a70bfc5b34
Model: fpadovani/tur-latn-100mb-after-ppt-Dp-100mb-ckpt500_seed10 Source: Original Platform
6046 lines
164 KiB
JSON
6046 lines
164 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.299895036737142,
|
|
"eval_steps": 3000,
|
|
"global_step": 3000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 8.173395156860352,
|
|
"epoch": 0.00049982506122857,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 2e-06,
|
|
"loss": 7.9212,
|
|
"mean_token_accuracy": 0.09272176176309585,
|
|
"num_tokens": 8821.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 8.15390853881836,
|
|
"epoch": 0.00099965012245714,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 7.8813,
|
|
"mean_token_accuracy": 0.0939578540623188,
|
|
"num_tokens": 18288.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 8.147719764709473,
|
|
"epoch": 0.00149947518368571,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 7e-06,
|
|
"loss": 8.0013,
|
|
"mean_token_accuracy": 0.08617180287837982,
|
|
"num_tokens": 28664.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 8.167346668243407,
|
|
"epoch": 0.00199930024491428,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 7.9255,
|
|
"mean_token_accuracy": 0.0916962169110775,
|
|
"num_tokens": 37807.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 8.143739604949952,
|
|
"epoch": 0.00249912530614285,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 8.0114,
|
|
"mean_token_accuracy": 0.08655632585287094,
|
|
"num_tokens": 48086.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 8.162391948699952,
|
|
"epoch": 0.00299895036737142,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 7.9097,
|
|
"mean_token_accuracy": 0.09338272213935853,
|
|
"num_tokens": 57427.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 8.124217319488526,
|
|
"epoch": 0.00349877542859999,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 7.8375,
|
|
"mean_token_accuracy": 0.09512318149209023,
|
|
"num_tokens": 66662.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 8.138414859771729,
|
|
"epoch": 0.00399860048982856,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 7.9693,
|
|
"mean_token_accuracy": 0.08915233314037323,
|
|
"num_tokens": 77388.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 8.167016983032227,
|
|
"epoch": 0.00449842555105713,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 7.8205,
|
|
"mean_token_accuracy": 0.09171208068728447,
|
|
"num_tokens": 86093.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 8.184170150756836,
|
|
"epoch": 0.0049982506122857,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 7.9262,
|
|
"mean_token_accuracy": 0.09001774936914445,
|
|
"num_tokens": 96097.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 8.148734855651856,
|
|
"epoch": 0.00549807567351427,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 7.9451,
|
|
"mean_token_accuracy": 0.08841896653175355,
|
|
"num_tokens": 106328.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 8.164736080169678,
|
|
"epoch": 0.00599790073474284,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 7.8896,
|
|
"mean_token_accuracy": 0.09127758592367172,
|
|
"num_tokens": 114822.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 8.159956741333009,
|
|
"epoch": 0.00649772579597141,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 7.9015,
|
|
"mean_token_accuracy": 0.0870350182056427,
|
|
"num_tokens": 124984.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 8.099590635299682,
|
|
"epoch": 0.00699755085719998,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 7.8877,
|
|
"mean_token_accuracy": 0.09039942994713783,
|
|
"num_tokens": 134054.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 8.094889259338379,
|
|
"epoch": 0.00749737591842855,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 7.8934,
|
|
"mean_token_accuracy": 0.09580017626285553,
|
|
"num_tokens": 144561.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 8.143476486206055,
|
|
"epoch": 0.00799720097965712,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 7.9329,
|
|
"mean_token_accuracy": 0.08533147275447846,
|
|
"num_tokens": 153701.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 8.166958999633788,
|
|
"epoch": 0.00849702604088569,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 7.8542,
|
|
"mean_token_accuracy": 0.09379108399152755,
|
|
"num_tokens": 164291.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 8.122808074951172,
|
|
"epoch": 0.00899685110211426,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 7.86,
|
|
"mean_token_accuracy": 0.09373755380511284,
|
|
"num_tokens": 174136.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 8.091786527633667,
|
|
"epoch": 0.00949667616334283,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 7.9022,
|
|
"mean_token_accuracy": 0.09065977856516838,
|
|
"num_tokens": 184368.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 8.127646446228027,
|
|
"epoch": 0.0099965012245714,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 7.9161,
|
|
"mean_token_accuracy": 0.08597206845879554,
|
|
"num_tokens": 194659.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 8.213620471954346,
|
|
"epoch": 0.01049632628579997,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 7.9287,
|
|
"mean_token_accuracy": 0.09312979727983475,
|
|
"num_tokens": 204875.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 8.149574470520019,
|
|
"epoch": 0.01099615134702854,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 7.9428,
|
|
"mean_token_accuracy": 0.09381906017661094,
|
|
"num_tokens": 217033.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 8.211454486846923,
|
|
"epoch": 0.01149597640825711,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 7.8896,
|
|
"mean_token_accuracy": 0.09600678682327271,
|
|
"num_tokens": 225946.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 8.188517951965332,
|
|
"epoch": 0.01199580146948568,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 7.871,
|
|
"mean_token_accuracy": 0.09085513278841972,
|
|
"num_tokens": 235413.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 8.094170618057252,
|
|
"epoch": 0.01249562653071425,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 7.9383,
|
|
"mean_token_accuracy": 0.08237705007195473,
|
|
"num_tokens": 247913.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 8.203950881958008,
|
|
"epoch": 0.01299545159194282,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 7.9114,
|
|
"mean_token_accuracy": 0.09513814747333527,
|
|
"num_tokens": 258486.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 8.173905754089356,
|
|
"epoch": 0.01349527665317139,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 7.8574,
|
|
"mean_token_accuracy": 0.08711725249886512,
|
|
"num_tokens": 268027.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 8.097312259674073,
|
|
"epoch": 0.01399510171439996,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 7.8699,
|
|
"mean_token_accuracy": 0.09045619666576385,
|
|
"num_tokens": 277470.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 8.162187767028808,
|
|
"epoch": 0.01449492677562853,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 7.8441,
|
|
"mean_token_accuracy": 0.08916656076908111,
|
|
"num_tokens": 286891.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 8.138840484619141,
|
|
"epoch": 0.0149947518368571,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 7.8221,
|
|
"mean_token_accuracy": 0.09832631349563599,
|
|
"num_tokens": 295636.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 8.100650215148926,
|
|
"epoch": 0.01549457689808567,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 7.807,
|
|
"mean_token_accuracy": 0.09535080567002296,
|
|
"num_tokens": 306542.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 8.136592578887939,
|
|
"epoch": 0.01599440195931424,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 7.8128,
|
|
"mean_token_accuracy": 0.09563795924186706,
|
|
"num_tokens": 315956.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 8.075897836685181,
|
|
"epoch": 0.01649422702054281,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 7.7835,
|
|
"mean_token_accuracy": 0.09556139633059502,
|
|
"num_tokens": 325500.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 8.13330774307251,
|
|
"epoch": 0.01699405208177138,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 7.8728,
|
|
"mean_token_accuracy": 0.09840985015034676,
|
|
"num_tokens": 335194.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 8.178883743286132,
|
|
"epoch": 0.01749387714299995,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 7.8081,
|
|
"mean_token_accuracy": 0.09958252236247063,
|
|
"num_tokens": 344717.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 8.01774287223816,
|
|
"epoch": 0.01799370220422852,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 7.7695,
|
|
"mean_token_accuracy": 0.09593843147158623,
|
|
"num_tokens": 354476.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 8.1070050239563,
|
|
"epoch": 0.01849352726545709,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 7.837,
|
|
"mean_token_accuracy": 0.09266547411680222,
|
|
"num_tokens": 363939.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 8.165003967285156,
|
|
"epoch": 0.01899335232668566,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 7.8697,
|
|
"mean_token_accuracy": 0.08987938240170479,
|
|
"num_tokens": 373187.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 8.064292907714844,
|
|
"epoch": 0.01949317738791423,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 7.8155,
|
|
"mean_token_accuracy": 0.09654008895158768,
|
|
"num_tokens": 382999.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 8.19270725250244,
|
|
"epoch": 0.0199930024491428,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 7.8707,
|
|
"mean_token_accuracy": 0.09406451731920243,
|
|
"num_tokens": 392639.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 8.113720321655274,
|
|
"epoch": 0.02049282751037137,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000102,
|
|
"loss": 7.8688,
|
|
"mean_token_accuracy": 0.0874548889696598,
|
|
"num_tokens": 403089.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 8.125567817687989,
|
|
"epoch": 0.02099265257159994,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 7.8475,
|
|
"mean_token_accuracy": 0.08455977067351342,
|
|
"num_tokens": 412321.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 8.179554748535157,
|
|
"epoch": 0.02149247763282851,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000107,
|
|
"loss": 7.8661,
|
|
"mean_token_accuracy": 0.08831506222486496,
|
|
"num_tokens": 421599.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 8.149456882476807,
|
|
"epoch": 0.02199230269405708,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 7.8491,
|
|
"mean_token_accuracy": 0.08751258924603462,
|
|
"num_tokens": 432012.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 8.103495025634766,
|
|
"epoch": 0.02249212775528565,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000112,
|
|
"loss": 7.8785,
|
|
"mean_token_accuracy": 0.08636855706572533,
|
|
"num_tokens": 441989.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 8.124602317810059,
|
|
"epoch": 0.02299195281651422,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 7.8288,
|
|
"mean_token_accuracy": 0.09801522344350815,
|
|
"num_tokens": 451532.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 8.118602657318116,
|
|
"epoch": 0.02349177787774279,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 7.8538,
|
|
"mean_token_accuracy": 0.09045086875557899,
|
|
"num_tokens": 461815.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 8.224643325805664,
|
|
"epoch": 0.02399160293897136,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 7.9141,
|
|
"mean_token_accuracy": 0.08622012361884117,
|
|
"num_tokens": 470860.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 8.085096645355225,
|
|
"epoch": 0.02449142800019993,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000122,
|
|
"loss": 7.8658,
|
|
"mean_token_accuracy": 0.08970579206943512,
|
|
"num_tokens": 480649.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 8.196398639678955,
|
|
"epoch": 0.0249912530614285,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 7.791,
|
|
"mean_token_accuracy": 0.09182884991168976,
|
|
"num_tokens": 489969.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 7.999597597122192,
|
|
"epoch": 0.02549107812265707,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000127,
|
|
"loss": 7.8234,
|
|
"mean_token_accuracy": 0.09344998225569726,
|
|
"num_tokens": 500000.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 8.161861276626587,
|
|
"epoch": 0.02599090318388564,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 7.7993,
|
|
"mean_token_accuracy": 0.09596751630306244,
|
|
"num_tokens": 510013.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 8.045274543762208,
|
|
"epoch": 0.026490728245114212,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000132,
|
|
"loss": 7.8612,
|
|
"mean_token_accuracy": 0.09452076926827431,
|
|
"num_tokens": 519698.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 8.16001009941101,
|
|
"epoch": 0.02699055330634278,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 7.8053,
|
|
"mean_token_accuracy": 0.09544829428195953,
|
|
"num_tokens": 531631.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 8.094933128356933,
|
|
"epoch": 0.02749037836757135,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 7.8554,
|
|
"mean_token_accuracy": 0.09051231518387795,
|
|
"num_tokens": 542204.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 8.072505760192872,
|
|
"epoch": 0.02799020342879992,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 7.7632,
|
|
"mean_token_accuracy": 0.09450774788856506,
|
|
"num_tokens": 552269.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 8.006140613555909,
|
|
"epoch": 0.02849002849002849,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 7.7554,
|
|
"mean_token_accuracy": 0.09378736913204193,
|
|
"num_tokens": 561907.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 8.243315029144288,
|
|
"epoch": 0.02898985355125706,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 7.8846,
|
|
"mean_token_accuracy": 0.08584100976586342,
|
|
"num_tokens": 571283.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 7.974696350097656,
|
|
"epoch": 0.02948967861248563,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000147,
|
|
"loss": 7.7631,
|
|
"mean_token_accuracy": 0.09530414417386054,
|
|
"num_tokens": 579896.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 8.0429096698761,
|
|
"epoch": 0.0299895036737142,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 7.7369,
|
|
"mean_token_accuracy": 0.09685113728046417,
|
|
"num_tokens": 588856.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 8.04590039253235,
|
|
"epoch": 0.03048932873494277,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000152,
|
|
"loss": 7.7846,
|
|
"mean_token_accuracy": 0.09521858915686607,
|
|
"num_tokens": 598910.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 8.120123100280761,
|
|
"epoch": 0.03098915379617134,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 7.8292,
|
|
"mean_token_accuracy": 0.09306757375597954,
|
|
"num_tokens": 609248.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 8.05753664970398,
|
|
"epoch": 0.03148897885739991,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000157,
|
|
"loss": 7.8521,
|
|
"mean_token_accuracy": 0.09199029803276063,
|
|
"num_tokens": 619352.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 8.209227561950684,
|
|
"epoch": 0.03198880391862848,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 7.824,
|
|
"mean_token_accuracy": 0.08493875190615655,
|
|
"num_tokens": 628300.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 8.080143022537232,
|
|
"epoch": 0.03248862897985705,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000162,
|
|
"loss": 7.803,
|
|
"mean_token_accuracy": 0.09538680538535119,
|
|
"num_tokens": 637969.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 8.04603624343872,
|
|
"epoch": 0.03298845404108562,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 7.7472,
|
|
"mean_token_accuracy": 0.09739784002304078,
|
|
"num_tokens": 647518.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 8.218221759796142,
|
|
"epoch": 0.03348827910231419,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 7.8654,
|
|
"mean_token_accuracy": 0.08986226171255111,
|
|
"num_tokens": 658292.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 8.023103809356689,
|
|
"epoch": 0.03398810416354276,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 7.7836,
|
|
"mean_token_accuracy": 0.09298105165362358,
|
|
"num_tokens": 667872.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 8.046844100952148,
|
|
"epoch": 0.03448792922477133,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 7.6883,
|
|
"mean_token_accuracy": 0.0971065603196621,
|
|
"num_tokens": 676976.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 8.024046325683594,
|
|
"epoch": 0.0349877542859999,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 7.7503,
|
|
"mean_token_accuracy": 0.09279201328754424,
|
|
"num_tokens": 686149.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 8.001934909820557,
|
|
"epoch": 0.03548757934722847,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000177,
|
|
"loss": 7.6529,
|
|
"mean_token_accuracy": 0.10482841432094574,
|
|
"num_tokens": 696439.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 7.9410679817199705,
|
|
"epoch": 0.03598740440845704,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 7.6498,
|
|
"mean_token_accuracy": 0.10238936245441436,
|
|
"num_tokens": 705902.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 8.022974014282227,
|
|
"epoch": 0.03648722946968561,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000182,
|
|
"loss": 7.8524,
|
|
"mean_token_accuracy": 0.09500225633382797,
|
|
"num_tokens": 715973.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 8.071463918685913,
|
|
"epoch": 0.03698705453091418,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 7.7332,
|
|
"mean_token_accuracy": 0.09426685646176339,
|
|
"num_tokens": 725463.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 8.053776121139526,
|
|
"epoch": 0.03748687959214275,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000187,
|
|
"loss": 7.7399,
|
|
"mean_token_accuracy": 0.09462474286556244,
|
|
"num_tokens": 734941.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 8.029221868515014,
|
|
"epoch": 0.03798670465337132,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 7.777,
|
|
"mean_token_accuracy": 0.09015404880046844,
|
|
"num_tokens": 744302.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 7.99616174697876,
|
|
"epoch": 0.03848652971459989,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000192,
|
|
"loss": 7.7275,
|
|
"mean_token_accuracy": 0.10049449354410171,
|
|
"num_tokens": 754341.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 8.145702171325684,
|
|
"epoch": 0.03898635477582846,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 7.852,
|
|
"mean_token_accuracy": 0.08332133702933789,
|
|
"num_tokens": 764087.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 7.944943904876709,
|
|
"epoch": 0.03948617983705703,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 7.7887,
|
|
"mean_token_accuracy": 0.08848774060606956,
|
|
"num_tokens": 773728.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 8.168435096740723,
|
|
"epoch": 0.0399860048982856,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 7.822,
|
|
"mean_token_accuracy": 0.08284367993474007,
|
|
"num_tokens": 784839.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 7.93064603805542,
|
|
"epoch": 0.04048582995951417,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000202,
|
|
"loss": 7.7929,
|
|
"mean_token_accuracy": 0.09478651136159896,
|
|
"num_tokens": 794514.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 8.11144437789917,
|
|
"epoch": 0.04098565502074274,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 7.7581,
|
|
"mean_token_accuracy": 0.09314420819282532,
|
|
"num_tokens": 805254.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 7.990531015396118,
|
|
"epoch": 0.04148548008197131,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000207,
|
|
"loss": 7.6794,
|
|
"mean_token_accuracy": 0.10085502117872239,
|
|
"num_tokens": 814135.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 7.9582349300384525,
|
|
"epoch": 0.04198530514319988,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 7.7453,
|
|
"mean_token_accuracy": 0.0957567848265171,
|
|
"num_tokens": 823531.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 7.954767322540283,
|
|
"epoch": 0.04248513020442845,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000212,
|
|
"loss": 7.6464,
|
|
"mean_token_accuracy": 0.10113119706511497,
|
|
"num_tokens": 832833.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 7.997408628463745,
|
|
"epoch": 0.04298495526565702,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 7.6441,
|
|
"mean_token_accuracy": 0.09947716444730759,
|
|
"num_tokens": 841541.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 7.836303043365478,
|
|
"epoch": 0.04348478032688559,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 7.6644,
|
|
"mean_token_accuracy": 0.09943394884467124,
|
|
"num_tokens": 850689.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 7.932573461532593,
|
|
"epoch": 0.04398460538811416,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 7.624,
|
|
"mean_token_accuracy": 0.10144704058766366,
|
|
"num_tokens": 860573.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 8.005117082595826,
|
|
"epoch": 0.04448443044934273,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000222,
|
|
"loss": 7.7274,
|
|
"mean_token_accuracy": 0.090135994926095,
|
|
"num_tokens": 869784.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 8.012764692306519,
|
|
"epoch": 0.0449842555105713,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 7.6871,
|
|
"mean_token_accuracy": 0.09482940882444382,
|
|
"num_tokens": 878716.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 7.914750099182129,
|
|
"epoch": 0.04548408057179987,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 7.7939,
|
|
"mean_token_accuracy": 0.09040690958499908,
|
|
"num_tokens": 888334.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 8.02715539932251,
|
|
"epoch": 0.04598390563302844,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 7.684,
|
|
"mean_token_accuracy": 0.09270390123128891,
|
|
"num_tokens": 897701.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 7.970236349105835,
|
|
"epoch": 0.04648373069425701,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 7.6925,
|
|
"mean_token_accuracy": 0.09443332329392433,
|
|
"num_tokens": 907278.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 7.925041341781617,
|
|
"epoch": 0.04698355575548558,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 7.7006,
|
|
"mean_token_accuracy": 0.09271714985370635,
|
|
"num_tokens": 916194.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 7.967321968078613,
|
|
"epoch": 0.04748338081671415,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000237,
|
|
"loss": 7.7231,
|
|
"mean_token_accuracy": 0.09261031746864319,
|
|
"num_tokens": 926743.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 8.015508699417115,
|
|
"epoch": 0.04798320587794272,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 7.7504,
|
|
"mean_token_accuracy": 0.08958175107836723,
|
|
"num_tokens": 936059.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 7.923208951950073,
|
|
"epoch": 0.04848303093917129,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000242,
|
|
"loss": 7.6733,
|
|
"mean_token_accuracy": 0.09590794965624809,
|
|
"num_tokens": 945990.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 8.079939603805542,
|
|
"epoch": 0.04898285600039986,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 7.7223,
|
|
"mean_token_accuracy": 0.10266662836074829,
|
|
"num_tokens": 956626.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 7.87365756034851,
|
|
"epoch": 0.04948268106162843,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000247,
|
|
"loss": 7.7187,
|
|
"mean_token_accuracy": 0.09226388484239578,
|
|
"num_tokens": 966200.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 7.9425849437713625,
|
|
"epoch": 0.049982506122857,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 7.662,
|
|
"mean_token_accuracy": 0.09558572769165039,
|
|
"num_tokens": 975651.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 7.913667392730713,
|
|
"epoch": 0.05048233118408557,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000252,
|
|
"loss": 7.6696,
|
|
"mean_token_accuracy": 0.0961525209248066,
|
|
"num_tokens": 985264.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 7.940064716339111,
|
|
"epoch": 0.05098215624531414,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 7.65,
|
|
"mean_token_accuracy": 0.09761169999837875,
|
|
"num_tokens": 996723.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 7.919295358657837,
|
|
"epoch": 0.05148198130654271,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000257,
|
|
"loss": 7.6735,
|
|
"mean_token_accuracy": 0.09729609489440919,
|
|
"num_tokens": 1006098.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 8.019027423858642,
|
|
"epoch": 0.05198180636777128,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 7.719,
|
|
"mean_token_accuracy": 0.09270480126142502,
|
|
"num_tokens": 1016595.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 7.7847301959991455,
|
|
"epoch": 0.05248163142899985,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000262,
|
|
"loss": 7.5765,
|
|
"mean_token_accuracy": 0.10053420215845107,
|
|
"num_tokens": 1026281.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 7.8970424175262455,
|
|
"epoch": 0.052981456490228424,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 7.6903,
|
|
"mean_token_accuracy": 0.10703469291329384,
|
|
"num_tokens": 1036697.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 7.789024686813354,
|
|
"epoch": 0.05348128155145699,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 7.6547,
|
|
"mean_token_accuracy": 0.09684248864650727,
|
|
"num_tokens": 1047433.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 7.969110536575317,
|
|
"epoch": 0.05398110661268556,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 7.6915,
|
|
"mean_token_accuracy": 0.09020176380872727,
|
|
"num_tokens": 1056774.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 7.943284511566162,
|
|
"epoch": 0.05448093167391413,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 7.5707,
|
|
"mean_token_accuracy": 0.10046748295426369,
|
|
"num_tokens": 1068056.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 7.795782899856567,
|
|
"epoch": 0.0549807567351427,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 7.6036,
|
|
"mean_token_accuracy": 0.10044094324111938,
|
|
"num_tokens": 1077698.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 7.8286316871643065,
|
|
"epoch": 0.05548058179637127,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000277,
|
|
"loss": 7.5719,
|
|
"mean_token_accuracy": 0.09958620220422745,
|
|
"num_tokens": 1086485.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 7.919136619567871,
|
|
"epoch": 0.05598040685759984,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 7.6477,
|
|
"mean_token_accuracy": 0.0894574172794819,
|
|
"num_tokens": 1097329.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 7.742609977722168,
|
|
"epoch": 0.05648023191882841,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 7.6188,
|
|
"mean_token_accuracy": 0.09743130803108216,
|
|
"num_tokens": 1107990.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 7.8571289539337155,
|
|
"epoch": 0.05698005698005698,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 7.5419,
|
|
"mean_token_accuracy": 0.10700362995266914,
|
|
"num_tokens": 1117798.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 7.760644626617432,
|
|
"epoch": 0.05747988204128555,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000287,
|
|
"loss": 7.6946,
|
|
"mean_token_accuracy": 0.09315006881952285,
|
|
"num_tokens": 1126976.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 7.9075384616851805,
|
|
"epoch": 0.05797970710251412,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 7.6043,
|
|
"mean_token_accuracy": 0.10048359259963036,
|
|
"num_tokens": 1136410.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 7.852177858352661,
|
|
"epoch": 0.05847953216374269,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000292,
|
|
"loss": 7.6589,
|
|
"mean_token_accuracy": 0.09688285812735557,
|
|
"num_tokens": 1147162.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 7.778061771392823,
|
|
"epoch": 0.05897935722497126,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 7.5948,
|
|
"mean_token_accuracy": 0.09637040942907334,
|
|
"num_tokens": 1157578.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 7.852608489990234,
|
|
"epoch": 0.05947918228619983,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000297,
|
|
"loss": 7.5039,
|
|
"mean_token_accuracy": 0.10554338097572327,
|
|
"num_tokens": 1166914.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 7.852068567276001,
|
|
"epoch": 0.0599790073474284,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 7.6895,
|
|
"mean_token_accuracy": 0.08630285412073135,
|
|
"num_tokens": 1176740.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 7.816021823883057,
|
|
"epoch": 0.06047883240865697,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000302,
|
|
"loss": 7.5753,
|
|
"mean_token_accuracy": 0.09594688341021537,
|
|
"num_tokens": 1185497.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 7.933215665817261,
|
|
"epoch": 0.06097865746988554,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 7.6755,
|
|
"mean_token_accuracy": 0.09170238226652146,
|
|
"num_tokens": 1197390.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 7.677834701538086,
|
|
"epoch": 0.06147848253111411,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000307,
|
|
"loss": 7.5827,
|
|
"mean_token_accuracy": 0.09688961803913117,
|
|
"num_tokens": 1208293.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 7.839175367355347,
|
|
"epoch": 0.06197830759234268,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 7.5679,
|
|
"mean_token_accuracy": 0.09913268983364106,
|
|
"num_tokens": 1217860.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 7.758148860931397,
|
|
"epoch": 0.06247813265357125,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000312,
|
|
"loss": 7.5767,
|
|
"mean_token_accuracy": 0.09510255008935928,
|
|
"num_tokens": 1227259.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 7.715111303329468,
|
|
"epoch": 0.06297795771479982,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 7.466,
|
|
"mean_token_accuracy": 0.10256180614233017,
|
|
"num_tokens": 1236775.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 7.763536643981934,
|
|
"epoch": 0.06347778277602839,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000317,
|
|
"loss": 7.6092,
|
|
"mean_token_accuracy": 0.09816056564450264,
|
|
"num_tokens": 1246307.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 7.900314426422119,
|
|
"epoch": 0.06397760783725696,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 7.5545,
|
|
"mean_token_accuracy": 0.09914906919002534,
|
|
"num_tokens": 1255197.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 7.679573202133179,
|
|
"epoch": 0.06447743289848552,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000322,
|
|
"loss": 7.5638,
|
|
"mean_token_accuracy": 0.10264531224966049,
|
|
"num_tokens": 1265056.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 7.778749275207519,
|
|
"epoch": 0.0649772579597141,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 7.5018,
|
|
"mean_token_accuracy": 0.09979739040136337,
|
|
"num_tokens": 1274718.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 7.823064184188842,
|
|
"epoch": 0.06547708302094267,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 7.6216,
|
|
"mean_token_accuracy": 0.09702884927392005,
|
|
"num_tokens": 1284364.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 7.74606237411499,
|
|
"epoch": 0.06597690808217124,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 7.5995,
|
|
"mean_token_accuracy": 0.09949352443218232,
|
|
"num_tokens": 1294186.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 7.743727207183838,
|
|
"epoch": 0.06647673314339982,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 7.5094,
|
|
"mean_token_accuracy": 0.10350405499339103,
|
|
"num_tokens": 1303393.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 7.670324659347534,
|
|
"epoch": 0.06697655820462838,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 7.5125,
|
|
"mean_token_accuracy": 0.09411343447864055,
|
|
"num_tokens": 1312819.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 7.773294258117676,
|
|
"epoch": 0.06747638326585695,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000337,
|
|
"loss": 7.5869,
|
|
"mean_token_accuracy": 0.09254579842090607,
|
|
"num_tokens": 1323001.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 7.692234659194947,
|
|
"epoch": 0.06797620832708552,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 7.5356,
|
|
"mean_token_accuracy": 0.09674872979521751,
|
|
"num_tokens": 1333260.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 7.714693260192871,
|
|
"epoch": 0.0684760333883141,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000342,
|
|
"loss": 7.5253,
|
|
"mean_token_accuracy": 0.1035267636179924,
|
|
"num_tokens": 1342696.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 7.71041955947876,
|
|
"epoch": 0.06897585844954265,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 7.5005,
|
|
"mean_token_accuracy": 0.1020401656627655,
|
|
"num_tokens": 1353104.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 7.7471325397491455,
|
|
"epoch": 0.06947568351077123,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000347,
|
|
"loss": 7.5799,
|
|
"mean_token_accuracy": 0.09462966471910476,
|
|
"num_tokens": 1362871.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 7.774437189102173,
|
|
"epoch": 0.0699755085719998,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 7.5494,
|
|
"mean_token_accuracy": 0.09824139177799225,
|
|
"num_tokens": 1373622.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 7.5870044231414795,
|
|
"epoch": 0.07047533363322837,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000352,
|
|
"loss": 7.4243,
|
|
"mean_token_accuracy": 0.10344729945063591,
|
|
"num_tokens": 1382707.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 7.7422362804412845,
|
|
"epoch": 0.07097515869445695,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 7.5181,
|
|
"mean_token_accuracy": 0.09872173815965653,
|
|
"num_tokens": 1392048.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 7.511621618270874,
|
|
"epoch": 0.0714749837556855,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000357,
|
|
"loss": 7.3933,
|
|
"mean_token_accuracy": 0.10354112610220909,
|
|
"num_tokens": 1401387.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 7.69247579574585,
|
|
"epoch": 0.07197480881691408,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 7.4989,
|
|
"mean_token_accuracy": 0.09920497015118598,
|
|
"num_tokens": 1411404.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 7.644815969467163,
|
|
"epoch": 0.07247463387814265,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000362,
|
|
"loss": 7.5194,
|
|
"mean_token_accuracy": 0.09978774040937424,
|
|
"num_tokens": 1420292.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 7.674730587005615,
|
|
"epoch": 0.07297445893937123,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 7.4475,
|
|
"mean_token_accuracy": 0.10385879799723625,
|
|
"num_tokens": 1429990.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 7.65957236289978,
|
|
"epoch": 0.07347428400059978,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000367,
|
|
"loss": 7.4864,
|
|
"mean_token_accuracy": 0.09656506404280663,
|
|
"num_tokens": 1440148.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 7.612310075759888,
|
|
"epoch": 0.07397410906182836,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 7.4143,
|
|
"mean_token_accuracy": 0.09919942021369935,
|
|
"num_tokens": 1450015.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 7.595290803909302,
|
|
"epoch": 0.07447393412305693,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000372,
|
|
"loss": 7.4663,
|
|
"mean_token_accuracy": 0.09626267701387406,
|
|
"num_tokens": 1459582.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 7.677187204360962,
|
|
"epoch": 0.0749737591842855,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 7.5235,
|
|
"mean_token_accuracy": 0.09861956685781478,
|
|
"num_tokens": 1468151.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 7.5536364078521725,
|
|
"epoch": 0.07547358424551406,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000377,
|
|
"loss": 7.4131,
|
|
"mean_token_accuracy": 0.10350600630044937,
|
|
"num_tokens": 1479099.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 7.644258260726929,
|
|
"epoch": 0.07597340930674264,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 7.5166,
|
|
"mean_token_accuracy": 0.10102088227868081,
|
|
"num_tokens": 1488060.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 7.6076555252075195,
|
|
"epoch": 0.07647323436797121,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000382,
|
|
"loss": 7.5237,
|
|
"mean_token_accuracy": 0.09237042292952538,
|
|
"num_tokens": 1498230.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 7.625078392028809,
|
|
"epoch": 0.07697305942919978,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 7.4769,
|
|
"mean_token_accuracy": 0.10016548410058021,
|
|
"num_tokens": 1507962.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 7.708804130554199,
|
|
"epoch": 0.07747288449042836,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 7.5617,
|
|
"mean_token_accuracy": 0.09648449942469597,
|
|
"num_tokens": 1518607.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 7.697318172454834,
|
|
"epoch": 0.07797270955165692,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 7.4201,
|
|
"mean_token_accuracy": 0.09753957316279412,
|
|
"num_tokens": 1527166.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 7.599863815307617,
|
|
"epoch": 0.07847253461288549,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 7.5271,
|
|
"mean_token_accuracy": 0.09614471271634102,
|
|
"num_tokens": 1536683.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 7.574948406219482,
|
|
"epoch": 0.07897235967411406,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 7.4201,
|
|
"mean_token_accuracy": 0.09909558668732643,
|
|
"num_tokens": 1546243.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 7.641019535064697,
|
|
"epoch": 0.07947218473534264,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 7.435,
|
|
"mean_token_accuracy": 0.09994245618581772,
|
|
"num_tokens": 1555916.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 7.438870811462403,
|
|
"epoch": 0.0799720097965712,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 7.369,
|
|
"mean_token_accuracy": 0.10524533912539483,
|
|
"num_tokens": 1566617.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 7.572072315216064,
|
|
"epoch": 0.08047183485779977,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000402,
|
|
"loss": 7.4247,
|
|
"mean_token_accuracy": 0.09702792316675186,
|
|
"num_tokens": 1575413.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 7.568275737762451,
|
|
"epoch": 0.08097165991902834,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 7.4234,
|
|
"mean_token_accuracy": 0.09980287402868271,
|
|
"num_tokens": 1586863.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 7.546803331375122,
|
|
"epoch": 0.08147148498025691,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 7.5189,
|
|
"mean_token_accuracy": 0.10001372396945954,
|
|
"num_tokens": 1597685.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 7.595981025695801,
|
|
"epoch": 0.08197131004148547,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 7.3956,
|
|
"mean_token_accuracy": 0.10019611120223999,
|
|
"num_tokens": 1607103.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 7.573238372802734,
|
|
"epoch": 0.08247113510271405,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000412,
|
|
"loss": 7.4421,
|
|
"mean_token_accuracy": 0.10041169673204423,
|
|
"num_tokens": 1617919.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 7.571632623672485,
|
|
"epoch": 0.08297096016394262,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 7.4844,
|
|
"mean_token_accuracy": 0.09938613995909691,
|
|
"num_tokens": 1627293.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 7.595695161819458,
|
|
"epoch": 0.08347078522517119,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000417,
|
|
"loss": 7.5219,
|
|
"mean_token_accuracy": 0.0978666827082634,
|
|
"num_tokens": 1638440.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 7.5352317810058596,
|
|
"epoch": 0.08397061028639977,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 7.4249,
|
|
"mean_token_accuracy": 0.10109311267733574,
|
|
"num_tokens": 1648148.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 7.512708568572998,
|
|
"epoch": 0.08447043534762833,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000422,
|
|
"loss": 7.4451,
|
|
"mean_token_accuracy": 0.10042148157954216,
|
|
"num_tokens": 1658334.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 7.617625761032104,
|
|
"epoch": 0.0849702604088569,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 7.4846,
|
|
"mean_token_accuracy": 0.09633303582668304,
|
|
"num_tokens": 1667963.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 7.4715556621551515,
|
|
"epoch": 0.08547008547008547,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000427,
|
|
"loss": 7.3979,
|
|
"mean_token_accuracy": 0.10262207016348839,
|
|
"num_tokens": 1677270.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 7.523194360733032,
|
|
"epoch": 0.08596991053131404,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 7.3859,
|
|
"mean_token_accuracy": 0.10481420755386353,
|
|
"num_tokens": 1686770.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 7.529279613494873,
|
|
"epoch": 0.0864697355925426,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000432,
|
|
"loss": 7.4609,
|
|
"mean_token_accuracy": 0.09573153108358383,
|
|
"num_tokens": 1697507.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 7.387008571624756,
|
|
"epoch": 0.08696956065377118,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 7.3945,
|
|
"mean_token_accuracy": 0.10062696561217307,
|
|
"num_tokens": 1708253.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 7.612355899810791,
|
|
"epoch": 0.08746938571499975,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000437,
|
|
"loss": 7.4601,
|
|
"mean_token_accuracy": 0.09850295558571816,
|
|
"num_tokens": 1717827.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 7.336903047561646,
|
|
"epoch": 0.08796921077622832,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 7.2649,
|
|
"mean_token_accuracy": 0.11100565418601036,
|
|
"num_tokens": 1726678.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 7.556534910202027,
|
|
"epoch": 0.0884690358374569,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000442,
|
|
"loss": 7.3976,
|
|
"mean_token_accuracy": 0.09947276636958122,
|
|
"num_tokens": 1737518.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 7.438637018203735,
|
|
"epoch": 0.08896886089868546,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 7.2915,
|
|
"mean_token_accuracy": 0.10892865434288979,
|
|
"num_tokens": 1746338.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 7.425498580932617,
|
|
"epoch": 0.08946868595991403,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000447,
|
|
"loss": 7.3736,
|
|
"mean_token_accuracy": 0.10575593486428261,
|
|
"num_tokens": 1756538.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 7.557357740402222,
|
|
"epoch": 0.0899685110211426,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 7.4052,
|
|
"mean_token_accuracy": 0.10165804401040077,
|
|
"num_tokens": 1766722.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 7.337777996063233,
|
|
"epoch": 0.09046833608237118,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 7.3223,
|
|
"mean_token_accuracy": 0.10339211374521255,
|
|
"num_tokens": 1777039.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 7.548654174804687,
|
|
"epoch": 0.09096816114359974,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 7.4393,
|
|
"mean_token_accuracy": 0.09877310320734978,
|
|
"num_tokens": 1787621.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 7.429612350463867,
|
|
"epoch": 0.09146798620482831,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 7.4313,
|
|
"mean_token_accuracy": 0.10118876844644546,
|
|
"num_tokens": 1798345.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 7.510519886016846,
|
|
"epoch": 0.09196781126605688,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 7.4015,
|
|
"mean_token_accuracy": 0.10110852941870689,
|
|
"num_tokens": 1807994.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 7.367496538162231,
|
|
"epoch": 0.09246763632728545,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000462,
|
|
"loss": 7.3139,
|
|
"mean_token_accuracy": 0.09367315769195557,
|
|
"num_tokens": 1817965.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 7.464560461044312,
|
|
"epoch": 0.09296746138851401,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 7.3635,
|
|
"mean_token_accuracy": 0.10010309666395187,
|
|
"num_tokens": 1827094.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 7.467557430267334,
|
|
"epoch": 0.09346728644974259,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000467,
|
|
"loss": 7.3466,
|
|
"mean_token_accuracy": 0.10039986148476601,
|
|
"num_tokens": 1837754.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 7.335368013381958,
|
|
"epoch": 0.09396711151097116,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 7.3533,
|
|
"mean_token_accuracy": 0.10200253203511238,
|
|
"num_tokens": 1847500.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 7.444225072860718,
|
|
"epoch": 0.09446693657219973,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000472,
|
|
"loss": 7.4125,
|
|
"mean_token_accuracy": 0.0964927189052105,
|
|
"num_tokens": 1857663.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 7.509044599533081,
|
|
"epoch": 0.0949667616334283,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 7.4629,
|
|
"mean_token_accuracy": 0.09966767057776452,
|
|
"num_tokens": 1867752.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 7.410632658004761,
|
|
"epoch": 0.09546658669465687,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000477,
|
|
"loss": 7.3962,
|
|
"mean_token_accuracy": 0.09652933329343796,
|
|
"num_tokens": 1877479.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 7.43900876045227,
|
|
"epoch": 0.09596641175588544,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 7.4226,
|
|
"mean_token_accuracy": 0.09707022532820701,
|
|
"num_tokens": 1887944.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 7.46921329498291,
|
|
"epoch": 0.09646623681711401,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000482,
|
|
"loss": 7.3202,
|
|
"mean_token_accuracy": 0.1051582269370556,
|
|
"num_tokens": 1896991.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 7.35594482421875,
|
|
"epoch": 0.09696606187834259,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 7.3518,
|
|
"mean_token_accuracy": 0.10959891974925995,
|
|
"num_tokens": 1907216.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 7.475865411758423,
|
|
"epoch": 0.09746588693957114,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000487,
|
|
"loss": 7.3681,
|
|
"mean_token_accuracy": 0.09844867512583733,
|
|
"num_tokens": 1917206.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 7.342016315460205,
|
|
"epoch": 0.09796571200079972,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 7.4607,
|
|
"mean_token_accuracy": 0.09241715744137764,
|
|
"num_tokens": 1929669.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 7.476624441146851,
|
|
"epoch": 0.09846553706202829,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000492,
|
|
"loss": 7.3029,
|
|
"mean_token_accuracy": 0.10470175147056579,
|
|
"num_tokens": 1939881.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 7.328264808654785,
|
|
"epoch": 0.09896536212325686,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 7.346,
|
|
"mean_token_accuracy": 0.10308508202433586,
|
|
"num_tokens": 1949423.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 7.44049825668335,
|
|
"epoch": 0.09946518718448542,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000497,
|
|
"loss": 7.3721,
|
|
"mean_token_accuracy": 0.10048017129302025,
|
|
"num_tokens": 1959214.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 7.437930011749268,
|
|
"epoch": 0.099965012245714,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 7.3243,
|
|
"mean_token_accuracy": 0.09923652932047844,
|
|
"num_tokens": 1968963.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 7.347122669219971,
|
|
"epoch": 0.10046483730694257,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999999981884985,
|
|
"loss": 7.3358,
|
|
"mean_token_accuracy": 0.10006266087293625,
|
|
"num_tokens": 1979551.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 7.342271709442139,
|
|
"epoch": 0.10096466236817114,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004999999908292739,
|
|
"loss": 7.2707,
|
|
"mean_token_accuracy": 0.10789052844047546,
|
|
"num_tokens": 1988432.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 7.405298137664795,
|
|
"epoch": 0.10146448742939972,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999999778091072,
|
|
"loss": 7.3429,
|
|
"mean_token_accuracy": 0.10290407985448838,
|
|
"num_tokens": 1997509.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 7.448093605041504,
|
|
"epoch": 0.10196431249062828,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999999591279991,
|
|
"loss": 7.5284,
|
|
"mean_token_accuracy": 0.09559334665536881,
|
|
"num_tokens": 2007406.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 7.455267906188965,
|
|
"epoch": 0.10246413755185685,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00049999993478595,
|
|
"loss": 7.3217,
|
|
"mean_token_accuracy": 0.09977051839232445,
|
|
"num_tokens": 2016760.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 7.275325965881348,
|
|
"epoch": 0.10296396261308542,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999999047829604,
|
|
"loss": 7.3609,
|
|
"mean_token_accuracy": 0.10224623009562492,
|
|
"num_tokens": 2027776.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 7.378179454803467,
|
|
"epoch": 0.103463787674314,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499999869119031,
|
|
"loss": 7.3113,
|
|
"mean_token_accuracy": 0.10338322818279266,
|
|
"num_tokens": 2036955.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 7.345253419876099,
|
|
"epoch": 0.10396361273554255,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999998277941629,
|
|
"loss": 7.2195,
|
|
"mean_token_accuracy": 0.10754978880286217,
|
|
"num_tokens": 2046118.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 7.256439685821533,
|
|
"epoch": 0.10446343779677113,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999997808083569,
|
|
"loss": 7.282,
|
|
"mean_token_accuracy": 0.10003011375665664,
|
|
"num_tokens": 2056266.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 7.421114683151245,
|
|
"epoch": 0.1049632628579997,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999997281616144,
|
|
"loss": 7.3354,
|
|
"mean_token_accuracy": 0.10521339923143387,
|
|
"num_tokens": 2067416.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 7.324567222595215,
|
|
"epoch": 0.10546308791922827,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999996698539366,
|
|
"loss": 7.33,
|
|
"mean_token_accuracy": 0.10143450647592545,
|
|
"num_tokens": 2076926.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 7.306933975219726,
|
|
"epoch": 0.10596291298045685,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499999605885325,
|
|
"loss": 7.3169,
|
|
"mean_token_accuracy": 0.10499019995331764,
|
|
"num_tokens": 2088017.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 7.321994495391846,
|
|
"epoch": 0.1064627380416854,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999995362557813,
|
|
"loss": 7.3576,
|
|
"mean_token_accuracy": 0.10440385192632676,
|
|
"num_tokens": 2097249.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 7.292541551589966,
|
|
"epoch": 0.10696256310291398,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000499999460965307,
|
|
"loss": 7.3116,
|
|
"mean_token_accuracy": 0.09968645870685577,
|
|
"num_tokens": 2105778.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 7.35160641670227,
|
|
"epoch": 0.10746238816414255,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999993800139043,
|
|
"loss": 7.3278,
|
|
"mean_token_accuracy": 0.10377108082175254,
|
|
"num_tokens": 2114710.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 7.34290714263916,
|
|
"epoch": 0.10796221322537113,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999992934015752,
|
|
"loss": 7.2596,
|
|
"mean_token_accuracy": 0.10727637037634849,
|
|
"num_tokens": 2124002.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 7.377143383026123,
|
|
"epoch": 0.10846203828659969,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999992011283215,
|
|
"loss": 7.3426,
|
|
"mean_token_accuracy": 0.103351741284132,
|
|
"num_tokens": 2134592.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 7.273125696182251,
|
|
"epoch": 0.10896186334782826,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999991031941459,
|
|
"loss": 7.1919,
|
|
"mean_token_accuracy": 0.1127089373767376,
|
|
"num_tokens": 2143641.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 7.344776439666748,
|
|
"epoch": 0.10946168840905683,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004999989995990509,
|
|
"loss": 7.2986,
|
|
"mean_token_accuracy": 0.10175277665257454,
|
|
"num_tokens": 2154738.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 7.166865539550781,
|
|
"epoch": 0.1099615134702854,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999988903430389,
|
|
"loss": 7.2791,
|
|
"mean_token_accuracy": 0.10936013385653495,
|
|
"num_tokens": 2164365.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 7.3008204936981205,
|
|
"epoch": 0.11046133853151396,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999987754261126,
|
|
"loss": 7.1491,
|
|
"mean_token_accuracy": 0.1082618147134781,
|
|
"num_tokens": 2173185.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 7.216965007781982,
|
|
"epoch": 0.11096116359274254,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999986548482751,
|
|
"loss": 7.2612,
|
|
"mean_token_accuracy": 0.10522031784057617,
|
|
"num_tokens": 2184717.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 7.27905764579773,
|
|
"epoch": 0.11146098865397111,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999985286095293,
|
|
"loss": 7.2279,
|
|
"mean_token_accuracy": 0.10826601237058639,
|
|
"num_tokens": 2193681.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 7.277110385894775,
|
|
"epoch": 0.11196081371519968,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999983967098785,
|
|
"loss": 7.2467,
|
|
"mean_token_accuracy": 0.10190426334738731,
|
|
"num_tokens": 2203366.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 7.271683073043823,
|
|
"epoch": 0.11246063877642826,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999982591493258,
|
|
"loss": 7.2459,
|
|
"mean_token_accuracy": 0.10593178719282151,
|
|
"num_tokens": 2213982.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 7.318293666839599,
|
|
"epoch": 0.11296046383765682,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999981159278749,
|
|
"loss": 7.3031,
|
|
"mean_token_accuracy": 0.10162633955478668,
|
|
"num_tokens": 2222897.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 7.238396883010864,
|
|
"epoch": 0.11346028889888539,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999979670455292,
|
|
"loss": 7.2558,
|
|
"mean_token_accuracy": 0.11027894765138627,
|
|
"num_tokens": 2232472.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 7.249378728866577,
|
|
"epoch": 0.11396011396011396,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004999978125022926,
|
|
"loss": 7.294,
|
|
"mean_token_accuracy": 0.1087009809911251,
|
|
"num_tokens": 2242666.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 7.319674825668335,
|
|
"epoch": 0.11445993902134254,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000499997652298169,
|
|
"loss": 7.3479,
|
|
"mean_token_accuracy": 0.09625119417905807,
|
|
"num_tokens": 2254586.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 7.281134080886841,
|
|
"epoch": 0.1149597640825711,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999974864331624,
|
|
"loss": 7.202,
|
|
"mean_token_accuracy": 0.11020608842372895,
|
|
"num_tokens": 2264619.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 7.388929986953736,
|
|
"epoch": 0.11545958914379967,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999973149072768,
|
|
"loss": 7.2859,
|
|
"mean_token_accuracy": 0.09894285909831524,
|
|
"num_tokens": 2274114.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 7.06968936920166,
|
|
"epoch": 0.11595941420502824,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999971377205167,
|
|
"loss": 7.1888,
|
|
"mean_token_accuracy": 0.11129210293292999,
|
|
"num_tokens": 2283887.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 7.307636737823486,
|
|
"epoch": 0.11645923926625681,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999969548728864,
|
|
"loss": 7.2059,
|
|
"mean_token_accuracy": 0.11073495373129845,
|
|
"num_tokens": 2293090.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 7.2551915645599365,
|
|
"epoch": 0.11695906432748537,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999967663643908,
|
|
"loss": 7.3175,
|
|
"mean_token_accuracy": 0.10531776547431945,
|
|
"num_tokens": 2302828.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 7.2968638896942135,
|
|
"epoch": 0.11745888938871395,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999965721950345,
|
|
"loss": 7.1898,
|
|
"mean_token_accuracy": 0.10970171466469765,
|
|
"num_tokens": 2311415.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 7.247892379760742,
|
|
"epoch": 0.11795871444994252,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999963723648222,
|
|
"loss": 7.2905,
|
|
"mean_token_accuracy": 0.1028762400150299,
|
|
"num_tokens": 2321512.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 7.223724460601806,
|
|
"epoch": 0.1184585395111711,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499996166873759,
|
|
"loss": 7.1816,
|
|
"mean_token_accuracy": 0.10487090200185775,
|
|
"num_tokens": 2331398.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 7.114894962310791,
|
|
"epoch": 0.11895836457239967,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999959557218502,
|
|
"loss": 7.1949,
|
|
"mean_token_accuracy": 0.10667292214930058,
|
|
"num_tokens": 2341751.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 7.293861246109008,
|
|
"epoch": 0.11945818963362823,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999957389091012,
|
|
"loss": 7.1852,
|
|
"mean_token_accuracy": 0.10581460520625115,
|
|
"num_tokens": 2352538.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 7.263128328323364,
|
|
"epoch": 0.1199580146948568,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999955164355171,
|
|
"loss": 7.2807,
|
|
"mean_token_accuracy": 0.101702369004488,
|
|
"num_tokens": 2362433.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 7.23228964805603,
|
|
"epoch": 0.12045783975608537,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999952883011038,
|
|
"loss": 7.2357,
|
|
"mean_token_accuracy": 0.10086923241615295,
|
|
"num_tokens": 2372431.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 7.155064105987549,
|
|
"epoch": 0.12095766481731395,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499995054505867,
|
|
"loss": 7.261,
|
|
"mean_token_accuracy": 0.11123752519488335,
|
|
"num_tokens": 2382483.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 7.333055305480957,
|
|
"epoch": 0.1214574898785425,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999948150498124,
|
|
"loss": 7.2314,
|
|
"mean_token_accuracy": 0.09728648811578751,
|
|
"num_tokens": 2392835.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 7.157829141616821,
|
|
"epoch": 0.12195731493977108,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999945699329462,
|
|
"loss": 7.2069,
|
|
"mean_token_accuracy": 0.10083935856819153,
|
|
"num_tokens": 2402305.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 7.154402446746826,
|
|
"epoch": 0.12245714000099965,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999943191552745,
|
|
"loss": 7.1366,
|
|
"mean_token_accuracy": 0.1104811742901802,
|
|
"num_tokens": 2412093.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 7.197684717178345,
|
|
"epoch": 0.12295696506222822,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999940627168037,
|
|
"loss": 7.1138,
|
|
"mean_token_accuracy": 0.11224015802145004,
|
|
"num_tokens": 2421349.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 7.113976287841797,
|
|
"epoch": 0.12345679012345678,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00049999380061754,
|
|
"loss": 7.0816,
|
|
"mean_token_accuracy": 0.12027929723262787,
|
|
"num_tokens": 2430672.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 7.171084785461426,
|
|
"epoch": 0.12395661518468536,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999935328574903,
|
|
"loss": 7.1672,
|
|
"mean_token_accuracy": 0.10523176565766335,
|
|
"num_tokens": 2439355.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 7.167644071578979,
|
|
"epoch": 0.12445644024591393,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999932594366613,
|
|
"loss": 7.1629,
|
|
"mean_token_accuracy": 0.11419163346290588,
|
|
"num_tokens": 2448860.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 7.165760946273804,
|
|
"epoch": 0.1249562653071425,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999929803550597,
|
|
"loss": 7.2068,
|
|
"mean_token_accuracy": 0.1069261223077774,
|
|
"num_tokens": 2458276.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 7.17039475440979,
|
|
"epoch": 0.12545609036837108,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999926956126927,
|
|
"loss": 7.1266,
|
|
"mean_token_accuracy": 0.11022537723183631,
|
|
"num_tokens": 2467791.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 7.146854448318481,
|
|
"epoch": 0.12595591542959964,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999924052095672,
|
|
"loss": 7.2725,
|
|
"mean_token_accuracy": 0.10534469336271286,
|
|
"num_tokens": 2477549.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 7.200028324127198,
|
|
"epoch": 0.12645574049082822,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999921091456907,
|
|
"loss": 7.1641,
|
|
"mean_token_accuracy": 0.10597576200962067,
|
|
"num_tokens": 2487549.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 7.233373498916626,
|
|
"epoch": 0.12695556555205678,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999918074210707,
|
|
"loss": 7.1615,
|
|
"mean_token_accuracy": 0.11181024834513664,
|
|
"num_tokens": 2496799.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 7.232607460021972,
|
|
"epoch": 0.12745539061328534,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999915000357147,
|
|
"loss": 7.2669,
|
|
"mean_token_accuracy": 0.10368774533271789,
|
|
"num_tokens": 2505795.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 7.204328823089599,
|
|
"epoch": 0.12795521567451393,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004999911869896305,
|
|
"loss": 7.0697,
|
|
"mean_token_accuracy": 0.10817176178097725,
|
|
"num_tokens": 2515289.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 7.2058745384216305,
|
|
"epoch": 0.1284550407357425,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999908682828258,
|
|
"loss": 7.2686,
|
|
"mean_token_accuracy": 0.09726808145642281,
|
|
"num_tokens": 2524563.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 7.179253101348877,
|
|
"epoch": 0.12895486579697105,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999905439153089,
|
|
"loss": 7.1331,
|
|
"mean_token_accuracy": 0.11065928637981415,
|
|
"num_tokens": 2534057.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 7.125552940368652,
|
|
"epoch": 0.12945469085819963,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999902138870878,
|
|
"loss": 7.1287,
|
|
"mean_token_accuracy": 0.11491556018590927,
|
|
"num_tokens": 2544646.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 7.201935863494873,
|
|
"epoch": 0.1299545159194282,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999898781981707,
|
|
"loss": 7.1982,
|
|
"mean_token_accuracy": 0.1065469078719616,
|
|
"num_tokens": 2553843.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 7.158224201202392,
|
|
"epoch": 0.13045434098065678,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999895368485662,
|
|
"loss": 7.2568,
|
|
"mean_token_accuracy": 0.10226461961865425,
|
|
"num_tokens": 2564061.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 7.151171636581421,
|
|
"epoch": 0.13095416604188534,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499989189838283,
|
|
"loss": 7.1242,
|
|
"mean_token_accuracy": 0.10985731407999992,
|
|
"num_tokens": 2574758.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 7.168261194229126,
|
|
"epoch": 0.1314539911031139,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999888371673295,
|
|
"loss": 7.1635,
|
|
"mean_token_accuracy": 0.10855096057057381,
|
|
"num_tokens": 2585213.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 7.2063212394714355,
|
|
"epoch": 0.13195381616434249,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999884788357147,
|
|
"loss": 7.2354,
|
|
"mean_token_accuracy": 0.10834863558411598,
|
|
"num_tokens": 2595511.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 7.141773223876953,
|
|
"epoch": 0.13245364122557104,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999881148434478,
|
|
"loss": 7.1519,
|
|
"mean_token_accuracy": 0.10698395371437072,
|
|
"num_tokens": 2605930.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 7.183522272109985,
|
|
"epoch": 0.13295346628679963,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999877451905378,
|
|
"loss": 7.0084,
|
|
"mean_token_accuracy": 0.12175094336271286,
|
|
"num_tokens": 2614224.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 7.179550838470459,
|
|
"epoch": 0.1334532913480282,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999873698769941,
|
|
"loss": 7.2662,
|
|
"mean_token_accuracy": 0.1017696812748909,
|
|
"num_tokens": 2624879.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 7.120278787612915,
|
|
"epoch": 0.13395311640925675,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499986988902826,
|
|
"loss": 7.117,
|
|
"mean_token_accuracy": 0.10926841422915459,
|
|
"num_tokens": 2633836.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 7.138001871109009,
|
|
"epoch": 0.13445294147048534,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999866022680431,
|
|
"loss": 7.1771,
|
|
"mean_token_accuracy": 0.10937484353780746,
|
|
"num_tokens": 2643754.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 7.255338096618653,
|
|
"epoch": 0.1349527665317139,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999862099726552,
|
|
"loss": 7.2411,
|
|
"mean_token_accuracy": 0.10106356516480446,
|
|
"num_tokens": 2652708.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 7.085612630844116,
|
|
"epoch": 0.13545259159294248,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999858120166721,
|
|
"loss": 7.1799,
|
|
"mean_token_accuracy": 0.10279356613755226,
|
|
"num_tokens": 2662353.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 7.2352677345275875,
|
|
"epoch": 0.13595241665417104,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999854084001039,
|
|
"loss": 7.092,
|
|
"mean_token_accuracy": 0.1117504045367241,
|
|
"num_tokens": 2672376.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 7.125872230529785,
|
|
"epoch": 0.1364522417153996,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999849991229608,
|
|
"loss": 7.1979,
|
|
"mean_token_accuracy": 0.10238617360591888,
|
|
"num_tokens": 2682115.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 7.1724754810333256,
|
|
"epoch": 0.1369520667766282,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499984584185253,
|
|
"loss": 7.1836,
|
|
"mean_token_accuracy": 0.10678994581103325,
|
|
"num_tokens": 2692429.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 7.102124166488648,
|
|
"epoch": 0.13745189183785675,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999841635869909,
|
|
"loss": 7.1257,
|
|
"mean_token_accuracy": 0.10722747519612312,
|
|
"num_tokens": 2701373.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 7.279002380371094,
|
|
"epoch": 0.1379517168990853,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004999837373281852,
|
|
"loss": 7.3167,
|
|
"mean_token_accuracy": 0.10132398679852486,
|
|
"num_tokens": 2710717.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 7.091415548324585,
|
|
"epoch": 0.1384515419603139,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999833054088465,
|
|
"loss": 7.1606,
|
|
"mean_token_accuracy": 0.10936282426118851,
|
|
"num_tokens": 2720936.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 7.2388688087463375,
|
|
"epoch": 0.13895136702154245,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999828678289858,
|
|
"loss": 7.0993,
|
|
"mean_token_accuracy": 0.11418369710445404,
|
|
"num_tokens": 2730504.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 7.0881829261779785,
|
|
"epoch": 0.13945119208277104,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000499982424588614,
|
|
"loss": 7.1144,
|
|
"mean_token_accuracy": 0.11084567457437515,
|
|
"num_tokens": 2739069.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 7.147162532806396,
|
|
"epoch": 0.1399510171439996,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999819756877422,
|
|
"loss": 7.1945,
|
|
"mean_token_accuracy": 0.10329353213310241,
|
|
"num_tokens": 2748941.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 7.18705563545227,
|
|
"epoch": 0.14045084220522816,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999815211263819,
|
|
"loss": 7.1507,
|
|
"mean_token_accuracy": 0.10858112126588822,
|
|
"num_tokens": 2758915.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 7.191486263275147,
|
|
"epoch": 0.14095066726645675,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999810609045444,
|
|
"loss": 7.1754,
|
|
"mean_token_accuracy": 0.10965260490775108,
|
|
"num_tokens": 2768972.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 7.156418704986573,
|
|
"epoch": 0.1414504923276853,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999805950222412,
|
|
"loss": 7.0278,
|
|
"mean_token_accuracy": 0.10822951421141624,
|
|
"num_tokens": 2777989.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 7.091416835784912,
|
|
"epoch": 0.1419503173889139,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999801234794843,
|
|
"loss": 7.1096,
|
|
"mean_token_accuracy": 0.11228812485933304,
|
|
"num_tokens": 2788227.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 7.147107839584351,
|
|
"epoch": 0.14245014245014245,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999796462762853,
|
|
"loss": 7.1112,
|
|
"mean_token_accuracy": 0.11311104521155357,
|
|
"num_tokens": 2797729.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 7.119664812088013,
|
|
"epoch": 0.142949967511371,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999791634126562,
|
|
"loss": 7.1126,
|
|
"mean_token_accuracy": 0.11075319051742553,
|
|
"num_tokens": 2807215.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 7.124571132659912,
|
|
"epoch": 0.1434497925725996,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004999786748886094,
|
|
"loss": 7.0246,
|
|
"mean_token_accuracy": 0.11238908171653747,
|
|
"num_tokens": 2816945.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 7.017452239990234,
|
|
"epoch": 0.14394961763382816,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999781807041569,
|
|
"loss": 7.1146,
|
|
"mean_token_accuracy": 0.10776891112327576,
|
|
"num_tokens": 2827072.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 7.165062618255615,
|
|
"epoch": 0.14444944269505672,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999776808593113,
|
|
"loss": 7.0482,
|
|
"mean_token_accuracy": 0.11216341257095337,
|
|
"num_tokens": 2837928.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 7.001790475845337,
|
|
"epoch": 0.1449492677562853,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999771753540852,
|
|
"loss": 7.0846,
|
|
"mean_token_accuracy": 0.11152777597308158,
|
|
"num_tokens": 2847861.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 7.149148035049438,
|
|
"epoch": 0.14544909281751386,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999766641884912,
|
|
"loss": 7.0848,
|
|
"mean_token_accuracy": 0.11256931573152543,
|
|
"num_tokens": 2857885.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 7.160283946990967,
|
|
"epoch": 0.14594891787874245,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999761473625422,
|
|
"loss": 7.0932,
|
|
"mean_token_accuracy": 0.10660878345370292,
|
|
"num_tokens": 2867004.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 7.065319442749024,
|
|
"epoch": 0.146448742939971,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999756248762513,
|
|
"loss": 6.9736,
|
|
"mean_token_accuracy": 0.11344703435897827,
|
|
"num_tokens": 2876285.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 7.079582357406617,
|
|
"epoch": 0.14694856800119957,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999750967296315,
|
|
"loss": 7.112,
|
|
"mean_token_accuracy": 0.10987017676234245,
|
|
"num_tokens": 2886967.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 7.077367973327637,
|
|
"epoch": 0.14744839306242816,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999745629226962,
|
|
"loss": 7.0936,
|
|
"mean_token_accuracy": 0.10697494596242904,
|
|
"num_tokens": 2897137.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 7.038984680175782,
|
|
"epoch": 0.14794821812365672,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999740234554589,
|
|
"loss": 7.0472,
|
|
"mean_token_accuracy": 0.12016323506832123,
|
|
"num_tokens": 2907658.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 7.136841917037964,
|
|
"epoch": 0.1484480431848853,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999734783279327,
|
|
"loss": 7.0572,
|
|
"mean_token_accuracy": 0.11264566704630852,
|
|
"num_tokens": 2917801.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 7.058710241317749,
|
|
"epoch": 0.14894786824611386,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499972927540132,
|
|
"loss": 7.1593,
|
|
"mean_token_accuracy": 0.1104632668197155,
|
|
"num_tokens": 2927188.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 7.148079061508179,
|
|
"epoch": 0.14944769330734242,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999723710920703,
|
|
"loss": 7.0421,
|
|
"mean_token_accuracy": 0.10991474613547325,
|
|
"num_tokens": 2936781.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 6.985206222534179,
|
|
"epoch": 0.149947518368571,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999718089837616,
|
|
"loss": 7.0034,
|
|
"mean_token_accuracy": 0.11071012616157531,
|
|
"num_tokens": 2946426.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 6.977966022491455,
|
|
"epoch": 0.15044734342979957,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00049997124121522,
|
|
"loss": 7.0591,
|
|
"mean_token_accuracy": 0.11089984625577927,
|
|
"num_tokens": 2956246.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 7.119696187973022,
|
|
"epoch": 0.15094716849102813,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999706677864599,
|
|
"loss": 7.0301,
|
|
"mean_token_accuracy": 0.11129701286554336,
|
|
"num_tokens": 2965930.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 7.027358150482177,
|
|
"epoch": 0.15144699355225671,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999700886974958,
|
|
"loss": 6.9594,
|
|
"mean_token_accuracy": 0.11398379057645798,
|
|
"num_tokens": 2975975.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 7.029348134994507,
|
|
"epoch": 0.15194681861348527,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499969503948342,
|
|
"loss": 6.9922,
|
|
"mean_token_accuracy": 0.11278997659683228,
|
|
"num_tokens": 2985343.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 6.995435190200806,
|
|
"epoch": 0.15244664367471386,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999689135390134,
|
|
"loss": 7.0206,
|
|
"mean_token_accuracy": 0.11354669854044915,
|
|
"num_tokens": 2994420.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 7.102861928939819,
|
|
"epoch": 0.15294646873594242,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999683174695249,
|
|
"loss": 7.1314,
|
|
"mean_token_accuracy": 0.11147044822573662,
|
|
"num_tokens": 3004447.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 7.11038761138916,
|
|
"epoch": 0.15344629379717098,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999677157398914,
|
|
"loss": 7.0136,
|
|
"mean_token_accuracy": 0.11158140152692794,
|
|
"num_tokens": 3014596.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 7.001529932022095,
|
|
"epoch": 0.15394611885839957,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999671083501281,
|
|
"loss": 6.9424,
|
|
"mean_token_accuracy": 0.11554695665836334,
|
|
"num_tokens": 3024528.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 7.043489742279053,
|
|
"epoch": 0.15444594391962813,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999664953002502,
|
|
"loss": 7.0757,
|
|
"mean_token_accuracy": 0.1089545451104641,
|
|
"num_tokens": 3035233.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 7.057877731323242,
|
|
"epoch": 0.1549457689808567,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499965876590273,
|
|
"loss": 7.0639,
|
|
"mean_token_accuracy": 0.11354411020874977,
|
|
"num_tokens": 3045890.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 7.006091165542602,
|
|
"epoch": 0.15544559404208527,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999652522202125,
|
|
"loss": 6.9704,
|
|
"mean_token_accuracy": 0.11927012428641319,
|
|
"num_tokens": 3056640.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 6.988191604614258,
|
|
"epoch": 0.15594541910331383,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999646221900839,
|
|
"loss": 6.9995,
|
|
"mean_token_accuracy": 0.11643217280507087,
|
|
"num_tokens": 3066938.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 7.100666046142578,
|
|
"epoch": 0.15644524416454242,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999639864999034,
|
|
"loss": 7.1224,
|
|
"mean_token_accuracy": 0.11021771505475045,
|
|
"num_tokens": 3076791.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 7.040261554718017,
|
|
"epoch": 0.15694506922577098,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499963345149687,
|
|
"loss": 6.9766,
|
|
"mean_token_accuracy": 0.1124839298427105,
|
|
"num_tokens": 3087532.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 7.011826610565185,
|
|
"epoch": 0.15744489428699954,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999626981394506,
|
|
"loss": 7.1019,
|
|
"mean_token_accuracy": 0.11321934536099434,
|
|
"num_tokens": 3097465.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 7.116326904296875,
|
|
"epoch": 0.15794471934822812,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999620454692106,
|
|
"loss": 7.0088,
|
|
"mean_token_accuracy": 0.11308922916650772,
|
|
"num_tokens": 3107162.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 7.002964687347412,
|
|
"epoch": 0.15844454440945668,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999613871389836,
|
|
"loss": 6.9932,
|
|
"mean_token_accuracy": 0.11376159563660622,
|
|
"num_tokens": 3117154.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 7.0667582035064695,
|
|
"epoch": 0.15894436947068527,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999607231487858,
|
|
"loss": 7.0118,
|
|
"mean_token_accuracy": 0.11034693121910095,
|
|
"num_tokens": 3127635.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 7.099604892730713,
|
|
"epoch": 0.15944419453191383,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000499960053498634,
|
|
"loss": 7.0542,
|
|
"mean_token_accuracy": 0.10722034946084022,
|
|
"num_tokens": 3137806.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 6.99808521270752,
|
|
"epoch": 0.1599440195931424,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999593781885454,
|
|
"loss": 7.0869,
|
|
"mean_token_accuracy": 0.10542495176196098,
|
|
"num_tokens": 3147704.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 7.039315319061279,
|
|
"epoch": 0.16044384465437098,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999586972185366,
|
|
"loss": 7.0516,
|
|
"mean_token_accuracy": 0.10607154071331024,
|
|
"num_tokens": 3158486.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 7.045173120498657,
|
|
"epoch": 0.16094366971559954,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999580105886248,
|
|
"loss": 7.0479,
|
|
"mean_token_accuracy": 0.11122439876198768,
|
|
"num_tokens": 3168518.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 7.000042533874511,
|
|
"epoch": 0.16144349477682812,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999573182988275,
|
|
"loss": 6.9298,
|
|
"mean_token_accuracy": 0.11688626557588577,
|
|
"num_tokens": 3177502.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 7.017080640792846,
|
|
"epoch": 0.16194331983805668,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999566203491619,
|
|
"loss": 6.9921,
|
|
"mean_token_accuracy": 0.11503020003437996,
|
|
"num_tokens": 3187408.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 7.0513831615448,
|
|
"epoch": 0.16244314489928524,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999559167396455,
|
|
"loss": 7.0567,
|
|
"mean_token_accuracy": 0.11678390353918075,
|
|
"num_tokens": 3196812.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 6.902290725708008,
|
|
"epoch": 0.16294296996051383,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999552074702963,
|
|
"loss": 6.9108,
|
|
"mean_token_accuracy": 0.11789578422904015,
|
|
"num_tokens": 3206159.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 7.007291650772094,
|
|
"epoch": 0.1634427950217424,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999544925411318,
|
|
"loss": 6.8954,
|
|
"mean_token_accuracy": 0.12061700448393822,
|
|
"num_tokens": 3217329.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 6.951911449432373,
|
|
"epoch": 0.16394262008297095,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999537719521703,
|
|
"loss": 7.0219,
|
|
"mean_token_accuracy": 0.11060998439788819,
|
|
"num_tokens": 3227558.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 7.113637161254883,
|
|
"epoch": 0.16444244514419953,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999530457034297,
|
|
"loss": 7.1038,
|
|
"mean_token_accuracy": 0.10778464749455452,
|
|
"num_tokens": 3237719.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 7.020438766479492,
|
|
"epoch": 0.1649422702054281,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999523137949283,
|
|
"loss": 7.0316,
|
|
"mean_token_accuracy": 0.11263542622327805,
|
|
"num_tokens": 3246483.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 6.933847713470459,
|
|
"epoch": 0.16544209526665668,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999515762266846,
|
|
"loss": 6.9301,
|
|
"mean_token_accuracy": 0.1197948582470417,
|
|
"num_tokens": 3256955.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 7.0298436164855955,
|
|
"epoch": 0.16594192032788524,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999508329987173,
|
|
"loss": 6.998,
|
|
"mean_token_accuracy": 0.11044911220669747,
|
|
"num_tokens": 3266799.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 6.953704118728638,
|
|
"epoch": 0.1664417453891138,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999500841110447,
|
|
"loss": 6.9928,
|
|
"mean_token_accuracy": 0.11013735309243203,
|
|
"num_tokens": 3276595.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 7.008637952804565,
|
|
"epoch": 0.16694157045034239,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499949329563686,
|
|
"loss": 6.9401,
|
|
"mean_token_accuracy": 0.11440528258681297,
|
|
"num_tokens": 3286047.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 7.053787803649902,
|
|
"epoch": 0.16744139551157095,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00049994856935666,
|
|
"loss": 7.0196,
|
|
"mean_token_accuracy": 0.11221319362521172,
|
|
"num_tokens": 3295364.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 6.936156606674194,
|
|
"epoch": 0.16794122057279953,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499947803489986,
|
|
"loss": 6.9291,
|
|
"mean_token_accuracy": 0.12198807075619697,
|
|
"num_tokens": 3305319.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 6.941357517242432,
|
|
"epoch": 0.1684410456340281,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999470319636829,
|
|
"loss": 6.9625,
|
|
"mean_token_accuracy": 0.11831458657979965,
|
|
"num_tokens": 3315349.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 7.03402681350708,
|
|
"epoch": 0.16894087069525665,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999462547777705,
|
|
"loss": 7.0281,
|
|
"mean_token_accuracy": 0.10700425431132317,
|
|
"num_tokens": 3325603.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 6.9488404273986815,
|
|
"epoch": 0.16944069575648524,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999454719322682,
|
|
"loss": 6.9345,
|
|
"mean_token_accuracy": 0.11474086120724677,
|
|
"num_tokens": 3334693.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 7.03020396232605,
|
|
"epoch": 0.1699405208177138,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999446834271958,
|
|
"loss": 6.9321,
|
|
"mean_token_accuracy": 0.1120713397860527,
|
|
"num_tokens": 3345259.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 6.898108196258545,
|
|
"epoch": 0.17044034587894236,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999438892625728,
|
|
"loss": 6.9402,
|
|
"mean_token_accuracy": 0.11133012548089027,
|
|
"num_tokens": 3354072.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 7.105929708480835,
|
|
"epoch": 0.17094017094017094,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999430894384198,
|
|
"loss": 6.9114,
|
|
"mean_token_accuracy": 0.11355426013469697,
|
|
"num_tokens": 3364881.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 6.9483030319213865,
|
|
"epoch": 0.1714399960013995,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999422839547564,
|
|
"loss": 6.9086,
|
|
"mean_token_accuracy": 0.11701997593045235,
|
|
"num_tokens": 3374030.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 6.9252705574035645,
|
|
"epoch": 0.1719398210626281,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999414728116029,
|
|
"loss": 6.8956,
|
|
"mean_token_accuracy": 0.11267698481678963,
|
|
"num_tokens": 3384009.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 7.041887044906616,
|
|
"epoch": 0.17243964612385665,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999406560089798,
|
|
"loss": 7.0475,
|
|
"mean_token_accuracy": 0.10910101756453514,
|
|
"num_tokens": 3393660.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 7.037035226821899,
|
|
"epoch": 0.1729394711850852,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999398335469078,
|
|
"loss": 7.0708,
|
|
"mean_token_accuracy": 0.11321713551878929,
|
|
"num_tokens": 3404364.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 6.9971565246582035,
|
|
"epoch": 0.1734392962463138,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999390054254074,
|
|
"loss": 6.9521,
|
|
"mean_token_accuracy": 0.1106104426085949,
|
|
"num_tokens": 3412990.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 6.852579402923584,
|
|
"epoch": 0.17393912130754235,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004999381716444996,
|
|
"loss": 6.9329,
|
|
"mean_token_accuracy": 0.11495454907417298,
|
|
"num_tokens": 3422339.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 6.959084606170654,
|
|
"epoch": 0.17443894636877094,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999373322042052,
|
|
"loss": 6.9043,
|
|
"mean_token_accuracy": 0.11547202616930008,
|
|
"num_tokens": 3433093.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 7.003214359283447,
|
|
"epoch": 0.1749387714299995,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999364871045455,
|
|
"loss": 6.9932,
|
|
"mean_token_accuracy": 0.11007570326328278,
|
|
"num_tokens": 3443464.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 6.978196811676026,
|
|
"epoch": 0.17543859649122806,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999356363455415,
|
|
"loss": 6.9345,
|
|
"mean_token_accuracy": 0.11543623134493827,
|
|
"num_tokens": 3453380.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 6.9858551025390625,
|
|
"epoch": 0.17593842155245665,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499934779927215,
|
|
"loss": 6.9758,
|
|
"mean_token_accuracy": 0.11607812270522118,
|
|
"num_tokens": 3463583.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 6.9328991889953615,
|
|
"epoch": 0.1764382466136852,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999339178495872,
|
|
"loss": 6.8913,
|
|
"mean_token_accuracy": 0.122561364620924,
|
|
"num_tokens": 3473640.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 6.92822413444519,
|
|
"epoch": 0.1769380716749138,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999330501126798,
|
|
"loss": 6.9503,
|
|
"mean_token_accuracy": 0.1169328160583973,
|
|
"num_tokens": 3483827.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 6.91102409362793,
|
|
"epoch": 0.17743789673614235,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999321767165148,
|
|
"loss": 6.9004,
|
|
"mean_token_accuracy": 0.12227763310074806,
|
|
"num_tokens": 3493763.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 7.019092321395874,
|
|
"epoch": 0.1779377217973709,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999312976611142,
|
|
"loss": 7.0148,
|
|
"mean_token_accuracy": 0.11686293035745621,
|
|
"num_tokens": 3503119.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 7.024073219299316,
|
|
"epoch": 0.1784375468585995,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999304129465,
|
|
"loss": 6.9535,
|
|
"mean_token_accuracy": 0.11344824209809304,
|
|
"num_tokens": 3513235.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 7.011400938034058,
|
|
"epoch": 0.17893737191982806,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999295225726945,
|
|
"loss": 7.0523,
|
|
"mean_token_accuracy": 0.10902164354920388,
|
|
"num_tokens": 3523633.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 6.947716617584229,
|
|
"epoch": 0.17943719698105662,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00049992862653972,
|
|
"loss": 6.8941,
|
|
"mean_token_accuracy": 0.11354788541793823,
|
|
"num_tokens": 3532888.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 6.984013509750366,
|
|
"epoch": 0.1799370220422852,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999277248475992,
|
|
"loss": 6.9221,
|
|
"mean_token_accuracy": 0.11461929455399514,
|
|
"num_tokens": 3541942.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 6.907126140594483,
|
|
"epoch": 0.18043684710351376,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999268174963547,
|
|
"loss": 6.8983,
|
|
"mean_token_accuracy": 0.11499835699796676,
|
|
"num_tokens": 3551544.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 6.945745325088501,
|
|
"epoch": 0.18093667216474235,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999259044860093,
|
|
"loss": 6.8902,
|
|
"mean_token_accuracy": 0.11644125431776046,
|
|
"num_tokens": 3561024.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 6.9447986602783205,
|
|
"epoch": 0.1814364972259709,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999249858165861,
|
|
"loss": 6.8811,
|
|
"mean_token_accuracy": 0.1235733337700367,
|
|
"num_tokens": 3570962.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 6.819528198242187,
|
|
"epoch": 0.18193632228719947,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999240614881082,
|
|
"loss": 6.8763,
|
|
"mean_token_accuracy": 0.1207821324467659,
|
|
"num_tokens": 3580669.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 7.0006632804870605,
|
|
"epoch": 0.18243614734842806,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999231315005987,
|
|
"loss": 6.8879,
|
|
"mean_token_accuracy": 0.11845619827508927,
|
|
"num_tokens": 3590627.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 6.9256019115448,
|
|
"epoch": 0.18293597240965662,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999221958540811,
|
|
"loss": 6.9646,
|
|
"mean_token_accuracy": 0.10778707936406136,
|
|
"num_tokens": 3599872.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 6.9726580619812015,
|
|
"epoch": 0.1834357974708852,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999212545485789,
|
|
"loss": 6.9475,
|
|
"mean_token_accuracy": 0.11592329442501068,
|
|
"num_tokens": 3609809.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 7.054142475128174,
|
|
"epoch": 0.18393562253211376,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999203075841159,
|
|
"loss": 6.9647,
|
|
"mean_token_accuracy": 0.11736813709139823,
|
|
"num_tokens": 3619385.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 6.828405857086182,
|
|
"epoch": 0.18443544759334232,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999193549607157,
|
|
"loss": 6.8006,
|
|
"mean_token_accuracy": 0.12424161806702613,
|
|
"num_tokens": 3628867.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 6.887426710128784,
|
|
"epoch": 0.1849352726545709,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999183966784026,
|
|
"loss": 6.8011,
|
|
"mean_token_accuracy": 0.13002747148275376,
|
|
"num_tokens": 3637528.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 6.9064164638519285,
|
|
"epoch": 0.18543509771579947,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999174327372004,
|
|
"loss": 6.943,
|
|
"mean_token_accuracy": 0.11500856131315232,
|
|
"num_tokens": 3648011.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 6.918382453918457,
|
|
"epoch": 0.18593492277702803,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999164631371335,
|
|
"loss": 6.9275,
|
|
"mean_token_accuracy": 0.11812992170453071,
|
|
"num_tokens": 3657648.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 7.01478066444397,
|
|
"epoch": 0.18643474783825661,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999154878782262,
|
|
"loss": 6.9333,
|
|
"mean_token_accuracy": 0.11356185749173164,
|
|
"num_tokens": 3666965.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 6.965643262863159,
|
|
"epoch": 0.18693457289948517,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499914506960503,
|
|
"loss": 6.9537,
|
|
"mean_token_accuracy": 0.10866264775395393,
|
|
"num_tokens": 3676609.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 6.886865043640137,
|
|
"epoch": 0.18743439796071376,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999135203839889,
|
|
"loss": 6.8298,
|
|
"mean_token_accuracy": 0.1227896973490715,
|
|
"num_tokens": 3685884.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 6.844762706756592,
|
|
"epoch": 0.18793422302194232,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999125281487084,
|
|
"loss": 6.9795,
|
|
"mean_token_accuracy": 0.114560666680336,
|
|
"num_tokens": 3695436.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 6.946454906463623,
|
|
"epoch": 0.18843404808317088,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999115302546866,
|
|
"loss": 6.7854,
|
|
"mean_token_accuracy": 0.12357550859451294,
|
|
"num_tokens": 3704806.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 6.897518253326416,
|
|
"epoch": 0.18893387314439947,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004999105267019486,
|
|
"loss": 6.8642,
|
|
"mean_token_accuracy": 0.1193320944905281,
|
|
"num_tokens": 3713927.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 6.967895030975342,
|
|
"epoch": 0.18943369820562803,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004999095174905195,
|
|
"loss": 6.9635,
|
|
"mean_token_accuracy": 0.11119818165898324,
|
|
"num_tokens": 3723685.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 6.898874568939209,
|
|
"epoch": 0.1899335232668566,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999085026204249,
|
|
"loss": 6.9147,
|
|
"mean_token_accuracy": 0.11309322565793992,
|
|
"num_tokens": 3733918.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 6.957060718536377,
|
|
"epoch": 0.19043334832808517,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999074820916903,
|
|
"loss": 6.8693,
|
|
"mean_token_accuracy": 0.11191848888993264,
|
|
"num_tokens": 3744466.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 6.869232225418091,
|
|
"epoch": 0.19093317338931373,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999064559043412,
|
|
"loss": 6.827,
|
|
"mean_token_accuracy": 0.11591498851776123,
|
|
"num_tokens": 3754082.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 6.862514638900757,
|
|
"epoch": 0.19143299845054232,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999054240584037,
|
|
"loss": 6.8541,
|
|
"mean_token_accuracy": 0.12327471598982812,
|
|
"num_tokens": 3763111.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 6.996739625930786,
|
|
"epoch": 0.19193282351177088,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999043865539035,
|
|
"loss": 6.8973,
|
|
"mean_token_accuracy": 0.11046274900436401,
|
|
"num_tokens": 3772555.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 6.9612620830535885,
|
|
"epoch": 0.19243264857299944,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999033433908667,
|
|
"loss": 6.9552,
|
|
"mean_token_accuracy": 0.11249120384454728,
|
|
"num_tokens": 3783073.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 6.834769010543823,
|
|
"epoch": 0.19293247363422802,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999022945693198,
|
|
"loss": 6.8807,
|
|
"mean_token_accuracy": 0.11839989647269249,
|
|
"num_tokens": 3792277.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 6.931283950805664,
|
|
"epoch": 0.19343229869545658,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499901240089289,
|
|
"loss": 6.8551,
|
|
"mean_token_accuracy": 0.11572782248258591,
|
|
"num_tokens": 3801098.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 6.933052253723145,
|
|
"epoch": 0.19393212375668517,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999001799508009,
|
|
"loss": 6.8941,
|
|
"mean_token_accuracy": 0.1140223778784275,
|
|
"num_tokens": 3810614.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 6.9448882102966305,
|
|
"epoch": 0.19443194881791373,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998991141538821,
|
|
"loss": 6.8723,
|
|
"mean_token_accuracy": 0.11779175996780396,
|
|
"num_tokens": 3818989.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 6.793414831161499,
|
|
"epoch": 0.1949317738791423,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998980426985596,
|
|
"loss": 6.9092,
|
|
"mean_token_accuracy": 0.1152567982673645,
|
|
"num_tokens": 3829319.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 6.958078002929687,
|
|
"epoch": 0.19543159894037088,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00049989696558486,
|
|
"loss": 6.9356,
|
|
"mean_token_accuracy": 0.1145101934671402,
|
|
"num_tokens": 3839545.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 6.871245193481445,
|
|
"epoch": 0.19593142400159944,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004998958828128108,
|
|
"loss": 6.8735,
|
|
"mean_token_accuracy": 0.1180442787706852,
|
|
"num_tokens": 3849029.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 6.933473062515259,
|
|
"epoch": 0.19643124906282802,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998947943824389,
|
|
"loss": 6.9198,
|
|
"mean_token_accuracy": 0.11709642335772515,
|
|
"num_tokens": 3859463.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 7.0088598251342775,
|
|
"epoch": 0.19693107412405658,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998937002937719,
|
|
"loss": 6.9588,
|
|
"mean_token_accuracy": 0.11571476459503174,
|
|
"num_tokens": 3869695.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 6.87238917350769,
|
|
"epoch": 0.19743089918528514,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998926005468373,
|
|
"loss": 6.9183,
|
|
"mean_token_accuracy": 0.11517301499843598,
|
|
"num_tokens": 3879608.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 6.92598967552185,
|
|
"epoch": 0.19793072424651373,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998914951416627,
|
|
"loss": 6.8308,
|
|
"mean_token_accuracy": 0.11759625598788262,
|
|
"num_tokens": 3888709.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 6.7358252048492435,
|
|
"epoch": 0.1984305493077423,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000499890384078276,
|
|
"loss": 6.7746,
|
|
"mean_token_accuracy": 0.12024817541241646,
|
|
"num_tokens": 3898392.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 6.905943870544434,
|
|
"epoch": 0.19893037436897085,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998892673567051,
|
|
"loss": 6.9924,
|
|
"mean_token_accuracy": 0.10537268072366715,
|
|
"num_tokens": 3909508.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 6.925677967071533,
|
|
"epoch": 0.19943019943019943,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004998881449769781,
|
|
"loss": 6.8298,
|
|
"mean_token_accuracy": 0.11959851756691933,
|
|
"num_tokens": 3918155.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 6.9149247169494625,
|
|
"epoch": 0.199930024491428,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998870169391232,
|
|
"loss": 6.8808,
|
|
"mean_token_accuracy": 0.11446636393666268,
|
|
"num_tokens": 3928478.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 6.903803873062134,
|
|
"epoch": 0.20042984955265658,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499885883243169,
|
|
"loss": 6.9271,
|
|
"mean_token_accuracy": 0.12026000469923019,
|
|
"num_tokens": 3938126.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 6.782207250595093,
|
|
"epoch": 0.20092967461388514,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998847438891437,
|
|
"loss": 6.7315,
|
|
"mean_token_accuracy": 0.11714796498417854,
|
|
"num_tokens": 3948176.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 6.901465272903442,
|
|
"epoch": 0.2014294996751137,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998835988770761,
|
|
"loss": 6.8789,
|
|
"mean_token_accuracy": 0.1191024824976921,
|
|
"num_tokens": 3958983.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 6.933460426330567,
|
|
"epoch": 0.20192932473634229,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499882448206995,
|
|
"loss": 6.8457,
|
|
"mean_token_accuracy": 0.12024828121066093,
|
|
"num_tokens": 3968766.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 6.861673736572266,
|
|
"epoch": 0.20242914979757085,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998812918789293,
|
|
"loss": 6.8413,
|
|
"mean_token_accuracy": 0.11853379607200623,
|
|
"num_tokens": 3979487.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 6.832311201095581,
|
|
"epoch": 0.20292897485879943,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998801298929084,
|
|
"loss": 6.8225,
|
|
"mean_token_accuracy": 0.11745660156011581,
|
|
"num_tokens": 3988450.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 6.882190370559693,
|
|
"epoch": 0.203428799920028,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004998789622489611,
|
|
"loss": 6.825,
|
|
"mean_token_accuracy": 0.11936729922890663,
|
|
"num_tokens": 3997492.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 6.902972221374512,
|
|
"epoch": 0.20392862498125655,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998777889471171,
|
|
"loss": 6.8323,
|
|
"mean_token_accuracy": 0.12065311595797538,
|
|
"num_tokens": 4007298.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 6.8405660629272464,
|
|
"epoch": 0.20442845004248514,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998766099874056,
|
|
"loss": 6.8628,
|
|
"mean_token_accuracy": 0.1189582072198391,
|
|
"num_tokens": 4017727.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 6.887753915786743,
|
|
"epoch": 0.2049282751037137,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998754253698566,
|
|
"loss": 6.8607,
|
|
"mean_token_accuracy": 0.11793215274810791,
|
|
"num_tokens": 4027618.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 6.814794063568115,
|
|
"epoch": 0.20542810016494226,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998742350944998,
|
|
"loss": 6.8848,
|
|
"mean_token_accuracy": 0.11500374749302864,
|
|
"num_tokens": 4038831.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 6.859647417068482,
|
|
"epoch": 0.20592792522617084,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998730391613651,
|
|
"loss": 6.8482,
|
|
"mean_token_accuracy": 0.11991979852318764,
|
|
"num_tokens": 4048736.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 6.81789493560791,
|
|
"epoch": 0.2064277502873994,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998718375704825,
|
|
"loss": 6.7655,
|
|
"mean_token_accuracy": 0.11906948909163476,
|
|
"num_tokens": 4057633.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 6.886240243911743,
|
|
"epoch": 0.206927575348628,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998706303218825,
|
|
"loss": 6.8785,
|
|
"mean_token_accuracy": 0.1240123063325882,
|
|
"num_tokens": 4067883.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 6.954527091979981,
|
|
"epoch": 0.20742740040985655,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998694174155952,
|
|
"loss": 6.7437,
|
|
"mean_token_accuracy": 0.12506394237279891,
|
|
"num_tokens": 4078147.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 6.741695070266724,
|
|
"epoch": 0.2079272254710851,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998681988516512,
|
|
"loss": 6.7181,
|
|
"mean_token_accuracy": 0.12472501173615455,
|
|
"num_tokens": 4087130.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 6.781894207000732,
|
|
"epoch": 0.2084270505323137,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998669746300811,
|
|
"loss": 6.851,
|
|
"mean_token_accuracy": 0.12515389323234558,
|
|
"num_tokens": 4096840.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 7.006636762619019,
|
|
"epoch": 0.20892687559354226,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998657447509159,
|
|
"loss": 6.8735,
|
|
"mean_token_accuracy": 0.11554861664772034,
|
|
"num_tokens": 4105842.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 6.778407716751099,
|
|
"epoch": 0.20942670065477084,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998645092141864,
|
|
"loss": 6.7627,
|
|
"mean_token_accuracy": 0.12160579934716224,
|
|
"num_tokens": 4114865.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 6.914173173904419,
|
|
"epoch": 0.2099265257159994,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004998632680199238,
|
|
"loss": 6.8991,
|
|
"mean_token_accuracy": 0.11216249763965606,
|
|
"num_tokens": 4124954.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 6.829844617843628,
|
|
"epoch": 0.21042635077722796,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998620211681591,
|
|
"loss": 6.7727,
|
|
"mean_token_accuracy": 0.12200651988387108,
|
|
"num_tokens": 4134091.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 6.9233245849609375,
|
|
"epoch": 0.21092617583845655,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998607686589239,
|
|
"loss": 6.8436,
|
|
"mean_token_accuracy": 0.11750573813915252,
|
|
"num_tokens": 4143566.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 6.829675722122192,
|
|
"epoch": 0.2114260008996851,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004998595104922496,
|
|
"loss": 6.8147,
|
|
"mean_token_accuracy": 0.1171520471572876,
|
|
"num_tokens": 4153053.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 6.852267074584961,
|
|
"epoch": 0.2119258259609137,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998582466681678,
|
|
"loss": 6.7949,
|
|
"mean_token_accuracy": 0.12671943306922911,
|
|
"num_tokens": 4162925.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 6.735289525985718,
|
|
"epoch": 0.21242565102214225,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998569771867105,
|
|
"loss": 6.7167,
|
|
"mean_token_accuracy": 0.12583983838558196,
|
|
"num_tokens": 4172077.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 6.815008449554443,
|
|
"epoch": 0.2129254760833708,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998557020479095,
|
|
"loss": 6.807,
|
|
"mean_token_accuracy": 0.1230967991054058,
|
|
"num_tokens": 4182134.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 6.904581451416016,
|
|
"epoch": 0.2134253011445994,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998544212517968,
|
|
"loss": 6.8459,
|
|
"mean_token_accuracy": 0.11531514376401901,
|
|
"num_tokens": 4191963.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 6.808885908126831,
|
|
"epoch": 0.21392512620582796,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998531347984047,
|
|
"loss": 6.7897,
|
|
"mean_token_accuracy": 0.12169457077980042,
|
|
"num_tokens": 4202180.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 6.8748163223266605,
|
|
"epoch": 0.21442495126705652,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004998518426877656,
|
|
"loss": 6.8107,
|
|
"mean_token_accuracy": 0.12011150643229485,
|
|
"num_tokens": 4211874.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 6.78511381149292,
|
|
"epoch": 0.2149247763282851,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998505449199122,
|
|
"loss": 6.7715,
|
|
"mean_token_accuracy": 0.11865760311484337,
|
|
"num_tokens": 4221610.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 6.713295936584473,
|
|
"epoch": 0.21542460138951366,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004998492414948768,
|
|
"loss": 6.7396,
|
|
"mean_token_accuracy": 0.12928089648485183,
|
|
"num_tokens": 4230610.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 6.8231436252594,
|
|
"epoch": 0.21592442645074225,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004998479324126924,
|
|
"loss": 6.8422,
|
|
"mean_token_accuracy": 0.11402832642197609,
|
|
"num_tokens": 4241389.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 6.889860057830811,
|
|
"epoch": 0.2164242515119708,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998466176733918,
|
|
"loss": 6.7815,
|
|
"mean_token_accuracy": 0.12243804410099983,
|
|
"num_tokens": 4250617.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 6.73257622718811,
|
|
"epoch": 0.21692407657319937,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998452972770082,
|
|
"loss": 6.7796,
|
|
"mean_token_accuracy": 0.12635771334171295,
|
|
"num_tokens": 4260000.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 6.793949365615845,
|
|
"epoch": 0.21742390163442796,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998439712235747,
|
|
"loss": 6.7069,
|
|
"mean_token_accuracy": 0.12508605569601058,
|
|
"num_tokens": 4269751.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 6.805910682678222,
|
|
"epoch": 0.21792372669565652,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998426395131248,
|
|
"loss": 6.7758,
|
|
"mean_token_accuracy": 0.11987375542521476,
|
|
"num_tokens": 4279210.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 6.804451131820679,
|
|
"epoch": 0.2184235517568851,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998413021456919,
|
|
"loss": 6.7386,
|
|
"mean_token_accuracy": 0.12299165651202201,
|
|
"num_tokens": 4288573.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 6.781830787658691,
|
|
"epoch": 0.21892337681811366,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998399591213098,
|
|
"loss": 6.7641,
|
|
"mean_token_accuracy": 0.11898610666394234,
|
|
"num_tokens": 4298438.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 6.778064155578614,
|
|
"epoch": 0.21942320187934222,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998386104400122,
|
|
"loss": 6.6757,
|
|
"mean_token_accuracy": 0.13105980008840562,
|
|
"num_tokens": 4307174.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 6.902370309829712,
|
|
"epoch": 0.2199230269405708,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998372561018329,
|
|
"loss": 6.8756,
|
|
"mean_token_accuracy": 0.11589000076055526,
|
|
"num_tokens": 4317220.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 6.813035392761231,
|
|
"epoch": 0.22042285200179937,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998358961068062,
|
|
"loss": 6.7789,
|
|
"mean_token_accuracy": 0.1260307364165783,
|
|
"num_tokens": 4326496.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 6.771057558059693,
|
|
"epoch": 0.22092267706302793,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998345304549661,
|
|
"loss": 6.7837,
|
|
"mean_token_accuracy": 0.12462224960327148,
|
|
"num_tokens": 4335705.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 6.854783344268799,
|
|
"epoch": 0.22142250212425652,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998331591463471,
|
|
"loss": 6.816,
|
|
"mean_token_accuracy": 0.12542387172579766,
|
|
"num_tokens": 4344711.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 6.836872529983521,
|
|
"epoch": 0.22192232718548507,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998317821809837,
|
|
"loss": 6.823,
|
|
"mean_token_accuracy": 0.12106759324669839,
|
|
"num_tokens": 4355448.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 6.691077804565429,
|
|
"epoch": 0.22242215224671366,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998303995589104,
|
|
"loss": 6.6938,
|
|
"mean_token_accuracy": 0.12454739660024643,
|
|
"num_tokens": 4365104.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 6.707037878036499,
|
|
"epoch": 0.22292197730794222,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004998290112801623,
|
|
"loss": 6.6715,
|
|
"mean_token_accuracy": 0.12494275271892548,
|
|
"num_tokens": 4375219.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 6.891085195541382,
|
|
"epoch": 0.22342180236917078,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499827617344774,
|
|
"loss": 6.8096,
|
|
"mean_token_accuracy": 0.1162020929157734,
|
|
"num_tokens": 4385294.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 6.842881155014038,
|
|
"epoch": 0.22392162743039937,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998262177527807,
|
|
"loss": 6.7727,
|
|
"mean_token_accuracy": 0.11394542381167412,
|
|
"num_tokens": 4394305.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 6.6954185485839846,
|
|
"epoch": 0.22442145249162793,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998248125042177,
|
|
"loss": 6.6253,
|
|
"mean_token_accuracy": 0.1304540902376175,
|
|
"num_tokens": 4403732.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 6.796254825592041,
|
|
"epoch": 0.2249212775528565,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998234015991202,
|
|
"loss": 6.8615,
|
|
"mean_token_accuracy": 0.11681714579463005,
|
|
"num_tokens": 4413730.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 6.899509286880493,
|
|
"epoch": 0.22542110261408507,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998219850375238,
|
|
"loss": 6.859,
|
|
"mean_token_accuracy": 0.11603142693638802,
|
|
"num_tokens": 4423051.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 6.866402816772461,
|
|
"epoch": 0.22592092767531363,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998205628194641,
|
|
"loss": 6.8641,
|
|
"mean_token_accuracy": 0.12003328129649163,
|
|
"num_tokens": 4433363.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 6.876128149032593,
|
|
"epoch": 0.22642075273654222,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004998191349449768,
|
|
"loss": 6.8133,
|
|
"mean_token_accuracy": 0.11659364998340607,
|
|
"num_tokens": 4442984.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 6.778914976119995,
|
|
"epoch": 0.22692057779777078,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998177014140981,
|
|
"loss": 6.7622,
|
|
"mean_token_accuracy": 0.11801078915596008,
|
|
"num_tokens": 4452364.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 6.881569671630859,
|
|
"epoch": 0.22742040285899934,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998162622268637,
|
|
"loss": 6.7927,
|
|
"mean_token_accuracy": 0.11506244912743568,
|
|
"num_tokens": 4461904.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 6.80613260269165,
|
|
"epoch": 0.22792022792022792,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998148173833101,
|
|
"loss": 6.7406,
|
|
"mean_token_accuracy": 0.11940495148301125,
|
|
"num_tokens": 4470633.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 6.768052959442139,
|
|
"epoch": 0.22842005298145648,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998133668834735,
|
|
"loss": 6.7526,
|
|
"mean_token_accuracy": 0.1232437625527382,
|
|
"num_tokens": 4480673.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 6.768804597854614,
|
|
"epoch": 0.22891987804268507,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004998119107273905,
|
|
"loss": 6.743,
|
|
"mean_token_accuracy": 0.11722776517271996,
|
|
"num_tokens": 4489923.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 6.719747304916382,
|
|
"epoch": 0.22941970310391363,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998104489150975,
|
|
"loss": 6.7136,
|
|
"mean_token_accuracy": 0.12137444093823432,
|
|
"num_tokens": 4501007.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 6.784075307846069,
|
|
"epoch": 0.2299195281651422,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004998089814466318,
|
|
"loss": 6.7367,
|
|
"mean_token_accuracy": 0.11942115277051926,
|
|
"num_tokens": 4510460.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 6.869019842147827,
|
|
"epoch": 0.23041935322637078,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004998075083220295,
|
|
"loss": 6.8036,
|
|
"mean_token_accuracy": 0.12088342234492302,
|
|
"num_tokens": 4521026.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 6.728188514709473,
|
|
"epoch": 0.23091917828759934,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998060295413286,
|
|
"loss": 6.7208,
|
|
"mean_token_accuracy": 0.12475512400269509,
|
|
"num_tokens": 4530818.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 6.693582963943482,
|
|
"epoch": 0.23141900334882792,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998045451045656,
|
|
"loss": 6.6643,
|
|
"mean_token_accuracy": 0.13362600281834602,
|
|
"num_tokens": 4539512.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 6.876028394699096,
|
|
"epoch": 0.23191882841005648,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998030550117782,
|
|
"loss": 6.8587,
|
|
"mean_token_accuracy": 0.11190490797162056,
|
|
"num_tokens": 4549030.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 6.743910264968872,
|
|
"epoch": 0.23241865347128504,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998015592630037,
|
|
"loss": 6.698,
|
|
"mean_token_accuracy": 0.1262820728123188,
|
|
"num_tokens": 4559347.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 6.810586643218994,
|
|
"epoch": 0.23291847853251363,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004998000578582798,
|
|
"loss": 6.752,
|
|
"mean_token_accuracy": 0.11423259377479553,
|
|
"num_tokens": 4568721.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 6.790478038787842,
|
|
"epoch": 0.2334183035937422,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997985507976443,
|
|
"loss": 6.7539,
|
|
"mean_token_accuracy": 0.1210959531366825,
|
|
"num_tokens": 4578265.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 6.713445091247559,
|
|
"epoch": 0.23391812865497075,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004997970380811351,
|
|
"loss": 6.718,
|
|
"mean_token_accuracy": 0.1265711396932602,
|
|
"num_tokens": 4588694.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 6.8143064975738525,
|
|
"epoch": 0.23441795371619933,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004997955197087904,
|
|
"loss": 6.7238,
|
|
"mean_token_accuracy": 0.1284726820886135,
|
|
"num_tokens": 4597754.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 6.756000995635986,
|
|
"epoch": 0.2349177787774279,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004997939956806481,
|
|
"loss": 6.7397,
|
|
"mean_token_accuracy": 0.12147602438926697,
|
|
"num_tokens": 4606874.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 6.706974267959595,
|
|
"epoch": 0.23541760383865648,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997924659967467,
|
|
"loss": 6.623,
|
|
"mean_token_accuracy": 0.12457457929849625,
|
|
"num_tokens": 4615588.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 6.68896107673645,
|
|
"epoch": 0.23591742889988504,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997909306571248,
|
|
"loss": 6.7797,
|
|
"mean_token_accuracy": 0.12551534697413444,
|
|
"num_tokens": 4625919.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 6.834859418869018,
|
|
"epoch": 0.2364172539611136,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997893896618209,
|
|
"loss": 6.726,
|
|
"mean_token_accuracy": 0.11857106536626816,
|
|
"num_tokens": 4635539.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 6.732093048095703,
|
|
"epoch": 0.2369170790223422,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004997878430108738,
|
|
"loss": 6.7191,
|
|
"mean_token_accuracy": 0.12062986120581627,
|
|
"num_tokens": 4645833.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 6.7105419635772705,
|
|
"epoch": 0.23741690408357075,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004997862907043224,
|
|
"loss": 6.8265,
|
|
"mean_token_accuracy": 0.1232969455420971,
|
|
"num_tokens": 4655166.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 6.9115959167480465,
|
|
"epoch": 0.23791672914479933,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997847327422059,
|
|
"loss": 6.7108,
|
|
"mean_token_accuracy": 0.12596101090312004,
|
|
"num_tokens": 4664884.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 6.6541790008544925,
|
|
"epoch": 0.2384165542060279,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997831691245632,
|
|
"loss": 6.7907,
|
|
"mean_token_accuracy": 0.12016936019062996,
|
|
"num_tokens": 4675172.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 6.848490476608276,
|
|
"epoch": 0.23891637926725645,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997815998514337,
|
|
"loss": 6.7032,
|
|
"mean_token_accuracy": 0.12810124084353447,
|
|
"num_tokens": 4684588.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 6.729746675491333,
|
|
"epoch": 0.23941620432848504,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997800249228572,
|
|
"loss": 6.816,
|
|
"mean_token_accuracy": 0.12293470725417137,
|
|
"num_tokens": 4694434.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 6.746816682815552,
|
|
"epoch": 0.2399160293897136,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997784443388732,
|
|
"loss": 6.7548,
|
|
"mean_token_accuracy": 0.12327200025320054,
|
|
"num_tokens": 4705080.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 6.883273792266846,
|
|
"epoch": 0.24041585445094216,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004997768580995212,
|
|
"loss": 6.8304,
|
|
"mean_token_accuracy": 0.12185543552041053,
|
|
"num_tokens": 4714466.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 6.736199378967285,
|
|
"epoch": 0.24091567951217074,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997752662048413,
|
|
"loss": 6.7419,
|
|
"mean_token_accuracy": 0.12363232001662254,
|
|
"num_tokens": 4724047.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 6.775224685668945,
|
|
"epoch": 0.2414155045733993,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997736686548736,
|
|
"loss": 6.7772,
|
|
"mean_token_accuracy": 0.11827057525515557,
|
|
"num_tokens": 4733153.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 6.771958589553833,
|
|
"epoch": 0.2419153296346279,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004997720654496582,
|
|
"loss": 6.6351,
|
|
"mean_token_accuracy": 0.1304004967212677,
|
|
"num_tokens": 4743239.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 6.749918031692505,
|
|
"epoch": 0.24241515469585645,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997704565892355,
|
|
"loss": 6.6749,
|
|
"mean_token_accuracy": 0.12188196331262588,
|
|
"num_tokens": 4753128.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 6.858197546005249,
|
|
"epoch": 0.242914979757085,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004997688420736459,
|
|
"loss": 6.9063,
|
|
"mean_token_accuracy": 0.10862480849027634,
|
|
"num_tokens": 4764056.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 6.790316009521485,
|
|
"epoch": 0.2434148048183136,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997672219029301,
|
|
"loss": 6.7419,
|
|
"mean_token_accuracy": 0.12110049352049827,
|
|
"num_tokens": 4773354.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 6.717658138275146,
|
|
"epoch": 0.24391462987954216,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997655960771288,
|
|
"loss": 6.6883,
|
|
"mean_token_accuracy": 0.1205076090991497,
|
|
"num_tokens": 4783367.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 6.718193531036377,
|
|
"epoch": 0.24441445494077074,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.000499763964596283,
|
|
"loss": 6.5672,
|
|
"mean_token_accuracy": 0.13306122049689292,
|
|
"num_tokens": 4793028.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 6.765444898605347,
|
|
"epoch": 0.2449142800019993,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997623274604336,
|
|
"loss": 6.7561,
|
|
"mean_token_accuracy": 0.11872197464108467,
|
|
"num_tokens": 4804032.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 6.793762731552124,
|
|
"epoch": 0.24541410506322786,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000499760684669622,
|
|
"loss": 6.7854,
|
|
"mean_token_accuracy": 0.12456026300787926,
|
|
"num_tokens": 4813294.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 6.7408191680908205,
|
|
"epoch": 0.24591393012445645,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004997590362238894,
|
|
"loss": 6.6902,
|
|
"mean_token_accuracy": 0.11964407935738564,
|
|
"num_tokens": 4823461.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 6.703203010559082,
|
|
"epoch": 0.246413755185685,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997573821232772,
|
|
"loss": 6.7469,
|
|
"mean_token_accuracy": 0.1259793259203434,
|
|
"num_tokens": 4832464.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 6.755440807342529,
|
|
"epoch": 0.24691358024691357,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997557223678272,
|
|
"loss": 6.7035,
|
|
"mean_token_accuracy": 0.11913309246301651,
|
|
"num_tokens": 4842697.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 6.782284879684449,
|
|
"epoch": 0.24741340530814215,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997540569575809,
|
|
"loss": 6.7543,
|
|
"mean_token_accuracy": 0.12437557801604271,
|
|
"num_tokens": 4853129.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 6.83038649559021,
|
|
"epoch": 0.2479132303693707,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997523858925805,
|
|
"loss": 6.7974,
|
|
"mean_token_accuracy": 0.11816194653511047,
|
|
"num_tokens": 4864048.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 6.671797800064087,
|
|
"epoch": 0.2484130554305993,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997507091728678,
|
|
"loss": 6.7311,
|
|
"mean_token_accuracy": 0.12627621069550515,
|
|
"num_tokens": 4874368.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 6.8561256408691404,
|
|
"epoch": 0.24891288049182786,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997490267984853,
|
|
"loss": 6.7148,
|
|
"mean_token_accuracy": 0.12414158284664153,
|
|
"num_tokens": 4884813.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 6.699068689346314,
|
|
"epoch": 0.24941270555305642,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997473387694749,
|
|
"loss": 6.7832,
|
|
"mean_token_accuracy": 0.118557108938694,
|
|
"num_tokens": 4895594.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 6.756707620620728,
|
|
"epoch": 0.249912530614285,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004997456450858793,
|
|
"loss": 6.6781,
|
|
"mean_token_accuracy": 0.12389897853136063,
|
|
"num_tokens": 4904922.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 6.794224119186401,
|
|
"epoch": 0.25041235567551356,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997439457477412,
|
|
"loss": 6.6721,
|
|
"mean_token_accuracy": 0.12629162073135375,
|
|
"num_tokens": 4915009.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 6.742335557937622,
|
|
"epoch": 0.25091218073674215,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997422407551032,
|
|
"loss": 6.818,
|
|
"mean_token_accuracy": 0.117496757209301,
|
|
"num_tokens": 4924916.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 6.740524244308472,
|
|
"epoch": 0.2514120057979707,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997405301080082,
|
|
"loss": 6.7218,
|
|
"mean_token_accuracy": 0.12168776243925095,
|
|
"num_tokens": 4935127.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 6.776787757873535,
|
|
"epoch": 0.25191183085919927,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004997388138064994,
|
|
"loss": 6.7088,
|
|
"mean_token_accuracy": 0.12240934222936631,
|
|
"num_tokens": 4944749.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 6.69001955986023,
|
|
"epoch": 0.25241165592042786,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997370918506198,
|
|
"loss": 6.568,
|
|
"mean_token_accuracy": 0.1336754024028778,
|
|
"num_tokens": 4953868.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 6.680736446380616,
|
|
"epoch": 0.25291148098165644,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997353642404129,
|
|
"loss": 6.6791,
|
|
"mean_token_accuracy": 0.12432244718074799,
|
|
"num_tokens": 4963282.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 6.6588935375213625,
|
|
"epoch": 0.253411306042885,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997336309759219,
|
|
"loss": 6.531,
|
|
"mean_token_accuracy": 0.13633738234639167,
|
|
"num_tokens": 4973099.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 6.730578756332397,
|
|
"epoch": 0.25391113110411356,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997318920571907,
|
|
"loss": 6.6989,
|
|
"mean_token_accuracy": 0.11887490078806877,
|
|
"num_tokens": 4983771.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 6.627429342269897,
|
|
"epoch": 0.25441095616534215,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499730147484263,
|
|
"loss": 6.5654,
|
|
"mean_token_accuracy": 0.12911427095532418,
|
|
"num_tokens": 4993648.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 6.69837760925293,
|
|
"epoch": 0.2549107812265707,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997283972571824,
|
|
"loss": 6.7168,
|
|
"mean_token_accuracy": 0.12526629120111465,
|
|
"num_tokens": 5002821.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 6.832654714584351,
|
|
"epoch": 0.25541060628779927,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997266413759934,
|
|
"loss": 6.7327,
|
|
"mean_token_accuracy": 0.12186189666390419,
|
|
"num_tokens": 5012655.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 6.656014776229858,
|
|
"epoch": 0.25591043134902786,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004997248798407397,
|
|
"loss": 6.7004,
|
|
"mean_token_accuracy": 0.12474093288183212,
|
|
"num_tokens": 5023649.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 6.723897504806518,
|
|
"epoch": 0.2564102564102564,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004997231126514659,
|
|
"loss": 6.6708,
|
|
"mean_token_accuracy": 0.13028084263205528,
|
|
"num_tokens": 5031945.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 6.767000675201416,
|
|
"epoch": 0.256910081471485,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004997213398082165,
|
|
"loss": 6.6893,
|
|
"mean_token_accuracy": 0.12177317440509797,
|
|
"num_tokens": 5042036.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 6.682856845855713,
|
|
"epoch": 0.25740990653271356,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499719561311036,
|
|
"loss": 6.7122,
|
|
"mean_token_accuracy": 0.1242594949901104,
|
|
"num_tokens": 5050986.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 6.787206935882568,
|
|
"epoch": 0.2579097315939421,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997177771599691,
|
|
"loss": 6.7099,
|
|
"mean_token_accuracy": 0.1260345883667469,
|
|
"num_tokens": 5061408.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 6.657704401016235,
|
|
"epoch": 0.2584095566551707,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997159873550607,
|
|
"loss": 6.6111,
|
|
"mean_token_accuracy": 0.125968037545681,
|
|
"num_tokens": 5071646.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 6.647315835952758,
|
|
"epoch": 0.25890938171639927,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004997141918963561,
|
|
"loss": 6.7173,
|
|
"mean_token_accuracy": 0.12666191905736923,
|
|
"num_tokens": 5083185.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 6.773238277435302,
|
|
"epoch": 0.25940920677762785,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997123907839001,
|
|
"loss": 6.6628,
|
|
"mean_token_accuracy": 0.1251784197986126,
|
|
"num_tokens": 5092993.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 6.78870210647583,
|
|
"epoch": 0.2599090318388564,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997105840177381,
|
|
"loss": 6.7272,
|
|
"mean_token_accuracy": 0.12102791294455528,
|
|
"num_tokens": 5102709.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 6.701229047775269,
|
|
"epoch": 0.260408856900085,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004997087715979157,
|
|
"loss": 6.6704,
|
|
"mean_token_accuracy": 0.11898972243070602,
|
|
"num_tokens": 5112858.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 6.76274938583374,
|
|
"epoch": 0.26090868196131356,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997069535244785,
|
|
"loss": 6.5925,
|
|
"mean_token_accuracy": 0.13014568462967874,
|
|
"num_tokens": 5123573.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 6.64758710861206,
|
|
"epoch": 0.2614085070225421,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997051297974722,
|
|
"loss": 6.7694,
|
|
"mean_token_accuracy": 0.12116136848926544,
|
|
"num_tokens": 5132908.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 6.752505588531494,
|
|
"epoch": 0.2619083320837707,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004997033004169425,
|
|
"loss": 6.6314,
|
|
"mean_token_accuracy": 0.13227704614400865,
|
|
"num_tokens": 5142331.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 6.808556032180786,
|
|
"epoch": 0.26240815714499927,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997014653829357,
|
|
"loss": 6.7369,
|
|
"mean_token_accuracy": 0.12015433385968208,
|
|
"num_tokens": 5152517.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 6.724541759490966,
|
|
"epoch": 0.2629079822062278,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004996996246954977,
|
|
"loss": 6.6678,
|
|
"mean_token_accuracy": 0.12828353345394133,
|
|
"num_tokens": 5162418.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 6.698705959320068,
|
|
"epoch": 0.2634078072674564,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004996977783546752,
|
|
"loss": 6.69,
|
|
"mean_token_accuracy": 0.1206023059785366,
|
|
"num_tokens": 5171948.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 6.750772285461426,
|
|
"epoch": 0.26390763232868497,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004996959263605143,
|
|
"loss": 6.6106,
|
|
"mean_token_accuracy": 0.1264311730861664,
|
|
"num_tokens": 5180963.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 6.683148622512817,
|
|
"epoch": 0.2644074573899135,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996940687130617,
|
|
"loss": 6.7276,
|
|
"mean_token_accuracy": 0.12301484346389771,
|
|
"num_tokens": 5192305.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 6.740709686279297,
|
|
"epoch": 0.2649072824511421,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996922054123641,
|
|
"loss": 6.6007,
|
|
"mean_token_accuracy": 0.1260277345776558,
|
|
"num_tokens": 5201503.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 6.702259254455567,
|
|
"epoch": 0.2654071075123707,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004996903364584685,
|
|
"loss": 6.5746,
|
|
"mean_token_accuracy": 0.1269563689827919,
|
|
"num_tokens": 5210206.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 6.542616653442383,
|
|
"epoch": 0.26590693257359926,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004996884618514219,
|
|
"loss": 6.596,
|
|
"mean_token_accuracy": 0.13134641647338868,
|
|
"num_tokens": 5220256.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 6.699193620681763,
|
|
"epoch": 0.2664067576348278,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004996865815912713,
|
|
"loss": 6.6338,
|
|
"mean_token_accuracy": 0.13359641507267953,
|
|
"num_tokens": 5229128.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 6.726186513900757,
|
|
"epoch": 0.2669065826960564,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004996846956780642,
|
|
"loss": 6.5722,
|
|
"mean_token_accuracy": 0.12618556693196298,
|
|
"num_tokens": 5239468.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 6.633094072341919,
|
|
"epoch": 0.26740640775728497,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499682804111848,
|
|
"loss": 6.6844,
|
|
"mean_token_accuracy": 0.12155252695083618,
|
|
"num_tokens": 5247957.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 6.73829493522644,
|
|
"epoch": 0.2679062328185135,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004996809068926702,
|
|
"loss": 6.6877,
|
|
"mean_token_accuracy": 0.12203190922737121,
|
|
"num_tokens": 5257960.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 6.618297576904297,
|
|
"epoch": 0.2684060578797421,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996790040205786,
|
|
"loss": 6.538,
|
|
"mean_token_accuracy": 0.1295544274151325,
|
|
"num_tokens": 5266696.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 6.642504405975342,
|
|
"epoch": 0.2689058829409707,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004996770954956211,
|
|
"loss": 6.52,
|
|
"mean_token_accuracy": 0.1335084095597267,
|
|
"num_tokens": 5275619.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 6.690548467636108,
|
|
"epoch": 0.2694057080021992,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996751813178456,
|
|
"loss": 6.6938,
|
|
"mean_token_accuracy": 0.12373248711228371,
|
|
"num_tokens": 5284884.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 6.612657642364502,
|
|
"epoch": 0.2699055330634278,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004996732614873005,
|
|
"loss": 6.5796,
|
|
"mean_token_accuracy": 0.13691650182008744,
|
|
"num_tokens": 5293909.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 6.598701143264771,
|
|
"epoch": 0.2704053581246564,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004996713360040339,
|
|
"loss": 6.6494,
|
|
"mean_token_accuracy": 0.12244352400302887,
|
|
"num_tokens": 5303142.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 6.737385845184326,
|
|
"epoch": 0.27090518318588497,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004996694048680942,
|
|
"loss": 6.595,
|
|
"mean_token_accuracy": 0.12717368975281715,
|
|
"num_tokens": 5313055.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 6.666927337646484,
|
|
"epoch": 0.2714050082471135,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004996674680795302,
|
|
"loss": 6.709,
|
|
"mean_token_accuracy": 0.11881735101342202,
|
|
"num_tokens": 5323773.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 6.573076391220093,
|
|
"epoch": 0.2719048333083421,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004996655256383905,
|
|
"loss": 6.487,
|
|
"mean_token_accuracy": 0.14107831716537475,
|
|
"num_tokens": 5334613.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 6.6817444324493405,
|
|
"epoch": 0.2724046583695707,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499663577544724,
|
|
"loss": 6.5659,
|
|
"mean_token_accuracy": 0.13264155611395836,
|
|
"num_tokens": 5344151.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 6.620177268981934,
|
|
"epoch": 0.2729044834307992,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004996616237985796,
|
|
"loss": 6.549,
|
|
"mean_token_accuracy": 0.1309521608054638,
|
|
"num_tokens": 5352425.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 6.676284456253052,
|
|
"epoch": 0.2734043084920278,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004996596644000066,
|
|
"loss": 6.7542,
|
|
"mean_token_accuracy": 0.12151754051446914,
|
|
"num_tokens": 5361811.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 6.73824896812439,
|
|
"epoch": 0.2739041335532564,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996576993490543,
|
|
"loss": 6.6959,
|
|
"mean_token_accuracy": 0.1195530690252781,
|
|
"num_tokens": 5371463.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 6.662166357040405,
|
|
"epoch": 0.2744039586144849,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004996557286457721,
|
|
"loss": 6.5441,
|
|
"mean_token_accuracy": 0.1362849183380604,
|
|
"num_tokens": 5381464.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 6.587826251983643,
|
|
"epoch": 0.2749037836757135,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004996537522902096,
|
|
"loss": 6.634,
|
|
"mean_token_accuracy": 0.12591350078582764,
|
|
"num_tokens": 5391012.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 6.7804382801055905,
|
|
"epoch": 0.2754036087369421,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996517702824163,
|
|
"loss": 6.7322,
|
|
"mean_token_accuracy": 0.12323454171419143,
|
|
"num_tokens": 5401198.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 6.769994783401489,
|
|
"epoch": 0.2759034337981706,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004996497826224425,
|
|
"loss": 6.6698,
|
|
"mean_token_accuracy": 0.12419450357556343,
|
|
"num_tokens": 5410592.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 6.562923526763916,
|
|
"epoch": 0.2764032588593992,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004996477893103379,
|
|
"loss": 6.6448,
|
|
"mean_token_accuracy": 0.12875826954841613,
|
|
"num_tokens": 5420878.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 6.72771463394165,
|
|
"epoch": 0.2769030839206278,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004996457903461527,
|
|
"loss": 6.643,
|
|
"mean_token_accuracy": 0.12691074088215828,
|
|
"num_tokens": 5431199.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 6.6997754096984865,
|
|
"epoch": 0.2774029089818564,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004996437857299373,
|
|
"loss": 6.5783,
|
|
"mean_token_accuracy": 0.12888110503554345,
|
|
"num_tokens": 5441661.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 6.5640599727630615,
|
|
"epoch": 0.2779027340430849,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499641775461742,
|
|
"loss": 6.579,
|
|
"mean_token_accuracy": 0.12949036434292793,
|
|
"num_tokens": 5451863.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 6.697029161453247,
|
|
"epoch": 0.2784025591043135,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996397595416173,
|
|
"loss": 6.6365,
|
|
"mean_token_accuracy": 0.12379389107227326,
|
|
"num_tokens": 5461600.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 6.774936103820801,
|
|
"epoch": 0.2789023841655421,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996377379696143,
|
|
"loss": 6.6492,
|
|
"mean_token_accuracy": 0.12262091562151908,
|
|
"num_tokens": 5470097.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 6.73469181060791,
|
|
"epoch": 0.2794022092267706,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996357107457834,
|
|
"loss": 6.814,
|
|
"mean_token_accuracy": 0.11655468791723252,
|
|
"num_tokens": 5480906.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 6.808956336975098,
|
|
"epoch": 0.2799020342879992,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000499633677870176,
|
|
"loss": 6.6844,
|
|
"mean_token_accuracy": 0.12597069665789604,
|
|
"num_tokens": 5489732.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 6.528180980682373,
|
|
"epoch": 0.2804018593492278,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004996316393428429,
|
|
"loss": 6.4803,
|
|
"mean_token_accuracy": 0.13605385273694992,
|
|
"num_tokens": 5498422.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 6.613443279266358,
|
|
"epoch": 0.2809016844104563,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004996295951638357,
|
|
"loss": 6.6409,
|
|
"mean_token_accuracy": 0.12768530771136283,
|
|
"num_tokens": 5507958.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 6.775778770446777,
|
|
"epoch": 0.2814015094716849,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004996275453332057,
|
|
"loss": 6.6654,
|
|
"mean_token_accuracy": 0.1298332244157791,
|
|
"num_tokens": 5516752.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 6.648133945465088,
|
|
"epoch": 0.2819013345329135,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004996254898510043,
|
|
"loss": 6.6731,
|
|
"mean_token_accuracy": 0.12450689151883125,
|
|
"num_tokens": 5527211.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 6.654214859008789,
|
|
"epoch": 0.282401159594142,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004996234287172835,
|
|
"loss": 6.5656,
|
|
"mean_token_accuracy": 0.12709278836846352,
|
|
"num_tokens": 5536925.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 6.69185094833374,
|
|
"epoch": 0.2829009846553706,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000499621361932095,
|
|
"loss": 6.7517,
|
|
"mean_token_accuracy": 0.12027538269758224,
|
|
"num_tokens": 5546800.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 6.633594799041748,
|
|
"epoch": 0.2834008097165992,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004996192894954909,
|
|
"loss": 6.5781,
|
|
"mean_token_accuracy": 0.12837735265493394,
|
|
"num_tokens": 5557266.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 6.729125261306763,
|
|
"epoch": 0.2839006347778278,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004996172114075232,
|
|
"loss": 6.5663,
|
|
"mean_token_accuracy": 0.12667735964059829,
|
|
"num_tokens": 5566169.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 6.662754964828491,
|
|
"epoch": 0.2844004598390563,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004996151276682443,
|
|
"loss": 6.6598,
|
|
"mean_token_accuracy": 0.12701473608613015,
|
|
"num_tokens": 5575566.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 6.615578985214233,
|
|
"epoch": 0.2849002849002849,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996130382777065,
|
|
"loss": 6.546,
|
|
"mean_token_accuracy": 0.13053665533661843,
|
|
"num_tokens": 5584804.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 6.638299226760864,
|
|
"epoch": 0.2854001099615135,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004996109432359625,
|
|
"loss": 6.6009,
|
|
"mean_token_accuracy": 0.1265592433512211,
|
|
"num_tokens": 5594361.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 6.683030986785889,
|
|
"epoch": 0.285899935022742,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004996088425430651,
|
|
"loss": 6.6219,
|
|
"mean_token_accuracy": 0.12339444905519485,
|
|
"num_tokens": 5605682.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 6.641170263290405,
|
|
"epoch": 0.2863997600839706,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996067361990669,
|
|
"loss": 6.6897,
|
|
"mean_token_accuracy": 0.12035760283470154,
|
|
"num_tokens": 5617251.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 6.7068572521209715,
|
|
"epoch": 0.2868995851451992,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004996046242040209,
|
|
"loss": 6.5628,
|
|
"mean_token_accuracy": 0.12945612370967866,
|
|
"num_tokens": 5627140.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 6.550381660461426,
|
|
"epoch": 0.28739941020642773,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004996025065579805,
|
|
"loss": 6.485,
|
|
"mean_token_accuracy": 0.13200978338718414,
|
|
"num_tokens": 5635486.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 6.645271348953247,
|
|
"epoch": 0.2878992352676563,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996003832609988,
|
|
"loss": 6.675,
|
|
"mean_token_accuracy": 0.1206593632698059,
|
|
"num_tokens": 5645621.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 6.811749696731567,
|
|
"epoch": 0.2883990603288849,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004995982543131292,
|
|
"loss": 6.7572,
|
|
"mean_token_accuracy": 0.11400788351893425,
|
|
"num_tokens": 5655626.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 6.684689092636108,
|
|
"epoch": 0.28889888539011344,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004995961197144254,
|
|
"loss": 6.6776,
|
|
"mean_token_accuracy": 0.12474105134606361,
|
|
"num_tokens": 5664547.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 6.67263617515564,
|
|
"epoch": 0.289398710451342,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499593979464941,
|
|
"loss": 6.6308,
|
|
"mean_token_accuracy": 0.12696049585938454,
|
|
"num_tokens": 5674861.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 6.643967628479004,
|
|
"epoch": 0.2898985355125706,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004995918335647298,
|
|
"loss": 6.5706,
|
|
"mean_token_accuracy": 0.1286863476037979,
|
|
"num_tokens": 5684143.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 6.593589925765992,
|
|
"epoch": 0.2903983605737992,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004995896820138459,
|
|
"loss": 6.5715,
|
|
"mean_token_accuracy": 0.12647168189287186,
|
|
"num_tokens": 5693837.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 6.714412641525269,
|
|
"epoch": 0.29089818563502773,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004995875248123434,
|
|
"loss": 6.6512,
|
|
"mean_token_accuracy": 0.11919039636850357,
|
|
"num_tokens": 5704827.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 6.721566820144654,
|
|
"epoch": 0.2913980106962563,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004995853619602766,
|
|
"loss": 6.6848,
|
|
"mean_token_accuracy": 0.12311125099658966,
|
|
"num_tokens": 5714419.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 6.657805967330932,
|
|
"epoch": 0.2918978357574849,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004995831934576998,
|
|
"loss": 6.6042,
|
|
"mean_token_accuracy": 0.12744421064853667,
|
|
"num_tokens": 5724983.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 6.611767673492432,
|
|
"epoch": 0.29239766081871343,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004995810193046677,
|
|
"loss": 6.5242,
|
|
"mean_token_accuracy": 0.13742104694247245,
|
|
"num_tokens": 5734471.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 6.707096099853516,
|
|
"epoch": 0.292897485879942,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499578839501235,
|
|
"loss": 6.6545,
|
|
"mean_token_accuracy": 0.12848085910081863,
|
|
"num_tokens": 5744801.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 6.626270914077759,
|
|
"epoch": 0.2933973109411706,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004995766540474564,
|
|
"loss": 6.6228,
|
|
"mean_token_accuracy": 0.12304180413484574,
|
|
"num_tokens": 5754267.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 6.61904239654541,
|
|
"epoch": 0.29389713600239914,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000499574462943387,
|
|
"loss": 6.5306,
|
|
"mean_token_accuracy": 0.13505666479468345,
|
|
"num_tokens": 5764466.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 6.673902082443237,
|
|
"epoch": 0.2943969610636277,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000499572266189082,
|
|
"loss": 6.6548,
|
|
"mean_token_accuracy": 0.12099963128566742,
|
|
"num_tokens": 5775158.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 6.636359071731567,
|
|
"epoch": 0.2948967861248563,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004995700637845964,
|
|
"loss": 6.4623,
|
|
"mean_token_accuracy": 0.13724422752857207,
|
|
"num_tokens": 5783320.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 6.554117107391358,
|
|
"epoch": 0.29539661118608485,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004995678557299859,
|
|
"loss": 6.6023,
|
|
"mean_token_accuracy": 0.1300165981054306,
|
|
"num_tokens": 5792980.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 6.71733250617981,
|
|
"epoch": 0.29589643624731343,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004995656420253058,
|
|
"loss": 6.6511,
|
|
"mean_token_accuracy": 0.12479741126298904,
|
|
"num_tokens": 5802338.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 6.630457496643066,
|
|
"epoch": 0.296396261308542,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000499563422670612,
|
|
"loss": 6.554,
|
|
"mean_token_accuracy": 0.12994145452976227,
|
|
"num_tokens": 5811388.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 6.584511566162109,
|
|
"epoch": 0.2968960863697706,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004995611976659604,
|
|
"loss": 6.5898,
|
|
"mean_token_accuracy": 0.127712956815958,
|
|
"num_tokens": 5821108.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 6.6266556739807125,
|
|
"epoch": 0.29739591143099914,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004995589670114067,
|
|
"loss": 6.6609,
|
|
"mean_token_accuracy": 0.11711250171065331,
|
|
"num_tokens": 5831389.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 6.604189395904541,
|
|
"epoch": 0.2978957364922277,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004995567307070072,
|
|
"loss": 6.4889,
|
|
"mean_token_accuracy": 0.13330937549471855,
|
|
"num_tokens": 5840392.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 6.632587146759033,
|
|
"epoch": 0.2983955615534563,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004995544887528182,
|
|
"loss": 6.5082,
|
|
"mean_token_accuracy": 0.13582244664430618,
|
|
"num_tokens": 5850032.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 6.613868570327758,
|
|
"epoch": 0.29889538661468484,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004995522411488959,
|
|
"loss": 6.574,
|
|
"mean_token_accuracy": 0.12751223295927047,
|
|
"num_tokens": 5859204.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 6.610184240341186,
|
|
"epoch": 0.29939521167591343,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004995499878952971,
|
|
"loss": 6.588,
|
|
"mean_token_accuracy": 0.13020774498581886,
|
|
"num_tokens": 5868582.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 6.630722141265869,
|
|
"epoch": 0.299895036737142,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004995477289920784,
|
|
"loss": 6.5448,
|
|
"mean_token_accuracy": 0.12928271293640137,
|
|
"num_tokens": 5879601.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.299895036737142,
|
|
"eval_entropy": 6.478444874947049,
|
|
"eval_loss": 6.631077289581299,
|
|
"eval_mean_token_accuracy": 0.13178826568691893,
|
|
"eval_num_tokens": 5879601.0,
|
|
"eval_runtime": 23.8125,
|
|
"eval_samples_per_second": 1303.725,
|
|
"eval_steps_per_second": 162.981,
|
|
"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": 9383935887360000.0,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|