
|
"step": 16140
|
|
},
|
|
{
|
|
"entropy": 6.2167332649230955,
|
|
"epoch": 1.6138851402009298,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004745299010104226,
|
|
"loss": 5.6687,
|
|
"mean_token_accuracy": 0.18002031594514847,
|
|
"num_tokens": 31566333.0,
|
|
"step": 16145
|
|
},
|
|
{
|
|
"entropy": 6.143579578399658,
|
|
"epoch": 1.6143849652621582,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047451340463083527,
|
|
"loss": 5.6033,
|
|
"mean_token_accuracy": 0.19851152151823043,
|
|
"num_tokens": 31575971.0,
|
|
"step": 16150
|
|
},
|
|
{
|
|
"entropy": 6.2184137344360355,
|
|
"epoch": 1.6148847903233867,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00047449690323154206,
|
|
"loss": 5.5962,
|
|
"mean_token_accuracy": 0.2030606374144554,
|
|
"num_tokens": 31585396.0,
|
|
"step": 16155
|
|
},
|
|
{
|
|
"entropy": 6.2637608528137205,
|
|
"epoch": 1.6153846153846154,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047448039681295814,
|
|
"loss": 5.7505,
|
|
"mean_token_accuracy": 0.17251552492380143,
|
|
"num_tokens": 31595800.0,
|
|
"step": 16160
|
|
},
|
|
{
|
|
"entropy": 6.231928443908691,
|
|
"epoch": 1.6158844404458441,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00047446388537549867,
|
|
"loss": 5.7738,
|
|
"mean_token_accuracy": 0.1726772204041481,
|
|
"num_tokens": 31604792.0,
|
|
"step": 16165
|
|
},
|
|
{
|
|
"entropy": 6.308490180969239,
|
|
"epoch": 1.6163842655070724,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004744473689195793,
|
|
"loss": 5.737,
|
|
"mean_token_accuracy": 0.17246246933937073,
|
|
"num_tokens": 31614952.0,
|
|
"step": 16170
|
|
},
|
|
{
|
|
"entropy": 6.195409059524536,
|
|
"epoch": 1.616884090568301,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004744308474456154,
|
|
"loss": 5.6027,
|
|
"mean_token_accuracy": 0.19911020547151564,
|
|
"num_tokens": 31624635.0,
|
|
"step": 16175
|
|
},
|
|
{
|
|
"entropy": 6.191937494277954,
|
|
"epoch": 1.6173839156295298,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004744143209540227,
|
|
"loss": 5.663,
|
|
"mean_token_accuracy": 0.1871604725718498,
|
|
"num_tokens": 31634710.0,
|
|
"step": 16180
|
|
},
|
|
{
|
|
"entropy": 6.406743144989013,
|
|
"epoch": 1.6178837406907582,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004743977894452169,
|
|
"loss": 5.8143,
|
|
"mean_token_accuracy": 0.17300723493099213,
|
|
"num_tokens": 31644371.0,
|
|
"step": 16185
|
|
},
|
|
{
|
|
"entropy": 6.273921823501587,
|
|
"epoch": 1.6183835657519867,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004743812529196142,
|
|
"loss": 5.698,
|
|
"mean_token_accuracy": 0.182975435256958,
|
|
"num_tokens": 31654262.0,
|
|
"step": 16190
|
|
},
|
|
{
|
|
"entropy": 6.28781213760376,
|
|
"epoch": 1.6188833908132154,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004743647113776304,
|
|
"loss": 5.7675,
|
|
"mean_token_accuracy": 0.1730612426996231,
|
|
"num_tokens": 31663209.0,
|
|
"step": 16195
|
|
},
|
|
{
|
|
"entropy": 6.189882707595825,
|
|
"epoch": 1.619383215874444,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047434816481968175,
|
|
"loss": 5.7072,
|
|
"mean_token_accuracy": 0.1770116537809372,
|
|
"num_tokens": 31672370.0,
|
|
"step": 16200
|
|
},
|
|
{
|
|
"entropy": 6.264673280715942,
|
|
"epoch": 1.6198830409356724,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047433161324618456,
|
|
"loss": 5.7312,
|
|
"mean_token_accuracy": 0.18192571252584458,
|
|
"num_tokens": 31681886.0,
|
|
"step": 16205
|
|
},
|
|
{
|
|
"entropy": 6.285514259338379,
|
|
"epoch": 1.620382865996901,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004743150566575553,
|
|
"loss": 5.6843,
|
|
"mean_token_accuracy": 0.1885819911956787,
|
|
"num_tokens": 31691098.0,
|
|
"step": 16210
|
|
},
|
|
{
|
|
"entropy": 6.226838684082031,
|
|
"epoch": 1.6208826910581298,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004742984950542105,
|
|
"loss": 5.6509,
|
|
"mean_token_accuracy": 0.18235402405261994,
|
|
"num_tokens": 31700638.0,
|
|
"step": 16215
|
|
},
|
|
{
|
|
"entropy": 6.241306209564209,
|
|
"epoch": 1.6213825161193582,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00047428192843656684,
|
|
"loss": 5.7151,
|
|
"mean_token_accuracy": 0.18054245561361312,
|
|
"num_tokens": 31711326.0,
|
|
"step": 16220
|
|
},
|
|
{
|
|
"entropy": 6.255591917037964,
|
|
"epoch": 1.6218823411805867,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00047426535680504105,
|
|
"loss": 5.661,
|
|
"mean_token_accuracy": 0.18916254937648774,
|
|
"num_tokens": 31721220.0,
|
|
"step": 16225
|
|
},
|
|
{
|
|
"entropy": 6.254164505004883,
|
|
"epoch": 1.6223821662418154,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047424878016005036,
|
|
"loss": 5.7117,
|
|
"mean_token_accuracy": 0.18118501156568528,
|
|
"num_tokens": 31731190.0,
|
|
"step": 16230
|
|
},
|
|
{
|
|
"entropy": 6.339414644241333,
|
|
"epoch": 1.622881991303044,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004742321985020115,
|
|
"loss": 5.7324,
|
|
"mean_token_accuracy": 0.18600254207849504,
|
|
"num_tokens": 31740761.0,
|
|
"step": 16235
|
|
},
|
|
{
|
|
"entropy": 6.269197750091553,
|
|
"epoch": 1.6233818163642724,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004742156118313418,
|
|
"loss": 5.7312,
|
|
"mean_token_accuracy": 0.1840945824980736,
|
|
"num_tokens": 31750038.0,
|
|
"step": 16240
|
|
},
|
|
{
|
|
"entropy": 6.27452654838562,
|
|
"epoch": 1.623881641425501,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00047419902014845855,
|
|
"loss": 5.6705,
|
|
"mean_token_accuracy": 0.18643890768289567,
|
|
"num_tokens": 31761574.0,
|
|
"step": 16245
|
|
},
|
|
{
|
|
"entropy": 6.277727270126343,
|
|
"epoch": 1.6243814664867298,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004741824234537793,
|
|
"loss": 5.721,
|
|
"mean_token_accuracy": 0.17776667177677155,
|
|
"num_tokens": 31771980.0,
|
|
"step": 16250
|
|
},
|
|
{
|
|
"entropy": 6.228938198089599,
|
|
"epoch": 1.6248812915479582,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047416582174772143,
|
|
"loss": 5.6534,
|
|
"mean_token_accuracy": 0.18792832195758818,
|
|
"num_tokens": 31781242.0,
|
|
"step": 16255
|
|
},
|
|
{
|
|
"entropy": 6.363392162322998,
|
|
"epoch": 1.6253811166091867,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047414921503070276,
|
|
"loss": 5.765,
|
|
"mean_token_accuracy": 0.1820707768201828,
|
|
"num_tokens": 31792250.0,
|
|
"step": 16260
|
|
},
|
|
{
|
|
"entropy": 6.2381385326385494,
|
|
"epoch": 1.6258809416704154,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047413260330314116,
|
|
"loss": 5.6468,
|
|
"mean_token_accuracy": 0.18365052044391633,
|
|
"num_tokens": 31802512.0,
|
|
"step": 16265
|
|
},
|
|
{
|
|
"entropy": 6.205749797821045,
|
|
"epoch": 1.626380766731644,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004741159865654544,
|
|
"loss": 5.6146,
|
|
"mean_token_accuracy": 0.19138796031475067,
|
|
"num_tokens": 31811957.0,
|
|
"step": 16270
|
|
},
|
|
{
|
|
"entropy": 6.26729154586792,
|
|
"epoch": 1.6268805917928724,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047409936481806076,
|
|
"loss": 5.6823,
|
|
"mean_token_accuracy": 0.1921049103140831,
|
|
"num_tokens": 31821101.0,
|
|
"step": 16275
|
|
},
|
|
{
|
|
"entropy": 6.258500671386718,
|
|
"epoch": 1.627380416854101,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004740827380613782,
|
|
"loss": 5.5855,
|
|
"mean_token_accuracy": 0.18763114511966705,
|
|
"num_tokens": 31831085.0,
|
|
"step": 16280
|
|
},
|
|
{
|
|
"entropy": 6.216111421585083,
|
|
"epoch": 1.6278802419153298,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047406610629582526,
|
|
"loss": 5.729,
|
|
"mean_token_accuracy": 0.17692421972751618,
|
|
"num_tokens": 31840354.0,
|
|
"step": 16285
|
|
},
|
|
{
|
|
"entropy": 6.229984092712402,
|
|
"epoch": 1.6283800669765582,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00047404946952182034,
|
|
"loss": 5.6793,
|
|
"mean_token_accuracy": 0.1836089164018631,
|
|
"num_tokens": 31849250.0,
|
|
"step": 16290
|
|
},
|
|
{
|
|
"entropy": 6.3105110168457035,
|
|
"epoch": 1.6288798920377867,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004740328277397819,
|
|
"loss": 5.7311,
|
|
"mean_token_accuracy": 0.17855875343084335,
|
|
"num_tokens": 31859533.0,
|
|
"step": 16295
|
|
},
|
|
{
|
|
"entropy": 6.333483123779297,
|
|
"epoch": 1.6293797170990154,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004740161809501288,
|
|
"loss": 5.7746,
|
|
"mean_token_accuracy": 0.17692707777023314,
|
|
"num_tokens": 31868821.0,
|
|
"step": 16300
|
|
},
|
|
{
|
|
"entropy": 6.27053599357605,
|
|
"epoch": 1.6298795421602439,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00047399952915327975,
|
|
"loss": 5.7207,
|
|
"mean_token_accuracy": 0.17059052586555482,
|
|
"num_tokens": 31878084.0,
|
|
"step": 16305
|
|
},
|
|
{
|
|
"entropy": 6.272861480712891,
|
|
"epoch": 1.6303793672214724,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004739828723496538,
|
|
"loss": 5.6697,
|
|
"mean_token_accuracy": 0.1841153845191002,
|
|
"num_tokens": 31887634.0,
|
|
"step": 16310
|
|
},
|
|
{
|
|
"entropy": 6.230046176910401,
|
|
"epoch": 1.630879192282701,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047396621053967,
|
|
"loss": 5.6581,
|
|
"mean_token_accuracy": 0.18600920587778091,
|
|
"num_tokens": 31897871.0,
|
|
"step": 16315
|
|
},
|
|
{
|
|
"entropy": 6.27843976020813,
|
|
"epoch": 1.6313790173439298,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047394954372374743,
|
|
"loss": 5.7374,
|
|
"mean_token_accuracy": 0.18155126571655272,
|
|
"num_tokens": 31907960.0,
|
|
"step": 16320
|
|
},
|
|
{
|
|
"entropy": 6.258498239517212,
|
|
"epoch": 1.6318788424051582,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00047393287190230566,
|
|
"loss": 5.6929,
|
|
"mean_token_accuracy": 0.17756998240947724,
|
|
"num_tokens": 31918550.0,
|
|
"step": 16325
|
|
},
|
|
{
|
|
"entropy": 6.311553573608398,
|
|
"epoch": 1.6323786674663867,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004739161950757639,
|
|
"loss": 5.7666,
|
|
"mean_token_accuracy": 0.18040726482868194,
|
|
"num_tokens": 31927941.0,
|
|
"step": 16330
|
|
},
|
|
{
|
|
"entropy": 6.338873958587646,
|
|
"epoch": 1.6328784925276154,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000473899513244542,
|
|
"loss": 5.7699,
|
|
"mean_token_accuracy": 0.17777851819992066,
|
|
"num_tokens": 31938179.0,
|
|
"step": 16335
|
|
},
|
|
{
|
|
"entropy": 6.256214141845703,
|
|
"epoch": 1.6333783175888439,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004738828264090594,
|
|
"loss": 5.6218,
|
|
"mean_token_accuracy": 0.18889059126377106,
|
|
"num_tokens": 31947287.0,
|
|
"step": 16340
|
|
},
|
|
{
|
|
"entropy": 6.1830634593963625,
|
|
"epoch": 1.6338781426500724,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047386613456973614,
|
|
"loss": 5.6501,
|
|
"mean_token_accuracy": 0.18416523188352585,
|
|
"num_tokens": 31955953.0,
|
|
"step": 16345
|
|
},
|
|
{
|
|
"entropy": 6.203140306472778,
|
|
"epoch": 1.634377967711301,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004738494377269921,
|
|
"loss": 5.6975,
|
|
"mean_token_accuracy": 0.17849279344081878,
|
|
"num_tokens": 31964874.0,
|
|
"step": 16350
|
|
},
|
|
{
|
|
"entropy": 6.253929138183594,
|
|
"epoch": 1.6348777927725298,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047383273588124736,
|
|
"loss": 5.7709,
|
|
"mean_token_accuracy": 0.17547807097434998,
|
|
"num_tokens": 31975865.0,
|
|
"step": 16355
|
|
},
|
|
{
|
|
"entropy": 6.285162782669067,
|
|
"epoch": 1.6353776178337582,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004738160290329222,
|
|
"loss": 5.6567,
|
|
"mean_token_accuracy": 0.18262240588665007,
|
|
"num_tokens": 31985229.0,
|
|
"step": 16360
|
|
},
|
|
{
|
|
"entropy": 6.232009315490723,
|
|
"epoch": 1.6358774428949867,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047379931718243684,
|
|
"loss": 5.7482,
|
|
"mean_token_accuracy": 0.1853403627872467,
|
|
"num_tokens": 31995195.0,
|
|
"step": 16365
|
|
},
|
|
{
|
|
"entropy": 6.259085655212402,
|
|
"epoch": 1.6363772679562154,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004737826003302118,
|
|
"loss": 5.712,
|
|
"mean_token_accuracy": 0.18391203582286836,
|
|
"num_tokens": 32006053.0,
|
|
"step": 16370
|
|
},
|
|
{
|
|
"entropy": 6.365154218673706,
|
|
"epoch": 1.6368770930174439,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00047376587847666767,
|
|
"loss": 5.7834,
|
|
"mean_token_accuracy": 0.17620052248239518,
|
|
"num_tokens": 32015025.0,
|
|
"step": 16375
|
|
},
|
|
{
|
|
"entropy": 6.188209199905396,
|
|
"epoch": 1.6373769180786724,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004737491516222253,
|
|
"loss": 5.6389,
|
|
"mean_token_accuracy": 0.18282725065946578,
|
|
"num_tokens": 32025116.0,
|
|
"step": 16380
|
|
},
|
|
{
|
|
"entropy": 6.19824743270874,
|
|
"epoch": 1.637876743139901,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047373241976730537,
|
|
"loss": 5.6646,
|
|
"mean_token_accuracy": 0.1854210689663887,
|
|
"num_tokens": 32034271.0,
|
|
"step": 16385
|
|
},
|
|
{
|
|
"entropy": 6.238119983673096,
|
|
"epoch": 1.6383765682011298,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004737156829123289,
|
|
"loss": 5.5951,
|
|
"mean_token_accuracy": 0.19987418502569199,
|
|
"num_tokens": 32043139.0,
|
|
"step": 16390
|
|
},
|
|
{
|
|
"entropy": 6.21785340309143,
|
|
"epoch": 1.638876393262358,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047369894105771693,
|
|
"loss": 5.6317,
|
|
"mean_token_accuracy": 0.1876357913017273,
|
|
"num_tokens": 32052719.0,
|
|
"step": 16395
|
|
},
|
|
{
|
|
"entropy": 6.287605476379395,
|
|
"epoch": 1.6393762183235867,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00047368219420389077,
|
|
"loss": 5.6873,
|
|
"mean_token_accuracy": 0.18046283423900605,
|
|
"num_tokens": 32062430.0,
|
|
"step": 16400
|
|
},
|
|
{
|
|
"entropy": 6.177883052825928,
|
|
"epoch": 1.6398760433848154,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004736654423512717,
|
|
"loss": 5.5739,
|
|
"mean_token_accuracy": 0.19802180379629136,
|
|
"num_tokens": 32072396.0,
|
|
"step": 16405
|
|
},
|
|
{
|
|
"entropy": 6.206494331359863,
|
|
"epoch": 1.6403758684460439,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004736486855002813,
|
|
"loss": 5.7299,
|
|
"mean_token_accuracy": 0.17646244317293167,
|
|
"num_tokens": 32082200.0,
|
|
"step": 16410
|
|
},
|
|
{
|
|
"entropy": 6.237953042984008,
|
|
"epoch": 1.6408756935072724,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000473631923651341,
|
|
"loss": 5.5868,
|
|
"mean_token_accuracy": 0.20149494856595992,
|
|
"num_tokens": 32091670.0,
|
|
"step": 16415
|
|
},
|
|
{
|
|
"entropy": 6.310654020309448,
|
|
"epoch": 1.641375518568501,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004736151568048726,
|
|
"loss": 5.7887,
|
|
"mean_token_accuracy": 0.16995955556631087,
|
|
"num_tokens": 32102072.0,
|
|
"step": 16420
|
|
},
|
|
{
|
|
"entropy": 6.2326983451843265,
|
|
"epoch": 1.6418753436297298,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000473598384961298,
|
|
"loss": 5.6194,
|
|
"mean_token_accuracy": 0.18644488006830215,
|
|
"num_tokens": 32111367.0,
|
|
"step": 16425
|
|
},
|
|
{
|
|
"entropy": 6.299352836608887,
|
|
"epoch": 1.642375168690958,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00047358160812103925,
|
|
"loss": 5.679,
|
|
"mean_token_accuracy": 0.18445358127355577,
|
|
"num_tokens": 32121065.0,
|
|
"step": 16430
|
|
},
|
|
{
|
|
"entropy": 6.306634187698364,
|
|
"epoch": 1.6428749937521867,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004735648262845182,
|
|
"loss": 5.7332,
|
|
"mean_token_accuracy": 0.17964619547128677,
|
|
"num_tokens": 32130142.0,
|
|
"step": 16435
|
|
},
|
|
{
|
|
"entropy": 6.278433799743652,
|
|
"epoch": 1.6433748188134154,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047354803945215727,
|
|
"loss": 5.8129,
|
|
"mean_token_accuracy": 0.17718289121985437,
|
|
"num_tokens": 32140689.0,
|
|
"step": 16440
|
|
},
|
|
{
|
|
"entropy": 6.247654390335083,
|
|
"epoch": 1.6438746438746439,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00047353124762437865,
|
|
"loss": 5.5827,
|
|
"mean_token_accuracy": 0.1945711553096771,
|
|
"num_tokens": 32150888.0,
|
|
"step": 16445
|
|
},
|
|
{
|
|
"entropy": 6.303831958770752,
|
|
"epoch": 1.6443744689358724,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004735144508016051,
|
|
"loss": 5.7905,
|
|
"mean_token_accuracy": 0.17226203829050063,
|
|
"num_tokens": 32161188.0,
|
|
"step": 16450
|
|
},
|
|
{
|
|
"entropy": 6.247508001327515,
|
|
"epoch": 1.644874293997101,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004734976489842589,
|
|
"loss": 5.6781,
|
|
"mean_token_accuracy": 0.18523656576871872,
|
|
"num_tokens": 32171684.0,
|
|
"step": 16455
|
|
},
|
|
{
|
|
"entropy": 6.299356269836426,
|
|
"epoch": 1.6453741190583295,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000473480842172763,
|
|
"loss": 5.7647,
|
|
"mean_token_accuracy": 0.17075978219509125,
|
|
"num_tokens": 32181497.0,
|
|
"step": 16460
|
|
},
|
|
{
|
|
"entropy": 6.253592014312744,
|
|
"epoch": 1.645873944119558,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047346403036754023,
|
|
"loss": 5.6486,
|
|
"mean_token_accuracy": 0.1847634270787239,
|
|
"num_tokens": 32190653.0,
|
|
"step": 16465
|
|
},
|
|
{
|
|
"entropy": 6.262989330291748,
|
|
"epoch": 1.6463737691807867,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00047344721356901344,
|
|
"loss": 5.7411,
|
|
"mean_token_accuracy": 0.17972230166196823,
|
|
"num_tokens": 32200367.0,
|
|
"step": 16470
|
|
},
|
|
{
|
|
"entropy": 6.276791429519653,
|
|
"epoch": 1.6468735942420154,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004734303917776059,
|
|
"loss": 5.7869,
|
|
"mean_token_accuracy": 0.17071703523397447,
|
|
"num_tokens": 32210187.0,
|
|
"step": 16475
|
|
},
|
|
{
|
|
"entropy": 6.315084791183471,
|
|
"epoch": 1.6473734193032439,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047341356499374065,
|
|
"loss": 5.6532,
|
|
"mean_token_accuracy": 0.1885552778840065,
|
|
"num_tokens": 32218754.0,
|
|
"step": 16480
|
|
},
|
|
{
|
|
"entropy": 6.213974142074585,
|
|
"epoch": 1.6478732443644724,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004733967332178412,
|
|
"loss": 5.7028,
|
|
"mean_token_accuracy": 0.18173779398202897,
|
|
"num_tokens": 32228105.0,
|
|
"step": 16485
|
|
},
|
|
{
|
|
"entropy": 6.274206972122192,
|
|
"epoch": 1.648373069425701,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004733798964503311,
|
|
"loss": 5.7501,
|
|
"mean_token_accuracy": 0.18304921239614486,
|
|
"num_tokens": 32239303.0,
|
|
"step": 16490
|
|
},
|
|
{
|
|
"entropy": 6.216256332397461,
|
|
"epoch": 1.6488728944869295,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004733630546916338,
|
|
"loss": 5.6069,
|
|
"mean_token_accuracy": 0.18784720152616502,
|
|
"num_tokens": 32248614.0,
|
|
"step": 16495
|
|
},
|
|
{
|
|
"entropy": 6.231598520278931,
|
|
"epoch": 1.649372719548158,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00047334620794217306,
|
|
"loss": 5.7372,
|
|
"mean_token_accuracy": 0.18167714625597,
|
|
"num_tokens": 32257012.0,
|
|
"step": 16500
|
|
},
|
|
{
|
|
"entropy": 6.240571022033691,
|
|
"epoch": 1.6498725446093867,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004733293562023727,
|
|
"loss": 5.6456,
|
|
"mean_token_accuracy": 0.1907830372452736,
|
|
"num_tokens": 32267990.0,
|
|
"step": 16505
|
|
},
|
|
{
|
|
"entropy": 6.273388385772705,
|
|
"epoch": 1.6503723696706154,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047331249947265685,
|
|
"loss": 5.6246,
|
|
"mean_token_accuracy": 0.19026638120412825,
|
|
"num_tokens": 32277519.0,
|
|
"step": 16510
|
|
},
|
|
{
|
|
"entropy": 6.291073131561279,
|
|
"epoch": 1.6508721947318439,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004732956377534496,
|
|
"loss": 5.6691,
|
|
"mean_token_accuracy": 0.1755306079983711,
|
|
"num_tokens": 32286749.0,
|
|
"step": 16515
|
|
},
|
|
{
|
|
"entropy": 6.341662645339966,
|
|
"epoch": 1.6513720197930724,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000473278771045175,
|
|
"loss": 5.8565,
|
|
"mean_token_accuracy": 0.17097005993127823,
|
|
"num_tokens": 32296344.0,
|
|
"step": 16520
|
|
},
|
|
{
|
|
"entropy": 6.336608123779297,
|
|
"epoch": 1.651871844854301,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047326189934825764,
|
|
"loss": 5.6629,
|
|
"mean_token_accuracy": 0.1800965428352356,
|
|
"num_tokens": 32305857.0,
|
|
"step": 16525
|
|
},
|
|
{
|
|
"entropy": 6.226555967330933,
|
|
"epoch": 1.6523716699155295,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004732450226631219,
|
|
"loss": 5.6778,
|
|
"mean_token_accuracy": 0.18976286053657532,
|
|
"num_tokens": 32315265.0,
|
|
"step": 16530
|
|
},
|
|
{
|
|
"entropy": 6.323258876800537,
|
|
"epoch": 1.652871494976758,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047322814099019236,
|
|
"loss": 5.8314,
|
|
"mean_token_accuracy": 0.17309070378541946,
|
|
"num_tokens": 32324724.0,
|
|
"step": 16535
|
|
},
|
|
{
|
|
"entropy": 6.274085617065429,
|
|
"epoch": 1.6533713200379867,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004732112543298938,
|
|
"loss": 5.7282,
|
|
"mean_token_accuracy": 0.17484845966100693,
|
|
"num_tokens": 32334958.0,
|
|
"step": 16540
|
|
},
|
|
{
|
|
"entropy": 6.262060546875,
|
|
"epoch": 1.6538711450992154,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004731943626826511,
|
|
"loss": 5.7288,
|
|
"mean_token_accuracy": 0.17748114764690398,
|
|
"num_tokens": 32345153.0,
|
|
"step": 16545
|
|
},
|
|
{
|
|
"entropy": 6.28246750831604,
|
|
"epoch": 1.6543709701604439,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047317746604888923,
|
|
"loss": 5.6767,
|
|
"mean_token_accuracy": 0.18091294169425964,
|
|
"num_tokens": 32354692.0,
|
|
"step": 16550
|
|
},
|
|
{
|
|
"entropy": 6.283524894714356,
|
|
"epoch": 1.6548707952216724,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047316056442903333,
|
|
"loss": 5.7702,
|
|
"mean_token_accuracy": 0.17521451264619828,
|
|
"num_tokens": 32363614.0,
|
|
"step": 16555
|
|
},
|
|
{
|
|
"entropy": 6.29973030090332,
|
|
"epoch": 1.655370620282901,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004731436578235086,
|
|
"loss": 5.6847,
|
|
"mean_token_accuracy": 0.18788749426603318,
|
|
"num_tokens": 32373139.0,
|
|
"step": 16560
|
|
},
|
|
{
|
|
"entropy": 6.289681720733642,
|
|
"epoch": 1.6558704453441295,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00047312674623274046,
|
|
"loss": 5.7037,
|
|
"mean_token_accuracy": 0.1762819841504097,
|
|
"num_tokens": 32383624.0,
|
|
"step": 16565
|
|
},
|
|
{
|
|
"entropy": 6.224221801757812,
|
|
"epoch": 1.656370270405358,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004731098296571543,
|
|
"loss": 5.559,
|
|
"mean_token_accuracy": 0.1859237179160118,
|
|
"num_tokens": 32393221.0,
|
|
"step": 16570
|
|
},
|
|
{
|
|
"entropy": 6.2904465675354,
|
|
"epoch": 1.6568700954665867,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047309290809717584,
|
|
"loss": 5.7607,
|
|
"mean_token_accuracy": 0.17705345749855042,
|
|
"num_tokens": 32402908.0,
|
|
"step": 16575
|
|
},
|
|
{
|
|
"entropy": 6.226483488082886,
|
|
"epoch": 1.6573699205278154,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00047307598155323083,
|
|
"loss": 5.6929,
|
|
"mean_token_accuracy": 0.17667610347270965,
|
|
"num_tokens": 32413597.0,
|
|
"step": 16580
|
|
},
|
|
{
|
|
"entropy": 6.27813572883606,
|
|
"epoch": 1.6578697455890439,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000473059050025745,
|
|
"loss": 5.7114,
|
|
"mean_token_accuracy": 0.18675362467765808,
|
|
"num_tokens": 32423948.0,
|
|
"step": 16585
|
|
},
|
|
{
|
|
"entropy": 6.255496168136597,
|
|
"epoch": 1.6583695706502724,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004730421135151445,
|
|
"loss": 5.6792,
|
|
"mean_token_accuracy": 0.18273984789848327,
|
|
"num_tokens": 32433176.0,
|
|
"step": 16590
|
|
},
|
|
{
|
|
"entropy": 6.171598196029663,
|
|
"epoch": 1.658869395711501,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004730251720218554,
|
|
"loss": 5.6378,
|
|
"mean_token_accuracy": 0.18659755885601043,
|
|
"num_tokens": 32442868.0,
|
|
"step": 16595
|
|
},
|
|
{
|
|
"entropy": 6.257648086547851,
|
|
"epoch": 1.6593692207727295,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047300822554630393,
|
|
"loss": 5.688,
|
|
"mean_token_accuracy": 0.18560874462127686,
|
|
"num_tokens": 32451966.0,
|
|
"step": 16600
|
|
},
|
|
{
|
|
"entropy": 6.264009857177735,
|
|
"epoch": 1.659869045833958,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004729912740889164,
|
|
"loss": 5.6471,
|
|
"mean_token_accuracy": 0.19028035998344422,
|
|
"num_tokens": 32462442.0,
|
|
"step": 16605
|
|
},
|
|
{
|
|
"entropy": 6.289176034927368,
|
|
"epoch": 1.6603688708951867,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047297431765011945,
|
|
"loss": 5.6746,
|
|
"mean_token_accuracy": 0.18580541163682937,
|
|
"num_tokens": 32471709.0,
|
|
"step": 16610
|
|
},
|
|
{
|
|
"entropy": 6.247317266464234,
|
|
"epoch": 1.6608686959564154,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047295735623033953,
|
|
"loss": 5.6934,
|
|
"mean_token_accuracy": 0.18983864039182663,
|
|
"num_tokens": 32482147.0,
|
|
"step": 16615
|
|
},
|
|
{
|
|
"entropy": 6.231543397903442,
|
|
"epoch": 1.6613685210176439,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004729403898300035,
|
|
"loss": 5.558,
|
|
"mean_token_accuracy": 0.19614147692918776,
|
|
"num_tokens": 32492626.0,
|
|
"step": 16620
|
|
},
|
|
{
|
|
"entropy": 6.222279262542725,
|
|
"epoch": 1.6618683460788723,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047292341844953813,
|
|
"loss": 5.6673,
|
|
"mean_token_accuracy": 0.18872719556093215,
|
|
"num_tokens": 32502887.0,
|
|
"step": 16625
|
|
},
|
|
{
|
|
"entropy": 6.3229677200317385,
|
|
"epoch": 1.662368171140101,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004729064420893706,
|
|
"loss": 5.7634,
|
|
"mean_token_accuracy": 0.17217572033405304,
|
|
"num_tokens": 32512860.0,
|
|
"step": 16630
|
|
},
|
|
{
|
|
"entropy": 6.348876667022705,
|
|
"epoch": 1.6628679962013295,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004728894607499278,
|
|
"loss": 5.8132,
|
|
"mean_token_accuracy": 0.16550493985414505,
|
|
"num_tokens": 32523103.0,
|
|
"step": 16635
|
|
},
|
|
{
|
|
"entropy": 6.219545602798462,
|
|
"epoch": 1.663367821262558,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004728724744316371,
|
|
"loss": 5.6313,
|
|
"mean_token_accuracy": 0.1827996179461479,
|
|
"num_tokens": 32532940.0,
|
|
"step": 16640
|
|
},
|
|
{
|
|
"entropy": 6.342902326583863,
|
|
"epoch": 1.6638676463237867,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00047285548313492594,
|
|
"loss": 5.7797,
|
|
"mean_token_accuracy": 0.17874480187892913,
|
|
"num_tokens": 32543503.0,
|
|
"step": 16645
|
|
},
|
|
{
|
|
"entropy": 6.279630851745606,
|
|
"epoch": 1.6643674713850154,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004728384868602217,
|
|
"loss": 5.6423,
|
|
"mean_token_accuracy": 0.18792956918478013,
|
|
"num_tokens": 32552025.0,
|
|
"step": 16650
|
|
},
|
|
{
|
|
"entropy": 6.231253814697266,
|
|
"epoch": 1.6648672964462436,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000472821485607952,
|
|
"loss": 5.6373,
|
|
"mean_token_accuracy": 0.18175789564847947,
|
|
"num_tokens": 32561262.0,
|
|
"step": 16655
|
|
},
|
|
{
|
|
"entropy": 6.282629537582397,
|
|
"epoch": 1.6653671215074723,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004728044793785446,
|
|
"loss": 5.7344,
|
|
"mean_token_accuracy": 0.1765179693698883,
|
|
"num_tokens": 32572067.0,
|
|
"step": 16660
|
|
},
|
|
{
|
|
"entropy": 6.3066840171813965,
|
|
"epoch": 1.665866946568701,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00047278746817242754,
|
|
"loss": 5.6826,
|
|
"mean_token_accuracy": 0.18877280950546266,
|
|
"num_tokens": 32582033.0,
|
|
"step": 16665
|
|
},
|
|
{
|
|
"entropy": 6.229464721679688,
|
|
"epoch": 1.6663667716299295,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004727704519900286,
|
|
"loss": 5.6625,
|
|
"mean_token_accuracy": 0.1859361559152603,
|
|
"num_tokens": 32592338.0,
|
|
"step": 16670
|
|
},
|
|
{
|
|
"entropy": 6.2402809143066404,
|
|
"epoch": 1.666866596691158,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000472753430831776,
|
|
"loss": 5.6208,
|
|
"mean_token_accuracy": 0.18977890759706498,
|
|
"num_tokens": 32602310.0,
|
|
"step": 16675
|
|
},
|
|
{
|
|
"entropy": 6.364634847640991,
|
|
"epoch": 1.6673664217523867,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047273640469809786,
|
|
"loss": 5.7794,
|
|
"mean_token_accuracy": 0.17878334522247313,
|
|
"num_tokens": 32612632.0,
|
|
"step": 16680
|
|
},
|
|
{
|
|
"entropy": 6.249752521514893,
|
|
"epoch": 1.6678662468136154,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004727193735894227,
|
|
"loss": 5.6785,
|
|
"mean_token_accuracy": 0.1825347900390625,
|
|
"num_tokens": 32622455.0,
|
|
"step": 16685
|
|
},
|
|
{
|
|
"entropy": 6.183070802688599,
|
|
"epoch": 1.6683660718748436,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047270233750617907,
|
|
"loss": 5.6683,
|
|
"mean_token_accuracy": 0.1821190670132637,
|
|
"num_tokens": 32631854.0,
|
|
"step": 16690
|
|
},
|
|
{
|
|
"entropy": 6.27028079032898,
|
|
"epoch": 1.6688658969360723,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00047268529644879545,
|
|
"loss": 5.7601,
|
|
"mean_token_accuracy": 0.18616943806409836,
|
|
"num_tokens": 32641532.0,
|
|
"step": 16695
|
|
},
|
|
{
|
|
"entropy": 6.30070481300354,
|
|
"epoch": 1.669365721997301,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047266825041770066,
|
|
"loss": 5.6995,
|
|
"mean_token_accuracy": 0.18255635350942612,
|
|
"num_tokens": 32650748.0,
|
|
"step": 16700
|
|
},
|
|
{
|
|
"entropy": 6.247910356521606,
|
|
"epoch": 1.6698655470585295,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004726511994133235,
|
|
"loss": 5.6994,
|
|
"mean_token_accuracy": 0.1835823953151703,
|
|
"num_tokens": 32660828.0,
|
|
"step": 16705
|
|
},
|
|
{
|
|
"entropy": 6.217136669158935,
|
|
"epoch": 1.670365372119758,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00047263414343609307,
|
|
"loss": 5.7169,
|
|
"mean_token_accuracy": 0.18359023630619048,
|
|
"num_tokens": 32670951.0,
|
|
"step": 16710
|
|
},
|
|
{
|
|
"entropy": 6.300764560699463,
|
|
"epoch": 1.6708651971809867,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00047261708248643846,
|
|
"loss": 5.6899,
|
|
"mean_token_accuracy": 0.18620773702859877,
|
|
"num_tokens": 32680977.0,
|
|
"step": 16715
|
|
},
|
|
{
|
|
"entropy": 6.3109142780303955,
|
|
"epoch": 1.6713650222422152,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004726000165647888,
|
|
"loss": 5.6981,
|
|
"mean_token_accuracy": 0.18302771598100662,
|
|
"num_tokens": 32690004.0,
|
|
"step": 16720
|
|
},
|
|
{
|
|
"entropy": 6.287534904479981,
|
|
"epoch": 1.6718648473034436,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004725829456715737,
|
|
"loss": 5.7139,
|
|
"mean_token_accuracy": 0.17607163190841674,
|
|
"num_tokens": 32699862.0,
|
|
"step": 16725
|
|
},
|
|
{
|
|
"entropy": 6.266330814361572,
|
|
"epoch": 1.6723646723646723,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004725658698072225,
|
|
"loss": 5.6802,
|
|
"mean_token_accuracy": 0.18517099767923356,
|
|
"num_tokens": 32708732.0,
|
|
"step": 16730
|
|
},
|
|
{
|
|
"entropy": 6.31958703994751,
|
|
"epoch": 1.672864497425901,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004725487889721648,
|
|
"loss": 5.8112,
|
|
"mean_token_accuracy": 0.17096830308437347,
|
|
"num_tokens": 32719117.0,
|
|
"step": 16735
|
|
},
|
|
{
|
|
"entropy": 6.319113254547119,
|
|
"epoch": 1.6733643224871295,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004725317031668304,
|
|
"loss": 5.6833,
|
|
"mean_token_accuracy": 0.17487334012985228,
|
|
"num_tokens": 32728357.0,
|
|
"step": 16740
|
|
},
|
|
{
|
|
"entropy": 6.309004306793213,
|
|
"epoch": 1.673864147548358,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00047251461239164916,
|
|
"loss": 5.6831,
|
|
"mean_token_accuracy": 0.1838237911462784,
|
|
"num_tokens": 32738249.0,
|
|
"step": 16745
|
|
},
|
|
{
|
|
"entropy": 6.164138412475586,
|
|
"epoch": 1.6743639726095867,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004724975166470512,
|
|
"loss": 5.6389,
|
|
"mean_token_accuracy": 0.1880248799920082,
|
|
"num_tokens": 32747880.0,
|
|
"step": 16750
|
|
},
|
|
{
|
|
"entropy": 6.279034233093261,
|
|
"epoch": 1.6748637976708152,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004724804159334665,
|
|
"loss": 5.6521,
|
|
"mean_token_accuracy": 0.18064113706350327,
|
|
"num_tokens": 32758215.0,
|
|
"step": 16755
|
|
},
|
|
{
|
|
"entropy": 6.3476622104644775,
|
|
"epoch": 1.6753636227320436,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004724633102513253,
|
|
"loss": 5.777,
|
|
"mean_token_accuracy": 0.17687715590000153,
|
|
"num_tokens": 32767426.0,
|
|
"step": 16760
|
|
},
|
|
{
|
|
"entropy": 6.231785726547241,
|
|
"epoch": 1.6758634477932723,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004724461996010581,
|
|
"loss": 5.5901,
|
|
"mean_token_accuracy": 0.1894110009074211,
|
|
"num_tokens": 32776507.0,
|
|
"step": 16765
|
|
},
|
|
{
|
|
"entropy": 6.141523981094361,
|
|
"epoch": 1.676363272854501,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004724290839830953,
|
|
"loss": 5.6712,
|
|
"mean_token_accuracy": 0.18906268030405043,
|
|
"num_tokens": 32787386.0,
|
|
"step": 16770
|
|
},
|
|
{
|
|
"entropy": 6.261982107162476,
|
|
"epoch": 1.6768630979157295,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004724119633978675,
|
|
"loss": 5.6929,
|
|
"mean_token_accuracy": 0.1823606476187706,
|
|
"num_tokens": 32797245.0,
|
|
"step": 16775
|
|
},
|
|
{
|
|
"entropy": 6.286819410324097,
|
|
"epoch": 1.677362922976958,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047239483784580554,
|
|
"loss": 5.7213,
|
|
"mean_token_accuracy": 0.19030696749687195,
|
|
"num_tokens": 32807256.0,
|
|
"step": 16780
|
|
},
|
|
{
|
|
"entropy": 6.295222187042237,
|
|
"epoch": 1.6778627480381867,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004723777073273403,
|
|
"loss": 5.7328,
|
|
"mean_token_accuracy": 0.1824662283062935,
|
|
"num_tokens": 32816818.0,
|
|
"step": 16785
|
|
},
|
|
{
|
|
"entropy": 6.24727087020874,
|
|
"epoch": 1.6783625730994152,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004723605718429026,
|
|
"loss": 5.7745,
|
|
"mean_token_accuracy": 0.17679570019245147,
|
|
"num_tokens": 32826275.0,
|
|
"step": 16790
|
|
},
|
|
{
|
|
"entropy": 6.226606845855713,
|
|
"epoch": 1.6788623981606436,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004723434313929238,
|
|
"loss": 5.7038,
|
|
"mean_token_accuracy": 0.18361091315746308,
|
|
"num_tokens": 32836703.0,
|
|
"step": 16795
|
|
},
|
|
{
|
|
"entropy": 6.209852027893066,
|
|
"epoch": 1.6793622232218723,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047232628597783507,
|
|
"loss": 5.6233,
|
|
"mean_token_accuracy": 0.18867835104465486,
|
|
"num_tokens": 32847745.0,
|
|
"step": 16800
|
|
},
|
|
{
|
|
"entropy": 6.292082786560059,
|
|
"epoch": 1.679862048283101,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047230913559806773,
|
|
"loss": 5.6688,
|
|
"mean_token_accuracy": 0.18543678671121597,
|
|
"num_tokens": 32857123.0,
|
|
"step": 16805
|
|
},
|
|
{
|
|
"entropy": 6.178192377090454,
|
|
"epoch": 1.6803618733443295,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004722919802540533,
|
|
"loss": 5.6309,
|
|
"mean_token_accuracy": 0.18582808822393418,
|
|
"num_tokens": 32866337.0,
|
|
"step": 16810
|
|
},
|
|
{
|
|
"entropy": 6.22785701751709,
|
|
"epoch": 1.680861698405558,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004722748199462234,
|
|
"loss": 5.7566,
|
|
"mean_token_accuracy": 0.18384657353162764,
|
|
"num_tokens": 32877525.0,
|
|
"step": 16815
|
|
},
|
|
{
|
|
"entropy": 6.332187938690185,
|
|
"epoch": 1.6813615234667867,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004722576546750098,
|
|
"loss": 5.7172,
|
|
"mean_token_accuracy": 0.18436505049467086,
|
|
"num_tokens": 32888165.0,
|
|
"step": 16820
|
|
},
|
|
{
|
|
"entropy": 6.315145492553711,
|
|
"epoch": 1.6818613485280152,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.00047224048444084434,
|
|
"loss": 5.7187,
|
|
"mean_token_accuracy": 0.18431114703416823,
|
|
"num_tokens": 32898541.0,
|
|
"step": 16825
|
|
},
|
|
{
|
|
"entropy": 6.181602334976196,
|
|
"epoch": 1.6823611735892436,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00047222330924415906,
|
|
"loss": 5.5798,
|
|
"mean_token_accuracy": 0.1919554963707924,
|
|
"num_tokens": 32907796.0,
|
|
"step": 16830
|
|
},
|
|
{
|
|
"entropy": 6.255088949203492,
|
|
"epoch": 1.6828609986504723,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004722061290853862,
|
|
"loss": 5.6147,
|
|
"mean_token_accuracy": 0.188002872467041,
|
|
"num_tokens": 32917067.0,
|
|
"step": 16835
|
|
},
|
|
{
|
|
"entropy": 6.280344915390015,
|
|
"epoch": 1.683360823711701,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00047218894396495765,
|
|
"loss": 5.6464,
|
|
"mean_token_accuracy": 0.1919111892580986,
|
|
"num_tokens": 32927039.0,
|
|
"step": 16840
|
|
},
|
|
{
|
|
"entropy": 6.243479824066162,
|
|
"epoch": 1.6838606487729295,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004721717538833061,
|
|
"loss": 5.6814,
|
|
"mean_token_accuracy": 0.18858575969934463,
|
|
"num_tokens": 32937574.0,
|
|
"step": 16845
|
|
},
|
|
{
|
|
"entropy": 6.335844850540161,
|
|
"epoch": 1.684360473834158,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000472154558840864,
|
|
"loss": 5.7708,
|
|
"mean_token_accuracy": 0.1788774013519287,
|
|
"num_tokens": 32948401.0,
|
|
"step": 16850
|
|
},
|
|
{
|
|
"entropy": 6.251031446456909,
|
|
"epoch": 1.6848602988953867,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000472137358838064,
|
|
"loss": 5.6827,
|
|
"mean_token_accuracy": 0.1830250710248947,
|
|
"num_tokens": 32957359.0,
|
|
"step": 16855
|
|
},
|
|
{
|
|
"entropy": 6.182391119003296,
|
|
"epoch": 1.6853601239566152,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004721201538753387,
|
|
"loss": 5.5814,
|
|
"mean_token_accuracy": 0.19801218807697296,
|
|
"num_tokens": 32966340.0,
|
|
"step": 16860
|
|
},
|
|
{
|
|
"entropy": 6.225259017944336,
|
|
"epoch": 1.6858599490178436,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047210294395312103,
|
|
"loss": 5.6641,
|
|
"mean_token_accuracy": 0.18303921371698378,
|
|
"num_tokens": 32976376.0,
|
|
"step": 16865
|
|
},
|
|
{
|
|
"entropy": 6.2387096881866455,
|
|
"epoch": 1.6863597740790723,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000472085729071844,
|
|
"loss": 5.6174,
|
|
"mean_token_accuracy": 0.19593114405870438,
|
|
"num_tokens": 32985680.0,
|
|
"step": 16870
|
|
},
|
|
{
|
|
"entropy": 6.228881883621216,
|
|
"epoch": 1.686859599140301,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047206850923194076,
|
|
"loss": 5.6601,
|
|
"mean_token_accuracy": 0.18412352204322815,
|
|
"num_tokens": 32995557.0,
|
|
"step": 16875
|
|
},
|
|
{
|
|
"entropy": 6.2974841594696045,
|
|
"epoch": 1.6873594242015295,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047205128443384456,
|
|
"loss": 5.6658,
|
|
"mean_token_accuracy": 0.18460905253887178,
|
|
"num_tokens": 33004655.0,
|
|
"step": 16880
|
|
},
|
|
{
|
|
"entropy": 6.2723565101623535,
|
|
"epoch": 1.687859249262758,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004720340546779887,
|
|
"loss": 5.712,
|
|
"mean_token_accuracy": 0.1804384782910347,
|
|
"num_tokens": 33014621.0,
|
|
"step": 16885
|
|
},
|
|
{
|
|
"entropy": 6.259779739379883,
|
|
"epoch": 1.6883590743239867,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004720168199648068,
|
|
"loss": 5.632,
|
|
"mean_token_accuracy": 0.18828185349702836,
|
|
"num_tokens": 33024390.0,
|
|
"step": 16890
|
|
},
|
|
{
|
|
"entropy": 6.254510498046875,
|
|
"epoch": 1.6888588993852152,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047199958029473237,
|
|
"loss": 5.7696,
|
|
"mean_token_accuracy": 0.18567049354314805,
|
|
"num_tokens": 33035351.0,
|
|
"step": 16895
|
|
},
|
|
{
|
|
"entropy": 6.171364068984985,
|
|
"epoch": 1.6893587244464436,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00047198233566819915,
|
|
"loss": 5.5746,
|
|
"mean_token_accuracy": 0.19844255447387696,
|
|
"num_tokens": 33044148.0,
|
|
"step": 16900
|
|
},
|
|
{
|
|
"entropy": 6.215256643295288,
|
|
"epoch": 1.6898585495076723,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004719650860856411,
|
|
"loss": 5.6869,
|
|
"mean_token_accuracy": 0.18458660691976547,
|
|
"num_tokens": 33053772.0,
|
|
"step": 16905
|
|
},
|
|
{
|
|
"entropy": 6.296458625793457,
|
|
"epoch": 1.690358374568901,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00047194783154749217,
|
|
"loss": 5.6733,
|
|
"mean_token_accuracy": 0.18709744960069657,
|
|
"num_tokens": 33064422.0,
|
|
"step": 16910
|
|
},
|
|
{
|
|
"entropy": 6.357833909988403,
|
|
"epoch": 1.6908581996301293,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004719305720541865,
|
|
"loss": 5.814,
|
|
"mean_token_accuracy": 0.17227787524461746,
|
|
"num_tokens": 33075235.0,
|
|
"step": 16915
|
|
},
|
|
{
|
|
"entropy": 6.245255661010742,
|
|
"epoch": 1.691358024691358,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047191330760615823,
|
|
"loss": 5.6673,
|
|
"mean_token_accuracy": 0.1838690906763077,
|
|
"num_tokens": 33085489.0,
|
|
"step": 16920
|
|
},
|
|
{
|
|
"entropy": 6.262874984741211,
|
|
"epoch": 1.6918578497525867,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047189603820384186,
|
|
"loss": 5.7054,
|
|
"mean_token_accuracy": 0.1846708580851555,
|
|
"num_tokens": 33094932.0,
|
|
"step": 16925
|
|
},
|
|
{
|
|
"entropy": 6.215816974639893,
|
|
"epoch": 1.6923576748138152,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047187876384767187,
|
|
"loss": 5.669,
|
|
"mean_token_accuracy": 0.18884633332490922,
|
|
"num_tokens": 33104224.0,
|
|
"step": 16930
|
|
},
|
|
{
|
|
"entropy": 6.233232069015503,
|
|
"epoch": 1.6928574998750436,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047186148453808274,
|
|
"loss": 5.6326,
|
|
"mean_token_accuracy": 0.18473802804946898,
|
|
"num_tokens": 33114039.0,
|
|
"step": 16935
|
|
},
|
|
{
|
|
"entropy": 6.2805530548095705,
|
|
"epoch": 1.6933573249362723,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004718442002755094,
|
|
"loss": 5.714,
|
|
"mean_token_accuracy": 0.18395548909902573,
|
|
"num_tokens": 33123274.0,
|
|
"step": 16940
|
|
},
|
|
{
|
|
"entropy": 6.281697607040405,
|
|
"epoch": 1.693857149997501,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004718269110603866,
|
|
"loss": 5.6929,
|
|
"mean_token_accuracy": 0.18693676590919495,
|
|
"num_tokens": 33134259.0,
|
|
"step": 16945
|
|
},
|
|
{
|
|
"entropy": 6.305875158309936,
|
|
"epoch": 1.6943569750587293,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00047180961689314937,
|
|
"loss": 5.6455,
|
|
"mean_token_accuracy": 0.19250985383987426,
|
|
"num_tokens": 33144662.0,
|
|
"step": 16950
|
|
},
|
|
{
|
|
"entropy": 6.2643217086792,
|
|
"epoch": 1.694856800119958,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004717923177742329,
|
|
"loss": 5.692,
|
|
"mean_token_accuracy": 0.18114591687917708,
|
|
"num_tokens": 33154074.0,
|
|
"step": 16955
|
|
},
|
|
{
|
|
"entropy": 6.261256694793701,
|
|
"epoch": 1.6953566251811867,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047177501370407223,
|
|
"loss": 5.6867,
|
|
"mean_token_accuracy": 0.18100175112485886,
|
|
"num_tokens": 33163973.0,
|
|
"step": 16960
|
|
},
|
|
{
|
|
"entropy": 6.3157538890838625,
|
|
"epoch": 1.6958564502424152,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047175770468310294,
|
|
"loss": 5.7306,
|
|
"mean_token_accuracy": 0.17960360944271087,
|
|
"num_tokens": 33173607.0,
|
|
"step": 16965
|
|
},
|
|
{
|
|
"entropy": 6.215094709396363,
|
|
"epoch": 1.6963562753036436,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047174039071176037,
|
|
"loss": 5.5799,
|
|
"mean_token_accuracy": 0.1945421054959297,
|
|
"num_tokens": 33183104.0,
|
|
"step": 16970
|
|
},
|
|
{
|
|
"entropy": 6.280225706100464,
|
|
"epoch": 1.6968561003648723,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00047172307179048025,
|
|
"loss": 5.6395,
|
|
"mean_token_accuracy": 0.1850980043411255,
|
|
"num_tokens": 33191066.0,
|
|
"step": 16975
|
|
},
|
|
{
|
|
"entropy": 6.2481749057769775,
|
|
"epoch": 1.697355925426101,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004717057479196982,
|
|
"loss": 5.6822,
|
|
"mean_token_accuracy": 0.18823699206113814,
|
|
"num_tokens": 33201499.0,
|
|
"step": 16980
|
|
},
|
|
{
|
|
"entropy": 6.2327125549316404,
|
|
"epoch": 1.6978557504873293,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004716884190998502,
|
|
"loss": 5.6146,
|
|
"mean_token_accuracy": 0.1837209329009056,
|
|
"num_tokens": 33211989.0,
|
|
"step": 16985
|
|
},
|
|
{
|
|
"entropy": 6.320825529098511,
|
|
"epoch": 1.698355575548558,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004716710853313721,
|
|
"loss": 5.7503,
|
|
"mean_token_accuracy": 0.17770535498857498,
|
|
"num_tokens": 33221715.0,
|
|
"step": 16990
|
|
},
|
|
{
|
|
"entropy": 6.2913788795471195,
|
|
"epoch": 1.6988554006097867,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047165374661470023,
|
|
"loss": 5.7072,
|
|
"mean_token_accuracy": 0.17932816743850707,
|
|
"num_tokens": 33232812.0,
|
|
"step": 16995
|
|
},
|
|
{
|
|
"entropy": 6.354789781570434,
|
|
"epoch": 1.6993552256710152,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047163640295027064,
|
|
"loss": 5.6601,
|
|
"mean_token_accuracy": 0.18094070255756378,
|
|
"num_tokens": 33242147.0,
|
|
"step": 17000
|
|
},
|
|
{
|
|
"entropy": 6.283501148223877,
|
|
"epoch": 1.6998550507322436,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047161905433851974,
|
|
"loss": 5.6944,
|
|
"mean_token_accuracy": 0.18424150794744493,
|
|
"num_tokens": 33251433.0,
|
|
"step": 17005
|
|
},
|
|
{
|
|
"entropy": 6.230720520019531,
|
|
"epoch": 1.7003548757934723,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00047160170077988403,
|
|
"loss": 5.6084,
|
|
"mean_token_accuracy": 0.18305566310882568,
|
|
"num_tokens": 33261338.0,
|
|
"step": 17010
|
|
},
|
|
{
|
|
"entropy": 6.244995975494385,
|
|
"epoch": 1.7008547008547008,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004715843422748001,
|
|
"loss": 5.739,
|
|
"mean_token_accuracy": 0.17670915722846986,
|
|
"num_tokens": 33271312.0,
|
|
"step": 17015
|
|
},
|
|
{
|
|
"entropy": 6.32011570930481,
|
|
"epoch": 1.7013545259159293,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047156697882370474,
|
|
"loss": 5.6927,
|
|
"mean_token_accuracy": 0.17892508655786515,
|
|
"num_tokens": 33280525.0,
|
|
"step": 17020
|
|
},
|
|
{
|
|
"entropy": 6.282282876968384,
|
|
"epoch": 1.701854350977158,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004715496104270348,
|
|
"loss": 5.7005,
|
|
"mean_token_accuracy": 0.1863795429468155,
|
|
"num_tokens": 33289968.0,
|
|
"step": 17025
|
|
},
|
|
{
|
|
"entropy": 6.2288073062896725,
|
|
"epoch": 1.7023541760383867,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004715322370852272,
|
|
"loss": 5.7,
|
|
"mean_token_accuracy": 0.18164553195238115,
|
|
"num_tokens": 33299262.0,
|
|
"step": 17030
|
|
},
|
|
{
|
|
"entropy": 6.253278350830078,
|
|
"epoch": 1.7028540010996152,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047151485879871907,
|
|
"loss": 5.6833,
|
|
"mean_token_accuracy": 0.18298567533493043,
|
|
"num_tokens": 33309433.0,
|
|
"step": 17035
|
|
},
|
|
{
|
|
"entropy": 6.232338619232178,
|
|
"epoch": 1.7033538261608436,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00047149747556794763,
|
|
"loss": 5.6446,
|
|
"mean_token_accuracy": 0.1848660632967949,
|
|
"num_tokens": 33318587.0,
|
|
"step": 17040
|
|
},
|
|
{
|
|
"entropy": 6.268502235412598,
|
|
"epoch": 1.7038536512220723,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00047148008739335035,
|
|
"loss": 5.649,
|
|
"mean_token_accuracy": 0.19021392315626146,
|
|
"num_tokens": 33327487.0,
|
|
"step": 17045
|
|
},
|
|
{
|
|
"entropy": 6.299037218093872,
|
|
"epoch": 1.7043534762833008,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004714626942753646,
|
|
"loss": 5.743,
|
|
"mean_token_accuracy": 0.1797867089509964,
|
|
"num_tokens": 33337151.0,
|
|
"step": 17050
|
|
},
|
|
{
|
|
"entropy": 6.31919584274292,
|
|
"epoch": 1.7048533013445293,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000471445296214428,
|
|
"loss": 5.6203,
|
|
"mean_token_accuracy": 0.18206046670675277,
|
|
"num_tokens": 33346547.0,
|
|
"step": 17055
|
|
},
|
|
{
|
|
"entropy": 6.266007757186889,
|
|
"epoch": 1.705353126405758,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047142789321097834,
|
|
"loss": 5.6634,
|
|
"mean_token_accuracy": 0.1805412769317627,
|
|
"num_tokens": 33355277.0,
|
|
"step": 17060
|
|
},
|
|
{
|
|
"entropy": 6.240981149673462,
|
|
"epoch": 1.7058529514669867,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004714104852654534,
|
|
"loss": 5.625,
|
|
"mean_token_accuracy": 0.1934993028640747,
|
|
"num_tokens": 33364340.0,
|
|
"step": 17065
|
|
},
|
|
{
|
|
"entropy": 6.2624640464782715,
|
|
"epoch": 1.7063527765282152,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004713930723782912,
|
|
"loss": 5.6733,
|
|
"mean_token_accuracy": 0.1831752374768257,
|
|
"num_tokens": 33374302.0,
|
|
"step": 17070
|
|
},
|
|
{
|
|
"entropy": 6.3204841136932375,
|
|
"epoch": 1.7068526015894436,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047137565454992983,
|
|
"loss": 5.7496,
|
|
"mean_token_accuracy": 0.18061256259679795,
|
|
"num_tokens": 33384098.0,
|
|
"step": 17075
|
|
},
|
|
{
|
|
"entropy": 6.239755153656006,
|
|
"epoch": 1.7073524266506723,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047135823178080745,
|
|
"loss": 5.6661,
|
|
"mean_token_accuracy": 0.18604766726493835,
|
|
"num_tokens": 33393032.0,
|
|
"step": 17080
|
|
},
|
|
{
|
|
"entropy": 6.203013372421265,
|
|
"epoch": 1.7078522517119008,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004713408040713626,
|
|
"loss": 5.6079,
|
|
"mean_token_accuracy": 0.18342242538928985,
|
|
"num_tokens": 33402533.0,
|
|
"step": 17085
|
|
},
|
|
{
|
|
"entropy": 6.248910427093506,
|
|
"epoch": 1.7083520767731293,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047132337142203365,
|
|
"loss": 5.7082,
|
|
"mean_token_accuracy": 0.18358322381973266,
|
|
"num_tokens": 33412826.0,
|
|
"step": 17090
|
|
},
|
|
{
|
|
"entropy": 6.334503889083862,
|
|
"epoch": 1.708851901834358,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004713059338332591,
|
|
"loss": 5.7011,
|
|
"mean_token_accuracy": 0.17544405162334442,
|
|
"num_tokens": 33422485.0,
|
|
"step": 17095
|
|
},
|
|
{
|
|
"entropy": 6.260263156890869,
|
|
"epoch": 1.7093517268955867,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047128849130547774,
|
|
"loss": 5.5504,
|
|
"mean_token_accuracy": 0.18897906243801116,
|
|
"num_tokens": 33432575.0,
|
|
"step": 17100
|
|
},
|
|
{
|
|
"entropy": 6.1911859035491945,
|
|
"epoch": 1.7098515519568152,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00047127104383912856,
|
|
"loss": 5.7085,
|
|
"mean_token_accuracy": 0.18430694043636323,
|
|
"num_tokens": 33442893.0,
|
|
"step": 17105
|
|
},
|
|
{
|
|
"entropy": 6.2806541442871096,
|
|
"epoch": 1.7103513770180436,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004712535914346504,
|
|
"loss": 5.7861,
|
|
"mean_token_accuracy": 0.17677056044340134,
|
|
"num_tokens": 33452080.0,
|
|
"step": 17110
|
|
},
|
|
{
|
|
"entropy": 6.288609361648559,
|
|
"epoch": 1.7108512020792723,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047123613409248233,
|
|
"loss": 5.6325,
|
|
"mean_token_accuracy": 0.19234236478805541,
|
|
"num_tokens": 33461721.0,
|
|
"step": 17115
|
|
},
|
|
{
|
|
"entropy": 6.328894853591919,
|
|
"epoch": 1.7113510271405008,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00047121867181306365,
|
|
"loss": 5.7104,
|
|
"mean_token_accuracy": 0.1767329290509224,
|
|
"num_tokens": 33470731.0,
|
|
"step": 17120
|
|
},
|
|
{
|
|
"entropy": 6.242598676681519,
|
|
"epoch": 1.7118508522017293,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004712012045968337,
|
|
"loss": 5.723,
|
|
"mean_token_accuracy": 0.18115333020687102,
|
|
"num_tokens": 33481000.0,
|
|
"step": 17125
|
|
},
|
|
{
|
|
"entropy": 6.255340194702148,
|
|
"epoch": 1.712350677262958,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047118373244423197,
|
|
"loss": 5.6985,
|
|
"mean_token_accuracy": 0.18707783669233322,
|
|
"num_tokens": 33489535.0,
|
|
"step": 17130
|
|
},
|
|
{
|
|
"entropy": 6.276972055435181,
|
|
"epoch": 1.7128505023241867,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00047116625535569787,
|
|
"loss": 5.6236,
|
|
"mean_token_accuracy": 0.1792913019657135,
|
|
"num_tokens": 33499746.0,
|
|
"step": 17135
|
|
},
|
|
{
|
|
"entropy": 6.271984624862671,
|
|
"epoch": 1.7133503273854152,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00047114877333167133,
|
|
"loss": 5.6632,
|
|
"mean_token_accuracy": 0.19209207594394684,
|
|
"num_tokens": 33508526.0,
|
|
"step": 17140
|
|
},
|
|
{
|
|
"entropy": 6.228291368484497,
|
|
"epoch": 1.7138501524466436,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047113128637259216,
|
|
"loss": 5.6739,
|
|
"mean_token_accuracy": 0.18288003653287888,
|
|
"num_tokens": 33518675.0,
|
|
"step": 17145
|
|
},
|
|
{
|
|
"entropy": 6.2777135372161865,
|
|
"epoch": 1.7143499775078723,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004711137944789003,
|
|
"loss": 5.7533,
|
|
"mean_token_accuracy": 0.1780509188771248,
|
|
"num_tokens": 33528132.0,
|
|
"step": 17150
|
|
},
|
|
{
|
|
"entropy": 6.257867813110352,
|
|
"epoch": 1.7148498025691008,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047109629765103577,
|
|
"loss": 5.6543,
|
|
"mean_token_accuracy": 0.18690105229616166,
|
|
"num_tokens": 33537259.0,
|
|
"step": 17155
|
|
},
|
|
{
|
|
"entropy": 6.1878790855407715,
|
|
"epoch": 1.7153496276303293,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00047107879588943887,
|
|
"loss": 5.6672,
|
|
"mean_token_accuracy": 0.18558045327663422,
|
|
"num_tokens": 33546189.0,
|
|
"step": 17160
|
|
},
|
|
{
|
|
"entropy": 6.300174951553345,
|
|
"epoch": 1.715849452691558,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047106128919455,
|
|
"loss": 5.7425,
|
|
"mean_token_accuracy": 0.17724650651216506,
|
|
"num_tokens": 33555392.0,
|
|
"step": 17165
|
|
},
|
|
{
|
|
"entropy": 6.332749462127685,
|
|
"epoch": 1.7163492777527867,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004710437775668094,
|
|
"loss": 5.7625,
|
|
"mean_token_accuracy": 0.18211378008127213,
|
|
"num_tokens": 33564766.0,
|
|
"step": 17170
|
|
},
|
|
{
|
|
"entropy": 6.282221889495849,
|
|
"epoch": 1.7168491028140151,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004710262610066579,
|
|
"loss": 5.7587,
|
|
"mean_token_accuracy": 0.17815640419721604,
|
|
"num_tokens": 33574680.0,
|
|
"step": 17175
|
|
},
|
|
{
|
|
"entropy": 6.302897167205811,
|
|
"epoch": 1.7173489278752436,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047100873951453617,
|
|
"loss": 5.7087,
|
|
"mean_token_accuracy": 0.18155068308115005,
|
|
"num_tokens": 33583068.0,
|
|
"step": 17180
|
|
},
|
|
{
|
|
"entropy": 6.230348062515259,
|
|
"epoch": 1.7178487529364723,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00047099121309088487,
|
|
"loss": 5.6804,
|
|
"mean_token_accuracy": 0.18799203485250474,
|
|
"num_tokens": 33592838.0,
|
|
"step": 17185
|
|
},
|
|
{
|
|
"entropy": 6.275839567184448,
|
|
"epoch": 1.7183485779977008,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047097368173614515,
|
|
"loss": 5.6969,
|
|
"mean_token_accuracy": 0.18504282236099243,
|
|
"num_tokens": 33603627.0,
|
|
"step": 17190
|
|
},
|
|
{
|
|
"entropy": 6.224845457077026,
|
|
"epoch": 1.7188484030589293,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00047095614545075807,
|
|
"loss": 5.7097,
|
|
"mean_token_accuracy": 0.1831938073039055,
|
|
"num_tokens": 33614604.0,
|
|
"step": 17195
|
|
},
|
|
{
|
|
"entropy": 6.226759767532348,
|
|
"epoch": 1.719348228120158,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004709386042351647,
|
|
"loss": 5.5794,
|
|
"mean_token_accuracy": 0.19621719419956207,
|
|
"num_tokens": 33624604.0,
|
|
"step": 17200
|
|
},
|
|
{
|
|
"entropy": 6.345744895935058,
|
|
"epoch": 1.7198480531813867,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004709210580898065,
|
|
"loss": 5.7458,
|
|
"mean_token_accuracy": 0.18154867738485336,
|
|
"num_tokens": 33634842.0,
|
|
"step": 17205
|
|
},
|
|
{
|
|
"entropy": 6.328478527069092,
|
|
"epoch": 1.720347878242615,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004709035070151249,
|
|
"loss": 5.7381,
|
|
"mean_token_accuracy": 0.18429091274738313,
|
|
"num_tokens": 33644829.0,
|
|
"step": 17210
|
|
},
|
|
{
|
|
"entropy": 6.3416553974151615,
|
|
"epoch": 1.7208477033038436,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004708859510115614,
|
|
"loss": 5.8,
|
|
"mean_token_accuracy": 0.16693058460950852,
|
|
"num_tokens": 33653952.0,
|
|
"step": 17215
|
|
},
|
|
{
|
|
"entropy": 6.24476637840271,
|
|
"epoch": 1.7213475283650723,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004708683900795579,
|
|
"loss": 5.7566,
|
|
"mean_token_accuracy": 0.18085306286811828,
|
|
"num_tokens": 33664014.0,
|
|
"step": 17220
|
|
},
|
|
{
|
|
"entropy": 6.2911388874053955,
|
|
"epoch": 1.7218473534263008,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047085082421955603,
|
|
"loss": 5.6786,
|
|
"mean_token_accuracy": 0.18630780279636383,
|
|
"num_tokens": 33674575.0,
|
|
"step": 17225
|
|
},
|
|
{
|
|
"entropy": 6.268541717529297,
|
|
"epoch": 1.7223471784875293,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047083325343199786,
|
|
"loss": 5.7092,
|
|
"mean_token_accuracy": 0.18924397975206375,
|
|
"num_tokens": 33684431.0,
|
|
"step": 17230
|
|
},
|
|
{
|
|
"entropy": 6.335117292404175,
|
|
"epoch": 1.722847003548758,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004708156777173254,
|
|
"loss": 5.7729,
|
|
"mean_token_accuracy": 0.17423705905675888,
|
|
"num_tokens": 33693502.0,
|
|
"step": 17235
|
|
},
|
|
{
|
|
"entropy": 6.27399959564209,
|
|
"epoch": 1.7233468286099867,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004707980970759809,
|
|
"loss": 5.7539,
|
|
"mean_token_accuracy": 0.17633218169212342,
|
|
"num_tokens": 33703034.0,
|
|
"step": 17240
|
|
},
|
|
{
|
|
"entropy": 6.257549619674682,
|
|
"epoch": 1.723846653671215,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047078051150840666,
|
|
"loss": 5.6938,
|
|
"mean_token_accuracy": 0.18819527477025985,
|
|
"num_tokens": 33712429.0,
|
|
"step": 17245
|
|
},
|
|
{
|
|
"entropy": 6.2346161842346195,
|
|
"epoch": 1.7243464787324436,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004707629210150451,
|
|
"loss": 5.7198,
|
|
"mean_token_accuracy": 0.18337262123823167,
|
|
"num_tokens": 33724254.0,
|
|
"step": 17250
|
|
},
|
|
{
|
|
"entropy": 6.134075260162353,
|
|
"epoch": 1.7248463037936723,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004707453255963388,
|
|
"loss": 5.4374,
|
|
"mean_token_accuracy": 0.204163034260273,
|
|
"num_tokens": 33735706.0,
|
|
"step": 17255
|
|
},
|
|
{
|
|
"entropy": 6.304078769683838,
|
|
"epoch": 1.7253461288549008,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047072772525273053,
|
|
"loss": 5.6896,
|
|
"mean_token_accuracy": 0.18524314910173417,
|
|
"num_tokens": 33745683.0,
|
|
"step": 17260
|
|
},
|
|
{
|
|
"entropy": 6.263715696334839,
|
|
"epoch": 1.7258459539161293,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00047071011998466304,
|
|
"loss": 5.7038,
|
|
"mean_token_accuracy": 0.17771171182394027,
|
|
"num_tokens": 33756776.0,
|
|
"step": 17265
|
|
},
|
|
{
|
|
"entropy": 6.25303635597229,
|
|
"epoch": 1.726345778977358,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047069250979257934,
|
|
"loss": 5.6155,
|
|
"mean_token_accuracy": 0.1878563404083252,
|
|
"num_tokens": 33766004.0,
|
|
"step": 17270
|
|
},
|
|
{
|
|
"entropy": 6.29105134010315,
|
|
"epoch": 1.7268456040385864,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047067489467692236,
|
|
"loss": 5.7896,
|
|
"mean_token_accuracy": 0.17453796416521072,
|
|
"num_tokens": 33774709.0,
|
|
"step": 17275
|
|
},
|
|
{
|
|
"entropy": 6.352645969390869,
|
|
"epoch": 1.727345429099815,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004706572746381354,
|
|
"loss": 5.7484,
|
|
"mean_token_accuracy": 0.18377119898796082,
|
|
"num_tokens": 33785032.0,
|
|
"step": 17280
|
|
},
|
|
{
|
|
"entropy": 6.305694150924682,
|
|
"epoch": 1.7278452541610436,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047063964967666177,
|
|
"loss": 5.6451,
|
|
"mean_token_accuracy": 0.18360677510499954,
|
|
"num_tokens": 33795320.0,
|
|
"step": 17285
|
|
},
|
|
{
|
|
"entropy": 6.2895934104919435,
|
|
"epoch": 1.7283450792222723,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004706220197929449,
|
|
"loss": 5.72,
|
|
"mean_token_accuracy": 0.1918773740530014,
|
|
"num_tokens": 33805764.0,
|
|
"step": 17290
|
|
},
|
|
{
|
|
"entropy": 6.30126724243164,
|
|
"epoch": 1.7288449042835008,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004706043849874284,
|
|
"loss": 5.7465,
|
|
"mean_token_accuracy": 0.1761904999613762,
|
|
"num_tokens": 33816045.0,
|
|
"step": 17295
|
|
},
|
|
{
|
|
"entropy": 6.329774379730225,
|
|
"epoch": 1.7293447293447293,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047058674526055585,
|
|
"loss": 5.685,
|
|
"mean_token_accuracy": 0.1876777306199074,
|
|
"num_tokens": 33825192.0,
|
|
"step": 17300
|
|
},
|
|
{
|
|
"entropy": 6.258170413970947,
|
|
"epoch": 1.729844554405958,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047056910061277115,
|
|
"loss": 5.6969,
|
|
"mean_token_accuracy": 0.18592295348644255,
|
|
"num_tokens": 33835034.0,
|
|
"step": 17305
|
|
},
|
|
{
|
|
"entropy": 6.247967910766602,
|
|
"epoch": 1.7303443794671864,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004705514510445182,
|
|
"loss": 5.7259,
|
|
"mean_token_accuracy": 0.18162100315093993,
|
|
"num_tokens": 33845225.0,
|
|
"step": 17310
|
|
},
|
|
{
|
|
"entropy": 6.304800128936767,
|
|
"epoch": 1.730844204528415,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000470533796556241,
|
|
"loss": 5.7116,
|
|
"mean_token_accuracy": 0.18165984451770784,
|
|
"num_tokens": 33855303.0,
|
|
"step": 17315
|
|
},
|
|
{
|
|
"entropy": 6.284218263626099,
|
|
"epoch": 1.7313440295896436,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004705161371483839,
|
|
"loss": 5.6822,
|
|
"mean_token_accuracy": 0.1839149221777916,
|
|
"num_tokens": 33865336.0,
|
|
"step": 17320
|
|
},
|
|
{
|
|
"entropy": 6.308512878417969,
|
|
"epoch": 1.7318438546508723,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047049847282139095,
|
|
"loss": 5.7569,
|
|
"mean_token_accuracy": 0.17610084861516953,
|
|
"num_tokens": 33875707.0,
|
|
"step": 17325
|
|
},
|
|
{
|
|
"entropy": 6.346711730957031,
|
|
"epoch": 1.7323436797121008,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047048080357570685,
|
|
"loss": 5.793,
|
|
"mean_token_accuracy": 0.17951326072216034,
|
|
"num_tokens": 33886649.0,
|
|
"step": 17330
|
|
},
|
|
{
|
|
"entropy": 6.309351110458374,
|
|
"epoch": 1.7328435047733293,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000470463129411776,
|
|
"loss": 5.6985,
|
|
"mean_token_accuracy": 0.1880176454782486,
|
|
"num_tokens": 33896815.0,
|
|
"step": 17335
|
|
},
|
|
{
|
|
"entropy": 6.293674039840698,
|
|
"epoch": 1.733343329834558,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004704454503300431,
|
|
"loss": 5.6778,
|
|
"mean_token_accuracy": 0.18379359990358352,
|
|
"num_tokens": 33907481.0,
|
|
"step": 17340
|
|
},
|
|
{
|
|
"entropy": 6.285873126983643,
|
|
"epoch": 1.7338431548957864,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000470427766330953,
|
|
"loss": 5.6881,
|
|
"mean_token_accuracy": 0.18921777606010437,
|
|
"num_tokens": 33917011.0,
|
|
"step": 17345
|
|
},
|
|
{
|
|
"entropy": 6.078107023239136,
|
|
"epoch": 1.734342979957015,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004704100774149506,
|
|
"loss": 5.4367,
|
|
"mean_token_accuracy": 0.2089824289083481,
|
|
"num_tokens": 33926528.0,
|
|
"step": 17350
|
|
},
|
|
{
|
|
"entropy": 6.295071268081665,
|
|
"epoch": 1.7348428050182436,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00047039238358248086,
|
|
"loss": 5.7604,
|
|
"mean_token_accuracy": 0.17921016961336136,
|
|
"num_tokens": 33936207.0,
|
|
"step": 17355
|
|
},
|
|
{
|
|
"entropy": 6.261696720123291,
|
|
"epoch": 1.7353426300794723,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000470374684833989,
|
|
"loss": 5.7519,
|
|
"mean_token_accuracy": 0.18161948770284653,
|
|
"num_tokens": 33946632.0,
|
|
"step": 17360
|
|
},
|
|
{
|
|
"entropy": 6.316333150863647,
|
|
"epoch": 1.7358424551407008,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004703569811699205,
|
|
"loss": 5.7527,
|
|
"mean_token_accuracy": 0.1783376768231392,
|
|
"num_tokens": 33956469.0,
|
|
"step": 17365
|
|
},
|
|
{
|
|
"entropy": 6.288906812667847,
|
|
"epoch": 1.7363422802019293,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047033927259072046,
|
|
"loss": 5.6693,
|
|
"mean_token_accuracy": 0.18783483058214187,
|
|
"num_tokens": 33965699.0,
|
|
"step": 17370
|
|
},
|
|
{
|
|
"entropy": 6.225472784042358,
|
|
"epoch": 1.736842105263158,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047032155909683464,
|
|
"loss": 5.6245,
|
|
"mean_token_accuracy": 0.18819790631532668,
|
|
"num_tokens": 33975108.0,
|
|
"step": 17375
|
|
},
|
|
{
|
|
"entropy": 6.309022331237793,
|
|
"epoch": 1.7373419303243864,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004703038406887087,
|
|
"loss": 5.7601,
|
|
"mean_token_accuracy": 0.17357840836048127,
|
|
"num_tokens": 33986321.0,
|
|
"step": 17380
|
|
},
|
|
{
|
|
"entropy": 6.376512813568115,
|
|
"epoch": 1.737841755385615,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047028611736678837,
|
|
"loss": 5.7872,
|
|
"mean_token_accuracy": 0.16529452055692673,
|
|
"num_tokens": 33996038.0,
|
|
"step": 17385
|
|
},
|
|
{
|
|
"entropy": 6.249833488464356,
|
|
"epoch": 1.7383415804468436,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004702683891315196,
|
|
"loss": 5.6835,
|
|
"mean_token_accuracy": 0.1882496178150177,
|
|
"num_tokens": 34004773.0,
|
|
"step": 17390
|
|
},
|
|
{
|
|
"entropy": 6.287700462341308,
|
|
"epoch": 1.7388414055080723,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047025065598334834,
|
|
"loss": 5.6936,
|
|
"mean_token_accuracy": 0.1801225498318672,
|
|
"num_tokens": 34014249.0,
|
|
"step": 17395
|
|
},
|
|
{
|
|
"entropy": 6.34089732170105,
|
|
"epoch": 1.7393412305693008,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004702329179227208,
|
|
"loss": 5.7907,
|
|
"mean_token_accuracy": 0.17060537487268448,
|
|
"num_tokens": 34025553.0,
|
|
"step": 17400
|
|
},
|
|
{
|
|
"entropy": 6.312642812728882,
|
|
"epoch": 1.7398410556305293,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047021517495008335,
|
|
"loss": 5.7288,
|
|
"mean_token_accuracy": 0.18137481063604355,
|
|
"num_tokens": 34036536.0,
|
|
"step": 17405
|
|
},
|
|
{
|
|
"entropy": 6.29936203956604,
|
|
"epoch": 1.740340880691758,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047019742706588233,
|
|
"loss": 5.7095,
|
|
"mean_token_accuracy": 0.1836495131254196,
|
|
"num_tokens": 34046353.0,
|
|
"step": 17410
|
|
},
|
|
{
|
|
"entropy": 6.267517042160034,
|
|
"epoch": 1.7408407057529864,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004701796742705642,
|
|
"loss": 5.6102,
|
|
"mean_token_accuracy": 0.1973572000861168,
|
|
"num_tokens": 34056172.0,
|
|
"step": 17415
|
|
},
|
|
{
|
|
"entropy": 6.266970586776734,
|
|
"epoch": 1.741340530814215,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00047016191656457573,
|
|
"loss": 5.6444,
|
|
"mean_token_accuracy": 0.18569154143333436,
|
|
"num_tokens": 34066313.0,
|
|
"step": 17420
|
|
},
|
|
{
|
|
"entropy": 6.259730625152588,
|
|
"epoch": 1.7418403558754436,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047014415394836374,
|
|
"loss": 5.6584,
|
|
"mean_token_accuracy": 0.19026273488998413,
|
|
"num_tokens": 34075594.0,
|
|
"step": 17425
|
|
},
|
|
{
|
|
"entropy": 6.251816844940185,
|
|
"epoch": 1.7423401809366723,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004701263864223749,
|
|
"loss": 5.6688,
|
|
"mean_token_accuracy": 0.19045528024435043,
|
|
"num_tokens": 34085619.0,
|
|
"step": 17430
|
|
},
|
|
{
|
|
"entropy": 6.315893268585205,
|
|
"epoch": 1.7428400059979008,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004701086139870565,
|
|
"loss": 5.7216,
|
|
"mean_token_accuracy": 0.17693424373865127,
|
|
"num_tokens": 34094626.0,
|
|
"step": 17435
|
|
},
|
|
{
|
|
"entropy": 6.33891453742981,
|
|
"epoch": 1.7433398310591293,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004700908366428556,
|
|
"loss": 5.6841,
|
|
"mean_token_accuracy": 0.18001603037118913,
|
|
"num_tokens": 34104950.0,
|
|
"step": 17440
|
|
},
|
|
{
|
|
"entropy": 6.365847826004028,
|
|
"epoch": 1.743839656120358,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004700730543902194,
|
|
"loss": 5.8262,
|
|
"mean_token_accuracy": 0.175016550719738,
|
|
"num_tokens": 34114407.0,
|
|
"step": 17445
|
|
},
|
|
{
|
|
"entropy": 6.335444688796997,
|
|
"epoch": 1.7443394811815864,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00047005526722959537,
|
|
"loss": 5.7491,
|
|
"mean_token_accuracy": 0.17518844306468964,
|
|
"num_tokens": 34124842.0,
|
|
"step": 17450
|
|
},
|
|
{
|
|
"entropy": 6.297077608108521,
|
|
"epoch": 1.744839306242815,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047003747516143095,
|
|
"loss": 5.626,
|
|
"mean_token_accuracy": 0.1963572233915329,
|
|
"num_tokens": 34134265.0,
|
|
"step": 17455
|
|
},
|
|
{
|
|
"entropy": 6.301560401916504,
|
|
"epoch": 1.7453391313040436,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00047001967818617385,
|
|
"loss": 5.7283,
|
|
"mean_token_accuracy": 0.1762249290943146,
|
|
"num_tokens": 34143915.0,
|
|
"step": 17460
|
|
},
|
|
{
|
|
"entropy": 6.291181421279907,
|
|
"epoch": 1.7458389563652723,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004700018763042719,
|
|
"loss": 5.6995,
|
|
"mean_token_accuracy": 0.18996072709560394,
|
|
"num_tokens": 34154869.0,
|
|
"step": 17465
|
|
},
|
|
{
|
|
"entropy": 6.259565019607544,
|
|
"epoch": 1.7463387814265006,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004699840695161728,
|
|
"loss": 5.6219,
|
|
"mean_token_accuracy": 0.19015975892543793,
|
|
"num_tokens": 34164494.0,
|
|
"step": 17470
|
|
},
|
|
{
|
|
"entropy": 6.280099773406983,
|
|
"epoch": 1.7468386064877293,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004699662578223248,
|
|
"loss": 5.6799,
|
|
"mean_token_accuracy": 0.1801822677254677,
|
|
"num_tokens": 34173986.0,
|
|
"step": 17475
|
|
},
|
|
{
|
|
"entropy": 6.416690397262573,
|
|
"epoch": 1.747338431548958,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046994844122317587,
|
|
"loss": 5.9156,
|
|
"mean_token_accuracy": 0.1669814556837082,
|
|
"num_tokens": 34183129.0,
|
|
"step": 17480
|
|
},
|
|
{
|
|
"entropy": 6.247329187393189,
|
|
"epoch": 1.7478382566101864,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00046993061971917433,
|
|
"loss": 5.6559,
|
|
"mean_token_accuracy": 0.18423862457275392,
|
|
"num_tokens": 34192559.0,
|
|
"step": 17485
|
|
},
|
|
{
|
|
"entropy": 6.306975603103638,
|
|
"epoch": 1.748338081671415,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046991279331076865,
|
|
"loss": 5.7266,
|
|
"mean_token_accuracy": 0.18176641464233398,
|
|
"num_tokens": 34202599.0,
|
|
"step": 17490
|
|
},
|
|
{
|
|
"entropy": 6.346726942062378,
|
|
"epoch": 1.7488379067326436,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004698949619984071,
|
|
"loss": 5.769,
|
|
"mean_token_accuracy": 0.17250953167676925,
|
|
"num_tokens": 34212883.0,
|
|
"step": 17495
|
|
},
|
|
{
|
|
"entropy": 6.239811897277832,
|
|
"epoch": 1.7493377317938723,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004698771257825385,
|
|
"loss": 5.6811,
|
|
"mean_token_accuracy": 0.19192008972167968,
|
|
"num_tokens": 34222019.0,
|
|
"step": 17500
|
|
},
|
|
{
|
|
"entropy": 6.232729387283325,
|
|
"epoch": 1.7498375568551006,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004698592846636116,
|
|
"loss": 5.6262,
|
|
"mean_token_accuracy": 0.19030729830265045,
|
|
"num_tokens": 34231817.0,
|
|
"step": 17505
|
|
},
|
|
{
|
|
"entropy": 6.323407316207886,
|
|
"epoch": 1.7503373819163293,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004698414386420752,
|
|
"loss": 5.7046,
|
|
"mean_token_accuracy": 0.1848825052380562,
|
|
"num_tokens": 34242035.0,
|
|
"step": 17510
|
|
},
|
|
{
|
|
"entropy": 6.287502193450928,
|
|
"epoch": 1.750837206977558,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004698235877183784,
|
|
"loss": 5.699,
|
|
"mean_token_accuracy": 0.183151076734066,
|
|
"num_tokens": 34251728.0,
|
|
"step": 17515
|
|
},
|
|
{
|
|
"entropy": 6.25726284980774,
|
|
"epoch": 1.7513370320387864,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046980573189297017,
|
|
"loss": 5.7261,
|
|
"mean_token_accuracy": 0.17788038700819014,
|
|
"num_tokens": 34262036.0,
|
|
"step": 17520
|
|
},
|
|
{
|
|
"entropy": 6.27021975517273,
|
|
"epoch": 1.751836857100015,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004697878711662999,
|
|
"loss": 5.7174,
|
|
"mean_token_accuracy": 0.18198858350515365,
|
|
"num_tokens": 34272335.0,
|
|
"step": 17525
|
|
},
|
|
{
|
|
"entropy": 6.358492183685303,
|
|
"epoch": 1.7523366821612436,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00046977000553881696,
|
|
"loss": 5.7181,
|
|
"mean_token_accuracy": 0.17103411853313447,
|
|
"num_tokens": 34282931.0,
|
|
"step": 17530
|
|
},
|
|
{
|
|
"entropy": 6.332013463973999,
|
|
"epoch": 1.752836507222472,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046975213501097076,
|
|
"loss": 5.6669,
|
|
"mean_token_accuracy": 0.18624796867370605,
|
|
"num_tokens": 34293716.0,
|
|
"step": 17535
|
|
},
|
|
{
|
|
"entropy": 6.316254568099976,
|
|
"epoch": 1.7533363322837006,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004697342595832109,
|
|
"loss": 5.7916,
|
|
"mean_token_accuracy": 0.17503857016563415,
|
|
"num_tokens": 34303411.0,
|
|
"step": 17540
|
|
},
|
|
{
|
|
"entropy": 6.338593769073486,
|
|
"epoch": 1.7538361573449293,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046971637925598725,
|
|
"loss": 5.6921,
|
|
"mean_token_accuracy": 0.17753490358591079,
|
|
"num_tokens": 34313092.0,
|
|
"step": 17545
|
|
},
|
|
{
|
|
"entropy": 6.251081418991089,
|
|
"epoch": 1.754335982406158,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004696984940297496,
|
|
"loss": 5.6436,
|
|
"mean_token_accuracy": 0.1890241965651512,
|
|
"num_tokens": 34321909.0,
|
|
"step": 17550
|
|
},
|
|
{
|
|
"entropy": 6.333289337158203,
|
|
"epoch": 1.7548358074673864,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000469680603904948,
|
|
"loss": 5.8073,
|
|
"mean_token_accuracy": 0.17246865332126618,
|
|
"num_tokens": 34330213.0,
|
|
"step": 17555
|
|
},
|
|
{
|
|
"entropy": 6.351892185211182,
|
|
"epoch": 1.755335632528615,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046966270888203237,
|
|
"loss": 5.7323,
|
|
"mean_token_accuracy": 0.17856392711400987,
|
|
"num_tokens": 34339731.0,
|
|
"step": 17560
|
|
},
|
|
{
|
|
"entropy": 6.231314992904663,
|
|
"epoch": 1.7558354575898436,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004696448089614532,
|
|
"loss": 5.6351,
|
|
"mean_token_accuracy": 0.18533465564250945,
|
|
"num_tokens": 34348620.0,
|
|
"step": 17565
|
|
},
|
|
{
|
|
"entropy": 6.234904527664185,
|
|
"epoch": 1.756335282651072,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004696269041436606,
|
|
"loss": 5.6263,
|
|
"mean_token_accuracy": 0.190339195728302,
|
|
"num_tokens": 34358292.0,
|
|
"step": 17570
|
|
},
|
|
{
|
|
"entropy": 6.29240083694458,
|
|
"epoch": 1.7568351077123006,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004696089944291052,
|
|
"loss": 5.7378,
|
|
"mean_token_accuracy": 0.1821004793047905,
|
|
"num_tokens": 34367379.0,
|
|
"step": 17575
|
|
},
|
|
{
|
|
"entropy": 6.340983963012695,
|
|
"epoch": 1.7573349327735293,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004695910798182377,
|
|
"loss": 5.7475,
|
|
"mean_token_accuracy": 0.17353577464818953,
|
|
"num_tokens": 34376422.0,
|
|
"step": 17580
|
|
},
|
|
{
|
|
"entropy": 6.302516508102417,
|
|
"epoch": 1.757834757834758,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004695731603115086,
|
|
"loss": 5.7466,
|
|
"mean_token_accuracy": 0.18470296114683152,
|
|
"num_tokens": 34386509.0,
|
|
"step": 17585
|
|
},
|
|
{
|
|
"entropy": 6.305944728851318,
|
|
"epoch": 1.7583345828959864,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00046955523590936884,
|
|
"loss": 5.7728,
|
|
"mean_token_accuracy": 0.17437458485364915,
|
|
"num_tokens": 34396070.0,
|
|
"step": 17590
|
|
},
|
|
{
|
|
"entropy": 6.301299047470093,
|
|
"epoch": 1.758834407957215,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004695373066122694,
|
|
"loss": 5.7018,
|
|
"mean_token_accuracy": 0.17779178470373153,
|
|
"num_tokens": 34405707.0,
|
|
"step": 17595
|
|
},
|
|
{
|
|
"entropy": 6.286515569686889,
|
|
"epoch": 1.7593342330184436,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004695193724206615,
|
|
"loss": 5.7017,
|
|
"mean_token_accuracy": 0.18503737598657607,
|
|
"num_tokens": 34415621.0,
|
|
"step": 17600
|
|
},
|
|
{
|
|
"entropy": 6.348013782501221,
|
|
"epoch": 1.759834058079672,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046950143333499613,
|
|
"loss": 5.7488,
|
|
"mean_token_accuracy": 0.17963546216487886,
|
|
"num_tokens": 34425115.0,
|
|
"step": 17605
|
|
},
|
|
{
|
|
"entropy": 6.316310787200928,
|
|
"epoch": 1.7603338831409006,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00046948348935572476,
|
|
"loss": 5.7454,
|
|
"mean_token_accuracy": 0.17767828553915024,
|
|
"num_tokens": 34434164.0,
|
|
"step": 17610
|
|
},
|
|
{
|
|
"entropy": 6.233690595626831,
|
|
"epoch": 1.7608337082021293,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004694655404832988,
|
|
"loss": 5.591,
|
|
"mean_token_accuracy": 0.1912773922085762,
|
|
"num_tokens": 34443620.0,
|
|
"step": 17615
|
|
},
|
|
{
|
|
"entropy": 6.306690359115601,
|
|
"epoch": 1.761333533263358,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00046944758671817,
|
|
"loss": 5.6881,
|
|
"mean_token_accuracy": 0.1802062213420868,
|
|
"num_tokens": 34452831.0,
|
|
"step": 17620
|
|
},
|
|
{
|
|
"entropy": 6.253866910934448,
|
|
"epoch": 1.7618333583245864,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004694296280607899,
|
|
"loss": 5.5746,
|
|
"mean_token_accuracy": 0.1891826346516609,
|
|
"num_tokens": 34462484.0,
|
|
"step": 17625
|
|
},
|
|
{
|
|
"entropy": 6.18457727432251,
|
|
"epoch": 1.762333183385815,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004694116645116104,
|
|
"loss": 5.6343,
|
|
"mean_token_accuracy": 0.19356480091810227,
|
|
"num_tokens": 34471546.0,
|
|
"step": 17630
|
|
},
|
|
{
|
|
"entropy": 6.280801296234131,
|
|
"epoch": 1.7628330084470436,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004693936960710834,
|
|
"loss": 5.7367,
|
|
"mean_token_accuracy": 0.18373825550079345,
|
|
"num_tokens": 34482384.0,
|
|
"step": 17635
|
|
},
|
|
{
|
|
"entropy": 6.266839838027954,
|
|
"epoch": 1.763332833508272,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046937572273966104,
|
|
"loss": 5.567,
|
|
"mean_token_accuracy": 0.19869975447654725,
|
|
"num_tokens": 34491897.0,
|
|
"step": 17640
|
|
},
|
|
{
|
|
"entropy": 6.287574672698975,
|
|
"epoch": 1.7638326585695006,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00046935774451779556,
|
|
"loss": 5.6848,
|
|
"mean_token_accuracy": 0.17779678255319595,
|
|
"num_tokens": 34501709.0,
|
|
"step": 17645
|
|
},
|
|
{
|
|
"entropy": 6.256862926483154,
|
|
"epoch": 1.7643324836307293,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004693397614059392,
|
|
"loss": 5.6206,
|
|
"mean_token_accuracy": 0.1883917674422264,
|
|
"num_tokens": 34510560.0,
|
|
"step": 17650
|
|
},
|
|
{
|
|
"entropy": 6.258419322967529,
|
|
"epoch": 1.764832308691958,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004693217734045445,
|
|
"loss": 5.7056,
|
|
"mean_token_accuracy": 0.17872990518808365,
|
|
"num_tokens": 34519363.0,
|
|
"step": 17655
|
|
},
|
|
{
|
|
"entropy": 6.250803375244141,
|
|
"epoch": 1.7653321337531864,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00046930378051406393,
|
|
"loss": 5.6733,
|
|
"mean_token_accuracy": 0.18730759918689727,
|
|
"num_tokens": 34530335.0,
|
|
"step": 17660
|
|
},
|
|
{
|
|
"entropy": 6.248498916625977,
|
|
"epoch": 1.765831958814415,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046928578273495026,
|
|
"loss": 5.6113,
|
|
"mean_token_accuracy": 0.18894475251436232,
|
|
"num_tokens": 34540603.0,
|
|
"step": 17665
|
|
},
|
|
{
|
|
"entropy": 6.26874270439148,
|
|
"epoch": 1.7663317838756436,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004692677800676563,
|
|
"loss": 5.626,
|
|
"mean_token_accuracy": 0.19217611849308014,
|
|
"num_tokens": 34550765.0,
|
|
"step": 17670
|
|
},
|
|
{
|
|
"entropy": 6.312981176376343,
|
|
"epoch": 1.766831608936872,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00046924977251263495,
|
|
"loss": 5.6571,
|
|
"mean_token_accuracy": 0.18669699132442474,
|
|
"num_tokens": 34560330.0,
|
|
"step": 17675
|
|
},
|
|
{
|
|
"entropy": 6.26354751586914,
|
|
"epoch": 1.7673314339981006,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046923176007033937,
|
|
"loss": 5.6886,
|
|
"mean_token_accuracy": 0.18526094704866408,
|
|
"num_tokens": 34569356.0,
|
|
"step": 17680
|
|
},
|
|
{
|
|
"entropy": 6.222706079483032,
|
|
"epoch": 1.7678312590593293,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046921374274122265,
|
|
"loss": 5.6582,
|
|
"mean_token_accuracy": 0.18519156724214553,
|
|
"num_tokens": 34578613.0,
|
|
"step": 17685
|
|
},
|
|
{
|
|
"entropy": 6.186944437026978,
|
|
"epoch": 1.768331084120558,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046919572052573814,
|
|
"loss": 5.5644,
|
|
"mean_token_accuracy": 0.19506643563508988,
|
|
"num_tokens": 34587394.0,
|
|
"step": 17690
|
|
},
|
|
{
|
|
"entropy": 6.203925848007202,
|
|
"epoch": 1.7688309091817864,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046917769342433925,
|
|
"loss": 5.6151,
|
|
"mean_token_accuracy": 0.20106736272573472,
|
|
"num_tokens": 34598707.0,
|
|
"step": 17695
|
|
},
|
|
{
|
|
"entropy": 6.311947584152222,
|
|
"epoch": 1.769330734243015,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004691596614374796,
|
|
"loss": 5.7298,
|
|
"mean_token_accuracy": 0.17767031043767928,
|
|
"num_tokens": 34608270.0,
|
|
"step": 17700
|
|
},
|
|
{
|
|
"entropy": 6.29536623954773,
|
|
"epoch": 1.7698305593042436,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004691416245656128,
|
|
"loss": 5.7185,
|
|
"mean_token_accuracy": 0.18451306819915772,
|
|
"num_tokens": 34618533.0,
|
|
"step": 17705
|
|
},
|
|
{
|
|
"entropy": 6.285868358612061,
|
|
"epoch": 1.770330384365472,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046912358280919267,
|
|
"loss": 5.7737,
|
|
"mean_token_accuracy": 0.17638520747423173,
|
|
"num_tokens": 34628158.0,
|
|
"step": 17710
|
|
},
|
|
{
|
|
"entropy": 6.269874429702758,
|
|
"epoch": 1.7708302094267006,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046910553616867314,
|
|
"loss": 5.6417,
|
|
"mean_token_accuracy": 0.1881925195455551,
|
|
"num_tokens": 34638046.0,
|
|
"step": 17715
|
|
},
|
|
{
|
|
"entropy": 6.284053707122803,
|
|
"epoch": 1.7713300344879293,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004690874846445083,
|
|
"loss": 5.7416,
|
|
"mean_token_accuracy": 0.17439831793308258,
|
|
"num_tokens": 34647847.0,
|
|
"step": 17720
|
|
},
|
|
{
|
|
"entropy": 6.298317861557007,
|
|
"epoch": 1.771829859549158,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004690694282371523,
|
|
"loss": 5.6377,
|
|
"mean_token_accuracy": 0.18452051728963853,
|
|
"num_tokens": 34658830.0,
|
|
"step": 17725
|
|
},
|
|
{
|
|
"entropy": 6.237199306488037,
|
|
"epoch": 1.7723296846103862,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004690513669470594,
|
|
"loss": 5.6278,
|
|
"mean_token_accuracy": 0.19321763813495635,
|
|
"num_tokens": 34668679.0,
|
|
"step": 17730
|
|
},
|
|
{
|
|
"entropy": 6.274099206924438,
|
|
"epoch": 1.772829509671615,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000469033300774684,
|
|
"loss": 5.6825,
|
|
"mean_token_accuracy": 0.18412975817918778,
|
|
"num_tokens": 34678443.0,
|
|
"step": 17735
|
|
},
|
|
{
|
|
"entropy": 6.287502002716065,
|
|
"epoch": 1.7733293347328436,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004690152297204808,
|
|
"loss": 5.701,
|
|
"mean_token_accuracy": 0.1827107459306717,
|
|
"num_tokens": 34688348.0,
|
|
"step": 17740
|
|
},
|
|
{
|
|
"entropy": 6.023687362670898,
|
|
"epoch": 1.773829159794072,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046899715378490427,
|
|
"loss": 5.386,
|
|
"mean_token_accuracy": 0.2096478074789047,
|
|
"num_tokens": 34698402.0,
|
|
"step": 17745
|
|
},
|
|
{
|
|
"entropy": 6.225782823562622,
|
|
"epoch": 1.7743289848553006,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046897907296840927,
|
|
"loss": 5.6539,
|
|
"mean_token_accuracy": 0.18930648863315583,
|
|
"num_tokens": 34707761.0,
|
|
"step": 17750
|
|
},
|
|
{
|
|
"entropy": 6.28306097984314,
|
|
"epoch": 1.7748288099165292,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004689609872714507,
|
|
"loss": 5.7616,
|
|
"mean_token_accuracy": 0.17853187769651413,
|
|
"num_tokens": 34717934.0,
|
|
"step": 17755
|
|
},
|
|
{
|
|
"entropy": 6.359382295608521,
|
|
"epoch": 1.775328634977758,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046894289669448366,
|
|
"loss": 5.7674,
|
|
"mean_token_accuracy": 0.17791376113891602,
|
|
"num_tokens": 34727486.0,
|
|
"step": 17760
|
|
},
|
|
{
|
|
"entropy": 6.315619087219238,
|
|
"epoch": 1.7758284600389862,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046892480123796314,
|
|
"loss": 5.6539,
|
|
"mean_token_accuracy": 0.18840387016534804,
|
|
"num_tokens": 34738080.0,
|
|
"step": 17765
|
|
},
|
|
{
|
|
"entropy": 6.2763511657714846,
|
|
"epoch": 1.776328285100215,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004689067009023446,
|
|
"loss": 5.7268,
|
|
"mean_token_accuracy": 0.18260511606931687,
|
|
"num_tokens": 34747595.0,
|
|
"step": 17770
|
|
},
|
|
{
|
|
"entropy": 6.217519330978393,
|
|
"epoch": 1.7768281101614436,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004688885956880834,
|
|
"loss": 5.5574,
|
|
"mean_token_accuracy": 0.19334616363048554,
|
|
"num_tokens": 34756818.0,
|
|
"step": 17775
|
|
},
|
|
{
|
|
"entropy": 6.192587661743164,
|
|
"epoch": 1.777327935222672,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004688704855956349,
|
|
"loss": 5.6287,
|
|
"mean_token_accuracy": 0.19062644094228745,
|
|
"num_tokens": 34767263.0,
|
|
"step": 17780
|
|
},
|
|
{
|
|
"entropy": 6.320554447174072,
|
|
"epoch": 1.7778277602839005,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046885237062545493,
|
|
"loss": 5.7278,
|
|
"mean_token_accuracy": 0.1795194774866104,
|
|
"num_tokens": 34776767.0,
|
|
"step": 17785
|
|
},
|
|
{
|
|
"entropy": 6.273306512832642,
|
|
"epoch": 1.7783275853451292,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046883425077799923,
|
|
"loss": 5.6308,
|
|
"mean_token_accuracy": 0.1899044021964073,
|
|
"num_tokens": 34787587.0,
|
|
"step": 17790
|
|
},
|
|
{
|
|
"entropy": 6.277393579483032,
|
|
"epoch": 1.7788274104063577,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004688161260537236,
|
|
"loss": 5.7233,
|
|
"mean_token_accuracy": 0.17846356183290482,
|
|
"num_tokens": 34798586.0,
|
|
"step": 17795
|
|
},
|
|
{
|
|
"entropy": 6.3168529033660885,
|
|
"epoch": 1.7793272354675862,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004687979964530842,
|
|
"loss": 5.6768,
|
|
"mean_token_accuracy": 0.1833574429154396,
|
|
"num_tokens": 34808469.0,
|
|
"step": 17800
|
|
},
|
|
{
|
|
"entropy": 6.292975330352784,
|
|
"epoch": 1.779827060528815,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000468779861976537,
|
|
"loss": 5.6485,
|
|
"mean_token_accuracy": 0.19143728613853456,
|
|
"num_tokens": 34817933.0,
|
|
"step": 17805
|
|
},
|
|
{
|
|
"entropy": 6.216028451919556,
|
|
"epoch": 1.7803268855900436,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046876172262453843,
|
|
"loss": 5.6164,
|
|
"mean_token_accuracy": 0.1868711605668068,
|
|
"num_tokens": 34827370.0,
|
|
"step": 17810
|
|
},
|
|
{
|
|
"entropy": 6.288786458969116,
|
|
"epoch": 1.780826710651272,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046874357839754463,
|
|
"loss": 5.6986,
|
|
"mean_token_accuracy": 0.18303592056035994,
|
|
"num_tokens": 34835521.0,
|
|
"step": 17815
|
|
},
|
|
{
|
|
"entropy": 6.3622904300689695,
|
|
"epoch": 1.7813265357125005,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046872542929601234,
|
|
"loss": 5.7846,
|
|
"mean_token_accuracy": 0.18383541703224182,
|
|
"num_tokens": 34846151.0,
|
|
"step": 17820
|
|
},
|
|
{
|
|
"entropy": 6.242295980453491,
|
|
"epoch": 1.7818263607737292,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046870727532039816,
|
|
"loss": 5.6234,
|
|
"mean_token_accuracy": 0.1871954694390297,
|
|
"num_tokens": 34855536.0,
|
|
"step": 17825
|
|
},
|
|
{
|
|
"entropy": 6.248191785812378,
|
|
"epoch": 1.7823261858349577,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004686891164711586,
|
|
"loss": 5.6547,
|
|
"mean_token_accuracy": 0.18848408609628678,
|
|
"num_tokens": 34865428.0,
|
|
"step": 17830
|
|
},
|
|
{
|
|
"entropy": 6.251362752914429,
|
|
"epoch": 1.7828260108961862,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00046867095274875085,
|
|
"loss": 5.6336,
|
|
"mean_token_accuracy": 0.18266007900238038,
|
|
"num_tokens": 34875273.0,
|
|
"step": 17835
|
|
},
|
|
{
|
|
"entropy": 6.246617317199707,
|
|
"epoch": 1.783325835957415,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046865278415363174,
|
|
"loss": 5.7122,
|
|
"mean_token_accuracy": 0.1795117199420929,
|
|
"num_tokens": 34885438.0,
|
|
"step": 17840
|
|
},
|
|
{
|
|
"entropy": 6.3378438472747805,
|
|
"epoch": 1.7838256610186436,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004686346106862584,
|
|
"loss": 5.7484,
|
|
"mean_token_accuracy": 0.17730722576379776,
|
|
"num_tokens": 34895245.0,
|
|
"step": 17845
|
|
},
|
|
{
|
|
"entropy": 6.29679012298584,
|
|
"epoch": 1.784325486079872,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004686164323470881,
|
|
"loss": 5.5965,
|
|
"mean_token_accuracy": 0.19442152678966523,
|
|
"num_tokens": 34905028.0,
|
|
"step": 17850
|
|
},
|
|
{
|
|
"entropy": 6.286964845657349,
|
|
"epoch": 1.7848253111411005,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004685982491365781,
|
|
"loss": 5.7419,
|
|
"mean_token_accuracy": 0.1862476199865341,
|
|
"num_tokens": 34915756.0,
|
|
"step": 17855
|
|
},
|
|
{
|
|
"entropy": 6.2940772533416744,
|
|
"epoch": 1.7853251362023292,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046858006105518615,
|
|
"loss": 5.698,
|
|
"mean_token_accuracy": 0.17972381114959718,
|
|
"num_tokens": 34925369.0,
|
|
"step": 17860
|
|
},
|
|
{
|
|
"entropy": 6.303058385848999,
|
|
"epoch": 1.7858249612635577,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004685618681033695,
|
|
"loss": 5.7351,
|
|
"mean_token_accuracy": 0.17690120190382003,
|
|
"num_tokens": 34935693.0,
|
|
"step": 17865
|
|
},
|
|
{
|
|
"entropy": 6.269779205322266,
|
|
"epoch": 1.7863247863247862,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004685436702815861,
|
|
"loss": 5.7324,
|
|
"mean_token_accuracy": 0.18123798072338104,
|
|
"num_tokens": 34944582.0,
|
|
"step": 17870
|
|
},
|
|
{
|
|
"entropy": 6.2960411548614506,
|
|
"epoch": 1.786824611386015,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004685254675902938,
|
|
"loss": 5.6935,
|
|
"mean_token_accuracy": 0.18080695122480392,
|
|
"num_tokens": 34953762.0,
|
|
"step": 17875
|
|
},
|
|
{
|
|
"entropy": 6.343185234069824,
|
|
"epoch": 1.7873244364472436,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004685072600299505,
|
|
"loss": 5.6438,
|
|
"mean_token_accuracy": 0.18965058624744416,
|
|
"num_tokens": 34963003.0,
|
|
"step": 17880
|
|
},
|
|
{
|
|
"entropy": 6.262334871292114,
|
|
"epoch": 1.787824261508472,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004684890476010144,
|
|
"loss": 5.6926,
|
|
"mean_token_accuracy": 0.18148817569017411,
|
|
"num_tokens": 34972968.0,
|
|
"step": 17885
|
|
},
|
|
{
|
|
"entropy": 6.302862358093262,
|
|
"epoch": 1.7883240865697005,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004684708303039435,
|
|
"loss": 5.7311,
|
|
"mean_token_accuracy": 0.18991549909114838,
|
|
"num_tokens": 34983050.0,
|
|
"step": 17890
|
|
},
|
|
{
|
|
"entropy": 6.370472002029419,
|
|
"epoch": 1.7888239116309292,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00046845260813919645,
|
|
"loss": 5.7178,
|
|
"mean_token_accuracy": 0.1812927395105362,
|
|
"num_tokens": 34992192.0,
|
|
"step": 17895
|
|
},
|
|
{
|
|
"entropy": 6.276365852355957,
|
|
"epoch": 1.7893237366921577,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046843438110723143,
|
|
"loss": 5.6538,
|
|
"mean_token_accuracy": 0.18420782387256623,
|
|
"num_tokens": 35001135.0,
|
|
"step": 17900
|
|
},
|
|
{
|
|
"entropy": 6.232102632522583,
|
|
"epoch": 1.7898235617533862,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.00046841614920850724,
|
|
"loss": 5.5707,
|
|
"mean_token_accuracy": 0.19542672783136367,
|
|
"num_tokens": 35011389.0,
|
|
"step": 17905
|
|
},
|
|
{
|
|
"entropy": 6.315951538085938,
|
|
"epoch": 1.790323386814615,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046839791244348243,
|
|
"loss": 5.7621,
|
|
"mean_token_accuracy": 0.18132130950689315,
|
|
"num_tokens": 35021752.0,
|
|
"step": 17910
|
|
},
|
|
{
|
|
"entropy": 6.251948118209839,
|
|
"epoch": 1.7908232118758436,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00046837967081261606,
|
|
"loss": 5.6741,
|
|
"mean_token_accuracy": 0.18420567214488984,
|
|
"num_tokens": 35031878.0,
|
|
"step": 17915
|
|
},
|
|
{
|
|
"entropy": 6.23393406867981,
|
|
"epoch": 1.791323036937072,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004683614243163668,
|
|
"loss": 5.6043,
|
|
"mean_token_accuracy": 0.19250608533620833,
|
|
"num_tokens": 35040995.0,
|
|
"step": 17920
|
|
},
|
|
{
|
|
"entropy": 6.2367338180542,
|
|
"epoch": 1.7918228619983005,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004683431729551939,
|
|
"loss": 5.6457,
|
|
"mean_token_accuracy": 0.19055599123239517,
|
|
"num_tokens": 35050680.0,
|
|
"step": 17925
|
|
},
|
|
{
|
|
"entropy": 6.232040119171143,
|
|
"epoch": 1.7923226870595292,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004683249167295565,
|
|
"loss": 5.6561,
|
|
"mean_token_accuracy": 0.18732904344797136,
|
|
"num_tokens": 35059910.0,
|
|
"step": 17930
|
|
},
|
|
{
|
|
"entropy": 6.218836259841919,
|
|
"epoch": 1.7928225121207577,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000468306655639914,
|
|
"loss": 5.6081,
|
|
"mean_token_accuracy": 0.19485781490802764,
|
|
"num_tokens": 35069711.0,
|
|
"step": 17935
|
|
},
|
|
{
|
|
"entropy": 6.304515933990478,
|
|
"epoch": 1.7933223371819862,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004682883896867257,
|
|
"loss": 5.7075,
|
|
"mean_token_accuracy": 0.18112001419067383,
|
|
"num_tokens": 35078711.0,
|
|
"step": 17940
|
|
},
|
|
{
|
|
"entropy": 6.270399284362793,
|
|
"epoch": 1.793822162243215,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004682701188704513,
|
|
"loss": 5.7067,
|
|
"mean_token_accuracy": 0.1854171097278595,
|
|
"num_tokens": 35087632.0,
|
|
"step": 17945
|
|
},
|
|
{
|
|
"entropy": 6.260859441757202,
|
|
"epoch": 1.7943219873044436,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004682518431915505,
|
|
"loss": 5.6775,
|
|
"mean_token_accuracy": 0.18419694453477858,
|
|
"num_tokens": 35097257.0,
|
|
"step": 17950
|
|
},
|
|
{
|
|
"entropy": 6.253331708908081,
|
|
"epoch": 1.794821812365672,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046823356265048293,
|
|
"loss": 5.6416,
|
|
"mean_token_accuracy": 0.1956460803747177,
|
|
"num_tokens": 35107734.0,
|
|
"step": 17955
|
|
},
|
|
{
|
|
"entropy": 6.291684818267822,
|
|
"epoch": 1.7953216374269005,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004682152772477087,
|
|
"loss": 5.6691,
|
|
"mean_token_accuracy": 0.18845112025737762,
|
|
"num_tokens": 35117052.0,
|
|
"step": 17960
|
|
},
|
|
{
|
|
"entropy": 6.2805602073669435,
|
|
"epoch": 1.7958214624881292,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046819698698368785,
|
|
"loss": 5.686,
|
|
"mean_token_accuracy": 0.18143279403448104,
|
|
"num_tokens": 35127345.0,
|
|
"step": 17965
|
|
},
|
|
{
|
|
"entropy": 6.244322824478149,
|
|
"epoch": 1.7963212875493577,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046817869185888044,
|
|
"loss": 5.6169,
|
|
"mean_token_accuracy": 0.1861143708229065,
|
|
"num_tokens": 35137216.0,
|
|
"step": 17970
|
|
},
|
|
{
|
|
"entropy": 6.288218784332275,
|
|
"epoch": 1.7968211126105862,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004681603918737469,
|
|
"loss": 5.7162,
|
|
"mean_token_accuracy": 0.19053661972284316,
|
|
"num_tokens": 35146433.0,
|
|
"step": 17975
|
|
},
|
|
{
|
|
"entropy": 6.280591297149658,
|
|
"epoch": 1.7973209376718149,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046814208702874766,
|
|
"loss": 5.7142,
|
|
"mean_token_accuracy": 0.1805400460958481,
|
|
"num_tokens": 35155841.0,
|
|
"step": 17980
|
|
},
|
|
{
|
|
"entropy": 6.277318668365479,
|
|
"epoch": 1.7978207627330436,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046812377732434316,
|
|
"loss": 5.7527,
|
|
"mean_token_accuracy": 0.18027301728725434,
|
|
"num_tokens": 35165962.0,
|
|
"step": 17985
|
|
},
|
|
{
|
|
"entropy": 6.331356573104858,
|
|
"epoch": 1.7983205877942718,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046810546276099415,
|
|
"loss": 5.7213,
|
|
"mean_token_accuracy": 0.17875098437070847,
|
|
"num_tokens": 35175887.0,
|
|
"step": 17990
|
|
},
|
|
{
|
|
"entropy": 6.34421706199646,
|
|
"epoch": 1.7988204128555005,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004680871433391613,
|
|
"loss": 5.7154,
|
|
"mean_token_accuracy": 0.18464528620243073,
|
|
"num_tokens": 35185763.0,
|
|
"step": 17995
|
|
},
|
|
{
|
|
"entropy": 6.278444290161133,
|
|
"epoch": 1.7993202379167292,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046806881905930565,
|
|
"loss": 5.685,
|
|
"mean_token_accuracy": 0.1887924388051033,
|
|
"num_tokens": 35195452.0,
|
|
"step": 18000
|
|
},
|
|
{
|
|
"epoch": 1.7993202379167292,
|
|
"eval_entropy": 5.984952585809595,
|
|
"eval_loss": 5.720641613006592,
|
|
"eval_mean_token_accuracy": 0.19168390800633617,
|
|
"eval_num_tokens": 35195452.0,
|
|
"eval_runtime": 18.4429,
|
|
"eval_samples_per_second": 1683.305,
|
|
"eval_steps_per_second": 210.434,
|
|
"step": 18000
|
|
},
|
|
{
|
|
"entropy": 6.279402542114258,
|
|
"epoch": 1.7998200629779577,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046805048992188823,
|
|
"loss": 5.7182,
|
|
"mean_token_accuracy": 0.17866053730249404,
|
|
"num_tokens": 35205261.0,
|
|
"step": 18005
|
|
},
|
|
{
|
|
"entropy": 6.259926652908325,
|
|
"epoch": 1.8003198880391862,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046803215592737014,
|
|
"loss": 5.6996,
|
|
"mean_token_accuracy": 0.18275742679834367,
|
|
"num_tokens": 35214965.0,
|
|
"step": 18010
|
|
},
|
|
{
|
|
"entropy": 6.278678512573242,
|
|
"epoch": 1.8008197131004149,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046801381707621266,
|
|
"loss": 5.65,
|
|
"mean_token_accuracy": 0.18730299025774003,
|
|
"num_tokens": 35224371.0,
|
|
"step": 18015
|
|
},
|
|
{
|
|
"entropy": 6.181397390365601,
|
|
"epoch": 1.8013195381616436,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00046799547336887727,
|
|
"loss": 5.5919,
|
|
"mean_token_accuracy": 0.19935844093561172,
|
|
"num_tokens": 35234282.0,
|
|
"step": 18020
|
|
},
|
|
{
|
|
"entropy": 6.283225107192993,
|
|
"epoch": 1.8018193632228718,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004679771248058254,
|
|
"loss": 5.6238,
|
|
"mean_token_accuracy": 0.19509967267513276,
|
|
"num_tokens": 35243112.0,
|
|
"step": 18025
|
|
},
|
|
{
|
|
"entropy": 6.27493953704834,
|
|
"epoch": 1.8023191882841005,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004679587713875187,
|
|
"loss": 5.6545,
|
|
"mean_token_accuracy": 0.1759701266884804,
|
|
"num_tokens": 35253398.0,
|
|
"step": 18030
|
|
},
|
|
{
|
|
"entropy": 6.248467969894409,
|
|
"epoch": 1.8028190133453292,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000467940413114419,
|
|
"loss": 5.6229,
|
|
"mean_token_accuracy": 0.1850960373878479,
|
|
"num_tokens": 35263359.0,
|
|
"step": 18035
|
|
},
|
|
{
|
|
"entropy": 6.349578142166138,
|
|
"epoch": 1.8033188384065577,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004679220499869881,
|
|
"loss": 5.7534,
|
|
"mean_token_accuracy": 0.178440161049366,
|
|
"num_tokens": 35272500.0,
|
|
"step": 18040
|
|
},
|
|
{
|
|
"entropy": 6.383653879165649,
|
|
"epoch": 1.8038186634677862,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004679036820056881,
|
|
"loss": 5.758,
|
|
"mean_token_accuracy": 0.17000945955514907,
|
|
"num_tokens": 35282415.0,
|
|
"step": 18045
|
|
},
|
|
{
|
|
"entropy": 6.27096037864685,
|
|
"epoch": 1.8043184885290149,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046788530917098105,
|
|
"loss": 5.6464,
|
|
"mean_token_accuracy": 0.19096913635730745,
|
|
"num_tokens": 35291567.0,
|
|
"step": 18050
|
|
},
|
|
{
|
|
"entropy": 6.247561502456665,
|
|
"epoch": 1.8048183135902434,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004678669314833293,
|
|
"loss": 5.7515,
|
|
"mean_token_accuracy": 0.1824422925710678,
|
|
"num_tokens": 35301397.0,
|
|
"step": 18055
|
|
},
|
|
{
|
|
"entropy": 6.260967254638672,
|
|
"epoch": 1.8053181386514718,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046784854894319525,
|
|
"loss": 5.6126,
|
|
"mean_token_accuracy": 0.19380173236131668,
|
|
"num_tokens": 35311296.0,
|
|
"step": 18060
|
|
},
|
|
{
|
|
"entropy": 6.335537528991699,
|
|
"epoch": 1.8058179637127005,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046783016155104123,
|
|
"loss": 5.7292,
|
|
"mean_token_accuracy": 0.18626139163970948,
|
|
"num_tokens": 35322819.0,
|
|
"step": 18065
|
|
},
|
|
{
|
|
"entropy": 6.283369302749634,
|
|
"epoch": 1.8063177887739292,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046781176930732997,
|
|
"loss": 5.6246,
|
|
"mean_token_accuracy": 0.18755377531051637,
|
|
"num_tokens": 35331374.0,
|
|
"step": 18070
|
|
},
|
|
{
|
|
"entropy": 6.260044813156128,
|
|
"epoch": 1.8068176138351577,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004677933722125243,
|
|
"loss": 5.7217,
|
|
"mean_token_accuracy": 0.18340437188744546,
|
|
"num_tokens": 35341040.0,
|
|
"step": 18075
|
|
},
|
|
{
|
|
"entropy": 6.313361930847168,
|
|
"epoch": 1.8073174388963862,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004677749702670869,
|
|
"loss": 5.7125,
|
|
"mean_token_accuracy": 0.18078085482120515,
|
|
"num_tokens": 35351387.0,
|
|
"step": 18080
|
|
},
|
|
{
|
|
"entropy": 6.311421060562134,
|
|
"epoch": 1.8078172639576149,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004677565634714809,
|
|
"loss": 5.7243,
|
|
"mean_token_accuracy": 0.18633250743150712,
|
|
"num_tokens": 35361864.0,
|
|
"step": 18085
|
|
},
|
|
{
|
|
"entropy": 6.25033802986145,
|
|
"epoch": 1.8083170890188434,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004677381518261693,
|
|
"loss": 5.6635,
|
|
"mean_token_accuracy": 0.19325382709503175,
|
|
"num_tokens": 35370539.0,
|
|
"step": 18090
|
|
},
|
|
{
|
|
"entropy": 6.234656143188476,
|
|
"epoch": 1.8088169140800718,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046771973533161543,
|
|
"loss": 5.621,
|
|
"mean_token_accuracy": 0.19653997719287872,
|
|
"num_tokens": 35381851.0,
|
|
"step": 18095
|
|
},
|
|
{
|
|
"entropy": 6.2969237804412845,
|
|
"epoch": 1.8093167391413005,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046770131398828264,
|
|
"loss": 5.6563,
|
|
"mean_token_accuracy": 0.18805955946445466,
|
|
"num_tokens": 35391440.0,
|
|
"step": 18100
|
|
},
|
|
{
|
|
"entropy": 6.28504433631897,
|
|
"epoch": 1.8098165642025292,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046768288779663436,
|
|
"loss": 5.7065,
|
|
"mean_token_accuracy": 0.18247218430042267,
|
|
"num_tokens": 35401370.0,
|
|
"step": 18105
|
|
},
|
|
{
|
|
"entropy": 6.270773839950562,
|
|
"epoch": 1.8103163892637577,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004676644567571342,
|
|
"loss": 5.6613,
|
|
"mean_token_accuracy": 0.1835208997130394,
|
|
"num_tokens": 35411015.0,
|
|
"step": 18110
|
|
},
|
|
{
|
|
"entropy": 6.339329433441162,
|
|
"epoch": 1.8108162143249862,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046764602087024596,
|
|
"loss": 5.6746,
|
|
"mean_token_accuracy": 0.18362541794776915,
|
|
"num_tokens": 35421741.0,
|
|
"step": 18115
|
|
},
|
|
{
|
|
"entropy": 6.40608401298523,
|
|
"epoch": 1.8113160393862149,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004676275801364332,
|
|
"loss": 5.8277,
|
|
"mean_token_accuracy": 0.17390751242637634,
|
|
"num_tokens": 35432899.0,
|
|
"step": 18120
|
|
},
|
|
{
|
|
"entropy": 6.187169408798217,
|
|
"epoch": 1.8118158644474434,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004676091345561603,
|
|
"loss": 5.5792,
|
|
"mean_token_accuracy": 0.1956627681851387,
|
|
"num_tokens": 35442220.0,
|
|
"step": 18125
|
|
},
|
|
{
|
|
"entropy": 6.224408054351807,
|
|
"epoch": 1.8123156895086718,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000467590684129891,
|
|
"loss": 5.6139,
|
|
"mean_token_accuracy": 0.1938367545604706,
|
|
"num_tokens": 35452193.0,
|
|
"step": 18130
|
|
},
|
|
{
|
|
"entropy": 6.280084705352783,
|
|
"epoch": 1.8128155145699005,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046757222885808973,
|
|
"loss": 5.6759,
|
|
"mean_token_accuracy": 0.18832276463508607,
|
|
"num_tokens": 35462152.0,
|
|
"step": 18135
|
|
},
|
|
{
|
|
"entropy": 6.28092737197876,
|
|
"epoch": 1.8133153396311292,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046755376874122075,
|
|
"loss": 5.6546,
|
|
"mean_token_accuracy": 0.18768989741802217,
|
|
"num_tokens": 35472210.0,
|
|
"step": 18140
|
|
},
|
|
{
|
|
"entropy": 6.2869274616241455,
|
|
"epoch": 1.8138151646923577,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004675353037797485,
|
|
"loss": 5.7334,
|
|
"mean_token_accuracy": 0.17769500166177749,
|
|
"num_tokens": 35482238.0,
|
|
"step": 18145
|
|
},
|
|
{
|
|
"entropy": 6.2729674816131595,
|
|
"epoch": 1.8143149897535862,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004675168339741375,
|
|
"loss": 5.725,
|
|
"mean_token_accuracy": 0.17594169974327087,
|
|
"num_tokens": 35492042.0,
|
|
"step": 18150
|
|
},
|
|
{
|
|
"entropy": 6.32383131980896,
|
|
"epoch": 1.8148148148148149,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004674983593248525,
|
|
"loss": 5.777,
|
|
"mean_token_accuracy": 0.17768839746713638,
|
|
"num_tokens": 35501892.0,
|
|
"step": 18155
|
|
},
|
|
{
|
|
"entropy": 6.2992987632751465,
|
|
"epoch": 1.8153146398760434,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046747987983235836,
|
|
"loss": 5.7368,
|
|
"mean_token_accuracy": 0.1771694540977478,
|
|
"num_tokens": 35512472.0,
|
|
"step": 18160
|
|
},
|
|
{
|
|
"entropy": 6.306866025924682,
|
|
"epoch": 1.8158144649372718,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046746139549711993,
|
|
"loss": 5.6228,
|
|
"mean_token_accuracy": 0.18365788757801055,
|
|
"num_tokens": 35521467.0,
|
|
"step": 18165
|
|
},
|
|
{
|
|
"entropy": 6.213927698135376,
|
|
"epoch": 1.8163142899985005,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004674429063196023,
|
|
"loss": 5.7191,
|
|
"mean_token_accuracy": 0.18364608585834502,
|
|
"num_tokens": 35531584.0,
|
|
"step": 18170
|
|
},
|
|
{
|
|
"entropy": 6.219142770767212,
|
|
"epoch": 1.8168141150597292,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00046742441230027067,
|
|
"loss": 5.5193,
|
|
"mean_token_accuracy": 0.20028796643018723,
|
|
"num_tokens": 35541687.0,
|
|
"step": 18175
|
|
},
|
|
{
|
|
"entropy": 6.264583873748779,
|
|
"epoch": 1.8173139401209577,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004674059134395904,
|
|
"loss": 5.644,
|
|
"mean_token_accuracy": 0.18367187976837157,
|
|
"num_tokens": 35551310.0,
|
|
"step": 18180
|
|
},
|
|
{
|
|
"entropy": 6.24519305229187,
|
|
"epoch": 1.8178137651821862,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004673874097380268,
|
|
"loss": 5.624,
|
|
"mean_token_accuracy": 0.1893189087510109,
|
|
"num_tokens": 35560356.0,
|
|
"step": 18185
|
|
},
|
|
{
|
|
"entropy": 6.232676410675049,
|
|
"epoch": 1.8183135902434149,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004673689011960455,
|
|
"loss": 5.6067,
|
|
"mean_token_accuracy": 0.19017356187105178,
|
|
"num_tokens": 35570633.0,
|
|
"step": 18190
|
|
},
|
|
{
|
|
"entropy": 6.360257863998413,
|
|
"epoch": 1.8188134153046434,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046735038781411204,
|
|
"loss": 5.8051,
|
|
"mean_token_accuracy": 0.17184835076332092,
|
|
"num_tokens": 35581341.0,
|
|
"step": 18195
|
|
},
|
|
{
|
|
"entropy": 6.26134147644043,
|
|
"epoch": 1.8193132403658718,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004673318695926925,
|
|
"loss": 5.5484,
|
|
"mean_token_accuracy": 0.20065570920705794,
|
|
"num_tokens": 35592301.0,
|
|
"step": 18200
|
|
},
|
|
{
|
|
"entropy": 6.2105358123779295,
|
|
"epoch": 1.8198130654271005,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004673133465322525,
|
|
"loss": 5.6029,
|
|
"mean_token_accuracy": 0.19283967912197114,
|
|
"num_tokens": 35601782.0,
|
|
"step": 18205
|
|
},
|
|
{
|
|
"entropy": 6.198134851455689,
|
|
"epoch": 1.8203128904883292,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004672948186332582,
|
|
"loss": 5.5931,
|
|
"mean_token_accuracy": 0.19068953543901443,
|
|
"num_tokens": 35611307.0,
|
|
"step": 18210
|
|
},
|
|
{
|
|
"entropy": 6.2827483177185055,
|
|
"epoch": 1.8208127155495577,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046727628589617574,
|
|
"loss": 5.7378,
|
|
"mean_token_accuracy": 0.18194995671510697,
|
|
"num_tokens": 35621358.0,
|
|
"step": 18215
|
|
},
|
|
{
|
|
"entropy": 6.303504991531372,
|
|
"epoch": 1.8213125406107862,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046725774832147147,
|
|
"loss": 5.6611,
|
|
"mean_token_accuracy": 0.1820487141609192,
|
|
"num_tokens": 35630976.0,
|
|
"step": 18220
|
|
},
|
|
{
|
|
"entropy": 6.222074413299561,
|
|
"epoch": 1.8218123656720149,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046723920590961167,
|
|
"loss": 5.622,
|
|
"mean_token_accuracy": 0.1851010650396347,
|
|
"num_tokens": 35640126.0,
|
|
"step": 18225
|
|
},
|
|
{
|
|
"entropy": 6.230450534820557,
|
|
"epoch": 1.8223121907332434,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004672206586610629,
|
|
"loss": 5.6481,
|
|
"mean_token_accuracy": 0.1896085485816002,
|
|
"num_tokens": 35649282.0,
|
|
"step": 18230
|
|
},
|
|
{
|
|
"entropy": 6.238442373275757,
|
|
"epoch": 1.8228120157944718,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046720210657629185,
|
|
"loss": 5.6029,
|
|
"mean_token_accuracy": 0.19529436975717546,
|
|
"num_tokens": 35658284.0,
|
|
"step": 18235
|
|
},
|
|
{
|
|
"entropy": 6.32085485458374,
|
|
"epoch": 1.8233118408557005,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046718354965576527,
|
|
"loss": 5.7578,
|
|
"mean_token_accuracy": 0.17749711126089096,
|
|
"num_tokens": 35668355.0,
|
|
"step": 18240
|
|
},
|
|
{
|
|
"entropy": 6.3018858432769775,
|
|
"epoch": 1.8238116659169292,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00046716498789995,
|
|
"loss": 5.7085,
|
|
"mean_token_accuracy": 0.17954145967960358,
|
|
"num_tokens": 35677582.0,
|
|
"step": 18245
|
|
},
|
|
{
|
|
"entropy": 6.305690145492553,
|
|
"epoch": 1.8243114909781575,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00046714642130931306,
|
|
"loss": 5.7437,
|
|
"mean_token_accuracy": 0.1817459434270859,
|
|
"num_tokens": 35687691.0,
|
|
"step": 18250
|
|
},
|
|
{
|
|
"entropy": 6.315854263305664,
|
|
"epoch": 1.8248113160393862,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046712784988432173,
|
|
"loss": 5.7239,
|
|
"mean_token_accuracy": 0.1802698031067848,
|
|
"num_tokens": 35697796.0,
|
|
"step": 18255
|
|
},
|
|
{
|
|
"entropy": 6.288722372055053,
|
|
"epoch": 1.8253111411006149,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000467109273625443,
|
|
"loss": 5.6464,
|
|
"mean_token_accuracy": 0.18663733452558517,
|
|
"num_tokens": 35706795.0,
|
|
"step": 18260
|
|
},
|
|
{
|
|
"entropy": 6.286833381652832,
|
|
"epoch": 1.8258109661618434,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004670906925331444,
|
|
"loss": 5.7249,
|
|
"mean_token_accuracy": 0.18639680594205857,
|
|
"num_tokens": 35717260.0,
|
|
"step": 18265
|
|
},
|
|
{
|
|
"entropy": 6.28852801322937,
|
|
"epoch": 1.8263107912230718,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046707210660789343,
|
|
"loss": 5.7488,
|
|
"mean_token_accuracy": 0.18116626888513565,
|
|
"num_tokens": 35726671.0,
|
|
"step": 18270
|
|
},
|
|
{
|
|
"entropy": 6.311827945709228,
|
|
"epoch": 1.8268106162843005,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004670535158501577,
|
|
"loss": 5.7387,
|
|
"mean_token_accuracy": 0.18040221631526948,
|
|
"num_tokens": 35736672.0,
|
|
"step": 18275
|
|
},
|
|
{
|
|
"entropy": 6.340602922439575,
|
|
"epoch": 1.8273104413455292,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046703492026040495,
|
|
"loss": 5.6565,
|
|
"mean_token_accuracy": 0.18481340557336806,
|
|
"num_tokens": 35746291.0,
|
|
"step": 18280
|
|
},
|
|
{
|
|
"entropy": 6.252474689483643,
|
|
"epoch": 1.8278102664067575,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00046701631983910296,
|
|
"loss": 5.6571,
|
|
"mean_token_accuracy": 0.17793803215026854,
|
|
"num_tokens": 35755683.0,
|
|
"step": 18285
|
|
},
|
|
{
|
|
"entropy": 6.298862791061401,
|
|
"epoch": 1.8283100914679862,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046699771458671974,
|
|
"loss": 5.704,
|
|
"mean_token_accuracy": 0.18606535196304322,
|
|
"num_tokens": 35765870.0,
|
|
"step": 18290
|
|
},
|
|
{
|
|
"entropy": 6.166363143920899,
|
|
"epoch": 1.8288099165292149,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046697910450372356,
|
|
"loss": 5.4982,
|
|
"mean_token_accuracy": 0.2048130750656128,
|
|
"num_tokens": 35777055.0,
|
|
"step": 18295
|
|
},
|
|
{
|
|
"entropy": 6.216614389419556,
|
|
"epoch": 1.8293097415904434,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046696048959058236,
|
|
"loss": 5.58,
|
|
"mean_token_accuracy": 0.19545502364635467,
|
|
"num_tokens": 35786846.0,
|
|
"step": 18300
|
|
},
|
|
{
|
|
"entropy": 6.24962043762207,
|
|
"epoch": 1.8298095666516718,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004669418698477647,
|
|
"loss": 5.5827,
|
|
"mean_token_accuracy": 0.19768730401992798,
|
|
"num_tokens": 35795471.0,
|
|
"step": 18305
|
|
},
|
|
{
|
|
"entropy": 6.2720294952392575,
|
|
"epoch": 1.8303093917129005,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046692324527573907,
|
|
"loss": 5.5667,
|
|
"mean_token_accuracy": 0.19045081734657288,
|
|
"num_tokens": 35804559.0,
|
|
"step": 18310
|
|
},
|
|
{
|
|
"entropy": 6.2466936111450195,
|
|
"epoch": 1.830809216774129,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004669046158749738,
|
|
"loss": 5.678,
|
|
"mean_token_accuracy": 0.1852458342909813,
|
|
"num_tokens": 35813545.0,
|
|
"step": 18315
|
|
},
|
|
{
|
|
"entropy": 6.234023380279541,
|
|
"epoch": 1.8313090418353575,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00046688598164593793,
|
|
"loss": 5.6784,
|
|
"mean_token_accuracy": 0.18767408579587935,
|
|
"num_tokens": 35822740.0,
|
|
"step": 18320
|
|
},
|
|
{
|
|
"entropy": 6.288696813583374,
|
|
"epoch": 1.8318088668965862,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004668673425891001,
|
|
"loss": 5.7006,
|
|
"mean_token_accuracy": 0.18056905567646026,
|
|
"num_tokens": 35832593.0,
|
|
"step": 18325
|
|
},
|
|
{
|
|
"entropy": 6.29388747215271,
|
|
"epoch": 1.8323086919578149,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00046684869870492927,
|
|
"loss": 5.624,
|
|
"mean_token_accuracy": 0.1914693757891655,
|
|
"num_tokens": 35841399.0,
|
|
"step": 18330
|
|
},
|
|
{
|
|
"entropy": 6.245185661315918,
|
|
"epoch": 1.8328085170190433,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00046683004999389455,
|
|
"loss": 5.7192,
|
|
"mean_token_accuracy": 0.17989216595888138,
|
|
"num_tokens": 35850099.0,
|
|
"step": 18335
|
|
},
|
|
{
|
|
"entropy": 6.293751573562622,
|
|
"epoch": 1.8333083420802718,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004668113964564651,
|
|
"loss": 5.7403,
|
|
"mean_token_accuracy": 0.1765054404735565,
|
|
"num_tokens": 35860398.0,
|
|
"step": 18340
|
|
},
|
|
{
|
|
"entropy": 6.271749496459961,
|
|
"epoch": 1.8338081671415005,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004667927380931104,
|
|
"loss": 5.6576,
|
|
"mean_token_accuracy": 0.18864368498325348,
|
|
"num_tokens": 35870390.0,
|
|
"step": 18345
|
|
},
|
|
{
|
|
"entropy": 6.248590564727783,
|
|
"epoch": 1.834307992202729,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004667740749042997,
|
|
"loss": 5.5834,
|
|
"mean_token_accuracy": 0.19075098782777786,
|
|
"num_tokens": 35881633.0,
|
|
"step": 18350
|
|
},
|
|
{
|
|
"entropy": 6.268173551559448,
|
|
"epoch": 1.8348078172639575,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046675540689050253,
|
|
"loss": 5.7206,
|
|
"mean_token_accuracy": 0.18211477249860764,
|
|
"num_tokens": 35891904.0,
|
|
"step": 18355
|
|
},
|
|
{
|
|
"entropy": 6.407538604736328,
|
|
"epoch": 1.8353076423251862,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046673673405218876,
|
|
"loss": 5.9311,
|
|
"mean_token_accuracy": 0.16604947820305824,
|
|
"num_tokens": 35901712.0,
|
|
"step": 18360
|
|
},
|
|
{
|
|
"entropy": 6.358740568161011,
|
|
"epoch": 1.8358074673864149,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004667180563898281,
|
|
"loss": 5.8174,
|
|
"mean_token_accuracy": 0.1769548773765564,
|
|
"num_tokens": 35911314.0,
|
|
"step": 18365
|
|
},
|
|
{
|
|
"entropy": 6.337567567825317,
|
|
"epoch": 1.8363072924476433,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046669937390389043,
|
|
"loss": 5.7418,
|
|
"mean_token_accuracy": 0.18407788425683974,
|
|
"num_tokens": 35921135.0,
|
|
"step": 18370
|
|
},
|
|
{
|
|
"entropy": 6.385389232635498,
|
|
"epoch": 1.8368071175088718,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046668068659484584,
|
|
"loss": 5.7325,
|
|
"mean_token_accuracy": 0.17921245694160462,
|
|
"num_tokens": 35930784.0,
|
|
"step": 18375
|
|
},
|
|
{
|
|
"entropy": 6.266321802139283,
|
|
"epoch": 1.8373069425701005,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046666199446316454,
|
|
"loss": 5.6132,
|
|
"mean_token_accuracy": 0.19053089171648024,
|
|
"num_tokens": 35940372.0,
|
|
"step": 18380
|
|
},
|
|
{
|
|
"entropy": 6.305325508117676,
|
|
"epoch": 1.837806767631329,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046664329750931675,
|
|
"loss": 5.6293,
|
|
"mean_token_accuracy": 0.17875406593084336,
|
|
"num_tokens": 35949507.0,
|
|
"step": 18385
|
|
},
|
|
{
|
|
"entropy": 6.269118928909302,
|
|
"epoch": 1.8383065926925575,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000466624595733773,
|
|
"loss": 5.6189,
|
|
"mean_token_accuracy": 0.18680285066366195,
|
|
"num_tokens": 35958981.0,
|
|
"step": 18390
|
|
},
|
|
{
|
|
"entropy": 6.303173208236695,
|
|
"epoch": 1.8388064177537862,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004666058891370036,
|
|
"loss": 5.68,
|
|
"mean_token_accuracy": 0.18204384297132492,
|
|
"num_tokens": 35967842.0,
|
|
"step": 18395
|
|
},
|
|
{
|
|
"entropy": 6.279737043380737,
|
|
"epoch": 1.8393062428150149,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004665871777194794,
|
|
"loss": 5.6812,
|
|
"mean_token_accuracy": 0.18196066319942475,
|
|
"num_tokens": 35977669.0,
|
|
"step": 18400
|
|
},
|
|
{
|
|
"entropy": 6.244293832778931,
|
|
"epoch": 1.8398060678762433,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046656846148167107,
|
|
"loss": 5.6881,
|
|
"mean_token_accuracy": 0.1834797352552414,
|
|
"num_tokens": 35987815.0,
|
|
"step": 18405
|
|
},
|
|
{
|
|
"entropy": 6.371722745895386,
|
|
"epoch": 1.8403058929374718,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00046654974042404957,
|
|
"loss": 5.8005,
|
|
"mean_token_accuracy": 0.17735863029956817,
|
|
"num_tokens": 35997831.0,
|
|
"step": 18410
|
|
},
|
|
{
|
|
"entropy": 6.319525289535522,
|
|
"epoch": 1.8408057179987005,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046653101454708593,
|
|
"loss": 5.6551,
|
|
"mean_token_accuracy": 0.18901575803756715,
|
|
"num_tokens": 36006822.0,
|
|
"step": 18415
|
|
},
|
|
{
|
|
"entropy": 6.254029083251953,
|
|
"epoch": 1.841305543059929,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004665122838512512,
|
|
"loss": 5.5893,
|
|
"mean_token_accuracy": 0.18879642486572265,
|
|
"num_tokens": 36015648.0,
|
|
"step": 18420
|
|
},
|
|
{
|
|
"entropy": 6.334623956680298,
|
|
"epoch": 1.8418053681211575,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004664935483370167,
|
|
"loss": 5.8292,
|
|
"mean_token_accuracy": 0.17122648656368256,
|
|
"num_tokens": 36025713.0,
|
|
"step": 18425
|
|
},
|
|
{
|
|
"entropy": 6.316956233978272,
|
|
"epoch": 1.8423051931823862,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004664748080048537,
|
|
"loss": 5.6237,
|
|
"mean_token_accuracy": 0.18450038731098176,
|
|
"num_tokens": 36035054.0,
|
|
"step": 18430
|
|
},
|
|
{
|
|
"entropy": 6.216502475738525,
|
|
"epoch": 1.8428050182436149,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046645606285523395,
|
|
"loss": 5.6527,
|
|
"mean_token_accuracy": 0.19344937950372695,
|
|
"num_tokens": 36045449.0,
|
|
"step": 18435
|
|
},
|
|
{
|
|
"entropy": 6.3011268138885494,
|
|
"epoch": 1.8433048433048433,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046643731288862884,
|
|
"loss": 5.7101,
|
|
"mean_token_accuracy": 0.180694343149662,
|
|
"num_tokens": 36055269.0,
|
|
"step": 18440
|
|
},
|
|
{
|
|
"entropy": 6.37471284866333,
|
|
"epoch": 1.8438046683660718,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004664185581055103,
|
|
"loss": 5.7998,
|
|
"mean_token_accuracy": 0.18517909348011016,
|
|
"num_tokens": 36064791.0,
|
|
"step": 18445
|
|
},
|
|
{
|
|
"entropy": 6.310286998748779,
|
|
"epoch": 1.8443044934273005,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00046639979850634995,
|
|
"loss": 5.6539,
|
|
"mean_token_accuracy": 0.17444707304239274,
|
|
"num_tokens": 36075583.0,
|
|
"step": 18450
|
|
},
|
|
{
|
|
"entropy": 6.316530179977417,
|
|
"epoch": 1.844804318488529,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046638103409162,
|
|
"loss": 5.6883,
|
|
"mean_token_accuracy": 0.1821175515651703,
|
|
"num_tokens": 36084664.0,
|
|
"step": 18455
|
|
},
|
|
{
|
|
"entropy": 6.320005178451538,
|
|
"epoch": 1.8453041435497575,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00046636226486179244,
|
|
"loss": 5.649,
|
|
"mean_token_accuracy": 0.19046313166618348,
|
|
"num_tokens": 36094184.0,
|
|
"step": 18460
|
|
},
|
|
{
|
|
"entropy": 6.341013193130493,
|
|
"epoch": 1.8458039686109862,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004663434908173396,
|
|
"loss": 5.6704,
|
|
"mean_token_accuracy": 0.18098355382680892,
|
|
"num_tokens": 36103148.0,
|
|
"step": 18465
|
|
},
|
|
{
|
|
"entropy": 6.32598876953125,
|
|
"epoch": 1.8463037936722149,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004663247119587338,
|
|
"loss": 5.6865,
|
|
"mean_token_accuracy": 0.18698904663324356,
|
|
"num_tokens": 36114268.0,
|
|
"step": 18470
|
|
},
|
|
{
|
|
"entropy": 6.29911961555481,
|
|
"epoch": 1.8468036187334433,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004663059282864474,
|
|
"loss": 5.6651,
|
|
"mean_token_accuracy": 0.18232974857091905,
|
|
"num_tokens": 36124690.0,
|
|
"step": 18475
|
|
},
|
|
{
|
|
"entropy": 6.320910406112671,
|
|
"epoch": 1.8473034437946718,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004662871398009531,
|
|
"loss": 5.6592,
|
|
"mean_token_accuracy": 0.1852748677134514,
|
|
"num_tokens": 36134628.0,
|
|
"step": 18480
|
|
},
|
|
{
|
|
"entropy": 6.29833574295044,
|
|
"epoch": 1.8478032688559005,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004662683465027235,
|
|
"loss": 5.7023,
|
|
"mean_token_accuracy": 0.18533039689064026,
|
|
"num_tokens": 36144919.0,
|
|
"step": 18485
|
|
},
|
|
{
|
|
"entropy": 6.257374382019043,
|
|
"epoch": 1.848303093917129,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046624954839223165,
|
|
"loss": 5.6437,
|
|
"mean_token_accuracy": 0.182338348031044,
|
|
"num_tokens": 36154081.0,
|
|
"step": 18490
|
|
},
|
|
{
|
|
"entropy": 6.20949764251709,
|
|
"epoch": 1.8488029189783575,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046623074546995024,
|
|
"loss": 5.6099,
|
|
"mean_token_accuracy": 0.19357000887393952,
|
|
"num_tokens": 36164318.0,
|
|
"step": 18495
|
|
},
|
|
{
|
|
"entropy": 6.329076671600342,
|
|
"epoch": 1.8493027440395862,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00046621193773635256,
|
|
"loss": 5.7368,
|
|
"mean_token_accuracy": 0.18459465354681015,
|
|
"num_tokens": 36173361.0,
|
|
"step": 18500
|
|
},
|
|
{
|
|
"entropy": 6.218807506561279,
|
|
"epoch": 1.8498025691008149,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004661931251919118,
|
|
"loss": 5.5388,
|
|
"mean_token_accuracy": 0.19682642370462416,
|
|
"num_tokens": 36183133.0,
|
|
"step": 18505
|
|
},
|
|
{
|
|
"entropy": 6.2400124073028564,
|
|
"epoch": 1.8503023941620433,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046617430783710105,
|
|
"loss": 5.6007,
|
|
"mean_token_accuracy": 0.19013876914978028,
|
|
"num_tokens": 36193041.0,
|
|
"step": 18510
|
|
},
|
|
{
|
|
"entropy": 6.223023319244385,
|
|
"epoch": 1.8508022192232718,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000466155485672394,
|
|
"loss": 5.5806,
|
|
"mean_token_accuracy": 0.19615132808685304,
|
|
"num_tokens": 36202306.0,
|
|
"step": 18515
|
|
},
|
|
{
|
|
"entropy": 6.2625633716583256,
|
|
"epoch": 1.8513020442845005,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004661366586982641,
|
|
"loss": 5.6085,
|
|
"mean_token_accuracy": 0.19166960716247558,
|
|
"num_tokens": 36212342.0,
|
|
"step": 18520
|
|
},
|
|
{
|
|
"entropy": 6.261753129959106,
|
|
"epoch": 1.851801869345729,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004661178269151851,
|
|
"loss": 5.6836,
|
|
"mean_token_accuracy": 0.1798086494207382,
|
|
"num_tokens": 36221181.0,
|
|
"step": 18525
|
|
},
|
|
{
|
|
"entropy": 6.294492149353028,
|
|
"epoch": 1.8523016944069575,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00046609899032363074,
|
|
"loss": 5.6729,
|
|
"mean_token_accuracy": 0.1881666362285614,
|
|
"num_tokens": 36230813.0,
|
|
"step": 18530
|
|
},
|
|
{
|
|
"entropy": 6.266712856292725,
|
|
"epoch": 1.8528015194681862,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004660801489240749,
|
|
"loss": 5.7335,
|
|
"mean_token_accuracy": 0.1828066810965538,
|
|
"num_tokens": 36242315.0,
|
|
"step": 18535
|
|
},
|
|
{
|
|
"entropy": 6.233140087127685,
|
|
"epoch": 1.8533013445294149,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046606130271699175,
|
|
"loss": 5.5885,
|
|
"mean_token_accuracy": 0.19295239299535752,
|
|
"num_tokens": 36253665.0,
|
|
"step": 18540
|
|
},
|
|
{
|
|
"entropy": 6.325166368484497,
|
|
"epoch": 1.8538011695906431,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004660424517028553,
|
|
"loss": 5.7761,
|
|
"mean_token_accuracy": 0.17748988121747972,
|
|
"num_tokens": 36263514.0,
|
|
"step": 18545
|
|
},
|
|
{
|
|
"entropy": 6.2426330089569095,
|
|
"epoch": 1.8543009946518718,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046602359588214,
|
|
"loss": 5.6636,
|
|
"mean_token_accuracy": 0.18400596380233764,
|
|
"num_tokens": 36273103.0,
|
|
"step": 18550
|
|
},
|
|
{
|
|
"entropy": 6.336312627792358,
|
|
"epoch": 1.8548008197131005,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004660047352553202,
|
|
"loss": 5.6979,
|
|
"mean_token_accuracy": 0.1847234159708023,
|
|
"num_tokens": 36283079.0,
|
|
"step": 18555
|
|
},
|
|
{
|
|
"entropy": 6.305031633377075,
|
|
"epoch": 1.855300644774329,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046598586982287034,
|
|
"loss": 5.6783,
|
|
"mean_token_accuracy": 0.17801758795976638,
|
|
"num_tokens": 36292405.0,
|
|
"step": 18560
|
|
},
|
|
{
|
|
"entropy": 6.266739416122436,
|
|
"epoch": 1.8558004698355575,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046596699958526515,
|
|
"loss": 5.6408,
|
|
"mean_token_accuracy": 0.18750482946634292,
|
|
"num_tokens": 36301516.0,
|
|
"step": 18565
|
|
},
|
|
{
|
|
"entropy": 6.311913871765137,
|
|
"epoch": 1.8563002948967862,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046594812454297944,
|
|
"loss": 5.727,
|
|
"mean_token_accuracy": 0.18137274086475372,
|
|
"num_tokens": 36311414.0,
|
|
"step": 18570
|
|
},
|
|
{
|
|
"entropy": 6.443040037155152,
|
|
"epoch": 1.8568001199580149,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000465929244696488,
|
|
"loss": 5.8011,
|
|
"mean_token_accuracy": 0.17184364348649978,
|
|
"num_tokens": 36321521.0,
|
|
"step": 18575
|
|
},
|
|
{
|
|
"entropy": 6.337374019622803,
|
|
"epoch": 1.8572999450192431,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004659103600462659,
|
|
"loss": 5.7381,
|
|
"mean_token_accuracy": 0.18028470873832703,
|
|
"num_tokens": 36331115.0,
|
|
"step": 18580
|
|
},
|
|
{
|
|
"entropy": 6.229982948303222,
|
|
"epoch": 1.8577997700804718,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004658914705927883,
|
|
"loss": 5.7527,
|
|
"mean_token_accuracy": 0.18022053837776184,
|
|
"num_tokens": 36341131.0,
|
|
"step": 18585
|
|
},
|
|
{
|
|
"entropy": 6.219628810882568,
|
|
"epoch": 1.8582995951417005,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004658725763365304,
|
|
"loss": 5.586,
|
|
"mean_token_accuracy": 0.19425978064537047,
|
|
"num_tokens": 36350378.0,
|
|
"step": 18590
|
|
},
|
|
{
|
|
"entropy": 6.287558078765869,
|
|
"epoch": 1.858799420202929,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004658536772779676,
|
|
"loss": 5.6578,
|
|
"mean_token_accuracy": 0.18635154664516448,
|
|
"num_tokens": 36359706.0,
|
|
"step": 18595
|
|
},
|
|
{
|
|
"entropy": 6.2782487869262695,
|
|
"epoch": 1.8592992452641575,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004658347734175754,
|
|
"loss": 5.713,
|
|
"mean_token_accuracy": 0.18505863845348358,
|
|
"num_tokens": 36370068.0,
|
|
"step": 18600
|
|
},
|
|
{
|
|
"entropy": 6.262794065475464,
|
|
"epoch": 1.8597990703253862,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00046581586475582946,
|
|
"loss": 5.6609,
|
|
"mean_token_accuracy": 0.18392906934022904,
|
|
"num_tokens": 36380400.0,
|
|
"step": 18605
|
|
},
|
|
{
|
|
"entropy": 6.294452905654907,
|
|
"epoch": 1.8602988953866146,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004657969512932054,
|
|
"loss": 5.6421,
|
|
"mean_token_accuracy": 0.18545740842819214,
|
|
"num_tokens": 36390114.0,
|
|
"step": 18610
|
|
},
|
|
{
|
|
"entropy": 6.214505529403686,
|
|
"epoch": 1.8607987204478431,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004657780330301791,
|
|
"loss": 5.6138,
|
|
"mean_token_accuracy": 0.19188884943723677,
|
|
"num_tokens": 36399389.0,
|
|
"step": 18615
|
|
},
|
|
{
|
|
"entropy": 6.241682147979736,
|
|
"epoch": 1.8612985455090718,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00046575910996722657,
|
|
"loss": 5.6055,
|
|
"mean_token_accuracy": 0.18662422746419907,
|
|
"num_tokens": 36408512.0,
|
|
"step": 18620
|
|
},
|
|
{
|
|
"entropy": 6.338972043991089,
|
|
"epoch": 1.8617983705703005,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000465740182104824,
|
|
"loss": 5.8226,
|
|
"mean_token_accuracy": 0.16950636655092238,
|
|
"num_tokens": 36419049.0,
|
|
"step": 18625
|
|
},
|
|
{
|
|
"entropy": 6.26429123878479,
|
|
"epoch": 1.862298195631529,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046572124944344745,
|
|
"loss": 5.5852,
|
|
"mean_token_accuracy": 0.1831025719642639,
|
|
"num_tokens": 36428561.0,
|
|
"step": 18630
|
|
},
|
|
{
|
|
"entropy": 6.304585027694702,
|
|
"epoch": 1.8627980206927575,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046570231198357344,
|
|
"loss": 5.7501,
|
|
"mean_token_accuracy": 0.17950779795646668,
|
|
"num_tokens": 36438346.0,
|
|
"step": 18635
|
|
},
|
|
{
|
|
"entropy": 6.266301107406616,
|
|
"epoch": 1.8632978457539862,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004656833697256783,
|
|
"loss": 5.6554,
|
|
"mean_token_accuracy": 0.18619112074375152,
|
|
"num_tokens": 36447756.0,
|
|
"step": 18640
|
|
},
|
|
{
|
|
"entropy": 6.266196966171265,
|
|
"epoch": 1.8637976708152146,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004656644226702386,
|
|
"loss": 5.6318,
|
|
"mean_token_accuracy": 0.1933731734752655,
|
|
"num_tokens": 36457784.0,
|
|
"step": 18645
|
|
},
|
|
{
|
|
"entropy": 6.179813289642334,
|
|
"epoch": 1.8642974958764431,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00046564547081773115,
|
|
"loss": 5.5936,
|
|
"mean_token_accuracy": 0.19045981913805007,
|
|
"num_tokens": 36467952.0,
|
|
"step": 18650
|
|
},
|
|
{
|
|
"entropy": 6.36432032585144,
|
|
"epoch": 1.8647973209376718,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004656265141686326,
|
|
"loss": 5.7901,
|
|
"mean_token_accuracy": 0.17905865460634232,
|
|
"num_tokens": 36478595.0,
|
|
"step": 18655
|
|
},
|
|
{
|
|
"entropy": 6.2221839427948,
|
|
"epoch": 1.8652971459989005,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00046560755272342014,
|
|
"loss": 5.5558,
|
|
"mean_token_accuracy": 0.19264188259840012,
|
|
"num_tokens": 36487866.0,
|
|
"step": 18660
|
|
},
|
|
{
|
|
"entropy": 6.294560813903809,
|
|
"epoch": 1.865796971060129,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004655885864825706,
|
|
"loss": 5.6763,
|
|
"mean_token_accuracy": 0.17900269478559494,
|
|
"num_tokens": 36497828.0,
|
|
"step": 18665
|
|
},
|
|
{
|
|
"entropy": 6.273143100738525,
|
|
"epoch": 1.8662967961213575,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004655696154465613,
|
|
"loss": 5.6091,
|
|
"mean_token_accuracy": 0.18669350147247316,
|
|
"num_tokens": 36508361.0,
|
|
"step": 18670
|
|
},
|
|
{
|
|
"entropy": 6.268481349945068,
|
|
"epoch": 1.8667966211825862,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00046555063961586956,
|
|
"loss": 5.5885,
|
|
"mean_token_accuracy": 0.19052444845438005,
|
|
"num_tokens": 36518458.0,
|
|
"step": 18675
|
|
},
|
|
{
|
|
"entropy": 6.231949949264527,
|
|
"epoch": 1.8672964462438146,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004655316589909727,
|
|
"loss": 5.6652,
|
|
"mean_token_accuracy": 0.1864815816283226,
|
|
"num_tokens": 36527952.0,
|
|
"step": 18680
|
|
},
|
|
{
|
|
"entropy": 6.25091061592102,
|
|
"epoch": 1.867796271305043,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004655126735723484,
|
|
"loss": 5.684,
|
|
"mean_token_accuracy": 0.18222041577100753,
|
|
"num_tokens": 36537231.0,
|
|
"step": 18685
|
|
},
|
|
{
|
|
"entropy": 6.323439598083496,
|
|
"epoch": 1.8682960963662718,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046549368336047415,
|
|
"loss": 5.7477,
|
|
"mean_token_accuracy": 0.18234278857707978,
|
|
"num_tokens": 36546524.0,
|
|
"step": 18690
|
|
},
|
|
{
|
|
"entropy": 6.281253910064697,
|
|
"epoch": 1.8687959214275005,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004654746883558279,
|
|
"loss": 5.5995,
|
|
"mean_token_accuracy": 0.19168957471847534,
|
|
"num_tokens": 36557064.0,
|
|
"step": 18695
|
|
},
|
|
{
|
|
"entropy": 6.275532341003418,
|
|
"epoch": 1.869295746488729,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004654556885588875,
|
|
"loss": 5.5603,
|
|
"mean_token_accuracy": 0.18872976005077363,
|
|
"num_tokens": 36565986.0,
|
|
"step": 18700
|
|
},
|
|
{
|
|
"entropy": 6.331531095504761,
|
|
"epoch": 1.8697955715499575,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046543668397013103,
|
|
"loss": 5.7314,
|
|
"mean_token_accuracy": 0.17860317826271058,
|
|
"num_tokens": 36575646.0,
|
|
"step": 18705
|
|
},
|
|
{
|
|
"entropy": 6.241415309906006,
|
|
"epoch": 1.8702953966111862,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004654176745900365,
|
|
"loss": 5.6248,
|
|
"mean_token_accuracy": 0.18761643171310424,
|
|
"num_tokens": 36585472.0,
|
|
"step": 18710
|
|
},
|
|
{
|
|
"entropy": 6.277038955688477,
|
|
"epoch": 1.8707952216724146,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046539866041908233,
|
|
"loss": 5.6176,
|
|
"mean_token_accuracy": 0.19399500340223313,
|
|
"num_tokens": 36594309.0,
|
|
"step": 18715
|
|
},
|
|
{
|
|
"entropy": 6.324639844894409,
|
|
"epoch": 1.871295046733643,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046537964145774687,
|
|
"loss": 5.7327,
|
|
"mean_token_accuracy": 0.17855128049850463,
|
|
"num_tokens": 36604027.0,
|
|
"step": 18720
|
|
},
|
|
{
|
|
"entropy": 6.271830797195435,
|
|
"epoch": 1.8717948717948718,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004653606177065086,
|
|
"loss": 5.6494,
|
|
"mean_token_accuracy": 0.18452674001455308,
|
|
"num_tokens": 36613613.0,
|
|
"step": 18725
|
|
},
|
|
{
|
|
"entropy": 6.293476676940918,
|
|
"epoch": 1.8722946968561005,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004653415891658462,
|
|
"loss": 5.6755,
|
|
"mean_token_accuracy": 0.18832513689994812,
|
|
"num_tokens": 36624049.0,
|
|
"step": 18730
|
|
},
|
|
{
|
|
"entropy": 6.294981479644775,
|
|
"epoch": 1.872794521917329,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046532255583623837,
|
|
"loss": 5.6654,
|
|
"mean_token_accuracy": 0.18383627533912658,
|
|
"num_tokens": 36634815.0,
|
|
"step": 18735
|
|
},
|
|
{
|
|
"entropy": 6.326095628738403,
|
|
"epoch": 1.8732943469785575,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000465303517718164,
|
|
"loss": 5.6948,
|
|
"mean_token_accuracy": 0.17993152588605882,
|
|
"num_tokens": 36644701.0,
|
|
"step": 18740
|
|
},
|
|
{
|
|
"entropy": 6.275757694244385,
|
|
"epoch": 1.8737941720397862,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004652844748121021,
|
|
"loss": 5.6494,
|
|
"mean_token_accuracy": 0.18765501976013182,
|
|
"num_tokens": 36653581.0,
|
|
"step": 18745
|
|
},
|
|
{
|
|
"entropy": 6.230726051330566,
|
|
"epoch": 1.8742939971010146,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004652654271185318,
|
|
"loss": 5.6917,
|
|
"mean_token_accuracy": 0.18706122040748596,
|
|
"num_tokens": 36662644.0,
|
|
"step": 18750
|
|
},
|
|
{
|
|
"entropy": 6.276381731033325,
|
|
"epoch": 1.874793822162243,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046524637463793233,
|
|
"loss": 5.7029,
|
|
"mean_token_accuracy": 0.1779522106051445,
|
|
"num_tokens": 36673260.0,
|
|
"step": 18755
|
|
},
|
|
{
|
|
"entropy": 6.350884246826172,
|
|
"epoch": 1.8752936472234718,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000465227317370783,
|
|
"loss": 5.7256,
|
|
"mean_token_accuracy": 0.1858867734670639,
|
|
"num_tokens": 36682899.0,
|
|
"step": 18760
|
|
},
|
|
{
|
|
"entropy": 6.271539688110352,
|
|
"epoch": 1.8757934722847005,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00046520825531756326,
|
|
"loss": 5.6925,
|
|
"mean_token_accuracy": 0.17972541749477386,
|
|
"num_tokens": 36693190.0,
|
|
"step": 18765
|
|
},
|
|
{
|
|
"entropy": 6.233624076843261,
|
|
"epoch": 1.876293297345929,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004651891884787528,
|
|
"loss": 5.549,
|
|
"mean_token_accuracy": 0.1867420807480812,
|
|
"num_tokens": 36701263.0,
|
|
"step": 18770
|
|
},
|
|
{
|
|
"entropy": 6.279172706604004,
|
|
"epoch": 1.8767931224071575,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046517011685483136,
|
|
"loss": 5.6966,
|
|
"mean_token_accuracy": 0.18015545904636382,
|
|
"num_tokens": 36710622.0,
|
|
"step": 18775
|
|
},
|
|
{
|
|
"entropy": 6.2557018280029295,
|
|
"epoch": 1.8772929474683862,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00046515104044627867,
|
|
"loss": 5.6544,
|
|
"mean_token_accuracy": 0.18664415180683136,
|
|
"num_tokens": 36720510.0,
|
|
"step": 18780
|
|
},
|
|
{
|
|
"entropy": 6.254063510894776,
|
|
"epoch": 1.8777927725296146,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004651319592535747,
|
|
"loss": 5.6972,
|
|
"mean_token_accuracy": 0.17918993383646012,
|
|
"num_tokens": 36730570.0,
|
|
"step": 18785
|
|
},
|
|
{
|
|
"entropy": 6.268753719329834,
|
|
"epoch": 1.878292597590843,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004651128732771996,
|
|
"loss": 5.6175,
|
|
"mean_token_accuracy": 0.19103719741106034,
|
|
"num_tokens": 36739834.0,
|
|
"step": 18790
|
|
},
|
|
{
|
|
"entropy": 6.264542961120606,
|
|
"epoch": 1.8787924226520718,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046509378251763346,
|
|
"loss": 5.5234,
|
|
"mean_token_accuracy": 0.19096072018146515,
|
|
"num_tokens": 36750193.0,
|
|
"step": 18795
|
|
},
|
|
{
|
|
"entropy": 6.340397119522095,
|
|
"epoch": 1.8792922477133005,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004650746869753567,
|
|
"loss": 5.6542,
|
|
"mean_token_accuracy": 0.18075035661458969,
|
|
"num_tokens": 36759253.0,
|
|
"step": 18800
|
|
},
|
|
{
|
|
"entropy": 6.340481281280518,
|
|
"epoch": 1.8797920727745288,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004650555866508498,
|
|
"loss": 5.7611,
|
|
"mean_token_accuracy": 0.17450972497463227,
|
|
"num_tokens": 36768841.0,
|
|
"step": 18805
|
|
},
|
|
{
|
|
"entropy": 6.323821210861206,
|
|
"epoch": 1.8802918978357575,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00046503648154459315,
|
|
"loss": 5.7873,
|
|
"mean_token_accuracy": 0.1784950911998749,
|
|
"num_tokens": 36780146.0,
|
|
"step": 18810
|
|
},
|
|
{
|
|
"entropy": 6.333207750320435,
|
|
"epoch": 1.8807917228969862,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004650173716570676,
|
|
"loss": 5.6729,
|
|
"mean_token_accuracy": 0.18400220870971679,
|
|
"num_tokens": 36789948.0,
|
|
"step": 18815
|
|
},
|
|
{
|
|
"entropy": 6.270326232910156,
|
|
"epoch": 1.8812915479582146,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046499825698875384,
|
|
"loss": 5.5786,
|
|
"mean_token_accuracy": 0.1921565130352974,
|
|
"num_tokens": 36799496.0,
|
|
"step": 18820
|
|
},
|
|
{
|
|
"entropy": 6.243523979187012,
|
|
"epoch": 1.881791373019443,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046497913754013284,
|
|
"loss": 5.7011,
|
|
"mean_token_accuracy": 0.18471659421920777,
|
|
"num_tokens": 36809905.0,
|
|
"step": 18825
|
|
},
|
|
{
|
|
"entropy": 6.301621913909912,
|
|
"epoch": 1.8822911980806718,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004649600133116856,
|
|
"loss": 5.6844,
|
|
"mean_token_accuracy": 0.1805134519934654,
|
|
"num_tokens": 36819855.0,
|
|
"step": 18830
|
|
},
|
|
{
|
|
"entropy": 6.314302158355713,
|
|
"epoch": 1.8827910231419005,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00046494088430389335,
|
|
"loss": 5.708,
|
|
"mean_token_accuracy": 0.1764696940779686,
|
|
"num_tokens": 36830456.0,
|
|
"step": 18835
|
|
},
|
|
{
|
|
"entropy": 6.221128225326538,
|
|
"epoch": 1.8832908482031288,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004649217505172373,
|
|
"loss": 5.6126,
|
|
"mean_token_accuracy": 0.19140670150518418,
|
|
"num_tokens": 36839914.0,
|
|
"step": 18840
|
|
},
|
|
{
|
|
"entropy": 6.311464023590088,
|
|
"epoch": 1.8837906732643575,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004649026119521989,
|
|
"loss": 5.5958,
|
|
"mean_token_accuracy": 0.18759126514196395,
|
|
"num_tokens": 36848644.0,
|
|
"step": 18845
|
|
},
|
|
{
|
|
"entropy": 6.245556116104126,
|
|
"epoch": 1.8842904983255861,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046488346860925955,
|
|
"loss": 5.6505,
|
|
"mean_token_accuracy": 0.18612904399633406,
|
|
"num_tokens": 36857490.0,
|
|
"step": 18850
|
|
},
|
|
{
|
|
"entropy": 6.352661752700806,
|
|
"epoch": 1.8847903233868146,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046486432048890104,
|
|
"loss": 5.8547,
|
|
"mean_token_accuracy": 0.17048121988773346,
|
|
"num_tokens": 36867617.0,
|
|
"step": 18855
|
|
},
|
|
{
|
|
"entropy": 6.315634679794312,
|
|
"epoch": 1.885290148448043,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004648451675916051,
|
|
"loss": 5.6778,
|
|
"mean_token_accuracy": 0.1853662133216858,
|
|
"num_tokens": 36876626.0,
|
|
"step": 18860
|
|
},
|
|
{
|
|
"entropy": 6.310365629196167,
|
|
"epoch": 1.8857899735092718,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046482600991785365,
|
|
"loss": 5.7088,
|
|
"mean_token_accuracy": 0.18102081567049028,
|
|
"num_tokens": 36887693.0,
|
|
"step": 18865
|
|
},
|
|
{
|
|
"entropy": 6.325302314758301,
|
|
"epoch": 1.8862897985705003,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046480684746812856,
|
|
"loss": 5.7125,
|
|
"mean_token_accuracy": 0.1885442018508911,
|
|
"num_tokens": 36897817.0,
|
|
"step": 18870
|
|
},
|
|
{
|
|
"entropy": 6.283907842636109,
|
|
"epoch": 1.8867896236317288,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046478768024291205,
|
|
"loss": 5.6417,
|
|
"mean_token_accuracy": 0.18815297931432723,
|
|
"num_tokens": 36908154.0,
|
|
"step": 18875
|
|
},
|
|
{
|
|
"entropy": 6.31000280380249,
|
|
"epoch": 1.8872894486929574,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046476850824268633,
|
|
"loss": 5.6638,
|
|
"mean_token_accuracy": 0.18109962940216065,
|
|
"num_tokens": 36917748.0,
|
|
"step": 18880
|
|
},
|
|
{
|
|
"entropy": 6.262924146652222,
|
|
"epoch": 1.8877892737541861,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004647493314679338,
|
|
"loss": 5.66,
|
|
"mean_token_accuracy": 0.19627050012350084,
|
|
"num_tokens": 36927128.0,
|
|
"step": 18885
|
|
},
|
|
{
|
|
"entropy": 6.2481707572937015,
|
|
"epoch": 1.8882890988154146,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000464730149919137,
|
|
"loss": 5.6134,
|
|
"mean_token_accuracy": 0.19095664322376252,
|
|
"num_tokens": 36936822.0,
|
|
"step": 18890
|
|
},
|
|
{
|
|
"entropy": 6.357352304458618,
|
|
"epoch": 1.888788923876643,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004647109635967783,
|
|
"loss": 5.7208,
|
|
"mean_token_accuracy": 0.17439100295305252,
|
|
"num_tokens": 36946781.0,
|
|
"step": 18895
|
|
},
|
|
{
|
|
"entropy": 6.28590497970581,
|
|
"epoch": 1.8892887489378718,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004646917725013406,
|
|
"loss": 5.6476,
|
|
"mean_token_accuracy": 0.1867256850004196,
|
|
"num_tokens": 36956998.0,
|
|
"step": 18900
|
|
},
|
|
{
|
|
"entropy": 6.3051306247711185,
|
|
"epoch": 1.8897885739991003,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004646725766333068,
|
|
"loss": 5.6819,
|
|
"mean_token_accuracy": 0.1873082473874092,
|
|
"num_tokens": 36966138.0,
|
|
"step": 18905
|
|
},
|
|
{
|
|
"entropy": 6.1966815948486325,
|
|
"epoch": 1.8902883990603288,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00046465337599315966,
|
|
"loss": 5.6389,
|
|
"mean_token_accuracy": 0.1925529271364212,
|
|
"num_tokens": 36976282.0,
|
|
"step": 18910
|
|
},
|
|
{
|
|
"entropy": 6.347519731521606,
|
|
"epoch": 1.8907882241215574,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046463417058138247,
|
|
"loss": 5.7114,
|
|
"mean_token_accuracy": 0.17943407148122786,
|
|
"num_tokens": 36986795.0,
|
|
"step": 18915
|
|
},
|
|
{
|
|
"entropy": 6.262246894836426,
|
|
"epoch": 1.8912880491827861,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004646149603984583,
|
|
"loss": 5.6741,
|
|
"mean_token_accuracy": 0.18451131731271744,
|
|
"num_tokens": 36997334.0,
|
|
"step": 18920
|
|
},
|
|
{
|
|
"entropy": 6.2433860301971436,
|
|
"epoch": 1.8917878742440146,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004645957454448706,
|
|
"loss": 5.5938,
|
|
"mean_token_accuracy": 0.18700933307409287,
|
|
"num_tokens": 37006978.0,
|
|
"step": 18925
|
|
},
|
|
{
|
|
"entropy": 6.20086407661438,
|
|
"epoch": 1.892287699305243,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004645765257211026,
|
|
"loss": 5.6006,
|
|
"mean_token_accuracy": 0.20016707926988603,
|
|
"num_tokens": 37016821.0,
|
|
"step": 18930
|
|
},
|
|
{
|
|
"entropy": 6.240530776977539,
|
|
"epoch": 1.8927875243664718,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00046455730122763804,
|
|
"loss": 5.6371,
|
|
"mean_token_accuracy": 0.1861592411994934,
|
|
"num_tokens": 37026596.0,
|
|
"step": 18935
|
|
},
|
|
{
|
|
"entropy": 6.272572422027588,
|
|
"epoch": 1.8932873494277003,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004645380719649606,
|
|
"loss": 5.6445,
|
|
"mean_token_accuracy": 0.1878703311085701,
|
|
"num_tokens": 37035899.0,
|
|
"step": 18940
|
|
},
|
|
{
|
|
"entropy": 6.271205139160156,
|
|
"epoch": 1.8937871744889287,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046451883793355406,
|
|
"loss": 5.7471,
|
|
"mean_token_accuracy": 0.181737919151783,
|
|
"num_tokens": 37045747.0,
|
|
"step": 18945
|
|
},
|
|
{
|
|
"entropy": 6.305781030654908,
|
|
"epoch": 1.8942869995501574,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046449959913390227,
|
|
"loss": 5.7151,
|
|
"mean_token_accuracy": 0.1771324247121811,
|
|
"num_tokens": 37056673.0,
|
|
"step": 18950
|
|
},
|
|
{
|
|
"entropy": 6.308448266983032,
|
|
"epoch": 1.8947868246113861,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00046448035556648936,
|
|
"loss": 5.6639,
|
|
"mean_token_accuracy": 0.1897890567779541,
|
|
"num_tokens": 37065375.0,
|
|
"step": 18955
|
|
},
|
|
{
|
|
"entropy": 6.326512861251831,
|
|
"epoch": 1.8952866496726146,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00046446110723179945,
|
|
"loss": 5.6047,
|
|
"mean_token_accuracy": 0.19356833398342133,
|
|
"num_tokens": 37074088.0,
|
|
"step": 18960
|
|
},
|
|
{
|
|
"entropy": 6.269736051559448,
|
|
"epoch": 1.895786474733843,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004644418541303169,
|
|
"loss": 5.6298,
|
|
"mean_token_accuracy": 0.17816174030303955,
|
|
"num_tokens": 37085418.0,
|
|
"step": 18965
|
|
},
|
|
{
|
|
"entropy": 6.29596700668335,
|
|
"epoch": 1.8962862997950718,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046442259626252593,
|
|
"loss": 5.7035,
|
|
"mean_token_accuracy": 0.18872252106666565,
|
|
"num_tokens": 37095029.0,
|
|
"step": 18970
|
|
},
|
|
{
|
|
"entropy": 6.284410285949707,
|
|
"epoch": 1.8967861248563003,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046440333362891123,
|
|
"loss": 5.6383,
|
|
"mean_token_accuracy": 0.19221088290214539,
|
|
"num_tokens": 37104398.0,
|
|
"step": 18975
|
|
},
|
|
{
|
|
"entropy": 6.369149160385132,
|
|
"epoch": 1.8972859499175287,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004643840662299574,
|
|
"loss": 5.7017,
|
|
"mean_token_accuracy": 0.18493416011333466,
|
|
"num_tokens": 37114546.0,
|
|
"step": 18980
|
|
},
|
|
{
|
|
"entropy": 6.222436904907227,
|
|
"epoch": 1.8977857749787574,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004643647940661492,
|
|
"loss": 5.5821,
|
|
"mean_token_accuracy": 0.19767787754535676,
|
|
"num_tokens": 37124113.0,
|
|
"step": 18985
|
|
},
|
|
{
|
|
"entropy": 6.313520193099976,
|
|
"epoch": 1.8982856000399861,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046434551713797146,
|
|
"loss": 5.66,
|
|
"mean_token_accuracy": 0.19058231711387635,
|
|
"num_tokens": 37133661.0,
|
|
"step": 18990
|
|
},
|
|
{
|
|
"entropy": 6.303951644897461,
|
|
"epoch": 1.8987854251012146,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004643262354459093,
|
|
"loss": 5.6862,
|
|
"mean_token_accuracy": 0.19088131189346313,
|
|
"num_tokens": 37143987.0,
|
|
"step": 18995
|
|
},
|
|
{
|
|
"entropy": 6.375118160247803,
|
|
"epoch": 1.899285250162443,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046430694899044774,
|
|
"loss": 5.783,
|
|
"mean_token_accuracy": 0.1838818147778511,
|
|
"num_tokens": 37153227.0,
|
|
"step": 19000
|
|
},
|
|
{
|
|
"entropy": 6.323116970062256,
|
|
"epoch": 1.8997850752236718,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000464287657772072,
|
|
"loss": 5.665,
|
|
"mean_token_accuracy": 0.1868035078048706,
|
|
"num_tokens": 37162524.0,
|
|
"step": 19005
|
|
},
|
|
{
|
|
"entropy": 6.285127592086792,
|
|
"epoch": 1.9002849002849003,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004642683617912676,
|
|
"loss": 5.6584,
|
|
"mean_token_accuracy": 0.18748643547296523,
|
|
"num_tokens": 37172729.0,
|
|
"step": 19010
|
|
},
|
|
{
|
|
"entropy": 6.243903493881225,
|
|
"epoch": 1.9007847253461287,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00046424906104851994,
|
|
"loss": 5.6204,
|
|
"mean_token_accuracy": 0.18629823625087738,
|
|
"num_tokens": 37182561.0,
|
|
"step": 19015
|
|
},
|
|
{
|
|
"entropy": 6.354578304290771,
|
|
"epoch": 1.9012845504073574,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046422975554431453,
|
|
"loss": 5.6955,
|
|
"mean_token_accuracy": 0.18762026727199554,
|
|
"num_tokens": 37192089.0,
|
|
"step": 19020
|
|
},
|
|
{
|
|
"entropy": 6.317183208465576,
|
|
"epoch": 1.9017843754685861,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046421044527913713,
|
|
"loss": 5.6036,
|
|
"mean_token_accuracy": 0.19325114488601686,
|
|
"num_tokens": 37200739.0,
|
|
"step": 19025
|
|
},
|
|
{
|
|
"entropy": 6.341985511779785,
|
|
"epoch": 1.9022842005298146,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004641911302534737,
|
|
"loss": 5.683,
|
|
"mean_token_accuracy": 0.18456723690032958,
|
|
"num_tokens": 37209507.0,
|
|
"step": 19030
|
|
},
|
|
{
|
|
"entropy": 6.2820408821105955,
|
|
"epoch": 1.902784025591043,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046417181046781004,
|
|
"loss": 5.6685,
|
|
"mean_token_accuracy": 0.1912584826350212,
|
|
"num_tokens": 37219252.0,
|
|
"step": 19035
|
|
},
|
|
{
|
|
"entropy": 6.267204618453979,
|
|
"epoch": 1.9032838506522718,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004641524859226324,
|
|
"loss": 5.6081,
|
|
"mean_token_accuracy": 0.18701117634773254,
|
|
"num_tokens": 37229925.0,
|
|
"step": 19040
|
|
},
|
|
{
|
|
"entropy": 6.235636234283447,
|
|
"epoch": 1.9037836757135003,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00046413315661842676,
|
|
"loss": 5.6566,
|
|
"mean_token_accuracy": 0.19395248740911483,
|
|
"num_tokens": 37239513.0,
|
|
"step": 19045
|
|
},
|
|
{
|
|
"entropy": 6.302892208099365,
|
|
"epoch": 1.9042835007747287,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004641138225556797,
|
|
"loss": 5.6517,
|
|
"mean_token_accuracy": 0.1875390037894249,
|
|
"num_tokens": 37249143.0,
|
|
"step": 19050
|
|
},
|
|
{
|
|
"entropy": 6.296295213699341,
|
|
"epoch": 1.9047833258359574,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004640944837348774,
|
|
"loss": 5.595,
|
|
"mean_token_accuracy": 0.18987502306699752,
|
|
"num_tokens": 37258834.0,
|
|
"step": 19055
|
|
},
|
|
{
|
|
"entropy": 6.295371389389038,
|
|
"epoch": 1.9052831508971861,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046407514015650667,
|
|
"loss": 5.7063,
|
|
"mean_token_accuracy": 0.18541822135448455,
|
|
"num_tokens": 37269554.0,
|
|
"step": 19060
|
|
},
|
|
{
|
|
"entropy": 6.305230760574341,
|
|
"epoch": 1.9057829759584144,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046405579182105393,
|
|
"loss": 5.6779,
|
|
"mean_token_accuracy": 0.18317256718873978,
|
|
"num_tokens": 37278842.0,
|
|
"step": 19065
|
|
},
|
|
{
|
|
"entropy": 6.2618495464324955,
|
|
"epoch": 1.906282801019643,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004640364387290062,
|
|
"loss": 5.6434,
|
|
"mean_token_accuracy": 0.1896285355091095,
|
|
"num_tokens": 37289056.0,
|
|
"step": 19070
|
|
},
|
|
{
|
|
"entropy": 6.230567264556885,
|
|
"epoch": 1.9067826260808718,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00046401708088085036,
|
|
"loss": 5.6462,
|
|
"mean_token_accuracy": 0.19375075846910478,
|
|
"num_tokens": 37298823.0,
|
|
"step": 19075
|
|
},
|
|
{
|
|
"entropy": 6.336221504211426,
|
|
"epoch": 1.9072824511421003,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046399771827707335,
|
|
"loss": 5.7723,
|
|
"mean_token_accuracy": 0.18121131360530854,
|
|
"num_tokens": 37310065.0,
|
|
"step": 19080
|
|
},
|
|
{
|
|
"entropy": 6.326562929153442,
|
|
"epoch": 1.9077822762033287,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046397835091816235,
|
|
"loss": 5.6725,
|
|
"mean_token_accuracy": 0.18217943757772445,
|
|
"num_tokens": 37320856.0,
|
|
"step": 19085
|
|
},
|
|
{
|
|
"entropy": 6.331386566162109,
|
|
"epoch": 1.9082821012645574,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00046395897880460474,
|
|
"loss": 5.7026,
|
|
"mean_token_accuracy": 0.18943878412246704,
|
|
"num_tokens": 37330705.0,
|
|
"step": 19090
|
|
},
|
|
{
|
|
"entropy": 6.279166316986084,
|
|
"epoch": 1.9087819263257861,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00046393960193688783,
|
|
"loss": 5.6717,
|
|
"mean_token_accuracy": 0.19205661863088608,
|
|
"num_tokens": 37339450.0,
|
|
"step": 19095
|
|
},
|
|
{
|
|
"entropy": 6.255859375,
|
|
"epoch": 1.9092817513870144,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046392022031549907,
|
|
"loss": 5.6493,
|
|
"mean_token_accuracy": 0.19097375869750977,
|
|
"num_tokens": 37349173.0,
|
|
"step": 19100
|
|
},
|
|
{
|
|
"entropy": 6.297963190078735,
|
|
"epoch": 1.909781576448243,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004639008339409263,
|
|
"loss": 5.7749,
|
|
"mean_token_accuracy": 0.17749871015548707,
|
|
"num_tokens": 37359246.0,
|
|
"step": 19105
|
|
},
|
|
{
|
|
"entropy": 6.330770540237427,
|
|
"epoch": 1.9102814015094718,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004638814428136571,
|
|
"loss": 5.75,
|
|
"mean_token_accuracy": 0.18420721143484114,
|
|
"num_tokens": 37368056.0,
|
|
"step": 19110
|
|
},
|
|
{
|
|
"entropy": 6.438050413131714,
|
|
"epoch": 1.9107812265707003,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004638620469341794,
|
|
"loss": 5.8952,
|
|
"mean_token_accuracy": 0.16977925151586531,
|
|
"num_tokens": 37377997.0,
|
|
"step": 19115
|
|
},
|
|
{
|
|
"entropy": 6.279723310470581,
|
|
"epoch": 1.9112810516319287,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004638426463029812,
|
|
"loss": 5.6203,
|
|
"mean_token_accuracy": 0.18548129498958588,
|
|
"num_tokens": 37387365.0,
|
|
"step": 19120
|
|
},
|
|
{
|
|
"entropy": 6.308482265472412,
|
|
"epoch": 1.9117808766931574,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004638232409205506,
|
|
"loss": 5.6763,
|
|
"mean_token_accuracy": 0.1825825899839401,
|
|
"num_tokens": 37396649.0,
|
|
"step": 19125
|
|
},
|
|
{
|
|
"entropy": 6.295954036712646,
|
|
"epoch": 1.912280701754386,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046380383078737584,
|
|
"loss": 5.7507,
|
|
"mean_token_accuracy": 0.18126633763313293,
|
|
"num_tokens": 37407576.0,
|
|
"step": 19130
|
|
},
|
|
{
|
|
"entropy": 6.329332590103149,
|
|
"epoch": 1.9127805268156144,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046378441590394525,
|
|
"loss": 5.6908,
|
|
"mean_token_accuracy": 0.1830546349287033,
|
|
"num_tokens": 37419270.0,
|
|
"step": 19135
|
|
},
|
|
{
|
|
"entropy": 6.340182733535767,
|
|
"epoch": 1.913280351876843,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004637649962707474,
|
|
"loss": 5.7229,
|
|
"mean_token_accuracy": 0.1781681776046753,
|
|
"num_tokens": 37429155.0,
|
|
"step": 19140
|
|
},
|
|
{
|
|
"entropy": 6.306576776504516,
|
|
"epoch": 1.9137801769380718,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046374557188827084,
|
|
"loss": 5.7007,
|
|
"mean_token_accuracy": 0.1877602979540825,
|
|
"num_tokens": 37439952.0,
|
|
"step": 19145
|
|
},
|
|
{
|
|
"entropy": 6.306686735153198,
|
|
"epoch": 1.9142800019993003,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004637261427570042,
|
|
"loss": 5.6758,
|
|
"mean_token_accuracy": 0.183102585375309,
|
|
"num_tokens": 37449537.0,
|
|
"step": 19150
|
|
},
|
|
{
|
|
"entropy": 6.264483404159546,
|
|
"epoch": 1.9147798270605287,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004637067088774364,
|
|
"loss": 5.7108,
|
|
"mean_token_accuracy": 0.18334032744169235,
|
|
"num_tokens": 37460202.0,
|
|
"step": 19155
|
|
},
|
|
{
|
|
"entropy": 6.285115385055542,
|
|
"epoch": 1.9152796521217574,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046368727025005634,
|
|
"loss": 5.6527,
|
|
"mean_token_accuracy": 0.18644581139087676,
|
|
"num_tokens": 37469715.0,
|
|
"step": 19160
|
|
},
|
|
{
|
|
"entropy": 6.337317705154419,
|
|
"epoch": 1.915779477182986,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046366782687535315,
|
|
"loss": 5.7222,
|
|
"mean_token_accuracy": 0.1814061611890793,
|
|
"num_tokens": 37478495.0,
|
|
"step": 19165
|
|
},
|
|
{
|
|
"entropy": 6.314341259002686,
|
|
"epoch": 1.9162793022442144,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000463648378753816,
|
|
"loss": 5.7619,
|
|
"mean_token_accuracy": 0.17998271137475969,
|
|
"num_tokens": 37488125.0,
|
|
"step": 19170
|
|
},
|
|
{
|
|
"entropy": 6.264962291717529,
|
|
"epoch": 1.916779127305443,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046362892588593406,
|
|
"loss": 5.5719,
|
|
"mean_token_accuracy": 0.19342506378889085,
|
|
"num_tokens": 37498097.0,
|
|
"step": 19175
|
|
},
|
|
{
|
|
"entropy": 6.298321962356567,
|
|
"epoch": 1.9172789523666718,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046360946827219703,
|
|
"loss": 5.7576,
|
|
"mean_token_accuracy": 0.18541185706853866,
|
|
"num_tokens": 37507713.0,
|
|
"step": 19180
|
|
},
|
|
{
|
|
"entropy": 6.322887277603149,
|
|
"epoch": 1.9177787774279003,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004635900059130942,
|
|
"loss": 5.7368,
|
|
"mean_token_accuracy": 0.1831180840730667,
|
|
"num_tokens": 37517862.0,
|
|
"step": 19185
|
|
},
|
|
{
|
|
"entropy": 6.291020059585572,
|
|
"epoch": 1.9182786024891287,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004635705388091154,
|
|
"loss": 5.6893,
|
|
"mean_token_accuracy": 0.18089330196380615,
|
|
"num_tokens": 37528988.0,
|
|
"step": 19190
|
|
},
|
|
{
|
|
"entropy": 6.305382490158081,
|
|
"epoch": 1.9187784275503574,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004635510669607504,
|
|
"loss": 5.7837,
|
|
"mean_token_accuracy": 0.17768747806549073,
|
|
"num_tokens": 37538467.0,
|
|
"step": 19195
|
|
},
|
|
{
|
|
"entropy": 6.309880304336548,
|
|
"epoch": 1.919278252611586,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000463531590368489,
|
|
"loss": 5.6265,
|
|
"mean_token_accuracy": 0.1798609808087349,
|
|
"num_tokens": 37547986.0,
|
|
"step": 19200
|
|
},
|
|
{
|
|
"entropy": 6.293581771850586,
|
|
"epoch": 1.9197780776728144,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00046351210903282136,
|
|
"loss": 5.752,
|
|
"mean_token_accuracy": 0.18208894580602647,
|
|
"num_tokens": 37557403.0,
|
|
"step": 19205
|
|
},
|
|
{
|
|
"entropy": 6.286957883834839,
|
|
"epoch": 1.920277902734043,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046349262295423754,
|
|
"loss": 5.6875,
|
|
"mean_token_accuracy": 0.18514282405376434,
|
|
"num_tokens": 37568504.0,
|
|
"step": 19210
|
|
},
|
|
{
|
|
"entropy": 6.335913228988647,
|
|
"epoch": 1.9207777277952718,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00046347313213322786,
|
|
"loss": 5.6708,
|
|
"mean_token_accuracy": 0.18373890668153764,
|
|
"num_tokens": 37577816.0,
|
|
"step": 19215
|
|
},
|
|
{
|
|
"entropy": 6.292560815811157,
|
|
"epoch": 1.9212775528565003,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004634536365702826,
|
|
"loss": 5.6093,
|
|
"mean_token_accuracy": 0.18711042553186416,
|
|
"num_tokens": 37587315.0,
|
|
"step": 19220
|
|
},
|
|
{
|
|
"entropy": 6.3475665092468265,
|
|
"epoch": 1.9217773779177287,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00046343413626589243,
|
|
"loss": 5.748,
|
|
"mean_token_accuracy": 0.179219052195549,
|
|
"num_tokens": 37597708.0,
|
|
"step": 19225
|
|
},
|
|
{
|
|
"entropy": 6.247457647323609,
|
|
"epoch": 1.9222772029789574,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004634146312205478,
|
|
"loss": 5.5706,
|
|
"mean_token_accuracy": 0.2064844325184822,
|
|
"num_tokens": 37608093.0,
|
|
"step": 19230
|
|
},
|
|
{
|
|
"entropy": 6.224476861953735,
|
|
"epoch": 1.922777028040186,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046339512143473956,
|
|
"loss": 5.6266,
|
|
"mean_token_accuracy": 0.1855505347251892,
|
|
"num_tokens": 37617742.0,
|
|
"step": 19235
|
|
},
|
|
{
|
|
"entropy": 6.2903142929077145,
|
|
"epoch": 1.9232768531014144,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046337560690895856,
|
|
"loss": 5.6667,
|
|
"mean_token_accuracy": 0.18465671837329864,
|
|
"num_tokens": 37626999.0,
|
|
"step": 19240
|
|
},
|
|
{
|
|
"entropy": 6.340635538101196,
|
|
"epoch": 1.923776678162643,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046335608764369574,
|
|
"loss": 5.7698,
|
|
"mean_token_accuracy": 0.17550156712532045,
|
|
"num_tokens": 37638142.0,
|
|
"step": 19245
|
|
},
|
|
{
|
|
"entropy": 6.293743848800659,
|
|
"epoch": 1.9242765032238718,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046333656363944226,
|
|
"loss": 5.7127,
|
|
"mean_token_accuracy": 0.18628273159265518,
|
|
"num_tokens": 37647373.0,
|
|
"step": 19250
|
|
},
|
|
{
|
|
"entropy": 6.246408843994141,
|
|
"epoch": 1.9247763282851003,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00046331703489668925,
|
|
"loss": 5.6324,
|
|
"mean_token_accuracy": 0.1896443024277687,
|
|
"num_tokens": 37658677.0,
|
|
"step": 19255
|
|
},
|
|
{
|
|
"entropy": 6.205169343948365,
|
|
"epoch": 1.9252761533463287,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046329750141592814,
|
|
"loss": 5.5386,
|
|
"mean_token_accuracy": 0.19803785234689714,
|
|
"num_tokens": 37668344.0,
|
|
"step": 19260
|
|
},
|
|
{
|
|
"entropy": 6.214850425720215,
|
|
"epoch": 1.9257759784075574,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004632779631976503,
|
|
"loss": 5.6184,
|
|
"mean_token_accuracy": 0.18516730517148972,
|
|
"num_tokens": 37678000.0,
|
|
"step": 19265
|
|
},
|
|
{
|
|
"entropy": 6.310432481765747,
|
|
"epoch": 1.926275803468786,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046325842024234735,
|
|
"loss": 5.781,
|
|
"mean_token_accuracy": 0.17967032343149186,
|
|
"num_tokens": 37688404.0,
|
|
"step": 19270
|
|
},
|
|
{
|
|
"entropy": 6.324656677246094,
|
|
"epoch": 1.9267756285300144,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046323887255051105,
|
|
"loss": 5.7021,
|
|
"mean_token_accuracy": 0.18711716830730438,
|
|
"num_tokens": 37697699.0,
|
|
"step": 19275
|
|
},
|
|
{
|
|
"entropy": 6.328532266616821,
|
|
"epoch": 1.927275453591243,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00046321932012263317,
|
|
"loss": 5.5972,
|
|
"mean_token_accuracy": 0.19243917912244796,
|
|
"num_tokens": 37707261.0,
|
|
"step": 19280
|
|
},
|
|
{
|
|
"entropy": 6.2623837947845455,
|
|
"epoch": 1.9277752786524718,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004631997629592055,
|
|
"loss": 5.6446,
|
|
"mean_token_accuracy": 0.1821594014763832,
|
|
"num_tokens": 37716500.0,
|
|
"step": 19285
|
|
},
|
|
{
|
|
"entropy": 6.182284736633301,
|
|
"epoch": 1.9282751037137003,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004631802010607204,
|
|
"loss": 5.5744,
|
|
"mean_token_accuracy": 0.1880323886871338,
|
|
"num_tokens": 37725881.0,
|
|
"step": 19290
|
|
},
|
|
{
|
|
"entropy": 6.207870388031006,
|
|
"epoch": 1.9287749287749287,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046316063442766975,
|
|
"loss": 5.6164,
|
|
"mean_token_accuracy": 0.19331529438495637,
|
|
"num_tokens": 37736233.0,
|
|
"step": 19295
|
|
},
|
|
{
|
|
"entropy": 6.344576597213745,
|
|
"epoch": 1.9292747538361574,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00046314106306054596,
|
|
"loss": 5.6726,
|
|
"mean_token_accuracy": 0.18719703257083892,
|
|
"num_tokens": 37747230.0,
|
|
"step": 19300
|
|
},
|
|
{
|
|
"entropy": 6.306136226654052,
|
|
"epoch": 1.929774578897386,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046312148695984147,
|
|
"loss": 5.6795,
|
|
"mean_token_accuracy": 0.18491515666246414,
|
|
"num_tokens": 37758470.0,
|
|
"step": 19305
|
|
},
|
|
{
|
|
"entropy": 6.357076692581177,
|
|
"epoch": 1.9302744039586144,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004631019061260488,
|
|
"loss": 5.7134,
|
|
"mean_token_accuracy": 0.19000933915376664,
|
|
"num_tokens": 37767912.0,
|
|
"step": 19310
|
|
},
|
|
{
|
|
"entropy": 6.279764699935913,
|
|
"epoch": 1.930774229019843,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004630823205596605,
|
|
"loss": 5.6169,
|
|
"mean_token_accuracy": 0.1837780237197876,
|
|
"num_tokens": 37776847.0,
|
|
"step": 19315
|
|
},
|
|
{
|
|
"entropy": 6.285478830337524,
|
|
"epoch": 1.9312740540810718,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046306273026116944,
|
|
"loss": 5.7172,
|
|
"mean_token_accuracy": 0.17899317294359207,
|
|
"num_tokens": 37786960.0,
|
|
"step": 19320
|
|
},
|
|
{
|
|
"entropy": 6.262777948379517,
|
|
"epoch": 1.9317738791423,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004630431352310685,
|
|
"loss": 5.7102,
|
|
"mean_token_accuracy": 0.1793321430683136,
|
|
"num_tokens": 37797007.0,
|
|
"step": 19325
|
|
},
|
|
{
|
|
"entropy": 6.269992780685425,
|
|
"epoch": 1.9322737042035287,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046302353546985066,
|
|
"loss": 5.6214,
|
|
"mean_token_accuracy": 0.1892771065235138,
|
|
"num_tokens": 37806877.0,
|
|
"step": 19330
|
|
},
|
|
{
|
|
"entropy": 6.281510972976685,
|
|
"epoch": 1.9327735292647574,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000463003930978009,
|
|
"loss": 5.6074,
|
|
"mean_token_accuracy": 0.18379399329423904,
|
|
"num_tokens": 37815513.0,
|
|
"step": 19335
|
|
},
|
|
{
|
|
"entropy": 6.261120557785034,
|
|
"epoch": 1.933273354325986,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004629843217560369,
|
|
"loss": 5.5954,
|
|
"mean_token_accuracy": 0.1910167381167412,
|
|
"num_tokens": 37825240.0,
|
|
"step": 19340
|
|
},
|
|
{
|
|
"entropy": 6.305397653579712,
|
|
"epoch": 1.9337731793872144,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004629647078044276,
|
|
"loss": 5.6966,
|
|
"mean_token_accuracy": 0.1851574257016182,
|
|
"num_tokens": 37834333.0,
|
|
"step": 19345
|
|
},
|
|
{
|
|
"entropy": 6.2862835884094235,
|
|
"epoch": 1.934273004448443,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004629450891236746,
|
|
"loss": 5.652,
|
|
"mean_token_accuracy": 0.18419956266880036,
|
|
"num_tokens": 37844548.0,
|
|
"step": 19350
|
|
},
|
|
{
|
|
"entropy": 6.270841932296753,
|
|
"epoch": 1.9347728295096718,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004629254657142715,
|
|
"loss": 5.6499,
|
|
"mean_token_accuracy": 0.1870452269911766,
|
|
"num_tokens": 37853995.0,
|
|
"step": 19355
|
|
},
|
|
{
|
|
"entropy": 6.315723133087158,
|
|
"epoch": 1.9352726545709,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004629058375767121,
|
|
"loss": 5.7209,
|
|
"mean_token_accuracy": 0.1799814820289612,
|
|
"num_tokens": 37863472.0,
|
|
"step": 19360
|
|
},
|
|
{
|
|
"entropy": 6.350312900543213,
|
|
"epoch": 1.9357724796321287,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046288620471149014,
|
|
"loss": 5.7058,
|
|
"mean_token_accuracy": 0.189127816259861,
|
|
"num_tokens": 37872690.0,
|
|
"step": 19365
|
|
},
|
|
{
|
|
"entropy": 6.3357056140899655,
|
|
"epoch": 1.9362723046933574,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046286656711909966,
|
|
"loss": 5.7164,
|
|
"mean_token_accuracy": 0.18330460488796235,
|
|
"num_tokens": 37882296.0,
|
|
"step": 19370
|
|
},
|
|
{
|
|
"entropy": 6.243350219726563,
|
|
"epoch": 1.936772129754586,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00046284692480003467,
|
|
"loss": 5.6811,
|
|
"mean_token_accuracy": 0.18344116508960723,
|
|
"num_tokens": 37891612.0,
|
|
"step": 19375
|
|
},
|
|
{
|
|
"entropy": 6.317243194580078,
|
|
"epoch": 1.9372719548158144,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046282727775478935,
|
|
"loss": 5.6397,
|
|
"mean_token_accuracy": 0.183761391043663,
|
|
"num_tokens": 37901107.0,
|
|
"step": 19380
|
|
},
|
|
{
|
|
"entropy": 6.297483253479004,
|
|
"epoch": 1.937771779877043,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004628076259838581,
|
|
"loss": 5.783,
|
|
"mean_token_accuracy": 0.1805945798754692,
|
|
"num_tokens": 37912020.0,
|
|
"step": 19385
|
|
},
|
|
{
|
|
"entropy": 6.265715837478638,
|
|
"epoch": 1.9382716049382716,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046278796948773525,
|
|
"loss": 5.6792,
|
|
"mean_token_accuracy": 0.182799731194973,
|
|
"num_tokens": 37922681.0,
|
|
"step": 19390
|
|
},
|
|
{
|
|
"entropy": 6.340760612487793,
|
|
"epoch": 1.9387714299995,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046276830826691553,
|
|
"loss": 5.7064,
|
|
"mean_token_accuracy": 0.18309623301029204,
|
|
"num_tokens": 37934322.0,
|
|
"step": 19395
|
|
},
|
|
{
|
|
"entropy": 6.2607481479644775,
|
|
"epoch": 1.9392712550607287,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00046274864232189334,
|
|
"loss": 5.6814,
|
|
"mean_token_accuracy": 0.18700465708971023,
|
|
"num_tokens": 37945028.0,
|
|
"step": 19400
|
|
},
|
|
{
|
|
"entropy": 6.247370100021362,
|
|
"epoch": 1.9397710801219574,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046272897165316367,
|
|
"loss": 5.6004,
|
|
"mean_token_accuracy": 0.18575705140829085,
|
|
"num_tokens": 37955055.0,
|
|
"step": 19405
|
|
},
|
|
{
|
|
"entropy": 6.310463809967041,
|
|
"epoch": 1.940270905183186,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004627092962612215,
|
|
"loss": 5.6859,
|
|
"mean_token_accuracy": 0.19178764820098876,
|
|
"num_tokens": 37966018.0,
|
|
"step": 19410
|
|
},
|
|
{
|
|
"entropy": 6.284039545059204,
|
|
"epoch": 1.9407707302444144,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004626896161465616,
|
|
"loss": 5.6344,
|
|
"mean_token_accuracy": 0.19010500460863114,
|
|
"num_tokens": 37975541.0,
|
|
"step": 19415
|
|
},
|
|
{
|
|
"entropy": 6.30906925201416,
|
|
"epoch": 1.941270555305643,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046266993130967925,
|
|
"loss": 5.6601,
|
|
"mean_token_accuracy": 0.182487590610981,
|
|
"num_tokens": 37986312.0,
|
|
"step": 19420
|
|
},
|
|
{
|
|
"entropy": 6.26467604637146,
|
|
"epoch": 1.9417703803668716,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004626502417510698,
|
|
"loss": 5.6953,
|
|
"mean_token_accuracy": 0.17881643921136856,
|
|
"num_tokens": 37994717.0,
|
|
"step": 19425
|
|
},
|
|
{
|
|
"entropy": 6.301655101776123,
|
|
"epoch": 1.9422702054281,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00046263054747122857,
|
|
"loss": 5.7637,
|
|
"mean_token_accuracy": 0.17918247878551483,
|
|
"num_tokens": 38004282.0,
|
|
"step": 19430
|
|
},
|
|
{
|
|
"entropy": 6.343066120147705,
|
|
"epoch": 1.9427700304893287,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004626108484706509,
|
|
"loss": 5.7142,
|
|
"mean_token_accuracy": 0.184169739484787,
|
|
"num_tokens": 38013255.0,
|
|
"step": 19435
|
|
},
|
|
{
|
|
"entropy": 6.324895191192627,
|
|
"epoch": 1.9432698555505574,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046259114474983266,
|
|
"loss": 5.6703,
|
|
"mean_token_accuracy": 0.19030212312936784,
|
|
"num_tokens": 38023041.0,
|
|
"step": 19440
|
|
},
|
|
{
|
|
"entropy": 6.310053920745849,
|
|
"epoch": 1.943769680611786,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046257143630926953,
|
|
"loss": 5.6749,
|
|
"mean_token_accuracy": 0.1869705379009247,
|
|
"num_tokens": 38032193.0,
|
|
"step": 19445
|
|
},
|
|
{
|
|
"entropy": 6.299991607666016,
|
|
"epoch": 1.9442695056730144,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004625517231494573,
|
|
"loss": 5.6757,
|
|
"mean_token_accuracy": 0.18356558531522751,
|
|
"num_tokens": 38041470.0,
|
|
"step": 19450
|
|
},
|
|
{
|
|
"entropy": 6.15401062965393,
|
|
"epoch": 1.944769330734243,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004625320052708919,
|
|
"loss": 5.5035,
|
|
"mean_token_accuracy": 0.19961873143911363,
|
|
"num_tokens": 38051997.0,
|
|
"step": 19455
|
|
},
|
|
{
|
|
"entropy": 6.26406626701355,
|
|
"epoch": 1.9452691557954715,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004625122826740696,
|
|
"loss": 5.7025,
|
|
"mean_token_accuracy": 0.19005055874586105,
|
|
"num_tokens": 38061418.0,
|
|
"step": 19460
|
|
},
|
|
{
|
|
"entropy": 6.256187438964844,
|
|
"epoch": 1.9457689808567,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004624925553594865,
|
|
"loss": 5.5935,
|
|
"mean_token_accuracy": 0.19101831316947937,
|
|
"num_tokens": 38070853.0,
|
|
"step": 19465
|
|
},
|
|
{
|
|
"entropy": 6.346727275848389,
|
|
"epoch": 1.9462688059179287,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004624728233276389,
|
|
"loss": 5.7226,
|
|
"mean_token_accuracy": 0.17903521806001663,
|
|
"num_tokens": 38080565.0,
|
|
"step": 19470
|
|
},
|
|
{
|
|
"entropy": 6.264834785461426,
|
|
"epoch": 1.9467686309791574,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046245308657902334,
|
|
"loss": 5.5694,
|
|
"mean_token_accuracy": 0.20008725374937059,
|
|
"num_tokens": 38090899.0,
|
|
"step": 19475
|
|
},
|
|
{
|
|
"entropy": 6.237497472763062,
|
|
"epoch": 1.947268456040386,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004624333451141364,
|
|
"loss": 5.6137,
|
|
"mean_token_accuracy": 0.1918997883796692,
|
|
"num_tokens": 38100104.0,
|
|
"step": 19480
|
|
},
|
|
{
|
|
"entropy": 6.23376841545105,
|
|
"epoch": 1.9477682811016144,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004624135989334746,
|
|
"loss": 5.6833,
|
|
"mean_token_accuracy": 0.1873346149921417,
|
|
"num_tokens": 38109720.0,
|
|
"step": 19485
|
|
},
|
|
{
|
|
"entropy": 6.251634883880615,
|
|
"epoch": 1.948268106162843,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00046239384803753496,
|
|
"loss": 5.6897,
|
|
"mean_token_accuracy": 0.1876625820994377,
|
|
"num_tokens": 38119703.0,
|
|
"step": 19490
|
|
},
|
|
{
|
|
"entropy": 6.322715759277344,
|
|
"epoch": 1.9487679312240715,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046237409242681435,
|
|
"loss": 5.6139,
|
|
"mean_token_accuracy": 0.18311047405004502,
|
|
"num_tokens": 38129329.0,
|
|
"step": 19495
|
|
},
|
|
{
|
|
"entropy": 6.357153701782226,
|
|
"epoch": 1.9492677562853,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004623543321018097,
|
|
"loss": 5.6634,
|
|
"mean_token_accuracy": 0.18066980987787246,
|
|
"num_tokens": 38138607.0,
|
|
"step": 19500
|
|
},
|
|
{
|
|
"entropy": 6.248847723007202,
|
|
"epoch": 1.9497675813465287,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004623345670630184,
|
|
"loss": 5.6673,
|
|
"mean_token_accuracy": 0.18808155953884126,
|
|
"num_tokens": 38148749.0,
|
|
"step": 19505
|
|
},
|
|
{
|
|
"entropy": 6.309657144546509,
|
|
"epoch": 1.9502674064077574,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004623147973109375,
|
|
"loss": 5.7321,
|
|
"mean_token_accuracy": 0.1807377189397812,
|
|
"num_tokens": 38158929.0,
|
|
"step": 19510
|
|
},
|
|
{
|
|
"entropy": 6.310500907897949,
|
|
"epoch": 1.950767231468986,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046229502284606455,
|
|
"loss": 5.6008,
|
|
"mean_token_accuracy": 0.1911633864045143,
|
|
"num_tokens": 38169966.0,
|
|
"step": 19515
|
|
},
|
|
{
|
|
"entropy": 6.3343016624450685,
|
|
"epoch": 1.9512670565302144,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000462275243668897,
|
|
"loss": 5.635,
|
|
"mean_token_accuracy": 0.18781027793884278,
|
|
"num_tokens": 38180363.0,
|
|
"step": 19520
|
|
},
|
|
{
|
|
"entropy": 6.297638607025147,
|
|
"epoch": 1.951766881591443,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00046225545977993245,
|
|
"loss": 5.6125,
|
|
"mean_token_accuracy": 0.1878717765212059,
|
|
"num_tokens": 38190802.0,
|
|
"step": 19525
|
|
},
|
|
{
|
|
"entropy": 6.293096590042114,
|
|
"epoch": 1.9522667066526715,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004622356711796688,
|
|
"loss": 5.6805,
|
|
"mean_token_accuracy": 0.18823036998510362,
|
|
"num_tokens": 38201183.0,
|
|
"step": 19530
|
|
},
|
|
{
|
|
"entropy": 6.348311901092529,
|
|
"epoch": 1.9527665317139,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004622158778686038,
|
|
"loss": 5.7313,
|
|
"mean_token_accuracy": 0.1822906330227852,
|
|
"num_tokens": 38210953.0,
|
|
"step": 19535
|
|
},
|
|
{
|
|
"entropy": 6.264783525466919,
|
|
"epoch": 1.9532663567751287,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00046219607984723554,
|
|
"loss": 5.5892,
|
|
"mean_token_accuracy": 0.19491996467113495,
|
|
"num_tokens": 38220335.0,
|
|
"step": 19540
|
|
},
|
|
{
|
|
"entropy": 6.296955108642578,
|
|
"epoch": 1.9537661818363574,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00046217627711606205,
|
|
"loss": 5.6449,
|
|
"mean_token_accuracy": 0.18167179226875305,
|
|
"num_tokens": 38230530.0,
|
|
"step": 19545
|
|
},
|
|
{
|
|
"entropy": 6.328058815002441,
|
|
"epoch": 1.954266006897586,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00046215646967558155,
|
|
"loss": 5.5991,
|
|
"mean_token_accuracy": 0.1932425543665886,
|
|
"num_tokens": 38241275.0,
|
|
"step": 19550
|
|
},
|
|
{
|
|
"entropy": 6.359179258346558,
|
|
"epoch": 1.9547658319588144,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046213665752629246,
|
|
"loss": 5.6193,
|
|
"mean_token_accuracy": 0.19009732455015182,
|
|
"num_tokens": 38250158.0,
|
|
"step": 19555
|
|
},
|
|
{
|
|
"entropy": 6.308062505722046,
|
|
"epoch": 1.955265657020043,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004621168406686933,
|
|
"loss": 5.8491,
|
|
"mean_token_accuracy": 0.1766134664416313,
|
|
"num_tokens": 38259172.0,
|
|
"step": 19560
|
|
},
|
|
{
|
|
"entropy": 6.285812711715698,
|
|
"epoch": 1.9557654820812715,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046209701910328245,
|
|
"loss": 5.6776,
|
|
"mean_token_accuracy": 0.18310826718807222,
|
|
"num_tokens": 38268261.0,
|
|
"step": 19565
|
|
},
|
|
{
|
|
"entropy": 6.295361757278442,
|
|
"epoch": 1.9562653071425,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004620771928305588,
|
|
"loss": 5.6315,
|
|
"mean_token_accuracy": 0.19333881586790086,
|
|
"num_tokens": 38277843.0,
|
|
"step": 19570
|
|
},
|
|
{
|
|
"entropy": 6.235561895370483,
|
|
"epoch": 1.9567651322037287,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004620573618510211,
|
|
"loss": 5.5473,
|
|
"mean_token_accuracy": 0.19245010912418364,
|
|
"num_tokens": 38286878.0,
|
|
"step": 19575
|
|
},
|
|
{
|
|
"entropy": 6.30403208732605,
|
|
"epoch": 1.9572649572649574,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046203752616516834,
|
|
"loss": 5.5783,
|
|
"mean_token_accuracy": 0.1916244924068451,
|
|
"num_tokens": 38296289.0,
|
|
"step": 19580
|
|
},
|
|
{
|
|
"entropy": 6.35041880607605,
|
|
"epoch": 1.9577647823261857,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046201768577349957,
|
|
"loss": 5.7526,
|
|
"mean_token_accuracy": 0.17415452599525452,
|
|
"num_tokens": 38305238.0,
|
|
"step": 19585
|
|
},
|
|
{
|
|
"entropy": 6.245187520980835,
|
|
"epoch": 1.9582646073874144,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004619978406765139,
|
|
"loss": 5.6292,
|
|
"mean_token_accuracy": 0.18717288821935654,
|
|
"num_tokens": 38315079.0,
|
|
"step": 19590
|
|
},
|
|
{
|
|
"entropy": 6.337327909469605,
|
|
"epoch": 1.958764432448643,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004619779908747107,
|
|
"loss": 5.7103,
|
|
"mean_token_accuracy": 0.18505097776651383,
|
|
"num_tokens": 38324314.0,
|
|
"step": 19595
|
|
},
|
|
{
|
|
"entropy": 6.367226934432983,
|
|
"epoch": 1.9592642575098715,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004619581363685893,
|
|
"loss": 5.6983,
|
|
"mean_token_accuracy": 0.17370794117450714,
|
|
"num_tokens": 38334708.0,
|
|
"step": 19600
|
|
},
|
|
{
|
|
"entropy": 6.3441180229187015,
|
|
"epoch": 1.9597640825711,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004619382771586494,
|
|
"loss": 5.7032,
|
|
"mean_token_accuracy": 0.1816618859767914,
|
|
"num_tokens": 38344800.0,
|
|
"step": 19605
|
|
},
|
|
{
|
|
"entropy": 6.19998025894165,
|
|
"epoch": 1.9602639076323287,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004619184132453905,
|
|
"loss": 5.6236,
|
|
"mean_token_accuracy": 0.19138552993535995,
|
|
"num_tokens": 38354778.0,
|
|
"step": 19610
|
|
},
|
|
{
|
|
"entropy": 6.313777446746826,
|
|
"epoch": 1.9607637326935574,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004618985446293125,
|
|
"loss": 5.6035,
|
|
"mean_token_accuracy": 0.18619737774133682,
|
|
"num_tokens": 38365032.0,
|
|
"step": 19615
|
|
},
|
|
{
|
|
"entropy": 6.2957720279693605,
|
|
"epoch": 1.9612635577547857,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046187867131091504,
|
|
"loss": 5.6221,
|
|
"mean_token_accuracy": 0.19033189713954926,
|
|
"num_tokens": 38375051.0,
|
|
"step": 19620
|
|
},
|
|
{
|
|
"entropy": 6.240505599975586,
|
|
"epoch": 1.9617633828160144,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004618587932906984,
|
|
"loss": 5.6311,
|
|
"mean_token_accuracy": 0.19147706478834153,
|
|
"num_tokens": 38384107.0,
|
|
"step": 19625
|
|
},
|
|
{
|
|
"entropy": 6.1941791534423825,
|
|
"epoch": 1.962263207877243,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00046183891056916256,
|
|
"loss": 5.4927,
|
|
"mean_token_accuracy": 0.20570458471775055,
|
|
"num_tokens": 38394054.0,
|
|
"step": 19630
|
|
},
|
|
{
|
|
"entropy": 6.321862745285034,
|
|
"epoch": 1.9627630329384715,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004618190231468079,
|
|
"loss": 5.6889,
|
|
"mean_token_accuracy": 0.18334731161594392,
|
|
"num_tokens": 38403001.0,
|
|
"step": 19635
|
|
},
|
|
{
|
|
"entropy": 6.1807530403137205,
|
|
"epoch": 1.9632628579997,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046179913102413456,
|
|
"loss": 5.5691,
|
|
"mean_token_accuracy": 0.19501296877861024,
|
|
"num_tokens": 38412752.0,
|
|
"step": 19640
|
|
},
|
|
{
|
|
"entropy": 6.365077638626099,
|
|
"epoch": 1.9637626830609287,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004617792342016433,
|
|
"loss": 5.7812,
|
|
"mean_token_accuracy": 0.17603181749582292,
|
|
"num_tokens": 38423523.0,
|
|
"step": 19645
|
|
},
|
|
{
|
|
"entropy": 6.420029067993164,
|
|
"epoch": 1.9642625081221572,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004617593326798344,
|
|
"loss": 5.6929,
|
|
"mean_token_accuracy": 0.18581640273332595,
|
|
"num_tokens": 38433062.0,
|
|
"step": 19650
|
|
},
|
|
{
|
|
"entropy": 6.320886182785034,
|
|
"epoch": 1.9647623331833857,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004617394264592089,
|
|
"loss": 5.766,
|
|
"mean_token_accuracy": 0.17569827437400817,
|
|
"num_tokens": 38443008.0,
|
|
"step": 19655
|
|
},
|
|
{
|
|
"entropy": 6.2708087921142575,
|
|
"epoch": 1.9652621582446144,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004617195155402674,
|
|
"loss": 5.6304,
|
|
"mean_token_accuracy": 0.1888537511229515,
|
|
"num_tokens": 38451805.0,
|
|
"step": 19660
|
|
},
|
|
{
|
|
"entropy": 6.367570543289185,
|
|
"epoch": 1.965761983305843,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00046169959992351103,
|
|
"loss": 5.718,
|
|
"mean_token_accuracy": 0.1807909905910492,
|
|
"num_tokens": 38461826.0,
|
|
"step": 19665
|
|
},
|
|
{
|
|
"entropy": 6.295428943634033,
|
|
"epoch": 1.9662618083670715,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046167967960944066,
|
|
"loss": 5.6427,
|
|
"mean_token_accuracy": 0.1870558261871338,
|
|
"num_tokens": 38471746.0,
|
|
"step": 19670
|
|
},
|
|
{
|
|
"entropy": 6.315507698059082,
|
|
"epoch": 1.9667616334283,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004616597545985577,
|
|
"loss": 5.639,
|
|
"mean_token_accuracy": 0.1879568338394165,
|
|
"num_tokens": 38480749.0,
|
|
"step": 19675
|
|
},
|
|
{
|
|
"entropy": 6.293980503082276,
|
|
"epoch": 1.9672614584895287,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004616398248913632,
|
|
"loss": 5.6844,
|
|
"mean_token_accuracy": 0.17802098989486695,
|
|
"num_tokens": 38491327.0,
|
|
"step": 19680
|
|
},
|
|
{
|
|
"entropy": 6.337799167633056,
|
|
"epoch": 1.9677612835507572,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046161989048835886,
|
|
"loss": 5.7206,
|
|
"mean_token_accuracy": 0.17911253422498702,
|
|
"num_tokens": 38500573.0,
|
|
"step": 19685
|
|
},
|
|
{
|
|
"entropy": 6.314667797088623,
|
|
"epoch": 1.9682611086119857,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00046159995139004594,
|
|
"loss": 5.6829,
|
|
"mean_token_accuracy": 0.18614282011985778,
|
|
"num_tokens": 38510156.0,
|
|
"step": 19690
|
|
},
|
|
{
|
|
"entropy": 6.36279330253601,
|
|
"epoch": 1.9687609336732144,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004615800075969264,
|
|
"loss": 5.6395,
|
|
"mean_token_accuracy": 0.19169894009828567,
|
|
"num_tokens": 38519804.0,
|
|
"step": 19695
|
|
},
|
|
{
|
|
"entropy": 6.374940061569214,
|
|
"epoch": 1.969260758734443,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00046156005910950187,
|
|
"loss": 5.7181,
|
|
"mean_token_accuracy": 0.1852960467338562,
|
|
"num_tokens": 38530332.0,
|
|
"step": 19700
|
|
},
|
|
{
|
|
"entropy": 6.392696332931519,
|
|
"epoch": 1.9697605837956715,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004615401059282742,
|
|
"loss": 5.7532,
|
|
"mean_token_accuracy": 0.17759696692228316,
|
|
"num_tokens": 38540480.0,
|
|
"step": 19705
|
|
},
|
|
{
|
|
"entropy": 6.282466125488281,
|
|
"epoch": 1.9702604088569,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00046152014805374546,
|
|
"loss": 5.6636,
|
|
"mean_token_accuracy": 0.18967380076646806,
|
|
"num_tokens": 38549644.0,
|
|
"step": 19710
|
|
},
|
|
{
|
|
"entropy": 6.306640672683716,
|
|
"epoch": 1.9707602339181287,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004615001854864179,
|
|
"loss": 5.7631,
|
|
"mean_token_accuracy": 0.17581263482570647,
|
|
"num_tokens": 38560018.0,
|
|
"step": 19715
|
|
},
|
|
{
|
|
"entropy": 6.291389608383179,
|
|
"epoch": 1.9712600589793572,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046148021822679347,
|
|
"loss": 5.6042,
|
|
"mean_token_accuracy": 0.1863902449607849,
|
|
"num_tokens": 38569584.0,
|
|
"step": 19720
|
|
},
|
|
{
|
|
"entropy": 6.341624546051025,
|
|
"epoch": 1.9717598840405857,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004614602462753749,
|
|
"loss": 5.7355,
|
|
"mean_token_accuracy": 0.18261632770299913,
|
|
"num_tokens": 38579358.0,
|
|
"step": 19725
|
|
},
|
|
{
|
|
"entropy": 6.228896284103394,
|
|
"epoch": 1.9722597091018144,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004614402696326645,
|
|
"loss": 5.603,
|
|
"mean_token_accuracy": 0.19273519068956374,
|
|
"num_tokens": 38588850.0,
|
|
"step": 19730
|
|
},
|
|
{
|
|
"entropy": 6.255621767044067,
|
|
"epoch": 1.972759534163043,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046142028829916485,
|
|
"loss": 5.7163,
|
|
"mean_token_accuracy": 0.1863835409283638,
|
|
"num_tokens": 38598972.0,
|
|
"step": 19735
|
|
},
|
|
{
|
|
"entropy": 6.444262742996216,
|
|
"epoch": 1.9732593592242715,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004614003022753787,
|
|
"loss": 5.783,
|
|
"mean_token_accuracy": 0.18506786972284317,
|
|
"num_tokens": 38609640.0,
|
|
"step": 19740
|
|
},
|
|
{
|
|
"entropy": 6.3458315372467045,
|
|
"epoch": 1.9737591842855,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004613803115618089,
|
|
"loss": 5.6785,
|
|
"mean_token_accuracy": 0.1856277883052826,
|
|
"num_tokens": 38619487.0,
|
|
"step": 19745
|
|
},
|
|
{
|
|
"entropy": 6.345234537124634,
|
|
"epoch": 1.9742590093467287,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046136031615895846,
|
|
"loss": 5.7884,
|
|
"mean_token_accuracy": 0.18335890918970107,
|
|
"num_tokens": 38629681.0,
|
|
"step": 19750
|
|
},
|
|
{
|
|
"entropy": 6.329167127609253,
|
|
"epoch": 1.9747588344079572,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004613403160673305,
|
|
"loss": 5.7769,
|
|
"mean_token_accuracy": 0.18000289052724838,
|
|
"num_tokens": 38640003.0,
|
|
"step": 19755
|
|
},
|
|
{
|
|
"entropy": 6.296251392364502,
|
|
"epoch": 1.9752586594691857,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000461320311287428,
|
|
"loss": 5.6237,
|
|
"mean_token_accuracy": 0.18356284946203233,
|
|
"num_tokens": 38650691.0,
|
|
"step": 19760
|
|
},
|
|
{
|
|
"entropy": 6.319665956497192,
|
|
"epoch": 1.9757584845304144,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046130030181975446,
|
|
"loss": 5.6834,
|
|
"mean_token_accuracy": 0.17791340947151185,
|
|
"num_tokens": 38660144.0,
|
|
"step": 19765
|
|
},
|
|
{
|
|
"entropy": 6.319990921020508,
|
|
"epoch": 1.976258309591643,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004612802876648133,
|
|
"loss": 5.7247,
|
|
"mean_token_accuracy": 0.19006171822547913,
|
|
"num_tokens": 38670654.0,
|
|
"step": 19770
|
|
},
|
|
{
|
|
"entropy": 6.279607772827148,
|
|
"epoch": 1.9767581346528715,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000461260268823108,
|
|
"loss": 5.6485,
|
|
"mean_token_accuracy": 0.18571143299341203,
|
|
"num_tokens": 38681616.0,
|
|
"step": 19775
|
|
},
|
|
{
|
|
"entropy": 6.177262878417968,
|
|
"epoch": 1.9772579597141,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046124024529514224,
|
|
"loss": 5.5613,
|
|
"mean_token_accuracy": 0.20717367976903917,
|
|
"num_tokens": 38691586.0,
|
|
"step": 19780
|
|
},
|
|
{
|
|
"entropy": 6.368677091598511,
|
|
"epoch": 1.9777577847753287,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004612202170814198,
|
|
"loss": 5.6932,
|
|
"mean_token_accuracy": 0.18844407051801682,
|
|
"num_tokens": 38703320.0,
|
|
"step": 19785
|
|
},
|
|
{
|
|
"entropy": 6.292947769165039,
|
|
"epoch": 1.9782576098365572,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004612001841824447,
|
|
"loss": 5.6934,
|
|
"mean_token_accuracy": 0.19348025023937226,
|
|
"num_tokens": 38713318.0,
|
|
"step": 19790
|
|
},
|
|
{
|
|
"entropy": 6.320004796981811,
|
|
"epoch": 1.9787574348977857,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046118014659872085,
|
|
"loss": 5.6843,
|
|
"mean_token_accuracy": 0.17852539122104644,
|
|
"num_tokens": 38723237.0,
|
|
"step": 19795
|
|
},
|
|
{
|
|
"entropy": 6.3227887630462645,
|
|
"epoch": 1.9792572599590144,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004611601043307525,
|
|
"loss": 5.616,
|
|
"mean_token_accuracy": 0.19342767894268037,
|
|
"num_tokens": 38732742.0,
|
|
"step": 19800
|
|
},
|
|
{
|
|
"entropy": 6.3027623176574705,
|
|
"epoch": 1.979757085020243,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046114005737904376,
|
|
"loss": 5.764,
|
|
"mean_token_accuracy": 0.1728943333029747,
|
|
"num_tokens": 38743259.0,
|
|
"step": 19805
|
|
},
|
|
{
|
|
"entropy": 6.325743341445923,
|
|
"epoch": 1.9802569100814715,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000461120005744099,
|
|
"loss": 5.7461,
|
|
"mean_token_accuracy": 0.17993077486753464,
|
|
"num_tokens": 38753267.0,
|
|
"step": 19810
|
|
},
|
|
{
|
|
"entropy": 6.287398910522461,
|
|
"epoch": 1.9807567351427,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046109994942642287,
|
|
"loss": 5.6333,
|
|
"mean_token_accuracy": 0.18514054119586945,
|
|
"num_tokens": 38763897.0,
|
|
"step": 19815
|
|
},
|
|
{
|
|
"entropy": 6.322884464263916,
|
|
"epoch": 1.9812565602039287,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004610798884265199,
|
|
"loss": 5.6805,
|
|
"mean_token_accuracy": 0.18416360020637512,
|
|
"num_tokens": 38774864.0,
|
|
"step": 19820
|
|
},
|
|
{
|
|
"entropy": 6.298828554153443,
|
|
"epoch": 1.9817563852651572,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046105982274489483,
|
|
"loss": 5.6112,
|
|
"mean_token_accuracy": 0.19049372673034667,
|
|
"num_tokens": 38784726.0,
|
|
"step": 19825
|
|
},
|
|
{
|
|
"entropy": 6.275451707839966,
|
|
"epoch": 1.9822562103263857,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046103975238205244,
|
|
"loss": 5.7143,
|
|
"mean_token_accuracy": 0.1796577975153923,
|
|
"num_tokens": 38794649.0,
|
|
"step": 19830
|
|
},
|
|
{
|
|
"entropy": 6.366576290130615,
|
|
"epoch": 1.9827560353876144,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004610196773384978,
|
|
"loss": 5.741,
|
|
"mean_token_accuracy": 0.18055340945720671,
|
|
"num_tokens": 38804567.0,
|
|
"step": 19835
|
|
},
|
|
{
|
|
"entropy": 6.337870359420776,
|
|
"epoch": 1.983255860448843,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046099959761473593,
|
|
"loss": 5.6843,
|
|
"mean_token_accuracy": 0.18937747031450272,
|
|
"num_tokens": 38813874.0,
|
|
"step": 19840
|
|
},
|
|
{
|
|
"entropy": 6.245906066894531,
|
|
"epoch": 1.9837556855100713,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00046097951321127207,
|
|
"loss": 5.7109,
|
|
"mean_token_accuracy": 0.18491997718811035,
|
|
"num_tokens": 38822110.0,
|
|
"step": 19845
|
|
},
|
|
{
|
|
"entropy": 6.328630590438843,
|
|
"epoch": 1.9842555105713,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00046095942412861145,
|
|
"loss": 5.7145,
|
|
"mean_token_accuracy": 0.18751643896102904,
|
|
"num_tokens": 38832628.0,
|
|
"step": 19850
|
|
},
|
|
{
|
|
"entropy": 6.3432347774505615,
|
|
"epoch": 1.9847553356325287,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004609393303672596,
|
|
"loss": 5.6218,
|
|
"mean_token_accuracy": 0.18714223057031631,
|
|
"num_tokens": 38841742.0,
|
|
"step": 19855
|
|
},
|
|
{
|
|
"entropy": 6.359265470504761,
|
|
"epoch": 1.9852551606937572,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046091923192772205,
|
|
"loss": 5.6456,
|
|
"mean_token_accuracy": 0.1837995946407318,
|
|
"num_tokens": 38851338.0,
|
|
"step": 19860
|
|
},
|
|
{
|
|
"entropy": 6.268640470504761,
|
|
"epoch": 1.9857549857549857,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004608991288105045,
|
|
"loss": 5.6432,
|
|
"mean_token_accuracy": 0.1841577723622322,
|
|
"num_tokens": 38861308.0,
|
|
"step": 19865
|
|
},
|
|
{
|
|
"entropy": 6.325604057312011,
|
|
"epoch": 1.9862548108162144,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046087902101611265,
|
|
"loss": 5.679,
|
|
"mean_token_accuracy": 0.1877095952630043,
|
|
"num_tokens": 38871911.0,
|
|
"step": 19870
|
|
},
|
|
{
|
|
"entropy": 6.2312346458435055,
|
|
"epoch": 1.986754635877443,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004608589085450525,
|
|
"loss": 5.561,
|
|
"mean_token_accuracy": 0.1940962240099907,
|
|
"num_tokens": 38882330.0,
|
|
"step": 19875
|
|
},
|
|
{
|
|
"entropy": 6.252489233016968,
|
|
"epoch": 1.9872544609386713,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00046083879139783,
|
|
"loss": 5.5992,
|
|
"mean_token_accuracy": 0.19512980729341506,
|
|
"num_tokens": 38892080.0,
|
|
"step": 19880
|
|
},
|
|
{
|
|
"entropy": 6.3059983253479,
|
|
"epoch": 1.9877542859999,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004608186695749514,
|
|
"loss": 5.6406,
|
|
"mean_token_accuracy": 0.18398079872131348,
|
|
"num_tokens": 38901190.0,
|
|
"step": 19885
|
|
},
|
|
{
|
|
"entropy": 6.368316984176635,
|
|
"epoch": 1.9882541110611287,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004607985430769228,
|
|
"loss": 5.8059,
|
|
"mean_token_accuracy": 0.17921683341264724,
|
|
"num_tokens": 38910900.0,
|
|
"step": 19890
|
|
},
|
|
{
|
|
"entropy": 6.2940192222595215,
|
|
"epoch": 1.9887539361223572,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004607784119042507,
|
|
"loss": 5.6481,
|
|
"mean_token_accuracy": 0.1867693081498146,
|
|
"num_tokens": 38919988.0,
|
|
"step": 19895
|
|
},
|
|
{
|
|
"entropy": 6.25293493270874,
|
|
"epoch": 1.9892537611835857,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004607582760574416,
|
|
"loss": 5.6675,
|
|
"mean_token_accuracy": 0.18733438104391098,
|
|
"num_tokens": 38930288.0,
|
|
"step": 19900
|
|
},
|
|
{
|
|
"entropy": 6.25381875038147,
|
|
"epoch": 1.9897535862448144,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000460738135537002,
|
|
"loss": 5.4919,
|
|
"mean_token_accuracy": 0.20128263235092164,
|
|
"num_tokens": 38938920.0,
|
|
"step": 19905
|
|
},
|
|
{
|
|
"entropy": 6.304710912704468,
|
|
"epoch": 1.9902534113060428,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046071799034343874,
|
|
"loss": 5.6831,
|
|
"mean_token_accuracy": 0.1874738946557045,
|
|
"num_tokens": 38948453.0,
|
|
"step": 19910
|
|
},
|
|
{
|
|
"entropy": 6.374382543563843,
|
|
"epoch": 1.9907532363672713,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004606978404772587,
|
|
"loss": 5.7897,
|
|
"mean_token_accuracy": 0.17610470056533814,
|
|
"num_tokens": 38958421.0,
|
|
"step": 19915
|
|
},
|
|
{
|
|
"entropy": 6.252900123596191,
|
|
"epoch": 1.9912530614285,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046067768593896865,
|
|
"loss": 5.613,
|
|
"mean_token_accuracy": 0.1865411415696144,
|
|
"num_tokens": 38967641.0,
|
|
"step": 19920
|
|
},
|
|
{
|
|
"entropy": 6.322945213317871,
|
|
"epoch": 1.9917528864897287,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004606575267290759,
|
|
"loss": 5.6452,
|
|
"mean_token_accuracy": 0.1944785699248314,
|
|
"num_tokens": 38977601.0,
|
|
"step": 19925
|
|
},
|
|
{
|
|
"entropy": 6.281358003616333,
|
|
"epoch": 1.9922527115509572,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004606373628480875,
|
|
"loss": 5.6806,
|
|
"mean_token_accuracy": 0.1885598510503769,
|
|
"num_tokens": 38987398.0,
|
|
"step": 19930
|
|
},
|
|
{
|
|
"entropy": 6.297123432159424,
|
|
"epoch": 1.9927525366121857,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004606171942965108,
|
|
"loss": 5.6511,
|
|
"mean_token_accuracy": 0.18369088768959047,
|
|
"num_tokens": 38997831.0,
|
|
"step": 19935
|
|
},
|
|
{
|
|
"entropy": 6.318940734863281,
|
|
"epoch": 1.9932523616734144,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004605970210748533,
|
|
"loss": 5.8058,
|
|
"mean_token_accuracy": 0.1814221203327179,
|
|
"num_tokens": 39007667.0,
|
|
"step": 19940
|
|
},
|
|
{
|
|
"entropy": 6.300132369995117,
|
|
"epoch": 1.9937521867346428,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004605768431836225,
|
|
"loss": 5.6113,
|
|
"mean_token_accuracy": 0.19269392639398575,
|
|
"num_tokens": 39018192.0,
|
|
"step": 19945
|
|
},
|
|
{
|
|
"entropy": 6.2978424549102785,
|
|
"epoch": 1.9942520117958713,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046055666062332605,
|
|
"loss": 5.6119,
|
|
"mean_token_accuracy": 0.19083652794361114,
|
|
"num_tokens": 39027440.0,
|
|
"step": 19950
|
|
},
|
|
{
|
|
"entropy": 6.194023275375367,
|
|
"epoch": 1.9947518368571,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046053647339447184,
|
|
"loss": 5.5484,
|
|
"mean_token_accuracy": 0.19681550562381744,
|
|
"num_tokens": 39037078.0,
|
|
"step": 19955
|
|
},
|
|
{
|
|
"entropy": 6.284176635742187,
|
|
"epoch": 1.9952516619183287,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046051628149756767,
|
|
"loss": 5.6808,
|
|
"mean_token_accuracy": 0.18022795170545577,
|
|
"num_tokens": 39046462.0,
|
|
"step": 19960
|
|
},
|
|
{
|
|
"entropy": 6.3016462326049805,
|
|
"epoch": 1.9957514869795572,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004604960849331216,
|
|
"loss": 5.6491,
|
|
"mean_token_accuracy": 0.18782006502151488,
|
|
"num_tokens": 39057004.0,
|
|
"step": 19965
|
|
},
|
|
{
|
|
"entropy": 6.334831237792969,
|
|
"epoch": 1.9962513120407857,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004604758837016417,
|
|
"loss": 5.7483,
|
|
"mean_token_accuracy": 0.18399794548749923,
|
|
"num_tokens": 39066612.0,
|
|
"step": 19970
|
|
},
|
|
{
|
|
"entropy": 6.326824903488159,
|
|
"epoch": 1.9967511371020144,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004604556778036363,
|
|
"loss": 5.7282,
|
|
"mean_token_accuracy": 0.17492252737283706,
|
|
"num_tokens": 39076702.0,
|
|
"step": 19975
|
|
},
|
|
{
|
|
"entropy": 6.251965570449829,
|
|
"epoch": 1.9972509621632428,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046043546723961384,
|
|
"loss": 5.5505,
|
|
"mean_token_accuracy": 0.19981497079133986,
|
|
"num_tokens": 39087110.0,
|
|
"step": 19980
|
|
},
|
|
{
|
|
"entropy": 6.278290128707885,
|
|
"epoch": 1.9977507872244713,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046041525201008266,
|
|
"loss": 5.7148,
|
|
"mean_token_accuracy": 0.17934041172266008,
|
|
"num_tokens": 39097204.0,
|
|
"step": 19985
|
|
},
|
|
{
|
|
"entropy": 6.30532021522522,
|
|
"epoch": 1.9982506122857,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046039503211555154,
|
|
"loss": 5.6767,
|
|
"mean_token_accuracy": 0.1840882733464241,
|
|
"num_tokens": 39106469.0,
|
|
"step": 19990
|
|
},
|
|
{
|
|
"entropy": 6.312009859085083,
|
|
"epoch": 1.9987504373469287,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00046037480755652913,
|
|
"loss": 5.6657,
|
|
"mean_token_accuracy": 0.1908571407198906,
|
|
"num_tokens": 39116304.0,
|
|
"step": 19995
|
|
},
|
|
{
|
|
"entropy": 6.32871265411377,
|
|
"epoch": 1.9992502624081572,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046035457833352414,
|
|
"loss": 5.7337,
|
|
"mean_token_accuracy": 0.17620302885770797,
|
|
"num_tokens": 39125573.0,
|
|
"step": 20000
|
|
},
|
|
{
|
|
"entropy": 6.292783403396607,
|
|
"epoch": 1.9997500874693857,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00046033434444704577,
|
|
"loss": 5.6475,
|
|
"mean_token_accuracy": 0.18877426236867906,
|
|
"num_tokens": 39134876.0,
|
|
"step": 20005
|
|
},
|
|
{
|
|
"entropy": 6.258329550425212,
|
|
"epoch": 2.0001999300244915,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046031410589760294,
|
|
"loss": 5.5734,
|
|
"mean_token_accuracy": 0.18886381884415945,
|
|
"num_tokens": 39143851.0,
|
|
"step": 20010
|
|
},
|
|
{
|
|
"entropy": 6.1876668453216555,
|
|
"epoch": 2.00069975508572,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046029386268570485,
|
|
"loss": 5.5276,
|
|
"mean_token_accuracy": 0.1966059386730194,
|
|
"num_tokens": 39152748.0,
|
|
"step": 20015
|
|
},
|
|
{
|
|
"entropy": 6.3027044296264645,
|
|
"epoch": 2.0011995801469484,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004602736148118609,
|
|
"loss": 5.6134,
|
|
"mean_token_accuracy": 0.18683958500623704,
|
|
"num_tokens": 39162097.0,
|
|
"step": 20020
|
|
},
|
|
{
|
|
"entropy": 6.3027012825012205,
|
|
"epoch": 2.001699405208177,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046025336227658047,
|
|
"loss": 5.6285,
|
|
"mean_token_accuracy": 0.18991807401180266,
|
|
"num_tokens": 39171629.0,
|
|
"step": 20025
|
|
},
|
|
{
|
|
"entropy": 6.400193119049073,
|
|
"epoch": 2.002199230269406,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046023310508037316,
|
|
"loss": 5.7176,
|
|
"mean_token_accuracy": 0.172764952480793,
|
|
"num_tokens": 39181368.0,
|
|
"step": 20030
|
|
},
|
|
{
|
|
"entropy": 6.263208341598511,
|
|
"epoch": 2.002699055330634,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046021284322374847,
|
|
"loss": 5.5391,
|
|
"mean_token_accuracy": 0.20389751344919205,
|
|
"num_tokens": 39190492.0,
|
|
"step": 20035
|
|
},
|
|
{
|
|
"entropy": 6.316159296035766,
|
|
"epoch": 2.003198880391863,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004601925767072164,
|
|
"loss": 5.6414,
|
|
"mean_token_accuracy": 0.18525973260402678,
|
|
"num_tokens": 39200915.0,
|
|
"step": 20040
|
|
},
|
|
{
|
|
"entropy": 6.329231309890747,
|
|
"epoch": 2.0036987054530915,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00046017230553128675,
|
|
"loss": 5.5715,
|
|
"mean_token_accuracy": 0.19211390912532805,
|
|
"num_tokens": 39210370.0,
|
|
"step": 20045
|
|
},
|
|
{
|
|
"entropy": 6.350512504577637,
|
|
"epoch": 2.00419853051432,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00046015202969646953,
|
|
"loss": 5.6783,
|
|
"mean_token_accuracy": 0.18333791941404343,
|
|
"num_tokens": 39221731.0,
|
|
"step": 20050
|
|
},
|
|
{
|
|
"entropy": 6.341350173950195,
|
|
"epoch": 2.0046983555755484,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004601317492032749,
|
|
"loss": 5.6041,
|
|
"mean_token_accuracy": 0.19623432904481888,
|
|
"num_tokens": 39232951.0,
|
|
"step": 20055
|
|
},
|
|
{
|
|
"entropy": 6.359805917739868,
|
|
"epoch": 2.005198180636777,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000460111464052213,
|
|
"loss": 5.6846,
|
|
"mean_token_accuracy": 0.18301958441734315,
|
|
"num_tokens": 39242433.0,
|
|
"step": 20060
|
|
},
|
|
{
|
|
"entropy": 6.32698392868042,
|
|
"epoch": 2.005698005698006,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046009117424379445,
|
|
"loss": 5.6557,
|
|
"mean_token_accuracy": 0.18624758571386338,
|
|
"num_tokens": 39253496.0,
|
|
"step": 20065
|
|
},
|
|
{
|
|
"entropy": 6.272800016403198,
|
|
"epoch": 2.006197830759234,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046007087977852947,
|
|
"loss": 5.6174,
|
|
"mean_token_accuracy": 0.19386347383260727,
|
|
"num_tokens": 39263108.0,
|
|
"step": 20070
|
|
},
|
|
{
|
|
"entropy": 6.2413177490234375,
|
|
"epoch": 2.0066976558204628,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046005058065692883,
|
|
"loss": 5.5509,
|
|
"mean_token_accuracy": 0.19596139043569566,
|
|
"num_tokens": 39272331.0,
|
|
"step": 20075
|
|
},
|
|
{
|
|
"entropy": 6.308123350143433,
|
|
"epoch": 2.0071974808816915,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046003027687950316,
|
|
"loss": 5.5952,
|
|
"mean_token_accuracy": 0.1898687243461609,
|
|
"num_tokens": 39282387.0,
|
|
"step": 20080
|
|
},
|
|
{
|
|
"entropy": 6.310680341720581,
|
|
"epoch": 2.00769730594292,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004600099684467634,
|
|
"loss": 5.6214,
|
|
"mean_token_accuracy": 0.19078501611948012,
|
|
"num_tokens": 39293212.0,
|
|
"step": 20085
|
|
},
|
|
{
|
|
"entropy": 6.346165323257447,
|
|
"epoch": 2.0081971310041484,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004599896553592204,
|
|
"loss": 5.6876,
|
|
"mean_token_accuracy": 0.18680369704961777,
|
|
"num_tokens": 39302728.0,
|
|
"step": 20090
|
|
},
|
|
{
|
|
"entropy": 6.281501150131225,
|
|
"epoch": 2.008696956065377,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004599693376173853,
|
|
"loss": 5.5726,
|
|
"mean_token_accuracy": 0.18860770910978317,
|
|
"num_tokens": 39313079.0,
|
|
"step": 20095
|
|
},
|
|
{
|
|
"entropy": 6.326069498062134,
|
|
"epoch": 2.009196781126606,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004599490152217692,
|
|
"loss": 5.7184,
|
|
"mean_token_accuracy": 0.172953462600708,
|
|
"num_tokens": 39323563.0,
|
|
"step": 20100
|
|
},
|
|
{
|
|
"entropy": 6.290507650375366,
|
|
"epoch": 2.009696606187834,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045992868817288355,
|
|
"loss": 5.5539,
|
|
"mean_token_accuracy": 0.19996872991323472,
|
|
"num_tokens": 39334541.0,
|
|
"step": 20105
|
|
},
|
|
{
|
|
"entropy": 6.355439758300781,
|
|
"epoch": 2.0101964312490628,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004599083564712396,
|
|
"loss": 5.6438,
|
|
"mean_token_accuracy": 0.19150479137897491,
|
|
"num_tokens": 39344848.0,
|
|
"step": 20110
|
|
},
|
|
{
|
|
"entropy": 6.282812309265137,
|
|
"epoch": 2.0106962563102915,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045988802011734896,
|
|
"loss": 5.5818,
|
|
"mean_token_accuracy": 0.1817746043205261,
|
|
"num_tokens": 39354830.0,
|
|
"step": 20115
|
|
},
|
|
{
|
|
"entropy": 6.3071849822998045,
|
|
"epoch": 2.01119608137152,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045986767911172343,
|
|
"loss": 5.6966,
|
|
"mean_token_accuracy": 0.18683125376701354,
|
|
"num_tokens": 39363838.0,
|
|
"step": 20120
|
|
},
|
|
{
|
|
"entropy": 6.284457540512085,
|
|
"epoch": 2.0116959064327484,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045984733345487465,
|
|
"loss": 5.5973,
|
|
"mean_token_accuracy": 0.1849298134446144,
|
|
"num_tokens": 39373549.0,
|
|
"step": 20125
|
|
},
|
|
{
|
|
"entropy": 6.328730726242066,
|
|
"epoch": 2.012195731493977,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045982698314731447,
|
|
"loss": 5.573,
|
|
"mean_token_accuracy": 0.18916163593530655,
|
|
"num_tokens": 39383747.0,
|
|
"step": 20130
|
|
},
|
|
{
|
|
"entropy": 6.278315496444702,
|
|
"epoch": 2.012695556555206,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045980662818955495,
|
|
"loss": 5.6183,
|
|
"mean_token_accuracy": 0.18822738379240037,
|
|
"num_tokens": 39394283.0,
|
|
"step": 20135
|
|
},
|
|
{
|
|
"entropy": 6.289247941970825,
|
|
"epoch": 2.013195381616434,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045978626858210833,
|
|
"loss": 5.502,
|
|
"mean_token_accuracy": 0.20015420913696289,
|
|
"num_tokens": 39404777.0,
|
|
"step": 20140
|
|
},
|
|
{
|
|
"entropy": 6.26576681137085,
|
|
"epoch": 2.0136952066776628,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004597659043254866,
|
|
"loss": 5.5117,
|
|
"mean_token_accuracy": 0.18770646154880524,
|
|
"num_tokens": 39414749.0,
|
|
"step": 20145
|
|
},
|
|
{
|
|
"entropy": 6.311955356597901,
|
|
"epoch": 2.0141950317388915,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004597455354202023,
|
|
"loss": 5.5839,
|
|
"mean_token_accuracy": 0.19331734478473664,
|
|
"num_tokens": 39424185.0,
|
|
"step": 20150
|
|
},
|
|
{
|
|
"entropy": 6.307501602172851,
|
|
"epoch": 2.01469485680012,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004597251618667679,
|
|
"loss": 5.6562,
|
|
"mean_token_accuracy": 0.18653793185949324,
|
|
"num_tokens": 39433442.0,
|
|
"step": 20155
|
|
},
|
|
{
|
|
"entropy": 6.292524147033691,
|
|
"epoch": 2.0151946818613484,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045970478366569594,
|
|
"loss": 5.6136,
|
|
"mean_token_accuracy": 0.1907440632581711,
|
|
"num_tokens": 39443373.0,
|
|
"step": 20160
|
|
},
|
|
{
|
|
"entropy": 6.291722965240479,
|
|
"epoch": 2.015694506922577,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045968440081749917,
|
|
"loss": 5.5414,
|
|
"mean_token_accuracy": 0.19386045038700103,
|
|
"num_tokens": 39452293.0,
|
|
"step": 20165
|
|
},
|
|
{
|
|
"entropy": 6.301443386077881,
|
|
"epoch": 2.016194331983806,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004596640133226904,
|
|
"loss": 5.5924,
|
|
"mean_token_accuracy": 0.18820145428180696,
|
|
"num_tokens": 39463063.0,
|
|
"step": 20170
|
|
},
|
|
{
|
|
"entropy": 6.31938738822937,
|
|
"epoch": 2.016694157045034,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045964362118178253,
|
|
"loss": 5.5871,
|
|
"mean_token_accuracy": 0.19149488508701323,
|
|
"num_tokens": 39473349.0,
|
|
"step": 20175
|
|
},
|
|
{
|
|
"entropy": 6.32560544013977,
|
|
"epoch": 2.0171939821062628,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004596232243952887,
|
|
"loss": 5.5921,
|
|
"mean_token_accuracy": 0.1849885031580925,
|
|
"num_tokens": 39485106.0,
|
|
"step": 20180
|
|
},
|
|
{
|
|
"entropy": 6.297823476791382,
|
|
"epoch": 2.0176938071674915,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000459602822963722,
|
|
"loss": 5.6731,
|
|
"mean_token_accuracy": 0.181381855905056,
|
|
"num_tokens": 39494785.0,
|
|
"step": 20185
|
|
},
|
|
{
|
|
"entropy": 6.223841810226441,
|
|
"epoch": 2.01819363222872,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045958241688759583,
|
|
"loss": 5.5106,
|
|
"mean_token_accuracy": 0.19528110921382905,
|
|
"num_tokens": 39503846.0,
|
|
"step": 20190
|
|
},
|
|
{
|
|
"entropy": 6.333830785751343,
|
|
"epoch": 2.0186934572899484,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045956200616742356,
|
|
"loss": 5.6372,
|
|
"mean_token_accuracy": 0.18715271055698396,
|
|
"num_tokens": 39515207.0,
|
|
"step": 20195
|
|
},
|
|
{
|
|
"entropy": 6.305516576766967,
|
|
"epoch": 2.019193282351177,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004595415908037187,
|
|
"loss": 5.5868,
|
|
"mean_token_accuracy": 0.18982867449522017,
|
|
"num_tokens": 39524698.0,
|
|
"step": 20200
|
|
},
|
|
{
|
|
"entropy": 6.224255228042603,
|
|
"epoch": 2.019693107412406,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004595211707969948,
|
|
"loss": 5.5086,
|
|
"mean_token_accuracy": 0.20530221462249756,
|
|
"num_tokens": 39534485.0,
|
|
"step": 20205
|
|
},
|
|
{
|
|
"entropy": 6.208833694458008,
|
|
"epoch": 2.020192932473634,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004595007461477658,
|
|
"loss": 5.4775,
|
|
"mean_token_accuracy": 0.20928129106760024,
|
|
"num_tokens": 39544039.0,
|
|
"step": 20210
|
|
},
|
|
{
|
|
"entropy": 6.3153763771057125,
|
|
"epoch": 2.0206927575348628,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045948031685654557,
|
|
"loss": 5.5819,
|
|
"mean_token_accuracy": 0.19117067158222198,
|
|
"num_tokens": 39553139.0,
|
|
"step": 20215
|
|
},
|
|
{
|
|
"entropy": 6.348113679885865,
|
|
"epoch": 2.0211925825960915,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004594598829238479,
|
|
"loss": 5.6598,
|
|
"mean_token_accuracy": 0.17788584679365158,
|
|
"num_tokens": 39562385.0,
|
|
"step": 20220
|
|
},
|
|
{
|
|
"entropy": 6.291152286529541,
|
|
"epoch": 2.0216924076573197,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004594394443501872,
|
|
"loss": 5.5351,
|
|
"mean_token_accuracy": 0.19321103543043136,
|
|
"num_tokens": 39571855.0,
|
|
"step": 20225
|
|
},
|
|
{
|
|
"entropy": 6.305307817459107,
|
|
"epoch": 2.0221922327185484,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004594190011360775,
|
|
"loss": 5.5326,
|
|
"mean_token_accuracy": 0.19529323875904084,
|
|
"num_tokens": 39581230.0,
|
|
"step": 20230
|
|
},
|
|
{
|
|
"entropy": 6.292298030853272,
|
|
"epoch": 2.022692057779777,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004593985532820331,
|
|
"loss": 5.6316,
|
|
"mean_token_accuracy": 0.18460247069597244,
|
|
"num_tokens": 39590730.0,
|
|
"step": 20235
|
|
},
|
|
{
|
|
"entropy": 6.282548284530639,
|
|
"epoch": 2.023191882841006,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004593781007885686,
|
|
"loss": 5.5636,
|
|
"mean_token_accuracy": 0.20052370876073838,
|
|
"num_tokens": 39600110.0,
|
|
"step": 20240
|
|
},
|
|
{
|
|
"entropy": 6.34203610420227,
|
|
"epoch": 2.023691707902234,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004593576436561985,
|
|
"loss": 5.6696,
|
|
"mean_token_accuracy": 0.18130548894405366,
|
|
"num_tokens": 39610379.0,
|
|
"step": 20245
|
|
},
|
|
{
|
|
"entropy": 6.333920335769653,
|
|
"epoch": 2.0241915329634628,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045933718188543763,
|
|
"loss": 5.6617,
|
|
"mean_token_accuracy": 0.1835823431611061,
|
|
"num_tokens": 39619857.0,
|
|
"step": 20250
|
|
},
|
|
{
|
|
"entropy": 6.307488441467285,
|
|
"epoch": 2.0246913580246915,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004593167154768006,
|
|
"loss": 5.5639,
|
|
"mean_token_accuracy": 0.19355114549398422,
|
|
"num_tokens": 39630049.0,
|
|
"step": 20255
|
|
},
|
|
{
|
|
"entropy": 6.293506336212158,
|
|
"epoch": 2.0251911830859197,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004592962444308024,
|
|
"loss": 5.6408,
|
|
"mean_token_accuracy": 0.18290168792009354,
|
|
"num_tokens": 39638794.0,
|
|
"step": 20260
|
|
},
|
|
{
|
|
"entropy": 6.280803680419922,
|
|
"epoch": 2.0256910081471484,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004592757687479582,
|
|
"loss": 5.5422,
|
|
"mean_token_accuracy": 0.19286417216062546,
|
|
"num_tokens": 39648261.0,
|
|
"step": 20265
|
|
},
|
|
{
|
|
"entropy": 6.239557600021362,
|
|
"epoch": 2.026190833208377,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000459255288428783,
|
|
"loss": 5.4882,
|
|
"mean_token_accuracy": 0.20378650426864625,
|
|
"num_tokens": 39659217.0,
|
|
"step": 20270
|
|
},
|
|
{
|
|
"entropy": 6.133231830596924,
|
|
"epoch": 2.026690658269606,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004592348034737922,
|
|
"loss": 5.3464,
|
|
"mean_token_accuracy": 0.22013464868068694,
|
|
"num_tokens": 39669535.0,
|
|
"step": 20275
|
|
},
|
|
{
|
|
"entropy": 6.305775499343872,
|
|
"epoch": 2.027190483330834,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004592143138835012,
|
|
"loss": 5.6411,
|
|
"mean_token_accuracy": 0.18386248648166656,
|
|
"num_tokens": 39678640.0,
|
|
"step": 20280
|
|
},
|
|
{
|
|
"entropy": 6.230612945556641,
|
|
"epoch": 2.0276903083920628,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004591938196584254,
|
|
"loss": 5.6185,
|
|
"mean_token_accuracy": 0.18950971215963364,
|
|
"num_tokens": 39688000.0,
|
|
"step": 20285
|
|
},
|
|
{
|
|
"entropy": 6.293808698654175,
|
|
"epoch": 2.0281901334532915,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045917332079908055,
|
|
"loss": 5.5868,
|
|
"mean_token_accuracy": 0.19116679728031158,
|
|
"num_tokens": 39697778.0,
|
|
"step": 20290
|
|
},
|
|
{
|
|
"entropy": 6.260827207565308,
|
|
"epoch": 2.0286899585145197,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004591528173059823,
|
|
"loss": 5.5286,
|
|
"mean_token_accuracy": 0.19019242376089096,
|
|
"num_tokens": 39707842.0,
|
|
"step": 20295
|
|
},
|
|
{
|
|
"entropy": 6.288250398635864,
|
|
"epoch": 2.0291897835757484,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004591323091796465,
|
|
"loss": 5.6486,
|
|
"mean_token_accuracy": 0.1849869966506958,
|
|
"num_tokens": 39716465.0,
|
|
"step": 20300
|
|
},
|
|
{
|
|
"entropy": 6.284556770324707,
|
|
"epoch": 2.029689608636977,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004591117964205893,
|
|
"loss": 5.5503,
|
|
"mean_token_accuracy": 0.18978286534547806,
|
|
"num_tokens": 39725862.0,
|
|
"step": 20305
|
|
},
|
|
{
|
|
"entropy": 6.2455153465271,
|
|
"epoch": 2.030189433698206,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00045909127902932657,
|
|
"loss": 5.6037,
|
|
"mean_token_accuracy": 0.1839647486805916,
|
|
"num_tokens": 39737042.0,
|
|
"step": 20310
|
|
},
|
|
{
|
|
"entropy": 6.334717416763306,
|
|
"epoch": 2.030689258759434,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004590707570063747,
|
|
"loss": 5.5833,
|
|
"mean_token_accuracy": 0.18604134917259216,
|
|
"num_tokens": 39747849.0,
|
|
"step": 20315
|
|
},
|
|
{
|
|
"entropy": 6.281769943237305,
|
|
"epoch": 2.0311890838206628,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00045905023035224993,
|
|
"loss": 5.5469,
|
|
"mean_token_accuracy": 0.18865158259868622,
|
|
"num_tokens": 39757544.0,
|
|
"step": 20320
|
|
},
|
|
{
|
|
"entropy": 6.244071674346924,
|
|
"epoch": 2.0316889088818915,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00045902969906746875,
|
|
"loss": 5.5411,
|
|
"mean_token_accuracy": 0.19490079283714296,
|
|
"num_tokens": 39766127.0,
|
|
"step": 20325
|
|
},
|
|
{
|
|
"entropy": 6.359896659851074,
|
|
"epoch": 2.0321887339431197,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045900916315254765,
|
|
"loss": 5.706,
|
|
"mean_token_accuracy": 0.18514567464590073,
|
|
"num_tokens": 39775711.0,
|
|
"step": 20330
|
|
},
|
|
{
|
|
"entropy": 6.3245843887329105,
|
|
"epoch": 2.0326885590043484,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045898862260800337,
|
|
"loss": 5.6659,
|
|
"mean_token_accuracy": 0.195673605799675,
|
|
"num_tokens": 39786132.0,
|
|
"step": 20335
|
|
},
|
|
{
|
|
"entropy": 6.35602216720581,
|
|
"epoch": 2.033188384065577,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045896807743435263,
|
|
"loss": 5.6719,
|
|
"mean_token_accuracy": 0.17703330218791963,
|
|
"num_tokens": 39796196.0,
|
|
"step": 20340
|
|
},
|
|
{
|
|
"entropy": 6.308265113830567,
|
|
"epoch": 2.033688209126806,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004589475276321125,
|
|
"loss": 5.5437,
|
|
"mean_token_accuracy": 0.19479951709508897,
|
|
"num_tokens": 39805912.0,
|
|
"step": 20345
|
|
},
|
|
{
|
|
"entropy": 6.269448137283325,
|
|
"epoch": 2.034188034188034,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045892697320179987,
|
|
"loss": 5.5484,
|
|
"mean_token_accuracy": 0.19842515736818314,
|
|
"num_tokens": 39814990.0,
|
|
"step": 20350
|
|
},
|
|
{
|
|
"entropy": 6.265544176101685,
|
|
"epoch": 2.0346878592492628,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004589064141439319,
|
|
"loss": 5.639,
|
|
"mean_token_accuracy": 0.18963855355978013,
|
|
"num_tokens": 39823877.0,
|
|
"step": 20355
|
|
},
|
|
{
|
|
"entropy": 6.195603322982788,
|
|
"epoch": 2.0351876843104915,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004588858504590259,
|
|
"loss": 5.473,
|
|
"mean_token_accuracy": 0.2018556296825409,
|
|
"num_tokens": 39832784.0,
|
|
"step": 20360
|
|
},
|
|
{
|
|
"entropy": 6.336241626739502,
|
|
"epoch": 2.0356875093717197,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004588652821475992,
|
|
"loss": 5.6018,
|
|
"mean_token_accuracy": 0.18473476469516753,
|
|
"num_tokens": 39842388.0,
|
|
"step": 20365
|
|
},
|
|
{
|
|
"entropy": 6.269664525985718,
|
|
"epoch": 2.0361873344329484,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045884470921016935,
|
|
"loss": 5.5411,
|
|
"mean_token_accuracy": 0.2031690001487732,
|
|
"num_tokens": 39851657.0,
|
|
"step": 20370
|
|
},
|
|
{
|
|
"entropy": 6.312665033340454,
|
|
"epoch": 2.036687159494177,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045882413164725395,
|
|
"loss": 5.6063,
|
|
"mean_token_accuracy": 0.19240303635597228,
|
|
"num_tokens": 39861941.0,
|
|
"step": 20375
|
|
},
|
|
{
|
|
"entropy": 6.238644552230835,
|
|
"epoch": 2.037186984555406,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045880354945937056,
|
|
"loss": 5.5483,
|
|
"mean_token_accuracy": 0.19783882051706314,
|
|
"num_tokens": 39872000.0,
|
|
"step": 20380
|
|
},
|
|
{
|
|
"entropy": 6.297913694381714,
|
|
"epoch": 2.037686809616634,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004587829626470373,
|
|
"loss": 5.6272,
|
|
"mean_token_accuracy": 0.18480814695358277,
|
|
"num_tokens": 39882281.0,
|
|
"step": 20385
|
|
},
|
|
{
|
|
"entropy": 6.295593786239624,
|
|
"epoch": 2.0381866346778628,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045876237121077196,
|
|
"loss": 5.5892,
|
|
"mean_token_accuracy": 0.1986783191561699,
|
|
"num_tokens": 39892445.0,
|
|
"step": 20390
|
|
},
|
|
{
|
|
"entropy": 6.266243314743042,
|
|
"epoch": 2.0386864597390915,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004587417751510926,
|
|
"loss": 5.5404,
|
|
"mean_token_accuracy": 0.19729396253824233,
|
|
"num_tokens": 39902077.0,
|
|
"step": 20395
|
|
},
|
|
{
|
|
"entropy": 6.293939018249512,
|
|
"epoch": 2.0391862848003197,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00045872117446851753,
|
|
"loss": 5.6029,
|
|
"mean_token_accuracy": 0.19325414896011353,
|
|
"num_tokens": 39912930.0,
|
|
"step": 20400
|
|
},
|
|
{
|
|
"entropy": 6.276841402053833,
|
|
"epoch": 2.0396861098615484,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004587005691635649,
|
|
"loss": 5.5729,
|
|
"mean_token_accuracy": 0.1927273690700531,
|
|
"num_tokens": 39921884.0,
|
|
"step": 20405
|
|
},
|
|
{
|
|
"entropy": 6.3644633293151855,
|
|
"epoch": 2.040185934922777,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045867995923675326,
|
|
"loss": 5.665,
|
|
"mean_token_accuracy": 0.18458607494831086,
|
|
"num_tokens": 39931589.0,
|
|
"step": 20410
|
|
},
|
|
{
|
|
"entropy": 6.37223105430603,
|
|
"epoch": 2.040685759984006,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004586593446886011,
|
|
"loss": 5.7017,
|
|
"mean_token_accuracy": 0.17775675803422927,
|
|
"num_tokens": 39941624.0,
|
|
"step": 20415
|
|
},
|
|
{
|
|
"entropy": 6.278075122833252,
|
|
"epoch": 2.041185585045234,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004586387255196271,
|
|
"loss": 5.5354,
|
|
"mean_token_accuracy": 0.20050561875104905,
|
|
"num_tokens": 39951541.0,
|
|
"step": 20420
|
|
},
|
|
{
|
|
"entropy": 6.292483758926392,
|
|
"epoch": 2.0416854101064628,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045861810173035,
|
|
"loss": 5.601,
|
|
"mean_token_accuracy": 0.1940241739153862,
|
|
"num_tokens": 39962729.0,
|
|
"step": 20425
|
|
},
|
|
{
|
|
"entropy": 6.284097290039062,
|
|
"epoch": 2.0421852351676915,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045859747332128883,
|
|
"loss": 5.6192,
|
|
"mean_token_accuracy": 0.18831405490636827,
|
|
"num_tokens": 39972193.0,
|
|
"step": 20430
|
|
},
|
|
{
|
|
"entropy": 6.283842372894287,
|
|
"epoch": 2.0426850602289197,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004585768402929623,
|
|
"loss": 5.614,
|
|
"mean_token_accuracy": 0.1836085334420204,
|
|
"num_tokens": 39980813.0,
|
|
"step": 20435
|
|
},
|
|
{
|
|
"entropy": 6.2953209400177,
|
|
"epoch": 2.0431848852901484,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004585562026458898,
|
|
"loss": 5.5567,
|
|
"mean_token_accuracy": 0.19610280245542527,
|
|
"num_tokens": 39989147.0,
|
|
"step": 20440
|
|
},
|
|
{
|
|
"entropy": 6.245561504364014,
|
|
"epoch": 2.043684710351377,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045853556038059044,
|
|
"loss": 5.556,
|
|
"mean_token_accuracy": 0.20140862017869948,
|
|
"num_tokens": 40000091.0,
|
|
"step": 20445
|
|
},
|
|
{
|
|
"entropy": 6.366636276245117,
|
|
"epoch": 2.0441845354126054,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045851491349758366,
|
|
"loss": 5.704,
|
|
"mean_token_accuracy": 0.18285867124795913,
|
|
"num_tokens": 40009443.0,
|
|
"step": 20450
|
|
},
|
|
{
|
|
"entropy": 6.320323705673218,
|
|
"epoch": 2.044684360473834,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045849426199738884,
|
|
"loss": 5.6213,
|
|
"mean_token_accuracy": 0.19392164796590805,
|
|
"num_tokens": 40020877.0,
|
|
"step": 20455
|
|
},
|
|
{
|
|
"entropy": 6.291071462631225,
|
|
"epoch": 2.0451841855350628,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004584736058805256,
|
|
"loss": 5.6733,
|
|
"mean_token_accuracy": 0.18912886530160905,
|
|
"num_tokens": 40030952.0,
|
|
"step": 20460
|
|
},
|
|
{
|
|
"entropy": 6.306222152709961,
|
|
"epoch": 2.0456840105962915,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004584529451475137,
|
|
"loss": 5.5877,
|
|
"mean_token_accuracy": 0.19246142953634263,
|
|
"num_tokens": 40039995.0,
|
|
"step": 20465
|
|
},
|
|
{
|
|
"entropy": 6.284151220321656,
|
|
"epoch": 2.0461838356575197,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045843227979887286,
|
|
"loss": 5.537,
|
|
"mean_token_accuracy": 0.19558872282505035,
|
|
"num_tokens": 40049346.0,
|
|
"step": 20470
|
|
},
|
|
{
|
|
"entropy": 6.267987966537476,
|
|
"epoch": 2.0466836607187484,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045841160983512303,
|
|
"loss": 5.6313,
|
|
"mean_token_accuracy": 0.1836278721690178,
|
|
"num_tokens": 40058371.0,
|
|
"step": 20475
|
|
},
|
|
{
|
|
"entropy": 6.299350118637085,
|
|
"epoch": 2.047183485779977,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004583909352567843,
|
|
"loss": 5.5729,
|
|
"mean_token_accuracy": 0.1935303658246994,
|
|
"num_tokens": 40067504.0,
|
|
"step": 20480
|
|
},
|
|
{
|
|
"entropy": 6.290389966964722,
|
|
"epoch": 2.0476833108412054,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004583702560643769,
|
|
"loss": 5.6068,
|
|
"mean_token_accuracy": 0.19720487296581268,
|
|
"num_tokens": 40077551.0,
|
|
"step": 20485
|
|
},
|
|
{
|
|
"entropy": 6.237022256851196,
|
|
"epoch": 2.048183135902434,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000458349572258421,
|
|
"loss": 5.5029,
|
|
"mean_token_accuracy": 0.2043307200074196,
|
|
"num_tokens": 40087896.0,
|
|
"step": 20490
|
|
},
|
|
{
|
|
"entropy": 6.261611127853394,
|
|
"epoch": 2.0486829609636628,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00045832888383943706,
|
|
"loss": 5.5594,
|
|
"mean_token_accuracy": 0.1898348867893219,
|
|
"num_tokens": 40097197.0,
|
|
"step": 20495
|
|
},
|
|
{
|
|
"entropy": 6.347422122955322,
|
|
"epoch": 2.0491827860248915,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004583081908079455,
|
|
"loss": 5.6522,
|
|
"mean_token_accuracy": 0.1911693826317787,
|
|
"num_tokens": 40108068.0,
|
|
"step": 20500
|
|
},
|
|
{
|
|
"entropy": 6.282192087173462,
|
|
"epoch": 2.0496826110861197,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004582874931644671,
|
|
"loss": 5.6072,
|
|
"mean_token_accuracy": 0.18707363605499266,
|
|
"num_tokens": 40116905.0,
|
|
"step": 20505
|
|
},
|
|
{
|
|
"entropy": 6.261910152435303,
|
|
"epoch": 2.0501824361473484,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045826679090952253,
|
|
"loss": 5.577,
|
|
"mean_token_accuracy": 0.18941278904676437,
|
|
"num_tokens": 40126611.0,
|
|
"step": 20510
|
|
},
|
|
{
|
|
"entropy": 6.236411666870117,
|
|
"epoch": 2.050682261208577,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045824608404363267,
|
|
"loss": 5.4843,
|
|
"mean_token_accuracy": 0.19810643196105956,
|
|
"num_tokens": 40136557.0,
|
|
"step": 20515
|
|
},
|
|
{
|
|
"entropy": 6.322499752044678,
|
|
"epoch": 2.0511820862698054,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004582253725673184,
|
|
"loss": 5.6105,
|
|
"mean_token_accuracy": 0.18748037815093993,
|
|
"num_tokens": 40146637.0,
|
|
"step": 20520
|
|
},
|
|
{
|
|
"entropy": 6.293696880340576,
|
|
"epoch": 2.051681911331034,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000458204656481101,
|
|
"loss": 5.5003,
|
|
"mean_token_accuracy": 0.199627348780632,
|
|
"num_tokens": 40156763.0,
|
|
"step": 20525
|
|
},
|
|
{
|
|
"entropy": 6.256087732315064,
|
|
"epoch": 2.0521817363922628,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004581839357855015,
|
|
"loss": 5.5754,
|
|
"mean_token_accuracy": 0.19467224627733232,
|
|
"num_tokens": 40167024.0,
|
|
"step": 20530
|
|
},
|
|
{
|
|
"entropy": 6.26756796836853,
|
|
"epoch": 2.0526815614534915,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045816321048104143,
|
|
"loss": 5.5198,
|
|
"mean_token_accuracy": 0.20136089324951173,
|
|
"num_tokens": 40176977.0,
|
|
"step": 20535
|
|
},
|
|
{
|
|
"entropy": 6.250778865814209,
|
|
"epoch": 2.0531813865147197,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004581424805682421,
|
|
"loss": 5.485,
|
|
"mean_token_accuracy": 0.1967400848865509,
|
|
"num_tokens": 40187820.0,
|
|
"step": 20540
|
|
},
|
|
{
|
|
"entropy": 6.329632091522217,
|
|
"epoch": 2.0536812115759484,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000458121746047625,
|
|
"loss": 5.5987,
|
|
"mean_token_accuracy": 0.18722328692674636,
|
|
"num_tokens": 40197518.0,
|
|
"step": 20545
|
|
},
|
|
{
|
|
"entropy": 6.331918144226075,
|
|
"epoch": 2.054181036637177,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004581010069197119,
|
|
"loss": 5.6529,
|
|
"mean_token_accuracy": 0.1855643466114998,
|
|
"num_tokens": 40208360.0,
|
|
"step": 20550
|
|
},
|
|
{
|
|
"entropy": 6.3333092212677,
|
|
"epoch": 2.0546808616984054,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045808026318502464,
|
|
"loss": 5.6681,
|
|
"mean_token_accuracy": 0.19405155777931213,
|
|
"num_tokens": 40219526.0,
|
|
"step": 20555
|
|
},
|
|
{
|
|
"entropy": 6.360285520553589,
|
|
"epoch": 2.055180686759634,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004580595148440851,
|
|
"loss": 5.6183,
|
|
"mean_token_accuracy": 0.18495364636182784,
|
|
"num_tokens": 40230661.0,
|
|
"step": 20560
|
|
},
|
|
{
|
|
"entropy": 6.36408257484436,
|
|
"epoch": 2.0556805118208628,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004580387618974152,
|
|
"loss": 5.656,
|
|
"mean_token_accuracy": 0.18995786756277083,
|
|
"num_tokens": 40241675.0,
|
|
"step": 20565
|
|
},
|
|
{
|
|
"entropy": 6.3287672996521,
|
|
"epoch": 2.0561803368820915,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045801800434553715,
|
|
"loss": 5.5533,
|
|
"mean_token_accuracy": 0.1886907011270523,
|
|
"num_tokens": 40251275.0,
|
|
"step": 20570
|
|
},
|
|
{
|
|
"entropy": 6.335565567016602,
|
|
"epoch": 2.0566801619433197,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004579972421889732,
|
|
"loss": 5.6096,
|
|
"mean_token_accuracy": 0.19379623234272003,
|
|
"num_tokens": 40260975.0,
|
|
"step": 20575
|
|
},
|
|
{
|
|
"entropy": 6.262555503845215,
|
|
"epoch": 2.0571799870045484,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004579764754282458,
|
|
"loss": 5.5766,
|
|
"mean_token_accuracy": 0.18848264515399932,
|
|
"num_tokens": 40271617.0,
|
|
"step": 20580
|
|
},
|
|
{
|
|
"entropy": 6.327578067779541,
|
|
"epoch": 2.057679812065777,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045795570406387726,
|
|
"loss": 5.5267,
|
|
"mean_token_accuracy": 0.19109539389610292,
|
|
"num_tokens": 40281365.0,
|
|
"step": 20585
|
|
},
|
|
{
|
|
"entropy": 6.315209770202637,
|
|
"epoch": 2.0581796371270054,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004579349280963904,
|
|
"loss": 5.5783,
|
|
"mean_token_accuracy": 0.18573855757713317,
|
|
"num_tokens": 40291050.0,
|
|
"step": 20590
|
|
},
|
|
{
|
|
"entropy": 6.211524963378906,
|
|
"epoch": 2.058679462188234,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045791414752630765,
|
|
"loss": 5.459,
|
|
"mean_token_accuracy": 0.1969476595520973,
|
|
"num_tokens": 40299911.0,
|
|
"step": 20595
|
|
},
|
|
{
|
|
"entropy": 6.290552425384521,
|
|
"epoch": 2.0591792872494628,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004578933623541522,
|
|
"loss": 5.5769,
|
|
"mean_token_accuracy": 0.1928010642528534,
|
|
"num_tokens": 40310860.0,
|
|
"step": 20600
|
|
},
|
|
{
|
|
"entropy": 6.32452425956726,
|
|
"epoch": 2.0596791123106915,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045787257258044666,
|
|
"loss": 5.6444,
|
|
"mean_token_accuracy": 0.1894327476620674,
|
|
"num_tokens": 40320045.0,
|
|
"step": 20605
|
|
},
|
|
{
|
|
"entropy": 6.291404151916504,
|
|
"epoch": 2.0601789373719197,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045785177820571434,
|
|
"loss": 5.6499,
|
|
"mean_token_accuracy": 0.18694813698530197,
|
|
"num_tokens": 40329082.0,
|
|
"step": 20610
|
|
},
|
|
{
|
|
"entropy": 6.201000165939331,
|
|
"epoch": 2.0606787624331484,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00045783097923047833,
|
|
"loss": 5.5412,
|
|
"mean_token_accuracy": 0.19684422612190247,
|
|
"num_tokens": 40338161.0,
|
|
"step": 20615
|
|
},
|
|
{
|
|
"entropy": 6.294027805328369,
|
|
"epoch": 2.061178587494377,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045781017565526194,
|
|
"loss": 5.6314,
|
|
"mean_token_accuracy": 0.18936269879341125,
|
|
"num_tokens": 40348316.0,
|
|
"step": 20620
|
|
},
|
|
{
|
|
"entropy": 6.300285911560058,
|
|
"epoch": 2.0616784125556054,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00045778936748058855,
|
|
"loss": 5.5255,
|
|
"mean_token_accuracy": 0.1974417343735695,
|
|
"num_tokens": 40358112.0,
|
|
"step": 20625
|
|
},
|
|
{
|
|
"entropy": 6.276049995422364,
|
|
"epoch": 2.062178237616834,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045776855470698163,
|
|
"loss": 5.5659,
|
|
"mean_token_accuracy": 0.19931767582893373,
|
|
"num_tokens": 40368670.0,
|
|
"step": 20630
|
|
},
|
|
{
|
|
"entropy": 6.232395935058594,
|
|
"epoch": 2.0626780626780628,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00045774773733496505,
|
|
"loss": 5.5592,
|
|
"mean_token_accuracy": 0.1964890718460083,
|
|
"num_tokens": 40378082.0,
|
|
"step": 20635
|
|
},
|
|
{
|
|
"entropy": 6.317739534378052,
|
|
"epoch": 2.0631778877392914,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004577269153650624,
|
|
"loss": 5.5751,
|
|
"mean_token_accuracy": 0.19304899424314498,
|
|
"num_tokens": 40387679.0,
|
|
"step": 20640
|
|
},
|
|
{
|
|
"entropy": 6.313536834716797,
|
|
"epoch": 2.0636777128005197,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004577060887977975,
|
|
"loss": 5.5427,
|
|
"mean_token_accuracy": 0.19024659991264342,
|
|
"num_tokens": 40397599.0,
|
|
"step": 20645
|
|
},
|
|
{
|
|
"entropy": 6.322851228713989,
|
|
"epoch": 2.0641775378617484,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045768525763369443,
|
|
"loss": 5.5852,
|
|
"mean_token_accuracy": 0.19647787064313887,
|
|
"num_tokens": 40407163.0,
|
|
"step": 20650
|
|
},
|
|
{
|
|
"entropy": 6.274277544021606,
|
|
"epoch": 2.064677362922977,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045766442187327735,
|
|
"loss": 5.5631,
|
|
"mean_token_accuracy": 0.19257672131061554,
|
|
"num_tokens": 40416489.0,
|
|
"step": 20655
|
|
},
|
|
{
|
|
"entropy": 6.290967178344727,
|
|
"epoch": 2.0651771879842054,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00045764358151707043,
|
|
"loss": 5.625,
|
|
"mean_token_accuracy": 0.18357208520174026,
|
|
"num_tokens": 40425193.0,
|
|
"step": 20660
|
|
},
|
|
{
|
|
"entropy": 6.292745590209961,
|
|
"epoch": 2.065677013045434,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004576227365655979,
|
|
"loss": 5.6609,
|
|
"mean_token_accuracy": 0.19056256264448165,
|
|
"num_tokens": 40434025.0,
|
|
"step": 20665
|
|
},
|
|
{
|
|
"entropy": 6.3010515689849855,
|
|
"epoch": 2.0661768381066627,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004576018870193844,
|
|
"loss": 5.653,
|
|
"mean_token_accuracy": 0.18887847810983657,
|
|
"num_tokens": 40443010.0,
|
|
"step": 20670
|
|
},
|
|
{
|
|
"entropy": 6.306450462341308,
|
|
"epoch": 2.0666766631678914,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004575810328789543,
|
|
"loss": 5.6173,
|
|
"mean_token_accuracy": 0.1866568848490715,
|
|
"num_tokens": 40452673.0,
|
|
"step": 20675
|
|
},
|
|
{
|
|
"entropy": 6.280855703353882,
|
|
"epoch": 2.0671764882291197,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004575601741448325,
|
|
"loss": 5.6125,
|
|
"mean_token_accuracy": 0.18934193700551988,
|
|
"num_tokens": 40461747.0,
|
|
"step": 20680
|
|
},
|
|
{
|
|
"entropy": 6.294939565658569,
|
|
"epoch": 2.0676763132903484,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00045753931081754366,
|
|
"loss": 5.5647,
|
|
"mean_token_accuracy": 0.19054541140794753,
|
|
"num_tokens": 40470674.0,
|
|
"step": 20685
|
|
},
|
|
{
|
|
"entropy": 6.277087116241455,
|
|
"epoch": 2.068176138351577,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004575184428976127,
|
|
"loss": 5.5695,
|
|
"mean_token_accuracy": 0.19064904898405075,
|
|
"num_tokens": 40480287.0,
|
|
"step": 20690
|
|
},
|
|
{
|
|
"entropy": 6.225280523300171,
|
|
"epoch": 2.0686759634128054,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004574975703855647,
|
|
"loss": 5.4636,
|
|
"mean_token_accuracy": 0.21286716610193251,
|
|
"num_tokens": 40489990.0,
|
|
"step": 20695
|
|
},
|
|
{
|
|
"entropy": 6.317387819290161,
|
|
"epoch": 2.069175788474034,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045747669328192477,
|
|
"loss": 5.5934,
|
|
"mean_token_accuracy": 0.2045411139726639,
|
|
"num_tokens": 40500999.0,
|
|
"step": 20700
|
|
},
|
|
{
|
|
"entropy": 6.299488258361817,
|
|
"epoch": 2.0696756135352627,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004574558115872183,
|
|
"loss": 5.6221,
|
|
"mean_token_accuracy": 0.19151395708322524,
|
|
"num_tokens": 40509607.0,
|
|
"step": 20705
|
|
},
|
|
{
|
|
"entropy": 6.212558555603027,
|
|
"epoch": 2.0701754385964914,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00045743492530197046,
|
|
"loss": 5.5093,
|
|
"mean_token_accuracy": 0.1966950550675392,
|
|
"num_tokens": 40518312.0,
|
|
"step": 20710
|
|
},
|
|
{
|
|
"entropy": 6.293013238906861,
|
|
"epoch": 2.0706752636577197,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004574140344267069,
|
|
"loss": 5.6152,
|
|
"mean_token_accuracy": 0.18728483766317366,
|
|
"num_tokens": 40528015.0,
|
|
"step": 20715
|
|
},
|
|
{
|
|
"entropy": 6.325496625900269,
|
|
"epoch": 2.0711750887189484,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004573931389619531,
|
|
"loss": 5.664,
|
|
"mean_token_accuracy": 0.17838239818811416,
|
|
"num_tokens": 40537557.0,
|
|
"step": 20720
|
|
},
|
|
{
|
|
"entropy": 6.354433536529541,
|
|
"epoch": 2.071674913780177,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045737223890823494,
|
|
"loss": 5.5787,
|
|
"mean_token_accuracy": 0.1870134249329567,
|
|
"num_tokens": 40547360.0,
|
|
"step": 20725
|
|
},
|
|
{
|
|
"entropy": 6.38896951675415,
|
|
"epoch": 2.0721747388414054,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045735133426607813,
|
|
"loss": 5.6907,
|
|
"mean_token_accuracy": 0.18676772266626357,
|
|
"num_tokens": 40558156.0,
|
|
"step": 20730
|
|
},
|
|
{
|
|
"entropy": 6.293235492706299,
|
|
"epoch": 2.072674563902634,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045733042503600865,
|
|
"loss": 5.6259,
|
|
"mean_token_accuracy": 0.18445304036140442,
|
|
"num_tokens": 40568732.0,
|
|
"step": 20735
|
|
},
|
|
{
|
|
"entropy": 6.228060865402222,
|
|
"epoch": 2.0731743889638627,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045730951121855255,
|
|
"loss": 5.5121,
|
|
"mean_token_accuracy": 0.19526112973690032,
|
|
"num_tokens": 40579093.0,
|
|
"step": 20740
|
|
},
|
|
{
|
|
"entropy": 6.3750206470489506,
|
|
"epoch": 2.0736742140250914,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004572885928142362,
|
|
"loss": 5.7131,
|
|
"mean_token_accuracy": 0.18153361976146698,
|
|
"num_tokens": 40589327.0,
|
|
"step": 20745
|
|
},
|
|
{
|
|
"entropy": 6.310486602783203,
|
|
"epoch": 2.0741740390863197,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004572676698235857,
|
|
"loss": 5.5817,
|
|
"mean_token_accuracy": 0.19068121612071992,
|
|
"num_tokens": 40600054.0,
|
|
"step": 20750
|
|
},
|
|
{
|
|
"entropy": 6.3421581268310545,
|
|
"epoch": 2.0746738641475484,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004572467422471275,
|
|
"loss": 5.6063,
|
|
"mean_token_accuracy": 0.1971362441778183,
|
|
"num_tokens": 40609286.0,
|
|
"step": 20755
|
|
},
|
|
{
|
|
"entropy": 6.304021787643433,
|
|
"epoch": 2.075173689208777,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00045722581008538816,
|
|
"loss": 5.7145,
|
|
"mean_token_accuracy": 0.19307217448949815,
|
|
"num_tokens": 40618150.0,
|
|
"step": 20760
|
|
},
|
|
{
|
|
"entropy": 6.1813570022583,
|
|
"epoch": 2.0756735142700053,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004572048733388944,
|
|
"loss": 5.4638,
|
|
"mean_token_accuracy": 0.20692546516656876,
|
|
"num_tokens": 40627842.0,
|
|
"step": 20765
|
|
},
|
|
{
|
|
"entropy": 6.2931303024292,
|
|
"epoch": 2.076173339331234,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045718393200817284,
|
|
"loss": 5.561,
|
|
"mean_token_accuracy": 0.19797753542661667,
|
|
"num_tokens": 40637767.0,
|
|
"step": 20770
|
|
},
|
|
{
|
|
"entropy": 6.309898138046265,
|
|
"epoch": 2.0766731643924627,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045716298609375044,
|
|
"loss": 5.6786,
|
|
"mean_token_accuracy": 0.18014351278543472,
|
|
"num_tokens": 40648611.0,
|
|
"step": 20775
|
|
},
|
|
{
|
|
"entropy": 6.310971069335937,
|
|
"epoch": 2.077172989453691,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00045714203559615423,
|
|
"loss": 5.6484,
|
|
"mean_token_accuracy": 0.1893630012869835,
|
|
"num_tokens": 40659664.0,
|
|
"step": 20780
|
|
},
|
|
{
|
|
"entropy": 6.315824794769287,
|
|
"epoch": 2.0776728145149197,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004571210805159112,
|
|
"loss": 5.5704,
|
|
"mean_token_accuracy": 0.18956442326307296,
|
|
"num_tokens": 40669145.0,
|
|
"step": 20785
|
|
},
|
|
{
|
|
"entropy": 6.330518102645874,
|
|
"epoch": 2.0781726395761484,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004571001208535487,
|
|
"loss": 5.5851,
|
|
"mean_token_accuracy": 0.1940823584794998,
|
|
"num_tokens": 40678250.0,
|
|
"step": 20790
|
|
},
|
|
{
|
|
"entropy": 6.317599821090698,
|
|
"epoch": 2.078672464637377,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000457079156609594,
|
|
"loss": 5.548,
|
|
"mean_token_accuracy": 0.1959165558218956,
|
|
"num_tokens": 40687590.0,
|
|
"step": 20795
|
|
},
|
|
{
|
|
"entropy": 6.180674028396607,
|
|
"epoch": 2.0791722896986053,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004570581877845746,
|
|
"loss": 5.5098,
|
|
"mean_token_accuracy": 0.19641805291175843,
|
|
"num_tokens": 40697452.0,
|
|
"step": 20800
|
|
},
|
|
{
|
|
"entropy": 6.2959065437316895,
|
|
"epoch": 2.079672114759834,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000457037214379018,
|
|
"loss": 5.6624,
|
|
"mean_token_accuracy": 0.18874581009149552,
|
|
"num_tokens": 40707608.0,
|
|
"step": 20805
|
|
},
|
|
{
|
|
"entropy": 6.306282234191895,
|
|
"epoch": 2.0801719398210627,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045701623639345204,
|
|
"loss": 5.5629,
|
|
"mean_token_accuracy": 0.1943386062979698,
|
|
"num_tokens": 40717369.0,
|
|
"step": 20810
|
|
},
|
|
{
|
|
"entropy": 6.267837762832642,
|
|
"epoch": 2.080671764882291,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045699525382840423,
|
|
"loss": 5.5404,
|
|
"mean_token_accuracy": 0.19602471143007277,
|
|
"num_tokens": 40725899.0,
|
|
"step": 20815
|
|
},
|
|
{
|
|
"entropy": 6.285295820236206,
|
|
"epoch": 2.0811715899435197,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045697426668440277,
|
|
"loss": 5.7031,
|
|
"mean_token_accuracy": 0.17772537767887114,
|
|
"num_tokens": 40735252.0,
|
|
"step": 20820
|
|
},
|
|
{
|
|
"entropy": 6.308203887939453,
|
|
"epoch": 2.0816714150047484,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00045695327496197557,
|
|
"loss": 5.6468,
|
|
"mean_token_accuracy": 0.1876654252409935,
|
|
"num_tokens": 40745828.0,
|
|
"step": 20825
|
|
},
|
|
{
|
|
"entropy": 6.33184814453125,
|
|
"epoch": 2.082171240065977,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004569322786616508,
|
|
"loss": 5.5614,
|
|
"mean_token_accuracy": 0.19272243082523347,
|
|
"num_tokens": 40756388.0,
|
|
"step": 20830
|
|
},
|
|
{
|
|
"entropy": 6.296332597732544,
|
|
"epoch": 2.0826710651272053,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004569112777839567,
|
|
"loss": 5.5071,
|
|
"mean_token_accuracy": 0.19397503435611724,
|
|
"num_tokens": 40765914.0,
|
|
"step": 20835
|
|
},
|
|
{
|
|
"entropy": 6.2250550270080565,
|
|
"epoch": 2.083170890188434,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00045689027232942165,
|
|
"loss": 5.5135,
|
|
"mean_token_accuracy": 0.19624340981245042,
|
|
"num_tokens": 40775015.0,
|
|
"step": 20840
|
|
},
|
|
{
|
|
"entropy": 6.19823989868164,
|
|
"epoch": 2.0836707152496627,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004568692622985742,
|
|
"loss": 5.5289,
|
|
"mean_token_accuracy": 0.194357830286026,
|
|
"num_tokens": 40783743.0,
|
|
"step": 20845
|
|
},
|
|
{
|
|
"entropy": 6.28757152557373,
|
|
"epoch": 2.084170540310891,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00045684824769194284,
|
|
"loss": 5.6496,
|
|
"mean_token_accuracy": 0.19287378191947938,
|
|
"num_tokens": 40793973.0,
|
|
"step": 20850
|
|
},
|
|
{
|
|
"entropy": 6.3074122905731205,
|
|
"epoch": 2.0846703653721197,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004568272285100564,
|
|
"loss": 5.5715,
|
|
"mean_token_accuracy": 0.1939896360039711,
|
|
"num_tokens": 40803800.0,
|
|
"step": 20855
|
|
},
|
|
{
|
|
"entropy": 6.3362702369689945,
|
|
"epoch": 2.0851701904333484,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004568062047534437,
|
|
"loss": 5.6381,
|
|
"mean_token_accuracy": 0.1893434777855873,
|
|
"num_tokens": 40812791.0,
|
|
"step": 20860
|
|
},
|
|
{
|
|
"entropy": 6.3180193424224855,
|
|
"epoch": 2.085670015494577,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004567851764226337,
|
|
"loss": 5.6274,
|
|
"mean_token_accuracy": 0.18973061293363572,
|
|
"num_tokens": 40822498.0,
|
|
"step": 20865
|
|
},
|
|
{
|
|
"entropy": 6.258359718322754,
|
|
"epoch": 2.0861698405558053,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045676414351815533,
|
|
"loss": 5.5172,
|
|
"mean_token_accuracy": 0.19388890266418457,
|
|
"num_tokens": 40831965.0,
|
|
"step": 20870
|
|
},
|
|
{
|
|
"entropy": 6.287127828598022,
|
|
"epoch": 2.086669665617034,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004567431060405379,
|
|
"loss": 5.5939,
|
|
"mean_token_accuracy": 0.18830618858337403,
|
|
"num_tokens": 40840521.0,
|
|
"step": 20875
|
|
},
|
|
{
|
|
"entropy": 6.2519299507141115,
|
|
"epoch": 2.0871694906782627,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004567220639903108,
|
|
"loss": 5.6726,
|
|
"mean_token_accuracy": 0.1918438494205475,
|
|
"num_tokens": 40850935.0,
|
|
"step": 20880
|
|
},
|
|
{
|
|
"entropy": 6.260649538040161,
|
|
"epoch": 2.087669315739491,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045670101736800325,
|
|
"loss": 5.5962,
|
|
"mean_token_accuracy": 0.1902648001909256,
|
|
"num_tokens": 40860662.0,
|
|
"step": 20885
|
|
},
|
|
{
|
|
"entropy": 6.150567960739136,
|
|
"epoch": 2.0881691408007197,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045667996617414485,
|
|
"loss": 5.3649,
|
|
"mean_token_accuracy": 0.21322287917137145,
|
|
"num_tokens": 40870818.0,
|
|
"step": 20890
|
|
},
|
|
{
|
|
"entropy": 6.360186815261841,
|
|
"epoch": 2.0886689658619484,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004566589104092653,
|
|
"loss": 5.7237,
|
|
"mean_token_accuracy": 0.1796552762389183,
|
|
"num_tokens": 40880842.0,
|
|
"step": 20895
|
|
},
|
|
{
|
|
"entropy": 6.35585207939148,
|
|
"epoch": 2.089168790923177,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004566378500738943,
|
|
"loss": 5.6974,
|
|
"mean_token_accuracy": 0.1875266283750534,
|
|
"num_tokens": 40892070.0,
|
|
"step": 20900
|
|
},
|
|
{
|
|
"entropy": 6.202683162689209,
|
|
"epoch": 2.0896686159844053,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045661678516856164,
|
|
"loss": 5.4329,
|
|
"mean_token_accuracy": 0.2004683345556259,
|
|
"num_tokens": 40901588.0,
|
|
"step": 20905
|
|
},
|
|
{
|
|
"entropy": 6.344196462631226,
|
|
"epoch": 2.090168441045634,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004565957156937975,
|
|
"loss": 5.6311,
|
|
"mean_token_accuracy": 0.1855525404214859,
|
|
"num_tokens": 40909961.0,
|
|
"step": 20910
|
|
},
|
|
{
|
|
"entropy": 6.332730913162232,
|
|
"epoch": 2.0906682661068627,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004565746416501318,
|
|
"loss": 5.6114,
|
|
"mean_token_accuracy": 0.1915970489382744,
|
|
"num_tokens": 40919528.0,
|
|
"step": 20915
|
|
},
|
|
{
|
|
"entropy": 6.28860387802124,
|
|
"epoch": 2.091168091168091,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045655356303809494,
|
|
"loss": 5.6005,
|
|
"mean_token_accuracy": 0.1854033425450325,
|
|
"num_tokens": 40929975.0,
|
|
"step": 20920
|
|
},
|
|
{
|
|
"entropy": 6.306995820999146,
|
|
"epoch": 2.0916679162293197,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045653247985821707,
|
|
"loss": 5.5484,
|
|
"mean_token_accuracy": 0.1943736881017685,
|
|
"num_tokens": 40939952.0,
|
|
"step": 20925
|
|
},
|
|
{
|
|
"entropy": 6.252080249786377,
|
|
"epoch": 2.0921677412905484,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045651139211102875,
|
|
"loss": 5.5186,
|
|
"mean_token_accuracy": 0.20106859505176544,
|
|
"num_tokens": 40948935.0,
|
|
"step": 20930
|
|
},
|
|
{
|
|
"entropy": 6.269422626495361,
|
|
"epoch": 2.092667566351777,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045649029979706054,
|
|
"loss": 5.5783,
|
|
"mean_token_accuracy": 0.19000239968299865,
|
|
"num_tokens": 40958169.0,
|
|
"step": 20935
|
|
},
|
|
{
|
|
"entropy": 6.253466796875,
|
|
"epoch": 2.0931673914130053,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045646920291684303,
|
|
"loss": 5.6053,
|
|
"mean_token_accuracy": 0.1935863748192787,
|
|
"num_tokens": 40967920.0,
|
|
"step": 20940
|
|
},
|
|
{
|
|
"entropy": 6.249287509918213,
|
|
"epoch": 2.093667216474234,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004564481014709072,
|
|
"loss": 5.5541,
|
|
"mean_token_accuracy": 0.19059744477272034,
|
|
"num_tokens": 40977494.0,
|
|
"step": 20945
|
|
},
|
|
{
|
|
"entropy": 6.346336078643799,
|
|
"epoch": 2.0941670415354627,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004564269954597836,
|
|
"loss": 5.6853,
|
|
"mean_token_accuracy": 0.18295411318540572,
|
|
"num_tokens": 40987838.0,
|
|
"step": 20950
|
|
},
|
|
{
|
|
"entropy": 6.292280149459839,
|
|
"epoch": 2.094666866596691,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045640588488400364,
|
|
"loss": 5.4787,
|
|
"mean_token_accuracy": 0.19714477211236953,
|
|
"num_tokens": 40997308.0,
|
|
"step": 20955
|
|
},
|
|
{
|
|
"entropy": 6.2680610656738285,
|
|
"epoch": 2.0951666916579197,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004563847697440983,
|
|
"loss": 5.5776,
|
|
"mean_token_accuracy": 0.1965549424290657,
|
|
"num_tokens": 41008159.0,
|
|
"step": 20960
|
|
},
|
|
{
|
|
"entropy": 6.333496046066284,
|
|
"epoch": 2.0956665167191484,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045636365004059876,
|
|
"loss": 5.6165,
|
|
"mean_token_accuracy": 0.19089804142713546,
|
|
"num_tokens": 41018224.0,
|
|
"step": 20965
|
|
},
|
|
{
|
|
"entropy": 6.332746458053589,
|
|
"epoch": 2.0961663417803766,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045634252577403644,
|
|
"loss": 5.5601,
|
|
"mean_token_accuracy": 0.19025755375623704,
|
|
"num_tokens": 41026995.0,
|
|
"step": 20970
|
|
},
|
|
{
|
|
"entropy": 6.217279148101807,
|
|
"epoch": 2.0966661668416053,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00045632139694494294,
|
|
"loss": 5.5256,
|
|
"mean_token_accuracy": 0.19811540842056274,
|
|
"num_tokens": 41036243.0,
|
|
"step": 20975
|
|
},
|
|
{
|
|
"entropy": 6.242064762115478,
|
|
"epoch": 2.097165991902834,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004563002635538496,
|
|
"loss": 5.5583,
|
|
"mean_token_accuracy": 0.19185113906860352,
|
|
"num_tokens": 41046196.0,
|
|
"step": 20980
|
|
},
|
|
{
|
|
"entropy": 6.29636960029602,
|
|
"epoch": 2.0976658169640627,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004562791256012884,
|
|
"loss": 5.5914,
|
|
"mean_token_accuracy": 0.197222763299942,
|
|
"num_tokens": 41057053.0,
|
|
"step": 20985
|
|
},
|
|
{
|
|
"entropy": 6.378403186798096,
|
|
"epoch": 2.098165642025291,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004562579830877911,
|
|
"loss": 5.7126,
|
|
"mean_token_accuracy": 0.1869557037949562,
|
|
"num_tokens": 41067349.0,
|
|
"step": 20990
|
|
},
|
|
{
|
|
"entropy": 6.334090852737427,
|
|
"epoch": 2.0986654670865197,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004562368360138894,
|
|
"loss": 5.6375,
|
|
"mean_token_accuracy": 0.18605091124773027,
|
|
"num_tokens": 41077327.0,
|
|
"step": 20995
|
|
},
|
|
{
|
|
"entropy": 6.2840296745300295,
|
|
"epoch": 2.0991652921477484,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004562156843801157,
|
|
"loss": 5.5936,
|
|
"mean_token_accuracy": 0.19329406470060348,
|
|
"num_tokens": 41086569.0,
|
|
"step": 21000
|
|
},
|
|
{
|
|
"epoch": 2.0991652921477484,
|
|
"eval_entropy": 6.031967407709175,
|
|
"eval_loss": 5.683615684509277,
|
|
"eval_mean_token_accuracy": 0.19639710589947698,
|
|
"eval_num_tokens": 41086569.0,
|
|
"eval_runtime": 18.4588,
|
|
"eval_samples_per_second": 1681.857,
|
|
"eval_steps_per_second": 210.252,
|
|
"step": 21000
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 100030,
|
|
"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": 9668203610112000.0,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|