6046 lines
164 KiB
JSON
6046 lines
164 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.299895036737142,
|
|
"eval_steps": 3000,
|
|
"global_step": 3000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 10.742113018035889,
|
|
"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
|
|
}
|
|
],
|
|
"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": 1391279704473600.0,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|